path: root/net/core/netpoll.c

/*
 * 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.
 */

#include <linux/moduleparam.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 <net/tcp.h>
#include <net/udp.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 USEC_PER_POLL	50
#define NETPOLL_RX_ENABLED  1
#define NETPOLL_RX_DROP     2

#define MAX_SKB_SIZE \
		(MAX_UDP_CHUNK + sizeof(struct udphdr) + \
				sizeof(struct iphdr) + sizeof(struct ethhdr))

static void zap_completion_queue(void);
static void arp_reply(struct sk_buff *skb);

static unsigned int carrier_timeout = 4;
module_param(carrier_timeout, uint, 0644);

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_tx_queue_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(dev->npinfo, napi, budget);
			spin_unlock(&napi->poll_lock);

			if (!budget)
				break;
		}
	}
}

static void service_arp_queue(struct netpoll_info *npi)
{
	if (npi) {
		struct sk_buff *skb;

		while ((skb = skb_dequeue(&npi->arp_tx)))
			arp_reply(skb);
	}
}

void netpoll_poll_dev(struct net_device *dev)
{
	const struct net_device_ops *ops;

	if (!dev || !netif_running(dev))
		r