Fix a regression in JE_COMPILABLE().

Revert JE_COMPILABLE() so that it detects link errors.  Cross-compiling
should still work as long as a valid configure cache is provided.

Clean up some comments/whitespace.
diff --git a/configure.ac b/configure.ac
index 5cf2855..a5ca859 100644
--- a/configure.ac
+++ b/configure.ac
@@ -26,14 +26,17 @@
 ])
 
 dnl JE_COMPILABLE(label, hcode, mcode, rvar)
+dnl 
+dnl Use AC_RUN_IFELSE() rather than AC_COMPILE_IFELSE() so that linker errors
+dnl cause failure.
 AC_DEFUN([JE_COMPILABLE],
 [
 AC_CACHE_CHECK([whether $1 is compilable],
                [$4],
-               [AC_COMPILE_IFELSE([AC_LANG_PROGRAM([$2],
-                                                   [$3])],
-                                  [$4=yes],
-                                  [$4=no])])
+               [AC_RUN_IFELSE([AC_LANG_PROGRAM([$2],
+                                               [$3])],
+                              [$4=yes],
+                              [$4=no])])
 ])
 
 dnl ============================================================================
@@ -801,16 +804,13 @@
 dnl Check for ffsl(3), and fail if not found.  This function exists on all
 dnl platforms that jemalloc currently has a chance of functioning on without
 dnl modification.
-JE_COMPILABLE([a program using ffsl],
-              [
-              #include <string.h>
-              ],
-              [
-                {
-                        int rv = ffsl(0x08);
-                }
-              ],
-              [je_cv_function_ffsl])
+JE_COMPILABLE([a program using ffsl], [
+#include <string.h>
+], [
+	{
+		int rv = ffsl(0x08);
+	}
+], [je_cv_function_ffsl])
 if test "x${je_cv_function_ffsl}" != "xyes" ; then
    AC_MSG_ERROR([Cannot build without ffsl(3)])
 fi
diff --git a/include/jemalloc/internal/jemalloc_internal.h.in b/include/jemalloc/internal/jemalloc_internal.h.in
index 3774bb5..5759ed5 100644
--- a/include/jemalloc/internal/jemalloc_internal.h.in
+++ b/include/jemalloc/internal/jemalloc_internal.h.in
@@ -240,14 +240,14 @@
 #define	LONG_MASK		(LONG - 1)
 
 /* Return the smallest long multiple that is >= a. */
-#define	LONG_CEILING(a)						\
+#define	LONG_CEILING(a)							\
 	(((a) + LONG_MASK) & ~LONG_MASK)
 
 #define	SIZEOF_PTR		(1U << LG_SIZEOF_PTR)
 #define	PTR_MASK		(SIZEOF_PTR - 1)
 
 /* Return the smallest (void *) multiple that is >= a. */
-#define	PTR_CEILING(a)						\
+#define	PTR_CEILING(a)							\
 	(((a) + PTR_MASK) & ~PTR_MASK)
 
 /*
@@ -566,10 +566,7 @@
 	}
 }
 
-/*
- * Choose an arena based on a per-thread value (fast-path code, calls slow-path
- * code if necessary).
- */
+/* Choose an arena based on a per-thread value. */
 JEMALLOC_INLINE arena_t *
 choose_arena(void)
 {
diff --git a/src/jemalloc.c b/src/jemalloc.c
index e148ae0..f564b65 100644
--- a/src/jemalloc.c
+++ b/src/jemalloc.c
@@ -101,10 +101,7 @@
 	return (arenas[0]);
 }
 
-/*
- * Choose an arena based on a per-thread value (slow-path code only, called
- * only by choose_arena()).
- */
+/* Slow path, called only by choose_arena(). */
 arena_t *
 choose_arena_hard(void)
 {