M7350v1_en_gpl

kernel/arch/s390/appldata/Makefile

@@ -0,0 +1,8 @@
+#
+# Makefile for the Linux - z/VM Monitor Stream.
+#
+
+obj-$(CONFIG_APPLDATA_BASE) += appldata_base.o
+obj-$(CONFIG_APPLDATA_MEM) += appldata_mem.o
+obj-$(CONFIG_APPLDATA_OS) += appldata_os.o
+obj-$(CONFIG_APPLDATA_NET_SUM) += appldata_net_sum.o

kernel/arch/s390/appldata/appldata.h

@@ -0,0 +1,49 @@
+/*
+ * arch/s390/appldata/appldata.h
+ *
+ * Definitions and interface for Linux - z/VM Monitor Stream.
+ *
+ * Copyright IBM Corp. 2003, 2008
+ *
+ * Author: Gerald Schaefer <gerald.schaefer@de.ibm.com>
+ */
+
+#define APPLDATA_MAX_REC_SIZE	  4024	/* Maximum size of the */
+					/* data buffer */
+#define APPLDATA_MAX_PROCS 100
+
+#define APPLDATA_PROC_NAME_LENGTH 16	/* Max. length of /proc name */
+
+#define APPLDATA_RECORD_MEM_ID		0x01	/* IDs to identify the */
+#define APPLDATA_RECORD_OS_ID		0x02	/* individual records, */
+#define APPLDATA_RECORD_NET_SUM_ID	0x03	/* must be < 256 !     */
+#define APPLDATA_RECORD_PROC_ID		0x04
+
+#define CTL_APPLDATA_TIMER 	2121	/* sysctl IDs, must be unique */
+#define CTL_APPLDATA_INTERVAL 	2122
+#define CTL_APPLDATA_MEM	2123
+#define CTL_APPLDATA_OS		2124
+#define CTL_APPLDATA_NET_SUM	2125
+#define CTL_APPLDATA_PROC	2126
+
+struct appldata_ops {
+	struct list_head list;
+	struct ctl_table_header *sysctl_header;
+	struct ctl_table *ctl_table;
+	int    active;				/* monitoring status */
+
+	/* fill in from here */
+	char name[APPLDATA_PROC_NAME_LENGTH];	/* name of /proc fs node */
+	unsigned char record_nr;		/* Record Nr. for Product ID */
+	void (*callback)(void *data);		/* callback function */
+	void *data;				/* record data */
+	unsigned int size;			/* size of record */
+	struct module *owner;			/* THIS_MODULE */
+	char mod_lvl[2];			/* modification level, EBCDIC */
+};
+
+extern int appldata_register_ops(struct appldata_ops *ops);
+extern void appldata_unregister_ops(struct appldata_ops *ops);
+extern int appldata_diag(char record_nr, u16 function, unsigned long buffer,
+			 u16 length, char *mod_lvl);
+

kernel/arch/s390/appldata/appldata_base.c

@@ -0,0 +1,673 @@
+/*
+ * arch/s390/appldata/appldata_base.c
+ *
+ * Base infrastructure for Linux-z/VM Monitor Stream, Stage 1.
+ * Exports appldata_register_ops() and appldata_unregister_ops() for the
+ * data gathering modules.
+ *
+ * Copyright IBM Corp. 2003, 2009
+ *
+ * Author: Gerald Schaefer <gerald.schaefer@de.ibm.com>
+ */
+
+#define KMSG_COMPONENT	"appldata"
+#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
+
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/slab.h>
+#include <linux/errno.h>
+#include <linux/interrupt.h>
+#include <linux/proc_fs.h>
+#include <linux/mm.h>
+#include <linux/swap.h>
+#include <linux/pagemap.h>
+#include <linux/sysctl.h>
+#include <linux/notifier.h>
+#include <linux/cpu.h>
+#include <linux/workqueue.h>
+#include <linux/suspend.h>
+#include <linux/platform_device.h>
+#include <asm/appldata.h>
+#include <asm/timer.h>
+#include <asm/uaccess.h>
+#include <asm/io.h>
+#include <asm/smp.h>
+
+#include "appldata.h"
+
+
+#define APPLDATA_CPU_INTERVAL	10000		/* default (CPU) time for
+						   sampling interval in
+						   milliseconds */
+
+#define TOD_MICRO	0x01000			/* nr. of TOD clock units
+						   for 1 microsecond */
+
+static struct platform_device *appldata_pdev;
+
+/*
+ * /proc entries (sysctl)
+ */
+static const char appldata_proc_name[APPLDATA_PROC_NAME_LENGTH] = "appldata";
+static int appldata_timer_handler(ctl_table *ctl, int write,
+				  void __user *buffer, size_t *lenp, loff_t *ppos);
+static int appldata_interval_handler(ctl_table *ctl, int write,
+					 void __user *buffer,
+					 size_t *lenp, loff_t *ppos);
+
+static struct ctl_table_header *appldata_sysctl_header;
+static struct ctl_table appldata_table[] = {
+	{
+		.procname	= "timer",
+		.mode		= S_IRUGO | S_IWUSR,
+		.proc_handler	= appldata_timer_handler,
+	},
+	{
+		.procname	= "interval",
+		.mode		= S_IRUGO | S_IWUSR,
+		.proc_handler	= appldata_interval_handler,
+	},
+	{ },
+};
+
+static struct ctl_table appldata_dir_table[] = {
+	{
+		.procname	= appldata_proc_name,
+		.maxlen		= 0,
+		.mode		= S_IRUGO | S_IXUGO,
+		.child		= appldata_table,
+	},
+	{ },
+};
+
+/*
+ * Timer
+ */
+static DEFINE_PER_CPU(struct vtimer_list, appldata_timer);
+static atomic_t appldata_expire_count = ATOMIC_INIT(0);
+
+static DEFINE_SPINLOCK(appldata_timer_lock);
+static int appldata_interval = APPLDATA_CPU_INTERVAL;
+static int appldata_timer_active;
+static int appldata_timer_suspended = 0;
+
+/*
+ * Work queue
+ */
+static struct workqueue_struct *appldata_wq;
+static void appldata_work_fn(struct work_struct *work);
