Message-ID: <CAJF2gTSjyDR5vK6ccFqC21T4-s5AQWOANfBoBRWHcU514As39Q@mail.gmail.com>
Date:   Tue, 20 Sep 2022 13:08:34 +0800
From:   Guo Ren <guoren@...nel.org>
To:     Peter Zijlstra <peterz@...radead.org>
Cc:     richard.henderson@...aro.org, ink@...assic.park.msu.ru,
        mattst88@...il.com, vgupta@...nel.org, linux@...linux.org.uk,
        ulli.kroll@...glemail.com, linus.walleij@...aro.org,
        shawnguo@...nel.org, Sascha Hauer <s.hauer@...gutronix.de>,
        kernel@...gutronix.de, festevam@...il.com, linux-imx@....com,
        tony@...mide.com, khilman@...nel.org, catalin.marinas@....com,
        will@...nel.org, bcain@...cinc.com, chenhuacai@...nel.org,
        kernel@...0n.name, geert@...ux-m68k.org, sammy@...my.net,
        monstr@...str.eu, tsbogend@...ha.franken.de, dinguyen@...nel.org,
        jonas@...thpole.se, stefan.kristiansson@...nalahti.fi,
        shorne@...il.com, James.Bottomley@...senpartnership.com,
        deller@....de, mpe@...erman.id.au, npiggin@...il.com,
        christophe.leroy@...roup.eu, paul.walmsley@...ive.com,
        palmer@...belt.com, aou@...s.berkeley.edu, hca@...ux.ibm.com,
        gor@...ux.ibm.com, agordeev@...ux.ibm.com,
        borntraeger@...ux.ibm.com, svens@...ux.ibm.com,
        ysato@...rs.sourceforge.jp, dalias@...c.org, davem@...emloft.net,
        richard@....at, anton.ivanov@...bridgegreys.com,
        johannes@...solutions.net, tglx@...utronix.de, mingo@...hat.com,
        bp@...en8.de, dave.hansen@...ux.intel.com, x86@...nel.org,
        hpa@...or.com, acme@...nel.org, mark.rutland@....com,
        alexander.shishkin@...ux.intel.com, jolsa@...nel.org,
        namhyung@...nel.org, jgross@...e.com, srivatsa@...il.mit.edu,
        amakhalov@...are.com, pv-drivers@...are.com,
        boris.ostrovsky@...cle.com, chris@...kel.net, jcmvbkbc@...il.com,
        rafael@...nel.org, lenb@...nel.org, pavel@....cz,
        gregkh@...uxfoundation.org, mturquette@...libre.com,
        sboyd@...nel.org, daniel.lezcano@...aro.org, lpieralisi@...nel.org,
        sudeep.holla@....com, agross@...nel.org,
        bjorn.andersson@...aro.org, konrad.dybcio@...ainline.org,
        anup@...infault.org, thierry.reding@...il.com,
        jonathanh@...dia.com, jacob.jun.pan@...ux.intel.com,
        atishp@...shpatra.org, Arnd Bergmann <arnd@...db.de>,
        yury.norov@...il.com, andriy.shevchenko@...ux.intel.com,
        linux@...musvillemoes.dk, dennis@...nel.org, tj@...nel.org,
        cl@...ux.com, rostedt@...dmis.org, pmladek@...e.com,
        senozhatsky@...omium.org, john.ogness@...utronix.de,
        juri.lelli@...hat.com, vincent.guittot@...aro.org,
        dietmar.eggemann@....com, bsegall@...gle.com, mgorman@...e.de,
        bristot@...hat.com, vschneid@...hat.com, fweisbec@...il.com,
        ryabinin.a.a@...il.com, glider@...gle.com, andreyknvl@...il.com,
        dvyukov@...gle.com, vincenzo.frascino@....com,
        Andrew Morton <akpm@...ux-foundation.org>, jpoimboe@...nel.org,
        linux-alpha@...r.kernel.org, linux-kernel@...r.kernel.org,
        linux-snps-arc@...ts.infradead.org, linux-omap@...r.kernel.org,
        linux-csky@...r.kernel.org, linux-hexagon@...r.kernel.org,
        linux-ia64@...r.kernel.org, loongarch@...ts.linux.dev,
        linux-m68k@...ts.linux-m68k.org, linux-mips@...r.kernel.org,
        openrisc@...ts.librecores.org, linux-parisc@...r.kernel.org,
        linuxppc-dev@...ts.ozlabs.org, linux-riscv@...ts.infradead.org,
        linux-s390@...r.kernel.org, linux-sh@...r.kernel.org,
        sparclinux@...r.kernel.org, linux-um@...ts.infradead.org,
        linux-perf-users@...r.kernel.org,
        virtualization@...ts.linux-foundation.org,
        linux-xtensa@...ux-xtensa.org, linux-acpi@...r.kernel.org,
        linux-pm@...r.kernel.org, linux-clk@...r.kernel.org,
        linux-arm-msm@...r.kernel.org, linux-tegra@...r.kernel.org,
        linux-arch@...r.kernel.org, kasan-dev@...glegroups.com,
        "Gautham R. Shenoy" <gautham.shenoy@....com>,
        "Rafael J. Wysocki" <rafael.j.wysocki@...el.com>
Subject: Re: [PATCH v2 21/44] arch/idle: Change arch_cpu_idle() IRQ behaviour

On Mon, Sep 19, 2022 at 6:18 PM Peter Zijlstra <peterz@...radead.org> wrote:
>
> Current arch_cpu_idle() is called with IRQs disabled, but will return
> with IRQs enabled.
