[PATCH v5 4/8] iommu/vt-d: Aux-domain specific domain attach/detach
When multiple domains per device has been enabled by the device driver, the device will tag the default PASID for the domain to all DMA traffics out of the subset of this device; and the IOMMU should translate the DMA requests in PASID granularity. This adds the intel_iommu_aux_attach/detach_device() ops to support managing PASID granular translation structures when the device driver has enabled multiple domains per device. Cc: Ashok Raj Cc: Jacob Pan Cc: Kevin Tian Signed-off-by: Sanjay Kumar Signed-off-by: Liu Yi L Signed-off-by: Lu Baolu --- drivers/iommu/intel-iommu.c | 152 include/linux/intel-iommu.h | 10 +++ 2 files changed, 162 insertions(+) diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c index e9119d45a29d..b8fb6a4bd447 100644 --- a/drivers/iommu/intel-iommu.c +++ b/drivers/iommu/intel-iommu.c @@ -2482,6 +2482,7 @@ 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(>auxiliary_domains); if (dev && dev_is_pci(dev)) { struct pci_dev *pdev = to_pci_dev(info->dev); @@ -5058,6 +5059,131 @@ static void intel_iommu_domain_free(struct iommu_domain *domain) domain_exit(to_dmar_domain(domain)); } +/* + * Check whether a @domain could be attached to the @dev through the + * aux-domain attach/detach APIs. + */ +static inline bool +is_aux_domain(struct device *dev, struct iommu_domain *domain) +{ + struct device_domain_info *info = dev->archdata.iommu; + + return info && info->auxd_enabled && + domain->type == IOMMU_DOMAIN_UNMANAGED; +} + +static void auxiliary_link_device(struct dmar_domain *domain, + struct device *dev) +{ + struct device_domain_info *info = dev->archdata.iommu; + + assert_spin_locked(_domain_lock); + if (WARN_ON(!info)) + return; + + domain->auxd_refcnt++; + list_add(>auxd, >auxiliary_domains); +} + +static void auxiliary_unlink_device(struct dmar_domain *domain, + struct device *dev) +{ + struct device_domain_info *info = dev->archdata.iommu; + + assert_spin_locked(_domain_lock); + if (WARN_ON(!info)) + return; + + list_del(>auxd); + domain->auxd_refcnt--; + + if (!domain->auxd_refcnt && domain->default_pasid > 0) + intel_pasid_free_id(domain->default_pasid); +} + +static int aux_domain_add_dev(struct dmar_domain *domain, + struct device *dev) +{ + int ret; + u8 bus, devfn; + unsigned long flags; + struct intel_iommu *iommu; + + iommu = device_to_iommu(dev, , ); + if (!iommu) + return -ENODEV; + + if (domain->default_pasid <= 0) { + int pasid; + + pasid = intel_pasid_alloc_id(domain, PASID_MIN, +pci_max_pasids(to_pci_dev(dev)), +GFP_KERNEL); + if (pasid <= 0) { + pr_err("Can't allocate default pasid\n"); + return -ENODEV; + } + domain->default_pasid = pasid; + } + + spin_lock_irqsave(_domain_lock, flags); + /* +* iommu->lock must be held to attach domain to iommu and setup the +* pasid entry for second level translation. +*/ + spin_lock(>lock); + ret = domain_attach_iommu(domain, iommu); + if (ret) + goto attach_failed; + + /* Setup the PASID entry for mediated devices: */ + ret = intel_pasid_setup_second_level(iommu, domain, dev, +domain->default_pasid); + if (ret) + goto table_failed; + spin_unlock(>lock); + + auxiliary_link_device(domain, dev); + + spin_unlock_irqrestore(_domain_lock, flags); + + return 0; + +table_failed: + domain_detach_iommu(domain, iommu); +attach_failed: + spin_unlock(>lock); + spin_unlock_irqrestore(_domain_lock, flags); + if (!domain->auxd_refcnt && domain->default_pasid > 0) + intel_pasid_free_id(domain->default_pasid); + + return ret; +} + +static void aux_domain_remove_dev(struct dmar_domain *domain, + struct device *dev) +{ + struct device_domain_info *info; + struct intel_iommu *iommu; + unsigned long flags; + + if (!is_aux_domain(dev, >domain)) + return; + + spin_lock_irqsave(_domain_lock, flags); + info = dev->archdata.iommu; + iommu = info->iommu; + + auxiliary_unlink_device(domain, dev); + + spin_lock(>lock); + intel_pasid_tear_down_entry(iommu, dev, domain->default_pasid); +
[PATCH v5 5/8] iommu/vt-d: Return ID associated with an auxiliary domain
