I finally got around to testing the updated wakeup event hooks for rtc-cmos,
and they follow in two patches:

 - Interface update ... when a simple enable_irq_wake() doesn't suffice,
   the platform data can hold suspend/resume callback hooks.

 - ACPI implementation ... provides callback hooks to do ACPI magic, and
   eliminate the legacy /proc/acpi/alarm file.

The interface update could go into 2.6.21, but that's not essential; they
will be NOPs on most PCs, without the ACPI stuff.

I suspect the ACPI folk may have opinions about how to merge that second
patch, and how to obsolete that legacy procfs file.  I'd like to see that
merge into 2.6.22 if possible...

As for how to kick it in ... two ways:

 - The appended "rtcwake" program; updated since the last time it was
   posted, it deals much better with timezones and DST.

 - Write the /sys/class/rtc/.../wakealarm file, then go to sleep.

For some reason RTC wake from "swsusp" stopped working on a system where
it previously worked; the alarm setting appears to get clobbered.  But
on the bright side, RTC wake from "standby" worked on a system that had
never been able to resume from that state before ... IDEACPI is my guess
as to why it finally started to work.  It's the old "two steps forward,
one step back" dance, I guess.

- Dave

/* gcc -Wall -Os -o rtcwake rtcwake.c */

#include <stdio.h>
#include <getopt.h>
#include <fcntl.h>
#include <stdlib.h>
#include <string.h>
#include <unistd.h>
#include <errno.h>
#include <time.h>

#include <sys/ioctl.h>
#include <sys/time.h>
#include <sys/types.h>

#include <linux/rtc.h>

/* constants from legacy PC/AT hardware */
#define	RTC_PF	0x40
#define	RTC_AF	0x20
#define	RTC_UF	0x10

/*
 * rtcwake -- enter a system sleep state until specified wakeup time.
 *
 * This uses cross-platform Linux interfaces to enter a system sleep state,
 * and leave it no later than a specified time.  It uses any RTC framework
 * driver that supports standard driver model wakeup flags.
 *
 * This is normally used like the old "apmsleep" utility, to wake from a
 * suspend state like ACPI S1 (standby) or S3 (suspend-to-RAM).  Most
 * platforms can implement those without analogues of BIOS, APM, or ACPI.
 *
 * On some systems, this can also be used like "nvram-wakeup", waking
 * from states like ACPI S4 (suspend to disk).  Not all systems have
 * persistent media that are appropriate for such suspend modes.
 *
 * The best way to set the system's RTC is so that it holds the current
 * time in UTC.  Use the "-l" flag to tell this program that the system
 * RTC uses a local timezone instead (maybe you dual-boot MS-Windows).
 */

static char		*progname;

#ifdef	DEBUG
#define	VERSION	"1.0 dev (" __DATE__ " " __TIME__ ")"
#else
#define	VERSION	"0.9"
#endif

static unsigned		verbose;
static int		rtc_is_utc = -1;

static int may_wakeup(const char *devname)
{
	char	buf[128], *s;
	FILE	*f;

	snprintf(buf, sizeof buf, "/sys/class/rtc/%s/device/power/wakeup",
			devname);
	f = fopen(buf, "r");
	if (!f) {
		perror(buf);
		return 0;
	}
	fgets(buf, sizeof buf, f);
	fclose(f);

	s = strchr(buf, '\n');
	if (!s)
		return 0;
	*s = 0;

	/* wakeup events could be disabled or not supported */
	return strcmp(buf, "enabled") == 0;
}

/* all times should be in UTC */
static time_t	sys_time;
static time_t	rtc_time;

static int get_basetimes(int fd)
{
	struct tm	tm;
	struct rtc_time	rtc;

	/* this process works in RTC time, except when working
	 * with the system clock (which always uses UTC).
	 */
	if (rtc_is_utc)
		setenv("TZ", "UTC", 1);
	tzset();

	/* read rtc and system clocks "at the same time", or as
	 * precisely (+/- a second) as we can read them.
	 */
	if (ioctl(fd, RTC_RD_TIME, &rtc) < 0) {
		perror("read rtc time");
		return 0;
	}
	sys_time = time(0);
	if (sys_time == (time_t)-1) {
		perror("read system time");
		return 0;
	}

