qemu-devel.nongnu.org archive mirror
 help / color / mirror / Atom feed
From: Igor Mammedov <imammedo@redhat.com>
To: Babu Moger <babu.moger@amd.com>
Cc: ehabkost@redhat.com, mst@redhat.com, qemu-devel@nongnu.org,
	pbonzini@redhat.com, rth@twiddle.net
Subject: Re: [PATCH v4 04/16] hw/i386: Introduce init_topo_info to initialize X86CPUTopoInfo
Date: Mon, 24 Feb 2020 09:18:33 +0100	[thread overview]
Message-ID: <20200224091833.2d3dec7f@redhat.com> (raw)
In-Reply-To: <3188d0e7-7f1c-aa03-d3ec-f512d9905158@amd.com>

On Fri, 21 Feb 2020 11:51:15 -0600
Babu Moger <babu.moger@amd.com> wrote:

> On 2/21/20 11:05 AM, Igor Mammedov wrote:
> > On Thu, 13 Feb 2020 12:16:51 -0600
> > Babu Moger <babu.moger@amd.com> wrote:
> >   
> >> Initialize all the parameters in one function init_topo_info.  
> > 
> > is it possible to squash it in 2/16
> >   
> Sure. We can do that.
> >   
> >>
> >> Move the data structure X86CPUTopoIDs and X86CPUTopoInfo into
> >> x86.h.  
> > A reason why it's moved should be here.  
> 
> Apicid functions will be part of X86MachineState data structure(patches
> introduced later).These functions will use X86CPUTopoIDs and
> X86CPUTopoInfo definition. Will add these details. Thanks

why not just include topology.h into the X86MachineState header,
and keep topo structures/functions where they are now?
(I dislike a little scattering consolidated pieces across multiple files,
but what worries me more is that it makes target/i386/cpu.c via
topology.h -> x86.h chain pull in a lot of unrelated dependencies)

So I'd keep X86CPUTopoIDs and X86CPUTopoInfo in topology.h 

[...]
> >> +static inline void init_topo_info(X86CPUTopoInfo *topo_info,
> >> +                                  const X86MachineState *x86ms)
> >> +{
> >> +    MachineState *ms = MACHINE(x86ms);
> >> +
> >> +    topo_info->dies_per_pkg = x86ms->smp_dies;
> >> +    topo_info->cores_per_die = ms->smp.cores;
> >> +    topo_info->threads_per_core = ms->smp.threads;
> >> +}

this is pure machine specific helper, and aren't used anywhere else
beside machine code.
Suggest to put it in pc.c or x86.c to keep topology.h machine independent.

> >>  
> >>  /* Return the bit width needed for 'count' IDs
> >>   */
> >> diff --git a/include/hw/i386/x86.h b/include/hw/i386/x86.h
> >> index 4b84917885..ad62b01cf2 100644
> >> --- a/include/hw/i386/x86.h
> >> +++ b/include/hw/i386/x86.h
> >> @@ -36,6 +36,23 @@ typedef struct {
> >>      bool compat_apic_id_mode;
> >>  } X86MachineClass;
> >>  
> >> +/* APIC IDs can be 32-bit, but beware: APIC IDs > 255 require x2APIC support
> >> + */
> >> +typedef uint32_t apic_id_t;
> >> +
> >> +typedef struct X86CPUTopoIDs {
> >> +    unsigned pkg_id;
> >> +    unsigned die_id;
> >> +    unsigned core_id;
> >> +    unsigned smt_id;
> >> +} X86CPUTopoIDs;
> >> +
> >> +typedef struct X86CPUTopoInfo {
> >> +    unsigned dies_per_pkg;
> >> +    unsigned cores_per_die;
> >> +    unsigned threads_per_core;
> >> +} X86CPUTopoInfo;
> >> +
> >>  typedef struct {
> >>      /*< private >*/
> >>      MachineState parent;
> >>  
> >   
> 



  reply	other threads:[~2020-02-24  8:19 UTC|newest]

