diff options
Diffstat (limited to 'drivers/vfio')
-rw-r--r-- | drivers/vfio/pci/vfio_pci.c | 25 | ||||
-rw-r--r-- | drivers/vfio/pci/vfio_pci_config.c | 31 | ||||
-rw-r--r-- | drivers/vfio/vfio_iommu_spapr_tce.c | 10 |
3 files changed, 52 insertions, 14 deletions
diff --git a/drivers/vfio/pci/vfio_pci.c b/drivers/vfio/pci/vfio_pci.c index 6f5cc67e343e..9bd3e7911af2 100644 --- a/drivers/vfio/pci/vfio_pci.c +++ b/drivers/vfio/pci/vfio_pci.c @@ -363,11 +363,20 @@ static void vfio_pci_disable(struct vfio_pci_device *vdev) pci_write_config_word(pdev, PCI_COMMAND, PCI_COMMAND_INTX_DISABLE); /* - * Try to reset the device. The success of this is dependent on - * being able to lock the device, which is not always possible. + * Try to get the locks ourselves to prevent a deadlock. The + * success of this is dependent on being able to lock the device, + * which is not always possible. + * We can not use the "try" reset interface here, which will + * overwrite the previously restored configuration information. */ - if (vdev->reset_works && !pci_try_reset_function(pdev)) - vdev->needs_reset = false; + if (vdev->reset_works && pci_cfg_access_trylock(pdev)) { + if (device_trylock(&pdev->dev)) { + if (!__pci_reset_function_locked(pdev)) + vdev->needs_reset = false; + device_unlock(&pdev->dev); + } + pci_cfg_access_unlock(pdev); + } pci_restore_state(pdev); out: @@ -424,10 +433,14 @@ static int vfio_pci_get_irq_count(struct vfio_pci_device *vdev, int irq_type) { if (irq_type == VFIO_PCI_INTX_IRQ_INDEX) { u8 pin; + + if (!IS_ENABLED(CONFIG_VFIO_PCI_INTX) || + vdev->nointx || vdev->pdev->is_virtfn) + return 0; + pci_read_config_byte(vdev->pdev, PCI_INTERRUPT_PIN, &pin); - if (IS_ENABLED(CONFIG_VFIO_PCI_INTX) && !vdev->nointx && pin) - return 1; + return pin ? 1 : 0; } else if (irq_type == VFIO_PCI_MSI_IRQ_INDEX) { u8 pos; u16 flags; diff --git a/drivers/vfio/pci/vfio_pci_config.c b/drivers/vfio/pci/vfio_pci_config.c index 115a36f6f403..423ea1f98441 100644 --- a/drivers/vfio/pci/vfio_pci_config.c +++ b/drivers/vfio/pci/vfio_pci_config.c @@ -1180,8 +1180,10 @@ static int vfio_msi_cap_len(struct vfio_pci_device *vdev, u8 pos) return -ENOMEM; ret = init_pci_cap_msi_perm(vdev->msi_perm, len, flags); - if (ret) + if (ret) { + kfree(vdev->msi_perm); return ret; + } return len; } @@ -1610,6 +1612,15 @@ static int vfio_ecap_init(struct vfio_pci_device *vdev) } /* + * Nag about hardware bugs, hopefully to have vendors fix them, but at least + * to collect a list of dependencies for the VF INTx pin quirk below. + */ +static const struct pci_device_id known_bogus_vf_intx_pin[] = { + { PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x270c) }, + {} +}; + +/* * For each device we allocate a pci_config_map that indicates the * capability occupying each dword and thus the struct perm_bits we * use for read and write. We also allocate a virtualized config @@ -1674,6 +1685,24 @@ int vfio_config_init(struct vfio_pci_device *vdev) if (pdev->is_virtfn) { *(__le16 *)&vconfig[PCI_VENDOR_ID] = cpu_to_le16(pdev->vendor); *(__le16 *)&vconfig[PCI_DEVICE_ID] = cpu_to_le16(pdev->device); + + /* + * Per SR-IOV spec rev 1.1, 3.4.1.18 the interrupt pin register + * does not apply to VFs and VFs must implement this register + * as read-only with value zero. Userspace is not readily able + * to identify whether a device is a VF and thus that the pin + * definition on the device is bogus should it violate this + * requirement. We already virtualize the pin register for + * other purposes, so we simply need to replace the bogus value + * and consider VFs when we determine INTx IRQ count. + */ + if (vconfig[PCI_INTERRUPT_PIN] && + !pci_match_id(known_bogus_vf_intx_pin, pdev)) + pci_warn(pdev, + "Hardware bug: VF reports bogus INTx pin %d\n", + vconfig[PCI_INTERRUPT_PIN]); + + vconfig[PCI_INTERRUPT_PIN] = 0; /* Gratuitous for good VFs */ } if (!IS_ENABLED(CONFIG_VFIO_PCI_INTX) || vdev->nointx) diff --git a/drivers/vfio/vfio_iommu_spapr_tce.c b/drivers/vfio/vfio_iommu_spapr_tce.c index b4c68f3b82be..eba9aaf3cc17 100644 --- a/drivers/vfio/vfio_iommu_spapr_tce.c +++ b/drivers/vfio/vfio_iommu_spapr_tce.c @@ -409,6 +409,7 @@ static void tce_iommu_release(void *iommu_data) { struct tce_container *container = iommu_data; struct tce_iommu_group *tcegrp; + struct tce_iommu_prereg *tcemem, *tmtmp; long i; while (tce_groups_attached(container)) { @@ -431,13 +432,8 @@ static void tce_iommu_release(void *iommu_data) tce_iommu_free_table(container, tbl); } - while (!list_empty(&container->prereg_list)) { - struct tce_iommu_prereg *tcemem; - - tcemem = list_first_entry(&container->prereg_list, - struct tce_iommu_prereg, next); - WARN_ON_ONCE(tce_iommu_prereg_free(container, tcemem)); - } + list_for_each_entry_safe(tcemem, tmtmp, &container->prereg_list, next) + WARN_ON(tce_iommu_prereg_free(container, tcemem)); tce_iommu_disable(container); if (container->mm) |