[patch] softirq-2.4.10-B3

[Ingo Molnar <mingo@elte.hu>]

[-- Attachment #1: Type: TEXT/PLAIN, Size: 418 bytes --]


On Fri, 28 Sep 2001 kuznet@ms2.inr.ac.ru wrote:

> >  - '[ksoftirqd_CPU0]' is confusing on UP systems, changed it to
> >    '[ksoftirqd]' instead.
>
> It is useless to argue about preferences, but universal naming scheme
> looks as less confusing yet. :-)

since you are the second one to complain, i'm convinced :) reverted.

i've also added back the BUG() check for smp_processor_id() == cpu.

-B3 attached.

	Ingo

[-- Attachment #2: Type: TEXT/PLAIN, Size: 28319 bytes --]

--- linux/kernel/ksyms.c.orig	Wed Sep 26 17:04:40 2001
+++ linux/kernel/ksyms.c	Wed Sep 26 17:04:48 2001
@@ -538,8 +538,6 @@
 EXPORT_SYMBOL(tasklet_kill);
 EXPORT_SYMBOL(__run_task_queue);
 EXPORT_SYMBOL(do_softirq);
-EXPORT_SYMBOL(raise_softirq);
-EXPORT_SYMBOL(cpu_raise_softirq);
 EXPORT_SYMBOL(__tasklet_schedule);
 EXPORT_SYMBOL(__tasklet_hi_schedule);
 
--- linux/kernel/sched.c.orig	Wed Sep 26 17:04:40 2001
+++ linux/kernel/sched.c	Wed Sep 26 17:04:48 2001
@@ -366,6 +366,28 @@
 }
 
 /**
+ * unwakeup - undo wakeup if possible.
+ * @p: task
+ * @state: new task state
+ *
+ * Undo a previous wakeup of the specified task - if the process
+ * is not running already. The main interface to be used is
+ * unwakeup_process(), it will do a lockless test whether the task
+ * is on the runqueue.
+ */
+void __unwakeup_process(struct task_struct * p, long state)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&runqueue_lock, flags);
+	if (!p->has_cpu && (p != current) && task_on_runqueue(p)) {
+		del_from_runqueue(p);
+		p->state = state;
+	}
+	spin_unlock_irqrestore(&runqueue_lock, flags);
+}
+
+/**
  * schedule_timeout - sleep until timeout
  * @timeout: timeout value in jiffies
  *
--- linux/kernel/softirq.c.orig	Wed Sep 26 17:04:40 2001
+++ linux/kernel/softirq.c	Fri Sep 28 18:16:21 2001
@@ -58,12 +58,35 @@
 		wake_up_process(tsk);
 }
 
+/*
+ * If a softirqs were fully handled after ksoftirqd was woken
+ * up then try to undo the wakeup.
+ */
+static inline void unwakeup_softirqd(unsigned cpu)
+{
+	struct task_struct * tsk = ksoftirqd_task(cpu);
+
+	if (tsk)
+		unwakeup_process(tsk, TASK_INTERRUPTIBLE);
+}
+
+/*
+ * We restart softirq processing MAX_SOFTIRQ_RESTART times,
+ * and we fall back to softirqd after that.
+ *
+ * This number has been established via experimentation.
+ * The two things to balance is latency against fairness -
+ * we want to handle softirqs as soon as possible, but they
+ * should not be able to lock up the box.
+ */
+#define MAX_SOFTIRQ_RESTART 10
+
 asmlinkage void do_softirq()
 {
+	int max_restart = MAX_SOFTIRQ_RESTART;
 	int cpu = smp_processor_id();
 	__u32 pending;
 	long flags;
-	__u32 mask;
 
 	if (in_interrupt())
 		return;
@@ -75,7 +98,6 @@
 	if (pending) {
 		struct softirq_action *h;
 
-		mask = ~pending;
 		local_bh_disable();
 restart:
 		/* Reset the pending bitmask before enabling irqs */
@@ -95,55 +117,37 @@
 		local_irq_disable();
 
 		pending = softirq_pending(cpu);
-		if (pending & mask) {
-			mask &= ~pending;
+		if (pending && --max_restart && (current->need_resched != 1))
 			goto restart;
-		}
 		__local_bh_enable();
 
 		if (pending)
+			/*
+			 * In the normal case ksoftirqd is rarely activated,
+			 * increased scheduling hurts performance.
+			 * It's a safety measure: if external load starts
+			 * to flood the system with softirqs then we
+			 * will mitigate softirq work to the softirq thread.
+			 */
 			wakeup_softirqd(cpu);
+		else
+			/*
+			 * All softirqs are handled - undo any possible
+			 * wakeup of softirqd. This reduces context switch
+			 * overhead.
+			 */
+			unwakeup_softirqd(cpu);
 	}
 
