This adds the infrastructure for an execution context for GEM buffers
which is similar to the existing TTMs execbuf util and intended to replace
it in the long term.
The basic functionality is that we abstracts the necessary loop to lock
many different GEM buffers with automated deadlock and dupli
Hi guys,
so well known patch set by now. I've tried to address all review
comments and extended the set to also replace
drm_gem_lock_reservations() as suggested by Thomas.
I won't have much time to work on this in the next few weeks, so feel
free to pick up this work and commit it when you need i
Largely just the initial skeleton.
v2: add array test as well
Signed-off-by: Christian König
---
drivers/gpu/drm/Kconfig | 1 +
drivers/gpu/drm/tests/Makefile| 3 +-
drivers/gpu/drm/tests/drm_exec_test.c | 96 +++
3 files changed, 99 insertions(+)
Start using the new component here as well.
Signed-off-by: Christian König
---
drivers/gpu/drm/amd/amdgpu/amdgpu_csa.c | 42 ++
drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c | 77 +++--
2 files changed, 53 insertions(+), 66 deletions(-)
diff --git a/drivers/gpu/drm/amd
Use the new component here as well and remove the old handling.
v2: drop dupplicate handling
Signed-off-by: Christian König
---
drivers/gpu/drm/amd/amdgpu/amdgpu.h | 1 -
drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c | 71 ++-
drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.h | 5 +-
d
Start using the new component here as well.
Signed-off-by: Christian König
---
drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c | 86 +++--
1 file changed, 39 insertions(+), 47 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c
b/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.
Avoids quite a bit of logic and kmalloc overhead.
v2: fix multiple problems pointed out by Felix
Signed-off-by: Christian König
---
drivers/gpu/drm/amd/amdgpu/Kconfig| 1 +
drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h| 5 +-
.../gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c | 302
Just a straightforward conversion without any optimization.
Only compile tested for now.
Signed-off-by: Christian König
---
drivers/gpu/drm/qxl/Kconfig | 1 +
drivers/gpu/drm/qxl/qxl_drv.h | 7 ++--
drivers/gpu/drm/qxl/qxl_release.c | 67 ---
3 files chan
Just a straightforward conversion without any optimization.
Signed-off-by: Christian König
---
drivers/gpu/drm/radeon/Kconfig | 1 +
drivers/gpu/drm/radeon/radeon.h| 7 ++--
drivers/gpu/drm/radeon/radeon_cs.c | 45 +-
drivers/gpu/drm/radeon/radeon_ge
Just a straightforward conversion without any optimization.
Only compile tested for now.
Signed-off-by: Christian König
---
drivers/gpu/drm/lima/Kconfig| 1 +
drivers/gpu/drm/lima/lima_gem.c | 15 +++
2 files changed, 8 insertions(+), 8 deletions(-)
diff --git a/drivers/gpu/dr
Just a straightforward conversion without any optimization.
Only compile tested for now.
Signed-off-by: Christian König
---
drivers/gpu/drm/panfrost/Kconfig| 1 +
drivers/gpu/drm/panfrost/panfrost_job.c | 11 ++-
2 files changed, 7 insertions(+), 5 deletions(-)
diff --git a/dr
Not used any more.
Signed-off-by: Christian König
---
drivers/gpu/drm/drm_gem.c | 78 --
drivers/gpu/drm/scheduler/sched_main.c | 5 +-
include/drm/drm_gem.h | 4 --
3 files changed, 2 insertions(+), 85 deletions(-)
diff --git a/drivers/gp
Just a straightforward conversion without any optimization.
Only compile tested for now.
Signed-off-by: Christian König
---
drivers/gpu/drm/virtio/Kconfig | 1 +
drivers/gpu/drm/virtio/virtgpu_drv.h | 3 ++-
drivers/gpu/drm/virtio/virtgpu_gem.c | 29 +++-
3 files
Just a straightforward conversion without any optimization.
Only compile tested for now.
Signed-off-by: Christian König
---
drivers/gpu/drm/v3d/v3d_gem.c | 43 ---
1 file changed, 19 insertions(+), 24 deletions(-)
diff --git a/drivers/gpu/drm/v3d/v3d_gem.c b/dri
Hi Christian,
It would be nice if you use the KUnit macros, instead of pr_info.
