| Message ID | 20210425073451.2557394-1-ray.huang@amd.com |
|---|---|
| State | Accepted |
| Commit | 3743d55b289c203d8f77b7cd47c24926b9d186ae |
| Headers | show |
| Series | [v4] x86, sched: Fix the AMD CPPC maximum perf on some specific generations | expand |
On Sun, Apr 25, 2021 at 9:35 AM Huang Rui <ray.huang@amd.com> wrote: > > Some AMD Ryzen generations has different calculation method on maximum > perf. 255 is not for all asics, some specific generations should use 166 > as the maximum perf. Otherwise, it will report incorrect frequency value > like below: > > ~ → lscpu | grep MHz > CPU MHz: 3400.000 > CPU max MHz: 7228.3198 > CPU min MHz: 2200.0000 > > Fixes: 41ea667227ba ("x86, sched: Calculate frequency invariance for AMD systems") > Fixes: 3c55e94c0ade ("cpufreq: ACPI: Extend frequency tables to cover boost frequencies") > > Reported-by: Jason Bagavatsingham <jason.bagavatsingham@gmail.com> > Tested-by: Jason Bagavatsingham <jason.bagavatsingham@gmail.com> > Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=211791 > Signed-off-by: Huang Rui <ray.huang@amd.com> > Cc: Alex Deucher <alexander.deucher@amd.com> > Cc: Nathan Fontenot <nathan.fontenot@amd.com> > Cc: Rafael J. Wysocki <rafael.j.wysocki@intel.com> > Cc: Borislav Petkov <bp@suse.de> > Cc: x86@kernel.org > Cc: stable@vger.kernel.org > --- > > Changes from V1 -> V2: > - Enhance the commit message. > - Move amd_get_highest_perf() into amd.c. > - Refine the implementation of switch-case. > - Cc stable mail list. > > Changes from V2 -> V3: > - Move the update into cppc_get_perf_caps() to correct the highest perf value in > the API. > > Changes from V3 -> V4: > - Rollback to V2 implementation because acpi_cppc.c will be used by ARM as well. > It's not good to add x86-specific calling there. > - Simplify the implementation of the functions. All of my comments have been addressed, so: Reviewed-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com> and I'm expecting the x86 maintainers to take care of this patch. > --- > arch/x86/include/asm/processor.h | 2 ++ > arch/x86/kernel/cpu/amd.c | 16 ++++++++++++++++ > arch/x86/kernel/smpboot.c | 2 +- > drivers/cpufreq/acpi-cpufreq.c | 6 +++++- > 4 files changed, 24 insertions(+), 2 deletions(-) > > diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h > index f1b9ed5efaa9..908bcaea1361 100644 > --- a/arch/x86/include/asm/processor.h > +++ b/arch/x86/include/asm/processor.h > @@ -804,8 +804,10 @@ DECLARE_PER_CPU(u64, msr_misc_features_shadow); > > #ifdef CONFIG_CPU_SUP_AMD > extern u32 amd_get_nodes_per_socket(void); > +extern u32 amd_get_highest_perf(void); > #else > static inline u32 amd_get_nodes_per_socket(void) { return 0; } > +static inline u32 amd_get_highest_perf(void) { return 0; } > #endif > > static inline uint32_t hypervisor_cpuid_base(const char *sig, uint32_t leaves) > diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c > index 347a956f71ca..bc3496669def 100644 > --- a/arch/x86/kernel/cpu/amd.c > +++ b/arch/x86/kernel/cpu/amd.c > @@ -1170,3 +1170,19 @@ void set_dr_addr_mask(unsigned long mask, int dr) > break; > } > } > + > +u32 amd_get_highest_perf(void) > +{ > + struct cpuinfo_x86 *c = &boot_cpu_data; > + > + if (c->x86 == 0x17 && ((c->x86_model >= 0x30 && c->x86_model < 0x40) || > + (c->x86_model >= 0x70 && c->x86_model < 0x80))) > + return 166; > + > + if (c->x86 == 0x19 && ((c->x86_model >= 0x20 && c->x86_model < 0x30) || > + (c->x86_model >= 0x40 && c->x86_model < 0x70))) > + return 166; > + > + return 225; > +} > +EXPORT_SYMBOL_GPL(amd_get_highest_perf); > diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c > index 02813a7f3a7c..7bec57d04a87 100644 > --- a/arch/x86/kernel/smpboot.c > +++ b/arch/x86/kernel/smpboot.c > @@ -2046,7 +2046,7 @@ static bool amd_set_max_freq_ratio(void) > return false; > } > > - highest_perf = perf_caps.highest_perf; > + highest_perf = amd_get_highest_perf(); > nominal_perf = perf_caps.nominal_perf; > > if (!highest_perf || !nominal_perf) { > diff --git a/drivers/cpufreq/acpi-cpufreq.c b/drivers/cpufreq/acpi-cpufreq.c > index d1bbc16fba4b..7e7450453714 100644 > --- a/drivers/cpufreq/acpi-cpufreq.c > +++ b/drivers/cpufreq/acpi-cpufreq.c > @@ -646,7 +646,11 @@ static u64 get_max_boost_ratio(unsigned int cpu) > return 0; > } > > - highest_perf = perf_caps.highest_perf; > + if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD) > + highest_perf = amd_get_highest_perf(); > + else > + highest_perf = perf_caps.highest_perf; > + > nominal_perf = perf_caps.nominal_perf; > > if (!highest_perf || !nominal_perf) { > -- > 2.25.1 >
* Huang Rui <ray.huang@amd.com> wrote: > Some AMD Ryzen generations has different calculation method on maximum > perf. 255 is not for all asics, some specific generations should use 166 > as the maximum perf. Otherwise, it will report incorrect frequency value > like below: > > ~ → lscpu | grep MHz > CPU MHz: 3400.000 > CPU max MHz: 7228.3198 > CPU min MHz: 2200.0000 It would have been useful to also quote the 'after' part. > +u32 amd_get_highest_perf(void) > +{ > + struct cpuinfo_x86 *c = &boot_cpu_data; > + > + if (c->x86 == 0x17 && ((c->x86_model >= 0x30 && c->x86_model < 0x40) || > + (c->x86_model >= 0x70 && c->x86_model < 0x80))) > + return 166; > + > + if (c->x86 == 0x19 && ((c->x86_model >= 0x20 && c->x86_model < 0x30) || > + (c->x86_model >= 0x40 && c->x86_model < 0x70))) > + return 166; I fixed these stray 4-space tabs. Looks good otherwise - queued up in tip:sched/urgent. Thanks, Ingo
On Sun, 25 Apr 2021, Huang Rui wrote: > Some AMD Ryzen generations has different calculation method on maximum > perf. 255 is not for all asics, some specific generations should use 166 > as the maximum perf. Otherwise, it will report incorrect frequency value > like below: The commit message says '255', but the code: > --- a/arch/x86/kernel/cpu/amd.c > +++ b/arch/x86/kernel/cpu/amd.c > @@ -1170,3 +1170,19 @@ void set_dr_addr_mask(unsigned long mask, int dr) > break; > } > } > + > +u32 amd_get_highest_perf(void) > +{ > + struct cpuinfo_x86 *c = &boot_cpu_data; > + > + if (c->x86 == 0x17 && ((c->x86_model >= 0x30 && c->x86_model < 0x40) || > + (c->x86_model >= 0x70 && c->x86_model < 0x80))) > + return 166; > + > + if (c->x86 == 0x19 && ((c->x86_model >= 0x20 && c->x86_model < 0x30) || > + (c->x86_model >= 0x40 && c->x86_model < 0x70))) > + return 166; > + > + return 225; > +} says 225? This is probably a typo? In any case they are out of sync. Alexander
* Alexander Monakov <amonakov@ispras.ru> wrote: > On Sun, 25 Apr 2021, Huang Rui wrote: > > > Some AMD Ryzen generations has different calculation method on maximum > > perf. 255 is not for all asics, some specific generations should use 166 > > as the maximum perf. Otherwise, it will report incorrect frequency value > > like below: > > The commit message says '255', but the code: > > > --- a/arch/x86/kernel/cpu/amd.c > > +++ b/arch/x86/kernel/cpu/amd.c > > @@ -1170,3 +1170,19 @@ void set_dr_addr_mask(unsigned long mask, int dr) > > break; > > } > > } > > + > > +u32 amd_get_highest_perf(void) > > +{ > > + struct cpuinfo_x86 *c = &boot_cpu_data; > > + > > + if (c->x86 == 0x17 && ((c->x86_model >= 0x30 && c->x86_model < 0x40) || > > + (c->x86_model >= 0x70 && c->x86_model < 0x80))) > > + return 166; > > + > > + if (c->x86 == 0x19 && ((c->x86_model >= 0x20 && c->x86_model < 0x30) || > > + (c->x86_model >= 0x40 && c->x86_model < 0x70))) > > + return 166; > > + > > + return 225; > > +} > > says 225? This is probably a typo? In any case they are out of sync. > > Alexander Ugh - that's indeed a good question ... Thanks, Ingo
On Thu, May 13, 2021 at 06:59:02AM +0800, Ingo Molnar wrote: > > * Alexander Monakov <amonakov@ispras.ru> wrote: > > > On Sun, 25 Apr 2021, Huang Rui wrote: > > > > > Some AMD Ryzen generations has different calculation method on maximum > > > perf. 255 is not for all asics, some specific generations should use 166 > > > as the maximum perf. Otherwise, it will report incorrect frequency value > > > like below: > > > > The commit message says '255', but the code: > > > > > --- a/arch/x86/kernel/cpu/amd.c > > > +++ b/arch/x86/kernel/cpu/amd.c > > > @@ -1170,3 +1170,19 @@ void set_dr_addr_mask(unsigned long mask, int dr) > > > break; > > > } > > > } > > > + > > > +u32 amd_get_highest_perf(void) > > > +{ > > > + struct cpuinfo_x86 *c = &boot_cpu_data; > > > + > > > + if (c->x86 == 0x17 && ((c->x86_model >= 0x30 && c->x86_model < 0x40) || > > > + (c->x86_model >= 0x70 && c->x86_model < 0x80))) > > > + return 166; > > > + > > > + if (c->x86 == 0x19 && ((c->x86_model >= 0x20 && c->x86_model < 0x30) || > > > + (c->x86_model >= 0x40 && c->x86_model < 0x70))) > > > + return 166; > > > + > > > + return 225; > > > +} > > > > says 225? This is probably a typo? In any case they are out of sync. > > > > Alexander > > Ugh - that's indeed a good question ... > Ah sorry! It's my typo. It should be 255 (confirmed in the ucode). Alexander, thanks a lot to catch this! Ingo, would you mind to update it from 225 -> 255 while you apply this patch or let me know if you want me to send v5? Thanks, Ray
* Huang Rui <ray.huang@amd.com> wrote: > On Thu, May 13, 2021 at 06:59:02AM +0800, Ingo Molnar wrote: > > > > * Alexander Monakov <amonakov@ispras.ru> wrote: > > > > > On Sun, 25 Apr 2021, Huang Rui wrote: > > > > > > > Some AMD Ryzen generations has different calculation method on maximum > > > > perf. 255 is not for all asics, some specific generations should use 166 > > > > as the maximum perf. Otherwise, it will report incorrect frequency value > > > > like below: > > > > > > The commit message says '255', but the code: > > > > > > > --- a/arch/x86/kernel/cpu/amd.c > > > > +++ b/arch/x86/kernel/cpu/amd.c > > > > @@ -1170,3 +1170,19 @@ void set_dr_addr_mask(unsigned long mask, int dr) > > > > break; > > > > } > > > > } > > > > + > > > > +u32 amd_get_highest_perf(void) > > > > +{ > > > > + struct cpuinfo_x86 *c = &boot_cpu_data; > > > > + > > > > + if (c->x86 == 0x17 && ((c->x86_model >= 0x30 && c->x86_model < 0x40) || > > > > + (c->x86_model >= 0x70 && c->x86_model < 0x80))) > > > > + return 166; > > > > + > > > > + if (c->x86 == 0x19 && ((c->x86_model >= 0x20 && c->x86_model < 0x30) || > > > > + (c->x86_model >= 0x40 && c->x86_model < 0x70))) > > > > + return 166; > > > > + > > > > + return 225; > > > > +} > > > > > > says 225? This is probably a typo? In any case they are out of sync. > > > > > > Alexander > > > > Ugh - that's indeed a good question ... > > > > Ah sorry! It's my typo. It should be 255 (confirmed in the ucode). > > Alexander, thanks a lot to catch this! > > Ingo, would you mind to update it from 225 -> 255 while you apply this > patch or let me know if you want me to send v5? No need to send v5, done! I have a system that appears to be affected by this bug: kepler:~> lscpu | grep -i mhz CPU MHz: 4000.000 CPU max MHz: 7140.6250 CPU min MHz: 2200.0000 So I should be able to confirm after a reboot. Thanks, Ingo
On Thu, May 13, 2021 at 06:12:14PM +0800, Ingo Molnar wrote: > > * Huang Rui <ray.huang@amd.com> wrote: > > > On Thu, May 13, 2021 at 06:59:02AM +0800, Ingo Molnar wrote: > > > > > > * Alexander Monakov <amonakov@ispras.ru> wrote: > > > > > > > On Sun, 25 Apr 2021, Huang Rui wrote: > > > > > > > > > Some AMD Ryzen generations has different calculation method on maximum > > > > > perf. 255 is not for all asics, some specific generations should use 166 > > > > > as the maximum perf. Otherwise, it will report incorrect frequency value > > > > > like below: > > > > > > > > The commit message says '255', but the code: > > > > > > > > > --- a/arch/x86/kernel/cpu/amd.c > > > > > +++ b/arch/x86/kernel/cpu/amd.c > > > > > @@ -1170,3 +1170,19 @@ void set_dr_addr_mask(unsigned long mask, int dr) > > > > > break; > > > > > } > > > > > } > > > > > + > > > > > +u32 amd_get_highest_perf(void) > > > > > +{ > > > > > + struct cpuinfo_x86 *c = &boot_cpu_data; > > > > > + > > > > > + if (c->x86 == 0x17 && ((c->x86_model >= 0x30 && c->x86_model < 0x40) || > > > > > + (c->x86_model >= 0x70 && c->x86_model < 0x80))) > > > > > + return 166; > > > > > + > > > > > + if (c->x86 == 0x19 && ((c->x86_model >= 0x20 && c->x86_model < 0x30) || > > > > > + (c->x86_model >= 0x40 && c->x86_model < 0x70))) > > > > > + return 166; > > > > > + > > > > > + return 225; > > > > > +} > > > > > > > > says 225? This is probably a typo? In any case they are out of sync. > > > > > > > > Alexander > > > > > > Ugh - that's indeed a good question ... > > > > > > > Ah sorry! It's my typo. It should be 255 (confirmed in the ucode). > > > > Alexander, thanks a lot to catch this! > > > > Ingo, would you mind to update it from 225 -> 255 while you apply this > > patch or let me know if you want me to send v5? > > No need to send v5, done! > > I have a system that appears to be affected by this bug: > > kepler:~> lscpu | grep -i mhz > CPU MHz: 4000.000 > CPU max MHz: 7140.6250 > CPU min MHz: 2200.0000 > > So I should be able to confirm after a reboot. > Thanks! Please feel free to let me know whether it's able to fix your machine. :-) Thanks, Ray
On Thu, May 13, 2021 at 06:39:08PM +0800, Ingo Molnar wrote: > > * Ingo Molnar <mingo@kernel.org> wrote: > > > No need to send v5, done! > > > > I have a system that appears to be affected by this bug: > > > > kepler:~> lscpu | grep -i mhz > > CPU MHz: 4000.000 > > CPU max MHz: 7140.6250 > > CPU min MHz: 2200.0000 > > > > So I should be able to confirm after a reboot. > > 'CPU max Mhz' seems to be saner now: > > kepler:~> lscpu | grep -i mhz > > CPU MHz: 2200.000 > CPU max MHz: 4917.9678 > CPU min MHz: 2200.0000 > Yes, happy to know this :-) Thanks, Ray
