OpenCloudOS-Kernel/include/linux/time.h

259 lines
7.2 KiB
C
Raw Normal View History

#ifndef _LINUX_TIME_H
#define _LINUX_TIME_H
#include <linux/types.h>
#ifdef __KERNEL__
# include <linux/cache.h>
# include <linux/seqlock.h>
# include <linux/math64.h>
#endif
#ifndef _STRUCT_TIMESPEC
#define _STRUCT_TIMESPEC
struct timespec {
__kernel_time_t tv_sec; /* seconds */
long tv_nsec; /* nanoseconds */
};
#endif
struct timeval {
__kernel_time_t tv_sec; /* seconds */
__kernel_suseconds_t tv_usec; /* microseconds */
};
struct timezone {
int tz_minuteswest; /* minutes west of Greenwich */
int tz_dsttime; /* type of dst correction */
};
#ifdef __KERNEL__
extern struct timezone sys_tz;
/* Parameters used to convert the timespec values: */
#define MSEC_PER_SEC 1000L
#define USEC_PER_MSEC 1000L
#define NSEC_PER_USEC 1000L
#define NSEC_PER_MSEC 1000000L
#define USEC_PER_SEC 1000000L
#define NSEC_PER_SEC 1000000000L
#define FSEC_PER_SEC 1000000000000000L
#define TIME_T_MAX (time_t)((1UL << ((sizeof(time_t) << 3) - 1)) - 1)
static inline int timespec_equal(const struct timespec *a,
const struct timespec *b)
{
return (a->tv_sec == b->tv_sec) && (a->tv_nsec == b->tv_nsec);
}
/*
* lhs < rhs: return <0
* lhs == rhs: return 0
* lhs > rhs: return >0
*/
static inline int timespec_compare(const struct timespec *lhs, const struct timespec *rhs)
{
if (lhs->tv_sec < rhs->tv_sec)
return -1;
if (lhs->tv_sec > rhs->tv_sec)
return 1;
return lhs->tv_nsec - rhs->tv_nsec;
}
static inline int timeval_compare(const struct timeval *lhs, const struct timeval *rhs)
{
if (lhs->tv_sec < rhs->tv_sec)
return -1;
if (lhs->tv_sec > rhs->tv_sec)
return 1;
return lhs->tv_usec - rhs->tv_usec;
}
extern unsigned long mktime(const unsigned int year, const unsigned int mon,
const unsigned int day, const unsigned int hour,
const unsigned int min, const unsigned int sec);
extern void set_normalized_timespec(struct timespec *ts, time_t sec, long nsec);
extern struct timespec timespec_add_safe(const struct timespec lhs,
const struct timespec rhs);
/*
* sub = lhs - rhs, in normalized form
*/
static inline struct timespec timespec_sub(struct timespec lhs,
struct timespec rhs)
{
struct timespec ts_delta;
set_normalized_timespec(&ts_delta, lhs.tv_sec - rhs.tv_sec,
lhs.tv_nsec - rhs.tv_nsec);
return ts_delta;
}
/*
* Returns true if the timespec is norm, false if denorm:
*/
#define timespec_valid(ts) \
(((ts)->tv_sec >= 0) && (((unsigned long) (ts)->tv_nsec) < NSEC_PER_SEC))
extern struct timespec xtime;
extern struct timespec wall_to_monotonic;
extern seqlock_t xtime_lock;
extern unsigned long read_persistent_clock(void);
extern int update_persistent_clock(struct timespec now);
extern int no_sync_cmos_clock __read_mostly;
void timekeeping_init(void);
extern int timekeeping_suspended;
unsigned long get_seconds(void);
struct timespec current_kernel_time(void);
#define CURRENT_TIME (current_kernel_time())
#define CURRENT_TIME_SEC ((struct timespec) { get_seconds(), 0 })
/* Some architectures do not supply their own clocksource.
* This is mainly the case in architectures that get their
* inter-tick times by reading the counter on their interval
* timer. Since these timers wrap every tick, they're not really
* useful as clocksources. Wrapping them to act like one is possible
* but not very efficient. So we provide a callout these arches
* can implement for use with the jiffies clocksource to provide
* finer then tick granular time.
