pkg/aflow/tool/codesearcher: take into account DB format when caching

If format of the codesearch DB file changes,
we need to create new DB rather than use old cached one.
Add DB format hash to cache signature.

Author: dvyukov

pkg/aflow/tool/codesearcher/codesearcher.go

@@ -138,8 +138,8 @@ func (index) UnmarshalJSON([]byte) error {
 }
 
 func prepare(ctx *aflow.Context, args prepareArgs) (prepareResult, error) {
-	desc := fmt.Sprintf("kernel commit %v, config hash %v",
-		args.KernelCommit, hash.String(args.KernelConfig))
+	desc := fmt.Sprintf("kernel commit %v, config hash %v, databash hash %v",
+		args.KernelCommit, hash.String(args.KernelConfig), codesearch.DatabaseFormatHash)
 	dir, err := ctx.Cache("codesearch", desc, func(dir string) error {
 		cfg := &clangtool.Config{
 			ToolBin:   args.CodesearchToolBin,

pkg/codesearch/database.go

@@ -4,9 +4,12 @@
 package codesearch
 
 import (
+	"encoding/json"
 	"strings"
 
+	"github.com/google/jsonschema-go/jsonschema"
 	"github.com/google/syzkaller/pkg/clangtool"
+	"github.com/google/syzkaller/pkg/hash"
 )
 
 type Database struct {
@@ -36,6 +39,24 @@ type LineRange struct {
 	EndLine   int    `json:"end_line,omitempty"`
 }
 
+// DatabaseFormatHash contains a hash uniquely identifying format of the database.
+// In covers both structure and semantics of the data, and is supposed to be used
+// for caching of the database files.
+var DatabaseFormatHash = func() string {
+	// Semantic version should be bumped when the schema does not change,
+	// but stored values changes.
+	const semanticVersion = "1"
+	schema, err := jsonschema.For[Database](nil)
+	if err != nil {
+		panic(err)
+	}
+	serialized, err := json.Marshal(schema)
+	if err != nil {
+		panic(err)
+	}
+	return hash.String(serialized, semanticVersion)
+}()
+
 func (db *Database) Merge(other *Database) {
 	db.Definitions = append(db.Definitions, other.Definitions...)
 }