Header refactoring: ctl - unify and remove from catchall.

In order to do this, we introduce the mutex_prof module, which breaks a circular
dependency between ctl and prof.

include/jemalloc/internal/mutex_structs.h

@@ -2,39 +2,7 @@
 #define JEMALLOC_INTERNAL_MUTEX_STRUCTS_H
 
 #include "jemalloc/internal/atomic.h"
-#include "jemalloc/internal/nstime.h"
-
-struct mutex_prof_data_s {
-	/*
-	 * Counters touched on the slow path, i.e. when there is lock
-	 * contention.  We update them once we have the lock.
-	 */
-	/* Total time (in nano seconds) spent waiting on this mutex. */
-	nstime_t		tot_wait_time;
-	/* Max time (in nano seconds) spent on a single lock operation. */
-	nstime_t		max_wait_time;
-	/* # of times have to wait for this mutex (after spinning). */
-	uint64_t		n_wait_times;
-	/* # of times acquired the mutex through local spinning. */
-	uint64_t		n_spin_acquired;
-	/* Max # of threads waiting for the mutex at the same time. */
-	uint32_t		max_n_thds;
-	/* Current # of threads waiting on the lock.  Atomic synced. */
-	atomic_u32_t		n_waiting_thds;
-
-	/*
-	 * Data touched on the fast path.  These are modified right after we
-	 * grab the lock, so it's placed closest to the end (i.e. right before
-	 * the lock) so that we have a higher chance of them being on the same
-	 * cacheline.
-	 */
-	/* # of times the mutex holder is different than the previous one. */
-	uint64_t		n_owner_switches;
-	/* Previous mutex holder, to facilitate n_owner_switches. */
-	tsdn_t			*prev_owner;
-	/* # of lock() operations in total. */
-	uint64_t		n_lock_ops;
-};
+#include "jemalloc/internal/mutex_prof.h"
 
 struct malloc_mutex_s {
 	union {