 	local_irq_restore(flags);
 }
 
-/*
- * This function must run with irq disabled!
- */
-inline void cpu_raise_softirq(unsigned int cpu, unsigned int nr)
-{
-	__cpu_raise_softirq(cpu, nr);
-
-	/*
-	 * If we're in an interrupt or bh, we're done
-	 * (this also catches bh-disabled code). We will
-	 * actually run the softirq once we return from
-	 * the irq or bh.
-	 *
-	 * Otherwise we wake up ksoftirqd to make sure we
-	 * schedule the softirq soon.
-	 */
-	if (!(local_irq_count(cpu) | local_bh_count(cpu)))
-		wakeup_softirqd(cpu);
-}
-
-void raise_softirq(unsigned int nr)
-{
-	long flags;
-
-	local_irq_save(flags);
-	cpu_raise_softirq(smp_processor_id(), nr);
-	local_irq_restore(flags);
-}
-
 void open_softirq(int nr, void (*action)(struct softirq_action*), void *data)
 {
 	softirq_vec[nr].data = data;
 	softirq_vec[nr].action = action;
 }
 
-
 /* Tasklets */
 
 struct tasklet_head tasklet_vec[NR_CPUS] __cacheline_aligned;
@@ -157,8 +161,9 @@
 	local_irq_save(flags);
 	t->next = tasklet_vec[cpu].list;
 	tasklet_vec[cpu].list = t;
-	cpu_raise_softirq(cpu, TASKLET_SOFTIRQ);
+	__cpu_raise_softirq(cpu, TASKLET_SOFTIRQ);
 	local_irq_restore(flags);
+	rerun_softirqs(cpu);
 }
 
 void __tasklet_hi_schedule(struct tasklet_struct *t)
@@ -169,8 +174,9 @@
 	local_irq_save(flags);
 	t->next = tasklet_hi_vec[cpu].list;
 	tasklet_hi_vec[cpu].list = t;
-	cpu_raise_softirq(cpu, HI_SOFTIRQ);
+	__cpu_raise_softirq(cpu, HI_SOFTIRQ);
 	local_irq_restore(flags);
+	rerun_softirqs(cpu);
 }
 
 static void tasklet_action(struct softirq_action *a)
@@ -241,7 +247,6 @@
 	}
 }
 
-
 void tasklet_init(struct tasklet_struct *t,
 		  void (*func)(unsigned long), unsigned long data)
 {
@@ -268,8 +273,6 @@
 	clear_bit(TASKLET_STATE_SCHED, &t->state);
 }
 
-
-
 /* Old style BHs */
 
 static void (*bh_base[32])(void);
@@ -325,7 +328,7 @@
 {
 	int i;
 
-	for (i=0; i<32; i++)
+	for (i = 0; i < 32; i++)
 		tasklet_init(bh_task_vec+i, bh_action, i);
 
 	open_softirq(TASKLET_SOFTIRQ, tasklet_action, NULL);
@@ -361,38 +364,41 @@
 
 static int ksoftirqd(void * __bind_cpu)
 {
-	int bind_cpu = *(int *) __bind_cpu;
-	int cpu = cpu_logical_map(bind_cpu);
+	int cpu = cpu_logical_map((int)__bind_cpu);
 
 	daemonize();
-	current->nice = 19;
+
 	sigfillset(&current->blocked);
 
 	/* Migrate to the right CPU */
-	current->cpus_allowed = 1UL << cpu;
-	while (smp_processor_id() != cpu)
-		schedule();
-
-	sprintf(current->comm, "ksoftirqd_CPU%d", bind_cpu);
+	current->cpus_allowed = 1 << cpu;
 
-	__set_current_state(TASK_INTERRUPTIBLE);
-	mb();
+	sprintf(current->comm, "ksoftirqd CPU%d", cpu);
 
+	current->nice = 19;
+	schedule();
 	ksoftirqd_task(cpu) = current;
 
-	for (;;) {
-		if (!softirq_pending(cpu))
-			schedule();
-
-		__set_current_state(TASK_RUNNING);
+	if (smp_processor_id() != cpu)
+		BUG();
 
+	for (;;) {
 		while (softirq_pending(cpu)) {
 			do_softirq();
 			if (current->need_resched)
-				schedule();
+				goto preempt;
 		}
 
