[PATCH] dma-mapping: use exact allocation for DMA pages

[Qingfang Deng]

DMA page allocation fallbacks use alloc_pages_node() with get_order(size),
wasting the unused tail for non-power-of-two requests.

Use alloc_pages_exact_nid() and free_pages_exact() so that a buddy
fallback retains only requested pages.

Signed-off-by: Qingfang Deng <qingfang.deng@xxxxxxxxx>
---
 drivers/iommu/dma-iommu.c   | 10 ++++++----
 include/linux/dma-map-ops.h |  2 +-
 kernel/dma/contiguous.c     |  6 +++---
 kernel/dma/direct.c         |  8 +++++---
 kernel/dma/ops_helpers.c    | 11 +++++++----
 5 files changed, 22 insertions(+), 15 deletions(-)

diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c
index 58c624513cd4..8f262c83802c 100644
--- a/drivers/iommu/dma-iommu.c
+++ b/drivers/iommu/dma-iommu.c
@@ -1628,10 +1628,12 @@ static void *iommu_dma_alloc_pages(struct device *dev, size_t size,
 	void *cpu_addr;
 
 	page = dma_alloc_contiguous(dev, alloc_size, gfp);
-	if (!page)
-		page = alloc_pages_node(node, gfp, get_order(alloc_size));
-	if (!page)
-		return NULL;
+	if (!page) {
+		cpu_addr = alloc_pages_exact_nid(node, alloc_size, gfp);
+		if (!cpu_addr)
+			return NULL;
+		page = virt_to_page(cpu_addr);
+	}
 
 	if (!coherent || PageHighMem(page)) {
 		pgprot_t prot = dma_pgprot(dev, PAGE_KERNEL, attrs);
diff --git a/include/linux/dma-map-ops.h b/include/linux/dma-map-ops.h
index 8fae2b7deb20..3ef3003713a6 100644
--- a/include/linux/dma-map-ops.h
+++ b/include/linux/dma-map-ops.h
@@ -143,7 +143,7 @@ static inline struct page *dma_alloc_contiguous(struct device *dev, size_t size,
 static inline void dma_free_contiguous(struct device *dev, struct page *page,
 		size_t size)
 {
-	__free_pages(page, get_order(size));
+	free_pages_exact(page_address(page), size);
 }
 #endif /* CONFIG_DMA_CMA*/
 
diff --git a/kernel/dma/contiguous.c b/kernel/dma/contiguous.c
index 66093460584e..90937dc7c627 100644
--- a/kernel/dma/contiguous.c
+++ b/kernel/dma/contiguous.c
@@ -451,8 +451,8 @@ struct page *dma_alloc_contiguous(struct device *dev, size_t size, gfp_t gfp)
  *
  * This function releases memory allocated by dma_alloc_contiguous(). As the
  * cma_release returns false when provided pages do not belong to contiguous
- * area and true otherwise, this function then does a fallback __free_pages()
- * upon a false-return.
+ * area and true otherwise, this function then does a fallback
+ * free_pages_exact() upon a false-return.
  */
 void dma_free_contiguous(struct device *dev, struct page *page, size_t size)
 {
@@ -476,7 +476,7 @@ void dma_free_contiguous(struct device *dev, struct page *page, size_t size)
 	}
 
 	/* not in any cma, free from buddy */
-	__free_pages(page, get_order(size));
+	free_pages_exact(page_address(page), size);
 }
 
 /*
diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c
index da665ca22d5c..ea64453d7370 100644
--- a/kernel/dma/direct.c
+++ b/kernel/dma/direct.c
@@ -120,6 +120,7 @@ static struct page *__dma_direct_alloc_pages(struct device *dev, size_t size,
 	int node = dev_to_node(dev);
 	struct page *page;
 	u64 phys_limit;
+	void *va;
 
 	WARN_ON_ONCE(!PAGE_ALIGNED(size));
 
@@ -133,9 +134,9 @@ static struct page *__dma_direct_alloc_pages(struct device *dev, size_t size,
 		dma_free_contiguous(dev, page, size);
 	}
 
-	while ((page = alloc_pages_node(node, gfp, get_order(size)))
-	       && !dma_coherent_ok(dev, page_to_phys(page), size)) {
-		__free_pages(page, get_order(size));
+	while ((va = alloc_pages_exact_nid(node, size, gfp)) &&
+	       !dma_coherent_ok(dev, virt_to_phys(va), size)) {
+		free_pages_exact(va, size);
 
 		if (IS_ENABLED(CONFIG_ZONE_DMA32) &&
 		    phys_limit < DMA_BIT_MASK(64) &&
@@ -146,6 +147,7 @@ static struct page *__dma_direct_alloc_pages(struct device *dev, size_t size,
 		else
 			return NULL;
 	}
+	page = va ? virt_to_page(va) : NULL;
 
 	return page;
 }
diff --git a/kernel/dma/ops_helpers.c b/kernel/dma/ops_helpers.c
index 6b5f9208d31c..5cdf3f60cf47 100644
--- a/kernel/dma/ops_helpers.c
+++ b/kernel/dma/ops_helpers.c
@@ -67,10 +67,13 @@ struct page *dma_common_alloc_pages(struct device *dev, size_t size,
 	phys_addr_t phys;
 
 	page = dma_alloc_contiguous(dev, size, gfp);
-	if (!page)
-		page = alloc_pages_node(dev_to_node(dev), gfp, get_order(size));
-	if (!page)
-		return NULL;
+	if (!page) {
+		void *va = alloc_pages_exact_nid(dev_to_node(dev), size, gfp);
+
+		if (!va)
+			return NULL;
+		page = virt_to_page(va);
+	}
 
 	phys = page_to_phys(page);
 	if (use_dma_iommu(dev))
-- 
2.43.0