*/
#ifdef CONFIG_ARCH_USES_GETTIMEOFFSET
extern u32 arch_gettimeoffset(void);
#else
static inline u32 arch_gettimeoffset(void) { return 0; }
#endif
extern void do_gettimeofday(struct timeval *tv);
extern int do_settimeofday(struct timespec *tv);
extern int do_sys_settimeofday(struct timespec *tv, struct timezone *tz);
#define do_posix_clock_monotonic_gettime(ts) ktime_get_ts(ts)
utimensat implementation 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: Ulrich 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: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-05-08 15:33:25 +08:00
extern long do_utimes(int dfd, char __user *filename, struct timespec *times, int flags);
struct itimerval;
extern int do_setitimer(int which, struct itimerval *value,
struct itimerval *ovalue);
extern unsigned int alarm_setitimer(unsigned int seconds);
extern int do_getitimer(int which, struct itimerval *value);
extern void getnstimeofday(struct timespec *tv);
extern void getrawmonotonic(struct timespec *ts);
extern void getboottime(struct timespec *ts);
extern void monotonic_to_bootbased(struct timespec *ts);
extern struct timespec timespec_trunc(struct timespec t, unsigned gran);
extern int timekeeping_valid_for_hres(void);
extern void update_wall_time(void);
extern void update_xtime_cache(u64 nsec);
timers: fix itimer/many thread hang Overview This patch reworks the handling of POSIX CPU timers, including the ITIMER_PROF, ITIMER_VIRT timers and rlimit handling. It was put together with the help of Roland McGrath, the owner and original writer of this code. The problem we ran into, and the reason for this rework, has to do with using a profiling timer in a process with a large number of threads. It appears that the performance of the old implementation of run_posix_cpu_timers() was at least O(n*3) (where "n" is the number of threads in a process) or worse. Everything is fine with an increasing number of threads until the time taken for that routine to run becomes the same as or greater than the tick time, at which point things degrade rather quickly. This patch fixes bug 9906, "Weird hang with NPTL and SIGPROF." Code Changes This rework corrects the implementation of run_posix_cpu_timers() to make it run in constant time for a particular machine. (Performance may vary between one machine and another depending upon whether the kernel is built as single- or multiprocessor and, in the latter case, depending upon the number of running processors.) To do this, at each tick we now update fields in signal_struct as well as task_struct. The run_posix_cpu_timers() function uses those fields to make its decisions. We define a new structure, "task_cputime," to contain user, system and scheduler times and use these in appropriate places: struct task_cputime { cputime_t utime; cputime_t stime; unsigned long long sum_exec_runtime; }; This is included in the structure "thread_group_cputime," which is a new substructure of signal_struct and which varies for uniprocessor versus multiprocessor kernels. For uniprocessor kernels, it uses "task_cputime" as a simple substructure, while for multiprocessor kernels it is a pointer: struct thread_group_cputime { struct task_cputime totals; }; struct thread_group_cputime { struct task_cputime *totals; }; We also add a new task_cputime substructure directly to signal_struct, to cache the earliest expiration of process-wide timers, and task_cputime also replaces the it_*_expires fields of task_struct (used for earliest expiration of thread timers). The "thread_group_cputime" structure contains process-wide timers that are updated via account_user_time() and friends. In the non-SMP case the structure is a simple aggregator; unfortunately in the SMP case that simplicity was not achievable due to cache-line contention between CPUs (in one measured case performance was actually _worse_ on a 16-cpu system than the same test on a 4-cpu system, due to this contention). For SMP, the thread_group_cputime counters are maintained as a per-cpu structure allocated using alloc_percpu(). The timer functions update only the timer field in the structure corresponding to the running CPU, obtained using per_cpu_ptr(). We define a set of inline functions in sched.h that we use to maintain the thread_group_cputime structure and hide the differences between UP and SMP implementations from the rest of the kernel. The thread_group_cputime_init() function initializes the thread_group_cputime structure for the given task. The thread_group_cputime_alloc() is a no-op for UP; for SMP it calls the out-of-line function thread_group_cputime_alloc_smp() to allocate and fill in the per-cpu structures and fields. The thread_group_cputime_free() function, also a no-op for UP, in SMP frees the per-cpu structures. The thread_group_cputime_clone_thread() function (also a UP no-op) for SMP calls thread_group_cputime_alloc() if the per-cpu structures haven't yet been allocated. The thread_group_cputime() function fills the task_cputime structure it is passed with the contents of the thread_group_cputime fields; in UP it's that simple but in SMP it must also safely check that tsk->signal is non-NULL (if it is it just uses the appropriate fields of task_struct) and, if so, sums the per-cpu values for each online CPU. Finally, the three functions account_group_user_time(), account_group_system_time() and account_group_exec_runtime() are used by timer functions to update the respective fields of the thread_group_cputime structure. Non-SMP operation is trivial and will not be mentioned further. The per-cpu