diff options
Diffstat (limited to 'drivers/vfio/pci/vfio_pci_core.c')
| -rw-r--r-- | drivers/vfio/pci/vfio_pci_core.c | 2127 |
1 files changed, 1285 insertions, 842 deletions
diff --git a/drivers/vfio/pci/vfio_pci_core.c b/drivers/vfio/pci/vfio_pci_core.c index f948e6cd2993..3a11e6f450f7 100644 --- a/drivers/vfio/pci/vfio_pci_core.c +++ b/drivers/vfio/pci/vfio_pci_core.c @@ -10,6 +10,7 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt +#include <linux/aperture.h> #include <linux/device.h> #include <linux/eventfd.h> #include <linux/file.h> @@ -26,8 +27,13 @@ #include <linux/vgaarb.h> #include <linux/nospec.h> #include <linux/sched/mm.h> +#include <linux/iommufd.h> +#include <linux/pci-p2pdma.h> +#if IS_ENABLED(CONFIG_EEH) +#include <asm/eeh.h> +#endif -#include <linux/vfio_pci_core.h> +#include "vfio_pci_priv.h" #define DRIVER_AUTHOR "Alex Williamson <alex.williamson@redhat.com>" #define DRIVER_DESC "core driver for VFIO based PCI devices" @@ -36,6 +42,56 @@ static bool nointxmask; static bool disable_vga; static bool disable_idle_d3; +static void vfio_pci_eventfd_rcu_free(struct rcu_head *rcu) +{ + struct vfio_pci_eventfd *eventfd = + container_of(rcu, struct vfio_pci_eventfd, rcu); + + eventfd_ctx_put(eventfd->ctx); + kfree(eventfd); +} + +int vfio_pci_eventfd_replace_locked(struct vfio_pci_core_device *vdev, + struct vfio_pci_eventfd __rcu **peventfd, + struct eventfd_ctx *ctx) +{ + struct vfio_pci_eventfd *new = NULL; + struct vfio_pci_eventfd *old; + + lockdep_assert_held(&vdev->igate); + + if (ctx) { + new = kzalloc(sizeof(*new), GFP_KERNEL_ACCOUNT); + if (!new) + return -ENOMEM; + + new->ctx = ctx; + } + + old = rcu_replace_pointer(*peventfd, new, + lockdep_is_held(&vdev->igate)); + if (old) + call_rcu(&old->rcu, vfio_pci_eventfd_rcu_free); + + return 0; +} + +/* 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); + +struct vfio_pci_dummy_resource { + struct resource resource; + int index; + struct list_head res_next; +}; + +struct vfio_pci_vf_token { + struct mutex lock; + uuid_t uuid; + int users; +}; + static inline bool vfio_vga_disabled(void) { #ifdef CONFIG_VFIO_PCI_VGA @@ -94,7 +150,7 @@ static void vfio_pci_probe_mmaps(struct vfio_pci_core_device *vdev) res = &vdev->pdev->resource[bar]; - if (!IS_ENABLED(CONFIG_VFIO_PCI_MMAP)) + if (vdev->pdev->non_mappable_bars) goto no_mmap; if (!(res->flags & IORESOURCE_MEM)) @@ -119,7 +175,8 @@ static void vfio_pci_probe_mmaps(struct vfio_pci_core_device *vdev) * of the exclusive page in case that hot-add * device's bar is assigned into it. */ - dummy_res = kzalloc(sizeof(*dummy_res), GFP_KERNEL); + dummy_res = + kzalloc(sizeof(*dummy_res), GFP_KERNEL_ACCOUNT); if (dummy_res == NULL) goto no_mmap; @@ -152,9 +209,10 @@ no_mmap: } struct vfio_pci_group_info; -static bool vfio_pci_dev_set_try_reset(struct vfio_device_set *dev_set); +static void vfio_pci_dev_set_try_reset(struct vfio_device_set *dev_set); static int vfio_pci_dev_set_hot_reset(struct vfio_device_set *dev_set, - struct vfio_pci_group_info *groups); + struct vfio_pci_group_info *groups, + struct iommufd_ctx *iommufd_ctx); /* * INTx masking requires the ability to disable INTx signaling via PCI_COMMAND @@ -213,6 +271,10 @@ int vfio_pci_set_power_state(struct vfio_pci_core_device *vdev, pci_power_t stat bool needs_restore = false, needs_save = false; int ret; + /* Prevent changing power state for PFs with VFs enabled */ + if (pci_num_vf(pdev) && state > PCI_D0) + return -EBUSY; + if (vdev->needs_pm_restore) { if (pdev->current_state < PCI_D3hot && state >= PCI_D3hot) { pci_save_state(pdev); @@ -228,6 +290,19 @@ 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); @@ -238,6 +313,188 @@ int vfio_pci_set_power_state(struct vfio_pci_core_device *vdev, pci_power_t stat return ret; } +static int vfio_pci_runtime_pm_entry(struct vfio_pci_core_device *vdev, + struct eventfd_ctx *efdctx) +{ + /* + * The vdev power related flags are protected with 'memory_lock' + * semaphore. + */ + vfio_pci_zap_and_down_write_memory_lock(vdev); + vfio_pci_dma_buf_move(vdev, true); + + if (vdev->pm_runtime_engaged) { + up_write(&vdev->memory_lock); + return -EINVAL; + } + + vdev->pm_runtime_engaged = true; + vdev->pm_wake_eventfd_ctx = efdctx; + pm_runtime_put_noidle(&vdev->pdev->dev); + up_write(&vdev->memory_lock); + + return 0; +} + +static int vfio_pci_core_pm_entry(struct vfio_pci_core_device *vdev, u32 flags, + void __user *arg, size_t argsz) +{ + int ret; + + ret = vfio_check_feature(flags, argsz, VFIO_DEVICE_FEATURE_SET, 0); + if (ret != 1) + return ret; + + /* + * Inside vfio_pci_runtime_pm_entry(), only the runtime PM usage count + * will be decremented. The pm_runtime_put() will be invoked again + * while returning from the ioctl and then the device can go into + * runtime suspended state. + */ + return vfio_pci_runtime_pm_entry(vdev, NULL); +} + +static int vfio_pci_core_pm_entry_with_wakeup( + struct vfio_pci_core_device *vdev, u32 flags, + struct vfio_device_low_power_entry_with_wakeup __user *arg, + size_t argsz) +{ + struct vfio_device_low_power_entry_with_wakeup entry; + struct eventfd_ctx *efdctx; + int ret; + + ret = vfio_check_feature(flags, argsz, VFIO_DEVICE_FEATURE_SET, + sizeof(entry)); + if (ret != 1) + return ret; + + if (copy_from_user(&entry, arg, sizeof(entry))) + return -EFAULT; + + if (entry.wakeup_eventfd < 0) + return -EINVAL; + + efdctx = eventfd_ctx_fdget(entry.wakeup_eventfd); + if (IS_ERR(efdctx)) + return PTR_ERR(efdctx); + + ret = vfio_pci_runtime_pm_entry(vdev, efdctx); + if (ret) + eventfd_ctx_put(efdctx); + + return ret; +} + +static void __vfio_pci_runtime_pm_exit(struct vfio_pci_core_device *vdev) +{ + if (vdev->pm_runtime_engaged) { + vdev->pm_runtime_engaged = false; + pm_runtime_get_noresume(&vdev->pdev->dev); + + if (vdev->pm_wake_eventfd_ctx) { + eventfd_ctx_put(vdev->pm_wake_eventfd_ctx); + vdev->pm_wake_eventfd_ctx = NULL; + } + } +} + +static void vfio_pci_runtime_pm_exit(struct vfio_pci_core_device *vdev) +{ + /* + * The vdev power related flags are protected with 'memory_lock' + * semaphore. + */ + down_write(&vdev->memory_lock); + __vfio_pci_runtime_pm_exit(vdev); + if (__vfio_pci_memory_enabled(vdev)) + vfio_pci_dma_buf_move(vdev, false); + up_write(&vdev->memory_lock); +} + +static int vfio_pci_core_pm_exit(struct vfio_pci_core_device *vdev, u32 flags, + void __user *arg, size_t argsz) +{ + int ret; + + ret = vfio_check_feature(flags, argsz, VFIO_DEVICE_FEATURE_SET, 0); + if (ret != 1) + return ret; + + /* + * The device is always in the active state here due to pm wrappers + * around ioctls. If the device had entered a low power state and + * pm_wake_eventfd_ctx is valid, vfio_pci_core_runtime_resume() has + * already signaled the eventfd and exited low power mode itself. + * pm_runtime_engaged protects the redundant call here. + */ + vfio_pci_runtime_pm_exit(vdev); + return 0; +} + +#ifdef CONFIG_PM +static int vfio_pci_core_runtime_suspend(struct device *dev) +{ + struct vfio_pci_core_device *vdev = dev_get_drvdata(dev); + + down_write(&vdev->memory_lock); + /* + * The user can move the device into D3hot state before invoking + * power management IOCTL. Move the device into D0 state here and then + * the pci-driver core runtime PM suspend function will move the device + * into the low power state. Also, for the devices which have + * NoSoftRst-, it will help in restoring the original state + * (saved locally in 'vdev->pm_save'). + */ + vfio_pci_set_power_state(vdev, PCI_D0); + up_write(&vdev->memory_lock); + + /* + * If INTx is enabled, then mask INTx before going into the runtime + * suspended state and unmask the same in the runtime resume. + * If INTx has already been masked by the user, then + * vfio_pci_intx_mask() will return false and in that case, INTx + * should not be unmasked in the runtime resume. + */ + vdev->pm_intx_masked = ((vdev->irq_type == VFIO_PCI_INTX_IRQ_INDEX) && + vfio_pci_intx_mask(vdev)); + + return 0; +} + +static int vfio_pci_core_runtime_resume(struct device *dev) +{ + struct vfio_pci_core_device *vdev = dev_get_drvdata(dev); + + /* + * Resume with a pm_wake_eventfd_ctx signals the eventfd and exit + * low power mode. + */ + down_write(&vdev->memory_lock); + if (vdev->pm_wake_eventfd_ctx) { + eventfd_signal(vdev->pm_wake_eventfd_ctx); + __vfio_pci_runtime_pm_exit(vdev); + } + up_write(&vdev->memory_lock); + + if (vdev->pm_intx_masked) + vfio_pci_intx_unmask(vdev); + + return 0; +} +#endif /* CONFIG_PM */ + +/* + * The pci-driver core runtime PM routines always save the device state + * before going into suspended state. If the device is going into low power + * state with only with runtime PM ops, then no explicit handling is needed + * for the devices which have NoSoftRst-. + */ +static const struct dev_pm_ops vfio_pci_core_pm_ops = { + SET_RUNTIME_PM_OPS(vfio_pci_core_runtime_suspend, + vfio_pci_core_runtime_resume, + NULL) +}; + int vfio_pci_core_enable(struct vfio_pci_core_device *vdev) { struct pci_dev *pdev = vdev->pdev; @@ -245,21 +502,23 @@ int vfio_pci_core_enable(struct vfio_pci_core_device *vdev) u16 cmd; u8 msix_pos; - vfio_pci_set_power_state(vdev, PCI_D0); + if (!disable_idle_d3) { + ret = pm_runtime_resume_and_get(&pdev->dev); + if (ret < 0) + return ret; + } /* Don't allow our initial saved state to include busmaster */ pci_clear_master(pdev); ret = pci_enable_device(pdev); if (ret) - return ret; + goto