1
0
Fork 0
mirror of https://github.com/git/git.git synced 2024-11-05 08:47:56 +01:00
git/connect.c

1143 lines
27 KiB
C
Raw Normal View History

#include "git-compat-util.h"
#include "cache.h"
#include "config.h"
#include "pkt-line.h"
#include "quote.h"
#include "refs.h"
#include "run-command.h"
#include "remote.h"
#include "connect.h"
#include "url.h"
#include "string-list.h"
#include "sha1-array.h"
transport: add a protocol-whitelist environment variable If we are cloning an untrusted remote repository into a sandbox, we may also want to fetch remote submodules in order to get the complete view as intended by the other side. However, that opens us up to attacks where a malicious user gets us to clone something they would not otherwise have access to (this is not necessarily a problem by itself, but we may then act on the cloned contents in a way that exposes them to the attacker). Ideally such a setup would sandbox git entirely away from high-value items, but this is not always practical or easy to set up (e.g., OS network controls may block multiple protocols, and we would want to enable some but not others). We can help this case by providing a way to restrict particular protocols. We use a whitelist in the environment. This is more annoying to set up than a blacklist, but defaults to safety if the set of protocols git supports grows). If no whitelist is specified, we continue to default to allowing all protocols (this is an "unsafe" default, but since the minority of users will want this sandboxing effect, it is the only sensible one). A note on the tests: ideally these would all be in a single test file, but the git-daemon and httpd test infrastructure is an all-or-nothing proposition rather than a test-by-test prerequisite. By putting them all together, we would be unable to test the file-local code on machines without apache. Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2015-09-16 19:12:52 +02:00
#include "transport.h"
#include "strbuf.h"
#include "protocol.h"
static char *server_capabilities;
static const char *parse_feature_value(const char *, const char *, int *);
static int check_ref(const char *name, unsigned int flags)
{
if (!flags)
return 1;
if (!skip_prefix(name, "refs/", &name))
return 0;
/* REF_NORMAL means that we don't want the magic fake tag refs */
if ((flags & REF_NORMAL) && check_refname_format(name, 0))
return 0;
/* REF_HEADS means that we want regular branch heads */
if ((flags & REF_HEADS) && starts_with(name, "heads/"))
return 1;
/* REF_TAGS means that we want tags */
if ((flags & REF_TAGS) && starts_with(name, "tags/"))
return 1;
/* All type bits clear means that we are ok with anything */
return !(flags & ~REF_NORMAL);
}
int check_ref_type(const struct ref *ref, int flags)
{
return check_ref(ref->name, flags);
}
static void die_initial_contact(int unexpected)
{
if (unexpected)
die(_("The remote end hung up upon initial contact"));
else
die(_("Could not read from remote repository.\n\n"
"Please make sure you have the correct access rights\n"
"and the repository exists."));
}
static void parse_one_symref_info(struct string_list *symref, const char *val, int len)
{
char *sym, *target;
struct string_list_item *item;
if (!len)
return; /* just "symref" */
/* e.g. "symref=HEAD:refs/heads/master" */
sym = xmemdupz(val, len);
target = strchr(sym, ':');
if (!target)
/* just "symref=something" */
goto reject;
*(target++) = '\0';
if (check_refname_format(sym, REFNAME_ALLOW_ONELEVEL) ||
check_refname_format(target, REFNAME_ALLOW_ONELEVEL))
/* "symref=bogus:pair */
goto reject;
item = string_list_append_nodup(symref, sym);
item->util = target;
return;
reject:
free(sym);
return;
}
static void annotate_refs_with_symref_info(struct ref *ref)
{
struct string_list symref = STRING_LIST_INIT_DUP;
const char *feature_list = server_capabilities;
while (feature_list) {
int len;
const char *val;
val = parse_feature_value(feature_list, "symref", &len);
if (!val)
break;
parse_one_symref_info(&symref, val, len);
feature_list = val + 1;
}
string_list_sort(&symref);
for (; ref; ref = ref->next) {
struct string_list_item *item;
item = string_list_lookup(&symref, ref->name);
if (!item)
continue;
ref->symref = xstrdup((char *)item->util);
}
string_list_clear(&symref, 0);
}
/*
* Read one line of a server's ref advertisement into packet_buffer.
*/
static int read_remote_ref(int in, char **src_buf, size_t *src_len,
int *responded)
{
int len = packet_read(in, src_buf, src_len,
packet_buffer, sizeof(packet_buffer),
PACKET_READ_GENTLE_ON_EOF |
PACKET_READ_CHOMP_NEWLINE);
const char *arg;
if (len < 0)
die_initial_contact(*responded);
if (len > 4 && skip_prefix(packet_buffer, "ERR ", &arg))
die("remote error: %s", arg);
*responded = 1;
return len;
}
#define EXPECTING_PROTOCOL_VERSION 0
#define EXPECTING_FIRST_REF 1
#define EXPECTING_REF 2
#define EXPECTING_SHALLOW 3
/* Returns 1 if packet_buffer is a protocol version pkt-line, 0 otherwise. */
static int process_protocol_version(void)
{
switch (determine_protocol_version_client(packet_buffer)) {
case protocol_v1:
return 1;
case protocol_v0:
return 0;
default:
die("server is speaking an unknown protocol");
}
}
static void process_capabilities(int *len)
{
int nul_location = strlen(packet_buffer);
if (nul_location == *len)
return;
server_capabilities = xstrdup(packet_buffer + nul_location + 1);
*len = nul_location;
}
static int process_dummy_ref(void)
{
struct object_id oid;
const char *name;
if (parse_oid_hex(packet_buffer, &oid, &name))
return 0;
if (*name != ' ')
return 0;
name++;
return !oidcmp(&null_oid, &oid) && !strcmp(name, "capabilities^{}");
}
static void check_no_capabilities(int len)
{
if (strlen(packet_buffer) != len)
warning("Ignoring capabilities after first line '%s'",
packet_buffer + strlen(packet_buffer));
}
static int process_ref(int len, struct ref ***list, unsigned int flags,
struct oid_array *extra_have)
{
struct object_id old_oid;
const char *name;
if (parse_oid_hex(packet_buffer, &old_oid, &name))
return 0;
if (*name != ' ')
return 0;
name++;
if (extra_have && !strcmp(name, ".have")) {
oid_array_append(extra_have, &old_oid);
} else if (!strcmp(name, "capabilities^{}")) {
die("protocol error: unexpected capabilities^{}");
} else if (check_ref(name, flags)) {
struct ref *ref = alloc_ref(name);
oidcpy(&ref->old_oid, &old_oid);
**list = ref;
*list = &ref->next;
}
check_no_capabilities(len);
return 1;
}
static int process_shallow(int len, struct oid_array *shallow_points)
{
const char *arg;
struct object_id old_oid;
if (!skip_prefix(packet_buffer, "shallow ", &arg))
return 0;
if (get_oid_hex(arg, &old_oid))
die("protocol error: expected shallow sha-1, got '%s'", arg);
if (!shallow_points)
die("repository on the other end cannot be shallow");
oid_array_append(shallow_points, &old_oid);
check_no_capabilities(len);
return 1;
}
/*
* Read all the refs from the other end
*/
struct ref **get_remote_heads(int in, char *src_buf, size_t src_len,
struct ref **list, unsigned int flags,
struct oid_array *extra_have,
struct oid_array *shallow_points)
{
struct ref **orig_list = list;
/*
* A hang-up after seeing some response from the other end
* means that it is unexpected, as we know the other end is
* willing to talk to us. A hang-up before seeing any
* response does not necessarily mean an ACL problem, though.
*/
int responded = 0;
int len;
int state = EXPECTING_PROTOCOL_VERSION;
*list = NULL;
while ((len = read_remote_ref(in, &src_buf, &src_len, &responded))) {
switch (state) {
case EXPECTING_PROTOCOL_VERSION:
if (process_protocol_version()) {
state = EXPECTING_FIRST_REF;
break;
}
state = EXPECTING_FIRST_REF;
/* fallthrough */
case EXPECTING_FIRST_REF:
process_capabilities(&len);
if (process_dummy_ref()) {
state = EXPECTING_SHALLOW;
break;
}
state = EXPECTING_REF;
/* fallthrough */
case EXPECTING_REF:
if (process_ref(len, &list, flags, extra_have))
break;
state = EXPECTING_SHALLOW;
/* fallthrough */
case EXPECTING_SHALLOW:
if (process_shallow(len, shallow_points))
break;
die("protocol error: unexpected '%s'", packet_buffer);
default:
die("unexpected state %d", state);
}
}
annotate_refs_with_symref_info(*orig_list);
return list;
}
static const char *parse_feature_value(const char *feature_list, const char *feature, int *lenp)
{
int len;
if (!feature_list)
return NULL;
len = strlen(feature);
while (*feature_list) {
const char *found = strstr(feature_list, feature);
if (!found)
return NULL;
2012-08-14 03:59:27 +02:00
if (feature_list == found || isspace(found[-1])) {
const char *value = found + len;
/* feature with no value (e.g., "thin-pack") */
if (!*value || isspace(*value)) {
if (lenp)
*lenp = 0;
return value;
}
/* feature with a value (e.g., "agent=git/1.2.3") */
else if (*value == '=') {
value++;
if (lenp)
*lenp = strcspn(value, " \t\n");
return value;
}
/*
* otherwise we matched a substring of another feature;
* keep looking
*/
}
feature_list = found + 1;
}
return NULL;
}
2012-08-14 03:59:27 +02:00
int parse_feature_request(const char *feature_list, const char *feature)
{
return !!parse_feature_value(feature_list, feature, NULL);
}
const char *server_feature_value(const char *feature, int *len)
{
return parse_feature_value(server_capabilities, feature, len);
}
int server_supports(const char *feature)
{
return !!server_feature_value(feature, NULL);
}
enum protocol {
PROTO_LOCAL = 1,
PROTO_FILE,
PROTO_SSH,
PROTO_GIT
};
int url_is_local_not_ssh(const char *url)
{
const char *colon = strchr(url, ':');
const char *slash = strchr(url, '/');
return !colon || (slash && slash < colon) ||
has_dos_drive_prefix(url);
}
static const char *prot_name(enum protocol protocol)
{
switch (protocol) {
case PROTO_LOCAL:
case PROTO_FILE:
return "file";
case PROTO_SSH:
return "ssh";
case PROTO_GIT:
return "git";
default:
return "unknown protocol";
}
}
static enum protocol get_protocol(const char *name)
{
if (!strcmp(name, "ssh"))
return PROTO_SSH;
if (!strcmp(name, "git"))
return PROTO_GIT;
if (!strcmp(name, "git+ssh")) /* deprecated - do not use */
return PROTO_SSH;
if (!strcmp(name, "ssh+git")) /* deprecated - do not use */
return PROTO_SSH;
if (!strcmp(name, "file"))
return PROTO_FILE;
die("I don't handle protocol '%s'", name);
}
static char *host_end(char **hoststart, int removebrackets)
{
char *host = *hoststart;
char *end;
char *start = strstr(host, "@[");
if (start)
start++; /* Jump over '@' */
else
start = host;
if (start[0] == '[') {
end = strchr(start + 1, ']');
if (end) {
if (removebrackets) {
*end = 0;
memmove(start, start + 1, end - start);
end++;
}
} else
end = host;
} else
end = host;
return end;
}
#define STR_(s) # s
#define STR(s) STR_(s)
static void get_host_and_port(char **host, const char **port)
{
char *colon, *end;
end = host_end(host, 1);
colon = strchr(end, ':');
if (colon) {
long portnr = strtol(colon + 1, &end, 10);
if (end != colon + 1 && *end == '\0' && 0 <= portnr && portnr < 65536) {
*colon = 0;
*port = colon + 1;
} else if (!colon[1]) {
*colon = 0;
}
}
}
static void enable_keepalive(int sockfd)
{
int ka = 1;
if (setsockopt(sockfd, SOL_SOCKET, SO_KEEPALIVE, &ka, sizeof(ka)) < 0)
fprintf(stderr, "unable to set SO_KEEPALIVE on socket: %s\n",
strerror(errno));
}
#ifndef NO_IPV6
static const char *ai_name(const struct addrinfo *ai)
{
static char addr[NI_MAXHOST];
if (getnameinfo(ai->ai_addr, ai->ai_addrlen, addr, sizeof(addr), NULL, 0,
NI_NUMERICHOST) != 0)
xsnprintf(addr, sizeof(addr), "(unknown)");
return addr;
}
/*
* Returns a connected socket() fd, or else die()s.
