[edk2-devel] [edk2-platforms] [PATCH v1 2/3] Platform/ARM/SgiPkg: Add HMAT ACPI table for RdN1EdgeX2

Jonathan Cameron via groups.io jonathan.cameron=huawei.com at groups.io
Fri Jan 29 09:49:40 UTC 2021


On Thu, 28 Jan 2021 15:58:48 +0000
Jonathan Cameron via groups.io <jonathan.cameron=huawei.com at groups.io> wrote:

> On Thu, 28 Jan 2021 19:12:30 +0530
> Vijayenthiran Subramaniam <vijayenthiran.subramaniam at arm.com> wrote:
> 
> > Add HMAT table support for RD-N1-Edge Dual-chip platform.
> > 
> > Signed-off-by: Vijayenthiran Subramaniam <vijayenthiran.subramaniam at arm.com>
> > ---
> >  Platform/ARM/SgiPkg/AcpiTables/RdN1EdgeX2AcpiTables.inf |   1 +
> >  Platform/ARM/SgiPkg/AcpiTables/RdN1EdgeX2/Hmat.aslc     | 108 ++++++++++++++++++++
> >  2 files changed, 109 insertions(+)
> > 
> > diff --git a/Platform/ARM/SgiPkg/AcpiTables/RdN1EdgeX2AcpiTables.inf b/Platform/ARM/SgiPkg/AcpiTables/RdN1EdgeX2AcpiTables.inf
> > index d44f02ab0c16..36d41281439d 100644
> > --- a/Platform/ARM/SgiPkg/AcpiTables/RdN1EdgeX2AcpiTables.inf
> > +++ b/Platform/ARM/SgiPkg/AcpiTables/RdN1EdgeX2AcpiTables.inf
> > @@ -22,6 +22,7 @@ [Sources]
> >    Iort.aslc
> >    Mcfg.aslc
> >    RdN1Edge/Dsdt.asl
> > +  RdN1EdgeX2/Hmat.aslc
> >    RdN1EdgeX2/Madt.aslc
> >    RdN1EdgeX2/Srat.aslc
> >    Spcr.aslc
> > diff --git a/Platform/ARM/SgiPkg/AcpiTables/RdN1EdgeX2/Hmat.aslc b/Platform/ARM/SgiPkg/AcpiTables/RdN1EdgeX2/Hmat.aslc
> > new file mode 100644
> > index 000000000000..29d089aed053
> > --- /dev/null
> > +++ b/Platform/ARM/SgiPkg/AcpiTables/RdN1EdgeX2/Hmat.aslc
> > @@ -0,0 +1,108 @@
> > +/** @file
> > +*  Heterogeneous Memory Attribute Table (HMAT)
> > +*
> > +*  Copyright (c) 2020, ARM Limited. All rights reserved.
> > +*
> > +*  SPDX-License-Identifier: BSD-2-Clause-Patent
> > +*
> > +**/
> > +
> > +#include "SgiAcpiHeader.h"
> > +#include "SgiPlatform.h"
> > +#include <IndustryStandard/Acpi.h>
> > +#include <Library/AcpiLib.h>
> > +#include <Library/ArmLib.h>
> > +
> > +#define CHIP_CNT                      FixedPcdGet32 (PcdChipCount)
> > +#define INITATOR_PROXIMITY_DOMAIN_CNT 2
> > +#define TARGET_PROXIMITY_DOMIAIN_CNT  2  
> 
> DOMAIN
> 
> > +
> > +//
> > +// HMAT Table
> > +//
> > +#pragma pack (1)
> > +
> > +typedef struct {
> > +  UINT32  InitatorProximityDomain[INITATOR_PROXIMITY_DOMAIN_CNT];
> > +  UINT32  TargetProximityDomiain[TARGET_PROXIMITY_DOMIAIN_CNT];
> > +  UINT16  MatrixEntry[INITATOR_PROXIMITY_DOMAIN_CNT * TARGET_PROXIMITY_DOMIAIN_CNT];
> > +} InitiatorTargetProximityMatrix;
> > +
> > +typedef struct {
> > +  EFI_ACPI_6_3_HETEROGENEOUS_MEMORY_ATTRIBUTE_TABLE_HEADER                Header;
> > +  EFI_ACPI_6_3_HMAT_STRUCTURE_MEMORY_PROXIMITY_DOMAIN_ATTRIBUTES          Proximity[CHIP_CNT];
> > +  EFI_ACPI_6_3_HMAT_STRUCTURE_SYSTEM_LOCALITY_LATENCY_AND_BANDWIDTH_INFO  LatencyInfo;
> > +  InitiatorTargetProximityMatrix                                          Matrix;
> > +  EFI_ACPI_6_3_HMAT_STRUCTURE_MEMORY_SIDE_CACHE_INFO                      MemSideCache0;
> > +  EFI_ACPI_6_3_HMAT_STRUCTURE_MEMORY_SIDE_CACHE_INFO                      MemSideCache1;
> > +} EFI_ACPI_HETEROGENEOUS_MEMORY_ATTRIBUTE_TABLE;
> > +
> > +#pragma pack ()
> > +
> > +#define HMAT_STRUCTURE_MEMORY_SIDE_CACHE_INFO_CACHE_ATTRIBUTES_INIT(           \
> > +  TotalCacheLevels, CacheLevel, CacheAssociativity, WritePolicy, CacheLineSize \
> > +    )                                                                          \
> > +{                                                                              \
> > +  TotalCacheLevels, CacheLevel, CacheAssociativity, WritePolicy, CacheLineSize \
> > +}
> > +
> > +EFI_ACPI_HETEROGENEOUS_MEMORY_ATTRIBUTE_TABLE Hmat = {
> > +  // Header
> > +  {
> > +    ARM_ACPI_HEADER (
> > +      EFI_ACPI_6_3_HETEROGENEOUS_MEMORY_ATTRIBUTE_TABLE_SIGNATURE,
> > +      EFI_ACPI_HETEROGENEOUS_MEMORY_ATTRIBUTE_TABLE,
> > +      EFI_ACPI_6_3_HETEROGENEOUS_MEMORY_ATTRIBUTE_TABLE_REVISION
> > +    ),
> > +    {
> > +      EFI_ACPI_RESERVED_BYTE,
> > +      EFI_ACPI_RESERVED_BYTE,
> > +      EFI_ACPI_RESERVED_BYTE,
> > +      EFI_ACPI_RESERVED_BYTE
> > +    },
> > +  },
> > +
> > +  // Memory Proximity Domain
> > +  {
> > +    EFI_ACPI_6_3_HMAT_STRUCTURE_MEMORY_PROXIMITY_DOMAIN_ATTRIBUTES_INIT (
> > +      1, 0x0, 0x0),
> > +    EFI_ACPI_6_3_HMAT_STRUCTURE_MEMORY_PROXIMITY_DOMAIN_ATTRIBUTES_INIT (
> > +      1, 0x1, 0x1),
> > +   },
> > +
> > +  // Latency Info
> > +  EFI_ACPI_6_3_HMAT_STRUCTURE_SYSTEM_LOCALITY_LATENCY_AND_BANDWIDTH_INFO_INIT (
> > +    0, 0, INITATOR_PROXIMITY_DOMAIN_CNT, TARGET_PROXIMITY_DOMIAIN_CNT, 100),
> > +  {
> > +    {0, 1}, {0, 1},
> > +    {
> > +      10, 20,
> > +      20, 10,
> > +    }
> > +  },

