diff options
Diffstat (limited to 'net')
157 files changed, 2455 insertions, 1601 deletions
diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c index bc25286..2b5fcde 100644 --- a/net/8021q/vlan_dev.c +++ b/net/8021q/vlan_dev.c @@ -591,18 +591,17 @@ static void vlan_dev_uninit(struct net_device *dev) } } -static u32 vlan_dev_fix_features(struct net_device *dev, u32 features) +static netdev_features_t vlan_dev_fix_features(struct net_device *dev, + netdev_features_t features) { struct net_device *real_dev = vlan_dev_info(dev)->real_dev; u32 old_features = features; - features &= real_dev->features; features &= real_dev->vlan_features; + features |= NETIF_F_RXCSUM; + features &= real_dev->features; features |= old_features & NETIF_F_SOFT_FEATURES; - - if (dev_ethtool_get_rx_csum(real_dev)) - features |= NETIF_F_RXCSUM; features |= NETIF_F_LLTX; return features; diff --git a/net/Kconfig b/net/Kconfig index a073148..63d2c5d 100644 --- a/net/Kconfig +++ b/net/Kconfig @@ -232,6 +232,13 @@ config XPS depends on SMP && SYSFS && USE_GENERIC_SMP_HELPERS default y +config NETPRIO_CGROUP + tristate "Network priority cgroup" + depends on CGROUPS + ---help--- + Cgroup subsystem for use in assigning processes to network priorities on + a per-interface basis + config HAVE_BPF_JIT bool diff --git a/net/atm/atm_misc.c b/net/atm/atm_misc.c index f41f026..876fbe8 100644 --- a/net/atm/atm_misc.c +++ b/net/atm/atm_misc.c @@ -26,7 +26,7 @@ struct sk_buff *atm_alloc_charge(struct atm_vcc *vcc, int pdu_size, gfp_t gfp_flags) { struct sock *sk = sk_atm(vcc); - int guess = atm_guess_pdu2truesize(pdu_size); + int guess = SKB_TRUESIZE(pdu_size); atm_force_charge(vcc, guess); if (atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf) { diff --git a/net/atm/br2684.c b/net/atm/br2684.c index d07223c..53b0aa1 100644 --- a/net/atm/br2684.c +++ b/net/atm/br2684.c @@ -489,15 +489,11 @@ free_skb: */ static int br2684_regvcc(struct atm_vcc *atmvcc, void __user * arg) { - struct sk_buff_head queue; - int err; struct br2684_vcc *brvcc; - struct sk_buff *skb, *tmp; - struct sk_buff_head *rq; struct br2684_dev *brdev; struct net_device *net_dev; struct atm_backend_br2684 be; - unsigned long flags; + int err; if (copy_from_user(&be, arg, sizeof be)) return -EFAULT; @@ -550,23 +546,6 @@ static int br2684_regvcc(struct atm_vcc *atmvcc, void __user * arg) atmvcc->push = br2684_push; atmvcc->pop = br2684_pop; - __skb_queue_head_init(&queue); - rq = &sk_atm(atmvcc)->sk_receive_queue; - - spin_lock_irqsave(&rq->lock, flags); - skb_queue_splice_init(rq, &queue); - spin_unlock_irqrestore(&rq->lock, flags); - - skb_queue_walk_safe(&queue, skb, tmp) { - struct net_device *dev; - - br2684_push(atmvcc, skb); - dev = skb->dev; - - dev->stats.rx_bytes -= skb->len; - dev->stats.rx_packets--; - } - /* initialize netdev carrier state */ if (atmvcc->dev->signal == ATM_PHY_SIG_LOST) netif_carrier_off(net_dev); @@ -574,6 +553,10 @@ static int br2684_regvcc(struct atm_vcc *atmvcc, void __user * arg) netif_carrier_on(net_dev); __module_get(THIS_MODULE); + + /* re-process everything received between connection setup and + backend setup */ + vcc_process_recv_queue(atmvcc); return 0; error: diff --git a/net/atm/clip.c b/net/atm/clip.c index 8523940..11439a7 100644 --- a/net/atm/clip.c +++ b/net/atm/clip.c @@ -189,6 +189,13 @@ static void clip_push(struct atm_vcc *vcc, struct sk_buff *skb) struct clip_vcc *clip_vcc = CLIP_VCC(vcc); pr_debug("\n"); + + if (!clip_devs) { + atm_return(vcc, skb->truesize); + kfree_skb(skb); + return; + } + if (!skb) { pr_debug("removing VCC %p\n", clip_vcc); if (clip_vcc->entry) @@ -329,7 +336,7 @@ static struct neigh_table clip_tbl = { .gc_staletime = 60 * HZ, .reachable_time = 30 * HZ, .delay_probe_time = 5 * HZ, - .queue_len = 3, + .queue_len_bytes = 64 * 1024, .ucast_probes = 3, .mcast_probes = 3, .anycast_delay = 1 * HZ, @@ -448,10 +455,7 @@ static netdev_tx_t clip_start_xmit(struct sk_buff *skb, static int clip_mkip(struct atm_vcc *vcc, int timeout) { - struct sk_buff_head *rq, queue; struct clip_vcc *clip_vcc; - struct sk_buff *skb, *tmp; - unsigned long flags; if (!vcc->push) return -EBADFD; @@ -472,29 +476,9 @@ static int clip_mkip(struct atm_vcc *vcc, int timeout) vcc->push = clip_push; vcc->pop = clip_pop; - __skb_queue_head_init(&queue); - rq = &sk_atm(vcc)->sk_receive_queue; - - spin_lock_irqsave(&rq->lock, flags); - skb_queue_splice_init(rq, &queue); - spin_unlock_irqrestore(&rq->lock, flags); - /* re-process everything received between connection setup and MKIP */ - skb_queue_walk_safe(&queue, skb, tmp) { - if (!clip_devs) { - atm_return(vcc, skb->truesize); - kfree_skb(skb); - } else { - struct net_device *dev = skb->dev; - unsigned int len = skb->len; - - skb_get(skb); - clip_push(vcc, skb); - dev->stats.rx_packets--; - dev->stats.rx_bytes -= len; - kfree_skb(skb); - } - } + vcc_process_recv_queue(vcc); + return 0; } diff --git a/net/atm/common.c b/net/atm/common.c index 14ff9fe..b4b44db 100644 --- a/net/atm/common.c +++ b/net/atm/common.c @@ -214,6 +214,26 @@ void vcc_release_async(struct atm_vcc *vcc, int reply) } EXPORT_SYMBOL(vcc_release_async); +void vcc_process_recv_queue(struct atm_vcc *vcc) +{ + struct sk_buff_head queue, *rq; + struct sk_buff *skb, *tmp; + unsigned long flags; + + __skb_queue_head_init(&queue); + rq = &sk_atm(vcc)->sk_receive_queue; + + spin_lock_irqsave(&rq->lock, flags); + skb_queue_splice_init(rq, &queue); + spin_unlock_irqrestore(&rq->lock, flags); + + skb_queue_walk_safe(&queue, skb, tmp) { + __skb_unlink(skb, &queue); + vcc->push(vcc, skb); + } +} +EXPORT_SYMBOL(vcc_process_recv_queue); + void atm_dev_signal_change(struct atm_dev *dev, char signal) { pr_debug("%s signal=%d dev=%p number=%d dev->signal=%d\n", @@ -502,8 +522,11 @@ int vcc_recvmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg, if (sock->state != SS_CONNECTED) return -ENOTCONN; - if (flags & ~MSG_DONTWAIT) /* only handle MSG_DONTWAIT */ + + /* only handle MSG_DONTWAIT and MSG_PEEK */ + if (flags & ~(MSG_DONTWAIT | MSG_PEEK)) return -EOPNOTSUPP; + vcc = ATM_SD(sock); if (test_bit(ATM_VF_RELEASED, &vcc->flags) || test_bit(ATM_VF_CLOSE, &vcc->flags) || @@ -524,8 +547,13 @@ int vcc_recvmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg, if (error) return error; sock_recv_ts_and_drops(msg, sk, skb); - pr_debug("%d -= %d\n", atomic_read(&sk->sk_rmem_alloc), skb->truesize); - atm_return(vcc, skb->truesize); + + if (!(flags & MSG_PEEK)) { + pr_debug("%d -= %d\n", atomic_read(&sk->sk_rmem_alloc), + skb->truesize); + atm_return(vcc, skb->truesize); + } + skb_free_datagram(sk, skb); return copied; } diff --git a/net/atm/common.h b/net/atm/common.h index f48a76b..cc3c2da 100644 --- a/net/atm/common.h +++ b/net/atm/common.h @@ -24,6 +24,7 @@ int vcc_setsockopt(struct socket *sock, int level, int optname, char __user *optval, unsigned int optlen); int vcc_getsockopt(struct socket *sock, int level, int optname, char __user *optval, int __user *optlen); +void vcc_process_recv_queue(struct atm_vcc *vcc); int atmpvc_init(void); void atmpvc_exit(void); diff --git a/net/atm/pppoatm.c b/net/atm/pppoatm.c index db4a11c..df35d9a 100644 --- a/net/atm/pppoatm.c +++ b/net/atm/pppoatm.c @@ -303,6 +303,10 @@ static int pppoatm_assign_vcc(struct atm_vcc *atmvcc, void __user *arg) atmvcc->push = pppoatm_push; atmvcc->pop = pppoatm_pop; __module_get(THIS_MODULE); + + /* re-process everything received between connection setup and + backend setup */ + vcc_process_recv_queue(atmvcc); return 0; } diff --git a/net/batman-adv/bat_sysfs.c b/net/batman-adv/bat_sysfs.c index b8a7414..c25492f 100644 --- a/net/batman-adv/bat_sysfs.c +++ b/net/batman-adv/bat_sysfs.c @@ -174,7 +174,7 @@ static int store_uint_attr(const char *buff, size_t count, unsigned long uint_val; int ret; - ret = strict_strtoul(buff, 10, &uint_val); + ret = kstrtoul(buff, 10, &uint_val); if (ret) { bat_info(net_dev, "%s: Invalid parameter received: %s\n", @@ -239,7 +239,7 @@ static ssize_t store_vis_mode(struct kobject *kobj, struct attribute *attr, unsigned long val; int ret, vis_mode_tmp = -1; - ret = strict_strtoul(buff, 10, &val); + ret = kstrtoul(buff, 10, &val); if (((count == 2) && (!ret) && (val == VIS_TYPE_CLIENT_UPDATE)) || (strncmp(buff, "client", 6) == 0) || diff --git a/net/batman-adv/bitarray.c b/net/batman-adv/bitarray.c index 0be9ff3..9bc63b2 100644 --- a/net/batman-adv/bitarray.c +++ b/net/batman-adv/bitarray.c @@ -155,7 +155,7 @@ int bit_get_packet(void *priv, unsigned long *seq_bits, /* sequence number is much newer, probably missed a lot of packets */ if ((seq_num_diff >= TQ_LOCAL_WINDOW_SIZE) - || (seq_num_diff < EXPECTED_SEQNO_RANGE)) { + && (seq_num_diff < EXPECTED_SEQNO_RANGE)) { bat_dbg(DBG_BATMAN, bat_priv, "We missed a lot of packets (%i) !\n", seq_num_diff - 1); diff --git a/net/batman-adv/gateway_client.c b/net/batman-adv/gateway_client.c index 619fb73..9373a14 100644 --- a/net/batman-adv/gateway_client.c +++ b/net/batman-adv/gateway_client.c @@ -25,6 +25,7 @@ #include "gateway_common.h" #include "hard-interface.h" #include "originator.h" +#include "translation-table.h" #include "routing.h" #include <linux/ip.h> #include <linux/ipv6.h> @@ -572,108 +573,142 @@ out: return ret; } -int gw_is_target(struct bat_priv *bat_priv, struct sk_buff *skb, - struct orig_node *old_gw) +bool gw_is_dhcp_target(struct sk_buff *skb, unsigned int *header_len) { struct ethhdr *ethhdr; struct iphdr *iphdr; struct ipv6hdr *ipv6hdr; struct udphdr *udphdr; - struct gw_node *curr_gw; - struct neigh_node *neigh_curr = NULL, *neigh_old = NULL; - unsigned int header_len = 0; - int ret = 1; - - if (atomic_read(&bat_priv->gw_mode) == GW_MODE_OFF) - return 0; /* check for ethernet header */ - if (!pskb_may_pull(skb, header_len + ETH_HLEN)) - return 0; + if (!pskb_may_pull(skb, *header_len + ETH_HLEN)) + return false; ethhdr = (struct ethhdr *)skb->data; - header_len += ETH_HLEN; + *header_len += ETH_HLEN; /* check for initial vlan header */ if (ntohs(ethhdr->h_proto) == ETH_P_8021Q) { - if (!pskb_may_pull(skb, header_len + VLAN_HLEN)) - return 0; + if (!pskb_may_pull(skb, *header_len + VLAN_HLEN)) + return false; ethhdr = (struct ethhdr *)(skb->data + VLAN_HLEN); - header_len += VLAN_HLEN; + *header_len += VLAN_HLEN; } /* check for ip header */ switch (ntohs(ethhdr->h_proto)) { case ETH_P_IP: - if (!pskb_may_pull(skb, header_len + sizeof(*iphdr))) - return 0; - iphdr = (struct iphdr *)(skb->data + header_len); - header_len += iphdr->ihl * 4; + if (!pskb_may_pull(skb, *header_len + sizeof(*iphdr))) + return false; + iphdr = (struct iphdr *)(skb->data + *header_len); + *header_len += iphdr->ihl * 4; /* check for udp header */ if (iphdr->protocol != IPPROTO_UDP) - return 0; + return false; break; case ETH_P_IPV6: - if (!pskb_may_pull(skb, header_len + sizeof(*ipv6hdr))) - return 0; - ipv6hdr = (struct ipv6hdr *)(skb->data + header_len); - header_len += sizeof(*ipv6hdr); + if (!pskb_may_pull(skb, *header_len + sizeof(*ipv6hdr))) + return false; + ipv6hdr = (struct ipv6hdr *)(skb->data + *header_len); + *header_len += sizeof(*ipv6hdr); /* check for udp header */ if (ipv6hdr->nexthdr != IPPROTO_UDP) - return 0; + return false; break; default: - return 0; + return false; } - if (!pskb_may_pull(skb, header_len + sizeof(*udphdr))) - return 0; - udphdr = (struct udphdr *)(skb->data + header_len); - header_len += sizeof(*udphdr); + if (!pskb_may_pull(skb, *header_len + sizeof(*udphdr))) + return false; + udphdr = (struct udphdr *)(skb->data + *header_len); + *header_len += sizeof(*udphdr); /* check for bootp port */ if ((ntohs(ethhdr->h_proto) == ETH_P_IP) && (ntohs(udphdr->dest) != 67)) - return 0; + return false; if ((ntohs(ethhdr->h_proto) == ETH_P_IPV6) && (ntohs(udphdr->dest) != 547)) - return 0; + return false; - if (atomic_read(&bat_priv->gw_mode) == GW_MODE_SERVER) - return -1; + return true; +} - curr_gw = gw_get_selected_gw_node(bat_priv); - if (!curr_gw) - return 0; - - /* If old_gw != NULL then this packet is unicast. - * So, at this point we have to check the message type: if it is a - * DHCPREQUEST we have to decide whether to drop it or not */ - if (old_gw && curr_gw->orig_node != old_gw) { - if (is_type_dhcprequest(skb, header_len)) { - /* If the dhcp packet has been sent to a different gw, - * we have to evaluate whether the old gw is still - * reliable enough */ - neigh_curr = find_router(bat_priv, curr_gw->orig_node, - NULL); - neigh_old = find_router(bat_priv, old_gw, NULL); - if (!neigh_curr || !neigh_old) - goto free_neigh; - if (neigh_curr->tq_avg - neigh_old->tq_avg < - GW_THRESHOLD) - ret = -1; - } +bool gw_out_of_range(struct bat_priv *bat_priv, + struct sk_buff *skb, struct ethhdr *ethhdr) +{ + struct neigh_node *neigh_curr = NULL, *neigh_old = NULL; + struct orig_node *orig_dst_node = NULL; + struct gw_node *curr_gw = NULL; + bool ret, out_of_range = false; + unsigned int header_len = 0; + uint8_t curr_tq_avg; + + ret = gw_is_dhcp_target(skb, &header_len); + if (!ret) + goto out; + + orig_dst_node = transtable_search(bat_priv, ethhdr->h_source, + ethhdr->h_dest); + if (!orig_dst_node) + goto out; + + if (!orig_dst_node->gw_flags) + goto out; + + ret = is_type_dhcprequest(skb, header_len); + if (!ret) + goto out; + + switch (atomic_read(&bat_priv->gw_mode)) { + case GW_MODE_SERVER: + /* If we are a GW then we are our best GW. We can artificially + * set the tq towards ourself as the maximum value */ + curr_tq_avg = TQ_MAX_VALUE; + break; + case GW_MODE_CLIENT: + curr_gw = gw_get_selected_gw_node(bat_priv); + if (!curr_gw) + goto out; + + /* packet is going to our gateway */ + if (curr_gw->orig_node == orig_dst_node) + goto out; + + /* If the dhcp packet has been sent to a different gw, + * we have to evaluate whether the old gw is still + * reliable enough */ + neigh_curr = find_router(bat_priv, curr_gw->orig_node, NULL); + if (!neigh_curr) + goto out; + + curr_tq_avg = neigh_curr->tq_avg; + break; + case GW_MODE_OFF: + default: + goto out; } -free_neigh: + + neigh_old = find_router(bat_priv, orig_dst_node, NULL); + if (!!neigh_old) + goto out; + + if (curr_tq_avg - neigh_old->tq_avg > GW_THRESHOLD) + out_of_range = true; + +out: + if (orig_dst_node) + orig_node_free_ref(orig_dst_node); + if (curr_gw) + gw_node_free_ref(curr_gw); if (neigh_old) neigh_node_free_ref(neigh_old); if (neigh_curr) neigh_node_free_ref(neigh_curr); - if (curr_gw) - gw_node_free_ref(curr_gw); - return ret; + return out_of_range; } diff --git a/net/batman-adv/gateway_client.h b/net/batman-adv/gateway_client.h index b9b983c..e1edba0 100644 --- a/net/batman-adv/gateway_client.h +++ b/net/batman-adv/gateway_client.h @@ -31,7 +31,8 @@ void gw_node_update(struct bat_priv *bat_priv, void gw_node_delete(struct bat_priv *bat_priv, struct orig_node *orig_node); void gw_node_purge(struct bat_priv *bat_priv); int gw_client_seq_print_text(struct seq_file *seq, void *offset); -int gw_is_target(struct bat_priv *bat_priv, struct sk_buff *skb, - struct orig_node *old_gw); +bool gw_is_dhcp_target(struct sk_buff *skb, unsigned int *header_len); +bool gw_out_of_range(struct bat_priv *bat_priv, + struct sk_buff *skb, struct ethhdr *ethhdr); #endif /* _NET_BATMAN_ADV_GATEWAY_CLIENT_H_ */ diff --git a/net/batman-adv/gateway_common.c b/net/batman-adv/gateway_common.c index 18661af..c4ac7b0 100644 --- a/net/batman-adv/gateway_common.c +++ b/net/batman-adv/gateway_common.c @@ -97,7 +97,7 @@ static bool parse_gw_bandwidth(struct net_device *net_dev, char *buff, *tmp_ptr = '\0'; } - ret = strict_strtol(buff, 10, &ldown); + ret = kstrtol(buff, 10, &ldown); if (ret) { bat_err(net_dev, "Download speed of gateway mode invalid: %s\n", @@ -122,7 +122,7 @@ static bool parse_gw_bandwidth(struct net_device *net_dev, char *buff, *tmp_ptr = '\0'; } - ret = strict_strtol(slash_ptr + 1, 10, &lup); + ret = kstrtol(slash_ptr + 1, 10, &lup); if (ret) { bat_err(net_dev, "Upload speed of gateway mode invalid: " diff --git a/net/batman-adv/hash.c b/net/batman-adv/hash.c index 2a17250..d1da29d 100644 --- a/net/batman-adv/hash.c +++ b/net/batman-adv/hash.c @@ -25,7 +25,7 @@ /* clears the hash */ static void hash_init(struct hashtable_t *hash) { - int i; + uint32_t i; for (i = 0 ; i < hash->size; i++) { INIT_HLIST_HEAD(&hash->table[i]); @@ -42,7 +42,7 @@ void hash_destroy(struct hashtable_t *hash) } /* allocates and clears the hash */ -struct hashtable_t *hash_new(int size) +struct hashtable_t *hash_new(uint32_t size) { struct hashtable_t *hash; diff --git a/net/batman-adv/hash.h b/net/batman-adv/hash.h index d20aa71..4768717 100644 --- a/net/batman-adv/hash.h +++ b/net/batman-adv/hash.h @@ -33,17 +33,17 @@ typedef int (*hashdata_compare_cb)(const struct hlist_node *, const void *); /* the hashfunction, should return an index * based on the key in the data of the first * argument and the size the second */ -typedef int (*hashdata_choose_cb)(const void *, int); +typedef uint32_t (*hashdata_choose_cb)(const void *, uint32_t); typedef void (*hashdata_free_cb)(struct hlist_node *, void *); struct hashtable_t { struct hlist_head *table; /* the hashtable itself with the buckets */ spinlock_t *list_locks; /* spinlock for each hash list entry */ - int size; /* size of hashtable */ + uint32_t size; /* size of hashtable */ }; /* allocates and clears the hash */ -struct hashtable_t *hash_new(int size); +struct hashtable_t *hash_new(uint32_t size); /* free only the hashtable and the hash itself. */ void hash_destroy(struct hashtable_t *hash); @@ -57,7 +57,7 @@ static inline void hash_delete(struct hashtable_t *hash, struct hlist_head *head; struct hlist_node *node, *node_tmp; spinlock_t *list_lock; /* spinlock to protect write access */ - int i; + uint32_t i; for (i = 0; i < hash->size; i++) { head = &hash->table[i]; @@ -93,7 +93,8 @@ static inline int hash_add(struct hashtable_t *hash, hashdata_choose_cb choose, const void *data, struct hlist_node *data_node) { - int index, ret = -1; + uint32_t index; + int ret = -1; struct hlist_head *head; struct hlist_node *node; spinlock_t *list_lock; /* spinlock to protect write access */ @@ -137,7 +138,7 @@ static inline void *hash_remove(struct hashtable_t *hash, hashdata_compare_cb compare, hashdata_choose_cb choose, void *data) { - size_t index; + uint32_t index; struct hlist_node *node; struct hlist_head *head; void *data_save = NULL; diff --git a/net/batman-adv/main.h b/net/batman-adv/main.h index 964ad4d..86354e0 100644 --- a/net/batman-adv/main.h +++ b/net/batman-adv/main.h @@ -28,7 +28,7 @@ #define DRIVER_DEVICE "batman-adv" #ifndef SOURCE_VERSION -#define SOURCE_VERSION "2011.4.0" +#define SOURCE_VERSION "2012.0.0" #endif /* B.A.T.M.A.N. parameters */ diff --git a/net/batman-adv/originator.c b/net/batman-adv/originator.c index 0e5b772..0bc2045 100644 --- a/net/batman-adv/originator.c +++ b/net/batman-adv/originator.c @@ -164,7 +164,7 @@ void originator_free(struct bat_priv *bat_priv) struct hlist_head *head; spinlock_t *list_lock; /* spinlock to protect write access */ struct orig_node *orig_node; - int i; + uint32_t i; if (!hash) return; @@ -350,7 +350,7 @@ static void _purge_orig(struct bat_priv *bat_priv) struct hlist_head *head; spinlock_t *list_lock; /* spinlock to protect write access */ struct orig_node *orig_node; - int i; + uint32_t i; if (!hash) return; @@ -413,7 +413,8 @@ int orig_seq_print_text(struct seq_file *seq, void *offset) int batman_count = 0; int last_seen_secs; int last_seen_msecs; - int i, ret = 0; + uint32_t i; + int ret = 0; primary_if = primary_if_get_selected(bat_priv); @@ -519,7 +520,8 @@ int orig_hash_add_if(struct hard_iface *hard_iface, int max_if_num) struct hlist_node *node; struct hlist_head *head; struct orig_node *orig_node; - int i, ret; + uint32_t i; + int ret; /* resize all orig nodes because orig_node->bcast_own(_sum) depend on * if_num */ @@ -601,7 +603,8 @@ int orig_hash_del_if(struct hard_iface *hard_iface, int max_if_num) struct hlist_head *head; struct hard_iface *hard_iface_tmp; struct orig_node *orig_node; - int i, ret; + uint32_t i; + int ret; /* resize all orig nodes because orig_node->bcast_own(_sum) depend on * if_num */ diff --git a/net/batman-adv/originator.h b/net/batman-adv/originator.h index cfc1f60..67765ff 100644 --- a/net/batman-adv/originator.h +++ b/net/batman-adv/originator.h @@ -42,7 +42,7 @@ int orig_hash_del_if(struct hard_iface *hard_iface, int max_if_num); /* hashfunction to choose an entry in a hash table of given size */ /* hash algorithm from http://en.wikipedia.org/wiki/Hash_table */ -static inline int choose_orig(const void *data, int32_t size) +static inline uint32_t choose_orig(const void *data, uint32_t size) { const unsigned char *key = data; uint32_t hash = 0; diff --git a/net/batman-adv/routing.c b/net/batman-adv/routing.c index f961cc5..ef24a72 100644 --- a/net/batman-adv/routing.c +++ b/net/batman-adv/routing.c @@ -39,7 +39,7 @@ void slide_own_bcast_window(struct hard_iface *hard_iface) struct hlist_head *head; struct orig_node *orig_node; unsigned long *word; - int i; + uint32_t i; size_t word_index; for (i = 0; i < hash->size; i++) { @@ -578,6 +578,7 @@ int recv_tt_query(struct sk_buff *skb, struct hard_iface *recv_if) { struct bat_priv *bat_priv = netdev_priv(recv_if->soft_iface); struct tt_query_packet *tt_query; + uint16_t tt_len; struct ethhdr *ethhdr; /* drop packet if it has not necessary minimum size */ @@ -616,13 +617,22 @@ int recv_tt_query(struct sk_buff *skb, struct hard_iface *recv_if) } break; case TT_RESPONSE: - /* packet needs to be linearized to access the TT changes */ - if (skb_linearize(skb) < 0) - goto out; + if (is_my_mac(tt_query->dst)) { + /* packet needs to be linearized to access the TT + * changes */ + if (skb_linearize(skb) < 0) + goto out; + + tt_len = tt_query->tt_data * sizeof(struct tt_change); + + /* Ensure we have all the claimed data */ + if (unlikely(skb_headlen(skb) < + sizeof(struct tt_query_packet) + + tt_len)) + goto out; - if (is_my_mac(tt_query->dst)) handle_tt_response(bat_priv, tt_query); - else { + } else { bat_dbg(DBG_TT, bat_priv, "Routing TT_RESPONSE to %pM [%c]\n", tt_query->dst, diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c index f9cc957..45297c8 100644 --- a/net/batman-adv/soft-interface.c +++ b/net/batman-adv/soft-interface.c @@ -563,10 +563,10 @@ static int interface_tx(struct sk_buff *skb, struct net_device *soft_iface) struct bcast_packet *bcast_packet; struct vlan_ethhdr *vhdr; struct softif_neigh *curr_softif_neigh = NULL; - struct orig_node *orig_node = NULL; + unsigned int header_len = 0; int data_len = skb->len, ret; short vid = -1; - bool do_bcast; + bool do_bcast = false; if (atomic_read(&bat_priv->mesh_state) != MESH_ACTIVE) goto dropped; @@ -598,17 +598,28 @@ static int interface_tx(struct sk_buff *skb, struct net_device *soft_iface) /* Register the client MAC in the transtable */ tt_local_add(soft_iface, ethhdr->h_source, skb->skb_iif); - orig_node = transtable_search(bat_priv, ethhdr->h_source, - ethhdr->h_dest); - do_bcast = is_multicast_ether_addr(ethhdr->h_dest); - if (do_bcast || (orig_node && orig_node->gw_flags)) { - ret = gw_is_target(bat_priv, skb, orig_node); + if (is_multicast_ether_addr(ethhdr->h_dest)) { + do_bcast = true; - if (ret < 0) - goto dropped; - - if (ret) - do_bcast = false; + switch (atomic_read(&bat_priv->gw_mode)) { + case GW_MODE_SERVER: + /* gateway servers should not send dhcp + * requests into the mesh */ + ret = gw_is_dhcp_target(skb, &header_len); + if (ret) + goto dropped; + break; + case GW_MODE_CLIENT: + /* gateway clients should send dhcp requests + * via unicast to their gateway */ + ret = gw_is_dhcp_target(skb, &header_len); + if (ret) + do_bcast = false; + break; + case GW_MODE_OFF: + default: + break; + } } /* ethernet packet should be broadcasted */ @@ -644,6 +655,12 @@ static int interface_tx(struct sk_buff *skb, struct net_device *soft_iface) /* unicast packet */ } else { + if (atomic_read(&bat_priv->gw_mode) != GW_MODE_OFF) { + ret = gw_out_of_range(bat_priv, skb, ethhdr); + if (ret) + goto dropped; + } + ret = unicast_send_skb(skb, bat_priv); if (ret != 0) goto dropped_freed; @@ -662,8 +679,6 @@ end: softif_neigh_free_ref(curr_softif_neigh); if (primary_if) hardif_free_ref(primary_if); - if (orig_node) - orig_node_free_ref(orig_node); return NETDEV_TX_OK; } diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c index c7aafc7..78b9528 100644 --- a/net/batman-adv/translation-table.c +++ b/net/batman-adv/translation-table.c @@ -67,7 +67,7 @@ static struct tt_local_entry *tt_local_hash_find(struct bat_priv *bat_priv, struct hlist_head *head; struct hlist_node *node; struct tt_local_entry *tt_local_entry, *tt_local_entry_tmp = NULL; - int index; + uint32_t index; if (!hash) return NULL; @@ -99,7 +99,7 @@ static struct tt_global_entry *tt_global_hash_find(struct bat_priv *bat_priv, struct hlist_node *node; struct tt_global_entry *tt_global_entry; struct tt_global_entry *tt_global_entry_tmp = NULL; - int index; + uint32_t index; if (!hash) return NULL; @@ -314,9 +314,8 @@ int tt_local_seq_print_text(struct seq_file *seq, void *offset) struct hard_iface *primary_if; struct hlist_node *node; struct hlist_head *head; - size_t buf_size, pos; - char *buff; - int i, ret = 0; + uint32_t i; + int ret = 0; primary_if = primary_if_get_selected(bat_priv); if (!primary_if) { @@ -337,34 +336,13 @@ int tt_local_seq_print_text(struct seq_file *seq, void *offset) "announced via TT (TTVN: %u):\n", net_dev->name, (uint8_t)atomic_read(&bat_priv->ttvn)); - buf_size = 1; - /* Estimate length for: " * xx:xx:xx:xx:xx:xx\n" */ - for (i = 0; i < hash->size; i++) { - head = &hash->table[i]; - - rcu_read_lock(); - __hlist_for_each_rcu(node, head) - buf_size += 29; - rcu_read_unlock(); - } - - buff = kmalloc(buf_size, GFP_ATOMIC); - if (!buff) { - ret = -ENOMEM; - goto out; - } - - buff[0] = '\0'; - pos = 0; - for (i = 0; i < hash->size; i++) { head = &hash->table[i]; rcu_read_lock(); hlist_for_each_entry_rcu(tt_local_entry, node, head, hash_entry) { - pos += snprintf(buff + pos, 30, " * %pM " - "[%c%c%c%c%c]\n", + seq_printf(seq, " * %pM [%c%c%c%c%c]\n", tt_local_entry->addr, (tt_local_entry->flags & TT_CLIENT_ROAM ? 'R' : '.'), @@ -379,9 +357,6 @@ int tt_local_seq_print_text(struct seq_file *seq, void *offset) } rcu_read_unlock(); } - - seq_printf(seq, "%s", buff); - kfree(buff); out: if (primary_if) hardif_free_ref(primary_if); @@ -427,7 +402,7 @@ static void tt_local_purge(struct bat_priv *bat_priv) struct hlist_node *node, *node_tmp; struct hlist_head *head; spinlock_t *list_lock; /* protects write access to the hash lists */ - int i; + uint32_t i; for (i = 0; i < hash->size; i++) { head = &hash->table[i]; @@ -465,7 +440,7 @@ static void tt_local_table_free(struct bat_priv *bat_priv) struct tt_local_entry *tt_local_entry; struct hlist_node *node, *node_tmp; struct hlist_head *head; - int i; + uint32_t i; if (!bat_priv->tt_local_hash) return; @@ -590,9 +565,8 @@ int tt_global_seq_print_text(struct seq_file *seq, void *offset) struct hard_iface *primary_if; struct hlist_node *node; struct hlist_head *head; - size_t buf_size, pos; - char *buff; - int i, ret = 0; + uint32_t i; + int ret = 0; primary_if = primary_if_get_selected(bat_priv); if (!primary_if) { @@ -615,35 +589,13 @@ int tt_global_seq_print_text(struct seq_file *seq, void *offset) seq_printf(seq, " %-13s %s %-15s %s %s\n", "Client", "(TTVN)", "Originator", "(Curr TTVN)", "Flags"); - buf_size = 1; - /* Estimate length for: " * xx:xx:xx:xx:xx:xx (ttvn) via - * xx:xx:xx:xx:xx:xx (cur_ttvn)\n"*/ - for (i = 0; i < hash->size; i++) { - head = &hash->table[i]; - - rcu_read_lock(); - __hlist_for_each_rcu(node, head) - buf_size += 67; - rcu_read_unlock(); - } - - buff = kmalloc(buf_size, GFP_ATOMIC); - if (!buff) { - ret = -ENOMEM; - goto out; - } - - buff[0] = '\0'; - pos = 0; - for (i = 0; i < hash->size; i++) { head = &hash->table[i]; rcu_read_lock(); hlist_for_each_entry_rcu(tt_global_entry, node, head, hash_entry) { - pos += snprintf(buff + pos, 69, - " * %pM (%3u) via %pM (%3u) " + seq_printf(seq, " * %pM (%3u) via %pM (%3u) " "[%c%c%c]\n", tt_global_entry->addr, tt_global_entry->ttvn, tt_global_entry->orig_node->orig, @@ -659,9 +611,6 @@ int tt_global_seq_print_text(struct seq_file *seq, void *offset) } rcu_read_unlock(); } - - seq_printf(seq, "%s", buff); - kfree(buff); out: if (primary_if) hardif_free_ref(primary_if); @@ -716,7 +665,7 @@ void tt_global_del_orig(struct bat_priv *bat_priv, struct orig_node *orig_node, const char *message) { struct tt_global_entry *tt_global_entry; - int i; + uint32_t i; struct hashtable_t *hash = bat_priv->tt_global_hash; struct hlist_node *node, *safe; struct hlist_head *head; @@ -735,9 +684,10 @@ void tt_global_del_orig(struct bat_priv *bat_priv, if (tt_global_entry->orig_node == orig_node) { bat_dbg(DBG_TT, bat_priv, "Deleting global tt entry %pM " - "(via %pM): originator time out\n", + "(via %pM): %s\n", tt_global_entry->addr, - tt_global_entry->orig_node->orig); + tt_global_entry->orig_node->orig, + message); hlist_del_rcu(node); tt_global_entry_free_ref(tt_global_entry); } @@ -754,7 +704,7 @@ static void tt_global_roam_purge(struct bat_priv *bat_priv) struct hlist_node *node, *node_tmp; struct hlist_head *head; spinlock_t *list_lock; /* protects write access to the hash lists */ - int i; + uint32_t i; for (i = 0; i < hash->size; i++) { head = &hash->table[i]; @@ -788,7 +738,7 @@ static void tt_global_table_free(struct bat_priv *bat_priv) struct tt_global_entry *tt_global_entry; struct hlist_node *node, *node_tmp; struct hlist_head *head; - int i; + uint32_t i; if (!bat_priv->tt_global_hash) return; @@ -874,7 +824,8 @@ uint16_t tt_global_crc(struct bat_priv *bat_priv, struct orig_node *orig_node) struct tt_global_entry *tt_global_entry; struct hlist_node *node; struct hlist_head *head; - int i, j; + uint32_t i; + int j; for (i = 0; i < hash->size; i++) { head = &hash->table[i]; @@ -911,7 +862,8 @@ uint16_t tt_local_crc(struct bat_priv *bat_priv) struct tt_local_entry *tt_local_entry; struct hlist_node *node; struct hlist_head *head; - int i, j; + uint32_t i; + int j; for (i = 0; i < hash->size; i++) { head = &hash->table[i]; @@ -1048,7 +1000,7 @@ static struct sk_buff *tt_response_fill_table(uint16_t tt_len, uint8_t ttvn, struct sk_buff *skb = NULL; uint16_t tt_tot, tt_count; ssize_t tt_query_size = sizeof(struct tt_query_packet); - int i; + uint32_t i; if (tt_query_size + tt_len > primary_if->soft_iface->mtu) { tt_len = primary_if->soft_iface->mtu - tt_query_size; @@ -1187,11 +1139,11 @@ static bool send_other_tt_response(struct bat_priv *bat_priv, (tt_request->flags & TT_FULL_TABLE ? 'F' : '.')); /* Let's get the orig node of the REAL destination */ - req_dst_orig_node = get_orig_node(bat_priv, tt_request->dst); + req_dst_orig_node = orig_hash_find(bat_priv, tt_request->dst); if (!req_dst_orig_node) goto out; - res_dst_orig_node = get_orig_node(bat_priv, tt_request->src); + res_dst_orig_node = orig_hash_find(bat_priv, tt_request->src); if (!res_dst_orig_node) goto out; @@ -1317,7 +1269,7 @@ static bool send_my_tt_response(struct bat_priv *bat_priv, my_ttvn = (uint8_t)atomic_read(&bat_priv->ttvn); req_ttvn = tt_request->ttvn; - orig_node = get_orig_node(bat_priv, tt_request->src); + orig_node = orig_hash_find(bat_priv, tt_request->src); if (!orig_node) goto out; @@ -1725,7 +1677,7 @@ void tt_free(struct bat_priv *bat_priv) * entry */ static void tt_local_reset_flags(struct bat_priv *bat_priv, uint16_t flags) { - int i; + uint32_t i; struct hashtable_t *hash = bat_priv->tt_local_hash; struct hlist_head *head; struct hlist_node *node; @@ -1758,7 +1710,7 @@ static void tt_local_purge_pending_clients(struct bat_priv *bat_priv) struct hlist_node *node, *node_tmp; struct hlist_head *head; spinlock_t *list_lock; /* protects write access to the hash lists */ - int i; + uint32_t i; if (!hash) return; diff --git a/net/batman-adv/vis.c b/net/batman-adv/vis.c index f81a6b6..7445413 100644 --- a/net/batman-adv/vis.c +++ b/net/batman-adv/vis.c @@ -66,7 +66,7 @@ static int vis_info_cmp(const struct hlist_node *node, const void *data2) /* hash function to choose an entry in a hash table of given size */ /* hash algorithm from http://en.wikipedia.org/wiki/Hash_table */ -static int vis_info_choose(const void *data, int size) +static uint32_t vis_info_choose(const void *data, uint32_t size) { const struct vis_info *vis_info = data; const struct vis_packet *packet; @@ -96,7 +96,7 @@ static struct vis_info *vis_hash_find(struct bat_priv *bat_priv, struct hlist_head *head; struct hlist_node *node; struct vis_info *vis_info, *vis_info_tmp = NULL; - int index; + uint32_t index; if (!hash) return NULL; @@ -202,7 +202,8 @@ int vis_seq_print_text(struct seq_file *seq, void *offset) HLIST_HEAD(vis_if_list); struct if_list_entry *entry; struct hlist_node *pos, *n; - int i, j, ret = 0; + uint32_t i; + int j, ret = 0; int vis_server = atomic_read(&bat_priv->vis_mode); size_t buff_pos, buf_size; char *buff; @@ -556,7 +557,8 @@ static int find_best_vis_server(struct bat_priv *bat_priv, struct hlist_head *head; struct orig_node *orig_node; struct vis_packet *packet; - int best_tq = -1, i; + int best_tq = -1; + uint32_t i; packet = (struct vis_packet *)info->skb_packet->data; @@ -608,7 +610,8 @@ static int generate_vis_packet(struct bat_priv *bat_priv) struct vis_packet *packet = (struct vis_packet *)info->skb_packet->data; struct vis_info_entry *entry; struct tt_local_entry *tt_local_entry; - int best_tq = -1, i; + int best_tq = -1; + uint32_t i; info->first_seen = jiffies; packet->vis_type = atomic_read(&bat_priv->vis_mode); @@ -696,7 +699,7 @@ unlock: * held */ static void purge_vis_packets(struct bat_priv *bat_priv) { - int i; + uint32_t i; struct hashtable_t *hash = bat_priv->vis_hash; struct hlist_node *node, *node_tmp; struct hlist_head *head; @@ -733,7 +736,7 @@ static void broadcast_vis_packet(struct bat_priv *bat_priv, struct sk_buff *skb; struct hard_iface *hard_iface; uint8_t dstaddr[ETH_ALEN]; - int i; + uint32_t i; packet = (struct vis_packet *)info->skb_packet->data; diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c index feb77ea..a3754ac 100644 --- a/net/bridge/br_device.c +++ b/net/bridge/br_device.c @@ -186,7 +186,8 @@ static void br_getinfo(struct net_device *dev, struct ethtool_drvinfo *info) strcpy(info->bus_info, "N/A"); } -static u32 br_fix_features(struct net_device *dev, u32 features) +static netdev_features_t br_fix_features(struct net_device *dev, + netdev_features_t features) { struct net_bridge *br = netdev_priv(dev); @@ -341,10 +342,10 @@ void br_dev_setup(struct net_device *dev) dev->priv_flags = IFF_EBRIDGE; dev->features = NETIF_F_SG | NETIF_F_FRAGLIST | NETIF_F_HIGHDMA | - NETIF_F_GSO_MASK | NETIF_F_NO_CSUM | NETIF_F_LLTX | + NETIF_F_GSO_MASK | NETIF_F_HW_CSUM | NETIF_F_LLTX | NETIF_F_NETNS_LOCAL | NETIF_F_HW_VLAN_TX; dev->hw_features = NETIF_F_SG | NETIF_F_FRAGLIST | NETIF_F_HIGHDMA | - NETIF_F_GSO_MASK | NETIF_F_NO_CSUM | + NETIF_F_GSO_MASK | NETIF_F_HW_CSUM | NETIF_F_HW_VLAN_TX; br->dev = dev; diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c index c8e7861..973813e 100644 --- a/net/bridge/br_fdb.c +++ b/net/bridge/br_fdb.c @@ -556,7 +556,7 @@ skip: return skb->len; } -/* Create new static fdb entry */ +/* Update (create or replace) forwarding database entry */ static int fdb_add_entry(struct net_bridge_port *source, const __u8 *addr, __u16 state, __u16 flags) { @@ -575,16 +575,21 @@ static int fdb_add_entry(struct net_bridge_port *source, const __u8 *addr, } else { if (flags & NLM_F_EXCL) return -EEXIST; + } + + if (fdb_to_nud(fdb) != state) { + if (state & NUD_PERMANENT) + fdb->is_local = fdb->is_static = 1; + else if (state & NUD_NOARP) { + fdb->is_local = 0; + fdb->is_static = 1; + } else + fdb->is_local = fdb->is_static = 0; - if (flags & NLM_F_REPLACE) - fdb->updated = fdb->used = jiffies; - fdb->is_local = fdb->is_static = 0; + fdb->updated = fdb->used = jiffies; + fdb_notify(fdb, RTM_NEWNEIGH); } - if (state & NUD_PERMANENT) - fdb->is_local = fdb->is_static = 1; - else if (state & NUD_NOARP) - fdb->is_static = 1; return 0; } @@ -627,6 +632,11 @@ int br_fdb_add(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) return -EINVAL; } + if (!