[dev.simd] cmd/compile: keep track of multiple rule file names in ssa/_gen

This was a long-standing "we need to fix this"
for simd work, this fixes it.  I expect that
simd peephole rule files will be coming soon
and there will be more errors and we will be
happier to have this.

Change-Id: Iefffc43e3e2110939f8d406f6e5da7e9e2d55bd9
Reviewed-on: https://go-review.googlesource.com/c/go/+/694455
Reviewed-by: Cherry Mui <cherryyz@google.com>
LUCI-TryBot-Result: Go LUCI <golang-scoped@luci-project-accounts.iam.gserviceaccount.com>

src/cmd/compile/internal/ssa/_gen/multiscanner.go

@@ -0,0 +1,117 @@
+// Copyright 2025 The Go Authors. All rights reserved.
+// Use of this source code is governed by a BSD-style
+// license that can be found in the LICENSE file.
+
+package main
+
+import (
+	"bufio"
+	"io"
+)
+
+// NamedScanner is a simple struct to pair a name with a Scanner.
+type NamedScanner struct {
+	Name    string
+	Scanner *bufio.Scanner
+}
+
+// NamedReader is a simple struct to pair a name with a Reader,
+// which will be converted to a Scanner using bufio.NewScanner.
+type NamedReader struct {
+	Name   string
+	Reader io.Reader
+}
+
+// MultiScanner scans over multiple bufio.Scanners as if they were a single stream.
+// It also keeps track of the name of the current scanner and the line number.
+type MultiScanner struct {
+	scanners   []NamedScanner
+	scannerIdx int
+	line       int
+	totalLine  int
+	err        error
+}
+
+// NewMultiScanner creates a new MultiScanner from slice of NamedScanners.
+func NewMultiScanner(scanners []NamedScanner) *MultiScanner {
+	return &MultiScanner{
+		scanners:   scanners,
+		scannerIdx: -1, // Start before the first scanner
+	}
+}
+
+// MultiScannerFromReaders creates a new MultiScanner from a slice of NamedReaders.
+func MultiScannerFromReaders(readers []NamedReader) *MultiScanner {
+	var scanners []NamedScanner
+	for _, r := range readers {
+		scanners = append(scanners, NamedScanner{
+			Name:    r.Name,
+			Scanner: bufio.NewScanner(r.Reader),
+		})
+	}
+	return NewMultiScanner(scanners)
+}
+
+// Scan advances the scanner to the next token, which will then be
+// available through the Text method. It returns false when the scan stops,
+// either by reaching the end of the input or an error.
+// After Scan returns false, the Err method will return any error that
+// occurred during scanning, except that if it was io.EOF, Err
+// will return nil.
+func (ms *MultiScanner) Scan() bool {
+	if ms.scannerIdx == -1 {
+		ms.scannerIdx = 0
+	}
+
+	for ms.scannerIdx < len(ms.scanners) {
+		current := ms.scanners[ms.scannerIdx]
+		if current.Scanner.Scan() {
+			ms.line++
+			ms.totalLine++
+			return true
+		}
+		if err := current.Scanner.Err(); err != nil {
+			ms.err = err
+			return false
+		}
+		// Move to the next scanner
+		ms.scannerIdx++
+		ms.line = 0
+	}
+
+	return false
+}
+
+// Text returns the most recent token generated by a call to Scan.
+func (ms *MultiScanner) Text() string {
+	if ms.scannerIdx < 0 || ms.scannerIdx >= len(ms.scanners) {
+		return ""
+	}
+	return ms.scanners[ms.scannerIdx].Scanner.Text()
+}
+
+// Err returns the first non-EOF error that was encountered by the MultiScanner.
+func (ms *MultiScanner) Err() error {
+	return ms.err
+}
+
+// Name returns the name of the current scanner.
+func (ms *MultiScanner) Name() string {
+	if ms.scannerIdx < 0 {
+		return "<before first>"
+	}
+	if ms.scannerIdx >= len(ms.scanners) {
+		return "<after last>"
+	}
+	return ms.scanners[ms.scannerIdx].Name
+}
+
+// Line returns the current line number within the current scanner.
+func (ms *MultiScanner) Line() int {
+	return ms.line
+}
+
+// TotalLine returns the total number of lines scanned across all scanners.
+func (ms *MultiScanner) TotalLine() int {
+	return ms.totalLine
+}

src/cmd/compile/internal/ssa/_gen/rulegen.go

@@ -94,9 +94,11 @@ func genSplitLoadRules(arch arch) { genRulesSuffix(arch, "splitload") }
 func genLateLowerRules(arch arch) { genRulesSuffix(arch, "latelower") }
 
 func genRulesSuffix(arch arch, suff string) {
+	var readers []NamedReader
 	// Open input file.
 	var text io.Reader
-	text, err := os.Open(arch.name + suff + ".rules")
+	name := arch.name + suff + ".rules"
+	text, err := os.Open(name)
 	if err != nil {
 		if suff == "" {
 			// All architectures must have a plain rules file.
@@ -105,12 +107,14 @@ func genRulesSuffix(arch arch, suff string) {
 		// Some architectures have bonus rules files that others don't share. That's fine.
 		return
 	}
+	readers = append(readers, NamedReader{name, text})
 
 	// Check for file of SIMD rules to add
 	if suff == "" {
-		simdtext, err := os.Open("simd" + arch.name + ".rules")
+		simdname := "simd" + arch.name + ".rules"
+		simdtext, err := os.Open(simdname)
 		if err == nil {
-			text = io.MultiReader(text, simdtext)
+			readers = append(readers, NamedReader{simdname, simdtext})
 		}
 	}
 
@@ -119,12 +123,12 @@ func genRulesSuffix(arch arch, suff string) {
 	oprules := map[string][]Rule{}
 
 	// read rule file
-	scanner := bufio.NewScanner(text)
+	scanner := MultiScannerFromReaders(readers)
 	rule := ""
 	var lineno int
 	var ruleLineno int // line number of "=>"
 	for scanner.Scan() {
-		lineno++
+		lineno = scanner.Line()
 		line := scanner.Text()
 		if i := strings.Index(line, "//"); i >= 0 {
 			// Remove comments. Note that this isn't string safe, so
@@ -151,7 +155,7 @@ func genRulesSuffix(arch arch, suff string) {
 			break // continuing the line can't help, and it will only make errors worse
 		}
 
-		loc := fmt.Sprintf("%s%s.rules:%d", arch.name, suff, ruleLineno)
+		loc := fmt.Sprintf("%s:%d", scanner.Name(), ruleLineno)
 		for _, rule2 := range expandOr(rule) {
 			r := Rule{Rule: rule2, Loc: loc}
 			if rawop := strings.Split(rule2, " ")[0][1:]; isBlock(rawop, arch) {
@@ -171,7 +175,7 @@ func genRulesSuffix(arch arch, suff string) {
 		log.Fatalf("scanner failed: %v\n", err)
 	}
 	if balance(rule) != 0 {
-		log.Fatalf("%s.rules:%d: unbalanced rule: %v\n", arch.name, lineno, rule)
+		log.Fatalf("%s:%d: unbalanced rule: %v\n", scanner.Name(), lineno, rule)
 	}
 
 	// Order all the ops.