[PATCH 2/3] drm/radeon: no need to check all relocs for dublicates

2011-10-25 Thread Christian König
Only check the previusly checked relocs for dublicates. Also leaving the handle uninitialized isn't such a good idea. Signed-off-by: Christian König deathsim...@vodafone.de --- drivers/gpu/drm/radeon/radeon_cs.c |5 +++-- 1 files changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers

[PATCH 1/3] drm/radeon: fix debugfs handling

2011-10-25 Thread Christian König
Having registered debugfs files globally causes the files to not show up on the second, third etc.. card in the system. Signed-off-by: Christian König deathsim...@vodafone.de --- drivers/gpu/drm/radeon/radeon.h|8 +++ drivers/gpu/drm/radeon/radeon_device.c | 33

[PATCH 3/3] drm/radeon: fix a spelling mistake

2011-10-25 Thread Christian König
Better fix it before this obvious typo spreads even more. Signed-off-by: Christian König deathsim...@vodafone.de --- drivers/gpu/drm/radeon/radeon.h |4 +- drivers/gpu/drm/radeon/radeon_fence.c | 34 drivers/gpu/drm/radeon/radeon_pm.c|4

[PATCH 1/3] drm/radeon: fix debugfs handling

2011-10-28 Thread Christian König
Having registered debugfs files globally causes the files to not show up on the second, third etc.. card in the system. Signed-off-by: Christian König deathsim...@vodafone.de Reviewed-by: Alex Deucher alexander.deuc...@amd.com --- drivers/gpu/drm/radeon/radeon.h|8 drivers

[PATCH 2/3] drm/radeon: no need to check all relocs for duplicates

2011-10-28 Thread Christian König
Only check the previously checked relocs for duplicates. Also leaving the handle uninitialized isn't such a good idea. Signed-off-by: Christian König deathsim...@vodafone.de --- drivers/gpu/drm/radeon/radeon_cs.c |5 +++-- 1 files changed, 3 insertions(+), 2 deletions(-) diff --git

Some minor bugfixes

2011-10-28 Thread Christian König
The following three patches are just minor bug fixes. I've send them to the list previously, but this time they are based upon drm-next instead of drm-fixes and I also fixed some spelling mistakes in the commit messages. Please commit. Thanks, Christian.

[PATCH 3/3] drm/radeon: fix a spelling mistake

2011-10-28 Thread Christian König
Better fix it before this obvious typo spreads even more. Signed-off-by: Christian König deathsim...@vodafone.de Reviewed-by: Alex Deucher alexander.deuc...@amd.com --- drivers/gpu/drm/radeon/radeon.h |4 +- drivers/gpu/drm/radeon/radeon_fence.c | 34

RFC: Radeon multi ring support branch

2011-10-29 Thread Christian König
Hello everybody, to support multiple compute rings, async DMA engines and UVD we need to teach the radeon kernel module how to sync buffers between different rings and make some changes to the command submission ioctls. Since we can't release any documentation about async DMA or UVD (yet),

Re: RFC: Radeon multi ring support branch

2011-11-02 Thread Christian König
On 31.10.2011 16:05, Jerome Glisse wrote: On Sat, Oct 29, 2011 at 03:00:28PM +0200, Christian König wrote: Hello everybody, to support multiple compute rings, async DMA engines and UVD we need to teach the radeon kernel module how to sync buffers between different rings and make some changes

Re: RFC: Radeon multi ring support branch

2011-11-15 Thread Christian König
On 15.11.2011 20:32, Jerome Glisse wrote: On Sat, Oct 29, 2011 at 03:00:28PM +0200, Christian König wrote: Hello everybody, to support multiple compute rings, async DMA engines and UVD we need to teach the radeon kernel module how to sync buffers between different rings and make some changes

Re: RFC: Radeon multi ring support branch

2011-11-17 Thread Christian König
On 16.11.2011 01:24, Jerome Glisse wrote: Well as we don't specify on which value semaphore should wait on, i am prety sure the first ring to increment the semaphore will unblock all waiter. So if you have ring1 that want to wait on ring2 and ring3 as soon as ring2 or ring3 is done ring1 will

Re: RFC: Radeon multi ring support branch

2011-11-18 Thread Christian König
On 17.11.2011 17:58, Jerome Glisse wrote: 2011/11/17 Christian Königdeathsim...@vodafone.de: On 16.11.2011 01:24, Jerome Glisse wrote: Well as we don't specify on which value semaphore should wait on, i am prety sure the first ring to increment the semaphore will unblock all waiter. So if you

Re: [PATCH 1/3] drm/radeon: GPU virtual memory support v22

2012-01-06 Thread Christian König
On -10.01.-28163 20:59, alexdeuc...@gmail.com wrote: [SNIP] #define RADEON_CHUNK_ID_RELOCS0x01 #define RADEON_CHUNK_ID_IB0x02 #define RADEON_CHUNK_ID_FLAGS 0x03 /* The first dword of RADEON_CHUNK_ID_FLAGS is a uint32 of these flags: */ #define RADEON_CS_KEEP_TILING_FLAGS

