mod_cache.c

来自「apache服务器源代码（版本号：2.2.2）」· C语言 代码 · 共 1,250 行 · 第 1/3 页

        /* RFC2616 13.4 we are allowed to cache 200, 203, 206, 300, 301 or 410
         * We don't cache 206, because we don't (yet) cache partial responses.
         * We include 304 Not Modified here too as this is the origin server
         * telling us to serve the cached copy.
         */
        reason = apr_psprintf(p, "Response status %d", r->status);
    }
    else if (exps != NULL && exp == APR_DATE_BAD) {
        /* if a broken Expires header is present, don't cache it */
        reason = apr_pstrcat(p, "Broken expires header: ", exps, NULL);
    }
    else if (r->args && exps == NULL) {
        /* if query string present but no expiration time, don't cache it
         * (RFC 2616/13.9)
         */
        reason = "Query string present but no expires header";
    }
    else if (r->status == HTTP_NOT_MODIFIED &&
             !cache->handle && !cache->stale_handle) {
        /* if the server said 304 Not Modified but we have no cache
         * file - pass this untouched to the user agent, it's not for us.
         */
        reason = "HTTP Status 304 Not Modified";
    }
    else if (r->status == HTTP_OK && lastmods == NULL && etag == NULL
             && (exps == NULL) && (conf->no_last_mod_ignore ==0)) {
        /* 200 OK response from HTTP/1.0 and up without Last-Modified,
         * Etag, or Expires headers.
         */
        /* Note: mod-include clears last_modified/expires/etags - this
         * is why we have an optional function for a key-gen ;-)
         */
        reason = "No Last-Modified, Etag, or Expires headers";
    }
    else if (r->header_only) {
        /* HEAD requests */
        reason = "HTTP HEAD request";
    }
    else if (!conf->store_nostore &&
             ap_cache_liststr(NULL, cc_out, "no-store", NULL)) {
        /* RFC2616 14.9.2 Cache-Control: no-store response
         * indicating do not cache, or stop now if you are
         * trying to cache it.
         */
        /* FIXME: The Cache-Control: no-store could have come in on a 304,
         * FIXME: while the original request wasn't conditional.  IOW, we
         * FIXME:  made the the request conditional earlier to revalidate
         * FIXME: our cached response.
         */
        reason = "Cache-Control: no-store present";
    }
    else if (!conf->store_private &&
             ap_cache_liststr(NULL, cc_out, "private", NULL)) {
        /* RFC2616 14.9.1 Cache-Control: private response
         * this object is marked for this user's eyes only. Behave
         * as a tunnel.
         */
        /* FIXME: See above (no-store) */
        reason = "Cache-Control: private present";
    }
    else if (apr_table_get(r->headers_in, "Authorization") != NULL
             && !(ap_cache_liststr(NULL, cc_out, "s-maxage", NULL)
                  || ap_cache_liststr(NULL, cc_out, "must-revalidate", NULL)
                  || ap_cache_liststr(NULL, cc_out, "public", NULL))) {
        /* RFC2616 14.8 Authorisation:
         * if authorisation is included in the request, we don't cache,
         * but we can cache if the following exceptions are true:
         * 1) If Cache-Control: s-maxage is included
         * 2) If Cache-Control: must-revalidate is included
         * 3) If Cache-Control: public is included
         */
        reason = "Authorization required";
    }
    else if (ap_cache_liststr(NULL,
                              apr_table_get(r->headers_out, "Vary"),
                              "*", NULL)) {
        reason = "Vary header contains '*'";
    }
    else if (r->no_cache) {
        /* or we've been asked not to cache it above */
        reason = "r->no_cache present";
    }

    if (reason) {
        ap_log_error(APLOG_MARK, APLOG_DEBUG, 0, r->server,
                     "cache: %s not cached. Reason: %s", r->unparsed_uri,
                     reason);

        /* remove this filter from the chain */
        ap_remove_output_filter(f);

        /* ship the data up the stack */
        return ap_pass_brigade(f->next, in);
    }

    /* Make it so that we don't execute this path again. */
    cache->in_checked = 1;

    /* Set the content length if known.
     */
    cl = apr_table_get(r->err_headers_out, "Content-Length");
    if (cl == NULL) {
        cl = apr_table_get(r->headers_out, "Content-Length");
    }
    if (cl) {
        char *errp;
        if (apr_strtoff(&size, cl, &errp, 10) || *errp || size < 0) {
            cl = NULL; /* parse error, see next 'if' block */
        }
    }

    if (!cl) {
        /* if we don't get the content-length, see if we have all the
         * buckets and use their length to calculate the size
         */
        apr_bucket *e;
        int all_buckets_here=0;
        int unresolved_length = 0;
        size=0;
        for (e = APR_BRIGADE_FIRST(in);
             e != APR_BRIGADE_SENTINEL(in);
             e = APR_BUCKET_NEXT(e))
        {
            if (APR_BUCKET_IS_EOS(e)) {
                all_buckets_here=1;
                break;
            }
            if (APR_BUCKET_IS_FLUSH(e)) {
                unresolved_length = 1;
                continue;
            }
            if (e->length == (apr_size_t)-1) {
                break;
            }
            size += e->length;
        }
        if (!all_buckets_here) {
            size = -1;
        }
    }

