Re: [Publicity] Xen Project Hypervisor 4.5 blog

[Julien Grall <julien.grall@xxxxxxxxxx>]

On 04/01/15 22:53, Sarah Conway wrote:
> 
>   Hi everyone.

Hi Sarah,

Few comments on the ARM part below.

> 
> ARM Hypervisor-Specific Updates
> 
> The ARM ecosystem operates differently to the x86 architecture – in
> which ARM licensees design new chipsets and features and OEMs
> manufacture platforms based on these specifications.
> 
> 
> OEMs designing ARM based platforms determine what they need on the SoC –
> that is the System On Chip. As such they can selectively enable or
> disable certain functionality that they consider important (or
> unimportant). ARM provides the Intellectual Property (IP) and standards
> from which OEMs can further specialize and optimize. Therefore the list
> of features that Xen Project Hypervisor supports on ARM is not for a
> specific platform – but rather for functionality SoCs provide. New
> updates include:
> 
> 
>   *
> 
>     Support for more than 1TB guests.
> 
>   *
> 
>     The Generic Interrupt Controller (GIC) v3 is supported in Xen 4.5.
>     v3 supports Message Signaled Interrupts (MSI), emulation of GICv3
>     for guests – and most importantly – support for more 8 CPUS.

I think this item is confusing. While GICv3 supports MSI and more than 8
CPUs. None of those has been implemented on Xen 4.5.

>   *
> 
>     Power State Coordination Interface (PSCI) – important in the
>     embedded environment where power consumption needs to be kept to the
>     absolute minimum. It allows us to power down/up CPUS, suspend them, etc.

This was already supported in Xen 4.4. Though, we add support of PSCI
0.2 for the host.

>   *
> 
>     UEFI booting. On ARM64 servers both U-Boot and UEFI can be used to
>     boot the OS.
> 
>   *
> 
>     IOMMU support (SMMUv1). For isolation between guests, ARM hardware
>     can come with an IOMMU chipset based on the SMMU specification.
> 
>   *
> 
>     Super Pages (2MB) support in Xen. Using super pages for the guest
>     pseudo-physical to physical translation tables significantly
>     improves overall guest performance.
> 
>   *
> 
>     Passthrough – the PCI passthrough features did not make on time, but
>     doing passthrough of MMIO regions did. In the ARM world it is quite
>     common to have no PCIe devices and to only access devices using MMIO
>     regions. As such this feature allows us to have driver domains be in
>     charge of network or storage devices.

Network and storage devices will likely use IRQ and DMA. While MMIO
passthrough is fully implemented in Xen 4.5, IRQ and IOMMU suport for
guest (necessary for DMA) has been deferred for Xen 4.6.

>   *
> 
>     Interrupt latency reduction: no maintenance interrupts. Please see
>     Stefano’s slides.
> 
> 
> 
> With these new features, the following motherboards
> <http://wiki.xenproject.org/wiki/Xen_ARM_with_Virtualization_Extensions>are
> now supported in Xen Project Hypervisor 4.5:
> 
>   *
> 
>     AMD Seattle
> 
>   *
> 
>     Broadcom 7445D0 A15
> 
>   *
> 
>     Midway (Calxeda)
> 
>   *
> 
>     Odroid-XU

The Odroid-Xu is based on the an Exynos5 processor. It might be
interesting to merge this with the "Exynos5" item below.

>   *
> 
>     Vexpress (ARM Ltd.)
> 
>   *
> 
>     OMAP5, OMAP6, DRA7 (Texas Instrument)

What is OMAP6? I can't find a board

> 
>   *
> 
>     Exynos5 (Samsung chip on the Arndale and various smartphones and
>     tablets)

In the Exynos 5 family we only support Exynos 5250 (Exynos 5 Dual) and
Exynos 5420 (Exynos Octa).

Regards,

-- 
Julien Grall

_______________________________________________
Publicity mailing list
Publicity@xxxxxxxxxxxxxxxxxxxx
http://lists.xenproject.org/cgi-bin/mailman/listinfo/publicity