From 00208852d351ca6e4a8b9ff0c5376fa3a8ed8eaa Mon Sep 17 00:00:00 2001 From: Nicolin Chen Date: Mon, 17 Oct 2022 16:01:22 -0700 Subject: iommu: Add return value rules to attach_dev op and APIs Cases like VFIO wish to attach a device to an existing domain that was not allocated specifically from the device. This raises a condition where the IOMMU driver can fail the domain attach because the domain and device are incompatible with each other. This is a soft failure that can be resolved by using a different domain. Provide a dedicated errno EINVAL from the IOMMU driver during attach that the reason why the attach failed is because of domain incompatibility. VFIO can use this to know that the attach is a soft failure and it should continue searching. Otherwise, the attach will be a hard failure and VFIO will return the code to userspace. Update kdocs to add rules of return value to the attach_dev op and APIs. Link: https://lore.kernel.org/r/bd56d93c18621104a0fa1b0de31e9b760b81b769.1666042872.git.nicolinc@nvidia.com Suggested-by: Jason Gunthorpe Reviewed-by: Kevin Tian Reviewed-by: Jason Gunthorpe Signed-off-by: Nicolin Chen Reviewed-by: Lu Baolu Signed-off-by: Jason Gunthorpe --- drivers/iommu/iommu.c | 24 ++++++++++++++++++++++++ 1 file changed, 24 insertions(+) (limited to 'drivers/iommu/iommu.c') diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c index 65a3b3d886dc..972731f0b328 100644 --- a/drivers/iommu/iommu.c +++ b/drivers/iommu/iommu.c @@ -1949,6 +1949,18 @@ static int __iommu_attach_device(struct iommu_domain *domain, return ret; } +/** + * 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; @@ -2075,6 +2087,18 @@ static int __iommu_attach_group(struct iommu_domain *domain, return ret; } +/** + * 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; -- cgit v1.2.3 From 22d2c7afb3697a68c7fc05c935ef662dee06dc60 Mon Sep 17 00:00:00 2001 From: Lu Baolu Date: Mon, 31 Oct 2022 08:59:06 +0800 Subject: iommu: Add max_pasids field in struct dev_iommu Use this field to save the number of PASIDs that a device is able to consume. It is a generic attribute of a device and lifting it into the per-device dev_iommu struct could help to avoid the boilerplate code in various IOMMU drivers. Signed-off-by: Lu Baolu Reviewed-by: Kevin Tian Reviewed-by: Jason Gunthorpe Reviewed-by: Yi Liu Tested-by: Zhangfei Gao Tested-by: Tony Zhu Link: https://lore.kernel.org/r/20221031005917.45690-3-baolu.lu@linux.intel.com Signed-off-by: Joerg Roedel --- drivers/iommu/iommu.c | 20 ++++++++++++++++++++ include/linux/iommu.h | 2 ++ 2 files changed, 22 insertions(+) (limited to 'drivers/iommu/iommu.c') diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c index 65a3b3d886dc..297ac79bc21c 100644 --- a/drivers/iommu/iommu.c +++ b/drivers/iommu/iommu.c @@ -21,6 +21,7 @@ #include #include #include +#include #include #include #include @@ -278,6 +279,24 @@ static void dev_iommu_free(struct device *dev) kfree(param); } +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); +} + static int __iommu_probe_device(struct device *dev, struct list_head *group_list) { const struct iommu_ops *ops = dev->bus->iommu_ops; @@ -303,6 +322,7 @@ static int __iommu_probe_device(struct device *dev, struct list_head *group_list } dev->iommu->iommu_dev = iommu_dev; + dev->iommu->max_pasids = dev_iommu_get_max_pasids(dev); group = iommu_group_get_for_dev(dev); if (IS_ERR(group)) { diff --git a/include/linux/iommu.h b/include/linux/iommu.h index e3af4f46e6e0..ac3f6c6dcc6d 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -368,6 +368,7 @@ struct iommu_fault_param { * @fwspec: IOMMU fwspec data * @iommu_dev: IOMMU device this device is linked to * @priv: IOMMU Driver private data + * @max_pasids: number of PASIDs this device can consume * * TODO: migrate other per device data pointers under iommu_dev_data, e.g. * struct iommu_group *iommu_group; @@ -379,6 +380,7 @@ struct dev_iommu { struct iommu_fwspec *fwspec; struct iommu_device *iommu_dev; void *priv; + u32 max_pasids; }; int iommu_device_register(struct iommu_device *iommu, -- cgit v1.2.3 From 942fd5435dccb273f90176b046ae6bbba60cfbd8 Mon Sep 17 00:00:00 2001 From: Lu Baolu Date: Mon, 31 Oct 2022 08:59:07 +0800 Subject: iommu: Remove SVM_FLAG_SUPERVISOR_MODE support The current kernel DMA with PASID support is based on the SVA with a flag SVM_FLAG_SUPERVISOR_MODE. The IOMMU driver binds the kernel memory address space to a PASID of the device. The device driver programs the device with kernel virtual address (KVA) for DMA access. There have been security and functional issues with this approach: - The lack of IOTLB synchronization upon kernel page table updates. (vmalloc, module/BPF loading, CONFIG_DEBUG_PAGEALLOC etc.) - Other than slight more protection, using kernel virtual address (KVA) has little advantage over physical address. There are also no use cases yet where DMA engines need kernel virtual addresses for in-kernel DMA. This removes SVM_FLAG_SUPERVISOR_MODE support from the IOMMU interface. The device drivers are suggested to handle kernel DMA with PASID through the kernel DMA APIs. The drvdata parameter in iommu_sva_bind_device() and all callbacks is not needed anymore. Cleanup them as well. Link: https://lore.kernel.org/linux-iommu/20210511194726.GP1002214@nvidia.com/ Signed-off-by: Jacob Pan Signed-off-by: Lu Baolu Reviewed-by: Jason Gunthorpe Reviewed-by: Jean-Philippe Brucker Reviewed-by: Kevin Tian Reviewed-by: Fenghua Yu Tested-by: Zhangfei Gao Tested-by: Tony Zhu Link: https://lore.kernel.org/r/20221031005917.45690-4-baolu.lu@linux.intel.com Signed-off-by: Joerg Roedel --- drivers/dma/idxd/cdev.c | 3 +- drivers/dma/idxd/init.c | 25 +---------- drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c | 3 +- drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h | 5 +-- drivers/iommu/intel/iommu.h | 3 +- drivers/iommu/intel/svm.c | 55 ++++++------------------- drivers/iommu/iommu.c | 5 +-- drivers/misc/uacce/uacce.c | 2 +- include/linux/intel-svm.h | 13 ------ include/linux/iommu.h | 8 ++-- 10 files changed, 25 insertions(+), 97 deletions(-) (limited to 'drivers/iommu/iommu.c') diff --git a/drivers/dma/idxd/cdev.c b/drivers/dma/idxd/cdev.c index c2808fd081d6..66720001ba1c 100644 --- a/drivers/dma/idxd/cdev.c +++ b/drivers/dma/idxd/cdev.c @@ -6,7 +6,6 @@ #include #include #include -#include #include #include #include @@ -100,7 +99,7 @@ static int idxd_cdev_open(struct inode *inode, struct file *filp) filp->private_data = ctx; if (device_user_pasid_enabled(idxd)) { - sva = iommu_sva_bind_device(dev, current->mm, NULL); + sva = iommu_sva_bind_device(dev, current->mm); if (IS_ERR(sva)) { rc = PTR_ERR(sva); dev_err(dev, "pasid allocation failed: %d\n", rc); diff --git a/drivers/dma/idxd/init.c b/drivers/dma/idxd/init.c index 2b18d512cbfc..2c0fcfdc75c7 100644 --- a/drivers/dma/idxd/init.c +++ b/drivers/dma/idxd/init.c @@ -14,7 +14,6 @@ #include #include #include -#include #include #include #include @@ -502,29 +501,7 @@ static struct idxd_device *idxd_alloc(struct pci_dev *pdev, struct idxd_driver_d static int idxd_enable_system_pasid(struct idxd_device *idxd) { - int flags; - unsigned int pasid; - struct iommu_sva *sva; - - flags = SVM_FLAG_SUPERVISOR_MODE; - - sva = iommu_sva_bind_device(&idxd->pdev->dev, NULL, &flags); - if (IS_ERR(sva)) { - dev_warn(&idxd->pdev->dev, - "iommu sva bind failed: %ld\n", PTR_ERR(sva)); - return PTR_ERR(sva); - } - - pasid = iommu_sva_get_pasid(sva); - if (pasid == IOMMU_PASID_INVALID) { - iommu_sva_unbind_device(sva); - return -ENODEV; - } - - idxd->sva = sva; - idxd->pasid = pasid; - dev_dbg(&idxd->pdev->dev, "system pasid: %u\n", pasid); - return 0; + return -EOPNOTSUPP; } static void idxd_disable_system_pasid(struct idxd_device *idxd) diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c index 5968a568aae2..8fcf0df4bd0e 100644 --- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c +++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c @@ -367,8 +367,7 @@ err_free_bond: return ERR_PTR(ret); } -struct iommu_sva * -arm_smmu_sva_bind(struct device *dev, struct mm_struct *mm, void *drvdata) +struct iommu_sva *arm_smmu_sva_bind(struct device *dev, struct mm_struct *mm) { struct iommu_sva *handle; struct iommu_domain *domain = iommu_get_domain_for_dev(dev); diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h index cd48590ada30..d2ba86470c42 100644 --- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h +++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h @@ -754,8 +754,7 @@ bool arm_smmu_master_sva_enabled(struct arm_smmu_master *master); int arm_smmu_master_enable_sva(struct arm_smmu_master *master); int arm_smmu_master_disable_sva(struct arm_smmu_master *master); bool arm_smmu_master_iopf_supported(struct arm_smmu_master *master); -struct iommu_sva *arm_smmu_sva_bind(struct device *dev, struct mm_struct *mm, - void *drvdata); +struct iommu_sva *arm_smmu_sva_bind(struct device *dev, struct mm_struct *mm); void arm_smmu_sva_unbind(struct iommu_sva *handle); u32 arm_smmu_sva_get_pasid(struct iommu_sva *handle); void arm_smmu_sva_notifier_synchronize(void); @@ -791,7 +790,7 @@ static inline bool arm_smmu_master_iopf_supported(struct arm_smmu_master *master } static inline struct iommu_sva * -arm_smmu_sva_bind(struct device *dev, struct mm_struct *mm, void *drvdata) +arm_smmu_sva_bind(struct device *dev, struct mm_struct *mm) { return ERR_PTR(-ENODEV); } diff --git a/drivers/iommu/intel/iommu.h b/drivers/iommu/intel/iommu.h index cce0598f4109..33e5bcaf2a6c 100644 --- a/drivers/iommu/intel/iommu.h +++ b/drivers/iommu/intel/iommu.h @@ -748,8 +748,7 @@ struct intel_iommu *device_to_iommu(struct device *dev, u8 *bus, u8 *devfn); extern void intel_svm_check(struct intel_iommu *iommu); extern int intel_svm_enable_prq(struct intel_iommu *iommu); extern int intel_svm_finish_prq(struct intel_iommu *iommu); -struct iommu_sva *intel_svm_bind(struct device *dev, struct mm_struct *mm, - void *drvdata); +struct iommu_sva *intel_svm_bind(struct device *dev, struct mm_struct *mm); void intel_svm_unbind(struct iommu_sva *handle); u32 intel_svm_get_pasid(struct iommu_sva *handle); int intel_svm_page_response(struct device *dev, struct iommu_fault_event *evt, diff --git a/drivers/iommu/intel/svm.c b/drivers/iommu/intel/svm.c index 7d08eb034f2d..94bc47b68c93 100644 --- a/drivers/iommu/intel/svm.c +++ b/drivers/iommu/intel/svm.c @@ -296,8 +296,7 @@ out: return 0; } -static int intel_svm_alloc_pasid(struct device *dev, struct mm_struct *mm, - unsigned int flags) +static int intel_svm_alloc_pasid(struct device *dev, struct mm_struct *mm) { ioasid_t max_pasid = dev_is_pci(dev) ? pci_max_pasids(to_pci_dev(dev)) : intel_pasid_max_id; @@ -307,8 +306,7 @@ static int intel_svm_alloc_pasid(struct device *dev, struct mm_struct *mm, static struct iommu_sva *intel_svm_bind_mm(struct intel_iommu *iommu, struct device *dev, - struct mm_struct *mm, - unsigned int flags) + struct mm_struct *mm) { struct device_domain_info *info = dev_iommu_priv_get(dev); struct intel_svm_dev *sdev; @@ -324,22 +322,18 @@ static struct iommu_sva *intel_svm_bind_mm(struct intel_iommu *iommu, svm->pasid = mm->pasid; svm->mm = mm; - svm->flags = flags; INIT_LIST_HEAD_RCU(&svm->devs); - if (!(flags & SVM_FLAG_SUPERVISOR_MODE)) { - svm->notifier.ops = &intel_mmuops; - ret = mmu_notifier_register(&svm->notifier, mm); - if (ret) { - kfree(svm); - return ERR_PTR(ret); - } + svm->notifier.ops = &intel_mmuops; + ret = mmu_notifier_register(&svm->notifier, mm); + if (ret) { + kfree(svm); + return ERR_PTR(ret); } ret = pasid_private_add(svm->pasid, svm); if (ret) { - if (svm->notifier.ops) - mmu_notifier_unregister(&svm->notifier, mm); + mmu_notifier_unregister(&svm->notifier, mm); kfree(svm); return ERR_PTR(ret); } @@ -374,9 +368,7 @@ static struct iommu_sva *intel_svm_bind_mm(struct intel_iommu *iommu, } /* Setup the pasid table: */ - sflags = (flags & SVM_FLAG_SUPERVISOR_MODE) ? - PASID_FLAG_SUPERVISOR_MODE : 0; - sflags |= cpu_feature_enabled(X86_FEATURE_LA57) ? PASID_FLAG_FL5LP : 0; + sflags = cpu_feature_enabled(X86_FEATURE_LA57) ? PASID_FLAG_FL5LP : 0; ret = intel_pasid_setup_first_level(iommu, dev, mm->pgd, mm->pasid, FLPT_DEFAULT_DID, sflags); if (ret) @@ -390,8 +382,7 @@ free_sdev: kfree(sdev); free_svm: if (list_empty(&svm->devs)) { - if (svm->notifier.ops) - mmu_notifier_unregister(&svm->notifier, mm); + mmu_notifier_unregister(&svm->notifier, mm); pasid_private_remove(mm->pasid); kfree(svm); } @@ -780,40 +771,20 @@ prq_advance: return IRQ_RETVAL(handled); } -struct iommu_sva *intel_svm_bind(struct device *dev, struct mm_struct *mm, void *drvdata) +struct iommu_sva *intel_svm_bind(struct device *dev, struct mm_struct *mm) { struct intel_iommu *iommu = device_to_iommu(dev, NULL, NULL); - unsigned int flags = 0; struct iommu_sva *sva; int ret; - if (drvdata) - flags = *(unsigned int *)drvdata; - - if (flags & SVM_FLAG_SUPERVISOR_MODE) { - if (!ecap_srs(iommu->ecap)) { - dev_err(dev, "%s: Supervisor PASID not supported\n", - iommu->name); - return ERR_PTR(-EOPNOTSUPP); - } - - if (mm) { - dev_err(dev, "%s: Supervisor PASID with user provided mm\n", - iommu->name); - return ERR_PTR(-EINVAL); - } - - mm = &init_mm; - } - mutex_lock(&pasid_mutex); - ret = intel_svm_alloc_pasid(dev, mm, flags); + ret = intel_svm_alloc_pasid(dev, mm); if (ret) { mutex_unlock(&pasid_mutex); return ERR_PTR(ret); } - sva = intel_svm_bind_mm(iommu, dev, mm, flags); + sva = intel_svm_bind_mm(iommu, dev, mm); mutex_unlock(&pasid_mutex); return sva; diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c index 297ac79bc21c..a94ec648c88b 100644 --- a/drivers/iommu/iommu.c +++ b/drivers/iommu/iommu.c @@ -2750,7 +2750,6 @@ EXPORT_SYMBOL_GPL(iommu_dev_disable_feature); * 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 - * @drvdata: opaque data pointer to pass to bind callback * * 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 @@ -2763,7 +2762,7 @@ EXPORT_SYMBOL_GPL(iommu_dev_disable_feature); * On error, returns an ERR_PTR value. */ struct iommu_sva * -iommu_sva_bind_device(struct device *dev, struct mm_struct *mm, void *drvdata) +iommu_sva_bind_device(struct device *dev, struct mm_struct *mm) { struct iommu_group *group; struct iommu_sva *handle = ERR_PTR(-EINVAL); @@ -2788,7 +2787,7 @@ iommu_sva_bind_device(struct device *dev, struct mm_struct *mm, void *drvdata) if (iommu_group_device_count(group) != 1) goto out_unlock; - handle = ops->sva_bind(dev, mm, drvdata); + handle = ops->sva_bind(dev, mm); out_unlock: mutex_unlock(&group->mutex); diff --git a/drivers/misc/uacce/uacce.c b/drivers/misc/uacce/uacce.c index b70a013139c7..905eff1f840e 100644 --- a/drivers/misc/uacce/uacce.c +++ b/drivers/misc/uacce/uacce.c @@ -108,7 +108,7 @@ static int uacce_bind_queue(struct uacce_device *uacce, struct uacce_queue *q) if (!(uacce->flags & UACCE_DEV_SVA)) return 0; - handle = iommu_sva_bind_device(uacce->parent, current->mm, NULL); + handle = iommu_sva_bind_device(uacce->parent, current->mm); if (IS_ERR(handle)) return PTR_ERR(handle); diff --git a/include/linux/intel-svm.h b/include/linux/intel-svm.h index 207ef06ba3e1..f9a0d44f6fdb 100644 --- a/include/linux/intel-svm.h +++ b/include/linux/intel-svm.h @@ -13,17 +13,4 @@ #define PRQ_RING_MASK ((0x1000 << PRQ_ORDER) - 0x20) #define PRQ_DEPTH ((0x1000 << PRQ_ORDER) >> 5) -/* - * The SVM_FLAG_SUPERVISOR_MODE flag requests a PASID which can be used only - * for access to kernel addresses. No IOTLB flushes are automatically done - * for kernel mappings; it is valid only for access to the kernel's static - * 1:1 mapping of physical memory — not to vmalloc or even module mappings. - * A future API addition may permit the use of such ranges, by means of an - * explicit IOTLB flush call (akin to the DMA API's unmap method). - * - * It is unlikely that we will ever hook into flush_tlb_kernel_range() to - * do such IOTLB flushes automatically. - */ -#define SVM_FLAG_SUPERVISOR_MODE BIT(0) - #endif /* __INTEL_SVM_H__ */ diff --git a/include/linux/iommu.h b/include/linux/iommu.h index ac3f6c6dcc6d..72bb0531aa76 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -247,8 +247,7 @@ struct iommu_ops { int (*dev_enable_feat)(struct device *dev, enum iommu_dev_features f); int (*dev_disable_feat)(struct device *dev, enum iommu_dev_features f); - struct iommu_sva *(*sva_bind)(struct device *dev, struct mm_struct *mm, - void *drvdata); + struct iommu_sva *(*sva_bind)(struct device *dev, struct mm_struct *mm); void (*sva_unbind)(struct iommu_sva *handle); u32 (*sva_get_pasid)(struct iommu_sva *handle); @@ -668,8 +667,7 @@ int iommu_dev_enable_feature(struct device *dev, enum iommu_dev_features f); int iommu_dev_disable_feature(struct device *dev, enum iommu_dev_features f); struct iommu_sva *iommu_sva_bind_device(struct device *dev, - struct mm_struct *mm, - void *drvdata); + struct mm_struct *mm); void iommu_sva_unbind_device(struct iommu_sva *handle); u32 iommu_sva_get_pasid(struct iommu_sva *handle); @@ -1000,7 +998,7 @@ iommu_dev_disable_feature(struct device *dev, enum iommu_dev_features feat) } static inline struct iommu_sva * -iommu_sva_bind_device(struct device *dev, struct mm_struct *mm, void *drvdata) +iommu_sva_bind_device(struct device *dev, struct mm_struct *mm) { return NULL; } -- cgit v1.2.3 From 16603704559c7a68718059c4f75287886c01b20f Mon Sep 17 00:00:00 2001 From: Lu Baolu Date: Mon, 31 Oct 2022 08:59:09 +0800 Subject: iommu: Add attach/detach_dev_pasid iommu interfaces Attaching an IOMMU domain to a PASID of a device is a generic operation for modern IOMMU drivers which support PASID-granular DMA address translation. Currently visible usage scenarios include (but not limited): - SVA (Shared Virtual Address) - kernel DMA with PASID - hardware-assist mediated device This adds the set_dev_pasid domain ops for setting the domain onto a PASID of a device and remove_dev_pasid iommu ops for removing any setup on a PASID of device. This also adds interfaces for device drivers to attach/detach/retrieve