+static DECLARE_WORK(appldata_work, appldata_work_fn);
+
+
+/*
+ * Ops list
+ */
+static DEFINE_MUTEX(appldata_ops_mutex);
+static LIST_HEAD(appldata_ops_list);
+
+
+/*************************** timer, work, DIAG *******************************/
+/*
+ * appldata_timer_function()
+ *
+ * schedule work and reschedule timer
+ */
+static void appldata_timer_function(unsigned long data)
+{
+	if (atomic_dec_and_test(&appldata_expire_count)) {
+		atomic_set(&appldata_expire_count, num_online_cpus());
+		queue_work(appldata_wq, (struct work_struct *) data);
+	}
+}
+
+/*
+ * appldata_work_fn()
+ *
+ * call data gathering function for each (active) module
+ */
+static void appldata_work_fn(struct work_struct *work)
+{
+	struct list_head *lh;
+	struct appldata_ops *ops;
+
+	get_online_cpus();
+	mutex_lock(&appldata_ops_mutex);
+	list_for_each(lh, &appldata_ops_list) {
+		ops = list_entry(lh, struct appldata_ops, list);
+		if (ops->active == 1) {
+			ops->callback(ops->data);
+		}
+	}
+	mutex_unlock(&appldata_ops_mutex);
+	put_online_cpus();
+}
+
+/*
+ * appldata_diag()
+ *
+ * prepare parameter list, issue DIAG 0xDC
+ */
+int appldata_diag(char record_nr, u16 function, unsigned long buffer,
+			u16 length, char *mod_lvl)
+{
+	struct appldata_product_id id = {
+		.prod_nr    = {0xD3, 0xC9, 0xD5, 0xE4,
+			       0xE7, 0xD2, 0xD9},	/* "LINUXKR" */
+		.prod_fn    = 0xD5D3,			/* "NL" */
+		.version_nr = 0xF2F6,			/* "26" */
+		.release_nr = 0xF0F1,			/* "01" */
+	};
+
+	id.record_nr = record_nr;
+	id.mod_lvl = (mod_lvl[0]) << 8 | mod_lvl[1];
+	return appldata_asm(&id, function, (void *) buffer, length);
+}
+/************************ timer, work, DIAG <END> ****************************/
+
+
+/****************************** /proc stuff **********************************/
+
+/*
+ * appldata_mod_vtimer_wrap()
+ *
+ * wrapper function for mod_virt_timer(), because smp_call_function_single()
+ * accepts only one parameter.
+ */
+static void __appldata_mod_vtimer_wrap(void *p) {
+	struct {
+		struct vtimer_list *timer;
+		u64    expires;
+	} *args = p;
+	mod_virt_timer_periodic(args->timer, args->expires);
+}
+
+#define APPLDATA_ADD_TIMER	0
+#define APPLDATA_DEL_TIMER	1
+#define APPLDATA_MOD_TIMER	2
+
+/*
+ * __appldata_vtimer_setup()
+ *
+ * Add, delete or modify virtual timers on all online cpus.
+ * The caller needs to get the appldata_timer_lock spinlock.
+ */
+static void
+__appldata_vtimer_setup(int cmd)
+{
+	u64 per_cpu_interval;
+	int i;
+
+	switch (cmd) {
+	case APPLDATA_ADD_TIMER:
+		if (appldata_timer_active)
+			break;
+		per_cpu_interval = (u64) (appldata_interval*1000 /
+					  num_online_cpus()) * TOD_MICRO;
+		for_each_online_cpu(i) {
+			per_cpu(appldata_timer, i).expires = per_cpu_interval;
+			smp_call_function_single(i, add_virt_timer_periodic,
+						 &per_cpu(appldata_timer, i),
+						 1);
+		}
+		appldata_timer_active = 1;
+		break;
+	case APPLDATA_DEL_TIMER:
+		for_each_online_cpu(i)
+			del_virt_timer(&per_cpu(appldata_timer, i));
+		if (!appldata_timer_active)
+			break;
+		appldata_timer_active = 0;
+		atomic_set(&appldata_expire_count, num_online_cpus());
+		break;
+	case APPLDATA_MOD_TIMER:
+		per_cpu_interval = (u64) (appldata_interval*1000 /
+					  num_online_cpus()) * TOD_MICRO;
+		if (!appldata_timer_active)
+			break;
+		for_each_online_cpu(i) {
+			struct {
+				struct vtimer_list *timer;
+				u64    expires;
+			} args;
+			args.timer = &per_cpu(appldata_timer, i);
+			args.expires = per_cpu_interval;
+			smp_call_function_single(i, __appldata_mod_vtimer_wrap,
+						 &args, 1);
+		}
+	}
+}
+
+/*
+ * appldata_timer_handler()
+ *
+ * Start/Stop timer, show status of timer (0 = not active, 1 = active)
+ */
+static int
+appldata_timer_handler(ctl_table *ctl, int write,
+			   void __user *buffer, size_t *lenp, loff_t *ppos)
+{
+	int len;
+	char buf[2];
+
+	if (!*lenp || *ppos) {
+		*lenp = 0;
+		return 0;
+	}
+	if (!write) {
+		len = sprintf(buf, appldata_timer_active ? "1\n" : "0\n");
+		if (len > *lenp)
+			len = *lenp;
+		if (copy_to_user(buffer, buf, len))
+			return -EFAULT;
+		goto out;
+	}
+	len = *lenp;
+	if (copy_from_user(buf, buffer, len > sizeof(buf) ? sizeof(buf) : len))
+		return -EFAULT;
+	get_online_cpus();
+	spin_lock(&appldata_timer_lock);
+	if (buf[0] == '1')
+		__appldata_vtimer_setup(APPLDATA_ADD_TIMER);
+	else if (buf[0] == '0')
+		__appldata_vtimer_setup(APPLDATA_DEL_TIMER);
+	spin_unlock(&appldata_timer_lock);
+	put_online_cpus();
+out:
+	*lenp = len;
+	*ppos += len;
+	return 0;
+}
+
+/*
+ * appldata_interval_handler()
+ *
+ * Set (CPU) timer interval for collection of data (in milliseconds), show
+ * current timer interval.
