Add unserializehash fuzzer.

Unlike the straight unserialize fuzzer, this runs only on HashContexts,
and it does an update and finalize on the contexts it creates.

Co-authored-by: Nikita Popov <nikic@php.net>

5 files changed, 127 insertions, 0 deletions

diff --git a/sapi/fuzzer/Makefile.frag b/sapi/fuzzer/Makefile.frag
index 57952a8ff4..75a387d3d4 100644
--- a/sapi/fuzzer/Makefile.frag
+++ b/sapi/fuzzer/Makefile.frag
@@ -8,6 +8,9 @@ $(SAPI_FUZZER_PATH)/php-fuzz-parser: $(PHP_GLOBAL_OBJS) $(PHP_SAPI_OBJS) $(PHP_F
 $(SAPI_FUZZER_PATH)/php-fuzz-unserialize: $(PHP_GLOBAL_OBJS) $(PHP_SAPI_OBJS) $(PHP_FUZZER_UNSERIALIZE_OBJS)
 	$(FUZZER_BUILD) $(PHP_FUZZER_UNSERIALIZE_OBJS) -o $@
 
+$(SAPI_FUZZER_PATH)/php-fuzz-unserializehash: $(PHP_GLOBAL_OBJS) $(PHP_SAPI_OBJS) $(PHP_FUZZER_UNSERIALIZEHASH_OBJS)
+	$(FUZZER_BUILD) $(PHP_FUZZER_UNSERIALIZEHASH_OBJS) -o $@
+
 $(SAPI_FUZZER_PATH)/php-fuzz-json: $(PHP_GLOBAL_OBJS) $(PHP_SAPI_OBJS) $(PHP_FUZZER_JSON_OBJS)
 	$(FUZZER_BUILD) $(PHP_FUZZER_JSON_OBJS) -o $@
 
diff --git a/sapi/fuzzer/README.md b/sapi/fuzzer/README.md
index 0645a04bc7..710a10f053 100644
--- a/sapi/fuzzer/README.md
+++ b/sapi/fuzzer/README.md
@@ -22,6 +22,7 @@ When running `make` it creates these binaries in `sapi/fuzzer/`:
 
 * `php-fuzz-parser`: Fuzzing language parser and compiler
 * `php-fuzz-unserialize`: Fuzzing unserialize() function
+* `php-fuzz-unserializehash`: Fuzzing unserialize() for HashContext objects
 * `php-fuzz-json`: Fuzzing JSON parser (requires --enable-json)
 * `php-fuzz-exif`: Fuzzing `exif_read_data()` function (requires --enable-exif)
 * `php-fuzz-mbstring`: fuzzing `mb_ereg[i]()` (requires --enable-mbstring)
@@ -41,6 +42,14 @@ cp -r sapi/fuzzer/corpus/unserialize ./my-unserialize-corpus
 sapi/fuzzer/php-fuzz-unserialize -dict=$PWD/sapi/fuzzer/dict/unserialize ./my-unserialize-corpus
 ```
 
+For the unserializehash fuzzer, generate a corpus of initial hash serializations:
+
+```sh
+sapi/cli/php sapi/fuzzer/generate_unserializehash_corpus.php
+cp -r sapi/fuzzer/corpus/unserializehash ./my-unserialize-corpus
+sapi/fuzzer/php-fuzz-unserializehash ./my-unserialize-corpus
+```
+
 For the parser fuzzer, a corpus may be generated from Zend test files:
 
 ```sh
diff --git a/sapi/fuzzer/config.m4 b/sapi/fuzzer/config.m4
index 8e15a274ec..a148985df9 100644
--- a/sapi/fuzzer/config.m4
+++ b/sapi/fuzzer/config.m4
@@ -76,6 +76,7 @@ if test "$PHP_FUZZER" != "no"; then
 
   PHP_FUZZER_TARGET([parser], PHP_FUZZER_PARSER_OBJS)
   PHP_FUZZER_TARGET([unserialize], PHP_FUZZER_UNSERIALIZE_OBJS)
+  PHP_FUZZER_TARGET([unserializehash], PHP_FUZZER_UNSERIALIZEHASH_OBJS)
   PHP_FUZZER_TARGET([json], PHP_FUZZER_JSON_OBJS)
 
