Files
seaweedfs/weed/server/filer_server_handlers.go
T
Chris LuandClaude Opus 5.5 533f5060b9 filer: scope a prefix JWT to the directory a zip extract writes under (#12305)
* filer: scope a prefix JWT to the directory a zip extract writes under

Without a trailing slash, an extract request writes members beside the
named path, in its parent directory, while the JWT check only saw the
request path. A token scoped to /tenant1 could therefore extract into /
by posting to /tenant1?extract=zip. Add the extract root to the paths a
prefix-restricted token must cover.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

* filer: do not keep an extracted archive under the name ".."

A multipart file name of ".." passes path.Base unchanged, so
extract.keep stored the archive as an entry literally named ".." in the
target directory, a name that local sinks resolve to the parent.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

* leveldb3: keep a non-local bucket name out of the per-bucket folder

findDB splits the bucket out of a /buckets/ path and uses it as a folder
name under the store directory. The name cannot hold a slash and dot
names already go to the default DB, so this only rejects an empty or
non-local name, but it also lets static analysis see the folder cannot
escape the store directory.

* filer: clean the zip extract root before scoping and writing

A percent-encoded dot segment survives the path cleaning in front of the
mux, so a request path ending in "/" reached extractZipRoot with ".."
in it. The JWT scope check cleans the path it compares, but the members
were written under the raw root, so the two could disagree.

* leveldb3: apply the bucket folder check to bucket create and delete events

findDB already keeps dot and non-local bucket names out of the per-bucket
folders, but OnBucketCreation and OnBucketDeletion used the name as is. A
directory event for /buckets/.. opened a DB in the parent of the store
directory, and its delete removed that parent.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

* leveldb3: keep a bucket delete event off the default DB

A bucket named _main maps to the default DB in findDB, so deleting
/buckets/_main closed the default DB and removed its folder, taking every
non-bucket entry with it.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

* leveldb3: keep bucket names with a path separator out of the store dir

A bucket event named x/../_main passed the local-name check, and its
delete removed the default DB folder once store.dir/x existed.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

* leveldb3: only reject the platform separator in a bucket name

A backslash is an ordinary file name character on Unix, and a bucket
folder named that way already exists for anyone who created one. Rejecting
it on every platform would route those entries to the default DB after an
upgrade. The slash can never appear in a bucket name here, and on Windows
the backslash is the separator, so rejecting os.PathSeparator alongside
the slash keeps the folder flat without changing Unix routing.