This adds support to return the default pasid associated with an auxiliary domain. The PCI device which is bound with this domain should use this value as the pasid for all DMA requests of the subset of device which is isolated and protected with this domain. Cc: Ashok Raj Cc: Jacob Pan Cc: Kevin Tian Signed-off-by: Sanjay Kumar Signed-off-by: Liu Yi L Signed-off-by: Lu Baolu --- drivers/iommu/intel-iommu.c | 10 ++ 1 file changed, 10 insertions(+) diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c index b8fb6a4bd447..614906276bf1 100644 --- a/drivers/iommu/intel-iommu.c +++ b/drivers/iommu/intel-iommu.c @@ -5624,6 +5624,15 @@ intel_iommu_dev_disable_feat(struct device *dev, enum iommu_dev_features feat) return -ENODEV; } +static int +intel_iommu_aux_get_pasid(struct iommu_domain *domain, struct device *dev) +{ + struct dmar_domain *dmar_domain = to_dmar_domain(domain); + + return dmar_domain->default_pasid > 0 ? + dmar_domain->default_pasid : -EINVAL; +} + const struct iommu_ops intel_iommu_ops = { .capable= intel_iommu_capable, .domain_alloc = intel_iommu_domain_alloc, @@ -5632,6 +5641,7 @@ const struct iommu_ops intel_iommu_ops = { .detach_dev = intel_iommu_detach_device, .aux_attach_dev = intel_iommu_aux_attach_device, .aux_detach_dev = intel_iommu_aux_detach_device, + .aux_get_pasid = intel_iommu_aux_get_pasid, .map= intel_iommu_map, .unmap = intel_iommu_unmap, .iova_to_phys = intel_iommu_iova_to_phys, -- 2.17.1 ___ iommu mailing list iommu@lists.linux-foundation.org https://lists.linuxfoundation.org/mailman/listinfo/iommu
[PATCH v5 7/8] vfio/type1: Add domain at(de)taching group helpers
This adds helpers to attach or detach a domain to a group. This will replace iommu_attach_group() which only works for non-mdev devices. If a domain is attaching to a group which includes the mediated devices, it should attach to the iommu device (a pci device which represents the mdev in iommu scope) instead. The added helper supports attaching domain to groups for both pci and mdev devices. Cc: Ashok Raj Cc: Jacob Pan Cc: Kevin Tian Signed-off-by: Sanjay Kumar Signed-off-by: Liu Yi L Signed-off-by: Lu Baolu --- drivers/vfio/vfio_iommu_type1.c | 84 ++--- 1 file changed, 77 insertions(+), 7 deletions(-) diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c index 7651cfb14836..97278ac8da95 100644 --- a/drivers/vfio/vfio_iommu_type1.c +++ b/drivers/vfio/vfio_iommu_type1.c @@ -91,6 +91,7 @@ struct vfio_dma { struct vfio_group { struct iommu_group *iommu_group; struct list_headnext; + boolmdev_group; /* An mdev group */ }; /* @@ -1298,6 +1299,75 @@ static bool vfio_iommu_has_sw_msi(struct iommu_group *group, phys_addr_t *base) return ret; } +static struct device *vfio_mdev_get_iommu_device(struct device *dev) +{ + struct device *(*fn)(struct device *dev); + struct device *iommu_device; + + fn = symbol_get(mdev_get_iommu_device); + if (fn) { + iommu_device = fn(dev); + symbol_put(mdev_get_iommu_device); + + return iommu_device; + } + + return NULL; +} + +static int vfio_mdev_attach_domain(struct device *dev, void *data) +{ + struct iommu_domain *domain = data; + struct device *iommu_device; + + iommu_device = vfio_mdev_get_iommu_device(dev); + if (iommu_device) { + if (iommu_dev_has_feature(iommu_device, IOMMU_DEV_FEAT_AUX)) + return iommu_aux_attach_device(domain, iommu_device); + else + return iommu_attach_device(domain, iommu_device); + } + + return -EINVAL; +} + +static int vfio_mdev_detach_domain(struct device *dev, void *data) +{ + struct iommu_domain *domain = data; + struct device *iommu_device; + + iommu_device = vfio_mdev_get_iommu_device(dev); + if (iommu_device) { + if (iommu_dev_has_feature(iommu_device, IOMMU_DEV_FEAT_AUX)) + iommu_aux_detach_device(domain, iommu_device); + else + iommu_detach_device(domain, iommu_device); + } + + return 0; +} + +static int vfio_iommu_attach_group(struct vfio_domain *domain, + struct vfio_group *group) +{ + if (group->mdev_group) + return iommu_group_for_each_dev(group->iommu_group, + domain->domain, + vfio_mdev_attach_domain); + else + return iommu_attach_group(domain->domain, group->iommu_group); +} + +static void vfio_iommu_detach_group(struct vfio_domain *domain, + struct vfio_group *group) +{ + if (group->mdev_group) + iommu_group_for_each_dev(group->iommu_group, domain->domain, +vfio_mdev_detach_domain); + else + iommu_detach_group(domain->domain, group->iommu_group); +} + static int vfio_iommu_type1_attach_group(void *iommu_data, struct iommu_group *iommu_group) { @@ -1373,7 +1443,7 @@ static int vfio_iommu_type1_attach_group(void *iommu_data, goto