fix(debug): hardware watchpoints, signal stops and breakpoint restore

Assisted-by: GLM 5.3

debug/ptrace_linux.go

@@ -23,7 +23,13 @@ type Session struct {
 	stopped  bool
 	exited   bool
 	codeBase uint64   // base address of the JIT code in the debuggee
-	wpSlots  [16]bool // hardware watchpoint slots in use (DR0-DR3, arm64 BADVR0-15)
+	tmpDir   string   // scratch directory of the session, removed on Kill
+	wpSlots  [16]bool // hardware watchpoint slots in use (DR0-DR3, arm64 DBGWVR0-15)
+	// lastSignal holds the signal of the most recent stop when that stop
+	// was a genuine signal-delivery-stop the caller must see (a fault such
+	// as SIGSEGV, SIGBUS, SIGFPE or SIGILL); 0 for breakpoint traps,
+	// single-steps, SIGSTOP and suppressed runtime signals.
+	lastSignal syscall.Signal
 }
 
 // Launch starts the debuggee subprocess (gasm debug --target ...) and
@@ -78,7 +84,7 @@ func LaunchWithBuffers(gasmBin, asmPath, funcName string, args []byte, bufSpec s
 		return nil, nil, fmt.Errorf("debug: start debuggee: %w", err)
 	}
 
-	s := &Session{pid: cmd.Process.Pid, cmd: cmd}
+	s := &Session{pid: cmd.Process.Pid, cmd: cmd, tmpDir: tmpDir}
 
 	readyFile := filepath.Join(tmpDir, "ready")
 	for range 500 {
@@ -125,29 +131,17 @@ func LaunchWithBuffers(gasmBin, asmPath, funcName string, args []byte, bufSpec s
 	return s, bufAddrs, nil
 }
 
-// wait waits for the debuggee to stop and returns the wait status.
-func (s *Session) wait() error {
-	var ws syscall.WaitStatus
-	_, err := syscall.Wait4(s.pid, &ws, 0, nil)
-	if err != nil {
-		return err
-	}
-	if ws.Exited() {
-		s.exited = true
-		return fmt.Errorf("debuggee exited with status %d", ws.ExitStatus())
-	}
-	s.stopped = true
-	return nil
-}
-
 // waitStopped consumes ptrace-stop events until one the debugger cares
-// about arrives: SIGTRAP (a breakpoint or a completed single-step) or the
-// debuggee's own SIGSTOP.  A Go tracee's runtime raises SIGURG for
-// asynchronous preemption, and every signal on a traced thread surfaces as
-// a signal-delivery-stop, so those are suppressed and the tracee resumed
-// without them.  Runtime noise is why a single wait can return in the
-// middle of runtime code and a resume can then fail: the event stream must
-// be drained by the tracer.
+// about arrives: SIGTRAP (a breakpoint or a completed single-step), the
+// debuggee's own SIGSTOP, or a genuine signal-delivery-stop.  A Go tracee's
+// runtime raises SIGURG for asynchronous preemption, and every signal on a
+// traced thread surfaces as a signal-delivery-stop, so SIGURG is suppressed
+// and the tracee resumed without it.  Every other signal (SIGSEGV, SIGBUS,
+// SIGFPE, SIGILL, ...) is returned to the caller: resuming with signal 0
+// would restart the faulting instruction and fault forever, so a faulting
+// kernel must surface as a stop the caller reports.  Runtime noise is also
+// why a single wait can return in the middle of runtime code and a resume
+// can then fail: the event stream must be drained by the tracer.
 func (s *Session) waitStopped() (syscall.Signal, error) {
 	for {
 		var ws syscall.WaitStatus
@@ -165,10 +159,12 @@ func (s *Session) waitStopped() (syscall.Signal, error) {
 		switch sig := ws.StopSignal(); sig {
 		case syscall.SIGTRAP, syscall.SIGSTOP:
 			s.stopped = true
+			s.lastSignal = 0
 			return sig, nil
-		default:
-			// Runtime noise (SIGURG preemption and friends): resume the
-			// tracee without delivering the signal.
+		case syscall.SIGURG:
+			// Go runtime asynchronous preemption: resume the tracee
+			// without delivering the signal.
+			s.lastSignal = 0
 			if _, _, errno := syscall.Syscall6(
 				syscall.SYS_PTRACE,
 				uintptr(syscall.PTRACE_CONT),
@@ -177,10 +173,22 @@ func (s *Session) waitStopped() (syscall.Signal, error) {
 			); errno != 0 {
 				return 0, fmt.Errorf("debug: PTRACE_CONT: %w", errno)
 			}
+		default:
+			// A genuine signal-delivery-stop.  Report it; the caller
+			// decides how to proceed.
+			s.stopped = true
+			s.lastSignal = sig
+			return sig, nil
 		}
 	}
 }
 
+// LastSignal returns the signal of the most recent stop when that stop was
+// a genuine signal-delivery-stop (a fault such as SIGSEGV, SIGFPE, SIGILL
+// or SIGBUS), and 0 for breakpoint traps, single-steps, SIGSTOP and
+// suppressed runtime signals.
+func (s *Session) LastSignal() syscall.Signal { return s.lastSignal }
+
 // Peek reads a word (8 bytes) from the debuggee's memory at addr.
 func (s *Session) Peek(addr uint64) (uint64, error) {
 	mem, err := os.OpenFile(fmt.Sprintf("/proc/%d/mem", s.pid), os.O_RDONLY, 0)
@@ -294,7 +302,8 @@ func (s *Session) Pid() int { return s.pid }
 // CodeBase returns the base address of the JIT code in the debuggee.
 func (s *Session) CodeBase() uint64 { return s.codeBase }
 
-// Kill terminates the debuggee.
+// Kill terminates the debuggee and removes the session's scratch
+// directory, so a successful session leaves no gasm-debug-* debris behind.
 func (s *Session) Kill() {
 	if !s.exited {
 		syscall.Kill(s.pid, syscall.SIGKILL)
@@ -304,6 +313,35 @@ func (s *Session) Kill() {
 	if s.cmd != nil && s.cmd.Process != nil {
 		s.cmd.Wait()
 	}
+	if s.tmpDir != "" {
+		os.RemoveAll(s.tmpDir)
+		s.tmpDir = ""
+	}
+}
+
+// execRange is one executable mapping of the debuggee.
+type execRange struct {
+	lo, hi uint64
+}
+
+// execRanges parses the debuggee's executable mappings from /proc/pid/maps.
+func execRanges(pid int) []execRange {
+	data, err := os.ReadFile(fmt.Sprintf("/proc/%d/maps", pid))
+	if err != nil {
+		return nil
+	}
+	var out []execRange
+	for line := range strings.SplitSeq(string(data), "\n") {
+		fields := strings.Fields(line)
+		if len(fields) < 2 || !strings.Contains(fields[1], "x") {
+			continue
+		}
+		var lo, hi uint64
+		if _, err := fmt.Sscanf(fields[0], "%x-%x", &lo, &hi); err == nil {
+			out = append(out, execRange{lo, hi})
+		}
+	}
+	return out
 }
 
 // findRWXMapping reads /proc/pid/maps and returns the base address of the