(ndm->ndm_state & (NUD_PERMANENT|NUD_NOARP|NUD_REACHABLE))) { + pr_info("bridge: RTM_NEWNEIGH with invalid state %#x\n", ndm->ndm_state); + return -EINVAL; + } + p = br_port_get_rtnl(dev); if (p == NULL) { pr_info("bridge: RTM_NEWNEIGH %s not a bridge port\n", @@ -634,9 +644,15 @@ int br_fdb_add(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) return -EINVAL; } - spin_lock_bh(&p->br->hash_lock); - err = fdb_add_entry(p, addr, ndm->ndm_state, nlh->nlmsg_flags); - spin_unlock_bh(&p->br->hash_lock); + if (ndm->ndm_flags & NTF_USE) { + rcu_read_lock(); + br_fdb_update(p->br, p, addr); + rcu_read_unlock(); + } else { + spin_lock_bh(&p->br->hash_lock); + err = fdb_add_entry(p, addr, ndm->ndm_state, nlh->nlmsg_flags); + spin_unlock_bh(&p->br->hash_lock); + } return err; } diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c index f603e5b..0a942fb 100644 --- a/net/bridge/br_if.c +++ b/net/bridge/br_if.c @@ -296,10 +296,11 @@ int br_min_mtu(const struct net_bridge *br) /* * Recomputes features using slave's features */ -u32 br_features_recompute(struct net_bridge *br, u32 features) +netdev_features_t br_features_recompute(struct net_bridge *br, + netdev_features_t features) { struct net_bridge_port *p; - u32 mask; + netdev_features_t mask; if (list_empty(&br->port_list)) return features; diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index 995cbe0..7743e0d 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -127,7 +127,7 @@ static struct net_bridge_mdb_entry *br_mdb_ip6_get( { struct br_ip br_dst; - ipv6_addr_copy(&br_dst.u.ip6, dst); + br_dst.u.ip6 = *dst; br_dst.proto = htons(ETH_P_IPV6); return br_mdb_ip_get(mdb, &br_dst); @@ -154,7 +154,7 @@ struct net_bridge_mdb_entry *br_mdb_get(struct net_bridge *br, break; #if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) case htons(ETH_P_IPV6): - ipv6_addr_copy(&ip.u.ip6, &ipv6_hdr(skb)->daddr); + ip.u.ip6 = ipv6_hdr(skb)->daddr; break; #endif default: @@ -474,7 +474,7 @@ static struct sk_buff *br_ip6_multicast_alloc_query(struct net_bridge *br, mldq->mld_cksum = 0; mldq->mld_maxdelay = htons((u16)jiffies_to_msecs(interval)); mldq->mld_reserved = 0; - ipv6_addr_copy(&mldq->mld_mca, group); + mldq->mld_mca = *group; /* checksum */ mldq->mld_cksum = csum_ipv6_magic(&ip6h->saddr, &ip6h->daddr, @@ -783,7 +783,7 @@ static int br_ip6_multicast_add_group(struct net_bridge *br, if (!ipv6_is_transient_multicast(group)) return 0; - ipv6_addr_copy(&br_group.u.ip6, group); + br_group.u.ip6 = *group; br_group.proto = htons(ETH_P_IPV6); return br_multicast_add_group(br, port, &br_group); @@ -1344,7 +1344,7 @@ static void br_ip6_multicast_leave_group(struct net_bridge *br, if (!ipv6_is_transient_multicast(group)) return; - ipv6_addr_copy(&br_group.u.ip6, group); + br_group.u.ip6 = *group; br_group.proto = htons(ETH_P_IPV6); br_multicast_leave_group(br, port, &br_group); @@ -1501,6 +1501,8 @@ static int br_multicast_ipv6_rcv(struct net_bridge *br, __skb_pull(skb2, offset); skb_reset_transport_header(skb2); + skb_postpull_rcsum(skb2, skb_network_header(skb2), + skb_network_header_len(skb2)); icmp6_type = icmp6_hdr(skb2)->icmp6_type; @@ -1770,7 +1772,7 @@ int br_multicast_toggle(struct net_bridge *br, unsigned long val) int err = 0; struct net_bridge_mdb_htable *mdb; - spin_lock(&br->multicast_lock); + spin_lock_bh(&br->multicast_lock); if (br->multicast_disabled == !val) goto unlock; @@ -1806,7 +1808,7 @@ rollback: } unlock: - spin_unlock(&br->multicast_lock); + spin_unlock_bh(&br->multicast_lock); return err; } diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index d7d6fb0..4027029 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -387,7 +387,8 @@ extern int br_add_if(struct net_bridge *br, extern int br_del_if(struct net_bridge *br, struct net_device *dev); extern int br_min_mtu(const struct net_bridge *br); -extern u32 br_features_recompute(struct net_bridge *br, u32 features); +extern netdev_features_t br_features_recompute(struct net_bridge *br, + netdev_features_t features); /* br_input.c */ extern int br_handle_frame_finish(struct sk_buff *skb); diff --git a/net/caif/cffrml.c b/net/caif/cffrml.c index f399211..d3ca87b 100644 --- a/net/caif/cffrml.c +++ b/net/caif/cffrml.c @@ -136,20 +136,21 @@ static int cffrml_receive(struct cflayer *layr, struct cfpkt *pkt) static int cffrml_transmit(struct cflayer *layr, struct cfpkt *pkt) { - int tmp; u16 chks; u16 len; + __le16 data; + struct cffrml *this = container_obj(layr); if (this->dofcs) { chks = cfpkt_iterate(pkt, cffrml_checksum, 0xffff); - tmp = cpu_to_le16(chks); - cfpkt_add_trail(pkt, &tmp, 2); + data = cpu_to_le16(chks); + cfpkt_add_trail(pkt, &data, 2); } else { cfpkt_pad_trail(pkt, 2); } len = cfpkt_getlen(pkt); - tmp = cpu_to_le16(len); - cfpkt_add_head(pkt, &tmp, 2); + data = cpu_to_le16(len); + cfpkt_add_head(pkt, &data, 2); cfpkt_info(pkt)->hdr_len += 2; if (cfpkt_erroneous(pkt)) { pr_err("Packet is erroneous!\n"); diff --git a/net/core/Makefile b/net/core/Makefile index 0d357b1..3606d40 100644 --- a/net/core/Makefile +++ b/net/core/Makefile @@ -19,3 +19,4 @@ obj-$(CONFIG_FIB_RULES) += fib_rules.o obj-$(CONFIG_TRACEPOINTS) += net-traces.o obj-$(CONFIG_NET_DROP_MONITOR) += drop_monitor.o obj-$(CONFIG_NETWORK_PHY_TIMESTAMPING) += timestamping.o +obj-$(CONFIG_NETPRIO_CGROUP) += netprio_cgroup.o diff --git a/net/core/dev.c b/net/core/dev.c index 6ba50a1..8afb244 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -137,6 +137,7 @@ #include <linux/if_pppox.h> #include <linux/ppp_defs.h> #include <linux/net_tstamp.h> +#include <linux/jump_label.h> #include "net-sysfs.h" @@ -1320,8 +1321,6 @@ EXPORT_SYMBOL(dev_close); */ void dev_disable_lro(struct net_device *dev) { - u32 flags; - /* * If we're trying to disable lro on a vlan device * use the underlying physical device instead @@ -1329,15 +1328,9 @@ void dev_disable_lro(struct net_device *dev) if (is_vlan_dev(dev)) dev = vlan_dev_real_dev(dev); - if (dev->ethtool_ops && dev->ethtool_ops->get_flags) - flags = dev->ethtool_ops->get_flags(dev); - else - flags = ethtool_op_get_flags(dev); + dev->wanted_features &= ~NETIF_F_LRO; + netdev_update_features(dev); - if (!(flags & ETH_FLAG_LRO)) - return; - - __ethtool_set_flags(dev, flags & ~ETH_FLAG_LRO); if (unlikely(dev->features & NETIF_F_LRO)) netdev_WARN(dev, "failed to disable LRO!\n"); } @@ -1449,34 +1442,32 @@ int call_netdevice_notifiers(unsigned long val, struct net_device *dev) } EXPORT_SYMBOL(call_netdevice_notifiers); -/* When > 0 there are consumers of rx skb time stamps */ -static atomic_t netstamp_needed = ATOMIC_INIT(0); +static struct jump_label_key netstamp_needed __read_mostly; void net_enable_timestamp(void) { - atomic_inc(&netstamp_needed); + jump_label_inc(&netstamp_needed); } EXPORT_SYMBOL(net_enable_timestamp); void net_disable_timestamp(void) { - atomic_dec(&netstamp_needed); + jump_label_dec(&netstamp_needed); } EXPORT_SYMBOL(net_disable_timestamp); static inline void net_timestamp_set(struct sk_buff *skb) { - if (atomic_read(&netstamp_needed)) + skb->tstamp.tv64 = 0; + if (static_branch(&netstamp_needed)) __net_timestamp(skb); - else - skb->tstamp.tv64 = 0; } -static inline void net_timestamp_check(struct sk_buff *skb) -{ - if (!skb->tstamp.tv64 && atomic_read(&netstamp_needed)) - __net_timestamp(skb); -} +#define net_timestamp_check(COND, SKB) \ + if (static_branch(&netstamp_needed)) { \ + if ((COND) && !(SKB)->tstamp.tv64) \ + __net_timestamp(SKB); \ + } \ static int net_hwtstamp_validate(struct ifreq *ifr) { @@ -1923,7 +1914,8 @@ EXPORT_SYMBOL(skb_checksum_help); * It may return NULL if the skb requires no segmentation. This is * only possible when GSO is used for verifying header integrity. */ -struct sk_buff *skb_gso_segment(struct sk_buff *skb, u32 features) +struct sk_buff *skb_gso_segment(struct sk_buff *skb, + netdev_features_t features) { struct sk_buff *segs = ERR_PTR(-EPROTONOSUPPORT); struct packet_type *ptype; @@ -1953,9 +1945,9 @@ struct sk_buff *skb_gso_segment(struct sk_buff *skb, u32 features) if (dev && dev->ethtool_ops && dev->ethtool_ops->get_drvinfo) dev->ethtool_ops->get_drvinfo(dev, &info); - WARN(1, "%s: caps=(0x%lx, 0x%lx) len=%d data_len=%d ip_summed=%d\n", - info.driver, dev ? dev->features : 0L, - skb->sk ? skb->sk->sk_route_caps : 0L, + WARN(1, "%s: caps=(%pNF, %pNF) len=%d data_len=%d ip_summed=%d\n", + info.driver, dev ? &dev->features : NULL, + skb->sk ? &skb->sk->sk_route_caps : NULL, skb->len, skb->data_len, skb->ip_summed); if (skb_header_cloned(skb) && @@ -2064,7 +2056,7 @@ static void dev_gso_skb_destructor(struct sk_buff *skb) * This function segments the given skb and stores the list of segments * in skb->next. */ -static int dev_gso_segment(struct sk_buff *skb, int features) +static int dev_gso_segment(struct sk_buff *skb, netdev_features_t features) { struct sk_buff *segs; @@ -2103,7 +2095,7 @@ static inline void skb_orphan_try(struct sk_buff *skb) } } -static bool can_checksum_protocol(unsigned long features, __be16 protocol) +static bool can_checksum_protocol(netdev_features_t features, __be16 protocol) { return ((features & NETIF_F_GEN_CSUM) || ((features & NETIF_F_V4_CSUM) && @@ -2114,7 +2106,8 @@ static bool can_checksum_protocol(unsigned long features, __be16 protocol) protocol == htons(ETH_P_FCOE))); } -static u32 harmonize_features(struct sk_buff *skb, __be16 protocol, u32 features) +static netdev_features_t harmonize_features(struct sk_buff *skb, + __be16 protocol, netdev_features_t features) { if (!can_checksum_protocol(features, protocol)) { features &= ~NETIF_F_ALL_CSUM; @@ -2126,10 +2119,10 @@ static u32 harmonize_features(struct sk_buff *skb, __be16 protocol, u32 features return features; } -u32 netif_skb_features(struct sk_buff *skb) +netdev_features_t netif_skb_features(struct sk_buff *skb) { __be16 protocol = skb->protocol; - u32 features = skb->dev->features; + netdev_features_t features = skb->dev->features; if (protocol == htons(ETH_P_8021Q)) { struct vlan_ethhdr *veh = (struct vlan_ethhdr *)skb->data; @@ -2175,7 +2168,7 @@ int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev, unsigned int skb_len; if (likely(!skb->next)) { - u32 features; + netdev_features_t features; /* * If device doesn't need skb->dst, release it right now while @@ -2456,6 +2449,18 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q, return rc; } +#if IS_ENABLED(CONFIG_NETPRIO_CGROUP) +static void skb_update_prio(struct sk_buff *skb) +{ + struct netprio_map *map = rcu_dereference(skb->dev->priomap); + + if ((!skb->priority) && (skb->sk) && map) + skb->priority = map->priomap[skb->sk->sk_cgrp_prioidx]; +} +#else +#define skb_update_prio(skb) +#endif + static DEFINE_PER_CPU(int, xmit_recursion); #define RECURSION_LIMIT 10 @@ -2496,6 +2501,8 @@ int dev_queue_xmit(struct sk_buff *skb) */ rcu_read_lock_bh(); + skb_update_prio(skb); + txq = dev_pick_tx(dev, skb); q = rcu_dereference_bh(txq->qdisc); @@ -2718,6 +2725,8 @@ EXPORT_SYMBOL(__skb_get_rxhash); struct rps_sock_flow_table __rcu *rps_sock_flow_table __read_mostly; EXPORT_SYMBOL(rps_sock_flow_table); +struct jump_label_key rps_needed __read_mostly; + static struct rps_dev_flow * set_rps_cpu(struct net_device *dev, struct sk_buff *skb, struct rps_dev_flow *rflow, u16 next_cpu) @@ -2997,12 +3006,11 @@ int netif_rx(struct sk_buff *skb) if (netpoll_rx(skb)) return NET_RX_DROP; - if (netdev_tstamp_prequeue) - net_timestamp_check(skb); + net_timestamp_check(netdev_tstamp_prequeue, skb); trace_netif_rx(skb); #ifdef CONFIG_RPS - { + if (static_branch(&rps_needed)) { struct rps_dev_flow voidflow, *rflow = &voidflow; int cpu; @@ -3017,14 +3025,13 @@ int netif_rx(struct sk_buff *skb) rcu_read_unlock(); preempt_enable(); - } -#else + } else +#endif { unsigned int qtail; ret = enqueue_to_backlog(skb, get_cpu(), &qtail); put_cpu(); } -#endif return ret; } EXPORT_SYMBOL(netif_rx); @@ -3230,8 +3237,7 @@ static int __netif_receive_skb(struct sk_buff *skb) int ret = NET_RX_DROP; __be16 type; - if (!netdev_tstamp_prequeue) - net_timestamp_check(skb); + net_timestamp_check(!netdev_tstamp_prequeue, skb); trace_netif_receive_skb(skb); @@ -3362,14 +3368,13 @@ out: */ int netif_receive_skb(struct sk_buff *skb) { - if (netdev_tstamp_prequeue) - net_timestamp_check(skb); + net_timestamp_check(netdev_tstamp_prequeue, skb); if (skb_defer_rx_timestamp(skb)) return NET_RX_SUCCESS; #ifdef CONFIG_RPS - { + if (static_branch(&rps_needed)) { struct rps_dev_flow voidflow, *rflow = &voidflow; int cpu, ret; @@ -3380,16 +3385,12 @@ int netif_receive_skb(struct sk_buff *skb) if (cpu >= 0) { ret = enqueue_to_backlog(skb, cpu, &rflow->last_qtail); rcu_read_unlock(); - } else { - rcu_read_unlock(); - ret = __netif_receive_skb(skb); + return ret; } - - return ret; + rcu_read_unlock(); } -#else - return __netif_receive_skb(skb); #endif + return __netif_receive_skb(skb); } EXPORT_SYMBOL(netif_receive_skb); @@ -5362,7 +5363,8 @@ static void rollback_registered(struct net_device *dev) list_del(&single); } -static u32 netdev_fix_features(struct net_device *dev, u32 features) +static netdev_features_t netdev_fix_features(struct net_device *dev, + netdev_features_t features) { /* Fix illegal checksum combinations */ if ((features & NETIF_F_HW_CSUM) && @@ -5371,12 +5373,6 @@ static u32 netdev_fix_features(struct net_device *dev, u32 features) features &= ~(NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM); } - if ((features & NETIF_F_NO_CSUM) && - (features & (NETIF_F_HW_CSUM|NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM))) { - netdev_warn(dev, "mixed no checksumming and other settings.\n"); - features &= ~(NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM|NETIF_F_HW_CSUM); - } - /* Fix illegal SG+CSUM combinations. */ if ((features & NETIF_F_SG) && !(features & NETIF_F_ALL_CSUM)) { @@ -5424,7 +5420,7 @@ static u32 netdev_fix_features(struct net_device *dev, u32 features) int __netdev_update_features(struct net_device *dev) { - u32 features; + netdev_features_t features; int err = 0; ASSERT_RTNL(); @@ -5440,16 +5436,16 @@ int __netdev_update_features(struct net_device *dev) if (dev->features == features) return 0; - netdev_dbg(dev, "Features changed: 0x%08x -> 0x%08x\n", - dev->features, features); + netdev_dbg(dev, "Features changed: %pNF -> %pNF\n", + &dev->features, &features); if (dev->netdev_ops->ndo_set_features) err = dev->netdev_ops->ndo_set_features(dev, features); if (unlikely(err < 0)) { netdev_err(dev, - "set_features() failed (%d); wanted 0x%08x, left 0x%08x\n", - err, features, dev->features); + "set_features() failed (%d); wanted %pNF, left %pNF\n", + err, &features, &dev->features); return -1; } @@ -5633,11 +5629,12 @@ int register_netdevice(struct net_device *dev) dev->wanted_features = dev->features & dev->hw_features; /* 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; + if (!(dev->flags & IFF_LOOPBACK)) { + dev->hw_features |= NETIF_F_NOCACHE_COPY; + if (dev->features & NETIF_F_ALL_CSUM) { + dev->wanted_features |= NETIF_F_NOCACHE_COPY; + dev->features |= NETIF_F_NOCACHE_COPY; + } } /* Make NETIF_F_HIGHDMA inheritable to VLAN devices. @@ -6373,7 +6370,8 @@ static int dev_cpu_callback(struct notifier_block *nfb, * @one to the master device with current feature set @all. Will not * enable anything that is off in @mask. Returns the new feature set. */ -u32 netdev_increment_features(u32 all, u32 one, u32 mask) +netdev_features_t netdev_increment_features(netdev_features_t all, + netdev_features_t one, netdev_features_t mask) { if (mask & NETIF_F_GEN_CSUM) mask |= NETIF_F_ALL_CSUM; @@ -6382,10 +6380,6 @@ u32 netdev_increment_features(u32 all, u32 one, u32 mask) all |= one & (NETIF_F_ONE_FOR_ALL|NETIF_F_ALL_CSUM) & mask; all &= one | ~NETIF_F_ALL_FOR_ALL; - /* If device needs checksumming, downgrade to it. */ - if (all & (NETIF_F_ALL_CSUM & ~NETIF_F_NO_CSUM)) - all &= ~NETIF_F_NO_CSUM; - /* If one device supports hw checksumming, set for all. */ if (all & NETIF_F_GEN_CSUM) all &= ~(NETIF_F_ALL_CSUM & ~NETIF_F_GEN_CSUM); diff --git a/net/core/ethtool.c b/net/core/ethtool.c index f444817..31b0b7f 100644 --- a/net/core/ethtool.c +++ b/net/core/ethtool.c @@ -36,235 +36,44 @@ u32 ethtool_op_get_link(struct net_device *dev) } EXPORT_SYMBOL(ethtool_op_get_link); -u32 ethtool_op_get_tx_csum(struct net_device *dev) -{ - return (dev->features & NETIF_F_ALL_CSUM) != 0; -} -EXPORT_SYMBOL(ethtool_op_get_tx_csum); - -int ethtool_op_set_tx_csum(struct net_device *dev, u32 data) -{ - if (data) - dev->features |= NETIF_F_IP_CSUM; - else - dev->features &= ~NETIF_F_IP_CSUM; - - return 0; -} -EXPORT_SYMBOL(ethtool_op_set_tx_csum); - -int ethtool_op_set_tx_hw_csum(struct net_device *dev, u32 data) -{ - if (data) - dev->features |= NETIF_F_HW_CSUM; - else - dev->features &= ~NETIF_F_HW_CSUM; - - return 0; -} -EXPORT_SYMBOL(ethtool_op_set_tx_hw_csum); - -int ethtool_op_set_tx_ipv6_csum(struct net_device *dev, u32 data) -{ - if (data) - dev->features |= NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM; - else - dev->features &= ~(NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM); - - return 0; -} -EXPORT_SYMBOL(ethtool_op_set_tx_ipv6_csum); - -u32 ethtool_op_get_sg(struct net_device *dev) -{ - return (dev->features & NETIF_F_SG) != 0; -} -EXPORT_SYMBOL(ethtool_op_get_sg); - -int ethtool_op_set_sg(struct net_device *dev, u32 data) -{ - if (data) - dev->features |= NETIF_F_SG; - else - dev->features &= ~NETIF_F_SG; - - return 0; -} -EXPORT_SYMBOL(ethtool_op_set_sg); - -u32 ethtool_op_get_tso(struct net_device *dev) -{ - return (dev->features & NETIF_F_TSO) != 0; -} -EXPORT_SYMBOL(ethtool_op_get_tso); - -int ethtool_op_set_tso(struct net_device *dev, u32 data) -{ - if (data) - dev->features |= NETIF_F_TSO; - else - dev->features &= ~NETIF_F_TSO; - - return 0; -} -EXPORT_SYMBOL(ethtool_op_set_tso); - -u32 ethtool_op_get_ufo(struct net_device *dev) -{ - return (dev->features & NETIF_F_UFO) != 0; -} -EXPORT_SYMBOL(ethtool_op_get_ufo); - -int ethtool_op_set_ufo(struct net_device *dev, u32 data) -{ - if (data) - dev->features |= NETIF_F_UFO; - else - dev->features &= ~NETIF_F_UFO; - return 0; -} -EXPORT_SYMBOL(ethtool_op_set_ufo); - -/* the following list of flags are the same as their associated - * NETIF_F_xxx values in include/linux/netdevice.h - */ -static const u32 flags_dup_features = - (ETH_FLAG_LRO | ETH_FLAG_RXVLAN | ETH_FLAG_TXVLAN | ETH_FLAG_NTUPLE | - ETH_FLAG_RXHASH); - -u32 ethtool_op_get_flags(struct net_device *dev) -{ - /* in the future, this function will probably contain additional - * handling for flags which are not so easily handled - * by a simple masking operation - */ - - return dev->features & flags_dup_features; -} -EXPORT_SYMBOL(ethtool_op_get_flags); - -/* Check if device can enable (or disable) particular feature coded in "data" - * argument. Flags "supported" describe features that can be toggled by device. - * If feature can not be toggled, it state (enabled or disabled) must match - * hardcoded device features state, otherwise flags are marked as invalid. - */ -bool ethtool_invalid_flags(struct net_device *dev, u32 data, u32 supported) -{ - u32 features = dev->features & flags_dup_features; - /* "data" can contain only flags_dup_features bits, - * see __ethtool_set_flags */ - - return (features & ~supported) != (data & ~supported); -} -EXPORT_SYMBOL(ethtool_invalid_flags); - -int ethtool_op_set_flags(struct net_device *dev, u32 data, u32 supported) -{ - if (ethtool_invalid_flags(dev, data, supported)) - return -EINVAL; - - dev->features = ((dev->features & ~flags_dup_features) | - (data & flags_dup_features)); - return 0; -} -EXPORT_SYMBOL(ethtool_op_set_flags); - /* Handlers for each ethtool command */ -#define ETHTOOL_DEV_FEATURE_WORDS 1 - -static void ethtool_get_features_compat(struct net_device *dev, - struct ethtool_get_features_block *features) -{ - if (!dev->ethtool_ops) - return; - - /* getting RX checksum */ - if (dev->ethtool_ops->get_rx_csum) - if (dev->ethtool_ops->get_rx_csum(dev)) - features[0].active |= NETIF_F_RXCSUM; - - /* mark legacy-changeable features */ - if (dev->ethtool_ops->set_sg) - features[0].available |= NETIF_F_SG; - if (dev->ethtool_ops->set_tx_csum) - features[0].available |= NETIF_F_ALL_CSUM; - if (dev->ethtool_ops->set_tso) - features[0].available |= NETIF_F_ALL_TSO; - if (dev->ethtool_ops->set_rx_csum) - features[0].available |= NETIF_F_RXCSUM; - if (dev->ethtool_ops->set_flags) - features[0].available |= flags_dup_features; -} - -static int ethtool_set_feature_compat(struct net_device *dev, - int (*legacy_set)(struct net_device *, u32), - struct ethtool_set_features_block *features, u32 mask) -{ - u32 do_set; - - if (!legacy_set) - return 0; - - if (!(features[0].valid & mask)) - return 0; - - features[0].valid &= ~mask; - - do_set = !!(features[0].requested & mask); - - if (legacy_set(dev, do_set) < 0) - netdev_info(dev, - "Legacy feature change (%s) failed for 0x%08x\n", - do_set ? "set" : "clear", mask); - - return 1; -} - -static int ethtool_set_flags_compat(struct net_device *dev, - int (*legacy_set)(struct net_device *, u32), - struct ethtool_set_features_block *features, u32 mask) -{ - u32 value; - - if (!legacy_set) - return 0; - - if (!(features[0].valid & mask)) - return 0; - - value = dev->features & ~features[0].valid; - value |= features[0].requested; - - features[0].valid &= ~mask; - - if (legacy_set(dev, value & mask) < 0) - netdev_info(dev, "Legacy flags change failed\n"); - - return 1; -} - -static int ethtool_set_features_compat(struct net_device *dev, - struct ethtool_set_features_block *features) -{ - int compat; - - if (!dev->ethtool_ops) - return 0; - - compat = ethtool_set_feature_compat(dev, dev->ethtool_ops->set_sg, - features, NETIF_F_SG); - compat |= ethtool_set_feature_compat(dev, dev->ethtool_ops->set_tx_csum, - features, NETIF_F_ALL_CSUM); - compat |= ethtool_set_feature_compat(dev, dev->ethtool_ops->set_tso, - features, NETIF_F_ALL_TSO); - compat |= ethtool_set_feature_compat(dev, dev->ethtool_ops->set_rx_csum, - features, NETIF_F_RXCSUM); - compat |= ethtool_set_flags_compat(dev, dev->ethtool_ops->set_flags, - features, flags_dup_features); - - return compat; -} +#define ETHTOOL_DEV_FEATURE_WORDS ((NETDEV_FEATURE_COUNT + 31) / 32) + +static const char netdev_features_strings[NETDEV_FEATURE_COUNT][ETH_GSTRING_LEN] = { + [NETIF_F_SG_BIT] = "tx-scatter-gather", + [NETIF_F_IP_CSUM_BIT] = "tx-checksum-ipv4", + [NETIF_F_HW_CSUM_BIT] = "tx-checksum-ip-generic", + [NETIF_F_IPV6_CSUM_BIT] = "tx-checksum-ipv6", + [NETIF_F_HIGHDMA_BIT] = "highdma", + [NETIF_F_FRAGLIST_BIT] = "tx-scatter-gather-fraglist", + [NETIF_F_HW_VLAN_TX_BIT] = "tx-vlan-hw-insert", + + [NETIF_F_HW_VLAN_RX_BIT] = "rx-vlan-hw-parse", + [NETIF_F_HW_VLAN_FILTER_BIT] = "rx-vlan-filter", + [NETIF_F_VLAN_CHALLENGED_BIT] = "vlan-challenged", + [NETIF_F_GSO_BIT] = "tx-generic-segmentation", + [NETIF_F_LLTX_BIT] = "tx-lockless", + [NETIF_F_NETNS_LOCAL_BIT] = "netns-local", + [NETIF_F_GRO_BIT] = "rx-gro", + [NETIF_F_LRO_BIT] = "rx-lro", + + [NETIF_F_TSO_BIT] = "tx-tcp-segmentation", + [NETIF_F_UFO_BIT] = "tx-udp-fragmentation", + [NETIF_F_GSO_ROBUST_BIT] = "tx-gso-robust", + [NETIF_F_TSO_ECN_BIT] = "tx-tcp-ecn-segmentation", + [NETIF_F_TSO6_BIT] = "tx-tcp6-segmentation", + [NETIF_F_FSO_BIT] = "tx-fcoe-segmentation", + + [NETIF_F_FCOE_CRC_BIT] = "tx-checksum-fcoe-crc", + [NETIF_F_SCTP_CSUM_BIT] = "tx-checksum-sctp", + [NETIF_F_FCOE_MTU_BIT] = "fcoe-mtu", + [NETIF_F_NTUPLE_BIT] = "rx-ntuple-filter", + [NETIF_F_RXHASH_BIT] = "rx-hashing", + [NETIF_F_RXCSUM_BIT] = "rx-checksum", + [NETIF_F_NOCACHE_COPY_BIT] = "tx-nocache-copy", + [NETIF_F_LOOPBACK_BIT] = "loopback", +}; static int ethtool_get_features(struct net_device *dev, void __user *useraddr) { @@ -272,18 +81,21 @@ static int ethtool_get_features(struct net_device *dev, void __user *useraddr) .cmd = ETHTOOL_GFEATURES, .size = ETHTOOL_DEV_FEATURE_WORDS, }; - struct ethtool_get_features_block features[ETHTOOL_DEV_FEATURE_WORDS] = { - { - .available = dev->hw_features, - .requested = dev->wanted_features, - .active = dev->features, - .never_changed = NETIF_F_NEVER_CHANGE, - }, - }; + struct ethtool_get_features_block features[ETHTOOL_DEV_FEATURE_WORDS]; u32 __user *sizeaddr; u32 copy_size; + int i; - ethtool_get_features_compat(dev, features); + /* in case feature bits run out again */ + BUILD_BUG_ON(ETHTOOL_DEV_FEATURE_WORDS * sizeof(u32) > sizeof(netdev_features_t)); + + for (i = 0; i < ETHTOOL_DEV_FEATURE_WORDS; ++i) { + features[i].available = (u32)(dev->hw_features >> (32 * i)); + features[i].requested = (u32)(dev->wanted_features >> (32 * i)); + features[i].active = (u32)(dev->features >> (32 * i)); + features[i].never_changed = + (u32)(NETIF_F_NEVER_CHANGE >> (32 * i)); + } sizeaddr = useraddr + offsetof(struct ethtool_gfeatures, size); if (get_user(copy_size, sizeaddr)) @@ -305,7 +117,8 @@ static int ethtool_set_features(struct net_device *dev, void __user *useraddr) { struct ethtool_sfeatures cmd; struct ethtool_set_features_block features[ETHTOOL_DEV_FEATURE_WORDS]; - int ret = 0; + netdev_features_t wanted = 0, valid = 0; + int i, ret = 0; if (copy_from_user(&cmd, useraddr, sizeof(cmd))) return -EFAULT; @@ -317,65 +130,29 @@ static int ethtool_set_features(struct net_device *dev, void __user *useraddr) if (copy_from_user(features, useraddr, sizeof(features))) return -EFAULT; - if (features[0].valid & ~NETIF_F_ETHTOOL_BITS) - return -EINVAL; + for (i = 0; i < ETHTOOL_DEV_FEATURE_WORDS; ++i) { + valid |= (netdev_features_t)features[i].valid << (32 * i); + wanted |= (netdev_features_t)features[i].requested << (32 * i); + } - if (ethtool_set_features_compat(dev, features)) - ret |= ETHTOOL_F_COMPAT; + if (valid & ~NETIF_F_ETHTOOL_BITS) + return -EINVAL; - if (features[0].valid & ~dev->hw_features) { - features[0].valid &= dev->hw_features; + if (valid & ~dev->hw_features) { + valid &= dev->hw_features; ret |= ETHTOOL_F_UNSUPPORTED; } - dev->wanted_features &= ~features[0].valid; - dev->wanted_features |= features[0].valid & features[0].requested; + dev->wanted_features &= ~valid; + dev->wanted_features |= wanted & valid; __netdev_update_features(dev); - if ((dev->wanted_features ^ dev->features) & features[0].valid) + if ((dev->wanted_features ^ dev->features) & valid) ret |= ETHTOOL_F_WISH; return ret; } -static const char netdev_features_strings[ETHTOOL_DEV_FEATURE_WORDS * 32][ETH_GSTRING_LEN] = { - /* NETIF_F_SG */ "tx-scatter-gather", - /* NETIF_F_IP_CSUM */ "tx-checksum-ipv4", - /* NETIF_F_NO_CSUM */ "tx-checksum-unneeded", - /* NETIF_F_HW_CSUM */ "tx-checksum-ip-generic", - /* NETIF_F_IPV6_CSUM */ "tx-checksum-ipv6", - /* NETIF_F_HIGHDMA */ "highdma", - /* NETIF_F_FRAGLIST */ "tx-scatter-gather-fraglist", - /* NETIF_F_HW_VLAN_TX */ "tx-vlan-hw-insert", - - /* NETIF_F_HW_VLAN_RX */ "rx-vlan-hw-parse", - /* NETIF_F_HW_VLAN_FILTER */ "rx-vlan-filter", - /* NETIF_F_VLAN_CHALLENGED */ "vlan-challenged", - /* NETIF_F_GSO */ "tx-generic-segmentation", - /* NETIF_F_LLTX */ "tx-lockless", - /* NETIF_F_NETNS_LOCAL */ "netns-local", - /* NETIF_F_GRO */ "rx-gro", - /* NETIF_F_LRO */ "rx-lro", - - /* NETIF_F_TSO */ "tx-tcp-segmentation", - /* NETIF_F_UFO */ "tx-udp-fragmentation", - /* NETIF_F_GSO_ROBUST */ "tx-gso-robust", - /* NETIF_F_TSO_ECN */ "tx-tcp-ecn-segmentation", - /* NETIF_F_TSO6 */ "tx-tcp6-segmentation", - /* NETIF_F_FSO */ "tx-fcoe-segmentation", - "", - "", - - /* NETIF_F_FCOE_CRC */ "tx-checksum-fcoe-crc", - /* NETIF_F_SCTP_CSUM */ "tx-checksum-sctp", - /* NETIF_F_FCOE_MTU */ "fcoe-mtu", - /* NETIF_F_NTUPLE */ "rx-ntuple-filter", - /* NETIF_F_RXHASH */ "rx-hashing", - /* NETIF_F_RXCSUM */ "rx-checksum", - /* NETIF_F_NOCACHE_COPY */ "tx-nocache-copy", - /* NETIF_F_LOOPBACK */ "loopback", -}; - static int __ethtool_get_sset_count(struct net_device *dev, int sset) { const struct ethtool_ops *ops = dev->ethtool_ops; @@ -402,7 +179,7 @@ static void __ethtool_get_strings(struct net_device *dev, ops->get_strings(dev, stringset, data); } -static u32 ethtool_get_feature_mask(u32 eth_cmd) +static netdev_features_t ethtool_get_feature_mask(u32 eth_cmd) { /* feature masks of legacy discrete ethtool ops */ @@ -433,136 +210,82 @@ static u32 ethtool_get_feature_mask(u32 eth_cmd) } } -static void *__ethtool_get_one_feature_actor(struct net_device *dev, u32 ethcmd) -{ - const struct ethtool_ops *ops = dev->ethtool_ops; - - if (!ops) - return NULL; - - switch (ethcmd) { - case ETHTOOL_GTXCSUM: - return ops->get_tx_csum; - case ETHTOOL_GRXCSUM: - return ops->get_rx_csum; - case ETHTOOL_SSG: - return ops->get_sg; - case ETHTOOL_STSO: - return ops->get_tso; - case ETHTOOL_SUFO: - return ops->get_ufo; - default: - return NULL; - } -} - -static u32 __ethtool_get_rx_csum_oldbug(struct net_device *dev) -{ - return !!(dev->features & NETIF_F_ALL_CSUM); -} - static int ethtool_get_one_feature(struct net_device *dev, char __user *useraddr, u32 ethcmd) { - u32 mask = ethtool_get_feature_mask(ethcmd); + netdev_features_t mask = ethtool_get_feature_mask(ethcmd); struct ethtool_value edata = { .cmd = ethcmd, .data = !!(dev->features & mask), }; - /* compatibility with discrete get_ ops */ - if (!(dev->hw_features & mask)) { - u32 (*actor)(struct net_device *); - - actor = __ethtool_get_one_feature_actor(dev, ethcmd); - - /* bug compatibility with old get_rx_csum */ - if (ethcmd == ETHTOOL_GRXCSUM && !actor) - actor = __ethtool_get_rx_csum_oldbug; - - if (actor) - edata.data = actor(dev); - } - if (copy_to_user(useraddr, &edata, sizeof(edata))) return -EFAULT; return 0; } -static int __ethtool_set_tx_csum(struct net_device *dev, u32 data); -static int __ethtool_set_rx_csum(struct net_device *dev, u32 data); -static int __ethtool_set_sg(struct net_device *dev, u32 data); -static int __ethtool_set_tso(struct net_device *dev, u32 data); -static int __ethtool_set_ufo(struct net_device *dev, u32 data); - static int ethtool_set_one_feature(struct net_device *dev, void __user *useraddr, u32 ethcmd) { struct ethtool_value edata; - u32 mask; + netdev_features_t mask; if (copy_from_user(&edata, useraddr, sizeof(edata))) return -EFAULT; mask = ethtool_get_feature_mask(ethcmd); mask &= dev->hw_features; - if (mask) { - if (edata.data) - dev->wanted_features |= mask; - else - dev->wanted_features &= ~mask; + if (!mask) + return -EOPNOTSUPP; - __netdev_update_features(dev); - return 0; - } + if (edata.data) + dev->wanted_features |= mask; + else + dev->wanted_features &= ~mask; - /* Driver is not converted to ndo_fix_features or does not - * support changing this offload. In the latter case it won't - * have corresponding ethtool_ops field set. - * - * Following part is to be removed after all drivers advertise - * their changeable features in netdev->hw_features and stop - * using discrete offload setting ops. - */ + __netdev_update_features(dev); - switch (ethcmd) { - case ETHTOOL_STXCSUM: - return __ethtool_set_tx_csum(dev, edata.data); - case ETHTOOL_SRXCSUM: - return __ethtool_set_rx_csum(dev, edata.data); - case ETHTOOL_SSG: - return __ethtool_set_sg(dev, edata.data); - case ETHTOOL_STSO: - return __ethtool_set_tso(dev, edata.data); - case ETHTOOL_SUFO: - return __ethtool_set_ufo(dev, edata.data); - default: - return -EOPNOTSUPP; - } + return 0; +} + +#define ETH_ALL_FLAGS (ETH_FLAG_LRO | ETH_FLAG_RXVLAN | ETH_FLAG_TXVLAN | \ + ETH_FLAG_NTUPLE | ETH_FLAG_RXHASH) +#define ETH_ALL_FEATURES (NETIF_F_LRO | NETIF_F_HW_VLAN_RX | \ + NETIF_F_HW_VLAN_TX | NETIF_F_NTUPLE | NETIF_F_RXHASH) + +static u32 __ethtool_get_flags(struct net_device *dev) +{ + u32 flags = 0; + + if (dev->features & NETIF_F_LRO) flags |= ETH_FLAG_LRO; + if (dev->features & NETIF_F_HW_VLAN_RX) flags |= ETH_FLAG_RXVLAN; + if (dev->features & NETIF_F_HW_VLAN_TX) flags |= ETH_FLAG_TXVLAN; + if (dev->features & NETIF_F_NTUPLE) flags |= ETH_FLAG_NTUPLE; + if (dev->features & NETIF_F_RXHASH) flags |= ETH_FLAG_RXHASH; + + return flags; } -int __ethtool_set_flags(struct net_device *dev, u32 data) +static int __ethtool_set_flags(struct net_device *dev, u32 data) { - u32 changed; + netdev_features_t features = 0, changed; - if (data & ~flags_dup_features) + if (data & ~ETH_ALL_FLAGS) return -EINVAL; - /* legacy set_flags() op */ - if (dev->ethtool_ops->set_flags) { - if (unlikely(dev->hw_features & flags_dup_features)) - netdev_warn(dev, - "driver BUG: mixed hw_features and set_flags()\n"); - return dev->ethtool_ops->set_flags(dev, data); - } + if (data & ETH_FLAG_LRO) features |= NETIF_F_LRO; + if (data & ETH_FLAG_RXVLAN) features |= NETIF_F_HW_VLAN_RX; + if (data & ETH_FLAG_TXVLAN) features |= NETIF_F_HW_VLAN_TX; + if (data & ETH_FLAG_NTUPLE) features |= NETIF_F_NTUPLE; + if (data & ETH_FLAG_RXHASH) features |= NETIF_F_RXHASH; /* allow changing only bits set in hw_features */ - changed = (data ^ dev->features) & flags_dup_features; + changed = (features ^ dev->features) & ETH_ALL_FEATURES; if (changed & ~dev->hw_features) return (changed & dev->hw_features) ? -EINVAL : -EOPNOTSUPP; dev->wanted_features = - (dev->wanted_features & ~changed) | (data & dev->hw_features); + (dev->wanted_features & ~changed) | (features & changed); __netdev_update_features(dev); @@ -1231,81 +954,6 @@ static int ethtool_set_pauseparam(struct net_device *dev, void __user *useraddr) return dev->ethtool_ops->set_pauseparam(dev, &pauseparam); } -static int __ethtool_set_sg(struct net_device *dev, u32 data) -{ - int err; - - if (!dev->ethtool_ops->set_sg) - return -EOPNOTSUPP; - - if (data && !