2fa5f28eee
intel: libdrm support for fence management in execbuf
...
This patch tries to use the available fence count to figure out whether a
given batch can succeed or not (just like the aperture check).
Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
Signed-off-by: Eric Anholt <eric@anholt.net>
2009-01-27 17:23:42 -08:00
e6a062c21a
nv50: support chipset NV96
...
ctxprog seen in okias' trace identical to one we use on NV94, assuming
the initial context values for NV94 will work here too.
2009-01-27 08:36:33 +10:00
753d4c39ff
nv04-nv40: correct RAMHT size
2009-01-27 08:36:08 +10:00
ac8b3308b9
nv50: ack nsource to prevent continuous protection fault irqs
2009-01-12 10:33:48 +10:00
58d557c73b
[FreeBSD] Fix build on FreeBSD after modesetting import.
2008-12-23 13:56:23 -05:00
b48bd3a036
radeon: only write irq regs if irq is enabled
2008-12-23 11:30:37 +10:00
dfd7fdafd8
intel: Rename plane[AB]* back to pipe[AB]*.
...
The values are really going to continue meaning pipe, not plane, and that's
what they're called in the kernel copy of the header. Userland hasn't ever
made the switch to pipe!=plane, since userland checks are based on DRM
version, which is still stuck at 1.6. However, Mesa did start using
plane[AB] names, so provide a compat define.
2008-12-22 16:03:35 -08:00
d221e00105
intel: Sync GEM ioctl comments for easier diffing against the kernel.
2008-12-22 16:03:35 -08:00
731cd5526e
libdrm: add mode setting files
...
Add mode setting files to libdrm, including xf86drmMode.* and the new
drm_mode.h header. Also add a couple of tests to sanity check the
kernel interfaces and update code to support them.
2008-12-17 10:11:37 -08:00
9583c099b4
Revert "Merge branch 'modesetting-gem'"
...
This reverts commit 6656db1055
2008-12-10 15:50:22 -08:00
d5d5aca7f9
Merge branch 'master' into modesetting-gem
2008-12-03 11:53:36 -08:00
7e4e0fbbb8
nv50: support NV94 chipset
2008-11-23 18:49:09 +11:00
52232ad702
nv50: update context-related tables for original 8800GTS
...
I either messed up when I pulled these from a mmio-trace last time, or
the previous values didn't work on my card. Hopefully it's the former!
In any case, at least one of the original NV50 chipsets work now.
2008-11-21 13:18:58 +11:00
2e2fd6c632
DRM: make drm_map_type match upstream kernel
...
Since the TTM type isn't upstream yet, we need to make sure libdrm uses
what the kernel uses, which is _DRM_GEM = 6.
2008-11-20 11:00:29 -08:00
5923831baf
DRM: make drm_map_type match kernel
...
GEM is upstream, but TTM isn't, so _DRM_GEM needs to be 6, not 7.
2008-11-20 10:57:33 -08:00
c029ed2510
Unbreak drm build.
2008-11-19 23:17:27 +01:00
c67a83dfe1
Merge branch 'modesetting-gem' of ssh://git.freedesktop.org/git/mesa/drm into modesetting-gem
2008-11-19 12:42:49 -08:00
7270731a8b
radeon: protect cs ioctl atomic part with a mutex
...
A small subset of CS need to be atomic (relocation+IB commit to
ring) right now, because of the way relocation are handled, we
need to protect the whole ioctl.
2008-11-16 18:11:00 +01:00
965b4d662a
Merge branch 'master' into modesetting-gem
...
Conflicts:
libdrm/Makefile.am
libdrm/intel/intel_bufmgr.h
libdrm/intel/intel_bufmgr_fake.c
libdrm/intel/intel_bufmgr_gem.c
shared-core/drm.h
shared-core/i915_dma.c
shared-core/i915_irq.c
shared-core/radeon_cp.c
shared-core/radeon_drv.h
2008-11-13 15:30:06 -08:00
276c07d885
libdrm: add support for i915 GTT mapping ioctl
...
Add a drm_intel_gem_bo_map_gtt() function for mapping a buffer object
through the aperture rather than directly to its CPU cacheable memory.
2008-11-13 13:52:04 -08:00
9a4cb7eab4
mode: Minor reodering and renaming
2008-11-12 19:17:18 +01:00
17789a409d
mode: Reorder the ioctls and numbering
...
This is to fill in the gaps left by the removal of
the hotplug ioctls. And they also look better :)
2008-11-12 19:10:50 +01:00
1ead45c8f0
mode: Remove hotplug support from ioctl interface
2008-11-12 18:40:04 +01:00
13948c635d
mode: Unify types for ids and strings
2008-11-12 18:16:38 +01:00
15464f5181
radeon: add gart useable size to report to userspace
2008-11-10 15:38:32 +10:00
994f240503
radeon: fix ring tail overflow issue since alignment
2008-11-10 15:25:27 +10:00
758376e6eb
radeon: disable HDP read cache for now
2008-11-10 15:25:12 +10:00
08ef5b5e67
radeon: force all ring writes to 16-dword alignment.
2008-11-10 15:24:42 +10:00
7abb8416a7
radeon: add more packet3 relocations handling
2008-11-09 18:48:46 +01:00
68fcb7770e
radeon: make build again
2008-11-03 09:58:12 +10:00
0e1df6216e
radeon: add mtrr support for VRAM aperture.
2008-11-03 09:52:25 +10:00
2b9a7d5381
radeon: disable AGP for certain chips if not specified until we figure it out
2008-11-03 09:51:57 +10:00
d3aa052f61
radeon: disable debugging message
2008-11-03 09:51:33 +10:00
28c9eb7b74
radeon: commit ring after emitting the buffer discards
2008-11-03 09:50:46 +10:00
e829d5b6bc
radeon: setup isync cntl properly
2008-11-03 09:47:49 +10:00
31b8a640db
radeon: overhaul ring interactions
...
emit in 16-dword blocks, emit irqs at same time as everything else
2008-11-03 09:46:54 +10:00
4ef8ace9a9
radeon: add proc debugging for interrupts/ring
2008-11-03 09:45:43 +10:00
be3dac976e
radeon: only enable dynclks if asked for
2008-11-03 09:44:32 +10:00
31f8d4218c
radeon: add wait rendering API
2008-11-03 09:44:03 +10:00
fc25c81eab
radeon: rs480 fixes for bus mastering
2008-11-03 09:43:29 +10:00
4ccec67a23
radeon: remove unused gem indirect ioctl
2008-11-03 09:42:01 +10:00
6000fa6862
radeon: CS2 make it all work with new relocs style
2008-11-03 09:40:52 +10:00
35f0805592
radeon: don't copy to user the cs ids
2008-11-03 09:40:24 +10:00
8b2925468d
radeon: make new CS2 command submission interface port older interface to this
2008-11-03 09:39:53 +10:00
fd9e05b3f4
radeon: release agp on module unload
2008-11-03 09:33:32 +10:00
624da91277
radeon: add r423 bits to modesetting
2008-11-03 09:33:12 +10:00
1c817cc3fc
radeon: pull bus master enable into its own function
2008-11-03 09:32:39 +10:00
b4803991c8
radeon: update proper chip family
2008-11-03 09:30:48 +10:00
3fd0e1483e
radeon: fixup scratch register interactions properly
2008-11-03 09:29:22 +10:00
a066a5f908
radeon: make writeback work again
2008-11-03 09:28:56 +10:00
Jesse Barnes
Ben Skeggs
Robert Noland
Dave Airlie
Eric Anholt
Stephane Marchesin
Jerome Glisse
Jakob Bornecrantz