feat(cmd): generate go_asm.h for package-context assembly

Assisted-by: GLM 5.3 Flash

cmd/gasm/audit.go

@@ -418,7 +418,9 @@ func cmdAuditCorpus(args []string, dirs includeDirs) error {
 	// The toolchain's shipped headers (funcdata.h and friends) define the
 	// macros GOROOT files include; a corpus audit measures those files, so
 	// the header directory joins the search path automatically.  go_asm.h
-	// is compiler-generated per package and stays unresolvable on purpose.
+	// is compiler-generated per package, so it is not resolved from here:
+	// files that include it get one generated per target architecture,
+	// which runCorpusAudit arranges.
 	if out, err := exec.Command("go", "env", "GOROOT").Output(); err == nil {
 		pkgInclude := filepath.Join(strings.TrimSpace(string(out)), "pkg", "include")
 		if fi, err := os.Stat(pkgInclude); err == nil && fi.IsDir() {
@@ -462,9 +464,15 @@ var goPortSuffixes = []string{
 	"s390x", "wasm",
 }
 
-// otherPortFile reports whether the file's name carries a Go-architecture
-// suffix gasm does not support.
+// otherPortFile reports whether the file belongs to a build no supported
+// target ever compiles: either its name carries a Go-architecture suffix
+// gasm does not support, or, for a file with no architecture suffix at all,
+// it names another GOOS, which go/build drops from the file set
+// (rt0_js_wasm.s is a javascript build, not a generic one).
 func otherPortFile(path string) bool {
+	if otherGOOSFile(path) {
+		return true
+	}
 	base := path
 	if i := strings.LastIndexByte(base, '/'); i >= 0 {
 		base = base[i+1:]
@@ -477,6 +485,29 @@ func otherPortFile(path string) bool {
 	return false
 }
 
+// goOSNames are the GOOS values go/build recognises in file names.
+var goOSNames = map[string]bool{
+	"aix": true, "darwin": true, "dragonfly": true, "freebsd": true,
+	"ios": true, "js": true, "linux": true, "netbsd": true,
+	"openbsd": true, "plan9": true, "solaris": true, "wasip1": true,
+	"windows": true,
+}
+
+// otherGOOSFile reports whether the file's name names a GOOS other than the
+// host's, by go/build's file-name rules.
+func otherGOOSFile(path string) bool {
+	base := path
+	if i := strings.LastIndexByte(base, '/'); i >= 0 {
+		base = base[i+1:]
+	}
+	for seg := range strings.SplitSeq(strings.TrimSuffix(base, ".s"), "_") {
+		if goOSNames[seg] && seg != runtime.GOOS {
+			return true
+		}
+	}
+	return false
+}
+
 func runCorpusAudit(root string, dirs includeDirs) (*corpusStats, error) {
 	files, err := asmFiles(root)
 	if err != nil {
@@ -497,12 +528,20 @@ func runCorpusAudit(root string, dirs includeDirs) (*corpusStats, error) {
 	// its name allows assembles it.
 	full, generic, otherPort := 0, 0, 0
 
+	// Header generation is created on first use, so a corpus with no
+	// go_asm.h includes never pays for a temp directory.
+	var hdr *asmhdrCache
+	defer func() {
+		if hdr != nil {
+			hdr.close()
+		}
+	}()
+
 	for _, path := range files {
 		src, err := readSource(path)
 		if err != nil {
 			return nil, err
 		}
-		f, errs := parser.ParseWithOptions(path, src, parser.Options{Expand: true, IncludeDirs: dirs})
 
 		var wanted []int // indexes into targets
 		if a := arch.FromFilename(path); a != arch.Unknown {
@@ -513,10 +552,11 @@ func runCorpusAudit(root string, dirs includeDirs) (*corpusStats, error) {
 			}
 		} else if otherPortFile(path) {
 			// A file named for a Go port gasm does not support (arm,
-			// 386, s390x, ...) is compiled by no supported-arch build,
-			// so it is neither generic nor a per-arch attempt: counting
-			// it as generic would make the headline unreachably low
-			// for reasons no supported target can fix.
+			// 386, s390x, ...) or for another GOOS is compiled by no
+			// supported-arch build, so it is neither generic nor a
+			// per-arch attempt: counting it as generic would make the
+			// headline unreachably low for reasons no supported target
+			// can fix.
 			otherPort++
 		} else {
 			generic++
@@ -525,6 +565,54 @@ func runCorpusAudit(root string, dirs includeDirs) (*corpusStats, error) {
 			}
 		}
 
+		// A file that includes go_asm.h parses against a per-target header:
+		// the defines differ per architecture (internal/cpu's layout, for
+		// one), so the parse cannot be shared the way a header-free file's
+		// can.  A generation failure is a failure for every target, named
+		// for the package rather than a bare "include not found".  A header
+		// already resolvable in the package directory or the -I list is
+		// left alone.
+		if len(wanted) > 0 && needsGoAsmHeader(src) && !goAsmHeaderResolved(filepath.Dir(path), dirs) {
+			if hdr == nil {
+				if hdr, err = newAsmhdrCache(); err != nil {
+					return nil, err
+				}
+			}
+			pkgDir := filepath.Dir(path)
+			ok := true
+			for _, i := range wanted {
+				tg, t := targets[i], tallies[i]
+				t.attempted++
+				hdrDir, err := hdr.dirFor(pkgDir, goarchName(tg.a))
+				if err != nil {
+					ok = false
+					t.fail(path, corpusReason(err))
+					continue
+				}
+				f, errs := parser.ParseWithOptions(path, src, parser.Options{
+					Expand:      true,
+					IncludeDirs: append(slices.Clone(dirs), hdrDir),
+				})
+				if len(errs) > 0 {
+					ok = false
+					t.fail(path, corpusReason(errs[0]))
+					continue
+				}
+				if _, err := assembleFile(tg.a, f); err != nil {
+					ok = false
+					t.fail(path, corpusReason(err))
+					continue
+				}
+				t.assembled++
+			}
+			if ok && len(wanted) > 0 {
+				full++
+			}
+			continue
+		}
+
+		f, errs := parser.ParseWithOptions(path, src, parser.Options{Expand: true, IncludeDirs: dirs})
+
 		ok := true
 		for _, i := range wanted {
 			tg, t := targets[i], tallies[i]
@@ -581,6 +669,8 @@ func printCorpusStats(s *corpusStats) {
 func corpusReason(err error) string {
 	msg := err.Error()
 	switch {
+	case strings.Contains(msg, "go_asm.h for GOARCH"):
+		return "go_asm.h generation failed"
 	case strings.Contains(msg, "unsupported"), strings.Contains(msg, "cannot encode"):
 		return "instruction not encodable"
 	case strings.Contains(msg, "undefined label"):