Merge remote-tracking branch 'remotes/ericb/tags/pull-nbd-2021-01-20' into staging

nbd patches for 2021-01-20

- minor resource leak fixes in qemu-nbd
- ensure proper aio context when nbd server uses iothreads
- iotest refactorings in preparation for rewriting ./check to be more
flexible, and preparing for more nbd server reconnect features

# gpg: Signature made Thu 21 Jan 2021 02:28:19 GMT
# gpg:                using RSA key 71C2CC22B1C4602927D2F3AAA7A16B4A2527436A
# gpg: Good signature from "Eric Blake <eblake@redhat.com>" [full]
# gpg:                 aka "Eric Blake (Free Software Programmer) <ebb9@byu.net>" [full]
# gpg:                 aka "[jpeg image of size 6874]" [full]
# Primary key fingerprint: 71C2 CC22 B1C4 6029 27D2  F3AA A7A1 6B4A 2527 436A

* remotes/ericb/tags/pull-nbd-2021-01-20:
  iotests.py: qemu_io(): reuse qemu_tool_pipe_and_status()
  iotests.py: fix qemu_tool_pipe_and_status()
  iotests/264: fix style
  iotests: define group in each iotest
  iotests/294: add shebang line
  iotests: make tests executable
  iotests: fix some whitespaces in test output files
  iotests/303: use dot slash for qcow2.py running
  iotests/277: use dot slash for nbd-fault-injector.py running
  nbd/server: Quiesce coroutines on context switch
  block: Honor blk_set_aio_context() context requirements
  qemu-nbd: Fix a memleak in nbd_client_thread()
  qemu-nbd: Fix a memleak in qemu_nbd_client_list()

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>

hw/block/dataplane/virtio-blk.c

@@ -172,6 +172,7 @@ int virtio_blk_data_plane_start(VirtIODevice *vdev)
     VirtIOBlockDataPlane *s = vblk->dataplane;
     BusState *qbus = BUS(qdev_get_parent_bus(DEVICE(vblk)));
     VirtioBusClass *k = VIRTIO_BUS_GET_CLASS(qbus);
+    AioContext *old_context;
     unsigned i;
     unsigned nvqs = s->conf->num_queues;
     Error *local_err = NULL;
@@ -214,7 +215,10 @@ int virtio_blk_data_plane_start(VirtIODevice *vdev)
     vblk->dataplane_started = true;
     trace_virtio_blk_data_plane_start(s);
 
+    old_context = blk_get_aio_context(s->conf->conf.blk);
+    aio_context_acquire(old_context);
     r = blk_set_aio_context(s->conf->conf.blk, s->ctx, &local_err);
+    aio_context_release(old_context);
     if (r < 0) {
         error_report_err(local_err);
         goto fail_guest_notifiers;

hw/block/dataplane/xen-block.c

@@ -725,6 +725,7 @@ void xen_block_dataplane_start(XenBlockDataPlane *dataplane,
 {
     ERRP_GUARD();
     XenDevice *xendev = dataplane->xendev;
+    AioContext *old_context;
     unsigned int ring_size;
     unsigned int i;
 
@@ -808,10 +809,14 @@ void xen_block_dataplane_start(XenBlockDataPlane *dataplane,
         goto stop;
     }
 
-    aio_context_acquire(dataplane->ctx);
+    old_context = blk_get_aio_context(dataplane->blk);
+    aio_context_acquire(old_context);
     /* If other users keep the BlockBackend in the iothread, that's ok */
     blk_set_aio_context(dataplane->blk, dataplane->ctx, NULL);
+    aio_context_release(old_context);
+
     /* Only reason for failure is a NULL channel */
+    aio_context_acquire(dataplane->ctx);
     xen_device_set_event_channel_context(xendev, dataplane->event_channel,
                                          dataplane->ctx, &error_abort);
     aio_context_release(dataplane->ctx);

hw/scsi/virtio-scsi.c

@@ -849,15 +849,17 @@ static void virtio_scsi_hotplug(HotplugHandler *hotplug_dev, DeviceState *dev,
     VirtIODevice *vdev = VIRTIO_DEVICE(hotplug_dev);
     VirtIOSCSI *s = VIRTIO_SCSI(vdev);
     SCSIDevice *sd = SCSI_DEVICE(dev);
+    AioContext *old_context;
     int ret;
 
     if (s->ctx && !s->dataplane_fenced) {
         if (blk_op_is_blocked(sd->conf.blk, BLOCK_OP_TYPE_DATAPLANE, errp)) {
             return;
         }
-        virtio_scsi_acquire(s);
+        old_context = blk_get_aio_context(sd->conf.blk);
+        aio_context_acquire(old_context);
         ret = blk_set_aio_context(sd->conf.blk, s->ctx, errp);
-        virtio_scsi_release(s);
+        aio_context_release(old_context);
         if (ret < 0) {
             return;
         }

nbd/server.c

@@ -132,6 +132,9 @@ struct NBDClient {
     CoMutex send_lock;
     Coroutine *send_coroutine;
 
