php · iluuu1994 · Jan 30, 2024
@@ -0,0 +1,29 @@
+name: Docs
+on:
+  push:
+    branches:
+      - master
+    paths:
+      - docs/*
+  pull_request:
+    paths:
+      - docs/*
+jobs:
+  pages:
+    runs-on: ubuntu-22.04
+    permissions:
+      pages: write
+      id-token: write
+    steps:
+      - name: git checkout
+        uses: actions/checkout@v4
+      - name: Install dependencies
+        run: pip install sphinx-design sphinxawesome-theme rstfmt
+      - name: Check formatting
+        run: rstfmt --check -w 100 docs/source
+      - name: Publish
+        if: github.event_name == 'push'
+        uses: sphinx-notes/pages@v3
+        with:
+          checkout: false
+          documentation_path: docs/source
diff --git a/docs/input-filter.md → docs-old/input-filter.md b/docs/input-filter.md → docs-old/input-filter.md
diff --git a/docs/mailinglist-rules.md → docs-old/mailinglist-rules.md b/docs/mailinglist-rules.md → docs-old/mailinglist-rules.md
diff --git a/docs/output-api.md → docs-old/output-api.md b/docs/output-api.md → docs-old/output-api.md
diff --git a/docs/parameter-parsing-api.md → docs-old/parameter-parsing-api.md b/docs/parameter-parsing-api.md → docs-old/parameter-parsing-api.md
diff --git a/docs/release-process.md → docs-old/release-process.md b/docs/release-process.md → docs-old/release-process.md
diff --git a/docs/self-contained-extensions.md → docs-old/self-contained-extensions.md b/docs/self-contained-extensions.md → docs-old/self-contained-extensions.md
diff --git a/docs/streams.md → docs-old/streams.md b/docs/streams.md → docs-old/streams.md
diff --git a/docs/unix-build-system.md → docs-old/unix-build-system.md b/docs/unix-build-system.md → docs-old/unix-build-system.md
diff --git a/docs/.gitignore b/docs/.gitignore
@@ -0,0 +1 @@
+build/
diff --git a/docs/README.md b/docs/README.md
@@ -0,0 +1,20 @@
+# php-src docs
+
+This is the home of the php-src internal documentation. It is in very early stages, but is intended
+to become the primary place where new information about php-src is documented. Over time, it is
+expected to replace various mediums like:
+
+* https://www.phpinternalsbook.com/
+* https://wiki.php.net/internals
+* Blogs from contributors
+
+## How to build
+
+`python` 3 and `pip` are required.
+
+```bash
+pip install sphinx sphinx-design sphinxawesome-theme
+make html
+```
+
+That's it! You can view the documentation under `./build/html/index.html` in your browser.
diff --git a/docs/make.bat b/docs/make.bat
@@ -0,0 +1,35 @@
+@ECHO OFF
+
+pushd %~dp0
+
+REM Command file for Sphinx documentation
+
+if "%SPHINXBUILD%" == "" (
+	set SPHINXBUILD=sphinx-build
+)
+set SOURCEDIR=source
+set BUILDDIR=build
+
+%SPHINXBUILD% >NUL 2>NUL
+if errorlevel 9009 (
+	echo.
+	echo.The 'sphinx-build' command was not found. Make sure you have Sphinx
+	echo.installed, then set the SPHINXBUILD environment variable to point
+	echo.to the full path of the 'sphinx-build' executable. Alternatively you
+	echo.may add the Sphinx directory to PATH.
+	echo.
+	echo.If you don't have Sphinx installed, grab it from
+	echo.https://www.sphinx-doc.org/
+	exit /b 1
+)
+
+if "%1" == "" goto help
+
+%SPHINXBUILD% -M %1 %SOURCEDIR% %BUILDDIR% %SPHINXOPTS% %O%
+goto end
+
+:help
+%SPHINXBUILD% -M help %SOURCEDIR% %BUILDDIR% %SPHINXOPTS% %O%
+
+:end
+popd
diff --git a/docs/source/_static/.gitkeep b/docs/source/_static/.gitkeep
diff --git a/docs/source/_templates/.gitkeep b/docs/source/_templates/.gitkeep
diff --git a/docs/source/conf.py b/docs/source/conf.py
@@ -0,0 +1,59 @@
+# Configuration file for the Sphinx documentation builder.
