This bug was fixed in the package linux-nvidia-bos - 7.0.0-2024.25
---------------
linux-nvidia-bos (7.0.0-2024.25) resolute; urgency=medium
* resolute/linux-nvidia-bos: 7.0.0-2024.25 -proposed tracker (LP:
#2172849)
* ipv4: free inet_opt and ireq_opt after an RCU grace period (LP: #2172774)
- ipv4: free inet_opt and ireq_opt after an RCU grace period
* lan743x: use-after-free write in the RX checksum offload path
(LP: #2171561)
- net: lan743x: fix RX checksum use-after-free
* arm-smmu-v3: SVA does not enable hardware Access/Dirty updates, so GPU
writes to MADV_FREE memory hang or crawl on Vera (LP: #2172334)
- iommu/arm-smmu-v3-sva: Enable Hardware Access and Hardware Dirty bits
linux-nvidia-bos (7.0.0-2023.24) resolute; urgency=medium
* resolute/linux-nvidia-bos: 7.0.0-2023.24 -proposed tracker (LP:
#2171965)
* CXL: Restore Type 3 memory by accepting firmware-committed zero-size HDM
decoders (LP: #2171032)
- NVIDIA: VR: SAUCE: cxl: Do not reject committed zero-size HDM decoders
* sched/fair: Prevent runnable tasks from starving during cgroup
reweighting (LP: #2170798)
- sched/fair: Increase weight bits for avg_vruntime
- sched/fair: Revert 6d71a9c61604 ("sched/fair: Fix EEVDF entity placement
bug causing scheduling lag")
- sched/fair: Avoid overflow in enqueue_entity()
- sched/fair: Fix overflow in vruntime_eligible()
* [linux-nvidia]: selftests/bpf: verifier_ptr_to_buf and
verifier_raw_tp_writable fail on 7.0 (selftest backported without its
kernel change) (LP: #2170741)
- NVIDIA: SAUCE: selftests/bpf: Match 7.0 verifier message for negative
buffer offsets
* cxl: Kernel panic in cxl_probe_component_regs() when the CXL HDM cache
probes an unassigned BAR (LP: #2170528)
- NVIDIA: VR: SAUCE: cxl: Do not probe HDM registers on unassigned BARs
* [linux-nvidia]: nvme-rdma: GDS scatterlist can be undersized for GPU I/O
(LP: #2170268)
- NVIDIA: SAUCE: nvme-rdma: size NVFS SGL for GPU pages
- NVIDIA: SAUCE: nvme-rdma: size NVFS SGL per bio
* BPMP debugfs population significantly delays boot on Vera (LP: #2170236)
- firmware: tegra: bpmp: Allow BPMP debugfs population to be skipped
-- Jacob Martin <[email protected]> Tue, 03 Nov 2026 10:56:24
-0600
** Changed in: linux-nvidia-bos (Ubuntu Resolute)
Status: Fix Committed => Fix Released
--
You received this bug notification because you are a member of Ubuntu
Bugs, which is subscribed to Ubuntu.
https://bugs.launchpad.net/bugs/2172334
Title:
arm-smmu-v3: SVA does not enable hardware Access/Dirty updates, so GPU
writes to MADV_FREE memory hang or crawl on Vera
To manage notifications about this bug go to:
https://bugs.launchpad.net/ubuntu/+source/linux-nvidia-bos/+bug/2172334/+subscriptions
--
ubuntu-bugs mailing list
[email protected]
https://lists.ubuntu.com/mailman/listinfo/ubuntu-bugs
