[clocksource,3/5] clocksource: Check per-CPU clock synchronization when marked unstable
diff mbox series

Message ID 20210217212923.21418-3-paulmck@kernel.org
State In Next
Commit 860a912c1a0a855676dc52c4e04a1048775752ac
Headers show
Series
  • [clocksource,1/5] clocksource: Provide module parameters to inject delays in watchdog
Related show

Commit Message

Paul E. McKenney Feb. 17, 2021, 9:29 p.m. UTC
From: "Paul E. McKenney" <paulmck@kernel.org>

Some sorts of per-CPU clock sources have a history of going out of
synchronization with each other.  However, this problem has purportedy
been solved in the past ten years.  Except that it is all too possible
that the problem has instead simply been made less likely, which might
mean that some of the occasional "Marking clocksource 'tsc' as unstable"
messages might be due to desynchronization.  How would anyone know?

This commit therefore adds CPU-to-CPU synchronization checking
for newly unstable clocksource that are marked with the new
CLOCK_SOURCE_VERIFY_PERCPU flag.  Lists of desynchronized CPUs are
printed, with the caveat that if it is the reporting CPU that is itself
desynchronized, it will appear that all the other clocks are wrong.
Just like in real life.

Cc: John Stultz <john.stultz@linaro.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Stephen Boyd <sboyd@kernel.org>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Mark Rutland <Mark.Rutland@arm.com>
Cc: Marc Zyngier <maz@kernel.org>
Cc: Andi Kleen <ak@linux.intel.com>
Reported-by: Chris Mason <clm@fb.com>
[ paulmck: Add "static" to clocksource_verify_one_cpu() per kernel test robot feedback. ]
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
---
 arch/x86/kernel/kvmclock.c  |  2 +-
 arch/x86/kernel/tsc.c       |  3 +-
 include/linux/clocksource.h |  2 +-
 kernel/time/clocksource.c   | 73 +++++++++++++++++++++++++++++++++++++++++++++
 4 files changed, 77 insertions(+), 3 deletions(-)

Patch
diff mbox series

diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c
index aa59374..337bb2c 100644
--- a/arch/x86/kernel/kvmclock.c
+++ b/arch/x86/kernel/kvmclock.c
@@ -169,7 +169,7 @@  struct clocksource kvm_clock = {
 	.read	= kvm_clock_get_cycles,
 	.rating	= 400,
 	.mask	= CLOCKSOURCE_MASK(64),
-	.flags	= CLOCK_SOURCE_IS_CONTINUOUS,
+	.flags	= CLOCK_SOURCE_IS_CONTINUOUS | CLOCK_SOURCE_VERIFY_PERCPU,
 	.enable	= kvm_cs_enable,
 };
 EXPORT_SYMBOL_GPL(kvm_clock);
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index f70dffc..5628917 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -1151,7 +1151,8 @@  static struct clocksource clocksource_tsc = {
 	.mask			= CLOCKSOURCE_MASK(64),
 	.flags			= CLOCK_SOURCE_IS_CONTINUOUS |
 				  CLOCK_SOURCE_VALID_FOR_HRES |
-				  CLOCK_SOURCE_MUST_VERIFY,
+				  CLOCK_SOURCE_MUST_VERIFY |
+				  CLOCK_SOURCE_VERIFY_PERCPU,
 	.vdso_clock_mode	= VDSO_CLOCKMODE_TSC,
 	.enable			= tsc_cs_enable,
 	.resume			= tsc_resume,
diff --git a/include/linux/clocksource.h b/include/linux/clocksource.h
index 86d143d..83a3ebf 100644
--- a/include/linux/clocksource.h
+++ b/include/linux/clocksource.h
@@ -131,7 +131,7 @@  struct clocksource {
 #define CLOCK_SOURCE_UNSTABLE			0x40
 #define CLOCK_SOURCE_SUSPEND_NONSTOP		0x80
 #define CLOCK_SOURCE_RESELECT			0x100
-
+#define CLOCK_SOURCE_VERIFY_PERCPU		0x200
 /* simplify initialization of mask field */
 #define CLOCKSOURCE_MASK(bits) GENMASK_ULL((bits) - 1, 0)
 
diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c
index 3f734c6..663bc53 100644
--- a/kernel/time/clocksource.c
+++ b/kernel/time/clocksource.c
@@ -211,6 +211,78 @@  static void clocksource_watchdog_inject_delay(void)
 	WARN_ON_ONCE(injectfail < 0);
 }
 
+static struct clocksource *clocksource_verify_work_cs;
+static DEFINE_PER_CPU(u64, csnow_mid);
+static cpumask_t cpus_ahead;
+static cpumask_t cpus_behind;
+
+static void clocksource_verify_one_cpu(void *csin)
+{
+	struct clocksource *cs = (struct clocksource *)csin;
+
+	__this_cpu_write(csnow_mid, cs->read(cs));
+}
+
+static void clocksource_verify_percpu_wq(struct work_struct *unused)
+{
+	int cpu;
+	struct clocksource *cs;
+	int64_t cs_nsec;
+	u64 csnow_begin;
+	u64 csnow_end;
+	u64 delta;
+
+	cs = smp_load_acquire(&clocksource_verify_work_cs); // pairs with release
+	if (WARN_ON_ONCE(!cs))
+		return;
+	pr_warn("Checking clocksource %s synchronization from CPU %d.\n",
+		cs->name, smp_processor_id());
+	cpumask_clear(&cpus_ahead);
+	cpumask_clear(&cpus_behind);
+	csnow_begin = cs->read(cs);
+	smp_call_function(clocksource_verify_one_cpu, cs, 1);
+	csnow_end = cs->read(cs);
+	for_each_online_cpu(cpu) {
+		if (cpu == smp_processor_id())
+			continue;
+		delta = (per_cpu(csnow_mid, cpu) - csnow_begin) & cs->mask;
+		if ((s64)delta < 0)
+			cpumask_set_cpu(cpu, &cpus_behind);
+		delta = (csnow_end - per_cpu(csnow_mid, cpu)) & cs->mask;
+		if ((s64)delta < 0)
+			cpumask_set_cpu(cpu, &cpus_ahead);
+	}
+	if (!cpumask_empty(&cpus_ahead))
+		pr_warn("        CPUs %*pbl ahead of CPU %d for clocksource %s.\n",
+			cpumask_pr_args(&cpus_ahead),
+			smp_processor_id(), cs->name);
+	if (!cpumask_empty(&cpus_behind))
+		pr_warn("        CPUs %*pbl behind CPU %d for clocksource %s.\n",
+			cpumask_pr_args(&cpus_behind),
+			smp_processor_id(), cs->name);
+	if (!cpumask_empty(&cpus_ahead) || !cpumask_empty(&cpus_behind)) {
+		delta = clocksource_delta(csnow_end, csnow_begin, cs->mask);
+		cs_nsec = clocksource_cyc2ns(delta, cs->mult, cs->shift);
+		pr_warn("        CPU %d duration %lldns for clocksource %s.\n",
+			smp_processor_id(), cs_nsec, cs->name);
+	}
+	smp_store_release(&clocksource_verify_work_cs, NULL); // pairs with acquire.
+}
+
+static DECLARE_WORK(clocksource_verify_work, clocksource_verify_percpu_wq);
+
+static void clocksource_verify_percpu(struct clocksource *cs)
+{
+	if (!(cs->flags & CLOCK_SOURCE_VERIFY_PERCPU))
+		return;
+	if (smp_load_acquire(&clocksource_verify_work_cs)) { // pairs with release.
+		pr_warn("Previous clocksource synchronization still in flight.\n");
+		return;
+	}
+	smp_store_release(&clocksource_verify_work_cs, cs); //pairs with acquire.
+	queue_work(system_highpri_wq, &clocksource_verify_work);
+}
+
 static void clocksource_watchdog(struct timer_list *unused)
 {
 	struct clocksource *cs;
@@ -284,6 +356,7 @@  static void clocksource_watchdog(struct timer_list *unused)
 				watchdog->name, wdnow, wdlast, watchdog->mask);
 			pr_warn("                      '%s' cs_now: %llx cs_last: %llx mask: %llx\n",
 				cs->name, csnow, cslast, cs->mask);
+			clocksource_verify_percpu(cs);
 			__clocksource_unstable(cs);
 			continue;
 		}