linux/drivers/s390/char/vmwatchdog.c

338 lines
8.1 KiB
C
Raw Normal View History

/*
* Watchdog implementation based on z/VM Watchdog Timer API
*
* Copyright IBM Corp. 2004, 2009
*
* The user space watchdog daemon can use this driver as
* /dev/vmwatchdog to have z/VM execute the specified CP
* command when the timeout expires. The default command is
* "IPL", which which cause an immediate reboot.
*/
#define KMSG_COMPONENT "vmwatchdog"
#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
#include <linux/init.h>
#include <linux/fs.h>
#include <linux/kernel.h>
#include <linux/miscdevice.h>
#include <linux/module.h>
#include <linux/moduleparam.h>
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo <tj@kernel.org> Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 09:04:11 +01:00
#include <linux/slab.h>
#include <linux/suspend.h>
#include <linux/watchdog.h>
#include <asm/ebcdic.h>
#include <asm/io.h>
#include <asm/uaccess.h>
#define MAX_CMDLEN 240
#define MIN_INTERVAL 15
static char vmwdt_cmd[MAX_CMDLEN] = "IPL";
static bool vmwdt_conceal;
static bool vmwdt_nowayout = WATCHDOG_NOWAYOUT;
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Arnd Bergmann <arndb@de.ibm.com>");
MODULE_DESCRIPTION("z/VM Watchdog Timer");
module_param_string(cmd, vmwdt_cmd, MAX_CMDLEN, 0644);
MODULE_PARM_DESC(cmd, "CP command that is run when the watchdog triggers");
module_param_named(conceal, vmwdt_conceal, bool, 0644);
MODULE_PARM_DESC(conceal, "Enable the CONCEAL CP option while the watchdog "
" is active");
module_param_named(nowayout, vmwdt_nowayout, bool, 0);
MODULE_PARM_DESC(nowayout, "Watchdog cannot be stopped once started"
" (default=CONFIG_WATCHDOG_NOWAYOUT)");
MODULE_ALIAS_MISCDEV(WATCHDOG_MINOR);
static unsigned int vmwdt_interval = 60;
static unsigned long vmwdt_is_open;
static int vmwdt_expect_close;
static DEFINE_MUTEX(vmwdt_mutex);
#define VMWDT_OPEN 0 /* devnode is open or suspend in progress */
#define VMWDT_RUNNING 1 /* The watchdog is armed */
enum vmwdt_func {
/* function codes */
wdt_init = 0,
wdt_change = 1,
wdt_cancel = 2,
/* flags */
wdt_conceal = 0x80000000,
};
static int __diag288(enum vmwdt_func func, unsigned int timeout,
char *cmd, size_t len)
{
register unsigned long __func asm("2") = func;
register unsigned long __timeout asm("3") = timeout;
register unsigned long __cmdp asm("4") = virt_to_phys(cmd);
register unsigned long __cmdl asm("5") = len;
int err;
err = -EINVAL;
asm volatile(
" diag %1,%3,0x288\n"
"0: la %0,0\n"
"1:\n"
EX_TABLE(0b,1b)
: "+d" (err) : "d"(__func), "d"(__timeout),
"d"(__cmdp), "d"(__cmdl) : "1", "cc");
return err;
}
static int vmwdt_keepalive(void)
{
/* we allocate new memory every time to avoid having
* to track the state. static allocation is not an
* option since that might not be contiguous in real
* storage in case of a modular build */
static char *ebc_cmd;
size_t len;
int ret;
unsigned int func;
ebc_cmd = kmalloc(MAX_CMDLEN, GFP_KERNEL);
if (!ebc_cmd)
return -ENOMEM;
len = strlcpy(ebc_cmd, vmwdt_cmd, MAX_CMDLEN);
ASCEBC(ebc_cmd, MAX_CMDLEN);
EBC_TOUPPER(ebc_cmd, MAX_CMDLEN);
func = vmwdt_conceal ? (wdt_init | wdt_conceal) : wdt_init;
