Commit f1a0a376 authored by Valentin Schneider's avatar Valentin Schneider Committed by Ingo Molnar

sched/core: Initialize the idle task with preemption disabled

As pointed out by commit

  de9b8f5d ("sched: Fix crash trying to dequeue/enqueue the idle thread")

init_idle() can and will be invoked more than once on the same idle
task. At boot time, it is invoked for the boot CPU thread by
sched_init(). Then smp_init() creates the threads for all the secondary
CPUs and invokes init_idle() on them.

As the hotplug machinery brings the secondaries to life, it will issue
calls to idle_thread_get(), which itself invokes init_idle() yet again.
In this case it's invoked twice more per secondary: at _cpu_up(), and at
bringup_cpu().

Given smp_init() already initializes the idle tasks for all *possible*
CPUs, no further initialization should be required. Now, removing
init_idle() from idle_thread_get() exposes some interesting expectations
with regards to the idle task's preempt_count: the secondary startup always
issues a preempt_disable(), requiring some reset of the preempt count to 0
between hot-unplug and hotplug, which is currently served by
idle_thread_get() -> idle_init().

Given the idle task is supposed to have preemption disabled once and never
see it re-enabled, it seems that what we actually want is to initialize its
preempt_count to PREEMPT_DISABLED and leave it there. Do that, and remove
init_idle() from idle_thread_get().

Secondary startups were patched via coccinelle:

