Do not double encode encoded slashes

In case that AllowEncodedSlashes is set to NoDecode do not double encode
encoded slashes in the URL sent by the reverse proxy to the backend.

* include/ap_mmn.h: Document the addition of ap_proxy_canonenc_ex to the API.

* modules/proxy/mod_proxy.h: Declare ap_proxy_canonenc_ex and define flag
      values.

* modules/proxy/proxy_util.c: Implement ap_proxy_canonenc_ex by modifying
      ap_proxy_canonenc accordingly and reimplement ap_proxy_canonenc to
      use ap_proxy_canonenc_ex with the appropriate flag.

* modules/http2/mod_proxy_http2.c, modules/proxy/mod_proxy_*.c: Set the
      correct flag based on the AllowEncodedSlashes configuration and use
      ap_proxy_canonenc_ex instead of ap_proxy_canonenc.


git-svn-id: https://svn.apache.org/repos/asf/httpd/httpd/trunk@1908341 13f79535-47bb-0310-9956-ffa450edef68

11 files changed, 83 insertions, 22 deletions

diff --git a/modules/http2/mod_proxy_http2.c b/modules/http2/mod_proxy_http2.c
index f1c1bb92f4..94f28bebb7 100644
--- a/modules/http2/mod_proxy_http2.c
+++ b/modules/http2/mod_proxy_http2.c
@@ -159,8 +159,11 @@ static int proxy_http2_canon(request_rec *r, char *url)
             search = r->args;
         }
         else {
-            path = ap_proxy_canonenc(r->pool, url, (int)strlen(url),
-                                     enc_path, 0, r->proxyreq);
+            core_dir_config *d = ap_get_core_module_config(r->per_dir_config);
+            int flags = d->allow_encoded_slashes  && !d->decode_encoded_slashes ? PROXY_CANONENC_NOENCODEDSLASHENCODING : 0;
+
+            path = ap_proxy_canonenc_ex(r->pool, url, (int)strlen(url),
+                                        enc_path, flags, r->proxyreq);
             search = r->args;
         }
         if (search && *ap_scan_vchar_obstext(search)) {
diff --git a/modules/proxy/mod_proxy.h b/modules/proxy/mod_proxy.h
index 0df3dc2801..04fee22742 100644
--- a/modules/proxy/mod_proxy.h
+++ b/modules/proxy/mod_proxy.h
@@ -76,6 +76,10 @@ enum enctype {
     enc_path, enc_search, enc_user, enc_fpath, enc_parm
 };
 
