[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Date: Wed, 11 Nov 2020 08:56:39 -0700
From: Alex Williamson <alex.williamson@...hat.com>
To: "xuxiaoyang (C)" <xuxiaoyang2@...wei.com>
Cc: <linux-kernel@...r.kernel.org>, <kvm@...r.kernel.org>,
<kwankhede@...dia.com>, <wu.wubin@...wei.com>,
<maoming.maoming@...wei.com>, <xieyingtai@...wei.com>,
<lizhengui@...wei.com>, <wubinfeng@...wei.com>
Subject: Re: [PATCH] vfio iommu type1: Improve vfio_iommu_type1_pin_pages
performance
On Tue, 10 Nov 2020 21:42:33 +0800
"xuxiaoyang (C)" <xuxiaoyang2@...wei.com> wrote:
> vfio_iommu_type1_pin_pages is very inefficient because
> it is processed page by page when calling vfio_pin_page_external.
> Added contiguous_vaddr_get_pfn to process continuous pages
> to reduce the number of loops, thereby improving performance.
vfio_pin_pages() accepts an array of unrelated iova pfns and processes
each to return the physical pfn. AFAICT this proposal makes an
unfounded and unverified assumption that the caller is asking for a
range of contiguous iova pfns. That's not the semantics of the call.
This is wrong. Thanks,
Alex
Powered by blists - more mailing lists