diff options
Diffstat (limited to 'net/core')
-rw-r--r-- | net/core/Makefile | 3 | ||||
-rw-r--r-- | net/core/datagram.c | 2 | ||||
-rw-r--r-- | net/core/dev.c | 258 | ||||
-rw-r--r-- | net/core/drop_monitor.c | 263 | ||||
-rw-r--r-- | net/core/ethtool.c | 58 | ||||
-rw-r--r-- | net/core/fib_rules.c | 3 | ||||
-rw-r--r-- | net/core/neighbour.c | 15 | ||||
-rw-r--r-- | net/core/net-sysfs.c | 2 | ||||
-rw-r--r-- | net/core/net-traces.c | 29 | ||||
-rw-r--r-- | net/core/pktgen.c | 18 | ||||
-rw-r--r-- | net/core/rtnetlink.c | 9 | ||||
-rw-r--r-- | net/core/skbuff.c | 235 | ||||
-rw-r--r-- | net/core/sock.c | 95 | ||||
-rw-r--r-- | net/core/sysctl_net_core.c | 1 | ||||
-rw-r--r-- | net/core/utils.c | 1 |
15 files changed, 769 insertions, 223 deletions
diff --git a/net/core/Makefile b/net/core/Makefile index 26a37cb31923..796f46eece5f 100644 --- a/net/core/Makefile +++ b/net/core/Makefile @@ -17,3 +17,6 @@ obj-$(CONFIG_NET_PKTGEN) += pktgen.o obj-$(CONFIG_NETPOLL) += netpoll.o obj-$(CONFIG_NET_DMA) += user_dma.o obj-$(CONFIG_FIB_RULES) += fib_rules.o +obj-$(CONFIG_TRACEPOINTS) += net-traces.o +obj-$(CONFIG_NET_DROP_MONITOR) += drop_monitor.o + diff --git a/net/core/datagram.c b/net/core/datagram.c index 5e2ac0c4b07c..d0de644b378d 100644 --- a/net/core/datagram.c +++ b/net/core/datagram.c @@ -208,7 +208,7 @@ struct sk_buff *skb_recv_datagram(struct sock *sk, unsigned flags, void skb_free_datagram(struct sock *sk, struct sk_buff *skb) { - kfree_skb(skb); + consume_skb(skb); sk_mem_reclaim_partial(sk); } diff --git a/net/core/dev.c b/net/core/dev.c index e3fe5c705606..052dd478d3e1 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -1668,8 +1668,8 @@ int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev, struct netdev_queue *txq) { const struct net_device_ops *ops = dev->netdev_ops; + int rc; - prefetch(&dev->netdev_ops->ndo_start_xmit); if (likely(!skb->next)) { if (!list_empty(&ptype_all)) dev_queue_xmit_nit(skb, dev); @@ -1681,13 +1681,27 @@ int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev, goto gso; } - return ops->ndo_start_xmit(skb, dev); + rc = ops->ndo_start_xmit(skb, dev); + /* + * TODO: if skb_orphan() was called by + * dev->hard_start_xmit() (for example, the unmodified + * igb driver does that; bnx2 doesn't), then + * skb_tx_software_timestamp() will be unable to send + * back the time stamp. + * + * How can this be prevented? Always create another + * reference to the socket before calling + * dev->hard_start_xmit()? Prevent that skb_orphan() + * does anything in dev->hard_start_xmit() by clearing + * the skb destructor before the call and restoring it + * afterwards, then doing the skb_orphan() ourselves? + */ + return rc; } gso: do { struct sk_buff *nskb = skb->next; - int rc; skb->next = nskb->next; nskb->next = NULL; @@ -1708,59 +1722,24 @@ out_kfree_skb: return 0; } -static u32 simple_tx_hashrnd; -static int simple_tx_hashrnd_initialized = 0; +static u32 skb_tx_hashrnd; -static u16 simple_tx_hash(struct net_device *dev, struct sk_buff *skb) +u16 skb_tx_hash(const struct net_device *dev, const struct sk_buff *skb) { - u32 addr1, addr2, ports; - u32 hash, ihl; - u8 ip_proto = 0; - - if (unlikely(!simple_tx_hashrnd_initialized)) { - get_random_bytes(&simple_tx_hashrnd, 4); - simple_tx_hashrnd_initialized = 1; - } - - switch (skb->protocol) { - case htons(ETH_P_IP): - if (!(ip_hdr(skb)->frag_off & htons(IP_MF | IP_OFFSET))) - ip_proto = ip_hdr(skb)->protocol; - addr1 = ip_hdr(skb)->saddr; - addr2 = ip_hdr(skb)->daddr; - ihl = ip_hdr(skb)->ihl; - break; - case htons(ETH_P_IPV6): - ip_proto = ipv6_hdr(skb)->nexthdr; - addr1 = ipv6_hdr(skb)->saddr.s6_addr32[3]; - addr2 = ipv6_hdr(skb)->daddr.s6_addr32[3]; - ihl = (40 >> 2); - break; - default: - return 0; - } - + u32 hash; - switch (ip_proto) { - case IPPROTO_TCP: - case IPPROTO_UDP: - case IPPROTO_DCCP: - case IPPROTO_ESP: - case IPPROTO_AH: - case IPPROTO_SCTP: - case IPPROTO_UDPLITE: - ports = *((u32 *) (skb_network_header(skb) + (ihl * 4))); - break; - - default: - ports = 0; - break; - } + if (skb_rx_queue_recorded(skb)) { + hash = skb_get_rx_queue(skb); + } else if (skb->sk && skb->sk->sk_hash) { + hash = skb->sk->sk_hash; + } else + hash = skb->protocol; - hash = jhash_3words(addr1, addr2, ports, simple_tx_hashrnd); + hash = jhash_1word(hash, skb_tx_hashrnd); return (u16) (((u64) hash * dev->real_num_tx_queues) >> 32); } +EXPORT_SYMBOL(skb_tx_hash); static struct netdev_queue *dev_pick_tx(struct net_device *dev, struct sk_buff *skb) @@ -1771,7 +1750,7 @@ static struct netdev_queue *dev_pick_tx(struct net_device *dev, if (ops->ndo_select_queue) queue_index = ops->ndo_select_queue(dev, skb); else if (dev->real_num_tx_queues > 1) - queue_index = simple_tx_hash(dev, skb); + queue_index = skb_tx_hash(dev, skb); skb_set_queue_mapping(skb, queue_index); return netdev_get_tx_queue(dev, queue_index); @@ -2297,6 +2276,8 @@ ncls: if (!skb) goto out; + skb_orphan(skb); + type = skb->protocol; list_for_each_entry_rcu(ptype, &ptype_base[ntohs(type) & PTYPE_HASH_MASK], list) { @@ -2366,7 +2347,6 @@ static int napi_gro_complete(struct sk_buff *skb) out: skb_shinfo(skb)->gso_size = 0; - __skb_push(skb, -skb_network_offset(skb)); return netif_receive_skb(skb); } @@ -2380,20 +2360,40 @@ void napi_gro_flush(struct napi_struct *napi) napi_gro_complete(skb); } + napi->gro_count = 0; napi->gro_list = NULL; } EXPORT_SYMBOL(napi_gro_flush); +void *skb_gro_header(struct sk_buff *skb, unsigned int hlen) +{ + unsigned int offset = skb_gro_offset(skb); + + hlen += offset; + if (hlen <= skb_headlen(skb)) + return skb->data + offset; + + if (unlikely(!skb_shinfo(skb)->nr_frags || + skb_shinfo(skb)->frags[0].size <= + hlen - skb_headlen(skb) || + PageHighMem(skb_shinfo(skb)->frags[0].page))) + return pskb_may_pull(skb, hlen) ? skb->data + offset : NULL; + + return page_address(skb_shinfo(skb)->frags[0].page) + + skb_shinfo(skb)->frags[0].page_offset + + offset - skb_headlen(skb); +} +EXPORT_SYMBOL(skb_gro_header); + int dev_gro_receive(struct napi_struct *napi, struct sk_buff *skb) { struct sk_buff **pp = NULL; struct packet_type *ptype; __be16 type = skb->protocol; struct list_head *head = &ptype_base[ntohs(type) & PTYPE_HASH_MASK]; - int count = 0; int same_flow; int mac_len; - int free; + int ret; if (!