(dev->features & NETIF_F_ALL_CSUM)) - return -EINVAL; - - if (!data && dev->ethtool_ops->set_tso) { - err = dev->ethtool_ops->set_tso(dev, 0); - if (err) - return err; - } - - if (!data && dev->ethtool_ops->set_ufo) { - err = dev->ethtool_ops->set_ufo(dev, 0); - if (err) - return err; - } - return dev->ethtool_ops->set_sg(dev, data); -} - -static int __ethtool_set_tx_csum(struct net_device *dev, u32 data) -{ - int err; - - if (!dev->ethtool_ops->set_tx_csum) - return -EOPNOTSUPP; - - if (!data && dev->ethtool_ops->set_sg) { - err = __ethtool_set_sg(dev, 0); - if (err) - return err; - } - - return dev->ethtool_ops->set_tx_csum(dev, data); -} - -static int __ethtool_set_rx_csum(struct net_device *dev, u32 data) -{ - if (!dev->ethtool_ops->set_rx_csum) - return -EOPNOTSUPP; - - if (!data) - dev->features &= ~NETIF_F_GRO; - - return dev->ethtool_ops->set_rx_csum(dev, data); -} - -static int __ethtool_set_tso(struct net_device *dev, u32 data) -{ - if (!dev->ethtool_ops->set_tso) - return -EOPNOTSUPP; - - if (data && !(dev->features & NETIF_F_SG)) - return -EINVAL; - - return dev->ethtool_ops->set_tso(dev, data); -} - -static int __ethtool_set_ufo(struct net_device *dev, u32 data) -{ - if (!dev->ethtool_ops->set_ufo) - return -EOPNOTSUPP; - if (data && !(dev->features & NETIF_F_SG)) - return -EINVAL; - if (data && !((dev->features & NETIF_F_GEN_CSUM) || - (dev->features & (NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM)) - == (NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM))) - return -EINVAL; - return dev->ethtool_ops->set_ufo(dev, data); -} - static int ethtool_self_test(struct net_device *dev, char __user *useraddr) { struct ethtool_test test; @@ -1771,9 +1419,7 @@ int dev_ethtool(struct net *net, struct ifreq *ifr) break; case ETHTOOL_GFLAGS: rc = ethtool_get_value(dev, useraddr, ethcmd, - (dev->ethtool_ops->get_flags ? - dev->ethtool_ops->get_flags : - ethtool_op_get_flags)); + __ethtool_get_flags); break; case ETHTOOL_SFLAGS: rc = ethtool_set_value(dev, useraddr, __ethtool_set_flags); diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 039d51e..27d3fef 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -238,6 +238,7 @@ static void neigh_flush_dev(struct neigh_table *tbl, struct net_device *dev) it to safe state. */ skb_queue_purge(&n->arp_queue); + n->arp_queue_len_bytes = 0; n->output = neigh_blackhole; if (n->nud_state & NUD_VALID) n->nud_state = NUD_NOARP; @@ -702,6 +703,7 @@ void neigh_destroy(struct neighbour *neigh) printk(KERN_WARNING "Impossible event.\n"); skb_queue_purge(&neigh->arp_queue); + neigh->arp_queue_len_bytes = 0; dev_put(neigh->dev); neigh_parms_put(neigh->parms); @@ -842,6 +844,7 @@ static void neigh_invalidate(struct neighbour *neigh) write_lock(&neigh->lock); } skb_queue_purge(&neigh->arp_queue); + neigh->arp_queue_len_bytes = 0; } static void neigh_probe(struct neighbour *neigh) @@ -980,15 +983,20 @@ int __neigh_event_send(struct neighbour *neigh, struct sk_buff *skb) if (neigh->nud_state == NUD_INCOMPLETE) { if (skb) { - if (skb_queue_len(&neigh->arp_queue) >= - neigh->parms->queue_len) { + while (neigh->arp_queue_len_bytes + skb->truesize > + neigh->parms->queue_len_bytes) { struct sk_buff *buff; + buff = __skb_dequeue(&neigh->arp_queue); + if (!buff) + break; + neigh->arp_queue_len_bytes -= buff->truesize; kfree_skb(buff); NEIGH_CACHE_STAT_INC(neigh->tbl, unres_discards); } skb_dst_force(skb); __skb_queue_tail(&neigh->arp_queue, skb); + neigh->arp_queue_len_bytes += skb->truesize; } rc = 1; } @@ -1175,6 +1183,7 @@ int neigh_update(struct neighbour *neigh, const u8 *lladdr, u8 new, write_lock_bh(&neigh->lock); } skb_queue_purge(&neigh->arp_queue); + neigh->arp_queue_len_bytes = 0; } out: if (update_isrouter) { @@ -1747,7 +1756,11 @@ static int neightbl_fill_parms(struct sk_buff *skb, struct neigh_parms *parms) NLA_PUT_U32(skb, NDTPA_IFINDEX, parms->dev->ifindex); NLA_PUT_U32(skb, NDTPA_REFCNT, atomic_read(&parms->refcnt)); - NLA_PUT_U32(skb, NDTPA_QUEUE_LEN, parms->queue_len); + NLA_PUT_U32(skb, NDTPA_QUEUE_LENBYTES, parms->queue_len_bytes); + /* approximative value for deprecated QUEUE_LEN (in packets) */ + NLA_PUT_U32(skb, NDTPA_QUEUE_LEN, + DIV_ROUND_UP(parms->queue_len_bytes, + SKB_TRUESIZE(ETH_FRAME_LEN))); NLA_PUT_U32(skb, NDTPA_PROXY_QLEN, parms->proxy_qlen); NLA_PUT_U32(skb, NDTPA_APP_PROBES, parms->app_probes); NLA_PUT_U32(skb, NDTPA_UCAST_PROBES, parms->ucast_probes); @@ -1974,7 +1987,11 @@ static int neightbl_set(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) switch (i) { case NDTPA_QUEUE_LEN: - p->queue_len = nla_get_u32(tbp[i]); + p->queue_len_bytes = nla_get_u32(tbp[i]) * + SKB_TRUESIZE(ETH_FRAME_LEN); + break; + case NDTPA_QUEUE_LENBYTES: + p->queue_len_bytes = nla_get_u32(tbp[i]); break; case NDTPA_PROXY_QLEN: p->proxy_qlen = nla_get_u32(tbp[i]); @@ -2397,7 +2414,10 @@ static struct pneigh_entry *pneigh_get_next(struct seq_file *seq, struct net *net = seq_file_net(seq); struct neigh_table *tbl = state->tbl; - pn = pn->next; + do { + pn = pn->next; + } while (pn && !net_eq(pneigh_net(pn), net)); + while (!pn) { if (++state->bucket > PNEIGH_HASHMASK) break; @@ -2635,117 +2655,158 @@ EXPORT_SYMBOL(neigh_app_ns); #ifdef CONFIG_SYSCTL -#define NEIGH_VARS_MAX 19 +static int proc_unres_qlen(ctl_table *ctl, int write, void __user *buffer, + size_t *lenp, loff_t *ppos) +{ + int size, ret; + ctl_table tmp = *ctl; + + tmp.data = &size; + size = DIV_ROUND_UP(*(int *)ctl->data, SKB_TRUESIZE(ETH_FRAME_LEN)); + ret = proc_dointvec(&tmp, write, buffer, lenp, ppos); + if (write && !ret) + *(int *)ctl->data = size * SKB_TRUESIZE(ETH_FRAME_LEN); + return ret; +} + +enum { + NEIGH_VAR_MCAST_PROBE, + NEIGH_VAR_UCAST_PROBE, + NEIGH_VAR_APP_PROBE, + NEIGH_VAR_RETRANS_TIME, + NEIGH_VAR_BASE_REACHABLE_TIME, + NEIGH_VAR_DELAY_PROBE_TIME, + NEIGH_VAR_GC_STALETIME, + NEIGH_VAR_QUEUE_LEN, + NEIGH_VAR_QUEUE_LEN_BYTES, + NEIGH_VAR_PROXY_QLEN, + NEIGH_VAR_ANYCAST_DELAY, + NEIGH_VAR_PROXY_DELAY, + NEIGH_VAR_LOCKTIME, + NEIGH_VAR_RETRANS_TIME_MS, + NEIGH_VAR_BASE_REACHABLE_TIME_MS, + NEIGH_VAR_GC_INTERVAL, + NEIGH_VAR_GC_THRESH1, + NEIGH_VAR_GC_THRESH2, + NEIGH_VAR_GC_THRESH3, + NEIGH_VAR_MAX +}; static struct neigh_sysctl_table { struct ctl_table_header *sysctl_header; - struct ctl_table neigh_vars[NEIGH_VARS_MAX]; + struct ctl_table neigh_vars[NEIGH_VAR_MAX + 1]; char *dev_name; } neigh_sysctl_template __read_mostly = { .neigh_vars = { - { + [NEIGH_VAR_MCAST_PROBE] = { .procname = "mcast_solicit", .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, - { + [NEIGH_VAR_UCAST_PROBE] = { .procname = "ucast_solicit", .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, - { + [NEIGH_VAR_APP_PROBE] = { .procname = "app_solicit", .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, - { + [NEIGH_VAR_RETRANS_TIME] = { .procname = "retrans_time", .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_userhz_jiffies, }, - { + [NEIGH_VAR_BASE_REACHABLE_TIME] = { .procname = "base_reachable_time", .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, - { + [NEIGH_VAR_DELAY_PROBE_TIME] = { .procname = "delay_first_probe_time", .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, - { + [NEIGH_VAR_GC_STALETIME] = { .procname = "gc_stale_time", .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, - { + [NEIGH_VAR_QUEUE_LEN] = { .procname = "unres_qlen", .maxlen = sizeof(int), .mode = 0644, + .proc_handler = proc_unres_qlen, + }, + [NEIGH_VAR_QUEUE_LEN_BYTES] = { + .procname = "unres_qlen_bytes", + .maxlen = sizeof(int), + .mode = 0644, .proc_handler = proc_dointvec, }, - { + [NEIGH_VAR_PROXY_QLEN] = { .procname = "proxy_qlen", .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, - { + [NEIGH_VAR_ANYCAST_DELAY] = { .procname = "anycast_delay", .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_userhz_jiffies, }, - { + [NEIGH_VAR_PROXY_DELAY] = { .procname = "proxy_delay", .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_userhz_jiffies, }, - { + [NEIGH_VAR_LOCKTIME] = { .procname = "locktime", .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_userhz_jiffies, }, - { + [NEIGH_VAR_RETRANS_TIME_MS] = { .procname = "retrans_time_ms", .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_ms_jiffies, }, - { + [NEIGH_VAR_BASE_REACHABLE_TIME_MS] = { .procname = "base_reachable_time_ms", .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_ms_jiffies, }, - { + [NEIGH_VAR_GC_INTERVAL] = { .procname = "gc_interval", .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, - { + [NEIGH_VAR_GC_THRESH1] = { .procname = "gc_thresh1", .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, - { + [NEIGH_VAR_GC_THRESH2] = { .procname = "gc_thresh2", .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, - { + [NEIGH_VAR_GC_THRESH3] = { .procname = "gc_thresh3", .maxlen = sizeof(int), .mode = 0644, @@ -2778,47 +2839,49 @@ int neigh_sysctl_register(struct net_device *dev, struct neigh_parms *p, if (!t) goto err; - t->neigh_vars[0].data = &p->mcast_probes; - t->neigh_vars[1].data = &p->ucast_probes; - t->neigh_vars[2].data = &p->app_probes; - t->neigh_vars[3].data = &p->retrans_time; - t->neigh_vars[4].data = &p->base_reachable_time; - t->neigh_vars[5].data = &p->delay_probe_time; - t->neigh_vars[6].data = &p->gc_staletime; - t->neigh_vars[7].data = &p->queue_len; - t->neigh_vars[8].data = &p->proxy_qlen; - t->neigh_vars[9].data = &p->anycast_delay; - t->neigh_vars[10].data = &p->proxy_delay; - t->neigh_vars[11].data = &p->locktime; - t->neigh_vars[12].data = &p->retrans_time; - t->neigh_vars[13].data = &p->base_reachable_time; + t->neigh_vars[NEIGH_VAR_MCAST_PROBE].data = &p->mcast_probes; + t->neigh_vars[NEIGH_VAR_UCAST_PROBE].data = &p->ucast_probes; + t->neigh_vars[NEIGH_VAR_APP_PROBE].data = &p->app_probes; + t->neigh_vars[NEIGH_VAR_RETRANS_TIME].data = &p->retrans_time; + t->neigh_vars[NEIGH_VAR_BASE_REACHABLE_TIME].data = &p->base_reachable_time; + t->neigh_vars[NEIGH_VAR_DELAY_PROBE_TIME].data = &p->delay_probe_time; + t->neigh_vars[NEIGH_VAR_GC_STALETIME].data = &p->gc_staletime; + t->neigh_vars[NEIGH_VAR_QUEUE_LEN].data = &p->queue_len_bytes; + t->neigh_vars[NEIGH_VAR_QUEUE_LEN_BYTES].data = &p->queue_len_bytes; + t->neigh_vars[NEIGH_VAR_PROXY_QLEN].data = &p->proxy_qlen; + t->neigh_vars[NEIGH_VAR_ANYCAST_DELAY].data = &p->anycast_delay; + t->neigh_vars[NEIGH_VAR_PROXY_DELAY].data = &p->proxy_delay; + t->neigh_vars[NEIGH_VAR_LOCKTIME].data = &p->locktime; + t->neigh_vars[NEIGH_VAR_RETRANS_TIME_MS].data = &p->retrans_time; + t->neigh_vars[NEIGH_VAR_BASE_REACHABLE_TIME_MS].data = &p->base_reachable_time; if (dev) { dev_name_source = dev->name; /* Terminate the table early */ - memset(&t->neigh_vars[14], 0, sizeof(t->neigh_vars[14])); + memset(&t->neigh_vars[NEIGH_VAR_GC_INTERVAL], 0, + sizeof(t->neigh_vars[NEIGH_VAR_GC_INTERVAL])); } else { dev_name_source = neigh_path[NEIGH_CTL_PATH_DEV].procname; - t->neigh_vars[14].data = (int *)(p + 1); - t->neigh_vars[15].data = (int *)(p + 1) + 1; - t->neigh_vars[16].data = (int *)(p + 1) + 2; - t->neigh_vars[17].data = (int *)(p + 1) + 3; + t->neigh_vars[NEIGH_VAR_GC_INTERVAL].data = (int *)(p + 1); + t->neigh_vars[NEIGH_VAR_GC_THRESH1].data = (int *)(p + 1) + 1; + t->neigh_vars[NEIGH_VAR_GC_THRESH2].data = (int *)(p + 1) + 2; + t->neigh_vars[NEIGH_VAR_GC_THRESH3].data = (int *)(p + 1) + 3; } if (handler) { /* RetransTime */ - t->neigh_vars[3].proc_handler = handler; - t->neigh_vars[3].extra1 = dev; + t->neigh_vars[NEIGH_VAR_RETRANS_TIME].proc_handler = handler; + t->neigh_vars[NEIGH_VAR_RETRANS_TIME].extra1 = dev; /* ReachableTime */ - t->neigh_vars[4].proc_handler = handler; - t->neigh_vars[4].extra1 = dev; + t->neigh_vars[NEIGH_VAR_BASE_REACHABLE_TIME].proc_handler = handler; + t->neigh_vars[NEIGH_VAR_BASE_REACHABLE_TIME].extra1 = dev; /* RetransTime (in milliseconds)*/ - t->neigh_vars[12].proc_handler = handler; - t->neigh_vars[12].extra1 = dev; + t->neigh_vars[NEIGH_VAR_RETRANS_TIME_MS].proc_handler = handler; + t->neigh_vars[NEIGH_VAR_RETRANS_TIME_MS].extra1 = dev; /* ReachableTime (in milliseconds) */ - t->neigh_vars[13].proc_handler = handler; - t->neigh_vars[13].extra1 = dev; + t->neigh_vars[NEIGH_VAR_BASE_REACHABLE_TIME_MS].proc_handler = handler; + t->neigh_vars[NEIGH_VAR_BASE_REACHABLE_TIME_MS].extra1 = dev; } t->dev_name = kstrdup(dev_name_source, GFP_KERNEL); diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index c71c434..db6c2f8 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -606,9 +606,12 @@ static ssize_t store_rps_map(struct netdev_rx_queue *queue, rcu_assign_pointer(queue->rps_map, map); spin_unlock(&rps_map_lock); - if (old_map) + if (map) + jump_label_inc(&rps_needed); + if (old_map) { kfree_rcu(old_map, rcu); - + jump_label_dec(&rps_needed); + } free_cpumask_var(mask); return len; } @@ -780,7 +783,7 @@ net_rx_queue_update_kobjects(struct net_device *net, int old_num, int new_num) #endif } -#ifdef CONFIG_XPS +#ifdef CONFIG_SYSFS /* * netdev_queue sysfs structures and functions. */ @@ -826,6 +829,23 @@ static const struct sysfs_ops netdev_queue_sysfs_ops = { .store = netdev_queue_attr_store, }; +static ssize_t show_trans_timeout(struct netdev_queue *queue, + struct netdev_queue_attribute *attribute, + char *buf) +{ + unsigned long trans_timeout; + + spin_lock_irq(&queue->_xmit_lock); + trans_timeout = queue->trans_timeout; + spin_unlock_irq(&queue->_xmit_lock); + + return sprintf(buf, "%lu", trans_timeout); +} + +static struct netdev_queue_attribute queue_trans_timeout = + __ATTR(tx_timeout, S_IRUGO, show_trans_timeout, NULL); + +#ifdef CONFIG_XPS static inline unsigned int get_netdev_queue_index(struct netdev_queue *queue) { struct net_device *dev = queue->dev; @@ -901,7 +921,7 @@ static ssize_t store_xps_map(struct netdev_queue *queue, struct xps_map *map, *new_map; struct xps_dev_maps *dev_maps, *new_dev_maps; int nonempty = 0; - int numa_node = -2; + int numa_node_id = -2; if (!capable(CAP_NET_ADMIN)) return -EPERM; @@ -944,10 +964,10 @@ static ssize_t store_xps_map(struct netdev_queue *queue, need_set = cpumask_test_cpu(cpu, mask) && cpu_online(cpu); #ifdef CONFIG_NUMA if (need_set) { - if (numa_node == -2) - numa_node = cpu_to_node(cpu); - else if (numa_node != cpu_to_node(cpu)) - numa_node = -1; + if (numa_node_id == -2) + numa_node_id = cpu_to_node(cpu); + else if (numa_node_id != cpu_to_node(cpu)) + numa_node_id = -1; } #endif if (need_set && pos >= map_len) { @@ -997,7 +1017,7 @@ static ssize_t store_xps_map(struct netdev_queue *queue, if (dev_maps) kfree_rcu(dev_maps, rcu); - netdev_queue_numa_node_write(queue, (numa_node >= 0) ? numa_node : + netdev_queue_numa_node_write(queue, (numa_node_id >= 0) ? numa_node_id : NUMA_NO_NODE); mutex_unlock(&xps_map_mutex); @@ -1020,12 +1040,17 @@ error: static struct netdev_queue_attribute xps_cpus_attribute = __ATTR(xps_cpus, S_IRUGO | S_IWUSR, show_xps_map, store_xps_map); +#endif /* CONFIG_XPS */ static struct attribute *netdev_queue_default_attrs[] = { + &queue_trans_timeout.attr, +#ifdef CONFIG_XPS &xps_cpus_attribute.attr, +#endif NULL }; +#ifdef CONFIG_XPS static void netdev_queue_release(struct kobject *kobj) { struct netdev_queue *queue = to_netdev_queue(kobj); @@ -1076,10 +1101,13 @@ static void netdev_queue_release(struct kobject *kobj) memset(kobj, 0, sizeof(*kobj)); dev_put(queue->dev); } +#endif /* CONFIG_XPS */ static struct kobj_type netdev_queue_ktype = { .sysfs_ops = &netdev_queue_sysfs_ops, +#ifdef CONFIG_XPS .release = netdev_queue_release, +#endif .default_attrs = netdev_queue_default_attrs, }; @@ -1102,12 +1130,12 @@ static int netdev_queue_add_kobject(struct net_device *net, int index) return error; } -#endif /* CONFIG_XPS */ +#endif /* CONFIG_SYSFS */ int netdev_queue_update_kobjects(struct net_device *net, int old_num, int new_num) { -#ifdef CONFIG_XPS +#ifdef CONFIG_SYSFS int i; int error = 0; @@ -1125,14 +1153,14 @@ netdev_queue_update_kobjects(struct net_device *net, int old_num, int new_num) return error; #else return 0; -#endif +#endif /* CONFIG_SYSFS */ } static int register_queue_kobjects(struct net_device *net) { int error = 0, txq = 0, rxq = 0, real_rx = 0, real_tx = 0; -#if defined(CONFIG_RPS) || defined(CONFIG_XPS) +#ifdef CONFIG_SYSFS net->queues_kset = kset_create_and_add("queues", NULL, &net->dev.kobj); if (!net->queues_kset) @@ -1173,7 +1201,7 @@ static void remove_queue_kobjects(struct net_device *net) net_rx_queue_update_kobjects(net, real_rx, 0); netdev_queue_update_kobjects(net, real_tx, 0); -#if defined(CONFIG_RPS) || defined(CONFIG_XPS) +#ifdef CONFIG_SYSFS kset_unregister(net->queues_kset); #endif } diff --git a/net/core/netpoll.c b/net/core/netpoll.c index cf64c1f..1a7d8e2 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -422,6 +422,7 @@ static void arp_reply(struct sk_buff *skb) struct sk_buff *send_skb; struct netpoll *np, *tmp; unsigned long flags; + int hlen, tlen; int hits = 0; if (list_empty(&npinfo->rx_np)) @@ -479,8 +480,9 @@ static void arp_reply(struct sk_buff *skb) if (tip != np->local_ip) continue; - send_skb = find_skb(np, size + LL_ALLOCATED_SPACE(np->dev), - LL_RESERVED_SPACE(np->dev)); + hlen = LL_RESERVED_SPACE(np->dev); + tlen = np->dev->needed_tailroom; + send_skb = find_skb(np, size + hlen + tlen, hlen); if (!send_skb) continue; diff --git a/net/core/netprio_cgroup.c b/net/core/netprio_cgroup.c new file mode 100644 index 0000000..3a9fd48 --- /dev/null +++ b/net/core/netprio_cgroup.c @@ -0,0 +1,344 @@ +/* + * net/core/netprio_cgroup.c Priority Control Group + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + * + * Authors: Neil Horman <nhorman@tuxdriver.com> + */ + +#include <linux/module.h> +#include <linux/slab.h> +#include <linux/types.h> +#include <linux/string.h> +#include <linux/errno.h> +#include <linux/skbuff.h> +#include <linux/cgroup.h> +#include <linux/rcupdate.h> +#include <linux/atomic.h> +#include <net/rtnetlink.h> +#include <net/pkt_cls.h> +#include <net/sock.h> +#include <net/netprio_cgroup.h> + +static struct cgroup_subsys_state *cgrp_create(struct cgroup_subsys *ss, + struct cgroup *cgrp); +static void cgrp_destroy(struct cgroup_subsys *ss, struct cgroup *cgrp); +static int cgrp_populate(struct cgroup_subsys *ss, struct cgroup *cgrp); + +struct cgroup_subsys net_prio_subsys = { + .name = "net_prio", + .create = cgrp_create, + .destroy = cgrp_destroy, + .populate = cgrp_populate, +#ifdef CONFIG_NETPRIO_CGROUP + .subsys_id = net_prio_subsys_id, +#endif + .module = THIS_MODULE +}; + +#define PRIOIDX_SZ 128 + +static unsigned long prioidx_map[PRIOIDX_SZ]; +static DEFINE_SPINLOCK(prioidx_map_lock); +static atomic_t max_prioidx = ATOMIC_INIT(0); + +static inline struct cgroup_netprio_state *cgrp_netprio_state(struct cgroup *cgrp) +{ + return container_of(cgroup_subsys_state(cgrp, net_prio_subsys_id), + struct cgroup_netprio_state, css); +} + +static int get_prioidx(u32 *prio) +{ + unsigned long flags; + u32 prioidx; + + spin_lock_irqsave(&prioidx_map_lock, flags); + prioidx = find_first_zero_bit(prioidx_map, sizeof(unsigned long) * PRIOIDX_SZ); + set_bit(prioidx, prioidx_map); + spin_unlock_irqrestore(&prioidx_map_lock, flags); + if (prioidx == sizeof(unsigned long) * PRIOIDX_SZ) + return -ENOSPC; + + atomic_set(&max_prioidx, prioidx); + *prio = prioidx; + return 0; +} + +static void put_prioidx(u32 idx) +{ + unsigned long flags; + + spin_lock_irqsave(&prioidx_map_lock, flags); + clear_bit(idx, prioidx_map); + spin_unlock_irqrestore(&prioidx_map_lock, flags); +} + +static void extend_netdev_table(struct net_device *dev, u32 new_len) +{ + size_t new_size = sizeof(struct netprio_map) + + ((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); + + if (!new_priomap) { + printk(KERN_WARNING "Unable to alloc new priomap!\n"); + return; + } + + for (i = 0; + old_priomap && (i < old_priomap->priomap_len); + i++) + new_priomap->priomap[i] = old_priomap->priomap[i]; + + new_priomap->priomap_len = new_len; + + rcu_assign_pointer(dev->priomap, new_priomap); + if (old_priomap) + kfree_rcu(old_priomap, rcu); +} + +static void update_netdev_tables(void) +{ + struct net_device *dev; + u32 max_len = atomic_read(&max_prioidx); + struct netprio_map *map; + + rtnl_lock(); + for_each_netdev(&init_net, dev) { + map = rtnl_dereference(dev->priomap); + if ((!map) || + (map->priomap_len < max_len)) + extend_netdev_table(dev, max_len); + } + rtnl_unlock(); +} + +static struct cgroup_subsys_state *cgrp_create(struct cgroup_subsys *ss, + struct cgroup *cgrp) +{ + struct cgroup_netprio_state *cs; + int ret; + + cs = kzalloc(sizeof(*cs), GFP_KERNEL); + if (!cs) + return ERR_PTR(-ENOMEM); + + if (cgrp->parent && cgrp_netprio_state(cgrp->parent)->prioidx) { + kfree(cs); + return ERR_PTR(-EINVAL); + } + + ret = get_prioidx(&cs->prioidx); + if (ret != 0) { + printk(KERN_WARNING "No space in priority index array\n"); + kfree(cs); + return ERR_PTR(ret); + } + + return &cs->css; +} + +static void cgrp_destroy(struct cgroup_subsys *ss, struct cgroup *cgrp) +{ + struct cgroup_netprio_state *cs; + struct net_device *dev; + struct netprio_map *map; + + cs = cgrp_netprio_state(cgrp); + rtnl_lock(); + for_each_netdev(&init_net, dev) { + map = rtnl_dereference(dev->priomap); + if (map) + map->priomap[cs->prioidx] = 0; + } + rtnl_unlock(); + put_prioidx(cs->prioidx); + kfree(cs); +} + +static u64 read_prioidx(struct cgroup *cgrp, struct cftype *cft) +{ + return (u64)cgrp_netprio_state(cgrp)->prioidx; +} + +static int read_priomap(struct cgroup *cont, struct cftype *cft, + struct cgroup_map_cb *cb) +{ + struct net_device *dev; + u32 prioidx = cgrp_netprio_state(cont)->prioidx; + u32 priority; + struct netprio_map *map; + + rcu_read_lock(); + for_each_netdev_rcu(&init_net, dev) { + map = rcu_dereference(dev->priomap); + priority = map ? map->priomap[prioidx] : 0; + cb->fill(cb, dev->name, priority); + } + rcu_read_unlock(); + return 0; +} + +static int write_priomap(struct cgroup *cgrp, struct cftype *cft, + const char *buffer) +{ + char *devname = kstrdup(buffer, GFP_KERNEL); + int ret = -EINVAL; + u32 prioidx = cgrp_netprio_state(cgrp)->prioidx; + unsigned long priority; + char *priostr; + struct net_device *dev; + struct netprio_map *map; + + if (!devname) + return -ENOMEM; + + /* + * Minimally sized valid priomap string + */ + if (strlen(devname) < 3) + goto out_free_devname; + + priostr = strstr(devname, " "); + if (!priostr) + goto out_free_devname; + + /* + *Separate the devname from the associated priority + *and advance the priostr poitner to the priority value + */ + *priostr = '\0'; + priostr++; + + /* + * If the priostr points to NULL, we're at the end of the passed + * in string, and its not a valid write + */ + if (*priostr == '\0') + goto out_free_devname; + + ret = kstrtoul(priostr, 10, &priority); + if (ret < 0) + goto out_free_devname; + + ret = -ENODEV; + + dev = dev_get_by_name(&init_net, devname); + if (!dev) + goto out_free_devname; + + update_netdev_tables(); + ret = 0; + rcu_read_lock(); + map = rcu_dereference(dev->priomap); + if (map) + map->priomap[prioidx] = priority; + rcu_read_unlock(); + dev_put(dev); + +out_free_devname: + kfree(devname); + return ret; +} + +static struct cftype ss_files[] = { + { + .name = "prioidx", + .read_u64 = read_prioidx, + }, + { + .name = "ifpriomap", + .read_map = read_priomap, + .write_string = write_priomap, + }, +}; + +static int cgrp_populate(struct cgroup_subsys *ss, struct cgroup *cgrp) +{ + return cgroup_add_files(cgrp, ss, ss_files, ARRAY_SIZE(ss_files)); +} + +static int netprio_device_event(struct notifier_block *unused, + unsigned long event, void *ptr) +{ + struct net_device *dev = ptr; + struct netprio_map *old; + u32 max_len = atomic_read(&max_prioidx); + + /* + * Note this is called with rtnl_lock held so we have update side + * protection on our rcu assignments + */ + + switch (event) { + + case NETDEV_REGISTER: + if (max_len) + extend_netdev_table(dev, max_len); + break; + case NETDEV_UNREGISTER: + old = rtnl_dereference(dev->priomap); + RCU_INIT_POINTER(dev->priomap, NULL); + if (old) + kfree_rcu(old, rcu); + break; + } + return NOTIFY_DONE; +} + +static struct notifier_block netprio_device_notifier = { + .notifier_call = netprio_device_event +}; + +static int __init init_cgroup_netprio(void) +{ + int ret; + + 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); + +out: + return ret; +} + +static void __exit exit_cgroup_netprio(void) +{ + struct netprio_map *old; + struct net_device *dev; + + unregister_netdevice_notifier(&netprio_device_notifier); + + 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); + RCU_INIT_POINTER(dev->priomap, NULL); + if (old) + kfree_rcu(old, rcu); + } + rtnl_unlock(); +} + +module_init(init_cgroup_netprio); +module_exit(exit_cgroup_netprio); +MODULE_LICENSE("GPL v2"); diff --git a/net/core/pktgen.c b/net/core/pktgen.c index 0001c24..aa53a35 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -1304,7 +1304,7 @@ static ssize_t pktgen_if_write(struct file *file, scan_ip6(buf, pkt_dev->in6_daddr.s6_addr); snprintf(buf, sizeof(buf), "%pI6c", &pkt_dev->in6_daddr); - ipv6_addr_copy(&pkt_dev->cur_in6_daddr, &pkt_dev->in6_daddr); + pkt_dev->cur_in6_daddr = pkt_dev->in6_daddr; if (debug) printk(KERN_DEBUG "pktgen: dst6 set to: %s\n", buf); @@ -1327,8 +1327,7 @@ static ssize_t pktgen_if_write(struct file *file, scan_ip6(buf, pkt_dev->min_in6_daddr.s6_addr); snprintf(buf, sizeof(buf), "%pI6c", &pkt_dev->min_in6_daddr); - ipv6_addr_copy(&pkt_dev->cur_in6_daddr, - &pkt_dev->min_in6_daddr); + pkt_dev->cur_in6_daddr = pkt_dev->min_in6_daddr; if (debug) printk(KERN_DEBUG "pktgen: dst6_min set to: %s\n", buf); @@ -1371,7 +1370,7 @@ static ssize_t pktgen_if_write(struct file *file, scan_ip6(buf, pkt_dev->in6_saddr.s6_addr); snprintf(buf, sizeof(buf), "%pI6c", &pkt_dev->in6_saddr); - ipv6_addr_copy(&pkt_dev->cur_in6_saddr, &pkt_dev->in6_saddr); + pkt_dev->cur_in6_saddr = pkt_dev->in6_saddr; if (debug) printk(KERN_DEBUG "pktgen: src6 set to: %s\n", buf); @@ -2079,9 +2078,7 @@ static void pktgen_setup_inject(struct pktgen_dev *pkt_dev) ifp = ifp->if_next) { if (ifp->scope == IFA_LINK && !(ifp->flags & IFA_F_TENTATIVE)) { - ipv6_addr_copy(&pkt_dev-> - cur_in6_saddr, - &ifp->addr); + pkt_dev->cur_in6_saddr = ifp->addr; err = 0; break; } @@ -2958,8 +2955,8 @@ static struct sk_buff *fill_packet_ipv6(struct net_device *odev, iph->payload_len = htons(sizeof(struct udphdr) + datalen); iph->nexthdr = IPPROTO_UDP; - ipv6_addr_copy(&iph->daddr, &pkt_dev->cur_in6_daddr); - ipv6_addr_copy(&iph->saddr, &pkt_dev->cur_in6_saddr); + iph->daddr = pkt_dev->cur_in6_daddr; + iph->saddr = pkt_dev->cur_in6_saddr; skb->mac_header = (skb->network_header - ETH_HLEN - pkt_dev->pkt_overhead); diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 06438f9..678ae4e 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -245,6 +245,55 @@ nodata: EXPORT_SYMBOL(__alloc_skb); /** + * build_skb - build a network buffer + * @data: data buffer provided by caller + * + * Allocate a new &sk_buff. Caller provides space holding head and + * skb_shared_info. @data must have been allocated by kmalloc() + * The return is the new skb buffer. + * On a failure the return is %NULL, and @data is not freed. + * Notes : + * Before IO, driver allocates only data buffer where NIC put incoming frame + * Driver should add room at head (NET_SKB_PAD) and + * MUST add room at tail (SKB_DATA_ALIGN(skb_shared_info)) + * After IO, driver calls build_skb(), to allocate sk_buff and populate it + * before giving packet to stack. + * RX rings only contains data buffers, not full skbs. + */ +struct sk_buff *build_skb(void *data) +{ + struct skb_shared_info *shinfo; + struct sk_buff *skb; + unsigned int size; + + skb = kmem_cache_alloc(skbuff_head_cache, GFP_ATOMIC); + if (!skb) + return NULL; + + size = ksize(data) - SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); + + memset(skb, 0, offsetof(struct sk_buff, tail)); + skb->truesize = SKB_TRUESIZE(size); + atomic_set(&skb->users, 1); + skb->head = data; + skb->data = data; + skb_reset_tail_pointer(skb); + skb->end = skb->tail + size; +#ifdef NET_SKBUFF_DATA_USES_OFFSET + skb->mac_header = ~0U; +#endif + + /* make sure we initialize shinfo sequentially */ + shinfo = skb_shinfo(skb); + memset(shinfo, 0, offsetof(struct skb_shared_info, dataref)); + atomic_set(&shinfo->dataref, 1); + kmemcheck_annotate_variable(shinfo->destructor_arg); + + return skb; +} +EXPORT_SYMBOL(build_skb); + +/** * __netdev_alloc_skb - allocate an skbuff for rx on a specific device * @dev: network device to receive on * @length: length to allocate @@ -2230,7 +2279,7 @@ static int skb_prepare_for_shift(struct sk_buff *skb) * @shiftlen: shift up to this many bytes * * Attempts to shift up to shiftlen worth of bytes, which may be less than - * the length of the skb, from tgt to skb. Returns number bytes shifted. + * the length of the skb, from skb to tgt. Returns number bytes shifted. * It's up to caller to free skb if everything was shifted. * * If @tgt runs out of frags, the whole operation is aborted. @@ -2621,7 +2670,7 @@ EXPORT_SYMBOL_GPL(skb_pull_rcsum); * a pointer to the first in a list of new skbs for the segments. * In case of error it returns ERR_PTR(err). */ -struct sk_buff *skb_segment(struct sk_buff *skb, u32 features) +struct sk_buff *skb_segment(struct sk_buff *skb, netdev_features_t features) { struct sk_buff *segs = NULL; struct sk_buff *tail = NULL; diff --git a/net/core/sock.c b/net/core/sock.c index cbdf51c..1606913 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -125,6 +125,7 @@ #include <net/xfrm.h> #include <linux/ipsec.h> #include <net/cls_cgroup.h> +#include <net/netprio_cgroup.h> #include <linux/filter.h> @@ -221,10 +222,16 @@ __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) && !defined(CONFIG_NET_CLS_CGROUP) +#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 static int sock_set_timeout(long *timeo_p, char __user *optval, int optlen) { @@ -1120,6 +1127,18 @@ void sock_update_classid(struct sock *sk) sk->sk_classid = classid; } EXPORT_SYMBOL(sock_update_classid); + +void sock_update_netprioidx(struct sock *sk) +{ + struct cgroup_netprio_state *state; + if (in_interrupt()) + return; + rcu_read_lock(); + state = task_netprio_state(current); + sk->sk_cgrp_prioidx = state ? state->prioidx : 0; + rcu_read_unlock(); +} +EXPORT_SYMBOL_GPL(sock_update_netprioidx); #endif /** @@ -1147,6 +1166,7 @@ struct sock *sk_alloc(struct net *net, int family, gfp_t priority, atomic_set(&sk->sk_wmem_alloc, 1); sock_update_classid(sk); + sock_update_netprioidx(sk); } return sk; @@ -1213,7 +1233,14 @@ void sk_release_kernel(struct sock *sk) } EXPORT_SYMBOL(sk_release_kernel); -struct sock *sk_clone(const struct sock *sk, const gfp_t priority) +/** + * sk_clone_lock - clone a socket, and lock its clone + * @sk: the socket to clone + * @priority: for allocation (%GFP_KERNEL, %GFP_ATOMIC, etc) + * + * Caller must unlock socket even in error path (bh_unlock_sock(newsk)) + */ +struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority) { struct sock *newsk; @@ -1306,7 +1333,7 @@ struct sock *sk_clone(const struct sock *sk, const gfp_t priority) out: return newsk; } -EXPORT_SYMBOL_GPL(sk_clone); +EXPORT_SYMBOL_GPL(sk_clone_lock); void sk_setup_caps(struct sock *sk, struct dst_entry *dst) { diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c index 77a65f0..d05559d 100644 --- a/net/core/sysctl_net_core.c +++ b/net/core/sysctl_net_core.c @@ -68,8 +68,13 @@ static int rps_sock_flow_sysctl(ctl_table *table, int write, if (sock_table != orig_sock_table) { rcu_assign_pointer(rps_sock_flow_table, sock_table); - synchronize_rcu(); - vfree(orig_sock_table); + if (sock_table) + jump_label_inc(&rps_needed); + if (orig_sock_table) { + jump_label_dec(&rps_needed); + synchronize_rcu(); + vfree(orig_sock_table); + } } } diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c index 90a919a..3f4e541 100644 --- a/net/dccp/ipv4.c +++ b/net/dccp/ipv4.c @@ -111,6 +111,7 @@ int dccp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) rt = ip_route_newports(fl4, rt, orig_sport, orig_dport, inet->inet_sport, inet->inet_dport, sk); if (IS_ERR(rt)) { + err = PTR_ERR(rt); rt = NULL; goto failure; } diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index 17ee85c..ce903f7 100644 --- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -150,8 +150,8 @@ static void dccp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, */ memset(&fl6, 0, sizeof(fl6)); fl6.flowi6_proto = IPPROTO_DCCP; - ipv6_addr_copy(&fl6.daddr, &np->daddr); - ipv6_addr_copy(&fl6.saddr, &np->saddr); + fl6.daddr = np->daddr; + fl6.saddr = np->saddr; fl6.flowi6_oif = sk->sk_bound_dev_if; fl6.fl6_dport = inet->inet_dport; fl6.fl6_sport = inet->inet_sport; @@ -244,8 +244,8 @@ static int dccp_v6_send_response(struct sock *sk, struct request_sock *req, memset(&fl6, 0, sizeof(fl6)); fl6.flowi6_proto = IPPROTO_DCCP; - ipv6_addr_copy(&fl6.daddr, &ireq6->rmt_addr); - ipv6_addr_copy(&fl6.saddr, &ireq6->loc_addr); + fl6.daddr = ireq6->rmt_addr; + fl6.saddr = ireq6->loc_addr; fl6.flowlabel = 0; fl6.flowi6_oif = ireq6->iif; fl6.fl6_dport = inet_rsk(req)->rmt_port; @@ -270,7 +270,7 @@ static int