[PATCH net] octeontx2-af: Fix memory scaling limitation in SR-IOV mode

[Ratheesh Kannoth]

The original code used DMA_ATTR_FORCE_CONTIGUOUS, which could exhaust
the CMA pool when a large number of VFs were requested.

Fix this by switching to the DMA streaming API. This is equivalent on
Octeon platforms, which provide full I/O coherency via the SMMU.

Cc: Leon Romanovsky <leon@xxxxxxxxxx>
Fixes: 73d33dbc0723 ("octeontx2-af: Use DMA_ATTR_FORCE_CONTIGUOUS attribute in DMA alloc")
Signed-off-by: Ratheesh Kannoth <rkannoth@xxxxxxxxxxx>

---
v9 -> v10: Updated commit message as suggested by Leon

v8 -> v9: Addressed Leon comment.
- Used kzalloc instead of kmalloc.

v7 -> v8: Addressed Leon comments.
- Replace __get_free_pages() and __GFP_COMP with kmalloc()
- Drop GFP_DMA32 retry loop and dma_capable()/phys_to_dma() mask probing
- Use dma_map_single()/dma_unmap_single() instead of dma_map_page_attrs()
  with DMA_ATTR_REQUIRE_COHERENT
- Remove defensive parameter checks and dma_max_mapping_size() from the
  allocator helper
- Move MAX_PAGE_ORDER validation to qmem_alloc()

v6 -> v7: Addressed Sashiko comments.
	https://lore.kernel.org/netdev/178863855246.219967.10510865726694393307@xxxxxxxxxx/

v5 -> v6: Addressed review comments.
	https://lore.kernel.org/netdev/20260901015621.2708182-1-rkannoth@xxxxxxxxxxx/

v4 -> v5: Fixed compilation issues.
	https://lore.kernel.org/netdev/20260831024210.208447-1-rkannoth@xxxxxxxxxxx/

v3 -> v4: Fixed compilation issues.
	https://lore.kernel.org/netdev/apTpKcN_S1xIwRbZ@rkannoth-OptiPlex-7090/

v2 -> v3: Addressed sashiko comments.
	https://sashiko.dev/#/patchset/20260825045616.3723078-1-rkannoth%40marvell.com

v1 -> v2: Rewrote patch as per sashiko comment.
---
 .../ethernet/marvell/octeontx2/af/common.h    | 45 ++++++++++++++++---
 1 file changed, 39 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/marvell/octeontx2/af/common.h b/drivers/net/ethernet/marvell/octeontx2/af/common.h
index 779413a383b7..78e42549d990 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/common.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/common.h
@@ -7,6 +7,10 @@
 #ifndef COMMON_H
 #define COMMON_H
 
+#include <linux/dma-mapping.h>
+#include <linux/gfp.h>
+#include <linux/mm.h>
+
 #include "rvu_struct.h"
 
 #define OTX2_ALIGN			128  /* Align to cacheline */
@@ -44,6 +48,33 @@ struct qmem {
 	u32		qsize;
 };
 
+static inline void *otx2_dma_alloc_coherent(struct device *dev, size_t size,
+					    dma_addr_t *dma_handle)
+{
+	dma_addr_t dma_addr;
+	void *vaddr;
+
+	vaddr = kzalloc(size, GFP_KERNEL);
+	if (!vaddr)
+		return NULL;
+
+	dma_addr = dma_map_single(dev, vaddr, size, DMA_BIDIRECTIONAL);
+	if (dma_mapping_error(dev, dma_addr)) {
+		kfree(vaddr);
+		return NULL;
+	}
+
+	*dma_handle = dma_addr;
+	return vaddr;
+}
+
+static inline void otx2_dma_free_coherent(struct device *dev, size_t size,
+					  void *vaddr, dma_addr_t dma_handle)
+{
+	dma_unmap_single(dev, dma_handle, size, DMA_BIDIRECTIONAL);
+	kfree(vaddr);
+}
+
 static inline int qmem_alloc(struct device *dev, struct qmem **q,
 			     int qsize, int entry_sz)
 {
@@ -60,8 +91,11 @@ static inline int qmem_alloc(struct device *dev, struct qmem **q,
 
 	qmem->entry_sz = entry_sz;
 	qmem->alloc_sz = (qsize * entry_sz) + OTX2_ALIGN;
-	qmem->base = dma_alloc_attrs(dev, qmem->alloc_sz, &qmem->iova,
-				     GFP_KERNEL, DMA_ATTR_FORCE_CONTIGUOUS);
+
+	if (get_order(PAGE_ALIGN(qmem->alloc_sz)) > MAX_PAGE_ORDER)
+		return -ENOMEM;
+
+	qmem->base = otx2_dma_alloc_coherent(dev, qmem->alloc_sz, &qmem->iova);
 	if (!qmem->base)
 		return -ENOMEM;
 
@@ -80,10 +114,9 @@ static inline void qmem_free(struct device *dev, struct qmem *qmem)
 		return;
 
 	if (qmem->base)
-		dma_free_attrs(dev, qmem->alloc_sz,
-			       qmem->base - qmem->align,
-			       qmem->iova - qmem->align,
-			       DMA_ATTR_FORCE_CONTIGUOUS);
+		otx2_dma_free_coherent(dev, qmem->alloc_sz,
+				       qmem->base - qmem->align,
+				       qmem->iova - qmem->align);
 	devm_kfree(dev, qmem);
 }
 
-- 
2.43.0