	/* convert rtc_time to normal arithmetic-friendly form,
	 * updating tm.tm_wday as used by asctime().
	 */
	memset(&tm, 0, sizeof tm);
	tm.tm_sec = rtc.tm_sec;
	tm.tm_min = rtc.tm_min;
	tm.tm_hour = rtc.tm_hour;
	tm.tm_mday = rtc.tm_mday;
	tm.tm_mon = rtc.tm_mon;
	tm.tm_year = rtc.tm_year;
	tm.tm_isdst = rtc.tm_isdst;	/* stays unspecified? */
	rtc_time = mktime(&tm);

	if (rtc_time == (time_t)-1) {
		perror("convert rtc time");
		return 0;
	}

	if (verbose) {
		if (!rtc_is_utc) {
			printf("\ttzone   = %ld\n", timezone);
			printf("\ttzname  = %s\n", tzname[daylight]);
			gmtime_r(&rtc_time, &tm);
		}
		printf("\tsystime = %ld, (UTC) %s",
				(long) sys_time, asctime(gmtime(&sys_time)));
		printf("\trtctime = %ld, (UTC) %s",
				(long) rtc_time, asctime(&tm));
	}

	return 1;
}

static int setup_alarm(int fd, time_t *wakeup)
{
	struct tm		*tm;
	struct rtc_wkalrm	wake;

	tm = gmtime(wakeup);

	wake.time.tm_sec = tm->tm_sec;
	wake.time.tm_min = tm->tm_min;
	wake.time.tm_hour = tm->tm_hour;
	wake.time.tm_mday = tm->tm_mday;
	wake.time.tm_mon = tm->tm_mon;
	wake.time.tm_year = tm->tm_year;
	wake.time.tm_wday = tm->tm_wday;
	wake.time.tm_yday = tm->tm_yday;
	wake.time.tm_isdst = tm->tm_isdst;

	/* many rtc alarms only support up to 24 hours from 'now' ... */
	if ((rtc_time + (24 * 60 * 60)) > *wakeup) {
		if (ioctl(fd, RTC_ALM_SET, &wake.time) < 0) {
			perror("set rtc alarm");
			return 0;
		}
		if (ioctl(fd, RTC_AIE_ON, 0) < 0) {
			perror("enable rtc alarm");
			return 0;
		}

	/* ... so use the "more than 24 hours" request only if we must */
	} else {
		/* avoid an extra AIE_ON call */
		wake.enabled = 1;

		if (ioctl(fd, RTC_WKALM_SET, &wake) < 0) {
			perror("set rtc wake alarm");
			return 0;
		}
	}

	return 1;
}

static void suspend_system(const char *suspend)
{
	FILE	*f = fopen("/sys/power/state", "w");

	if (!f) {
		perror("/sys/power/state");
		return;
	}

	fprintf(f, "%s\n", suspend);
	fflush(f);

	/* this executes after wake from suspend */
	fclose(f);
}

int main(int argc, char **argv)
{
	static char		*devname = "rtc0";
	static unsigned		seconds = 0;
	static char		*suspend = "standby";

	int		t;
	int		fd;
	time_t		alarm = 0;

	progname = strrchr(argv[0], '/');
	if (progname)
		progname++;
	else
		progname = argv[0];
	if (chdir("/dev/") < 0) {
		perror("chdir /dev");
		return 1;
	}

	while ((t = getopt(argc, argv, "d:lm:s:t:uVv")) != EOF) {
		switch (t) {

		case 'd':
			devname = optarg;
			break;

		case 'l':
			rtc_is_utc = 0;
			break;

		/* what system power mode to use?  for now handle only
		 * standardized mode names; eventually when systems define
		 * their own state names, parse /sys/power/state.
		 *
		 * "on" is used just to test the RTC alarm mechanism,
		 * bypassing all the wakeup-from-sleep infrastructure.
		 */
		case 'm':
			if (strcmp(optarg, "standby") == 0
					|| strcmp(optarg, "mem") == 0
					|| strcmp(optarg, "disk") == 0
					|| strcmp(optarg, "on") == 0
					) {
				suspend = optarg;
				break;
			}
			printf("%s: unrecognized suspend state '%s'\n",
					progname, optarg);
			goto usage;

		/* alarm time, seconds-to-sleep (relative) */
		case 's':
			t = atoi(optarg);
			if (t < 0) {
				printf("%s: illegal interval %s seconds\n",
						progname, optarg);
				goto usage;
			}
			seconds = t;
			break;

		/* alarm time, time_t (absolute, seconds since 1/1 1970 UTC) */
		case 't':
			t = atoi(optarg);
			if (t < 0) {
				printf("%s: illegal time_t value %s\n",
						progname, optarg);
				goto usage;
			}
			alarm = t;
			break;

		case 'u':
			rtc_is_utc = 1;
			break;

		case 'v':
			verbose++;
			break;

		case 'V':
			printf("%s: version %s\n", progname, VERSION);
			break;

		default:
usage:
			printf("usage: %s [options]"
				"\n\t"
				"-d rtc0|rtc1|...\t(select rtc)"
				"\n\t"
				"-l\t\t\t(RTC uses local timezone)"
				"\n\t"
				"-m standby|mem|...\t(sleep mode)"
				"\n\t"
				"-s seconds\t\t(seconds to sleep)"
				"\n\t"
				"-t time_t\t\t(time to wake)"
				"\n\t"
				"-u\t\t\t(RTC uses UTC)"
				"\n\t"
				"-v\t\t\t(verbose messages)"
				"\n\t"
				"-V\t\t\t(show version)"
				"\n",
				progname);
			return 1;
		}
	}

	if (!alarm && !seconds) {
		printf("%s: must provide wake time\n", progname);
		goto usage;
	}