 		__set_current_state(TASK_INTERRUPTIBLE);
+		/* This has to be here to make the test IRQ-correct. */
+		barrier();
+		if (!softirq_pending(cpu)) {
+preempt:
+			if (current->counter > 1)
+				current->counter = 1;
+			schedule();
+		}
+		__set_current_state(TASK_RUNNING);
 	}
 }
 
@@ -400,17 +406,10 @@
 {
 	int cpu;
 
-	for (cpu = 0; cpu < smp_num_cpus; cpu++) {
-		if (kernel_thread(ksoftirqd, (void *) &cpu,
+	for (cpu = 0; cpu < smp_num_cpus; cpu++)
+		if (kernel_thread(ksoftirqd, (void *) cpu,
 				  CLONE_FS | CLONE_FILES | CLONE_SIGNAL) < 0)
-			printk("spawn_ksoftirqd() failed for cpu %d\n", cpu);
-		else {
-			while (!ksoftirqd_task(cpu_logical_map(cpu))) {
-				current->policy |= SCHED_YIELD;
-				schedule();
-			}
-		}
-	}
+			BUG();
 
 	return 0;
 }
--- linux/include/linux/netdevice.h.orig	Wed Sep 26 17:04:36 2001
+++ linux/include/linux/netdevice.h	Fri Sep 28 07:44:01 2001
@@ -486,8 +486,9 @@
 		local_irq_save(flags);
 		dev->next_sched = softnet_data[cpu].output_queue;
 		softnet_data[cpu].output_queue = dev;
-		cpu_raise_softirq(cpu, NET_TX_SOFTIRQ);
+		__cpu_raise_softirq(cpu, NET_TX_SOFTIRQ);
 		local_irq_restore(flags);
+		rerun_softirqs(cpu);
 	}
 }
 
@@ -535,8 +536,9 @@
 		local_irq_save(flags);
 		skb->next = softnet_data[cpu].completion_queue;
 		softnet_data[cpu].completion_queue = skb;
-		cpu_raise_softirq(cpu, NET_TX_SOFTIRQ);
+		__cpu_raise_softirq(cpu, NET_TX_SOFTIRQ);
 		local_irq_restore(flags);
+		rerun_softirqs(cpu);
 	}
 }
 
--- linux/include/linux/interrupt.h.orig	Wed Sep 26 17:04:40 2001
+++ linux/include/linux/interrupt.h	Fri Sep 28 07:44:01 2001
@@ -74,9 +74,14 @@
 asmlinkage void do_softirq(void);
 extern void open_softirq(int nr, void (*action)(struct softirq_action*), void *data);
 extern void softirq_init(void);
-#define __cpu_raise_softirq(cpu, nr) do { softirq_pending(cpu) |= 1UL << (nr); } while (0)
-extern void FASTCALL(cpu_raise_softirq(unsigned int cpu, unsigned int nr));
-extern void FASTCALL(raise_softirq(unsigned int nr));
+#define __cpu_raise_softirq(cpu, nr) \
+		do { softirq_pending(cpu) |= 1UL << (nr); } while (0)
+
+#define rerun_softirqs(cpu) 					\
+do {								\
+	if (!(local_irq_count(cpu) | local_bh_count(cpu)))	\
+		do_softirq();					\
+} while (0);
 
 
 
--- linux/include/linux/sched.h.orig	Wed Sep 26 17:04:40 2001
+++ linux/include/linux/sched.h	Fri Sep 28 07:44:01 2001
@@ -556,6 +556,7 @@
 
 extern void FASTCALL(__wake_up(wait_queue_head_t *q, unsigned int mode, int nr));
 extern void FASTCALL(__wake_up_sync(wait_queue_head_t *q, unsigned int mode, int nr));
+extern void FASTCALL(__unwakeup_process(struct task_struct * p, long state));
 extern void FASTCALL(sleep_on(wait_queue_head_t *q));
 extern long FASTCALL(sleep_on_timeout(wait_queue_head_t *q,
 				      signed long timeout));
@@ -574,6 +575,13 @@
 #define wake_up_interruptible_all(x)	__wake_up((x),TASK_INTERRUPTIBLE, 0)
 #define wake_up_interruptible_sync(x)	__wake_up_sync((x),TASK_INTERRUPTIBLE, 1)
 #define wake_up_interruptible_sync_nr(x) __wake_up_sync((x),TASK_INTERRUPTIBLE,  nr)
+
+#define unwakeup_process(tsk,state)		\
+do {						\
+	if (task_on_runqueue(tsk))		\
+		__unwakeup_process(tsk,state);	\
+} while (0)
+
 asmlinkage long sys_wait4(pid_t pid,unsigned int * stat_addr, int options, struct rusage * ru);
 
 extern int in_group_p(gid_t);
--- linux/include/asm-mips/softirq.h.orig	Wed Sep 26 20:58:00 2001
+++ linux/include/asm-mips/softirq.h	Wed Sep 26 20:58:07 2001
@@ -40,6 +40,4 @@
 
