Skip site navigation (1)Skip section navigation (2)
Date:      Sat, 6 Apr 2019 01:25:13 -0700
From:      Mark Millard <marklmi@yahoo.com>
To:        Konstantin Belousov <kostikbel@gmail.com>, Bruce Evans <brde@optusnet.com.au>
Cc:        freebsd-hackers Hackers <freebsd-hackers@freebsd.org>, FreeBSD PowerPC ML <freebsd-ppc@freebsd.org>
Subject:   Re: powerpc64 head -r344018 stuck sleeping problems: th->th_scale * tc_delta(th) overflows unsigned 64 bits sometimes [patched failed]
Message-ID:  <7B096BB4-7DBA-4B95-AC1E-DDD9A7DF3B22@yahoo.com>
In-Reply-To: <3592A7F1-9EAE-4A33-B51A-678BE104E18C@yahoo.com>
References:  <20190307222220.GK2492@kib.kiev.ua> <20190309144844.K1166@besplex.bde.org> <20190324110138.GR1923@kib.kiev.ua> <E0785613-2B6E-4BB3-95CD-03DD96902CD8@fh-muenster.de> <20190403070045.GW1923@kib.kiev.ua> <20190404011802.E2390@besplex.bde.org> <F22CCA2C-08BB-452E-B00C-A36CD4611540@yahoo.com> <20190405150236.A959@besplex.bde.org> <F3BBD355-5198-41A0-A461-8E5E12984BE7@yahoo.com> <20190405201055.I2396@besplex.bde.org> <20190405113504.GA1923@kib.kiev.ua> <55604EF6-CB81-4300-8E9E-E3A94504D0B5@yahoo.com> <3592A7F1-9EAE-4A33-B51A-678BE104E18C@yahoo.com>

next in thread | previous in thread | raw e-mail | index | archive | help
[Another document was more explicit about 1/16 mode.]

On 2019-Apr-6, at 00:54, Mark Millard <marklmi at yahoo.com> wrote:

