From: George Dunlap <george.dunlap@eu.citrix.com>
To: Elena Ufimtseva <ufimtseva@gmail.com>
Cc: keir@xen.org, stefano.stabellini@eu.citrix.com, msw@linux.com,
dario.faggioli@citrix.com, lccycc123@gmail.com,
xen-devel@lists.xen.org, JBeulich@suse.com
Subject: Re: [PATCH 2/7] libxc: Plumb Xen with vNUMA topology for domain.
Date: Thu, 14 Nov 2013 22:56:59 +0000 [thread overview]
Message-ID: <5285553B.2090809@eu.citrix.com> (raw)
In-Reply-To: <1381963226-7843-1-git-send-email-ufimtseva@gmail.com>
On 10/16/2013 11:40 PM, Elena Ufimtseva wrote:
> Per-domain vNUMA topology initialization.
> domctl hypercall is used to set vNUMA topology
> per domU during domain build time.
>
> Signed-off-by: Elena Ufimtseva <ufimtseva@gmail.com>
>
> ---
> Changes since RFC v2:
> - copy vNUMA topology information in hypercall in one go;
> ---
> tools/libxc/xc_dom.h | 9 ++++++++
> tools/libxc/xc_domain.c | 59 +++++++++++++++++++++++++++++++++++++++++++++++
> tools/libxc/xenctrl.h | 9 ++++++++
> 3 files changed, 77 insertions(+)
>
> diff --git a/tools/libxc/xc_dom.h b/tools/libxc/xc_dom.h
> index 86e23ee..a271b7c 100644
> --- a/tools/libxc/xc_dom.h
> +++ b/tools/libxc/xc_dom.h
> @@ -114,6 +114,15 @@ struct xc_dom_image {
> struct xc_dom_phys *phys_pages;
> int realmodearea_log;
>
> + /*
> + * vNUMA topology and memory allocation structure.
> + * Defines the way to allocate memory on per NUMA
> + * physical nodes that is defined by vnode_to_pnode.
> + */
> + uint16_t nr_vnodes;
> + uint64_t *vnuma_memszs;
> + unsigned int *vnode_to_pnode;
This isn't really used in this patch -- I think this should probably be
put in the next patch.
> +
> /* malloc memory pool */
> struct xc_dom_mem *memblocks;
>
> diff --git a/tools/libxc/xc_domain.c b/tools/libxc/xc_domain.c
> index 2cea6e3..6cab681 100644
> --- a/tools/libxc/xc_domain.c
> +++ b/tools/libxc/xc_domain.c
> @@ -1777,6 +1777,65 @@ int xc_domain_set_max_evtchn(xc_interface *xch, uint32_t domid,
> return do_domctl(xch, &domctl);
> }
>
> +/* Plumbs Xen with vNUMA topology */
> +int xc_domain_setvnodes(xc_interface *xch,
> + uint32_t domid,
> + uint16_t nr_vnodes,
> + uint16_t nr_vcpus,
> + vnuma_memblk_t *vmemblks,
> + unsigned int *vdistance,
> + unsigned int *vcpu_to_vnode,
> + unsigned int *vnode_to_pnode)
> +{
> + int rc;
> + DECLARE_DOMCTL;
> + DECLARE_HYPERCALL_BOUNCE(vmemblks, sizeof(*vmemblks) * nr_vnodes,
> + XC_HYPERCALL_BUFFER_BOUNCE_BOTH);
> + DECLARE_HYPERCALL_BOUNCE(vdistance, sizeof(*vdistance) *
> + nr_vnodes * nr_vnodes,
> + XC_HYPERCALL_BUFFER_BOUNCE_BOTH);
> + DECLARE_HYPERCALL_BOUNCE(vcpu_to_vnode, sizeof(*vcpu_to_vnode) * nr_vcpus,
> + XC_HYPERCALL_BUFFER_BOUNCE_BOTH);
> + DECLARE_HYPERCALL_BOUNCE(vnode_to_pnode, sizeof(*vnode_to_pnode) *
> + nr_vnodes,
> + XC_HYPERCALL_BUFFER_BOUNCE_BOTH);
> +
> + if ( vdistance == NULL || vcpu_to_vnode == NULL ||
> + vmemblks == NULL || vnode_to_pnode == NULL )
> + {
> + PERROR("Incorrect parameters for XEN_DOMCTL_setvnumainfo\n");
> + return -EINVAL;
> + }
> +
> + rc = -EINVAL;
> +
> + if (xc_hypercall_bounce_pre(xch, vmemblks) ||
> + xc_hypercall_bounce_pre(xch, vdistance) ||
> + xc_hypercall_bounce_pre(xch, vcpu_to_vnode) ||
> + xc_hypercall_bounce_pre(xch, vnode_to_pnode))
> + {
> + PERROR("Could not bounce buffer for xc_domain_setvnodes");
> + return rc;
As Dario said, this should be setting errno and returning -1.
(A bit of a weird convention, but it's as old as Unix, and not worth
breaking at this point.)
Other than that it looks fine to me; but I'm not up on the details of
bounce buffers and what not enough to give a proper reviewed-by.
-George
> + }
> +
> + set_xen_guest_handle(domctl.u.vnuma.vnuma_memblks, vmemblks);
> + set_xen_guest_handle(domctl.u.vnuma.vdistance, vdistance);
> + set_xen_guest_handle(domctl.u.vnuma.vcpu_to_vnode, vcpu_to_vnode);
> + set_xen_guest_handle(domctl.u.vnuma.vnode_to_pnode, vnode_to_pnode);
> +
> + domctl.cmd = XEN_DOMCTL_setvnumainfo;
> + domctl.domain = (domid_t)domid;
> + domctl.u.vnuma.nr_vnodes = nr_vnodes;
> + rc = do_domctl(xch, &domctl);
> +
> + xc_hypercall_bounce_post(xch, vmemblks);
> + xc_hypercall_bounce_post(xch, vdistance);
> + xc_hypercall_bounce_post(xch, vcpu_to_vnode);
> + xc_hypercall_bounce_post(xch, vnode_to_pnode);
> +
> + return rc;
> +}
> +
> /*
> * Local variables:
> * mode: C
> diff --git a/tools/libxc/xenctrl.h b/tools/libxc/xenctrl.h
> index 8cf3f3b..3dbd035 100644
> --- a/tools/libxc/xenctrl.h
> +++ b/tools/libxc/xenctrl.h
> @@ -1108,6 +1108,15 @@ int xc_domain_set_memmap_limit(xc_interface *xch,
> uint32_t domid,
> unsigned long map_limitkb);
>
> +int xc_domain_setvnodes(xc_interface *xch,
> + uint32_t domid,
> + uint16_t nr_vnodes,
> + uint16_t nr_vcpus,
> + vnuma_memblk_t *vmemareas,
> + unsigned int *vdistance,
> + unsigned int *vcpu_to_vnode,
> + unsigned int *vnode_to_pnode);
> +
> #if defined(__i386__) || defined(__x86_64__)
> /*
> * PC BIOS standard E820 types and structure.
>
prev parent reply other threads:[~2013-11-14 22:56 UTC|newest]
Thread overview: 2+ messages / expand[flat|nested] mbox.gz Atom feed top
2013-10-16 22:40 [PATCH 2/7] libxc: Plumb Xen with vNUMA topology for domain Elena Ufimtseva
2013-11-14 22:56 ` George Dunlap [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:
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=5285553B.2090809@eu.citrix.com \
--to=george.dunlap@eu.citrix.com \
--cc=JBeulich@suse.com \
--cc=dario.faggioli@citrix.com \
--cc=keir@xen.org \
--cc=lccycc123@gmail.com \
--cc=msw@linux.com \
--cc=stefano.stabellini@eu.citrix.com \
--cc=ufimtseva@gmail.com \
--cc=xen-devel@lists.xen.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 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).