mod_proxy_http.c

Apache官方在今天放出产品系列2.2的最新版本2.2.11的源码包 最流行的HTTP服务器软件之一

     *
     *   We have no request body (handled by RB_STREAM_CL)
     *
     *   We have a request body length <= MAX_MEM_SPOOL
     *
     *   The administrator has setenv force-proxy-request-1.0
     *
     *   The client sent a C-L body, and the administrator has
     *   not setenv proxy-sendchunked or has set setenv proxy-sendcl
     *
     *   The client sent a T-E body, and the administrator has
     *   setenv proxy-sendcl, and not setenv proxy-sendchunked
     *
     * If both proxy-sendcl and proxy-sendchunked are set, the
     * behavior is the same as if neither were set, large bodies
     * that can't be read will be forwarded in their original
     * form of C-L, or T-E.
     *
     * To ensure maximum compatibility, setenv proxy-sendcl
     * To reduce server resource use,   setenv proxy-sendchunked
     *
     * Then address specific servers with conditional setenv
     * options to restore the default behavior where desireable.
     *
     * We have to compute content length by reading the entire request
     * body; if request body is not small, we'll spool the remaining
     * input to a temporary file.  Chunked is always preferable.
     *
     * We can only trust the client-provided C-L if the T-E header
     * is absent, and the filters are unchanged (the body won't
     * be resized by another content filter).
     */
    if (APR_BUCKET_IS_EOS(APR_BRIGADE_LAST(input_brigade))) {
        /* The whole thing fit, so our decision is trivial, use
         * the filtered bytes read from the client for the request
         * body Content-Length.
         *
         * If we expected no body, and read no body, do not set
         * the Content-Length.
         */
        if (old_cl_val || old_te_val || bytes_read) {
            old_cl_val = apr_off_t_toa(r->pool, bytes_read);
        }
        rb_method = RB_STREAM_CL;
    }
    else if (old_te_val) {
        if (force10
             || (apr_table_get(r->subprocess_env, "proxy-sendcl")
                  && !apr_table_get(r->subprocess_env, "proxy-sendchunks")
                  && !apr_table_get(r->subprocess_env, "proxy-sendchunked"))) {
            rb_method = RB_SPOOL_CL;
        }
        else {
            rb_method = RB_STREAM_CHUNKED;
        }
    }
    else if (old_cl_val) {
        if (r->input_filters == r->proto_input_filters) {
            rb_method = RB_STREAM_CL;
        }
        else if (!force10
                  && (apr_table_get(r->subprocess_env, "proxy-sendchunks")
                      || apr_table_get(r->subprocess_env, "proxy-sendchunked"))
                  && !apr_table_get(r->subprocess_env, "proxy-sendcl")) {
            rb_method = RB_STREAM_CHUNKED;
        }
        else {
            rb_method = RB_SPOOL_CL;
        }
    }
    else {
        /* This is an appropriate default; very efficient for no-body
         * requests, and has the behavior that it will not add any C-L
         * when the old_cl_val is NULL.
         */
        rb_method = RB_SPOOL_CL;
    }

/* Yes I hate gotos.  This is the subrequest shortcut */
skip_body:
    /*
     * Handle Connection: header if we do HTTP/1.1 request:
     * If we plan to close the backend connection sent Connection: close
     * otherwise sent Connection: Keep-Alive.
     */
    if (!force10) {
        if (p_conn->close || p_conn->close_on_recycle) {
            buf = apr_pstrdup(p, "Connection: close" CRLF);
        }
        else {
            buf = apr_pstrdup(p, "Connection: Keep-Alive" CRLF);
        }
        ap_xlate_proto_to_ascii(buf, strlen(buf));
        e = apr_bucket_pool_create(buf, strlen(buf), p, c->bucket_alloc);
        APR_BRIGADE_INSERT_TAIL(header_brigade, e);
    }