Re: [PATCH 1/3] drm/radeon: GPU virtual memory support v22

2012-01-06 Thread Christian König
On 06.01.2012 15:12, Alex Deucher wrote: 2012/1/6 Christian Königdeathsim...@vodafone.de: On -10.01.-28163 20:59, alexdeuc...@gmail.com wrote: [SNIP] #define RADEON_CHUNK_ID_RELOCS0x01 #define RADEON_CHUNK_ID_IB0x02 #define RADEON_CHUNK_ID_FLAGS 0x03 /* The first dword of

Re: Re: [PATCH 1/2] drm/radeon/kms: use drm_detect_hdmi_monitor for picking encoder mode

2012-01-27 Thread Christian König
On -10.01.-28163 20:59, Rafał Miłecki wrote: 2012/1/20alexdeuc...@gmail.com: From: Alex Deucheralexander.deuc...@amd.com We were previously just checking for audio. So... Does every hdmi_monitor supports audio? Or should it rather be if (drm_detect_monitor_audio(radeon_connector-edid)

Re: Re: [PATCH] drm/radeon: Add support for userspace fence waits

2012-01-31 Thread Christian König
On -10.01.-28163 20:59, Jerome Glisse wrote: On Tue, Jan 31, 2012 at 02:13:00PM -0500, Alex Deucher wrote: On Tue, Jan 31, 2012 at 2:07 PM, Jerome Glissej.gli...@gmail.com wrote: On Tue, Jan 31, 2012 at 01:55:43PM -0500, David Airlie wrote: Some comments below. + struct radeon_device

Re: [PATCH] drm/radeon: Add support for userspace fence waits

2012-02-01 Thread Christian König
On 01.02.2012 12:31, Simon Farnsworth wrote: Christian, You said elsewhere that you have half-finished patches that illustrate the interface Jerome prefers - if you send them to me, I can work on finishing them. Responding to the rest of the message: Well it's probably easier to type that down

[PATCH] drm/radeon: move ring syncing after bo validation

2012-02-03 Thread Christian König
The function radeon_bo_list_validate can cause a bo to move, resulting in a different sync_obj and a dependency to wait for this move to finish. Signed-off-by: Christian König deathsim...@vodafone.de --- drivers/gpu/drm/radeon/radeon.h|1 - drivers/gpu/drm/radeon/radeon_cs.c | 21

[PATCH 1/4] drm/radeon: move ring syncing after bo validation

2012-02-23 Thread Christian König
The function radeon_bo_list_validate can cause a bo to move, resulting in a different sync_obj and a dependency to wait for this move to finish. Signed-off-by: Christian König deathsim...@vodafone.de Reviewed-by: Alex Deucher alexander.deuc...@amd.com --- drivers/gpu/drm/radeon/radeon.h

[PATCH 2/4] drm/radeon/kms: no need to align IB like this

2012-02-23 Thread Christian König
So don't confuse devs by doing so. Signed-off-by: Christian König deathsim...@vodafone.de --- drivers/gpu/drm/radeon/r600.c | 15 +-- 1 files changed, 1 insertions(+), 14 deletions(-) diff --git a/drivers/gpu/drm/radeon/r600.c b/drivers/gpu/drm/radeon/r600.c index 4f08e5e..4a4ac8f

[PATCH 3/4] drm/radeon: also make the cs_parse function per ring

2012-02-23 Thread Christian König
Not all rings use PM4, so the cs_parser also needs to be per ring. Signed-off-by: Christian König deathsim...@vodafone.de --- drivers/gpu/drm/radeon/radeon.h |4 +- drivers/gpu/drm/radeon/radeon_asic.c | 38 + drivers/gpu/drm/radeon/radeon_cs.c |2

[PATCH 4/4] drm/radeon: fix IB debugfs files for multiple cards

2012-02-23 Thread Christian König
Storing pointers to the IBs in a static var just leads to giving the same content back for all cards in the system. Signed-off-by: Christian König deathsim...@vodafone.de --- drivers/gpu/drm/radeon/radeon_ring.c |8 ++-- 1 files changed, 6 insertions(+), 2 deletions(-) diff --git

Re: [PATCH 2/4] drm/radeon/kms: no need to align IB like this

2012-02-23 Thread Christian König
On 23.02.2012 18:00, Jerome Glisse wrote: 2012/2/23 Christian König deathsim...@vodafone.de mailto:deathsim...@vodafone.de So don't confuse devs by doing so. Signed-off-by: Christian König deathsim...@vodafone.de mailto:deathsim...@vodafone..de --- drivers/gpu/drm

Re: [PATCH 1/4] drm/radeon: move ring syncing after bo validation

2012-02-23 Thread Christian König
On 23.02.2012 18:32, Jerome Glisse wrote: 2012/2/23 Mathias Fröhlich mathias.froehl...@gmx.net mailto:mathias.froehl...@gmx.net Christian, On Thursday, February 23, 2012 15:18:42 Christian König wrote: The function radeon_bo_list_validate can cause a bo to move, resulting

Re: [drm-next 00/14] radeon_asic cleanups for drm-next

2012-02-24 Thread Christian König
On 23.02.2012 23:53, alexdeuc...@gmail.com wrote: From: Alex Deucheralexander.deuc...@amd.com This patch set cleans up radeon_asic and organizes the asic specific callbacks based on their function. Not change in functionality. It requires Christian's patch: drm/radeon: also make the cs_parse

