linux-kernel - Re: MSI interrupt for xhci still lost on 5.6-rc6 after cpu hotplug

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [day] [month] [year] [list]

Date:   Thu, 07 May 2020 21:41:36 +0200
From:   Thomas Gleixner <tglx@...utronix.de>
To:     "Raj\, Ashok" <ashok.raj@...el.com>
Cc:     "Raj\, Ashok" <ashok.raj@...ux.intel.com>,
        Evan Green <evgreen@...omium.org>,
        Mathias Nyman <mathias.nyman@...ux.intel.com>, x86@...nel.org,
        linux-pci <linux-pci@...r.kernel.org>,
        LKML <linux-kernel@...r.kernel.org>,
        Bjorn Helgaas <bhelgaas@...gle.com>,
        "Ghorai\, Sukumar" <sukumar.ghorai@...el.com>,
        "Amara\, Madhusudanarao" <madhusudanarao.amara@...el.com>,
        "Nandamuri\, Srikanth" <srikanth.nandamuri@...el.com>,
        Ashok Raj <ashok.raj@...el.com>
Subject: Re: MSI interrupt for xhci still lost on 5.6-rc6 after cpu hotplug

Ashok,

"Raj, Ashok" <ashok.raj@...el.com> writes:
> 
> I think i got mixed up with logical apic id and logical cpu :-(

Stuff happens.

>           <idle>-0     [000] d.h.    44.376659: msi_set_affinity: quirk[1] new vector allocated, new apic = 2 vector = 33 this apic = 0
>           <idle>-0     [000] d.h.    44.376684: msi_set_affinity: Direct Update: irq 123 Ovec=33 Oapic 0 Nvec 33 Napic 2

>           <idle>-0     [000] d.h.    44.376685: xhci_irq: xhci irq

>           <idle>-0     [001] d.h.    44.376750: msi_set_affinity: quirk[1] new vector allocated, new apic = 2 vector = 33 this apic = 2
>           <idle>-0     [001] d.h.    44.376774: msi_set_affinity: Direct Update: irq 123 Ovec=33 Oapic 2 Nvec 33 Napic 2

>           <idle>-0     [001] d.h.    44.376776: xhci_irq: xhci irq
>           <idle>-0     [001] d.h.    44.395824: xhci_irq: xhci irq

>            <...>-14    [001] d..1    44.400666: msi_set_affinity: quirk[1] new vector allocated, new apic = 6 vector = 33 this apic = 2
>            <...>-14    [001] d..1    44.400691: msi_set_affinity: Direct Update: irq 123 Ovec=33 Oapic 2 Nvec 33 Napic 6

>           <idle>-0     [003] d.h.    44.421021: xhci_irq: xhci irq
>           <idle>-0     [003] d.h.    44.421135: xhci_irq: xhci irq

>      migration/3-24    [003] d..1    44.421784: msi_set_affinity: quirk[1] new vector allocated, new apic = 0 vector = 33 this apic = 6
>      migration/3-24    [003] d..1    44.421803: msi_set_affinity: Direct Update: irq 123 Ovec=33 Oapic 6 Nvec 33 Napic 0

So this last one is a direct update. Straight forward moving it from one
to the other CPU on the same vector number.

And that's the case where we either expect the interrupt to come in on
CPU3 or on CPU0.

There is actually an example in the trace:

	<idle>-0     [000] d.h.    40.616467: msi_set_affinity: quirk[1] new vector allocated, new apic = 2 vector = 33 this apic = 0
	<idle>-0     [000] d.h.    40.616488: msi_set_affinity: Direct Update: irq 123 Ovec=33 Oapic 0 Nvec 33 Napic 2
	<idle>-0     [000] d.h.    40.616488: xhci_irq: xhci irq
	<idle>-0     [001] d.h.    40.616504: xhci_irq: xhci irq

>      migration/3-24    [003] d..1    44.421784: msi_set_affinity: quirk[1] new vector allocated, new apic = 0 vector = 33 this apic = 6
>      migration/3-24    [003] d..1    44.421803: msi_set_affinity: Direct Update: irq 123 Ovec=33 Oapic 6 Nvec 33 Napic 0

But as this last one is the migration thread, aka stomp machine, I
assume this is a hotplug operation. Which means the CPU cannot handle
interrupts anymore. In that case we check the old vector on the
unplugged CPU in fixup_irqs() and do the retrigger from there.
Can you please add tracing to that one as well?

Thanks,

        tglx