a domain for a PASID of a device. If multiple devices share a single group, it's fine as long the fabric always routes every TLP marked with a PASID to the host bridge and only the host bridge. For example, ACS achieves this universally and has been checked when pci_enable_pasid() is called. As we can't reliably tell the source apart in a group, all the devices in a group have to be considered as the same source, and mapped to the same PASID table. The DMA ownership is about the whole device (more precisely, iommu group), including the RID and PASIDs. When the ownership is converted, the pasid array must be empty. This also adds necessary checks in the DMA ownership interfaces. Signed-off-by: Lu Baolu Reviewed-by: Jean-Philippe Brucker Reviewed-by: Kevin Tian Reviewed-by: Yi Liu Reviewed-by: Jason Gunthorpe Tested-by: Zhangfei Gao Tested-by: Tony Zhu Link: https://lore.kernel.org/r/20221031005917.45690-6-baolu.lu@linux.intel.com Signed-off-by: Joerg Roedel --- drivers/iommu/iommu.c | 141 ++++++++++++++++++++++++++++++++++++++++++++++++-- include/linux/iommu.h | 32 ++++++++++++ 2 files changed, 169 insertions(+), 4 deletions(-) (limited to 'drivers/iommu/iommu.c') diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c index a94ec648c88b..bf22992beb98 100644 --- a/drivers/iommu/iommu.c +++ b/drivers/iommu/iommu.c @@ -43,6 +43,7 @@ struct iommu_group { struct kobject kobj; struct kobject *devices_kobj; struct list_head devices; + struct xarray pasid_array; struct mutex mutex; void *iommu_data; void (*iommu_data_release)(void *iommu_data); @@ -723,6 +724,7 @@ struct iommu_group *iommu_group_alloc(void) mutex_init(&group->mutex); INIT_LIST_HEAD(&group->devices); INIT_LIST_HEAD(&group->entry); + xa_init(&group->pasid_array); ret = ida_alloc(&iommu_group_ida, GFP_KERNEL); if (ret < 0) { @@ -3106,7 +3108,8 @@ int iommu_device_use_default_domain(struct device *dev) mutex_lock(&group->mutex); if (group->owner_cnt) { - if (group->owner || !iommu_is_default_domain(group)) { + if (group->owner || !iommu_is_default_domain(group) || + !xa_empty(&group->pasid_array)) { ret = -EBUSY; goto unlock_out; } @@ -3137,7 +3140,7 @@ void iommu_device_unuse_default_domain(struct device *dev) return; mutex_lock(&group->mutex); - if (!WARN_ON(!group->owner_cnt)) + if (!WARN_ON(!group->owner_cnt || !xa_empty(&group->pasid_array))) group->owner_cnt--; mutex_unlock(&group->mutex); @@ -3185,7 +3188,8 @@ int iommu_group_claim_dma_owner(struct iommu_group *group, void *owner) ret = -EPERM; goto unlock_out; } else { - if (group->domain && group->domain != group->default_domain) { + if ((group->domain && group->domain != group->default_domain) || + !xa_empty(&group->pasid_array)) { ret = -EBUSY; goto unlock_out; } @@ -3219,7 +3223,8 @@ void iommu_group_release_dma_owner(struct iommu_group *group) int ret; mutex_lock(&group->mutex); - if (WARN_ON(!group->owner_cnt || !group->owner)) + if (WARN_ON(!group->owner_cnt || !group->owner || + !xa_empty(&group->pasid_array))) goto unlock_out; group->owner_cnt = 0; @@ -3250,3 +3255,131 @@ bool iommu_group_dma_owner_claimed(struct iommu_group *group) return user; } EXPORT_SYMBOL_GPL(iommu_group_dma_owner_claimed); + +static int __iommu_set_group_pasid(struct iommu_domain *domain, + struct iommu_group *group, ioasid_t pasid) +{ + struct group_device *device; + int ret = 0; + + list_for_each_entry(device, &group->devices, list) { + ret = domain->ops->set_dev_pasid(domain, device->dev, pasid); + if (ret) + break; + } + + return ret; +} + +static void __iommu_remove_group_pasid(struct iommu_group *group, + ioasid_t pasid) +{ + struct group_device *device; + const struct iommu_ops *ops; + + list_for_each_entry(device, &group->devices, list) { + ops = dev_iommu_ops(device->dev); + ops->remove_dev_pasid(device->dev, pasid); + } +} + +/* + * 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. + * + * Return: 0 on success, or an error. + */ +int iommu_attach_device_pasid(struct iommu_domain *domain, + struct device *dev, ioasid_t pasid) +{ + struct iommu_group *group; + void *curr; + int ret; + + if (!domain->ops->set_dev_pasid) + return -EOPNOTSUPP; + + group = iommu_group_get(dev); + if (!group) + return -ENODEV; + + mutex_lock(&group->mutex); + curr = xa_cmpxchg(&group->pasid_array, pasid, NULL, domain, GFP_KERNEL); + if (curr) { + ret = xa_err(curr) ? : -EBUSY; + goto out_unlock; + } + + ret = __iommu_set_group_pasid(domain, group, pasid); + if (ret) { + __iommu_remove_group_pasid(group, pasid); + xa_erase(&group->pasid_array, pasid); + } +out_unlock: + mutex_unlock(&group->mutex); + iommu_group_put(group); + + return ret; +} +EXPORT_SYMBOL_GPL(iommu_attach_device_pasid); + +/* + * 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) +{ + struct iommu_group *group = iommu_group_get(dev); + + mutex_lock(&group->mutex); + __iommu_remove_group_pasid(group, pasid); + WARN_ON(xa_erase(&group->pasid_array, pasid) != domain); + mutex_unlock(&group->mutex); + + iommu_group_put(group); +} +EXPORT_SYMBOL_GPL(iommu_detach_device_pasid); + +/* + * iommu_get_domain_for_dev_pasid() - Retrieve domain for @pasid of @dev + * @dev: the queried device + * @pasid: the pasid of the device + * @type: matched domain type, 0 for any match + * + * This is a variant of iommu_get_domain_for_dev(). It returns the existing + * domain attached to pasid of a device. Callers must hold a lock around this + * function, and both iommu_attach/detach_dev_pasid() whenever a domain of + * type is being manipulated. This API does not internally resolve races with + * attach/detach. + * + * Return: attached domain on success, NULL otherwise. + */ +struct iommu_domain *iommu_get_domain_for_dev_pasid(struct device *dev, + ioasid_t pasid, + unsigned int type) +{ + struct iommu_domain *domain; + struct iommu_group *group; + + group = iommu_group_get(dev); + if (!group) + return NULL; + + xa_lock(&group->pasid_array); + domain = xa_load(&group->pasid_array, pasid); + if (type && domain && domain->type != type) + domain = ERR_PTR(-EBUSY); + xa_unlock(&group->pasid_array); + iommu_group_put(group); + + return domain; +} +EXPORT_SYMBOL_GPL(iommu_get_domain_for_dev_pasid); diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 72bb0531aa76..5d2b78ac5416 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -223,6 +223,9 @@ struct iommu_iotlb_gather { * - IOMMU_DOMAIN_DMA: must use a dma domain * - 0: use the default setting * @default_domain_ops: the default ops for domains + * @remove_dev_pasid: Remove any translation configurations of a specific + * pasid, so that any DMA transactions with this pasid + * will be blocked by the hardware. * @pgsize_bitmap: bitmap of all possible supported page sizes * @owner: Driver module providing these ops */ @@ -256,6 +259,7 @@ struct iommu_ops { struct iommu_page_response *msg); int (*def_domain_type)(struct device *dev); + void (*remove_dev_pasid)(struct device *dev, ioasid_t pasid); const struct iommu_domain_ops *default_domain_ops; unsigned long pgsize_bitmap; @@ -266,6 +270,7 @@ struct iommu_ops { * struct iommu_domain_ops - domain specific operations * @attach_dev: attach an iommu domain to a device * @detach_dev: detach an iommu domain from a device + * @set_dev_pasid: set an iommu domain to a pasid of device * @map: map a physically contiguous memory region to an iommu domain * @map_pages: map a physically contiguous set of pages of the same size to * an iommu domain. @@ -286,6 +291,8 @@ struct iommu_ops { struct iommu_domain_ops { int (*attach_dev)(struct iommu_domain *domain, struct device *dev); void (*detach_dev)(struct iommu_domain *domain, struct device *dev); + int (*set_dev_pasid)(struct iommu_domain *domain, struct device *dev, + ioasid_t pasid); int (*map)(struct iommu_domain *domain, unsigned long iova, phys_addr_t paddr, size_t size, int prot, gfp_t gfp); @@ -678,6 +685,13 @@ int iommu_group_claim_dma_owner(struct iommu_group *group, void *owner); void iommu_group_release_dma_owner(struct iommu_group *group); bool iommu_group_dma_owner_claimed(struct iommu_group *group); +int iommu_attach_device_pasid(struct iommu_domain *domain, + struct device *dev, ioasid_t pasid); +void iommu_detach_device_pasid(struct iommu_domain *domain, + struct device *dev, ioasid_t pasid); +struct iommu_domain * +iommu_get_domain_for_dev_pasid(struct device *dev, ioasid_t pasid, + unsigned int type); #else /* CONFIG_IOMMU_API */ struct iommu_ops {}; @@ -1040,6 +1054,24 @@ static inline bool iommu_group_dma_owner_claimed(struct iommu_group *group) { return false; } + +static inline int iommu_attach_device_pasid(struct iommu_domain *domain, + struct device *dev, ioasid_t pasid) +{ + return -ENODEV; +} + +static inline void iommu_detach_device_pasid(struct iommu_domain *domain, + struct device *dev, ioasid_t pasid) +{ +} + +static inline struct iommu_domain * +iommu_get_domain_for_dev_pasid(struct device *dev, ioasid_t pasid, + unsigned int type) +{ + return NULL; +} #endif /* CONFIG_IOMMU_API */ /** -- cgit v1.2.3 