From: Leon Romanovsky <leonro@nvidia.com>

Separate IOVA allocation to dedicated callback so it will allow
cache of IOVA and reuse it in fast paths for devices which support
ODP (on-demand-paging) mechanism.

Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
---
 drivers/iommu/dma-iommu.c | 57 ++++++++++++++++++++++++++++++---------
 include/linux/iommu-dma.h | 11 ++++++++
 2 files changed, 56 insertions(+), 12 deletions(-)

diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c
index 65a38b5695f9..09deea2fc86b 100644
--- a/drivers/iommu/dma-iommu.c
+++ b/drivers/iommu/dma-iommu.c
@@ -358,7 +358,7 @@ int iommu_dma_init_fq(struct iommu_domain *domain)
 	atomic_set(&cookie->fq_timer_on, 0);
 	/*
 	 * Prevent incomplete fq state being observable. Pairs with path from
-	 * __iommu_dma_unmap() through iommu_dma_free_iova() to queue_iova()
+	 * __iommu_dma_unmap() through __iommu_dma_free_iova() to queue_iova()
 	 */
 	smp_wmb();
 	WRITE_ONCE(cookie->fq_domain, domain);
@@ -759,7 +759,7 @@ static int dma_info_to_prot(enum dma_data_direction dir, bool coherent,
 	}
 }
 
-static dma_addr_t iommu_dma_alloc_iova(struct iommu_domain *domain,
+static dma_addr_t __iommu_dma_alloc_iova(struct iommu_domain *domain,
 		size_t size, u64 dma_limit, struct device *dev)
 {
 	struct iommu_dma_cookie *cookie = domain->iova_cookie;
@@ -805,7 +805,7 @@ static dma_addr_t iommu_dma_alloc_iova(struct iommu_domain *domain,
 	return (dma_addr_t)iova << shift;
 }
 
-static void iommu_dma_free_iova(struct iommu_dma_cookie *cookie,
+static void __iommu_dma_free_iova(struct iommu_dma_cookie *cookie,
 		dma_addr_t iova, size_t size, struct iommu_iotlb_gather *gather)
 {
 	struct iova_domain *iovad = &cookie->iovad;
@@ -842,7 +842,7 @@ static void __iommu_dma_unmap(struct device *dev, dma_addr_t dma_addr,
 
 	if (!iotlb_gather.queued)
 		iommu_iotlb_sync(domain, &iotlb_gather);
-	iommu_dma_free_iova(cookie, dma_addr, size, &iotlb_gather);
+	__iommu_dma_free_iova(cookie, dma_addr, size, &iotlb_gather);
 }
 
 static dma_addr_t __iommu_dma_map(struct device *dev, phys_addr_t phys,
@@ -865,12 +865,12 @@ static dma_addr_t __iommu_dma_map(struct device *dev, phys_addr_t phys,
 
 	size = iova_align(iovad, size + iova_off);
 
-	iova = iommu_dma_alloc_iova(domain, size, dma_mask, dev);
+	iova = __iommu_dma_alloc_iova(domain, size, dma_mask, dev);
 	if (!iova)
 		return DMA_MAPPING_ERROR;
 
 	if (iommu_map(domain, iova, phys - iova_off, size, prot, GFP_ATOMIC)) {
-		iommu_dma_free_iova(cookie, iova, size, NULL);
+		__iommu_dma_free_iova(cookie, iova, size, NULL);
 		return DMA_MAPPING_ERROR;
 	}
 	return iova + iova_off;
@@ -973,7 +973,7 @@ static struct page **__iommu_dma_alloc_noncontiguous(struct device *dev,
 		return NULL;
 
 	size = iova_align(iovad, size);
-	iova = iommu_dma_alloc_iova(domain, size, dev->coherent_dma_mask, dev);
+	iova = __iommu_dma_alloc_iova(domain, size, dev->coherent_dma_mask, dev);
 	if (!iova)
 		goto out_free_pages;
 
@@ -1007,7 +1007,7 @@ static struct page **__iommu_dma_alloc_noncontiguous(struct device *dev,
 out_free_sg:
 	sg_free_table(sgt);
 out_free_iova:
-	iommu_dma_free_iova(cookie, iova, size, NULL);
+	__iommu_dma_free_iova(cookie, iova, size, NULL);
 out_free_pages:
 	__iommu_dma_free_pages(pages, count);
 	return NULL;
@@ -1434,7 +1434,7 @@ int iommu_dma_map_sg(struct device *dev, struct scatterlist *sg, int nents,
 	if (!iova_len)
 		return __finalise_sg(dev, sg, nents, 0);
 
