Re: [PATCH 1/2] drm/ttm: Fix cached TTM page allocation.

-bit vm. Signed-off-by: Thomas Hellstrom thellst...@vmware.com Reviewed-by: Jerome Glisse jgli...@redhat.com --- drivers/gpu/drm/ttm/ttm_page_alloc.c |2 +- 1 files changed, 1 insertions(+), 1 deletions(-) diff --git a/drivers/gpu/drm/ttm/ttm_page_alloc.c b/drivers/gpu/drm/ttm

Re: [PATCH 2/2] drm/ttm: Fix ttm_page_alloc.c

On Wed, May 26, 2010 at 04:18:50PM +0200, Thomas Hellstrom wrote: Fix a number of typos misspellings and checkpatch.pl warnings. Replace [ttm] with TTM_PFX Signed-off-by: Thomas Hellstrom thellst...@vmware.com Reviewed-by: Jerome Glisse jgli...@redhat.com --- drivers/gpu/drm/ttm

Re: 2.6.33.2 kmalloc-8 slab leaks ~512 objects per second

On Wed, May 12, 2010 at 11:50:41AM +0100, Tvrtko Ursulin wrote: On Wednesday 12 May 2010 11:38:05 Tvrtko Ursulin wrote: [snip] I think it is DRM (radeon) related, leak stopped when I closed all X programs. I am compiling 2.6.33.3 right now and will soon reboot into it. Leak is still

Re: 2.6.34-rc5: Reported regressions from 2.6.33

On Wed, Apr 21, 2010 at 07:15:38AM +0200, Rafael J. Wysocki wrote: On Tuesday 20 April 2010, Nick Bowler wrote: On 05:15 Tue 20 Apr , Rafael J. Wysocki wrote: If you know of any other unresolved regressions from 2.6.33, please let us know either and we'll add them to the list. Also,

[PATCH] drm/radeon/kms: print GPU family and device id when loading

This will help figuring out GPU when looking at bugs log. Signed-off-by: Jerome Glisse jgli...@redhat.com --- drivers/gpu/drm/radeon/radeon_device.c | 53 +++- drivers/gpu/drm/radeon/radeon_family.h |3 +- 2 files changed, 54 insertions(+), 2 deletions(-) diff

[PATCH 03/13] drm/nouveau: update to TTM no_wait splitted argument

This patch update radeon to the new no_wait splitted argument TTM functionality. Compile tested only (but thing should run as there is no operating change from driver point of view) Signed-off-by: Jerome Glisse jgli...@redhat.com --- drivers/gpu/drm/nouveau/nouveau_bo.c | 45

[PATCH 01/13] drm/ttm: split no_wait argument in 2 GPU or reserve wait

, update to others driver are following in separate patches. Signed-off-by: Jerome Glisse jgli...@redhat.com --- drivers/gpu/drm/ttm/ttm_bo.c | 57 drivers/gpu/drm/ttm/ttm_bo_util.c |9 -- include/drm/ttm/ttm_bo_api.h |6 ++- include/drm/ttm

[PATCH 04/13] drm/vmwgfx: update to TTM no_wait splitted argument

This patch update radeon to the new no_wait splitted argument TTM functionality. Compile tested only (but thing should run as there is no operating change from driver point of view) Signed-off-by: Jerome Glisse jgli...@redhat.com --- drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c |4 ++-- drivers

[PATCH 09/13] drm/radeon/kms: don't initialize TTM io memory manager field

This isn't needed anymore with the new TTM fault callback Signed-off-by: Jerome Glisse jgli...@redhat.com --- drivers/gpu/drm/radeon/radeon_ttm.c | 13 + 1 files changed, 1 insertions(+), 12 deletions(-) diff --git a/drivers/gpu/drm/radeon/radeon_ttm.c b/drivers/gpu/drm/radeon

unmappable vram v8

Ok so here again this time ioremap is kept inside ttm so we don't waste ioremap when faulting page. Cheers, Jerome -- Download Intel#174; Parallel Studio Eval Try the new software tools for yourself. Speed compiling,

[PATCH 02/13] drm/radeon/kms: update to TTM no_wait splitted argument

This patch update radeon to the new no_wait splitted argument TTM functionality. Signed-off-by: Jerome Glisse jgli...@redhat.com --- drivers/gpu/drm/radeon/radeon_object.c |6 ++-- drivers/gpu/drm/radeon/radeon_ttm.c| 39 +-- 2 files changed, 24 insertions

[PATCH 11/13] drm/vmwgfx: don't initialize TTM io memory manager field

This isn't needed anymore with the new TTM fault callback Signed-off-by: Jerome Glisse jgli...@redhat.com --- drivers/gpu/drm/vmwgfx/vmwgfx_buffer.c |6 -- 1 files changed, 0 insertions(+), 6 deletions(-) diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_buffer.c b/drivers/gpu/drm/vmwgfx

[PATCH 05/13] drm/ttm: ttm_fault callback to allow driver to handle bo placement V6

needed but we don't necesarily need to ioremap in the callback but still allow driver to use static mapping Signed-off-by: Jerome Glisse jgli...@redhat.com --- drivers/gpu/drm/ttm/ttm_bo.c |7 ++- drivers/gpu/drm/ttm/ttm_bo_util.c | 124 ++-- drivers

