On a per processor family basis, Intel decides if they want to override the default ACPI idle state structure used by linux kernels. This is done in the kernel source tree under drivers/idle/intel_idle.c
. An example override for my Comet Lake processor:
doug@s19:~/temp-k-git/linux$ git diff
diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c
index 3273360f30f7..770660d777c4 100644
--- a/drivers/idle/intel_idle.c
+++ b/drivers/idle/intel_idle.c
@@ -1155,6 +1155,7 @@ static const struct x86_cpu_id intel_idle_ids[] __initconst = {
X86_MATCH_INTEL_FAM6_MODEL(KABYLAKE_L, &idle_cpu_skl),
X86_MATCH_INTEL_FAM6_MODEL(KABYLAKE, &idle_cpu_skl),
X86_MATCH_INTEL_FAM6_MODEL(SKYLAKE_X, &idle_cpu_skx),
+ X86_MATCH_INTEL_FAM6_MODEL(COMETLAKE, &idle_cpu_skl),
X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_X, &idle_cpu_icx),
X86_MATCH_INTEL_FAM6_MODEL(XEON_PHI_KNL, &idle_cpu_knl),
X86_MATCH_INTEL_FAM6_MODEL(XEON_PHI_KNM, &idle_cpu_knl),
By default the idle states are:
$ grep . /sys/devices/system/cpu/cpu0/cpuidle/state*/name
/sys/devices/system/cpu/cpu0/cpuidle/state0/name:POLL
/sys/devices/system/cpu/cpu0/cpuidle/state1/name:C1_ACPI
/sys/devices/system/cpu/cpu0/cpuidle/state2/name:C2_ACPI
/sys/devices/system/cpu/cpu0/cpuidle/state3/name:C3_ACPI
$ grep . /sys/devices/system/cpu/cpu0/cpuidle/state*/desc
/sys/devices/system/cpu/cpu0/cpuidle/state0/desc:CPUIDLE CORE POLL IDLE
/sys/devices/system/cpu/cpu0/cpuidle/state1/desc:ACPI FFH MWAIT 0x0
/sys/devices/system/cpu/cpu0/cpuidle/state2/desc:ACPI FFH MWAIT 0x30
/sys/devices/system/cpu/cpu0/cpuidle/state3/desc:ACPI FFH MWAIT 0x60
Via the above override the idle states are:
$ grep . /sys/devices/system/cpu/cpu0/cpuidle/state*/name
/sys/devices/system/cpu/cpu0/cpuidle/state0/name:POLL
/sys/devices/system/cpu/cpu0/cpuidle/state1/name:C1
/sys/devices/system/cpu/cpu0/cpuidle/state2/name:C1E
/sys/devices/system/cpu/cpu0/cpuidle/state3/name:C3
/sys/devices/system/cpu/cpu0/cpuidle/state4/name:C6
/sys/devices/system/cpu/cpu0/cpuidle/state5/name:C7s
/sys/devices/system/cpu/cpu0/cpuidle/state6/name:C8
/sys/devices/system/cpu/cpu0/cpuidle/state7/name:C9
/sys/devices/system/cpu/cpu0/cpuidle/state8/name:C10
$ grep . /sys/devices/system/cpu/cpu0/cpuidle/state*/desc
/sys/devices/system/cpu/cpu0/cpuidle/state0/desc:CPUIDLE CORE POLL IDLE
/sys/devices/system/cpu/cpu0/cpuidle/state1/desc:MWAIT 0x00
/sys/devices/system/cpu/cpu0/cpuidle/state2/desc:MWAIT 0x01
/sys/devices/system/cpu/cpu0/cpuidle/state3/desc:MWAIT 0x10
/sys/devices/system/cpu/cpu0/cpuidle/state4/desc:MWAIT 0x20
/sys/devices/system/cpu/cpu0/cpuidle/state5/desc:MWAIT 0x33
/sys/devices/system/cpu/cpu0/cpuidle/state6/desc:MWAIT 0x40
/sys/devices/system/cpu/cpu0/cpuidle/state7/desc:MWAIT 0x50
/sys/devices/system/cpu/cpu0/cpuidle/state8/desc:MWAIT 0x60
This statement:
I noticed that available C States has decreased which probably means
that there is more room for power saving.
Is incorrect, there isn't room for power saving just in currently available states. Observe the deepest state is the same. You might achieve some power savings via selection of the idle governor as a function of your particular workflow requirements:
$ grep . /sys/devices/system/cpu/cpuidle/*
/sys/devices/system/cpu/cpuidle/available_governors:ladder menu teo
/sys/devices/system/cpu/cpuidle/current_driver:intel_idle
/sys/devices/system/cpu/cpuidle/current_governor:teo
/sys/devices/system/cpu/cpuidle/current_governor_ro:teo
/sys/devices/system/cpu/cpuidle/low_power_idle_cpu_residency_us:0
/sys/devices/system/cpu/cpuidle/low_power_idle_system_residency_us:0
grep . /sys/devices/system/cpu/cpu0/cpuidle/state*/name
? This will list the available C-States for your CPU as per the installed kernel and the limitations imposed by the UEFI configuration. With this info, it may be possible to offer a solution.