[PATCH v3 0/4] Introduce 'yank' oob qmp command to recover from hanging qemu

[PATCH v3 0/4] Introduce 'yank' oob qmp command to recover from hanging qemu

[Lukas Straub]

[-- Attachment #1: Type: text/plain, Size: 1632 bytes --]

Hello Everyone,
In many cases, if qemu has a network connection (qmp, migration, chardev, etc.)
to some other server and that server dies or hangs, qemu hangs too.
These patches introduce the new 'yank' out-of-band qmp command to recover from
these kinds of hangs. The different subsystems register callbacks which get
executed with the yank command. For example the callback can shutdown() a
socket. This is intended for the colo use-case, but it can be used for other
things too of course.

Regards,
Lukas Straub

v3:
 -don't touch softmmu/vl.c, use __contructor__ attribute instead (Paolo Bonzini)
 -fix build errors
 -rewrite migration patch so it actually passes all tests

v2:
 -don't touch io/ code anymore
 -always register yank functions
 -'yank' now takes a list of instances to yank
 -'query-yank' returns a list of yankable instances

Lukas Straub (4):
  Introduce yank feature
  block/nbd.c: Add yank feature
  chardev/char-socket.c: Add yank feature
  migration: Add yank feature

 Makefile.objs                 |   3 +
 block/nbd.c                   | 101 ++++++++++++--------
 chardev/char-socket.c         |  24 +++++
 migration/channel.c           |  12 +++
 migration/migration.c         |  18 +++-
 migration/multifd.c           |  10 ++
 migration/qemu-file-channel.c |   6 ++
 qapi/misc.json                |  45 +++++++++
 yank.c                        | 174 ++++++++++++++++++++++++++++++++++
 yank.h                        |  67 +++++++++++++
 10 files changed, 422 insertions(+), 38 deletions(-)
 create mode 100644 yank.c
 create mode 100644 yank.h

--
2.20.1

[-- Attachment #2: OpenPGP digital signature --]
[-- Type: application/pgp-signature, Size: 833 bytes --]

[PATCH v3 1/4] Introduce yank feature

[Lukas Straub]

[-- Attachment #1: Type: text/plain, Size: 8617 bytes --]

The yank feature allows to recover from hanging qemu by "yanking"
at various parts. Other qemu systems can register themselves and
multiple yank functions. Then all yank functions for selected
instances can be called by the 'yank' out-of-band qmp command.
Available instances can be queried by a 'query-yank' oob command.

Signed-off-by: Lukas Straub <lukasstraub2@web.de>
---
 qapi/misc.json |  45 +++++++++++++
 yank.c         | 174 +++++++++++++++++++++++++++++++++++++++++++++++++
 yank.h         |  67 +++++++++++++++++++
 3 files changed, 286 insertions(+)
 create mode 100644 yank.c
 create mode 100644 yank.h

diff --git a/qapi/misc.json b/qapi/misc.json
index 99b90ac80b..f5228b2502 100644
--- a/qapi/misc.json
+++ b/qapi/misc.json
@@ -1550,3 +1550,48 @@
 ##
 { 'command': 'query-vm-generation-id', 'returns': 'GuidInfo' }

+##
+# @YankInstances:
+#
+# @instances: List of yank instances.
+#
+# Yank instances are named after the following schema:
+# "blockdev:<node-name>", "chardev:<chardev-name>" and "migration"
+#
+# Since: 5.1
+##
+{ 'struct': 'YankInstances', 'data': {'instances': ['str'] } }
+
+##
+# @yank:
+#
+# Recover from hanging qemu by yanking the specified instances.
+#
+# Takes @YankInstances as argument.
+#
+# Returns: nothing.
+#
+# Example:
+#
+# -> { "execute": "yank", "arguments": { "instances": ["blockdev:nbd0"] } }
+# <- { "return": {} }
+#
+# Since: 5.1
+##
+{ 'command': 'yank', 'data': 'YankInstances', 'allow-oob': true }
+
+##
+# @query-yank:
+#
+# Query yank instances.
+#
+# Returns: @YankInstances
+#
+# Example:
+#
+# -> { "execute": "query-yank" }
+# <- { "return": { "instances": ["blockdev:nbd0"] } }
+#
+# Since: 5.1
+##
+{ 'command': 'query-yank', 'returns': 'YankInstances', 'allow-oob': true }
diff --git a/yank.c b/yank.c
new file mode 100644
index 0000000000..36d8139d4d
--- /dev/null
+++ b/yank.c
@@ -0,0 +1,174 @@
+/*
+ * QEMU yank feature
+ *
+ * Copyright (c) Lukas Straub <lukasstraub2@web.de>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2 or later.
+ * See the COPYING file in the top-level directory.
+ */
+
+#include "qemu/osdep.h"
+#include "qapi/error.h"
+#include "qemu/thread.h"
+#include "qemu/queue.h"
+#include "qapi/qapi-commands-misc.h"
+#include "io/channel.h"
+#include "yank.h"
+
+struct YankFuncAndParam {
+    YankFn *func;
+    void *opaque;
+    QLIST_ENTRY(YankFuncAndParam) next;
+};
+
+struct YankInstance {
+    char *name;
+    QLIST_HEAD(, YankFuncAndParam) yankfns;
+    QLIST_ENTRY(YankInstance) next;
+};
+
+static QemuMutex lock;
+static QLIST_HEAD(yankinst_list, YankInstance) head
+    = QLIST_HEAD_INITIALIZER(head);
+
+static struct YankInstance *yank_find_instance(char *name)
+{
+    struct YankInstance *tmp, *instance;
+    instance = NULL;
+    QLIST_FOREACH(tmp, &head, next) {
+        if (!strcmp(tmp->name, name)) {
+            instance = tmp;
+        }
+    }
+    return instance;
+}
+
+void yank_register_instance(char *instance_name)
+{
+    struct YankInstance *instance;
+
+    qemu_mutex_lock(&lock);
+    assert(!yank_find_instance(instance_name));
+
+    instance = g_slice_new(struct YankInstance);
+    instance->name = g_strdup(instance_name);
+    QLIST_INIT(&instance->yankfns);
+    QLIST_INSERT_HEAD(&head, instance, next);
+
+    qemu_mutex_unlock(&lock);
+}
+
+void yank_unregister_instance(char *instance_name)
+{
+    struct YankInstance *instance;
+
+    qemu_mutex_lock(&lock);
+    instance = yank_find_instance(instance_name);
+    assert(instance);
+
+    assert(QLIST_EMPTY(&instance->yankfns));
+    QLIST_REMOVE(instance, next);
+    g_free(instance->name);
+    g_slice_free(struct YankInstance, instance);
+
+    qemu_mutex_unlock(&lock);
+}
+
+void yank_register_function(char *instance_name, YankFn *func, void *opaque)
+{
+    struct YankInstance *instance;
+    struct YankFuncAndParam *entry;
+
+    qemu_mutex_lock(&lock);
+    instance = yank_find_instance(instance_name);
+    assert(instance);
+
+    entry = g_slice_new(struct YankFuncAndParam);
+    entry->func = func;
+    entry->opaque = opaque;
+
+    QLIST_INSERT_HEAD(&instance->yankfns, entry, next);
+    qemu_mutex_unlock(&lock);
+}
+
+void yank_unregister_function(char *instance_name, YankFn *func, void *opaque)
+{
+    struct YankInstance *instance;
+    struct YankFuncAndParam *entry;
+
+    qemu_mutex_lock(&lock);
+    instance = yank_find_instance(instance_name);
+    assert(instance);
+
+    QLIST_FOREACH(entry, &instance->yankfns, next) {
+        if (entry->func == func && entry->opaque == opaque) {
+            QLIST_REMOVE(entry, next);
+            g_slice_free(struct YankFuncAndParam, entry);
+            qemu_mutex_unlock(&lock);
+            return;
+        }
+    }
+
+    abort();
+}
+
+void yank_generic_iochannel(void *opaque)
+{
+    QIOChannel *ioc = QIO_CHANNEL(opaque);
+
+    qio_channel_shutdown(ioc, QIO_CHANNEL_SHUTDOWN_BOTH, NULL);
+}
+
+void qmp_yank(strList *instances, Error **errp)
+{
+    strList *tmp;
+    struct YankInstance *instance;
+    struct YankFuncAndParam *entry;
+
+    qemu_mutex_lock(&lock);
+    tmp = instances;
+    for (; tmp; tmp = tmp->next) {
+        instance = yank_find_instance(tmp->value);
+        if (!instance) {
+            error_set(errp, ERROR_CLASS_DEVICE_NOT_FOUND,
+                      "Instance '%s' not found", tmp->value);
+            qemu_mutex_unlock(&lock);
+            return;
+        }
+    }
+    tmp = instances;
+    for (; tmp; tmp = tmp->next) {
+        instance = yank_find_instance(tmp->value);
+        assert(instance);
+        QLIST_FOREACH(entry, &instance->yankfns, next) {
+            entry->func(entry->opaque);
+        }
+    }
+    qemu_mutex_unlock(&lock);
+}
+
+YankInstances *qmp_query_yank(Error **errp)
+{
+    struct YankInstance *instance;
+    YankInstances *ret;
+
+    ret = g_new0(YankInstances, 1);
+    ret->instances = NULL;
+
+    qemu_mutex_lock(&lock);
+    QLIST_FOREACH(instance, &head, next) {
+        strList *entry;
+        entry = g_new0(strList, 1);
+        entry->value = g_strdup(instance->name);
+        entry->next = ret->instances;
+        ret->instances = entry;
+    }
+    qemu_mutex_unlock(&lock);
+
+    return ret;
+}
+
+static void __attribute__((__constructor__)) yank_init(void)
+{
+    qemu_mutex_init(&lock);
+}
diff --git a/yank.h b/yank.h
new file mode 100644
index 0000000000..f1c8743b72
--- /dev/null
+++ b/yank.h
@@ -0,0 +1,67 @@
+
+#ifndef YANK_H
+#define YANK_H
+
+typedef void (YankFn) (void *opaque);
+
+/**
+ * yank_register_instance: Register a new instance.
+ *
+ * This registers a new instance for yanking. Must be called before any yank
+ * function is registered for this instance.
+ *
+ * This function is thread-safe.
+ *
+ * @instance_name: The globally unique name of the instance.
+ */
+void yank_register_instance(char *instance_name);
+
+/**
+ * yank_unregister_instance: Unregister a instance.
+ *
+ * This unregisters a instance. Must be called only after every yank function
+ * of the instance has been unregistered.
+ *
+ * This function is thread-safe.
+ *
+ * @instance_name: The name of the instance.
+ */
+void yank_unregister_instance(char *instance_name);
+
+/**
+ * yank_register_function: Register a yank function
+ *
+ * This registers a yank function. All limitations of qmp oob commands apply
+ * to the yank function as well.
+ *
+ * This function is thread-safe.
+ *
+ * @instance_name: The name of the instance
+ * @func: The yank function
+ * @opaque: Will be passed to the yank function
+ */
+void yank_register_function(char *instance_name, YankFn *func, void *opaque);
+
+/**
+ * yank_unregister_function: Unregister a yank function
+ *
+ * This unregisters a yank function.
+ *
+ * This function is thread-safe.
+ *
+ * @instance_name: The name of the instance
+ * @func: func that was passed to yank_register_function
+ * @opaque: opaque that was passed to yank_register_function
+ */
+void yank_unregister_function(char *instance_name, YankFn *func, void *opaque);
+
+/**
+ * yank_unregister_function: Generic yank function for iochannel
+ *
+ * This is a generic yank function which will call qio_channel_shutdown on the
+ * provided QIOChannel.
+ *
+ * @opaque: QIOChannel to shutdown
+ */
+void yank_generic_iochannel(void *opaque);
+#endif
--
2.20.1


[-- Attachment #2: OpenPGP digital signature --]
[-- Type: application/pgp-signature, Size: 833 bytes --]

[PATCH v3 2/4] block/nbd.c: Add yank feature

[Lukas Straub]

[-- Attachment #1: Type: text/plain, Size: 12595 bytes --]

Register a yank function which shuts down the socket and sets
s->state = NBD_CLIENT_QUIT. This is the same behaviour as if an
error occured.

Signed-off-by: Lukas Straub <lukasstraub2@web.de>
---
 Makefile.objs |   1 +
 block/nbd.c   | 101 ++++++++++++++++++++++++++++++++------------------
 2 files changed, 65 insertions(+), 37 deletions(-)

diff --git a/Makefile.objs b/Makefile.objs
index a7c967633a..8e403b81f3 100644
--- a/Makefile.objs
+++ b/Makefile.objs
@@ -18,6 +18,7 @@ block-obj-y += block.o blockjob.o job.o
 block-obj-y += block/ scsi/
 block-obj-y += qemu-io-cmds.o
 block-obj-$(CONFIG_REPLICATION) += replication.o
+block-obj-y += yank.o

 block-obj-m = block/

diff --git a/block/nbd.c b/block/nbd.c
index 2160859f64..3a41749f1b 100644
--- a/block/nbd.c
+++ b/block/nbd.c
@@ -35,6 +35,7 @@
 #include "qemu/option.h"
 #include "qemu/cutils.h"
 #include "qemu/main-loop.h"
+#include "qemu/atomic.h"

 #include "qapi/qapi-visit-sockets.h"
 #include "qapi/qmp/qstring.h"
@@ -43,6 +44,8 @@
 #include "block/nbd.h"
 #include "block/block_int.h"

+#include "yank.h"
+
 #define EN_OPTSTR ":exportname="
 #define MAX_NBD_REQUESTS    16

@@ -84,6 +87,8 @@ typedef struct BDRVNBDState {
     NBDReply reply;
     BlockDriverState *bs;

+    char *yank_name;
+
     /* Connection parameters */
     uint32_t reconnect_delay;
     SocketAddress *saddr;
@@ -94,6 +99,7 @@ typedef struct BDRVNBDState {
 } BDRVNBDState;

 static int nbd_client_connect(BlockDriverState *bs, Error **errp);
+static void nbd_yank(void *opaque);

 static void nbd_clear_bdrvstate(BDRVNBDState *s)
 {
@@ -106,17 +112,19 @@ static void nbd_clear_bdrvstate(BDRVNBDState *s)
     s->tlscredsid = NULL;
     g_free(s->x_dirty_bitmap);
     s->x_dirty_bitmap = NULL;
+    g_free(s->yank_name);
+    s->yank_name = NULL;
 }

 static void nbd_channel_error(BDRVNBDState *s, int ret)
 {
     if (ret == -EIO) {
-        if (s->state == NBD_CLIENT_CONNECTED) {
+        if (atomic_read(&s->state) == NBD_CLIENT_CONNECTED) {
             s->state = s->reconnect_delay ? NBD_CLIENT_CONNECTING_WAIT :
                                             NBD_CLIENT_CONNECTING_NOWAIT;
         }
     } else {
-        if (s->state == NBD_CLIENT_CONNECTED) {
+        if (atomic_read(&s->state) == NBD_CLIENT_CONNECTED) {
             qio_channel_shutdown(s->ioc, QIO_CHANNEL_SHUTDOWN_BOTH, NULL);
         }
         s->state = NBD_CLIENT_QUIT;
@@ -167,7 +175,7 @@ static void nbd_client_attach_aio_context(BlockDriverState *bs,
      * s->connection_co is either yielded from nbd_receive_reply or from
      * nbd_co_reconnect_loop()
      */
-    if (s->state == NBD_CLIENT_CONNECTED) {
+    if (atomic_read(&s->state) == NBD_CLIENT_CONNECTED) {
         qio_channel_attach_aio_context(QIO_CHANNEL(s->ioc), new_context);
     }

@@ -206,7 +214,7 @@ static void nbd_teardown_connection(BlockDriverState *bs)
 {
     BDRVNBDState *s = (BDRVNBDState *)bs->opaque;

-    if (s->state == NBD_CLIENT_CONNECTED) {
+    if (atomic_read(&s->state) == NBD_CLIENT_CONNECTED) {
         /* finish any pending coroutines */
         assert(s->ioc);
         qio_channel_shutdown(s->ioc, QIO_CHANNEL_SHUTDOWN_BOTH, NULL);
@@ -230,13 +238,14 @@ static void nbd_teardown_connection(BlockDriverState *bs)

 static bool nbd_client_connecting(BDRVNBDState *s)
 {
-    return s->state == NBD_CLIENT_CONNECTING_WAIT ||
-        s->state == NBD_CLIENT_CONNECTING_NOWAIT;
+    NBDClientState state = atomic_read(&s->state);
+    return state == NBD_CLIENT_CONNECTING_WAIT ||
+        state == NBD_CLIENT_CONNECTING_NOWAIT;
 }

 static bool nbd_client_connecting_wait(BDRVNBDState *s)
 {
-    return s->state == NBD_CLIENT_CONNECTING_WAIT;
+    return atomic_read(&s->state) == NBD_CLIENT_CONNECTING_WAIT;
 }

 static coroutine_fn void nbd_reconnect_attempt(BDRVNBDState *s)
@@ -274,6 +283,7 @@ static coroutine_fn void nbd_reconnect_attempt(BDRVNBDState *s)
     /* Finalize previous connection if any */
     if (s->ioc) {
         nbd_client_detach_aio_context(s->bs);
+        yank_unregister_function(s->yank_name, nbd_yank, s->bs);
         object_unref(OBJECT(s->sioc));
         s->sioc = NULL;
         object_unref(OBJECT(s->ioc));
@@ -305,7 +315,7 @@ static coroutine_fn void nbd_co_reconnect_loop(BDRVNBDState *s)
     nbd_reconnect_attempt(s);

     while (nbd_client_connecting(s)) {
-        if (s->state == NBD_CLIENT_CONNECTING_WAIT &&
+        if (atomic_read(&s->state) == NBD_CLIENT_CONNECTING_WAIT &&
             qemu_clock_get_ns(QEMU_CLOCK_REALTIME) - start_time_ns > delay_ns)
         {
             s->state = NBD_CLIENT_CONNECTING_NOWAIT;
@@ -341,7 +351,7 @@ static coroutine_fn void nbd_connection_entry(void *opaque)
     int ret = 0;
     Error *local_err = NULL;

-    while (s->state != NBD_CLIENT_QUIT) {
+    while (atomic_read(&s->state) != NBD_CLIENT_QUIT) {
         /*
          * The NBD client can only really be considered idle when it has
          * yielded from qio_channel_readv_all_eof(), waiting for data. This is
@@ -356,7 +366,7 @@ static coroutine_fn void nbd_connection_entry(void *opaque)
             nbd_co_reconnect_loop(s);
         }

-        if (s->state != NBD_CLIENT_CONNECTED) {
+        if (atomic_read(&s->state) != NBD_CLIENT_CONNECTED) {
             continue;
         }

@@ -411,6 +421,7 @@ static coroutine_fn void nbd_connection_entry(void *opaque)
     s->connection_co = NULL;
     if (s->ioc) {
         nbd_client_detach_aio_context(s->bs);
+        yank_unregister_function(s->yank_name, nbd_yank, s->bs);
         object_unref(OBJECT(s->sioc));
         s->sioc = NULL;
         object_unref(OBJECT(s->ioc));
@@ -435,7 +446,7 @@ static int nbd_co_send_request(BlockDriverState *bs,
         qemu_co_queue_wait(&s->free_sema, &s->send_mutex);
     }

-    if (s->state != NBD_CLIENT_CONNECTED) {
+    if (atomic_read(&s->state) != NBD_CLIENT_CONNECTED) {
         rc = -EIO;
         goto err;
     }
@@ -462,7 +473,7 @@ static int nbd_co_send_request(BlockDriverState *bs,
     if (qiov) {
         qio_channel_set_cork(s->ioc, true);
         rc = nbd_send_request(s->ioc, request);
-        if (rc >= 0 && s->state == NBD_CLIENT_CONNECTED) {
+        if (rc >= 0 && atomic_read(&s->state) == NBD_CLIENT_CONNECTED) {
             if (qio_channel_writev_all(s->ioc, qiov->iov, qiov->niov,
                                        NULL) < 0) {
                 rc = -EIO;
@@ -777,7 +788,7 @@ static coroutine_fn int nbd_co_do_receive_one_chunk(
     s->requests[i].receiving = true;
     qemu_coroutine_yield();
     s->requests[i].receiving = false;
-    if (s->state != NBD_CLIENT_CONNECTED) {
+    if (atomic_read(&s->state) != NBD_CLIENT_CONNECTED) {
         error_setg(errp, "Connection closed");
         return -EIO;
     }
@@ -936,7 +947,7 @@ static bool nbd_reply_chunk_iter_receive(BDRVNBDState *s,
     NBDReply local_reply;
     NBDStructuredReplyChunk *chunk;
     Error *local_err = NULL;
-    if (s->state != NBD_CLIENT_CONNECTED) {
+    if (atomic_read(&s->state) != NBD_CLIENT_CONNECTED) {
         error_setg(&local_err, "Connection closed");
         nbd_iter_channel_error(iter, -EIO, &local_err);
         goto break_loop;
@@ -961,7 +972,8 @@ static bool nbd_reply_chunk_iter_receive(BDRVNBDState *s,
     }

     /* Do not execute the body of NBD_FOREACH_REPLY_CHUNK for simple reply. */
-    if (nbd_reply_is_simple(reply) || s->state != NBD_CLIENT_CONNECTED) {
+    if (nbd_reply_is_simple(reply) ||
+        atomic_read(&s->state) != NBD_CLIENT_CONNECTED) {
         goto break_loop;
     }

@@ -1395,6 +1407,15 @@ static int nbd_client_reopen_prepare(BDRVReopenState *state,
     return 0;
 }

+static void nbd_yank(void *opaque)
+{
+    BlockDriverState *bs = opaque;
+    BDRVNBDState *s = (BDRVNBDState *)bs->opaque;
+
+    qio_channel_shutdown(QIO_CHANNEL(s->sioc), QIO_CHANNEL_SHUTDOWN_BOTH, NULL);
+    atomic_set(&s->state, NBD_CLIENT_QUIT);
+}
+
 static void nbd_client_close(BlockDriverState *bs)
 {
     BDRVNBDState *s = (BDRVNBDState *)bs->opaque;
@@ -1407,25 +1428,29 @@ static void nbd_client_close(BlockDriverState *bs)
     nbd_teardown_connection(bs);
 }

-static QIOChannelSocket *nbd_establish_connection(SocketAddress *saddr,
-                                                  Error **errp)
+static int nbd_establish_connection(BlockDriverState *bs,
+                                    SocketAddress *saddr,
+                                    Error **errp)
 {
-    QIOChannelSocket *sioc;
+    BDRVNBDState *s = (BDRVNBDState *)bs->opaque;
     Error *local_err = NULL;

-    sioc = qio_channel_socket_new();
-    qio_channel_set_name(QIO_CHANNEL(sioc), "nbd-client");
+    s->sioc = qio_channel_socket_new();
+    qio_channel_set_name(QIO_CHANNEL(s->sioc), "nbd-client");
+    yank_register_function(s->yank_name, nbd_yank, bs);

-    qio_channel_socket_connect_sync(sioc, saddr, &local_err);
+    qio_channel_socket_connect_sync(s->sioc, saddr, &local_err);
     if (local_err) {
-        object_unref(OBJECT(sioc));
+        yank_unregister_function(s->yank_name, nbd_yank, bs);
+        object_unref(OBJECT(s->sioc));
+        s->sioc = NULL;
         error_propagate(errp, local_err);
-        return NULL;
+        return -1;
     }

-    qio_channel_set_delay(QIO_CHANNEL(sioc), false);
+    qio_channel_set_delay(QIO_CHANNEL(s->sioc), false);

-    return sioc;
+    return 0;
 }

 static int nbd_client_connect(BlockDriverState *bs, Error **errp)
@@ -1438,28 +1463,27 @@ static int nbd_client_connect(BlockDriverState *bs, Error **errp)
      * establish TCP connection, return error if it fails
      * TODO: Configurable retry-until-timeout behaviour.
      */
-    QIOChannelSocket *sioc = nbd_establish_connection(s->saddr, errp);
-
-    if (!sioc) {
+    if (nbd_establish_connection(bs, s->saddr, errp) < 0) {
         return -ECONNREFUSED;
     }

     /* NBD handshake */
     trace_nbd_client_connect(s->export);
-    qio_channel_set_blocking(QIO_CHANNEL(sioc), false, NULL);
-    qio_channel_attach_aio_context(QIO_CHANNEL(sioc), aio_context);
+    qio_channel_set_blocking(QIO_CHANNEL(s->sioc), false, NULL);
+    qio_channel_attach_aio_context(QIO_CHANNEL(s->sioc), aio_context);

     s->info.request_sizes = true;
     s->info.structured_reply = true;
     s->info.base_allocation = true;
     s->info.x_dirty_bitmap = g_strdup(s->x_dirty_bitmap);
     s->info.name = g_strdup(s->export ?: "");
-    ret = nbd_receive_negotiate(aio_context, QIO_CHANNEL(sioc), s->tlscreds,
+    ret = nbd_receive_negotiate(aio_context, QIO_CHANNEL(s->sioc), s->tlscreds,
                                 s->hostname, &s->ioc, &s->info, errp);
     g_free(s->info.x_dirty_bitmap);
     g_free(s->info.name);
     if (ret < 0) {
-        object_unref(OBJECT(sioc));
+        yank_unregister_function(s->yank_name, nbd_yank, bs);
+        object_unref(OBJECT(s->sioc));
         return ret;
     }
     if (s->x_dirty_bitmap && !s->info.base_allocation) {
@@ -1485,10 +1509,8 @@ static int nbd_client_connect(BlockDriverState *bs, Error **errp)
         }
     }

-    s->sioc = sioc;
-
     if (!s->ioc) {
-        s->ioc = QIO_CHANNEL(sioc);
+        s->ioc = QIO_CHANNEL(s->sioc);
         object_ref(OBJECT(s->ioc));
     }

@@ -1504,9 +1526,10 @@ static int nbd_client_connect(BlockDriverState *bs, Error **errp)
     {
         NBDRequest request = { .type = NBD_CMD_DISC };

-        nbd_send_request(s->ioc ?: QIO_CHANNEL(sioc), &request);
+        nbd_send_request(s->ioc ?: QIO_CHANNEL(s->sioc), &request);

-        object_unref(OBJECT(sioc));
+        yank_unregister_function(s->yank_name, nbd_yank, bs);
+        object_unref(OBJECT(s->sioc));

         return ret;
     }
@@ -1913,6 +1936,9 @@ static int nbd_open(BlockDriverState *bs, QDict *options, int flags,
     qemu_co_mutex_init(&s->send_mutex);
     qemu_co_queue_init(&s->free_sema);

+    s->yank_name = g_strconcat("blockdev:", bs->node_name, NULL);
+    yank_register_instance(s->yank_name);
+
     ret = nbd_client_connect(bs, errp);
     if (ret < 0) {
         nbd_clear_bdrvstate(s);
@@ -1972,6 +1998,7 @@ static void nbd_close(BlockDriverState *bs)
     BDRVNBDState *s = bs->opaque;

     nbd_client_close(bs);
+    yank_unregister_instance(s->yank_name);
     nbd_clear_bdrvstate(s);
 }

--
2.20.1


[-- Attachment #2: OpenPGP digital signature --]
[-- Type: application/pgp-signature, Size: 833 bytes --]

[PATCH v3 3/4] chardev/char-socket.c: Add yank feature

[Lukas Straub]

[-- Attachment #1: Type: text/plain, Size: 4627 bytes --]

Register a yank function to shutdown the socket on yank.

Signed-off-by: Lukas Straub <lukasstraub2@web.de>
---
 Makefile.objs         |  1 +
 chardev/char-socket.c | 24 ++++++++++++++++++++++++
 2 files changed, 25 insertions(+)

diff --git a/Makefile.objs b/Makefile.objs
index 8e403b81f3..5582f4eda9 100644
--- a/Makefile.objs
+++ b/Makefile.objs
@@ -10,6 +10,7 @@ qom-obj-y = qom/
 ifeq ($(call lor,$(CONFIG_SOFTMMU),$(CONFIG_TOOLS)),y)

 chardev-obj-y = chardev/
+chardev-obj-y += yank.o

 authz-obj-y = authz/

diff --git a/chardev/char-socket.c b/chardev/char-socket.c
index 185fe38dda..d5c6cd2153 100644
--- a/chardev/char-socket.c
+++ b/chardev/char-socket.c
@@ -34,6 +34,7 @@
 #include "qapi/error.h"
 #include "qapi/clone-visitor.h"
 #include "qapi/qapi-visit-sockets.h"
+#include "yank.h"

 #include "chardev/char-io.h"

@@ -69,6 +70,7 @@ typedef struct {
     size_t read_msgfds_num;
     int *write_msgfds;
     size_t write_msgfds_num;
+    char *yank_name;

     SocketAddress *addr;
     bool is_listen;
@@ -409,6 +411,11 @@ static void tcp_chr_free_connection(Chardev *chr)

     tcp_set_msgfds(chr, NULL, 0);
     remove_fd_in_watch(chr);
+    if (s->state == TCP_CHARDEV_STATE_CONNECTING
+        || s->state == TCP_CHARDEV_STATE_CONNECTED) {
+        yank_unregister_function(s->yank_name, yank_generic_iochannel,
+                                 QIO_CHANNEL(s->sioc));
+    }
     object_unref(OBJECT(s->sioc));
     s->sioc = NULL;
     object_unref(OBJECT(s->ioc));
@@ -912,6 +919,8 @@ static int tcp_chr_add_client(Chardev *chr, int fd)
     }
     tcp_chr_change_state(s, TCP_CHARDEV_STATE_CONNECTING);
     tcp_chr_set_client_ioc_name(chr, sioc);
+    yank_register_function(s->yank_name, yank_generic_iochannel,
+                           QIO_CHANNEL(sioc));
     ret = tcp_chr_new_client(chr, sioc);
     object_unref(OBJECT(sioc));
     return ret;
@@ -926,6 +935,8 @@ static void tcp_chr_accept(QIONetListener *listener,

     tcp_chr_change_state(s, TCP_CHARDEV_STATE_CONNECTING);
     tcp_chr_set_client_ioc_name(chr, cioc);
+    yank_register_function(s->yank_name, yank_generic_iochannel,
+                           QIO_CHANNEL(cioc));
     tcp_chr_new_client(chr, cioc);
 }

@@ -941,6 +952,8 @@ static int tcp_chr_connect_client_sync(Chardev *chr, Error **errp)
         object_unref(OBJECT(sioc));
         return -1;
     }
+    yank_register_function(s->yank_name, yank_generic_iochannel,
+                           QIO_CHANNEL(sioc));
     tcp_chr_new_client(chr, sioc);
     object_unref(OBJECT(sioc));
     return 0;
@@ -956,6 +969,8 @@ static void tcp_chr_accept_server_sync(Chardev *chr)
     tcp_chr_change_state(s, TCP_CHARDEV_STATE_CONNECTING);
     sioc = qio_net_listener_wait_client(s->listener);
     tcp_chr_set_client_ioc_name(chr, sioc);
+    yank_register_function(s->yank_name, yank_generic_iochannel,
+                           QIO_CHANNEL(sioc));
     tcp_chr_new_client(chr, sioc);
     object_unref(OBJECT(sioc));
 }
@@ -1066,6 +1081,8 @@ static void char_socket_finalize(Object *obj)
         object_unref(OBJECT(s->tls_creds));
     }
     g_free(s->tls_authz);
+    yank_unregister_instance(s->yank_name);
+    g_free(s->yank_name);

     qemu_chr_be_event(chr, CHR_EVENT_CLOSED);
 }
@@ -1081,6 +1098,8 @@ static void qemu_chr_socket_connected(QIOTask *task, void *opaque)

     if (qio_task_propagate_error(task, &err)) {
         tcp_chr_change_state(s, TCP_CHARDEV_STATE_DISCONNECTED);
+        yank_unregister_function(s->yank_name, yank_generic_iochannel,
+                                 QIO_CHANNEL(sioc));
         check_report_connect_error(chr, err);
         error_free(err);
         goto cleanup;
@@ -1115,6 +1134,8 @@ static void tcp_chr_connect_client_async(Chardev *chr)
     tcp_chr_change_state(s, TCP_CHARDEV_STATE_CONNECTING);
     sioc = qio_channel_socket_new();
     tcp_chr_set_client_ioc_name(chr, sioc);
+    yank_register_function(s->yank_name, yank_generic_iochannel,
+                           QIO_CHANNEL(sioc));
     /*
      * Normally code would use the qio_channel_socket_connect_async
      * method which uses a QIOTask + qio_task_set_error internally
@@ -1356,6 +1377,9 @@ static void qmp_chardev_open_socket(Chardev *chr,
         qemu_chr_set_feature(chr, QEMU_CHAR_FEATURE_FD_PASS);
     }

+    s->yank_name = g_strconcat("chardev:", chr->label, NULL);
+    yank_register_instance(s->yank_name);
+
     /* be isn't opened until we get a connection */
     *be_opened = false;

--
2.20.1


[-- Attachment #2: OpenPGP digital signature --]
[-- Type: application/pgp-signature, Size: 833 bytes --]

[PATCH v3 4/4] migration: Add yank feature

[Lukas Straub]

[-- Attachment #1: Type: text/plain, Size: 7172 bytes --]

Register yank functions on sockets to shut them down.

Signed-off-by: Lukas Straub <lukasstraub2@web.de>
---
 Makefile.objs                 |  1 +
 migration/channel.c           | 12 ++++++++++++
 migration/migration.c         | 18 +++++++++++++++++-
 migration/multifd.c           | 10 ++++++++++
 migration/qemu-file-channel.c |  6 ++++++
 5 files changed, 46 insertions(+), 1 deletion(-)

diff --git a/Makefile.objs b/Makefile.objs
index 5582f4eda9..d2a49d3834 100644
--- a/Makefile.objs
+++ b/Makefile.objs
@@ -58,6 +58,7 @@ common-obj-$(CONFIG_LINUX) += fsdev/

 common-obj-y += accel/
 common-obj-y += migration/
+common-obj-y += yank.o

 common-obj-y += audio/
 common-obj-m += audio/
diff --git a/migration/channel.c b/migration/channel.c
index 20e4c8e2dc..5cb48d403a 100644
--- a/migration/channel.c
+++ b/migration/channel.c
@@ -18,6 +18,8 @@
 #include "trace.h"
 #include "qapi/error.h"
 #include "io/channel-tls.h"
+#include "io/channel-socket.h"
+#include "yank.h"

 /**
  * @migration_channel_process_incoming - Create new incoming migration channel
@@ -35,6 +37,11 @@ void migration_channel_process_incoming(QIOChannel *ioc)
     trace_migration_set_incoming_channel(
         ioc, object_get_typename(OBJECT(ioc)));

+    if (object_dynamic_cast(OBJECT(ioc), TYPE_QIO_CHANNEL_SOCKET)) {
+        yank_register_function((char *) "migration", yank_generic_iochannel,
+                               QIO_CHANNEL(ioc));
+    }
+
     if (s->parameters.tls_creds &&
         *s->parameters.tls_creds &&
         !object_dynamic_cast(OBJECT(ioc),
@@ -67,6 +74,11 @@ void migration_channel_connect(MigrationState *s,
         ioc, object_get_typename(OBJECT(ioc)), hostname, error);

     if (!error) {
+        if (object_dynamic_cast(OBJECT(ioc), TYPE_QIO_CHANNEL_SOCKET)) {
+            yank_register_function((char *) "migration", yank_generic_iochannel,
+                                   QIO_CHANNEL(ioc));
+        }
+
         if (s->parameters.tls_creds &&
             *s->parameters.tls_creds &&
             !object_dynamic_cast(OBJECT(ioc),
diff --git a/migration/migration.c b/migration/migration.c
index 187ac0410c..c6d7119c08 100644
--- a/migration/migration.c
+++ b/migration/migration.c
@@ -54,6 +54,7 @@
 #include "net/announce.h"
 #include "qemu/queue.h"
 #include "multifd.h"
+#include "yank.h"

 #define MAX_THROTTLE  (32 << 20)      /* Migration transfer speed throttling */

@@ -231,6 +232,8 @@ void migration_incoming_state_destroy(void)
         qapi_free_SocketAddressList(mis->socket_address_list);
         mis->socket_address_list = NULL;
     }
+
+    yank_unregister_instance((char *) "migration");
 }

 static void migrate_generate_event(int new_state)
@@ -362,7 +365,9 @@ void qemu_start_incoming_migration(const char *uri, Error **errp)
     const char *p;

     qapi_event_send_migration(MIGRATION_STATUS_SETUP);
+    yank_register_instance((char *) "migration");
     if (!strcmp(uri, "defer")) {
+        yank_unregister_instance((char *) "migration");
         deferred_incoming_migration(errp);
     } else if (strstart(uri, "tcp:", &p)) {
         tcp_start_incoming_migration(p, errp);
@@ -377,6 +382,7 @@ void qemu_start_incoming_migration(const char *uri, Error **errp)
     } else if (strstart(uri, "fd:", &p)) {
         fd_start_incoming_migration(p, errp);
     } else {
+        yank_unregister_instance((char *) "migration");
         error_setg(errp, "unknown migration protocol: %s", uri);
     }
 }
@@ -1632,6 +1638,7 @@ static void migrate_fd_cleanup(MigrationState *s)
     }
     notifier_list_notify(&migration_state_notifiers, s);
     block_cleanup_parameters(s);
+    yank_unregister_instance((char *) "migration");
 }

 static void migrate_fd_cleanup_schedule(MigrationState *s)
@@ -1899,6 +1906,7 @@ void qmp_migrate_recover(const char *uri, Error **errp)
      * only re-setup the migration stream and poke existing migration
      * to continue using that newly established channel.
      */
+    yank_unregister_instance((char *) "migration");
     qemu_start_incoming_migration(uri, errp);
 }

@@ -2035,7 +2043,9 @@ void qmp_migrate(const char *uri, bool has_blk, bool blk,
         /* Error detected, put into errp */
         return;
     }
-
+    if (!(has_resume && resume)) {
+        yank_register_instance((char *) "migration");
+    }
     if (strstart(uri, "tcp:", &p)) {
         tcp_start_outgoing_migration(s, p, &local_err);
 #ifdef CONFIG_RDMA
@@ -2049,6 +2059,9 @@ void qmp_migrate(const char *uri, bool has_blk, bool blk,
     } else if (strstart(uri, "fd:", &p)) {
         fd_start_outgoing_migration(s, p, &local_err);
     } else {
+        if (!(has_resume && resume)) {
+            yank_unregister_instance((char *) "migration");
+        }
         error_setg(errp, QERR_INVALID_PARAMETER_VALUE, "uri",
                    "a valid migration protocol");
         migrate_set_state(&s->state, MIGRATION_STATUS_SETUP,
@@ -2058,6 +2071,9 @@ void qmp_migrate(const char *uri, bool has_blk, bool blk,
     }

     if (local_err) {
+        if (!(has_resume && resume)) {
+            yank_unregister_instance((char *) "migration");
+        }
         migrate_fd_error(s, local_err);
         error_propagate(errp, local_err);
         return;
diff --git a/migration/multifd.c b/migration/multifd.c
index cb6a4a3ab8..97566262c1 100644
--- a/migration/multifd.c
+++ b/migration/multifd.c
@@ -24,6 +24,9 @@
 #include "trace.h"
 #include "multifd.h"

+#include "yank.h"
+#include "io/channel-socket.h"
+
 /* Multiple fd's */

 #define MULTIFD_MAGIC 0x11223344U
@@ -856,6 +859,13 @@ int multifd_load_cleanup(Error **errp)
     for (i = 0; i < migrate_multifd_channels(); i++) {
         MultiFDRecvParams *p = &multifd_recv_state->params[i];

+        if (object_dynamic_cast(OBJECT(p->c), TYPE_QIO_CHANNEL_SOCKET)
+            && OBJECT(p->c)->ref == 1) {
+            yank_unregister_function((char *) "migration",
+                                     yank_generic_iochannel,
+                                     QIO_CHANNEL(p->c));
+        }
+
         object_unref(OBJECT(p->c));
         p->c = NULL;
         qemu_mutex_destroy(&p->mutex);
diff --git a/migration/qemu-file-channel.c b/migration/qemu-file-channel.c
index d2ce32f4b9..b725ac8098 100644
--- a/migration/qemu-file-channel.c
+++ b/migration/qemu-file-channel.c
@@ -27,6 +27,7 @@
 #include "qemu-file.h"
 #include "io/channel-socket.h"
 #include "qemu/iov.h"
+#include "yank.h"


 static ssize_t channel_writev_buffer(void *opaque,
@@ -104,6 +105,11 @@ static int channel_close(void *opaque, Error **errp)
     int ret;
     QIOChannel *ioc = QIO_CHANNEL(opaque);
     ret = qio_channel_close(ioc, errp);
+    if (object_dynamic_cast(OBJECT(ioc), TYPE_QIO_CHANNEL_SOCKET)
+        && OBJECT(ioc)->ref == 1) {
+        yank_unregister_function((char *) "migration", yank_generic_iochannel,
+                                 QIO_CHANNEL(ioc));
+    }
     object_unref(OBJECT(ioc));
     return ret;
 }
--
2.20.1

[-- Attachment #2: OpenPGP digital signature --]
[-- Type: application/pgp-signature, Size: 833 bytes --]

Re: [PATCH v3 0/4] Introduce 'yank' oob qmp command to recover from hanging qemu

[no-reply]

Patchew URL: https://patchew.org/QEMU/cover.1590344541.git.lukasstraub2@web.de/



Hi,

This series failed the docker-quick@centos7 build test. Please find the testing commands and
their output below. If you have Docker installed, you can probably reproduce it
locally.

=== TEST SCRIPT BEGIN ===
#!/bin/bash
make docker-image-centos7 V=1 NETWORK=1
time make docker-test-quick@centos7 SHOW_ENV=1 J=14 NETWORK=1
=== TEST SCRIPT END ===

migration/qemu-file-channel.o: In function `channel_close':
/tmp/qemu-test/src/migration/qemu-file-channel.c:110: undefined reference to `yank_generic_iochannel'
/tmp/qemu-test/src/migration/qemu-file-channel.c:110: undefined reference to `yank_unregister_function'
collect2: error: ld returned 1 exit status
  LINK    tests/test-cutils
make: *** [tests/test-vmstate] Error 1
make: *** Waiting for unfinished jobs....
  TEST    iotest-qcow2: 001
  TEST    iotest-qcow2: 002
---
Not run: 259
Failures: 267
Failed 1 of 119 iotests
make: *** [check-tests/check-block.sh] Error 1
make: *** wait: No child processes.  Stop.
Traceback (most recent call last):
  File "./tests/docker/docker.py", line 664, in <module>
---
    raise CalledProcessError(retcode, cmd)
subprocess.CalledProcessError: Command '['sudo', '-n', 'docker', 'run', '--label', 'com.qemu.instance.uuid=db483e1a7b374ed8a9cf3528ad2357b2', '-u', '1003', '--security-opt', 'seccomp=unconfined', '--rm', '-e', 'TARGET_LIST=', '-e', 'EXTRA_CONFIGURE_OPTS=', '-e', 'V=', '-e', 'J=14', '-e', 'DEBUG=', '-e', 'SHOW_ENV=1', '-e', 'CCACHE_DIR=/var/tmp/ccache', '-v', '/home/patchew2/.cache/qemu-docker-ccache:/var/tmp/ccache:z', '-v', '/var/tmp/patchew-tester-tmp-4gmncabb/src/docker-src.2020-05-24-17.04.07.24804:/var/tmp/qemu:z,ro', 'qemu:centos7', '/var/tmp/qemu/run', 'test-quick']' returned non-zero exit status 2.
filter=--filter=label=com.qemu.instance.uuid=db483e1a7b374ed8a9cf3528ad2357b2
make[1]: *** [docker-run] Error 1
make[1]: Leaving directory `/var/tmp/patchew-tester-tmp-4gmncabb/src'
make: *** [docker-run-test-quick@centos7] Error 2

real    12m5.130s
user    0m8.082s


The full log is available at
http://patchew.org/logs/cover.1590344541.git.lukasstraub2@web.de/testing.docker-quick@centos7/?type=message.
---
Email generated automatically by Patchew [https://patchew.org/].
Please send your feedback to patchew-devel@redhat.com

Re: [PATCH v3 0/4] Introduce 'yank' oob qmp command to recover from hanging qemu

[no-reply]

Patchew URL: https://patchew.org/QEMU/cover.1590344541.git.lukasstraub2@web.de/



Hi,

This series failed the asan build test. Please find the testing commands and
their output below. If you have Docker installed, you can probably reproduce it
locally.

=== TEST SCRIPT BEGIN ===
#!/bin/bash
export ARCH=x86_64
make docker-image-fedora V=1 NETWORK=1
time make docker-test-debug@fedora TARGET_LIST=x86_64-softmmu J=14 NETWORK=1
=== TEST SCRIPT END ===

migration/qemu-file-channel.o: in function `channel_close':
/tmp/qemu-test/src/migration/qemu-file-channel.c:111: undefined reference to `yank_generic_iochannel'
/usr/bin/ld: /tmp/qemu-test/src/migration/qemu-file-channel.c:110: undefined reference to `yank_unregister_function'
clang-8: error: linker command failed with exit code 1 (use -v to see invocation)
make: *** [/tmp/qemu-test/src/rules.mak:124: tests/test-vmstate] Error 1
make: *** Waiting for unfinished jobs....
Traceback (most recent call last):
  File "./tests/docker/docker.py", line 664, in <module>
---
    raise CalledProcessError(retcode, cmd)
subprocess.CalledProcessError: Command '['sudo', '-n', 'docker', 'run', '--label', 'com.qemu.instance.uuid=18e540c0fae14ac68e571023cc096e31', '-u', '1001', '--security-opt', 'seccomp=unconfined', '--rm', '-e', 'TARGET_LIST=x86_64-softmmu', '-e', 'EXTRA_CONFIGURE_OPTS=', '-e', 'V=', '-e', 'J=14', '-e', 'DEBUG=', '-e', 'SHOW_ENV=', '-e', 'CCACHE_DIR=/var/tmp/ccache', '-v', '/home/patchew/.cache/qemu-docker-ccache:/var/tmp/ccache:z', '-v', '/var/tmp/patchew-tester-tmp-92q_wrsw/src/docker-src.2020-05-24-17.15.58.27154:/var/tmp/qemu:z,ro', 'qemu:fedora', '/var/tmp/qemu/run', 'test-debug']' returned non-zero exit status 2.
filter=--filter=label=com.qemu.instance.uuid=18e540c0fae14ac68e571023cc096e31
make[1]: *** [docker-run] Error 1
make[1]: Leaving directory `/var/tmp/patchew-tester-tmp-92q_wrsw/src'
make: *** [docker-run-test-debug@fedora] Error 2

real    5m14.699s
user    0m8.970s


The full log is available at
http://patchew.org/logs/cover.1590344541.git.lukasstraub2@web.de/testing.asan/?type=message.
---
Email generated automatically by Patchew [https://patchew.org/].
Please send your feedback to patchew-devel@redhat.com