internal/storage/file.go

@@ -120,9 +120,10 @@ func (f *FileStorer) Delete(_ context.Context, key string) error {
 	return nil
 }
 
-// List returns all keys with the given prefix. It fails when the
+// List returns all keys with the given prefix, reading through symlinked
-// destination directory is missing; a missing prefix under it is an
+// directories. It fails when the destination directory is missing, or
-// empty listing.
+// when the prefix or a directory above it is a symlink whose target is
+// missing; a prefix that is truly missing is an empty listing.
 func (f *FileStorer) List(ctx context.Context, prefix string) ([]string, error) {
 	var keys []string
 
@@ -133,8 +134,7 @@ func (f *FileStorer) List(ctx context.Context, prefix string) ([]string, error)
 
 	basePath := f.fullPath(prefix)
 
-	// Check if the prefix exists
+	exists, err := f.prefixExists(prefix)
-	exists, err := afero.Exists(f.fs, basePath)
 	if err != nil {
 		return nil, fmt.Errorf("checking path: %w", err)
 	}
@@ -143,7 +143,7 @@ func (f *FileStorer) List(ctx context.Context, prefix string) ([]string, error)
 		return keys, nil // Empty list for non-existent prefix
 	}
 
-	err = afero.Walk(f.fs, basePath, func(path string, info os.FileInfo, err error) error {
+	err = f.walk(basePath, func(path string, info os.FileInfo, err error) error {
 		if err != nil {
 			return err
 		}
@@ -176,7 +176,9 @@ func (f *FileStorer) List(ctx context.Context, prefix string) ([]string, error)
 }
 
 // ListStream returns a channel of ObjectInfo for large result sets. Like
-// List, it sends an error when the destination directory is missing.
+// List, it reads through symlinked directories and sends an error when
+// the destination directory is missing, or when the prefix or a directory
+// above it is a symlink whose target is missing.
 func (f *FileStorer) ListStream(ctx context.Context, prefix string) <-chan ObjectInfo {
 	ch := make(chan ObjectInfo)
 
@@ -192,8 +194,7 @@ func (f *FileStorer) ListStream(ctx context.Context, prefix string) <-chan Objec
 
 		basePath := f.fullPath(prefix)
 
-		// Check if the prefix exists
+		exists, err := f.prefixExists(prefix)
-		exists, err := afero.Exists(f.fs, basePath)
 		if err != nil {
 			ch <- ObjectInfo{Err: fmt.Errorf("checking path: %w", err)}
 
@@ -204,7 +205,7 @@ func (f *FileStorer) ListStream(ctx context.Context, prefix string) <-chan Objec
 			return // Empty channel for non-existent prefix
 		}
 
-		_ = afero.Walk(f.fs, basePath, func(path string, info os.FileInfo, err error) error {
+		_ = f.walk(basePath, func(path string, info os.FileInfo, err error) error {
 			// Check context cancellation
 			select {
 			case <-ctx.Done():
@@ -243,11 +244,12 @@ func (f *FileStorer) ListStream(ctx context.Context, prefix string) <-chan Objec
 }
 
 // DeletePartialUploads removes every file under prefix whose name ends in
-// tempSuffix. A missing prefix has none to remove.
+// tempSuffix. Like List, it reads through symlinked directories and fails
+// on one whose target is missing. A missing prefix has none to remove.
 func (f *FileStorer) DeletePartialUploads(ctx context.Context, prefix string) error {
 	basePath := f.fullPath(prefix)
 
-	exists, err := afero.Exists(f.fs, basePath)
+	exists, err := f.prefixExists(prefix)
 	if err != nil {
 		return fmt.Errorf("checking path: %w", err)
 	}
@@ -256,7 +258,7 @@ func (f *FileStorer) DeletePartialUploads(ctx context.Context, prefix string) er
 		return nil
 	}
 
-	err = afero.Walk(f.fs, basePath, func(path string, info os.FileInfo, err error) error {
+	err = f.walk(basePath, func(path string, info os.FileInfo, err error) error {
 		if err != nil {
 			return err
 		}
@@ -352,6 +354,54 @@ func (f *FileStorer) writeAtomic(
 	return nil
 }
 