[PATCH] drm/radeon: fix uninitialized variable

2012-02-28 Thread Christian König
Without this fix the driver randomly treats textures as arrays and I'm really wondering why gcc isn't complaining about it. Signed-off-by: Christian König deathsim...@vodafone.de --- drivers/gpu/drm/radeon/r600_cs.c |1 + 1 files changed, 1 insertions(+), 0 deletions(-) diff --git a/drivers

Re: [PATCH] drm/radeon: fix uninitialized variable

2012-02-29 Thread Christian König
On 29.02.2012 00:23, Jerome Glisse wrote: On Tue, 2012-02-28 at 23:19 +0100, Christian König wrote: Without this fix the driver randomly treats textures as arrays and I'm really wondering why gcc isn't complaining about it. Signed-off-by: Christian Königdeathsim...@vodafone.de --- drivers

[PATCH] drm/radeon: fix a semaphore deadlock on pre cayman asics

2012-03-07 Thread Christian König
The out of order execution of semaphore commands on pre cayman asics doesn't work correctly and can cause deadlocks, so turn it off for now. Signed-off-by: Christian König deathsim...@vodafone.de --- drivers/gpu/drm/radeon/r600.c |3 +++ drivers/gpu/drm/radeon/r600d.h |1 + 2 files

Re: [PATCH 00/48] Add SI, TN support

2012-03-21 Thread Christian König
perfectly, so both: Tested reviewed by Christian König christian.koe...@amd.com Alex Deucher (46): drm/radeon/kms: Upstream ObjectID.h updates drm/radeon/kms: upstream atombios.h updates drm/radeon/kms: upstream power table updates drm/radeon/kms: add SI chip families drm/radeon/kms

Re: [PATCH] drm/radeon/kms: add register definitions for audio

2012-03-29 Thread Christian König
with this new informations. Well, it's auto-generated, so you can't do much wrong, but anyway: Reviewed by: Christian König christian.koe...@amd.com On 28.03.2012 19:19, alexdeuc...@gmail.com wrote: From: Alex Deucheralexander.deuc...@amd.com This adds register definitions for HDMI/DP audio

[PATCH 2/4] drm/radeon: replace gpu_lockup with ring-ready flag

2012-04-11 Thread Christian König
It makes no sense at all to have more than one flag. Signed-off-by: Christian König deathsim...@vodafone.de --- drivers/gpu/drm/radeon/r100.c |1 - drivers/gpu/drm/radeon/r300.c |1 - drivers/gpu/drm/radeon/radeon.h|1 - drivers/gpu/drm/radeon

[PATCH 4/4] drm/radeon:use central function for IB testing

2012-04-11 Thread Christian König
Removing all the different error messages and having just one standard behaviour over all chipset generations. Signed-off-by: Christian König deathsim...@vodafone.de --- drivers/gpu/drm/radeon/evergreen.c |7 ++- drivers/gpu/drm/radeon/ni.c |7 ++- drivers/gpu/drm

[PATCH 1/4] drm/radeon: make radeon_gpu_is_lockup a per ring function

2012-04-11 Thread Christian König
Different rings have different criteria to test if they are stuck. Signed-off-by: Christian König deathsim...@vodafone.de --- drivers/gpu/drm/radeon/radeon.h |4 +- drivers/gpu/drm/radeon/radeon_asic.c | 36 +--- drivers/gpu/drm/radeon/radeon_fence.c

[PATCH 3/4] drm/radeon: register ring debugfs handlers on init

2012-04-11 Thread Christian König
Just register the debugfs files on init instead of checking the chipset type multiple times. Signed-off-by: Christian König deathsim...@vodafone.de --- drivers/gpu/drm/radeon/radeon_ring.c | 31 +++ 1 files changed, 19 insertions(+), 12 deletions(-) diff --git

Reworking of GPU reset logic

2012-04-19 Thread Christian König
This includes mostly fixes for multi ring lockups and GPU resets, but it should general improve the behavior of the kernel mode driver in case something goes badly wrong. On the other hand it completely rewrites the IB pool and semaphore handling, so I think there are still a couple of

[PATCH 01/13] drm/radeon: make radeon_gpu_is_lockup a per ring function

2012-04-19 Thread Christian König
Different rings have different criteria to test if they are stuck. v2: rebased on current drm-next Signed-off-by: Christian König deathsim...@vodafone.de Reviewed-by: Alex Deucher alexander.deuc...@amd.com --- drivers/gpu/drm/radeon/radeon.h |4 +- drivers/gpu/drm/radeon/radeon_asic.c

[PATCH 02/13] drm/radeon: replace gpu_lockup with ring-ready flag

2012-04-19 Thread Christian König
It makes no sense at all to have more than one flag. Signed-off-by: Christian König deathsim...@vodafone.de Reviewed-by: Alex Deucher alexander.deuc...@amd.com --- drivers/gpu/drm/radeon/r100.c |1 - drivers/gpu/drm/radeon/r300.c |1 - drivers/gpu/drm/radeon/radeon.h

[PATCH 03/13] drm/radeon: register ring debugfs handlers on init

2012-04-19 Thread Christian König
Just register the debugfs files on init instead of checking the chipset type multiple times. Signed-off-by: Christian König deathsim...@vodafone.de Reviewed-by: Alex Deucher alexander.deuc...@amd.com --- drivers/gpu/drm/radeon/radeon_ring.c | 31 +++ 1 files changed

