Skip to content

L
linux
Commit 23a299cd authored by Len Brown's avatar Len Brown
Browse files
Options

Merge branches 'turbostat' and 'intel_idle' into release

parents 455c6fdb 4e8e863f 0138d8f0
Expand all Hide whitespace changes
Inline Side-by-side
Showing with 362 additions and 213 deletions
arch/x86/kernel/acpi/cstate.c
View file @ 23a299cd
......@@ -87,7 +87,9 @@ static long acpi_processor_ffh_cstate_probe_cpu(void *_cx)
num_cstate_subtype = edx_part & MWAIT_SUBSTATE_MASK;
retval = 0;
if (num_cstate_subtype < (cx->address & MWAIT_SUBSTATE_MASK)) {
/* If the HW does not support any sub-states in this C-state */
if (num_cstate_subtype == 0) {
pr_warn(FW_BUG "ACPI MWAIT C-state 0x%x not supported by HW (0x%x)\n", cx->address, edx_part);
retval = -1;
goto out;
}
......
drivers/idle/intel_idle.c
View file @ 23a299cd
......@@ -196,6 +196,53 @@ static struct cpuidle_state snb_cstates[] = {
.enter = NULL }
};
static struct cpuidle_state byt_cstates[] = {
{
.name = "C1-BYT",
.desc = "MWAIT 0x00",
.flags = MWAIT2flg(0x00) | CPUIDLE_FLAG_TIME_VALID,
.exit_latency = 1,
.target_residency = 1,
.enter = &intel_idle },
{
.name = "C1E-BYT",
.desc = "MWAIT 0x01",
.flags = MWAIT2flg(0x01) | CPUIDLE_FLAG_TIME_VALID,
.exit_latency = 15,
.target_residency = 30,
.enter = &intel_idle },
{
.name = "C6N-BYT",
.desc = "MWAIT 0x58",
.flags = MWAIT2flg(0x58) | CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_TLB_FLUSHED,
.exit_latency = 40,
.target_residency = 275,
.enter = &intel_idle },
{
.name = "C6S-BYT",
.desc = "MWAIT 0x52",
.flags = MWAIT2flg(0x52) | CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_TLB_FLUSHED,
.exit_latency = 140,
.target_residency = 560,
.enter = &intel_idle },
{
.name = "C7-BYT",
.desc = "MWAIT 0x60",
.flags = MWAIT2flg(0x60) | CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_TLB_FLUSHED,
.exit_latency = 1200,
.target_residency = 1500,
.enter = &intel_idle },
{
.name = "C7S-BYT",
.desc = "MWAIT 0x64",
.flags = MWAIT2flg(0x64) | CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_TLB_FLUSHED,
.exit_latency = 10000,
.target_residency = 20000,
.enter = &intel_idle },
{
.enter = NULL }
};
static struct cpuidle_state ivb_cstates[] = {
{
.name = "C1-IVB",
......@@ -236,6 +283,105 @@ static struct cpuidle_state ivb_cstates[] = {
.enter = NULL }
};
static struct cpuidle_state ivt_cstates[] = {
{
.name = "C1-IVT",
.desc = "MWAIT 0x00",
.flags = MWAIT2flg(0x00) | CPUIDLE_FLAG_TIME_VALID,
.exit_latency = 1,
.target_residency = 1,
.enter = &intel_idle },
{
.name = "C1E-IVT",
.desc = "MWAIT 0x01",
.flags = MWAIT2flg(0x01) | CPUIDLE_FLAG_TIME_VALID,
.exit_latency = 10,
.target_residency = 80,
.enter = &intel_idle },
{
.name = "C3-IVT",
.desc = "MWAIT 0x10",
.flags = MWAIT2flg(0x10) | CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_TLB_FLUSHED,
.exit_latency = 59,
.target_residency = 156,
.enter = &intel_idle },
{
.name = "C6-IVT",
.desc = "MWAIT 0x20",
.flags = MWAIT2flg(0x20) | CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_TLB_FLUSHED,
.exit_latency = 82,
.target_residency = 300,
.enter = &intel_idle },
{
.enter = NULL }
};
static struct cpuidle_state ivt_cstates_4s[] = {
{
.name = "C1-IVT-4S",
.desc = "MWAIT 0x00",
.flags = MWAIT2flg(0x00) | CPUIDLE_FLAG_TIME_VALID,
