public inbox for linuxppc-dev@ozlabs.org
 help / color / mirror / Atom feed
From: Ricardo Neri <ricardo.neri-calderon@linux.intel.com>
To: Tony Luck <tony.luck@intel.com>,
	Dave Hansen <dave.hansen@intel.com>,
	"Rafael J. Wysocki" <rafael.j.wysocki@intel.com>,
	Reinette Chatre <reinette.chatre@intel.com>,
	Dan Williams <dan.j.williams@intel.com>,
	Len Brown <len.brown@intel.com>
Cc: "Ravi V. Shankar" <ravi.v.shankar@intel.com>,
	Andi Kleen <ak@linux.intel.com>,
	Ricardo Neri <ricardo.neri-calderon@linux.intel.com>,
	Ricardo Neri <ricardo.neri@intel.com>,
	Stephane Eranian <eranian@google.com>,
	linux-kernel@vger.kernel.org, iommu@lists.linux-foundation.org,
	Nicholas Piggin <npiggin@gmail.com>,
	Andrew Morton <akpm@linux-foundation.org>,
	linuxppc-dev@lists.ozlabs.org
Subject: [PATCH v7 17/24] watchdog/hardlockup: Decouple the hardlockup detector from perf
Date: Wed,  1 Mar 2023 15:47:46 -0800	[thread overview]
Message-ID: <20230301234753.28582-18-ricardo.neri-calderon@linux.intel.com> (raw)
In-Reply-To: <20230301234753.28582-1-ricardo.neri-calderon@linux.intel.com>

The current default implementation of the hardlockup detector assumes that
it is implemented using perf events. However, the hardlockup detector can
be driven by other sources of non-maskable interrupts (e.g., a properly
configured timer).

Group and wrap in #ifdef CONFIG_HARDLOCKUP_DETECTOR_PERF all the code
specific to perf: create and manage perf events, stop and start the perf-
based detector.

The generic portion of the detector (monitor the timers' thresholds, check
timestamps and detect hardlockups as well as the implementation of
arch_touch_nmi_watchdog()) is now selected with the new intermediate config
symbol CONFIG_HARDLOCKUP_DETECTOR_CORE.

The perf-based implementation of the detector selects the new intermediate
symbol. Other implementations should do the same.

Cc: Andi Kleen <ak@linux.intel.com>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: "Ravi V. Shankar" <ravi.v.shankar@intel.com>
Cc: iommu@lists.linux-foundation.org
Cc: linuxppc-dev@lists.ozlabs.org
Reviewed-by: Tony Luck <tony.luck@intel.com>
Signed-off-by: Ricardo Neri <ricardo.neri-calderon@linux.intel.com>
---
Changes since v6:
 * None

Changes since v5:
 * None

Changes since v4:
 * None

Changes since v3:
 * Squashed into this patch a previous patch to make
   arch_touch_nmi_watchdog() part of the core detector code.

Changes since v2:
 * Undid split of the generic hardlockup detector into a separate file.
   (Thomas Gleixner)
 * Added a new intermediate symbol CONFIG_HARDLOCKUP_DETECTOR_CORE to
   select generic parts of the detector (Paul E. McKenney,
   Thomas Gleixner).

Changes since v1:
 * Make the generic detector code with CONFIG_HARDLOCKUP_DETECTOR.
---
 include/linux/nmi.h   |  5 ++++-
 kernel/Makefile       |  2 +-
 kernel/watchdog_hld.c | 32 ++++++++++++++++++++------------
 lib/Kconfig.debug     |  4 ++++
 4 files changed, 29 insertions(+), 14 deletions(-)

diff --git a/include/linux/nmi.h b/include/linux/nmi.h
index 75038cb2710e..a38c4509f9eb 100644
--- a/include/linux/nmi.h
+++ b/include/linux/nmi.h
@@ -94,8 +94,11 @@ static inline void hardlockup_detector_disable(void) {}
 # define NMI_WATCHDOG_SYSCTL_PERM	0444
 #endif
 
