[PATCH v12 05/17] iommu: Add attach/detach_dev_pasid iommu interface

[Lu Baolu]

Attaching an IOMMU domain to a PASID of a device is a generic operation
for modern IOMMU drivers which support PASID-granular DMA address
translation. Currently visible usage scenarios include (but not limited):

 - SVA (Shared Virtual Address)
 - kernel DMA with PASID
 - hardware-assist mediated device

This adds set_dev_pasid domain ops for this purpose and also adds some
interfaces for device drivers to attach/detach/retrieve a domain for a
PASID of a device.

If multiple devices share a single group, it's fine as long the fabric
always routes every TLP marked with a PASID to the host bridge and only
the host bridge. For example, ACS achieves this universally and has been
checked when pci_enable_pasid() is called. As we can't reliably tell the
source apart in a group, all the devices in a group have to be considered
as the same source, and mapped to the same PASID table.

Signed-off-by: Lu Baolu <baolu.lu@xxxxxxxxxxxxxxx>
Reviewed-by: Jean-Philippe Brucker <jean-philippe@xxxxxxxxxx>
Reviewed-by: Kevin Tian <kevin.tian@xxxxxxxxx>
Reviewed-by: Yi Liu <yi.l.liu@xxxxxxxxx>
Tested-by: Zhangfei Gao <zhangfei.gao@xxxxxxxxxx>
Tested-by: Tony Zhu <tony.zhu@xxxxxxxxx>
---
 include/linux/iommu.h |  28 ++++++++++
 drivers/iommu/iommu.c | 126 ++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 154 insertions(+)

diff --git a/include/linux/iommu.h b/include/linux/iommu.h
index 2f237c3cd680..5e9553a7de0d 100644
--- a/include/linux/iommu.h
+++ b/include/linux/iommu.h
@@ -266,6 +266,7 @@ struct iommu_ops {
  * struct iommu_domain_ops - domain specific operations
  * @attach_dev: attach an iommu domain to a device
  * @detach_dev: detach an iommu domain from a device
+ * @set_dev_pasid: set an iommu domain to a pasid of device
  * @map: map a physically contiguous memory region to an iommu domain
  * @map_pages: map a physically contiguous set of pages of the same size to
  *             an iommu domain.
@@ -286,6 +287,8 @@ struct iommu_ops {
 struct iommu_domain_ops {
 	int (*attach_dev)(struct iommu_domain *domain, struct device *dev);
 	void (*detach_dev)(struct iommu_domain *domain, struct device *dev);
+	int (*set_dev_pasid)(struct iommu_domain *domain, struct device *dev,
+			     ioasid_t pasid);
 
 	int (*map)(struct iommu_domain *domain, unsigned long iova,
 		   phys_addr_t paddr, size_t size, int prot, gfp_t gfp);
@@ -680,6 +683,13 @@ int iommu_group_claim_dma_owner(struct iommu_group *group, void *owner);
 void iommu_group_release_dma_owner(struct iommu_group *group);
 bool iommu_group_dma_owner_claimed(struct iommu_group *group);
 
+int iommu_attach_device_pasid(struct iommu_domain *domain,
+			      struct device *dev, ioasid_t pasid);
+void iommu_detach_device_pasid(struct iommu_domain *domain,
+			       struct device *dev, ioasid_t pasid);
+struct iommu_domain *
+iommu_get_domain_for_dev_pasid(struct device *dev, ioasid_t pasid,
+			       unsigned int type);
 #else /* CONFIG_IOMMU_API */
 
 struct iommu_ops {};
@@ -1047,6 +1057,24 @@ static inline bool iommu_group_dma_owner_claimed(struct iommu_group *group)
 {
 	return false;
 }
+
+static inline int iommu_attach_device_pasid(struct iommu_domain *domain,
+					    struct device *dev, ioasid_t pasid)
+{
+	return -ENODEV;
+}
+
+static inline void iommu_detach_device_pasid(struct iommu_domain *domain,
+					     struct device *dev, ioasid_t pasid)
+{
+}
+
+static inline struct iommu_domain *
+iommu_get_domain_for_dev_pasid(struct device *dev, ioasid_t pasid,
+			       unsigned int type)
+{
+	return NULL;
+}
 #endif /* CONFIG_IOMMU_API */
 
