From: "Michael S. Tsirkin" <firstname.lastname@example.org> To: Alexander Duyck <email@example.com> Cc: Dave Hansen <firstname.lastname@example.org>, Alexander Duyck <email@example.com>, firstname.lastname@example.org, email@example.com, firstname.lastname@example.org, email@example.com, firstname.lastname@example.org, email@example.com, firstname.lastname@example.org, email@example.com, firstname.lastname@example.org, email@example.com, firstname.lastname@example.org Subject: Re: [RFC PATCH 2/4] kvm: Add host side support for free memory hints Date: Mon, 11 Feb 2019 14:24:58 -0500 [thread overview] Message-ID: <email@example.com> (raw) In-Reply-To: <firstname.lastname@example.org> On Mon, Feb 11, 2019 at 10:30:10AM -0800, Alexander Duyck wrote: > On Mon, 2019-02-11 at 12:48 -0500, Michael S. Tsirkin wrote: > > On Mon, Feb 11, 2019 at 09:41:19AM -0800, Dave Hansen wrote: > > > On 2/9/19 4:44 PM, Michael S. Tsirkin wrote: > > > > So the policy should not leak into host/guest interface. > > > > Instead it is better to just keep the pages pinned and > > > > ignore the hint for now. > > > > > > It does seems a bit silly to have guests forever hinting about freed > > > memory when the host never has a hope of doing anything about it. > > > > > > Is that part fixable? > > > > > > Yes just not with existing IOMMU APIs. > > > > It's in the paragraph just above that you cut out: > > Yes right now assignment is not smart enough but generally > > you can protect the unused page in the IOMMU and that's it, > > it's safe. > > > > So e.g. > > extern int iommu_remap(struct iommu_domain *domain, unsigned long iova, > > phys_addr_t paddr, size_t size, int prot); > > > > > > I can elaborate if you like but generally we would need an API that > > allows you to atomically update a mapping for a specific page without > > perturbing the mapping for other pages. > > > > I still don't see how this would solve anything unless you have the > guest somehow hinting on what pages it is providing to the devices. > > You would have to have the host invalidating the pages when the hint is > provided, and have a new hint tied to arch_alloc_page that would > rebuild the IOMMU mapping when a page is allocated. > > I'm pretty certain that the added cost of that would make the hinting > pretty pointless as my experience has been that the IOMMU is too much > of a bottleneck to have multiple CPUs trying to create and invalidate > mappings simultaneously. I agree it's a concern. Another option would involve passing these hints in the DMA API. How about the option of removing the device by hotplug when host needs overcommit? That would involve either buffering on host, or requesting free pages after device is removed along the lines of existing balloon code. That btw seems to be an argument for making this hinting part of balloon. -- MST
