linux-kernel - [RFC PATCH v5 05/16] watchdog/hardlockup: Decouple the hardlockup detector from perf

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-Id: <20210504190526.22347-6-ricardo.neri-calderon@linux.intel.com>
Date:   Tue,  4 May 2021 12:05:15 -0700
From:   Ricardo Neri <ricardo.neri-calderon@...ux.intel.com>
To:     Thomas Gleixner <tglx@...utronix.de>,
        Ingo Molnar <mingo@...nel.org>, Borislav Petkov <bp@...e.de>
Cc:     "H. Peter Anvin" <hpa@...or.com>, Ashok Raj <ashok.raj@...el.com>,
        Andi Kleen <ak@...ux.intel.com>,
        Tony Luck <tony.luck@...el.com>,
        Nicholas Piggin <npiggin@...il.com>,
        "Peter Zijlstra (Intel)" <peterz@...radead.org>,
        Andrew Morton <akpm@...ux-foundation.org>,
        Stephane Eranian <eranian@...gle.com>,
        Suravee Suthikulpanit <Suravee.Suthikulpanit@....com>,
        "Ravi V. Shankar" <ravi.v.shankar@...el.com>,
        Ricardo Neri <ricardo.neri@...el.com>, x86@...nel.org,
        linux-kernel@...r.kernel.org,
        Ricardo Neri <ricardo.neri-calderon@...ux.intel.com>,
        Andi Kleen <andi.kleen@...el.com>,
        linuxppc-dev@...ts.ozlabs.org
Subject: [RFC PATCH v5 05/16] watchdog/hardlockup: Decouple the hardlockup detector from perf

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: "H. Peter Anvin" <hpa@...or.com>
Cc: Ashok Raj <ashok.raj@...el.com>
Cc: Andi Kleen <andi.kleen@...el.com>
Cc: Tony Luck <tony.luck@...el.com>
Cc: Nicholas Piggin <npiggin@...il.com>
Cc: Peter Zijlstra <peterz@...radead.org>
Cc: Andrew Morton <akpm@...ux-foundation.org>
Cc: Stephane Eranian <eranian@...gle.com>
Cc: Suravee Suthikulpanit <Suravee.Suthikulpanit@....com>
Cc: "Ravi V. Shankar" <ravi.v.shankar@...el.com>
Cc: x86@...nel.org
Cc: linuxppc-dev@...ts.ozlabs.org
Signed-off-by: Ricardo Neri <ricardo.neri-calderon@...ux.intel.com>
---
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 1b68f48ad440..cf12380e51b3 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 e8a6715f38dc..03ac041abfff 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -95,7 +95,7 @@ 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 5918e1686736..08332b5ad4fe 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -1021,9 +1021,13 @@ config BOOTPARAM_SOFTLOCKUP_PANIC_VALUE
 	default 0 if !BOOTPARAM_SOFTLOCKUP_PANIC
 	default 1 if BOOTPARAM_SOFTLOCKUP_PANIC
 
+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
-- 
2.17.1