OpenCloudOS-Kernel/arch/s390/appldata/appldata_base.c

429 lines
10 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0
/*
* 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/sched/stat.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/uaccess.h>
#include <linux/io.h>
#include <asm/appldata.h>
#include <asm/vtimer.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 */
/*
* /proc entries (sysctl)
*/
static const char appldata_proc_name[APPLDATA_PROC_NAME_LENGTH] = "appldata";
static int appldata_timer_handler(struct ctl_table *ctl, int write,
void *buffer, size_t *lenp, loff_t *ppos);
static int appldata_interval_handler(struct ctl_table *ctl, int write,
void *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,
},
{ },
};
/*
* Timer
*/
static struct vtimer_list appldata_timer;
static DEFINE_SPINLOCK(appldata_timer_lock);
static int appldata_interval = APPLDATA_CPU_INTERVAL;
static int appldata_timer_active;
/*
* 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)
{
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;
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);
}
static struct appldata_product_id appldata_id = {
.prod_nr = {0xD3, 0xC9, 0xD5, 0xE4,
0xE7, 0xD2, 0xD9}, /* "LINUXKR" */
.prod_fn = 0xD5D3, /* "NL" */
.version_nr = 0xF2F6, /* "26" */
.release_nr = 0xF0F1, /* "01" */
};
/*
* 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_parameter_list *parm_list;
struct appldata_product_id *id;
int rc;
parm_list = kmalloc(sizeof(*parm_list), GFP_KERNEL);
id = kmemdup(&appldata_id, sizeof(appldata_id), GFP_KERNEL);
rc = -ENOMEM;
if (parm_list && id) {
id->record_nr = record_nr;
id->mod_lvl = (mod_lvl[0]) << 8 | mod_lvl[1];
rc = appldata_asm(parm_list, id, function,
(void *) buffer, length);
}
kfree(id);
kfree(parm_list);
return rc;
}
/************************ timer, work, DIAG <END> ****************************/
/****************************** /proc stuff **********************************/
#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 timer_interval = (u64) appldata_interval * 1000 * TOD_MICRO;
switch (cmd) {
case APPLDATA_ADD_TIMER:
if (appldata_timer_active)
break;
appldata_timer.expires = timer_interval;
add_virt_timer_periodic(&appldata_timer);
appldata_timer_active = 1;
break;
case APPLDATA_DEL_TIMER:
del_virt_timer(&appldata_timer);
if (!appldata_timer_active)
break;
appldata_timer_active = 0;
break;
case APPLDATA_MOD_TIMER:
if (!appldata_timer_active)
break;
mod_virt_timer_periodic(&appldata_timer, timer_interval);
}
}
/*
* appldata_timer_handler()
*
* Start/Stop timer, show status of timer (0 = not active, 1 = active)
*/
static int
appldata_timer_handler(struct ctl_table *ctl, int write,
void *buffer, size_t *lenp, loff_t *ppos)
{
int timer_active = appldata_timer_active;
int rc;
struct ctl_table ctl_entry = {
.procname = ctl->procname,
.data = &timer_active,
.maxlen = sizeof(int),
proc/sysctl: add shared variables for range check In the sysctl code the proc_dointvec_minmax() function is often used to validate the user supplied value between an allowed range. This function uses the extra1 and extra2 members from struct ctl_table as minimum and maximum allowed value. On sysctl handler declaration, in every source file there are some readonly variables containing just an integer which address is assigned to the extra1 and extra2 members, so the sysctl range is enforced. The special values 0, 1 and INT_MAX are very often used as range boundary, leading duplication of variables like zero=0, one=1, int_max=INT_MAX in different source files: $ git grep -E '\.extra[12].