similar to: [PATCH] drm/nouveau: Constify struct nouveau_job_ops

nouveau_abi16_ioctl_channel_alloc() and nouveau_cli_init() simply call their corresponding *_fini() counterpart. This can lead to nouveau_sched_fini() being called without struct nouveau_sched ever being initialized in the first place. Instead of embedding struct nouveau_sched into struct nouveau_cli and struct nouveau_chan_abi16, allocate struct nouveau_sched separately, such that we can check

If a sched job depends on a dma-fence from a job from the same GPU scheduler instance, but a different scheduler entity, the GPU scheduler does only wait for the particular job to be scheduled, rather than for the job to fully complete. This is due to the GPU scheduler assuming that there is a scheduler instance per ring. However, the current implementation, in order to avoid arbitrary amounts of

nouveau_fence_emit() can fail before and after initializing the dma-fence and hence before and after initializing the dma-fence' kref. In order to avoid nouveau_fence_emit() potentially failing before dma-fence initialization pass the channel to nouveau_fence_new() already and perform the required check before even allocating the fence. While at it, restore the original behavior of

Currently, NO_PREFETCH is passed implicitly through drm_nouveau_gem_pushbuf_push::length and drm_nouveau_exec_push::va_len. Since this is a direct representation of how the HW is programmed it isn't really future proof for a uAPI. Hence, fix this up for the new uAPI and split up the va_len field of struct drm_nouveau_exec_push, such that we keep 32bit for va_len and 32bit for flags. For

On Tue, Aug 22, 2023 at 6:41?PM Danilo Krummrich <dakr at redhat.com> wrote: > Currently, NO_PREFETCH is passed implicitly through > drm_nouveau_gem_pushbuf_push::length and drm_nouveau_exec_push::va_len. > > Since this is a direct representation of how the HW is programmed it > isn't really future proof for a uAPI. Hence, fix this up for the new > uAPI and split up

Currently, NO_PREFETCH is passed implicitly through drm_nouveau_gem_pushbuf_push::length and drm_nouveau_exec_push::va_len. Since this is a direct representation of how the HW is programmed it isn't really future proof for a uAPI. Hence, fix this up for the new uAPI and split up the va_len field of struct drm_nouveau_exec_push, such that we keep 32bit for va_len and 32bit for flags. For

So far the DRM GPUVA manager offers common infrastructure to track GPU VA allocations and mappings, generically connect GPU VA mappings to their backing buffers and perform more complex mapping operations on the GPU VA space. However, there are more design patterns commonly used by drivers, which can potentially be generalized in order to make the DRM GPUVA manager represent a basic GPU-VM

nouveau_sched_init() uses the function drm_sched_init(). The latter function has parameters called "hang_limit" and "timeout" in its API documentation. nouveau_sched_init(), however, defines a variable called "job_hang_limit" which is passed to drm_sched_init()'s "timeout" parameter. The actual "hang_limit" parameter is directly set to 0.

nouveau_sched_init() uses the function drm_sched_init(). The latter function has parameters called "hang_limit" and "timeout" in its API documentation. nouveau_sched_init(), however, defines a variable called "job_hang_limit" which is passed to drm_sched_init()'s "timeout" parameter. The actual "hang_limit" parameter is directly set to 0.

From: Dave Airlie <airlied at redhat.com> dEQP-VK.sparse_resources.image_rebind.2d_array.r64i.128_128_8 was causing a remap operation like the below. op_remap: prev: 0000003fffed0000 00000000000f0000 00000000a5abd18a 0000000000000000 op_remap: next: op_remap: unmap: 0000003fffed0000 0000000000100000 0 op_map: map: 0000003ffffc0000 0000000000010000 000000005b1ba33c 00000000000e0000 This

Implement reference counting for struct drm_gpuvm. Signed-off-by: Danilo Krummrich <dakr at redhat.com> --- drivers/gpu/drm/drm_gpuvm.c | 56 +++++++++++++++++++++----- drivers/gpu/drm/nouveau/nouveau_uvmm.c | 20 ++++++--- include/drm/drm_gpuvm.h | 31 +++++++++++++- 3 files changed, 90 insertions(+), 17 deletions(-) diff --git a/drivers/gpu/drm/drm_gpuvm.c

From: Dave Airlie <airlied at redhat.com> When a buffer is evicted for memory pressure or TTM evict all, the placement is set to the eviction domain, this means the buffer never gets revalidated on the next exec to the correct domain. I think this should be fine to use the initial domain from the object creation, as least with VM_BIND this won't change after init so this should be the

On Fri, 2024-02-02 at 17:14 +0000, Timur Tabi wrote: > On Fri, 2024-02-02 at 01:05 +0100, Danilo Krummrich wrote: > > nouveau_abi16_ioctl_channel_alloc() and nouveau_cli_init() simply call > > their corresponding *_fini() counterpart. This can lead to > > nouveau_sched_fini() being called without struct nouveau_sched ever > > being initialized in the first place. >