structure is always allocated when a task creates its first new thread, via a call to thread_group_cputime_clone_thread() from copy_signal(). It is freed at process exit via a call to thread_group_cputime_free() from cleanup_signal(). All functions that formerly summed utime/stime/sum_sched_runtime values from from all threads in the thread group now use thread_group_cputime() to snapshot the values in the thread_group_cputime structure or the values in the task structure itself if the per-cpu structure hasn't been allocated. Finally, the code in kernel/posix-cpu-timers.c has changed quite a bit. The run_posix_cpu_timers() function has been split into a fast path and a slow path; the former safely checks whether there are any expired thread timers and, if not, just returns, while the slow path does the heavy lifting. With the dedicated thread group fields, timers are no longer "rebalanced" and the process_timer_rebalance() function and related code has gone away. All summing loops are gone and all code that used them now uses the thread_group_cputime() inline. When process-wide timers are set, the new task_cputime structure in signal_struct is used to cache the earliest expiration; this is checked in the fast path. Performance The fix appears not to add significant overhead to existing operations. It generally performs the same as the current code except in two cases, one in which it performs slightly worse (Case 5 below) and one in which it performs very significantly better (Case 2 below). Overall it's a wash except in those two cases. I've since done somewhat more involved testing on a dual-core Opteron system. Case 1: With no itimer running, for a test with 100,000 threads, the fixed kernel took 1428.5 seconds, 513 seconds more than the unfixed system, all of which was spent in the system. There were twice as many voluntary context switches with the fix as without it. Case 2: With an itimer running at .01 second ticks and 4000 threads (the most an unmodified kernel can handle), the fixed kernel ran the test in eight percent of the time (5.8 seconds as opposed to 70 seconds) and had better tick accuracy (.012 seconds per tick as opposed to .023 seconds per tick). Case 3: A 4000-thread test with an initial timer tick of .01 second and an interval of 10,000 seconds (i.e. a timer that ticks only once) had very nearly the same performance in both cases: 6.3 seconds elapsed for the fixed kernel versus 5.5 seconds for the unfixed kernel. With fewer threads (eight in these tests), the Case 1 test ran in essentially the same time on both the modified and unmodified kernels (5.2 seconds versus 5.8 seconds). The Case 2 test ran in about the same time as well, 5.9 seconds versus 5.4 seconds but again with much better tick accuracy, .013 seconds per tick versus .025 seconds per tick for the unmodified kernel. Since the fix affected the rlimit code, I also tested soft and hard CPU limits. Case 4: With a hard CPU limit of 20 seconds and eight threads (and an itimer running), the modified kernel was very slightly favored in that while it killed the process in 19.997 seconds of CPU time (5.002 seconds of wall time), only .003 seconds of that was system time, the rest was user time. The unmodified kernel killed the process in 20.001 seconds of CPU (5.014 seconds of wall time) of which .016 seconds was system time. Really, though, the results were too close to call. The results were essentially the same with no itimer running. Case 5: With a soft limit of 20 seconds and a hard limit of 2000 seconds (where the hard limit would never be reached) and an itimer running, the modified kernel exhibited worse tick accuracy than the unmodified kernel: .050 seconds/tick versus .028 seconds/tick. Otherwise, performance was almost indistinguishable. With no itimer running this test exhibited virtually identical behavior and times in both cases. In times past I did some limited performance testing. those results are below. On a four-cpu Opteron system without this fix, a sixteen-thread test executed in 3569.991 seconds, of which user was 3568.435s and system was 1.556s. On the same system with the fix, user and elapsed time were about the same, but system time dropped to 0.007 seconds. Performance with eight, four and one thread were comparable. Interestingly, the timer ticks with the fix seemed more accurate: The sixteen-thread test with the fix received 149543 ticks for 0.024 seconds per tick, while the same test without the fix received 58720 for 0.061 seconds per tick. Both cases were configured for an interval of 0.01 seconds. Again, the other tests were comparable. Each thread in this test computed the primes up to 25,000,000. I also did a test with a large number of threads, 100,000 threads, which is impossible without the fix. In this case each thread computed the primes only up to 10,000 (to make the runtime manageable). System time dominated, at 1546.968 seconds out of a total 2176.906 seconds (giving a user time of 629.938s). It received 147651 ticks for 0.015 seconds per tick, still quite accurate. There is obviously no comparable test without the fix. Signed-off-by: Frank Mayhar <fmayhar@google.com> Cc: Roland McGrath <roland@redhat.com> Cc: Alexey Dobriyan <adobriyan@gmail.com> Cc: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-09-13 00:54:39 +08:00
struct tms;
extern void do_sys_times(struct tms *);
/**
* timespec_to_ns - Convert timespec to nanoseconds
* @ts: pointer to the timespec variable to be converted
*
* Returns the scalar nanosecond representation of the timespec
* parameter.