*/
static int git_tcp_connect_sock(char *host, int flags)
{
struct strbuf error_message = STRBUF_INIT;
int sockfd = -1;
const char *port = STR(DEFAULT_GIT_PORT);
struct addrinfo hints, *ai0, *ai;
int gai;
int cnt = 0;
get_host_and_port(&host, &port);
if (!*port)
port = "<none>";
memset(&hints, 0, sizeof(hints));
if (flags & CONNECT_IPV4)
hints.ai_family = AF_INET;
else if (flags & CONNECT_IPV6)
hints.ai_family = AF_INET6;
hints.ai_socktype = SOCK_STREAM;
hints.ai_protocol = IPPROTO_TCP;
if (flags & CONNECT_VERBOSE)
fprintf(stderr, "Looking up %s ... ", host);
gai = getaddrinfo(host, port, &hints, &ai);
if (gai)
die("Unable to look up %s (port %s) (%s)", host, port, gai_strerror(gai));
if (flags & CONNECT_VERBOSE)
fprintf(stderr, "done.\nConnecting to %s (port %s) ... ", host, port);
for (ai0 = ai; ai; ai = ai->ai_next, cnt++) {
sockfd = socket(ai->ai_family,
ai->ai_socktype, ai->ai_protocol);
if ((sockfd < 0) ||
(connect(sockfd, ai->ai_addr, ai->ai_addrlen) < 0)) {
strbuf_addf(&error_message, "%s[%d: %s]: errno=%s\n",
host, cnt, ai_name(ai), strerror(errno));
if (0 <= sockfd)
close(sockfd);
sockfd = -1;
continue;
}
if (flags & CONNECT_VERBOSE)
fprintf(stderr, "%s ", ai_name(ai));
break;
}
freeaddrinfo(ai0);
if (sockfd < 0)
die("unable to connect to %s:\n%s", host, error_message.buf);
enable_keepalive(sockfd);
if (flags & CONNECT_VERBOSE)
fprintf(stderr, "done.\n");
strbuf_release(&error_message);
return sockfd;
}
#else /* NO_IPV6 */
/*
* Returns a connected socket() fd, or else die()s.
*/
static int git_tcp_connect_sock(char *host, int flags)
{
struct strbuf error_message = STRBUF_INIT;
int sockfd = -1;
const char *port = STR(DEFAULT_GIT_PORT);
char *ep;
struct hostent *he;
struct sockaddr_in sa;
char **ap;
unsigned int nport;
int cnt;
get_host_and_port(&host, &port);
if (flags & CONNECT_VERBOSE)
fprintf(stderr, "Looking up %s ... ", host);
he = gethostbyname(host);
if (!he)
die("Unable to look up %s (%s)", host, hstrerror(h_errno));
nport = strtoul(port, &ep, 10);
if ( ep == port || *ep ) {
/* Not numeric */
struct servent *se = getservbyname(port,"tcp");
if ( !se )
die("Unknown port %s", port);
nport = se->s_port;
}
if (flags & CONNECT_VERBOSE)
fprintf(stderr, "done.\nConnecting to %s (port %s) ... ", host, port);
for (cnt = 0, ap = he->h_addr_list; *ap; ap++, cnt++) {
memset(&sa, 0, sizeof sa);
sa.sin_family = he->h_addrtype;
2005-09-29 02:26:44 +02:00
sa.sin_port = htons(nport);
memcpy(&sa.sin_addr, *ap, he->h_length);
sockfd = socket(he->h_addrtype, SOCK_STREAM, 0);
if ((sockfd < 0) ||
connect(sockfd, (struct sockaddr *)&sa, sizeof sa) < 0) {
strbuf_addf(&error_message, "%s[%d: %s]: errno=%s\n",
host,
cnt,
inet_ntoa(*(struct in_addr *)&sa.sin_addr),
strerror(errno));
if (0 <= sockfd)
close(sockfd);
sockfd = -1;
continue;
}
if (flags & CONNECT_VERBOSE)
fprintf(stderr, "%s ",
inet_ntoa(*(struct in_addr *)&sa.sin_addr));
break;
}
if (sockfd < 0)
die("unable to connect to %s:\n%s", host, error_message.buf);
enable_keepalive(sockfd);
if (flags & CONNECT_VERBOSE)
fprintf(stderr, "done.\n");
return sockfd;
}
#endif /* NO_IPV6 */
/*
* Dummy child_process returned by git_connect() if the transport protocol
* does not need fork(2).
*/
static struct child_process no_fork = CHILD_PROCESS_INIT;
int git_connection_is_socket(struct child_process *conn)
{
return conn == &no_fork;
}
static struct child_process *git_tcp_connect(int fd[2], char *host, int flags)
{
int sockfd = git_tcp_connect_sock(host, flags);
fd[0] = sockfd;
fd[1] = dup(sockfd);
return &no_fork;
}
static char *git_proxy_command;
static int git_proxy_command_options(const char *var, const char *value,
void *cb)
{
if (!strcmp(var, "core.gitproxy")) {
const char *for_pos;
int matchlen = -1;
int hostlen;
const char *rhost_name = cb;
int rhost_len = strlen(rhost_name);
if (git_proxy_command)
return 0;
if (!value)
return config_error_nonbool(var);
/* [core]
* ;# matches www.kernel.org as well
* gitproxy = netcatter-1 for kernel.org
* gitproxy = netcatter-2 for sample.xz
* gitproxy = netcatter-default
*/
for_pos = strstr(value, " for ");
if (!for_pos)
/* matches everybody */
matchlen = strlen(value);
else {
hostlen = strlen(for_pos + 5);
if (rhost_len < hostlen)
matchlen = -1;
else if (!strncmp(for_pos + 5,
rhost_name + rhost_len - hostlen,
hostlen) &&
((rhost_len == hostlen) ||
rhost_name[rhost_len - hostlen -1] == '.'))
