diff --git a/include/linux/dma-direct.h b/include/linux/dma-direct.h
index 5184735..ab2e20c 100644
--- a/include/linux/dma-direct.h
+++ b/include/linux/dma-direct.h
@@ -69,6 +69,7 @@ static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size,
 u64 dma_direct_get_required_mask(struct device *dev);
 gfp_t dma_direct_optimal_gfp_mask(struct device *dev, u64 dma_mask,
 				  u64 *phys_mask);
+bool dma_coherent_ok(struct device *dev, phys_addr_t phys, size_t size);
 void *dma_direct_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle,
 		gfp_t gfp, unsigned long attrs);
 void dma_direct_free(struct device *dev, size_t size, void *cpu_addr,
diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c
index 95866b6..67f060b 100644
--- a/kernel/dma/direct.c
+++ b/kernel/dma/direct.c
@@ -70,7 +70,7 @@ gfp_t dma_direct_optimal_gfp_mask(struct device *dev, u64 dma_mask,
 	return 0;
 }
 
-static bool dma_coherent_ok(struct device *dev, phys_addr_t phys, size_t size)
+bool dma_coherent_ok(struct device *dev, phys_addr_t phys, size_t size)
 {
 	return phys_to_dma_direct(dev, phys) + size - 1 <=
 			min_not_zero(dev->coherent_dma_mask, dev->bus_dma_limit);
diff --git a/kernel/dma/pool.c b/kernel/dma/pool.c
index 39ca26f..6bc74a2 100644
--- a/kernel/dma/pool.c
+++ b/kernel/dma/pool.c
@@ -6,7 +6,6 @@
 #include <linux/debugfs.h>
 #include <linux/dma-direct.h>
 #include <linux/dma-noncoherent.h>
-#include <linux/dma-contiguous.h>
 #include <linux/init.h>
 #include <linux/genalloc.h>
 #include <linux/set_memory.h>
@@ -69,12 +68,7 @@ static int atomic_pool_expand(struct gen_pool *pool, size_t pool_size,
 
 	do {
 		pool_size = 1 << (PAGE_SHIFT + order);
-
-		if (dev_get_cma_area(NULL))
-			page = dma_alloc_from_contiguous(NULL, 1 << order,
-							 order, false);
-		else
-			page = alloc_pages(gfp, order);
+		page = alloc_pages(gfp, order);
 	} while (!page && order-- > 0);
 	if (!page)
 		goto out;
@@ -118,8 +112,7 @@ static int atomic_pool_expand(struct gen_pool *pool, size_t pool_size,
 	dma_common_free_remap(addr, pool_size);
 #endif
 free_page: __maybe_unused
-	if (!dma_release_from_contiguous(NULL, page, 1 << order))
-		__free_pages(page, order);
+	__free_pages(page, order);
 out:
 	return ret;
 }
@@ -203,7 +196,7 @@ static int __init dma_atomic_pool_init(void)
 }
 postcore_initcall(dma_atomic_pool_init);
 
-static inline struct gen_pool *dev_to_pool(struct device *dev)
+static inline struct gen_pool *dma_guess_pool_from_device(struct device *dev)
 {
 	u64 phys_mask;
 	gfp_t gfp;
@@ -217,51 +210,79 @@ static inline struct gen_pool *dev_to_pool(struct device *dev)
 	return atomic_pool_kernel;
 }
 
-static bool dma_in_atomic_pool(struct device *dev, void *start, size_t size)
+static inline struct gen_pool *dma_get_safer_pool(struct gen_pool *bad_pool)
 {
-	struct gen_pool *pool = dev_to_pool(dev);
+	if (bad_pool == atomic_pool_kernel)
+		return atomic_pool_dma32 ? : atomic_pool_dma;
 
-	if (unlikely(!pool))
-		return false;
-	return gen_pool_has_addr(pool, (unsigned long)start, size);
+	if (bad_pool == atomic_pool_dma32)
+		return atomic_pool_dma;
+
+	return NULL;
+}
+
+static inline struct gen_pool *dma_guess_pool(struct device *dev,
+					      struct gen_pool *bad_pool)
+{
+	if (bad_pool)
+		return dma_get_safer_pool(bad_pool);
+
+	return dma_guess_pool_from_device(dev);
 }
 
 void *dma_alloc_from_pool(struct device *dev, size_t size,
 			  struct page **ret_page, gfp_t flags)
 {
-	struct gen_pool *pool = dev_to_pool(dev);
-	unsigned long val;
+	struct gen_pool *pool = NULL;
+	unsigned long val = 0;
 	void *ptr = NULL;
+	phys_addr_t phys;
 
-	if (!pool) {
-		WARN(1, "%pGg atomic pool not initialised!\n", &flags);
-		return NULL;
+	while (1) {
+		pool = dma_guess_pool(dev, pool);
+		if (!pool) {
+			WARN(1, "Failed to get suitable pool for %s\n",
+			     dev_name(dev));
+			break;
+		}
+
+		val = gen_pool_alloc(pool, size);
+		if (!val)
+			continue;
+
+		phys = gen_pool_virt_to_phys(pool, val);
+		if (dma_coherent_ok(dev, phys, size))
+			break;
+
+		gen_pool_free(pool, val, size);
+		val = 0;
 	}
 
-	val = gen_pool_alloc(pool, size);
-	if (likely(val)) {
-		phys_addr_t phys = gen_pool_virt_to_phys(pool, val);
 
+	if (val) {
 		*ret_page = pfn_to_page(__phys_to_pfn(phys));
 		ptr = (void *)val;
 		memset(ptr, 0, size);
-	} else {
-		WARN_ONCE(1, "DMA coherent pool depleted, increase size "
-			     "(recommended min coherent_pool=%zuK)\n",
-			  gen_pool_size(pool) >> 9);
+
+		if (gen_pool_avail(pool) < atomic_pool_size)
+			schedule_work(&atomic_pool_work);
 	}
-	if (gen_pool_avail(pool) < atomic_pool_size)
-		schedule_work(&atomic_pool_work);
 
 	return ptr;
 }
 
 bool dma_free_from_pool(struct device *dev, void *start, size_t size)
 {
-	struct gen_pool *pool = dev_to_pool(dev);
+	struct gen_pool *pool = NULL;
 
-	if (!dma_in_atomic_pool(dev, start, size))
-		return false;
-	gen_pool_free(pool, (unsigned long)start, size);
-	return true;
+	while (1) {
+		pool = dma_guess_pool(dev, pool);
+		if (!pool)
+			return false;
+
+		if (gen_pool_has_addr(pool, (unsigned long)start, size)) {
+			gen_pool_free(pool, (unsigned long)start, size);
+			return true;
+		}
+	}
 }