 #define in_softirq() (local_bh_count(smp_processor_id()) != 0)
 
-#define __cpu_raise_softirq(cpu, nr)	set_bit(nr, &softirq_pending(cpu))
-
 #endif /* _ASM_SOFTIRQ_H */
--- linux/include/asm-mips64/softirq.h.orig	Wed Sep 26 20:58:20 2001
+++ linux/include/asm-mips64/softirq.h	Wed Sep 26 20:58:26 2001
@@ -39,19 +39,4 @@
 
 #define in_softirq() (local_bh_count(smp_processor_id()) != 0)
 
-extern inline void __cpu_raise_softirq(int cpu, int nr)
-{
-	unsigned int *m = (unsigned int *) &softirq_pending(cpu);
-	unsigned int temp;
-
-	__asm__ __volatile__(
-		"1:\tll\t%0, %1\t\t\t# __cpu_raise_softirq\n\t"
-		"or\t%0, %2\n\t"
-		"sc\t%0, %1\n\t"
-		"beqz\t%0, 1b"
-		: "=&r" (temp), "=m" (*m)
-		: "ir" (1UL << nr), "m" (*m)
-		: "memory");
-}
-
 #endif /* _ASM_SOFTIRQ_H */
--- linux/net/core/dev.c.orig	Wed Sep 26 17:04:41 2001
+++ linux/net/core/dev.c	Wed Sep 26 17:04:48 2001
@@ -1218,8 +1218,9 @@
 			dev_hold(skb->dev);
 			__skb_queue_tail(&queue->input_pkt_queue,skb);
 			/* Runs from irqs or BH's, no need to wake BH */
-			cpu_raise_softirq(this_cpu, NET_RX_SOFTIRQ);
+			__cpu_raise_softirq(this_cpu, NET_RX_SOFTIRQ);
 			local_irq_restore(flags);
+			rerun_softirqs(this_cpu);
 #ifndef OFFLINE_SAMPLE
 			get_sample_stats(this_cpu);
 #endif
@@ -1529,8 +1530,9 @@
 	local_irq_disable();
 	netdev_rx_stat[this_cpu].time_squeeze++;
 	/* This already runs in BH context, no need to wake up BH's */
-	cpu_raise_softirq(this_cpu, NET_RX_SOFTIRQ);
+	__cpu_raise_softirq(this_cpu, NET_RX_SOFTIRQ);
 	local_irq_enable();
+	rerun_softirqs(this_cpu);
 
 	NET_PROFILE_LEAVE(softnet_process);
 	return;
--- linux/linux/include/linux/netdevice.h.orig	Wed Sep 26 21:14:55 2001
+++ linux/linux/include/linux/netdevice.h	Thu Sep 27 07:51:00 2001
@@ -390,6 +390,8 @@
 						     unsigned char *haddr);
 	int			(*neigh_setup)(struct net_device *dev, struct neigh_parms *);
 	int			(*accept_fastpath)(struct net_device *, struct dst_entry*);
+#define HAVE_POLL_CONTROLLER
+	void			(*poll_controller)(struct net_device *dev);
 
 	/* open/release and usage marking */
 	struct module *owner;
--- linux/linux/drivers/net/tulip/tulip_core.c.orig	Wed Sep 26 21:14:58 2001
+++ linux/linux/drivers/net/tulip/tulip_core.c	Fri Sep 28 09:23:22 2001
@@ -243,6 +243,7 @@
 static struct net_device_stats *tulip_get_stats(struct net_device *dev);
 static int private_ioctl(struct net_device *dev, struct ifreq *rq, int cmd);
 static void set_rx_mode(struct net_device *dev);
+static void poll_tulip(struct net_device *dev);
 
 
 
