CVE-2026-43253

In the Linux kernel, the following vulnerability has been resolved:

iommu/amd: move waitonsem() out of spinlock

With iommu.strict=1, the existing completion wait path can cause soft lockups under stressed environment, as waitonsem() busy-waits under the spinlock with interrupts disabled.

Move the completion wait in iommucompletionwait() out of the spinlock. waitonsem() only polls the hardware-updated cmd_sem and does not require iommu->lock, so holding the lock during the busy wait unnecessarily increases contention and extends the time with interrupts disabled.