From b0bc225d0e5de887340d4d92a8c594ef0f60d412 Mon Sep 17 00:00:00 2001 From: Andrew Jones Date: Wed, 29 May 2013 14:48:15 +0200 Subject: sched/x86: Construct all sibling maps if smt Commit 316ad248307fb ("sched/x86: Rewrite set_cpu_sibling_map()") broke the construction of sibling maps, which also broke the booted_cores accounting. Before the rewrite, if smt was present, then each map was updated for each smt sibling. After the rewrite only cpu_sibling_mask gets updated, as the llc and core maps depend on 'has_mc = x86_max_cores > 1' instead. This leads to problems with topologies like the following (qemu -smp sockets=2,cores=1,threads=2) processor : 0 physical id : 0 siblings : 1 <= should be 2 core id : 0 cpu cores : 1 processor : 1 physical id : 0 siblings : 1 <= should be 2 core id : 0 cpu cores : 0 <= should be 1 processor : 2 physical id : 1 siblings : 1 <= should be 2 core id : 0 cpu cores : 1 processor : 3 physical id : 1 siblings : 1 <= should be 2 core id : 0 cpu cores : 0 <= should be 1 This patch restores the former construction by defining has_mc as (has_smt || x86_max_cores > 1). This should be fine as there were no (has_smt && !has_mc) conditions in the context. Aso rename has_mc to has_mp now that it's not just for cores. Signed-off-by: Andrew Jones Acked-by: Peter Zijlstra Cc: a.p.zijlstra@chello.nl Cc: fenghua.yu@intel.com Link: http://lkml.kernel.org/r/1369831695-11970-1-git-send-email-drjones@redhat.com Signed-off-by: Ingo Molnar --- arch/x86/kernel/smpboot.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 9c73b51817e4..bfd348e99369 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -372,15 +372,15 @@ static bool __cpuinit match_mc(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o) void __cpuinit set_cpu_sibling_map(int cpu) { - bool has_mc = boot_cpu_data.x86_max_cores > 1; bool has_smt = smp_num_siblings > 1; + bool has_mp = has_smt || boot_cpu_data.x86_max_cores > 1; struct cpuinfo_x86 *c = &cpu_data(cpu); struct cpuinfo_x86 *o; int i; cpumask_set_cpu(cpu, cpu_sibling_setup_mask); - if (!has_smt && !has_mc) { + if (!has_mp) { cpumask_set_cpu(cpu, cpu_sibling_mask(cpu)); cpumask_set_cpu(cpu, cpu_llc_shared_mask(cpu)); cpumask_set_cpu(cpu, cpu_core_mask(cpu)); @@ -394,7 +394,7 @@ void __cpuinit set_cpu_sibling_map(int cpu) if ((i == cpu) || (has_smt && match_smt(c, o))) link_mask(sibling, cpu, i); - if ((i == cpu) || (has_mc && match_llc(c, o))) + if ((i == cpu) || (has_mp && match_llc(c, o))) link_mask(llc_shared, cpu, i); } @@ -406,7 +406,7 @@ void __cpuinit set_cpu_sibling_map(int cpu) for_each_cpu(i, cpu_sibling_setup_mask) { o = &cpu_data(i); - if ((i == cpu) || (has_mc && match_mc(c, o))) { + if ((i == cpu) || (has_mp && match_mc(c, o))) { link_mask(core, cpu, i); /* -- cgit v1.2.3 From 873b4c65b519fd769940eb281f77848227d4e5c1 Mon Sep 17 00:00:00 2001 From: Vincent Guittot Date: Wed, 5 Jun 2013 10:13:11 +0200 Subject: sched: Fix clear NOHZ_BALANCE_KICK I have faced a sequence where the Idle Load Balance was sometime not triggered for a while on my platform, in the following scenario: CPU 0 and CPU 1 are running tasks and CPU 2 is idle CPU 1 kicks the Idle Load Balance CPU 1 selects CPU 2 as the new Idle Load Balancer CPU 2 sets NOHZ_BALANCE_KICK for CPU 2 CPU 2 sends a reschedule IPI to CPU 2 While CPU 3 wakes up, CPU 0 or CPU 1 migrates a waking up task A on CPU 2 CPU 2 finally wakes up, runs task A and discards the Idle Load Balance task A quickly goes back to sleep (before a tick occurs on CPU 2) CPU 2 goes back to idle with NOHZ_BALANCE_KICK set Whenever CPU 2 will be selected as the ILB, no reschedule IPI will be sent because NOHZ_BALANCE_KICK is already set and no Idle Load Balance will be performed. We