    /* It's safe to cache the response.
     *
     * There are two possiblities at this point:
     * - cache->handle == NULL. In this case there is no previously
     * cached entity anywhere on the system. We must create a brand
     * new entity and store the response in it.
     * - cache->stale_handle != NULL. In this case there is a stale
     * entity in the system which needs to be replaced by new
     * content (unless the result was 304 Not Modified, which means
     * the cached entity is actually fresh, and we should update
     * the headers).
     */

    /* Did we have a stale cache entry that really is stale? */
    if (cache->stale_handle) {
        if (r->status == HTTP_NOT_MODIFIED) {
            /* Oh, hey.  It isn't that stale!  Yay! */
            cache->handle = cache->stale_handle;
            info = &cache->handle->cache_obj->info;
            rv = OK;
        }
        else {
            /* Oh, well.  Toss it. */
            cache->provider->remove_entity(cache->stale_handle);
            /* Treat the request as if it wasn't conditional. */
            cache->stale_handle = NULL;
        }
    }

    /* no cache handle, create a new entity */
    if (!cache->handle) {
        rv = cache_create_entity(r, size);
        info = apr_pcalloc(r->pool, sizeof(cache_info));
        /* We only set info->status upon the initial creation. */
        info->status = r->status;
    }

    if (rv != OK) {
        /* Caching layer declined the opportunity to cache the response */
        ap_remove_output_filter(f);
        return ap_pass_brigade(f->next, in);
    }

    ap_log_error(APLOG_MARK, APLOG_DEBUG, 0, r->server,
                 "cache: Caching url: %s", r->unparsed_uri);

    /* We are actually caching this response. So it does not
     * make sense to remove this entity any more.
     */
    ap_log_error(APLOG_MARK, APLOG_DEBUG, 0, r->server,
                 "cache: Removing CACHE_REMOVE_URL filter.");
    ap_remove_output_filter(cache->remove_url_filter);

    /*
     * We now want to update the cache file header information with
     * the new date, last modified, expire and content length and write
     * it away to our cache file. First, we determine these values from
     * the response, using heuristics if appropriate.
     *
     * In addition, we make HTTP/1.1 age calculations and write them away
     * too.
     */

    /* Read the date. Generate one if one is not supplied */
    dates = apr_table_get(r->err_headers_out, "Date");
    if (dates != NULL) {
        date_in_errhdr = 1;
    }
    else {
        dates = apr_table_get(r->headers_out, "Date");
    }
    if (dates != NULL) {
        info->date = apr_date_parse_http(dates);
    }
    else {
        info->date = APR_DATE_BAD;
    }

    now = apr_time_now();
    if (info->date == APR_DATE_BAD) {  /* No, or bad date */
        char *dates;
        /* no date header (or bad header)! */
        /* add one; N.B. use the time _now_ rather than when we were checking
         * the cache
         */
        if (date_in_errhdr == 1) {
            apr_table_unset(r->err_headers_out, "Date");
        }
        date = now;
        dates = apr_pcalloc(r->pool, MAX_STRING_LEN);
        apr_rfc822_date(dates, now);
        apr_table_set(r->headers_out, "Date", dates);
        ap_log_error(APLOG_MARK, APLOG_DEBUG, 0, r->server,
                     "cache: Added date header");
        info->date = date;
    }
    else {
        date = info->date;
    }

    /* set response_time for HTTP/1.1 age calculations */
    info->response_time = now;

    /* get the request time */
    info->request_time = r->request_time;

    /* check last-modified date */
    if (lastmod != APR_DATE_BAD && lastmod > date) {
        /* if it's in the future, then replace by date */
        lastmod = date;
        lastmods = dates;
        ap_log_error(APLOG_MARK, APLOG_DEBUG, 0,
                     r->server,
                     "cache: Last modified is in the future, "
                     "replacing with now");
    }

    /* if no expiry date then
     *   if lastmod
     *      expiry date = date + min((date - lastmod) * factor, maxexpire)
     *   else
     *      expire date = date + defaultexpire
     */
    if (exp == APR_DATE_BAD) {
        char expire_hdr[APR_RFC822_DATE_LEN];

        /* if lastmod == date then you get 0*conf->factor which results in
         *   an expiration time of now. This causes some problems with
         *   freshness calculations, so we choose the else path...
         */
        if ((lastmod != APR_DATE_BAD) && (lastmod < date)) {
            apr_time_t x = (apr_time_t) ((date - lastmod) * conf->factor);

            if (x > conf->maxex) {
                x = conf->maxex;
            }
            exp = date + x;
            apr_rfc822_date(expire_hdr, exp);
            apr_table_set(r->headers_out, "Expires", expire_hdr);
        }
        else {
            exp = date + conf->defex;
            apr_rfc822_date(expire_hdr, exp);
            apr_table_set(r->headers_out, "Expires", expire_hdr);
        }
    }
    info->expire = exp;