matchlen = for_pos - value;
else
matchlen = -1;
}
if (0 <= matchlen) {
/* core.gitproxy = none for kernel.org */
if (matchlen == 4 &&
!memcmp(value, "none", 4))
matchlen = 0;
git_proxy_command = xmemdupz(value, matchlen);
}
return 0;
}
return git_default_config(var, value, cb);
}
static int git_use_proxy(const char *host)
{
git_proxy_command = getenv("GIT_PROXY_COMMAND");
git_config(git_proxy_command_options, (void*)host);
return (git_proxy_command && *git_proxy_command);
}
connect: treat generic proxy processes like ssh processes The git_connect function returns two ends of a pipe for talking with a remote, plus a struct child_process representing the other end of the pipe. If we have a direct socket connection, then this points to a special "no_fork" child process. The code path for doing git-over-pipes or git-over-ssh sets up this child process to point to the child git command or the ssh process. When we call finish_connect eventually, we check wait() on the command and report its return value. The code path for git://, on the other hand, always sets it to no_fork. In the case of a direct TCP connection, this makes sense; we have no child process. But in the case of a proxy command (configured by core.gitproxy), we do have a child process, but we throw away its pid, and therefore ignore its return code. Instead, let's keep that information in the proxy case, and respect its return code, which can help catch some errors (though depending on your proxy command, it will be errors reported by the proxy command itself, and not propagated from git commands. Still, it is probably better to propagate such errors than to ignore them). It also means that the child_process field can reliably be used to determine whether the returned descriptors are actually a full-duplex socket, which means we should be using shutdown() instead of a simple close. Signed-off-by: Jeff King <peff@peff.net> Helped-by: Johannes Sixt <j6t@kdbg.org> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2011-05-16 08:46:07 +02:00
static struct child_process *git_proxy_connect(int fd[2], char *host)
{
const char *port = STR(DEFAULT_GIT_PORT);
connect: treat generic proxy processes like ssh processes The git_connect function returns two ends of a pipe for talking with a remote, plus a struct child_process representing the other end of the pipe. If we have a direct socket connection, then this points to a special "no_fork" child process. The code path for doing git-over-pipes or git-over-ssh sets up this child process to point to the child git command or the ssh process. When we call finish_connect eventually, we check wait() on the command and report its return value. The code path for git://, on the other hand, always sets it to no_fork. In the case of a direct TCP connection, this makes sense; we have no child process. But in the case of a proxy command (configured by core.gitproxy), we do have a child process, but we throw away its pid, and therefore ignore its return code. Instead, let's keep that information in the proxy case, and respect its return code, which can help catch some errors (though depending on your proxy command, it will be errors reported by the proxy command itself, and not propagated from git commands. Still, it is probably better to propagate such errors than to ignore them). It also means that the child_process field can reliably be used to determine whether the returned descriptors are actually a full-duplex socket, which means we should be using shutdown() instead of a simple close. Signed-off-by: Jeff King <peff@peff.net> Helped-by: Johannes Sixt <j6t@kdbg.org> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2011-05-16 08:46:07 +02:00
struct child_process *proxy;
get_host_and_port(&host, &port);
if (looks_like_command_line_option(host))
die("strange hostname '%s' blocked", host);
if (looks_like_command_line_option(port))
die("strange port '%s' blocked", port);
proxy = xmalloc(sizeof(*proxy));
child_process_init(proxy);
argv_array_push(&proxy->args, git_proxy_command);
argv_array_push(&proxy->args, host);
argv_array_push(&proxy->args, port);
connect: treat generic proxy processes like ssh processes The git_connect function returns two ends of a pipe for talking with a remote, plus a struct child_process representing the other end of the pipe. If we have a direct socket connection, then this points to a special "no_fork" child process. The code path for doing git-over-pipes or git-over-ssh sets up this child process to point to the child git command or the ssh process. When we call finish_connect eventually, we check wait() on the command and report its return value. The code path for git://, on the other hand, always sets it to no_fork. In the case of a direct TCP connection, this makes sense; we have no child process. But in the case of a proxy command (configured by core.gitproxy), we do have a child process, but we throw away its pid, and therefore ignore its return code. Instead, let's keep that information in the proxy case, and respect its return code, which can help catch some errors (though depending on your proxy command, it will be errors reported by the proxy command itself, and not propagated from git commands. Still, it is probably better to propagate such errors than to ignore them). It also means that the child_process field can reliably be used to determine whether the returned descriptors are actually a full-duplex socket, which means we should be using shutdown() instead of a simple close. Signed-off-by: Jeff King <peff@peff.net> Helped-by: Johannes Sixt <j6t@kdbg.org> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2011-05-16 08:46:07 +02:00
proxy->in = -1;
proxy->out = -1;
if (start_command(proxy))
die("cannot start proxy %s", git_proxy_command);
connect: treat generic proxy processes like ssh processes The git_connect function returns two ends of a pipe for talking with a remote, plus a struct child_process representing the other end of the pipe. If we have a direct socket connection, then this points to a special "no_fork" child process. The code path for doing git-over-pipes or git-over-ssh sets up this child process to point to the child git command or the ssh process. When we call finish_connect eventually, we check wait() on the command and report its return value. The code path for git://, on the other hand, always sets it to no_fork. In the case of a direct TCP connection, this makes sense; we have no child process. But in the case of a proxy command (configured by core.gitproxy), we do have a child process, but we throw away its pid, and therefore ignore its return code. Instead, let's keep that information in the proxy case, and respect its return code, which can help catch some errors (though depending on your proxy command, it will be errors reported by the proxy command itself, and not propagated from git commands. Still, it is probably better to propagate such errors than to ignore them). It also means that the child_process field can reliably be used to determine whether the returned descriptors are actually a full-duplex socket, which means we should be using shutdown() instead of a simple close. Signed-off-by: Jeff King <peff@peff.net> Helped-by: Johannes Sixt <j6t@kdbg.org> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2011-05-16 08:46:07 +02:00
fd[0] = proxy->out; /* read from proxy stdout */
fd[1] = proxy->in; /* write to proxy stdin */
return proxy;
}
static char *get_port(char *host)
{
char *end;
char *p = strchr(host, ':');
if (p) {
long port = strtol(p + 1, &end, 10);
if (end != p + 1 && *end == '\0' && 0 <= port && port < 65536) {
*p = '\0';
return p+1;
}
}
return NULL;
}
/*
* Extract protocol and relevant parts from the specified connection URL.
* The caller must free() the returned strings.
*/
static enum protocol parse_connect_url(const char *url_orig, char **ret_host,
char **ret_path)
{
char *url;
char *host, *path;
char *end;
int separator = '/';
enum protocol protocol = PROTO_LOCAL;
if (is_url(url_orig))
url = url_decode(url_orig);
else
url = xstrdup(url_orig);
host = strstr(url, "://");
if (host) {
*host = '\0';
protocol = get_protocol(url);
host += 3;
} else {
host = url;
if (!url_is_local_not_ssh(url)) {
protocol = PROTO_SSH;
separator = ':';
}
}
/*
* Don't do destructive transforms as protocol code does
* '[]' unwrapping in get_host_and_port()
*/
end = host_end(&host, 0);
if (protocol == PROTO_LOCAL)
path = end;
else if (protocol == PROTO_FILE && has_dos_drive_prefix(end))
path = end; /* "file://$(pwd)" may be "file://C:/projects/repo" */
else
path = strchr(end, separator);
if (!path || !*path)
die("No path specified. See 'man git-pull' for valid url syntax");
/*
* null-terminate hostname and point path to ~ for URL's like this:
* ssh://host.xz/~user/repo
*/
end = path; /* Need to \0 terminate host here */
if (separator == ':')
path++; /* path starts after ':' */
if (protocol == PROTO_GIT || protocol == PROTO_SSH) {
if (path[1] == '~')
path++;
}
path = xstrdup(path);
*end = '\0';
*ret_host = xstrdup(host);
*ret_path = path;
free(url);
return protocol;
}
static const char *get_ssh_command(void)
{
const char *ssh;
if ((ssh = getenv("GIT_SSH_COMMAND")))
return ssh;
if (!git_config_get_string_const("core.sshcommand", &ssh))
return ssh;
return NULL;
}
ssh: introduce a 'simple' ssh variant When using the 'ssh' transport, the '-o' option is used to specify an environment variable which should be set on the remote end. This allows git to send additional information when contacting the server, requesting the use of a different protocol version via the 'GIT_PROTOCOL' environment variable like so: "-o SendEnv=GIT_PROTOCOL". Unfortunately not all ssh variants support the sending of environment variables to the remote end. To account for this, only use the '-o' option for ssh variants which are OpenSSH compliant. This is done by checking that the basename of the ssh command is 'ssh' or the ssh variant is overridden to be 'ssh' (via the ssh.variant config). Other options like '-p' and '-P', which are used to specify a specific port to use, or '-4' and '-6', which are used to indicate that IPV4 or IPV6 addresses should be used, may also not be supported by all ssh variants. Currently if an ssh command's basename wasn't 'plink' or 'tortoiseplink' git assumes that the command is an OpenSSH variant. Since user configured ssh commands may not be OpenSSH compliant, tighten this constraint and assume a variant of 'simple' if the basename of the command doesn't match the variants known to git. The new ssh variant 'simple' will only have the host and command to execute ([username@]host command) passed as parameters to the ssh command. Update the Documentation to better reflect the command-line options sent to ssh commands based on their variant. Reported-by: Jeffrey Yasskin <jyasskin@google.com> Signed-off-by: Brandon Williams <bmwill@google.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2017-10-16 19:55:31 +02:00
enum ssh_variant {
ssh: 'auto' variant to select between 'ssh' and 'simple' Android's "repo" tool is a tool for managing a large codebase consisting of multiple smaller repositories, similar to Git's submodule feature. Starting with Git 94b8ae5a (ssh: introduce a 'simple' ssh variant, 2017-10-16), users noticed that it stopped handling the port in ssh:// URLs. The cause: when it encounters ssh:// URLs, repo pre-connects to the server and sets GIT_SSH to a helper ".repo/repo/git_ssh" that reuses that connection. Before 94b8ae5a, the helper was assumed to support OpenSSH options for lack of a better guess and got passed a -p option to set the port. After that patch, it uses the new default of a simple helper that does not accept an option to set the port. The next release of "repo" will set GIT_SSH_VARIANT to "ssh" to avoid that. But users of old versions and of other similar GIT_SSH implementations would not get the benefit of that fix. So update the default to use OpenSSH options again, with a twist. As observed in 94b8ae5a, we cannot assume that $GIT_SSH always handles OpenSSH options: common helpers such as travis-ci's dpl[*] are configured using GIT_SSH and do not accept OpenSSH options. So make the default a new variant "auto", with the following behavior: 1. First, check for a recognized basename, like today. 2. If the basename is not recognized, check whether $GIT_SSH supports OpenSSH options by running $GIT_SSH -G <options> <host> This returns status 0 and prints configuration in OpenSSH if it recognizes all <options> and returns status 255 if it encounters an unrecognized option. A wrapper script like exec ssh -- "$@" would fail with ssh: Could not resolve hostname -g: Name or service not known , correctly reflecting that it does not support OpenSSH options. The command is run with stdin, stdout, and stderr redirected to /dev/null so even a command that expects a terminal would exit immediately. 3. Based on the result from step (2), behave like "ssh" (if it succeeded) or "simple" (if it failed). This way, the default ssh variant for unrecognized commands can handle both the repo and dpl cases as intended. This autodetection has been running on Google workstations since 2017-10-23 with no reported negative effects. [*] https://github.com/travis-ci/dpl/blob/6c3fddfda1f2a85944c544446b068bac0a77c049/lib/dpl/provider.rb#L215 Reported-by: William Yan <wyan@google.com> Improved-by: Jonathan Tan <jonathantanmy@google.com> Signed-off-by: Jonathan Nieder <jrnieder@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2017-11-20 22:30:04 +01:00
VARIANT_AUTO,
ssh: introduce a 'simple' ssh variant When using the 'ssh' transport, the '-o' option is used to specify an environment variable which should be set on the remote end. This allows git to send additional information when contacting the server, requesting the use of a different protocol version via the 'GIT_PROTOCOL' environment variable like so: "-o SendEnv=GIT_PROTOCOL". Unfortunately not all ssh variants support the sending of environment variables to the remote end. To account for this, only use the '-o' option for ssh variants which are OpenSSH compliant. This is done by checking that the basename of the ssh command is 'ssh' or the ssh variant is overridden to be 'ssh' (via the ssh.variant config). Other options like '-p' and '-P', which are used to specify a specific port to use, or '-4' and '-6', which are used to indicate that IPV4 or IPV6 addresses should be used, may also not be supported by all ssh variants. Currently if an ssh command's basename wasn't 'plink' or 'tortoiseplink' git assumes that the command is an OpenSSH variant. Since user configured ssh commands may not be OpenSSH compliant, tighten this constraint and assume a variant of 'simple' if the basename of the command doesn't match the variants known to git. The new ssh variant 'simple' will only have the host and command to execute ([username@]host command) passed as parameters to the ssh command. Update the Documentation to better reflect the command-line options sent to ssh commands based on their variant. Reported-by: Jeffrey Yasskin <jyasskin@google.com> Signed-off-by: Brandon Williams <bmwill@google.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2017-10-16 19:55:31 +02:00
VARIANT_SIMPLE,
VARIANT_SSH,
VARIANT_PLINK,
VARIANT_PUTTY,
VARIANT_TORTOISEPLINK,
};
ssh: 'auto' variant to select between 'ssh' and 'simple' Android's "repo" tool is a tool for managing a large codebase consisting of multiple smaller repositories, similar to Git's submodule feature. Starting with Git 94b8ae5a (ssh: introduce a 'simple' ssh variant, 2017-10-16), users noticed that it stopped handling the port in ssh:// URLs. The cause: when it encounters ssh:// URLs, repo pre-connects to the server and sets GIT_SSH to a helper ".repo/repo/git_ssh" that reuses that connection. Before 94b8ae5a, the helper was assumed to support OpenSSH options for lack of a better guess and got passed a -p option to set the port. After that patch, it uses the new default of a simple helper that does not accept an option to set the port. The next release of "repo" will set GIT_SSH_VARIANT to "ssh" to avoid that. But users of old versions and of other similar GIT_SSH implementations would not get the benefit of that fix. So update the default to use OpenSSH options again, with a twist. As observed in 94b8ae5a, we cannot assume that $GIT_SSH always handles OpenSSH options: common helpers such as travis-ci's dpl[*] are configured using GIT_SSH and do not accept OpenSSH options. So make the default a new variant "auto", with the following behavior: 1. First, check for a recognized basename, like today. 2. If the basename is not recognized, check whether $GIT_SSH supports OpenSSH options by running $GIT_SSH -G <options> <host> This returns status 0 and prints configuration in OpenSSH if it recognizes all <options> and returns status 255 if it encounters an unrecognized option. A wrapper script like exec ssh -- "$@" would fail with ssh: Could not resolve hostname -g: Name or service not known , correctly reflecting that it does not support OpenSSH options. The command is run with stdin, stdout, and stderr redirected to /dev/null so even a command that expects a terminal would exit immediately. 3. Based on the result from step (2), behave like "ssh" (if it succeeded) or "simple" (if it failed). This way, the default ssh variant for unrecognized commands can handle both the repo and dpl cases as intended. This autodetection has been running on Google workstations since 2017-10-23 with no reported negative effects. [*] https://github.com/travis-ci/dpl/blob/6c3fddfda1f2a85944c544446b068bac0a77c049/lib/dpl/provider.rb#L215 Reported-by: William Yan <wyan@google.com> Improved-by: Jonathan Tan <jonathantanmy@google.com> Signed-off-by: Jonathan Nieder <jrnieder@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2017-11-20 22:30:04 +01:00
static void override_ssh_variant(enum ssh_variant *ssh_variant)
{
ssh: introduce a 'simple' ssh variant When using the 'ssh' transport, the '-o' option is used to specify an environment variable which should be set on the remote end. This allows git to send additional information when contacting the server, requesting the use of a different protocol version via the 'GIT_PROTOCOL' environment variable like so: "-o SendEnv=GIT_PROTOCOL". Unfortunately not all ssh variants support the sending of environment variables to the remote end. To account for this, only use the '-o' option for ssh variants which are OpenSSH compliant. This is done by checking that the basename of the ssh command is 'ssh' or the ssh variant is overridden to be 'ssh' (via the ssh.variant config). Other options like '-p' and '-P', which are used to specify a specific port to use, or '-4' and '-6', which are used to indicate that IPV4 or IPV6 addresses should be used, may also not be supported by all ssh variants. Currently if an ssh command's basename wasn't 'plink' or 'tortoiseplink' git assumes that the command is an OpenSSH variant. Since user configured ssh commands may not be OpenSSH compliant, tighten this constraint and assume a variant of 'simple' if the basename of the command doesn't match the variants known to git. The new ssh variant 'simple' will only have the host and command to execute ([username@]host command) passed as parameters to the ssh command. Update the Documentation to better reflect the command-line options sent to ssh commands based on their variant. Reported-by: Jeffrey Yasskin <jyasskin@google.com> Signed-off-by: Brandon Williams <bmwill@google.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2017-10-16 19:55:31 +02:00
const char *variant = getenv("GIT_SSH_VARIANT");
connect.c: stop conflating ssh command names and overrides dd33e07766 ("connect: Add the envvar GIT_SSH_VARIANT and ssh.variant config", 2017-02-01) attempted to add support for configuration and environment variable to override the different handling of port_option and needs_batch settings suitable for variants of the ssh implementation that was autodetected by looking at the ssh command name. Because it piggybacked on the code that turns command name to specific override (e.g. "plink.exe" and "plink" means port_option needs to be set to 'P' instead of the default 'p'), yet it defined a separate namespace for these overrides (e.g. "putty" can be usable to signal that port_option needs to be 'P'), however, it made the auto-detection based on the command name less robust (e.g. the code now accepts "putty" as a SSH command name and applies the same override). Separate the code that interprets the override that was read from the configuration & environment from the original code that handles the command names, as they are in separate namespaces, to fix this confusion. This incidentally also makes it easier for future enhancement of the override syntax (e.g. "port_option=p,needs_batch=1" may want to be accepted as a more explicit syntax) without affecting the code for auto-detection based on the command name. While at it, update the return type of the handle_ssh_variant() helper function to void; the caller does not use it, and the function does not return any meaningful value. Signed-off-by: Junio C Hamano <gitster@pobox.com>
2017-02-09 18:20:25 +01:00
ssh: introduce a 'simple' ssh variant When using the 'ssh' transport, the '-o' option is used to specify an environment variable which should be set on the remote end. This allows git to send additional information when contacting the server, requesting the use of a different protocol version via the 'GIT_PROTOCOL' environment variable like so: "-o SendEnv=GIT_PROTOCOL". Unfortunately not all ssh variants support the sending of environment variables to the remote end. To account for this, only use the '-o' option for ssh variants which are OpenSSH compliant. This is done by checking that the basename of the ssh command is 'ssh' or the ssh variant is overridden to be 'ssh' (via the ssh.variant config). Other options like '-p' and '-P', which are used to specify a specific port to use, or '-4' and '-6', which are used to indicate that IPV4 or IPV6 addresses should be used, may also not be supported by all ssh variants. Currently if an ssh command's basename wasn't 'plink' or 'tortoiseplink' git assumes that the command is an OpenSSH variant. Since user configured ssh commands may not be OpenSSH compliant, tighten this constraint and assume a variant of 'simple' if the basename of the command doesn't match the variants known to git. The new ssh variant 'simple' will only have the host and command to execute ([username@]host command) passed as parameters to the ssh command. Update the Documentation to better reflect the command-line options sent to ssh commands based on their variant. Reported-by: Jeffrey Yasskin <jyasskin@google.com> Signed-off-by: Brandon Williams <bmwill@google.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2017-10-16 19:55:31 +02:00
if (!variant && git_config_get_string_const("ssh.variant", &variant))
ssh: 'auto' variant to select between 'ssh' and 'simple' Android's "repo" tool is a tool for managing a large codebase consisting of multiple smaller repositories, similar to Git's submodule feature. Starting with Git 94b8ae5a (ssh: introduce a 'simple' ssh variant, 2017-10-16), users noticed that it stopped handling the port in ssh:// URLs. The cause: when it encounters ssh:// URLs, repo pre-connects to the server and sets GIT_SSH to a helper ".repo/repo/git_ssh" that reuses that connection. Before 94b8ae5a, the helper was assumed to support OpenSSH options for lack of a better guess and got passed a -p option to set the port. After that patch, it uses the new default of a simple helper that does not accept an option to set the port. The next release of "repo" will set GIT_SSH_VARIANT to "ssh" to avoid that. But users of old versions and of other similar GIT_SSH implementations would not get the benefit of that fix. So update the default to use OpenSSH options again, with a twist. As observed in 94b8ae5a, we cannot assume that $GIT_SSH always handles OpenSSH options: common helpers such as travis-ci's dpl[*] are configured using GIT_SSH and do not accept OpenSSH options. So make the default a new variant "auto", with the following behavior: 1. First, check for a recognized basename, like today. 2. If the basename is not recognized, check whether $GIT_SSH supports OpenSSH options by running $GIT_SSH -G <options> <host> This returns status 0 and prints configuration in OpenSSH if it recognizes all <options> and returns status 255 if it encounters an unrecognized option. A wrapper script like exec ssh -- "$@" would fail with ssh: Could not resolve hostname -g: Name or service not known , correctly reflecting that it does not support OpenSSH options. The command is run with stdin, stdout, and stderr redirected to /dev/null so even a command that expects a terminal would exit immediately. 3. Based on the result from step (2), behave like "ssh" (if it succeeded) or "simple" (if it failed). This way, the default ssh variant for unrecognized commands can handle both the repo and dpl cases as intended. This autodetection has been running on Google workstations since 2017-10-23 with no reported negative effects. [*] https://github.com/travis-ci/dpl/blob/6c3fddfda1f2a85944c544446b068bac0a77c049/lib/dpl/provider.rb#L215 Reported-by: William Yan <wyan@google.com> Improved-by: Jonathan Tan <jonathantanmy@google.com> Signed-off-by: Jonathan Nieder <jrnieder@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2017-11-20 22:30:04 +01:00
return;
connect.c: stop conflating ssh command names and overrides dd33e07766 ("connect: Add the envvar GIT_SSH_VARIANT and ssh.variant config", 2017-02-01) attempted to add support for configuration and environment variable to override the different handling of port_option and needs_batch settings suitable for variants of the ssh implementation that was autodetected by looking at the ssh command name. Because it piggybacked on the code that turns command name to specific override (e.g. "plink.exe" and "plink" means port_option needs to be set to 'P' instead of the default 'p'), yet it defined a separate namespace for these overrides (e.g. "putty" can be usable to signal that port_option needs to be 'P'), however, it made the auto-detection based on the command name less robust (e.g. the code now accepts "putty" as a SSH command name and applies the same override). Separate the code that interprets the override that was read from the configuration & environment from the original code that handles the command names, as they are in separate namespaces, to fix this confusion. This incidentally also makes it easier for future enhancement of the override syntax (e.g. "port_option=p,needs_batch=1" may want to be accepted as a more explicit syntax) without affecting the code for auto-detection based on the command name. While at it, update the return type of the handle_ssh_variant() helper function to void; the caller does not use it, and the function does not return any meaningful value. Signed-off-by: Junio C Hamano <gitster@pobox.com>
2017-02-09 18:20:25 +01:00
