From ee974e01e5ef2914036f08c8e41d1a3fa8bfc9d9 Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 20 Aug 2008 16:37:26 -0700 Subject: clocksource: check range Check that the value being passed to parse_pmtmr() does not exceed the limits of pmtmr_ioport. Signed-off-by: David Howells Signed-off-by: Andrew Morton Signed-off-by: Ingo Molnar --- drivers/clocksource/acpi_pm.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/drivers/clocksource/acpi_pm.c b/drivers/clocksource/acpi_pm.c index 5ca1d80de182..3df338481004 100644 --- a/drivers/clocksource/acpi_pm.c +++ b/drivers/clocksource/acpi_pm.c @@ -226,9 +226,12 @@ static int __init parse_pmtmr(char *arg) if (strict_strtoul(arg, 16, &base)) return -EINVAL; - +#ifdef CONFIG_X86_64 + if (base > UINT_MAX) + return -ERANGE; +#endif printk(KERN_INFO "PMTMR IOPort override: 0x%04x -> 0x%04lx\n", - (unsigned int)pmtmr_ioport, base); + pmtmr_ioport, base); pmtmr_ioport = base; return 1; -- cgit v1.2.3 From 1aa5dfb751d275ae7117d3b73ac423b4a46f2a73 Mon Sep 17 00:00:00 2001 From: John Stultz Date: Wed, 20 Aug 2008 16:37:28 -0700 Subject: clocksource: keep track of original clocksource frequency The clocksource frequency is represented by clocksource->mult/2^(clocksource->shift). Currently, when NTP makes adjustments to the clock frequency, they are made directly to the mult value. This has the drawback that once changed, we cannot know what the orignal mult value was, or how much adjustment has been applied. This property causes problems in calculating proper ntp intervals when switching back and forth between clocksources. This patch separates the current mult value into a mult and mult_orig pair. The mult_orig value stays constant, while the ntp clocksource adjustments are done only to the mult value. This allows for correct ntp interval calculation and additionally lays the groundwork for a new notion of time, what I'm calling the monotonic-raw time, which is introduced in a following patch. Signed-off-by: John Stultz Signed-off-by: Roman Zippel Signed-off-by: Andrew Morton Signed-off-by: Ingo Molnar --- include/linux/clocksource.h | 11 +++++++---- kernel/time/clocksource.c | 3 +++ kernel/time/jiffies.c | 1 + 3 files changed, 11 insertions(+), 4 deletions(-) diff --git a/include/linux/clocksource.h b/include/linux/clocksource.h index 55e434feec99..f0a7fb984413 100644 --- a/include/linux/clocksource.h +++ b/include/linux/clocksource.h @@ -45,7 +45,8 @@ struct clocksource; * @read: returns a cycle value * @mask: bitmask for two's complement * subtraction of non 64 bit counters - * @mult: cycle to nanosecond multiplier + * @mult: cycle to nanosecond multiplier (adjusted by NTP) + * @mult_orig: cycle to nanosecond multiplier (unadjusted by NTP) * @shift: cycle to nanosecond divisor (power of two) * @flags: flags describing special properties * @vread: vsyscall based read @@ -63,6 +64,7 @@ struct clocksource { cycle_t (*read)(void); cycle_t mask; u32 mult; + u32 mult_orig; u32 shift; unsigned long flags; cycle_t (*vread)(void); @@ -201,16 +203,17 @@ static inline void clocksource_calculate_interval(struct clocksource *c, { u64 tmp; - /* XXX - All of this could use a whole lot of optimization */ + /* Do the ns -> cycle conversion first, using original mult */ tmp = length_nsec; tmp <<= c->shift; - tmp += c->mult/2; - do_div(tmp, c->mult); + tmp += c->mult_orig/2; + do_div(tmp, c->mult_orig); c->cycle_interval = (cycle_t)tmp; if (c->cycle_interval == 0) c->cycle_interval = 1; + /* Go back from cycles -> shifted ns, this time use ntp adjused mult */ c->xtime_interval = (u64)c->cycle_interval * c->mult; } diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c index 093d4acf993b..9ed2eec97526 100644 --- a/kernel/time/clocksource.c +++ b/kernel/time/clocksource.c @@ -325,6 +325,9 @@ int clocksource_register(struct clocksource *c) unsigned long flags; int ret; + /* save mult_orig on registration */ + c->mult_orig = c->mult; + spin_lock_irqsave(&clocksource_lock, flags); ret = clocksource_enqueue(c); if (!ret) diff --git a/kernel/time/jiffies.c b/kernel/time/jiffies.c index 4c256fdb8875..1ca99557e929 100644 --- a/kernel/time/jiffies.c +++ b/kernel/time/jiffies.c @@ -61,6 +61,7 @@ struct clocksource clocksource_jiffies = { .read = jiffies_read, .mask = 0xffffffff, /*32bits*/ .mult = NSEC_PER_JIFFY << JIFFIES_SHIFT, /* details above */ + .mult_orig = NSEC_PER_JIFFY << JIFFIES_SHIFT, .shift = JIFFIES_SHIFT, }; -- cgit v1.2.3 From 9a055117d3d9cb562f83f8d4cd88772761f4cab0 Mon Sep 17 00:00:00 2001 From: Roman Zippel Date: Wed, 20 Aug 2008 16:37:28 -0700 Subject: clocksource: introduce clocksource_forward_now() To keep the raw monotonic patch simple first introduce clocksource_forward_now(), which takes care of the offset since the last update_wall_time() call and adds it to the clock, so there is no need anymore to deal with it explicitly at various places, which need to make significant changes to the clock. This is also gets rid of the timekeeping_suspend_nsecs, instead of waiting until resume, the value is accumulated during suspend. In the end there is only a single user of __get_nsec_offset() left, so I integrated it back to getnstimeofday(). Signed-off-by: Roman Zippel Signed-off-by: Andrew Morton Signed-off-by: Ingo Molnar --- kernel/time/timekeeping.c | 71 ++++++++++++++++++++++------------------------- 1 file changed, 33 insertions(+), 38 deletions(-) diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index e91c29f961c9..83d3555a6998 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -58,27 +58,23 @@ struct clocksource *clock; #ifdef CONFIG_GENERIC_TIME /** - * __get_nsec_offset - Returns nanoseconds since last call to periodic_hook + * clocksource_forward_now - update clock to the current time * - * private function, must hold xtime_lock lock when being - * called. Returns the number of nanoseconds since the - * last call to update_wall_time() (adjusted by NTP scaling) + * Forward the current clock to update its state since the last call to + * update_wall_time(). This is useful before significant clock changes, + * as it avoids having to deal with this time offset explicitly. */ -static inline s64 __get_nsec_offset(void) +static void clocksource_forward_now(void) { cycle_t cycle_now, cycle_delta; - s64 ns_offset; + s64 nsec; - /* read clocksource: */ cycle_now = clocksource_read(clock); - - /* calculate the delta since the last update_wall_time: */ cycle_delta = (cycle_now - clock->cycle_last) & clock->mask; + clock->cycle_last = cycle_now; - /* convert to nanoseconds: */ - ns_offset = cyc2ns(clock, cycle_delta); - - return ns_offset; + nsec = cyc2ns(clock, cycle_delta); + timespec_add_ns(&xtime, nsec); } /** @@ -89,6 +85,7 @@ static inline s64 __get_nsec_offset(void) */ void getnstimeofday(struct timespec *ts) { + cycle_t cycle_now, cycle_delta; unsigned long seq; s64 nsecs; @@ -96,7 +93,15 @@ void getnstimeofday(struct timespec *ts) seq = read_seqbegin(&xtime_lock); *ts = xtime; - nsecs = __get_nsec_offset(); + + /* read clocksource: */ + cycle_now = clocksource_read(clock); + + /* calculate the delta since the last update_wall_time: */ + cycle_delta = (cycle_now - clock->cycle_last) & clock->mask; + + /* convert to nanoseconds: */ + nsecs = cyc2ns(clock, cycle_delta); } while (read_seqretry(&xtime_lock, seq)); @@ -129,22 +134,22 @@ EXPORT_SYMBOL(do_gettimeofday); */ int do_settimeofday(struct timespec *tv) { + struct timespec ts_delta; unsigned long flags; - time_t wtm_sec, sec = tv->tv_sec; - long wtm_nsec, nsec = tv->tv_nsec; if ((unsigned long)tv->tv_nsec >= NSEC_PER_SEC) return -EINVAL; write_seqlock_irqsave(&xtime_lock, flags); - nsec -= __get_nsec_offset(); + clocksource_forward_now(); + + ts_delta.tv_sec = tv->tv_sec - xtime.tv_sec; + ts_delta.tv_nsec = tv->tv_nsec - xtime.tv_nsec; + wall_to_monotonic = timespec_sub(wall_to_monotonic, ts_delta); - wtm_sec = wall_to_monotonic.tv_sec + (xtime.tv_sec - sec); - wtm_nsec = wall_to_monotonic.tv_nsec + (xtime.tv_nsec - nsec); + xtime = *tv; - set_normalized_timespec(&xtime, sec, nsec); - set_normalized_timespec(&wall_to_monotonic, wtm_sec, wtm_nsec); update_xtime_cache(0); clock->error = 0; @@ -170,22 +175,17 @@ EXPORT_SYMBOL(do_settimeofday); static void change_clocksource(void) { struct clocksource *new; - cycle_t now; - u64 nsec; new = clocksource_get_next(); if (clock == new) return; - new->cycle_last = 0; - now = clocksource_read(new); - nsec = __get_nsec_offset(); - timespec_add_ns(&xtime, nsec); + clocksource_forward_now(); clock = new; - clock->cycle_last = now; - + clock->cycle_last = 0; + clock->cycle_last = clocksource_read(new); clock->error = 0; clock->xtime_nsec = 0; clocksource_calculate_interval(clock, NTP_INTERVAL_LENGTH); @@ -200,8 +200,8 @@ static void change_clocksource(void) */ } #else +static inline void clocksource_forward_now(void) { } static inline void change_clocksource(void) { } -static inline s64 __get_nsec_offset(void) { return 0; } #endif /** @@ -265,8 +265,6 @@ void __init timekeeping_init(void) static int timekeeping_suspended; /* time in seconds when suspend began */ static unsigned long timekeeping_suspend_time; -/* xtime offset when we went into suspend */ -static s64 timekeeping_suspend_nsecs; /** * timekeeping_resume - Resumes the generic timekeeping subsystem. @@ -292,8 +290,6 @@ static int timekeeping_resume(struct sys_device *dev) wall_to_monotonic.tv_sec -= sleep_length; total_sleep_time += sleep_length; } - /* Make sure that we have the correct xtime reference */ - timespec_add_ns(&xtime, timekeeping_suspend_nsecs); update_xtime_cache(0); /* re-base the last cycle value */ clock->cycle_last = 0; @@ -319,8 +315,7 @@ static int timekeeping_suspend(struct sys_device *dev, pm_message_t state) timekeeping_suspend_time = read_persistent_clock(); write_seqlock_irqsave(&xtime_lock, flags); - /* Get the current xtime offset */ - timekeeping_suspend_nsecs = __get_nsec_offset(); + clocksource_forward_now(); timekeeping_suspended = 1; write_sequnlock_irqrestore(&xtime_lock, flags); @@ -461,10 +456,10 @@ void update_wall_time(void) */ while (offset >= clock->cycle_interval) { /* accumulate one interval */ - clock->xtime_nsec += clock->xtime_interval; - clock->cycle_last += clock->cycle_interval; offset -= clock->cycle_interval; + clock->cycle_last += clock->cycle_interval; + clock->xtime_nsec += clock->xtime_interval; if (clock->xtime_nsec >= (u64)NSEC_PER_SEC << clock->shift) { clock->xtime_nsec -= (u64)NSEC_PER_SEC << clock->shift; xtime.tv_sec++; -- cgit v1.2.3 From 2d42244ae71d6c7b0884b5664cf2eda30fb2ae68 Mon Sep 17 00:00:00 2001 From: John Stultz Date: Wed, 20 Aug 2008 16:37:30 -0700 Subject: clocksource: introduce CLOCK_MONOTONIC_RAW In talking with Josip Loncaric, and his work on clock synchronization (see btime.sf.net), he mentioned that for really close synchronization, it is useful to have access to "hardware time", that is a notion of time that is not in any way adjusted by the clock slewing done to keep close time sync. Part of the issue is if we are using the kernel's ntp adjusted representation of time in order to measure how we should correct time, we can run into what Paul McKenney aptly described as "Painting a road using the lines we're painting as the guide". I had been thinking of a similar problem, and was trying to come up with a way to give users access to a purely hardware based time representation that avoided users having to know the underlying frequency and mask values needed to deal with the wide variety of possible underlying hardware counters. My solution is to introduce CLOCK_MONOTONIC_RAW. This exposes a nanosecond based time value, that increments starting at bootup and has no frequency adjustments made to it what so ever. The time is accessed from userspace via the posix_clock_gettime() syscall, passing CLOCK_MONOTONIC_RAW as the clock_id. Signed-off-by: John Stultz Signed-off-by: Roman Zippel Signed-off-by: Andrew Morton Signed-off-by: Ingo Molnar --- include/linux/clocksource.h | 3 +++ include/linux/time.h | 2 ++ kernel/posix-timers.c | 15 +++++++++++++++ kernel/time/timekeeping.c | 44 ++++++++++++++++++++++++++++++++++++++++++++ 4 files changed, 64 insertions(+) diff --git a/include/linux/clocksource.h b/include/linux/clocksource.h index f0a7fb984413..f88d32f8ff7c 100644 --- a/include/linux/clocksource.h +++ b/include/linux/clocksource.h @@ -79,6 +79,7 @@ struct clocksource { /* timekeeping specific data, ignore */ cycle_t cycle_interval; u64 xtime_interval; + u32 raw_interval; /* * Second part is written at each timer interrupt * Keep it in a different cache line to dirty no @@ -87,6 +88,7 @@ struct clocksource { cycle_t cycle_last ____cacheline_aligned_in_smp; u64 xtime_nsec; s64 error; + struct timespec raw_time; #ifdef CONFIG_CLOCKSOURCE_WATCHDOG /* Watchdog related data, used by the framework */ @@ -215,6 +217,7 @@ static inline void clocksource_calculate_interval(struct clocksource *c, /* Go back from cycles -> shifted ns, this time use ntp adjused mult */ c->xtime_interval = (u64)c->cycle_interval * c->mult; + c->raw_interval = ((u64)c->cycle_interval * c->mult_orig) >> c->shift; } diff --git a/include/linux/time.h b/include/linux/time.h index e15206a7e82e..205f974b9ebf 100644 --- a/include/linux/time.h +++ b/include/linux/time.h @@ -117,6 +117,7 @@ extern int do_setitimer(int which, struct itimerval *value, 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); @@ -214,6 +215,7 @@ struct itimerval { #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: diff --git a/kernel/posix-timers.c b/kernel/posix-timers.c index e36d5798cbff..d3c66b53dff6 100644 --- a/kernel/posix-timers.c +++ b/kernel/posix-timers.c @@ -222,6 +222,15 @@ static int posix_ktime_get_ts(clockid_t which_clock, struct timespec *tp) return 0; } +/* + * Get monotonic time for posix timers + */ +static int posix_get_monotonic_raw(clockid_t which_clock, struct timespec *tp) +{ + getrawmonotonic(tp); + return 0; +} + /* * Initialize everything, well, just everything in Posix clocks/timers ;) */ @@ -235,9 +244,15 @@ static __init int init_posix_timers(void) .clock_get = posix_ktime_get_ts, .clock_set = do_posix_clock_nosettime, }; + struct k_clock clock_monotonic_raw = { + .clock_getres = hrtimer_get_res, + .clock_get = posix_get_monotonic_raw, + .clock_set = do_posix_clock_nosettime, + }; register_posix_clock(CLOCK_REALTIME, &clock_realtime); register_posix_clock(CLOCK_MONOTONIC, &clock_monotonic); + register_posix_clock(CLOCK_MONOTONIC_RAW, &clock_monotonic_raw); posix_timers_cache = kmem_cache_create("posix_timers_cache", sizeof (struct k_itimer), 0, SLAB_PANIC, diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index 83d3555a6998..5099c95b8aa2 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -75,6 +75,9 @@ static void clocksource_forward_now(void) nsec = cyc2ns(clock, cycle_delta); timespec_add_ns(&xtime, nsec); + + nsec = ((s64)cycle_delta * clock->mult_orig) >> clock->shift; + clock->raw_time.tv_nsec += nsec; } /** @@ -183,6 +186,8 @@ static void change_clocksource(void) clocksource_forward_now(); + new->raw_time = clock->raw_time; + clock = new; clock->cycle_last = 0; clock->cycle_last = clocksource_read(new); @@ -204,6 +209,39 @@ static inline void clocksource_forward_now(void) { } static inline void change_clocksource(void) { } #endif +/** + * getrawmonotonic - Returns the raw monotonic time in a timespec + * @ts: pointer to the timespec to be set + * + * Returns the raw monotonic time (completely un-modified by ntp) + */ +void getrawmonotonic(struct timespec *ts) +{ + unsigned long seq; + s64 nsecs; + cycle_t cycle_now, cycle_delta; + + do { + seq = read_seqbegin(&xtime_lock); + + /* read clocksource: */ + cycle_now = clocksource_read(clock); + + /* calculate the delta since the last update_wall_time: */ + cycle_delta = (cycle_now - clock->cycle_last) & clock->mask; + + /* convert to nanoseconds: */ + nsecs = ((s64)cycle_delta * clock->mult_orig) >> clock->shift; + + *ts = clock->raw_time; + + } while (read_seqretry(&xtime_lock, seq)); + + timespec_add_ns(ts, nsecs); +} +EXPORT_SYMBOL(getrawmonotonic); + + /** * timekeeping_valid_for_hres - Check if timekeeping is suitable for hres */ @@ -466,6 +504,12 @@ void update_wall_time(void) second_overflow(); } + clock->raw_time.tv_nsec += clock->raw_interval; + if (clock->raw_time.tv_nsec >= NSEC_PER_SEC) { + clock->raw_time.tv_nsec -= NSEC_PER_SEC; + clock->raw_time.tv_sec++; + } + /* accumulate error between NTP and clock interval */ clock->error += tick_length; clock->error -= clock->xtime_interval << (NTP_SCALE_SHIFT - clock->shift); -- cgit v1.2.3 From d82f0b0f6f1a0a25afc288fb7135b1601fe6df18 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Wed, 20 Aug 2008 16:46:04 -0700 Subject: migrate_timers: add comment, use spinlock_irq() Add the comment to explain why the double lock in migrate_timers() can't deadlock. Change the code to use spinlock_irq() instead of local_irq_disable() + spin_lock(). Signed-off-by: Oleg Nesterov Acked-by: Steven Rostedt Signed-off-by: Andrew Morton Signed-off-by: Ingo Molnar --- kernel/hrtimer.c | 11 ++++++----- kernel/timer.c | 11 ++++++----- 2 files changed, 12 insertions(+), 10 deletions(-) diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c index b8e4dce80a74..03ea1378c43b 100644 --- a/kernel/hrtimer.c +++ b/kernel/hrtimer.c @@ -1620,9 +1620,11 @@ static void migrate_hrtimers(int cpu) new_base = &get_cpu_var(hrtimer_bases); tick_cancel_sched_timer(cpu); - - local_irq_disable(); - spin_lock(&new_base->lock); + /* + * The caller is globally serialized and nobody else + * takes two locks at once, deadlock is not possible. + */ + spin_lock_irq(&new_base->lock); spin_lock_nested(&old_base->lock, SINGLE_DEPTH_NESTING); for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++) { @@ -1631,8 +1633,7 @@ static void migrate_hrtimers(int cpu) } spin_unlock(&old_base->lock); - spin_unlock(&new_base->lock); - local_irq_enable(); + spin_unlock_irq(&new_base->lock); put_cpu_var(hrtimer_bases); } #endif /* CONFIG_HOTPLUG_CPU */ diff --git a/kernel/timer.c b/kernel/timer.c index 03bc7f1f1593..e8019cc3418d 100644 --- a/kernel/timer.c +++ b/kernel/timer.c @@ -1435,9 +1435,11 @@ static void __cpuinit migrate_timers(int cpu) BUG_ON(cpu_online(cpu)); old_base = per_cpu(tvec_bases, cpu); new_base = get_cpu_var(tvec_bases); - - local_irq_disable(); - spin_lock(&new_base->lock); + /* + * The caller is globally serialized and nobody else + * takes two locks at once, deadlock is not possible. + */ + spin_lock_irq(&new_base->lock); spin_lock_nested(&old_base->lock, SINGLE_DEPTH_NESTING); BUG_ON(old_base->running_timer); @@ -1452,8 +1454,7 @@ static void __cpuinit migrate_timers(int cpu) } spin_unlock(&old_base->lock); - spin_unlock(&new_base->lock); - local_irq_enable(); + spin_unlock_irq(&new_base->lock); put_cpu_var(tvec_bases); } #endif /* CONFIG_HOTPLUG_CPU */ -- cgit v1.2.3 From 916c7a855174e3b53d182b97a26b2e27a29726a1 Mon Sep 17 00:00:00 2001 From: Roman Zippel Date: Wed, 20 Aug 2008 16:46:08 -0700 Subject: ntp: fix ADJ_OFFSET_SS_READ bug and do_adjtimex() cleanup Thanks to the review by Michael Kerrisk a bug in the recent ADJ_OFFSET_SS_READ option was discovered, where the ntp time_offset was inadvertently set by it. This fixes this by making the adjtime code more separate from the ntp_adjtime code (both of which really want to be separate syscalls). Signed-off-by: Roman Zippel Signed-off-by: Andrew Morton Acked-by: John Stultz Signed-off-by: Ingo Molnar --- include/linux/timex.h | 9 +++++- kernel/time/ntp.c | 76 +++++++++++++++++++++++++++------------------------ 