linux/kernel/time.c

729 lines
19 KiB
C
Raw Normal View History

/*
* linux/kernel/time.c
*
* Copyright (C) 1991, 1992 Linus Torvalds
*
* This file contains the interface functions for the various
* time related system calls: time, stime, gettimeofday, settimeofday,
* adjtime
*/
/*
* Modification history kernel/time.c
*
* 1993-09-02 Philip Gladstone
* Created file with time related functions from sched.c and adjtimex()
* 1993-10-08 Torsten Duwe
* adjtime interface update and CMOS clock write code
* 1995-08-13 Torsten Duwe
* kernel PLL updated to 1994-12-13 specs (rfc-1589)
* 1999-01-16 Ulrich Windl
* Introduced error checking for many cases in adjtimex().
* Updated NTP code according to technical memorandum Jan '96
* "A Kernel Model for Precision Timekeeping" by Dave Mills
* Allow time_constant larger than MAXTC(6) for NTP v4 (MAXTC == 10)
* (Even though the technical memorandum forbids it)
* 2004-07-14 Christoph Lameter
* Added getnstimeofday to allow the posix timer functions to return
* with nanosecond accuracy
*/
#include <linux/module.h>
#include <linux/timex.h>
#include <linux/capability.h>
#include <linux/clocksource.h>
#include <linux/errno.h>
#include <linux/syscalls.h>
#include <linux/security.h>
#include <linux/fs.h>
#include <linux/slab.h>
#include <linux/math64.h>
Allow times and time system calls to return small negative values At the moment, the times() system call will appear to fail for a period shortly after boot, while the value it want to return is between -4095 and -1. The same thing will also happen for the time() system call on 32-bit platforms some time in 2106 or so. On some platforms, such as x86, this is unavoidable because of the system call ABI, but other platforms such as powerpc have a separate error indication from the return value, so system calls can in fact return small negative values without indicating an error. On those platforms, force_successful_syscall_return() provides a way to indicate that the system call return value should not be treated as an error even if it is in the range which would normally be taken as a negative error number. This adds a force_successful_syscall_return() call to the time() and times() system calls plus their 32-bit compat versions, so that they don't erroneously indicate an error on those platforms whose system call ABI has a separate error indication. This will not affect anything on other platforms. Joakim Tjernlund added the fix for time() and the compat versions of time() and times(), after I did the fix for times(). Signed-off-by: Joakim Tjernlund <Joakim.Tjernlund@transmode.se> Signed-off-by: Paul Mackerras <paulus@samba.org> Acked-by: David S. Miller <davem@davemloft.net> Cc: Ingo Molnar <mingo@elte.hu> Cc: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-01-06 22:41:02 +00:00
#include <linux/ptrace.h>
#include <asm/uaccess.h>
#include <asm/unistd.h>
avoid overflows in kernel/time.c When the conversion factor between jiffies and milli- or microseconds is not a single multiply or divide, as for the case of HZ == 300, we currently do a multiply followed by a divide. The intervening result, however, is subject to overflows, especially since the fraction is not simplified (for HZ == 300, we multiply by 300 and divide by 1000). This is exposed to the user when passing a large timeout to poll(), for example. This patch replaces the multiply-divide with a reciprocal multiplication on 32-bit platforms. When the input is an unsigned long, there is no portable way to do this on 64-bit platforms there is no portable way to do this since it requires a 128-bit intermediate result (which gcc does support on 64-bit platforms but may generate libgcc calls, e.g. on 64-bit s390), but since the output is a 32-bit integer in the cases affected, just simplify the multiply-divide (*3/10 instead of *300/1000). The reciprocal multiply used can have off-by-one errors in the upper half of the valid output range. This could be avoided at the expense of having to deal with a potential 65-bit intermediate result. Since the intent is to avoid overflow problems and most of the other time conversions are only semiexact, the off-by-one errors were considered an acceptable tradeoff. At Ralf Baechle's suggestion, this version uses a Perl script to compute the necessary constants. We already have dependencies on Perl for kernel compiles. This does, however, require the Perl module Math::BigInt, which is included in the standard Perl distribution starting with version 5.8.0. In order to support older versions of Perl, include a table of canned constants in the script itself, and structure the script so that Math::BigInt isn't required if pulling values from said table. Running the script requires that the HZ value is available from the Makefile. Thus, this patch also adds the Kconfig variable CONFIG_HZ to the architectures which didn't already have it (alpha, cris, frv, h8300, m32r, m68k, m68knommu, sparc, v850, and xtensa.) It does *not* touch the sh or sh64 architectures, since Paul Mundt has dealt with those separately in the sh tree. Signed-off-by: H. Peter Anvin <hpa@zytor.com> Cc: Ralf Baechle <ralf@linux-mips.org>, Cc: Sam Ravnborg <sam@ravnborg.org>, Cc: Paul Mundt <lethal@linux-sh.org>, Cc: Richard Henderson <rth@twiddle.net>, Cc: Michael Starvik <starvik@axis.com>, Cc: David Howells <dhowells@redhat.com>, Cc: Yoshinori Sato <ysato@users.sourceforge.jp>, Cc: Hirokazu Takata <takata@linux-m32r.org>, Cc: Geert Uytterhoeven <geert@linux-m68k.org>, Cc: Roman Zippel <zippel@linux-m68k.org>, Cc: William L. Irwin <sparclinux@vger.kernel.org>, Cc: Chris Zankel <chris@zankel.net>, Cc: H. Peter Anvin <hpa@zytor.com>, Cc: Jan Engelhardt <jengelh@computergmbh.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-08 12:21:26 +00:00
#include "timeconst.h"
/*
* The timezone where the local system is located. Used as a default by some
* programs who obtain this value by using gettimeofday.
*/
struct timezone sys_tz;
EXPORT_SYMBOL(sys_tz);
#ifdef __ARCH_WANT_SYS_TIME
/*
* sys_time() can be implemented in user-level using
* sys_gettimeofday(). Is this for backwards compatibility? If so,
* why not move it into the appropriate arch directory (for those
* architectures that need it).
