From 5097cbcb38e6e0d2627c9dde1985e91d2c9f880e Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Thu, 11 Apr 2024 16:39:05 +0200 Subject: sched/isolation: Prevent boot crash when the boot CPU is nohz_full Documentation/timers/no_hz.rst states that the "nohz_full=" mask must not include the boot CPU, which is no longer true after: 08ae95f4fd3b ("nohz_full: Allow the boot CPU to be nohz_full"). However after: aae17ebb53cd ("workqueue: Avoid using isolated cpus' timers on queue_delayed_work") the kernel will crash at boot time in this case; housekeeping_any_cpu() returns an invalid CPU number until smp_init() brings the first housekeeping CPU up. Change housekeeping_any_cpu() to check the result of cpumask_any_and() and return smp_processor_id() in this case. This is just the simple and backportable workaround which fixes the symptom, but smp_processor_id() at boot time should be safe at least for type == HK_TYPE_TIMER, this more or less matches the tick_do_timer_boot_cpu logic. There is no worry about cpu_down(); tick_nohz_cpu_down() will not allow to offline tick_do_timer_cpu (the 1st online housekeeping CPU). Fixes: aae17ebb53cd ("workqueue: Avoid using isolated cpus' timers on queue_delayed_work") Reported-by: Chris von Recklinghausen Signed-off-by: Oleg Nesterov Signed-off-by: Thomas Gleixner Signed-off-by: Ingo Molnar Reviewed-by: Phil Auld Acked-by: Frederic Weisbecker Link: https://lore.kernel.org/r/20240411143905.GA19288@redhat.com Closes: https://lore.kernel.org/all/20240402105847.GA24832@redhat.com/ --- kernel/sched/isolation.c | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) (limited to 'kernel/sched/isolation.c') diff --git a/kernel/sched/isolation.c b/kernel/sched/isolation.c index 373d42c707bc..2a262d3ecb3d 100644 --- a/kernel/sched/isolation.c +++ b/kernel/sched/isolation.c @@ -46,7 +46,16 @@ int housekeeping_any_cpu(enum hk_type type) if (cpu < nr_cpu_ids) return cpu; - return cpumask_any_and(housekeeping.cpumasks[type], cpu_online_mask); + cpu = cpumask_any_and(housekeeping.cpumasks[type], cpu_online_mask); + if (likely(cpu < nr_cpu_ids)) + return cpu; + /* + * Unless we have another problem this can only happen + * at boot time before start_secondary() brings the 1st + * housekeeping CPU up. + */ + WARN_ON_ONCE(system_state == SYSTEM_RUNNING || + type != HK_TYPE_TIMER); } } return smp_processor_id(); -- cgit v1.2.3-59-g8ed1b From 257bf89d84121280904800acd25cc2c444c717ae Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Sat, 13 Apr 2024 16:17:46 +0200 Subject: sched/isolation: Fix boot crash when maxcpus < first housekeeping CPU housekeeping_setup() checks cpumask_intersects(present, online) to ensure that the kernel will have at least one housekeeping CPU after smp_init(), but this doesn't work if the maxcpus= kernel parameter limits the number of processors available after bootup. For example, a kernel with "maxcpus=2 nohz_full=0-2" parameters crashes at boot time on a virtual machine with 4 CPUs. Change housekeeping_setup() to use cpumask_first_and() and check that the returned CPU number is valid and less than setup_max_cpus. Another corner case is "nohz_full=0" on a machine with a single CPU or with the maxcpus=1 kernel argument. In this case non_housekeeping_mask is empty and tick_nohz_full_setup() makes no sense. And indeed, the kernel hits the WARN_ON(tick_nohz_full_running) in tick_sched_do_timer(). And how should the kernel interpret the "nohz_full=" parameter? It should be silently ignored, but currently cpulist_parse() happily returns the empty cpumask and this leads to the same problem. Change housekeeping_setup() to check cpumask_empty(non_housekeeping_mask) and do nothing in this case. Signed-off-by: Oleg Nesterov Signed-off-by: Thomas Gleixner Signed-off-by: Ingo Molnar Reviewed-by: Phil Auld Acked-by: Frederic Weisbecker Link: https://lore.kernel.org/r/20240413141746.GA10008@redhat.com --- kernel/sched/isolation.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'kernel/sched/isolation.c') diff --git a/kernel/sched/isolation.c b/kernel/sched/isolation.c index 2a262d3ecb3d..5891e715f00d 100644 --- a/kernel/sched/isolation.c +++ b/kernel/sched/isolation.c @@ -118,6 +118,7 @@ static void __init housekeeping_setup_type(enum hk_type type, static int __init housekeeping_setup(char *str, unsigned long flags) { cpumask_var_t non_housekeeping_mask, housekeeping_staging; + unsigned int first_cpu; int err = 0; if ((flags & HK_FLAG_TICK) && !(housekeeping.flags & HK_FLAG_TICK)) { @@ -138,7 +139,8 @@ static int __init housekeeping_setup(char *str, unsigned long flags) cpumask_andnot(housekeeping_staging, cpu_possible_mask, non_housekeeping_mask); - if (!cpumask_intersects(cpu_present_mask, housekeeping_staging)) { + first_cpu = cpumask_first_and(cpu_present_mask, housekeeping_staging); + if (first_cpu >= nr_cpu_ids || first_cpu >= setup_max_cpus) { __cpumask_set_cpu(smp_processor_id(), housekeeping_staging); __cpumask_clear_cpu(smp_processor_id(), non_housekeeping_mask); if (!housekeeping.flags) { @@ -147,6 +149,9 @@ static int __init housekeeping_setup(char *str, unsigned long flags) } } + if (cpumask_empty(non_housekeeping_mask)) + goto free_housekeeping_staging; + if (!housekeeping.flags) { /* First setup call ("nohz_full=" or "isolcpus=") */ enum hk_type type; -- cgit v1.2.3-59-g8ed1b