2 files changed, 48 insertions(+), 37 deletions(-) diff --git a/include/linux/timex.h b/include/linux/timex.h index fc6035d29d56..c00bcdd3ae42 100644 --- a/include/linux/timex.h +++ b/include/linux/timex.h @@ -141,8 +141,15 @@ struct timex { #define ADJ_MICRO 0x1000 /* select microsecond resolution */ #define ADJ_NANO 0x2000 /* select nanosecond resolution */ #define ADJ_TICK 0x4000 /* tick value */ + +#ifdef __KERNEL__ +#define ADJ_ADJTIME 0x8000 /* switch between adjtime/adjtimex modes */ +#define ADJ_OFFSET_SINGLESHOT 0x0001 /* old-fashioned adjtime */ +#define ADJ_OFFSET_READONLY 0x2000 /* read-only adjtime */ +#else #define ADJ_OFFSET_SINGLESHOT 0x8001 /* old-fashioned adjtime */ -#define ADJ_OFFSET_SS_READ 0xa001 /* read-only adjtime */ +#define ADJ_OFFSET_SS_READ 0xa001 /* read-only adjtime */ +#endif /* xntp 3.4 compatibility names */ #define MOD_OFFSET ADJ_OFFSET diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c index 5125ddd8196b..c6921aa1a42a 100644 --- a/kernel/time/ntp.c +++ b/kernel/time/ntp.c @@ -277,38 +277,50 @@ static inline void notify_cmos_timer(void) { } int do_adjtimex(struct timex *txc) { struct timespec ts; - long save_adjust, sec; int result; - /* In order to modify anything, you gotta be super-user! */ - if (txc->modes && !capable(CAP_SYS_TIME)) - return -EPERM; - - /* Now we validate the data before disabling interrupts */ - - if ((txc->modes & ADJ_OFFSET_SINGLESHOT) == ADJ_OFFSET_SINGLESHOT) { + /* Validate the data before disabling interrupts */ + if (txc->modes & ADJ_ADJTIME) { /* singleshot must not be used with any other mode bits */ - if (txc->modes & ~ADJ_OFFSET_SS_READ) + if (!(txc->modes & ADJ_OFFSET_SINGLESHOT)) return -EINVAL; + if (!(txc->modes & ADJ_OFFSET_READONLY) && + !capable(CAP_SYS_TIME)) + return -EPERM; + } else { + /* In order to modify anything, you gotta be super-user! */ + if (txc->modes && !capable(CAP_SYS_TIME)) + return -EPERM; + + /* if the quartz is off by more than 10% something is VERY wrong! */ + if (txc->modes & ADJ_TICK && + (txc->tick < 900000/USER_HZ || + txc->tick > 1100000/USER_HZ)) + return -EINVAL; + + if (txc->modes & ADJ_STATUS && time_state != TIME_OK) + hrtimer_cancel(&leap_timer); } - /* if the quartz is off by more than 10% something is VERY wrong ! */ - if (txc->modes & ADJ_TICK) - if (txc->tick < 900000/USER_HZ || - txc->tick > 1100000/USER_HZ) - return -EINVAL; - - if (time_state != TIME_OK && txc->modes & ADJ_STATUS) - hrtimer_cancel(&leap_timer); getnstimeofday(&ts); write_seqlock_irq(&xtime_lock); - /* Save for later - semantics of adjtime is to return old value */ - save_adjust = time_adjust; - /* If there are input parameters, then process them */ + if (txc->modes & ADJ_ADJTIME) { + long save_adjust = time_adjust; + + if (!(txc->modes & ADJ_OFFSET_READONLY)) { + /* adjtime() is independent from ntp_adjtime() */ + time_adjust = txc->offset; + ntp_update_frequency(); + } + txc->offset = save_adjust; + goto adj_done; + } if (txc->modes) { + long sec; + if (txc->modes & ADJ_STATUS) { if ((time_status & STA_PLL) && !(txc->status & STA_PLL)) { @@ -375,13 +387,8 @@ int do_adjtimex(struct timex *txc) if (txc->modes & ADJ_TAI && txc->constant > 0) time_tai = txc->constant; - if (txc->modes & ADJ_OFFSET) { - if (txc->modes == ADJ_OFFSET_SINGLESHOT) - /* adjtime() is independent from ntp_adjtime() */ - time_adjust = txc->offset; - else - ntp_update_offset(txc->offset); - } + if (txc->modes & ADJ_OFFSET) + ntp_update_offset(txc->offset); if (txc->modes & ADJ_TICK) tick_usec = txc->tick; @@ -389,19 +396,16 @@ int do_adjtimex(struct timex *txc) ntp_update_frequency(); } + txc->offset = shift_right(time_offset * NTP_INTERVAL_FREQ, + NTP_SCALE_SHIFT); + if (!(time_status & STA_NANO)) + txc->offset /= NSEC_PER_USEC; + +adj_done: result = time_state; /* mostly `TIME_OK' */ if (time_status & (STA_UNSYNC|STA_CLOCKERR)) result = TIME_ERROR; - if ((txc->modes == ADJ_OFFSET_SINGLESHOT) || - (txc->modes == ADJ_OFFSET_SS_READ)) - txc->offset = save_adjust; - else { - txc->offset = shift_right(time_offset * NTP_INTERVAL_FREQ, - NTP_SCALE_SHIFT); - if (!(time_status & STA_NANO)) - txc->offset /= NSEC_PER_USEC; - } txc->freq = shift_right((s32)(time_freq >> PPM_SCALE_INV_SHIFT) * (s64)PPM_SCALE_INV, NTP_SCALE_SHIFT); -- cgit v1.2.3 From f06febc96ba8e0af80bcc3eaec0a109e88275fac Mon Sep 17 00:00:00 2001 From: Frank Mayhar Date: Fri, 12 Sep 2008 09:54:39 -0700 Subject: 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 Cc: Roland McGrath Cc: Alexey Dobriyan Cc: Andrew Morton Signed-off-by: Ingo Molnar --- fs/binfmt_elf.c | 19 +- fs/proc/array.c | 8 +- include/linux/posix-timers.h | 2 + include/linux/sched.h | 257 +++++++++++++++++++++-- include/linux/time.h | 3 + kernel/compat.c | 53 ++--- kernel/exit.c | 19 +- kernel/fork.c | 88 ++++---- kernel/itimer.c | 33 +-- kernel/posix-cpu-timers.c | 471 +++++++++++++++++++++++-------------------- kernel/sched.c | 53 ++++- kernel/sched_fair.c | 1 + kernel/sched_rt.c | 4 +- kernel/signal.c | 8 +- kernel/sys.c | 75 +++---- security/selinux/hooks.c | 9 +- 16 files changed, 677 insertions(+), 426 deletions(-) diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c index 655ed8d30a86..a8635f637038 100644 --- a/fs/binfmt_elf.c +++ b/fs/binfmt_elf.c @@ -1333,20 +1333,15 @@ static void fill_prstatus(struct elf_prstatus *prstatus, prstatus->pr_pgrp = task_pgrp_vnr(p); prstatus->pr_sid = task_session_vnr(p); if (thread_group_leader(p)) { + struct task_cputime cputime; + /* - * This is the record for the group leader. Add in the - * cumulative times of previous dead threads. This total - * won't include the time of each live thread whose state - * is included in the core dump. The final total reported - * to our parent process when it calls wait4 will include - * those sums as well as the little bit more time it takes - * this and each other thread to finish dying after the - * core dump synchronization phase. + * This is the record for the group leader. It shows the + * group-wide total, not its individual thread total. */ - cputime_to_timeval(cputime_add(p->utime, p->signal->utime), - &prstatus->pr_utime); - cputime_to_timeval(cputime_add(p->stime, p->signal->stime), - &prstatus->pr_stime); + thread_group_cputime(p, &cputime); + cputime_to_timeval(cputime.utime, &prstatus->pr_utime); + cputime_to_timeval(cputime.stime, &prstatus->pr_stime); } else { cputime_to_timeval(p->utime, &prstatus->pr_utime); cputime_to_timeval(p->stime, &prstatus->pr_stime); diff --git a/fs/proc/array.c