*/
SYSCALL_DEFINE1(time, time_t __user *, tloc)
{
time: introduce xtime_seconds improve performance of sys_time(). sys_time() returns time in seconds, but it does so by calling do_gettimeofday() and then returning the tv_sec portion of the GTOD time. But the data structure "xtime", which is updated by every timer/scheduler tick, already offers HZ granularity time. the patch improves the sysbench oltp macrobenchmark by 4-5% on an AMD dual-core system: v2.6.23: #threads 1: transactions: 4073 (407.23 per sec.) 2: transactions: 8530 (852.81 per sec.) 3: transactions: 8321 (831.88 per sec.) 4: transactions: 8407 (840.58 per sec.) 5: transactions: 8070 (806.74 per sec.) v2.6.23 + sys_time-speedup.patch: 1: transactions: 4281 (428.09 per sec.) 2: transactions: 8910 (890.85 per sec.) 3: transactions: 8659 (865.79 per sec.) 4: transactions: 8676 (867.34 per sec.) 5: transactions: 8532 (852.91 per sec.) and by 4-5% on an Intel dual-core system too: 2.6.23: 1: transactions: 4560 (455.94 per sec.) 2: transactions: 10094 (1009.30 per sec.) 3: transactions: 9755 (975.36 per sec.) 4: transactions: 9859 (985.78 per sec.) 5: transactions: 9701 (969.72 per sec.) 2.6.23 + sys_time-speedup.patch: 1: transactions: 4779 (477.84 per sec.) 2: transactions: 10103 (1010.14 per sec.) 3: transactions: 10141 (1013.93 per sec.) 4: transactions: 10371 (1036.89 per sec.) 5: transactions: 10178 (1017.50 per sec.) (the more CPUs the system has, the more speedup this patch gives for this particular workload.) Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-16 14:09:20 +00:00
time_t i = get_seconds();
if (tloc) {
if (put_user(i,tloc))
Allow times and time system calls to return small negative values At the moment, the times() system call will appear to fail for a period shortly after boot, while the value it want to return is between -4095 and -1. The same thing will also happen for the time() system call on 32-bit platforms some time in 2106 or so. On some platforms, such as x86, this is unavoidable because of the system call ABI, but other platforms such as powerpc have a separate error indication from the return value, so system calls can in fact return small negative values without indicating an error. On those platforms, force_successful_syscall_return() provides a way to indicate that the system call return value should not be treated as an error even if it is in the range which would normally be taken as a negative error number. This adds a force_successful_syscall_return() call to the time() and times() system calls plus their 32-bit compat versions, so that they don't erroneously indicate an error on those platforms whose system call ABI has a separate error indication. This will not affect anything on other platforms. Joakim Tjernlund added the fix for time() and the compat versions of time() and times(), after I did the fix for times(). Signed-off-by: Joakim Tjernlund <Joakim.Tjernlund@transmode.se> Signed-off-by: Paul Mackerras <paulus@samba.org> Acked-by: David S. Miller <davem@davemloft.net> Cc: Ingo Molnar <mingo@elte.hu> Cc: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-01-06 22:41:02 +00:00
return -EFAULT;
}
Allow times and time system calls to return small negative values At the moment, the times() system call will appear to fail for a period shortly after boot, while the value it want to return is between -4095 and -1. The same thing will also happen for the time() system call on 32-bit platforms some time in 2106 or so. On some platforms, such as x86, this is unavoidable because of the system call ABI, but other platforms such as powerpc have a separate error indication from the return value, so system calls can in fact return small negative values without indicating an error. On those platforms, force_successful_syscall_return() provides a way to indicate that the system call return value should not be treated as an error even if it is in the range which would normally be taken as a negative error number. This adds a force_successful_syscall_return() call to the time() and times() system calls plus their 32-bit compat versions, so that they don't erroneously indicate an error on those platforms whose system call ABI has a separate error indication. This will not affect anything on other platforms. Joakim Tjernlund added the fix for time() and the compat versions of time() and times(), after I did the fix for times(). Signed-off-by: Joakim Tjernlund <Joakim.Tjernlund@transmode.se> Signed-off-by: Paul Mackerras <paulus@samba.org> Acked-by: David S. Miller <davem@davemloft.net> Cc: Ingo Molnar <mingo@elte.hu> Cc: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-01-06 22:41:02 +00:00
force_successful_syscall_return();
return i;
}
/*
* sys_stime() can be implemented in user-level using
* sys_settimeofday(). Is this for backwards compatibility? If so,
* why not move it into the appropriate arch directory (for those
* architectures that need it).
*/
SYSCALL_DEFINE1(stime, time_t __user *, tptr)
{
struct timespec tv;
int err;
if (get_user(tv.tv_sec, tptr))
return -EFAULT;
tv.tv_nsec = 0;
err = security_settime(&tv, NULL);
if (err)
return err;
do_settimeofday(&tv);
return 0;
}
#endif /* __ARCH_WANT_SYS_TIME */
SYSCALL_DEFINE2(gettimeofday, struct timeval __user *, tv,
struct timezone __user *, tz)
{
if (likely(tv != NULL)) {
struct timeval ktv;
do_gettimeofday(&ktv);
if (copy_to_user(tv, &ktv, sizeof(ktv)))
return -EFAULT;
}
if (unlikely(tz != NULL)) {
if (copy_to_user(tz, &sys_tz, sizeof(sys_tz)))
return -EFAULT;
}
return 0;
}
/*
* Adjust the time obtained from the CMOS to be UTC time instead of
* local time.
*
* This is ugly, but preferable to the alternatives. Otherwise we
* would either need to write a program to do it in /etc/rc (and risk
* confusion if the program gets run more than once; it would also be
* hard to make the program warp the clock precisely n hours) or
* compile in the timezone information into the kernel. Bad, bad....
*
avoid overflows in kernel/time.c When the conversion factor between jiffies and milli- or microseconds is not a single multiply or divide, as for the case of HZ == 300, we currently do a multiply followed by a divide. The intervening result, however, is subject to overflows, especially since the fraction is not simplified (for HZ == 300, we multiply by 300 and divide by 1000). This is exposed to the user when passing a large timeout to poll(), for example. This patch replaces the multiply-divide with a reciprocal multiplication on 32-bit platforms. When the input is an unsigned long, there is no portable way to do this on 64-bit platforms there is no portable way to do this since it requires a 128-bit intermediate result (which gcc does support on 64-bit platforms but may generate libgcc calls, e.g. on 64-bit s390), but since the output is a 32-bit integer in the cases affected, just simplify the multiply-divide (*3/10 instead of *300/1000). The reciprocal multiply used can have off-by-one errors in the upper half of the valid output range. This could be avoided at the expense of having to deal with a potential 65-bit intermediate result. Since the intent is to avoid overflow problems and most of the other time conversions are only semiexact, the off-by-one errors were considered an acceptable tradeoff. At Ralf Baechle's suggestion, this version uses a Perl script to compute the necessary constants. We already have dependencies on Perl for kernel compiles. This does, however, require the Perl module Math::BigInt, which is included in the standard Perl distribution starting with version 5.8.0. In order to support older versions of Perl, include a table of canned constants in the script itself, and structure the script so that Math::BigInt isn't required if pulling values from said table. Running the script requires that the HZ value is available from the Makefile. Thus, this patch also adds the Kconfig variable CONFIG_HZ to the architectures which didn't already have it (alpha, cris, frv, h8300, m32r, m68k, m68knommu, sparc, v850, and xtensa.) It does *not* touch the sh or sh64 architectures, since Paul Mundt has dealt with those separately in the sh tree. Signed-off-by: H. Peter Anvin <hpa@zytor.com> Cc: Ralf Baechle <ralf@linux-mips.org>, Cc: Sam Ravnborg <sam@ravnborg.org>, Cc: Paul Mundt <lethal@linux-sh.org>, Cc: Richard Henderson <rth@twiddle.net>, Cc: Michael Starvik <starvik@axis.com>, Cc: David Howells <dhowells@redhat.com>, Cc: Yoshinori Sato <ysato@users.sourceforge.jp>, Cc: Hirokazu Takata <takata@linux-m32r.org>, Cc: Geert Uytterhoeven <geert@linux-m68k.org>, Cc: Roman Zippel <zippel@linux-m68k.org>, Cc: William L. Irwin <sparclinux@vger.kernel.org>, Cc: Chris Zankel <chris@zankel.net>, Cc: H. Peter Anvin <hpa@zytor.com>, Cc: Jan Engelhardt <jengelh@computergmbh.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-08 12:21:26 +00:00
* - TYT, 1992-01-01
*
* The best thing to do is to keep the CMOS clock in universal time (UTC)
* as real UNIX machines always do it. This avoids all headaches about
* daylight saving times and warping kernel clocks.