-	iova = iommu_dma_alloc_iova(domain, iova_len, dma_get_mask(dev), dev);
+	iova = __iommu_dma_alloc_iova(domain, iova_len, dma_get_mask(dev), dev);
 	if (!iova) {
 		ret = -ENOMEM;
 		goto out_restore_sg;
@@ -1451,7 +1451,7 @@ int iommu_dma_map_sg(struct device *dev, struct scatterlist *sg, int nents,
 	return __finalise_sg(dev, sg, nents, iova);
 
 out_free_iova:
-	iommu_dma_free_iova(cookie, iova, iova_len, NULL);
+	__iommu_dma_free_iova(cookie, iova, iova_len, NULL);
 out_restore_sg:
 	__invalidate_sg(sg, nents);
 out:
@@ -1710,6 +1710,39 @@ size_t iommu_dma_max_mapping_size(struct device *dev)
 	return SIZE_MAX;
 }
 
+int iommu_dma_alloc_iova(struct dma_iova_state *state, phys_addr_t phys,
+			 size_t size)
+{
+	struct iommu_domain *domain = iommu_get_dma_domain(state->dev);
+	struct iommu_dma_cookie *cookie = domain->iova_cookie;
+	struct iova_domain *iovad = &cookie->iovad;
+	dma_addr_t addr;
+
+	size = iova_align(iovad, size + iova_offset(iovad, phys));
+	addr = __iommu_dma_alloc_iova(domain, size, dma_get_mask(state->dev),
+				      state->dev);
+	if (addr == DMA_MAPPING_ERROR)
+		return -EINVAL;
+
+	state->addr = addr;
+	state->size = size;
+	return 0;
+}
+
+void iommu_dma_free_iova(struct dma_iova_state *state)
+{
+	struct iommu_domain *domain = iommu_get_dma_domain(state->dev);
+	struct iommu_dma_cookie *cookie = domain->iova_cookie;
+	struct iova_domain *iovad = &cookie->iovad;
+	size_t iova_off = iova_offset(iovad, state->addr);
+	struct iommu_iotlb_gather iotlb_gather;
+
+	iommu_iotlb_gather_init(&iotlb_gather);
+	__iommu_dma_free_iova(cookie, state->addr - iova_off,
+			      iova_align(iovad, state->size + iova_off),
+			      &iotlb_gather);
+}
+
 void iommu_setup_dma_ops(struct device *dev)
 {
 	struct iommu_domain *domain = iommu_get_domain_for_dev(dev);
@@ -1746,7 +1779,7 @@ static struct iommu_dma_msi_page *iommu_dma_get_msi_page(struct device *dev,
 	if (!msi_page)
 		return NULL;
 
-	iova = iommu_dma_alloc_iova(domain, size, dma_get_mask(dev), dev);
+	iova = __iommu_dma_alloc_iova(domain, size, dma_get_mask(dev), dev);
 	if (!iova)
 		goto out_free_page;
 
@@ -1760,7 +1793,7 @@ static struct iommu_dma_msi_page *iommu_dma_get_msi_page(struct device *dev,
 	return msi_page;
 
 out_free_iova:
-	iommu_dma_free_iova(cookie, iova, size, NULL);
+	__iommu_dma_free_iova(cookie, iova, size, NULL);
 out_free_page:
 	kfree(msi_page);
 	return NULL;
diff --git a/include/linux/iommu-dma.h b/include/linux/iommu-dma.h
index 13874f95d77f..698df67b152a 100644
--- a/include/linux/iommu-dma.h
+++ b/include/linux/iommu-dma.h
@@ -57,6 +57,9 @@ void iommu_dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sgl,
 			       int nelems, enum dma_data_direction dir);
 void iommu_dma_sync_sg_for_device(struct device *dev, struct scatterlist *sgl,
 				  int nelems, enum dma_data_direction dir);
+int iommu_dma_alloc_iova(struct dma_iova_state *state, phys_addr_t phys,
+			 size_t size);
+void iommu_dma_free_iova(struct dma_iova_state *state);
 #else
 static inline bool use_dma_iommu(struct device *dev)
 {
@@ -173,5 +176,13 @@ static inline void iommu_dma_sync_sg_for_device(struct device *dev,
 						enum dma_data_direction dir)
 {
 }
+static inline int iommu_dma_alloc_iova(struct dma_iova_state *state,
+				       phys_addr_t phys, size_t size)
+{
+	return -EOPNOTSUPP;
+}
+static inline void iommu_dma_free_iova(struct dma_iova_state *state)
+{
+}
 #endif /* CONFIG_IOMMU_DMA */
 #endif /* _LINUX_IOMMU_DMA_H */
-- 
2.46.0