linux-stable/arch/x86/include/asm/preempt.h
Valentin Schneider f1a0a376ca sched/core: Initialize the idle task with preemption disabled
As pointed out by commit

  de9b8f5dcb ("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: Valentin Schneider <valentin.schneider@arm.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Acked-by: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/20210512094636.2958515-1-valentin.schneider@arm.com
2021-05-12 13:01:45 +02:00

148 lines
4 KiB
C

/* SPDX-License-Identifier: GPL-2.0 */
#ifndef __ASM_PREEMPT_H
#define __ASM_PREEMPT_H
#include <asm/rmwcc.h>
#include <asm/percpu.h>
#include <linux/thread_info.h>
#include <linux/static_call_types.h>
DECLARE_PER_CPU(int, __preempt_count);
/* We use the MSB mostly because its available */
#define PREEMPT_NEED_RESCHED 0x80000000
/*
* We use the PREEMPT_NEED_RESCHED bit as an inverted NEED_RESCHED such
* that a decrement hitting 0 means we can and should reschedule.
*/
#define PREEMPT_ENABLED (0 + PREEMPT_NEED_RESCHED)
/*
* We mask the PREEMPT_NEED_RESCHED bit so as not to confuse all current users
* that think a non-zero value indicates we cannot preempt.
*/
static __always_inline int preempt_count(void)
{
return raw_cpu_read_4(__preempt_count) & ~PREEMPT_NEED_RESCHED;
}
static __always_inline void preempt_count_set(int pc)
{
int old, new;
do {
old = raw_cpu_read_4(__preempt_count);
new = (old & PREEMPT_NEED_RESCHED) |
(pc & ~PREEMPT_NEED_RESCHED);
} while (raw_cpu_cmpxchg_4(__preempt_count, old, new) != old);
}
/*
* must be macros to avoid header recursion hell
*/
#define init_task_preempt_count(p) do { } while (0)
#define init_idle_preempt_count(p, cpu) do { \
per_cpu(__preempt_count, (cpu)) = PREEMPT_DISABLED; \
} while (0)
/*
* We fold the NEED_RESCHED bit into the preempt count such that
* preempt_enable() can decrement and test for needing to reschedule with a
* single instruction.
*
* We invert the actual bit, so that when the decrement hits 0 we know we both
* need to resched (the bit is cleared) and can resched (no preempt count).
*/
static __always_inline void set_preempt_need_resched(void)
{
raw_cpu_and_4(__preempt_count, ~PREEMPT_NEED_RESCHED);
}
static __always_inline void clear_preempt_need_resched(void)
{
raw_cpu_or_4(__preempt_count, PREEMPT_NEED_RESCHED);
}
static __always_inline bool test_preempt_need_resched(void)
{
return !(raw_cpu_read_4(__preempt_count) & PREEMPT_NEED_RESCHED);
}
/*
* The various preempt_count add/sub methods
*/
static __always_inline void __preempt_count_add(int val)
{
raw_cpu_add_4(__preempt_count, val);
}
static __always_inline void __preempt_count_sub(int val)
{
raw_cpu_add_4(__preempt_count, -val);
}
/*
* Because we keep PREEMPT_NEED_RESCHED set when we do _not_ need to reschedule
* a decrement which hits zero means we have no preempt_count and should
* reschedule.
*/
static __always_inline bool __preempt_count_dec_and_test(void)
{
return GEN_UNARY_RMWcc("decl", __preempt_count, e, __percpu_arg([var]));
}
/*
* Returns true when we need to resched and can (barring IRQ state).
*/
static __always_inline bool should_resched(int preempt_offset)
{
return unlikely(raw_cpu_read_4(__preempt_count) == preempt_offset);
}
#ifdef CONFIG_PREEMPTION
extern asmlinkage void preempt_schedule(void);
extern asmlinkage void preempt_schedule_thunk(void);
#define __preempt_schedule_func preempt_schedule_thunk
extern asmlinkage void preempt_schedule_notrace(void);
extern asmlinkage void preempt_schedule_notrace_thunk(void);
#define __preempt_schedule_notrace_func preempt_schedule_notrace_thunk
#ifdef CONFIG_PREEMPT_DYNAMIC
DECLARE_STATIC_CALL(preempt_schedule, __preempt_schedule_func);
#define __preempt_schedule() \
do { \
__STATIC_CALL_MOD_ADDRESSABLE(preempt_schedule); \
asm volatile ("call " STATIC_CALL_TRAMP_STR(preempt_schedule) : ASM_CALL_CONSTRAINT); \
} while (0)
DECLARE_STATIC_CALL(preempt_schedule_notrace, __preempt_schedule_notrace_func);
#define __preempt_schedule_notrace() \
do { \
__STATIC_CALL_MOD_ADDRESSABLE(preempt_schedule_notrace); \
asm volatile ("call " STATIC_CALL_TRAMP_STR(preempt_schedule_notrace) : ASM_CALL_CONSTRAINT); \
} while (0)
#else /* PREEMPT_DYNAMIC */
#define __preempt_schedule() \
asm volatile ("call preempt_schedule_thunk" : ASM_CALL_CONSTRAINT);
#define __preempt_schedule_notrace() \
asm volatile ("call preempt_schedule_notrace_thunk" : ASM_CALL_CONSTRAINT);
#endif /* PREEMPT_DYNAMIC */
#endif /* PREEMPTION */
#endif /* __ASM_PREEMPT_H */