*/
static inline void warp_clock(void)
{
write_seqlock_irq(&xtime_lock);
wall_to_monotonic.tv_sec -= sys_tz.tz_minuteswest * 60;
xtime.tv_sec += sys_tz.tz_minuteswest * 60;
Revert "time: Remove xtime_cache" This reverts commit 7bc7d637452383d56ba4368d4336b0dde1bb476d, as requested by John Stultz. Quoting John: "Petr Titěra reported an issue where he saw odd atime regressions with 2.6.33 where there were a full second worth of nanoseconds in the nanoseconds field. He also reviewed the time code and narrowed down the problem: unhandled overflow of the nanosecond field caused by rounding up the sub-nanosecond accumulated time. Details: * At the end of update_wall_time(), we currently round up the sub-nanosecond portion of accumulated time when storing it into xtime. This was added to avoid time inconsistencies caused when the sub-nanosecond portion was truncated when storing into xtime. Unfortunately we don't handle the possible second overflow caused by that rounding. * Previously the xtime_cache code hid this overflow by normalizing the xtime value when storing into the xtime_cache. * We could try to handle the second overflow after the rounding up, but since this affects the timekeeping's internal state, this would further complicate the next accumulation cycle, causing small errors in ntp steering. As much as I'd like to get rid of it, the xtime_cache code is known to work. * The correct fix is really to include the sub-nanosecond portion in the timekeeping accessor function, so we don't need to round up at during accumulation. This would greatly simplify the accumulation code. Unfortunately, we can't do this safely until the last three non-GENERIC_TIME arches (sparc32, arm, cris) are converted (those patches are in -mm) and we kill off the spots where arches set xtime directly. This is all 2.6.34 material, so I think reverting the xtime_cache change is the best approach for now. Many thanks to Petr for both reporting and finding the issue!" Reported-by: Petr Titěra <P.Titera@century.cz> Requested-by: john stultz <johnstul@us.ibm.com> Cc: Ingo Molnar <mingo@elte.hu> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-12-22 22:10:37 +00:00
update_xtime_cache(0);
write_sequnlock_irq(&xtime_lock);
clock_was_set();
}
/*
* In case for some reason the CMOS clock has not already been running
* in UTC, but in some local time: The first time we set the timezone,
* we will warp the clock so that it is ticking UTC time instead of
* local time. Presumably, if someone is setting the timezone then we
* are running in an environment where the programs understand about
* timezones. This should be done at boot time in the /etc/rc script,
* as soon as possible, so that the clock can be set right. Otherwise,
* various programs will get confused when the clock gets warped.
*/
int do_sys_settimeofday(struct timespec *tv, struct timezone *tz)
{
static int firsttime = 1;
int error = 0;
if (tv && !timespec_valid(tv))
return -EINVAL;
error = security_settime(tv, tz);
if (error)
return error;
if (tz) {
/* SMP safe, global irq locking makes it work. */
sys_tz = *tz;
update_vsyscall_tz();
if (firsttime) {
firsttime = 0;
if (!tv)
warp_clock();
}
}
if (tv)
{
/* SMP safe, again the code in arch/foo/time.c should
* globally block out interrupts when it runs.
*/
return do_settimeofday(tv);
}
return 0;
}
SYSCALL_DEFINE2(settimeofday, struct timeval __user *, tv,
struct timezone __user *, tz)
{
struct timeval user_tv;
struct timespec new_ts;
struct timezone new_tz;
if (tv) {
if (copy_from_user(&user_tv, tv, sizeof(*tv)))
return -EFAULT;
new_ts.tv_sec = user_tv.tv_sec;
new_ts.tv_nsec = user_tv.tv_usec * NSEC_PER_USEC;
}
if (tz) {
if (copy_from_user(&new_tz, tz, sizeof(*tz)))
return -EFAULT;
}
return do_sys_settimeofday(tv ? &new_ts : NULL, tz ? &new_tz : NULL);
}
SYSCALL_DEFINE1(adjtimex, struct timex __user *, txc_p)
{
struct timex txc; /* Local copy of parameter */
int ret;
/* Copy the user data space into the kernel copy
* structure. But bear in mind that the structures
* may change
*/
if(copy_from_user(&txc, txc_p, sizeof(struct timex)))
return -EFAULT;
ret = do_adjtimex(&txc);
return copy_to_user(txc_p, &txc, sizeof(struct timex)) ? -EFAULT : ret;
}
/**
* current_fs_time - Return FS time
* @sb: Superblock.
*
* Return the current time truncated to the time granularity supported by
* the fs.
*/
struct timespec current_fs_time(struct super_block *sb)
{
struct timespec now = current_kernel_time();
return timespec_trunc(now, sb->s_time_gran);
}
EXPORT_SYMBOL(current_fs_time);
/*
* Convert jiffies to milliseconds and back.
*
* Avoid unnecessary multiplications/divisions in the
* two most common HZ cases:
*/
unsigned int inline jiffies_to_msecs(const unsigned long j)
{
#if HZ <= MSEC_PER_SEC && !(MSEC_PER_SEC % HZ)
return (MSEC_PER_SEC / HZ) * j;
#elif HZ > MSEC_PER_SEC && !(HZ % MSEC_PER_SEC)
return (j + (HZ / MSEC_PER_SEC) - 1)/(HZ / MSEC_PER_SEC);
#else
avoid overflows in kernel/time.c When the conversion factor between jiffies and milli- or microseconds is not a single multiply or divide, as for the case of HZ == 300, we currently do a multiply followed by a divide. The intervening result, however, is subject to overflows, especially since the fraction is not simplified (for HZ == 300, we multiply by 300 and divide by 1000). This is exposed to the user when passing a large timeout to poll(), for example. This patch replaces the multiply-divide with a reciprocal multiplication on 32-bit platforms. When the input is an unsigned long, there is no portable way to do this on 64-bit platforms there is no portable way to do this since it requires a 128-bit intermediate result (which gcc does support on 64-bit platforms but may generate libgcc calls, e.g. on 64-bit s390), but since the output is a 32-bit integer in the cases affected, just simplify the multiply-divide (*3/10 instead of *300/1000). The reciprocal multiply used can have off-by-one errors in the upper half of the valid output range. This could be avoided at the expense of having to deal with a potential 65-bit intermediate result. Since the intent is to avoid overflow problems and most of the other time conversions are only semiexact, the off-by-one errors were considered an acceptable tradeoff. At Ralf Baechle's suggestion, this version uses a Perl script to compute the necessary constants. We already have dependencies on Perl for kernel compiles. This does, however, require the Perl module Math::BigInt, which is included in the standard Perl distribution starting with version 5.8.0. In order to support older versions of Perl, include a table of canned constants in the script itself, and structure the script so that Math::BigInt isn't required if pulling values from said table. Running the script requires that the HZ value is available from the Makefile. Thus, this patch also adds the Kconfig variable CONFIG_HZ to the architectures which didn't already have it (alpha, cris, frv, h8300, m32r, m68k, m68knommu, sparc, v850, and xtensa.) It does *not* touch the sh or sh64 architectures, since Paul Mundt has dealt with those separately in the sh tree. Signed-off-by: H. Peter Anvin <hpa@zytor.com> Cc: Ralf Baechle <ralf@linux-mips.org>, Cc: Sam Ravnborg <sam@ravnborg.org>, Cc: Paul Mundt <lethal@linux-sh.org>, Cc: Richard Henderson <rth@twiddle.net>, Cc: Michael Starvik <starvik@axis.com>, Cc: David Howells <dhowells@redhat.com>, Cc: Yoshinori Sato <ysato@users.sourceforge.jp>, Cc: Hirokazu Takata <takata@linux-m32r.org>, Cc: Geert Uytterhoeven <geert@linux-m68k.org>, Cc: Roman Zippel <zippel@linux-m68k.org>, Cc: William L. Irwin <sparclinux@vger.kernel.org>, Cc: Chris Zankel <chris@zankel.net>, Cc: H. Peter Anvin <hpa@zytor.com>, Cc: Jan Engelhardt <jengelh@computergmbh.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-08 12:21:26 +00:00
# if BITS_PER_LONG == 32
return (HZ_TO_MSEC_MUL32 * j) >> HZ_TO_MSEC_SHR32;
avoid overflows in kernel/time.c When the conversion factor between jiffies and milli- or microseconds is not a single multiply or divide, as for the case of HZ == 300, we currently do a multiply followed by a divide. The intervening result, however, is subject to overflows, especially since the fraction is not simplified (for HZ == 300, we multiply by 300 and divide by 1000). This is exposed to the user when passing a large timeout to poll(), for example. This patch replaces the multiply-divide with a reciprocal multiplication on 32-bit platforms. When the input is an unsigned long, there is no portable way to do this on 64-bit platforms there is no portable way to do this since it requires a 128-bit intermediate result (which gcc does support on 64-bit platforms but may generate libgcc calls, e.g. on 64-bit s390), but since the output is a 32-bit integer in the cases affected, just simplify the multiply-divide (*3/10 instead of *300/1000). The reciprocal multiply used can have off-by-one errors in the upper half of the valid output range. This could be avoided at the expense of having to deal with a potential 65-bit intermediate result. Since the intent is to avoid overflow problems and most of the other time conversions are only semiexact, the off-by-one errors were considered an acceptable tradeoff. At Ralf Baechle's suggestion, this version uses a Perl script to compute the necessary constants. We already have dependencies on Perl for kernel compiles. This does, however, require the Perl module Math::BigInt, which is included in the standard Perl distribution starting with version 5.8.0. In order to support older versions of Perl, include a table of canned constants in the script itself, and structure the script so that Math::BigInt isn't required if pulling values from said table. Running the script requires that the HZ value is available from the Makefile. Thus, this patch also adds the Kconfig variable CONFIG_HZ to the architectures which didn't already have it (alpha, cris, frv, h8300, m32r, m68k, m68knommu, sparc, v850, and xtensa.) It does *not* touch the sh or sh64 architectures, since Paul Mundt has dealt with those separately in the sh tree. Signed-off-by: H. Peter Anvin <hpa@zytor.com> Cc: Ralf Baechle <ralf@linux-mips.org>, Cc: Sam Ravnborg <sam@ravnborg.org>, Cc: Paul Mundt <lethal@linux-sh.org>, Cc: Richard Henderson <rth@twiddle.net>, Cc: Michael Starvik <starvik@axis.com>, Cc: David Howells <dhowells@redhat.com>, Cc: Yoshinori Sato <ysato@users.sourceforge.jp>, Cc: Hirokazu Takata <takata@linux-m32r.org>, Cc: Geert Uytterhoeven <geert@linux-m68k.org>, Cc: Roman Zippel <zippel@linux-m68k.org>, Cc: William L. Irwin <sparclinux@vger.kernel.org>, Cc: Chris Zankel <chris@zankel.net>, Cc: H. Peter Anvin <hpa@zytor.com>, Cc: Jan Engelhardt <jengelh@computergmbh.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-08 12:21:26 +00:00
# else
return (j * HZ_TO_MSEC_NUM) / HZ_TO_MSEC_DEN;
# endif
#endif
}
EXPORT_SYMBOL(jiffies_to_msecs);
unsigned int inline jiffies_to_usecs(const unsigned long j)
{
#if HZ <= USEC_PER_SEC && !(USEC_PER_SEC % HZ)
return (USEC_PER_SEC / HZ) * j;
#elif HZ > USEC_PER_SEC && !(HZ % USEC_PER_SEC)
return (j + (HZ / USEC_PER_SEC) - 1)/(HZ / USEC_PER_SEC);
#else
avoid overflows in kernel/time.c When the conversion factor between jiffies and milli- or microseconds is not a single multiply or divide, as for the case of HZ == 300, we currently do a multiply followed by a divide. The intervening result, however, is subject to overflows, especially since the fraction is not simplified (for HZ == 300, we multiply by 300 and divide by 1000). This is exposed to the user when passing a large timeout to poll(), for example. This patch replaces the multiply-divide with a reciprocal multiplication on 32-bit platforms. When the input is an unsigned long, there is no portable way to do this on 64-bit platforms there is no portable way to do this since it requires a 128-bit intermediate result (which gcc does support on 64-bit platforms but may generate libgcc calls, e.g. on 64-bit s390), but since the output is a 32-bit integer in the cases affected, just simplify the multiply-divide (*3/10 instead of *300/1000). The reciprocal multiply used can have off-by-one errors in the upper half of the valid output range. This could be avoided at the expense of having to deal with a potential 65-bit intermediate result. Since the intent is to avoid overflow problems and most of the other time conversions are only semiexact, the off-by-one errors were considered an acceptable tradeoff. At Ralf Baechle's suggestion, this version uses a Perl script to compute the necessary constants. We already have dependencies on Perl for kernel compiles. This does, however, require the Perl module Math::BigInt, which is included in the standard Perl distribution starting with version 5.8.0. In order to support older versions of Perl, include a table of canned constants in the script itself, and structure the script so that Math::BigInt isn't required if pulling values from said table. Running the script requires that the HZ value is available from the Makefile. Thus, this patch also adds the Kconfig variable CONFIG_HZ to the architectures which didn't already have it (alpha, cris, frv, h8300, m32r, m68k, m68knommu, sparc, v850, and xtensa.) It does *not* touch the sh or sh64 architectures, since Paul Mundt has dealt with those separately in the sh tree. Signed-off-by: H. Peter Anvin <hpa@zytor.com> Cc: Ralf Baechle <ralf@linux-mips.org>, Cc: Sam Ravnborg <sam@ravnborg.org>, Cc: Paul Mundt <lethal@linux-sh.org>, Cc: Richard Henderson <rth@twiddle.net>, Cc: Michael Starvik <starvik@axis.com>, Cc: David Howells <dhowells@redhat.com>, Cc: Yoshinori Sato <ysato@users.sourceforge.jp>, Cc: Hirokazu Takata <takata@linux-m32r.org>, Cc: Geert Uytterhoeven <geert@linux-m68k.org>, Cc: Roman Zippel <zippel@linux-m68k.org>, Cc: William L. Irwin <sparclinux@vger.kernel.org>, Cc: Chris Zankel <chris@zankel.net>, Cc: H. Peter Anvin <hpa@zytor.com>, Cc: Jan Engelhardt <jengelh@computergmbh.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-08 12:21:26 +00:00
# if BITS_PER_LONG == 32
return (HZ_TO_USEC_MUL32 * j) >> HZ_TO_USEC_SHR32;