dccp_v6_send_response(struct sock *sk, struct request_sock *req, dh->dccph_checksum = dccp_v6_csum_finish(skb, &ireq6->loc_addr, &ireq6->rmt_addr); - ipv6_addr_copy(&fl6.daddr, &ireq6->rmt_addr); + fl6.daddr = ireq6->rmt_addr; err = ip6_xmit(sk, skb, &fl6, opt, np->tclass); err = net_xmit_eval(err); } @@ -313,8 +313,8 @@ static void dccp_v6_ctl_send_reset(struct sock *sk, struct sk_buff *rxskb) &rxip6h->daddr); memset(&fl6, 0, sizeof(fl6)); - ipv6_addr_copy(&fl6.daddr, &rxip6h->saddr); - ipv6_addr_copy(&fl6.saddr, &rxip6h->daddr); + fl6.daddr = rxip6h->saddr; + fl6.saddr = rxip6h->daddr; fl6.flowi6_proto = IPPROTO_DCCP; fl6.flowi6_oif = inet6_iif(rxskb); @@ -419,8 +419,8 @@ static int dccp_v6_conn_request(struct sock *sk, struct sk_buff *skb) goto drop_and_free; ireq6 = inet6_rsk(req); - ipv6_addr_copy(&ireq6->rmt_addr, &ipv6_hdr(skb)->saddr); - ipv6_addr_copy(&ireq6->loc_addr, &ipv6_hdr(skb)->daddr); + ireq6->rmt_addr = ipv6_hdr(skb)->saddr; + ireq6->loc_addr = ipv6_hdr(skb)->daddr; if (ipv6_opt_accepted(sk, skb) || np->rxopt.bits.rxinfo || np->rxopt.bits.rxoinfo || @@ -491,7 +491,7 @@ static struct sock *dccp_v6_request_recv_sock(struct sock *sk, ipv6_addr_set_v4mapped(newinet->inet_saddr, &newnp->saddr); - ipv6_addr_copy(&newnp->rcv_saddr, &newnp->saddr); + newnp->rcv_saddr = newnp->saddr; inet_csk(newsk)->icsk_af_ops = &dccp_ipv6_mapped; newsk->sk_backlog_rcv = dccp_v4_do_rcv; @@ -526,9 +526,9 @@ static struct sock *dccp_v6_request_recv_sock(struct sock *sk, memset(&fl6, 0, sizeof(fl6)); fl6.flowi6_proto = IPPROTO_DCCP; - ipv6_addr_copy(&fl6.daddr, &ireq6->rmt_addr); + fl6.daddr = ireq6->rmt_addr; final_p = fl6_update_dst(&fl6, opt, &final); - ipv6_addr_copy(&fl6.saddr, &ireq6->loc_addr); + fl6.saddr = ireq6->loc_addr; fl6.flowi6_oif = sk->sk_bound_dev_if; fl6.fl6_dport = inet_rsk(req)->rmt_port; fl6.fl6_sport = inet_rsk(req)->loc_port; @@ -559,9 +559,9 @@ static struct sock *dccp_v6_request_recv_sock(struct sock *sk, memcpy(newnp, np, sizeof(struct ipv6_pinfo)); - ipv6_addr_copy(&newnp->daddr, &ireq6->rmt_addr); - ipv6_addr_copy(&newnp->saddr, &ireq6->loc_addr); - ipv6_addr_copy(&newnp->rcv_saddr, &ireq6->loc_addr); + newnp->daddr = ireq6->rmt_addr; + newnp->saddr = ireq6->loc_addr; + newnp->rcv_saddr = ireq6->loc_addr; newsk->sk_bound_dev_if = ireq6->iif; /* Now IPv6 options... @@ -877,7 +877,7 @@ static int dccp_v6_connect(struct sock *sk, struct sockaddr *uaddr, flowlabel = fl6_sock_lookup(sk, fl6.flowlabel); if (flowlabel == NULL) return -EINVAL; - ipv6_addr_copy(&usin->sin6_addr, &flowlabel->dst); + usin->sin6_addr = flowlabel->dst; fl6_sock_release(flowlabel); } } @@ -910,7 +910,7 @@ static int dccp_v6_connect(struct sock *sk, struct sockaddr *uaddr, return -EINVAL; } - ipv6_addr_copy(&np->daddr, &usin->sin6_addr); + np->daddr = usin->sin6_addr; np->flow_label = fl6.flowlabel; /* @@ -949,8 +949,8 @@ static int dccp_v6_connect(struct sock *sk, struct sockaddr *uaddr, saddr = &np->rcv_saddr; fl6.flowi6_proto = IPPROTO_DCCP; - ipv6_addr_copy(&fl6.daddr, &np->daddr); - ipv6_addr_copy(&fl6.saddr, saddr ? saddr : &np->saddr); + fl6.daddr = np->daddr; + fl6.saddr = saddr ? *saddr : np->saddr; fl6.flowi6_oif = sk->sk_bound_dev_if; fl6.fl6_dport = usin->sin6_port; fl6.fl6_sport = inet->inet_sport; @@ -966,11 +966,11 @@ static int dccp_v6_connect(struct sock *sk, struct sockaddr *uaddr, if (saddr == NULL) { saddr = &fl6.saddr; - ipv6_addr_copy(&np->rcv_saddr, saddr); + np->rcv_saddr = *saddr; } /* set the source address */ - ipv6_addr_copy(&np->saddr, saddr); + np->saddr = *saddr; inet->inet_rcv_saddr = LOOPBACK4_IPV6; __ip6_dst_store(sk, dst, NULL, NULL); diff --git a/net/dccp/minisocks.c b/net/dccp/minisocks.c index d7041a0..b50d5fd 100644 --- a/net/dccp/minisocks.c +++ b/net/dccp/minisocks.c @@ -60,8 +60,8 @@ void dccp_time_wait(struct sock *sk, int state, int timeo) tw->tw_ipv6_offset = inet6_tw_offset(sk->sk_prot); tw6 = inet6_twsk((struct sock *)tw); - ipv6_addr_copy(&tw6->tw_v6_daddr, &np->daddr); - ipv6_addr_copy(&tw6->tw_v6_rcv_saddr, &np->rcv_saddr); + tw6->tw_v6_daddr = np->daddr; + tw6->tw_v6_rcv_saddr = np->rcv_saddr; tw->tw_ipv6only = np->ipv6only; } #endif @@ -100,7 +100,7 @@ struct sock *dccp_create_openreq_child(struct sock *sk, * (* Generate a new socket and switch to that socket *) * Set S := new socket for this port pair */ - struct sock *newsk = inet_csk_clone(sk, req, GFP_ATOMIC); + struct sock *newsk = inet_csk_clone_lock(sk, req, GFP_ATOMIC); if (newsk != NULL) { struct dccp_request_sock *dreq = dccp_rsk(req); diff --git a/net/decnet/dn_neigh.c b/net/decnet/dn_neigh.c index 7f0eb08..3532ac6 100644 --- a/net/decnet/dn_neigh.c +++ b/net/decnet/dn_neigh.c @@ -107,7 +107,7 @@ struct neigh_table dn_neigh_table = { .gc_staletime = 60 * HZ, .reachable_time = 30 * HZ, .delay_probe_time = 5 * HZ, - .queue_len = 3, + .queue_len_bytes = 64*1024, .ucast_probes = 0, .app_probes = 0, .mcast_probes = 0, diff --git a/net/decnet/dn_route.c b/net/decnet/dn_route.c index a77d161..94f4ec0 100644 --- a/net/decnet/dn_route.c +++ b/net/decnet/dn_route.c @@ -112,7 +112,7 @@ static unsigned long dn_rt_deadline; static int dn_dst_gc(struct dst_ops *ops); static struct dst_entry *dn_dst_check(struct dst_entry *, __u32); static unsigned int dn_dst_default_advmss(const struct dst_entry *dst); -static unsigned int dn_dst_default_mtu(const struct dst_entry *dst); +static unsigned int dn_dst_mtu(const struct dst_entry *dst); static void dn_dst_destroy(struct dst_entry *); static struct dst_entry *dn_dst_negative_advice(struct dst_entry *); static void dn_dst_link_failure(struct sk_buff *); @@ -135,7 +135,7 @@ static struct dst_ops dn_dst_ops = { .gc = dn_dst_gc, .check = dn_dst_check, .default_advmss = dn_dst_default_advmss, - .default_mtu = dn_dst_default_mtu, + .mtu = dn_dst_mtu, .cow_metrics = dst_cow_metrics_generic, .destroy = dn_dst_destroy, .negative_advice = dn_dst_negative_advice, @@ -825,9 +825,11 @@ static unsigned int dn_dst_default_advmss(const struct dst_entry *dst) return dn_mss_from_pmtu(dst->dev, dst_mtu(dst)); } -static unsigned int dn_dst_default_mtu(const struct dst_entry *dst) +static unsigned int dn_dst_mtu(const struct dst_entry *dst) { - return dst->dev->mtu; + unsigned int mtu = dst_metric_raw(dst, RTAX_MTU); + + return mtu ? : dst->dev->mtu; } static struct neighbour *dn_dst_neigh_lookup(const struct dst_entry *dst, const void *daddr) diff --git a/net/dsa/Kconfig b/net/dsa/Kconfig index c53ded2..7e12303 100644 --- a/net/dsa/Kconfig +++ b/net/dsa/Kconfig @@ -1,5 +1,5 @@ menuconfig NET_DSA - bool "Distributed Switch Architecture support" + tristate "Distributed Switch Architecture support" default n depends on EXPERIMENTAL && NETDEVICES && !S390 select PHYLIB @@ -26,11 +26,11 @@ config NET_DSA_TAG_TRAILER # switch drivers config NET_DSA_MV88E6XXX - bool + tristate default n config NET_DSA_MV88E6060 - bool "Marvell 88E6060 ethernet switch chip support" + tristate "Marvell 88E6060 ethernet switch chip support" select NET_DSA_TAG_TRAILER ---help--- This enables support for the Marvell 88E6060 ethernet switch @@ -41,7 +41,7 @@ config NET_DSA_MV88E6XXX_NEED_PPU default n config NET_DSA_MV88E6131 - bool "Marvell 88E6085/6095/6095F/6131 ethernet switch chip support" + tristate "Marvell 88E6085/6095/6095F/6131 ethernet switch chip support" select NET_DSA_MV88E6XXX select NET_DSA_MV88E6XXX_NEED_PPU select NET_DSA_TAG_DSA @@ -50,7 +50,7 @@ config NET_DSA_MV88E6131 ethernet switch chips. config NET_DSA_MV88E6123_61_65 - bool "Marvell 88E6123/6161/6165 ethernet switch chip support" + tristate "Marvell 88E6123/6161/6165 ethernet switch chip support" select NET_DSA_MV88E6XXX select NET_DSA_TAG_EDSA ---help--- diff --git a/net/dsa/Makefile b/net/dsa/Makefile index 2374faf..191dd48 100644 --- a/net/dsa/Makefile +++ b/net/dsa/Makefile @@ -1,13 +1,19 @@ +# the core +obj-$(CONFIG_NET_DSA) += dsa_core.o +dsa_core-y += dsa.o slave.o + # tagging formats -obj-$(CONFIG_NET_DSA_TAG_DSA) += tag_dsa.o -obj-$(CONFIG_NET_DSA_TAG_EDSA) += tag_edsa.o -obj-$(CONFIG_NET_DSA_TAG_TRAILER) += tag_trailer.o +dsa_core-$(CONFIG_NET_DSA_TAG_DSA) += tag_dsa.o +dsa_core-$(CONFIG_NET_DSA_TAG_EDSA) += tag_edsa.o +dsa_core-$(CONFIG_NET_DSA_TAG_TRAILER) += tag_trailer.o # switch drivers -obj-$(CONFIG_NET_DSA_MV88E6XXX) += mv88e6xxx.o obj-$(CONFIG_NET_DSA_MV88E6060) += mv88e6060.o -obj-$(CONFIG_NET_DSA_MV88E6123_61_65) += mv88e6123_61_65.o -obj-$(CONFIG_NET_DSA_MV88E6131) += mv88e6131.o - -# the core -obj-$(CONFIG_NET_DSA) += dsa.o slave.o +obj-$(CONFIG_NET_DSA_MV88E6XXX) += mv88e6xxx_drv.o +mv88e6xxx_drv-y += mv88e6xxx.o +ifdef CONFIG_NET_DSA_MV88E6123_61_65 +mv88e6xxx_drv-y += mv88e6123_61_65.o +endif +ifdef CONFIG_NET_DSA_MV88E6131 +mv88e6xxx_drv-y += mv88e6131.o +endif diff --git a/net/dsa/dsa.c b/net/dsa/dsa.c index 0dc1589..88e7c2f 100644 --- a/net/dsa/dsa.c +++ b/net/dsa/dsa.c @@ -29,6 +29,7 @@ void register_switch_driver(struct dsa_switch_driver *drv) list_add_tail(&drv->list, &dsa_switch_drivers); mutex_unlock(&dsa_switch_drivers_mutex); } +EXPORT_SYMBOL_GPL(register_switch_driver); void unregister_switch_driver(struct dsa_switch_driver *drv) { @@ -36,6 +37,7 @@ void unregister_switch_driver(struct dsa_switch_driver *drv) list_del_init(&drv->list); mutex_unlock(&dsa_switch_drivers_mutex); } +EXPORT_SYMBOL_GPL(unregister_switch_driver); static struct dsa_switch_driver * dsa_switch_probe(struct mii_bus *bus, int sw_addr, char **_name) @@ -199,29 +201,6 @@ static void dsa_switch_destroy(struct dsa_switch *ds) } -/* hooks for ethertype-less tagging formats *********************************/ -/* - * The original DSA tag format and some other tag formats have no - * ethertype, which means that we need to add a little hack to the - * networking receive path to make sure that received frames get - * the right ->protocol assigned to them when one of those tag - * formats is in use. - */ -bool dsa_uses_dsa_tags(void *dsa_ptr) -{ - struct dsa_switch_tree *dst = dsa_ptr; - - return !!(dst->tag_protocol == htons(ETH_P_DSA)); -} - -bool dsa_uses_trailer_tags(void *dsa_ptr) -{ - struct dsa_switch_tree *dst = dsa_ptr; - - return !!(dst->tag_protocol == htons(ETH_P_TRAILER)); -} - - /* link polling *************************************************************/ static void dsa_link_poll_work(struct work_struct *ugly) { @@ -419,12 +398,36 @@ static struct platform_driver dsa_driver = { static int __init dsa_init_module(void) { - return platform_driver_register(&dsa_driver); + int rc; + + rc = platform_driver_register(&dsa_driver); + if (rc) + return rc; + +#ifdef CONFIG_NET_DSA_TAG_DSA + dev_add_pack(&dsa_packet_type); +#endif +#ifdef CONFIG_NET_DSA_TAG_EDSA + dev_add_pack(&edsa_packet_type); +#endif +#ifdef CONFIG_NET_DSA_TAG_TRAILER + dev_add_pack(&trailer_packet_type); +#endif + return 0; } module_init(dsa_init_module); static void __exit dsa_cleanup_module(void) { +#ifdef CONFIG_NET_DSA_TAG_TRAILER + dev_remove_pack(&trailer_packet_type); +#endif +#ifdef CONFIG_NET_DSA_TAG_EDSA + dev_remove_pack(&edsa_packet_type); +#endif +#ifdef CONFIG_NET_DSA_TAG_DSA + dev_remove_pack(&dsa_packet_type); +#endif platform_driver_unregister(&dsa_driver); } module_exit(dsa_cleanup_module); diff --git a/net/dsa/dsa_priv.h b/net/dsa/dsa_priv.h index 4b0ea05..89a2eb4 100644 --- a/net/dsa/dsa_priv.h +++ b/net/dsa/dsa_priv.h @@ -48,39 +48,6 @@ struct dsa_switch { struct net_device *ports[DSA_MAX_PORTS]; }; -struct dsa_switch_tree { - /* - * Configuration data for the platform device that owns - * this dsa switch tree instance. - */ - struct dsa_platform_data *pd; - - /* - * Reference to network device to use, and which tagging - * protocol to use. - */ - struct net_device *master_netdev; - __be16 tag_protocol; - - /* - * The switch and port to which the CPU is attached. - */ - s8 cpu_switch; - s8 cpu_port; - - /* - * Link state polling. - */ - int link_poll_needed; - struct work_struct link_poll_work; - struct timer_list link_poll_timer; - - /* - * Data for the individual switch chips. - */ - struct dsa_switch *ds[DSA_MAX_SWITCHES]; -}; - static inline bool dsa_is_cpu_port(struct dsa_switch *ds, int p) { return !!(ds->index == ds->dst->cpu_switch && p == ds->dst->cpu_port); @@ -170,12 +137,15 @@ struct net_device *dsa_slave_create(struct dsa_switch *ds, /* tag_dsa.c */ netdev_tx_t dsa_xmit(struct sk_buff *skb, struct net_device *dev); +extern struct packet_type dsa_packet_type; /* tag_edsa.c */ netdev_tx_t edsa_xmit(struct sk_buff *skb, struct net_device *dev); +extern struct packet_type edsa_packet_type; /* tag_trailer.c */ netdev_tx_t trailer_xmit(struct sk_buff *skb, struct net_device *dev); +extern struct packet_type trailer_packet_type; #endif diff --git a/net/dsa/mv88e6060.c b/net/dsa/mv88e6060.c index 8f4ff5a..0e028df 100644 --- a/net/dsa/mv88e6060.c +++ b/net/dsa/mv88e6060.c @@ -286,3 +286,8 @@ static void __exit mv88e6060_cleanup(void) unregister_switch_driver(&mv88e6060_switch_driver); } module_exit(mv88e6060_cleanup); + +MODULE_AUTHOR("Lennert Buytenhek <buytenh@wantstofly.org>"); +MODULE_DESCRIPTION("Driver for Marvell 88E6060 ethernet switch chip"); +MODULE_LICENSE("GPL"); +MODULE_ALIAS("platform:mv88e6060"); diff --git a/net/dsa/mv88e6123_61_65.c b/net/dsa/mv88e6123_61_65.c index 52faaa2..6504405 100644 --- a/net/dsa/mv88e6123_61_65.c +++ b/net/dsa/mv88e6123_61_65.c @@ -419,7 +419,7 @@ static int mv88e6123_61_65_get_sset_count(struct dsa_switch *ds) return ARRAY_SIZE(mv88e6123_61_65_hw_stats); } -static struct dsa_switch_driver mv88e6123_61_65_switch_driver = { +struct dsa_switch_driver mv88e6123_61_65_switch_driver = { .tag_protocol = cpu_to_be16(ETH_P_EDSA), .priv_size = sizeof(struct mv88e6xxx_priv_state), .probe = mv88e6123_61_65_probe, @@ -433,15 +433,6 @@ static struct dsa_switch_driver mv88e6123_61_65_switch_driver = { .get_sset_count = mv88e6123_61_65_get_sset_count, }; -static int __init mv88e6123_61_65_init(void) -{ - register_switch_driver(&mv88e6123_61_65_switch_driver); - return 0; -} -module_init(mv88e6123_61_65_init); - -static void __exit mv88e6123_61_65_cleanup(void) -{ - unregister_switch_driver(&mv88e6123_61_65_switch_driver); -} -module_exit(mv88e6123_61_65_cleanup); +MODULE_ALIAS("platform:mv88e6123"); +MODULE_ALIAS("platform:mv88e6161"); +MODULE_ALIAS("platform:mv88e6165"); diff --git a/net/dsa/mv88e6131.c b/net/dsa/mv88e6131.c index 9bd1061..6786ba4 100644 --- a/net/dsa/mv88e6131.c +++ b/net/dsa/mv88e6131.c @@ -415,7 +415,7 @@ static int mv88e6131_get_sset_count(struct dsa_switch *ds) return ARRAY_SIZE(mv88e6131_hw_stats); } -static struct dsa_switch_driver mv88e6131_switch_driver = { +struct dsa_switch_driver mv88e6131_switch_driver = { .tag_protocol = cpu_to_be16(ETH_P_DSA), .priv_size = sizeof(struct mv88e6xxx_priv_state), .probe = mv88e6131_probe, @@ -429,15 +429,7 @@ static struct dsa_switch_driver mv88e6131_switch_driver = { .get_sset_count = mv88e6131_get_sset_count, }; -static int __init mv88e6131_init(void) -{ - register_switch_driver(&mv88e6131_switch_driver); - return 0; -} -module_init(mv88e6131_init); - -static void __exit mv88e6131_cleanup(void) -{ - unregister_switch_driver(&mv88e6131_switch_driver); -} -module_exit(mv88e6131_cleanup); +MODULE_ALIAS("platform:mv88e6085"); +MODULE_ALIAS("platform:mv88e6095"); +MODULE_ALIAS("platform:mv88e6095f"); +MODULE_ALIAS("platform:mv88e6131"); diff --git a/net/dsa/mv88e6xxx.c b/net/dsa/mv88e6xxx.c index efe661a..cacd955 100644 --- a/net/dsa/mv88e6xxx.c +++ b/net/dsa/mv88e6xxx.c @@ -520,3 +520,30 @@ void mv88e6xxx_get_ethtool_stats(struct dsa_switch *ds, mutex_unlock(&ps->stats_mutex); } + +static int __init mv88e6xxx_init(void) +{ +#if IS_ENABLED(CONFIG_NET_DSA_MV88E6131) + register_switch_driver(&mv88e6131_switch_driver); +#endif +#if IS_ENABLED(CONFIG_NET_DSA_MV88E6123_61_65) + register_switch_driver(&mv88e6123_61_65_switch_driver); +#endif + return 0; +} +module_init(mv88e6xxx_init); + +static void __exit mv88e6xxx_cleanup(void) +{ +#if IS_ENABLED(CONFIG_NET_DSA_MV88E6123_61_65) + unregister_switch_driver(&mv88e6123_61_65_switch_driver); +#endif +#if IS_ENABLED(CONFIG_NET_DSA_MV88E6131) + unregister_switch_driver(&mv88e6131_switch_driver); +#endif +} +module_exit(mv88e6xxx_cleanup); + +MODULE_AUTHOR("Lennert Buytenhek <buytenh@wantstofly.org>"); +MODULE_DESCRIPTION("Driver for Marvell 88E6XXX ethernet switch chips"); +MODULE_LICENSE("GPL"); diff --git a/net/dsa/mv88e6xxx.h b/net/dsa/mv88e6xxx.h index 61156ca2..fc2cd7b 100644 --- a/net/dsa/mv88e6xxx.h +++ b/net/dsa/mv88e6xxx.h @@ -71,6 +71,9 @@ void mv88e6xxx_get_ethtool_stats(struct dsa_switch *ds, int nr_stats, struct mv88e6xxx_hw_stat *stats, int port, uint64_t *data); +extern struct dsa_switch_driver mv88e6131_switch_driver; +extern struct dsa_switch_driver mv88e6123_61_65_switch_driver; + #define REG_READ(addr, reg) \ ({ \ int __ret; \ diff --git a/net/dsa/slave.c b/net/dsa/slave.c index 56cf9b8..c9d52ca 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -45,6 +45,7 @@ void dsa_slave_mii_bus_init(struct dsa_switch *ds) ds->master_mii_bus->id, ds->pd->sw_addr); ds->slave_mii_bus->parent = &ds->master_mii_bus->dev; } +EXPORT_SYMBOL_GPL(dsa_slave_mii_bus_init); /* slave device handling ****************************************************/ @@ -402,3 +403,4 @@ dsa_slave_create(struct dsa_switch *ds, struct device *parent, return slave_dev; } +EXPORT_SYMBOL_GPL(dsa_slave_create); diff --git a/net/dsa/tag_dsa.c b/net/dsa/tag_dsa.c index 98dfe80..cacce1e 100644 --- a/net/dsa/tag_dsa.c +++ b/net/dsa/tag_dsa.c @@ -186,20 +186,7 @@ out: return 0; } -static struct packet_type dsa_packet_type __read_mostly = { +struct packet_type dsa_packet_type __read_mostly = { .type = cpu_to_be16(ETH_P_DSA), .func = dsa_rcv, }; - -static int __init dsa_init_module(void) -{ - dev_add_pack(&dsa_packet_type); - return 0; -} -module_init(dsa_init_module); - -static void __exit dsa_cleanup_module(void) -{ - dev_remove_pack(&dsa_packet_type); -} -module_exit(dsa_cleanup_module); diff --git a/net/dsa/tag_edsa.c b/net/dsa/tag_edsa.c index 6f38332..e70c43c 100644 --- a/net/dsa/tag_edsa.c +++ b/net/dsa/tag_edsa.c @@ -205,20 +205,7 @@ out: return 0; } -static struct packet_type edsa_packet_type __read_mostly = { +struct packet_type edsa_packet_type __read_mostly = { .type = cpu_to_be16(ETH_P_EDSA), .func = edsa_rcv, }; - -static int __init edsa_init_module(void) -{ - dev_add_pack(&edsa_packet_type); - return 0; -} -module_init(edsa_init_module); - -static void __exit edsa_cleanup_module(void) -{ - dev_remove_pack(&edsa_packet_type); -} -module_exit(edsa_cleanup_module); diff --git a/net/dsa/tag_trailer.c b/net/dsa/tag_trailer.c index d6d7d0a..94bc260 100644 --- a/net/dsa/tag_trailer.c +++ b/net/dsa/tag_trailer.c @@ -114,20 +114,7 @@ out: return 0; } -static struct packet_type trailer_packet_type __read_mostly = { +struct packet_type trailer_packet_type __read_mostly = { .type = cpu_to_be16(ETH_P_TRAILER), .func = trailer_rcv, }; - -static int __init trailer_init_module(void) -{ - dev_add_pack(&trailer_packet_type); - return 0; -} -module_init(trailer_init_module); - -static void __exit trailer_cleanup_module(void) -{ - dev_remove_pack(&trailer_packet_type); -} -module_exit(trailer_cleanup_module); diff --git a/net/econet/af_econet.c b/net/econet/af_econet.c index 1c1f26c..7e717cb 100644 --- a/net/econet/af_econet.c +++ b/net/econet/af_econet.c @@ -322,6 +322,7 @@ static int econet_sendmsg(struct kiocb *iocb, struct socket *sock, /* Real hardware Econet. We're not worthy etc. */ #ifdef CONFIG_ECONET_NATIVE unsigned short proto = 0; + int hlen, tlen; int res; if (len + 15 > dev->mtu) { @@ -331,12 +332,14 @@ static int econet_sendmsg(struct kiocb *iocb, struct socket *sock, dev_hold(dev); - skb = sock_alloc_send_skb(sk, len + LL_ALLOCATED_SPACE(dev), + hlen = LL_RESERVED_SPACE(dev); + tlen = dev->needed_tailroom; + skb = sock_alloc_send_skb(sk, len + hlen + tlen, msg->msg_flags & MSG_DONTWAIT, &err); if (skb == NULL) goto out_unlock; - skb_reserve(skb, LL_RESERVED_SPACE(dev)); + skb_reserve(skb, hlen); skb_reset_network_header(skb); eb = (struct ec_cb *)&skb->cb; diff --git a/net/ieee802154/6lowpan.c b/net/ieee802154/6lowpan.c index 19d6aef..e4ecc1e 100644 --- a/net/ieee802154/6lowpan.c +++ b/net/ieee802154/6lowpan.c @@ -50,8 +50,6 @@ * SUCH DAMAGE. */ -#define DEBUG - #include <linux/bitops.h> #include <linux/if_arp.h> #include <linux/module.h> @@ -113,6 +111,20 @@ struct lowpan_dev_record { struct list_head list; }; +struct lowpan_fragment { + struct sk_buff *skb; /* skb to be assembled */ + spinlock_t lock; /* concurency lock */ + u16 length; /* length to be assemled */ + u32 bytes_rcv; /* bytes received */ + u16 tag; /* current fragment tag */ + struct timer_list timer; /* assembling timer */ + struct list_head list; /* fragments list */ +}; + +static unsigned short fragment_tag; +static LIST_HEAD(lowpan_fragments); +spinlock_t flist_lock; + static inline struct lowpan_dev_info *lowpan_dev_info(const struct net_device *dev) { @@ -234,6 +246,50 @@ lowpan_uncompress_addr(struct sk_buff *skb, struct in6_addr *ipaddr, return 0; } +static void +lowpan_compress_udp_header(u8 **hc06_ptr, struct sk_buff *skb) +{ + struct udphdr *uh = udp_hdr(skb); + + pr_debug("(%s): UDP header compression\n", __func__); + + if (((uh->source & LOWPAN_NHC_UDP_4BIT_MASK) == + LOWPAN_NHC_UDP_4BIT_PORT) && + ((uh->dest & LOWPAN_NHC_UDP_4BIT_MASK) == + LOWPAN_NHC_UDP_4BIT_PORT)) { + pr_debug("(%s): both ports compression to 4 bits\n", __func__); + **hc06_ptr = LOWPAN_NHC_UDP_CS_P_11; + **(hc06_ptr + 1) = /* subtraction is faster */ + (u8)((uh->dest - LOWPAN_NHC_UDP_4BIT_PORT) + + ((uh->source & LOWPAN_NHC_UDP_4BIT_PORT) << 4)); + *hc06_ptr += 2; + } else if ((uh->dest & LOWPAN_NHC_UDP_8BIT_MASK) == + LOWPAN_NHC_UDP_8BIT_PORT) { + pr_debug("(%s): remove 8 bits of dest\n", __func__); + **hc06_ptr = LOWPAN_NHC_UDP_CS_P_01; + memcpy(*hc06_ptr + 1, &uh->source, 2); + **(hc06_ptr + 3) = (u8)(uh->dest - LOWPAN_NHC_UDP_8BIT_PORT); + *hc06_ptr += 4; + } else if ((uh->source & LOWPAN_NHC_UDP_8BIT_MASK) == + LOWPAN_NHC_UDP_8BIT_PORT) { + pr_debug("(%s): remove 8 bits of source\n", __func__); + **hc06_ptr = LOWPAN_NHC_UDP_CS_P_10; + memcpy(*hc06_ptr + 1, &uh->dest, 2); + **(hc06_ptr + 3) = (u8)(uh->source - LOWPAN_NHC_UDP_8BIT_PORT); + *hc06_ptr += 4; + } else { + pr_debug("(%s): can't compress header\n", __func__); + **hc06_ptr = LOWPAN_NHC_UDP_CS_P_00; + memcpy(*hc06_ptr + 1, &uh->source, 2); + memcpy(*hc06_ptr + 3, &uh->dest, 2); + *hc06_ptr += 5; + } + + /* checksum is always inline */ + memcpy(*hc06_ptr, &uh->check, 2); + *hc06_ptr += 2; +} + static u8 lowpan_fetch_skb_u8(struct sk_buff *skb) { u8 ret; @@ -244,6 +300,73 @@ static u8 lowpan_fetch_skb_u8(struct sk_buff *skb) return ret; } +static u16 lowpan_fetch_skb_u16(struct sk_buff *skb) +{ + u16 ret; + + BUG_ON(!pskb_may_pull(skb, 2)); + + ret = skb->data[0] | (skb->data[1] << 8); + skb_pull(skb, 2); + return ret; +} + +static int +lowpan_uncompress_udp_header(struct sk_buff *skb) +{ + struct udphdr *uh = udp_hdr(skb); + u8 tmp; + + tmp = lowpan_fetch_skb_u8(skb); + + if ((tmp & LOWPAN_NHC_UDP_MASK) == LOWPAN_NHC_UDP_ID) { + pr_debug("(%s): UDP header uncompression\n", __func__); + switch (tmp & LOWPAN_NHC_UDP_CS_P_11) { + case LOWPAN_NHC_UDP_CS_P_00: + memcpy(&uh->source, &skb->data[0], 2); + memcpy(&uh->dest, &skb->data[2], 2); + skb_pull(skb, 4); + break; + case LOWPAN_NHC_UDP_CS_P_01: + memcpy(&uh->source, &skb->data[0], 2); + uh->dest = + skb->data[2] + LOWPAN_NHC_UDP_8BIT_PORT; + skb_pull(skb, 3); + break; + case LOWPAN_NHC_UDP_CS_P_10: + uh->source = skb->data[0] + LOWPAN_NHC_UDP_8BIT_PORT; + memcpy(&uh->dest, &skb->data[1], 2); + skb_pull(skb, 3); + break; + case LOWPAN_NHC_UDP_CS_P_11: + uh->source = + LOWPAN_NHC_UDP_4BIT_PORT + (skb->data[0] >> 4); + uh->dest = + LOWPAN_NHC_UDP_4BIT_PORT + (skb->data[0] & 0x0f); + skb_pull(skb, 1); + break; + default: + pr_debug("(%s) ERROR: unknown UDP format\n", __func__); + goto err; + break; + } + + pr_debug("(%s): uncompressed UDP ports: src = %d, dst = %d\n", + __func__, uh->source, uh->dest); + + /* copy checksum */ + memcpy(&uh->check, &skb->data[0], 2); + skb_pull(skb, 2); + } else { + pr_debug("(%s): ERROR: unsupported NH format\n", __func__); + goto err; + } + + return 0; +err: + return -EINVAL; +} + static int lowpan_header_create(struct sk_buff *skb, struct net_device *dev, unsigned short type, const void *_daddr, @@ -342,8 +465,6 @@ static int lowpan_header_create(struct sk_buff *skb, if (hdr->nexthdr == UIP_PROTO_UDP) iphc0 |= LOWPAN_IPHC_NH_C; -/* TODO: next header compression */ - if ((iphc0 & LOWPAN_IPHC_NH_C) == 0) { *hc06_ptr = hdr->nexthdr; hc06_ptr += 1; @@ -431,8 +552,9 @@ static int lowpan_header_create(struct sk_buff *skb, } } - /* TODO: UDP header compression */ - /* TODO: Next Header compression */ + /* UDP header compression */ + if (hdr->nexthdr == UIP_PROTO_UDP) + lowpan_compress_udp_header(&hc06_ptr, skb); head[0] = iphc0; head[1] = iphc1; @@ -467,6 +589,7 @@ static int lowpan_header_create(struct sk_buff *skb, memcpy(&(sa.hwaddr), saddr, 8); mac_cb(skb)->flags = IEEE802154_FC_TYPE_DATA; + return dev_hard_header(skb, lowpan_dev_info(dev)->real_dev, type, (void *)&da, (void *)&sa, skb->len); } @@ -511,6 +634,21 @@ static int lowpan_skb_deliver(struct sk_buff *skb, struct ipv6hdr *hdr) return stat; } +static void lowpan_fragment_timer_expired(unsigned long entry_addr) +{ + struct lowpan_fragment *entry = (struct lowpan_fragment *)entry_addr; + + pr_debug("%s: timer expired for frame with tag %d\n", __func__, + entry->tag); + + spin_lock(&flist_lock); + list_del(&entry->list); + spin_unlock(&flist_lock); + + dev_kfree_skb(entry->skb); + kfree(entry); +} + static int lowpan_process_data(struct sk_buff *skb) { @@ -525,6 +663,107 @@ lowpan_process_data(struct sk_buff *skb) if (skb->len < 2) goto drop; iphc0 = lowpan_fetch_skb_u8(skb); + + /* fragments assembling */ + switch (iphc0 & LOWPAN_DISPATCH_MASK) { + case LOWPAN_DISPATCH_FRAG1: + case LOWPAN_DISPATCH_FRAGN: + { + struct lowpan_fragment *frame; + u8 len, offset; + u16 tag; + bool found = false; + + len = lowpan_fetch_skb_u8(skb); /* frame length */ + tag = lowpan_fetch_skb_u16(skb); + + /* + * check if frame assembling with the same tag is + * already in progress + */ + spin_lock(&flist_lock); + + list_for_each_entry(frame, &lowpan_fragments, list) + if (frame->tag == tag) { + found = true; + break; + } + + /* alloc new frame structure */ + if (!found) { + frame = kzalloc(sizeof(struct lowpan_fragment), + GFP_ATOMIC); + if (!frame) + goto unlock_and_drop; + + INIT_LIST_HEAD(&frame->list); + + frame->length = (iphc0 & 7) | (len << 3); + frame->tag = tag; + + /* allocate buffer for frame assembling */ + frame->skb = alloc_skb(frame->length + + sizeof(struct ipv6hdr), GFP_ATOMIC); + + if (!frame->skb) { + kfree(frame); + goto unlock_and_drop; + } + + frame->skb->priority = skb->priority; + frame->skb->dev = skb->dev; + + /* reserve headroom for uncompressed ipv6 header */ + skb_reserve(frame->skb, sizeof(struct ipv6hdr)); + skb_put(frame->skb, frame->length); + + init_timer(&frame->timer); + /* time out is the same as for ipv6 - 60 sec */ + frame->timer.expires = jiffies + LOWPAN_FRAG_TIMEOUT; + frame->timer.data = (unsigned long)frame; + frame->timer.function = lowpan_fragment_timer_expired; + + add_timer(&frame->timer); + + list_add_tail(&frame->list, &lowpan_fragments); + } + + if ((iphc0 & LOWPAN_DISPATCH_MASK) == LOWPAN_DISPATCH_FRAG1) + goto unlock_and_drop; + + offset = lowpan_fetch_skb_u8(skb); /* fetch offset */ + + /* if payload fits buffer, copy it */ + if (likely((offset * 8 + skb->len) <= frame->length)) + skb_copy_to_linear_data_offset(frame->skb, offset * 8, + skb->data, skb->len); + else + goto unlock_and_drop; + + frame->bytes_rcv += skb->len; + + /* frame assembling complete */ + if ((frame->bytes_rcv == frame->length) && + frame->timer.expires > jiffies) { + /* if timer haven't expired - first of all delete it */ + del_timer(&frame->timer); + list_del(&frame->list); + spin_unlock(&flist_lock); + + dev_kfree_skb(skb); + skb = frame->skb; + kfree(frame); + iphc0 = lowpan_fetch_skb_u8(skb); + break; + } + spin_unlock(&flist_lock); + + return kfree_skb(skb), 0; + } + default: + break; + } + iphc1 = lowpan_fetch_skb_u8(skb); _saddr = mac_cb(skb)->sa.hwaddr; @@ -659,7 +898,10 @@ lowpan_process_data(struct sk_buff *skb) goto drop; } - /* TODO: UDP header parse */ + /* UDP data uncompression */ + if (iphc0 & LOWPAN_IPHC_NH_C) + if (lowpan_uncompress_udp_header(skb)) + goto drop; /* Not fragmented package */ hdr.payload_len = htons(skb->len); @@ -674,6 +916,9 @@ lowpan_process_data(struct sk_buff *skb) lowpan_raw_dump_table(__func__, "raw header dump", (u8 *)&hdr, sizeof(hdr)); return lowpan_skb_deliver(skb, &hdr); + +unlock_and_drop: + spin_unlock(&flist_lock); drop: kfree_skb(skb); return -EINVAL; @@ -692,18 +937,115 @@ static int lowpan_set_address(struct net_device *dev, void *p) return 0; } +static int lowpan_get_mac_header_length(struct sk_buff *skb) +{ + /* + * Currently long addressing mode is supported only, so the overall + * header size is 21: + * FC SeqNum DPAN DA SA Sec + * 2 + 1 + 2 + 8 + 8 + 0 = 21 + */ + return 21; +} + +static int +lowpan_fragment_xmit(struct sk_buff *skb, u8 *head, + int mlen, int plen, int offset) +{ + struct sk_buff *frag; + int hlen, ret; + + /* if payload length is zero, therefore it's a first fragment */ + hlen = (plen == 0 ? LOWPAN_FRAG1_HEAD_SIZE : LOWPAN_FRAGN_HEAD_SIZE); + + lowpan_raw_dump_inline(__func__, "6lowpan fragment header", head, hlen); + + frag = dev_alloc_skb(hlen + mlen + plen + IEEE802154_MFR_SIZE); + if (!frag) + return -ENOMEM; + + frag->priority = skb->priority; + frag->dev = skb->dev; + + /* copy header, MFR and payload */ + memcpy(skb_put(frag, mlen), skb->data, mlen); + memcpy(skb_put(frag, hlen), head, hlen); + + if (plen) + skb_copy_from_linear_data_offset(skb, offset + mlen, + skb_put(frag, plen), plen); + + lowpan_raw_dump_table(__func__, " raw fragment dump", frag->data, + frag->len); + + ret = dev_queue_xmit(frag); + + return ret; +} + +static int +lowpan_skb_fragmentation(struct sk_buff *skb) +{ + int err, header_length, payload_length, tag, offset = 0; + u8 head[5]; + + header_length = lowpan_get_mac_header_length(skb); + payload_length = skb->len - header_length; + tag = fragment_tag++; + + /* first fragment header */ + head[0] = LOWPAN_DISPATCH_FRAG1 | (payload_length & 0x7); + head[1] = (payload_length >> 3) & 0xff; + head[2] = tag & 0xff; + head[3] = tag >> 8; + + err = lowpan_fragment_xmit(skb, head, header_length, 0, 0); + + /* next fragment header */ + head[0] &= ~LOWPAN_DISPATCH_FRAG1; + head[0] |= LOWPAN_DISPATCH_FRAGN; + + while ((payload_length - offset > 0) && (err >= 0)) { + int len = LOWPAN_FRAG_SIZE; + + head[4] = offset / 8; + + if (payload_length - offset < len) + len = payload_length - offset; + + err = lowpan_fragment_xmit(skb, head, header_length, + len, offset); + offset += len; + } + + return err; +} + static netdev_tx_t lowpan_xmit(struct sk_buff *skb, struct net_device *dev) { - int err = 0; + int err = -1; pr_debug("(%s): package xmit\n", __func__); skb->dev = lowpan_dev_info(dev)->real_dev; if (skb->dev == NULL) { pr_debug("(%s) ERROR: no real wpan device found\n", __func__); - dev_kfree_skb(skb); - } else + goto error; + } + + if (skb->len <= IEEE802154_MTU) { err = dev_queue_xmit(skb); + goto out; + } + + pr_debug("(%s): frame is too big, fragmentation is needed\n", + __func__); + err = lowpan_skb_fragmentation(skb); +error: + dev_kfree_skb(skb); +out: + if (err < 0) + pr_debug("(%s): ERROR: xmit failed\n", __func__); return (err < 0 ? NETDEV_TX_BUSY : NETDEV_TX_OK); } @@ -730,13 +1072,12 @@ static void lowpan_setup(struct net_device *dev) dev->addr_len = IEEE802154_ADDR_LEN; memset(dev->broadcast, 0xff, IEEE802154_ADDR_LEN); dev->type = ARPHRD_IEEE802154; - dev->features = NETIF_F_NO_CSUM; /* Frame Control + Sequence Number + Address fields + Security Header */ dev->hard_header_len = 2 + 1 + 20 + 14; dev->needed_tailroom = 2; /* FCS */ dev->mtu = 1281; dev->tx_queue_len = 0; - dev->flags = IFF_NOARP | IFF_BROADCAST; + dev->flags = IFF_BROADCAST | IFF_MULTICAST; dev->watchdog_timeo = 0; dev->netdev_ops = &lowpan_netdev_ops; @@ -765,8 +1106,15 @@ static int lowpan_rcv(struct sk_buff *skb, struct net_device *dev, goto drop; /* check that it's our buffer */ - if ((skb->data[0] & 0xe0) == 0x60) + switch (skb->data[0] & 0xe0) { + case LOWPAN_DISPATCH_IPHC: /* ipv6 datagram */ + case LOWPAN_DISPATCH_FRAG1: /* first fragment header */ + case LOWPAN_DISPATCH_FRAGN: /* next fragments headers */ lowpan_process_data(skb); + break; + default: + break; + } return NET_RX_SUCCESS; diff --git a/net/ieee802154/6lowpan.h b/net/ieee802154/6lowpan.h index 5d8cf80..aeff3f3 100644 --- a/net/ieee802154/6lowpan.h +++ b/net/ieee802154/6lowpan.h @@ -159,6 +159,24 @@ #define LOWPAN_DISPATCH_FRAG1 0xc0 /* 11000xxx */ #define LOWPAN_DISPATCH_FRAGN 0xe0 /* 11100xxx */ +#define LOWPAN_DISPATCH_MASK 0xf8 /* 11111000 */ + +#define LOWPAN_FRAG_TIMEOUT (HZ * 60) /* time-out 60 sec */ + +#define LOWPAN_FRAG1_HEAD_SIZE 0x4 +#define LOWPAN_FRAGN_HEAD_SIZE 0x5 + +/* + * According IEEE802.15.4 standard: + * - MTU is 127 octets + * - maximum MHR size is 37 octets + * - MFR size is 2 octets + * + * so minimal payload size that we may guarantee is: + * MTU - MHR - MFR = 88 octets + */ +#define LOWPAN_FRAG_SIZE 88 + /* * Values of fields within the IPHC encoding first byte * (C stands for compressed and I for inline) @@ -201,6 +219,11 @@ #define LOWPAN_NHC_UDP_CHECKSUMC 0x04 #define LOWPAN_NHC_UDP_CHECKSUMI 0x00 +#define LOWPAN_NHC_UDP_4BIT_PORT 0xF0B0 +#define LOWPAN_NHC_UDP_4BIT_MASK 0xFFF0 +#define LOWPAN_NHC_UDP_8BIT_PORT 0xF000 +#define LOWPAN_NHC_UDP_8BIT_MASK 0xFF00 + /* values for port compression, _with checksum_ ie bit 5 set to 0 */ #define LOWPAN_NHC_UDP_CS_P_00 0xF0 /* all inline */ #define LOWPAN_NHC_UDP_CS_P_01 0xF1 /* source 16bit inline, diff --git a/net/ieee802154/dgram.c b/net/ieee802154/dgram.c index faecf64..1b09eaa 100644 --- a/net/ieee802154/dgram.c +++ b/net/ieee802154/dgram.c @@ -209,6 +209,7 @@ static int dgram_sendmsg(struct kiocb *iocb, struct sock *sk, unsigned mtu; struct sk_buff *skb; struct dgram_sock *ro = dgram_sk(sk); + int