Drop umbrella include from 15 more .c files (batch 4)

Converted: prof_stack_range, jemalloc_fork, san, pa_extra, mutex,
thread_event_registry, rtree, ehooks, pa, extent_dss, decay, large,
nstime, bin, arenas_management.

One latent hermeticity bug surfaced: prof_sys.h declares
`void bt_init(prof_bt_t *bt, void **vec);` but didn't include prof.h
where prof_bt_t is defined.  Added the include.

Step 6 (Option B) of the cyclical-dep cleanup, batch 4 of N.

include/jemalloc/internal/prof_sys.h

@@ -4,6 +4,7 @@
 #include "jemalloc/internal/jemalloc_preamble.h"
 #include "jemalloc/internal/base.h"
 #include "jemalloc/internal/mutex.h"
+#include "jemalloc/internal/prof.h"
 
 extern malloc_mutex_t prof_dump_filename_mtx;
 extern base_t        *prof_base;

src/arenas_management.c

@@ -1,11 +1,17 @@
 #include "jemalloc/internal/jemalloc_preamble.h"
-#include "jemalloc/internal/jemalloc_internal_includes.h"
 
+#include "jemalloc/internal/arena.h"
 #include "jemalloc/internal/arenas_management.h"
+#include "jemalloc/internal/background_thread.h"
+#include "jemalloc/internal/background_thread_inlines.h"
 #include "jemalloc/internal/jemalloc_init.h"
+#include "jemalloc/internal/jemalloc_internal_inlines_a.h"
+#include "jemalloc/internal/jemalloc_internal_inlines_b.h"
+#include "jemalloc/internal/jemalloc_internal_inlines_c.h"
 #include "jemalloc/internal/malloc_io.h"
 #include "jemalloc/internal/mutex.h"
 #include "jemalloc/internal/sz.h"
+#include "jemalloc/internal/tcache.h"
 
 JEMALLOC_ALIGNED(CACHELINE)
 atomic_p_t arenas[MALLOCX_ARENA_LIMIT];

src/bin.c

@@ -1,6 +1,7 @@
 #include "jemalloc/internal/jemalloc_preamble.h"
-#include "jemalloc/internal/jemalloc_internal_includes.h"
 
+#include "jemalloc/internal/arena.h"
+#include "jemalloc/internal/arena_inlines_b.h"
 #include "jemalloc/internal/assert.h"
 #include "jemalloc/internal/bin.h"
 #include "jemalloc/internal/sc.h"

src/decay.c

@@ -1,5 +1,4 @@
 #include "jemalloc/internal/jemalloc_preamble.h"
-#include "jemalloc/internal/jemalloc_internal_includes.h"
 
 #include "jemalloc/internal/decay.h"
 

src/ehooks.c

@@ -1,8 +1,14 @@
 #include "jemalloc/internal/jemalloc_preamble.h"
-#include "jemalloc/internal/jemalloc_internal_includes.h"
 
+#include "jemalloc/internal/arena.h"
+#include "jemalloc/internal/base.h"
+#include "jemalloc/internal/edata.h"
 #include "jemalloc/internal/ehooks.h"
+#include "jemalloc/internal/emap.h"
+#include "jemalloc/internal/extent.h"
+#include "jemalloc/internal/extent_dss.h"
 #include "jemalloc/internal/extent_mmap.h"
+#include "jemalloc/internal/jemalloc_internal_inlines_a.h"
 
 void
 ehooks_init(ehooks_t *ehooks, extent_hooks_t *extent_hooks, unsigned ind) {

src/extent_dss.c

@@ -1,9 +1,14 @@
 #include "jemalloc/internal/jemalloc_preamble.h"
-#include "jemalloc/internal/jemalloc_internal_includes.h"
 
+#include "jemalloc/internal/arena.h"
+#include "jemalloc/internal/arena_inlines_a.h"
 #include "jemalloc/internal/assert.h"
+#include "jemalloc/internal/edata_cache.h"
+#include "jemalloc/internal/extent.h"
 #include "jemalloc/internal/extent_dss.h"
+#include "jemalloc/internal/jemalloc_internal_inlines_a.h"
 #include "jemalloc/internal/spin.h"
+#include "jemalloc/internal/tsd.h"
 
 /******************************************************************************/
 /* Data. */

src/jemalloc_fork.c

@@ -1,10 +1,17 @@
 #include "jemalloc/internal/jemalloc_preamble.h"
-#include "jemalloc/internal/jemalloc_internal_includes.h"
 
+#include "jemalloc/internal/arena.h"
 #include "jemalloc/internal/arenas_management.h"
+#include "jemalloc/internal/background_thread.h"
 #include "jemalloc/internal/ctl.h"
 #include "jemalloc/internal/jemalloc_fork.h"
 #include "jemalloc/internal/jemalloc_init.h"
+#include "jemalloc/internal/jemalloc_internal_inlines_a.h"
+#include "jemalloc/internal/jemalloc_internal_inlines_b.h"
+#include "jemalloc/internal/mutex.h"
+#include "jemalloc/internal/prof.h"
+#include "jemalloc/internal/tcache.h"
+#include "jemalloc/internal/tsd.h"
 
