kernel.git/drivers/pci/iov.c, branch linux-6.17.y

PCI/IOV: Add PCI rescan-remove locking when enabling/disabling SR-IOV

2025-10-19T14:37:33Z

commit 05703271c3cdcc0f2a8cf6ebdc45892b8ca83520 upstream. Before disabling SR-IOV via config space accesses to the parent PF, sriov_disable() first removes the PCI devices representing the VFs. Since commit 9d16947b7583 ("PCI: Add global pci_lock_rescan_remove()") such removal operations are serialized against concurrent remove and rescan using the pci_rescan_remove_lock. No such locking was ever added in sriov_disable() however. In particular when commit 18f9e9d150fc ("PCI/IOV: Factor out sriov_add_vfs()") factored out the PCI device removal into sriov_del_vfs() there was still no locking around the pci_iov_remove_virtfn() calls. On s390 the lack of serialization in sriov_disable() may cause double remove and list corruption with the below (amended) trace being observed: PSW: 0704c00180000000 0000000c914e4b38 (klist_put+56) GPRS: 000003800313fb48 0000000000000000 0000000100000001 0000000000000001 00000000f9b520a8 0000000000000000 0000000000002fbd 00000000f4cc9480 0000000000000001 0000000000000000 0000000000000000 0000000180692828 00000000818e8000 000003800313fe2c 000003800313fb20 000003800313fad8 #0 [3800313fb20] device_del at c9158ad5c #1 [3800313fb88] pci_remove_bus_device at c915105ba #2 [3800313fbd0] pci_iov_remove_virtfn at c9152f198 #3 [3800313fc28] zpci_iov_remove_virtfn at c90fb67c0 #4 [3800313fc60] zpci_bus_remove_device at c90fb6104 #5 [3800313fca0] __zpci_event_availability at c90fb3dca #6 [3800313fd08] chsc_process_sei_nt0 at c918fe4a2 #7 [3800313fd60] crw_collect_info at c91905822 #8 [3800313fe10] kthread at c90feb390 #9 [3800313fe68] __ret_from_fork at c90f6aa64 #10 [3800313fe98] ret_from_fork at c9194f3f2. This is because in addition to sriov_disable() removing the VFs, the platform also generates hot-unplug events for the VFs. This being the reverse operation to the hotplug events generated by sriov_enable() and handled via pdev->no_vf_scan. And while the event processing takes pci_rescan_remove_lock and checks whether the struct pci_dev still exists, the lack of synchronization makes this checking racy. Other races may also be possible of course though given that this lack of locking persisted so long observable races seem very rare. Even on s390 the list corruption was only observed with certain devices since the platform events are only triggered by config accesses after the removal, so as long as the removal finished synchronously they would not race. Either way the locking is missing so fix this by adding it to the sriov_del_vfs() helper. Just like PCI rescan-remove, locking is also missing in sriov_add_vfs() including for the error case where pci_stop_and_remove_bus_device() is called without the PCI rescan-remove lock being held. Even in the non-error case, adding new PCI devices and buses should be serialized via the PCI rescan-remove lock. Add the necessary locking. Fixes: 18f9e9d150fc ("PCI/IOV: Factor out sriov_add_vfs()") Signed-off-by: Niklas Schnelle Signed-off-by: Bjorn Helgaas Reviewed-by: Benjamin Block Reviewed-by: Farhan Ali Reviewed-by: Julian Ruess Cc: stable@vger.kernel.org Link: https://patch.msgid.link/20250826-pci_fix_sriov_disable-v1-1-2d0bc938f2a3@linux.ibm.com Signed-off-by: Greg Kroah-Hartman

PCI/IOV: Allow drivers to control VF BAR size

2025-07-14T20:04:23Z

Drivers could leverage the fact that the VF BAR MMIO reservation is created for total number of VFs supported by the device by resizing the BAR to larger size when smaller number of VFs is enabled. Add pci_iov_vf_bar_set_size() to control the size and a pci_iov_vf_bar_get_sizes() helper to get the VF BAR sizes that will allow up to num_vfs to be successfully enabled with the current underlying reservation size. Signed-off-by: Michał Winiarski Signed-off-by: Bjorn Helgaas Reviewed-by: Ilpo Järvinen Link: https://patch.msgid.link/20250702093522.518099-6-michal.winiarski@intel.com

PCI/IOV: Check that VF BAR fits within the reservation

2025-07-14T20:04:23Z

When the resource representing a VF MMIO BAR reservation is created, its size is always large enough to accommodate the BAR of all SR-IOV Virtual Functions that can potentially be created (total VFs). If for whatever reason it's not possible to accommodate all VFs, the resource is not assigned and no VFs can be created. An upcoming change will allow VF BAR size to be modified by drivers at a later point in time, which means that the check for resource assignment is no longer sufficient. Add an additional check that verifies that the VF BAR for all enabled VFs fits within the underlying reservation resource. Signed-off-by: Michał Winiarski Signed-off-by: Bjorn Helgaas Reviewed-by: Ilpo Järvinen Link: https://patch.msgid.link/20250702093522.518099-5-michal.winiarski@intel.com

PCI/IOV: Allow IOV resources to be resized in pci_resize_resource()