out_power; /* If reset fails because of the device lock, fail this path entirely */ ret = pci_try_reset_function(pdev); - if (ret == -EAGAIN) { - pci_disable_device(pdev); - return ret; - } + if (ret == -EAGAIN) + goto out_disable_device; vdev->reset_works = !ret; pci_save_state(pdev); @@ -282,13 +541,13 @@ int vfio_pci_core_enable(struct vfio_pci_core_device *vdev) pci_write_config_word(pdev, PCI_COMMAND, cmd); } + ret = vfio_pci_zdev_open_device(vdev); + if (ret) + goto out_free_state; + ret = vfio_config_init(vdev); - if (ret) { - kfree(vdev->pci_saved_state); - vdev->pci_saved_state = NULL; - pci_disable_device(pdev); - return ret; - } + if (ret) + goto out_free_zdev; msix_pos = pdev->msix_cap; if (msix_pos) { @@ -301,14 +560,29 @@ int vfio_pci_core_enable(struct vfio_pci_core_device *vdev) vdev->msix_bar = table & PCI_MSIX_TABLE_BIR; vdev->msix_offset = table & PCI_MSIX_TABLE_OFFSET; vdev->msix_size = ((flags & PCI_MSIX_FLAGS_QSIZE) + 1) * 16; - } else + vdev->has_dyn_msix = pci_msix_can_alloc_dyn(pdev); + } else { vdev->msix_bar = 0xFF; + vdev->has_dyn_msix = false; + } if (!vfio_vga_disabled() && vfio_pci_is_vga(pdev)) vdev->has_vga = true; return 0; + +out_free_zdev: + vfio_pci_zdev_close_device(vdev); +out_free_state: + kfree(vdev->pci_saved_state); + vdev->pci_saved_state = NULL; +out_disable_device: + pci_disable_device(pdev); +out_power: + if (!disable_idle_d3) + pm_runtime_put(&pdev->dev); + return ret; } EXPORT_SYMBOL_GPL(vfio_pci_core_enable); @@ -322,6 +596,29 @@ 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 non-D0 power state can be with or without runtime PM. + * vfio_pci_runtime_pm_exit() will internally increment the usage + * count corresponding to pm_runtime_put() called during low power + * feature entry and then pm_runtime_resume() will wake up the device, + * if the device has already gone into the suspended state. Otherwise, + * the vfio_pci_set_power_state() will change the device power state + * to D0. + */ + vfio_pci_runtime_pm_exit(vdev); + pm_runtime_resume(&pdev->dev); + + /* + * 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); @@ -367,6 +664,8 @@ void vfio_pci_core_disable(struct vfio_pci_core_device *vdev) vdev->needs_reset = true; + vfio_pci_zdev_close_device(vdev); + /* * If we have saved state, restore it. If we can reset the device, * even better. Resetting with current state seems better than @@ -405,64 +704,35 @@ void vfio_pci_core_disable(struct vfio_pci_core_device *vdev) out: pci_disable_device(pdev); - if (!vfio_pci_dev_set_try_reset(vdev->vdev.dev_set) && !disable_idle_d3) - vfio_pci_set_power_state(vdev, PCI_D3hot); -} -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; + vfio_pci_dev_set_try_reset(vdev->vdev.dev_set); - 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); + /* Put the pm-runtime usage counter acquired during enable */ + if (!disable_idle_d3) + pm_runtime_put(&pdev->dev); } +EXPORT_SYMBOL_GPL(vfio_pci_core_disable); 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); - vfio_spapr_pci_eeh_release(vdev->pdev); + 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); + } +#if IS_ENABLED(CONFIG_EEH) + eeh_dev_release(vdev->pdev); +#endif vfio_pci_core_disable(vdev); + vfio_pci_dma_buf_cleanup(vdev); + mutex_lock(&vdev->igate); - if (vdev->err_trigger) { - eventfd_ctx_put(vdev->err_trigger); - vdev->err_trigger = NULL; - } - if (vdev->req_trigger) { - eventfd_ctx_put(vdev->req_trigger); - vdev->req_trigger = NULL; - } + vfio_pci_eventfd_replace_locked(vdev, &vdev->err_trigger, NULL); + vfio_pci_eventfd_replace_locked(vdev, &vdev->req_trigger, NULL); mutex_unlock(&vdev->igate); } EXPORT_SYMBOL_GPL(vfio_pci_core_close_device); @@ -470,23 +740,22 @@ EXPORT_SYMBOL_GPL(vfio_pci_core_close_device); 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 IS_ENABLED(CONFIG_EEH) + eeh_dev_open(vdev->pdev); +#endif + + 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); static int vfio_pci_get_irq_count(struct vfio_pci_core_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); - - return pin ? 1 : 0; + return vdev->vconfig[PCI_INTERRUPT_PIN] ? 1 : 0; } else if (irq_type == VFIO_PCI_MSI_IRQ_INDEX) { u8 pos; u16 flags; @@ -525,35 +794,69 @@ static int vfio_pci_count_devs(struct pci_dev *pdev, void *data) } struct vfio_pci_fill_info { - int max; - int cur; + struct vfio_device *vdev; struct vfio_pci_dependent_device *devices; + int nr_devices; + u32 count; + u32 flags; }; static int vfio_pci_fill_devs(struct pci_dev *pdev, void *data) { + struct vfio_pci_dependent_device *info; struct vfio_pci_fill_info *fill = data; - struct iommu_group *iommu_group; - if (fill->cur == fill->max) - return -EAGAIN; /* Something changed, try again */ + /* The topology changed since we counted devices */ + if (fill->count >= fill->nr_devices) + return -EAGAIN; + + info = &fill->devices[fill->count++]; + info->segment = pci_domain_nr(pdev->bus); + info->bus = pdev->bus->number; + info->devfn = pdev->devfn; + + if (fill->flags & VFIO_PCI_HOT_RESET_FLAG_DEV_ID) { + struct iommufd_ctx *iommufd = vfio_iommufd_device_ictx(fill->vdev); + struct vfio_device_set *dev_set = fill->vdev->dev_set; + struct vfio_device *vdev; + + /* + * hot-reset requires all affected devices be represented in + * the dev_set. + */ + vdev = vfio_find_device_in_devset(dev_set, &pdev->dev); + if (!vdev) { + info->devid = VFIO_PCI_DEVID_NOT_OWNED; + } else { + int id = vfio_iommufd_get_dev_id(vdev, iommufd); + + if (id > 0) + info->devid = id; + else if (id == -ENOENT) + info->devid = VFIO_PCI_DEVID_OWNED; + else + info->devid = VFIO_PCI_DEVID_NOT_OWNED; + } + /* If devid is VFIO_PCI_DEVID_NOT_OWNED, clear owned flag. */ + if (info->devid == VFIO_PCI_DEVID_NOT_OWNED) + fill->flags &= ~VFIO_PCI_HOT_RESET_FLAG_DEV_ID_OWNED; + } else { + struct iommu_group *iommu_group; - iommu_group = iommu_group_get(&pdev->dev); - if (!iommu_group) - return -EPERM; /* Cannot reset non-isolated devices */ + iommu_group = iommu_group_get(&pdev->dev); + if (!iommu_group) + return -EPERM; /* Cannot reset non-isolated devices */ + + info->group_id = iommu_group_id(iommu_group); + iommu_group_put(iommu_group); + } - fill->devices[fill->cur].group_id = iommu_group_id(iommu_group); - fill->devices[fill->cur].segment = pci_domain_nr(pdev->bus); - fill->devices[fill->cur].bus = pdev->bus->number; - fill->devices[fill->cur].devfn = pdev->devfn; - fill->cur++; - iommu_group_put(iommu_group); return 0; } struct vfio_pci_group_info { int count; - struct vfio_group **groups; + struct file **files; }; static bool vfio_pci_dev_below_slot(struct pci_dev *pdev, struct pci_slot *slot) @@ -607,16 +910,16 @@ static int msix_mmappable_cap(struct vfio_pci_core_device *vdev, return vfio_info_add_capability(caps, &header, sizeof(header)); } -int vfio_pci_register_dev_region(struct vfio_pci_core_device *vdev, - unsigned int type, unsigned int subtype, - const struct vfio_pci_regops *ops, - size_t size, u32 flags, void *data) +int vfio_pci_core_register_dev_region(struct vfio_pci_core_device *vdev, + unsigned int type, unsigned int subtype, + const struct vfio_pci_regops *ops, + size_t size, u32 flags, void *data) { struct vfio_pci_region *region; region = krealloc(vdev->region, (vdev->num_regions + 1) * sizeof(*region), - GFP_KERNEL); + GFP_KERNEL_ACCOUNT); if (!region) return -ENOMEM; @@ -632,582 +935,648 @@ int vfio_pci_register_dev_region(struct vfio_pci_core_device *vdev, return 0; } -EXPORT_SYMBOL_GPL(vfio_pci_register_dev_region); +EXPORT_SYMBOL_GPL(vfio_pci_core_register_dev_region); -long vfio_pci_core_ioctl(struct vfio_device *core_vdev, unsigned int cmd, - unsigned long arg) +static int vfio_pci_info_atomic_cap(struct vfio_pci_core_device *vdev, + struct vfio_info_cap *caps) { - struct vfio_pci_core_device *vdev = - container_of(core_vdev, struct vfio_pci_core_device, vdev); - unsigned long minsz; + struct vfio_device_info_cap_pci_atomic_comp cap = { + .header.id = VFIO_DEVICE_INFO_CAP_PCI_ATOMIC_COMP, + .header.version = 1 + }; + struct pci_dev *pdev = pci_physfn(vdev->pdev); + u32 devcap2; - if (cmd == VFIO_DEVICE_GET_INFO) { - struct vfio_device_info info; - struct vfio_info_cap caps = { .buf = NULL, .size = 0 }; - unsigned long capsz; - int ret; + pcie_capability_read_dword(pdev, PCI_EXP_DEVCAP2, &devcap2); - minsz = offsetofend(struct vfio_device_info, num_irqs); + if ((devcap2 & PCI_EXP_DEVCAP2_ATOMIC_COMP32) && + !pci_enable_atomic_ops_to_root(pdev, PCI_EXP_DEVCAP2_ATOMIC_COMP32)) + cap.flags |= VFIO_PCI_ATOMIC_COMP32; - /* For backward compatibility, cannot require this */ - capsz = offsetofend(struct vfio_iommu_type1_info, cap_offset); + if ((devcap2 & PCI_EXP_DEVCAP2_ATOMIC_COMP64) && + !pci_enable_atomic_ops_to_root(pdev, PCI_EXP_DEVCAP2_ATOMIC_COMP64)) + cap.flags |= VFIO_PCI_ATOMIC_COMP64; - if (copy_from_user(&info, (void __user *)arg, minsz)) - return -EFAULT; + if ((devcap2 & PCI_EXP_DEVCAP2_ATOMIC_COMP128) && + !pci_enable_atomic_ops_to_root(pdev, + PCI_EXP_DEVCAP2_ATOMIC_COMP128)) + cap.flags |= VFIO_PCI_ATOMIC_COMP128; - if (info.argsz < minsz) - return -EINVAL; + if (!cap.flags) + return -ENODEV; - if (info.argsz >= capsz) { - minsz = capsz; - info.cap_offset = 0; - } + return vfio_info_add_capability(caps, &cap.header, sizeof(cap)); +} - info.flags = VFIO_DEVICE_FLAGS_PCI; +static int vfio_pci_ioctl_get_info(struct vfio_pci_core_device *vdev, + struct vfio_device_info __user *arg) +{ + unsigned long