+ */
+static int
+appldata_interval_handler(ctl_table *ctl, int write,
+			   void __user *buffer, size_t *lenp, loff_t *ppos)
+{
+	int len, interval;
+	char buf[16];
+
+	if (!*lenp || *ppos) {
+		*lenp = 0;
+		return 0;
+	}
+	if (!write) {
+		len = sprintf(buf, "%i\n", appldata_interval);
+		if (len > *lenp)
+			len = *lenp;
+		if (copy_to_user(buffer, buf, len))
+			return -EFAULT;
+		goto out;
+	}
+	len = *lenp;
+	if (copy_from_user(buf, buffer, len > sizeof(buf) ? sizeof(buf) : len)) {
+		return -EFAULT;
+	}
+	interval = 0;
+	sscanf(buf, "%i", &interval);
+	if (interval <= 0)
+		return -EINVAL;
+
+	get_online_cpus();
+	spin_lock(&appldata_timer_lock);
+	appldata_interval = interval;
+	__appldata_vtimer_setup(APPLDATA_MOD_TIMER);
+	spin_unlock(&appldata_timer_lock);
+	put_online_cpus();
+out:
+	*lenp = len;
+	*ppos += len;
+	return 0;
+}
+
+/*
+ * appldata_generic_handler()
+ *
+ * Generic start/stop monitoring and DIAG, show status of
+ * monitoring (0 = not in process, 1 = in process)
+ */
+static int
+appldata_generic_handler(ctl_table *ctl, int write,
+			   void __user *buffer, size_t *lenp, loff_t *ppos)
+{
+	struct appldata_ops *ops = NULL, *tmp_ops;
+	int rc, len, found;
+	char buf[2];
+	struct list_head *lh;
+
+	found = 0;
+	mutex_lock(&appldata_ops_mutex);
+	list_for_each(lh, &appldata_ops_list) {
+		tmp_ops = list_entry(lh, struct appldata_ops, list);
+		if (&tmp_ops->ctl_table[2] == ctl) {
+			found = 1;
+		}
+	}
+	if (!found) {
+		mutex_unlock(&appldata_ops_mutex);
+		return -ENODEV;
+	}
+	ops = ctl->data;
+	if (!try_module_get(ops->owner)) {	// protect this function
+		mutex_unlock(&appldata_ops_mutex);
+		return -ENODEV;
+	}
+	mutex_unlock(&appldata_ops_mutex);
+
+	if (!*lenp || *ppos) {
+		*lenp = 0;
+		module_put(ops->owner);
+		return 0;
+	}
+	if (!write) {
+		len = sprintf(buf, ops->active ? "1\n" : "0\n");
+		if (len > *lenp)
+			len = *lenp;
+		if (copy_to_user(buffer, buf, len)) {
+			module_put(ops->owner);
+			return -EFAULT;
+		}
+		goto out;
+	}
+	len = *lenp;
+	if (copy_from_user(buf, buffer,
+			   len > sizeof(buf) ? sizeof(buf) : len)) {
+		module_put(ops->owner);
+		return -EFAULT;
+	}
+
+	mutex_lock(&appldata_ops_mutex);
+	if ((buf[0] == '1') && (ops->active == 0)) {
+		// protect work queue callback
+		if (!try_module_get(ops->owner)) {
+			mutex_unlock(&appldata_ops_mutex);
+			module_put(ops->owner);
+			return -ENODEV;
+		}
+		ops->callback(ops->data);	// init record
+		rc = appldata_diag(ops->record_nr,
+					APPLDATA_START_INTERVAL_REC,
+					(unsigned long) ops->data, ops->size,
+					ops->mod_lvl);
+		if (rc != 0) {
+			pr_err("Starting the data collection for %s "
+			       "failed with rc=%d\n", ops->name, rc);
+			module_put(ops->owner);
+		} else
+			ops->active = 1;
+	} else if ((buf[0] == '0') && (ops->active == 1)) {
+		ops->active = 0;
+		rc = appldata_diag(ops->record_nr, APPLDATA_STOP_REC,
+				(unsigned long) ops->data, ops->size,
+				ops->mod_lvl);
+		if (rc != 0)
+			pr_err("Stopping the data collection for %s "
+			       "failed with rc=%d\n", ops->name, rc);
+		module_put(ops->owner);
+	}
+	mutex_unlock(&appldata_ops_mutex);
+out:
+	*lenp = len;
+	*ppos += len;
+	module_put(ops->owner);
+	return 0;
+}
+
+/*************************** /proc stuff <END> *******************************/
+
+
+/************************* module-ops management *****************************/
+/*
+ * appldata_register_ops()
+ *
+ * update ops list, register /proc/sys entries
+ */
+int appldata_register_ops(struct appldata_ops *ops)
+{
+	if (ops->size > APPLDATA_MAX_REC_SIZE)
+		return -EINVAL;
+
+	ops->ctl_table = kzalloc(4 * sizeof(struct ctl_table), GFP_KERNEL);
+	if (!ops->ctl_table)
+		return -ENOMEM;
+
+	mutex_lock(&appldata_ops_mutex);
+	list_add(&ops->list, &appldata_ops_list);
+	mutex_unlock(&appldata_ops_mutex);
+
+	ops->ctl_table[0].procname = appldata_proc_name;
+	ops->ctl_table[0].maxlen   = 0;
+	ops->ctl_table[0].mode     = S_IRUGO | S_IXUGO;
+	ops->ctl_table[0].child    = &ops->ctl_table[2];
+
+	ops->ctl_table[2].procname = ops->name;
+	ops->ctl_table[2].mode     = S_IRUGO | S_IWUSR;
+	ops->ctl_table[2].proc_handler = appldata_generic_handler;
+	ops->ctl_table[2].data = ops;