[PATCH 06/13] drm/radeon: improve sub allocator

2012-04-19 Thread Christian König
Make the suballocator self containing to locking and fix a overrun bug which happens with allocations of different alignments. Signed-off-by: Christian König deathsim...@vodafone.de --- drivers/gpu/drm/radeon/radeon.h|1 + drivers/gpu/drm/radeon/radeon_sa.c | 19 --- 2

[PATCH 04/13] drm/radeon: use central function for IB testing

2012-04-19 Thread Christian König
Removing all the different error messages and having just one standard behaviour over all chipset generations. Signed-off-by: Christian König deathsim...@vodafone.de Reviewed-by: Alex Deucher alexander.deuc...@amd.com --- drivers/gpu/drm/radeon/evergreen.c |7 ++- drivers/gpu/drm

[PATCH 05/13] drm/radeon: rework gpu lockup detection and processing

2012-04-19 Thread Christian König
Previusly multiple ring could trigger multiple GPU resets at the same time. Signed-off-by: Christian König deathsim...@vodafone.de --- drivers/gpu/drm/radeon/radeon.h |3 +- drivers/gpu/drm/radeon/radeon_fence.c | 146 + 2 files changed, 75 insertions

[PATCH 07/13] drm/radeon: add sub allocator debugfs file

2012-04-19 Thread Christian König
Dumping the current allocations. Signed-off-by: Christian König deathsim...@vodafone.de --- drivers/gpu/drm/radeon/radeon_object.h |5 + drivers/gpu/drm/radeon/radeon_ring.c | 22 ++ drivers/gpu/drm/radeon/radeon_sa.c | 15 +++ 3 files changed

[PATCH 10/13] drm/radeon: return -ENOENT in fence_wait_*

2012-04-19 Thread Christian König
Signed-off-by: Christian König deathsim...@vodafone.de --- drivers/gpu/drm/radeon/radeon_fence.c |4 ++-- 1 files changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/radeon/radeon_fence.c b/drivers/gpu/drm/radeon/radeon_fence.c index 1a9765a..764ab7e 100644 --- a/drivers

[PATCH 08/13] drm/radeon: add biggest hole tracking and wakequeue to the sa

2012-04-19 Thread Christian König
With that in place clients are automatically blocking until their memory request can be handled. Signed-off-by: Christian König deathsim...@vodafone.de --- drivers/gpu/drm/radeon/radeon.h |5 +- drivers/gpu/drm/radeon/radeon_ring.c | 18 ++-- drivers/gpu/drm/radeon/radeon_sa.c

[PATCH 09/13] drm/radeon: simplify semaphore handling

2012-04-19 Thread Christian König
Directly use the suballocator to get small chunks of memory. It's equally fast and doesn't crash when we encounter a GPU reset. Signed-off-by: Christian König deathsim...@vodafone.de --- drivers/gpu/drm/radeon/evergreen.c|1 - drivers/gpu/drm/radeon/ni.c |1

[PATCH 12/13] drm/radeon: fix a bug with the ring syncing code

2012-04-19 Thread Christian König
Rings need to lock in order, otherwise the ring subsystem can deadlock. Signed-off-by: Christian König deathsim...@vodafone.de --- drivers/gpu/drm/radeon/radeon.h |4 ++ drivers/gpu/drm/radeon/radeon_cs.c| 33 ++ drivers/gpu/drm/radeon/radeon_semaphore.c

[PATCH 13/13] drm/radeon: rework recursive gpu reset handling

2012-04-19 Thread Christian König
Instead of all this humpy pumpy with recursive mutex (which also fixes only halve of the problem) move the actual gpu reset out of the fence code, return -EDEADLK and then reset the gpu in the calling ioctl function. Signed-off-by: Christian König deathsim...@vodafone.de --- drivers/gpu/drm

[PATCH 11/13] drm/radeon: rip out the ib pool

2012-04-19 Thread Christian König
It isn't necessary any more and the suballocator seems to perform even better. Signed-off-by: Christian König deathsim...@vodafone.de --- drivers/gpu/drm/radeon/radeon.h | 22 +-- drivers/gpu/drm/radeon/radeon_device.c|1 - drivers/gpu/drm/radeon/radeon_fence.c | 44

Re: [PATCH 10/13] drm/radeon: return -ENOENT in fence_wait_*

2012-04-20 Thread Christian König
On 20.04.2012 09:20, Michel Dänzer wrote: On Fre, 2012-04-20 at 00:39 +0200, Christian König wrote: Signed-off-by: Christian Königdeathsim...@vodafone.de --- drivers/gpu/drm/radeon/radeon_fence.c |4 ++-- 1 files changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm

Re: [PATCH 06/13] drm/radeon: improve sub allocator

2012-04-20 Thread Christian König
On 20.04.2012 09:24, Michel Dänzer wrote: On Fre, 2012-04-20 at 00:39 +0200, Christian König wrote: Make the suballocator self containing to locking and fix a overrun bug which happens with allocations of different alignments. Sounds like this should be split up into two changes. :) Yeah you

Re: [PATCH 13/13] drm/radeon: rework recursive gpu reset handling

2012-04-20 Thread Christian König
On 20.04.2012 09:50, Daniel Vetter wrote: On Fri, Apr 20, 2012 at 07:57:09AM +0100, Dave Airlie wrote: 2012/4/19 Christian Königdeathsim...@vodafone.de: Instead of all this humpy pumpy with recursive mutex (which also fixes only halve of the problem) move the actual gpu reset out of the fence

