Smart fetch and push over HTTP: server side

Requests for $GIT_URL/git-receive-pack and $GIT_URL/git-upload-pack
are forwarded to the corresponding backend process by directly
executing it and leaving stdin and stdout connected to the invoking
web server.  Prior to starting the backend process the HTTP response
headers are sent, thereby freeing the backend from needing to know
about the HTTP protocol.

Requests that are encoded with Content-Encoding: gzip are
automatically inflated before being streamed into the backend.
This is primarily useful for the git-upload-pack backend, which
receives highly repetitive text data from clients that easily
compresses to 50% of its original size.

Signed-off-by: Shawn O. Pearce <spearce@spearce.org>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

diff --git a/Documentation/git-http-backend.txt b/Documentation/git-http-backend.txt
index 867675fcecc98280ac493f3c8fde0825bc432c05..022a2433a86a1939435b5d76a95daf39ff0a32e1 100644 (file)
--- a/Documentation/git-http-backend.txt
+++ b/Documentation/git-http-backend.txt
@@ -22,6 +22,23 @@ By default, only the `upload-pack` service is enabled, which serves
 This is ideally suited for read-only updates, i.e., pulling from
 git repositories.
 
 This is ideally suited for read-only updates, i.e., pulling from
 git repositories.
 

+SERVICES
+--------
+These services can be enabled/disabled using the per-repository
+configuration file:
+
+http.uploadpack::
+       This serves 'git-fetch-pack' and 'git-ls-remote' clients.
+       It is enabled by default, but a repository can disable it
+       by setting this configuration item to `false`.
+
+http.receivepack::
+       This serves 'git-send-pack' clients, allowing push.  It is
+       disabled by default for anonymous users, and enabled by
+       default for users authenticated by the web server.  It can be
+       disabled by setting this item to `false`, or enabled for all
+       users, including anonymous users, by setting it to `true`.
+

 URL TRANSLATION
 ---------------
 'git-http-backend' relies on the invoking web server to perform
 URL TRANSLATION
 ---------------
 'git-http-backend' relies on the invoking web server to perform


@@ -49,7 +66,19 @@ ScriptAlias /git/ /usr/libexec/git-core/git-http-backend/git/
 </Files>
 ----------------------------------------------------------------
 +
 </Files>
 ----------------------------------------------------------------
 +

-To require authentication for reads, use a Directory
+To enable anonymous read access but authenticated write access,
+require authorization with a LocationMatch directive:
++
+----------------------------------------------------------------
+<LocationMatch ".*/git-receive-pack$">
+       AuthType Basic
+       AuthName "Git Access"
+       Require group committers
+       ...
+</LocationMatch>
+----------------------------------------------------------------
++
+To require authentication for both reads and writes, use a Directory

 directive around the repository, or one of its parent directories:
 +
 ----------------------------------------------------------------
 directive around the repository, or one of its parent directories:
 +
 ----------------------------------------------------------------


@@ -92,6 +121,14 @@ by the invoking web server, including:
 * QUERY_STRING
 * REQUEST_METHOD
 
 * QUERY_STRING
 * REQUEST_METHOD
 

+The backend process sets GIT_COMMITTER_NAME to '$REMOTE_USER' and
+GIT_COMMITTER_EMAIL to '$\{REMOTE_USER}@http.$\{REMOTE_ADDR\}',
+ensuring that any reflogs created by 'git-receive-pack' contain some
+identifying information of the remote user who performed the push.
+
+All CGI environment variables are available to each of the hooks
+invoked by the 'git-receive-pack'.
+

 Author
 ------
 Written by Shawn O. Pearce <spearce@spearce.org>.
 Author
 ------
 Written by Shawn O. Pearce <spearce@spearce.org>.

diff --git a/http-backend.c b/http-backend.c
index 22bec56b980ebad9d620b619879e7ce8515bbf58..bfce52063f2dd31b56fb421acf6c4b4f856749d6 100644 (file)
--- a/http-backend.c
+++ b/http-backend.c
@@ -4,11 +4,109 @@
 #include "object.h"
 #include "tag.h"
 #include "exec_cmd.h"
 #include "object.h"
 #include "tag.h"
 #include "exec_cmd.h"

