1323 lines · 31.0 KB · C
RawDownload
/* * Common framework for low-level network console, dump, and debugger code * * Sep 8 2003  Matt Mackall <mpm@selenic.com> * * based on the netconsole code from: * * Copyright (C) 2001  Ingo Molnar <mingo@redhat.com> * Copyright (C) 2002  Red Hat, Inc. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/moduleparam.h>#include <linux/kernel.h>#include <linux/netdevice.h>#include <linux/etherdevice.h>#include <linux/string.h>#include <linux/if_arp.h>#include <linux/inetdevice.h>#include <linux/inet.h>#include <linux/interrupt.h>#include <linux/netpoll.h>#include <linux/sched.h>#include <linux/delay.h>#include <linux/rcupdate.h>#include <linux/workqueue.h>#include <linux/slab.h>#include <linux/export.h>#include <linux/if_vlan.h>#include <net/tcp.h>#include <net/udp.h>#include <net/addrconf.h>#include <net/ndisc.h>#include <net/ip6_checksum.h>#include <asm/unaligned.h>#include <trace/events/napi.h> /* * We maintain a small pool of fully-sized skbs, to make sure the * message gets out even in extreme OOM situations. */ #define MAX_UDP_CHUNK 1460#define MAX_SKBS 32 static struct sk_buff_head skb_pool; static atomic_t trapped; DEFINE_STATIC_SRCU(netpoll_srcu); #define USEC_PER_POLL	50#define NETPOLL_RX_ENABLED  1#define NETPOLL_RX_DROP     2 #define MAX_SKB_SIZE							\	(sizeof(struct ethhdr) +					\	 sizeof(struct iphdr) +						\	 sizeof(struct udphdr) +					\	 MAX_UDP_CHUNK) static void zap_completion_queue(void);static void netpoll_neigh_reply(struct sk_buff *skb, struct netpoll_info *npinfo);static void netpoll_async_cleanup(struct work_struct *work); static unsigned int carrier_timeout = 4;module_param(carrier_timeout, uint, 0644); #define np_info(np, fmt, ...)				\	pr_info("%s: " fmt, np->name, ##__VA_ARGS__)#define np_err(np, fmt, ...)				\	pr_err("%s: " fmt, np->name, ##__VA_ARGS__)#define np_notice(np, fmt, ...)				\	pr_notice("%s: " fmt, np->name, ##__VA_ARGS__) static void queue_process(struct work_struct *work){	struct netpoll_info *npinfo =		container_of(work, struct netpoll_info, tx_work.work);	struct sk_buff *skb;	unsigned long flags; 	while ((skb = skb_dequeue(&npinfo->txq))) {		struct net_device *dev = skb->dev;		const struct net_device_ops *ops = dev->netdev_ops;		struct netdev_queue *txq; 		if (!netif_device_present(dev) || !netif_running(dev)) {			__kfree_skb(skb);			continue;		} 		txq = netdev_get_tx_queue(dev, skb_get_queue_mapping(skb)); 		local_irq_save(flags);		__netif_tx_lock(txq, smp_processor_id());		if (netif_xmit_frozen_or_stopped(txq) ||		    ops->ndo_start_xmit(skb, dev) != NETDEV_TX_OK) {			skb_queue_head(&npinfo->txq, skb);			__netif_tx_unlock(txq);			local_irq_restore(flags); 			schedule_delayed_work(&npinfo->tx_work, HZ/10);			return;		}		__netif_tx_unlock(txq);		local_irq_restore(flags);	}} static __sum16 checksum_udp(struct sk_buff *skb, struct udphdr *uh,			    unsigned short ulen, __be32 saddr, __be32 daddr){	__wsum psum; 	if (uh->check == 0 || skb_csum_unnecessary(skb))		return 0; 	psum = csum_tcpudp_nofold(saddr, daddr, ulen, IPPROTO_UDP, 0); 	if (skb->ip_summed == CHECKSUM_COMPLETE &&	    !csum_fold(csum_add(psum, skb->csum)))		return 0; 	skb->csum = psum; 	return __skb_checksum_complete(skb);} /* * Check whether delayed processing was scheduled for our NIC. If so, * we attempt to grab the poll lock and use ->poll() to pump the card. * If this fails, either we've recursed in ->poll() or it's already * running on another CPU. * * Note: we don't mask interrupts with this lock because we're using * trylock here and interrupts are already disabled in the softirq * case. Further, we test the poll_owner to avoid recursion on UP * systems where the lock doesn't exist. * * In cases where there is bi-directional communications, reading only * one message at a time can lead to packets being dropped by the * network adapter, forcing superfluous retries and possibly timeouts. * Thus, we set our budget to greater than 1. */static int poll_one_napi(struct netpoll_info *npinfo,			 struct napi_struct *napi, int budget){	int work; 	/* net_rx_action's ->poll() invocations and our's are	 * synchronized by this test which is only made while	 * holding the napi->poll_lock.	 */	if (!test_bit(NAPI_STATE_SCHED, &napi->state))		return budget; 	npinfo->rx_flags |= NETPOLL_RX_DROP;	atomic_inc(&trapped);	set_bit(NAPI_STATE_NPSVC, &napi->state); 	work = napi->poll(napi, budget);	trace_napi_poll(napi); 	clear_bit(NAPI_STATE_NPSVC, &napi->state);	atomic_dec(&trapped);	npinfo->rx_flags &= ~NETPOLL_RX_DROP; 	return budget - work;} static void poll_napi(struct net_device *dev){	struct napi_struct *napi;	int budget = 16; 	list_for_each_entry(napi, &dev->napi_list, dev_list) {		if (napi->poll_owner != smp_processor_id() &&		    spin_trylock(&napi->poll_lock)) {			budget = poll_one_napi(rcu_dereference_bh(dev->npinfo),					       napi, budget);			spin_unlock(&napi->poll_lock); 			if (!budget)				break;		}	}} static void service_neigh_queue(struct netpoll_info *npi){	if (npi) {		struct sk_buff *skb; 		while ((skb = skb_dequeue(&npi->neigh_tx)))			netpoll_neigh_reply(skb, npi);	}} static void netpoll_poll_dev(struct net_device *dev){	const struct net_device_ops *ops;	struct netpoll_info *ni = rcu_dereference_bh(dev->npinfo); 	/* Don't do any rx activity if the dev_lock mutex is held	 * the dev_open/close paths use this to block netpoll activity	 * while changing device state	 */	if (down_trylock(&ni->dev_lock))		return; 	if (!netif_running(dev)) {		up(&ni->dev_lock);		return;	} 	ops = dev->netdev_ops;	if (!ops->ndo_poll_controller) {		up(&ni->dev_lock);		return;	} 	/* Process pending work on NIC */	ops->ndo_poll_controller(dev); 	poll_napi(dev); 	up(&ni->dev_lock); 	if (dev->flags & IFF_SLAVE) {		if (ni) {			struct net_device *bond_dev;			struct sk_buff *skb;			struct netpoll_info *bond_ni; 			bond_dev = netdev_master_upper_dev_get_rcu(dev);			bond_ni = rcu_dereference_bh(bond_dev->npinfo);			while ((skb = skb_dequeue(&ni->neigh_tx))) {				skb->dev = bond_dev;				skb_queue_tail(&bond_ni->neigh_tx, skb);			}		}	} 	service_neigh_queue(ni); 	zap_completion_queue();} void netpoll_rx_disable(struct net_device *dev){	struct netpoll_info *ni;	int idx;	might_sleep();	idx = srcu_read_lock(&netpoll_srcu);	ni = srcu_dereference(dev->npinfo, &netpoll_srcu);	if (ni)		down(&ni->dev_lock);	srcu_read_unlock(&netpoll_srcu, idx);}EXPORT_SYMBOL(netpoll_rx_disable); void netpoll_rx_enable(struct net_device *dev){	struct netpoll_info *ni;	rcu_read_lock();	ni = rcu_dereference(dev->npinfo);	if (ni)		up(&ni->dev_lock);	rcu_read_unlock();}EXPORT_SYMBOL(netpoll_rx_enable); static void refill_skbs(void){	struct sk_buff *skb;	unsigned long flags; 	spin_lock_irqsave(&skb_pool.lock, flags);	while (skb_pool.qlen < MAX_SKBS) {		skb = alloc_skb(MAX_SKB_SIZE, GFP_ATOMIC);		if (!skb)			break; 		__skb_queue_tail(&skb_pool, skb);	}	spin_unlock_irqrestore(&skb_pool.lock, flags);} static void zap_completion_queue(void){	unsigned long flags;	struct softnet_data *sd = &get_cpu_var(softnet_data); 	if (sd->completion_queue) {		struct sk_buff *clist; 		local_irq_save(flags);		clist = sd->completion_queue;		sd->completion_queue = NULL;		local_irq_restore(flags); 		while (clist != NULL) {			struct sk_buff *skb = clist;			clist = clist->next;			if (skb->destructor) {				atomic_inc(&skb->users);				dev_kfree_skb_any(skb); /* put this one back */			} else {				__kfree_skb(skb);			}		}	} 	put_cpu_var(softnet_data);} static struct sk_buff *find_skb(struct netpoll *np, int len, int reserve){	int count = 0;	struct sk_buff *skb; 	zap_completion_queue();	refill_skbs();repeat: 	skb = alloc_skb(len, GFP_ATOMIC);	if (!skb)		skb = skb_dequeue(&skb_pool); 	if (!skb) {		if (++count < 10) {			netpoll_poll_dev(np->dev);			goto repeat;		}		return NULL;	} 	atomic_set(&skb->users, 1);	skb_reserve(skb, reserve);	return skb;} static int