All of lore.kernel.org
 help / color / mirror / Atom feed
From: "Paul E. McKenney" <paulmck@kernel.org>
To: tglx@linutronix.de
Cc: linux-kernel@vger.kernel.org, john.stultz@linaro.org,
	sboyd@kernel.org, corbet@lwn.net, Mark.Rutland@arm.com,
	maz@kernel.org, kernel-team@fb.com, neeraju@codeaurora.org,
	ak@linux.intel.com, feng.tang@intel.com, zhengjun.xing@intel.com,
	"Paul E. McKenney" <paulmck@kernel.org>,
	Xing Zhengjun <zhengjun.xing@linux.intel.com>
Subject: [PATCH v11 clocksource 5/6] clocksource: Limit number of CPUs checked for clock synchronization
Date: Wed, 28 Apr 2021 18:30:36 -0700	[thread overview]
Message-ID: <20210429013037.3958717-5-paulmck@kernel.org> (raw)
In-Reply-To: <20210429012909.GA3958584@paulmck-ThinkPad-P17-Gen-1>

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/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@linutronix.de> # For verify_n_cpus=1.
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>
Cc: Feng Tang <feng.tang@intel.com>
Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
---
 .../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 babcc9e80fba..4058a74df9ab 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -626,6 +626,16 @@
 			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 584433448226..f71f375df544 100644
--- a/kernel/time/clocksource.c
+++ b/kernel/time/clocksource.c
@@ -15,6 +15,8 @@
 #include <linux/tick.h>
 #include <linux/kthread.h>
 #include <linux/delay.h>
+#include <linux/prandom.h>
+#include <linux/cpu.h>
 
 #include "tick-internal.h"
 #include "timekeeping_internal.h"
@@ -200,6 +202,8 @@ static int inject_delay_shift_percpu = -1;
 module_param(inject_delay_shift_percpu, int, 0644);
 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 void clocksource_watchdog_inject_delay(void)
 {
@@ -250,6 +254,55 @@ 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)
 {
@@ -271,12 +324,22 @@ 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);
@@ -296,6 +359,7 @@ 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);
@@ -366,6 +430,12 @@ 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


  parent reply	other threads:[~2021-04-29  1:30 UTC|newest]

Thread overview: 22+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-04-29  1:29 [PATCH V11 clocksource 0/6] Do not mark clocks unstable due to delays for v5.13 Paul E. McKenney
2021-04-29  1:30 ` [PATCH v11 clocksource 1/6] clocksource: Provide module parameters to inject delays in watchdog Paul E. McKenney
2021-04-29  1:30 ` [PATCH v11 clocksource 2/6] clocksource: Retry clock read if long delays detected Paul E. McKenney
2021-04-29  1:30 ` [PATCH v11 clocksource 3/6] clocksource: Check per-CPU clock synchronization when marked unstable Paul E. McKenney
2021-04-29  1:30 ` [PATCH v11 clocksource 4/6] clocksource: Provide a module parameter to fuzz per-CPU clock checking Paul E. McKenney
2021-04-29  1:30 ` Paul E. McKenney [this message]
2021-04-29  1:30 ` [PATCH v11 clocksource 6/6] clocksource: Reduce clocksource-skew threshold for TSC Paul E. McKenney
2021-04-29  7:02   ` kernel test robot
2021-04-29  7:02     ` kernel test robot
2021-04-29 14:04     ` Paul E. McKenney
2021-04-29 14:04       ` Paul E. McKenney
2021-04-29 11:13 ` [PATCH V11 clocksource 0/6] Do not mark clocks unstable due to delays for v5.13 Luming Yu
2021-04-30  5:10   ` Paul E. McKenney
2021-04-30  6:52     ` Luming Yu
2021-05-01  4:28       ` Paul E. McKenney
2021-06-02  5:10         ` Luming Yu
2021-06-02 17:46           ` Paul E. McKenney
2021-06-02 18:24             ` Paul E. McKenney
2021-06-03  4:25               ` Luming Yu
2021-06-03 14:40                 ` Paul E. McKenney
2021-06-04  4:23                   ` Luming Yu
2021-06-04 20:26                     ` Paul E. McKenney

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=20210429013037.3958717-5-paulmck@kernel.org \
    --to=paulmck@kernel.org \
    --cc=Mark.Rutland@arm.com \
    --cc=ak@linux.intel.com \
    --cc=corbet@lwn.net \
    --cc=feng.tang@intel.com \
    --cc=john.stultz@linaro.org \
    --cc=kernel-team@fb.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=maz@kernel.org \
    --cc=neeraju@codeaurora.org \
    --cc=sboyd@kernel.org \
    --cc=tglx@linutronix.de \
    --cc=zhengjun.xing@intel.com \
    --cc=zhengjun.xing@linux.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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.