From 51d0d098b82276657fcc4e8d80c87ba3cf514f98 Mon Sep 17 00:00:00 2001 From: Tom Lane Date: Mon, 17 Aug 2026 13:37:33 -0400 Subject: [PATCH v2] Make plperl's handling of Perl arrays safer and more consistent. plperl_func_handler()'s stanza for handling an arrayref result in a SETOF function could loop forever (or at least till OOM) when given a tied array, since av_fetch won't necessarily ever return a null pointer in that case. Be consistent with the other places where we traverse a perl array: call av_len() once and use len+1 as the loop limit, silently ignoring any null pointers we get back from that range of subscripts. But actually, Perl's preferred locution for this seems to be to use av_count() not av_len()+1. av_count() seems better since there's less risk of forgetting to add 1. Also, both of those functions return Size_t (or SSize_t) not int, creating at least a theoretical overflow hazard. While we're modernizing this, let's use the correct variable type where we can, and include an overflow check where we can't. Reported-by: Claude Code (via Noah Misch) Author: Tom Lane Discussion: https://postgr.es/m/569769.1786901901@sss.pgh.pa.us Backpatch-through: 14 --- contrib/jsonb_plperl/jsonb_plperl.c | 5 ++-- src/pl/plperl/plperl.c | 41 ++++++++++++++++++++++------- 2 files changed, 33 insertions(+), 13 deletions(-) diff --git a/contrib/jsonb_plperl/jsonb_plperl.c b/contrib/jsonb_plperl/jsonb_plperl.c index 97d147cc65a..00a99d303c6 100644 --- a/contrib/jsonb_plperl/jsonb_plperl.c +++ b/contrib/jsonb_plperl/jsonb_plperl.c @@ -135,12 +135,11 @@ static void AV_to_JsonbValue(AV *in, JsonbInState *jsonb_state) { dTHX; - SSize_t pcount = av_len(in) + 1; - SSize_t i; + Size_t pcount = av_count(in); pushJsonbValue(jsonb_state, WJB_BEGIN_ARRAY, NULL); - for (i = 0; i < pcount; i++) + for (Size_t i = 0; i < pcount; i++) { SV **value = av_fetch(in, i, FALSE); diff --git a/src/pl/plperl/plperl.c b/src/pl/plperl/plperl.c index eba91f2d7d6..8175407849e 100644 --- a/src/pl/plperl/plperl.c +++ b/src/pl/plperl/plperl.c @@ -279,6 +279,7 @@ static void array_to_datum_internal(AV *av, ArrayBuildState **astatep, int *ndims, int *dims, int cur_depth, Oid elemtypid, int32 typmod, FmgrInfo *finfo, Oid typioparam); +static int av_count_limit(AV *av); static Datum plperl_hash_to_datum(SV *src, TupleDesc td); static void plperl_init_shared_libs(pTHX); @@ -1173,8 +1174,8 @@ get_perl_array_ref(SV *sv) * is frozen). * * Caller is required to have set dims[cur_depth - 1] to the length of the - * input array, i.e., av_len(av) + 1. We make this requirement so as to - * avoid reading av_len() twice, which is hazardous for tied arrays. + * input array, i.e., av_count_limit(av). We make this requirement so as to + * avoid reading av_count() twice, which is hazardous for tied arrays. */ static void array_to_datum_internal(AV *av, ArrayBuildState **astatep, @@ -1214,11 +1215,11 @@ array_to_datum_internal(AV *av, ArrayBuildState **astatep, errmsg("number of array dimensions exceeds the maximum allowed (%d)", MAXDIM))); /* OK, add a dimension */ - dims[*ndims] = av_len(nav) + 1; + dims[*ndims] = av_count_limit(nav); (*ndims)++; } else if (cur_depth >= *ndims || - av_len(nav) + 1 != dims[cur_depth]) + av_count_limit(nav) != dims[cur_depth]) ereport(ERROR, (errcode(ERRCODE_INVALID_TEXT_REPRESENTATION), errmsg("multidimensional arrays must have array expressions with matching dimensions"))); @@ -1260,6 +1261,25 @@ array_to_datum_internal(AV *av, ArrayBuildState **astatep, } } +/* + * av_count returns Size_t, so at least in theory it could overrun INT_MAX. + * As long as we have to check, let's throw error for anything above + * MaxArraySize, which will surely fail later. + */ +static int +av_count_limit(AV *av) +{ + dTHX; + Size_t cnt = av_count(av); + + if (cnt > MaxArraySize) + ereport(ERROR, + (errcode(ERRCODE_PROGRAM_LIMIT_EXCEEDED), + errmsg("array size exceeds the maximum allowed (%zu)", + MaxArraySize))); + return (int) cnt; +} + /* * convert perl array ref to a datum */ @@ -1287,7 +1307,7 @@ plperl_array_to_datum(SV *src, Oid typid, int32 typmod) _sv_to_datum_finfo(elemtypid, &finfo, &typioparam); memset(dims, 0, sizeof(dims)); - dims[0] = av_len(nav) + 1; + dims[0] = av_count_limit(nav); array_to_datum_internal(nav, &astate, &ndims, dims, 1, @@ -2478,14 +2498,15 @@ plperl_func_handler(PG_FUNCTION_ARGS) if (sav) { dTHX; - int i = 0; - SV **svp = 0; AV *rav = (AV *) SvRV(sav); + Size_t alen = av_count(rav); - while ((svp = av_fetch(rav, i, FALSE)) != NULL) + for (Size_t i = 0; i < alen; i++) { - plperl_return_next_internal(*svp); - i++; + SV **svp = av_fetch(rav, i, FALSE); + + if (svp) + plperl_return_next_internal(*svp); } } else if (SvOK(perlret)) -- 2.52.0