[release-branch.go1.18] runtime: use saved LR when unwinding through morestack

On LR machine, consider F calling G calling H, which grows stack.
The stack looks like
...
G's frame:
	... locals ...
	saved LR = return PC in F  <- SP points here at morestack
H's frame (to be created)

At morestack, we save
	gp.sched.pc = H's morestack call
	gp.sched.sp = H's entry SP (the arrow above)
	gp.sched.lr = return PC in G

Currently, when unwinding through morestack (if _TraceJumpStack
is set), we switch PC and SP but not LR. We then have
	frame.pc = H's morestack call
	frame.sp = H's entry SP (the arrow above)
As LR is not set, we load it from stack at *sp, so
	frame.lr = return PC in F
As the SP hasn't decremented at the morestack call,
	frame.fp = frame.sp = H's entry SP

Unwinding a frame, we have
	frame.pc = old frame.lr = return PC in F
	frame.sp = old frame.fp = H's entry SP a.k.a. G's SP
The PC and SP don't match. The unwinding will go off if F and G
have different frame sizes.

Fix this by preserving the LR when switching stack.

Also add code to detect infinite loop in unwinding.

TODO: add some test. I can reproduce the infinite loop (or throw
with added check) but the frequency is low.

Fixes #53112.
Updates #52116.

Change-Id: I6e1294f1c6e55f664c962767a1cf6c466a0c0eff
Reviewed-on: https://go-review.googlesource.com/c/go/+/400575
TryBot-Result: Gopher Robot <gobot@golang.org>
Run-TryBot: Cherry Mui <cherryyz@google.com>
Reviewed-by: Eric Fang <eric.fang@arm.com>
Reviewed-by: Benny Siegert <bsiegert@gmail.com>
(cherry picked from commit 74f00094220f26c80fbaab6eca28c3a664897d24)
Reviewed-on: https://go-review.googlesource.com/c/go/+/408821
Reviewed-by: Austin Clements <austin@google.com>

1 files changed, 13 insertions, 2 deletions

diff --git a/src/runtime/traceback.go b/src/runtime/traceback.go
index 229e3a9105..56128dc882 100644
--- a/src/runtime/traceback.go
+++ b/src/runtime/traceback.go
@@ -82,6 +82,7 @@ func gentraceback(pc0, sp0, lr0 uintptr, gp *g, skip int, pcbuf *uintptr, max in
 	}
 	waspanic := false
 	cgoCtxt := gp.cgoCtxt
+	stack := gp.stack
 	printing := pcbuf == nil && callback == nil
 
 	// If the PC is zero, it's likely a nil function call.
@@ -114,7 +115,7 @@ func gentraceback(pc0, sp0, lr0 uintptr, gp *g, skip int, pcbuf *uintptr, max in
 	if !f.valid() {
 		if callback != nil || printing {
 			print("runtime: unknown pc ", hex(frame.pc), "\n")
-			tracebackHexdump(gp.stack, &frame, 0)
+			tracebackHexdump(stack, &frame, 0)
 		}
 		if callback != nil {
 			throw("unknown pc")
@@ -174,12 +175,15 @@ func gentraceback(pc0, sp0, lr0 uintptr, gp *g, skip int, pcbuf *uintptr, max in
 					frame.fn = findfunc(frame.pc)
 					f = frame.fn
 					flag = f.flag
+					frame.lr = gp.m.curg.sched.lr
 					frame.sp = gp.m.curg.sched.sp
+					stack = gp.m.curg.stack
 					cgoCtxt = gp.m.curg.cgoCtxt
 				case funcID_systemstack:
 					// systemstack returns normally, so just follow the
 					// stack transition.
 					frame.sp = gp.m.curg.sched.sp
+					stack = gp.m.curg.stack
 					cgoCtxt = gp.m.curg.cgoCtxt
 					flag &^= funcFlag_SPWRITE
 				}
@@ -248,7 +252,7 @@ func gentraceback(pc0, sp0, lr0 uintptr, gp *g, skip int, pcbuf *uintptr, max in
 				}
 				if callback != nil || doPrint {
 					print("runtime: unexpected return pc for ", funcname(f), " called from ", hex(frame.lr), "\n")
-					tracebackHexdump(gp.stack, &frame, lrPtr)
+					tracebackHexdump(stack, &frame, lrPtr)
 				}
 				if callback != nil {
 					throw("unknown caller pc")
@@ -477,6 +481,13 @@ func gentraceback(pc0, sp0, lr0 uintptr, gp *g, skip int, pcbuf *uintptr, max in
 			break
 		}
 
+		if frame.pc == frame.lr && frame.sp == frame.fp {
+			// If the next frame is identical to the current frame, we cannot make progress.
+			print("runtime: traceback stuck. pc=", hex(frame.pc), " sp=", hex(frame.sp), "\n")
+			tracebackHexdump(stack, &frame, frame.sp)
+			throw("traceback stuck")
+		}
+
 		// Unwind to next frame.
 		frame.fn = flr
 		frame.pc = frame.lr