linux_dsm_epyc7002/include/linux/time.h

306 lines
8.8 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 1000000000000000LL
#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, s64 nsec);
/*
* timespec_add_safe assumes both values are positive and checks
* for overflow. It will return TIME_T_MAX if the reutrn would be
* smaller then either of the arguments.
*/
extern struct timespec timespec_add_safe(const struct timespec lhs,
const struct timespec rhs);
static inline struct timespec timespec_add(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;
}
/*
* 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 void read_persistent_clock(struct timespec *ts);
extern void read_boot_clock(struct timespec *ts);
extern int update_persistent_clock(struct timespec now);
void timekeeping_init(void);
extern int timekeeping_suspended;
unsigned long get_seconds(void);
struct timespec current_kernel_time(void);
struct timespec __current_kernel_time(void); /* does not take xtime_lock */
struct timespec get_monotonic_coarse(void);
void get_xtime_and_monotonic_and_sleep_offset(struct timespec *xtim,
struct timespec *wtom, struct timespec *sleep);
void timekeeping_inject_sleeptime(struct timespec *delta);
#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(const struct timespec *tv);
extern int do_sys_settimeofday(const struct timespec *tv,
const struct timezone *tz);
#define do_posix_clock_monotonic_gettime(ts) ktime_get_ts(ts)
extern long do_utimes(int dfd, const 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 getnstime_raw_and_real(struct timespec *ts_raw,
struct timespec *ts_real);
extern void getboottime(struct timespec *ts);
extern void monotonic_to_bootbased(struct timespec *ts);
extern void get_monotonic_boottime(struct timespec *ts);
extern struct timespec timespec_trunc(struct timespec t, unsigned gran);
extern int timekeeping_valid_for_hres(void);
extern u64 timekeeping_max_deferment(void);
extern int timekeeping_inject_offset(struct timespec *ts);
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>
2008-09-12 23:54:39 +07:00
struct tms;
extern void do_sys_times(struct tms *);
/*
* Similar to the struct tm in userspace <time.h>, but it needs to be here so
* that the kernel source is self contained.
*/
struct tm {
/*
* the number of seconds after the minute, normally in the range
* 0 to 59, but can be up to 60 to allow for leap seconds
*/
int tm_sec;
/* the number of minutes after the hour, in the range 0 to 59*/
int tm_min;
/* the number of hours past midnight, in the range 0 to 23 */
int tm_hour;
/* the day of the month, in the range 1 to 31 */
int tm_mday;
/* the number of months since January, in the range 0 to 11 */
int tm_mon;
/* the number of years since 1900 */
long tm_year;
/* the number of days since Sunday, in the range 0 to 6 */
int tm_wday;
/* the number of days since January 1, in the range 0 to 365 */
int tm_yday;
};
void time_to_tm(time_t totalsecs, int offset, struct tm *result);
/**
* 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__ */
/*
* 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
#define CLOCK_REALTIME_COARSE 5
#define CLOCK_MONOTONIC_COARSE 6
#define CLOCK_BOOTTIME 7
timers: Posix interface for alarm-timers This patch exposes alarm-timers to userland via the posix clock and timers interface, using two new clockids: CLOCK_REALTIME_ALARM and CLOCK_BOOTTIME_ALARM. Both clockids behave identically to CLOCK_REALTIME and CLOCK_BOOTTIME, respectively, but timers set against the _ALARM suffixed clockids will wake the system if it is suspended. Some background can be found here: https://lwn.net/Articles/429925/ The concept for Alarm-timers was inspired by the Android Alarm driver (by Arve Hjønnevåg) found in the Android kernel tree. See: http://android.git.kernel.org/?p=kernel/common.git;a=blob;f=drivers/rtc/alarm.c;h=1250edfbdf3302f5e4ea6194847c6ef4bb7beb1c;hb=android-2.6.36 While the in-kernel interface is pretty similar between alarm-timers and Android alarm driver, the user-space interface for the Android alarm driver is via ioctls to a new char device. As mentioned above, I've instead chosen to export this functionality via the posix interface, as it seemed a little simpler and avoids creating duplicate interfaces to things like CLOCK_REALTIME and CLOCK_MONOTONIC under alternate names (ie:ANDROID_ALARM_RTC and ANDROID_ALARM_SYSTEMTIME). The semantics of the Android alarm driver are different from what this posix interface provides. For instance, threads other then the thread waiting on the Android alarm driver are able to modify the alarm being waited on. Also this interface does not allow the same wakelock semantics that the Android driver provides (ie: kernel takes a wakelock on RTC alarm-interupt, and holds it through process wakeup, and while the process runs, until the process either closes the char device or calls back in to wait on a new alarm). One potential way to implement similar semantics may be via the timerfd infrastructure, but this needs more research. There may also need to be some sort of sysfs system level policy hooks that allow alarm timers to be disabled to keep them from firing at inappropriate times (ie: laptop in a well insulated bag, mid-flight). CC: Arve Hjønnevåg <arve@android.com> CC: Thomas Gleixner <tglx@linutronix.de> CC: Alessandro Zummo <a.zummo@towertech.it> Acked-by: Arnd Bergmann <arnd@arndb.de> Signed-off-by: John Stultz <john.stultz@linaro.org>
2011-01-12 00:54:33 +07:00
#define CLOCK_REALTIME_ALARM 8
#define CLOCK_BOOTTIME_ALARM 9
/*
* 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