1 files changed, 61 insertions, 71 deletions

diff --git a/tools/testing/selftests/resctrl/fill_buf.c b/tools/testing/selftests/resctrl/fill_buf.c
index 0d425f26583a..ae120f1735c0 100644
--- a/tools/testing/selftests/resctrl/fill_buf.c
+++ b/tools/testing/selftests/resctrl/fill_buf.c
@@ -38,7 +38,7 @@ static void cl_flush(void *p)
 #endif
 }
 
-static void mem_flush(unsigned char *buf, size_t buf_size)
+void mem_flush(unsigned char *buf, size_t buf_size)
 {
 	unsigned char *cp = buf;
 	size_t i = 0;
@@ -51,39 +51,38 @@ static void mem_flush(unsigned char *buf, size_t buf_size)
 	sb();
 }
 
-static void *malloc_and_init_memory(size_t buf_size)
-{
-	void *p = NULL;
-	uint64_t *p64;
-	size_t s64;
-	int ret;
-
-	ret = posix_memalign(&p, PAGE_SIZE, buf_size);
-	if (ret < 0)
-		return NULL;
-
-	p64 = (uint64_t *)p;
-	s64 = buf_size / sizeof(uint64_t);
-
-	while (s64 > 0) {
-		*p64 = (uint64_t)rand();
-		p64 += (CL_SIZE / sizeof(uint64_t));
-		s64 -= (CL_SIZE / sizeof(uint64_t));
-	}
-
-	return p;
-}
+/*
+ * Buffer index step advance to workaround HW prefetching interfering with
+ * the measurements.
+ *
+ * Must be a prime to step through all indexes of the buffer.
+ *
+ * Some primes work better than others on some architectures (from MBA/MBM
+ * result stability point of view).
+ */
+#define FILL_IDX_MULT	23
 
 static int fill_one_span_read(unsigned char *buf, size_t buf_size)
 {
-	unsigned char *end_ptr = buf + buf_size;
-	unsigned char sum, *p;
-
-	sum = 0;
-	p = buf;
-	while (p < end_ptr) {
-		sum += *p;
-		p += (CL_SIZE / 2);
+	unsigned int size = buf_size / (CL_SIZE / 2);
+	unsigned int i, idx = 0;
+	unsigned char sum = 0;
+
+	/*
+	 * Read the buffer in an order that is unexpected by HW prefetching
+	 * optimizations to prevent them interfering with the caching pattern.
+	 *
+	 * The read order is (in terms of halves of cachelines):
+	 *	i * FILL_IDX_MULT % size
+	 * The formula is open-coded below to avoiding modulo inside the loop
+	 * as it improves MBA/MBM result stability on some architectures.
+	 */
+	for (i = 0; i < size; i++) {
+		sum += buf[idx * (CL_SIZE / 2)];
+
+		idx += FILL_IDX_MULT;
+		while (idx >= size)
+			idx -= size;
 	}
 
 	return sum;
@@ -101,10 +100,9 @@ static void fill_one_span_write(unsigned char *buf, size_t buf_size)
 	}
 }
 
-static int fill_cache_read(unsigned char *buf, size_t buf_size, bool once)
+void fill_cache_read(unsigned char *buf, size_t buf_size, bool once)
 {
 	int ret = 0;
-	FILE *fp;
 
 	while (1) {
 		ret = fill_one_span_read(buf, buf_size);
@@ -113,67 +111,59 @@ static int fill_cache_read(unsigned char *buf, size_t buf_size, bool once)
 	}
 
 	/* Consume read result so that reading memory is not optimized out. */
-	fp = fopen("/dev/null", "w");
-	if (!fp) {
-		perror("Unable to write to /dev/null");
-		return -1;
-	}
-	fprintf(fp, "Sum: %d ", ret);
-	fclose(fp);
-
-	return 0;
+	*value_sink = ret;
 }
 
-static int fill_cache_write(unsigned char *buf, size_t buf_size, bool once)
+static void fill_cache_write(unsigned char *buf, size_t buf_size, bool once)
 {
 	while (1) {
 		fill_one_span_write(buf, buf_size);
 		if (once)
 			break;
 	}
-
-	return 0;
 }
 
-static int fill_cache(size_t buf_size, int memflush, int op, bool once)
+unsigned char *alloc_buffer(size_t buf_size, int memflush)
 {
-	unsigned char *buf;
+	void *buf = NULL;
+	uint64_t *p64;
+	size_t s64;
 	int ret;
 
-	buf = malloc_and_init_memory(buf_size);
-	if (!buf)
-		return -1;
-
-	/* Flush the memory before using to avoid "cache hot pages" effect */
-	if (memflush)
-		mem_flush(buf, buf_size);
-
-	if (op == 0)
-		ret = fill_cache_read(buf, buf_size, once);
-	else
-		ret = fill_cache_write(buf, buf_size, once);
+	ret = posix_memalign(&buf, PAGE_SIZE, buf_size);
+	if (ret < 0)
+		return NULL;
 
-	free(buf);
+	/* Initialize the buffer */
+	p64 = buf;
+	s64 = buf_size / sizeof(uint64_t);
 
-	if (ret) {
-		printf("\n Error in fill cache read/write...\n");
-		return -1;
+	while (s64 > 0) {
+		*p64 = (uint64_t)rand();
+		p64 += (CL_SIZE / sizeof(uint64_t));
+		s64 -= (CL_SIZE / sizeof(uint64_t));
 	}
 
+	/* Flush the memory before using to avoid "cache hot pages" effect */
+	if (memflush)
+		mem_flush(buf, buf_size);
 
-	return 0;
+	return buf;
 }
 
-int run_fill_buf(size_t span, int memflush, int op, bool once)
+int run_fill_buf(size_t buf_size, int memflush, int op, bool once)
 {
-	size_t cache_size = span;
-	int ret;
+	unsigned char *buf;
 
-	ret = fill_cache(cache_size, memflush, op, once);
-	if (ret) {
-		printf("\n Error in fill cache\n");
+	buf = alloc_buffer(buf_size, memflush);
+	if (!buf)
 		return -1;
-	}
+
+	if (op == 0)
+		fill_cache_read(buf, buf_size, once);
+	else
+		fill_cache_write(buf, buf_size, once);
+	free(buf);
 
 	return 0;
 }