ssh: 'auto' variant to select between 'ssh' and 'simple' Android's "repo" tool is a tool for managing a large codebase consisting of multiple smaller repositories, similar to Git's submodule feature. Starting with Git 94b8ae5a (ssh: introduce a 'simple' ssh variant, 2017-10-16), users noticed that it stopped handling the port in ssh:// URLs. The cause: when it encounters ssh:// URLs, repo pre-connects to the server and sets GIT_SSH to a helper ".repo/repo/git_ssh" that reuses that connection. Before 94b8ae5a, the helper was assumed to support OpenSSH options for lack of a better guess and got passed a -p option to set the port. After that patch, it uses the new default of a simple helper that does not accept an option to set the port. The next release of "repo" will set GIT_SSH_VARIANT to "ssh" to avoid that. But users of old versions and of other similar GIT_SSH implementations would not get the benefit of that fix. So update the default to use OpenSSH options again, with a twist. As observed in 94b8ae5a, we cannot assume that $GIT_SSH always handles OpenSSH options: common helpers such as travis-ci's dpl[*] are configured using GIT_SSH and do not accept OpenSSH options. So make the default a new variant "auto", with the following behavior: 1. First, check for a recognized basename, like today. 2. If the basename is not recognized, check whether $GIT_SSH supports OpenSSH options by running $GIT_SSH -G <options> <host> This returns status 0 and prints configuration in OpenSSH if it recognizes all <options> and returns status 255 if it encounters an unrecognized option. A wrapper script like exec ssh -- "$@" would fail with ssh: Could not resolve hostname -g: Name or service not known , correctly reflecting that it does not support OpenSSH options. The command is run with stdin, stdout, and stderr redirected to /dev/null so even a command that expects a terminal would exit immediately. 3. Based on the result from step (2), behave like "ssh" (if it succeeded) or "simple" (if it failed). This way, the default ssh variant for unrecognized commands can handle both the repo and dpl cases as intended. This autodetection has been running on Google workstations since 2017-10-23 with no reported negative effects. [*] https://github.com/travis-ci/dpl/blob/6c3fddfda1f2a85944c544446b068bac0a77c049/lib/dpl/provider.rb#L215 Reported-by: William Yan <wyan@google.com> Improved-by: Jonathan Tan <jonathantanmy@google.com> Signed-off-by: Jonathan Nieder <jrnieder@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2017-11-20 22:30:04 +01:00
if (!strcmp(variant, "auto"))
*ssh_variant = VARIANT_AUTO;
else if (!strcmp(variant, "plink"))
ssh: introduce a 'simple' ssh variant When using the 'ssh' transport, the '-o' option is used to specify an environment variable which should be set on the remote end. This allows git to send additional information when contacting the server, requesting the use of a different protocol version via the 'GIT_PROTOCOL' environment variable like so: "-o SendEnv=GIT_PROTOCOL". Unfortunately not all ssh variants support the sending of environment variables to the remote end. To account for this, only use the '-o' option for ssh variants which are OpenSSH compliant. This is done by checking that the basename of the ssh command is 'ssh' or the ssh variant is overridden to be 'ssh' (via the ssh.variant config). Other options like '-p' and '-P', which are used to specify a specific port to use, or '-4' and '-6', which are used to indicate that IPV4 or IPV6 addresses should be used, may also not be supported by all ssh variants. Currently if an ssh command's basename wasn't 'plink' or 'tortoiseplink' git assumes that the command is an OpenSSH variant. Since user configured ssh commands may not be OpenSSH compliant, tighten this constraint and assume a variant of 'simple' if the basename of the command doesn't match the variants known to git. The new ssh variant 'simple' will only have the host and command to execute ([username@]host command) passed as parameters to the ssh command. Update the Documentation to better reflect the command-line options sent to ssh commands based on their variant. Reported-by: Jeffrey Yasskin <jyasskin@google.com> Signed-off-by: Brandon Williams <bmwill@google.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2017-10-16 19:55:31 +02:00
*ssh_variant = VARIANT_PLINK;
else if (!strcmp(variant, "putty"))
*ssh_variant = VARIANT_PUTTY;
else if (!strcmp(variant, "tortoiseplink"))
*ssh_variant = VARIANT_TORTOISEPLINK;
else if (!strcmp(variant, "simple"))
*ssh_variant = VARIANT_SIMPLE;
else
*ssh_variant = VARIANT_SSH;
connect.c: stop conflating ssh command names and overrides dd33e07766 ("connect: Add the envvar GIT_SSH_VARIANT and ssh.variant config", 2017-02-01) attempted to add support for configuration and environment variable to override the different handling of port_option and needs_batch settings suitable for variants of the ssh implementation that was autodetected by looking at the ssh command name. Because it piggybacked on the code that turns command name to specific override (e.g. "plink.exe" and "plink" means port_option needs to be set to 'P' instead of the default 'p'), yet it defined a separate namespace for these overrides (e.g. "putty" can be usable to signal that port_option needs to be 'P'), however, it made the auto-detection based on the command name less robust (e.g. the code now accepts "putty" as a SSH command name and applies the same override). Separate the code that interprets the override that was read from the configuration & environment from the original code that handles the command names, as they are in separate namespaces, to fix this confusion. This incidentally also makes it easier for future enhancement of the override syntax (e.g. "port_option=p,needs_batch=1" may want to be accepted as a more explicit syntax) without affecting the code for auto-detection based on the command name. While at it, update the return type of the handle_ssh_variant() helper function to void; the caller does not use it, and the function does not return any meaningful value. Signed-off-by: Junio C Hamano <gitster@pobox.com>
2017-02-09 18:20:25 +01:00
}
ssh: introduce a 'simple' ssh variant When using the 'ssh' transport, the '-o' option is used to specify an environment variable which should be set on the remote end. This allows git to send additional information when contacting the server, requesting the use of a different protocol version via the 'GIT_PROTOCOL' environment variable like so: "-o SendEnv=GIT_PROTOCOL". Unfortunately not all ssh variants support the sending of environment variables to the remote end. To account for this, only use the '-o' option for ssh variants which are OpenSSH compliant. This is done by checking that the basename of the ssh command is 'ssh' or the ssh variant is overridden to be 'ssh' (via the ssh.variant config). Other options like '-p' and '-P', which are used to specify a specific port to use, or '-4' and '-6', which are used to indicate that IPV4 or IPV6 addresses should be used, may also not be supported by all ssh variants. Currently if an ssh command's basename wasn't 'plink' or 'tortoiseplink' git assumes that the command is an OpenSSH variant. Since user configured ssh commands may not be OpenSSH compliant, tighten this constraint and assume a variant of 'simple' if the basename of the command doesn't match the variants known to git. The new ssh variant 'simple' will only have the host and command to execute ([username@]host command) passed as parameters to the ssh command. Update the Documentation to better reflect the command-line options sent to ssh commands based on their variant. Reported-by: Jeffrey Yasskin <jyasskin@google.com> Signed-off-by: Brandon Williams <bmwill@google.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2017-10-16 19:55:31 +02:00
static enum ssh_variant determine_ssh_variant(const char *ssh_command,
int is_cmdline)
connect.c: stop conflating ssh command names and overrides dd33e07766 ("connect: Add the envvar GIT_SSH_VARIANT and ssh.variant config", 2017-02-01) attempted to add support for configuration and environment variable to override the different handling of port_option and needs_batch settings suitable for variants of the ssh implementation that was autodetected by looking at the ssh command name. Because it piggybacked on the code that turns command name to specific override (e.g. "plink.exe" and "plink" means port_option needs to be set to 'P' instead of the default 'p'), yet it defined a separate namespace for these overrides (e.g. "putty" can be usable to signal that port_option needs to be 'P'), however, it made the auto-detection based on the command name less robust (e.g. the code now accepts "putty" as a SSH command name and applies the same override). Separate the code that interprets the override that was read from the configuration & environment from the original code that handles the command names, as they are in separate namespaces, to fix this confusion. This incidentally also makes it easier for future enhancement of the override syntax (e.g. "port_option=p,needs_batch=1" may want to be accepted as a more explicit syntax) without affecting the code for auto-detection based on the command name. While at it, update the return type of the handle_ssh_variant() helper function to void; the caller does not use it, and the function does not return any meaningful value. Signed-off-by: Junio C Hamano <gitster@pobox.com>
2017-02-09 18:20:25 +01:00
{
ssh: 'auto' variant to select between 'ssh' and 'simple' Android's "repo" tool is a tool for managing a large codebase consisting of multiple smaller repositories, similar to Git's submodule feature. Starting with Git 94b8ae5a (ssh: introduce a 'simple' ssh variant, 2017-10-16), users noticed that it stopped handling the port in ssh:// URLs. The cause: when it encounters ssh:// URLs, repo pre-connects to the server and sets GIT_SSH to a helper ".repo/repo/git_ssh" that reuses that connection. Before 94b8ae5a, the helper was assumed to support OpenSSH options for lack of a better guess and got passed a -p option to set the port. After that patch, it uses the new default of a simple helper that does not accept an option to set the port. The next release of "repo" will set GIT_SSH_VARIANT to "ssh" to avoid that. But users of old versions and of other similar GIT_SSH implementations would not get the benefit of that fix. So update the default to use OpenSSH options again, with a twist. As observed in 94b8ae5a, we cannot assume that $GIT_SSH always handles OpenSSH options: common helpers such as travis-ci's dpl[*] are configured using GIT_SSH and do not accept OpenSSH options. So make the default a new variant "auto", with the following behavior: 1. First, check for a recognized basename, like today. 2. If the basename is not recognized, check whether $GIT_SSH supports OpenSSH options by running $GIT_SSH -G <options> <host> This returns status 0 and prints configuration in OpenSSH if it recognizes all <options> and returns status 255 if it encounters an unrecognized option. A wrapper script like exec ssh -- "$@" would fail with ssh: Could not resolve hostname -g: Name or service not known , correctly reflecting that it does not support OpenSSH options. The command is run with stdin, stdout, and stderr redirected to /dev/null so even a command that expects a terminal would exit immediately. 3. Based on the result from step (2), behave like "ssh" (if it succeeded) or "simple" (if it failed). This way, the default ssh variant for unrecognized commands can handle both the repo and dpl cases as intended. This autodetection has been running on Google workstations since 2017-10-23 with no reported negative effects. [*] https://github.com/travis-ci/dpl/blob/6c3fddfda1f2a85944c544446b068bac0a77c049/lib/dpl/provider.rb#L215 Reported-by: William Yan <wyan@google.com> Improved-by: Jonathan Tan <jonathantanmy@google.com> Signed-off-by: Jonathan Nieder <jrnieder@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2017-11-20 22:30:04 +01:00
enum ssh_variant ssh_variant = VARIANT_AUTO;
connect.c: stop conflating ssh command names and overrides dd33e07766 ("connect: Add the envvar GIT_SSH_VARIANT and ssh.variant config", 2017-02-01) attempted to add support for configuration and environment variable to override the different handling of port_option and needs_batch settings suitable for variants of the ssh implementation that was autodetected by looking at the ssh command name. Because it piggybacked on the code that turns command name to specific override (e.g. "plink.exe" and "plink" means port_option needs to be set to 'P' instead of the default 'p'), yet it defined a separate namespace for these overrides (e.g. "putty" can be usable to signal that port_option needs to be 'P'), however, it made the auto-detection based on the command name less robust (e.g. the code now accepts "putty" as a SSH command name and applies the same override). Separate the code that interprets the override that was read from the configuration & environment from the original code that handles the command names, as they are in separate namespaces, to fix this confusion. This incidentally also makes it easier for future enhancement of the override syntax (e.g. "port_option=p,needs_batch=1" may want to be accepted as a more explicit syntax) without affecting the code for auto-detection based on the command name. While at it, update the return type of the handle_ssh_variant() helper function to void; the caller does not use it, and the function does not return any meaningful value. Signed-off-by: Junio C Hamano <gitster@pobox.com>