hlen, tlen; int err; if (msg->msg_flags & MSG_OOB) { @@ -229,13 +230,15 @@ static int dgram_sendmsg(struct kiocb *iocb, struct sock *sk, mtu = dev->mtu; pr_debug("name = %s, mtu = %u\n", dev->name, mtu); - skb = sock_alloc_send_skb(sk, LL_ALLOCATED_SPACE(dev) + size, + hlen = LL_RESERVED_SPACE(dev); + tlen = dev->needed_tailroom; + skb = sock_alloc_send_skb(sk, hlen + tlen + size, msg->msg_flags & MSG_DONTWAIT, &err); if (!skb) goto out_dev; - skb_reserve(skb, LL_RESERVED_SPACE(dev)); + skb_reserve(skb, hlen); skb_reset_network_header(skb); diff --git a/net/ieee802154/raw.c b/net/ieee802154/raw.c index 10970ca..f96bae8 100644 --- a/net/ieee802154/raw.c +++ b/net/ieee802154/raw.c @@ -108,6 +108,7 @@ static int raw_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, struct net_device *dev; unsigned mtu; struct sk_buff *skb; + int hlen, tlen; int err; if (msg->msg_flags & MSG_OOB) { @@ -137,12 +138,14 @@ static int raw_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, goto out_dev; } - skb = sock_alloc_send_skb(sk, LL_ALLOCATED_SPACE(dev) + size, + hlen = LL_RESERVED_SPACE(dev); + tlen = dev->needed_tailroom; + skb = sock_alloc_send_skb(sk, hlen + tlen + size, msg->msg_flags & MSG_DONTWAIT, &err); if (!skb) goto out_dev; - skb_reserve(skb, LL_RESERVED_SPACE(dev)); + skb_reserve(skb, hlen); skb_reset_mac_header(skb); skb_reset_network_header(skb); diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 1b5096a..15dc4c4 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -1250,7 +1250,8 @@ out: return err; } -static struct sk_buff *inet_gso_segment(struct sk_buff *skb, u32 features) +static struct sk_buff *inet_gso_segment(struct sk_buff *skb, + netdev_features_t features) { struct sk_buff *segs = ERR_PTR(-EINVAL); struct iphdr *iph; @@ -1572,9 +1573,9 @@ static __net_init int ipv4_mib_init_net(struct net *net) sizeof(struct icmp_mib), __alignof__(struct icmp_mib)) < 0) goto err_icmp_mib; - if (snmp_mib_init((void __percpu **)net->mib.icmpmsg_statistics, - sizeof(struct icmpmsg_mib), - __alignof__(struct icmpmsg_mib)) < 0) + net->mib.icmpmsg_statistics = kzalloc(sizeof(struct icmpmsg_mib), + GFP_KERNEL); + if (!net->mib.icmpmsg_statistics) goto err_icmpmsg_mib; tcp_mib_init(net); @@ -1598,7 +1599,7 @@ err_tcp_mib: static __net_exit void ipv4_mib_exit_net(struct net *net) { - snmp_mib_free((void __percpu **)net->mib.icmpmsg_statistics); + kfree(net->mib.icmpmsg_statistics); snmp_mib_free((void __percpu **)net->mib.icmp_statistics); snmp_mib_free((void __percpu **)net->mib.udplite_statistics); snmp_mib_free((void __percpu **)net->mib.udp_statistics); diff --git a/net/ipv4/ah4.c b/net/ipv4/ah4.c index c1f4154..36d1440 100644 --- a/net/ipv4/ah4.c +++ b/net/ipv4/ah4.c @@ -136,8 +136,6 @@ static void ah_output_done(struct crypto_async_request *base, int err) memcpy(top_iph+1, iph+1, top_iph->ihl*4 - sizeof(struct iphdr)); } - err = ah->nexthdr; - kfree(AH_SKB_CB(skb)->tmp); xfrm_output_resume(skb, err); } @@ -264,12 +262,12 @@ static void ah_input_done(struct crypto_async_request *base, int err) if (err) goto out; + err = ah->nexthdr; + skb->network_header += ah_hlen; memcpy(skb_network_header(skb), work_iph, ihl); __skb_pull(skb, ah_hlen + ihl); skb_set_transport_header(skb, -ihl); - - err = ah->nexthdr; out: kfree(AH_SKB_CB(skb)->tmp); xfrm_input_resume(skb, err); @@ -371,8 +369,6 @@ static int ah_input(struct xfrm_state *x, struct sk_buff *skb) if (err == -EINPROGRESS) goto out; - if (err == -EBUSY) - err = NET_XMIT_DROP; goto out_free; } diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c index 96a164a..5c29ac5 100644 --- a/net/ipv4/arp.c +++ b/net/ipv4/arp.c @@ -177,7 +177,7 @@ struct neigh_table arp_tbl = { .gc_staletime = 60 * HZ, .reachable_time = 30 * HZ, .delay_probe_time = 5 * HZ, - .queue_len = 3, + .queue_len_bytes = 64*1024, .ucast_probes = 3, .mcast_probes = 3, .anycast_delay = 1 * HZ, @@ -592,16 +592,18 @@ struct sk_buff *arp_create(int type, int ptype, __be32 dest_ip, struct sk_buff *skb; struct arphdr *arp; unsigned char *arp_ptr; + int hlen = LL_RESERVED_SPACE(dev); + int tlen = dev->needed_tailroom; /* * Allocate a buffer */ - skb = alloc_skb(arp_hdr_len(dev) + LL_ALLOCATED_SPACE(dev), GFP_ATOMIC); + skb = alloc_skb(arp_hdr_len(dev) + hlen + tlen, GFP_ATOMIC); if (skb == NULL) return NULL; - skb_reserve(skb, LL_RESERVED_SPACE(dev)); + skb_reserve(skb, hlen); skb_reset_network_header(skb); arp = (struct arphdr *) skb_put(skb, arp_hdr_len(dev)); skb->dev = dev; diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index c7472ef..313ad93 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -304,9 +304,11 @@ static struct sk_buff *igmpv3_newpack(struct net_device *dev, int size) struct igmpv3_report *pig; struct net *net = dev_net(dev); struct flowi4 fl4; + int hlen = LL_RESERVED_SPACE(dev); + int tlen = dev->needed_tailroom; while (1) { - skb = alloc_skb(size + LL_ALLOCATED_SPACE(dev), + skb = alloc_skb(size + hlen + tlen, GFP_ATOMIC | __GFP_NOWARN); if (skb) break; @@ -327,7 +329,7 @@ static struct sk_buff *igmpv3_newpack(struct net_device *dev, int size) skb_dst_set(skb, &rt->dst); skb->dev = dev; - skb_reserve(skb, LL_RESERVED_SPACE(dev)); + skb_reserve(skb, hlen); skb_reset_network_header(skb); pip = ip_hdr(skb); @@ -647,6 +649,7 @@ static int igmp_send_report(struct in_device *in_dev, struct ip_mc_list *pmc, __be32 group = pmc ? pmc->multiaddr : 0; struct flowi4 fl4; __be32 dst; + int hlen, tlen; if (type == IGMPV3_HOST_MEMBERSHIP_REPORT) return igmpv3_send_report(in_dev, pmc); @@ -661,7 +664,9 @@ static int igmp_send_report(struct in_device *in_dev, struct ip_mc_list *pmc, if (IS_ERR(rt)) return -1; - skb = alloc_skb(IGMP_SIZE+LL_ALLOCATED_SPACE(dev), GFP_ATOMIC); + hlen = LL_RESERVED_SPACE(dev); + tlen = dev->needed_tailroom; + skb = alloc_skb(IGMP_SIZE + hlen + tlen, GFP_ATOMIC); if (skb == NULL) { ip_rt_put(rt); return -1; @@ -669,7 +674,7 @@ static int igmp_send_report(struct in_device *in_dev, struct ip_mc_list *pmc, skb_dst_set(skb, &rt->dst); - skb_reserve(skb, LL_RESERVED_SPACE(dev)); + skb_reserve(skb, hlen); skb_reset_network_header(skb); iph = ip_hdr(skb); @@ -1716,7 +1721,8 @@ static int ip_mc_add_src(struct in_device *in_dev, __be32 *pmca, int sfmode, if (err) { int j; - pmc->sfcount[sfmode]--; + if (!delta) + pmc->sfcount[sfmode]--; for (j=0; j<i; j++) (void) ip_mc_del1_src(pmc, sfmode, &psfsrc[j]); } else if (isexclude != (pmc->sfcount[MCAST_EXCLUDE] != 0)) { diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index c14d88a..a598768 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -588,10 +588,19 @@ void inet_csk_reqsk_queue_prune(struct sock *parent, } EXPORT_SYMBOL_GPL(inet_csk_reqsk_queue_prune); -struct sock *inet_csk_clone(struct sock *sk, const struct request_sock *req, - const gfp_t priority) +/** + * inet_csk_clone_lock - clone an inet socket, and lock its clone + * @sk: the socket to clone + * @req: request_sock + * @priority: for allocation (%GFP_KERNEL, %GFP_ATOMIC, etc) + * + * Caller must unlock socket even in error path (bh_unlock_sock(newsk)) + */ +struct sock *inet_csk_clone_lock(const struct sock *sk, + const struct request_sock *req, + const gfp_t priority) { - struct sock *newsk = sk_clone(sk, priority); + struct sock *newsk = sk_clone_lock(sk, priority); if (newsk != NULL) { struct inet_connection_sock *newicsk = inet_csk(newsk); @@ -615,7 +624,7 @@ struct sock *inet_csk_clone(struct sock *sk, const struct request_sock *req, } return newsk; } -EXPORT_SYMBOL_GPL(inet_csk_clone); +EXPORT_SYMBOL_GPL(inet_csk_clone_lock); /* * At this point, there should be no process reference to this diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index f5e2bda..0a46c54 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -108,9 +108,6 @@ static int inet_csk_diag_fill(struct sock *sk, icsk->icsk_ca_ops->name); } - if ((ext & (1 << (INET_DIAG_TOS - 1))) && (sk->sk_family != AF_INET6)) - RTA_PUT_U8(skb, INET_DIAG_TOS, inet->tos); - r->idiag_family = sk->sk_family; r->idiag_state = sk->sk_state; r->idiag_timer = 0; @@ -125,16 +122,20 @@ static int inet_csk_diag_fill(struct sock *sk, r->id.idiag_src[0] = inet->inet_rcv_saddr; r->id.idiag_dst[0] = inet->inet_daddr; + /* IPv6 dual-stack sockets use inet->tos for IPv4 connections, + * hence this needs to be included regardless of socket family. + */ + if (ext & (1 << (INET_DIAG_TOS - 1))) + RTA_PUT_U8(skb, INET_DIAG_TOS, inet->tos); + #if defined(CONFIG_IPV6) || defined (CONFIG_IPV6_MODULE) if (r->idiag_family == AF_INET6) { const struct ipv6_pinfo *np = inet6_sk(sk); - ipv6_addr_copy((struct in6_addr *)r->id.idiag_src, - &np->rcv_saddr); - ipv6_addr_copy((struct in6_addr *)r->id.idiag_dst, - &np->daddr); - if (ext & (1 << (INET_DIAG_TOS - 1))) - RTA_PUT_U8(skb, INET_DIAG_TOS, np->tclass); + *(struct in6_addr *)r->id.idiag_src = np->rcv_saddr; + *(struct in6_addr *)r->id.idiag_dst = np->daddr; + if (ext & (1 << (INET_DIAG_TCLASS - 1))) + RTA_PUT_U8(skb, INET_DIAG_TCLASS, np->tclass); } #endif @@ -224,10 +225,8 @@ static int inet_twsk_diag_fill(struct inet_timewait_sock *tw, const struct inet6_timewait_sock *tw6 = inet6_twsk((struct sock *)tw); - ipv6_addr_copy((struct in6_addr *)r->id.idiag_src, - &tw6->tw_v6_rcv_saddr); - ipv6_addr_copy((struct in6_addr *)r->id.idiag_dst, - &tw6->tw_v6_daddr); + *(struct in6_addr *)r->id.idiag_src = tw6->tw_v6_rcv_saddr; + *(struct in6_addr *)r->id.idiag_dst = tw6->tw_v6_daddr; } #endif nlh->nlmsg_len = skb_tail_pointer(skb) - previous_tail; @@ -603,10 +602,8 @@ static int inet_diag_fill_req(struct sk_buff *skb, struct sock *sk, r->idiag_inode = 0; #if defined(CONFIG_IPV6) || defined (CONFIG_IPV6_MODULE) if (r->idiag_family == AF_INET6) { - ipv6_addr_copy((struct in6_addr *)r->id.idiag_src, - &inet6_rsk(req)->loc_addr); - ipv6_addr_copy((struct in6_addr *)r->id.idiag_dst, - &inet6_rsk(req)->rmt_addr); + *(struct in6_addr *)r->id.idiag_src = inet6_rsk(req)->loc_addr; + *(struct in6_addr *)r->id.idiag_dst = inet6_rsk(req)->rmt_addr; } #endif nlh->nlmsg_len = skb_tail_pointer(skb) - b; diff --git a/net/ipv4/ip_forward.c b/net/ipv4/ip_forward.c index 3b34d1c..29a07b6 100644 --- a/net/ipv4/ip_forward.c +++ b/net/ipv4/ip_forward.c @@ -84,7 +84,7 @@ int ip_forward(struct sk_buff *skb) rt = skb_rtable(skb); - if (opt->is_strictroute && ip_hdr(skb)->daddr != rt->rt_gateway) + if (opt->is_strictroute && opt->nexthop != rt->rt_gateway) goto sr_failed; if (unlikely(skb->len > dst_mtu(&rt->dst) && !skb_is_gso(skb) && diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index d55110e..2b32296 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -171,7 +171,7 @@ struct pcpu_tstats { unsigned long rx_bytes; unsigned long tx_packets; unsigned long tx_bytes; -}; +} __attribute__((aligned(4*sizeof(unsigned long)))); static struct net_device_stats *ipgre_get_stats(struct net_device *dev) { @@ -835,6 +835,8 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev if (skb_headroom(skb) < max_headroom || skb_shared(skb)|| (skb_cloned(skb) && !skb_clone_writable(skb, 0))) { struct sk_buff *new_skb = skb_realloc_headroom(skb, max_headroom); + if (max_headroom > dev->needed_headroom) + dev->needed_headroom = max_headroom; if (!new_skb) { ip_rt_put(rt); dev->stats.tx_dropped++; diff --git a/net/ipv4/ip_options.c b/net/ipv4/ip_options.c index ec93335..1e60f76 100644 --- a/net/ipv4/ip_options.c +++ b/net/ipv4/ip_options.c @@ -568,12 +568,13 @@ void ip_forward_options(struct sk_buff *skb) ) { if (srrptr + 3 > srrspace) break; - if (memcmp(&ip_hdr(skb)->daddr, &optptr[srrptr-1], 4) == 0) + if (memcmp(&opt->nexthop, &optptr[srrptr-1], 4) == 0) break; } if (srrptr + 3 <= srrspace) { opt->is_changed = 1; ip_rt_get_source(&optptr[srrptr-1], skb, rt); + ip_hdr(skb)->daddr = opt->nexthop; optptr[2] = srrptr+4; } else if (net_ratelimit()) printk(KERN_CRIT "ip_forward(): Argh! Destination lost!\n"); @@ -640,6 +641,7 @@ int ip_options_rcv_srr(struct sk_buff *skb) } if (srrptr <= srrspace) { opt->srr_is_hit = 1; + opt->nexthop = nexthop; opt->is_changed = 1; } return 0; diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index 09ff51b..80d5fa4 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -55,20 +55,13 @@ /* * SOL_IP control messages. */ +#define PKTINFO_SKB_CB(__skb) ((struct in_pktinfo *)((__skb)->cb)) static void ip_cmsg_recv_pktinfo(struct msghdr *msg, struct sk_buff *skb) { - struct in_pktinfo info; - struct rtable *rt = skb_rtable(skb); + struct in_pktinfo info = *PKTINFO_SKB_CB(skb); info.ipi_addr.s_addr = ip_hdr(skb)->daddr; - if (rt) { - info.ipi_ifindex = rt->rt_iif; - info.ipi_spec_dst.s_addr = rt->rt_spec_dst; - } else { - info.ipi_ifindex = 0; - info.ipi_spec_dst.s_addr = 0; - } put_cmsg(msg, SOL_IP, IP_PKTINFO, sizeof(info), &info); } @@ -992,20 +985,28 @@ e_inval: } /** - * ip_queue_rcv_skb - Queue an skb into sock receive queue + * ipv4_pktinfo_prepare - transfert some info from rtable to skb * @sk: socket * @skb: buffer * - * Queues an skb into socket receive queue. If IP_CMSG_PKTINFO option - * is not set, we drop skb dst entry now, while dst cache line is hot. + * To support IP_CMSG_PKTINFO option, we store rt_iif and rt_spec_dst + * in skb->cb[] before dst drop. + * This way, receiver doesnt make cache line misses to read rtable. */ -int ip_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) +void ipv4_pktinfo_prepare(struct sk_buff *skb) { - if (!(inet_sk(sk)->cmsg_flags & IP_CMSG_PKTINFO)) - skb_dst_drop(skb); - return sock_queue_rcv_skb(sk, skb); + struct in_pktinfo *pktinfo = PKTINFO_SKB_CB(skb); + const struct rtable *rt = skb_rtable(skb); + + if (rt) { + pktinfo->ipi_ifindex = rt->rt_iif; + pktinfo->ipi_spec_dst.s_addr = rt->rt_spec_dst; + } else { + pktinfo->ipi_ifindex = 0; + pktinfo->ipi_spec_dst.s_addr = 0; + } + skb_dst_drop(skb); } -EXPORT_SYMBOL(ip_queue_rcv_skb); int ip_setsockopt(struct sock *sk, int level, int optname, char __user *optval, unsigned int optlen) diff --git a/net/ipv4/ipconfig.c b/net/ipv4/ipconfig.c index 0da2afc..915eb52 100644 --- a/net/ipv4/ipconfig.c +++ b/net/ipv4/ipconfig.c @@ -763,13 +763,15 @@ static void __init ic_bootp_send_if(struct ic_device *d, unsigned long jiffies_d struct sk_buff *skb; struct bootp_pkt *b; struct iphdr *h; + int hlen = LL_RESERVED_SPACE(dev); + int tlen = dev->needed_tailroom; /* Allocate packet */ - skb = alloc_skb(sizeof(struct bootp_pkt) + LL_ALLOCATED_SPACE(dev) + 15, + skb = alloc_skb(sizeof(struct bootp_pkt) + hlen + tlen + 15, GFP_KERNEL); if (!skb) return; - skb_reserve(skb, LL_RESERVED_SPACE(dev)); + skb_reserve(skb, hlen); b = (struct bootp_pkt *) skb_put(skb, sizeof(struct bootp_pkt)); memset(b, 0, sizeof(struct bootp_pkt)); @@ -822,8 +824,13 @@ static void __init ic_bootp_send_if(struct ic_device *d, unsigned long jiffies_d skb->dev = dev; skb->protocol = htons(ETH_P_IP); if (dev_hard_header(skb, dev, ntohs(skb->protocol), - dev->broadcast, dev->dev_addr, skb->len) < 0 || - dev_queue_xmit(skb) < 0) + dev->broadcast, dev->dev_addr, skb->len) < 0) { + kfree_skb(skb); + printk("E"); + return; + } + + if (dev_queue_xmit(skb) < 0) printk("E"); } diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c index 065effd..9490690 100644 --- a/net/ipv4/ipip.c +++ b/net/ipv4/ipip.c @@ -148,7 +148,7 @@ struct pcpu_tstats { unsigned long rx_bytes; unsigned long tx_packets; unsigned long tx_bytes; -}; +} __attribute__((aligned(4*sizeof(unsigned long)))); static struct net_device_stats *ipip_get_stats(struct net_device *dev) { diff --git a/net/ipv4/netfilter/Kconfig b/net/ipv4/netfilter/Kconfig index 1dfc18a..f19f218 100644 --- a/net/ipv4/netfilter/Kconfig +++ b/net/ipv4/netfilter/Kconfig @@ -325,7 +325,6 @@ config IP_NF_TARGET_TTL # raw + specific targets config IP_NF_RAW tristate 'raw table support (required for NOTRACK/TRACE)' - depends on NETFILTER_ADVANCED help This option adds a `raw' table to iptables. This table is the very first in the netfilter framework and hooks in at the PREROUTING diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c index a06f73f..43d4c3b 100644 --- a/net/ipv4/ping.c +++ b/net/ipv4/ping.c @@ -339,7 +339,6 @@ void ping_err(struct sk_buff *skb, u32 info) sk = ping_v4_lookup(net, iph->daddr, iph->saddr, ntohs(icmph->un.echo.id), skb->dev->ifindex); if (sk == NULL) { - ICMP_INC_STATS_BH(net, ICMP_MIB_INERRORS); pr_debug("no socket, dropping\n"); return; /* No socket for error */ } @@ -679,7 +678,6 @@ static int ping_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) pr_debug("ping_queue_rcv_skb(sk=%p,sk->num=%d,skb=%p)\n", inet_sk(sk), inet_sk(sk)->inet_num, skb); if (sock_queue_rcv_skb(sk, skb) < 0) { - ICMP_INC_STATS_BH(sock_net(sk), ICMP_MIB_INERRORS); kfree_skb(skb); pr_debug("ping_queue_rcv_skb -> failed\n"); return -1; diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c index 466ea8b..961eed4 100644 --- a/net/ipv4/proc.c +++ b/net/ipv4/proc.c @@ -288,7 +288,7 @@ static void icmpmsg_put(struct seq_file *seq) count = 0; for (i = 0; i < ICMPMSG_MIB_MAX; i++) { - val = snmp_fold_field((void __percpu **) net->mib.icmpmsg_statistics, i); + val = atomic_long_read(&net->mib.icmpmsg_statistics->mibs[i]); if (val) { type[count] = i; vals[count++] = val; @@ -307,6 +307,7 @@ static void icmp_put(struct seq_file *seq) { int i; struct net *net = seq->private; + atomic_long_t *ptr = net->mib.icmpmsg_statistics->mibs; seq_puts(seq, "\nIcmp: InMsgs InErrors"); for (i=0; icmpmibmap[i].name != NULL; i++) @@ -319,15 +320,13 @@ static void icmp_put(struct seq_file *seq) snmp_fold_field((void __percpu **) net->mib.icmp_statistics, ICMP_MIB_INERRORS)); for (i=0; icmpmibmap[i].name != NULL; i++) seq_printf(seq, " %lu", - snmp_fold_field((void __percpu **) net->mib.icmpmsg_statistics, - icmpmibmap[i].index)); + atomic_long_read(ptr + icmpmibmap[i].index)); seq_printf(seq, " %lu %lu", snmp_fold_field((void __percpu **) net->mib.icmp_statistics, ICMP_MIB_OUTMSGS), snmp_fold_field((void __percpu **) net->mib.icmp_statistics, ICMP_MIB_OUTERRORS)); for (i=0; icmpmibmap[i].name != NULL; i++) seq_printf(seq, " %lu", - snmp_fold_field((void __percpu **) net->mib.icmpmsg_statistics, - icmpmibmap[i].index | 0x100)); + atomic_long_read(ptr + (icmpmibmap[i].index | 0x100))); } /* diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index 007e2eb..3ccda5a 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -292,7 +292,8 @@ static int raw_rcv_skb(struct sock * sk, struct sk_buff * skb) { /* Charge it to the socket. */ - if (ip_queue_rcv_skb(sk, skb) < 0) { + ipv4_pktinfo_prepare(skb); + if (sock_queue_rcv_skb(sk, skb) < 0) { kfree_skb(skb); return NET_RX_DROP; } @@ -327,6 +328,7 @@ static int raw_send_hdrinc(struct sock *sk, struct flowi4 *fl4, unsigned int iphlen; int err; struct rtable *rt = *rtp; + int hlen, tlen; if (length > rt->dst.dev->mtu) { ip_local_error(sk, EMSGSIZE, fl4->daddr, inet->inet_dport, @@ -336,12 +338,14 @@ static int raw_send_hdrinc(struct sock *sk, struct flowi4 *fl4, if (flags&MSG_PROBE) goto out; + hlen = LL_RESERVED_SPACE(rt->dst.dev); + tlen = rt->dst.dev->needed_tailroom; skb = sock_alloc_send_skb(sk, - length + LL_ALLOCATED_SPACE(rt->dst.dev) + 15, + length + hlen + tlen + 15, flags & MSG_DONTWAIT, &err); if (skb == NULL) goto error; - skb_reserve(skb, LL_RESERVED_SPACE(rt->dst.dev)); + skb_reserve(skb, hlen); skb->priority = sk->sk_priority; skb->mark = sk->sk_mark; diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 155138d..fb47c8f 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -138,7 +138,7 @@ static int rt_chain_length_max __read_mostly = 20; static struct dst_entry *ipv4_dst_check(struct dst_entry *dst, u32 cookie); static unsigned int ipv4_default_advmss(const struct dst_entry *dst); -static unsigned int ipv4_default_mtu(const struct dst_entry *dst); +static unsigned int ipv4_mtu(const struct dst_entry *dst); static void ipv4_dst_destroy(struct dst_entry *dst); static struct dst_entry *ipv4_negative_advice(struct dst_entry *dst); static void ipv4_link_failure(struct sk_buff *skb); @@ -193,7 +193,7 @@ static struct dst_ops ipv4_dst_ops = { .gc = rt_garbage_collect, .check = ipv4_dst_check, .default_advmss = ipv4_default_advmss, - .default_mtu = ipv4_default_mtu, + .mtu = ipv4_mtu, .cow_metrics = ipv4_cow_metrics, .destroy = ipv4_dst_destroy, .ifdown = ipv4_dst_ifdown, @@ -1304,16 +1304,42 @@ static void rt_del(unsigned hash, struct rtable *rt) spin_unlock_bh(rt_hash_lock_addr(hash)); } +static int check_peer_redir(struct dst_entry *dst, struct inet_peer *peer) +{ + struct rtable *rt = (struct rtable *) dst; + __be32 orig_gw = rt->rt_gateway; + struct neighbour *n, *old_n; + + dst_confirm(&rt->dst); + + rt->rt_gateway = peer->redirect_learned.a4; + + n = ipv4_neigh_lookup(&rt->dst, &rt->rt_gateway); + if (IS_ERR(n)) + return PTR_ERR(n); + old_n = xchg(&rt->dst._neighbour, n); + if (old_n) + neigh_release(old_n); + if (!n || !(n->nud_state & NUD_VALID)) { + if (n) + neigh_event_send(n, NULL); + rt->rt_gateway = orig_gw; + return -EAGAIN; + } else { + rt->rt_flags |= RTCF_REDIRECTED; + call_netevent_notifiers(NETEVENT_NEIGH_UPDATE, n); + } + return 0; +} + /* called in rcu_read_lock() section */ void ip_rt_redirect(__be32 old_gw, __be32 daddr, __be32 new_gw, __be32 saddr, struct net_device *dev) { int s, i; struct in_device *in_dev = __in_dev_get_rcu(dev); - struct rtable *rt; __be32 skeys[2] = { saddr, 0 }; int ikeys[2] = { dev->ifindex, 0 }; - struct flowi4 fl4; struct inet_peer *peer; struct net *net; @@ -1336,33 +1362,42 @@ void ip_rt_redirect(__be32 old_gw, __be32 daddr, __be32 new_gw, goto reject_redirect; } - memset(&fl4, 0, sizeof(fl4)); - fl4.daddr = daddr; for (s = 0; s < 2; s++) { for (i = 0; i < 2; i++) { - fl4.flowi4_oif = ikeys[i]; - fl4.saddr = skeys[s]; - rt = __ip_route_output_key(net, &fl4); - if (IS_ERR(rt)) - continue; - - if (rt->dst.error || rt->dst.dev != dev || - rt->rt_gateway != old_gw) { - ip_rt_put(rt); - continue; - } + unsigned int hash; + struct rtable __rcu **rthp; + struct rtable *rt; + + hash = rt_hash(daddr, skeys[s], ikeys[i], rt_genid(net)); + + rthp = &rt_hash_table[hash].chain; + + while ((rt = rcu_dereference(*rthp)) != NULL) { + rthp = &rt->dst.rt_next; + + if (rt->rt_key_dst != daddr || + rt->rt_key_src != skeys[s] || + rt->rt_oif != ikeys[i] || + rt_is_input_route(rt) || + rt_is_expired(rt) || + !net_eq(dev_net(rt->dst.dev), net) || + rt->dst.error || + rt->dst.dev != dev || + rt->rt_gateway != old_gw) + continue; - if (!rt->peer) - rt_bind_peer(rt, rt->rt_dst, 1); + if (!rt->peer) + rt_bind_peer(rt, rt->rt_dst, 1); - peer = rt->peer; - if (peer) { - peer->redirect_learned.a4 = new_gw; - atomic_inc(&__rt_peer_genid); + peer = rt->peer; + if (peer) { + if (peer->redirect_learned.a4 != new_gw) { + peer->redirect_learned.a4 = new_gw; + atomic_inc(&__rt_peer_genid); + } + check_peer_redir(&rt->dst, peer); + } } - - ip_rt_put(rt); - return; } } return; @@ -1649,33 +1684,6 @@ static void ip_rt_update_pmtu(struct dst_entry *dst, u32 mtu) } } -static int check_peer_redir(struct dst_entry *dst, struct inet_peer *peer) -{ - struct rtable *rt = (struct rtable *) dst; - __be32 orig_gw = rt->rt_gateway; - struct neighbour *n, *old_n; - - dst_confirm(&rt->dst); - - rt->rt_gateway = peer->redirect_learned.a4; - - n = ipv4_neigh_lookup(&rt->dst, &rt->rt_gateway); - if (IS_ERR(n)) - return PTR_ERR(n); - old_n = xchg(&rt->dst._neighbour, n); - if (old_n) - neigh_release(old_n); - if (!n || !(n->nud_state & NUD_VALID)) { - if (n) - neigh_event_send(n, NULL); - rt->rt_gateway = orig_gw; - return -EAGAIN; - } else { - rt->rt_flags |= RTCF_REDIRECTED; - call_netevent_notifiers(NETEVENT_NEIGH_UPDATE, n); - } - return 0; -} static struct dst_entry *ipv4_dst_check(struct dst_entry *dst, u32 cookie) { @@ -1806,12 +1814,17 @@ static unsigned int ipv4_default_advmss(const struct dst_entry *dst) return advmss; } -static unsigned int ipv4_default_mtu(const struct dst_entry *dst) +static unsigned int ipv4_mtu(const struct dst_entry *dst) { - unsigned int mtu = dst->dev->mtu; + const struct rtable *rt = (const struct rtable *) dst; + unsigned int mtu = dst_metric_raw(dst, RTAX_MTU); + + if (mtu && rt_is_output_route(rt)) + return mtu; + + mtu = dst->dev->mtu; if (unlikely(dst_metric_locked(dst, RTAX_MTU))) { - const struct rtable *rt = (const struct rtable *) dst; if (rt->rt_gateway != rt->rt_dst && mtu > 576) mtu = 576; @@ -2747,9 +2760,11 @@ static struct dst_entry *ipv4_blackhole_dst_check(struct dst_entry *dst, u32 coo return NULL; } -static unsigned int ipv4_blackhole_default_mtu(const struct dst_entry *dst) +static unsigned int ipv4_blackhole_mtu(const struct dst_entry *dst) { - return 0; + unsigned int mtu = dst_metric_raw(dst, RTAX_MTU); + + return mtu ? : dst->dev->mtu; } static void ipv4_rt_blackhole_update_pmtu(struct dst_entry *dst, u32 mtu) @@ -2767,7 +2782,7 @@ static struct dst_ops ipv4_dst_blackhole_ops = { .protocol = cpu_to_be16(ETH_P_IP), .destroy = ipv4_dst_destroy, .check = ipv4_blackhole_dst_check, - .default_mtu = ipv4_blackhole_default_mtu, + .mtu = ipv4_blackhole_mtu, .default_advmss = ipv4_default_advmss, .update_pmtu = ipv4_rt_blackhole_update_pmtu, .cow_metrics = ipv4_rt_blackhole_cow_metrics, @@ -2845,7 +2860,7 @@ static int rt_fill_info(struct net *net, struct rtable *rt = skb_rtable(skb); struct rtmsg *r; struct nlmsghdr *nlh; - long expires = 0; + unsigned long expires = 0; const struct inet_peer *peer = rt->peer; u32 id = 0, ts = 0, tsage = 0, error; @@ -2902,8 +2917,12 @@ static int rt_fill_info(struct net *net, tsage = get_seconds() - peer->tcp_ts_stamp; } expires = ACCESS_ONCE(peer->pmtu_expires); - if (expires) - expires -= jiffies; + if (expires) { + if (time_before(jiffies, expires)) + expires -= jiffies; + else + expires = 0; + } } if (rt_is_input_route(rt)) { diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 34f5db1..50c3596 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -2653,7 +2653,8 @@ int compat_tcp_getsockopt(struct sock *sk, int level, int optname, EXPORT_SYMBOL(compat_tcp_getsockopt); #endif -struct sk_buff *tcp_tso_segment(struct sk_buff *skb, u32 features) +struct sk_buff *tcp_tso_segment(struct sk_buff *skb, + netdev_features_t features) { struct sk_buff *segs = ERR_PTR(-EINVAL); struct tcphdr *th; diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 52b5c2d..78dd38c 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -2858,7 +2858,7 @@ static void tcp_try_keep_open(struct sock *sk) struct tcp_sock *tp = tcp_sk(sk); int state = TCP_CA_Open; - if (tcp_left_out(tp) || tcp_any_retrans_done(sk) || tp->undo_marker) + if (tcp_left_out(tp) || tcp_any_retrans_done(sk)) state = TCP_CA_Disorder; if (inet_csk(sk)->icsk_ca_state != state) { @@ -2881,7 +2881,8 @@ static void tcp_try_to_open(struct sock *sk, int flag) if (inet_csk(sk)->icsk_ca_state != TCP_CA_CWR) { tcp_try_keep_open(sk); - tcp_moderate_cwnd(tp); + if (inet_csk(sk)->icsk_ca_state != TCP_CA_Open) + tcp_moderate_cwnd(tp); } else { tcp_cwnd_down(sk, flag); } @@ -3009,11 +3010,11 @@ static void tcp_update_cwnd_in_recovery(struct sock *sk, int newly_acked_sacked, * tcp_xmit_retransmit_queue(). */ static void tcp_fastretrans_alert(struct sock *sk, int pkts_acked, - int newly_acked_sacked, int flag) + int newly_acked_sacked, bool is_dupack, + int flag) { struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); - int is_dupack = !(flag & (FLAG_SND_UNA_ADVANCED | FLAG_NOT_DUP)); int do_lost = is_dupack || ((flag & FLAG_DATA_SACKED) && (tcp_fackets_out(tp) > tp->reordering)); int fast_rexmit = 0, mib_idx; @@ -3066,17 +3067,6 @@ static void tcp_fastretrans_alert(struct sock *sk, int pkts_acked, } break; - case TCP_CA_Disorder: - tcp_try_undo_dsack(sk); - if (!tp->undo_marker || - /* For SACK case do not Open to allow to undo - * catching for all duplicate ACKs. */ - tcp_is_reno(tp) || tp->snd_una != tp->high_seq) { - tp->undo_marker = 0; - tcp_set_ca_state(sk, TCP_CA_Open); - } - break; - case TCP_CA_Recovery: if (tcp_is_reno(tp)) tcp_reset_reno_sack(tp); @@ -3117,7 +3107,7 @@ static void tcp_fastretrans_alert(struct sock *sk, int pkts_acked, tcp_add_reno_sack(sk); } - if (icsk->icsk_ca_state == TCP_CA_Disorder) + if (icsk->icsk_ca_state <= TCP_CA_Disorder) tcp_try_undo_dsack(sk); if (!tcp_time_to_recover(sk)) { @@ -3681,10 +3671,12 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) u32 prior_snd_una = tp->snd_una; u32 ack_seq = TCP_SKB_CB(skb)->seq; u32 ack = TCP_SKB_CB(skb)->ack_seq; + bool is_dupack = false; u32 prior_in_flight; u32 prior_fackets; int prior_packets; int prior_sacked = tp->sacked_out; + int pkts_acked = 0; int newly_acked_sacked = 0; int frto_cwnd = 0; @@ -3757,6 +3749,7 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) /* See if we can take anything off of the retransmit queue. */ flag |= tcp_clean_rtx_queue(sk, prior_fackets, prior_snd_una); + pkts_acked = prior_packets - tp->packets_out; newly_acked_sacked = (prior_packets - prior_sacked) - (tp->packets_out - tp->sacked_out); @@ -3771,8 +3764,9 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) if ((flag & FLAG_DATA_ACKED) && !frto_cwnd && tcp_may_raise_cwnd(sk, flag)) tcp_cong_avoid(sk, ack, prior_in_flight); - tcp_fastretrans_alert(sk, prior_packets - tp->packets_out, - newly_acked_sacked, flag); + is_dupack = !(flag & (FLAG_SND_UNA_ADVANCED | FLAG_NOT_DUP)); + tcp_fastretrans_alert(sk, pkts_acked, newly_acked_sacked, + is_dupack, flag); } else { if ((flag & FLAG_DATA_ACKED) && !frto_cwnd) tcp_cong_avoid(sk, ack, prior_in_flight); @@ -3784,6 +3778,10 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) return 1; no_queue: + /* If data was DSACKed, see if we can undo a cwnd reduction. */ + if (flag & FLAG_DSACKING_ACK) + tcp_fastretrans_alert(sk, pkts_acked, newly_acked_sacked, + is_dupack, flag); /* If this ack opens up a zero window, clear backoff. It was * being used to time the probes, and is probably far higher than * it needs to be for normal retransmission. @@ -3797,10 +3795,14 @@ invalid_ack: return -1; old_ack: + /* If data was SACKed, tag it and see if we should send more data. + * If data was DSACKed, see if we can undo a cwnd reduction. + */ if (TCP_SKB_CB(skb)->sacked) { - tcp_sacktag_write_queue(sk, skb, prior_snd_una); - if (icsk->icsk_ca_state == TCP_CA_Open) - tcp_try_keep_open(sk); + flag |= tcp_sacktag_write_queue(sk, skb, prior_snd_una); + newly_acked_sacked = tp->sacked_out - prior_sacked; + tcp_fastretrans_alert(sk, pkts_acked, newly_acked_sacked, + is_dupack, flag); } SOCK_DEBUG(sk, "Ack %u before %u:%u\n", ack, tp->snd_una, tp->snd_nxt); diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index a744315..a9db4b1 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1510,6 +1510,7 @@ exit: NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENDROPS); return NULL; put_and_exit: + tcp_clear_xmit_timers(newsk); bh_unlock_sock(newsk); sock_put(newsk); goto exit; diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index 66363b6..945efff 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -343,8 +343,8 @@ void tcp_time_wait(struct sock *sk, int state, int timeo) tw->tw_ipv6_offset = inet6_tw_offset(sk->sk_prot); tw6 = inet6_twsk((struct sock *)tw); - ipv6_addr_copy(&tw6->tw_v6_daddr, &np->daddr); - ipv6_addr_copy(&tw6->tw_v6_rcv_saddr, &np->rcv_saddr); + tw6->tw_v6_daddr = np->daddr; + tw6->tw_v6_rcv_saddr = np->rcv_saddr; tw->tw_tclass = np->tclass; tw->tw_ipv6only = np->ipv6only; } @@ -425,7 +425,7 @@ static inline void TCP_ECN_openreq_child(struct tcp_sock *tp, */ struct sock *tcp_create_openreq_child(struct sock *sk, struct request_sock *req, struct sk_buff *skb) { - struct sock *newsk = inet_csk_clone(sk, req, GFP_ATOMIC); + struct sock *newsk = inet_csk_clone_lock(sk, req, GFP_ATOMIC); if (newsk != NULL) { const struct inet_request_sock *ireq = inet_rsk(req); diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 980b98f..63170e29 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -1382,7 +1382,7 @@ static inline int tcp_minshall_check(const struct tcp_sock *tp) /* Return 0, if packet can be sent now without violation Nagle's rules: * 1. It is full sized. * 2. Or it contains FIN. (already checked by caller) - * 3. Or TCP_NODELAY was set. + * 3. Or TCP_CORK is not set, and TCP_NODELAY is set. * 4. Or TCP_CORK is not set, and all sent packets are ACKed. * With Minshall's modification: all sent small packets are ACKed. */ diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index ab0966d..b867ea2 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1357,7 +1357,7 @@ static int __udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) if (inet_sk(sk)->inet_daddr) sock_rps_save_rxhash(sk, skb); - rc = ip_queue_rcv_skb(sk, skb); + rc = sock_queue_rcv_skb(sk, skb); if (rc < 0) { int is_udplite = IS_UDPLITE(sk); @@ -1473,6 +1473,7 @@ int udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) rc = 0; + ipv4_pktinfo_prepare(skb); bh_lock_sock(sk); if (!sock_owned_by_user(sk)) rc = __udp_queue_rcv_skb(sk, skb); @@ -2246,7 +2247,8 @@ int udp4_ufo_send_check(struct sk_buff *skb) return 0; } -struct sk_buff *udp4_ufo_fragment(struct sk_buff *skb, u32 features) +struct sk_buff *udp4_ufo_fragment(struct sk_buff *skb, + netdev_features_t features) { struct sk_buff *segs = ERR_PTR(-EINVAL); unsigned int mss; diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index cf88df8..5860517 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -636,7 +636,7 @@ ipv6_add_addr(struct inet6_dev *idev, const struct in6_addr *addr, int pfxlen, goto out; } - ipv6_addr_copy(&ifa->addr, addr); + ifa->addr = *addr; spin_lock_init(&ifa->lock); spin_lock_init(&ifa->state_lock); @@ -1228,7 +1228,7 @@ try_nextdev: if (!hiscore->ifa) return -EADDRNOTAVAIL; - ipv6_addr_copy(saddr, &hiscore->ifa->addr); + *saddr = hiscore->ifa->addr; in6_ifa_put(hiscore->ifa); return 0; } @@ -1249,7 +1249,7 @@ int ipv6_get_lladdr(struct net_device *dev, struct in6_addr *addr, list_for_each_entry(ifp, &idev->addr_list, if_list) { if (ifp->scope == IFA_LINK && !(ifp->flags & banned_flags)) { - ipv6_addr_copy(addr, &ifp->addr); + *addr = ifp->addr; err = 0; break; } @@ -1700,7 +1700,7 @@ addrconf_prefix_route(struct in6_addr *pfx, int plen, struct net_device *dev, .fc_protocol = RTPROT_KERNEL, }; - ipv6_addr_copy(&cfg.fc_dst, pfx); + cfg.fc_dst = *pfx; /* Prevent useless cloning on PtP SIT. This thing is done here expecting that the whole diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index d27c797..7694c82 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -347,7 +347,7 @@ int inet6_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) */ v4addr = LOOPBACK4_IPV6; if (!