	/* REVISIT:  if /etc/adjtime exists, read it to see what
	 * the util-linux version of hwclock assumes.
	 */
	if (rtc_is_utc == -1) {
		printf("%s: assuming RTC uses UTC ...\n", progname);
		rtc_is_utc = 1;
	}

	/* this RTC must exist and (if we'll sleep) be wakeup-enabled */
	fd = open(devname, O_RDONLY);
	if (fd < 0) {
		perror(devname);
		return 1;
	}
	if (strcmp(suspend, "on") != 0 && !may_wakeup(devname)) {
		printf("%s: %s not enabled for wakeup events\n",
				progname, devname);
		return 1;
	}

	/* relative or absolute alarm time, normalized to time_t */
	if (!get_basetimes(fd))
		return 1;
	if (verbose)
		printf("alarm %ld, sys_time %ld, rtc_time %ld, seconds %u\n",
				alarm, sys_time, rtc_time, seconds);
	if (alarm) {
		if (alarm < sys_time) {
			printf("%s: time doesn't go backward to %s",
					progname, ctime(&alarm));
			return 1;
		}
		alarm += sys_time - rtc_time;
	} else
		alarm = rtc_time + seconds + 1;
	if (setup_alarm(fd, &alarm) < 0)
		return 1;

	sync();
	printf("%s: wakeup from \"%s\" using %s at %s",
			progname, suspend, devname,
			ctime(&alarm));
	fflush(stdout);
	usleep(10 * 1000);

	if (strcmp(suspend, "on") != 0)
		suspend_system(suspend);
	else {
		unsigned long data;

		do {
			t = read(fd, &data, sizeof data);
			if (t < 0) {
				perror("rtc read");
				break;
			}
			if (verbose)
				printf("... %s: %03lx\n", devname, data);
		} while (!(data & RTC_AF));
	}

	if (ioctl(fd, RTC_AIE_OFF, 0) < 0)
		perror("disable rtc alarm interrupt");

	close(fd);
	return 0;
}

This patch:

Make rtc-cmos do the relevant magic so this RTC can wake the system from a
sleep state.  That magic comes in two basic flavors:

 - Straightforward:  enable_irq_wake(), the way it'd work on most SOC chips;
   or generally with system sleep states which don't disable core IRQ logic.

 - Roundabout, using non-IRQ platform hooks.  This is needed with ACPI and
   one almost-clone chip which uses a special wakeup-only alarm.  (That's
   the RTC used on Footbridge boards, FWIW, which don't do PM in Linux.)

A separate patch implements those hooks for ACPI platforms, so that rtc_cmos
can issue system wakeup events (and its sysfs "wakealarm" attribute works on
at least some systems).
Signed-off-by: NDavid Brownell <dbrownell@users.sourceforge.net>
Cc: Alessandro Zummo <a.zummo@towertech.it>
Cc: Len Brown <lenb@kernel.org>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

- vr41xx_rtc_read_alarm() reports alarm enabled.
- vr41xx_rtc_set_alarm() sets alarm disable/enable by rtc_wkalrm.enabled.
Signed-off-by: NYoichi Yuasa <yoichi_yuasa@tripeaks.co.jp>
Acked-by: NAlessandro Zummo <a.zummo@towertech.it>
Acked-by: NDavid Brownell <dbrownell@users.sourceforge.net>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Signed-off-by: NAlessandro Zummo <a.zummo@towertech.it>
Cc: David Brownell <david-b@pacbell.net>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Fix a goof in the revised classdev support for RTCs: make sure the /dev
node info is ready before the device is registered, not after.  Otherwise
the /sys/class/rtc/rtcN/dev attribute won't be created and then udev won't
have the information it needs to create the /dev/rtcN node.
Signed-off-by: NDavid Brownell <dbrownell@users.sourceforge.net>
Cc: Alessandro Zummo <a.zummo@towertech.it>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Signed-off-by: NDavid Brownell <dbrownell@users.sourceforge.net>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

RTC class suspend/resume support, re-initializing the system clock on resume
from the clock used to initialize it at boot time.

 - The reinit-on-resume is hooked to the existing RTC_HCTOSYS config
   option, on the grounds that a clock good enough for init must also
   be good enough for re-init.

 - Inlining a version of the code used by ARM, to save and restore the
   delta between a selected RTC and the current system wall-clock time.

 - Removes calls to that ARM code from AT91, OMAP1, and S3C RTCs.  This
   means that systems using those RTCs across suspend/resume will likely
   want to change their kernel configs to enable RTC_HCTOSYS.

   If HCTOSYS isn't using a second RTC (with battery?), this changes the
   system's initial date from Jan 1970 to the epoch this hardware uses:
   1998 for AT91, 2000 for OMAP1 (assuming no split power mode), etc.