.exit_latency = 1,
.target_residency = 1,
.enter = &intel_idle },
{
.name = "C1E-IVT-4S",
.desc = "MWAIT 0x01",
.flags = MWAIT2flg(0x01) | CPUIDLE_FLAG_TIME_VALID,
.exit_latency = 10,
.target_residency = 250,
.enter = &intel_idle },
{
.name = "C3-IVT-4S",
.desc = "MWAIT 0x10",
.flags = MWAIT2flg(0x10) | CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_TLB_FLUSHED,
.exit_latency = 59,
.target_residency = 300,
.enter = &intel_idle },
{
.name = "C6-IVT-4S",
.desc = "MWAIT 0x20",
.flags = MWAIT2flg(0x20) | CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_TLB_FLUSHED,
.exit_latency = 84,
.target_residency = 400,
.enter = &intel_idle },
{
.enter = NULL }
};
static struct cpuidle_state ivt_cstates_8s[] = {
{
.name = "C1-IVT-8S",
.desc = "MWAIT 0x00",
.flags = MWAIT2flg(0x00) | CPUIDLE_FLAG_TIME_VALID,
.exit_latency = 1,
.target_residency = 1,
.enter = &intel_idle },
{
.name = "C1E-IVT-8S",
.desc = "MWAIT 0x01",
.flags = MWAIT2flg(0x01) | CPUIDLE_FLAG_TIME_VALID,
.exit_latency = 10,
.target_residency = 500,
.enter = &intel_idle },
{
.name = "C3-IVT-8S",
.desc = "MWAIT 0x10",
.flags = MWAIT2flg(0x10) | CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_TLB_FLUSHED,
.exit_latency = 59,
.target_residency = 600,
.enter = &intel_idle },
{
.name = "C6-IVT-8S",
.desc = "MWAIT 0x20",
.flags = MWAIT2flg(0x20) | CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_TLB_FLUSHED,
.exit_latency = 88,
.target_residency = 700,
.enter = &intel_idle },
{
.enter = NULL }
};
static struct cpuidle_state hsw_cstates[] = {
{
.name = "C1-HSW",
......@@ -464,11 +610,21 @@ static const struct idle_cpu idle_cpu_snb = {
.disable_promotion_to_c1e = true,
};
static const struct idle_cpu idle_cpu_byt = {
.state_table = byt_cstates,
.disable_promotion_to_c1e = true,
};
static const struct idle_cpu idle_cpu_ivb = {
.state_table = ivb_cstates,
.disable_promotion_to_c1e = true,
};
static const struct idle_cpu idle_cpu_ivt = {
.state_table = ivt_cstates,
.disable_promotion_to_c1e = true,
};
static const struct idle_cpu idle_cpu_hsw = {
.state_table = hsw_cstates,
.disable_promotion_to_c1e = true,
......@@ -494,8 +650,10 @@ static const struct x86_cpu_id intel_idle_ids[] = {
ICPU(0x2f, idle_cpu_nehalem),
ICPU(0x2a, idle_cpu_snb),
ICPU(0x2d, idle_cpu_snb),
ICPU(0x36, idle_cpu_atom),
ICPU(0x37, idle_cpu_byt),
ICPU(0x3a, idle_cpu_ivb),
ICPU(0x3e, idle_cpu_ivb),
ICPU(0x3e, idle_cpu_ivt),
ICPU(0x3c, idle_cpu_hsw),
ICPU(0x3f, idle_cpu_hsw),
ICPU(0x45, idle_cpu_hsw),
......@@ -572,6 +730,39 @@ static void intel_idle_cpuidle_devices_uninit(void)
free_percpu(intel_idle_cpuidle_devices);
return;
}
/*
* intel_idle_state_table_update()
*
* Update the default state_table for this CPU-id
*
* Currently used to access tuned IVT multi-socket targets
* Assumption: num_sockets == (max_package_num + 1)
*/
void intel_idle_state_table_update(void)
{
/* IVT uses a different table for 1-2, 3-4, and > 4 sockets */
if (boot_cpu_data.x86_model == 0x3e) { /* IVT */
int cpu, package_num, num_sockets = 1;
for_each_online_cpu(cpu) {
package_num = topology_physical_package_id(cpu);
if (package_num + 1 > num_sockets) {
num_sockets = package_num + 1;
if (num_sockets > 4)
cpuidle_state_table = ivt_cstates_8s;
return;
}
}
if (num_sockets > 2)
cpuidle_state_table = ivt_cstates_4s;