>
> However, the very first thing the generic code does after calling
> arch_cpu_idle() is raw_local_irq_disable(). This means that
> architectures that can idle with IRQs disabled end up doing a
> pointless 'enable-disable' dance.
>
> Therefore, push this IRQ disabling into the idle function, meaning
> that those architectures can avoid the pointless IRQ state flipping.
>
> Signed-off-by: Peter Zijlstra (Intel) <peterz@...radead.org>
> Reviewed-by: Gautham R. Shenoy <gautham.shenoy@....com>
> Acked-by: Mark Rutland <mark.rutland@....com> [arm64]
> Acked-by: Rafael J. Wysocki <rafael.j.wysocki@...el.com>
> ---
>  arch/alpha/kernel/process.c      |    1 -
>  arch/arc/kernel/process.c        |    3 +++
>  arch/arm/kernel/process.c        |    1 -
>  arch/arm/mach-gemini/board-dt.c  |    3 ++-
>  arch/arm64/kernel/idle.c         |    1 -
>  arch/csky/kernel/process.c       |    1 -
>  arch/csky/kernel/smp.c           |    2 +-
>  arch/hexagon/kernel/process.c    |    1 -
>  arch/ia64/kernel/process.c       |    1 +
>  arch/loongarch/kernel/idle.c     |    1 +
>  arch/microblaze/kernel/process.c |    1 -
>  arch/mips/kernel/idle.c          |    8 +++-----
>  arch/nios2/kernel/process.c      |    1 -
>  arch/openrisc/kernel/process.c   |    1 +
>  arch/parisc/kernel/process.c     |    2 --
>  arch/powerpc/kernel/idle.c       |    5 ++---
>  arch/riscv/kernel/process.c      |    1 -
>  arch/s390/kernel/idle.c          |    1 -
>  arch/sh/kernel/idle.c            |    1 +
>  arch/sparc/kernel/leon_pmc.c     |    4 ++++
>  arch/sparc/kernel/process_32.c   |    1 -
>  arch/sparc/kernel/process_64.c   |    3 ++-
>  arch/um/kernel/process.c         |    1 -
>  arch/x86/coco/tdx/tdx.c          |    3 +++
>  arch/x86/kernel/process.c        |   15 ++++-----------
>  arch/xtensa/kernel/process.c     |    1 +
>  kernel/sched/idle.c              |    2 --
>  27 files changed, 29 insertions(+), 37 deletions(-)
>
> --- a/arch/alpha/kernel/process.c
> +++ b/arch/alpha/kernel/process.c
> @@ -57,7 +57,6 @@ EXPORT_SYMBOL(pm_power_off);
>  void arch_cpu_idle(void)
>  {
>         wtint(0);
> -       raw_local_irq_enable();
>  }
>
>  void arch_cpu_idle_dead(void)
> --- a/arch/arc/kernel/process.c
> +++ b/arch/arc/kernel/process.c
> @@ -114,6 +114,8 @@ void arch_cpu_idle(void)
>                 "sleep %0       \n"
>                 :
>                 :"I"(arg)); /* can't be "r" has to be embedded const */
> +
> +       raw_local_irq_disable();
>  }
>
>  #else  /* ARC700 */
> @@ -122,6 +124,7 @@ void arch_cpu_idle(void)
>  {
>         /* sleep, but enable both set E1/E2 (levels of interrupts) before committing */
>         __asm__ __volatile__("sleep 0x3 \n");
> +       raw_local_irq_disable();
>  }
>
>  #endif
> --- a/arch/arm/kernel/process.c
> +++ b/arch/arm/kernel/process.c
> @@ -78,7 +78,6 @@ void arch_cpu_idle(void)
>                 arm_pm_idle();
>         else
>                 cpu_do_idle();
> -       raw_local_irq_enable();
>  }
>
>  void arch_cpu_idle_prepare(void)
> --- a/arch/arm/mach-gemini/board-dt.c
> +++ b/arch/arm/mach-gemini/board-dt.c
> @@ -42,8 +42,9 @@ static void gemini_idle(void)
>          */
>
>         /* FIXME: Enabling interrupts here is racy! */
> -       local_irq_enable();
> +       raw_local_irq_enable();
>         cpu_do_idle();
> +       raw_local_irq_disable();
>  }
>
>  static void __init gemini_init_machine(void)