2025-07-14T20:04:18Z

Similar to regular resizable BARs, VF BARs can also be resized. The capability layout is the same as PCI_EXT_CAP_ID_REBAR, which means we can reuse most of the implementation, the only difference being resource size calculation (which is multiplied by total VFs) and memory decoding (which is controlled by a separate VF MSE field in SR-IOV cap). Extend the pci_resize_resource() function to accept IOV resources. See PCIe r6.2, sec 7.8.7. Signed-off-by: Michał Winiarski Signed-off-by: Bjorn Helgaas Reviewed-by: Ilpo Järvinen Link: https://patch.msgid.link/20250702093522.518099-4-michal.winiarski@intel.com

PCI/IOV: Add pci_resource_num_to_vf_bar() to convert VF BAR number to/from IOV resource

2025-07-14T20:03:23Z

There are multiple places where conversions between IOV resources and corresponding VF BAR numbers are done. Extract the logic to pci_resource_num_from_vf_bar() and pci_resource_num_to_vf_bar() helpers. Suggested-by: Ilpo Järvinen Signed-off-by: Michał Winiarski Signed-off-by: Bjorn Helgaas Reviewed-by: Ilpo Järvinen Acked-by: Christian König Link: https://patch.msgid.link/20250702093522.518099-3-michal.winiarski@intel.com

PCI/IOV: Restore VF resizable BAR state after reset

2025-07-14T19:58:13Z

Similar to regular resizable BARs, VF BARs can also be resized, e.g. by the system firmware or the PCI subsystem itself. The capability layout is the same as PCI_EXT_CAP_ID_REBAR. Add the capability ID and restore it as a part of IOV state. See PCIe r6.2, sec 7.8.7. Signed-off-by: Michał Winiarski Signed-off-by: Bjorn Helgaas Reviewed-by: Ilpo Järvinen Reviewed-by: Christian König Link: https://patch.msgid.link/20250702093522.518099-2-michal.winiarski@intel.com

PCI: Fix NULL dereference in SR-IOV VF creation error path

2025-03-21T19:54:16Z

Clean up when virtfn setup fails to prevent NULL pointer dereference during device removal. The kernel oops below occurred due to incorrect error handling flow when pci_setup_device() fails. Add pci_iov_scan_device(), which handles virtfn allocation and setup and cleans up if pci_setup_device() fails, so pci_iov_add_virtfn() doesn't need to call pci_stop_and_remove_bus_device(). This prevents accessing partially initialized virtfn devices during removal. BUG: kernel NULL pointer dereference, address: 00000000000000d0 RIP: 0010:device_del+0x3d/0x3d0 Call Trace: pci_remove_bus_device+0x7c/0x100 pci_iov_add_virtfn+0xfa/0x200 sriov_enable+0x208/0x420 mlx5_core_sriov_configure+0x6a/0x160 [mlx5_core] sriov_numvfs_store+0xae/0x1a0 Link: https://lore.kernel.org/r/20250310084524.599225-1-shayd@nvidia.com Fixes: e3f30d563a38 ("PCI: Make pci_destroy_dev() concurrent safe") Signed-off-by: Shay Drory [bhelgaas: commit log, return ERR_PTR(-ENOMEM) directly] Signed-off-by: Bjorn Helgaas Cc: Keith Busch

PCI: Cleanup dev->resource + resno to use pci_resource_n()

2025-02-14T20:39:31Z

Replace pointer arithmetic in finding the correct resource entry with the pci_resource_n() helper. Link: https://lore.kernel.org/r/20250207162301.2842-1-ilpo.jarvinen@linux.intel.com Signed-off-by: Ilpo Järvinen Signed-off-by: Bjorn Helgaas

PCI: Batch BAR sizing operations

2025-01-23T17:05:20Z

Toggling memory enable is free on bare metal, but potentially expensive in virtualized environments as the device MMIO spaces are added and removed from the VM address space, including DMA mapping of those spaces through the IOMMU where peer-to-peer is supported. Currently memory decode is disabled around sizing each individual BAR, even for SR-IOV BARs while VF Enable is cleared. This can be better optimized for virtual environments by sizing a set of BARs at once, stashing the resulting mask into an array, while only toggling memory enable once. This also naturally improves the SR-IOV path as the caller becomes responsible for any necessary decode disables while sizing BARs, therefore SR-IOV BARs are sized relying only on the VF Enable rather than toggling the PF memory enable in the command register. Link: https://lore.kernel.org/r/20250120182202.1878581-1-alex.williamson@redhat.com Reported-by: Mitchell Augustin Link: https://lore.kernel.org/r/CAHTA-uYp07FgM6T1OZQKqAdSA5JrZo0ReNEyZgQZub4mDRrV5w@mail.gmail.com Signed-off-by: Alex Williamson Signed-off-by: Bjorn Helgaas Tested-by: Mitchell Augustin Reviewed-by: Mitchell Augustin Reviewed-by: Ilpo Järvinen

PCI: Use resource_set_{range,size}() helpers

2024-10-10T22:44:57Z

Convert open-coded resource size calculations to use resource_set_{range,size}() helpers. While at it, use SZ_* for size parameter where appropriate which makes the intent of code more obvious. Also, cast sizes to resource_size_t, not u64. Link: https://lore.kernel.org/r/20240614100606.15830-3-ilpo.jarvinen@linux.intel.com Signed-off-by: Ilpo Järvinen Signed-off-by: Bjorn Helgaas Reviewed-by: Jonathan Cameron