* leveldb3: check for an escaped bucket db before its delete event

---------

Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-01 18:36:31 -08:00

375 lines
12 KiB
Go

package weed_server
import (
"context"
"errors"
"net/http"
"path"
"strconv"
"strings"
"sync/atomic"
"time"
"github.com/seaweedfs/seaweedfs/weed/filer"
"github.com/seaweedfs/seaweedfs/weed/glog"
"github.com/seaweedfs/seaweedfs/weed/pb/filer_pb"
"github.com/seaweedfs/seaweedfs/weed/security"
"github.com/seaweedfs/seaweedfs/weed/stats"
util_http "github.com/seaweedfs/seaweedfs/weed/util/http"
"github.com/seaweedfs/seaweedfs/weed/util/version"
)
func (fs *FilerServer) filerHandler(w http.ResponseWriter, r *http.Request) {
start := time.Now()
inFlightGauge := stats.FilerInFlightRequestsGauge.WithLabelValues(r.Method)
inFlightGauge.Inc()
defer inFlightGauge.Dec()
statusRecorder := stats.NewStatusResponseWriter(w)
w = statusRecorder
origin := r.Header.Get("Origin")
if origin != "" {
if fs.option.AllowedOrigins == nil || len(fs.option.AllowedOrigins) == 0 || fs.option.AllowedOrigins[0] == "*" {
origin = "*"
} else {
originFound := false
for _, allowedOrigin := range fs.option.AllowedOrigins {
if origin == allowedOrigin {
originFound = true
}
}
if !originFound {
writeJsonError(w, r, http.StatusForbidden, errors.New("origin not allowed"))
return
}
}
w.Header().Set("Access-Control-Allow-Origin", origin)
w.Header().Set("Access-Control-Expose-Headers", "*")
w.Header().Set("Access-Control-Allow-Headers", "*")
w.Header().Set("Access-Control-Allow-Credentials", "true")
w.Header().Set("Access-Control-Allow-Methods", "PUT, POST, GET, DELETE, OPTIONS")
}
if r.Method == http.MethodOptions {
OptionsHandler(w, r, false)
return
}
requestMethod := r.Method
defer func(method *string) {
stats.FilerRequestCounter.WithLabelValues(*method, strconv.Itoa(statusRecorder.Status)).Inc()
stats.FilerRequestHistogram.WithLabelValues(*method).Observe(time.Since(start).Seconds())
}(&requestMethod)
isReadHttpCall := r.Method == http.MethodGet || r.Method == http.MethodHead
if !fs.maybeCheckJwtAuthorization(r, !isReadHttpCall) {
writeJsonError(w, r, http.StatusUnauthorized, errors.New("wrong jwt"))
return
}
// proxy to volume servers, after the gate: this is the one port operators
// expose, and the branch reaches any needle in the cluster by file id.
if r.URL.Path == "/" {
if fileId := r.URL.Query().Get(util_http.ProxyChunkIdParam); fileId != "" {
fs.proxyToVolumeServer(w, r, fileId)
stats.FilerHandlerCounter.WithLabelValues(stats.ChunkProxy).Inc()
// Name the deferred observation after the proxy rather than
// observing a second time, which would count the request twice.
requestMethod = stats.ChunkProxy
return
}
}
w.Header().Set("Server", "SeaweedFS "+version.VERSION)
switch r.Method {
case http.MethodGet, http.MethodHead:
fs.GetOrHeadHandler(w, r)
case http.MethodDelete:
if _, ok := r.URL.Query()["tagging"]; ok {
fs.DeleteTaggingHandler(w, r)
} else {
fs.DeleteHandler(w, r)
}
case http.MethodPost, http.MethodPut:
// wait until in flight data is less than the limit
contentLength := getContentLength(r)
fs.inFlightDataLimitCond.L.Lock()
inFlightDataSize := atomic.LoadInt64(&fs.inFlightDataSize)
inFlightUploads := atomic.LoadInt64(&fs.inFlightUploads)
// Wait if either data size limit or file count limit is exceeded
for (fs.option.ConcurrentUploadLimit != 0 && inFlightDataSize > fs.option.ConcurrentUploadLimit) || (fs.option.ConcurrentFileUploadLimit != 0 && inFlightUploads >= fs.option.ConcurrentFileUploadLimit) {
if fs.option.ConcurrentUploadLimit != 0 && inFlightDataSize > fs.option.ConcurrentUploadLimit {
glog.V(4).Infof("wait because inflight data %d > %d", inFlightDataSize, fs.option.ConcurrentUploadLimit)
}
if fs.option.ConcurrentFileUploadLimit != 0 && inFlightUploads >= fs.option.ConcurrentFileUploadLimit {
glog.V(4).Infof("wait because inflight uploads %d >= %d", inFlightUploads, fs.option.ConcurrentFileUploadLimit)
}
fs.inFlightDataLimitCond.Wait()
inFlightDataSize = atomic.LoadInt64(&fs.inFlightDataSize)
inFlightUploads = atomic.LoadInt64(&fs.inFlightUploads)
