Re: [Qemu-arm] [PATCH] KVM: arm/arm64: vgic: Allow more than 256 vcpus for KVM_IRQ_LINE

[Marc Zyngier]

On 19/08/2019 08:41, Will Deacon wrote:
> On Sun, Aug 18, 2019 at 03:07:10PM +0100, Marc Zyngier wrote:
>> While parts of the VGIC support a large number of vcpus (we
>> bravely allow up to 512), other parts are more limited.
>>
>> One of these limits is visible in the KVM_IRQ_LINE ioctl, which
>> only allows 256 vcpus to be signalled when using the CPU or PPI
>> types. Unfortunately, we've cornered ourselves badly by allocating
>> all the bits in the irq field.
>>
>> Since the irq_type subfield (8 bit wide) is currently only taking
>> the values 0, 1 and 2 (and we have been careful not to allow anything
>> else), let's reduce this field to only 4 bits, and allocate the
>> remaining 4 bits to a vcpu2_index, which acts as a multiplier:
>>
>>   vcpu_id = 256 * vcpu2_index + vcpu_index
>>
>> With that, and a new capability (KVM_CAP_ARM_IRQ_LINE_LAYOUT_2)
>> allowing this to be discovered, it becomes possible to inject
>> PPIs to up to 4096 vcpus. But please just don't.
> 
> Do you actually need a new capability for this? Older kernels reject
> non-zero upper bits in the 'irq_type', so isn't that enough to probe
> for this directly?

'Probing' is a bit of an overstatement. You'll get an error back when
userspace will try to inject a PPI into a vcpu whose ID is in the new
range. But nothing at VM creation time will indicate the interrupt
injection API supports more than 256 vcpus.

I think userspace should be able to fail the creation of such large VM
immediately, before actually running it.

        M.
-- 
Jazz is not dead, it just smells funny...