next prev parent reply other threads:[~2019-02-11 19:25 UTC|newest] Thread overview: 55+ messages / expand[flat|nested] mbox.gz Atom feed top 2019-02-04 18:15 [RFC PATCH 0/4] kvm: Report unused guest pages to host Alexander Duyck 2019-02-04 18:15 ` [RFC PATCH 1/4] madvise: Expose ability to set dontneed from kernel Alexander Duyck 2019-02-04 18:15 ` [RFC PATCH 2/4] kvm: Add host side support for free memory hints Alexander Duyck 2019-02-10 0:44 ` Michael S. Tsirkin 2019-02-11 17:34 ` Alexander Duyck 2019-02-11 17:36 ` Michael S. Tsirkin 2019-02-11 17:41 ` Dave Hansen 2019-02-11 17:48 ` Michael S. Tsirkin 2019-02-11 18:30 ` Alexander Duyck 2019-02-11 19:24 ` Michael S. Tsirkin [this message] 2019-02-04 18:15 ` [RFC PATCH 3/4] kvm: Add guest " Alexander Duyck 2019-02-04 19:44 ` Dave Hansen 2019-02-04 20:42 ` Alexander Duyck 2019-02-04 23:00 ` Nadav Amit 2019-02-04 23:37 ` Alexander Duyck 2019-02-05 0:03 ` Nadav Amit 2019-02-05 0:16 ` Alexander Duyck 2019-02-05 1:46 ` Nadav Amit 2019-02-05 18:09 ` Alexander Duyck 2019-02-07 18:21 ` Luiz Capitulino 2019-02-07 18:44 ` Alexander Duyck 2019-02-07 20:02 ` Luiz Capitulino 2019-02-08 21:05 ` Nitesh Narayan Lal 2019-02-08 21:31 ` Alexander Duyck 2019-02-10 0:49 ` Michael S. Tsirkin 2019-02-11 16:31 ` Alexander Duyck 2019-02-11 17:36 ` Michael S. Tsirkin 2019-02-11 18:10 ` Alexander Duyck 2019-02-11 19:54 ` Michael S. Tsirkin 2019-02-11 21:00 ` Alexander Duyck 2019-02-11 22:52 ` Michael S. Tsirkin [not found] ` <email@example.com> 2019-02-12 0:34 ` Michael S. Tsirkin 2019-02-11 17:48 ` Dave Hansen 2019-02-11 17:58 ` Michael S. Tsirkin 2019-02-11 18:19 ` Dave Hansen 2019-02-11 19:56 ` Michael S. Tsirkin 2019-02-04 18:15 ` [RFC PATCH 4/4] mm: Add merge page notifier Alexander Duyck 2019-02-04 19:40 ` Dave Hansen 2019-02-04 19:51 ` Alexander Duyck 2019-02-10 0:57 ` Michael S. Tsirkin 2019-02-11 13:30 ` Nitesh Narayan Lal 2019-02-11 14:17 ` Michael S. Tsirkin 2019-02-11 16:24 ` Nitesh Narayan Lal 2019-02-11 17:41 ` Michael S. Tsirkin 2019-02-11 18:09 ` Nitesh Narayan Lal 2019-02-11 6:40 ` Aaron Lu 2019-02-11 15:58 ` Alexander Duyck 2019-02-12 2:09 ` Aaron Lu 2019-02-12 17:20 ` Alexander Duyck 2019-02-04 18:19 ` [RFC PATCH QEMU] i386/kvm: Enable paravirtual unused page hint mechanism Alexander Duyck 2019-02-05 17:25 ` [RFC PATCH 0/4] kvm: Report unused guest pages to host Nitesh Narayan Lal 2019-02-05 18:43 ` Alexander Duyck 2019-02-07 14:48 ` Nitesh Narayan Lal 2019-02-07 16:56 ` Alexander Duyck 2019-02-10 0:51 ` Michael S. Tsirkin
Reply instructions: You may reply publicly to this message via plain-text email using any one of the following methods: * Save the following mbox file, import it into your mail client, and reply-to-all from there: mbox Avoid top-posting and favor interleaved quoting: https://en.wikipedia.org/wiki/Posting_style#Interleaved_style * Reply using the --to, --cc, and --in-reply-to switches of git-send-email(1): git send-email \ --firstname.lastname@example.org \ --email@example.com \ --firstname.lastname@example.org \ --email@example.com \ --firstname.lastname@example.org \ --email@example.com \ --firstname.lastname@example.org \ --email@example.com \ --firstname.lastname@example.org \ --email@example.com \ --firstname.lastname@example.org \ --email@example.com \ --firstname.lastname@example.org \ --email@example.com \ --firstname.lastname@example.org \ --email@example.com \ --subject='Re: [RFC PATCH 2/4] kvm: Add host side support for free memory hints' \ /path/to/YOUR_REPLY https://kernel.org/pub/software/scm/git/docs/git-send-email.html * If your mail client supports setting the In-Reply-To header via mailto: links, try the mailto: link
This is a public inbox, see mirroring instructions for how to clone and mirror all data and code used for this inbox; as well as URLs for NNTP newsgroup(s).