> --- a/arch/arm64/kernel/idle.c
> +++ b/arch/arm64/kernel/idle.c
> @@ -42,5 +42,4 @@ void noinstr arch_cpu_idle(void)
>          * tricks
>          */
>         cpu_do_idle();
> -       raw_local_irq_enable();
>  }
> --- a/arch/csky/kernel/process.c
> +++ b/arch/csky/kernel/process.c
> @@ -100,6 +100,5 @@ void arch_cpu_idle(void)
>  #ifdef CONFIG_CPU_PM_STOP
>         asm volatile("stop\n");
>  #endif
> -       raw_local_irq_enable();
Acked-by: Guo Ren <guoren@...nel.org>

>  }
>  #endif
> --- a/arch/csky/kernel/smp.c
> +++ b/arch/csky/kernel/smp.c
> @@ -309,7 +309,7 @@ void arch_cpu_idle_dead(void)
>         while (!secondary_stack)
>                 arch_cpu_idle();
>
> -       local_irq_disable();
> +       raw_local_irq_disable();
Acked-by ..., because:

                local_irq_disable();

                if (cpu_is_offline(cpu)) {
                        tick_nohz_idle_stop_tick();
                        cpuhp_report_idle_dead();
                        arch_cpu_idle_dead();
                }

>
>         asm volatile(
>                 "mov    sp, %0\n"
> --- a/arch/hexagon/kernel/process.c
> +++ b/arch/hexagon/kernel/process.c
> @@ -44,7 +44,6 @@ void arch_cpu_idle(void)
>  {
>         __vmwait();
>         /*  interrupts wake us up, but irqs are still disabled */
> -       raw_local_irq_enable();
>  }
>
>  /*
> --- a/arch/ia64/kernel/process.c
> +++ b/arch/ia64/kernel/process.c
> @@ -242,6 +242,7 @@ void arch_cpu_idle(void)
>                 (*mark_idle)(1);
>
>         raw_safe_halt();
> +       raw_local_irq_disable();
>
>         if (mark_idle)
>                 (*mark_idle)(0);
> --- a/arch/loongarch/kernel/idle.c
> +++ b/arch/loongarch/kernel/idle.c
> @@ -13,4 +13,5 @@ void __cpuidle arch_cpu_idle(void)
>  {
>         raw_local_irq_enable();
>         __arch_cpu_idle(); /* idle instruction needs irq enabled */
> +       raw_local_irq_disable();
>  }
> --- a/arch/microblaze/kernel/process.c
> +++ b/arch/microblaze/kernel/process.c
> @@ -140,5 +140,4 @@ int dump_fpu(struct pt_regs *regs, elf_f
>
>  void arch_cpu_idle(void)
>  {
> -       raw_local_irq_enable();
>  }
> --- a/arch/mips/kernel/idle.c
> +++ b/arch/mips/kernel/idle.c
> @@ -33,13 +33,13 @@ static void __cpuidle r3081_wait(void)
>  {
>         unsigned long cfg = read_c0_conf();
>         write_c0_conf(cfg | R30XX_CONF_HALT);
> -       raw_local_irq_enable();
>  }
>
>  void __cpuidle r4k_wait(void)
>  {
>         raw_local_irq_enable();
>         __r4k_wait();
> +       raw_local_irq_disable();
>  }
>
>  /*
> @@ -57,7 +57,6 @@ void __cpuidle r4k_wait_irqoff(void)
>                 "       .set    arch=r4000      \n"
>                 "       wait                    \n"
>                 "       .set    pop             \n");
> -       raw_local_irq_enable();
>  }
>
>  /*
> @@ -77,7 +76,6 @@ static void __cpuidle rm7k_wait_irqoff(v
>                 "       wait                                            \n"
>                 "       mtc0    $1, $12         # stalls until W stage  \n"
>                 "       .set    pop                                     \n");
> -       raw_local_irq_enable();
>  }
>
>  /*
> @@ -103,6 +101,8 @@ static void __cpuidle au1k_wait(void)
>         "       nop                             \n"
>         "       .set    pop                     \n"
>         : : "r" (au1k_wait), "r" (c0status));
> +
> +       raw_local_irq_disable();
>  }
>