2017-02-09 18:20:25 +01:00
const char *variant;
char *p = NULL;
ssh: 'auto' variant to select between 'ssh' and 'simple' Android's "repo" tool is a tool for managing a large codebase consisting of multiple smaller repositories, similar to Git's submodule feature. Starting with Git 94b8ae5a (ssh: introduce a 'simple' ssh variant, 2017-10-16), users noticed that it stopped handling the port in ssh:// URLs. The cause: when it encounters ssh:// URLs, repo pre-connects to the server and sets GIT_SSH to a helper ".repo/repo/git_ssh" that reuses that connection. Before 94b8ae5a, the helper was assumed to support OpenSSH options for lack of a better guess and got passed a -p option to set the port. After that patch, it uses the new default of a simple helper that does not accept an option to set the port. The next release of "repo" will set GIT_SSH_VARIANT to "ssh" to avoid that. But users of old versions and of other similar GIT_SSH implementations would not get the benefit of that fix. So update the default to use OpenSSH options again, with a twist. As observed in 94b8ae5a, we cannot assume that $GIT_SSH always handles OpenSSH options: common helpers such as travis-ci's dpl[*] are configured using GIT_SSH and do not accept OpenSSH options. So make the default a new variant "auto", with the following behavior: 1. First, check for a recognized basename, like today. 2. If the basename is not recognized, check whether $GIT_SSH supports OpenSSH options by running $GIT_SSH -G <options> <host> This returns status 0 and prints configuration in OpenSSH if it recognizes all <options> and returns status 255 if it encounters an unrecognized option. A wrapper script like exec ssh -- "$@" would fail with ssh: Could not resolve hostname -g: Name or service not known , correctly reflecting that it does not support OpenSSH options. The command is run with stdin, stdout, and stderr redirected to /dev/null so even a command that expects a terminal would exit immediately. 3. Based on the result from step (2), behave like "ssh" (if it succeeded) or "simple" (if it failed). This way, the default ssh variant for unrecognized commands can handle both the repo and dpl cases as intended. This autodetection has been running on Google workstations since 2017-10-23 with no reported negative effects. [*] https://github.com/travis-ci/dpl/blob/6c3fddfda1f2a85944c544446b068bac0a77c049/lib/dpl/provider.rb#L215 Reported-by: William Yan <wyan@google.com> Improved-by: Jonathan Tan <jonathantanmy@google.com> Signed-off-by: Jonathan Nieder <jrnieder@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2017-11-20 22:30:04 +01:00
override_ssh_variant(&ssh_variant);
if (ssh_variant != VARIANT_AUTO)
ssh: introduce a 'simple' ssh variant When using the 'ssh' transport, the '-o' option is used to specify an environment variable which should be set on the remote end. This allows git to send additional information when contacting the server, requesting the use of a different protocol version via the 'GIT_PROTOCOL' environment variable like so: "-o SendEnv=GIT_PROTOCOL". Unfortunately not all ssh variants support the sending of environment variables to the remote end. To account for this, only use the '-o' option for ssh variants which are OpenSSH compliant. This is done by checking that the basename of the ssh command is 'ssh' or the ssh variant is overridden to be 'ssh' (via the ssh.variant config). Other options like '-p' and '-P', which are used to specify a specific port to use, or '-4' and '-6', which are used to indicate that IPV4 or IPV6 addresses should be used, may also not be supported by all ssh variants. Currently if an ssh command's basename wasn't 'plink' or 'tortoiseplink' git assumes that the command is an OpenSSH variant. Since user configured ssh commands may not be OpenSSH compliant, tighten this constraint and assume a variant of 'simple' if the basename of the command doesn't match the variants known to git. The new ssh variant 'simple' will only have the host and command to execute ([username@]host command) passed as parameters to the ssh command. Update the Documentation to better reflect the command-line options sent to ssh commands based on their variant. Reported-by: Jeffrey Yasskin <jyasskin@google.com> Signed-off-by: Brandon Williams <bmwill@google.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2017-10-16 19:55:31 +02:00
return ssh_variant;
connect.c: stop conflating ssh command names and overrides dd33e07766 ("connect: Add the envvar GIT_SSH_VARIANT and ssh.variant config", 2017-02-01) attempted to add support for configuration and environment variable to override the different handling of port_option and needs_batch settings suitable for variants of the ssh implementation that was autodetected by looking at the ssh command name. Because it piggybacked on the code that turns command name to specific override (e.g. "plink.exe" and "plink" means port_option needs to be set to 'P' instead of the default 'p'), yet it defined a separate namespace for these overrides (e.g. "putty" can be usable to signal that port_option needs to be 'P'), however, it made the auto-detection based on the command name less robust (e.g. the code now accepts "putty" as a SSH command name and applies the same override). Separate the code that interprets the override that was read from the configuration & environment from the original code that handles the command names, as they are in separate namespaces, to fix this confusion. This incidentally also makes it easier for future enhancement of the override syntax (e.g. "port_option=p,needs_batch=1" may want to be accepted as a more explicit syntax) without affecting the code for auto-detection based on the command name. While at it, update the return type of the handle_ssh_variant() helper function to void; the caller does not use it, and the function does not return any meaningful value. Signed-off-by: Junio C Hamano <gitster@pobox.com>
2017-02-09 18:20:25 +01:00
if (!is_cmdline) {
p = xstrdup(ssh_command);
variant = basename(p);
} else {
const char **ssh_argv;
p = xstrdup(ssh_command);
if (split_cmdline(p, &ssh_argv) > 0) {
variant = basename((char *)ssh_argv[0]);
/*
* At this point, variant points into the buffer
* referenced by p, hence we do not need ssh_argv
* any longer.
*/
free(ssh_argv);
} else {
free(p);
ssh: introduce a 'simple' ssh variant When using the 'ssh' transport, the '-o' option is used to specify an environment variable which should be set on the remote end. This allows git to send additional information when contacting the server, requesting the use of a different protocol version via the 'GIT_PROTOCOL' environment variable like so: "-o SendEnv=GIT_PROTOCOL". Unfortunately not all ssh variants support the sending of environment variables to the remote end. To account for this, only use the '-o' option for ssh variants which are OpenSSH compliant. This is done by checking that the basename of the ssh command is 'ssh' or the ssh variant is overridden to be 'ssh' (via the ssh.variant config). Other options like '-p' and '-P', which are used to specify a specific port to use, or '-4' and '-6', which are used to indicate that IPV4 or IPV6 addresses should be used, may also not be supported by all ssh variants. Currently if an ssh command's basename wasn't 'plink' or 'tortoiseplink' git assumes that the command is an OpenSSH variant. Since user configured ssh commands may not be OpenSSH compliant, tighten this constraint and assume a variant of 'simple' if the basename of the command doesn't match the variants known to git. The new ssh variant 'simple' will only have the host and command to execute ([username@]host command) passed as parameters to the ssh command. Update the Documentation to better reflect the command-line options sent to ssh commands based on their variant. Reported-by: Jeffrey Yasskin <jyasskin@google.com> Signed-off-by: Brandon Williams <bmwill@google.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2017-10-16 19:55:31 +02:00
return ssh_variant;
}
}
ssh: introduce a 'simple' ssh variant When using the 'ssh' transport, the '-o' option is used to specify an environment variable which should be set on the remote end. This allows git to send additional information when contacting the server, requesting the use of a different protocol version via the 'GIT_PROTOCOL' environment variable like so: "-o SendEnv=GIT_PROTOCOL". Unfortunately not all ssh variants support the sending of environment variables to the remote end. To account for this, only use the '-o' option for ssh variants which are OpenSSH compliant. This is done by checking that the basename of the ssh command is 'ssh' or the ssh variant is overridden to be 'ssh' (via the ssh.variant config). Other options like '-p' and '-P', which are used to specify a specific port to use, or '-4' and '-6', which are used to indicate that IPV4 or IPV6 addresses should be used, may also not be supported by all ssh variants. Currently if an ssh command's basename wasn't 'plink' or 'tortoiseplink' git assumes that the command is an OpenSSH variant. Since user configured ssh commands may not be OpenSSH compliant, tighten this constraint and assume a variant of 'simple' if the basename of the command doesn't match the variants known to git. The new ssh variant 'simple' will only have the host and command to execute ([username@]host command) passed as parameters to the ssh command. Update the Documentation to better reflect the command-line options sent to ssh commands based on their variant. Reported-by: Jeffrey Yasskin <jyasskin@google.com> Signed-off-by: Brandon Williams <bmwill@google.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2017-10-16 19:55:31 +02:00
if (!strcasecmp(variant, "ssh") ||
!strcasecmp(variant, "ssh.exe"))
ssh_variant = VARIANT_SSH;
else if (!strcasecmp(variant, "plink") ||
!strcasecmp(variant, "plink.exe"))
ssh_variant = VARIANT_PLINK;
else if (!strcasecmp(variant, "tortoiseplink") ||
ssh: introduce a 'simple' ssh variant When using the 'ssh' transport, the '-o' option is used to specify an environment variable which should be set on the remote end. This allows git to send additional information when contacting the server, requesting the use of a different protocol version via the 'GIT_PROTOCOL' environment variable like so: "-o SendEnv=GIT_PROTOCOL". Unfortunately not all ssh variants support the sending of environment variables to the remote end. To account for this, only use the '-o' option for ssh variants which are OpenSSH compliant. This is done by checking that the basename of the ssh command is 'ssh' or the ssh variant is overridden to be 'ssh' (via the ssh.variant config). Other options like '-p' and '-P', which are used to specify a specific port to use, or '-4' and '-6', which are used to indicate that IPV4 or IPV6 addresses should be used, may also not be supported by all ssh variants. Currently if an ssh command's basename wasn't 'plink' or 'tortoiseplink' git assumes that the command is an OpenSSH variant. Since user configured ssh commands may not be OpenSSH compliant, tighten this constraint and assume a variant of 'simple' if the basename of the command doesn't match the variants known to git. The new ssh variant 'simple' will only have the host and command to execute ([username@]host command) passed as parameters to the ssh command. Update the Documentation to better reflect the command-line options sent to ssh commands based on their variant. Reported-by: Jeffrey Yasskin <jyasskin@google.com> Signed-off-by: Brandon Williams <bmwill@google.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2017-10-16 19:55:31 +02:00
!strcasecmp(variant, "tortoiseplink.exe"))
ssh_variant = VARIANT_TORTOISEPLINK;
free(p);
ssh: introduce a 'simple' ssh variant When using the 'ssh' transport, the '-o' option is used to specify an environment variable which should be set on the remote end. This allows git to send additional information when contacting the server, requesting the use of a different protocol version via the 'GIT_PROTOCOL' environment variable like so: "-o SendEnv=GIT_PROTOCOL". Unfortunately not all ssh variants support the sending of environment variables to the remote end. To account for this, only use the '-o' option for ssh variants which are OpenSSH compliant. This is done by checking that the basename of the ssh command is 'ssh' or the ssh variant is overridden to be 'ssh' (via the ssh.variant config). Other options like '-p' and '-P', which are used to specify a specific port to use, or '-4' and '-6', which are used to indicate that IPV4 or IPV6 addresses should be used, may also not be supported by all ssh variants. Currently if an ssh command's basename wasn't 'plink' or 'tortoiseplink' git assumes that the command is an OpenSSH variant. Since user configured ssh commands may not be OpenSSH compliant, tighten this constraint and assume a variant of 'simple' if the basename of the command doesn't match the variants known to git. The new ssh variant 'simple' will only have the host and command to execute ([username@]host command) passed as parameters to the ssh command. Update the Documentation to better reflect the command-line options sent to ssh commands based on their variant. Reported-by: Jeffrey Yasskin <jyasskin@google.com> Signed-off-by: Brandon Williams <bmwill@google.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2017-10-16 19:55:31 +02:00
return ssh_variant;
}
/*
* Open a connection using Git's native protocol.