This goes on top of the patch series removing "struct class_device" usage
from the RTC framework.  That's all needed for class suspend()/resume().
Signed-off-by: NDavid Brownell <dbrownell@users.sourceforge.net>
Acked-by: NGreg Kroah-Hartman <gregkh@suse.de>
Acked-By: NAlessandro Zummo <a.zummo@towertech.it>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Finish converting the RTC framework so it no longer uses class_device.
Signed-off-by: NDavid Brownell <dbrownell@users.sourceforge.net>
Acked-by: NGreg Kroah-Hartman <gregkh@suse.de>
Acked-By: NAlessandro Zummo <a.zummo@towertech.it>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

This simplifies the RTC procfs support by removing the class_interface that
hooks it into the rtc core.  If it's configured, then sysfs support is now
part of the RTC core, and is never a separate module.

It also removes the class_interface hook, now that its last remaining user is
gone.  (That API is usable only with a "struct class_device".)

It's another step towards being able to remove "struct class_device".
Signed-off-by: NDavid Brownell <dbrownell@users.sourceforge.net>
Acked-by: NGreg Kroah-Hartman <gregkh@suse.de>
Acked-By: NAlessandro Zummo <a.zummo@towertech.it>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

This simplifies the RTC sysfs support by removing the class_interface that
hooks it into the rtc core.  If it's configured, then sysfs support is now
part of the RTC core, and is never a separate module.

It's another step towards being able to remove "struct class_device".
Signed-off-by: NDavid Brownell <dbrownell@users.sourceforge.net>
Acked-by: NGreg Kroah-Hartman <gregkh@suse.de>
Acked-By: NAlessandro Zummo <a.zummo@towertech.it>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

This patch removes class_device from the programming interface that the RTC
framework exposes to the rest of the kernel.  Now an rtc_device is passed,
which is more type-safe and streamlines all the relevant code.
Signed-off-by: NDavid Brownell <dbrownell@users.sourceforge.net>
Acked-by: NGreg Kroah-Hartman <gregkh@suse.de>
Acked-By: NAlessandro Zummo <a.zummo@towertech.it>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

This simplifies the /dev support by removing a superfluous class_device (the
/sys/class/rtc-dev stuff) and the class_interface that hooks it into the rtc
core.  Accordingly, if it's configured then /dev support is now part of the
RTC core, and is never a separate module.

It's another step towards being able to remove "struct class_device".

[bunk@stusta.de: drivers/rtc/rtc-dev.c should #include "rtc-core.h"]
Signed-off-by: NDavid Brownell <dbrownell@users.sourceforge.net>
Acked-by: NGreg Kroah-Hartman <gregkh@suse.de>
Acked-By: NAlessandro Zummo <a.zummo@towertech.it>
Signed-off-by: NAdrian Bunk <bunk@stusta.de>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Implement utimensat(2) which is an extension to futimesat(2) in that it

a) supports nano-second resolution for the timestamps
b) allows to selectively ignore the atime/mtime value
c) allows to selectively use the current time for either atime or mtime
d) supports changing the atime/mtime of a symlink itself along the lines
   of the BSD lutimes(3) functions

For this change the internally used do_utimes() functions was changed to
accept a timespec time value and an additional flags parameter.

Additionally the sys_utime function was changed to match compat_sys_utime
which already use do_utimes instead of duplicating the work.

Also, the completely missing futimensat() functionality is added.  We have
such a function in glibc but we have to resort to using /proc/self/fd/* which
not everybody likes (chroot etc).

Test application (the syscall number will need per-arch editing):

#include <errno.h>
#include <fcntl.h>
#include <time.h>
#include <sys/time.h>
#include <stddef.h>
#include <syscall.h>

#define __NR_utimensat 280

#define UTIME_NOW       ((1l << 30) - 1l)
#define UTIME_OMIT      ((1l << 30) - 2l)

int
main(void)
{
  int status = 0;

  int fd = open("ttt", O_RDWR|O_CREAT|O_EXCL, 0666);
  if (fd == -1)
    error (1, errno, "failed to create test file \"ttt\"");

  struct stat64 st1;
  if (fstat64 (fd, &st1) != 0)
    error (1, errno, "fstat failed");

  struct timespec t[2];
  t[0].tv_sec = 0;
  t[0].tv_nsec = 0;
  t[1].tv_sec = 0;
  t[1].tv_nsec = 0;
  if (syscall(__NR_utimensat, AT_FDCWD, "ttt", t, 0) != 0)
    error (1, errno, "utimensat failed");

  struct stat64 st2;
  if (fstat64 (fd, &st2) != 0)
    error (1, errno, "fstat failed");

  if (st2.st_atim.tv_sec != 0 || st2.st_atim.tv_nsec != 0)
    {
      puts ("atim not reset to zero");
      status = 1;
    }
  if (st2.st_mtim.tv_sec != 0 || st2.st_mtim.tv_nsec != 0)
    {
      puts ("mtim not reset to zero");
      status = 1;
    }
  if (status != 0)
    goto out;