(addr_type & IPV6_ADDR_MULTICAST)) { - if (!inet->transparent && + if (!(inet->freebind || inet->transparent) && !ipv6_chk_addr(net, &addr->sin6_addr, dev, 0)) { err = -EADDRNOTAVAIL; @@ -361,10 +361,10 @@ int inet6_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) inet->inet_rcv_saddr = v4addr; inet->inet_saddr = v4addr; - ipv6_addr_copy(&np->rcv_saddr, &addr->sin6_addr); + np->rcv_saddr = addr->sin6_addr; if (!(addr_type & IPV6_ADDR_MULTICAST)) - ipv6_addr_copy(&np->saddr, &addr->sin6_addr); + np->saddr = addr->sin6_addr; /* Make sure we are allowed to bind here. */ if (sk->sk_prot->get_port(sk, snum)) { @@ -458,14 +458,14 @@ int inet6_getname(struct socket *sock, struct sockaddr *uaddr, peer == 1) return -ENOTCONN; sin->sin6_port = inet->inet_dport; - ipv6_addr_copy(&sin->sin6_addr, &np->daddr); + sin->sin6_addr = np->daddr; if (np->sndflow) sin->sin6_flowinfo = np->flow_label; } else { if (ipv6_addr_any(&np->rcv_saddr)) - ipv6_addr_copy(&sin->sin6_addr, &np->saddr); + sin->sin6_addr = np->saddr; else - ipv6_addr_copy(&sin->sin6_addr, &np->rcv_saddr); + sin->sin6_addr = np->rcv_saddr; sin->sin6_port = inet->inet_sport; } @@ -660,8 +660,8 @@ int inet6_sk_rebuild_header(struct sock *sk) memset(&fl6, 0, sizeof(fl6)); fl6.flowi6_proto = sk->sk_protocol; - ipv6_addr_copy(&fl6.daddr, &np->daddr); - ipv6_addr_copy(&fl6.saddr, &np->saddr); + fl6.daddr = np->daddr; + fl6.saddr = np->saddr; fl6.flowlabel = np->flow_label; fl6.flowi6_oif = sk->sk_bound_dev_if; fl6.flowi6_mark = sk->sk_mark; @@ -769,7 +769,8 @@ out: return err; } -static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb, u32 features) +static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb, + netdev_features_t features) { struct sk_buff *segs = ERR_PTR(-EINVAL); struct ipv6hdr *ipv6h; @@ -985,9 +986,9 @@ static int __net_init ipv6_init_mibs(struct net *net) sizeof(struct icmpv6_mib), __alignof__(struct icmpv6_mib)) < 0) goto err_icmp_mib; - if (snmp_mib_init((void __percpu **)net->mib.icmpv6msg_statistics, - sizeof(struct icmpv6msg_mib), - __alignof__(struct icmpv6msg_mib)) < 0) + net->mib.icmpv6msg_statistics = kzalloc(sizeof(struct icmpv6msg_mib), + GFP_KERNEL); + if (!net->mib.icmpv6msg_statistics) goto err_icmpmsg_mib; return 0; @@ -1008,7 +1009,7 @@ static void ipv6_cleanup_mibs(struct net *net) snmp_mib_free((void __percpu **)net->mib.udplite_stats_in6); snmp_mib_free((void __percpu **)net->mib.ipv6_statistics); snmp_mib_free((void __percpu **)net->mib.icmpv6_statistics); - snmp_mib_free((void __percpu **)net->mib.icmpv6msg_statistics); + kfree(net->mib.icmpv6msg_statistics); } static int __net_init inet6_net_init(struct net *net) diff --git a/net/ipv6/ah6.c b/net/ipv6/ah6.c index 2195ae6..2ae79db 100644 --- a/net/ipv6/ah6.c +++ b/net/ipv6/ah6.c @@ -193,9 +193,9 @@ static void ipv6_rearrange_destopt(struct ipv6hdr *iph, struct ipv6_opt_hdr *des printk(KERN_WARNING "destopt hao: invalid header length: %u\n", hao->length); goto bad; } - ipv6_addr_copy(&final_addr, &hao->addr); - ipv6_addr_copy(&hao->addr, &iph->saddr); - ipv6_addr_copy(&iph->saddr, &final_addr); + final_addr = hao->addr; + hao->addr = iph->saddr; + iph->saddr = final_addr; } break; } @@ -241,13 +241,13 @@ static void ipv6_rearrange_rthdr(struct ipv6hdr *iph, struct ipv6_rt_hdr *rthdr) segments = rthdr->hdrlen >> 1; addrs = ((struct rt0_hdr *)rthdr)->addr; - ipv6_addr_copy(&final_addr, addrs + segments - 1); + final_addr = addrs[segments - 1]; addrs += segments - segments_left; memmove(addrs + 1, addrs, (segments_left - 1) * sizeof(*addrs)); - ipv6_addr_copy(addrs, &iph->daddr); - ipv6_addr_copy(&iph->daddr, &final_addr); + addrs[0] = iph->daddr; + iph->daddr = final_addr; } static int ipv6_clear_mutable_options(struct ipv6hdr *iph, int len, int dir) @@ -324,8 +324,6 @@ static void ah6_output_done(struct crypto_async_request *base, int err) #endif } - err = ah->nexthdr; - kfree(AH_SKB_CB(skb)->tmp); xfrm_output_resume(skb, err); } @@ -466,12 +464,12 @@ static void ah6_input_done(struct crypto_async_request *base, int err) if (err) goto out; + err = ah->nexthdr; + skb->network_header += ah_hlen; memcpy(skb_network_header(skb), work_iph, hdr_len); __skb_pull(skb, ah_hlen + hdr_len); skb_set_transport_header(skb, -hdr_len); - - err = ah->nexthdr; out: kfree(AH_SKB_CB(skb)->tmp); xfrm_input_resume(skb, err); @@ -583,8 +581,6 @@ static int ah6_input(struct xfrm_state *x, struct sk_buff *skb) if (err == -EINPROGRESS) goto out; - if (err == -EBUSY) - err = NET_XMIT_DROP; goto out_free; } diff --git a/net/ipv6/anycast.c b/net/ipv6/anycast.c index 674255f..fc1cdcd 100644 --- a/net/ipv6/anycast.c +++ b/net/ipv6/anycast.c @@ -75,7 +75,7 @@ int ipv6_sock_ac_join(struct sock *sk, int ifindex, const struct in6_addr *addr) if (pac == NULL) return -ENOMEM; pac->acl_next = NULL; - ipv6_addr_copy(&pac->acl_addr, addr); + pac->acl_addr = *addr; rcu_read_lock(); if (ifindex == 0) { @@ -296,7 +296,7 @@ int ipv6_dev_ac_inc(struct net_device *dev, const struct in6_addr *addr) goto out; } - ipv6_addr_copy(&aca->aca_addr, addr); + aca->aca_addr = *addr; aca->aca_idev = idev; aca->aca_rt = rt; aca->aca_users = 1; diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c index e248069..ae08aee 100644 --- a/net/ipv6/datagram.c +++ b/net/ipv6/datagram.c @@ -71,7 +71,7 @@ int ip6_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) flowlabel = fl6_sock_lookup(sk, fl6.flowlabel); if (flowlabel == NULL) return -EINVAL; - ipv6_addr_copy(&usin->sin6_addr, &flowlabel->dst); + usin->sin6_addr = flowlabel->dst; } } @@ -143,7 +143,7 @@ ipv4_connected: } } - ipv6_addr_copy(&np->daddr, daddr); + np->daddr = *daddr; np->flow_label = fl6.flowlabel; inet->inet_dport = usin->sin6_port; @@ -154,8 +154,8 @@ ipv4_connected: */ fl6.flowi6_proto = sk->sk_protocol; - ipv6_addr_copy(&fl6.daddr, &np->daddr); - ipv6_addr_copy(&fl6.saddr, &np->saddr); + fl6.daddr = np->daddr; + fl6.saddr = np->saddr; fl6.flowi6_oif = sk->sk_bound_dev_if; fl6.flowi6_mark = sk->sk_mark; fl6.fl6_dport = inet->inet_dport; @@ -179,10 +179,10 @@ ipv4_connected: /* source address lookup done in ip6_dst_lookup */ if (ipv6_addr_any(&np->saddr)) - ipv6_addr_copy(&np->saddr, &fl6.saddr); + np->saddr = fl6.saddr; if (ipv6_addr_any(&np->rcv_saddr)) { - ipv6_addr_copy(&np->rcv_saddr, &fl6.saddr); + np->rcv_saddr = fl6.saddr; inet->inet_rcv_saddr = LOOPBACK4_IPV6; if (sk->sk_prot->rehash) sk->sk_prot->rehash(sk); @@ -257,7 +257,7 @@ void ipv6_local_error(struct sock *sk, int err, struct flowi6 *fl6, u32 info) skb_put(skb, sizeof(struct ipv6hdr)); skb_reset_network_header(skb); iph = ipv6_hdr(skb); - ipv6_addr_copy(&iph->daddr, &fl6->daddr); + iph->daddr = fl6->daddr; serr = SKB_EXT_ERR(skb); serr->ee.ee_errno = err; @@ -294,7 +294,7 @@ void ipv6_local_rxpmtu(struct sock *sk, struct flowi6 *fl6, u32 mtu) skb_put(skb, sizeof(struct ipv6hdr)); skb_reset_network_header(skb); iph = ipv6_hdr(skb); - ipv6_addr_copy(&iph->daddr, &fl6->daddr); + iph->daddr = fl6->daddr; mtu_info = IP6CBMTU(skb); @@ -303,7 +303,7 @@ void ipv6_local_rxpmtu(struct sock *sk, struct flowi6 *fl6, u32 mtu) mtu_info->ip6m_addr.sin6_port = 0; mtu_info->ip6m_addr.sin6_flowinfo = 0; mtu_info->ip6m_addr.sin6_scope_id = fl6->flowi6_oif; - ipv6_addr_copy(&mtu_info->ip6m_addr.sin6_addr, &ipv6_hdr(skb)->daddr); + mtu_info->ip6m_addr.sin6_addr = ipv6_hdr(skb)->daddr; __skb_pull(skb, skb_tail_pointer(skb) - skb->data); skb_reset_transport_header(skb); @@ -354,8 +354,8 @@ int ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len) sin->sin6_port = serr->port; sin->sin6_scope_id = 0; if (skb->protocol == htons(ETH_P_IPV6)) { - ipv6_addr_copy(&sin->sin6_addr, - (struct in6_addr *)(nh + serr->addr_offset)); + sin->sin6_addr = + *(struct in6_addr *)(nh + serr->addr_offset); if (np->sndflow) sin->sin6_flowinfo = (*(__be32 *)(nh + serr->addr_offset - 24) & @@ -376,7 +376,7 @@ int ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len) sin->sin6_flowinfo = 0; sin->sin6_scope_id = 0; if (skb->protocol == htons(ETH_P_IPV6)) { - ipv6_addr_copy(&sin->sin6_addr, &ipv6_hdr(skb)->saddr); + sin->sin6_addr = ipv6_hdr(skb)->saddr; if (np->rxopt.all) datagram_recv_ctl(sk, msg, skb); if (ipv6_addr_type(&sin->sin6_addr) & IPV6_ADDR_LINKLOCAL) @@ -451,7 +451,7 @@ int ipv6_recv_rxpmtu(struct sock *sk, struct msghdr *msg, int len) sin->sin6_flowinfo = 0; sin->sin6_port = 0; sin->sin6_scope_id = mtu_info.ip6m_addr.sin6_scope_id; - ipv6_addr_copy(&sin->sin6_addr, &mtu_info.ip6m_addr.sin6_addr); + sin->sin6_addr = mtu_info.ip6m_addr.sin6_addr; } put_cmsg(msg, SOL_IPV6, IPV6_PATHMTU, sizeof(mtu_info), &mtu_info); @@ -475,7 +475,7 @@ int datagram_recv_ctl(struct sock *sk, struct msghdr *msg, struct sk_buff *skb) struct in6_pktinfo src_info; src_info.ipi6_ifindex = opt->iif; - ipv6_addr_copy(&src_info.ipi6_addr, &ipv6_hdr(skb)->daddr); + src_info.ipi6_addr = ipv6_hdr(skb)->daddr; put_cmsg(msg, SOL_IPV6, IPV6_PKTINFO, sizeof(src_info), &src_info); } @@ -550,7 +550,7 @@ int datagram_recv_ctl(struct sock *sk, struct msghdr *msg, struct sk_buff *skb) struct in6_pktinfo src_info; src_info.ipi6_ifindex = opt->iif; - ipv6_addr_copy(&src_info.ipi6_addr, &ipv6_hdr(skb)->daddr); + src_info.ipi6_addr = ipv6_hdr(skb)->daddr; put_cmsg(msg, SOL_IPV6, IPV6_2292PKTINFO, sizeof(src_info), &src_info); } if (np->rxopt.bits.rxohlim) { @@ -584,7 +584,7 @@ int datagram_recv_ctl(struct sock *sk, struct msghdr *msg, struct sk_buff *skb) */ sin6.sin6_family = AF_INET6; - ipv6_addr_copy(&sin6.sin6_addr, &ipv6_hdr(skb)->daddr); + sin6.sin6_addr = ipv6_hdr(skb)->daddr; sin6.sin6_port = ports[1]; sin6.sin6_flowinfo = 0; sin6.sin6_scope_id = 0; @@ -654,12 +654,12 @@ int datagram_send_ctl(struct net *net, struct sock *sk, if (addr_type != IPV6_ADDR_ANY) { int strict = __ipv6_addr_src_scope(addr_type) <= IPV6_ADDR_SCOPE_LINKLOCAL; - if (!inet_sk(sk)->transparent && + if (!(inet_sk(sk)->freebind || inet_sk(sk)->transparent) && !ipv6_chk_addr(net, &src_info->ipi6_addr, strict ? dev : NULL, 0)) err = -EINVAL; else - ipv6_addr_copy(&fl6->saddr, &src_info->ipi6_addr); + fl6->saddr = src_info->ipi6_addr; } rcu_read_unlock(); diff --git a/net/ipv6/exthdrs.c b/net/ipv6/exthdrs.c index bf22a22..3d641b6 100644 --- a/net/ipv6/exthdrs.c +++ b/net/ipv6/exthdrs.c @@ -243,9 +243,9 @@ static int ipv6_dest_hao(struct sk_buff *skb, int optoff) if (skb->ip_summed == CHECKSUM_COMPLETE) skb->ip_summed = CHECKSUM_NONE; - ipv6_addr_copy(&tmp_addr, &ipv6h->saddr); - ipv6_addr_copy(&ipv6h->saddr, &hao->addr); - ipv6_addr_copy(&hao->addr, &tmp_addr); + tmp_addr = ipv6h->saddr; + ipv6h->saddr = hao->addr; + hao->addr = tmp_addr; if (skb->tstamp.tv64 == 0) __net_timestamp(skb); @@ -461,9 +461,9 @@ looped_back: return -1; } - ipv6_addr_copy(&daddr, addr); - ipv6_addr_copy(addr, &ipv6_hdr(skb)->daddr); - ipv6_addr_copy(&ipv6_hdr(skb)->daddr, &daddr); + daddr = *addr; + *addr = ipv6_hdr(skb)->daddr; + ipv6_hdr(skb)->daddr = daddr; skb_dst_drop(skb); ip6_route_input(skb); @@ -690,7 +690,7 @@ static void ipv6_push_rthdr(struct sk_buff *skb, u8 *proto, memcpy(phdr->addr, ihdr->addr + 1, (hops - 1) * sizeof(struct in6_addr)); - ipv6_addr_copy(phdr->addr + (hops - 1), *addr_p); + phdr->addr[hops - 1] = **addr_p; *addr_p = ihdr->addr; phdr->rt_hdr.nexthdr = *proto; @@ -888,8 +888,8 @@ struct in6_addr *fl6_update_dst(struct flowi6 *fl6, if (!opt || !opt->srcrt) return NULL; - ipv6_addr_copy(orig, &fl6->daddr); - ipv6_addr_copy(&fl6->daddr, ((struct rt0_hdr *)opt->srcrt)->addr); + *orig = fl6->daddr; + fl6->daddr = *((struct rt0_hdr *)opt->srcrt)->addr; return orig; } diff --git a/net/ipv6/fib6_rules.c b/net/ipv6/fib6_rules.c index 2955715..b6c5731 100644 --- a/net/ipv6/fib6_rules.c +++ b/net/ipv6/fib6_rules.c @@ -96,7 +96,7 @@ static int fib6_rule_action(struct fib_rule *rule, struct flowi *flp, if (!ipv6_prefix_equal(&saddr, &r->src.addr, r->src.plen)) goto again; - ipv6_addr_copy(&flp6->saddr, &saddr); + flp6->saddr = saddr; } goto out; } diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c index 90868fb..9e2bdcc 100644 --- a/net/ipv6/icmp.c +++ b/net/ipv6/icmp.c @@ -290,9 +290,9 @@ static void mip6_addr_swap(struct sk_buff *skb) if (likely(off >= 0)) { hao = (struct ipv6_destopt_hao *) (skb_network_header(skb) + off); - ipv6_addr_copy(&tmp, &iph->saddr); - ipv6_addr_copy(&iph->saddr, &hao->addr); - ipv6_addr_copy(&hao->addr, &tmp); + tmp = iph->saddr; + iph->saddr = hao->addr; + hao->addr = tmp; } } } @@ -444,9 +444,9 @@ void icmpv6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info) memset(&fl6, 0, sizeof(fl6)); fl6.flowi6_proto = IPPROTO_ICMPV6; - ipv6_addr_copy(&fl6.daddr, &hdr->saddr); + fl6.daddr = hdr->saddr; if (saddr) - ipv6_addr_copy(&fl6.saddr, saddr); + fl6.saddr = *saddr; fl6.flowi6_oif = iif; fl6.fl6_icmp_type = type; fl6.fl6_icmp_code = code; @@ -538,9 +538,9 @@ static void icmpv6_echo_reply(struct sk_buff *skb) memset(&fl6, 0, sizeof(fl6)); fl6.flowi6_proto = IPPROTO_ICMPV6; - ipv6_addr_copy(&fl6.daddr, &ipv6_hdr(skb)->saddr); + fl6.daddr = ipv6_hdr(skb)->saddr; if (saddr) - ipv6_addr_copy(&fl6.saddr, saddr); + fl6.saddr = *saddr; fl6.flowi6_oif = skb->dev->ifindex; fl6.fl6_icmp_type = ICMPV6_ECHO_REPLY; security_skb_classify_flow(skb, flowi6_to_flowi(&fl6)); @@ -786,8 +786,8 @@ void icmpv6_flow_init(struct sock *sk, struct flowi6 *fl6, int oif) { memset(fl6, 0, sizeof(*fl6)); - ipv6_addr_copy(&fl6->saddr, saddr); - ipv6_addr_copy(&fl6->daddr, daddr); + fl6->saddr = *saddr; + fl6->daddr = *daddr; fl6->flowi6_proto = IPPROTO_ICMPV6; fl6->fl6_icmp_type = type; fl6->fl6_icmp_code = 0; diff --git a/net/ipv6/inet6_connection_sock.c b/net/ipv6/inet6_connection_sock.c index fee46d5..02dd203 100644 --- a/net/ipv6/inet6_connection_sock.c +++ b/net/ipv6/inet6_connection_sock.c @@ -65,9 +65,9 @@ struct dst_entry *inet6_csk_route_req(struct sock *sk, memset(&fl6, 0, sizeof(fl6)); fl6.flowi6_proto = IPPROTO_TCP; - ipv6_addr_copy(&fl6.daddr, &treq->rmt_addr); + fl6.daddr = treq->rmt_addr; final_p = fl6_update_dst(&fl6, np->opt, &final); - ipv6_addr_copy(&fl6.saddr, &treq->loc_addr); + fl6.saddr = treq->loc_addr; fl6.flowi6_oif = sk->sk_bound_dev_if; fl6.flowi6_mark = sk->sk_mark; fl6.fl6_dport = inet_rsk(req)->rmt_port; @@ -85,7 +85,7 @@ struct dst_entry *inet6_csk_route_req(struct sock *sk, * request_sock (formerly open request) hash tables. */ static u32 inet6_synq_hash(const struct in6_addr *raddr, const __be16 rport, - const u32 rnd, const u16 synq_hsize) + const u32 rnd, const u32 synq_hsize) { u32 c; @@ -157,7 +157,7 @@ void inet6_csk_addr2sockaddr(struct sock *sk, struct sockaddr * uaddr) struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *) uaddr; sin6->sin6_family = AF_INET6; - ipv6_addr_copy(&sin6->sin6_addr, &np->daddr); + sin6->sin6_addr = np->daddr; sin6->sin6_port = inet_sk(sk)->inet_dport; /* We do not store received flowlabel for TCP */ sin6->sin6_flowinfo = 0; @@ -215,8 +215,8 @@ int inet6_csk_xmit(struct sk_buff *skb, struct flowi *fl_unused) memset(&fl6, 0, sizeof(fl6)); fl6.flowi6_proto = sk->sk_protocol; - ipv6_addr_copy(&fl6.daddr, &np->daddr); - ipv6_addr_copy(&fl6.saddr, &np->saddr); + fl6.daddr = np->daddr; + fl6.saddr = np->saddr; fl6.flowlabel = np->flow_label; IP6_ECN_flow_xmit(sk, fl6.flowlabel); fl6.flowi6_oif = sk->sk_bound_dev_if; @@ -246,7 +246,7 @@ int inet6_csk_xmit(struct sk_buff *skb, struct flowi *fl_unused) skb_dst_set_noref(skb, dst); /* Restore final destination back after routing done */ - ipv6_addr_copy(&fl6.daddr, &np->daddr); + fl6.daddr = np->daddr; res = ip6_xmit(sk, skb, &fl6, np->opt, np->tclass); rcu_read_unlock(); diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 93718f3..424f063 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -425,7 +425,8 @@ out: static struct fib6_node * fib6_add_1(struct fib6_node *root, void *addr, int addrlen, int plen, - int offset) + int offset, int allow_create, + int replace_required) { struct fib6_node *fn, *in, *ln; struct fib6_node *pn = NULL; @@ -447,8 +448,18 @@ static struct fib6_node * fib6_add_1(struct fib6_node *root, void *addr, * Prefix match */ if (plen < fn->fn_bit || - !ipv6_prefix_equal(&key->addr, addr, fn->fn_bit)) + !ipv6_prefix_equal(&key->addr, addr, fn->fn_bit)) { + if (!allow_create) { + if (replace_required) { + pr_warn("IPv6: Can't replace route, " + "no match found\n"); + return ERR_PTR(-ENOENT); + } + pr_warn("IPv6: NLM_F_CREATE should be set " + "when creating new route\n"); + } goto insert_above; + } /* * Exact match ? @@ -477,6 +488,23 @@ static struct fib6_node * fib6_add_1(struct fib6_node *root, void *addr, fn = dir ? fn->right: fn->left; } while (fn); + if (!allow_create) { + /* We should not create new node because + * NLM_F_REPLACE was specified without NLM_F_CREATE + * I assume it is safe to require NLM_F_CREATE when + * REPLACE flag is used! Later we may want to remove the + * check for replace_required, because according + * to netlink specification, NLM_F_CREATE + * MUST be specified if new route is created. + * That would keep IPv6 consistent with IPv4 + */ + if (replace_required) { + pr_warn("IPv6: Can't replace route, no match found\n"); + return ERR_PTR(-ENOENT); + } + pr_warn("IPv6: NLM_F_CREATE should be set " + "when creating new route\n"); + } /* * We walked to the bottom of tree. * Create new leaf node without children. @@ -614,6 +642,11 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt, { struct rt6_info *iter = NULL; struct rt6_info **ins; + int replace = (NULL != info->nlh && + (info->nlh->nlmsg_flags&NLM_F_REPLACE)); + int add = (NULL == info->nlh || + (info->nlh->nlmsg_flags&NLM_F_CREATE)); + int found = 0; ins = &fn->leaf; @@ -626,6 +659,13 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt, /* * Same priority level */ + if (NULL != info->nlh && + (info->nlh->nlmsg_flags&NLM_F_EXCL)) + return -EEXIST; + if (replace) { + found++; + break; + } if (iter->rt6i_dev == rt->rt6i_dev && iter->rt6i_idev == rt->rt6i_idev && @@ -655,17 +695,40 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt, /* * insert node */ + if (!replace) { + if (!add) + pr_warn("IPv6: NLM_F_CREATE should be set when creating new route\n"); + +add: + rt->dst.rt6_next = iter; + *ins = rt; + rt->rt6i_node = fn; + atomic_inc(&rt->rt6i_ref); + inet6_rt_notify(RTM_NEWROUTE, rt, info); + info->nl_net->ipv6.rt6_stats->fib_rt_entries++; + + if ((fn->fn_flags & RTN_RTINFO) == 0) { + info->nl_net->ipv6.rt6_stats->fib_route_nodes++; + fn->fn_flags |= RTN_RTINFO; + } - rt->dst.rt6_next = iter; - *ins = rt; - rt->rt6i_node = fn; - atomic_inc(&rt->rt6i_ref); - inet6_rt_notify(RTM_NEWROUTE, rt, info); - info->nl_net->ipv6.rt6_stats->fib_rt_entries++; - - if ((fn->fn_flags & RTN_RTINFO) == 0) { - info->nl_net->ipv6.rt6_stats->fib_route_nodes++; - fn->fn_flags |= RTN_RTINFO; + } else { + if (!found) { + if (add) + goto add; + pr_warn("IPv6: NLM_F_REPLACE set, but no existing node found!\n"); + return -ENOENT; + } + *ins = rt; + rt->rt6i_node = fn; + rt->dst.rt6_next = iter->dst.rt6_next; + atomic_inc(&rt->rt6i_ref); + inet6_rt_notify(RTM_NEWROUTE, rt, info); + rt6_release(iter); + if ((fn->fn_flags & RTN_RTINFO) == 0) { + info->nl_net->ipv6.rt6_stats->fib_route_nodes++; + fn->fn_flags |= RTN_RTINFO; + } } return 0; @@ -696,9 +759,25 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt, struct nl_info *info) { struct fib6_node *fn, *pn = NULL; int err = -ENOMEM; + int allow_create = 1; + int replace_required = 0; + if (NULL != info->nlh) { + if (!(info->nlh->nlmsg_flags&NLM_F_CREATE)) + allow_create = 0; + if ((info->nlh->nlmsg_flags&NLM_F_REPLACE)) + replace_required = 1; + } + if (!allow_create && !replace_required) + pr_warn("IPv6: RTM_NEWROUTE with no NLM_F_CREATE or NLM_F_REPLACE\n"); fn = fib6_add_1(root, &rt->rt6i_dst.addr, sizeof(struct in6_addr), - rt->rt6i_dst.plen, offsetof(struct rt6_info, rt6i_dst)); + rt->rt6i_dst.plen, offsetof(struct rt6_info, rt6i_dst), + allow_create, replace_required); + + if (IS_ERR(fn)) { + err = PTR_ERR(fn); + fn = NULL; + } if (fn == NULL) goto out; @@ -736,7 +815,8 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt, struct nl_info *info) sn = fib6_add_1(sfn, &rt->rt6i_src.addr, sizeof(struct in6_addr), rt->rt6i_src.plen, - offsetof(struct rt6_info, rt6i_src)); + offsetof(struct rt6_info, rt6i_src), + allow_create, replace_required); if (sn == NULL) { /* If it is failed, discard just allocated @@ -753,8 +833,13 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt, struct nl_info *info) } else { sn = fib6_add_1(fn->subtree, &rt->rt6i_src.addr, sizeof(struct in6_addr), rt->rt6i_src.plen, - offsetof(struct rt6_info, rt6i_src)); + offsetof(struct rt6_info, rt6i_src), + allow_create, replace_required); + if (IS_ERR(sn)) { + err = PTR_ERR(sn); + sn = NULL; + } if (sn == NULL) goto st_failure; } diff --git a/net/ipv6/ip6_flowlabel.c b/net/ipv6/ip6_flowlabel.c index 4566dbd..b7867a1 100644 --- a/net/ipv6/ip6_flowlabel.c +++ b/net/ipv6/ip6_flowlabel.c @@ -386,7 +386,7 @@ fl_create(struct net *net, struct sock *sk, struct in6_flowlabel_req *freq, err = -EINVAL; goto done; } - ipv6_addr_copy(&fl->dst, &freq->flr_dst); + fl->dst = freq->flr_dst; atomic_set(&fl->users, 1); switch (fl->share) { case IPV6_FL_S_EXCL: diff --git a/net/ipv6/ip6_input.c b/net/ipv6/ip6_input.c index 027c7ff..a46c64e 100644 --- a/net/ipv6/ip6_input.c +++ b/net/ipv6/ip6_input.c @@ -111,6 +111,14 @@ int ipv6_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt ipv6_addr_loopback(&hdr->daddr)) goto err; + /* + * RFC4291 2.7 + * Multicast addresses must not be used as source addresses in IPv6 + * packets or appear in any Routing header. + */ + if (ipv6_addr_is_multicast(&hdr->saddr)) + goto err; + skb->transport_header = skb->network_header + sizeof(*hdr); IP6CB(skb)->nhoff = offsetof(struct ipv6hdr, nexthdr); diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 84d0bd5..a24e155 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -238,8 +238,8 @@ int ip6_xmit(struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6, hdr->nexthdr = proto; hdr->hop_limit = hlimit; - ipv6_addr_copy(&hdr->saddr, &fl6->saddr); - ipv6_addr_copy(&hdr->daddr, first_hop); + hdr->saddr = fl6->saddr; + hdr->daddr = *first_hop; skb->priority = sk->sk_priority; skb->mark = sk->sk_mark; @@ -290,8 +290,8 @@ int ip6_nd_hdr(struct sock *sk, struct sk_buff *skb, struct net_device *dev, hdr->nexthdr = proto; hdr->hop_limit = np->hop_limit; - ipv6_addr_copy(&hdr->saddr, saddr); - ipv6_addr_copy(&hdr->daddr, daddr); + hdr->saddr = *saddr; + hdr->daddr = *daddr; return 0; } @@ -631,6 +631,7 @@ int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)) struct ipv6hdr *tmp_hdr; struct frag_hdr *fh; unsigned int mtu, hlen, left, len; + int hroom, troom; __be32 frag_id = 0; int ptr, offset = 0, err=0; u8 *prevhdr, nexthdr = 0; @@ -797,6 +798,8 @@ slow_path: */ *prevhdr = NEXTHDR_FRAGMENT; + hroom = LL_RESERVED_SPACE(rt->dst.dev); + troom = rt->dst.dev->needed_tailroom; /* * Keep copying data until we run out. @@ -815,7 +818,8 @@ slow_path: * Allocate buffer. */ - if ((frag = alloc_skb(len+hlen+sizeof(struct frag_hdr)+LL_ALLOCATED_SPACE(rt->dst.dev), GFP_ATOMIC)) == NULL) { + if ((frag = alloc_skb(len + hlen + sizeof(struct frag_hdr) + + hroom + troom, GFP_ATOMIC)) == NULL) { NETDEBUG(KERN_INFO "IPv6: frag: no memory for new fragment!\n"); IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_FRAGFAILS); @@ -828,7 +832,7 @@ slow_path: */ ip6_copy_metadata(frag, skb); - skb_reserve(frag, LL_RESERVED_SPACE(rt->dst.dev)); + skb_reserve(frag, hroom); skb_put(frag, len + hlen + sizeof(struct frag_hdr)); skb_reset_network_header(frag); fh = (struct frag_hdr *)(skb_network_header(frag) + hlen); @@ -1059,7 +1063,7 @@ struct dst_entry *ip6_dst_lookup_flow(struct sock *sk, struct flowi6 *fl6, if (err) return ERR_PTR(err); if (final_dst) - ipv6_addr_copy(&fl6->daddr, final_dst); + fl6->daddr = *final_dst; if (can_sleep) fl6->flowi6_flags |= FLOWI_FLAG_CAN_SLEEP; @@ -1095,7 +1099,7 @@ struct dst_entry *ip6_sk_dst_lookup_flow(struct sock *sk, struct flowi6 *fl6, if (err) return ERR_PTR(err); if (final_dst) - ipv6_addr_copy(&fl6->daddr, final_dst); + fl6->daddr = *final_dst; if (can_sleep) fl6->flowi6_flags |= FLOWI_FLAG_CAN_SLEEP; @@ -1588,7 +1592,7 @@ int ip6_push_pending_frames(struct sock *sk) if (np->pmtudisc < IPV6_PMTUDISC_DO) skb->local_df = 1; - ipv6_addr_copy(final_dst, &fl6->daddr); + *final_dst = fl6->daddr; __skb_pull(skb, skb_network_header_len(skb)); if (opt && opt->opt_flen) ipv6_push_frag_opts(skb, opt, &proto); @@ -1604,8 +1608,8 @@ int ip6_push_pending_frames(struct sock *sk) hdr->hop_limit = np->cork.hop_limit; hdr->nexthdr = proto; - ipv6_addr_copy(&hdr->saddr, &fl6->saddr); - ipv6_addr_copy(&hdr->daddr, final_dst); + hdr->saddr = fl6->saddr; + hdr->daddr = *final_dst; skb->priority = sk->sk_priority; skb->mark = sk->sk_mark; diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index bdc15c9..f5f98f5 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -93,7 +93,7 @@ struct pcpu_tstats { unsigned long rx_bytes; unsigned long tx_packets; unsigned long tx_bytes; -}; +} __attribute__((aligned(4*sizeof(unsigned long)))); static struct net_device_stats *ip6_get_stats(struct net_device *dev) { @@ -289,6 +289,8 @@ static struct ip6_tnl *ip6_tnl_create(struct net *net, struct ip6_tnl_parm *p) if ((err = register_netdevice(dev)) < 0) goto failed_free; + strcpy(t->parms.name, dev->name); + dev_hold(dev); ip6_tnl_link(ip6n, t); return t; @@ -977,8 +979,8 @@ static int ip6_tnl_xmit2(struct sk_buff *skb, ipv6_change_dsfield(ipv6h, ~INET_ECN_MASK, dsfield); ipv6h->hop_limit = t->parms.hop_limit; ipv6h->nexthdr = proto; - ipv6_addr_copy(&ipv6h->saddr, &fl6->saddr); - ipv6_addr_copy(&ipv6h->daddr, &fl6->daddr); + ipv6h->saddr = fl6->saddr; + ipv6h->daddr = fl6->daddr; nf_reset(skb); pkt_len = skb->len; err = ip6_local_out(skb); @@ -1153,8 +1155,8 @@ static void ip6_tnl_link_config(struct ip6_tnl *t) memcpy(dev->broadcast, &p->raddr, sizeof(struct in6_addr)); /* Set up flowi template */ - ipv6_addr_copy(&fl6->saddr, &p->laddr); - ipv6_addr_copy(&fl6->daddr, &p->raddr); + fl6->saddr = p->laddr; + fl6->daddr = p->raddr; fl6->flowi6_oif = p->link; fl6->flowlabel = 0; @@ -1210,8 +1212,8 @@ static void ip6_tnl_link_config(struct ip6_tnl *t) static int ip6_tnl_change(struct ip6_tnl *t, struct ip6_tnl_parm *p) { - ipv6_addr_copy(&t->parms.laddr, &p->laddr); - ipv6_addr_copy(&t->parms.raddr, &p->raddr); + t->parms.laddr = p->laddr; + t->parms.raddr = p->raddr; t->parms.flags = p->flags; t->parms.hop_limit = p->hop_limit; t->parms.encap_limit = p->encap_limit; @@ -1407,7 +1409,6 @@ ip6_tnl_dev_init_gen(struct net_device *dev) struct ip6_tnl *t = netdev_priv(dev); t->dev = dev; - strcpy(t->parms.name, dev->name); dev->tstats = alloc_percpu(struct pcpu_tstats); if (!dev->tstats) return -ENOMEM; @@ -1487,6 +1488,7 @@ static void __net_exit ip6_tnl_destroy_tunnels(struct ip6_tnl_net *ip6n) static int __net_init ip6_tnl_init_net(struct net *net) { struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id); + struct ip6_tnl *t = NULL; int err; ip6n->tnls[0] = ip6n->tnls_wc; @@ -1507,6 +1509,10 @@ static int __net_init ip6_tnl_init_net(struct net *net) err = register_netdev(ip6n->fb_tnl_dev); if (err < 0) goto err_register; + + t = netdev_priv(ip6n->fb_tnl_dev); + + strcpy(t->parms.name, ip6n->fb_tnl_dev->name); return 0; err_register: diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index 449a918..c7e95c8 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -1105,8 +1105,8 @@ static int ip6mr_cache_report(struct mr6_table *mrt, struct sk_buff *pkt, msg->im6_msgtype = MRT6MSG_WHOLEPKT; msg->im6_mif = mrt->mroute_reg_vif_num; msg->im6_pad = 0; - ipv6_addr_copy(&msg->im6_src, &ipv6_hdr(pkt)->saddr); - ipv6_addr_copy(&msg->im6_dst, &ipv6_hdr(pkt)->daddr); + msg->im6_src = ipv6_hdr(pkt)->saddr; + msg->im6_dst = ipv6_hdr(pkt)->daddr; skb->ip_summed = CHECKSUM_UNNECESSARY; } else @@ -1131,8 +1131,8 @@ static int ip6mr_cache_report(struct mr6_table *mrt, struct sk_buff *pkt, msg->im6_msgtype = assert; msg->im6_mif = mifi; msg->im6_pad = 0; - ipv6_addr_copy(&msg->im6_src, &ipv6_hdr(pkt)->saddr); - ipv6_addr_copy(&msg->im6_dst, &ipv6_hdr(pkt)->daddr); + msg->im6_src = ipv6_hdr(pkt)->saddr; + msg->im6_dst = ipv6_hdr(pkt)->daddr; skb_dst_set(skb, dst_clone(skb_dst(pkt))); skb->ip_summed = CHECKSUM_UNNECESSARY; @@ -2181,8 +2181,8 @@ int ip6mr_get_route(struct net *net, iph->payload_len = 0; iph->nexthdr = IPPROTO_NONE; iph->hop_limit = 0; - ipv6_addr_copy(&iph->saddr, &rt->rt6i_src.addr); - ipv6_addr_copy(&iph->daddr, &rt->rt6i_dst.addr); + iph->saddr = rt->rt6i_src.addr; + iph->daddr = rt->rt6i_dst.addr; err = ip6mr_cache_unresolved(mrt, vif, skb2); read_unlock(&mrt_lock); diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c index c99e3ee..29993b7 100644 --- a/net/ipv6/ipv6_sockglue.c +++ b/net/ipv6/ipv6_sockglue.c @@ -435,7 +435,7 @@ sticky_done: goto e_inval; np->sticky_pktinfo.ipi6_ifindex = pkt.ipi6_ifindex; - ipv6_addr_copy(&np->sticky_pktinfo.ipi6_addr, &pkt.ipi6_addr); + np->sticky_pktinfo.ipi6_addr = pkt.ipi6_addr; retv = 0; break; } @@ -980,8 +980,7 @@ static int do_ipv6_getsockopt(struct sock *sk, int level, int optname, struct in6_pktinfo src_info; src_info.ipi6_ifindex = np->mcast_oif ? np->mcast_oif : np->sticky_pktinfo.ipi6_ifindex; - np->mcast_oif? ipv6_addr_copy(&src_info.ipi6_addr, &np->daddr) : - ipv6_addr_copy(&src_info.ipi6_addr, &(np->sticky_pktinfo.ipi6_addr)); + src_info.ipi6_addr = np->mcast_oif ? np->daddr : np->sticky_pktinfo.ipi6_addr; put_cmsg(&msg, SOL_IPV6, IPV6_PKTINFO, sizeof(src_info), &src_info); } if (np->rxopt.bits.rxhlim) { @@ -992,8 +991,7 @@ static int do_ipv6_getsockopt(struct sock *sk, int level, int optname, struct in6_pktinfo src_info; src_info.ipi6_ifindex = np->mcast_oif ? np->mcast_oif : np->sticky_pktinfo.ipi6_ifindex; - np->mcast_oif? ipv6_addr_copy(&src_info.ipi6_addr, &np->daddr) : - ipv6_addr_copy(&src_info.ipi6_addr, &(np->sticky_pktinfo.ipi6_addr)); + src_info.ipi6_addr = np->mcast_oif ? np->daddr : np->sticky_pktinfo.ipi6_addr; put_cmsg(&msg, SOL_IPV6, IPV6_2292PKTINFO, sizeof(src_info), &src_info); } if (np->rxopt.bits.rxohlim) { diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index ee7839f..6cc4d1f 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -155,7 +155,7 @@ int ipv6_sock_mc_join(struct sock *sk, int ifindex, const struct in6_addr *addr) return -ENOMEM; mc_lst->next = NULL; - ipv6_addr_copy(&mc_lst->addr, addr); + mc_lst->addr = *addr; rcu_read_lock(); if (ifindex == 0) { @@ -858,7 +858,7 @@ int ipv6_dev_mc_inc(struct net_device *dev, const struct in6_addr *addr) setup_timer(&mc->mca_timer, igmp6_timer_handler, (unsigned long)mc); - ipv6_addr_copy(&mc->mca_addr, addr); + mc->mca_addr = *addr; mc->idev = idev; /* (reference taken) */ mc->mca_users = 1; /* mca_stamp should be updated upon changes */ @@ -1343,13 +1343,15 @@ static struct sk_buff *mld_newpack(struct net_device *dev, int size) struct mld2_report *pmr; struct in6_addr addr_buf; const struct in6_addr *saddr; + int hlen = LL_RESERVED_SPACE(dev); + int tlen = dev->needed_tailroom; int err; u8 ra[8] = { IPPROTO_ICMPV6, 0, IPV6_TLV_ROUTERALERT, 2, 0, 0, IPV6_TLV_PADN, 0 }; /* we assume size > sizeof(ra) here */ - size += LL_ALLOCATED_SPACE(dev); + size += hlen + tlen; /* limit our allocations to order-0 page */ size = min_t(int, size, SKB_MAX_ORDER(0, 0)); skb = sock_alloc_send_skb(sk, size, 1, &err); @@ -1357,7 +1359,7 @@ static struct sk_buff *mld_newpack(struct net_device *dev, int size) if (!skb) return NULL; - skb_reserve(skb, LL_RESERVED_SPACE(dev)); + skb_reserve(skb, hlen); if (ipv6_get_lladdr(dev, &addr_buf, IFA_F_TENTATIVE)) { /* <draft-ietf-magma-mld-source-05.txt>: @@ -1723,6 +1725,8 @@ static void igmp6_send(struct in6_addr *addr, struct net_device *dev, int type) struct mld_msg *hdr; const struct in6_addr *snd_addr, *saddr; struct in6_addr addr_buf; + int hlen = LL_RESERVED_SPACE(dev); + int tlen = dev->needed_tailroom; int err, len, payload_len, full_len; u8 ra[8] = { IPPROTO_ICMPV6, 0, IPV6_TLV_ROUTERALERT, 2, 0, 0, @@ -1744,7 +1748,7 @@ static void igmp6_send(struct in6_addr *addr, struct net_device *dev, int type) IPSTATS_MIB_OUT, full_len); rcu_read_unlock(); - skb = sock_alloc_send_skb(sk, LL_ALLOCATED_SPACE(dev) + full_len, 1, &err); + skb = sock_alloc_send_skb(sk, hlen + tlen + full_len, 1, &err); if (skb == NULL) { rcu_read_lock(); @@ -1754,7 +1758,7 @@ static void igmp6_send(struct in6_addr *addr, struct net_device *dev, int type) return; } - skb_reserve(skb, LL_RESERVED_SPACE(dev)); + skb_reserve(skb, hlen); if (ipv6_get_lladdr(dev, &addr_buf, IFA_F_TENTATIVE)) { /* <draft-ietf-magma-mld-source-05.txt>: @@ -1772,7 +1776,7 @@ static void igmp6_send(struct in6_addr *addr, struct net_device *dev, int type) hdr = (struct mld_msg *) skb_put(skb, sizeof(struct mld_msg)); memset(hdr, 0, sizeof(struct mld_msg)); hdr->mld_type = type; - ipv6_addr_copy(&hdr->mld_mca, addr); + hdr->mld_mca = *addr; hdr->mld_cksum = csum_ipv6_magic(saddr, snd_addr, len, IPPROTO_ICMPV6, diff --git a/net/ipv6/mip6.c b/net/ipv6/mip6.c index 43242e6..7e1e0fb 100644 --- a/net/ipv6/mip6.c +++ b/net/ipv6/mip6.c @@ -195,8 +195,8 @@ static inline int mip6_report_rl_allow(struct timeval *stamp, mip6_report_rl.stamp.tv_sec = stamp->tv_sec; mip6_report_rl.stamp.tv_usec = stamp->tv_usec; mip6_report_rl.iif = iif; - ipv6_addr_copy(&mip6_report_rl.src, src); - ipv6_addr_copy(&mip6_report_rl.dst, dst); + mip6_report_rl.src = *src; + mip6_report_rl.dst = *dst; allow = 1; } spin_unlock_bh(&mip6_report_rl.lock); diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index 44e5b7f..2854705 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -141,7 +141,7 @@ struct neigh_table nd_tbl = { .gc_staletime = 60 * HZ, .reachable_time = ND_REACHABLE_TIME, .delay_probe_time = 5 * HZ, - .queue_len = 3, + .queue_len_bytes = 64*1024, .ucast_probes = 3, .mcast_probes = 3, .anycast_delay = 1 * HZ, @@ -446,6 +446,8 @@ struct sk_buff *ndisc_build_skb(struct net_device *dev, struct sock *sk = net->ipv6.ndisc_sk; struct sk_buff *skb; struct icmp6hdr *hdr; + int hlen = LL_RESERVED_SPACE(dev); + int tlen = dev->needed_tailroom; int len; int err; u8 *opt; @@ -459,7 +461,7 @@ struct sk_buff *ndisc_build_skb(struct net_device *dev, skb = sock_alloc_send_skb(sk, (MAX_HEADER + sizeof(struct ipv6hdr) + - len + LL_ALLOCATED_SPACE(dev)), + len + hlen + tlen), 1, &err); if (!skb) { ND_PRINTK0(KERN_ERR @@ -468,7 +470,7 @@ struct sk_buff *ndisc_build_skb(struct net_device *dev, return NULL; } - skb_reserve(skb, LL_RESERVED_SPACE(dev)); + skb_reserve(skb, hlen); ip6_nd_hdr(sk, skb, dev, saddr, daddr, IPPROTO_ICMPV6, len); skb->transport_header = skb->tail; @@ -479,7 +481,7 @@ struct sk_buff *ndisc_build_skb(struct net_device *dev, opt = skb_transport_header(skb) + sizeof(struct icmp6hdr); if (target) { - ipv6_addr_copy((struct in6_addr *)opt, target); + *(struct in6_addr *)opt = *target; opt += sizeof(*target); } @@ -1533,6 +1535,7 @@ void ndisc_send_redirect(struct sk_buff *skb, struct neighbour *neigh, struct inet6_dev *idev; struct flowi6 fl6; u8 *opt; + int hlen, tlen; int rd_len; int err; u8 ha_buf[MAX_ADDR_LEN], *ha = NULL; @@ -1571,7 +1574,7 @@ void ndisc_send_redirect(struct sk_buff *skb, struct neighbour *neigh, } if (!rt->rt6i_peer) rt6_bind_peer(rt, 1); - if (inet_peer_xrlim_allow(rt->rt6i_peer, 1*HZ)) + if (!inet_peer_xrlim_allow(rt->rt6i_peer, 1*HZ)) goto release; if (dev->addr_len) { @@ -1590,9 +1593,11 @@ void ndisc_send_redirect(struct sk_buff *skb, struct neighbour *neigh, rd_len &= ~0x7; len += rd_len; + hlen = LL_RESERVED_SPACE(dev); + tlen = dev->needed_tailroom; buff = sock_alloc_send_skb(sk, (MAX_HEADER + sizeof(struct ipv6hdr) + - len + LL_ALLOCATED_SPACE(dev)), + len + hlen + tlen), 1, &err); if (buff == NULL) { ND_PRINTK0(KERN_ERR @@ -1601,7 +1606,7 @@ void ndisc_send_redirect(struct sk_buff *skb, struct neighbour *neigh, goto release; } - skb_reserve(buff, LL_RESERVED_SPACE(dev)); + skb_reserve(buff, hlen); ip6_nd_hdr(sk, buff, dev, &saddr_buf, &ipv6_hdr(skb)->saddr, IPPROTO_ICMPV6, len); @@ -1617,9 +1622,9 @@ void ndisc_send_redirect(struct sk_buff *skb, struct neighbour *neigh, */ addrp = (struct in6_addr *)(icmph + 1); - ipv6_addr_copy(addrp, target); + *addrp = *target; addrp++; - ipv6_addr_copy(addrp, &ipv6_hdr(skb)->daddr); + *addrp = ipv6_hdr(skb)->daddr; opt = (u8*) (addrp + 1); diff --git a/net/ipv6/netfilter/Kconfig b/net/ipv6/netfilter/Kconfig index 4484648..f792b34 100644 --- a/net/ipv6/netfilter/Kconfig +++ b/net/ipv6/netfilter/Kconfig @@ -186,7 +186,6 @@ config IP6_NF_MANGLE config IP6_NF_RAW tristate 'raw table support (required for TRACE)' - depends on NETFILTER_ADVANCED help This option adds a `raw' table to ip6tables. This table is the very first in the netfilter framework and hooks in at the PREROUTING diff --git a/net/ipv6/netfilter/ip6t_REJECT.c b/net/ipv6/netfilter/ip6t_REJECT.c index a5a4c5d..b5a2aa5 100644 --- a/net/ipv6/netfilter/ip6t_REJECT.c +++ b/net/ipv6/netfilter/ip6t_REJECT.c @@ -93,8 +93,8 @@ static void send_reset(struct net *net, struct sk_buff *oldskb) memset(&fl6, 0, sizeof(fl6)); fl6.flowi6_proto = IPPROTO_TCP; - ipv6_addr_copy(&fl6.saddr, &oip6h->daddr); - ipv6_addr_copy(&fl6.daddr, &oip6h->saddr); + fl6.saddr = oip6h->daddr; + fl6.daddr = oip6h->saddr; fl6.fl6_sport = otcph.dest; fl6.fl6_dport = otcph.source; security_skb_classify_flow(oldskb, flowi6_to_flowi(&fl6)); @@ -129,8 +129,8 @@ static void send_reset(struct net *net, struct sk_buff *oldskb) *(__be32 *)ip6h = htonl(0x60000000 | (tclass << 20)); ip6h->hop_limit = ip6_dst_hoplimit(dst); ip6h->nexthdr = IPPROTO_TCP; - ipv6_addr_copy(&ip6h->saddr, &oip6h->daddr); - ipv6_addr_copy(&ip6h->daddr, &oip6h->saddr); + ip6h->saddr = oip6h->daddr; + ip6h->daddr = oip6h->saddr; tcph = (struct tcphdr *)skb_put(nskb, sizeof(struct tcphdr)); /* Truncate to length (no data) */ diff --git a/net/ipv6/proc.c b/net/ipv6/proc.c index 1008ce9..fdeb6d0 100644 --- a/net/ipv6/proc.c +++ b/net/ipv6/proc.c @@ -142,11 +142,7 @@ static const struct snmp_mib snmp6_udplite6_list[] = { SNMP_MIB_SENTINEL }; -/* can be called either with percpu mib (pcpumib != NULL), - * or shared one (smib != NULL) - */ -static void snmp6_seq_show_icmpv6msg(struct seq_file *seq, void __percpu **pcpumib, - atomic_long_t *smib) +static void snmp6_seq_show_icmpv6msg(struct seq_file *seq, atomic_long_t *smib) { char name[32]; int i; @@ -163,14 +159,14 @@ static void snmp6_seq_show_icmpv6msg(struct seq_file *seq, void __percpu **pcpum snprintf(name, sizeof(name), "Icmp6%s%s", i & 0x100 ? "Out" : "In", p); seq_printf(seq, "%-32s\t%lu\n", name, - pcpumib ? snmp_fold_field(pcpumib, i) : atomic_long_read(smib + i)); + atomic_long_read(smib + i)); } /* print by number (nonzero only) - ICMPMsgStat format */ for (i = 0; i < ICMP6MSG_MIB_MAX; i++) { unsigned long val; - val = pcpumib ? snmp_fold_field(pcpumib, i) : atomic_long_read(smib + i); + val = atomic_long_read(smib + i); if (!val) continue; snprintf(name, sizeof(name), "Icmp6%sType%u", @@ -215,8 +211,7 @@ static int snmp6_seq_show(struct seq_file *seq, void *v) snmp6_ipstats_list, offsetof(struct ipstats_mib, syncp)); snmp6_seq_show_item(seq, (void __percpu **)net->mib.icmpv6_statistics, NULL, snmp6_icmp6_list); - snmp6_seq_show_icmpv6msg(seq, - (void __percpu **)net->mib.icmpv6msg_statistics, NULL); + snmp6_seq_show_icmpv6msg(seq, net->mib.icmpv6msg_statistics->mibs); snmp6_seq_show_item(seq, (void __percpu **)net->mib.udp_stats_in6, NULL, snmp6_udp6_list); snmp6_seq_show_item(seq, (void __percpu **)net->mib.udplite_stats_in6, @@ -246,7 +241,7 @@ static int snmp6_dev_seq_show(struct seq_file *seq, void *v) snmp6_ipstats_list); snmp6_seq_show_item(seq, NULL, idev->stats.icmpv6dev->mibs, snmp6_icmp6_list); - snmp6_seq_show_icmpv6msg(seq, NULL, idev->stats.icmpv6msgdev->mibs); + snmp6_seq_show_icmpv6msg(seq, idev->stats.icmpv6msgdev->mibs); return 0; } diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index 331af3b8..a4894f4 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -299,9 +299,9 @@ static int rawv6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len) } inet->inet_rcv_saddr = inet->inet_saddr = v4addr; - ipv6_addr_copy(&np->rcv_saddr, &addr->sin6_addr); + np->rcv_saddr = addr->sin6_addr; if (!(addr_type & IPV6_ADDR_MULTICAST)) - ipv6_addr_copy(&np->saddr, &addr->sin6_addr); + np->saddr = addr->sin6_addr; err = 0; out_unlock: rcu_read_unlock(); @@ -383,7 +383,8 @@ static inline int rawv6_rcv_skb(struct sock *sk, struct sk_buff *skb) } /* Charge it to the socket. */ - if (ip_queue_rcv_skb(sk, skb) < 0) { + skb_dst_drop(skb); + if (sock_queue_rcv_skb(sk, skb) < 0) { kfree_skb(skb); return NET_RX_DROP; } @@ -494,7 +495,7 @@ static int rawv6_recvmsg(struct kiocb *iocb, struct sock *sk, if (sin6) { sin6->sin6_family = AF_INET6; sin6->sin6_port = 0; - ipv6_addr_copy(&sin6->sin6_addr, &ipv6_hdr(skb)->saddr); + sin6->sin6_addr = ipv6_hdr(skb)->saddr; sin6->sin6_flowinfo = 0; sin6->sin6_scope_id = 0; if (ipv6_addr_type(&sin6->sin6_addr) & IPV6_ADDR_LINKLOCAL) @@ -610,6 +611,8 @@ static int rawv6_send_hdrinc(struct sock *sk, void *from, int length, struct sk_buff *skb; int err; struct rt6_info *rt = (struct rt6_info *)*dstp; + int hlen = LL_RESERVED_SPACE(rt->dst.dev); + int tlen = rt->dst.dev->needed_tailroom; if (length > rt->dst.dev->mtu) { ipv6_local_error(sk, EMSGSIZE, fl6, rt->dst.dev->mtu); @@ -619,11 +622,11 @@ static int rawv6_send_hdrinc(struct sock *sk, void *from, int length, goto out; skb = sock_alloc_send_skb(sk, - length + LL_ALLOCATED_SPACE(rt->dst.dev) + 15, + length + hlen + tlen + 15, flags & MSG_DONTWAIT, &err); if (skb == NULL) goto error; - skb_reserve(skb, LL_RESERVED_SPACE(rt->dst.dev)); + skb_reserve(skb, hlen); skb->priority = sk->sk_priority; skb->mark = sk->sk_mark; @@ -843,11 +846,11 @@ static int rawv6_sendmsg(struct kiocb *iocb, struct sock *sk, goto out; if (!ipv6_addr_any(daddr)) - ipv6_addr_copy(&fl6.daddr, daddr); + fl6.daddr = *daddr; else fl6.daddr.s6_addr[15] = 0x1; /* :: means loopback (BSD'ism) */ if (ipv6_addr_any(&fl6.saddr) && !ipv6_addr_any(&np->saddr)) - ipv6_addr_copy(&fl6.saddr, &np->saddr); + fl6.saddr = np->saddr; final_p = fl6_update_dst(&fl6, opt, &final); diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c index dfb164e..b69fae7 100644 --- a/net/ipv6/reassembly.c +++ b/net/ipv6/reassembly.c @@ -153,8 +153,8 @@ void ip6_frag_init(struct inet_frag_queue *q, void *a) fq->id = arg->id; fq->user = arg->user; - ipv6_addr_copy(&fq->saddr, arg->src); - ipv6_addr_copy(&fq->daddr, arg->dst); + fq->saddr = *arg->src; + fq->daddr = *arg->dst; } EXPORT_SYMBOL(ip6_frag_init); diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 8473016..0e381bb 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -77,7 +77,7 @@ static struct rt6_info *ip6_rt_copy(const struct rt6_info *ort, const struct in6_addr *dest); static struct dst_entry *ip6_dst_check(struct dst_entry *dst, u32 cookie); static unsigned int ip6_default_advmss(const struct dst_entry *dst); -static unsigned int ip6_default_mtu(const struct dst_entry *dst); +static unsigned int ip6_mtu(const struct dst_entry *dst); static struct dst_entry *ip6_negative_advice(struct dst_entry *); static void ip6_dst_destroy(struct dst_entry *); static void ip6_dst_ifdown(struct dst_entry *, @@ -144,7 +144,7 @@ static struct dst_ops ip6_dst_ops_template = { .gc_thresh = 1024, .check = ip6_dst_check, .default_advmss = ip6_default_advmss, - .default_mtu = ip6_default_mtu, + .mtu = ip6_mtu, .cow_metrics = ipv6_cow_metrics, .destroy = ip6_dst_destroy, .ifdown = ip6_dst_ifdown, @@ -155,9 +155,11 @@ static struct dst_ops ip6_dst_ops_template = { .neigh_lookup = ip6_neigh_lookup, }; -static unsigned int ip6_blackhole_default_mtu(const struct dst_entry *dst) +static unsigned int ip6_blackhole_mtu(const struct dst_entry *dst) { - return 0; + unsigned int mtu = dst_metric_raw(dst, RTAX_MTU); + + return mtu ? : dst->dev->mtu; } static void ip6_rt_blackhole_update_pmtu(struct dst_entry *dst, u32 mtu) @@ -175,7 +177,7 @@ static struct dst_ops ip6_dst_blackhole_ops = { .protocol = cpu_to_be16(ETH_P_IPV6), .destroy = ip6_dst_destroy, .check = ip6_dst_check, - .default_mtu = ip6_blackhole_default_mtu, + .mtu = ip6_blackhole_mtu, .default_advmss = ip6_default_advmss, .update_pmtu = ip6_rt_blackhole_update_pmtu, .cow_metrics = ip6_rt_blackhole_cow_metrics, @@ -729,14 +731,14 @@ static struct rt6_info *rt6_alloc_cow(const struct rt6_info *ort, if (rt->rt6i_dst.plen != 128 && ipv6_addr_equal(&ort->rt6i_dst.addr, daddr)) rt->rt6i_flags |= RTF_ANYCAST; - ipv6_addr_copy(&rt->rt6i_gateway, daddr); + rt->rt6i_gateway = *daddr; } rt->rt6i_flags |= RTF_CACHE; #ifdef CONFIG_IPV6_SUBTREES if (rt->rt6i_src.plen && saddr) { - ipv6_addr_copy(&rt->rt6i_src.addr, saddr); + rt->rt6i_src.addr = *saddr; rt->rt6i_src.plen = 128; } #endif @@ -932,7 +934,7 @@ struct dst_entry *ip6_blackhole_route(struct net *net, struct dst_entry *dst_ori in6_dev_hold(rt->rt6i_idev); rt->rt6i_expires = 0; - ipv6_addr_copy(&rt->rt6i_gateway, &ort->rt6i_gateway); + rt->rt6i_gateway = ort->rt6i_gateway; rt->rt6i_flags = ort->rt6i_flags & ~RTF_EXPIRES; rt->rt6i_metric = 0; @@ -1041,10 +1043,15 @@ static unsigned int ip6_default_advmss(const struct dst_entry *dst) return mtu; } -static unsigned int ip6_default_mtu(const struct dst_entry *dst) +static unsigned int ip6_mtu(const struct dst_entry *dst) { - unsigned int mtu = IPV6_MIN_MTU; struct inet6_dev *idev; + unsigned int mtu = dst_metric_raw(dst, RTAX_MTU); + + if (mtu) + return mtu; + + mtu = IPV6_MIN_MTU; rcu_read_lock(); idev = __in6_dev_get(dst->dev); @@ -1087,7 +1094,7 @@ struct dst_entry *icmp6_dst_alloc(struct net_device *dev, rt->dst.output = ip6_output; dst_set_neighbour(&rt->dst, neigh); atomic_set(&rt->dst.__refcnt, 1); - ipv6_addr_copy(&rt->rt6i_dst.addr, addr); + rt->rt6i_dst.addr = *addr; rt->rt6i_dst.plen = 128; rt->rt6i_idev = idev; dst_metric_set(&rt->dst, RTAX_HOPLIMIT, 255); @@ -1230,9 +1237,18 @@ int ip6_route_add(struct fib6_config *cfg) if (cfg->fc_metric == 0) cfg->fc_metric = IP6_RT_PRIO_USER; - table = fib6_new_table(net, cfg->fc_table); + err = -ENOBUFS; + if (NULL != cfg->fc_nlinfo.nlh && + !(cfg->fc_nlinfo.nlh->nlmsg_flags&NLM_F_CREATE)) { + table = fib6_get_table(net, cfg->fc_table); + if (table == NULL) { + printk(KERN_WARNING "IPv6: NLM_F_CREATE should be specified when creating new route\n"); + table = fib6_new_table(net, cfg->fc_table); + } + } else { + table = fib6_new_table(net, cfg->fc_table); + } if (table == NULL) { - err = -ENOBUFS; goto out; } @@ -1315,7 +1331,7 @@ int ip6_route_add(struct fib6_config *cfg) int gwa_type; gw_addr = &cfg->fc_gateway; - ipv6_addr_copy(&rt->rt6i_gateway, gw_addr); + rt->rt6i_gateway = *gw_addr; gwa_type = ipv6_addr_type(gw_addr); if (gwa_type != (IPV6_ADDR_LINKLOCAL|IPV6_ADDR_UNICAST)) { @@ -1369,7 +1385,7 @@ int ip6_route_add(struct fib6_config *cfg) err = -EINVAL; goto out; } - ipv6_addr_copy(&rt->rt6i_prefsrc.addr, &cfg->fc_prefsrc); + rt->rt6i_prefsrc.addr = cfg->fc_prefsrc; rt->rt6i_prefsrc.plen = 128; } else rt->rt6i_prefsrc.plen = 0; @@ -1566,7 +1582,7 @@ static struct rt6_info *ip6_route_redirect(const struct in6_addr *dest, }, }; - ipv6_addr_copy(&rdfl.gateway, gateway); + rdfl.gateway = *gateway; if (rt6_need_strict(dest)) flags |= RT6_LOOKUP_F_IFACE; @@ -1622,7 +1638,7 @@ void rt6_redirect(const struct in6_addr *dest, const struct in6_addr *src, if (on_link) nrt->rt6i_flags &= ~RTF_GATEWAY; - ipv6_addr_copy(&nrt->rt6i_gateway, (struct in6_addr*)neigh->primary_key); + nrt->rt6i_gateway = *(struct in6_addr *)neigh->primary_key; dst_set_neighbour(&nrt->dst, neigh_clone(neigh)); if (ip6_ins_rt(nrt)) @@ -1768,7 +1784,7 @@ static struct rt6_info *ip6_rt_copy(const struct rt6_info *ort, rt->dst.output = ort->dst.output; rt->dst.flags |= DST_HOST; - ipv6_addr_copy(&rt->rt6i_dst.addr, dest); + rt->rt6i_dst.addr = *dest; rt->rt6i_dst.plen = 128; dst_copy_metrics(&rt->dst, &ort->dst); rt->dst.error = ort->dst.error; @@ -1778,7 +1794,7 @@ static struct rt6_info *ip6_rt_copy(const struct rt6_info *ort, rt->dst.lastuse = jiffies; rt->rt6i_expires = 0; - ipv6_addr_copy(&rt->rt6i_gateway, &ort->rt6i_gateway); + rt->rt6i_gateway = ort->rt6i_gateway; rt->rt6i_flags = ort->rt6i_flags & ~RTF_EXPIRES; rt->rt6i_metric = 0; @@ -1841,8 +1857,8 @@ static struct rt6_info *rt6_add_route_info(struct net *net, .fc_nlinfo.nl_net = net, }; - ipv6_addr_copy(&cfg.fc_dst, prefix); - ipv6_addr_copy(&cfg.fc_gateway, gwaddr); + cfg.fc_dst = *prefix; + cfg.fc_gateway = *gwaddr; /* We should treat it as a default route if prefix length is 0. */ if (!prefixlen) @@ -1891,7 +1907,7 @@ struct rt6_info *rt6_add_dflt_router(const struct in6_addr *gwaddr, .fc_nlinfo.nl_net = dev_net(dev), }; - ipv6_addr_copy(&cfg.fc_gateway, gwaddr); + cfg.fc_gateway = *gwaddr; ip6_route_add(&cfg); @@ -1937,9 +1953,9 @@ static void rtmsg_to_fib6_config(struct net *net, cfg->fc_nlinfo.nl_net = net; - ipv6_addr_copy(&cfg->fc_dst, &rtmsg->rtmsg_dst); - ipv6_addr_copy(&cfg->fc_src, &rtmsg->rtmsg_src); - ipv6_addr_copy(&cfg->fc_gateway, &rtmsg->rtmsg_gateway); + cfg->fc_dst = rtmsg->rtmsg_dst; + cfg->fc_src = rtmsg->rtmsg_src; + cfg->fc_gateway = rtmsg->rtmsg_gateway; } int ipv6_route_ioctl(struct net *net, unsigned int cmd, void __user *arg) @@ -2073,7 +2089,7 @@ struct rt6_info *addrconf_dst_alloc(struct inet6_dev *idev, } dst_set_neighbour(&rt->dst, neigh); - ipv6_addr_copy(&rt->rt6i_dst.addr, addr); + rt->rt6i_dst.addr = *addr; rt->rt6i_dst.plen = 128; rt->rt6i_table = fib6_get_table(net, RT6_TABLE_LOCAL); @@ -2091,7 +2107,7 @@ int ip6_route_get_saddr(struct net *net, struct inet6_dev *idev = ip6_dst_idev((struct dst_entry*)rt); int err = 0; if (rt->rt6i_prefsrc.plen) - ipv6_addr_copy(saddr, &rt->rt6i_prefsrc.addr); + *saddr = rt->rt6i_prefsrc.addr; else err = ipv6_dev_get_saddr(net, idev ? idev->dev : NULL, daddr, prefs, saddr); @@ -2430,7 +2446,7 @@ static int rt6_fill_node(struct net *net, if (rt->rt6i_prefsrc.plen) { struct in6_addr saddr_buf; - ipv6_addr_copy(&saddr_buf, &rt->rt6i_prefsrc.addr); + saddr_buf = rt->rt6i_prefsrc.addr; NLA_PUT(skb, RTA_PREFSRC, 16, &saddr_buf); } @@ -2504,14 +2520,14 @@ static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr* nlh, void if (nla_len(tb[RTA_SRC]) < sizeof(struct in6_addr)) goto errout; - ipv6_addr_copy(&fl6.saddr, nla_data(tb[RTA_SRC])); + fl6.saddr = *(struct in6_addr *)nla_data(tb[RTA_SRC]); } if (tb[RTA_DST]) { if (nla_len(tb[RTA_DST]) < sizeof(struct in6_addr)) goto errout; - ipv6_addr_copy(&fl6.daddr, nla_data(tb[RTA_DST])); + fl6.daddr = *(struct in6_addr *)nla_data(tb[RTA_DST]); } if (tb[RTA_IIF]) diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index a7a1860..50968f2 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -91,7 +91,7 @@ struct pcpu_tstats { unsigned long rx_bytes; unsigned long tx_packets; unsigned long tx_bytes; -}; +} __attribute__((aligned(4*sizeof(unsigned long)))); static struct net_device_stats *ipip6_get_stats(struct net_device *dev) { @@ -914,7 +914,7 @@ ipip6_tunnel_ioctl (struct net_device *dev, struct ifreq *ifr, int cmd) goto done; #ifdef CONFIG_IPV6_SIT_6RD } else { - ipv6_addr_copy(&ip6rd.prefix, &t->ip6rd.prefix); + ip6rd.prefix = t->ip6rd.prefix; ip6rd.relay_prefix = t->ip6rd.relay_prefix; ip6rd.prefixlen = t->ip6rd.prefixlen; ip6rd.relay_prefixlen = t->ip6rd.relay_prefixlen; @@ -1082,7 +1082,7 @@ ipip6_tunnel_ioctl (struct net_device *dev, struct ifreq *ifr, int cmd) if (relay_prefix != ip6rd.relay_prefix) goto done; - ipv6_addr_copy(&t->ip6rd.prefix, &prefix); + t->ip6rd.prefix = prefix; t->ip6rd.relay_prefix = relay_prefix; t->ip6rd.prefixlen = ip6rd.prefixlen; t->ip6rd.relay_prefixlen = ip6rd.relay_prefixlen; diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c index 5a0d664..8e951d8 100644 --- a/net/ipv6/syncookies.c +++ b/net/ipv6/syncookies.c @@ -200,8 +200,8 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb) req->mss = mss; ireq->rmt_port = th->source; ireq->loc_port = th->dest; - ipv6_addr_copy(&ireq6->rmt_addr, &ipv6_hdr(skb)->saddr); - ipv6_addr_copy(&ireq6->loc_addr, &ipv6_hdr(skb)->daddr); + ireq6->rmt_addr = ipv6_hdr(skb)->saddr; + ireq6->loc_addr = ipv6_hdr(skb)->daddr; if (ipv6_opt_accepted(sk, skb) || np->rxopt.bits.rxinfo || np->rxopt.bits.rxoinfo || np->rxopt.bits.rxhlim || np->rxopt.bits.rxohlim) { @@ -237,9 +237,9 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb) struct flowi6 fl6; memset(&fl6, 0, sizeof(fl6)); fl6.flowi6_proto = IPPROTO_TCP; - ipv6_addr_copy(&fl6.daddr, &ireq6->rmt_addr); + fl6.daddr = ireq6->rmt_addr; final_p = fl6_update_dst(&fl6, np->opt, &final); - ipv6_addr_copy(&fl6.saddr, &ireq6->loc_addr); + fl6.saddr = ireq6->loc_addr; fl6.flowi6_oif = sk->sk_bound_dev_if; fl6.flowi6_mark = sk->sk_mark; fl6.fl6_dport = inet_rsk(req)->rmt_port; diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 36131d1..9d74eee 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -153,7 +153,7 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, flowlabel = fl6_sock_lookup(sk, fl6.flowlabel); if (flowlabel == NULL) return -EINVAL; - ipv6_addr_copy(&usin->sin6_addr, &flowlabel->dst); + usin->sin6_addr = flowlabel->dst; fl6_sock_release(flowlabel); } } @@ -195,7 +195,7 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, tp->write_seq = 0; } - ipv6_addr_copy(&np->daddr, &usin->sin6_addr); + np->daddr = usin->sin6_addr; np->flow_label = fl6.flowlabel; /* @@ -244,9 +244,8 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, saddr = &np->rcv_saddr; fl6.flowi6_proto = IPPROTO_TCP; - ipv6_addr_copy(&fl6.daddr, &np->daddr); - ipv6_addr_copy(&fl6.saddr, - (saddr ? saddr : &np->saddr)); + fl6.daddr = np->daddr; + fl6.saddr = saddr ? *saddr : np->saddr; fl6.flowi6_oif = sk->sk_bound_dev_if; fl6.flowi6_mark = sk->sk_mark; fl6.fl6_dport = usin->sin6_port; @@ -264,11 +263,11 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, if (saddr == NULL) { saddr = &fl6.saddr; - ipv6_addr_copy(&np->rcv_saddr, saddr); + np->rcv_saddr = *saddr; } /* set the source address */ - ipv6_addr_copy(&np->saddr, saddr); + np->saddr = *saddr; inet->inet_rcv_saddr = LOOPBACK4_IPV6; sk->sk_gso_type = SKB_GSO_TCPV6; @@ -398,8 +397,8 @@ static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, */ memset(&fl6, 0, sizeof(fl6)); fl6.flowi6_proto = IPPROTO_TCP; - ipv6_addr_copy(&fl6.daddr, &np->daddr); - ipv6_addr_copy(&fl6.saddr, &np->saddr); + fl6.daddr = np->daddr; + fl6.saddr = np->saddr; fl6.flowi6_oif = sk->sk_bound_dev_if; fl6.flowi6_mark = sk->sk_mark; fl6.fl6_dport = inet->inet_dport; @@ -489,8 +488,8 @@ static int tcp_v6_send_synack(struct sock *sk, struct request_sock *req, memset(&fl6, 0, sizeof(fl6)); fl6.flowi6_proto = IPPROTO_TCP; - ipv6_addr_copy(&fl6.daddr, &treq->rmt_addr); - ipv6_addr_copy(&fl6.saddr, &treq->loc_addr); + fl6.daddr = treq->rmt_addr; + fl6.saddr = treq->loc_addr; fl6.flowlabel = 0; fl6.flowi6_oif = treq->iif; fl6.flowi6_mark = sk->sk_mark; @@ -512,7 +511,7 @@ static int tcp_v6_send_synack(struct sock *sk, struct request_sock *req, if (skb) { __tcp_v6_send_check(skb, &treq->loc_addr, &treq->rmt_addr); - ipv6_addr_copy(&fl6.daddr, &treq->rmt_addr); + fl6.daddr = treq->rmt_addr; err = ip6_xmit(sk, skb, &fl6, opt, np->tclass); err = net_xmit_eval(err); } @@ -617,8 +616,7 @@ static int tcp_v6_md5_do_add(struct sock *sk, const struct in6_addr *peer, tp->md5sig_info->alloced6++; } - ipv6_addr_copy(&tp->md5sig_info->keys6[tp->md5sig_info->entries6].addr, - peer); + tp->md5sig_info->keys6[tp->md5sig_info->entries6].addr = *peer; tp->md5sig_info->keys6[tp->md5sig_info->entries6].base.key = newkey; tp->md5sig_info->keys6[tp->md5sig_info->entries6].base.keylen = newkeylen; @@ -750,8 +748,8 @@ static int tcp_v6_md5_hash_pseudoheader(struct tcp_md5sig_pool *hp, bp = &hp->md5_blk.ip6; /* 1. TCP pseudo-header (RFC2460) */ - ipv6_addr_copy(&bp->saddr, saddr); - ipv6_addr_copy(&bp->daddr, daddr); + bp->saddr = *saddr; + bp->daddr = *daddr; bp->protocol = cpu_to_be32(IPPROTO_TCP); bp->len = cpu_to_be32(nbytes); @@ -1039,8 +1037,8 @@ static void tcp_v6_send_response(struct sk_buff *skb, u32 seq, u32 ack, u32 win, #endif memset(&fl6, 0, sizeof(fl6)); - ipv6_addr_copy(&fl6.daddr, &ipv6_hdr(skb)->saddr); - ipv6_addr_copy(&fl6.saddr, &ipv6_hdr(skb)->daddr); + fl6.daddr = ipv6_hdr(skb)->saddr; + fl6.saddr = ipv6_hdr(skb)->daddr; buff->ip_summed = CHECKSUM_PARTIAL; buff->csum = 0; @@ -1250,11 +1248,18 @@ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb) tcp_openreq_init(req, &tmp_opt, skb); treq = inet6_rsk(req); - ipv6_addr_copy(&treq->rmt_addr, &ipv6_hdr(skb)->saddr); - ipv6_addr_copy(&treq->loc_addr, &ipv6_hdr(skb)->daddr); + treq->rmt_addr = ipv6_hdr(skb)->saddr; + treq->loc_addr = ipv6_hdr(skb)->daddr; if (!want_cookie || tmp_opt.tstamp_ok) TCP_ECN_create_request(req, tcp_hdr(skb)); + treq->iif = sk->sk_bound_dev_if; + + /* So that link locals have meaning */ + if (!sk->sk_bound_dev_if && + ipv6_addr_type(&treq->rmt_addr) & IPV6_ADDR_LINKLOCAL) + treq->iif = inet6_iif(skb); + if (!isn) { struct inet_peer *peer = NULL; @@ -1264,12 +1269,6 @@ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb) atomic_inc(&skb->users); treq->pktopts = skb; } - treq->iif = sk->sk_bound_dev_if; - - /* So that link locals have meaning */ - if (!sk->sk_bound_dev_if && - ipv6_addr_type(&treq->rmt_addr) & IPV6_ADDR_LINKLOCAL) - treq->iif = inet6_iif(skb); if (want_cookie) { isn = cookie_v6_init_sequence(sk, skb, &req->mss); @@ -1380,7 +1379,7 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb, ipv6_addr_set_v4mapped(newinet->inet_saddr, &newnp->saddr); - ipv6_addr_copy(&newnp->rcv_saddr, &newnp->saddr); + newnp->rcv_saddr = newnp->saddr; inet_csk(newsk)->icsk_af_ops = &ipv6_mapped; newsk->sk_backlog_rcv = tcp_v4_do_rcv; @@ -1444,9 +1443,9 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb, memcpy(newnp, np, sizeof(struct ipv6_pinfo)); - ipv6_addr_copy(&newnp->daddr, &treq->rmt_addr); - ipv6_addr_copy(&newnp->saddr, &treq->loc_addr); - ipv6_addr_copy(&newnp->rcv_saddr, &treq->loc_addr); + newnp->daddr = treq->rmt_addr; + newnp->saddr = treq->loc_addr; + newnp->rcv_saddr = treq->loc_addr; newsk->sk_bound_dev_if = treq->iif; /* Now IPv6 options... diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 846f4757..84ec9db 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -417,8 +417,7 @@ try_again: ipv6_addr_set_v4mapped(ip_hdr(skb)->saddr, &sin6->sin6_addr); else { - ipv6_addr_copy(&sin6->sin6_addr, - &ipv6_hdr(skb)->saddr); + sin6->sin6_addr = ipv6_hdr(skb)->saddr; if (ipv6_addr_type(&sin6->sin6_addr) & IPV6_ADDR_LINKLOCAL) sin6->sin6_scope_id = IP6CB(skb)->iif; } @@ -538,7 +537,9 @@ int udpv6_queue_rcv_skb(struct sock * sk, struct sk_buff *skb) goto drop; } - if ((rc = ip_queue_rcv_skb(sk, skb)) < 0) { + skb_dst_drop(skb); + rc = sock_queue_rcv_skb(sk, skb); + if (rc < 0) { /* Note that an ENOMEM error is charged twice */ if (rc == -ENOMEM) UDP6_INC_STATS_BH(sock_net(sk), @@ -1113,11 +1114,11 @@ do_udp_sendmsg: fl6.flowi6_proto = sk->sk_protocol; if (!ipv6_addr_any(daddr)) - ipv6_addr_copy(&fl6.daddr, daddr); + fl6.daddr = *daddr; else fl6.daddr.s6_addr[15] = 0x1; /* :: means loopback (BSD'ism) */ if (ipv6_addr_any(&fl6.saddr) && !ipv6_addr_any(&np->saddr)) - ipv6_addr_copy(&fl6.saddr, &np->saddr); + fl6.saddr = np->saddr; fl6.fl6_sport = inet->inet_sport; final_p = fl6_update_dst(&fl6, opt, &final); @@ -1298,7 +1299,8 @@ static int udp6_ufo_send_check(struct sk_buff *skb) return 0; } -static struct sk_buff *udp6_ufo_fragment(struct sk_buff *skb, u32 features) +static struct sk_buff *udp6_ufo_fragment(struct sk_buff *skb, + netdev_features_t features) { struct sk_buff *segs = ERR_PTR(-EINVAL); unsigned int mss; diff --git a/net/ipv6/xfrm6_mode_beet.c b/net/ipv6/xfrm6_mode_beet.c index 3437d7d..a81ce94 100644 --- a/net/ipv6/xfrm6_mode_beet.c +++ b/net/ipv6/xfrm6_mode_beet.c @@ -72,8 +72,8 @@ static int xfrm6_beet_output(struct xfrm_state *x, struct sk_buff *skb) top_iph->nexthdr = IPPROTO_BEETPH; } - ipv6_addr_copy(&top_iph->saddr, (struct in6_addr *)&x->props.saddr); - ipv6_addr_copy(&top_iph->daddr, (struct in6_addr *)&x->id.daddr); + top_iph->saddr = *(struct in6_addr *)&x->props.saddr; + top_iph->daddr = *(struct in6_addr *)&x->id.daddr; return 0; } @@ -99,8 +99,8 @@ static int xfrm6_beet_input(struct xfrm_state *x, struct sk_buff *skb) ip6h = ipv6_hdr(skb); ip6h->payload_len = htons(skb->len - size); - ipv6_addr_copy(&ip6h->daddr, (struct in6_addr *) &x->sel.daddr.a6); - ipv6_addr_copy(&ip6h->saddr, (struct in6_addr *) &x->sel.saddr.a6); + ip6h->daddr = *(struct in6_addr *)&x->sel.daddr.a6; + ip6h->saddr = *(struct in6_addr *)&x->sel.saddr.a6; err = 0; out: return err; diff --git a/net/ipv6/xfrm6_mode_tunnel.c b/net/ipv6/xfrm6_mode_tunnel.c index 4d6edff..261e6e6 100644 --- a/net/ipv6/xfrm6_mode_tunnel.c +++ b/net/ipv6/xfrm6_mode_tunnel.c @@ -55,8 +55,8 @@ static int xfrm6_mode_tunnel_output(struct xfrm_state *x, struct sk_buff *skb) dsfield &= ~INET_ECN_MASK; ipv6_change_dsfield(top_iph, 0, dsfield); top_iph->hop_limit = ip6_dst_hoplimit(dst->child); - ipv6_addr_copy(&top_iph->saddr, (const struct in6_addr *)&x->props.saddr); - ipv6_addr_copy(&top_iph->daddr, (const struct in6_addr *)&x->id.daddr); + top_iph->saddr = *(struct in6_addr *)&x->props.saddr; + top_iph->daddr = *(struct in6_addr *)&x->id.daddr; return 0; } diff --git a/net/ipv6/xfrm6_output.c b/net/ipv6/xfrm6_output.c index faae417..4eeff89 100644 --- a/net/ipv6/xfrm6_output.c +++ b/net/ipv6/xfrm6_output.c @@ -49,7 +49,7 @@ static void xfrm6_local_rxpmtu(struct sk_buff *skb, u32 mtu) struct sock *sk = skb->sk; fl6.flowi6_oif = sk->sk_bound_dev_if; - ipv6_addr_copy(&fl6.daddr, &ipv6_hdr(skb)->daddr); + fl6.daddr = ipv6_hdr(skb)->daddr; ipv6_local_rxpmtu(sk, &fl6, mtu); } @@ -60,7 +60,7 @@ static void xfrm6_local_error(struct sk_buff *skb, u32 mtu) struct sock *sk = skb->sk; fl6.fl6_dport = inet_sk(sk)->inet_dport; - ipv6_addr_copy(&fl6.daddr, &ipv6_hdr(skb)->daddr); + fl6.daddr = ipv6_hdr(skb)->daddr; ipv6_local_error(sk, EMSGSIZE, &fl6, mtu); } diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c index d879f7e..8ea65e0 100644 --- a/net/ipv6/xfrm6_policy.c +++ b/net/ipv6/xfrm6_policy.c @@ -132,8 +132,8 @@ _decode_session6(struct sk_buff *skb, struct flowi *fl, int reverse) memset(fl6, 0, sizeof(struct flowi6)); fl6->flowi6_mark = skb->mark; - ipv6_addr_copy(&fl6->daddr, reverse ? &hdr->saddr : &hdr->daddr); - ipv6_addr_copy(&fl6->saddr, reverse ? &hdr->daddr : &hdr->saddr); + fl6->daddr = reverse ? hdr->saddr : hdr->daddr; + fl6->saddr = reverse ? hdr->daddr : hdr->saddr; while (nh + offset + 1 < skb->data || pskb_may_pull(skb, nh + offset + 1 - skb->data)) { diff --git a/net/ipv6/xfrm6_state.c b/net/ipv6/xfrm6_state.c index f2d72b8..3f2f7c4 100644 --- a/net/ipv6/xfrm6_state.c +++ b/net/ipv6/xfrm6_state.c @@ -27,8 +27,8 @@ __xfrm6_init_tempsel(struct xfrm_selector *sel, const struct flowi *fl) /* Initialize temporary selector matching only * to current session. */ - ipv6_addr_copy((struct in6_addr *)&sel->daddr, &fl6->daddr); - ipv6_addr_copy((struct in6_addr *)&sel->saddr, &fl6->saddr); + *(struct in6_addr *)&sel->daddr = fl6->daddr; + *(struct in6_addr *)&sel->saddr = fl6->saddr; sel->dport = xfrm_flowi_dport(fl, &fl6->uli); sel->dport_mask = htons(0xffff); sel->sport = xfrm_flowi_sport(fl, &fl6->uli); diff --git a/net/irda/irttp.c b/net/irda/irttp.c index 32e3bb0..5c93f29 100644 --- a/net/irda/irttp.c +++ b/net/irda/irttp.c @@ -1461,14 +1461,12 @@ struct tsap_cb *irttp_dup(struct tsap_cb *orig, void *instance) } /* Allocate a new instance */ - new = kmalloc(sizeof(struct tsap_cb), GFP_ATOMIC); + new = kmemdup(orig, sizeof(struct tsap_cb), GFP_ATOMIC); if (!new) { IRDA_DEBUG(0, "%s(), unable to kmalloc\n", __func__); spin_unlock_irqrestore(&irttp->tsaps->hb_spinlock, flags); return NULL; } - /* Dup */ - memcpy(new, orig, sizeof(struct tsap_cb)); spin_lock_init(&new->lock); /* We don't need the old instance any more */ diff --git a/net/key/af_key.c b/net/key/af_key.c index 1e733e9..bfc0bef 100644 --- a/net/key/af_key.c +++ b/net/key/af_key.c @@ -712,7 +712,7 @@ static unsigned int pfkey_sockaddr_fill(const xfrm_address_t *xaddr, __be16 port sin6->sin6_family = AF_INET6; sin6->sin6_port = port; sin6->sin6_flowinfo = 0; - ipv6_addr_copy(&sin6->sin6_addr, (const struct in6_addr *)xaddr->a6); + sin6->sin6_addr = *(struct in6_addr *)xaddr->a6; sin6->sin6_scope_id = 0; return 128; } diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c index bf8d50c..cf0f308 100644 --- a/net/l2tp/l2tp_core.c +++ b/net/l2tp/l2tp_core.c @@ -756,9 +756,6 @@ static int l2tp_udp_recv_core(struct l2tp_tunnel *tunnel, struct sk_buff *skb, goto error; } - /* Point to L2TP header */ - optr = ptr = skb->data; - /* Trace packet contents, if enabled */ if (tunnel->debug & L2TP_MSG_DATA) { length = min(32u, skb->len); @@ -769,12 +766,15 @@ static int l2tp_udp_recv_core(struct l2tp_tunnel *tunnel, struct sk_buff *skb, offset = 0; do { - printk(" %02X", ptr[offset]); + printk(" %02X", skb->data[offset]); } while (++offset < length); printk("\n"); } + /* Point to L2TP header */ + optr = ptr = skb->data; + /* Get L2TP header flags */ hdrflags = ntohs(*(__be16 *) ptr); diff --git a/net/mac80211/debugfs_sta.c b/net/mac80211/debugfs_sta.c index edfdd74..2406b3e 100644 --- a/net/mac80211/debugfs_sta.c +++ b/net/mac80211/debugfs_sta.c @@ -274,9 +274,9 @@ static ssize_t sta_ht_capa_read(struct file *file, char __user *userbuf, PRINT_HT_CAP((htc->cap & BIT(10)), "HT Delayed Block Ack"); - PRINT_HT_CAP((htc->cap & BIT(11)), "Max AMSDU length: " - "3839 bytes"); PRINT_HT_CAP(!(htc->cap & BIT(11)), "Max AMSDU length: " + "3839 bytes"); + PRINT_HT_CAP((htc->cap & BIT(11)), "Max AMSDU length: " "7935 bytes"); /* diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index a6ad197..09019d1 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -2301,6 +2301,7 @@ void ieee80211_sta_quiesce(struct ieee80211_sub_if_data *sdata) cancel_work_sync(&ifmgd->request_smps_work); + cancel_work_sync(&ifmgd->monitor_work); cancel_work_sync(&ifmgd->beacon_connection_loss_work); if (del_timer_sync(&ifmgd->timer)) set_bit(TMR_RUNNING_TIMER, &ifmgd->timers_running); @@ -2309,7 +2310,6 @@ void ieee80211_sta_quiesce(struct ieee80211_sub_if_data *sdata) if (del_timer_sync(&ifmgd->chswitch_timer)) set_bit(TMR_RUNNING_CHANSW, &ifmgd->timers_running); - cancel_work_sync(&ifmgd->monitor_work); /* these will just be re-established on connection */ del_timer_sync(&ifmgd->conn_mon_timer); del_timer_sync(&ifmgd->bcn_mon_timer); diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index 4eafbfd..d1a8869 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -141,8 +141,9 @@ ieee80211_add_rx_radiotap_header(struct ieee80211_local *local, pos++; /* IEEE80211_RADIOTAP_RATE */ - if (status->flag & RX_FLAG_HT) { + if (!rate || status->flag & RX_FLAG_HT) { /* + * Without rate information don't add it. If we have, * MCS information is a separate field in radiotap, * added below. The byte here is needed as padding * for the channel though, so initialise it to 0. @@ -163,12 +164,14 @@ ieee80211_add_rx_radiotap_header(struct ieee80211_local *local, else if (status->flag & RX_FLAG_HT) put_unaligned_le16(IEEE80211_CHAN_DYN | IEEE80211_CHAN_2GHZ, pos); - else if (rate->flags & IEEE80211_RATE_ERP_G) + else if (rate && rate->flags & IEEE80211_RATE_ERP_G) put_unaligned_le16(IEEE80211_CHAN_OFDM | IEEE80211_CHAN_2GHZ, pos); - else + else if (rate) put_unaligned_le16(IEEE80211_CHAN_CCK | IEEE80211_CHAN_2GHZ, pos); + else + put_unaligned_le16(IEEE80211_CHAN_2GHZ, pos); pos += 2; /* IEEE80211_RADIOTAP_DBM_ANTSIGNAL */ diff --git a/net/mac80211/status.c b/net/mac80211/status.c index a9da6ee..46222ce 100644 --- a/net/mac80211/status.c +++ b/net/mac80211/status.c @@ -260,7 +260,7 @@ static void ieee80211_add_tx_radiotap_header(struct ieee80211_supported_band struct ieee80211_hdr *hdr = (struct ieee80211_hdr *) skb->data; struct ieee80211_radiotap_header *rthdr; unsigned char *pos; - __le16 txflags; + u16 txflags; rthdr = (struct ieee80211_radiotap_header *) skb_push(skb, rtap_len); @@ -290,13 +290,13 @@ static void ieee80211_add_tx_radiotap_header(struct ieee80211_supported_band txflags = 0; if (!