Hi Lu, On 11/5/18 8:34 AM, Lu Baolu wrote: > 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 includes: > > * iommu_get_dev_attr(dev, IOMMU_DEV_ATTR_AUXD_CAPABILITY) > - Represents the ability of supporting multiple domains > per device. > > * iommu_get_dev_attr(dev, IOMMU_DEV_ATTR_AUXD_ENABLED) > - Checks whether the device identified by @dev is working > in auxiliary mode. > > * iommu_set_dev_attr(dev, IOMMU_DEV_ATTR_AUXD_ENABLE) > - Enables the multiple domains capability for the device > referenced by @dev. > > * iommu_set_dev_attr(dev, IOMMU_DEV_ATTR_AUXD_DISABLE) > - Disables the multiple domains capability for the device > referenced by @dev. > > * iommu_attach_device_aux(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_detach_device_aux(domain, dev) > - Detach @domain which has been attached to @dev in the > auxiliary mode. > > * iommu_domain_get_attr(domain, DOMAIN_ATTR_AUXD_ID) > - Return ID used for finer-granularity DMA translation. > For the Intel Scalable IOV usage model, this will be > a PASID. The device which supports Scalalbe IOV needs s/Scalalbe/Scalable > to writes this ID to the device register so that DMA s/writes/write > requests could be tagged with a right PASID prefix. This is not crystal clear to me as the intel implementation returns the default PASID and not the PASID of the aux domain. > > 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> > > and some discussions can be found here [4]. > > [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 > > 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> > Signed-off-by: Lu Baolu <baolu.lu@xxxxxxxxxxxxxxx> > --- > drivers/iommu/iommu.c | 52 +++++++++++++++++++++++++++++++++++++++++++ > include/linux/iommu.h | 52 +++++++++++++++++++++++++++++++++++++++++++ > 2 files changed, 104 insertions(+) > > diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c > index edbdf5d6962c..0b7c96d1425e 100644 > --- a/drivers/iommu/iommu.c > +++ b/drivers/iommu/iommu.c > @@ -2030,3 +2030,55 @@ int iommu_fwspec_add_ids(struct device *dev, u32 *ids, int num_ids) > return 0; > } > EXPORT_SYMBOL_GPL(iommu_fwspec_add_ids); > + > +/* > + * Generic interfaces to get or set per device IOMMU attributions. > + */ > +int iommu_get_dev_attr(struct device *dev, enum iommu_dev_attr attr, void *data) > +{ > + const struct iommu_ops *ops = dev->bus->iommu_ops; > + > + if (ops && ops->get_dev_attr) > + return ops->get_dev_attr(dev, attr, data); > + > + return -EINVAL; > +} > +EXPORT_SYMBOL_GPL(iommu_get_dev_attr); > + > +int iommu_set_dev_attr(struct device *dev, enum iommu_dev_attr attr, void *data) > +{ > + const struct iommu_ops *ops = dev->bus->iommu_ops; > + > + if (ops && ops->set_dev_attr) > + return ops->set_dev_attr(dev, attr, data); > + > + return -EINVAL; > +} > +EXPORT_SYMBOL_GPL(iommu_set_dev_attr); > + > +/* > + * APIs to attach/detach a domain to/from a device in the > + * auxiliary mode. > + */ > +int iommu_attach_device_aux(struct iommu_domain *domain, struct device *dev) > +{ > + int ret = -ENODEV; > + > + if (domain->ops->attach_dev_aux) > + ret = domain->ops->attach_dev_aux(domain, dev); > + > + if (!ret) > + trace_attach_device_to_domain(dev); > + > + return ret; > +} > +EXPORT_SYMBOL_GPL(iommu_attach_device_aux); > + > +void iommu_detach_device_aux(struct iommu_domain *domain, struct device *dev) > +{ > + if (domain->ops->detach_dev_aux) { > + domain->ops->detach_dev_aux(domain, dev); > + trace_detach_device_from_domain(dev); > + } > +} > +EXPORT_SYMBOL_GPL(iommu_detach_device_aux); > diff --git a/include/linux/iommu.h b/include/linux/iommu.h > index a1d28f42cb77..9bf1b3f2457a 100644 > --- a/include/linux/iommu.h > +++ b/include/linux/iommu.h > @@ -126,6 +126,7 @@ enum iommu_attr { > DOMAIN_ATTR_NESTING, /* two stages of translation */ > DOMAIN_ATTR_DMA_USE_FLUSH_QUEUE, > DOMAIN_ATTR_MAX, > + DOMAIN_ATTR_AUXD_ID, > }; > > /* These are the possible reserved region types */ > @@ -156,6 +157,14 @@ struct iommu_resv_region { > enum iommu_resv_type type; > }; > > +/* Per device IOMMU attributions */ > +enum iommu_dev_attr { > + IOMMU_DEV_ATTR_AUXD_CAPABILITY, > + IOMMU_DEV_ATTR_AUXD_ENABLED, > + IOMMU_DEV_ATTR_AUXD_ENABLE, > + IOMMU_DEV_ATTR_AUXD_DISABLE, > +}; > + > #ifdef CONFIG_IOMMU_API > > /** > @@ -183,6 +192,8 @@ 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 > + * @get_dev_attr: get per device IOMMU attributions s/attributions/attributes here and other locations? > + * @set_dev_attr: set per device IOMMU attributions > * @pgsize_bitmap: bitmap of all possible supported page sizes > */ > struct iommu_ops { > @@ -226,6 +237,15 @@ 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); > > + /* Get/set per device IOMMU attributions */ > + int (*get_dev_attr)(struct device *dev, > + enum iommu_dev_attr attr, void *data); > + int (*set_dev_attr)(struct device *dev, > + enum iommu_dev_attr attr, void *data); > + /* Attach/detach aux domain */ > + int (*attach_dev_aux)(struct iommu_domain *domain, struct device *dev); > + void (*detach_dev_aux)(struct iommu_domain *domain, struct device *dev); > + > unsigned long pgsize_bitmap; > }; > > @@ -398,6 +418,16 @@ void iommu_fwspec_free(struct device *dev); > int iommu_fwspec_add_ids(struct device *dev, u32 *ids, int num_ids); > const struct iommu_ops *iommu_ops_from_fwnode(struct fwnode_handle *fwnode); > > +int iommu_get_dev_attr(struct device *dev, > + enum iommu_dev_attr attr, void *data); > +int iommu_set_dev_attr(struct device *dev, > + enum iommu_dev_attr attr, void *data); > + > +extern int iommu_attach_device_aux(struct iommu_domain *domain, > + struct device *dev); > +extern void iommu_detach_device_aux(struct iommu_domain *domain, > + struct device *dev); > + > #else /* CONFIG_IOMMU_API */ > > struct iommu_ops {}; > @@ -682,6 +712,28 @@ const struct iommu_ops *iommu_ops_from_fwnode(struct fwnode_handle *fwnode) > return NULL; > } > > +static inline int > +iommu_get_dev_attr(struct device *dev, enum iommu_dev_attr attr, void *data) > +{ > + return -EINVAL; > +} > + > +static inline int > +iommu_set_dev_attr(struct device *dev, enum iommu_dev_attr attr, void *data) > +{ > + return -EINVAL; > +} > + > +static inline int > +iommu_attach_device_aux(struct iommu_domain *domain, struct device *dev) > +{ > + return -ENODEV; > +} > + > +static inline void > +iommu_detach_device_aux(struct iommu_domain *domain, struct device *dev) > +{ > +} > #endif /* CONFIG_IOMMU_API */ > > #ifdef CONFIG_IOMMU_DEBUGFS > Thanks Eric
