diff options
| author | Len Brown <len.brown@intel.com> | 2017-05-02 05:06:08 +0200 |
|---|---|---|
| committer | Len Brown <len.brown@intel.com> | 2017-05-12 03:27:53 +0200 |
| commit | 3cedbc5a6d7f7c5539e139f89ec9f6e1ed668418 (patch) | |
| tree | a00534027c4ac7a238791527a0a9ccc810ab87e9 | |
| parent | tools/power x86_energy_perf_policy: support HWP.EPP (diff) | |
| download | linux-3cedbc5a6d7f7c5539e139f89ec9f6e1ed668418.tar.xz linux-3cedbc5a6d7f7c5539e139f89ec9f6e1ed668418.zip | |
intel_pstate: use updated msr-index.h HWP.EPP values
intel_pstate exports sysfs attributes for setting and observing HWP.EPP.
These attributes use strings to describe 4 operating states, and
inside the driver, these strings are mapped to numerical register
values.
The authorative mapping between the strings and numerical HWP.EPP values
are now globally defined in msr-index.h, replacing the out-dated
mapping that were open-coded into intel_pstate.c
new old string
--- --- ------
0 0 performance
128 64 balance_performance
192 128 balance_power
255 192 power
Note that the HW and BIOS default value on most system is 128,
which intel_pstate will now call "balance_performance"
while it used to call it "balance_power".
Signed-off-by: Len Brown <len.brown@intel.com>
| -rw-r--r-- | drivers/cpufreq/intel_pstate.c | 34 |
1 files changed, 15 insertions, 19 deletions
diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c index 50bd6d987fc3..ab8ebaeb3621 100644 --- a/drivers/cpufreq/intel_pstate.c +++ b/drivers/cpufreq/intel_pstate.c @@ -716,6 +716,12 @@ static const char * const energy_perf_strings[] = { "power", NULL }; +static const unsigned int epp_values[] = { + HWP_EPP_PERFORMANCE, + HWP_EPP_BALANCE_PERFORMANCE, + HWP_EPP_BALANCE_POWERSAVE, + HWP_EPP_POWERSAVE +}; static int intel_pstate_get_energy_pref_index(struct cpudata *cpu_data) { @@ -727,17 +733,14 @@ static int intel_pstate_get_energy_pref_index(struct cpudata *cpu_data) return epp; if (static_cpu_has(X86_FEATURE_HWP_EPP)) { - /* - * Range: - * 0x00-0x3F : Performance - * 0x40-0x7F : Balance performance - * 0x80-0xBF : Balance power - * 0xC0-0xFF : Power - * The EPP is a 8 bit value, but our ranges restrict the - * value which can be set. Here only using top two bits - * effectively. - */ - index = (epp >> 6) + 1; + if (epp == HWP_EPP_PERFORMANCE) + return 1; + if (epp <= HWP_EPP_BALANCE_PERFORMANCE) + return 2; + if (epp <= HWP_EPP_BALANCE_POWERSAVE) + return 3; + else + return 4; } else if (static_cpu_has(X86_FEATURE_EPB)) { /* * Range: @@ -775,15 +778,8 @@ static int intel_pstate_set_energy_pref_index(struct cpudata *cpu_data, value &= ~GENMASK_ULL(31, 24); - /* - * If epp is not default, convert from index into - * energy_perf_strings to epp value, by shifting 6 - * bits left to use only top two bits in epp. - * The resultant epp need to shifted by 24 bits to - * epp position in MSR_HWP_REQUEST. - */ if (epp == -EINVAL) - epp = (pref_index - 1) << 6; + epp = epp_values[pref_index - 1]; value |= (u64)epp << 24; ret = wrmsrl_on_cpu(cpu_data->cpu, MSR_HWP_REQUEST, value); |