bpo-30860: Consolidate stateful runtime globals. (#3397)

* group the (stateful) runtime globals into various topical structs
* consolidate the topical structs under a single top-level _PyRuntimeState struct
* add a check-c-globals.py script that helps identify runtime globals

Other globals are excluded (see globals.txt and check-c-globals.py).

7 files changed, 943 insertions, 0 deletions

diff --git a/Include/internal/ceval.h b/Include/internal/ceval.h
new file mode 100644
index 0000000000..57db9b1ebc
--- /dev/null
+++ b/Include/internal/ceval.h
@@ -0,0 +1,53 @@
+#ifndef Py_INTERNAL_CEVAL_H
+#define Py_INTERNAL_CEVAL_H
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+#include "pyatomic.h"
+#include "pythread.h"
+
+struct _pending_calls {
+    unsigned long main_thread;
+    PyThread_type_lock lock;
+    /* Request for running pending calls. */
+    _Py_atomic_int calls_to_do;
+    /* Request for looking at the `async_exc` field of the current
+       thread state.
+       Guarded by the GIL. */
+    int async_exc;
+#define NPENDINGCALLS 32
+    struct {
+        int (*func)(void *);
+        void *arg;
+    } calls[NPENDINGCALLS];
+    int first;
+    int last;
+};
+
+#include "internal/gil.h"
+
+struct _ceval_runtime_state {
+    int recursion_limit;
+    int check_recursion_limit;
+    /* Records whether tracing is on for any thread.  Counts the number
+       of threads for which tstate->c_tracefunc is non-NULL, so if the
+       value is 0, we know we don't have to check this thread's
+       c_tracefunc.  This speeds up the if statement in
+       PyEval_EvalFrameEx() after fast_next_opcode. */
+    int tracing_possible;
+    /* This single variable consolidates all requests to break out of
+       the fast path in the eval loop. */
+    _Py_atomic_int eval_breaker;
+    /* Request for dropping the GIL */
+    _Py_atomic_int gil_drop_request;
+    struct _pending_calls pending;
+    struct _gil_runtime_state gil;
+};
+
+PyAPI_FUNC(void) _PyEval_Initialize(struct _ceval_runtime_state *);
+
+#ifdef __cplusplus
+}
+#endif
+#endif /* !Py_INTERNAL_CEVAL_H */
diff --git a/Include/internal/condvar.h b/Include/internal/condvar.h
new file mode 100644
index 0000000000..f9330890d3
--- /dev/null
+++ b/Include/internal/condvar.h
@@ -0,0 +1,91 @@
+#ifndef Py_INTERNAL_CONDVAR_H
+#define Py_INTERNAL_CONDVAR_H
+
+#ifndef _POSIX_THREADS
+/* This means pthreads are not implemented in libc headers, hence the macro
+   not present in unistd.h. But they still can be implemented as an external
+   library (e.g. gnu pth in pthread emulation) */
+# ifdef HAVE_PTHREAD_H
+#  include <pthread.h> /* _POSIX_THREADS */
+# endif
+#endif
+
+#ifdef _POSIX_THREADS
+/*
+ * POSIX support
+ */
+#define Py_HAVE_CONDVAR
+
+#include <pthread.h>
+
+#define PyMUTEX_T pthread_mutex_t
+#define PyCOND_T pthread_cond_t
+
+#elif defined(NT_THREADS)
+/*
+ * Windows (XP, 2003 server and later, as well as (hopefully) CE) support
+ *
+ * Emulated condition variables ones that work with XP and later, plus
+ * example native support on VISTA and onwards.
+ */
+#define Py_HAVE_CONDVAR
+
+/* include windows if it hasn't been done before */
+#define WIN32_LEAN_AND_MEAN
+#include <windows.h>
+
+/* options */
+/* non-emulated condition variables are provided for those that want
+ * to target Windows Vista.  Modify this macro to enable them.
+ */
+#ifndef _PY_EMULATED_WIN_CV
+#define _PY_EMULATED_WIN_CV 1  /* use emulated condition variables */
+#endif
+
+/* fall back to emulation if not targeting Vista */
+#if !defined NTDDI_VISTA || NTDDI_VERSION < NTDDI_VISTA
+#undef _PY_EMULATED_WIN_CV
+#define _PY_EMULATED_WIN_CV 1
+#endif
+
+#if _PY_EMULATED_WIN_CV
+
+typedef CRITICAL_SECTION PyMUTEX_T;
+
+/* The ConditionVariable object.  From XP onwards it is easily emulated
+   with a Semaphore.
+   Semaphores are available on Windows XP (2003 server) and later.
+   We use a Semaphore rather than an auto-reset event, because although
+   an auto-resent event might appear to solve the lost-wakeup bug (race
+   condition between releasing the outer lock and waiting) because it
+   maintains state even though a wait hasn't happened, there is still
+   a lost wakeup problem if more than one thread are interrupted in the
+   critical place.  A semaphore solves that, because its state is
+   counted, not Boolean.
+   Because it is ok to signal a condition variable with no one
+   waiting, we need to keep track of the number of
+   waiting threads.  Otherwise, the semaphore's state could rise
+   without bound.  This also helps reduce the number of "spurious wakeups"
+   that would otherwise happen.
+ */
+
+typedef struct _PyCOND_T
+{
+    HANDLE sem;
+    int waiting; /* to allow PyCOND_SIGNAL to be a no-op */
+} PyCOND_T;
+
+#else /* !_PY_EMULATED_WIN_CV */
+
+/* Use native Win7 primitives if build target is Win7 or higher */
+
+/* SRWLOCK is faster and better than CriticalSection */
+typedef SRWLOCK PyMUTEX_T;
+
+typedef CONDITION_VARIABLE  PyCOND_T;
+
+#endif /* _PY_EMULATED_WIN_CV */
+
+#endif /* _POSIX_THREADS, NT_THREADS */
+
+#endif /* Py_INTERNAL_CONDVAR_H */
diff --git a/Include/internal/gil.h b/Include/internal/gil.h
new file mode 100644
index 0000000000..6139bd215c
--- /dev/null
+++ b/Include/internal/gil.h
@@ -0,0 +1,46 @@
+#ifndef Py_INTERNAL_GIL_H
+#define Py_INTERNAL_GIL_H
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+#include "pyatomic.h"
+
+#include "internal/condvar.h"
+#ifndef Py_HAVE_CONDVAR
+#error You need either a POSIX-compatible or a Windows system!
+#endif
+
+/* Enable if you want to force the switching of threads at least
+   every `interval`. */
+#undef FORCE_SWITCHING
+#define FORCE_SWITCHING
+
+struct _gil_runtime_state {
+    /* microseconds (the Python API uses seconds, though) */
+    unsigned long interval;
+    /* Last PyThreadState holding / having held the GIL. This helps us
+       know whether anyone else was scheduled after we dropped the GIL. */
+    _Py_atomic_address last_holder;
+    /* Whether the GIL is already taken (-1 if uninitialized). This is
+       atomic because it can be read without any lock taken in ceval.c. */
+    _Py_atomic_int locked;
+    /* Number of GIL switches since the beginning. */
+    unsigned long switch_number;
+    /* This condition variable allows one or several threads to wait
+       until the GIL is released. In addition, the mutex also protects
+       the above variables. */
+    PyCOND_T cond;
+    PyMUTEX_T mutex;
+#ifdef FORCE_SWITCHING
+    /* This condition variable helps the GIL-releasing thread wait for
+       a GIL-awaiting thread to be scheduled and take the GIL. */
+    PyCOND_T switch_cond;
+    PyMUTEX_T switch_mutex;
+#endif
+};
+
+#ifdef __cplusplus
+}
+#endif
+#endif /* !Py_INTERNAL_GIL_H */
diff --git a/Include/internal/mem.h b/Include/internal/mem.h
new file mode 100644
index 0000000000..1624f378f6
--- /dev/null
+++ b/Include/internal/mem.h
@@ -0,0 +1,197 @@
+#ifndef Py_INTERNAL_MEM_H
+#define Py_INTERNAL_MEM_H
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+#include "objimpl.h"
+#include "pymem.h"
+
+#ifdef WITH_PYMALLOC
+#include "internal/pymalloc.h"
+#endif
+
+/* Low-level memory runtime state */
+
+struct _pymem_runtime_state {
+    struct _allocator_runtime_state {
+        PyMemAllocatorEx mem;
+        PyMemAllocatorEx obj;
+        PyMemAllocatorEx raw;
+    } allocators;
+#ifdef WITH_PYMALLOC
+    /* Array of objects used to track chunks of memory (arenas). */
+    struct arena_object* arenas;
+    /* The head of the singly-linked, NULL-terminated list of available
+       arena_objects. */
+    struct arena_object* unused_arena_objects;
+    /* The head of the doubly-linked, NULL-terminated at each end,
+       list of arena_objects associated with arenas that have pools
+       available. */
+    struct arena_object* usable_arenas;
+    /* Number of slots currently allocated in the `arenas` vector. */
+    unsigned int maxarenas;
+    /* Number of arenas allocated that haven't been free()'d. */
+    size_t narenas_currently_allocated;
+    /* High water mark (max value ever seen) for
+     * narenas_currently_allocated. */
+    size_t narenas_highwater;
+    /* Total number of times malloc() called to allocate an arena. */
+    size_t ntimes_arena_allocated;
+    poolp usedpools[MAX_POOLS];
+    Py_ssize_t num_allocated_blocks;
+    size_t serialno;     /* incremented on each debug {m,re}alloc */
+#endif /* WITH_PYMALLOC */
+};
+
+PyAPI_FUNC(void) _PyMem_Initialize(struct _pymem_runtime_state *);
+
+
+/* High-level memory runtime state */
+
+struct _pyobj_runtime_state {
+    PyObjectArenaAllocator allocator_arenas;
+};
+
+PyAPI_FUNC(void) _PyObject_Initialize(struct _pyobj_runtime_state *);
+
+
+/* GC runtime state */
+
+/* If we change this, we need to change the default value in the
+   signature of gc.collect. */
+#define NUM_GENERATIONS 3
+
+/*
+   NOTE: about the counting of long-lived objects.
+
+   To limit the cost of garbage collection, there are two strategies;
+     - make each collection faster, e.g. by scanning fewer objects
+     - do less collections
+   This heuristic is about the latter strategy.
+
+   In addition to the various configurable thresholds, we only trigger a
+   full collection if the ratio
+    long_lived_pending / long_lived_total
+   is above a given value (hardwired to 25%).
+
+   The reason is that, while "non-full" collections (i.e., collections of
+   the young and middle generations) will always examine roughly the same
+   number of objects -- determined by the aforementioned thresholds --,
+   the cost of a full collection is proportional to the total number of
+   long-lived objects, which is virtually unbounded.
+
+   Indeed, it has been remarked that doing a full collection every
+   <constant number> of object creations entails a dramatic performance
+   degradation in workloads which consist in creating and storing lots of
+   long-lived objects (e.g. building a large list of GC-tracked objects would
+   show quadratic performance, instead of linear as expected: see issue #4074).
+
+   Using the above ratio, instead, yields amortized linear performance in
+   the total number of objects (the effect of which can be summarized
+   thusly: "each full garbage collection is more and more costly as the
+   number of objects grows, but we do fewer and fewer of them").
+
+   This heuristic was suggested by Martin von Löwis on python-dev in
+   June 2008. His original analysis and proposal can be found at:
+    http://mail.python.org/pipermail/python-dev/2008-June/080579.html
+*/
+
+/*
+   NOTE: about untracking of mutable objects.
+
+   Certain types of container cannot participate in a reference cycle, and
+   so do not need to be tracked by the garbage collector. Untracking these
+   objects reduces the cost of garbage collections. However, determining
+   which objects may be untracked is not free, and the costs must be
+   weighed against the benefits for garbage collection.
+
+   There are two possible strategies for when to untrack a container:
+
+   i) When the container is created.
+   ii) When the container is examined by the garbage collector.
+
+   Tuples containing only immutable objects (integers, strings etc, and
+   recursively, tuples of immutable objects) do not need to be tracked.
+   The interpreter creates a large number of tuples, many of which will
+   not survive until garbage collection. It is therefore not worthwhile
+   to untrack eligible tuples at creation time.
+
+   Instead, all tuples except the empty tuple are tracked when created.
+   During garbage collection it is determined whether any surviving tuples
+   can be untracked. A tuple can be untracked if all of its contents are
+   already not tracked. Tuples are examined for untracking in all garbage
+   collection cycles. It may take more than one cycle to untrack a tuple.
+
+   Dictionaries containing only immutable objects also do not need to be
+   tracked. Dictionaries are untracked when created. If a tracked item is
+   inserted into a dictionary (either as a key or value), the dictionary
+   becomes tracked. During a full garbage collection (all generations),
+   the collector will untrack any dictionaries whose contents are not
+   tracked.
+
+   The module provides the python function is_tracked(obj), which returns
+   the CURRENT tracking status of the object. Subsequent garbage
+   collections may change the tracking status of the object.
+
+   Untracking of certain containers was introduced in issue #4688, and
+   the algorithm was refined in response to issue #14775.
+*/
+
+struct gc_generation {
+    PyGC_Head head;
+    int threshold; /* collection threshold */
+    int count; /* count of allocations or collections of younger
+                  generations */
+};
+
+/* Running stats per generation */
+struct gc_generation_stats {
+    /* total number of collections */
+    Py_ssize_t collections;
+    /* total number of collected objects */
+    Py_ssize_t collected;
+    /* total number of uncollectable objects (put into gc.garbage) */
+    Py_ssize_t uncollectable;
+};
+
+struct _gc_runtime_state {
+    /* List of objects that still need to be cleaned up, singly linked
+     * via their gc headers' gc_prev pointers.  */
+    PyObject *trash_delete_later;
+    /* Current call-stack depth of tp_dealloc calls. */
+    int trash_delete_nesting;
+
+    int enabled;
+    int debug;
+    /* linked lists of container objects */
+    struct gc_generation generations[NUM_GENERATIONS];
+    PyGC_Head *generation0;
+    struct gc_generation_stats generation_stats[NUM_GENERATIONS];
+    /* true if we are currently running the collector */
+    int collecting;
+    /* list of uncollectable objects */
+    PyObject *garbage;
+    /* a list of callbacks to be invoked when collection is performed */
+    PyObject *callbacks;
+    /* This is the number of objects that survived the last full
+       collection. It approximates the number of long lived objects
+       tracked by the GC.
+
+       (by "full collection", we mean a collection of the oldest
+       generation). */
+    Py_ssize_t long_lived_total;
+    /* This is the number of objects that survived all "non-full"
+       collections, and are awaiting to undergo a full collection for
+       the first time. */
+    Py_ssize_t long_lived_pending;
+};
+
+PyAPI_FUNC(void) _PyGC_Initialize(struct _gc_runtime_state *);
+
+#define _PyGC_generation0 _PyRuntime.gc.generation0
+
+#ifdef __cplusplus
+}
+#endif
+#endif /* !Py_INTERNAL_MEM_H */
diff --git a/Include/internal/pymalloc.h b/Include/internal/pymalloc.h
new file mode 100644
index 0000000000..e9d6ab6a8b
--- /dev/null
+++ b/Include/internal/pymalloc.h
@@ -0,0 +1,443 @@
+
+/* An object allocator for Python.
+
+   Here is an introduction to the layers of the Python memory architecture,
+   showing where the object allocator is actually used (layer +2), It is
+   called for every object allocation and deallocation (PyObject_New/Del),
+   unless the object-specific allocators implement a proprietary allocation
+   scheme (ex.: ints use a simple free list). This is also the place where
+   the cyclic garbage collector operates selectively on container objects.
+
+
+    Object-specific allocators
+    _____   ______   ______       ________
+   [ int ] [ dict ] [ list ] ... [ string ]       Python core         |
++3 | <----- Object-specific memory -----> | <-- Non-object memory --> |
+    _______________________________       |                           |
+   [   Python's object allocator   ]      |                           |
++2 | ####### Object memory ####### | <------ Internal buffers ------> |
+    ______________________________________________________________    |
+   [          Python's raw memory allocator (PyMem_ API)          ]   |
++1 | <----- Python memory (under PyMem manager's control) ------> |   |
+    __________________________________________________________________
+   [    Underlying general-purpose allocator (ex: C library malloc)   ]
+ 0 | <------ Virtual memory allocated for the python process -------> |
+
+   =========================================================================
+    _______________________________________________________________________
+   [                OS-specific Virtual Memory Manager (VMM)               ]
+-1 | <--- Kernel dynamic storage allocation & management (page-based) ---> |
+    __________________________________   __________________________________
+   [                                  ] [                                  ]
+-2 | <-- Physical memory: ROM/RAM --> | | <-- Secondary storage (swap) --> |
+
+*/
+/*==========================================================================*/
+
+/* A fast, special-purpose memory allocator for small blocks, to be used
+   on top of a general-purpose malloc -- heavily based on previous art. */
+
+/* Vladimir Marangozov -- August 2000 */
+
+/*
+ * "Memory management is where the rubber meets the road -- if we do the wrong
+ * thing at any level, the results will not be good. And if we don't make the
+ * levels work well together, we are in serious trouble." (1)
+ *
+ * (1) Paul R. Wilson, Mark S. Johnstone, Michael Neely, and David Boles,
+ *    "Dynamic Storage Allocation: A Survey and Critical Review",
+ *    in Proc. 1995 Int'l. Workshop on Memory Management, September 1995.
+ */
+
+#ifndef Py_INTERNAL_PYMALLOC_H
+#define Py_INTERNAL_PYMALLOC_H
+
+/* #undef WITH_MEMORY_LIMITS */         /* disable mem limit checks  */
+
+/*==========================================================================*/
+
+/*
+ * Allocation strategy abstract:
+ *
+ * For small requests, the allocator sub-allocates <Big> blocks of memory.
+ * Requests greater than SMALL_REQUEST_THRESHOLD bytes are routed to the
+ * system's allocator.
+ *
+ * Small requests are grouped in size classes spaced 8 bytes apart, due
+ * to the required valid alignment of the returned address. Requests of
+ * a particular size are serviced from memory pools of 4K (one VMM page).
+ * Pools are fragmented on demand and contain free lists of blocks of one
+ * particular size class. In other words, there is a fixed-size allocator
+ * for each size class. Free pools are shared by the different allocators
+ * thus minimizing the space reserved for a particular size class.
+ *
+ * This allocation strategy is a variant of what is known as "simple
+ * segregated storage based on array of free lists". The main drawback of
+ * simple segregated storage is that we might end up with lot of reserved
+ * memory for the different free lists, which degenerate in time. To avoid
+ * this, we partition each free list in pools and we share dynamically the
+ * reserved space between all free lists. This technique is quite efficient
+ * for memory intensive programs which allocate mainly small-sized blocks.
+ *
+ * For small requests we have the following table:
+ *
+ * Request in bytes     Size of allocated block      Size class idx
+ * ----------------------------------------------------------------
+ *        1-8                     8                       0
+ *        9-16                   16                       1
+ *       17-24                   24                       2
+ *       25-32                   32                       3
+ *       33-40                   40                       4
+ *       41-48                   48                       5
+ *       49-56                   56                       6
+ *       57-64                   64                       7
+ *       65-72                   72                       8
+ *        ...                   ...                     ...
+ *      497-504                 504                      62
+ *      505-512                 512                      63
+ *
+ *      0, SMALL_REQUEST_THRESHOLD + 1 and up: routed to the underlying
+ *      allocator.
+ */
+
+/*==========================================================================*/
+
+/*
+ * -- Main tunable settings section --
+ */
+
+/*
+ * Alignment of addresses returned to the user. 8-bytes alignment works
+ * on most current architectures (with 32-bit or 64-bit address busses).
+ * The alignment value is also used for grouping small requests in size
+ * classes spaced ALIGNMENT bytes apart.
+ *
+ * You shouldn't change this unless you know what you are doing.
+ */
+#define ALIGNMENT               8               /* must be 2^N */
+#define ALIGNMENT_SHIFT         3
+
+/* Return the number of bytes in size class I, as a uint. */
+#define INDEX2SIZE(I) (((unsigned int)(I) + 1) << ALIGNMENT_SHIFT)
+
+/*
+ * Max size threshold below which malloc requests are considered to be
+ * small enough in order to use preallocated memory pools. You can tune
+ * this value according to your application behaviour and memory needs.
+ *
+ * Note: a size threshold of 512 guarantees that newly created dictionaries
+ * will be allocated from preallocated memory pools on 64-bit.
+ *
+ * The following invariants must hold:
+ *      1) ALIGNMENT <= SMALL_REQUEST_THRESHOLD <= 512
+ *      2) SMALL_REQUEST_THRESHOLD is evenly divisible by ALIGNMENT
+ *
+ * Although not required, for better performance and space efficiency,
+ * it is recommended that SMALL_REQUEST_THRESHOLD is set to a power of 2.
+ */
+#define SMALL_REQUEST_THRESHOLD 512
+#define NB_SMALL_SIZE_CLASSES   (SMALL_REQUEST_THRESHOLD / ALIGNMENT)
+
+#if NB_SMALL_SIZE_CLASSES > 64
+#error "NB_SMALL_SIZE_CLASSES should be less than 64"
+#endif /* NB_SMALL_SIZE_CLASSES > 64 */
+
+/*
+ * The system's VMM page size can be obtained on most unices with a
+ * getpagesize() call or deduced from various header files. To make
+ * things simpler, we assume that it is 4K, which is OK for most systems.
+ * It is probably better if this is the native page size, but it doesn't
+ * have to be.  In theory, if SYSTEM_PAGE_SIZE is larger than the native page
+ * size, then `POOL_ADDR(p)->arenaindex' could rarely cause a segmentation
+ * violation fault.  4K is apparently OK for all the platforms that python
+ * currently targets.
+ */
+#define SYSTEM_PAGE_SIZE        (4 * 1024)
+#define SYSTEM_PAGE_SIZE_MASK   (SYSTEM_PAGE_SIZE - 1)
+
+/*
+ * Maximum amount of memory managed by the allocator for small requests.
+ */
+#ifdef WITH_MEMORY_LIMITS
+#ifndef SMALL_MEMORY_LIMIT
+#define SMALL_MEMORY_LIMIT      (64 * 1024 * 1024)      /* 64 MB -- more? */
+#endif
+#endif
+
+/*
+ * The allocator sub-allocates <Big> blocks of memory (called arenas) aligned
+ * on a page boundary. This is a reserved virtual address space for the
+ * current process (obtained through a malloc()/mmap() call). In no way this
+ * means that the memory arenas will be used entirely. A malloc(<Big>) is
+ * usually an address range reservation for <Big> bytes, unless all pages within
+ * this space are referenced subsequently. So malloc'ing big blocks and not
+ * using them does not mean "wasting memory". It's an addressable range
+ * wastage...
+ *
+ * Arenas are allocated with mmap() on systems supporting anonymous memory
+ * mappings to reduce heap fragmentation.
+ */
+#define ARENA_SIZE              (256 << 10)     /* 256KB */
+
+#ifdef WITH_MEMORY_LIMITS
+#define MAX_ARENAS              (SMALL_MEMORY_LIMIT / ARENA_SIZE)
+#endif
+
+/*
+ * Size of the pools used for small blocks. Should be a power of 2,
+ * between 1K and SYSTEM_PAGE_SIZE, that is: 1k, 2k, 4k.
+ */
+#define POOL_SIZE               SYSTEM_PAGE_SIZE        /* must be 2^N */
+#define POOL_SIZE_MASK          SYSTEM_PAGE_SIZE_MASK
+
+/*
+ * -- End of tunable settings section --
+ */
+
+/*==========================================================================*/
+
+/*
+ * Locking
+ *
+ * To reduce lock contention, it would probably be better to refine the
+ * crude function locking with per size class locking. I'm not positive
+ * however, whether it's worth switching to such locking policy because
+ * of the performance penalty it might introduce.
+ *
+ * The following macros describe the simplest (should also be the fastest)
+ * lock object on a particular platform and the init/fini/lock/unlock
+ * operations on it. The locks defined here are not expected to be recursive
+ * because it is assumed that they will always be called in the order:
+ * INIT, [LOCK, UNLOCK]*, FINI.
