Nouveau - Jun 2013 - [Bug 66176] New: nouveau.perflvl kernel parameter doesn't work

https://bugs.freedesktop.org/show_bug.cgi?id=66176

          Priority: medium
            Bug ID: 66176
          Assignee: nouveau at lists.freedesktop.org
           Summary: nouveau.perflvl kernel parameter doesn't work
        QA Contact: xorg-team at lists.x.org
          Severity: normal
    Classification: Unclassified
                OS: All
          Reporter: mr.dash.four at googlemail.com
          Hardware: Other
            Status: NEW
           Version: unspecified
         Component: Driver/nouveau
           Product: xorg

When I specify the following kernel parameter - "nouveau.perflvl=0,0"
(that is
in addition to "nouveau.perflvl_wr=7777"), I get the following error
during
boot up (and afterwards, when I try to make this change manually):

kernel: [drm] Initialized drm 1.1.0 20060810
kernel: nouveau  [  DEVICE][0000:01:00.0] BOOT0  : 0x049200a2
kernel: nouveau  [  DEVICE][0000:01:00.0] Chipset: G71 (NV49)
kernel: nouveau  [  DEVICE][0000:01:00.0] Family : NV40
kernel: nouveau  [   VBIOS][0000:01:00.0] checking PRAMIN for image...
kernel: nouveau  [   VBIOS][0000:01:00.0] ... checksum invalid
kernel: nouveau  [   VBIOS][0000:01:00.0] checking PROM for image...
kernel: nouveau  [   VBIOS][0000:01:00.0] ... appears to be valid
kernel: nouveau  [   VBIOS][0000:01:00.0] using image from PROM
kernel: nouveau  [   VBIOS][0000:01:00.0] BIT signature found
kernel: nouveau  [   VBIOS][0000:01:00.0] version 05.71.22.21.0a
kernel: nouveau  [     PFB][0000:01:00.0] RAM type: GDDR3
kernel: nouveau  [     PFB][0000:01:00.0] RAM size: 256 MiB
kernel: nouveau  [     PFB][0000:01:00.0]    ZCOMP: 294912 tags
kernel: nouveau  [  PTHERM][0000:01:00.0] FAN control: PWM
kernel: nouveau  [  PTHERM][0000:01:00.0] fan management: disabled
kernel: nouveau  [  PTHERM][0000:01:00.0] internal sensor: yes
kernel: nouveau  [  PTHERM][0000:01:00.0] programmed thresholds [ 90(3), 95(3),
115(2), 135(5) ]
kernel: agpgart-via 0000:00:00.0: AGP 3.5 bridge
kernel: agpgart: modprobe tried to set rate=x12. Setting to AGP3 x8 mode.
kernel: agpgart-via 0000:00:00.0: putting AGP V3 device into 8x mode
kernel: nouveau 0000:01:00.0: putting AGP V3 device into 8x mode
kernel: [TTM] Zone  kernel: Available graphics memory: 1026356 kiB
kernel: [TTM] Initializing pool allocator
kernel: [TTM] Initializing DMA pool allocator
kernel: nouveau  [     DRM] VRAM: 251 MiB
kernel: nouveau  [     DRM] GART: 256 MiB
kernel: nouveau  [     DRM] TMDS table version 1.1
kernel: nouveau W[     DRM] TMDS table script pointers not stubbed
kernel: nouveau  [     DRM] DCB version 3.0
kernel: nouveau  [     DRM] DCB outp 00: 04011310 00000028
kernel: nouveau  [     DRM] DCB outp 01: 0c011312 00000000
kernel: nouveau  [     DRM] DCB outp 02: 01000300 00000028
kernel: nouveau  [     DRM] DCB outp 03: 020223f1 00c0c083
kernel: nouveau  [     DRM] DCB conn 00: 0000
kernel: nouveau  [     DRM] DCB conn 01: 2130
kernel: nouveau  [     DRM] DCB conn 02: 0210
kernel: nouveau  [     DRM] DCB conn 03: 0211
kernel: nouveau  [     DRM] DCB conn 04: 0213
kernel: nouveau  [     DRM] Saving VGA fonts
kernel: [drm] Supports vblank timestamp caching Rev 1 (10.10.2010).
kernel: [drm] No driver support for vblank timestamp query.
kernel: nouveau  [     DRM] 0xD3FB: Parsing digital output script table
kernel: nouveau  [     DRM] 4 available performance level(s)
kernel: nouveau  [     DRM] 0: core 275MHz shader 275MHz memory 600MHz voltage
1050mV fanspeed 40%
kernel: nouveau  [     DRM] 1: core 400MHz shader 400MHz memory 625MHz voltage
1100mV fanspeed 70%
kernel: nouveau  [     DRM] 2: core 440MHz shader 440MHz memory 650MHz voltage
1100mV fanspeed 79%
kernel: nouveau  [     DRM] 3: core 487MHz shader 487MHz memory 695MHz voltage
1200mV fanspeed 100%
kernel: nouveau  [     DRM] c: core 275MHz shader 275MHz memory 600MHz voltage
1050mV fanspeed 100%
kernel: nouveau  [     DRM] setting performance level: 0
kernel: nouveau E[     DRM] fanspeed set failed: -22
kernel: nouveau  [     DRM] > reclocking failed: -34
kernel: 
kernel: nouveau  [     DRM] > reclocking took 83072ns
kernel: 
kernel: nouveau  [     DRM] MM: using M2MF for buffer copies
kernel: nouveau  [     DRM] Setting dpms mode 3 on TV encoder (output 3)
kernel: nouveau  [     DRM] allocated 1600x1200 fb: 0x9000, bo ffff8800375e6800
kernel: fbcon: nouveaufb (fb0) is primary device
kernel: nouveau  [     DRM] 0xD3FB: Parsing digital output script table
kernel: Console: switching to colour frame buffer device 200x75
kernel: nouveau 0000:01:00.0: fb0: nouveaufb frame buffer device
kernel: nouveau 0000:01:00.0: registered panic notifier
kernel: [drm] Initialized nouveau 1.1.0 20120801 for 0000:01:00.0 on minor 0

