tree 4bee96879dd1a3aeb6a4e6730722c9974b2a95a8
parent 95e92ac420ca0edaa9dabdbe76583affbc1015a0
author Russ Cox <rsc@golang.org> 1417470161 -0500
committer Russ Cox <rsc@golang.org> 1417470161 -0500
golang-hg 9e6afb82e1eb6b2b3a58ceb362bde1d5c4fb6831

[release-branch.go1.4] runtime: fix hang in GC due to shrinkstack vs netpoll race

««« CL 179680043 / 752cd9199639
runtime: fix hang in GC due to shrinkstack vs netpoll race

During garbage collection, after scanning a stack, we think about
shrinking it to reclaim some memory. The shrinking code (called
while the world is stopped) checked that the status was Gwaiting
or Grunnable and then changed the state to Gcopystack, to essentially
lock the stack so that no other GC thread is scanning it.
The same locking happens for stack growth (and is more necessary there).

        oldstatus = runtime·readgstatus(gp);
        oldstatus &= ~Gscan;
        if(oldstatus == Gwaiting || oldstatus == Grunnable)
                runtime·casgstatus(gp, oldstatus, Gcopystack); // oldstatus is Gwaiting or Grunnable
        else
                runtime·throw("copystack: bad status, not Gwaiting or Grunnable");

Unfortunately, "stop the world" doesn't stop everything. It stops all
normal goroutine execution, but the network polling thread is still
blocked in epoll and may wake up. If it does, and it chooses a goroutine
to mark runnable, and that goroutine is the one whose stack is shrinking,
then it can happen that between readgstatus and casgstatus, the status
changes from Gwaiting to Grunnable.

casgstatus assumes that if the status is not what is expected, it is a
transient change (like from Gwaiting to Gscanwaiting and back, or like
from Gwaiting to Gcopystack and back), and it loops until the status
has been restored to the expected value. In this case, the status has
changed semi-permanently from Gwaiting to Grunnable - it won't
change again until the GC is done and the world can continue, but the
GC is waiting for the status to change back. This wedges the program.

To fix, call a special variant of casgstatus that accepts either Gwaiting
or Grunnable as valid statuses.

Without the fix bug with the extra check+throw in casgstatus, the
program below dies in a few seconds (2-10) with GOMAXPROCS=8
on a 2012 Retina MacBook Pro. With the fix, it runs for minutes
and minutes.

package main

import (
        "io"
        "log"
        "net"
        "runtime"
)

func main() {
        const N = 100
        for i := 0; i < N; i++ {
                l, err := net.Listen("tcp", "127.0.0.1:0")
                if err != nil {
                        log.Fatal(err)
                }
                ch := make(chan net.Conn, 1)
                go func() {
                        var err error
                        c1, err := net.Dial("tcp", l.Addr().String())
                        if err != nil {
                                log.Fatal(err)
                        }
                        ch <- c1
                }()
                c2, err := l.Accept()
                if err != nil {
                        log.Fatal(err)
                }
                c1 := <-ch
                l.Close()
                go netguy(c1, c2)
                go netguy(c2, c1)
                c1.Write(make([]byte, 100))
        }
        for {
                runtime.GC()
        }
}

func netguy(r, w net.Conn) {
        buf := make([]byte, 100)
        for {
                bigstack(1000)
                _, err := io.ReadFull(r, buf)
                if err != nil {
                        log.Fatal(err)
                }
                w.Write(buf)
        }
}

var g int

func bigstack(n int) {
        var buf [100]byte
        if n > 0 {
                bigstack(n - 1)
        }
        g = int(buf[0]) + int(buf[99])
}

Fixes #9186.

LGTM=rlh
R=austin, rlh
CC=dvyukov, golang-codereviews, iant, khr, r
https://golang.org/cl/179680043
»»»

TBR=rlh
CC=golang-codereviews
https://golang.org/cl/184030043