Since 30b3e9d2 (libselinux: Workaround for heap overhead of pcre,
2023-01-12), performance of PCRE2 matches has been affected due to
excesive recreation of the match_data in an attempt to reduce memory
utilization, but instead of a workaround, it would be better to
address the problem and maybe even improve performance in the process.
The issue is that currently the structure that holds PCRE state has
both a pcre2_code (which is per pattern) and a pcre2_match_data (which
is per match), forcing us to add a mutex to prevent multiple matches to
step on each other.
Lets remove the match_data and the mutex and instead allocate one once
in a thread independent way that could be used and reused, by extending
our pthread inteface to not only store TLS variables but also retrieve
them, and use one of those.
Since we are not interested on the capture groups (if any) lets only
allocate 1 pair which is all that will be needed and change the logic
so that a return of 0 (which means the pattern matched but there were
not enough fields) is also considered a match.
This will ensure that the memory use would be bound to the number of
concurrent matches instead of the number of patterns and therefore
reduce the impact that recent changes on the way the frames used for
matching are allocated might had brough since 10.41 was released.
Signed-off-by: Carlo Marcelo Arenas Belón <carenas@xxxxxxxxx>
---
Sent as an RFC since it has been very lightly tested (I can't even
build the whole project), and because I couldn't figure out where to
destroy the key, so it is adding a once on a lifetime leak of a pointer.
It is also more verbose than it needs, because I am combining it with
the revert of the workaround, and that could be split away, but that
would hopefully help with testing as well.
libselinux/src/regex.c | 77 ++++++++++++-------------------
libselinux/src/selinux_internal.h | 4 ++
2 files changed, 34 insertions(+), 47 deletions(-)
diff --git a/libselinux/src/regex.c b/libselinux/src/regex.c
index 16df6790..201a6695 100644
--- a/libselinux/src/regex.c
+++ b/libselinux/src/regex.c
@@ -30,6 +30,10 @@
#endif
#ifdef USE_PCRE2
+static pthread_key_t match_data_key;
+static int match_data_key_uninitialized = 1;
+static __thread char match_data_initialized;
+
char const *regex_arch_string(void)
{
static char arch_string_buffer[32];
@@ -60,14 +64,6 @@ char const *regex_arch_string(void)
struct regex_data {
pcre2_code *regex; /* compiled regular expression */
-#ifndef AGGRESSIVE_FREE_AFTER_REGEX_MATCH
- /*
- * match data block required for the compiled
- * pattern in pcre2
- */
- pcre2_match_data *match_data;
-#endif
- pthread_mutex_t match_mutex;
};
int regex_prepare_data(struct regex_data **regex, char const *pattern_string,
@@ -86,13 +82,6 @@ int regex_prepare_data(struct regex_data **regex, char const *pattern_string,
goto err;
}
-#ifndef AGGRESSIVE_FREE_AFTER_REGEX_MATCH
- (*regex)->match_data =
- pcre2_match_data_create_from_pattern((*regex)->regex, NULL);
- if (!(*regex)->match_data) {
- goto err;
- }
-#endif
return 0;
err:
@@ -142,13 +131,6 @@ int regex_load_mmap(struct mmap_area *mmap_area, struct regex_data **regex,
if (rc != 1)
goto err;
-#ifndef AGGRESSIVE_FREE_AFTER_REGEX_MATCH
- (*regex)->match_data =
- pcre2_match_data_create_from_pattern((*regex)->regex, NULL);
- if (!(*regex)->match_data)
- goto err;
-#endif
-
*regex_compiled = true;
}
@@ -204,18 +186,16 @@ out:
return rc;
}
+static void match_data_thread_free(void *match_data)
+{
+ pcre2_match_data_free(match_data);
+}
+
void regex_data_free(struct regex_data *regex)
{
if (regex) {
if (regex->regex)
pcre2_code_free(regex->regex);
-
-#ifndef AGGRESSIVE_FREE_AFTER_REGEX_MATCH
- if (regex->match_data)
- pcre2_match_data_free(regex->match_data);
-#endif
-
- __pthread_mutex_destroy(®ex->match_mutex);
free(regex);
}
}
@@ -223,32 +203,30 @@ void regex_data_free(struct regex_data *regex)
int regex_match(struct regex_data *regex, char const *subject, int partial)
{
int rc;
+ bool slow;
pcre2_match_data *match_data;
- __pthread_mutex_lock(®ex->match_mutex);
-#ifdef AGGRESSIVE_FREE_AFTER_REGEX_MATCH
- match_data = pcre2_match_data_create_from_pattern(
- regex->regex, NULL);
- if (match_data == NULL) {
- __pthread_mutex_unlock(®ex->match_mutex);
- return REGEX_ERROR;
+ if (match_data_initialized == 0) {
+ match_data = pcre2_match_data_create(1, NULL);
+ match_data_initialized = 1;
+ __selinux_setspecific(match_data_key, match_data);
+ } else
+ match_data = __selinux_getspecific(match_data_key);
+
+ slow = (match_data == NULL);
+ if (slow) {
+ match_data = pcre2_match_data_create_from_pattern(regex->regex,
+ NULL);
}
-#else
- match_data = regex->match_data;
-#endif
rc = pcre2_match(
regex->regex, (PCRE2_SPTR)subject, PCRE2_ZERO_TERMINATED, 0,
partial ? PCRE2_PARTIAL_SOFT : 0, match_data, NULL);
-#ifdef AGGRESSIVE_FREE_AFTER_REGEX_MATCH
- // pcre2_match allocates heap and it won't be freed until
- // pcre2_match_data_free, resulting in heap overhead.
- pcre2_match_data_free(match_data);
-#endif
+ if (slow)
+ pcre2_match_data_free(match_data);
- __pthread_mutex_unlock(®ex->match_mutex);
- if (rc > 0)
+ if (rc >= 0)
return REGEX_MATCH;
switch (rc) {
case PCRE2_ERROR_PARTIAL:
@@ -290,7 +268,12 @@ struct regex_data *regex_data_create(void)
if (!regex_data)
return NULL;
- __pthread_mutex_init(®ex_data->match_mutex, NULL);
+ if (match_data_key_uninitialized) {
+ match_data_key_uninitialized = __selinux_key_create(
+ &match_data_key,
+ match_data_thread_free);
+ }
+
return regex_data;
}
diff --git a/libselinux/src/selinux_internal.h b/libselinux/src/selinux_internal.h
index 06f2c038..d1e6c50f 100644
--- a/libselinux/src/selinux_internal.h
+++ b/libselinux/src/selinux_internal.h
@@ -13,6 +13,7 @@ extern int selinux_page_size ;
#pragma weak pthread_key_create
#pragma weak pthread_key_delete
#pragma weak pthread_setspecific
+#pragma weak pthread_getspecific
/* Call handler iff the first call. */
#define __selinux_once(ONCE_CONTROL, INIT_FUNCTION) \
@@ -41,6 +42,9 @@ extern int selinux_page_size ;
pthread_setspecific(KEY, VALUE); \
} while (0)
+#define __selinux_getspecific(KEY) \
+ (pthread_getspecific != NULL ? pthread_getspecific(KEY) : NULL)
+
/* selabel_lookup() is only thread safe if we're compiled with pthreads */
#pragma weak pthread_mutex_init
--
2.30.2