(skb->dev->features & NETIF_F_GRO)) goto normal; @@ -2403,30 +2403,16 @@ int dev_gro_receive(struct napi_struct *napi, struct sk_buff *skb) rcu_read_lock(); list_for_each_entry_rcu(ptype, head, list) { - struct sk_buff *p; - if (ptype->type != type || ptype->dev || !ptype->gro_receive) continue; - skb_reset_network_header(skb); + skb_set_network_header(skb, skb_gro_offset(skb)); mac_len = skb->network_header - skb->mac_header; skb->mac_len = mac_len; NAPI_GRO_CB(skb)->same_flow = 0; NAPI_GRO_CB(skb)->flush = 0; NAPI_GRO_CB(skb)->free = 0; - for (p = napi->gro_list; p; p = p->next) { - count++; - - if (!NAPI_GRO_CB(p)->same_flow) - continue; - - if (p->mac_len != mac_len || - memcmp(skb_mac_header(p), skb_mac_header(skb), - mac_len)) - NAPI_GRO_CB(p)->same_flow = 0; - } - pp = ptype->gro_receive(&napi->gro_list, skb); break; } @@ -2436,7 +2422,7 @@ int dev_gro_receive(struct napi_struct *napi, struct sk_buff *skb) goto normal; same_flow = NAPI_GRO_CB(skb)->same_flow; - free = NAPI_GRO_CB(skb)->free; + ret = NAPI_GRO_CB(skb)->free ? GRO_MERGED_FREE : GRO_MERGED; if (pp) { struct sk_buff *nskb = *pp; @@ -2444,27 +2430,35 @@ int dev_gro_receive(struct napi_struct *napi, struct sk_buff *skb) *pp = nskb->next; nskb->next = NULL; napi_gro_complete(nskb); - count--; + napi->gro_count--; } if (same_flow) goto ok; - if (NAPI_GRO_CB(skb)->flush || count >= MAX_GRO_SKBS) { - __skb_push(skb, -skb_network_offset(skb)); + if (NAPI_GRO_CB(skb)->flush || napi->gro_count >= MAX_GRO_SKBS) goto normal; - } + napi->gro_count++; NAPI_GRO_CB(skb)->count = 1; - skb_shinfo(skb)->gso_size = skb->len; + skb_shinfo(skb)->gso_size = skb_gro_len(skb); skb->next = napi->gro_list; napi->gro_list = skb; + ret = GRO_HELD; + +pull: + if (unlikely(!pskb_may_pull(skb, skb_gro_offset(skb)))) { + if (napi->gro_list == skb) + napi->gro_list = skb->next; + ret = GRO_DROP; + } ok: - return free; + return ret; normal: - return -1; + ret = GRO_NORMAL; + goto pull; } EXPORT_SYMBOL(dev_gro_receive); @@ -2472,29 +2466,44 @@ static int __napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb) { struct sk_buff *p; + if (netpoll_rx_on(skb)) + return GRO_NORMAL; + for (p = napi->gro_list; p; p = p->next) { - NAPI_GRO_CB(p)->same_flow = 1; + NAPI_GRO_CB(p)->same_flow = !compare_ether_header( + skb_mac_header(p), skb_gro_mac_header(skb)); NAPI_GRO_CB(p)->flush = 0; } return dev_gro_receive(napi, skb); } -int napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb) +int napi_skb_finish(int ret, struct sk_buff *skb) { - if (netpoll_receive_skb(skb)) - return NET_RX_DROP; + int err = NET_RX_SUCCESS; - switch (__napi_gro_receive(napi, skb)) { - case -1: + switch (ret) { + case GRO_NORMAL: return netif_receive_skb(skb); - case 1: + case GRO_DROP: + err = NET_RX_DROP; + /* fall through */ + + case GRO_MERGED_FREE: kfree_skb(skb); break; } - return NET_RX_SUCCESS; + return err; +} +EXPORT_SYMBOL(napi_skb_finish); + +int napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb) +{ + skb_gro_reset_offset(skb); + + return napi_skb_finish(__napi_gro_receive(napi, skb), skb); } EXPORT_SYMBOL(napi_gro_receive); @@ -2512,6 +2521,9 @@ struct sk_buff *napi_fraginfo_skb(struct napi_struct *napi, { struct net_device *dev = napi->dev; struct sk_buff *skb = napi->skb; + struct ethhdr *eth; + skb_frag_t *frag; + int i; napi->skb = NULL; @@ -2524,20 +2536,36 @@ struct sk_buff *napi_fraginfo_skb(struct napi_struct *napi, } BUG_ON(info->nr_frags > MAX_SKB_FRAGS); + frag = &info->frags[info->nr_frags - 1]; + + for (i = skb_shinfo(skb)->nr_frags; i < info->nr_frags; i++) { + skb_fill_page_desc(skb, i, frag->page, frag->page_offset, + frag->size); + frag++; + } skb_shinfo(skb)->nr_frags = info->nr_frags; - memcpy(skb_shinfo(skb)->frags, info->frags, sizeof(info->frags)); skb->data_len = info->len; skb->len += info->len; skb->truesize += info->len; - if (!pskb_may_pull(skb, ETH_HLEN)) { + skb_reset_mac_header(skb); + skb_gro_reset_offset(skb); + + eth = skb_gro_header(skb, sizeof(*eth)); + if (!eth) { napi_reuse_skb(napi, skb); skb = NULL; goto out; } - skb->protocol = eth_type_trans(skb, dev); + skb_gro_pull(skb, sizeof(*eth)); + + /* + * This works because the only protocols we care about don't require + * special handling. We'll fix it up properly at the end. + */ + skb->protocol = eth->h_proto; skb->ip_summed = info->ip_summed; skb->csum = info->csum; @@ -2547,32 +2575,43 @@ out: } EXPORT_SYMBOL(napi_fraginfo_skb); -int napi_gro_frags(struct napi_struct *napi, struct napi_gro_fraginfo *info) +int napi_frags_finish(struct napi_struct *napi, struct sk_buff *skb, int ret) { - struct sk_buff *skb = napi_fraginfo_skb(napi, info); - int err = NET_RX_DROP; + int err = NET_RX_SUCCESS; - if (!skb) - goto out; + switch (ret) { + case GRO_NORMAL: + case GRO_HELD: + skb->protocol = eth_type_trans(skb, napi->dev); - if (netpoll_receive_skb(skb)) - goto out; + if (ret == GRO_NORMAL) + return netif_receive_skb(skb); - err = NET_RX_SUCCESS; + skb_gro_pull(skb, -ETH_HLEN); + break; - switch (__napi_gro_receive(napi, skb)) { - case -1: - return netif_receive_skb(skb); + case GRO_DROP: + err = NET_RX_DROP; + /* fall through */ - case 0: - goto out; + case GRO_MERGED_FREE: + napi_reuse_skb(napi, skb); + break; } - napi_reuse_skb(napi, skb); - -out: return err; } +EXPORT_SYMBOL(napi_frags_finish); + +int napi_gro_frags(struct napi_struct *napi, struct napi_gro_fraginfo *info) +{ + struct sk_buff *skb = napi_fraginfo_skb(napi, info); + + if (!skb) + return NET_RX_DROP; + + return napi_frags_finish(napi, skb, __napi_gro_receive(napi, skb)); +} EXPORT_SYMBOL(napi_gro_frags); static int process_backlog(struct napi_struct *napi, int quota) @@ -2653,6 +2692,7 @@ void netif_napi_add(struct net_device *dev, struct napi_struct *napi, int (*poll)(struct napi_struct *, int), int weight) { INIT_LIST_HEAD(&napi->poll_list); + napi->gro_count = 0; napi->gro_list = NULL; napi->skb = NULL; napi->poll = poll; @@ -2681,6 +2721,7 @@ void netif_napi_del(struct napi_struct *napi) } napi->gro_list = NULL; + napi->gro_count = 0; } EXPORT_SYMBOL(netif_napi_del); @@ -3949,6 +3990,7 @@ static int dev_ifsioc(struct net *net, struct ifreq *ifr, unsigned int cmd) cmd == SIOCSMIIREG || cmd == SIOCBRADDIF || cmd == SIOCBRDELIF || + cmd == SIOCSHWTSTAMP || cmd == SIOCWANDEV) { err = -EOPNOTSUPP; if (ops->ndo_do_ioctl) { @@ -4103,6 +4145,7 @@ int dev_ioctl(struct net *net, unsigned int cmd, void __user *arg) case SIOCBONDCHANGEACTIVE: case SIOCBRADDIF: case SIOCBRDELIF: + case SIOCSHWTSTAMP: if (!capable(CAP_NET_ADMIN)) return -EPERM; /* fall through */ @@ -5199,6 +5242,7 @@ static int __init net_dev_init(void) queue->backlog.poll = process_backlog; queue->backlog.weight = weight_p; queue->backlog.gro_list = NULL; + queue->backlog.gro_count = 0; } dev_boot_phase = 0; @@ -5231,6 +5275,14 @@ out: subsys_initcall(net_dev_init); +static int __init initialize_hashrnd(void) +{ + get_random_bytes(&skb_tx_hashrnd, sizeof(skb_tx_hashrnd)); + return 0; +} + +late_initcall_sync(initialize_hashrnd); + EXPORT_SYMBOL(__dev_get_by_index); EXPORT_SYMBOL(__dev_get_by_name); EXPORT_SYMBOL(__dev_remove_pack); diff --git a/net/core/drop_monitor.c b/net/core/drop_monitor.c new file mode 100644 index 000000000000..9fd0dc3cca99 --- /dev/null +++ b/net/core/drop_monitor.c @@ -0,0 +1,263 @@ +/* + * Monitoring code for network dropped packet alerts + * + * Copyright (C) 2009 Neil Horman <nhorman@tuxdriver.com> + */ + +#include <linux/netdevice.h> +#include <linux/etherdevice.h> +#include <linux/string.h> +#include <linux/if_arp.h> +#include <linux/inetdevice.h> +#include <linux/inet.h> +#include <linux/interrupt.h> +#include <linux/netpoll.h> +#include <linux/sched.h> +#include <linux/delay.h> +#include <linux/types.h> +#include <linux/workqueue.h> +#include <linux/netlink.h> +#include <linux/net_dropmon.h> +#include <linux/percpu.h> +#include <linux/timer.h> +#include <linux/bitops.h> +#include <net/genetlink.h> + +#include <trace/skb.h> + +#include <asm/unaligned.h> + +#define TRACE_ON 1 +#define TRACE_OFF 0 + +static void send_dm_alert(struct work_struct *unused); + + +/* + * Globals, our netlink socket pointer + * and the work handle that will send up + * netlink alerts + */ +struct sock *dm_sock; + +struct per_cpu_dm_data { + struct work_struct dm_alert_work; + struct sk_buff *skb; + atomic_t dm_hit_count; + struct timer_list send_timer; +}; + +static struct genl_family net_drop_monitor_family = { + .id = GENL_ID_GENERATE, + .hdrsize = 0, + .name = "NET_DM", + .version = 1, + .maxattr = NET_DM_CMD_MAX, +}; + +static DEFINE_PER_CPU(struct per_cpu_dm_data, dm_cpu_data); + +static int dm_hit_limit = 64; +static int dm_delay = 1; + + +static void reset_per_cpu_data(struct per_cpu_dm_data *data) +{ + size_t al; + struct net_dm_alert_msg *msg; + + al = sizeof(struct net_dm_alert_msg); + al += dm_hit_limit * sizeof(struct net_dm_drop_point); + data->skb = genlmsg_new(al, GFP_KERNEL); + genlmsg_put(data->skb, 0, 0, &net_drop_monitor_family, + 0, NET_DM_CMD_ALERT); + msg = __nla_reserve_nohdr(data->skb, sizeof(struct net_dm_alert_msg)); + memset(msg, 0, al); + atomic_set(&data->dm_hit_count, dm_hit_limit); +} + +static void send_dm_alert(struct work_struct *unused) +{ + struct sk_buff *skb; + struct per_cpu_dm_data *data = &__get_cpu_var(dm_cpu_data); + + /* + * Grab the skb we're about to send + */ + skb = data->skb; + + /* + * Replace it with a new one + */ + reset_per_cpu_data(data); + + /* + * Ship it! + */ + genlmsg_multicast(skb, 0, NET_DM_GRP_ALERT, GFP_KERNEL); + +} + +/* + * This is the timer function to delay the sending of an alert + * in the event that more drops will arrive during the + * hysteresis period. Note that it operates under the timer interrupt + * so we don't need to disable preemption here + */ +static void sched_send_work(unsigned long unused) +{ + struct per_cpu_dm_data *data = &__get_cpu_var(dm_cpu_data); + + schedule_work(&data->dm_alert_work); +} + +static void trace_kfree_skb_hit(struct sk_buff *skb, void *location) +{ + struct net_dm_alert_msg *msg; + struct nlmsghdr *nlh; + int i; + struct per_cpu_dm_data *data = &__get_cpu_var(dm_cpu_data); + + + if (!atomic_add_unless(&data->dm_hit_count, -1, 0)) { + /* + * we're already at zero, discard this hit + */ + goto out; + } + + nlh = (struct nlmsghdr *)data->skb->data; + msg = genlmsg_data(nlmsg_data(nlh)); + for (i = 0; i < msg->entries; i++) { + if (!memcmp(&location, msg->points[i].pc, sizeof(void *))) { + msg->points[i].count++; + goto out; + } + } + + /* + * We need to create a new entry + */ + __nla_reserve_nohdr(data->skb, sizeof(struct net_dm_drop_point)); + memcpy(msg->points[msg->entries].pc, &location, sizeof(void *)); + msg->points[msg->entries].count = 1; + msg->entries++; + + if (!timer_pending(&data->send_timer)) { + data->send_timer.expires = jiffies + dm_delay * HZ; + add_timer_on(&data->send_timer, smp_processor_id()); + } + +out: + return; +} + +static int set_all_monitor_traces(int state) +{ + int rc = 0; + + switch (state) { + case TRACE_ON: + rc |= register_trace_kfree_skb(trace_kfree_skb_hit); + break; + case TRACE_OFF: + rc |= unregister_trace_kfree_skb(trace_kfree_skb_hit); + + tracepoint_synchronize_unregister(); + break; + default: + rc = 1; + break; + } + + if (rc) + return -EINPROGRESS; + return rc; +} + + +static int net_dm_cmd_config(struct sk_buff *skb, + struct genl_info *info) +{ + return -ENOTSUPP; +} + +static int net_dm_cmd_trace(struct sk_buff *skb, + struct genl_info *info) +{ + switch (info->genlhdr->cmd) { + case NET_DM_CMD_START: + return set_all_monitor_traces(TRACE_ON); + break; + case NET_DM_CMD_STOP: + return set_all_monitor_traces(TRACE_OFF); + break; + } + + return -ENOTSUPP; +} + + +static struct genl_ops dropmon_ops[] = { + { + .cmd = NET_DM_CMD_CONFIG, + .doit = net_dm_cmd_config, + }, + { + .cmd = NET_DM_CMD_START, + .doit = net_dm_cmd_trace, + }, + { + .cmd = NET_DM_CMD_STOP, + .doit = net_dm_cmd_trace, + }, +}; + +static int __init init_net_drop_monitor(void) +{ + int cpu; + int rc, i, ret; + struct per_cpu_dm_data *data; + printk(KERN_INFO "Initalizing network drop monitor service\n"); + + if (sizeof(void *) > 8) { + printk(KERN_ERR "Unable to store program counters on this arch, Drop monitor failed\n"); + return -ENOSPC; + } + + if (genl_register_family(&net_drop_monitor_family) < 0) { + printk(KERN_ERR "Could not create drop monitor netlink family\n"); + return -EFAULT; + } + + rc = -EFAULT; + + for (i = 0; i < ARRAY_SIZE(dropmon_ops); i++) { + ret = genl_register_ops(&net_drop_monitor_family, + &dropmon_ops[i]); + if (ret) { + printk(KERN_CRIT "failed to register operation %d\n", + dropmon_ops[i].cmd); + goto out_unreg; + } + } + + rc = 0; + + for_each_present_cpu(cpu) { + data = &per_cpu(dm_cpu_data, cpu); + reset_per_cpu_data(data); + INIT_WORK(&data->dm_alert_work, send_dm_alert); + init_timer(&data->send_timer); + data->send_timer.data = cpu; + data->send_timer.function = sched_send_work; + } + goto out; + +out_unreg: + genl_unregister_family(&net_drop_monitor_family); +out: + return rc; +} + +late_initcall(init_net_drop_monitor); diff --git a/net/core/ethtool.c b/net/core/ethtool.c index 947710a36ced..244ca56dffac 100644 --- a/net/core/ethtool.c +++ b/net/core/ethtool.c @@ -209,34 +209,62 @@ static int ethtool_get_drvinfo(struct net_device *dev, void __user *useraddr) return 0; } -static int ethtool_set_rxhash(struct net_device *dev, void __user *useraddr) +static int ethtool_set_rxnfc(struct net_device *dev, void __user *useraddr) { struct ethtool_rxnfc cmd; - if (!dev->ethtool_ops->set_rxhash) + if (!dev->ethtool_ops->set_rxnfc) return -EOPNOTSUPP; if (copy_from_user(&cmd, useraddr, sizeof(cmd))) return -EFAULT; - return dev->ethtool_ops->set_rxhash(dev, &cmd); + return dev->ethtool_ops->set_rxnfc(dev, &cmd); } -static int ethtool_get_rxhash(struct net_device *dev, void __user *useraddr) +static int ethtool_get_rxnfc(struct net_device *dev, void __user *useraddr) { struct ethtool_rxnfc info; + const struct ethtool_ops *ops = dev->ethtool_ops; + int ret; + void *rule_buf = NULL; - if (!dev->ethtool_ops->get_rxhash) + if (!ops->get_rxnfc) return -EOPNOTSUPP; if (copy_from_user(&info, useraddr, sizeof(info))) return -EFAULT; - dev->ethtool_ops->get_rxhash(dev, &info); + if (info.cmd == ETHTOOL_GRXCLSRLALL) { + if (info.rule_cnt > 0) { + rule_buf = kmalloc(info.rule_cnt * sizeof(u32), + GFP_USER); + if (!rule_buf) + return -ENOMEM; + } + } + ret = ops->get_rxnfc(dev, &info, rule_buf); + if (ret < 0) + goto err_out; + + ret = -EFAULT; if (copy_to_user(useraddr, &info, sizeof(info))) - return -EFAULT; - return 0; + goto err_out; + + if (rule_buf) { + useraddr += offsetof(struct ethtool_rxnfc, rule_locs); + if (copy_to_user(useraddr, rule_buf, + info.rule_cnt * sizeof(u32))) + goto err_out; + } + ret = 0; + +err_out: + if (rule_buf) + kfree(rule_buf); + + return ret; } static int ethtool_get_regs(struct net_device *dev, char __user *useraddr) @@ -901,6 +929,10 @@ int dev_ethtool(struct net *net, struct ifreq *ifr) case ETHTOOL_GFLAGS: case ETHTOOL_GPFLAGS: case ETHTOOL_GRXFH: + case ETHTOOL_GRXRINGS: + case ETHTOOL_GRXCLSRLCNT: + case ETHTOOL_GRXCLSRULE: + case ETHTOOL_GRXCLSRLALL: break; default: if (!capable(CAP_NET_ADMIN)) @@ -1052,10 +1084,16 @@ int dev_ethtool(struct net *net, struct ifreq *ifr) dev->ethtool_ops->set_priv_flags); break; case ETHTOOL_GRXFH: - rc = ethtool_get_rxhash(dev, useraddr); + case ETHTOOL_GRXRINGS: + case ETHTOOL_GRXCLSRLCNT: + case ETHTOOL_GRXCLSRULE: + case ETHTOOL_GRXCLSRLALL: + rc = ethtool_get_rxnfc(dev, useraddr); break; case ETHTOOL_SRXFH: - rc = ethtool_set_rxhash(dev, useraddr); + case ETHTOOL_SRXCLSRLDEL: + case ETHTOOL_SRXCLSRLINS: + rc = ethtool_set_rxnfc(dev, useraddr); break; case ETHTOOL_GGRO: rc = ethtool_get_gro(dev, useraddr); diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c index 32b3a0152d7a..98691e1466b8 100644 --- a/net/core/fib_rules.c +++ b/net/core/fib_rules.c @@ -588,7 +588,8 @@ static void notify_rule_change(int event, struct fib_rule *rule, goto errout; } - err = rtnl_notify(skb, net, pid, ops->nlgroup, nlh, GFP_KERNEL); + rtnl_notify(skb, net, pid, ops->nlgroup, nlh, GFP_KERNEL); + return; errout: if (err < 0) rtnl_set_sk_err(net, ops->nlgroup, err); diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 278a142d1047..a1cbce7fdae5 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -871,8 +871,7 @@ static void neigh_timer_handler(unsigned long arg) write_unlock(&neigh->lock); neigh->ops->solicit(neigh, skb); atomic_inc(&neigh->probes); - if (skb) - kfree_skb(skb); + kfree_skb(skb); } else { out: write_unlock(&neigh->lock); @@ -908,8 +907,7 @@ int __neigh_event_send(struct neighbour *neigh, struct sk_buff *skb) neigh->updated = jiffies; write_unlock_bh(&neigh->lock); - if (skb) - kfree_skb(skb); + kfree_skb(skb); return 1; } } else if (neigh->nud_state & NUD_STALE) { @@ -1656,7 +1654,11 @@ static int neigh_add(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) flags &= ~NEIGH_UPDATE_F_OVERRIDE; } - err = neigh_update(neigh, lladdr, ndm->ndm_state, flags); + if (ndm->ndm_flags & NTF_USE) { + neigh_event_send(neigh, NULL); + err = 0; + } else + err = neigh_update(neigh, lladdr, ndm->ndm_state, flags); neigh_release(neigh); goto out_dev_put; } @@ -2534,7 +2536,8 @@ static void __neigh_notify(struct neighbour *n, int type, int flags) kfree_skb(skb); goto errout; } - err = rtnl_notify(skb, net, 0, RTNLGRP_NEIGH, NULL, GFP_ATOMIC); + rtnl_notify(skb, net, 0, RTNLGRP_NEIGH, NULL, GFP_ATOMIC); + return; errout: if (err < 0) rtnl_set_sk_err(net, RTNLGRP_NEIGH, err); diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index 484f58750eba..2da59a0ac4ac 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -498,7 +498,7 @@ int netdev_register_kobject(struct net_device *net) dev->groups = groups; BUILD_BUG_ON(BUS_ID_SIZE < IFNAMSIZ); - dev_set_name(dev, net->name); + dev_set_name(dev, "%s", net->name); #ifdef CONFIG_SYSFS *groups++ = &netstat_group; diff --git a/net/core/net-traces.c b/net/core/net-traces.c new file mode 100644 index 000000000000..c8fb45665e4f --- /dev/null +++ b/net/core/net-traces.c @@ -0,0 +1,29 @@ +/* + * consolidates trace point definitions + * + * Copyright (C) 2009 Neil Horman <nhorman@tuxdriver.com> + */ + +#include <linux/netdevice.h> +#include <linux/etherdevice.h> +#include <linux/string.h> +#include <linux/if_arp.h> +#include <linux/inetdevice.h> +#include <linux/inet.h> +#include <linux/interrupt.h> +#include <linux/netpoll.h> +#include <linux/sched.h> +#include <linux/delay.h> +#include <linux/rcupdate.h> +#include <linux/types.h> +#include <linux/workqueue.h> +#include <linux/netlink.h> +#include <linux/net_dropmon.h> +#include <trace/skb.h> + +#include <asm/unaligned.h> +#include <asm/bitops.h> + + +DEFINE_TRACE(kfree_skb); +EXPORT_TRACEPOINT_SYMBOL_GPL(kfree_skb); diff --git a/net/core/pktgen.c b/net/core/pktgen.c index 65498483325a..32d419f5ac98 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -3275,8 +3275,7 @@ static void pktgen_stop(struct pktgen_thread *t) list_for_each_entry(pkt_dev, &t->if_list, list) { pktgen_stop_device(pkt_dev); - if (pkt_dev->skb) - kfree_skb(pkt_dev->skb); + kfree_skb(pkt_dev->skb); pkt_dev->skb = NULL; } @@ -3303,8 +3302,7 @@ static void pktgen_rem_one_if(struct pktgen_thread *t) if (!cur->removal_mark) continue; - if (cur->skb) - kfree_skb(cur->skb); + kfree_skb(cur->skb); cur->skb = NULL; pktgen_remove_device(t, cur); @@ -3328,8 +3326,7 @@ static void pktgen_rem_all_ifs(struct pktgen_thread *t) list_for_each_safe(q, n, &t->if_list) { cur = list_entry(q, struct pktgen_dev, list); - if (cur->skb) - kfree_skb(cur->skb); + kfree_skb(cur->skb); cur->skb = NULL; pktgen_remove_device(t, cur); @@ -3393,8 +3390,7 @@ static __inline__ void pktgen_xmit(struct