diff options
Diffstat (limited to 'net/core')
| -rw-r--r-- | net/core/Makefile | 2 | ||||
| -rw-r--r-- | net/core/datagram.c | 1 | ||||
| -rw-r--r-- | net/core/dev.c | 1077 | ||||
| -rw-r--r-- | net/core/dev_addr_lists.c | 741 | ||||
| -rw-r--r-- | net/core/dev_mcast.c | 232 | ||||
| -rw-r--r-- | net/core/drop_monitor.c | 1 | ||||
| -rw-r--r-- | net/core/dst.c | 46 | ||||
| -rw-r--r-- | net/core/ethtool.c | 149 | ||||
| -rw-r--r-- | net/core/fib_rules.c | 20 | ||||
| -rw-r--r-- | net/core/filter.c | 1 | ||||
| -rw-r--r-- | net/core/flow.c | 405 | ||||
| -rw-r--r-- | net/core/gen_estimator.c | 1 | ||||
| -rw-r--r-- | net/core/iovec.c | 1 | ||||
| -rw-r--r-- | net/core/link_watch.c | 1 | ||||
| -rw-r--r-- | net/core/neighbour.c | 1 | ||||
| -rw-r--r-- | net/core/net-sysfs.c | 104 | ||||
| -rw-r--r-- | net/core/net-traces.c | 1 | ||||
| -rw-r--r-- | net/core/netpoll.c | 8 | ||||
| -rw-r--r-- | net/core/pktgen.c | 58 | ||||
| -rw-r--r-- | net/core/rtnetlink.c | 79 | ||||
| -rw-r--r-- | net/core/scm.c | 1 | ||||
| -rw-r--r-- | net/core/sock.c | 8 | ||||
| -rw-r--r-- | net/core/sysctl_net_core.c | 69 |
23 files changed, 1739 insertions, 1268 deletions
diff --git a/net/core/Makefile b/net/core/Makefile index 08791ac3e05a..51c3eec850ef 100644 --- a/net/core/Makefile +++ b/net/core/Makefile @@ -7,7 +7,7 @@ obj-y := sock.o request_sock.o skbuff.o iovec.o datagram.o stream.o scm.o \ obj-$(CONFIG_SYSCTL) += sysctl_net_core.o -obj-y += dev.o ethtool.o dev_mcast.o dst.o netevent.o \ +obj-y += dev.o ethtool.o dev_addr_lists.o dst.o netevent.o \ neighbour.o rtnetlink.o utils.o link_watch.o filter.o obj-$(CONFIG_XFRM) += flow.o diff --git a/net/core/datagram.c b/net/core/datagram.c index 95c2e0840d0d..2dccd4ee591b 100644 --- a/net/core/datagram.c +++ b/net/core/datagram.c @@ -48,6 +48,7 @@ #include <linux/poll.h> #include <linux/highmem.h> #include <linux/spinlock.h> +#include <linux/slab.h> #include <net/protocol.h> #include <linux/skbuff.h> diff --git a/net/core/dev.c b/net/core/dev.c index 17b168671501..b31d5d69a467 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -80,6 +80,7 @@ #include <linux/types.h> #include <linux/kernel.h> #include <linux/hash.h> +#include <linux/slab.h> #include <linux/sched.h> #include <linux/mutex.h> #include <linux/string.h> @@ -129,6 +130,7 @@ #include <linux/jhash.h> #include <linux/random.h> #include <trace/events/napi.h> +#include <linux/pci.h> #include "net-sysfs.h" @@ -206,6 +208,20 @@ static inline struct hlist_head *dev_index_hash(struct net *net, int ifindex) return &net->dev_index_head[ifindex & (NETDEV_HASHENTRIES - 1)]; } +static inline void rps_lock(struct softnet_data *sd) +{ +#ifdef CONFIG_RPS + spin_lock(&sd->input_pkt_queue.lock); +#endif +} + +static inline void rps_unlock(struct softnet_data *sd) +{ +#ifdef CONFIG_RPS + spin_unlock(&sd->input_pkt_queue.lock); +#endif +} + /* Device list insertion */ static int list_netdevice(struct net_device *dev) { @@ -248,7 +264,7 @@ static RAW_NOTIFIER_HEAD(netdev_chain); * queue in the local softnet handler. */ -DEFINE_PER_CPU(struct softnet_data, softnet_data); +DEFINE_PER_CPU_ALIGNED(struct softnet_data, softnet_data); EXPORT_PER_CPU_SYMBOL(softnet_data); #ifdef CONFIG_LOCKDEP @@ -772,14 +788,17 @@ EXPORT_SYMBOL(__dev_getfirstbyhwtype); struct net_device *dev_getfirstbyhwtype(struct net *net, unsigned short type) { - struct net_device *dev; + struct net_device *dev, *ret = NULL; - rtnl_lock(); - dev = __dev_getfirstbyhwtype(net, type); - if (dev) - dev_hold(dev); - rtnl_unlock(); - return dev; + rcu_read_lock(); + for_each_netdev_rcu(net, dev) + if (dev->type == type) { + dev_hold(dev); + ret = dev; + break; + } + rcu_read_unlock(); + return ret; } EXPORT_SYMBOL(dev_getfirstbyhwtype); @@ -1084,9 +1103,9 @@ void netdev_state_change(struct net_device *dev) } EXPORT_SYMBOL(netdev_state_change); -void netdev_bonding_change(struct net_device *dev, unsigned long event) +int netdev_bonding_change(struct net_device *dev, unsigned long event) { - call_netdevice_notifiers(event, dev); + return call_netdevice_notifiers(event, dev); } EXPORT_SYMBOL(netdev_bonding_change); @@ -1416,6 +1435,7 @@ EXPORT_SYMBOL(unregister_netdevice_notifier); int call_netdevice_notifiers(unsigned long val, struct net_device *dev) { + ASSERT_RTNL(); return raw_notifier_call_chain(&netdev_chain, val, dev); } @@ -1783,18 +1803,27 @@ EXPORT_SYMBOL(netdev_rx_csum_fault); * 2. No high memory really exists on this machine. */ -static inline int illegal_highdma(struct net_device *dev, struct sk_buff *skb) +static int illegal_highdma(struct net_device *dev, struct sk_buff *skb) { #ifdef CONFIG_HIGHMEM int i; + if (!(dev->features & NETIF_F_HIGHDMA)) { + for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) + if (PageHighMem(skb_shinfo(skb)->frags[i].page)) + return 1; + } - if (dev->features & NETIF_F_HIGHDMA) - return 0; - - for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) - if (PageHighMem(skb_shinfo(skb)->frags[i].page)) - return 1; + if (PCI_DMA_BUS_IS_PHYS) { + struct device *pdev = dev->dev.parent; + if (!pdev) + return 0; + for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { + dma_addr_t addr = page_to_phys(skb_shinfo(skb)->frags[i].page); + if (!pdev->dma_mask || addr + PAGE_SIZE - 1 > *pdev->dma_mask) + return 1; + } + } #endif return 0; } @@ -1852,6 +1881,17 @@ static int dev_gso_segment(struct sk_buff *skb) return 0; } +/* + * Try to orphan skb early, right before transmission by the device. + * We cannot orphan skb if tx timestamp is requested, since + * drivers need to call skb_tstamp_tx() to send the timestamp. + */ +static inline void skb_orphan_try(struct sk_buff *skb) +{ + if (!skb_tx(skb)->flags) + skb_orphan(skb); +} + int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev, struct netdev_queue *txq) { @@ -1876,23 +1916,10 @@ int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev, if (dev->priv_flags & IFF_XMIT_DST_RELEASE) skb_dst_drop(skb); + skb_orphan_try(skb); rc = ops->ndo_start_xmit(skb, dev); if (rc == NETDEV_TX_OK) txq_trans_update(txq); - /* - * 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; } @@ -1910,6 +1937,7 @@ gso: if (dev->priv_flags & IFF_XMIT_DST_RELEASE) skb_dst_drop(nskb); + skb_orphan_try(nskb); rc = ops->ndo_start_xmit(nskb, dev); if (unlikely(rc != NETDEV_TX_OK)) { if (rc & ~NETDEV_TX_MASK) @@ -1947,7 +1975,7 @@ u16 skb_tx_hash(const struct net_device *dev, const struct sk_buff *skb) if (skb->sk && skb->sk->sk_hash) hash = skb->sk->sk_hash; else - hash = skb->protocol; + hash = (__force u16) skb->protocol; hash = jhash_1word(hash, hashrnd); @@ -1959,9 +1987,9 @@ static inline u16 dev_cap_txqueue(struct net_device *dev, u16 queue_index) { if (unlikely(queue_index >= dev->real_num_tx_queues)) { if (net_ratelimit()) { - netdev_warn(dev, "selects TX queue %d, but " - "real number of TX queues is %d\n", - queue_index, dev->real_num_tx_queues); + pr_warning("%s selects TX queue %d, but " + "real number of TX queues is %d\n", + dev->name, queue_index, dev->real_num_tx_queues); } return 0; } @@ -1987,7 +2015,7 @@ static struct netdev_queue *dev_pick_tx(struct net_device *dev, if (dev->real_num_tx_queues > 1) queue_index = skb_tx_hash(dev, skb); - if (sk && sk->sk_dst_cache) + if (sk && rcu_dereference_check(sk->sk_dst_cache, 1)) sk_tx_queue_set(sk, queue_index); } } @@ -2174,29 +2202,38 @@ int weight_p __read_mostly = 64; /* old backlog weight */ DEFINE_PER_CPU(struct netif_rx_stats, netdev_rx_stat) = { 0, }; +#ifdef CONFIG_RPS + +/* One global table that all flow-based protocols share. */ +struct rps_sock_flow_table *rps_sock_flow_table __read_mostly; +EXPORT_SYMBOL(rps_sock_flow_table); + /* * get_rps_cpu is called from netif_receive_skb and returns the target * CPU from the RPS map of the receiving queue for a given skb. + * rcu_read_lock must be held on entry. */ -static int get_rps_cpu(struct net_device *dev, struct sk_buff *skb) +static int get_rps_cpu(struct net_device *dev, struct sk_buff *skb, + struct rps_dev_flow **rflowp) { struct ipv6hdr *ip6; struct iphdr *ip; struct netdev_rx_queue *rxqueue; struct rps_map *map; + struct rps_dev_flow_table *flow_table; + struct rps_sock_flow_table *sock_flow_table; int cpu = -1; u8 ip_proto; + u16 tcpu; u32 addr1, addr2, ports, ihl; - rcu_read_lock(); - if (skb_rx_queue_recorded(skb)) { u16 index = skb_get_rx_queue(skb); if (unlikely(index >= dev->num_rx_queues)) { if (net_ratelimit()) { - netdev_warn(dev, "received packet on queue " - "%u, but number of RX queues is %u\n", - index, dev->num_rx_queues); + pr_warning("%s received packet on queue " + "%u, but number of RX queues is %u\n", + dev->name, index, dev->num_rx_queues); } goto done; } @@ -2204,7 +2241,7 @@ static int get_rps_cpu(struct net_device *dev, struct sk_buff *skb) } else rxqueue = dev->_rx; - if (!rxqueue->rps_map) + if (!rxqueue->rps_map && !rxqueue->rps_flow_table) goto done; if (skb->rxhash) @@ -2217,8 +2254,8 @@ static int get_rps_cpu(struct net_device *dev, struct sk_buff *skb) ip = (struct iphdr *) skb->data; ip_proto = ip->protocol; - addr1 = ip->saddr; - addr2 = ip->daddr; + addr1 = (__force u32) ip->saddr; + addr2 = (__force u32) ip->daddr; ihl = ip->ihl; break; case __constant_htons(ETH_P_IPV6): @@ -2227,8 +2264,8 @@ static int get_rps_cpu(struct net_device *dev, struct sk_buff *skb) ip6 = (struct ipv6hdr *) skb->data; ip_proto = ip6->nexthdr; - addr1 = ip6->saddr.s6_addr32[3]; - addr2 = ip6->daddr.s6_addr32[3]; + addr1 = (__force u32) ip6->saddr.s6_addr32[3]; + addr2 = (__force u32) ip6->daddr.s6_addr32[3]; ihl = (40 >> 2); break; default: @@ -2243,22 +2280,72 @@ static int get_rps_cpu(struct net_device *dev, struct sk_buff *skb) case IPPROTO_AH: case IPPROTO_SCTP: case IPPROTO_UDPLITE: - if (pskb_may_pull(skb, (ihl * 4) + 4)) - ports = *((u32 *) (skb->data + (ihl * 4))); + if (pskb_may_pull(skb, (ihl * 4) + 4)) { + __be16 *hports = (__be16 *) (skb->data + (ihl * 4)); + u32 sport, dport; + + sport = (__force u16) hports[0]; + dport = (__force u16) hports[1]; + if (dport < sport) + swap(sport, dport); + ports = (sport << 16) + dport; + } break; default: break; } + /* get a consistent hash (same value on both flow directions) */ + if (addr2 < addr1) + swap(addr1, addr2); skb->rxhash = jhash_3words(addr1, addr2, ports, hashrnd); if (!skb->rxhash) skb->rxhash = 1; got_hash: + flow_table = rcu_dereference(rxqueue->rps_flow_table); + sock_flow_table = rcu_dereference(rps_sock_flow_table); + if (flow_table && sock_flow_table) { + u16 next_cpu; + struct rps_dev_flow *rflow; + + rflow = &flow_table->flows[skb->rxhash & flow_table->mask]; + tcpu = rflow->cpu; + + next_cpu = sock_flow_table->ents[skb->rxhash & + sock_flow_table->mask]; + + /* + * If the desired CPU (where last recvmsg was done) is + * different from current CPU (one in the rx-queue flow + * table entry), switch if one of the following holds: + * - Current CPU is unset (equal to RPS_NO_CPU). + * - Current CPU is offline. + * - The current CPU's queue tail has advanced beyond the + * last packet that was enqueued using this table entry. + * This guarantees that all previous packets for the flow + * have been dequeued, thus preserving in order delivery. + */ + if (unlikely(tcpu != next_cpu) && + (tcpu == RPS_NO_CPU || !cpu_online(tcpu) || + ((int)(per_cpu(softnet_data, tcpu).input_queue_head - + rflow->last_qtail)) >= 0)) { + tcpu = rflow->cpu = next_cpu; + if (tcpu != RPS_NO_CPU) + rflow->last_qtail = per_cpu(softnet_data, + tcpu).input_queue_head; + } + if (tcpu != RPS_NO_CPU && cpu_online(tcpu)) { + *rflowp = rflow; + cpu = tcpu; + goto done; + } + } + map = rcu_dereference(rxqueue->rps_map); if (map) { - u16 tcpu = map->cpus[((u64) skb->rxhash * map->len) >> 32]; + tcpu = map->cpus[((u64) skb->rxhash * map->len) >> 32]; if (cpu_online(tcpu)) { cpu = tcpu; @@ -2267,72 +2354,78 @@ got_hash: } done: - rcu_read_unlock(); return cpu; } -/* - * This structure holds the per-CPU mask of CPUs for which IPIs are scheduled - * to be sent to kick remote softirq processing. There are two masks since - * the sending of IPIs must be done with interrupts enabled. The select field - * indicates the current mask that enqueue_backlog uses to schedule IPIs. - * select is flipped before net_rps_action is called while still under lock, - * net_rps_action then uses the non-selected mask to send the IPIs and clears - * it without conflicting with enqueue_backlog operation. - */ -struct rps_remote_softirq_cpus { - cpumask_t mask[2]; - int select; -}; -static DEFINE_PER_CPU(struct rps_remote_softirq_cpus, rps_remote_softirq_cpus); - /* Called from hardirq (IPI) context */ -static void trigger_softirq(void *data) +static void rps_trigger_softirq(void *data) { - struct softnet_data *queue = data; - __napi_schedule(&queue->backlog); + struct softnet_data *sd = data; + + __napi_schedule(&sd->backlog); __get_cpu_var(netdev_rx_stat).received_rps++; } +#endif /* CONFIG_RPS */ + +/* + * Check if this softnet_data structure is another cpu one + * If yes, queue it to our IPI list and return 1 + * If no, return 0 + */ +static int rps_ipi_queued(struct softnet_data *sd) +{ +#ifdef CONFIG_RPS + struct softnet_data *mysd = &__get_cpu_var(softnet_data); + + if (sd != mysd) { + sd->rps_ipi_next = mysd->rps_ipi_list; + mysd->rps_ipi_list = sd; + + __raise_softirq_irqoff(NET_RX_SOFTIRQ); + return 1; + } +#endif /* CONFIG_RPS */ + return 0; +} + /* * enqueue_to_backlog is called to queue an skb to a per CPU backlog * queue (may be a remote CPU queue). */ -static int enqueue_to_backlog(struct sk_buff *skb, int cpu) +static int enqueue_to_backlog(struct sk_buff *skb, int cpu, + unsigned int *qtail) { - struct softnet_data *queue; + struct softnet_data *sd; unsigned long flags; - queue = &per_cpu(softnet_data, cpu); + sd = &per_cpu(softnet_data, cpu); local_irq_save(flags); __get_cpu_var(netdev_rx_stat).total++; - spin_lock(&queue->input_pkt_queue.lock); - if (queue->input_pkt_queue.qlen <= netdev_max_backlog) { - if (queue->input_pkt_queue.qlen) { + rps_lock(sd); + if (sd->input_pkt_queue.qlen <= netdev_max_backlog) { + if (sd->input_pkt_queue.qlen) { enqueue: - __skb_queue_tail(&queue->input_pkt_queue, skb); - spin_unlock_irqrestore(&queue->input_pkt_queue.lock, - flags); + __skb_queue_tail(&sd->input_pkt_queue, skb); +#ifdef CONFIG_RPS + *qtail = sd->input_queue_head + sd->input_pkt_queue.qlen; +#endif + rps_unlock(sd); + local_irq_restore(flags); return