}
fs.inFlightDataLimitCond.L.Unlock()
// Increment counters
newUploads := atomic.AddInt64(&fs.inFlightUploads, 1)
newSize := atomic.AddInt64(&fs.inFlightDataSize, contentLength)
// Update metrics
stats.FilerInFlightUploadCountGauge.Set(float64(newUploads))
stats.FilerInFlightUploadBytesGauge.Set(float64(newSize))
defer func() {
// Decrement counters
newUploads := atomic.AddInt64(&fs.inFlightUploads, -1)
newSize := atomic.AddInt64(&fs.inFlightDataSize, -contentLength)
// Update metrics
stats.FilerInFlightUploadCountGauge.Set(float64(newUploads))
stats.FilerInFlightUploadBytesGauge.Set(float64(newSize))
fs.inFlightDataLimitCond.Signal()
}()
if r.Method == http.MethodPut {
if _, ok := r.URL.Query()["tagging"]; ok {
fs.PutTaggingHandler(w, r)
} else {
fs.PostHandler(w, r, contentLength)
}
} else { // method == "POST"
fs.PostHandler(w, r, contentLength)
}
default:
requestMethod = "INVALID"
w.WriteHeader(http.StatusMethodNotAllowed)
}
}
func (fs *FilerServer) readonlyFilerHandler(w http.ResponseWriter, r *http.Request) {
start := time.Now()
statusRecorder := stats.NewStatusResponseWriter(w)
w = statusRecorder
glog.V(4).Infof("Request: %s %s", r.Method, r.URL.Path)
origin := r.Header.Get("Origin")
if origin != "" {
if fs.option.AllowedOrigins == nil || len(fs.option.AllowedOrigins) == 0 || fs.option.AllowedOrigins[0] == "*" {
origin = "*"
} else {
originFound := false
for _, allowedOrigin := range fs.option.AllowedOrigins {
if origin == allowedOrigin {
originFound = true
}
}
if !originFound {
writeJsonError(w, r, http.StatusForbidden, errors.New("origin not allowed"))
return
}
}
w.Header().Set("Access-Control-Allow-Origin", origin)
w.Header().Set("Access-Control-Allow-Headers", "OPTIONS, GET, HEAD")
w.Header().Set("Access-Control-Allow-Credentials", "true")
}
requestMethod := r.Method
defer func(method *string) {
stats.FilerRequestCounter.WithLabelValues(*method, strconv.Itoa(statusRecorder.Status)).Inc()
stats.FilerRequestHistogram.WithLabelValues(*method).Observe(time.Since(start).Seconds())
}(&requestMethod)
// We handle OPTIONS first because it never should be authenticated
if r.Method == http.MethodOptions {
OptionsHandler(w, r, true)
return
}
if !fs.maybeCheckJwtAuthorization(r, false) {
writeJsonError(w, r, http.StatusUnauthorized, errors.New("wrong jwt"))
return
}
w.Header().Set("Server", "SeaweedFS "+version.VERSION)
switch r.Method {
case http.MethodGet, http.MethodHead:
fs.GetOrHeadHandler(w, r)
default:
requestMethod = "INVALID"
w.WriteHeader(http.StatusMethodNotAllowed)
}
}
func OptionsHandler(w http.ResponseWriter, r *http.Request, isReadOnly bool) {
if isReadOnly {
w.Header().Set("Access-Control-Allow-Methods", "GET, OPTIONS")
} else {
w.Header().Set("Access-Control-Allow-Methods", "PUT, POST, GET, DELETE, OPTIONS")
w.Header().Set("Access-Control-Expose-Headers", "*")
}
w.Header().Set("Access-Control-Allow-Headers", "*")
w.Header().Set("Access-Control-Allow-Credentials", "true")
}
// maybeCheckJwtAuthorization returns true if access should be granted, false if it should be denied
func (fs *FilerServer) maybeCheckJwtAuthorization(r *http.Request, isWrite bool) bool {
return fs.checkJwtAuthorization(r, isWrite, jwtScopedRequestPaths(r))
}
// checkJwtAuthorization verifies the request carries a valid filer JWT for the
// requested access level and, for prefix-restricted tokens, that every path in
// scopedPaths falls within AllowedPrefixes.
func (fs *FilerServer) checkJwtAuthorization(r *http.Request, isWrite bool, scopedPaths []string) bool {
claims, ok := fs.authenticateFilerJwt(r, isWrite)
if !ok {
return false
}
return authorizeFilerJwtPaths(r, claims, scopedPaths)
}
// authenticateFilerJwt verifies the JWT signature and method claims. A nil claims
// with ok true means authentication is disabled for this access level. Splitting
// authentication from path authorization lets a handler load an indirect resource
// (the TUS session target) only after the caller's credential is verified.
func (fs *FilerServer) authenticateFilerJwt(r *http.Request, isWrite bool) (*security.SeaweedFilerClaims, bool) {
