diff --git a/mm/gup_benchmark.c b/mm/gup_benchmark.c
index 8dba38e79a9f..be690fa66a46 100644
--- a/mm/gup_benchmark.c
+++ b/mm/gup_benchmark.c
@@ -8,6 +8,8 @@
 #define GUP_FAST_BENCHMARK	_IOWR('g', 1, struct gup_benchmark)
 #define GUP_LONGTERM_BENCHMARK	_IOWR('g', 2, struct gup_benchmark)
 #define GUP_BENCHMARK		_IOWR('g', 3, struct gup_benchmark)
+#define PIN_FAST_BENCHMARK	_IOWR('g', 4, struct gup_benchmark)
+#define PIN_BENCHMARK		_IOWR('g', 5, struct gup_benchmark)
 
 struct gup_benchmark {
 	__u64 get_delta_usec;
@@ -19,6 +21,48 @@ struct gup_benchmark {
 	__u64 expansion[10];	/* For future use */
 };
 
+static void put_back_pages(unsigned int cmd, struct page **pages,
+			   unsigned long nr_pages)
+{
+	unsigned long i;
+
+	switch (cmd) {
+	case GUP_FAST_BENCHMARK:
+	case GUP_LONGTERM_BENCHMARK:
+	case GUP_BENCHMARK:
+		for (i = 0; i < nr_pages; i++)
+			put_page(pages[i]);
+		break;
+
+	case PIN_FAST_BENCHMARK:
+	case PIN_BENCHMARK:
+		unpin_user_pages(pages, nr_pages);
+		break;
+	}
+}
+
+static void verify_dma_pinned(unsigned int cmd, struct page **pages,
+			      unsigned long nr_pages)
+{
+	unsigned long i;
+	struct page *page;
+
+	switch (cmd) {
+	case PIN_FAST_BENCHMARK:
+	case PIN_BENCHMARK:
+		for (i = 0; i < nr_pages; i++) {
+			page = pages[i];
+			if (WARN(!page_maybe_dma_pinned(page),
+				 "pages[%lu] is NOT dma-pinned\n", i)) {
+
+				dump_page(page, "gup_benchmark failure");
+				break;
+			}
+		}
+		break;
+	}
+}
+
 static int __gup_benchmark_ioctl(unsigned int cmd,
 		struct gup_benchmark *gup)
 {
@@ -66,6 +110,14 @@ static int __gup_benchmark_ioctl(unsigned int cmd,
 			nr = get_user_pages(addr, nr, gup->flags, pages + i,
 					    NULL);
 			break;
+		case PIN_FAST_BENCHMARK:
+			nr = pin_user_pages_fast(addr, nr, gup->flags,
+						 pages + i);
+			break;
+		case PIN_BENCHMARK:
+			nr = pin_user_pages(addr, nr, gup->flags, pages + i,
+					    NULL);
+			break;
 		default:
 			kvfree(pages);
 			ret = -EINVAL;
@@ -78,15 +130,22 @@ static int __gup_benchmark_ioctl(unsigned int cmd,
 	}
 	end_time = ktime_get();
 
+	/* Shifting the meaning of nr_pages: now it is actual number pinned: */
+	nr_pages = i;
+
 	gup->get_delta_usec = ktime_us_delta(end_time, start_time);
 	gup->size = addr - gup->addr;
 
+	/*
+	 * Take an un-benchmark-timed moment to verify DMA pinned
+	 * state: print a warning if any non-dma-pinned pages are found:
+	 */
+	verify_dma_pinned(cmd, pages, nr_pages);
+
 	start_time = ktime_get();
-	for (i = 0; i < nr_pages; i++) {
-		if (!pages[i])
-			break;
-		put_page(pages[i]);
-	}
+
+	put_back_pages(cmd, pages, nr_pages);
+
 	end_time = ktime_get();
 	gup->put_delta_usec = ktime_us_delta(end_time, start_time);
 
@@ -105,6 +164,8 @@ static long gup_benchmark_ioctl(struct file *filep, unsigned int cmd,
 	case GUP_FAST_BENCHMARK:
 	case GUP_LONGTERM_BENCHMARK:
 	case GUP_BENCHMARK:
+	case PIN_FAST_BENCHMARK:
+	case PIN_BENCHMARK:
 		break;
 	default:
 		return -EINVAL;
diff --git a/tools/testing/selftests/vm/gup_benchmark.c b/tools/testing/selftests/vm/gup_benchmark.c
index 389327e9b30a..43b4dfe161a2 100644
--- a/tools/testing/selftests/vm/gup_benchmark.c
+++ b/tools/testing/selftests/vm/gup_benchmark.c
@@ -18,6 +18,10 @@
 #define GUP_LONGTERM_BENCHMARK	_IOWR('g', 2, struct gup_benchmark)
 #define GUP_BENCHMARK		_IOWR('g', 3, struct gup_benchmark)
 
+/* Similar to above, but use FOLL_PIN instead of FOLL_GET. */
+#define PIN_FAST_BENCHMARK	_IOWR('g', 4, struct gup_benchmark)
+#define PIN_BENCHMARK		_IOWR('g', 5, struct gup_benchmark)
+
 /* Just the flags we need, copied from mm.h: */
 #define FOLL_WRITE	0x01	/* check pte is writable */
 
@@ -40,8 +44,14 @@ int main(int argc, char **argv)
 	char *file = "/dev/zero";
 	char *p;
 
-	while ((opt = getopt(argc, argv, "m:r:n:f:tTLUwSH")) != -1) {
+	while ((opt = getopt(argc, argv, "m:r:n:f:abtTLUuwSH")) != -1) {
 		switch (opt) {
+		case 'a':
+			cmd = PIN_FAST_BENCHMARK;
+			break;
+		case 'b':
+			cmd = PIN_BENCHMARK;
+			break;
 		case 'm':
 			size = atoi(optarg) * MB;
 			break;
@@ -63,6 +73,9 @@ int main(int argc, char **argv)
 		case 'U':
 			cmd = GUP_BENCHMARK;
 			break;
+		case 'u':
+			cmd = GUP_FAST_BENCHMARK;
+			break;
 		case 'w':
 			write = 1;
 			break;