+/* Flags for ap_proxy_canonenc_ex */
+#define PROXY_CANONENC_FORCEDEC 0x01
+#define PROXY_CANONENC_NOENCODEDSLASHENCODING 0x02
+
 typedef enum {
     NONE, TCP, OPTIONS, HEAD, GET, CPING, PROVIDER, OPTIONS11, HEAD11, GET11, EOT
 } hcmethod_t;
@@ -693,6 +697,8 @@ PROXY_DECLARE(apr_status_t) ap_proxy_strncpy(char *dst, const char *src,
                                              apr_size_t dlen);
 PROXY_DECLARE(int) ap_proxy_hex2c(const char *x);
 PROXY_DECLARE(void) ap_proxy_c2hex(int ch, char *x);
+PROXY_DECLARE(char *)ap_proxy_canonenc_ex(apr_pool_t *p, const char *x, int len, enum enctype t,
+                                          int flags, int proxyreq);
 PROXY_DECLARE(char *)ap_proxy_canonenc(apr_pool_t *p, const char *x, int len, enum enctype t,
                                        int forcedec, int proxyreq);
 PROXY_DECLARE(char *)ap_proxy_canon_netloc(apr_pool_t *p, char **const urlp, char **userp,
diff --git a/modules/proxy/mod_proxy_ajp.c b/modules/proxy/mod_proxy_ajp.c
index d7fd47574c..54862ffa03 100644
--- a/modules/proxy/mod_proxy_ajp.c
+++ b/modules/proxy/mod_proxy_ajp.c
@@ -70,8 +70,11 @@ static int proxy_ajp_canon(request_rec *r, char *url)
         search = r->args;
     }
     else {
-        path = ap_proxy_canonenc(r->pool, url, strlen(url), enc_path, 0,
-                                 r->proxyreq);
+        core_dir_config *d = ap_get_core_module_config(r->per_dir_config);
+        int flags = d->allow_encoded_slashes  && !d->decode_encoded_slashes ? PROXY_CANONENC_NOENCODEDSLASHENCODING : 0;
+
+        path = ap_proxy_canonenc_ex(r->pool, url, strlen(url), enc_path, flags,
+                                    r->proxyreq);
         search = r->args;
     }
     if (search && *ap_scan_vchar_obstext(search)) {
diff --git a/modules/proxy/mod_proxy_balancer.c b/modules/proxy/mod_proxy_balancer.c
index 0d51011367..8f3a3615cf 100644
--- a/modules/proxy/mod_proxy_balancer.c
+++ b/modules/proxy/mod_proxy_balancer.c
@@ -107,8 +107,11 @@ static int proxy_balancer_canon(request_rec *r, char *url)
         search = r->args;
     }
     else {
-        path = ap_proxy_canonenc(r->pool, url, strlen(url), enc_path, 0,
-                                 r->proxyreq);
+        core_dir_config *d = ap_get_core_module_config(r->per_dir_config);
+        int flags = d->allow_encoded_slashes  && !d->decode_encoded_slashes ? PROXY_CANONENC_NOENCODEDSLASHENCODING : 0;
+
+        path = ap_proxy_canonenc_ex(r->pool, url, strlen(url), enc_path, flags,
+                                    r->proxyreq);
         search = r->args;
     }
     if (search && *ap_scan_vchar_obstext(search)) {
diff --git a/modules/proxy/mod_proxy_fcgi.c b/modules/proxy/mod_proxy_fcgi.c
index a89b9a9c7b..dd58e1bcce 100644
--- a/modules/proxy/mod_proxy_fcgi.c
+++ b/modules/proxy/mod_proxy_fcgi.c
@@ -97,8 +97,11 @@ static int proxy_fcgi_canon(request_rec *r, char *url)
         path = url;   /* this is the raw/encoded path */
     }
     else {
-        path = ap_proxy_canonenc(r->pool, url, strlen(url), enc_path, 0,
-                             r->proxyreq);
+        core_dir_config *d = ap_get_core_module_config(r->per_dir_config);
+        int flags = d->allow_encoded_slashes  && !d->decode_encoded_slashes ? PROXY_CANONENC_NOENCODEDSLASHENCODING : 0;
+
+        path = ap_proxy_canonenc_ex(r->pool, url, strlen(url), enc_path, flags,
+                                    r->proxyreq);
     }
     if (path == NULL)
         return HTTP_BAD_REQUEST;
diff --git a/modules/proxy/mod_proxy_ftp.c b/modules/proxy/mod_proxy_ftp.c
index a63b09929b..8b75d97c7e 100644
--- a/modules/proxy/mod_proxy_ftp.c
+++ b/modules/proxy/mod_proxy_ftp.c
@@ -289,6 +289,8 @@ static int proxy_ftp_canon(request_rec *r, char *url)
     apr_pool_t *p = r->pool;
     const char *err;
     apr_port_t port, def_port;
+    core_dir_config *d = ap_get_core_module_config(r->per_dir_config);
+    int flags = d->allow_encoded_slashes  && !d->decode_encoded_slashes ? PROXY_CANONENC_NOENCODEDSLASHENCODING : 0;
 
     /* */
     if (ap_cstr_casecmpn(url, "ftp:", 4) == 0) {
@@ -327,7 +329,8 @@ static int proxy_ftp_canon(request_rec *r, char *url)
     else
         parms = "";
 
-    path = ap_proxy_canonenc(p, url, strlen(url), enc_path, 0, r->proxyreq);
+    path = ap_proxy_canonenc_ex(p, url, strlen(url), enc_path, flags,
+                                r->proxyreq);
     if (path == NULL)
         return HTTP_BAD_REQUEST;
     if (!ftp_check_string(path))
diff --git a/modules/proxy/mod_proxy_http.c b/modules/proxy/mod_proxy_http.c
index 1ec5fe1134..23c5b691f7 100644
--- a/modules/proxy/mod_proxy_http.c
+++ b/modules/proxy/mod_proxy_http.c
@@ -123,8 +123,11 @@ static int proxy_http_canon(request_rec *r, char *url)
             search = r->args;
         }
         else {
-            path = ap_proxy_canonenc(r->pool, url, strlen(url),
-                                     enc_path, 0, r->proxyreq);
+            core_dir_config *d = ap_get_core_module_config(r->per_dir_config);
+            int flags = d->allow_encoded_slashes  && !d->decode_encoded_slashes ? PROXY_CANONENC_NOENCODEDSLASHENCODING : 0;
+
+            path = ap_proxy_canonenc_ex(r->pool, url, strlen(url), enc_path,
+                                        flags, r->proxyreq);
             search = r->args;
         }
         if (search && *ap_scan_vchar_obstext(search)) {
diff --git a/modules/proxy/mod_proxy_scgi.c b/modules/proxy/mod_proxy_scgi.c
index 493757d3c9..4674ccf906 100644
--- a/modules/proxy/mod_proxy_scgi.c
+++ b/modules/proxy/mod_proxy_scgi.c
@@ -179,6 +179,8 @@ static int scgi_canon(request_rec *r, char *url)
     char *host, sport[sizeof(":65535")];
     const char *err, *path;
     apr_port_t port, def_port;
+    core_dir_config *d = ap_get_core_module_config(r->per_dir_config);
+    int flags = d->allow_encoded_slashes  && !d->decode_encoded_slashes ? PROXY_CANONENC_NOENCODEDSLASHENCODING : 0;
 
     if (ap_cstr_casecmpn(url, SCHEME "://", sizeof(SCHEME) + 2)) {
         return DECLINED;
@@ -205,8 +207,8 @@ static int scgi_canon(request_rec *r, char *url)
         host = apr_pstrcat(r->pool, "[", host, "]", NULL);
     }
 
-    path = ap_proxy_canonenc(r->pool, url, strlen(url), enc_path, 0,
-                             r->proxyreq);
+    path = ap_proxy_canonenc_ex(r->pool, url, strlen(url), enc_path, flags,
+                                r->proxyreq);
     if (!path) {
         return HTTP_BAD_REQUEST;
     }
diff --git a/modules/proxy/mod_proxy_uwsgi.c b/modules/proxy/mod_proxy_uwsgi.c
index 720dfa8487..1a56bb88b5 100644
--- a/modules/proxy/mod_proxy_uwsgi.c
+++ b/modules/proxy/mod_proxy_uwsgi.c
@@ -89,8 +89,11 @@ static int uwsgi_canon(request_rec *r, char *url)
         path = url;   /* this is the raw/encoded path */
     }
     else {
-        path = ap_proxy_canonenc(r->pool, url, strlen(url), enc_path, 0,
-                                 r->proxyreq);
+        core_dir_config *d = ap_get_core_module_config(r->per_dir_config);
+        int flags = d->allow_encoded_slashes  && !d->decode_encoded_slashes ? PROXY_CANONENC_NOENCODEDSLASHENCODING : 0;
+
+        path = ap_proxy_canonenc_ex(r->pool, url, strlen(url), enc_path, flags,
+                                    r->proxyreq);
     }
     if (!path) {
         return HTTP_BAD_REQUEST;
diff --git a/modules/proxy/mod_proxy_wstunnel.c b/modules/proxy/mod_proxy_wstunnel.c
index d1db872e11..81f932a864 100644
--- a/modules/proxy/mod_proxy_wstunnel.c
+++ b/modules/proxy/mod_proxy_wstunnel.c
@@ -200,8 +200,11 @@ static int proxy_wstunnel_canon(request_rec *r, char *url)
         search = r->args;
     }
     else {
-        path = ap_proxy_canonenc(r->pool, url, strlen(url), enc_path, 0,
-                                 r->proxyreq);
+        core_dir_config *d = ap_get_core_module_config(r->per_dir_config);
+        int flags = d->allow_encoded_slashes  && !d->decode_encoded_slashes ? PROXY_CANONENC_NOENCODEDSLASHENCODING : 0;
+
+        path = ap_proxy_canonenc_ex(r->pool, url, strlen(url), enc_path, flags,
+                                    r->proxyreq);
         search = r->args;
     }
     if (search && *ap_scan_vchar_obstext(search)) {
diff --git a/modules/proxy/proxy_util.c b/modules/proxy/proxy_util.c
index 3dacec38ee..7d0062b89f 100644
--- a/modules/proxy/proxy_util.c
+++ b/modules/proxy/proxy_util.c
@@ -200,14 +200,16 @@ PROXY_DECLARE(void) ap_proxy_c2hex(int ch, char *x)
  * and encodes those which must be encoded, and does not touch
  * those which must not be touched.
  */
-PROXY_DECLARE(char *)ap_proxy_canonenc(apr_pool_t *p, const char *x, int len,
-                                       enum enctype t, int forcedec,
-                                       int proxyreq)
+PROXY_DECLARE(char *)ap_proxy_canonenc_ex(apr_pool_t *p, const char *x, int len,
+                                          enum enctype t, int flags,
+                                          int proxyreq)
 {
     int i, j, ch;
     char *y;
     char *allowed;  /* characters which should not be encoded */
     char *reserved; /* characters which much not be en/de-coded */
+    int forcedec = flags & PROXY_CANONENC_FORCEDEC;
+    int noencslashesenc = flags & PROXY_CANONENC_NOENCODEDSLASHENCODING;
 
 /*
  * N.B. in addition to :@&=, this allows ';' in an http path
@@ -256,7 +258,8 @@ PROXY_DECLARE(char *)ap_proxy_canonenc(apr_pool_t *p, const char *x, int len,
  * decode it if not already done. do not decode reverse proxied URLs
  * unless specifically forced
  */
-        if ((forcedec || (proxyreq && proxyreq != PROXYREQ_REVERSE)) && ch == '%') {
+        if ((forcedec || noencslashesenc
+            ||(proxyreq && proxyreq != PROXYREQ_REVERSE)) && ch == '%') {
             if (!apr_isxdigit(x[i + 1]) || !apr_isxdigit(x[i + 2])) {
                 return NULL;
             }
@@ -267,7 +270,17 @@ PROXY_DECLARE(char *)ap_proxy_canonenc(apr_pool_t *p, const char *x, int len,
                 y[j] = x[i];
                 continue;
             }
-            i += 2;
+            if (noencslashesenc && !forcedec && (proxyreq == PROXYREQ_REVERSE)) {
+                /*
+                 * In the reverse proxy case when we only want to keep encoded
+                 * slashes untouched revert back to '%' which will cause
+                 * '%' to be encoded in the following.
+                 */
+                ch = '%';
+            }
+            else {
+                i += 2;
+            }
         }
 /* recode it, if necessary */
         if (!apr_isalnum(ch) && !strchr(allowed, ch)) {
@@ -283,6 +296,22 @@ PROXY_DECLARE(char *)ap_proxy_canonenc(apr_pool_t *p, const char *x, int len,
 }
 
 /*
+ * Convert a URL-encoded string to canonical form.
+ * It decodes characters which need not be encoded,
+ * and encodes those which must be encoded, and does not touch
+ * those which must not be touched.
+ */
+PROXY_DECLARE(char *)ap_proxy_canonenc(apr_pool_t *p, const char *x, int len,
+                                       enum enctype t, int forcedec,
+                                       int proxyreq)
+{
+    int flags;
+
+    flags = forcedec ? PROXY_CANONENC_FORCEDEC : 0;
+    return ap_proxy_canonenc_ex(p, x, len, t, flags, proxyreq);
+}
+
+/*
  * Parses network-location.
  *    urlp           on input the URL; on output the path, after the leading /
  *    user           NULL if no user/password permitted