 /**
diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c
index 1d28a74a0511..26aca46193c3 100644
--- a/drivers/iommu/iommu.c
+++ b/drivers/iommu/iommu.c
@@ -39,6 +39,7 @@ struct iommu_group {
 	struct kobject kobj;
 	struct kobject *devices_kobj;
 	struct list_head devices;
+	struct xarray pasid_array;
 	struct mutex mutex;
 	void *iommu_data;
 	void (*iommu_data_release)(void *iommu_data);
@@ -663,6 +664,7 @@ struct iommu_group *iommu_group_alloc(void)
 	mutex_init(&group->mutex);
 	INIT_LIST_HEAD(&group->devices);
 	INIT_LIST_HEAD(&group->entry);
+	xa_init(&group->pasid_array);
 
 	ret = ida_alloc(&iommu_group_ida, GFP_KERNEL);
 	if (ret < 0) {
@@ -3258,3 +3260,127 @@ bool iommu_group_dma_owner_claimed(struct iommu_group *group)
 	return user;
 }
 EXPORT_SYMBOL_GPL(iommu_group_dma_owner_claimed);
+
+static int __iommu_set_group_pasid(struct iommu_domain *domain,
+				   struct iommu_group *group, ioasid_t pasid)
+{
+	struct group_device *device;
+	int ret = 0;
+
+	list_for_each_entry(device, &group->devices, list) {
+		ret = domain->ops->set_dev_pasid(domain, device->dev, pasid);
+		if (ret)
+			break;
+	}
+
+	return ret;
+}
+
+/*
+ * iommu_attach_device_pasid() - Attach a domain to pasid of device
+ * @domain: the iommu domain.
+ * @dev: the attached device.
+ * @pasid: the pasid of the device.
+ *
+ * Return: 0 on success, or an error.
+ */
+int iommu_attach_device_pasid(struct iommu_domain *domain,
+			      struct device *dev, ioasid_t pasid)
+{
+	struct iommu_group *group;
+	void *curr;
+	int ret;
+
+	if (!domain->ops->set_dev_pasid)
+		return -EOPNOTSUPP;
+
+	group = iommu_group_get(dev);
+	if (!group)
+		return -ENODEV;
+
+	mutex_lock(&group->mutex);
+	curr = xa_cmpxchg(&group->pasid_array, pasid, NULL, domain, GFP_KERNEL);
+	if (curr) {
+		ret = xa_err(curr) ? : -EBUSY;
+		goto out_unlock;
+	}
+
+	ret = __iommu_set_group_pasid(domain, group, pasid);
+	if (ret) {
+		/*
+		 * Setting blocking domain to a PASID cannot fail in this path,
+		 * so we can safely error unwind a failure to attach a domain
+		 * back to the original group configuration of the PASID being
+		 * unused.
+		 */
+		__iommu_set_group_pasid(group->blocking_domain, group, pasid);
+		xa_erase(&group->pasid_array, pasid);
+	}
+out_unlock:
+	mutex_unlock(&group->mutex);
+	iommu_group_put(group);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(iommu_attach_device_pasid);
+
+/*
+ * iommu_detach_device_pasid() - Detach the domain from pasid of device
+ * @domain: the iommu domain.
+ * @dev: the attached device.
+ * @pasid: the pasid of the device.
+ *
+ * The @domain must have been attached to @pasid of the @dev with
+ * iommu_attach_device_pasid().
+ */
+void iommu_detach_device_pasid(struct iommu_domain *domain, struct device *dev,
+			       ioasid_t pasid)
+{
+	struct iommu_group *group = iommu_group_get(dev);
+
+	mutex_lock(&group->mutex);
+	WARN_ON(__iommu_set_group_pasid(group->blocking_domain, group, pasid));
+	WARN_ON(xa_erase(&group->pasid_array, pasid) != domain);
+	mutex_unlock(&group->mutex);
+
+	iommu_group_put(group);
+}
+EXPORT_SYMBOL_GPL(iommu_detach_device_pasid);
+
+/*
+ * iommu_get_domain_for_dev_pasid() - Retrieve domain for @pasid of @dev
+ * @dev: the queried device
+ * @pasid: the pasid of the device
+ * @type: matched domain type, 0 for any match
+ *
+ * This is a variant of iommu_get_domain_for_dev(). It returns the existing
+ * domain attached to pasid of a device. It's only for internal use of the
+ * IOMMU subsystem. The returned domain pointer could only be used before
+ * detaching from the device PASID.
+ *
+ * Return: attached domain on success, NULL otherwise.
+ */
+struct iommu_domain *iommu_get_domain_for_dev_pasid(struct device *dev,
+						    ioasid_t pasid,
+						    unsigned int type)
+{
+	struct iommu_domain *domain;
+	struct iommu_group *group;
+
+	group = iommu_group_get(dev);
+	if (!group)
+		return NULL;
+	/*
+	 * The xarray protects its internal state with RCU. Hence the domain
+	 * obtained is either NULL or fully formed.
+	 */
+	xa_lock(&group->pasid_array);
+	domain = xa_load(&group->pasid_array, pasid);
+	if (type && domain && domain->type != type)
+		domain = ERR_PTR(-EBUSY);
+	xa_unlock(&group->pasid_array);
+	iommu_group_put(group);
+
+	return domain;
+}
+EXPORT_SYMBOL_GPL(iommu_get_domain_for_dev_pasid);
-- 
2.25.1