[PATCH 13/13] drm/radeon/kms: enable use of unmappable VRAM V2

This patch enable the use of unmappable VRAM thanks to previous TTM infrastructure change. V2 update after io_mem_reserve/io_mem_free callback balancing Signed-off-by: Jerome Glisse jgli...@redhat.com --- drivers/gpu/drm/radeon/evergreen.c |5 - drivers/gpu/drm/radeon/r100.c |5

[PATCH 06/13] drm/radeon/kms: add support for new fault callback V7

io_mem_reserve/free change V6 callback is responsible for iomapping memory V7 move back iomapping to ttm Signed-off-by: Jerome Glisse jgli...@redhat.com --- drivers/gpu/drm/radeon/radeon_object.c | 26 +++- drivers/gpu/drm/radeon/radeon_object.h |2 +- drivers/gpu/drm/radeon/radeon_ttm.c

[PATCH 07/13] drm/nouveau/kms: add support for new TTM fault callback V5

tested on any hw. V2 don't derefence bo-mem.mm_node as it's not NULL only for VRAM or GTT V3 update after io_mem_reserve/io_mem_free callback balancing V4 callback has to ioremap V5 ioremap is done by ttm Signed-off-by: Jerome Glisse jgli...@redhat.com --- drivers/gpu/drm/nouveau/nouveau_bo.c

[PATCH 08/13] drm/vmwgfx: add support for new TTM fault callback V5

for VRAM or GTT V3 update after io_mem_reserve/io_mem_free callback balancing V4 callback has to ioremap V5 ioremap is done by TTM Signed-off-by: Jerome Glisse jgli...@redhat.com --- drivers/gpu/drm/vmwgfx/vmwgfx_buffer.c | 44 +-- 1 files changed, 41 insertions(+), 3

[PATCH 10/13] drm/nouveau/kms: don't initialize TTM io memory manager field

This isn't needed anymore with the new TTM fault callback Signed-off-by: Jerome Glisse jgli...@redhat.com --- drivers/gpu/drm/nouveau/nouveau_bo.c | 11 --- 1 files changed, 0 insertions(+), 11 deletions(-) diff --git a/drivers/gpu/drm/nouveau/nouveau_bo.c b/drivers/gpu/drm/nouveau

[PATCH 12/13] drm/ttm: remove io_ field from TTM V6

All TTM driver have been converted to new io_mem_reserve/free interface which allow driver to choose and return proper io base, offset to core TTM for ioremapping if necessary. This patch remove what is now deadcode. V2 adapt to match with change in first patch of the patchset V3 update after

radeondb capturing replaying GPU command stream

Hi all, So i pushed a new dump facility in libdrm, it will dump everything needed to replay a command stream you just need to set CS_BOF_DUMP to 1 but be aware that any application that you launch will than create a new file for each cs it sends and file can be several M or maybe even G if you

Re: radeondb capturing replaying GPU command stream

On Thu, Apr 08, 2010 at 11:09:33PM +0300, Pauli Nieminen wrote: On Thu, Apr 8, 2010 at 7:10 PM, Jerome Glisse gli...@freedesktop.org wrote: Hi all, So i pushed a new dump facility in libdrm, it will dump everything needed to replay a command stream you just need to set CS_BOF_DUMP to 1

[PATCH 11/13] drm/vmwgfx: don't initialize TTM io memory manager field

This isn't needed anymore with the new TTM fault callback Signed-off-by: Jerome Glisse jgli...@redhat.com --- drivers/gpu/drm/vmwgfx/vmwgfx_buffer.c |6 -- 1 files changed, 0 insertions(+), 6 deletions(-) diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_buffer.c b/drivers/gpu/drm/vmwgfx

[PATCH 04/13] drm/vmwgfx: update to TTM no_wait splitted argument

This patch update radeon to the new no_wait splitted argument TTM functionality. Compile tested only (but thing should run as there is no operating change from driver point of view) Signed-off-by: Jerome Glisse jgli...@redhat.com --- drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c |4 ++-- drivers

[PATCH 02/13] drm/radeon/kms: update to TTM no_wait splitted argument

This patch update radeon to the new no_wait splitted argument TTM functionality. Signed-off-by: Jerome Glisse jgli...@redhat.com --- drivers/gpu/drm/radeon/radeon_object.c |6 ++-- drivers/gpu/drm/radeon/radeon_ttm.c| 39 +-- 2 files changed, 24 insertions

unmappable vram V7

So here is i hope the last spawn of the patch serie, i drop the needs ioremap flag and callback is responsible for ioremapping memory and providing a valid virtual address this simplify TTM code. I haven't change the value of enum after removing dead flag, Thomas maybe you prefer to change the

[PATCH 06/13] drm/radeon/kms: add support for new fault callback V6

io_mem_reserve/free change V6 callback is responsible for iomapping memory Signed-off-by: Jerome Glisse jgli...@redhat.com --- drivers/gpu/drm/radeon/radeon_object.c | 26 +- drivers/gpu/drm/radeon/radeon_object.h |2 +- drivers/gpu/drm/radeon/radeon_ttm.c| 59

