grep: make PCRE2 aware of custom allocator

94da919 (grep: add support for PCRE v2, 2017-06-01) didn't include
a way to override the system allocator, and so it is incompatible with
USE_NED_ALLOCATOR.  The problem was made visible when an attempt to
avoid a leak in a data structure that is created by the library was
passed to NED's free for disposal triggering a segfault in Windows.

PCRE2 requires the use of a general context to override the allocator
and therefore, there is a lot more code needed than in PCRE1, including
a couple of wrapper functions.

Extend the grep API with a "destructor" that could be called to cleanup
any objects that were created and used globally.

Update builtin/grep to use that new API, but any other future
users should make sure to have matching grep_init/grep_destroy calls
if they are using the pattern matching functionality (currently only
relevant when using both NED and PCRE2)

Move some of the logic that was before done per thread (in the workers)
into an earlier phase to avoid degrading performance, but as the use
of PCRE2 with NED is better understood it is expected more of its
functions will be instructed to use the custom allocator as well as
was done in the original code[1] this work was based on.

[1] https://public-inbox.org/git/3397e6797f872aedd18c6d795f4976e1c579514b.1565005867.git.gitgitgadget@gmail.com/

Reported-by: Johannes Schindelin <[email protected]>
Signed-off-by: Carlo Marcelo Arenas Belón <[email protected]>
Signed-off-by: Junio C Hamano <[email protected]>

Author: carenas

builtin/grep.c

@@ -1145,5 +1145,6 @@ int cmd_grep(int argc, const char **argv, const char *prefix)
 		run_pager(&opt, prefix);
 	clear_pathspec(&pathspec);
 	free_grep_patterns(&opt);
+	grep_destroy();
 	return !hit;
 }

grep.c

@@ -16,6 +16,22 @@ static int grep_source_is_binary(struct grep_source *gs,
 
 static struct grep_opt grep_defaults;
 
+#ifdef USE_LIBPCRE2
+static pcre2_general_context *pcre2_global_context;
+
+#ifdef USE_NED_ALLOCATOR
+static void *pcre2_malloc(PCRE2_SIZE size, MAYBE_UNUSED void *memory_data)
+{
+	return malloc(size);
+}
+
+static void pcre2_free(void *pointer, MAYBE_UNUSED void *memory_data)
+{
+	return free(pointer);
+}
+#endif
+#endif
+
 static const char *color_grep_slots[] = {
 	[GREP_COLOR_CONTEXT]	    = "context",
 	[GREP_COLOR_FILENAME]	    = "filename",
@@ -153,6 +169,7 @@ int grep_config(const char *var, const char *value, void *cb)
  *
  * If using PCRE make sure that the library is configured
  * to use the right allocator (ex: NED)
+ * if any object is created it should be cleaned up in grep_destroy()
  */
 void grep_init(struct grep_opt *opt, struct repository *repo, const char *prefix)
 {
@@ -188,6 +205,13 @@ void grep_init(struct grep_opt *opt, struct repository *repo, const char *prefix
 		color_set(opt->colors[i], def->colors[i]);
 }
 
+void grep_destroy(void)
+{
+#ifdef USE_LIBPCRE2
+	pcre2_general_context_free(pcre2_global_context);
+#endif
+}
+
 static void grep_set_pattern_type_option(enum grep_pattern_type pattern_type, struct grep_opt *opt)
 {
 	/*
@@ -319,6 +343,11 @@ void append_header_grep_pattern(struct grep_opt *opt,
 void append_grep_pattern(struct grep_opt *opt, const char *pat,
 			 const char *origin, int no, enum grep_pat_token t)
 {
+#if defined(USE_LIBPCRE2) && defined(USE_NED_ALLOCATOR)
+	if (!pcre2_global_context && opt->ignore_case && has_non_ascii(pat))
+		pcre2_global_context = pcre2_general_context_create(
+					pcre2_malloc, pcre2_free, NULL);
+#endif
 	append_grep_pat(opt, pat, strlen(pat), origin, no, t);
 }
 
@@ -507,9 +536,14 @@ static void compile_pcre2_pattern(struct grep_pat *p, const struct grep_opt *opt
 
 	p->pcre2_compile_context = NULL;
 
+	/* pcre2_global_context is initialized in append_grep_pattern */
 	if (opt->ignore_case) {
 		if (has_non_ascii(p->pattern)) {
-			character_tables = pcre2_maketables(NULL);
+#ifdef USE_NED_ALLOCATOR
+			if (!pcre2_global_context)
+				BUG("pcre2_global_context uninitialized");
+#endif
+			character_tables = pcre2_maketables(pcre2_global_context);
 			p->pcre2_compile_context = pcre2_compile_context_create(NULL);
 			pcre2_set_character_tables(p->pcre2_compile_context, character_tables);
 		}

grep.h

@@ -189,6 +189,7 @@ struct grep_opt {
 void init_grep_defaults(struct repository *);
 int grep_config(const char *var, const char *value, void *);
 void grep_init(struct grep_opt *, struct repository *repo, const char *prefix);
+void grep_destroy(void);
 void grep_commit_pattern_type(enum grep_pattern_type, struct grep_opt *opt);
 
 void append_grep_pat(struct grep_opt *opt, const char *pat, size_t patlen, const char *origin, int no, enum grep_pat_token t);