From 136467962e49931dbc6240aea8197fab7e407ba4 Mon Sep 17 00:00:00 2001 From: Lu Baolu Date: Mon, 31 Oct 2022 08:59:10 +0800 Subject: iommu: Add IOMMU SVA domain support The SVA iommu_domain represents a hardware pagetable that the IOMMU hardware could use for SVA translation. This adds some infrastructures to support SVA domain in the iommu core. It includes: - Extend the iommu_domain to support a new IOMMU_DOMAIN_SVA domain type. The IOMMU drivers that support allocation of the SVA domain should provide its own SVA domain specific iommu_domain_ops. - Add a helper to allocate an SVA domain. The iommu_domain_free() is still used to free an SVA domain. The report_iommu_fault() should be replaced by the new iommu_report_device_fault(). Leave the existing fault handler with the existing users and the newly added SVA members excludes it. Suggested-by: Jean-Philippe Brucker Suggested-by: Jason Gunthorpe Signed-off-by: Lu Baolu Reviewed-by: Jean-Philippe Brucker Reviewed-by: Kevin Tian Reviewed-by: Jason Gunthorpe Reviewed-by: Yi Liu Tested-by: Zhangfei Gao Tested-by: Tony Zhu Link: https://lore.kernel.org/r/20221031005917.45690-7-baolu.lu@linux.intel.com Signed-off-by: Joerg Roedel --- drivers/iommu/iommu.c | 20 ++++++++++++++++++++ include/linux/iommu.h | 25 +++++++++++++++++++++++-- 2 files changed, 43 insertions(+), 2 deletions(-) (limited to 'drivers/iommu/iommu.c') diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c index bf22992beb98..6a1cd2018e30 100644 --- a/drivers/iommu/iommu.c +++ b/drivers/iommu/iommu.c @@ -29,6 +29,7 @@ #include #include #include +#include #include "dma-iommu.h" @@ -1934,6 +1935,8 @@ EXPORT_SYMBOL_GPL(iommu_domain_alloc); void iommu_domain_free(struct iommu_domain *domain) { + if (domain->type == IOMMU_DOMAIN_SVA) + mmdrop(domain->mm); iommu_put_dma_cookie(domain); domain->ops->free(domain); } @@ -3383,3 +3386,20 @@ struct iommu_domain *iommu_get_domain_for_dev_pasid(struct device *dev, return domain; } EXPORT_SYMBOL_GPL(iommu_get_domain_for_dev_pasid); + +struct iommu_domain *iommu_sva_domain_alloc(struct device *dev, + struct mm_struct *mm) +{ + const struct iommu_ops *ops = dev_iommu_ops(dev); + struct iommu_domain *domain; + + domain = ops->domain_alloc(IOMMU_DOMAIN_SVA); + if (!domain) + return NULL; + + domain->type = IOMMU_DOMAIN_SVA; + mmgrab(mm); + domain->mm = mm; + + return domain; +} diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 5d2b78ac5416..776baa375967 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -64,6 +64,8 @@ struct iommu_domain_geometry { #define __IOMMU_DOMAIN_PT (1U << 2) /* Domain is identity mapped */ #define __IOMMU_DOMAIN_DMA_FQ (1U << 3) /* DMA-API uses flush queue */ +#define __IOMMU_DOMAIN_SVA (1U << 4) /* Shared process address space */ + /* * This are the possible domain-types * @@ -77,6 +79,8 @@ struct iommu_domain_geometry { * certain optimizations for these domains * IOMMU_DOMAIN_DMA_FQ - As above, but definitely using batched TLB * invalidation. + * IOMMU_DOMAIN_SVA - DMA addresses are shared process addresses + * represented by mm_struct's. */ #define IOMMU_DOMAIN_BLOCKED (0U) #define IOMMU_DOMAIN_IDENTITY (__IOMMU_DOMAIN_PT) @@ -86,15 +90,24 @@ struct iommu_domain_geometry { #define IOMMU_DOMAIN_DMA_FQ (__IOMMU_DOMAIN_PAGING | \ __IOMMU_DOMAIN_DMA_API | \ __IOMMU_DOMAIN_DMA_FQ) +#define IOMMU_DOMAIN_SVA (__IOMMU_DOMAIN_SVA) struct iommu_domain { unsigned type; const struct iommu_domain_ops *ops; unsigned long pgsize_bitmap; /* Bitmap of page sizes in use */ - iommu_fault_handler_t handler; - void *handler_token; struct iommu_domain_geometry geometry; struct iommu_dma_cookie *iova_cookie; + union { + struct { + iommu_fault_handler_t handler; + void *handler_token; + }; + struct { /* IOMMU_DOMAIN_SVA */ + struct mm_struct *mm; + int users; + }; + }; }; static inline bool iommu_is_dma_domain(struct iommu_domain *domain) @@ -685,6 +698,8 @@ int iommu_group_claim_dma_owner(struct iommu_group *group, void *owner); void iommu_group_release_dma_owner(struct iommu_group *group); bool iommu_group_dma_owner_claimed(struct iommu_group *group); +struct iommu_domain *iommu_sva_domain_alloc(struct device *dev, + struct mm_struct *mm); int iommu_attach_device_pasid(struct iommu_domain *domain, struct device *dev, ioasid_t pasid); void iommu_detach_device_pasid(struct iommu_domain *domain, @@ -1055,6 +1070,12 @@ static inline bool iommu_group_dma_owner_claimed(struct iommu_group *group) return false; } +static inline struct iommu_domain * +iommu_sva_domain_alloc(struct device *dev, struct mm_struct *mm) +{ + return NULL; +} + static inline int iommu_attach_device_pasid(struct iommu_domain *domain, struct device *dev, ioasid_t pasid) { -- cgit v1.2.3 From be51b1d6bbff48c7d1943a8ff1e5a55777807f6e Mon Sep 17 00:00:00 2001 From: Lu Baolu Date: Mon, 31 Oct 2022 08:59:13 +0800 Subject: iommu/sva: Refactoring iommu_sva_bind/unbind_device() The existing iommu SVA interfaces are implemented by calling the SVA specific iommu ops provided by the IOMMU drivers. There's no need for any SVA specific ops in iommu_ops vector anymore as we can achieve this through the generic attach/detach_dev_pasid domain ops. This refactors the IOMMU SVA interfaces implementation by using the iommu_attach/detach_device_pasid interfaces and align them with the concept of the SVA iommu domain. Put the new SVA code in the SVA related file in order to make it self-contained. Signed-off-by: Lu Baolu Reviewed-by: Jean-Philippe Brucker Reviewed-by: Kevin Tian Reviewed-by: Jason Gunthorpe Tested-by: Zhangfei Gao Tested-by: Tony Zhu Link: https://lore.kernel.org/r/20221031005917.45690-10-baolu.lu@linux.intel.com Signed-off-by: Joerg Roedel --- drivers/iommu/iommu-sva-lib.c | 111 ++++++++++++++++++++++++++++++++++++++++++ drivers/iommu/iommu.c | 91 ---------------------------------- include/linux/iommu.h | 43 ++++++++-------- 3 files changed, 134 insertions(+), 111 deletions(-) (limited to 'drivers/iommu/iommu.c') diff --git a/drivers/iommu/iommu-sva-lib.c b/drivers/iommu/iommu-sva-lib.c index 106506143896..e425573a1787 100644 --- a/drivers/iommu/iommu-sva-lib.c +++ b/drivers/iommu/iommu-sva-lib.c @@ -4,6 +4,7 @@ */ #include #include +#include #include "iommu-sva-lib.h" @@ -69,3 +70,113 @@ struct mm_struct *iommu_sva_find(ioasid_t pasid) return ioasid_find(&iommu_sva_pasid, pasid, __mmget_not_zero); } EXPORT_SYMBOL_GPL(iommu_sva_find); + +/** + * 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 mm_users + * + * Create a bond between device and address space, allowing the device to + * access the mm using the PASID returned by iommu_sva_get_pasid(). If a + * bond already exists between @device and @mm, an additional internal + * 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. + * + * On error, returns an ERR_PTR value. + */ +struct iommu_sva *iommu_sva_bind_device(struct device *dev, struct mm_struct *mm) +{ + struct iommu_domain *domain; + struct iommu_sva *handle; + ioasid_t max_pasids; + int ret; + + max_pasids = dev->iommu->max_pasids; + if (!max_pasids) + return ERR_PTR(-EOPNOTSUPP); + + /* Allocate mm->pasid if necessary. */ + ret = iommu_sva_alloc_pasid(mm, 1, max_pasids - 1); + if (ret) + return ERR_PTR(ret); + + handle = kzalloc(sizeof(*handle), GFP_KERNEL); + if (!handle) + return ERR_PTR(-ENOMEM); + + mutex_lock(&iommu_sva_lock); + /* Search for an existing domain. */ + domain = iommu_get_domain_for_dev_pasid(dev, mm->pasid, + IOMMU_DOMAIN_SVA); + if (IS_ERR(domain)) { + ret = PTR_ERR(domain); + goto out_unlock; + } + + if (domain) { + domain->users++; + goto out; + } + + /* Allocate a new domain and set it on device pasid. */ + domain = iommu_sva_domain_alloc(dev, mm); + if (!domain) { + ret = -ENOMEM; + goto out_unlock; + } + + ret = iommu_attach_device_pasid(domain, dev, mm->pasid); + if (ret) + goto out_free_domain; + domain->users = 1; +out: + mutex_unlock(&iommu_sva_lock); + handle->dev = dev; + handle->domain = domain; + + return handle; + +out_free_domain: + iommu_domain_free(domain); +out_unlock: + mutex_unlock(&iommu_sva_lock); + kfree(handle); + + return ERR_PTR(ret); +} +EXPORT_SYMBOL_GPL(iommu_sva_bind_device); + +/** + * iommu_sva_unbind_device() - Remove a bond created with iommu_sva_bind_device + * @handle: the handle returned by iommu_sva_bind_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. + */ +void iommu_sva_unbind_device(struct iommu_sva *handle) +{ + struct iommu_domain *domain = handle->domain; + ioasid_t pasid = domain->mm->pasid; + struct device *dev = handle->dev; + + mutex_lock(&iommu_sva_lock); + if (--domain->users == 0) { + iommu_detach_device_pasid(domain, dev, pasid); + iommu_domain_free(domain); + } + mutex_unlock(&iommu_sva_lock); + kfree(handle); +} +EXPORT_SYMBOL_GPL(iommu_sva_unbind_device); + +u32 iommu_sva_get_pasid(struct iommu_sva *handle) +{ + struct iommu_domain *domain = handle->domain; + + return domain->mm->pasid; +} +EXPORT_SYMBOL_GPL(iommu_sva_get_pasid); diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c