>  static int __initdata nowait;
> @@ -245,8 +245,6 @@ void arch_cpu_idle(void)
>  {
>         if (cpu_wait)
>                 cpu_wait();
> -       else
> -               raw_local_irq_enable();
>  }
>
>  #ifdef CONFIG_CPU_IDLE
> --- a/arch/nios2/kernel/process.c
> +++ b/arch/nios2/kernel/process.c
> @@ -33,7 +33,6 @@ EXPORT_SYMBOL(pm_power_off);
>
>  void arch_cpu_idle(void)
>  {
> -       raw_local_irq_enable();
>  }
>
>  /*
> --- a/arch/openrisc/kernel/process.c
> +++ b/arch/openrisc/kernel/process.c
> @@ -102,6 +102,7 @@ void arch_cpu_idle(void)
>         raw_local_irq_enable();
>         if (mfspr(SPR_UPR) & SPR_UPR_PMP)
>                 mtspr(SPR_PMR, mfspr(SPR_PMR) | SPR_PMR_DME);
> +       raw_local_irq_disable();
>  }
>
>  void (*pm_power_off)(void) = NULL;
> --- a/arch/parisc/kernel/process.c
> +++ b/arch/parisc/kernel/process.c
> @@ -187,8 +187,6 @@ void arch_cpu_idle_dead(void)
>
>  void __cpuidle arch_cpu_idle(void)
>  {
> -       raw_local_irq_enable();
> -
>         /* nop on real hardware, qemu will idle sleep. */
>         asm volatile("or %%r10,%%r10,%%r10\n":::);
>  }
> --- a/arch/powerpc/kernel/idle.c
> +++ b/arch/powerpc/kernel/idle.c
> @@ -51,10 +51,9 @@ void arch_cpu_idle(void)
>                  * Some power_save functions return with
>                  * interrupts enabled, some don't.
>                  */
> -               if (irqs_disabled())
> -                       raw_local_irq_enable();
> +               if (!irqs_disabled())
> +                       raw_local_irq_disable();
>         } else {
> -               raw_local_irq_enable();
>                 /*
>                  * Go into low thread priority and possibly
>                  * low power mode.
> --- a/arch/riscv/kernel/process.c
> +++ b/arch/riscv/kernel/process.c
> @@ -39,7 +39,6 @@ extern asmlinkage void ret_from_kernel_t
>  void arch_cpu_idle(void)
>  {
>         cpu_do_idle();
> -       raw_local_irq_enable();
>  }
>
>  void __show_regs(struct pt_regs *regs)
> --- a/arch/s390/kernel/idle.c
> +++ b/arch/s390/kernel/idle.c
> @@ -66,7 +66,6 @@ void arch_cpu_idle(void)
>         idle->idle_count++;
>         account_idle_time(cputime_to_nsecs(idle_time));
>         raw_write_seqcount_end(&idle->seqcount);
> -       raw_local_irq_enable();
>  }
>
>  static ssize_t show_idle_count(struct device *dev,
> --- a/arch/sh/kernel/idle.c
> +++ b/arch/sh/kernel/idle.c
> @@ -25,6 +25,7 @@ void default_idle(void)
>         raw_local_irq_enable();
>         /* Isn't this racy ? */
>         cpu_sleep();
> +       raw_local_irq_disable();
>         clear_bl_bit();
>  }
>
> --- a/arch/sparc/kernel/leon_pmc.c
> +++ b/arch/sparc/kernel/leon_pmc.c
> @@ -57,6 +57,8 @@ static void pmc_leon_idle_fixup(void)
>                 "lda    [%0] %1, %%g0\n"
>                 :
>                 : "r"(address), "i"(ASI_LEON_BYPASS));
> +
> +       raw_local_irq_disable();
>  }
>
>  /*
> @@ -70,6 +72,8 @@ static void pmc_leon_idle(void)
>
>         /* For systems without power-down, this will be no-op */
>         __asm__ __volatile__ ("wr       %g0, %asr19\n\t");
> +
> +       raw_local_irq_disable();
>  }
>
>  /* Install LEON Power Down function */
> --- a/arch/sparc/kernel/process_32.c
> +++ b/arch/sparc/kernel/process_32.c
> @@ -71,7 +71,6 @@ void arch_cpu_idle(void)
>  {
>         if (sparc_idle)
>                 (*sparc_idle)();
> -       raw_local_irq_enable();
>  }
>
>  /* XXX cli/sti -> local_irq_xxx here, check this works once SMP is fixed. */
> --- a/arch/sparc/kernel/process_64.c
> +++ b/arch/sparc/kernel/process_64.c
> @@ -59,7 +59,6 @@ void arch_cpu_idle(void)
>  {
>         if (tlb_type != hypervisor) {
>                 touch_nmi_watchdog();
> -               raw_local_irq_enable();
>         } else {
>                 unsigned long pstate;
>
> @@ -90,6 +89,8 @@ void arch_cpu_idle(void)
>                         "wrpr %0, %%g0, %%pstate"
>                         : "=&r" (pstate)
>                         : "i" (PSTATE_IE));
> +
> +               raw_local_irq_disable();
>         }
>  }
>
> --- a/arch/um/kernel/process.c
> +++ b/arch/um/kernel/process.c
> @@ -217,7 +217,6 @@ void arch_cpu_idle(void)
>  {
>         cpu_tasks[current_thread_info()->cpu].pid = os_getpid();
>         um_idle_sleep();
> -       raw_local_irq_enable();
>  }
>
>  int __cant_sleep(void) {
> --- a/arch/x86/coco/tdx/tdx.c
> +++ b/arch/x86/coco/tdx/tdx.c
> @@ -223,6 +223,9 @@ void __cpuidle tdx_safe_halt(void)
>          */
>         if (__halt(irq_disabled, do_sti))
>                 WARN_ONCE(1, "HLT instruction emulation failed\n");
> +
> +       /* XXX I can't make sense of what @do_sti actually does */
> +       raw_local_irq_disable();
>  }
>
>  static int read_msr(struct pt_regs *regs, struct ve_info *ve)
> --- a/arch/x86/kernel/process.c
> +++ b/arch/x86/kernel/process.c
> @@ -701,6 +701,7 @@ EXPORT_SYMBOL(boot_option_idle_override)
>  void __cpuidle default_idle(void)
>  {
>         raw_safe_halt();
> +       raw_local_irq_disable();
>  }
>  #if defined(CONFIG_APM_MODULE) || defined(CONFIG_HALTPOLL_CPUIDLE_MODULE)
>  EXPORT_SYMBOL(default_idle);
> @@ -806,13 +807,7 @@ static void amd_e400_idle(void)
>
>         default_idle();
>
> -       /*
> -        * The switch back from broadcast mode needs to be called with
> -        * interrupts disabled.
> -        */
> -       raw_local_irq_disable();
>         tick_broadcast_exit();
> -       raw_local_irq_enable();
>  }
>
>  /*
> @@ -870,12 +865,10 @@ static __cpuidle void mwait_idle(void)
>                 }
>
>                 __monitor((void *)&current_thread_info()->flags, 0, 0);
> -               if (!need_resched())
> +               if (!need_resched()) {
>                         __sti_mwait(0, 0);
> -               else
> -                       raw_local_irq_enable();
> -       } else {
> -               raw_local_irq_enable();
> +                       raw_local_irq_disable();
> +               }
>         }
>         __current_clr_polling();
>  }
> --- a/arch/xtensa/kernel/process.c
> +++ b/arch/xtensa/kernel/process.c
> @@ -183,6 +183,7 @@ void coprocessor_flush_release_all(struc
>  void arch_cpu_idle(void)
>  {
>         platform_idle();
> +       raw_local_irq_disable();
>  }
>
>  /*
> --- a/kernel/sched/idle.c
> +++ b/kernel/sched/idle.c
> @@ -79,7 +79,6 @@ void __weak arch_cpu_idle_dead(void) { }
>  void __weak arch_cpu_idle(void)
>  {
>         cpu_idle_force_poll = 1;
> -       raw_local_irq_enable();
>  }
>
>  /**
> @@ -96,7 +95,6 @@ void __cpuidle default_idle_call(void)
>
>                 ct_cpuidle_enter();
>                 arch_cpu_idle();
> -               raw_local_irq_disable();
>                 ct_cpuidle_exit();
>
>                 start_critical_timings();
>
>


-- 
Best Regards
 Guo Ren

Powered by blists - more mailing lists