proxy_http.c

Apache HTTP Server 是一个功能强大的灵活的与HTTP/1.1相兼容的web服务器.这里给出的是Apache HTTP服务器的源码。

                 * ap_send_error relies on a headers_out to be present. we
                 * are in a bad position here.. so force everything we send out
                 * to have nothing to do with the incoming packet
                 */
                r->headers_out = apr_table_make(r->pool,1);
                r->status = HTTP_BAD_GATEWAY;
                r->status_line = "bad gateway";
                return r->status;

            } else {
                /* strip connection listed hop-by-hop headers from response */
                const char *buf;
                p_conn->close += ap_proxy_liststr(apr_table_get(r->headers_out,
                                                                "Connection"),
                                                  "close");
                ap_proxy_clear_connection(p, r->headers_out);
                if ((buf = apr_table_get(r->headers_out, "Content-Type"))) {
                    ap_set_content_type(r, apr_pstrdup(p, buf));
                }            
                ap_proxy_pre_http_request(origin,rp);
            }

            /* handle Via header in response */
            if (conf->viaopt != via_off && conf->viaopt != via_block) {
                /* create a "Via:" response header entry and merge it */
                apr_table_mergen(r->headers_out, "Via",
                                 (conf->viaopt == via_full)
                                     ? apr_psprintf(p, "%d.%d %s%s (%s)",
                                           HTTP_VERSION_MAJOR(r->proto_num),
                                           HTTP_VERSION_MINOR(r->proto_num),
                                           ap_get_server_name(r),
                                           server_portstr,
                                           AP_SERVER_BASEVERSION)
                                     : apr_psprintf(p, "%d.%d %s%s",
                                           HTTP_VERSION_MAJOR(r->proto_num),
                                           HTTP_VERSION_MINOR(r->proto_num),
                                           ap_get_server_name(r),
                                           server_portstr)
                );
            }

            /* cancel keepalive if HTTP/1.0 or less */
            if ((major < 1) || (minor < 1)) {
                p_conn->close += 1;
                origin->keepalive = AP_CONN_CLOSE;
            }
        } else {
            /* an http/0.9 response */
            backasswards = 1;
            r->status = 200;
            r->status_line = "200 OK";
            p_conn->close += 1;
        }

        if ( r->status != HTTP_CONTINUE ) {
            received_continue = 0;
        } else {
            ap_log_error(APLOG_MARK, APLOG_DEBUG, 0, NULL,
                         "proxy: HTTP: received 100 CONTINUE");
        }

        /* we must accept 3 kinds of date, but generate only 1 kind of date */
        {
            const char *buf;
            if ((buf = apr_table_get(r->headers_out, "Date")) != NULL) {
                apr_table_set(r->headers_out, "Date",
                              ap_proxy_date_canon(p, buf));
            }
            if ((buf = apr_table_get(r->headers_out, "Expires")) != NULL) {
                apr_table_set(r->headers_out, "Expires",
                              ap_proxy_date_canon(p, buf));
            }
            if ((buf = apr_table_get(r->headers_out, "Last-Modified")) != NULL) {
                apr_table_set(r->headers_out, "Last-Modified",
                              ap_proxy_date_canon(p, buf));
            }
        }

        /* munge the Location and URI response headers according to
         * ProxyPassReverse
         */
        {
            const char *buf;
            if ((buf = apr_table_get(r->headers_out, "Location")) != NULL) {
                apr_table_set(r->headers_out, "Location",
                              ap_proxy_location_reverse_map(r, conf, buf));
            }
            if ((buf = apr_table_get(r->headers_out, "Content-Location")) != NULL) {
                apr_table_set(r->headers_out, "Content-Location",
                              ap_proxy_location_reverse_map(r, conf, buf));
            }
            if ((buf = apr_table_get(r->headers_out, "URI")) != NULL) {
                apr_table_set(r->headers_out, "URI",
                              ap_proxy_location_reverse_map(r, conf, buf));
            }
        }

        if ((r->status == 401) && (conf->error_override != 0)) {
            const char *buf;
            const char *wa = "WWW-Authenticate";
            if ((buf = apr_table_get(r->headers_out, wa))) {
                apr_table_set(r->err_headers_out, wa, buf);
            } else {
                ap_log_error(APLOG_MARK, APLOG_DEBUG, 0, r->server,
                             "proxy: origin server sent 401 without WWW-Authenticate header");
            }
        }

        r->sent_bodyct = 1;
        /* Is it an HTTP/0.9 response? If so, send the extra data */
        if (backasswards) {
            apr_ssize_t cntr = len;
            e = apr_bucket_heap_create(buffer, cntr, NULL, c->bucket_alloc);
            APR_BRIGADE_INSERT_TAIL(bb, e);
        }

