diff options
Diffstat (limited to 'drivers/iommu/intel')
| -rw-r--r-- | drivers/iommu/intel/dmar.c | 8 | ||||
| -rw-r--r-- | drivers/iommu/intel/iommu.c | 154 | ||||
| -rw-r--r-- | drivers/iommu/intel/iommu.h | 23 | ||||
| -rw-r--r-- | drivers/iommu/intel/irq_remapping.c | 52 | ||||
| -rw-r--r-- | drivers/iommu/intel/pasid.c | 11 | ||||
| -rw-r--r-- | drivers/iommu/intel/svm.c | 164 |
6 files changed, 253 insertions, 159 deletions
diff --git a/drivers/iommu/intel/dmar.c b/drivers/iommu/intel/dmar.c index 5a8f780e7ffd..b00a0ceb2d13 100644 --- a/drivers/iommu/intel/dmar.c +++ b/drivers/iommu/intel/dmar.c @@ -820,6 +820,7 @@ int __init dmar_dev_scope_init(void) info = dmar_alloc_pci_notify_info(dev, BUS_NOTIFY_ADD_DEVICE); if (!info) { + pci_dev_put(dev); return dmar_dev_scope_status; } else { dmar_pci_bus_add_dev(info); @@ -1105,6 +1106,13 @@ static int alloc_iommu(struct dmar_drhd_unit *drhd) raw_spin_lock_init(&iommu->register_lock); /* + * A value of N in PSS field of eCap register indicates hardware + * supports PASID field of N+1 bits. + */ + if (pasid_supported(iommu)) + iommu->iommu.max_pasids = 2UL << ecap_pss(iommu->ecap); + + /* * This is only for hotplug; at boot time intel_iommu_enabled won't * be set yet. When intel_iommu_init() runs, it registers the units * present at boot time, then sets intel_iommu_enabled. diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c index a8b36c3fddf1..bef8e8f7ca25 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" @@ -959,11 +959,9 @@ static struct dma_pte *pfn_to_dma_pte(struct dmar_domain *domain, domain_flush_cache(domain, tmp_page, VTD_PAGE_SIZE); pteval = ((uint64_t)virt_to_dma_pfn(tmp_page) << VTD_PAGE_SHIFT) | DMA_PTE_READ | DMA_PTE_WRITE; - if (domain_use_first_level(domain)) { - pteval |= DMA_FL_PTE_XD | DMA_FL_PTE_US; - if (iommu_is_dma_domain(&domain->domain)) - pteval |= DMA_FL_PTE_ACCESS; - } + if (domain_use_first_level(domain)) + pteval |= DMA_FL_PTE_XD | DMA_FL_PTE_US | DMA_FL_PTE_ACCESS; + if (cmpxchg64(&pte->val, 0ULL, pteval)) /* Someone else set it while we were thinking; use theirs. */ free_pgtable_page(tmp_page); @@ -1398,6 +1396,24 @@ static void domain_update_iotlb(struct dmar_domain *domain) spin_unlock_irqrestore(&domain->lock, flags); } +/* + * The extra devTLB flush quirk impacts those QAT devices with PCI device + * IDs ranging from 0x4940 to 0x4943. It is exempted from risky_device() + * check because it applies only to the built-in QAT devices and it doesn't + * grant additional privileges. + */ +#define BUGGY_QAT_DEVID_MASK 0x4940 +static bool dev_needs_extra_dtlb_flush(struct pci_dev *pdev) +{ + if (pdev->vendor != PCI_VENDOR_ID_INTEL) + return false; + + if ((pdev->device & 0xfffc) != BUGGY_QAT_DEVID_MASK) + return false; + + return true; +} + static void iommu_enable_pci_caps(struct device_domain_info *info) { struct pci_dev *pdev; @@ -1480,6 +1496,7 @@ static void __iommu_flush_dev_iotlb(struct device_domain_info *info, qdep = info->ats_qdep; qi_flush_dev_iotlb(info->iommu, sid, info->pfsid, qdep, addr, mask); + quirk_extra_dev_tlb_flush(info, addr, mask, PASID_RID2PASID, qdep); } static void iommu_flush_dev_iotlb(struct dmar_domain *domain, @@ -2410,6 +2427,7 @@ static int __init si_domain_init(int hw) if (md_domain_init(si_domain, DEFAULT_DOMAIN_ADDRESS_WIDTH)) { domain_exit(si_domain); + si_domain = NULL; return -EFAULT; } @@ -3052,6 +3070,10 @@ free_iommu: disable_dmar_iommu(iommu); free_dmar_iommu(iommu); } + if (si_domain) { + domain_exit(si_domain); + si_domain = NULL; + } return ret; } @@ -3851,8 +3873,10 @@ static inline bool has_external_pci(void) struct pci_dev *pdev = NULL; for_each_pci_dev(pdev) - if (pdev->external_facing) + if (pdev->external_facing) { + pci_dev_put(pdev); return true; + } return false; } @@ -4164,6 +4188,8 @@ static struct iommu_domain *intel_iommu_domain_alloc(unsigned type) return domain; case IOMMU_DOMAIN_IDENTITY: return &si_domain->domain; + case IOMMU_DOMAIN_SVA: + return intel_svm_domain_alloc(); default: return NULL; } @@ -4189,19 +4215,15 @@ static int prepare_domain_attach_device(struct iommu_domain *domain, return -ENODEV; if (dmar_domain->force_snooping && !ecap_sc_support(iommu->ecap)) - return -EOPNOTSUPP; + return -EINVAL; /* check if this iommu agaw is sufficient for max mapped address */ addr_width = agaw_to_width(iommu->agaw); if (addr_width > cap_mgaw(iommu->cap)) addr_width = cap_mgaw(iommu->cap); - if (dmar_domain->max_addr > (1LL << addr_width)) { - dev_err(dev, "%s: iommu width (%d) is not " - "sufficient for the mapped address (%llx)\n", - __func__, addr_width, dmar_domain->max_addr); - return -EFAULT; - } + if (dmar_domain->max_addr > (1LL << addr_width)) + return -EINVAL; dmar_domain->gaw = addr_width; /* @@ -4447,14 +4469,20 @@ static bool intel_iommu_enforce_cache_coherency(struct iommu_domain *domain) static bool intel_iommu_capable(struct device *dev, enum iommu_cap cap) { - if (cap == IOMMU_CAP_CACHE_COHERENCY) + struct device_domain_info *info = dev_iommu_priv_get(dev); + + switch (cap) { + case IOMMU_CAP_CACHE_COHERENCY: return true; - if (cap == IOMMU_CAP_INTR_REMAP) + case IOMMU_CAP_INTR_REMAP: return irq_remapping_enabled == 1; - if (cap == IOMMU_CAP_PRE_BOOT_PROTECTION) + case IOMMU_CAP_PRE_BOOT_PROTECTION: return dmar_platform_optin(); - - return false; + case IOMMU_CAP_ENFORCE_CACHE_COHERENCY: + return ecap_sc_support(info->iommu->ecap); + default: + return false; + } } static struct iommu_device *intel_iommu_probe_device(struct device *dev) @@ -4487,9 +4515,10 @@ static struct iommu_device *intel_iommu_probe_device(struct device *dev) if (dev_is_pci(dev)) { if (ecap_dev_iotlb_support(iommu->ecap) && pci_ats_supported(pdev) && - dmar_ats_supported(pdev, iommu)) + dmar_ats_supported(pdev, iommu)) { info->ats_supported = 1; - + info->dtlb_extra_inval = dev_needs_extra_dtlb_flush(pdev); + } if (sm_supported(iommu)) { if (pasid_supported(iommu)) { int features = pci_pasid_features(pdev); @@ -4534,7 +4563,7 @@ static void intel_iommu_get_resv_regions(struct device *device, struct device *i_dev; int i; - down_read(&dmar_global_lock); + rcu_read_lock(); for_each_rmrr_units(rmrr) { for_each_active_dev_scope(rmrr->devices, rmrr->devices_cnt, i, i_dev) { @@ -4552,14 +4581,15 @@ static void intel_iommu_get_resv_regions(struct device *device, IOMMU_RESV_DIRECT_RELAXABLE : IOMMU_RESV_DIRECT; resv = iommu_alloc_resv_region(rmrr->base_address, - length, prot, type); + length, prot, type, + GFP_ATOMIC); if (!resv) break; list_add_tail(&resv->list, head); } } - up_read(&dmar_global_lock); + rcu_read_unlock(); #ifdef CONFIG_INTEL_IOMMU_FLOPPY_WA if (dev_is_pci(device)) { @@ -4567,7 +4597,8 @@ static void intel_iommu_get_resv_regions(struct device *device, if ((pdev->class >> 8) == PCI_CLASS_BRIDGE_ISA) { reg = iommu_alloc_resv_region(0, 1UL << 24, prot, - IOMMU_RESV_DIRECT_RELAXABLE); + IOMMU_RESV_DIRECT_RELAXABLE, + GFP_KERNEL); if (reg) list_add_tail(®->list, head); } @@ -4576,7 +4607,7 @@ static void intel_iommu_get_resv_regions(struct device *device, reg = iommu_alloc_resv_region(IOAPIC_RANGE_START, IOAPIC_RANGE_END - IOAPIC_RANGE_START + 1, - 0, IOMMU_RESV_MSI); + 0, IOMMU_RESV_MSI, GFP_KERNEL); if (!reg) return; list_add_tail(®->list, head); @@ -4705,6 +4736,28 @@ static void intel_iommu_iotlb_sync_map(struct iommu_domain *domain, __mapping_notify_one(info->iommu, dmar_domain, pfn, pages); } +static void intel_iommu_remove_dev_pasid(struct device *dev, ioasid_t pasid) +{ + struct intel_iommu *iommu = device_to_iommu(dev, NULL, NULL); + struct iommu_domain *domain; + + /* Domain type specific cleanup: */ + domain = iommu_get_domain_for_dev_pasid(dev, pasid, 0); + if (domain) { + switch (domain->type) { + case IOMMU_DOMAIN_SVA: + intel_svm_remove_dev_pasid(dev, pasid); + break; + default: + /* should never reach here */ + WARN_ON(1); + break; + } + } + + intel_pasid_tear_down_entry(iommu, dev, pasid, false); +} + const struct iommu_ops intel_iommu_ops = { .capable = intel_iommu_capable, .domain_alloc = intel_iommu_domain_alloc, @@ -4717,11 +4770,9 @@ const struct iommu_ops intel_iommu_ops = { .dev_disable_feat = intel_iommu_dev_disable_feat, .is_attach_deferred = intel_iommu_is_attach_deferred, .def_domain_type = device_def_domain_type, + .remove_dev_pasid = intel_iommu_remove_dev_pasid, .pgsize_bitmap = SZ_4K, #ifdef CONFIG_INTEL_IOMMU_SVM - .sva_bind = intel_svm_bind, - .sva_unbind = intel_svm_unbind, - .sva_get_pasid = intel_svm_get_pasid, .page_response = intel_svm_page_response, #endif .default_domain_ops = &(const struct iommu_domain_ops) { @@ -4926,3 +4977,48 @@ static void __init check_tylersburg_isoch(void) pr_warn("Recommended TLB entries for ISOCH unit is 16; your BIOS set %d\n", vtisochctrl); } + +/* + * Here we deal with a device TLB defect where device may inadvertently issue ATS + * invalidation completion before posted writes initiated with translated address + * that utilized translations matching the invalidation address range, violating + * the invalidation completion ordering. + * Therefore, any use cases that cannot guarantee DMA is stopped before unmap is + * vulnerable to this defect. In other words, any dTLB invalidation initiated not + * under the control of the trusted/privileged host device driver must use this + * quirk. + * Device TLBs are invalidated under the following six conditions: + * 1. Device driver does DMA API unmap IOVA + * 2. Device driver unbind a PASID from a process, sva_unbind_device() + * 3. PASID is torn down, after PASID cache is flushed. e.g. process + * exit_mmap() due to crash + * 4. Under SVA usage, called by mmu_notifier.invalidate_range() where + * VM has to free pages that were unmapped + * 5. Userspace driver unmaps a DMA buffer + * 6. Cache invalidation in vSVA usage (upcoming) + * + * For #1 and #2, device drivers are responsible for stopping DMA traffic + * before unmap/unbind. For #3, iommu driver gets mmu_notifier to + * invalidate TLB the same way as normal user unmap which will use this quirk. + * The dTLB invalidation after PASID cache flush does not need this quirk. + * + * As