 /******************************************************************************/
 /*

src/large.c

@@ -1,10 +1,16 @@
 #include "jemalloc/internal/jemalloc_preamble.h"
-#include "jemalloc/internal/jemalloc_internal_includes.h"
 
+#include "jemalloc/internal/arena.h"
+#include "jemalloc/internal/arena_inlines_b.h"
 #include "jemalloc/internal/assert.h"
 #include "jemalloc/internal/emap.h"
+#include "jemalloc/internal/extent.h"
 #include "jemalloc/internal/extent_mmap.h"
+#include "jemalloc/internal/jemalloc_internal_inlines_c.h"
+#include "jemalloc/internal/large.h"
 #include "jemalloc/internal/mutex.h"
+#include "jemalloc/internal/prof.h"
+#include "jemalloc/internal/prof_inlines.h"
 #include "jemalloc/internal/prof_recent.h"
 #include "jemalloc/internal/util.h"
 

src/mutex.c

@@ -1,8 +1,8 @@
 #include "jemalloc/internal/jemalloc_preamble.h"
-#include "jemalloc/internal/jemalloc_internal_includes.h"
 
 #include "jemalloc/internal/assert.h"
 #include "jemalloc/internal/malloc_io.h"
+#include "jemalloc/internal/mutex.h"
 #include "jemalloc/internal/spin.h"
 
 #if defined(_WIN32) && !defined(_CRT_SPINCOUNT)

src/nstime.c

@@ -1,9 +1,7 @@
 #include "jemalloc/internal/jemalloc_preamble.h"
-#include "jemalloc/internal/jemalloc_internal_includes.h"
-
-#include "jemalloc/internal/nstime.h"
 
 #include "jemalloc/internal/assert.h"
+#include "jemalloc/internal/nstime.h"
 
 #define BILLION UINT64_C(1000000000)
 #define MILLION UINT64_C(1000000)

src/pa.c

@@ -1,8 +1,9 @@
 #include "jemalloc/internal/jemalloc_preamble.h"
-#include "jemalloc/internal/jemalloc_internal_includes.h"
 
-#include "jemalloc/internal/san.h"
+#include "jemalloc/internal/background_thread.h"
 #include "jemalloc/internal/hpa.h"
+#include "jemalloc/internal/pa.h"
+#include "jemalloc/internal/san.h"
 
 static void
 pa_nactive_add(pa_shard_t *shard, size_t add_pages) {

src/pa_extra.c

@@ -1,5 +1,6 @@
 #include "jemalloc/internal/jemalloc_preamble.h"
-#include "jemalloc/internal/jemalloc_internal_includes.h"
+
+#include "jemalloc/internal/pa.h"
 
 /*
  * This file is logically part of the PA module.  While pa.c contains the core

src/prof_stack_range.c

@@ -1,5 +1,4 @@
 #include "jemalloc/internal/jemalloc_preamble.h"
-#include "jemalloc/internal/jemalloc_internal_includes.h"
 
 #include "jemalloc/internal/malloc_io.h"
 #include "jemalloc/internal/prof_sys.h"

src/rtree.c

@@ -1,8 +1,8 @@
 #include "jemalloc/internal/jemalloc_preamble.h"
-#include "jemalloc/internal/jemalloc_internal_includes.h"
 
 #include "jemalloc/internal/assert.h"
 #include "jemalloc/internal/mutex.h"
+#include "jemalloc/internal/rtree.h"
 
 /*
  * Only the most significant bits of keys passed to rtree_{read,write}() are

src/san.c

@@ -1,8 +1,8 @@
 #include "jemalloc/internal/jemalloc_preamble.h"
-#include "jemalloc/internal/jemalloc_internal_includes.h"
 
 #include "jemalloc/internal/assert.h"
 #include "jemalloc/internal/ehooks.h"
+#include "jemalloc/internal/emap.h"
 #include "jemalloc/internal/san.h"
 #include "jemalloc/internal/tsd.h"
 

src/thread_event_registry.c

@@ -1,12 +1,15 @@
 #include "jemalloc/internal/jemalloc_preamble.h"
-#include "jemalloc/internal/jemalloc_internal_includes.h"
 
-#include "jemalloc/internal/thread_event.h"
-#include "jemalloc/internal/thread_event_registry.h"
-#include "jemalloc/internal/tcache.h"
+#include "jemalloc/internal/jemalloc_internal_inlines_a.h"
+#include "jemalloc/internal/mutex.h"
 #include "jemalloc/internal/peak_event.h"
 #include "jemalloc/internal/prof.h"
 #include "jemalloc/internal/stats.h"
+#include "jemalloc/internal/tcache.h"
+#include "jemalloc/internal/thread_event.h"
+#include "jemalloc/internal/thread_event_registry.h"
+#include "jemalloc/internal/tsd.h"
+#include "jemalloc/internal/witness.h"
 
 static malloc_mutex_t uevents_mu;