minsz = offsetofend(struct vfio_device_info, num_irqs); + struct vfio_device_info info = {}; + struct vfio_info_cap caps = { .buf = NULL, .size = 0 }; + int ret; - if (vdev->reset_works) - info.flags |= VFIO_DEVICE_FLAGS_RESET; + if (copy_from_user(&info, arg, minsz)) + return -EFAULT; - info.num_regions = VFIO_PCI_NUM_REGIONS + vdev->num_regions; - info.num_irqs = VFIO_PCI_NUM_IRQS; + if (info.argsz < minsz) + return -EINVAL; - ret = vfio_pci_info_zdev_add_caps(vdev, &caps); - if (ret && ret != -ENODEV) { - pci_warn(vdev->pdev, "Failed to setup zPCI info capabilities\n"); - return ret; - } + minsz = min_t(size_t, info.argsz, sizeof(info)); - if (caps.size) { - info.flags |= VFIO_DEVICE_FLAGS_CAPS; - if (info.argsz < sizeof(info) + caps.size) { - info.argsz = sizeof(info) + caps.size; - } else { - vfio_info_cap_shift(&caps, sizeof(info)); - if (copy_to_user((void __user *)arg + - sizeof(info), caps.buf, - caps.size)) { - kfree(caps.buf); - return -EFAULT; - } - info.cap_offset = sizeof(info); - } + info.flags = VFIO_DEVICE_FLAGS_PCI; - kfree(caps.buf); - } + if (vdev->reset_works) + info.flags |= VFIO_DEVICE_FLAGS_RESET; - return copy_to_user((void __user *)arg, &info, minsz) ? - -EFAULT : 0; + info.num_regions = VFIO_PCI_NUM_REGIONS + vdev->num_regions; + info.num_irqs = VFIO_PCI_NUM_IRQS; - } else if (cmd == VFIO_DEVICE_GET_REGION_INFO) { - struct pci_dev *pdev = vdev->pdev; - struct vfio_region_info info; - struct vfio_info_cap caps = { .buf = NULL, .size = 0 }; - int i, ret; + ret = vfio_pci_info_zdev_add_caps(vdev, &caps); + if (ret && ret != -ENODEV) { + pci_warn(vdev->pdev, + "Failed to setup zPCI info capabilities\n"); + return ret; + } - minsz = offsetofend(struct vfio_region_info, offset); + ret = vfio_pci_info_atomic_cap(vdev, &caps); + if (ret && ret != -ENODEV) { + pci_warn(vdev->pdev, + "Failed to setup AtomicOps info capability\n"); + return ret; + } - if (copy_from_user(&info, (void __user *)arg, minsz)) - return -EFAULT; + if (caps.size) { + info.flags |= VFIO_DEVICE_FLAGS_CAPS; + if (info.argsz < sizeof(info) + caps.size) { + info.argsz = sizeof(info) + caps.size; + } else { + vfio_info_cap_shift(&caps, sizeof(info)); + if (copy_to_user(arg + 1, caps.buf, caps.size)) { + kfree(caps.buf); + return -EFAULT; + } + info.cap_offset = sizeof(*arg); + } - if (info.argsz < minsz) - return -EINVAL; + kfree(caps.buf); + } - switch (info.index) { - case VFIO_PCI_CONFIG_REGION_INDEX: - info.offset = VFIO_PCI_INDEX_TO_OFFSET(info.index); - info.size = pdev->cfg_size; - info.flags = VFIO_REGION_INFO_FLAG_READ | - VFIO_REGION_INFO_FLAG_WRITE; - break; - case VFIO_PCI_BAR0_REGION_INDEX ... VFIO_PCI_BAR5_REGION_INDEX: - info.offset = VFIO_PCI_INDEX_TO_OFFSET(info.index); - info.size = pci_resource_len(pdev, info.index); - if (!info.size) { - info.flags = 0; - break; - } + return copy_to_user(arg, &info, minsz) ? -EFAULT : 0; +} - info.flags = VFIO_REGION_INFO_FLAG_READ | - VFIO_REGION_INFO_FLAG_WRITE; - if (vdev->bar_mmap_supported[info.index]) { - info.flags |= VFIO_REGION_INFO_FLAG_MMAP; - if (info.index == vdev->msix_bar) { - ret = msix_mmappable_cap(vdev, &caps); - if (ret) - return ret; - } - } +int vfio_pci_ioctl_get_region_info(struct vfio_device *core_vdev, + struct vfio_region_info *info, + struct vfio_info_cap *caps) +{ + struct vfio_pci_core_device *vdev = + container_of(core_vdev, struct vfio_pci_core_device, vdev); + struct pci_dev *pdev = vdev->pdev; + int i, ret; + switch (info->index) { + case VFIO_PCI_CONFIG_REGION_INDEX: + info->offset = VFIO_PCI_INDEX_TO_OFFSET(info->index); + info->size = pdev->cfg_size; + info->flags = VFIO_REGION_INFO_FLAG_READ | + VFIO_REGION_INFO_FLAG_WRITE; + break; + case VFIO_PCI_BAR0_REGION_INDEX ... VFIO_PCI_BAR5_REGION_INDEX: + info->offset = VFIO_PCI_INDEX_TO_OFFSET(info->index); + info->size = pci_resource_len(pdev, info->index); + if (!info->size) { + info->flags = 0; break; - case VFIO_PCI_ROM_REGION_INDEX: - { - void __iomem *io; - size_t size; - u16 cmd; - - info.offset = VFIO_PCI_INDEX_TO_OFFSET(info.index); - info.flags = 0; - - /* Report the BAR size, not the ROM size */ - info.size = pci_resource_len(pdev, info.index); - if (!info.size) { - /* Shadow ROMs appear as PCI option ROMs */ - if (pdev->resource[PCI_ROM_RESOURCE].flags & - IORESOURCE_ROM_SHADOW) - info.size = 0x20000; - else - break; + } + + info->flags = VFIO_REGION_INFO_FLAG_READ | + VFIO_REGION_INFO_FLAG_WRITE; + if (vdev->bar_mmap_supported[info->index]) { + info->flags |= VFIO_REGION_INFO_FLAG_MMAP; + if (info->index == vdev->msix_bar) { + ret = msix_mmappable_cap(vdev, caps); + if (ret) + return ret; } + } + + break; + case VFIO_PCI_ROM_REGION_INDEX: { + void __iomem *io; + size_t size; + u16 cmd; + info->offset = VFIO_PCI_INDEX_TO_OFFSET(info->index); + info->flags = 0; + info->size = 0; + + if (pci_resource_start(pdev, PCI_ROM_RESOURCE)) { /* - * Is it really there? Enable memory decode for - * implicit access in pci_map_rom(). + * Check ROM content is valid. Need to enable memory + * decode for ROM access in pci_map_rom(). */ cmd = vfio_pci_memory_lock_and_enable(vdev); io = pci_map_rom(pdev, &size); if (io) { - info.flags = VFIO_REGION_INFO_FLAG_READ; + info->flags = VFIO_REGION_INFO_FLAG_READ; + /* Report the BAR size, not the ROM size. */ + info->size = pci_resource_len(pdev, + PCI_ROM_RESOURCE); pci_unmap_rom(pdev, io); - } else { - info.size = 0; } vfio_pci_memory_unlock_and_restore(vdev, cmd); - - break; + } else if (pdev->rom && pdev->romlen) { + info->flags = VFIO_REGION_INFO_FLAG_READ; + /* Report BAR size as power of two. */ + info->size = roundup_pow_of_two(pdev->romlen); } - case VFIO_PCI_VGA_REGION_INDEX: - if (!vdev->has_vga) - return -EINVAL; - info.offset = VFIO_PCI_INDEX_TO_OFFSET(info.index); - info.size = 0xc0000; - info.flags = VFIO_REGION_INFO_FLAG_READ | - VFIO_REGION_INFO_FLAG_WRITE; - - break; - default: - { - struct vfio_region_info_cap_type cap_type = { - .header.id = VFIO_REGION_INFO_CAP_TYPE, - .header.version = 1 }; + break; + } + case VFIO_PCI_VGA_REGION_INDEX: + if (!vdev->has_vga) + return -EINVAL; - if (info.index >= - VFIO_PCI_NUM_REGIONS + vdev->num_regions) - return -EINVAL; - info.index = array_index_nospec(info.index, - VFIO_PCI_NUM_REGIONS + - vdev->num_regions); + info->offset = VFIO_PCI_INDEX_TO_OFFSET(info->index); + info->size = 0xc0000; + info->flags = VFIO_REGION_INFO_FLAG_READ | + VFIO_REGION_INFO_FLAG_WRITE; - i = info.index - VFIO_PCI_NUM_REGIONS; + break; + default: { + struct vfio_region_info_cap_type cap_type = { + .header.id = VFIO_REGION_INFO_CAP_TYPE, + .header.version = 1 + }; - info.offset = VFIO_PCI_INDEX_TO_OFFSET(info.index); - info.size = vdev->region[i].size; - info.flags = vdev->region[i].flags; + if (info->index >= VFIO_PCI_NUM_REGIONS + vdev->num_regions) + return -EINVAL; + info->index = array_index_nospec( + info->index, VFIO_PCI_NUM_REGIONS + vdev->num_regions); - cap_type.type = vdev->region[i].type; - cap_type.subtype = vdev->region[i].subtype; + i = info->index - VFIO_PCI_NUM_REGIONS; - ret = vfio_info_add_capability(&caps, &cap_type.header, - sizeof(cap_type)); - if (ret) - return ret; + info->offset = VFIO_PCI_INDEX_TO_OFFSET(info->index); + info->size = vdev->region[i].size; + info->flags = vdev->region[i].flags; - if (vdev->region[i].ops->add_capability) { - ret = vdev->region[i].ops->add_capability(vdev, - &vdev->region[i], &caps); - if (ret) - return ret; - } - } - } + cap_type.type = vdev->region[i].type; + cap_type.subtype = vdev->region[i].subtype; - if (caps.size) { - info.flags |= VFIO_REGION_INFO_FLAG_CAPS; - if (info.argsz < sizeof(info) + caps.size) { - info.argsz = sizeof(info) + caps.size; - info.cap_offset = 0; - } else { - vfio_info_cap_shift(&caps, sizeof(info)); - if (copy_to_user((void __user *)arg + - sizeof(info), caps.buf, - caps.size)) { - kfree(caps.buf); - return -EFAULT; - } - info.cap_offset = sizeof(info); - } + ret = vfio_info_add_capability(caps, &cap_type.header, + sizeof(cap_type)); + if (ret) + return ret; - kfree(caps.buf); + if (vdev->region[i].ops->add_capability) { + ret = vdev->region[i].ops->add_capability( + vdev, &vdev->region[i], caps); + if (ret) + return ret; } + } + } + return 0; +} +EXPORT_SYMBOL_GPL(vfio_pci_ioctl_get_region_info); - return copy_to_user((void __user *)arg, &info, minsz) ? - -EFAULT : 0; - - } else if (cmd == VFIO_DEVICE_GET_IRQ_INFO) { - struct vfio_irq_info info; - - minsz = offsetofend(struct vfio_irq_info, count); +static int vfio_pci_ioctl_get_irq_info(struct vfio_pci_core_device *vdev, + struct vfio_irq_info __user *arg) +{ + unsigned long minsz = offsetofend(struct vfio_irq_info, count); + struct vfio_irq_info info; - if (copy_from_user(&info, (void __user *)arg, minsz)) - return -EFAULT; + if (copy_from_user(&info, arg, minsz)) + return -EFAULT; - if (info.argsz < minsz || info.index >= VFIO_PCI_NUM_IRQS) - return -EINVAL; + if (info.argsz < minsz || info.index >= VFIO_PCI_NUM_IRQS) + return -EINVAL; - switch (info.index) { - case VFIO_PCI_INTX_IRQ_INDEX ... VFIO_PCI_MSIX_IRQ_INDEX: - case VFIO_PCI_REQ_IRQ_INDEX: + switch (info.index) { + case VFIO_PCI_INTX_IRQ_INDEX ... VFIO_PCI_MSIX_IRQ_INDEX: + case VFIO_PCI_REQ_IRQ_INDEX: + break; + case VFIO_PCI_ERR_IRQ_INDEX: + if (pci_is_pcie(vdev->pdev)) break; - case VFIO_PCI_ERR_IRQ_INDEX: - if (pci_is_pcie(vdev->pdev)) - break; - fallthrough; - default: - return -EINVAL; - } + fallthrough; + default: + return -EINVAL; + } - info.flags = VFIO_IRQ_INFO_EVENTFD; + info.flags = VFIO_IRQ_INFO_EVENTFD; - info.count = vfio_pci_get_irq_count(vdev, info.index); + info.count = vfio_pci_get_irq_count(vdev, info.index); - if (info.index == VFIO_PCI_INTX_IRQ_INDEX) - info.flags |= (VFIO_IRQ_INFO_MASKABLE | - VFIO_IRQ_INFO_AUTOMASKED); - else - info.flags |= VFIO_IRQ_INFO_NORESIZE; + if (info.index == VFIO_PCI_INTX_IRQ_INDEX) + info.flags |= + (VFIO_IRQ_INFO_MASKABLE | VFIO_IRQ_INFO_AUTOMASKED); + else if (info.index != VFIO_PCI_MSIX_IRQ_INDEX || !vdev->has_dyn_msix) + info.flags |= VFIO_IRQ_INFO_NORESIZE; - return copy_to_user((void __user *)arg, &info, minsz) ? - -EFAULT : 0; + return copy_to_user(arg, &info, minsz) ? -EFAULT : 0; +} - } else if (cmd == VFIO_DEVICE_SET_IRQS) { - struct vfio_irq_set hdr; - u8 *data = NULL; - int max, ret = 0; - size_t data_size = 0; +static int vfio_pci_ioctl_set_irqs(struct vfio_pci_core_device *vdev, + struct vfio_irq_set __user *arg) +{ + unsigned long minsz = offsetofend(struct vfio_irq_set, count); + struct vfio_irq_set hdr; + u8 *data = NULL; + int max, ret = 0; + size_t data_size = 0; - minsz = offsetofend(struct vfio_irq_set, count); + if (copy_from_user(&hdr, arg, minsz)) + return -EFAULT; - if (copy_from_user(&hdr, (void __user *)arg, minsz)) - return -EFAULT; + max = vfio_pci_get_irq_count(vdev, hdr.index); - max = vfio_pci_get_irq_count(vdev, hdr.index); + ret = vfio_set_irqs_validate_and_prepare(&hdr, max, VFIO_PCI_NUM_IRQS, + &data_size); + if (ret) + return ret; - ret = vfio_set_irqs_validate_and_prepare(&hdr, max, - VFIO_PCI_NUM_IRQS, &data_size); - if (ret) - return ret; + if (data_size) { + data = memdup_user(&arg->data, data_size); + if (IS_ERR(data)) + return PTR_ERR(data); + } - if (data_size) { - data = memdup_user((void __user *)(arg + minsz), - data_size); - if (IS_ERR(data)) - return PTR_ERR(data); - } + mutex_lock(&vdev->igate); - mutex_lock(&vdev->igate); + ret = vfio_pci_set_irqs_ioctl(vdev, hdr.flags, hdr.index, hdr.start, + hdr.count, data); - ret = vfio_pci_set_irqs_ioctl(vdev, hdr.flags, hdr.index, - hdr.start, hdr.count, data); + mutex_unlock(&vdev->igate); + kfree(data); - mutex_unlock(&vdev->igate); - kfree(data); + return ret; +} - return ret; +static int vfio_pci_ioctl_reset(struct vfio_pci_core_device *vdev, + void __user *arg) +{ + int ret; - } else if (cmd == VFIO_DEVICE_RESET) { - int ret; + if (!vdev->reset_works) + return -EINVAL; - if (!vdev->reset_works) - return -EINVAL; + vfio_pci_zap_and_down_write_memory_lock(vdev); - vfio_pci_zap_and_down_write_memory_lock(vdev); - ret = pci_try_reset_function(vdev->pdev); - up_write(&vdev->memory_lock); + /* + * 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); - return ret; + vfio_pci_dma_buf_move(vdev, true); + ret = pci_try_reset_function(vdev->pdev); + if (__vfio_pci_memory_enabled(vdev)) + vfio_pci_dma_buf_move(vdev, false); + up_write(&vdev->memory_lock); - } else if (cmd == VFIO_DEVICE_GET_PCI_HOT_RESET_INFO) { - struct vfio_pci_hot_reset_info hdr; - struct vfio_pci_fill_info fill = { 0 }; - struct vfio_pci_dependent_device *devices = NULL; - bool slot = false; - int ret = 0; + return ret; +} - minsz = offsetofend(struct vfio_pci_hot_reset_info, count); +static int vfio_pci_ioctl_get_pci_hot_reset_info( + struct vfio_pci_core_device *vdev, + struct vfio_pci_hot_reset_info __user *arg) +{ + unsigned long minsz = + offsetofend(struct vfio_pci_hot_reset_info, count); + struct vfio_pci_dependent_device *devices = NULL; + struct vfio_pci_hot_reset_info hdr; + struct vfio_pci_fill_info fill = {}; + bool slot = false; + int ret, count = 0; + + if (copy_from_user(&hdr, arg, minsz)) + return -EFAULT; + + if (hdr.argsz < minsz) + return -EINVAL; - if (copy_from_user(&hdr, (void __user *)arg, minsz)) - return -EFAULT; + hdr.flags = 0; - if (hdr.argsz < minsz) - return -EINVAL; + /* Can we do a slot or bus reset or neither? */ + if (!pci_probe_reset_slot(vdev->pdev->slot)) + slot = true; + else if (pci_probe_reset_bus(vdev->pdev->bus)) + return -ENODEV; - hdr.flags = 0; + ret = vfio_pci_for_each_slot_or_bus(vdev->pdev, vfio_pci_count_devs, + &count, slot); + if (ret) + return ret; - /* Can we do a slot or bus reset or neither? */ - if (!pci_probe_reset_slot(vdev->pdev->slot)) - slot = true; - else if (pci_probe_reset_bus(vdev->pdev->bus)) - return -ENODEV; + if (WARN_ON(!count)) /* Should always be at least one */ + return -ERANGE; - /* How many devices are affected? */ - ret = vfio_pci_for_each_slot_or_bus(vdev->pdev, - vfio_pci_count_devs, - &fill.max, slot); - if (ret) - return ret; + if (count > (hdr.argsz - sizeof(hdr)) / sizeof(*devices)) { + hdr.count = count; + ret = -ENOSPC; + goto header; + } - WARN_ON(!fill.max); /* Should always be at least one */ + devices = kcalloc(count, sizeof(*devices), GFP_KERNEL); + if (!devices) + return -ENOMEM; - /* - * If there's enough space, fill it now, otherwise return - * -ENOSPC and the number of devices affected. - */ - if (hdr.argsz < sizeof(hdr) + (fill.max * sizeof(*devices))) { - ret = -ENOSPC; - hdr.count = fill.max; - goto reset_info_exit; - } + fill.devices = devices; + fill.nr_devices = count; + fill.vdev = &vdev->vdev; - devices = kcalloc(fill.max, sizeof(*devices), GFP_KERNEL); - if (!devices) - return -ENOMEM; + if (vfio_device_cdev_opened(&vdev->vdev)) + fill.flags |= VFIO_PCI_HOT_RESET_FLAG_DEV_ID | + VFIO_PCI_HOT_RESET_FLAG_DEV_ID_OWNED; - fill.devices = devices; + mutex_lock(&vdev->vdev.dev_set->lock); + ret = vfio_pci_for_each_slot_or_bus(vdev->pdev, vfio_pci_fill_devs, + &fill, slot); + mutex_unlock(&vdev->vdev.dev_set->lock); + if (ret) + goto out; - ret = vfio_pci_for_each_slot_or_bus(vdev->pdev, - vfio_pci_fill_devs, - &fill, slot); + if (copy_to_user(arg->devices, devices, + sizeof(*devices) * fill.count)) { + ret = -EFAULT; + goto out; + } - /* - * If a device was removed between counting and filling, - * we may come up short of fill.max. If a device was - * added, we'll have a return of -EAGAIN above. - */ - if (!ret) - hdr.count = fill.cur; + hdr.count = fill.count; + hdr.flags = fill.flags; -reset_info_exit: - if (copy_to_user((void __user *)arg, &hdr, minsz)) - ret = -EFAULT; +header: + if (copy_to_user(arg, &hdr, minsz)) + ret = -EFAULT; +out: + kfree(devices); + return ret; +} - if (!ret) { - if (copy_to_user((void __user *)(arg + minsz), devices, - hdr.count * sizeof(*devices))) - ret = -EFAULT; - } +static int +vfio_pci_ioctl_pci_hot_reset_groups(struct vfio_pci_core_device *vdev, + u32 array_count, bool slot, + struct vfio_pci_hot_reset __user *arg) +{ + int32_t *group_fds; + struct file **files; + struct vfio_pci_group_info info; + int file_idx, count = 0, ret = 0; - kfree(devices); + /* + * We can't let userspace give us an arbitrarily large buffer to copy, + * so verify how many we think there could be. Note groups can have + * multiple devices so one group per device is the max. + */ + ret = vfio_pci_for_each_slot_or_bus(vdev->pdev, vfio_pci_count_devs, + &count, slot); + if (ret) return ret; - } else if (cmd == VFIO_DEVICE_PCI_HOT_RESET) { - struct vfio_pci_hot_reset hdr; - int32_t *group_fds; - struct vfio_group **groups; - struct vfio_pci_group_info info; - bool slot = false; - int group_idx, count = 0, ret = 0; - - minsz = offsetofend(struct vfio_pci_hot_reset, count); - - if (copy_from_user(&hdr, (void __user *)arg, minsz)) - return -EFAULT; - - if (hdr.argsz < minsz || hdr.flags) - return -EINVAL; + if (array_count > count) + return -EINVAL; - /* Can we do a slot or bus reset or neither? */ - if (!pci_probe_reset_slot(vdev->pdev->slot)) - slot = true; - else if (pci_probe_reset_bus(vdev->pdev->bus)) - return -ENODEV; + group_fds = kcalloc(array_count, sizeof(*group_fds), GFP_KERNEL); + files = kcalloc(array_count, sizeof(*files), GFP_KERNEL); + if (!group_fds || !files) { + kfree(group_fds); + kfree(files); + return -ENOMEM; + } - /* - * We can't let userspace give us an arbitrarily large - * buffer to copy, so verify how many we think there - * could be. Note groups can have multiple devices so - * one group per device is the max. - */ - ret = vfio_pci_for_each_slot_or_bus(vdev->pdev, - vfio_pci_count_devs, - &count, slot); - if (ret) - return ret; + if (copy_from_user(group_fds, arg->group_fds, + array_count * sizeof(*group_fds))) { + kfree(group_fds); + kfree(files); + return -EFAULT; + } - /* Somewhere between 1 and count is OK */ - if (!hdr.count || hdr.count > count) - return -EINVAL; + /* + * Get the group file for each fd to ensure the group is held across + * the reset + */ + for (file_idx = 0; file_idx < array_count; file_idx++) { + struct file *file = fget(group_fds[file_idx]); - group_fds = kcalloc(hdr.count, sizeof(*group_fds), GFP_KERNEL); - groups = kcalloc(hdr.count, sizeof(*groups), GFP_KERNEL); - if (!group_fds || !groups) { - kfree(group_fds); - kfree(groups); - return -ENOMEM; + if (!file) { + ret = -EBADF; + break; } - if (copy_from_user(group_fds, (void __user *)(arg + minsz), - hdr.count * sizeof(*group_fds))) { - kfree(group_fds); - kfree(groups); - return -EFAULT; + /* Ensure the FD is a vfio group FD.