/* else, 1 and 2 socket systems use default ivt_cstates */
}
return;
}
/*
* intel_idle_cpuidle_driver_init()
* allocate, initialize cpuidle_states
......@@ -581,10 +772,12 @@ static int __init intel_idle_cpuidle_driver_init(void)
int cstate;
struct cpuidle_driver *drv = &intel_idle_driver;
intel_idle_state_table_update();
drv->state_count = 1;
for (cstate = 0; cstate < CPUIDLE_STATE_MAX; ++cstate) {
int num_substates, mwait_hint, mwait_cstate, mwait_substate;
int num_substates, mwait_hint, mwait_cstate;
if (cpuidle_state_table[cstate].enter == NULL)
break;
......@@ -597,14 +790,13 @@ static int __init intel_idle_cpuidle_driver_init(void)
mwait_hint = flg2MWAIT(cpuidle_state_table[cstate].flags);
mwait_cstate = MWAIT_HINT2CSTATE(mwait_hint);
mwait_substate = MWAIT_HINT2SUBSTATE(mwait_hint);
/* does the state exist in CPUID.MWAIT? */
/* number of sub-states for this state in CPUID.MWAIT */
num_substates = (mwait_substates >> ((mwait_cstate + 1) * 4))
& MWAIT_SUBSTATE_MASK;
/* if sub-state in table is not enumerated by CPUID */
if ((mwait_substate + 1) > num_substates)
/* if NO sub-states for this state in CPUID, skip it */
if (num_substates == 0)
continue;
if (((mwait_cstate + 1) > 2) &&
......
tools/power/x86/turbostat/turbostat.8
View file @ 23a299cd
......@@ -47,21 +47,22 @@ displays the statistics gathered since it was forked.
.PP
.SH FIELD DESCRIPTIONS
.nf
\fBpk\fP processor package number.
\fBcor\fP processor core number.
\fBPackage\fP processor package number.
\fBCore\fP processor core number.
\fBCPU\fP Linux CPU (logical processor) number.
Note that multiple CPUs per core indicate support for Intel(R) Hyper-Threading Technology.
\fB%c0\fP percent of the interval that the CPU retired instructions.
\fBGHz\fP average clock rate while the CPU was in c0 state.
\fBTSC\fP average GHz that the TSC ran during the entire interval.
\fB%c1, %c3, %c6, %c7\fP show the percentage residency in hardware core idle states.
\fBCTMP\fP Degrees Celsius reported by the per-core Digital Thermal Sensor.
\fBPTMP\fP Degrees Celsius reported by the per-package Package Thermal Monitor.
\fB%pc2, %pc3, %pc6, %pc7\fP percentage residency in hardware package idle states.
\fBPkg_W\fP Watts consumed by the whole package.
\fBCor_W\fP Watts consumed by the core part of the package.
\fBGFX_W\fP Watts consumed by the Graphics part of the package -- available only on client processors.
\fBRAM_W\fP Watts consumed by the DRAM DIMMS -- available only on server processors.
\fBAVG_MHz\fP number of cycles executed divided by time elapsed.
\fB%Buzy\fP percent of the interval that the CPU retired instructions, aka. % of time in "C0" state.
\fBBzy_MHz\fP average clock rate while the CPU was busy (in "c0" state).
\fBTSC_MHz\fP average MHz that the TSC ran during the entire interval.
\fBCPU%c1, CPU%c3, CPU%c6, CPU%c7\fP show the percentage residency in hardware core idle states.
\fBCoreTmp\fP Degrees Celsius reported by the per-core Digital Thermal Sensor.
\fBPkgTtmp\fP Degrees Celsius reported by the per-package Package Thermal Monitor.
\fBPkg%pc2, Pkg%pc3, Pkg%pc6, Pkg%pc7\fP percentage residency in hardware package idle states.
\fBPkgWatt\fP Watts consumed by the whole package.
\fBCorWatt\fP Watts consumed by the core part of the package.