+#include "run-command.h"
+#include "string-list.h"

 
 static const char content_type[] = "Content-Type";
 static const char content_length[] = "Content-Length";
 static const char last_modified[] = "Last-Modified";
 
 
 static const char content_type[] = "Content-Type";
 static const char content_length[] = "Content-Length";
 static const char last_modified[] = "Last-Modified";
 

+static struct string_list *query_params;
+
+struct rpc_service {
+       const char *name;
+       const char *config_name;
+       signed enabled : 2;
+};
+
+static struct rpc_service rpc_service[] = {
+       { "upload-pack", "uploadpack", 1 },
+       { "receive-pack", "receivepack", -1 },
+};
+
+static int decode_char(const char *q)
+{
+       int i;
+       unsigned char val = 0;
+       for (i = 0; i < 2; i++) {
+               unsigned char c = *q++;
+               val <<= 4;
+               if (c >= '0' && c <= '9')
+                       val += c - '0';
+               else if (c >= 'a' && c <= 'f')
+                       val += c - 'a' + 10;
+               else if (c >= 'A' && c <= 'F')
+                       val += c - 'A' + 10;
+               else
+                       return -1;
+       }
+       return val;
+}
+
+static char *decode_parameter(const char **query, int is_name)
+{
+       const char *q = *query;
+       struct strbuf out;
+
+       strbuf_init(&out, 16);
+       do {
+               unsigned char c = *q;
+
+               if (!c)
+                       break;
+               if (c == '&' || (is_name && c == '=')) {
+                       q++;
+                       break;
+               }
+
+               if (c == '%') {
+                       int val = decode_char(q + 1);
+                       if (0 <= val) {
+                               strbuf_addch(&out, val);
+                               q += 3;
+                               continue;
+                       }
+               }
+
+               if (c == '+')
+                       strbuf_addch(&out, ' ');
+               else
+                       strbuf_addch(&out, c);
+               q++;
+       } while (1);
+       *query = q;
+       return strbuf_detach(&out, NULL);
+}
+
+static struct string_list *get_parameters(void)
+{
+       if (!query_params) {
+               const char *query = getenv("QUERY_STRING");
+
+               query_params = xcalloc(1, sizeof(*query_params));
+               while (query && *query) {
+                       char *name = decode_parameter(&query, 1);
+                       char *value = decode_parameter(&query, 0);
+                       struct string_list_item *i;
+
+                       i = string_list_lookup(name, query_params);
+                       if (!i)
+                               i = string_list_insert(name, query_params);
+                       else
+                               free(i->util);
+                       i->util = value;
+               }
+       }
+       return query_params;
+}
+
+static const char *get_parameter(const char *name)
+{
+       struct string_list_item *i;
+       i = string_list_lookup(name, get_parameters());
+       return i ? i->util : NULL;
+}
+

 static void format_write(int fd, const char *fmt, ...)
 {
        static char buffer[1024];
 static void format_write(int fd, const char *fmt, ...)
 {
        static char buffer[1024];


@@ -81,6 +179,21 @@ static NORETURN void not_found(const char *err, ...)
        exit(0);
 }
 
        exit(0);
 }
 

+static NORETURN void forbidden(const char *err, ...)
+{
+       va_list params;
+
+       http_status(403, "Forbidden");
+       hdr_nocache();
+       end_headers();
+
+       va_start(params, err);
+       if (err && *err)
+               vfprintf(stderr, err, params);
+       va_end(params);
+       exit(0);
+}
+

 static void send_strbuf(const char *type, struct strbuf *buf)
 {
        hdr_int(content_length, buf->len);
 static void send_strbuf(const char *type, struct strbuf *buf)
 {
        hdr_int(content_length, buf->len);