[PATCH 12/13] drm/ttm: remove io_ field from TTM V5

io_mem_reserve/io_mem_free callback balancing V4 adjust to minor cleanup V5 remove the needs ioremap flag Signed-off-by: Jerome Glisse jgli...@redhat.com --- drivers/gpu/drm/ttm/ttm_bo.c | 22 -- drivers/gpu/drm/ttm/ttm_bo_util.c | 80 ++--- include

[PATCH 10/13] drm/nouveau/kms: don't initialize TTM io memory manager field

This isn't needed anymore with the new TTM fault callback Signed-off-by: Jerome Glisse jgli...@redhat.com --- drivers/gpu/drm/nouveau/nouveau_bo.c | 11 --- 1 files changed, 0 insertions(+), 11 deletions(-) diff --git a/drivers/gpu/drm/nouveau/nouveau_bo.c b/drivers/gpu/drm/nouveau

[PATCH 03/13] drm/nouveau: update to TTM no_wait splitted argument

This patch update radeon to the new no_wait splitted argument TTM functionality. Compile tested only (but thing should run as there is no operating change from driver point of view) Signed-off-by: Jerome Glisse jgli...@redhat.com --- drivers/gpu/drm/nouveau/nouveau_bo.c | 45

[PATCH 01/13] drm/ttm: split no_wait argument in 2 GPU or reserve wait

, update to others driver are following in separate patches. Signed-off-by: Jerome Glisse jgli...@redhat.com --- drivers/gpu/drm/ttm/ttm_bo.c | 57 drivers/gpu/drm/ttm/ttm_bo_util.c |9 -- include/drm/ttm/ttm_bo_api.h |6 ++- include/drm/ttm

[PATCH 07/13] drm/nouveau/kms: add support for new TTM fault callback V4

tested on any hw. V2 don't derefence bo-mem.mm_node as it's not NULL only for VRAM or GTT V3 update after io_mem_reserve/io_mem_free callback balancing V4 callback has to ioremap Signed-off-by: Jerome Glisse jgli...@redhat.com --- drivers/gpu/drm/nouveau/nouveau_bo.c | 66

[PATCH 08/13] drm/vmwgfx: add support for new TTM fault callback V4

for VRAM or GTT V3 update after io_mem_reserve/io_mem_free callback balancing V4 callback has to ioremap Signed-off-by: Jerome Glisse jgli...@redhat.com --- drivers/gpu/drm/vmwgfx/vmwgfx_buffer.c | 49 ++-- 1 files changed, 46 insertions(+), 3 deletions(-) diff --git

[PATCH 09/13] drm/radeon/kms: don't initialize TTM io memory manager field

This isn't needed anymore with the new TTM fault callback Signed-off-by: Jerome Glisse jgli...@redhat.com --- drivers/gpu/drm/radeon/radeon_ttm.c | 13 + 1 files changed, 1 insertions(+), 12 deletions(-) diff --git a/drivers/gpu/drm/radeon/radeon_ttm.c b/drivers/gpu/drm/radeon

[PATCH 13/13] drm/radeon/kms: enable use of unmappable VRAM V2

This patch enable the use of unmappable VRAM thanks to previous TTM infrastructure change. V2 update after io_mem_reserve/io_mem_free callback balancing Signed-off-by: Jerome Glisse jgli...@redhat.com --- drivers/gpu/drm/radeon/evergreen.c |5 - drivers/gpu/drm/radeon/r100.c |5

Re: unmappable vram V6

On Mon, Apr 05, 2010 at 02:23:58PM +0200, Thomas Hellstrom wrote: Jerome Glisse wrote: So in these patchset i use bool instead of atomic remove empty line removal, and i hope addressed standing issues. Again only compile tested for nouveau vmwgfx. Tested this time only tested on RV710

Re: [PATCH 1/7] drm/ttm: add pool wc/uc page allocator V2

the loop prettier in get_num_unused_pages Based on Jerome Glisse's and Dave Airlie's pool allocator. Signed-off-by: Jerome Glisse jgli...@redhat.com Signed-off-by: Dave Airlie airl...@redhat.com Signed-off-by: Pauli Nieminen suok...@gmail.com I think there is only one issue left see below

Re: [PATCH 1/7] drm/ttm: add pool wc/uc page allocator V3

the loop prettier in get_num_unused_pages. * Moved pages_freed reseting inside the loop in ttm_page_pool_free. * Add warning comment about spinlock context in ttm_page_pool_free. Based on Jerome Glisse's and Dave Airlie's pool allocator. Signed-off-by: Jerome Glisse jgli...@redhat.com

AGP force use of scratch page

5b2469a7149280fb6866345cb6d3d395ee400cd8 Mon Sep 17 00:00:00 2001 From: Jerome Glisse jgli...@redhat.com Date: Thu, 1 Apr 2010 16:46:15 +0200 Subject: [PATCH] agp: force use of scratch page It seems that some AGP hardware can induce activity on bus after reporting being idle with the memory (preteching maybe). As new

