Commits · a8ccbb7701d41a772d839acb3d81d7f9ac84c678 · nexedi / linux

23 Jan, 2014 40 commits
- drm/nve0/fb/gddr5: 10f698/69c · a8ccbb77
  Ben Skeggs authored Dec 03, 2013
```
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
```
  a8ccbb77
- drm/nve0/fb: it's now safe to obey the memory voltage setting properly · cfe17608
  Ben Skeggs authored Dec 03, 2013
```
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
```
  cfe17608
- drm/nve0/fb: multi-stage reclock is required for certain transitions · 46bf1c38
  Ben Skeggs authored Dec 03, 2013
```
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
```
  46bf1c38
- drm/nouveau/clk: allow fb to signal it needs to do a multi-stage reclock · 1789cab4
  Ben Skeggs authored Dec 03, 2013
```
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
```
  1789cab4
- drm/nve0/fb/gddr5: parse bios data into struct rather than using directly · b655f2bb
  Ben Skeggs authored Dec 02, 2013
```
Still essentially a struct of magic values with magic names and unknown
purposes.  But, we will shortly need to be able to mix and match bits of
the previous and next configurations to do a transition reclock, as such,
we can no longer directly use the vbios data with any ease.

This is probably nicer anyway in the long run, for a few reasons.
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
```
  b655f2bb
- drm/nve0/fb/gddr5: found LP3 setting · ea8b4a38
  Ben Skeggs authored Dec 02, 2013
```
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
```
  ea8b4a38
- drm/nve0/fb: note the memory voltage toggle, not using it yet · 971372ea
  Ben Skeggs authored Dec 02, 2013
```
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
```
  971372ea
- drm/nve0/fb/gddr5: somewhat better attempt at 100770/10f604/610/614 · db6735ca
  Ben Skeggs authored Nov 30, 2013
```
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>

fb/gddr5/nve0: 100770 is like 10f604
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
```
  db6735ca
- drm/nve0/fb/gddr5: fixup delays a bit · f4aa2c66
  Ben Skeggs authored Nov 30, 2013
```
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
```
  f4aa2c66
- drm/nouveau/bios: timing 2.0 entries can have subentries · 1522ecae
  Ben Skeggs authored Nov 30, 2013
```
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
```
  1522ecae
- drm/nve0/fb/gddr5: note another semi-unknown · 09692e5b
  Ben Skeggs authored Nov 28, 2013
```
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
```
  09692e5b
- drm/nouveau/fb/gddr5: modify mr8 with high bits of CL/WR · 1e1d6b4c
  Ben Skeggs authored Nov 28, 2013
```
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
```
  1e1d6b4c
- drm/nve0/fb/gddr5: fix calculation of RDQS setting · e7084c66
  Ben Skeggs authored Nov 28, 2013
```
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
```
  e7084c66
- drm/nve0/fb/gddr5: switch off some other random bit at some point · 334565ab
  Ben Skeggs authored Nov 28, 2013
```
As seen when comparing us vs nv on my GTX660
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
```
  334565ab
- drm/nve0/fb/gddr5: punt all 10f910/914 accesses through ram_train · 01891690
  Ben Skeggs authored Nov 28, 2013
```
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
```
  01891690
- drm/nve0/fb/gddr5: not all memory partitions are created equal · d394fb12
  Ben Skeggs authored Nov 27, 2013
```
As seen when comparing us vs nv on my GTX660.
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
```
  d394fb12
- drm/nve0/fb: typo in register name · dd95c8f7
  Ben Skeggs authored Nov 27, 2013
```
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
```
  dd95c8f7
- drm/nouveau/bios: make common code to handle ramcfg strap etc · 0a0dc8f5
  Ben Skeggs authored Nov 27, 2013
```
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
```
  0a0dc8f5
- drm/nve0/fb/gddr5: fix an assumption of sane memory controller layout · 59054392
  Ben Skeggs authored Nov 26, 2013
```
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
```
  59054392
- drm/nve0/fb/gddr5: fix behaviour of lp3 setting · 2daaf5b0
  Ben Skeggs authored Nov 26, 2013
```
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
```
  2daaf5b0
- drm/nve0/fifo: recover from mmu faults on bar1/bar3 · cb1567c2
  Ben Skeggs authored Jan 09, 2014
```
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
```
  cb1567c2
- drm/nve0/fifo: keep mmu fault interrupts enabled at all times · 649ec925
  Ben Skeggs authored Jan 09, 2014
```
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
```
  649ec925
- drm/nve0/fifo: update human-readable mmu fault descriptions · e1b6b14a
  Ben Skeggs authored Jan 08, 2014
```
Ordering from Android GK20A driver, names from binary driver strings.
