[PATCH v3] fetch-pack: redact packfile urls in traces

From: Ivan Frade <ifrade@google.com>

In some setups, packfile uris act as bearer token. It is not recommended to expose them plainly in logs, although in special circunstances (e.g. debug) it makes sense to write them.

Redact the packfile URL paths by default, unless the GIT_TRACE_REDACT variable is set to false. This mimics the redacting of the Authorization header in HTTP.

Signed-off-by: Ivan Frade <ifrade@google.com>
---
    fetch-pack: redact packfile urls in traces
    
    Changes since v1:
    
     * Redact only the path of the URL
     * Test are now strict, validating the exact line expected in the log
    
    Changes since v1:
    
     * Removed non-POSIX flags in tests
     * More accurate regex for the non-encrypted packfile line
     * Dropped documentation change
     * Dropped redacting the die message in http-fetch

Published-As: https://github.com/gitgitgadget/git/releases/tag/pr-1052%2Fifradeo%2Fredact-packfile-uri-v3
Fetch-It-Via: git fetch https://github.com/gitgitgadget/git pr-1052/ifradeo/redact-packfile-uri-v3
Pull-Request: https://github.com/gitgitgadget/git/pull/1052

Range-diff vs v2:

 1:  701cb7a6ab9 ! 1:  9afe0093af4 fetch-pack: redact packfile urls in traces
     @@ Commit message
          recommended to expose them plainly in logs, although in special
          circunstances (e.g. debug) it makes sense to write them.
      
     -    Redact the packfile-uri lines by default, unless the GIT_TRACE_REDACT
     -    variable is set to false. This mimics the redacting of the
     -    Authorization header in HTTP.
     -
     -    Changes since v1:
     -    - Removed non-POSIX flags in tests
     -    - More accurate regex for the non-encrypted packfile line
     -    - Dropped documentation change
     -    - Dropped redacting the die message in http-fetch
     +    Redact the packfile URL paths by default, unless the GIT_TRACE_REDACT
     +    variable is set to false. This mimics the redacting of the Authorization
     +    header in HTTP.
      
          Signed-off-by: Ivan Frade <ifrade@google.com>
      
     @@ fetch-pack.c: static void receive_wanted_refs(struct packet_reader *reader,
       static void receive_packfile_uris(struct packet_reader *reader,
       				  struct string_list *uris)
       {
     -+	int original_options;
     ++	int saved_options;
       	process_section_header(reader, "packfile-uris", 0);
      +	/*
      +	 * In some setups, packfile-uris act as bearer tokens,
      +	 * redact them by default.
      +	 */
     -+	original_options = reader->options;
     ++	saved_options = reader->options;
      +	if (git_env_bool("GIT_TRACE_REDACT", 1))
     -+		reader->options |= PACKET_READ_REDACT_ON_TRACE;
     ++		reader->options |= PACKET_READ_REDACT_URL_PATH;
      +
       	while (packet_reader_read(reader) == PACKET_READ_NORMAL) {
       		if (reader->pktlen < the_hash_algo->hexsz ||
     @@ fetch-pack.c: static void receive_packfile_uris(struct packet_reader *reader,
       
       		string_list_append(uris, reader->line);
       	}
     -+	reader->options = original_options;
     ++	reader->options = saved_options;
      +
       	if (reader->status != PACKET_READ_DELIM)
       		die("expected DELIM");
       }
      
       ## pkt-line.c ##
     +@@ pkt-line.c: int packet_length(const char lenbuf_hex[4])
     + 	return (val < 0) ? val : (val << 8) | hex2chr(lenbuf_hex + 2);
     + }
     + 
     ++static int find_url_path_start(const char* buffer)
     ++{
     ++	const char *URL_MARK = "://";
     ++	char *p = strstr(buffer, URL_MARK);
     ++	if (!p) {
     ++		return -1;
     ++	}
     ++
     ++	p += strlen(URL_MARK);
     ++	while (*p && *p != '/')
     ++		p++;
     ++
     ++	// Position after '/'
     ++	if (*p && *(p + 1))
     ++		return (p + 1) - buffer;
     ++
     ++	return -1;
     ++}
     ++
     + enum packet_read_status packet_read_with_status(int fd, char **src_buffer,
     + 						size_t *src_len, char *buffer,
     + 						unsigned size, int *pktlen,
     +@@ pkt-line.c: enum packet_read_status packet_read_with_status(int fd, char **src_buffer,
     + {
     + 	int len;
     + 	char linelen[4];
     ++	int url_path_start;
     + 
     + 	if (get_packet_data(fd, src_buffer, src_len, linelen, 4, options) < 0) {
     + 		*pktlen = -1;
      @@ pkt-line.c: enum packet_read_status packet_read_with_status(int fd, char **src_buffer,
       		len--;
       