index 6a1cd2018e30..c9da0a1bb3b8 100644 --- a/drivers/iommu/iommu.c +++ b/drivers/iommu/iommu.c @@ -2751,97 +2751,6 @@ int iommu_dev_disable_feature(struct device *dev, enum iommu_dev_features feat) } EXPORT_SYMBOL_GPL(iommu_dev_disable_feature); -/** - * 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 - * - * 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. - * - * On error, returns an ERR_PTR value. - */ -struct iommu_sva * -iommu_sva_bind_device(struct device *dev, struct mm_struct *mm) -{ - struct iommu_group *group; - struct iommu_sva *handle = ERR_PTR(-EINVAL); - const struct iommu_ops *ops = dev_iommu_ops(dev); - - if (!ops->sva_bind) - return ERR_PTR(-ENODEV); - - group = iommu_group_get(dev); - if (!group) - return ERR_PTR(-ENODEV); - - /* Ensure device count and domain don't change while we're binding */ - mutex_lock(&group->mutex); - - /* - * 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; - - handle = ops->sva_bind(dev, mm); - -out_unlock: - mutex_unlock(&group->mutex); - iommu_group_put(group); - - return handle; -} -EXPORT_SYMBOL_GPL(iommu_sva_bind_device); - -/** - * iommu_sva_unbind_device() - Remove a bond created with iommu_sva_bind_device - * @handle: the handle returned by iommu_sva_bind_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. - */ -void iommu_sva_unbind_device(struct iommu_sva *handle) -{ - struct iommu_group *group; - struct device *dev = handle->dev; - const struct iommu_ops *ops = dev_iommu_ops(dev); - - if (!ops->sva_unbind) - return; - - group = iommu_group_get(dev); - if (!group) - return; - - mutex_lock(&group->mutex); - ops->sva_unbind(handle); - mutex_unlock(&group->mutex); - - iommu_group_put(group); -} -EXPORT_SYMBOL_GPL(iommu_sva_unbind_device); - -u32 iommu_sva_get_pasid(struct iommu_sva *handle) -{ - const struct iommu_ops *ops = dev_iommu_ops(handle->dev); - - if (!ops->sva_get_pasid) - return IOMMU_PASID_INVALID; - - return ops->sva_get_pasid(handle); -} -EXPORT_SYMBOL_GPL(iommu_sva_get_pasid); - /* * Changes the default domain of an iommu group that has *only* one device * diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 776baa375967..bee5659d07eb 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -645,6 +645,7 @@ struct iommu_fwspec { */ struct iommu_sva { struct device *dev; + struct iommu_domain *domain; }; int iommu_fwspec_init(struct device *dev, struct fwnode_handle *iommu_fwnode, @@ -686,11 +687,6 @@ void iommu_release_device(struct device *dev); int iommu_dev_enable_feature(struct device *dev, enum iommu_dev_features f); int iommu_dev_disable_feature(struct device *dev, enum iommu_dev_features f); -struct iommu_sva *iommu_sva_bind_device(struct device *dev, - struct mm_struct *mm); -void iommu_sva_unbind_device(struct iommu_sva *handle); -u32 iommu_sva_get_pasid(struct iommu_sva *handle); - int iommu_device_use_default_domain(struct device *dev); void iommu_device_unuse_default_domain(struct device *dev); @@ -1026,21 +1022,6 @@ iommu_dev_disable_feature(struct device *dev, enum iommu_dev_features feat) return -ENODEV; } -static inline struct iommu_sva * -iommu_sva_bind_device(struct device *dev, struct mm_struct *mm) -{ - return NULL; -} - -static inline void iommu_sva_unbind_device(struct iommu_sva *handle) -{ -} - -static inline u32 iommu_sva_get_pasid(struct iommu_sva *handle) -{ - return IOMMU_PASID_INVALID; -} - static inline struct iommu_fwspec *dev_iommu_fwspec_get(struct device *dev) { return NULL; @@ -1154,4 +1135,26 @@ static inline void iommu_dma_compose_msi_msg(struct msi_desc *desc, struct msi_m #endif /* CONFIG_IOMMU_DMA */ +#ifdef CONFIG_IOMMU_SVA +struct iommu_sva *iommu_sva_bind_device(struct device *dev, + struct mm_struct *mm); +void iommu_sva_unbind_device(struct iommu_sva *handle); +u32 iommu_sva_get_pasid(struct iommu_sva *handle); +#else +static inline struct iommu_sva * +iommu_sva_bind_device(struct device *dev, struct mm_struct *mm) +{ + return NULL; +} + +static inline void iommu_sva_unbind_device(struct iommu_sva *handle) +{ +} + +static inline u32 iommu_sva_get_pasid(struct iommu_sva *handle) +{ + return IOMMU_PASID_INVALID; +} +#endif /* CONFIG_IOMMU_SVA */ + #endif /* __LINUX_IOMMU_H */ -- cgit v1.2.3 From 8cc93159f91960b4812ea48887e9e7501babc95a Mon Sep 17 00:00:00 2001 From: Lu Baolu Date: Mon, 31 Oct 2022 08:59:15 +0800 Subject: iommu: Prepare IOMMU domain for IOPF This adds some mechanisms around the iommu_domain so that the I/O page fault handling framework could route a page fault to the domain and call the fault handler from it. Add pointers to the page fault handler and its private data in struct iommu_domain. The fault handler will be called with the private data as a parameter once a page fault is routed to the domain. Any kernel component which owns an iommu domain could install handler and its private parameter so that the page fault could be further routed and handled. This also prepares the SVA implementation to be the first consumer of the per-domain page fault handling model. The I/O page fault handler for SVA is copied to the SVA file with mmget_not_zero() added before mmap_read_lock(). Suggested-by: Jean-Philippe Brucker Signed-off-by: Lu Baolu Reviewed-by: Jean-Philippe Brucker Reviewed-by: Kevin Tian Reviewed-by: Jason Gunthorpe Tested-by: Zhangfei Gao Tested-by: Tony Zhu Link: https://lore.kernel.org/r/20221031005917.45690-12-baolu.lu@linux.intel.com Signed-off-by: Joerg Roedel --- drivers/iommu/io-pgfault.c | 7 ++++++ drivers/iommu/iommu-sva-lib.c | 58 +++++++++++++++++++++++++++++++++++++++++++ drivers/iommu/iommu-sva-lib.h | 8 ++++++ drivers/iommu/iommu.c | 4 +++ include/linux/iommu.h | 3 +++ 5 files changed, 80 insertions(+) (limited to 'drivers/iommu/iommu.c') diff --git a/drivers/iommu/io-pgfault.c b/drivers/iommu/io-pgfault.c index 1df8c1dcae77..aee9e033012f 100644 --- a/drivers/iommu/io-pgfault.c +++ b/drivers/iommu/io-pgfault.c @@ -181,6 +181,13 @@ static void iopf_handle_group(struct work_struct *work) * request completes, outstanding faults will have been dealt with by the time * the PASID is freed. * + * Any valid page fault will be eventually routed to an iommu domain and the + * page fault handler installed there will get called. The users of this + * handling framework should guarantee that the iommu domain could only be + * freed after the device has stopped generating page faults (or the iommu + * hardware has been set to block the page faults) and the pending page faults + * have been flushed. + * * Return: 0 on success and <0 on error. */ int iommu_queue_iopf(struct iommu_fault *fault, void *cookie) diff --git a/drivers/iommu/iommu-sva-lib.c b/drivers/iommu/iommu-sva-lib.c index e425573a1787..089fd61ff453 100644 --- a/drivers/iommu/iommu-sva-lib.c +++ b/drivers/iommu/iommu-sva-lib.c @@ -180,3 +180,61 @@ u32 iommu_sva_get_pasid(struct iommu_sva *handle) return domain->mm->pasid; } EXPORT_SYMBOL_GPL(iommu_sva_get_pasid); + +/* + * I/O page fault handler for SVA + */ +enum iommu_page_response_code +iommu_sva_handle_iopf(struct iommu_fault *fault, void *data) +{ + vm_fault_t ret; + struct vm_area_struct *vma; + struct mm_struct *mm = data; + unsigned int access_flags = 0; + unsigned int fault_flags = FAULT_FLAG_REMOTE; + struct iommu_fault_page_request *prm = &fault->prm; + enum iommu_page_response_code status = IOMMU_PAGE_RESP_INVALID; + + if (!(prm->flags & IOMMU_FAULT_PAGE_REQUEST_PASID_VALID)) + return status; + + if (!mmget_not_zero(mm)) + return status; + + mmap_read_lock(mm); + + vma = find_extend_vma(mm, prm->addr); + if (!vma) + /* Unmapped area */ + goto out_put_mm; + + if (prm->perm & IOMMU_FAULT_PERM_READ) + access_flags |= VM_READ; + + if (prm->perm & IOMMU_FAULT_PERM_WRITE) { + access_flags |= VM_WRITE; + fault_flags |= FAULT_FLAG_WRITE; + } + + if (prm->perm & IOMMU_FAULT_PERM_EXEC) { + access_flags |= VM_EXEC; + fault_flags |= FAULT_FLAG_INSTRUCTION; + } + + if (!