  t[0] = st1.st_atim;
  t[1].tv_sec = 0;
  t[1].tv_nsec = UTIME_OMIT;
  if (syscall(__NR_utimensat, AT_FDCWD, "ttt", t, 0) != 0)
    error (1, errno, "utimensat failed");

  if (fstat64 (fd, &st2) != 0)
    error (1, errno, "fstat failed");

  if (st2.st_atim.tv_sec != st1.st_atim.tv_sec
      || st2.st_atim.tv_nsec != st1.st_atim.tv_nsec)
    {
      puts ("atim not set");
      status = 1;
    }
  if (st2.st_mtim.tv_sec != 0 || st2.st_mtim.tv_nsec != 0)
    {
      puts ("mtim changed from zero");
      status = 1;
    }
  if (status != 0)
    goto out;

  t[0].tv_sec = 0;
  t[0].tv_nsec = UTIME_OMIT;
  t[1] = st1.st_mtim;
  if (syscall(__NR_utimensat, AT_FDCWD, "ttt", t, 0) != 0)
    error (1, errno, "utimensat failed");

  if (fstat64 (fd, &st2) != 0)
    error (1, errno, "fstat failed");

  if (st2.st_atim.tv_sec != st1.st_atim.tv_sec
      || st2.st_atim.tv_nsec != st1.st_atim.tv_nsec)
    {
      puts ("mtim changed from original time");
      status = 1;
    }
  if (st2.st_mtim.tv_sec != st1.st_mtim.tv_sec
      || st2.st_mtim.tv_nsec != st1.st_mtim.tv_nsec)
    {
      puts ("mtim not set");
      status = 1;
    }
  if (status != 0)
    goto out;

  sleep (2);

  t[0].tv_sec = 0;
  t[0].tv_nsec = UTIME_NOW;
  t[1].tv_sec = 0;
  t[1].tv_nsec = UTIME_NOW;
  if (syscall(__NR_utimensat, AT_FDCWD, "ttt", t, 0) != 0)
    error (1, errno, "utimensat failed");

  if (fstat64 (fd, &st2) != 0)
    error (1, errno, "fstat failed");

  struct timeval tv;
  gettimeofday(&tv,NULL);

  if (st2.st_atim.tv_sec <= st1.st_atim.tv_sec
      || st2.st_atim.tv_sec > tv.tv_sec)
    {
      puts ("atim not set to NOW");
      status = 1;
    }
  if (st2.st_mtim.tv_sec <= st1.st_mtim.tv_sec
      || st2.st_mtim.tv_sec > tv.tv_sec)
    {
      puts ("mtim not set to NOW");
      status = 1;
    }

  if (symlink ("ttt", "tttsym") != 0)
    error (1, errno, "cannot create symlink");

  t[0].tv_sec = 0;
  t[0].tv_nsec = 0;
  t[1].tv_sec = 0;
  t[1].tv_nsec = 0;
  if (syscall(__NR_utimensat, AT_FDCWD, "tttsym", t, AT_SYMLINK_NOFOLLOW) != 0)
    error (1, errno, "utimensat failed");

  if (lstat64 ("tttsym", &st2) != 0)
    error (1, errno, "lstat failed");

  if (st2.st_atim.tv_sec != 0 || st2.st_atim.tv_nsec != 0)
    {
      puts ("symlink atim not reset to zero");
      status = 1;
    }
  if (st2.st_mtim.tv_sec != 0 || st2.st_mtim.tv_nsec != 0)
    {
      puts ("symlink mtim not reset to zero");
      status = 1;
    }
  if (status != 0)
    goto out;

  t[0].tv_sec = 1;
  t[0].tv_nsec = 0;
  t[1].tv_sec = 1;
  t[1].tv_nsec = 0;
  if (syscall(__NR_utimensat, fd, NULL, t, 0) != 0)
    error (1, errno, "utimensat failed");

  if (fstat64 (fd, &st2) != 0)
    error (1, errno, "fstat failed");

  if (st2.st_atim.tv_sec != 1 || st2.st_atim.tv_nsec != 0)
    {
      puts ("atim not reset to one");
      status = 1;
    }
  if (st2.st_mtim.tv_sec != 1 || st2.st_mtim.tv_nsec != 0)
    {
      puts ("mtim not reset to one");
      status = 1;
    }

  if (status == 0)
     puts ("all OK");

 out:
  close (fd);
  unlink ("ttt");
  unlink ("tttsym");

  return status;
}

[akpm@linux-foundation.org: add missing i386 syscall table entry]
Signed-off-by: NUlrich Drepper <drepper@redhat.com>
Cc: Alexey Dobriyan <adobriyan@openvz.org>
Cc: Michael Kerrisk <mtk-manpages@gmx.net>
Cc: <linux-arch@vger.kernel.org>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