+ */
+
+/*
+ * Python's threads are serialized, so object malloc locking is disabled.
+ */
+#define SIMPLELOCK_DECL(lock)   /* simple lock declaration              */
+#define SIMPLELOCK_INIT(lock)   /* allocate (if needed) and initialize  */
+#define SIMPLELOCK_FINI(lock)   /* free/destroy an existing lock        */
+#define SIMPLELOCK_LOCK(lock)   /* acquire released lock */
+#define SIMPLELOCK_UNLOCK(lock) /* release acquired lock */
+
+/* When you say memory, my mind reasons in terms of (pointers to) blocks */
+typedef uint8_t pyblock;
+
+/* Pool for small blocks. */
+struct pool_header {
+    union { pyblock *_padding;
+            unsigned int count; } ref;  /* number of allocated blocks    */
+    pyblock *freeblock;                 /* pool's free list head         */
+    struct pool_header *nextpool;       /* next pool of this size class  */
+    struct pool_header *prevpool;       /* previous pool       ""        */
+    unsigned int arenaindex;            /* index into arenas of base adr */
+    unsigned int szidx;                 /* block size class index        */
+    unsigned int nextoffset;            /* bytes to virgin block         */
+    unsigned int maxnextoffset;         /* largest valid nextoffset      */
+};
+
+typedef struct pool_header *poolp;
+
+/* Record keeping for arenas. */
+struct arena_object {
+    /* The address of the arena, as returned by malloc.  Note that 0
+     * will never be returned by a successful malloc, and is used
+     * here to mark an arena_object that doesn't correspond to an
+     * allocated arena.
+     */
+    uintptr_t address;
+
+    /* Pool-aligned pointer to the next pool to be carved off. */
+    pyblock* pool_address;
+
+    /* The number of available pools in the arena:  free pools + never-
+     * allocated pools.
+     */
+    unsigned int nfreepools;
+
+    /* The total number of pools in the arena, whether or not available. */
+    unsigned int ntotalpools;
+
+    /* Singly-linked list of available pools. */
+    struct pool_header* freepools;
+
+    /* Whenever this arena_object is not associated with an allocated
+     * arena, the nextarena member is used to link all unassociated
+     * arena_objects in the singly-linked `unused_arena_objects` list.
+     * The prevarena member is unused in this case.
+     *
+     * When this arena_object is associated with an allocated arena
+     * with at least one available pool, both members are used in the
+     * doubly-linked `usable_arenas` list, which is maintained in
+     * increasing order of `nfreepools` values.
+     *
+     * Else this arena_object is associated with an allocated arena
+     * all of whose pools are in use.  `nextarena` and `prevarena`
+     * are both meaningless in this case.
+     */
+    struct arena_object* nextarena;
+    struct arena_object* prevarena;
+};
+
+#define POOL_OVERHEAD   _Py_SIZE_ROUND_UP(sizeof(struct pool_header), ALIGNMENT)
+
+#define DUMMY_SIZE_IDX          0xffff  /* size class of newly cached pools */
+
+/* Round pointer P down to the closest pool-aligned address <= P, as a poolp */
+#define POOL_ADDR(P) ((poolp)_Py_ALIGN_DOWN((P), POOL_SIZE))
+
+/* Return total number of blocks in pool of size index I, as a uint. */
+#define NUMBLOCKS(I) \
+    ((unsigned int)(POOL_SIZE - POOL_OVERHEAD) / INDEX2SIZE(I))
+
+/*==========================================================================*/
+
+/*
+ * This malloc lock
+ */
+SIMPLELOCK_DECL(_malloc_lock)
+#define LOCK()          SIMPLELOCK_LOCK(_malloc_lock)
+#define UNLOCK()        SIMPLELOCK_UNLOCK(_malloc_lock)
+#define LOCK_INIT()     SIMPLELOCK_INIT(_malloc_lock)
+#define LOCK_FINI()     SIMPLELOCK_FINI(_malloc_lock)
+
+/*
+ * Pool table -- headed, circular, doubly-linked lists of partially used pools.
+
+This is involved.  For an index i, usedpools[i+i] is the header for a list of
+all partially used pools holding small blocks with "size class idx" i. So
+usedpools[0] corresponds to blocks of size 8, usedpools[2] to blocks of size
+16, and so on:  index 2*i <-> blocks of size (i+1)<<ALIGNMENT_SHIFT.
+
+Pools are carved off an arena's highwater mark (an arena_object's pool_address
+member) as needed.  Once carved off, a pool is in one of three states forever
+after:
+
+used == partially used, neither empty nor full
+    At least one block in the pool is currently allocated, and at least one
+    block in the pool is not currently allocated (note this implies a pool
+    has room for at least two blocks).
+    This is a pool's initial state, as a pool is created only when malloc
+    needs space.
