Allow regex operations to be terminated early by query cancel requests.

The regex code didn't have any provision for query cancel; which is
unsurprising given its non-Postgres origin, but still problematic since
some operations can take a long time.  Introduce a callback function to
check for a pending query cancel or session termination request, and
call it in a couple of strategic spots where we can make the regex code
exit with an error indicator.

If we ever actually split out the regex code as a standalone library,
some additional work will be needed to let the cancel callback function
be specified externally to the library.  But that's straightforward
(certainly so by comparison to putting the locale-dependent character
classification logic on a similar arms-length basis), and there seems
no need to do it right now.

A bigger issue is that there may be more places than these two where
we need to check for cancels.  We can always add more checks later,
now that the infrastructure is in place.

Since there are known examples of not-terribly-long regexes that can
lock up a backend for a long time, back-patch to all supported branches.
I have hopes of fixing the known performance problems later, but adding
query cancel ability seems like a good idea even if they were all fixed.

diff --git a/src/backend/regex/regc_nfa.c b/src/backend/regex/regc_nfa.c
index 05fe8b0808c21a2946a3cef8d896ec74cd298ba6..170da5954c7e11a5bcad65110ac4239dafa072db 100644 (file)
--- a/src/backend/regex/regc_nfa.c
+++ b/src/backend/regex/regc_nfa.c
@@ -174,11 +174,23 @@ newstate(struct nfa * nfa)
 {
        struct state *s;
 
+       /*
+        * This is a handy place to check for operation cancel during regex
+        * compilation, since no code path will go very long without making a new
+        * state.
+        */
+       if (CANCEL_REQUESTED(nfa->v->re))
+       {
+               NERR(REG_CANCEL);
+               return NULL;
+       }
+
        if (TooManyStates(nfa))
        {
                NERR(REG_ETOOBIG);
                return NULL;
        }
+
        if (nfa->free != NULL)
        {
                s = nfa->free;

diff --git a/src/backend/regex/regcomp.c b/src/backend/regex/regcomp.c
index 9d92f9888bb547b3c593c1845fe046bb545969bc..2ddcdff09a4058a9949c920ea3a14fc1263edbc1 100644 (file)
--- a/src/backend/regex/regcomp.c
+++ b/src/backend/regex/regcomp.c
@@ -34,6 +34,8 @@
 
 #include "regex/regguts.h"
 
+#include "miscadmin.h"                 /* needed by rcancelrequested() */
+
 /*
  * forward declarations, up here so forward datatypes etc. are defined early
  */
@@ -67,6 +69,7 @@ static long nfanode(struct vars *, struct subre *, FILE *);
 static int     newlacon(struct vars *, struct state *, struct state *, int);
 static void freelacons(struct subre *, int);
 static void rfree(regex_t *);
+static int     rcancelrequested(void);
 
 #ifdef REG_DEBUG
 static void dump(regex_t *, FILE *);
@@ -276,6 +279,7 @@ struct vars
 /* static function list */
 static struct fns functions = {
        rfree,                                          /* regfree insides */
+       rcancelrequested                        /* check for cancel request */
 };
 
 
@@ -1876,6 +1880,22 @@ rfree(regex_t *re)
        }
 }
 
+/*
+ * rcancelrequested - check for external request to cancel regex operation
+ *
+ * Return nonzero to fail the operation with error code REG_CANCEL,
+ * zero to keep going
+ *
+ * The current implementation is Postgres-specific.  If we ever get around
+ * to splitting the regex code out as a standalone library, there will need
+ * to be some API to let applications define a callback function for this.
+ */
+static int
+rcancelrequested(void)
+{
+       return InterruptPending && (QueryCancelPending || ProcDiePending);
+}
+
 #ifdef REG_DEBUG
 
 /*

diff --git a/src/backend/regex/regexec.c b/src/backend/regex/regexec.c
index abcb5e7439f35f88a81c55ade68325b43034d408..7cd6679ededa06dcd0fbe7fd34287dd776ca04ac 100644 (file)
--- a/src/backend/regex/regexec.c
+++ b/src/backend/regex/regexec.c
@@ -713,6 +713,10 @@ cdissect(struct vars * v,
        assert(t != NULL);
        MDEBUG(("cdissect %ld-%ld %c\n", LOFF(begin), LOFF(end), t->op));
 
+       /* handy place to check for operation cancel */
+       if (CANCEL_REQUESTED(v->re))
+               return REG_CANCEL;
+
        switch (t->op)
        {
                case '=':                               /* terminal node */

diff --git a/src/backend/utils/adt/regexp.c b/src/backend/utils/adt/regexp.c
index b15b0905b74c2bb562a03ebe8b44ec6fadd3703a..7e05a53810e764cfa3dcfcf59f5f6ce72dfb6eeb 100644 (file)
--- a/src/backend/utils/adt/regexp.c
+++ b/src/backend/utils/adt/regexp.c
@@ -31,6 +31,7 @@
 
