diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2022-12-14 09:15:43 -0800 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2022-12-14 09:15:43 -0800 |
commit | 08cdc2157966c07d3f986a097ddaa74cee312751 (patch) | |
tree | dad2562768b49876c642c2505813e90a467ae40a /drivers/iommu/intel/svm.c | |
parent | aa5ad10f6cca6d42f3fef6cb862e03b220ea19a6 (diff) | |
parent | d6c55c0a20e5059abdde81713ddf6324a946eb3c (diff) | |
download | linux-stable-08cdc2157966c07d3f986a097ddaa74cee312751.tar.gz linux-stable-08cdc2157966c07d3f986a097ddaa74cee312751.tar.bz2 linux-stable-08cdc2157966c07d3f986a097ddaa74cee312751.zip |
Merge tag 'for-linus-iommufd' of git://git.kernel.org/pub/scm/linux/kernel/git/jgg/iommufd
Pull iommufd implementation from Jason Gunthorpe:
"iommufd is the user API to control the IOMMU subsystem as it relates
to managing IO page tables that point at user space memory.
It takes over from drivers/vfio/vfio_iommu_type1.c (aka the VFIO
container) which is the VFIO specific interface for a similar idea.
We see a broad need for extended features, some being highly IOMMU
device specific:
- Binding iommu_domain's to PASID/SSID
- Userspace IO page tables, for ARM, x86 and S390
- Kernel bypassed invalidation of user page tables
- Re-use of the KVM page table in the IOMMU
- Dirty page tracking in the IOMMU
- Runtime Increase/Decrease of IOPTE size
- PRI support with faults resolved in userspace
Many of these HW features exist to support VM use cases - for instance
the combination of PASID, PRI and Userspace IO Page Tables allows an
implementation of DMA Shared Virtual Addressing (vSVA) within a guest.
Dirty tracking enables VM live migration with SRIOV devices and PASID
support allow creating "scalable IOV" devices, among other things.
As these features are fundamental to a VM platform they need to be
uniformly exposed to all the driver families that do DMA into VMs,
which is currently VFIO and VDPA"
For more background, see the extended explanations in Jason's pull request:
https://lore.kernel.org/lkml/Y5dzTU8dlmXTbzoJ@nvidia.com/
* tag 'for-linus-iommufd' of git://git.kernel.org/pub/scm/linux/kernel/git/jgg/iommufd: (62 commits)
iommufd: Change the order of MSI setup
iommufd: Improve a few unclear bits of code
iommufd: Fix comment typos
vfio: Move vfio group specific code into group.c
vfio: Refactor dma APIs for emulated devices
vfio: Wrap vfio group module init/clean code into helpers
vfio: Refactor vfio_device open and close
vfio: Make vfio_device_open() truly device specific
vfio: Swap order of vfio_device_container_register() and open_device()
vfio: Set device->group in helper function
vfio: Create wrappers for group register/unregister
vfio: Move the sanity check of the group to vfio_create_group()
vfio: Simplify vfio_create_group()
iommufd: Allow iommufd to supply /dev/vfio/vfio
vfio: Make vfio_container optionally compiled
vfio: Move container related MODULE_ALIAS statements into container.c
vfio-iommufd: Support iommufd for emulated VFIO devices
vfio-iommufd: Support iommufd for physical VFIO devices
vfio-iommufd: Allow iommufd to be used in place of a container fd
vfio: Use IOMMU_CAP_ENFORCE_CACHE_COHERENCY for vfio_file_enforced_coherent()
...
Diffstat (limited to 'drivers/iommu/intel/svm.c')
-rw-r--r-- | drivers/iommu/intel/svm.c | 145 |
1 files changed, 57 insertions, 88 deletions
diff --git a/drivers/iommu/intel/svm.c b/drivers/iommu/intel/svm.c index 03b25358946c..c76b66263467 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); @@ -299,19 +299,9 @@ out: return 0; } -static int intel_svm_alloc_pasid(struct device *dev, struct mm_struct *mm, - unsigned int flags) -{ - ioasid_t max_pasid = dev_is_pci(dev) ? - pci_max_pasids(to_pci_dev(dev)) : intel_pasid_max_id; - - return iommu_sva_alloc_pasid(mm, PASID_MIN, max_pasid - 1); -} - 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; @@ -327,22 +317,18 @@ 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); } @@ -377,9 +363,7 @@ 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) @@ -393,8 +377,7 @@ 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); } @@ -787,67 +770,6 @@ prq_advance: return IRQ_RETVAL(handled); } -struct iommu_sva *intel_svm_bind(struct device *dev, struct mm_struct *mm, void *drvdata) -{ - 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); - if (ret) { - mutex_unlock(&pasid_mutex); - return ERR_PTR(ret); - } - - sva = intel_svm_bind_mm(iommu, dev, mm, flags); - mutex_unlock(&pasid_mutex); - - return sva; -} - -void intel_svm_unbind(struct iommu_sva *sva) -{ - struct intel_svm_dev *sdev = to_intel_svm_dev(sva); - - mutex_lock(&pasid_mutex); - intel_svm_unbind_mm(sdev->dev, sdev->pasid); - mutex_unlock(&pasid_mutex); -} - -u32 intel_svm_get_pasid(struct iommu_sva *sva) -{ - struct intel_svm_dev *sdev; - u32 pasid; - - mutex_lock(&pasid_mutex); - sdev = to_intel_svm_dev(sva); - pasid = sdev->pasid; - mutex_unlock(&pasid_mutex); - - return pasid; -} - int intel_svm_page_response(struct device *dev, struct iommu_fault_event *evt, struct iommu_page_response *msg) @@ -918,3 +840,50 @@ int intel_svm_page_response(struct device *dev, out: return ret; } + +void intel_svm_remove_dev_pasid(struct device *dev, ioasid_t pasid) +{ + mutex_lock(&pasid_mutex); + intel_svm_unbind_mm(dev, pasid); + mutex_unlock(&pasid_mutex); +} + +static int intel_svm_set_dev_pasid(struct iommu_domain *domain, + struct device *dev, ioasid_t pasid) +{ + struct device_domain_info *info = dev_iommu_priv_get(dev); + struct intel_iommu *iommu = info->iommu; + struct mm_struct *mm = domain->mm; + struct iommu_sva *sva; + int ret = 0; + + mutex_lock(&pasid_mutex); + sva = intel_svm_bind_mm(iommu, dev, mm); + if (IS_ERR(sva)) + ret = PTR_ERR(sva); + mutex_unlock(&pasid_mutex); + + return ret; +} + +static void intel_svm_domain_free(struct iommu_domain *domain) +{ + kfree(to_dmar_domain(domain)); +} + +static const struct iommu_domain_ops intel_svm_domain_ops = { + .set_dev_pasid = intel_svm_set_dev_pasid, + .free = intel_svm_domain_free +}; + +struct iommu_domain *intel_svm_domain_alloc(void) +{ + struct dmar_domain *domain; + + domain = kzalloc(sizeof(*domain), GFP_KERNEL); + if (!domain) + return NULL; + domain->domain.ops = &intel_svm_domain_ops; + + return &domain->domain; +} |