diff options
| author | Szabolcs Nagy <nsz@port70.net> | 2026-03-23 17:33:20 +0000 |
|---|---|---|
| committer | Rich Felker <dalias@aerifal.cx> | 2026-03-30 15:59:35 -0400 |
| commit | 40acb04b2c1291f7d3091c61080109da11eea48b (patch) | |
| tree | 06a95e4fed688e1bc3d1f254a7e2a9c0769f65f0 /src | |
| parent | 0572555dab1d1e10b5f7351a005ec588cab41e25 (diff) | |
| download | musl-40acb04b2c1291f7d3091c61080109da11eea48b.tar.gz | |
regex: reject invalid \digit back reference in BRE
in BRE \n matches the nth subexpression, but regcomp did not check if
the nth subexpression was complete or not, only that there were more
subexpressions overall than the largest backref.
fix regcomp to error if the referenced subexpression is incomplete.
the bug could cause an infinite loop in regexec:
regcomp(&re, "\\(^a*\\1\\)*", 0);
regexec(&re, "aa", 0, 0, 0);
since BRE has backreferences, any application accepting a BRE from
untrusted sources is already vulnerable to an attacker-controlled
near-infinite (exponential-time) loop, but this particular case where
the loop is actually infinite can and should be avoided.
ERE is not affected since the language an ERE describes is actually
regular.
Reported-by: Simon Resch <simon.resch@code-intelligence.com>
Diffstat (limited to 'src')
| -rw-r--r-- | src/regex/regcomp.c | 6 |
1 files changed, 6 insertions, 0 deletions
diff --git a/src/regex/regcomp.c b/src/regex/regcomp.c index fb24556e..b4b81968 100644 --- a/src/regex/regcomp.c +++ b/src/regex/regcomp.c @@ -409,6 +409,8 @@ typedef struct { int position; /* The highest back reference or -1 if none seen so far. */ int max_backref; + /* Bit mask of submatch IDs that can be back referenced. */ + int backref_ok; /* Compilation flags. */ int cflags; } tre_parse_ctx_t; @@ -769,6 +771,8 @@ static reg_errcode_t marksub(tre_parse_ctx_t *ctx, tre_ast_node_t *node, int sub node->submatch_id = subid; node->num_submatches++; ctx->n = node; + if (subid < 10) + ctx->backref_ok |= 1<<subid; return REG_OK; } @@ -864,6 +868,8 @@ static reg_errcode_t parse_atom(tre_parse_ctx_t *ctx, const char *s) if (!ere && (unsigned)*s-'1' < 9) { /* back reference */ int val = *s - '0'; + if (!(ctx->backref_ok & 1<<val)) + return REG_ESUBREG; node = tre_ast_new_literal(ctx->mem, BACKREF, val, ctx->position++); ctx->max_backref = MAX(val, ctx->max_backref); } else { |