netpoll_owner_active(struct net_device *dev){	struct napi_struct *napi; 	list_for_each_entry(napi, &dev->napi_list, dev_list) {		if (napi->poll_owner == smp_processor_id())			return 1;	}	return 0;} /* call with IRQ disabled */void netpoll_send_skb_on_dev(struct netpoll *np, struct sk_buff *skb,			     struct net_device *dev){	int status = NETDEV_TX_BUSY;	unsigned long tries;	const struct net_device_ops *ops = dev->netdev_ops;	/* It is up to the caller to keep npinfo alive. */	struct netpoll_info *npinfo; 	WARN_ON_ONCE(!irqs_disabled()); 	npinfo = rcu_dereference_bh(np->dev->npinfo);	if (!npinfo || !netif_running(dev) || !netif_device_present(dev)) {		__kfree_skb(skb);		return;	} 	/* don't get messages out of order, and no recursion */	if (skb_queue_len(&npinfo->txq) == 0 && !netpoll_owner_active(dev)) {		struct netdev_queue *txq; 		txq = netdev_pick_tx(dev, skb, NULL); 		/* try until next clock tick */		for (tries = jiffies_to_usecs(1)/USEC_PER_POLL;		     tries > 0; --tries) {			if (__netif_tx_trylock(txq)) {				if (!netif_xmit_stopped(txq)) {					if (vlan_tx_tag_present(skb) &&					    !vlan_hw_offload_capable(netif_skb_features(skb),								     skb->vlan_proto)) {						skb = __vlan_put_tag(skb, skb->vlan_proto, vlan_tx_tag_get(skb));						if (unlikely(!skb)) {							/* This is actually a packet drop, but we							 * don't want the code at the end of this							 * function to try and re-queue a NULL skb.							 */							status = NETDEV_TX_OK;							goto unlock_txq;						}						skb->vlan_tci = 0;					} 					status = ops->ndo_start_xmit(skb, dev);					if (status == NETDEV_TX_OK)						txq_trans_update(txq);				}			unlock_txq:				__netif_tx_unlock(txq); 				if (status == NETDEV_TX_OK)					break; 			} 			/* tickle device maybe there is some cleanup */			netpoll_poll_dev(np->dev); 			udelay(USEC_PER_POLL);		} 		WARN_ONCE(!irqs_disabled(),			"netpoll_send_skb_on_dev(): %s enabled interrupts in poll (%pF)\n",			dev->name, ops->ndo_start_xmit); 	} 	if (status != NETDEV_TX_OK) {		skb_queue_tail(&npinfo->txq, skb);		schedule_delayed_work(&npinfo->tx_work,0);	}}EXPORT_SYMBOL(netpoll_send_skb_on_dev); void netpoll_send_udp(struct netpoll *np, const char *msg, int len){	int total_len, ip_len, udp_len;	struct sk_buff *skb;	struct udphdr *udph;	struct iphdr *iph;	struct ethhdr *eth;	static atomic_t ip_ident;	struct ipv6hdr *ip6h; 	udp_len = len + sizeof(*udph);	if (np->ipv6)		ip_len = udp_len + sizeof(*ip6h);	else		ip_len = udp_len + sizeof(*iph); 	total_len = ip_len + LL_RESERVED_SPACE(np->dev); 	skb = find_skb(np, total_len + np->dev->needed_tailroom,		       total_len - len);	if (!skb)		return; 	skb_copy_to_linear_data(skb, msg, len);	skb_put(skb, len); 	skb_push(skb, sizeof(*udph));	skb_reset_transport_header(skb);	udph = udp_hdr(skb);	udph->source = htons(np->local_port);	udph->dest = htons(np->remote_port);	udph->len = htons(udp_len); 	if (np->ipv6) {		udph->check = 0;		udph->check = csum_ipv6_magic(&np->local_ip.in6,					      &np->remote_ip.in6,					      udp_len, IPPROTO_UDP,					      csum_partial(udph, udp_len, 0));		if (udph->check == 0)			udph->check = CSUM_MANGLED_0; 		skb_push(skb, sizeof(*ip6h));		skb_reset_network_header(skb);		ip6h = ipv6_hdr(skb); 		/* ip6h->version = 6; ip6h->priority = 0; */		put_unaligned(0x60, (unsigned char *)ip6h);		ip6h->flow_lbl[0] = 0;		ip6h->flow_lbl[1] = 0;		ip6h->flow_lbl[2] = 0; 		ip6h->payload_len = htons(sizeof(struct udphdr) + len);		ip6h->nexthdr = IPPROTO_UDP;		ip6h->hop_limit = 32;		ip6h->saddr = np->local_ip.in6;		ip6h->daddr = np->remote_ip.in6; 		eth = (struct ethhdr *) skb_push(skb, ETH_HLEN);		skb_reset_mac_header(skb);		skb->protocol = eth->h_proto = htons(ETH_P_IPV6);	} else {		udph->check = 0;		udph->check = csum_tcpudp_magic(np->local_ip.ip,						np->remote_ip.ip,						udp_len, IPPROTO_UDP,						csum_partial(udph, udp_len, 0));		if (udph->check == 0)			udph->check = CSUM_MANGLED_0; 

Lines 1–500 of 1323.