must wait for the sched softirq to be raised on CPU 2 thanks to another part the kernel to come back to clear NOHZ_BALANCE_KICK. The proposed solution clears NOHZ_BALANCE_KICK in schedule_ipi if we can't raise the sched_softirq for the Idle Load Balance. Change since V1: - move the clear of NOHZ_BALANCE_KICK in got_nohz_idle_kick if the ILB can't run on this CPU (as suggested by Peter) Signed-off-by: Vincent Guittot Signed-off-by: Peter Zijlstra Link: http://lkml.kernel.org/r/1370419991-13870-1-git-send-email-vincent.guittot@linaro.org Signed-off-by: Ingo Molnar --- kernel/sched/core.c | 21 +++++++++++++++++---- 1 file changed, 17 insertions(+), 4 deletions(-) diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 58453b8272fd..919bee68032b 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -633,7 +633,19 @@ void wake_up_nohz_cpu(int cpu) static inline bool got_nohz_idle_kick(void) { int cpu = smp_processor_id(); - return idle_cpu(cpu) && test_bit(NOHZ_BALANCE_KICK, nohz_flags(cpu)); + + if (!test_bit(NOHZ_BALANCE_KICK, nohz_flags(cpu))) + return false; + + if (idle_cpu(cpu) && !need_resched()) + return true; + + /* + * We can't run Idle Load Balance on this CPU for this time so we + * cancel it and clear NOHZ_BALANCE_KICK + */ + clear_bit(NOHZ_BALANCE_KICK, nohz_flags(cpu)); + return false; } #else /* CONFIG_NO_HZ_COMMON */ @@ -1393,8 +1405,9 @@ static void sched_ttwu_pending(void) void scheduler_ipi(void) { - if (llist_empty(&this_rq()->wake_list) && !got_nohz_idle_kick() - && !tick_nohz_full_cpu(smp_processor_id())) + if (llist_empty(&this_rq()->wake_list) + && !tick_nohz_full_cpu(smp_processor_id()) + && !got_nohz_idle_kick()) return; /* @@ -1417,7 +1430,7 @@ void scheduler_ipi(void) /* * Check if someone kicked us for doing the nohz idle load balance. */ - if (unlikely(got_nohz_idle_kick() && !need_resched())) { + if (unlikely(got_nohz_idle_kick())) { this_rq()->idle_balance = 1; raise_softirq_irqoff(SCHED_SOFTIRQ); } -- cgit v1.2.3 From 29bb9e5a75684106a37593ad75ec75ff8312731b Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Fri, 24 May 2013 15:23:40 -0400 Subject: tracing/context-tracking: Add preempt_schedule_context() for tracing Dave Jones hit the following bug report: =============================== [ INFO: suspicious RCU usage. ] 3.10.0-rc2+ #1 Not tainted ------------------------------- include/linux/rcupdate.h:771 rcu_read_lock() used illegally while idle! other info that might help us debug this: RCU used illegally from idle CPU! rcu_scheduler_active = 1, debug_locks = 0 RCU used illegally from extended quiescent state! 2 locks held by cc1/63645: #0: (&rq->lock){-.-.-.}, at: [] __schedule+0xed/0x9b0 #1: (rcu_read_lock){.+.+..}, at: [] cpuacct_charge+0x5/0x1f0 CPU: 1 PID: 63645 Comm: cc1 Not tainted 3.10.0-rc2+ #1 [loadavg: 40.57 27.55 13.39 25/277 64369] Hardware name: Gigabyte Technology Co., Ltd. GA-MA78GM-S2H/GA-MA78GM-S2H, BIOS F12a 04/23/2010 0000000000000000 ffff88010f78fcf8 ffffffff816ae383 ffff88010f78fd28 ffffffff810b698d ffff88011c092548 000000000023d073 ffff88011c092500 0000000000000001 ffff88010f78fd60 ffffffff8109d7c5 ffffffff8109d645 Call Trace: [] dump_stack+0x19/0x1b [] lockdep_rcu_suspicious+0xfd/0x130 [] cpuacct_charge+0x185/0x1f0 [] ? cpuacct_charge+0x5/0x1f0 [] update_curr+0xec/0x240 [] put_prev_task_fair+0x228/0x480 [] __schedule+0x161/0x9b0 [] preempt_schedule+0x51/0x80 [] ? __cond_resched_softirq+0x60/0x60 [] ? retint_careful+0x12/0x2e [] ftrace_ops_control_func+0x1dc/0x210 [] ftrace_call+0x5/0x2f [] ? retint_careful+0xb/0x2e [] ? schedule_user+0x5/0x70 [] ? schedule_user+0x5/0x70 [] ? retint_careful+0x12/0x2e ------------[ cut here ]------------ What happened was that the function tracer traced