[PATCH RFC] x86 / CPU: Add cpu isolation flag for avoiding disturbance from aperfmperf IPI

[Konstantin Khlebnikov]

Sensitive workloads like DPDK polling do not like any interrupts.

This patch adds flag 'freq' for boot option 'isolcpu': isolcpu=freq,<cpus>.

Users like show_cpuinfo() fallback to frequency from generic cpufreq
policy if arch-specific requesting method returns 0.

Signed-off-by: Konstantin Khlebnikov <khlebnikov@xxxxxxxxxxxxxx>
---
 Documentation/admin-guide/kernel-parameters.txt |    3 +++
 arch/x86/kernel/cpu/aperfmperf.c                |   12 +++++++++++-
 include/linux/sched/isolation.h                 |    1 +
 kernel/sched/isolation.c                        |    6 ++++++
 4 files changed, 21 insertions(+), 1 deletion(-)

diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index 2b8ee90bb644..3797cd5c2b2e 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -1900,6 +1900,9 @@
 			  <cpu number> begins at 0 and the maximum value is
 			  "number of CPUs in system - 1".
 
+			freq
+			  Do not request current cpu frequency via IPI.
+
 			The format of <cpu-list> is described above.
 
 
diff --git a/arch/x86/kernel/cpu/aperfmperf.c b/arch/x86/kernel/cpu/aperfmperf.c
index 804c49493938..e8fb917980a8 100644
--- a/arch/x86/kernel/cpu/aperfmperf.c
+++ b/arch/x86/kernel/cpu/aperfmperf.c
@@ -14,6 +14,7 @@
 #include <linux/percpu.h>
 #include <linux/cpufreq.h>
 #include <linux/smp.h>
+#include <linux/sched/isolation.h>
 
 #include "cpu.h"
 
@@ -86,6 +87,9 @@ unsigned int aperfmperf_get_khz(int cpu)
 	if (!static_cpu_has(X86_FEATURE_APERFMPERF))
 		return 0;
 
+	if (!housekeeping_cpu(cpu, HK_FLAG_FREQ))
+		return 0;
+
 	aperfmperf_snapshot_cpu(cpu, ktime_get(), true);
 	return per_cpu(samples.khz, cpu);
 }
@@ -102,9 +106,12 @@ void arch_freq_prepare_all(void)
 	if (!static_cpu_has(X86_FEATURE_APERFMPERF))
 		return;
 
-	for_each_online_cpu(cpu)
+	for_each_online_cpu(cpu) {
+		if (!housekeeping_cpu(cpu, HK_FLAG_FREQ))
+			continue;
 		if (!aperfmperf_snapshot_cpu(cpu, now, false))
 			wait = true;
+	}
 
 	if (wait)
 		msleep(APERFMPERF_REFRESH_DELAY_MS);
@@ -118,6 +125,9 @@ unsigned int arch_freq_get_on_cpu(int cpu)
 	if (!static_cpu_has(X86_FEATURE_APERFMPERF))
 		return 0;
 
+	if (!housekeeping_cpu(cpu, HK_FLAG_FREQ))
+		return 0;
+
 	if (aperfmperf_snapshot_cpu(cpu, ktime_get(), true))
 		return per_cpu(samples.khz, cpu);
 
diff --git a/include/linux/sched/isolation.h b/include/linux/sched/isolation.h
index b0fb1446fe04..88e6013ac8a9 100644
--- a/include/linux/sched/isolation.h
+++ b/include/linux/sched/isolation.h
@@ -13,6 +13,7 @@ enum hk_flags {
 	HK_FLAG_TICK		= (1 << 4),
 	HK_FLAG_DOMAIN		= (1 << 5),
 	HK_FLAG_WQ		= (1 << 6),
+	HK_FLAG_FREQ		= (1 << 7),
 };
 
 #ifdef CONFIG_CPU_ISOLATION
diff --git a/kernel/sched/isolation.c b/kernel/sched/isolation.c
index b02d148e7672..456b5f1dfa11 100644
--- a/kernel/sched/isolation.c
+++ b/kernel/sched/isolation.c
@@ -140,6 +140,12 @@ static int __init housekeeping_isolcpus_setup(char *str)
 			continue;
 		}
 
+		if (!strncmp(str, "freq,", 5)) {
+			str += 5;
+			flags |= HK_FLAG_FREQ;
+			continue;
+		}
+
 		pr_warn("isolcpus: Error, unknown flag\n");
 		return 0;
 	}