tick/nohz: Only check for RCU deferred wakeup on user/guest entry when needed

Checking for and processing RCU-nocb deferred wakeup upon user/guest
entry is only relevant when nohz_full runs on the local CPU, otherwise
the periodic tick should take care of it.

Make sure we don't needlessly pollute these fast-paths as a -3%
performance regression on a will-it-scale.per_process_ops has been
reported so far.

Fixes: 47b8ff194c1f (entry: Explicitly flush pending rcuog wakeup before last rescheduling point)
Fixes: 4ae7dc97f726 (entry/kvm: Explicitly flush pending rcuog wakeup before last rescheduling point)
Reported-by: kernel test robot <oliver.sang@intel.com>
Signed-off-by: Frederic Weisbecker <frederic@kernel.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Paul E. McKenney <paulmck@kernel.org>
Cc: stable@vger.kernel.org
Link: https://lkml.kernel.org/r/20210527113441.465489-1-frederic@kernel.org

diff --git a/include/linux/entry-kvm.h b/include/linux/entry-kvm.h
index 8b2b1d68b9545602534692c5670f41b7f6fcdf18..136b8d97d8c01216657e4e3a6587d73eae865efb 100644 (file)
--- a/include/linux/entry-kvm.h
+++ b/include/linux/entry-kvm.h
@@ -3,6 +3,7 @@
 #define __LINUX_ENTRYKVM_H
 
 #include <linux/entry-common.h>
+#include <linux/tick.h>
 
 /* Transfer to guest mode work */
 #ifdef CONFIG_KVM_XFER_TO_GUEST_WORK
@@ -57,7 +58,7 @@ int xfer_to_guest_mode_handle_work(struct kvm_vcpu *vcpu);
 static inline void xfer_to_guest_mode_prepare(void)
 {
        lockdep_assert_irqs_disabled();
-       rcu_nocb_flush_deferred_wakeup();
+       tick_nohz_user_enter_prepare();
 }
 
 /**

diff --git a/include/linux/tick.h b/include/linux/tick.h
index 7340613c7eff7ad791634c76ae2ecd547f711c45..1a0ff88fa107b3e8fd05c3b5824367b7283752b9 100644 (file)
--- a/include/linux/tick.h
+++ b/include/linux/tick.h
@@ -11,6 +11,7 @@
 #include <linux/context_tracking_state.h>
 #include <linux/cpumask.h>
 #include <linux/sched.h>
+#include <linux/rcupdate.h>
 
 #ifdef CONFIG_GENERIC_CLOCKEVENTS
 extern void __init tick_init(void);
@@ -300,4 +301,10 @@ static inline void tick_nohz_task_switch(void)
                __tick_nohz_task_switch();
 }
 
+static inline void tick_nohz_user_enter_prepare(void)
+{
+       if (tick_nohz_full_cpu(smp_processor_id()))
+               rcu_nocb_flush_deferred_wakeup();
+}
+
 #endif

diff --git a/kernel/entry/common.c b/kernel/entry/common.c
index a0b3b04fb5965995ea991f8aa6e375c62e8d9c2d..bf16395b9e1351f843edce4335df8bddb5a49686 100644 (file)
--- a/kernel/entry/common.c
+++ b/kernel/entry/common.c
@@ -5,6 +5,7 @@
 #include <linux/highmem.h>
 #include <linux/livepatch.h>
 #include <linux/audit.h>
+#include <linux/tick.h>
 
 #include "common.h"
 
@@ -186,7 +187,7 @@ static unsigned long exit_to_user_mode_loop(struct pt_regs *regs,
                local_irq_disable_exit_to_user();
 
                /* Check if any of the above work has queued a deferred wakeup */
-               rcu_nocb_flush_deferred_wakeup();
+               tick_nohz_user_enter_prepare();
 
                ti_work = READ_ONCE(current_thread_info()->flags);
        }
@@ -202,7 +203,7 @@ static void exit_to_user_mode_prepare(struct pt_regs *regs)
        lockdep_assert_irqs_disabled();
 
        /* Flush pending rcuog wakeup before the last need_resched() check */
-       rcu_nocb_flush_deferred_wakeup();
+       tick_nohz_user_enter_prepare();
 
        if (unlikely(ti_work & EXIT_TO_USER_MODE_WORK))
                ti_work = exit_to_user_mode_loop(regs, ti_work);

diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 828b091501ca4571040e88b336276ee39b7a0cb2..6784f27a309937a5ecffad50e0dc1af0cdfd5e68 100644 (file)
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -230,6 +230,7 @@ static void tick_sched_handle(struct tick_sched *ts, struct pt_regs *regs)
 
 #ifdef CONFIG_NO_HZ_FULL
 cpumask_var_t tick_nohz_full_mask;
+EXPORT_SYMBOL_GPL(tick_nohz_full_mask);
 bool tick_nohz_full_running;
 EXPORT_SYMBOL_GPL(tick_nohz_full_running);
 static atomic_t tick_dep_mask;