public inbox for devel@edk2.groups.io
 help / color / mirror / Atom feed
From: "Ni, Ruiyu" <ruiyu.ni@intel.com>
To: "Dong, Eric" <eric.dong@intel.com>,
	"edk2-devel@lists.01.org" <edk2-devel@lists.01.org>
Cc: Laszlo Ersek <lersek@redhat.com>
Subject: Re: [Patch v2 0/6] Fix performance issue caused by Set MSR task.
Date: Thu, 18 Oct 2018 02:12:32 +0000	[thread overview]
Message-ID: <734D49CCEBEEF84792F5B80ED585239D5BE97331@SHSMSX104.ccr.corp.intel.com> (raw)
In-Reply-To: <20181017021635.14972-1-eric.dong@intel.com>

Eric,
Can you post your changes to github yours mirror repo?
I found #3/6 cannot be applied to my code properly.

Thanks/Ray

> -----Original Message-----
> From: Dong, Eric
> Sent: Wednesday, October 17, 2018 10:16 AM
> To: edk2-devel@lists.01.org
> Cc: Ni, Ruiyu <ruiyu.ni@intel.com>; Laszlo Ersek <lersek@redhat.com>
> Subject: [Patch v2 0/6] Fix performance issue caused by Set MSR task.
> 
> V2 changes include:
> 1. Include the change for CpuCommonFeaturesLib which used to set MSR
> base on its scope info.
> 2. Include the change for CpuS3DataDxe driver which also handle the
> AcpiCpuData data.
> 3. Update code base on feedback for V1 changes.
> 
> V1 changes include:
> In a system which has multiple cores, current set register value task costs
> huge times.
> After investigation, current set MSR task costs most of the times. Current
> logic uses SpinLock to let set MSR task as an single thread task for all cores.
> Because MSR has scope attribute which may cause GP fault if multiple APs
> set MSR at the same time, current logic use an easiest solution (use SpinLock)
> to avoid this issue, but it will cost huge times.
> 
> In order to fix this performance issue, new solution will set MSRs base on
> their scope attribute. After this, the SpinLock will not needed. Without
> SpinLock, new issue raised which is caused by MSR dependence. For
> example, MSR A depends on MSR B which means MSR A must been set after
> MSR B has been set. Also MSR B is package scope level and MSR A is thread
> scope level. If system has multiple threads, Thread 1 needs to set the thread
> level MSRs and thread 2 needs to set thread and package level MSRs. Set
> MSRs task for thread 1 and thread 2 like below:
> 
>             Thread 1                 Thread 2
> MSR B          N                        Y
> MSR A          Y                        Y
> 
> If driver don't control execute MSR order, for thread 1, it will execute MSR A
> first, but at this time, MSR B not been executed yet by thread 2. system may
> trig exception at this time.
> 
> In order to fix the above issue, driver introduces semaphore logic to control
> the MSR execute sequence. For the above case, a semaphore will be add
> between MSR A and B for all threads. Semaphore has scope info for it. The
> possible scope value is core or package.
> For each thread, when it meets a semaphore during it set registers, it will 1)
> release semaphore (+1) for each threads in this core or package(based on
> the scope info for this
> semaphore) 2) acquire semaphore (-1) for all the threads in this core or
> package(based on the scope info for this semaphore). With these two steps,
> driver can control MSR sequence. Sample code logic like below:
> 
>   //
>   // First increase semaphore count by 1 for processors in this package.
>   //
>   for (ProcessorIndex = 0; ProcessorIndex < PackageThreadsCount ;
> ProcessorIndex ++) {
>     LibReleaseSemaphore ((UINT32 *) &SemaphorePtr[PackageOffset +
> ProcessorIndex]);
>   }
>   //
>   // Second, check whether the count has reach the check number.
>   //
>   for (ProcessorIndex = 0; ProcessorIndex < ValidApCount; ProcessorIndex ++)
> {
>     LibWaitForSemaphore (&SemaphorePtr[ApOffset]);
>   }
> 
> Platform Requirement:
> 1. This change requires register MSR setting base on MSR scope info. If still
> register MSR
>    for all threads, exception may raised.
> 
> Known limitation:
> 1. Current CpuFeatures driver supports DXE instance and PEI instance. But
> semaphore logic
>    requires Aps execute in async mode which is not supported by PEI driver.
> So CpuFeature
>    PEI instance not works after this change. We plan to support async mode
> for PEI in phase
>    2 for this task.
> 2. Current execute MSR task code in duplicated in PiSmmCpuDxeSmm driver
> and
>    RegisterCpuFeaturesLib library because the schedule limitation. Will merge
> the code to
>    RegisterCpuFeaturesLib and export as an API in phase 2 for this task.
> 
> Cc: Ruiyu Ni <ruiyu.ni@intel.com>
> Cc: Laszlo Ersek <lersek@redhat.com>
> Contributed-under: TianoCore Contribution Agreement 1.1
> Signed-off-by: Eric Dong <eric.dong@intel.com>
> 
> 
> Eric Dong (6):
>   UefiCpuPkg/Include/AcpiCpuData.h: Add Semaphore related Information.
>   UefiCpuPkg/RegisterCpuFeaturesLib.h: Add new dependence types.
>   UefiCpuPkg/RegisterCpuFeaturesLib: Add logic to support semaphore
>     type.
>   UefiCpuPkg/PiSmmCpuDxeSmm: Add logic to support semaphore type.
>   UefiCpuPkg/CpuS3DataDxe: Keep old data if value already existed.
>   UefiCpuPkg/CpuCommonFeaturesLib: Register MSR base on scope Info.
> 
>  UefiCpuPkg/CpuS3DataDxe/CpuS3Data.c                |   2 +
>  UefiCpuPkg/Include/AcpiCpuData.h                   |  45 +-
>  .../Include/Library/RegisterCpuFeaturesLib.h       |  25 +-
>  UefiCpuPkg/Library/CpuCommonFeaturesLib/C1e.c      |   8 +
>  UefiCpuPkg/Library/CpuCommonFeaturesLib/Eist.c     |  12 +
>  .../Library/CpuCommonFeaturesLib/ExecuteDisable.c  |  10 +
>  .../Library/CpuCommonFeaturesLib/FastStrings.c     |  12 +
>  .../Library/CpuCommonFeaturesLib/FeatureControl.c  |  38 ++
>  .../CpuCommonFeaturesLib/LimitCpuIdMaxval.c        |  14 +
>  .../Library/CpuCommonFeaturesLib/MachineCheck.c    |  38 ++
>  .../Library/CpuCommonFeaturesLib/MonitorMwait.c    |  15 +
>  .../Library/CpuCommonFeaturesLib/PendingBreak.c    |  11 +
>  UefiCpuPkg/Library/CpuCommonFeaturesLib/Ppin.c     |  11 +
>  .../Library/CpuCommonFeaturesLib/ProcTrace.c       |  11 +
>  UefiCpuPkg/Library/CpuCommonFeaturesLib/X2Apic.c   |  10 +
>  .../RegisterCpuFeaturesLib/CpuFeaturesInitialize.c | 438
> ++++++++++++++++---
>  .../DxeRegisterCpuFeaturesLib.c                    |  71 ++-
>  .../DxeRegisterCpuFeaturesLib.inf                  |   3 +
>  .../PeiRegisterCpuFeaturesLib.c                    |  55 ++-
>  .../PeiRegisterCpuFeaturesLib.inf                  |   1 +
>  .../RegisterCpuFeaturesLib/RegisterCpuFeatures.h   |  61 ++-
>  .../RegisterCpuFeaturesLib.c                       | 484 ++++++++++++++++++---
>  UefiCpuPkg/PiSmmCpuDxeSmm/CpuS3.c                  | 406 +++++++++++------
>  UefiCpuPkg/PiSmmCpuDxeSmm/MpService.c              |   3 -
>  UefiCpuPkg/PiSmmCpuDxeSmm/PiSmmCpuDxeSmm.h         |   3 +-
>  25 files changed, 1505 insertions(+), 282 deletions(-)
> 
> --
> 2.15.0.windows.1