+    The pool holds blocks of a fixed size, and is in the circular list headed
+    at usedpools[i] (see above).  It's linked to the other used pools of the
+    same size class via the pool_header's nextpool and prevpool members.
+    If all but one block is currently allocated, a malloc can cause a
+    transition to the full state.  If all but one block is not currently
+    allocated, a free can cause a transition to the empty state.
+
+full == all the pool's blocks are currently allocated
+    On transition to full, a pool is unlinked from its usedpools[] list.
+    It's not linked to from anything then anymore, and its nextpool and
+    prevpool members are meaningless until it transitions back to used.
+    A free of a block in a full pool puts the pool back in the used state.
+    Then it's linked in at the front of the appropriate usedpools[] list, so
+    that the next allocation for its size class will reuse the freed block.
+
+empty == all the pool's blocks are currently available for allocation
+    On transition to empty, a pool is unlinked from its usedpools[] list,
+    and linked to the front of its arena_object's singly-linked freepools list,
+    via its nextpool member.  The prevpool member has no meaning in this case.
+    Empty pools have no inherent size class:  the next time a malloc finds
+    an empty list in usedpools[], it takes the first pool off of freepools.
+    If the size class needed happens to be the same as the size class the pool
+    last had, some pool initialization can be skipped.
+
+
+Block Management
+
+Blocks within pools are again carved out as needed.  pool->freeblock points to
+the start of a singly-linked list of free blocks within the pool.  When a
+block is freed, it's inserted at the front of its pool's freeblock list.  Note
+that the available blocks in a pool are *not* linked all together when a pool
+is initialized.  Instead only "the first two" (lowest addresses) blocks are
+set up, returning the first such block, and setting pool->freeblock to a
+one-block list holding the second such block.  This is consistent with that
+pymalloc strives at all levels (arena, pool, and block) never to touch a piece
+of memory until it's actually needed.
+
+So long as a pool is in the used state, we're certain there *is* a block
+available for allocating, and pool->freeblock is not NULL.  If pool->freeblock
+points to the end of the free list before we've carved the entire pool into
+blocks, that means we simply haven't yet gotten to one of the higher-address
+blocks.  The offset from the pool_header to the start of "the next" virgin
+block is stored in the pool_header nextoffset member, and the largest value
+of nextoffset that makes sense is stored in the maxnextoffset member when a
+pool is initialized.  All the blocks in a pool have been passed out at least
+once when and only when nextoffset > maxnextoffset.
+
+
+Major obscurity:  While the usedpools vector is declared to have poolp
+entries, it doesn't really.  It really contains two pointers per (conceptual)
+poolp entry, the nextpool and prevpool members of a pool_header.  The
+excruciating initialization code below fools C so that
+
+    usedpool[i+i]
+
+"acts like" a genuine poolp, but only so long as you only reference its
+nextpool and prevpool members.  The "- 2*sizeof(block *)" gibberish is
+compensating for that a pool_header's nextpool and prevpool members
+immediately follow a pool_header's first two members:
+
+    union { block *_padding;
+            uint count; } ref;
+    block *freeblock;
+
+each of which consume sizeof(block *) bytes.  So what usedpools[i+i] really
+contains is a fudged-up pointer p such that *if* C believes it's a poolp
+pointer, then p->nextpool and p->prevpool are both p (meaning that the headed
+circular list is empty).
+
+It's unclear why the usedpools setup is so convoluted.  It could be to
+minimize the amount of cache required to hold this heavily-referenced table
+(which only *needs* the two interpool pointer members of a pool_header). OTOH,
+referencing code has to remember to "double the index" and doing so isn't
+free, usedpools[0] isn't a strictly legal pointer, and we're crucially relying
+on that C doesn't insert any padding anywhere in a pool_header at or before
+the prevpool member.
+**************************************************************************** */
+
+#define MAX_POOLS  (2 * ((NB_SMALL_SIZE_CLASSES + 7) / 8) * 8)
+
+/*==========================================================================
+Arena management.
+
+`arenas` is a vector of arena_objects.  It contains maxarenas entries, some of
+which may not be currently used (== they're arena_objects that aren't
+currently associated with an allocated arena).  Note that arenas proper are
+separately malloc'ed.
+
+Prior to Python 2.5, arenas were never free()'ed.  Starting with Python 2.5,
+we do try to free() arenas, and use some mild heuristic strategies to increase
+the likelihood that arenas eventually can be freed.
+
+unused_arena_objects
+
+    This is a singly-linked list of the arena_objects that are currently not
+    being used (no arena is associated with them).  Objects are taken off the
+    head of the list in new_arena(), and are pushed on the head of the list in
+    PyObject_Free() when the arena is empty.  Key invariant:  an arena_object
+    is on this list if and only if its .address member is 0.
+
+usable_arenas
+
+    This is a doubly-linked list of the arena_objects associated with arenas
+    that have pools available.  These pools are either waiting to be reused,
+    or have not been used before.  The list is sorted to have the most-
+    allocated arenas first (ascending order based on the nfreepools member).
