[PATCH v12 clocksource 3/5] clocksource: Limit number of CPUs checked for clock synchronization

[Paul E. McKenney]

Currently, if skew is detected on a clock marked CLOCK_SOURCE_VERIFY_PERCPU,
that clock is checked on all CPUs.  This is thorough, but might not be
what you want on a system with a few tens of CPUs, let alone a few hundred
of them.

Therefore, by default check only up to eight randomly chosen CPUs.
Also provide a new clocksource.verify_n_cpus kernel boot parameter.
A value of -1 says to check all of the CPUs, and a non-negative value says
to randomly select that number of CPUs, without concern about selecting
the same CPU multiple times.  However, make use of a cpumask so that a
given CPU will be checked at most once.

Link: https://lore.kernel.org/lkml/202104291438.PuHsxRkl-lkp@xxxxxxxxx/
Link: https://lore.kernel.org/lkml/20210429140440.GT975577@paulmck-ThinkPad-P17-Gen-1
Link: https://lore.kernel.org/lkml/20210425224540.GA1312438@paulmck-ThinkPad-P17-Gen-1/
Link: https://lore.kernel.org/lkml/20210420064934.GE31773@xsang-OptiPlex-9020/
Link: https://lore.kernel.org/lkml/20210106004013.GA11179@paulmck-ThinkPad-P72/
Link: https://lore.kernel.org/lkml/20210414043435.GA2812539@paulmck-ThinkPad-P17-Gen-1/
Link: https://lore.kernel.org/lkml/20210419045155.GA596058@paulmck-ThinkPad-P17-Gen-1/
Suggested-by: Thomas Gleixner <tglx@xxxxxxxxxxxxx> # For verify_n_cpus=1.
Cc: John Stultz <john.stultz@xxxxxxxxxx>
Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Cc: Stephen Boyd <sboyd@xxxxxxxxxx>
Cc: Jonathan Corbet <corbet@xxxxxxx>
Cc: Mark Rutland <Mark.Rutland@xxxxxxx>
Cc: Marc Zyngier <maz@xxxxxxxxxx>
Cc: Andi Kleen <ak@xxxxxxxxxxxxxxx>
Cc: Feng Tang <feng.tang@xxxxxxxxx>
Cc: Xing Zhengjun <zhengjun.xing@xxxxxxxxxxxxxxx>
Signed-off-by: Paul E. McKenney <paulmck@xxxxxxxxxx>
---
 .../admin-guide/kernel-parameters.txt         | 10 +++
 kernel/time/clocksource.c                     | 74 ++++++++++++++++++-
 2 files changed, 82 insertions(+), 2 deletions(-)

diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index 4ab93f2612a2..485023c99244 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -589,6 +589,16 @@
 			unstable.  Defaults to three retries, that is,
 			four attempts to read the clock under test.
 
+	clocksource.verify_n_cpus= [KNL]
+			Limit the number of CPUs checked for clocksources
+			marked with CLOCK_SOURCE_VERIFY_PERCPU that
+			are marked unstable due to excessive skew.
+			A negative value says to check all CPUs, while
+			zero says not to check any.  Values larger than
+			nr_cpu_ids are silently truncated to nr_cpu_ids.
+			The actual CPUs are chosen randomly, with
+			no replacement if the same CPU is chosen twice.
+
 	clearcpuid=BITNUM[,BITNUM...] [X86]
 			Disable CPUID feature X for the kernel. See
 			arch/x86/include/asm/cpufeatures.h for the valid bit
diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c
index 5ba978a5f45d..8a7d704aa46b 100644
--- a/kernel/time/clocksource.c
+++ b/kernel/time/clocksource.c
@@ -14,6 +14,8 @@
 #include <linux/sched.h> /* for spin_unlock_irq() using preempt_count() m68k */
 #include <linux/tick.h>
 #include <linux/kthread.h>
+#include <linux/prandom.h>
+#include <linux/cpu.h>
 
 #include "tick-internal.h"
 #include "timekeeping_internal.h"
@@ -193,6 +195,8 @@ void clocksource_mark_unstable(struct clocksource *cs)
 
 static ulong max_read_retries = 3;
 module_param(max_read_retries, ulong, 0644);
+static int verify_n_cpus = 8;
+module_param(verify_n_cpus, int, 0644);
 
 static bool cs_watchdog_read(struct clocksource *cs, u64 *csnow, u64 *wdnow)
 {
@@ -226,6 +230,55 @@ static bool cs_watchdog_read(struct clocksource *cs, u64 *csnow, u64 *wdnow)
 static u64 csnow_mid;
 static cpumask_t cpus_ahead;
 static cpumask_t cpus_behind;
+static cpumask_t cpus_chosen;
+
+static void clocksource_verify_choose_cpus(void)
+{
+	int cpu, i, n = verify_n_cpus;
+
+	if (n < 0) {
+		/* Check all of the CPUs. */
+		cpumask_copy(&cpus_chosen, cpu_online_mask);
+		cpumask_clear_cpu(smp_processor_id(), &cpus_chosen);
+		return;
+	}
+
+	/* If no checking desired, or no other CPU to check, leave. */
+	cpumask_clear(&cpus_chosen);
+	if (n == 0 || num_online_cpus() <= 1)
+		return;
+
+	/* Make sure to select at least one CPU other than the current CPU. */
+	cpu = cpumask_next(-1, cpu_online_mask);
+	if (cpu == smp_processor_id())
+		cpu = cpumask_next(cpu, cpu_online_mask);
+	if (WARN_ON_ONCE(cpu >= nr_cpu_ids))
+		return;
+	cpumask_set_cpu(cpu, &cpus_chosen);
+
+	/* Force a sane value for the boot parameter. */
+	if (n > nr_cpu_ids)
+		n = nr_cpu_ids;
+
+	/*
+	 * Randomly select the specified number of CPUs.  If the same
+	 * CPU is selected multiple times, that CPU is checked only once,
+	 * and no replacement CPU is selected.  This gracefully handles
+	 * situations where verify_n_cpus is greater than the number of
+	 * CPUs that are currently online.
+	 */
+	for (i = 1; i < n; i++) {
+		cpu = prandom_u32() % nr_cpu_ids;
+		cpu = cpumask_next(cpu - 1, cpu_online_mask);
+		if (cpu >= nr_cpu_ids)
+			cpu = cpumask_next(-1, cpu_online_mask);
+		if (!WARN_ON_ONCE(cpu >= nr_cpu_ids))
+			cpumask_set_cpu(cpu, &cpus_chosen);
+	}
+
+	/* Don't verify ourselves. */
+	cpumask_clear_cpu(smp_processor_id(), &cpus_chosen);
+}
 
 static void clocksource_verify_one_cpu(void *csin)
 {
@@ -241,12 +294,22 @@ static void clocksource_verify_percpu(struct clocksource *cs)
 	int cpu, testcpu;
 	s64 delta;
 
+	if (verify_n_cpus == 0)
+		return;
 	cpumask_clear(&cpus_ahead);
 	cpumask_clear(&cpus_behind);
+	get_online_cpus();
 	preempt_disable();
+	clocksource_verify_choose_cpus();
+	if (cpumask_weight(&cpus_chosen) == 0) {
+		preempt_enable();
+		put_online_cpus();
+		pr_warn("Not enough CPUs to check clocksource '%s'.\n", cs->name);
+		return;
+	}
 	testcpu = smp_processor_id();
-	pr_warn("Checking clocksource %s synchronization from CPU %d.\n", cs->name, testcpu);
-	for_each_online_cpu(cpu) {
+	pr_warn("Checking clocksource %s synchronization from CPU %d to CPUs %*pbl.\n", cs->name, testcpu, cpumask_pr_args(&cpus_chosen));
+	for_each_cpu(cpu, &cpus_chosen) {
 		if (cpu == testcpu)
 			continue;
 		csnow_begin = cs->read(cs);
@@ -266,6 +329,7 @@ static void clocksource_verify_percpu(struct clocksource *cs)
 			cs_nsec_min = cs_nsec;
 	}
 	preempt_enable();
+	put_online_cpus();
 	if (!cpumask_empty(&cpus_ahead))
 		pr_warn("        CPUs %*pbl ahead of CPU %d for clocksource %s.\n",
 			cpumask_pr_args(&cpus_ahead), testcpu, cs->name);
@@ -336,6 +400,12 @@ 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);
+			if (curr_clocksource == cs)
+				pr_warn("                      '%s' is current clocksource.\n", cs->name);
+			else if (curr_clocksource)
+				pr_warn("                      '%s' (not '%s') is current clocksource.\n", curr_clocksource->name, cs->name);
+			else
+				pr_warn("                      No current clocksource.\n");
 			__clocksource_unstable(cs);
 			continue;
 		}
-- 
2.31.1.189.g2e36527f23