Messages in this thread | | | Date | Thu, 21 Oct 2010 09:16:27 -0700 | From | "Paul E. McKenney" <> | Subject | Re: [PATCH 1/2 v2] rcu,cleanup: move synchronize_sched_expedited() out of sched.c |
| |
On Wed, Oct 20, 2010 at 09:39:53PM -0700, Paul E. McKenney wrote: > On Thu, Oct 21, 2010 at 11:29:05AM +0800, Lai Jiangshan wrote: > > On 10/21/2010 08:19 AM, Paul E. McKenney wrote: > > > On Wed, Oct 20, 2010 at 12:15:12PM -0700, Paul E. McKenney wrote: > > >> On Wed, Oct 20, 2010 at 02:12:58PM +0800, Lai Jiangshan wrote: > > >>> The first version of synchronize_sched_expedited() use the migration code > > >>> of the scheduler code, so it have to be implemented in sched.c > > >>> > > >>> but now, the synchronize_sched_expedited() does not use such code, > > >>> it is time to move it out of sched.c. > > >>> > > >>> Different rcu implementation' synchronize_sched_expedited() are also > > >>> different. so we move synchronize_sched_expedited() to kernel/rcutree_plugin.h > > >>> or include/linux/rcutiny.h instead of kerenl/rcupdate.c > > >> > > >> Queued, thank you!!! > > > > > > Hello again, Lai, > > > > > > I hit the following build error during testing: > > > > > > kernel/built-in.o: In function `.synchronize_rcu_expedited': > > > (.text+0x787d8): undefined reference to `.synchronize_sched_expedited' > > > kernel/built-in.o:(.toc1+0x1fe0): undefined reference to `synchronize_sched_expedited' > > > > > > This build uses defconfig with the following applied: > > > > > > CONFIG_RCU_TRACE=y > > > CONFIG_RCU_FAST_NO_HZ=y > > > CONFIG_NO_HZ=y > > > CONFIG_RCU_CPU_STALL_DETECTOR=y > > > CONFIG_SMP=y > > > CONFIG_RCU_FANOUT=8 > > > CONFIG_NR_CPUS=8 > > > CONFIG_RCU_FANOUT_EXACT=n > > > CONFIG_HOTPLUG_CPU=y > > > CONFIG_PREEMPT_NONE=y > > > CONFIG_PREEMPT_VOLUNTARY=n > > > CONFIG_PREEMPT=n > > > CONFIG_TREE_RCU=y > > > CONFIG_TREE_PREEMPT_RCU=n > > > CONFIG_RCU_TORTURE_TEST=m > > > CONFIG_MODULE_UNLOAD=y > > > CONFIG_SYSFS_DEPRECATED_V2=y > > > CONFIG_IKCONFIG=y > > > CONFIG_IKCONFIG_PROC=y > > > > > > Thoughts? > > > > > > Thanx, Paul > > > > > > > > > > I moved the code into CONFIG_TREE_PREEMPT_RCU=y codes. fixed version: > > Thank you, queued and am retesting.
And the new version works much better, thank you! Any news on the cpumask_any() issue?
Thanx, Paul
> > Signed-off-by: Lai Jiangshan <laijs@cn.fujitsu.com> > > --- > > diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h > > index 0d0b640..ead36da 100644 > > --- a/include/linux/rcupdate.h > > +++ b/include/linux/rcupdate.h > > @@ -66,7 +66,6 @@ extern void call_rcu_sched(struct rcu_head *head, > > extern void synchronize_sched(void); > > extern void rcu_barrier_bh(void); > > extern void rcu_barrier_sched(void); > > -extern void synchronize_sched_expedited(void); > > extern int sched_expedited_torture_stats(char *page); > > > > static inline void __rcu_read_lock_bh(void) > > diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h > > index 13877cb..4d84452 100644 > > --- a/include/linux/rcutiny.h > > +++ b/include/linux/rcutiny.h > > @@ -58,6 +58,11 @@ static inline void synchronize_rcu_bh_expedited(void) > > synchronize_sched(); > > } > > > > +static inline void synchronize_sched_expedited(void) > > +{ > > + synchronize_sched(); > > +} > > + > > #ifdef CONFIG_TINY_RCU > > > > static inline void rcu_preempt_note_context_switch(void) > > diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h > > index 95518e6..9a1fd6c 100644 > > --- a/include/linux/rcutree.h > > +++ b/include/linux/rcutree.h > > @@ -47,6 +47,7 @@ static inline void exit_rcu(void) > > #endif /* #else #ifdef CONFIG_TREE_PREEMPT_RCU */ > > > > extern void synchronize_rcu_bh(void); > > +extern void synchronize_sched_expedited(void); > > extern void synchronize_rcu_expedited(void); > > > > static inline void synchronize_rcu_bh_expedited(void) > > diff --git a/kernel/rcutree_plugin.h b/kernel/rcutree_plugin.h > > index 0e75d60..0de359b 100644 > > --- a/kernel/rcutree_plugin.h > > +++ b/kernel/rcutree_plugin.h > > @@ -25,6 +25,7 @@ > > */ > > > > #include <linux/delay.h> > > +#include <linux/stop_machine.h> > > > > /* > > * Check the RCU kernel configuration parameters and print informative > > @@ -1014,6 +1015,76 @@ static void __init __rcu_init_preempt(void) > > > > #endif /* #else #ifdef CONFIG_TREE_PREEMPT_RCU */ > > > > +#ifndef CONFIG_SMP > > + > > +void synchronize_sched_expedited(void) > > +{ > > + cond_resched(); > > +} > > +EXPORT_SYMBOL_GPL(synchronize_sched_expedited); > > + > > +#else /* #ifndef CONFIG_SMP */ > > + > > +static atomic_t synchronize_sched_expedited_count = ATOMIC_INIT(0); > > + > > +static int synchronize_sched_expedited_cpu_stop(void *data) > > +{ > > + /* > > + * There must be a full memory barrier on each affected CPU > > + * between the time that try_stop_cpus() is called and the > > + * time