x86/cpu: Disable frequency requests via aperfmperf IPI for nohz_full CPUs

Since commit 7d5905dc14a8 ("x86 / CPU: Always show current CPU frequency
in /proc/cpuinfo") open and read of /proc/cpuinfo sends IPI to all CPUs.
Many applications read /proc/cpuinfo at the start for trivial reasons like
counting cores or detecting cpu features. While sensitive workloads like
DPDK network polling don't like any interrupts.

Integrates this feature with cpu isolation and do not send IPIs to CPUs
without housekeeping flag HK_FLAG_MISC (set by nohz_full).

Code that requests cpu frequency like show_cpuinfo() falls back to the last
frequency set by the cpufreq driver if this method returns 0.

Signed-off-by: Konstantin Khlebnikov <khlebnikov@yandex-team.ru>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Len Brown <len.brown@intel.com>
Cc: Frederic Weisbecker <frederic@kernel.org>
Cc: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Link: https://lkml.kernel.org/r/155790354043.1104.15333317408370209.stgit@buzz

diff --git a/arch/x86/kernel/cpu/aperfmperf.c b/arch/x86/kernel/cpu/aperfmperf.c
index e71a6ff8a67ea22a90be3f2a7a5be934db0b556b..e2f319dc992d0d9405d65b9d665f5a986b537f4b 100644 (file)
--- a/arch/x86/kernel/cpu/aperfmperf.c
+++ b/arch/x86/kernel/cpu/aperfmperf.c
@@ -13,6 +13,7 @@
 #include <linux/percpu.h>
 #include <linux/cpufreq.h>
 #include <linux/smp.h>
+#include <linux/sched/isolation.h>
 
 #include "cpu.h"
 
@@ -85,6 +86,9 @@ unsigned int aperfmperf_get_khz(int cpu)
        if (!boot_cpu_has(X86_FEATURE_APERFMPERF))
                return 0;
 
+       if (!housekeeping_cpu(cpu, HK_FLAG_MISC))
+               return 0;
+
        aperfmperf_snapshot_cpu(cpu, ktime_get(), true);
        return per_cpu(samples.khz, cpu);
 }
@@ -101,9 +105,12 @@ void arch_freq_prepare_all(void)
        if (!boot_cpu_has(X86_FEATURE_APERFMPERF))
                return;
 
-       for_each_online_cpu(cpu)
+       for_each_online_cpu(cpu) {
+               if (!housekeeping_cpu(cpu, HK_FLAG_MISC))
+                       continue;
                if (!aperfmperf_snapshot_cpu(cpu, now, false))
                        wait = true;
+       }
 
        if (wait)
                msleep(APERFMPERF_REFRESH_DELAY_MS);
@@ -117,6 +124,9 @@ unsigned int arch_freq_get_on_cpu(int cpu)
        if (!boot_cpu_has(X86_FEATURE_APERFMPERF))
                return 0;
 
+       if (!housekeeping_cpu(cpu, HK_FLAG_MISC))
+               return 0;
+
        if (aperfmperf_snapshot_cpu(cpu, ktime_get(), true))
                return per_cpu(samples.khz, cpu);