List a file:// destination through a symlinked directory (closes #296)

List and ListStream walked the destination with afero.Walk, which uses
Lstat and so reported a symlinked metadata/ or blobs/ directory as one
file, while Put, Get and Stat follow the link. The store then listed as
empty, and prune removed the local snapshot records and deleted every
blob. Both listings now walk a view of the filesystem without its Lstat
method, so afero falls back to Stat and enters the link. A listed prefix
that is a symlink whose target is missing, such as a link to a volume
that is not mounted, fails the listing, as a missing destination
directory does.

A symlink loop is not detected: it is followed until the system refuses
the path for too many levels of links, and the listing fails.

Model: opus-5-5

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
-// destination directory is missing; a missing prefix under it is an
-// empty listing.
+// List returns all keys with the given prefix, reading through symlinked
+// directories. It fails when the destination directory is missing or the
+// prefix is a symlink whose target is missing; a missing prefix under the
+// destination directory 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 := afero.Exists(f.fs, basePath)
+	exists, err := f.prefixExists(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 the prefix 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 := afero.Exists(f.fs, basePath)
+		exists, err := f.prefixExists(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():
@@ -352,6 +353,40 @@ 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 is afero.Exists, except that it does not follow a symlink
+// at path. A symlinked prefix whose target is missing, such as a link to
+// a volume that is not mounted, therefore exists, and walk then fails on
+// it; with afero.Exists it would list as empty, and prune would delete
+// every blob.
+func (f *FileStorer) prefixExists(path string) (bool, error) {
+	lstater, ok := f.fs.(afero.Lstater)
+	if !ok {
+		return afero.Exists(f.fs, path)
+	}
+
+	_, _, err := lstater.LstatIfPossible(path)
+	if err == nil {
+		return true, nil
+	}
+
+	if os.IsNotExist(err) {
+		return false, nil
+	}
+
+	return false, err
+}
+
 // 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 +63,151 @@ func TestFileStorerListMissingDestination(t *testing.T) {
 		t.Errorf("ListStream error = %v, want a not-exist error", streamErr)
 	}
 }
+
+// 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.
+func TestFileStorerListsThroughSymlinkedDirectory(t *testing.T) {
+	t.Parallel()
+
+	for _, dir := range []string{"metadata", "blobs"} {
+		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)
+			}
+
+			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)
+			}
+
+			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)
+				}
+			}
+		})
+	}
+}
+
+// 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.
+func TestFileStorerListFailsOnSymlinkWithMissingTarget(t *testing.T) {
+	t.Parallel()
+
+	ctx := context.Background()
+
+	for _, dir := range []string{"metadata", "blobs"} {
+		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 + "/"} {
+				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")
+	}
+}

internal/vaultik/symlinked_destination_test.go

@@ -0,0 +1,121 @@
+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")
+		})
+	}
+}
+
+// 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
+}