On 5/4/23 08:51, Christian König wrote:
Largely just the initial skeleton.
v2: add array test as well
Signed-off-by: Christian König
---
drivers/gpu/drm/Kconfig | 1 +
drivers/gpu/drm/tests/Make
The Board of Directors election and the vote on the By-laws concluded at
14:00 UTC on May 1st 2023 and these are the results:
- We had 75 members this year, of which 55 cast a vote, so the turnout
is 73.3%.
- On the question "Do you accept the proposed By-Law changes to make SFC
the new fiscal sp
Hi Maira,
Am 04.05.23 um 14:07 schrieb Maíra Canal:
Hi Christian,
It would be nice if you use the KUnit macros, instead of pr_info.
yeah this was initially written before the DRM tests moved to KUnit and
I only quickly converted it over. Going to give this a cleanup.
Thanks,
Christian.
On 5/4/23 13:51, Christian König wrote:
This adds the infrastructure for an execution context for GEM buffers
which is similar to the existing TTMs execbuf util and intended to replace
it in the long term.
The basic functionality is that we abstracts the necessary loop to lock
many different G
vm_inv_engs should be changd accordingly.
Signed-off-by: Yifan Zhang
---
drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c | 8 +---
1 file changed, 5 insertions(+), 3 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
index 8c8a2f37ba33..eeaa
tlb flush has to be changed for the new mmhub layout
Signed-off-by: Yifan Zhang
---
drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c | 16
drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c | 10 +++---
2 files changed, 19 insertions(+), 7 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu
Maybe add:
Fixes: dc267018dac1 ("drm/amdgpu: introduce vmhub definition for
multi-partition cases (v3)")
to the series. With that, the series is:
Reviewed-by: Alex Deucher
Alex
On Thu, May 4, 2023 at 11:51 AM Yifan Zhang wrote:
>
> tlb flush has to be changed for the new mmhub layout
>
> Signe
tree/branch:
https://git.kernel.org/pub/scm/linux/kernel/git/next/linux-next.git master
branch HEAD: 145e5cddfe8b4bf607510b2dcf630d95f4db420f Add linux-next specific
files for 20230504
Error/Warning reports:
https://lore.kernel.org/oe-kbuild-all/202304102354.q4voxgte-...@intel.com
https
v1: Vmbo->shadow is used to back vram bo up when vram lost. So that we
should set shadow as vmbo->shadow to recover vmbo->bo
v2: Modify if(vmbo->shadow) shadow = vmbo->shadow as if(!vmbo->shadow)
continue;
Fix: 'commit e18aaea733da ("drm/amdgpu: move shadow_list to amdgpu_bo_vm")'
Signed-off-by: L
From: Le Ma
As the layout of VMHUB definition has been changed to cover multiple
XCD/AID case, the original num_vmhubs is not appropriate to do vmhub
iteration any more.
Drop num_vmhubs and introduce vmhubs_mask instead.
v2: switch to the new VMHUB layout
v3: use DECLARE_BITMAP to define vmhubs
From: Shiwu Zhang
There are AMDGPU_MAX_VMHUBS of vmhub in maximum and need to init the
vm_inv_engs for all of them.
In this way, the below error can be ruled out.
[ 217.317752] amdgpu :02:00.0: amdgpu: no VM inv eng for ring sdma0
Signed-off-by: Shiwu Zhang
Reviewed-by: Christian Koenig
This patch is to enable vmhub bitmask on gmc11.
Signed-off-by: Yifan Zhang
---
drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c | 5 +++--
1 file changed, 3 insertions(+), 2 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c
b/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c
index 90cf79f8ddde..b669
to facilitate debugging.
Signed-off-by: Yifan Zhang
---
drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
index a4ba2c50a5c3..abdc2923cb62 100644
--- a
The number of kernel queues has impact on the latency under sriov
usecase. So to reduce the latency we set the default num_kcq = 2 under
sriov if not set manually.
Signed-off-by: YuBiao Wang
---
drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c | 3 +++
1 file changed, 3 insertions(+)
diff --git a/drive
28 matches
Mail list logo
