Skip site navigation (1)Skip section navigation (2)
Date:      Sat, 6 Apr 2019 11:21:18 -0700
From:      Mark Millard <marklmi@yahoo.com>
To:        Konstantin Belousov <kostikbel@gmail.com>
Cc:        freebsd-amd64@freebsd.org
Subject:   Re: head -r345758 Ryzen Threadripper 1950X vs. amdtemp.ko : dev.cpu.31 missing
Message-ID:  <18972821-7476-4B31-ADB2-2DA38BB5C955@yahoo.com>
In-Reply-To: <20190406165031.GK1923@kib.kiev.ua>
References:  <403763BB-4DB9-488F-9480-C71871ED66B5@yahoo.com> <20190405114617.GC1923@kib.kiev.ua> <DAF73A33-C69E-46D5-A749-AA77D884203D@yahoo.com> <20190406165031.GK1923@kib.kiev.ua>

next in thread | previous in thread | raw e-mail | index | archive | help


On 2019-Apr-6, at 09:50, Konstantin Belousov <kostikbel at gmail.com> =
wrote:

> On Fri, Apr 05, 2019 at 11:47:58AM -0700, Mark Millard wrote:
>>=20
>>=20
>> On 2019-Apr-5, at 04:46, Konstantin Belousov <kostikbel at gmail.com> =
wrote:
>>=20
>>> On Thu, Apr 04, 2019 at 04:58:15PM -0700, Mark Millard via =
freebsd-amd64 wrote:
>>>> On a:
>>>>=20
>>>> CPU: AMD Ryzen Threadripper 1950X 16-Core Processor  (3393.70-MHz =
K8-class CPU)
>>>> Origin=3D"AuthenticAMD"  Id=3D0x800f11  Family=3D0x17  Model=3D0x1  =
Stepping=3D1
>>>> =
Features=3D0x178bfbff<FPU,VME,DE,PSE,TSC,MSR,PAE,MCE,CX8,APIC,SEP,MTRR,PGE=
,MCA,CMOV,PAT,PSE36,CLFLUSH,MMX,FXSR,SSE,SSE2,HTT>
>>>> =
Features2=3D0x7ed8320b<SSE3,PCLMULQDQ,MON,SSSE3,FMA,CX16,SSE4.1,SSE4.2,MOV=
BE,POPCNT,AESNI,XSAVE,OSXSAVE,AVX,F16C,RDRAND>
>>>> AMD Features=3D0x2e500800<SYSCALL,NX,MMX+,FFXSR,Page1GB,RDTSCP,LM>
>>>> AMD =
Features2=3D0x35c233ff<LAHF,CMP,SVM,ExtAPIC,CR8,ABM,SSE4A,MAS,Prefetch,OSV=
W,SKINIT,WDT,TCE,Topology,PCXC,PNXC,DBE,PL2I,MWAITX>
>>>> Structured Extended =
Features=3D0x209c01a9<FSGSBASE,BMI1,AVX2,SMEP,BMI2,RDSEED,ADX,SMAP,CLFLUSH=
OPT,SHA>
>>>> XSAVE Features=3D0xf<XSAVEOPT,XSAVEC,XINUSE,XSAVES>
>>>> AMD Extended Feature Extensions ID =
EBX=3D0x1007<CLZERO,IRPerf,XSaveErPtr,IBPB>
>>>> SVM: NP,NRIP,VClean,AFlush,DAssist,NAsids=3D32768
>>>> TSC: P-state invariant, performance statistics
>>>>=20
>>>> after "kldload amdtemp" the following is seen:
>>>>=20
>>>> # sysctl dev.cpu.31
>>>> sysctl: unknown oid 'dev.cpu.31'
>>>>=20
>>>> # sysctl dev.cpu.30
>>>> dev.cpu.30.temperature: 62.1C
>>>> dev.cpu.30.cx_method: C1/hlt C2/io
>>>> dev.cpu.30.cx_usage_counters: 0 0
>>>> dev.cpu.30.cx_usage: 0.00% 0.00% last 1000000us
>>>> dev.cpu.30.cx_lowest: C1
>>>> dev.cpu.30.cx_supported: C1/1/0 C2/2/100
>>>> dev.cpu.30.%parent: acpi0
>>>> dev.cpu.30.%pnpinfo: _HID=3Dnone _UID=3D0
>>>> dev.cpu.30.%location: handle=3D\_PR_.C01F
>>>> dev.cpu.30.%driver: cpu
>>>> dev.cpu.30.%desc: ACPI CPU
>>>>=20
>>>> . . .=20
>>>=20
>>> In the output of devinfo(8), how many CPUs do you see ?  Is there =
cpu31,
>>> and does it have amdtemp child ?
>>=20
>> (I only used 'sysctl -a | grep "temp.*[0-9]C$"' as a short
>> way to show one line per dev.cpu.N so show the others  were
>> all present.)
>>=20
>> cpu31 is missing in the devinfo output. The amdtempM's are under
>> pcibX > pciY > hostbZ , not per cpuN .
>>=20
>> Shortended output but showing all the cpuN and amdtmpM
>> and their "parents" and "childern":
>>=20
>> # devinfo
>> nexus0
>>  cryptosoft0
>>  vtvga0
>>  apic0
>>  ram0
>>  acpi0
>>    cpu0
>>      hwpstate0
>>      cpufreq0
>>    cpu1
>>    cpu2
>>    cpu3
>>    cpu4
>>    cpu5
>>    cpu6
>>    cpu7
>>    cpu8
>>    cpu9
>>    cpu10
>>    cpu11
>>    cpu12
>>    cpu13
>>    cpu14
>>    cpu15
>>    cpu16
>>    cpu17
>>    cpu18
>>    cpu19
>>    cpu20
>>    cpu21
>>    cpu22
>>    cpu23
>>    cpu24
>>    cpu25
>>    cpu26
>>    cpu27
>>    cpu28
>>    cpu29
>>    cpu30
>>    pcib0
>>      pci0
>>        hostb0
>>          amdsmn0
>>          amdtemp0
>> . . ,
>>    pcib12
>>      pci12
>>        hostb23
>>          amdsmn1
>>          amdtemp1
>> . . .
>=20
> Ok, I see, it was unexpected to see amdtemp to attach under the host
> bridge instead of cpu device.  Please post complete output of devinfo =
-r
> and pciconf -lvcb somewhere.

Sure. Thanks. I created:

https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=3D237063

and added the two files with the output as attachments.


Note: I'm not going to have more access to the system for
a few(?) days. Hopefully the 2 files are sufficient
evidence for now.

=3D=3D=3D
Mark Millard
marklmi at yahoo.com
( dsl-only.net went
away in early 2018-Mar)




Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?18972821-7476-4B31-ADB2-2DA38BB5C955>