avoid overflows in kernel/time.c When the conversion factor between jiffies and milli- or microseconds is not a single multiply or divide, as for the case of HZ == 300, we currently do a multiply followed by a divide. The intervening result, however, is subject to overflows, especially since the fraction is not simplified (for HZ == 300, we multiply by 300 and divide by 1000). This is exposed to the user when passing a large timeout to poll(), for example. This patch replaces the multiply-divide with a reciprocal multiplication on 32-bit platforms. When the input is an unsigned long, there is no portable way to do this on 64-bit platforms there is no portable way to do this since it requires a 128-bit intermediate result (which gcc does support on 64-bit platforms but may generate libgcc calls, e.g. on 64-bit s390), but since the output is a 32-bit integer in the cases affected, just simplify the multiply-divide (*3/10 instead of *300/1000). The reciprocal multiply used can have off-by-one errors in the upper half of the valid output range. This could be avoided at the expense of having to deal with a potential 65-bit intermediate result. Since the intent is to avoid overflow problems and most of the other time conversions are only semiexact, the off-by-one errors were considered an acceptable tradeoff. At Ralf Baechle's suggestion, this version uses a Perl script to compute the necessary constants. We already have dependencies on Perl for kernel compiles. This does, however, require the Perl module Math::BigInt, which is included in the standard Perl distribution starting with version 5.8.0. In order to support older versions of Perl, include a table of canned constants in the script itself, and structure the script so that Math::BigInt isn't required if pulling values from said table. Running the script requires that the HZ value is available from the Makefile. Thus, this patch also adds the Kconfig variable CONFIG_HZ to the architectures which didn't already have it (alpha, cris, frv, h8300, m32r, m68k, m68knommu, sparc, v850, and xtensa.) It does *not* touch the sh or sh64 architectures, since Paul Mundt has dealt with those separately in the sh tree. Signed-off-by: H. Peter Anvin <hpa@zytor.com> Cc: Ralf Baechle <ralf@linux-mips.org>, Cc: Sam Ravnborg <sam@ravnborg.org>, Cc: Paul Mundt <lethal@linux-sh.org>, Cc: Richard Henderson <rth@twiddle.net>, Cc: Michael Starvik <starvik@axis.com>, Cc: David Howells <dhowells@redhat.com>, Cc: Yoshinori Sato <ysato@users.sourceforge.jp>, Cc: Hirokazu Takata <takata@linux-m32r.org>, Cc: Geert Uytterhoeven <geert@linux-m68k.org>, Cc: Roman Zippel <zippel@linux-m68k.org>, Cc: William L. Irwin <sparclinux@vger.kernel.org>, Cc: Chris Zankel <chris@zankel.net>, Cc: H. Peter Anvin <hpa@zytor.com>, Cc: Jan Engelhardt <jengelh@computergmbh.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-08 12:21:26 +00:00
# else
return (j * HZ_TO_USEC_NUM) / HZ_TO_USEC_DEN;
# endif
#endif
}
EXPORT_SYMBOL(jiffies_to_usecs);
/**
* timespec_trunc - Truncate timespec to a granularity
* @t: Timespec
* @gran: Granularity in ns.
*
* Truncate a timespec to a granularity. gran must be smaller than a second.
* Always rounds down.
*
* This function should be only used for timestamps returned by
* current_kernel_time() or CURRENT_TIME, not with do_gettimeofday() because
* it doesn't handle the better resolution of the latter.
*/
struct timespec timespec_trunc(struct timespec t, unsigned gran)
{
/*
* Division is pretty slow so avoid it for common cases.
* Currently current_kernel_time() never returns better than
* jiffies resolution. Exploit that.
*/
if (gran <= jiffies_to_usecs(1) * 1000) {
/* nothing */
} else if (gran == 1000000000) {
t.tv_nsec = 0;
} else {
t.tv_nsec -= t.tv_nsec % gran;
}
return t;
}
EXPORT_SYMBOL(timespec_trunc);
#ifndef CONFIG_GENERIC_TIME
/*
* Simulate gettimeofday using do_gettimeofday which only allows a timeval
* and therefore only yields usec accuracy
*/
void getnstimeofday(struct timespec *tv)
{
struct timeval x;
do_gettimeofday(&x);
tv->tv_sec = x.tv_sec;
tv->tv_nsec = x.tv_usec * NSEC_PER_USEC;
}
EXPORT_SYMBOL_GPL(getnstimeofday);
#endif
/* Converts Gregorian date to seconds since 1970-01-01 00:00:00.
* Assumes input in normal date format, i.e. 1980-12-31 23:59:59
* => year=1980, mon=12, day=31, hour=23, min=59, sec=59.
*
* [For the Julian calendar (which was used in Russia before 1917,
* Britain & colonies before 1752, anywhere else before 1582,
* and is still in use by some communities) leave out the
* -year/100+year/400 terms, and add 10.]
*
* This algorithm was first published by Gauss (I think).
*
* WARNING: this function will overflow on 2106-02-07 06:28:16 on
* machines where long is 32-bit! (However, as time_t is signed, we
* will already get problems at other places on 2038-01-19 03:14:08)
*/
unsigned long
mktime(const unsigned int year0, const unsigned int mon0,
const unsigned int day, const unsigned int hour,
const unsigned int min, const unsigned int sec)
{
unsigned int mon = mon0, year = year0;
/* 1..12 -> 11,12,1..10 */
if (0 >= (int) (mon -= 2)) {
mon += 12; /* Puts Feb last since it has leap day */
year -= 1;
}
return ((((unsigned long)
(year/4 - year/100 + year/400 + 367*mon/12 + day) +
year*365 - 719499
)*24 + hour /* now have hours */
)*60 + min /* now have minutes */
)*60 + sec; /* finally seconds */
}
EXPORT_SYMBOL(mktime);
/**
* set_normalized_timespec - set timespec sec and nsec parts and normalize
*
* @ts: pointer to timespec variable to be set
* @sec: seconds to set
* @nsec: nanoseconds to set
*
* Set seconds and nanoseconds field of a timespec variable and
* normalize to the timespec storage format
*
* Note: The tv_nsec part is always in the range of
avoid overflows in kernel/time.c When the conversion factor between jiffies and milli- or microseconds is not a single multiply or divide, as for the case of HZ == 300, we currently do a multiply followed by a divide. The intervening result, however, is subject to overflows, especially since the fraction is not simplified (for HZ == 300, we multiply by 300 and divide by 1000). This is exposed to the user when passing a large timeout to poll(), for example. This patch replaces the multiply-divide with a reciprocal multiplication on 32-bit platforms. When the input is an unsigned long, there is no portable way to do this on 64-bit platforms there is no portable way to do this since it requires a 128-bit intermediate result (which gcc does support on 64-bit platforms but may generate libgcc calls, e.g. on 64-bit s390), but since the output is a 32-bit integer in the cases affected, just simplify the multiply-divide (*3/10 instead of *300/1000). The reciprocal multiply used can have off-by-one errors in the upper half of the valid output range. This could be avoided at the expense of having to deal with a potential 65-bit intermediate result. Since the intent is to avoid overflow problems and most of the other time conversions are only semiexact, the off-by-one errors were considered an acceptable tradeoff. At Ralf Baechle's suggestion, this version uses a Perl script to compute the necessary constants. We already have dependencies on Perl for kernel compiles. This does, however, require the Perl module Math::BigInt, which is included in the standard Perl distribution starting with version 5.8.0. In order to support older versions of Perl, include a table of canned constants in the script itself, and structure the script so that Math::BigInt isn't required if pulling values from said table. Running the script requires that the HZ value is available from the Makefile. Thus, this patch also adds the Kconfig variable CONFIG_HZ to the architectures which didn't already have it (alpha, cris, frv, h8300, m32r, m68k, m68knommu, sparc, v850, and xtensa.) It does *not* touch the sh or sh64 architectures, since Paul Mundt has dealt with those separately in the sh tree. Signed-off-by: H. Peter Anvin <hpa@zytor.com> Cc: Ralf Baechle <ralf@linux-mips.org>, Cc: Sam Ravnborg <sam@ravnborg.org>, Cc: Paul Mundt <lethal@linux-sh.org>, Cc: Richard Henderson <rth@twiddle.net>, Cc: Michael Starvik <starvik@axis.com>, Cc: David Howells <dhowells@redhat.com>, Cc: Yoshinori Sato <ysato@users.sourceforge.jp>, Cc: Hirokazu Takata <takata@linux-m32r.org>, Cc: Geert Uytterhoeven <geert@linux-m68k.org>, Cc: Roman Zippel <zippel@linux-m68k.org>, Cc: William L. Irwin <sparclinux@vger.kernel.org>, Cc: Chris Zankel <chris@zankel.net>, Cc: H. Peter Anvin <hpa@zytor.com>, Cc: Jan Engelhardt <jengelh@computergmbh.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-08 12:21:26 +00:00
* 0 <= tv_nsec < NSEC_PER_SEC
* For negative values only the tv_sec field is negative !
