archive mirror
 help / color / mirror / Atom feed
From: James Morse <>
To: Marc Zyngier <>
Cc: "Julien Thierry" <>,
	"Suzuki K Poulose" <>,
	"James Hogan" <>,
	"Paul Mackerras" <>,
	"Paolo Bonzini" <>,
	"Radim Krčmář" <>,
	"Sean Christopherson" <>,
	"Vitaly Kuznetsov" <>,
	"Wanpeng Li" <>,
	"Jim Mattson" <>,
	"Joerg Roedel" <>,,,,,
Subject: Re: [PATCH 7/7] KVM: arm/arm64: Elide CMOs when unmapping a range
Date: Thu, 19 Dec 2019 13:46:19 +0000	[thread overview]
Message-ID: <> (raw)
In-Reply-To: <>

Hi Marc,

On 18/12/2019 15:30, Marc Zyngier wrote:
> On 2019-12-18 15:07, James Morse wrote:
>> On 13/12/2019 18:25, Marc Zyngier wrote:
>>> If userspace issues a munmap() on a set of pages, there is no
>>> expectation that the pages are cleaned to the PoC.

>>> So let's
>>> not do more work than strictly necessary, and set the magic
>>> flag that avoids CMOs in this case.
>> I think this assumes the pages went from anonymous->free, so no-one
>> cares about the contents.
>> If the pages are backed by a file, won't dirty pages will still get
>> written back before the page is free? (e.g. EFI flash 'file' mmap()ed in)
> I believe so. Is that a problem?

If we skipped the dcache maintenance on unmap, when the the dirty page is later reclaimed
the clean+stale lines are written back to the file. File-backed dirty pages will stick
around in the page cache in the hope someone else needs them.

This would happen for a guest:device-mapping that is written to, but is actually backed by
a mmap()d file. I think the EFI flash emulation does exactly this.

>> What if this isn't the only mapping of the page? Can't it be swapped
>> out from another VMA? (tenuous example, poor man's memory mirroring?)
> Swap-out wouldn't trigger this code path, as it would use a different
> MMU notifier event (MMU_NOTIFY_CLEAR vs MMU_NOTIFY_UNMAP), I believe.

This was a half thought-through special case of the above. The sequence would be:

VM-A and VM-B both share a mapping of $page.

1. VM-A writes to $page through a device mapping
2. The kernel unmaps $page from VM-A for swap. KVM does the maintenance

3. VM-B writes to $page through a device mapping
4. VM-B exits, KVM skips the maintenance, $page may have clean+stale lines

5. Swap finds no further mappings, and writes $page and its clean+stale lines to disk.

Two VMs with a shared mapping is the 'easy' example. I think you just need a second
mapping for this to happen: it means the page isn't really free after the VM has exited.



      reply	other threads:[~2019-12-19 13:46 UTC|newest]

Thread overview: 15+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-12-13 18:24 [PATCH 0/7] KVM: arm/arm64: Help VMs dying quicker Marc Zyngier
2019-12-13 18:24 ` [PATCH 1/7] KVM: Pass mmu_notifier_range down to kvm_unmap_hva_range() Marc Zyngier
2019-12-13 18:59   ` Suzuki Kuruppassery Poulose
2019-12-14 10:37     ` Marc Zyngier
2019-12-15 10:27   ` Marc Zyngier
2020-01-15 18:10   ` Paolo Bonzini
2019-12-13 18:24 ` [PATCH 2/7] KVM: arm/arm64: Pass flags along Stage-2 unmapping functions Marc Zyngier
2019-12-13 18:24 ` [PATCH 3/7] KVM: arm/arm64: Condition cache maintenance on unmap with a flag Marc Zyngier
2019-12-13 18:25 ` [PATCH 4/7] KVM: arm/arm64: Condition TLB " Marc Zyngier
2019-12-13 18:25 ` [PATCH 5/7] KVM: arm/arm64: Elide both CMOs and TBLIs on freeing the whole Stage-2 Marc Zyngier
2019-12-13 18:25 ` [PATCH 6/7] KVM: arm/arm64: Elide CMOs when retrying a block mapping Marc Zyngier
2019-12-13 18:25 ` [PATCH 7/7] KVM: arm/arm64: Elide CMOs when unmapping a range Marc Zyngier
2019-12-18 15:07   ` James Morse
2019-12-18 15:30     ` Marc Zyngier
2019-12-19 13:46       ` James Morse [this message]

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:

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
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).