[RFC 01/11] dma-contiguous: pass the NUMA node to dma_alloc_contiguous()

[Jakub Kicinski <kuba@kernel.org>]

dma_alloc_contiguous() picks the per-numa CMA area based on the node of
the device. Let the callers pass the node in, so that the DMA allocators
can be extended to place memory on a node other than the device's.

All callers pass dev_to_node() for now, no functional change.

Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/linux/dma-map-ops.h |  5 +++--
 drivers/iommu/dma-iommu.c   |  2 +-
 kernel/dma/contiguous.c     | 12 +++++-------
 kernel/dma/direct.c         |  2 +-
 kernel/dma/ops_helpers.c    |  5 +++--
 5 files changed, 13 insertions(+), 13 deletions(-)

diff --git a/include/linux/dma-map-ops.h b/include/linux/dma-map-ops.h
index 8fae2b7deb20..3f1e4cd3392e 100644
--- a/include/linux/dma-map-ops.h
+++ b/include/linux/dma-map-ops.h
@@ -102,7 +102,8 @@ struct page *dma_alloc_from_contiguous(struct device *dev, size_t count,
 				       unsigned int order, bool no_warn);
 bool dma_release_from_contiguous(struct device *dev, struct page *pages,
 				 int count);
-struct page *dma_alloc_contiguous(struct device *dev, size_t size, gfp_t gfp);
+struct page *dma_alloc_contiguous(struct device *dev, size_t size, gfp_t gfp,
+				  int nid);
 void dma_free_contiguous(struct device *dev, struct page *page, size_t size);
 
 void dma_contiguous_early_fixup(phys_addr_t base, unsigned long size);
@@ -136,7 +137,7 @@ static inline bool dma_release_from_contiguous(struct device *dev,
 }
 /* Use fallback alloc() and free() when CONFIG_DMA_CMA=n */
 static inline struct page *dma_alloc_contiguous(struct device *dev, size_t size,
-		gfp_t gfp)
+		gfp_t gfp, int nid)
 {
 	return NULL;
 }
diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c
index 68ee57800fef..bb82ba3be440 100644
--- a/drivers/iommu/dma-iommu.c
+++ b/drivers/iommu/dma-iommu.c
@@ -1627,7 +1627,7 @@ static void *iommu_dma_alloc_pages(struct device *dev, size_t size,
 	struct page *page = NULL;
 	void *cpu_addr;
 
-	page = dma_alloc_contiguous(dev, alloc_size, gfp);
+	page = dma_alloc_contiguous(dev, alloc_size, gfp, node);
 	if (!page)
 		page = alloc_pages_node(node, gfp, get_order(alloc_size));
 	if (!page)
diff --git a/kernel/dma/contiguous.c b/kernel/dma/contiguous.c
index 66093460584e..b5944ffefca7 100644
--- a/kernel/dma/contiguous.c
+++ b/kernel/dma/contiguous.c
@@ -402,22 +402,20 @@ static struct page *cma_alloc_aligned(struct cma *cma, size_t size, gfp_t gfp)
  * @dev:   Pointer to device for which the allocation is performed.
  * @size:  Requested allocation size.
  * @gfp:   Allocation flags.
+ * @nid:   NUMA node to allocate the memory on.
  *
  * tries to use device specific contiguous memory area if available, or it
- * tries to use per-numa cma, if the allocation fails, it will fallback to
- * try default global one.
+ * tries to use per-numa cma of @nid, if the allocation fails, it will fallback
+ * to try default global one.
  *
  * Note that it bypass one-page size of allocations from the per-numa and
  * global area as the addresses within one page are always contiguous, so
  * there is no need to waste CMA pages for that kind; it also helps reduce
  * fragmentations.
  */
-struct page *dma_alloc_contiguous(struct device *dev, size_t size, gfp_t gfp)
+struct page *dma_alloc_contiguous(struct device *dev, size_t size, gfp_t gfp,
+				  int nid)
 {
-#ifdef CONFIG_DMA_NUMA_CMA
-	int nid = dev_to_node(dev);
-#endif
-
 	/* CMA can be used only in the context which permits sleeping */
 	if (!gfpflags_allow_blocking(gfp))
 		return NULL;
diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c
index da665ca22d5c..9787a45f46f1 100644
--- a/kernel/dma/direct.c
+++ b/kernel/dma/direct.c
@@ -124,7 +124,7 @@ static struct page *__dma_direct_alloc_pages(struct device *dev, size_t size,
 	WARN_ON_ONCE(!PAGE_ALIGNED(size));
 
 	gfp |= dma_direct_optimal_gfp_mask(dev, &phys_limit);
-	page = dma_alloc_contiguous(dev, size, gfp);
+	page = dma_alloc_contiguous(dev, size, gfp, node);
 	if (page) {
 		if (dma_coherent_ok(dev, page_to_phys(page), size) &&
 		    (allow_highmem || !PageHighMem(page)))
diff --git a/kernel/dma/ops_helpers.c b/kernel/dma/ops_helpers.c
index 6b5f9208d31c..28a3c958158b 100644
--- a/kernel/dma/ops_helpers.c
+++ b/kernel/dma/ops_helpers.c
@@ -63,12 +63,13 @@ struct page *dma_common_alloc_pages(struct device *dev, size_t size,
 		dma_addr_t *dma_handle, enum dma_data_direction dir, gfp_t gfp)
 {
 	const struct dma_map_ops *ops = get_dma_ops(dev);
+	int nid = dev_to_node(dev);
 	struct page *page;
 	phys_addr_t phys;
 
-	page = dma_alloc_contiguous(dev, size, gfp);
+	page = dma_alloc_contiguous(dev, size, gfp, nid);
 	if (!page)
-		page = alloc_pages_node(dev_to_node(dev), gfp, get_order(size));
+		page = alloc_pages_node(nid, gfp, get_order(size));
 	if (!page)
 		return NULL;
 
-- 
2.56.0