+
+	ops->sysctl_header = register_sysctl_table(ops->ctl_table);
+	if (!ops->sysctl_header)
+		goto out;
+	return 0;
+out:
+	mutex_lock(&appldata_ops_mutex);
+	list_del(&ops->list);
+	mutex_unlock(&appldata_ops_mutex);
+	kfree(ops->ctl_table);
+	return -ENOMEM;
+}
+
+/*
+ * appldata_unregister_ops()
+ *
+ * update ops list, unregister /proc entries, stop DIAG if necessary
+ */
+void appldata_unregister_ops(struct appldata_ops *ops)
+{
+	mutex_lock(&appldata_ops_mutex);
+	list_del(&ops->list);
+	mutex_unlock(&appldata_ops_mutex);
+	unregister_sysctl_table(ops->sysctl_header);
+	kfree(ops->ctl_table);
+}
+/********************** module-ops management <END> **************************/
+
+
+/**************************** suspend / resume *******************************/
+static int appldata_freeze(struct device *dev)
+{
+	struct appldata_ops *ops;
+	int rc;
+	struct list_head *lh;
+
+	get_online_cpus();
+	spin_lock(&appldata_timer_lock);
+	if (appldata_timer_active) {
+		__appldata_vtimer_setup(APPLDATA_DEL_TIMER);
+		appldata_timer_suspended = 1;
+	}
+	spin_unlock(&appldata_timer_lock);
+	put_online_cpus();
+
+	mutex_lock(&appldata_ops_mutex);
+	list_for_each(lh, &appldata_ops_list) {
+		ops = list_entry(lh, struct appldata_ops, list);
+		if (ops->active == 1) {
+			rc = appldata_diag(ops->record_nr, APPLDATA_STOP_REC,
+					(unsigned long) ops->data, ops->size,
+					ops->mod_lvl);
+			if (rc != 0)
+				pr_err("Stopping the data collection for %s "
+				       "failed with rc=%d\n", ops->name, rc);
+		}
+	}
+	mutex_unlock(&appldata_ops_mutex);
+	return 0;
+}
+
+static int appldata_restore(struct device *dev)
+{
+	struct appldata_ops *ops;
+	int rc;
+	struct list_head *lh;
+
+	get_online_cpus();
+	spin_lock(&appldata_timer_lock);
+	if (appldata_timer_suspended) {
+		__appldata_vtimer_setup(APPLDATA_ADD_TIMER);
+		appldata_timer_suspended = 0;
+	}
+	spin_unlock(&appldata_timer_lock);
+	put_online_cpus();
+
+	mutex_lock(&appldata_ops_mutex);
+	list_for_each(lh, &appldata_ops_list) {
+		ops = list_entry(lh, struct appldata_ops, list);
+		if (ops->active == 1) {
+			ops->callback(ops->data);	// init record
+			rc = appldata_diag(ops->record_nr,
+					APPLDATA_START_INTERVAL_REC,
+					(unsigned long) ops->data, ops->size,
+					ops->mod_lvl);
+			if (rc != 0) {
+				pr_err("Starting the data collection for %s "
+				       "failed with rc=%d\n", ops->name, rc);
+			}
+		}
+	}
+	mutex_unlock(&appldata_ops_mutex);
+	return 0;
+}
+
+static int appldata_thaw(struct device *dev)
+{
+	return appldata_restore(dev);
+}
+
+static const struct dev_pm_ops appldata_pm_ops = {
+	.freeze		= appldata_freeze,
+	.thaw		= appldata_thaw,
+	.restore	= appldata_restore,
+};
+
+static struct platform_driver appldata_pdrv = {
+	.driver = {
+		.name	= "appldata",
+		.owner	= THIS_MODULE,
+		.pm	= &appldata_pm_ops,
+	},
+};
+/************************* suspend / resume <END> ****************************/
+
+
+/******************************* init / exit *********************************/
+
+static void __cpuinit appldata_online_cpu(int cpu)
+{
+	init_virt_timer(&per_cpu(appldata_timer, cpu));
+	per_cpu(appldata_timer, cpu).function = appldata_timer_function;
+	per_cpu(appldata_timer, cpu).data = (unsigned long)
+		&appldata_work;
+	atomic_inc(&appldata_expire_count);
+	spin_lock(&appldata_timer_lock);
+	__appldata_vtimer_setup(APPLDATA_MOD_TIMER);
+	spin_unlock(&appldata_timer_lock);
+}
+
+static void __cpuinit appldata_offline_cpu(int cpu)
+{
+	del_virt_timer(&per_cpu(appldata_timer, cpu));
+	if (atomic_dec_and_test(&appldata_expire_count)) {
+		atomic_set(&appldata_expire_count, num_online_cpus());
+		queue_work(appldata_wq, &appldata_work);
+	}
+	spin_lock(&appldata_timer_lock);
+	__appldata_vtimer_setup(APPLDATA_MOD_TIMER);
+	spin_unlock(&appldata_timer_lock);
+}
+
+static int __cpuinit appldata_cpu_notify(struct notifier_block *self,
+					 unsigned long action,
+					 void *hcpu)
+{
+	switch (action) {
+	case CPU_ONLINE:
+	case CPU_ONLINE_FROZEN:
+		appldata_online_cpu((long) hcpu);
+		break;
+	case CPU_DEAD:
+	case CPU_DEAD_FROZEN:
+		appldata_offline_cpu((long) hcpu);
+		break;
+	default:
+		break;
+	}
+	return NOTIFY_OK;