       	buffer[len] = 0;
      -	packet_trace(buffer, len, 0);
     -+	if (options & PACKET_READ_REDACT_ON_TRACE) {
     ++	if (options & PACKET_READ_REDACT_URL_PATH &&
     ++	    (url_path_start = find_url_path_start(buffer)) != -1) {
      +		const char *redacted = "<redacted>";
     -+		packet_trace(redacted, strlen(redacted), 0);
     ++		struct strbuf tracebuf = STRBUF_INIT;
     ++		strbuf_insert(&tracebuf, 0, buffer, len);
     ++		strbuf_splice(&tracebuf, url_path_start,
     ++			      len - url_path_start, redacted, strlen(redacted));
     ++		packet_trace(tracebuf.buf, tracebuf.len, 0);
     ++		strbuf_release(&tracebuf);
      +	} else {
      +		packet_trace(buffer, len, 0);
      +	}
     @@ pkt-line.h: void packet_fflush(FILE *f);
       #define PACKET_READ_CHOMP_NEWLINE        (1u<<1)
       #define PACKET_READ_DIE_ON_ERR_PACKET    (1u<<2)
       #define PACKET_READ_GENTLE_ON_READ_ERROR (1u<<3)
     -+#define PACKET_READ_REDACT_ON_TRACE      (1u<<4)
     ++#define PACKET_READ_REDACT_URL_PATH      (1u<<4)
       int packet_read(int fd, char **src_buffer, size_t *src_len, char
       		*buffer, unsigned size, int options);
       
     @@ t/t5702-protocol-v2.sh: test_expect_success 'packfile-uri with transfer.fsckobje
       	test_i18ngrep "disallowed submodule name" err
       '
       
     -+test_expect_success 'packfile-uri redacted in trace' '
     ++test_expect_success 'packfile-uri path redacted in trace' '
      +	P="$HTTPD_DOCUMENT_ROOT_PATH/http_parent" &&
      +	rm -rf "$P" http_child log &&
      +
     @@ t/t5702-protocol-v2.sh: test_expect_success 'packfile-uri with transfer.fsckobje
      +	git -C "$P" add my-blob &&
      +	git -C "$P" commit -m x &&
      +
     -+	configure_exclusion "$P" my-blob >h &&
     ++	git -C "$P" hash-object my-blob >objh &&
     ++	git -C "$P" pack-objects "$HTTPD_DOCUMENT_ROOT_PATH/mypack" <objh >packh &&
     ++	git -C "$P" config --add \
     ++		"uploadpack.blobpackfileuri" \
     ++		"$(cat objh) $(cat packh) $HTTPD_URL/dumb/mypack-$(cat packh).pack" &&
      +
      +	GIT_TRACE=1 GIT_TRACE_PACKET="$(pwd)/log" GIT_TEST_SIDEBAND_ALL=1 \
      +	git -c protocol.version=2 \
      +		-c fetch.uriprotocols=http,https \
      +		clone "$HTTPD_URL/smart/http_parent" http_child &&
      +
     -+	grep "clone< <redacted>" log
     ++	grep -F "clone< \\1$(cat packh) $HTTPD_URL/<redacted>" log
      +'
      +
     -+test_expect_success 'packfile-uri not redacted in trace when GIT_TRACE_REDACT=0' '
     ++test_expect_success 'packfile-uri path not redacted in trace when GIT_TRACE_REDACT=0' '
      +	P="$HTTPD_DOCUMENT_ROOT_PATH/http_parent" &&
      +	rm -rf "$P" http_child log &&
      +
     @@ t/t5702-protocol-v2.sh: test_expect_success 'packfile-uri with transfer.fsckobje
      +	git -C "$P" add my-blob &&
      +	git -C "$P" commit -m x &&
      +
     -+	configure_exclusion "$P" my-blob >h &&
     ++	git -C "$P" hash-object my-blob >objh &&
     ++	git -C "$P" pack-objects "$HTTPD_DOCUMENT_ROOT_PATH/mypack" <objh >packh &&
     ++	git -C "$P" config --add \
     ++		"uploadpack.blobpackfileuri" \
     ++		"$(cat objh) $(cat packh) $HTTPD_URL/dumb/mypack-$(cat packh).pack" &&
      +
      +	GIT_TRACE=1 GIT_TRACE_PACKET="$(pwd)/log" GIT_TEST_SIDEBAND_ALL=1 \
      +	GIT_TRACE_REDACT=0 \
     @@ t/t5702-protocol-v2.sh: test_expect_success 'packfile-uri with transfer.fsckobje
      +		-c fetch.uriprotocols=http,https \
      +		clone "$HTTPD_URL/smart/http_parent" http_child &&
      +
     -+	grep -E "clone< ..[0-9a-f]{40,64} http://" log
     ++	grep -F "clone< \\1$(cat packh) $HTTPD_URL/dumb/mypack-$(cat packh).pack" log
      +'
      +
       test_expect_success 'http:// --negotiate-only' '

 fetch-pack.c           | 11 +++++++++
 pkt-line.c             | 33 ++++++++++++++++++++++++++-
 pkt-line.h             |  1 +
 t/t5702-protocol-v2.sh | 51 ++++++++++++++++++++++++++++++++++++++++++
 4 files changed, 95 insertions(+), 1 deletion(-)