pktgen_dev *pkt_dev) if (!netif_running(odev)) { pktgen_stop_device(pkt_dev); - if (pkt_dev->skb) - kfree_skb(pkt_dev->skb); + kfree_skb(pkt_dev->skb); pkt_dev->skb = NULL; goto out; } @@ -3415,8 +3411,7 @@ static __inline__ void pktgen_xmit(struct pktgen_dev *pkt_dev) if ((++pkt_dev->clone_count >= pkt_dev->clone_skb) || (!pkt_dev->skb)) { /* build a new pkt */ - if (pkt_dev->skb) - kfree_skb(pkt_dev->skb); + kfree_skb(pkt_dev->skb); pkt_dev->skb = fill_packet(odev, pkt_dev); if (pkt_dev->skb == NULL) { @@ -3498,8 +3493,7 @@ static __inline__ void pktgen_xmit(struct pktgen_dev *pkt_dev) /* Done with this */ pktgen_stop_device(pkt_dev); - if (pkt_dev->skb) - kfree_skb(pkt_dev->skb); + kfree_skb(pkt_dev->skb); pkt_dev->skb = NULL; } out:; diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 790dd205bb5d..d78030f88bd0 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -455,8 +455,8 @@ int rtnl_unicast(struct sk_buff *skb, struct net *net, u32 pid) return nlmsg_unicast(rtnl, skb, pid); } -int rtnl_notify(struct sk_buff *skb, struct net *net, u32 pid, u32 group, - struct nlmsghdr *nlh, gfp_t flags) +void rtnl_notify(struct sk_buff *skb, struct net *net, u32 pid, u32 group, + struct nlmsghdr *nlh, gfp_t flags) { struct sock *rtnl = net->rtnl; int report = 0; @@ -464,7 +464,7 @@ int rtnl_notify(struct sk_buff *skb, struct net *net, u32 pid, u32 group, if (nlh) report = nlmsg_report(nlh); - return nlmsg_notify(rtnl, skb, pid, group, report, flags); + nlmsg_notify(rtnl, skb, pid, group, report, flags); } void rtnl_set_sk_err(struct net *net, u32 group, int error) @@ -1246,7 +1246,8 @@ void rtmsg_ifinfo(int type, struct net_device *dev, unsigned change) kfree_skb(skb); goto errout; } - err = rtnl_notify(skb, net, 0, RTNLGRP_LINK, NULL, GFP_KERNEL); + rtnl_notify(skb, net, 0, RTNLGRP_LINK, NULL, GFP_KERNEL); + return; errout: if (err < 0) rtnl_set_sk_err(net, RTNLGRP_LINK, err); diff --git a/net/core/skbuff.c b/net/core/skbuff.c index c6a6b166f8d6..6acbf9e79eb1 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -55,6 +55,7 @@ #include <linux/rtnetlink.h> #include <linux/init.h> #include <linux/scatterlist.h> +#include <linux/errqueue.h> #include <net/protocol.h> #include <net/dst.h> @@ -64,6 +65,7 @@ #include <asm/uaccess.h> #include <asm/system.h> +#include <trace/skb.h> #include "kmap_skb.h" @@ -123,6 +125,7 @@ void skb_over_panic(struct sk_buff *skb, int sz, void *here) skb->dev ? skb->dev->name : "<NULL>"); BUG(); } +EXPORT_SYMBOL(skb_over_panic); /** * skb_under_panic - private function @@ -142,6 +145,7 @@ void skb_under_panic(struct sk_buff *skb, int sz, void *here) skb->dev ? skb->dev->name : "<NULL>"); BUG(); } +EXPORT_SYMBOL(skb_under_panic); /* Allocate a new skbuff. We do this ourselves so we can fill in a few * 'private' fields and also do memory statistics to find all the @@ -205,7 +209,9 @@ struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask, shinfo->gso_segs = 0; shinfo->gso_type = 0; shinfo->ip6_frag_id = 0; + shinfo->tx_flags.flags = 0; shinfo->frag_list = NULL; + memset(&shinfo->hwtstamps, 0, sizeof(shinfo->hwtstamps)); if (fclone) { struct sk_buff *child = skb + 1; @@ -223,6 +229,7 @@ nodata: skb = NULL; goto out; } +EXPORT_SYMBOL(__alloc_skb); /** * __netdev_alloc_skb - allocate an skbuff for rx on a specific device @@ -250,6 +257,7 @@ struct sk_buff *__netdev_alloc_skb(struct net_device *dev, } return skb; } +EXPORT_SYMBOL(__netdev_alloc_skb); struct page *__netdev_alloc_page(struct net_device *dev, gfp_t gfp_mask) { @@ -418,6 +426,7 @@ void __kfree_skb(struct sk_buff *skb) skb_release_all(skb); kfree_skbmem(skb); } +EXPORT_SYMBOL(__kfree_skb); /** * kfree_skb - free an sk_buff @@ -434,8 +443,30 @@ void kfree_skb(struct sk_buff *skb) smp_rmb(); else if (likely(!atomic_dec_and_test(&skb->users))) return; + trace_kfree_skb(skb, __builtin_return_address(0)); + __kfree_skb(skb); +} +EXPORT_SYMBOL(kfree_skb); + +/** + * consume_skb - free an skbuff + * @skb: buffer to free + * + * Drop a ref to the buffer and free it if the usage count has hit zero + * Functions identically to kfree_skb, but kfree_skb assumes that the frame + * is being dropped after a failure and notes that + */ +void consume_skb(struct sk_buff *skb) +{ + if (unlikely(!skb)) + return; + if (likely(atomic_read(&skb->users) == 1)) + smp_rmb(); + else if (likely(!atomic_dec_and_test(&skb->users))) + return; __kfree_skb(skb); } +EXPORT_SYMBOL(consume_skb); /** * skb_recycle_check - check if skb can be reused for receive @@ -605,6 +636,7 @@ struct sk_buff *skb_clone(struct sk_buff *skb, gfp_t gfp_mask) return __skb_clone(n, skb); } +EXPORT_SYMBOL(skb_clone); static void copy_skb_header(struct sk_buff *new, const struct sk_buff *old) { @@ -671,7 +703,7 @@ struct sk_buff *skb_copy(const struct sk_buff *skb, gfp_t gfp_mask) copy_skb_header(n, skb); return n; } - +EXPORT_SYMBOL(skb_copy); /** * pskb_copy - create copy of an sk_buff with private head. @@ -730,6 +762,7 @@ struct sk_buff *pskb_copy(struct sk_buff *skb, gfp_t gfp_mask) out: return n; } +EXPORT_SYMBOL(pskb_copy); /** * pskb_expand_head - reallocate header of &sk_buff @@ -813,6 +846,7 @@ int pskb_expand_head(struct sk_buff *skb, int nhead, int ntail, nodata: return -ENOMEM; } +EXPORT_SYMBOL(pskb_expand_head); /* Make private copy of skb with writable head and some headroom */ @@ -833,7 +867,7 @@ struct sk_buff *skb_realloc_headroom(struct sk_buff *skb, unsigned int headroom) } return skb2; } - +EXPORT_SYMBOL(skb_realloc_headroom); /** * skb_copy_expand - copy and expand sk_buff @@ -898,6 +932,7 @@ struct sk_buff *skb_copy_expand(const struct sk_buff *skb, return n; } +EXPORT_SYMBOL(skb_copy_expand); /** * skb_pad - zero pad the tail of an skb @@ -943,6 +978,7 @@ free_skb: kfree_skb(skb); return err; } +EXPORT_SYMBOL(skb_pad); /** * skb_put - add data to a buffer @@ -1100,6 +1136,7 @@ done: return 0; } +EXPORT_SYMBOL(___pskb_trim); /** * __pskb_pull_tail - advance tail of skb header @@ -1193,8 +1230,7 @@ unsigned char *__pskb_pull_tail(struct sk_buff *skb, int delta) insp = list; } if (!pskb_pull(list, eat)) { - if (clone) - kfree_skb(clone); + kfree_skb(clone); return NULL; } break; @@ -1238,6 +1274,7 @@ pull_pages: return skb_tail_pointer(skb); } +EXPORT_SYMBOL(__pskb_pull_tail); /* Copy some data bits from skb to kernel buffer. */ @@ -1315,6 +1352,7 @@ int skb_copy_bits(const struct sk_buff *skb, int offset, void *to, int len) fault: return -EFAULT; } +EXPORT_SYMBOL(skb_copy_bits); /* * Callback from splice_to_pipe(), if we need to