[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20210830120036.GA22005@lst.de>
Date: Mon, 30 Aug 2021 14:00:36 +0200
From: Christoph Hellwig <hch@....de>
To: Tianyu Lan <ltykernel@...il.com>
Cc: kys@...rosoft.com, haiyangz@...rosoft.com, sthemmin@...rosoft.com,
wei.liu@...nel.org, decui@...rosoft.com, catalin.marinas@....com,
will@...nel.org, tglx@...utronix.de, mingo@...hat.com,
bp@...en8.de, x86@...nel.org, hpa@...or.com,
dave.hansen@...ux.intel.com, luto@...nel.org, peterz@...radead.org,
konrad.wilk@...cle.com, boris.ostrovsky@...cle.com,
jgross@...e.com, sstabellini@...nel.org, joro@...tes.org,
davem@...emloft.net, kuba@...nel.org, jejb@...ux.ibm.com,
martin.petersen@...cle.com, gregkh@...uxfoundation.org,
arnd@...db.de, hch@....de, m.szyprowski@...sung.com,
robin.murphy@....com, brijesh.singh@....com,
thomas.lendacky@....com, Tianyu.Lan@...rosoft.com,
pgonda@...gle.com, martin.b.radev@...il.com,
akpm@...ux-foundation.org, kirill.shutemov@...ux.intel.com,
rppt@...nel.org, hannes@...xchg.org, aneesh.kumar@...ux.ibm.com,
krish.sadhukhan@...cle.com, saravanand@...com,
linux-arm-kernel@...ts.infradead.org,
xen-devel@...ts.xenproject.org, rientjes@...gle.com,
ardb@...nel.org, michael.h.kelley@...rosoft.com,
iommu@...ts.linux-foundation.org, linux-arch@...r.kernel.org,
linux-hyperv@...r.kernel.org, linux-kernel@...r.kernel.org,
linux-scsi@...r.kernel.org, netdev@...r.kernel.org,
vkuznets@...hat.com, parri.andrea@...il.com, dave.hansen@...el.com
Subject: Re: [PATCH V4 00/13] x86/Hyper-V: Add Hyper-V Isolation VM support
Sorry for the delayed answer, but I look at the vmap_pfn usage in the
previous version and tried to come up with a better version. This
mostly untested branch:
http://git.infradead.org/users/hch/misc.git/shortlog/refs/heads/hyperv-vmap
get us there for swiotlb and the channel infrastructure I've started
looking at the network driver and didn't get anywhere due to other work.
As far as I can tell the network driver does gigantic multi-megabyte
vmalloc allocation for the send and receive buffers, which are then
passed to the hardware, but always copied to/from when interacting
with the networking stack. Did I see that right? Are these big
buffers actually required unlike the normal buffer management schemes
in other Linux network drivers?
If so I suspect the best way to allocate them is by not using vmalloc
but just discontiguous pages, and then use kmap_local_pfn where the
PFN includes the share_gpa offset when actually copying from/to the
skbs.
Powered by blists - more mailing lists