  parent reply	other threads:[~2018-10-18  2:12 UTC|newest]

Thread overview: 18+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2018-10-17  2:16 [Patch v2 0/6] Fix performance issue caused by Set MSR task Eric Dong
2018-10-17  2:16 ` [Patch v2 1/6] UefiCpuPkg/Include/AcpiCpuData.h: Add Semaphore related Information Eric Dong
2018-10-18  3:04   ` Ni, Ruiyu
2018-10-18  3:10   ` Ni, Ruiyu
2018-10-17  2:16 ` [Patch v2 2/6] UefiCpuPkg/RegisterCpuFeaturesLib.h: Add new dependence types Eric Dong
2018-10-18  3:31   ` Ni, Ruiyu
2018-10-17  2:16 ` [Patch v2 3/6] UefiCpuPkg/RegisterCpuFeaturesLib: Add logic to support semaphore type Eric Dong
2018-10-18  5:46   ` Ni, Ruiyu
2018-10-17  2:16 ` [Patch v2 4/6] UefiCpuPkg/PiSmmCpuDxeSmm: " Eric Dong
2018-10-18  5:54   ` Ni, Ruiyu
2018-10-17  2:16 ` [Patch v2 5/6] UefiCpuPkg/CpuS3DataDxe: Keep old data if value already existed Eric Dong
2018-10-18  5:57   ` Ni, Ruiyu
2018-10-17  2:16 ` [Patch v2 6/6] UefiCpuPkg/CpuCommonFeaturesLib: Register MSR base on scope Info Eric Dong
2018-10-18  6:01   ` Ni, Ruiyu
2018-10-17 17:33 ` [Patch v2 0/6] Fix performance issue caused by Set MSR task Laszlo Ersek
2018-10-18  7:36   ` Dong, Eric
2018-10-18  2:12 ` Ni, Ruiyu [this message]
2018-10-18  2:35   ` Dong, Eric

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-list 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=734D49CCEBEEF84792F5B80ED585239D5BE97331@SHSMSX104.ccr.corp.intel.com \
    --to=devel@edk2.groups.io \
    /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