+    bool read_yielding;
+    bool quiescing;
+
     QTAILQ_ENTRY(NBDClient) next;
     int nb_requests;
     bool closing;
@@ -1352,14 +1355,60 @@ static coroutine_fn int nbd_negotiate(NBDClient *client, Error **errp)
     return 0;
 }
 
-static int nbd_receive_request(QIOChannel *ioc, NBDRequest *request,
+/* nbd_read_eof
+ * Tries to read @size bytes from @ioc. This is a local implementation of
+ * qio_channel_readv_all_eof. We have it here because we need it to be
+ * interruptible and to know when the coroutine is yielding.
+ * Returns 1 on success
+ *         0 on eof, when no data was read (errp is not set)
+ *         negative errno on failure (errp is set)
+ */
+static inline int coroutine_fn
+nbd_read_eof(NBDClient *client, void *buffer, size_t size, Error **errp)
+{
+    bool partial = false;
+
+    assert(size);
+    while (size > 0) {
+        struct iovec iov = { .iov_base = buffer, .iov_len = size };
+        ssize_t len;
+
+        len = qio_channel_readv(client->ioc, &iov, 1, errp);
+        if (len == QIO_CHANNEL_ERR_BLOCK) {
+            client->read_yielding = true;
+            qio_channel_yield(client->ioc, G_IO_IN);
+            client->read_yielding = false;
+            if (client->quiescing) {
+                return -EAGAIN;
+            }
+            continue;
+        } else if (len < 0) {
+            return -EIO;
+        } else if (len == 0) {
+            if (partial) {
+                error_setg(errp,
+                           "Unexpected end-of-file before all bytes were read");
+                return -EIO;
+            } else {
+                return 0;
+            }
+        }
+
+        partial = true;
+        size -= len;
+        buffer = (uint8_t *) buffer + len;
+    }
+    return 1;
+}
+
+static int nbd_receive_request(NBDClient *client, NBDRequest *request,
                                Error **errp)
 {
     uint8_t buf[NBD_REQUEST_SIZE];
     uint32_t magic;
     int ret;
 
-    ret = nbd_read(ioc, buf, sizeof(buf), "request", errp);
+    ret = nbd_read_eof(client, buf, sizeof(buf), errp);
     if (ret < 0) {
         return ret;
     }
@@ -1480,11 +1529,37 @@ static void blk_aio_attached(AioContext *ctx, void *opaque)
 
     QTAILQ_FOREACH(client, &exp->clients, next) {
         qio_channel_attach_aio_context(client->ioc, ctx);
-        if (client->recv_coroutine) {
-            aio_co_schedule(ctx, client->recv_coroutine);
+
+        assert(client->recv_coroutine == NULL);
+        assert(client->send_coroutine == NULL);
+
+        if (client->quiescing) {
+            client->quiescing = false;
+            nbd_client_receive_next_request(client);
         }
+    }
+}
+
+static void nbd_aio_detach_bh(void *opaque)
+{
+    NBDExport *exp = opaque;
+    NBDClient *client;
+
+    QTAILQ_FOREACH(client, &exp->clients, next) {
+        qio_channel_detach_aio_context(client->ioc);
+        client->quiescing = true;
+
+        if (client->recv_coroutine) {
+            if (client->read_yielding) {
+                qemu_aio_coroutine_enter(exp->common.ctx,
+                                         client->recv_coroutine);
+            } else {
+                AIO_WAIT_WHILE(exp->common.ctx, client->recv_coroutine != NULL);
+            }
+        }
+
         if (client->send_coroutine) {
-            aio_co_schedule(ctx, client->send_coroutine);
+            AIO_WAIT_WHILE(exp->common.ctx, client->send_coroutine != NULL);
         }
     }
 }
@@ -1492,13 +1567,10 @@ static void blk_aio_attached(AioContext *ctx, void *opaque)
 static void blk_aio_detach(void *opaque)
 {
     NBDExport *exp = opaque;
-    NBDClient *client;
 
     trace_nbd_blk_aio_detach(exp->name, exp->common.ctx);
 
