httpserver/all: Clean up and standardize request URL handling (#1633)

* httpserver/all: Clean up and standardize request URL handling

The HTTP server now always creates a context value on the request which
is a copy of the request's URL struct. It should not be modified by
middlewares, but it is safe to get the value out of the request and make
changes to it locally-scoped. Thus, the value in the context always
stores the original request URL information as it was received. Any
rewrites that happen will be to the request's URL field directly.

The HTTP server no longer cleans /sanitizes the request URL. It made too
many strong assumptions and ended up making a lot of middleware more
complicated, including upstream proxying (and fastcgi). To alleviate
this complexity, we no longer change the request URL. Middlewares are
responsible to access the disk safely by using http.Dir or, if not
actually opening files, they can use httpserver.SafePath().

I'm hoping this will address issues with #1624, #1584, #1582, and others.

* staticfiles: Fix test on Windows

@abiosoft: I still can't figure out exactly what this is for. 😅

* Use (potentially) changed URL for browse redirects, as before

* Use filepath.ToSlash, clean up a couple proxy test cases

* Oops, fix variable name
This commit is contained in:
Matt Holt 2017-05-01 23:11:10 -06:00 committed by GitHub
parent 5685a16449
commit d5371aff22
23 changed files with 366 additions and 574 deletions

View file

@ -9,7 +9,10 @@ import (
"log"
"net"
"net/http"
"net/url"
"os"
"path"
"path/filepath"
"runtime"
"strings"
"sync"
@ -290,11 +293,18 @@ func (s *Server) ServeHTTP(w http.ResponseWriter, r *http.Request) {
}
}()
w.Header().Set("Server", "Caddy")
c := context.WithValue(r.Context(), staticfiles.URLPathCtxKey, r.URL.Path)
// copy the original, unchanged URL into the context
// so it can be referenced by middlewares
urlCopy := *r.URL
if r.URL.User != nil {
userInfo := new(url.Userinfo)
*userInfo = *r.URL.User
urlCopy.User = userInfo
}
c := context.WithValue(r.Context(), OriginalURLCtxKey, urlCopy)
r = r.WithContext(c)
sanitizePath(r)
w.Header().Set("Server", "Caddy")
status, _ := s.serveHTTP(w, r)
@ -353,6 +363,7 @@ func (s *Server) serveHTTP(w http.ResponseWriter, r *http.Request) (int, error)
// The error returned by MaxBytesReader is meant to be handled
// by whichever middleware/plugin that receives it when calling
// .Read() or a similar method on the request body
// TODO: Make this middleware instead?
if r.Body != nil {
for _, pathlimit := range vhost.MaxRequestBodySizes {
if Path(r.URL.Path).Matches(pathlimit.Path) {
@ -407,28 +418,6 @@ func (s *Server) Stop() error {
return nil
}
// sanitizePath collapses any ./ ../ /// madness which helps prevent
// path traversal attacks. Note to middleware: use the value within the
// request's context at key caddy.URLPathContextKey to access the
// "original" URL.Path value.
func sanitizePath(r *http.Request) {
if r.URL.Path == "/" {
return
}
cleanedPath := CleanPath(r.URL.Path)
if cleanedPath == "." {
r.URL.Path = "/"
} else {
if !strings.HasPrefix(cleanedPath, "/") {
cleanedPath = "/" + cleanedPath
}
if strings.HasSuffix(r.URL.Path, "/") && !strings.HasSuffix(cleanedPath, "/") {
cleanedPath = cleanedPath + "/"
}
r.URL.Path = cleanedPath
}
}
// OnStartupComplete lists the sites served by this server
// and any relevant information, assuming caddy.Quiet == false.
func (s *Server) OnStartupComplete() {
@ -558,3 +547,20 @@ func WriteTextResponse(w http.ResponseWriter, status int, body string) {
w.WriteHeader(status)
w.Write([]byte(body))
}
// SafePath joins siteRoot and reqPath and converts it to a path that can
// be used to access a path on the local disk. It ensures the path does
// not traverse outside of the site root.
//
// If opening a file, use http.Dir instead.
func SafePath(siteRoot, reqPath string) string {
reqPath = filepath.ToSlash(reqPath)
reqPath = strings.Replace(reqPath, "\x00", "", -1) // NOTE: Go 1.9 checks for null bytes in the syscall package
if siteRoot == "" {
siteRoot = "."
}
return filepath.Join(siteRoot, filepath.FromSlash(path.Clean("/"+reqPath)))
}
// OriginalURLCtxKey is the key for accessing the original, incoming URL on an HTTP request.
const OriginalURLCtxKey = caddy.CtxKey("original_url")