Messages in this thread Patch in this message | | | Subject | Re: There is something with scheduler (was Re: [patch] Re: [regression bisect -next] BUG: using smp_processor_id() in preemptible [00000000] code: rmmod) | From | Mike Galbraith <> | Date | Thu, 05 Nov 2009 15:30:37 +0100 |
| |
BTW, with (only) the full scheduler pull request applied, it also acts sane, and this little hunk is responsible... somehow. But if that's the problem, why does locking the runqueue fix it too??
Index: linux-2.6.32.git/kernel/sched.c =================================================================== --- linux-2.6.32.git.orig/kernel/sched.c +++ linux-2.6.32.git/kernel/sched.c @@ -9552,13 +9584,13 @@ void __init sched_init(void) current->sched_class = &fair_sched_class; /* Allocate the nohz_cpu_mask if CONFIG_CPUMASK_OFFSTACK */ - alloc_cpumask_var(&nohz_cpu_mask, GFP_NOWAIT); + zalloc_cpumask_var(&nohz_cpu_mask, GFP_NOWAIT); #ifdef CONFIG_SMP #ifdef CONFIG_NO_HZ - alloc_cpumask_var(&nohz.cpu_mask, GFP_NOWAIT); + zalloc_cpumask_var(&nohz.cpu_mask, GFP_NOWAIT); alloc_cpumask_var(&nohz.ilb_grp_nohz_mask, GFP_NOWAIT); #endif - alloc_cpumask_var(&cpu_isolated_map, GFP_NOWAIT); + zalloc_cpumask_var(&cpu_isolated_map, GFP_NOWAIT); #endif /* SMP */ perf_event_init();
| |