-    QTAILQ_FOREACH(client, &exp->clients, next) {
-        qio_channel_detach_aio_context(client->ioc);
-    }
+    aio_wait_bh_oneshot(exp->common.ctx, nbd_aio_detach_bh, exp);
 
     exp->common.ctx = NULL;
 }
@@ -2151,20 +2223,23 @@ static int nbd_co_send_bitmap(NBDClient *client, uint64_t handle,
 
 /* nbd_co_receive_request
  * Collect a client request. Return 0 if request looks valid, -EIO to drop
- * connection right away, and any other negative value to report an error to
- * the client (although the caller may still need to disconnect after reporting
- * the error).
+ * connection right away, -EAGAIN to indicate we were interrupted and the
+ * channel should be quiesced, and any other negative value to report an error
+ * to the client (although the caller may still need to disconnect after
+ * reporting the error).
  */
 static int nbd_co_receive_request(NBDRequestData *req, NBDRequest *request,
                                   Error **errp)
 {
     NBDClient *client = req->client;
     int valid_flags;
+    int ret;
 
     g_assert(qemu_in_coroutine());
     assert(client->recv_coroutine == qemu_coroutine_self());
-    if (nbd_receive_request(client->ioc, request, errp) < 0) {
-        return -EIO;
+    ret = nbd_receive_request(client, request, errp);
+    if (ret < 0) {
+        return  ret;
     }
 
     trace_nbd_co_receive_request_decode_type(request->handle, request->type,
@@ -2507,6 +2582,17 @@ static coroutine_fn void nbd_trip(void *opaque)
         return;
     }
 
+    if (client->quiescing) {
+        /*
+         * We're switching between AIO contexts. Don't attempt to receive a new
+         * request and kick the main context which may be waiting for us.
+         */
+        nbd_client_put(client);
+        client->recv_coroutine = NULL;
+        aio_wait_kick();
+        return;
+    }
+
     req = nbd_request_get(client);
     ret = nbd_co_receive_request(req, &request, &local_err);
     client->recv_coroutine = NULL;
@@ -2519,6 +2605,11 @@ static coroutine_fn void nbd_trip(void *opaque)
         goto done;
     }
 
+    if (ret == -EAGAIN) {
+        assert(client->quiescing);
+        goto done;
+    }
+
     nbd_client_receive_next_request(client);
     if (ret == -EIO) {
         goto disconnect;
@@ -2565,7 +2656,8 @@ disconnect:
 
 static void nbd_client_receive_next_request(NBDClient *client)
 {
-    if (!client->recv_coroutine && client->nb_requests < MAX_NBD_REQUESTS) {
+    if (!client->recv_coroutine && client->nb_requests < MAX_NBD_REQUESTS &&
+        !client->quiescing) {
         nbd_client_get(client);
         client->recv_coroutine = qemu_coroutine_create(nbd_trip, client);
         aio_co_schedule(client->exp->common.ctx, client->recv_coroutine);

qemu-nbd.c

@@ -181,7 +181,7 @@ static int qemu_nbd_client_list(SocketAddress *saddr, QCryptoTLSCreds *tls,
     sioc = qio_channel_socket_new();
     if (qio_channel_socket_connect_sync(sioc, saddr, &err) < 0) {
         error_report_err(err);
-        return EXIT_FAILURE;
+        goto out;
     }
     rc = nbd_receive_export_list(QIO_CHANNEL(sioc), tls, hostname, &list,
                                  &err);
@@ -265,8 +265,8 @@ static void *nbd_client_thread(void *arg)
     char *device = arg;
     NBDExportInfo info = { .request_sizes = false, .name = g_strdup("") };
     QIOChannelSocket *sioc;
-    int fd;
-    int ret;
+    int fd = -1;
+    int ret = EXIT_FAILURE;
     pthread_t show_parts_thread;
     Error *local_error = NULL;
 
@@ -278,26 +278,24 @@ static void *nbd_client_thread(void *arg)
         goto out;
     }
 
-    ret = nbd_receive_negotiate(NULL, QIO_CHANNEL(sioc),
-                                NULL, NULL, NULL, &info, &local_error);
-    if (ret < 0) {
+    if (nbd_receive_negotiate(NULL, QIO_CHANNEL(sioc),
+                              NULL, NULL, NULL, &info, &local_error) < 0) {
         if (local_error) {
             error_report_err(local_error);
         }
-        goto out_socket;
+        goto out;
     }
 
     fd = open(device, O_RDWR);
     if (fd < 0) {
         /* Linux-only, we can use %m in printf.  */
         error_report("Failed to open %s: %m", device);
-        goto out_socket;
+        goto out;
     }
 