When I try to do this from the command line with "echo 0,0 >
/sys/class/hwmon/hwmon0/device/performance_level" I get the exact same
error:

kernel: nouveau  [     DRM] setting performance level: 0
kernel: nouveau E[     DRM] fanspeed set failed: -22
kernel: nouveau  [     DRM] > reclocking failed: -34
kernel: 
kernel: nouveau  [     DRM] > reclocking took 25088ns
kernel: 

The kernel in use is 3.9.6 with the stock-supplied nouveau driver.

-- 
You are receiving this mail because:
You are the assignee for the bug.
-------------- next part --------------
An HTML attachment was scrubbed...
URL:
<http://lists.freedesktop.org/archives/nouveau/attachments/20130625/8b0c6a65/attachment.html>

https://bugs.freedesktop.org/show_bug.cgi?id=66176

Roy <r.spliet at student.tudelft.nl> changed:

           What    |Removed                     |Added
----------------------------------------------------------------------------
             Status|NEW                         |NEEDINFO

--- Comment #1 from Roy <r.spliet at student.tudelft.nl> ---
I'm sorry, but unfortunately reclocking is not implemented for this family
of
cards (NV4x) in nouveau. None of the developers has such a board capable of
reclocking. I have marked this bug NEEDINFO because... well, we need a lot more
info about the internals of this card to be able to implement reclocking. Given
the amount of users actually still using NV49s (and the complete lack of
developer manpower on reclocking) it will probably end up being a
very-low-priority task though.

-- 
You are receiving this mail because:
You are the assignee for the bug.
-------------- next part --------------
An HTML attachment was scrubbed...
URL:
<http://lists.freedesktop.org/archives/nouveau/attachments/20130625/62127df5/attachment.html>

https://bugs.freedesktop.org/show_bug.cgi?id=66176

--- Comment #2 from Mr-4 <mr.dash.four at googlemail.com> ---
I am willing to give you a hand in the development and/or testing, if needed.