+// walk is afero.Walk, except that it reads through a symlinked directory
+// the way Get and Stat do, where afero.Walk reports the link as one file.
+// afero.Walk uses Lstat, which does not follow a link, whenever the
+// filesystem has one; the struct below carries only the afero.Fs methods,
+// so the walk uses Stat instead. A link back up the tree is followed until
+// the operating system refuses the path for too many levels of links, and
+// the walk then fails.
+func (f *FileStorer) walk(root string, fn filepath.WalkFunc) error {
+	return afero.Walk(struct{ afero.Fs }{f.fs}, root, fn)
+}
+
+// prefixExists reports whether prefix exists under the destination
+// directory. It checks each directory on the way down to prefix in turn,
+// and the first one Stat cannot find decides: if it is not there at all,
+// prefix is missing; if it is a symlink whose target is missing, such as
+// a link to a volume that is not mounted, prefixExists fails, since
+// listing it as empty would let prune delete every blob.
+func (f *FileStorer) prefixExists(prefix string) (bool, error) {
+	lstater, canLstat := f.fs.(afero.Lstater)
+	path := f.basePath
+
+	for name := range strings.SplitSeq(prefix, "/") {
+		path = filepath.Join(path, name)
+
+		_, err := f.fs.Stat(path)
+		if err == nil {
+			continue
+		}
+
+		if !os.IsNotExist(err) {
+			return false, err
+		}
+
+		// Lstat does not follow a symlink at path, so it finds the link
+		// that Stat could not follow.
+		if canLstat {
+			_, _, lstatErr := lstater.LstatIfPossible(path)
+			if lstatErr == nil {
+				return false, err
+			}
+		}
+
+		return false, nil
+	}
+
+	return true, nil
+}
+
 // fullPath returns the full filesystem path for a key.
 func (f *FileStorer) fullPath(key string) string {
 	return filepath.Join(f.basePath, key)

internal/storage/file_backend_test.go

@@ -4,7 +4,10 @@ import (
 	"context"
 	"errors"
 	"io/fs"
+	"os"
 	"path/filepath"
+	"reflect"
+	"strings"
 	"testing"
 
