[PATCH v2] eal: fix DMA mask validation inconsistency in IOVA VA
Thomas Monjalon
thomas at monjalon.net
Fri Sep 19 12:41:40 CEST 2025
18/09/2025 09:55, Shani Peretz:
> From: Shani Peretz <shperetz at nvidia.com>
> >
> > When --iova-mode is explicitly specified in command line, DMA mask
> > constraints were not being validated, leading to potential runtime failures
> > when device DMA capabilities are exceeded.
> >
> > The issue occurred because rte_bus_get_iommu_class() was only called during
> > IOVA mode auto-detection, but this function has the important side effect of
> > triggering DMA mask detection (e.g., Intel IOMMU address width checking via
> > pci_device_iommu_support_va()).
> >
> > This created an inconsistency, when choosing explicit mode, the DMA checks
> > are bypassed, but when choosing auto-detection mode, the constraints are
> > checked and enforced.
> >
> > The fix moves rte_bus_get_iommu_class() outside the conditional logic to
> > ensure it's always called during EAL initialization.
> >
> > Fixes: 4374ebc24bc1 ("malloc: modify error message for DMA mask check")
> > Cc: stable at dpdk.org
> >
> > Signed-off-by: Shani Peretz <shperetz at nvidia.com>
>
> Rebased on latest main. Patch was already acked
>
> Acked-by: Anatoly Burakov <anatoly.burakov at intel.com>
Applied, thanks.
More information about the stable
mailing list