Merge branch 'PHP-8.4' into PHP-8.5

* PHP-8.4:
  Forbid \C in UTF-8 patterns (#21139)

Author: arnaud-lb

NEWS

@@ -22,6 +22,10 @@ PHP                                                                        NEWS
   . Fixed bug GH-22779 (mb_strrpos() returns the wrong position for a negative
     offset in a non-UTF-8 encoding). (Eyüp Can Akman)
 
+- PCRE:
+  . Fixed bug GH-21134 (Crash with \C + UTF-8). Using \C in UTF-8 patterns is
+    now forbidden. (Arnaud)
+
 - Sockets:
   . Fixed socket_set_option() validation error messages for UDP_SEGMENT and
     SO_LINGER options. (Weilin Du)

ext/pcre/php_pcre.c

@@ -725,6 +725,8 @@ PHPAPI pcre_cache_entry* pcre_get_compiled_regex_cache_ex(zend_string *regex, bo
 #ifdef PCRE2_UCP
 						coptions |= PCRE2_UCP;
 #endif
+						/* The \C escape sequence is unsafe in PCRE2_UTF mode */
+						coptions |= PCRE2_NEVER_BACKSLASH_C;
 				break;
 			case 'J':	coptions |= PCRE2_DUPNAMES;		break;
 
@@ -778,8 +780,13 @@ PHPAPI pcre_cache_entry* pcre_get_compiled_regex_cache_ex(zend_string *regex, bo
 		if (key != regex) {
 			zend_string_release_ex(key, 0);
 		}
-		pcre2_get_error_message(errnumber, error, sizeof(error));
-		php_error_docref(NULL,E_WARNING, "Compilation failed: %s at offset %zu", error, erroffset);
+		const char *err_msg = (const char*) error;
+		if (errnumber == PCRE2_ERROR_BACKSLASH_C_CALLER_DISABLED) {
+			err_msg = "using \\C is incompatible with the 'u' modifier";
+		} else {
+			pcre2_get_error_message(errnumber, error, sizeof(error));
+		}
+		php_error_docref(NULL,E_WARNING, "Compilation failed: %s at offset %zu", err_msg, erroffset);
 		pcre_handle_exec_error(PCRE2_ERROR_INTERNAL);
 		efree(pattern);
 		return NULL;

ext/pcre/tests/gh21134.phpt

@@ -0,0 +1,15 @@
+--TEST--
+GH-21134: ASan negative-size-param in preg_match_all() with \C + UTF-8 multibyte input
+--CREDITS--
+vi3tL0u1s
+--FILE--
+<?php
+
+$r = preg_match_all("/(.*)\\C/u", "à", $m);
+var_dump($r, $m);
+
+?>
+--EXPECTF--
+Warning: preg_match_all(): Compilation failed: using \C is incompatible with the 'u' modifier at offset 6 in %s on line %d
+bool(false)
+NULL