Re: [PATCH 10/13] drm/radeon: return -ENOENT in fence_wait_*

2012-04-20 Thread Christian König
On 20.04.2012 11:15, Michel Dänzer wrote: On Fre, 2012-04-20 at 10:49 +0200, Christian König wrote: On 20.04.2012 09:20, Michel Dänzer wrote: On Fre, 2012-04-20 at 00:39 +0200, Christian König wrote: Signed-off-by: Christian Königdeathsim...@vodafone.de --- drivers/gpu/drm/radeon

Re: Reworking of GPU reset logic

2012-04-21 Thread Christian König
On 20.04.2012 01:47, Jerome Glisse wrote: 2012/4/19 Christian Königdeathsim...@vodafone.de: This includes mostly fixes for multi ring lockups and GPU resets, but it should general improve the behavior of the kernel mode driver in case something goes badly wrong. On the other hand it

Re: VM lockdep warning

2012-04-21 Thread Christian König
Interesting, I'm pretty sure that I haven't touched the locking order of the cs_mutex vs. vm_mutex. Maybe it is just some kind of side effect, going to locking into it anyway. Christian. On 21.04.2012 13:39, Dave Airlie wrote: running 3.4.0-rc3 + Christian's reset patch series. The locks

Re: VM lockdep warning

2012-04-21 Thread Christian König
On 21.04.2012 16:08, Jerome Glisse wrote: 2012/4/21 Christian Königdeathsim...@vodafone.de: Interesting, I'm pretty sure that I haven't touched the locking order of the cs_mutex vs. vm_mutex. Maybe it is just some kind of side effect, going to locking into it anyway. Christian. It's the

Re: VM lockdep warning

2012-04-21 Thread Christian König
On 21.04.2012 17:57, Dave Airlie wrote: 2012/4/21 Jerome Glissej.gli...@gmail.com: 2012/4/21 Christian Königdeathsim...@vodafone.de: On 21.04.2012 16:08, Jerome Glisse wrote: 2012/4/21 Christian Königdeathsim...@vodafone.de: Interesting, I'm pretty sure that I haven't touched the locking

Re: VM lockdep warning

2012-04-21 Thread Christian König
On 21.04.2012 19:30, Jerome Glisse wrote: 2012/4/21 Christian Königdeathsim...@vodafone.de: On 21.04.2012 17:57, Dave Airlie wrote: 2012/4/21 Jerome Glissej.gli...@gmail.com: 2012/4/21 Christian Königdeathsim...@vodafone.de: On 21.04.2012 16:08, Jerome Glisse wrote: 2012/4/21 Christian

Re: [PATCH 12/13] drm/radeon: fix a bug with the ring syncing code

2012-04-24 Thread Christian König
On 24.04.2012 16:04, Dave Airlie wrote: 2012/4/19 Christian Königdeathsim...@vodafone.de: Rings need to lock in order, otherwise the ring subsystem can deadlock. No sure if its the commit or not but I was profiling on an r700 and saw it create a semaphore for ring syncing. surely the r700

[PATCH 02/26] drm/radeon: replace gpu_lockup with ring-ready flag

2012-04-25 Thread Christian König
It makes no sense at all to have more than one flag. Signed-off-by: Christian König deathsim...@vodafone.de Reviewed-by: Alex Deucher alexander.deuc...@amd.com --- drivers/gpu/drm/radeon/r100.c |1 - drivers/gpu/drm/radeon/r300.c |1 - drivers/gpu/drm/radeon/radeon.h

Re: Reworking of GPU reset logic

2012-04-25 Thread Christian König
Second round of patchset. Thanks for all the comments and/or bug reports, allot of patches are now v2/v3 and should get another look. Every regression known so far should be fixed with them now. Additionally to the patches that where already included in the last set there are 8 new ones which

[PATCH 04/26] drm/radeon: use central function for IB testing

2012-04-25 Thread Christian König
Removing all the different error messages and having just one standard behaviour over all chipset generations. Signed-off-by: Christian König deathsim...@vodafone.de Reviewed-by: Alex Deucher alexander.deuc...@amd.com --- drivers/gpu/drm/radeon/evergreen.c |7 ++- drivers/gpu/drm

[PATCH 03/26] drm/radeon: register ring debugfs handlers on init

2012-04-25 Thread Christian König
Just register the debugfs files on init instead of checking the chipset type multiple times. Signed-off-by: Christian König deathsim...@vodafone.de Reviewed-by: Alex Deucher alexander.deuc...@amd.com --- drivers/gpu/drm/radeon/radeon_ring.c | 31 +++ 1 files changed

[PATCH 01/26] drm/radeon: make radeon_gpu_is_lockup a per ring function

2012-04-25 Thread Christian König
Different rings have different criteria to test if they are stuck. v2: rebased on current drm-next Signed-off-by: Christian König deathsim...@vodafone.de Reviewed-by: Alex Deucher alexander.deuc...@amd.com --- drivers/gpu/drm/radeon/radeon.h |4 +- drivers/gpu/drm/radeon/radeon_asic.c

