From: Julien Thierry <julien.thierry@arm.com> To: Jian-Lin Chen <lecopzer@gmail.com> Cc: Jian-Lin Chen <lecopzer.chen@mediatek.com>, linux-arm-kernel@lists.infradead.org, linux-kernel@vger.kernel.org, daniel.thompson@linaro.org, joel@joelfernandes.org, marc.zyngier@arm.com, christoffer.dall@arm.com, james.morse@arm.com, catalin.marinas@arm.com, will.deacon@arm.com, mark.rutland@arm.com, Ard Biesheuvel <ard.biesheuvel@linaro.org>, Oleg Nesterov <oleg@redhat.com> Subject: Re: [PATCH v7 11/25] arm64: irqflags: Use ICC_PMR_EL1 for interrupt masking Date: Mon, 17 Dec 2018 09:26:02 +0000 [thread overview] Message-ID: <e69be9ad-fcda-fa8d-1844-ad0decffb876@arm.com> (raw) In-Reply-To: <20181216144715.7486-1-lecopzer@gmail.com> Hi Jian-Lin, Thanks for looking at this. On 16/12/2018 14:47, Jian-Lin Chen wrote: > From: Jian-Lin Chen <lecopzer.chen@mediatek.com> > > > On Wed, 12 Dec 2018 at 17:48, Julien Thierry <julien.thierry@arm.com> wrote: >> static inline void arch_local_irq_enable(void) >> { >> - asm volatile( >> - "msr daifclr, #2 // arch_local_irq_enable" >> - : >> + unsigned long unmasked = GIC_PRIO_IRQON; >> + > > Should we need a WARN_ON() to check if the daif_I bit is masked, or > explicitly unmasked I bit here? > While I would agree, adding the WARN_ON() will add some non-negligible overhead, especially if we need to read the daif flags to check it. Since these functions are called often in the whole system and using PMR already makes things a bit slower, I'd prefer to avoid checks in here. > If I bit was masked and someone calls arch_local_irq_enable(), they still > couldn't recieve any interrupt. > > >> + asm volatile(ALTERNATIVE( >> + "msr daifclr, #2 // arch_local_irq_enable\n" >> + "nop", >> + "msr_s " __stringify(SYS_ICC_PMR_EL1) ",%0\n" >> + "dsb sy", >> + ARM64_HAS_IRQ_PRIO_MASKING) >> : >> + : "r" (unmasked) >> : "memory"); >> } >> >> static inline void arch_local_irq_disable(void) >> { >> - asm volatile( >> - "msr daifset, #2 // arch_local_irq_disable" >> - : >> + unsigned long masked = GIC_PRIO_IRQOFF; >> + >> + asm volatile(ALTERNATIVE( >> + "msr daifset, #2 // arch_local_irq_disable", >> + "msr_s " __stringify(SYS_ICC_PMR_EL1) ", %0", > > May be a "dsb sy" here? So, we need a "dsb sy" when unmasking interrupts because this ensures the redistributor sees the latest PMR value and starts forwarding lower priority interrupts again. When we disable interrupts however, the GIC CPU interface guarantees that no interrupts of lower priority than the current value of PMR will be taken. So we don't really need the redistributor to immediately see the new value of PMR as the logic in the GIC CPU interface is good enough for our goal. Thanks, -- Julien Thierry
WARNING: multiple messages have this Message-ID (diff)