out_domain; } - ret = iommu_attach_group(domain->domain, iommu_group); + ret = vfio_iommu_attach_group(domain, group); if (ret) goto out_domain; @@ -1405,8 +1475,8 @@ static int vfio_iommu_type1_attach_group(void *iommu_data, list_for_each_entry(d, >domain_list, next) { if (d->domain->ops == domain->domain->ops && d->prot == domain->prot) { - iommu_detach_group(domain->domain, iommu_group); - if (!iommu_attach_group(d->domain, iommu_group)) { + vfio_iommu_detach_group(domain, group); + if (!vfio_iommu_attach_group(d, group)) { list_add(>next, >group_list); iommu_domain_free(domain->domain); kfree(domain); @@ -1414,7 +1484,7 @@ static int vfio_iommu_type1_attach_group(void *iommu_data, return 0; } - ret = iommu_attach_group(domain->domain, iommu_group); + ret = vfio_iommu_attach_group(domain, group); if (ret) goto
[PATCH v5 8/8] vfio/type1: Handle different mdev isolation type
This adds the support to determine the isolation type of a mediated device group by checking whether it has an iommu device. If an iommu device exists, an iommu domain will be allocated and then attached to the iommu device. Otherwise, keep the same behavior as it is. Cc: Ashok Raj Cc: Jacob Pan Cc: Kevin Tian Signed-off-by: Sanjay Kumar Signed-off-by: Liu Yi L Signed-off-by: Lu Baolu --- drivers/vfio/vfio_iommu_type1.c | 48 - 1 file changed, 41 insertions(+), 7 deletions(-) diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c index 97278ac8da95..140366014a1b 100644 --- a/drivers/vfio/vfio_iommu_type1.c +++ b/drivers/vfio/vfio_iommu_type1.c @@ -1368,13 +1368,40 @@ static void vfio_iommu_detach_group(struct vfio_domain *domain, iommu_detach_group(domain->domain, group->iommu_group); } +static bool vfio_bus_is_mdev(struct bus_type *bus) +{ + struct bus_type *mdev_bus; + bool ret = false; + + mdev_bus = symbol_get(mdev_bus_type); + if (mdev_bus) { + ret = (bus == mdev_bus); + symbol_put(mdev_bus_type); + } + + return ret; +} + +static int vfio_mdev_iommu_device(struct device *dev, void *data) +{ + struct device **old = data, *new; + + new = vfio_mdev_get_iommu_device(dev); + if (!new || (*old && *old != new)) + return -EINVAL; + + *old = new; + + return 0; +} + static int vfio_iommu_type1_attach_group(void *iommu_data, struct iommu_group *iommu_group) { struct vfio_iommu *iommu = iommu_data; struct vfio_group *group; struct vfio_domain *domain, *d; - struct bus_type *bus = NULL, *mdev_bus; + struct bus_type *bus = NULL; int ret; bool resv_msi, msi_remap; phys_addr_t resv_msi_base; @@ -1409,23 +1436,30 @@ static int vfio_iommu_type1_attach_group(void *iommu_data, if (ret) goto out_free; - mdev_bus = symbol_get(mdev_bus_type); + if (vfio_bus_is_mdev(bus)) { + struct device *iommu_device = NULL; - if (mdev_bus) { - if ((bus == mdev_bus) && !iommu_present(bus)) { - symbol_put(mdev_bus_type); + group->mdev_group = true; + + /* Determine the isolation type */ + ret = iommu_group_for_each_dev(iommu_group, _device, + vfio_mdev_iommu_device); + if (ret || !iommu_device) { if (!iommu->external_domain) { INIT_LIST_HEAD(>group_list); iommu->external_domain = domain; - } else + } else { kfree(domain); + } list_add(>next, >external_domain->group_list); mutex_unlock(>lock); + return 0; } - symbol_put(mdev_bus_type); + + bus = iommu_device->bus; } domain->domain = iommu_domain_alloc(bus); -- 2.17.1 ___ iommu mailing list iommu@lists.linux-foundation.org https://lists.linuxfoundation.org/mailman/listinfo/iommu
[PATCH v5 2/8] iommu/vt-d: Add per-device IOMMU feature ops entries
This adds the iommu ops entries for aux-domain per-device feature query and enable/disable. Cc: Ashok Raj Cc: Jacob Pan Cc: Kevin Tian Signed-off-by: Sanjay Kumar Signed-off-by: Liu Yi L Signed-off-by: Lu Baolu --- drivers/iommu/intel-iommu.c | 86 + include/linux/intel-iommu.h | 1 + 2 files changed, 87 insertions(+) diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c index 2bd9ac285c0d..ee8832d26f7e 100644 --- a/drivers/iommu/intel-iommu.c +++ b/drivers/iommu/intel-iommu.c @@ -2481,6 +2481,7 @@ static struct dmar_domain *dmar_insert_one_dev_info(struct intel_iommu *iommu, info->domain = domain; info->iommu = iommu; info->pasid_table = NULL; + info->auxd_enabled = 0; if (dev && dev_is_pci(dev)) { struct pci_dev *pdev = to_pci_dev(info->dev); @@ -5215,6 +5216,24 @@ static phys_addr_t intel_iommu_iova_to_phys(struct