linux-stable.git/drivers/gpu/drm/ttm, branch linux-2.6.33.y

drm/ttm: fix ttm_bo_add_ttm(user) failure path

2011-08-29T21:33:02+00:00

commit 7c4c3960dff109bc5db4c35da481c212dadb5eb5 upstream.

ttm_tt_destroy kfrees passed object, so we need to nullify
a reference to it.

Signed-off-by: Marcin Slusarz 
Reviewed-by: Thomas Hellstrom 
Signed-off-by: Dave Airlie 
Signed-off-by: Greg Kroah-Hartman

drm/ttm: Fix two race conditions + fix busy codepaths

2011-03-21T19:45:30+00:00

commit 1df6a2ebd75067aefbdf07482bf8e3d0584e04ee upstream.

This fixes a race pointed out by Dave Airlie where we don't take a buffer
object about to be destroyed off the LRU lists properly. It also fixes a rare
case where a buffer object could be destroyed in the middle of an
accelerated eviction.

The patch also adds a utility function that can be used to prematurely
release GPU memory space usage of an object waiting to be destroyed.
For example during eviction or swapout.

The above mentioned commit didn't queue the buffer on the delayed destroy
list under some rare circumstances. It also didn't completely honor the
remove_all parameter.

Fixes:
https://bugzilla.redhat.com/show_bug.cgi?id=615505
http://bugs.debian.org/cgi-bin/bugreport.cgi?bug=591061

Signed-off-by: Thomas Hellstrom 
Signed-off-by: Dave Airlie 
[ Backported to 2.6.33 -maks ]
Cc: maximilian attems 
Signed-off-by: Greg Kroah-Hartman

drm/ttm: Clear the ghost cpu_writers flag on ttm_buffer_object_transfer.

2011-03-21T19:43:58+00:00

commit 0fbecd400dd0a82d465b3086f209681e8c54cb0f upstream.

It makes sense for a BO to move after a process has requested
exclusive RW access on it (e.g. because the BO used to be located in
unmappable VRAM and we intercepted the CPU access from the fault
handler).

If we let the ghost object inherit cpu_writers from the original
object, ttm_bo_release_list() will raise a kernel BUG when the ghost
object is destroyed. This can be reproduced with the nouveau driver on
nv5x.

Reported-by: Marcin Slusarz 
Reviewed-by: Jerome Glisse 
Tested-by: Marcin Slusarz 
Signed-off-by: Francisco Jerez 
Signed-off-by: Dave Airlie 
Signed-off-by: Greg Kroah-Hartman

drm/ttm: handle OOM in ttm_tt_swapout

2010-03-15T16:07:00+00:00

commit 290e55056ec3d25c72088628245d8cae037b30db upstream.

- Without this change I get a general protection fault.
- Also use PTR_ERR where applicable.

Signed-off-by: Maarten Maathuis 
Reviewed-by: Dave Airlie 
Acked-by: Thomas Hellstrom 
Signed-off-by: Dave Airlie 
Signed-off-by: Greg Kroah-Hartman

drm/ttm: fix caching problem on non-PAT systems.

2010-02-19T21:30:15+00:00

http://bugzilla.kernel.org/show_bug.cgi?id=15328

This fixes a serious regression on AGP/non-PAT systems, where
pages were ending up in the wrong state and slowing down the
whole system.

[airlied: taken this from the bug as the other option is to revert
the change which caused it].

Tested-by: John W. Linville (in bug).
Signed-off-by: Dave Airlie

drm/ttm: Fix a bug occuring when validating a buffer object in a range.

2010-02-15T01:19:14+00:00

If the buffer object was already in the requested memory type, but
outside of the requested range it was never moved into the requested range.

Signed-off-by: Thomas Hellstrom 
Signed-off-by: Dave Airlie

Merge branch 'drm-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/airlied/drm-2.6

2010-02-01T18:46:49+00:00

* 'drm-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/airlied/drm-2.6:
  drm/radeon/kms: Fix oops after radeon_cs_parser_init() failure.
  drm/radeon/kms: move radeon KMS on/off switch out of staging.
  drm/radeon/kms: Bailout of blit if error happen & protect with mutex V3
  drm/vmwgfx: Don't send bad flags to the host
  drm/vmwgfx: Request SVGA version 2 and bail if not found
  drm/vmwgfx: Correctly detect 3D
  drm/ttm: remove unnecessary save_flags and ttm_flag_masked in ttm_bo_util.c
  drm/kms: Remove incorrect comment in struct drm_mode_modeinfo
  drm/ttm: remove padding from ttm_ref_object on 64bit builds
  drm/radeon/kms: release agp on error.
  drm/kms/radeon/agp: Move the check of the aper_size after drm_acp_acquire and drm_agp_info
  drm/kms/radeon/agp: Fix warning, format ‘%d’ expects type ‘int’, but argument 4 has type ‘size_t’
  drm/ttm: Avoid conflicting reserve_memtype during ttm_tt_set_page_caching.
  drm/kms/radeon: pick digitial encoders smarter. (v3)
  drm/radeon/kms: use active device to pick connector for encoder
  drm/radeon/kms: fix incorrect logic in DP vs eDP connector checking.

drm/ttm: remove unnecessary save_flags and ttm_flag_masked in ttm_bo_util.c

2010-02-01T01:27:25+00:00

Signed-off-by: Austin Yuan 
Acked-by: Thomas Hellstrom 
Signed-off-by: Dave Airlie

drm/ttm: remove padding from ttm_ref_object on 64bit builds

2010-02-01T01:24:50+00:00

Re-order structure ttm_ref_object to remove 8 bytes of alignment padding
on 64 bit builds, so shrinking its size from 72 to 64 bytes allowing it
to fit into a smaller slab.

Signed-off-by: Richard Kennedy 
Acked-by: Thomas Hellstrom 
Signed-off-by: Dave Airlie

drm/ttm: Avoid conflicting reserve_memtype during ttm_tt_set_page_caching.

2010-02-01T01:15:37+00:00

Fixes errors like:
> reserve_ram_pages_type failed 0x15b7a000-0x15b7b000, track 0x8, req 0x10
when a BO is moved between WC and UC areas.

Reported-by: Xavier Chantry 
Signed-off-by: Francisco Jerez 
Acked-by: Thomas Hellstrom 
Signed-off-by: Dave Airlie