 #include "catalog/pg_type.h"
 #include "funcapi.h"
+#include "miscadmin.h"
 #include "regex/regex.h"
 #include "utils/builtins.h"
 #include "utils/guc.h"
@@ -188,6 +189,15 @@ RE_compile_and_cache(text *text_re, int cflags, Oid collation)
        if (regcomp_result != REG_OKAY)
        {
                /* re didn't compile (no need for pg_regfree, if so) */
+
+               /*
+                * Here and in other places in this file, do CHECK_FOR_INTERRUPTS
+                * before reporting a regex error.      This is so that if the regex
+                * library aborts and returns REG_CANCEL, we don't print an error
+                * message that implies the regex was invalid.
+                */
+               CHECK_FOR_INTERRUPTS();
+
                pg_regerror(regcomp_result, &re_temp.cre_re, errMsg, sizeof(errMsg));
                ereport(ERROR,
                                (errcode(ERRCODE_INVALID_REGULAR_EXPRESSION),
@@ -268,6 +278,7 @@ RE_wchar_execute(regex_t *re, pg_wchar *data, int data_len,
        if (regexec_result != REG_OKAY && regexec_result != REG_NOMATCH)
        {
                /* re failed??? */
+               CHECK_FOR_INTERRUPTS();
                pg_regerror(regexec_result, re, errMsg, sizeof(errMsg));
                ereport(ERROR,
                                (errcode(ERRCODE_INVALID_REGULAR_EXPRESSION),
@@ -1216,6 +1227,7 @@ regexp_fixed_prefix(text *text_re, bool case_insensitive, Oid collation,
 
                default:
                        /* re failed??? */
+                       CHECK_FOR_INTERRUPTS();
                        pg_regerror(re_result, re, errMsg, sizeof(errMsg));
                        ereport(ERROR,
                                        (errcode(ERRCODE_INVALID_REGULAR_EXPRESSION),

diff --git a/src/backend/utils/adt/varlena.c b/src/backend/utils/adt/varlena.c
index fe06f1b5527b2fee63b46481d395f67730dc2deb..e9ea62880485e6291bf098ed2b58fdda69895132 100644 (file)
--- a/src/backend/utils/adt/varlena.c
+++ b/src/backend/utils/adt/varlena.c
@@ -2854,6 +2854,7 @@ replace_text_regexp(text *src_text, void *regexp,
                {
                        char            errMsg[100];
 
+                       CHECK_FOR_INTERRUPTS();
                        pg_regerror(regexec_result, re, errMsg, sizeof(errMsg));
                        ereport(ERROR,
                                        (errcode(ERRCODE_INVALID_REGULAR_EXPRESSION),

diff --git a/src/include/regex/regerrs.h b/src/include/regex/regerrs.h
index f02711ee1762604dee60ce2b99a3858dded91ccf..809b511266047a32b403ac05f0f3b22d3437b5dc 100644 (file)
--- a/src/include/regex/regerrs.h
+++ b/src/include/regex/regerrs.h
@@ -81,3 +81,7 @@
 {
        REG_ECOLORS, "REG_ECOLORS", "too many colors"
 },
+
+{
+       REG_CANCEL, "REG_CANCEL", "operation cancelled"
+},

diff --git a/src/include/regex/regex.h b/src/include/regex/regex.h
index 3e87dff17b27f6c622a9e9278a64ea7a2bc8abad..2c7fa4df46f818f1e139f0eae1b50e0a5fe78524 100644 (file)
--- a/src/include/regex/regex.h
+++ b/src/include/regex/regex.h
@@ -154,6 +154,7 @@ typedef struct
 #define REG_BADOPT     18                      /* invalid embedded option */
 #define REG_ETOOBIG 19                 /* nfa has too many states */
 #define REG_ECOLORS 20                 /* too many colors */
+#define REG_CANCEL     21                      /* operation cancelled */
 /* two specials for debugging and testing */
 #define REG_ATOI       101                     /* convert error-code name to number */
 #define REG_ITOA       102                     /* convert error-code number to name */

diff --git a/src/include/regex/regguts.h b/src/include/regex/regguts.h
index 968a04edd999063ecdcaedb629c5f2a37d0874ae..55e1696fe8ccb0603ae0a719700ed803037a4cc1 100644 (file)
--- a/src/include/regex/regguts.h
+++ b/src/include/regex/regguts.h
@@ -403,8 +403,11 @@ struct subre
 struct fns
 {
        void            FUNCPTR(free, (regex_t *));
+       int                     FUNCPTR(cancel_requested, (void));
 };
 
+#define CANCEL_REQUESTED(re)  \
+       ((*((struct fns *) (re)->re_fns)->cancel_requested) ())
 
 
 /*