Re: [PATCH v2 08/44] cpuidle,imx6: Push RCU-idle into driver
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
- To: Frederic Weisbecker <frederic@xxxxxxxxxx>
- Subject: Re: [PATCH v2 08/44] cpuidle,imx6: Push RCU-idle into driver
- From: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
- Date: Mon, 19 Sep 2022 17:00:52 +0200
- Cc: richard.henderson@xxxxxxxxxx, ink@xxxxxxxxxxxxxxxxxxxx, mattst88@xxxxxxxxx, vgupta@xxxxxxxxxx, linux@xxxxxxxxxxxxxxx, ulli.kroll@xxxxxxxxxxxxxx, linus.walleij@xxxxxxxxxx, shawnguo@xxxxxxxxxx, Sascha Hauer <s.hauer@xxxxxxxxxxxxxx>, kernel@xxxxxxxxxxxxxx, festevam@xxxxxxxxx, linux-imx@xxxxxxx, tony@xxxxxxxxxxx, khilman@xxxxxxxxxx, catalin.marinas@xxxxxxx, will@xxxxxxxxxx, guoren@xxxxxxxxxx, bcain@xxxxxxxxxxx, chenhuacai@xxxxxxxxxx, kernel@xxxxxxxxxx, geert@xxxxxxxxxxxxxx, sammy@xxxxxxxxx, monstr@xxxxxxxxx, tsbogend@xxxxxxxxxxxxxxxx, dinguyen@xxxxxxxxxx, jonas@xxxxxxxxxxxx, stefan.kristiansson@xxxxxxxxxxxxx, shorne@xxxxxxxxx, James.Bottomley@xxxxxxxxxxxxxxxxxxxxx, deller@xxxxxx, mpe@xxxxxxxxxxxxxx, npiggin@xxxxxxxxx, christophe.leroy@xxxxxxxxxx, paul.walmsley@xxxxxxxxxx, palmer@xxxxxxxxxxx, aou@xxxxxxxxxxxxxxxxx, hca@xxxxxxxxxxxxx, gor@xxxxxxxxxxxxx, agordeev@xxxxxxxxxxxxx, borntraeger@xxxxxxxxxxxxx, svens@xxxxxxxxxxxxx, ysato@xxxxxxxxxxxxx, dalias@xxxxxxxx, davem@xxxxxxxxxxxxx, richard@xxxxxx, anton.ivanov@xxxxxxxxxxxxxxxxxx, johannes@xxxxxxxxxxxxxxxx, tglx@xxxxxxxxxxxxx, mingo@xxxxxxxxxx, bp@xxxxxxxxx, dave.hansen@xxxxxxxxxxxxxxx, x86@xxxxxxxxxx, hpa@xxxxxxxxx, acme@xxxxxxxxxx, mark.rutland@xxxxxxx, alexander.shishkin@xxxxxxxxxxxxxxx, jolsa@xxxxxxxxxx, namhyung@xxxxxxxxxx, jgross@xxxxxxxx, srivatsa@xxxxxxxxxxxxx, amakhalov@xxxxxxxxxx, pv-drivers@xxxxxxxxxx, boris.ostrovsky@xxxxxxxxxx, chris@xxxxxxxxxx, jcmvbkbc@xxxxxxxxx, rafael@xxxxxxxxxx, lenb@xxxxxxxxxx, pavel@xxxxxx, gregkh@xxxxxxxxxxxxxxxxxxx, mturquette@xxxxxxxxxxxx, sboyd@xxxxxxxxxx, daniel.lezcano@xxxxxxxxxx, lpieralisi@xxxxxxxxxx, sudeep.holla@xxxxxxx, agross@xxxxxxxxxx, bjorn.andersson@xxxxxxxxxx, konrad.dybcio@xxxxxxxxxxxxxx, anup@xxxxxxxxxxxxxx, thierry.reding@xxxxxxxxx, jonathanh@xxxxxxxxxx, jacob.jun.pan@xxxxxxxxxxxxxxx, atishp@xxxxxxxxxxxxxx, Arnd Bergmann <arnd@xxxxxxxx>, yury.norov@xxxxxxxxx, andriy.shevchenko@xxxxxxxxxxxxxxx, linux@xxxxxxxxxxxxxxxxxx, dennis@xxxxxxxxxx, tj@xxxxxxxxxx, cl@xxxxxxxxx, rostedt@xxxxxxxxxxx, pmladek@xxxxxxxx, senozhatsky@xxxxxxxxxxxx, john.ogness@xxxxxxxxxxxxx, juri.lelli@xxxxxxxxxx, vincent.guittot@xxxxxxxxxx, dietmar.eggemann@xxxxxxx, bsegall@xxxxxxxxxx, mgorman@xxxxxxx, bristot@xxxxxxxxxx, vschneid@xxxxxxxxxx, fweisbec@xxxxxxxxx, ryabinin.a.a@xxxxxxxxx, glider@xxxxxxxxxx, andreyknvl@xxxxxxxxx, dvyukov@xxxxxxxxxx, vincenzo.frascino@xxxxxxx, Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>, jpoimboe@xxxxxxxxxx, linux-alpha@xxxxxxxxxxxxxxx, linux-kernel@xxxxxxxxxxxxxxx, linux-snps-arc@xxxxxxxxxxxxxxxxxxx, linux-omap@xxxxxxxxxxxxxxx, linux-csky@xxxxxxxxxxxxxxx, linux-hexagon@xxxxxxxxxxxxxxx, linux-ia64@xxxxxxxxxxxxxxx, loongarch@xxxxxxxxxxxxxxx, linux-m68k@xxxxxxxxxxxxxxx, linux-mips@xxxxxxxxxxxxxxx, openrisc@xxxxxxxxxxxxxxxxxxxx, linux-parisc@xxxxxxxxxxxxxxx, linuxppc-dev@xxxxxxxxxxxxxxxx, linux-riscv@xxxxxxxxxxxxxxxxxxx, linux-s390@xxxxxxxxxxxxxxx, linux-sh@xxxxxxxxxxxxxxx, sparclinux@xxxxxxxxxxxxxxx, linux-um@xxxxxxxxxxxxxxxxxxx, linux-perf-users@xxxxxxxxxxxxxxx, virtualization@xxxxxxxxxxxxxxxxxxxxxxxxxx, linux-xtensa@xxxxxxxxxxxxxxxx, linux-acpi@xxxxxxxxxxxxxxx, linux-pm@xxxxxxxxxxxxxxx, linux-clk@xxxxxxxxxxxxxxx, linux-arm-msm@xxxxxxxxxxxxxxx, linux-tegra@xxxxxxxxxxxxxxx, linux-arch@xxxxxxxxxxxxxxx, kasan-dev@xxxxxxxxxxxxxxxx
- In-reply-to: <20220919142123.GE58444@lothringen>
- References: <20220919095939.761690562@infradead.org> <20220919101520.869531945@infradead.org> <20220919142123.GE58444@lothringen>
On Mon, Sep 19, 2022 at 04:21:23PM +0200, Frederic Weisbecker wrote:
> On Mon, Sep 19, 2022 at 11:59:47AM +0200, Peter Zijlstra wrote:
> > Doing RCU-idle outside the driver, only to then temporarily enable it
> > again, at least twice, before going idle is daft.
>
> Hmm, what ends up calling RCU_IDLE() here? Also what about
> cpu_do_idle()?
Both cpu_pm_enter() and cpu_cluster_pm_enter() use ct_irq_enter_irqson()
which is another way to spell RCU_NONIDLE().
[Index of Archives]
[Linux Kernel]
[Sparc Linux]
[DCCP]
[Linux ARM]
[Yosemite News]
[Linux SCSI]
[Linux x86_64]
[Linux for Ham Radio]
