netpoll.c

Linux Kernel 2.6.9 for OMAP1710

/*
 * Common framework for low-level network console, dump, and debugger code
 *
 * Sep 8 2003  Matt Mackall <[e-mail]>
 *
 * based on the netconsole code from:
 *
 * Copyright (C) 2001  Ingo Molnar <[e-mail]>
 * Copyright (C) 2002  Red Hat, Inc.
 */

#include <linux/smp_lock.h>
#include <linux/netdevice.h>
#include <linux/etherdevice.h>
#include <linux/string.h>
#include <linux/inetdevice.h>
#include <linux/inet.h>
#include <linux/interrupt.h>
#include <linux/netpoll.h>
#include <linux/sched.h>
#include <linux/rcupdate.h>
#include <net/tcp.h>
#include <net/udp.h>
#include <asm/unaligned.h>

/*
 * We maintain a small pool of fully-sized skbs, to make sure the
 * message gets out even in extreme OOM situations.
 */

#define MAX_SKBS 32
#define MAX_UDP_CHUNK 1460

static spinlock_t skb_list_lock = SPIN_LOCK_UNLOCKED;
static int nr_skbs;
static struct sk_buff *skbs;

static spinlock_t rx_list_lock = SPIN_LOCK_UNLOCKED;
static LIST_HEAD(rx_list);

static atomic_t trapped;
spinlock_t netpoll_poll_lock = SPIN_LOCK_UNLOCKED;

#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 int checksum_udp(struct sk_buff *skb, struct udphdr *uh,
			     unsigned short ulen, u32 saddr, u32 daddr)
{
	if (uh->check == 0)
		return 0;

	if (skb->ip_summed == CHECKSUM_HW)
		return csum_tcpudp_magic(
			saddr, daddr, ulen, IPPROTO_UDP, skb->csum);

	skb->csum = csum_tcpudp_nofold(saddr, daddr, ulen, IPPROTO_UDP, 0);

	return csum_fold(skb_checksum(skb, 0, skb->len, skb->csum));
}

void netpoll_poll(struct netpoll *np)
{
	/*
	 * 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 a more reasonable value.
	 */
	int budget = 16;
	unsigned long flags;

	if(!np->dev || !netif_running(np->dev) || !np->dev->poll_controller)
		return;

	/* Process pending work on NIC */
	np->dev->poll_controller(np->dev);

	/* If scheduling is stopped, tickle NAPI bits */
	spin_lock_irqsave(&netpoll_poll_lock, flags);
	if (np->dev->poll &&
	    test_bit(__LINK_STATE_RX_SCHED, &np->dev->state)) {
		np->dev->netpoll_rx |= NETPOLL_RX_DROP;
		atomic_inc(&trapped);

		np->dev->poll(np->dev, &budget);

		atomic_dec(&trapped);
		np->dev->netpoll_rx &= ~NETPOLL_RX_DROP;
	}
	spin_unlock_irqrestore(&netpoll_poll_lock, flags);

	zap_completion_queue();
}

static void refill_skbs(void)
{
	struct sk_buff *skb;
	unsigned long flags;

	spin_lock_irqsave(&skb_list_lock, flags);
	while (nr_skbs < MAX_SKBS) {
		skb = alloc_skb(MAX_SKB_SIZE, GFP_ATOMIC);
		if (!skb)
			break;

		skb->next = skbs;
		skbs = skb;
		nr_skbs++;
	}
	spin_unlock_irqrestore(&skb_list_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;
			__kfree_skb(skb);
		}
	}

	put_cpu_var(softnet_data);
}

static struct sk_buff * find_skb(struct netpoll *np, int len, int reserve)
{
	int once = 1, count = 0;
	unsigned long flags;
	struct sk_buff *skb = NULL;

	zap_completion_queue();
repeat:
	if (nr_skbs < MAX_SKBS)
		refill_skbs();

	skb = alloc_skb(len, GFP_ATOMIC);

	if (!skb) {
		spin_lock_irqsave(&skb_list_lock, flags);
		skb = skbs;
		if (skb)
			skbs = skb->next;
		skb->next = NULL;
		nr_skbs--;
		spin_unlock_irqrestore(&skb_list_lock, flags);
	}

	if(!skb) {
		count++;
		if (once && (count == 1000000)) {
			printk("out of netpoll skbs!\n");
			once = 0;
		}
		netpoll_poll(np);
		goto repeat;
	}

	atomic_set(&skb->users, 1);
	skb_reserve(skb, reserve);
	return skb;
}

void netpoll_send_skb(struct netpoll *np, struct sk_buff *skb)
{
	int status;

repeat:
	if(!np || !np->dev || !netif_running(np->dev)) {
		__kfree_skb(skb);
		return;
	}

	spin_lock(&np->dev->xmit_lock);
	np->dev->xmit_lock_owner = smp_processor_id();

