All of lore.kernel.org
 help / color / mirror / Atom feed
From: Babu Moger <babu.moger@amd.com>
To: Igor Mammedov <imammedo@redhat.com>
Cc: ehabkost@redhat.com, mst@redhat.com, qemu-devel@nongnu.org,
	pbonzini@redhat.com, rth@twiddle.net
Subject: Re: [PATCH v4 08/16] hw/386: Add EPYC mode topology decoding functions
Date: Mon, 24 Feb 2020 11:24:36 -0600	[thread overview]
Message-ID: <1e23d802-8e88-1eec-f220-1e0d6b2e4839@amd.com> (raw)
In-Reply-To: <20200224095021.78472314@redhat.com>



On 2/24/20 2:50 AM, Igor Mammedov wrote:
> On Thu, 13 Feb 2020 12:17:18 -0600
> Babu Moger <babu.moger@amd.com> wrote:
> 
>> These functions add support for building EPYC mode topology given the smp
>> details like numa nodes, cores, threads and sockets.
>>
>> The new apic id decoding is mostly similar to current apic id decoding
>> except that it adds a new field llc_id when numa configured. Removes all
> 
> llc_id/nodes_per_pkg

Good catch. Thanks.

> 
>> the hardcoded values. Subsequent patches will use these functions to build
>> the topology.
>>
>> Following functions are added.
>> apicid_llc_width_epyc
>> apicid_llc_offset_epyc
>> apicid_pkg_offset_epyc
>> apicid_from_topo_ids_epyc
>> x86_topo_ids_from_idx_epyc
>> x86_topo_ids_from_apicid_epyc
>> x86_apicid_from_cpu_idx_epyc
>>
>> The topology details are available in Processor Programming Reference (PPR)
>> for AMD Family 17h Model 01h, Revision B1 Processors.
>> https://nam11.safelinks.protection.outlook.com/?url=https%3A%2F%2Fwww.amd.com%2Fsystem%2Ffiles%2FTechDocs%2F55570-B1_PUB.zip&amp;data=02%7C01%7Cbabu.moger%40amd.com%7C07f6ec6272fa4a0bb44608d7b9069ef6%7C3dd8961fe4884e608e11a82d994e183d%7C0%7C0%7C637181310409402221&amp;sdata=nPUTNqiXVSihj8mHt%2FO6sSGCL4uTtPsfvIiEJ0WosaM%3D&amp;reserved=0
> 
> also checkpatch doesn't like this patch for too long strings.

Yes. I saw that.  Some are bit tricky. I may need to break the definitions
like this below.

static inline apic_id_t
x86_apicid_from_topo_ids_epyc(X86CPUTopoInfo *topo_info,
                              const X86CPUTopoIDs *topo_ids)


> with that fixed
>   Acked-by: Igor Mammedov <imammedo@redhat.com>
> 
> 
> PS:
> similar checkpatch warnings should be fixed in preceding patches