+}
+
+static struct notifier_block __cpuinitdata appldata_nb = {
+	.notifier_call = appldata_cpu_notify,
+};
+
+/*
+ * appldata_init()
+ *
+ * init timer, register /proc entries
+ */
+static int __init appldata_init(void)
+{
+	int i, rc;
+
+	rc = platform_driver_register(&appldata_pdrv);
+	if (rc)
+		return rc;
+
+	appldata_pdev = platform_device_register_simple("appldata", -1, NULL,
+							0);
+	if (IS_ERR(appldata_pdev)) {
+		rc = PTR_ERR(appldata_pdev);
+		goto out_driver;
+	}
+	appldata_wq = create_singlethread_workqueue("appldata");
+	if (!appldata_wq) {
+		rc = -ENOMEM;
+		goto out_device;
+	}
+
+	get_online_cpus();
+	for_each_online_cpu(i)
+		appldata_online_cpu(i);
+	put_online_cpus();
+
+	/* Register cpu hotplug notifier */
+	register_hotcpu_notifier(&appldata_nb);
+
+	appldata_sysctl_header = register_sysctl_table(appldata_dir_table);
+	return 0;
+
+out_device:
+	platform_device_unregister(appldata_pdev);
+out_driver:
+	platform_driver_unregister(&appldata_pdrv);
+	return rc;
+}
+
+__initcall(appldata_init);
+
+/**************************** init / exit <END> ******************************/
+
+EXPORT_SYMBOL_GPL(appldata_register_ops);
+EXPORT_SYMBOL_GPL(appldata_unregister_ops);
+EXPORT_SYMBOL_GPL(appldata_diag);
+
+#ifdef CONFIG_SWAP
+EXPORT_SYMBOL_GPL(si_swapinfo);
+#endif
+EXPORT_SYMBOL_GPL(nr_threads);
+EXPORT_SYMBOL_GPL(nr_running);
+EXPORT_SYMBOL_GPL(nr_iowait);

kernel/arch/s390/appldata/appldata_mem.c

@@ -0,0 +1,155 @@
+/*
+ * arch/s390/appldata/appldata_mem.c
+ *
+ * Data gathering module for Linux-VM Monitor Stream, Stage 1.
+ * Collects data related to memory management.
+ *
+ * Copyright (C) 2003,2006 IBM Corporation, IBM Deutschland Entwicklung GmbH.
+ *
+ * Author: Gerald Schaefer <gerald.schaefer@de.ibm.com>
+ */
+
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/errno.h>
+#include <linux/kernel_stat.h>
+#include <linux/pagemap.h>
+#include <linux/swap.h>
+#include <asm/io.h>
+
+#include "appldata.h"
+
+
+#define P2K(x) ((x) << (PAGE_SHIFT - 10))	/* Converts #Pages to KB */
+
+/*
+ * Memory data
+ *
+ * This is accessed as binary data by z/VM. If changes to it can't be avoided,
+ * the structure version (product ID, see appldata_base.c) needs to be changed
+ * as well and all documentation and z/VM applications using it must be
+ * updated.
+ *
+ * The record layout is documented in the Linux for zSeries Device Drivers
+ * book:
+ * http://oss.software.ibm.com/developerworks/opensource/linux390/index.shtml
+ */
+static struct appldata_mem_data {
+	u64 timestamp;
+	u32 sync_count_1;       /* after VM collected the record data, */
+	u32 sync_count_2;	/* sync_count_1 and sync_count_2 should be the
+				   same. If not, the record has been updated on
+				   the Linux side while VM was collecting the
+				   (possibly corrupt) data */
+
+	u64 pgpgin;		/* data read from disk  */
+	u64 pgpgout;		/* data written to disk */
+	u64 pswpin;		/* pages swapped in  */
+	u64 pswpout;		/* pages swapped out */
+
+	u64 sharedram;		/* sharedram is currently set to 0 */
+
+	u64 totalram;		/* total main memory size */
+	u64 freeram;		/* free main memory size  */
+	u64 totalhigh;		/* total high memory size */
+	u64 freehigh;		/* free high memory size  */
+
+	u64 bufferram;		/* memory reserved for buffers, free cache */
+	u64 cached;		/* size of (used) cache, w/o buffers */
+	u64 totalswap;		/* total swap space size */
+	u64 freeswap;		/* free swap space */
+
+// New in 2.6 -->
+	u64 pgalloc;		/* page allocations */
+	u64 pgfault;		/* page faults (major+minor) */
+	u64 pgmajfault;		/* page faults (major only) */
+// <-- New in 2.6
+
+} __attribute__((packed)) appldata_mem_data;
+
+
+/*
+ * appldata_get_mem_data()
+ *
+ * gather memory data
+ */
+static void appldata_get_mem_data(void *data)
+{
+	/*
+	 * don't put large structures on the stack, we are
+	 * serialized through the appldata_ops_mutex and can use static
+	 */
+	static struct sysinfo val;
+	unsigned long ev[NR_VM_EVENT_ITEMS];
+	struct appldata_mem_data *mem_data;
+
+	mem_data = data;
+	mem_data->sync_count_1++;
+
+	all_vm_events(ev);
+	mem_data->pgpgin     = ev[PGPGIN] >> 1;
+	mem_data->pgpgout    = ev[PGPGOUT] >> 1;