+#
+# For the full list of built-in configuration values, see the documentation:
+# https://www.sphinx-doc.org/en/master/usage/configuration.html
+
+from dataclasses import asdict
+from sphinxawesome_theme import ThemeOptions
+from sphinxawesome_theme.postprocess import Icons
+from sphinx.highlighting import lexers
+from pygments.lexers.web import PhpLexer
+
+lexers['php'] = PhpLexer(startinline=True)
+lexers['php-annotations'] = PhpLexer(startinline=True)
+
+project = 'php-src docs'
+author = 'The PHP Group'
+extensions = [
+    'sphinx_design',
+    'sphinxawesome_theme.highlighting',
+]
+templates_path = ['_templates']
+html_theme = 'sphinxawesome_theme'
+html_static_path = ['_static']
+html_title = project
+html_permalinks_icon = Icons.permalinks_icon
+theme_options = ThemeOptions(
+    show_prev_next=True,
+    extra_header_link_icons={
+        'repository on GitHub': {
+            'link': 'https://github.com/php/php-src',
+            'icon': (
+                '<svg height="26px" style="margin-top:-2px;display:inline" '
+                'viewBox="0 0 45 44" '
+                'fill="currentColor" xmlns="http://www.w3.org/2000/svg">'
+                '<path fill-rule="evenodd" clip-rule="evenodd" '
+                'd="M22.477.927C10.485.927.76 10.65.76 22.647c0 9.596 6.223 17.736 '
+                '14.853 20.608 1.087.2 1.483-.47 1.483-1.047 '
+                '0-.516-.019-1.881-.03-3.693-6.04 '
+                '1.312-7.315-2.912-7.315-2.912-.988-2.51-2.412-3.178-2.412-3.178-1.972-1.346.149-1.32.149-1.32 '  # noqa
+                '2.18.154 3.327 2.24 3.327 2.24 1.937 3.318 5.084 2.36 6.321 '
+                '1.803.197-1.403.759-2.36 '
+                '1.379-2.903-4.823-.548-9.894-2.412-9.894-10.734 '
+                '0-2.37.847-4.31 2.236-5.828-.224-.55-.969-2.759.214-5.748 0 0 '
+                '1.822-.584 5.972 2.226 '
+                '1.732-.482 3.59-.722 5.437-.732 1.845.01 3.703.25 5.437.732 '
+                '4.147-2.81 5.967-2.226 '
+                '5.967-2.226 1.185 2.99.44 5.198.217 5.748 1.392 1.517 2.232 3.457 '
+                '2.232 5.828 0 '
+                '8.344-5.078 10.18-9.916 10.717.779.67 1.474 1.996 1.474 4.021 0 '
+                '2.904-.027 5.247-.027 '
+                '5.96 0 .58.392 1.256 1.493 1.044C37.981 40.375 44.2 32.24 44.2 '
+                '22.647c0-11.996-9.726-21.72-21.722-21.72" '
+                'fill="currentColor"/></svg>'
+            ),
+        },
+    },
+)
+html_theme_options = asdict(theme_options)
+pygments_style = 'sphinx'
diff --git a/docs/source/core/data-structures/index.rst b/docs/source/core/data-structures/index.rst
@@ -0,0 +1,12 @@
+#################
+ Data structures
+#################
+
+.. toctree::
+   :hidden:
+
+   zval
+   reference-counting
+   zend_string
+
+This section provides an overview of the core data structures used in php-src.
diff --git a/docs/source/core/data-structures/reference-counting.rst b/docs/source/core/data-structures/reference-counting.rst
@@ -0,0 +1,228 @@
+####################
+ Reference counting
+####################
+
+In languages like C, when you need memory for storing data for an indefinite period of time or in a
+large amount, you call ``malloc`` and ``free`` to acquire and release blocks of memory of some size.
+This sounds simple on the surface but turns out to be quite tricky, mainly because the data may not
+be freed for as long as it is used anywhere in the program. Sometimes this makes it unclear who is
+responsible for freeing the memory, and when to do so. Failure to handle this correctly may result
+in a use-after-free, double-free, or memory leak.
