[RFC PATCH v1 8/8] iommu/dma: Introduce iommu_dma_prepare_msi_list()

[Andrew Jones]

Add iommu_dma_prepare_msi_list() to map an ordered physical address list
through the current domain backend. Validate that the requested granule
is a power of two no smaller than PAGE_SIZE and that every address is
aligned to it.

Refactor iommu_dma_prepare_msi() to obtain the backend granule and align
its single address before using the same list dispatcher. Convert the
DMA-IOMMU and iommufd backend entry points to consume address lists
directly.

Signed-off-by: Andrew Jones <andrew.jones@xxxxxxxxxxxxxxxx>
---
 drivers/iommu/dma-iommu.c      |  13 ++--
 drivers/iommu/dma-iommu.h      |  13 +++-
 drivers/iommu/iommu-priv.h     |   7 ++-
 drivers/iommu/iommu.c          | 109 +++++++++++++++++++++++++++------
 drivers/iommu/iommufd/driver.c |  24 +++-----
 include/linux/iommu.h          |   8 +++
 6 files changed, 126 insertions(+), 48 deletions(-)

diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c
index c256531ff19f..0699785adbfb 100644
--- a/drivers/iommu/dma-iommu.c
+++ b/drivers/iommu/dma-iommu.c
@@ -2173,7 +2173,7 @@ static bool has_msi_cookie(const struct iommu_domain *domain)
 			  domain->cookie_type == IOMMU_COOKIE_DMA_MSI);
 }
 
-static size_t cookie_msi_granule(const struct iommu_domain *domain)
+size_t iommu_dma_msi_granule(const struct iommu_domain *domain)
 {
 	switch (domain->cookie_type) {
 	case IOMMU_COOKIE_DMA_IOVA:
@@ -2303,23 +2303,20 @@ static struct iommu_dma_msi_page *iommu_dma_get_msi_page(struct device *dev,
 }
 
 int iommu_dma_sw_msi(struct iommu_domain *domain, struct msi_desc *desc,
-		     phys_addr_t msi_addr)
+		     const phys_addr_t *phys_addrs, unsigned int nr_addrs, size_t granule)
 {
 	struct device *dev = msi_desc_to_dev(desc);
 	const struct iommu_dma_msi_page *msi_page;
-	phys_addr_t phys_addr;
-	size_t granule;
 
 	if (!has_msi_cookie(domain)) {
 		msi_desc_set_iommu_msi_iova(desc, 0, 0);
 		return 0;
 	}
-
-	granule = cookie_msi_granule(domain);
-	phys_addr = ALIGN_DOWN(msi_addr, granule);
+	if (granule != iommu_dma_msi_granule(domain))
+		return -EOPNOTSUPP;
 
 	iommu_group_mutex_assert(dev);
-	msi_page = iommu_dma_get_msi_page(dev, &phys_addr, 1, granule, domain);
+	msi_page = iommu_dma_get_msi_page(dev, phys_addrs, nr_addrs, granule, domain);
 	if (!msi_page)
 		return -ENOMEM;
 
diff --git a/drivers/iommu/dma-iommu.h b/drivers/iommu/dma-iommu.h
index 040d00252563..bf9cd4102d35 100644
--- a/drivers/iommu/dma-iommu.h
+++ b/drivers/iommu/dma-iommu.h
@@ -19,8 +19,9 @@ int iommu_dma_init_fq(struct iommu_domain *domain);
 
 void iommu_dma_get_resv_regions(struct device *dev, struct list_head *list);
 
+size_t iommu_dma_msi_granule(const struct iommu_domain *domain);
 int iommu_dma_sw_msi(struct iommu_domain *domain, struct msi_desc *desc,
-		     phys_addr_t msi_addr);
+		     const phys_addr_t *phys_addrs, unsigned int nr_addrs, size_t granule);
 
 extern bool iommu_dma_forcedac;
 
@@ -53,8 +54,14 @@ static inline void iommu_dma_get_resv_regions(struct device *dev, struct list_he
 {
 }
 
-static inline int iommu_dma_sw_msi(struct iommu_domain *domain,
-				   struct msi_desc *desc, phys_addr_t msi_addr)
+static inline size_t iommu_dma_msi_granule(const struct iommu_domain *domain)
+{
+	return 0;
+}
+
+static inline int iommu_dma_sw_msi(struct iommu_domain *domain, struct msi_desc *desc,
+				   const phys_addr_t *phys_addrs, unsigned int nr_addrs,
+				   size_t granule)
 {
 	return -ENODEV;
 }
diff --git a/drivers/iommu/iommu-priv.h b/drivers/iommu/iommu-priv.h
index aaffad5854fc..1122c99566d5 100644
--- a/drivers/iommu/iommu-priv.h
+++ b/drivers/iommu/iommu-priv.h
@@ -54,10 +54,11 @@ int iommu_replace_group_handle(struct iommu_group *group,
 