[PATCH 05/26] drm/radeon: rework gpu lockup detection and processing

2012-04-25 Thread Christian König
Previusly multiple rings could trigger multiple GPU resets at the same time. Signed-off-by: Christian König deathsim...@vodafone.de --- drivers/gpu/drm/radeon/radeon.h |3 +- drivers/gpu/drm/radeon/radeon_fence.c | 146 + 2 files changed, 75 insertions

[PATCH 06/26] drm/radeon: fix a critical bug in the SA code

2012-04-25 Thread Christian König
Aligning offset can make it bigger than tmp-offset leading to an overrun bug in the following subtraction. Signed-off-by: Christian König deathsim...@vodafone.de --- drivers/gpu/drm/radeon/radeon_sa.c |2 +- 1 files changed, 1 insertions(+), 1 deletions(-) diff --git a/drivers/gpu/drm

[PATCH 07/26] drm/radeon: add proper locking to the SA v2

2012-04-25 Thread Christian König
Make the suballocator self containing to locking. v2: split the bugfix into a seperate patch. Signed-off-by: Christian König deathsim...@vodafone.de --- drivers/gpu/drm/radeon/radeon.h|1 + drivers/gpu/drm/radeon/radeon_sa.c | 17 +++-- 2 files changed, 12 insertions(+), 6

[PATCH 08/26] drm/radeon: add sub allocator debugfs file

2012-04-25 Thread Christian König
Dumping the current allocations. Signed-off-by: Christian König deathsim...@vodafone.de --- drivers/gpu/drm/radeon/radeon_object.h |5 + drivers/gpu/drm/radeon/radeon_ring.c | 22 ++ drivers/gpu/drm/radeon/radeon_sa.c | 15 +++ 3 files changed

[PATCH 09/26] drm/radeon: add biggest hole tracking and wakequeue to the sa v3

2012-04-25 Thread Christian König
bug with biggest hole tracking. Signed-off-by: Christian König deathsim...@vodafone.de --- drivers/gpu/drm/radeon/radeon.h|5 +- drivers/gpu/drm/radeon/radeon_gart.c |2 +- drivers/gpu/drm/radeon/radeon_object.h |2 +- drivers/gpu/drm/radeon/radeon_ring.c | 20

[PATCH 11/26] drm/radeon: return -ENOENT in fence_wait_next v2

2012-04-25 Thread Christian König
We should signal the caller that we haven't waited at all. v2: only change fence_wait_next not fence_wait_last. Signed-off-by: Christian König deathsim...@vodafone.de --- drivers/gpu/drm/radeon/radeon_fence.c |2 +- 1 files changed, 1 insertions(+), 1 deletions(-) diff --git a/drivers/gpu

[PATCH 10/26] drm/radeon: simplify semaphore handling

2012-04-25 Thread Christian König
Directly use the suballocator to get small chunks of memory. It's equally fast and doesn't crash when we encounter a GPU reset. Signed-off-by: Christian König deathsim...@vodafone.de --- drivers/gpu/drm/radeon/evergreen.c|1 - drivers/gpu/drm/radeon/ni.c |1

[PATCH 12/26] drm/radeon: rename fence_wait_last to fence_wait_empty

2012-04-25 Thread Christian König
As discussed with Michel that name better describes the behavior of this function. Signed-off-by: Christian König deathsim...@vodafone.de --- drivers/gpu/drm/radeon/radeon.h|2 +- drivers/gpu/drm/radeon/radeon_device.c |2 +- drivers/gpu/drm/radeon/radeon_fence.c |4 ++-- 3

[PATCH 13/26] drm/radeon: rip out the ib pool

2012-04-25 Thread Christian König
It isn't necessary any more and the suballocator seems to perform even better. Signed-off-by: Christian König deathsim...@vodafone.de --- drivers/gpu/drm/radeon/radeon.h | 22 +-- drivers/gpu/drm/radeon/radeon_device.c|1 - drivers/gpu/drm/radeon/radeon_fence.c | 44

[PATCH 15/26] drm/radeon: rework recursive gpu reset handling

2012-04-25 Thread Christian König
if reset is successful. Signed-off-by: Christian König deathsim...@vodafone.de --- drivers/gpu/drm/radeon/radeon_cs.c | 13 + drivers/gpu/drm/radeon/radeon_device.c |5 - drivers/gpu/drm/radeon/radeon_fence.c | 10 +++--- drivers/gpu/drm/radeon/radeon_gem.c| 16

[PATCH 14/26] drm/radeon: fix a bug with the ring syncing code

2012-04-25 Thread Christian König
Rings need to lock in order, otherwise the ring subsystem can deadlock. v2: fix error handling and number of locked doublewords. v3: stop creating unneeded semaphores. Signed-off-by: Christian König deathsim...@vodafone.de --- drivers/gpu/drm/radeon/radeon.h |4 ++ drivers/gpu/drm

[PATCH 16/26] drm/radeon: remove recursive mutex implementation

2012-04-25 Thread Christian König
Not needed anymore. Signed-off-by: Christian König deathsim...@vodafone.de --- drivers/gpu/drm/radeon/radeon.h| 44 +--- drivers/gpu/drm/radeon/radeon_cs.c | 10 +++--- drivers/gpu/drm/radeon/radeon_device.c |2 +- drivers/gpu/drm/radeon

