pkg/codesearch: add skeleton for code searching tool

Add a clang tool that is used for code indexing (tools/clang/codesearch/).
It follows conventions and build procedure of the declextract tool.

Add pkg/codesearch package that aggregates the info exposed by the clang tools,
and allows doing simple queries:
 - show source code of an entity (function, struct, etc)
 - show entity comment
 - show all entities defined in a source file

Add tools/syz-codesearch wrapper tool that allows to create index for a kernel build,
and then run code queries on it.

1 files changed, 66 insertions, 0 deletions

diff --git a/tools/syz-codesearch/codesearch.go b/tools/syz-codesearch/codesearch.go
new file mode 100644
index 000000000..afd3840c7
--- /dev/null
+++ b/tools/syz-codesearch/codesearch.go
@@ -0,0 +1,66 @@
+// Copyright 2025 syzkaller project authors. All rights reserved.
+// Use of this source code is governed by Apache 2 LICENSE that can be found in the LICENSE file.
+
+package main
+
+import (
+	"flag"
+	"fmt"
+	"os"
+
+	"github.com/google/syzkaller/pkg/clangtool"
+	"github.com/google/syzkaller/pkg/codesearch"
+	"github.com/google/syzkaller/pkg/tool"
+)
+
+func main() {
+	var (
+		flagDatabase  = flag.String("database", "", "path to input/output database file (mandatory)")
+		flagKernelSrc = flag.String("kernel-src", "", "path to kernel source directory (mandatory)")
+		flagKernelObj = flag.String("kernel-obj", "", "path to kernel build directory (mandatory)")
+	)
+	flag.Parse()
+	if len(flag.Args()) == 0 || *flagDatabase == "" || *flagKernelSrc == "" || *flagKernelObj == "" {
+		printUsageAndExit()
+	}
+	cmd, args := flag.Args()[0], flag.Args()[1:]
+	if cmd == "index" {
+		if len(args) != 1 {
+			printUsageAndExit()
+		}
+		cfg := &clangtool.Config{
+			ToolBin:    args[0],
+			KernelSrc:  *flagKernelSrc,
+			KernelObj:  *flagKernelObj,
+			CacheFile:  *flagDatabase,
+			DebugTrace: os.Stderr,
+		}
+
+		if _, err := clangtool.Run[codesearch.Database](cfg); err != nil {
+			tool.Fail(err)
+		}
+		return
+	}
+	index, err := codesearch.NewIndex(*flagDatabase, []string{*flagKernelSrc, *flagKernelObj})
+	if err != nil {
+		tool.Fail(err)
+	}
+	res, err := index.Command(cmd, args)
+	if err != nil {
+		tool.Fail(err)
+	}
+	os.Stdout.WriteString(res)
+}
+
+func printUsageAndExit() {
+	fmt.Printf(`syz-codesearch usage:
+syz-codesearch [flags] command [command arguments]
+commands and their arguments:
+`)
+	for _, cmd := range codesearch.Commands {
+		fmt.Printf("  - %v [%v args]\n", cmd.Name, cmd.NArgs)
+	}
+	fmt.Printf("\nflags:\n")
+	flag.PrintDefaults()
+	os.Exit(1)
+}