set_bit(VMWDT_RUNNING, &vmwdt_is_open);
ret = __diag288(func, vmwdt_interval, ebc_cmd, len);
WARN_ON(ret != 0);
kfree(ebc_cmd);
return ret;
}
static int vmwdt_disable(void)
{
int ret = __diag288(wdt_cancel, 0, "", 0);
WARN_ON(ret != 0);
clear_bit(VMWDT_RUNNING, &vmwdt_is_open);
return ret;
}
static int __init vmwdt_probe(void)
{
/* there is no real way to see if the watchdog is supported,
* so we try initializing it with a NOP command ("BEGIN")
* that won't cause any harm even if the following disable
* fails for some reason */
static char __initdata ebc_begin[] = {
194, 197, 199, 201, 213
};
if (__diag288(wdt_init, 15, ebc_begin, sizeof(ebc_begin)) != 0)
return -EINVAL;
return vmwdt_disable();
}
static int vmwdt_open(struct inode *i, struct file *f)
{
int ret;
if (test_and_set_bit(VMWDT_OPEN, &vmwdt_is_open))
return -EBUSY;
ret = vmwdt_keepalive();
if (ret)
clear_bit(VMWDT_OPEN, &vmwdt_is_open);
return ret ? ret : nonseekable_open(i, f);
}
static int vmwdt_close(struct inode *i, struct file *f)
{
if (vmwdt_expect_close == 42)
vmwdt_disable();
vmwdt_expect_close = 0;
clear_bit(VMWDT_OPEN, &vmwdt_is_open);
return 0;
}
static struct watchdog_info vmwdt_info = {
.options = WDIOF_SETTIMEOUT | WDIOF_KEEPALIVEPING | WDIOF_MAGICCLOSE,
.firmware_version = 0,
.identity = "z/VM Watchdog Timer",
};
static int __vmwdt_ioctl(unsigned int cmd, unsigned long arg)
{
switch (cmd) {
case WDIOC_GETSUPPORT:
if (copy_to_user((void __user *)arg, &vmwdt_info,
sizeof(vmwdt_info)))
return -EFAULT;
return 0;
case WDIOC_GETSTATUS:
case WDIOC_GETBOOTSTATUS:
return put_user(0, (int __user *)arg);
case WDIOC_GETTEMP:
return -EINVAL;
case WDIOC_SETOPTIONS:
{
int options, ret;
if (get_user(options, (int __user *)arg))
return -EFAULT;
ret = -EINVAL;
if (options & WDIOS_DISABLECARD) {
ret = vmwdt_disable();
if (ret)
return ret;
}
if (options & WDIOS_ENABLECARD) {
ret = vmwdt_keepalive();
}
return ret;
}
case WDIOC_GETTIMEOUT:
return put_user(vmwdt_interval, (int __user *)arg);
case WDIOC_SETTIMEOUT:
{
int interval;
if (get_user(interval, (int __user *)arg))
return -EFAULT;
if (interval < MIN_INTERVAL)
return -EINVAL;
vmwdt_interval = interval;
}
return vmwdt_keepalive();
case WDIOC_KEEPALIVE:
return vmwdt_keepalive();
}
return -EINVAL;
}
static long vmwdt_ioctl(struct file *f, unsigned int cmd, unsigned long arg)
{
int rc;
mutex_lock(&vmwdt_mutex);
rc = __vmwdt_ioctl(cmd, arg);
mutex_unlock(&vmwdt_mutex);
return (long) rc;
}
static ssize_t vmwdt_write(struct file *f, const char __user *buf,
size_t count, loff_t *ppos)
{
if(count) {
if (!vmwdt_nowayout) {
size_t i;
/* note: just in case someone wrote the magic character
* five months ago... */
vmwdt_expect_close = 0;
for (i = 0; i != count; i++) {
char c;
if (get_user(c, buf+i))
return -EFAULT;
if (c == 'V')
vmwdt_expect_close = 42;
}
}
/* someone wrote to us, we should restart timer */
vmwdt_keepalive();
}
return count;
}
static int vmwdt_resume(void)
{
clear_bit(VMWDT_OPEN, &vmwdt_is_open);
return NOTIFY_DONE;
}
/*
* It makes no sense to go into suspend while the watchdog is running.
* Depending on the memory size, the watchdog might trigger, while we
* are still saving the memory.
