diff options
Diffstat (limited to 'drivers/iommu/intel/iommu.c')
| -rw-r--r-- | drivers/iommu/intel/iommu.c | 181 |
1 files changed, 139 insertions, 42 deletions
diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c index 788119c5b021..06b00b5363d8 100644 --- a/drivers/iommu/intel/iommu.c +++ b/drivers/iommu/intel/iommu.c @@ -38,7 +38,6 @@ #include <linux/dmi.h> #include <linux/pci-ats.h> #include <linux/memblock.h> -#include <linux/dma-map-ops.h> #include <linux/dma-direct.h> #include <linux/crash_dump.h> #include <linux/numa.h> @@ -719,6 +718,8 @@ static int domain_update_device_node(struct dmar_domain *domain) return nid; } +static void domain_update_iotlb(struct dmar_domain *domain); + /* Some capabilities may be different across iommus */ static void domain_update_iommu_cap(struct dmar_domain *domain) { @@ -744,6 +745,8 @@ static void domain_update_iommu_cap(struct dmar_domain *domain) domain->domain.geometry.aperture_end = __DOMAIN_MAX_ADDR(domain->gaw - 1); else domain->domain.geometry.aperture_end = __DOMAIN_MAX_ADDR(domain->gaw); + + domain_update_iotlb(domain); } struct context_entry *iommu_context_addr(struct intel_iommu *iommu, u8 bus, @@ -1464,17 +1467,22 @@ static void domain_update_iotlb(struct dmar_domain *domain) assert_spin_locked(&device_domain_lock); - list_for_each_entry(info, &domain->devices, link) { - struct pci_dev *pdev; - - if (!info->dev || !dev_is_pci(info->dev)) - continue; - - pdev = to_pci_dev(info->dev); - if (pdev->ats_enabled) { + list_for_each_entry(info, &domain->devices, link) + if (info->ats_enabled) { has_iotlb_device = true; break; } + + if (!has_iotlb_device) { + struct subdev_domain_info *sinfo; + + list_for_each_entry(sinfo, &domain->subdevices, link_domain) { + info = get_domain_info(sinfo->pdev); + if (info && info->ats_enabled) { + has_iotlb_device = true; + break; + } + } } domain->has_iotlb_device = has_iotlb_device; @@ -1555,25 +1563,37 @@ static void iommu_disable_dev_iotlb(struct device_domain_info *info) #endif } +static void __iommu_flush_dev_iotlb(struct device_domain_info *info, + u64 addr, unsigned int mask) +{ + u16 sid, qdep; + + if (!info || !info->ats_enabled) + return; + + sid = info->bus << 8 | info->devfn; + qdep = info->ats_qdep; + qi_flush_dev_iotlb(info->iommu, sid, info->pfsid, + qdep, addr, mask); +} + static void iommu_flush_dev_iotlb(struct dmar_domain *domain, u64 addr, unsigned mask) { - u16 sid, qdep; unsigned long flags; struct device_domain_info *info; + struct subdev_domain_info *sinfo; if (!domain->has_iotlb_device) return; spin_lock_irqsave(&device_domain_lock, flags); - list_for_each_entry(info, &domain->devices, link) { - if (!info->ats_enabled) - continue; + list_for_each_entry(info, &domain->devices, link) + __iommu_flush_dev_iotlb(info, addr, mask); - sid = info->bus << 8 | info->devfn; - qdep = info->ats_qdep; - qi_flush_dev_iotlb(info->iommu, sid, info->pfsid, - qdep, addr, mask); + list_for_each_entry(sinfo, &domain->subdevices, link_domain) { + info = get_domain_info(sinfo->pdev); + __iommu_flush_dev_iotlb(info, addr, mask); } spin_unlock_irqrestore(&device_domain_lock, flags); } @@ -1877,6 +1897,7 @@ static struct dmar_domain *alloc_domain(int flags) domain->flags |= DOMAIN_FLAG_USE_FIRST_LEVEL; domain->has_iotlb_device = false; INIT_LIST_HEAD(&domain->devices); + INIT_LIST_HEAD(&domain->subdevices); return domain; } @@ -2547,7 +2568,7 @@ static struct dmar_domain *dmar_insert_one_dev_info(struct intel_iommu *iommu, info->iommu = iommu; info->pasid_table = NULL; info->auxd_enabled = 0; - INIT_LIST_HEAD(&info->auxiliary_domains); + INIT_LIST_HEAD(&info->subdevices); if (dev && dev_is_pci(dev)) { struct pci_dev *pdev = to_pci_dev(info->dev); @@ -4475,33 +4496,61 @@ is_aux_domain(struct device *dev, struct iommu_domain *domain) domain->type == IOMMU_DOMAIN_UNMANAGED; } -static void auxiliary_link_device(struct dmar_domain *domain, - struct device *dev) +static inline struct subdev_domain_info * +lookup_subdev_info(struct dmar_domain *domain, struct device *dev) +{ + struct subdev_domain_info *sinfo; + + if (!list_empty(&domain->subdevices)) { + list_for_each_entry(sinfo, &domain->subdevices, link_domain) { + if (sinfo->pdev == dev) + return sinfo; + } + } + + return NULL; +} + +static int auxiliary_link_device(struct dmar_domain *domain, + struct device *dev) { struct device_domain_info *info = get_domain_info(dev); + struct subdev_domain_info *sinfo = lookup_subdev_info(domain, dev); assert_spin_locked(&device_domain_lock); if (WARN_ON(!info)) - return; + return -EINVAL; + + if (!sinfo) { + sinfo = kzalloc(sizeof(*sinfo), GFP_ATOMIC); + sinfo->domain = domain; + sinfo->pdev = dev; + list_add(&sinfo->link_phys, &info->subdevices); + list_add(&sinfo->link_domain, &domain->subdevices); + } - domain->auxd_refcnt++; - list_add(&domain->auxd, &info->auxiliary_domains); + return ++sinfo->users; } -static void auxiliary_unlink_device(struct dmar_domain *domain, - struct device *dev) +static int auxiliary_unlink_device(struct dmar_domain *domain, + struct device *dev) { struct device_domain_info *info = get_domain_info(dev); + struct subdev_domain_info *sinfo = lookup_subdev_info(domain, dev); + int ret; assert_spin_locked(&device_domain_lock); - if (WARN_ON(!info)) - return; + if (WARN_ON(!info || !sinfo || sinfo->users <= 0)) + return -EINVAL; - list_del(&domain->auxd); - domain->auxd_refcnt--; + ret = --sinfo->users; + if (!ret) { + list_del(&sinfo->link_phys); + list_del(&sinfo->link_domain); + kfree(sinfo); + } - if (!domain->auxd_refcnt && domain->default_pasid > 0) - ioasid_put(domain->default_pasid); + return ret; } static int aux_domain_add_dev(struct dmar_domain *domain, @@ -4530,6 +4579,19 @@ static int aux_domain_add_dev(struct dmar_domain *domain, } spin_lock_irqsave(&device_domain_lock, flags); + ret = auxiliary_link_device(domain, dev); + if (ret <= 0) + goto link_failed; + + /* + * Subdevices from the same physical device can be attached to the + * same domain. For such cases, only the first subdevice attachment + * needs to go through the full steps in this function. So if ret > + * 1, just goto out. + */ + if (ret > 1) + goto out; + /* * iommu->lock must be held to attach domain to iommu and setup the * pasid entry for second level translation. @@ -4548,10 +4610,9 @@ static int aux_domain_add_dev(struct dmar_domain *domain, domain->default_pasid); if (ret) goto table_failed; - spin_unlock(&iommu->lock); - - auxiliary_link_device(domain, dev); + spin_unlock(&iommu->lock); +out: spin_unlock_irqrestore(&device_domain_lock, flags); return 0; @@ -4560,8 +4621,10 @@ table_failed: domain_detach_iommu(domain, iommu); attach_failed: spin_unlock(&iommu->lock); + auxiliary_unlink_device(domain, dev); +link_failed: spin_unlock_irqrestore(&device_domain_lock, flags); - if (!domain->auxd_refcnt && domain->default_pasid > 0) + if (list_empty(&domain->subdevices) && domain->default_pasid > 0) ioasid_put(domain->default_pasid); return ret; @@ -4581,14 +4644,18 @@ static void aux_domain_remove_dev(struct dmar_domain *domain, info = get_domain_info(dev); iommu = info->iommu; - auxiliary_unlink_device(domain, dev); - - spin_lock(&iommu->lock); - intel_pasid_tear_down_entry(iommu, dev, domain->default_pasid, false); - domain_detach_iommu(domain, iommu); - spin_unlock(&iommu->lock); + if (!auxiliary_unlink_device(domain, dev)) { + spin_lock(&iommu->lock); + intel_pasid_tear_down_entry(iommu, dev, + domain->default_pasid, false); + domain_detach_iommu(domain, iommu); + spin_unlock(&iommu->lock); + } spin_unlock_irqrestore(&device_domain_lock, flags); + + if (list_empty(&domain->subdevices) && domain->default_pasid > 0) + ioasid_put(domain->default_pasid); } static int prepare_domain_attach_device(struct iommu_domain *domain, @@ -5373,6 +5440,36 @@ intel_iommu_domain_set_attr(struct iommu_domain *domain, return ret; } +static bool domain_use_flush_queue(void) +{ + struct dmar_drhd_unit *drhd; + struct intel_iommu *iommu; + bool r = true; + + if (intel_iommu_strict) + return false; + + /* + * The flush queue implementation does not perform page-selective + * invalidations that are required for efficient TLB flushes in virtual + * environments. The benefit of batching is likely to be much lower than + * the overhead of synchronizing the virtual and physical IOMMU + * page-tables. + */ + rcu_read_lock(); + for_each_active_iommu(iommu, drhd) { + if (!cap_caching_mode(iommu->cap)) + continue; + + pr_warn_once("IOMMU batching is disabled due to virtualization"); + r = false; + break; + } + rcu_read_unlock(); + + return r; +} + static int intel_iommu_domain_get_attr(struct iommu_domain *domain, enum iommu_attr attr, void *data) @@ -5383,7 +5480,7 @@ intel_iommu_domain_get_attr(struct iommu_domain *domain, case IOMMU_DOMAIN_DMA: switch (attr) { case DOMAIN_ATTR_DMA_USE_FLUSH_QUEUE: - *(int *)data = !intel_iommu_strict; + *(int *)data = domain_use_flush_queue(); return 0; default: return -ENODEV; |