* [PATCH v2 0/2] cpufreq: intel_pstate: Add scaling factor for Bartlett Lake P-core only SKUs
@ 2026-05-08 6:30 Henry Tseng
2026-05-08 6:30 ` [PATCH v2 1/2] cpufreq: intel_pstate: Fix scaling for hybrid-capable CPUs not reporting hybrid Henry Tseng
2026-05-08 6:30 ` [PATCH v2 2/2] cpufreq: intel_pstate: Use HYBRID_SCALING_FACTOR_ADL for Bartlett Lake Henry Tseng
0 siblings, 2 replies; 4+ messages in thread
From: Henry Tseng @ 2026-05-08 6:30 UTC (permalink / raw)
To: Srinivas Pandruvada, Rafael J. Wysocki, Len Brown, Viresh Kumar
Cc: linux-pm, SW Chen, Kevin Ko, Henry Tseng
On Bartlett Lake P-core only SKUs (e.g. Intel Core 9 273PE),
cpuinfo_max_freq is reported as 7.0/7.3 GHz, exceeding the datasheet
Max Turbo Frequency of 5.7 GHz. Root cause: hwp_get_cpu_scaling()
returns 100000 (default core scaling) instead of the correct factor
78741.
Patch 1 fixes a framework regression introduced by 9b18d536b124,
where the registered hybrid_scaling_factor is bypassed for
table-registered models not reporting X86_FEATURE_HYBRID_CPU.
Patch 1 must apply before patch 2; the Bartlett Lake entry alone has
no effect on these SKUs without the framework fix.
Patch 2 adds Bartlett Lake to intel_hybrid_scaling_factor[] with
HYBRID_SCALING_FACTOR_ADL.
---
v2:
- Reuse intel_hybrid_scaling_factor[] with HYBRID_SCALING_FACTOR_ADL
instead of introducing a new intel_cppc_scaling_ids[] table and
computing the scaling factor via CPPC at runtime.
- Split into two patches: framework fix + Bartlett Lake entry.
v1:
- https://lore.kernel.org/linux-pm/20260506095157.1591221-1-henrytseng@qnap.com/
Henry Tseng (2):
cpufreq: intel_pstate: Fix scaling for hybrid-capable CPUs not
reporting hybrid
cpufreq: intel_pstate: Use HYBRID_SCALING_FACTOR_ADL for Bartlett Lake
drivers/cpufreq/intel_pstate.c | 6 +++++-
1 file changed, 5 insertions(+), 1 deletion(-)
--
2.43.0
^ permalink raw reply [flat|nested] 4+ messages in thread* [PATCH v2 1/2] cpufreq: intel_pstate: Fix scaling for hybrid-capable CPUs not reporting hybrid 2026-05-08 6:30 [PATCH v2 0/2] cpufreq: intel_pstate: Add scaling factor for Bartlett Lake P-core only SKUs Henry Tseng @ 2026-05-08 6:30 ` Henry Tseng 2026-05-10 14:34 ` srinivas pandruvada 2026-05-08 6:30 ` [PATCH v2 2/2] cpufreq: intel_pstate: Use HYBRID_SCALING_FACTOR_ADL for Bartlett Lake Henry Tseng 1 sibling, 1 reply; 4+ messages in thread From: Henry Tseng @ 2026-05-08 6:30 UTC (permalink / raw) To: Srinivas Pandruvada, Rafael J. Wysocki, Len Brown, Viresh Kumar Cc: linux-pm, SW Chen, Kevin Ko, Henry Tseng Commit 9b18d536b124 ("cpufreq: intel_pstate: Use CPPC to get scaling factors") restructured hwp_get_cpu_scaling() so that, when the CPU model is registered in intel_hybrid_scaling_factor[] and hybrid_get_cpu_type() does not return INTEL_CPU_TYPE_CORE, the function early-returns core_get_scaling() (100000) instead of falling through to intel_pstate_cppc_get_scaling(). This regresses the behavior previously addressed by commit 0fcfc9e51990 ("cpufreq: intel_pstate: Fix scaling for hybrid-capable systems with disabled E-cores"). On hybrid-capable processors not reporting X86_FEATURE_HYBRID_CPU (no E-cores enumerated), hybrid_get_cpu_type() returns 0. Before 