Re: [git pull] drm fixes

On Tue, Mar 30, 2010 at 07:24:42AM -0700, Linus Torvalds wrote: On Tue, 30 Mar 2010, Dave Airlie wrote: Actually Linus, don't bother, consider this revoked, I'm going to kill the GPU reset code and re-send this tomorrow, its just a mess to get it back out of the tree at this point,

Re: [PATCH 1/7] drm/ttm: add pool wc/uc page allocator

they are required for something else. Based on Jerome Glisse's and Dave Airlie's pool allocator. Signed-off-by: Jerome Glisse jgli...@redhat.com Signed-off-by: Dave Airlie airl...@redhat.com Signed-off-by: Pauli Nieminen suok...@gmail.com I think using array rather than list would have make things

[PATCH 07/13] drm/nouveau/kms: add support for new TTM fault callback V3

tested on any hw. V2 don't derefence bo-mem.mm_node as it's not NULL only for VRAM or GTT V3 update after io_mem_reserve/io_mem_free callback balancing Signed-off-by: Jerome Glisse jgli...@redhat.com --- drivers/gpu/drm/nouveau/nouveau_bo.c | 51 ++ 1 files

unmappable vram V6

So in these patchset i use bool instead of atomic remove empty line removal, and i hope addressed standing issues. Again only compile tested for nouveau vmwgfx. Tested this time only tested on RV710 with special patch to force unmappable vram use.

[PATCH 12/13] drm/ttm: remove io_ field from TTM V4

io_mem_reserve/io_mem_free callback balancing V4 adjust to minor cleanup Signed-off-by: Jerome Glisse jgli...@redhat.com --- drivers/gpu/drm/ttm/ttm_bo.c | 22 -- drivers/gpu/drm/ttm/ttm_bo_util.c | 29 + include/drm/ttm/ttm_bo_driver.h

[PATCH 11/13] drm/vmwgfx: don't initialize TTM io memory manager field

This isn't needed anymore with the new TTM fault callback Signed-off-by: Jerome Glisse jgli...@redhat.com --- drivers/gpu/drm/vmwgfx/vmwgfx_buffer.c |6 -- 1 files changed, 0 insertions(+), 6 deletions(-) diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_buffer.c b/drivers/gpu/drm/vmwgfx

[PATCH 04/13] drm/vmwgfx: update to TTM no_wait splitted argument

This patch update radeon to the new no_wait splitted argument TTM functionality. Compile tested only (but thing should run as there is no operating change from driver point of view) Signed-off-by: Jerome Glisse jgli...@redhat.com --- drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c |4 ++-- drivers

[PATCH 08/13] drm/vmwgfx: add support for new TTM fault callback V3

for VRAM or GTT V3 update after io_mem_reserve/io_mem_free callback balancing Signed-off-by: Jerome Glisse jgli...@redhat.com --- drivers/gpu/drm/vmwgfx/vmwgfx_buffer.c | 40 +++- 1 files changed, 39 insertions(+), 1 deletions(-) diff --git a/drivers/gpu/drm/vmwgfx

[PATCH 10/13] drm/nouveau/kms: don't initialize TTM io memory manager field

This isn't needed anymore with the new TTM fault callback Signed-off-by: Jerome Glisse jgli...@redhat.com --- drivers/gpu/drm/nouveau/nouveau_bo.c | 11 --- 1 files changed, 0 insertions(+), 11 deletions(-) diff --git a/drivers/gpu/drm/nouveau/nouveau_bo.c b/drivers/gpu/drm/nouveau

[PATCH 06/13] drm/radeon/kms: add support for new fault callback V5

io_mem_reserve/free change Signed-off-by: Jerome Glisse jgli...@redhat.com --- drivers/gpu/drm/radeon/radeon_object.c | 26 - drivers/gpu/drm/radeon/radeon_object.h |2 +- drivers/gpu/drm/radeon/radeon_ttm.c| 47 +++- 3 files changed, 71 insertions(+), 4

[PATCH 02/13] drm/radeon/kms: update to TTM no_wait splitted argument

This patch update radeon to the new no_wait splitted argument TTM functionality. Signed-off-by: Jerome Glisse jgli...@redhat.com --- drivers/gpu/drm/radeon/radeon_object.c |6 ++-- drivers/gpu/drm/radeon/radeon_ttm.c| 39 +-- 2 files changed, 24 insertions

[PATCH 03/13] drm/nouveau: update to TTM no_wait splitted argument

This patch update radeon to the new no_wait splitted argument TTM functionality. Compile tested only (but thing should run as there is no operating change from driver point of view) Signed-off-by: Jerome Glisse jgli...@redhat.com --- drivers/gpu/drm/nouveau/nouveau_bo.c | 45

[PATCH 09/13] drm/radeon/kms: don't initialize TTM io memory manager field

This isn't needed anymore with the new TTM fault callback Signed-off-by: Jerome Glisse jgli...@redhat.com --- drivers/gpu/drm/radeon/radeon_ttm.c | 13 + 1 files changed, 1 insertions(+), 12 deletions(-) diff --git a/drivers/gpu/drm/radeon/radeon_ttm.c b/drivers/gpu/drm/radeon