*/ + if (!vfio_file_is_group(file)) { + fput(file); + ret = -EINVAL; + break; } - /* - * For each group_fd, get the group through the vfio external - * user interface and store the group and iommu ID. This - * ensures the group is held across the reset. - */ - for (group_idx = 0; group_idx < hdr.count; group_idx++) { - struct vfio_group *group; - struct fd f = fdget(group_fds[group_idx]); - if (!f.file) { - ret = -EBADF; - break; - } - - group = vfio_group_get_external_user(f.file); - fdput(f); - if (IS_ERR(group)) { - ret = PTR_ERR(group); - break; - } + files[file_idx] = file; + } - groups[group_idx] = group; - } + kfree(group_fds); - kfree(group_fds); - - /* release reference to groups on error */ - if (ret) - goto hot_reset_release; + /* release reference to groups on error */ + if (ret) + goto hot_reset_release; - info.count = hdr.count; - info.groups = groups; + info.count = array_count; + info.files = files; - ret = vfio_pci_dev_set_hot_reset(vdev->vdev.dev_set, &info); + ret = vfio_pci_dev_set_hot_reset(vdev->vdev.dev_set, &info, NULL); hot_reset_release: - for (group_idx--; group_idx >= 0; group_idx--) - vfio_group_put_external_user(groups[group_idx]); + for (file_idx--; file_idx >= 0; file_idx--) + fput(files[file_idx]); - kfree(groups); - return ret; - } else if (cmd == VFIO_DEVICE_IOEVENTFD) { - struct vfio_device_ioeventfd ioeventfd; - int count; + kfree(files); + return ret; +} - minsz = offsetofend(struct vfio_device_ioeventfd, fd); +static int vfio_pci_ioctl_pci_hot_reset(struct vfio_pci_core_device *vdev, + struct vfio_pci_hot_reset __user *arg) +{ + unsigned long minsz = offsetofend(struct vfio_pci_hot_reset, count); + struct vfio_pci_hot_reset hdr; + bool slot = false; - if (copy_from_user(&ioeventfd, (void __user *)arg, minsz)) - return -EFAULT; + if (copy_from_user(&hdr, arg, minsz)) + return -EFAULT; - if (ioeventfd.argsz < minsz) - return -EINVAL; + if (hdr.argsz < minsz || hdr.flags) + return -EINVAL; - if (ioeventfd.flags & ~VFIO_DEVICE_IOEVENTFD_SIZE_MASK) - return -EINVAL; + /* zero-length array is only for cdev opened devices */ + if (!!hdr.count == vfio_device_cdev_opened(&vdev->vdev)) + return -EINVAL; - count = ioeventfd.flags & VFIO_DEVICE_IOEVENTFD_SIZE_MASK; + /* Can we do a slot or bus reset or neither? */ + if (!pci_probe_reset_slot(vdev->pdev->slot)) + slot = true; + else if (pci_probe_reset_bus(vdev->pdev->bus)) + return -ENODEV; - if (hweight8(count) != 1 || ioeventfd.fd < -1) - return -EINVAL; + if (hdr.count) + return vfio_pci_ioctl_pci_hot_reset_groups(vdev, hdr.count, slot, arg); - return vfio_pci_ioeventfd(vdev, ioeventfd.offset, - ioeventfd.data, count, ioeventfd.fd); - } else if (cmd == VFIO_DEVICE_FEATURE) { - struct vfio_device_feature feature; - uuid_t uuid; + return vfio_pci_dev_set_hot_reset(vdev->vdev.dev_set, NULL, + vfio_iommufd_device_ictx(&vdev->vdev)); +} - minsz = offsetofend(struct vfio_device_feature, flags); +static int vfio_pci_ioctl_ioeventfd(struct vfio_pci_core_device *vdev, + struct vfio_device_ioeventfd __user *arg) +{ + unsigned long minsz = offsetofend(struct vfio_device_ioeventfd, fd); + struct vfio_device_ioeventfd ioeventfd; + int count; - if (copy_from_user(&feature, (void __user *)arg, minsz)) - return -EFAULT; + if (copy_from_user(&ioeventfd, arg, minsz)) + return -EFAULT; - if (feature.argsz < minsz) - return -EINVAL; + if (ioeventfd.argsz < minsz) + return -EINVAL; - /* Check unknown flags */ - if (feature.flags & ~(VFIO_DEVICE_FEATURE_MASK | - VFIO_DEVICE_FEATURE_SET | - VFIO_DEVICE_FEATURE_GET | - VFIO_DEVICE_FEATURE_PROBE)) - return -EINVAL; + if (ioeventfd.flags & ~VFIO_DEVICE_IOEVENTFD_SIZE_MASK) + return -EINVAL; - /* GET & SET are mutually exclusive except with PROBE */ - if (!(feature.flags & VFIO_DEVICE_FEATURE_PROBE) && - (feature.flags & VFIO_DEVICE_FEATURE_SET) && - (feature.flags & VFIO_DEVICE_FEATURE_GET)) - return -EINVAL; + count = ioeventfd.flags & VFIO_DEVICE_IOEVENTFD_SIZE_MASK; - switch (feature.flags & VFIO_DEVICE_FEATURE_MASK) { - case VFIO_DEVICE_FEATURE_PCI_VF_TOKEN: - if (!vdev->vf_token) - return -ENOTTY; + if (hweight8(count) != 1 || ioeventfd.fd < -1) + return -EINVAL; - /* - * We do not support GET of the VF Token UUID as this - * could expose the token of the previous device user. - */ - if (feature.flags & VFIO_DEVICE_FEATURE_GET) - return -EINVAL; + return vfio_pci_ioeventfd(vdev, ioeventfd.offset, ioeventfd.data, count, + ioeventfd.fd); +} - if (feature.flags & VFIO_DEVICE_FEATURE_PROBE) - return 0; +long vfio_pci_core_ioctl(struct vfio_device *core_vdev, unsigned int cmd, + unsigned long arg) +{ + struct vfio_pci_core_device *vdev = + container_of(core_vdev, struct vfio_pci_core_device, vdev); + void __user *uarg = (void __user *)arg; + + switch (cmd) { + case VFIO_DEVICE_GET_INFO: + return vfio_pci_ioctl_get_info(vdev, uarg); + case VFIO_DEVICE_GET_IRQ_INFO: + return vfio_pci_ioctl_get_irq_info(vdev, uarg); + case VFIO_DEVICE_GET_PCI_HOT_RESET_INFO: + return vfio_pci_ioctl_get_pci_hot_reset_info(vdev, uarg); + case VFIO_DEVICE_IOEVENTFD: + return vfio_pci_ioctl_ioeventfd(vdev, uarg); + case VFIO_DEVICE_PCI_HOT_RESET: + return vfio_pci_ioctl_pci_hot_reset(vdev, uarg); + case VFIO_DEVICE_RESET: + return vfio_pci_ioctl_reset(vdev, uarg); + case VFIO_DEVICE_SET_IRQS: + return vfio_pci_ioctl_set_irqs(vdev, uarg); + default: + return -ENOTTY; + } +} +EXPORT_SYMBOL_GPL(vfio_pci_core_ioctl); - /* Don't SET unless told to do so */ - if (!(feature.flags & VFIO_DEVICE_FEATURE_SET)) - return -EINVAL; +static int vfio_pci_core_feature_token(struct vfio_pci_core_device *vdev, + u32 flags, uuid_t __user *arg, + size_t argsz) +{ + uuid_t uuid; + int ret; - if (feature.argsz < minsz + sizeof(uuid)) - return -EINVAL; + if (!vdev->vf_token) + return -ENOTTY; + /* + * We do not support GET of the VF Token UUID as this could + * expose the token of the previous device user. + */ + ret = vfio_check_feature(flags, argsz, VFIO_DEVICE_FEATURE_SET, + sizeof(uuid)); + if (ret != 1) + return ret; - if (copy_from_user(&uuid, (void __user *)(arg + minsz), - sizeof(uuid))) - return -EFAULT; + if (copy_from_user(&uuid, arg, sizeof(uuid))) + return -EFAULT; - mutex_lock(&vdev->vf_token->lock); - uuid_copy(&vdev->vf_token->uuid, &uuid); - mutex_unlock(&vdev->vf_token->lock); + mutex_lock(&vdev->vf_token->lock); + uuid_copy(&vdev->vf_token->uuid, &uuid); + mutex_unlock(&vdev->vf_token->lock); + return 0; +} - return 0; - default: - return -ENOTTY; - } +int vfio_pci_core_ioctl_feature(struct vfio_device *device, u32 flags, + void __user *arg, size_t argsz) +{ + struct vfio_pci_core_device *vdev = + container_of(device, struct vfio_pci_core_device, vdev); + + switch (flags & VFIO_DEVICE_FEATURE_MASK) { + case VFIO_DEVICE_FEATURE_LOW_POWER_ENTRY: + return vfio_pci_core_pm_entry(vdev, flags, arg, argsz); + case VFIO_DEVICE_FEATURE_LOW_POWER_ENTRY_WITH_WAKEUP: + return vfio_pci_core_pm_entry_with_wakeup(vdev, flags, + arg, argsz); + case VFIO_DEVICE_FEATURE_LOW_POWER_EXIT: + return vfio_pci_core_pm_exit(vdev, flags, arg, argsz); + case VFIO_DEVICE_FEATURE_PCI_VF_TOKEN: + return vfio_pci_core_feature_token(vdev, flags, arg, argsz); + case VFIO_DEVICE_FEATURE_DMA_BUF: + return vfio_pci_core_feature_dma_buf(vdev, flags, arg, argsz); + default: + return -ENOTTY; } - - return -ENOTTY; } -EXPORT_SYMBOL_GPL(vfio_pci_core_ioctl); +EXPORT_SYMBOL_GPL(vfio_pci_core_ioctl_feature); static ssize_t vfio_pci_rw(struct vfio_pci_core_device *vdev, char __user *buf, size_t count, loff_t *ppos, bool iswrite) { unsigned int index = VFIO_PCI_OFFSET_TO_INDEX(*ppos); + int ret; if (index >= VFIO_PCI_NUM_REGIONS + vdev->num_regions) return -EINVAL; + ret = pm_runtime_resume_and_get(&vdev->pdev->dev); + if (ret) { + pci_info_ratelimited(vdev->pdev, "runtime resume failed %d\n", + ret); + return -EIO; + } + switch (index) { case VFIO_PCI_CONFIG_REGION_INDEX: - return vfio_pci_config_rw(vdev, buf, count, ppos, iswrite); + ret = vfio_pci_config_rw(vdev, buf, count, ppos, iswrite); + break; case VFIO_PCI_ROM_REGION_INDEX: if (iswrite) - return -EINVAL; - return vfio_pci_bar_rw(vdev, buf, count, ppos, false); + ret = -EINVAL; + else + ret = vfio_pci_bar_rw(vdev, buf, count, ppos, false); + break; case VFIO_PCI_BAR0_REGION_INDEX ... VFIO_PCI_BAR5_REGION_INDEX: - return vfio_pci_bar_rw(vdev, buf, count, ppos, iswrite); + ret = vfio_pci_bar_rw(vdev, buf, count, ppos, iswrite); + break; case VFIO_PCI_VGA_REGION_INDEX: - return vfio_pci_vga_rw(vdev, buf, count, ppos, iswrite); + ret = vfio_pci_vga_rw(vdev, buf, count, ppos, iswrite); + break; + default: index -= VFIO_PCI_NUM_REGIONS; - return vdev->region[index].ops->rw(vdev, buf, + ret = vdev->region[index].ops->rw(vdev, buf, count, ppos, iswrite); + break; } - return -EINVAL; + pm_runtime_put(&vdev->pdev->dev); + return ret; } ssize_t vfio_pci_core_read(struct vfio_device *core_vdev, char __user *buf, @@ -1236,100 +1605,20 @@ ssize_t vfio_pci_core_write(struct vfio_device *core_vdev, const char __user *bu } EXPORT_SYMBOL_GPL(vfio_pci_core_write); -/* Return 1 on zap and vma_lock acquired, 0 on contention (only with @try) */ -static int vfio_pci_zap_and_vma_lock(struct vfio_pci_core_device *vdev, bool try) +static void vfio_pci_zap_bars(struct vfio_pci_core_device *vdev) { - struct vfio_pci_mmap_vma *mmap_vma, *tmp; - - /* - * Lock ordering: - * vma_lock is nested under mmap_lock for vm_ops callback paths. - * The memory_lock semaphore is used by both code paths calling - * into this function to zap vmas and the vm_ops.fault callback - * to protect the memory enable state of the device. - * - * When zapping vmas we need to maintain the mmap_lock => vma_lock - * ordering, which requires using vma_lock