        /* send body - but only if a body is expected */
        if ((!r->header_only) &&                   /* not HEAD request */
            (r->status > 199) &&                   /* not any 1xx response */
            (r->status != HTTP_NO_CONTENT) &&      /* not 204 */
            (r->status != HTTP_RESET_CONTENT) &&   /* not 205 */
            (r->status != HTTP_NOT_MODIFIED)) {    /* not 304 */

            /* We need to copy the output headers and treat them as input
             * headers as well.  BUT, we need to do this before we remove
             * TE, so that they are preserved accordingly for
             * ap_http_filter to know where to end.
             */
            rp->headers_in = apr_table_copy(r->pool, r->headers_out);

            apr_table_unset(r->headers_out,"Transfer-Encoding");

            ap_log_error(APLOG_MARK, APLOG_DEBUG, 0, r->server,
                         "proxy: start body send");
             
            /*
             * if we are overriding the errors, we can't put the content
             * of the page into the brigade
             */
            if ( (conf->error_override ==0) || r->status < 400 ) {

                /* read the body, pass it to the output filters */
                int finish = FALSE;
                while (ap_get_brigade(rp->input_filters, 
                                      bb, 
                                      AP_MODE_READBYTES, 
                                      APR_BLOCK_READ, 
                                      conf->io_buffer_size) == APR_SUCCESS) {
#if DEBUGGING
                    {
                    apr_off_t readbytes;
                    apr_brigade_length(bb, 0, &readbytes);
                    ap_log_error(APLOG_MARK, APLOG_DEBUG, 0,
                                 r->server, "proxy (PID %d): readbytes: %#x",
                                 getpid(), readbytes);
                    }
#endif
                    /* sanity check */
                    if (APR_BRIGADE_EMPTY(bb)) {
                        apr_brigade_cleanup(bb);
                        break;
                    }

                    /* found the last brigade? */
                    if (APR_BUCKET_IS_EOS(APR_BRIGADE_LAST(bb))) {
                        /* if this is the last brigade, cleanup the
                         * backend connection first to prevent the
                         * backend server from hanging around waiting
                         * for a slow client to eat these bytes
                         */
                        ap_proxy_http_cleanup(r, p_conn, backend);
                        /* signal that we must leave */
                        finish = TRUE;
                    }

                    /* try send what we read */
                    if (ap_pass_brigade(r->output_filters, bb) != APR_SUCCESS
                        || c->aborted) {
                        /* Ack! Phbtt! Die! User aborted! */
                        p_conn->close = 1;  /* this causes socket close below */
                        finish = TRUE;
                    }

                    /* make sure we always clean up after ourselves */
                    apr_brigade_cleanup(bb);

                    /* if we are done, leave */
                    if (TRUE == finish) {
                        break;
                    }
                }
            }
            ap_log_error(APLOG_MARK, APLOG_DEBUG, 0, r->server,
                         "proxy: end body send");
        } else {
            ap_log_error(APLOG_MARK, APLOG_DEBUG, 0, r->server,
                         "proxy: header only");
        }
    }

    if ( conf->error_override ) {
        /* the code above this checks for 'OK' which is what the hook expects */
        if ( r->status == HTTP_OK )
            return OK;
        else  {
            /* clear r->status for override error, otherwise ErrorDocument
             * thinks that this is a recursive error, and doesn't find the
             * custom error page
             */
            int status = r->status;
            r->status = HTTP_OK;
            /* Discard body, if one is expected */
            if ((status > 199) && /* not any 1xx response */
                (status != HTTP_NO_CONTENT) && /* not 204 */
                (status != HTTP_RESET_CONTENT) && /* not 205 */
                (status != HTTP_NOT_MODIFIED)) { /* not 304 */
               ap_discard_request_body(rp);
           }
            return status;
        }
    } else 
        return OK;
}

static
apr_status_t ap_proxy_http_cleanup(request_rec *r, proxy_http_conn_t *p_conn,
                                   proxy_conn_rec *backend) {
    /* If there are no KeepAlives, or if the connection has been signalled
     * to close, close the socket and clean up
     */

    /* if the connection is < HTTP/1.1, or Connection: close,
     * we close the socket, otherwise we leave it open for KeepAlive support
     */
    if (p_conn->close || (r->proto_num < HTTP_VERSION(1,1))) {
        if (p_conn->sock) {
            apr_socket_close(p_conn->sock);
            p_conn->sock = NULL;
            backend->connection = NULL;
        }
    }
    return OK;
}

/*
 * This handles http:// URLs, and other URLs using a remote proxy over http
 * If proxyhost is NULL, then contact the server directly, otherwise
 * go via the proxy.
 * Note that if a proxy is used, then URLs other than http: can be accessed,
 * also, if we have trouble which is clearly specific to the proxy, then
 * we return DECLINED so that we can try another proxy. (Or the direct
 * route.)
 */
int ap_proxy_http_handler(request_rec *r, proxy_server_conf *conf,
                          char *url, const char *proxyname, 
                          apr_port_t proxyport)
{
    int status;
    char server_portstr[32];
    conn_rec *origin = NULL;
    proxy_conn_rec *backend = NULL;
    int is_ssl = 0;

