diff options
Diffstat (limited to 'drivers/iommu/iommu.c')
| -rw-r--r-- | drivers/iommu/iommu.c | 3580 |
1 files changed, 2098 insertions, 1482 deletions
diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c index 5419c4b9f27a..2ca990dfbb88 100644 --- a/drivers/iommu/iommu.c +++ b/drivers/iommu/iommu.c @@ -6,45 +6,65 @@ #define pr_fmt(fmt) "iommu: " fmt +#include <linux/amba/bus.h> #include <linux/device.h> #include <linux/kernel.h> +#include <linux/bits.h> #include <linux/bug.h> #include <linux/types.h> #include <linux/init.h> #include <linux/export.h> #include <linux/slab.h> #include <linux/errno.h> +#include <linux/host1x_context_bus.h> #include <linux/iommu.h> +#include <linux/iommufd.h> #include <linux/idr.h> -#include <linux/notifier.h> #include <linux/err.h> #include <linux/pci.h> +#include <linux/pci-ats.h> #include <linux/bitops.h> +#include <linux/platform_device.h> #include <linux/property.h> #include <linux/fsl/mc.h> #include <linux/module.h> +#include <linux/cc_platform.h> +#include <linux/cdx/cdx_bus.h> #include <trace/events/iommu.h> +#include <linux/sched/mm.h> +#include <linux/msi.h> +#include <uapi/linux/iommufd.h> + +#include "dma-iommu.h" +#include "iommu-priv.h" static struct kset *iommu_group_kset; static DEFINE_IDA(iommu_group_ida); +static DEFINE_IDA(iommu_global_pasid_ida); static unsigned int iommu_def_domain_type __read_mostly; -static bool iommu_dma_strict __read_mostly = true; +static bool iommu_dma_strict __read_mostly = IS_ENABLED(CONFIG_IOMMU_DEFAULT_DMA_STRICT); static u32 iommu_cmd_line __read_mostly; +/* Tags used with xa_tag_pointer() in group->pasid_array */ +enum { IOMMU_PASID_ARRAY_DOMAIN = 0, IOMMU_PASID_ARRAY_HANDLE = 1 }; + struct iommu_group { struct kobject kobj; struct kobject *devices_kobj; struct list_head devices; + struct xarray pasid_array; struct mutex mutex; - struct blocking_notifier_head notifier; void *iommu_data; void (*iommu_data_release)(void *iommu_data); char *name; int id; struct iommu_domain *default_domain; + struct iommu_domain *blocking_domain; struct iommu_domain *domain; struct list_head entry; + unsigned int owner_cnt; + void *owner; }; struct group_device { @@ -53,6 +73,10 @@ struct group_device { char *name; }; +/* Iterate over each struct group_device in a struct iommu_group */ +#define for_each_group_device(group, pos) \ + list_for_each_entry(pos, &(group)->devices, list) + struct iommu_group_attribute { struct attribute attr; ssize_t (*show)(struct iommu_group *group, char *buf); @@ -71,21 +95,54 @@ static const char * const iommu_group_resv_type_string[] = { #define IOMMU_CMD_LINE_DMA_API BIT(0) #define IOMMU_CMD_LINE_STRICT BIT(1) -static int iommu_alloc_default_domain(struct iommu_group *group, - struct device *dev); -static struct iommu_domain *__iommu_domain_alloc(struct bus_type *bus, - unsigned type); +static int bus_iommu_probe(const struct bus_type *bus); +static int iommu_bus_notifier(struct notifier_block *nb, + unsigned long action, void *data); +static void iommu_release_device(struct device *dev); static int __iommu_attach_device(struct iommu_domain *domain, - struct device *dev); + struct device *dev, struct iommu_domain *old); static int __iommu_attach_group(struct iommu_domain *domain, struct iommu_group *group); -static void __iommu_detach_group(struct iommu_domain *domain, - struct iommu_group *group); -static int iommu_create_device_direct_mappings(struct iommu_group *group, +static struct iommu_domain *__iommu_paging_domain_alloc_flags(struct device *dev, + unsigned int type, + unsigned int flags); + +enum { + IOMMU_SET_DOMAIN_MUST_SUCCEED = 1 << 0, +}; + +static int __iommu_device_set_domain(struct iommu_group *group, + struct device *dev, + struct iommu_domain *new_domain, + struct iommu_domain *old_domain, + unsigned int flags); +static int __iommu_group_set_domain_internal(struct iommu_group *group, + struct iommu_domain *new_domain, + unsigned int flags); +static int __iommu_group_set_domain(struct iommu_group *group, + struct iommu_domain *new_domain) +{ + return __iommu_group_set_domain_internal(group, new_domain, 0); +} +static void __iommu_group_set_domain_nofail(struct iommu_group *group, + struct iommu_domain *new_domain) +{ + WARN_ON(__iommu_group_set_domain_internal( + group, new_domain, IOMMU_SET_DOMAIN_MUST_SUCCEED)); +} + +static int iommu_setup_default_domain(struct iommu_group *group, + int target_type); +static int iommu_create_device_direct_mappings(struct iommu_domain *domain, struct device *dev); -static struct iommu_group *iommu_group_get_for_dev(struct device *dev); static ssize_t iommu_group_store_type(struct iommu_group *group, const char *buf, size_t count); +static struct group_device *iommu_group_alloc_device(struct iommu_group *group, + struct device *dev); +static void __iommu_group_free_device(struct iommu_group *group, + struct group_device *grp_dev); +static void iommu_domain_init(struct iommu_domain *domain, unsigned int type, + const struct iommu_ops *ops); #define IOMMU_GROUP_ATTR(_name, _mode, _show, _store) \ struct iommu_group_attribute iommu_group_attr_##_name = \ @@ -99,6 +156,25 @@ struct iommu_group_attribute iommu_group_attr_##_name = \ static LIST_HEAD(iommu_device_list); static DEFINE_SPINLOCK(iommu_device_lock); +static const struct bus_type * const iommu_buses[] = { + &platform_bus_type, +#ifdef CONFIG_PCI + &pci_bus_type, +#endif +#ifdef CONFIG_ARM_AMBA + &amba_bustype, +#endif +#ifdef CONFIG_FSL_MC_BUS + &fsl_mc_bus_type, +#endif +#ifdef CONFIG_TEGRA_HOST1X_CONTEXT_BUS + &host1x_context_device_bus_type, +#endif +#ifdef CONFIG_CDX_BUS + &cdx_bus_type, +#endif +}; + /* * Use a function instead of an array here because the domain-type is a * bit-field, so an array would waste memory. @@ -113,7 +189,10 @@ static const char *iommu_domain_type_str(unsigned int t) case IOMMU_DOMAIN_UNMANAGED: return "Unmanaged"; case IOMMU_DOMAIN_DMA: + case IOMMU_DOMAIN_DMA_FQ: return "Translated"; + case IOMMU_DOMAIN_PLATFORM: + return "Platform"; default: return "Unknown"; } @@ -121,27 +200,55 @@ static const char *iommu_domain_type_str(unsigned int t) static int __init iommu_subsys_init(void) { + struct notifier_block *nb; + if (!(iommu_cmd_line & IOMMU_CMD_LINE_DMA_API)) { if (IS_ENABLED(CONFIG_IOMMU_DEFAULT_PASSTHROUGH)) iommu_set_default_passthrough(false); else iommu_set_default_translated(false); - if (iommu_default_passthrough() && mem_encrypt_active()) { + if (iommu_default_passthrough() && cc_platform_has(CC_ATTR_MEM_ENCRYPT)) { pr_info("Memory encryption detected - Disabling default IOMMU Passthrough\n"); iommu_set_default_translated(false); } } - pr_info("Default domain type: %s %s\n", + if (!iommu_default_passthrough() && !iommu_dma_strict) + iommu_def_domain_type = IOMMU_DOMAIN_DMA_FQ; + + pr_info("Default domain type: %s%s\n", iommu_domain_type_str(iommu_def_domain_type), (iommu_cmd_line & IOMMU_CMD_LINE_DMA_API) ? - "(set via kernel command line)" : ""); + " (set via kernel command line)" : ""); + + if (!iommu_default_passthrough()) + pr_info("DMA domain TLB invalidation policy: %s mode%s\n", + iommu_dma_strict ? "strict" : "lazy", + (iommu_cmd_line & IOMMU_CMD_LINE_STRICT) ? + " (set via kernel command line)" : ""); + + nb = kcalloc(ARRAY_SIZE(iommu_buses), sizeof(*nb), GFP_KERNEL); + if (!nb) + return -ENOMEM; + + for (int i = 0; i < ARRAY_SIZE(iommu_buses); i++) { + nb[i].notifier_call = iommu_bus_notifier; + bus_register_notifier(iommu_buses[i], &nb[i]); + } return 0; } subsys_initcall(iommu_subsys_init); +static int remove_iommu_group(struct device *dev, void *data) +{ + if (dev->iommu && dev->iommu->iommu_dev == data) + iommu_release_device(dev); + + return 0; +} + /** * iommu_device_register() - Register an IOMMU hardware instance * @iommu: IOMMU handle for the instance @@ -153,33 +260,119 @@ subsys_initcall(iommu_subsys_init); int iommu_device_register(struct iommu_device *iommu, const struct iommu_ops *ops, struct device *hwdev) { + int err = 0; + /* We need to be able to take module references appropriately */ if (WARN_ON(is_module_address((unsigned long)ops) && !ops->owner)) return -EINVAL; iommu->ops = ops; if (hwdev) - iommu->fwnode = hwdev->fwnode; + iommu->fwnode = dev_fwnode(hwdev); spin_lock(&iommu_device_lock); list_add_tail(&iommu->list, &iommu_device_list); spin_unlock(&iommu_device_lock); - return 0; + + for (int i = 0; i < ARRAY_SIZE(iommu_buses) && !err; i++) + err = bus_iommu_probe(iommu_buses[i]); + if (err) + iommu_device_unregister(iommu); + else + WRITE_ONCE(iommu->ready, true); + return err; } EXPORT_SYMBOL_GPL(iommu_device_register); void iommu_device_unregister(struct iommu_device *iommu) { + for (int i = 0; i < ARRAY_SIZE(iommu_buses); i++) + bus_for_each_dev(iommu_buses[i], NULL, iommu, remove_iommu_group); + spin_lock(&iommu_device_lock); list_del(&iommu->list); spin_unlock(&iommu_device_lock); + + /* Pairs with the alloc in generic_single_device_group() */ + iommu_group_put(iommu->singleton_group); + iommu->singleton_group = NULL; } EXPORT_SYMBOL_GPL(iommu_device_unregister); +#if IS_ENABLED(CONFIG_IOMMUFD_TEST) +void iommu_device_unregister_bus(struct iommu_device *iommu, + const struct bus_type *bus, + struct notifier_block *nb) +{ + bus_unregister_notifier(bus, nb); + fwnode_remove_software_node(iommu->fwnode); + iommu_device_unregister(iommu); +} +EXPORT_SYMBOL_GPL(iommu_device_unregister_bus); + +/* + * Register an iommu driver against a single bus. This is only used by iommufd + * selftest to create a mock iommu driver. The caller must provide + * some memory to hold a notifier_block. + */ +int iommu_device_register_bus(struct iommu_device *iommu, + const struct iommu_ops *ops, + const struct bus_type *bus, + struct notifier_block *nb) +{ + int err; + + iommu->ops = ops; + nb->notifier_call = iommu_bus_notifier; + err = bus_register_notifier(bus, nb); + if (err) + return err; + + iommu->fwnode = fwnode_create_software_node(NULL, NULL); + if (IS_ERR(iommu->fwnode)) { + bus_unregister_notifier(bus, nb); + return PTR_ERR(iommu->fwnode); + } + + spin_lock(&iommu_device_lock); + list_add_tail(&iommu->list, &iommu_device_list); + spin_unlock(&iommu_device_lock); + + err = bus_iommu_probe(bus); + if (err) { + iommu_device_unregister_bus(iommu, bus, nb); + return err; + } + WRITE_ONCE(iommu->ready, true); + return 0; +} +EXPORT_SYMBOL_GPL(iommu_device_register_bus); + +int iommu_mock_device_add(struct device *dev, struct iommu_device *iommu) +{ + int rc; + + mutex_lock(&iommu_probe_device_lock); + rc = iommu_fwspec_init(dev, iommu->fwnode); + mutex_unlock(&iommu_probe_device_lock); + + if (rc) + return rc; + + rc = device_add(dev); + if (rc) + iommu_fwspec_free(dev); + return rc; +} +EXPORT_SYMBOL_GPL(iommu_mock_device_add); +#endif + static struct dev_iommu *dev_iommu_get(struct device *dev) { struct dev_iommu *param = dev->iommu; + lockdep_assert_held(&iommu_probe_device_lock); + if (param) return param; @@ -192,25 +385,94 @@ static struct dev_iommu *dev_iommu_get(struct device *dev) return param; } -static void dev_iommu_free(struct device *dev) +void dev_iommu_free(struct device *dev) { - iommu_fwspec_free(dev); - kfree(dev->iommu); + struct dev_iommu *param = dev->iommu; + dev->iommu = NULL; + if (param->fwspec) { + fwnode_handle_put(param->fwspec->iommu_fwnode); + kfree(param->fwspec); + } + kfree(param); } -static int __iommu_probe_device(struct device *dev, struct list_head *group_list) +/* + * Internal equivalent of device_iommu_mapped() for when we care that a device + * actually has API ops, and don't want false positives from VFIO-only groups. + */ +static bool dev_has_iommu(struct device *dev) +{ + return dev->iommu && dev->iommu->iommu_dev; +} + +static u32 dev_iommu_get_max_pasids(struct device *dev) +{ + u32 max_pasids = 0, bits = 0; + int ret; + + if (dev_is_pci(dev)) { + ret = pci_max_pasids(to_pci_dev(dev)); + if (ret > 0) + max_pasids = ret; + } else { + ret = device_property_read_u32(dev, "pasid-num-bits", &bits); + if (!ret) + max_pasids = 1UL << bits; + } + + return min_t(u32, max_pasids, dev->iommu->iommu_dev->max_pasids); +} + +void dev_iommu_priv_set(struct device *dev, void *priv) { - const struct iommu_ops *ops = dev->bus->iommu_ops; + /* FSL_PAMU does something weird */ + if (!IS_ENABLED(CONFIG_FSL_PAMU)) + lockdep_assert_held(&iommu_probe_device_lock); + dev->iommu->priv = priv; +} +EXPORT_SYMBOL_GPL(dev_iommu_priv_set); + +/* + * Init the dev->iommu and dev->iommu_group in the struct device and get the + * driver probed + */ +static int iommu_init_device(struct device *dev) +{ + const struct iommu_ops *ops; struct iommu_device *iommu_dev; struct iommu_group *group; int ret; - if (!ops) - return -ENODEV; - if (!dev_iommu_get(dev)) return -ENOMEM; + /* + * For FDT-based systems and ACPI IORT/VIOT, the common firmware parsing + * is buried in the bus dma_configure path. Properly unpicking that is + * still a big job, so for now just invoke the whole thing. The device + * already having a driver bound means dma_configure has already run and + * found no IOMMU to wait for, so there's no point calling it again. + */ + if (!dev->iommu->fwspec && !dev->driver && dev->bus->dma_configure) { + mutex_unlock(&iommu_probe_device_lock); + dev->bus->dma_configure(dev); + mutex_lock(&iommu_probe_device_lock); + /* If another instance finished the job for us, skip it */ + if (!dev->iommu || dev->iommu_group) + return -ENODEV; + } + /* + * At this point, relevant devices either now have a fwspec which will + * match ops registered with a non-NULL fwnode, or we can reasonably + * assume that only one of Intel, AMD, s390, PAMU or legacy SMMUv2 can + * be present, and that any of their registered instances has suitable + * ops for probing, and thus cheekily co-opt the same mechanism. + */ + ops = iommu_fwspec_ops(dev->iommu->fwspec); + if (!ops) { + ret = -ENODEV; + goto err_free; + } if (!try_module_get(ops->owner)) { ret = -EINVAL; @@ -220,100 +482,281 @@ static int __iommu_probe_device(struct device *dev, struct list_head *group_list iommu_dev = ops->probe_device(dev); if (IS_ERR(iommu_dev)) { ret = PTR_ERR(iommu_dev); - goto out_module_put; + goto err_module_put; } - dev->iommu->iommu_dev = iommu_dev; - group = iommu_group_get_for_dev(dev); + ret = iommu_device_link(iommu_dev, dev); + if (ret) + goto err_release; + + group = ops->device_group(dev); + if (WARN_ON_ONCE(group == NULL)) + group = ERR_PTR(-EINVAL); if (IS_ERR(group)) { ret = PTR_ERR(group); - goto out_release; + goto err_unlink; } - iommu_group_put(group); + dev->iommu_group = group; - if (group_list && !group->default_domain && list_empty(&group->entry)) - list_add_tail(&group->entry, group_list); + dev->iommu->max_pasids = dev_iommu_get_max_pasids(dev); + if (ops->is_attach_deferred) + dev->iommu->attach_deferred = ops->is_attach_deferred(dev); + return 0; - iommu_device_link(iommu_dev, dev); +err_unlink: + iommu_device_unlink(iommu_dev, dev); +err_release: + if (ops->release_device) + ops->release_device(dev); +err_module_put: + module_put(ops->owner); +err_free: + dev->iommu->iommu_dev = NULL; + dev_iommu_free(dev); + return ret; +} - return 0; +static void iommu_deinit_device(struct device *dev) +{ + struct iommu_group *group = dev->iommu_group; + const struct iommu_ops *ops = dev_iommu_ops(dev); -out_release: - ops->release_device(dev); + lockdep_assert_held(&group->mutex); -out_module_put: - module_put(ops->owner); + iommu_device_unlink(dev->iommu->iommu_dev, dev); -err_free: + /* + * release_device() must stop using any attached domain on the device. + * If there are still other devices in the group, they are not affected + * by this callback. + * + * If the iommu driver provides release_domain, the core code ensures + * that domain is attached prior to calling release_device. Drivers can + * use this to enforce a translation on the idle iommu. Typically, the + * global static blocked_domain is a good choice. + * + * Otherwise, the iommu driver must set the device to either an identity + * or a blocking translation in release_device() and stop using any + * domain pointer, as it is going to be freed. + * + * Regardless, if a delayed attach never occurred, then the release + * should still avoid touching any hardware configuration either. + */ + if (!dev->iommu->attach_deferred && ops->release_domain) { + struct iommu_domain *release_domain = ops->release_domain; + + /* + * If the device requires direct mappings then it should not + * be parked on a BLOCKED domain during release as that would + * break the direct mappings. + */ + if (dev->iommu->require_direct && ops->identity_domain && + release_domain == ops->blocked_domain) + release_domain = ops->identity_domain; + + release_domain->ops->attach_dev(release_domain, dev, + group->domain); + } + + if (ops->release_device) + ops->release_device(dev); + + /* + * If this is the last driver to use the group then we must free the + * domains before we do the module_put(). + */ + if (list_empty(&group->devices)) { + if (group->default_domain) { + iommu_domain_free(group->default_domain); + group->default_domain = NULL; + } + if (group->blocking_domain) { + iommu_domain_free(group->blocking_domain); + group->blocking_domain = NULL; + } + group->domain = NULL; + } + + /* Caller must put iommu_group */ + dev->iommu_group = NULL; + module_put(ops->owner); dev_iommu_free(dev); +#ifdef CONFIG_IOMMU_DMA + dev->dma_iommu = false; +#endif +} - return ret; +static struct iommu_domain *pasid_array_entry_to_domain(void *entry) +{ + if (xa_pointer_tag(entry) == IOMMU_PASID_ARRAY_DOMAIN) + return xa_untag_pointer(entry); + return ((struct iommu_attach_handle *)xa_untag_pointer(entry))->domain; } -int iommu_probe_device(struct device *dev) +DEFINE_MUTEX(iommu_probe_device_lock); + +static int __iommu_probe_device(struct device *dev, struct list_head *group_list) { - const struct iommu_ops *ops = dev->bus->iommu_ops; struct iommu_group *group; + struct group_device *gdev; int ret; - ret = __iommu_probe_device(dev, NULL); + /* + * Serialise to avoid races between IOMMU drivers registering in + * parallel and/or the "replay" calls from ACPI/OF code via client + * driver probe. Once the latter have been cleaned up we should + * probably be able to use device_lock() here to minimise the scope, + * but for now enforcing a simple global ordering is fine. + */ + lockdep_assert_held(&iommu_probe_device_lock); + + /* Device is probed already if in a group */ + if (dev->iommu_group) + return 0; + + ret = iommu_init_device(dev); if (ret) - goto err_out; + return ret; + /* + * And if we do now see any replay calls, they would indicate someone + * misusing the dma_configure path outside bus code. + */ + if (dev->driver) + dev_WARN(dev, "late IOMMU probe at driver bind, something fishy here!