The following changes since commit 0ab4537f08e09b13788db67efd760592fb7db769:

Merge remote-tracking branch 'remotes/stefanberger/tags/pull-tpm-2018-03-07-1' into staging (2018-03-08 12:56:39 +0000)

git://github.com/stefanha/qemu.git tags/block-pull-request

for you to fetch changes up to 4486e89c219c0d1b9bd8dfa0b1dd5b0d51ff2268:

vl: introduce vm_shutdown() (2018-03-08 17:38:51 +0000)

----------------------------------------------------------------

Deepa Srinivasan (1):

block: Fix qemu crash when using scsi-block

Fam Zheng (1):

README: Fix typo 'git-publish'

Sergio Lopez (1):

virtio-blk: dataplane: Don't batch notifications if EVENT_IDX is

present

Stefan Hajnoczi (4):

block: add aio_wait_bh_oneshot()

virtio-blk: fix race between .ioeventfd_stop() and vq handler

virtio-scsi: fix race between .ioeventfd_stop() and vq handler

vl: introduce vm_shutdown()

include/block/aio-wait.h | 13 +++++++++++

include/sysemu/iothread.h | 1 -

include/sysemu/sysemu.h | 1 +

block/block-backend.c | 51 ++++++++++++++++++++---------------------

cpus.c | 16 ++++++++++---

hw/block/dataplane/virtio-blk.c | 39 +++++++++++++++++++++++--------

hw/scsi/virtio-scsi-dataplane.c | 9 ++++----

iothread.c | 31 -------------------------

util/aio-wait.c | 31 +++++++++++++++++++++++++

vl.c | 13 +++--------

README | 2 +-

11 files changed, 122 insertions(+), 85 deletions(-)

2.14.3

Commit 00d09fdbbae5f7864ce754913efc84c12fdf9f1a ("vl: pause vcpus before

stopping iothreads") and commit dce8921b2baaf95974af8176406881872067adfa

("iothread: Stop threads before main() quits") tried to work around the

fact that emulation was still active during termination by stopping

iothreads. They suffer from race conditions:

1. virtio_scsi_handle_cmd_vq() racing with iothread_stop_all() hits the

virtio_scsi_ctx_check() assertion failure because the BDS AioContext

has been modified by iothread_stop_all().

2. Guest vq kick racing with main loop termination leaves a readable

ioeventfd that is handled by the next aio_poll() when external

clients are enabled again, resulting in unwanted emulation activity.

This patch obsoletes those commits by fully disabling emulation activity

when vcpus are stopped.

Use the new vm_shutdown() function instead of pause_all_vcpus() so that

vm change state handlers are invoked too. Virtio devices will now stop

their ioeventfds, preventing further emulation activity after vm_stop().

include/sysemu/iothread.h | 1 -

include/sysemu/sysemu.h | 1 +

cpus.c | 16 +++++++++++++---

iothread.c | 31 -------------------------------

vl.c | 13 +++----------

5 files changed, 17 insertions(+), 45 deletions(-)

diff --git a/include/sysemu/iothread.h b/include/sysemu/iothread.h

--- a/include/sysemu/iothread.h

+++ b/include/sysemu/iothread.h

@@ -XXX,XX +XXX,XX @@ typedef struct {

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);

/*

diff --git a/include/sysemu/sysemu.h b/include/sysemu/sysemu.h

index XXXXXXX..XXXXXXX 100644

--- a/include/sysemu/sysemu.h

+++ b/include/sysemu/sysemu.h

@@ -XXX,XX +XXX,XX @@ void vm_start(void);

int vm_prepare_start(void);

int vm_stop(RunState state);

int vm_stop_force_state(RunState state);

+int vm_shutdown(void);

typedef enum WakeupReason {

/* Always keep QEMU_WAKEUP_REASON_NONE = 0 */

diff --git a/cpus.c b/cpus.c

index XXXXXXX..XXXXXXX 100644

--- a/cpus.c

+++ b/cpus.c

@@ -XXX,XX +XXX,XX @@ void cpu_synchronize_all_pre_loadvm(void)

}

-static int do_vm_stop(RunState state)

+static int do_vm_stop(RunState state, bool send_stop)

{

int ret = 0;

@@ -XXX,XX +XXX,XX @@ static int do_vm_stop(RunState state)

pause_all_vcpus();

runstate_set(state);

vm_state_notify(0, state);

- qapi_event_send_stop(&error_abort);

+ if (send_stop) {

+ qapi_event_send_stop(&error_abort);

bdrv_drain_all();

@@ -XXX,XX +XXX,XX @@ static int do_vm_stop(RunState state)

return ret;

}

+/* Special vm_stop() variant for terminating the process. Historically clients

+ * did not expect a QMP STOP event and so we need to retain compatibility.

+ */

+int vm_shutdown(void)

+{

+ return do_vm_stop(RUN_STATE_SHUTDOWN, false);

+}

+

static bool cpu_can_run(CPUState *cpu)

{

if (cpu->stop) {

@@ -XXX,XX +XXX,XX @@ int vm_stop(RunState state)

return 0;

- return do_vm_stop(state);

+ return do_vm_stop(state, true);

}

/**

diff --git a/iothread.c b/iothread.c

index XXXXXXX..XXXXXXX 100644

--- a/iothread.c

+++ b/iothread.c

@@ -XXX,XX +XXX,XX @@ void iothread_stop(IOThread *iothread)

qemu_thread_join(&iothread->thread);

}

-static int iothread_stop_iter(Object *object, void *opaque)

-{

- IOThread *iothread;

-

- iothread = (IOThread *)object_dynamic_cast(object, TYPE_IOTHREAD);

- if (!iothread) {

- return 0;

- }

- iothread_stop(iothread);

- return 0;

-}

-

static void iothread_instance_init(Object *obj)

{

IOThread *iothread = IOTHREAD(obj);

@@ -XXX,XX +XXX,XX @@ IOThreadInfoList *qmp_query_iothreads(Error **errp)

return head;

}

-void iothread_stop_all(void)

-{

- Object *container = object_get_objects_root();

- BlockDriverState *bs;

- BdrvNextIterator it;

-

- for (bs = bdrv_first(&it); bs; bs = bdrv_next(&it)) {

- AioContext *ctx = bdrv_get_aio_context(bs);

- if (ctx == qemu_get_aio_context()) {

- continue;

- }

- aio_context_acquire(ctx);

- bdrv_set_aio_context(bs, qemu_get_aio_context());

- aio_context_release(ctx);

- }

-

- object_child_foreach(container, iothread_stop_iter, NULL);

-}

-

static gpointer iothread_g_main_context_init(gpointer opaque)

{

AioContext *ctx;

diff --git a/vl.c b/vl.c

index XXXXXXX..XXXXXXX 100644

--- a/vl.c

+++ b/vl.c

@@ -XXX,XX +XXX,XX @@ int main(int argc, char **argv, char **envp)

os_setup_post();

main_loop();

- replay_disable_events();

- /* The ordering of the following is delicate. Stop vcpus to prevent new

- * I/O requests being queued by the guest. Then stop IOThreads (this

- * includes a drain operation and completes all request processing). At

- * this point emulated devices are still associated with their IOThreads

- * (if any) but no longer have any work to do. Only then can we close

- * block devices safely because we know there is no more I/O coming.

- */

- pause_all_vcpus();

- iothread_stop_all();

+ /* No more vcpu or device emulation activity beyond this point */

+ vm_shutdown();

+

bdrv_close_all();

res_free();

2.14.3

If the main loop thread invokes .ioeventfd_stop() just as the vq handler

function begins in the IOThread then the handler may lose the race for

the AioContext lock. By the time the vq handler is able to acquire the

AioContext lock the ioeventfd has already been removed and the handler

isn't supposed to run anymore!

Use the new aio_wait_bh_oneshot() function to perform ioeventfd removal

from within the IOThread. This way no races with the vq handler are

possible.

Reviewed-by: Fam Zheng <famz@redhat.com>

Acked-by: Paolo Bonzini <pbonzini@redhat.com>

Message-id: 20180307144205.20619-4-stefanha@redhat.com

hw/scsi/virtio-scsi-dataplane.c | 9 +++++----

1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/hw/scsi/virtio-scsi-dataplane.c b/hw/scsi/virtio-scsi-dataplane.c

--- a/hw/scsi/virtio-scsi-dataplane.c

+++ b/hw/scsi/virtio-scsi-dataplane.c

@@ -XXX,XX +XXX,XX @@ static int virtio_scsi_vring_init(VirtIOSCSI *s, VirtQueue *vq, int n,

return 0;

}

-/* assumes s->ctx held */

-static void virtio_scsi_clear_aio(VirtIOSCSI *s)

+/* Context: BH in IOThread */

+static void virtio_scsi_dataplane_stop_bh(void *opaque)

{

+ VirtIOSCSI *s = opaque;

VirtIOSCSICommon *vs = VIRTIO_SCSI_COMMON(s);

int i;

@@ -XXX,XX +XXX,XX @@ int virtio_scsi_dataplane_start(VirtIODevice *vdev)

return 0;

fail_vrings:

- virtio_scsi_clear_aio(s);

+ aio_wait_bh_oneshot(s->ctx, virtio_scsi_dataplane_stop_bh, s);

aio_context_release(s->ctx);

for (i = 0; i < vs->conf.num_queues + 2; i++) {

virtio_bus_set_host_notifier(VIRTIO_BUS(qbus), i, false);

@@ -XXX,XX +XXX,XX @@ void virtio_scsi_dataplane_stop(VirtIODevice *vdev)

s->dataplane_stopping = true;

aio_context_acquire(s->ctx);

- virtio_scsi_clear_aio(s);

+ aio_wait_bh_oneshot(s->ctx, virtio_scsi_dataplane_stop_bh, s);

aio_context_release(s->ctx);

blk_drain_all(); /* ensure there are no in-flight requests */

2.14.3

If the main loop thread invokes .ioeventfd_stop() just as the vq handler

function begins in the IOThread then the handler may lose the race for

the AioContext lock. By the time the vq handler is able to acquire the

AioContext lock the ioeventfd has already been removed and the handler

isn't supposed to run anymore!

Use the new aio_wait_bh_oneshot() function to perform ioeventfd removal

from within the IOThread. This way no races with the vq handler are

possible.

hw/block/dataplane/virtio-blk.c | 24 +++++++++++++++++-------

1 file changed, 17 insertions(+), 7 deletions(-)

diff --git a/hw/block/dataplane/virtio-blk.c b/hw/block/dataplane/virtio-blk.c

--- a/hw/block/dataplane/virtio-blk.c

+++ b/hw/block/dataplane/virtio-blk.c

@@ -XXX,XX +XXX,XX @@ int virtio_blk_data_plane_start(VirtIODevice *vdev)

return -ENOSYS;

2.14.3