From 8c0abfd6d2f6b0221194241ac2908751a2a0385f Mon Sep 17 00:00:00 2001 From: Paul E. McKenney Date: Wed, 17 Nov 2021 18:57:01 -0800 Subject: rcutorture: Add CONFIG_PREEMPT_DYNAMIC=n to tiny scenarios With CONFIG_PREEMPT_DYNAMIC=y, the kernel builds with CONFIG_PREEMPTION=y because preemption can be enabled at runtime. This prevents any tests of Tiny RCU or Tiny SRCU from running correctly. This commit therefore explicitly sets CONFIG_PREEMPT_DYNAMIC=n for those scenarios. Signed-off-by: Paul E. McKenney --- tools/testing/selftests/rcutorture/configs/rcu/SRCU-T | 1 + tools/testing/selftests/rcutorture/configs/rcu/SRCU-U | 1 + tools/testing/selftests/rcutorture/configs/rcu/TINY01 | 1 + tools/testing/selftests/rcutorture/configs/rcu/TINY02 | 1 + tools/testing/selftests/rcutorture/configs/rcuscale/TINY | 1 + 5 files changed, 5 insertions(+) diff --git a/tools/testing/selftests/rcutorture/configs/rcu/SRCU-T b/tools/testing/selftests/rcutorture/configs/rcu/SRCU-T index d6557c38dfe4..c70cf0405f24 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/SRCU-T +++ b/tools/testing/selftests/rcutorture/configs/rcu/SRCU-T @@ -2,6 +2,7 @@ CONFIG_SMP=n CONFIG_PREEMPT_NONE=y CONFIG_PREEMPT_VOLUNTARY=n CONFIG_PREEMPT=n +CONFIG_PREEMPT_DYNAMIC=n #CHECK#CONFIG_TINY_SRCU=y CONFIG_RCU_TRACE=n CONFIG_DEBUG_LOCK_ALLOC=y diff --git a/tools/testing/selftests/rcutorture/configs/rcu/SRCU-U b/tools/testing/selftests/rcutorture/configs/rcu/SRCU-U index 6bc24e99862f..bc9eeabaa1b1 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/SRCU-U +++ b/tools/testing/selftests/rcutorture/configs/rcu/SRCU-U @@ -2,6 +2,7 @@ CONFIG_SMP=n CONFIG_PREEMPT_NONE=y CONFIG_PREEMPT_VOLUNTARY=n CONFIG_PREEMPT=n +CONFIG_PREEMPT_DYNAMIC=n #CHECK#CONFIG_TINY_SRCU=y CONFIG_RCU_TRACE=n CONFIG_DEBUG_LOCK_ALLOC=n diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TINY01 b/tools/testing/selftests/rcutorture/configs/rcu/TINY01 index 6db705e55487..0953c52fcfd7 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TINY01 +++ b/tools/testing/selftests/rcutorture/configs/rcu/TINY01 @@ -2,6 +2,7 @@ CONFIG_SMP=n CONFIG_PREEMPT_NONE=y CONFIG_PREEMPT_VOLUNTARY=n CONFIG_PREEMPT=n +CONFIG_PREEMPT_DYNAMIC=n #CHECK#CONFIG_TINY_RCU=y CONFIG_HZ_PERIODIC=n CONFIG_NO_HZ_IDLE=y diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TINY02 b/tools/testing/selftests/rcutorture/configs/rcu/TINY02 index d8674264318d..30439f6fc20e 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TINY02 +++ b/tools/testing/selftests/rcutorture/configs/rcu/TINY02 @@ -2,6 +2,7 @@ CONFIG_SMP=n CONFIG_PREEMPT_NONE=y CONFIG_PREEMPT_VOLUNTARY=n CONFIG_PREEMPT=n +CONFIG_PREEMPT_DYNAMIC=n #CHECK#CONFIG_TINY_RCU=y CONFIG_HZ_PERIODIC=y CONFIG_NO_HZ_IDLE=n diff --git a/tools/testing/selftests/rcutorture/configs/rcuscale/TINY b/tools/testing/selftests/rcutorture/configs/rcuscale/TINY index fb05ef5279b4..64e9490c1f79 100644 --- a/tools/testing/selftests/rcutorture/configs/rcuscale/TINY +++ b/tools/testing/selftests/rcutorture/configs/rcuscale/TINY @@ -2,6 +2,7 @@ CONFIG_SMP=n CONFIG_PREEMPT_NONE=y CONFIG_PREEMPT_VOLUNTARY=n CONFIG_PREEMPT=n +CONFIG_PREEMPT_DYNAMIC=n #CHECK#CONFIG_TINY_RCU=y CONFIG_HZ_PERIODIC=n CONFIG_NO_HZ_IDLE=y -- cgit v1.2.3 From c86ff8c55b8ae68837b2fa59dc0c203907e9a15f Mon Sep 17 00:00:00 2001 From: Waiman Long Date: Thu, 18 Nov 2021 14:14:36 -0500 Subject: clocksource: Avoid accidental unstable marking of clocksources Since commit db3a34e17433 ("clocksource: Retry clock read if long delays detected") and commit 2e27e793e280 ("clocksource: Reduce clocksource-skew threshold"), it is found that tsc clocksource fallback to hpet can sometimes happen on both Intel and AMD systems especially when they are running stressful benchmarking workloads. Of the 23 systems tested with a v5.14 kernel, 10 of them have switched to hpet clock source during the test run. The result of falling back to hpet is a drastic reduction of performance when running benchmarks. For example, the fio performance tests can drop up to 70% whereas the iperf3 performance can drop up to 80%. 