Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) client-ip=23.128.96.18;
From:   Thomas Gleixner <tglx@linutronix.de>
To:     Chris Friesen <chris.friesen@windriver.com>,
        LKML <linux-kernel@vger.kernel.org>
Subject: Re: IRQs in /proc/irq/* that aren't listed in /proc/interrupts?
In-Reply-To: <c74773ba-10ff-ba3a-b144-da5c2a34c74e@windriver.com>
References: <c74773ba-10ff-ba3a-b144-da5c2a34c74e@windriver.com>
Date:   Mon, 12 Oct 2020 21:37:38 +0200
Message-ID: <87wnzvp75p.fsf@nanos.tec.linutronix.de>
MIME-Version: 1.0
Content-Type: text/plain
Precedence: bulk

Chris,

On Mon, Oct 12 2020 at 12:40, Chris Friesen wrote:
> On one of my X86-64 systems /proc/interrupts starts with the following 
> interrupts (per-cpu info snipped):
>
>    0:      IR-IO-APIC-edge      timer
>     4:      IR-IO-APIC-edge      serial
>     8:      IR-IO-APIC-edge      rtc0
>     9:      IR-IO-APIC-fasteoi   acpi
>    17:      IR-IO-APIC-fasteoi   ehci_hcd:usb1, hpilo
>
>
> On this same system /proc/irq shows these interrupts:
>
> 0-15, 17
>
> Is there any way to determine what the interrupts are that aren't listed 
> in /proc/interrupts?

They are simply unused.

> Six of them are affined to all CPUs, and I'm trying to affine as many
> interrupts as possible to housekeeping CPUs to free up application
> CPUs for low-latency operations.

Affining unused and therefore disabled interrupts is a pretty pointless
exercise.

Thanks,

        tglx