\n"); - group = iommu_group_get(dev); - if (!group) { - ret = -ENODEV; - goto err_release; + group = dev->iommu_group; + gdev = iommu_group_alloc_device(group, dev); + mutex_lock(&group->mutex); + if (IS_ERR(gdev)) { + ret = PTR_ERR(gdev); + goto err_put_group; } /* - * Try to allocate a default domain - needs support from the - * IOMMU driver. There are still some drivers which don't - * support default domains, so the return value is not yet - * checked. + * The gdev must be in the list before calling + * iommu_setup_default_domain() */ - iommu_alloc_default_domain(group, dev); - - if (group->default_domain) { - ret = __iommu_attach_device(group->default_domain, dev); - if (ret) { - iommu_group_put(group); - goto err_release; - } + list_add_tail(&gdev->list, &group->devices); + WARN_ON(group->default_domain && !group->domain); + if (group->default_domain) + iommu_create_device_direct_mappings(group->default_domain, dev); + if (group->domain) { + ret = __iommu_device_set_domain(group, dev, group->domain, NULL, + 0); + if (ret) + goto err_remove_gdev; + } else if (!group->default_domain && !group_list) { + ret = iommu_setup_default_domain(group, 0); + if (ret) + goto err_remove_gdev; + } else if (!group->default_domain) { + /* + * With a group_list argument we defer the default_domain setup + * to the caller by providing a de-duplicated list of groups + * that need further setup. + */ + if (list_empty(&group->entry)) + list_add_tail(&group->entry, group_list); } - iommu_create_device_direct_mappings(group, dev); + if (group->default_domain) + iommu_setup_dma_ops(dev); + mutex_unlock(&group->mutex); + + return 0; + +err_remove_gdev: + list_del(&gdev->list); + __iommu_group_free_device(group, gdev); +err_put_group: + iommu_deinit_device(dev); + mutex_unlock(&group->mutex); iommu_group_put(group); + return ret; +} + +int iommu_probe_device(struct device *dev) +{ + const struct iommu_ops *ops; + int ret; + + mutex_lock(&iommu_probe_device_lock); + ret = __iommu_probe_device(dev, NULL); + mutex_unlock(&iommu_probe_device_lock); + if (ret) + return ret; + + ops = dev_iommu_ops(dev); if (ops->probe_finalize) ops->probe_finalize(dev); return 0; +} -err_release: - iommu_release_device(dev); +static void __iommu_group_free_device(struct iommu_group *group, + struct group_device *grp_dev) +{ + struct device *dev = grp_dev->dev; -err_out: - return ret; + sysfs_remove_link(group->devices_kobj, grp_dev->name); + sysfs_remove_link(&dev->kobj, "iommu_group"); + + trace_remove_device_from_group(group->id, dev); + + /* + * If the group has become empty then ownership must have been + * released, and the current domain must be set back to NULL or + * the default domain. + */ + if (list_empty(&group->devices)) + WARN_ON(group->owner_cnt || + group->domain != group->default_domain); + kfree(grp_dev->name); + kfree(grp_dev); } -void iommu_release_device(struct device *dev) +/* Remove the iommu_group from the struct device. */ +static void __iommu_group_remove_device(struct device *dev) { - const struct iommu_ops *ops = dev->bus->iommu_ops; + struct iommu_group *group = dev->iommu_group; + struct group_device *device; - if (!dev->iommu) - return; + mutex_lock(&group->mutex); + for_each_group_device(group, device) { + if (device->dev != dev) + continue; - iommu_device_unlink(dev->iommu->iommu_dev, dev); + list_del(&device->list); + __iommu_group_free_device(group, device); + if (dev_has_iommu(dev)) + iommu_deinit_device(dev); + else + dev->iommu_group = NULL; + break; + } + mutex_unlock(&group->mutex); - ops->release_device(dev); + /* + * Pairs with the get in iommu_init_device() or + * iommu_group_add_device() + */ + iommu_group_put(group); +} - iommu_group_remove_device(dev); - module_put(ops->owner); - dev_iommu_free(dev); +static void iommu_release_device(struct device *dev) +{ + struct iommu_group *group = dev->iommu_group; + + if (group) + __iommu_group_remove_device(dev); + + /* Free any fwspec if no iommu_driver was ever attached */ + if (dev->iommu) + dev_iommu_free(dev); } static int __init iommu_set_def_domain_type(char *str) @@ -344,21 +787,13 @@ static int __init iommu_dma_setup(char *str) } early_param("iommu.strict", iommu_dma_setup); -void iommu_set_dma_strict(bool strict) +void iommu_set_dma_strict(void) { - if (strict || !(iommu_cmd_line & IOMMU_CMD_LINE_STRICT)) - iommu_dma_strict = strict; + iommu_dma_strict = true; + if (iommu_def_domain_type == IOMMU_DOMAIN_DMA_FQ) + iommu_def_domain_type = IOMMU_DOMAIN_DMA; } -bool iommu_get_dma_strict(struct iommu_domain *domain) -{ - /* only allow lazy flushing for DMA domains */ - if (domain->type == IOMMU_DOMAIN_DMA) - return iommu_dma_strict; - return true; -} -EXPORT_SYMBOL_GPL(iommu_get_dma_strict); - static ssize_t iommu_group_attr_show(struct kobject *kobj, struct attribute *__attr, char *buf) { @@ -403,7 +838,7 @@ static void iommu_group_remove_file(struct iommu_group *group, static ssize_t iommu_group_show_name(struct iommu_group *group, char *buf) { - return sprintf(buf, "%s\n", group->name); + return sysfs_emit(buf, "%s\n", group->name); } /** @@ -422,7 +857,7 @@ static int iommu_insert_resv_region(struct iommu_resv_region *new, LIST_HEAD(stack); nr = iommu_alloc_resv_region(new->start, new->length, - new->prot, new->type); + new->prot, new->type, GFP_KERNEL); if (!nr) return -ENOMEM; @@ -489,9 +924,16 @@ int iommu_get_group_resv_regions(struct iommu_group *group, int ret = 0; mutex_lock(&group->mutex); - list_for_each_entry(device, &group->devices, list) { + for_each_group_device(group, device) { struct list_head dev_resv_regions; + /* + * Non-API groups still expose reserved_regions in sysfs, + * so filter out calls that get here that way. + */ + if (!dev_has_iommu(device->dev)) + break; + INIT_LIST_HEAD(&dev_resv_regions); iommu_get_resv_regions(device->dev, &dev_resv_regions); ret = iommu_insert_device_resv_regions(&dev_resv_regions, head); @@ -509,49 +951,51 @@ static ssize_t iommu_group_show_resv_regions(struct iommu_group *group, { struct iommu_resv_region *region, *next; struct list_head group_resv_regions; - char *str = buf; + int offset = 0; INIT_LIST_HEAD(&group_resv_regions); iommu_get_group_resv_regions(group, &group_resv_regions); list_for_each_entry_safe(region, next, &group_resv_regions, list) { - str += sprintf(str, "0x%016llx 0x%016llx %s\n", - (long long int)region->start, - (long long int)(region->start + - region->length - 1), - iommu_group_resv_type_string[region->type]); + offset += sysfs_emit_at(buf, offset, "0x%016llx 0x%016llx %s\n", + (long long)region->start, + (long long)(region->start + + region->length - 1), + iommu_group_resv_type_string[region->type]); kfree(region); } - return (str - buf); + return offset; } static ssize_t iommu_group_show_type(struct iommu_group *group, char *buf) { - char *type = "unknown\n"; + char *type = "unknown"; mutex_lock(&group->mutex); if (group->default_domain) { switch (group->default_domain->type) { case IOMMU_DOMAIN_BLOCKED: - type = "blocked\n"; + type = "blocked"; break; case IOMMU_DOMAIN_IDENTITY: - type = "identity\n"; + type = "identity"; break; case IOMMU_DOMAIN_UNMANAGED: - type = "unmanaged\n"; + type = "unmanaged"; break; case IOMMU_DOMAIN_DMA: - type = "DMA\n"; + type = "DMA"; + break; + case IOMMU_DOMAIN_DMA_FQ: + type = "DMA-FQ"; break; } } mutex_unlock(&group->mutex); - strcpy(buf, type); - return strlen(type); + return sysfs_emit(buf, "%s\n", type); } static IOMMU_GROUP_ATTR(name, S_IRUGO, iommu_group_show_name, NULL); @@ -571,16 +1015,17 @@ static void iommu_group_release(struct kobject *kobj) if (group->iommu_data_release) group->iommu_data_release(group->iommu_data); - ida_simple_remove(&iommu_group_ida, group->id); + ida_free(&iommu_group_ida, group->id); - if (group->default_domain) - iommu_domain_free(group->default_domain); + /* Domains are free'd by iommu_deinit_device() */ + WARN_ON(group->default_domain); + WARN_ON(group->blocking_domain); kfree(group->name); kfree(group); } -static struct kobj_type iommu_group_ktype = { +static const struct kobj_type iommu_group_ktype = { .sysfs_ops = &iommu_group_sysfs_ops, .release = iommu_group_release, }; @@ -609,9 +1054,9 @@ struct iommu_group *iommu_group_alloc(void) mutex_init(&group->mutex); INIT_LIST_HEAD(&group->devices); INIT_LIST_HEAD(&group->entry); - BLOCKING_INIT_NOTIFIER_HEAD(&group->notifier); + xa_init(&group->pasid_array); - ret = ida_simple_get(&iommu_group_ida, 0, 0, GFP_KERNEL); + ret = ida_alloc(&iommu_group_ida, GFP_KERNEL); if (ret < 0) { kfree(group); return ERR_PTR(ret); @@ -621,7 +1066,6 @@ struct iommu_group *iommu_group_alloc(void) ret = kobject_init_and_add(&group->kobj, &iommu_group_ktype, NULL, "%d", group->id); if (ret) { - ida_simple_remove(&iommu_group_ida, group->id); kobject_put(&group->kobj); return ERR_PTR(ret); } @@ -641,12 +1085,16 @@ struct iommu_group *iommu_group_alloc(void) ret = iommu_group_create_file(group, &iommu_group_attr_reserved_regions); - if (ret) + if (ret) { + kobject_put(group->devices_kobj); return ERR_PTR(ret); + } ret = iommu_group_create_file(group, &iommu_group_attr_type); - if (ret) + if (ret) { + kobject_put(group->devices_kobj); return ERR_PTR(ret); + } pr_debug("Allocated group %d\n", group->id); @@ -654,35 +1102,6 @@ struct iommu_group *iommu_group_alloc(void) } EXPORT_SYMBOL_GPL(iommu_group_alloc); -struct iommu_group *iommu_group_get_by_id(int id) -{ - struct kobject *group_kobj; - struct iommu_group *group; - const char *name; - - if (!iommu_group_kset) - return NULL; - - name = kasprintf(GFP_KERNEL, "%d", id); - if (!name) - return NULL; - - group_kobj = kset_find_obj(iommu_group_kset, name); - kfree(name); - - if (!group_kobj) - return NULL; - - group = container_of(group_kobj, struct iommu_group, kobj); - BUG_ON(group->id != id); - - kobject_get(group->devices_kobj); - kobject_put(&group->kobj); - - return group; -} -EXPORT_SYMBOL_GPL(iommu_group_get_by_id); - /** * iommu_group_get_iommudata - retrieve iommu_data registered for a group * @group: the group @@ -750,23 +1169,20 @@ int iommu_group_set_name(struct iommu_group *group, const char *name) } EXPORT_SYMBOL_GPL(iommu_group_set_name); -static int iommu_create_device_direct_mappings(struct iommu_group *group, +static int iommu_create_device_direct_mappings(struct iommu_domain *domain, struct device *dev) { - struct iommu_domain *domain = group->default_domain; struct iommu_resv_region *entry; struct list_head mappings; unsigned long pg_size; int ret = 0; - if (!domain || domain->type != IOMMU_DOMAIN_DMA) - return 0; - - BUG_ON(!domain->pgsize_bitmap); - - pg_size = 1UL << __ffs(domain->pgsize_bitmap); + pg_size = domain->pgsize_bitmap ? 1UL << __ffs(domain->pgsize_bitmap) : 0; INIT_LIST_HEAD(&mappings); + if (WARN_ON_ONCE(iommu_is_dma_domain(domain) && !pg_size)) + return -EINVAL; + iommu_get_resv_regions(dev, &mappings); /* We need to consider overlapping regions for different devices */ @@ -774,16 +1190,17 @@ static int iommu_create_device_direct_mappings(struct iommu_group *group, dma_addr_t start, end, addr; size_t map_size = 0; - if (domain->ops->apply_resv_region) - domain->ops->apply_resv_region(dev, domain, entry); + if (entry->type == IOMMU_RESV_DIRECT) + dev->iommu->require_direct = 1; + + if ((entry->type != IOMMU_RESV_DIRECT && + entry->type != IOMMU_RESV_DIRECT_RELAXABLE) || + !iommu_is_dma_domain(domain)) + continue; start = ALIGN(entry->start, pg_size); end = ALIGN(entry->start + entry->length, pg_size); - if (entry->type != IOMMU_RESV_DIRECT && - entry->type != IOMMU_RESV_DIRECT_RELAXABLE) - continue; - for (addr = start; addr <= end; addr += pg_size) { phys_addr_t phys_addr; @@ -800,7 +1217,7 @@ map_end: if (map_size) { ret = iommu_map(domain, addr - map_size, addr - map_size, map_size, - entry->prot); + entry->prot, GFP_KERNEL); if (ret) goto out; map_size = 0; @@ -808,40 +1225,22 @@ map_end: } } - - iommu_flush_iotlb_all(domain); - out: iommu_put_resv_regions(dev, &mappings); return ret; } -static bool iommu_is_attach_deferred(struct iommu_domain *domain, - struct device *dev) -{ - if (domain->ops->is_attach_deferred) - return domain->ops->is_attach_deferred(domain, dev); - - return false; -} - -/** - * iommu_group_add_device - add a device to an iommu group - * @group: the group into which to add the device (reference should be held) - * @dev: the device - * - * This function is called by an iommu driver to add a device into a - * group. Adding a device increments the group reference count. - */ -int iommu_group_add_device(struct iommu_group *group, struct device *dev) +/* This is undone by __iommu_group_free_device() */ +static struct group_device *iommu_group_alloc_device(struct iommu_group *group, + struct device *dev) { int ret, i = 0; struct group_device *device; device = kzalloc(sizeof(*device), GFP_KERNEL); if (!device) - return -ENOMEM; + return ERR_PTR(-ENOMEM); device->dev = dev; @@ -872,35 +1271,12 @@ rename: goto err_free_name; } - kobject_get(group->devices_kobj); - - dev->iommu_group = group; - - mutex_lock(&group->mutex); - list_add_tail(&device->list, &group->devices); - if (group->domain && !iommu_is_attach_deferred(group->domain, dev)) - ret = __iommu_attach_device(group->domain, dev); - mutex_unlock(&group->mutex); - if (ret) - goto err_put_group; - - /* Notify any listeners about change to group. */ - blocking_notifier_call_chain(&group->notifier, - IOMMU_GROUP_NOTIFY_ADD_DEVICE, dev); - trace_add_device_to_group(group->id, dev); dev_info(dev, "Adding to iommu group %d\n", group->id); - return 0; + return device; -err_put_group: - mutex_lock(&group->mutex); - list_del(&device->list); - mutex_unlock(&group->mutex); - dev->iommu_group = NULL; - kobject_put(group->devices_kobj); - sysfs_remove_link(group->devices_kobj, device->name); err_free_name: kfree(device->name); err_remove_link: @@ -908,7 +1284,32 @@ err_remove_link: err_free_device: kfree(device); dev_err(dev, "Failed to add to iommu group %d: %d\n", group->id, ret); - return ret; + return ERR_PTR(ret); +} + +/** + * iommu_group_add_device - add a device to an iommu group + * @group: the group into which to add the device (reference should be held) + * @dev: the device + * + * This function is called by an iommu driver to add a device into a + * group. Adding a device increments the group reference count. + */ +int iommu_group_add_device(struct iommu_group *group, struct device *dev) +{ + struct group_device *gdev; + + gdev = iommu_group_alloc_device(group, dev); + if (IS_ERR(gdev)) + return PTR_ERR(gdev); + + iommu_group_ref_get(group); + dev->iommu_group = group; + + mutex_lock(&group->mutex); + list_add_tail(&gdev->list, &group->devices); + mutex_unlock(&group->mutex); + return 0; } EXPORT_SYMBOL_GPL(iommu_group_add_device); @@ -922,48 +1323,39 @@ EXPORT_SYMBOL_GPL(iommu_group_add_device); void iommu_group_remove_device(struct device *dev) { struct iommu_group *group = dev->iommu_group; - struct group_device *tmp_device, *device = NULL; - - dev_info(dev, "Removing from iommu group %d\n", group->id); - - /* Pre-notify listeners that a device is being removed. */ - blocking_notifier_call_chain(&group->notifier, - IOMMU_GROUP_NOTIFY_DEL_DEVICE, dev); - - mutex_lock(&group->mutex); - list_for_each_entry(tmp_device, &group->devices, list) { - if (tmp_device->dev == dev) { - device = tmp_device; - list_del(&device->list); - break; - } - } - mutex_unlock(&group->mutex); - if (!device) + if (!group) return; - sysfs_remove_link(group->devices_kobj, device->name); - sysfs_remove_link(&dev->kobj, "iommu_group"); - - trace_remove_device_from_group(group->id, dev); + dev_info(dev, "Removing from iommu group %d\n", group->id); - kfree(device->name); - kfree(device); - dev->iommu_group = NULL; - kobject_put(group->devices_kobj); + __iommu_group_remove_device(dev); } EXPORT_SYMBOL_GPL(iommu_group_remove_device); -static int iommu_group_device_count(struct iommu_group *group) +#if IS_ENABLED(CONFIG_LOCKDEP) && IS_ENABLED(CONFIG_IOMMU_API) +/** + * iommu_group_mutex_assert - Check device group mutex lock + * @dev: the device that has group param set + * + * This function is called by an iommu driver to check whether it holds + * group mutex lock for the given device or not. + * + * Note that this function must be called after device group param is set. + */ +void iommu_group_mutex_assert(struct device *dev) { - struct group_device *entry; - int ret = 0; + struct iommu_group *group = dev->iommu_group; - list_for_each_entry(entry, &group->devices, list) - ret++; + lockdep_assert_held(&group->mutex); +} +EXPORT_SYMBOL_GPL(iommu_group_mutex_assert); +#endif - return ret; +static struct device *iommu_group_first_dev(struct iommu_group *group) +{ + lockdep_assert_held(&group->mutex); + return list_first_entry(&group->devices, struct group_device, list)->dev; } /** @@ -977,28 +1369,18 @@ static int iommu_group_device_count(struct iommu_group *group) * The group->mutex is held across callbacks, which will block calls to * iommu_group_add/remove_device. */ -static int __iommu_group_for_each_dev(struct iommu_group *group, void *data, - int (*fn)(struct device *, void *)) +int iommu_group_for_each_dev(struct iommu_group *group, void *data, + int (*fn)(struct device *, void *)) { struct group_device *device; int ret = 0; - list_for_each_entry(device, &group->devices, list) { + mutex_lock(&group->mutex); + for_each_group_device(group, device) { ret = fn(device->dev, data); if (ret) break; } - return ret; -} - - -int iommu_group_for_each_dev(struct iommu_group *group, void *data, - int (*fn)(struct device *, void *)) -{ - int ret; - - mutex_lock(&group->mutex); - ret = __iommu_group_for_each_dev(group, data, fn); mutex_unlock(&group->mutex); return ret; @@ -1053,247 +1435,6 @@ void iommu_group_put(struct iommu_group *group) EXPORT_SYMBOL_GPL(iommu_group_put); /** - * iommu_group_register_notifier - Register a notifier for group changes - * @group: the group to watch - * @nb: notifier block to signal - * - * This function allows iommu group users to track changes in a group. - * See include/linux/iommu.h for actions sent via this notifier. Caller - * should hold a reference to the group throughout notifier registration. - */ -int iommu_group_register_notifier(struct iommu_group *group, - struct notifier_block *nb) -{ - return blocking_notifier_chain_register(&group->notifier, nb); -} -EXPORT_SYMBOL_GPL(iommu_group_register_notifier); - -/** - * iommu_group_unregister_notifier - Unregister a notifier - * @group: the group to watch - * @nb: notifier block to signal - * - * Unregister a previously registered group notifier block. - */ -int iommu_group_unregister_notifier(struct iommu_group *group, - struct notifier_block *nb) -{ - return blocking_notifier_chain_unregister(&group->notifier, nb); -} -EXPORT_SYMBOL_GPL(iommu_group_unregister_notifier); - -/** - * iommu_register_device_fault_handler() - Register a device fault handler - * @dev: the device - * @handler: the fault handler - * @data: private data passed as argument to the handler - * - * When an IOMMU fault event is received, this handler gets called with the - * fault event and data as argument. The handler should return 0 on success. If - * the fault is recoverable (IOMMU_FAULT_PAGE_REQ), the consumer should also - * complete the fault by calling iommu_page_response() with one of the following - * response code: - * - IOMMU_PAGE_RESP_SUCCESS: retry the translation - * - IOMMU_PAGE_RESP_INVALID: terminate the fault - * - IOMMU_PAGE_RESP_FAILURE: terminate the fault and stop reporting - * page faults if possible. - * - * Return 0 if the fault handler was installed successfully, or an error. - */ -int iommu_register_device_fault_handler(struct device *dev, - iommu_dev_fault_handler_t handler, - void *data) -{ - struct dev_iommu *param = dev->iommu; - int ret = 0; - - if (!param) - return -EINVAL; - - mutex_lock(¶m->lock); - /* Only allow one fault handler registered for each device */ - if (param->fault_param) { - ret = -EBUSY; - goto done_unlock; - } - - get_device(dev); - param->fault_param = kzalloc(sizeof(*param->fault_param), GFP_KERNEL); - if (!param->fault_param) { - put_device(dev); - ret = -ENOMEM; - goto done_unlock; - } - param->fault_param->handler = handler; - param->fault_param->data = data; - mutex_init(¶m->fault_param->lock); - INIT_LIST_HEAD(¶m->fault_param->faults); - -done_unlock: - mutex_unlock(¶m->lock); - - return ret; -} -EXPORT_SYMBOL_GPL(iommu_register_device_fault_handler); - -/** - * iommu_unregister_device_fault_handler() - Unregister the device fault handler - * @dev: the device - * - * Remove the device fault handler installed with - * iommu_register_device_fault_handler(). - * - * Return 0 on success, or an error. - */ -int iommu_unregister_device_fault_handler(struct device *dev) -{ - struct dev_iommu *param = dev->iommu; - int ret = 0; - - if (!param) - return -EINVAL; - - mutex_lock(¶m->lock); - - if (!param->fault_param) - goto unlock; - - /* we cannot unregister handler if there are pending faults */ - if (!list_empty(¶m->fault_param->faults)) { - ret = -EBUSY; - goto unlock; - } - - kfree(param->fault_param); - param->fault_param = NULL; - put_device(dev); -unlock: - mutex_unlock(¶m->lock); - - return ret; -} -EXPORT_SYMBOL_GPL(iommu_unregister_device_fault_handler); - -/** - * iommu_report_device_fault() - Report fault event to device driver - * @dev: the device - * @evt: fault event data - * - * Called by IOMMU drivers when a fault is detected, typically in a threaded IRQ - * handler. When this function fails and the fault is recoverable, it is the - * caller's responsibility to complete the fault. - * - * Return 0 on success, or an error. - */ -int iommu_report_device_fault(struct device *dev, struct iommu_fault_event *evt) -{ - struct dev_iommu *param = dev->iommu; - struct iommu_fault_event *evt_pending = NULL; - struct iommu_fault_param *fparam; - int ret = 0; - - if (!param || !evt) - return -EINVAL; - - /* we only report device fault if there is a handler registered */ - mutex_lock(¶m->lock); - fparam = param->fault_param; - if (!fparam || !fparam->handler) { - ret = -EINVAL; - goto done_unlock; - } - - if (evt->fault.type == IOMMU_FAULT_PAGE_REQ && - (evt->fault.prm.flags & IOMMU_FAULT_PAGE_REQUEST_LAST_PAGE)) { - evt_pending = kmemdup(evt, sizeof(struct iommu_fault_event), - GFP_KERNEL); - if (!evt_pending) { - ret = -ENOMEM; - goto done_unlock; - } - mutex_lock(&fparam->lock); - list_add_tail(&evt_pending->list, &fparam->faults); - mutex_unlock(&fparam->lock); - } - - ret = fparam->handler(&evt->fault, fparam->data); - if (ret && evt_pending) { - mutex_lock(&fparam->lock); - list_del(&evt_pending->list); - mutex_unlock(&fparam->lock); - kfree(evt_pending); - } -done_unlock: - mutex_unlock(¶m->lock); - return ret; -} -EXPORT_SYMBOL_GPL(iommu_report_device_fault); - -int iommu_page_response(struct device *dev, - struct iommu_page_response *msg) -{ - bool needs_pasid; - int ret = -EINVAL; - struct iommu_fault_event *evt; - struct iommu_fault_page_request *prm; - struct dev_iommu *param = dev->iommu; - bool has_pasid = msg->flags & IOMMU_PAGE_RESP_PASID_VALID; - struct iommu_domain *domain = iommu_get_domain_for_dev(dev); - - if (!domain || !domain->ops->page_response) - return -ENODEV; - - if (!param || !param->fault_param) - return -EINVAL; - - if (msg->version != IOMMU_PAGE_RESP_VERSION_1 || - msg->flags & ~IOMMU_PAGE_RESP_PASID_VALID) - return -EINVAL; - - /* Only send response if there is a fault report pending */ - mutex_lock(¶m->fault_param->lock); - if (list_empty(¶m->fault_param->faults)) { - dev_warn_ratelimited(dev, "no pending PRQ, drop response\n"); - goto done_unlock; - } - /* - * Check if we have a matching page request pending to respond, - * otherwise return -EINVAL - */ - list_for_each_entry(evt, ¶m->fault_param->faults, list) { - prm = &evt->fault.prm; - if (prm->grpid != msg->grpid) - continue; - - /* - * If the PASID is required, the corresponding request is - * matched using the group ID, the PASID valid bit and the PASID - * value. Otherwise only the group ID matches request and - * response. - */ - needs_pasid = prm->flags & IOMMU_FAULT_PAGE_RESPONSE_NEEDS_PASID; - if (needs_pasid && (!has_pasid || msg->pasid != prm->pasid)) - continue; - - if (!needs_pasid && has_pasid) { - /* No big deal, just clear it. */ - msg->flags &= ~IOMMU_PAGE_RESP_PASID_VALID; - msg->pasid = 0; - } - - ret = domain->ops->page_response(dev, evt, msg); - list_del(&evt->list); - kfree(evt); - break; - } - -done_unlock: - mutex_unlock(¶m->fault_param->lock); - return ret; -} -EXPORT_SYMBOL_GPL(iommu_page_response); - -/** * iommu_group_id - Return ID for a group * @group: the group to ID * @@ -1424,6 +1565,27 @@ struct iommu_group *generic_device_group(struct device *dev) EXPORT_SYMBOL_GPL(generic_device_group); /* + * Generic device_group call-back function. It just allocates one + * iommu-group per iommu driver instance shared by every device + * probed by that iommu driver. + */ +struct iommu_group *generic_single_device_group(struct device *dev) +{ + struct iommu_device *iommu = dev->iommu->iommu_dev; + + if (!iommu->singleton_group) { + struct iommu_group *group; + + group = iommu_group_alloc(); + if (IS_ERR(group)) + return group; + iommu->singleton_group = group; + } + return iommu_group_ref_get(iommu->singleton_group); +} +EXPORT_SYMBOL_GPL(generic_single_device_group); + +/* * Use standard PCI bus topology, isolation features, and DMA alias quirks * to find or create an IOMMU group for a device. */ @@ -1504,95 +1666,100 @@ struct iommu_group *fsl_mc_device_group(struct device *dev) } EXPORT_SYMBOL_GPL(fsl_mc_device_group); -static int iommu_get_def_domain_type(struct device *dev) +static struct iommu_domain *__iommu_alloc_identity_domain(struct device *dev) { - const struct iommu_ops *ops = dev->bus->iommu_ops; + const struct iommu_ops *ops = dev_iommu_ops(dev); + struct iommu_domain *domain; - if (dev_is_pci(dev) && to_pci_dev(dev)->untrusted) - return IOMMU_DOMAIN_DMA; + if (ops->identity_domain) + return ops->identity_domain; - if (ops->def_domain_type) - return ops->def_domain_type(dev); + if (ops->domain_alloc_identity) { + domain = ops->domain_alloc_identity(dev); + if (IS_ERR(domain)) + return domain; + } else { + return ERR_PTR(-EOPNOTSUPP); + } - return 0; + iommu_domain_init(domain, IOMMU_DOMAIN_IDENTITY, ops); + return domain; } -static int iommu_group_alloc_default_domain(struct bus_type *bus, - struct iommu_group *group, - unsigned int type) +static struct iommu_domain * +__iommu_group_alloc_default_domain(struct iommu_group *group, int req_type) { + struct device *dev = iommu_group_first_dev(group); struct iommu_domain *dom; - dom = __iommu_domain_alloc(bus, type); - if (!dom && type != IOMMU_DOMAIN_DMA) { - dom = __iommu_domain_alloc(bus, IOMMU_DOMAIN_DMA); - if (dom) - pr_warn("Failed to allocate default IOMMU domain of type %u for group %s - Falling back to IOMMU_DOMAIN_DMA", - type, group->name); - } - - if (!dom) - return -ENOMEM; + if (group->default_domain && group->default_domain->type == req_type) + return group->default_domain; - group->default_domain = dom; - if (!group->domain) - group->domain = dom; - return 0; -} + /* + * When allocating the DMA API domain assume that the driver is going to + * use PASID and make sure the RID's domain is PASID compatible. + */ + if (req_type & __IOMMU_DOMAIN_PAGING) { + dom = __iommu_paging_domain_alloc_flags(dev, req_type, + dev->iommu->max_pasids ? IOMMU_HWPT_ALLOC_PASID : 0); -static int iommu_alloc_default_domain(struct iommu_group *group, - struct device *dev) -{ - unsigned int type; + /* + * If driver does not support PASID feature then + * try to allocate non-PASID domain + */ + if (PTR_ERR(dom) == -EOPNOTSUPP) + dom = __iommu_paging_domain_alloc_flags(dev, req_type, 0); - if (group->default_domain) - return 0; + return dom; + } - type = iommu_get_def_domain_type(dev) ? : iommu_def_domain_type; + if (req_type == IOMMU_DOMAIN_IDENTITY) + return __iommu_alloc_identity_domain(dev); - return iommu_group_alloc_default_domain(dev->bus, group, type); + return ERR_PTR(-EINVAL); } -/** - * iommu_group_get_for_dev - Find or create the IOMMU group for a device - * @dev: target device - * - * This function is intended to be called by IOMMU drivers and extended to - * support common, bus-defined algorithms when determining or creating the - * IOMMU group for a device. On success, the caller will hold a reference - * to the returned IOMMU group, which will already include the provided - * device. The reference should be released with iommu_group_put(). +/* + * req_type of 0 means "auto" which means to select a domain based on + * iommu_def_domain_type or what the driver actually supports. */ -static struct iommu_group *iommu_group_get_for_dev(struct device *dev) +static struct iommu_domain * +iommu_group_alloc_default_domain(struct iommu_group *group, int req_type) { - const struct iommu_ops *ops = dev->bus->iommu_ops; - struct iommu_group *group; - int ret; - - group = iommu_group_get(dev); - if (group) - return group; - - if (!ops) - return ERR_PTR(-EINVAL); + const struct iommu_ops *ops = dev_iommu_ops(iommu_group_first_dev(group)); + struct iommu_domain *dom; - group = ops->device_group(dev); - if (WARN_ON_ONCE(group == NULL)) - return ERR_PTR(-EINVAL); + lockdep_assert_held(&group->mutex); - if (IS_ERR(group)) - return group; + /* + * Allow legacy drivers to specify the domain that will be the default + * domain. This should always be either an IDENTITY/BLOCKED/PLATFORM + * domain. Do not use in new drivers. + */ + if (ops->default_domain) { + if (req_type != ops->default_domain->type) + return ERR_PTR(-EINVAL); + return ops->default_domain; + } - ret = iommu_group_add_device(group, dev); - if (ret) - goto out_put_group; + if (req_type) + return __iommu_group_alloc_default_domain(group, req_type); - return group; + /* The driver gave no guidance on what type to use, try the default */ + dom = __iommu_group_alloc_default_domain(group, iommu_def_domain_type); + if (!IS_ERR(dom)) + return dom; -out_put_group: - iommu_group_put(group); + /* Otherwise IDENTITY and DMA_FQ defaults will try DMA */ + if (iommu_def_domain_type == IOMMU_DOMAIN_DMA) + return ERR_PTR(-EINVAL); + dom = __iommu_group_alloc_default_domain(group, IOMMU_DOMAIN_DMA); + if (IS_ERR(dom)) + return dom; - return ERR_PTR(ret); + pr_warn("Failed to allocate default IOMMU domain of type %u for group %s - Falling back to IOMMU_DOMAIN_DMA", + iommu_def_domain_type, group->name); + return dom; } struct iommu_domain *iommu_group_default_domain(struct iommu_group *group) @@ -1603,41 +1770,22 @@ struct iommu_domain *iommu_group_default_domain(struct iommu_group *group) static int probe_iommu_group(struct device *dev, void *data) { struct list_head *group_list = data; - struct iommu_group *group; int ret; - /* Device is probed already if in a group */ - group = iommu_group_get(dev); - if (group) { - iommu_group_put(group); - return 0; - } - + mutex_lock(&iommu_probe_device_lock); ret = __iommu_probe_device(dev, group_list); + mutex_unlock(&iommu_probe_device_lock); if (ret == -ENODEV) ret = 0; return ret; } -static int remove_iommu_group(struct device *dev, void *data) -{ - iommu_release_device(dev); - - return 0; -} - static int iommu_bus_notifier(struct notifier_block *nb, unsigned long action, void *data) { - unsigned long group_action = 0; struct device *dev = data; - struct iommu_group *group; - /* - * ADD/DEL call into iommu driver ops if provided, which may - * result in ADD/DEL notifiers to group->notifier - */ if (action == BUS_NOTIFY_ADD_DEVICE) { int ret; @@ -1648,258 +1796,220 @@ static int iommu_bus_notifier(struct notifier_block *nb, return