\fBGFXWatt\fP Watts consumed by the Graphics part of the package -- available only on client processors.
\fBRAMWatt\fP Watts consumed by the DRAM DIMMS -- available only on server processors.
\fBPKG_%\fP percent of the interval that RAPL throttling was active on the Package.
\fBRAM_%\fP percent of the interval that RAPL throttling was active on DRAM.
.fi
......@@ -78,29 +79,17 @@ For Watts columns, the summary is a system total.
Subsequent rows show per-CPU statistics.
.nf
[root@sandy]# ./turbostat
cor CPU %c0 GHz TSC %c1 %c3 %c6 %c7 CTMP PTMP %pc2 %pc3 %pc6 %pc7 Pkg_W Cor_W GFX_W
0.06 0.80 2.29 0.11 0.00 0.00 99.83 47 40 0.26 0.01 0.44 98.78 3.49 0.12 0.14
0 0 0.07 0.80 2.29 0.07 0.00 0.00 99.86 40 40 0.26 0.01 0.44 98.78 3.49 0.12 0.14
0 4 0.03 0.80 2.29 0.12
1 1 0.04 0.80 2.29 0.25 0.01 0.00 99.71 40
1 5 0.16 0.80 2.29 0.13
2 2 0.05 0.80 2.29 0.06 0.01 0.00 99.88 40
2 6 0.03 0.80 2.29 0.08
3 3 0.05 0.80 2.29 0.08 0.00 0.00 99.87 47
3 7 0.04 0.84 2.29 0.09
.fi
.SH SUMMARY EXAMPLE
The "-s" option prints the column headers just once,
and then the one line system summary for each sample interval.
.nf
[root@wsm]# turbostat -S
%c0 GHz TSC %c1 %c3 %c6 CTMP %pc3 %pc6
1.40 2.81 3.38 10.78 43.47 44.35 42 13.67 2.09
1.34 2.90 3.38 11.48 58.96 28.23 41 19.89 0.15
1.55 2.72 3.38 26.73 37.66 34.07 42 2.53 2.80
1.37 2.83 3.38 16.95 60.05 21.63 42 5.76 0.20
[root@ivy]# ./turbostat
Core CPU Avg_MHz %Busy Bzy_MHz TSC_MHz SMI CPU%c1 CPU%c3 CPU%c6 CPU%c7 CoreTmp PkgTmp Pkg%pc2 Pkg%pc3 Pkg%pc6 Pkg%pc7 PkgWatt CorWatt GFXWatt
- - 6 0.36 1596 3492 0 0.59 0.01 99.04 0.00 23 24 23.82 0.01 72.47 0.00 6.40 1.01 0.00
0 0 9 0.58 1596 3492 0 0.28 0.01 99.13 0.00 23 24 23.82 0.01 72.47 0.00 6.40 1.01 0.00
0 4 1 0.07 1596 3492 0 0.79
1 1 10 0.65 1596 3492 0 0.59 0.00 98.76 0.00 23
1 5 5 0.28 1596 3492 0 0.95
2 2 10 0.66 1596 3492 0 0.41 0.01 98.92 0.00 23
2 6 2 0.10 1597 3492 0 0.97
3 3 3 0.20 1596 3492 0 0.44 0.00 99.37 0.00 23
3 7 5 0.31 1596 3492 0 0.33
.fi
.SH VERBOSE EXAMPLE
The "-v" option adds verbosity to the output:
......@@ -154,55 +143,35 @@ eg. Here a cycle soaker is run on 1 CPU (see %c0) for a few seconds
until ^C while the other CPUs are mostly idle:
.nf
[root@x980 lenb]# ./turbostat cat /dev/zero > /dev/null
root@ivy: turbostat cat /dev/zero > /dev/null
^C
cor CPU %c0 GHz TSC %c1 %c3 %c6 %pc3 %pc6
8.86 3.61 3.38 15.06 31.19 44.89 0.00 0.00
0 0 1.46 3.22 3.38 16.84 29.48 52.22 0.00 0.00
0 6 0.21 3.06 3.38 18.09
1 2 0.53 3.33 3.38 2.80 46.40 50.27
1 8 0.89 3.47 3.38 2.44
2 4 1.36 3.43 3.38 9.04 23.71 65.89
2 10 0.18 2.86 3.38 10.22
8 1 0.04 2.87 3.38 99.96 0.01 0.00
8 7 99.72 3.63 3.38 0.27
9 3 0.31 3.21 3.38 7.64 56.55 35.50
9 9 0.08 2.95 3.38 7.88
10 5 1.42 3.43 3.38 2.14 30.99 65.44