*/
static inline s64 timespec_to_ns(const struct timespec *ts)
{
return ((s64) ts->tv_sec * NSEC_PER_SEC) + ts->tv_nsec;
}
/**
* timeval_to_ns - Convert timeval to nanoseconds
* @ts: pointer to the timeval variable to be converted
*
* Returns the scalar nanosecond representation of the timeval
* parameter.
*/
static inline s64 timeval_to_ns(const struct timeval *tv)
{
return ((s64) tv->tv_sec * NSEC_PER_SEC) +
tv->tv_usec * NSEC_PER_USEC;
}
/**
* ns_to_timespec - Convert nanoseconds to timespec
* @nsec: the nanoseconds value to be converted
*
* Returns the timespec representation of the nsec parameter.
*/
extern struct timespec ns_to_timespec(const s64 nsec);
/**
* ns_to_timeval - Convert nanoseconds to timeval
* @nsec: the nanoseconds value to be converted
*
* Returns the timeval representation of the nsec parameter.
*/
extern struct timeval ns_to_timeval(const s64 nsec);
/**
* timespec_add_ns - Adds nanoseconds to a timespec
* @a: pointer to timespec to be incremented
* @ns: unsigned nanoseconds value to be added
*
* This must always be inlined because its used from the x86-64 vdso,
* which cannot call other kernel functions.
*/
static __always_inline void timespec_add_ns(struct timespec *a, u64 ns)
{
a->tv_sec += __iter_div_u64_rem(a->tv_nsec + ns, NSEC_PER_SEC, &ns);
a->tv_nsec = ns;
}
#endif /* __KERNEL__ */
#define NFDBITS __NFDBITS
#define FD_SETSIZE __FD_SETSIZE
#define FD_SET(fd,fdsetp) __FD_SET(fd,fdsetp)
#define FD_CLR(fd,fdsetp) __FD_CLR(fd,fdsetp)
#define FD_ISSET(fd,fdsetp) __FD_ISSET(fd,fdsetp)
#define FD_ZERO(fdsetp) __FD_ZERO(fdsetp)
/*
* Names of the interval timers, and structure
* defining a timer setting:
*/
#define ITIMER_REAL 0
#define ITIMER_VIRTUAL 1
#define ITIMER_PROF 2
struct itimerspec {
struct timespec it_interval; /* timer period */
struct timespec it_value; /* timer expiration */
};
struct itimerval {
struct timeval it_interval; /* timer interval */
struct timeval it_value; /* current value */
};
/*
* The IDs of the various system clocks (for POSIX.1b interval timers):
*/
#define CLOCK_REALTIME 0
#define CLOCK_MONOTONIC 1
#define CLOCK_PROCESS_CPUTIME_ID 2
#define CLOCK_THREAD_CPUTIME_ID 3
#define CLOCK_MONOTONIC_RAW 4
/*
* The IDs of various hardware clocks:
*/
#define CLOCK_SGI_CYCLE 10
#define MAX_CLOCKS 16
#define CLOCKS_MASK (CLOCK_REALTIME | CLOCK_MONOTONIC)
#define CLOCKS_MONO CLOCK_MONOTONIC
/*
* The various flags for setting POSIX.1b interval timers:
*/
#define TIMER_ABSTIME 0x01
#endif