[PATCH 19/26] drm/radeon: unlock the ring mutex while waiting for the next fence

2012-04-25 Thread Christian König
Fixing just another deadlock problem with gpu reset tests. Signed-off-by: Christian König deathsim...@vodafone.de --- drivers/gpu/drm/radeon/radeon_ring.c |2 ++ 1 files changed, 2 insertions(+), 0 deletions(-) diff --git a/drivers/gpu/drm/radeon/radeon_ring.c b/drivers/gpu/drm/radeon

[PATCH 18/26] drm/radeon: make lockup timeout a module param

2012-04-25 Thread Christian König
Don't hard code the 10 seconds timeout. Compute jobs can run much longer. Signed-off-by: Christian König deathsim...@vodafone.de --- drivers/gpu/drm/radeon/radeon.h |1 + drivers/gpu/drm/radeon/radeon_drv.c |4 drivers/gpu/drm/radeon/radeon_ring.c |2 +- 3 files changed, 6

[PATCH 17/26] drm/radeon: move lockup detection code into radeon_ring.c

2012-04-25 Thread Christian König
It isn't chipset specific, so it makes no sense to have that inside r100.c. Signed-off-by: Christian König deathsim...@vodafone.de --- drivers/gpu/drm/radeon/evergreen.c |5 +-- drivers/gpu/drm/radeon/ni.c |5 +-- drivers/gpu/drm/radeon/r100.c| 57

[PATCH 21/26] drm/radeon: remove r300_gpu_is_lockup

2012-04-25 Thread Christian König
Since it is now identical to r100_gpu_is_lockup. Signed-off-by: Christian König deathsim...@vodafone.de --- drivers/gpu/drm/radeon/r300.c| 14 -- drivers/gpu/drm/radeon/radeon_asic.c | 16 drivers/gpu/drm/radeon/radeon_asic.h |1 - 3 files changed, 8

[PATCH 20/26] drm/radeon: make forcing ring activity a common function

2012-04-25 Thread Christian König
Nothing chipset or ring specific with it, so also move it to radon_ring. Signed-off-by: Christian König deathsim...@vodafone.de --- drivers/gpu/drm/radeon/evergreen.c | 10 +- drivers/gpu/drm/radeon/ni.c | 11 +-- drivers/gpu/drm/radeon/r100.c| 10

[PATCH 22/26] drm/radeon: remove cayman_gpu_is_lockup

2012-04-25 Thread Christian König
Since it is now identical to evergreen_gpu_is_lockup. Signed-off-by: Christian König deathsim...@vodafone.de --- drivers/gpu/drm/radeon/ni.c | 19 --- drivers/gpu/drm/radeon/radeon_asic.c | 12 ++-- drivers/gpu/drm/radeon/radeon_asic.h |1 - 3 files

[PATCH 23/26] drm/radeon: add missing locking to fence debugfs function

2012-04-25 Thread Christian König
Signed-off-by: Christian König deathsim...@vodafone.de --- drivers/gpu/drm/radeon/radeon_fence.c |3 +++ 1 files changed, 3 insertions(+), 0 deletions(-) diff --git a/drivers/gpu/drm/radeon/radeon_fence.c b/drivers/gpu/drm/radeon/radeon_fence.c index 66e6ee0..09e13e3 100644 --- a/drivers

[PATCH 24/26] drm/radeon: extend ring debugfs files with fence info

2012-04-25 Thread Christian König
That should aid in debugging multi ring lockups. Signed-off-by: Christian König deathsim...@vodafone.de --- drivers/gpu/drm/radeon/radeon.h |1 + drivers/gpu/drm/radeon/radeon_fence.c |1 + drivers/gpu/drm/radeon/radeon_ring.c | 43 - 3 files

[PATCH 26/26] drm/radeon: add the ib content and relocs to the ring debugfs file

2012-04-25 Thread Christian König
Signed-off-by: Christian König deathsim...@vodafone.de --- drivers/gpu/drm/radeon/radeon_ring.c | 22 ++ 1 files changed, 22 insertions(+), 0 deletions(-) diff --git a/drivers/gpu/drm/radeon/radeon_ring.c b/drivers/gpu/drm/radeon/radeon_ring.c index 1c4348c..c563c25 100644

[PATCH 25/26] drm/radeon: keep the cs relocs inside the ib

2012-04-25 Thread Christian König
Free them wenn the ib is freed, another step to better debugging. Signed-off-by: Christian König deathsim...@vodafone.de --- drivers/gpu/drm/radeon/radeon.h |3 +++ drivers/gpu/drm/radeon/radeon_cs.c | 14 -- drivers/gpu/drm/radeon/radeon_ring.c |3 +++ 3 files

Re: Reworking of GPU reset logic

2012-04-25 Thread Christian König
On 23.04.2012 09:40, Michel Dänzer wrote: On Sam, 2012-04-21 at 11:42 +0200, Christian König wrote: Regarding the debugging of lockups I had the following on my in mind todo list: 1. Rework the chip specific lockup detection code a bit more and probably clean it up a bit. 2. Make the timeout

Re: Reworking of GPU reset logic

2012-04-25 Thread Christian König
On 21.04.2012 16:14, Jerome Glisse wrote: 2012/4/21 Christian Königdeathsim...@vodafone.de: On 20.04.2012 01:47, Jerome Glisse wrote: 2012/4/19 Christian Königdeathsim...@vodafone.de: This includes mostly fixes for multi ring lockups and GPU resets, but it should general improve the behavior