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index f1b9ed5efaa9..908bcaea1361 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -804,8 +804,10 @@ DECLARE_PER_CPU(u64, msr_misc_features_shadow); #ifdef CONFIG_CPU_SUP_AMD extern u32 amd_get_nodes_per_socket(void); +extern u32 amd_get_highest_perf(void); #else static inline u32 amd_get_nodes_per_socket(void) { return 0; } +static inline u32 amd_get_highest_perf(void) { return 0; } #endif static inline uint32_t hypervisor_cpuid_base(const char *sig, uint32_t leaves) diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index 347a956f71ca..bc3496669def 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -1170,3 +1170,19 @@ void set_dr_addr_mask(unsigned long mask, int dr) break; } } + +u32 amd_get_highest_perf(void) +{ + struct cpuinfo_x86 *c = &boot_cpu_data; + + if (c->x86 == 0x17 && ((c->x86_model >= 0x30 && c->x86_model < 0x40) || + (c->x86_model >= 0x70 && c->x86_model < 0x80))) + return 166; + + if (c->x86 == 0x19 && ((c->x86_model >= 0x20 && c->x86_model < 0x30) || + (c->x86_model >= 0x40 && c->x86_model < 0x70))) + return 166; + + return 225; +} +EXPORT_SYMBOL_GPL(amd_get_highest_perf); diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 02813a7f3a7c..7bec57d04a87 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -2046,7 +2046,7 @@ static bool amd_set_max_freq_ratio(void) return false; } - highest_perf = perf_caps.highest_perf; + highest_perf = amd_get_highest_perf(); nominal_perf = perf_caps.nominal_perf; if (!highest_perf || !nominal_perf) { diff --git a/drivers/cpufreq/acpi-cpufreq.c b/drivers/cpufreq/acpi-cpufreq.c index d1bbc16fba4b..7e7450453714 100644 --- a/drivers/cpufreq/acpi-cpufreq.c +++ b/drivers/cpufreq/acpi-cpufreq.c @@ -646,7 +646,11 @@ static u64 get_max_boost_ratio(unsigned int cpu) return 0; } - highest_perf = perf_caps.highest_perf; + if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD) + highest_perf = amd_get_highest_perf(); + else + highest_perf = perf_caps.highest_perf; + nominal_perf = perf_caps.nominal_perf; if (!highest_perf || !nominal_perf) {
Some AMD Ryzen generations has different calculation method on maximum perf. 255 is not for all asics, some specific generations should use 166 as the maximum perf. Otherwise, it will report incorrect frequency value like below: ~ → lscpu | grep MHz CPU MHz: 3400.000 CPU max MHz: 7228.3198 CPU min MHz: 2200.0000 Fixes: 41ea667227ba ("x86, sched: Calculate frequency invariance for AMD systems") Fixes: 3c55e94c0ade ("cpufreq: ACPI: Extend frequency tables to cover boost frequencies") Reported-by: Jason Bagavatsingham <jason.bagavatsingham@gmail.com> Tested-by: Jason Bagavatsingham <jason.bagavatsingham@gmail.com> Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=211791 Signed-off-by: Huang Rui <ray.huang@amd.com> Cc: Alex Deucher <alexander.deucher@amd.com> Cc: Nathan Fontenot <nathan.fontenot@amd.com> Cc: Rafael J. Wysocki <rafael.j.wysocki@intel.com> Cc: Borislav Petkov <bp@suse.de> Cc: x86@kernel.org Cc: stable@vger.kernel.org --- Changes from V1 -> V2: - Enhance the commit message. - Move amd_get_highest_perf() into amd.c. - Refine the implementation of switch-case. - Cc stable mail list. Changes from V2 -> V3: - Move the update into cppc_get_perf_caps() to correct the highest perf value in the API. Changes from V3 -> V4: - Rollback to V2 implementation because acpi_cppc.c will be used by ARM as well. It's not good to add x86-specific calling there. - Simplify the implementation of the functions. --- arch/x86/include/asm/processor.h | 2 ++ arch/x86/kernel/cpu/amd.c | 16 ++++++++++++++++ arch/x86/kernel/smpboot.c | 2 +- drivers/cpufreq/acpi-cpufreq.c | 6 +++++- 4 files changed, 24 insertions(+), 2 deletions(-)