b/fs/proc/array.c index 71c9be59c9c2..933953c4e407 100644 --- a/fs/proc/array.c +++ b/fs/proc/array.c @@ -395,20 +395,20 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns, /* add up live thread stats at the group level */ if (whole) { + struct task_cputime cputime; struct task_struct *t = task; do { min_flt += t->min_flt; maj_flt += t->maj_flt; - utime = cputime_add(utime, task_utime(t)); - stime = cputime_add(stime, task_stime(t)); gtime = cputime_add(gtime, task_gtime(t)); t = next_thread(t); } while (t != task); min_flt += sig->min_flt; maj_flt += sig->maj_flt; - utime = cputime_add(utime, sig->utime); - stime = cputime_add(stime, sig->stime); + thread_group_cputime(task, &cputime); + utime = cputime.utime; + stime = cputime.stime; gtime = cputime_add(gtime, sig->gtime); } diff --git a/include/linux/posix-timers.h b/include/linux/posix-timers.h index a7dd38f30ade..f9d8e9e94e9b 100644 --- a/include/linux/posix-timers.h +++ b/include/linux/posix-timers.h @@ -115,4 +115,6 @@ void set_process_cpu_timer(struct task_struct *task, unsigned int clock_idx, long clock_nanosleep_restart(struct restart_block *restart_block); +void update_rlimit_cpu(unsigned long rlim_new); + #endif diff --git a/include/linux/sched.h b/include/linux/sched.h index 3d9120c5ad15..26d7a5f2d0ba 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -425,6 +425,45 @@ struct pacct_struct { unsigned long ac_minflt, ac_majflt; }; +/** + * struct task_cputime - collected CPU time counts + * @utime: time spent in user mode, in &cputime_t units + * @stime: time spent in kernel mode, in &cputime_t units + * @sum_exec_runtime: total time spent on the CPU, in nanoseconds + * + * This structure groups together three kinds of CPU time that are + * tracked for threads and thread groups. Most things considering + * CPU time want to group these counts together and treat all three + * of them in parallel. + */ +struct task_cputime { + cputime_t utime; + cputime_t stime; + unsigned long long sum_exec_runtime; +}; +/* Alternate field names when used to cache expirations. */ +#define prof_exp stime +#define virt_exp utime +#define sched_exp sum_exec_runtime + +/** + * struct thread_group_cputime - thread group interval timer counts + * @totals: thread group interval timers; substructure for + * uniprocessor kernel, per-cpu for SMP kernel. + * + * This structure contains the version of task_cputime, above, that is + * used for thread group CPU clock calculations. + */ +#ifdef CONFIG_SMP +struct thread_group_cputime { + struct task_cputime *totals; +}; +#else +struct thread_group_cputime { + struct task_cputime totals; +}; +#endif + /* * NOTE! "signal_struct" does not have it's own * locking, because a shared signal_struct always @@ -470,6 +509,17 @@ struct signal_struct { cputime_t it_prof_expires, it_virt_expires; cputime_t it_prof_incr, it_virt_incr; + /* + * Thread group totals for process CPU clocks. + * See thread_group_cputime(), et al, for details. + */ + struct thread_group_cputime cputime; + + /* Earliest-expiration cache. */ + struct task_cputime cputime_expires; + + struct list_head cpu_timers[3]; + /* job control IDs */ /* @@ -500,7 +550,7 @@ struct signal_struct { * Live threads maintain their own counters and add to these * in __exit_signal, except for the group leader. */ - cputime_t utime, stime, cutime, cstime; + cputime_t cutime, cstime; cputime_t gtime; cputime_t cgtime; unsigned long nvcsw, nivcsw, cnvcsw, cnivcsw; @@ -508,14 +558,6 @@ struct signal_struct { unsigned long inblock, oublock, cinblock, coublock; struct task_io_accounting ioac; - /* - * Cumulative ns of scheduled CPU time for dead threads in the - * group, not including a zombie group leader. (This only differs - * from jiffies_to_ns(utime + stime) if sched_clock uses something - * other than jiffies.) - */ - unsigned long long sum_sched_runtime; - /* * We don't bother to synchronize most readers of this at all, * because there is no reader checking a limit that actually needs @@ -527,8 +569,6 @@ struct signal_struct { */ struct rlimit rlim[RLIM_NLIMITS]; - struct list_head cpu_timers[3]; - /* keep the process-shared keyrings here so that they do the right * thing in threads created with CLONE_THREAD */ #ifdef CONFIG_KEYS @@ -1134,8 +1174,7 @@ struct task_struct { /* mm fault and swap info: this can arguably be seen as either mm-specific or thread-specific */ unsigned long min_flt, maj_flt; - cputime_t it_prof_expires, it_virt_expires; - unsigned long long it_sched_expires; + struct task_cputime cputime_expires; struct list_head cpu_timers[3]; /* process credentials */ @@ -1585,6 +1624,7 @@ extern unsigned long long cpu_clock(int cpu); extern unsigned long long task_sched_runtime(struct task_struct *task); +extern unsigned long long thread_group_sched_runtime(struct task_struct *task); /* sched_exec is called by processes performing an exec */ #ifdef CONFIG_SMP @@ -2081,6 +2121,197 @@ static inline int spin_needbreak(spinlock_t *lock) #endif } +/* + * Thread group CPU time accounting. + */ +#ifdef CONFIG_SMP + +extern int thread_group_cputime_alloc_smp(struct task_struct *); +extern void thread_group_cputime_smp(struct task_struct *, struct task_cputime *); + +static inline void thread_group_cputime_init(struct signal_struct *sig) +{ + sig->cputime.totals = NULL; +} + +static inline int thread_group_cputime_clone_thread(struct task_struct *curr, + struct task_struct *new) +{ + if (curr->signal->cputime.totals) + return 0; + return thread_group_cputime_alloc_smp(curr); +} + +static inline void thread_group_cputime_free(struct signal_struct *sig) +{ + free_percpu(sig->cputime.totals); +} + +/** + * thread_group_cputime - Sum the thread group time fields across all CPUs. + * + * This is a wrapper for the real routine, thread_group_cputime_smp(). See + * that routine for details. + */ +static inline void thread_group_cputime( + struct task_struct *tsk, + struct task_cputime *times) +{ + thread_group_cputime_smp(tsk, times); +} + +/** + * thread_group_cputime_account_user - Maintain utime for a thread group. + * + * @tgtimes: Pointer to thread_group_cputime structure. + * @cputime: Time value by which to increment the utime field of that + * structure. + * + * If thread group time is being maintained, get the structure for the + * running CPU and update the utime field there. + */ +static inline void thread_group_cputime_account_user( + struct thread_group_cputime *tgtimes, + cputime_t cputime) +{ + if (tgtimes->totals) { + struct task_cputime *times; + + times = per_cpu_ptr(tgtimes->totals, get_cpu()); + times->utime = cputime_add(times->utime, cputime); + put_cpu_no_resched(); + } +} + +/** + * thread_group_cputime_account_system - Maintain stime for a thread group. + * + * @tgtimes: Pointer to thread_group_cputime structure. + * @cputime: Time value by which to increment the stime field of that + * structure. + * + * If thread group time is being maintained, get the structure for the + * running CPU and update the stime field there. + */ +static inline void thread_group_cputime_account_system( + struct thread_group_cputime *tgtimes, + cputime_t cputime) +{ + if (tgtimes->totals) { + struct task_cputime *times; + + times = per_cpu_ptr(tgtimes->totals, get_cpu()); + times->stime = cputime_add(times->stime, cputime); + put_cpu_no_resched(); + } +} + +/** + * thread_group_cputime_account_exec_runtime - Maintain exec runtime for a + * thread group. + * + * @tgtimes: Pointer to thread_group_cputime structure. + * @ns: Time value by which to increment the sum_exec_runtime field + * of that structure. + * + * If thread group time is being maintained, get the structure for the + * running CPU and update the sum_exec_runtime field there. + */ +static inline void thread_group_cputime_account_exec_runtime( + struct thread_group_cputime *tgtimes, + unsigned long long ns) +{ + if (tgtimes->totals) { + struct task_cputime *times; + + times = per_cpu_ptr(tgtimes->totals, get_cpu()); + times->sum_exec_runtime += ns; + put_cpu_no_resched(); + } +} + +#else /* CONFIG_SMP */ + +static inline void thread_group_cputime_init(struct signal_struct *sig) +{ + sig->cputime.totals.utime = cputime_zero; + sig->cputime.totals.stime = cputime_zero; + sig->cputime.totals.sum_exec_runtime = 0; +} + +static inline int thread_group_cputime_alloc(struct task_struct *tsk) +{ + return 0; +} + +static inline void thread_group_cputime_free(struct signal_struct *sig) +{ +} + +static inline int thread_group_cputime_clone_thread(struct task_struct *curr, + struct task_struct *tsk) +{ +} + +static inline void thread_group_cputime(struct task_struct *tsk, + struct task_cputime *cputime) +{ + *cputime = tsk->signal->cputime.totals; +} + +static inline void thread_group_cputime_account_user( + struct thread_group_cputime *tgtimes, + cputime_t cputime) +{ + tgtimes->totals->utime = cputime_add(tgtimes->totals->utime, cputime); +} + +static inline void thread_group_cputime_account_system( + struct thread_group_cputime *tgtimes, + cputime_t cputime) +{ + tgtimes->totals->stime = cputime_add(tgtimes->totals->stime, cputime); +} + +static inline void thread_group_cputime_account_exec_runtime( + struct thread_group_cputime *tgtimes, + unsigned long long ns) +{ + tgtimes->totals->sum_exec_runtime += ns; +} + +#endif /* CONFIG_SMP */ + +static inline void account_group_user_time(struct task_struct *tsk, + cputime_t cputime) +{ + struct signal_struct *sig; + + sig = tsk->signal; + if (likely(sig)) + thread_group_cputime_account_user(&sig->cputime, cputime); +} + +static inline void account_group_system_time(struct task_struct *tsk, + cputime_t cputime) +{ + struct signal_struct *sig; + + sig = tsk->signal; + if (likely(sig)) + thread_group_cputime_account_system(&sig->cputime, cputime); +} + +static inline void account_group_exec_runtime(struct task_struct *tsk, + unsigned long long ns) +{ + struct signal_struct *sig; + + sig = tsk->signal; + if (likely(sig)) + thread_group_cputime_account_exec_runtime(&sig->cputime, ns); +} + /* * Reevaluate whether the task has signals pending delivery. * Wake the task if so. diff --git a/include/linux/time.h b/include/linux/time.h index e15206a7e82e..1b70b3c293e9 100644 --- a/include/linux/time.h +++ b/include/linux/time.h @@ -125,6 +125,9 @@ extern int timekeeping_valid_for_hres(void); extern void update_wall_time(void); extern void update_xtime_cache(u64 nsec); +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 diff --git a/kernel/compat.c b/kernel/compat.c index 32c254a8ab9a..72650e39b3e6 100644 --- a/kernel/compat.c +++ b/kernel/compat.c @@ -23,6 +23,7 @@ #include #include #include +#include #include @@ -150,49 +151,23 @@ asmlinkage long compat_sys_setitimer(int which, return 0; } +static compat_clock_t clock_t_to_compat_clock_t(clock_t x) +{ + return compat_jiffies_to_clock_t(clock_t_to_jiffies(x)); +} + asmlinkage long compat_sys_times(struct compat_tms __user *tbuf) { - /* - * In the SMP world we might just be unlucky and have one of - * the times increment as we use it. Since the value is an - * atomically safe type this is just fine. Conceptually its - * as if the syscall took an instant longer to occur. - */ if (tbuf) { + struct tms tms; struct compat_tms tmp; - struct task_struct *tsk = current; - struct task_struct *t; - cputime_t utime, stime, cutime, cstime; - - read_lock(&tasklist_lock); - utime = tsk->signal->utime; - stime = tsk->signal->stime; - t = tsk; - do { - utime = cputime_add(utime, t->utime); - stime = cputime_add(stime, t->stime); - t = next_thread(t); - } while (t != tsk); - - /* - * While we have tasklist_lock read-locked, no dying thread - * can be updating current->signal->[us]time. Instead, - * we got their counts included in the live thread loop. - * However, another thread can come in right now and - * do a wait call that updates current->signal->c[us]time. - * To make sure we always see that pair updated atomically, - * we take the siglock around fetching them. - */ - spin_lock_irq(&tsk->sighand->siglock); - cutime = tsk->signal->cutime; - cstime = tsk->signal->cstime; - spin_unlock_irq(&tsk->sighand->siglock); - read_unlock(&tasklist_lock); - - tmp.tms_utime = compat_jiffies_to_clock_t(cputime_to_jiffies(utime)); - tmp.tms_stime = compat_jiffies_to_clock_t(cputime_to_jiffies(stime)); - tmp.tms_cutime = compat_jiffies_to_clock_t(cputime_to_jiffies(cutime)); - tmp.tms_cstime = compat_jiffies_to_clock_t(cputime_to_jiffies(cstime)); + + do_sys_times(&tms); + /* Convert our struct tms to the compat version. */ + tmp.tms_utime = clock_t_to_compat_clock_t(tms.tms_utime); + tmp.tms_stime = clock_t_to_compat_clock_t(tms.tms_stime); + tmp.tms_cutime = clock_t_to_compat_clock_t(tms.tms_cutime); + tmp.tms_cstime = clock_t_to_compat_clock_t(tms.tms_cstime); if (copy_to_user(tbuf, &tmp, sizeof(tmp))) return -EFAULT; } diff --git a/kernel/exit.c b/kernel/exit.c index 16395644a98f..40036ac04271 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -112,8 +112,6 @@ static void __exit_signal(struct task_struct *tsk) * We won't ever get