a reminder, #6 will *NEED* this quirk as we enable nested translation. + */ +void quirk_extra_dev_tlb_flush(struct device_domain_info *info, + unsigned long address, unsigned long mask, + u32 pasid, u16 qdep) +{ + u16 sid; + + if (likely(!info->dtlb_extra_inval)) + return; + + sid = PCI_DEVID(info->bus, info->devfn); + if (pasid == PASID_RID2PASID) { + qi_flush_dev_iotlb(info->iommu, sid, info->pfsid, + qdep, address, mask); + } else { + qi_flush_dev_iotlb_pasid(info->iommu, sid, info->pfsid, + pasid, qdep, address, mask); + } +} diff --git a/drivers/iommu/intel/iommu.h b/drivers/iommu/intel/iommu.h index 92023dff9513..f83ad8ddcf4d 100644 --- a/drivers/iommu/intel/iommu.h +++ b/drivers/iommu/intel/iommu.h @@ -480,8 +480,6 @@ enum { #define VTD_FLAG_IRQ_REMAP_PRE_ENABLED (1 << 1) #define VTD_FLAG_SVM_CAPABLE (1 << 2) -extern int intel_iommu_sm; - #define sm_supported(iommu) (intel_iommu_sm && ecap_smts((iommu)->ecap)) #define pasid_supported(iommu) (sm_supported(iommu) && \ ecap_pasid((iommu)->ecap)) @@ -600,7 +598,6 @@ struct intel_iommu { #ifdef CONFIG_IRQ_REMAP struct ir_table *ir_table; /* Interrupt remapping info */ struct irq_domain *ir_domain; - struct irq_domain *ir_msi_domain; #endif struct iommu_device iommu; /* IOMMU core code handle */ int node; @@ -623,6 +620,7 @@ struct device_domain_info { u8 pri_enabled:1; u8 ats_supported:1; u8 ats_enabled:1; + u8 dtlb_extra_inval:1; /* Quirk for devices need extra flush */ u8 ats_qdep; struct device *dev; /* it's NULL for PCIe-to-PCI bridge */ struct intel_iommu *iommu; /* IOMMU used by this device */ @@ -728,6 +726,9 @@ void qi_flush_piotlb(struct intel_iommu *iommu, u16 did, u32 pasid, u64 addr, void qi_flush_dev_iotlb_pasid(struct intel_iommu *iommu, u16 sid, u16 pfsid, u32 pasid, u16 qdep, u64 addr, unsigned int size_order); +void quirk_extra_dev_tlb_flush(struct device_domain_info *info, + unsigned long address, unsigned long pages, + u32 pasid, u16 qdep); void qi_flush_pasid_cache(struct intel_iommu *iommu, u16 did, u64 granu, u32 pasid); @@ -750,12 +751,10 @@ 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); -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, struct iommu_page_response *msg); +struct iommu_domain *intel_svm_domain_alloc(void); +void intel_svm_remove_dev_pasid(struct device *dev, ioasid_t pasid); struct intel_svm_dev { struct list_head list; @@ -780,6 +779,14 @@ struct intel_svm { }; #else static inline void intel_svm_check(struct intel_iommu *iommu) {} +static inline struct iommu_domain *intel_svm_domain_alloc(void) +{ + return NULL; +} + +static inline void intel_svm_remove_dev_pasid(struct device *dev, ioasid_t pasid) +{ +} #endif #ifdef CONFIG_INTEL_IOMMU_DEBUGFS @@ -795,6 +802,7 @@ struct context_entry *iommu_context_addr(struct intel_iommu *iommu, u8 bus, extern const struct iommu_ops intel_iommu_ops; #ifdef CONFIG_INTEL_IOMMU +extern int intel_iommu_sm; extern int iommu_calculate_agaw(struct intel_iommu *iommu); extern int iommu_calculate_max_sagaw(struct intel_iommu *iommu); extern int dmar_disabled; @@ -810,6 +818,7 @@ static inline int iommu_calculate_max_sagaw(struct intel_iommu *iommu) } #define dmar_disabled (1) #define intel_iommu_enabled (0) +#define intel_iommu_sm (0) #endif static inline const char *decode_prq_descriptor(char *str, size_t size, diff --git a/drivers/iommu/intel/irq_remapping.c