to walk vma_list to - * acquire an mm, then dropping vma_lock to get the mmap_lock and - * reacquiring vma_lock. This logic is derived from similar - * requirements in uverbs_user_mmap_disassociate(). - * - * mmap_lock must always be the top-level lock when it is taken. - * Therefore we can only hold the memory_lock write lock when - * vma_list is empty, as we'd need to take mmap_lock to clear - * entries. vma_list can only be guaranteed empty when holding - * vma_lock, thus memory_lock is nested under vma_lock. - * - * This enables the vm_ops.fault callback to acquire vma_lock, - * followed by memory_lock read lock, while already holding - * mmap_lock without risk of deadlock. - */ - while (1) { - struct mm_struct *mm = NULL; - - if (try) { - if (!mutex_trylock(&vdev->vma_lock)) - return 0; - } else { - mutex_lock(&vdev->vma_lock); - } - while (!list_empty(&vdev->vma_list)) { - mmap_vma = list_first_entry(&vdev->vma_list, - struct vfio_pci_mmap_vma, - vma_next); - mm = mmap_vma->vma->vm_mm; - if (mmget_not_zero(mm)) - break; - - list_del(&mmap_vma->vma_next); - kfree(mmap_vma); - mm = NULL; - } - if (!mm) - return 1; - mutex_unlock(&vdev->vma_lock); - - if (try) { - if (!mmap_read_trylock(mm)) { - mmput(mm); - return 0; - } - } else { - mmap_read_lock(mm); - } - if (try) { - if (!mutex_trylock(&vdev->vma_lock)) { - mmap_read_unlock(mm); - mmput(mm); - return 0; - } - } else { - mutex_lock(&vdev->vma_lock); - } - list_for_each_entry_safe(mmap_vma, tmp, - &vdev->vma_list, vma_next) { - struct vm_area_struct *vma = mmap_vma->vma; - - if (vma->vm_mm != mm) - continue; - - list_del(&mmap_vma->vma_next); - kfree(mmap_vma); + struct vfio_device *core_vdev = &vdev->vdev; + loff_t start = VFIO_PCI_INDEX_TO_OFFSET(VFIO_PCI_BAR0_REGION_INDEX); + loff_t end = VFIO_PCI_INDEX_TO_OFFSET(VFIO_PCI_ROM_REGION_INDEX); + loff_t len = end - start; - zap_vma_ptes(vma, vma->vm_start, - vma->vm_end - vma->vm_start); - } - mutex_unlock(&vdev->vma_lock); - mmap_read_unlock(mm); - mmput(mm); - } + unmap_mapping_range(core_vdev->inode->i_mapping, start, len, true); } void vfio_pci_zap_and_down_write_memory_lock(struct vfio_pci_core_device *vdev) { - vfio_pci_zap_and_vma_lock(vdev, false); down_write(&vdev->memory_lock); - mutex_unlock(&vdev->vma_lock); + vfio_pci_zap_bars(vdev); } u16 vfio_pci_memory_lock_and_enable(struct vfio_pci_core_device *vdev) @@ -1351,96 +1640,81 @@ void vfio_pci_memory_unlock_and_restore(struct vfio_pci_core_device *vdev, u16 c up_write(&vdev->memory_lock); } -/* Caller holds vma_lock */ -static int __vfio_pci_add_vma(struct vfio_pci_core_device *vdev, - struct vm_area_struct *vma) +static unsigned long vma_to_pfn(struct vm_area_struct *vma) { - struct vfio_pci_mmap_vma *mmap_vma; - - mmap_vma = kmalloc(sizeof(*mmap_vma), GFP_KERNEL); - if (!mmap_vma) - return -ENOMEM; + struct vfio_pci_core_device *vdev = vma->vm_private_data; + int index = vma->vm_pgoff >> (VFIO_PCI_OFFSET_SHIFT - PAGE_SHIFT); + u64 pgoff; - mmap_vma->vma = vma; - list_add(&mmap_vma->vma_next, &vdev->vma_list); + pgoff = vma->vm_pgoff & + ((1U << (VFIO_PCI_OFFSET_SHIFT - PAGE_SHIFT)) - 1); - return 0; + return (pci_resource_start(vdev->pdev, index) >> PAGE_SHIFT) + pgoff; } -/* - * Zap mmaps on open so that we can fault them in on access and therefore - * our vma_list only tracks mappings accessed since last zap. - */ -static void vfio_pci_mmap_open(struct vm_area_struct *vma) +vm_fault_t vfio_pci_vmf_insert_pfn(struct vfio_pci_core_device *vdev, + struct vm_fault *vmf, + unsigned long pfn, + unsigned int order) { - zap_vma_ptes(vma, vma->vm_start, vma->vm_end - vma->vm_start); -} + lockdep_assert_held_read(&vdev->memory_lock); -static void vfio_pci_mmap_close(struct vm_area_struct *vma) -{ - struct vfio_pci_core_device *vdev = vma->vm_private_data; - struct vfio_pci_mmap_vma *mmap_vma; + if (vdev->pm_runtime_engaged || !__vfio_pci_memory_enabled(vdev)) + return VM_FAULT_SIGBUS; - mutex_lock(&vdev->vma_lock); - list_for_each_entry(mmap_vma, &vdev->vma_list, vma_next) { - if (mmap_vma->vma == vma) { - list_del(&mmap_vma->vma_next); - kfree(mmap_vma); - break; - } + switch (order) { + case 0: + return vmf_insert_pfn(vmf->vma, vmf->address, pfn); +#ifdef CONFIG_ARCH_SUPPORTS_PMD_PFNMAP + case PMD_ORDER: + return vmf_insert_pfn_pmd(vmf, pfn, false); +#endif +#ifdef CONFIG_ARCH_SUPPORTS_PUD_PFNMAP + case PUD_ORDER: + return vmf_insert_pfn_pud(vmf, pfn, false); + break; +#endif + default: + return VM_FAULT_FALLBACK; } - mutex_unlock(&vdev->vma_lock); } +EXPORT_SYMBOL_GPL(vfio_pci_vmf_insert_pfn); -static vm_fault_t vfio_pci_mmap_fault(struct vm_fault *vmf) +static vm_fault_t vfio_pci_mmap_huge_fault(struct vm_fault *vmf, + unsigned int order) { struct vm_area_struct *vma = vmf->vma; struct vfio_pci_core_device *vdev = vma->vm_private_data; - struct vfio_pci_mmap_vma *mmap_vma; - vm_fault_t ret = VM_FAULT_NOPAGE; - - mutex_lock(&vdev->vma_lock); - down_read(&vdev->memory_lock); - - if (!__vfio_pci_memory_enabled(vdev)) { - ret = VM_FAULT_SIGBUS; - goto up_out; + unsigned long addr = vmf->address & ~((PAGE_SIZE << order) - 1); + unsigned long pgoff = (addr - vma->vm_start) >> PAGE_SHIFT; + unsigned long pfn = vma_to_pfn(vma) + pgoff; + vm_fault_t ret = VM_FAULT_FALLBACK; + + if (is_aligned_for_order(vma, addr, pfn, order)) { + scoped_guard(rwsem_read, &vdev->memory_lock) + ret = vfio_pci_vmf_insert_pfn(vdev, vmf, pfn, order); } - /* - * We populate the whole vma on fault, so we need to test whether - * the vma has already been mapped, such as for concurrent faults - * to the same vma. io_remap_pfn_range() will trigger a BUG_ON if - * we ask it to fill the same range again. - */ - list_for_each_entry(mmap_vma, &vdev->vma_list, vma_next) { - if (mmap_vma->vma == vma) - goto up_out; - } + dev_dbg_ratelimited(&vdev->pdev->dev, + "%s(,order = %d) BAR %ld page offset 0x%lx: 0x%x\n", + __func__, order, + vma->vm_pgoff >> + (VFIO_PCI_OFFSET_SHIFT - PAGE_SHIFT), + pgoff, (unsigned int)ret); - if (io_remap_pfn_range(vma, vma->vm_start, vma->vm_pgoff, - vma->vm_end - vma->vm_start, - vma->vm_page_prot)) { - ret = VM_FAULT_SIGBUS; - zap_vma_ptes(vma, vma->vm_start, vma->vm_end - vma->vm_start); - goto up_out; - } - - if (__vfio_pci_add_vma(vdev, vma)) { - ret = VM_FAULT_OOM; - zap_vma_ptes(vma, vma->vm_start, vma->vm_end - vma->vm_start); - } - -up_out: - up_read(&vdev->memory_lock); - mutex_unlock(&vdev->vma_lock); return ret; } +static vm_fault_t vfio_pci_mmap_page_fault(struct vm_fault *vmf) +{ + return vfio_pci_mmap_huge_fault(vmf, 0); +} + static const struct vm_operations_struct vfio_pci_mmap_ops = { - .open = vfio_pci_mmap_open, - .close = vfio_pci_mmap_close, - .fault = vfio_pci_mmap_fault, + .fault = vfio_pci_mmap_page_fault, +#ifdef CONFIG_ARCH_SUPPORTS_HUGE_PFNMAP + .huge_fault = vfio_pci_mmap_huge_fault, +#endif }; int vfio_pci_core_mmap(struct vfio_device *core_vdev, struct vm_area_struct *vma) @@ -1487,28 +1761,37 @@ int vfio_pci_core_mmap(struct vfio_device *core_vdev, struct vm_area_struct *vma * Even though we don't make use of the barmap for the mmap, * we need to request the region and the barmap tracks that. */ - if (!vdev->barmap[index]) { - ret = pci_request_selected_regions(pdev, - 1 << index, "vfio-pci"); - if (ret) - return ret; - - vdev->barmap[index] = pci_iomap(pdev, index, 0); - if (!vdev->barmap[index]) { - pci_release_selected_regions(pdev, 1 << index); - return -ENOMEM; - } - } + ret = vfio_pci_core_setup_barmap(vdev, index); + if (ret) + return ret; vma->vm_private_data = vdev; vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot); - vma->vm_pgoff = (pci_resource_start(pdev, index) >> PAGE_SHIFT) + pgoff; + vma->vm_page_prot = pgprot_decrypted(vma->vm_page_prot); /* - * See remap_pfn_range(), called from vfio_pci_fault() but we can't - * change vm_flags within the fault handler. Set them now. + * Set vm_flags now, they should not be changed in the fault handler. + * We want the same flags and page protection (decrypted above) as + * io_remap_pfn_range() would set. + * + * VM_ALLOW_ANY_UNCACHED: The VMA flag is implemented for ARM64, + * allowing KVM stage 2 device mapping attributes to use Normal-NC + * rather than DEVICE_nGnRE, which allows guest mappings + * supporting write-combining attributes (WC). ARM does not + * architecturally guarantee this is safe, and indeed some MMIO + * regions like the GICv2 VCPU interface can trigger uncontained + * faults if Normal-NC is used. + * + * To safely use VFIO in KVM the platform must guarantee full + * safety in the guest where no action taken against a MMIO + * mapping can trigger an uncontained failure. The assumption is + * that most VFIO PCI platforms support this for both mapping types, + * at least in common flows, based on some expectations of how + * PCI IP is integrated. Hence VM_ALLOW_ANY_UNCACHED is set in + * the VMA flags. */ - vma->vm_flags |= VM_IO | VM_PFNMAP | VM_DONTEXPAND | VM_DONTDUMP; + vm_flags_set(vma, VM_ALLOW_ANY_UNCACHED | VM_IO | VM_PFNMAP | + VM_DONTEXPAND | VM_DONTDUMP); vma->vm_ops = &vfio_pci_mmap_ops; return 0; @@ -1520,27 +1803,31 @@ void vfio_pci_core_request(struct vfio_device *core_vdev, unsigned int count) struct vfio_pci_core_device *vdev = container_of(core_vdev, struct vfio_pci_core_device, vdev); struct pci_dev *pdev = vdev->pdev; + struct vfio_pci_eventfd *eventfd; - mutex_lock(&vdev->igate); - - if (vdev->req_trigger) { + rcu_read_lock(); + eventfd = rcu_dereference(vdev->req_trigger); + if (eventfd) { if (!