    /* send the request body, if any. */
    switch(rb_method) {
    case RB_STREAM_CHUNKED:
        rv = stream_reqbody_chunked(p, r, p_conn, origin, header_brigade,
                                        input_brigade);
        break;
    case RB_STREAM_CL:
        rv = stream_reqbody_cl(p, r, p_conn, origin, header_brigade,
                                   input_brigade, old_cl_val);
        break;
    case RB_SPOOL_CL:
        rv = spool_reqbody_cl(p, r, p_conn, origin, header_brigade,
                                  input_brigade, (old_cl_val != NULL)
                                              || (old_te_val != NULL)
                                              || (bytes_read > 0));
        break;
    default:
        /* shouldn't be possible */
        rv = HTTP_INTERNAL_SERVER_ERROR ;
        break;
    }

    if (rv != OK) {
        /* apr_errno value has been logged in lower level method */
        ap_log_error(APLOG_MARK, APLOG_ERR, 0, r->server,
                     "proxy: pass request body failed to %pI (%s)"
                     " from %s (%s)",
                     p_conn->addr,
                     p_conn->hostname ? p_conn->hostname: "",
                     c->remote_ip,
                     c->remote_host ? c->remote_host: "");
        return rv;
    }

    return OK;
}

static void process_proxy_header(request_rec* r, proxy_dir_conf* c,
                      const char* key, const char* value)
{
    static const char* date_hdrs[]
        = { "Date", "Expires", "Last-Modified", NULL } ;
    static const struct {
        const char* name;
        ap_proxy_header_reverse_map_fn func;
    } transform_hdrs[] = {
        { "Location", ap_proxy_location_reverse_map } ,
        { "Content-Location", ap_proxy_location_reverse_map } ,
        { "URI", ap_proxy_location_reverse_map } ,
        { "Destination", ap_proxy_location_reverse_map } ,
        { "Set-Cookie", ap_proxy_cookie_reverse_map } ,
        { NULL, NULL }
    } ;
    int i ;
    for ( i = 0 ; date_hdrs[i] ; ++i ) {
        if ( !strcasecmp(date_hdrs[i], key) ) {
            apr_table_add(r->headers_out, key,
                ap_proxy_date_canon(r->pool, value)) ;
            return ;
        }
    }
    for ( i = 0 ; transform_hdrs[i].name ; ++i ) {
        if ( !strcasecmp(transform_hdrs[i].name, key) ) {
            apr_table_add(r->headers_out, key,
                (*transform_hdrs[i].func)(r, c, value)) ;
            return ;
       }
    }
    apr_table_add(r->headers_out, key, value) ;
    return ;
}

/*
 * Note: pread_len is the length of the response that we've  mistakenly
 * read (assuming that we don't consider that an  error via
 * ProxyBadHeader StartBody). This depends on buffer actually being
 * local storage to the calling code in order for pread_len to make
 * any sense at all, since we depend on buffer still containing
 * what was read by ap_getline() upon return.
 */
static void ap_proxy_read_headers(request_rec *r, request_rec *rr,
                                  char *buffer, int size,
                                  conn_rec *c, int *pread_len)
{
    int len;
    char *value, *end;
    char field[MAX_STRING_LEN];
    int saw_headers = 0;
    void *sconf = r->server->module_config;
    proxy_server_conf *psc;
    proxy_dir_conf *dconf;

    dconf = ap_get_module_config(r->per_dir_config, &proxy_module);
    psc = (proxy_server_conf *) ap_get_module_config(sconf, &proxy_module);

    r->headers_out = apr_table_make(r->pool, 20);
    *pread_len = 0;

    /*
     * Read header lines until we get the empty separator line, a read error,
     * the connection closes (EOF), or we timeout.
     */
    while ((len = ap_getline(buffer, size, rr, 1)) > 0) {

        if (!(value = strchr(buffer, ':'))) {     /* Find the colon separator */

            /* We may encounter invalid headers, usually from buggy
             * MS IIS servers, so we need to determine just how to handle
             * them. We can either ignore them, assume that they mark the
             * start-of-body (eg: a missing CRLF) or (the default) mark
             * the headers as totally bogus and return a 500. The sole
             * exception is an extra "HTTP/1.0 200, OK" line sprinkled
             * in between the usual MIME headers, which is a favorite
             * IIS bug.
             */
             /* XXX: The mask check is buggy if we ever see an HTTP/1.10 */