Hi,

Now either you have a very odd machine in which latencies are round numbers that happen
to look like the values in SLIT or ... ?

HMAT has very carefully defined real world units to overcome the fact that there
was no standard scaling etc for SLIT.  It is not a good idea to put tables out
there which don't do this right as someone may copy this for a real system
and we end up with HMAT being roughly as useless for performance prediction as
SLIT is.  That is not something I would want to see.

Jonathan

> > +
> > +  // Memory Side Cache
> > +  EFI_ACPI_6_3_HMAT_STRUCTURE_MEMORY_SIDE_CACHE_INFO_INIT (
> > +    0x0, SIZE_8MB,
> > +    HMAT_STRUCTURE_MEMORY_SIDE_CACHE_INFO_CACHE_ATTRIBUTES_INIT (
> > +      1,
> > +      1,
> > +      2,
> > +      2,
> > +      64 // 64 bytes cache line length
> > +    ),
> > +    0),
> > +
> > +  EFI_ACPI_6_3_HMAT_STRUCTURE_MEMORY_SIDE_CACHE_INFO_INIT (
> > +    0x1, SIZE_8MB,
> > +    HMAT_STRUCTURE_MEMORY_SIDE_CACHE_INFO_CACHE_ATTRIBUTES_INIT (
> > +      1,
> > +      1,
> > +      2,
> > +      2,
> > +      64 // 64 bytes cache line length
> > +    ),
> > +    0),
> > +};
> > +
> > +VOID* CONST ReferenceAcpiTable = &Hmat;  
> 
> 
> 
> 
> 
> 



-=-=-=-=-=-=-=-=-=-=-=-
Groups.io Links: You receive all messages sent to this group.
View/Reply Online (#70905): https://edk2.groups.io/g/devel/message/70905
Mute This Topic: https://groups.io/mt/80183279/1813853
Group Owner: devel+owner at edk2.groups.io
Unsubscribe: https://edk2.groups.io/g/devel/unsub [edk2-devel-archive at redhat.com]
-=-=-=-=-=-=-=-=-=-=-=-





More information about the edk2-devel-archive mailing list