(count % 10)) pci_notice_ratelimited(pdev, "Relaying device request to user (#%u)\n", count); - eventfd_signal(vdev->req_trigger, 1); + eventfd_signal(eventfd->ctx); } else if (count == 0) { pci_warn(pdev, "No device request channel registered, blocked until released by user\n"); } - - mutex_unlock(&vdev->igate); + rcu_read_unlock(); } EXPORT_SYMBOL_GPL(vfio_pci_core_request); -static int vfio_pci_validate_vf_token(struct vfio_pci_core_device *vdev, - bool vf_token, uuid_t *uuid) +int vfio_pci_core_match_token_uuid(struct vfio_device *core_vdev, + const uuid_t *uuid) + { + struct vfio_pci_core_device *vdev = + container_of(core_vdev, struct vfio_pci_core_device, vdev); + /* * There's always some degree of trust or collaboration between SR-IOV * PF and VFs, even if just that the PF hosts the SR-IOV capability and @@ -1566,15 +1853,12 @@ 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) { - if (!vf_token) + if (!uuid) return 0; /* PF is not vfio-pci, no VF token */ pci_info_ratelimited(vdev->pdev, @@ -1582,8 +1866,7 @@ static int vfio_pci_validate_vf_token(struct vfio_pci_core_device *vdev, return -EINVAL; } - if (!vf_token) { - vfio_device_put(&pf_vdev->vdev); + if (!uuid) { pci_info_ratelimited(vdev->pdev, "VF token required to access device\n"); return -EACCES; @@ -1593,8 +1876,6 @@ 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"); @@ -1603,7 +1884,7 @@ static int vfio_pci_validate_vf_token(struct vfio_pci_core_device *vdev, } else if (vdev->vf_token) { mutex_lock(&vdev->vf_token->lock); if (vdev->vf_token->users) { - if (!vf_token) { + if (!uuid) { mutex_unlock(&vdev->vf_token->lock); pci_info_ratelimited(vdev->pdev, "VF token required to access device\n"); @@ -1616,12 +1897,12 @@ static int vfio_pci_validate_vf_token(struct vfio_pci_core_device *vdev, "Incorrect VF token provided for device\n"); return -EACCES; } - } else if (vf_token) { + } else if (uuid) { uuid_copy(&vdev->vf_token->uuid, uuid); } mutex_unlock(&vdev->vf_token->lock); - } else if (vf_token) { + } else if (uuid) { pci_info_ratelimited(vdev->pdev, "VF token incorrectly provided, not a PF or VF\n"); return -EINVAL; @@ -1629,6 +1910,7 @@ static int vfio_pci_validate_vf_token(struct vfio_pci_core_device *vdev, return 0; } +EXPORT_SYMBOL_GPL(vfio_pci_core_match_token_uuid); #define VF_TOKEN_ARG "vf_token=" @@ -1675,7 +1957,8 @@ int vfio_pci_core_match(struct vfio_device *core_vdev, char *buf) } } - ret = vfio_pci_validate_vf_token(vdev, vf_token, &uuid); + ret = core_vdev->ops->match_token_uuid(core_vdev, + vf_token ? &uuid : NULL); if (ret) return ret; @@ -1698,6 +1981,7 @@ static int vfio_pci_bus_notifier(struct notifier_block *nb, pci_name(pdev)); pdev->driver_override = kasprintf(GFP_KERNEL, "%s", vdev->vdev.ops->name); + WARN_ON(!pdev->driver_override); } else if (action == BUS_NOTIFY_BOUND_DRIVER && pdev->is_virtfn && physfn == vdev->pdev) { struct pci_driver *drv = pci_dev_driver(pdev); @@ -1715,8 +1999,30 @@ 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; @@ -1755,6 +2061,10 @@ static int vfio_pci_vga_init(struct vfio_pci_core_device *vdev) if (!vfio_pci_is_vga(pdev)) return 0; + ret = aperture_remove_conflicting_pci_devices(pdev, vdev->vdev.ops->name); + if (ret) + return ret; + ret = vga_client_register(pdev, vfio_pci_set_decode); if (ret) return ret; @@ -1774,43 +2084,69 @@ static void vfio_pci_vga_uninit(struct vfio_pci_core_device *vdev) VGA_RSRC_LEGACY_MEM); } -void vfio_pci_core_init_device(struct vfio_pci_core_device *vdev, - struct pci_dev *pdev, - const struct vfio_device_ops *vfio_pci_ops) +int vfio_pci_core_init_dev(struct vfio_device *core_vdev) { - vfio_init_group_dev(&vdev->vdev, &pdev->dev, vfio_pci_ops); - vdev->pdev = pdev; + struct vfio_pci_core_device *vdev = + container_of(core_vdev, struct vfio_pci_core_device, vdev); + int ret; + + vdev->pdev = to_pci_dev(core_vdev->dev); vdev->irq_type = VFIO_PCI_NUM_IRQS; mutex_init(&vdev->igate); spin_lock_init(&vdev->irqlock); mutex_init(&vdev->ioeventfds_lock); INIT_LIST_HEAD(&vdev->dummy_resources_list); INIT_LIST_HEAD(&vdev->ioeventfds_list); - mutex_init(&vdev->vma_lock); - INIT_LIST_HEAD(&vdev->vma_list); + INIT_LIST_HEAD(&vdev->sriov_pfs_item); + ret = pcim_p2pdma_init(vdev->pdev); + if (ret && ret != -EOPNOTSUPP) + return ret; + INIT_LIST_HEAD(&vdev->dmabufs); init_rwsem(&vdev->memory_lock); + xa_init(&vdev->ctx); + + return 0; } -EXPORT_SYMBOL_GPL(vfio_pci_core_init_device); +EXPORT_SYMBOL_GPL(vfio_pci_core_init_dev); -void vfio_pci_core_uninit_device(struct vfio_pci_core_device *vdev) +void vfio_pci_core_release_dev(struct vfio_device *core_vdev) { + struct vfio_pci_core_device *vdev = + container_of(core_vdev, struct vfio_pci_core_device, vdev); + mutex_destroy(&vdev->igate); mutex_destroy(&vdev->ioeventfds_lock); - mutex_destroy(&vdev->vma_lock); - vfio_uninit_group_dev(&vdev->vdev); kfree(vdev->region); kfree(vdev->pm_save); } -EXPORT_SYMBOL_GPL(vfio_pci_core_uninit_device); +EXPORT_SYMBOL_GPL(vfio_pci_core_release_dev); int vfio_pci_core_register_device(struct vfio_pci_core_device *vdev) { struct pci_dev *pdev = vdev->pdev; + struct device *dev = &pdev->dev; int ret; + /* Drivers must set the vfio_pci_core_device to their drvdata */ + if (WARN_ON(vdev != dev_get_drvdata(dev))) + return -EINVAL; + if (pdev->hdr_type != PCI_HEADER_TYPE_NORMAL) return -EINVAL; + if (vdev->vdev.mig_ops) { + if (!(vdev->vdev.mig_ops->migration_get_state && + vdev->vdev.mig_ops->migration_set_state && + vdev->vdev.mig_ops->migration_get_data_size) || + !(vdev->vdev.migration_flags & VFIO_MIGRATION_STOP_COPY)) + return -EINVAL; + } + + if (vdev->vdev.log_ops && !(vdev->vdev.log_ops->log_start && + vdev->vdev.log_ops->log_stop && + vdev->vdev.log_ops->log_read_and_clear)) + return -EINVAL; + /* * Prevent binding to PFs with VFs enabled, the VFs might be in use * by the host or other users. We cannot capture the VFs if they @@ -1824,7 +2160,7 @@ int vfio_pci_core_register_device(struct vfio_pci_core_device *vdev) return -EBUSY; } - if (pci_is_root_bus(pdev->bus)) { + if (pci_is_root_bus(pdev->bus) || pdev->is_virtfn) { ret = vfio_assign_device_set(&vdev->vdev, vdev); } else if (!pci_probe_reset_slot(pdev->slot)) { ret = vfio_assign_device_set(&vdev->vdev, pdev->slot); @@ -1847,19 +2183,21 @@ int vfio_pci_core_register_device(struct vfio_pci_core_device *vdev) vfio_pci_probe_power_state(vdev); - if (!disable_idle_d3) { - /* - * pci-core sets the device power state to an unknown value at - * bootup and after being removed from a driver. The only - * transition it allows from this unknown state is to D0, which - * typically happens when a driver calls pci_enable_device(). - * We're not ready to enable the device yet, but we do want to - * be able to get to D3. Therefore first do a D0 transition - * before going to D3. - */ - vfio_pci_set_power_state(vdev, PCI_D0); - vfio_pci_set_power_state(vdev, PCI_D3hot); - } + /* + * pci-core sets the device power state to an unknown value at + * bootup and after being removed from a driver. The only + * transition it allows from this unknown state is to D0, which + * typically happens when a driver calls pci_enable_device(). + * We're not ready to enable the device yet, but we do want to + * be able to get to D3. Therefore first do a D0 transition + * before enabling runtime PM. + */ + vfio_pci_set_power_state(vdev, PCI_D0); + + dev->driver->pm = &vfio_pci_core_pm_ops; + pm_runtime_allow(dev); + if (!disable_idle_d3) + pm_runtime_put(dev); ret = vfio_register_group_dev(&vdev->vdev); if (ret) @@ -1868,7 +2206,9 @@ int vfio_pci_core_register_device(struct vfio_pci_core_device *vdev) out_power: if (!disable_idle_d3) - vfio_pci_set_power_state(vdev, PCI_D0); + pm_runtime_get_noresume(dev); + + pm_runtime_forbid(dev); out_vf: vfio_pci_vf_uninit(vdev); return ret; @@ -1877,9 +2217,7 @@ EXPORT_SYMBOL_GPL(vfio_pci_core_register_device); 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(vdev, 0); vfio_unregister_group_dev(&vdev->vdev); @@ -1887,66 +2225,105 @@ void vfio_pci_core_unregister_device(struct vfio_pci_core_device *vdev) vfio_pci_vga_uninit(vdev); if (!disable_idle_d3) - vfio_pci_set_power_state(vdev, PCI_D0); + pm_runtime_get_noresume(&vdev->pdev->dev); + + pm_runtime_forbid(&vdev->pdev->dev); } EXPORT_SYMBOL_GPL(vfio_pci_core_unregister_device); -static pci_ers_result_t vfio_pci_aer_err_detected(struct pci_dev *pdev, - pci_channel_state_t state) +pci_ers_result_t vfio_pci_core_aer_err_detected(struct pci_dev *pdev, + pci_channel_state_t state) { - struct vfio_pci_core_device *vdev; - struct vfio_device *device; + struct vfio_pci_core_device *vdev = dev_get_drvdata(&pdev->dev); + struct vfio_pci_eventfd *eventfd; - device = vfio_device_get_from_dev(&pdev->dev); - if (device == NULL) - return PCI_ERS_RESULT_DISCONNECT; - - vdev = container_of(device, struct vfio_pci_core_device, vdev); - - mutex_lock(&vdev->igate); - - if (vdev->err_trigger) - eventfd_signal(vdev->err_trigger, 1); - - mutex_unlock(&vdev->igate); - - vfio_device_put(device); + rcu_read_lock(); + eventfd = rcu_dereference(vdev->err_trigger); + if (eventfd) + eventfd_signal(eventfd->ctx); + rcu_read_unlock(); return PCI_ERS_RESULT_CAN_RECOVER; } +EXPORT_SYMBOL_GPL(vfio_pci_core_aer_err_detected); -int vfio_pci_core_sriov_configure(struct pci_dev *pdev, int nr_virtfn) +int