+	mem_data->pswpin     = ev[PSWPIN];
+	mem_data->pswpout    = ev[PSWPOUT];
+	mem_data->pgalloc    = ev[PGALLOC_NORMAL];
+	mem_data->pgalloc    += ev[PGALLOC_DMA];
+	mem_data->pgfault    = ev[PGFAULT];
+	mem_data->pgmajfault = ev[PGMAJFAULT];
+
+	si_meminfo(&val);
+	mem_data->sharedram = val.sharedram;
+	mem_data->totalram  = P2K(val.totalram);
+	mem_data->freeram   = P2K(val.freeram);
+	mem_data->totalhigh = P2K(val.totalhigh);
+	mem_data->freehigh  = P2K(val.freehigh);
+	mem_data->bufferram = P2K(val.bufferram);
+	mem_data->cached    = P2K(global_page_state(NR_FILE_PAGES)
+				- val.bufferram);
+
+	si_swapinfo(&val);
+	mem_data->totalswap = P2K(val.totalswap);
+	mem_data->freeswap  = P2K(val.freeswap);
+
+	mem_data->timestamp = get_clock();
+	mem_data->sync_count_2++;
+}
+
+
+static struct appldata_ops ops = {
+	.name      = "mem",
+	.record_nr = APPLDATA_RECORD_MEM_ID,
+	.size	   = sizeof(struct appldata_mem_data),
+	.callback  = &appldata_get_mem_data,
+	.data      = &appldata_mem_data,
+	.owner     = THIS_MODULE,
+	.mod_lvl   = {0xF0, 0xF0},		/* EBCDIC "00" */
+};
+
+
+/*
+ * appldata_mem_init()
+ *
+ * init_data, register ops
+ */
+static int __init appldata_mem_init(void)
+{
+	return appldata_register_ops(&ops);
+}
+
+/*
+ * appldata_mem_exit()
+ *
+ * unregister ops
+ */
+static void __exit appldata_mem_exit(void)
+{
+	appldata_unregister_ops(&ops);
+}
+
+
+module_init(appldata_mem_init);
+module_exit(appldata_mem_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Gerald Schaefer");
+MODULE_DESCRIPTION("Linux-VM Monitor Stream, MEMORY statistics");

kernel/arch/s390/appldata/appldata_net_sum.c

@@ -0,0 +1,158 @@
+/*
+ * arch/s390/appldata/appldata_net_sum.c
+ *
+ * Data gathering module for Linux-VM Monitor Stream, Stage 1.
+ * Collects accumulated network statistics (Packets received/transmitted,
+ * dropped, errors, ...).
+ *
+ * Copyright (C) 2003,2006 IBM Corporation, IBM Deutschland Entwicklung GmbH.
+ *
+ * Author: Gerald Schaefer <gerald.schaefer@de.ibm.com>
+ */
+
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/errno.h>
+#include <linux/kernel_stat.h>
+#include <linux/netdevice.h>
+#include <net/net_namespace.h>
+
+#include "appldata.h"
+
+
+/*
+ * Network data
+ *
+ * This is accessed as binary data by z/VM. If changes to it can't be avoided,
+ * the structure version (product ID, see appldata_base.c) needs to be changed
+ * as well and all documentation and z/VM applications using it must be updated.
+ *
+ * The record layout is documented in the Linux for zSeries Device Drivers
+ * book:
+ * http://oss.software.ibm.com/developerworks/opensource/linux390/index.shtml
+ */
+static struct appldata_net_sum_data {
+	u64 timestamp;
+	u32 sync_count_1;	/* after VM collected the record data, */
+	u32 sync_count_2;	/* sync_count_1 and sync_count_2 should be the
+				   same. If not, the record has been updated on
+				   the Linux side while VM was collecting the
+				   (possibly corrupt) data */
+
+	u32 nr_interfaces;	/* nr. of network interfaces being monitored */
+
+	u32 padding;		/* next value is 64-bit aligned, so these */
+				/* 4 byte would be padded out by compiler */
+
+	u64 rx_packets;		/* total packets received        */
+	u64 tx_packets;		/* total packets transmitted     */
+	u64 rx_bytes;		/* total bytes received          */
+	u64 tx_bytes;		/* total bytes transmitted       */
+	u64 rx_errors;		/* bad packets received          */
+	u64 tx_errors;		/* packet transmit problems      */
+	u64 rx_dropped;		/* no space in linux buffers     */
+	u64 tx_dropped;		/* no space available in linux   */
+	u64 collisions;		/* collisions while transmitting */
+} __attribute__((packed)) appldata_net_sum_data;
+
+
+/*
+ * appldata_get_net_sum_data()
+ *
+ * gather accumulated network statistics
+ */
+static void appldata_get_net_sum_data(void *data)
+{
+	int i;
+	struct appldata_net_sum_data *net_data;
+	struct net_device *dev;
+	unsigned long rx_packets, tx_packets, rx_bytes, tx_bytes, rx_errors,
+			tx_errors, rx_dropped, tx_dropped, collisions;
+
+	net_data = data;
+	net_data->sync_count_1++;
+
+	i = 0;
+	rx_packets = 0;
+	tx_packets = 0;
+	rx_bytes   = 0;
+	tx_bytes   = 0;
+	rx_errors  = 0;
+	tx_errors  = 0;