NOTIFY_OK; } - /* - * Remaining BUS_NOTIFYs get filtered and republished to the - * group, if anyone is listening - */ - group = iommu_group_get(dev); - if (!group) - return 0; - - switch (action) { - case BUS_NOTIFY_BIND_DRIVER: - group_action = IOMMU_GROUP_NOTIFY_BIND_DRIVER; - break; - case BUS_NOTIFY_BOUND_DRIVER: - group_action = IOMMU_GROUP_NOTIFY_BOUND_DRIVER; - break; - case BUS_NOTIFY_UNBIND_DRIVER: - group_action = IOMMU_GROUP_NOTIFY_UNBIND_DRIVER; - break; - case BUS_NOTIFY_UNBOUND_DRIVER: - group_action = IOMMU_GROUP_NOTIFY_UNBOUND_DRIVER; - break; - } - - if (group_action) - blocking_notifier_call_chain(&group->notifier, - group_action, dev); - - iommu_group_put(group); return 0; } -struct __group_domain_type { - struct device *dev; - unsigned int type; -}; - -static int probe_get_default_domain_type(struct device *dev, void *data) +/* + * Combine the driver's chosen def_domain_type across all the devices in a + * group. Drivers must give a consistent result. + */ +static int iommu_get_def_domain_type(struct iommu_group *group, + struct device *dev, int cur_type) { - struct __group_domain_type *gtype = data; - unsigned int type = iommu_get_def_domain_type(dev); - - if (type) { - if (gtype->type && gtype->type != type) { - dev_warn(dev, "Device needs domain type %s, but device %s in the same iommu group requires type %s - using default\n", - iommu_domain_type_str(type), - dev_name(gtype->dev), - iommu_domain_type_str(gtype->type)); - gtype->type = 0; - } + const struct iommu_ops *ops = dev_iommu_ops(dev); + int type; - if (!gtype->dev) { - gtype->dev = dev; - gtype->type = type; - } + if (ops->default_domain) { + /* + * Drivers that declare a global static default_domain will + * always choose that. + */ + type = ops->default_domain->type; + } else { + if (ops->def_domain_type) + type = ops->def_domain_type(dev); + else + return cur_type; } + if (!type || cur_type == type) + return cur_type; + if (!cur_type) + return type; - return 0; -} - -static void probe_alloc_default_domain(struct bus_type *bus, - struct iommu_group *group) -{ - struct __group_domain_type gtype; - - memset(>ype, 0, sizeof(gtype)); - - /* Ask for default domain requirements of all devices in the group */ - __iommu_group_for_each_dev(group, >ype, - probe_get_default_domain_type); - - if (!gtype.type) - gtype.type = iommu_def_domain_type; - - iommu_group_alloc_default_domain(bus, group, gtype.type); + dev_err_ratelimited( + dev, + "IOMMU driver error, requesting conflicting def_domain_type, %s and %s, for devices in group %u.\n", + iommu_domain_type_str(cur_type), iommu_domain_type_str(type), + group->id); + /* + * Try to recover, drivers are allowed to force IDENTITY or DMA, IDENTITY + * takes precedence. + */ + if (type == IOMMU_DOMAIN_IDENTITY) + return type; + return cur_type; } -static int iommu_group_do_dma_attach(struct device *dev, void *data) +/* + * A target_type of 0 will select the best domain type. 0 can be returned in + * this case meaning the global default should be used. + */ +static int iommu_get_default_domain_type(struct iommu_group *group, + int target_type) { - struct iommu_domain *domain = data; - int ret = 0; - - if (!iommu_is_attach_deferred(domain, dev)) - ret = __iommu_attach_device(domain, dev); + struct device *untrusted = NULL; + struct group_device *gdev; + int driver_type = 0; - return ret; -} + lockdep_assert_held(&group->mutex); -static int __iommu_group_dma_attach(struct iommu_group *group) -{ - return __iommu_group_for_each_dev(group, group->default_domain, - iommu_group_do_dma_attach); -} + /* + * ARM32 drivers supporting CONFIG_ARM_DMA_USE_IOMMU can declare an + * identity_domain and it will automatically become their default + * domain. Later on ARM_DMA_USE_IOMMU will install its UNMANAGED domain. + * Override the selection to IDENTITY. + */ + if (IS_ENABLED(CONFIG_ARM_DMA_USE_IOMMU)) { + static_assert(!(IS_ENABLED(CONFIG_ARM_DMA_USE_IOMMU) && + IS_ENABLED(CONFIG_IOMMU_DMA))); + driver_type = IOMMU_DOMAIN_IDENTITY; + } -static int iommu_group_do_probe_finalize(struct device *dev, void *data) -{ - struct iommu_domain *domain = data; + for_each_group_device(group, gdev) { + driver_type = iommu_get_def_domain_type(group, gdev->dev, + driver_type); - if (domain->ops->probe_finalize) - domain->ops->probe_finalize(dev); + if (dev_is_pci(gdev->dev) && to_pci_dev(gdev->dev)->untrusted) { + /* + * No ARM32 using systems will set untrusted, it cannot + * work. + */ + if (WARN_ON(IS_ENABLED(CONFIG_ARM_DMA_USE_IOMMU))) + return -1; + untrusted = gdev->dev; + } + } - return 0; -} + /* + * If the common dma ops are not selected in kconfig then we cannot use + * IOMMU_DOMAIN_DMA at all. Force IDENTITY if nothing else has been + * selected. + */ + if (!IS_ENABLED(CONFIG_IOMMU_DMA)) { + if (WARN_ON(driver_type == IOMMU_DOMAIN_DMA)) + return -1; + if (!driver_type) + driver_type = IOMMU_DOMAIN_IDENTITY; + } + + if (untrusted) { + if (driver_type && driver_type != IOMMU_DOMAIN_DMA) { + dev_err_ratelimited( + untrusted, + "Device is not trusted, but driver is overriding group %u to %s, refusing to probe.\n", + group->id, iommu_domain_type_str(driver_type)); + return -1; + } + driver_type = IOMMU_DOMAIN_DMA; + } -static void __iommu_group_dma_finalize(struct iommu_group *group) -{ - __iommu_group_for_each_dev(group, group->default_domain, - iommu_group_do_probe_finalize); + if (target_type) { + if (driver_type && target_type != driver_type) + return -1; + return target_type; + } + return driver_type; } -static int iommu_do_create_direct_mappings(struct device *dev, void *data) +static void iommu_group_do_probe_finalize(struct device *dev) { - struct iommu_group *group = data; - - iommu_create_device_direct_mappings(group, dev); + const struct iommu_ops *ops = dev_iommu_ops(dev); - return 0; -} - -static int iommu_group_create_direct_mappings(struct iommu_group *group) -{ - return __iommu_group_for_each_dev(group, group, - iommu_do_create_direct_mappings); + if (ops->probe_finalize) + ops->probe_finalize(dev); } -int bus_iommu_probe(struct bus_type *bus) +static int bus_iommu_probe(const struct bus_type *bus) { struct iommu_group *group, *next; LIST_HEAD(group_list); int ret; - /* - * This code-path does not allocate the default domain when - * creating the iommu group, so do it after the groups are - * created. - */ ret = bus_for_each_dev(bus, NULL, &group_list, probe_iommu_group); if (ret) return ret; list_for_each_entry_safe(group, next, &group_list, entry) { - /* Remove item from the list */ - list_del_init(&group->entry); + struct group_device *gdev; mutex_lock(&group->mutex); - /* Try to allocate default domain */ - probe_alloc_default_domain(bus, group); + /* Remove item from the list */ + list_del_init(&group->entry); - if (!group->default_domain) { + /* + * We go to the trouble of deferred default domain creation so + * that the cross-group default domain type and the setup of the + * IOMMU_RESV_DIRECT will work correctly in non-hotpug scenarios. + */ + ret = iommu_setup_default_domain(group, 0); + if (ret) { mutex_unlock(&group->mutex); - continue; + return ret; } - - iommu_group_create_direct_mappings(group); - - ret = __iommu_group_dma_attach(group); - + for_each_group_device(group, gdev) + iommu_setup_dma_ops(gdev->dev); mutex_unlock(&group->mutex); - if (ret) - break; - - __iommu_group_dma_finalize(group); + /* + * FIXME: Mis-locked because the ops->probe_finalize() call-back + * of some IOMMU drivers calls arm_iommu_attach_device() which + * in-turn might call back into IOMMU core code, where it tries + * to take group->mutex, resulting in a deadlock. + */ + for_each_group_device(group, gdev) + iommu_group_do_probe_finalize(gdev->dev); } - return ret; -} - -static int iommu_bus_init(struct bus_type *bus, const struct iommu_ops *ops) -{ - struct notifier_block *nb; - int err; - - nb = kzalloc(sizeof(struct notifier_block), GFP_KERNEL); - if (!nb) - return -ENOMEM; - - nb->notifier_call = iommu_bus_notifier; - - err = bus_register_notifier(bus, nb); - if (err) - goto out_free; - - err = bus_iommu_probe(bus); - if (err) - goto out_err; - - return 0; - -out_err: - /* Clean up */ - bus_for_each_dev(bus, NULL, NULL, remove_iommu_group); - bus_unregister_notifier(bus, nb); - -out_free: - kfree(nb); - - return err; } /** - * bus_set_iommu - set iommu-callbacks for the bus - * @bus: bus. - * @ops: the callbacks provided by the iommu-driver + * device_iommu_capable() - check for a general IOMMU capability + * @dev: device to which the capability would be relevant, if available + * @cap: IOMMU capability * - * This function is called by an iommu driver to set the iommu methods - * used for a particular bus. Drivers for devices on that bus can use - * the iommu-api after these ops are registered. - * This special function is needed because IOMMUs are usually devices on - * the bus itself, so the iommu drivers are not initialized when the bus - * is set up. With this function the iommu-driver can set the iommu-ops - * afterwards. + * Return: true if an IOMMU is present and supports the given capability + * for the given device, otherwise false. */ -int bus_set_iommu(struct bus_type *bus, const struct iommu_ops *ops) +bool device_iommu_capable(struct device *dev, enum iommu_cap cap) { - int err; + const struct iommu_ops *ops; - if (ops == NULL) { - bus->iommu_ops = NULL; - return 0; - } - - if (bus->iommu_ops != NULL) - return -EBUSY; - - bus->iommu_ops = ops; - - /* Do IOMMU specific setup for this bus-type */ - err = iommu_bus_init(bus, ops); - if (err) - bus->iommu_ops = NULL; + if (!dev_has_iommu(dev)) + return false; - return err; -} -EXPORT_SYMBOL_GPL(bus_set_iommu); + ops = dev_iommu_ops(dev); + if (!ops->capable) + return false; -bool iommu_present(struct bus_type *bus) -{ - return bus->iommu_ops != NULL; + return ops->capable(dev, cap); } -EXPORT_SYMBOL_GPL(iommu_present); +EXPORT_SYMBOL_GPL(device_iommu_capable); -bool iommu_capable(struct bus_type *bus, enum iommu_cap cap) +/** + * iommu_group_has_isolated_msi() - Compute msi_device_has_isolated_msi() + * for a group + * @group: Group to query + * + * IOMMU groups should not have differing values of + * msi_device_has_isolated_msi() for devices in a group. However nothing + * directly prevents this, so ensure mistakes don't result in isolation failures + * by checking that all the devices are the same. + */ +bool iommu_group_has_isolated_msi(struct iommu_group *group) { - if (!bus->iommu_ops || !bus->iommu_ops->capable) - return false; + struct group_device *group_dev; + bool ret = true; - return bus->iommu_ops->capable(cap); + mutex_lock(&group->mutex); + for_each_group_device(group, group_dev) + ret &= msi_device_has_isolated_msi(group_dev->dev); + mutex_unlock(&group->mutex); + return ret; } -EXPORT_SYMBOL_GPL(iommu_capable); +EXPORT_SYMBOL_GPL(iommu_group_has_isolated_msi); /** * iommu_set_fault_handler() - set a fault handler for an iommu domain @@ -1917,65 +2027,142 @@ void iommu_set_fault_handler(struct iommu_domain *domain, iommu_fault_handler_t handler, void *token) { - BUG_ON(!domain); + if (WARN_ON(!domain || domain->cookie_type != IOMMU_COOKIE_NONE)) + return; + domain->cookie_type = IOMMU_COOKIE_FAULT_HANDLER; domain->handler = handler; domain->handler_token = token; } EXPORT_SYMBOL_GPL(iommu_set_fault_handler); -static struct iommu_domain *__iommu_domain_alloc(struct bus_type *bus, - unsigned type) +static void iommu_domain_init(struct iommu_domain *domain, unsigned int type, + const struct iommu_ops *ops) +{ + domain->type = type; + domain->owner = ops; + if (!domain->ops) + domain->ops = ops->default_domain_ops; +} + +static struct iommu_domain * +__iommu_paging_domain_alloc_flags(struct device *dev, unsigned int type, + unsigned int flags) { + const struct iommu_ops *ops; struct iommu_domain *domain; - if (bus == NULL || bus->iommu_ops == NULL) - return NULL; + if (!dev_has_iommu(dev)) + return ERR_PTR(-ENODEV); - domain = bus->iommu_ops->domain_alloc(type); - if (!domain) - return NULL; + ops = dev_iommu_ops(dev); - domain->ops = bus->iommu_ops; - domain->type = type; - /* Assume all sizes by default; the driver may override this later */ - domain->pgsize_bitmap = bus->iommu_ops->pgsize_bitmap; + if (ops->domain_alloc_paging && !flags) + domain = ops->domain_alloc_paging(dev); + else if (ops->domain_alloc_paging_flags) + domain = ops->domain_alloc_paging_flags(dev, flags, NULL); +#if IS_ENABLED(CONFIG_FSL_PAMU) + else if (ops->domain_alloc && !flags) + domain = ops->domain_alloc(IOMMU_DOMAIN_UNMANAGED); +#endif + else + return ERR_PTR(-EOPNOTSUPP); + if (IS_ERR(domain)) + return domain; + if (!domain) + return ERR_PTR(-ENOMEM); + + iommu_domain_init(domain, type, ops); return domain; } -struct iommu_domain *iommu_domain_alloc(struct bus_type *bus) +/** + * iommu_paging_domain_alloc_flags() - Allocate a paging domain + * @dev: device for which the domain is allocated + * @flags: Bitmap of iommufd_hwpt_alloc_flags + * + * Allocate a paging domain which will be managed by a kernel driver. Return + * allocated domain if successful, or an ERR pointer for failure. + */ +struct iommu_domain *iommu_paging_domain_alloc_flags(struct device *dev, + unsigned int flags) { - return __iommu_domain_alloc(bus, IOMMU_DOMAIN_UNMANAGED); + return __iommu_paging_domain_alloc_flags(dev, + IOMMU_DOMAIN_UNMANAGED, flags); } -EXPORT_SYMBOL_GPL(iommu_domain_alloc); +EXPORT_SYMBOL_GPL(iommu_paging_domain_alloc_flags); void iommu_domain_free(struct iommu_domain *domain) { - domain->ops->domain_free(domain); + switch (domain->cookie_type) { + case IOMMU_COOKIE_DMA_IOVA: + iommu_put_dma_cookie(domain); + break; + case IOMMU_COOKIE_DMA_MSI: + iommu_put_msi_cookie(domain); + break; + case IOMMU_COOKIE_SVA: + mmdrop(domain->mm); + break; + default: + break; + } + if (domain->ops->free) + domain->ops->free(domain); } EXPORT_SYMBOL_GPL(iommu_domain_free); +/* + * Put the group's domain back to the appropriate core-owned domain - either the + * standard kernel-mode DMA configuration or an all-DMA-blocked domain. + */ +static void __iommu_group_set_core_domain(struct iommu_group *group) +{ + struct iommu_domain *new_domain; + + if (group->owner) + new_domain = group->blocking_domain; + else + new_domain = group->default_domain; + + __iommu_group_set_domain_nofail(group, new_domain); +} + static int __iommu_attach_device(struct iommu_domain *domain, - struct device *dev) + struct device *dev, struct iommu_domain *old) { int ret; if (unlikely(domain->ops->attach_dev == NULL)) return -ENODEV; - ret = domain->ops->attach_dev(domain, dev); - if (!ret) - trace_attach_device_to_domain(dev); - return ret; + ret = domain->ops->attach_dev(domain, dev, old); + if (ret) + return ret; + dev->iommu->attach_deferred = 0; + trace_attach_device_to_domain(dev); + return 0; } +/** + * iommu_attach_device - Attach an IOMMU domain to a device + * @domain: IOMMU domain to attach + * @dev: Device that will be attached + * + * Returns 0 on success and error code on failure + * + * Note that EINVAL can be treated as a soft failure, indicating + * that certain configuration of the domain is incompatible with + * the device. In this case attaching a different domain to the + * device may succeed. + */ int iommu_attach_device(struct iommu_domain *domain, struct device *dev) { - struct iommu_group *group; + /* Caller must be a probed driver on dev */ + struct iommu_group *group = dev->iommu_group; int ret; - group = iommu_group_get(dev); if (!group) return -ENODEV; @@ -1985,288 +2172,53 @@ int iommu_attach_device(struct iommu_domain *domain, struct device *dev) */ mutex_lock(&group->mutex); ret = -EINVAL; - if (iommu_group_device_count(group) != 1) + if (list_count_nodes(&group->devices) != 1) goto out_unlock; ret = __iommu_attach_group(domain, group); out_unlock: mutex_unlock(&group->mutex); - iommu_group_put(group); - return ret; } EXPORT_SYMBOL_GPL(iommu_attach_device); int iommu_deferred_attach(struct device *dev, struct iommu_domain *domain) { - const struct iommu_ops *ops = domain->ops; - - if (ops->is_attach_deferred && ops->is_attach_deferred(domain, dev)) - return __iommu_attach_device(domain, dev); - - return 0; -} - -/* - * Check flags and other user provided data for valid combinations. We also - * make sure no reserved fields or unused flags are set. This is to ensure - * not breaking userspace in the future when these fields or flags are used. - */ -static int iommu_check_cache_invl_data(struct iommu_cache_invalidate_info *info) -{ - u32 mask; - int i; - - if (info->version != IOMMU_CACHE_INVALIDATE_INFO_VERSION_1) - return -EINVAL; - - mask = (1 << IOMMU_CACHE_INV_TYPE_NR) - 1; - if (info->cache & ~mask) - return -EINVAL; - - if (info->granularity >= IOMMU_INV_GRANU_NR) - return -EINVAL; - - switch (info->granularity) { - case