@@ -147,6 +260,145 @@ static void get_idx_file(char *name)
        send_file("application/x-git-packed-objects-toc", name);
 }
 
        send_file("application/x-git-packed-objects-toc", name);
 }
 

+static int http_config(const char *var, const char *value, void *cb)
+{
+       struct rpc_service *svc = cb;
+
+       if (!prefixcmp(var, "http.") &&
+           !strcmp(var + 5, svc->config_name)) {
+               svc->enabled = git_config_bool(var, value);
+               return 0;
+       }
+
+       /* we are not interested in parsing any other configuration here */
+       return 0;
+}
+
+static struct rpc_service *select_service(const char *name)
+{
+       struct rpc_service *svc = NULL;
+       int i;
+
+       if (prefixcmp(name, "git-"))
+               forbidden("Unsupported service: '%s'", name);
+
+       for (i = 0; i < ARRAY_SIZE(rpc_service); i++) {
+               struct rpc_service *s = &rpc_service[i];
+               if (!strcmp(s->name, name + 4)) {
+                       svc = s;
+                       break;
+               }
+       }
+
+       if (!svc)
+               forbidden("Unsupported service: '%s'", name);
+
+       git_config(http_config, svc);
+       if (svc->enabled < 0) {
+               const char *user = getenv("REMOTE_USER");
+               svc->enabled = (user && *user) ? 1 : 0;
+       }
+       if (!svc->enabled)
+               forbidden("Service not enabled: '%s'", svc->name);
+       return svc;
+}
+
+static void inflate_request(const char *prog_name, int out)
+{
+       z_stream stream;
+       unsigned char in_buf[8192];
+       unsigned char out_buf[8192];
+       unsigned long cnt = 0;
+       int ret;
+
+       memset(&stream, 0, sizeof(stream));
+       ret = inflateInit2(&stream, (15 + 16));
+       if (ret != Z_OK)
+               die("cannot start zlib inflater, zlib err %d", ret);
+
+       while (1) {
+               ssize_t n = xread(0, in_buf, sizeof(in_buf));
+               if (n <= 0)
+                       die("request ended in the middle of the gzip stream");
+
+               stream.next_in = in_buf;
+               stream.avail_in = n;
+
+               while (0 < stream.avail_in) {
+                       int ret;
+
+                       stream.next_out = out_buf;
+                       stream.avail_out = sizeof(out_buf);
+
+                       ret = inflate(&stream, Z_NO_FLUSH);
+                       if (ret != Z_OK && ret != Z_STREAM_END)
+                               die("zlib error inflating request, result %d", ret);
+
+                       n = stream.total_out - cnt;
+                       if (write_in_full(out, out_buf, n) != n)
+                               die("%s aborted reading request", prog_name);
+                       cnt += n;
+
+                       if (ret == Z_STREAM_END)
+                               goto done;
+               }
+       }
+
+done:
+       inflateEnd(&stream);
+       close(out);
+}
+
+static void run_service(const char **argv)
+{
+       const char *encoding = getenv("HTTP_CONTENT_ENCODING");
+       const char *user = getenv("REMOTE_USER");
+       const char *host = getenv("REMOTE_ADDR");
+       char *env[3];
+       struct strbuf buf = STRBUF_INIT;
+       int gzipped_request = 0;
+       struct child_process cld;
+
+       if (encoding && !strcmp(encoding, "gzip"))
+               gzipped_request = 1;
+       else if (encoding && !strcmp(encoding, "x-gzip"))
+               gzipped_request = 1;
+
+       if (!user || !*user)
+               user = "anonymous";
+       if (!host || !*host)
+               host = "(none)";
+
+       memset(&env, 0, sizeof(env));
+       strbuf_addf(&buf, "GIT_COMMITTER_NAME=%s", user);
+       env[0] = strbuf_detach(&buf, NULL);
+
+       strbuf_addf(&buf, "GIT_COMMITTER_EMAIL=%s@http.%s", user, host);
+       env[1] = strbuf_detach(&buf, NULL);
+       env[2] = NULL;
+
+       memset(&cld, 0, sizeof(cld));
+       cld.argv = argv;
+       cld.env = (const char *const *)env;
+       if (gzipped_request)
+               cld.in = -1;
+       cld.git_cmd = 1;
+       if (start_command(&cld))
+               exit(1);
+
+       close(1);
+       if (gzipped_request)
+               inflate_request(argv[0], cld.in);
+       else
+               close(0);
+
+       if (finish_command(&cld))
+               exit(1);
+       free(env[0]);
+       free(env[1]);
+       strbuf_release(&buf);
+}
+

 static int show_text_ref(const char *name, const unsigned char *sha1,
        int flag, void *cb_data)
 {
 static int show_text_ref(const char *name, const unsigned char *sha1,
        int flag, void *cb_data)
 {


