From c47ad25ea3b484e10326f933e927c0bc8cded3da Mon Sep 17 00:00:00 2001
From: Rich Felker <dalias@aerifal.cx>
Date: Wed, 12 Feb 2025 17:06:30 -0500
Subject: iconv: harden UTF-8 output code path against input decoder bugs

the UTF-8 output code was written assuming an invariant that iconv's
decoders only emit valid Unicode Scalar Values which wctomb can encode
successfully, thereby always returning a value between 1 and 4.

if this invariant is not satisfied, wctomb returns (size_t)-1, and the
subsequent adjustments to the output buffer pointer and remaining
output byte count overflow, moving the output position backwards,
potentially past the beginning of the buffer, without storing any
bytes.
---
 src/locale/iconv.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/src/locale/iconv.c b/src/locale/iconv.c
index 008c93f0..52178950 100644
--- a/src/locale/iconv.c
+++ b/src/locale/iconv.c
@@ -545,6 +545,10 @@ size_t iconv(iconv_t cd, char **restrict in, size_t *restrict inb, char **restri
 				if (*outb < k) goto toobig;
 				memcpy(*out, tmp, k);
 			} else k = wctomb_utf8(*out, c);
+			/* This failure condition should be unreachable, but
+			 * is included to prevent decoder bugs from translating
+			 * into advancement outside the output buffer range. */
+			if (k>4) goto ilseq;
 			*out += k;
 			*outb -= k;
 			break;
-- 
cgit v1.2.1