*&(zero|one|int_max)' |wc -l 248 Add a const int array containing the most commonly used values, some macros to refer more easily to the correct array member, and use them instead of creating a local one for every object file. This is the bloat-o-meter output comparing the old and new binary compiled with the default Fedora config: # scripts/bloat-o-meter -d vmlinux.o.old vmlinux.o add/remove: 2/2 grow/shrink: 0/2 up/down: 24/-188 (-164) Data old new delta sysctl_vals - 12 +12 __kstrtab_sysctl_vals - 12 +12 max 14 10 -4 int_max 16 - -16 one 68 - -68 zero 128 28 -100 Total: Before=20583249, After=20583085, chg -0.00% [mcroce@redhat.com: tipc: remove two unused variables] Link: http://lkml.kernel.org/r/20190530091952.4108-1-mcroce@redhat.com [akpm@linux-foundation.org: fix net/ipv6/sysctl_net_ipv6.c] [arnd@arndb.de: proc/sysctl: make firmware loader table conditional] Link: http://lkml.kernel.org/r/20190617130014.1713870-1-arnd@arndb.de [akpm@linux-foundation.org: fix fs/eventpoll.c] Link: http://lkml.kernel.org/r/20190430180111.10688-1-mcroce@redhat.com Signed-off-by: Matteo Croce <mcroce@redhat.com> Signed-off-by: Arnd Bergmann <arnd@arndb.de> Acked-by: Kees Cook <keescook@chromium.org> Reviewed-by: Aaron Tomlin <atomlin@redhat.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Stephen Rothwell <sfr@canb.auug.org.au> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-07-19 06:58:50 +08:00
.extra1 = SYSCTL_ZERO,
.extra2 = SYSCTL_ONE,
};
rc = proc_douintvec_minmax(&ctl_entry, write, buffer, lenp, ppos);
if (rc < 0 || !write)
return rc;
spin_lock(&appldata_timer_lock);
if (timer_active)
__appldata_vtimer_setup(APPLDATA_ADD_TIMER);
else
__appldata_vtimer_setup(APPLDATA_DEL_TIMER);
spin_unlock(&appldata_timer_lock);
return 0;
}
/*
* appldata_interval_handler()
*
* Set (CPU) timer interval for collection of data (in milliseconds), show
* current timer interval.
*/
static int
appldata_interval_handler(struct ctl_table *ctl, int write,
void *buffer, size_t *lenp, loff_t *ppos)
{
int interval = appldata_interval;
int rc;
struct ctl_table ctl_entry = {
.procname = ctl->procname,
.data = &interval,
.maxlen = sizeof(int),
proc/sysctl: add shared variables for range check In the sysctl code the proc_dointvec_minmax() function is often used to validate the user supplied value between an allowed range. This function uses the extra1 and extra2 members from struct ctl_table as minimum and maximum allowed value. On sysctl handler declaration, in every source file there are some readonly variables containing just an integer which address is assigned to the extra1 and extra2 members, so the sysctl range is enforced. The special values 0, 1 and INT_MAX are very often used as range boundary, leading duplication of variables like zero=0, one=1, int_max=INT_MAX in different source files: $ git grep -E '\.extra[12].*&(zero|one|int_max)' |wc -l 248 Add a const int array containing the most commonly used values, some macros to refer more easily to the correct array member, and use them instead of creating a local one for every object file. This is the bloat-o-meter output comparing the old and new binary compiled with the default Fedora config: # scripts/bloat-o-meter -d vmlinux.o.old vmlinux.o add/remove: 2/2 grow/shrink: 0/2 up/down: 24/-188 (-164) Data old new delta sysctl_vals - 12 +12 __kstrtab_sysctl_vals - 12 +12 max 14 10 -4 int_max 16 - -16 one 68 - -68 zero 128 28 -100 Total: Before=20583249, After=20583085, chg -0.00% [mcroce@redhat.com: tipc: remove two unused variables] Link: http://lkml.kernel.org/r/20190530091952.4108-1-mcroce@redhat.com [akpm@linux-foundation.org: fix net/ipv6/sysctl_net_ipv6.c] [arnd@arndb.de: proc/sysctl: make firmware loader table conditional] Link: http://lkml.kernel.org/r/20190617130014.1713870-1-arnd@arndb.de [akpm@linux-foundation.org: fix fs/eventpoll.c] Link: http://lkml.kernel.org/r/20190430180111.10688-1-mcroce@redhat.com Signed-off-by: Matteo Croce <mcroce@redhat.com> Signed-off-by: Arnd Bergmann <arnd@arndb.de> Acked-by: Kees Cook <keescook@chromium.org> Reviewed-by: Aaron Tomlin <atomlin@redhat.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Stephen Rothwell <sfr@canb.auug.org.au> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-07-19 06:58:50 +08:00
.extra1 = SYSCTL_ONE,
};
rc = proc_dointvec_minmax(&ctl_entry, write, buffer, lenp, ppos);
if (rc < 0 || !write)
return rc;
spin_lock(&appldata_timer_lock);
appldata_interval = interval;