IOMMU_INV_GRANU_ADDR: - if (info->cache & IOMMU_CACHE_INV_TYPE_PASID) - return -EINVAL; - - mask = IOMMU_INV_ADDR_FLAGS_PASID | - IOMMU_INV_ADDR_FLAGS_ARCHID | - IOMMU_INV_ADDR_FLAGS_LEAF; - - if (info->granu.addr_info.flags & ~mask) - return -EINVAL; - break; - case IOMMU_INV_GRANU_PASID: - mask = IOMMU_INV_PASID_FLAGS_PASID | - IOMMU_INV_PASID_FLAGS_ARCHID; - if (info->granu.pasid_info.flags & ~mask) - return -EINVAL; - - break; - case IOMMU_INV_GRANU_DOMAIN: - if (info->cache & IOMMU_CACHE_INV_TYPE_DEV_IOTLB) - return -EINVAL; - break; - default: - return -EINVAL; - } - - /* Check reserved padding fields */ - for (i = 0; i < sizeof(info->padding); i++) { - if (info->padding[i]) - return -EINVAL; - } - - return 0; -} - -int iommu_uapi_cache_invalidate(struct iommu_domain *domain, struct device *dev, - void __user *uinfo) -{ - struct iommu_cache_invalidate_info inv_info = { 0 }; - u32 minsz; - int ret; - - if (unlikely(!domain->ops->cache_invalidate)) - return -ENODEV; - - /* - * No new spaces can be added before the variable sized union, the - * minimum size is the offset to the union. - */ - minsz = offsetof(struct iommu_cache_invalidate_info, granu); - - /* Copy minsz from user to get flags and argsz */ - if (copy_from_user(&inv_info, uinfo, minsz)) - return -EFAULT; - - /* Fields before the variable size union are mandatory */ - if (inv_info.argsz < minsz) - return -EINVAL; - - /* PASID and address granu require additional info beyond minsz */ - if (inv_info.granularity == IOMMU_INV_GRANU_PASID && - inv_info.argsz < offsetofend(struct iommu_cache_invalidate_info, granu.pasid_info)) - return -EINVAL; - - if (inv_info.granularity == IOMMU_INV_GRANU_ADDR && - inv_info.argsz < offsetofend(struct iommu_cache_invalidate_info, granu.addr_info)) - return -EINVAL; - - /* - * User might be using a newer UAPI header which has a larger data - * size, we shall support the existing flags within the current - * size. Copy the remaining user data _after_ minsz but not more - * than the current kernel supported size. - */ - if (copy_from_user((void *)&inv_info + minsz, uinfo + minsz, - min_t(u32, inv_info.argsz, sizeof(inv_info)) - minsz)) - return -EFAULT; - - /* Now the argsz is validated, check the content */ - ret = iommu_check_cache_invl_data(&inv_info); - if (ret) - return ret; - - return domain->ops->cache_invalidate(domain, dev, &inv_info); -} -EXPORT_SYMBOL_GPL(iommu_uapi_cache_invalidate); - -static int iommu_check_bind_data(struct iommu_gpasid_bind_data *data) -{ - u64 mask; - int i; - - if (data->version != IOMMU_GPASID_BIND_VERSION_1) - return -EINVAL; - - /* Check the range of supported formats */ - if (data->format >= IOMMU_PASID_FORMAT_LAST) - return -EINVAL; - - /* Check all flags */ - mask = IOMMU_SVA_GPASID_VAL; - if (data->flags & ~mask) - return -EINVAL; - - /* Check reserved padding fields */ - for (i = 0; i < sizeof(data->padding); i++) { - if (data->padding[i]) - return -EINVAL; - } + if (dev->iommu && dev->iommu->attach_deferred) + return __iommu_attach_device(domain, dev, NULL); return 0; } -static int iommu_sva_prepare_bind_data(void __user *udata, - struct iommu_gpasid_bind_data *data) -{ - u32 minsz; - - /* - * No new spaces can be added before the variable sized union, the - * minimum size is the offset to the union. - */ - minsz = offsetof(struct iommu_gpasid_bind_data, vendor); - - /* Copy minsz from user to get flags and argsz */ - if (copy_from_user(data, udata, minsz)) - return -EFAULT; - - /* Fields before the variable size union are mandatory */ - if (data->argsz < minsz) - return -EINVAL; - /* - * User might be using a newer UAPI header, we shall let IOMMU vendor - * driver decide on what size it needs. Since the guest PASID bind data - * can be vendor specific, larger argsz could be the result of extension - * for one vendor but it should not affect another vendor. - * Copy the remaining user data _after_ minsz - */ - if (copy_from_user((void *)data + minsz, udata + minsz, - min_t(u32, data->argsz, sizeof(*data)) - minsz)) - return -EFAULT; - - return iommu_check_bind_data(data); -} - -int iommu_uapi_sva_bind_gpasid(struct iommu_domain *domain, struct device *dev, - void __user *udata) -{ - struct iommu_gpasid_bind_data data = { 0 }; - int ret; - - if (unlikely(!domain->ops->sva_bind_gpasid)) - return -ENODEV; - - ret = iommu_sva_prepare_bind_data(udata, &data); - if (ret) - return ret; - - return domain->ops->sva_bind_gpasid(domain, dev, &data); -} -EXPORT_SYMBOL_GPL(iommu_uapi_sva_bind_gpasid); - -int iommu_sva_unbind_gpasid(struct iommu_domain *domain, struct device *dev, - ioasid_t pasid) -{ - if (unlikely(!domain->ops->sva_unbind_gpasid)) - return -ENODEV; - - return domain->ops->sva_unbind_gpasid(dev, pasid); -} -EXPORT_SYMBOL_GPL(iommu_sva_unbind_gpasid); - -int iommu_uapi_sva_unbind_gpasid(struct iommu_domain *domain, struct device *dev, - void __user *udata) -{ - struct iommu_gpasid_bind_data data = { 0 }; - int ret; - - if (unlikely(!domain->ops->sva_bind_gpasid)) - return -ENODEV; - - ret = iommu_sva_prepare_bind_data(udata, &data); - if (ret) - return ret; - - return iommu_sva_unbind_gpasid(domain, dev, data.hpasid); -} -EXPORT_SYMBOL_GPL(iommu_uapi_sva_unbind_gpasid); - -static void __iommu_detach_device(struct iommu_domain *domain, - struct device *dev) -{ - if (iommu_is_attach_deferred(domain, dev)) - return; - - if (unlikely(domain->ops->detach_dev == NULL)) - return; - - domain->ops->detach_dev(domain, dev); - trace_detach_device_from_domain(dev); -} - void iommu_detach_device(struct iommu_domain *domain, struct device *dev) { - struct iommu_group *group; + /* Caller must be a probed driver on dev */ + struct iommu_group *group = dev->iommu_group; - group = iommu_group_get(dev); if (!group) return; mutex_lock(&group->mutex); - if (iommu_group_device_count(group) != 1) { - WARN_ON(1); + if (WARN_ON(domain != group->domain) || + WARN_ON(list_count_nodes(&group->devices) != 1)) goto out_unlock; - } - - __iommu_detach_group(domain, group); + __iommu_group_set_core_domain(group); out_unlock: mutex_unlock(&group->mutex); - iommu_group_put(group); } EXPORT_SYMBOL_GPL(iommu_detach_device); struct iommu_domain *iommu_get_domain_for_dev(struct device *dev) { - struct iommu_domain *domain; - struct iommu_group *group; + /* Caller must be a probed driver on dev */ + struct iommu_group *group = dev->iommu_group; - group = iommu_group_get(dev); if (!group) return NULL; - domain = group->domain; - - iommu_group_put(group); - - return domain; + return group->domain; } EXPORT_SYMBOL_GPL(iommu_get_domain_for_dev); @@ -2279,39 +2231,59 @@ struct iommu_domain *iommu_get_dma_domain(struct device *dev) return dev->iommu_group->default_domain; } -/* - * IOMMU groups are really the natural working unit of the IOMMU, but - * the IOMMU API works on domains and devices. Bridge that gap by - * iterating over the devices in a group. Ideally we'd have a single - * device which represents the requestor ID of the group, but we also - * allow IOMMU drivers to create policy defined minimum sets, where - * the physical hardware may be able to distiguish members, but we - * wish to group them at a higher level (ex. untrusted multi-function - * PCI devices). Thus we attach each device. - */ -static int iommu_group_do_attach_device(struct device *dev, void *data) +static void *iommu_make_pasid_array_entry(struct iommu_domain *domain, + struct iommu_attach_handle *handle) { - struct iommu_domain *domain = data; + if (handle) { + handle->domain = domain; + return xa_tag_pointer(handle, IOMMU_PASID_ARRAY_HANDLE); + } - return __iommu_attach_device(domain, dev); + return xa_tag_pointer(domain, IOMMU_PASID_ARRAY_DOMAIN); +} + +static bool domain_iommu_ops_compatible(const struct iommu_ops *ops, + struct iommu_domain *domain) +{ + if (domain->owner == ops) + return true; + + /* For static domains, owner isn't set. */ + if (domain == ops->blocked_domain || domain == ops->identity_domain) + return true; + + return false; } static int __iommu_attach_group(struct iommu_domain *domain, struct iommu_group *group) { - int ret; + struct device *dev; - if (group->default_domain && group->domain != group->default_domain) + if (group->domain && group->domain != group->default_domain && + group->domain != group->blocking_domain) return -EBUSY; - ret = __iommu_group_for_each_dev(group, domain, - iommu_group_do_attach_device); - if (ret == 0) - group->domain = domain; + dev = iommu_group_first_dev(group); + if (!dev_has_iommu(dev) || + !domain_iommu_ops_compatible(dev_iommu_ops(dev), domain)) + return -EINVAL; - return ret; + return __iommu_group_set_domain(group, domain); } +/** + * iommu_attach_group - Attach an IOMMU domain to an IOMMU group + * @domain: IOMMU domain to attach + * @group: IOMMU group that will be attached + * + * Returns 0 on success and error code on failure + * + * Note that EINVAL can be treated as a soft failure, indicating + * that certain configuration of the domain is incompatible with + * the group. In this case attaching a different domain to the + * group may succeed. + */ int iommu_attach_group(struct iommu_domain *domain, struct iommu_group *group) { int ret; @@ -2324,105 +2296,233 @@ int iommu_attach_group(struct iommu_domain *domain, struct iommu_group *group) } EXPORT_SYMBOL_GPL(iommu_attach_group); -static int iommu_group_do_detach_device(struct device *dev, void *data) +static int __iommu_device_set_domain(struct iommu_group *group, + struct device *dev, + struct iommu_domain *new_domain, + struct iommu_domain *old_domain, + unsigned int flags) { - struct iommu_domain *domain = data; + int ret; - __iommu_detach_device(domain, dev); + /* + * If the device requires IOMMU_RESV_DIRECT then we cannot allow + * the blocking domain to be attached as it does not contain the + * required 1:1 mapping. This test effectively excludes the device + * being used with iommu_group_claim_dma_owner() which will block + * vfio and iommufd as well. + */ + if (dev->iommu->require_direct && + (new_domain->type == IOMMU_DOMAIN_BLOCKED || + new_domain == group->blocking_domain)) { + dev_warn(dev, + "Firmware has requested this device have a 1:1 IOMMU mapping, rejecting configuring the device without a 1:1 mapping. Contact your platform vendor.\n"); + return -EINVAL; + } + if (dev->iommu->attach_deferred) { + if (new_domain == group->default_domain) + return 0; + dev->iommu->attach_deferred = 0; + } + + ret = __iommu_attach_device(new_domain, dev, old_domain); + if (ret) { + /* + * If we have a blocking domain then try to attach that in hopes + * of avoiding a UAF. Modern drivers should implement blocking + * domains as global statics that cannot fail. + */ + if ((flags & IOMMU_SET_DOMAIN_MUST_SUCCEED) && + group->blocking_domain && + group->blocking_domain != new_domain) + __iommu_attach_device(group->blocking_domain, dev, + old_domain); + return ret; + } return 0; } -static void __iommu_detach_group(struct iommu_domain *domain, - struct iommu_group *group) +/* + * If 0 is returned the group's domain is new_domain. If an error is returned + * then the group's domain will be set back to the existing domain unless + * IOMMU_SET_DOMAIN_MUST_SUCCEED, otherwise an error is returned and the group's + * domains is left inconsistent. This is a driver bug to fail attach with a + * previously good domain. We try to avoid a kernel UAF because of this. + * + * IOMMU groups are really the natural working unit of the IOMMU, but the IOMMU + * API works on domains and devices. Bridge that gap by iterating over the + * devices in a group. Ideally we'd have a single device which represents the + * requestor ID of the group, but we also allow IOMMU drivers to create policy + * defined minimum sets, where the physical hardware may be able to distiguish + * members, but we wish to group them at a higher level (ex. untrusted + * multi-function PCI devices). Thus we attach each device. + */ +static int __iommu_group_set_domain_internal(struct iommu_group *group, + struct iommu_domain *new_domain, + unsigned int flags) { + struct group_device *last_gdev; + struct group_device *gdev; + int result; int ret; - if (!group->default_domain) { - __iommu_group_for_each_dev(group, domain, - iommu_group_do_detach_device); - group->domain = NULL; - return; - } + lockdep_assert_held(&group->mutex); - if (group->domain == group->default_domain) - return; + if (group->domain == new_domain) + return 0; - /* Detach by re-attaching to the default domain */ - ret = __iommu_group_for_each_dev(group, group->default_domain, - iommu_group_do_attach_device); - if (ret != 0) - WARN_ON(1); - else - group->domain = group->default_domain; + if (WARN_ON(!new_domain)) + return -EINVAL; + + /* + * Changing the domain is done by calling attach_dev() on the new + * domain. This switch does not have to be atomic and DMA can be + * discarded during the transition. DMA must only be able to access + * either new_domain or group->domain, never something else. + */ + result = 0; + for_each_group_device(group, gdev) { + ret = __iommu_device_set_domain(group, gdev->dev, new_domain, + group->domain, flags); + if (ret) { + result = ret; + /* + * Keep trying the other devices in the group. If a + * driver fails attach to an otherwise good domain, and + * does not support blocking domains, it should at least + * drop its reference on the current domain so we don't + * UAF. + */ + if (flags & IOMMU_SET_DOMAIN_MUST_SUCCEED) + continue; + goto err_revert; + } + } + group->domain = new_domain; + return result; + +err_revert: + /* + * This is called in error unwind paths. A well behaved driver should + * always allow us to attach to a domain that was already attached. + */ + last_gdev = gdev; + for_each_group_device(group, gdev) { + /* No need to revert the last gdev that failed to set domain */ + if (gdev == last_gdev) + break; + /* + * A NULL domain can happen only for first probe, in which case + * we leave group->domain as NULL and let release clean + * everything up. + */ + if (group->domain) + WARN_ON(__iommu_device_set_domain( + group, gdev->dev, group->domain, new_domain, + IOMMU_SET_DOMAIN_MUST_SUCCEED)); + } + return ret; } void iommu_detach_group(struct iommu_domain *domain, struct iommu_group *group) { mutex_lock(&group->mutex); - __iommu_detach_group(domain, group); + __iommu_group_set_core_domain(group); mutex_unlock(&group->mutex); } EXPORT_SYMBOL_GPL(iommu_detach_group); phys_addr_t iommu_iova_to_phys(struct iommu_domain *domain, dma_addr_t iova) { - if (unlikely(domain->ops->iova_to_phys == NULL)) + if (domain->type == IOMMU_DOMAIN_IDENTITY) + return iova; + + if (domain->type == IOMMU_DOMAIN_BLOCKED) return 0; return domain->ops->iova_to_phys(domain, iova); } EXPORT_SYMBOL_GPL(iommu_iova_to_phys); -static size_t iommu_pgsize(struct iommu_domain *domain, - unsigned long addr_merge, size_t size) +static size_t iommu_pgsize(struct iommu_domain *domain, unsigned long iova, + phys_addr_t paddr, size_t size, size_t *count) { - unsigned int pgsize_idx; - size_t pgsize; + unsigned int pgsize_idx, pgsize_idx_next; + unsigned long pgsizes; + size_t offset, pgsize, pgsize_next; + size_t offset_end; + unsigned long addr_merge = paddr | iova; - /* Max page size that still fits into 'size' */ - pgsize_idx = __fls(size); + /* Page sizes supported by the hardware and small enough for @size */ + pgsizes = domain->pgsize_bitmap & GENMASK(__fls(size), 0); - /* need to consider alignment requirements ? */ - if (likely(addr_merge)) { - /* Max page size allowed by address */ - unsigned int align_pgsize_idx = __ffs(addr_merge); - pgsize_idx = min(pgsize_idx, align_pgsize_idx); - } + /* Constrain the page sizes further based on the maximum alignment */ + if (likely(addr_merge)) + pgsizes &= GENMASK(__ffs(addr_merge), 0); + + /* Make sure we have at least one suitable page size */ + BUG_ON(!pgsizes); + + /* Pick the biggest page size remaining */ + pgsize_idx = __fls(pgsizes); + pgsize = BIT(pgsize_idx); + if (!count) + return pgsize; - /* build a mask of acceptable page sizes */ - pgsize = (1UL << (pgsize_idx + 1)) - 1; + /* Find the next biggest support page size, if it exists */ + pgsizes = domain->pgsize_bitmap & ~GENMASK(pgsize_idx, 0); + if (!pgsizes) + goto out_set_count; - /* throw away page sizes not supported by the hardware */ - pgsize &= domain->pgsize_bitmap; + pgsize_idx_next = __ffs(pgsizes); + pgsize_next = BIT(pgsize_idx_next); - /* make sure we're still sane */ - BUG_ON(!pgsize); + /* + * There's no point trying a bigger page size unless the virtual + * and physical addresses are similarly offset within the larger page. + */ + if ((iova ^ paddr) & (pgsize_next - 1)) + goto out_set_count; - /* pick the biggest page */ - pgsize_idx = __fls(pgsize); - pgsize = 1UL << pgsize_idx; + /* Calculate the offset to the next page size alignment boundary */ + offset = pgsize_next - (addr_merge & (pgsize_next - 1)); + /* + * If size is big enough to accommodate the larger page, reduce + * the number of smaller pages. + */ + if (!check_add_overflow(offset, pgsize_next, &offset_end) && + offset_end <= size) + size = offset; + +out_set_count: + *count = size >> pgsize_idx; return pgsize; } -static int __iommu_map(struct iommu_domain *domain, unsigned long iova, - phys_addr_t paddr, size_t size, int prot, gfp_t gfp) +int iommu_map_nosync(struct iommu_domain *domain, unsigned long iova, + phys_addr_t paddr, size_t size, int prot, gfp_t gfp) { - const struct iommu_ops *ops = domain->ops; + const struct iommu_domain_ops *ops = domain->ops; unsigned long orig_iova = iova; unsigned int min_pagesz; size_t orig_size = size; phys_addr_t orig_paddr = paddr; int ret = 0; - if (unlikely(ops->map == NULL || - domain->pgsize_bitmap == 0UL)) - return -ENODEV; + might_sleep_if(gfpflags_allow_blocking(gfp)); if (unlikely(!