iommu_domain *domain, return phys; } +static inline bool scalable_mode_support(void) +{ + struct dmar_drhd_unit *drhd; + struct intel_iommu *iommu; + bool ret = true; + + rcu_read_lock(); + for_each_active_iommu(iommu, drhd) { + if (!sm_supported(iommu)) { + ret = false; + break; + } + } + rcu_read_unlock(); + + return ret; +} + static bool intel_iommu_capable(enum iommu_cap cap) { if (cap == IOMMU_CAP_CACHE_COHERENCY) @@ -5379,6 +5398,70 @@ struct intel_iommu *intel_svm_device_to_iommu(struct device *dev) } #endif /* CONFIG_INTEL_IOMMU_SVM */ +static int intel_iommu_enable_auxd(struct device *dev) +{ + struct device_domain_info *info; + struct dmar_domain *domain; + unsigned long flags; + + if (!scalable_mode_support()) + return -ENODEV; + + domain = get_valid_domain_for_dev(dev); + if (!domain) + return -ENODEV; + + spin_lock_irqsave(_domain_lock, flags); + info = dev->archdata.iommu; + info->auxd_enabled = 1; + spin_unlock_irqrestore(_domain_lock, flags); + + return 0; +} + +static int intel_iommu_disable_auxd(struct device *dev) +{ + struct device_domain_info *info; + unsigned long flags; + + spin_lock_irqsave(_domain_lock, flags); + info = dev->archdata.iommu; + if (!WARN_ON(!info)) + info->auxd_enabled = 0; + spin_unlock_irqrestore(_domain_lock, flags); + + return 0; +} + +static bool +intel_iommu_dev_has_feat(struct device *dev, enum iommu_dev_features feat) +{ + struct device_domain_info *info = dev->archdata.iommu; + + if (feat == IOMMU_DEV_FEAT_AUX) + return scalable_mode_support() && info && info->auxd_enabled; + + return false; +} + +static int +intel_iommu_dev_enable_feat(struct device *dev, enum iommu_dev_features feat) +{ + if (feat == IOMMU_DEV_FEAT_AUX) + return intel_iommu_enable_auxd(dev); + + return -ENODEV; +} + +static int +intel_iommu_dev_disable_feat(struct device *dev, enum iommu_dev_features feat) +{ + if (feat == IOMMU_DEV_FEAT_AUX) + return intel_iommu_disable_auxd(dev); + + return -ENODEV; +} + const struct iommu_ops intel_iommu_ops = { .capable= intel_iommu_capable, .domain_alloc = intel_iommu_domain_alloc, @@ -5393,6 +5476,9 @@ const struct iommu_ops intel_iommu_ops = { .get_resv_regions = intel_iommu_get_resv_regions, .put_resv_regions = intel_iommu_put_resv_regions, .device_group = pci_device_group, + .dev_has_feat = intel_iommu_dev_has_feat, + .dev_enable_feat= intel_iommu_dev_enable_feat, + .dev_disable_feat = intel_iommu_dev_disable_feat, .pgsize_bitmap = INTEL_IOMMU_PGSIZES, }; diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h index 0605f3bf6e79..7cf9f7f3724a 100644 --- a/include/linux/intel-iommu.h +++ b/include/linux/intel-iommu.h @@ -571,6 +571,7 @@ struct device_domain_info { u8 pri_enabled:1; u8 ats_supported:1; u8 ats_enabled:1; + u8 auxd_enabled:1; /* Multiple domains per device */ u8 ats_qdep; struct device *dev; /* it's NULL for PCIe-to-PCI bridge */ struct intel_iommu *iommu; /* IOMMU used by this device */ -- 2.17.1 ___ iommu mailing list iommu@lists.linux-foundation.org https://lists.linuxfoundation.org/mailman/listinfo/iommu
[PATCH v5 3/8] iommu/vt-d: Move common code out of iommu_attch_device()
This part of code could be used by both normal and aux domain specific attach entries. Hence move them into a common function to avoid duplication. Cc: Ashok Raj Cc: Jacob Pan Cc: Kevin Tian Signed-off-by: Lu Baolu --- drivers/iommu/intel-iommu.c | 60 ++--- 1 file changed, 36 insertions(+), 24 deletions(-) diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c index ee8832d26f7e..e9119d45a29d 100644 --- a/drivers/iommu/intel-iommu.c +++ b/drivers/iommu/intel-iommu.c @@ -5058,35 +5058,14 @@ static void intel_iommu_domain_free(struct iommu_domain *domain) domain_exit(to_dmar_domain(domain)); } -static int intel_iommu_attach_device(struct iommu_domain *domain, -struct device *dev) +static int prepare_domain_attach_device(struct iommu_domain *domain, + struct device *dev) { struct dmar_domain *dmar_domain = to_dmar_domain(domain); struct intel_iommu *iommu; int addr_width; u8 bus, devfn; - if (device_is_rmrr_locked(dev)) { - dev_warn(dev, "Device is ineligible for IOMMU domain attach due to platform RMRR requirement. Contact your platform vendor.