10 11 0.16 2.88 3.38 3.40
Core CPU Avg_MHz %Busy Bzy_MHz TSC_MHz SMI CPU%c1 CPU%c3 CPU%c6 CPU%c7 CoreTmp PkgTmp Pkg%pc2 Pkg%pc3 Pkg%pc6 Pkg%pc7 PkgWatt CorWatt GFXWatt
- - 496 12.75 3886 3492 0 13.16 0.04 74.04 0.00 36 36 0.00 0.00 0.00 0.00 23.15 17.65 0.00
0 0 22 0.57 3830 3492 0 0.83 0.02 98.59 0.00 27 36 0.00 0.00 0.00 0.00 23.15 17.65 0.00
0 4 9 0.24 3829 3492 0 1.15
1 1 4 0.09 3783 3492 0 99.91 0.00 0.00 0.00 36
1 5 3880 99.82 3888 3492 0 0.18
2 2 17 0.44 3813 3492 0 0.77 0.04 98.75 0.00 28
2 6 12 0.32 3823 3492 0 0.89
3 3 16 0.43 3844 3492 0 0.63 0.11 98.84 0.00 30
3 7 4 0.11 3827 3492 0 0.94
30.372243 sec
.fi
Above the cycle soaker drives cpu7 up its 3.6 GHz turbo limit
Above the cycle soaker drives cpu5 up its 3.8 GHz turbo limit
while the other processors are generally in various states of idle.
Note that cpu1 and cpu7 are HT siblings within core8.
As cpu7 is very busy, it prevents its sibling, cpu1,
Note that cpu1 and cpu5 are HT siblings within core1.
As cpu5 is very busy, it prevents its sibling, cpu1,
from entering a c-state deeper than c1.
Note that turbostat reports average GHz of 3.63, while
the arithmetic average of the GHz column above is lower.
This is a weighted average, where the weight is %c0. ie. it is the total number of
un-halted cycles elapsed per time divided by the number of CPUs.
.SH SMI COUNTING EXAMPLE
On Intel Nehalem and newer processors, MSR 0x34 is a System Management Mode Interrupt (SMI) counter.
This counter is shown by default under the "SMI" column.
.nf
[root@x980 ~]# turbostat
cor CPU %c0 GHz TSC SMI %c1 %c3 %c6 CTMP %pc3 %pc6
0.11 1.91 3.38 0 1.84 0.26 97.79 29 0.82 83.87
0 0 0.40 1.63 3.38 0 10.27 0.12 89.20 20 0.82 83.88
0 6 0.06 1.63 3.38 0 10.61
1 2 0.37 2.63 3.38 0 0.02 0.10 99.51 22
1 8 0.01 1.62 3.38 0 0.39
2 4 0.07 1.62 3.38 0 0.04 0.07 99.82 23
2 10 0.02 1.62 3.38 0 0.09
8 1 0.23 1.64 3.38 0 0.10 1.07 98.60 24
8 7 0.02 1.64 3.38 0 0.31
9 3 0.03 1.62 3.38 0 0.03 0.05 99.89 29
9 9 0.02 1.62 3.38 0 0.05
10 5 0.07 1.62 3.38 0 0.08 0.12 99.73 27
10 11 0.03 1.62 3.38 0 0.13
^C
.fi
Note that the Avg_MHz column reflects the total number of cycles executed
divided by the measurement interval. If the %Busy column is 100%,
then the processor was running at that speed the entire interval.
The Avg_MHz multiplied by the %Busy results in the Bzy_MHz --
which is the average frequency while the processor was executing --
not including any non-busy idle time.
.SH NOTES
.B "turbostat "
......
tools/power/x86/turbostat/turbostat.c
View file @ 23a299cd
This diff is collapsed.
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment
GitLab Nexedi Edition | About GitLab | About Nexedi | 沪ICP备2021021310号-2 | 沪ICP备2021021310号-7