Thread overview: 44+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-02-13 18:16 [PATCH v4 00/16] APIC ID fixes for AMD EPYC CPU model Babu Moger
2020-02-13 18:16 ` [PATCH v4 01/16] hw/i386: Rename X86CPUTopoInfo structure to X86CPUTopoIDs Babu Moger
2020-02-13 18:16 ` [PATCH v4 02/16] hw/i386: Introduce X86CPUTopoInfo to contain topology info Babu Moger
2020-02-13 18:16 ` [PATCH v4 03/16] hw/i386: Consolidate topology functions Babu Moger
2020-02-13 18:16 ` [PATCH v4 04/16] hw/i386: Introduce init_topo_info to initialize X86CPUTopoInfo Babu Moger
2020-02-21 17:05   ` Igor Mammedov
2020-02-21 17:51     ` Babu Moger
2020-02-24  8:18       ` Igor Mammedov [this message]
2020-02-24 16:54         ` Babu Moger
2020-02-13 18:16 ` [PATCH v4 05/16] machine: Add SMP Sockets in CpuTopology Babu Moger
2020-02-24  8:37   ` Igor Mammedov
2020-02-13 18:17 ` [PATCH v4 06/16] hw/i386: Update structures for nodes_per_pkg Babu Moger
2020-02-24  8:34   ` Igor Mammedov
2020-02-24 17:12     ` Babu Moger
2020-02-25  7:42       ` Igor Mammedov
2020-02-13 18:17 ` [PATCH v4 07/16] hw/i386: Rename apicid_from_topo_ids to x86_apicid_from_topo_ids Babu Moger
2020-02-20 12:43   ` Igor Mammedov
2020-02-13 18:17 ` [PATCH v4 08/16] hw/386: Add EPYC mode topology decoding functions Babu Moger
2020-02-24  8:50   ` Igor Mammedov
2020-02-24 17:24     ` Babu Moger
2020-02-13 18:17 ` [PATCH v4 09/16] target/i386: Cleanup and use the EPYC mode topology functions Babu Moger
2020-02-24  8:52   ` Igor Mammedov
2020-02-24 17:29     ` Babu Moger
2020-02-25  7:49       ` Igor Mammedov
2020-02-25 15:10         ` Babu Moger
2020-03-02 17:09         ` Babu Moger
2020-03-03  8:47           ` Igor Mammedov
2020-02-13 18:17 ` [PATCH v4 10/16] hw/i386: Introduce apicid functions inside X86MachineState Babu Moger
2020-02-24 17:01   ` Igor Mammedov
2020-02-24 17:30     ` Babu Moger
2020-02-13 18:17 ` [PATCH v4 11/16] target/i386: Load apicid model specific handlers from X86CPUDefinition Babu Moger
2020-02-13 18:17 ` [PATCH v4 12/16] hw/i386: Use the apicid handlers from X86MachineState Babu Moger
2020-02-24 17:19   ` Igor Mammedov
2020-02-24 17:58     ` Babu Moger
2020-02-24 22:31       ` Eduardo Habkost
2020-02-24 23:13         ` Babu Moger
2020-02-25 15:32           ` Eduardo Habkost
2020-02-25 15:41             ` Babu Moger
2020-02-25  8:16         ` Igor Mammedov
2020-02-25 15:26           ` Eduardo Habkost
2020-02-13 18:17 ` [PATCH v4 13/16] target/i386: Add EPYC model specific handlers Babu Moger
2020-02-13 18:17 ` [PATCH v4 14/16] hw/i386: Move arch_id decode inside x86_cpus_init Babu Moger
2020-02-13 18:18 ` [PATCH v4 15/16] i386: Fix pkg_id offset for EPYC cpu models Babu Moger
2020-02-13 18:18 ` [PATCH v4 16/16] tests: Update the Unit tests Babu Moger

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=20200224091833.2d3dec7f@redhat.com \
    --to=imammedo@redhat.com \
    --cc=babu.moger@amd.com \
    --cc=ehabkost@redhat.com \
    --cc=mst@redhat.com \
    --cc=pbonzini@redhat.com \
    --cc=qemu-devel@nongnu.org \
    --cc=rth@twiddle.net \
    /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).