[PATCH 01/13] drm/ttm: split no_wait argument in 2 GPU or reserve wait

, update to others driver are following in separate patches. Signed-off-by: Jerome Glisse jgli...@redhat.com --- drivers/gpu/drm/ttm/ttm_bo.c | 57 drivers/gpu/drm/ttm/ttm_bo_util.c |9 -- include/drm/ttm/ttm_bo_api.h |6 ++- include/drm/ttm

[PATCH 13/13] drm/radeon/kms: enable use of unmappable VRAM V2

This patch enable the use of unmappable VRAM thanks to previous TTM infrastructure change. V2 update after io_mem_reserve/io_mem_free callback balancing Signed-off-by: Jerome Glisse jgli...@redhat.com --- drivers/gpu/drm/radeon/evergreen.c |5 - drivers/gpu/drm/radeon/r100.c |5

[PATCH 05/13] drm/ttm: ttm_fault callback to allow driver to handle bo placement V4

as member is protected by reserve mecanism from concurent access Signed-off-by: Jerome Glisse jgli...@redhat.com --- drivers/gpu/drm/ttm/ttm_bo.c |7 ++- drivers/gpu/drm/ttm/ttm_bo_util.c | 98 ++-- drivers/gpu/drm/ttm/ttm_bo_vm.c | 41

unmappable vram V5

I think i have addressed all concern. Patch doesn't follow 80colons limit as their was discussion about dropping that on lkml. only compile tested on nouveau vmwgfx. Sorry for short mail but i wrote a lot longer one which got lost ... don't feel like rewriting it. Cheers, Jerome

[PATCH 04/14] drm/vmwgfx: update to TTM no_wait splitted argument

This patch update radeon to the new no_wait splitted argument TTM functionality. Compile tested only (but thing should run as there is no operating change from driver point of view) Signed-off-by: Jerome Glisse jgli...@redhat.com --- drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c |4 ++-- drivers

[PATCH 02/14] drm/radeon/kms: update to TTM no_wait splitted argument

This patch update radeon to the new no_wait splitted argument TTM functionality. Signed-off-by: Jerome Glisse jgli...@redhat.com --- drivers/gpu/drm/radeon/radeon_object.c |6 ++-- drivers/gpu/drm/radeon/radeon_ttm.c| 39 +-- 2 files changed, 24 insertions

[PATCH 06/14] drm/radeon/kms: add support for new fault callback V5

io_mem_reserve/free change Signed-off-by: Jerome Glisse jgli...@redhat.com --- drivers/gpu/drm/radeon/radeon_object.c | 26 - drivers/gpu/drm/radeon/radeon_object.h |2 +- drivers/gpu/drm/radeon/radeon_ttm.c| 47 +++- 3 files changed, 71 insertions(+), 4

[PATCH 10/14] drm/nouveau/kms: don't initialize TTM io memory manager field

This isn't needed anymore with the new TTM fault callback Signed-off-by: Jerome Glisse jgli...@redhat.com --- drivers/gpu/drm/nouveau/nouveau_bo.c | 11 --- 1 files changed, 0 insertions(+), 11 deletions(-) diff --git a/drivers/gpu/drm/nouveau/nouveau_bo.c b/drivers/gpu/drm/nouveau

[PATCH 09/14] drm/radeon/kms: don't initialize TTM io memory manager field

This isn't needed anymore with the new TTM fault callback Signed-off-by: Jerome Glisse jgli...@redhat.com --- drivers/gpu/drm/radeon/radeon_ttm.c | 13 + 1 files changed, 1 insertions(+), 12 deletions(-) diff --git a/drivers/gpu/drm/radeon/radeon_ttm.c b/drivers/gpu/drm/radeon

[PATCH 11/14] drm/vmwgfx: don't initialize TTM io memory manager field

This isn't needed anymore with the new TTM fault callback Signed-off-by: Jerome Glisse jgli...@redhat.com --- drivers/gpu/drm/vmwgfx/vmwgfx_buffer.c |6 -- 1 files changed, 0 insertions(+), 6 deletions(-) diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_buffer.c b/drivers/gpu/drm/vmwgfx

[PATCH 13/14] drm/radeon/kms: enable use of unmappable VRAM V2

This patch enable the use of unmappable VRAM thanks to previous TTM infrastructure change. V2 update after io_mem_reserve/io_mem_free callback balancing Signed-off-by: Jerome Glisse jgli...@redhat.com --- drivers/gpu/drm/radeon/evergreen.c |5 - drivers/gpu/drm/radeon/r100.c |5

[PATCH 08/14] drm/vmwgfx: add support for new TTM fault callback V3

for VRAM or GTT V3 update after io_mem_reserve/io_mem_free callback balancing Signed-off-by: Jerome Glisse jgli...@redhat.com --- drivers/gpu/drm/vmwgfx/vmwgfx_buffer.c | 40 +++- 1 files changed, 39 insertions(+), 1 deletions(-) diff --git a/drivers/gpu/drm/vmwgfx