*/
void set_normalized_timespec(struct timespec *ts, time_t sec, s64 nsec)
{
while (nsec >= NSEC_PER_SEC) {
/*
* The following asm() prevents the compiler from
* optimising this loop into a modulo operation. See
* also __iter_div_u64_rem() in include/linux/time.h
*/
asm("" : "+rm"(nsec));
nsec -= NSEC_PER_SEC;
++sec;
}
while (nsec < 0) {
asm("" : "+rm"(nsec));
nsec += NSEC_PER_SEC;
--sec;
}
ts->tv_sec = sec;
ts->tv_nsec = nsec;
}
EXPORT_SYMBOL(set_normalized_timespec);
/**
* ns_to_timespec - Convert nanoseconds to timespec
* @nsec: the nanoseconds value to be converted
*
* Returns the timespec representation of the nsec parameter.
*/
struct timespec ns_to_timespec(const s64 nsec)
{
struct timespec ts;
s32 rem;
if (!nsec)
return (struct timespec) {0, 0};
ts.tv_sec = div_s64_rem(nsec, NSEC_PER_SEC, &rem);
if (unlikely(rem < 0)) {
ts.tv_sec--;
rem += NSEC_PER_SEC;
}
ts.tv_nsec = rem;
return ts;
}
EXPORT_SYMBOL(ns_to_timespec);
/**
* ns_to_timeval - Convert nanoseconds to timeval
* @nsec: the nanoseconds value to be converted
*
* Returns the timeval representation of the nsec parameter.
*/
struct timeval ns_to_timeval(const s64 nsec)
{
struct timespec ts = ns_to_timespec(nsec);
struct timeval tv;
tv.tv_sec = ts.tv_sec;
tv.tv_usec = (suseconds_t) ts.tv_nsec / 1000;
return tv;
}
EXPORT_SYMBOL(ns_to_timeval);
/*
* When we convert to jiffies then we interpret incoming values
* the following way:
*
* - negative values mean 'infinite timeout' (MAX_JIFFY_OFFSET)
*
* - 'too large' values [that would result in larger than
* MAX_JIFFY_OFFSET values] mean 'infinite timeout' too.
*
* - all other values are converted to jiffies by either multiplying
* the input value by a factor or dividing it with a factor
*
* We must also be careful about 32-bit overflows.
*/
unsigned long msecs_to_jiffies(const unsigned int m)
{
/*
* Negative value, means infinite timeout:
*/
if ((int)m < 0)
return MAX_JIFFY_OFFSET;
#if HZ <= MSEC_PER_SEC && !(MSEC_PER_SEC % HZ)
/*
* HZ is equal to or smaller than 1000, and 1000 is a nice
* round multiple of HZ, divide with the factor between them,
* but round upwards:
*/
return (m + (MSEC_PER_SEC / HZ) - 1) / (MSEC_PER_SEC / HZ);
#elif HZ > MSEC_PER_SEC && !(HZ % MSEC_PER_SEC)
/*
* HZ is larger than 1000, and HZ is a nice round multiple of
* 1000 - simply multiply with the factor between them.
*
* But first make sure the multiplication result cannot
* overflow:
*/
if (m > jiffies_to_msecs(MAX_JIFFY_OFFSET))
return MAX_JIFFY_OFFSET;
return m * (HZ / MSEC_PER_SEC);
#else
/*
* Generic case - multiply, round and divide. But first
* check that if we are doing a net multiplication, that
avoid overflows in kernel/time.c When the conversion factor between jiffies and milli- or microseconds is not a single multiply or divide, as for the case of HZ == 300, we currently do a multiply followed by a divide. The intervening result, however, is subject to overflows, especially since the fraction is not simplified (for HZ == 300, we multiply by 300 and divide by 1000). This is exposed to the user when passing a large timeout to poll(), for example. This patch replaces the multiply-divide with a reciprocal multiplication on 32-bit platforms. When the input is an unsigned long, there is no portable way to do this on 64-bit platforms there is no portable way to do this since it requires a 128-bit intermediate result (which gcc does support on 64-bit platforms but may generate libgcc calls, e.g. on 64-bit s390), but since the output is a 32-bit integer in the cases affected, just simplify the multiply-divide (*3/10 instead of *300/1000). The reciprocal multiply used can have off-by-one errors in the upper half of the valid output range. This could be avoided at the expense of having to deal with a potential 65-bit intermediate result. Since the intent is to avoid overflow problems and most of the other time conversions are only semiexact, the off-by-one errors were considered an acceptable tradeoff. At Ralf Baechle's suggestion, this version uses a Perl script to compute the necessary constants. We already have dependencies on Perl for kernel compiles. This does, however, require the Perl module Math::BigInt, which is included in the standard Perl distribution starting with version 5.8.0. In order to support older versions of Perl, include a table of canned constants in the script itself, and structure the script so that Math::BigInt isn't required if pulling values from said table. Running the script requires that the HZ value is available from the Makefile. Thus, this patch also adds the Kconfig variable CONFIG_HZ to the architectures which didn't already have it (alpha, cris, frv, h8300, m32r, m68k, m68knommu, sparc, v850, and xtensa.) It does *not* touch the sh or sh64 architectures, since Paul Mundt has dealt with those separately in the sh tree. Signed-off-by: H. Peter Anvin <hpa@zytor.com> Cc: Ralf Baechle <ralf@linux-mips.org>, Cc: Sam Ravnborg <sam@ravnborg.org>, Cc: Paul Mundt <lethal@linux-sh.org>, Cc: Richard Henderson <rth@twiddle.net>, Cc: Michael Starvik <starvik@axis.com>, Cc: David Howells <dhowells@redhat.com>, Cc: Yoshinori Sato <ysato@users.sourceforge.jp>, Cc: Hirokazu Takata <takata@linux-m32r.org>, Cc: Geert Uytterhoeven <geert@linux-m68k.org>, Cc: Roman Zippel <zippel@linux-m68k.org>, Cc: William L. Irwin <sparclinux@vger.kernel.org>, Cc: Chris Zankel <chris@zankel.net>, Cc: H. Peter Anvin <hpa@zytor.com>, Cc: Jan Engelhardt <jengelh@computergmbh.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-08 12:21:26 +00:00
* we wouldn't overflow:
*/
if (HZ > MSEC_PER_SEC && m > jiffies_to_msecs(MAX_JIFFY_OFFSET))
return MAX_JIFFY_OFFSET;
return (MSEC_TO_HZ_MUL32 * m + MSEC_TO_HZ_ADJ32)