    /* We found a stale entry which wasn't really stale. */
    if (cache->stale_handle) {
        /* Load in the saved status and clear the status line. */
        r->status = info->status;
        r->status_line = NULL;

        /* RFC 2616 10.3.5 states that entity headers are not supposed
         * to be in the 304 response.  Therefore, we need to combine the
         * response headers with the cached headers *before* we update
         * the cached headers.
         *
         * However, before doing that, we need to first merge in
         * err_headers_out and we also need to strip any hop-by-hop
         * headers that might have snuck in.
         */
        r->headers_out = apr_table_overlay(r->pool, r->headers_out,
                                           r->err_headers_out);
        r->headers_out = ap_cache_cacheable_hdrs_out(r->pool, r->headers_out,
                                                     r->server);
        apr_table_clear(r->err_headers_out);

        /* Merge in our cached headers.  However, keep any updated values. */
        ap_cache_accept_headers(cache->handle, r, 1);
    }

    /* Write away header information to cache. It is possible that we are
     * trying to update headers for an entity which has already been cached.
     *
     * This may fail, due to an unwritable cache area. E.g. filesystem full,
     * permissions problems or a read-only (re)mount. This must be handled
     * later.
     */
    rv = cache->provider->store_headers(cache->handle, r, info);

    /* Did we just update the cached headers on a revalidated response?
     *
     * If so, we can now decide what to serve to the client.  This is done in
     * the same way as with a regular response, but conditions are now checked
     * against the cached or merged response headers.
     */
    if (cache->stale_handle) {
        apr_bucket_brigade *bb;
        apr_bucket *bkt;
        int status;

        bb = apr_brigade_create(r->pool, r->connection->bucket_alloc);

        /* Restore the original request headers and see if we need to
         * return anything else than the cached response (ie. the original
         * request was conditional).
         */
        r->headers_in = cache->stale_headers;
        status = ap_meets_conditions(r);
        if (status != OK) {
            r->status = status;

            bkt = apr_bucket_flush_create(bb->bucket_alloc);
            APR_BRIGADE_INSERT_TAIL(bb, bkt);
        }
        else {
            cache->provider->recall_body(cache->handle, r->pool, bb);
        }

        cache->block_response = 1;

        /* Before returning we need to handle the possible case of an
         * unwritable cache. Rather than leaving the entity in the cache
         * and having it constantly re-validated, now that we have recalled
         * the body it is safe to try and remove the url from the cache.
         */
        if (rv != APR_SUCCESS) {
            ap_log_error(APLOG_MARK, APLOG_DEBUG, rv, r->server,
                         "cache: updating headers with store_headers failed. "
                         "Removing cached url.");

            rv = cache->provider->remove_url(cache->stale_handle, r->pool);
            if (rv != OK) {
                /* Probably a mod_disk_cache cache area has been (re)mounted
                 * read-only, or that there is a permissions problem.
                 */
                ap_log_error(APLOG_MARK, APLOG_DEBUG, rv, r->server,
                     "cache: attempt to remove url from cache unsuccessful.");
            }
        }

        return ap_pass_brigade(f->next, bb);
    }

    if(rv != APR_SUCCESS) {
        ap_log_error(APLOG_MARK, APLOG_DEBUG, rv, r->server,
                     "cache: store_headers failed");
        ap_remove_output_filter(f);

        return ap_pass_brigade(f->next, in);
    }

    rv = cache->provider->store_body(cache->handle, r, in);
    if (rv != APR_SUCCESS) {
        ap_log_error(APLOG_MARK, APLOG_DEBUG, rv, r->server,
                     "cache: store_body failed");
        ap_remove_output_filter(f);
    }

    return ap_pass_brigade(f->next, in);
}

/*
 * CACHE_REMOVE_URL filter
 * ---------------
 *
 * This filter gets added in the quick handler every time the CACHE_SAVE filter
 * gets inserted. Its purpose is to remove a confirmed stale cache entry from
 * the cache.
 *
 * CACHE_REMOVE_URL has to be a protocol filter to ensure that is run even if
 * the response is a canned error message, which removes the content filters
 * and thus the CACHE_SAVE filter from the chain.
 *
 * CACHE_REMOVE_URL expects cache request rec within its context because the
 * request this filter runs on can be different from the one whose cache entry
 * should be removed, due to internal redirects.
 *
 * Note that CACHE_SAVE_URL (as a content-set filter, hence run before the
 * protocol filters) will remove this filter if it decides to cache the file.
 * Therefore, if this filter is left in, it must mean we need to toss any
 * existing files.
 */
static int cache_remove_url_filter(ap_filter_t *f, apr_bucket_brigade *in)