*
* The caller is responsible for freeing hostandport, but this function may
* modify it (for example, to truncate it to remove the port part).
*/
static struct child_process *git_connect_git(int fd[2], char *hostandport,
const char *path, const char *prog,
int flags)
{
struct child_process *conn;
struct strbuf request = STRBUF_INIT;
/*
* Set up virtual host information based on where we will
* connect, unless the user has overridden us in
* the environment.
*/
char *target_host = getenv("GIT_OVERRIDE_VIRTUAL_HOST");
if (target_host)
target_host = xstrdup(target_host);
else
target_host = xstrdup(hostandport);
transport_check_allowed("git");
/*
* These underlying connection commands die() if they
* cannot connect.
*/
if (git_use_proxy(hostandport))
conn = git_proxy_connect(fd, hostandport);
else
conn = git_tcp_connect(fd, hostandport, flags);
/*
* Separate original protocol components prog and path
* from extended host header with a NUL byte.
*
* Note: Do not add any other headers here! Doing so
* will cause older git-daemon servers to crash.
*/
strbuf_addf(&request,
"%s %s%chost=%s%c",
prog, path, 0,
target_host, 0);
/* If using a new version put that stuff here after a second null byte */
if (get_protocol_version_config() > 0) {
strbuf_addch(&request, '\0');
strbuf_addf(&request, "version=%d%c",
get_protocol_version_config(), '\0');
}
packet_write(fd[1], request.buf, request.len);
free(target_host);
strbuf_release(&request);
return conn;
}
/*
* Append the appropriate environment variables to `env` and options to
* `args` for running ssh in Git's SSH-tunneled transport.
*/
static void push_ssh_options(struct argv_array *args, struct argv_array *env,
enum ssh_variant variant, const char *port,
int flags)
{
if (variant == VARIANT_SSH &&
get_protocol_version_config() > 0) {
argv_array_push(args, "-o");
argv_array_push(args, "SendEnv=" GIT_PROTOCOL_ENVIRONMENT);
argv_array_pushf(env, GIT_PROTOCOL_ENVIRONMENT "=version=%d",
get_protocol_version_config());
}
if (flags & CONNECT_IPV4) {
switch (variant) {
case VARIANT_AUTO:
BUG("VARIANT_AUTO passed to push_ssh_options");
case VARIANT_SIMPLE:
die("ssh variant 'simple' does not support -4");
case VARIANT_SSH:
case VARIANT_PLINK:
case VARIANT_PUTTY:
case VARIANT_TORTOISEPLINK:
argv_array_push(args, "-4");
}
} else if (flags & CONNECT_IPV6) {
switch (variant) {
case VARIANT_AUTO:
BUG("VARIANT_AUTO passed to push_ssh_options");
case VARIANT_SIMPLE:
die("ssh variant 'simple' does not support -6");
case VARIANT_SSH:
case VARIANT_PLINK:
case VARIANT_PUTTY:
case VARIANT_TORTOISEPLINK:
argv_array_push(args, "-6");
}
}
if (variant == VARIANT_TORTOISEPLINK)
argv_array_push(args, "-batch");
if (port) {
switch (variant) {
case VARIANT_AUTO:
BUG("VARIANT_AUTO passed to push_ssh_options");
case VARIANT_SIMPLE:
die("ssh variant 'simple' does not support setting port");
case VARIANT_SSH:
argv_array_push(args, "-p");
break;
case VARIANT_PLINK:
case VARIANT_PUTTY:
case VARIANT_TORTOISEPLINK:
argv_array_push(args, "-P");
}
argv_array_push(args, port);
}
}
/* Prepare a child_process for use by Git's SSH-tunneled transport. */
static void fill_ssh_args(struct child_process *conn, const char *ssh_host,
const char *port, int flags)
{
const char *ssh;
enum ssh_variant variant;
if (looks_like_command_line_option(ssh_host))
die("strange hostname '%s' blocked", ssh_host);
ssh = get_ssh_command();
if (ssh) {
variant = determine_ssh_variant(ssh, 1);
} else {
/*
* GIT_SSH is the no-shell version of
* GIT_SSH_COMMAND (and must remain so for
* historical compatibility).
*/
conn->use_shell = 0;
ssh = getenv("GIT_SSH");
if (!ssh)
ssh = "ssh";
variant = determine_ssh_variant(ssh, 0);
}
ssh: 'auto' variant to select between 'ssh' and 'simple' Android's "repo" tool is a tool for managing a large codebase consisting of multiple smaller repositories, similar to Git's submodule feature. Starting with Git 94b8ae5a (ssh: introduce a 'simple' ssh variant, 2017-10-16), users noticed that it stopped handling the port in ssh:// URLs. The cause: when it encounters ssh:// URLs, repo pre-connects to the server and sets GIT_SSH to a helper ".repo/repo/git_ssh" that reuses that connection. Before 94b8ae5a, the helper was assumed to support OpenSSH options for lack of a better guess and got passed a -p option to set the port. After that patch, it uses the new default of a simple helper that does not accept an option to set the port. The next release of "repo" will set GIT_SSH_VARIANT to "ssh" to avoid that. But users of old versions and of other similar GIT_SSH implementations would not get the benefit of that fix. So update the default to use OpenSSH options again, with a twist. As observed in 94b8ae5a, we cannot assume that $GIT_SSH always handles OpenSSH options: common helpers such as travis-ci's dpl[*] are configured using GIT_SSH and do not accept OpenSSH options. So make the default a new variant "auto", with the following behavior: 1. First, check for a recognized basename, like today. 2. If the basename is not recognized, check whether $GIT_SSH supports OpenSSH options by running $GIT_SSH -G <options> <host> This returns status 0 and prints configuration in OpenSSH if it recognizes all <options> and returns status 255 if it encounters an unrecognized option. A wrapper script like exec ssh -- "$@" would fail with ssh: Could not resolve hostname -g: Name or service not known , correctly reflecting that it does not support OpenSSH options. The command is run with stdin, stdout, and stderr redirected to /dev/null so even a command that expects a terminal would exit immediately. 3. Based on the result from step (2), behave like "ssh" (if it succeeded) or "simple" (if it failed). This way, the default ssh variant for unrecognized commands can handle both the repo and dpl cases as intended. This autodetection has been running on Google workstations since 2017-10-23 with no reported negative effects. [*] https://github.com/travis-ci/dpl/blob/6c3fddfda1f2a85944c544446b068bac0a77c049/lib/dpl/provider.rb#L215 Reported-by: William Yan <wyan@google.com> Improved-by: Jonathan Tan <jonathantanmy@google.com> Signed-off-by: Jonathan Nieder <jrnieder@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2017-11-20 22:30:04 +01:00
if (variant == VARIANT_AUTO) {
struct child_process detect = CHILD_PROCESS_INIT;
detect.use_shell = conn->use_shell;
detect.no_stdin = detect.no_stdout = detect.no_stderr = 1;
argv_array_push(&detect.args, ssh);
argv_array_push(&detect.args, "-G");
push_ssh_options(&detect.args, &detect.env_array,
VARIANT_SSH, port, flags);
argv_array_push(&detect.args, ssh_host);
variant = run_command(&detect) ? VARIANT_SIMPLE : VARIANT_SSH;
}
argv_array_push(&conn->args, ssh);
push_ssh_options(&conn->args, &conn->env_array, variant, port, flags);
argv_array_push(&conn->args, ssh_host);
}
/*
* This returns the dummy child_process `no_fork` if the transport protocol
* does not need fork(2), or a struct child_process object if it does. Once
* done, finish the connection with finish_connect() with the value returned
* from this function (it is safe to call finish_connect() with NULL to
* support the former case).
*
* If it returns, the connect is successful; it just dies on errors (this
* will hopefully be changed in a libification effort, to return NULL when
* the connection failed).
*/
struct child_process *git_connect(int fd[2], const char *url,
const char *prog, int flags)
{
char *hostandport, *path;
struct child_process *conn;
enum protocol protocol;
/* Without this we cannot rely on waitpid() to tell
* what happened to our children.
*/
signal(SIGCHLD, SIG_DFL);
protocol = parse_connect_url(url, &hostandport, &path);
if ((flags & CONNECT_DIAG_URL) && (protocol != PROTO_SSH)) {
printf("Diag: url=%s\n", url ? url : "NULL");
printf("Diag: protocol=%s\n", prot_name(protocol));
printf("Diag: hostandport=%s\n", hostandport ? hostandport : "NULL");
printf("Diag: path=%s\n", path ? path : "NULL");
conn = NULL;
} else if (protocol == PROTO_GIT) {
conn = git_connect_git(fd, hostandport, path, prog, flags);
} else {
struct strbuf cmd = STRBUF_INIT;
connect: tell server that the client understands v1 Teach the connection logic to tell a serve that it understands protocol v1. This is done in 2 different ways for the builtin transports, both of which ultimately set 'GIT_PROTOCOL' to 'version=1' on the server. 1. git:// A normal request to git-daemon is structured as "command path/to/repo\0host=..\0" and due to a bug introduced in 49ba83fb6 (Add virtualization support to git-daemon, 2006-09-19) we aren't able to place any extra arguments (separated by NULs) besides the host otherwise the parsing of those arguments would enter an infinite loop. This bug was fixed in 73bb33a94 (daemon: Strictly parse the "extra arg" part of the command, 2009-06-04) but a check was put in place to disallow extra arguments so that new clients wouldn't trigger this bug in older servers. In order to get around this limitation git-daemon was taught to recognize additional request arguments hidden behind a second NUL byte. Requests can then be structured like: "command path/to/repo\0host=..\0\0version=1\0key=value\0". git-daemon can then parse out the extra arguments and set 'GIT_PROTOCOL' accordingly. By placing these extra arguments behind a second NUL byte we can skirt around both the infinite loop bug in 49ba83fb6 (Add virtualization support to git-daemon, 2006-09-19) as well as the explicit disallowing of extra arguments introduced in 73bb33a94 (daemon: Strictly parse the "extra arg" part of the command, 2009-06-04) because both of these versions of git-daemon check for a single NUL byte after the host argument before terminating the argument parsing. 2. ssh://, file:// Set 'GIT_PROTOCOL' environment variable with the desired protocol version. With the file:// transport, 'GIT_PROTOCOL' can be set explicitly in the locally running git-upload-pack or git-receive-pack processes. With the ssh:// transport and OpenSSH compliant ssh programs, 'GIT_PROTOCOL' can be sent across ssh by using '-o SendEnv=GIT_PROTOCOL' and having the server whitelist this environment variable. Signed-off-by: Brandon Williams <bmwill@google.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2017-10-16 19:55:28 +02:00
const char *const *var;
conn = xmalloc(sizeof(*conn));
child_process_init(conn);
if (looks_like_command_line_option(path))
die("strange pathname '%s' blocked", path);
strbuf_addstr(&cmd, prog);
strbuf_addch(&cmd, ' ');
sq_quote_buf(&cmd, path);
/* remove repo-local variables from the environment */
connect: tell server that the client understands v1 Teach the connection logic to tell a serve that it understands protocol v1. This is done in 2 different ways for the builtin transports, both of which ultimately set 'GIT_PROTOCOL' to 'version=1' on the server. 1. git:// A normal request to git-daemon is structured as "command path/to/repo\0host=..\0" and due to a bug introduced in 49ba83fb6 (Add virtualization support to git-daemon, 2006-09-19) we aren't able to place any extra arguments (separated by NULs) besides the host otherwise the parsing of those arguments would enter an infinite loop. This bug was fixed in 73bb33a94 (daemon: Strictly parse the "extra arg" part of the command, 2009-06-04) but a check was put in place to disallow extra arguments so that new clients wouldn't trigger this bug in older servers. In order to get around this limitation git-daemon was taught to recognize additional request arguments hidden behind a second NUL byte. Requests can then be structured like: "command path/to/repo\0host=..\0\0version=1\0key=value\0". git-daemon can then parse out the extra arguments and set 'GIT_PROTOCOL' accordingly. By placing these extra arguments behind a second NUL byte we can skirt around both the infinite loop bug in 49ba83fb6 (Add virtualization support to git-daemon, 2006-09-19) as well as the explicit disallowing of extra arguments introduced in 73bb33a94 (daemon: Strictly parse the "extra arg" part of the command, 2009-06-04) because both of these versions of git-daemon check for a single NUL byte after the host argument before terminating the argument parsing. 2. ssh://, file:// Set 'GIT_PROTOCOL' environment variable with the desired protocol version. With the file:// transport, 'GIT_PROTOCOL' can be set explicitly in the locally running git-upload-pack or git-receive-pack processes. With the ssh:// transport and OpenSSH compliant ssh programs, 'GIT_PROTOCOL' can be sent across ssh by using '-o SendEnv=GIT_PROTOCOL' and having the server whitelist this environment variable. Signed-off-by: Brandon Williams <bmwill@google.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2017-10-16 19:55:28 +02:00
for (var = local_repo_env; *var; var++)
argv_array_push(&conn->env_array, *var);
conn->use_shell = 1;
conn->in = conn->out = -1;
if (protocol == PROTO_SSH) {
char *ssh_host = hostandport;
const char *port = NULL;
transport: add a protocol-whitelist environment variable If we are cloning an untrusted remote repository into a sandbox, we may also want to fetch remote submodules in order to get the complete view as intended by the other side. However, that opens us up to attacks where a malicious user gets us to clone something they would not otherwise have access to (this is not necessarily a problem by itself, but we may then act on the cloned contents in a way that exposes them to the attacker). Ideally such a setup would sandbox git entirely away from high-value items, but this is not always practical or easy to set up (e.g., OS network controls may block multiple protocols, and we would want to enable some but not others). We can help this case by providing a way to restrict particular protocols. We use a whitelist in the environment. This is more annoying to set up than a blacklist, but defaults to safety if the set of protocols git supports grows). If no whitelist is specified, we continue to default to allowing all protocols (this is an "unsafe" default, but since the minority of users will want this sandboxing effect, it is the only sensible one). A note on the tests: ideally these would all be in a single test file, but the git-daemon and httpd test infrastructure is an all-or-nothing proposition rather than a test-by-test prerequisite. By putting them all together, we would be unable to test the file-local code on machines without apache. Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2015-09-16 19:12:52 +02:00
transport_check_allowed("ssh");
get_host_and_port(&ssh_host, &port);
if (!port)
port = get_port(ssh_host);
if (flags & CONNECT_DIAG_URL) {
printf("Diag: url=%s\n", url ? url : "NULL");
printf("Diag: protocol=%s\n", prot_name(protocol));
printf("Diag: userandhost=%s\n", ssh_host ? ssh_host : "NULL");
printf("Diag: port=%s\n", port ? port : "NONE");
printf("Diag: path=%s\n", path ? path : "NULL");
free(hostandport);
free(path);
free(conn);
strbuf_release(&cmd);
return NULL;
}
fill_ssh_args(conn, ssh_host, port, flags);
} else {
transport: add a protocol-whitelist environment variable If we are cloning an untrusted remote repository into a sandbox, we may also want to fetch remote submodules in order to get the complete view as intended by the other side. However, that opens us up to attacks where a malicious user gets us to clone something they would not otherwise have access to (this is not necessarily a problem by itself, but we may then act on the cloned contents in a way that exposes them to the attacker). Ideally such a setup would sandbox git entirely away from high-value items, but this is not always practical or easy to set up (e.g., OS network controls may block multiple protocols, and we would want to enable some but not others). We can help this case by providing a way to restrict particular protocols. We use a whitelist in the environment. This is more annoying to set up than a blacklist, but defaults to safety if the set of protocols git supports grows). If no whitelist is specified, we continue to default to allowing all protocols (this is an "unsafe" default, but since the minority of users will want this sandboxing effect, it is the only sensible one). A note on the tests: ideally these would all be in a single test file, but the git-daemon and httpd test infrastructure is an all-or-nothing proposition rather than a test-by-test prerequisite. By putting them all together, we would be unable to test the file-local code on machines without apache. Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2015-09-16 19:12:52 +02:00
transport_check_allowed("file");
connect: tell server that the client understands v1 Teach the connection logic to tell a serve that it understands protocol v1. This is done in 2 different ways for the builtin transports, both of which ultimately set 'GIT_PROTOCOL' to 'version=1' on the server. 1. git:// A normal request to git-daemon is structured as "command path/to/repo\0host=..\0" and due to a bug introduced in 49ba83fb6 (Add virtualization support to git-daemon, 2006-09-19) we aren't able to place any extra arguments (separated by NULs) besides the host otherwise the parsing of those arguments would enter an infinite loop. This bug was fixed in 73bb33a94 (daemon: Strictly parse the "extra arg" part of the command, 2009-06-04) but a check was put in place to disallow extra arguments so that new clients wouldn't trigger this bug in older servers. In order to get around this limitation git-daemon was taught to recognize additional request arguments hidden behind a second NUL byte. Requests can then be structured like: "command path/to/repo\0host=..\0\0version=1\0key=value\0". git-daemon can then parse out the extra arguments and set 'GIT_PROTOCOL' accordingly. By placing these extra arguments behind a second NUL byte we can skirt around both the infinite loop bug in 49ba83fb6 (Add virtualization support to git-daemon, 2006-09-19) as well as the explicit disallowing of extra arguments introduced in 73bb33a94 (daemon: Strictly parse the "extra arg" part of the command, 2009-06-04) because both of these versions of git-daemon check for a single NUL byte after the host argument before terminating the argument parsing. 2. ssh://, file:// Set 'GIT_PROTOCOL' environment variable with the desired protocol version. With the file:// transport, 'GIT_PROTOCOL' can be set explicitly in the locally running git-upload-pack or git-receive-pack processes. With the ssh:// transport and OpenSSH compliant ssh programs, 'GIT_PROTOCOL' can be sent across ssh by using '-o SendEnv=GIT_PROTOCOL' and having the server whitelist this environment variable. Signed-off-by: Brandon Williams <bmwill@google.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
2017-10-16 19:55:28 +02:00
if (get_protocol_version_config() > 0) {
argv_array_pushf(&conn->env_array, GIT_PROTOCOL_ENVIRONMENT "=version=%d",
get_protocol_version_config());
}
}
argv_array_push(&conn->args, cmd.buf);
if (start_command(conn))
die("unable to fork");
fd[0] = conn->out; /* read from child's stdout */
fd[1] = conn->in; /* write to child's stdin */
strbuf_release(&cmd);
}
free(hostandport);
free(path);
return conn;
}
int finish_connect(struct child_process *conn)
{
int code;
if (!conn || git_connection_is_socket(conn))
return 0;
code = finish_command(conn);
free(conn);
return code;
}