Re: [PATCH v10 0/7] AMD Pstate Driver Core Performance Boost

[Oleksandr Natalenko <oleksandr@natalenko.name>]

[-- Attachment #1: Type: text/plain, Size: 10212 bytes --]

Hello.

On středa 8. května 2024 9:21:05, SELČ Perry Yuan wrote:
> Hi all,
> The patchset series add core performance boost feature for AMD pstate
> driver including passisve ,guide and active mode support.
> 
> User can change core frequency boost control with a new sysfs entry:
> 
> "/sys/devices/system/cpu/amd_pstate/cpb_boost"
> 
> 
> 1) globally disable core boost:
> $ sudo bash -c "echo 0 > /sys/devices/system/cpu/amd_pstate/cpb_boost"
> $ lscpu -ae
> CPU NODE SOCKET CORE L1d:L1i:L2:L3 ONLINE    MAXMHZ   MINMHZ      MHZ
>   0    0      0    0 0:0:0:0          yes 4201.0000 400.0000 2983.578
>   1    0      0    1 1:1:1:0          yes 4201.0000 400.0000 2983.578
>   2    0      0    2 2:2:2:0          yes 4201.0000 400.0000 2583.855
>   3    0      0    3 3:3:3:0          yes 4201.0000 400.0000 2983.578
>   4    0      0    4 4:4:4:0          yes 4201.0000 400.0000 2983.578
> 
> 2) globally enable core boost:
> $ sudo bash -c "echo 1 > /sys/devices/system/cpu/amd_pstate/cpb_boost"
> $ lscpu -ae
>    0    0      0    0 0:0:0:0          yes 5759.0000 400.0000 2983.578
>   1    0      0    1 1:1:1:0          yes 5759.0000 400.0000 2983.578
>   2    0      0    2 2:2:2:0          yes 5759.0000 400.0000 2983.578
>   3    0      0    3 3:3:3:0          yes 5759.0000 400.0000 2983.578
>   4    0      0    4 4:4:4:0          yes 5759.0000 400.0000 2983.578
> 
> 
> ============================================================================
> The V9 patches add per CPU boost control, user can enable/disable CPUs boost
> as the below command tested on a laptop system.
> # before
>   CPU NODE SOCKET CORE L1d:L1i:L2:L3 ONLINE    MAXMHZ   MINMHZ       MHZ
>   0    0      0    0 0:0:0:0          yes 4208.0000 400.0000 1666.7740
>   1    0      0    0 0:0:0:0          yes 4208.0000 400.0000  400.0000
>   2    0      0    1 1:1:1:0          yes 4208.0000 400.0000 3386.1260
>   3    0      0    1 1:1:1:0          yes 4208.0000 400.0000  400.0000
> $ sudo rdmsr 0xc00102b3 -p 0
> 10a6
> 
> $ sudo bash -c "echo 1 > /sys/devices/system/cpu/cpu0/cpufreq/boost"
> # after
>   CPU NODE SOCKET CORE L1d:L1i:L2:L3 ONLINE    MAXMHZ   MINMHZ       MHZ
>     0    0      0    0 0:0:0:0          yes 3501.0000 400.0000  400.0000
>     1    0      0    0 0:0:0:0          yes 4208.0000 400.0000 1391.0690
>     2    0      0    1 1:1:1:0          yes 4208.0000 400.0000 3654.4541
>     3    0      0    1 1:1:1:0          yes 4208.0000 400.0000  400.0000
> $ sudo rdmsr 0xc00102b3 -p 0
> 108a
> 
> 
> The patches have been tested with the AMD 7950X processor and many users
> would like to get core boost control enabled for power saving.
> 
> Perry.
> 
> 
> Changes from v9:
>  * change per CPU boost sysfs file name to `boost` (Mario)
>  * rebased to latest linux-pm/bleeding-edge
> 
> Changes from v8:
>  * pick RB flag for patch 4 (Mario)
>  * change boot_cpu_has to cpu_feature_enabled for patch 2 (Boris)
>  * merge patch 6 into patch 3 (Mario)
>  * add two patch for per CPU boost control patch 6 & 7(Mario)
>  * rebased to latest linux-pm/bleeding-edge
> 
> Changes from v7:
>  * fix the mutext locking issue in the sysfs file update(Ray, Mario)
>  * pick ack flag from Ray
>  * use X86_FEATURE_CPB to verify the CPB function in Patch #2(Ray)
>  * rerun the testing to check function works well
>  * rebased to linux-pm/bleeding-edge latest
> 
> Changes from v6:
>  * reword patch 2 commit log (Gautham)
>  * update cover letter description(Gautham)
>  * rebase to kernel v6.9-rc5
> 
> Changes from v4:
>  * drop the legacy boost remove patch, let us keep the legacy interface
>    in case some applications break.
>  * rebase to linux-pm/bleeding-edge branch
>  * rework the patchset base on [PATCH v8 0/8] AMD Pstate Fixes And
>    Enhancements which has some intial work done there.
> 
> Changes from v4:
>  * move MSR_K7_HWCR_CPB_DIS_BIT into msr-index.h
>  * pick RB flag from Gautham R. Shenoy
>  * add Cc Oleksandr Natalenko <oleksandr@natalenko.name>
>  * rebase to latest linux-pm/bleeding-edge branch
>  * rebase the patch set on top of [PATCH v7 0/6] AMD Pstate Fixes And Enhancements
>  * update  [PATCH v7 2/6] to use MSR_K7_HWCR_CPB_DIS_BIT
> 
> Changes from v3:
>  * rebased to linux-pm/bleeding-edge v6.8
>  * rename global to amd_pstate_global_params(Oleksandr Natalenko)
>  * remove comments for boot_supported in amd_pstate.h
>  * fix the compiler warning for amd-pstate-ut.ko
>  * use for_each_online_cpu in cpb_boost_store which fix the null pointer
>    error during testing
>  * fix the max frequency value to be KHz when cpb boost disabled(Gautham R. Shenoy)
> 
> Changes from v2:
>  * move global struct to amd-pstate.h
>  * fix the amd-pstate-ut with new cpb control interface
> 
> Changes from v1:
>  * drop suspend/resume fix patch 6/7 because of the fix should be in
>    another fix series instead of CPB feature
>  * move the set_boost remove patch to the last(Mario)
>  * Fix commit info with "Closes:" (Mario)
>  * simplified global.cpb_supported initialization(Mario)
>  * Add guide mode support for CPB control
>  * Fixed some Doc typos and add guide mode info to Doc as well.
> 
> v1: https://lore.kernel.org/all/cover.1706255676.git.perry.yuan@amd.com/
> v2: https://lore.kernel.org/lkml/cover.1707047943.git.perry.yuan@amd.com/
> v3: https://lore.kernel.org/lkml/cover.1707297581.git.perry.yuan@amd.com/
> v4: https://lore.kernel.org/lkml/cover.1710322310.git.perry.yuan@amd.com/
> v5: https://lore.kernel.org/lkml/cover.1710473712.git.perry.yuan@amd.com/
> v6: https://lore.kernel.org/lkml/cover.1710754236.git.perry.yuan@amd.com/
> v7: https://lore.kernel.org/lkml/cover.1713861200.git.perry.yuan@amd.com/
> v8: https://lore.kernel.org/lkml/cover.1714112854.git.perry.yuan@amd.com/
> v9: https://lore.kernel.org/lkml/cover.1714989803.git.perry.yuan@amd.com/
> 
> Perry Yuan (7):
>   cpufreq: acpi: move MSR_K7_HWCR_CPB_DIS_BIT into msr-index.h
>   cpufreq: amd-pstate: initialize new core precision boost state
>   cpufreq: amd-pstate: implement cpb_boost sysfs entry for boost control
>   cpufreq: amd-pstate: fix the MSR highest perf will be reset issue
>     while cpb boost off
>   Documentation: cpufreq: amd-pstate: introduce the new cpu boost
>     control method
>   cpufreq: amd-pstate: introduce per CPU frequency boost control
>   Documentation: cpufreq: amd-pstate: update doc for Per CPU boost
>     control method
> 
>  Documentation/admin-guide/pm/amd-pstate.rst |  30 ++++
>  arch/x86/include/asm/msr-index.h            |   2 +
>  drivers/cpufreq/acpi-cpufreq.c              |   2 -
>  drivers/cpufreq/amd-pstate-ut.c             |   2 +-
>  drivers/cpufreq/amd-pstate.c                | 189 ++++++++++++++++++--
>  include/linux/amd-pstate.h                  |  14 ++
>  6 files changed, 225 insertions(+), 14 deletions(-)

I've applied this series along with fixes and improvements [1], and I cannot get guided mode to work with my CPU any more.