 	"sneak.berlin/go/vaultik/internal/storage"
@@ -60,3 +63,232 @@ func TestFileStorerListMissingDestination(t *testing.T) {
 		t.Errorf("ListStream error = %v, want a not-exist error", streamErr)
 	}
 }
+
+// The two directories at the top of a destination, either of which the
+// tests below replace with a symlink.
+const (
+	metadataDir = "metadata"
+	blobsDir    = "blobs"
+)
+
+// moveBehindSymlink moves base/dir to a directory elsewhere and puts a
+// symlink to it in its place.
+func moveBehindSymlink(t *testing.T, base, dir string) {
+	t.Helper()
+
+	linkPath := filepath.Join(base, dir)
+	movedPath := filepath.Join(t.TempDir(), dir)
+
+	err := os.Rename(linkPath, movedPath)
+	if err != nil {
+		t.Fatalf("moving %s away: %v", dir, err)
+	}
+
+	err = os.Symlink(movedPath, linkPath)
+	if err != nil {
+		t.Fatalf("linking %s: %v", dir, err)
+	}
+}
+
+// TestFileStorerListsThroughSymlinkedDirectory checks that List and
+// ListStream read through a symlinked metadata/ or blobs/ directory, as Get
+// and Stat do, instead of listing the link as one key. Listing the whole
+// destination meets the link part-way through the walk; listing its prefix
+// starts the walk at the link. A prefix missing behind the link lists as
+// empty.
+func TestFileStorerListsThroughSymlinkedDirectory(t *testing.T) {
+	t.Parallel()
+
+	for _, dir := range []string{metadataDir, blobsDir} {
+		t.Run(dir, func(t *testing.T) {
+			t.Parallel()
+
+			base := t.TempDir()
+			key := dir + "/aa/bb/object"
+
+			s, err := storage.NewFileStorer(base)
+			if err != nil {
+				t.Fatalf("NewFileStorer: %v", err)
+			}
+
+			err = s.Put(context.Background(), key, strings.NewReader("data"))
+			if err != nil {
+				t.Fatalf("Put: %v", err)
+			}
+
+			moveBehindSymlink(t, base, dir)
+
+			want := []string{key}
+
+			for _, prefix := range []string{"", dir + "/"} {
+				got := listSorted(t, s, prefix)
+				if !reflect.DeepEqual(got, want) {
+					t.Errorf("List(%q) = %v, want %v", prefix, got, want)
+				}
+
+				got = listStreamKeys(t, s, prefix)
+				if !reflect.DeepEqual(got, want) {
+					t.Errorf("ListStream(%q) = %v, want %v", prefix, got, want)
+				}
+			}
+
+			absent := dir + "/absent/"
+
+			if got := listSorted(t, s, absent); len(got) != 0 {
+				t.Errorf("List(%q) = %v, want empty", absent, got)
+			}
+
+			if got := listStreamKeys(t, s, absent); len(got) != 0 {
+				t.Errorf("ListStream(%q) = %v, want empty", absent, got)
+			}
+		})
+	}
+}
+
+// TestFileStorerListFailsOnSymlinkWithMissingTarget checks that List and
+// ListStream fail on a symlinked metadata/ or blobs/ directory whose target
+// is missing, such as a link to a volume that is not mounted, as they do on
+// a missing destination directory, instead of listing it as empty. That
+// holds for a prefix below the link too.
+func TestFileStorerListFailsOnSymlinkWithMissingTarget(t *testing.T) {
+	t.Parallel()
+
+	ctx := context.Background()
+
+	for _, dir := range []string{metadataDir, blobsDir} {
+		t.Run(dir, func(t *testing.T) {
+			t.Parallel()
+
+			base := t.TempDir()
+
+			s, err := storage.NewFileStorer(base)
+			if err != nil {
+				t.Fatalf("NewFileStorer: %v", err)