I know for a fact that re-clocking is possible on this card - I do that (quite
regularly) on Windows and if I remember correctly I've also done this
"manually" using the pathscale tools.

-- 
You are receiving this mail because:
You are the assignee for the bug.
-------------- next part --------------
An HTML attachment was scrubbed...
URL:
<http://lists.freedesktop.org/archives/nouveau/attachments/20130626/d4640d44/attachment.html>

https://bugs.freedesktop.org/show_bug.cgi?id=66176

--- Comment #3 from Emil Velikov <emil.l.velikov at gmail.com> ---
(In reply to comment #2)
> I am willing to give you a hand in the development and/or testing, if
needed.
Glad to hear, there are a few notes further down that you can start with
> 
> I know for a fact that re-clocking is possible on this card - I do that
> (quite regularly) on Windows and if I remember correctly I've also done
this
> "manually" using the pathscale tools.
Afaik Windows is another kettle of fish, although if it worked previously
that's a good starting point

On the other from you can work from the current state and nitpick until it
works

* The fanspeed set fails as the mode is not NOUVEAU_THERM_CTRL_MANUAL
Annoying but not crucial for the re-clocking to complete. Note I'm not
entirely
sure where it should be set

* pclk->pll_calc seems to return 0, causing nv40_calc_pll() to throw ERANGE
* Some of the functions called within nouveau_mem_timing_calc() may need
tweaking depending on now well we generate the appropriate memory timings

Happy hacking :)

P.S.
Only one zero is required to change the perflvl - "0" rather than
"0,0"

-- 
You are receiving this mail because:
You are the assignee for the bug.
-------------- next part --------------
An HTML attachment was scrubbed...
URL:
<http://lists.freedesktop.org/archives/nouveau/attachments/20130626/25c6cc66/attachment.html>

https://bugs.freedesktop.org/show_bug.cgi?id=66176

--- Comment #4 from Mr-4 <mr.dash.four at googlemail.com> ---
(In reply to comment #3)
> * The fanspeed set fails as the mode is not NOUVEAU_THERM_CTRL_MANUAL
> Annoying but not crucial for the re-clocking to complete. Note I'm not
> entirely sure where it should be set
So, the logical solution to this particular problem would be for that mode to
be *forced* to MANUAL, regardless of its previous state (which I suspect is
NONE) and then try and set the fan speed.
> * pclk->pll_calc seems to return 0, causing nv40_calc_pll() to throw
ERANGE
> * Some of the functions called within nouveau_mem_timing_calc() may need
> tweaking depending on now well we generate the appropriate memory timings
You've lost me! I am no expert in Nouveau development, although I am a
(willing) developer, so you need to explain the above a little bit.
> P.S.
> Only one zero is required to change the perflvl - "0" rather than
"0,0"
Well, by looking at the code, the performance level consists of 2 parts - AC
(power) and DC (battery) separated by a comma (","), so I used
"0,0" for the
sake of completeness.

-- 
You are receiving this mail because:
You are the assignee for the bug.
-------------- next part --------------
An HTML attachment was scrubbed...
URL:
<http://lists.freedesktop.org/archives/nouveau/attachments/20130626/611840c2/attachment.html>

https://bugs.freedesktop.org/show_bug.cgi?id=66176

--- Comment #5 from Emil Velikov <emil.l.velikov at gmail.com> ---
(In reply to comment #4)
...
> to be *forced* to MANUAL, regardless of its previous state (which I suspect
> is NONE) and then try and set the fan speed.
I would call it "set", rather than "forced"

In the second part you'll need a "reference point" - which can be
one of
* The kernel and/or "...I've also done this "manually" using
the pathscale
tools"
* Mmio dump of the blob reclocking the card