that it returns. > > + * > > + * In the current initial implementation of cpu_stop, the > > + * above condition is already met when the control reaches > > + * this point and the following smp_mb() is not strictly > > + * necessary. Do smp_mb() anyway for documentation and > > + * robustness against future implementation changes. > > + */ > > + smp_mb(); /* See above comment block. */ > > + return 0; > > +} > > + > > +/* > > + * Wait for an rcu-sched grace period to elapse, but use "big hammer" > > + * approach to force grace period to end quickly. This consumes > > + * significant time on all CPUs, and is thus not recommended for > > + * any sort of common-case code. > > + * > > + * Note that it is illegal to call this function while holding any > > + * lock that is acquired by a CPU-hotplug notifier. Failing to > > + * observe this restriction will result in deadlock. > > + */ > > +void synchronize_sched_expedited(void) > > +{ > > + int snap, trycount = 0; > > + > > + smp_mb(); /* ensure prior mod happens before capturing snap. */ > > + snap = atomic_read(&synchronize_sched_expedited_count) + 1; > > + get_online_cpus(); > > + while (try_stop_cpus(cpu_online_mask, > > + synchronize_sched_expedited_cpu_stop, > > + NULL) == -EAGAIN) { > > + put_online_cpus(); > > + if (trycount++ < 10) > > + udelay(trycount * num_online_cpus()); > > + else { > > + synchronize_sched(); > > + return; > > + } > > + if (atomic_read(&synchronize_sched_expedited_count) - snap > 0) { > > + smp_mb(); /* ensure test happens before caller kfree */ > > + return; > > + } > > + get_online_cpus(); > > + } > > + atomic_inc(&synchronize_sched_expedited_count); > > + smp_mb__after_atomic_inc(); /* ensure post-GP actions seen after GP. */ > > + put_online_cpus(); > > +} > > +EXPORT_SYMBOL_GPL(synchronize_sched_expedited); > > + > > +#endif /* #else #ifndef CONFIG_SMP */ > > + > > #if !defined(CONFIG_RCU_FAST_NO_HZ) > > > > /* > > diff --git a/kernel/sched.c b/kernel/sched.c > > index abf8440..9dc7775 100644 > > --- a/kernel/sched.c > > +++ b/kernel/sched.c > > @@ -9332,72 +9332,3 @@ struct cgroup_subsys cpuacct_subsys = { > > }; > > #endif /* CONFIG_CGROUP_CPUACCT */ > > > > -#ifndef CONFIG_SMP > > - > > -void synchronize_sched_expedited(void) > > -{ > > - barrier(); > > -} > > -EXPORT_SYMBOL_GPL(synchronize_sched_expedited); > > - > > -#else /* #ifndef CONFIG_SMP */ > > - > > -static atomic_t synchronize_sched_expedited_count = ATOMIC_INIT(0); > > - > > -static int synchronize_sched_expedited_cpu_stop(void *data) > > -{ > > - /* > > - * There must be a full memory barrier on each affected CPU > > - * between the time that try_stop_cpus() is called and the > > - * time that it returns. > > - * > > - * In the current initial implementation of cpu_stop, the > > - * above condition is already met when the control reaches > > - * this point and the following smp_mb() is not strictly > > - * necessary. Do smp_mb() anyway for documentation and > > - * robustness against future implementation changes. > > - */ > > - smp_mb(); /* See above comment block. */ > > - return 0; > > -} > > - > > -/* > > - * Wait for an rcu-sched grace period to elapse, but use "big hammer" > > - * approach to force grace period to end quickly. This consumes > > - * significant time on all CPUs, and is thus not recommended for > > - * any sort of common-case code. > > - * > > - * Note that it is illegal to call this function while holding any > > - * lock that is acquired by a CPU-hotplug notifier. Failing to > > - * observe this restriction will result in deadlock. > > - */ > > -void synchronize_sched_expedited(void) > > -{ > > - int snap, trycount = 0; > > - > > - smp_mb(); /* ensure prior mod happens before capturing snap. */ > > - snap = atomic_read(&synchronize_sched_expedited_count) + 1; > > - get_online_cpus(); > > - while (try_stop_cpus(cpu_online_mask, > > - synchronize_sched_expedited_cpu_stop, > > - NULL) == -EAGAIN) { > > - put_online_cpus(); > > - if (trycount++ < 10) > > - udelay(trycount * num_online_cpus()); > > - else { > > - synchronize_sched(); > > - return; > > - } > > - if (atomic_read(&synchronize_sched_expedited_count) - snap > 0) { > > - smp_mb(); /* ensure test happens before caller kfree */ > > - return; > > - } > > - get_online_cpus(); > > - } > > - atomic_inc(&synchronize_sched_expedited_count); > > - smp_mb__after_atomic_inc(); /* ensure post-GP actions seen after GP. */ > > - put_online_cpus(); > > -} > > -EXPORT_SYMBOL_GPL(synchronize_sched_expedited); > > - > > -#endif /* #else #ifndef CONFIG_SMP */ > > -- > > To unsubscribe from this list: send the line "unsubscribe linux-kernel" in > > the body of a message to majordomo@vger.kernel.org > > More majordomo info at http://vger.kernel.org/majordomo-info.html > > Please read the FAQ at http://www.tux.org/lkml/
| |