From: Dexuan Cui <decui@microsoft.com>
To: Thomas Gleixner <tglx@linutronix.de>,
Saeed Mahameed <saeed@kernel.org>,
Leon Romanovsky <leon@kernel.org>
Cc: "linux-pci@vger.kernel.org" <linux-pci@vger.kernel.org>,
"'netdev@vger.kernel.org'" <netdev@vger.kernel.org>,
"'x86@kernel.org'" <x86@kernel.org>,
Haiyang Zhang <haiyangz@microsoft.com>,
"'linux-kernel@vger.kernel.org'" <linux-kernel@vger.kernel.org>
Subject: RE: [5.14-rc1] mlx5_core receives no interrupts with maxcpus=8
Date: Wed, 18 Aug 2021 21:08:14 +0000 [thread overview]
Message-ID: <DM6PR21MB12752F080EEE916DACA9F8D6BFFF9@DM6PR21MB1275.namprd21.prod.outlook.com> (raw)
In-Reply-To: <87czrbpdty.ffs@nanos.tec.linutronix.de>
> From: Thomas Gleixner <tglx@linutronix.de>
> Sent: Wednesday, July 21, 2021 2:17 PM
> To: Dexuan Cui <decui@microsoft.com>; Saeed Mahameed
>
> On Mon, Jul 19 2021 at 20:33, Dexuan Cui wrote:
> > This is a bare metal x86-64 host with Intel CPUs. Yes, I believe the
> > issue is in the IOMMU Interrupt Remapping mechanism rather in the
> > NIC driver. I just don't understand why bringing the CPUs online and
> > offline can work around the issue. I'm trying to dump the IOMMU IR
> > table entries to look for any error.
>
> can you please enable GENERIC_IRQ_DEBUGFS and provide the output of
>
> cat /sys/kernel/debug/irq/irqs/$THENICIRQS
>
> Thanks,
>
> tglx
Sorry for the late response! I checked the below sys file, and the output is
exactly the same in the good/bad cases -- in both cases, I use maxcpus=8;
the only difference in the good case is that I online and then offline CPU 8~31:
for i in `seq 8 31`; do echo 1 > /sys/devices/system/cpu/cpu$i/online; done
for i in `seq 8 31`; do echo 0 > /sys/devices/system/cpu/cpu$i/online; done
# cat /sys/kernel/debug/irq/irqs/209
handler: handle_edge_irq
device: 0000:d8:00.0
status: 0x00004000
istate: 0x00000000
ddepth: 0
wdepth: 0
dstate: 0x35409200
IRQD_ACTIVATED
IRQD_IRQ_STARTED
IRQD_SINGLE_TARGET
IRQD_MOVE_PCNTXT
IRQD_AFFINITY_SET
IRQD_AFFINITY_ON_ACTIVATE
IRQD_CAN_RESERVE
IRQD_HANDLE_ENFORCE_IRQCTX
node: 1
affinity: 0-7
effectiv: 5
pending:
domain: INTEL-IR-MSI-3-3
hwirq: 0x6c00000
chip: IR-PCI-MSI
flags: 0x30
IRQCHIP_SKIP_SET_WAKE
IRQCHIP_ONESHOT_SAFE
parent:
domain: INTEL-IR-3
hwirq: 0x20000
chip: INTEL-IR
flags: 0x0
parent:
domain: VECTOR
hwirq: 0xd1
chip: APIC
flags: 0x0
Vector: 42
Target: 5
move_in_progress: 0
is_managed: 0
can_reserve: 1
has_reserved: 0
cleanup_pending: 0
Thanks,
Dexuan
next prev parent reply other threads:[~2021-08-18 21:08 UTC|newest]
Thread overview: 10+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-07-15 0:38 [5.14-rc1] mlx5_core receives no interrupts with maxcpus=8 Dexuan Cui
2021-07-15 1:11 ` Dexuan Cui
2021-07-18 9:12 ` Leon Romanovsky
2021-07-19 20:17 ` Saeed Mahameed
2021-07-19 20:33 ` Dexuan Cui
2021-07-21 21:16 ` Thomas Gleixner
2021-08-18 21:08 ` Dexuan Cui [this message]
2021-08-19 20:41 ` Dexuan Cui
[not found] <draft-87h7fa1m37.ffs@tglx>
2021-08-28 20:44 ` Thomas Gleixner
2021-08-29 20:11 ` Dexuan Cui
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=DM6PR21MB12752F080EEE916DACA9F8D6BFFF9@DM6PR21MB1275.namprd21.prod.outlook.com \
--to=decui@microsoft.com \
--cc=haiyangz@microsoft.com \
--cc=leon@kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-pci@vger.kernel.org \
--cc=netdev@vger.kernel.org \
--cc=saeed@kernel.org \
--cc=tglx@linutronix.de \
--cc=x86@kernel.org \
/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: link
Be 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.