[AMD Official Use Only - General] Hi Rafael: > -----Original Message----- > From: Rafael J. Wysocki <rafael@xxxxxxxxxx> > Sent: Tuesday, December 12, 2023 9:44 PM > To: Meng, Li (Jassmine) <Li.Meng@xxxxxxx> > Cc: Rafael J . Wysocki <rafael.j.wysocki@xxxxxxxxx>; Huang, Ray > <Ray.Huang@xxxxxxx>; linux-pm@xxxxxxxxxxxxxxx; linux- > kernel@xxxxxxxxxxxxxxx; x86@xxxxxxxxxx; linux-acpi@xxxxxxxxxxxxxxx; Shuah > Khan <skhan@xxxxxxxxxxxxxxxxxxx>; linux-kselftest@xxxxxxxxxxxxxxx; > Fontenot, Nathan <Nathan.Fontenot@xxxxxxx>; Sharma, Deepak > <Deepak.Sharma@xxxxxxx>; Deucher, Alexander > <Alexander.Deucher@xxxxxxx>; Limonciello, Mario > <Mario.Limonciello@xxxxxxx>; Huang, Shimmer > <Shimmer.Huang@xxxxxxx>; Yuan, Perry <Perry.Yuan@xxxxxxx>; Du, > Xiaojian <Xiaojian.Du@xxxxxxx>; Viresh Kumar <viresh.kumar@xxxxxxxxxx>; > Borislav Petkov <bp@xxxxxxxxx>; Oleksandr Natalenko > <oleksandr@xxxxxxxxxxxxxx> > Subject: Re: [PATCH V12 4/7] cpufreq: Add a notification message that the > highest perf has changed > > Caution: This message originated from an External Source. Use proper > caution when opening attachments, clicking links, or responding. > > > On Wed, Dec 6, 2023 at 10:13 PM Rafael J. Wysocki <rafael@xxxxxxxxxx> > wrote: > > > > On Wed, Dec 6, 2023 at 9:58 PM Rafael J. Wysocki <rafael@xxxxxxxxxx> > wrote: > > > > > > On Tue, Dec 5, 2023 at 7:38 AM Meng Li <li.meng@xxxxxxx> wrote: > > > > > > > > ACPI 6.5 section 8.4.6.1.1.1 specifies that Notify event 0x85 can > > > > be emmitted to cause the the OSPM to re-evaluate the highest > > > > performance > > > > > > Typos above. Given the number of iterations of this patch, this is > > > kind of disappointing. > > > > > > > register. Add support for this event. > > > > > > Also it would be nice to describe how this is supposed to work at > > > least roughly, so it is not necessary to reverse-engineer the patch > > > to find out that. > > > > > > > Tested-by: Oleksandr Natalenko <oleksandr@xxxxxxxxxxxxxx> > > > > Reviewed-by: Mario Limonciello <mario.limonciello@xxxxxxx> > > > > Reviewed-by: Huang Rui <ray.huang@xxxxxxx> > > > > Reviewed-by: Perry Yuan <perry.yuan@xxxxxxx> > > > > Signed-off-by: Meng Li <li.meng@xxxxxxx> > > > > Link: > > > > > https://uefi.org/specs/ACPI/6.5/05_ACPI_Software_Programming_Model > > > > .html#processor-device-notification-values > > > > --- > > > > drivers/acpi/processor_driver.c | 6 ++++++ > > > > drivers/cpufreq/cpufreq.c | 13 +++++++++++++ > > > > include/linux/cpufreq.h | 5 +++++ > > > > 3 files changed, 24 insertions(+) > > > > > > > > diff --git a/drivers/acpi/processor_driver.c > > > > b/drivers/acpi/processor_driver.c index 4bd16b3f0781..29b2fb68a35d > > > > 100644 > > > > --- a/drivers/acpi/processor_driver.c > > > > +++ b/drivers/acpi/processor_driver.c > > > > @@ -27,6 +27,7 @@ > > > > #define ACPI_PROCESSOR_NOTIFY_PERFORMANCE 0x80 > > > > #define ACPI_PROCESSOR_NOTIFY_POWER 0x81 > > > > #define ACPI_PROCESSOR_NOTIFY_THROTTLING 0x82 > > > > +#define ACPI_PROCESSOR_NOTIFY_HIGEST_PERF_CHANGED 0x85 > > > > > > > > MODULE_AUTHOR("Paul Diefenbaugh"); > MODULE_DESCRIPTION("ACPI > > > > Processor Driver"); @@ -83,6 +84,11 @@ static void > > > > acpi_processor_notify(acpi_handle handle, u32 event, void *data) > > > > acpi_bus_generate_netlink_event(device->pnp.device_class, > > > > dev_name(&device->dev), event, 0); > > > > break; > > > > + case ACPI_PROCESSOR_NOTIFY_HIGEST_PERF_CHANGED: > > > > + cpufreq_update_highest_perf(pr->id); > > > > > > And the design appears to be a bit ad-hoc here. > > > > > > Because why does it have anything to do with cpufreq? > > > > Well, clearly, cpufreq can be affected by this, but why would it be > > not affected the same way as in the > ACPI_PROCESSOR_NOTIFY_PERFORMANCE > > case? > > > > That is, why isn't cpufreq_update_limits() the right thing to do? > > Seriously, I'm not going to apply this patch so long as my comments above > are not addressed. [Meng, Li (Jassmine)] Sorry for the delayed reply to the email. BIOS/AGESA is responsible to issue the Notify 0x85 to OS that the preferred core has changed. It will only affect the ranking of the preferred core, not the impact policy limits. AMD P-state driver will set the priority of the cores based on the preferred core ranking, and prioritize selecting higher priority core to run the task.