-#if defined(CONFIG_HARDLOCKUP_DETECTOR_PERF)
+#if defined(CONFIG_HARDLOCKUP_DETECTOR_CORE)
 extern void arch_touch_nmi_watchdog(void);
+#endif
+
+#if defined(CONFIG_HARDLOCKUP_DETECTOR_PERF)
 extern void hardlockup_detector_perf_stop(void);
 extern void hardlockup_detector_perf_restart(void);
 extern void hardlockup_detector_perf_disable(void);
diff --git a/kernel/Makefile b/kernel/Makefile
index 10ef068f598d..f35fad36cf81 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -91,7 +91,7 @@ obj-$(CONFIG_FAIL_FUNCTION) += fail_function.o
 obj-$(CONFIG_KGDB) += debug/
 obj-$(CONFIG_DETECT_HUNG_TASK) += hung_task.o
 obj-$(CONFIG_LOCKUP_DETECTOR) += watchdog.o
-obj-$(CONFIG_HARDLOCKUP_DETECTOR_PERF) += watchdog_hld.o
+obj-$(CONFIG_HARDLOCKUP_DETECTOR_CORE) += watchdog_hld.o
 obj-$(CONFIG_SECCOMP) += seccomp.o
 obj-$(CONFIG_RELAY) += relay.o
 obj-$(CONFIG_SYSCTL) += utsname_sysctl.o
diff --git a/kernel/watchdog_hld.c b/kernel/watchdog_hld.c
index b352e507b17f..bb6435978c46 100644
--- a/kernel/watchdog_hld.c
+++ b/kernel/watchdog_hld.c
@@ -22,12 +22,8 @@
 
 static DEFINE_PER_CPU(bool, hard_watchdog_warn);
 static DEFINE_PER_CPU(bool, watchdog_nmi_touch);
-static DEFINE_PER_CPU(struct perf_event *, watchdog_ev);
-static DEFINE_PER_CPU(struct perf_event *, dead_event);
-static struct cpumask dead_events_mask;
 
 static unsigned long hardlockup_allcpu_dumped;
-static atomic_t watchdog_cpus = ATOMIC_INIT(0);
 
 notrace void arch_touch_nmi_watchdog(void)
 {
@@ -98,14 +94,6 @@ static inline bool watchdog_check_timestamp(void)
 }
 #endif
 
-static struct perf_event_attr wd_hw_attr = {
-	.type		= PERF_TYPE_HARDWARE,
-	.config		= PERF_COUNT_HW_CPU_CYCLES,
-	.size		= sizeof(struct perf_event_attr),
-	.pinned		= 1,
-	.disabled	= 1,
-};
-
 void inspect_for_hardlockups(struct pt_regs *regs)
 {
 	if (__this_cpu_read(watchdog_nmi_touch) == true) {
@@ -157,6 +145,24 @@ void inspect_for_hardlockups(struct pt_regs *regs)
 	return;
 }
 
+#ifdef CONFIG_HARDLOCKUP_DETECTOR_PERF
+#undef pr_fmt
+#define pr_fmt(fmt) "NMI perf watchdog: " fmt
+
+static DEFINE_PER_CPU(struct perf_event *, watchdog_ev);
+static DEFINE_PER_CPU(struct perf_event *, dead_event);
+static struct cpumask dead_events_mask;
+
+static atomic_t watchdog_cpus = ATOMIC_INIT(0);
+
+static struct perf_event_attr wd_hw_attr = {
+	.type		= PERF_TYPE_HARDWARE,
+	.config		= PERF_COUNT_HW_CPU_CYCLES,
+	.size		= sizeof(struct perf_event_attr),
+	.pinned		= 1,
+	.disabled	= 1,
+};
+
 /* Callback function for perf event subsystem */
 static void watchdog_overflow_callback(struct perf_event *event,
 				       struct perf_sample_data *data,
@@ -298,3 +304,5 @@ int __init hardlockup_detector_perf_init(void)
 	}
 	return ret;
 }
+
+#endif /* CONFIG_HARDLOCKUP_DETECTOR_PERF */
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index c8b379e2e9ad..1ff53c5995b1 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -1025,9 +1025,13 @@ config BOOTPARAM_SOFTLOCKUP_PANIC
 
 	  Say N if unsure.
 
+config HARDLOCKUP_DETECTOR_CORE
+	bool
+
 config HARDLOCKUP_DETECTOR_PERF
 	bool
 	select SOFTLOCKUP_DETECTOR
+	select HARDLOCKUP_DETECTOR_CORE
 
 #
 # Enables a timestamp based low pass filter to compensate for perf based
-- 
2.25.1


  parent reply	other threads:[~2023-03-01 23:54 UTC|newest]