The CPU is:

```
Vendor ID:                AuthenticAMD
  Model name:             AMD Ryzen 9 5950X 16-Core Processor
    CPU family:           25
    Model:                33
    Thread(s) per core:   2
    Core(s) per socket:   16
    Socket(s):            1
    Stepping:             2
```

I've got `amd_pstate=guided` set in the kernel cmdline, but `amd-pstate-epp` gets loaded anyway. When I try to set `guided` manually via `echo guided | sudo tee /sys/devices/system/cpu/amd_pstate/status`, the status gets dropped to `disable`, `tee` errors out with `-ENODEV`, and there's this in the kernel log:

```
$ jctl -kb | grep sysfs: | cut -d ' ' -f 5-
kernel: sysfs: cannot create duplicate filename '/devices/system/cpu/cpufreq/policy0/boost'
…
kernel: sysfs: cannot create duplicate filename '/devices/system/cpu/cpufreq/policy31/boost'
```

The following is applied on top of v6.9-rc7:

```
cpufreq: amd-pstate: automatically load pstate driver by default
cpufreq: amd-pstate: fix the highest frequency issue which limit performance
cpufreq: amd-pstate: implement heterogeneous core topology for highest performance initialization
x86/cpufeatures: Add feature bits for AMD heterogeneous processor
cpufreq: amd-pstate: switch boot_cpu_has() to cpu_feature_enabled()
Documentation: PM: amd-pstate: add guide mode to the Operation mode
Documentation: PM: amd-pstate: add debugging section for driver loading failure
Documentation: PM: amd-pstate: introducing recommended reboot requirement during driver switch
cpufreq: amd-pstate: add debug message while CPPC is supported and disabled by SBIOS
cpufreq: amd-pstate: show CPPC debug message if CPPC is not supported
cpufreq: amd-pstate: optimiza the initial frequency values verification
Documentation: cpufreq: amd-pstate: update doc for Per CPU boost control method
cpufreq: amd-pstate: introduce per CPU frequency boost control
Documentation: cpufreq: amd-pstate: introduce the new cpu boost control method
cpufreq: amd-pstate: fix the MSR highest perf will be reset issue while cpb boost off
cpufreq: amd-pstate: implement cpb_boost sysfs entry for boost control
cpufreq: amd-pstate: initialize new core precision boost state
cpufreq: acpi: move MSR_K7_HWCR_CPB_DIS_BIT into msr-index.h
cpufreq: amd-pstate: remove unused variable lowest_nonlinear_freq
cpufreq: amd-pstate: fix code format problems
cpufreq: amd-pstate: Add quirk for the pstate CPPC capabilities missing
cpufreq: amd-pstate: get transition delay and latency value from ACPI tables
cpufreq: amd-pstate: Bail out if min/max/nominal_freq is 0
cpufreq: amd-pstate: Remove amd_get_{min,max,nominal,lowest_nonlinear}_freq()
cpufreq: amd-pstate: Unify computation of {max,min,nominal,lowest_nonlinear}_freq
cpufreq: amd-pstate: Document the units for freq variables in amd_cpudata
cpufreq: amd-pstate: Document *_limit_* fields in struct amd_cpudata
```

Previously, with your submissions, it was possible to use `guided` mode with my Zen 3.

[1] https://lore.kernel.org/lkml/cover.1715065568.git.perry.yuan@amd.com/

-- 
Oleksandr Natalenko (post-factum)

[-- Attachment #2: This is a digitally signed message part. --]
[-- Type: application/pgp-signature, Size: 833 bytes --]