NET_RX_SUCCESS; } /* Schedule NAPI for backlog device */ - if (napi_schedule_prep(&queue->backlog)) { - if (cpu != smp_processor_id()) { - struct rps_remote_softirq_cpus *rcpus = - &__get_cpu_var(rps_remote_softirq_cpus); - - cpu_set(cpu, rcpus->mask[rcpus->select]); - __raise_softirq_irqoff(NET_RX_SOFTIRQ); - } else - __napi_schedule(&queue->backlog); + if (napi_schedule_prep(&sd->backlog)) { + if (!rps_ipi_queued(sd)) + __napi_schedule(&sd->backlog); } goto enqueue; } - spin_unlock(&queue->input_pkt_queue.lock); + rps_unlock(sd); __get_cpu_var(netdev_rx_stat).dropped++; local_irq_restore(flags); @@ -2358,7 +2451,7 @@ enqueue: int netif_rx(struct sk_buff *skb) { - int cpu; + int ret; /* if netpoll wants it, pretend we never saw it */ if (netpoll_rx(skb)) @@ -2367,11 +2460,29 @@ int netif_rx(struct sk_buff *skb) if (!skb->tstamp.tv64) net_timestamp(skb); - cpu = get_rps_cpu(skb->dev, skb); - if (cpu < 0) - cpu = smp_processor_id(); +#ifdef CONFIG_RPS + { + struct rps_dev_flow voidflow, *rflow = &voidflow; + int cpu; - return enqueue_to_backlog(skb, cpu); + rcu_read_lock(); + + cpu = get_rps_cpu(skb->dev, skb, &rflow); + if (cpu < 0) + cpu = smp_processor_id(); + + ret = enqueue_to_backlog(skb, cpu, &rflow->last_qtail); + + rcu_read_unlock(); + } +#else + { + unsigned int qtail; + ret = enqueue_to_backlog(skb, get_cpu(), &qtail); + put_cpu(); + } +#endif + return ret; } EXPORT_SYMBOL(netif_rx); @@ -2608,10 +2719,60 @@ void netif_nit_deliver(struct sk_buff *skb) rcu_read_unlock(); } -int __netif_receive_skb(struct sk_buff *skb) +static inline void skb_bond_set_mac_by_master(struct sk_buff *skb, + struct net_device *master) +{ + if (skb->pkt_type == PACKET_HOST) { + u16 *dest = (u16 *) eth_hdr(skb)->h_dest; + + memcpy(dest, master->dev_addr, ETH_ALEN); + } +} + +/* On bonding slaves other than the currently active slave, suppress + * duplicates except for 802.3ad ETH_P_SLOW, alb non-mcast/bcast, and + * ARP on active-backup slaves with arp_validate enabled. + */ +int __skb_bond_should_drop(struct sk_buff *skb, struct net_device *master) +{ + struct net_device *dev = skb->dev; + + if (master->priv_flags & IFF_MASTER_ARPMON) + dev->last_rx = jiffies; + + if ((master->priv_flags & IFF_MASTER_ALB) && master->br_port) { + /* Do address unmangle. The local destination address + * will be always the one master has. Provides the right + * functionality in a bridge. + */ + skb_bond_set_mac_by_master(skb, master); + } + + if (dev->priv_flags & IFF_SLAVE_INACTIVE) { + if ((dev->priv_flags & IFF_SLAVE_NEEDARP) && + skb->protocol == __cpu_to_be16(ETH_P_ARP)) + return 0; + + if (master->priv_flags & IFF_MASTER_ALB) { + if (skb->pkt_type != PACKET_BROADCAST && + skb->pkt_type != PACKET_MULTICAST) + return 0; + } + if (master->priv_flags & IFF_MASTER_8023AD && + skb->protocol == __cpu_to_be16(ETH_P_SLOW)) + return 0; + + return 1; + } + return 0; +} +EXPORT_SYMBOL(__skb_bond_should_drop); + +static int __netif_receive_skb(struct sk_buff *skb) { struct packet_type *ptype, *pt_prev; struct net_device *orig_dev; + struct net_device *master; struct net_device *null_or_orig; struct net_device *null_or_bond; int ret = NET_RX_DROP; @@ -2632,11 +2793,12 @@ int __netif_receive_skb(struct sk_buff *skb) null_or_orig = NULL; orig_dev = skb->dev; - if (orig_dev->master) { - if (skb_bond_should_drop(skb)) + master = ACCESS_ONCE(orig_dev->master); + if (master) { + if (skb_bond_should_drop(skb, master)) null_or_orig = orig_dev; /* deliver only exact match */ else - skb->dev = orig_dev->master; + skb->dev = master; } __get_cpu_var(netdev_rx_stat).total++; @@ -2735,29 +2897,46 @@ out: */ int netif_receive_skb(struct sk_buff *skb) { - int cpu; +#ifdef CONFIG_RPS + struct rps_dev_flow voidflow, *rflow = &voidflow; + int cpu, ret; + + rcu_read_lock(); - cpu = get_rps_cpu(skb->dev, skb); + cpu = get_rps_cpu(skb->dev, skb, &rflow); - if (cpu < 0) - return __netif_receive_skb(skb); - else - return enqueue_to_backlog(skb, cpu); + 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; +#else + return __netif_receive_skb(skb); +#endif } EXPORT_SYMBOL(netif_receive_skb); -/* Network device is going away, flush any packets still pending */ +/* Network device is going away, flush any packets still pending + * Called with irqs disabled. + */ static void flush_backlog(void *arg) { struct net_device *dev = arg; - struct softnet_data *queue = &__get_cpu_var(softnet_data); + struct softnet_data *sd = &__get_cpu_var(softnet_data); struct sk_buff *skb, *tmp; - skb_queue_walk_safe(&queue->input_pkt_queue, skb, tmp) + rps_lock(sd); + skb_queue_walk_safe(&sd->input_pkt_queue, skb, tmp) if (skb->dev == dev) { - __skb_unlink(skb, &queue->input_pkt_queue); + __skb_unlink(skb, &sd->input_pkt_queue); kfree_skb(skb); + input_queue_head_incr(sd); } + rps_unlock(sd); } static int napi_gro_complete(struct sk_buff *skb) @@ -3063,24 +3242,27 @@ EXPORT_SYMBOL(napi_gro_frags); static int process_backlog(struct napi_struct *napi, int quota) { int work = 0; - struct softnet_data *queue = &__get_cpu_var(softnet_data); - unsigned long start_time = jiffies; + struct softnet_data *sd = &__get_cpu_var(softnet_data); napi->weight = weight_p; do { struct sk_buff *skb; - spin_lock_irq(&queue->input_pkt_queue.lock); - skb = __skb_dequeue(&queue->input_pkt_queue); + local_irq_disable(); + rps_lock(sd); + skb = __skb_dequeue(&sd->input_pkt_queue); if (!skb) { __napi_complete(napi); - spin_unlock_irq(&queue->input_pkt_queue.lock); + rps_unlock(sd); + local_irq_enable(); break; } - spin_unlock_irq(&queue->input_pkt_queue.lock); + input_queue_head_incr(sd); + rps_unlock(sd); + local_irq_enable(); __netif_receive_skb(skb); - } while (++work < quota && jiffies == start_time); + } while (++work < quota); return work; } @@ -3169,20 +3351,32 @@ void netif_napi_del(struct napi_struct *napi) EXPORT_SYMBOL(netif_napi_del); /* - * net_rps_action sends any pending IPI's for rps. This is only called from - * softirq and interrupts must be enabled. + * net_rps_action sends any pending IPI's for rps. + * Note: called with local irq disabled, but exits with local irq enabled. */ -static void net_rps_action(cpumask_t *mask) +static void net_rps_action_and_irq_disable(void) { - int cpu; +#ifdef CONFIG_RPS + struct softnet_data *sd = &__get_cpu_var(softnet_data); + struct softnet_data *remsd = sd->rps_ipi_list; - /* Send pending IPI's to kick RPS processing on remote cpus. */ - for_each_cpu_mask_nr(cpu, *mask) { - struct softnet_data *queue = &per_cpu(softnet_data, cpu); - if (cpu_online(cpu)) - __smp_call_function_single(cpu, &queue->csd, 0); - } - cpus_clear(*mask); + if (remsd) { + sd->rps_ipi_list = NULL; + + local_irq_enable(); + + /* Send pending IPI's to kick RPS processing on remote cpus. */ + while (remsd) { + struct softnet_data *next = remsd->rps_ipi_next; + + if (cpu_online(remsd->cpu)) + __smp_call_function_single(remsd->cpu, + &remsd->csd, 0); + remsd = next; + } + } else +#endif + local_irq_enable(); } static void net_rx_action(struct softirq_action *h) @@ -3191,8 +3385,6 @@ static void net_rx_action(struct softirq_action *h) unsigned long time_limit = jiffies + 2; int budget = netdev_budget; void *have; - int select; - struct rps_remote_softirq_cpus *rcpus; local_irq_disable(); @@ -3255,13 +3447,7 @@ static void net_rx_action(struct softirq_action *h) netpoll_poll_unlock(have); } out: - rcpus = &__get_cpu_var(rps_remote_softirq_cpus); - select = rcpus->select; - rcpus->select ^= 1; - - local_irq_enable(); - - net_rps_action(&rcpus->mask[select]); + net_rps_action_and_irq_disable(); #ifdef CONFIG_NET_DMA /* @@ -3733,11 +3919,10 @@ int netdev_set_master(struct net_device *slave, struct net_device *master) slave->master = master; - synchronize_net(); - - if (old) + if (old) { + synchronize_net(); dev_put(old); - + } if (master) slave->flags |= IFF_SLAVE; else @@ -3914,562 +4099,6 @@ void dev_set_rx_mode(struct net_device *dev) netif_addr_unlock_bh(dev); } -/* hw addresses list handling functions */ - -static int __hw_addr_add(struct netdev_hw_addr_list *list, unsigned char *addr, - int addr_len, unsigned char addr_type) -{ - struct netdev_hw_addr *ha; - int alloc_size; - - if (addr_len > MAX_ADDR_LEN) - return -EINVAL; - - list_for_each_entry(ha, &list->list, list) { - if (!memcmp(ha->addr, addr, addr_len) && - ha->type == addr_type) { - ha->refcount++; - return 0; - } - } - - - alloc_size = sizeof(*ha); - if (alloc_size < L1_CACHE_BYTES) - alloc_size = L1_CACHE_BYTES; - ha = kmalloc(alloc_size, GFP_ATOMIC); - if (!ha) - return -ENOMEM; - memcpy(ha->addr, addr, addr_len); - ha->type = addr_type; - ha->refcount = 1; - ha->synced = false; - list_add_tail_rcu(&ha->list, &list->list); - list->count++; - return 0; -} - -static void ha_rcu_free(struct rcu_head *head) -{ - struct netdev_hw_addr *ha; - - ha = container_of(head, struct netdev_hw_addr, rcu_head); - kfree(ha); -} - -static int __hw_addr_del(struct netdev_hw_addr_list *list, unsigned char *addr, - int addr_len, unsigned char addr_type) -{ - struct netdev_hw_addr *ha; - - list_for_each_entry(ha, &list->list, list) { - if (!memcmp(ha->addr, addr, addr_len) && - (ha->type == addr_type || !addr_type)) { - if (--ha->refcount) - return 0; - list_del_rcu(&ha->list); - call_rcu(&ha->rcu_head, ha_rcu_free); - list->count--; - return 0; - } - } - return -ENOENT; -} - -static int __hw_addr_add_multiple(struct netdev_hw_addr_list *to_list, - struct netdev_hw_addr_list *from_list, - int addr_len, - unsigned char addr_type) -{ - int err; - struct netdev_hw_addr *ha, *ha2; - unsigned char type; - - list_for_each_entry(ha, &from_list->list, list) { - type = addr_type ? addr_type : ha->type; - err = __hw_addr_add(to_list, ha->addr, addr_len, type); - if (err) - goto unroll; - } - return 0; - -unroll: - list_for_each_entry(ha2, &from_list->list, list) { - if (ha2 == ha) - break; - type = addr_type ? addr_type : ha2->type; - __hw_addr_del(to_list, ha2->addr, addr_len, type); - } - return err; -} - -static void __hw_addr_del_multiple(struct netdev_hw_addr_list *to_list, - struct netdev_hw_addr_list *from_list, - int addr_len, - unsigned char addr_type) -{ - struct netdev_hw_addr *ha; - unsigned char type; - - list_for_each_entry(ha, &from_list->list, list) { - type = addr_type ? addr_type : ha->type; - __hw_addr_del(to_list, ha->addr, addr_len, addr_type); - } -} - -static int __hw_addr_sync(struct netdev_hw_addr_list *to_list, - struct netdev_hw_addr_list *from_list, - int addr_len) -{ - int err = 0; - struct netdev_hw_addr *ha, *tmp; - - list_for_each_entry_safe(ha, tmp, &from_list->list, list) { - if (!ha->synced) { - err = __hw_addr_add(to_list, ha->addr, - addr_len, ha->type); - if (err) - break; - ha->synced = true; - ha->refcount++; - } else if (ha->refcount == 1) { - __hw_addr_del(to_list, ha->addr, addr_len, ha->type); - __hw_addr_del(from_list, ha->addr, addr_len, ha->type); - } - } - return err; -} - -static void __hw_addr_unsync(struct netdev_hw_addr_list *to_list, - struct netdev_hw_addr_list *from_list, - int addr_len) -{ - struct netdev_hw_addr *ha, *tmp; - - list_for_each_entry_safe(ha, tmp, &from_list->list, list) { - if (ha->synced) { - __hw_addr_del(to_list, ha->addr, - addr_len, ha->type); - ha->synced = false; - __hw_addr_del(from_list, ha->addr, - addr_len, ha->type); - } - } -} - -static void __hw_addr_flush(struct netdev_hw_addr_list *list) -{ - struct netdev_hw_addr *ha, *tmp; - - list_for_each_entry_safe(ha, tmp, &list->list, list) { - list_del_rcu(&ha->list); - call_rcu(&ha->rcu_head, ha_rcu_free); - } - list->count = 0; -} - -static void __hw_addr_init(struct netdev_hw_addr_list *list) -{ - INIT_LIST_HEAD(&list->list); - list->count = 0; -} - -/* Device addresses handling functions */ - -static void dev_addr_flush(struct net_device *dev) -{ - /* rtnl_mutex must be held here */ - - __hw_addr_flush(&dev->dev_addrs); - dev->dev_addr = NULL; -} - -static int dev_addr_init(struct net_device *dev) -{ - unsigned char addr[MAX_ADDR_LEN]; - struct netdev_hw_addr *ha; - int err; - - /* rtnl_mutex must be held here */ - - __hw_addr_init(&dev->dev_addrs); - memset(addr, 0, sizeof(addr)); - err = __hw_addr_add(&dev->dev_addrs, addr, sizeof(addr), - NETDEV_HW_ADDR_T_LAN); - if (!err) { - /* - * Get the first (previously created) address from the list - * and set dev_addr pointer to this location. - */ - ha = list_first_entry(&dev->dev_addrs.list, - struct netdev_hw_addr, list); - dev->dev_addr = ha->addr; - } - return err; -} - -/** - * dev_addr_add - Add a device address - * @dev: device - * @addr: address to add - * @addr_type: address type - * - * Add a device address to the device or increase the reference count if - * it already exists. - * - * The caller must hold the rtnl_mutex. - */ -int dev_addr_add(struct net_device *dev, unsigned char *addr, - unsigned char addr_type) -{ - int err; - - ASSERT_RTNL(); - - err = __hw_addr_add(&dev->dev_addrs, addr, dev->addr_len, addr_type); - if (!err) - call_netdevice_notifiers(NETDEV_CHANGEADDR, dev); - return err; -} -EXPORT_SYMBOL(dev_addr_add); - -/** - * dev_addr_del - Release a device address. - * @dev: device - * @addr: address to delete - * @addr_type: address type - * - * Release reference to a device address and remove it from the device - * if the reference count drops to zero. - * - * The caller must hold the rtnl_mutex. - */ -int dev_addr_del(struct net_device *dev, unsigned char *addr, - unsigned char addr_type) -{ - int err; - struct netdev_hw_addr *ha; - - ASSERT_RTNL(); - - /* - * We can not remove the first address from the list because - * dev->dev_addr points to that. - */ - ha = list_first_entry(&dev->dev_addrs.list, - struct netdev_hw_addr, list); - if (ha->addr == dev->dev_addr && ha->refcount == 1) - return -ENOENT; - - err = __hw_addr_del(&dev->dev_addrs, addr, dev->addr_len, - addr_type); - if (!err) - call_netdevice_notifiers(NETDEV_CHANGEADDR, dev); - return err; -} -EXPORT_SYMBOL(dev_addr_del); - -/** - * dev_addr_add_multiple - Add device addresses from another device - * @to_dev: device to which addresses will be added - * @from_dev: device from which addresses will be added - * @addr_type: address type - 0 means type will be used from from_dev - * - * Add device addresses of the one device to another. - ** - * The caller must hold the rtnl_mutex. - */ -int dev_addr_add_multiple(struct net_device *to_dev, - struct