[PATCH v1 01/14] iommu: Add iommu_get_unmanaged_domain helper

[Nicolin Chen]

The nature of ITS virtualization on ARM is done via hypercalls, so kernel
handles all IOVA mappings for the MSI doorbell in iommu_dma_prepare_msi()
and iommu_dma_compose_msi_msg(). The current virtualization solution with
a 2-stage nested translation setup is to do 1:1 IOVA mappings at stage-1
guest-level IO page table via a RMR region in guest-level IORT, aligning
with an IOVA region that's predefined and mapped in the host kernel:

  [stage-2 host level]
  #define MSI_IOVA_BASE		0x8000000
  #define MSI_IOVA_LENGTH	0x100000
  ...
  iommu_get_msi_cookie():
	cookie->msi_iova = MSI_IOVA_BASE;
  ...
  iommu_dma_prepare_msi(its_pa):
	domain = iommu_get_domain_for_dev(dev);
	iommu_dma_get_msi_page(its_pa, domain):
		cookie = domain->iova_cookie;
		iova = iommu_dma_alloc_iova():
			return cookie->msi_iova - size;
		iommu_map(iova, its_pa, ...);

  [stage-1 guest level]
  // Define in IORT a RMR [MSI_IOVA_BASE, MSI_IOVA_LENGTH]
  ...
  iommu_create_device_direct_mappings():
	iommu_map(iova=MSI_IOVA_BASE, pa=MSI_IOVA_BASE, len=MSI_IOVA_LENGTH);

This solution calling iommu_get_domain_for_dev() needs the device to get
attached to a host-level iommu_domain that has the msi_cookie.

On the other hand, IOMMUFD designs two iommu_domain objects to represent
the two stages: a stage-1 domain (IOMMU_DOMAIN_NESTED type) and a stage-2
domain (IOMMU_DOMAIN_UNMANAGED type). In this design, the device will be
attached to the stage-1 domain representing a guest-level IO page table,
or a Context Descriptor Table in SMMU's term.

This is obviously a mismatch, as the iommu_get_domain_for_dev() does not
return the correct domain pointer in iommu_dma_prepare_msi().

Add an iommu_get_unmanaged_domain helper to allow drivers to return the
correct IOMMU_DOMAIN_UNMANAGED iommu_domain having the IOVA mappings for
the msi_cookie. Keep it in the iommu-priv header for internal use only.

Suggested-by: Jason Gunthorpe <jgg at nvidia.com>
Signed-off-by: Nicolin Chen <nicolinc at nvidia.com>
---
 drivers/iommu/dma-iommu.c  |  5 +++--
 drivers/iommu/iommu-priv.h | 15 +++++++++++++++
 include/linux/iommu.h      |  2 ++
 3 files changed, 20 insertions(+), 2 deletions(-)

diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c
index 99b2646cb5c7..6b0409d0ff85 100644
--- a/drivers/iommu/dma-iommu.c
+++ b/drivers/iommu/dma-iommu.c
@@ -31,6 +31,7 @@
 #include <linux/vmalloc.h>
 
 #include "dma-iommu.h"
+#include "iommu-priv.h"
 
 struct iommu_dma_msi_page {
 	struct list_head	list;
@@ -1652,7 +1653,7 @@ static struct iommu_dma_msi_page *iommu_dma_get_msi_page(struct device *dev,
 int iommu_dma_prepare_msi(struct msi_desc *desc, phys_addr_t msi_addr)
 {
 	struct device *dev = msi_desc_to_dev(desc);
-	struct iommu_domain *domain = iommu_get_domain_for_dev(dev);
+	struct iommu_domain *domain = iommu_get_unmanaged_domain(dev);
 	struct iommu_dma_msi_page *msi_page;
 	static DEFINE_MUTEX(msi_prepare_lock); /* see below */
 
@@ -1685,7 +1686,7 @@ int iommu_dma_prepare_msi(struct msi_desc *desc, phys_addr_t msi_addr)
 void iommu_dma_compose_msi_msg(struct msi_desc *desc, struct msi_msg *msg)
 {
 	struct device *dev = msi_desc_to_dev(desc);
-	const struct iommu_domain *domain = iommu_get_domain_for_dev(dev);
+	const struct iommu_domain *domain = iommu_get_unmanaged_domain(dev);
 	const struct iommu_dma_msi_page *msi_page;
 
 	msi_page = msi_desc_get_iommu_cookie(desc);
diff --git a/drivers/iommu/iommu-priv.h b/drivers/iommu/iommu-priv.h
index a6e694f59f64..da8044da9ad8 100644
--- a/drivers/iommu/iommu-priv.h
+++ b/drivers/iommu/iommu-priv.h
@@ -15,6 +15,21 @@ static inline const struct iommu_ops *dev_iommu_ops(struct device *dev)
 	return dev->iommu->iommu_dev->ops;
 }
 
+static inline struct iommu_domain *iommu_get_unmanaged_domain(struct device *dev)
+{
+	const struct iommu_ops *ops;
+
+	if (!dev->iommu || !dev->iommu->iommu_dev)
+		goto attached_domain;
+
+	ops = dev_iommu_ops(dev);
+	if (ops->get_unmanaged_domain)
+		return ops->get_unmanaged_domain(dev);
+
+attached_domain:
+	return iommu_get_domain_for_dev(dev);
+}
+
 int iommu_group_replace_domain(struct iommu_group *group,
 			       struct iommu_domain *new_domain);
 
diff --git a/include/linux/iommu.h b/include/linux/iommu.h
index 080278c8154d..76c65cc4fc15 100644
--- a/include/linux/iommu.h
+++ b/include/linux/iommu.h
@@ -275,6 +275,8 @@ struct iommu_ops {
 						  struct iommu_domain *parent,
 						  const void *user_data);
 
+	struct iommu_domain *(*get_unmanaged_domain)(struct device *dev);
+
 	struct iommu_device *(*probe_device)(struct device *dev);
 	void (*release_device)(struct device *dev);
 	void (*probe_finalize)(struct device *dev);
-- 
2.39.2