@@ -1671,6 +1672,9 @@
 	dev->get_stats = tulip_get_stats;
 	dev->do_ioctl = private_ioctl;
 	dev->set_multicast_list = set_rx_mode;
+#ifdef HAVE_POLL_CONTROLLER
+	dev->poll_controller = &poll_tulip;
+#endif
 
 	if (register_netdev(dev))
 		goto err_out_free_ring;
@@ -1839,6 +1843,24 @@
 
 	/* pci_power_off (pdev, -1); */
 }
+
+
+#ifdef HAVE_POLL_CONTROLLER
+
+/*
+ * Polling 'interrupt' - used by things like netconsole to send skbs
+ * without having to re-enable interrupts. It's not called while
+ * the interrupt routine is executing.
+ */
+
+static void poll_tulip (struct net_device *dev)
+{
+       disable_irq(dev->irq);
+       tulip_interrupt (dev->irq, dev, NULL);
+       enable_irq(dev->irq);
+}
+
+#endif
 
 
 static struct pci_driver tulip_driver = {
--- linux/linux/drivers/net/eepro100.c.orig	Wed Sep 26 21:14:58 2001
+++ linux/linux/drivers/net/eepro100.c	Thu Sep 27 08:11:41 2001
@@ -542,6 +542,7 @@
 static int speedo_rx(struct net_device *dev);
 static void speedo_tx_buffer_gc(struct net_device *dev);
 static void speedo_interrupt(int irq, void *dev_instance, struct pt_regs *regs);
+static void poll_speedo (struct net_device *dev);
 static int speedo_close(struct net_device *dev);
 static struct net_device_stats *speedo_get_stats(struct net_device *dev);
 static int speedo_ioctl(struct net_device *dev, struct ifreq *rq, int cmd);
@@ -837,6 +838,9 @@
 	dev->get_stats = &speedo_get_stats;
 	dev->set_multicast_list = &set_rx_mode;
 	dev->do_ioctl = &speedo_ioctl;
+#ifdef HAVE_POLL_CONTROLLER
+	dev->poll_controller = &poll_speedo;
+#endif
 
 	return 0;
 }
@@ -1594,6 +1598,23 @@
 	clear_bit(0, (void*)&sp->in_interrupt);
 	return;
 }
+
+#ifdef HAVE_POLL_CONTROLLER
+
+/*
+ * Polling 'interrupt' - used by things like netconsole to send skbs
+ * without having to re-enable interrupts. It's not called while
+ * the interrupt routine is executing.
+ */
+
+static void poll_speedo (struct net_device *dev)
+{
+	disable_irq(dev->irq);
+	speedo_interrupt (dev->irq, dev, NULL);
+	enable_irq(dev->irq);
+}
+
+#endif
 