* We reuse the open flag to ensure that suspend and watchdog open are
* exclusive operations
*/
static int vmwdt_suspend(void)
{
if (test_and_set_bit(VMWDT_OPEN, &vmwdt_is_open)) {
pr_err("The system cannot be suspended while the watchdog"
" is in use\n");
return notifier_from_errno(-EBUSY);
}
if (test_bit(VMWDT_RUNNING, &vmwdt_is_open)) {
clear_bit(VMWDT_OPEN, &vmwdt_is_open);
pr_err("The system cannot be suspended while the watchdog"
" is running\n");
return notifier_from_errno(-EBUSY);
}
return NOTIFY_DONE;
}
/*
* This function is called for suspend and resume.
*/
static int vmwdt_power_event(struct notifier_block *this, unsigned long event,
void *ptr)
{
switch (event) {
case PM_POST_HIBERNATION:
case PM_POST_SUSPEND:
return vmwdt_resume();
case PM_HIBERNATION_PREPARE:
case PM_SUSPEND_PREPARE:
return vmwdt_suspend();
default:
return NOTIFY_DONE;
}
}
static struct notifier_block vmwdt_power_notifier = {
.notifier_call = vmwdt_power_event,
};
static const struct file_operations vmwdt_fops = {
.open = &vmwdt_open,
.release = &vmwdt_close,
.unlocked_ioctl = &vmwdt_ioctl,
.write = &vmwdt_write,
.owner = THIS_MODULE,
llseek: automatically add .llseek fop All file_operations should get a .llseek operation so we can make nonseekable_open the default for future file operations without a .llseek pointer. The three cases that we can automatically detect are no_llseek, seq_lseek and default_llseek. For cases where we can we can automatically prove that the file offset is always ignored, we use noop_llseek, which maintains the current behavior of not returning an error from a seek. New drivers should normally not use noop_llseek but instead use no_llseek and call nonseekable_open at open time. Existing drivers can be converted to do the same when the maintainer knows for certain that no user code relies on calling seek on the device file. The generated code is often incorrectly indented and right now contains comments that clarify for each added line why a specific variant was chosen. In the version that gets submitted upstream, the comments will be gone and I will manually fix the indentation, because there does not seem to be a way to do that using coccinelle. Some amount of new code is currently sitting in linux-next that should get the same modifications, which I will do at the end of the merge window. Many thanks to Julia Lawall for helping me learn to write a semantic patch that does all this. ===== begin semantic patch ===== // This adds an llseek= method to all file operations, // as a preparation for making no_llseek the default. // // The rules are // - use no_llseek explicitly if we do nonseekable_open // - use seq_lseek for sequential files // - use default_llseek if we know we access f_pos // - use noop_llseek if we know we don't access f_pos, // but we still want to allow users to call lseek // @ open1 exists @ identifier nested_open; @@ nested_open(...) { <+... nonseekable_open(...) ...+> } @ open exists@ identifier open_f; identifier i, f; identifier open1.nested_open; @@ int open_f(struct inode *i, struct file *f) { <+... ( nonseekable_open(...) | nested_open(...) ) ...+> } @ read disable optional_qualifier exists @ identifier read_f; identifier f, p, s, off; type ssize_t, size_t, loff_t; expression E; identifier func; @@ ssize_t read_f(struct file *f, char *p, size_t s, loff_t *off) { <+... ( *off = E | *off += E | func(..., off, ...) | E = *off ) ...+> } @ read_no_fpos disable optional_qualifier exists @ identifier read_f; identifier f, p, s, off; type ssize_t, size_t, loff_t; @@ ssize_t read_f(struct file *f, char *p, size_t s, loff_t *off) { ... when != off } @ write @ identifier write_f; identifier f, p, s, off; type ssize_t, size_t, loff_t; expression E; identifier func; @@ ssize_t write_f(struct file *f, const char *p, size_t s, loff_t *off) { <+... ( *off = E | *off += E | func(..., off, ...) | E = *off ) ...