similar to: [PATCH 1/2] drm/nouveau: don't fini scheduler if not initialized

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. >

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.

"struct nouveau_job_ops" is not modified in these drivers. Constifying this structure moves some data to a read-only section, so increase overall security. In order to do it, "struct nouveau_job" and "struct nouveau_job_args" also need to be adjusted to this new const qualifier. On a x86_64, with allmodconfig: Before: ====== text data bss dec hex

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

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

Hi I''m working actually on a project about Qos configuration on a linux computer. I need to access (read/write) at the informations generated by the "tc" command. I think that these informations are in the /proc/net/psched file, but I only got 4 hexadecimal number in it.. Can anyone help me? David

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

Hi, I''m trying to share internet on a LAN I''ve a linux router with SQUID (with ZPH support) + FAIRNAT The idea is: - fairness sharing internet - priorize interactive traffic - if a web object is on squid-cache (HIT), user can download it, with a rate = LAN rate I''ve: - Last Fairnat Script: www.metamorpher.de/fairnat/ - SQUID 2.5STABLE5 with ZPH patch

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

Using the kernel global workqueue to signal fences can lead to unexpected deadlocks. Some other work (e.g. from a different driver) could directly or indirectly depend on this fence to be signaled. However, if the WQ_MAX_ACTIVE limit is reached by waiters, this can prevent the work signaling the fence from running. While this seems fairly unlikely, it's potentially exploitable. Fixes:

On Fri, Feb 23, 2024 at 10:14:53AM +1000, Dave Airlie wrote: > On Fri, 23 Feb 2024 at 00:45, Danilo Krummrich <dakr at redhat.com> wrote: > > > > Using the kernel global workqueue to signal fences can lead to > > unexpected deadlocks. Some other work (e.g. from a different driver) > > could directly or indirectly depend on this fence to be signaled. > >

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

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

From: Colin Ian King <colin.king at canonical.com> The NOUVEAU_GETPARAM_PCI_DEVICE case is missing a break statement and falls through to the following NOUVEAU_GETPARAM_BUS_TYPE case and may end up re-assigning the getparam->value to an undesired value. Fix this by adding in the missing break. Detected by CoverityScan, CID#1460507 ("Missing break in switch") Fixes:

From: Emil Velikov <emil.velikov at collabora.com> Cc: Ben Skeggs <bskeggs at redhat.com> Cc: nouveau at lists.freedesktop.org Signed-off-by: Emil Velikov <emil.velikov at collabora.com> --- drivers/gpu/drm/nouveau/nouveau_abi16.c | 6 ------ drivers/gpu/drm/nouveau/nouveau_abi16.h | 1 - drivers/gpu/drm/nouveau/nouveau_drm.c | 2 +- 3 files changed, 1 insertion(+), 8

The ffsll function is a lot slower than the __ffs64 built-in which compiles to a single instruction on 64-bit. It's also nice to avoid custom versions of standard functions. Note that __ffs == ffs - 1. Signed-off-by: Ilia Mirkin <imirkin at alum.mit.edu> --- I wrote a user-space program to test these out and make sure that the functions behaved as expected. The logic in abi16 had to be