talos-obmc-linux/kernel/posix-cpu-timers.c, branch v3.2

Merge branch 'core-locking-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

2011-10-26T14:17:32+00:00

* 'core-locking-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (27 commits) rtmutex: Add missing rcu_read_unlock() in debug_rt_mutex_print_deadlock() lockdep: Comment all warnings lib: atomic64: Change the type of local lock to raw_spinlock_t locking, lib/atomic64: Annotate atomic64_lock::lock as raw locking, x86, iommu: Annotate qi->q_lock as raw locking, x86, iommu: Annotate irq_2_ir_lock as raw locking, x86, iommu: Annotate iommu->register_lock as raw locking, dma, ipu: Annotate bank_lock as raw locking, ARM: Annotate low level hw locks as raw locking, drivers/dca: Annotate dca_lock as raw locking, powerpc: Annotate uic->lock as raw locking, x86: mce: Annotate cmci_discover_lock as raw locking, ACPI: Annotate c3_lock as raw locking, oprofile: Annotate oprofilefs lock as raw locking, video: Annotate vga console lock as raw locking, latencytop: Annotate latency_lock as raw locking, timer_stats: Annotate table_lock as raw locking, rwsem: Annotate inner lock as raw locking, semaphores: Annotate inner lock as raw locking, sched: Annotate thread_group_cputimer as raw ... Fix up conflicts in kernel/posix-cpu-timers.c manually: making cputimer->cputime a raw lock conflicted with the ABBA fix in commit bcd5cff7216f ("cputimer: Cure lock inversion").

cputimer: Cure lock inversion

2011-10-18T09:36:59+00:00

There's a lock inversion between the cputimer->lock and rq->lock; notably the two callchains involved are: update_rlimit_cpu() sighand->siglock set_process_cpu_timer() cpu_timer_sample_group() thread_group_cputimer() cputimer->lock thread_group_cputime() task_sched_runtime() ->pi_lock rq->lock scheduler_tick() rq->lock task_tick_fair() update_curr() account_group_exec() cputimer->lock Where the first one is enabling a CLOCK_PROCESS_CPUTIME_ID timer, and the second one is keeping up-to-date. This problem was introduced by e8abccb7193 ("posix-cpu-timers: Cure SMP accounting oddities"). Cure the problem by removing the cputimer->lock and rq->lock nesting, this leaves concurrent enablers doing duplicate work, but the time wasted should be on the same order otherwise wasted spinning on the lock and the greater-than assignment filter should ensure we preserve monotonicity. Reported-by: Dave Jones Reported-by: Simon Kirby Signed-off-by: Peter Zijlstra Cc: stable@kernel.org Cc: Linus Torvalds Cc: Martin Schwidefsky Link: http://lkml.kernel.org/r/1318928713.21167.4.camel@twins Signed-off-by: Thomas Gleixner