here for the group leader, since it * will have been the last reference on the signal_struct. */ - sig->utime = cputime_add(sig->utime, task_utime(tsk)); - sig->stime = cputime_add(sig->stime, task_stime(tsk)); sig->gtime = cputime_add(sig->gtime, task_gtime(tsk)); sig->min_flt += tsk->min_flt; sig->maj_flt += tsk->maj_flt; @@ -122,7 +120,6 @@ static void __exit_signal(struct task_struct *tsk) sig->inblock += task_io_get_inblock(tsk); sig->oublock += task_io_get_oublock(tsk); task_io_accounting_add(&sig->ioac, &tsk->ioac); - sig->sum_sched_runtime += tsk->se.sum_exec_runtime; sig = NULL; /* Marker for below. */ } @@ -1294,6 +1291,7 @@ static int wait_task_zombie(struct task_struct *p, int options, if (likely(!traced)) { struct signal_struct *psig; struct signal_struct *sig; + struct task_cputime cputime; /* * The resource counters for the group leader are in its @@ -1309,20 +1307,23 @@ static int wait_task_zombie(struct task_struct *p, int options, * need to protect the access to p->parent->signal fields, * as other threads in the parent group can be right * here reaping other children at the same time. + * + * We use thread_group_cputime() to get times for the thread + * group, which consolidates times for all threads in the + * group including the group leader. */ spin_lock_irq(&p->parent->sighand->siglock); psig = p->parent->signal; sig = p->signal; + thread_group_cputime(p, &cputime); psig->cutime = cputime_add(psig->cutime, - cputime_add(p->utime, - cputime_add(sig->utime, - sig->cutime))); + cputime_add(cputime.utime, + sig->cutime)); psig->cstime = cputime_add(psig->cstime, - cputime_add(p->stime, - cputime_add(sig->stime, - sig->cstime))); + cputime_add(cputime.stime, + sig->cstime)); psig->cgtime = cputime_add(psig->cgtime, cputime_add(p->gtime, diff --git a/kernel/fork.c b/kernel/fork.c index 7ce2ebe84796..a8ac2efb8e30 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -759,15 +759,44 @@ void __cleanup_sighand(struct sighand_struct *sighand) kmem_cache_free(sighand_cachep, sighand); } + +/* + * Initialize POSIX timer handling for a thread group. + */ +static void posix_cpu_timers_init_group(struct signal_struct *sig) +{ + /* Thread group counters. */ + thread_group_cputime_init(sig); + + /* Expiration times and increments. */ + sig->it_virt_expires = cputime_zero; + sig->it_virt_incr = cputime_zero; + sig->it_prof_expires = cputime_zero; + sig->it_prof_incr = cputime_zero; + + /* Cached expiration times. */ + sig->cputime_expires.prof_exp = cputime_zero; + sig->cputime_expires.virt_exp = cputime_zero; + sig->cputime_expires.sched_exp = 0; + + /* The timer lists. */ + INIT_LIST_HEAD(&sig->cpu_timers[0]); + INIT_LIST_HEAD(&sig->cpu_timers[1]); + INIT_LIST_HEAD(&sig->cpu_timers[2]); +} + static int copy_signal(unsigned long clone_flags, struct task_struct *tsk) { struct signal_struct *sig; int ret; if (clone_flags & CLONE_THREAD) { - atomic_inc(¤t->signal->count); - atomic_inc(¤t->signal->live); - return 0; + ret = thread_group_cputime_clone_thread(current, tsk); + if (likely(!ret)) { + atomic_inc(¤t->signal->count); + atomic_inc(¤t->signal->live); + } + return ret; } sig = kmem_cache_alloc(signal_cachep, GFP_KERNEL); tsk->signal = sig; @@ -795,15 +824,10 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk) sig->it_real_incr.tv64 = 0; sig->real_timer.function = it_real_fn; - sig->it_virt_expires = cputime_zero; - sig->it_virt_incr = cputime_zero; - sig->it_prof_expires = cputime_zero; - sig->it_prof_incr = cputime_zero; - sig->leader = 0; /* session leadership doesn't inherit */ sig->tty_old_pgrp = NULL; - sig->utime = sig->stime = sig->cutime = sig->cstime = cputime_zero; + sig->cutime = sig->cstime = cputime_zero; sig->gtime = cputime_zero; sig->cgtime = cputime_zero; sig->nvcsw = sig->nivcsw = sig->cnvcsw = sig->cnivcsw = 0; @@ -820,14 +844,8 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk) memcpy(sig->rlim, current->signal->rlim, sizeof sig->rlim); task_unlock(current->group_leader); - if (sig->rlim[RLIMIT_CPU].rlim_cur != RLIM_INFINITY) { - /* - * New sole thread in the process gets an expiry time - * of the whole CPU time limit. - */ - tsk->it_prof_expires = - secs_to_cputime(sig->rlim[RLIMIT_CPU].rlim_cur); - } + posix_cpu_timers_init_group(sig); + acct_init_pacct(&sig->pacct); tty_audit_fork(sig); @@ -837,6 +855,7 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk) void __cleanup_signal(struct signal_struct *sig) { + thread_group_cputime_free(sig); exit_thread_group_keys(sig); kmem_cache_free(signal_cachep, sig); } @@ -885,6 +904,19 @@ void mm_init_owner(struct mm_struct *mm, struct task_struct *p) } #endif /* CONFIG_MM_OWNER */ +/* + * Initialize POSIX timer handling for a single task. + */ +static void posix_cpu_timers_init(struct task_struct *tsk) +{ + tsk->cputime_expires.prof_exp = cputime_zero; + tsk->cputime_expires.virt_exp = cputime_zero; + tsk->cputime_expires.sched_exp = 0; + INIT_LIST_HEAD(&tsk->cpu_timers[0]); + INIT_LIST_HEAD(&tsk->cpu_timers[1]); + INIT_LIST_HEAD(&tsk->cpu_timers[2]); +} + /* * This creates a new process as a copy of the old one, * but does not actually start it yet. @@ -995,12 +1027,7 @@ static struct task_struct *copy_process(unsigned long clone_flags, task_io_accounting_init(&p->ioac); acct_clear_integrals(p); - p->it_virt_expires = cputime_zero; - p->it_prof_expires = cputime_zero; - p->it_sched_expires = 0; - INIT_LIST_HEAD(&p->cpu_timers[0]); - INIT_LIST_HEAD(&p->cpu_timers[1]); - INIT_LIST_HEAD(&p->cpu_timers[2]); + posix_cpu_timers_init(p); p->lock_depth = -1; /* -1 = no lock */ do_posix_clock_monotonic_gettime(&p->start_time); @@ -1201,21 +1228,6 @@ static struct task_struct *copy_process(unsigned long clone_flags, if (clone_flags & CLONE_THREAD) { p->group_leader = current->group_leader; list_add_tail_rcu(&p->thread_group, &p->group_leader->thread_group); - - if (!cputime_eq(current->signal->it_virt_expires, - cputime_zero) || - !cputime_eq(current->signal->it_prof_expires, - cputime_zero) || - current->signal->rlim[RLIMIT_CPU].rlim_cur != RLIM_INFINITY || - !list_empty(¤t->signal->cpu_timers[0]) || - !list_empty(¤t->signal->cpu_timers[1]) || - !list_empty(¤t->signal->cpu_timers[2])) { - /* - * Have child wake up on its first tick to check - * for process CPU timers. - */ - p->it_prof_expires = jiffies_to_cputime(1); - } } if (likely(p->pid)) { diff --git a/kernel/itimer.c b/kernel/itimer.c index ab982747d9bd..db7c358b9a02 100644 --- a/kernel/itimer.c +++ b/kernel/itimer.c @@ -55,17 +55,15 @@ int do_getitimer(int