Commit Graph

28 Commits (3c9bd068e0aa8069f71e8193b82b231d6513ce35)

Author SHA1 Message Date
Ben Skeggs cbb3ae3dab nouveau: fix a thinko in copyless pushbuf ioctl
No idea why G80 doesn't hit this, but, this fixes at least one NV40 card.
2009-08-19 15:56:24 +10:00
Ben Skeggs 28f4bfa04b nouveau: support for copy-less pushbuf ioctl 2009-08-18 15:55:42 +10:00
Ben Skeggs 250ab3a38e nouveau: for the moment, assert if we exceed some reloc limits
Nasty, but nicer than silently not writing into the pushbuf
2009-08-18 15:55:02 +10:00
Ben Skeggs 5a73f066ba nouveau: don't overwrite user-specified bo size needlessly 2009-07-28 20:59:05 +10:00
Ben Skeggs 0bf8fb3bce nouveau: user buffers need to be mappable 2009-07-28 20:59:05 +10:00
Ben Skeggs 001331f4f1 nouveau: drm api 0.0.15, update object header, remove fake bo support 2009-07-28 20:59:05 +10:00
Maarten Maathuis 30449829c0 libdrm/nouveau: unmap before ufree means nvbo->sysmem != NULL, which inbalances cpu_prep/cpu_finish
- The bo was mapped with sysmem == NULL, so this means cpu prep is called.
- The bo was unmapped with sysmem != NULL, so this means cpu finish is not called.
- This can lead to a non-zero "cpu writers" count in ttm_bo.
2009-07-27 19:24:13 +02:00
Ben Skeggs f257201c11 nouveau: fix pin for buffers created with bo_wrap 2009-07-09 11:41:47 +10:00
Ben Skeggs 3d4bfe8c89 nouveau: 0.0.14 + extend bo interface to support subrange mapping
Normal map() should operate as before, and map_range()/map_flush() should
give correct results but lacking any performance difference from map().

Nothing exiting being done here yet, but the interface is a good start.
2009-06-05 14:07:23 +10:00
Ben Skeggs 2cb4c64d73 nouveau: fix bo mapping issue 2009-06-04 09:01:32 +10:00
Ben Skeggs 00fae87f96 nouveau: fill in bo->tiled field for referenced buffers
Fixes the dri1 gallium driver if the front buffer happens to be non-linear.
2009-06-03 10:25:53 +10:00
Ben Skeggs c65a343ed2 nouveau: bump for 0.0.13 2009-05-26 15:47:14 +10:00
Ben Skeggs a1e3ab9e55 nouveau: write posting got lost somewhere, bring it back 2009-04-17 09:29:19 +10:00
Ben Skeggs 78e753d033 nouveau: store bo handle in public struct in bo_ref_handle 2009-04-15 12:44:21 +10:00
Ben Skeggs d6ad0dba01 libdrm/nouveau: fix typo in nouveau_device_close() 2009-03-25 08:10:12 +10:00
Ben Skeggs 98b0df3953 libdrm/nouveau: ask the kernel for vram/gart aperture sizes 2009-03-20 10:41:28 +10:00
Ben Skeggs bad16a6b22 libdrm/nouveau: remove unneccesary null ptr checks 2009-03-20 10:32:47 +10:00
Ben Skeggs c37fca4ef6 libdrm/nouveau: incr refcount on ref fence before decr on old fence 2009-03-20 10:25:16 +10:00
Maarten Maathuis 00d8e960ca libdrm/nouveau: unref fences when deleting bo
- This was causing a significant memory leak.
2009-03-20 00:02:12 +01:00
Ben Skeggs 6169e3a601 libdrm/nouveau: implement bo_handle_get for !mm_enabled
bo_handle_ref on !mm_enabled treats handle as an offset, make
bo_handle_get do the same rather than failing.
2009-03-18 10:25:22 +10:00
Robert Noland 2e2e8575b1 libdrm_nouveau: The handle that is passed to mmap needs to be drm_handle_t
drm_handle_t is defined to be a u32 on linux and a u64 on everything
else.  This addresses an issue on FreeBSD amd64 where the map offsets
may be greater than 32bits.  When the handle is cast to 32bit, mmap
cannot match the requested map and causes X to crash.

This should be a NOOP on linux since drm_handle_t is always 32bit.

Signed-off-by: Robert Noland <rnoland@2hip.net>
2009-03-16 01:20:08 -05:00
Kristian Høgsberg c3c21303e3 nouveau: Dist nouvea_dma.h as well.
Oops.  Disting is hard.
2009-02-24 11:42:46 -05:00
Kristian Høgsberg a71d3edd6c nouveau: Also dist nouveau_private.h. 2009-02-24 11:19:41 -05:00
Ben Skeggs a1345338fe libdrm/nouveau: free drmVersion after we're done with it 2009-02-20 14:11:22 +10:00
Ben Skeggs 18f2fcf5aa libdrm/nouveau: fix dma debugging 2009-02-20 14:11:18 +10:00
Pekka Paalanen 2d2f105f79 nouveau: fix type warnings: void* arith, un/signed
nouveau_notifier.c had two places where void* was used in arithmetic,
fixed by using char*.

nouveau_dma_wait(), nouveau_notifier_wait_status() and
nouveau_resource_alloc() had signed/unsigned comparison warnings, fixed
by changing the function parameter into an unsigned type.

Signed-off-by: Pekka Paalanen <pq@iki.fi>
2009-02-11 23:48:49 +02:00
Ben Skeggs 97fdadee6a nouveau: fix some issues where buffer objects never get freed 2009-02-05 23:17:05 +10:00
Ben Skeggs 225e7e274f nouveau: install libdrm_nouveau with libdrm 2009-02-04 14:32:31 +10:00