(info->flags & IEEE80211_TX_STAT_ACK) && !is_multicast_ether_addr(hdr->addr1)) - txflags |= cpu_to_le16(IEEE80211_RADIOTAP_F_TX_FAIL); + txflags |= IEEE80211_RADIOTAP_F_TX_FAIL; if ((info->status.rates[0].flags & IEEE80211_TX_RC_USE_RTS_CTS) || (info->status.rates[0].flags & IEEE80211_TX_RC_USE_CTS_PROTECT)) - txflags |= cpu_to_le16(IEEE80211_RADIOTAP_F_TX_CTS); + txflags |= IEEE80211_RADIOTAP_F_TX_CTS; else if (info->status.rates[0].flags & IEEE80211_TX_RC_USE_RTS_CTS) - txflags |= cpu_to_le16(IEEE80211_RADIOTAP_F_TX_RTS); + txflags |= IEEE80211_RADIOTAP_F_TX_RTS; put_unaligned_le16(txflags, pos); pos += 2; diff --git a/net/mac80211/util.c b/net/mac80211/util.c index c499a16..3b9b492 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -1034,6 +1034,8 @@ struct sk_buff *ieee80211_build_probe_req(struct ieee80211_sub_if_data *sdata, skb = ieee80211_probereq_get(&local->hw, &sdata->vif, ssid, ssid_len, buf, buf_len); + if (!skb) + goto out; if (dst) { mgmt = (struct ieee80211_mgmt *) skb->data; @@ -1042,6 +1044,8 @@ struct sk_buff *ieee80211_build_probe_req(struct ieee80211_sub_if_data *sdata, } IEEE80211_SKB_CB(skb)->flags |= IEEE80211_TX_INTFL_DONT_ENCRYPT; + + out: kfree(buf); return skb; diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig index 8260b13..e8f3796 100644 --- a/net/netfilter/Kconfig +++ b/net/netfilter/Kconfig @@ -542,7 +542,6 @@ config NETFILTER_XT_TARGET_NOTRACK tristate '"NOTRACK" target support' depends on IP_NF_RAW || IP6_NF_RAW depends on NF_CONNTRACK - depends on NETFILTER_ADVANCED help The NOTRACK target allows a select rule to specify which packets *not* to enter the conntrack/NAT diff --git a/net/netfilter/core.c b/net/netfilter/core.c index afca6c7..4aa0f4b 100644 --- a/net/netfilter/core.c +++ b/net/netfilter/core.c @@ -54,6 +54,12 @@ EXPORT_SYMBOL_GPL(nf_unregister_afinfo); struct list_head nf_hooks[NFPROTO_NUMPROTO][NF_MAX_HOOKS] __read_mostly; EXPORT_SYMBOL(nf_hooks); + +#if defined(CONFIG_JUMP_LABEL) +struct jump_label_key nf_hooks_needed[NFPROTO_NUMPROTO][NF_MAX_HOOKS]; +EXPORT_SYMBOL(nf_hooks_needed); +#endif + static DEFINE_MUTEX(nf_hook_mutex); int nf_register_hook(struct nf_hook_ops *reg) @@ -70,6 +76,9 @@ int nf_register_hook(struct nf_hook_ops *reg) } list_add_rcu(®->list, elem->list.prev); mutex_unlock(&nf_hook_mutex); +#if defined(CONFIG_JUMP_LABEL) + jump_label_inc(&nf_hooks_needed[reg->pf][reg->hooknum]); +#endif return 0; } EXPORT_SYMBOL(nf_register_hook); @@ -79,7 +88,9 @@ void nf_unregister_hook(struct nf_hook_ops *reg) mutex_lock(&nf_hook_mutex); list_del_rcu(®->list); mutex_unlock(&nf_hook_mutex); - +#if defined(CONFIG_JUMP_LABEL) + jump_label_dec(&nf_hooks_needed[reg->pf][reg->hooknum]); +#endif synchronize_net(); } EXPORT_SYMBOL(nf_unregister_hook); diff --git a/net/netfilter/ipset/ip_set_hash_ip.c b/net/netfilter/ipset/ip_set_hash_ip.c index f2d576e..4015fca 100644 --- a/net/netfilter/ipset/ip_set_hash_ip.c +++ b/net/netfilter/ipset/ip_set_hash_ip.c @@ -241,7 +241,7 @@ hash_ip6_data_isnull(const struct hash_ip6_elem *elem) static inline void hash_ip6_data_copy(struct hash_ip6_elem *dst, const struct hash_ip6_elem *src) { - ipv6_addr_copy(&dst->ip.in6, &src->ip.in6); + dst->ip.in6 = src->ip.in6; } static inline void diff --git a/net/netfilter/ipset/ip_set_hash_net.c b/net/netfilter/ipset/ip_set_hash_net.c index 60d0165..2898819 100644 --- a/net/netfilter/ipset/ip_set_hash_net.c +++ b/net/netfilter/ipset/ip_set_hash_net.c @@ -267,7 +267,7 @@ static inline void hash_net6_data_copy(struct hash_net6_elem *dst, const struct hash_net6_elem *src) { - ipv6_addr_copy(&dst->ip.in6, &src->ip.in6); + dst->ip.in6 = src->ip.in6; dst->cidr = src->cidr; } diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index 093cc32..611c335 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -983,7 +983,7 @@ static int ip_vs_out_icmp_v6(struct sk_buff *skb, int *related, if (!cp) return NF_ACCEPT; - ipv6_addr_copy(&snet.in6, &iph->saddr); + snet.in6 = iph->saddr; return handle_response_icmp(AF_INET6, skb, &snet, cih->nexthdr, cp, pp, offset, sizeof(struct ipv6hdr)); } diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c index 3cdd479..bcf5563 100644 --- a/net/netfilter/ipvs/ip_vs_sync.c +++ b/net/netfilter/ipvs/ip_vs_sync.c @@ -603,9 +603,9 @@ sloop: #ifdef CONFIG_IP_VS_IPV6 if (cp->af == AF_INET6) { p += sizeof(struct ip_vs_sync_v6); - ipv6_addr_copy(&s->v6.caddr, &cp->caddr.in6); - ipv6_addr_copy(&s->v6.vaddr, &cp->vaddr.in6); - ipv6_addr_copy(&s->v6.daddr, &cp->daddr.in6); + s->v6.caddr = cp->caddr.in6; + s->v6.vaddr = cp->vaddr.in6; + s->v6.daddr = cp->daddr.in6; } else #endif { diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c index aa2d720..38a576d 100644 --- a/net/netfilter/ipvs/ip_vs_xmit.c +++ b/net/netfilter/ipvs/ip_vs_xmit.c @@ -235,7 +235,7 @@ __ip_vs_route_output_v6(struct net *net, struct in6_addr *daddr, goto out_err; } } - ipv6_addr_copy(ret_saddr, &fl6.saddr); + *ret_saddr = fl6.saddr; return dst; out_err: @@ -279,7 +279,7 @@ __ip_vs_get_out_rt_v6(struct sk_buff *skb, struct ip_vs_dest *dest, atomic_read(&rt->dst.__refcnt)); } if (ret_saddr) - ipv6_addr_copy(ret_saddr, &dest->dst_saddr.in6); + *ret_saddr = dest->dst_saddr.in6; spin_unlock(&dest->dst_lock); } else { dst = __ip_vs_route_output_v6(net, daddr, ret_saddr, do_xfrm); @@ -705,7 +705,7 @@ ip_vs_nat_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, /* mangle the packet */ if (pp->dnat_handler && !pp->dnat_handler(skb, pp, cp)) goto tx_error; - ipv6_addr_copy(&ipv6_hdr(skb)->daddr, &cp->daddr.in6); + ipv6_hdr(skb)->daddr = cp->daddr.in6; if (!local || !skb->dev) { /* drop the old route when skb is not shared */ @@ -967,8 +967,8 @@ ip_vs_tunnel_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, be16_add_cpu(&iph->payload_len, sizeof(*old_iph)); iph->priority = old_iph->priority; memset(&iph->flow_lbl, 0, sizeof(iph->flow_lbl)); - ipv6_addr_copy(&iph->daddr, &cp->daddr.in6); - ipv6_addr_copy(&iph->saddr, &saddr); + iph->daddr = cp->daddr.in6; + iph->saddr = saddr; iph->hop_limit = old_iph->hop_limit; /* Another hack: avoid icmp_send in ip_fragment */ diff --git a/net/netfilter/nf_conntrack_h323_main.c b/net/netfilter/nf_conntrack_h323_main.c index f03c2d4..f9368f3 100644 --- a/net/netfilter/nf_conntrack_h323_main.c +++ b/net/netfilter/nf_conntrack_h323_main.c @@ -750,10 +750,10 @@ static int callforward_do_filter(const union nf_inet_addr *src, struct rt6_info *rt1, *rt2; memset(&fl1, 0, sizeof(fl1)); - ipv6_addr_copy(&fl1.daddr, &src->in6); + fl1.daddr = src->in6; memset(&fl2, 0, sizeof(fl2)); - ipv6_addr_copy(&fl2.daddr, &dst->in6); + fl2.daddr = dst->in6; if (!afinfo->route(&init_net, (struct dst_entry **)&rt1, flowi6_to_flowi(&fl1), false)) { if (!afinfo->route(&init_net, (struct dst_entry **)&rt2, diff --git a/net/netfilter/xt_TCPMSS.c b/net/netfilter/xt_TCPMSS.c index 9e63b43..3ecade3 100644 --- a/net/netfilter/xt_TCPMSS.c +++ b/net/netfilter/xt_TCPMSS.c @@ -161,7 +161,7 @@ static u_int32_t tcpmss_reverse_mtu(const struct sk_buff *skb, struct flowi6 *fl6 = &fl.u.ip6; memset(fl6, 0, sizeof(*fl6)); - ipv6_addr_copy(&fl6->daddr, &ipv6_hdr(skb)->saddr); + fl6->daddr = ipv6_hdr(skb)->saddr; } rcu_read_lock(); ai = nf_get_afinfo(family); diff --git a/net/netfilter/xt_addrtype.c b/net/netfilter/xt_addrtype.c index b77d383..c047de2 100644 --- a/net/netfilter/xt_addrtype.c +++ b/net/netfilter/xt_addrtype.c @@ -42,7 +42,7 @@ static u32 match_lookup_rt6(struct net *net, const struct net_device *dev, int route_err; memset(&flow, 0, sizeof(flow)); - ipv6_addr_copy(&flow.daddr, addr); + flow.daddr = *addr; if (dev) flow.flowi6_oif = dev->ifindex; diff --git a/net/netlabel/netlabel_kapi.c b/net/netlabel/netlabel_kapi.c index 9c24de10..3735297 100644 --- a/net/netlabel/netlabel_kapi.c +++ b/net/netlabel/netlabel_kapi.c @@ -155,15 +155,15 @@ int netlbl_cfg_unlbl_map_add(const char *domain, if (map6 == NULL) goto cfg_unlbl_map_add_failure; map6->type = NETLBL_NLTYPE_UNLABELED; - ipv6_addr_copy(&map6->list.addr, addr6); + map6->list.addr = *addr6; map6->list.addr.s6_addr32[0] &= mask6->s6_addr32[0]; map6->list.addr.s6_addr32[1] &= mask6->s6_addr32[1]; map6->list.addr.s6_addr32[2] &= mask6->s6_addr32[2]; map6->list.addr.s6_addr32[3] &= mask6->s6_addr32[3]; - ipv6_addr_copy(&map6->list.mask, mask6); + map6->list.mask = *mask6; map6->list.valid = 1; - ret_val = netlbl_af4list_add(&map4->list, - &addrmap->list4); + ret_val = netlbl_af6list_add(&map6->list, + &addrmap->list6); if (ret_val != 0) goto cfg_unlbl_map_add_failure; break; diff --git a/net/netlabel/netlabel_mgmt.c b/net/netlabel/netlabel_mgmt.c index bfa5558..9879300 100644 --- a/net/netlabel/netlabel_mgmt.c +++ b/net/netlabel/netlabel_mgmt.c @@ -216,12 +216,12 @@ static int netlbl_mgmt_add_common(struct genl_info *info, ret_val = -ENOMEM; goto add_failure; } - ipv6_addr_copy(&map->list.addr, addr); + map->list.addr = *addr; map->list.addr.s6_addr32[0] &= mask->s6_addr32[0]; map->list.addr.s6_addr32[1] &= mask->s6_addr32[1]; map->list.addr.s6_addr32[2] &= mask->s6_addr32[2]; map->list.addr.s6_addr32[3] &= mask->s6_addr32[3]; - ipv6_addr_copy(&map->list.mask, mask); + map->list.mask = *mask; map->list.valid = 1; map->type = entry->type; diff --git a/net/netlabel/netlabel_unlabeled.c b/net/netlabel/netlabel_unlabeled.c index e251c2c..049ccd2 100644 --- a/net/netlabel/netlabel_unlabeled.c +++ b/net/netlabel/netlabel_unlabeled.c @@ -300,12 +300,12 @@ static int netlbl_unlhsh_add_addr6(struct netlbl_unlhsh_iface *iface, if (entry == NULL) return -ENOMEM; - ipv6_addr_copy(&entry->list.addr, addr); + entry->list.addr = *addr; entry->list.addr.s6_addr32[0] &= mask->s6_addr32[0]; entry->list.addr.s6_addr32[1] &= mask->s6_addr32[1]; entry->list.addr.s6_addr32[2] &= mask->s6_addr32[2]; entry->list.addr.s6_addr32[3] &= mask->s6_addr32[3]; - ipv6_addr_copy(&entry->list.mask, mask); + entry->list.mask = *mask; entry->list.valid = 1; entry->secid = secid; diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 82a6f34..0da505c 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -1499,10 +1499,11 @@ retry: if (!skb) { size_t reserved = LL_RESERVED_SPACE(dev); + int tlen = dev->needed_tailroom; unsigned int hhlen = dev->header_ops ? dev->hard_header_len : 0; rcu_read_unlock(); - skb = sock_wmalloc(sk, len + reserved, 0, GFP_KERNEL); + skb = sock_wmalloc(sk, len + reserved + tlen, 0, GFP_KERNEL); if (skb == NULL) return -ENOBUFS; /* FIXME: Save some space for broken drivers that write a hard @@ -1944,7 +1945,7 @@ static void tpacket_destruct_skb(struct sk_buff *skb) static int tpacket_fill_skb(struct packet_sock *po, struct sk_buff *skb, void *frame, struct net_device *dev, int size_max, - __be16 proto, unsigned char *addr) + __be16 proto, unsigned char *addr, int hlen) { union { struct tpacket_hdr *h1; @@ -1978,7 +1979,7 @@ static int tpacket_fill_skb(struct packet_sock *po, struct sk_buff *skb, return -EMSGSIZE; } - skb_reserve(skb, LL_RESERVED_SPACE(dev)); + skb_reserve(skb, hlen); skb_reset_network_header(skb); data = ph.raw + po->tp_hdrlen - sizeof(struct sockaddr_ll); @@ -2053,6 +2054,7 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg) unsigned char *addr; int len_sum = 0; int status = 0; + int hlen, tlen; mutex_lock(&po->pg_vec_lock); @@ -2101,16 +2103,17 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg) } status = TP_STATUS_SEND_REQUEST; + hlen = LL_RESERVED_SPACE(dev); + tlen = dev->needed_tailroom; skb = sock_alloc_send_skb(&po->sk, - LL_ALLOCATED_SPACE(dev) - + sizeof(struct sockaddr_ll), + hlen + tlen + sizeof(struct sockaddr_ll), 0, &err); if (unlikely(skb == NULL)) goto out_status; tp_len = tpacket_fill_skb(po, skb, ph, dev, size_max, proto, - addr); + addr, hlen); if (unlikely(tp_len < 0)) { if (po->tp_loss) { @@ -2207,6 +2210,7 @@ static int packet_snd(struct socket *sock, int vnet_hdr_len; struct packet_sock *po = pkt_sk(sk); unsigned short gso_type = 0; + int hlen, tlen; /* * Get and verify the address. @@ -2291,8 +2295,9 @@ static int packet_snd(struct socket *sock, goto out_unlock; err = -ENOBUFS; - skb = packet_alloc_skb(sk, LL_ALLOCATED_SPACE(dev), - LL_RESERVED_SPACE(dev), len, vnet_hdr.hdr_len, + hlen = LL_RESERVED_SPACE(dev); + tlen = dev->needed_tailroom; + skb = packet_alloc_skb(sk, hlen + tlen, hlen, len, vnet_hdr.hdr_len, msg->msg_flags & MSG_DONTWAIT, &err); if (skb == NULL) goto out_unlock; diff --git a/net/phonet/pep.c b/net/phonet/pep.c index 2ba6e9f..9f60008 100644 --- a/net/phonet/pep.c +++ b/net/phonet/pep.c @@ -534,6 +534,29 @@ static int pep_connresp_rcv(struct sock *sk, struct sk_buff *skb) return pipe_handler_send_created_ind(sk); } +static int pep_enableresp_rcv(struct sock *sk, struct sk_buff *skb) +{ + struct pnpipehdr *hdr = pnp_hdr(skb); + + if (hdr->error_code != PN_PIPE_NO_ERROR) + return -ECONNREFUSED; + + return pep_indicate(sk, PNS_PIPE_ENABLED_IND, 0 /* sub-blocks */, + NULL, 0, GFP_ATOMIC); + +} + +static void pipe_start_flow_control(struct sock *sk) +{ + struct pep_sock *pn = pep_sk(sk); + + if (!pn_flow_safe(pn->tx_fc)) { + atomic_set(&pn->tx_credits, 1); + sk->sk_write_space(sk); + } + pipe_grant_credits(sk, GFP_ATOMIC); +} + /* Queue an skb to an actively connected sock. * Socket lock must be held. */ static int pipe_handler_do_rcv(struct sock *sk, struct sk_buff *skb) @@ -579,13 +602,25 @@ static int pipe_handler_do_rcv(struct sock *sk, struct sk_buff *skb) sk->sk_state = TCP_CLOSE_WAIT; break; } + if (pn->init_enable == PN_PIPE_DISABLE) + sk->sk_state = TCP_SYN_RECV; + else { + sk->sk_state = TCP_ESTABLISHED; + pipe_start_flow_control(sk); + } + break; - sk->sk_state = TCP_ESTABLISHED; - if (!pn_flow_safe(pn->tx_fc)) { - atomic_set(&pn->tx_credits, 1); - sk->sk_write_space(sk); + case PNS_PEP_ENABLE_RESP: + if (sk->sk_state != TCP_SYN_SENT) + break; + + if (pep_enableresp_rcv(sk, skb)) { + sk->sk_state = TCP_CLOSE_WAIT; + break; } - pipe_grant_credits(sk, GFP_ATOMIC); + + sk->sk_state = TCP_ESTABLISHED; + pipe_start_flow_control(sk); break; case PNS_PEP_DISCONNECT_RESP: @@ -864,14 +899,32 @@ static int pep_sock_connect(struct sock *sk, struct sockaddr *addr, int len) int err; u8 data[4] = { 0 /* sub-blocks */, PAD, PAD, PAD }; - pn->pipe_handle = 1; /* anything but INVALID_HANDLE */ + if (pn->pipe_handle == PN_PIPE_INVALID_HANDLE) + pn->pipe_handle = 1; /* anything but INVALID_HANDLE */ + err = pipe_handler_request(sk, PNS_PEP_CONNECT_REQ, - PN_PIPE_ENABLE, data, 4); + pn->init_enable, data, 4); if (err) { pn->pipe_handle = PN_PIPE_INVALID_HANDLE; return err; } + sk->sk_state = TCP_SYN_SENT; + + return 0; +} + +static int pep_sock_enable(struct sock *sk, struct sockaddr *addr, int len) +{ + int err; + + err = pipe_handler_request(sk, PNS_PEP_ENABLE_REQ, PAD, + NULL, 0); + if (err) + return err; + + sk->sk_state = TCP_SYN_SENT; + return 0; } @@ -879,11 +932,14 @@ static int pep_ioctl(struct sock *sk, int cmd, unsigned long arg) { struct pep_sock *pn = pep_sk(sk); int answ; + int ret = -ENOIOCTLCMD; switch (cmd) { case SIOCINQ: - if (sk->sk_state == TCP_LISTEN) - return -EINVAL; + if (sk->sk_state == TCP_LISTEN) { + ret = -EINVAL; + break; + } lock_sock(sk); if (sock_flag(sk, SOCK_URGINLINE) && @@ -894,10 +950,22 @@ static int pep_ioctl(struct sock *sk, int cmd, unsigned long arg) else answ = 0; release_sock(sk); - return put_user(answ, (int __user *)arg); + ret = put_user(answ, (int __user *)arg); + break; + + case SIOCPNENABLEPIPE: + lock_sock(sk); + if (sk->sk_state == TCP_SYN_SENT) + ret = -EBUSY; + else if (sk->sk_state == TCP_ESTABLISHED) + ret = -EISCONN; + else + ret = pep_sock_enable(sk, NULL, 0); + release_sock(sk); + break; } - return -ENOIOCTLCMD; + return ret; } static int pep_init(struct sock *sk) @@ -960,6 +1028,18 @@ static int pep_setsockopt(struct sock *sk, int level, int optname, } goto out_norel; + case PNPIPE_HANDLE: + if ((sk->sk_state == TCP_CLOSE) && + (val >= 0) && (val < PN_PIPE_INVALID_HANDLE)) + pn->pipe_handle = val; + else + err = -EINVAL; + break; + + case PNPIPE_INITSTATE: + pn->init_enable = !!val; + break; + default: err = -ENOPROTOOPT; } @@ -995,6 +1075,10 @@ static int pep_getsockopt(struct sock *sk, int level, int optname, return -EINVAL; break; + case PNPIPE_INITSTATE: + val = pn->init_enable; + break; + default: return -ENOPROTOOPT; } diff --git a/net/rds/Kconfig b/net/rds/Kconfig index 4cf6dc7..ec753b3 100644 --- a/net/rds/Kconfig +++ b/net/rds/Kconfig @@ -9,7 +9,6 @@ config RDS config RDS_RDMA tristate "RDS over Infiniband and iWARP" - select LLIST depends on RDS && INFINIBAND && INFINIBAND_ADDR_TRANS ---help--- Allow RDS to use Infiniband and iWARP as a transport. diff --git a/net/rxrpc/ar-key.c b/net/rxrpc/ar-key.c index 43ea7de..4cba13e 100644 --- a/net/rxrpc/ar-key.c +++ b/net/rxrpc/ar-key.c @@ -306,10 +306,9 @@ static int rxrpc_krb5_decode_tagged_data(struct krb5_tagged_data *td, td->data_len = len; if (len > 0) { - td->data = kmalloc(len, GFP_KERNEL); + td->data = kmemdup(xdr, len, GFP_KERNEL); if (!td->data) return -ENOMEM; - memcpy(td->data, xdr, len); len = (len + 3) & ~3; toklen -= len; xdr += len >> 2; @@ -401,10 +400,9 @@ static int rxrpc_krb5_decode_ticket(u8 **_ticket, u16 *_tktlen, _debug("ticket len %u", len); if (len > 0) { - *_ticket = kmalloc(len, GFP_KERNEL); + *_ticket = kmemdup(xdr, len, GFP_KERNEL); if (!*_ticket) return -ENOMEM; - memcpy(*_ticket, xdr, len); len = (len + 3) & ~3; toklen -= len; xdr += len >> 2; diff --git a/net/sched/sch_choke.c b/net/sched/sch_choke.c index 3422b25..061bcb7 100644 --- a/net/sched/sch_choke.c +++ b/net/sched/sch_choke.c @@ -152,15 +152,14 @@ static bool choke_match_flow(struct sk_buff *skb1, { int off1, off2, poff; const u32 *ports1, *ports2; + u32 _ports1, _ports2; u8 ip_proto; __u32 hash1; if (skb1->protocol != skb2->protocol) return false; - /* Use hash value as quick check - * Assumes that __skb_get_rxhash makes IP header and ports linear - */ + /* Use rxhash value as quick check */ hash1 = skb_get_rxhash(skb1); if (!hash1 || hash1 != skb_get_rxhash(skb2)) return false; @@ -172,10 +171,12 @@ static bool choke_match_flow(struct sk_buff *skb1, switch (skb1->protocol) { case __constant_htons(ETH_P_IP): { const struct iphdr *ip1, *ip2; + struct iphdr _ip1, _ip2; - ip1 = (const struct iphdr *) (skb1->data + off1); - ip2 = (const struct iphdr *) (skb2->data + off2); - + ip1 = skb_header_pointer(skb1, off1, sizeof(_ip1), &_ip1); + ip2 = skb_header_pointer(skb2, off2, sizeof(_ip2), &_ip2); + if (!ip1 || !ip2) + return false; ip_proto = ip1->protocol; if (ip_proto != ip2->protocol || ip1->saddr != ip2->saddr || ip1->daddr != ip2->daddr) @@ -190,9 +191,12 @@ static bool choke_match_flow(struct sk_buff *skb1, case __constant_htons(ETH_P_IPV6): { const struct ipv6hdr *ip1, *ip2; + struct ipv6hdr _ip1, _ip2; - ip1 = (const struct ipv6hdr *) (skb1->data + off1); - ip2 = (const struct ipv6hdr *) (skb2->data + off2); + ip1 = skb_header_pointer(skb1, off1, sizeof(_ip1), &_ip1); + ip2 = skb_header_pointer(skb2, off2, sizeof(_ip2), &_ip2); + if (!ip1 || !ip2) + return false; ip_proto = ip1->nexthdr; if (ip_proto != ip2->nexthdr || @@ -214,8 +218,11 @@ static bool choke_match_flow(struct sk_buff *skb1, off1 += poff; off2 += poff; - ports1 = (__force u32 *)(skb1->data + off1); - ports2 = (__force u32 *)(skb2->data + off2); + ports1 = skb_header_pointer(skb1, off1, sizeof(_ports1), &_ports1); + ports2 = skb_header_pointer(skb2, off2, sizeof(_ports2), &_ports2); + if (!ports1 || !ports2) + return false; + return *ports1 == *ports2; } diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index 69fca27..79ac145 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -246,6 +246,7 @@ static void dev_watchdog(unsigned long arg) time_after(jiffies, (trans_start + dev->watchdog_timeo))) { some_queue_timedout = 1; + txq->trans_timeout++; break; } } diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c index 8104278..91f4791 100644 --- a/net/sctp/ipv6.c +++ b/net/sctp/ipv6.c @@ -107,7 +107,7 @@ static int sctp_inet6addr_event(struct notifier_block *this, unsigned long ev, if (addr) { addr->a.v6.sin6_family = AF_INET6; addr->a.v6.sin6_port = 0; - ipv6_addr_copy(&addr->a.v6.sin6_addr, &ifa->addr); + addr->a.v6.sin6_addr = ifa->addr; addr->a.v6.sin6_scope_id = ifa->idev->dev->ifindex; addr->valid = 1; spin_lock_bh(&sctp_local_addr_lock); @@ -219,8 +219,8 @@ static int sctp_v6_xmit(struct sk_buff *skb, struct sctp_transport *transport) /* Fill in the dest address from the route entry passed with the skb * and the source address from the transport. */ - ipv6_addr_copy(&fl6.daddr, &transport->ipaddr.v6.sin6_addr); - ipv6_addr_copy(&fl6.saddr, &transport->saddr.v6.sin6_addr); + fl6.daddr = transport->ipaddr.v6.sin6_addr; + fl6.saddr = transport->saddr.v6.sin6_addr; fl6.flowlabel = np->flow_label; IP6_ECN_flow_xmit(sk, fl6.flowlabel); @@ -231,7 +231,7 @@ static int sctp_v6_xmit(struct sk_buff *skb, struct sctp_transport *transport) if (np->opt && np->opt->srcrt) { struct rt0_hdr *rt0 = (struct rt0_hdr *) np->opt->srcrt; - ipv6_addr_copy(&fl6.daddr, rt0->addr); + fl6.daddr = *rt0->addr; } SCTP_DEBUG_PRINTK("%s: skb:%p, len:%d, src:%pI6 dst:%pI6\n", @@ -265,7 +265,7 @@ static void sctp_v6_get_dst(struct sctp_transport *t, union sctp_addr *saddr, sctp_scope_t scope; memset(fl6, 0, sizeof(struct flowi6)); - ipv6_addr_copy(&fl6->daddr, &daddr->v6.sin6_addr); + fl6->daddr = daddr->v6.sin6_addr; fl6->fl6_dport = daddr->v6.sin6_port; fl6->flowi6_proto = IPPROTO_SCTP; if (ipv6_addr_type(&daddr->v6.sin6_addr) & IPV6_ADDR_LINKLOCAL) @@ -277,7 +277,7 @@ static void sctp_v6_get_dst(struct sctp_transport *t, union sctp_addr *saddr, fl6->fl6_sport = htons(asoc->base.bind_addr.port); if (saddr) { - ipv6_addr_copy(&fl6->saddr, &saddr->v6.sin6_addr); + fl6->saddr = saddr->v6.sin6_addr; fl6->fl6_sport = saddr->v6.sin6_port; SCTP_DEBUG_PRINTK("SRC=%pI6 - ", &fl6->saddr); } @@ -334,7 +334,7 @@ static void sctp_v6_get_dst(struct sctp_transport *t, union sctp_addr *saddr, } rcu_read_unlock(); if (baddr) { - ipv6_addr_copy(&fl6->saddr, &baddr->v6.sin6_addr); + fl6->saddr = baddr->v6.sin6_addr; fl6->fl6_sport = baddr->v6.sin6_port; dst = ip6_dst_lookup_flow(sk, fl6, NULL, false); } @@ -375,7 +375,7 @@ static void sctp_v6_get_saddr(struct sctp_sock *sk, if (t->dst) { saddr->v6.sin6_family = AF_INET6; - ipv6_addr_copy(&saddr->v6.sin6_addr, &fl6->saddr); + saddr->v6.sin6_addr = fl6->saddr; } } @@ -400,7 +400,7 @@ static void sctp_v6_copy_addrlist(struct list_head *addrlist, if (addr) { addr->a.v6.sin6_family = AF_INET6; addr->a.v6.sin6_port = 0; - ipv6_addr_copy(&addr->a.v6.sin6_addr, &ifp->addr); + addr->a.v6.sin6_addr = ifp->addr; addr->a.v6.sin6_scope_id = dev->ifindex; addr->valid = 1; INIT_LIST_HEAD(&addr->list); @@ -416,7 +416,6 @@ static void sctp_v6_copy_addrlist(struct list_head *addrlist, static void sctp_v6_from_skb(union sctp_addr *addr,struct sk_buff *skb, int is_saddr) { - void *from; __be16 *port; struct sctphdr *sh; @@ -428,12 +427,11 @@ static void sctp_v6_from_skb(union sctp_addr *addr,struct sk_buff *skb, sh = sctp_hdr(skb); if (is_saddr) { *port = sh->source; - from = &ipv6_hdr(skb)->saddr; + addr->v6.sin6_addr = ipv6_hdr(skb)->saddr; } else { *port = sh->dest; - from = &ipv6_hdr(skb)->daddr; + addr->v6.sin6_addr = ipv6_hdr(skb)->daddr; } - ipv6_addr_copy(&addr->v6.sin6_addr, from); } /* Initialize an sctp_addr from a socket. */ @@ -441,7 +439,7 @@ static void sctp_v6_from_sk(union sctp_addr *addr, struct sock *sk) { addr->v6.sin6_family = AF_INET6; addr->v6.sin6_port = 0; - ipv6_addr_copy(&addr->v6.sin6_addr, &inet6_sk(sk)->rcv_saddr); + addr->v6.sin6_addr = inet6_sk(sk)->rcv_saddr; } /* Initialize sk->sk_rcv_saddr from sctp_addr. */ @@ -454,7 +452,7 @@ static void sctp_v6_to_sk_saddr(union sctp_addr *addr, struct sock *sk) inet6_sk(sk)->rcv_saddr.s6_addr32[3] = addr->v4.sin_addr.s_addr; } else { - ipv6_addr_copy(&inet6_sk(sk)->rcv_saddr, &addr->v6.sin6_addr); + inet6_sk(sk)->rcv_saddr = addr->v6.sin6_addr; } } @@ -467,7 +465,7 @@ static void sctp_v6_to_sk_daddr(union sctp_addr *addr, struct sock *sk) inet6_sk(sk)->daddr.s6_addr32[2] = htonl(0x0000ffff); inet6_sk(sk)->daddr.s6_addr32[3] = addr->v4.sin_addr.s_addr; } else { - ipv6_addr_copy(&inet6_sk(sk)->daddr, &addr->v6.sin6_addr); + inet6_sk(sk)->daddr = addr->v6.sin6_addr; } } @@ -479,7 +477,7 @@ static void sctp_v6_from_addr_param(union sctp_addr *addr, addr->v6.sin6_family = AF_INET6; addr->v6.sin6_port = port; addr->v6.sin6_flowinfo = 0; /* BUG */ - ipv6_addr_copy(&addr->v6.sin6_addr, ¶m->v6.addr); + addr->v6.sin6_addr = param->v6.addr; addr->v6.sin6_scope_id = iif; } @@ -493,7 +491,7 @@ static int sctp_v6_to_addr_param(const union sctp_addr *addr, param->v6.param_hdr.type = SCTP_PARAM_IPV6_ADDRESS; param->v6.param_hdr.length = htons(length); - ipv6_addr_copy(¶m->v6.addr, &addr->v6.sin6_addr); + param->v6.addr = addr->v6.sin6_addr; return length; } @@ -504,7 +502,7 @@ static void sctp_v6_to_addr(union sctp_addr *addr, struct in6_addr *saddr, { addr->sa.sa_family = AF_INET6; addr->v6.sin6_port = port; - ipv6_addr_copy(&addr->v6.sin6_addr, saddr); + addr->v6.sin6_addr = *saddr; } /* Compare addresses exactly. @@ -759,7 +757,7 @@ static void sctp_inet6_event_msgname(struct sctp_ulpevent *event, } sin6from = &asoc->peer.primary_addr.v6; - ipv6_addr_copy(&sin6->sin6_addr, &sin6from->sin6_addr); + sin6->sin6_addr = sin6from->sin6_addr; if (ipv6_addr_type(&sin6->sin6_addr) & IPV6_ADDR_LINKLOCAL) sin6->sin6_scope_id = sin6from->sin6_scope_id; } @@ -787,7 +785,7 @@ static void sctp_inet6_skb_msgname(struct sk_buff *skb, char *msgname, } /* Otherwise, just copy the v6 address. */ - ipv6_addr_copy(&sin6->sin6_addr, &ipv6_hdr(skb)->saddr); + sin6->sin6_addr = ipv6_hdr(skb)->saddr; if (ipv6_addr_type(&sin6->sin6_addr) & IPV6_ADDR_LINKLOCAL) { struct sctp_ulpevent *ev = sctp_skb2event(skb); sin6->sin6_scope_id = ev->iif; diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c index 0121e0a..a85eeeb 100644 --- a/net/sctp/sm_make_chunk.c +++ b/net/sctp/sm_make_chunk.c @@ -3400,8 +3400,10 @@ int sctp_process_asconf_ack(struct sctp_association *asoc, asconf_len -= length; } - if (no_err && asoc->src_out_of_asoc_ok) + if (no_err && asoc->src_out_of_asoc_ok) { asoc->src_out_of_asoc_ok = 0; + sctp_transport_immediate_rtx(asoc->peer.primary_path); + } /* Free the cached last sent asconf chunk. */ list_del_init(&asconf->transmitted_list); diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c index 76388b0..1ff51c9 100644 --- a/net/sctp/sm_sideeffect.c +++ b/net/sctp/sm_sideeffect.c @@ -666,6 +666,7 @@ static void sctp_cmd_transport_on(sctp_cmd_seq_t *cmds, struct sctp_chunk *chunk) { sctp_sender_hb_info_t *hbinfo; + int was_unconfirmed = 0; /* 8.3 Upon the receipt of the HEARTBEAT ACK, the sender of the * HEARTBEAT should clear the error counter of the destination @@ -692,9 +693,11 @@ static void sctp_cmd_transport_on(sctp_cmd_seq_t *cmds, /* Mark the destination transport address as active if it is not so * marked. */ - if ((t->state == SCTP_INACTIVE) || (t->state == SCTP_UNCONFIRMED)) + if ((t->state == SCTP_INACTIVE) || (t->state == SCTP_UNCONFIRMED)) { + was_unconfirmed = 1; sctp_assoc_control_transport(asoc, t, SCTP_TRANSPORT_UP, SCTP_HEARTBEAT_SUCCESS); + } /* The receiver of the HEARTBEAT ACK should also perform an * RTT measurement for that destination transport address @@ -712,6 +715,9 @@ static void sctp_cmd_transport_on(sctp_cmd_seq_t *cmds, /* Update the heartbeat timer. */ if (!mod_timer(&t->hb_timer, sctp_transport_timeout(t))) sctp_transport_hold(t); + + if (was_unconfirmed && asoc->peer.transport_count == 1) + sctp_transport_immediate_rtx(t); } diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 13bf5fc..d56c07a 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -804,7 +804,7 @@ static int sctp_send_asconf_del_ip(struct sock *sk, struct sockaddr_in6 *sin6; sin6 = (struct sockaddr_in6 *)addrs; - ipv6_addr_copy(&asoc->asconf_addr_del_pending->v6.sin6_addr, &sin6->sin6_addr); + asoc->asconf_addr_del_pending->v6.sin6_addr = sin6->sin6_addr; } SCTP_DEBUG_PRINTK_IPADDR("send_asconf_del_ip: keep the last address asoc: %p ", " at %p\n", asoc, asoc->asconf_addr_del_pending, diff --git a/net/sctp/transport.c b/net/sctp/transport.c index 394c57c..3889330 100644 --- a/net/sctp/transport.c +++ b/net/sctp/transport.c @@ -641,3 +641,19 @@ void sctp_transport_reset(struct sctp_transport *t) t->cacc.next_tsn_at_change = 0; t->cacc.cacc_saw_newack = 0; } + +/* Schedule retransmission on the given transport */ +void sctp_transport_immediate_rtx(struct sctp_transport *t) +{ + /* Stop pending T3_rtx_timer */ + if (timer_pending(&t->T3_rtx_timer)) { + (void)del_timer(&t->T3_rtx_timer); + sctp_transport_put(t); + } + sctp_retransmit(&t->asoc->outqueue, t, SCTP_RTXR_T3_RTX); + if (!timer_pending(&t->T3_rtx_timer)) { + if (!mod_timer(&t->T3_rtx_timer, jiffies + t->rto)) + sctp_transport_hold(t); + } + return; +} diff --git a/net/socket.c b/net/socket.c index 425ef42..e62b4f0 100644 --- a/net/socket.c +++ b/net/socket.c @@ -551,6 +551,8 @@ static inline int __sock_sendmsg_nosec(struct kiocb *iocb, struct socket *sock, sock_update_classid(sock->sk); + sock_update_netprioidx(sock->sk); + si->sock = sock; si->scm = NULL; si->msg = msg; diff --git a/net/sunrpc/svcauth_unix.c b/net/sunrpc/svcauth_unix.c index ce13632..fe258fc 100644 --- a/net/sunrpc/svcauth_unix.c +++ b/net/sunrpc/svcauth_unix.c @@ -134,7 +134,7 @@ static void ip_map_init(struct cache_head *cnew, struct cache_head *citem) struct ip_map *item = container_of(citem, struct ip_map, h); strcpy(new->m_class, item->m_class); - ipv6_addr_copy(&new->m_addr, &item->m_addr); + new->m_addr = item->m_addr; } static void update(struct cache_head *cnew, struct cache_head *citem) { @@ -274,7 +274,7 @@ static int ip_map_show(struct seq_file *m, } im = container_of(h, struct ip_map, h); /* class addr domain */ - ipv6_addr_copy(&addr, &im->m_addr); + addr = im->m_addr; if (test_bit(CACHE_VALID, &h->flags) && !test_bit(CACHE_NEGATIVE, &h->flags)) @@ -297,7 +297,7 @@ static struct ip_map *__ip_map_lookup(struct cache_detail *cd, char *class, struct cache_head *ch; strcpy(ip.m_class, class); - ipv6_addr_copy(&ip.m_addr, addr); + ip.m_addr = *addr; ch = sunrpc_cache_lookup(cd, &ip.h, hash_str(class, IP_HASHBITS) ^ hash_ip6(*addr)); diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c index 71bed1c..4653286 100644 --- a/net/sunrpc/svcsock.c +++ b/net/sunrpc/svcsock.c @@ -157,7 +157,7 @@ static void svc_set_cmsg_data(struct svc_rqst *rqstp, struct cmsghdr *cmh) cmh->cmsg_level = SOL_IPV6; cmh->cmsg_type = IPV6_PKTINFO; pki->ipi6_ifindex = daddr->sin6_scope_id; - ipv6_addr_copy(&pki->ipi6_addr, &daddr->sin6_addr); + pki->ipi6_addr = daddr->sin6_addr; cmh->cmsg_len = CMSG_LEN(sizeof(*pki)); } break; @@ -523,7 +523,7 @@ static int svc_udp_get_dest_address6(struct svc_rqst *rqstp, return 0; daddr->sin6_family = AF_INET6; - ipv6_addr_copy(&daddr->sin6_addr, &pki->ipi6_addr); + daddr->sin6_addr = pki->ipi6_addr; daddr->sin6_scope_id = pki->ipi6_ifindex; return 1; } diff --git a/net/wireless/reg.c b/net/wireless/reg.c index 0e67016..76b35df 100644 --- a/net/wireless/reg.c +++ b/net/wireless/reg.c @@ -2076,6 +2076,10 @@ static int __set_regdom(const struct ieee80211_regdomain *rd) } request_wiphy = wiphy_idx_to_wiphy(last_request->wiphy_idx); + if (!request_wiphy) { + reg_set_request_processed(); + return -ENODEV; + } if (!last_request->intersect) { int r; @@ -2304,6 +2308,9 @@ void /* __init_or_exit */ regulatory_exit(void) kfree(last_request); + last_request = NULL; + dev_set_uevent_suppress(®_pdev->dev, true); + platform_device_unregister(reg_pdev); spin_lock_bh(®_pending_beacons_lock); diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 552df27..4fce1ce 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -61,8 +61,8 @@ __xfrm4_selector_match(const struct xfrm_selector *sel, const struct flowi *fl) { const struct flowi4 *fl4 = &fl->u.ip4; - return addr_match(&fl4->daddr, &sel->daddr, sel->prefixlen_d) && - addr_match(&fl4->saddr, &sel->saddr, sel->prefixlen_s) && + return addr4_match(fl4->daddr, sel->daddr.a4, sel->prefixlen_d) && + addr4_match(fl4->saddr, sel->saddr.a4, sel->prefixlen_s) && !((xfrm_flowi_dport(fl, &fl4->uli) ^ sel->dport) & sel->dport_mask) && !((xfrm_flowi_sport(fl, &fl4->uli) ^ sel->sport) & sel->sport_mask) && (fl4->flowi4_proto == sel->proto || !sel->proto) && @@ -2382,9 +2382,11 @@ static unsigned int xfrm_default_advmss(const struct dst_entry *dst) return dst_metric_advmss(dst->path); } -static unsigned int xfrm_default_mtu(const struct dst_entry *dst) +static unsigned int xfrm_mtu(const struct dst_entry *dst) { - return dst_mtu(dst->path); + unsigned int mtu = dst_metric_raw(dst, RTAX_MTU); + + return mtu ? : dst_mtu(dst->path); } static struct neighbour *xfrm_neigh_lookup(const struct dst_entry *dst, const void *daddr) @@ -2411,8 +2413,8 @@ int xfrm_policy_register_afinfo(struct xfrm_policy_afinfo *afinfo) dst_ops->check = xfrm_dst_check; if (likely(dst_ops->default_advmss == NULL)) dst_ops->default_advmss = xfrm_default_advmss; - if (likely(dst_ops->default_mtu == NULL)) - dst_ops->default_mtu = xfrm_default_mtu; + if (likely(dst_ops->mtu == NULL)) + dst_ops->mtu = xfrm_mtu; if (likely(dst_ops->negative_advice == NULL)) dst_ops->negative_advice = xfrm_negative_advice; if (likely(dst_ops->link_failure == NULL)) diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index 9414b9c..5b228f9 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -1035,16 +1035,12 @@ static struct xfrm_state *__find_acq_core(struct net *net, struct xfrm_mark *m, break; case AF_INET6: - ipv6_addr_copy((struct in6_addr *)x->sel.daddr.a6, - (const struct in6_addr *)daddr); - ipv6_addr_copy((struct in6_addr *)x->sel.saddr.a6, - (const struct in6_addr *)saddr); + *(struct in6_addr *)x->sel.daddr.a6 = *(struct in6_addr *)daddr; + *(struct in6_addr *)x->sel.saddr.a6 = *(struct in6_addr *)saddr; x->sel.prefixlen_d = 128; x->sel.prefixlen_s = 128; - ipv6_addr_copy((struct in6_addr *)x->props.saddr.a6, - (const struct in6_addr *)saddr); - ipv6_addr_copy((struct in6_addr *)x->id.daddr.a6, - (const struct in6_addr *)daddr); + *(struct in6_addr *)x->props.saddr.a6 = *(struct in6_addr *)saddr; + *(struct in6_addr *)x->id.daddr.a6 = *(struct in6_addr *)daddr; break; } |
