Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67;
MIME-Version: 1.0
References: <3c0eb4e9-ee21-d07b-ad16-735b7dc06051@bluespec.com>
 <mhng-df6c7aad-d4fd-4c44-96c8-bf63465e0c97@palmer-si-x1c4>
 <20190916223323.07664bc2@why> <alpine.DEB.2.21.9999.1909170525170.30255@viisi.sifive.com>
In-Reply-To: <alpine.DEB.2.21.9999.1909170525170.30255@viisi.sifive.com>
From:   David Abdurachmanov <david.abdurachmanov@sifive.com>
Date:   Fri, 20 Sep 2019 16:28:48 +0300
Message-ID: <CAPSAq_y8x7AxU1jA25_9DRtHnup1w6AZTjgj-iQ1F3n-FH3+DA@mail.gmail.com>
Subject: Re: [PATCH] irqchip/sifive-plic: add irq_mask and irq_unmask
To:     Paul Walmsley <paul.walmsley@sifive.com>
Cc:     Marc Zyngier <maz@kernel.org>, Palmer Dabbelt <palmer@sifive.com>,
        Darius Rad <darius@bluespec.com>,
        linux-riscv@lists.infradead.org, linux-kernel@vger.kernel.org,
        tglx@linutronix.de, jason@lakedaemon.net
Content-Type: text/plain; charset="UTF-8"
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

On Tue, Sep 17, 2019 at 3:26 PM Paul Walmsley <paul.walmsley@sifive.com> wrote:
>
>
> Just tested this on the SiFive HiFive Unleashed.  Seems to work OK;
> however I did not stress-test it.
>
> Tested-by: Paul Walmsley <paul.walmsley@sifive.com> # HiFive Unleashed
>
>
> - Paul
>
>
> # !cat
> cat /proc/interrupts
>            CPU0       CPU1       CPU2       CPU3
>   1:          0          0          0          0  SiFive PLIC   5  10011000.serial
>   3:          0          0          0          0  SiFive PLIC  51  10040000.spi
>   4:       6266          0          0          0  SiFive PLIC   4  10010000.serial
>   5:        102          0          0          0  SiFive PLIC   6  10050000.spi
>   6:         37          0          0          0  SiFive PLIC  53  eth0
> IPI0:      1134      21128       9024     220261  Rescheduling interrupts
> IPI1:        10        143         18          7  Function call interrupts
> IPI2:         0          0          0          0  CPU stop interrupts
> #

I have applied the patch on top of 5.2.9 kernel and tried to stress it
with stress-ng interrupt stressors for 2:30+ hours.

# cat /proc/interrupts
           CPU0       CPU1       CPU2       CPU3
  1:          0          0          0          0  SiFive PLIC   5
10011000.serial
  3:          0          0          0          0  SiFive PLIC  51  10040000.spi
  4:      34240          0          0          0  SiFive PLIC   4
10010000.serial
  5:        102          0          0          0  SiFive PLIC   6  10050000.spi
  6:          0          0          0          0  SiFive PLIC  53  eth0
  7:          0          0          0          0  SiFive PLIC  32
microsemi-pcie
IPI0:  32013933   28068736   29345256   23346339  Rescheduling interrupts
IPI1:     78514      78586      63144     100317  Function call interrupts
IPI2:         0          0          0          0  CPU stop interrupts