+			}
+
+			unmounted := filepath.Join(t.TempDir(), "unmounted")
+
+			err = os.Symlink(unmounted, filepath.Join(base, dir))
+			if err != nil {
+				t.Fatalf("Symlink: %v", err)
+			}
+
+			for _, prefix := range []string{"", dir + "/", dir + "/aa/"} {
+				keys, err := s.List(ctx, prefix)
+				if !errors.Is(err, fs.ErrNotExist) {
+					t.Errorf("List(%q) = %v, %v; want a not-exist error",
+						prefix, keys, err)
+				}
+
+				var streamErr error
+
+				for object := range s.ListStream(ctx, prefix) {
+					if object.Err != nil {
+						streamErr = object.Err
+					}
+				}
+
+				if !errors.Is(streamErr, fs.ErrNotExist) {
+					t.Errorf("ListStream(%q) error = %v, want a not-exist error",
+						prefix, streamErr)
+				}
+			}
+		})
+	}
+}
+
+// TestFileStorerListFailsOnSymlinkLoop checks that a symlink pointing back
+// at the destination makes List and ListStream fail instead of walking it
+// forever.
+func TestFileStorerListFailsOnSymlinkLoop(t *testing.T) {
+	t.Parallel()
+
+	ctx := context.Background()
+	base := t.TempDir()
+
+	s, err := storage.NewFileStorer(base)
+	if err != nil {
+		t.Fatalf("NewFileStorer: %v", err)
+	}
+
+	err = s.Put(ctx, testBlobKey, strings.NewReader("data"))
+	if err != nil {
+		t.Fatalf("Put: %v", err)
+	}
+
+	err = os.Symlink(base, filepath.Join(base, "blobs", "loop"))
+	if err != nil {
+		t.Fatalf("Symlink: %v", err)
+	}
+
+	keys, err := s.List(ctx, "blobs/")
+	if err == nil {
+		t.Errorf("List = %d keys and no error, want an error", len(keys))
+	}
+
+	var streamErr error
+
+	for object := range s.ListStream(ctx, "blobs/") {
+		if object.Err != nil {
+			streamErr = object.Err
+		}
+	}
+
+	if streamErr == nil {
+		t.Error("ListStream sent no error, want one")
+	}
+}
+
+// TestFileStorerDeletePartialUploadsThroughSymlinkedDirectory checks that
+// DeletePartialUploads, which remote nuke uses, removes a leftover temp
+// file behind a symlinked metadata/ or blobs/ directory and keeps the
+// object at the real key.
+func TestFileStorerDeletePartialUploadsThroughSymlinkedDirectory(t *testing.T) {
+	t.Parallel()
+
+	ctx := context.Background()
+
+	for _, dir := range []string{metadataDir, blobsDir} {
+		t.Run(dir, func(t *testing.T) {
+			t.Parallel()
+
+			base := t.TempDir()
+			key := dir + "/aa/bb/object"
+
+			s, err := storage.NewFileStorer(base)
+			if err != nil {
+				t.Fatalf("NewFileStorer: %v", err)
+			}
+
+			err = s.Put(ctx, key, strings.NewReader("data"))
+			if err != nil {
+				t.Fatalf("Put: %v", err)
+			}
+
+			leftover := filepath.Join(base, key+"-123456.partial")
+
+			err = os.WriteFile(leftover, []byte("half"), 0o600)
+			if err != nil {
+				t.Fatalf("writing leftover temp file: %v", err)
+			}
+
+			moveBehindSymlink(t, base, dir)
+
+			err = s.DeletePartialUploads(ctx, dir+"/")
+			if err != nil {
+				t.Fatalf("DeletePartialUploads: %v", err)
+			}
+
+			// leftover runs through the link.
+			_, err = os.Stat(leftover)
+			if !os.IsNotExist(err) {
+				t.Errorf("leftover temp file was not removed: %v", err)
+			}
+
+			_, err = s.Stat(ctx, key)
+			if err != nil {
+				t.Errorf("Stat of the real key: %v", err)
+			}
+		})
+	}
+}