The for loop in rcutorture_init uses the condition
cur_ops = torture_ops[i], cur_ops
but then makes the same assignment to cur_ops inside the loop.  Remove the
redundant assignment inside the loop, and remove now-unnecessary braces.
Signed-off-by: NJosh Triplett <josh@kernel.org>
Cc: "Paul E. McKenney" <paulmck@us.ibm.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Signed-off-by: NJosh Triplett <josh@kernel.org>
Cc: "Paul E. McKenney" <paulmck@us.ibm.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Use ARRAY_SIZE macro already defined in kernel.h
Signed-off-by: NAhmed S. Darwish <darwish.07@gmail.com>
Cc: "Paul E. McKenney" <paulmck@us.ibm.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Align the per cpu runqueue to the cacheline boundary.  This will minimize
the number of cachelines touched during remote wakeup.
Signed-off-by: NSuresh Siddha <suresh.b.siddha@intel.com>
Acked-by: NIngo Molnar <mingo@elte.hu>
Cc: Ravikiran G Thirumalai <kiran@scalex86.org>
Cc: Nick Piggin <nickpiggin@yahoo.com.au>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

- Make TASK_PREEMPTS_CURR(task, rq) return "true" only if the task's prio
  is higher than the current's one and the task is in the "active" array.
  This ensures we don't make redundant resched_task() calls when the task
  is in the "expired" array (as may happen now in set_user_prio(),
  rt_mutex_setprio() and pull_task() ) ;

- generalise conditions for a call to resched_task() in set_user_nice(),
  rt_mutex_setprio() and sched_setscheduler()
Signed-off-by: NDmitry Adamushko <dmitry.adamushko@gmail.com>
Cc: Con Kolivas <kernel@kolivas.org>
Acked-by: NIngo Molnar <mingo@elte.hu>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

When a logical cpu 'x' already has more than one process running, then most
likely the siblings of that cpu 'x' must be busy.  Otherwise the idle
siblings would have likely(in most of the scenarios) picked up the extra
load making the load on 'x' atmost one.

Use this logic to eliminate the siblings status check and minimize the cache
misses encountered on a heavily loaded system.
Signed-off-by: NSuresh Siddha <suresh.b.siddha@intel.com>
Cc: Nick Piggin <nickpiggin@yahoo.com.au>
Acked-by: NIngo Molnar <mingo@elte.hu>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

I noticed expensive divides done in try_to_wakeup() and
find_busiest_group() on a bi dual core Opteron machine (total of 4 cores),
moderatly loaded (15.000 context switch per second)

oprofile numbers :

CPU: AMD64 processors, speed 2600.05 MHz (estimated)
Counted CPU_CLK_UNHALTED events (Cycles outside of halt state) with a unit
mask of 0x00 (No unit mask) count 50000
samples  %        symbol name
...
613914    1.0498  try_to_wake_up
    834  0.0013 :ffffffff80227ae1:   div    %rcx
77513  0.1191 :ffffffff80227ae4:   mov    %rax,%r11

608893    1.0413  find_busiest_group
   1841  0.0031 :ffffffff802260bf:       div    %rdi
140109  0.2394 :ffffffff802260c2:       test   %sil,%sil

Some of these divides can use the reciprocal divides we introduced some
time ago (currently used in slab AFAIK)

We can assume a load will fit in a 32bits number, because with a
SCHED_LOAD_SCALE=128 value, its still a theorical limit of 33554432

When/if we reach this limit one day, probably cpus will have a fast
hardware divide and we can zap the reciprocal divide trick.

Ingo suggested to rename cpu_power to __cpu_power to make clear it should
not be modified without changing its reciprocal value too.

I did not convert the divide in cpu_avg_load_per_task(), because tracking
nr_running changes may be not worth it ?  We could use a static table of 32
reciprocal values but it would add a conditional branch and table lookup.

[akpm@linux-foundation.org: !SMP build fix]
Signed-off-by: NEric Dumazet <dada1@cosmosbay.com>
Acked-by: NIngo Molnar <mingo@elte.hu>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Fix the process idle load balancing in the presence of dynticks.  cpus for
which ticks are stopped will sleep till the next event wakes it up.
Potentially these sleeps can be for large durations and during which today,
there is no periodic idle load balancing being done.

This patch nominates an owner among the idle cpus, which does the idle load
balancing on behalf of the other idle cpus.  And once all the cpus are
completely idle, then we can stop this idle load balancing too.  Checks added
in fast path are minimized.  Whenever there are busy cpus in the system, there
will be an owner(idle cpu) doing the system wide idle load balancing.

Open items:
1. Intelligent owner selection (like an idle core in a busy package).
2. Merge with rcu's nohz_cpu_mask?
Signed-off-by: NSuresh Siddha <suresh.b.siddha@intel.com>
Acked-by: NIngo Molnar <mingo@elte.hu>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Nick Piggin <nickpiggin@yahoo.com.au>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Periodic load balancing in recent kernels happen in the softirq.  In
certain -rt configurations, these softirqs are handled in softirqd context.
 And hence the check for idle processor was always returning busy (as
nr_running > 1).