4 hpet fallbacks happened during bootup. They were: [ 8.749399] clocksource: timekeeping watchdog on CPU13: hpet read-back delay of 263750ns, attempt 4, marking unstable [ 12.044610] clocksource: timekeeping watchdog on CPU19: hpet read-back delay of 186166ns, attempt 4, marking unstable [ 17.336941] clocksource: timekeeping watchdog on CPU28: hpet read-back delay of 182291ns, attempt 4, marking unstable [ 17.518565] clocksource: timekeeping watchdog on CPU34: hpet read-back delay of 252196ns, attempt 4, marking unstable Other fallbacks happen when the systems were running stressful benchmarks. For example: [ 2685.867873] clocksource: timekeeping watchdog on CPU117: hpet read-back delay of 57269ns, attempt 4, marking unstable [46215.471228] clocksource: timekeeping watchdog on CPU8: hpet read-back delay of 61460ns, attempt 4, marking unstable Commit 2e27e793e280 ("clocksource: Reduce clocksource-skew threshold"), changed the skew margin from 100us to 50us. I think this is too small and can easily be exceeded when running some stressful workloads on a thermally stressed system. So it is switched back to 100us. Even a maximum skew margin of 100us may be too small in for some systems when booting up especially if those systems are under thermal stress. To eliminate the case that the large skew is due to the system being too busy slowing down the reading of both the watchdog and the clocksource, an extra consecutive read of watchdog clock is being done to check this. The consecutive watchdog read delay is compared against WATCHDOG_MAX_SKEW/2. If the delay exceeds the limit, we assume that the system is just too busy. A warning will be printed to the console and the clock skew check is skipped for this round. Fixes: db3a34e17433 ("clocksource: Retry clock read if long delays detected") Fixes: 2e27e793e280 ("clocksource: Reduce clocksource-skew threshold") Signed-off-by: Waiman Long Signed-off-by: Paul E. McKenney --- kernel/time/clocksource.c | 50 ++++++++++++++++++++++++++++++++++++++--------- 1 file changed, 41 insertions(+), 9 deletions(-) diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c index b8a14d2fb5ba..bcad1a1e5dcf 100644 --- a/kernel/time/clocksource.c +++ b/kernel/time/clocksource.c @@ -107,7 +107,7 @@ static u64 suspend_start; * This delay could be due to SMIs, NMIs, or to VCPU preemptions. Used as * a lower bound for cs->uncertainty_margin values when registering clocks. */ -#define WATCHDOG_MAX_SKEW (50 * NSEC_PER_USEC) +#define WATCHDOG_MAX_SKEW (100 * NSEC_PER_USEC) #ifdef CONFIG_CLOCKSOURCE_WATCHDOG static void clocksource_watchdog_work(struct work_struct *work); @@ -205,17 +205,24 @@ EXPORT_SYMBOL_GPL(max_cswd_read_retries); static int verify_n_cpus = 8; module_param(verify_n_cpus, int, 0644); -static bool cs_watchdog_read(struct clocksource *cs, u64 *csnow, u64 *wdnow) +enum wd_read_status { + WD_READ_SUCCESS, + WD_READ_UNSTABLE, + WD_READ_SKIP +}; + +static enum wd_read_status cs_watchdog_read(struct clocksource *cs, u64 *csnow, u64 *wdnow) { unsigned int nretries; - u64 wd_end, wd_delta; - int64_t wd_delay; + u64 wd_end, wd_end2, wd_delta; + int64_t wd_delay, wd_seq_delay; for (nretries = 0; nretries <= max_cswd_read_retries; nretries++) { local_irq_disable(); *wdnow = watchdog->read(watchdog); *csnow = cs->read(cs); wd_end = watchdog->read(watchdog); + wd_end2 = watchdog->read(watchdog); local_irq_enable(); wd_delta = clocksource_delta(wd_end, *wdnow, watchdog->mask); @@ -226,13 +233,34 @@ static bool cs_watchdog_read(struct clocksource *cs, u64 *csnow, u64 *wdnow) pr_warn("timekeeping watchdog on CPU%d: %s retried %d times before success\n", smp_processor_id(), watchdog->name, nretries); } - return true; + return WD_READ_SUCCESS; } + + /* + * Now compute delay in consecutive watchdog read to see if + * 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 + * watchdog test. + */ + wd_delta = clocksource_delta(wd_end2, wd_end, watchdog->mask); + wd_seq_delay = clocksource_cyc2ns(wd_delta, watchdog->mult, watchdog->shift); + if (wd_seq_delay > WATCHDOG_MAX_SKEW/2) + goto skip_test; } pr_warn("timekeeping watchdog on CPU%d: %s read-back delay of %lldns, attempt %d, marking unstable\n", smp_processor_id(), watchdog->name, wd_delay, nretries); - return false; + return WD_READ_UNSTABLE; + +skip_test: + pr_info("timekeeping watchdog on CPU%d: %s wd-wd read-back delay of %lldns\n", + smp_processor_id(), watchdog->name, wd_seq_delay); + pr_info("wd-%s-wd read-back delay of %lldns, clock-skew test skipped!\n", + cs->name, wd_delay); + return WD_READ_SKIP; } static u64 csnow_mid; @@ -356,6 +384,7 @@ static void clocksource_watchdog(struct timer_list *unused) int next_cpu, reset_pending; int64_t wd_nsec, cs_nsec; struct clocksource *cs; + enum wd_read_status read_ret; u32 md; spin_lock(&watchdog_lock); @@ -373,9 +402,12 @@ static void clocksource_watchdog(struct timer_list *unused) continue; } - if (!cs_watchdog_read(cs, &csnow, &wdnow)) { - /* Clock readout unreliable, so give it up. */ - __clocksource_unstable(cs); + read_ret = cs_watchdog_read(cs, &csnow, &wdnow); + + if (read_ret != WD_READ_SUCCESS) { + if (read_ret == WD_READ_UNSTABLE) + /* Clock readout unreliable, so give it up. */ + __clocksource_unstable(cs); continue; } -- cgit v1.2.3 From 1a5620671a1b6fd9cc08761677d050f1702f910c Mon Sep 17 00:00:00 2001 From: Waiman Long Date: Thu, 18 Nov 2021 14:14:37 -0500 Subject: clocksource: Reduce the default clocksource_watchdog() retries to 2 With the previous patch, there is an extra watchdog read in each retry. Now the total number of clocksource reads is increased to 4 per iteration. In order to avoid increasing the clock skew check overhead, the default maximum number of retries is reduced from 3 to 2 to maintain the same 12 clocksource reads in the worst case. Suggested-by: Paul E. McKenney Signed-off-by: Waiman Long Signed-off-by: Paul E. McKenney --- Documentation/admin-guide/kernel-parameters.txt | 4 ++-- kernel/time/clocksource.c | 2 +- 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index 9725c546a0d4..3ea934b034f7 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -603,8 +603,8 @@ clocksource.max_cswd_read_retries= [KNL] Number of clocksource_watchdog() retries due to external delays before the clock will be marked - unstable. Defaults to three retries, that is, - four attempts to read the clock under test. + unstable. Defaults to two retries, that is, + three attempts to read the clock under test. clocksource.verify_n_cpus= [KNL] Limit the number of CPUs checked for clocksources diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c index bcad1a1e5dcf..b7e52a642948 100644 --- a/kernel/time/clocksource.c +++ b/kernel/time/clocksource.c @@ -199,7 +199,7 @@ void clocksource_mark_unstable(struct clocksource *cs) spin_unlock_irqrestore(&watchdog_lock, flags); } -ulong max_cswd_read_retries = 3; +ulong max_cswd_read_retries = 2; module_param(max_cswd_read_retries, ulong, 0644); EXPORT_SYMBOL_GPL(max_cswd_read_retries); static int verify_n_cpus = 8; -- cgit v1.2.3