Dear RT Folks, I'm pleased to announce the 3.2.22-rt35 stable release. You can get this release via the git tree at: git://git.kernel.org/pub/scm/linux/kernel/git/rt/linux-stable-rt.git Head SHA1: 852c3bd6c35aa3718de57c87f1a3bcd4dc69af3d Or to build 3.2.22-rt35 directly, the following patches should be applied: http://www.kernel.org/pub/linux/kernel/v3.x/linux-3.2.tar.xz http://www.kernel.org/pub/linux/kernel/v3.x/patch-3.2.22.xz http://www.kernel.org/pub/linux/kernel/projects/rt/3.2/patch-3.2.22-rt35.patch.xz You can also build from 3.2.22-rt34 by applying the incremental patch: http://www.kernel.org/pub/linux/kernel/projects/rt/3.2/incr/patch-3.2.22-rt34-rt35.patch.xz Note, I've upgraded to Evolution 3.4.3 on my Debian (testing) system, and I've had nothing but trouble. It locks up and it no longer accesses the address book. This has caused some issues in my work flow as I use my address book and Evolution in the RT release process :-p Enjoy, -- Steve Changes from 3.2.22-rt34: --- Carsten Emde (4): Latency histogramms: Cope with backwards running local trace clock Latency histograms: Adjust timer, if already elapsed when programmed Disable RT_GROUP_SCHED in PREEMPT_RT_FULL Latency histograms: Detect another yet overlooked sharedprio condition Mike Galbraith (1): fs, jbd: pull your plug when waiting for space Steven Rostedt (1): Linux 3.2.22-rt35 Thomas Gleixner (1): slab: Prevent local lock deadlock Yong Zhang (1): perf: Make swevent hrtimer run in irq instead of softirq ---- fs/jbd/checkpoint.c | 2 ++ include/linux/hrtimer.h | 3 ++ include/linux/sched.h | 2 +- init/Kconfig | 1 + kernel/events/core.c | 1 + kernel/hrtimer.c | 16 ++++++++-- kernel/trace/latency_hist.c | 74 +++++++++++++++++++++++-------------------- localversion-rt | 2 +- mm/slab.c | 26 ++++++++++++--- 9 files changed, 85 insertions(+), 42 deletions(-) --------------------------- diff --git a/fs/jbd/checkpoint.c b/fs/jbd/checkpoint.c index 5c93ffc..ddbd223 100644 --- a/fs/jbd/checkpoint.c +++ b/fs/jbd/checkpoint.c @@ -129,6 +129,8 @@ void __log_wait_for_space(journal_t *journal) if (journal->j_flags & JFS_ABORT) return; spin_unlock(&journal->j_state_lock); + if (current->plug) + io_schedule(); mutex_lock(&journal->j_checkpoint_mutex); /* diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h index 0e37086..7408760 100644 --- a/include/linux/hrtimer.h +++ b/include/linux/hrtimer.h @@ -113,6 +113,9 @@ struct hrtimer { unsigned long state; struct list_head cb_entry; int irqsafe; +#ifdef CONFIG_MISSED_TIMER_OFFSETS_HIST + ktime_t praecox; +#endif #ifdef CONFIG_TIMER_STATS int start_pid; void *start_site; diff --git a/include/linux/sched.h b/include/linux/sched.h index 1f6b11a..0174e3a 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1585,7 +1585,7 @@ struct task_struct { #ifdef CONFIG_WAKEUP_LATENCY_HIST u64 preempt_timestamp_hist; #ifdef CONFIG_MISSED_TIMER_OFFSETS_HIST - unsigned long timer_offset; + long timer_offset; #endif #endif #endif /* CONFIG_TRACING */ diff --git a/init/Kconfig b/init/Kconfig index dbc82d0..720c182 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -731,6 +731,7 @@ config RT_GROUP_SCHED bool "Group scheduling for SCHED_RR/FIFO" depends on EXPERIMENTAL depends on CGROUP_SCHED + depends on !PREEMPT_RT_FULL default n help This feature lets you explicitly allocate real CPU bandwidth diff --git a/kernel/events/core.c b/kernel/events/core.c index 58690af..4d9159a 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -5420,6 +5420,7 @@ static void perf_swevent_init_hrtimer(struct perf_event *event) hrtimer_init(&hwc->hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); hwc->hrtimer.function = perf_swevent_hrtimer; + hwc->hrtimer.irqsafe = 1; /* * Since hrtimers have a fixed rate, we can do a static freq->period diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c index 3991464..a080e62 100644 --- a/kernel/hrtimer.c +++ b/kernel/hrtimer.c @@ -1021,6 +1021,17 @@ int __hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim, #endif } +#ifdef CONFIG_MISSED_TIMER_OFFSETS_HIST + { + ktime_t now = new_base->get_time(); + + if (ktime_to_ns(tim) < ktime_to_ns(now)) + timer->praecox = now; + else + timer->praecox = ktime_set(0, 0); + } +#endif + hrtimer_set_expires_range_ns(timer, tim, delta_ns); timer_stats_hrtimer_set_start_info(timer); @@ -1458,8 +1469,9 @@ retry: timer = container_of(node, struct hrtimer, node); trace_hrtimer_interrupt(raw_smp_processor_id(), - ktime_to_ns(ktime_sub( - hrtimer_get_expires(timer), basenow)), + ktime_to_ns(ktime_sub(ktime_to_ns(timer->praecox) ? + timer->praecox : hrtimer_get_expires(timer), + basenow)), current, timer->function == hrtimer_wakeup ? container_of(timer, struct hrtimer_sleeper, diff --git a/kernel/trace/latency_hist.c b/kernel/trace/latency_hist.c index 9d49fcb..6a4c869 100644 --- a/kernel/trace/latency_hist.c +++ b/kernel/trace/latency_hist.c @@ -27,6 +27,8 @@ #include "trace.h" #include <trace/events/sched.h> +#define NSECS_PER_USECS 1000L + #define CREATE_TRACE_POINTS #include <trace/events/hist.h> @@ -46,11 +48,11 @@ enum { struct hist_data { atomic_t hist_mode; /* 0 log, 1 don't log */ long offset; /* set it to MAX_ENTRY_NUM/2 for a bipolar scale */ - unsigned long min_lat; - unsigned long max_lat; + long min_lat; + long max_lat; unsigned long long below_hist_bound_samples; unsigned long long above_hist_bound_samples; - unsigned long long accumulate_lat; + long long accumulate_lat; unsigned long long total_samples; unsigned long long hist_array[MAX_ENTRY_NUM]; }; @@ -152,8 +154,8 @@ static struct enable_data timerandwakeup_enabled_data = { static DEFINE_PER_CPU(struct maxlatproc_data, timerandwakeup_maxlatproc); #endif -void notrace latency_hist(int latency_type, int cpu, unsigned long latency, - unsigned long timeroffset, cycle_t stop, +void notrace latency_hist(int latency_type, int cpu, long latency, + long timeroffset, cycle_t stop, struct task_struct *p) { struct hist_data *my_hist; @@ -224,7 +226,7 @@ void notrace latency_hist(int latency_type, int cpu, unsigned long latency, my_hist->hist_array[latency]++; if (unlikely(latency > my_hist->max_lat || - my_hist->min_lat == ULONG_MAX)) { + my_hist->min_lat == LONG_MAX)) { #if defined(CONFIG_WAKEUP_LATENCY_HIST) || \ defined(CONFIG_MISSED_TIMER_OFFSETS_HIST) if (latency_type == WAKEUP_LATENCY || @@ -263,15 +265,14 @@ static void *l_start(struct seq_file *m, loff_t *pos) atomic_dec(&my_hist->hist_mode); if (likely(my_hist->total_samples)) { - unsigned long avg = (unsigned long) - div64_u64(my_hist->accumulate_lat, + long avg = (long) div64_s64(my_hist->accumulate_lat, my_hist->total_samples); snprintf(minstr, sizeof(minstr), "%ld", - (long) my_hist->min_lat - my_hist->offset); + my_hist->min_lat - my_hist->offset); snprintf(avgstr, sizeof(avgstr), "%ld", - (long) avg - my_hist->offset); + avg - my_hist->offset); snprintf(maxstr, sizeof(maxstr), "%ld", - (long) my_hist->max_lat - my_hist->offset); + my_hist->max_lat - my_hist->offset); } else { strcpy(minstr, "<undef>"); strcpy(avgstr, minstr); @@ -376,10 +377,10 @@ static void hist_reset(struct hist_data *hist) memset(hist->hist_array, 0, sizeof(hist->hist_array)); hist->below_hist_bound_samples = 0ULL; hist->above_hist_bound_samples = 0ULL; - hist->min_lat = ULONG_MAX; - hist->max_lat = 0UL; + hist->min_lat = LONG_MAX; + hist->max_lat = LONG_MIN; hist->total_samples = 0ULL; - hist->accumulate_lat = 0ULL; + hist->accumulate_lat = 0LL; atomic_inc(&hist->hist_mode); } @@ -790,9 +791,9 @@ static notrace void probe_preemptirqsoff_hist(void *v, int reason, stop = ftrace_now(cpu); time_set++; - if (start && stop >= start) { - unsigned long latency = - nsecs_to_usecs(stop - start); + if (start) { + long latency = ((long) (stop - start)) / + NSECS_PER_USECS; latency_hist(IRQSOFF_LATENCY, cpu, latency, 0, stop, NULL); @@ -808,9 +809,9 @@ static notrace void probe_preemptirqsoff_hist(void *v, int reason, if (!(time_set++)) stop = ftrace_now(cpu); - if (start && stop >= start) { - unsigned long latency = - nsecs_to_usecs(stop - start); + if (start) { + long latency = ((long) (stop - start)) / + NSECS_PER_USECS; latency_hist(PREEMPTOFF_LATENCY, cpu, latency, 0, stop, NULL); @@ -827,9 +828,10 @@ static notrace void probe_preemptirqsoff_hist(void *v, int reason, if (!time_set) stop = ftrace_now(cpu); - if (start && stop >= start) { - unsigned long latency = - nsecs_to_usecs(stop - start); + if (start) { + long latency = ((long) (stop - start)) / + NSECS_PER_USECS; + latency_hist(PREEMPTIRQSOFF_LATENCY, cpu, latency, 0, stop, NULL); } @@ -908,7 +910,7 @@ static notrace void probe_wakeup_latency_hist_stop(void *v, { unsigned long flags; int cpu = task_cpu(next); - unsigned long latency; + long latency; cycle_t stop; struct task_struct *cpu_wakeup_task; @@ -933,13 +935,17 @@ static notrace void probe_wakeup_latency_hist_stop(void *v, goto out; } + if (current->prio == cpu_wakeup_task->prio) + per_cpu(wakeup_sharedprio, cpu) = 1; + /* * The task we are waiting for is about to be switched to. * Calculate latency and store it in histogram. */ stop = ftrace_now(raw_smp_processor_id()); - latency = nsecs_to_usecs(stop - next->preempt_timestamp_hist); + latency = ((long) (stop - next->preempt_timestamp_hist)) / + NSECS_PER_USECS; if (per_cpu(wakeup_sharedprio, cpu)) { latency_hist(WAKEUP_LATENCY_SHAREDPRIO, cpu, latency, 0, stop, @@ -975,7 +981,7 @@ static notrace void probe_hrtimer_interrupt(void *v, int cpu, (task->prio < curr->prio || (task->prio == curr->prio && !cpumask_test_cpu(cpu, &task->cpus_allowed)))) { - unsigned long latency; + long latency; cycle_t now; if (missed_timer_offsets_pid) { @@ -985,7 +991,7 @@ static notrace void probe_hrtimer_interrupt(void *v, int cpu, } now = ftrace_now(cpu); - latency = (unsigned long) div_s64(-latency_ns, 1000); + latency = (long) div_s64(-latency_ns, NSECS_PER_USECS); latency_hist(MISSED_TIMER_OFFSETS, cpu, latency, latency, now, task); #ifdef CONFIG_WAKEUP_LATENCY_HIST @@ -1026,7 +1032,7 @@ static __init int latency_hist_init(void) &per_cpu(irqsoff_hist, i), &latency_hist_fops); my_hist = &per_cpu(irqsoff_hist, i); atomic_set(&my_hist->hist_mode, 1); - my_hist->min_lat = 0xFFFFFFFFUL; + my_hist->min_lat = LONG_MAX; } entry = debugfs_create_file("reset", 0644, dentry, (void *)IRQSOFF_LATENCY, &latency_hist_reset_fops); @@ -1041,7 +1047,7 @@ static __init int latency_hist_init(void) &per_cpu(preemptoff_hist, i), &latency_hist_fops); my_hist = &per_cpu(preemptoff_hist, i); atomic_set(&my_hist->hist_mode, 1); - my_hist->min_lat = 0xFFFFFFFFUL; + my_hist->min_lat = LONG_MAX; } entry = debugfs_create_file("reset", 0644, dentry, (void *)PREEMPTOFF_LATENCY, &latency_hist_reset_fops); @@ -1056,7 +1062,7 @@ static __init int latency_hist_init(void) &per_cpu(preemptirqsoff_hist, i), &latency_hist_fops); my_hist = &per_cpu(preemptirqsoff_hist, i); atomic_set(&my_hist->hist_mode, 1); - my_hist->min_lat = 0xFFFFFFFFUL; + my_hist->min_lat = LONG_MAX; } entry = debugfs_create_file("reset", 0644, dentry, (void *)PREEMPTIRQSOFF_LATENCY, &latency_hist_reset_fops); @@ -1081,14 +1087,14 @@ static __init int latency_hist_init(void) &latency_hist_fops); my_hist = &per_cpu(wakeup_latency_hist, i); atomic_set(&my_hist->hist_mode, 1); - my_hist->min_lat = 0xFFFFFFFFUL; + my_hist->min_lat = LONG_MAX; entry = debugfs_create_file(name, 0444, dentry_sharedprio, &per_cpu(wakeup_latency_hist_sharedprio, i), &latency_hist_fops); my_hist = &per_cpu(wakeup_latency_hist_sharedprio, i); atomic_set(&my_hist->hist_mode, 1); - my_hist->min_lat = 0xFFFFFFFFUL; + my_hist->min_lat = LONG_MAX; sprintf(name, cpufmt_maxlatproc, i); @@ -1122,7 +1128,7 @@ static __init int latency_hist_init(void) &per_cpu(missed_timer_offsets, i), &latency_hist_fops); my_hist = &per_cpu(missed_timer_offsets, i); atomic_set(&my_hist->hist_mode, 1); - my_hist->min_lat = 0xFFFFFFFFUL; + my_hist->min_lat = LONG_MAX; sprintf(name, cpufmt_maxlatproc, i); mp = &per_cpu(missed_timer_offsets_maxlatproc, i); @@ -1150,7 +1156,7 @@ static __init int latency_hist_init(void) &latency_hist_fops); my_hist = &per_cpu(timerandwakeup_latency_hist, i); atomic_set(&my_hist->hist_mode, 1); - my_hist->min_lat = 0xFFFFFFFFUL; + my_hist->min_lat = LONG_MAX; sprintf(name, cpufmt_maxlatproc, i); mp = &per_cpu(timerandwakeup_maxlatproc, i); diff --git a/localversion-rt b/localversion-rt index 21988f9..366440d 100644 --- a/localversion-rt +++ b/localversion-rt @@ -1 +1 @@ --rt34 +-rt35 diff --git a/mm/slab.c b/mm/slab.c index 5f0c5ef..3bef5e5 100644 --- a/mm/slab.c +++ b/mm/slab.c @@ -739,8 +739,26 @@ slab_on_each_cpu(void (*func)(void *arg, int this_cpu), void *arg) { unsigned int i; + get_cpu_light(); for_each_online_cpu(i) func(arg, i); + put_cpu_light(); +} + +static void lock_slab_on(unsigned int cpu) +{ + if (cpu == smp_processor_id()) + local_lock_irq(slab_lock); + else + local_spin_lock_irq(slab_lock, &per_cpu(slab_lock, cpu).lock); +} + +static void unlock_slab_on(unsigned int cpu) +{ + if (cpu == smp_processor_id()) + local_unlock_irq(slab_lock); + else + local_spin_unlock_irq(slab_lock, &per_cpu(slab_lock, cpu).lock); } #endif @@ -2627,10 +2645,10 @@ static void do_drain(void *arg, int cpu) { LIST_HEAD(tmp); - spin_lock_irq(&per_cpu(slab_lock, cpu).lock); + lock_slab_on(cpu); __do_drain(arg, cpu); list_splice_init(&per_cpu(slab_free_list, cpu), &tmp); - spin_unlock_irq(&per_cpu(slab_lock, cpu).lock); + unlock_slab_on(cpu); free_delayed(&tmp); } #endif @@ -4095,9 +4113,9 @@ static void do_ccupdate_local(void *info) #else static void do_ccupdate_local(void *info, int cpu) { - spin_lock_irq(&per_cpu(slab_lock, cpu).lock); + lock_slab_on(cpu); __do_ccupdate_local(info, cpu); - spin_unlock_irq(&per_cpu(slab_lock, cpu).lock); + unlock_slab_on(cpu); } #endif -- To unsubscribe from this list: send the line "unsubscribe linux-rt-users" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