9b18d536b124, such CPUs fell through to intel_pstate_cppc_get_scaling(), which returned the registered hybrid_scaling_factor. After 9b18d536b124, for models registered in the table the early return takes core_get_scaling() before reaching that fallback, so the registered factor is not used. Fix this by returning hybrid_scaling_factor directly for CPU models registered in intel_hybrid_scaling_factor[] that do not report X86_FEATURE_HYBRID_CPU, before checking hybrid_get_cpu_type(). With that fix, non-hybrid CPUs in the table now reach intel_pstate_hybrid_hwp_adjust() with scaling != perf_ctl_scaling. Since commit 5313ec4a215a ("cpufreq: intel_pstate: Improve printing of debug messages") sets hwp_is_hybrid = true unconditionally inside that function, set hwp_is_hybrid based on X86_FEATURE_HYBRID_CPU instead, so the flag is not set on non-hybrid systems. Fixes: 9b18d536b124 ("cpufreq: intel_pstate: Use CPPC to get scaling factors") Signed-off-by: Henry Tseng <henrytseng@qnap.com> --- drivers/cpufreq/intel_pstate.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c index 1292da53e5fc..d39592e86570 100644 --- a/drivers/cpufreq/intel_pstate.c +++ b/drivers/cpufreq/intel_pstate.c @@ -585,7 +585,7 @@ static void intel_pstate_hybrid_hwp_adjust(struct cpudata *cpu) if (scaling == perf_ctl_scaling) return; - hwp_is_hybrid = true; + hwp_is_hybrid = cpu_feature_enabled(X86_FEATURE_HYBRID_CPU); cpu->pstate.turbo_freq = rounddown(cpu->pstate.turbo_pstate * scaling, perf_ctl_scaling); @@ -2275,6 +2275,9 @@ static int knl_get_turbo_pstate(int cpu) static int hwp_get_cpu_scaling(int cpu) { if (hybrid_scaling_factor) { + if (!cpu_feature_enabled(X86_FEATURE_HYBRID_CPU)) + return hybrid_scaling_factor; + /* * Return the hybrid scaling factor for P-cores and use the * default core scaling for E-cores. -- 2.43.0 ^ permalink raw reply related [flat|nested] 4+ messages in thread
* Re: [PATCH v2 1/2] cpufreq: intel_pstate: Fix scaling for hybrid-capable CPUs not reporting hybrid 2026-05-08 6:30 ` [PATCH v2 1/2] cpufreq: intel_pstate: Fix scaling for hybrid-capable CPUs not reporting hybrid Henry Tseng @ 2026-05-10 14:34 ` srinivas pandruvada 0 siblings, 0 replies; 4+ messages in thread From: srinivas pandruvada @ 2026-05-10 14:34 UTC (permalink / raw) To: Henry Tseng, Rafael J. Wysocki, Len Brown, Viresh Kumar Cc: linux-pm, SW Chen, Kevin Ko On Fri, 2026-05-08 at 14:30 +0800, Henry Tseng wrote: > Commit 9b18d536b124 ("cpufreq: intel_pstate: Use CPPC to get scaling > factors") restructured hwp_get_cpu_scaling() so that, when the CPU > model is registered in intel_hybrid_scaling_factor[] and > hybrid_get_cpu_type() does not return INTEL_CPU_TYPE_CORE, the > function early-returns core_get_scaling() (100000) instead of > falling through to intel_pstate_cppc_get_scaling(). > > This regresses the behavior previously addressed by > commit 0fcfc9e51990 ("cpufreq: intel_pstate: Fix scaling for > hybrid-capable systems with disabled E-cores"). On hybrid-capable > processors not reporting X86_FEATURE_HYBRID_CPU (no E-cores > enumerated), hybrid_get_cpu_type() returns 0. Before 9b18d536b124, > such CPUs fell through to intel_pstate_cppc_get_scaling(), which > returned the registered hybrid_scaling_factor. After 9b18d536b124, > for models registered in the table the early return takes > core_get_scaling() before reaching that fallback, so the registered > factor is not used. > > Fix this by returning hybrid_scaling_factor directly for CPU models > registered in intel_hybrid_scaling_factor[] that do not report > X86_FEATURE_HYBRID_CPU, before checking hybrid_get_cpu_type(). > > With that fix, non-hybrid CPUs in the table now reach > intel_pstate_hybrid_hwp_adjust() with scaling != perf_ctl_scaling. > Since commit 5313ec4a215a ("cpufreq: intel_pstate: Improve printing > of > debug messages") sets hwp_is_hybrid = true unconditionally inside > that > function, set hwp_is_hybrid based on X86_FEATURE_HYBRID_CPU instead, > so the flag is not set on non-hybrid systems. > > Fixes: 9b18d536b124 ("cpufreq: intel_pstate: Use CPPC to get scaling > factors") > Signed-off-by: Henry Tseng <henrytseng@qnap.com> > --- > drivers/cpufreq/intel_pstate.c | 5 ++++- > 1 file changed, 4 insertions(+), 1 deletion(-) > > diff --git a/drivers/cpufreq/intel_pstate.c > b/drivers/cpufreq/intel_pstate.c > index 1292da53e5fc..d39592e86570 100644 > --- a/drivers/cpufreq/intel_pstate.c > +++ b/drivers/cpufreq/intel_pstate.c > @@ -585,7 +585,7 @@ static void intel_pstate_hybrid_hwp_adjust(struct > cpudata *cpu) > if (scaling == perf_ctl_scaling) > return; > > - hwp_is_hybrid = true; > + hwp_is_hybrid = cpu_feature_enabled(X86_FEATURE_HYBRID_CPU); > > cpu->pstate.turbo_freq = rounddown(cpu->pstate.turbo_pstate > * scaling, > perf_ctl_scaling); > @@ -2275,6 +2275,9 @@ static int knl_get_turbo_pstate(int cpu) > static int hwp_get_cpu_scaling(int cpu) > { > if (hybrid_scaling_factor) { > + if (!cpu_feature_enabled(X86_FEATURE_HYBRID_CPU)) > + return hybrid_scaling_factor; It breaks Alder Lake systems with only E-cores and no P-cores. So need to think about this. So this change didn't restore the behavior of 0fcfc9e51990. So need to think about this. Thanks, Srinivas > + > /* > * Return the hybrid scaling factor for P-cores and > use the > * default core scaling for E-cores. ^ permalink raw reply [flat|nested] 4+ messages in thread
* [PATCH v2 2/2] cpufreq: intel_pstate: Use HYBRID_SCALING_FACTOR_ADL for Bartlett Lake 2026-05-08 6:30 [PATCH v2 0/2] cpufreq: intel_pstate: Add scaling factor for Bartlett Lake P-core only SKUs Henry Tseng 2026-05-08 6:30 ` [PATCH v2 1/2] cpufreq: intel_pstate: Fix scaling for hybrid-capable CPUs not reporting hybrid Henry Tseng @ 2026-05-08 6:30 ` Henry Tseng 1 sibling, 0 replies; 4+ messages in thread From: Henry Tseng @ 2026-05-08 6:30 UTC (permalink / raw) To: Srinivas Pandruvada, Rafael J. Wysocki, Len Brown, Viresh Kumar Cc: linux-pm, SW Chen, Kevin Ko, Henry Tseng Bartlett Lake shares the same HWP-to-PERF_CTL scaling factor as Alder Lake / Raptor Lake P-cores. Add Bartlett Lake to intel_hybrid_scaling_factor[] with HYBRID_SCALING_FACTOR_ADL so HWP performance levels map to the correct CPU frequencies. Per the Intel datasheet [1], the Intel Core 9 273PE specifies: Performance-cores: 12 Efficient-cores: 0 Max Turbo Frequency: 5.7 GHz Intel Thermal Velocity Boost Frequency: 5.7 GHz Intel Turbo Boost Max