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
```
  e1b6b14a
- drm/nve0/fifo: document more intr status bits · e9fb9805
  Ben Skeggs authored Jan 08, 2014
```
As per Android GK20A driver.
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
```
  e9fb9805
- drm/nve0/fifo: populate PBDMA status bitfield with more definitions · 9f8459cf
  Ben Skeggs authored Jan 08, 2014
```
As per Android GK20A driver.
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
```
  9f8459cf
- drm/nve0/fifo: s/subfifo/PBDMA/ · 39b05542
  Ben Skeggs authored Jan 08, 2014
```
As per Android GK20A driver.
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
```
  39b05542
- drm/nve0/fifo: s/playlist/runlist/ · f82c44a7
  Ben Skeggs authored Jan 08, 2014
```
As per Android GK20A driver.
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
```
  f82c44a7
- drm/nvf0/gr: enable acceleration with our chsw ucode · f76dd80f
  Ben Skeggs authored Dec 10, 2013
```
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
```
  f76dd80f
- drm/nv108/gr: enable acceleration with our chsw ucode · aa97cd31
  Ben Skeggs authored Dec 10, 2013
```
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
```
  aa97cd31
- drm/nvc0-/gr: handle fwmthd interrupts in ucode · 5d91e191
  Ben Skeggs authored Dec 10, 2013
```
Compute code in mesa triggers one of these, hanging the engine.  Let's
at least ack the request for now to avoid the hang.
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
```
  5d91e191
- drm/nvc0-/gr: fiddle some magic around strand init · e1b22bc1
  Ben Skeggs authored Dec 10, 2013
```
Fixes HUB_INIT timeout on GK110/GK208 when not using NVIDIA's ucode.
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
```
  e1b22bc1
- drm/nv108/gr: initial support (need external fuc) · 96616b4c
  Ben Skeggs authored Nov 05, 2013
```
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
```
  96616b4c
- drm/nv108/ce: enable copy engines · daa9ab58
  Ben Skeggs authored Nov 05, 2013
```
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
```
  daa9ab58
- drm/nv108/fifo: initial support · a763951a
  Ben Skeggs authored Nov 05, 2013
```
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
```
  a763951a
- drm/nvf0/gr: remove a copy+pasto in ctx reglist · a0f95f11
  Ben Skeggs authored Dec 06, 2013
```
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
```
  a0f95f11
- drm/nvc0-/gr: bring in some macros to abstract falcon isa differences · 67af60f0
  Ben Skeggs authored Dec 06, 2013
```
Need. A. Compiler...
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
```
  67af60f0
- drm/nouveau/falcon: use vmalloc to create firwmare copies · 90d6db16
  Ilia Mirkin authored Dec 07, 2013
```
Some firmware images may be large (64K), so using kmalloc memory is
inappropriate for them. Use vmalloc instead, to avoid high-order
allocation failures.
Signed-off-by: Ilia Mirkin <imirkin@alum.mit.edu>
Cc: stable@vger.kernel.org
```
  90d6db16
- drm/nouveau/gem: remove (now) unneeded pre-validate fence sync · d96bf437
  Ben Skeggs authored Nov 22, 2013
```
Now that nouveau_bo.c can handle sync when it actually needs to, we can
remove this and avoid a double semaphore acquire when syncing in the
command submission path.
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
```
  d96bf437
- drm/nouveau/ttm: explicitly wait for bo idle before memcpy buffer move · cef9e99e
  Ben Skeggs authored Nov 22, 2013
```
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
```
  cef9e99e
- drm/nouveau/ttm: explicity sync with kernel channel before moving buffer · 35b8141b
  Ben Skeggs authored Nov 22, 2013
```
The GEM code handles this currently, but that'll be removed.
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
```
  35b8141b