avoid overflows in kernel/time.c When the conversion factor between jiffies and milli- or microseconds is not a single multiply or divide, as for the case of HZ == 300, we currently do a multiply followed by a divide. The intervening result, however, is subject to overflows, especially since the fraction is not simplified (for HZ == 300, we multiply by 300 and divide by 1000). This is exposed to the user when passing a large timeout to poll(), for example. This patch replaces the multiply-divide with a reciprocal multiplication on 32-bit platforms. When the input is an unsigned long, there is no portable way to do this on 64-bit platforms there is no portable way to do this since it requires a 128-bit intermediate result (which gcc does support on 64-bit platforms but may generate libgcc calls, e.g. on 64-bit s390), but since the output is a 32-bit integer in the cases affected, just simplify the multiply-divide (*3/10 instead of *300/1000). The reciprocal multiply used can have off-by-one errors in the upper half of the valid output range. This could be avoided at the expense of having to deal with a potential 65-bit intermediate result. Since the intent is to avoid overflow problems and most of the other time conversions are only semiexact, the off-by-one errors were considered an acceptable tradeoff. At Ralf Baechle's suggestion, this version uses a Perl script to compute the necessary constants. We already have dependencies on Perl for kernel compiles. This does, however, require the Perl module Math::BigInt, which is included in the standard Perl distribution starting with version 5.8.0. In order to support older versions of Perl, include a table of canned constants in the script itself, and structure the script so that Math::BigInt isn't required if pulling values from said table. Running the script requires that the HZ value is available from the Makefile. Thus, this patch also adds the Kconfig variable CONFIG_HZ to the architectures which didn't already have it (alpha, cris, frv, h8300, m32r, m68k, m68knommu, sparc, v850, and xtensa.) It does *not* touch the sh or sh64 architectures, since Paul Mundt has dealt with those separately in the sh tree. Signed-off-by: H. Peter Anvin <hpa@zytor.com> Cc: Ralf Baechle <ralf@linux-mips.org>, Cc: Sam Ravnborg <sam@ravnborg.org>, Cc: Paul Mundt <lethal@linux-sh.org>, Cc: Richard Henderson <rth@twiddle.net>, Cc: Michael Starvik <starvik@axis.com>, Cc: David Howells <dhowells@redhat.com>, Cc: Yoshinori Sato <ysato@users.sourceforge.jp>, Cc: Hirokazu Takata <takata@linux-m32r.org>, Cc: Geert Uytterhoeven <geert@linux-m68k.org>, Cc: Roman Zippel <zippel@linux-m68k.org>, Cc: William L. Irwin <sparclinux@vger.kernel.org>, Cc: Chris Zankel <chris@zankel.net>, Cc: H. Peter Anvin <hpa@zytor.com>, Cc: Jan Engelhardt <jengelh@computergmbh.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-08 12:21:26 +00:00
>> MSEC_TO_HZ_SHR32;
#endif
}
EXPORT_SYMBOL(msecs_to_jiffies);
unsigned long usecs_to_jiffies(const unsigned int u)
{
if (u > jiffies_to_usecs(MAX_JIFFY_OFFSET))
return MAX_JIFFY_OFFSET;
#if HZ <= USEC_PER_SEC && !(USEC_PER_SEC % HZ)
return (u + (USEC_PER_SEC / HZ) - 1) / (USEC_PER_SEC / HZ);
#elif HZ > USEC_PER_SEC && !(HZ % USEC_PER_SEC)
return u * (HZ / USEC_PER_SEC);
#else
return (USEC_TO_HZ_MUL32 * u + USEC_TO_HZ_ADJ32)
avoid overflows in kernel/time.c When the conversion factor between jiffies and milli- or microseconds is not a single multiply or divide, as for the case of HZ == 300, we currently do a multiply followed by a divide. The intervening result, however, is subject to overflows, especially since the fraction is not simplified (for HZ == 300, we multiply by 300 and divide by 1000). This is exposed to the user when passing a large timeout to poll(), for example. This patch replaces the multiply-divide with a reciprocal multiplication on 32-bit platforms. When the input is an unsigned long, there is no portable way to do this on 64-bit platforms there is no portable way to do this since it requires a 128-bit intermediate result (which gcc does support on 64-bit platforms but may generate libgcc calls, e.g. on 64-bit s390), but since the output is a 32-bit integer in the cases affected, just simplify the multiply-divide (*3/10 instead of *300/1000). The reciprocal multiply used can have off-by-one errors in the upper half of the valid output range. This could be avoided at the expense of having to deal with a potential 65-bit intermediate result. Since the intent is to avoid overflow problems and most of the other time conversions are only semiexact, the off-by-one errors were considered an acceptable tradeoff. At Ralf Baechle's suggestion, this version uses a Perl script to compute the necessary constants. We already have dependencies on Perl for kernel compiles. This does, however, require the Perl module Math::BigInt, which is included in the standard Perl distribution starting with version 5.8.0. In order to support older versions of Perl, include a table of canned constants in the script itself, and structure the script so that Math::BigInt isn't required if pulling values from said table. Running the script requires that the HZ value is available from the Makefile. Thus, this patch also adds the Kconfig variable CONFIG_HZ to the architectures which didn't already have it (alpha, cris, frv, h8300, m32r, m68k, m68knommu, sparc, v850, and xtensa.) It does *not* touch the sh or sh64 architectures, since Paul Mundt has dealt with those separately in the sh tree. Signed-off-by: H. Peter Anvin <hpa@zytor.com> Cc: Ralf Baechle <ralf@linux-mips.org>, Cc: Sam Ravnborg <sam@ravnborg.org>, Cc: Paul Mundt <lethal@linux-sh.org>, Cc: Richard Henderson <rth@twiddle.net>, Cc: Michael Starvik <starvik@axis.com>, Cc: David Howells <dhowells@redhat.com>, Cc: Yoshinori Sato <ysato@users.sourceforge.jp>, Cc: Hirokazu Takata <takata@linux-m32r.org>, Cc: Geert Uytterhoeven <geert@linux-m68k.org>, Cc: Roman Zippel <zippel@linux-m68k.org>, Cc: William L. Irwin <sparclinux@vger.kernel.org>, Cc: Chris Zankel <chris@zankel.net>, Cc: H. Peter Anvin <hpa@zytor.com>, Cc: Jan Engelhardt <jengelh@computergmbh.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-08 12:21:26 +00:00
>> USEC_TO_HZ_SHR32;
#endif
}
EXPORT_SYMBOL(usecs_to_jiffies);
/*
* The TICK_NSEC - 1 rounds up the value to the next resolution. Note
* that a remainder subtract here would not do the right thing as the
* resolution values don't fall on second boundries. I.e. the line:
* nsec -= nsec % TICK_NSEC; is NOT a correct resolution rounding.
