Updates for the clocksource watchdog:

- Make the uncertainty margin handling more robust to prevent false
     positives
 
   - Clarify comments
 -----BEGIN PGP SIGNATURE-----
 
 iQJHBAABCgAxFiEEQp8+kY+LLUocC4bMphj1TA10mKEFAmbn6xETHHRnbHhAbGlu
 dXRyb25peC5kZQAKCRCmGPVMDXSYoafvEAC30/0ePYUhwnJuhm1DboYLWWVGJlSI
 WpdwmL1YgBUTAjJC0wuYA+Fc8XV9grvxY86bPAsU2Lep85znCSIK/YEO4tsN5Tnq
 +aWGR8Q+2j80MxGCP2mFtG1P0K35P4dopRJgvGmE/xtqKxJ3IPryhfjegHVREDoe
 PNQt59lW1WZhydLXB60S9FCAJeLFRWAoc2tOIr9T2CnsRkc8aXdWnpEU40bN+nFH
 rX09ynPPOlxo5f6z5YWBOuv7LgjvNjmJP3qf8d4Sp4stj7+kI3ipZh6mlolek4l+
 sMlbBAelQk+eiPYPIbthZvMvhM3J+YFXy4nh1LPYSRqWIMsgtobxwNUvWV0CqZaQ
 ZEImJqh+QJA27RAD13Uiv3N68prgW7yj/65b3EbjiK9tka2+67JVWTnlxuuyYu+S
 JxetHfxLKqohGhKAgAeO11efcf4HBh82afqDvMlWvTwDxyqMVLXM2NeT2iOgeYZk
 eH85R7ophcVdQAHZlYagsYA1oQMyT+UD40kiZzrX6WVHqX5ohVpnV/X8cJUVcUGa
 phOdX03ARzTSYdbE+J61bfAMCS2Tme34LkBMgZmooVfKwmnJOCGcskljtLOssm7N
 pTU7dI5dJLt6P+HZ6dbxf0xd0z6mNLXbVDlibEfR1ISfhLOHyH+2ywM0OJFDI0sP
 Ydt3U0n8sNFiXw==
 =Y38F
 -----END PGP SIGNATURE-----

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

Pull clocksource watchdog updates from Thomas Gleixner:

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

 - Clarify comments

* tag 'timers-clocksource-2024-09-16' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  clocksource: Set cs_watchdog_read() checks based on .uncertainty_margin
  clocksource: Fix comments on WATCHDOG_THRESHOLD & WATCHDOG_MAX_SKEW
  clocksource: Improve comments for watchdog skew bounds
This commit is contained in:
Linus Torvalds 2024-09-17 07:05:08 +02:00
commit a64405b78b

View file

@ -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);