diff options
Diffstat (limited to 'drivers/vfio')
| -rw-r--r-- | drivers/vfio/pci/vfio_pci_core.c | 185 | ||||
| -rw-r--r-- | drivers/vfio/pci/vfio_pci_rdwr.c | 2 |
2 files changed, 137 insertions, 50 deletions
diff --git a/drivers/vfio/pci/vfio_pci_core.c b/drivers/vfio/pci/vfio_pci_core.c index a03b5a99c2da..f3916e6b16b9 100644 --- a/drivers/vfio/pci/vfio_pci_core.c +++ b/drivers/vfio/pci/vfio_pci_core.c @@ -36,6 +36,10 @@ static bool nointxmask; static bool disable_vga; static bool disable_idle_d3; +/* List of PF's that vfio_pci_core_sriov_configure() has been called on */ +static DEFINE_MUTEX(vfio_pci_sriov_pfs_mutex); +static LIST_HEAD(vfio_pci_sriov_pfs); + static inline bool vfio_vga_disabled(void) { #ifdef CONFIG_VFIO_PCI_VGA @@ -228,6 +232,19 @@ int vfio_pci_set_power_state(struct vfio_pci_core_device *vdev, pci_power_t stat if (!ret) { /* D3 might be unsupported via quirk, skip unless in D3 */ if (needs_save && pdev->current_state >= PCI_D3hot) { + /* + * The current PCI state will be saved locally in + * 'pm_save' during the D3hot transition. When the + * device state is changed to D0 again with the current + * function, then pci_store_saved_state() will restore + * the state and will free the memory pointed by + * 'pm_save'. There are few cases where the PCI power + * state can be changed to D0 without the involvement + * of the driver. For these cases, free the earlier + * allocated memory first before overwriting 'pm_save' + * to prevent the memory leak. + */ + kfree(vdev->pm_save); vdev->pm_save = pci_store_saved_state(pdev); } else if (needs_restore) { pci_load_and_free_saved_state(pdev, &vdev->pm_save); @@ -322,6 +339,17 @@ void vfio_pci_core_disable(struct vfio_pci_core_device *vdev) /* For needs_reset */ lockdep_assert_held(&vdev->vdev.dev_set->lock); + /* + * This function can be invoked while the power state is non-D0. + * This function calls __pci_reset_function_locked() which internally + * can use pci_pm_reset() for the function reset. pci_pm_reset() will + * fail if the power state is non-D0. Also, for the devices which + * have NoSoftRst-, the reset function can cause the PCI config space + * reset without restoring the original state (saved locally in + * 'vdev->pm_save'). + */ + vfio_pci_set_power_state(vdev, PCI_D0); + /* Stop the device from further DMA */ pci_clear_master(pdev); @@ -410,47 +438,17 @@ out: } EXPORT_SYMBOL_GPL(vfio_pci_core_disable); -static struct vfio_pci_core_device *get_pf_vdev(struct vfio_pci_core_device *vdev) -{ - struct pci_dev *physfn = pci_physfn(vdev->pdev); - struct vfio_device *pf_dev; - - if (!vdev->pdev->is_virtfn) - return NULL; - - pf_dev = vfio_device_get_from_dev(&physfn->dev); - if (!pf_dev) - return NULL; - - if (pci_dev_driver(physfn) != pci_dev_driver(vdev->pdev)) { - vfio_device_put(pf_dev); - return NULL; - } - - return container_of(pf_dev, struct vfio_pci_core_device, vdev); -} - -static void vfio_pci_vf_token_user_add(struct vfio_pci_core_device *vdev, int val) -{ - struct vfio_pci_core_device *pf_vdev = get_pf_vdev(vdev); - - if (!pf_vdev) - return; - - mutex_lock(&pf_vdev->vf_token->lock); - pf_vdev->vf_token->users += val; - WARN_ON(pf_vdev->vf_token->users < 0); - mutex_unlock(&pf_vdev->vf_token->lock); - - vfio_device_put(&pf_vdev->vdev); -} - void vfio_pci_core_close_device(struct vfio_device *core_vdev) { struct vfio_pci_core_device *vdev = container_of(core_vdev, struct vfio_pci_core_device, vdev); - vfio_pci_vf_token_user_add(vdev, -1); + if (vdev->sriov_pf_core_dev) { + mutex_lock(&vdev->sriov_pf_core_dev->vf_token->lock); + WARN_ON(!vdev->sriov_pf_core_dev->vf_token->users); + vdev->sriov_pf_core_dev->vf_token->users--; + mutex_unlock(&vdev->sriov_pf_core_dev->vf_token->lock); + } vfio_spapr_pci_eeh_release(vdev->pdev); vfio_pci_core_disable(vdev); @@ -471,7 +469,12 @@ void vfio_pci_core_finish_enable(struct vfio_pci_core_device *vdev) { vfio_pci_probe_mmaps(vdev); vfio_spapr_pci_eeh_open(vdev->pdev); - vfio_pci_vf_token_user_add(vdev, 1); + + if (vdev->sriov_pf_core_dev) { + mutex_lock(&vdev->sriov_pf_core_dev->vf_token->lock); + vdev->sriov_pf_core_dev->vf_token->users++; + mutex_unlock(&vdev->sriov_pf_core_dev->vf_token->lock); + } } EXPORT_SYMBOL_GPL(vfio_pci_core_finish_enable); @@ -921,6 +924,19 @@ long vfio_pci_core_ioctl(struct vfio_device *core_vdev, unsigned int cmd, return -EINVAL; vfio_pci_zap_and_down_write_memory_lock(vdev); + + /* + * This function can be invoked while the power state is non-D0. + * If pci_try_reset_function() has been called while the power + * state is non-D0, then pci_try_reset_function() will + * internally set the power state to D0 without vfio driver + * involvement. For the devices which have NoSoftRst-, the + * reset function can cause the PCI config space reset without + * restoring the original state (saved locally in + * 'vdev->pm_save'). + */ + vfio_pci_set_power_state(vdev, PCI_D0); + ret = pci_try_reset_function(vdev->pdev); up_write(&vdev->memory_lock); @@ -1566,11 +1582,8 @@ static int vfio_pci_validate_vf_token(struct vfio_pci_core_device *vdev, * * If the VF token is provided but unused, an error is generated. */ - if (!vdev->pdev->is_virtfn && !vdev->vf_token && !vf_token) - return 0; /* No VF token provided or required */ - if (vdev->pdev->is_virtfn) { - struct vfio_pci_core_device *pf_vdev = get_pf_vdev(vdev); + struct vfio_pci_core_device *pf_vdev = vdev->sriov_pf_core_dev; bool match; if (!pf_vdev) { @@ -1583,7 +1596,6 @@ static int vfio_pci_validate_vf_token(struct vfio_pci_core_device *vdev, } if (!vf_token) { - vfio_device_put(&pf_vdev->vdev); pci_info_ratelimited(vdev->pdev, "VF token required to access device\n"); return -EACCES; @@ -1593,8 +1605,6 @@ static int vfio_pci_validate_vf_token(struct vfio_pci_core_device *vdev, match = uuid_equal(uuid, &pf_vdev->vf_token->uuid); mutex_unlock(&pf_vdev->vf_token->lock); - vfio_device_put(&pf_vdev->vdev); - if (!match) { pci_info_ratelimited(vdev->pdev, "Incorrect VF token provided for device\n"); @@ -1715,8 +1725,30 @@ static int vfio_pci_bus_notifier(struct notifier_block *nb, static int vfio_pci_vf_init(struct vfio_pci_core_device *vdev) { struct pci_dev *pdev = vdev->pdev; + struct vfio_pci_core_device *cur; + struct pci_dev *physfn; int ret; + if (pdev->is_virtfn) { + /* + * If this VF was created by our vfio_pci_core_sriov_configure() + * then we can find the PF vfio_pci_core_device now, and due to + * the locking in pci_disable_sriov() it cannot change until + * this VF device driver is removed. + */ + physfn = pci_physfn(vdev->pdev); + mutex_lock(&vfio_pci_sriov_pfs_mutex); + list_for_each_entry(cur, &vfio_pci_sriov_pfs, sriov_pfs_item) { + if (cur->pdev == physfn) { + vdev->sriov_pf_core_dev = cur; + break; + } + } + mutex_unlock(&vfio_pci_sriov_pfs_mutex); + return 0; + } + + /* Not a SRIOV PF */ if (!pdev->is_physfn) return 0; @@ -1788,6 +1820,7 @@ void vfio_pci_core_init_device(struct vfio_pci_core_device *vdev, INIT_LIST_HEAD(&vdev->ioeventfds_list); mutex_init(&vdev->vma_lock); INIT_LIST_HEAD(&vdev->vma_list); + INIT_LIST_HEAD(&vdev->sriov_pfs_item); init_rwsem(&vdev->memory_lock); } EXPORT_SYMBOL_GPL(vfio_pci_core_init_device); @@ -1886,7 +1919,7 @@ void vfio_pci_core_unregister_device(struct