dma-contiguous: support per-numa CMA for all architectures

In the commit b7176c2 ("dma-contiguous: provide the ability to
reserve per-numa CMA"), Barry adds DMA_PERNUMA_CMA for ARM64.

But this feature is architecture independent, so support per-numa CMA
for all architectures, and enable it by default if NUMA.

Signed-off-by: Yajun Deng <yajun.deng@linux.dev>
Tested-by: Yicong Yang <yangyicong@hisilicon.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>

Author: Yajun Deng

Documentation/admin-guide/kernel-parameters.txt

@@ -696,7 +696,7 @@
 			kernel/dma/contiguous.c
 
 	cma_pernuma=nn[MG]
-			[ARM64,KNL,CMA]
+			[KNL,CMA]
 			Sets the size of kernel per-numa memory area for
 			contiguous memory allocations. A value of 0 disables
 			per-numa CMA altogether. And If this option is not

arch/arm64/mm/init.c

@@ -434,8 +434,6 @@ void __init bootmem_init(void)
 	arm64_hugetlb_cma_reserve();
 #endif
 
-	dma_pernuma_cma_reserve();
-
 	kvm_hyp_reserve();
 
 	/*

include/linux/dma-map-ops.h

@@ -169,12 +169,6 @@ static inline void dma_free_contiguous(struct device *dev, struct page *page,
 }
 #endif /* CONFIG_DMA_CMA*/
 
-#ifdef CONFIG_DMA_PERNUMA_CMA
-void dma_pernuma_cma_reserve(void);
-#else
-static inline void dma_pernuma_cma_reserve(void) { }
-#endif /* CONFIG_DMA_PERNUMA_CMA */
-
 #ifdef CONFIG_DMA_DECLARE_COHERENT
 int dma_declare_coherent_memory(struct device *dev, phys_addr_t phys_addr,
 		dma_addr_t device_addr, size_t size);

kernel/dma/Kconfig

@@ -147,10 +147,10 @@ if  DMA_CMA
 
 config DMA_PERNUMA_CMA
 	bool "Enable separate DMA Contiguous Memory Area for each NUMA Node"
-	default NUMA && ARM64
+	default NUMA
 	help
-	  Enable this option to get pernuma CMA areas so that devices like
-	  ARM64 SMMU can get local memory by DMA coherent APIs.
+	  Enable this option to get pernuma CMA areas so that NUMA devices
+	  can get local memory by DMA coherent APIs.
 
 	  You can set the size of pernuma CMA by specifying "cma_pernuma=size"
 	  on the kernel's command line.

kernel/dma/contiguous.c

@@ -128,7 +128,7 @@ static inline __maybe_unused phys_addr_t cma_early_percent_memory(void)
 #endif
 
 #ifdef CONFIG_DMA_PERNUMA_CMA
-void __init dma_pernuma_cma_reserve(void)
+static void __init dma_pernuma_cma_reserve(void)
 {
 	int nid;
 
@@ -153,6 +153,10 @@ void __init dma_pernuma_cma_reserve(void)
 			(unsigned long long)pernuma_size_bytes / SZ_1M, nid);
 	}
 }
+#else
+static inline void __init dma_pernuma_cma_reserve(void)
+{
+}
 #endif
 
 /**
@@ -171,6 +175,8 @@ void __init dma_contiguous_reserve(phys_addr_t limit)
 	phys_addr_t selected_limit = limit;
 	bool fixed = false;
 
+	dma_pernuma_cma_reserve();
+
 	pr_debug("%s(limit %08lx)\n", __func__, (unsigned long)limit);
 
 	if (size_cmdline != -1) {