[PATCH v3 2/2] clocksource: Use get_random_bytes() in clocksource_verify_choose_cpus()

[Waiman Long <longman@redhat.com>]

The following bug report happened in a PREEMPT_RT kernel.

[   30.957705] BUG: sleeping function called from invalid context at kernel/locking/spinlock_rt.c:48
[   30.957711] in_atomic(): 1, irqs_disabled(): 0, non_block: 0, pid: 2012, name: kwatchdog
[   30.962673] preempt_count: 1, expected: 0
[   30.962676] RCU nest depth: 0, expected: 0
[   30.962680] 3 locks held by kwatchdog/2012:
[   30.962684]  #0: ffffffff8af2da60 (clocksource_mutex){+.+.}-{3:3}, at: clocksource_watchdog_kthread+0x13/0x50
[   30.967703]  #1: ffffffff8aa8d4d0 (cpu_hotplug_lock){++++}-{0:0}, at: clocksource_verify_percpu.part.0+0x5c/0x330
[   30.972774]  #2: ffff9fe02f5f33e0 ((batched_entropy_u32.lock)){+.+.}-{2:2}, at: get_random_u32+0x4f/0x110
[   30.977827] Preemption disabled at:
[   30.977830] [<ffffffff88c1fe56>] clocksource_verify_percpu.part.0+0x66/0x330
[   30.982837] CPU: 33 PID: 2012 Comm: kwatchdog Not tainted 5.14.0-503.23.1.el9_5.x86_64+rt-debug #1
[   30.982843] Hardware name: HPE ProLiant DL385 Gen10 Plus/ProLiant DL385 Gen10 Plus, BIOS A42 04/29/2021
[   30.982846] Call Trace:
[   30.982850]  <TASK>
[   30.983821]  dump_stack_lvl+0x57/0x81
[   30.983821]  __might_resched.cold+0xf4/0x12f
[   30.983824]  rt_spin_lock+0x4c/0x100
[   30.988833]  get_random_u32+0x4f/0x110
[   30.988833]  clocksource_verify_choose_cpus+0xab/0x1a0
[   30.988833]  clocksource_verify_percpu.part.0+0x6b/0x330
[   30.993894]  __clocksource_watchdog_kthread+0x193/0x1a0
[   30.993898]  clocksource_watchdog_kthread+0x18/0x50
[   30.993898]  kthread+0x114/0x140
[   30.993898]  ret_from_fork+0x2c/0x50
[   31.002864]  </TASK>

It is due to the fact that get_random_u32() is called in
clocksource_verify_choose_cpus() with preemption disabled.  The
batched_entropy_32 local lock and/or the base_crng.lock spinlock will
be acquired. In PREEMPT_RT kernel, they are rtmutexes and the above
warning will be printed if the fast path fails because of contention.

Fix this problem by moving the clocksource_verify_choose_cpus() call
before preempt_disable() while moving the part that needs preemption to
be disabled out into a new clocksource_verify_fixup_cpus() helper that
is called after preempt_disable(). In that way, the get_random_u32()
function will now be called with preemption enabled.

Fixes: 7560c02bdffb ("clocksource: Check per-CPU clock synchronization when marked unstable")
Signed-off-by: Waiman Long <longman@redhat.com>
---
 kernel/time/clocksource.c | 42 ++++++++++++++++++++++++++-------------
 1 file changed, 28 insertions(+), 14 deletions(-)

diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c
index 77d9566d3aa6..08d6ac3a795f 100644
--- a/kernel/time/clocksource.c
+++ b/kernel/time/clocksource.c
@@ -313,23 +313,14 @@ static void clocksource_verify_choose_cpus(void)
 	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)
+	if (n <= 1 || num_online_cpus() <= 1)
 		return;
 
-	/* Make sure to select at least one CPU other than the current CPU. */
-	cpu = cpumask_first(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;
@@ -341,7 +332,7 @@ static void clocksource_verify_choose_cpus(void)
 	 * situations where verify_n_cpus is greater than the number of
 	 * CPUs that are currently online.
 	 */
-	for (i = 1; i < n; i++) {
+	for (i = 0; i < n; i++) {
 		cpu = get_random_u32_below(nr_cpu_ids);
 		cpu = cpumask_next(cpu - 1, cpu_online_mask);
 		if (cpu >= nr_cpu_ids)
@@ -349,9 +340,32 @@ static void clocksource_verify_choose_cpus(void)
 		if (!WARN_ON_ONCE(cpu >= nr_cpu_ids))
 			cpumask_set_cpu(cpu, &cpus_chosen);
 	}
+}
+
+/*
+ * Return: true if success, false if not
+ */
+static bool clocksource_verify_fixup_cpus(void)
+{
+	int testcpu = smp_processor_id();
+	int cpu, n = verify_n_cpus;
+	bool ret;
 
 	/* Don't verify ourselves. */
-	cpumask_clear_cpu(smp_processor_id(), &cpus_chosen);
+	cpumask_clear_cpu(testcpu, &cpus_chosen);
+
+	ret = !cpumask_empty(&cpus_chosen);
+	if (!ret && (n != 0) && (num_online_cpus() > 1)) {
+		/* Make sure to select at least one CPU other than the current CPU. */
+		cpu = cpumask_first(cpu_online_mask);
+		if (cpu == testcpu)
+			cpu = cpumask_next(cpu, cpu_online_mask);
+		if (WARN_ON_ONCE(cpu >= nr_cpu_ids))
+			return false;
+		cpumask_set_cpu(cpu, &cpus_chosen);
+		return true;
+	}
+	return ret;
 }
 
 static void clocksource_verify_one_cpu(void *csin)
@@ -373,9 +387,9 @@ void clocksource_verify_percpu(struct clocksource *cs)
 	cpumask_clear(&cpus_ahead);
 	cpumask_clear(&cpus_behind);
 	cpus_read_lock();
-	preempt_disable();
 	clocksource_verify_choose_cpus();
-	if (cpumask_empty(&cpus_chosen)) {
+	preempt_disable();
+	if (!clocksource_verify_fixup_cpus()) {
 		preempt_enable();
 		cpus_read_unlock();
 		pr_warn("Not enough CPUs to check clocksource '%s'.\n", cs->name);
-- 
2.48.1