\n"); - return -EPERM; - } - - /* normally dev is not mapped */ - if (unlikely(domain_context_mapped(dev))) { - struct dmar_domain *old_domain; - - old_domain = find_domain(dev); - if (old_domain) { - rcu_read_lock(); - dmar_remove_one_dev_info(old_domain, dev); - rcu_read_unlock(); - - if (!domain_type_is_vm_or_si(old_domain) && -list_empty(_domain->devices)) - domain_exit(old_domain); - } - } - iommu = device_to_iommu(dev, , ); if (!iommu) return -ENODEV; @@ -5119,7 +5098,40 @@ static int intel_iommu_attach_device(struct iommu_domain *domain, dmar_domain->agaw--; } - return domain_add_dev_info(dmar_domain, dev); + return 0; +} + +static int intel_iommu_attach_device(struct iommu_domain *domain, +struct device *dev) +{ + int ret; + + if (device_is_rmrr_locked(dev)) { + dev_warn(dev, "Device is ineligible for IOMMU domain attach due to platform RMRR requirement. Contact your platform vendor.\n"); + return -EPERM; + } + + /* normally dev is not mapped */ + if (unlikely(domain_context_mapped(dev))) { + struct dmar_domain *old_domain; + + old_domain = find_domain(dev); + if (old_domain) { + rcu_read_lock(); + dmar_remove_one_dev_info(old_domain, dev); + rcu_read_unlock(); + + if (!domain_type_is_vm_or_si(old_domain) && + list_empty(_domain->devices)) + domain_exit(old_domain); + } + } + + ret = prepare_domain_attach_device(domain, dev); + if (ret) + return ret; + + return domain_add_dev_info(to_dmar_domain(domain), dev); } static void intel_iommu_detach_device(struct iommu_domain *domain, -- 2.17.1 ___ iommu mailing list iommu@lists.linux-foundation.org https://lists.linuxfoundation.org/mailman/listinfo/iommu
[PATCH v5 6/8] vfio/mdev: Add iommu related member in mdev_device
A parent device might create different types of mediated devices. For example, a mediated device could be created by the parent device with full isolation and protection provided by the IOMMU. One usage case could be found on Intel platforms where a mediated device is an assignable subset of a PCI, the DMA requests on behalf of it are all tagged with a PASID. Since IOMMU supports PASID-granular translations (scalable mode in VT-d 3.0), this mediated device could be individually protected and isolated by an IOMMU. This patch adds a new member in the struct mdev_device to indicate that the mediated device represented by mdev could be isolated and protected by attaching a domain to a device represented by mdev->iommu_device. It also adds a helper to add or set the iommu device. * mdev_device->iommu_device - This, if set, indicates that the mediated device could be fully isolated and protected by IOMMU via attaching an iommu domain to this device. If empty, it indicates using vendor defined isolation, hence bypass IOMMU. * mdev_set/get_iommu_device(dev, iommu_device) - Set or get the iommu device which represents this mdev in IOMMU's device scope. Drivers don't need to set the iommu device if it uses vendor defined isolation. Cc: Ashok Raj Cc: Jacob Pan Cc: Kevin Tian Cc: Liu Yi L Suggested-by: Kevin Tian Suggested-by: Alex Williamson Signed-off-by: Lu Baolu --- drivers/vfio/mdev/mdev_core.c| 18 ++ drivers/vfio/mdev/mdev_private.h | 1 + include/linux/mdev.h | 14 ++ 3 files changed, 33 insertions(+) diff --git a/drivers/vfio/mdev/mdev_core.c b/drivers/vfio/mdev/mdev_core.c index 0212f0ee8aea..9be58d392d2b 100644 --- a/drivers/vfio/mdev/mdev_core.c +++ b/drivers/vfio/mdev/mdev_core.c @@ -390,6 +390,24 @@ int mdev_device_remove(struct device *dev, bool force_remove) return 0; } +int mdev_set_iommu_device(struct device *dev, struct device *iommu_device) +{ + struct mdev_device *mdev = to_mdev_device(dev); + + mdev->iommu_device = iommu_device; + + return 0; +} +EXPORT_SYMBOL(mdev_set_iommu_device); + +struct device *mdev_get_iommu_device(struct device *dev) +{ + struct mdev_device *mdev = to_mdev_device(dev); + + return mdev->iommu_device; +} +EXPORT_SYMBOL(mdev_get_iommu_device); + static int __init mdev_init(void) { return mdev_bus_register(); diff --git a/drivers/vfio/mdev/mdev_private.h b/drivers/vfio/mdev/mdev_private.h index b5819b7d7ef7..891841862ef8 100644 --- a/drivers/vfio/mdev/mdev_private.h +++ b/drivers/vfio/mdev/mdev_private.h @@ -34,6 +34,7 @@ struct mdev_device { struct list_head next; struct kobject *type_kobj; bool active; + struct device *iommu_device; }; #define to_mdev_device(dev)container_of(dev, struct mdev_device, dev) diff --git a/include/linux/mdev.h b/include/linux/mdev.h index