diff --git a/VERSION b/VERSION
index 139c590eb87892..47f498c4aa0e26 100644
--- a/VERSION
+++ b/VERSION
@@ -1,2 +1,2 @@
-go1.23.4
+go1.23.4-kb
 time 2024-11-27T20:27:20Z
diff --git a/src/cmd/cgo/out.go b/src/cmd/cgo/out.go
index 5329cb3cd2d224..e5429187547599 100644
--- a/src/cmd/cgo/out.go
+++ b/src/cmd/cgo/out.go
@@ -1039,7 +1039,7 @@ func (p *Package) writeExports(fgo2, fm, fgcc, fgcch io.Writer) {
 		// string.h for memset, and is also robust to C++
 		// types with constructors. Both GCC and LLVM optimize
 		// this into just zeroing _cgo_a.
-		fmt.Fprintf(fgcc, "\ttypedef %s %v _cgo_argtype;\n", ctype, p.packedAttribute())
+		fmt.Fprintf(fgcc, "\ttypedef %s %v __attribute__((aligned(8))) _cgo_argtype;\n", ctype, p.packedAttribute())
 		fmt.Fprintf(fgcc, "\tstatic _cgo_argtype _cgo_zero;\n")
 		fmt.Fprintf(fgcc, "\t_cgo_argtype _cgo_a = _cgo_zero;\n")
 		if gccResult != "void" && (len(fntype.Results.List) > 1 || len(fntype.Results.List[0].Names) > 1) {