[PATCH v10 1/8] Introduce yank feature

* [PATCH v10 1/8] Introduce yank feature
       [not found] <cover.1604075469.git.lukasstraub2@web.de>
@ 2020-10-30 16:41 ` Lukas Straub
  2020-11-02  6:32   ` Markus Armbruster
  2020-10-30 16:41 ` [PATCH v10 2/8] block/nbd.c: Add " Lukas Straub
                   ` (6 subsequent siblings)
  7 siblings, 1 reply; 12+ messages in thread
From: Lukas Straub @ 2020-10-30 16:41 UTC (permalink / raw)
  To: qemu-devel
  Cc: Kevin Wolf, Daniel P. Berrangé,
	qemu-block, Juan Quintela, Markus Armbruster,
	Dr. David Alan Gilbert, Max Reitz, Paolo Bonzini,
	Marc-André Lureau

[-- Attachment #1: Type: text/plain, Size: 13827 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>
Acked-by: Stefan Hajnoczi <stefanha@redhat.com>
---
 include/qemu/yank.h   |  95 +++++++++++++++++++
 qapi/meson.build      |   1 +
 qapi/qapi-schema.json |   1 +
 qapi/yank.json        | 115 ++++++++++++++++++++++
 util/meson.build      |   1 +
 util/yank.c           | 216 ++++++++++++++++++++++++++++++++++++++++++
 6 files changed, 429 insertions(+)
 create mode 100644 include/qemu/yank.h
 create mode 100644 qapi/yank.json
 create mode 100644 util/yank.c

diff --git a/include/qemu/yank.h b/include/qemu/yank.h
new file mode 100644
index 0000000000..96f5b2626f
--- /dev/null
+++ b/include/qemu/yank.h
@@ -0,0 +1,95 @@
+/*
+ * 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.
+ */
+
+#ifndef YANK_H
+#define YANK_H
+
+#include "qapi/qapi-types-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: The instance.
+ * @errp: Error object.
+ */
+void yank_register_instance(const YankInstance *instance, Error **errp);
+
+/**
+ * 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: The instance.
+ */
+void yank_unregister_instance(const YankInstance *instance);
+
+/**
+ * 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. See docs/devel/qapi-code-gen.txt under
+ * "An OOB-capable command handler must satisfy the following conditions".
+ *
+ * This function is thread-safe.
+ *
+ * @instance: The instance.
+ * @func: The yank function.
+ * @opaque: Will be passed to the yank function.
+ */
+void yank_register_function(const YankInstance *instance,
+                            YankFn *func,
+                            void *opaque);
+
+/**
+ * yank_unregister_function: Unregister a yank function
+ *
+ * This unregisters a yank function.
+ *
+ * This function is thread-safe.
+ *
+ * @instance: The instance.
+ * @func: func that was passed to yank_register_function.
+ * @opaque: opaque that was passed to yank_register_function.
+ */
+void yank_unregister_function(const YankInstance *instance,
+                              YankFn *func,
+                              void *opaque);
+
+/**
+ * yank_generic_iochannel: 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);
+
+#define BLOCKDEV_YANK_INSTANCE(the_node_name) (&(YankInstance) { \
+        .type = YANK_INSTANCE_TYPE_BLOCK_NODE, \
+        .u.block_node.node_name = (the_node_name) })
+
+#define CHARDEV_YANK_INSTANCE(the_id) (&(YankInstance) { \
+        .type = YANK_INSTANCE_TYPE_CHARDEV, \
+        .u.chardev.id = (the_id) })
+
+#define MIGRATION_YANK_INSTANCE (&(YankInstance) { \
+        .type = YANK_INSTANCE_TYPE_MIGRATION })
+
+#endif
diff --git a/qapi/meson.build b/qapi/meson.build
index 0e98146f1f..ab68e7900e 100644
--- a/qapi/meson.build
+++ b/qapi/meson.build
@@ -47,6 +47,7 @@ qapi_all_modules = [
   'trace',
   'transaction',
   'ui',
+  'yank',
 ]