From: Julien Thierry <julien.thierry@arm.com> To: Jian-Lin Chen <lecopzer@gmail.com> Cc: mark.rutland@arm.com, daniel.thompson@linaro.org, Jian-Lin Chen <lecopzer.chen@mediatek.com>, Ard Biesheuvel <ard.biesheuvel@linaro.org>, marc.zyngier@arm.com, catalin.marinas@arm.com, will.deacon@arm.com, linux-kernel@vger.kernel.org, christoffer.dall@arm.com, james.morse@arm.com, Oleg Nesterov <oleg@redhat.com>, joel@joelfernandes.org, linux-arm-kernel@lists.infradead.org Subject: Re: [PATCH v7 11/25] arm64: irqflags: Use ICC_PMR_EL1 for interrupt masking Date: Mon, 17 Dec 2018 09:26:02 +0000 [thread overview] Message-ID: <e69be9ad-fcda-fa8d-1844-ad0decffb876@arm.com> (raw) In-Reply-To: <20181216144715.7486-1-lecopzer@gmail.com> Hi Jian-Lin, Thanks for looking at this. On 16/12/2018 14:47, Jian-Lin Chen wrote: > From: Jian-Lin Chen <lecopzer.chen@mediatek.com> > > > On Wed, 12 Dec 2018 at 17:48, Julien Thierry <julien.thierry@arm.com> wrote: >> static inline void arch_local_irq_enable(void) >> { >> - asm volatile( >> - "msr daifclr, #2 // arch_local_irq_enable" >> - : >> + unsigned long unmasked = GIC_PRIO_IRQON; >> + > > Should we need a WARN_ON() to check if the daif_I bit is masked, or > explicitly unmasked I bit here? > While I would agree, adding the WARN_ON() will add some non-negligible overhead, especially if we need to read the daif flags to check it. Since these functions are called often in the whole system and using PMR already makes things a bit slower, I'd prefer to avoid checks in here. > If I bit was masked and someone calls arch_local_irq_enable(), they still > couldn't recieve any interrupt. > > >> + asm volatile(ALTERNATIVE( >> + "msr daifclr, #2 // arch_local_irq_enable\n" >> + "nop", >> + "msr_s " __stringify(SYS_ICC_PMR_EL1) ",%0\n" >> + "dsb sy", >> + ARM64_HAS_IRQ_PRIO_MASKING) >> : >> + : "r" (unmasked) >> : "memory"); >> } >> >> static inline void arch_local_irq_disable(void) >> { >> - asm volatile( >> - "msr daifset, #2 // arch_local_irq_disable" >> - : >> + unsigned long masked = GIC_PRIO_IRQOFF; >> + >> + asm volatile(ALTERNATIVE( >> + "msr daifset, #2 // arch_local_irq_disable", >> + "msr_s " __stringify(SYS_ICC_PMR_EL1) ", %0", > > May be a "dsb sy" here? So, we need a "dsb sy" when unmasking interrupts because this ensures the redistributor sees the latest PMR value and starts forwarding lower priority interrupts again. When we disable interrupts however, the GIC CPU interface guarantees that no interrupts of lower priority than the current value of PMR will be taken. So we don't really need the redistributor to immediately see the new value of PMR as the logic in the GIC CPU interface is good enough for our goal. Thanks, -- Julien Thierry _______________________________________________ linux-arm-kernel mailing list linux-arm-kernel@lists.infradead.org http://lists.infradead.org/mailman/listinfo/linux-arm-kernel
