Re: [PATCH linux-next][RFC]torture: avoid offline tick_do_timer_cpu
From: Christophe Leroy <hidden>
Date: 2023-07-06 07:10:26
Also in:
lkml
Le 21/11/2022 à 04:51, Zhouyi Zhou a écrit :
quoted hunk ↗ jump to hunk
During CPU-hotplug torture (CONFIG_NO_HZ_FULL=y), if we try to offline tick_do_timer_cpu, the operation will fail because in function tick_nohz_cpu_down:if (tick_nohz_full_running && tick_do_timer_cpu == cpu) return -EBUSY;Above bug was first discovered in torture tests performed in PPC VM of Open Source Lab of Oregon State University, and reproducable in RISC-V and X86-64 (with additional kernel commandline cpu0_hotplug). In this patch, we avoid offline tick_do_timer_cpu by distribute the offlining cpu among remaining cpus. Signed-off-by: Zhouyi Zhou <redacted> --- include/linux/tick.h | 1 + kernel/time/tick-common.c | 1 + kernel/time/tick-internal.h | 1 - kernel/torture.c | 10 ++++++++++ 4 files changed, 12 insertions(+), 1 deletion(-)diff --git a/include/linux/tick.h b/include/linux/tick.h index bfd571f18cfd..23cc0b205853 100644 --- a/include/linux/tick.h +++ b/include/linux/tick.h@@ -14,6 +14,7 @@ #include <linux/rcupdate.h> #ifdef CONFIG_GENERIC_CLOCKEVENTS +extern int tick_do_timer_cpu __read_mostly; extern void __init tick_init(void); /* Should be core only, but ARM BL switcher requires it */ extern void tick_suspend_local(void);diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c index 46789356f856..87b9b9afa320 100644 --- a/kernel/time/tick-common.c +++ b/kernel/time/tick-common.c@@ -48,6 +48,7 @@ ktime_t tick_next_period; * procedure also covers cpu hotplug. */ int tick_do_timer_cpu __read_mostly = TICK_DO_TIMER_BOOT; +EXPORT_SYMBOL_GPL(tick_do_timer_cpu); #ifdef CONFIG_NO_HZ_FULL /* * tick_do_timer_boot_cpu indicates the boot CPU temporarily ownsdiff --git a/kernel/time/tick-internal.h b/kernel/time/tick-internal.h index 649f2b48e8f0..8953dca10fdd 100644 --- a/kernel/time/tick-internal.h +++ b/kernel/time/tick-internal.h@@ -15,7 +15,6 @@ DECLARE_PER_CPU(struct tick_device, tick_cpu_device); extern ktime_t tick_next_period; -extern int tick_do_timer_cpu __read_mostly; extern void tick_setup_periodic(struct clock_event_device *dev, int broadcast); extern void tick_handle_periodic(struct clock_event_device *dev);diff --git a/kernel/torture.c b/kernel/torture.c index 789aeb0e1159..bccbdd33dda2 100644 --- a/kernel/torture.c +++ b/kernel/torture.c@@ -33,6 +33,7 @@ #include <linux/delay.h> #include <linux/stat.h> #include <linux/slab.h> +#include <linux/tick.h> #include <linux/trace_clock.h> #include <linux/ktime.h> #include <asm/byteorder.h>@@ -358,7 +359,16 @@ torture_onoff(void *arg) schedule_timeout_interruptible(HZ / 10); continue; } +#ifdef CONFIG_NO_HZ_FULL + /* do not offline tick do timer cpu */ + if (tick_nohz_full_running) {
Can you use fonction tick_nohz_full_enabled() instead and avoid the #ifdef ?
+ cpu = (torture_random(&rand) >> 4) % maxcpu; + if (cpu >= tick_do_timer_cpu) + cpu = (cpu + 1) % (maxcpu + 1); + } else +#else cpu = (torture_random(&rand) >> 4) % (maxcpu + 1); +#endif if (!torture_offline(cpu, &n_offline_attempts, &n_offline_successes, &sum_offline, &min_offline, &max_offline))