Defend against stack overrun in a few more places.

tglsfdc · tglsfdc · commit f5157a9acc9d · 2022-08-24T13:01:40.000-04:00
SplitToVariants() in the ispell code, lseg_inside_poly() in geo_ops.c, and regex_selectivity_sub() in selectivity estimation could recurse until stack overflow; fix by adding check_stack_depth() calls. So could next() in the regex compiler, but that case is better fixed by converting its tail recursion to a loop. (We probably get better code that way too, since next() can now be inlined into its sole caller.) There remains a reachable stack overrun in the Turkish stemmer, but we'll need some advice from the Snowball people about how to fix that. Per report from Egor Chindyaskin and Alexander Lakhin. These mistakes are old, so back-patch to all supported branches. Richard Guo and Tom Lane Discussion: https://postgr.es/m/1661334672.728714027@f473.i.mail.ru
diff --git a/src/backend/regex/regc_lex.c b/src/backend/regex/regc_lex.c
@@ -278,6 +278,8 @@ next(struct vars *v)
 {
 	chr			c;
 
+next_restart:					/* loop here after eating a comment */
+
 	/* errors yield an infinite sequence of failures */
 	if (ISERR())
 		return 0;				/* the error has set nexttype to EOS */
@@ -595,8 +597,7 @@ next(struct vars *v)
 						if (!ATEOS())
 							v->now++;
 						assert(v->nexttype == v->lasttype);
-						return next(v);
-						break;
+						goto next_restart;
 					case CHR('='):	/* positive lookahead */
 						NOTE(REG_ULOOKAROUND);
 						RETV(LACON, LATYPE_AHEAD_POS);
diff --git a/src/backend/tsearch/spell.c b/src/backend/tsearch/spell.c
@@ -63,6 +63,7 @@
 #include "postgres.h"
 
 #include "catalog/pg_collation.h"
+#include "miscadmin.h"
 #include "tsearch/dicts/spell.h"
 #include "tsearch/ts_locale.h"
 #include "utils/memutils.h"
@@ -2394,6 +2395,9 @@ SplitToVariants(IspellDict *Conf, SPNode *snode, SplitVar *orig, char *word, int
 	char	   *notprobed;
 	int			compoundflag = 0;
 
+	/* since this function recurses, it could be driven to stack overflow */
+	check_stack_depth();
+
 	notprobed = (char *) palloc(wordlen);
 	memset(notprobed, 1, wordlen);
 	var = CopyVar(orig, 1);
diff --git a/src/backend/utils/adt/geo_ops.c b/src/backend/utils/adt/geo_ops.c
@@ -3862,6 +3862,9 @@ lseg_inside_poly(Point *a, Point *b, POLYGON *poly, int start)
 	bool		res = true,
 				intersection = false;
 
+	/* since this function recurses, it could be driven to stack overflow */
+	check_stack_depth();
+
 	t.p[0] = *a;
 	t.p[1] = *b;
 	s.p[0] = poly->p[(start == 0) ? (poly->npts - 1) : (start - 1)];
diff --git a/src/backend/utils/adt/selfuncs.c b/src/backend/utils/adt/selfuncs.c
@@ -6022,6 +6022,9 @@ regex_selectivity_sub(const char *patt, int pattlen, bool case_insensitive)
 	int			paren_pos = 0;	/* dummy init to keep compiler quiet */
 	int			pos;
 
+	/* since this function recurses, it could be driven to stack overflow */
+	check_stack_depth();
+
 	for (pos = 0; pos < pattlen; pos++)
 	{
 		if (patt[pos] == '(')

Original file line number	Diff line number	Diff line change
`@@ -6022,6 +6022,9 @@ regex_selectivity_sub(const char *patt, int pattlen, bool case_insensitive)`
`6022`	`6022`	`int paren_pos = 0; /* dummy init to keep compiler quiet */`
`6023`	`6023`	`int pos;`
`6024`	`6024`
	`6025`	`+ /* since this function recurses, it could be driven to stack overflow */`
	`6026`	`+ check_stack_depth();`
	`6027`	`+`
`6025`	`6028`	`for (pos = 0; pos < pattlen; pos++)`
`6026`	`6029`	`{`
`6027`	`6030`	`if (patt[pos] == '(')`