Commit Graph

8 Commits (8576527cfacaf42af8316e1030c192193e94225a)

Author SHA1 Message Date
Maarten Lankhorst 56c4857f17 nouveau: Only export public functions.
This hides all the abi16_* functions and the nouveau_debug variable,
they should have been private to begin with.

Signed-off-by: Maarten Lankhorst <maarten.lankhorst@canonical.com>
Reviewed-by: Emil Velikov <emil.l.velikov@gmail.com>
2014-08-04 09:22:00 +02:00
Maarten Lankhorst 482abbfafb nouveau: prevent undefined behavior in nouveau_pushbuf_reloc with gcc-4.8
Reported-by: ronald645@gmail.com
Bisected-by (gcc): Andreas Radke <a.radke@arcor.de>
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=71116
Signed-off-by: Maarten Lankhorst <maarten.lankhorst@canonical.com>
2013-11-07 13:37:49 +01:00
Marcin Slusarz f92d7969bf nouveau: add a way to override single pushbuffer memory limits
Currently single pushbuffer can take up to 80% of VRAM and 80% of GART.
As this value seems to be arbitrary (and user may need to set it differently)
this patch adds support for 2 environment variables:
NOUVEAU_LIBDRM_VRAM_LIMIT_PERCENT (default 80)
NOUVEAU_LIBDRM_GART_LIMIT_PERCENT (default 80)
which will let users override pushbuffer VRAM/GART limits.

Signed-off-by: Marcin Slusarz <marcin.slusarz@gmail.com>
2013-03-26 21:08:03 +01:00
Marcin Slusarz 284421a569 nouveau: return error from pushbuf_validate
Signed-off-by: Marcin Slusarz <marcin.slusarz@gmail.com>
2013-03-26 21:08:03 +01:00
Ben Skeggs 891517f511 nouveau: disallow pushbuf BOs in multiple memory types
Under certain circumstances it's possible for libdrm to decide to move
a GART|VRAM pushbuf to be VRAM-only.  This causes the kernel to reject
the command submission on GF8 and up, due to a stricter policy where
buffers are only allowed to move to memory types that were specified
at creation time.

The simplest fix for this is to force the creation-time memory type for
the lifetime of the push buffer.

Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2013-01-07 13:15:28 +10:00
Marcin Slusarz 9e0026d35c nouveau: silence some remaining valgrind warnings
Valgrind can't understand some of the fields passed to ioctls are overwritten
by kernel, so we need to initialize them. Almost all of our ioctl wrappers
already do it and the cost of remaining 3 is very small.

Signed-off-by: Marcin Slusarz <marcin.slusarz@gmail.com>
2012-06-09 23:23:32 +02:00
Marcin Slusarz d954648b48 nouveau: remove unnecessary EAGAIN loops
drmCommandWrite / drmCommandWriteRead already loop on EAGAIN.

Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
2012-04-24 12:41:39 +10:00
Ben Skeggs 292da616fe nouveau: pull in major libdrm rewrite
Redesigned primarily to allow us to better take advantage of BO's having
fixed GPU virtual addresses on GeForce 8 and up, and to reduce the overhead
of handling relocations on earlier chipsets.

Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
Signed-off-by: Christoph Bumiller <e0425955@student.tuwien.ac.at>
2012-04-14 02:47:23 +10:00