This patch captures the idle information at the tick and passes this info
to softirq context through an element 'idle_at_tick' in rq.

[kernel@kolivas.org: Fix reverse idle at tick logic]
Signed-off-by: NSuresh Siddha <suresh.b.siddha@intel.com>
Acked-by: NIngo Molnar <mingo@elte.hu>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Nick Piggin <nickpiggin@yahoo.com.au>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Signed-off-by: NThomas Gleixner <tglx@linutronix.de>
Cc: Karsten Keil <kkeil@suse.de>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

The CAPI 2.0 interface uses a semaphore as mutex.  Use the mutex API instead
of the (binary) semaphore.
Signed-off-by: NMatthias Kaehlcke <matthias.kaehlcke@gmail.com>
Cc: Karsten Keil <kkeil@suse.de>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

the isdn_divertif contains kernel-only references so I've wrapped them in
__KERNEL__ and add proper #include statements.
Signed-off-by: NMike Frysinger <vapier@gentoo.org>
Cc: Karsten Keil <kkeil@suse.de>
Cc: David Woodhouse <dwmw2@infradead.org>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Fix incorrect spinlock use in hysdn_log_close().  The function declared a
spinlock on the stack and used it to 'protect' a shared driver structure.

The patch simply removes the useless code.
Signed-off-by: NMatthias Kaehlcke <matthias.kaehlcke@gmail.com>
Cc: Karsten Keil <kkeil@suse.de>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

As pointed out by Robert P.  J.  Day, here is a patch to remove unused
header files from Eicon/Dialogic ISDN driver.
Signed-off-by: NArmin Schindler <armin@melware.de>
Acked-by: NKarsten Keil <kkeil@suse.de>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Signed-off-by: NAdrian Bunk <bunk@stusta.de>
Acked-by: NKarsten Keil <kkeil@suse.de>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

This patch makes it so that simple_fill_super and get_sb_pseudo assign their
root inodes to be number 1.  It also fixes up a couple of callers of
simple_fill_super that were passing in files arrays that had an index at
number 1, and adds a warning for any caller that sends in such an array.

It would have been nice to have made it so that it wasn't possible to make
such a collision, but some callers need to be able to control what inode
number their entries get, so I think this is the best that can be done.
Signed-off-by: NJeff Layton <jlayton@redhat.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

The problems are:

- on filesystems w/o permanent inode numbers, i_ino values can be larger
  than 32 bits, which can cause problems for some 32 bit userspace programs on
  a 64 bit kernel.  We can't do anything for filesystems that have actual
  >32-bit inode numbers, but on filesystems that generate i_ino values on the
  fly, we should try to have them fit in 32 bits.  We could trivially fix this
  by making the static counters in new_inode and iunique 32 bits, but...

- many filesystems call new_inode and assume that the i_ino values they are
  given are unique.  They are not guaranteed to be so, since the static
  counter can wrap.  This problem is exacerbated by the fix for #1.

- after allocating a new inode, some filesystems call iunique to try to get
  a unique i_ino value, but they don't actually add their inodes to the
  hashtable, and so they're still not guaranteed to be unique if that counter
  wraps.

This patch set takes the simpler approach of simply using iunique and hashing
the inodes afterward.  Christoph H.  previously mentioned that he thought that
this approach may slow down lookups for filesystems that currently hash their
inodes.

The questions are:

1) how much would this slow down lookups for these filesystems?
2) is it enough to justify adding more infrastructure to avoid it?

What might be best is to start with this approach and then only move to using
IDR or some other scheme if these extra inodes in the hashtable prove to be
problematic.

I've done some cursory testing with this patch and the overhead of hashing and
unhashing the inodes with pipefs is pretty low -- just a few seconds of system
time added on to the creation and destruction of 10 million pipes (very
similar to the overhead that the IDR approach would add).

The hard thing to measure is what effect this has on other filesystems. I'm
open to ways to try and gauge this.

Again, I've only converted pipefs as an example. If this approach is
acceptable then I'll start work on patches to convert other filesystems.

With a pretty-much-worst-case microbenchmark provided by Eric Dumazet
<dada1@cosmosbay.com>:

hashing patch (pipebench):
sys     1m15.329s
sys     1m16.249s
sys     1m17.169s

unpatched (pipebench):
sys     1m9.836s
sys     1m12.541s
sys     1m14.153s

Which works out to 1.05642174294555027017.  So ~5-6% slowdown.

This patch:

When a 32-bit program that was not compiled with large file offsets does a
stat and gets a st_ino value back that won't fit in the 32 bit field, glibc
(correctly) generates an EOVERFLOW error.  We can't do anything about fs's
with larger permanent inode numbers, but when we generate them on the fly, we
ought to try and have them fit within a 32 bit field.

This patch takes the first step toward this by making the static counters in
these two functions be 32 bits.

[jlayton@redhat.com: mention that it's only the case for 32bit, non-LFS stat]
Signed-off-by: NJeff Layton <jlayton@redhat.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Here is a driver for the Alchemy au1550 PSC (Programmable Serial
Controller) in SPI master mode.