posix-cpu-timers: Cure SMP wobbles

2011-09-30T12:07:06+00:00

David reported: Attached below is a watered-down version of rt/tst-cpuclock2.c from GLIBC. Just build it with "gcc -o test test.c -lpthread -lrt" or similar. Run it several times, and you will see cases where the main thread will measure a process clock difference before and after the nanosleep which is smaller than the cpu-burner thread's individual thread clock difference. This doesn't make any sense since the cpu-burner thread is part of the top-level process's thread group. I've reproduced this on both x86-64 and sparc64 (using both 32-bit and 64-bit binaries). For example: [davem@boricha build-x86_64-linux]$ ./test process: before(0.001221967) after(0.498624371) diff(497402404) thread: before(0.000081692) after(0.498316431) diff(498234739) self: before(0.001223521) after(0.001240219) diff(16698) [davem@boricha build-x86_64-linux]$ The diff of 'process' should always be >= the diff of 'thread'. I make sure to wrap the 'thread' clock measurements the most tightly around the nanosleep() call, and that the 'process' clock measurements are the outer-most ones. --- #include #include #include #include #include #include #include #include static pthread_barrier_t barrier; static void *chew_cpu(void *arg) { pthread_barrier_wait(&barrier); while (1) __asm__ __volatile__("" : : : "memory"); return NULL; } int main(void) { clockid_t process_clock, my_thread_clock, th_clock; struct timespec process_before, process_after; struct timespec me_before, me_after; struct timespec th_before, th_after; struct timespec sleeptime; unsigned long diff; pthread_t th; int err; err = clock_getcpuclockid(0, &process_clock); if (err) return 1; err = pthread_getcpuclockid(pthread_self(), &my_thread_clock); if (err) return 1; pthread_barrier_init(&barrier, NULL, 2); err = pthread_create(&th, NULL, chew_cpu, NULL); if (err) return 1; err = pthread_getcpuclockid(th, &th_clock); if (err) return 1; pthread_barrier_wait(&barrier); err = clock_gettime(process_clock, &process_before); if (err) return 1; err = clock_gettime(my_thread_clock, &me_before); if (err) return 1; err = clock_gettime(th_clock, &th_before); if (err) return 1; sleeptime.tv_sec = 0; sleeptime.tv_nsec = 500000000; nanosleep(&sleeptime, NULL); err = clock_gettime(th_clock, &th_after); if (err) return 1; err = clock_gettime(my_thread_clock, &me_after); if (err) return 1; err = clock_gettime(process_clock, &process_after); if (err) return 1; diff = process_after.tv_nsec - process_before.tv_nsec; printf("process: before(%lu.%.9lu) after(%lu.%.9lu) diff(%lu)\n", process_before.tv_sec, process_before.tv_nsec, process_after.tv_sec, process_after.tv_nsec, diff); diff = th_after.tv_nsec - th_before.tv_nsec; printf("thread: before(%lu.%.9lu) after(%lu.%.9lu) diff(%lu)\n", th_before.tv_sec, th_before.tv_nsec, th_after.tv_sec, th_after.tv_nsec, diff); diff = me_after.tv_nsec - me_before.tv_nsec; printf("self: before(%lu.%.9lu) after(%lu.%.9lu) diff(%lu)\n", me_before.tv_sec, me_before.tv_nsec, me_after.tv_sec, me_after.tv_nsec, diff); return 0; } This is due to us using p->se.sum_exec_runtime in thread_group_cputime() where we iterate the thread group and sum all data. This does not take time since the last schedule operation (tick or otherwise) into account. We can cure this by using task_sched_runtime() at the cost of having to take locks. This also means we can (and must) do away with thread_group_sched_runtime() since the modified thread_group_cputime() is now more accurate and would deadlock when called from thread_group_sched_runtime(). Aside of that it makes the function safe on 32 bit systems. The old code added t->se.sum_exec_runtime unprotected. sum_exec_runtime is a 64bit value and could be changed on another cpu at the same time. Reported-by: David Miller Signed-off-by: Peter Zijlstra Cc: stable@kernel.org Link: http://lkml.kernel.org/r/1314874459.7945.22.camel@twins Tested-by: David Miller Signed-off-by: Thomas Gleixner

locking, sched: Annotate thread_group_cputimer as raw

2011-09-13T09:11:55+00:00

The thread_group_cputimer lock can be taken in atomic context and therefore cannot be preempted on -rt - annotate it. In mainline this change documents the low level nature of the lock - otherwise there's no functional difference. Lockdep and Sparse checking will work as usual. Signed-off-by: Thomas Gleixner Signed-off-by: Ingo Molnar

hrtimers: Avoid touching inactive timer bases

2011-05-23T11:59:54+00:00

Instead of iterating over all possible timer bases avoid it by marking the active bases in the cpu base. Signed-off-by: Thomas Gleixner Reviewed-by: Peter Zijlstra

Fix common misspellings

2011-03-31T14:26:23+00:00

Fixes generated by 'codespell' and manually reviewed. Signed-off-by: Lucas De Marchi

posix-timers: Cleanup namespace

2011-02-02T14:28:19+00:00

Rename register_posix_clock() to posix_timers_register_clock(). That's what the function really does. As a side effect this cleans up the posix_clock namespace for the upcoming dynamic posix_clock infrastructure. Signed-off-by: Thomas Gleixner Tested-by: Richard Cochran Cc: John Stultz LKML-Reference:

posix-timers: Make posix-cpu-timers functions static

2011-02-02T14:28:17+00:00

All functions are accessed via clock_posix_cpu now. So make them static. Signed-off-by: Thomas Gleixner Acked-by: John Stultz Tested-by: Richard Cochran LKML-Reference: <20110201134419.389755466@linutronix.de>

posix-timers: Convert clock_settime to clockid_to_kclock()

2011-02-02T14:28:14+00:00

Use the new kclock decoding function in clock_settime and cleanup all kclocks which use the default functions. Rename the misnomed common_clock_set() to posix_clock_realtime_set(). Signed-off-by: Thomas Gleixner Acked-by: John Stultz Tested-by: Richard Cochran LKML-Reference: <20110201134418.518851246@linutronix.de>

posix-cpu-timers: Remove the stub nanosleep functions

2011-02-02T14:28:14+00:00

CLOCK_THREAD_CPUTIME_ID implements stub functions for nanosleep and nanosleep_restart, which return -EINVAL. That return value is wrong. The correct return value is -ENOTSUP. Remove the stubs and let the new dispatch code return the correct error code. Signed-off-by: Thomas Gleixner Acked-by: John Stultz Tested-by: Richard Cochran LKML-Reference: <20110201134418.422446502@linutronix.de>