[<prev] [next>] [thread-next>] [day] [month] [year] [list]
Message-Id: <20211117023751.24190-1-feng.tang@intel.com>
Date: Wed, 17 Nov 2021 10:37:50 +0800
From: Feng Tang <feng.tang@...el.com>
To: Thomas Gleixner <tglx@...utronix.de>,
Ingo Molnar <mingo@...hat.com>, Borislav Petkov <bp@...en8.de>,
Dave Hansen <dave.hansen@...el.com>,
"H . Peter Anvin" <hpa@...or.com>,
Peter Zijlstra <peterz@...radead.org>, x86@...nel.org,
linux-kernel@...r.kernel.org
Cc: paulmck@...nel.org, rui.zhang@...el.com, andi.kleen@...el.com,
len.brown@...el.com, tim.c.chen@...el.com,
Feng Tang <feng.tang@...el.com>
Subject: [PATCH v3 1/2] x86/tsc: add a timer to make sure tsc_adjust is always checked
Normally the tsc_sync will get checked every time system enters idle state,
but Thomas Gleixner mentioned there is still a caveat that a system won't
enter idle [1], either because it's too busy or configured purposely to not
enter idle. Setup a periodic timer (every 10 minitues) to make sure the
check is always on.
[1]. https://lore.kernel.org/lkml/875z286xtk.fsf@nanos.tec.linutronix.de/
Signed-off-by: Feng Tang <feng.tang@...el.com>
---
Change log:
v3:
* rebase against 5.16-rc1
* small change to code comments and commit log
v2:
* skip timer setup when tsc_clocksource_reliabe==1 (Thomas)
* refine comment and code format (Thomas)
arch/x86/kernel/tsc_sync.c | 41 ++++++++++++++++++++++++++++++++++++++
1 file changed, 41 insertions(+)
diff --git a/arch/x86/kernel/tsc_sync.c b/arch/x86/kernel/tsc_sync.c
index 50a4515fe0ad..911df742145f 100644
--- a/arch/x86/kernel/tsc_sync.c
+++ b/arch/x86/kernel/tsc_sync.c
@@ -30,6 +30,7 @@ struct tsc_adjust {
};
static DEFINE_PER_CPU(struct tsc_adjust, tsc_adjust);
+static struct timer_list tsc_sync_check_timer;
/*
* TSC's on different sockets may be reset asynchronously.
@@ -77,6 +78,46 @@ void tsc_verify_tsc_adjust(bool resume)
}
}
+/*
+ * Normally the tsc_sync will be checked every time system enters idle
+ * state, but there is still caveat that a system won't enter idle,
+ * either because it's too busy or configured purposely to not enter
+ * idle.
+ *
+ * So setup a periodic timer (every 10 minutes) to make sure the check
+ * is always on.
+ */
+
+#define SYNC_CHECK_INTERVAL (HZ * 600)
+
+static void tsc_sync_check_timer_fn(struct timer_list *unused)
+{
+ int next_cpu;
+
+ tsc_verify_tsc_adjust(false);
+
+ /* Run the check for all onlined CPUs in turn */
+ next_cpu = cpumask_next(raw_smp_processor_id(), cpu_online_mask);
+ if (next_cpu >= nr_cpu_ids)
+ next_cpu = cpumask_first(cpu_online_mask);
+
+ tsc_sync_check_timer.expires += SYNC_CHECK_INTERVAL;
+ add_timer_on(&tsc_sync_check_timer, next_cpu);
+}
+
+static int __init start_sync_check_timer(void)
+{
+ if (!boot_cpu_has(X86_FEATURE_TSC_ADJUST) || tsc_clocksource_reliable)
+ return 0;
+
+ timer_setup(&tsc_sync_check_timer, tsc_sync_check_timer_fn, 0);
+ tsc_sync_check_timer.expires = jiffies + SYNC_CHECK_INTERVAL;
+ add_timer(&tsc_sync_check_timer);
+
+ return 0;
+}
+late_initcall(start_sync_check_timer);
+
static void tsc_sanitize_first_cpu(struct tsc_adjust *cur, s64 bootval,
unsigned int cpu, bool bootcpu)
{
--
2.27.0
Powered by blists - more mailing lists