[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
Re: [PATCH v2 1/3] hw/i386: Initialize topo_ids from CpuInstanceProperti
From: |
Igor Mammedov |
Subject: |
Re: [PATCH v2 1/3] hw/i386: Initialize topo_ids from CpuInstanceProperties |
Date: |
Mon, 13 Jul 2020 18:17:40 +0200 |
On Mon, 13 Jul 2020 10:02:22 -0500
Babu Moger <babu.moger@amd.com> wrote:
> > -----Original Message-----
> > From: Igor Mammedov <imammedo@redhat.com>
> > Sent: Monday, July 13, 2020 4:08 AM
> > To: Moger, Babu <Babu.Moger@amd.com>
> > Cc: pbonzini@redhat.com; rth@twiddle.net; ehabkost@redhat.com; qemu-
> > devel@nongnu.org
> > Subject: Re: [PATCH v2 1/3] hw/i386: Initialize topo_ids from
> > CpuInstanceProperties
[...]
> > > +
> > > +/*
> > > + * Initialize topo_ids from CpuInstanceProperties
> > > + * node_id in CpuInstanceProperties(or in CPU device) is a sequential
> > > + * number, but while building the topology
> >
> > >we need to separate it for
> > > + * each socket(mod nodes_per_pkg).
> > could you clarify a bit more on why this is necessary?
>
> If you have two sockets and 4 numa nodes, node_id in CpuInstanceProperties
> will be number sequentially as 0, 1, 2, 3. But in EPYC topology, it will
> be 0, 1, 0, 1( Basically mod % number of nodes per socket).
I'm confused, let's suppose we have 2 EPYC sockets with 2 nodes per socket
so APIC id woulbe be composed like:
1st socket
pkg_id(0) | node_id(0)
pkg_id(0) | node_id(1)
2nd socket
pkg_id(1) | node_id(0)
pkg_id(1) | node_id(1)
if that's the case, then EPYC's node_id here doesn't look like
a NUMA node in the sense it's usually used
(above config would have 4 different memory controllers => 4 conventional NUMA
nodes).
I wonder if linux guest actually uses node_id encoded in apic id for
configuring/checking numa structures, or it just uses whatever ACPI SRAT
table provided.
> > > + */
> > > +static inline void x86_init_topo_ids(X86CPUTopoInfo *topo_info,
> > > + CpuInstanceProperties props,
> > > + X86CPUTopoIDs *topo_ids) {
> > > + topo_ids->smt_id = props.has_thread_id ? props.thread_id : 0;
> > > + topo_ids->core_id = props.has_core_id ? props.core_id : 0;
> > > + topo_ids->die_id = props.has_die_id ? props.die_id : 0;
> > > + topo_ids->node_id = props.has_node_id ?
> > > + props.node_id % MAX(topo_info->nodes_per_pkg, 1)
> > > : 0;
> > > + topo_ids->pkg_id = props.has_socket_id ? props.socket_id : 0; }
> > > /*
> > > * Make APIC ID for the CPU 'cpu_index'
> > > *
> > >
>
- [PATCH v2 0/3] Fix couple of issues with AMD topology, Babu Moger, 2020/07/01
- [PATCH v2 1/3] hw/i386: Initialize topo_ids from CpuInstanceProperties, Babu Moger, 2020/07/01
- Re: [PATCH v2 1/3] hw/i386: Initialize topo_ids from CpuInstanceProperties, Igor Mammedov, 2020/07/13
- RE: [PATCH v2 1/3] hw/i386: Initialize topo_ids from CpuInstanceProperties, Babu Moger, 2020/07/13
- Re: [PATCH v2 1/3] hw/i386: Initialize topo_ids from CpuInstanceProperties,
Igor Mammedov <=
- Re: [PATCH v2 1/3] hw/i386: Initialize topo_ids from CpuInstanceProperties, Babu Moger, 2020/07/13
- Re: [PATCH v2 1/3] hw/i386: Initialize topo_ids from CpuInstanceProperties, Igor Mammedov, 2020/07/13
- RE: [PATCH v2 1/3] hw/i386: Initialize topo_ids from CpuInstanceProperties, Babu Moger, 2020/07/13
- Re: [PATCH v2 1/3] hw/i386: Initialize topo_ids from CpuInstanceProperties, Igor Mammedov, 2020/07/14
- RE: [PATCH v2 1/3] hw/i386: Initialize topo_ids from CpuInstanceProperties, Babu Moger, 2020/07/14
- Re: [PATCH v2 1/3] hw/i386: Initialize topo_ids from CpuInstanceProperties, Igor Mammedov, 2020/07/14
- Re: [PATCH v2 1/3] hw/i386: Initialize topo_ids from CpuInstanceProperties, Igor Mammedov, 2020/07/24
- RE: [PATCH v2 1/3] hw/i386: Initialize topo_ids from CpuInstanceProperties, Babu Moger, 2020/07/27
- Re: [PATCH v2 1/3] hw/i386: Initialize topo_ids from CpuInstanceProperties, Igor Mammedov, 2020/07/27
- RE: [PATCH v2 1/3] hw/i386: Initialize topo_ids from CpuInstanceProperties, Babu Moger, 2020/07/27