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 <kevin.tian@xxxxxxxxx>
Liu Yi L <yi.l.liu@xxxxxxxxx>
Ashok Raj <ashok.raj@xxxxxxxxx>
Sanjay Kumar <sanjay.k.kumar@xxxxxxxxx>
Jacob Pan <jacob.jun.pan@xxxxxxxxxxxxxxx>
Alex Williamson <alex.williamson@xxxxxxxxxx>
Jean-Philippe Brucker <jean-philippe.brucker@xxxxxxx>
Joerg Roedel <joro@xxxxxxxxxx>
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 <ashok.raj@xxxxxxxxx>
Cc: Jacob Pan <jacob.jun.pan@xxxxxxxxxxxxxxx>
Cc: Kevin Tian <kevin.tian@xxxxxxxxx>
Cc: Liu Yi L <yi.l.liu@xxxxxxxxx>
Suggested-by: Kevin Tian <kevin.tian@xxxxxxxxx>
Suggested-by: Jean-Philippe Brucker <jean-philippe.brucker@xxxxxxx>
Suggested-by: Joerg Roedel <jroedel@xxxxxxx>
Signed-off-by: Lu Baolu <baolu.lu@xxxxxxxxxxxxxxx>
---
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 = domain->ops->aux_attach_dev(domain, dev);
+
+ if (!ret)
+ trace_attach_device_to_domain(dev);
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(iommu_aux_attach_device);
+
+void iommu_aux_detach_device(struct iommu_domain *domain, struct device *dev)
+{
+ if (domain->ops->aux_detach_dev) {
+ domain->ops->aux_detach_dev(domain, dev);
+ trace_detach_device_from_domain(dev);
+ }
+}
+EXPORT_SYMBOL_GPL(iommu_aux_detach_device);
+
+int iommu_aux_get_pasid(struct iommu_domain *domain, struct device *dev)
+{
+ int ret = -ENODEV;
+
+ if (domain->ops->aux_get_pasid)
+ ret = domain->ops->aux_get_pasid(domain, dev);
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(iommu_aux_get_pasid);
diff --git a/include/linux/iommu.h b/include/linux/iommu.h
index e90da6b6f3d1..f4c3d2a2cc87 100644
--- a/include/linux/iommu.h
+++ b/include/linux/iommu.h
@@ -156,6 +156,11 @@ struct iommu_resv_region {
enum iommu_resv_type type;
};
+/* Per device IOMMU features */
+enum iommu_dev_features {
+ IOMMU_DEV_FEAT_AUX, /* Aux-domain feature */
+};
+
#ifdef CONFIG_IOMMU_API
/**
@@ -183,6 +188,10 @@ struct iommu_resv_region {
* @domain_window_enable: Configure and enable a particular window for a domain
* @domain_window_disable: Disable a particular window for a domain
* @of_xlate: add OF master IDs to iommu grouping
+ * @dev_has/enable/disable_feat: per device entries to check/enable/disable
+ * iommu specific features.
+ * @aux_attach/detach_dev: aux-domain specific attach/detach entries.
+ * @aux_get_pasid: get the pasid given an aux-domain
* @pgsize_bitmap: bitmap of all possible supported page sizes
*/
struct iommu_ops {
@@ -226,6 +235,16 @@ struct iommu_ops {
int (*of_xlate)(struct device *dev, struct of_phandle_args *args);
bool (*is_attach_deferred)(struct iommu_domain *domain, struct device *dev);
+ /* Per device IOMMU features */
+ bool (*dev_has_feat)(struct device *dev, enum iommu_dev_features f);
+ int (*dev_enable_feat)(struct device *dev, enum iommu_dev_features f);
+ int (*dev_disable_feat)(struct device *dev, enum iommu_dev_features f);
+
+ /* Aux-domain specific attach/detach entries */
+ int (*aux_attach_dev)(struct iommu_domain *domain, struct device *dev);
+ void (*aux_detach_dev)(struct iommu_domain *domain, struct device *dev);
+ int (*aux_get_pasid)(struct iommu_domain *domain, struct device *dev);
+
unsigned long pgsize_bitmap;
};
@@ -412,6 +431,13 @@ static inline void dev_iommu_fwspec_set(struct device *dev,
int iommu_probe_device(struct device *dev);
void iommu_release_device(struct device *dev);
+bool iommu_dev_has_feature(struct device *dev, enum iommu_dev_features feat);
+int iommu_dev_enable_feature(struct device *dev, enum iommu_dev_features feat);
+int iommu_dev_disable_feature(struct device *dev, enum iommu_dev_features feat);
+int iommu_aux_attach_device(struct iommu_domain *domain, struct device *dev);
+void iommu_aux_detach_device(struct iommu_domain *domain, struct device *dev);
+int iommu_aux_get_pasid(struct iommu_domain *domain, struct device *dev);
+
#else /* CONFIG_IOMMU_API */
struct iommu_ops {};
@@ -696,6 +722,41 @@ const struct iommu_ops *iommu_ops_from_fwnode(struct fwnode_handle *fwnode)
return NULL;
}
+static inline bool
+iommu_dev_has_feature(struct device *dev, enum iommu_dev_features feat)
+{
+ return false;
+}
+
+static inline int
+iommu_dev_enable_feature(struct device *dev, enum iommu_dev_features feat)
+{
+ return -ENODEV;
+}
+
+static inline int
+iommu_dev_disable_feature(struct device *dev, enum iommu_dev_features feat)
+{
+ return -ENODEV;
+}
+
+static inline int
+iommu_aux_attach_device(struct iommu_domain *domain, struct device *dev)
+{
+ return -ENODEV;
+}
+
+static inline void
+iommu_aux_detach_device(struct iommu_domain *domain, struct device *dev)
+{
+}
+
+static inline int
+iommu_aux_get_pasid(struct iommu_domain *domain, struct device *dev)
+{
+ return -ENODEV;
+}
+
#endif /* CONFIG_IOMMU_API */
#ifdef CONFIG_IOMMU_DEBUGFS
--
2.17.1