+> } @ write_no_fpos @ identifier write_f; identifier f, p, s, off; type ssize_t, size_t, loff_t; @@ ssize_t write_f(struct file *f, const char *p, size_t s, loff_t *off) { ... when != off } @ fops0 @ identifier fops; @@ struct file_operations fops = { ... }; @ has_llseek depends on fops0 @ identifier fops0.fops; identifier llseek_f; @@ struct file_operations fops = { ... .llseek = llseek_f, ... }; @ has_read depends on fops0 @ identifier fops0.fops; identifier read_f; @@ struct file_operations fops = { ... .read = read_f, ... }; @ has_write depends on fops0 @ identifier fops0.fops; identifier write_f; @@ struct file_operations fops = { ... .write = write_f, ... }; @ has_open depends on fops0 @ identifier fops0.fops; identifier open_f; @@ struct file_operations fops = { ... .open = open_f, ... }; // use no_llseek if we call nonseekable_open //////////////////////////////////////////// @ nonseekable1 depends on !has_llseek && has_open @ identifier fops0.fops; identifier nso ~= "nonseekable_open"; @@ struct file_operations fops = { ... .open = nso, ... +.llseek = no_llseek, /* nonseekable */ }; @ nonseekable2 depends on !has_llseek @ identifier fops0.fops; identifier open.open_f; @@ struct file_operations fops = { ... .open = open_f, ... +.llseek = no_llseek, /* open uses nonseekable */ }; // use seq_lseek for sequential files ///////////////////////////////////// @ seq depends on !has_llseek @ identifier fops0.fops; identifier sr ~= "seq_read"; @@ struct file_operations fops = { ... .read = sr, ... +.llseek = seq_lseek, /* we have seq_read */ }; // use default_llseek if there is a readdir /////////////////////////////////////////// @ fops1 depends on !has_llseek && !nonseekable1 && !nonseekable2 && !seq @ identifier fops0.fops; identifier readdir_e; @@ // any other fop is used that changes pos struct file_operations fops = { ... .readdir = readdir_e, ... +.llseek = default_llseek, /* readdir is present */ }; // use default_llseek if at least one of read/write touches f_pos ///////////////////////////////////////////////////////////////// @ fops2 depends on !fops1 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @ identifier fops0.fops; identifier read.read_f; @@ // read fops use offset struct file_operations fops = { ... .read = read_f, ... +.llseek = default_llseek, /* read accesses f_pos */ }; @ fops3 depends on !fops1 && !fops2 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @ identifier fops0.fops; identifier write.write_f; @@ // write fops use offset struct file_operations fops = { ... .write = write_f, ... + .llseek = default_llseek, /* write accesses f_pos */ }; // Use noop_llseek if neither read nor write accesses f_pos /////////////////////////////////////////////////////////// @ fops4 depends on !fops1 && !fops2 && !fops3 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @ identifier fops0.fops; identifier read_no_fpos.read_f; identifier write_no_fpos.write_f; @@ // write fops use offset struct file_operations fops = { ... .write = write_f, .read = read_f, ... +.llseek = noop_llseek, /* read and write both use no f_pos */ }; @ depends on has_write && !has_read && !fops1 && !fops2 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @ identifier fops0.fops; identifier write_no_fpos.write_f; @@ struct file_operations fops = { ... .write = write_f, ... +.llseek = noop_llseek, /* write uses no f_pos */ }; @ depends on has_read && !has_write && !fops1 && !fops2 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @ identifier fops0.fops; identifier read_no_fpos.read_f; @@ struct file_operations fops = { ... .read = read_f, ... +.llseek = noop_llseek, /* read uses no f_pos */ }; @ depends on !has_read && !has_write && !fops1 && !fops2 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @ identifier fops0.fops; @@ struct file_operations fops = { ... +.llseek = noop_llseek, /* no read or write fn */ }; ===== End semantic patch ===== Signed-off-by: Arnd Bergmann <arnd@arndb.de> Cc: Julia Lawall <julia@diku.dk> Cc: Christoph Hellwig <hch@infradead.org>
2010-08-15 18:52:59 +02:00
.llseek = noop_llseek,
};
static struct miscdevice vmwdt_dev = {
.minor = WATCHDOG_MINOR,
.name = "watchdog",
.fops = &vmwdt_fops,
};
static int __init vmwdt_init(void)
{
int ret;
ret = vmwdt_probe();
if (ret)
return ret;
ret = register_pm_notifier(&vmwdt_power_notifier);
if (ret)
return ret;
/*
* misc_register() has to be the last action in module_init(), because
* file operations will be available right after this.
*/
ret = misc_register(&vmwdt_dev);
if (ret) {
unregister_pm_notifier(&vmwdt_power_notifier);
return ret;
}
return 0;
}
module_init(vmwdt_init);
static void __exit vmwdt_exit(void)
{
unregister_pm_notifier(&vmwdt_power_notifier);
misc_deregister(&vmwdt_dev);
}
module_exit(vmwdt_exit);