vfio_pci_core_device *vdev) { struct pci_dev *pdev = vdev->pdev; - pci_disable_sriov(pdev); + vfio_pci_core_sriov_configure(pdev, 0); vfio_unregister_group_dev(&vdev->vdev); @@ -1926,21 +1959,49 @@ static pci_ers_result_t vfio_pci_aer_err_detected(struct pci_dev *pdev, int vfio_pci_core_sriov_configure(struct pci_dev *pdev, int nr_virtfn) { + struct vfio_pci_core_device *vdev; struct vfio_device *device; int ret = 0; + device_lock_assert(&pdev->dev); + device = vfio_device_get_from_dev(&pdev->dev); if (!device) return -ENODEV; - if (nr_virtfn == 0) - pci_disable_sriov(pdev); - else + vdev = container_of(device, struct vfio_pci_core_device, vdev); + + if (nr_virtfn) { + mutex_lock(&vfio_pci_sriov_pfs_mutex); + /* + * The thread that adds the vdev to the list is the only thread + * that gets to call pci_enable_sriov() and we will only allow + * it to be called once without going through + * pci_disable_sriov() + */ + if (!list_empty(&vdev->sriov_pfs_item)) { + ret = -EINVAL; + goto out_unlock; + } + list_add_tail(&vdev->sriov_pfs_item, &vfio_pci_sriov_pfs); + mutex_unlock(&vfio_pci_sriov_pfs_mutex); ret = pci_enable_sriov(pdev, nr_virtfn); + if (ret) + goto out_del; + ret = nr_virtfn; + goto out_put; + } - vfio_device_put(device); + pci_disable_sriov(pdev); - return ret < 0 ? ret : nr_virtfn; +out_del: + mutex_lock(&vfio_pci_sriov_pfs_mutex); + list_del_init(&vdev->sriov_pfs_item); +out_unlock: + mutex_unlock(&vfio_pci_sriov_pfs_mutex); +out_put: + vfio_device_put(device); + return ret; } EXPORT_SYMBOL_GPL(vfio_pci_core_sriov_configure); @@ -2064,6 +2125,18 @@ static int vfio_pci_dev_set_hot_reset(struct vfio_device_set *dev_set, } cur_mem = NULL; + /* + * The pci_reset_bus() will reset all the devices in the bus. + * The power state can be non-D0 for some of the devices in the bus. + * For these devices, the pci_reset_bus() will internally set + * the power state to D0 without vfio driver involvement. + * For the devices which have NoSoftRst-, the reset function can + * cause the PCI config space reset without restoring the original + * state (saved locally in 'vdev->pm_save'). + */ + list_for_each_entry(cur, &dev_set->device_list, vdev.dev_set_list) + vfio_pci_set_power_state(cur, PCI_D0); + ret = pci_reset_bus(pdev); err_undo: @@ -2117,6 +2190,18 @@ static bool vfio_pci_dev_set_try_reset(struct vfio_device_set *dev_set) if (!pdev) return false; + /* + * The pci_reset_bus() will reset all the devices in the bus. + * The power state can be non-D0 for some of the devices in the bus. + * For these devices, the pci_reset_bus() will internally set + * the power state to D0 without vfio driver involvement. + * For the devices which have NoSoftRst-, the reset function can + * cause the PCI config space reset without restoring the original + * state (saved locally in 'vdev->pm_save'). + */ + list_for_each_entry(cur, &dev_set->device_list, vdev.dev_set_list) + vfio_pci_set_power_state(cur, PCI_D0); + ret = pci_reset_bus(pdev); if (ret) return false; diff --git a/drivers/vfio/pci/vfio_pci_rdwr.c b/drivers/vfio/pci/vfio_pci_rdwr.c index 57d3b2cbbd8e..82ac1569deb0 100644 --- a/drivers/vfio/pci/vfio_pci_rdwr.c +++ b/drivers/vfio/pci/vfio_pci_rdwr.c @@ -288,6 +288,7 @@ out: return done; } +#ifdef CONFIG_VFIO_PCI_VGA ssize_t vfio_pci_vga_rw(struct vfio_pci_core_device *vdev, char __user *buf, size_t count, loff_t *ppos, bool iswrite) { @@ -355,6 +356,7 @@ ssize_t vfio_pci_vga_rw(struct vfio_pci_core_device *vdev, char __user *buf, return done; } +#endif static void vfio_pci_ioeventfd_do_write(struct vfio_pci_ioeventfd *ioeventfd, bool test_mem) |