next prev parent reply other threads:[~2018-12-17 9:26 UTC|newest] Thread overview: 91+ messages / expand[flat|nested] mbox.gz Atom feed top 2018-12-12 16:47 [PATCH v7 00/25] arm64: provide pseudo NMI with GICv3 Julien Thierry 2018-12-12 16:47 ` Julien Thierry 2018-12-12 16:47 ` [PATCH v7 01/25] arm64: Fix HCR.TGE status for NMI contexts Julien Thierry 2018-12-12 16:47 ` Julien Thierry 2018-12-12 21:39 ` Sasha Levin 2018-12-12 21:39 ` Sasha Levin 2018-12-17 8:49 ` Julien Thierry 2018-12-17 8:49 ` Julien Thierry 2018-12-12 16:47 ` [PATCH v7 02/25] arm64: Remove unused daif related functions/macros Julien Thierry 2018-12-12 16:47 ` Julien Thierry 2018-12-12 16:47 ` [PATCH v7 03/25] arm64: cpufeature: Set SYSREG_GIC_CPUIF as a boot system feature Julien Thierry 2018-12-12 16:47 ` Julien Thierry 2018-12-12 16:47 ` [PATCH v7 04/25] arm64: cpufeature: Add cpufeature for IRQ priority masking Julien Thierry 2018-12-12 16:47 ` Julien Thierry 2018-12-12 16:47 ` [PATCH v7 05/25] arm/arm64: gic-v3: Add PMR and RPR accessors Julien Thierry 2018-12-12 16:47 ` Julien Thierry 2018-12-12 16:47 ` [PATCH v7 06/25] irqchip/gic-v3: Switch to PMR masking before calling IRQ handler Julien Thierry 2018-12-12 16:47 ` Julien Thierry 2018-12-12 16:47 ` [PATCH v7 07/25] arm64: ptrace: Provide definitions for PMR values Julien Thierry 2018-12-12 16:47 ` Julien Thierry 2018-12-12 16:47 ` [PATCH v7 08/25] arm64: Make PMR part of task context Julien Thierry 2018-12-12 16:47 ` Julien Thierry 2018-12-12 16:47 ` [PATCH v7 09/25] arm64: Unmask PMR before going idle Julien Thierry 2018-12-12 16:47 ` Julien Thierry 2018-12-12 16:47 ` [PATCH v7 10/25] arm64: kvm: Unmask PMR before entering guest Julien Thierry 2018-12-12 16:47 ` Julien Thierry 2018-12-12 16:47 ` Julien Thierry 2018-12-12 16:47 ` [PATCH v7 11/25] arm64: irqflags: Use ICC_PMR_EL1 for interrupt masking Julien Thierry 2018-12-12 16:47 ` Julien Thierry 2018-12-12 17:27 ` Ard Biesheuvel 2018-12-12 17:27 ` Ard Biesheuvel 2018-12-12 17:59 ` Julien Thierry 2018-12-12 17:59 ` Julien Thierry 2018-12-12 18:10 ` Ard Biesheuvel 2018-12-12 18:10 ` Ard Biesheuvel 2018-12-13 8:54 ` Julien Thierry 2018-12-13 8:54 ` Julien Thierry 2018-12-13 11:35 ` Ard Biesheuvel 2018-12-13 11:35 ` Ard Biesheuvel 2018-12-13 12:02 ` Julien Thierry 2018-12-13 12:02 ` Julien Thierry 2018-12-13 15:03 ` Julien Thierry 2018-12-13 15:03 ` Julien Thierry 2018-12-14 15:23 ` Julien Thierry 2018-12-14 15:23 ` Julien Thierry 2018-12-14 15:49 ` Ard Biesheuvel 2018-12-14 15:49 ` Ard Biesheuvel 2018-12-14 16:40 ` Julien Thierry 2018-12-14 16:40 ` Julien Thierry 2018-12-19 17:01 ` Julien Thierry 2018-12-19 17:01 ` Julien Thierry 2018-12-20 17:53 ` Ard Biesheuvel 2018-12-20 17:53 ` Ard Biesheuvel 2018-12-21 10:25 ` Julien Thierry 2018-12-21 10:25 ` Julien Thierry 2018-12-16 14:47 ` Jian-Lin Chen 2018-12-16 14:47 ` Jian-Lin Chen 2018-12-17 9:26 ` Julien Thierry [this message] 2018-12-17 9:26 ` Julien Thierry 2018-12-18 8:36 ` Jian-Lin Chen 2018-12-18 8:36 ` Jian-Lin Chen 2018-12-12 16:47 ` [PATCH v7 12/25] arm64: daifflags: Include PMR in daifflags restore operations Julien Thierry 2018-12-12 16:47 ` Julien Thierry 2018-12-12 16:47 ` [PATCH v7 13/25] arm64: alternative: Allow alternative status checking per cpufeature Julien Thierry 2018-12-12 16:47 ` Julien Thierry 2018-12-12 16:47 ` [PATCH v7 14/25] arm64: alternative: Apply alternatives early in boot process Julien Thierry 2018-12-12 16:47 ` Julien Thierry 2018-12-12 16:47 ` [PATCH v7 15/25] irqchip/gic-v3: Factor group0 detection into functions Julien Thierry 2018-12-12 16:47 ` Julien Thierry 2018-12-12 16:47 ` [PATCH v7 16/25] arm64: Switch to PMR masking when starting CPUs Julien Thierry 2018-12-12 16:47 ` Julien Thierry 2018-12-12 16:47 ` [PATCH v7 17/25] arm64: gic-v3: Implement arch support for priority masking Julien Thierry 2018-12-12 16:47 ` Julien Thierry 2018-12-12 16:47 ` [PATCH v7 18/25] irqchip/gic-v3: Detect if GIC can support pseudo-NMIs Julien Thierry 2018-12-12 16:47 ` Julien Thierry 2018-12-12 16:47 ` [PATCH v7 19/25] irqchip/gic-v3: Handle pseudo-NMIs Julien Thierry 2018-12-12 16:47 ` Julien Thierry 2018-12-12 16:47 ` [PATCH v7 20/25] irqchip/gic: Add functions to access irq priorities Julien Thierry 2018-12-12 16:47 ` Julien Thierry 2018-12-12 16:47 ` [PATCH v7 21/25] irqchip/gic-v3: Allow interrupts to be set as pseudo-NMI Julien Thierry 2018-12-12 16:47 ` Julien Thierry 2018-12-12 16:47 ` [PATCH v7 22/25] arm64: Handle serror in NMI context Julien Thierry 2018-12-12 16:47 ` Julien Thierry 2018-12-12 16:47 ` [PATCH v7 23/25] arm64: Skip preemption when exiting an NMI Julien Thierry 2018-12-12 16:47 ` Julien Thierry 2018-12-12 16:47 ` [PATCH v7 24/25] arm64: Skip irqflags tracing for NMI in IRQs disabled context Julien Thierry 2018-12-12 16:47 ` Julien Thierry 2018-12-12 16:47 ` [PATCH v7 25/25] arm64: Enable the support of pseudo-NMIs Julien Thierry 2018-12-12 16:47 ` Julien Thierry 2018-12-12 16:52 ` [PATCH v7 00/25] arm64: provide pseudo NMI with GICv3 Julien Thierry 2018-12-12 16:52 ` Julien Thierry
Reply instructions: You may reply publicly to this message via plain-text email using any one of the following methods: * Save the following mbox file, import it into your mail client, and reply-to-all from there: mbox Avoid top-posting and favor interleaved quoting: https://en.wikipedia.org/wiki/Posting_style#Interleaved_style * Reply using the --to, --cc, and --in-reply-to switches of git-send-email(1): git send-email \ --in-reply-to=e69be9ad-fcda-fa8d-1844-ad0decffb876@arm.com \ --to=julien.thierry@arm.com \ --cc=ard.biesheuvel@linaro.org \ --cc=catalin.marinas@arm.com \ --cc=christoffer.dall@arm.com \ --cc=daniel.thompson@linaro.org \ --cc=james.morse@arm.com \ --cc=joel@joelfernandes.org \ --cc=lecopzer.chen@mediatek.com \ --cc=lecopzer@gmail.com \ --cc=linux-arm-kernel@lists.infradead.org \ --cc=linux-kernel@vger.kernel.org \ --cc=marc.zyngier@arm.com \ --cc=mark.rutland@arm.com \ --cc=oleg@redhat.com \ --cc=will.deacon@arm.com \ /path/to/YOUR_REPLY https://kernel.org/pub/software/scm/git/docs/git-send-email.html * If your mail client supports setting the In-Reply-To header via mailto: links, try the mailto: linkBe sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes, see mirroring instructions on how to clone and mirror all data and code used by this external index.