diff --git a/drivers/vfio/pci/vfio_pci_core.c b/drivers/vfio/pci/vfio_pci_core.c index 55e28feba475..5b5fb3366742 100644 --- a/drivers/vfio/pci/vfio_pci_core.c +++ b/drivers/vfio/pci/vfio_pci_core.c @@ -242,8 +242,11 @@ int vfio_pci_set_power_state(struct vfio_pci_core_device *vdev, pci_power_t stat int ret; /* Prevent changing power state for PFs with VFs enabled */ - if (pci_num_vf(pdev) && state > PCI_D0) - return -EBUSY; + if (state > PCI_D0) { + lockdep_assert_held_write(&vdev->memory_lock); + if (vdev->sriov_active) + return -EBUSY; + } if (vdev->needs_pm_restore) { if (pdev->current_state < PCI_D3hot && state >= PCI_D3hot) { @@ -2236,8 +2239,9 @@ int vfio_pci_core_sriov_configure(struct vfio_pci_core_device *vdev, down_write(&vdev->memory_lock); vfio_pci_set_power_state(vdev, PCI_D0); - ret = pci_enable_sriov(pdev, nr_virtfn); + vdev->sriov_active = true; up_write(&vdev->memory_lock); + ret = pci_enable_sriov(pdev, nr_virtfn); if (ret) { pm_runtime_put(&pdev->dev); goto out_del; @@ -2251,6 +2255,13 @@ int vfio_pci_core_sriov_configure(struct vfio_pci_core_device *vdev, } out_del: + /* + * Avoid taking the memory_lock intentionally. A race with a power + * state transition would at most result in an -EBUSY, leaving the + * device in PCI_D0. + */ + vdev->sriov_active = false; + mutex_lock(&vfio_pci_sriov_pfs_mutex); list_del_init(&vdev->sriov_pfs_item); out_unlock: diff --git a/include/linux/vfio_pci_core.h b/include/linux/vfio_pci_core.h index 4f283514a1ed..af448ba1de95 100644 --- a/include/linux/vfio_pci_core.h +++ b/include/linux/vfio_pci_core.h @@ -80,6 +80,7 @@ struct vfio_pci_core_device { bool needs_pm_restore:1; bool pm_intx_masked:1; bool pm_runtime_engaged:1; + bool sriov_active; struct pci_saved_state *pci_saved_state; struct pci_saved_state *pm_save; int ioeventfds_nr;