+    This means that the next allocation will come from a heavily used arena,
+    which gives the nearly empty arenas a chance to be returned to the system.
+    In my unscientific tests this dramatically improved the number of arenas
+    that could be freed.
+
+Note that an arena_object associated with an arena all of whose pools are
+currently in use isn't on either list.
+*/
+
+/* How many arena_objects do we initially allocate?
+ * 16 = can allocate 16 arenas = 16 * ARENA_SIZE = 4MB before growing the
+ * `arenas` vector.
+ */
+#define INITIAL_ARENA_OBJECTS 16
+
+#endif /* Py_INTERNAL_PYMALLOC_H */
diff --git a/Include/internal/pystate.h b/Include/internal/pystate.h
new file mode 100644
index 0000000000..20c5946b14
--- /dev/null
+++ b/Include/internal/pystate.h
@@ -0,0 +1,92 @@
+#ifndef Py_INTERNAL_PYSTATE_H
+#define Py_INTERNAL_PYSTATE_H
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+#include "pystate.h"
+#include "pyatomic.h"
+#include "pythread.h"
+
+#include "internal/mem.h"
+#include "internal/ceval.h"
+#include "internal/warnings.h"
+
+
+/* GIL state */
+
+struct _gilstate_runtime_state {
+    int check_enabled;
+    /* Assuming the current thread holds the GIL, this is the
+       PyThreadState for the current thread. */
+    _Py_atomic_address tstate_current;
+    PyThreadFrameGetter getframe;
+    /* The single PyInterpreterState used by this process'
+       GILState implementation
+    */
+    /* TODO: Given interp_main, it may be possible to kill this ref */
+    PyInterpreterState *autoInterpreterState;
+    int autoTLSkey;
+};
+
+/* hook for PyEval_GetFrame(), requested for Psyco */
+#define _PyThreadState_GetFrame _PyRuntime.gilstate.getframe
+
+/* Issue #26558: Flag to disable PyGILState_Check().
+   If set to non-zero, PyGILState_Check() always return 1. */
+#define _PyGILState_check_enabled _PyRuntime.gilstate.check_enabled
+
+
+/* Full Python runtime state */
+
+typedef struct pyruntimestate {
+    int initialized;
+    int core_initialized;
+    PyThreadState *finalizing;
+
+    struct pyinterpreters {
+        PyThread_type_lock mutex;
+        PyInterpreterState *head;
+        PyInterpreterState *main;
+        /* _next_interp_id is an auto-numbered sequence of small
+           integers.  It gets initialized in _PyInterpreterState_Init(),
+           which is called in Py_Initialize(), and used in
+           PyInterpreterState_New().  A negative interpreter ID
+           indicates an error occurred.  The main interpreter will
+           always have an ID of 0.  Overflow results in a RuntimeError.
+           If that becomes a problem later then we can adjust, e.g. by
+           using a Python int. */
+        int64_t next_id;
+    } interpreters;
+
+#define NEXITFUNCS 32
+    void (*exitfuncs[NEXITFUNCS])(void);
+    int nexitfuncs;
+    void (*pyexitfunc)(void);
+
+    struct _pyobj_runtime_state obj;
+    struct _gc_runtime_state gc;
+    struct _pymem_runtime_state mem;
+    struct _warnings_runtime_state warnings;
+    struct _ceval_runtime_state ceval;
+    struct _gilstate_runtime_state gilstate;
+
+    // XXX Consolidate globals found via the check-c-globals script.
+} _PyRuntimeState;
+
+PyAPI_DATA(_PyRuntimeState) _PyRuntime;
+PyAPI_FUNC(void) _PyRuntimeState_Init(_PyRuntimeState *);
+PyAPI_FUNC(void) _PyRuntimeState_Fini(_PyRuntimeState *);
+
+#define _Py_CURRENTLY_FINALIZING(tstate) \
+    (_PyRuntime.finalizing == tstate)
+
+
+/* Other */
+
+PyAPI_FUNC(void) _PyInterpreterState_Enable(_PyRuntimeState *);
+
+#ifdef __cplusplus
+}
+#endif
+#endif /* !Py_INTERNAL_PYSTATE_H */
diff --git a/Include/internal/warnings.h b/Include/internal/warnings.h
new file mode 100644
index 0000000000..2878a28a2e
--- /dev/null
+++ b/Include/internal/warnings.h
@@ -0,0 +1,21 @@
+#ifndef Py_INTERNAL_WARNINGS_H
+#define Py_INTERNAL_WARNINGS_H
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+#include "object.h"
+
+struct _warnings_runtime_state {
+    /* Both 'filters' and 'onceregistry' can be set in warnings.py;
+       get_warnings_attr() will reset these variables accordingly. */
+    PyObject *filters;  /* List */
+    PyObject *once_registry;  /* Dict */
+    PyObject *default_action; /* String */
+    long filters_version;
+};
+
+#ifdef __cplusplus
+}
+#endif
+#endif /* !Py_INTERNAL_WARNINGS_H */