+
+In PHP you usually do not need to think about memory management. The engine takes care of allocating
+and freeing memory for you by tracking which values are no longer needed. It does this by assigning
+a reference count to each allocated value, often abbreviated as refcount or RC. Whenever a reference
+to a value is passed somewhere else, its reference count is increased to indicate the value is now
+used by another party. When the party no longer needs the value, it is responsible for decreasing
+the reference count. Once the reference count reaches zero, we know the value is no longer needed
+anywhere, and that it may be freed.
+
+.. code:: php
+
+   $a = new stdClass; // RC 1
+   $b = $a;           // RC 2
+   unset($a);         // RC 1
+   unset($b);         // RC 0, free
+
+Reference counting is needed for types that store auxiliary data, which are the following:
+
+-  Strings
+-  Arrays
+-  Objects
+-  References
+-  Resources
+
+These are either reference types (objects, references and resources) or they are large types that
+don't fit in a single ``zend_value`` directly (strings, arrays). Simpler types either don't store a
+value at all (``null``, ``false``, ``true``) or their value is small enough to fit directly in
+``zend_value`` (``int``, ``float``).
+
+All of the reference counted types share a common initial struct sequence.
+
+.. code:: c
+
+   typedef struct _zend_refcounted_h {
+       uint32_t refcount; /* reference counter 32-bit */
+       union {
+           uint32_t type_info;
+       } u;
+   } zend_refcounted_h;
+
+    struct _zend_string {
+        zend_refcounted_h gc;
+        // ...
+    };
+
+    struct _zend_array {
+        zend_refcounted_h gc;
+        // ...
+    };
+
+The ``zend_refcounted_h`` struct is simple. It contains the reference count, and a ``type_info``
+field that repeats some of the type information that is also stored in the ``zval``, for situations
+where we're not dealing with a ``zval`` directly. It also stores some additional fields, described
+under `GC flags`_.
+
+********
+ Macros
+********
+
+As with ``zval``, ``zend_refcounted_h`` members should not be accessed directly. Instead, you should
+use the provided macros. There are macros that work with reference counted types directly, prefixed
+with ``GC_``, or macros that work on ``zval`` values, usually prefixed with ``Z_``. Unfortunately,
+naming is not always consistent.
+
+.. list-table:: ``zval`` macros
+   :header-rows: 1
+
+   -  -  Macro
+      -  Non-RC [#non-rc]_
+      -  Description
+
+   -  -  ``Z_REFCOUNT[_P]``
+      -  No
+      -  Returns the reference count.
+
+   -  -  ``Z_ADDREF[_P]``
+      -  No
+      -  Increases the reference count.
+
+   -  -  ``Z_TRY_ADDREF[_P]``
+      -  Yes
+      -  Increases the reference count. May be called on any ``zval``.
+
+   -  -  ``zval_ptr_dtor``
+      -  Yes
+      -  Decreases the reference count and frees the value if the reference count reaches zero.
+
+.. [#non-rc]
+
+   Whether the macro works with non-reference counted types. If it does, the operation is usually a
+   no-op. If it does not, using the macro on these values is undefined behavior.
+
+.. list-table:: ``zend_refcounted_h`` macros
+   :header-rows: 1
+
+   -  -  Macro
+      -  Immutable [#immutable]_
+      -  Description
+
+   -  -  ``GC_REFCOUNT[_P]``
+      -  Yes
+      -  Returns the reference count.
+
+   -  -  ``GC_ADDREF[_P]``
+      -  No
+      -  Increases the reference count.
+
+   -  -  ``GC_TRY_ADDREF[_P]``
+      -  Yes
+      -  Increases the reference count.
+
+   -  -  ``GC_DTOR[_P]``
+      -  Yes
+      -  Decreases the reference count and frees the value if the reference count reaches zero.
+
+.. [#immutable]
+
+   Whether the macro works with immutable types, described under `Immutable reference counted types`_.
+
+************
+ Separation
+************
+
+PHP has value and reference types. Reference types are types that are shared through a reference, a
+"pointer" to the value, rather than the value itself. Modifying such a value in one place changes it
+for all of its observers. For example, writing to a property changes the property in every place the
+object is referenced. Value types, on the other hand, are copied when passed to another party.
+Modifying the original value does not affect the copy, and vice versa.