[PATCH 03/14] drm/nouveau: update to TTM no_wait splitted argument

This patch update radeon to the new no_wait splitted argument TTM functionality. Compile tested only (but thing should run as there is no operating change from driver point of view) Signed-off-by: Jerome Glisse jgli...@redhat.com --- drivers/gpu/drm/nouveau/nouveau_bo.c | 45

[PATCH 07/14] drm/nouveau/kms: add support for new TTM fault callback V3

tested on any hw. V2 don't derefence bo-mem.mm_node as it's not NULL only for VRAM or GTT V3 update after io_mem_reserve/io_mem_free callback balancing Signed-off-by: Jerome Glisse jgli...@redhat.com --- drivers/gpu/drm/nouveau/nouveau_bo.c | 51 ++ 1 files

[PATCH 12/14] drm/ttm: remove io_ field from TTM V3

io_mem_reserve/io_mem_free callback balancing Signed-off-by: Jerome Glisse jgli...@redhat.com --- drivers/gpu/drm/ttm/ttm_bo.c | 22 -- drivers/gpu/drm/ttm/ttm_bo_util.c | 26 +++--- include/drm/ttm/ttm_bo_driver.h | 10 -- 3 files changed

[PATCH 01/14] drm/ttm: split no_wait argument in 2 GPU or reserve wait

, update to others driver are following in separate patches. Signed-off-by: Jerome Glisse jgli...@redhat.com --- drivers/gpu/drm/ttm/ttm_bo.c | 57 drivers/gpu/drm/ttm/ttm_bo_util.c |9 -- include/drm/ttm/ttm_bo_api.h |6 ++- include/drm/ttm

[PATCH] drm/ttm: ttm_fault callback to allow driver to handle bo placement V3

and remove the old path from TTM once driver are converted. V2 return VM_FAULT_NOPAGE if callback return -EBUSY or -ERESTARTSYS V3 balance io_mem_reserve and io_mem_free call, fault_reserve_notify is responsible to perform any necessary task for mapping to succeed Signed-off-by: Jerome Glisse jgli

Re: [PATCH] drm/ttm: ttm_fault callback to allow driver to handle bo placement V3

On Wed, Mar 24, 2010 at 07:27:57PM +0100, Thomas Hellstrom wrote: Jerome Glisse wrote: On fault the driver is given the opportunity to perform any operation it sees fit in order to place the buffer into a CPU visible area of memory. This patch doesn't break TTM users, nouveau, vmwgfx

Re: [PATCH] drm/ttm: ttm_fault callback to allow driver to handle bo placement V3

On Wed, Mar 24, 2010 at 09:08:08PM +0100, Thomas Hellstrom wrote: Jerome Glisse wrote: On Wed, Mar 24, 2010 at 07:27:57PM +0100, Thomas Hellstrom wrote: Jerome Glisse wrote: On fault the driver is given the opportunity to perform any operation it sees fit in order to place the buffer

Re: Unmappable VRAM patchset V4

On Mon, Mar 01, 2010 at 01:03:38PM +0100, Thomas Hellstrom wrote: Dave Airlie wrote: On Fri, Feb 26, 2010 at 3:01 AM, Jerome Glisse jgli...@redhat.com wrote: Updated patchset, to apply cleanly on top of TTM split no_wait argument. Compile tested for nouveau+vmwgfx, test in progress

[PATCH] drm/radeon/kms: avoid possible oops (call gart_fini before gart_disable)

radeon_gart_fini might call GART unbind callback function which might try to access GART table but if gart_disable is call first the GART table will be unmapped so any access to it will oops. Signed-off-by: Jerome Glisse jgli...@redhat.com --- drivers/gpu/drm/radeon/r100.c |2 +- drivers

Re: Unmappable VRAM patchset V4

On Wed, Mar 17, 2010 at 02:01:47PM +0100, Thomas Hellstrom wrote: Jerome Glisse wrote: On Mon, Mar 01, 2010 at 01:03:38PM +0100, Thomas Hellstrom wrote: Dave Airlie wrote: On Fri, Feb 26, 2010 at 3:01 AM, Jerome Glisse jgli...@redhat.com wrote: Updated patchset, to apply cleanly on top of TTM

[PATCH] drm/radeon/kms: fix typo in r520 asic functions

This will fix suspend/resume on r520 asic. Signed-off-by: Jerome Glisse jgli...@redhat.com --- drivers/gpu/drm/radeon/radeon_asic.c |4 ++-- 1 files changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/radeon/radeon_asic.c b/drivers/gpu/drm/radeon/radeon_asic.c index

Re: [PATCH 0/5] clean up radeon_asic.h v2

On Thu, Mar 11, 2010 at 10:19:13PM +0100, Daniel Vetter wrote: Hi all, All new patch pile to make radeon_asic.h into a real header file. Now all the asic structs are gathered in the new radeon_asic.c file. Tested on my rv570. I've also added a new patch that gathers all r100 specific

Re: [PATCH 00/14] cleanup radeon_asic.h

On Thu, Mar 11, 2010 at 02:06:02PM +0100, Daniel Vetter wrote: Hi all, This patch pile moves the static struct radeon_asic asic definitions form radeon_asic.h into the asic-specific files, where I think they belong. This way radeon_asic.h becomes a real header file that can be #included.

