[v5,6/6] arm64: Enable perf events based hard lockup detector

Commit Message

Lecopzer Chen June 13, 2022, 1:59 p.m. UTC

With the recent feature added to enable perf events to use pseudo NMIs
as interrupts on platforms which support GICv3 or later, its now been
possible to enable hard lockup detector (or NMI watchdog) on arm64
platforms. So enable corresponding support.

One thing to note here is that normally lockup detector is initialized
just after the early initcalls but PMU on arm64 comes up much later as
device_initcall(). To cope with that, overriding watchdog_nmi_probe() to
let the watchdog framework know PMU not ready, and inform the framework
to re-initialize lockup detection once PMU has been initialized.

[1]: http://lore.kernel.org/linux-arm-kernel/[e-mail]

Co-developed-by: Sumit Garg <[e-mail]>
Signed-off-by: Sumit Garg <[e-mail]>
Co-developed-by: Pingfan Liu <[e-mail]>
Signed-off-by: Pingfan Liu <[e-mail]>
Signed-off-by: Lecopzer Chen <[e-mail]>
---
 arch/arm64/Kconfig               |  2 ++
 arch/arm64/kernel/perf_event.c   | 12 ++++++++++--
 arch/arm64/kernel/watchdog_hld.c | 14 ++++++++++++++
 drivers/perf/arm_pmu.c           |  5 +++++
 include/linux/perf/arm_pmu.h     |  2 ++
 5 files changed, 33 insertions(+), 2 deletions(-)

Patch

diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 1652a9800ebe..a0dc5097b609 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -187,12 +187,14 @@  config ARM64
 	select HAVE_FUNCTION_ERROR_INJECTION
 	select HAVE_FUNCTION_GRAPH_TRACER
 	select HAVE_GCC_PLUGINS
+	select HAVE_HARDLOCKUP_DETECTOR_PERF if PERF_EVENTS && HAVE_PERF_EVENTS_NMI
 	select HAVE_HW_BREAKPOINT if PERF_EVENTS
 	select HAVE_IRQ_TIME_ACCOUNTING
 	select HAVE_KVM
 	select HAVE_NMI
 	select HAVE_PATA_PLATFORM
 	select HAVE_PERF_EVENTS
+	select HAVE_PERF_EVENTS_NMI if ARM64_PSEUDO_NMI
 	select HAVE_PERF_REGS
 	select HAVE_PERF_USER_STACK_DUMP
 	select HAVE_PREEMPT_DYNAMIC_KEY
diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c
index cb69ff1e6138..d9eec8911bf0 100644
--- a/arch/arm64/kernel/perf_event.c
+++ b/arch/arm64/kernel/perf_event.c
@@ -23,6 +23,7 @@ 
 #include <linux/platform_device.h>
 #include <linux/sched_clock.h>
 #include <linux/smp.h>
+#include <linux/nmi.h>
 
 /* ARMv8 Cortex-A53 specific event types. */
 #define ARMV8_A53_PERFCTR_PREF_LINEFILL				0xC2
@@ -1390,10 +1391,17 @@  static struct platform_driver armv8_pmu_driver = {
 
 static int __init armv8_pmu_driver_init(void)
 {
+	int ret;
+
 	if (acpi_disabled)
-		return platform_driver_register(&armv8_pmu_driver);
+		ret = platform_driver_register(&armv8_pmu_driver);
 	else
-		return arm_pmu_acpi_probe(armv8_pmuv3_pmu_init);
+		ret = arm_pmu_acpi_probe(armv8_pmuv3_pmu_init);
+
+	if (!ret)
+		retry_lockup_detector_init();
+
+	return ret;
 }
 device_initcall(armv8_pmu_driver_init)
 
diff --git a/arch/arm64/kernel/watchdog_hld.c b/arch/arm64/kernel/watchdog_hld.c
index de43318e4dd6..c9c6ec889c15 100644
--- a/arch/arm64/kernel/watchdog_hld.c
+++ b/arch/arm64/kernel/watchdog_hld.c
@@ -1,5 +1,7 @@ 
 // SPDX-License-Identifier: GPL-2.0
+#include <linux/nmi.h>
 #include <linux/cpufreq.h>
+#include <linux/perf/arm_pmu.h>
 
 /*
  * Safe maximum CPU frequency in case a particular platform doesn't implement
@@ -23,3 +25,15 @@  u64 hw_nmi_get_sample_period(int watchdog_thresh)
 	return (u64)max_cpu_freq * watchdog_thresh;
 }
 
+int __init watchdog_nmi_probe(void)
+{
+	/*
+	 * hardlockup_detector_perf_init() will success even if Pseudo-NMI turns off,
+	 * however, the pmu interrupts will act like a normal interrupt instead of
+	 * NMI and the hardlockup detector would be broken.
+	 */
+	if (!arm_pmu_irq_is_nmi())
+		return -ENODEV;
+
+	return hardlockup_detector_perf_init();
+}
diff --git a/drivers/perf/arm_pmu.c b/drivers/perf/arm_pmu.c
index 59d3980b8ca2..ceee2c55d436 100644
--- a/drivers/perf/arm_pmu.c
+++ b/drivers/perf/arm_pmu.c
@@ -697,6 +697,11 @@  static int armpmu_get_cpu_irq(struct arm_pmu *pmu, int cpu)
 	return per_cpu(hw_events->irq, cpu);
 }
 
+bool arm_pmu_irq_is_nmi(void)
+{
+	return has_nmi;
+}
+
 /*
  * PMU hardware loses all context when a CPU goes offline.
  * When a CPU is hotplugged back in, since some hardware registers are
diff --git a/include/linux/perf/arm_pmu.h b/include/linux/perf/arm_pmu.h
index 0407a38b470a..29c56c92bab7 100644
--- a/include/linux/perf/arm_pmu.h
+++ b/include/linux/perf/arm_pmu.h
@@ -171,6 +171,8 @@  void kvm_host_pmu_init(struct arm_pmu *pmu);
 #define kvm_host_pmu_init(x)	do { } while(0)
 #endif
 
+bool arm_pmu_irq_is_nmi(void);
+
 /* Internal functions only for core arm_pmu code */
 struct arm_pmu *armpmu_alloc(void);
 struct arm_pmu *armpmu_alloc_atomic(void);