            if (!apr_date_checkmask(buffer, "HTTP/#.# ###*")) {
                if (psc->badopt == bad_error) {
                    /* Nope, it wasn't even an extra HTTP header. Give up. */
                    r->headers_out = NULL;
                    return ;
                }
                else if (psc->badopt == bad_body) {
                    /* if we've already started loading headers_out, then
                     * return what we've accumulated so far, in the hopes
                     * that they are useful; also note that we likely pre-read
                     * the first line of the response.
                     */
                    if (saw_headers) {
                        ap_log_error(APLOG_MARK, APLOG_WARNING, 0, r->server,
                         "proxy: Starting body due to bogus non-header in headers "
                         "returned by %s (%s)", r->uri, r->method);
                        *pread_len = len;
                        return ;
                    } else {
                         ap_log_error(APLOG_MARK, APLOG_WARNING, 0, r->server,
                         "proxy: No HTTP headers "
                         "returned by %s (%s)", r->uri, r->method);
                        return ;
                    }
                }
            }
            /* this is the psc->badopt == bad_ignore case */
            ap_log_error(APLOG_MARK, APLOG_WARNING, 0, r->server,
                         "proxy: Ignoring bogus HTTP header "
                         "returned by %s (%s)", r->uri, r->method);
            continue;
        }

        *value = '\0';
        ++value;
        /* XXX: RFC2068 defines only SP and HT as whitespace, this test is
         * wrong... and so are many others probably.
         */
        while (apr_isspace(*value))
            ++value;            /* Skip to start of value   */

        /* should strip trailing whitespace as well */
        for (end = &value[strlen(value)-1]; end > value && apr_isspace(*end); --
end)
            *end = '\0';

        /* make sure we add so as not to destroy duplicated headers
         * Modify headers requiring canonicalisation and/or affected
         * by ProxyPassReverse and family with process_proxy_header
         */
        process_proxy_header(r, dconf, buffer, value) ;
        saw_headers = 1;

        /* the header was too long; at the least we should skip extra data */
        if (len >= size - 1) {
            while ((len = ap_getline(field, MAX_STRING_LEN, rr, 1))
                    >= MAX_STRING_LEN - 1) {
                /* soak up the extra data */
            }
            if (len == 0) /* time to exit the larger loop as well */
                break;
        }
    }
}



static int addit_dammit(void *v, const char *key, const char *val)
{
    apr_table_addn(v, key, val);
    return 1;
}

static
apr_status_t ap_proxygetline(apr_bucket_brigade *bb, char *s, int n, request_rec *r,
                             int fold, int *writen)
{
    char *tmp_s = s;
    apr_status_t rv;
    apr_size_t len;

    rv = ap_rgetline(&tmp_s, n, &len, r, fold, bb);
    apr_brigade_cleanup(bb);

    if (rv == APR_SUCCESS) {
        *writen = (int) len;
    } else if (rv == APR_ENOSPC) {
        *writen = n;
    } else {
        *writen = -1;
    }

    return rv;
}

/*
 * Limit the number of interim respones we sent back to the client. Otherwise
 * we suffer from a memory build up. Besides there is NO sense in sending back
 * an unlimited number of interim responses to the client. Thus if we cross
 * this limit send back a 502 (Bad Gateway).
 */
#ifndef AP_MAX_INTERIM_RESPONSES
#define AP_MAX_INTERIM_RESPONSES 10
#endif

static
apr_status_t ap_proxy_http_process_response(apr_pool_t * p, request_rec *r,
                                            proxy_conn_rec *backend,
                                            conn_rec *origin,
                                            proxy_server_conf *conf,
                                            char *server_portstr) {
    conn_rec *c = r->connection;
    char buffer[HUGE_STRING_LEN];
    const char *buf;
    char keepchar;
    request_rec *rp;
    apr_bucket *e;
    apr_bucket_brigade *bb, *tmp_bb;
    apr_bucket_brigade *pass_bb;
    int len, backasswards;
    int interim_response = 0; /* non-zero whilst interim 1xx responses
                               * are being read. */