+
+In PHP, arrays and strings are value types. Since they are also reference counted types, this
+requires some special care when modifying values. In particular, we need to make sure that modifying
+the value is not observable from other places. Modifying a value with RC 1 is unproblematic, since
+we are the values sole owner. However, if the value has a reference count of >1, we need to create a
+fresh copy before modifying it. This process is called separation or CoW (copy on write).
+
+.. code:: php
+
+   $a = [1, 2, 3]; // RC 1
+   $b = $a;        // RC 2
+   $b[] = 4;       // Separation, $a RC 1, $b RC 1
+   var_dump($a);   // [1, 2, 3]
+   var_dump($b);   // [1, 2, 3, 4]
+
+***********************************
+ Immutable reference counted types
+***********************************
+
+Sometimes, even a reference counted type is not reference counted. When PHP runs in a multi-process
+or multi-threaded environment with opcache enabled, it shares some common values between processes
+or threads to reduce memory consumption. As you may know, sharing memory between processes or
+threads can be tricky and requires special care when modifying values. In particular, modification
+usually requires exclusive access to the memory so that the other processes or threads wait until
+the value is done being updated. In this case, this synchronization is avoided by making the value
+immutable and never modifying the reference count. Such values will receive the ``GC_IMMUTABLE``
+flag in their ``gc->u.type_info`` field.
+
+Some macros like ``GC_TRY_ADDREF`` will guard against immutable values. You should not use immutable
+values on some macros, like ``GC_ADDREF``. This will result in undefined behavior, because the macro
+will not check whether the value is immutable before performing the reference count modifications.
+You may execute PHP with the ``-d opcache.protect_memory=1`` flag to mark the shared memory as
+read-only and trigger a hardware exception if the code accidentally attempts to modify it.
+
+*****************
+ Cycle collector
+*****************
+
+Sometimes, reference counting is not enough. Consider the following example:
+
+.. code:: php
+
+   $a = new stdClass;
+   $b = new stdClass;
+   $a->b = $b;
+   $b->a = $a;
+   unset($a);
+   unset($b);
+
+When this code finishes, the reference count of both instances of ``stdClass`` will still be 1, as
+they reference each other. This is called a reference cycle.
+
+PHP implements a cycle collector that detects such cycles and frees values that are only reachable
+through their own references. The cycle collector will record values that may be involved in a
+cycle, and run when this buffer becomes full. It is also possible to invoke it explicitly by calling
+the ``gc_collect_cycles()`` function. The cycle collectors design is described in the `Cycle
+collector <todo>`_ chapter.
+
+**********
+ GC flags
+**********
+
+.. code:: c
+
+   /* zval_gc_flags(zval.value->gc.u.type_info) (common flags) */
+   #define GC_NOT_COLLECTABLE  (1<<4)
+   #define GC_PROTECTED        (1<<5) /* used for recursion detection */
+   #define GC_IMMUTABLE        (1<<6) /* can't be changed in place */
+   #define GC_PERSISTENT       (1<<7) /* allocated using malloc */
+   #define GC_PERSISTENT_LOCAL (1<<8) /* persistent, but thread-local */
+
+The ``GC_NOT_COLLECTABLE`` flag indicates that the value may not be involved in a reference cycle.
+This allows for a fast way to detect values that don't need to be added to the cycle collector
+buffer. Only arrays and objects may actually be involved in reference cycles.
+
+The ``GC_PROTECTED`` flag is used to protect against recursion in various internal functions. For
+example, ``var_dump`` recursively prints the contents of values, and marks visited values with the
+``GC_PROTECTED`` flag. If the value is recursive, it prevents the same value from being visited
+again.
+
+``GC_IMMUTABLE`` has been discussed in `Immutable reference counted types`_.
+
+The ``GC_PERSISTENT`` flag indicates that the value was allocated using ``malloc``, instead of PHPs
+own allocator. Usually, such values are alive for the entire lifetime of the process, instead of
+being freed at the end of the request. See the `Zend allocator <todo>`_ chapter for more
+information.
+
+The ``GC_PERSISTENT_LOCAL`` flag indicates that a ``CG_PERSISTENT`` value is only accessibly in one
+thread, and is thus still safe to modify. This flag is only used in debug builds to satisfy an
+``assert``.