b6e048e1045f..c3ab8a9cfcc7 100644 --- a/include/linux/mdev.h +++ b/include/linux/mdev.h @@ -15,6 +15,20 @@ struct mdev_device; +/* + * Called by the parent device driver to set the device which represents + * this mdev in iommu protection scope. By default, the iommu device is + * NULL, that indicates using vendor defined isolation. + * + * @dev: the mediated device that iommu will isolate. + * @iommu_device: a pci device which represents the iommu for @dev. + * + * Return 0 for success, otherwise negative error value. + */ +int mdev_set_iommu_device(struct device *dev, struct device *iommu_device); + +struct device *mdev_get_iommu_device(struct device *dev); + /** * struct mdev_parent_ops - Structure to be registered for each parent device to * register the device to mdev module. -- 2.17.1 ___ iommu mailing list iommu@lists.linux-foundation.org https://lists.linuxfoundation.org/mailman/listinfo/iommu
[PATCH v5 0/8] vfio/mdev: IOMMU aware mediated device
Hi, The Mediate Device is a framework for fine-grained physical device sharing across the isolated domains. Currently the mdev framework is designed to be independent of the platform IOMMU support. As the result, the DMA isolation relies on the mdev parent device in a vendor specific way. There are several cases where a mediated device could be protected and isolated by the platform IOMMU. For example, Intel vt-d rev3.0 [1] introduces a new translation mode called 'scalable mode', which enables PASID-granular translations. The vt-d scalable mode is the key ingredient for Scalable I/O Virtualization [2] [3] which allows sharing a device in minimal possible granularity (ADI - Assignable Device Interface). A mediated device backed by an ADI could be protected and isolated by the IOMMU since 1) the parent device supports tagging an unique PASID to all DMA traffic out of the mediated device; and 2) the DMA translation unit (IOMMU) supports the PASID granular translation. We can apply IOMMU protection and isolation to this kind of devices just as what we are doing with an assignable PCI device. In order to distinguish the IOMMU-capable mediated devices from those which still need to rely on parent devices, this patch set adds one new member in struct mdev_device. * iommu_device - This, if set, indicates that the mediated device could be fully isolated and protected by IOMMU via attaching an iommu domain to this device. If empty, it indicates using vendor defined isolation. Below helpers are added to set and get above iommu device in mdev core implementation. * mdev_set/get_iommu_device(dev, iommu_device) - Set or get the iommu device which represents this mdev in IOMMU's device scope. Drivers don't need to set the iommu device if it uses vendor defined isolation. The mdev parent device driver could opt-in that the mdev could be fully isolated and protected by the IOMMU when the mdev is being created by invoking mdev_set_iommu_device() in its @create(). In the vfio_iommu_type1_attach_group(), a domain allocated through iommu_domain_alloc() will be attached to the mdev iommu device if an iommu device has been set. Otherwise, the dummy external domain will be used and all the DMA isolation and protection are routed to parent driver as the result. On IOMMU side, a basic requirement is allowing to attach multiple domains to a PCI device if the device advertises the capability and the IOMMU hardware supports finer granularity translations than the normal PCI Source ID based translation. As the result, a PCI device could work in two modes: normal mode and auxiliary mode. In the normal mode, a pci device could be isolated in the Source ID granularity; the pci device itself could be assigned to a user application by attaching a single domain to it. In the auxiliary mode, a pci device could be isolated in finer granularity, hence subsets of the device could be assigned to different user level application by attaching a different domain to each subset. Below APIs are introduced in iommu generic layer for aux-domain purpose: * iommu_dev_has_feature(dev, IOMMU_DEV_FEAT_AUX) - Check whether both IOMMU and device support IOMMU aux domain feature. Below aux-domain specific interfaces are available only after this returns true. * iommu_dev_enable/disable_feature(dev, IOMMU_DEV_FEAT_AUX) - Enable/disable device specific