internal/vaultik/symlinked_destination_test.go

@@ -0,0 +1,147 @@
+package vaultik_test
+
+import (
+	"context"
+	"io/fs"
+	"os"
+	"path/filepath"
+	"testing"
+
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+	"sneak.berlin/go/vaultik/internal/log"
+	"sneak.berlin/go/vaultik/internal/vaultik"
+)
+
+// TestPruneDeletesNothingThroughSymlinkedDirectory checks that prune keeps
+// every blob and the local snapshot record when the metadata/ or blobs/
+// directory of a file:// destination is a symlink to a directory elsewhere
+// (https://git.eeqj.de/sneak/vaultik/issues/296). A backup writes through
+// such a link, so prune has to list through it too.
+func TestPruneDeletesNothingThroughSymlinkedDirectory(t *testing.T) {
+	log.Initialize(log.Config{})
+	t.Parallel()
+
+	for _, dir := range []string{"metadata", "blobs"} {
+		t.Run(dir, func(t *testing.T) {
+			t.Parallel()
+
+			ctx := context.Background()
+			storeDir := filepath.Join(t.TempDir(), "store")
+			v, repos, _ := backUpToFileDestination(ctx, t, storeDir)
+			blobFiles := blobFilesIn(t, storeDir)
+			moveBehindSymlink(t, storeDir, dir)
+
+			require.NoError(t, v.Prune(&vaultik.PruneOptions{Force: true}))
+
+			// When blobs/ is the link, these paths run through it.
+			for _, blobFile := range blobFiles {
+				assert.FileExists(t, blobFile, "prune must delete no blob")
+			}
+
+			snapshots, err := repos.Snapshots.ListRecent(ctx, listRecentTestLimit)
+			require.NoError(t, err)
+			assert.Len(t, snapshots, 1, "prune must delete no local snapshot record")
+		})
+	}
+}
+
+// TestPruneFailsOnSymlinkedDirectoryWithMissingTarget checks that prune
+// fails, deleting no blob and keeping the local snapshot record, when the
+// metadata/ or blobs/ directory of a file:// destination is a symlink
+// whose target is missing, as a link to a volume that is not mounted is.
+func TestPruneFailsOnSymlinkedDirectoryWithMissingTarget(t *testing.T) {
+	log.Initialize(log.Config{})
+	t.Parallel()
+
+	for _, dir := range []string{"metadata", "blobs"} {
+		t.Run(dir, func(t *testing.T) {
+			t.Parallel()
+
+			ctx := context.Background()
+			storeDir := filepath.Join(t.TempDir(), "store")
+			v, repos, _ := backUpToFileDestination(ctx, t, storeDir)
+			blobFiles := blobFilesIn(t, storeDir)
+			targetPath := moveBehindSymlink(t, storeDir, dir)
+
+			// Unmount the volume the link points to, and mount it again
+			// once prune has run.
+			unmountedPath := targetPath + "-unmounted"
+			require.NoError(t, os.Rename(targetPath, unmountedPath))
+
+			err := v.Prune(&vaultik.PruneOptions{Force: true})
+			require.ErrorIs(t, err, fs.ErrNotExist)
+
+			require.NoError(t, os.Rename(unmountedPath, targetPath))
+
+			// When blobs/ is the link, these paths run through it.
+			for _, blobFile := range blobFiles {
+				assert.FileExists(t, blobFile, "prune must delete no blob")
+			}
+
+			snapshots, err := repos.Snapshots.ListRecent(ctx, listRecentTestLimit)
+			require.NoError(t, err)
+			assert.Len(t, snapshots, 1, "prune must delete no local snapshot record")
+		})
+	}
+}
+
+// TestRemoveSnapshotWarnsOnSymlinkedMetadataWithMissingTarget checks that
+// snapshot remove warns that the metadata could not be removed from the
+// destination when metadata/ is a symlink whose target is missing, as it
+// does when the destination directory is missing, instead of finding no
+// metadata to remove.
+func TestRemoveSnapshotWarnsOnSymlinkedMetadataWithMissingTarget(t *testing.T) {
+	log.Initialize(log.Config{})
+	t.Parallel()
+
+	ctx := context.Background()
+	storeDir := filepath.Join(t.TempDir(), "store")
+	v, repos, out := backUpToFileDestination(ctx, t, storeDir)
+	targetPath := moveBehindSymlink(t, storeDir, "metadata")
+	require.NoError(t, os.Rename(targetPath, targetPath+"-unmounted"))
+
+	result, err := v.RemoveSnapshot(localSnapshotID(ctx, t, repos, "first"),
+		&vaultik.RemoveOptions{Force: true})
+	require.NoError(t, err)
+
+	assert.False(t, result.RemoteRemoved)
+	assert.Contains(t, out.String(),
+		"Could not remove snapshot metadata from remote")
+	assert.NotContains(t, out.String(),
+		"Removed snapshot metadata from remote storage")
+}
+
+// blobFilesIn returns the paths of the blob files under storeDir/blobs, and
+// fails the test when there are none.
+func blobFilesIn(t *testing.T, storeDir string) []string {
+	t.Helper()
+
+	var blobFiles []string
+
+	err := filepath.WalkDir(filepath.Join(storeDir, "blobs"),
+		func(path string, entry fs.DirEntry, err error) error {
+			if err == nil && !entry.IsDir() {
+				blobFiles = append(blobFiles, path)
+			}
+
+			return err
+		})
+	require.NoError(t, err)
+	require.NotEmpty(t, blobFiles)
+
+	return blobFiles
+}
+
+// moveBehindSymlink moves storeDir/dir to a directory elsewhere, puts a
+// symlink to it in its place, and returns where it went.
+func moveBehindSymlink(t *testing.T, storeDir, dir string) string {
+	t.Helper()
+
+	linkPath := filepath.Join(storeDir, dir)
+	targetPath := filepath.Join(t.TempDir(), dir)
+	require.NoError(t, os.Rename(linkPath, targetPath))
+	require.NoError(t, os.Symlink(targetPath, linkPath))
+
+	return targetPath
+}