(domain->type & __IOMMU_DOMAIN_PAGING))) return -EINVAL; + if (WARN_ON(!ops->map_pages || domain->pgsize_bitmap == 0UL)) + return -ENODEV; + + /* Discourage passing strange GFP flags */ + if (WARN_ON_ONCE(gfp & (__GFP_COMP | __GFP_DMA | __GFP_DMA32 | + __GFP_HIGHMEM))) + return -EINVAL; + /* find out the minimum page size supported */ min_pagesz = 1 << __ffs(domain->pgsize_bitmap); @@ -2440,18 +2540,25 @@ static int __iommu_map(struct iommu_domain *domain, unsigned long iova, pr_debug("map: iova 0x%lx pa %pa size 0x%zx\n", iova, &paddr, size); while (size) { - size_t pgsize = iommu_pgsize(domain, iova | paddr, size); + size_t pgsize, count, mapped = 0; + + pgsize = iommu_pgsize(domain, iova, paddr, size, &count); - pr_debug("mapping: iova 0x%lx pa %pa pgsize 0x%zx\n", - iova, &paddr, pgsize); - ret = ops->map(domain, iova, paddr, pgsize, prot, gfp); + pr_debug("mapping: iova 0x%lx pa %pa pgsize 0x%zx count %zu\n", + iova, &paddr, pgsize, count); + ret = ops->map_pages(domain, iova, paddr, pgsize, count, prot, + gfp, &mapped); + /* + * Some pages may have been mapped, even if an error occurred, + * so we should account for those so they can be unmapped. + */ + size -= mapped; if (ret) break; - iova += pgsize; - paddr += pgsize; - size -= pgsize; + iova += mapped; + paddr += mapped; } /* unroll mapping in case something went wrong */ @@ -2463,48 +2570,45 @@ static int __iommu_map(struct iommu_domain *domain, unsigned long iova, return ret; } -static int _iommu_map(struct iommu_domain *domain, unsigned long iova, - phys_addr_t paddr, size_t size, int prot, gfp_t gfp) +int iommu_sync_map(struct iommu_domain *domain, unsigned long iova, size_t size) { - const struct iommu_ops *ops = domain->ops; - int ret; - - ret = __iommu_map(domain, iova, paddr, size, prot, gfp); - if (ret == 0 && ops->iotlb_sync_map) - ops->iotlb_sync_map(domain, iova, size); + const struct iommu_domain_ops *ops = domain->ops; - return ret; + if (!ops->iotlb_sync_map) + return 0; + return ops->iotlb_sync_map(domain, iova, size); } int iommu_map(struct iommu_domain *domain, unsigned long iova, - phys_addr_t paddr, size_t size, int prot) + phys_addr_t paddr, size_t size, int prot, gfp_t gfp) { - might_sleep(); - return _iommu_map(domain, iova, paddr, size, prot, GFP_KERNEL); -} -EXPORT_SYMBOL_GPL(iommu_map); + int ret; -int iommu_map_atomic(struct iommu_domain *domain, unsigned long iova, - phys_addr_t paddr, size_t size, int prot) -{ - return _iommu_map(domain, iova, paddr, size, prot, GFP_ATOMIC); + ret = iommu_map_nosync(domain, iova, paddr, size, prot, gfp); + if (ret) + return ret; + + ret = iommu_sync_map(domain, iova, size); + if (ret) + iommu_unmap(domain, iova, size); + + return ret; } -EXPORT_SYMBOL_GPL(iommu_map_atomic); +EXPORT_SYMBOL_GPL(iommu_map); static size_t __iommu_unmap(struct iommu_domain *domain, unsigned long iova, size_t size, struct iommu_iotlb_gather *iotlb_gather) { - const struct iommu_ops *ops = domain->ops; + const struct iommu_domain_ops *ops = domain->ops; size_t unmapped_page, unmapped = 0; unsigned long orig_iova = iova; unsigned int min_pagesz; - if (unlikely(ops->unmap == NULL || - domain->pgsize_bitmap == 0UL)) + if (unlikely(!(domain->type & __IOMMU_DOMAIN_PAGING))) return 0; - if (unlikely(!(domain->type & __IOMMU_DOMAIN_PAGING))) + if (WARN_ON(!ops->unmap_pages || domain->pgsize_bitmap == 0UL)) return 0; /* find out the minimum page size supported */ @@ -2528,9 +2632,10 @@ static size_t __iommu_unmap(struct iommu_domain *domain, * or we hit an area that isn't mapped. */ while (unmapped < size) { - size_t pgsize = iommu_pgsize(domain, iova, size - unmapped); + size_t pgsize, count; - unmapped_page = ops->unmap(domain, iova, pgsize, iotlb_gather); + pgsize = iommu_pgsize(domain, iova, iova, size - unmapped, &count); + unmapped_page = ops->unmap_pages(domain, iova, pgsize, count, iotlb_gather); if (!unmapped_page) break; @@ -2545,6 +2650,20 @@ static size_t __iommu_unmap(struct iommu_domain *domain, return unmapped; } +/** + * iommu_unmap() - Remove mappings from a range of IOVA + * @domain: Domain to manipulate + * @iova: IO virtual address to start + * @size: Length of the range starting from @iova + * + * iommu_unmap() will remove a translation created by iommu_map(). It cannot + * subdivide a mapping created by iommu_map(), so it should be called with IOVA + * ranges that match what was passed to iommu_map(). The range can aggregate + * contiguous iommu_map() calls so long as no individual range is split. + * + * Returns: Number of bytes of IOVA unmapped. iova + res will be the point + * unmapping stopped. + */ size_t iommu_unmap(struct iommu_domain *domain, unsigned long iova, size_t size) { @@ -2559,6 +2678,25 @@ size_t iommu_unmap(struct iommu_domain *domain, } EXPORT_SYMBOL_GPL(iommu_unmap); +/** + * iommu_unmap_fast() - Remove mappings from a range of IOVA without IOTLB sync + * @domain: Domain to manipulate + * @iova: IO virtual address to start + * @size: Length of the range starting from @iova + * @iotlb_gather: range information for a pending IOTLB flush + * + * iommu_unmap_fast() will remove a translation created by iommu_map(). + * It can't subdivide a mapping created by iommu_map(), so it should be + * called with IOVA ranges that match what was passed to iommu_map(). The + * range can aggregate contiguous iommu_map() calls so long as no individual + * range is split. + * + * Basically iommu_unmap_fast() is the same as iommu_unmap() but for callers + * which manage the IOTLB flushing externally to perform a batched sync. + * + * Returns: Number of bytes of IOVA unmapped. iova + res will be the point + * unmapping stopped. + */ size_t iommu_unmap_fast(struct iommu_domain *domain, unsigned long iova, size_t size, struct iommu_iotlb_gather *iotlb_gather) @@ -2567,11 +2705,10 @@ size_t iommu_unmap_fast(struct iommu_domain *domain, } EXPORT_SYMBOL_GPL(iommu_unmap_fast); -static size_t __iommu_map_sg(struct iommu_domain *domain, unsigned long iova, - struct scatterlist *sg, unsigned int nents, int prot, - gfp_t gfp) +ssize_t iommu_map_sg(struct iommu_domain *domain, unsigned long iova, + struct scatterlist *sg, unsigned int nents, int prot, + gfp_t gfp) { - const struct iommu_ops *ops = domain->ops; size_t len = 0, mapped = 0; phys_addr_t start; unsigned int i = 0; @@ -2581,9 +2718,8 @@ static size_t __iommu_map_sg(struct iommu_domain *domain, unsigned long iova, phys_addr_t s_phys = sg_phys(sg); if (len && s_phys != start + len) { - ret = __iommu_map(domain, iova + mapped, start, + ret = iommu_map_nosync(domain, iova + mapped, start, len, prot, gfp); - if (ret) goto out_err; @@ -2591,6 +2727,9 @@ static size_t __iommu_map_sg(struct iommu_domain *domain, unsigned long iova, len = 0; } + if (sg_dma_is_bus_address(sg)) + goto next; + if (len) { len += sg->length; } else { @@ -2598,36 +2737,25 @@ static size_t __iommu_map_sg(struct iommu_domain *domain, unsigned long iova, start = s_phys; } +next: if (++i < nents) sg = sg_next(sg); } - if (ops->iotlb_sync_map) - ops->iotlb_sync_map(domain, iova, mapped); + ret = iommu_sync_map(domain, iova, mapped); + if (ret) + goto out_err; + return mapped; out_err: /* undo mappings already done */ iommu_unmap(domain, iova, mapped); - return 0; - -} - -size_t iommu_map_sg(struct iommu_domain *domain, unsigned long iova, - struct scatterlist *sg, unsigned int nents, int prot) -{ - might_sleep(); - return __iommu_map_sg(domain, iova, sg, nents, prot, GFP_KERNEL); + return ret; } EXPORT_SYMBOL_GPL(iommu_map_sg); -size_t iommu_map_sg_atomic(struct iommu_domain *domain, unsigned long iova, - struct scatterlist *sg, unsigned int nents, int prot) -{ - return __iommu_map_sg(domain, iova, sg, nents, prot, GFP_ATOMIC); -} - /** * report_iommu_fault() - report about an IOMMU fault to the IOMMU framework * @domain: the iommu domain where the fault has happened @@ -2661,7 +2789,8 @@ int report_iommu_fault(struct iommu_domain *domain, struct device *dev, * if upper layers showed interest and installed a fault handler, * invoke it. */ - if (domain->handler) + if (domain->cookie_type == IOMMU_COOKIE_FAULT_HANDLER && + domain->handler) ret = domain->handler(domain, dev, iova, flags, domain->handler_token); @@ -2682,16 +2811,6 @@ static int __init iommu_init(void) } core_initcall(iommu_init); -int iommu_enable_nesting(struct iommu_domain *domain) -{ - if (domain->type != IOMMU_DOMAIN_UNMANAGED) - return -EINVAL; - if (!domain->ops->enable_nesting) - return -EINVAL; - return domain->ops->enable_nesting(domain); -} -EXPORT_SYMBOL_GPL(iommu_enable_nesting); - int iommu_set_pgtable_quirks(struct iommu_domain *domain, unsigned long quirk) { @@ -2703,48 +2822,51 @@ int iommu_set_pgtable_quirks(struct iommu_domain *domain, } EXPORT_SYMBOL_GPL(iommu_set_pgtable_quirks); +/** + * iommu_get_resv_regions - get reserved regions + * @dev: device for which to get reserved regions + * @list: reserved region list for device + * + * This returns a list of reserved IOVA regions specific to this device. + * A domain user should not map IOVA in these ranges. + */ void iommu_get_resv_regions(struct device *dev, struct list_head *list) { - const struct iommu_ops *ops = dev->bus->iommu_ops; + const struct iommu_ops *ops = dev_iommu_ops(dev); - if (ops && ops->get_resv_regions) + if (ops->get_resv_regions) ops->get_resv_regions(dev, list); } - -void iommu_put_resv_regions(struct device *dev, struct list_head *list) -{ - const struct iommu_ops *ops = dev->bus->iommu_ops; - - if (ops && ops->put_resv_regions) - ops->put_resv_regions(dev, list); -} +EXPORT_SYMBOL_GPL(iommu_get_resv_regions); /** - * generic_iommu_put_resv_regions - Reserved region driver helper + * iommu_put_resv_regions - release reserved regions * @dev: device for which to free reserved regions * @list: reserved region list for device * - * IOMMU drivers can use this to implement their .put_resv_regions() callback - * for simple reservations. Memory allocated for each reserved region will be - * freed. If an IOMMU driver allocates additional resources per region, it is - * going to have to implement a custom callback. + * This releases a reserved region list acquired by iommu_get_resv_regions(). */ -void generic_iommu_put_resv_regions(struct device *dev, struct list_head *list) +void iommu_put_resv_regions(struct device *dev, struct list_head *list) { struct iommu_resv_region *entry, *next; - list_for_each_entry_safe(entry, next, list, list) - kfree(entry); + list_for_each_entry_safe(entry, next, list, list) { + if (entry->free) + entry->free(dev, entry); + else + kfree(entry); + } } -EXPORT_SYMBOL(generic_iommu_put_resv_regions); +EXPORT_SYMBOL(iommu_put_resv_regions); struct iommu_resv_region *iommu_alloc_resv_region(phys_addr_t start, size_t length, int prot, - enum iommu_resv_type type) + enum iommu_resv_type type, + gfp_t gfp) { struct iommu_resv_region *region; - region = kzalloc(sizeof(*region), GFP_KERNEL); + region = kzalloc(sizeof(*region), gfp); if (!region) return NULL; @@ -2777,28 +2899,39 @@ bool iommu_default_passthrough(void) } EXPORT_SYMBOL_GPL(iommu_default_passthrough); -const struct iommu_ops *iommu_ops_from_fwnode(struct fwnode_handle *fwnode) +static const struct iommu_device *iommu_from_fwnode(const struct fwnode_handle *fwnode) { - const struct iommu_ops *ops = NULL; - struct iommu_device *iommu; + const struct iommu_device *iommu, *ret = NULL; spin_lock(&iommu_device_lock); list_for_each_entry(iommu, &iommu_device_list, list) if (iommu->fwnode == fwnode) { - ops = iommu->ops; + ret = iommu; break; } spin_unlock(&iommu_device_lock); - return ops; + return ret; +} + +const struct iommu_ops *iommu_ops_from_fwnode(const struct fwnode_handle *fwnode) +{ + const struct iommu_device *iommu = iommu_from_fwnode(fwnode); + + return iommu ? iommu->ops : NULL; } -int iommu_fwspec_init(struct device *dev, struct fwnode_handle *iommu_fwnode, - const struct iommu_ops *ops) +int iommu_fwspec_init(struct device *dev, struct fwnode_handle *iommu_fwnode) { + const struct iommu_device *iommu = iommu_from_fwnode(iommu_fwnode); struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev); + if (!iommu) + return driver_deferred_probe_check_state(dev); + if (!dev->iommu && !READ_ONCE(iommu->ready)) + return -EPROBE_DEFER; + if (fwspec) - return ops == fwspec->ops ? 0 : -EINVAL; + return iommu->ops == iommu_fwspec_ops(fwspec) ? 0 : -EINVAL; if (!dev_iommu_get(dev)) return -ENOMEM; @@ -2808,9 +2941,8 @@ int iommu_fwspec_init(struct device *dev, struct fwnode_handle *iommu_fwnode, if (!fwspec) return -ENOMEM; - of_node_get(to_of_node(iommu_fwnode)); + fwnode_handle_get(iommu_fwnode); fwspec->iommu_fwnode = iommu_fwnode; - fwspec->ops = ops; dev_iommu_fwspec_set(dev, fwspec); return 0; } @@ -2826,9 +2958,8 @@ void iommu_fwspec_free(struct device *dev) dev_iommu_fwspec_set(dev, NULL); } } -EXPORT_SYMBOL_GPL(iommu_fwspec_free); -int iommu_fwspec_add_ids(struct device *dev, u32 *ids, int num_ids) +int iommu_fwspec_add_ids(struct device *dev, const u32 *ids, int num_ids) { struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev); int i, new_num; @@ -2854,406 +2985,891 @@ int iommu_fwspec_add_ids(struct device *dev, u32 *ids, int num_ids) } EXPORT_SYMBOL_GPL(iommu_fwspec_add_ids); -/* - * Per device IOMMU features. +/** + * iommu_setup_default_domain - Set the default_domain for the group + * @group: Group to change + * @target_type: Domain type to set as the default_domain + * + * Allocate a default domain and set it as the current domain on the group. If + * the group already has a default domain it will be changed to the target_type. + * When target_type is 0 the default domain is selected based on driver and + * system preferences. */ -int iommu_dev_enable_feature(struct device *dev, enum iommu_dev_features feat) +static int iommu_setup_default_domain(struct iommu_group *group, + int target_type) { - if (dev->iommu && dev->iommu->iommu_dev) { - const struct iommu_ops *ops = dev->iommu->iommu_dev->ops; + struct iommu_domain *old_dom = group->default_domain; + struct group_device *gdev; + struct iommu_domain *dom; + bool direct_failed; + int req_type; + int ret; + + lockdep_assert_held(&group->mutex); + + req_type = iommu_get_default_domain_type(group, target_type); + if (req_type < 0) + return -EINVAL; + + dom = iommu_group_alloc_default_domain(group, req_type); + if (IS_ERR(dom)) + return PTR_ERR(dom); - if (ops->dev_enable_feat) - return ops->dev_enable_feat(dev, feat); + if (group->default_domain == dom) + return 0; + + if (iommu_is_dma_domain(dom)) { + ret = iommu_get_dma_cookie(dom); + if (ret) { + iommu_domain_free(dom); + return ret; + } } - return -ENODEV; + /* + * IOMMU_RESV_DIRECT and IOMMU_RESV_DIRECT_RELAXABLE regions must be + * mapped before their device is attached, in order to guarantee + * continuity with any FW activity + */ + direct_failed = false; + for_each_group_device(group, gdev) { + if (iommu_create_device_direct_mappings(dom, gdev->dev)) { + direct_failed = true; + dev_warn_once( + gdev->dev->iommu->iommu_dev->dev, + "IOMMU driver was not able to establish FW requested direct mapping."); + } + } + + /* We must set default_domain early for __iommu_device_set_domain */ + group->default_domain = dom; + if (!group->domain) { + /* + * Drivers are not allowed to fail the first domain attach. + * The only way to recover from this is to fail attaching the + * iommu driver and call ops->release_device. Put the domain + * in group->default_domain so it is freed after. + */ + ret = __iommu_group_set_domain_internal( + group, dom, IOMMU_SET_DOMAIN_MUST_SUCCEED); + if (WARN_ON(ret)) + goto out_free_old; + } else { + ret = __iommu_group_set_domain(group, dom); + if (ret) + goto err_restore_def_domain; + } + + /* + * Drivers are supposed to allow mappings to be installed in a domain + * before device attachment, but some don't. Hack