diff --git a/README.md b/README.md
index ab04af63..e73574a4 100644
--- a/README.md
+++ b/README.md
@@ -61,7 +61,7 @@ dpkg -i linux-xxx-dev_TARGET_VERSION.deb
 dpkg -i linux-xxx-tools_TARGET_VERSION.deb
 
 Boot up with target kernel version.
-cd cet_driver
+cd cet/cet_driver
 make
 ```
 
diff --git a/workload-xsave/work_AVX2.c b/workload-xsave/work_AVX2.c
index 4f237d56..051ac78a 100644
--- a/workload-xsave/work_AVX2.c
+++ b/workload-xsave/work_AVX2.c
@@ -14,6 +14,7 @@
 #include <sched.h>		/* CPU_SET */
 #include "yogini.h"
 #include <immintrin.h>
+#include <stdint.h>
 #include <err.h>
 
 #pragma GCC target("avx2,fma")
@@ -26,7 +27,7 @@
 #pragma GCC optimize("unroll-loops")
 
 struct thread_data {
-	u_int8_t *input_x;
+	uint8_t *input_x;
 	int8_t *input_y;
 	int16_t *output;
 	int data_entries;
diff --git a/workload-xsave/work_AVX512.c b/workload-xsave/work_AVX512.c
index 63542e4b..3f2092fa 100644
--- a/workload-xsave/work_AVX512.c
+++ b/workload-xsave/work_AVX512.c
@@ -15,6 +15,7 @@
 #include <sched.h>		/* CPU_SET */
 #include "yogini.h"
 #include <immintrin.h>
+#include <stdint.h>
 #include <err.h>
 
 #if __GNUC__ >= 11
@@ -29,7 +30,7 @@
 #pragma GCC optimize("unroll-loops")
 
 struct thread_data {
-	u_int8_t *input_x;
+	uint8_t *input_x;
 	int8_t *input_y;
 	int32_t *input_z;
 	int16_t *input_ones;
diff --git a/workload-xsave/work_DOTPROD.c b/workload-xsave/work_DOTPROD.c
index 15a186b1..b3abac7a 100644
--- a/workload-xsave/work_DOTPROD.c
+++ b/workload-xsave/work_DOTPROD.c
@@ -10,6 +10,7 @@
 #include <sched.h>		/* CPU_SET */
 #include "yogini.h"
 #include <immintrin.h>
+#include <stdint.h>
 #include <err.h>
 
 #pragma GCC target("avx2,fma")
@@ -22,7 +23,7 @@
 #pragma GCC optimize("unroll-loops")
 
 struct thread_data {
-	u_int8_t *input_x;
+	uint8_t *input_x;
 	int8_t *input_y;
 	int32_t *input_z;
 	int16_t *input_ones;
diff --git a/workload-xsave/work_VNNI.c b/workload-xsave/work_VNNI.c
index 4ccf0ec7..8051a53d 100644
--- a/workload-xsave/work_VNNI.c
+++ b/workload-xsave/work_VNNI.c
@@ -13,6 +13,7 @@
 #include <sched.h>		/* CPU_SET */
 #include "yogini.h"
 #include <immintrin.h>
+#include <stdint.h>
 #include <err.h>
 
 #if __GNUC__ >= 11
@@ -27,7 +28,7 @@
 #pragma GCC optimize("unroll-loops")
 
 struct thread_data {
-	u_int8_t *input_x;
+	uint8_t *input_x;
 	int8_t *input_y;
 	int32_t *input_z;
 	int16_t *input_ones;
diff --git a/workload-xsave/work_VNNI512.c b/workload-xsave/work_VNNI512.c
index 1849da85..55e8d5a7 100644
--- a/workload-xsave/work_VNNI512.c
+++ b/workload-xsave/work_VNNI512.c
@@ -10,6 +10,7 @@
 #include <sched.h>		/* CPU_SET */
 #include "yogini.h"
 #include <immintrin.h>
+#include <stdint.h>
 #include <err.h>
 
 #if __GNUC__ >= 9
@@ -24,7 +25,7 @@
 #pragma GCC optimize("unroll-loops")
 
 struct thread_data {
-	u_int8_t *input_x;
+	uint8_t *input_x;
 	int8_t *input_y;
 	int32_t *input_z;
 	int16_t *input_ones;
diff --git a/workload-xsave/worker_init_avx2.c b/workload-xsave/worker_init_avx2.c
index 03c02171..6449ca3b 100644
--- a/workload-xsave/worker_init_avx2.c
+++ b/workload-xsave/worker_init_avx2.c
@@ -3,7 +3,9 @@
  * Copyright (c) 2022 Intel Corporation.
  * Len Brown <len.brown@intel.com>
  */
-
+#include <stddef.h>
+#include <stdlib.h>
+#include <stdint.h>
 static int init(struct work_instance *wi)
 {
 	int i;
@@ -17,7 +19,7 @@ static int init(struct work_instance *wi)
 	if (!dp)
 		err(1, "thread_data");
 
-	dp->input_x = (u_int8_t *)calloc(entries, BYTES_PER_VECTOR);
+	dp->input_x = (uint8_t *)calloc(entries, BYTES_PER_VECTOR);
 	if (!dp->input_x)
 		err(1, "calloc input_x");
 
diff --git a/workload-xsave/worker_init_dotprod.c b/workload-xsave/worker_init_dotprod.c
index 1810870a..537489a5 100644
--- a/workload-xsave/worker_init_dotprod.c
+++ b/workload-xsave/worker_init_dotprod.c
@@ -3,7 +3,7 @@
  * Copyright (c) 2022 Intel Corporation.
  * Len Brown <len.brown@intel.com>
  */
-
+#include <stdint.h>
 static int init(struct work_instance *wi)
 {
 	int i;
@@ -17,7 +17,7 @@ static int init(struct work_instance *wi)
 	if (!dp)
 		err(1, "thread_data");
 
-	dp->input_x = (u_int8_t *)calloc(entries, BYTES_PER_VECTOR);
+	dp->input_x = (uint8_t *)calloc(entries, BYTES_PER_VECTOR);
 	if (!dp->input_x)
 		err(1, "calloc input_x");
 
diff --git a/workload-xsave/yogini.c b/workload-xsave/yogini.c
index 8d49e680..3e693dbc 100644
--- a/workload-xsave/yogini.c
+++ b/workload-xsave/yogini.c
@@ -264,12 +264,12 @@ static void cmdline(int argc, char **argv)
 
 	progname = argv[0];
 
+	if (argc == 1)
+		help();
+
 	while ((opt = getopt_long_only(argc, argv, "h:w:r:b:f",
-	       long_options, &option_index)) != -1) {
+				       long_options, &option_index)) != -1) {
 		switch (opt) {
-		case 'h':
-			help();
-			break;
 		case 'w':
 			if (parse_work_cmd(optarg))
 				help();
@@ -284,6 +284,8 @@ static void cmdline(int argc, char **argv)
 		case 'f':
 			clfulsh = 1;
 			break;
+		case '?':
+		case 'h':
 		default:
 			help();
 		}