(prm->perm & IOMMU_FAULT_PERM_PRIV)) + fault_flags |= FAULT_FLAG_USER; + + if (access_flags & ~vma->vm_flags) + /* Access fault */ + goto out_put_mm; + + ret = handle_mm_fault(vma, prm->addr, fault_flags, NULL); + status = ret & VM_FAULT_ERROR ? IOMMU_PAGE_RESP_INVALID : + IOMMU_PAGE_RESP_SUCCESS; + +out_put_mm: + mmap_read_unlock(mm); + mmput(mm); + + return status; +} diff --git a/drivers/iommu/iommu-sva-lib.h b/drivers/iommu/iommu-sva-lib.h index 8909ea1094e3..1b3ace4b5863 100644 --- a/drivers/iommu/iommu-sva-lib.h +++ b/drivers/iommu/iommu-sva-lib.h @@ -26,6 +26,8 @@ int iopf_queue_flush_dev(struct device *dev); struct iopf_queue *iopf_queue_alloc(const char *name); void iopf_queue_free(struct iopf_queue *queue); int iopf_queue_discard_partial(struct iopf_queue *queue); +enum iommu_page_response_code +iommu_sva_handle_iopf(struct iommu_fault *fault, void *data); #else /* CONFIG_IOMMU_SVA */ static inline int iommu_queue_iopf(struct iommu_fault *fault, void *cookie) @@ -63,5 +65,11 @@ static inline int iopf_queue_discard_partial(struct iopf_queue *queue) { return -ENODEV; } + +static inline enum iommu_page_response_code +iommu_sva_handle_iopf(struct iommu_fault *fault, void *data) +{ + return IOMMU_PAGE_RESP_INVALID; +} #endif /* CONFIG_IOMMU_SVA */ #endif /* _IOMMU_SVA_LIB_H */ diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c index c9da0a1bb3b8..9e0fb18e1b34 100644 --- a/drivers/iommu/iommu.c +++ b/drivers/iommu/iommu.c @@ -33,6 +33,8 @@ #include "dma-iommu.h" +#include "iommu-sva-lib.h" + static struct kset *iommu_group_kset; static DEFINE_IDA(iommu_group_ida); @@ -3309,6 +3311,8 @@ struct iommu_domain *iommu_sva_domain_alloc(struct device *dev, domain->type = IOMMU_DOMAIN_SVA; mmgrab(mm); domain->mm = mm; + domain->iopf_handler = iommu_sva_handle_iopf; + domain->fault_data = mm; return domain; } diff --git a/include/linux/iommu.h b/include/linux/iommu.h index c337ef1c97bc..7d2648058e43 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -98,6 +98,9 @@ struct iommu_domain { unsigned long pgsize_bitmap; /* Bitmap of page sizes in use */ struct iommu_domain_geometry geometry; struct iommu_dma_cookie *iova_cookie; + enum iommu_page_response_code (*iopf_handler)(struct iommu_fault *fault, + void *data); + void *fault_data; union { struct { iommu_fault_handler_t handler; -- cgit v1.2.3 From 757636ed2607a3269cd2764e3e4a0480384c6c26 Mon Sep 17 00:00:00 2001 From: Lu Baolu Date: Mon, 31 Oct 2022 08:59:17 +0800 Subject: iommu: Rename iommu-sva-lib.{c,h} Rename iommu-sva-lib.c[h] to iommu-sva.c[h] as it contains all code for SVA implementation in iommu core. Signed-off-by: Lu Baolu Reviewed-by: Jean-Philippe Brucker Reviewed-by: Kevin Tian Reviewed-by: Jason Gunthorpe Tested-by: Zhangfei Gao Tested-by: Tony Zhu Link: https://lore.kernel.org/r/20221031005917.45690-14-baolu.lu@linux.intel.com Signed-off-by: Joerg Roedel --- drivers/iommu/Makefile | 2 +- drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c | 2 +- drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c | 2 +- drivers/iommu/intel/iommu.c | 2 +- drivers/iommu/intel/svm.c | 2 +- drivers/iommu/io-pgfault.c | 2 +- drivers/iommu/iommu-sva-lib.c | 240 ------------------------ drivers/iommu/iommu-sva-lib.h | 75 -------- drivers/iommu/iommu-sva.c | 240 ++++++++++++++++++++++++ drivers/iommu/iommu-sva.h | 75 ++++++++ drivers/iommu/iommu.c | 2 +- 11 files changed, 322 insertions(+), 322 deletions(-) delete mode 100644 drivers/iommu/iommu-sva-lib.c delete mode 100644 drivers/iommu/iommu-sva-lib.h create mode 100644 drivers/iommu/iommu-sva.c create mode 100644 drivers/iommu/iommu-sva.h (limited to 'drivers/iommu/iommu.c') diff --git a/drivers/iommu/Makefile b/drivers/iommu/Makefile index cc9f381013c3..7fbf6a337662 100644 --- a/drivers/iommu/Makefile +++ b/drivers/iommu/Makefile @@ -28,6 +28,6 @@ obj-$(CONFIG_FSL_PAMU) += fsl_pamu.o fsl_pamu_domain.o obj-$(CONFIG_S390_IOMMU) += s390-iommu.o obj-$(CONFIG_HYPERV_IOMMU) += hyperv-iommu.o obj-$(CONFIG_VIRTIO_IOMMU) += virtio-iommu.o -obj-$(CONFIG_IOMMU_SVA) += iommu-sva-lib.o io-pgfault.o +obj-$(CONFIG_IOMMU_SVA) += iommu-sva.o io-pgfault.o obj-$(CONFIG_SPRD_IOMMU) += sprd-iommu.o obj-$(CONFIG_APPLE_DART) += apple-dart.o diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c index 9541afbba73c..a5a63b1c947e 100644 --- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c +++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c @@ -10,7 +10,7 @@ #include #include "arm-smmu-v3.h" -#include "../../iommu-sva-lib.h" +#include "../../iommu-sva.h" #include "../../io-pgtable-arm.h" struct arm_smmu_mmu_notifier { diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c index 891e87ea54db..94a2e53368af 100644 --- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c +++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c @@ -29,7 +29,7 @@ #include "arm-smmu-v3.h" #include "../../dma-iommu.h" -#include "../../iommu-sva-lib.h" +#include "../../iommu-sva.h" static bool disable_bypass = true; module_param(disable_bypass, bool, 0444); diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c index 5a41b10593b7..a934a46bb9e6 100644 --- a/drivers/iommu/intel/iommu.c +++ b/drivers/iommu/intel/iommu.c @@ -27,7 +27,7 @@ #include "iommu.h" #include "../dma-iommu.h" #include "../irq_remapping.h" -#include "../iommu-sva-lib.h" +#include "../iommu-sva.h" #include "pasid.h" #include "cap_audit.h" diff --git a/drivers/iommu/intel/svm.c b/drivers/iommu/intel/svm.c index fceae9387018..f32de15da61a 100644 --- a/drivers/iommu/intel/svm.c +++ b/drivers/iommu/intel/svm.c @@ -24,7 +24,7 @@ #include "iommu.h" #include "pasid.h" #include "perf.h" -#include "../iommu-sva-lib.h" +#include "../iommu-sva.h" #include "trace.h" static irqreturn_t prq_event_thread(int irq, void *d); diff --git a/drivers/iommu/io-pgfault.c b/drivers/iommu/io-pgfault.c index d046d89cec55..e5b8b9110c13 100644 --- a/drivers/iommu/io-pgfault.c +++ b/drivers/iommu/io-pgfault.c @@ -11,7 +11,7 @@ #include #include -#include "iommu-sva-lib.h" +#include "iommu-sva.h" /** * struct iopf_queue - IO Page Fault queue diff --git a/drivers/iommu/iommu-sva-lib.c b/drivers/iommu/iommu-sva-lib.c deleted file mode 100644 index 089fd61ff453..000000000000 --- a/drivers/iommu/iommu-sva-lib.c +++ /dev/null @@ -1,240 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * Helpers for IOMMU drivers implementing SVA - */ -#include -#include -#include - -#include "iommu-sva-lib.h" - -static DEFINE_MUTEX(iommu_sva_lock); -static DECLARE_IOASID_SET(iommu_sva_pasid); - -/** - * iommu_sva_alloc_pasid - Allocate a PASID for the mm - * @mm: the mm - * @min: minimum PASID value (inclusive) - * @max: maximum PASID value (inclusive) - * - * Try to allocate a PASID for this mm, or take a reference to the existing one - * provided it fits within the [@min, @max] range. On success the PASID is - * available in mm->pasid and will be available for the lifetime of the mm. - * - * Returns 0 on success and < 0 on error. - */ -int iommu_sva_alloc_pasid(struct mm_struct *mm, ioasid_t min, ioasid_t max) -{ - int ret = 0; - ioasid_t pasid; - - if (min == INVALID_IOASID || max == INVALID_IOASID || - min == 0 || max < min) - return -EINVAL; - - mutex_lock(&iommu_sva_lock); - /* Is a PASID already associated with this mm? */ - if (pasid_valid(mm->pasid)) { - if (mm->pasid < min || mm->pasid >= max) - ret = -EOVERFLOW; - goto out; - } - - pasid = ioasid_alloc(&iommu_sva_pasid, min, max, mm); - if (!pasid_valid(pasid)) - ret = -ENOMEM; - else - mm_pasid_set(mm, pasid); -out: - mutex_unlock(&iommu_sva_lock); - return ret; -} -EXPORT_SYMBOL_GPL(iommu_sva_alloc_pasid); - -/* ioasid_find getter() requires a void * argument */ -static bool __mmget_not_zero(void *mm) -{ - return mmget_not_zero(mm); -} - -/** - * iommu_sva_find() - Find mm associated to the given PASID - * @pasid: Process Address Space ID assigned to the mm - * - * On success a reference to the mm is taken, and must be released with mmput(). - * - * Returns the mm corresponding to this PASID, or an error if not found. - */ -struct mm_struct *iommu_sva_find(ioasid_t pasid) -{ - return ioasid_find(&iommu_sva_pasid, pasid, __mmget_not_zero); -} -EXPORT_SYMBOL_GPL(iommu_sva_find); - -/** - * 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 mm_users - * - * Create a bond between device and address space, allowing the device to - * access the mm using the PASID returned by iommu_sva_get_pasid(). If a - * bond already exists between @device and @mm, an additional internal - * 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. - * - * On error, returns an ERR_PTR value. - */ -struct iommu_sva *iommu_sva_bind_device(struct device *dev, struct mm_struct *mm) -{ - struct iommu_domain *domain; - struct iommu_sva *handle; - ioasid_t max_pasids; - int ret; - - max_pasids = dev->iommu->max_pasids; - if (!max_pasids) - return ERR_PTR(-EOPNOTSUPP); - - /* Allocate mm->pasid if necessary. */ - ret = iommu_sva_alloc_pasid(mm, 1, max_pasids - 1); - if (ret) - return ERR_PTR(ret); - - handle = kzalloc(sizeof(*handle), GFP_KERNEL); - if (!handle) - return ERR_PTR(-ENOMEM); - - mutex_lock(&iommu_sva_lock); - /* Search for an existing domain. */ - domain = iommu_get_domain_for_dev_pasid(dev, mm->pasid, - IOMMU_DOMAIN_SVA); - if (IS_ERR(domain)) { - ret = PTR_ERR(domain); - goto out_unlock; - } - - if (domain) { - domain->users++; - goto out; - } - - /* Allocate a new domain and set it on device pasid. */ - domain = iommu_sva_domain_alloc(dev, mm); - if (!domain) { - ret = -ENOMEM; - goto out_unlock; - } - - ret = iommu_attach_device_pasid(domain, dev, mm->pasid); - if (ret) - goto out_free_domain; - domain->users = 1; -out: - mutex_unlock(&iommu_sva_lock); - handle->dev = dev; - handle->domain = domain; - - return handle; - -out_free_domain: - iommu_domain_free(domain); -out_unlock: - mutex_unlock(&iommu_sva_lock); - kfree(handle); - - return ERR_PTR(ret); -} -EXPORT_SYMBOL_GPL(iommu_sva_bind_device); - -/** - * iommu_sva_unbind_device() - Remove a bond created with iommu_sva_bind_device - * @handle: the handle returned by iommu_sva_bind_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. - */ -void iommu_sva_unbind_device(struct iommu_sva *handle) -{ - struct iommu_domain *domain = handle->domain; - ioasid_t pasid = domain->mm->pasid; - struct device *dev = handle->dev; - - mutex_lock(&iommu_sva_lock); - if (--domain->users == 0) { - iommu_detach_device_pasid(domain, dev, pasid); - iommu_domain_free(domain); - } - mutex_unlock(&iommu_sva_lock); - kfree(handle); -} -EXPORT_SYMBOL_GPL(iommu_sva_unbind_device); - -u32 iommu_sva_get_pasid(struct iommu_sva *handle) -{ - struct iommu_domain *domain = handle->domain; - - return domain->mm->pasid; -} -EXPORT_SYMBOL_GPL(iommu_sva_get_pasid); - -/* - * I/O page fault handler for SVA - */ -enum iommu_page_response_code -iommu_sva_handle_iopf(struct iommu_fault *fault, void *data) -{ - vm_fault_t ret; - struct vm_area_struct *vma; - struct mm_struct *mm = data; - unsigned int access_flags = 0; - unsigned int fault_flags = FAULT_FLAG_REMOTE; - struct iommu_fault_page_request *prm = &fault->prm; - enum iommu_page_response_code status = IOMMU_PAGE_RESP_INVALID; - - if (!