 static inline struct RxFD *speedo_rx_alloc(struct net_device *dev, int entry)
 {
--- linux/linux/drivers/net/netconsole.c.orig	Wed Sep 26 21:15:15 2001
+++ linux/linux/drivers/net/netconsole.c	Thu Sep 27 16:12:10 2001
@@ -0,0 +1,331 @@
+/*
+ *  linux/drivers/net/netconsole.c
+ *
+ *  Copyright (C) 2001  Ingo Molnar <mingo@redhat.com>
+ *
+ *  This file contains the implementation of an IRQ-safe, crash-safe
+ *  kernel console implementation that outputs kernel messages to the
+ *  network.
+ *
+ * Modification history:
+ *
+ * 2001-09-17    started by Ingo Molnar.
+ */
+
+/****************************************************************
+ *      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, or (at your option)
+ *      any later version.
+ *
+ *      This program is distributed in the hope that it will be useful,
+ *      but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *      MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *      GNU General Public License for more details.
+ *
+ *      You should have received a copy of the GNU General Public License
+ *      along with this program; if not, write to the Free Software
+ *      Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+ *
+ ****************************************************************/
+
+#include <net/tcp.h>
+#include <net/udp.h>
+#include <linux/mm.h>
+#include <linux/tty.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <asm/unaligned.h>
+#include <linux/console.h>
+#include <linux/smp_lock.h>
+#include <linux/netdevice.h>
+#include <linux/tty_driver.h>
+#include <linux/etherdevice.h>
+
+static struct net_device *netconsole_dev;
+static u16 source_port, target_port;
+static u32 source_ip, target_ip;
+static unsigned char daddr[6] = {0xff, 0xff, 0xff, 0xff, 0xff, 0xff} ;
+
+#define NETCONSOLE_VERSION 0x01
+#define HEADER_LEN 5
+
+#define MAX_UDP_CHUNK 1460
+#define MAX_PRINT_CHUNK (MAX_UDP_CHUNK-HEADER_LEN)
+
+/*
+ * We maintain a small pool of fully-sized skbs,
+ * to make sure the message gets out even in
+ * extreme OOM situations.
+ */
+#define MAX_NETCONSOLE_SKBS 32
+
+static spinlock_t netconsole_lock = SPIN_LOCK_UNLOCKED;
+static int nr_netconsole_skbs;
+static struct sk_buff *netconsole_skbs;
+
+#define MAX_SKB_SIZE \
+		(MAX_UDP_CHUNK + sizeof(struct udphdr) + \
+				sizeof(struct iphdr) + sizeof(struct ethhdr))
+
+static void __refill_netconsole_skbs(void)
+{
+	struct sk_buff *skb;
+	unsigned long flags;
+
+	spin_lock_irqsave(&netconsole_lock, flags);
+	while (nr_netconsole_skbs < MAX_NETCONSOLE_SKBS) {
+		skb = alloc_skb(MAX_SKB_SIZE, GFP_ATOMIC);
+		if (!skb)
+			break;
+		if (netconsole_skbs)
+			skb->next = netconsole_skbs;
+		else
+			skb->next = NULL;
+		netconsole_skbs = skb;
+		nr_netconsole_skbs++;
+	}
+	spin_unlock_irqrestore(&netconsole_lock, flags);
+}
+
+static struct sk_buff * get_netconsole_skb(void)
+{
+	struct sk_buff *skb;
+
+	unsigned long flags;
+
+	spin_lock_irqsave(&netconsole_lock, flags);
+	skb = netconsole_skbs;
+	if (skb)
+		netconsole_skbs = skb->next;
+	skb->next = NULL;
+	nr_netconsole_skbs--;
+	spin_unlock_irqrestore(&netconsole_lock, flags);
+
+	return skb;
+}
+
+static spinlock_t sequence_lock = SPIN_LOCK_UNLOCKED;
+static unsigned int offset;
+
+static void send_netconsole_skb(struct net_device *dev, const char *msg, unsigned int msg_len)
+{
+	int total_len, eth_len, ip_len, udp_len;
+	unsigned long flags;
+	struct sk_buff *skb;
+	struct udphdr *udph;
+	struct iphdr *iph;
+	struct ethhdr *eth;
+
+	udp_len = msg_len + HEADER_LEN + sizeof(*udph);
+	ip_len = eth_len = udp_len + sizeof(*iph);
+	total_len = eth_len + ETH_HLEN;
+
+	if (nr_netconsole_skbs < MAX_NETCONSOLE_SKBS)
+		__refill_netconsole_skbs();
+
+	skb = alloc_skb(total_len, GFP_ATOMIC);
+	if (!skb) {
+		skb = get_netconsole_skb();
+		if (!skb)
+			/* tough! */
+			return;
+	}
+
+	atomic_set(&skb->users, 1);
+	skb_reserve(skb, total_len - msg_len - HEADER_LEN);
+	skb->data[0] = NETCONSOLE_VERSION;
+
+	spin_lock_irqsave(&sequence_lock, flags);
+	put_unaligned(htonl(offset), (u32 *) (skb->data + 1));
+	offset += msg_len;
+	spin_unlock_irqrestore(&sequence_lock, flags);
+
+	memcpy(skb->data + HEADER_LEN, msg, msg_len);
+	skb->len += msg_len + HEADER_LEN;
+
+	udph = (struct udphdr *) skb_push(skb, sizeof(*udph));
+	udph->source = source_port;
+	udph->dest = target_port;
+	udph->len = htons(udp_len);
+	udph->check = 0;
+
+	iph = (struct iphdr *)skb_push(skb, sizeof(*iph));
+
+	iph->version  = 4;
+	iph->ihl      = 5;
+	iph->tos      = 0;
+        iph->tot_len  = htons(ip_len);
+	iph->id       = 0;
+	iph->frag_off = 0;
+	iph->ttl      = 64;
+        iph->protocol = IPPROTO_UDP;
+	iph->check    = 0;
+        iph->saddr    = source_ip;
+        iph->daddr    = target_ip;
+	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, dev->dev_addr, dev->addr_len);