the schedule_user() code that tells RCU that the system is coming back from userspace, and to add the CPU back to the RCU monitoring. Because the function tracer does a preempt_disable/enable_notrace() calls the preempt_enable_notrace() checks the NEED_RESCHED flag. If it is set, then preempt_schedule() is called. But this is called before the user_exit() function can inform the kernel that the CPU is no longer in user mode and needs to be accounted for by RCU. The fix is to create a new preempt_schedule_context() that checks if the kernel is still in user mode and if so to switch it to kernel mode before calling schedule. It also switches back to user mode coming back from schedule in need be. The only user of this currently is the preempt_enable_notrace(), which is only used by the tracing subsystem. Signed-off-by: Steven Rostedt Signed-off-by: Peter Zijlstra Link: http://lkml.kernel.org/r/1369423420.6828.226.camel@gandalf.local.home Signed-off-by: Ingo Molnar --- include/linux/preempt.h | 18 +++++++++++++++++- kernel/context_tracking.c | 40 ++++++++++++++++++++++++++++++++++++++++ 2 files changed, 57 insertions(+), 1 deletion(-) diff --git a/include/linux/preempt.h b/include/linux/preempt.h index 87a03c746f17..f5d4723cdb3d 100644 --- a/include/linux/preempt.h +++ b/include/linux/preempt.h @@ -33,9 +33,25 @@ do { \ preempt_schedule(); \ } while (0) +#ifdef CONFIG_CONTEXT_TRACKING + +void preempt_schedule_context(void); + +#define preempt_check_resched_context() \ +do { \ + if (unlikely(test_thread_flag(TIF_NEED_RESCHED))) \ + preempt_schedule_context(); \ +} while (0) +#else + +#define preempt_check_resched_context() preempt_check_resched() + +#endif /* CONFIG_CONTEXT_TRACKING */ + #else /* !CONFIG_PREEMPT */ #define preempt_check_resched() do { } while (0) +#define preempt_check_resched_context() do { } while (0) #endif /* CONFIG_PREEMPT */ @@ -88,7 +104,7 @@ do { \ do { \ preempt_enable_no_resched_notrace(); \ barrier(); \ - preempt_check_resched(); \ + preempt_check_resched_context(); \ } while (0) #else /* !CONFIG_PREEMPT_COUNT */ diff --git a/kernel/context_tracking.c b/kernel/context_tracking.c index 65349f07b878..66677003e223 100644 --- a/kernel/context_tracking.c +++ b/kernel/context_tracking.c @@ -71,6 +71,46 @@ void user_enter(void) local_irq_restore(flags); } +#ifdef CONFIG_PREEMPT +/** + * preempt_schedule_context - preempt_schedule called by tracing + * + * The tracing infrastructure uses preempt_enable_notrace to prevent + * recursion and tracing preempt enabling caused by the tracing + * infrastructure itself. But as tracing can happen in areas coming + * from userspace or just about to enter userspace, a preempt enable + * can occur before user_exit() is called. This will cause the scheduler + * to be called when the system is still in usermode. + * + * To prevent this, the preempt_enable_notrace will use this function + * instead of preempt_schedule() to exit user context if needed before + * calling the scheduler. + */ +void __sched notrace preempt_schedule_context(void) +{ + struct thread_info *ti = current_thread_info(); + enum ctx_state prev_ctx; + + if (likely(ti->preempt_count || irqs_disabled())) + return; + + /* + * Need to disable preemption in case user_exit() is traced + * and the tracer calls preempt_enable_notrace() causing + * an infinite recursion. + */ + preempt_disable_notrace(); + prev_ctx = exception_enter(); + preempt_enable_no_resched_notrace(); + + preempt_schedule(); + + preempt_disable_notrace(); + exception_exit(prev_ctx); + preempt_enable_notrace(); +} +EXPORT_SYMBOL_GPL(preempt_schedule_context); +#endif /* CONFIG_PREEMPT */ /** * user_exit - Inform the context tracking that the CPU is -- cgit v1.2.3