+	rx_dropped = 0;
+	tx_dropped = 0;
+	collisions = 0;
+
+	rcu_read_lock();
+	for_each_netdev_rcu(&init_net, dev) {
+		const struct rtnl_link_stats64 *stats;
+		struct rtnl_link_stats64 temp;
+
+		stats = dev_get_stats(dev, &temp);
+		rx_packets += stats->rx_packets;
+		tx_packets += stats->tx_packets;
+		rx_bytes   += stats->rx_bytes;
+		tx_bytes   += stats->tx_bytes;
+		rx_errors  += stats->rx_errors;
+		tx_errors  += stats->tx_errors;
+		rx_dropped += stats->rx_dropped;
+		tx_dropped += stats->tx_dropped;
+		collisions += stats->collisions;
+		i++;
+	}
+	rcu_read_unlock();
+
+	net_data->nr_interfaces = i;
+	net_data->rx_packets = rx_packets;
+	net_data->tx_packets = tx_packets;
+	net_data->rx_bytes   = rx_bytes;
+	net_data->tx_bytes   = tx_bytes;
+	net_data->rx_errors  = rx_errors;
+	net_data->tx_errors  = tx_errors;
+	net_data->rx_dropped = rx_dropped;
+	net_data->tx_dropped = tx_dropped;
+	net_data->collisions = collisions;
+
+	net_data->timestamp = get_clock();
+	net_data->sync_count_2++;
+}
+
+
+static struct appldata_ops ops = {
+	.name	   = "net_sum",
+	.record_nr = APPLDATA_RECORD_NET_SUM_ID,
+	.size	   = sizeof(struct appldata_net_sum_data),
+	.callback  = &appldata_get_net_sum_data,
+	.data      = &appldata_net_sum_data,
+	.owner     = THIS_MODULE,
+	.mod_lvl   = {0xF0, 0xF0},		/* EBCDIC "00" */
+};
+
+
+/*
+ * appldata_net_init()
+ *
+ * init data, register ops
+ */
+static int __init appldata_net_init(void)
+{
+	return appldata_register_ops(&ops);
+}
+
+/*
+ * appldata_net_exit()
+ *
+ * unregister ops
+ */
+static void __exit appldata_net_exit(void)
+{
+	appldata_unregister_ops(&ops);
+}
+
+
+module_init(appldata_net_init);
+module_exit(appldata_net_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Gerald Schaefer");
+MODULE_DESCRIPTION("Linux-VM Monitor Stream, accumulated network statistics");

kernel/arch/s390/appldata/appldata_os.c

@@ -0,0 +1,220 @@
+/*
+ * arch/s390/appldata/appldata_os.c
+ *
+ * Data gathering module for Linux-VM Monitor Stream, Stage 1.
+ * Collects misc. OS related data (CPU utilization, running processes).
+ *
+ * Copyright (C) 2003,2006 IBM Corporation, IBM Deutschland Entwicklung GmbH.
+ *
+ * Author: Gerald Schaefer <gerald.schaefer@de.ibm.com>
+ */
+
+#define KMSG_COMPONENT	"appldata"
+#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
+
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/slab.h>
+#include <linux/errno.h>
+#include <linux/kernel_stat.h>
+#include <linux/netdevice.h>
+#include <linux/sched.h>
+#include <asm/appldata.h>
+#include <asm/smp.h>
+
+#include "appldata.h"
+
+
+#define LOAD_INT(x) ((x) >> FSHIFT)
+#define LOAD_FRAC(x) LOAD_INT(((x) & (FIXED_1-1)) * 100)
+
+/*
+ * OS data
+ *
+ * This is accessed as binary data by z/VM. If changes to it can't be avoided,
+ * the structure version (product ID, see appldata_base.c) needs to be changed
+ * as well and all documentation and z/VM applications using it must be
+ * updated.
+ *
+ * The record layout is documented in the Linux for zSeries Device Drivers
+ * book:
+ * http://oss.software.ibm.com/developerworks/opensource/linux390/index.shtml
+ */
+struct appldata_os_per_cpu {
+	u32 per_cpu_user;	/* timer ticks spent in user mode   */
+	u32 per_cpu_nice;	/* ... spent with modified priority */
+	u32 per_cpu_system;	/* ... spent in kernel mode         */
+	u32 per_cpu_idle;	/* ... spent in idle mode           */
+
+	/* New in 2.6 */
+	u32 per_cpu_irq;	/* ... spent in interrupts          */
+	u32 per_cpu_softirq;	/* ... spent in softirqs            */
+	u32 per_cpu_iowait;	/* ... spent while waiting for I/O  */
+
+	/* New in modification level 01 */
+	u32 per_cpu_steal;	/* ... stolen by hypervisor	    */
+	u32 cpu_id;		/* number of this CPU		    */
+} __attribute__((packed));
+
+struct appldata_os_data {
+	u64 timestamp;
+	u32 sync_count_1;	/* after VM collected the record data, */
+	u32 sync_count_2;	/* sync_count_1 and sync_count_2 should be the
+				   same. If not, the record has been updated on
+				   the Linux side while VM was collecting the
+				   (possibly corrupt) data */
+
+	u32 nr_cpus;		/* number of (virtual) CPUs        */
+	u32 per_cpu_size;	/* size of the per-cpu data struct */