around this defect by + * trying again after attaching. If this happens it means the device + * will not continuously have the IOMMU_RESV_DIRECT map. + */ + if (direct_failed) { + for_each_group_device(group, gdev) { + ret = iommu_create_device_direct_mappings(dom, gdev->dev); + if (ret) + goto err_restore_domain; + } + } + +out_free_old: + if (old_dom) + iommu_domain_free(old_dom); + return ret; + +err_restore_domain: + if (old_dom) + __iommu_group_set_domain_internal( + group, old_dom, IOMMU_SET_DOMAIN_MUST_SUCCEED); +err_restore_def_domain: + if (old_dom) { + iommu_domain_free(dom); + group->default_domain = old_dom; + } + return ret; } -EXPORT_SYMBOL_GPL(iommu_dev_enable_feature); /* - * The device drivers should do the necessary cleanups before calling this. - * For example, before disabling the aux-domain feature, the device driver - * should detach all aux-domains. Otherwise, this will return -EBUSY. + * Changing the default domain through sysfs requires the users to unbind the + * drivers from the devices in the iommu group, except for a DMA -> DMA-FQ + * transition. Return failure if this isn't met. + * + * We need to consider the race between this and the device release path. + * group->mutex is used here to guarantee that the device release path + * will not be entered at the same time. */ -int iommu_dev_disable_feature(struct device *dev, enum iommu_dev_features feat) +static ssize_t iommu_group_store_type(struct iommu_group *group, + const char *buf, size_t count) { - if (dev->iommu && dev->iommu->iommu_dev) { - const struct iommu_ops *ops = dev->iommu->iommu_dev->ops; + struct group_device *gdev; + int ret, req_type; + + if (!capable(CAP_SYS_ADMIN) || !capable(CAP_SYS_RAWIO)) + return -EACCES; + + if (WARN_ON(!group) || !group->default_domain) + return -EINVAL; - if (ops->dev_disable_feat) - return ops->dev_disable_feat(dev, feat); + if (sysfs_streq(buf, "identity")) + req_type = IOMMU_DOMAIN_IDENTITY; + else if (sysfs_streq(buf, "DMA")) + req_type = IOMMU_DOMAIN_DMA; + else if (sysfs_streq(buf, "DMA-FQ")) + req_type = IOMMU_DOMAIN_DMA_FQ; + else if (sysfs_streq(buf, "auto")) + req_type = 0; + else + return -EINVAL; + + mutex_lock(&group->mutex); + /* We can bring up a flush queue without tearing down the domain. */ + if (req_type == IOMMU_DOMAIN_DMA_FQ && + group->default_domain->type == IOMMU_DOMAIN_DMA) { + ret = iommu_dma_init_fq(group->default_domain); + if (ret) + goto out_unlock; + + group->default_domain->type = IOMMU_DOMAIN_DMA_FQ; + ret = count; + goto out_unlock; + } + + /* Otherwise, ensure that device exists and no driver is bound. */ + if (list_empty(&group->devices) || group->owner_cnt) { + ret = -EPERM; + goto out_unlock; } - return -EBUSY; + ret = iommu_setup_default_domain(group, req_type); + if (ret) + goto out_unlock; + + /* Make sure dma_ops is appropriatley set */ + for_each_group_device(group, gdev) + iommu_setup_dma_ops(gdev->dev); + +out_unlock: + mutex_unlock(&group->mutex); + return ret ?: count; } -EXPORT_SYMBOL_GPL(iommu_dev_disable_feature); -bool iommu_dev_feature_enabled(struct device *dev, enum iommu_dev_features feat) +/** + * iommu_device_use_default_domain() - Device driver wants to handle device + * DMA through the kernel DMA API. + * @dev: The device. + * + * The device driver about to bind @dev wants to do DMA through the kernel + * DMA API. Return 0 if it is allowed, otherwise an error. + */ +int iommu_device_use_default_domain(struct device *dev) { - if (dev->iommu && dev->iommu->iommu_dev) { - const struct iommu_ops *ops = dev->iommu->iommu_dev->ops; + /* Caller is the driver core during the pre-probe path */ + struct iommu_group *group = dev->iommu_group; + int ret = 0; - if (ops->dev_feat_enabled) - return ops->dev_feat_enabled(dev, feat); + if (!group) + return 0; + + mutex_lock(&group->mutex); + /* We may race against bus_iommu_probe() finalising groups here */ + if (!group->default_domain) { + ret = -EPROBE_DEFER; + goto unlock_out; + } + if (group->owner_cnt) { + if (group->domain != group->default_domain || group->owner || + !xa_empty(&group->pasid_array)) { + ret = -EBUSY; + goto unlock_out; + } } - return false; + group->owner_cnt++; + +unlock_out: + mutex_unlock(&group->mutex); + return ret; } -EXPORT_SYMBOL_GPL(iommu_dev_feature_enabled); -/* - * Aux-domain specific attach/detach. +/** + * iommu_device_unuse_default_domain() - Device driver stops handling device + * DMA through the kernel DMA API. + * @dev: The device. * - * Only works if iommu_dev_feature_enabled(dev, IOMMU_DEV_FEAT_AUX) returns - * true. Also, as long as domains are attached to a device through this - * interface, any tries to call iommu_attach_device() should fail - * (iommu_detach_device() can't fail, so we fail when trying to re-attach). - * This should make us safe against a device being attached to a guest as a - * whole while there are still pasid users on it (aux and sva). + * The device driver doesn't want to do DMA through kernel DMA API anymore. + * It must be called after iommu_device_use_default_domain(). */ -int iommu_aux_attach_device(struct iommu_domain *domain, struct device *dev) +void iommu_device_unuse_default_domain(struct device *dev) { - int ret = -ENODEV; + /* Caller is the driver core during the post-probe path */ + struct iommu_group *group = dev->iommu_group; - if (domain->ops->aux_attach_dev) - ret = domain->ops->aux_attach_dev(domain, dev); + if (!group) + return; - if (!ret) - trace_attach_device_to_domain(dev); + mutex_lock(&group->mutex); + if (!WARN_ON(!group->owner_cnt || !xa_empty(&group->pasid_array))) + group->owner_cnt--; - return ret; + mutex_unlock(&group->mutex); } -EXPORT_SYMBOL_GPL(iommu_aux_attach_device); -void iommu_aux_detach_device(struct iommu_domain *domain, struct device *dev) +static int __iommu_group_alloc_blocking_domain(struct iommu_group *group) { - if (domain->ops->aux_detach_dev) { - domain->ops->aux_detach_dev(domain, dev); - trace_detach_device_from_domain(dev); + struct device *dev = iommu_group_first_dev(group); + const struct iommu_ops *ops = dev_iommu_ops(dev); + struct iommu_domain *domain; + + if (group->blocking_domain) + return 0; + + if (ops->blocked_domain) { + group->blocking_domain = ops->blocked_domain; + return 0; } + + /* + * For drivers that do not yet understand IOMMU_DOMAIN_BLOCKED create an + * empty PAGING domain instead. + */ + domain = iommu_paging_domain_alloc(dev); + if (IS_ERR(domain)) + return PTR_ERR(domain); + group->blocking_domain = domain; + return 0; } -EXPORT_SYMBOL_GPL(iommu_aux_detach_device); -int iommu_aux_get_pasid(struct iommu_domain *domain, struct device *dev) +static int __iommu_take_dma_ownership(struct iommu_group *group, void *owner) { - int ret = -ENODEV; + int ret; - if (domain->ops->aux_get_pasid) - ret = domain->ops->aux_get_pasid(domain, dev); + if ((group->domain && group->domain != group->default_domain) || + !xa_empty(&group->pasid_array)) + return -EBUSY; - return ret; + ret = __iommu_group_alloc_blocking_domain(group); + if (ret) + return ret; + ret = __iommu_group_set_domain(group, group->blocking_domain); + if (ret) + return ret; + + group->owner = owner; + group->owner_cnt++; + return 0; } -EXPORT_SYMBOL_GPL(iommu_aux_get_pasid); /** - * iommu_sva_bind_device() - Bind a process address space to a device - * @dev: the device - * @mm: the mm to bind, caller must hold a reference to it + * iommu_group_claim_dma_owner() - Set DMA ownership of a group + * @group: The group. + * @owner: Caller specified pointer. Used for exclusive ownership. * - * Create a bond between device and address space, allowing the device to access - * the mm using the returned PASID. If a bond already exists between @device and - * @mm, it is returned and an additional reference is taken. Caller must call - * iommu_sva_unbind_device() to release each reference. - * - * iommu_dev_enable_feature(dev, IOMMU_DEV_FEAT_SVA) must be called first, to - * initialize the required SVA features. + * This is to support backward compatibility for vfio which manages the dma + * ownership in iommu_group level. New invocations on this interface should be + * prohibited. Only a single owner may exist for a group. + */ +int iommu_group_claim_dma_owner(struct iommu_group *group, void *owner) +{ + int ret = 0; + + if (WARN_ON(!owner)) + return -EINVAL; + + mutex_lock(&group->mutex); + if (group->owner_cnt) { + ret = -EPERM; + goto unlock_out; + } + + ret = __iommu_take_dma_ownership(group, owner); +unlock_out: + mutex_unlock(&group->mutex); + + return ret; +} +EXPORT_SYMBOL_GPL(iommu_group_claim_dma_owner); + +/** + * iommu_device_claim_dma_owner() - Set DMA ownership of a device + * @dev: The device. + * @owner: Caller specified pointer. Used for exclusive ownership. * - * On error, returns an ERR_PTR value. + * Claim the DMA ownership of a device. Multiple devices in the same group may + * concurrently claim ownership if they present the same owner value. Returns 0 + * on success and error code on failure */ -struct iommu_sva * -iommu_sva_bind_device(struct device *dev, struct mm_struct *mm, void *drvdata) +int iommu_device_claim_dma_owner(struct device *dev, void *owner) { - struct iommu_group *group; - struct iommu_sva *handle = ERR_PTR(-EINVAL); - const struct iommu_ops *ops = dev->bus->iommu_ops; + /* Caller must be a probed driver on dev */ + struct iommu_group *group = dev->iommu_group; + int ret = 0; - if (!ops || !ops->sva_bind) - return ERR_PTR(-ENODEV); + if (WARN_ON(!owner)) + return -EINVAL; - group = iommu_group_get(dev); if (!group) - return ERR_PTR(-ENODEV); + return -ENODEV; - /* Ensure device count and domain don't change while we're binding */ mutex_lock(&group->mutex); + if (group->owner_cnt) { + if (group->owner != owner) { + ret = -EPERM; + goto unlock_out; + } + group->owner_cnt++; + goto unlock_out; + } - /* - * To keep things simple, SVA currently doesn't support IOMMU groups - * with more than one device. Existing SVA-capable systems are not - * affected by the problems that required IOMMU groups (lack of ACS - * isolation, device ID aliasing and other hardware issues). - */ - if (iommu_group_device_count(group) != 1) - goto out_unlock; + ret = __iommu_take_dma_ownership(group, owner); +unlock_out: + mutex_unlock(&group->mutex); + return ret; +} +EXPORT_SYMBOL_GPL(iommu_device_claim_dma_owner); - handle = ops->sva_bind(dev, mm, drvdata); +static void __iommu_release_dma_ownership(struct iommu_group *group) +{ + if (WARN_ON(!group->owner_cnt || !group->owner || + !xa_empty(&group->pasid_array))) + return; -out_unlock: - mutex_unlock(&group->mutex); - iommu_group_put(group); + group->owner_cnt = 0; + group->owner = NULL; + __iommu_group_set_domain_nofail(group, group->default_domain); +} - return handle; +/** + * iommu_group_release_dma_owner() - Release DMA ownership of a group + * @group: The group + * + * Release the DMA ownership claimed by iommu_group_claim_dma_owner(). + */ +void iommu_group_release_dma_owner(struct iommu_group *group) +{ + mutex_lock(&group->mutex); + __iommu_release_dma_ownership(group); + mutex_unlock(&group->mutex); } -EXPORT_SYMBOL_GPL(iommu_sva_bind_device); +EXPORT_SYMBOL_GPL(iommu_group_release_dma_owner); /** - * iommu_sva_unbind_device() - Remove a bond created with iommu_sva_bind_device - * @handle: the handle returned by iommu_sva_bind_device() + * iommu_device_release_dma_owner() - Release DMA ownership of a device + * @dev: The device. * - * Put reference to a bond between device and address space. The device should - * not be issuing any more transaction for this PASID. All outstanding page - * requests for this PASID must have been flushed to the IOMMU. + * Release the DMA ownership claimed by iommu_device_claim_dma_owner(). */ -void iommu_sva_unbind_device(struct iommu_sva *handle) +void iommu_device_release_dma_owner(struct device *dev) { - struct iommu_group *group; - struct device *dev = handle->dev; - const struct iommu_ops *ops = dev->bus->iommu_ops; + /* Caller must be a probed driver on dev */ + struct iommu_group *group = dev->iommu_group; - if (!ops || !ops->sva_unbind) - return; + mutex_lock(&group->mutex); + if (group->owner_cnt > 1) + group->owner_cnt--; + else + __iommu_release_dma_ownership(group); + mutex_unlock(&group->mutex); +} +EXPORT_SYMBOL_GPL(iommu_device_release_dma_owner); - group = iommu_group_get(dev); - if (!group) - return; +/** + * iommu_group_dma_owner_claimed() - Query group dma ownership status + * @group: The group. + * + * This provides status query on a given group. It is racy and only for + * non-binding status reporting. + */ +bool iommu_group_dma_owner_claimed(struct iommu_group *group) +{ + unsigned int user; mutex_lock(&group->mutex); - ops->sva_unbind(handle); + user = group->owner_cnt; mutex_unlock(&group->mutex); - iommu_group_put(group); + return user; } -EXPORT_SYMBOL_GPL(iommu_sva_unbind_device); +EXPORT_SYMBOL_GPL(iommu_group_dma_owner_claimed); -u32 iommu_sva_get_pasid(struct iommu_sva *handle) +static void iommu_remove_dev_pasid(struct device *dev, ioasid_t pasid, + struct iommu_domain *domain) { - const struct iommu_ops *ops = handle->dev->bus->iommu_ops; + const struct iommu_ops *ops = dev_iommu_ops(dev); + struct iommu_domain *blocked_domain = ops->blocked_domain; - if (!ops || !ops->sva_get_pasid) - return IOMMU_PASID_INVALID; + WARN_ON(blocked_domain->ops->set_dev_pasid(blocked_domain, + dev, pasid, domain)); +} - return ops->sva_get_pasid(handle); +static int __iommu_set_group_pasid(struct iommu_domain *domain, + struct iommu_group *group, ioasid_t pasid, + struct iommu_domain *old) +{ + struct group_device *device, *last_gdev; + int ret; + + for_each_group_device(group, device) { + if (device->dev->iommu->max_pasids > 0) { + ret = domain->ops->set_dev_pasid(domain, device->dev, + pasid, old); + if (ret) + goto err_revert; + } + } + + return 0; + +err_revert: + last_gdev = device; + for_each_group_device(group, device) { + if (device == last_gdev) + break; + if (device->dev->iommu->max_pasids > 0) { + /* + * If no old domain, undo the succeeded devices/pasid. + * Otherwise, rollback the succeeded devices/pasid to + * the old domain. And it is a driver bug to fail + * attaching with a previously good domain. + */ + if (!old || + WARN_ON(old->ops->set_dev_pasid(old, device->dev, + pasid, domain))) + iommu_remove_dev_pasid(device->dev, pasid, domain); + } + } + return ret; +} + +static void __iommu_remove_group_pasid(struct iommu_group *group, + ioasid_t pasid, + struct iommu_domain *domain) +{ + struct group_device *device; + + for_each_group_device(group, device) { + if (device->dev->iommu->max_pasids > 0) + iommu_remove_dev_pasid(device->dev, pasid, domain); + } } -EXPORT_SYMBOL_GPL(iommu_sva_get_pasid); /* - * Changes the default domain of an iommu group that has *only* one device + * iommu_attach_device_pasid() - Attach a domain to pasid of device + * @domain: the iommu domain. + * @dev: the attached device. + * @pasid: the pasid of the device. + * @handle: the attach handle. * - * @group: The group for which the default domain should be changed - * @prev_dev: The device in the group (this is used to make sure that the device - * hasn't changed after the caller has called this function) - * @type: The type of the new default domain that gets associated with the group + * Caller should always provide a new handle to avoid race with the paths + * that have lockless reference to handle if it intends to pass a valid handle. * - * Returns 0 on success and error code on failure - * - * Note: - * 1. Presently, this function is called only when user requests to change the - * group's default domain type through /sys/kernel/iommu_groups/<grp_id>/type - * Please take a closer look if intended to use for other purposes. + * Return: 0 on success, or an error. */ -static int iommu_change_dev_def_domain(struct iommu_group *group, - struct device *prev_dev, int type) +int iommu_attach_device_pasid(struct iommu_domain *domain, + struct device *dev, ioasid_t pasid, + struct iommu_attach_handle *handle) { - struct iommu_domain *prev_dom; - struct group_device *grp_dev; - int ret, dev_def_dom; - struct device *dev; + /* Caller must be a probed driver on dev */ + struct iommu_group *group = dev->iommu_group; + struct group_device *device; + const struct iommu_ops *ops; + void *entry; + int ret; - mutex_lock(&group->mutex); + if (!group) + return -ENODEV; + + ops = dev_iommu_ops(dev); - if (group->default_domain != group->domain) { - dev_err_ratelimited(prev_dev, "Group not assigned to default domain\n"); - ret = -EBUSY; - goto out; + if (!domain->ops->set_dev_pasid || + !ops->blocked_domain || + !ops->blocked_domain->ops->set_dev_pasid) + return -EOPNOTSUPP; + + if (!domain_iommu_ops_compatible(ops, domain) || + pasid == IOMMU_NO_PASID) + return -EINVAL; + + mutex_lock(&group->mutex); + for_each_group_device(group, device) { + /* + * Skip PASID validation for devices without PASID support + * (max_pasids = 0). These devices cannot issue transactions + * with PASID, so they don't affect group's PASID usage. + */ + if ((device->dev->iommu->max_pasids > 0) && + (pasid >= device->dev->iommu->max_pasids)) { + ret = -EINVAL; + goto out_unlock; + } } + entry = iommu_make_pasid_array_entry(domain, handle); + /* - * iommu group wasn't locked while acquiring device lock in - * iommu_group_store_type(). So, make sure that the device count hasn't - * changed while acquiring device lock. - * - * Changing default domain of an iommu group with two or more devices - * isn't supported because there could be a potential deadlock. Consider - * the following scenario. T1 is trying to acquire device locks of all - * the devices in the group and before it could acquire all of them, - * there could be another thread T2 (from different sub-system and use - * case) that has already acquired some of the device locks and might be - * waiting for T1 to release other device locks. + * Entry present is a failure case. Use xa_insert() instead of + * xa_reserve(). */ - if (iommu_group_device_count(group) != 1) { - dev_err_ratelimited(prev_dev, "Cannot change default domain: Group has more than one device\n"); - ret = -EINVAL; - goto out; + ret = xa_insert(&group->pasid_array, pasid, XA_ZERO_ENTRY, GFP_KERNEL); + if (ret) + goto out_unlock; + + ret = __iommu_set_group_pasid(domain, group, pasid, NULL); + if (ret) { + xa_release(&group->pasid_array, pasid); + goto out_unlock; } - /* Since group has only one device */ - grp_dev = list_first_entry(&group->devices, struct group_device, list); - dev = grp_dev->dev; + /* + * The xa_insert() above reserved the memory, and the group->mutex is + * held, this cannot fail. The new domain cannot be visible until the + * operation succeeds as we cannot tolerate PRIs becoming concurrently + * queued and then failing attach. + */ + WARN_ON(xa_is_err(xa_store(&group->pasid_array, + pasid, entry, GFP_KERNEL))); + +out_unlock: + mutex_unlock(&group->mutex); + return ret; +} +EXPORT_SYMBOL_GPL(iommu_attach_device_pasid); + +/** + * iommu_replace_device_pasid - Replace the domain that a specific pasid + * of the device is attached to + * @domain: the new iommu domain + * @dev: the attached device. + * @pasid: the pasid of the device. + * @handle: the attach handle. + * + * This API allows the pasid to switch domains. The @pasid should have been + * attached. Otherwise, this fails. The pasid will keep the old configuration + * if replacement failed. + * + * Caller should always provide a new handle to avoid race with the paths + * that have lockless reference to handle if it intends to pass a valid handle. + * + * Return 0 on success, or an error. + */ +int iommu_replace_device_pasid(struct iommu_domain *domain, + struct device *dev, ioasid_t pasid, + struct iommu_attach_handle *handle) +{ + /* Caller must be a probed driver on dev */ + struct iommu_group *group = dev->iommu_group; + struct iommu_attach_handle *entry; + struct iommu_domain *curr_domain; + void *curr; + int ret; + + if (!group) + return -ENODEV; + + if (!domain->ops->set_dev_pasid) + return -EOPNOTSUPP; - if (prev_dev != dev) { - dev_err_ratelimited(prev_dev, "Cannot change default domain: Device has been changed\n"); - ret = -EBUSY; - goto out; + if (!domain_iommu_ops_compatible(dev_iommu_ops(dev), domain) || + pasid == IOMMU_NO_PASID || !handle) + return -EINVAL; + + mutex_lock(&group->mutex); + entry = iommu_make_pasid_array_entry(domain, handle); + curr = xa_cmpxchg(&group->pasid_array, pasid, NULL, + XA_ZERO_ENTRY, GFP_KERNEL); + if (xa_is_err(curr)) { + ret = xa_err(curr); + goto out_unlock; } - prev_dom = group->default_domain; - if (!prev_dom) { + /* + * No domain (with or without handle) attached, hence not + * a replace case. + */ + if (!curr) { + xa_release(&group->pasid_array, pasid); ret = -EINVAL; - goto out; + goto out_unlock; } - dev_def_dom = iommu_get_def_domain_type(dev); - if (!type) { - /* - * If the user hasn't requested any specific type of domain and - * if the device supports both the domains, then default to the - * domain the device was booted with - */ - type = dev_def_dom ? : iommu_def_domain_type; - } else if (dev_def_dom && type != dev_def_dom) { - dev_err_ratelimited(prev_dev, "Device cannot be in %s domain\n", - iommu_domain_type_str(type)); + /* + * Reusing handle is problematic as there are paths that refers + * the handle without lock. To avoid race, reject the callers that + * attempt it. + */ + if (curr == entry) { + WARN_ON(1); ret = -EINVAL; - goto out; + goto out_unlock; + } + + curr_domain = pasid_array_entry_to_domain(curr); + ret = 0; + + if (curr_domain != domain) { + ret = __iommu_set_group_pasid(domain, group, + pasid, curr_domain); + if (ret) + goto out_unlock; } /* - * Switch to a new domain only if the requested domain type is different - * from the existing default domain type + * The above xa_cmpxchg() reserved the memory, and the + * group->mutex is held, this cannot fail. */ - if (prev_dom->type == type) { - ret = 0; - goto out; - } + WARN_ON(xa_is_err(xa_store(&group->pasid_array, + pasid, entry, GFP_KERNEL))); - /* Sets group->default_domain to the newly allocated domain */ - ret = iommu_group_alloc_default_domain(dev->bus, group, type); - if (ret) - goto out; +out_unlock: + mutex_unlock(&group->mutex); + return ret; +} +EXPORT_SYMBOL_NS_GPL(iommu_replace_device_pasid, "IOMMUFD_INTERNAL"); - ret = iommu_create_device_direct_mappings(group, dev); - if (ret) - goto free_new_domain; +/* + * iommu_detach_device_pasid() - Detach the domain from pasid of device + * @domain: the iommu domain. + * @dev: the attached device. + * @pasid: the pasid of the device. + * + * The @domain must have been attached to @pasid of the @dev with + * iommu_attach_device_pasid(). + */ +void iommu_detach_device_pasid(struct iommu_domain *domain, struct device *dev, + ioasid_t pasid) +{ + /* Caller must be a probed driver on dev */ + struct iommu_group *group = dev->iommu_group; - ret = __iommu_attach_device(group->default_domain, dev); - if (ret) - goto free_new_domain; + mutex_lock(&group->mutex); + __iommu_remove_group_pasid(group, pasid, domain); + xa_erase(&group->pasid_array, pasid); + mutex_unlock(&group->mutex); +} +EXPORT_SYMBOL_GPL(iommu_detach_device_pasid); + +ioasid_t iommu_alloc_global_pasid(struct device *dev) +{ + int ret; - group->domain = group->default_domain; + /* max_pasids == 0 means that the device does not support PASID */ + if (!dev->iommu->max_pasids) + return IOMMU_PASID_INVALID; /* - * Release the mutex here because ops->probe_finalize() call-back of - * some vendor IOMMU drivers calls arm_iommu_attach_device() which - * in-turn might call back into IOMMU core code, where it tries to take - * group->mutex, resulting in a deadlock. + * max_pasids is set up by vendor driver based on number of PASID bits + * supported but the IDA allocation is inclusive. */ - mutex_unlock(&group->mutex); + ret = ida_alloc_range(&iommu_global_pasid_ida, IOMMU_FIRST_GLOBAL_PASID, + dev->iommu->max_pasids - 1, GFP_KERNEL); + return ret < 0 ? IOMMU_PASID_INVALID : ret; +} +EXPORT_SYMBOL_GPL(iommu_alloc_global_pasid); - /* Make sure dma_ops is appropriatley set */ - iommu_group_do_probe_finalize(dev, group->default_domain); - iommu_domain_free(prev_dom); - return 0; +void iommu_free_global_pasid(ioasid_t pasid) +{ + if (WARN_ON(pasid == IOMMU_PASID_INVALID)) + return; -free_new_domain: - iommu_domain_free(group->default_domain); - group->default_domain = prev_dom; - group->domain = prev_dom; + ida_free(&iommu_global_pasid_ida, pasid); +} +EXPORT_SYMBOL_GPL(iommu_free_global_pasid); -out: - mutex_unlock(&group->mutex); +/** + * iommu_attach_handle_get - Return the attach handle + * @group: the iommu group that domain was attached to + * @pasid: the pasid within the group + * @type: matched domain type, 0 for any match + * + * Return handle or ERR_PTR(-ENOENT) on none, ERR_PTR(-EBUSY) on mismatch. + * + * Return the attach handle to the caller. The life cycle of an iommu attach + * handle is from the time when the domain is attached to the time when the + * domain is detached. Callers are required to synchronize the call of + * iommu_attach_handle_get() with domain attachment and detachment. The attach + * handle can only be used during its life cycle. + */ +struct iommu_attach_handle * +iommu_attach_handle_get(struct iommu_group *group, ioasid_t pasid, unsigned int type) +{ + struct iommu_attach_handle *handle; + void *entry; - return ret; + xa_lock(&group->pasid_array); + entry = xa_load(&group->pasid_array, pasid); + if (!entry || xa_pointer_tag(entry) != IOMMU_PASID_ARRAY_HANDLE) { + handle = ERR_PTR(-ENOENT); + } else { + handle = xa_untag_pointer(entry); + if (type && handle->domain->type != type) + handle = ERR_PTR(-EBUSY); + } + xa_unlock(&group->pasid_array); + + return handle; } +EXPORT_SYMBOL_NS_GPL(iommu_attach_handle_get, "IOMMUFD_INTERNAL"); -/* - * Changing the default domain through sysfs requires the users to ubind the - * drivers from the devices in the iommu group. Return failure if this doesn't - * meet. +/** + * iommu_attach_group_handle - Attach an IOMMU domain to an IOMMU group + * @domain: IOMMU domain to attach + * @group: IOMMU group that will be attached + * @handle: attach handle * - * We need to consider the race between this and the device release path. - * device_lock(dev) is used here to guarantee that the device release path - * will not be entered at the same time. + * Returns 0 on success and error code on failure. + * + * This is a variant of iommu_attach_group(). It allows the caller to provide + * an attach handle and use it when the domain is attached. This is currently + * used by IOMMUFD to deliver the I/O page faults. + * + * Caller should always provide a new handle to avoid race with the paths + * that have lockless reference to handle. */ -static ssize_t iommu_group_store_type(struct iommu_group *group, - const char *buf, size_t count) +int iommu_attach_group_handle(struct iommu_domain *domain, + struct iommu_group *group, + struct iommu_attach_handle *handle) { - struct group_device *grp_dev; - struct device *dev; - int ret, req_type; - - if (!capable(CAP_SYS_ADMIN) || !capable(CAP_SYS_RAWIO)) - return -EACCES; + void *entry; + int ret; - if (WARN_ON(!group)) + if (!handle) return -EINVAL; - if (sysfs_streq(buf, "identity")) - req_type = IOMMU_DOMAIN_IDENTITY; - else if (sysfs_streq(buf, "DMA")) - req_type = IOMMU_DOMAIN_DMA; - else if (sysfs_streq(buf, "auto")) - req_type = 0; - else - return -EINVAL; + mutex_lock(&group->mutex); + entry = iommu_make_pasid_array_entry(domain, handle); + ret = xa_insert(&group->pasid_array, + IOMMU_NO_PASID, XA_ZERO_ENTRY, GFP_KERNEL); + if (ret) + goto out_unlock; + + ret = __iommu_attach_group(domain, group); + if (ret) { + xa_release(&group->pasid_array, IOMMU_NO_PASID); + goto out_unlock; + } /* - * Lock/Unlock the group mutex here before device lock to - * 1. Make sure that the iommu group has only one device (this is a - * prerequisite for step 2) - * 2. Get struct *dev which is needed to lock device + * The xa_insert() above reserved the memory, and the group->mutex is + * held, this cannot fail. The new domain cannot be visible until the + * operation succeeds as we cannot tolerate PRIs becoming concurrently + * queued and then failing attach. */ + WARN_ON(xa_is_err(xa_store(&group->pasid_array, + IOMMU_NO_PASID, entry, GFP_KERNEL))); + +out_unlock: + mutex_unlock(&group->mutex); + return ret; +} +EXPORT_SYMBOL_NS_GPL(iommu_attach_group_handle, "IOMMUFD_INTERNAL"); + +/** + * iommu_detach_group_handle - Detach an IOMMU domain from an IOMMU group + * @domain: IOMMU domain to attach + * @group: IOMMU group that will be attached + * + * Detach the specified IOMMU domain from the specified IOMMU group. + * It must be used in conjunction with iommu_attach_group_handle(). + */ +void iommu_detach_group_handle(struct iommu_domain *domain, + struct iommu_group *group) +{ mutex_lock(&group->mutex); - if (iommu_group_device_count(group) != 1) { - mutex_unlock(&group->mutex); - pr_err_ratelimited("Cannot change default domain: Group has more than one device\n"); + __iommu_group_set_core_domain(group); + xa_erase(&group->pasid_array, IOMMU_NO_PASID); + mutex_unlock(&group->mutex); +} +EXPORT_SYMBOL_NS_GPL(iommu_detach_group_handle, "IOMMUFD_INTERNAL"); + +/** + * iommu_replace_group_handle - replace the domain that a group is attached to + * @group: IOMMU group that will be attached to the new domain + * @new_domain: new IOMMU domain to replace with + * @handle: attach handle + * + * This API allows the group to switch domains without being forced to go to + * the blocking domain in-between. It allows the caller to provide an attach + * handle for the new domain and use it when the domain is attached. + * + * If the currently attached domain is a core domain (e.g. a default_domain), + * it will act just like the iommu_attach_group_handle(). + * + * Caller should always provide a new handle to avoid race with the paths + * that have lockless reference to handle. + */ +int iommu_replace_group_handle(struct iommu_group *group, + struct iommu_domain *new_domain, + struct iommu_attach_handle *handle) +{ + void *curr, *entry; + int ret; + + if (!new_domain || !handle) return -EINVAL; - } - /* Since group has only one device */ - grp_dev = list_first_entry(&group->devices, struct group_device, list); - dev = grp_dev->dev; - get_device(dev); + mutex_lock(&group->mutex); + entry = iommu_make_pasid_array_entry(new_domain, handle); + ret = xa_reserve(&group->pasid_array, IOMMU_NO_PASID, GFP_KERNEL); + if (ret) + goto err_unlock; + + ret = __iommu_group_set_domain(group, new_domain); + if (ret) + goto err_release; + + curr = xa_store(&group->pasid_array, IOMMU_NO_PASID, entry, GFP_KERNEL); + WARN_ON(xa_is_err(curr)); - /* - * Don't hold the group mutex because taking group mutex first and then - * the device lock could potentially cause a deadlock as below. Assume - * two threads T1 and T2. T1 is trying to change default domain of an - * iommu group and T2 is trying to hot unplug a device or release [1] VF - * of a PCIe device which is in the same iommu group. T1 takes group - * mutex and before it could take device lock assume T2 has taken device - * lock and is yet to take group mutex. Now, both the threads will be - * waiting for the other thread to release lock. Below, lock order was - * suggested. - * device_lock(dev); - * mutex_lock(&group->mutex); - * iommu_change_dev_def_domain(); - * mutex_unlock(&group->mutex); - * device_unlock(dev); - * - * [1] Typical device release path - * device_lock() from device/driver core code - * -> bus_notifier() - * -> iommu_bus_notifier() - * -> iommu_release_device() - * -> ops->release_device() vendor driver calls back iommu core code - * -> mutex_lock() from iommu core code - */ mutex_unlock(&group->mutex); - /* Check if the device in the group still has a driver bound to it */ - device_lock(dev); - if (device_is_bound(dev)) { - pr_err_ratelimited("Device is still bound to driver\n"); - ret = -EBUSY; - goto out; - } + return 0; +err_release: + xa_release(&group->pasid_array, IOMMU_NO_PASID); +err_unlock: + mutex_unlock(&group->mutex); + return ret; +} +EXPORT_SYMBOL_NS_GPL(iommu_replace_group_handle, "IOMMUFD_INTERNAL"); - ret = iommu_change_dev_def_domain(group, dev, req_type); - ret = ret ?: count; +#if IS_ENABLED(CONFIG_IRQ_MSI_IOMMU) +/** + * iommu_dma_prepare_msi() - Map the MSI page in the IOMMU domain + * @desc: MSI descriptor, will store the MSI page + * @msi_addr: MSI target address to be mapped + * + * The implementation of sw_msi() should take msi_addr and map it to + * an IOVA in the domain and call msi_desc_set_iommu_msi_iova() with the + * mapping information. + * + * Return: 0 on success or negative error code if the mapping failed. + */ +int iommu_dma_prepare_msi(struct msi_desc *desc, phys_addr_t msi_addr) +{ + struct device *dev = msi_desc_to_dev(desc); + struct iommu_group *group = dev->iommu_group; + int ret = 0; -out: - device_unlock(dev); - put_device(dev); + if (!group) + return 0; + mutex_lock(&group->mutex); + /* An IDENTITY domain must pass through */ + if (group->domain && group->domain->type != IOMMU_DOMAIN_IDENTITY) { + switch (group->domain->cookie_type) { + case IOMMU_COOKIE_DMA_MSI: + case IOMMU_COOKIE_DMA_IOVA: + ret = iommu_dma_sw_msi(group->domain, desc, msi_addr); + break; + case IOMMU_COOKIE_IOMMUFD: + ret = iommufd_sw_msi(group->domain, desc, msi_addr); + break; + default: + ret = -EOPNOTSUPP; + break; + } + } + mutex_unlock(&group->mutex); return ret; } +#endif /* CONFIG_IRQ_MSI_IOMMU */ |