Technology 3.0 Frequency: 5.6 GHz Performance-core Max Turbo Frequency: 5.4 GHz Performance-core Base Frequency: 2.3 GHz Because this CPU has no E-cores and does not report X86_FEATURE_HYBRID_CPU, hwp_get_cpu_scaling() returns 100000 (the default core scaling). In intel_pstate_get_cpu_pstates(), the condition cpu->pstate.scaling == perf_ctl_scaling then takes the early path that simply multiplies HWP performance levels by 100000, producing cpuinfo_max_freq values that exceed the documented Max Turbo Frequency: intel_pstate: CPU0: PERF_CTL turbo = 57 intel_pstate: CPU0: HWP_CAP guaranteed = 30 intel_pstate: CPU0: HWP_CAP highest = 70 intel_pstate: CPU0: HWP-to-frequency scaling factor: 100000 intel_pstate: set_policy cpuinfo.max 7000000 policy->max 7000000 ... intel_pstate: CPU12: HWP_CAP highest = 73 intel_pstate: CPU12: HWP-to-frequency scaling factor: 100000 intel_pstate: set_policy cpuinfo.max 7300000 policy->max 7300000 With this patch, the registered HYBRID_SCALING_FACTOR_ADL (78741) is used: intel_pstate: hybrid scaling factor: 78741 intel_pstate: CPU0: PERF_CTL turbo = 57 intel_pstate: CPU0: HWP_CAP guaranteed = 30 intel_pstate: CPU0: HWP_CAP highest = 70 intel_pstate: CPU0: HWP-to-frequency scaling factor: 78741 intel_pstate: set_policy cpuinfo.max 5500000 policy->max 5500000 ... intel_pstate: CPU12: HWP_CAP highest = 73 intel_pstate: CPU12: HWP-to-frequency scaling factor: 78741 intel_pstate: set_policy cpuinfo.max 5700000 policy->max 5700000 The reported cpuinfo_max_freq (5.5/5.7 GHz) now matches the datasheet's Max Turbo Frequency. [1] https://www.intel.com/content/www/us/en/products/sku/245717/intel-core-9-processor-273pe-36m-cache-up-to-5-70-ghz/specifications.html Signed-off-by: Henry Tseng <henrytseng@qnap.com> --- drivers/cpufreq/intel_pstate.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c index d39592e86570..82e82a70cacb 100644 --- a/drivers/cpufreq/intel_pstate.c +++ b/drivers/cpufreq/intel_pstate.c @@ -3737,6 +3737,7 @@ static const struct x86_cpu_id intel_hybrid_scaling_factor[] = { X86_MATCH_VFM(INTEL_RAPTORLAKE, HYBRID_SCALING_FACTOR_ADL), X86_MATCH_VFM(INTEL_RAPTORLAKE_P, HYBRID_SCALING_FACTOR_ADL), X86_MATCH_VFM(INTEL_RAPTORLAKE_S, HYBRID_SCALING_FACTOR_ADL), + X86_MATCH_VFM(INTEL_BARTLETTLAKE, HYBRID_SCALING_FACTOR_ADL), X86_MATCH_VFM(INTEL_METEORLAKE_L, HYBRID_SCALING_FACTOR_MTL), X86_MATCH_VFM(INTEL_LUNARLAKE_M, HYBRID_SCALING_FACTOR_LNL), {} -- 2.43.0 ^ permalink raw reply related [flat|nested] 4+ messages in thread
end of thread, other threads:[~2026-05-10 14:34 UTC | newest] Thread overview: 4+ messages (download: mbox.gz follow: Atom feed -- links below jump to the message on this page -- 2026-05-08 6:30 [PATCH v2 0/2] cpufreq: intel_pstate: Add scaling factor for Bartlett Lake P-core only SKUs Henry Tseng 2026-05-08 6:30 ` [PATCH v2 1/2] cpufreq: intel_pstate: Fix scaling for hybrid-capable CPUs not reporting hybrid Henry Tseng 2026-05-10 14:34 ` srinivas pandruvada 2026-05-08 6:30 ` [PATCH v2 2/2] cpufreq: intel_pstate: Use HYBRID_SCALING_FACTOR_ADL for Bartlett Lake Henry Tseng
This is a public inbox, see mirroring instructions for how to clone and mirror all data and code used for this inbox