pci_dev_reset_iommu_done(9)

πŸ“¦ version 7.3.1, in nixpkgs unstable

πŸŽ€ NAME πŸŽ€

Okay so this page is pci_dev_reset_iommu_done(9) from the Kernel API Manual, and the whole name vibe is: pci_dev_reset_iommu_done β€” restore IOMMU after a PCI device reset is done. πŸ’…

✨ SYNOPSIS ✨

The signature is giving one-line wonder:

void pci_dev_reset_iommu_done (struct pci_dev *pdev );

🫢 ARGUMENTS 🫢

  • pdev β€” PCI device that has finished a reset routine. 🫢

πŸ’– DESCRIPTION πŸ’–

So picture it: a PCIe device has just finished a reset routine, and it wants to restore its IOMMU activity β€” including new translation and cache invalidation β€” by re-attaching all RID/PASID of the device back to the domains retained in the core-level structure. ✨

Caller rule, no skipping: you must pair this with a successful pci_dev_reset_iommu_prepare. 🫢

Heads up bestie: even though it’s unlikely, there is a risk that re-attaching domains might fail due to some unexpected happening like OOM. 😭 So yeah, not every attach era is guaranteed-slay.

🌈 SEE ALSO 🌈

Kernel file: ./drivers/iommu/iommu.c β€” and the whole SEE ALSO squad is:

Okay that’s the whole page! Signing off from ./drivers/iommu, dated October 2026, on pci_dev_reset_iommu_done(9) in the Kernel API Manual. Stay slay, bestie. πŸŽ€βœ¨

πŸ“¦ where this page comes from