 qapi_storage_daemon_modules = [
diff --git a/qapi/qapi-schema.json b/qapi/qapi-schema.json
index 0b444b76d2..79c1705ed7 100644
--- a/qapi/qapi-schema.json
+++ b/qapi/qapi-schema.json
@@ -91,3 +91,4 @@
 { 'include': 'audio.json' }
 { 'include': 'acpi.json' }
 { 'include': 'pci.json' }
+{ 'include': 'yank.json' }
diff --git a/qapi/yank.json b/qapi/yank.json
new file mode 100644
index 0000000000..1964a2202e
--- /dev/null
+++ b/qapi/yank.json
@@ -0,0 +1,115 @@
+# -*- Mode: Python -*-
+# vim: filetype=python
+#
+
+##
+# @YankInstanceType:
+#
+# An enumeration of yank instance types. See @YankInstance for more
+# information.
+#
+# Since: 5.2
+##
+{ 'enum': 'YankInstanceType',
+  'data': [ 'block-node', 'chardev', 'migration' ] }
+
+##
+# @YankInstanceBlockNode:
+#
+# Specifies which block graph node to yank. See @YankInstance for more
+# information.
+#
+# @node-name: the name of the block graph node
+#
+# Since: 5.2
+##
+{ 'struct': 'YankInstanceBlockNode',
+  'data': { 'node-name': 'str' } }
+
+##
+# @YankInstanceChardev:
+#
+# Specifies which character device to yank. See @YankInstance for more
+# information.
+#
+# @id: the chardev's ID
+#
+# Since: 5.2
+##
+{ 'struct': 'YankInstanceChardev',
+  'data': { 'id': 'str' } }
+
+##
+# @YankInstance:
+#
+# A yank instance can be yanked with the @yank qmp command to recover from a
+# hanging QEMU.
+#
+# Currently implemented yank instances:
+#  - nbd block device:
+#    Yanking it will shut down the connection to the nbd server without
+#    attempting to reconnect.
+#  - socket chardev:
+#    Yanking it will shut down the connected socket.
+#  - migration:
+#    Yanking it will shut down all migration connections. Unlike
+#    @migrate_cancel, it will not notify the migration process, so migration
+#    will go into @failed state, instead of @cancelled state. @yank should be
+#    used to recover from hangs.
+#
+# Since: 5.2
+##
+{ 'union': 'YankInstance',
+  'base': { 'type': 'YankInstanceType' },
+  'discriminator': 'type',
+  'data': {
+      'block-node': 'YankInstanceBlockNode',
+      'chardev': 'YankInstanceChardev' } }
+
+##
+# @yank:
+#
+# Try to recover from hanging QEMU by yanking the specified instances. See
+# @YankInstance for more information.
+#
+# Takes a list of @YankInstance as argument.
+#
+# Returns: - Nothing on success
+#          - @DeviceNotFound error, if any of the YankInstances doesn't exist
+#
+# Example:
+#
+# -> { "execute": "yank",
+#      "arguments": {
+#          "instances": [
+#               { "type": "block-node",
+#                 "node-name": "nbd0" }
+#          ] } }
+# <- { "return": {} }
+#
+# Since: 5.2
+##
+{ 'command': 'yank',
+  'data': { 'instances': ['YankInstance'] },
+  'allow-oob': true }
+
+##
+# @query-yank:
+#
+# Query yank instances. See @YankInstance for more information.
+#
+# Returns: list of @YankInstance
+#
+# Example:
+#
+# -> { "execute": "query-yank" }
+# <- { "return": [
+#          { "type": "block-node",
+#            "node-name": "nbd0" }
+#      ] }
+#
+# Since: 5.2
+##
+{ 'command': 'query-yank',
+  'returns': ['YankInstance'],
+  'allow-oob': true }
diff --git a/util/meson.build b/util/meson.build
index c5159ad79d..dbda9d9123 100644
--- a/util/meson.build
+++ b/util/meson.build
@@ -50,6 +50,7 @@ endif

 if have_system
   util_ss.add(when: 'CONFIG_GIO', if_true: [files('dbus.c'), gio])
+  util_ss.add(files('yank.c'))
 endif

