[RFC PATCH v1 07/18] iommu/dma: Provide an interface to allow preallocate IOVA

[Leon Romanovsky]

From: Leon Romanovsky <leonro at 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 at nvidia.com>
---
 drivers/iommu/dma-iommu.c | 50 +++++++++++++++++++++++++++++----------
 1 file changed, 38 insertions(+), 12 deletions(-)

diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c
index 89e34503e0bb..0b5ca6961940 100644
--- a/drivers/iommu/dma-iommu.c
+++ b/drivers/iommu/dma-iommu.c
@@ -357,7 +357,7 @@ 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);
@@ -745,7 +745,7 @@ 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;
@@ -791,7 +791,7 @@ 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;
@@ -828,7 +828,7 @@ 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,
@@ -851,12 +851,12 @@ 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;
@@ -960,7 +960,7 @@ 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;
 
@@ -994,7 +994,7 @@ 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;
@@ -1429,7 +1429,7 @@ static int iommu_dma_map_sg(struct device *dev, struct scatterlist *sg,
 	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;
@@ -1446,7 +1446,7 @@ static int iommu_dma_map_sg(struct device *dev, struct scatterlist *sg,
 	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:
@@ -1707,6 +1707,30 @@ static size_t iommu_dma_max_mapping_size(struct device *dev)
 	return SIZE_MAX;
 }
 
+static dma_addr_t iommu_dma_alloc_iova(struct device *dev, size_t size)
+{
+	struct iommu_domain *domain = iommu_get_dma_domain(dev);
+	struct iommu_dma_cookie *cookie = domain->iova_cookie;
+	struct iova_domain *iovad = &cookie->iovad;
+	dma_addr_t dma_mask = dma_get_mask(dev);
+
+	size = iova_align(iovad, size);
+	return __iommu_dma_alloc_iova(domain, size, dma_mask, dev);
+}
+
+static void iommu_dma_free_iova(struct device *dev, dma_addr_t iova,
+				size_t size)
+{
+	struct iommu_domain *domain = iommu_get_dma_domain(dev);
+	struct iommu_dma_cookie *cookie = domain->iova_cookie;
+	struct iova_domain *iovad = &cookie->iovad;
+	struct iommu_iotlb_gather iotlb_gather;
+
+	size = iova_align(iovad, size);
+	iommu_iotlb_gather_init(&iotlb_gather);
+	__iommu_dma_free_iova(cookie, iova, size, &iotlb_gather);
+}
+
 static const struct dma_map_ops iommu_dma_ops = {
 	.flags			= DMA_F_PCI_P2PDMA_SUPPORTED |
 				  DMA_F_CAN_SKIP_SYNC,
@@ -1731,6 +1755,8 @@ static const struct dma_map_ops iommu_dma_ops = {
 	.get_merge_boundary	= iommu_dma_get_merge_boundary,
 	.opt_mapping_size	= iommu_dma_opt_mapping_size,
 	.max_mapping_size       = iommu_dma_max_mapping_size,
+	.alloc_iova		= iommu_dma_alloc_iova,
+	.free_iova		= iommu_dma_free_iova,
 };
 
 void iommu_setup_dma_ops(struct device *dev)
@@ -1773,7 +1799,7 @@ 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;
 
@@ -1787,7 +1813,7 @@ 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;
-- 
2.45.2