Sure. Will take care.
> 
> 
>>
>> Signed-off-by: Babu Moger <babu.moger@amd.com>
>> ---
>>  include/hw/i386/topology.h |   93 ++++++++++++++++++++++++++++++++++++++++++++
>>  include/hw/i386/x86.h      |    1 
>>  2 files changed, 94 insertions(+)
>>
>> diff --git a/include/hw/i386/topology.h b/include/hw/i386/topology.h
>> index 3158157430..d9319dc2ac 100644
>> --- a/include/hw/i386/topology.h
>> +++ b/include/hw/i386/topology.h
>> @@ -83,6 +83,11 @@ static inline unsigned apicid_die_width(X86CPUTopoInfo *topo_info)
>>      return apicid_bitwidth_for_count(topo_info->dies_per_pkg);
>>  }
>>  
>> +/* Bit width of the node_id field per socket */
>> +static inline unsigned apicid_node_width_epyc(X86CPUTopoInfo *topo_info)
>> +{
>> +    return apicid_bitwidth_for_count(MAX(topo_info->nodes_per_pkg, 1));
>> +}
>>  /* Bit offset of the Core_ID field
>>   */
>>  static inline unsigned apicid_core_offset(X86CPUTopoInfo *topo_info)
>> @@ -103,6 +108,94 @@ static inline unsigned apicid_pkg_offset(X86CPUTopoInfo *topo_info)
>>      return apicid_die_offset(topo_info) + apicid_die_width(topo_info);
>>  }
>>  
>> +#define LLC_OFFSET 3 /* Minimum LLC offset if numa configured */
>> +
>> +/* Bit offset of the node_id field */
>> +static inline unsigned apicid_node_offset_epyc(X86CPUTopoInfo *topo_info)
>> +{
>> +    unsigned offset = apicid_die_offset(topo_info) +
>> +                      apicid_die_width(topo_info);
>> +
>> +    if (topo_info->nodes_per_pkg) {
>> +        return MAX(LLC_OFFSET, offset);
>> +    } else {
>> +        return offset;
>> +    }
>> +}
>> +
>> +/* Bit offset of the Pkg_ID (socket ID) field */
>> +static inline unsigned apicid_pkg_offset_epyc(X86CPUTopoInfo *topo_info)
>> +{
>> +    return apicid_node_offset_epyc(topo_info) + apicid_node_width_epyc(topo_info);
>> +}
>> +
>> +/*
>> + * Make APIC ID for the CPU based on Pkg_ID, Core_ID, SMT_ID
>> + *
>> + * The caller must make sure core_id < nr_cores and smt_id < nr_threads.
>> + */
>> +static inline apic_id_t x86_apicid_from_topo_ids_epyc(X86CPUTopoInfo *topo_info,
>> +                                                      const X86CPUTopoIDs *topo_ids)
>> +{
>> +    return (topo_ids->pkg_id  << apicid_pkg_offset_epyc(topo_info)) |
>> +           (topo_ids->node_id << apicid_node_offset_epyc(topo_info)) |
>> +           (topo_ids->die_id  << apicid_die_offset(topo_info)) |
>> +           (topo_ids->core_id << apicid_core_offset(topo_info)) |
>> +           topo_ids->smt_id;
>> +}
>> +
>> +static inline void x86_topo_ids_from_idx_epyc(X86CPUTopoInfo *topo_info,
>> +                                              unsigned cpu_index,
>> +                                              X86CPUTopoIDs *topo_ids)
>> +{
>> +    unsigned nr_nodes = MAX(topo_info->nodes_per_pkg, 1);
>> +    unsigned nr_dies = topo_info->dies_per_pkg;
>> +    unsigned nr_cores = topo_info->cores_per_die;
>> +    unsigned nr_threads = topo_info->threads_per_core;
>> +    unsigned cores_per_node = DIV_ROUND_UP((nr_dies * nr_cores * nr_threads),
>> +                                            nr_nodes);
>> +
>> +    topo_ids->pkg_id = cpu_index / (nr_dies * nr_cores * nr_threads);
>> +    topo_ids->node_id = (cpu_index / cores_per_node) % nr_nodes;
>> +    topo_ids->die_id = cpu_index / (nr_cores * nr_threads) % nr_dies;
>> +    topo_ids->core_id = cpu_index / nr_threads % nr_cores;
>> +    topo_ids->smt_id = cpu_index % nr_threads;
>> +}
>> +
>> +/*
>> + * Calculate thread/core/package IDs for a specific topology,
>> + * based on APIC ID
>> + */
>> +static inline void x86_topo_ids_from_apicid_epyc(apic_id_t apicid,
>> +                                            X86CPUTopoInfo *topo_info,
>> +                                            X86CPUTopoIDs *topo_ids)
>> +{
>> +    topo_ids->smt_id = apicid &
>> +            ~(0xFFFFFFFFUL << apicid_smt_width(topo_info));
>> +    topo_ids->core_id =
>> +            (apicid >> apicid_core_offset(topo_info)) &
>> +            ~(0xFFFFFFFFUL << apicid_core_width(topo_info));
>> +    topo_ids->die_id =
>> +            (apicid >> apicid_die_offset(topo_info)) &
>> +            ~(0xFFFFFFFFUL << apicid_die_width(topo_info));
>> +    topo_ids->node_id =
>> +            (apicid >> apicid_node_offset_epyc(topo_info)) &
>> +            ~(0xFFFFFFFFUL << apicid_node_width_epyc(topo_info));
>> +    topo_ids->pkg_id = apicid >> apicid_pkg_offset_epyc(topo_info);
>> +}
>> +
>> +/*
>> + * Make APIC ID for the CPU 'cpu_index'
>> + *
>> + * 'cpu_index' is a sequential, contiguous ID for the CPU.
>> + */
>> +static inline apic_id_t x86_apicid_from_cpu_idx_epyc(X86CPUTopoInfo *topo_info,
>> +                                                     unsigned cpu_index)
>> +{
>> +    X86CPUTopoIDs topo_ids;
>> +    x86_topo_ids_from_idx_epyc(topo_info, cpu_index, &topo_ids);
>> +    return x86_apicid_from_topo_ids_epyc(topo_info, &topo_ids);
>> +}
>>  /* Make APIC ID for the CPU based on Pkg_ID, Core_ID, SMT_ID
>>   *
>>   * The caller must make sure core_id < nr_cores and smt_id < nr_threads.
>> diff --git a/include/hw/i386/x86.h b/include/hw/i386/x86.h
>> index d76fd0bbb1..38c2d27910 100644
>> --- a/include/hw/i386/x86.h
>> +++ b/include/hw/i386/x86.h
>> @@ -42,6 +42,7 @@ typedef uint32_t apic_id_t;
>>  
>>  typedef struct X86CPUTopoIDs {
>>      unsigned pkg_id;
>> +    unsigned node_id;
>>      unsigned die_id;
>>      unsigned core_id;
>>      unsigned smt_id;
>>
> 


  reply	other threads:[~2020-02-24 17:36 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
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 [this message]
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=1e23d802-8e88-1eec-f220-1e0d6b2e4839@amd.com \
    --to=babu.moger@amd.com \
    --cc=ehabkost@redhat.com \
    --cc=imammedo@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 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.