Re: [PATCH 00/14] cleanup radeon_asic.h

On Thu, Mar 11, 2010 at 05:24:22PM +0100, Rafał Miłecki wrote: 2010/3/11 Alex Deucher alexdeuc...@gmail.com: I like keeping all the asic definitions in one file as you tend to need to update them all at one time and having them spread across all the asic files increases the likelihood of

[PATCH 1/3] drm/radeon/kms: fence cleanup + more reliable GPU lockup detection V4

positive Signed-off-by: Jerome Glisse jgli...@redhat.com --- drivers/gpu/drm/radeon/evergreen.c|6 ++ drivers/gpu/drm/radeon/r100.c | 86 +++ drivers/gpu/drm/radeon/r300.c | 28 - drivers/gpu/drm/radeon/r600.c | 34

[PATCH 3/3] drm/radeon/kms: simplify improve GPU reset V2

cursor. Next step is to record the bogus command that leaded to the lockup. V2 Fix r6xx resume path to avoid reinitializing blit module, use the gpu_lockup boolean to avoid entering inifinite waiting loop on fence while reiniting the GPU Signed-off-by: Jerome Glisse jgli...@redhat.com

[PATCH 2/3] drm/radeon/kms: rename gpu_reset to asic_reset

Patch rename gpu_reset to asic_reset in prevision of having gpu_reset doing more stuff than just basic asic reset. Signed-off-by: Jerome Glisse jgli...@redhat.com --- drivers/gpu/drm/radeon/evergreen.c |2 +- drivers/gpu/drm/radeon/r100.c |6 ++-- drivers/gpu/drm/radeon/r300

Improved GPU reset

This serie of patch fix the shortcoming of the previous one, their shouldn't be any more false positive and resume should lead to infinite look or other reinitialization issue on r6xx/r7xx. Cheers, Jerome -- Download

Re: Improved GPU reset

On Sun, Mar 07, 2010 at 10:41:32AM +0100, Ladislav Kunc wrote: On Friday 05 March 2010 11:30:02 Jerome Glisse wrote: This patches improve the GPU reset, many time i able to successfully reset the GPU and carry on operation, note that after a reset you will likely see corrpution

Improved GPU reset

This patches improve the GPU reset, many time i able to successfully reset the GPU and carry on operation, note that after a reset you will likely see corrpution on the screen. Hope is that we should now be able to capture faulty command stream. I still need to do a full retesting with this patch

[PATCH 2/3] drm/radeon/kms: rename gpu_reset to asic_reset

Patch rename gpu_reset to asic_reset in prevision of having gpu_reset doing more stuff than just basic asic reset. Signed-off-by: Jerome Glisse jgli...@redhat.com --- drivers/gpu/drm/radeon/evergreen.c |2 +- drivers/gpu/drm/radeon/r100.c |6 ++-- drivers/gpu/drm/radeon/r300

[PATCH 3/3] drm/radeon/kms: simplify improve GPU reset

cursor. Next step is to record the bogus command that leaded to the lockup. Signed-off-by: Jerome Glisse jgli...@redhat.com --- drivers/gpu/drm/radeon/r100.c | 180 +++ drivers/gpu/drm/radeon/r100d.h | 128 ++ drivers/gpu/drm

Re: [git pull] drm request 3

On Fri, Mar 05, 2010 at 04:31:29PM +, Alan Cox wrote: On Fri, 05 Mar 2010 08:06:26 -0800 (PST) David Miller da...@davemloft.net wrote: From: Daniel Stone dan...@fooishbar.org Date: Fri, 5 Mar 2010 18:04:34 +0200 So you're saying that there's no way to develop any reasonable body

Re: TTM split no_wait argument in 2 (no_wait_reserve, no_wait_gpu)

On Thu, Feb 25, 2010 at 05:50:10PM +0100, Jerome Glisse wrote: This patch change the TTM API to allow driver to select btw choosing to wait or not either for bo reserve or GPU wait separately. This is needed for the unmappabled VRAM work. Comments ? Cheers, Jerome Thomas any chance you

Re: [RFC] drm/ttm: add pool wc/uc page allocator

On Wed, Mar 03, 2010 at 05:46:43PM +0200, Pauli Nieminen wrote: On Wed, Mar 3, 2010 at 4:50 PM, Jerome Glisse gli...@freedesktop.org wrote: On Wed, Mar 03, 2010 at 04:23:08PM +0200, Pauli Nieminen wrote: On Wed, Mar 3, 2010 at 3:33 PM, Jerome Glisse gli...@freedesktop.org wrote: On Tue

Re: [SPAM] [PATCH 1/3] drm/radeon/kms: fence cleanup + more reliable GPU lockup detection V2