(prm->flags & IOMMU_FAULT_PAGE_REQUEST_PASID_VALID)) - return status; - - if (!mmget_not_zero(mm)) - return status; - - mmap_read_lock(mm); - - vma = find_extend_vma(mm, prm->addr); - if (!vma) - /* Unmapped area */ - goto out_put_mm; - - if (prm->perm & IOMMU_FAULT_PERM_READ) - access_flags |= VM_READ; - - if (prm->perm & IOMMU_FAULT_PERM_WRITE) { - access_flags |= VM_WRITE; - fault_flags |= FAULT_FLAG_WRITE; - } - - if (prm->perm & IOMMU_FAULT_PERM_EXEC) { - access_flags |= VM_EXEC; - fault_flags |= FAULT_FLAG_INSTRUCTION; - } - - if (!(prm->perm & IOMMU_FAULT_PERM_PRIV)) - fault_flags |= FAULT_FLAG_USER; - - if (access_flags & ~vma->vm_flags) - /* Access fault */ - goto out_put_mm; - - ret = handle_mm_fault(vma, prm->addr, fault_flags, NULL); - status = ret & VM_FAULT_ERROR ? IOMMU_PAGE_RESP_INVALID : - IOMMU_PAGE_RESP_SUCCESS; - -out_put_mm: - mmap_read_unlock(mm); - mmput(mm); - - return status; -} diff --git a/drivers/iommu/iommu-sva-lib.h b/drivers/iommu/iommu-sva-lib.h deleted file mode 100644 index 1b3ace4b5863..000000000000 --- a/drivers/iommu/iommu-sva-lib.h +++ /dev/null @@ -1,75 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * SVA library for IOMMU drivers - */ -#ifndef _IOMMU_SVA_LIB_H -#define _IOMMU_SVA_LIB_H - -#include -#include - -int iommu_sva_alloc_pasid(struct mm_struct *mm, ioasid_t min, ioasid_t max); -struct mm_struct *iommu_sva_find(ioasid_t pasid); - -/* I/O Page fault */ -struct device; -struct iommu_fault; -struct iopf_queue; - -#ifdef CONFIG_IOMMU_SVA -int iommu_queue_iopf(struct iommu_fault *fault, void *cookie); - -int iopf_queue_add_device(struct iopf_queue *queue, struct device *dev); -int iopf_queue_remove_device(struct iopf_queue *queue, - struct device *dev); -int iopf_queue_flush_dev(struct device *dev); -struct iopf_queue *iopf_queue_alloc(const char *name); -void iopf_queue_free(struct iopf_queue *queue); -int iopf_queue_discard_partial(struct iopf_queue *queue); -enum iommu_page_response_code -iommu_sva_handle_iopf(struct iommu_fault *fault, void *data); - -#else /* CONFIG_IOMMU_SVA */ -static inline int iommu_queue_iopf(struct iommu_fault *fault, void *cookie) -{ - return -ENODEV; -} - -static inline int iopf_queue_add_device(struct iopf_queue *queue, - struct device *dev) -{ - return -ENODEV; -} - -static inline int iopf_queue_remove_device(struct iopf_queue *queue, - struct device *dev) -{ - return -ENODEV; -} - -static inline int iopf_queue_flush_dev(struct device *dev) -{ - return -ENODEV; -} - -static inline struct iopf_queue *iopf_queue_alloc(const char *name) -{ - return NULL; -} - -static inline void iopf_queue_free(struct iopf_queue *queue) -{ -} - -static inline int iopf_queue_discard_partial(struct iopf_queue *queue) -{ - return -ENODEV; -} - -static inline enum iommu_page_response_code -iommu_sva_handle_iopf(struct iommu_fault *fault, void *data) -{ - return IOMMU_PAGE_RESP_INVALID; -} -#endif /* CONFIG_IOMMU_SVA */ -#endif /* _IOMMU_SVA_LIB_H */ diff --git a/drivers/iommu/iommu-sva.c b/drivers/iommu/iommu-sva.c new file mode 100644 index 000000000000..24bf9b2b58aa --- /dev/null +++ b/drivers/iommu/iommu-sva.c @@ -0,0 +1,240 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Helpers for IOMMU drivers implementing SVA + */ +#include +#include +#include + +#include "iommu-sva.h" + +static DEFINE_MUTEX(iommu_sva_lock); +static DECLARE_IOASID_SET(iommu_sva_pasid); + +/** + * iommu_sva_alloc_pasid - Allocate a PASID for the mm + * @mm: the mm + * @min: minimum PASID value (inclusive) + * @max: maximum PASID value (inclusive) + * + * Try to allocate a PASID for this mm, or take a reference to the existing one + * provided it fits within the [@min, @max] range. On success the PASID is + * available in mm->pasid and will be available for the lifetime of the mm. + * + * Returns 0 on success and < 0 on error. + */ +int iommu_sva_alloc_pasid(struct mm_struct *mm, ioasid_t min, ioasid_t max) +{ + int ret = 0; + ioasid_t pasid; + + if (min == INVALID_IOASID || max == INVALID_IOASID || + min == 0 || max < min) + return -EINVAL; + + mutex_lock(&iommu_sva_lock); + /* Is a PASID already associated with this mm? */ + if (pasid_valid(mm->pasid)) { + if (mm->pasid < min || mm->pasid >= max) + ret = -EOVERFLOW; + goto out; + } + + pasid = ioasid_alloc(&iommu_sva_pasid, min, max, mm); + if (!pasid_valid(pasid)) + ret = -ENOMEM; + else + mm_pasid_set(mm, pasid); +out: + mutex_unlock(&iommu_sva_lock); + return ret; +} +EXPORT_SYMBOL_GPL(iommu_sva_alloc_pasid); + +/* ioasid_find getter() requires a void * argument */ +static bool __mmget_not_zero(void *mm) +{ + return mmget_not_zero(mm); +} + +/** + * iommu_sva_find() - Find mm associated to the given PASID + * @pasid: Process Address Space ID assigned to the mm + * + * On success a reference to the mm is taken, and must be released with mmput(). + * + * Returns the mm corresponding to this PASID, or an error if not found. + */ +struct mm_struct *iommu_sva_find(ioasid_t pasid) +{ + return ioasid_find(&iommu_sva_pasid, pasid, __mmget_not_zero); +} +EXPORT_SYMBOL_GPL(iommu_sva_find); + +/** + * 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 mm_users + * + * Create a bond between device and address space, allowing the device to + * access the mm using the PASID returned by iommu_sva_get_pasid(). If a + * bond already exists between @device and @mm, an additional internal + * 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. + * + * On error, returns an ERR_PTR value. + */ +struct iommu_sva *iommu_sva_bind_device(struct device *dev, struct mm_struct *mm) +{ + struct iommu_domain *domain; + struct iommu_sva *handle; + ioasid_t max_pasids; + int ret; + + max_pasids = dev->iommu->max_pasids; + if (!max_pasids) + return ERR_PTR(-EOPNOTSUPP); + + /* Allocate mm->pasid if necessary. */ + ret = iommu_sva_alloc_pasid(mm, 1, max_pasids - 1); + if (ret) + return ERR_PTR(ret); + + handle = kzalloc(sizeof(*handle), GFP_KERNEL); + if (!handle) + return ERR_PTR(-ENOMEM); + + mutex_lock(&iommu_sva_lock); + /* Search for an existing domain. */ + domain = iommu_get_domain_for_dev_pasid(dev, mm->pasid, + IOMMU_DOMAIN_SVA); + if (IS_ERR(domain)) { + ret = PTR_ERR(domain); + goto out_unlock; + } + + if (domain) { + domain->users++; + goto out; + } + + /* Allocate a new domain and set it on device pasid. */ + domain = iommu_sva_domain_alloc(dev, mm); + if (!domain) { + ret = -ENOMEM; + goto out_unlock; + } + + ret = iommu_attach_device_pasid(domain, dev, mm->pasid); + if (ret) + goto out_free_domain; + domain->users = 1; +out: + mutex_unlock(&iommu_sva_lock); + handle->dev = dev; + handle->domain = domain; + + return handle; + +out_free_domain: + iommu_domain_free(domain); +out_unlock: + mutex_unlock(&iommu_sva_lock); + kfree(handle); + + return ERR_PTR(ret); +} +EXPORT_SYMBOL_GPL(iommu_sva_bind_device); + +/** + * iommu_sva_unbind_device() - Remove a bond created with iommu_sva_bind_device + * @handle: the handle returned by iommu_sva_bind_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. + */ +void iommu_sva_unbind_device(struct iommu_sva *handle) +{ + struct iommu_domain *domain = handle->domain; + ioasid_t pasid = domain->mm->pasid; + struct device *dev = handle->dev; + + mutex_lock(&iommu_sva_lock); + if (--domain->users == 0) { + iommu_detach_device_pasid(domain, dev, pasid); + iommu_domain_free(domain); + } + mutex_unlock(&iommu_sva_lock); + kfree(handle); +} +EXPORT_SYMBOL_GPL(iommu_sva_unbind_device); + +u32 iommu_sva_get_pasid(struct iommu_sva *handle) +{ + struct iommu_domain *domain = handle->domain; + + return domain->mm->pasid; +} +EXPORT_SYMBOL_GPL(iommu_sva_get_pasid); + +/* + * I/O page fault handler for SVA + */ +enum iommu_page_response_code +iommu_sva_handle_iopf(struct iommu_fault *fault, void *data) +{ + vm_fault_t ret; + struct vm_area_struct *vma; + struct mm_struct *mm = data; + unsigned int access_flags = 0; + unsigned int fault_flags = FAULT_FLAG_REMOTE; + struct iommu_fault_page_request *prm = &fault->prm; + enum iommu_page_response_code status = IOMMU_PAGE_RESP_INVALID; + + if (!