From: Jan Beulich <jbeulich@suse.com>
To: Andrew Cooper <andrew.cooper3@citrix.com>
Cc: Xen-devel <xen-devel@lists.xenproject.org>,
"Ian Jackson" <Ian.Jackson@citrix.com>, "Wei Liu" <wl@xen.org>,
"Roger Pau Monné" <roger.pau@citrix.com>
Subject: Re: [Xen-devel] [PATCH] tools/libxc: Construct 32bit PV guests with L3 A/D bits set
Date: Tue, 14 Jan 2020 14:01:18 +0100 [thread overview]
Message-ID: <acee9e6a-74bf-8c21-4032-9efebf13d897@suse.com> (raw)
In-Reply-To: <20200114123921.30850-1-andrew.cooper3@citrix.com>
On 14.01.2020 13:39, Andrew Cooper wrote:
> With the 32 PAE build of Xen gone, 32bit PV guests' top level pagetables no
> longer behave exactly like PAE in hardware.
>
> They should have A/D bits set, for the same performance reasons as apply to
> other levels. This brings the domain builder in line with how Xen constructs
> a 32bit dom0.
>
> As a purely code improvement, make use of range notation to initialise
> identical values in adjacent array elements.
>
> Signed-off-by: Andrew Cooper <andrew.cooper3@citrix.com>
Reviewed-by: Jan Beulich <jbeulich@suse.com>
> It turns out that neither Xen nor libxc sets dirty bits on L1 pagetables, but
> I can't spot any documented reason for this. My best guess is to avoid having
> D/RO mappings of pagetables, but this isn't going to trip up a PV guest to
> begin with. Thoughts on reducing the performance cost there as well?
I'd ack such a patch.
> --- a/tools/libxc/xc_dom_x86.c
> +++ b/tools/libxc/xc_dom_x86.c
> @@ -277,8 +277,8 @@ static int alloc_pgtables_x86_32_pae(struct xc_dom_image *dom)
> .levels = PGTBL_LEVELS_I386,
> .vaddr_mask = bits_to_mask(VIRT_BITS_I386),
> .lvl_prot[0] = _PAGE_PRESENT|_PAGE_RW|_PAGE_ACCESSED,
> - .lvl_prot[1] = _PAGE_PRESENT|_PAGE_RW|_PAGE_ACCESSED|_PAGE_DIRTY|_PAGE_USER,
> - .lvl_prot[2] = _PAGE_PRESENT,
> + .lvl_prot[1 ... 2] =
> + _PAGE_PRESENT|_PAGE_RW|_PAGE_ACCESSED|_PAGE_DIRTY|_PAGE_USER,
Perhaps worthwhile leaving a comment as to the difference to what
readers might expect for PAE L3 entries?
Jan
_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xenproject.org
https://lists.xenproject.org/mailman/listinfo/xen-devel
next prev parent reply other threads:[~2020-01-14 13:01 UTC|newest]
Thread overview: 3+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-01-14 12:39 [Xen-devel] [PATCH] tools/libxc: Construct 32bit PV guests with L3 A/D bits set Andrew Cooper
2020-01-14 13:01 ` Jan Beulich [this message]
2020-01-14 13:02 ` Wei Liu
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 \
--in-reply-to=acee9e6a-74bf-8c21-4032-9efebf13d897@suse.com \
--to=jbeulich@suse.com \
--cc=Ian.Jackson@citrix.com \
--cc=andrew.cooper3@citrix.com \
--cc=roger.pau@citrix.com \
--cc=wl@xen.org \
--cc=xen-devel@lists.xenproject.org \
/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
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.