public inbox for iommu@lists.linux-foundation.org
 help / color / mirror / Atom feed
* [PATCH v2 0/2] iommu/vt-d: Skip dev-iotlb flush for inaccessible PCIe device
@ 2025-12-11  3:59 Jinhui Guo
  2025-12-11  3:59 ` [PATCH v2 1/2] iommu/vt-d: Skip dev-iotlb flush for inaccessible PCIe device without scalable mode Jinhui Guo
                   ` (3 more replies)
  0 siblings, 4 replies; 12+ messages in thread
From: Jinhui Guo @ 2025-12-11  3:59 UTC (permalink / raw)
  To: dwmw2, baolu.lu, joro, will; +Cc: guojinhui.liam, iommu, linux-kernel, stable

Hi, all

We hit hard-lockups when the Intel IOMMU waits indefinitely for an ATS invalidation
that cannot complete, especially under GDR high-load conditions.

1. Hard-lock when a passthrough PCIe NIC with ATS enabled link-down in Intel IOMMU
   non-scalable mode. Two scenarios exist: NIC link-down with an explicit link-down
   event and link-down without any event.

   a) NIC link-down with an explicit link-dow event.
      Call Trace:
       qi_submit_sync
       qi_flush_dev_iotlb
       __context_flush_dev_iotlb.part.0
       domain_context_clear_one_cb
       pci_for_each_dma_alias
       device_block_translation
       blocking_domain_attach_dev
       iommu_deinit_device
       __iommu_group_remove_device
       iommu_release_device
       iommu_bus_notifier
       blocking_notifier_call_chain
       bus_notify
       device_del
       pci_remove_bus_device
       pci_stop_and_remove_bus_device
       pciehp_unconfigure_device
       pciehp_disable_slot
       pciehp_handle_presence_or_link_change
       pciehp_ist

   b) NIC link-down without an event - hard-lock on VM destroy.
      Call Trace:
       qi_submit_sync
       qi_flush_dev_iotlb
       __context_flush_dev_iotlb.part.0
       domain_context_clear_one_cb
       pci_for_each_dma_alias
       device_block_translation
       blocking_domain_attach_dev
       __iommu_attach_device
       __iommu_device_set_domain
       __iommu_group_set_domain_internal
       iommu_detach_group
       vfio_iommu_type1_detach_group
       vfio_group_detach_container
       vfio_group_fops_release
       __fput

2. Hard-lock when a passthrough PCIe NIC with ATS enabled link-down in Intel IOMMU
   scalable mode; NIC link-down without an event hard-locks on VM destroy.
   Call Trace:
    qi_submit_sync
    qi_flush_dev_iotlb
    intel_pasid_tear_down_entry
    device_block_translation
    blocking_domain_attach_dev
    __iommu_attach_device
    __iommu_device_set_domain
    __iommu_group_set_domain_internal
    iommu_detach_group
    vfio_iommu_type1_detach_group
    vfio_group_detach_container
    vfio_group_fops_release
    __fput

Fix both issues with two patches:
1. Skip dev-IOTLB flush for inaccessible devices in __context_flush_dev_iotlb() using
   pci_device_is_present().
2. Use pci_device_is_present() instead of pci_dev_is_disconnected() to decide when to
   skip ATS invalidation in devtlb_invalidation_with_pasid().

Best Regards,
Jinhui

---
v1: https://lore.kernel.org/all/20251210171431.1589-1-guojinhui.liam@bytedance.com/

Changelog in v1 -> v2 (suggested by Baolu Lu)
 - Simplify the pci_device_is_present() check in __context_flush_dev_iotlb().
 - Add Cc: stable@vger.kernel.org to both patches.

Jinhui Guo (2):
  iommu/vt-d: Skip dev-iotlb flush for inaccessible PCIe device without
    scalable mode
  iommu/vt-d: Flush dev-IOTLB only when PCIe device is accessible in
    scalable mode

 drivers/iommu/intel/pasid.c | 11 ++++++++++-
 1 file changed, 10 insertions(+), 1 deletion(-)

-- 
2.20.1

^ permalink raw reply	[flat|nested] 12+ messages in thread

end of thread, other threads:[~2026-03-01  3:50 UTC | newest]

Thread overview: 12+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2025-12-11  3:59 [PATCH v2 0/2] iommu/vt-d: Skip dev-iotlb flush for inaccessible PCIe device Jinhui Guo
2025-12-11  3:59 ` [PATCH v2 1/2] iommu/vt-d: Skip dev-iotlb flush for inaccessible PCIe device without scalable mode Jinhui Guo
2025-12-11  3:59 ` [PATCH v2 2/2] iommu/vt-d: Flush dev-IOTLB only when PCIe device is accessible in " Jinhui Guo
2025-12-18  8:04   ` Tian, Kevin
2025-12-22 11:19     ` Jinhui Guo
2025-12-23  4:06       ` Baolu Lu
2025-12-23 14:58         ` Jinhui Guo
2025-12-24  3:08         ` Tian, Kevin
2026-02-10 23:39           ` Bjorn Helgaas
2026-02-27  1:44             ` Samiullah Khawaja
2026-01-20  6:49 ` [PATCH v2 0/2] iommu/vt-d: Skip dev-iotlb flush for inaccessible PCIe device Baolu Lu
2026-03-01  3:50 ` Ethan Zhao

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox