[Qemu-devel] [PULL for-1.6 0/6] Block patches

[Qemu-devel] [PULL for-1.6 0/6] Block patches

[Stefan Hajnoczi]

This pull request contains the final patches for QEMU 1.6.  They apply on top
of Kevin's pending block pull request from Friday.

Features:
 * Paolo/Bharata's gluster resize support
 * My virtio-blk-data-plane live migration support

Bug fixes:
 * Benoît's I/O throttling fix
 * My spice migration (also affects dataplane migration) and dataplane bdrv_in_use() fixes

The following changes since commit e3409362bd64731e042c9d001e43cc1d13d2df5d:

  Add tests for sync modes 'TOP' and 'NONE' (2013-07-26 22:01:31 +0200)

are available in the git repository at:

  git://github.com/stefanha/qemu.git block

for you to fetch changes up to b0f2027cde31c645524256763672e09eeb204a9a:

  dataplane: refuse to start if device is already in use (2013-07-29 17:19:15 +0200)

----------------------------------------------------------------
Benoît Canet (1):
      block: Repair the throttling code.

Paolo Bonzini (1):
      gluster: Add image resize support

Stefan Hajnoczi (4):
      migration: notify migration state before starting thread
      migration: fix spice migration
      dataplane: enable virtio-blk x-data-plane=on live migration
      dataplane: refuse to start if device is already in use

 block.c                         |  7 +++----
 block/gluster.c                 | 17 +++++++++++++++++
 hw/block/dataplane/virtio-blk.c | 17 ++++++++---------
 hw/block/virtio-blk.c           | 32 ++++++++++++++++++++++++++++++++
 include/block/coroutine.h       |  9 +++++++--
 include/hw/virtio/virtio-blk.h  |  1 +
 include/migration/migration.h   |  2 +-
 migration.c                     |  8 +++++---
 qemu-coroutine-lock.c           | 20 ++++++++++++++++++--
 ui/spice-core.c                 |  2 +-
 10 files changed, 93 insertions(+), 22 deletions(-)

-- 
1.8.1.4

[Qemu-devel] [PATCH 1/6] gluster: Add image resize support

[Stefan Hajnoczi]

From: Paolo Bonzini <pbonzini@redhat.com>

Implement .bdrv_truncate in GlusterFS block driver so that GlusterFS backend
can support image resizing.

Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Bharata B Rao <bharata@linux.vnet.ibm.com>
Tested-by: Bharata B Rao <bharata@linux.vnet.ibm.com>
Acked-by: Stefan Hajnoczi <stefanha@redhat.com>
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
---
 block/gluster.c | 17 +++++++++++++++++
 1 file changed, 17 insertions(+)

diff --git a/block/gluster.c b/block/gluster.c
index 6de418c..645b7f1 100644
--- a/block/gluster.c
+++ b/block/gluster.c
@@ -493,6 +493,19 @@ out:
     return NULL;
 }
 
+static int qemu_gluster_truncate(BlockDriverState *bs, int64_t offset)
+{
+    int ret;
+    BDRVGlusterState *s = bs->opaque;
+
+    ret = glfs_ftruncate(s->fd, offset);
+    if (ret < 0) {
+        return -errno;
+    }
+
+    return 0;
+}
+
 static BlockDriverAIOCB *qemu_gluster_aio_readv(BlockDriverState *bs,
         int64_t sector_num, QEMUIOVector *qiov, int nb_sectors,
         BlockDriverCompletionFunc *cb, void *opaque)
@@ -631,6 +644,7 @@ static BlockDriver bdrv_gluster = {
     .bdrv_create                  = qemu_gluster_create,
     .bdrv_getlength               = qemu_gluster_getlength,
     .bdrv_get_allocated_file_size = qemu_gluster_allocated_file_size,
+    .bdrv_truncate                = qemu_gluster_truncate,
     .bdrv_aio_readv               = qemu_gluster_aio_readv,
     .bdrv_aio_writev              = qemu_gluster_aio_writev,
     .bdrv_aio_flush               = qemu_gluster_aio_flush,
@@ -650,6 +664,7 @@ static BlockDriver bdrv_gluster_tcp = {
     .bdrv_create                  = qemu_gluster_create,
     .bdrv_getlength               = qemu_gluster_getlength,
     .bdrv_get_allocated_file_size = qemu_gluster_allocated_file_size,
+    .bdrv_truncate                = qemu_gluster_truncate,
     .bdrv_aio_readv               = qemu_gluster_aio_readv,
     .bdrv_aio_writev              = qemu_gluster_aio_writev,
     .bdrv_aio_flush               = qemu_gluster_aio_flush,
@@ -669,6 +684,7 @@ static BlockDriver bdrv_gluster_unix = {
     .bdrv_create                  = qemu_gluster_create,
     .bdrv_getlength               = qemu_gluster_getlength,
     .bdrv_get_allocated_file_size = qemu_gluster_allocated_file_size,
+    .bdrv_truncate                = qemu_gluster_truncate,
     .bdrv_aio_readv               = qemu_gluster_aio_readv,
     .bdrv_aio_writev              = qemu_gluster_aio_writev,
     .bdrv_aio_flush               = qemu_gluster_aio_flush,
@@ -688,6 +704,7 @@ static BlockDriver bdrv_gluster_rdma = {
     .bdrv_create                  = qemu_gluster_create,
     .bdrv_getlength               = qemu_gluster_getlength,
     .bdrv_get_allocated_file_size = qemu_gluster_allocated_file_size,
+    .bdrv_truncate                = qemu_gluster_truncate,
     .bdrv_aio_readv               = qemu_gluster_aio_readv,
     .bdrv_aio_writev              = qemu_gluster_aio_writev,
     .bdrv_aio_flush               = qemu_gluster_aio_flush,
-- 
1.8.1.4

[Qemu-devel] [PATCH 2/6] block: Repair the throttling code.

[Stefan Hajnoczi]

From: Benoît Canet <benoit@irqsave.net>

The throttling code was segfaulting since commit
02ffb504485f0920cfc75a0982a602f824a9a4f4 because some qemu_co_queue_next caller
does not run in a coroutine.
qemu_co_queue_do_restart assume that the caller is a coroutinne.
As suggested by Stefan fix this by entering the coroutine directly.
Also make sure like suggested that qemu_co_queue_next() and
qemu_co_queue_restart_all() can be called only in coroutines.

Signed-off-by: Benoit Canet <benoit@irqsave.net>
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
---
 block.c                   |  7 +++----
 include/block/coroutine.h |  9 +++++++--
 qemu-coroutine-lock.c     | 20 ++++++++++++++++++--
 3 files changed, 28 insertions(+), 8 deletions(-)

diff --git a/block.c b/block.c
index c77cfd1..01b66d8 100644
--- a/block.c
+++ b/block.c
@@ -127,7 +127,7 @@ void bdrv_io_limits_disable(BlockDriverState *bs)
 {
     bs->io_limits_enabled = false;
 
-    while (qemu_co_queue_next(&bs->throttled_reqs));
+    do {} while (qemu_co_enter_next(&bs->throttled_reqs));
 
     if (bs->block_timer) {
         qemu_del_timer(bs->block_timer);
@@ -143,7 +143,7 @@ static void bdrv_block_timer(void *opaque)
 {
     BlockDriverState *bs = opaque;
 
-    qemu_co_queue_next(&bs->throttled_reqs);
+    qemu_co_enter_next(&bs->throttled_reqs);
 }
 
 void bdrv_io_limits_enable(BlockDriverState *bs)
@@ -1452,8 +1452,7 @@ void bdrv_drain_all(void)
          * a busy wait.
          */
         QTAILQ_FOREACH(bs, &bdrv_states, list) {
-            if (!qemu_co_queue_empty(&bs->throttled_reqs)) {
-                qemu_co_queue_restart_all(&bs->throttled_reqs);
+            while (qemu_co_enter_next(&bs->throttled_reqs)) {
                 busy = true;
             }
         }
diff --git a/include/block/coroutine.h b/include/block/coroutine.h
index 377805a..1f2db3e 100644
--- a/include/block/coroutine.h
+++ b/include/block/coroutine.h
@@ -130,12 +130,17 @@ void coroutine_fn qemu_co_queue_wait_insert_head(CoQueue *queue);
  *
  * Returns true if a coroutine was restarted, false if the queue is empty.
  */
-bool qemu_co_queue_next(CoQueue *queue);
+bool coroutine_fn qemu_co_queue_next(CoQueue *queue);
 
 /**
  * Restarts all coroutines in the CoQueue and leaves the queue empty.
  */
-void qemu_co_queue_restart_all(CoQueue *queue);
+void coroutine_fn qemu_co_queue_restart_all(CoQueue *queue);
+
+/**
+ * Enter the next coroutine in the queue
+ */
+bool qemu_co_enter_next(CoQueue *queue);
 
 /**
  * Checks if the CoQueue is empty.
diff --git a/qemu-coroutine-lock.c b/qemu-coroutine-lock.c
index d9fea49..aeb33b9 100644
--- a/qemu-coroutine-lock.c
+++ b/qemu-coroutine-lock.c
@@ -88,16 +88,32 @@ static bool qemu_co_queue_do_restart(CoQueue *queue, bool single)
     return true;
 }
 
-bool qemu_co_queue_next(CoQueue *queue)
+bool coroutine_fn qemu_co_queue_next(CoQueue *queue)
 {
+    assert(qemu_in_coroutine());
     return qemu_co_queue_do_restart(queue, true);
 }
 
-void qemu_co_queue_restart_all(CoQueue *queue)
+void coroutine_fn qemu_co_queue_restart_all(CoQueue *queue)
 {
+    assert(qemu_in_coroutine());
     qemu_co_queue_do_restart(queue, false);
 }
 
+bool qemu_co_enter_next(CoQueue *queue)
+{
+    Coroutine *next;
+
+    next = QTAILQ_FIRST(&queue->entries);
+    if (!next) {
+        return false;
+    }
+
+    QTAILQ_REMOVE(&queue->entries, next, co_queue_next);
+    qemu_coroutine_enter(next, NULL);
+    return true;
+}
+
 bool qemu_co_queue_empty(CoQueue *queue)
 {
     return (QTAILQ_FIRST(&queue->entries) == NULL);
-- 
1.8.1.4

[Qemu-devel] [PATCH 3/6] migration: notify migration state before starting thread

[Stefan Hajnoczi]

The migration thread runs outside the QEMU global mutex when possible.
Therefore we must notify migration state change *before* starting the
migration thread.

This allows registered listeners to act before live migration iterations
begin.  Therefore they can get into a state that allows for live
migration.  When the migration thread starts everything will be ready.

Without this patch there is a race condition during migration setup,
depending on whether the migration thread has already transitioned from
SETUP to ACTIVE state.

Acked-by: Paolo Bonzini <pbonzini@redhat.com>
Reviewed-by: Kevin Wolf <kwolf@redhat.com>
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
---
 migration.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/migration.c b/migration.c
index e12e784..a5ed26b 100644
--- a/migration.c
+++ b/migration.c
@@ -658,7 +658,9 @@ void migrate_fd_connect(MigrationState *s)
     qemu_file_set_rate_limit(s->file,
                              s->bandwidth_limit / XFER_LIMIT_RATIO);
 
+    /* Notify before starting migration thread */
+    notifier_list_notify(&migration_state_notifiers, s);
+
     qemu_thread_create(&s->thread, migration_thread, s,
                        QEMU_THREAD_JOINABLE);
-    notifier_list_notify(&migration_state_notifiers, s);
 }
-- 
1.8.1.4

[Qemu-devel] [PATCH 4/6] migration: fix spice migration

[Stefan Hajnoczi]

Commit 29ae8a4133082e16970c9d4be09f4b6a15034617 ("rdma: introduce
MIG_STATE_NONE and change MIG_STATE_SETUP state transition") changed the
state transitions during migration setup.

Spice used to be notified with MIG_STATE_ACTIVE and it detected this
using migration_is_active().  Spice is now notified with
MIG_STATE_SETUP and migration_is_active() no longer works.

Replace migration_is_active() with migration_in_setup() to fix spice
migration.

Cc: Michael R. Hines <mrhines@us.ibm.com>
Reviewed-by: Kevin Wolf <kwolf@redhat.com>
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
---
 include/migration/migration.h | 2 +-
 migration.c                   | 4 ++--
 ui/spice-core.c               | 2 +-
 3 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/include/migration/migration.h b/include/migration/migration.h
index 08c772d..140e6b4 100644
--- a/include/migration/migration.h
+++ b/include/migration/migration.h
@@ -90,7 +90,7 @@ int migrate_fd_close(MigrationState *s);
 
 void add_migration_state_change_notifier(Notifier *notify);
 void remove_migration_state_change_notifier(Notifier *notify);
-bool migration_is_active(MigrationState *);
+bool migration_in_setup(MigrationState *);
 bool migration_has_finished(MigrationState *);
 bool migration_has_failed(MigrationState *);
 MigrationState *migrate_get_current(void);
diff --git a/migration.c b/migration.c
index a5ed26b..9fc7294 100644
--- a/migration.c
+++ b/migration.c
@@ -338,9 +338,9 @@ void remove_migration_state_change_notifier(Notifier *notify)
     notifier_remove(notify);
 }
 
-bool migration_is_active(MigrationState *s)
+bool migration_in_setup(MigrationState *s)
 {
-    return s->state == MIG_STATE_ACTIVE;
+    return s->state == MIG_STATE_SETUP;
 }
 
 bool migration_has_finished(MigrationState *s)
diff --git a/ui/spice-core.c b/ui/spice-core.c
index f308fd9..033fd89 100644
--- a/ui/spice-core.c
+++ b/ui/spice-core.c
@@ -563,7 +563,7 @@ static void migration_state_notifier(Notifier *notifier, void *data)
 {
     MigrationState *s = data;
 
-    if (migration_is_active(s)) {
+    if (migration_in_setup(s)) {
         spice_server_migrate_start(spice_server);
     } else if (migration_has_finished(s)) {
         spice_server_migrate_end(spice_server, true);
-- 
1.8.1.4

[Qemu-devel] [PATCH 5/6] dataplane: enable virtio-blk x-data-plane=on live migration

[Stefan Hajnoczi]

Although the dataplane thread does not cooperate with dirty memory
logging yet it's fairly easy to temporarily disable dataplane during
live migration.  This way virtio-blk can live migrate when
x-data-plane=on.

The dataplane thread will restart after migration is cancelled or if the
guest resuming virtio-blk operation after migration completes.

Reviewed-by: Kevin Wolf <kwolf@redhat.com>
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
---
 hw/block/dataplane/virtio-blk.c |  9 ---------
 hw/block/virtio-blk.c           | 32 ++++++++++++++++++++++++++++++++
 include/hw/virtio/virtio-blk.h  |  1 +
 3 files changed, 33 insertions(+), 9 deletions(-)

diff --git a/hw/block/dataplane/virtio-blk.c b/hw/block/dataplane/virtio-blk.c
index 2faed43..63c3ffa 100644
--- a/hw/block/dataplane/virtio-blk.c
+++ b/hw/block/dataplane/virtio-blk.c
@@ -18,7 +18,6 @@
 #include "qemu/error-report.h"
 #include "hw/virtio/dataplane/vring.h"
 #include "ioq.h"
-#include "migration/migration.h"
 #include "block/block.h"
 #include "hw/virtio/virtio-blk.h"
 #include "virtio-blk.h"
@@ -69,8 +68,6 @@ struct VirtIOBlockDataPlane {
                                              queue */
 
     unsigned int num_reqs;
-
-    Error *migration_blocker;
 };
 
 /* Raise an interrupt to signal guest, if necessary */
@@ -433,10 +430,6 @@ bool virtio_blk_data_plane_create(VirtIODevice *vdev, VirtIOBlkConf *blk,
     /* Prevent block operations that conflict with data plane thread */
     bdrv_set_in_use(blk->conf.bs, 1);
 
-    error_setg(&s->migration_blocker,
-            "x-data-plane does not support migration");
-    migrate_add_blocker(s->migration_blocker);
-
     *dataplane = s;
     return true;
 }
@@ -448,8 +441,6 @@ void virtio_blk_data_plane_destroy(VirtIOBlockDataPlane *s)
     }
 
     virtio_blk_data_plane_stop(s);
-    migrate_del_blocker(s->migration_blocker);
-    error_free(s->migration_blocker);
     bdrv_set_in_use(s->blk->conf.bs, 0);
     g_free(s);
 }
diff --git a/hw/block/virtio-blk.c b/hw/block/virtio-blk.c
index cf12469..1237b6a 100644
--- a/hw/block/virtio-blk.c
+++ b/hw/block/virtio-blk.c
@@ -19,6 +19,7 @@
 #include "hw/virtio/virtio-blk.h"
 #ifdef CONFIG_VIRTIO_BLK_DATA_PLANE
 # include "dataplane/virtio-blk.h"
+# include "migration/migration.h"
 #endif
 #include "block/scsi.h"
 #ifdef __linux__
@@ -628,6 +629,34 @@ void virtio_blk_set_conf(DeviceState *dev, VirtIOBlkConf *blk)
     memcpy(&(s->blk), blk, sizeof(struct VirtIOBlkConf));
 }
 
+#ifdef CONFIG_VIRTIO_BLK_DATA_PLANE
+/* Disable dataplane thread during live migration since it does not
+ * update the dirty memory bitmap yet.
+ */
+static void virtio_blk_migration_state_changed(Notifier *notifier, void *data)
+{
+    VirtIOBlock *s = container_of(notifier, VirtIOBlock,
+                                  migration_state_notifier);
+    MigrationState *mig = data;
+
+    if (migration_in_setup(mig)) {
+        if (!s->dataplane) {
+            return;
+        }
+        virtio_blk_data_plane_destroy(s->dataplane);
+        s->dataplane = NULL;
+    } else if (migration_has_finished(mig) ||
+               migration_has_failed(mig)) {
+        if (s->dataplane) {
+            return;
+        }
+        bdrv_drain_all(); /* complete in-flight non-dataplane requests */
+        virtio_blk_data_plane_create(VIRTIO_DEVICE(s), &s->blk,
+                                     &s->dataplane);
+    }
+}
+#endif /* CONFIG_VIRTIO_BLK_DATA_PLANE */
+
 static int virtio_blk_device_init(VirtIODevice *vdev)
 {
     DeviceState *qdev = DEVICE(vdev);
@@ -664,6 +693,8 @@ static int virtio_blk_device_init(VirtIODevice *vdev)
         virtio_cleanup(vdev);
         return -1;
     }
+    s->migration_state_notifier.notify = virtio_blk_migration_state_changed;
+    add_migration_state_change_notifier(&s->migration_state_notifier);
 #endif
 
     s->change = qemu_add_vm_change_state_handler(virtio_blk_dma_restart_cb, s);
@@ -683,6 +714,7 @@ static int virtio_blk_device_exit(DeviceState *dev)
     VirtIODevice *vdev = VIRTIO_DEVICE(dev);
     VirtIOBlock *s = VIRTIO_BLK(dev);
 #ifdef CONFIG_VIRTIO_BLK_DATA_PLANE
+    remove_migration_state_change_notifier(&s->migration_state_notifier);
     virtio_blk_data_plane_destroy(s->dataplane);
     s->dataplane = NULL;
 #endif
diff --git a/include/hw/virtio/virtio-blk.h b/include/hw/virtio/virtio-blk.h
index fc71853..b87cf49 100644
--- a/include/hw/virtio/virtio-blk.h
+++ b/include/hw/virtio/virtio-blk.h
@@ -125,6 +125,7 @@ typedef struct VirtIOBlock {
     unsigned short sector_mask;
     VMChangeStateEntry *change;
 #ifdef CONFIG_VIRTIO_BLK_DATA_PLANE
+    Notifier migration_state_notifier;
     struct VirtIOBlockDataPlane *dataplane;
 #endif
 } VirtIOBlock;
-- 
1.8.1.4

[Qemu-devel] [PATCH 6/6] dataplane: refuse to start if device is already in use

[Stefan Hajnoczi]

Dataplane must check whether a block device is in use before launching
the dataplane thread.  This is necessary since the thread does not
synchronize with the main loop and I/O requests could cause corruption.

One example is when a drive is added and a block job is started before
hotplugging the virtio-blk-pci adapter.  In this case we must not use
dataplane mode.

Cc: qemu-stable@nongnu.org
Reviewed-by: Kevin Wolf <kwolf@redhat.com>
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
---
 hw/block/dataplane/virtio-blk.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/hw/block/dataplane/virtio-blk.c b/hw/block/dataplane/virtio-blk.c
index 63c3ffa..411becc 100644
--- a/hw/block/dataplane/virtio-blk.c
+++ b/hw/block/dataplane/virtio-blk.c
@@ -415,6 +415,14 @@ bool virtio_blk_data_plane_create(VirtIODevice *vdev, VirtIOBlkConf *blk,
         return false;
     }
 
+    /* If dataplane is (re-)enabled while the guest is running there could be
+     * block jobs that can conflict.
+     */
+    if (bdrv_in_use(blk->conf.bs)) {
+        error_report("cannot start dataplane thread while device is in use");
+        return false;
+    }
+
     fd = raw_get_aio_fd(blk->conf.bs);
     if (fd < 0) {
         error_report("drive is incompatible with x-data-plane, "
-- 
1.8.1.4