__appldata_vtimer_setup(APPLDATA_MOD_TIMER);
spin_unlock(&appldata_timer_lock);
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(struct ctl_table *ctl, int write,
void *buffer, size_t *lenp, loff_t *ppos)
{
struct appldata_ops *ops = NULL, *tmp_ops;
struct list_head *lh;
int rc, found;
int active;
struct ctl_table ctl_entry = {
.data = &active,
.maxlen = sizeof(int),
proc/sysctl: add shared variables for range check In the sysctl code the proc_dointvec_minmax() function is often used to validate the user supplied value between an allowed range. This function uses the extra1 and extra2 members from struct ctl_table as minimum and maximum allowed value. On sysctl handler declaration, in every source file there are some readonly variables containing just an integer which address is assigned to the extra1 and extra2 members, so the sysctl range is enforced. The special values 0, 1 and INT_MAX are very often used as range boundary, leading duplication of variables like zero=0, one=1, int_max=INT_MAX in different source files: $ git grep -E '\.extra[12].*&(zero|one|int_max)' |wc -l 248 Add a const int array containing the most commonly used values, some macros to refer more easily to the correct array member, and use them instead of creating a local one for every object file. This is the bloat-o-meter output comparing the old and new binary compiled with the default Fedora config: # scripts/bloat-o-meter -d vmlinux.o.old vmlinux.o add/remove: 2/2 grow/shrink: 0/2 up/down: 24/-188 (-164) Data old new delta sysctl_vals - 12 +12 __kstrtab_sysctl_vals - 12 +12 max 14 10 -4 int_max 16 - -16 one 68 - -68 zero 128 28 -100 Total: Before=20583249, After=20583085, chg -0.00% [mcroce@redhat.com: tipc: remove two unused variables] Link: http://lkml.kernel.org/r/20190530091952.4108-1-mcroce@redhat.com [akpm@linux-foundation.org: fix net/ipv6/sysctl_net_ipv6.c] [arnd@arndb.de: proc/sysctl: make firmware loader table conditional] Link: http://lkml.kernel.org/r/20190617130014.1713870-1-arnd@arndb.de [akpm@linux-foundation.org: fix fs/eventpoll.c] Link: http://lkml.kernel.org/r/20190430180111.10688-1-mcroce@redhat.com Signed-off-by: Matteo Croce <mcroce@redhat.com> Signed-off-by: Arnd Bergmann <arnd@arndb.de> Acked-by: Kees Cook <keescook@chromium.org> Reviewed-by: Aaron Tomlin <atomlin@redhat.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Stephen Rothwell <sfr@canb.auug.org.au> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-07-19 06:58:50 +08:00
.extra1 = SYSCTL_ZERO,
.extra2 = SYSCTL_ONE,
};
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[0] == 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);
active = ops->active;
rc = proc_douintvec_minmax(&ctl_entry, write, buffer, lenp, ppos);
if (rc < 0 || !write) {
module_put(ops->owner);
return rc;
}
mutex_lock(&appldata_ops_mutex);
if (active && (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 (!active && (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);
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;
/* The last entry must be an empty one */
ops->ctl_table = kcalloc(2, 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 = ops->name;
ops->ctl_table[0].mode = S_IRUGO | S_IWUSR;
ops->ctl_table[0].proc_handler = appldata_generic_handler;
ops->ctl_table[0].data = ops;
ops->sysctl_header = register_sysctl(appldata_proc_name, 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> **************************/
/******************************* init / exit *********************************/
/*
* appldata_init()
*
* init timer, register /proc entries
*/
static int __init appldata_init(void)
{
init_virt_timer(&appldata_timer);
appldata_timer.function = appldata_timer_function;
appldata_timer.data = (unsigned long) &appldata_work;
appldata_wq = alloc_ordered_workqueue("appldata", 0);
if (!appldata_wq)
return -ENOMEM;
appldata_sysctl_header = register_sysctl(appldata_proc_name, appldata_table);
return 0;
}
__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);