net_device *from_dev, - unsigned char addr_type) -{ - int err; - - ASSERT_RTNL(); - - if (from_dev->addr_len != to_dev->addr_len) - return -EINVAL; - err = __hw_addr_add_multiple(&to_dev->dev_addrs, &from_dev->dev_addrs, - to_dev->addr_len, addr_type); - if (!err) - call_netdevice_notifiers(NETDEV_CHANGEADDR, to_dev); - return err; -} -EXPORT_SYMBOL(dev_addr_add_multiple); - -/** - * dev_addr_del_multiple - Delete device addresses by another device - * @to_dev: device where the addresses will be deleted - * @from_dev: device by which addresses the addresses will be deleted - * @addr_type: address type - 0 means type will used from from_dev - * - * Deletes addresses in to device by the list of addresses in from device. - * - * The caller must hold the rtnl_mutex. - */ -int dev_addr_del_multiple(struct net_device *to_dev, - struct net_device *from_dev, - unsigned char addr_type) -{ - ASSERT_RTNL(); - - if (from_dev->addr_len != to_dev->addr_len) - return -EINVAL; - __hw_addr_del_multiple(&to_dev->dev_addrs, &from_dev->dev_addrs, - to_dev->addr_len, addr_type); - call_netdevice_notifiers(NETDEV_CHANGEADDR, to_dev); - return 0; -} -EXPORT_SYMBOL(dev_addr_del_multiple); - -/* multicast addresses handling functions */ - -int __dev_addr_delete(struct dev_addr_list **list, int *count, - void *addr, int alen, int glbl) -{ - struct dev_addr_list *da; - - for (; (da = *list) != NULL; list = &da->next) { - if (memcmp(da->da_addr, addr, da->da_addrlen) == 0 && - alen == da->da_addrlen) { - if (glbl) { - int old_glbl = da->da_gusers; - da->da_gusers = 0; - if (old_glbl == 0) - break; - } - if (--da->da_users) - return 0; - - *list = da->next; - kfree(da); - (*count)--; - return 0; - } - } - return -ENOENT; -} - -int __dev_addr_add(struct dev_addr_list **list, int *count, - void *addr, int alen, int glbl) -{ - struct dev_addr_list *da; - - for (da = *list; da != NULL; da = da->next) { - if (memcmp(da->da_addr, addr, da->da_addrlen) == 0 && - da->da_addrlen == alen) { - if (glbl) { - int old_glbl = da->da_gusers; - da->da_gusers = 1; - if (old_glbl) - return 0; - } - da->da_users++; - return 0; - } - } - - da = kzalloc(sizeof(*da), GFP_ATOMIC); - if (da == NULL) - return -ENOMEM; - memcpy(da->da_addr, addr, alen); - da->da_addrlen = alen; - da->da_users = 1; - da->da_gusers = glbl ? 1 : 0; - da->next = *list; - *list = da; - (*count)++; - return 0; -} - -/** - * dev_unicast_delete - Release secondary unicast address. - * @dev: device - * @addr: address to delete - * - * Release reference to a secondary unicast address and remove it - * from the device if the reference count drops to zero. - * - * The caller must hold the rtnl_mutex. - */ -int dev_unicast_delete(struct net_device *dev, void *addr) -{ - int err; - - ASSERT_RTNL(); - - netif_addr_lock_bh(dev); - err = __hw_addr_del(&dev->uc, addr, dev->addr_len, - NETDEV_HW_ADDR_T_UNICAST); - if (!err) - __dev_set_rx_mode(dev); - netif_addr_unlock_bh(dev); - return err; -} -EXPORT_SYMBOL(dev_unicast_delete); - -/** - * dev_unicast_add - add a secondary unicast address - * @dev: device - * @addr: address to add - * - * Add a secondary unicast address to the device or increase - * the reference count if it already exists. - * - * The caller must hold the rtnl_mutex. - */ -int dev_unicast_add(struct net_device *dev, void *addr) -{ - int err; - - ASSERT_RTNL(); - - netif_addr_lock_bh(dev); - err = __hw_addr_add(&dev->uc, addr, dev->addr_len, - NETDEV_HW_ADDR_T_UNICAST); - if (!err) - __dev_set_rx_mode(dev); - netif_addr_unlock_bh(dev); - return err; -} -EXPORT_SYMBOL(dev_unicast_add); - -int __dev_addr_sync(struct dev_addr_list **to, int *to_count, - struct dev_addr_list **from, int *from_count) -{ - struct dev_addr_list *da, *next; - int err = 0; - - da = *from; - while (da != NULL) { - next = da->next; - if (!da->da_synced) { - err = __dev_addr_add(to, to_count, - da->da_addr, da->da_addrlen, 0); - if (err < 0) - break; - da->da_synced = 1; - da->da_users++; - } else if (da->da_users == 1) { - __dev_addr_delete(to, to_count, - da->da_addr, da->da_addrlen, 0); - __dev_addr_delete(from, from_count, - da->da_addr, da->da_addrlen, 0); - } - da = next; - } - return err; -} -EXPORT_SYMBOL_GPL(__dev_addr_sync); - -void __dev_addr_unsync(struct dev_addr_list **to, int *to_count, - struct dev_addr_list **from, int *from_count) -{ - struct dev_addr_list *da, *next; - - da = *from; - while (da != NULL) { - next = da->next; - if (da->da_synced) { - __dev_addr_delete(to, to_count, - da->da_addr, da->da_addrlen, 0); - da->da_synced = 0; - __dev_addr_delete(from, from_count, - da->da_addr, da->da_addrlen, 0); - } - da = next; - } -} -EXPORT_SYMBOL_GPL(__dev_addr_unsync); - -/** - * dev_unicast_sync - Synchronize device's unicast list to another device - * @to: destination device - * @from: source device - * - * Add newly added addresses to the destination device and release - * addresses that have no users left. The source device must be - * locked by netif_tx_lock_bh. - * - * This function is intended to be called from the dev->set_rx_mode - * function of layered software devices. - */ -int dev_unicast_sync(struct net_device *to, struct net_device *from) -{ - int err = 0; - - if (to->addr_len != from->addr_len) - return -EINVAL; - - netif_addr_lock_bh(to); - err = __hw_addr_sync(&to->uc, &from->uc, to->addr_len); - if (!err) - __dev_set_rx_mode(to); - netif_addr_unlock_bh(to); - return err; -} -EXPORT_SYMBOL(dev_unicast_sync); - -/** - * dev_unicast_unsync - Remove synchronized addresses from the destination device - * @to: destination device - * @from: source device - * - * Remove all addresses that were added to the destination device by - * dev_unicast_sync(). This function is intended to be called from the - * dev->stop function of layered software devices. - */ -void dev_unicast_unsync(struct net_device *to, struct net_device *from) -{ - if (to->addr_len != from->addr_len) - return; - - netif_addr_lock_bh(from); - netif_addr_lock(to); - __hw_addr_unsync(&to->uc, &from->uc, to->addr_len); - __dev_set_rx_mode(to); - netif_addr_unlock(to); - netif_addr_unlock_bh(from); -} -EXPORT_SYMBOL(dev_unicast_unsync); - -static void dev_unicast_flush(struct net_device *dev) -{ - netif_addr_lock_bh(dev); - __hw_addr_flush(&dev->uc); - netif_addr_unlock_bh(dev); -} - -static void dev_unicast_init(struct net_device *dev) -{ - __hw_addr_init(&dev->uc); -} - - -static void __dev_addr_discard(struct dev_addr_list **list) -{ - struct dev_addr_list *tmp; - - while (*list != NULL) { - tmp = *list; - *list = tmp->next; - if (tmp->da_users > tmp->da_gusers) - printk("__dev_addr_discard: address leakage! " - "da_users=%d\n", tmp->da_users); - kfree(tmp); - } -} - -static void dev_addr_discard(struct net_device *dev) -{ - netif_addr_lock_bh(dev); - - __dev_addr_discard(&dev->mc_list); - netdev_mc_count(dev) = 0; - - netif_addr_unlock_bh(dev); -} - /** * dev_get_flags - get flags reported to userspace * @dev: device @@ -4780,8 +4409,7 @@ static int dev_ifsioc(struct net *net, struct ifreq *ifr, unsigned int cmd) return -EINVAL; if (!netif_device_present(dev)) return -ENODEV; - return dev_mc_add(dev, ifr->ifr_hwaddr.sa_data, - dev->addr_len, 1); + return dev_mc_add_global(dev, ifr->ifr_hwaddr.sa_data); case SIOCDELMULTI: if ((!ops->ndo_set_multicast_list && !ops->ndo_set_rx_mode) || @@ -4789,8 +4417,7 @@ static int dev_ifsioc(struct net *net, struct ifreq *ifr, unsigned int cmd) return -EINVAL; if (!netif_device_present(dev)) return -ENODEV; - return dev_mc_delete(dev, ifr->ifr_hwaddr.sa_data, - dev->addr_len, 1); + return dev_mc_del_global(dev, ifr->ifr_hwaddr.sa_data); case SIOCSIFTXQLEN: if (ifr->ifr_qlen < 0) @@ -5097,8 +4724,8 @@ static void rollback_registered_many(struct list_head *head) /* * Flush the unicast and multicast chains */ - dev_unicast_flush(dev); - dev_addr_discard(dev); + dev_uc_flush(dev); + dev_mc_flush(dev); if (dev->netdev_ops->ndo_uninit) dev->netdev_ops->ndo_uninit(dev); @@ -5247,6 +4874,7 @@ int register_netdevice(struct net_device *dev) dev->iflink = -1; +#ifdef CONFIG_RPS if (!dev->num_rx_queues) { /* * Allocate a single RX queue if driver never called @@ -5263,7 +4891,7 @@ int register_netdevice(struct net_device *dev) atomic_set(&dev->_rx->count, 1); dev->num_rx_queues = 1; } - +#endif /* Init, if this function is available */ if (dev->netdev_ops->ndo_init) { ret = dev->netdev_ops->ndo_init(dev); @@ -5621,11 +5249,13 @@ struct net_device *alloc_netdev_mq(int sizeof_priv, const char *name, void (*setup)(struct net_device *), unsigned int queue_count) { struct netdev_queue *tx; - struct netdev_rx_queue *rx; struct net_device *dev; size_t alloc_size; struct net_device *p; +#ifdef CONFIG_RPS + struct netdev_rx_queue *rx; int i; +#endif BUG_ON(strlen(name) >= sizeof(dev->name)); @@ -5651,6 +5281,7 @@ struct net_device *alloc_netdev_mq(int sizeof_priv, const char *name, goto free_p; } +#ifdef CONFIG_RPS rx = kcalloc(queue_count, sizeof(struct netdev_rx_queue), GFP_KERNEL); if (!rx) { printk(KERN_ERR "alloc_netdev: Unable to allocate " @@ -5666,6 +5297,7 @@ struct net_device *alloc_netdev_mq(int sizeof_priv, const char *name, */ for (i = 0; i < queue_count; i++) rx[i].first = rx; +#endif dev = PTR_ALIGN(p, NETDEV_ALIGN); dev->padded = (char *)dev - (char *)p; @@ -5673,7 +5305,8 @@ struct net_device *alloc_netdev_mq(int sizeof_priv, const char *name, if (dev_addr_init(dev)) goto free_rx; - dev_unicast_init(dev); + dev_mc_init(dev); + dev_uc_init(dev); dev_net_set(dev, &init_net); @@ -5681,8 +5314,10 @@ struct net_device *alloc_netdev_mq(int sizeof_priv, const char *name, dev->num_tx_queues = queue_count; dev->real_num_tx_queues = queue_count; +#ifdef CONFIG_RPS dev->_rx = rx; dev->num_rx_queues = queue_count; +#endif dev->gso_max_size = GSO_MAX_SIZE; @@ -5699,8 +5334,10 @@ struct net_device *alloc_netdev_mq(int sizeof_priv, const char *name, return dev; free_rx: +#ifdef CONFIG_RPS kfree(rx); free_tx: +#endif kfree(tx); free_p: kfree(p); @@ -5903,8 +5540,8 @@ int dev_change_net_namespace(struct net_device *dev, struct net *net, const char /* * Flush the unicast and multicast chains */ - dev_unicast_flush(dev); - dev_addr_discard(dev); + dev_uc_flush(dev); + dev_mc_flush(dev); netdev_unregister_kobject(dev); @@ -5980,8 +5617,10 @@ static int dev_cpu_callback(struct notifier_block *nfb, local_irq_enable(); /* Process offline CPU's input_pkt_queue */ - while ((skb = __skb_dequeue(&oldsd->input_pkt_queue))) + while ((skb = __skb_dequeue(&oldsd->input_pkt_queue))) { netif_rx(skb); + input_queue_head_incr(oldsd); + } return NOTIFY_OK; } @@ -6197,21 +5836,23 @@ static int __init net_dev_init(void) */ for_each_possible_cpu(i) { - struct softnet_data *queue; + struct softnet_data *sd = &per_cpu(softnet_data, i); - queue = &per_cpu(softnet_data, i); - skb_queue_head_init(&queue->input_pkt_queue); - queue->completion_queue = NULL; - INIT_LIST_HEAD(&queue->poll_list); + skb_queue_head_init(&sd->input_pkt_queue); + sd->completion_queue = NULL; + INIT_LIST_HEAD(&sd->poll_list); - queue->csd.func = trigger_softirq; - queue->csd.info = queue; - queue->csd.flags = 0; +#ifdef CONFIG_RPS + sd->csd.func = rps_trigger_softirq; + sd->csd.info = sd; + sd->csd.flags = 0; + sd->cpu = i; +#endif - queue->backlog.poll = process_backlog; - queue->backlog.weight = weight_p; - queue->backlog.gro_list = NULL; - queue->backlog.gro_count = 0; + sd->backlog.poll = process_backlog; + sd->backlog.weight = weight_p; + sd->backlog.gro_list = NULL; + sd->backlog.gro_count = 0; } dev_boot_phase = 0; diff --git a/net/core/dev_addr_lists.c b/net/core/dev_addr_lists.c new file mode 100644 index 000000000000..508f9c18992f --- /dev/null +++ b/net/core/dev_addr_lists.c @@ -0,0 +1,741 @@ +/* + * net/core/dev_addr_lists.c - Functions for handling net device lists + * Copyright (c) 2010 Jiri Pirko <jpirko@redhat.com> + * + * This file contains functions for working with unicast, multicast and device + * addresses lists. + * + * 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. + */ + +#include <linux/netdevice.h> +#include <linux/rtnetlink.h> +#include <linux/list.h> +#include <linux/proc_fs.h> + +/* + * General list handling functions + */ + +static int __hw_addr_add_ex(struct netdev_hw_addr_list *list, + unsigned char *addr, int addr_len, + unsigned char addr_type, bool global) +{ + struct netdev_hw_addr *ha; + int alloc_size; + + if (addr_len > MAX_ADDR_LEN) + return -EINVAL; + + list_for_each_entry(ha, &list->list, list) { + if (!memcmp(ha->addr, addr, addr_len) && + ha->type == addr_type) { + if (global) { + /* check if addr is already used as global */ + if (ha->global_use) + return 0; + else + ha->global_use = true; + } + ha->refcount++; + return 0; + } + } + + + alloc_size = sizeof(*ha); + if (alloc_size < L1_CACHE_BYTES) + alloc_size = L1_CACHE_BYTES; + ha = kmalloc(alloc_size, GFP_ATOMIC); + if (!ha) + return -ENOMEM; + memcpy(ha->addr, addr, addr_len); + ha->type = addr_type; + ha->refcount = 1; + ha->global_use = global; + ha->synced = false; + list_add_tail_rcu(&ha->list, &list->list); + list->count++; + return 0; +} + +static int __hw_addr_add(struct netdev_hw_addr_list *list, unsigned char *addr, + int addr_len, unsigned char addr_type) +{ + return __hw_addr_add_ex(list, addr, addr_len, addr_type, false); +} + +static void ha_rcu_free(struct rcu_head *head) +{ + struct netdev_hw_addr *ha; + + ha = container_of(head, struct netdev_hw_addr, rcu_head); + kfree(ha); +} + +static int __hw_addr_del_ex(struct netdev_hw_addr_list *list, + unsigned char *addr, int addr_len, + unsigned char addr_type, bool global) +{ + struct netdev_hw_addr *ha; + + list_for_each_entry(ha, &list->list, list) { + if (!memcmp(ha->addr, addr, addr_len) && + (ha->type == addr_type || !addr_type)) { + if (global) { + if (!ha->global_use) + break; + else + ha->global_use = false; + } + if (--ha->refcount) + return 0; + list_del_rcu(&ha->list); + call_rcu(&ha->rcu_head, ha_rcu_free); + list->count--; + return 0; + } + } + return -ENOENT; +} + +static int __hw_addr_del(struct netdev_hw_addr_list *list, unsigned char *addr, + int addr_len, unsigned char addr_type) +{ + return __hw_addr_del_ex(list, addr, addr_len, addr_type, false); +} + +int __hw_addr_add_multiple(struct netdev_hw_addr_list *to_list, + struct netdev_hw_addr_list *from_list, + int addr_len, unsigned char addr_type) +{ + int err; + struct netdev_hw_addr *ha, *ha2; + unsigned char type; + + list_for_each_entry(ha, &from_list->list, list) { + type = addr_type ? addr_type : ha->type; + err = __hw_addr_add(to_list, ha->addr, addr_len, type); + if (err) + goto unroll; + } + return 0; + +unroll: + list_for_each_entry(ha2, &from_list->list, list) { + if (ha2 == ha) + break; + type = addr_type ? addr_type : ha2->type; + __hw_addr_del(to_list, ha2->addr, addr_len, type); + } + return err; +} +EXPORT_SYMBOL(__hw_addr_add_multiple); + +void __hw_addr_del_multiple(struct netdev_hw_addr_list *to_list, + struct netdev_hw_addr_list *from_list, + int addr_len, unsigned char addr_type) +{ + struct netdev_hw_addr *ha; + unsigned char type; + + list_for_each_entry(ha, &from_list->list, list) { + type = addr_type ? addr_type : ha->type; + __hw_addr_del(to_list, ha->addr, addr_len, addr_type); + } +} +EXPORT_SYMBOL(__hw_addr_del_multiple); + +int __hw_addr_sync(struct netdev_hw_addr_list *to_list, + struct netdev_hw_addr_list *from_list, + int addr_len) +{ + int err = 0; + struct netdev_hw_addr *ha, *tmp; + + list_for_each_entry_safe(ha, tmp, &from_list->list, list) { + if (!ha->synced) { + err = __hw_addr_add(to_list, ha->addr, + addr_len, ha->type); + if (err) + break; + ha->synced = true; + ha->refcount++; + } else if (ha->refcount == 1) { + __hw_addr_del(to_list, ha->addr, addr_len, ha->type); + __hw_addr_del(from_list, ha->addr, addr_len, ha->type); + } + } + return err; +} +EXPORT_SYMBOL(__hw_addr_sync); + +void __hw_addr_unsync(struct netdev_hw_addr_list *to_list, + struct netdev_hw_addr_list *from_list, + int addr_len) +{ + struct netdev_hw_addr *ha, *tmp; + + list_for_each_entry_safe(ha, tmp, &from_list->list, list) { + if (ha->synced) { + __hw_addr_del(to_list, ha->addr, + addr_len, ha->type); + ha->synced = false; + __hw_addr_del(from_list, ha->addr, + addr_len, ha->type); + } + } +} +EXPORT_SYMBOL(__hw_addr_unsync); + +void __hw_addr_flush(struct netdev_hw_addr_list *list) +{ + struct netdev_hw_addr *ha, *tmp; + + list_for_each_entry_safe(ha, tmp, &list->list, list) { + list_del_rcu(&ha->list); + call_rcu(&ha->rcu_head, ha_rcu_free); + } + list->count = 0; +} +EXPORT_SYMBOL(__hw_addr_flush); + +void __hw_addr_init(struct netdev_hw_addr_list *list) +{ + INIT_LIST_HEAD(&list->list); + list->count = 0; +} +EXPORT_SYMBOL(__hw_addr_init); + +/* + * Device addresses handling functions + */ + +/** + * dev_addr_flush - Flush device address list + * @dev: device + * + * Flush device address list and reset ->dev_addr. + * + * The caller must hold the rtnl_mutex. + */ +void dev_addr_flush(struct net_device *dev) +{ + /* rtnl_mutex must be held here */ + + __hw_addr_flush(&dev->dev_addrs); + dev->dev_addr = NULL; +} +EXPORT_SYMBOL(dev_addr_flush); + +/** + * dev_addr_init - Init device address list + * @dev: device + * + * Init device address list and create the first element, + * used by ->dev_addr. + * + * The caller must hold the rtnl_mutex. + */ +int dev_addr_init(struct net_device *dev) +{ + unsigned char addr[MAX_ADDR_LEN]; + struct netdev_hw_addr *ha; + int err; + + /* rtnl_mutex must be held here */ + + __hw_addr_init(&dev->dev_addrs); + memset(addr, 0, sizeof(addr)); + err = __hw_addr_add(&dev->dev_addrs, addr, sizeof(addr), + NETDEV_HW_ADDR_T_LAN); + if (!err) { + /* + * Get the first (previously created) address from the list + * and set dev_addr pointer to this location. + */ + ha = list_first_entry(&dev->dev_addrs.list, + struct netdev_hw_addr, list); + dev->dev_addr = ha->addr; + } + return err; +} +EXPORT_SYMBOL(dev_addr_init); + +/** + * dev_addr_add - Add a device address + * @dev: device + * @addr: address to add + * @addr_type: address type + * + * Add a device address to the device or increase the reference count if + * it already exists. + * + * The caller must hold the rtnl_mutex. + */ +int dev_addr_add(struct net_device *dev, unsigned char *addr, + unsigned char addr_type) +{ + int err; + + ASSERT_RTNL(); + + err = __hw_addr_add(&dev->dev_addrs, addr, dev->addr_len, addr_type); + if (!err) + call_netdevice_notifiers(NETDEV_CHANGEADDR, dev); + return err; +} +EXPORT_SYMBOL(dev_addr_add); + +/** + * dev_addr_del - Release a device address. + * @dev: device + * @addr: address to delete + * @addr_type: address type + * + * Release reference to a device address and remove it from the device + * if the reference count drops to zero. + * + * The caller must hold the rtnl_mutex. + */ +int dev_addr_del(struct net_device *dev, unsigned char *addr, + unsigned char addr_type) +{ + int err; + struct netdev_hw_addr *ha; + + ASSERT_RTNL(); + + /* + * We can not remove the first address from the list because + * dev->dev_addr points to that. + */ + ha = list_first_entry(&dev->dev_addrs.list, + struct netdev_hw_addr, list); + if (ha->addr == dev->dev_addr && ha->refcount == 1) + return -ENOENT; + + err = __hw_addr_del(&dev->dev_addrs, addr, dev->addr_len, + addr_type); + if (!err) + call_netdevice_notifiers(NETDEV_CHANGEADDR, dev); + return err; +} +EXPORT_SYMBOL(dev_addr_del); + +/** + * dev_addr_add_multiple - Add device addresses from another device + * @to_dev: device to which addresses will be added + * @from_dev: device from which addresses will be added + * @addr_type: address type - 0 means type will be used from from_dev + * + * Add device addresses of the one device to another. + ** + * The caller must hold the rtnl_mutex. + */ +int dev_addr_add_multiple(struct net_device *to_dev, + struct net_device *from_dev, + unsigned char addr_type) +{ + int err; + + ASSERT_RTNL(); + + if (from_dev->addr_len != to_dev->addr_len) + return -EINVAL; + err = __hw_addr_add_multiple(&to_dev->dev_addrs, &from_dev->dev_addrs, + to_dev->addr_len, addr_type); + if (!err) + call_netdevice_notifiers(NETDEV_CHANGEADDR, to_dev); + return err; +} +EXPORT_SYMBOL(dev_addr_add_multiple); + +/** + * dev_addr_del_multiple - Delete device addresses by another device + * @to_dev: device where the addresses will be deleted + * @from_dev: device by which addresses the addresses will be deleted + * @addr_type: address type - 0 means type will used from from_dev + * + * Deletes addresses in to device by the list of addresses in from device. + * + * The caller must hold the rtnl_mutex. + */ +int dev_addr_del_multiple(struct net_device *to_dev, + struct net_device *from_dev, + unsigned char addr_type) +{ + ASSERT_RTNL(); + + if (from_dev->addr_len != to_dev->addr_len) + return -EINVAL; + __hw_addr_del_multiple(&to_dev->dev_addrs, &from_dev->dev_addrs, + to_dev->addr_len, addr_type); + call_netdevice_notifiers(NETDEV_CHANGEADDR, to_dev); + return 0; +} +EXPORT_SYMBOL(dev_addr_del_multiple); + +/* + * Unicast list handling functions + */ + +/** + * dev_uc_add - Add a secondary unicast address + * @dev: device + * @addr: address to add + * + * Add a secondary unicast address to the device or increase + * the reference count if it already exists. + */ +int dev_uc_add(struct net_device *dev, unsigned char *addr) +{ + int err; + + netif_addr_lock_bh(dev); + err = __hw_addr_add(&dev->uc, addr, dev->addr_len, + NETDEV_HW_ADDR_T_UNICAST); + if (!err) + __dev_set_rx_mode(dev); + netif_addr_unlock_bh(dev); + return err; +} +EXPORT_SYMBOL(dev_uc_add); + +/** + * dev_uc_del - Release secondary unicast address. + * @dev: device + * @addr: address to delete + * + * Release reference to a secondary unicast address and remove it + * from the device if the reference count drops to zero. + */ +int dev_uc_del(struct net_device *dev, unsigned char *addr) +{ + int err; + + netif_addr_lock_bh(dev); + err = __hw_addr_del(&dev->uc, addr, dev->addr_len, + NETDEV_HW_ADDR_T_UNICAST); + if (!err) + __dev_set_rx_mode(dev); + netif_addr_unlock_bh(dev); + return err; +} +EXPORT_SYMBOL(dev_uc_del); + +/** + * dev_uc_sync - Synchronize device's unicast list to another device + * @to: destination device + * @from: source device + * + * Add newly added addresses to the destination device and release + * addresses that have no users left. The source device must be + * locked by netif_tx_lock_bh. + * + * This function is intended to be called from the dev->set_rx_mode + * function of layered software devices. + */ +int dev_uc_sync(struct net_device *to, struct net_device *from) +{ + int err = 0; + + if (to->addr_len != from->addr_len) + return -EINVAL; + + netif_addr_lock_bh(to); + err = __hw_addr_sync(&to->uc, &from->uc, to->addr_len); + if (!err) + __dev_set_rx_mode(to); + netif_addr_unlock_bh(to); + return err; +} +EXPORT_SYMBOL(dev_uc_sync); + +/** + * dev_uc_unsync - Remove synchronized addresses from the destination device + * @to: destination device + * @from: source device + * + * Remove all addresses that were added to the destination device by + * dev_uc_sync(). This function is intended to be called from the + * dev->stop function of layered software devices. + */ +void dev_uc_unsync(struct net_device *to, struct net_device *from) +{ + if (to->addr_len != from->addr_len) + return; + + netif_addr_lock_bh(from); + netif_addr_lock(to); + __hw_addr_unsync(&to->uc, &from->uc, to->addr_len); + __dev_set_rx_mode(to); + netif_addr_unlock(to); + netif_addr_unlock_bh(from); +} +EXPORT_SYMBOL(dev_uc_unsync); + +/** + * dev_uc_flush - Flush unicast addresses + * @dev: device + * + * Flush unicast addresses. + */ +void dev_uc_flush(struct net_device *dev) +{ + netif_addr_lock_bh(dev); + __hw_addr_flush(&dev->uc); + netif_addr_unlock_bh(dev); +} +EXPORT_SYMBOL(dev_uc_flush); + +/** + * dev_uc_flush - Init unicast address list + * @dev: device + * + * Init unicast address list. + */ +void dev_uc_init(struct net_device *dev) +{ + __hw_addr_init(&dev->uc); +} +EXPORT_SYMBOL(dev_uc_init); + +/* + * Multicast list handling functions + */ + +static int __dev_mc_add(struct net_device *dev, unsigned char *addr, + bool global) +{ + int err; + + netif_addr_lock_bh(dev); + err = __hw_addr_add_ex(&dev->mc, addr, dev->addr_len, + NETDEV_HW_ADDR_T_MULTICAST, global); + if (!err) + __dev_set_rx_mode(dev); + netif_addr_unlock_bh(dev); + return err; +} +/** + * dev_mc_add - Add a multicast address + * @dev: device + * @addr: address to add + * + * Add a multicast address to the device or increase + * the reference count if it already exists. + */ +int dev_mc_add(struct net_device *dev, unsigned char *addr) +{ + return __dev_mc_add(dev, addr, false); +} +EXPORT_SYMBOL(dev_mc_add); + +/** + * dev_mc_add_global - Add a global multicast address + * @dev: device + * @addr: address to add + * + * Add a global multicast address to the device. + */ +int dev_mc_add_global(struct net_device *dev, unsigned char *addr) +{ + return __dev_mc_add(dev, addr, true); +} +EXPORT_SYMBOL(dev_mc_add_global); + +static int __dev_mc_del(struct net_device *dev, unsigned char *addr, + bool global) +{ + int err; + + netif_addr_lock_bh(dev); + err = __hw_addr_del_ex(&dev->mc, addr, dev->addr_len, + NETDEV_HW_ADDR_T_MULTICAST, global); + if (!err) + __dev_set_rx_mode(dev); + netif_addr_unlock_bh(dev); + return err; +} + +/** + * dev_mc_del - Delete a multicast address. + * @dev: device + * @addr: address to delete + * + * Release reference to a multicast address and remove it + * from the device if the reference count drops to zero. + */ +int dev_mc_del(struct net_device *dev, unsigned char *addr) +{ + return __dev_mc_del(dev, addr, false); +} +EXPORT_SYMBOL(dev_mc_del); + +/** + * dev_mc_del_global - Delete a global multicast address. + * @dev: device + * @addr: address to delete + * + * Release reference to a multicast address and remove it + * from the device if the reference count drops to zero. + */ +int dev_mc_del_global(struct net_device *dev, unsigned char *addr) +{ + return __dev_mc_del(dev, addr, true); +} +EXPORT_SYMBOL(dev_mc_del_global); + +/** + * dev_mc_sync - Synchronize device's unicast list to another device + * @to: destination device + * @from: source device + * + * Add newly added addresses to the destination device and release + * addresses that have no users left. The source device must be + * locked by netif_tx_lock_bh. + * + * This function is intended to be called from the dev->set_multicast_list + * or dev->set_rx_mode function of layered software devices. + */ +int dev_mc_sync(struct net_device *to, struct net_device *from) +{ + int err = 0; + + if (to->addr_len != from->addr_len) + return -EINVAL; + + netif_addr_lock_bh(to); + err = __hw_addr_sync(&to->mc, &from->mc, to->addr_len); + if (!err) + __dev_set_rx_mode(to); + netif_addr_unlock_bh(to); + return err; +} +EXPORT_SYMBOL(dev_mc_sync); + +/** + * dev_mc_unsync - Remove synchronized addresses from the destination device + * @to: destination device + * @from: source device + * + * Remove all addresses that were added to the destination device by + * dev_mc_sync(). This function is intended to be called from the + * dev->stop function of layered software devices. + */ +void dev_mc_unsync(struct net_device *to, struct net_device *from) +{ + if (to->addr_len != from->addr_len) + return; + + netif_addr_lock_bh(from); + netif_addr_lock(to); + __hw_addr_unsync(&to->mc, &from->mc, to->addr_len); + __dev_set_rx_mode(to); + netif_addr_unlock(to); + netif_addr_unlock_bh(from); +} +EXPORT_SYMBOL(dev_mc_unsync); + +/** + * dev_mc_flush - Flush multicast addresses + * @dev: device + * + * Flush multicast addresses. + */ +void dev_mc_flush(struct net_device *dev) +{ + netif_addr_lock_bh(dev); + __hw_addr_flush(&dev->mc); + netif_addr_unlock_bh(dev); +} +EXPORT_SYMBOL(dev_mc_flush); + +/** + * dev_mc_flush - Init multicast address list + * @dev: device + * + * Init multicast address list. + */ +void dev_mc_init(struct net_device *dev) +{ + __hw_addr_init(&dev->mc); +} +EXPORT_SYMBOL(dev_mc_init); + +#ifdef CONFIG_PROC_FS +#include <linux/seq_file.h> + +static int dev_mc_seq_show(struct seq_file *seq, void *v) +{ + struct netdev_hw_addr *ha; + struct net_device *dev = v; + + if (v == SEQ_START_TOKEN) + return 0; + + netif_addr_lock_bh(dev); + netdev_for_each_mc_addr(ha, dev) { + int i; + + seq_printf(seq, "%-4d %-15s %-5d %-5d ", dev->ifindex, + dev->name, ha->refcount, ha->global_use); + + for (i = 0; i < dev->addr_len; i++) + seq_printf(seq, "%02x", ha->addr[i]); + + seq_putc(seq, '\n'); + } + netif_addr_unlock_bh(dev); + return 0; +} + +static const struct seq_operations dev_mc_seq_ops = { + .start = dev_seq_start, + .next = dev_seq_next, + .stop = dev_seq_stop, + .show = dev_mc_seq_show, +}; + +static int dev_mc_seq_open(struct inode *inode, struct file *file) +{ + return seq_open_net(inode, file, &dev_mc_seq_ops, + sizeof(struct seq_net_private)); +} + +static const struct file_operations dev_mc_seq_fops = { + .owner = THIS_MODULE, + .open = dev_mc_seq_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release_net, +}; + +#endif + +static int __net_init dev_mc_net_init(struct net *net) +{ + if (!proc_net_fops_create(net, "dev_mcast", 0, &dev_mc_seq_fops)) + return -ENOMEM; + return 0; +} + +static void __net_exit dev_mc_net_exit(struct net *net) +{ + proc_net_remove(net, "dev_mcast"); +} + +static struct pernet_operations __net_initdata dev_mc_net_ops = { + .init = dev_mc_net_init, + .exit = dev_mc_net_exit, +}; + +void __init dev_mcast_init(void) +{ + register_pernet_subsys(&dev_mc_net_ops); +} + diff --git a/net/core/dev_mcast.c b/net/core/dev_mcast.c deleted file mode 100644 index 3dc295beb483..000000000000 --- a/net/core/dev_mcast.c +++ /dev/null @@ -1,232 +0,0 @@ -/* - * Linux NET3: Multicast List maintenance. - * - * Authors: - * Tim Kordas <tjk@nostromo.eeap.cwru.edu> - * Richard Underwood <richard@wuzz.demon.co.uk> - * - * Stir fried together from the IP multicast and CAP patches above - * Alan Cox <alan@lxorguk.ukuu.org.uk> - * - * Fixes: - * Alan Cox : Update the device on a real delete - * rather than any time but... - * Alan Cox : IFF_ALLMULTI support. - * Alan Cox : New format set_multicast_list() calls. - * Gleb Natapov : Remove dev_mc_lock. - * - * 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. - */ - -#include <linux/module.h> -#include <asm/uaccess.h> -#include <asm/system.h> -#include <linux/bitops.h> -#include <linux/types.h> -#include <linux/kernel.h> -#include <linux/string.h> -#include <linux/mm.h> -#include <linux/socket.h> -#include <linux/sockios.h> -#include <linux/in.h> -#include <linux/errno.h> -#include <linux/interrupt.h> -#include <linux/if_ether.h> -#include <linux/inet.h> -#include <linux/netdevice.h> -#include <linux/etherdevice.h> -#include <linux/proc_fs.h> -#include <linux/seq_file.h> -#include <linux/init.h> -#include <net/net_namespace.h> -#include <net/ip.h> -#include <net/route.h> -#include <linux/skbuff.h> -#include <net/sock.h> -#include <net/arp.h> - - -/* - * Device multicast list maintenance. - * - * This is used both by IP and by the user level maintenance functions. - * Unlike BSD we maintain a usage count on a given multicast address so - * that a casual user application can add/delete multicasts used by - * protocols without doing damage to the protocols when it deletes the - * entries. It also helps IP as it tracks overlapping maps. - * - * Device mc lists are changed by bh at least if IPv6 is enabled, - * so that it must be bh protected. - * - * We block accesses to device mc filters with netif_tx_lock. - */ - -/* - * Delete a device level multicast - */ - -int dev_mc_delete(struct net_device *dev, void *addr, int alen, int glbl) -{ - int err; - - netif_addr_lock_bh(dev); - err = __dev_addr_delete(&dev->mc_list, &dev->mc_count, - addr, alen, glbl); - if (!err) { - /* - * We have altered the list, so the card - * loaded filter is now wrong. Fix it - */ - - __dev_set_rx_mode(dev); - } - netif_addr_unlock_bh(dev); - return err; -} - -/* - * Add a device level multicast - */ - -int dev_mc_add(struct net_device *dev, void *addr, int alen, int glbl) -{ - int err; - - netif_addr_lock_bh(dev); - if (alen != dev->addr_len) - err = -EINVAL; - else - err = __dev_addr_add(&dev->mc_list, &dev->mc_count, addr, alen, glbl); - if (!err) - __dev_set_rx_mode(dev); - netif_addr_unlock_bh(dev); - return err; -} - -/** - * dev_mc_sync - Synchronize device's multicast list to another device - * @to: destination device - * @from: source device - * - * Add newly added addresses to the destination device and release - * addresses that have no users left. The source device must be - * locked by netif_tx_lock_bh. - * - * This function is intended to be called from the dev->set_multicast_list - * or dev->set_rx_mode function of layered software devices. - */ -int dev_mc_sync(struct net_device *to, struct net_device *from) -{ - int err = 0; - - netif_addr_lock_bh(to); - err = __dev_addr_sync(&to->mc_list, &to->mc_count, - &from->mc_list, &from->mc_count); - if (!err) - __dev_set_rx_mode(to); - netif_addr_unlock_bh(to); - - return err; -} -EXPORT_SYMBOL(dev_mc_sync); - - -/** - * dev_mc_unsync - Remove synchronized addresses from the destination - * device - * @to: destination device - * @from: source device - * - * Remove all addresses that were added to the destination device by - * dev_mc_sync(). This function is intended to be called from the - * dev->stop function of layered software devices. - */ -void dev_mc_unsync(struct net_device *to, struct net_device *from) -{ - netif_addr_lock_bh(from); - netif_addr_lock(to); - - __dev_addr_unsync(&to->mc_list, &to->mc_count, - &from->mc_list, &from->mc_count); - __dev_set_rx_mode(to); - - netif_addr_unlock(to); - netif_addr_unlock_bh(from); -} -EXPORT_SYMBOL(dev_mc_unsync); - -#ifdef CONFIG_PROC_FS -static int dev_mc_seq_show(struct seq_file *seq, void *v) -{ - struct dev_addr_list *m; - struct net_device *dev = v; - - if (v == SEQ_START_TOKEN) - return 0; - - netif_addr_lock_bh(dev); - for (m = dev->mc_list; m; m = m->next) { - int i; - - seq_printf(seq, "%-4d %-15s %-5d %-5d ", dev->ifindex, - dev->name, m->dmi_users, m->dmi_gusers); - - for (i = 0; i < m->dmi_addrlen; i++) - seq_printf(seq, "%02x", m->dmi_addr[i]); - - seq_putc(seq, '\n'); - } - netif_addr_unlock_bh(dev); - return 0; -} - -static const struct seq_operations dev_mc_seq_ops = { - .start = dev_seq_start, - .next = dev_seq_next, - .stop = dev_seq_stop, - .show = dev_mc_seq_show, -}; - -static int dev_mc_seq_open(struct inode *inode, struct file *file) -{ - return seq_open_net(inode, file, &dev_mc_seq_ops, - sizeof(struct seq_net_private)); -} - -static const struct file_operations dev_mc_seq_fops = { - .owner = THIS_MODULE, - .open = dev_mc_seq_open, - .read = seq_read, - .llseek = seq_lseek, - .release = seq_release_net, -}; - -#endif - -static int __net_init dev_mc_net_init(struct net *net) -{ - if (!proc_net_fops_create(net, "dev_mcast", 0, &dev_mc_seq_fops)) - return -ENOMEM; - return 0; -} - -static void __net_exit dev_mc_net_exit(struct net *net) -{ - proc_net_remove(net, "dev_mcast"); -} - -static struct pernet_operations __net_initdata dev_mc_net_ops = { - .init = dev_mc_net_init, - .exit = dev_mc_net_exit, -}; - -void __init dev_mcast_init(void) -{ - register_pernet_subsys(&dev_mc_net_ops); -} - -EXPORT_SYMBOL(dev_mc_add); -EXPORT_SYMBOL(dev_mc_delete); diff --git a/net/core/drop_monitor.c b/net/core/drop_monitor.c index f8c874975350..cf208d8042b1 100644 --- a/net/core/drop_monitor.c +++ b/net/core/drop_monitor.c @@ -21,6 +21,7 @@ #include <linux/percpu.h> #include <linux/timer.h> #include <linux/bitops.h> +#include <linux/slab.h> #include <net/genetlink.h> #include <net/netevent.h> diff --git a/net/core/dst.c b/net/core/dst.c index cb1b3488b739..9920722cc82b 100644 --- a/net/core/dst.c +++ b/net/core/dst.c @@ -12,6 +12,7 @@ #include <linux/workqueue.h> #include <linux/mm.h> #include <linux/module.h> +#include <linux/slab.h> #include <linux/netdevice.h> #include <linux/skbuff.h> #include <linux/string.h> @@ -43,7 +44,7 @@ static atomic_t dst_total = ATOMIC_INIT(0); */ static struct { spinlock_t lock; - struct dst_entry *list; + struct dst_entry *list; unsigned long timer_inc; unsigned long timer_expires; } dst_garbage = { @@ -51,7 +52,7 @@ static struct { .timer_inc = DST_GC_MAX, }; static void dst_gc_task(struct work_struct *work); -static void ___dst_free(struct dst_entry * dst); +static void ___dst_free(struct dst_entry *dst); static DECLARE_DELAYED_WORK(dst_gc_work, dst_gc_task); @@ -135,8 +136,8 @@ loop: } expires = dst_garbage.timer_expires; /* - * if the next desired timer is more than 4 seconds in the future - * then round the timer to whole seconds + * if the next desired timer is more than 4 seconds in the + * future then round the timer to whole seconds */ if (expires > 4*HZ) expires = round_jiffies_relative(expires); @@ -151,7 +152,8 @@ loop: " expires: %lu elapsed: %lu us\n", atomic_read(&dst_total), delayed, work_performed, expires, - elapsed.tv_sec * USEC_PER_SEC + elapsed.tv_nsec / NSEC_PER_USEC); + elapsed.tv_sec * USEC_PER_SEC + + elapsed.tv_nsec / NSEC_PER_USEC); #endif } @@ -162,9 +164,9 @@ int dst_discard(struct sk_buff *skb) } EXPORT_SYMBOL(dst_discard); -void * dst_alloc(struct dst_ops * ops) +void *dst_alloc(struct dst_ops *ops) { - struct dst_entry * dst; + struct dst_entry *dst; if (ops->gc && atomic_read(&ops->entries) > ops->gc_thresh) { if (ops->gc(ops)) @@ -184,19 +186,20 @@ void * dst_alloc(struct dst_ops * ops) atomic_inc(&ops->entries); return dst; } +EXPORT_SYMBOL(dst_alloc); -static void ___dst_free(struct dst_entry * dst) +static void ___dst_free(struct dst_entry *dst) { /* The first case (dev==NULL) is required, when protocol module is unloaded. */ - if (dst->dev == NULL || !(dst->dev->flags&IFF_UP)) { + if (dst->dev == NULL || !(dst->dev->flags&IFF_UP)) dst->input = dst->output = dst_discard; - } dst->obsolete = 2; } +EXPORT_SYMBOL(__dst_free); -void __dst_free(struct dst_entry * dst) +void __dst_free(struct dst_entry *dst) { spin_lock_bh(&dst_garbage.lock); ___dst_free(dst); @@ -261,15 +264,16 @@ again: } return NULL; } +EXPORT_SYMBOL(dst_destroy); void dst_release(struct dst_entry *dst) { if (dst) { - int newrefcnt; + int newrefcnt; smp_mb__before_atomic_dec(); - newrefcnt = atomic_dec_return(&dst->__refcnt); - WARN_ON(newrefcnt < 0); + newrefcnt = atomic_dec_return(&dst->__refcnt); + WARN_ON(newrefcnt < 0); } } EXPORT_SYMBOL(dst_release); @@ -282,8 +286,8 @@ EXPORT_SYMBOL(dst_release); * * Commented and originally written by Alexey. */ -static inline void dst_ifdown(struct dst_entry *dst, struct net_device *dev, - int unregister) +static void dst_ifdown(struct dst_entry *dst, struct net_device *dev, + int unregister) { if (dst->ops->ifdown) dst->ops->ifdown(dst, dev, unregister); @@ -305,7 +309,8 @@ static inline void dst_ifdown(struct dst_entry *dst, struct net_device *dev, } } -static int dst_dev_event(struct notifier_block *this, unsigned long event, void *ptr) +static int dst_dev_event(struct notifier_block *this, unsigned long event, + void *ptr) { struct net_device *dev = ptr; struct dst_entry *dst, *last = NULL; @@ -328,9 +333,8 @@ static int dst_dev_event(struct notifier_block *this, unsigned long event, void last->next = dst; else dst_busy_list = dst; - for (; dst; dst = dst->next) { + for (; dst; dst = dst->next) dst_ifdown(dst, dev, event != NETDEV_DOWN); - } mutex_unlock(&dst_gc_mutex); break; } @@ -345,7 +349,3 @@ void __init dst_init(void) { register_netdevice_notifier(&dst_dev_notifier); } - -EXPORT_SYMBOL(__dst_free); -EXPORT_SYMBOL(dst_alloc); -EXPORT_SYMBOL(dst_destroy); diff --git a/net/core/ethtool.c b/net/core/ethtool.c index f4cb6b6299d9..1a7db92037fa 100644 --- a/net/core/ethtool.c +++ b/net/core/ethtool.c @@ -18,7 +18,8 @@ #include <linux/ethtool.h> #include <linux/netdevice.h> #include <linux/bitops.h> -#include <asm/uaccess.h> +#include <linux/uaccess.h> +#include <linux/slab.h> /* * Some useful ethtool_ops methods that're device independent. @@ -30,6 +31,7 @@ u32 ethtool_op_get_link(struct net_device *dev) { return netif_carrier_ok(dev) ? 1 : 0; } +EXPORT_SYMBOL(ethtool_op_get_link); u32 ethtool_op_get_rx_csum(struct net_device *dev) { @@ -62,6 +64,7 @@ int ethtool_op_set_tx_hw_csum(struct net_device *dev, u32 data) return 0; } +EXPORT_SYMBOL(ethtool_op_set_tx_hw_csum); int ethtool_op_set_tx_ipv6_csum(struct net_device *dev, u32 data) { @@ -72,11 +75,13 @@ int ethtool_op_set_tx_ipv6_csum(struct net_device *dev, u32 data) 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) { @@ -87,11 +92,13 @@ int ethtool_op_set_sg(struct net_device *dev, u32 data) 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) { @@ -102,11 +109,13 @@ int ethtool_op_set_tso(struct net_device *dev, u32 data) 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) { @@ -116,12 +125,13 @@ int ethtool_op_set_ufo(struct net_device *dev, u32 data) 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_NTUPLE); + (ETH_FLAG_LRO | ETH_FLAG_NTUPLE | ETH_FLAG_RXHASH); u32 ethtool_op_get_flags(struct net_device *dev) { @@ -132,6 +142,7 @@ u32 ethtool_op_get_flags(struct net_device *dev) return dev->features & flags_dup_features; } +EXPORT_SYMBOL(ethtool_op_get_flags); int ethtool_op_set_flags(struct net_device *dev, u32 data) { @@ -152,9 +163,15 @@ int ethtool_op_set_flags(struct net_device *dev, u32 data) features &= ~NETIF_F_NTUPLE; } + if (data & ETH_FLAG_RXHASH) + features |= NETIF_F_RXHASH; + else + features &= ~NETIF_F_RXHASH; + dev->features = features; return 0; } +EXPORT_SYMBOL(ethtool_op_set_flags); void ethtool_ntuple_flush(struct net_device *dev) { @@ -200,7 +217,8 @@ static int ethtool_set_settings(struct net_device *dev, void __user *useraddr) return dev->ethtool_ops->set_settings(dev, &cmd); } -static noinline_for_stack int ethtool_get_drvinfo(struct net_device *dev, void __user *useraddr) +static noinline_for_stack int ethtool_get_drvinfo(struct net_device *dev, + void __user *useraddr) { struct ethtool_drvinfo info; const struct ethtool_ops *ops = dev->ethtool_ops; @@ -240,7 +258,7 @@ static noinline_for_stack int ethtool_get_drvinfo(struct net_device *dev, void _ } static noinline_for_stack int ethtool_get_sset_info(struct net_device *dev, - void __user *useraddr) + void __user *useraddr) { struct ethtool_sset_info info; const struct ethtool_ops *ops = dev->ethtool_ops; @@ -299,7 +317,8 @@ out: return ret; } -static noinline_for_stack int ethtool_set_rxnfc(struct net_device *dev, void __user *useraddr) +static noinline_for_stack int ethtool_set_rxnfc(struct net_device *dev, + void __user *useraddr) { struct ethtool_rxnfc cmd; @@ -312,7 +331,8 @@ static noinline_for_stack int ethtool_set_rxnfc(struct net_device *dev, void __u return dev->ethtool_ops->set_rxnfc(dev, &cmd); } -static noinline_for_stack int ethtool_get_rxnfc(struct net_device *dev, void __user *useraddr) +static noinline_for_stack int ethtool_get_rxnfc(struct net_device *dev, + void __user *useraddr) { struct ethtool_rxnfc info; const struct ethtool_ops *ops = dev->ethtool_ops; @@ -357,8 +377,8 @@ err_out: } static void __rx_ntuple_filter_add(struct ethtool_rx_ntuple_list *list, - struct ethtool_rx_ntuple_flow_spec *spec, - struct ethtool_rx_ntuple_flow_spec_container *fsc) + struct ethtool_rx_ntuple_flow_spec *spec, + struct ethtool_rx_ntuple_flow_spec_container *fsc) { /* don't add filters forever */ @@ -384,7 +404,8 @@ static void __rx_ntuple_filter_add(struct ethtool_rx_ntuple_list *list, list->count++; } -static noinline_for_stack int ethtool_set_rx_ntuple(struct net_device *dev, void __user *useraddr) +static noinline_for_stack int ethtool_set_rx_ntuple(struct net_device *dev, + void __user *useraddr) { struct ethtool_rx_ntuple cmd; const struct ethtool_ops *ops = dev->ethtool_ops; @@ -509,125 +530,125 @@ static int ethtool_get_rx_ntuple(struct net_device *dev, void __user *useraddr) case UDP_V4_FLOW: case SCTP_V4_FLOW: sprintf(p, "\tSrc IP addr: 0x%x\n", - fsc->fs.h_u.tcp_ip4_spec.ip4src); + fsc->fs.h_u.tcp_ip4_spec.ip4src); p += ETH_GSTRING_LEN; num_strings++; sprintf(p, "\tSrc IP mask: 0x%x\n", - fsc->fs.m_u.tcp_ip4_spec.ip4src); + fsc->fs.m_u.tcp_ip4_spec.ip4src); p += ETH_GSTRING_LEN; num_strings++; sprintf(p, "\tDest IP addr: 0x%x\n", - fsc->fs.h_u.tcp_ip4_spec.ip4dst); + fsc->fs.h_u.tcp_ip4_spec.ip4dst); p += ETH_GSTRING_LEN; num_strings++; sprintf(p, "\tDest IP mask: 0x%x\n", - fsc->fs.m_u.tcp_ip4_spec.ip4dst); + fsc->fs.m_u.tcp_ip4_spec.ip4dst); p += ETH_GSTRING_LEN; num_strings++; sprintf(p, "\tSrc Port: %d, mask: 0x%x\n", - fsc->fs.h_u.tcp_ip4_spec.psrc, - fsc->fs.m_u.tcp_ip4_spec.psrc); + fsc->fs.h_u.tcp_ip4_spec.psrc, + fsc->fs.m_u.tcp_ip4_spec.psrc); p += ETH_GSTRING_LEN; num_strings++; sprintf(p, "\tDest Port: %d, mask: 0x%x\n", - fsc->fs.h_u.tcp_ip4_spec.pdst, - fsc->fs.m_u.tcp_ip4_spec.pdst); + fsc->fs.h_u.tcp_ip4_spec.pdst, + fsc->fs.m_u.tcp_ip4_spec.pdst); p += ETH_GSTRING_LEN; num_strings++; sprintf(p, "\tTOS: %d, mask: 0x%x\n", - fsc->fs.h_u.tcp_ip4_spec.tos, - fsc->fs.m_u.tcp_ip4_spec.tos); + fsc->fs.h_u.tcp_ip4_spec.tos, + fsc->fs.m_u.tcp_ip4_spec.tos); p += ETH_GSTRING_LEN; num_strings++; break; case AH_ESP_V4_FLOW: case ESP_V4_FLOW: sprintf(p, "\tSrc IP addr: 0x%x\n", - fsc->fs.h_u.ah_ip4_spec.ip4src); + fsc->fs.h_u.ah_ip4_spec.ip4src); p += ETH_GSTRING_LEN; num_strings++; sprintf(p, "\tSrc IP mask: 0x%x\n", - fsc->fs.m_u.ah_ip4_spec.ip4src); + fsc->fs.m_u.ah_ip4_spec.ip4src); p += ETH_GSTRING_LEN; num_strings++; sprintf(p, "\tDest IP addr: 0x%x\n", - fsc->fs.h_u.ah_ip4_spec.ip4dst); + fsc->fs.h_u.ah_ip4_spec.ip4dst); p += ETH_GSTRING_LEN; num_strings++; sprintf(p, "\tDest IP mask: 0x%x\n", - fsc->fs.m_u.ah_ip4_spec.ip4dst); + fsc->fs.m_u.ah_ip4_spec.ip4dst); p += ETH_GSTRING_LEN; num_strings++; sprintf(p, "\tSPI: %d, mask: 0x%x\n", - fsc->fs.h_u.ah_ip4_spec.spi, - fsc->fs.m_u.ah_ip4_spec.spi); + fsc->fs.h_u.ah_ip4_spec.spi, + fsc->fs.m_u.ah_ip4_spec.spi); p += ETH_GSTRING_LEN; num_strings++; sprintf(p, "\tTOS: %d, mask: 0x%x\n", - fsc->fs.h_u.ah_ip4_spec.tos, - fsc->fs.m_u.ah_ip4_spec.tos); + fsc->fs.h_u.ah_ip4_spec.tos, + fsc->fs.m_u.ah_ip4_spec.tos); p += ETH_GSTRING_LEN; num_strings++; break; case IP_USER_FLOW: sprintf(p, "\tSrc IP addr: 0x%x\n", - fsc->fs.h_u.raw_ip4_spec.ip4src); + fsc->fs.h_u.raw_ip4_spec.ip4src); p += ETH_GSTRING_LEN; num_strings++; sprintf(p, "\tSrc IP mask: 0x%x\n", - fsc->fs.m_u.raw_ip4_spec.ip4src); + fsc->fs.m_u.raw_ip4_spec.ip4src); p += ETH_GSTRING_LEN; num_strings++; sprintf(p, "\tDest IP addr: 0x%x\n", - fsc->fs.h_u.raw_ip4_spec.ip4dst); + fsc->fs.h_u.raw_ip4_spec.ip4dst); p += ETH_GSTRING_LEN; num_strings++; sprintf(p, "\tDest IP mask: 0x%x\n", - fsc->fs.m_u.raw_ip4_spec.ip4dst); + fsc->fs.m_u.raw_ip4_spec.ip4dst); p += ETH_GSTRING_LEN; num_strings++; break; case IPV4_FLOW: sprintf(p, "\tSrc IP addr: 0x%x\n", - fsc->fs.h_u.usr_ip4_spec.ip4src); + fsc->fs.h_u.usr_ip4_spec.ip4src); p += ETH_GSTRING_LEN; num_strings++; sprintf(p, "\tSrc IP mask: 0x%x\n", - fsc->fs.m_u.usr_ip4_spec.ip4src); + fsc->fs.m_u.usr_ip4_spec.ip4src); p += ETH_GSTRING_LEN; num_strings++; sprintf(p, "\tDest IP addr: 0x%x\n", - fsc->fs.h_u.usr_ip4_spec.ip4dst); + fsc->fs.h_u.usr_ip4_spec.ip4dst); p += ETH_GSTRING_LEN; num_strings++; sprintf(p, "\tDest IP mask: 0x%x\n", - fsc->fs.m_u.usr_ip4_spec.ip4dst); + fsc->fs.m_u.usr_ip4_spec.ip4dst); p += ETH_GSTRING_LEN; num_strings++; sprintf(p, "\tL4 bytes: 0x%x, mask: 0x%x\n", - fsc->fs.h_u.usr_ip4_spec.l4_4_bytes, - fsc->fs.m_u.usr_ip4_spec.l4_4_bytes); + fsc->fs.h_u.usr_ip4_spec.l4_4_bytes, + fsc->fs.m_u.usr_ip4_spec.l4_4_bytes); p += ETH_GSTRING_LEN; num_strings++; sprintf(p, "\tTOS: %d, mask: 0x%x\n", - fsc->fs.h_u.usr_ip4_spec.tos, - fsc->fs.m_u.usr_ip4_spec.tos); + fsc->fs.h_u.usr_ip4_spec.tos, + fsc->fs.m_u.usr_ip4_spec.tos); p += ETH_GSTRING_LEN; num_strings++; sprintf(p, "\tIP Version: %d, mask: 0x%x\n", - fsc->fs.h_u.usr_ip4_spec.ip_ver, - fsc->fs.m_u.usr_ip4_spec.ip_ver); + fsc->fs.h_u.usr_ip4_spec.ip_ver, + fsc->fs.m_u.usr_ip4_spec.ip_ver); p += ETH_GSTRING_LEN; num_strings++; sprintf(p, "\tProtocol: %d, mask: 0x%x\n", - fsc->fs.h_u.usr_ip4_spec.proto, - fsc->fs.m_u.usr_ip4_spec.proto); + fsc->fs.h_u.usr_ip4_spec.proto, + fsc->fs.m_u.usr_ip4_spec.proto); p += ETH_GSTRING_LEN; num_strings++; break; }; sprintf(p, "\tVLAN: %d, mask: 0x%x\n", - fsc->fs.vlan_tag, fsc->fs.vlan_tag_mask); + fsc->fs.vlan_tag, fsc->fs.vlan_tag_mask); p += ETH_GSTRING_LEN; num_strings++; sprintf(p, "\tUser-defined: 0x%Lx\n", fsc->fs.data); @@ -640,7 +661,7 @@ static int ethtool_get_rx_ntuple(struct net_device *dev, void __user *useraddr) sprintf(p, "\tAction: Drop\n"); else sprintf(p, "\tAction: Direct to queue %d\n", - fsc->fs.action); + fsc->fs.action); p += ETH_GSTRING_LEN; num_strings++; unknown_filter: @@ -852,7 +873,8 @@ static int ethtool_set_eeprom(struct net_device *dev, void __user *useraddr) return ret; } -static noinline_for_stack int ethtool_get_coalesce(struct net_device *dev, void __user *useraddr) +static noinline_for_stack int ethtool_get_coalesce(struct net_device *dev, + void __user *useraddr) { struct ethtool_coalesce coalesce = { .cmd = ETHTOOL_GCOALESCE }; @@ -866,7 +888,8 @@ static noinline_for_stack int ethtool_get_coalesce(struct net_device *dev, void return 0; } -static noinline_for_stack int ethtool_set_coalesce(struct net_device *dev, void __user *useraddr) +static noinline_for_stack int ethtool_set_coalesce(struct net_device *dev, + void __user *useraddr) { struct ethtool_coalesce coalesce; @@ -970,6 +993,7 @@ static int ethtool_set_tx_csum(struct net_device *dev, char __user *useraddr) return dev->ethtool_ops->set_tx_csum(dev, edata.data); } +EXPORT_SYMBOL(ethtool_op_set_tx_csum); static int ethtool_set_rx_csum(struct net_device *dev, char __user *useraddr) { @@ -1041,7 +1065,7 @@ static int ethtool_get_gso(struct net_device *dev, char __user *useraddr) edata.data = dev->features & NETIF_F_GSO; if (copy_to_user(useraddr, &edata, sizeof(edata))) - return -EFAULT; + return -EFAULT; return 0; } @@ -1064,7 +1088,7 @@ static int ethtool_get_gro(struct net_device *dev, char __user *useraddr) edata.data = dev->features & NETIF_F_GRO; if (copy_to_user(useraddr, &edata, sizeof(edata))) - return -EFAULT; + return -EFAULT; return 0; } @@ -1276,7 +1300,8 @@ static int ethtool_set_value(struct net_device *dev, char __user *useraddr, return actor(dev, edata.data); } -static noinline_for_stack int ethtool_flash_device(struct net_device *dev, char __user *useraddr) +static noinline_for_stack int ethtool_flash_device(struct net_device *dev, + char __user *useraddr) { struct ethtool_flash efl; @@ -1305,11 +1330,11 @@ int dev_ethtool(struct net *net, struct ifreq *ifr) if (!dev->ethtool_ops) return -EOPNOTSUPP; - if (copy_from_user(ðcmd, useraddr, sizeof (ethcmd))) + if (copy_from_user(ðcmd, useraddr, sizeof(ethcmd))) return -EFAULT; /* Allow some commands to be done by anyone */ - switch(ethcmd) { + switch (ethcmd) { case ETHTOOL_GDRVINFO: case ETHTOOL_GMSGLVL: case ETHTOOL_GCOALESCE: @@ -1337,10 +1362,11 @@ int dev_ethtool(struct net *net, struct ifreq *ifr) return -EPERM; } - if (dev->ethtool_ops->begin) - if ((rc = dev->ethtool_ops->begin(dev)) < 0) + if (dev->ethtool_ops->begin) { + rc = dev->ethtool_ops->begin(dev); + if (rc < 0) return rc; - + } old_features = dev->features; switch (ethcmd) { @@ -1530,16 +1556,3 @@ int dev_ethtool(struct net *net, struct ifreq *ifr) return rc; } - -EXPORT_SYMBOL(ethtool_op_get_link); -EXPORT_SYMBOL(ethtool_op_get_sg); -EXPORT_SYMBOL(ethtool_op_get_tso); -EXPORT_SYMBOL(ethtool_op_set_sg); -EXPORT_SYMBOL(ethtool_op_set_tso); -EXPORT_SYMBOL(ethtool_op_set_tx_csum); -EXPORT_SYMBOL(ethtool_op_set_tx_hw_csum); -EXPORT_SYMBOL(ethtool_op_set_tx_ipv6_csum); -EXPORT_SYMBOL(ethtool_op_set_ufo); -EXPORT_SYMBOL(ethtool_op_get_ufo); -EXPORT_SYMBOL(ethtool_op_set_flags); -EXPORT_SYMBOL(ethtool_op_get_flags); diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c index 2ff34894357a..1bc66592453c 100644 --- a/net/core/fib_rules.c +++ b/net/core/fib_rules.c @@ -10,6 +10,7 @@ #include <linux/types.h> #include <linux/kernel.h> +#include <linux/slab.h> #include <linux/list.h> #include <net/net_namespace.h> #include <net/sock.h> @@ -38,6 +39,24 @@ int fib_default_rule_add(struct fib_rules_ops *ops, } EXPORT_SYMBOL(fib_default_rule_add); +u32 fib_default_rule_pref(struct fib_rules_ops *ops) +{ + struct list_head *pos; + struct fib_rule *rule; + + if (!list_empty(&ops->rules_list)) { + pos = ops->rules_list.next; + if (pos->next != &ops->rules_list) { + rule = list_entry(pos->next, struct fib_rule, list); + if (rule->pref) + return rule->pref - 1; + } + } + + return 0; +} +EXPORT_SYMBOL(fib_default_rule_pref); + static void notify_rule_change(int event, struct fib_rule *rule, struct fib_rules_ops *ops, struct nlmsghdr *nlh, u32 pid); @@ -516,6 +535,7 @@ static int fib_nl_fill_rule(struct sk_buff *skb, struct fib_rule *rule, return -EMSGSIZE; frh = nlmsg_data(nlh); + frh->family = ops->family; frh->table = rule->table; NLA_PUT_U32(skb, FRA_TABLE, rule->table); frh->res1 = 0; diff --git a/net/core/filter.c b/net/core/filter.c index d38ef7fd50f0..ff943bed21af 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -25,6 +25,7 @@ #include <linux/inet.h> #include <linux/netdevice.h> #include <linux/if_packet.h> +#include <linux/gfp.h> #include <net/ip.h> #include <net/protocol.h> #include <net/netlink.h> diff --git a/net/core/flow.c b/net/core/flow.c index 96015871ecea..161900674009 100644 --- a/net/core/flow.c +++ b/net/core/flow.c @@ -26,113 +26,158 @@ #include <linux/security.h> struct flow_cache_entry { - struct flow_cache_entry *next; - u16 family; - u8 dir; - u32 genid; - struct flowi key; - void *object; - atomic_t *object_ref; + union { + struct hlist_node hlist; + struct list_head gc_list; + } u; + u16 family; + u8 dir; + u32 genid; + struct flowi key; + struct flow_cache_object *object; }; -atomic_t flow_cache_genid = ATOMIC_INIT(0); - -static u32 flow_hash_shift; -#define flow_hash_size (1 << flow_hash_shift) -static DEFINE_PER_CPU(struct flow_cache_entry **, flow_tables) = { NULL }; - -#define flow_table(cpu) (per_cpu(flow_tables, cpu)) - -static struct kmem_cache *flow_cachep __read_mostly; +struct flow_cache_percpu { + struct hlist_head *hash_table; + int hash_count; + u32 hash_rnd; + int hash_rnd_recalc; + struct tasklet_struct flush_tasklet; +}; -static int flow_lwm, flow_hwm; +struct flow_flush_info { + struct flow_cache *cache; + atomic_t cpuleft; + struct completion completion; +}; -struct flow_percpu_info { - int hash_rnd_recalc; - u32 hash_rnd; - int count; +struct flow_cache { + u32 hash_shift; + unsigned long order; + struct flow_cache_percpu *percpu; + struct notifier_block hotcpu_notifier; + int low_watermark; + int high_watermark; + struct timer_list rnd_timer; }; -static DEFINE_PER_CPU(struct flow_percpu_info, flow_hash_info) = { 0 }; -#define flow_hash_rnd_recalc(cpu) \ - (per_cpu(flow_hash_info, cpu).hash_rnd_recalc) -#define flow_hash_rnd(cpu) \ - (per_cpu(flow_hash_info, cpu).hash_rnd) -#define flow_count(cpu) \ - (per_cpu(flow_hash_info, cpu).count) +atomic_t flow_cache_genid = ATOMIC_INIT(0); +static struct flow_cache flow_cache_global; +static struct kmem_cache *flow_cachep; -static struct timer_list flow_hash_rnd_timer; +static DEFINE_SPINLOCK(flow_cache_gc_lock); +static LIST_HEAD(flow_cache_gc_list); -#define FLOW_HASH_RND_PERIOD (10 * 60 * HZ) - -struct flow_flush_info { - atomic_t cpuleft; - struct completion completion; -}; -static DEFINE_PER_CPU(struct tasklet_struct, flow_flush_tasklets) = { NULL }; - -#define flow_flush_tasklet(cpu) (&per_cpu(flow_flush_tasklets, cpu)) +#define flow_cache_hash_size(cache) (1 << (cache)->hash_shift) +#define FLOW_HASH_RND_PERIOD (10 * 60 * HZ) static void flow_cache_new_hashrnd(unsigned long arg) { + struct flow_cache *fc = (void *) arg; int i; for_each_possible_cpu(i) - flow_hash_rnd_recalc(i) = 1; + per_cpu_ptr(fc->percpu, i)->hash_rnd_recalc = 1; - flow_hash_rnd_timer.expires = jiffies + FLOW_HASH_RND_PERIOD; - add_timer(&flow_hash_rnd_timer); + fc->rnd_timer.expires = jiffies + FLOW_HASH_RND_PERIOD; + add_timer(&fc->rnd_timer); +} + +static int flow_entry_valid(struct flow_cache_entry *fle) +{ + if (atomic_read(&flow_cache_genid) != fle->genid) + return 0; + if (fle->object && !fle->object->ops->check(fle->object)) + return 0; + return 1; } -static void flow_entry_kill(int cpu, struct flow_cache_entry *fle) +static void flow_entry_kill(struct flow_cache_entry *fle) { if (fle->object) - atomic_dec(fle->object_ref); + fle->object->ops->delete(fle->object); kmem_cache_free(flow_cachep, fle); - flow_count(cpu)--; } -static void __flow_cache_shrink(int cpu, int shrink_to) +static void flow_cache_gc_task(struct work_struct *work) { - struct flow_cache_entry *fle, **flp; - int i; + struct list_head gc_list; + struct flow_cache_entry *fce, *n; - for (i = 0; i < flow_hash_size; i++) { - int k = 0; + INIT_LIST_HEAD(&gc_list); + spin_lock_bh(&flow_cache_gc_lock); + list_splice_tail_init(&flow_cache_gc_list, &gc_list); + spin_unlock_bh(&flow_cache_gc_lock); - flp = &flow_table(cpu)[i]; - while ((fle = *flp) != NULL && k < shrink_to) { - k++; - flp = &fle->next; - } - while ((fle = *flp) != NULL) { - *flp = fle->next; - flow_entry_kill(cpu, fle); - } + list_for_each_entry_safe(fce, n, &gc_list, u.gc_list) + flow_entry_kill(fce); +} +static DECLARE_WORK(flow_cache_gc_work, flow_cache_gc_task); + +static