*
* Rather, we just shift the bits off the right.
*
* The >> (NSEC_JIFFIE_SC - SEC_JIFFIE_SC) converts the scaled nsec
* value to a scaled second value.
*/
unsigned long
timespec_to_jiffies(const struct timespec *value)
{
unsigned long sec = value->tv_sec;
long nsec = value->tv_nsec + TICK_NSEC - 1;
if (sec >= MAX_SEC_IN_JIFFIES){
sec = MAX_SEC_IN_JIFFIES;
nsec = 0;
}
return (((u64)sec * SEC_CONVERSION) +
(((u64)nsec * NSEC_CONVERSION) >>
(NSEC_JIFFIE_SC - SEC_JIFFIE_SC))) >> SEC_JIFFIE_SC;
}
EXPORT_SYMBOL(timespec_to_jiffies);
void
jiffies_to_timespec(const unsigned long jiffies, struct timespec *value)
{
/*
* Convert jiffies to nanoseconds and separate with
* one divide.
*/
u32 rem;
value->tv_sec = div_u64_rem((u64)jiffies * TICK_NSEC,
NSEC_PER_SEC, &rem);
value->tv_nsec = rem;
}
EXPORT_SYMBOL(jiffies_to_timespec);
/* Same for "timeval"
*
* Well, almost. The problem here is that the real system resolution is
* in nanoseconds and the value being converted is in micro seconds.
* Also for some machines (those that use HZ = 1024, in-particular),
* there is a LARGE error in the tick size in microseconds.
* The solution we use is to do the rounding AFTER we convert the
* microsecond part. Thus the USEC_ROUND, the bits to be shifted off.
* Instruction wise, this should cost only an additional add with carry
* instruction above the way it was done above.
*/
unsigned long
timeval_to_jiffies(const struct timeval *value)
{
unsigned long sec = value->tv_sec;
long usec = value->tv_usec;
if (sec >= MAX_SEC_IN_JIFFIES){
sec = MAX_SEC_IN_JIFFIES;
usec = 0;
}
return (((u64)sec * SEC_CONVERSION) +
(((u64)usec * USEC_CONVERSION + USEC_ROUND) >>
(USEC_JIFFIE_SC - SEC_JIFFIE_SC))) >> SEC_JIFFIE_SC;
}
EXPORT_SYMBOL(timeval_to_jiffies);
void jiffies_to_timeval(const unsigned long jiffies, struct timeval *value)
{
/*
* Convert jiffies to nanoseconds and separate with
* one divide.
*/
u32 rem;
value->tv_sec = div_u64_rem((u64)jiffies * TICK_NSEC,
NSEC_PER_SEC, &rem);
value->tv_usec = rem / NSEC_PER_USEC;
}
EXPORT_SYMBOL(jiffies_to_timeval);
/*
* Convert jiffies/jiffies_64 to clock_t and back.
*/
clock_t jiffies_to_clock_t(long x)
{
#if (TICK_NSEC % (NSEC_PER_SEC / USER_HZ)) == 0
# if HZ < USER_HZ
return x * (USER_HZ / HZ);
# else
return x / (HZ / USER_HZ);
# endif
#else
return div_u64((u64)x * TICK_NSEC, NSEC_PER_SEC / USER_HZ);
#endif
}
EXPORT_SYMBOL(jiffies_to_clock_t);
unsigned long clock_t_to_jiffies(unsigned long x)
{
#if (HZ % USER_HZ)==0
if (x >= ~0UL / (HZ / USER_HZ))
return ~0UL;
return x * (HZ / USER_HZ);
#else
/* Don't worry about loss of precision here .. */
if (x >= ~0UL / HZ * USER_HZ)
return ~0UL;
/* .. but do try to contain it here */
return div_u64((u64)x * HZ, USER_HZ);
#endif
}
EXPORT_SYMBOL(clock_t_to_jiffies);
u64 jiffies_64_to_clock_t(u64 x)
{
#if (TICK_NSEC % (NSEC_PER_SEC / USER_HZ)) == 0
# if HZ < USER_HZ
x = div_u64(x * USER_HZ, HZ);
# elif HZ > USER_HZ
x = div_u64(x, HZ / USER_HZ);
# else
/* Nothing to do */
# endif
#else
/*
* There are better ways that don't overflow early,
* but even this doesn't overflow in hundreds of years
* in 64 bits, so..
*/
x = div_u64(x * TICK_NSEC, (NSEC_PER_SEC / USER_HZ));
#endif
return x;
}
EXPORT_SYMBOL(jiffies_64_to_clock_t);
u64 nsec_to_clock_t(u64 x)
{
#if (NSEC_PER_SEC % USER_HZ) == 0
return div_u64(x, NSEC_PER_SEC / USER_HZ);
#elif (USER_HZ % 512) == 0
return div_u64(x * USER_HZ / 512, NSEC_PER_SEC / 512);
#else
/*
* max relative error 5.7e-8 (1.8s per year) for USER_HZ <= 1024,
* overflow after 64.99 years.
* exact for HZ=60, 72, 90, 120, 144, 180, 300, 600, 900, ...
*/
return div_u64(x * 9, (9ull * NSEC_PER_SEC + (USER_HZ / 2)) / USER_HZ);
#endif
}
/**
* nsecs_to_jiffies - Convert nsecs in u64 to jiffies
*
* @n: nsecs in u64
*
* Unlike {m,u}secs_to_jiffies, type of input is not unsigned int but u64.
* And this doesn't return MAX_JIFFY_OFFSET since this function is designed
* for scheduler, not for use in device drivers to calculate timeout value.
*
* note:
* NSEC_PER_SEC = 10^9 = (5^9 * 2^9) = (1953125 * 512)
* ULLONG_MAX ns = 18446744073.709551615 secs = about 584 years
*/
unsigned long nsecs_to_jiffies(u64 n)
{
#if (NSEC_PER_SEC % HZ) == 0
/* Common case, HZ = 100, 128, 200, 250, 256, 500, 512, 1000 etc. */
return div_u64(n, NSEC_PER_SEC / HZ);
#elif (HZ % 512) == 0
/* overflow after 292 years if HZ = 1024 */
return div_u64(n * HZ / 512, NSEC_PER_SEC / 512);
#else
/*
* Generic case - optimized for cases where HZ is a multiple of 3.
* overflow after 64.99 years, exact for HZ = 60, 72, 90, 120 etc.
*/
return div_u64(n * 9, (9ull * NSEC_PER_SEC + HZ / 2) / HZ);
#endif
}
#if (BITS_PER_LONG < 64)
u64 get_jiffies_64(void)
{
unsigned long seq;
u64 ret;
do {
seq = read_seqbegin(&xtime_lock);
ret = jiffies_64;
} while (read_seqretry(&xtime_lock, seq));
return ret;
}
EXPORT_SYMBOL(get_jiffies_64);
#endif
EXPORT_SYMBOL(jiffies);
/*
* Add two timespec values and do a safety check for overflow.
* It's assumed that both values are valid (>= 0)
*/
struct timespec timespec_add_safe(const struct timespec lhs,
const struct timespec rhs)
{
struct timespec res;
set_normalized_timespec(&res, lhs.tv_sec + rhs.tv_sec,
lhs.tv_nsec + rhs.tv_nsec);
if (res.tv_sec < lhs.tv_sec || res.tv_sec < rhs.tv_sec)
res.tv_sec = TIME_T_MAX;
return res;
}