> On 2019-Apr-5, at 14:31, Mark Millard <marklmi at yahoo.com> wrote:
>=20
> [I found a document covering PLLs for the 970MP's in the old
> PowerMac G5 involved.]
>=20
>> On 2019-Apr-5, at 04:35, Konstantin Belousov <kostikbel at gmail.com> =
wrote:
>>>=20
>>> On Fri, Apr 05, 2019 at 09:13:50PM +1100, Bruce Evans wrote:
>>>> On Fri, 5 Apr 2019, Mark Millard wrote:
>>>>=20
>>>>> On 2019-Apr-4, at 21:38, Bruce Evans <brde at optusnet.com.au> =
wrote:
>>>>>=20
>>>>>> On Thu, 4 Apr 2019, Mark Millard wrote:
>>>>>>> ...
>>>>>>> Unfortunately, all the multi-socket contexts that I sometimes =
have
>>>>>>> access to are old PowerMacs. And, currently, the only such =
context
>>>>>>> is the G5 with 2 sockets, 2 cores per socket (powerpc64). So =
I've
>>>>>>> not been able to set up other types of examples to see if =
problems
>>>>>>> repeat.
>>>>>>>=20
>>>>>>> I do not have access to a single-socket powerpc64 for contrast =
in
>>>>>>> that direction.
>>>>>>=20
>>>>>> Testing 1 socket is time-consuming enough.  Do these old systems
>>>>>> use the equivalent of an x86 TSC for the timecounter?  With =
multiple
>>>>>> sockets, it isn't clear how even a hardware timer independent of =
the
>>>>>> CPUs can be distributed so as to appear to be monotonic on all =
cors.
>>>>>=20
>>>>> "The DEC frequency is based on the same implementation-dependent
>>>>> frequency that drives the time base." The frequency may well be
>>>>> fixed by the PowerMac G5 model implementation but is not fixed
>>>>> by the powerpc64 architecture.
>>>>>=20
>>>>> The Time Base Register (TBR) in a powerpc64 core (cpu in FreeBSD =
terms)
>>>>> increments at 33,333,333 Hz (nominal) and is 64 bits wide. Its =
value
>>>>> can be set (mttb instruction) and the boot sequence in FreeBSD =
does
>>>>> attempt to adjust as the FreeBSD CPU is brought-up/started. mftb =
is
>>>>> used to read the 64-bit value. FreeBSD masks it down to 32-bits to
>>>>> contribute to the time-counter.
>>>>>=20
>>>>> (Is that description sufficient for what you were after? I've =
never
>>>>> seen documentation of how the 33,333,333 MHz is produced.)
>>>>=20
>>>> This seems to be equivalent to an x86 TSC.
>>> It is equivalent from the interface PoV.  I saw some references that
>>> Powers do have per-core PLLs, the best I can find now is
>>> =
https://stackoverflow.com/questions/43844438/are-multiple-clock-domains-co=
mmon-in-modern-processors
>>=20
>> I finally found a document covering the 970MP in the old
>> PowerMac G5 in question:
>>=20
>> http://datasheets.chipdb.org/IBM/PowerPC/970/PowerPC-970MP.pdf
>>=20
>> It has material about the PLL's, pinout, etc. :
>>=20
>> "This section will help in configuring the PLL and determining SYSCLK =
input
>> frequency for PowerPC 970MP systems." Also: 100 MHz to 700 MHz =
SYSCLK.
>> "SYSCLK minimum frequency is for PLL mode. In PLL bypass mode (BYPASS =
low),
>> SYSCLK frequency may be as low as 10MHz." BUS_CFG[0:2], PLL_MULT, and
>> PLL_RANGE[1:0] are involved for PLL mode.
>>=20
>> Ratio from BUS_CFG: 3:1, 6:1, 12:1 normally use PLL_MULT=3D0 for a =
PLL multiplier of 12.
>> Ratio from BUS_CFG: 2:1, 4:1, 8:1 normally use PLL_MULT=3D1 for a PLL =
multiplier of 8.
>>=20
>> (It describes the PLL power supply filtering circuit as well.)
>>=20
>> So far I've not seen anything that is directly for the rate that the =
TBR
>> and DEC registers change.
>>=20
>>> For Intel there is no much information, the best guess is that TSC =
is in
>>> uncore and effectively shared by all cores.  See also
>>> =
https://software.intel.com/en-us/articles/best-timing-function-for-measuri=
ng-ipp-api-timing/
>>>=20
>>>>=20
>>>> x86 P-state-invariant TSCs apparently use a 100 MHz clock which =
corresponds
>>>> even more closely to this, except for historical reasons this clock =
is
>>>> scaled and interpolated to a clock resembling the CPU cycle count =
at a
>>>> nominal frequency.
>>> For Intel designs, there is indeed a single-source 100MHz signal =
which
>>> is distributed over all consumers using clock fan-out buffers like =
DB1900Z.
>>>=20
>>>>=20
>>>>> As FreeBSD supports multi-socket, what are its criteria for a =
sufficient
>>>>> context for it to work with for supporting sbinuptime and the =
like? Is
>>>>> FreeBSD supposed to then make it appear that sbinputime and the =
like are
>>>>> weakly increasing, even as threads migrate between CPUs (cores,
>>>>> hw-threads)?
>>>>=20
>>>> CLOCK_MONOTONIC has to be monotonic, but it is only clear what this =
means
>>>> within a single thread: sequential clock_gettime() calls must occur =
in
>>>> program order and the results must be consistent with that order.  =
Across
>>>> threads, I think it should mean that the results must be consistent =
with
>>>> any order established using any supported ordering methods.
>>>>=20
>>>>> ...
>>>>>>> One oddity is that the eventtimer's decrementer and timecounter
>>>>>>> may change (nearly) together: both change at 33,333,333 Hz, as =
if
>>>>>>> they are tied to the same clock (at least on one socket).
>>>>>>=20
>>>>>> I think this is from a normal hardware implementation.  On all of
>>>>>> my x86 systems with a TSC, the TSC frequency is an exact =
fractional
>>>>>> multiple of the i8254, the ACPI timer (if present) and the HPET =
(if
>>>>>> present).  Only the RTC has an independent frequency.  The =
fraction is
>>>>>> changed by changing the nominal TSC frequency in the BIOS, but is =
not
>>>>>> changed by temperature variations.  This must be because most =
clocks are
>>>>>> derived from a common clock using a PLL.  I use this to calibrate =
all
>>>>>> clocks (except the RTC) by calibrating only 1.
>>>>>=20
>>>>> I'm not aware of the OpenFirmware having any control over the
>>>>> TBR-change frequency behavior. I've no evidence about any =
variability
>>>>> based on temperature.
>>>>=20
>>>> Temperature changes usually affect the actual frequency but not the
>>>> nominal frequency.
>>>>=20
>>=20
>=20
> I found more about the 970MP's TB/DEC rate:
>=20
> "The TBEN input pin can be used as an enable for the internal
> timebase/decrementer or as an external clock input." Details:
>=20
> HID0 bit 19 =3D 0: update at 1/16th processor core frequency,
>                 but only when TBEN is high.

That 1/16th should be of "the full processor frequency, even when the
processor itself is running at a lower frequency".

The 970FX has 1/8th instead of 1/16th.

"Since the mesh clock frequency can be lowered to 1/64th of the
full-speed, the time base/decrementer may be increased/decreased
by more than one at a time." The decrementer tests for wrap, not
for reaching zero.


> HID0 bit 19 =3D 1: update at rising edge of TBEN
>                 (must not exceed 1/16th of the core processor's
>                  maximum frequency).
>=20
> So the 33,333,333 Hz TB&DEC update rate vs. 2500 MHz would mean
> that rising edges of TBEN are in use (HID0 bit 19 =3D 1) in the
> PowerMac G5 context in question.
>=20
> I've no information about how closely matched the TBEN signals are
> at the 2 sockets, beyond the nominal frequency.

=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?7B096BB4-7DBA-4B95-AC1E-DDD9A7DF3B22>