+	memcpy(eth->h_dest, daddr, dev->addr_len);
+
+repeat:
+	spin_lock(&dev->xmit_lock);
+	dev->xmit_lock_owner = smp_processor_id();
+
+	if (netif_queue_stopped(dev)) {
+		dev->xmit_lock_owner = -1;
+		spin_unlock(&dev->xmit_lock);
+
+		dev->poll_controller(dev);
+		goto repeat;
+	}
+
+	dev->hard_start_xmit(skb, dev);
+
+	dev->xmit_lock_owner = -1;
+	spin_unlock(&dev->xmit_lock);
+}
+
+static void write_netconsole_msg(struct console *con, const char *msg, unsigned int msg_len)
+{
+	int len, left;
+	struct net_device *dev;
+
+	dev = netconsole_dev;
+	if (!dev)
+		return;
+
+	if (dev->poll_controller && netif_running(dev)) {
+		unsigned long flags;
+
+		__save_flags(flags);
+		__cli();
+		left = msg_len;
+repeat:
+		if (left > MAX_PRINT_CHUNK)
+			len = MAX_PRINT_CHUNK;
+		else
+			len = left;
+		send_netconsole_skb(dev, msg, len);
+		msg += len;
+		left -= len;
+		if (left)
+			goto repeat;
+		__restore_flags(flags);
+	}
+}
+
+static char *dev;
+static int target_eth_byte0 = 255;
+static int target_eth_byte1 = 255;
+static int target_eth_byte2 = 255;
+static int target_eth_byte3 = 255;
+static int target_eth_byte4 = 255;
+static int target_eth_byte5 = 255;
+
+MODULE_PARM(target_ip, "i");
+MODULE_PARM(target_eth_byte0, "i");
+MODULE_PARM(target_eth_byte1, "i");
+MODULE_PARM(target_eth_byte2, "i");
+MODULE_PARM(target_eth_byte3, "i");
+MODULE_PARM(target_eth_byte4, "i");
+MODULE_PARM(target_eth_byte5, "i");
+MODULE_PARM(source_port, "h");
+MODULE_PARM(target_port, "h");
+MODULE_PARM(dev, "s");
+
+static struct console netconsole =
+	 { flags: CON_ENABLED, write: write_netconsole_msg };
+
+static int init_netconsole(void)
+{
+	struct net_device *ndev = NULL;
+	struct in_device *in_dev;
+
+	printk(KERN_INFO "netconsole: using network device <%s>\n", dev);
+	// this will be valid once the device goes up.
+	if (dev)
+		ndev = dev_get_by_name(dev);
+	if (!ndev) {
+		printk(KERN_ERR "netconsole: network device %s does not exist, aborting.\n", dev);
+		return -1;
+	}
+	if (!ndev->poll_controller) {
+		printk(KERN_ERR "netconsole: %s's network driver does not implement netlogging yet, aborting.\n", dev);
+		return -1;
+	}
+        in_dev = in_dev_get(ndev);
+	if (!in_dev) {
+		printk(KERN_ERR "netconsole: network device %s is not an IP protocol device, aborting.\n", dev);
+		return -1;
+	}
+	source_ip = ntohl(in_dev->ifa_list->ifa_local);
+	if (!source_ip) {
+		printk(KERN_ERR "netconsole: network device %s has no local address, aborting.\n", dev);
+		return -1;
+	}
+#define IP(x) ((char *)&source_ip)[x]
+	printk(KERN_INFO "netconsole: using source IP %i.%i.%i.%i\n",
+		IP(3), IP(2), IP(1), IP(0));
+#undef IP
+	source_ip = htonl(source_ip);
+	if (!target_ip) {
+		printk(KERN_ERR "netconsole: target_ip parameter not specified, aborting.\n");
+		return -1;
+	}
+#define IP(x) ((char *)&target_ip)[x]
+	printk(KERN_INFO "netconsole: using target IP %i.%i.%i.%i\n",
+		IP(3), IP(2), IP(1), IP(0));
+#undef IP
+	target_ip = htonl(target_ip);
+	if (!source_port) {
+		printk(KERN_ERR "netconsole: source_port parameter not specified, aborting.\n");
+		return -1;
+	}
+	printk(KERN_INFO "netconsole: using source UDP port: %i\n", source_port);
+	source_port = htons(source_port);
+	if (!target_port) {
+		printk(KERN_ERR "netconsole: target_port parameter not specified, aborting.\n");
+		return -1;
+	}
+	printk(KERN_INFO "netconsole: using target UDP port: %i\n", target_port);
+	target_port = htons(target_port);
+
+	daddr[0] = target_eth_byte0;
+	daddr[1] = target_eth_byte1;
+	daddr[2] = target_eth_byte2;
+	daddr[3] = target_eth_byte3;
+	daddr[4] = target_eth_byte4;
+	daddr[5] = target_eth_byte5;
+
+	if ((daddr[0] & daddr[1] & daddr[2] & daddr[3] & daddr[4] & daddr[5]) == 255)
+		printk(KERN_INFO "netconsole: using broadcast ethernet frames to send packets.\n");
+	else
+		printk(KERN_INFO "netconsole: using target ethernet address %02x:%02x:%02x:%02x:%02x:%02x.\n", daddr[0], daddr[1], daddr[2], daddr[3], daddr[4], daddr[5]);
+		
+	netconsole_dev = ndev;
+#define STARTUP_MSG "[...network console startup...]\n"
+	write_netconsole_msg(NULL, STARTUP_MSG, strlen(STARTUP_MSG));
+
+	register_console(&netconsole);
+	printk(KERN_INFO "netconsole: network logging started up successfully!\n");
+	return 0;
+}
+
+static void cleanup_netconsole(void)
+{
+	printk(KERN_INFO "netconsole: network logging shut down.\n");
+	unregister_console(&netconsole);
+
+#define SHUTDOWN_MSG "[...network console shutdown...]\n"
+	write_netconsole_msg(NULL, SHUTDOWN_MSG, strlen(SHUTDOWN_MSG));
+	netconsole_dev = NULL;
+}
+
+module_init(init_netconsole);
+module_exit(cleanup_netconsole);
+
+int dummy = MAX_SKB_SIZE;
--- linux/linux/drivers/net/Makefile.orig	Wed Sep 26 21:14:58 2001
+++ linux/linux/drivers/net/Makefile	Wed Sep 26 21:15:15 2001
@@ -216,6 +216,8 @@
 obj-y		+= ../acorn/net/acorn-net.o
 endif
 
+obj-$(CONFIG_NETCONSOLE) += netconsole.o
+
 #
 # HIPPI adapters
 #
--- linux/linux/drivers/net/Config.in.orig	Wed Sep 26 21:14:58 2001
+++ linux/linux/drivers/net/Config.in	Wed Sep 26 21:15:15 2001
@@ -248,6 +248,8 @@
    dep_tristate '  SysKonnect FDDI PCI support' CONFIG_SKFP $CONFIG_PCI
 fi
 
+dep_tristate 'Network logging support' CONFIG_NETCONSOLE
+
 if [ "$CONFIG_EXPERIMENTAL" = "y" ]; then
    if [ "$CONFIG_INET" = "y" ]; then
       bool 'HIPPI driver support (EXPERIMENTAL)' CONFIG_HIPPI
--- linux/linux/Documentation/networking/netlogging.txt.orig	Wed Sep 26 21:15:15 2001
+++ linux/linux/Documentation/networking/netlogging.txt	Wed Sep 26 21:15:15 2001
@@ -0,0 +1,46 @@
+
+started by Ingo Molnar <mingo@redhat.com>, 2001.09.17
+
+the network console can be configured over the module interface,
+by specifying the dev=, target_ip=, source_port=, target_port=
+module parameters. Sample use:
+
+insmod netconsole dev=eth0 target_ip=0x0a000701 \
+                  source_port=6666 target_port=6666
+
+IP addresses must be specified in hexadecimal numbers. The
+above example uses target host IP 10.0.7.1.
+
+if the module is loaded then all kernel messages are sent to the
+target host via UDP packets. The remote host should run the
+client-side 'netconsole' daemon to display & log the messages.
+
+WARNING: the default setting uses the broadcast ethernet address
+to send packets, which can cause increased load on other systems
+on the same ethernet segment. If this is not desired, then the
+target ethernet address can be specified via the target_eth_byte0,
+target_eth_byte1 ... byte5 module parameters. Eg.:
+
+insmod netconsole dev=eth0 target_ip=0x0a000701 \
+                  source_port=6666 target_port=6666 \
+                  target_eth_byte0=0x00 \
+                  target_eth_byte1=0x02\
+                  target_eth_byte2=0xA5 \
+                  target_eth_byte3=0x13 \
+                  target_eth_byte4=0x51 \
+                  target_eth_byte5=0xDD
+
+will instruct the netconsole code to use target ethernet address
+00:02:A5:13:51:DD.
+
+NOTE: the network device (eth0 in the above case) can run any kind
+of other network traffic, netconsole is not intrusive. Netconsole
+might cause slight delays in other traffic if the volume of kernel
+messages is high, but should have no other impact.
+
+netconsole was designed to be as instantaneous as possible, to
+enable the logging of even the most critical kernel bugs. It works
+from IRQ contexts as well, and does not enable interrupts while
+sending packets. Due to these unique needs, configuration can not
+be more automatic, and some fundamental limitations will remain:
+only IP networks, UDP packets and ethernet devices are supported.
--- linux/linux/Documentation/Configure.help.orig	Wed Sep 26 21:14:55 2001
+++ linux/linux/Documentation/Configure.help	Wed Sep 26 21:15:15 2001
@@ -9997,6 +9997,11 @@
   say M here and read Documentation/modules.txt. This is recommended.
   The module will be called skfp.o.
 
+Network logging support
+CONFIG_NETCONSOLE
+  If you want to log kernel messages over the network, then say
+  "M" here. See Documentation/networking/netlogging.txt for details.
+
 HIgh Performance Parallel Interface support (EXPERIMENTAL)
 CONFIG_HIPPI
   HIgh Performance Parallel Interface (HIPPI) is a 800Mbit/sec and