which, struct itimerval *value) spin_unlock_irq(&tsk->sighand->siglock); break; case ITIMER_VIRTUAL: - read_lock(&tasklist_lock); spin_lock_irq(&tsk->sighand->siglock); cval = tsk->signal->it_virt_expires; cinterval = tsk->signal->it_virt_incr; if (!cputime_eq(cval, cputime_zero)) { - struct task_struct *t = tsk; - cputime_t utime = tsk->signal->utime; - do { - utime = cputime_add(utime, t->utime); - t = next_thread(t); - } while (t != tsk); + struct task_cputime cputime; + cputime_t utime; + + thread_group_cputime(tsk, &cputime); + utime = cputime.utime; if (cputime_le(cval, utime)) { /* about to fire */ cval = jiffies_to_cputime(1); } else { @@ -73,25 +71,19 @@ int do_getitimer(int which, struct itimerval *value) } } spin_unlock_irq(&tsk->sighand->siglock); - read_unlock(&tasklist_lock); cputime_to_timeval(cval, &value->it_value); cputime_to_timeval(cinterval, &value->it_interval); break; case ITIMER_PROF: - read_lock(&tasklist_lock); spin_lock_irq(&tsk->sighand->siglock); cval = tsk->signal->it_prof_expires; cinterval = tsk->signal->it_prof_incr; if (!cputime_eq(cval, cputime_zero)) { - struct task_struct *t = tsk; - cputime_t ptime = cputime_add(tsk->signal->utime, - tsk->signal->stime); - do { - ptime = cputime_add(ptime, - cputime_add(t->utime, - t->stime)); - t = next_thread(t); - } while (t != tsk); + struct task_cputime times; + cputime_t ptime; + + thread_group_cputime(tsk, ×); + ptime = cputime_add(times.utime, times.stime); if (cputime_le(cval, ptime)) { /* about to fire */ cval = jiffies_to_cputime(1); } else { @@ -99,7 +91,6 @@ int do_getitimer(int which, struct itimerval *value) } } spin_unlock_irq(&tsk->sighand->siglock); - read_unlock(&tasklist_lock); cputime_to_timeval(cval, &value->it_value); cputime_to_timeval(cinterval, &value->it_interval); break; @@ -185,7 +176,6 @@ again: case ITIMER_VIRTUAL: nval = timeval_to_cputime(&value->it_value); ninterval = timeval_to_cputime(&value->it_interval); - read_lock(&tasklist_lock); spin_lock_irq(&tsk->sighand->siglock); cval = tsk->signal->it_virt_expires; cinterval = tsk->signal->it_virt_incr; @@ -200,7 +190,6 @@ again: tsk->signal->it_virt_expires = nval; tsk->signal->it_virt_incr = ninterval; spin_unlock_irq(&tsk->sighand->siglock); - read_unlock(&tasklist_lock); if (ovalue) { cputime_to_timeval(cval, &ovalue->it_value); cputime_to_timeval(cinterval, &ovalue->it_interval); @@ -209,7 +198,6 @@ again: case ITIMER_PROF: nval = timeval_to_cputime(&value->it_value); ninterval = timeval_to_cputime(&value->it_interval); - read_lock(&tasklist_lock); spin_lock_irq(&tsk->sighand->siglock); cval = tsk->signal->it_prof_expires; cinterval = tsk->signal->it_prof_incr; @@ -224,7 +212,6 @@ again: tsk->signal->it_prof_expires = nval; tsk->signal->it_prof_incr = ninterval; spin_unlock_irq(&tsk->sighand->siglock); - read_unlock(&tasklist_lock); if (ovalue) { cputime_to_timeval(cval, &ovalue->it_value); cputime_to_timeval(cinterval, &ovalue->it_interval); diff --git a/kernel/posix-cpu-timers.c b/kernel/posix-cpu-timers.c index c42a03aef36f..dba1c334c3e8 100644 --- a/kernel/posix-cpu-timers.c +++ b/kernel/posix-cpu-timers.c @@ -8,6 +8,99 @@ #include #include +#ifdef CONFIG_SMP +/* + * Allocate the thread_group_cputime structure appropriately for SMP kernels + * and fill in the current values of the fields. Called from copy_signal() + * via thread_group_cputime_clone_thread() when adding a second or subsequent + * thread to a thread group. Assumes interrupts are enabled when called. + */ +int thread_group_cputime_alloc_smp(struct task_struct *tsk) +{ + struct signal_struct *sig = tsk->signal; + struct task_cputime *cputime; + + /* + * If we have multiple threads and we don't already have a + * per-CPU task_cputime struct, allocate one and fill it in with + * the times accumulated so far. + */ + if (sig->cputime.totals) + return 0; + cputime = alloc_percpu(struct task_cputime); + if (cputime == NULL) + return -ENOMEM; + read_lock(&tasklist_lock); + spin_lock_irq(&tsk->sighand->siglock); + if (sig->cputime.totals) { + spin_unlock_irq(&tsk->sighand->siglock); + read_unlock(&tasklist_lock); + free_percpu(cputime); + return 0; + } + sig->cputime.totals = cputime; + cputime = per_cpu_ptr(sig->cputime.totals, get_cpu()); + cputime->utime = tsk->utime; + cputime->stime = tsk->stime; + cputime->sum_exec_runtime = tsk->se.sum_exec_runtime; + put_cpu_no_resched(); + spin_unlock_irq(&tsk->sighand->siglock); + read_unlock(&tasklist_lock); + return 0; +} + +/** + * thread_group_cputime_smp - Sum the thread group time fields across all CPUs. + * + * @tsk: The task we use to identify the thread group. + * @times: task_cputime structure in which we return the summed fields. + * + * Walk the list of CPUs to sum the per-CPU time fields in the thread group + * time structure. + */ +void thread_group_cputime_smp( + struct task_struct *tsk, + struct task_cputime *times) +{ + struct signal_struct *sig; + int i; + struct task_cputime *tot; + + sig = tsk->signal; + if (unlikely(!sig) || !sig->cputime.totals) { + times->utime = tsk->utime; + times->stime = tsk->stime; + times->sum_exec_runtime = tsk->se.sum_exec_runtime; + return; + } + times->stime = times->utime = cputime_zero; + times->sum_exec_runtime = 0; + for_each_possible_cpu(i) { + tot = per_cpu_ptr(tsk->signal->cputime.totals, i); + times->utime = cputime_add(times->utime, tot->utime); + times->stime = cputime_add(times->stime, tot->stime); + times->sum_exec_runtime += tot->sum_exec_runtime; + } +} + +#endif /* CONFIG_SMP */ + +/* + * Called after updating RLIMIT_CPU to set timer expiration if necessary. + */ +void update_rlimit_cpu(unsigned long rlim_new) +{ + cputime_t cputime; + + cputime = secs_to_cputime(rlim_new); + if (cputime_eq(current->signal->it_prof_expires, cputime_zero) || + cputime_lt(current->signal->it_prof_expires, cputime)) { + spin_lock_irq(¤t->sighand->siglock); + set_process_cpu_timer(current, CPUCLOCK_PROF, &cputime, NULL); + spin_unlock_irq(¤t->sighand->siglock); + } +} + static int check_clock(const clockid_t which_clock) { int error = 0; @@ -158,10 +251,6 @@ static inline cputime_t virt_ticks(struct task_struct *p) { return p->utime; } -static inline unsigned long long sched_ns(struct task_struct *p) -{ - return task_sched_runtime(p); -} int posix_cpu_clock_getres(const clockid_t which_clock, struct timespec *tp) { @@ -211,7 +300,7 @@ static int cpu_clock_sample(const clockid_t which_clock, struct task_struct *p, cpu->cpu = virt_ticks(p); break; case CPUCLOCK_SCHED: - cpu->sched = sched_ns(p); +