diff --git a/include/linux/cma.h b/include/linux/cma.h
index 63873b93deaa..82e31b4da486 100644
--- a/include/linux/cma.h
+++ b/include/linux/cma.h
@@ -48,6 +48,8 @@ extern int cma_init_reserved_mem(phys_addr_t base, phys_addr_t size,
 					unsigned int order_per_bit,
 					const char *name,
 					struct cma **res_cma);
+extern struct page *__cma_alloc(struct cma *cma, unsigned long count, unsigned int align,
+				gfp_t gfp_mask);
 extern struct page *cma_alloc(struct cma *cma, unsigned long count, unsigned int align,
 			      bool no_warn);
 extern bool cma_pages_valid(struct cma *cma, const struct page *pages, unsigned long count);
diff --git a/mm/cma.c b/mm/cma.c
index 332f3c631b1c..b64768625d82 100644
--- a/mm/cma.c
+++ b/mm/cma.c
@@ -416,17 +416,18 @@ static inline void cma_debug_show_areas(struct cma *cma) { }
 #endif
 
 /**
- * cma_alloc() - allocate pages from contiguous area
+ * __cma_alloc() - allocate pages from contiguous area
  * @cma:   Contiguous memory region for which the allocation is performed.
  * @count: Requested number of pages.
  * @align: Requested alignment of pages (in PAGE_SIZE order).
- * @no_warn: Avoid printing message about failed allocation
+ * @gfp_mask: GFP mask to use during the cma allocation.
  *
- * This function allocates part of contiguous memory on specific
- * contiguous memory area.
+ * This function is same with cma_alloc but supports gfp_mask.
+ * Currently, the gfp_mask supports only __GFP_NOWARN and __GFP_NORETRY.
+ * If user passes other flags, it fails the allocation.
  */
-struct page *cma_alloc(struct cma *cma, unsigned long count,
-		       unsigned int align, bool no_warn)
+struct page *__cma_alloc(struct cma *cma, unsigned long count,
+		       unsigned int align, gfp_t gfp_mask)
 {
 	unsigned long mask, offset;
 	unsigned long pfn = -1;
@@ -438,6 +439,10 @@ struct page *cma_alloc(struct cma *cma, unsigned long count,
 	int num_attempts = 0;
 	int max_retries = 5;
 
+	if (WARN_ON_ONCE((gfp_mask & GFP_KERNEL) == 0 ||
+		(gfp_mask & ~(GFP_KERNEL|__GFP_NOWARN|__GFP_NORETRY)) != 0))
+		goto out;
+
 	if (!cma || !cma->count || !cma->bitmap)
 		goto out;
 
@@ -466,7 +471,8 @@ struct page *cma_alloc(struct cma *cma, unsigned long count,
 			if ((num_attempts < max_retries) && (ret == -EBUSY)) {
 				spin_unlock_irq(&cma->lock);
 
-				if (fatal_signal_pending(current))
+				if (fatal_signal_pending(current) ||
+				    (gfp_mask & __GFP_NORETRY))
 					break;
 
 				/*
@@ -496,8 +502,7 @@ struct page *cma_alloc(struct cma *cma, unsigned long count,
 
 		pfn = cma->base_pfn + (bitmap_no << cma->order_per_bit);
 		mutex_lock(&cma_mutex);
-		ret = alloc_contig_range(pfn, pfn + count, MIGRATE_CMA,
-				     GFP_KERNEL | (no_warn ? __GFP_NOWARN : 0));
+		ret = alloc_contig_range(pfn, pfn + count, MIGRATE_CMA, gfp_mask);
 		mutex_unlock(&cma_mutex);
 		if (ret == 0) {
 			page = pfn_to_page(pfn);
@@ -529,7 +534,7 @@ struct page *cma_alloc(struct cma *cma, unsigned long count,
 			page_kasan_tag_reset(page + i);
 	}
 
-	if (ret && !no_warn) {
+	if (ret && !(gfp_mask & __GFP_NOWARN)) {
 		pr_err_ratelimited("%s: %s: alloc failed, req-size: %lu pages, ret: %d\n",
 				   __func__, cma->name, count, ret);
 		cma_debug_show_areas(cma);
@@ -548,6 +553,24 @@ struct page *cma_alloc(struct cma *cma, unsigned long count,
 
 	return page;
 }
+EXPORT_SYMBOL_GPL(__cma_alloc);
+
+/**
+ * cma_alloc() - allocate pages from contiguous area
+ * @cma:   Contiguous memory region for which the allocation is performed.
+ * @count: Requested number of pages.
+ * @align: Requested alignment of pages (in PAGE_SIZE order).
+ * @no_warn: Avoid printing message about failed allocation
+ *
+ * This function allocates part of contiguous memory on specific
+ * contiguous memory area.
+ */
+struct page *cma_alloc(struct cma *cma, unsigned long count,
+		       unsigned int align, bool no_warn)
+{
+	return __cma_alloc(cma, count, align, GFP_KERNEL |
+				(no_warn ? __GFP_NOWARN : 0));
+}
 EXPORT_SYMBOL_GPL(cma_alloc);
 
 bool cma_pages_valid(struct cma *cma, const struct page *pages,
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 33ad6d5e9497..dfc8658392c2 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -9336,12 +9336,16 @@ int __alloc_contig_migrate_range(struct compact_control *cc,
 	unsigned int nr_reclaimed;
 	unsigned long pfn = start;
 	unsigned int tries = 0;
+	unsigned int max_tries = 5;
 	int ret = 0;
 	struct migration_target_control mtc = {
 		.nid = zone_to_nid(cc->zone),
 		.gfp_mask = GFP_USER | __GFP_MOVABLE | __GFP_RETRY_MAYFAIL,
 	};
 
+	if (cc->gfp_mask & __GFP_NORETRY)
+		max_tries = 1;
+
 	lru_cache_disable();
 
 	while (pfn < end || !list_empty(&cc->migratepages)) {
@@ -9357,7 +9361,7 @@ int __alloc_contig_migrate_range(struct compact_control *cc,
 				break;
 			pfn = cc->migrate_pfn;
 			tries = 0;
-		} else if (++tries == 5) {
+		} else if (++tries == max_tries) {
 			ret = -EBUSY;
 			break;
 		}
@@ -9428,7 +9432,11 @@ int alloc_contig_range(unsigned long start, unsigned long end,
 		.nr_migratepages = 0,
 		.order = -1,
 		.zone = page_zone(pfn_to_page(start)),
-		.mode = MIGRATE_SYNC,
+		/*
+		 * Use MIGRATE_ASYNC for __GFP_NORETRY requests as it never
+		 * blocks.
+		 */
+		.mode = gfp_mask & __GFP_NORETRY ? MIGRATE_ASYNC : MIGRATE_SYNC,
 		.ignore_skip_hint = true,
 		.no_set_skip_hint = true,
 		.gfp_mask = current_gfp_context(gfp_mask),
@@ -9474,7 +9482,7 @@ int alloc_contig_range(unsigned long start, unsigned long end,
 	 * -EBUSY is not accidentally used or returned to caller.
 	 */
 	ret = __alloc_contig_migrate_range(&cc, start, end);
-	if (ret && ret != -EBUSY)
+	if (ret && (ret != -EBUSY || (gfp_mask & __GFP_NORETRY)))
 		goto done;
 	ret = 0;