Thread overview: 29+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2023-03-01 23:47 [PATCH v7 00/24] x86: Implement an HPET-based hardlockup detector Ricardo Neri
2023-03-01 23:47 ` [PATCH v7 01/24] x86/apic: Add irq_cfg::delivery_mode Ricardo Neri
2023-03-01 23:47 ` [PATCH v7 02/24] x86/apic/msi: Use the delivery mode from irq_cfg for message composition Ricardo Neri
2023-03-01 23:47 ` [PATCH v7 03/24] x86/apic: Add the X86_IRQ_ALLOC_AS_NMI interrupt allocation flag Ricardo Neri
2023-03-01 23:47 ` [PATCH v7 04/24] x86/apic/vector: Implement a local APIC NMI controller Ricardo Neri
2023-03-01 23:47 ` [PATCH v7 05/24] x86/apic/vector: Skip cleanup for the NMI vector Ricardo Neri
2023-03-01 23:47 ` [PATCH v7 06/24] iommu/vt-d: Clear the redirection hint when the destination mode is physical Ricardo Neri
2023-03-01 23:47 ` [PATCH v7 07/24] iommu/vt-d: Rework prepare_irte() to support per-interrupt delivery mode Ricardo Neri
2023-03-01 23:47 ` [PATCH v7 08/24] iommu/vt-d: Set the IRTE delivery mode individually for each interrupt Ricardo Neri
2023-03-01 23:47 ` [PATCH v7 09/24] iommu/amd: Expose [set|get]_dev_entry_bit() Ricardo Neri
2023-03-01 23:47 ` [PATCH v7 10/24] iommu/amd: Enable NMIPass when allocating an NMI Ricardo Neri
2023-03-01 23:47 ` [PATCH v7 11/24] iommu/amd: Compose MSI messages for NMIs in non-IR format Ricardo Neri
2023-03-01 23:47 ` [PATCH v7 12/24] x86/hpet: Expose hpet_writel() in header Ricardo Neri
2023-03-01 23:47 ` [PATCH v7 13/24] x86/hpet: Add helper function hpet_set_comparator_periodic() Ricardo Neri
2023-03-01 23:47 ` [PATCH v7 14/24] x86/hpet: Prepare IRQ assignments to use the X86_ALLOC_AS_NMI flag Ricardo Neri
2023-03-01 23:47 ` [PATCH v7 15/24] x86/hpet: Reserve an HPET channel for the hardlockup detector Ricardo Neri
2023-03-01 23:47 ` [PATCH v7 16/24] watchdog/hardlockup: Define a generic function to detect hardlockups Ricardo Neri
2023-03-01 23:47 ` Ricardo Neri [this message]
2023-03-01 23:47 ` [PATCH v7 18/24] init/main: Delay initialization of the lockup detector after smp_init() Ricardo Neri
2023-03-01 23:47 ` [PATCH v7 19/24] x86/watchdog/hardlockup: Add an HPET-based hardlockup detector Ricardo Neri
2026-02-03 17:02   ` Thomas Gleixner
2023-03-01 23:47 ` [PATCH v7 20/24] x86/watchdog/hardlockup/hpet: Determine if HPET timer caused NMI Ricardo Neri
2023-03-01 23:47 ` [PATCH v7 21/24] watchdog/hardlockup/hpet: Only enable the HPET watchdog via a boot parameter Ricardo Neri
2023-03-01 23:47 ` [PATCH v7 22/24] x86/watchdog: Add a shim hardlockup detector Ricardo Neri
2023-03-01 23:47 ` [PATCH v7 23/24] watchdog: Introduce hardlockup_detector_mark_unavailable() Ricardo Neri
2023-03-01 23:47 ` [PATCH v7 24/24] x86/tsc: Stop the HPET hardlockup detector if TSC become unstable Ricardo Neri
2023-04-13  3:58 ` [PATCH v7 00/24] x86: Implement an HPET-based hardlockup detector Ricardo Neri
2026-02-03 15:58   ` Thomas Gleixner
2026-02-04  5:02     ` Ricardo Neri

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20230301234753.28582-18-ricardo.neri-calderon@linux.intel.com \
    --to=ricardo.neri-calderon@linux.intel.com \
    --cc=ak@linux.intel.com \
    --cc=akpm@linux-foundation.org \
    --cc=dan.j.williams@intel.com \
    --cc=dave.hansen@intel.com \
    --cc=eranian@google.com \
    --cc=iommu@lists.linux-foundation.org \
    --cc=len.brown@intel.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linuxppc-dev@lists.ozlabs.org \
    --cc=npiggin@gmail.com \
    --cc=rafael.j.wysocki@intel.com \
    --cc=ravi.v.shankar@intel.com \
    --cc=reinette.chatre@intel.com \
    --cc=ricardo.neri@intel.com \
    --cc=tony.luck@intel.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox