runtime: make GOTRACEBACK=crash crash promptly in cgo binaries

GOTRACEBACK=crash works by bouncing a SIGQUIT around the process
sched.mcount times. However, sched.mcount includes the extra Ms
allocated by oneNewExtraM for cgo callbacks. Hence, if there are any
extra Ms that don't have real OS threads, we'll try to send SIGQUIT
more times than there are threads to catch it. Since nothing will
catch these extra signals, we'll fall back to blocking for five
seconds before aborting the process.

Avoid this five second delay by subtracting out the number of extra Ms
when sending SIGQUITs.

Of course, in a cgo binary, it's still possible for the SIGQUIT to go
to a cgo thread and cause some other failure mode. This does not fix
that.

Change-Id: I4fbf3c52dd721812796c4c1dcb2ab4cb7026d965
Reviewed-on: https://go-review.googlesource.com/38182
Run-TryBot: Austin Clements <austin@google.com>
TryBot-Result: Gobot Gobot <gobot@golang.org>
Reviewed-by: Ian Lance Taylor <iant@golang.org>
This commit is contained in:
Austin Clements 2017-03-15 14:48:23 -04:00
parent c03e75e539
commit f2e87158f0
2 changed files with 5 additions and 1 deletions

View File

@ -1399,6 +1399,7 @@ func needm(x byte) {
// running at all (that is, there's no garbage collection
// running right now).
mp.needextram = mp.schedlink == 0
extraMCount--
unlockextra(mp.schedlink.ptr())
// Save and block signals before installing g.
@ -1484,6 +1485,7 @@ func oneNewExtraM() {
// Add m to the extra list.
mnext := lockextra(true)
mp.schedlink.set(mnext)
extraMCount++
unlockextra(mp)
}
@ -1525,6 +1527,7 @@ func dropm() {
unminit()
mnext := lockextra(true)
extraMCount++
mp.schedlink.set(mnext)
setg(nil)
@ -1541,6 +1544,7 @@ func getm() uintptr {
}
var extram uintptr
var extraMCount uint32 // Protected by lockextra
var extraMWaiters uint32
// lockextra locks the extra list and returns the list head.

View File

@ -111,7 +111,7 @@ func sighandler(sig uint32, info *siginfo, ctxt unsafe.Pointer, gp *g) {
if docrash {
crashing++
if crashing < sched.mcount {
if crashing < sched.mcount-int32(extraMCount) {
// There are other m's that need to dump their stacks.
// Relay SIGQUIT to the next m by sending it to the current process.
// All m's that have already received SIGQUIT have signal masks blocking