 #if IS_ENABLED(CONFIG_IOMMUFD_DRIVER_CORE) && IS_ENABLED(CONFIG_IRQ_MSI_IOMMU)
 int iommufd_sw_msi(struct iommu_domain *domain, struct msi_desc *desc,
-		   phys_addr_t msi_addr);
+		   const phys_addr_t *phys_addrs, unsigned int nr_addrs, size_t granule);
 #else /* !CONFIG_IOMMUFD_DRIVER_CORE || !CONFIG_IRQ_MSI_IOMMU */
-static inline int iommufd_sw_msi(struct iommu_domain *domain,
-				 struct msi_desc *desc, phys_addr_t msi_addr)
+static inline int iommufd_sw_msi(struct iommu_domain *domain, struct msi_desc *desc,
+				 const phys_addr_t *phys_addrs, unsigned int nr_addrs,
+				 size_t granule)
 {
 	return -EOPNOTSUPP;
 }
diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c
index a3dea7353500..692e793c624e 100644
--- a/drivers/iommu/iommu.c
+++ b/drivers/iommu/iommu.c
@@ -4223,42 +4223,115 @@ void pci_dev_reset_iommu_done(struct pci_dev *pdev)
 EXPORT_SYMBOL_GPL(pci_dev_reset_iommu_done);
 
 #if IS_ENABLED(CONFIG_IRQ_MSI_IOMMU)
+static int __iommu_dma_prepare_msi_list(struct iommu_group *group, struct msi_desc *desc,
+					const phys_addr_t *phys_addrs, unsigned int nr_addrs,
+					size_t granule)
+{
+	if (!group->domain || group->domain->type == IOMMU_DOMAIN_IDENTITY)
+		return 0;
+
+	switch (group->domain->cookie_type) {
+	case IOMMU_COOKIE_DMA_MSI:
+	case IOMMU_COOKIE_DMA_IOVA:
+		return iommu_dma_sw_msi(group->domain, desc, phys_addrs, nr_addrs, granule);
+	case IOMMU_COOKIE_IOMMUFD:
+		return iommufd_sw_msi(group->domain, desc, phys_addrs, nr_addrs, granule);
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static int iommu_dma_validate_msi_list(const phys_addr_t *phys_addrs, unsigned int nr_addrs,
+				       size_t granule)
+{
+	unsigned int i;
+
+	if (!nr_addrs || granule < PAGE_SIZE || !is_power_of_2(granule) ||
+	    nr_addrs > SIZE_MAX / granule)
+		return -EINVAL;
+
+	for (i = 0; i < nr_addrs; i++)
+		if (!IS_ALIGNED(phys_addrs[i], granule))
+			return -EINVAL;
+
+	return 0;
+}
+
+/**
+ * iommu_dma_prepare_msi_list() - Map MSI pages in the IOMMU domain
+ * @desc: MSI descriptor to update with the base IOVA
+ * @phys_addrs: Ordered MSI target physical addresses
+ * @nr_addrs: Number of addresses in @phys_addrs
+ * @granule: Mapping granule for every address
+ *
+ * @nr_addrs must be nonzero and @granule must be a power of two no smaller than
+ * PAGE_SIZE. Every address must be aligned to @granule. The addresses are mapped
+ * in order to one contiguous IOVA range and may repeat. The list is consumed
+ * synchronously and is not retained.
+ *
+ * When a software MSI mapping is required, the backend records the base IOVA
+ * and granule shift in @desc. Otherwise, @desc is left unchanged.
+ *
+ * Return: 0 on success, -EINVAL if the parameters are invalid, -EOPNOTSUPP if
+ * the domain backend cannot provide the mapping, or another negative error
+ * code from the backend.
+ */
+int iommu_dma_prepare_msi_list(struct msi_desc *desc, const phys_addr_t *phys_addrs,
+			       unsigned int nr_addrs, size_t granule)
+{
+	struct device *dev = msi_desc_to_dev(desc);
+	struct iommu_group *group = dev->iommu_group;
+	int ret;
+
+	ret = iommu_dma_validate_msi_list(phys_addrs, nr_addrs, granule);
+	if (ret || !group)
+		return ret;
+
+	mutex_lock(&group->mutex);
+	ret = __iommu_dma_prepare_msi_list(group, desc, phys_addrs, nr_addrs, granule);
+	mutex_unlock(&group->mutex);
+	return ret;
+}
+
 /**
  * iommu_dma_prepare_msi() - Map the MSI page in the IOMMU domain
  * @desc: MSI descriptor, will store the MSI page
  * @msi_addr: MSI target address to be mapped
  *
- * The implementation of sw_msi() should take msi_addr and map it to
- * an IOVA in the domain and call msi_desc_set_iommu_msi_iova() with the
- * mapping information.
- *
  * Return: 0 on success or negative error code if the mapping failed.
  */
 int iommu_dma_prepare_msi(struct msi_desc *desc, phys_addr_t msi_addr)
 {
 	struct device *dev = msi_desc_to_dev(desc);
 	struct iommu_group *group = dev->iommu_group;
+	phys_addr_t phys_addr;
+	size_t granule;
 	int ret = 0;
 