	/*
	 * network drivers do not expect to be called if the queue is
	 * stopped.
	 */
	if (netif_queue_stopped(np->dev)) {
		np->dev->xmit_lock_owner = -1;
		spin_unlock(&np->dev->xmit_lock);

		netpoll_poll(np);
		goto repeat;
	}

	status = np->dev->hard_start_xmit(skb, np->dev);
	np->dev->xmit_lock_owner = -1;
	spin_unlock(&np->dev->xmit_lock);

	/* transmit busy */
	if(status) {
		netpoll_poll(np);
		goto repeat;
	}
}

void netpoll_send_udp(struct netpoll *np, const char *msg, int len)
{
	int total_len, eth_len, ip_len, udp_len;
	struct sk_buff *skb;
	struct udphdr *udph;
	struct iphdr *iph;
	struct ethhdr *eth;

	udp_len = len + sizeof(*udph);
	ip_len = eth_len = udp_len + sizeof(*iph);
	total_len = eth_len + ETH_HLEN;

	skb = find_skb(np, total_len, total_len - len);
	if (!skb)
		return;

	memcpy(skb->data, msg, len);
	skb->len += len;

	udph = (struct udphdr *) skb_push(skb, sizeof(*udph));
	udph->source = htons(np->local_port);
	udph->dest = htons(np->remote_port);
	udph->len = htons(udp_len);
	udph->check = 0;

	iph = (struct iphdr *)skb_push(skb, sizeof(*iph));

	/* iph->version = 4; iph->ihl = 5; */
	put_unaligned(0x45, (unsigned char *)iph);
	iph->tos      = 0;
	put_unaligned(htons(ip_len), &(iph->tot_len));
	iph->id       = 0;
	iph->frag_off = 0;
	iph->ttl      = 64;
	iph->protocol = IPPROTO_UDP;
	iph->check    = 0;
	put_unaligned(htonl(np->local_ip), &(iph->saddr));
	put_unaligned(htonl(np->remote_ip), &(iph->daddr));
	iph->check    = ip_fast_csum((unsigned char *)iph, iph->ihl);

	eth = (struct ethhdr *) skb_push(skb, ETH_HLEN);

	eth->h_proto = htons(ETH_P_IP);
	memcpy(eth->h_source, np->local_mac, 6);
	memcpy(eth->h_dest, np->remote_mac, 6);

	netpoll_send_skb(np, skb);
}

static void arp_reply(struct sk_buff *skb)
{
	struct arphdr *arp;
	unsigned char *arp_ptr;
	int size, type = ARPOP_REPLY, ptype = ETH_P_ARP;
	u32 sip, tip;
	struct sk_buff *send_skb;
	unsigned long flags;
	struct list_head *p;
	struct netpoll *np = NULL;

	spin_lock_irqsave(&rx_list_lock, flags);
	list_for_each(p, &rx_list) {
		np = list_entry(p, struct netpoll, rx_list);
		if ( np->dev == skb->dev )
			break;
		np = NULL;
	}
	spin_unlock_irqrestore(&rx_list_lock, flags);

	if (!np) return;

	/* No arp on this interface */
	if (skb->dev->flags & IFF_NOARP)
		return;

	if (!pskb_may_pull(skb, (sizeof(struct arphdr) +
				 (2 * skb->dev->addr_len) +
				 (2 * sizeof(u32)))))
		return;

	skb->h.raw = skb->nh.raw = skb->data;
	arp = skb->nh.arph;

	if ((arp->ar_hrd != htons(ARPHRD_ETHER) &&
	     arp->ar_hrd != htons(ARPHRD_IEEE802)) ||
	    arp->ar_pro != htons(ETH_P_IP) ||
	    arp->ar_op != htons(ARPOP_REQUEST))
		return;

	arp_ptr = (unsigned char *)(arp+1) + skb->dev->addr_len;
	memcpy(&sip, arp_ptr, 4);
	arp_ptr += 4 + skb->dev->addr_len;
	memcpy(&tip, arp_ptr, 4);

	/* Should we ignore arp? */
	if (tip != htonl(np->local_ip) || LOOPBACK(tip) || MULTICAST(tip))
		return;

	size = sizeof(struct arphdr) + 2 * (skb->dev->addr_len + 4);
	send_skb = find_skb(np, size + LL_RESERVED_SPACE(np->dev),
			    LL_RESERVED_SPACE(np->dev));

	if (!send_skb)
		return;

	send_skb->nh.raw = send_skb->data;
	arp = (struct arphdr *) skb_put(send_skb, size);
	send_skb->dev = skb->dev;
	send_skb->protocol = htons(ETH_P_ARP);

	/* Fill the device header for the ARP frame */

	if (np->dev->hard_header &&
	    np->dev->hard_header(send_skb, skb->dev, ptype,
				       np->remote_mac, np->local_mac,
				       send_skb->len) < 0) {
		kfree_skb(send_skb);
		return;
	}

	/*
	 * Fill out the arp protocol part.
	 *
	 * we only support ethernet device type,
	 * which (according to RFC 1390) should always equal 1 (Ethernet).