It supports dma transfers using the Alchemy descriptor based dma controller
for 4-8 bits per word SPI transfers.  For 9-24 bits per word transfers, pio
irq based mode is used to avoid setup of dma channels from scratch on each
number of bits per word change.

Tested with au1550; this may also work on other MIPS Alchemy cpus, like
au1200/au1210/au1250.  Used extensively with SD card connected via SPI;
this handles 8.1MHz SPI clock transfers using dma without any problem (the
highest SPI clock freq possible with au1550 running on 324MHz).

The driver supports sharing of SPI bus by multiple devices.  All features
of Alchemy SPI mode are supported (all SPI modes, msb/lsb first, bits per
word in 4-24 range).

As the SPI clock of the controller depends on main input clock that shall
be configured externally, platform data structure for au1550 SPI controller
driver contains mainclk_hz attribute to define the input clock rate.  From
this value, dividers of the controller for SPI clock are set up for
required frequency.
Signed-off-by: NJan Nikitenko <jan.nikitenko@gmail.com>

Whitespace and section fixups.  Remove partial workaround for platform
setup bug in dma_mask setup; it couldn't work with multiple controllers.
Signed-off-by: NDavid Brownell <dbrownell@users.sourceforge.net>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Various documentation updates for the SPI infrastructure, to clarify things
that may not have been clear, to cope with lack of editing, and fix
omissions.

Also, plug SPI into the kernel-api DocBook template, and fix all the
resulting glitches in document generation.
Signed-off-by: NDavid Brownell <dbrownell@users.sourceforge.net>
Cc: "Randy.Dunlap" <rdunlap@xenotime.net>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Add a filesystem API for <linux/spi/spi.h> stack.  The initial version of
this interface is purely synchronous.

dbrownell@users.sourceforge.net:

 Cleaned up, bugfixed; much simplified; added preliminary documentation.

 Works with mdev given CONFIG_SYSFS_DEPRECATED; and presumably udev.

 Updated SPI_IOC_MESSAGE ioctl to full spi_message semantics, supporting
 groups of one or more transfers (each of which may be full duplex if
 desired).

 This is marked as EXPERIMENTAL with an explicit disclaimer that the API
 (notably the ioctls) is subject to change.
Signed-off-by: NAndrea Paterniani <a.paterniani@swapp-eng.it>
Signed-off-by: NDavid Brownell <dbrownell@users.sourceforge.net>
Cc: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Simplify the spi_butterfly driver by removing incomplete/unused support for
the second SPI bus, implemented by the USI controller.  This should make
this a clearer example of how to write a parport bitbang driver.
Signed-off-by: NDavid Brownell <dbrownell@users.sourceforge.net>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Remove some obviously old interrupt disable/enable code that has been
commented out.
Signed-off-by: NJosh Boyer <jwboyer@gmail.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

The misc character device driver uses a semaphore as mutex.  Use the mutex API
instead of the (binary) semaphore.
Signed-off-by: NMatthias Kaehlcke <matthias.kaehlcke@gmail.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

The hdaps driver uses a semaphore as mutex.  Use the mutex API instead of the
(binary) semaphore.
Signed-off-by: NMatthias Kaehlcke <matthias.kaehlcke@gmail.com>
Cc: Robert Love <rlove@rlove.org>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

The TPM driver uses two semaphores as mutexes.  Use the mutex API instead of
the (binary) semaphores.
Signed-off-by: NMatthias Kaehlcke <matthias.kaehlcke@gmail.com>
Cc: Kylene Hall <kjhall@us.ibm.com>
Cc: Marcel Selhorst <tpm@selhorst.net>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

The RocketPort driver uses a semaphore as mutex.  Use the mutex API instead of
the (binary) semaphore.
Signed-off-by: NMatthias Kaehlcke <matthias.kaehlcke@gmail.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Other symbols of the hrtimers API are already exported.
Signed-off-by: NStas Sergeev <stsp@aknet.ru>
Acked-by: NThomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@elte.hu>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

When elf loader fails to map executable (due to memory shortage or because
binary is malformed), it can return 0.  Normally, this is invisible because
process is killed with SIGKILL and it never returns to user space.

But if exec() is called from kernel thread (hotplug, whatever)
consequences are more interesting and vary depending on architecture.

i386.   Nothing especially interesting, execve() just returns
        with "success"  :-)

x86_64. Fake zero frame is used on way to caller, RSP/RIP are loaded
        with zeros, ergo... double fault.

ia64.   Similar to i386, but r32...r95 are corrupted. Sometimes it
        oopses due to return to zero PC, sometimes it sees NaT in
        rXX and oopses due to NaT consumption.
Signed-off-by: NAlexey Kuznetsov <alexey@openvz.org>
Signed-off-by: NKirill Korotaev <dev@openvz.org>
Signed-off-by: NPavel Emelianov <xemul@openvz.org>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>