release some pages @@ -1325,14 +1363,39 @@ static void sock_spd_release(struct splice_pipe_desc *spd, unsigned int i) put_page(spd->pages[i]); } -static inline struct page *linear_to_page(struct page *page, unsigned int len, - unsigned int offset) +static inline struct page *linear_to_page(struct page *page, unsigned int *len, + unsigned int *offset, + struct sk_buff *skb) { - struct page *p = alloc_pages(GFP_KERNEL, 0); + struct sock *sk = skb->sk; + struct page *p = sk->sk_sndmsg_page; + unsigned int off; - if (!p) - return NULL; - memcpy(page_address(p) + offset, page_address(page) + offset, len); + if (!p) { +new_page: + p = sk->sk_sndmsg_page = alloc_pages(sk->sk_allocation, 0); + if (!p) + return NULL; + + off = sk->sk_sndmsg_off = 0; + /* hold one ref to this page until it's full */ + } else { + unsigned int mlen; + + off = sk->sk_sndmsg_off; + mlen = PAGE_SIZE - off; + if (mlen < 64 && mlen < *len) { + put_page(p); + goto new_page; + } + + *len = min_t(unsigned int, *len, mlen); + } + + memcpy(page_address(p) + off, page_address(page) + *offset, *len); + sk->sk_sndmsg_off += *len; + *offset = off; + get_page(p); return p; } @@ -1341,21 +1404,21 @@ static inline struct page *linear_to_page(struct page *page, unsigned int len, * Fill page/offset/length into spd, if it can hold more pages. */ static inline int spd_fill_page(struct splice_pipe_desc *spd, struct page *page, - unsigned int len, unsigned int offset, + unsigned int *len, unsigned int offset, struct sk_buff *skb, int linear) { if (unlikely(spd->nr_pages == PIPE_BUFFERS)) return 1; if (linear) { - page = linear_to_page(page, len, offset); + page = linear_to_page(page, len, &offset, skb); if (!page) return 1; } else get_page(page); spd->pages[spd->nr_pages] = page; - spd->partial[spd->nr_pages].len = len; + spd->partial[spd->nr_pages].len = *len; spd->partial[spd->nr_pages].offset = offset; spd->nr_pages++; @@ -1365,8 +1428,13 @@ static inline int spd_fill_page(struct splice_pipe_desc *spd, struct page *page, static inline void __segment_seek(struct page **page, unsigned int *poff, unsigned int *plen, unsigned int off) { + unsigned long n; + *poff += off; - *page += *poff / PAGE_SIZE; + n = *poff / PAGE_SIZE; + if (n) + *page = nth_page(*page, n); + *poff = *poff % PAGE_SIZE; *plen -= off; } @@ -1397,7 +1465,7 @@ static inline int __splice_segment(struct page *page, unsigned int poff, /* the linear region may spread across several pages */ flen = min_t(unsigned int, flen, PAGE_SIZE - poff); - if (spd_fill_page(spd, page, flen, poff, skb, linear)) + if (spd_fill_page(spd, page, &flen, poff, skb, linear)) return 1; __segment_seek(&page, &poff, &plen, flen); @@ -1590,7 +1658,6 @@ int skb_store_bits(struct sk_buff *skb, int offset, const void *from, int len) fault: return -EFAULT; } - EXPORT_SYMBOL(skb_store_bits); /* Checksum skb data. */ @@ -1667,6 +1734,7 @@ __wsum skb_checksum(const struct sk_buff *skb, int offset, return csum; } +EXPORT_SYMBOL(skb_checksum); /* Both of above in one bottle. */ @@ -1748,6 +1816,7 @@ __wsum skb_copy_and_csum_bits(const struct sk_buff *skb, int offset, BUG_ON(len); return csum; } +EXPORT_SYMBOL(skb_copy_and_csum_bits); void skb_copy_and_csum_dev(const struct sk_buff *skb, u8 *to) { @@ -1774,6 +1843,7 @@ void skb_copy_and_csum_dev(const struct sk_buff *skb, u8 *to) *((__sum16 *)(to + csstuff)) = csum_fold(csum); } } +EXPORT_SYMBOL(skb_copy_and_csum_dev); /** * skb_dequeue - remove from the head of the queue @@ -1794,6 +1864,7 @@ struct sk_buff *skb_dequeue(struct sk_buff_head *list) spin_unlock_irqrestore(&list->lock, flags); return result; } +EXPORT_SYMBOL(skb_dequeue); /** * skb_dequeue_tail - remove from the tail of the queue @@ -1813,6 +1884,7 @@ struct sk_buff *skb_dequeue_tail(struct sk_buff_head *list) spin_unlock_irqrestore(&list->lock, flags); return result; } +EXPORT_SYMBOL(skb_dequeue_tail); /** * skb_queue_purge - empty a list @@ -1828,6 +1900,7 @@ void skb_queue_purge(struct sk_buff_head *list) while ((skb = skb_dequeue(list)) != NULL) kfree_skb(skb); } +EXPORT_SYMBOL(skb_queue_purge); /** * skb_queue_head - queue a buffer at the list head @@ -1848,6 +1921,7 @@ void skb_queue_head(struct sk_buff_head *list, struct sk_buff *newsk) __skb_queue_head(list, newsk); spin_unlock_irqrestore(&list->lock, flags); } +EXPORT_SYMBOL(skb_queue_head); /** * skb_queue_tail - queue a buffer at the list tail @@ -1868,6 +1942,7 @@ void skb_queue_tail(struct sk_buff_head *list, struct sk_buff *newsk) __skb_queue_tail(list, newsk); spin_unlock_irqrestore(&list->lock, flags); } +EXPORT_SYMBOL(skb_queue_tail); /** * skb_unlink - remove a buffer from a list @@ -1887,6 +1962,7 @@ void skb_unlink(struct sk_buff *skb, struct sk_buff_head *list) __skb_unlink(skb, list); spin_unlock_irqrestore(&list->lock, flags); } +EXPORT_SYMBOL(skb_unlink); /** * skb_append - append a buffer @@ -1906,7 +1982,7 @@ void skb_append(struct sk_buff *old, struct sk_buff *newsk, struct sk_buff_head __skb_queue_after(list, old, newsk); spin_unlock_irqrestore(&list->lock, flags); } - +EXPORT_SYMBOL(skb_append); /** * skb_insert - insert a buffer @@ -1928,6 +2004,7 @@ void skb_insert(struct sk_buff *old, struct sk_buff *newsk, struct sk_buff_head __skb_insert(newsk, old->prev, old, list); spin_unlock_irqrestore(&list->lock, flags); } +EXPORT_SYMBOL(skb_insert); static inline void skb_split_inside_header(struct sk_buff *skb, struct sk_buff* skb1, @@ -2006,6 +2083,7 @@ void skb_split(struct sk_buff *skb, struct sk_buff *skb1, const u32 len) else /* Second chunk has no header, nothing to copy. */ skb_split_no_header(skb, skb1, len, pos); } +EXPORT_SYMBOL(skb_split); /* Shifting from/to a cloned skb is a no-go. * @@ -2168,6 +2246,7 @@ void skb_prepare_seq_read(struct sk_buff *skb, unsigned int from, st->frag_idx = st->stepped_offset = 0; st->frag_data = NULL; } +EXPORT_SYMBOL(skb_prepare_seq_read); /** * skb_seq_read - Sequentially read skb data @@ -2255,6 +2334,7 @@ next_skb: return 0; } +EXPORT_SYMBOL(skb_seq_read); /** * skb_abort_seq_read - Abort a sequential read of skb data @@ -2268,6 +2348,7 @@ void skb_abort_seq_read(struct skb_seq_state *st) if (st->frag_data) kunmap_skb_frag(st->frag_data); } +EXPORT_SYMBOL(skb_abort_seq_read); #define TS_SKB_CB(state) ((struct skb_seq_state *) &((state)->cb)) @@ -2310,6 +2391,7 @@ unsigned int skb_find_text(struct sk_buff *skb, unsigned int from, ret = textsearch_find(config, state); return (ret <= to - from ? ret : UINT_MAX); } +EXPORT_SYMBOL(skb_find_text); /** * skb_append_datato_frags: - append the user data to a skb @@ -2382,6 +2464,7 @@ int skb_append_datato_frags(struct sock *sk, struct sk_buff *skb, return 0; } +EXPORT_SYMBOL(skb_append_datato_frags); /** * skb_pull_rcsum - pull skb and update receive checksum @@ -2569,7 +2652,6 @@ err: } return ERR_PTR(err); } - EXPORT_SYMBOL_GPL(skb_segment); int skb_gro_receive(struct sk_buff **head, struct sk_buff *skb) @@ -2577,17 +2659,23 @@ int skb_gro_receive(struct sk_buff **head, struct sk_buff *skb) struct sk_buff *p = *head; struct sk_buff *nskb; unsigned int headroom; - unsigned int hlen = p->data - skb_mac_header(p); - unsigned int len = skb->len; + unsigned int len = skb_gro_len(skb); - if (hlen + p->len + len >= 65536) + if (p->len + len >= 65536) return -E2BIG; if (skb_shinfo(p)->frag_list) goto merge; - else if (!skb_headlen(p) && !skb_headlen(skb) && - skb_shinfo(p)->nr_frags + skb_shinfo(skb)->nr_frags < - MAX_SKB_FRAGS) { + else if (skb_headlen(skb) <= skb_gro_offset(skb)) { + if (skb_shinfo(p)->nr_frags + skb_shinfo(skb)->nr_frags > + MAX_SKB_FRAGS) + return -E2BIG; + + skb_shinfo(skb)->frags[0].page_offset += + skb_gro_offset(skb) - skb_headlen(skb); + skb_shinfo(skb)->frags[0].size -= + skb_gro_offset(skb) - skb_headlen(skb); + memcpy(skb_shinfo(p)->frags + skb_shinfo(p)->nr_frags, skb_shinfo(skb)->frags, skb_shinfo(skb)->nr_frags * sizeof(skb_frag_t)); @@ -2604,7 +2692,7 @@ int skb_gro_receive(struct sk_buff **head, struct sk_buff *skb) } headroom = skb_headroom(p); - nskb = netdev_alloc_skb(p->dev, headroom); + nskb = netdev_alloc_skb(p->dev, headroom + skb_gro_offset(p)); if (unlikely(!nskb)) return -ENOMEM; @@ -2612,12 +2700,15 @@ int skb_gro_receive(struct sk_buff **head, struct sk_buff *skb) nskb->mac_len = p->mac_len; skb_reserve(nskb, headroom); + __skb_put(nskb, skb_gro_offset(p)); - skb_set_mac_header(nskb, -hlen); + skb_set_mac_header(nskb, skb_mac_header(p) - p->data); skb_set_network_header(nskb, skb_network_offset(p)); skb_set_transport_header(nskb, skb_transport_offset(p)); - memcpy(skb_mac_header(nskb), skb_mac_header(p), hlen); + __skb_pull(p, skb_gro_offset(p)); + memcpy(skb_mac_header(nskb), skb_mac_header(p), + p->data - skb_mac_header(p)); *NAPI_GRO_CB(nskb) = *NAPI_GRO_CB(p); skb_shinfo(nskb)->frag_list = p; @@ -2636,6 +2727,17 @@ int skb_gro_receive(struct sk_buff **head, struct sk_buff *skb) p = nskb; merge: + if (skb_gro_offset(skb) > skb_headlen(skb)) { + skb_shinfo(skb)->frags[0].page_offset += + skb_gro_offset(skb) - skb_headlen(skb); + skb_shinfo(skb)->frags[0].size -= + skb_gro_offset(skb) - skb_headlen(skb); + skb_gro_reset_offset(skb); + skb_gro_pull(skb, skb_headlen(skb)); + } + + __skb_pull(skb, skb_gro_offset(skb)); + p->prev->next = skb; p->prev = skb; skb_header_release(skb); @@ -2747,6 +2849,7 @@ int skb_to_sgvec(struct sk_buff *skb, struct scatterlist *sg, int offset, int le return nsg; } +EXPORT_SYMBOL_GPL(skb_to_sgvec); /** * skb_cow_data - Check that a socket buffer's data buffers are writable @@ -2856,6 +2959,45 @@ int skb_cow_data(struct sk_buff *skb, int tailbits, struct sk_buff **trailer) return elt; } +EXPORT_SYMBOL_GPL(skb_cow_data); + +void skb_tstamp_tx(struct sk_buff *orig_skb, + struct skb_shared_hwtstamps *hwtstamps) +{ + struct sock *sk = orig_skb->sk; + struct sock_exterr_skb *serr; + struct sk_buff *skb; + int err; + + if (!sk) + return; + + skb = skb_clone(orig_skb, GFP_ATOMIC); + if (!skb) + return; + + if (hwtstamps) { + *skb_hwtstamps(skb) = + *hwtstamps; + } else { + /* + * no hardware time stamps available, + * so keep the skb_shared_tx and only + * store software time stamp + */ + skb->tstamp = ktime_get_real(); + } + + serr = SKB_EXT_ERR(skb); + memset(serr, 0, sizeof(*serr)); + serr->ee.ee_errno = ENOMSG; + serr->ee.ee_origin = SO_EE_ORIGIN_TIMESTAMPING; + err = sock_queue_err_skb(sk, skb); + if (err) + kfree_skb(skb); +} +EXPORT_SYMBOL_GPL(skb_tstamp_tx); + /** * skb_partial_csum_set - set up and verify partial csum values for packet @@ -2884,6 +3026,7 @@ bool skb_partial_csum_set(struct sk_buff *skb, u16 start, u16 off) skb->csum_offset = off; return true; } +EXPORT_SYMBOL_GPL(skb_partial_csum_set); void __skb_warn_lro_forwarding(const struct sk_buff *skb) { @@ -2891,42 +3034,4 @@ void __skb_warn_lro_forwarding(const struct sk_buff *skb) pr_warning("%s: received packets cannot be forwarded" " while LRO is enabled\n", skb->dev->name); } - -EXPORT_SYMBOL(___pskb_trim); -EXPORT_SYMBOL(__kfree_skb); -EXPORT_SYMBOL(kfree_skb); -EXPORT_SYMBOL(__pskb_pull_tail); -EXPORT_SYMBOL(__alloc_skb); -EXPORT_SYMBOL(__netdev_alloc_skb); -EXPORT_SYMBOL(pskb_copy); -EXPORT_SYMBOL(pskb_expand_head); -EXPORT_SYMBOL(skb_checksum); -EXPORT_SYMBOL(skb_clone); -EXPORT_SYMBOL(skb_copy); -EXPORT_SYMBOL(skb_copy_and_csum_bits); -EXPORT_SYMBOL(skb_copy_and_csum_dev); -EXPORT_SYMBOL(skb_copy_bits); -EXPORT_SYMBOL(skb_copy_expand); -EXPORT_SYMBOL(skb_over_panic); -EXPORT_SYMBOL(skb_pad); -EXPORT_SYMBOL(skb_realloc_headroom); -EXPORT_SYMBOL(skb_under_panic); -EXPORT_SYMBOL(skb_dequeue); -EXPORT_SYMBOL(skb_dequeue_tail); -EXPORT_SYMBOL(skb_insert); -EXPORT_SYMBOL(skb_queue_purge); -EXPORT_SYMBOL(skb_queue_head); -EXPORT_SYMBOL(skb_queue_tail); -EXPORT_SYMBOL(skb_unlink); -EXPORT_SYMBOL(skb_append); -EXPORT_SYMBOL(skb_split); -EXPORT_SYMBOL(skb_prepare_seq_read); -EXPORT_SYMBOL(skb_seq_read); -EXPORT_SYMBOL(skb_abort_seq_read); -EXPORT_SYMBOL(skb_find_text); -EXPORT_SYMBOL(skb_append_datato_frags); EXPORT_SYMBOL(__skb_warn_lro_forwarding); - -EXPORT_SYMBOL_GPL(skb_to_sgvec); -EXPORT_SYMBOL_GPL(skb_cow_data); -EXPORT_SYMBOL_GPL(skb_partial_csum_set); diff --git a/net/core/sock.c b/net/core/sock.c index 5f97caa158e8..0620046e4eba 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -120,6 +120,7 @@ #include <net/net_namespace.h> #include <net/request_sock.h> #include <net/sock.h> +#include <linux/net_tstamp.h> #include <net/xfrm.h> #include <linux/ipsec.h> @@ -149,7 +150,7 @@ static const char *af_family_key_strings[AF_MAX+1] = { "sk_lock-AF_DECnet", "sk_lock-AF_NETBEUI" , "sk_lock-AF_SECURITY" , "sk_lock-AF_KEY" , "sk_lock-AF_NETLINK" , "sk_lock-AF_PACKET" , "sk_lock-AF_ASH" , "sk_lock-AF_ECONET" , "sk_lock-AF_ATMSVC" , - "sk_lock-21" , "sk_lock-AF_SNA" , "sk_lock-AF_IRDA" , + "sk_lock-AF_RDS" , "sk_lock-AF_SNA" , "sk_lock-AF_IRDA" , "sk_lock-AF_PPPOX" , "sk_lock-AF_WANPIPE" , "sk_lock-AF_LLC" , "sk_lock-27" , "sk_lock-28" , "sk_lock-AF_CAN" , "sk_lock-AF_TIPC" , "sk_lock-AF_BLUETOOTH", "sk_lock-IUCV" , @@ -164,7 +165,7 @@ static const char *af_family_slock_key_strings[AF_MAX+1] = { "slock-AF_DECnet", "slock-AF_NETBEUI" , "slock-AF_SECURITY" , "slock-AF_KEY" , "slock-AF_NETLINK" , "slock-AF_PACKET" , "slock-AF_ASH" , "slock-AF_ECONET" , "slock-AF_ATMSVC" , - "slock-21" , "slock-AF_SNA" , "slock-AF_IRDA" , + "slock-AF_RDS" , "slock-AF_SNA" , "slock-AF_IRDA" , "slock-AF_PPPOX" , "slock-AF_WANPIPE" , "slock-AF_LLC" , "slock-27" , "slock-28" , "slock-AF_CAN" , "slock-AF_TIPC" , "slock-AF_BLUETOOTH", "slock-AF_IUCV" , @@ -179,7 +180,7 @@ static const char *af_family_clock_key_strings[AF_MAX+1] = { "clock-AF_DECnet", "clock-AF_NETBEUI" , "clock-AF_SECURITY" , "clock-AF_KEY" , "clock-AF_NETLINK" , "clock-AF_PACKET" , "clock-AF_ASH" , "clock-AF_ECONET" , "clock-AF_ATMSVC" , - "clock-21" , "clock-AF_SNA" , "clock-AF_IRDA" , + "clock-AF_RDS" , "clock-AF_SNA" , "clock-AF_IRDA" , "clock-AF_PPPOX" , "clock-AF_WANPIPE" , "clock-AF_LLC" , "clock-27" , "clock-28" , "clock-AF_CAN" , "clock-AF_TIPC" , "clock-AF_BLUETOOTH", "clock-AF_IUCV" , @@ -255,11 +256,14 @@ static void sock_warn_obsolete_bsdism(const char *name) } } -static void sock_disable_timestamp(struct sock *sk) +static void sock_disable_timestamp(struct sock *sk, int flag) { - if (sock_flag(sk, SOCK_TIMESTAMP)) { - sock_reset_flag(sk, SOCK_TIMESTAMP); - net_disable_timestamp(); + if (sock_flag(sk, flag)) { + sock_reset_flag(sk, flag); + if (!sock_flag(sk, SOCK_TIMESTAMP) && + !sock_flag(sk, SOCK_TIMESTAMPING_RX_SOFTWARE)) { + net_disable_timestamp(); + } } } @@ -614,13 +618,38 @@ set_rcvbuf: else sock_set_flag(sk, SOCK_RCVTSTAMPNS); sock_set_flag(sk, SOCK_RCVTSTAMP); - sock_enable_timestamp(sk); + sock_enable_timestamp(sk, SOCK_TIMESTAMP); } else { sock_reset_flag(sk, SOCK_RCVTSTAMP); sock_reset_flag(sk, SOCK_RCVTSTAMPNS); } break; + case SO_TIMESTAMPING: + if (val & ~SOF_TIMESTAMPING_MASK) { + ret = EINVAL; + break; + } + sock_valbool_flag(sk, SOCK_TIMESTAMPING_TX_HARDWARE, + val & SOF_TIMESTAMPING_TX_HARDWARE); + sock_valbool_flag(sk, SOCK_TIMESTAMPING_TX_SOFTWARE, + val & SOF_TIMESTAMPING_TX_SOFTWARE); + sock_valbool_flag(sk, SOCK_TIMESTAMPING_RX_HARDWARE, + val & SOF_TIMESTAMPING_RX_HARDWARE); + if (val & SOF_TIMESTAMPING_RX_SOFTWARE) + sock_enable_timestamp(sk, + SOCK_TIMESTAMPING_RX_SOFTWARE); + else + sock_disable_timestamp(sk, + SOCK_TIMESTAMPING_RX_SOFTWARE); + sock_valbool_flag(sk, SOCK_TIMESTAMPING_SOFTWARE, + val & SOF_TIMESTAMPING_SOFTWARE); + sock_valbool_flag(sk, SOCK_TIMESTAMPING_SYS_HARDWARE, + val & SOF_TIMESTAMPING_SYS_HARDWARE); + sock_valbool_flag(sk, SOCK_TIMESTAMPING_RAW_HARDWARE, + val & SOF_TIMESTAMPING_RAW_HARDWARE); + break; + case SO_RCVLOWAT: if (val < 0) val = INT_MAX; @@ -768,6 +797,24 @@ int sock_getsockopt(struct socket *sock, int level, int optname, v.val = sock_flag(sk, SOCK_RCVTSTAMPNS); break; + case SO_TIMESTAMPING: + v.val = 0; + if (sock_flag(sk, SOCK_TIMESTAMPING_TX_HARDWARE)) + v.val |= SOF_TIMESTAMPING_TX_HARDWARE; + if (sock_flag(sk, SOCK_TIMESTAMPING_TX_SOFTWARE)) + v.val |= SOF_TIMESTAMPING_TX_SOFTWARE; + if (sock_flag(sk, SOCK_TIMESTAMPING_RX_HARDWARE)) + v.val |= SOF_TIMESTAMPING_RX_HARDWARE; + if (sock_flag(sk, SOCK_TIMESTAMPING_RX_SOFTWARE)) + v.val |= SOF_TIMESTAMPING_RX_SOFTWARE; + if (sock_flag(sk, SOCK_TIMESTAMPING_SOFTWARE)) + v.val |= SOF_TIMESTAMPING_SOFTWARE; + if (sock_flag(sk, SOCK_TIMESTAMPING_SYS_HARDWARE)) + v.val |= SOF_TIMESTAMPING_SYS_HARDWARE; + if (sock_flag(sk, SOCK_TIMESTAMPING_RAW_HARDWARE)) + v.val |= SOF_TIMESTAMPING_RAW_HARDWARE; + break; + case SO_RCVTIMEO: lv=sizeof(struct timeval); if (sk->sk_rcvtimeo == MAX_SCHEDULE_TIMEOUT) { @@ -969,7 +1016,8 @@ void sk_free(struct sock *sk) rcu_assign_pointer(sk->sk_filter, NULL); } - sock_disable_timestamp(sk); + sock_disable_timestamp(sk, SOCK_TIMESTAMP); + sock_disable_timestamp(sk, SOCK_TIMESTAMPING_RX_SOFTWARE); if (atomic_read(&sk->sk_omem_alloc)) printk(KERN_DEBUG "%s: optmem leakage (%d bytes) detected.\n", @@ -1255,10 +1303,9 @@ static long sock_wait_for_wmem(struct sock * sk, long timeo) * Generic send/receive buffer handlers */ -static struct sk_buff *sock_alloc_send_pskb(struct sock *sk, - unsigned long header_len, - unsigned long data_len, - int noblock, int *errcode) +struct sk_buff *sock_alloc_send_pskb(struct sock *sk, unsigned long header_len, + unsigned long data_len, int noblock, + int *errcode) { struct sk_buff *skb; gfp_t gfp_mask; @@ -1338,6 +1385,7 @@ failure: *errcode = err; return NULL; } +EXPORT_SYMBOL(sock_alloc_send_pskb); struct sk_buff *sock_alloc_send_skb(struct sock *sk, unsigned long size, int noblock, int *errcode) @@ -1786,7 +1834,7 @@ int sock_get_timestamp(struct sock *sk, struct timeval __user *userstamp) { struct timeval tv; if (!sock_flag(sk, SOCK_TIMESTAMP)) - sock_enable_timestamp(sk); + sock_enable_timestamp(sk, SOCK_TIMESTAMP); tv = ktime_to_timeval(sk->sk_stamp); if (tv.tv_sec == -1) return -ENOENT; @@ -1802,7 +1850,7 @@ int sock_get_timestampns(struct sock *sk, struct timespec __user *userstamp) { struct timespec ts; if (!sock_flag(sk, SOCK_TIMESTAMP)) - sock_enable_timestamp(sk); + sock_enable_timestamp(sk, SOCK_TIMESTAMP); ts = ktime_to_timespec(sk->sk_stamp); if (ts.tv_sec == -1) return -ENOENT; @@ -1814,11 +1862,20 @@ int sock_get_timestampns(struct sock *sk, struct timespec __user *userstamp) } EXPORT_SYMBOL(sock_get_timestampns); -void sock_enable_timestamp(struct sock *sk) +void sock_enable_timestamp(struct sock *sk, int flag) { - if (!sock_flag(sk, SOCK_TIMESTAMP)) { - sock_set_flag(sk, SOCK_TIMESTAMP); - net_enable_timestamp(); + if (!sock_flag(sk, flag)) { + sock_set_flag(sk, flag); + /* + * we just set one of the two flags which require net + * time stamping, but time stamping might have been on + * already because of the other one + */ + if (!sock_flag(sk, + flag == SOCK_TIMESTAMP ? + SOCK_TIMESTAMPING_RX_SOFTWARE : + SOCK_TIMESTAMP)) + net_enable_timestamp(); } } diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c index 83d3398559ea..7db1de0497c6 100644 --- a/net/core/sysctl_net_core.c +++ b/net/core/sysctl_net_core.c @@ -11,6 +11,7 @@ #include <linux/socket.h> #include <linux/netdevice.h> #include <linux/init.h> +#include <net/ip.h> #include <net/sock.h> static struct ctl_table net_core_table[] = { diff --git a/net/core/utils.c b/net/core/utils.c index 72e0ebe964a0..83221aee7084 100644 --- a/net/core/utils.c +++ b/net/core/utils.c @@ -22,7 +22,6 @@ #include <linux/net.h> #include <linux/string.h> #include <linux/types.h> -#include <linux/random.h> #include <linux/percpu.h> #include <linux/init.h> #include <net/sock.h> |