(prm->flags & IOMMU_FAULT_PAGE_REQUEST_PASID_VALID)) + return status; + + if (!mmget_not_zero(mm)) + return status; + + mmap_read_lock(mm); + + vma = find_extend_vma(mm, prm->addr); + if (!vma) + /* Unmapped area */ + goto out_put_mm; + + if (prm->perm & IOMMU_FAULT_PERM_READ) + access_flags |= VM_READ; + + if (prm->perm & IOMMU_FAULT_PERM_WRITE) { + access_flags |= VM_WRITE; + fault_flags |= FAULT_FLAG_WRITE; + } + + if (prm->perm & IOMMU_FAULT_PERM_EXEC) { + access_flags |= VM_EXEC; + fault_flags |= FAULT_FLAG_INSTRUCTION; + } + + if (!(prm->perm & IOMMU_FAULT_PERM_PRIV)) + fault_flags |= FAULT_FLAG_USER; + + if (access_flags & ~vma->vm_flags) + /* Access fault */ + goto out_put_mm; + + ret = handle_mm_fault(vma, prm->addr, fault_flags, NULL); + status = ret & VM_FAULT_ERROR ? IOMMU_PAGE_RESP_INVALID : + IOMMU_PAGE_RESP_SUCCESS; + +out_put_mm: + mmap_read_unlock(mm); + mmput(mm); + + return status; +} diff --git a/drivers/iommu/iommu-sva.h b/drivers/iommu/iommu-sva.h new file mode 100644 index 000000000000..7215a761b962 --- /dev/null +++ b/drivers/iommu/iommu-sva.h @@ -0,0 +1,75 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * SVA library for IOMMU drivers + */ +#ifndef _IOMMU_SVA_H +#define _IOMMU_SVA_H + +#include +#include + +int iommu_sva_alloc_pasid(struct mm_struct *mm, ioasid_t min, ioasid_t max); +struct mm_struct *iommu_sva_find(ioasid_t pasid); + +/* I/O Page fault */ +struct device; +struct iommu_fault; +struct iopf_queue; + +#ifdef CONFIG_IOMMU_SVA +int iommu_queue_iopf(struct iommu_fault *fault, void *cookie); + +int iopf_queue_add_device(struct iopf_queue *queue, struct device *dev); +int iopf_queue_remove_device(struct iopf_queue *queue, + struct device *dev); +int iopf_queue_flush_dev(struct device *dev); +struct iopf_queue *iopf_queue_alloc(const char *name); +void iopf_queue_free(struct iopf_queue *queue); +int iopf_queue_discard_partial(struct iopf_queue *queue); +enum iommu_page_response_code +iommu_sva_handle_iopf(struct iommu_fault *fault, void *data); + +#else /* CONFIG_IOMMU_SVA */ +static inline int iommu_queue_iopf(struct iommu_fault *fault, void *cookie) +{ + return -ENODEV; +} + +static inline int iopf_queue_add_device(struct iopf_queue *queue, + struct device *dev) +{ + return -ENODEV; +} + +static inline int iopf_queue_remove_device(struct iopf_queue *queue, + struct device *dev) +{ + return -ENODEV; +} + +static inline int iopf_queue_flush_dev(struct device *dev) +{ + return -ENODEV; +} + +static inline struct iopf_queue *iopf_queue_alloc(const char *name) +{ + return NULL; +} + +static inline void iopf_queue_free(struct iopf_queue *queue) +{ +} + +static inline int iopf_queue_discard_partial(struct iopf_queue *queue) +{ + return -ENODEV; +} + +static inline enum iommu_page_response_code +iommu_sva_handle_iopf(struct iommu_fault *fault, void *data) +{ + return IOMMU_PAGE_RESP_INVALID; +} +#endif /* CONFIG_IOMMU_SVA */ +#endif /* _IOMMU_SVA_H */ diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c index 9e0fb18e1b34..c50f68b2b656 100644 --- a/drivers/iommu/iommu.c +++ b/drivers/iommu/iommu.c @@ -33,7 +33,7 @@ #include "dma-iommu.h" -#include "iommu-sva-lib.h" +#include "iommu-sva.h" static struct kset *iommu_group_kset; static DEFINE_IDA(iommu_group_ida); -- cgit v1.2.3 From 89395ccedbc153fecbc29342fbb94a6dfadf24cd Mon Sep 17 00:00:00 2001 From: Lu Baolu Date: Tue, 29 Nov 2022 16:29:25 -0400 Subject: iommu: Add device-centric DMA ownership interfaces These complement the group interfaces used by VFIO and are for use by iommufd. The main difference is that multiple devices in the same group can all share the ownership by passing the same ownership pointer. Move the common code into shared functions. Link: https://lore.kernel.org/r/2-v6-a196d26f289e+11787-iommufd_jgg@nvidia.com Tested-by: Nicolin Chen Tested-by: Yi Liu Tested-by: Lixiao Yang Tested-by: Matthew Rosato Reviewed-by: Kevin Tian Reviewed-by: Eric Auger Signed-off-by: Lu Baolu Signed-off-by: Jason Gunthorpe --- drivers/iommu/iommu.c | 121 +++++++++++++++++++++++++++++++++++++++----------- include/linux/iommu.h | 12 +++++ 2 files changed, 107 insertions(+), 26 deletions(-) (limited to 'drivers/iommu/iommu.c') diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c index 6ca377f4fbf9..d69ebba81beb 100644 --- a/drivers/iommu/iommu.c +++ b/drivers/iommu/iommu.c @@ -3108,41 +3108,49 @@ static int __iommu_group_alloc_blocking_domain(struct iommu_group *group) return 0; } +static int __iommu_take_dma_ownership(struct iommu_group *group, void *owner) +{ + int ret; + + if ((group->domain && group->domain != group->default_domain) || + !xa_empty(&group->pasid_array)) + return -EBUSY; + + 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; +} + /** * iommu_group_claim_dma_owner() - Set DMA ownership of a group * @group: The group. * @owner: Caller specified pointer. Used for exclusive ownership. * - * 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. + * 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; - } else { - if ((group->domain && group->domain != group->default_domain) || - !xa_empty(&group->pasid_array)) { - ret = -EBUSY; - goto unlock_out; - } - - ret = __iommu_group_alloc_blocking_domain(group); - if (ret) - goto unlock_out; - - ret = __iommu_group_set_domain(group, group->blocking_domain); - if (ret) - goto unlock_out; - group->owner = owner; } - group->owner_cnt++; + ret = __iommu_take_dma_ownership(group, owner); unlock_out: mutex_unlock(&group->mutex); @@ -3151,30 +3159,91 @@ unlock_out: EXPORT_SYMBOL_GPL(iommu_group_claim_dma_owner); /** - * iommu_group_release_dma_owner() - Release DMA ownership of a group - * @group: The group. + * iommu_device_claim_dma_owner() - Set DMA ownership of a device + * @dev: The device. + * @owner: Caller specified pointer. Used for exclusive ownership. * - * Release the DMA ownership claimed by iommu_group_claim_dma_owner(). + * 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 */ -void iommu_group_release_dma_owner(struct iommu_group *group) +int iommu_device_claim_dma_owner(struct device *dev, void *owner) { - int ret; + struct iommu_group *group = iommu_group_get(dev); + int ret = 0; + + if (!group) + return -ENODEV; + if (WARN_ON(!owner)) + return -EINVAL; mutex_lock(&group->mutex); + if (group->owner_cnt) { + if (group->owner != owner) { + ret = -EPERM; + goto unlock_out; + } + group->owner_cnt++; + goto unlock_out; + } + + ret = __iommu_take_dma_ownership(group, owner); +unlock_out: + mutex_unlock(&group->mutex); + iommu_group_put(group); + + return ret; +} +EXPORT_SYMBOL_GPL(iommu_device_claim_dma_owner); + +static void __iommu_release_dma_ownership(struct iommu_group *group) +{ + int ret; + if (WARN_ON(!group->owner_cnt || !group->owner || !xa_empty(&group->pasid_array))) - goto unlock_out; + return; group->owner_cnt = 0; group->owner = NULL; ret = __iommu_group_set_domain(group, group->default_domain); WARN(ret, "iommu driver failed to attach the default domain"); +} -unlock_out: +/** + * iommu_group_release_dma_owner() - Release DMA ownership of a group + * @dev: The device + * + * 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_group_release_dma_owner); +/** + * iommu_device_release_dma_owner() - Release DMA ownership of a device + * @group: The device. + * + * Release the DMA ownership claimed by iommu_device_claim_dma_owner(). + */ +void iommu_device_release_dma_owner(struct device *dev) +{ + struct iommu_group *group = iommu_group_get(dev); + + mutex_lock(&group->mutex); + if (group->owner_cnt > 1) + group->owner_cnt--; + else + __iommu_release_dma_ownership(group); + mutex_unlock(&group->mutex); + iommu_group_put(group); +} +EXPORT_SYMBOL_GPL(iommu_device_release_dma_owner); + /** * iommu_group_dma_owner_claimed() - Query group dma ownership status * @group: The group. diff --git a/include/linux/iommu.h b/include/linux/iommu.h index a09fd32d8cc2..1690c334e516 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -707,6 +707,9 @@ int iommu_group_claim_dma_owner(struct iommu_group *group, void *owner); void iommu_group_release_dma_owner(struct iommu_group *group); bool iommu_group_dma_owner_claimed(struct iommu_group *group); +int iommu_device_claim_dma_owner(struct device *dev, void *owner); +void iommu_device_release_dma_owner(struct device *dev); + struct iommu_domain *iommu_sva_domain_alloc(struct device *dev, struct mm_struct *mm); int iommu_attach_device_pasid(struct iommu_domain *domain, @@ -1064,6 +1067,15 @@ static inline bool iommu_group_dma_owner_claimed(struct iommu_group *group) return false; } +static inline void iommu_device_release_dma_owner(struct device *dev) +{ +} + +static inline int iommu_device_claim_dma_owner(struct device *dev, void *owner) +{ + return -ENODEV; +} + static inline struct iommu_domain * iommu_sva_domain_alloc(struct device *dev, struct mm_struct *mm) { -- cgit v1.2.3