mirror of
https://github.com/xemu-project/xemu.git
synced 2024-12-04 17:56:33 +00:00
2362a28ea1
There is a small chance that iothread_stop() hangs as follows: Thread 3 (Thread 0x7f63eba5f700 (LWP 16105)): #0 0x00007f64012c09b6 in ppoll () at /lib64/libc.so.6 #1 0x000055959992eac9 in ppoll (__ss=0x0, __timeout=0x0, __nfds=<optimized out>, __fds=<optimized out>) at /usr/include/bits/poll2.h:77 #2 0x000055959992eac9 in qemu_poll_ns (fds=<optimized out>, nfds=<optimized out>, timeout=<optimized out>) at util/qemu-timer.c:322 #3 0x0000559599930711 in aio_poll (ctx=0x55959bdb83c0, blocking=blocking@entry=true) at util/aio-posix.c:629 #4 0x00005595996806fe in iothread_run (opaque=0x55959bd78400) at iothread.c:59 #5 0x00007f640159f609 in start_thread () at /lib64/libpthread.so.0 #6 0x00007f64012cce6f in clone () at /lib64/libc.so.6 Thread 1 (Thread 0x7f640b45b280 (LWP 16103)): #0 0x00007f64015a0b6d in pthread_join () at /lib64/libpthread.so.0 #1 0x00005595999332ef in qemu_thread_join (thread=<optimized out>) at util/qemu-thread-posix.c:547 #2 0x00005595996808ae in iothread_stop (iothread=<optimized out>) at iothread.c:91 #3 0x000055959968094d in iothread_stop_iter (object=<optimized out>, opaque=<optimized out>) at iothread.c:102 #4 0x0000559599857d97 in do_object_child_foreach (obj=obj@entry=0x55959bdb8100, fn=fn@entry=0x559599680930 <iothread_stop_iter>, opaque=opaque@entry=0x0, recurse=recurse@entry=false) at qom/object.c:852 #5 0x0000559599859477 in object_child_foreach (obj=obj@entry=0x55959bdb8100, fn=fn@entry=0x559599680930 <iothread_stop_iter>, opaque=opaque@entry=0x0) at qom/object.c:867 #6 0x0000559599680a6e in iothread_stop_all () at iothread.c:341 #7 0x000055959955b1d5 in main (argc=<optimized out>, argv=<optimized out>, envp=<optimized out>) at vl.c:4913 The relevant code from iothread_run() is: while (!atomic_read(&iothread->stopping)) { aio_poll(iothread->ctx, true); and iothread_stop(): iothread->stopping = true; aio_notify(iothread->ctx); ... qemu_thread_join(&iothread->thread); The following scenario can occur: 1. IOThread: while (!atomic_read(&iothread->stopping)) -> stopping=false 2. Main loop: iothread->stopping = true; aio_notify(iothread->ctx); 3. IOThread: aio_poll(iothread->ctx, true); -> hang The bug is explained by the AioContext->notify_me doc comments: "If this field is 0, everything (file descriptors, bottom halves, timers) will be re-evaluated before the next blocking poll(), thus the event_notifier_set call can be skipped." The problem is that "everything" does not include checking iothread->stopping. This means iothread_run() will block in aio_poll() if aio_notify() was called just before aio_poll(). This patch fixes the hang by replacing aio_notify() with aio_bh_schedule_oneshot(). This makes aio_poll() or g_main_loop_run() to return. Implementing this properly required a new bool running flag. The new flag prevents races that are tricky if we try to use iothread->stopping. Now iothread->stopping is purely for iothread_stop() and iothread->running is purely for the iothread_run() thread. Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> Reviewed-by: Eric Blake <eblake@redhat.com> Message-id: 20171207201320.19284-6-stefanha@redhat.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
61 lines
1.5 KiB
C
61 lines
1.5 KiB
C
/*
|
|
* Event loop thread
|
|
*
|
|
* Copyright Red Hat Inc., 2013
|
|
*
|
|
* Authors:
|
|
* Stefan Hajnoczi <stefanha@redhat.com>
|
|
*
|
|
* This work is licensed under the terms of the GNU GPL, version 2 or later.
|
|
* See the COPYING file in the top-level directory.
|
|
*
|
|
*/
|
|
|
|
#ifndef IOTHREAD_H
|
|
#define IOTHREAD_H
|
|
|
|
#include "block/aio.h"
|
|
#include "qemu/thread.h"
|
|
|
|
#define TYPE_IOTHREAD "iothread"
|
|
|
|
typedef struct {
|
|
Object parent_obj;
|
|
|
|
QemuThread thread;
|
|
AioContext *ctx;
|
|
GMainContext *worker_context;
|
|
GMainLoop *main_loop;
|
|
GOnce once;
|
|
QemuMutex init_done_lock;
|
|
QemuCond init_done_cond; /* is thread initialization done? */
|
|
bool stopping; /* has iothread_stop() been called? */
|
|
bool running; /* should iothread_run() continue? */
|
|
int thread_id;
|
|
|
|
/* AioContext poll parameters */
|
|
int64_t poll_max_ns;
|
|
int64_t poll_grow;
|
|
int64_t poll_shrink;
|
|
} IOThread;
|
|
|
|
#define IOTHREAD(obj) \
|
|
OBJECT_CHECK(IOThread, obj, TYPE_IOTHREAD)
|
|
|
|
char *iothread_get_id(IOThread *iothread);
|
|
IOThread *iothread_by_id(const char *id);
|
|
AioContext *iothread_get_aio_context(IOThread *iothread);
|
|
void iothread_stop_all(void);
|
|
GMainContext *iothread_get_g_main_context(IOThread *iothread);
|
|
|
|
/*
|
|
* Helpers used to allocate iothreads for internal use. These
|
|
* iothreads will not be seen by monitor clients when query using
|
|
* "query-iothreads".
|
|
*/
|
|
IOThread *iothread_create(const char *id, Error **errp);
|
|
void iothread_stop(IOThread *iothread);
|
|
void iothread_destroy(IOThread *iothread);
|
|
|
|
#endif /* IOTHREAD_H */
|