b/drivers/iommu/intel/irq_remapping.c index 5962bb5027d0..a723f53ba472 100644 --- a/drivers/iommu/intel/irq_remapping.c +++ b/drivers/iommu/intel/irq_remapping.c @@ -82,6 +82,7 @@ static const struct irq_domain_ops intel_ir_domain_ops; static void iommu_disable_irq_remapping(struct intel_iommu *iommu); static int __init parse_ioapics_under_ir(void); +static const struct msi_parent_ops dmar_msi_parent_ops, virt_dmar_msi_parent_ops; static bool ir_pre_enabled(struct intel_iommu *iommu) { @@ -230,7 +231,7 @@ static struct irq_domain *map_dev_to_ir(struct pci_dev *dev) { struct dmar_drhd_unit *drhd = dmar_find_matched_drhd_unit(dev); - return drhd ? drhd->iommu->ir_msi_domain : NULL; + return drhd ? drhd->iommu->ir_domain : NULL; } static int clear_entries(struct irq_2_iommu *irq_iommu) @@ -573,10 +574,14 @@ static int intel_setup_irq_remapping(struct intel_iommu *iommu) pr_err("IR%d: failed to allocate irqdomain\n", iommu->seq_id); goto out_free_fwnode; } - iommu->ir_msi_domain = - arch_create_remap_msi_irq_domain(iommu->ir_domain, - "INTEL-IR-MSI", - iommu->seq_id); + + irq_domain_update_bus_token(iommu->ir_domain, DOMAIN_BUS_DMAR); + iommu->ir_domain->flags |= IRQ_DOMAIN_FLAG_MSI_PARENT; + + if (cap_caching_mode(iommu->cap)) + iommu->ir_domain->msi_parent_ops = &virt_dmar_msi_parent_ops; + else + iommu->ir_domain->msi_parent_ops = &dmar_msi_parent_ops; ir_table->base = page_address(pages); ir_table->bitmap = bitmap; @@ -620,9 +625,6 @@ static int intel_setup_irq_remapping(struct intel_iommu *iommu) return 0; out_free_ir_domain: - if (iommu->ir_msi_domain) - irq_domain_remove(iommu->ir_msi_domain); - iommu->ir_msi_domain = NULL; irq_domain_remove(iommu->ir_domain); iommu->ir_domain = NULL; out_free_fwnode: @@ -644,13 +646,6 @@ static void intel_teardown_irq_remapping(struct intel_iommu *iommu) struct fwnode_handle *fn; if (iommu && iommu->ir_table) { - if (iommu->ir_msi_domain) { - fn = iommu->ir_msi_domain->fwnode; - - irq_domain_remove(iommu->ir_msi_domain); - irq_domain_free_fwnode(fn); - iommu->ir_msi_domain = NULL; - } if (iommu->ir_domain) { fn = iommu->ir_domain->fwnode; @@ -1107,7 +1102,7 @@ error: */ void intel_irq_remap_add_device(struct dmar_pci_notify_info *info) { - if (!irq_remapping_enabled || pci_dev_has_special_msi_domain(info->dev)) + if (!irq_remapping_enabled || !pci_dev_has_default_msi_parent_domain(info->dev)) return; dev_set_msi_domain(&info->dev->dev, map_dev_to_ir(info->dev)); @@ -1334,17 +1329,9 @@ static int intel_irq_remapping_alloc(struct irq_domain *domain, if (!info || !iommu) return -EINVAL; - if (nr_irqs > 1 && info->type != X86_IRQ_ALLOC_TYPE_PCI_MSI && - info->type != X86_IRQ_ALLOC_TYPE_PCI_MSIX) + if (nr_irqs > 1 && info->type != X86_IRQ_ALLOC_TYPE_PCI_MSI) return -EINVAL; - /* - * With IRQ remapping enabled, don't need contiguous CPU vectors - * to support multiple MSI interrupts. - */ - if (info->type == X86_IRQ_ALLOC_TYPE_PCI_MSI) - info->flags &= ~X86_IRQ_ALLOC_CONTIGUOUS_VECTORS; - ret = irq_domain_alloc_irqs_parent(domain, virq, nr_irqs, arg); if (ret < 0) return ret; @@ -1445,6 +1432,21 @@ static const struct irq_domain_ops intel_ir_domain_ops = { .deactivate = intel_irq_remapping_deactivate, }; +static const struct msi_parent_ops dmar_msi_parent_ops = { + .supported_flags = X86_VECTOR_MSI_FLAGS_SUPPORTED | + MSI_FLAG_MULTI_PCI_MSI | + MSI_FLAG_PCI_IMS, + .prefix = "IR-", + .init_dev_msi_info = msi_parent_init_dev_msi_info, +}; + +static const struct msi_parent_ops virt_dmar_msi_parent_ops = { + .supported_flags = X86_VECTOR_MSI_FLAGS_SUPPORTED | + MSI_FLAG_MULTI_PCI_MSI, + .prefix = "vIR-", + .init_dev_msi_info = msi_parent_init_dev_msi_info, +}; + /* * Support of Interrupt Remapping Unit Hotplug */ diff --git a/drivers/iommu/intel/pasid.c b/drivers/iommu/intel/pasid.c index c30ddac40ee5..fb3c7020028d 100644 --- a/drivers/iommu/intel/pasid.c +++ b/drivers/iommu/intel/pasid.c @@ -101,8 +101,10 @@ int intel_pasid_alloc_table(struct device *dev) might_sleep(); info = dev_iommu_priv_get(dev); - if (WARN_ON(!info || !dev_is_pci(dev) || info->pasid_table)) - return -EINVAL; + if (WARN_ON(!info || !dev_is_pci(dev))) + return -ENODEV; + if (WARN_ON(info->pasid_table)) + return -EEXIST; pasid_table = kzalloc(sizeof(*pasid_table), GFP_KERNEL); if (!pasid_table) @@ -642,7 +644,7 @@ int intel_pasid_setup_second_level(struct intel_iommu *iommu, * Since it is a second level only translation setup, we should * set SRE bit as well (addresses are expected to be GPAs). */ - if (pasid != PASID_RID2PASID) + if (pasid != PASID_RID2PASID && ecap_srs(iommu->ecap)) pasid_set_sre(pte); pasid_set_present(pte); spin_unlock(&iommu->lock); @@ -685,7 +687,8 @@ int intel_pasid_setup_pass_through(struct intel_iommu *iommu, * We should set SRE bit as well since the addresses are expected * to be GPAs. */ - pasid_set_sre(pte); + if (ecap_srs(iommu->ecap)) + pasid_set_sre(pte); pasid_set_present(pte); spin_unlock(&iommu->lock); diff --git a/drivers/iommu/intel/svm.c b/drivers/iommu/intel/svm.c index 7d08eb034f2d..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); @@ -184,10 +184,13 @@ static void __flush_svm_range_dev(struct intel_svm *svm, return; qi_flush_piotlb(sdev->iommu, sdev->did, svm->pasid, address, pages, ih); - if (info->ats_enabled) + if (info->ats_enabled) { qi_flush_dev_iotlb_pasid(sdev->iommu, sdev->sid, info->pfsid, svm->pasid, sdev->qdep, address, order_base_2(pages)); + quirk_extra_dev_tlb_flush(info, address, order_base_2(pages), + svm->pasid, sdev->qdep); + } } static void intel_flush_svm_range_dev(struct intel_svm *svm, @@ -296,19 +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; @@ -324,22 +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); } @@ -374,9 +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) @@ -390,8 +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); } @@ -745,12 +731,16 @@ bad_req: * If prq is to be handled outside iommu driver via receiver of * the fault notifiers, we skip the page response here. */ - if (!pdev || intel_svm_prq_report(iommu, &pdev->dev, req)) - handle_bad_prq_event(iommu, req, QI_RESP_INVALID); + if (!pdev) + goto bad_req; - trace_prq_report(iommu, &pdev->dev, req->qw_0, req->qw_1, - req->priv_data[0], req->priv_data[1], - iommu->prq_seq_number++); + if (intel_svm_prq_report(iommu, &pdev->dev, req)) + handle_bad_prq_event(iommu, req, QI_RESP_INVALID); + else + trace_prq_report(iommu, &pdev->dev, req->qw_0, req->qw_1, + req->priv_data[0], req->priv_data[1], + iommu->prq_seq_number++); + pci_dev_put(pdev); prq_advance: head = (head + sizeof(*req)) & PRQ_RING_MASK; } @@ -780,67 +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) @@ -911,3 +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; +} |