var signingKey security.SigningKey
if isWrite {
signingKey = fs.filerGuard.SigningKey()
} else {
signingKey = fs.filerGuard.ReadSigningKey()
}
if len(signingKey) == 0 {
return nil, true
}
tokenStr := security.GetJwt(r)
if tokenStr == "" {
glog.V(1).Infof("missing jwt from %s", r.RemoteAddr)
return nil, false
}
token, err := security.DecodeJwt(signingKey, tokenStr, &security.SeaweedFilerClaims{})
if err != nil {
glog.V(1).Infof("jwt verification error from %s: %v", r.RemoteAddr, err)
return nil, false
}
if !token.Valid {
glog.V(1).Infof("jwt invalid from %s: %v", r.RemoteAddr, tokenStr)
return nil, false
}
claims, ok := token.Claims.(*security.SeaweedFilerClaims)
if !ok {
glog.V(1).Infof("jwt claims not of type *SeaweedFilerClaims from %s", r.RemoteAddr)
return nil, false
}
if claims.SessionId != "" {
glog.V(1).Infof("jwt is an STS session token, not a filer credential, from %s", r.RemoteAddr)
return nil, false
}
if len(claims.AllowedMethods) > 0 {
hasMethod := false
for _, method := range claims.AllowedMethods {
if method == r.Method {
hasMethod = true
break
}
}
if !hasMethod {
glog.V(1).Infof("jwt method not allowed from %s: %v", r.RemoteAddr, r.Method)
return nil, false
}
}
return claims, true
}
// authorizeFilerJwtPaths checks the resource scope after authentication. A
// prefix-restricted token must name at least one resource path; an empty list
// fails closed, so a caller that cannot resolve its target never falls open.
func authorizeFilerJwtPaths(r *http.Request, claims *security.SeaweedFilerClaims, scopedPaths []string) bool {
if claims == nil || len(claims.AllowedPrefixes) == 0 {
return true
}
if len(scopedPaths) == 0 {
glog.V(1).Infof("jwt resource path missing from %s", r.RemoteAddr)
return false
}
for _, p := range scopedPaths {
if !anyComponentPrefixMatches(claims.AllowedPrefixes, p) {
glog.V(1).Infof("jwt path not allowed from %s: %v", r.RemoteAddr, p)
return false
}
}
return true
}
// jwtScopedRequestPaths returns every filer path a request touches that must be
// covered by the JWT AllowedPrefixes: the write target (r.URL.Path), the
// directory a zip extract writes under, and any copy/move source named by the
// cp.from / mv.from query parameters.
func jwtScopedRequestPaths(r *http.Request) []string {
paths := []string{r.URL.Path}
if (r.Method == http.MethodPost || r.Method == http.MethodPut) && isExtractZip(r) {
paths = append(paths, extractZipRoot(r)+"/")
}
if query := r.URL.Query(); query.Has("cp.from") || query.Has("mv.from") {
if from := query.Get("cp.from"); from != "" {
paths = append(paths, from)
}
if from := query.Get("mv.from"); from != "" {
paths = append(paths, from)
}
}
return paths
}
// anyComponentPrefixMatches reports whether p is within any of the prefixes.
func anyComponentPrefixMatches(prefixes []string, p string) bool {
for _, prefix := range prefixes {
if pathHasComponentPrefix(p, prefix) {
return true
}
}
return false
}
// pathHasComponentPrefix reports whether reqPath is contained within the
// directory subtree denoted by prefix, treating both as "/"-separated
// path components. Both inputs are normalised with path.Clean to neutralise
// "." and ".." segments and collapse duplicate slashes. A prefix of "/"
// matches any path.
func pathHasComponentPrefix(reqPath, prefix string) bool {
if prefix == "" {
return false
}
cleanedPath := path.Clean(reqPath)
if cleanedPath == "." {
cleanedPath = "/"
}
cleanedPrefix := path.Clean(prefix)
if cleanedPrefix == "." {
cleanedPrefix = "/"
}
if cleanedPrefix == "/" {
return true
}
if cleanedPath == cleanedPrefix {
return true
}
return strings.HasPrefix(cleanedPath, cleanedPrefix+"/")
}
func (fs *FilerServer) filerHealthzHandler(w http.ResponseWriter, r *http.Request) {
w.Header().Set("Server", "SeaweedFS "+version.VERSION)
if _, err := fs.filer.Store.FindEntry(context.Background(), filer.TopicsDir); err != nil && err != filer_pb.ErrNotFound {
glog.Warningf("filerHealthzHandler FindEntry: %+v", err)
w.WriteHeader(http.StatusServiceUnavailable)
} else {
w.WriteHeader(http.StatusOK)
}
}