-    ret = nbd_init(fd, sioc, &info, &local_error);
-    if (ret < 0) {
+    if (nbd_init(fd, sioc, &info, &local_error) < 0) {
         error_report_err(local_error);
-        goto out_fd;
+        goto out;
     }
 
     /* update partition table */
@@ -311,24 +309,20 @@ static void *nbd_client_thread(void *arg)
         dup2(STDOUT_FILENO, STDERR_FILENO);
     }
 
-    ret = nbd_client(fd);
-    if (ret) {
-        goto out_fd;
+    if (nbd_client(fd) < 0) {
+        goto out;
     }
-    close(fd);
-    object_unref(OBJECT(sioc));
-    g_free(info.name);
-    kill(getpid(), SIGTERM);
-    return (void *) EXIT_SUCCESS;
 
-out_fd:
-    close(fd);
-out_socket:
+    ret = EXIT_SUCCESS;
+
+ out:
+    if (fd >= 0) {
+        close(fd);
+    }
     object_unref(OBJECT(sioc));
-out:
     g_free(info.name);
     kill(getpid(), SIGTERM);
-    return (void *) EXIT_FAILURE;
+    return (void *) (intptr_t) ret;
 }
 #endif /* HAVE_NBD_DEVICE */
 

tests/qemu-iotests/001

@@ -1,4 +1,5 @@
 #!/usr/bin/env bash
+# group: rw auto quick
 #
 # Test simple read/write using plain bdrv_pread/bdrv_pwrite
 #

tests/qemu-iotests/002

@@ -1,4 +1,5 @@
 #!/usr/bin/env bash
+# group: rw auto quick
 #
 # Test simple read/write using plain bdrv_pread/bdrv_pwrite
 #

tests/qemu-iotests/003

@@ -1,4 +1,5 @@
 #!/usr/bin/env bash
+# group: rw auto
 #
 # Test simple read/write using bdrv_aio_readv/bdrv_aio_writev
 #

tests/qemu-iotests/004

@@ -1,4 +1,5 @@
 #!/usr/bin/env bash
+# group: rw auto quick
 #
 # Make sure we can't read and write outside of the image size.
 #

tests/qemu-iotests/005

@@ -1,4 +1,5 @@
 #!/usr/bin/env bash
+# group: img auto quick
 #
 # Make sure qemu-img can create 5TB images
 #

tests/qemu-iotests/007

@@ -1,4 +1,5 @@
 #!/usr/bin/env bash
+# group: snapshot auto
 #
 # Check for one possible case of qcow2 refcount corruption.
 #

tests/qemu-iotests/008

@@ -1,4 +1,5 @@
 #!/usr/bin/env bash
+# group: rw auto quick
 #
 # Test simple asynchronous read/write operations.
 #

tests/qemu-iotests/009

@@ -1,4 +1,5 @@
 #!/usr/bin/env bash
+# group: rw auto quick
 #
 # Nolan I qcow2 corruption - incorrectly reports free clusters
 #

tests/qemu-iotests/010

@@ -1,4 +1,5 @@
 #!/usr/bin/env bash
+# group: rw auto quick
 #
 # Nolan II qcow2 corruption - wrong used cluster
 #

tests/qemu-iotests/011

@@ -1,4 +1,5 @@
 #!/usr/bin/env bash
+# group: rw auto quick
 #
 # Test for AIO allocation on the same cluster
 #

tests/qemu-iotests/012

@@ -1,4 +1,5 @@
 #!/usr/bin/env bash
+# group: auto quick
 #
 # Make sure we can open read-only images
 #

tests/qemu-iotests/013

@@ -1,4 +1,5 @@
 #!/usr/bin/env bash
+# group: rw auto
 #
 # qcow2 pattern test, empty and compressed image - 4k cluster patterns
 #

tests/qemu-iotests/014

@@ -1,4 +1,5 @@
 #!/usr/bin/env bash
+# group: rw
 #
 # qcow2 pattern test, complex patterns including compression and snapshots
 # Using patterns for 4k cluster size.

tests/qemu-iotests/015

@@ -1,4 +1,5 @@
 #!/usr/bin/env bash
+# group: rw snapshot
 #
 # Combined test to grow the refcount table and test snapshots.
 #

tests/qemu-iotests/017

@@ -1,4 +1,5 @@
 #!/usr/bin/env bash
+# group: rw backing auto quick
 #
 # Simple backing file reads
 #