   if test -n "$enable_exif" && test "$enable_exif" != "no"; then
diff --git a/sapi/fuzzer/fuzzer-unserializehash.c b/sapi/fuzzer/fuzzer-unserializehash.c
new file mode 100644
index 0000000000..9fbc10e6a8
--- /dev/null
+++ b/sapi/fuzzer/fuzzer-unserializehash.c
@@ -0,0 +1,104 @@
+/*
+   +----------------------------------------------------------------------+
+   | Copyright (c) The PHP Group                                          |
+   +----------------------------------------------------------------------+
+   | This source file is subject to version 3.01 of the PHP license,      |
+   | that is bundled with this package in the file LICENSE, and is        |
+   | available through the world-wide-web at the following url:           |
+   | http://www.php.net/license/3_01.txt                                  |
+   | If you did not receive a copy of the PHP license and are unable to   |
+   | obtain it through the world-wide-web, please send a note to          |
+   | license@php.net so we can mail you a copy immediately.               |
+   +----------------------------------------------------------------------+
+ */
+
+
+#include "fuzzer.h"
+
+#include "Zend/zend.h"
+#include "main/php_config.h"
+#include "main/php_main.h"
+
+#include <stdio.h>
+#include <stdint.h>
+#include <stdlib.h>
+
+#include "fuzzer-sapi.h"
+
+#include "ext/standard/php_var.h"
+
+int LLVMFuzzerTestOneInput(const uint8_t *Data, size_t FullSize) {
+	zend_execute_data execute_data;
+	zend_function func;
+	const uint8_t *Start = memchr(Data, '|', FullSize);
+	if (!Start) {
+		return 0;
+	}
+	++Start;
+
+	size_t Size = (Data + FullSize) - Start;
+	unsigned char *orig_data = malloc(Size+1);
+	memcpy(orig_data, Start, Size);
+	orig_data[Size] = '\0';
+
+	if (fuzzer_request_startup()==FAILURE) {
+		return 0;
+	}
+
+	/* Set up a dummy stack frame so that exceptions may be thrown. */
+	{
+		memset(&execute_data, 0, sizeof(zend_execute_data));
+		memset(&func, 0, sizeof(zend_function));
+
+		func.type = ZEND_INTERNAL_FUNCTION;
+		func.common.function_name = ZSTR_EMPTY_ALLOC();
+		execute_data.func = &func;
+		EG(current_execute_data) = &execute_data;
+	}
+
+	{
+		const unsigned char *data = orig_data;
+		zval result;
+		ZVAL_UNDEF(&result);
+
+		php_unserialize_data_t var_hash;
+		PHP_VAR_UNSERIALIZE_INIT(var_hash);
+		php_var_unserialize(&result, (const unsigned char **) &data, data + Size, &var_hash);
+		PHP_VAR_UNSERIALIZE_DESTROY(var_hash);
+
+		if (Z_TYPE(result) == IS_OBJECT
+			&& zend_string_equals_literal(Z_OBJCE(result)->name, "HashContext")) {
+			zval args[2];
+			ZVAL_COPY_VALUE(&args[0], &result);
+			ZVAL_STRINGL(&args[1], (char *) Data, (Start - Data) - 1);
+			fuzzer_call_php_func_zval("hash_update", 2, args);
+			zval_ptr_dtor(&args[1]);
+			fuzzer_call_php_func_zval("hash_final", 1, args);
+		}
+
+		zval_ptr_dtor(&result);
+
+		/* Destroy any thrown exception. */
+		if (EG(exception)) {
+			zend_object_release(EG(exception));
+			EG(exception) = NULL;
+		}
+	}
+
+	/* Unserialize may create circular structure. Make sure we free them.
+	 * Two calls are performed to handle objects with destructors. */
+	zend_gc_collect_cycles();
+	zend_gc_collect_cycles();
+	php_request_shutdown(NULL);
+
+	free(orig_data);
+
+	return 0;
+}
+
+int LLVMFuzzerInitialize(int *argc, char ***argv) {
+	fuzzer_init_php();
+
+	/* fuzzer_shutdown_php(); */
+	return 0;
+}
diff --git a/sapi/fuzzer/generate_unserializehash_corpus.php b/sapi/fuzzer/generate_unserializehash_corpus.php
new file mode 100644
index 0000000000..04c6ea1428
--- /dev/null
+++ b/sapi/fuzzer/generate_unserializehash_corpus.php
@@ -0,0 +1,10 @@
+<?php
+
+$corpusDir = __DIR__ . '/corpus/unserializehash';
+@mkdir($corpusDir);
+
+foreach (hash_algos() as $algo) {
+    $ctx = hash_init($algo);
+    $algx = preg_replace('/[^-_a-zA-Z0-9]/', '_', $algo);
+    file_put_contents($corpusDir . '/' . $algx, "x|" . serialize($ctx));
+}