1522ecae65
drm/nouveau/bios: timing 2.0 entries can have subentries
...
Signed-off-by: Ben Skeggs <bskeggs@redhat.com >
2014-01-23 13:38:54 +10:00
09692e5b4e
drm/nve0/fb/gddr5: note another semi-unknown
...
Signed-off-by: Ben Skeggs <bskeggs@redhat.com >
2014-01-23 13:38:53 +10:00
1e1d6b4c53
drm/nouveau/fb/gddr5: modify mr8 with high bits of CL/WR
...
Signed-off-by: Ben Skeggs <bskeggs@redhat.com >
2014-01-23 13:38:52 +10:00
e7084c669b
drm/nve0/fb/gddr5: fix calculation of RDQS setting
...
Signed-off-by: Ben Skeggs <bskeggs@redhat.com >
2014-01-23 13:38:52 +10:00
334565abfe
drm/nve0/fb/gddr5: switch off some other random bit at some point
...
As seen when comparing us vs nv on my GTX660
Signed-off-by: Ben Skeggs <bskeggs@redhat.com >
2014-01-23 13:38:51 +10:00
01891690e8
drm/nve0/fb/gddr5: punt all 10f910/914 accesses through ram_train
...
Signed-off-by: Ben Skeggs <bskeggs@redhat.com >
2014-01-23 13:38:50 +10:00
d394fb12ec
drm/nve0/fb/gddr5: not all memory partitions are created equal
...
As seen when comparing us vs nv on my GTX660.
Signed-off-by: Ben Skeggs <bskeggs@redhat.com >
2014-01-23 13:38:49 +10:00
dd95c8f782
drm/nve0/fb: typo in register name
...
Signed-off-by: Ben Skeggs <bskeggs@redhat.com >
2014-01-23 13:38:48 +10:00
0a0dc8f564
drm/nouveau/bios: make common code to handle ramcfg strap etc
...
Signed-off-by: Ben Skeggs <bskeggs@redhat.com >
2014-01-23 13:38:48 +10:00
5905439224
drm/nve0/fb/gddr5: fix an assumption of sane memory controller layout
...
Signed-off-by: Ben Skeggs <bskeggs@redhat.com >
2014-01-23 13:38:47 +10:00
2daaf5b0e4
drm/nve0/fb/gddr5: fix behaviour of lp3 setting
...
Signed-off-by: Ben Skeggs <bskeggs@redhat.com >
2014-01-23 13:38:46 +10:00
cb1567c286
drm/nve0/fifo: recover from mmu faults on bar1/bar3
...
Signed-off-by: Ben Skeggs <bskeggs@redhat.com >
2014-01-23 13:38:45 +10:00
649ec925ae
drm/nve0/fifo: keep mmu fault interrupts enabled at all times
...
Signed-off-by: Ben Skeggs <bskeggs@redhat.com >
2014-01-23 13:38:44 +10:00
e1b6b14ad5
drm/nve0/fifo: update human-readable mmu fault descriptions
...
Ordering from Android GK20A driver, names from binary driver strings.
Signed-off-by: Ben Skeggs <bskeggs@redhat.com >
2014-01-23 13:38:44 +10:00
e9fb9805ad
drm/nve0/fifo: document more intr status bits
...
As per Android GK20A driver.
Signed-off-by: Ben Skeggs <bskeggs@redhat.com >
2014-01-23 13:38:43 +10:00
9f8459cf06
drm/nve0/fifo: populate PBDMA status bitfield with more definitions
...
As per Android GK20A driver.
Signed-off-by: Ben Skeggs <bskeggs@redhat.com >
2014-01-23 13:38:42 +10:00
39b055427e
drm/nve0/fifo: s/subfifo/PBDMA/
...
As per Android GK20A driver.
Signed-off-by: Ben Skeggs <bskeggs@redhat.com >
2014-01-23 13:38:41 +10:00
f82c44a78f
drm/nve0/fifo: s/playlist/runlist/
...
As per Android GK20A driver.
Signed-off-by: Ben Skeggs <bskeggs@redhat.com >
2014-01-23 13:38:40 +10:00
f76dd80f76
drm/nvf0/gr: enable acceleration with our chsw ucode
...
Signed-off-by: Ben Skeggs <bskeggs@redhat.com >
2014-01-23 13:38:40 +10:00
aa97cd31b6
drm/nv108/gr: enable acceleration with our chsw ucode
...
Signed-off-by: Ben Skeggs <bskeggs@redhat.com >
2014-01-23 13:38:39 +10:00
5d91e1916d
drm/nvc0-/gr: handle fwmthd interrupts in ucode
...
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 >
2014-01-23 13:38:38 +10:00
e1b22bc148
drm/nvc0-/gr: fiddle some magic around strand init
...
Fixes HUB_INIT timeout on GK110/GK208 when not using NVIDIA's ucode.
Signed-off-by: Ben Skeggs <bskeggs@redhat.com >
2014-01-23 13:38:37 +10:00
96616b4caf
drm/nv108/gr: initial support (need external fuc)
...
Signed-off-by: Ben Skeggs <bskeggs@redhat.com >
2014-01-23 13:38:36 +10:00
daa9ab5821
drm/nv108/ce: enable copy engines
...
Signed-off-by: Ben Skeggs <bskeggs@redhat.com >
2014-01-23 13:38:35 +10:00
a763951a86
drm/nv108/fifo: initial support
...
Signed-off-by: Ben Skeggs <bskeggs@redhat.com >
2014-01-23 13:38:35 +10:00
Ben Skeggs