    /* Note: Memory pool allocation.
     * A downstream keepalive connection is always connected to the existence
     * (or not) of an upstream keepalive connection. If this is not done then
     * load balancing against multiple backend servers breaks (one backend
     * server ends up taking 100% of the load), and the risk is run of
     * downstream keepalive connections being kept open unnecessarily. This
     * keeps webservers busy and ties up resources.
     *
     * As a result, we allocate all sockets out of the upstream connection
     * pool, and when we want to reuse a socket, we check first whether the
     * connection ID of the current upstream connection is the same as that
     * of the connection when the socket was opened.
     */
    apr_pool_t *p = r->connection->pool;
    conn_rec *c = r->connection;
    apr_bucket_brigade *bb = apr_brigade_create(p, c->bucket_alloc);
    apr_uri_t *uri = apr_palloc(r->connection->pool, sizeof(*uri));
    proxy_http_conn_t *p_conn = apr_pcalloc(r->connection->pool,
                                           sizeof(*p_conn));

    /* is it for us? */
    if (strncasecmp(url, "https:", 6) == 0) {
        if (!ap_proxy_ssl_enable(NULL)) {
            ap_log_error(APLOG_MARK, APLOG_DEBUG, 0, r->server,
                         "proxy: HTTPS: declining URL %s"
                         " (mod_ssl not configured?)", url);
            return DECLINED;
        }
        is_ssl = 1;
    }
    else if (!(strncasecmp(url, "http:", 5)==0 || (strncasecmp(url, "ftp:", 4)==0 && proxyname))) {
        ap_log_error(APLOG_MARK, APLOG_DEBUG, 0, r->server,
                     "proxy: HTTP: declining URL %s", url);
        return DECLINED; /* only interested in HTTP, or FTP via proxy */
    }
    ap_log_error(APLOG_MARK, APLOG_DEBUG, 0, r->server,
             "proxy: HTTP: serving URL %s", url);
    
    
    /* only use stored info for top-level pages. Sub requests don't share 
     * in keepalives
     */
    if (!r->main) {
        backend = (proxy_conn_rec *) ap_get_module_config(c->conn_config,
                                                      &proxy_http_module);
    }
    /* create space for state information */
    if (!backend) {
        backend = apr_pcalloc(c->pool, sizeof(proxy_conn_rec));
        backend->connection = NULL;
        backend->hostname = NULL;
        backend->port = 0;
        if (!r->main) {
            ap_set_module_config(c->conn_config, &proxy_http_module, backend);
        }
    }

    backend->is_ssl = is_ssl;

    /* Step One: Determine Who To Connect To */
    status = ap_proxy_http_determine_connection(p, r, p_conn, c, conf, uri,
                                                &url, proxyname, proxyport,
                                                server_portstr,
                                                sizeof(server_portstr));
    if ( status != OK ) {
        return status;
    }

    /* Step Two: Make the Connection */
    status = ap_proxy_http_create_connection(p, r, p_conn, c, &origin, backend,
                                             conf, proxyname);
    if ( status != OK ) {
        return status;
    }
   
    /* Step Three: Send the Request */
    status = ap_proxy_http_request(p, r, p_conn, origin, conf, uri, url, bb,
                                   server_portstr);
    if ( status != OK ) {
        return status;
    }

    /* Step Four: Receive the Response */
    status = ap_proxy_http_process_response(p, r, p_conn, origin, backend, conf,
                                            bb, server_portstr);
    if ( status != OK ) {
        /* clean up even if there is an error */
        ap_proxy_http_cleanup(r, p_conn, backend);
        return status;
    }

    /* Step Five: Clean Up */
    status = ap_proxy_http_cleanup(r, p_conn, backend);
    if ( status != OK ) {
        return status;
    }

    return OK;
}

static void ap_proxy_http_register_hook(apr_pool_t *p)
{
    proxy_hook_scheme_handler(ap_proxy_http_handler, NULL, NULL, APR_HOOK_FIRST);
    proxy_hook_canon_handler(ap_proxy_http_canon, NULL, NULL, APR_HOOK_FIRST);
}

module AP_MODULE_DECLARE_DATA proxy_http_module = {
    STANDARD20_MODULE_STUFF,
    NULL,              /* create per-directory config structure */
    NULL,              /* merge per-directory config structures */
    NULL,              /* create per-server config structure */
    NULL,              /* merge per-server config structures */
    NULL,              /* command apr_table_t */
    ap_proxy_http_register_hook/* register hooks */
};