Re: [PATCH 06/26] drm/radeon: fix a critical bug in the SA code

2012-04-25 Thread Christian König
On 25.04.2012 15:19, Michel Dänzer wrote: On Mit, 2012-04-25 at 14:46 +0200, Christian König wrote: Aligning offset can make it bigger than tmp-offset leading to an overrun bug in the following subtraction. Signed-off-by: Christian Königdeathsim...@vodafone.de Please add Cc: sta

Re: [PATCH 06/26] drm/radeon: fix a critical bug in the SA code

2012-04-25 Thread Christian König
On 25.04.2012 16:34, Jerome Glisse wrote: On Wed, Apr 25, 2012 at 9:40 AM, Alex Deucheralexdeuc...@gmail.com wrote: On Wed, Apr 25, 2012 at 9:19 AM, Michel Dänzermic...@daenzer.net wrote: On Mit, 2012-04-25 at 14:46 +0200, Christian König wrote: Aligning offset can make it bigger than tmp

Re: [PATCH 26/26] drm/radeon: add the ib content and relocs to the ring debugfs file

2012-04-25 Thread Christian König
On 25.04.2012 16:36, Jerome Glisse wrote: NAK i would rather have a full dump as i described. I can do a patch for that if you want. I don't stick with those files neither, just wanted to restore the same functionality as we had before. Just finished a conference call with Alex and the rest

Re: [PATCH 01/24] drm/radeon: remove fence/ring/ib debugfs files

2012-04-26 Thread Christian König
Hi Jerome, I totally agree that we can remove the following debugfs files, since everything that just prints out or modifies register informations doesn't belongs into the kernel driver and should be moved to radeontool instead. static int r100_debugfs_rbbm_info(struct seq_file *m, void

Re: [next][PATCH 0/5] radeon HDMI cleaning

2012-04-29 Thread Christian König
and also just tested on my RV710. So both: /Tested-by: //Christian König deathsim...@vodafone.de/ /Reviewed-by: Christian König deathsim...@vodafone.de /// ___ dri-devel mailing list dri-devel@lists.freedesktop.org http://lists.freedesktop.org/mailman

Re: [PATCH] drm/radeon/kms: need to set up ss on DP bridges as well

2012-04-29 Thread Christian König
= radeon_get_connector_for_encoder(encoder); Also gets the NUTMEG bridge on my llano board working, but DP on trinity is still problematic. Anyway: Tested-by: Christian König deathsim...@vodafone.de ___ dri-devel mailing list dri

Include request for reset-rework branch.

2012-04-30 Thread Christian König
Hi Dave, if nobody has a last moment concern please include the following patches in drm-next. Except for some minor fixes they have already been on the list for quite some time, but I intentional left out the debugfs related patches cause we haven't finished the discussion about them yet.

[PATCH 01/26] drm/radeon: make radeon_gpu_is_lockup a per ring function

2012-04-30 Thread Christian König
Different rings have different criteria to test if they are stuck. v2: rebased on current drm-next Signed-off-by: Christian König deathsim...@vodafone.de Reviewed-by: Alex Deucher alexander.deuc...@amd.com --- drivers/gpu/drm/radeon/radeon.h |4 +- drivers/gpu/drm/radeon/radeon_asic.c

[PATCH 03/26] drm/radeon: register ring debugfs handlers on init

2012-04-30 Thread Christian König
Just register the debugfs files on init instead of checking the chipset type multiple times. Signed-off-by: Christian König deathsim...@vodafone.de Reviewed-by: Alex Deucher alexander.deuc...@amd.com --- drivers/gpu/drm/radeon/radeon_ring.c | 31 +++ 1 files changed

[PATCH 02/26] drm/radeon: replace gpu_lockup with ring-ready flag

2012-04-30 Thread Christian König
It makes no sense at all to have more than one flag. Signed-off-by: Christian König deathsim...@vodafone.de Reviewed-by: Alex Deucher alexander.deuc...@amd.com --- drivers/gpu/drm/radeon/r100.c |1 - drivers/gpu/drm/radeon/r300.c |1 - drivers/gpu/drm/radeon/radeon.h

[PATCH 04/26] drm/radeon: use central function for IB testing

2012-04-30 Thread Christian König
Removing all the different error messages and having just one standard behaviour over all chipset generations. Signed-off-by: Christian König deathsim...@vodafone.de Reviewed-by: Alex Deucher alexander.deuc...@amd.com --- drivers/gpu/drm/radeon/evergreen.c |7 ++- drivers/gpu/drm

[PATCH 05/26] drm/radeon: rework gpu lockup detection and processing

2012-04-30 Thread Christian König
Previusly multiple rings could trigger multiple GPU resets at the same time. Signed-off-by: Christian König deathsim...@vodafone.de --- drivers/gpu/drm/radeon/radeon.h |3 +- drivers/gpu/drm/radeon/radeon_fence.c | 146 + 2 files changed, 75 insertions

[PATCH 06/26] drm/radeon: fix a bug in the SA code

2012-04-30 Thread Christian König
Aligning offset can make it bigger than tmp-offset leading to an overrun bug in the following subtraction. v2: Against initial suspicions this can't happen in mainline, so no need to push it into stable. Signed-off-by: Christian König deathsim...@vodafone.de Reviewed-by: Michel Dänzer

  1   2   3   4   5   6   7   8   9   10   >