diff --git a/kernel/dma/Kconfig b/kernel/dma/Kconfig
index bfef21b4a9ae..c9fa0a922cba 100644
--- a/kernel/dma/Kconfig
+++ b/kernel/dma/Kconfig
@@ -181,6 +181,16 @@ config DMA_NUMA_CMA
 	  or set the node id and its size of CMA by specifying "numa_cma=
 	  <node>:size[,<node>:size]" on the kernel's command line.
 
+config CMA_SIZE_PERNUMA
+	bool "Default CMA area per NUMA node"
+	depends on DMA_NUMA_CMA
+	default y
+	help
+	  On systems with more than one NUMA node, the selected CMA
+	  area size will be also allocated on each additional node,
+	  so that most devices may have benefit from better DMA
+	  locality without an explicit command-line opt-in.
+
 comment "Default contiguous memory area size:"
 
 config CMA_SIZE_MBYTES
diff --git a/kernel/dma/contiguous.c b/kernel/dma/contiguous.c
index 03f52bd17120..799f6e9c88bd 100644
--- a/kernel/dma/contiguous.c
+++ b/kernel/dma/contiguous.c
@@ -136,6 +136,7 @@ static struct cma *dma_contiguous_numa_area[MAX_NUMNODES];
 static phys_addr_t numa_cma_size[MAX_NUMNODES] __initdata;
 static struct cma *dma_contiguous_pernuma_area[MAX_NUMNODES];
 static phys_addr_t pernuma_size_bytes __initdata;
+static bool numa_cma_configured __initdata;
 
 static int __init early_numa_cma(char *p)
 {
@@ -164,6 +165,7 @@ static int __init early_numa_cma(char *p)
 			break;
 	}
 
+	numa_cma_configured = true;
 	return 0;
 }
 early_param("numa_cma", early_numa_cma);
@@ -171,6 +173,7 @@ early_param("numa_cma", early_numa_cma);
 static int __init early_cma_pernuma(char *p)
 {
 	pernuma_size_bytes = memparse(p, &p);
+	numa_cma_configured = true;
 	return 0;
 }
 early_param("cma_pernuma", early_cma_pernuma);
@@ -199,6 +202,11 @@ static void __init dma_numa_cma_reserve(void)
 {
 	int nid;
 
+	if (IS_ENABLED(CONFIG_CMA_SIZE_PERNUMA) &&
+	    !numa_cma_configured && dma_contiguous_default_area &&
+	    nr_online_nodes > 1)
+		pernuma_size_bytes = cma_get_size(dma_contiguous_default_area);
+
 	for_each_node(nid) {
 		int ret;
 		char name[CMA_MAX_NAME];
@@ -255,8 +263,6 @@ void __init dma_contiguous_reserve(phys_addr_t limit)
 	phys_addr_t selected_limit = limit;
 	bool fixed = false;
 
-	dma_numa_cma_reserve();
-
 	pr_debug("%s(limit %08lx)\n", __func__, (unsigned long)limit);
 
 	if (size_cmdline != -1) {
@@ -312,6 +318,8 @@ void __init dma_contiguous_reserve(phys_addr_t limit)
 		if (ret)
 			pr_warn("Couldn't queue default CMA region for heap creation.");
 	}
+
+	dma_numa_cma_reserve();
 }
 
 void __weak