+	u32 cpu_offset;		/* offset of the first per-cpu data struct */
+
+	u32 nr_running;		/* number of runnable threads      */
+	u32 nr_threads;		/* number of threads               */
+	u32 avenrun[3];		/* average nr. of running processes during */
+				/* the last 1, 5 and 15 minutes */
+
+	/* New in 2.6 */
+	u32 nr_iowait;		/* number of blocked threads
+				   (waiting for I/O)               */
+
+	/* per cpu data */
+	struct appldata_os_per_cpu os_cpu[0];
+} __attribute__((packed));
+
+static struct appldata_os_data *appldata_os_data;
+
+static struct appldata_ops ops = {
+	.name	   = "os",
+	.record_nr = APPLDATA_RECORD_OS_ID,
+	.owner	   = THIS_MODULE,
+	.mod_lvl   = {0xF0, 0xF1},		/* EBCDIC "01" */
+};
+
+
+/*
+ * appldata_get_os_data()
+ *
+ * gather OS data
+ */
+static void appldata_get_os_data(void *data)
+{
+	int i, j, rc;
+	struct appldata_os_data *os_data;
+	unsigned int new_size;
+
+	os_data = data;
+	os_data->sync_count_1++;
+
+	os_data->nr_threads = nr_threads;
+	os_data->nr_running = nr_running();
+	os_data->nr_iowait  = nr_iowait();
+	os_data->avenrun[0] = avenrun[0] + (FIXED_1/200);
+	os_data->avenrun[1] = avenrun[1] + (FIXED_1/200);
+	os_data->avenrun[2] = avenrun[2] + (FIXED_1/200);
+
+	j = 0;
+	for_each_online_cpu(i) {
+		os_data->os_cpu[j].per_cpu_user =
+			cputime_to_jiffies(kcpustat_cpu(i).cpustat[CPUTIME_USER]);
+		os_data->os_cpu[j].per_cpu_nice =
+			cputime_to_jiffies(kcpustat_cpu(i).cpustat[CPUTIME_NICE]);
+		os_data->os_cpu[j].per_cpu_system =
+			cputime_to_jiffies(kcpustat_cpu(i).cpustat[CPUTIME_SYSTEM]);
+		os_data->os_cpu[j].per_cpu_idle =
+			cputime_to_jiffies(kcpustat_cpu(i).cpustat[CPUTIME_IDLE]);
+		os_data->os_cpu[j].per_cpu_irq =
+			cputime_to_jiffies(kcpustat_cpu(i).cpustat[CPUTIME_IRQ]);
+		os_data->os_cpu[j].per_cpu_softirq =
+			cputime_to_jiffies(kcpustat_cpu(i).cpustat[CPUTIME_SOFTIRQ]);
+		os_data->os_cpu[j].per_cpu_iowait =
+			cputime_to_jiffies(kcpustat_cpu(i).cpustat[CPUTIME_IOWAIT]);
+		os_data->os_cpu[j].per_cpu_steal =
+			cputime_to_jiffies(kcpustat_cpu(i).cpustat[CPUTIME_STEAL]);
+		os_data->os_cpu[j].cpu_id = i;
+		j++;
+	}
+
+	os_data->nr_cpus = j;
+
+	new_size = sizeof(struct appldata_os_data) +
+		   (os_data->nr_cpus * sizeof(struct appldata_os_per_cpu));
+	if (ops.size != new_size) {
+		if (ops.active) {
+			rc = appldata_diag(APPLDATA_RECORD_OS_ID,
+					   APPLDATA_START_INTERVAL_REC,
+					   (unsigned long) ops.data, new_size,
+					   ops.mod_lvl);
+			if (rc != 0)
+				pr_err("Starting a new OS data collection "
+				       "failed with rc=%d\n", rc);
+
+			rc = appldata_diag(APPLDATA_RECORD_OS_ID,
+					   APPLDATA_STOP_REC,
+					   (unsigned long) ops.data, ops.size,
+					   ops.mod_lvl);
+			if (rc != 0)
+				pr_err("Stopping a faulty OS data "
+				       "collection failed with rc=%d\n", rc);
+		}
+		ops.size = new_size;
+	}
+	os_data->timestamp = get_clock();
+	os_data->sync_count_2++;
+}
+
+
+/*
+ * appldata_os_init()
+ *
+ * init data, register ops
+ */
+static int __init appldata_os_init(void)
+{
+	int rc, max_size;
+
+	max_size = sizeof(struct appldata_os_data) +
+		   (NR_CPUS * sizeof(struct appldata_os_per_cpu));
+	if (max_size > APPLDATA_MAX_REC_SIZE) {
+		pr_err("Maximum OS record size %i exceeds the maximum "
+		       "record size %i\n", max_size, APPLDATA_MAX_REC_SIZE);
+		rc = -ENOMEM;
+		goto out;
+	}
+
+	appldata_os_data = kzalloc(max_size, GFP_KERNEL | GFP_DMA);
+	if (appldata_os_data == NULL) {
+		rc = -ENOMEM;
+		goto out;
+	}
+
+	appldata_os_data->per_cpu_size = sizeof(struct appldata_os_per_cpu);
+	appldata_os_data->cpu_offset   = offsetof(struct appldata_os_data,
+							os_cpu);
+
+	ops.data = appldata_os_data;
+	ops.callback  = &appldata_get_os_data;
+	rc = appldata_register_ops(&ops);
+	if (rc != 0)
+		kfree(appldata_os_data);
+out:
+	return rc;
+}
+
+/*
+ * appldata_os_exit()
+ *
+ * unregister ops
+ */
+static void __exit appldata_os_exit(void)
+{
+	appldata_unregister_ops(&ops);
+	kfree(appldata_os_data);
+}
+
+
+module_init(appldata_os_init);
+module_exit(appldata_os_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Gerald Schaefer");
+MODULE_DESCRIPTION("Linux-VM Monitor Stream, OS statistics");