void flow_cache_queue_garbage(struct flow_cache_percpu *fcp, + int deleted, struct list_head *gc_list) +{ + if (deleted) { + fcp->hash_count -= deleted; + spin_lock_bh(&flow_cache_gc_lock); + list_splice_tail(gc_list, &flow_cache_gc_list); + spin_unlock_bh(&flow_cache_gc_lock); + schedule_work(&flow_cache_gc_work); } } -static void flow_cache_shrink(int cpu) +static void __flow_cache_shrink(struct flow_cache *fc, + struct flow_cache_percpu *fcp, + int shrink_to) { - int shrink_to = flow_lwm / flow_hash_size; + struct flow_cache_entry *fle; + struct hlist_node *entry, *tmp; + LIST_HEAD(gc_list); + int i, deleted = 0; + + for (i = 0; i < flow_cache_hash_size(fc); i++) { + int saved = 0; + + hlist_for_each_entry_safe(fle, entry, tmp, + &fcp->hash_table[i], u.hlist) { + if (saved < shrink_to && + flow_entry_valid(fle)) { + saved++; + } else { + deleted++; + hlist_del(&fle->u.hlist); + list_add_tail(&fle->u.gc_list, &gc_list); + } + } + } - __flow_cache_shrink(cpu, shrink_to); + flow_cache_queue_garbage(fcp, deleted, &gc_list); } -static void flow_new_hash_rnd(int cpu) +static void flow_cache_shrink(struct flow_cache *fc, + struct flow_cache_percpu *fcp) { - get_random_bytes(&flow_hash_rnd(cpu), sizeof(u32)); - flow_hash_rnd_recalc(cpu) = 0; + int shrink_to = fc->low_watermark / flow_cache_hash_size(fc); - __flow_cache_shrink(cpu, 0); + __flow_cache_shrink(fc, fcp, shrink_to); } -static u32 flow_hash_code(struct flowi *key, int cpu) +static void flow_new_hash_rnd(struct flow_cache *fc, + struct flow_cache_percpu *fcp) +{ + get_random_bytes(&fcp->hash_rnd, sizeof(u32)); + fcp->hash_rnd_recalc = 0; + __flow_cache_shrink(fc, fcp, 0); +} + +static u32 flow_hash_code(struct flow_cache *fc, + struct flow_cache_percpu *fcp, + struct flowi *key) { u32 *k = (u32 *) key; - return (jhash2(k, (sizeof(*key) / sizeof(u32)), flow_hash_rnd(cpu)) & - (flow_hash_size - 1)); + return (jhash2(k, (sizeof(*key) / sizeof(u32)), fcp->hash_rnd) + & (flow_cache_hash_size(fc) - 1)); } #if (BITS_PER_LONG == 64) @@ -165,114 +210,117 @@ static int flow_key_compare(struct flowi *key1, struct flowi *key2) return 0; } -void *flow_cache_lookup(struct net *net, struct flowi *key, u16 family, u8 dir, - flow_resolve_t resolver) +struct flow_cache_object * +flow_cache_lookup(struct net *net, struct flowi *key, u16 family, u8 dir, + flow_resolve_t resolver, void *ctx) { - struct flow_cache_entry *fle, **head; + struct flow_cache *fc = &flow_cache_global; + struct flow_cache_percpu *fcp; + struct flow_cache_entry *fle, *tfle; + struct hlist_node *entry; + struct flow_cache_object *flo; unsigned int hash; - int cpu; local_bh_disable(); - cpu = smp_processor_id(); + fcp = per_cpu_ptr(fc->percpu, smp_processor_id()); fle = NULL; + flo = NULL; /* Packet really early in init? Making flow_cache_init a * pre-smp initcall would solve this. --RR */ - if (!flow_table(cpu)) + if (!fcp->hash_table) goto nocache; - if (flow_hash_rnd_recalc(cpu)) - flow_new_hash_rnd(cpu); - hash = flow_hash_code(key, cpu); + if (fcp->hash_rnd_recalc) + flow_new_hash_rnd(fc, fcp); - head = &flow_table(cpu)[hash]; - for (fle = *head; fle; fle = fle->next) { - if (fle->family == family && - fle->dir == dir && - flow_key_compare(key, &fle->key) == 0) { - if (fle->genid == atomic_read(&flow_cache_genid)) { - void *ret = fle->object; - - if (ret) - atomic_inc(fle->object_ref); - local_bh_enable(); - - return ret; - } + hash = flow_hash_code(fc, fcp, key); + hlist_for_each_entry(tfle, entry, &fcp->hash_table[hash], u.hlist) { + if (tfle->family == family && + tfle->dir == dir && + flow_key_compare(key, &tfle->key) == 0) { + fle = tfle; break; } } - if (!fle) { - if (flow_count(cpu) > flow_hwm) - flow_cache_shrink(cpu); + if (unlikely(!fle)) { + if (fcp->hash_count > fc->high_watermark) + flow_cache_shrink(fc, fcp); fle = kmem_cache_alloc(flow_cachep, GFP_ATOMIC); if (fle) { - fle->next = *head; - *head = fle; fle->family = family; fle->dir = dir; memcpy(&fle->key, key, sizeof(*key)); fle->object = NULL; - flow_count(cpu)++; + hlist_add_head(&fle->u.hlist, &fcp->hash_table[hash]); + fcp->hash_count++; } + } else if (likely(fle->genid == atomic_read(&flow_cache_genid))) { + flo = fle->object; + if (!flo) + goto ret_object; + flo = flo->ops->get(flo); + if (flo) + goto ret_object; + } else if (fle->object) { + flo = fle->object; + flo->ops->delete(flo); + fle->object = NULL; } nocache: - { - int err; - void *obj; - atomic_t *obj_ref; - - err = resolver(net, key, family, dir, &obj, &obj_ref); - - if (fle && !err) { - fle->genid = atomic_read(&flow_cache_genid); - - if (fle->object) - atomic_dec(fle->object_ref); - - fle->object = obj; - fle->object_ref = obj_ref; - if (obj) - atomic_inc(fle->object_ref); - } - local_bh_enable(); - - if (err) - obj = ERR_PTR(err); - return obj; + flo = NULL; + if (fle) { + flo = fle->object; + fle->object = NULL; } + flo = resolver(net, key, family, dir, flo, ctx); + if (fle) { + fle->genid = atomic_read(&flow_cache_genid); + if (!IS_ERR(flo)) + fle->object = flo; + else + fle->genid--; + } else { + if (flo && !IS_ERR(flo)) + flo->ops->delete(flo); + } +ret_object: + local_bh_enable(); + return flo; } static void flow_cache_flush_tasklet(unsigned long data) { struct flow_flush_info *info = (void *)data; - int i; - int cpu; - - cpu = smp_processor_id(); - for (i = 0; i < flow_hash_size; i++) { - struct flow_cache_entry *fle; - - fle = flow_table(cpu)[i]; - for (; fle; fle = fle->next) { - unsigned genid = atomic_read(&flow_cache_genid); - - if (!fle->object || fle->genid == genid) + struct flow_cache *fc = info->cache; + struct flow_cache_percpu *fcp; + struct flow_cache_entry *fle; + struct hlist_node *entry, *tmp; + LIST_HEAD(gc_list); + int i, deleted = 0; + + fcp = per_cpu_ptr(fc->percpu, smp_processor_id()); + for (i = 0; i < flow_cache_hash_size(fc); i++) { + hlist_for_each_entry_safe(fle, entry, tmp, + &fcp->hash_table[i], u.hlist) { + if (flow_entry_valid(fle)) continue; - fle->object = NULL; - atomic_dec(fle->object_ref); + deleted++; + hlist_del(&fle->u.hlist); + list_add_tail(&fle->u.gc_list, &gc_list); } } + flow_cache_queue_garbage(fcp, deleted, &gc_list); + if (atomic_dec_and_test(&info->cpuleft)) complete(&info->completion); } -static void flow_cache_flush_per_cpu(void *) __attribute__((__unused__)); static void flow_cache_flush_per_cpu(void *data) { struct flow_flush_info *info = data; @@ -280,8 +328,7 @@ static void flow_cache_flush_per_cpu(void *data) struct tasklet_struct *tasklet; cpu = smp_processor_id(); - - tasklet = flow_flush_tasklet(cpu); + tasklet = &per_cpu_ptr(info->cache->percpu, cpu)->flush_tasklet; tasklet->data = (unsigned long)info; tasklet_schedule(tasklet); } @@ -294,6 +341,7 @@ void flow_cache_flush(void) /* Don't want cpus going down or up during this. */ get_online_cpus(); mutex_lock(&flow_flush_sem); + info.cache = &flow_cache_global; atomic_set(&info.cpuleft, num_online_cpus()); init_completion(&info.completion); @@ -307,62 +355,75 @@ void flow_cache_flush(void) put_online_cpus(); } -static void __init flow_cache_cpu_prepare(int cpu) +static void __init flow_cache_cpu_prepare(struct flow_cache *fc, + struct flow_cache_percpu *fcp) { - struct tasklet_struct *tasklet; - unsigned long order; - - for (order = 0; - (PAGE_SIZE << order) < - (sizeof(struct flow_cache_entry *)*flow_hash_size); - order++) - /* NOTHING */; - - flow_table(cpu) = (struct flow_cache_entry **) - __get_free_pages(GFP_KERNEL|__GFP_ZERO, order); - if (!flow_table(cpu)) - panic("NET: failed to allocate flow cache order %lu\n", order); - - flow_hash_rnd_recalc(cpu) = 1; - flow_count(cpu) = 0; - - tasklet = flow_flush_tasklet(cpu); - tasklet_init(tasklet, flow_cache_flush_tasklet, 0); + fcp->hash_table = (struct hlist_head *) + __get_free_pages(GFP_KERNEL|__GFP_ZERO, fc->order); + if (!fcp->hash_table) + panic("NET: failed to allocate flow cache order %lu\n", fc->order); + + fcp->hash_rnd_recalc = 1; + fcp->hash_count = 0; + tasklet_init(&fcp->flush_tasklet, flow_cache_flush_tasklet, 0); } static int flow_cache_cpu(struct notifier_block *nfb, unsigned long action, void *hcpu) { + struct flow_cache *fc = container_of(nfb, struct flow_cache, hotcpu_notifier); + int cpu = (unsigned long) hcpu; + struct flow_cache_percpu *fcp = per_cpu_ptr(fc->percpu, cpu); + if (action == CPU_DEAD || action == CPU_DEAD_FROZEN) - __flow_cache_shrink((unsigned long)hcpu, 0); + __flow_cache_shrink(fc, fcp, 0); return NOTIFY_OK; } -static int __init flow_cache_init(void) +static int flow_cache_init(struct flow_cache *fc) { + unsigned long order; int i; - flow_cachep = kmem_cache_create("flow_cache", - sizeof(struct flow_cache_entry), - 0, SLAB_PANIC, - NULL); - flow_hash_shift = 10; - flow_lwm = 2 * flow_hash_size; - flow_hwm = 4 * flow_hash_size; + fc->hash_shift = 10; + fc->low_watermark = 2 * flow_cache_hash_size(fc); + fc->high_watermark = 4 * flow_cache_hash_size(fc); + + for (order = 0; + (PAGE_SIZE << order) < + (sizeof(struct hlist_head)*flow_cache_hash_size(fc)); + order++) + /* NOTHING */; + fc->order = order; + fc->percpu = alloc_percpu(struct flow_cache_percpu); - setup_timer(&flow_hash_rnd_timer, flow_cache_new_hashrnd, 0); - flow_hash_rnd_timer.expires = jiffies + FLOW_HASH_RND_PERIOD; - add_timer(&flow_hash_rnd_timer); + setup_timer(&fc->rnd_timer, flow_cache_new_hashrnd, + (unsigned long) fc); + fc->rnd_timer.expires = jiffies + FLOW_HASH_RND_PERIOD; + add_timer(&fc->rnd_timer); for_each_possible_cpu(i) - flow_cache_cpu_prepare(i); + flow_cache_cpu_prepare(fc, per_cpu_ptr(fc->percpu, i)); + + fc->hotcpu_notifier = (struct notifier_block){ + .notifier_call = flow_cache_cpu, + }; + register_hotcpu_notifier(&fc->hotcpu_notifier); - hotcpu_notifier(flow_cache_cpu, 0); return 0; } -module_init(flow_cache_init); +static int __init flow_cache_init_global(void) +{ + flow_cachep = kmem_cache_create("flow_cache", + sizeof(struct flow_cache_entry), + 0, SLAB_PANIC, NULL); + + return flow_cache_init(&flow_cache_global); +} + +module_init(flow_cache_init_global); EXPORT_SYMBOL(flow_cache_genid); EXPORT_SYMBOL(flow_cache_lookup); diff --git a/net/core/gen_estimator.c b/net/core/gen_estimator.c index 493775f4f2f1..cf8e70392fe0 100644 --- a/net/core/gen_estimator.c +++ b/net/core/gen_estimator.c @@ -32,6 +32,7 @@ #include <linux/rtnetlink.h> #include <linux/init.h> #include <linux/rbtree.h> +#include <linux/slab.h> #include <net/sock.h> #include <net/gen_stats.h> diff --git a/net/core/iovec.c b/net/core/iovec.c index 16ad45d4882b..1e7f4e91a935 100644 --- a/net/core/iovec.c +++ b/net/core/iovec.c @@ -20,7 +20,6 @@ #include <linux/module.h> #include <linux/kernel.h> #include <linux/mm.h> -#include <linux/slab.h> #include <linux/net.h> #include <linux/in6.h> #include <asm/uaccess.h> diff --git a/net/core/link_watch.c b/net/core/link_watch.c index 5910b555a54a..bdbce2f5875b 100644 --- a/net/core/link_watch.c +++ b/net/core/link_watch.c @@ -19,7 +19,6 @@ #include <linux/rtnetlink.h> #include <linux/jiffies.h> #include <linux/spinlock.h> -#include <linux/slab.h> #include <linux/workqueue.h> #include <linux/bitops.h> #include <asm/types.h> diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 6cee6434da67..bff37908bd55 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -15,6 +15,7 @@ * Harald Welte Add neighbour cache statistics like rtstat */ +#include <linux/slab.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/module.h> diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index 7a46343d5ae3..c57c4b228bb5 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -13,9 +13,11 @@ #include <linux/kernel.h> #include <linux/netdevice.h> #include <linux/if_arp.h> +#include <linux/slab.h> #include <net/sock.h> #include <linux/rtnetlink.h> #include <linux/wireless.h> +#include <linux/vmalloc.h> #include <net/wext.h> #include "net-sysfs.h" @@ -466,6 +468,7 @@ static struct attribute_group wireless_group = { }; #endif +#ifdef CONFIG_RPS /* * RX queue sysfs structures and functions. */ @@ -547,7 +550,7 @@ static void rps_map_release(struct rcu_head *rcu) kfree(map); } -ssize_t store_rps_map(struct netdev_rx_queue *queue, +static ssize_t store_rps_map(struct netdev_rx_queue *queue, struct rx_queue_attribute *attribute, const char *buf, size_t len) { @@ -599,22 +602,109 @@ ssize_t store_rps_map(struct netdev_rx_queue *queue, return len; } +static ssize_t show_rps_dev_flow_table_cnt(struct netdev_rx_queue *queue, + struct rx_queue_attribute *attr, + char *buf) +{ + struct rps_dev_flow_table *flow_table; + unsigned int val = 0; + + rcu_read_lock(); + flow_table = rcu_dereference(queue->rps_flow_table); + if (flow_table) + val = flow_table->mask + 1; + rcu_read_unlock(); + + return sprintf(buf, "%u\n", val); +} + +static void rps_dev_flow_table_release_work(struct work_struct *work) +{ + struct rps_dev_flow_table *table = container_of(work, + struct rps_dev_flow_table, free_work); + + vfree(table); +} + +static void rps_dev_flow_table_release(struct rcu_head *rcu) +{ + struct rps_dev_flow_table *table = container_of(rcu, + struct rps_dev_flow_table, rcu); + + INIT_WORK(&table->free_work, rps_dev_flow_table_release_work); + schedule_work(&table->free_work); +} + +static ssize_t store_rps_dev_flow_table_cnt(struct netdev_rx_queue *queue, + struct rx_queue_attribute *attr, + const char *buf, size_t len) +{ + unsigned int count; + char *endp; + struct rps_dev_flow_table *table, *old_table; + static DEFINE_SPINLOCK(rps_dev_flow_lock); + + if (!capable(CAP_NET_ADMIN)) + return -EPERM; + + count = simple_strtoul(buf, &endp, 0); + if (endp == buf) + return -EINVAL; + + if (count) { + int i; + + if (count > 1<<30) { + /* Enforce a limit to prevent overflow */ + return -EINVAL; + } + count = roundup_pow_of_two(count); + table = vmalloc(RPS_DEV_FLOW_TABLE_SIZE(count)); + if (!table) + return -ENOMEM; + + table->mask = count - 1; + for (i = 0; i < count; i++) + table->flows[i].cpu = RPS_NO_CPU; + } else + table = NULL; + + spin_lock(&rps_dev_flow_lock); + old_table = queue->rps_flow_table; + rcu_assign_pointer(queue->rps_flow_table, table); + spin_unlock(&rps_dev_flow_lock); + + if (old_table) + call_rcu(&old_table->rcu, rps_dev_flow_table_release); + + return len; +} + static struct rx_queue_attribute rps_cpus_attribute = __ATTR(rps_cpus, S_IRUGO | S_IWUSR, show_rps_map, store_rps_map); + +static struct rx_queue_attribute rps_dev_flow_table_cnt_attribute = + __ATTR(rps_flow_cnt, S_IRUGO | S_IWUSR, + show_rps_dev_flow_table_cnt, store_rps_dev_flow_table_cnt); + static struct attribute *rx_queue_default_attrs[] = { &rps_cpus_attribute.attr, + &rps_dev_flow_table_cnt_attribute.attr, NULL }; static void rx_queue_release(struct kobject *kobj) { struct netdev_rx_queue *queue = to_rx_queue(kobj); - struct rps_map *map = queue->rps_map; struct netdev_rx_queue *first = queue->first; - if (map) - call_rcu(&map->rcu, rps_map_release); + if (queue->rps_map) + call_rcu(&queue->rps_map->rcu, rps_map_release); + + if (queue->rps_flow_table) + call_rcu(&queue->rps_flow_table->rcu, + rps_dev_flow_table_release); if (atomic_dec_and_test(&first->count)) kfree(first); @@ -675,7 +765,7 @@ static void rx_queue_remove_kobjects(struct net_device *net) kobject_put(&net->_rx[i].kobj); kset_unregister(net->queues_kset); } - +#endif /* CONFIG_RPS */ #endif /* CONFIG_SYSFS */ #ifdef CONFIG_HOTPLUG @@ -739,7 +829,9 @@ void netdev_unregister_kobject(struct net_device * net) if (!net_eq(dev_net(net), &init_net)) return; +#ifdef CONFIG_RPS rx_queue_remove_kobjects(net); +#endif device_del(dev); } @@ -780,11 +872,13 @@ int netdev_register_kobject(struct net_device *net) if (error) return error; +#ifdef CONFIG_RPS error = rx_queue_register_kobjects(net); if (error) { device_del(dev); return error; } +#endif return error; } diff --git a/net/core/net-traces.c b/net/core/net-traces.c index f1e982c508bb..afa6380ed88a 100644 --- a/net/core/net-traces.c +++ b/net/core/net-traces.c @@ -19,6 +19,7 @@ #include <linux/workqueue.h> #include <linux/netlink.h> #include <linux/net_dropmon.h> +#include <linux/slab.h> #include <asm/unaligned.h> #include <asm/bitops.h> diff --git a/net/core/netpoll.c b/net/core/netpoll.c index d4ec38fa64e6..a58f59b97597 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -22,6 +22,7 @@ #include <linux/delay.h> #include <linux/rcupdate.h> #include <linux/workqueue.h> +#include <linux/slab.h> #include <net/tcp.h> #include <net/udp.h> #include <asm/unaligned.h> @@ -614,7 +615,7 @@ void netpoll_print_options(struct netpoll *np) np->name, np->local_port); printk(KERN_INFO "%s: local IP %pI4\n", np->name, &np->local_ip); - printk(KERN_INFO "%s: interface %s\n", + printk(KERN_INFO "%s: interface '%s'\n", np->name, np->dev_name); printk(KERN_INFO "%s: remote port %d\n", np->name, np->remote_port); @@ -661,6 +662,9 @@ int netpoll_parse_options(struct netpoll *np, char *opt) if ((delim = strchr(cur, '@')) == NULL) goto parse_failed; *delim = 0; + if (*cur == ' ' || *cur == '\t') + printk(KERN_INFO "%s: warning: whitespace" + "is not allowed\n", np->name); np->remote_port = simple_strtol(cur, NULL, 10); cur = delim; } @@ -708,7 +712,7 @@ int netpoll_parse_options(struct netpoll *np, char *opt) return 0; parse_failed: - printk(KERN_INFO "%s: couldn't parse config at %s!\n", + printk(KERN_INFO "%s: couldn't parse config at '%s'!\n", np->name, cur); return -1; } diff --git a/net/core/pktgen.c b/net/core/pktgen.c index 43923811bd6a..2ad68da418df 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -169,7 +169,7 @@ #include <asm/dma.h> #include <asm/div64.h> /* do_div */ -#define VERSION "2.72" +#define VERSION "2.73" #define IP_NAME_SZ 32 #define MAX_MPLS_LABELS 16 /* This is the max label stack depth */ #define MPLS_STACK_BOTTOM htonl(0x00000100) @@ -190,6 +190,7 @@ #define F_IPSEC_ON (1<<12) /* ipsec on for flows */ #define F_QUEUE_MAP_RND (1<<13) /* queue map Random */ #define F_QUEUE_MAP_CPU (1<<14) /* queue map mirrors smp_processor_id() */ +#define F_NODE (1<<15) /* Node memory alloc*/ /* Thread control flag bits */ #define T_STOP (1<<0) /* Stop run */ @@ -372,6 +373,7 @@ struct pktgen_dev { u16 queue_map_min; u16 queue_map_max; + int node; /* Memory node */ #ifdef CONFIG_XFRM __u8 ipsmode; /* IPSEC mode (config) */ @@ -607,6 +609,9 @@ static int pktgen_if_show(struct seq_file *seq, void *v) if (pkt_dev->traffic_class) seq_printf(seq, " traffic_class: 0x%02x\n", pkt_dev->traffic_class); + if (pkt_dev->node >= 0) + seq_printf(seq, " node: %d\n", pkt_dev->node); + seq_printf(seq, " Flags: "); if (pkt_dev->flags & F_IPV6) @@ -660,6 +665,9 @@ static int pktgen_if_show(struct seq_file *seq, void *v) if (pkt_dev->flags & F_SVID_RND) seq_printf(seq, "SVID_RND "); + if (pkt_dev->flags & F_NODE) + seq_printf(seq, "NODE_ALLOC "); + seq_puts(seq, "\n"); /* not really stopped, more like last-running-at */ @@ -1074,6 +1082,21 @@ static ssize_t pktgen_if_write(struct file *file, pkt_dev->dst_mac_count); return count; } + if (!strcmp(name, "node")) { + len = num_arg(&user_buffer[i], 10, &value); + if (len < 0) + return len; + + i += len; + + if (node_possible(value)) { + pkt_dev->node = value; + sprintf(pg_result, "OK: node=%d", pkt_dev->node); + } + else + sprintf(pg_result, "ERROR: node not possible"); + return count; + } if (!strcmp(name, "flag")) { char f[32]; memset(f, 0, 32); @@ -1166,12 +1189,18 @@ static ssize_t pktgen_if_write(struct file *file, else if (strcmp(f, "!IPV6") == 0) pkt_dev->flags &= ~F_IPV6; + else if (strcmp(f, "NODE_ALLOC") == 0) + pkt_dev->flags |= F_NODE; + + else if (strcmp(f, "!NODE_ALLOC") == 0) + pkt_dev->flags &= ~F_NODE; + else { sprintf(pg_result, "Flag -:%s:- unknown\nAvailable flags, (prepend ! to un-set flag):\n%s", f, "IPSRC_RND, IPDST_RND, UDPSRC_RND, UDPDST_RND, " - "MACSRC_RND, MACDST_RND, TXSIZE_RND, IPV6, MPLS_RND, VID_RND, SVID_RND, FLOW_SEQ, IPSEC\n"); + "MACSRC_RND, MACDST_RND, TXSIZE_RND, IPV6, MPLS_RND, VID_RND, SVID_RND, FLOW_SEQ, IPSEC, NODE_ALLOC\n"); return count; } sprintf(pg_result, "OK: flags=0x%x", pkt_dev->flags); @@ -2572,9 +2601,27 @@ static struct sk_buff *fill_packet_ipv4(struct net_device *odev, mod_cur_headers(pkt_dev); datalen = (odev->hard_header_len + 16) & ~0xf; - skb = __netdev_alloc_skb(odev, - pkt_dev->cur_pkt_size + 64 - + datalen + pkt_dev->pkt_overhead, GFP_NOWAIT); + + if (pkt_dev->flags & F_NODE) { + int node; + + if (pkt_dev->node >= 0) + node = pkt_dev->node; + else + node = numa_node_id(); + + skb = __alloc_skb(NET_SKB_PAD + pkt_dev->cur_pkt_size + 64 + + datalen + pkt_dev->pkt_overhead, GFP_NOWAIT, 0, node); + if (likely(skb)) { + skb_reserve(skb, NET_SKB_PAD); + skb->dev = odev; + } + } + else + skb = __netdev_alloc_skb(odev, + pkt_dev->cur_pkt_size + 64 + + datalen + pkt_dev->pkt_overhead, GFP_NOWAIT); + if (!skb) { sprintf(pkt_dev->result, "No memory"); return NULL; @@ -3674,6 +3721,7 @@ static int pktgen_add_device(struct pktgen_thread *t, const char *ifname) pkt_dev->svlan_p = 0; pkt_dev->svlan_cfi = 0; pkt_dev->svlan_id = 0xffff; + pkt_dev->node = -1; err = pktgen_setup_dev(pkt_dev, ifname); if (err) diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index e1121f0bca6a..78c85985cb30 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -118,7 +118,11 @@ static rtnl_doit_func rtnl_get_doit(int protocol, int msgindex) { struct rtnl_link *tab; - tab = rtnl_msg_handlers[protocol]; + if (protocol < NPROTO) + tab = rtnl_msg_handlers[protocol]; + else + tab = NULL; + if (tab == NULL || tab[msgindex].doit == NULL) tab = rtnl_msg_handlers[PF_UNSPEC]; @@ -129,7 +133,11 @@ static rtnl_dumpit_func rtnl_get_dumpit(int protocol, int msgindex) { struct rtnl_link *tab; - tab = rtnl_msg_handlers[protocol]; + if (protocol < NPROTO) + tab = rtnl_msg_handlers[protocol]; + else + tab = NULL; + if (tab == NULL || tab[msgindex].dumpit == NULL) tab = rtnl_msg_handlers[PF_UNSPEC]; @@ -602,36 +610,38 @@ static void copy_rtnl_link_stats(struct rtnl_link_stats *a, a->tx_compressed = b->tx_compressed; } -static void copy_rtnl_link_stats64(struct rtnl_link_stats64 *a, - const struct net_device_stats *b) +static void copy_rtnl_link_stats64(void *v, const struct net_device_stats *b) { - a->rx_packets = b->rx_packets; - a->tx_packets = b->tx_packets; - a->rx_bytes = b->rx_bytes; - a->tx_bytes = b->tx_bytes; - a->rx_errors = b->rx_errors; - a->tx_errors = b->tx_errors; - a->rx_dropped = b->rx_dropped; - a->tx_dropped = b->tx_dropped; - - a->multicast = b->multicast; - a->collisions = b->collisions; - - a->rx_length_errors = b->rx_length_errors; - a->rx_over_errors = b->rx_over_errors; - a->rx_crc_errors = b->rx_crc_errors; - a->rx_frame_errors = b->rx_frame_errors; - a->rx_fifo_errors = b->rx_fifo_errors; - a->rx_missed_errors = b->rx_missed_errors; - - a->tx_aborted_errors = b->tx_aborted_errors; - a->tx_carrier_errors = b->tx_carrier_errors; - a->tx_fifo_errors = b->tx_fifo_errors; - a->tx_heartbeat_errors = b->tx_heartbeat_errors; - a->tx_window_errors = b->tx_window_errors; - - a->rx_compressed = b->rx_compressed; - a->tx_compressed = b->tx_compressed; + struct rtnl_link_stats64 a; + + a.rx_packets = b->rx_packets; + a.tx_packets = b->tx_packets; + a.rx_bytes = b->rx_bytes; + a.tx_bytes = b->tx_bytes; + a.rx_errors = b->rx_errors; + a.tx_errors = b->tx_errors; + a.rx_dropped = b->rx_dropped; + a.tx_dropped = b->tx_dropped; + + a.multicast = b->multicast; + a.collisions = b->collisions; + + a.rx_length_errors = b->rx_length_errors; + a.rx_over_errors = b->rx_over_errors; + a.rx_crc_errors = b->rx_crc_errors; + a.rx_frame_errors = b->rx_frame_errors; + a.rx_fifo_errors = b->rx_fifo_errors; + a.rx_missed_errors = b->rx_missed_errors; + + a.tx_aborted_errors = b->tx_aborted_errors; + a.tx_carrier_errors = b->tx_carrier_errors; + a.tx_fifo_errors = b->tx_fifo_errors; + a.tx_heartbeat_errors = b->tx_heartbeat_errors; + a.tx_window_errors = b->tx_window_errors; + + a.rx_compressed = b->rx_compressed; + a.tx_compressed = b->tx_compressed; + memcpy(v, &a, sizeof(a)); } static inline int rtnl_vfinfo_size(const struct net_device *dev) @@ -651,6 +661,7 @@ static inline size_t if_nlmsg_size(const struct net_device *dev) + nla_total_size(IFNAMSIZ) /* IFLA_QDISC */ + nla_total_size(sizeof(struct rtnl_link_ifmap)) + nla_total_size(sizeof(struct rtnl_link_stats)) + + nla_total_size(sizeof(struct rtnl_link_stats64)) + nla_total_size(MAX_ADDR_LEN) /* IFLA_ADDRESS */ + nla_total_size(MAX_ADDR_LEN) /* IFLA_BROADCAST */ + nla_total_size(4) /* IFLA_TXQLEN */ @@ -734,8 +745,6 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, sizeof(struct rtnl_link_stats64)); if (attr == NULL) goto nla_put_failure; - - stats = dev_get_stats(dev); copy_rtnl_link_stats64(nla_data(attr), stats); if (dev->netdev_ops->ndo_get_vf_config && dev->dev.parent) { @@ -1443,9 +1452,6 @@ static int rtnetlink_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh) return 0; family = ((struct rtgenmsg *)NLMSG_DATA(nlh))->rtgen_family; - if (family >= NPROTO) - return -EAFNOSUPPORT; - sz_idx = type>>2; kind = type&3; @@ -1513,6 +1519,7 @@ static int rtnetlink_event(struct notifier_block *this, unsigned long event, voi case NETDEV_POST_INIT: case NETDEV_REGISTER: case NETDEV_CHANGE: + case NETDEV_PRE_TYPE_CHANGE: case NETDEV_GOING_DOWN: case NETDEV_UNREGISTER: case NETDEV_UNREGISTER_BATCH: diff --git a/net/core/scm.c b/net/core/scm.c index 9b264634acfd..b88f6f9d0b97 100644 --- a/net/core/scm.c +++ b/net/core/scm.c @@ -26,6 +26,7 @@ #include <linux/security.h> #include <linux/pid.h> #include <linux/nsproxy.h> +#include <linux/slab.h> #include <asm/system.h> #include <asm/uaccess.h> diff --git a/net/core/sock.c b/net/core/sock.c index c5812bbc2cc9..7effa1e689df 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -364,11 +364,11 @@ EXPORT_SYMBOL(sk_reset_txq); struct dst_entry *__sk_dst_check(struct sock *sk, u32 cookie) { - struct dst_entry *dst = sk->sk_dst_cache; + struct dst_entry *dst = __sk_dst_get(sk); if (dst && dst->obsolete && dst->ops->check(dst, cookie) == NULL) { sk_tx_queue_clear(sk); - sk->sk_dst_cache = NULL; + rcu_assign_pointer(sk->sk_dst_cache, NULL); dst_release(dst); return NULL; } @@ -1157,7 +1157,7 @@ struct sock *sk_clone(const struct sock *sk, const gfp_t priority) skb_queue_head_init(&newsk->sk_async_wait_queue); #endif - rwlock_init(&newsk->sk_dst_lock); + spin_lock_init(&newsk->sk_dst_lock); rwlock_init(&newsk->sk_callback_lock); lockdep_set_class_and_name(&newsk->sk_callback_lock, af_callback_keys + newsk->sk_family, @@ -1898,7 +1898,7 @@ void sock_init_data(struct socket *sock, struct sock *sk) } else sk->sk_sleep = NULL; - rwlock_init(&sk->sk_dst_lock); + spin_lock_init(&sk->sk_dst_lock); rwlock_init(&sk->sk_callback_lock); lockdep_set_class_and_name(&sk->sk_callback_lock, af_callback_keys + sk->sk_family, diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c index 06124872af5b..dcc7d25996ab 100644 --- a/net/core/sysctl_net_core.c +++ b/net/core/sysctl_net_core.c @@ -11,11 +11,72 @@ #include <linux/socket.h> #include <linux/netdevice.h> #include <linux/ratelimit.h> +#include <linux/vmalloc.h> #include <linux/init.h> +#include <linux/slab.h> #include <net/ip.h> #include <net/sock.h> +#ifdef CONFIG_RPS +static int rps_sock_flow_sysctl(ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos) +{ + unsigned int orig_size, size; + int ret, i; + ctl_table tmp = { + .data = &size, + .maxlen = sizeof(size), + .mode = table->mode + }; + struct rps_sock_flow_table *orig_sock_table, *sock_table; + static DEFINE_MUTEX(sock_flow_mutex); + + mutex_lock(&sock_flow_mutex); + + orig_sock_table = rps_sock_flow_table; + size = orig_size = orig_sock_table ? orig_sock_table->mask + 1 : 0; + + ret = proc_dointvec(&tmp, write, buffer, lenp, ppos); + + if (write) { + if (size) { + if (size > 1<<30) { + /* Enforce limit to prevent overflow */ + mutex_unlock(&sock_flow_mutex); + return -EINVAL; + } + size = roundup_pow_of_two(size); + if (size != orig_size) { + sock_table = + vmalloc(RPS_SOCK_FLOW_TABLE_SIZE(size)); + if (!sock_table) { + mutex_unlock(&sock_flow_mutex); + return -ENOMEM; + } + + sock_table->mask = size - 1; + } else + sock_table = orig_sock_table; + + for (i = 0; i < size; i++) + sock_table->ents[i] = RPS_NO_CPU; + } else + sock_table = NULL; + + if (sock_table != orig_sock_table) { + rcu_assign_pointer(rps_sock_flow_table, sock_table); + synchronize_rcu(); + vfree(orig_sock_table); + } + } + + mutex_unlock(&sock_flow_mutex); + + return ret; +} +#endif /* CONFIG_RPS */ + static struct ctl_table net_core_table[] = { #ifdef CONFIG_NET { @@ -81,6 +142,14 @@ static struct ctl_table net_core_table[] = { .mode = 0644, .proc_handler = proc_dointvec }, +#ifdef CONFIG_RPS + { + .procname = "rps_sock_flow_entries", + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = rps_sock_flow_sysctl + }, +#endif #endif /* CONFIG_NET */ { .procname = "netdev_budget", |