Initially I would recommend the former
> 
> > * pclk->pll_calc seems to return 0, causing nv40_calc_pll() to
throw ERANGE
Confirm if the function nv40_calc_pll() is the one throwing ERANGE. Then dwell
into the function, and analyse any differences with your "reff point".
There
may be a typo/inverted logic, as this code moved around in nouveau quite a few
times
> > * Some of the functions called within nouveau_mem_timing_calc() may
need
> > tweaking depending on now well we generate the appropriate memory
timings
nouveau_mem_timing_calc()
* parses the memory timing table stored in vbios - nouveau_perf_timing()
* generates the appropriate values based on the card generation -
nv**_mem_timing_calc()
* and the memory type - nouveau_mem_*ddr*()
* On newer cards (iirc nvc0+) it maps the timings with memory frequency range.
On previous generations the timings are related to the performance level rather
than the memory frequency (range)
> 
> > P.S.
> > Only one zero is required to change the perflvl - "0" rather
than "0,0"
> Well, by looking at the code, the performance level consists of 2 parts -
AC
> (power) and DC (battery) separated by a comma (","), so I used
"0,0" for the
> sake of completeness.
You got me there, I have no recollection when AC/DC got introduced ^_^

-- 
You are receiving this mail because:
You are the assignee for the bug.
-------------- next part --------------
An HTML attachment was scrubbed...
URL:
<http://lists.freedesktop.org/archives/nouveau/attachments/20130627/ed034d21/attachment.html>

https://bugs.freedesktop.org/show_bug.cgi?id=66176

--- Comment #6 from Emil Velikov <emil.l.velikov at gmail.com> ---
Although that seems too much as a start. Thus it would be nice to get the
non-memory engine(s) reclock first and then deal with memory/timings/etc

This can be done by forcing current code to ignore the memory clock stored in
vbios, i.e.

diff --git a/drm/nv40_pm.c b/drm/nv40_pm.c
index 3af5bcd..0be61db 100644
--- a/drm/nv40_pm.c
+++ b/drm/nv40_pm.c
@@ -191,7 +191,7 @@ nv40_pm_clocks_pre(struct drm_device *dev, struct
nouveau_pm_level *perflvl)
     }

     /* memory clock */
-    if (!perflvl->memory) {
+    if (1) {
         info->mpll_ctrl = 0x00000000;
         goto out;
     }

-- 
You are receiving this mail because:
You are the assignee for the bug.
-------------- next part --------------
An HTML attachment was scrubbed...
URL:
<http://lists.freedesktop.org/archives/nouveau/attachments/20130627/afdb9b5c/attachment.html>

https://bugs.freedesktop.org/show_bug.cgi?id=66176

--- Comment #7 from Ilia Mirkin <imirkin at alum.mit.edu> ---
Note that a NV40 reclocking fix just went into the nouveau/linux-2.6 tree:
http://cgit.freedesktop.org/nouveau/linux-2.6/commit/?id=dde3164f85035787ce7c63b791ce3c565ff3e3ff

Can you re-test with this fix in place?

-- 
You are receiving this mail because:
You are the assignee for the bug.
-------------- next part --------------
An HTML attachment was scrubbed...
URL:
<http://lists.freedesktop.org/archives/nouveau/attachments/20130821/06420e4d/attachment.html>

https://bugs.freedesktop.org/show_bug.cgi?id=66176

Ilia Mirkin <imirkin at alum.mit.edu> changed:

           What    |Removed                     |Added
----------------------------------------------------------------------------
             Status|NEEDINFO                    |RESOLVED
         Resolution|---                         |INVALID

--- Comment #8 from Ilia Mirkin <imirkin at alum.mit.edu> ---
No response to re-test request in a month. Closing as invalid.

-- 
You are receiving this mail because:
You are the assignee for the bug.
-------------- next part --------------
An HTML attachment was scrubbed...
URL:
<http://lists.freedesktop.org/archives/nouveau/attachments/20130921/6cbadf43/attachment.html>