 if have_block
diff --git a/util/yank.c b/util/yank.c
new file mode 100644
index 0000000000..4a0f538359
--- /dev/null
+++ b/util/yank.c
@@ -0,0 +1,216 @@
+/*
+ * 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-yank.h"
+#include "qapi/qapi-visit-yank.h"
+#include "qapi/clone-visitor.h"
+#include "io/channel.h"
+#include "qemu/yank.h"
+
+struct YankFuncAndParam {
+    YankFn *func;
+    void *opaque;
+    QLIST_ENTRY(YankFuncAndParam) next;
+};
+
+struct YankInstanceEntry {
+    YankInstance *instance;
+    QLIST_HEAD(, YankFuncAndParam) yankfns;
+    QLIST_ENTRY(YankInstanceEntry) next;
+};
+
+typedef struct YankFuncAndParam YankFuncAndParam;
+typedef struct YankInstanceEntry YankInstanceEntry;
+
+/*
+ * This lock protects the yank_instance_list below. Because it's taken by
+ * OOB-capable commands, it must be "fast", i.e. it may only be held for a
+ * bounded, short time. See docs/devel/qapi-code-gen.txt for additional
+ * information.
+ */
+static QemuMutex yank_lock;
+
+static QLIST_HEAD(, YankInstanceEntry) yank_instance_list
+    = QLIST_HEAD_INITIALIZER(yank_instance_list);
+
+static bool yank_compare_instances(const YankInstance *a, const YankInstance *b)
+{
+    if (a->type != b->type) {
+        return false;
+    }
+
+    switch (a->type) {
+    case YANK_INSTANCE_TYPE_BLOCK_NODE:
+        return !strcmp(a->u.block_node.node_name, b->u.block_node.node_name);
+    break;
+
+    case YANK_INSTANCE_TYPE_CHARDEV:
+        return !strcmp(a->u.chardev.id, b->u.chardev.id);
+    break;
+
+    case YANK_INSTANCE_TYPE_MIGRATION:
+        return true;
+    break;
+
+    default:
+        abort();
+    }
+}
+
+static YankInstanceEntry *yank_find_entry(const YankInstance *instance)
+{
+    YankInstanceEntry *entry;
+
+    QLIST_FOREACH(entry, &yank_instance_list, next) {
+        if (yank_compare_instances(entry->instance, instance)) {
+            return entry;
+        }
+    }
+    return NULL;
+}
+
+void yank_register_instance(const YankInstance *instance, Error **errp)
+{
+    YankInstanceEntry *entry;
+
+    qemu_mutex_lock(&yank_lock);
+
+    if (yank_find_entry(instance)) {
+        error_setg(errp, "duplicate yank instance");
+        qemu_mutex_unlock(&yank_lock);
+        return;
+    }
+
+    entry = g_slice_new(YankInstanceEntry);
+    entry->instance = QAPI_CLONE(YankInstance, instance);
+    QLIST_INIT(&entry->yankfns);
+    QLIST_INSERT_HEAD(&yank_instance_list, entry, next);
+
+    qemu_mutex_unlock(&yank_lock);
+}
+
+void yank_unregister_instance(const YankInstance *instance)
+{
+    YankInstanceEntry *entry;
+
+    qemu_mutex_lock(&yank_lock);
+    entry = yank_find_entry(instance);
+    assert(entry);
+
+    assert(QLIST_EMPTY(&entry->yankfns));
+    QLIST_REMOVE(entry, next);
+    qapi_free_YankInstance(entry->instance);
+    g_slice_free(YankInstanceEntry, entry);
+
+    qemu_mutex_unlock(&yank_lock);
+}
+
+void yank_register_function(const YankInstance *instance,
+                            YankFn *func,
+                            void *opaque)
+{
+    YankInstanceEntry *entry;
+    YankFuncAndParam *func_entry;
+
+    qemu_mutex_lock(&yank_lock);
+    entry = yank_find_entry(instance);
+    assert(entry);
+
+    func_entry = g_slice_new(YankFuncAndParam);
+    func_entry->func = func;
+    func_entry->opaque = opaque;
+
+    QLIST_INSERT_HEAD(&entry->yankfns, func_entry, next);
+    qemu_mutex_unlock(&yank_lock);
+}
+
+void yank_unregister_function(const YankInstance *instance,
+                              YankFn *func,
+                              void *opaque)
+{
+    YankInstanceEntry *entry;
+    YankFuncAndParam *func_entry;
+
+    qemu_mutex_lock(&yank_lock);
+    entry = yank_find_entry(instance);
+    assert(entry);
+
+    QLIST_FOREACH(func_entry, &entry->yankfns, next) {
+        if (func_entry->func == func && func_entry->opaque == opaque) {
+            QLIST_REMOVE(func_entry, next);
+            g_slice_free(YankFuncAndParam, func_entry);
+            qemu_mutex_unlock(&yank_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(YankInstanceList *instances,
+              Error **errp)
+{
+    YankInstanceList *tail;
+    YankInstanceEntry *entry;
+    YankFuncAndParam *func_entry;
+
+    qemu_mutex_lock(&yank_lock);
+    for (tail = instances; tail; tail = tail->next) {
+        entry = yank_find_entry(tail->value);
+        if (!entry) {
+            error_set(errp, ERROR_CLASS_DEVICE_NOT_FOUND, "Instance not found");
+            qemu_mutex_unlock(&yank_lock);
+            return;
+        }
+    }
+    for (tail = instances; tail; tail = tail->next) {
+        entry = yank_find_entry(tail->value);
+        assert(entry);
+        QLIST_FOREACH(func_entry, &entry->yankfns, next) {
+            func_entry->func(func_entry->opaque);
+        }
+    }
+    qemu_mutex_unlock(&yank_lock);
+}
+
+YankInstanceList *qmp_query_yank(Error **errp)
+{
+    YankInstanceEntry *entry;
+    YankInstanceList *ret;
+
+    ret = NULL;
+
+    qemu_mutex_lock(&yank_lock);
+    QLIST_FOREACH(entry, &yank_instance_list, next) {
+        YankInstanceList *new_entry;
+        new_entry = g_new0(YankInstanceList, 1);
+        new_entry->value = QAPI_CLONE(YankInstance, entry->instance);
+        new_entry->next = ret;
+        ret = new_entry;
+    }
+    qemu_mutex_unlock(&yank_lock);
+
+    return ret;
+}
+
+static void __attribute__((__constructor__)) yank_init(void)
+{
+    qemu_mutex_init(&yank_lock);
+}
--
2.20.1


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

^ permalink raw reply related	[flat|nested] 12+ messages in thread