@@ -167,11 +419,32 @@ static int show_text_ref(const char *name, const unsigned char *sha1,
 
 static void get_info_refs(char *arg)
 {
 
 static void get_info_refs(char *arg)
 {

+       const char *service_name = get_parameter("service");

        struct strbuf buf = STRBUF_INIT;
 
        struct strbuf buf = STRBUF_INIT;
 

-       for_each_ref(show_text_ref, &buf);

        hdr_nocache();
        hdr_nocache();

-       send_strbuf("text/plain", &buf);
+
+       if (service_name) {
+               const char *argv[] = {NULL /* service name */,
+                       "--stateless-rpc", "--advertise-refs",
+                       ".", NULL};
+               struct rpc_service *svc = select_service(service_name);
+
+               strbuf_addf(&buf, "application/x-git-%s-advertisement",
+                       svc->name);
+               hdr_str(content_type, buf.buf);
+               end_headers();
+
+               packet_write(1, "# service=git-%s\n", svc->name);
+               packet_flush(1);
+
+               argv[0] = svc->name;
+               run_service(argv);
+
+       } else {
+               for_each_ref(show_text_ref, &buf);
+               send_strbuf("text/plain", &buf);
+       }

        strbuf_release(&buf);
 }
 
        strbuf_release(&buf);
 }
 


@@ -200,6 +473,48 @@ static void get_info_packs(char *arg)
        strbuf_release(&buf);
 }
 
        strbuf_release(&buf);
 }
 

+static void check_content_type(const char *accepted_type)
+{
+       const char *actual_type = getenv("CONTENT_TYPE");
+
+       if (!actual_type)
+               actual_type = "";
+
+       if (strcmp(actual_type, accepted_type)) {
+               http_status(415, "Unsupported Media Type");
+               hdr_nocache();
+               end_headers();
+               format_write(1,
+                       "Expected POST with Content-Type '%s',"
+                       " but received '%s' instead.\n",
+                       accepted_type, actual_type);
+               exit(0);
+       }
+}
+
+static void service_rpc(char *service_name)
+{
+       const char *argv[] = {NULL, "--stateless-rpc", ".", NULL};
+       struct rpc_service *svc = select_service(service_name);
+       struct strbuf buf = STRBUF_INIT;
+
+       strbuf_reset(&buf);
+       strbuf_addf(&buf, "application/x-git-%s-request", svc->name);
+       check_content_type(buf.buf);
+
+       hdr_nocache();
+
+       strbuf_reset(&buf);
+       strbuf_addf(&buf, "application/x-git-%s-result", svc->name);
+       hdr_str(content_type, buf.buf);
+
+       end_headers();
+
+       argv[0] = svc->name;
+       run_service(argv);
+       strbuf_release(&buf);
+}
+

 static NORETURN void die_webcgi(const char *err, va_list params)
 {
        char buffer[1000];
 static NORETURN void die_webcgi(const char *err, va_list params)
 {
        char buffer[1000];


@@ -225,7 +540,10 @@ static struct service_cmd {
        {"GET", "/objects/info/packs$", get_info_packs},
        {"GET", "/objects/[0-9a-f]{2}/[0-9a-f]{38}$", get_loose_object},
        {"GET", "/objects/pack/pack-[0-9a-f]{40}\\.pack$", get_pack_file},
        {"GET", "/objects/info/packs$", get_info_packs},
        {"GET", "/objects/[0-9a-f]{2}/[0-9a-f]{38}$", get_loose_object},
        {"GET", "/objects/pack/pack-[0-9a-f]{40}\\.pack$", get_pack_file},

-       {"GET", "/objects/pack/pack-[0-9a-f]{40}\\.idx$", get_idx_file}
+       {"GET", "/objects/pack/pack-[0-9a-f]{40}\\.idx$", get_idx_file},
+
+       {"POST", "/git-upload-pack$", service_rpc},
+       {"POST", "/git-receive-pack$", service_rpc}

 };
 
 int main(int argc, char **argv)
 };
 
 int main(int argc, char **argv)