  @begone@
  @@

  -preempt_disable();
  ...
  cpu_startup_entry(CPUHP_AP_ONLINE_IDLE);
Signed-off-by: default avatarValentin Schneider <valentin.schneider@arm.com>
Signed-off-by: default avatarIngo Molnar <mingo@kernel.org>
Acked-by: default avatarPeter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/20210512094636.2958515-1-valentin.schneider@arm.com
parent 9f269900
......@@ -166,7 +166,6 @@ smp_callin(void)
DBGS(("smp_callin: commencing CPU %d current %p active_mm %p\n",
cpuid, current, current->active_mm));
preempt_disable();
cpu_startup_entry(CPUHP_AP_ONLINE_IDLE);
}
......
......@@ -189,7 +189,6 @@ void start_kernel_secondary(void)
pr_info("## CPU%u LIVE ##: Executing Code...\n", cpu);
local_irq_enable();
preempt_disable();
cpu_startup_entry(CPUHP_AP_ONLINE_IDLE);
}
......
......@@ -432,7 +432,6 @@ asmlinkage void secondary_start_kernel(void)
#endif
pr_debug("CPU%u: Booted secondary processor\n", cpu);
preempt_disable();
trace_hardirqs_off();
/*
......
......@@ -23,7 +23,7 @@ static inline void preempt_count_set(u64 pc)
} while (0)
#define init_idle_preempt_count(p, cpu) do { \
task_thread_info(p)->preempt_count = PREEMPT_ENABLED; \
task_thread_info(p)->preempt_count = PREEMPT_DISABLED; \
} while (0)
static inline void set_preempt_need_resched(void)
......
......@@ -224,7 +224,6 @@ asmlinkage notrace void secondary_start_kernel(void)
init_gic_priority_masking();
rcu_cpu_starting(cpu);
preempt_disable();
trace_hardirqs_off();
/*
......
......@@ -281,7 +281,6 @@ void csky_start_secondary(void)
pr_info("CPU%u Online: %s...\n", cpu, __func__);
local_irq_enable();
preempt_disable();
cpu_startup_entry(CPUHP_AP_ONLINE_IDLE);
}
......
......@@ -441,7 +441,6 @@ start_secondary (void *unused)
#endif
efi_map_pal_code();
cpu_init();
preempt_disable();
smp_callin();
cpu_startup_entry(CPUHP_AP_ONLINE_IDLE);
......
......@@ -348,7 +348,6 @@ asmlinkage void start_secondary(void)
*/
calibrate_delay();
preempt_disable();
cpu = smp_processor_id();
cpu_data[cpu].udelay_val = loops_per_jiffy;
......
......@@ -145,8 +145,6 @@ asmlinkage __init void secondary_start_kernel(void)
set_cpu_online(cpu, true);
local_irq_enable();
preempt_disable();
/*
* OK, it's off to the idle thread for us
*/
......
......@@ -302,7 +302,6 @@ void __init smp_callin(unsigned long pdce_proc)
#endif
smp_cpu_init(slave_id);
preempt_disable();
flush_cache_all_local(); /* start with known state */
flush_tlb_all_local(NULL);
......
......@@ -1547,7 +1547,6 @@ void start_secondary(void *unused)
smp_store_cpu_info(cpu);
set_dec(tb_ticks_per_jiffy);
rcu_cpu_starting(cpu);
preempt_disable();
cpu_callin_map[cpu] = 1;
if (smp_ops->setup_cpu)
......
......@@ -180,7 +180,6 @@ asmlinkage __visible void smp_callin(void)
* Disable preemption before enabling interrupts, so we don't try to
* schedule a CPU that hasn't actually started yet.
*/
preempt_disable();
local_irq_enable();
cpu_startup_entry(CPUHP_AP_ONLINE_IDLE);
}
......@@ -32,7 +32,7 @@ static inline void preempt_count_set(int pc)
#define init_task_preempt_count(p) do { } while (0)
#define init_idle_preempt_count(p, cpu) do { \
S390_lowcore.preempt_count = PREEMPT_ENABLED; \
S390_lowcore.preempt_count = PREEMPT_DISABLED; \
} while (0)
static inline void set_preempt_need_resched(void)
......@@ -91,7 +91,7 @@ static inline void preempt_count_set(int pc)
#define init_task_preempt_count(p) do { } while (0)
#define init_idle_preempt_count(p, cpu) do { \
S390_lowcore.preempt_count = PREEMPT_ENABLED; \
S390_lowcore.preempt_count = PREEMPT_DISABLED; \
} while (0)
static inline void set_preempt_need_resched(void)
......
......@@ -878,7 +878,6 @@ static void smp_init_secondary(void)
restore_access_regs(S390_lowcore.access_regs_save_area);
cpu_init();
rcu_cpu_starting(cpu);
preempt_disable();
init_cpu_timer();
vtime_init();
vdso_getcpu_init();
......
......@@ -186,8 +186,6 @@ asmlinkage void start_secondary(void)
per_cpu_trap_init();
preempt_disable();
notify_cpu_starting(cpu);
local_irq_enable();
......
......@@ -348,7 +348,6 @@ static void sparc_start_secondary(void *arg)
*/
arch_cpu_pre_starting(arg);
preempt_disable();
cpu = smp_processor_id();
notify_cpu_starting(cpu);
......
......@@ -138,9 +138,6 @@ void smp_callin(void)
set_cpu_online(cpuid, true);
/* idle thread is expected to have preempt disabled */
preempt_disable();
local_irq_enable();
cpu_startup_entry(CPUHP_AP_ONLINE_IDLE);
......
......@@ -44,7 +44,7 @@ static __always_inline void preempt_count_set(int pc)
#define init_task_preempt_count(p) do { } while (0)
#define init_idle_preempt_count(p, cpu) do { \
per_cpu(__preempt_count, (cpu)) = PREEMPT_ENABLED; \
per_cpu(__preempt_count, (cpu)) = PREEMPT_DISABLED; \
} while (0)
/*
......
......@@ -236,7 +236,6 @@ static void notrace start_secondary(void *unused)
cpu_init();
rcu_cpu_starting(raw_smp_processor_id());
x86_cpuinit.early_percpu_clock_init();
preempt_disable();
smp_callin();
enable_start_cpu0 = 0;
......
......@@ -145,7 +145,6 @@ void secondary_start_kernel(void)
cpumask_set_cpu(cpu, mm_cpumask(mm));
enter_lazy_tlb(mm, current);
preempt_disable();
trace_hardirqs_off();
calibrate_delay();
......
......@@ -29,7 +29,7 @@ static __always_inline void preempt_count_set(int pc)
} while (0)
#define init_idle_preempt_count(p, cpu) do { \
task_thread_info(p)->preempt_count = PREEMPT_ENABLED; \
task_thread_info(p)->preempt_count = PREEMPT_DISABLED; \
} while (0)
static __always_inline void set_preempt_need_resched(void)
......
......@@ -941,11 +941,7 @@ asmlinkage __visible void __init __no_sanitize_address start_kernel(void)
* time - but meanwhile we still have a functioning scheduler.
*/
sched_init();
/*
* Disable preemption - early bootup scheduling is extremely
* fragile until we cpu_idle() for the first time.
*/
preempt_disable();
if (WARN(!irqs_disabled(),
"Interrupts were enabled *very* early, fixing it\n"))
local_irq_disable();
......
......@@ -2412,7 +2412,7 @@ static inline void init_idle_pids(struct task_struct *idle)
}
}
struct task_struct *fork_idle(int cpu)
struct task_struct * __init fork_idle(int cpu)
{
struct task_struct *task;
struct kernel_clone_args args = {
......
......@@ -8227,7 +8227,7 @@ void show_state_filter(unsigned long state_filter)
* NOTE: this function does not set the idle thread's NEED_RESCHED
* flag, to make booting more robust.
*/
void init_idle(struct task_struct *idle, int cpu)
void __init init_idle(struct task_struct *idle, int cpu)
{
struct rq *rq = cpu_rq(cpu);
unsigned long flags;
......
......@@ -33,7 +33,6 @@ struct task_struct *idle_thread_get(unsigned int cpu)
if (!tsk)
return ERR_PTR(-ENOMEM);
init_idle(tsk, cpu);
return tsk;
}
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment