[PATCH v4 01/13] iov_iter: Add a benchmarking kunit test

[David Howells <dhowells@redhat.com>]

---
 lib/kunit_iov_iter.c | 181 +++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 181 insertions(+)

diff --git a/lib/kunit_iov_iter.c b/lib/kunit_iov_iter.c
index 859b67c4d697..478fea956f58 100644
--- a/lib/kunit_iov_iter.c
+++ b/lib/kunit_iov_iter.c
@@ -756,6 +756,184 @@ static void __init iov_kunit_extract_pages_xarray(struct kunit *test)
 	KUNIT_SUCCEED();
 }
 
+static void iov_kunit_free_page(void *data)
+{
+	__free_page(data);
+}
+
+static void __init iov_kunit_benchmark_print_stats(struct kunit *test,
+						   unsigned int *samples)
+{
+	unsigned long total = 0;
+	int i;
+
+	for (i = 0; i < 16; i++) {
+		total += samples[i];
+		kunit_info(test, "run %x: %u uS\n", i, samples[i]);
+	}
+
+	kunit_info(test, "avg %lu uS\n", total / 16);
+}
+
+/*
+ * Time copying 256MiB through an ITER_BVEC.
+ */
+static void __init iov_kunit_benchmark_bvec(struct kunit *test)
+{
+	struct iov_iter iter;
+	struct bio_vec *bvec;
+	struct page *page, **pages;
+	unsigned int samples[16];
+	ktime_t a, b;
+	ssize_t copied;
+	size_t size = 256 * 1024 * 1024, npages = size / PAGE_SIZE;
+	void *scratch;
+	int i;
+
+	/* Allocate a page and tile it repeatedly in the buffer. */
+	page = alloc_page(GFP_KERNEL);
+        KUNIT_ASSERT_NOT_NULL(test, page);
+	kunit_add_action_or_reset(test, iov_kunit_free_page, page);
+
+	bvec = kunit_kmalloc_array(test, npages, sizeof(bvec[0]), GFP_KERNEL);
+        KUNIT_ASSERT_NOT_NULL(test, bvec);
+	for (i = 0; i < npages; i++)
+		bvec_set_page(&bvec[i], page, PAGE_SIZE, 0);
+
+	/* Create a single large buffer to copy to/from. */
+	pages = kunit_kmalloc_array(test, npages, sizeof(pages[0]), GFP_KERNEL);
+        KUNIT_ASSERT_NOT_NULL(test, pages);
+	for (i = 0; i < npages; i++)
+		pages[i] = page;
+
+	scratch = vmap(pages, npages, VM_MAP | VM_MAP_PUT_PAGES, PAGE_KERNEL);
+        KUNIT_ASSERT_NOT_NULL(test, scratch);
+	kunit_add_action_or_reset(test, iov_kunit_unmap, scratch);
+
+	/* Perform and time a bunch of copies. */
+	kunit_info(test, "Benchmarking copy_to_iter() over BVEC:\n");
+	for (i = 0; i < 16; i++) {
+		iov_iter_bvec(&iter, ITER_DEST, bvec, npages, size);
+		a = ktime_get_real();
+		copied = copy_to_iter(scratch, size, &iter);
+		b = ktime_get_real();
+		KUNIT_EXPECT_EQ(test, copied, size);
+		samples[i] = ktime_to_us(ktime_sub(b, a));
+	}
+
+	iov_kunit_benchmark_print_stats(test, samples);
+	KUNIT_SUCCEED();
+}
+
+/*
+ * Time copying 256MiB through an ITER_BVEC in 256 page chunks.
+ */
+static void __init iov_kunit_benchmark_bvec_split(struct kunit *test)
+{
+	struct iov_iter iter;
+	struct bio_vec *bvec;
+	struct page *page, **pages;
+	unsigned int samples[16];
+	ktime_t a, b;
+	ssize_t copied;
+	size_t size, npages = 64;
+	void *scratch;
+	int i, j;
+
+	/* Allocate a page and tile it repeatedly in the buffer. */
+	page = alloc_page(GFP_KERNEL);
+        KUNIT_ASSERT_NOT_NULL(test, page);
+	kunit_add_action_or_reset(test, iov_kunit_free_page, page);
+
+	/* Create a single large buffer to copy to/from. */
+	pages = kunit_kmalloc_array(test, npages, sizeof(pages[0]), GFP_KERNEL);
+        KUNIT_ASSERT_NOT_NULL(test, pages);
+	for (i = 0; i < npages; i++)
+		pages[i] = page;
+
+	scratch = vmap(pages, npages, VM_MAP | VM_MAP_PUT_PAGES, PAGE_KERNEL);
+        KUNIT_ASSERT_NOT_NULL(test, scratch);
+	kunit_add_action_or_reset(test, iov_kunit_unmap, scratch);
+
+	/* Perform and time a bunch of copies. */
+	kunit_info(test, "Benchmarking copy_to_iter() over BVEC:\n");
+	for (i = 0; i < 16; i++) {
+		size = 256 * 1024 * 1024;
+		a = ktime_get_real();
+		do {
+			size_t part = min(size, npages * PAGE_SIZE);
+
+			bvec = kunit_kmalloc_array(test, npages, sizeof(bvec[0]), GFP_KERNEL);
+			KUNIT_ASSERT_NOT_NULL(test, bvec);
+			for (j = 0; j < npages; j++)
+				bvec_set_page(&bvec[j], page, PAGE_SIZE, 0);
+
+			iov_iter_bvec(&iter, ITER_DEST, bvec, npages, part);
+			copied = copy_to_iter(scratch, part, &iter);
+			KUNIT_EXPECT_EQ(test, copied, part);
+			size -= part;
+		} while (size > 0);
+		b = ktime_get_real();
+		samples[i] = ktime_to_us(ktime_sub(b, a));
+	}
+
+	iov_kunit_benchmark_print_stats(test, samples);
+	KUNIT_SUCCEED();
+}
+
+/*
+ * Time copying 256MiB through an ITER_XARRAY.
+ */
+static void __init iov_kunit_benchmark_xarray(struct kunit *test)
+{
+	struct iov_iter iter;
+	struct xarray *xarray;
+	struct page *page, **pages;
+	unsigned int samples[16];
+	ktime_t a, b;
+	ssize_t copied;
+	size_t size = 256 * 1024 * 1024, npages = size / PAGE_SIZE;
+	void *scratch;
+	int i;
+
+	/* Allocate a page and tile it repeatedly in the buffer. */
+	page = alloc_page(GFP_KERNEL);
+        KUNIT_ASSERT_NOT_NULL(test, page);
+	kunit_add_action_or_reset(test, iov_kunit_free_page, page);
+
+	xarray = iov_kunit_create_xarray(test);
+
+	for (i = 0; i < npages; i++) {
+		void *x = xa_store(xarray, i, page, GFP_KERNEL);
+
+		KUNIT_ASSERT_FALSE(test, xa_is_err(x));
+	}
+
+	/* Create a single large buffer to copy to/from. */
+	pages = kunit_kmalloc_array(test, npages, sizeof(pages[0]), GFP_KERNEL);
+        KUNIT_ASSERT_NOT_NULL(test, pages);
+	for (i = 0; i < npages; i++)
+		pages[i] = page;
+
+	scratch = vmap(pages, npages, VM_MAP | VM_MAP_PUT_PAGES, PAGE_KERNEL);
+        KUNIT_ASSERT_NOT_NULL(test, scratch);
+	kunit_add_action_or_reset(test, iov_kunit_unmap, scratch);
+
+	/* Perform and time a bunch of copies. */
+	kunit_info(test, "Benchmarking copy_to_iter() over XARRAY:\n");
+	for (i = 0; i < 16; i++) {
+		iov_iter_xarray(&iter, ITER_DEST, xarray, 0, size);
+		a = ktime_get_real();
+		copied = copy_to_iter(scratch, size, &iter);
+		b = ktime_get_real();
+		KUNIT_EXPECT_EQ(test, copied, size);
+		samples[i] = ktime_to_us(ktime_sub(b, a));
+	}
+
+	iov_kunit_benchmark_print_stats(test, samples);
+	KUNIT_SUCCEED();
+}
+
 static struct kunit_case __refdata iov_kunit_cases[] = {
 	KUNIT_CASE(iov_kunit_copy_to_kvec),
 	KUNIT_CASE(iov_kunit_copy_from_kvec),
@@ -766,6 +944,9 @@ static struct kunit_case __refdata iov_kunit_cases[] = {
 	KUNIT_CASE(iov_kunit_extract_pages_kvec),
 	KUNIT_CASE(iov_kunit_extract_pages_bvec),
 	KUNIT_CASE(iov_kunit_extract_pages_xarray),
+	KUNIT_CASE(iov_kunit_benchmark_bvec),
+	KUNIT_CASE(iov_kunit_benchmark_bvec_split),
+	KUNIT_CASE(iov_kunit_benchmark_xarray),
 	{}
 };