aux-domain feature. * iommu_aux_attach_device(domain, dev) - Attaches @domain to @dev in the auxiliary mode. Multiple domains could be attached to a single device in the auxiliary mode with each domain representing an isolated address space for an assignable subset of the device. * iommu_aux_detach_device(domain, dev) - Detach @domain which has been attached to @dev in the auxiliary mode. * iommu_aux_get_pasid(domain, dev) - Return ID used for finer-granularity DMA translation. For the Intel Scalable IOV usage model, this will be a PASID. The device which supports Scalable IOV needs to write this ID to the device register so that DMA requests could be tagged with a right PASID prefix. In order for the ease of discussion, sometimes we call "a domain in auxiliary mode' or simply 'an auxiliary domain' when a domain is attached to a device for finer granularity translations. But we need to keep in mind that this doesn't mean there is a differnt domain type. A same domain could be bound to a device for Source ID based translation, and bound to another device for finer granularity translation at the same time. This patch series extends both IOMMU and vfio components to support mdev device passing through when it could be isolated and protected by the IOMMU units. The first part of this series (PATCH 1/08~5/08) adds the interfaces and implementation of the multiple domains per device. The second part (PATCH 6/08~8/08) adds the iommu device attribute to each mdev, determines isolation type according to the existence of an iommu
[PATCH v5 1/8] iommu: Add APIs for multiple domains per device
Sharing a physical PCI device in a finer-granularity way is becoming a consensus in the industry. IOMMU vendors are also engaging efforts to support such sharing as well as possible. Among the efforts, the capability of support finer-granularity DMA isolation is a common requirement due to the security consideration. With finer-granularity DMA isolation, all DMA requests out of or to a subset of a physical PCI device can be protected by the IOMMU. As a result, there is a request in software to attach multiple domains to a physical PCI device. One example of such use model is the Intel Scalable IOV [1] [2]. The Intel vt-d 3.0 spec [3] introduces the scalable mode which enables PASID granularity DMA isolation. This adds the APIs to support multiple domains per device. In order to ease the discussions, we call it 'a domain in auxiliary mode' or simply 'auxiliary domain' when multiple domains are attached to a physical device. The APIs include: * iommu_dev_has_feature(dev, IOMMU_DEV_FEAT_AUX) - Check whether both IOMMU and device support IOMMU aux domain feature. Below aux-domain specific interfaces are available only after this returns true. * iommu_dev_enable/disable_feature(dev, IOMMU_DEV_FEAT_AUX) - Enable/disable device specific aux-domain feature. * iommu_aux_attach_device(domain, dev) - Attaches @domain to @dev in the auxiliary mode. Multiple domains could be attached to a single device in the auxiliary mode with each domain representing an isolated address space for an assignable subset of the device. * iommu_aux_detach_device(domain, dev) - Detach @domain which has been attached to @dev in the auxiliary mode. * iommu_aux_get_pasid(domain, dev) - Return ID used for finer-granularity DMA translation. For the Intel Scalable IOV usage model, this will be a PASID. The device which supports Scalable IOV needs to write this ID to the device register so that DMA requests could be tagged with a right PASID prefix. This has been updated with the latest proposal from Joerg posted here [5]. Many people involved in discussions of this design. Kevin Tian Liu Yi L Ashok Raj Sanjay Kumar Jacob Pan Alex Williamson Jean-Philippe Brucker Joerg Roedel and some discussions can be found here [4] [5]. [1] https://software.intel.com/en-us/download/intel-scalable-io-virtualization-technical-specification [2] https://schd.ws/hosted_files/lc32018/00/LC3-SIOV-final.pdf [3] https://software.intel.com/en-us/download/intel-virtualization-technology-for-directed-io-architecture-specification [4] https://lkml.org/lkml/2018/7/26/4 [5] https://www.spinics.net/lists/iommu/msg31874.html Cc: Ashok Raj Cc: Jacob Pan Cc: Kevin Tian Cc: Liu Yi L Suggested-by: Kevin Tian Suggested-by: Jean-Philippe Brucker Suggested-by: Joerg Roedel Signed-off-by: Lu Baolu --- drivers/iommu/iommu.c | 80 +++ include/linux/iommu.h | 61 + 2 files changed, 141 insertions(+) diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c index 3ed4db334341..9166b6145409 100644 --- a/drivers/iommu/iommu.c +++ b/drivers/iommu/iommu.c @@ -2033,3 +2033,83 @@ int iommu_fwspec_add_ids(struct device *dev, u32 *ids, int num_ids) return 0; } EXPORT_SYMBOL_GPL(iommu_fwspec_add_ids); + +/* + * Per device IOMMU features. + */ +bool iommu_dev_has_feature(struct device *dev, enum iommu_dev_features feat) +{ + const struct iommu_ops *ops = dev->bus->iommu_ops; + + if (ops && ops->dev_has_feat) + return ops->dev_has_feat(dev, feat); + + return false; +} +EXPORT_SYMBOL_GPL(iommu_dev_has_feature); + +int iommu_dev_enable_feature(struct device *dev, enum iommu_dev_features feat) +{ + const struct iommu_ops *ops = dev->bus->iommu_ops; + + if (ops && ops->dev_enable_feat) + return ops->dev_enable_feat(dev, feat); + + return -ENODEV; +} +EXPORT_SYMBOL_GPL(iommu_dev_enable_feature); + +int iommu_dev_disable_feature(struct device *dev, enum iommu_dev_features feat) +{ + const struct iommu_ops *ops = dev->bus->iommu_ops; + + if (ops && ops->dev_disable_feat) + return ops->dev_disable_feat(dev, feat); + + return -ENODEV; +} +EXPORT_SYMBOL_GPL(iommu_dev_disable_feature); + +/* + * Aux-domain specific attach/detach. + * + * Only works if iommu_dev_has_feature(dev, IOMMU_DEV_FEAT_AUX) returns true. + * Also, as long as domains are attached to a device through this interface, + * any tries to call iommu_attach_device() should fail (iommu_detach_device() + * can't fail, so we fail on the tryint to re-attach). This should make us safe + * against a device being attached to a guest as a whole while there are still + * pasid users on it (aux and sva). + */ +int iommu_aux_attach_device(struct iommu_domain *domain, struct device *dev) +{ + int ret = -ENODEV; + + if (domain->ops->aux_attach_dev) + ret =
Re: [PATCH] arm64: dts: stratix10: Add Stratix10 SMMU support
On 1/4/19 1:23 PM, thor.tha...@linux.intel.com wrote: > From: Thor Thayer > > Now there are device tree clocks for the ARM64 SMMU, > add SMMU support to the Stratix10 Device Tree which > includes adding the SMMU node and adding IOMMU stream > ids to the SMMU peripherals. > > Signed-off-by: Thor Thayer > --- > arch/arm64/boot/dts/altera/socfpga_stratix10.dtsi | 29 > +++ > 1 file changed, 29 insertions(+) Applied! Thanks, Dinh ___ iommu mailing list iommu@lists.linux-foundation.org https://lists.linuxfoundation.org/mailman/listinfo/iommu
Re: use generic DMA mapping code in powerpc V4
Next step: a64e18ba191ba9102fb174f27d707485ffd9389c (powerpc/dma: remove dma_nommu_get_required_mask) git clone git://git.infradead.org/users/hch/misc.git -b powerpc-dma.6 a git checkout a64e18ba191ba9102fb174f27d707485ffd9389c Link to the Git: http://git.infradead.org/users/hch/misc.git/shortlog/refs/heads/powerpc-dma.6 Results: PASEMI onboard ethernet works and the X5000 (P5020 board) boots. I also successfully tested sound, hardware 3D acceleration, Bluetooth, network, booting with a label etc. The uImages work also in a virtual e5500 quad-core QEMU machine. -- Christian On 05 January 2019 at 5:03PM, Christian Zigotzky wrote: Next step: c446404b041130fbd9d1772d184f24715cf2362f (powerpc/dma: remove dma_nommu_mmap_coherent) git clone git://git.infradead.org/users/hch/misc.git -b powerpc-dma.6 a git checkout c446404b041130fbd9d1772d184f24715cf2362f Output: Note: checking out 'c446404b041130fbd9d1772d184f24715cf2362f'. You are in 'detached HEAD' state. You can look around, make experimental changes and commit them, and you can discard any commits you make in this state without impacting any branches by performing another checkout. If you want to create a new branch to retain commits you create, you may do so (now or later) by using -b with the checkout command again. Example: git checkout -b HEAD is now at c446404... powerpc/dma: remove dma_nommu_mmap_coherent - Link to the Git: http://git.infradead.org/users/hch/misc.git/shortlog/refs/heads/powerpc-dma.6 Result: PASEMI onboard ethernet works and the X5000 (P5020 board) boots. -- Christian ___ iommu mailing list iommu@lists.linux-foundation.org https://lists.linuxfoundation.org/mailman/listinfo/iommu