From 91d96dc8ddaebe0b6cb393f672085e6bfaf15a31 Mon Sep 17 00:00:00 2001
From: Michael Niedermayer <michael@niedermayer.cc>
Date: Thu, 16 Jan 2025 01:28:46 +0100
Subject: [PATCH] avformat/hls: Be more picky on extensions

This blocks disallowed extensions from probing
It also requires all available segments to have matching extensions to the format
mpegts is treated independent of the extension

It is recommended to set the whitelists correctly
instead of depending on extensions, but this should help a bit,
and this is easier to backport

Fixes: CVE-2023-6602 II. HLS Force TTY Demuxer
Fixes: CVE-2023-6602 IV. HLS XBIN Demuxer DoS Amplification

The other parts of CVE-2023-6602 have been fixed by prior commits

Found-by: Harvey Phillips of Amazon Element55 (element55)
Signed-off-by: Michael Niedermayer <michael@niedermayer.cc>
---
 doc/demuxers.texi |  7 +++++++
 libavformat/hls.c | 50 +++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 57 insertions(+)

diff --git a/doc/demuxers.texi b/doc/demuxers.texi
index cc81c615dd..2324b3b469 100644
--- a/doc/demuxers.texi
+++ b/doc/demuxers.texi
@@ -564,6 +564,13 @@ prefer to use #EXT-X-START if it's in playlist instead of live_start_index.
 @item allowed_extensions
 ',' separated list of file extensions that hls is allowed to access.
 
+@item extension_picky
+This blocks disallowed extensions from probing
+It also requires all available segments to have matching extensions to the format
+except mpegts, which is always allowed.
+It is recommended to set the whitelists correctly instead of depending on extensions
+Enabled by default.
+
 @item max_reload
 Maximum number of times a insufficient list is attempted to be reloaded.
 Default value is 1000.
diff --git a/libavformat/hls.c b/libavformat/hls.c
index 045741c3b4..93f6d1f102 100644
--- a/libavformat/hls.c
+++ b/libavformat/hls.c
@@ -223,6 +223,7 @@ typedef struct HLSContext {
     AVDictionary *avio_opts;
     AVDictionary *seg_format_opts;
     char *allowed_extensions;
+    int extension_picky;
     int max_reload;
     int http_persistent;
     int http_multiple;
@@ -731,6 +732,40 @@ static int open_url(AVFormatContext *s, AVIOContext **pb, const char *url,
     return ret;
 }
 
+static int test_segment(AVFormatContext *s, const AVInputFormat *in_fmt, struct playlist *pls, struct segment *seg)
+{
+    HLSContext *c = s->priv_data;
+    int matchA = 3;
+    int matchF = 0;
+
+    if (!c->extension_picky)
+        return 0;
+
+    if (strcmp(c->allowed_extensions, "ALL"))
+        matchA =      av_match_ext    (seg->url, c->allowed_extensions)
+                 + 2*(ff_match_url_ext(seg->url, c->allowed_extensions) > 0);
+
+    if (!matchA) {
+        av_log(s, AV_LOG_ERROR, "URL %s is not in allowed_extensions\n", seg->url);
+        return AVERROR_INVALIDDATA;
+    }
+
+    if (in_fmt) {
+        if (in_fmt->extensions) {
+            matchF =      av_match_ext(    seg->url, in_fmt->extensions)
+                     + 2*(ff_match_url_ext(seg->url, in_fmt->extensions) > 0);
+        } else if (!strcmp(in_fmt->name, "mpegts"))
+            matchF = 3;
+
+        if (!(matchA & matchF)) {
+            av_log(s, AV_LOG_ERROR, "detected format extension %s mismatches allowed extensions in url %s\n", in_fmt->extensions ? in_fmt->extensions : "none", seg->url);
+            return AVERROR_INVALIDDATA;
+        }
+    }
+
+    return 0;
+}
+
 static int parse_playlist(HLSContext *c, const char *url,
                           struct playlist *pls, AVIOContext *in)
 {
@@ -989,6 +1024,14 @@ static int parse_playlist(HLSContext *c, const char *url,
                     goto fail;
                 }
 
+                ret = test_segment(c->ctx, pls->ctx ? pls->ctx->iformat : NULL, pls, seg);
+                if (ret < 0) {
+                    av_free(seg->url);
+                    av_free(seg->key);
+                    av_free(seg);
+                    goto fail;
+                }
+
                 if (duration < 0.001 * AV_TIME_BASE) {
                     av_log(c->ctx, AV_LOG_WARNING, "Cannot get correct #EXTINF value of segment %s,"
                                     " set to default value to 1ms.\n", seg->url);
@@ -2114,6 +2157,11 @@ static int hls_read_header(AVFormatContext *s)
             pls->ctx->interrupt_callback = s->interrupt_callback;
             url = av_strdup(pls->segments[0]->url);
             ret = av_probe_input_buffer(&pls->pb.pub, &in_fmt, url, NULL, 0, 0);
+
+            for (int n = 0; n < pls->n_segments; n++)
+                if (ret >= 0)
+                    ret = test_segment(s, in_fmt, pls, pls->segments[n]);
+
             if (ret < 0) {
                 /* Free the ctx - it isn't initialized properly at this point,
                 * so avformat_close_input shouldn't be called. If
@@ -2576,6 +2624,8 @@ static const AVOption hls_options[] = {
         OFFSET(allowed_extensions), AV_OPT_TYPE_STRING,
         {.str = "3gp,aac,avi,ac3,eac3,flac,mkv,m3u8,m4a,m4s,m4v,mpg,mov,mp2,mp3,mp4,mpeg,mpegts,ogg,ogv,oga,ts,vob,wav"},
         INT_MIN, INT_MAX, FLAGS},
+    {"extension_picky", "Be picky with all extensions matching",
+        OFFSET(extension_picky), AV_OPT_TYPE_BOOL, {.i64 = 1}, 0, 1, FLAGS},
     {"max_reload", "Maximum number of times a insufficient list is attempted to be reloaded",
         OFFSET(max_reload), AV_OPT_TYPE_INT, {.i64 = 3}, 0, INT_MAX, FLAGS},
     {"m3u8_hold_counters", "The maximum number of times to load m3u8 when it refreshes without new segments",