diff --git a/include/mimalloc/atomic.h b/include/mimalloc/atomic.h
index 572e18ed..42e76e7b 100644
--- a/include/mimalloc/atomic.h
+++ b/include/mimalloc/atomic.h
@@ -281,7 +281,7 @@ typedef _Atomic(uintptr_t) mi_atomic_once_t;
 static inline bool mi_atomic_once( mi_atomic_once_t* once ) {
   if (mi_atomic_load_relaxed(once) != 0) return false;     // quick test 
   uintptr_t expected = 0;
-  return mi_atomic_cas_strong_acq_rel(once, &expected, 1); // try to set to 1
+  return mi_atomic_cas_strong_acq_rel(once, &expected, 1UL); // try to set to 1
 }
 
 typedef _Atomic(uintptr_t) mi_atomic_guard_t;
diff --git a/readme.md b/readme.md
index 003cd8cf..7af7a264 100644
--- a/readme.md
+++ b/readme.md
@@ -518,7 +518,7 @@ Adress sanitizer support is in its initial development -- please report any issu
 ### ETW
 
 Event tracing for Windows ([ETW]) provides a high performance way to capture all allocations though
-mimalloc and analyze them later. To build with ETW support, use the `-DMI_TRACE_ETW=ON` cmake option. 
+mimalloc and analyze them later. To build with ETW support, use the `-DMI_TRACK_ETW=ON` cmake option. 
 
 You can then capture an allocation trace using the Windows performance recorder (WPR), using the 
 `src/prim/windows/etw-mimalloc.wprp` profile. In an admin prompt, you can use:
diff --git a/src/options.c b/src/options.c
index d801f0cd..3bbb18e8 100644
--- a/src/options.c
+++ b/src/options.c
@@ -251,7 +251,7 @@ void mi_register_output(mi_output_fun* out, void* arg) mi_attr_noexcept {
 }
 
 // add stderr to the delayed output after the module is loaded
-static void mi_add_stderr_output() {
+static void mi_add_stderr_output(void) {
   mi_assert_internal(mi_out_default == NULL);
   mi_out_buf_flush(&mi_out_stderr, false, NULL); // flush current contents to stderr
   mi_out_default = &mi_out_buf_stderr;           // and add stderr to the delayed output
diff --git a/src/os.c b/src/os.c
index a07a28ab..d657d5d5 100644
--- a/src/os.c
+++ b/src/os.c
@@ -217,8 +217,8 @@ static void* mi_os_mem_alloc_aligned(size_t size, size_t alignment, bool commit,
 
   // if not aligned, free it, overallocate, and unmap around it
   if (((uintptr_t)p % alignment != 0)) {
-    mi_os_mem_free(p, size, commit, stats);
     _mi_warning_message("unable to allocate aligned OS memory directly, fall back to over-allocation (size: 0x%zx bytes, address: %p, alignment: 0x%zx, commit: %d)\n", size, p, alignment, commit);
+    mi_os_mem_free(p, size, commit, stats);
     if (size >= (SIZE_MAX - alignment)) return NULL; // overflow
     const size_t over_size = size + alignment;
 
diff --git a/src/prim/unix/prim.c b/src/prim/unix/prim.c
index e3a6f8a9..b662698c 100644
--- a/src/prim/unix/prim.c
+++ b/src/prim/unix/prim.c
@@ -170,7 +170,7 @@ static void* unix_mmap_prim(void* addr, size_t size, size_t try_alignment, int p
       p = mmap(addr, size, protect_flags, flags | MAP_ALIGNED(n), fd, 0);
       if (p==MAP_FAILED || !_mi_is_aligned(p,try_alignment)) { 
         int err = errno;
-        _mi_warning_message("unable to directly request aligned OS memory (error: %d (0x%x), size: 0x%zx bytes, alignment: 0x%zx, hint address: %p)\n", err, err, size, try_alignment, hint);
+        _mi_warning_message("unable to directly request aligned OS memory (error: %d (0x%x), size: 0x%zx bytes, alignment: 0x%zx, hint address: %p)\n", err, err, size, try_alignment, addr);
       }
       if (p!=MAP_FAILED) return p;
       // fall back to regular mmap      
diff --git a/test/test-api.c b/test/test-api.c
index c78e1972..829d7d35 100644
--- a/test/test-api.c
+++ b/test/test-api.c
@@ -212,6 +212,11 @@ int main(void) {
     result = mi_heap_contains_block(heap, p);
     mi_heap_destroy(heap);
   }
+  CHECK_BODY("mimalloc-aligned12") {
+    void* p = mi_malloc_aligned(0x100, 0x100);
+    result = (((uintptr_t)p % 0x100) == 0); // #602
+    mi_free(p);
+  }
   CHECK_BODY("malloc-aligned-at1") {
     void* p = mi_malloc_aligned_at(48,32,0); result = (p != NULL && ((uintptr_t)(p) + 0) % 32 == 0); mi_free(p);
   };
@@ -286,7 +291,7 @@ int main(void) {
 // Larger test functions
 // ---------------------------------------------------
 
-bool test_heap1() {
+bool test_heap1(void) {
   mi_heap_t* heap = mi_heap_new();
   int* p1 = mi_heap_malloc_tp(heap,int);
   int* p2 = mi_heap_malloc_tp(heap,int);
@@ -295,7 +300,7 @@ bool test_heap1() {
   return true;
 }
 
-bool test_heap2() {
+bool test_heap2(void) {
   mi_heap_t* heap = mi_heap_new();
   int* p1 = mi_heap_malloc_tp(heap,int);
   int* p2 = mi_heap_malloc_tp(heap,int);
@@ -306,7 +311,7 @@ bool test_heap2() {
   return true;
 }
 
-bool test_stl_allocator1() {
+bool test_stl_allocator1(void) {
 #ifdef __cplusplus
   std::vector<int, mi_stl_allocator<int> > vec;
   vec.push_back(1);
@@ -319,7 +324,7 @@ bool test_stl_allocator1() {
 
 struct some_struct  { int i; int j; double z; };
 
-bool test_stl_allocator2() {
+bool test_stl_allocator2(void) {
 #ifdef __cplusplus
   std::vector<some_struct, mi_stl_allocator<some_struct> > vec;
   vec.push_back(some_struct());