Linus,

please pull the latest timers/clocksource branch from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git timers-clocksource-2024-09-16

up to:  4ac1dd3245b9: clocksource: Set cs_watchdog_read() checks based on .uncertainty_margin


Updates for the clocksource watchdog:

  - Make the uncertainty margin handling more robust to prevent false
    positives

  - Clarify comments


Thanks,

	tglx

------------------>
Borislav Petkov (1):
      clocksource: Improve comments for watchdog skew bounds

Paul E. McKenney (2):
      clocksource: Fix comments on WATCHDOG_THRESHOLD & WATCHDOG_MAX_SKEW
      clocksource: Set cs_watchdog_read() checks based on .uncertainty_margin


 kernel/time/clocksource.c | 45 ++++++++++++++++++++++++++++++++-------------
 1 file changed, 32 insertions(+), 13 deletions(-)

diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c
index d0538a75f4c6..23336eecb4f4 100644
--- a/kernel/time/clocksource.c
+++ b/kernel/time/clocksource.c
@@ -113,7 +113,6 @@ static u64 suspend_start;
 
 /*
  * Threshold: 0.0312s, when doubled: 0.0625s.
- * Also a default for cs->uncertainty_margin when registering clocks.
  */
 #define WATCHDOG_THRESHOLD (NSEC_PER_SEC >> 5)
 
@@ -125,6 +124,13 @@ static u64 suspend_start;
  *
  * The default of 500 parts per million is based on NTP's limits.
  * If a clocksource is good enough for NTP, it is good enough for us!
+ *
+ * In other words, by default, even if a clocksource is extremely
+ * precise (for example, with a sub-nanosecond period), the maximum
+ * permissible skew between the clocksource watchdog and the clocksource
+ * under test is not permitted to go below the 500ppm minimum defined
+ * by MAX_SKEW_USEC.  This 500ppm minimum may be overridden using the
+ * CLOCKSOURCE_WATCHDOG_MAX_SKEW_US Kconfig option.
  */
 #ifdef CONFIG_CLOCKSOURCE_WATCHDOG_MAX_SKEW_US
 #define MAX_SKEW_USEC	CONFIG_CLOCKSOURCE_WATCHDOG_MAX_SKEW_US
@@ -132,6 +138,13 @@ static u64 suspend_start;
 #define MAX_SKEW_USEC	(125 * WATCHDOG_INTERVAL / HZ)
 #endif
 
+/*
+ * Default for maximum permissible skew when cs->uncertainty_margin is
+ * not specified, and the lower bound even when cs->uncertainty_margin
+ * is specified.  This is also the default that is used when registering
+ * clocks with unspecifed cs->uncertainty_margin, so this macro is used
+ * even in CONFIG_CLOCKSOURCE_WATCHDOG=n kernels.
+ */
 #define WATCHDOG_MAX_SKEW (MAX_SKEW_USEC * NSEC_PER_USEC)
 
 #ifdef CONFIG_CLOCKSOURCE_WATCHDOG
@@ -231,6 +244,7 @@ enum wd_read_status {
 
 static enum wd_read_status cs_watchdog_read(struct clocksource *cs, u64 *csnow, u64 *wdnow)
 {
+	int64_t md = 2 * watchdog->uncertainty_margin;
 	unsigned int nretries, max_retries;
 	int64_t wd_delay, wd_seq_delay;
 	u64 wd_end, wd_end2;
@@ -245,7 +259,7 @@ static enum wd_read_status cs_watchdog_read(struct clocksource *cs, u64 *csnow,
 		local_irq_enable();
 
 		wd_delay = cycles_to_nsec_safe(watchdog, *wdnow, wd_end);
-		if (wd_delay <= WATCHDOG_MAX_SKEW) {
+		if (wd_delay <= md + cs->uncertainty_margin) {
 			if (nretries > 1 && nretries >= max_retries) {
 				pr_warn("timekeeping watchdog on CPU%d: %s retried %d times before success\n",
 					smp_processor_id(), watchdog->name, nretries);
@@ -258,12 +272,12 @@ static enum wd_read_status cs_watchdog_read(struct clocksource *cs, u64 *csnow,
 		 * there is too much external interferences that cause
 		 * significant delay in reading both clocksource and watchdog.
 		 *
-		 * If consecutive WD read-back delay > WATCHDOG_MAX_SKEW/2,
-		 * report system busy, reinit the watchdog and skip the current
+		 * If consecutive WD read-back delay > md, report
+		 * system busy, reinit the watchdog and skip the current
 		 * watchdog test.
 		 */
 		wd_seq_delay = cycles_to_nsec_safe(watchdog, wd_end, wd_end2);
-		if (wd_seq_delay > WATCHDOG_MAX_SKEW/2)
+		if (wd_seq_delay > md)
 			goto skip_test;
 	}
 
@@ -1146,14 +1160,19 @@ void __clocksource_update_freq_scale(struct clocksource *cs, u32 scale, u32 freq
 	}
 
 	/*
-	 * If the uncertainty margin is not specified, calculate it.
-	 * If both scale and freq are non-zero, calculate the clock
-	 * period, but bound below at 2*WATCHDOG_MAX_SKEW.  However,
-	 * if either of scale or freq is zero, be very conservative and
-	 * take the tens-of-milliseconds WATCHDOG_THRESHOLD value for the
-	 * uncertainty margin.  Allow stupidly small uncertainty margins
-	 * to be specified by the caller for testing purposes, but warn
-	 * to discourage production use of this capability.
+	 * If the uncertainty margin is not specified, calculate it.  If
+	 * both scale and freq are non-zero, calculate the clock period, but
+	 * bound below at 2*WATCHDOG_MAX_SKEW, that is, 500ppm by default.
+	 * However, if either of scale or freq is zero, be very conservative
+	 * and take the tens-of-milliseconds WATCHDOG_THRESHOLD value
+	 * for the uncertainty margin.  Allow stupidly small uncertainty
+	 * margins to be specified by the caller for testing purposes,
+	 * but warn to discourage production use of this capability.
+	 *
+	 * Bottom line:  The sum of the uncertainty margins of the
+	 * watchdog clocksource and the clocksource under test will be at
+	 * least 500ppm by default.  For more information, please see the
+	 * comment preceding CONFIG_CLOCKSOURCE_WATCHDOG_MAX_SKEW_US above.
 	 */
 	if (scale && freq && !cs->uncertainty_margin) {
 		cs->uncertainty_margin = NSEC_PER_SEC / (scale * freq);

The pull request you sent on Mon, 16 Sep 2024 10:38:39 +0200 (CEST):

> git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git timers-clocksource-2024-09-16

has been merged into torvalds/linux.git:
https://git.kernel.org/torvalds/c/a64405b78be95d786e15b2fd0a12999240b28ea5

Thank you!

-- 
Deet-doot-dot, I am a bot.
https://korg.docs.kernel.org/prtracker.html