 	if (!group)
 		return 0;
 
 	mutex_lock(&group->mutex);
-	/* An IDENTITY domain must pass through */
-	if (group->domain && group->domain->type != IOMMU_DOMAIN_IDENTITY) {
-		switch (group->domain->cookie_type) {
-		case IOMMU_COOKIE_DMA_MSI:
-		case IOMMU_COOKIE_DMA_IOVA:
-			ret = iommu_dma_sw_msi(group->domain, desc, msi_addr);
-			break;
-		case IOMMU_COOKIE_IOMMUFD:
-			ret = iommufd_sw_msi(group->domain, desc, msi_addr);
-			break;
-		default:
-			ret = -EOPNOTSUPP;
-			break;
-		}
+	if (!group->domain || group->domain->type == IOMMU_DOMAIN_IDENTITY)
+		goto out_unlock;
+
+	switch (group->domain->cookie_type) {
+	case IOMMU_COOKIE_DMA_MSI:
+	case IOMMU_COOKIE_DMA_IOVA:
+		granule = iommu_dma_msi_granule(group->domain);
+		break;
+	case IOMMU_COOKIE_IOMMUFD:
+		granule = PAGE_SIZE;
+		break;
+	default:
+		ret = -EOPNOTSUPP;
+		goto out_unlock;
 	}
+
+	phys_addr = ALIGN_DOWN(msi_addr, granule);
+	ret = __iommu_dma_prepare_msi_list(group, desc, &phys_addr, 1, granule);
+
+out_unlock:
 	mutex_unlock(&group->mutex);
 	return ret;
 }
diff --git a/drivers/iommu/iommufd/driver.c b/drivers/iommu/iommufd/driver.c
index 45278c11c688..72e9ce63a5ee 100644
--- a/drivers/iommu/iommufd/driver.c
+++ b/drivers/iommu/iommufd/driver.c
@@ -419,9 +419,14 @@ static void iommufd_sw_msi_set_required(struct iommufd_group *igroup,
 	}
 }
 
-static int iommufd_sw_msi_list(struct iommu_domain *domain, struct msi_desc *desc,
-			       const phys_addr_t *phys_addrs, unsigned int nr_addrs,
-			       size_t granule)
+/*
+ * Called by the irq code if the platform translates the MSI addresses through the
+ * IOMMU. phys_addrs are the physical addresses of the MSI pages. iommufd will
+ * allocate contiguous fd global iovas for the physical pages that are the same on
+ * all domains and devices.
+ */
+int iommufd_sw_msi(struct iommu_domain *domain, struct msi_desc *desc,
+		   const phys_addr_t *phys_addrs, unsigned int nr_addrs, size_t granule)
 {
 	struct device *dev = msi_desc_to_dev(desc);
 	struct iommufd_hwpt_paging *hwpt_paging;
@@ -505,19 +510,6 @@ static int iommufd_sw_msi_list(struct iommu_domain *domain, struct msi_desc *des
 	return rc;
 }
 
-/*
- * Called by the irq code if the platform translates the MSI address through the
- * IOMMU. msi_addr is the physical address of the MSI page. iommufd will
- * allocate a fd global iova for the physical page that is the same on all
- * domains and devices.
- */
-int iommufd_sw_msi(struct iommu_domain *domain, struct msi_desc *desc,
-		   phys_addr_t msi_addr)
-{
-	phys_addr_t phys_addr = msi_addr & PAGE_MASK;
-
-	return iommufd_sw_msi_list(domain, desc, &phys_addr, 1, PAGE_SIZE);
-}
 EXPORT_SYMBOL_NS_GPL(iommufd_sw_msi, "IOMMUFD");
 #endif
 
diff --git a/include/linux/iommu.h b/include/linux/iommu.h
index ac43b8b93f14..bf08be172e40 100644
--- a/include/linux/iommu.h
+++ b/include/linux/iommu.h
@@ -1561,8 +1561,16 @@ static inline void pci_dev_reset_iommu_done(struct pci_dev *pdev)
 
 #ifdef CONFIG_IRQ_MSI_IOMMU
 #ifdef CONFIG_IOMMU_API
+int iommu_dma_prepare_msi_list(struct msi_desc *desc, const phys_addr_t *phys_addrs,
+			       unsigned int nr_addrs, size_t granule);
 int iommu_dma_prepare_msi(struct msi_desc *desc, phys_addr_t msi_addr);
 #else
+static inline int iommu_dma_prepare_msi_list(struct msi_desc *desc, const phys_addr_t *phys_addrs,
+					     unsigned int nr_addrs, size_t granule)
+{
+	return 0;
+}
+
 static inline int iommu_dma_prepare_msi(struct msi_desc *desc,
 					phys_addr_t msi_addr)
 {
-- 
2.43.0