Re: [PATCH 08/12] x86: centralize setting SWIOTLB_FORCE when guest memory encryption is enabled
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
- To: Andrew Cooper <Andrew.Cooper3@xxxxxxxxxx>
- Subject: Re: [PATCH 08/12] x86: centralize setting SWIOTLB_FORCE when guest memory encryption is enabled
- From: Christoph Hellwig <hch@xxxxxx>
- Date: Tue, 1 Mar 2022 12:43:35 +0100
- Cc: Christoph Hellwig <hch@xxxxxx>, "iommu@xxxxxxxxxxxxxxxxxxxxxxxxxx" <iommu@xxxxxxxxxxxxxxxxxxxxxxxxxx>, "x86@xxxxxxxxxx" <x86@xxxxxxxxxx>, Anshuman Khandual <anshuman.khandual@xxxxxxx>, Tom Lendacky <thomas.lendacky@xxxxxxx>, Konrad Rzeszutek Wilk <konrad.wilk@xxxxxxxxxx>, Stefano Stabellini <sstabellini@xxxxxxxxxx>, Boris Ostrovsky <boris.ostrovsky@xxxxxxxxxx>, Juergen Gross <jgross@xxxxxxxx>, Joerg Roedel <joro@xxxxxxxxxx>, David Woodhouse <dwmw2@xxxxxxxxxxxxx>, Lu Baolu <baolu.lu@xxxxxxxxxxxxxxx>, Robin Murphy <robin.murphy@xxxxxxx>, "linux-arm-kernel@xxxxxxxxxxxxxxxxxxx" <linux-arm-kernel@xxxxxxxxxxxxxxxxxxx>, "xen-devel@xxxxxxxxxxxxxxxxxxxx" <xen-devel@xxxxxxxxxxxxxxxxxxxx>, "linux-ia64@xxxxxxxxxxxxxxx" <linux-ia64@xxxxxxxxxxxxxxx>, "linux-mips@xxxxxxxxxxxxxxx" <linux-mips@xxxxxxxxxxxxxxx>, "linuxppc-dev@xxxxxxxxxxxxxxxx" <linuxppc-dev@xxxxxxxxxxxxxxxx>, "linux-riscv@xxxxxxxxxxxxxxxxxxx" <linux-riscv@xxxxxxxxxxxxxxxxxxx>, "linux-s390@xxxxxxxxxxxxxxx" <linux-s390@xxxxxxxxxxxxxxx>, "linux-hyperv@xxxxxxxxxxxxxxx" <linux-hyperv@xxxxxxxxxxxxxxx>, "tboot-devel@xxxxxxxxxxxxxxxxxxxxx" <tboot-devel@xxxxxxxxxxxxxxxxxxxxx>, "linux-pci@xxxxxxxxxxxxxxx" <linux-pci@xxxxxxxxxxxxxxx>
- In-reply-to: <8e623a11-d809-4fab-401c-2ce609a9fc14@citrix.com>
- References: <20220301105311.885699-1-hch@lst.de> <20220301105311.885699-9-hch@lst.de> <8e623a11-d809-4fab-401c-2ce609a9fc14@citrix.com>
- User-agent: Mutt/1.5.17 (2007-11-01)
On Tue, Mar 01, 2022 at 11:39:29AM +0000, Andrew Cooper wrote:
> This isn't really "must". The guest is perfectly capable of sharing
> memory with the hypervisor.
>
> It's just that for now, bounce buffering is allegedly faster, and the
> simple way of getting it working.
Yeah, I guess you щould just share/unshare on demand. But given that
this isn't implemented it is a must in the current kernel. But if
you want a different wording suggest one and I'll put it in.
[Index of Archives]
[Linux Kernel]
[Sparc Linux]
[DCCP]
[Linux ARM]
[Yosemite News]
[Linux SCSI]
[Linux x86_64]
[Linux for Ham Radio]
