X-Git-Url: https://gerrit.opnfv.org/gerrit/gitweb?a=blobdiff_plain;f=kernel%2Fdrivers%2Fiommu%2Fintel-iommu.c;fp=kernel%2Fdrivers%2Fiommu%2Fintel-iommu.c;h=9413b07262371b205588c35e53ffd38580a01b06;hb=52f993b8e89487ec9ee15a7fb4979e0f09a45b27;hp=a2e1b7f14df29cc78b625ec88455438d0fa1fe07;hpb=c189ccac5702322ed843fe17057035b7222a59b6;p=kvmfornfv.git diff --git a/kernel/drivers/iommu/intel-iommu.c b/kernel/drivers/iommu/intel-iommu.c index a2e1b7f14..9413b0726 100644 --- a/kernel/drivers/iommu/intel-iommu.c +++ b/kernel/drivers/iommu/intel-iommu.c @@ -885,7 +885,13 @@ static struct intel_iommu *device_to_iommu(struct device *dev, u8 *bus, u8 *devf return NULL; if (dev_is_pci(dev)) { + struct pci_dev *pf_pdev; + pdev = to_pci_dev(dev); + /* VFs aren't listed in scope tables; we need to look up + * the PF instead to find the IOMMU. */ + pf_pdev = pci_physfn(pdev); + dev = &pf_pdev->dev; segment = pci_domain_nr(pdev->bus); } else if (has_acpi_companion(dev)) dev = &ACPI_COMPANION(dev)->dev; @@ -898,6 +904,13 @@ static struct intel_iommu *device_to_iommu(struct device *dev, u8 *bus, u8 *devf for_each_active_dev_scope(drhd->devices, drhd->devices_cnt, i, tmp) { if (tmp == dev) { + /* For a VF use its original BDF# not that of the PF + * which we used for the IOMMU lookup. Strictly speaking + * we could do this for all PCI devices; we only need to + * get the BDF# from the scope table for ACPI matches. */ + if (pdev->is_virtfn) + goto got_pdev; + *bus = drhd->devices[i].bus; *devfn = drhd->devices[i].devfn; goto out; @@ -1672,6 +1685,7 @@ static void disable_dmar_iommu(struct intel_iommu *iommu) if (!iommu->domains || !iommu->domain_ids) return; +again: spin_lock_irqsave(&device_domain_lock, flags); list_for_each_entry_safe(info, tmp, &device_domain_list, global) { struct dmar_domain *domain; @@ -1684,10 +1698,19 @@ static void disable_dmar_iommu(struct intel_iommu *iommu) domain = info->domain; - dmar_remove_one_dev_info(domain, info->dev); + __dmar_remove_one_dev_info(info); - if (!domain_type_is_vm_or_si(domain)) + if (!domain_type_is_vm_or_si(domain)) { + /* + * The domain_exit() function can't be called under + * device_domain_lock, as it takes this lock itself. + * So release the lock here and re-run the loop + * afterwards. + */ + spin_unlock_irqrestore(&device_domain_lock, flags); domain_exit(domain); + goto again; + } } spin_unlock_irqrestore(&device_domain_lock, flags); @@ -1970,6 +1993,25 @@ static int domain_context_mapping_one(struct dmar_domain *domain, if (context_present(context)) goto out_unlock; + /* + * For kdump cases, old valid entries may be cached due to the + * in-flight DMA and copied pgtable, but there is no unmapping + * behaviour for them, thus we need an explicit cache flush for + * the newly-mapped device. For kdump, at this point, the device + * is supposed to finish reset at its driver probe stage, so no + * in-flight DMA will exist, and we don't need to worry anymore + * hereafter. + */ + if (context_copied(context)) { + u16 did_old = context_domain_id(context); + + if (did_old >= 0 && did_old < cap_ndoms(iommu->cap)) + iommu->flush.flush_context(iommu, did_old, + (((u16)bus) << 8) | devfn, + DMA_CCMD_MASK_NOBIT, + DMA_CCMD_DEVICE_INVL); + } + pgd = domain->pgd; context_clear_entry(context); @@ -2032,7 +2074,7 @@ out_unlock: spin_unlock(&iommu->lock); spin_unlock_irqrestore(&device_domain_lock, flags); - return 0; + return ret; } struct domain_context_mapping_data { @@ -3169,11 +3211,6 @@ static int __init init_dmars(void) } } - iommu_flush_write_buffer(iommu); - iommu_set_root_entry(iommu); - iommu->flush.flush_context(iommu, 0, 0, 0, DMA_CCMD_GLOBAL_INVL); - iommu->flush.flush_iotlb(iommu, 0, 0, 0, DMA_TLB_GLOBAL_FLUSH); - if (!ecap_pass_through(iommu->ecap)) hw_pass_through = 0; #ifdef CONFIG_INTEL_IOMMU_SVM @@ -3182,6 +3219,18 @@ static int __init init_dmars(void) #endif } + /* + * Now that qi is enabled on all iommus, set the root entry and flush + * caches. This is required on some Intel X58 chipsets, otherwise the + * flush_context function will loop forever and the boot hangs. + */ + for_each_active_iommu(iommu, drhd) { + iommu_flush_write_buffer(iommu); + iommu_set_root_entry(iommu); + iommu->flush.flush_context(iommu, 0, 0, 0, DMA_CCMD_GLOBAL_INVL); + iommu->flush.flush_iotlb(iommu, 0, 0, 0, DMA_TLB_GLOBAL_FLUSH); + } + if (iommu_pass_through) iommu_identity_mapping |= IDENTMAP_ALL; @@ -4175,10 +4224,11 @@ int dmar_check_one_atsr(struct acpi_dmar_header *hdr, void *arg) if (!atsru) return 0; - if (!atsru->include_all && atsru->devices && atsru->devices_cnt) + if (!atsru->include_all && atsru->devices && atsru->devices_cnt) { for_each_active_dev_scope(atsru->devices, atsru->devices_cnt, i, dev) return -EBUSY; + } return 0; } @@ -4989,6 +5039,25 @@ static void intel_iommu_remove_device(struct device *dev) } #ifdef CONFIG_INTEL_IOMMU_SVM +#define MAX_NR_PASID_BITS (20) +static inline unsigned long intel_iommu_get_pts(struct intel_iommu *iommu) +{ + /* + * Convert ecap_pss to extend context entry pts encoding, also + * respect the soft pasid_max value set by the iommu. + * - number of PASID bits = ecap_pss + 1 + * - number of PASID table entries = 2^(pts + 5) + * Therefore, pts = ecap_pss - 4 + * e.g. KBL ecap_pss = 0x13, PASID has 20 bits, pts = 15 + */ + if (ecap_pss(iommu->ecap) < 5) + return 0; + + /* pasid_max is encoded as actual number of entries not the bits */ + return find_first_bit((unsigned long *)&iommu->pasid_max, + MAX_NR_PASID_BITS) - 5; +} + int intel_iommu_enable_pasid(struct intel_iommu *iommu, struct intel_svm_dev *sdev) { struct device_domain_info *info; @@ -5021,7 +5090,9 @@ int intel_iommu_enable_pasid(struct intel_iommu *iommu, struct intel_svm_dev *sd if (!(ctx_lo & CONTEXT_PASIDE)) { context[1].hi = (u64)virt_to_phys(iommu->pasid_state_table); - context[1].lo = (u64)virt_to_phys(iommu->pasid_table) | ecap_pss(iommu->ecap); + context[1].lo = (u64)virt_to_phys(iommu->pasid_table) | + intel_iommu_get_pts(iommu); + wmb(); /* CONTEXT_TT_MULTI_LEVEL and CONTEXT_TT_DEV_IOTLB are both * extended to permit requests-with-PASID if the PASIDE bit