vfio_pci_core_sriov_configure(struct vfio_pci_core_device *vdev, + int nr_virtfn) { - struct vfio_device *device; + struct pci_dev *pdev = vdev->pdev; int ret = 0; - device = vfio_device_get_from_dev(&pdev->dev); - if (!device) - return -ENODEV; + device_lock_assert(&pdev->dev); - if (nr_virtfn == 0) - pci_disable_sriov(pdev); - else + 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); + + /* + * The PF power state should always be higher than the VF power + * state. The PF can be in low power state either with runtime + * power management (when there is no user) or PCI_PM_CTRL + * register write by the user. If PF is in the low power state, + * then change the power state to D0 first before enabling + * SR-IOV. Also, this function can be called at any time, and + * userspace PCI_PM_CTRL write can race against this code path, + * so protect the same with 'memory_lock'. + */ + ret = pm_runtime_resume_and_get(&pdev->dev); + if (ret) + goto out_del; + + down_write(&vdev->memory_lock); + vfio_pci_set_power_state(vdev, PCI_D0); ret = pci_enable_sriov(pdev, nr_virtfn); + up_write(&vdev->memory_lock); + if (ret) { + pm_runtime_put(&pdev->dev); + goto out_del; + } + return nr_virtfn; + } - vfio_device_put(device); + if (pci_num_vf(pdev)) { + pci_disable_sriov(pdev); + pm_runtime_put(&pdev->dev); + } - 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); + return ret; } EXPORT_SYMBOL_GPL(vfio_pci_core_sriov_configure); const struct pci_error_handlers vfio_pci_core_err_handlers = { - .error_detected = vfio_pci_aer_err_detected, + .error_detected = vfio_pci_core_aer_err_detected, }; EXPORT_SYMBOL_GPL(vfio_pci_core_err_handlers); -static bool vfio_dev_in_groups(struct vfio_pci_core_device *vdev, +static bool vfio_dev_in_groups(struct vfio_device *vdev, struct vfio_pci_group_info *groups) { unsigned int i; + if (!groups) + return false; + for (i = 0; i < groups->count; i++) - if (groups->groups[i] == vdev->vdev.group) + if (vfio_file_has_dev(groups->files[i], vdev)) return true; return false; } @@ -1954,12 +2331,8 @@ static bool vfio_dev_in_groups(struct vfio_pci_core_device *vdev, static int vfio_pci_is_device_in_set(struct pci_dev *pdev, void *data) { struct vfio_device_set *dev_set = data; - struct vfio_device *cur; - list_for_each_entry(cur, &dev_set->device_list, dev_set_list) - if (cur->dev == &pdev->dev) - return 0; - return -EBUSY; + return vfio_find_device_in_devset(dev_set, &pdev->dev) ? 0 : -ENODEV; } /* @@ -1999,25 +2372,36 @@ vfio_pci_dev_set_resettable(struct vfio_device_set *dev_set) return pdev; } -/* - * We need to get memory_lock for each device, but devices can share mmap_lock, - * therefore we need to zap and hold the vma_lock for each device, and only then - * get each memory_lock. - */ -static int vfio_pci_dev_set_hot_reset(struct vfio_device_set *dev_set, - struct vfio_pci_group_info *groups) +static int vfio_pci_dev_set_pm_runtime_get(struct vfio_device_set *dev_set) { - struct vfio_pci_core_device *cur_mem; - struct vfio_pci_core_device *cur_vma; struct vfio_pci_core_device *cur; + int ret; + + list_for_each_entry(cur, &dev_set->device_list, vdev.dev_set_list) { + ret = pm_runtime_resume_and_get(&cur->pdev->dev); + if (ret) + goto unwind; + } + + return 0; + +unwind: + list_for_each_entry_continue_reverse(cur, &dev_set->device_list, + vdev.dev_set_list) + pm_runtime_put(&cur->pdev->dev); + + return ret; +} + +static int vfio_pci_dev_set_hot_reset(struct vfio_device_set *dev_set, + struct vfio_pci_group_info *groups, + struct iommufd_ctx *iommufd_ctx) +{ + struct vfio_pci_core_device *vdev; struct pci_dev *pdev; - bool is_mem = true; int ret; mutex_lock(&dev_set->lock); - cur_mem = list_first_entry(&dev_set->device_list, - struct vfio_pci_core_device, - vdev.dev_set_list); pdev = vfio_pci_dev_set_resettable(dev_set); if (!pdev) { @@ -2025,49 +2409,101 @@ static int vfio_pci_dev_set_hot_reset(struct vfio_device_set *dev_set, goto err_unlock; } - list_for_each_entry(cur_vma, &dev_set->device_list, vdev.dev_set_list) { + /* + * Some of the devices in the dev_set can be in the runtime suspended + * state. Increment the usage count for all the devices in the dev_set + * before reset and decrement the same after reset. + */ + ret = vfio_pci_dev_set_pm_runtime_get(dev_set); + if (ret) + goto err_unlock; + + list_for_each_entry(vdev, &dev_set->device_list, vdev.dev_set_list) { + bool owned; + /* - * Test whether all the affected devices are contained by the - * set of groups provided by the user. + * Test whether all the affected devices can be reset by the + * user. + * + * If called from a group opened device and the user provides + * a set of groups, all the devices in the dev_set should be + * contained by the set of groups provided by the user. + * + * If called from a cdev opened device and the user provides + * a zero-length array, all the devices in the dev_set must + * be bound to the same iommufd_ctx as the input iommufd_ctx. + * If there is any device that has not been bound to any + * iommufd_ctx yet, check if its iommu_group has any device + * bound to the input iommufd_ctx. Such devices can be + * considered owned by the input iommufd_ctx as the device + * cannot be owned by another iommufd_ctx when its iommu_group + * is owned. + * + * Otherwise, reset is not allowed. */ - if (!vfio_dev_in_groups(cur_vma, groups)) { + if (iommufd_ctx) { + int devid = vfio_iommufd_get_dev_id(&vdev->vdev, + iommufd_ctx); + + owned = (devid > 0 || devid == -ENOENT); + } else { + owned = vfio_dev_in_groups(&vdev->vdev, groups); + } + + if (!owned) { ret = -EINVAL; - goto err_undo; + break; } /* - * Locking multiple devices is prone to deadlock, runaway and - * unwind if we hit contention. + * Take the memory write lock for each device and zap BAR + * mappings to prevent the user accessing the device while in + * reset. Locking multiple devices is prone to deadlock, + * runaway and unwind if we hit contention. */ - if (!vfio_pci_zap_and_vma_lock(cur_vma, true)) { + if (!down_write_trylock(&vdev->memory_lock)) { ret = -EBUSY; - goto err_undo; + break; } + + vfio_pci_dma_buf_move(vdev, true); + vfio_pci_zap_bars(vdev); } - cur_vma = NULL; - list_for_each_entry(cur_mem, &dev_set->device_list, vdev.dev_set_list) { - if (!down_write_trylock(&cur_mem->memory_lock)) { - ret = -EBUSY; - goto err_undo; - } - mutex_unlock(&cur_mem->vma_lock); + if (!list_entry_is_head(vdev, + &dev_set->device_list, vdev.dev_set_list)) { + vdev = list_prev_entry(vdev, vdev.dev_set_list); + goto err_undo; } - 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(vdev, &dev_set->device_list, vdev.dev_set_list) + vfio_pci_set_power_state(vdev, PCI_D0); ret = pci_reset_bus(pdev); + vdev = list_last_entry(&dev_set->device_list, + struct vfio_pci_core_device, vdev.dev_set_list); + err_undo: - list_for_each_entry(cur, &dev_set->device_list, vdev.dev_set_list) { - if (cur == cur_mem) - is_mem = false; - if (cur == cur_vma) - break; - if (is_mem) - up_write(&cur->memory_lock); - else - mutex_unlock(&cur->vma_lock); + list_for_each_entry_from_reverse(vdev, &dev_set->device_list, + vdev.dev_set_list) { + if (vdev->vdev.open_count && __vfio_pci_memory_enabled(vdev)) + vfio_pci_dma_buf_move(vdev, false); + up_write(&vdev->memory_lock); } + + list_for_each_entry(vdev, &dev_set->device_list, vdev.dev_set_list) + pm_runtime_put(&vdev->pdev->dev); + err_unlock: mutex_unlock(&dev_set->lock); return ret; @@ -2078,12 +2514,12 @@ static bool vfio_pci_dev_set_needs_reset(struct vfio_device_set *dev_set) struct vfio_pci_core_device *cur; bool needs_reset = false; - list_for_each_entry(cur, &dev_set->device_list, vdev.dev_set_list) { - /* No VFIO device in the set can have an open device FD */ - if (cur->vdev.open_count) - return false; + /* No other VFIO device in the set can be open. */ + if (vfio_device_set_open_count(dev_set) > 1) + return false; + + list_for_each_entry(cur, &dev_set->device_list, vdev.dev_set_list) needs_reset |= cur->needs_reset; - } return needs_reset; } @@ -2093,31 +2529,38 @@ static bool vfio_pci_dev_set_needs_reset(struct vfio_device_set *dev_set) * - At least one of the affected devices is marked dirty via * needs_reset (such as by lack of FLR support) * Then attempt to perform that bus or slot reset. - * Returns true if the dev_set was reset. */ -static bool vfio_pci_dev_set_try_reset(struct vfio_device_set *dev_set) +static void vfio_pci_dev_set_try_reset(struct vfio_device_set *dev_set) { struct vfio_pci_core_device *cur; struct pci_dev *pdev; - int ret; + bool reset_done = false; if (!vfio_pci_dev_set_needs_reset(dev_set)) - return false; + return; pdev = vfio_pci_dev_set_resettable(dev_set); if (!pdev) - return false; + return; - ret = pci_reset_bus(pdev); - if (ret) - return false; + /* + * Some of the devices in the bus can be in the runtime suspended + * state. Increment the usage count for all the devices in the dev_set + * before reset and decrement the same after reset. + */ + if (!disable_idle_d3 && vfio_pci_dev_set_pm_runtime_get(dev_set)) + return; + + if (!pci_reset_bus(pdev)) + reset_done = true; list_for_each_entry(cur, &dev_set->device_list, vdev.dev_set_list) { - cur->needs_reset = false; + if (reset_done) + cur->needs_reset = false; + if (!disable_idle_d3) - vfio_pci_set_power_state(cur, PCI_D3hot); + pm_runtime_put(&cur->pdev->dev); } - return true; } void vfio_pci_core_set_params(bool is_nointxmask, bool is_disable_vga, |