path: root/arch/ia64/sn/kernel/xpc_main.c

/*
 * This file is subject to the terms and conditions of the GNU General Public
 * License.  See the file "COPYING" in the main directory of this archive
 * for more details.
 *
 * Copyright (c) 2004-2005 Silicon Graphics, Inc.  All Rights Reserved.
 */


/*
 * Cross Partition Communication (XPC) support - standard version.
 *
 *	XPC provides a message passing capability that crosses partition
 *	boundaries. This module is made up of two parts:
 *
 *	    partition	This part detects the presence/absence of other
 *			partitions. It provides a heartbeat and monitors
 *			the heartbeats of other partitions.
 *
 *	    channel	This part manages the channels and sends/receives
 *			messages across them to/from other partitions.
 *
 *	There are a couple of additional functions residing in XP, which
 *	provide an interface to XPC for its users.
 *
 *
 *	Caveats:
 *
 *	  . We currently have no way to determine which nasid an IPI came
 *	    from. Thus, xpc_IPI_send() does a remote AMO write followed by
 *	    an IPI. The AMO indicates where data is to be pulled from, so
 *	    after the IPI arrives, the remote partition checks the AMO word.
 *	    The IPI can actually arrive before the AMO however, so other code
 *	    must periodically check for this case. Also, remote AMO operations
 *	    do not reliably time out. Thus we do a remote PIO read solely to
 *	    know whether the remote partition is down and whether we should
 *	    stop sending IPIs to it. This remote PIO read operation is set up
 *	    in a special nofault region so SAL knows to ignore (and cleanup)
 *	    any errors due to the remote AMO write, PIO read, and/or PIO
 *	    write operations.
 *
 *	    If/when new hardware solves this IPI problem, we should abandon
 *	    the current approach.
 *
 */


#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/init.h>
#include <linux/sched.h>
#include <linux/syscalls.h>
#include <linux/cache.h>
#include <linux/interrupt.h>
#include <linux/slab.h>
#include <linux/delay.h>
#include <asm/sn/intr.h>
#include <asm/sn/sn_sal.h>
#include <asm/uaccess.h>
#include "xpc.h"


/* define two XPC debug device structures to be used with dev_dbg() et al */

struct device_driver xpc_dbg_name = {
	.name = "xpc"
};

struct device xpc_part_dbg_subname = {
	.bus_id = {0},		/* set to "part" at xpc_init() time */
	.driver = &xpc_dbg_name
};

struct device xpc_chan_dbg_subname = {
	.bus_id = {0},		/* set to "chan" at xpc_init() time */
	.driver = &xpc_dbg_name
};

struct device *xpc_part = &xpc_part_dbg_subname;
struct device *xpc_chan = &xpc_chan_dbg_subname;


/* systune related variables for /proc/sys directories */

static int xpc_hb_min = 1;
static int xpc_hb_max = 10;

static int xpc_hb_check_min = 10;
static int xpc_hb_check_max = 120;

static ctl_table xpc_sys_xpc_hb_dir[] = {
	{
		1,
		"hb_interval",
		&xpc_hb_interval,
		sizeof(int),
		0644,
		NULL,
		&proc_dointvec_minmax,
		&sysctl_intvec,
		NULL,
		&xpc_hb_min, &xpc_hb_max
	},
	{
		2,
		"hb_check_interval",
		&xpc_hb_check_interval,
		sizeof(int),
		0644,
		NULL,
		&proc_dointvec_minmax,
		&sysctl_intvec,
		NULL,
		&xpc_hb_check_min, &xpc_hb_check_max
	},
	{0}
};
static ctl_table xpc_sys_xpc_dir[] = {
	{
		1,
		"hb",
		NULL,
		0,
		0555,
		xpc_sys_xpc_hb_dir
	},
	{0}
};
static ctl_table xpc_sys_dir[] = {
	{
		1,
		"xpc",
		NULL,
		0,
		0555,
		xpc_sys_xpc_dir
	},
	{0}
};
static struct ctl_table_header *xpc_sysctl;


/* #of IRQs received */
static atomic_t xpc_act_IRQ_rcvd;

/* IRQ handler notifies this wait queue on receipt of an IRQ */
static DECLARE_WAIT_QUEUE_HEAD(xpc_act_IRQ_wq);

static unsigned long xpc_hb_check_timeout;

/* xpc_hb_checker thread exited notification */
static DECLARE_MUTEX_LOCKED(xpc_hb_checker_exited);

/* xpc_discovery thread exited notification */
static DECLARE_MUTEX_LOCKED(xpc_discovery_exited);


static struct timer_list xpc_hb_timer;


static void xpc_kthread_waitmsgs(struct xpc_partition *, struct xpc_channel *);


/*
 * Notify the heartbeat check thread that an IRQ has been received.
 */
static irqreturn_t
xpc_act_IRQ_handler(int irq, void *dev_id, struct pt_regs *regs)
{
	atomic_inc(&xpc_act_IRQ_rcvd);
	wake_up_interruptible(&xpc_act_IRQ_wq);
	return IRQ_HANDLED;
}


/*
 * Timer to produce the heartbeat.  The timer structures function is
 * already set when this is initially called.  A tunable is used to
 * specify when the next timeout should occur.
 */
static void
xpc_hb_beater(unsigned long dummy)
{
	xpc_vars->heartbeat++;

	if (jiffies >= xpc_hb_check_timeout) {
		wake_up_interruptible(&xpc_act_IRQ_wq);
	}

	xpc_hb_timer.expires = jiffies + (xpc_hb_interval * HZ);
	add_timer(&xpc_hb_timer);
}


/*
 * This thread is responsible for nearly all of the partition
 * activation/deactivation.
 */
static int
xpc_hb_checker(void *ignore)
{
	int last_IRQ_count = 0;
	int new_IRQ_count;
	int force_IRQ=0;


	/* this thread was marked active by xpc_hb_init() */

	daemonize(XPC_HB_CHECK_THREAD_NAME);

	set_cpus_allowed(current, cpumask_of_cpu(XPC_HB_CHECK_CPU));

	xpc_hb_check_timeout = jiffies + (xpc_hb_check_interval * HZ);

	while (!(volatile int) xpc_exiting)