| /linux/drivers/gpu/drm/nouveau/nvkm/subdev/bar/ |
| H A D | g84.c | diff 48fe02478a0ddb89930f3595f8217fa2dfd98796 Tue Oct 31 18:56:19 CET 2017 Ben Skeggs <bskeggs@redhat.com> drm/nouveau/bar: expose interface to bar2 initialisation
If we want to be able to hit the instmem fast-path in a few trickier cases,
we need to be more flexible with when we can initialise BAR2 access.
There's probably a decent case to be made for merging BAR/INSTMEM into BUS,
but that's something to ponder another day.
Flushes have been added after the write to bind the instance block,
as later commits will reveal the need for them.
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
|
| H A D | nv50.h | diff 48fe02478a0ddb89930f3595f8217fa2dfd98796 Tue Oct 31 18:56:19 CET 2017 Ben Skeggs <bskeggs@redhat.com> drm/nouveau/bar: expose interface to bar2 initialisation
If we want to be able to hit the instmem fast-path in a few trickier cases,
we need to be more flexible with when we can initialise BAR2 access.
There's probably a decent case to be made for merging BAR/INSTMEM into BUS,
but that's something to ponder another day.
Flushes have been added after the write to bind the instance block,
as later commits will reveal the need for them.
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
|
| H A D | nv50.c | diff 48fe02478a0ddb89930f3595f8217fa2dfd98796 Tue Oct 31 18:56:19 CET 2017 Ben Skeggs <bskeggs@redhat.com> drm/nouveau/bar: expose interface to bar2 initialisation
If we want to be able to hit the instmem fast-path in a few trickier cases,
we need to be more flexible with when we can initialise BAR2 access.
There's probably a decent case to be made for merging BAR/INSTMEM into BUS,
but that's something to ponder another day.
Flushes have been added after the write to bind the instance block,
as later commits will reveal the need for them.
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
|
| H A D | gf100.h | diff 48fe02478a0ddb89930f3595f8217fa2dfd98796 Tue Oct 31 18:56:19 CET 2017 Ben Skeggs <bskeggs@redhat.com> drm/nouveau/bar: expose interface to bar2 initialisation
If we want to be able to hit the instmem fast-path in a few trickier cases,
we need to be more flexible with when we can initialise BAR2 access.
There's probably a decent case to be made for merging BAR/INSTMEM into BUS,
but that's something to ponder another day.
Flushes have been added after the write to bind the instance block,
as later commits will reveal the need for them.
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
|
| H A D | base.c | diff 48fe02478a0ddb89930f3595f8217fa2dfd98796 Tue Oct 31 18:56:19 CET 2017 Ben Skeggs <bskeggs@redhat.com> drm/nouveau/bar: expose interface to bar2 initialisation
If we want to be able to hit the instmem fast-path in a few trickier cases,
we need to be more flexible with when we can initialise BAR2 access.
There's probably a decent case to be made for merging BAR/INSTMEM into BUS,
but that's something to ponder another day.
Flushes have been added after the write to bind the instance block,
as later commits will reveal the need for them.
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
|
| H A D | gf100.c | diff 48fe02478a0ddb89930f3595f8217fa2dfd98796 Tue Oct 31 18:56:19 CET 2017 Ben Skeggs <bskeggs@redhat.com> drm/nouveau/bar: expose interface to bar2 initialisation
If we want to be able to hit the instmem fast-path in a few trickier cases,
we need to be more flexible with when we can initialise BAR2 access.
There's probably a decent case to be made for merging BAR/INSTMEM into BUS,
but that's something to ponder another day.
Flushes have been added after the write to bind the instance block,
as later commits will reveal the need for them.
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
|
| H A D | priv.h | diff 48fe02478a0ddb89930f3595f8217fa2dfd98796 Tue Oct 31 18:56:19 CET 2017 Ben Skeggs <bskeggs@redhat.com> drm/nouveau/bar: expose interface to bar2 initialisation
If we want to be able to hit the instmem fast-path in a few trickier cases,
we need to be more flexible with when we can initialise BAR2 access.
There's probably a decent case to be made for merging BAR/INSTMEM into BUS,
but that's something to ponder another day.
Flushes have been added after the write to bind the instance block,
as later commits will reveal the need for them.
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
|
| /linux/drivers/gpu/drm/nouveau/include/nvkm/subdev/ |
| H A D | bar.h | diff 48fe02478a0ddb89930f3595f8217fa2dfd98796 Tue Oct 31 18:56:19 CET 2017 Ben Skeggs <bskeggs@redhat.com> drm/nouveau/bar: expose interface to bar2 initialisation
If we want to be able to hit the instmem fast-path in a few trickier cases,
we need to be more flexible with when we can initialise BAR2 access.
There's probably a decent case to be made for merging BAR/INSTMEM into BUS,
but that's something to ponder another day.
Flushes have been added after the write to bind the instance block,
as later commits will reveal the need for them.
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
|