malloc: Use global flag instead of function pointer dispatch for mtag

A flag check can be faster than function pointers because of how
branch prediction and speculation works and it can also remove a layer
of indirection when there is a mismatch between the malloc internal
tag_* api and __libc_mtag_* target hooks.

Memory tagging wrapper functions are moved to malloc.c from arena.c and
the logic now checks mmap_enabled.  The definition of tag_new_usable is
moved after chunk related definitions.

This refactoring also allows using mtag_enabled checks instead of
USE_MTAG ifdefs when memory tagging support only changes code logic
when memory tagging is enabled at runtime. Note: an "if (false)" code
block is optimized away even at -O0 by gcc.

Reviewed-by: DJ Delorie <dj@redhat.com>

malloc/arena.c

@@ -287,34 +287,6 @@ extern struct dl_open_hook *_dl_open_hook;
 libc_hidden_proto (_dl_open_hook);
 #endif
 
-#ifdef USE_MTAG
-
-/* Generate a new (random) tag value for PTR and tag the memory it
-   points to upto the end of the usable size for the chunk containing
-   it.  Return the newly tagged pointer.  */
-static void *
-__mtag_tag_new_usable (void *ptr)
-{
-  if (ptr)
-    {
-      mchunkptr cp = mem2chunk(ptr);
-      ptr = __libc_mtag_tag_region (__libc_mtag_new_tag (ptr),
-				    CHUNK_AVAILABLE_SIZE (cp) - CHUNK_HDR_SZ);
-    }
-  return ptr;
-}
-
-/* Generate a new (random) tag value for PTR, set the tags for the
-   memory to the new tag and initialize the memory contents to VAL.
-   In practice this function will only be called with VAL=0, but we
-   keep this parameter to maintain the same prototype as memset.  */
-static void *
-__mtag_tag_new_memset (void *ptr, int val, size_t size)
-{
-  return __libc_mtag_memset_with_tag (__libc_mtag_new_tag (ptr), val, size);
-}
-#endif
-
 static void
 ptmalloc_init (void)
 {
@@ -332,11 +304,8 @@ ptmalloc_init (void)
       if (__MTAG_SBRK_UNTAGGED)
 	__morecore = __failing_morecore;
 
+      mtag_enabled = true;
       mtag_mmap_flags = __MTAG_MMAP_FLAGS;
-      tag_new_memset = __mtag_tag_new_memset;
-      tag_region = __libc_mtag_tag_region;
-      tag_new_usable = __mtag_tag_new_usable;
-      tag_at = __libc_mtag_address_get_tag;
       mtag_granule_mask = ~(size_t)(__MTAG_GRANULE_SIZE - 1);
     }
 #endif

malloc/malloc.c

@@ -441,36 +441,42 @@ void *(*__morecore)(ptrdiff_t) = __default_morecore;
 */
 
 #ifdef USE_MTAG
-
+static bool mtag_enabled = false;
-/* Default implementaions when memory tagging is supported, but disabled.  */
-static void *
-__default_tag_region (void *ptr, size_t size)
-{
-  return ptr;
-}
-
-static void *
-__default_tag_nop (void *ptr)
-{
-  return ptr;
-}
-
 static int mtag_mmap_flags = 0;
 static size_t mtag_granule_mask = ~(size_t)0;
-
-static void *(*tag_new_memset)(void *, int, size_t) = memset;
-static void *(*tag_region)(void *, size_t) = __default_tag_region;
-static void *(*tag_new_usable)(void *) = __default_tag_nop;
-static void *(*tag_at)(void *) = __default_tag_nop;
-
 #else
+# define mtag_enabled false
 # define mtag_mmap_flags 0
-# define tag_new_memset(ptr, val, size) memset (ptr, val, size)
-# define tag_region(ptr, size) (ptr)
-# define tag_new_usable(ptr) (ptr)
-# define tag_at(ptr) (ptr)
 #endif
 
+static __always_inline void *
+tag_region (void *ptr, size_t size)
+{
+  if (__glibc_unlikely (mtag_enabled))
+    return __libc_mtag_tag_region (ptr, size);
+  return ptr;
+}
+
+static __always_inline void *
+tag_new_memset (void *ptr, int val, size_t size)
+{
+  if (__glibc_unlikely (mtag_enabled))
+    return __libc_mtag_memset_with_tag (__libc_mtag_new_tag (ptr), val, size);
+  return memset (ptr, val, size);
+}
+
+/* Defined later.  */
+static void *
+tag_new_usable (void *ptr);
+
+static __always_inline void *
+tag_at (void *ptr)
+{
+  if (__glibc_unlikely (mtag_enabled))
+    return __libc_mtag_address_get_tag (ptr);
+  return ptr;
+}
+
 #include <string.h>
 
 /*
@@ -1460,6 +1466,18 @@ checked_request2size (size_t req, size_t *sz) __nonnull (1)
 #pragma GCC poison mchunk_size
 #pragma GCC poison mchunk_prev_size
 
+static __always_inline void *
+tag_new_usable (void *ptr)
+{
+  if (__glibc_unlikely (mtag_enabled) && ptr)
+    {
+      mchunkptr cp = mem2chunk(ptr);
+      ptr = __libc_mtag_tag_region (__libc_mtag_new_tag (ptr),
+				    CHUNK_AVAILABLE_SIZE (cp) - CHUNK_HDR_SZ);
+    }
+  return ptr;
+}
+
 /*
    -------------------- Internal data structures --------------------