On Tue, Mar 02, 2010 at 10:13:19AM +0100, Erik Andrén wrote: 2010/3/1 y: From: Jerome Glisse jgli...@redhat.com This patch cleanup the fence code, it drops the timeout field of fence as the time to complete each IB is unpredictable and shouldn't be bound. The fence cleanup lead

[PATCH] drm/radeon/kms: catch atombios infinite loop and break out of it

in the kernel context which is bad. Signed-off-by: Jerome Glisse jgli...@redhat.com --- drivers/gpu/drm/radeon/atom.c | 59 drivers/gpu/drm/radeon/atom.h |2 +- 2 files changed, 48 insertions(+), 13 deletions(-) diff --git a/drivers/gpu/drm/radeon/atom.c b

[PATCH 1/3] drm/radeon/kms: fence cleanup + more reliable GPU lockup detection V3

timeout. V2 switch to 500ms timeout so GPU lockup get call at least 2 times in less than 2sec. V3 store last jiffies in fence struct so on ERESTART, EBUSY we keep track of how long we already wait for a given fence Signed-off-by: Jerome Glisse jgli...@redhat.com --- drivers/gpu/drm/radeon

Re: [PATCH] drm/radeon/kms: fence cleanup + more reliable GPU lockup detection

On Mon, Mar 01, 2010 at 04:00:02PM +1000, Dave Airlie wrote: On Mon, Mar 1, 2010 at 2:47 AM, Jerome Glisse jgli...@redhat.com wrote: On Sun, Feb 28, 2010 at 12:22:52PM +, Alan Swanson wrote: On Fri, 2010-02-26 at 15:49 +0100, Jerome Glisse wrote: This patch cleanup the fence code

Re: Convert DRM_INFO/DRM_ERROR to dev_info/dev_err

On Mon, Mar 01, 2010 at 03:47:35PM +1000, Dave Airlie wrote: On Fri, Feb 26, 2010 at 4:56 AM, Jerome Glisse gli...@freedesktop.org wrote: Attached is conversion from DRM_INFO/DRM_ERROR to dev_info/dev_err to apply it copy all doconv* file into the radeon subfolder of the kernel run

Re: [PATCH 2/2] drm/ttm: don't write to bo-reserved without holding glob-lru_lock

On Mon, Mar 01, 2010 at 07:34:40PM +0100, Maarten Maathuis wrote: - The headerfile says you can't write to it without holding the lock. Signed-off-by: Maarten Maathuis madman2...@gmail.com NAK, from my POV as we always use atomic_* on reserved it's useless to protect it with spinlock.

Re: [PATCH 1/2] drm/ttm: remove some bo-mutex remains

On Mon, Mar 01, 2010 at 07:34:39PM +0100, Maarten Maathuis wrote: - A few comments existed here and there that referred to a bo-mutex. Signed-off-by: Maarten Maathuis madman2...@gmail.com Reviewed-by: Jerome Glisse jgli...@redhat.com --- drivers/gpu/drm/ttm/ttm_bo.c|6

Re: [PATCH] drm/radeon/kms: fence cleanup + more reliable GPU lockup detection

On Sun, Feb 28, 2010 at 12:22:52PM +, Alan Swanson wrote: On Fri, 2010-02-26 at 15:49 +0100, Jerome Glisse wrote: This patch cleanup the fence code, it drops the timeout field of fence as the time to complete each IB is unpredictable and shouldn't be bound. The fence cleanup lead

Re: [PATCH 1/2] drm/radeon/kms: rename gpu_reset to asic_reset V2

On Fri, Feb 26, 2010 at 10:33:34PM +0100, Jerome Glisse wrote: Patch rename gpu_reset to asic_reset in prevision of having gpu_reset doing more stuff than just basic asic reset. V2 store the last time we had new fence in the fence driver so on EBUSY/ERESTART we still keep accurate timing

[PATCH] drm/radeon/kms: fence cleanup + more reliable GPU lockup detection

timeout. Signed-off-by: Jerome Glisse jgli...@redhat.com --- drivers/gpu/drm/radeon/evergreen.c|6 ++ drivers/gpu/drm/radeon/r100.c | 84 +++ drivers/gpu/drm/radeon/r300.c | 27 - drivers/gpu/drm/radeon/r600.c | 33

[PATCH] drm/radeon/kms: initialize set_surface_reg reg for rs600 asic

rs600 asic was missing set_surface_reg callback leading to oops. Signed-off-by: Jerome Glisse jgli...@redhat.com --- drivers/gpu/drm/radeon/radeon_asic.h |2 ++ 1 files changed, 2 insertions(+), 0 deletions(-) diff --git a/drivers/gpu/drm/radeon/radeon_asic.h b/drivers/gpu/drm/radeon

[PATCH 1/2] drm/radeon/kms: rename gpu_reset to asic_reset V2

-off-by: Jerome Glisse jgli...@redhat.com --- drivers/gpu/drm/radeon/evergreen.c |2 +- drivers/gpu/drm/radeon/r100.c |6 ++-- drivers/gpu/drm/radeon/r300.c |6 ++-- drivers/gpu/drm/radeon/r420.c |4 +- drivers/gpu/drm/radeon/r520.c |4

  1   2   3   4   5   6   7   8   >