Merge tag 'for-upstream' of https://repo.or.cz/qemu/kevin into staging

Block layer patches

- virtio-blk: use blk_io_plug_call() instead of notification BH
- mirror: allow switching from background to active mode
- qemu-img rebase: add compression support
- Fix locking in media change monitor commands
- Fix a few blockjob-related deadlocks when using iothread

# -----BEGIN PGP SIGNATURE-----
#
# iQJFBAABCAAvFiEE3D3rFZqa+V09dFb+fwmycsiPL9YFAmVBTkERHGt3b2xmQHJl
# ZGhhdC5jb20ACgkQfwmycsiPL9ZiqRAAqvsWbblmEGJ7TBKYQK3f8QshJ66RxzbC
# 4eSjKHrciWNTeeIeU8r8OvFcPPoTcPXxpcmasD2gsAxG5W5N8vkPbBkW+YT4YdDJ
# pWJXrbJ15nILC4DmnR1ARVtvxKgv9zy5LSm5bjss1K+OSYJl/nx+ILjmfVZnYDF7
# z1dP/G0JxKKm4JzAIdBE3uZS+6Q5kx/wGYlJv8EQmlH3DYfsJfy6Lthe9jfw8ijg
# lSqLoQ+D0lEd6Bk4XbkUqqBxFcYBWTfU6qPZoyIO94zCTwTG9yIjmoivxmmfwQZq
# cJUTGGZjcxpJYnvcC6P13WgcWBtcD9L2kYFVH0JyjpwcSg9cCGHMF66n9pSlyEGq
# DUikwVzbTwOotwzYQyM88v4ET+2+Qdcwn8pRbv9PllEczh0kAsUAEuxSgtz4NEcN
# bZrap/16xHFybNOKkMZcmpqxspT5NXKbDODUP0IvbSYMOYpWS983nBTxwMRpyHog
# 2TFDZu4DjNiPkI2BcYM5VOKk6diNowZFShcEKvoaOLX/n9EBhP0tjoH9VUn1800F
# myHrhF2jpIf9GhErMWB7N2W3/0aK0pqdQgbpVnd1ARDdIdYkr7G/S+50D9K80b6n
# 0q2E7br4S5bcsY0HQzBL9YARSayY+lVOssLoolCWEsYzijdBQmAvs5THajFKcism
# /idI6nlp2Vs=
# =RdxS
# -----END PGP SIGNATURE-----
# gpg: Signature made Wed 01 Nov 2023 03:58:09 JST
# gpg:                using RSA key DC3DEB159A9AF95D3D7456FE7F09B272C88F2FD6
# gpg:                issuer "kwolf@redhat.com"
# gpg: Good signature from "Kevin Wolf <kwolf@redhat.com>" [full]
# Primary key fingerprint: DC3D EB15 9A9A F95D 3D74  56FE 7F09 B272 C88F 2FD6

* tag 'for-upstream' of https://repo.or.cz/qemu/kevin: (27 commits)
  iotests: add test for changing mirror's copy_mode
  mirror: return mirror-specific information upon query
  blockjob: query driver-specific info via a new 'query' driver method
  qapi/block-core: turn BlockJobInfo into a union
  qapi/block-core: use JobType for BlockJobInfo's type
  mirror: implement mirror_change method
  block/mirror: determine copy_to_target only once
  block/mirror: move dirty bitmap to filter
  block/mirror: set actively_synced even after the job is ready
  blockjob: introduce block-job-change QMP command
  virtio-blk: remove batch notification BH
  virtio: use defer_call() in virtio_irqfd_notify()
  util/defer-call: move defer_call() to util/
  block: rename blk_io_plug_call() API to defer_call()
  blockdev: mirror: avoid potential deadlock when using iothread
  block: avoid potential deadlock during bdrv_graph_wrlock() in bdrv_close()
  blockjob: drop AioContext lock before calling bdrv_graph_wrlock()
  iotests: Test media change with iothreads
  block: Fix locking in media change monitor commands
  iotests: add tests for "qemu-img rebase" with compression
  ...

Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>

6 files changed, 27 insertions, 58 deletions

diff --git a/hw/block/dataplane/virtio-blk.c b/hw/block/dataplane/virtio-blk.c
index da36fcf..f83bb0f 100644
--- a/hw/block/dataplane/virtio-blk.c
+++ b/hw/block/dataplane/virtio-blk.c
@@ -31,9 +31,6 @@ struct VirtIOBlockDataPlane {
 
     VirtIOBlkConf *conf;
     VirtIODevice *vdev;
-    QEMUBH *bh;                     /* bh for guest notification */
-    unsigned long *batch_notify_vqs;
-    bool batch_notifications;
 
     /* Note that these EventNotifiers are assigned by value.  This is
      * fine as long as you do not call event_notifier_cleanup on them
@@ -47,36 +44,7 @@ struct VirtIOBlockDataPlane {
 /* Raise an interrupt to signal guest, if necessary */
 void virtio_blk_data_plane_notify(VirtIOBlockDataPlane *s, VirtQueue *vq)
 {
-    if (s->batch_notifications) {
-        set_bit(virtio_get_queue_index(vq), s->batch_notify_vqs);
-        qemu_bh_schedule(s->bh);
-    } else {
-        virtio_notify_irqfd(s->vdev, vq);
-    }
-}
-
-static void notify_guest_bh(void *opaque)
-{
-    VirtIOBlockDataPlane *s = opaque;
-    unsigned nvqs = s->conf->num_queues;
-    unsigned long bitmap[BITS_TO_LONGS(nvqs)];
-    unsigned j;
-
-    memcpy(bitmap, s->batch_notify_vqs, sizeof(bitmap));
-    memset(s->batch_notify_vqs, 0, sizeof(bitmap));
-
-    for (j = 0; j < nvqs; j += BITS_PER_LONG) {
-        unsigned long bits = bitmap[j / BITS_PER_LONG];
-
-        while (bits != 0) {
-            unsigned i = j + ctzl(bits);
-            VirtQueue *vq = virtio_get_queue(s->vdev, i);
-
-            virtio_notify_irqfd(s->vdev, vq);
-
-            bits &= bits - 1; /* clear right-most bit */
-        }
-    }
+    virtio_notify_irqfd(s->vdev, vq);
 }
 
 /* Context: QEMU global mutex held */
@@ -126,9 +94,6 @@ bool virtio_blk_data_plane_create(VirtIODevice *vdev, VirtIOBlkConf *conf,
     } else {
         s->ctx = qemu_get_aio_context();
     }
-    s->bh = aio_bh_new_guarded(s->ctx, notify_guest_bh, s,
-                               &DEVICE(vdev)->mem_reentrancy_guard);
-    s->batch_notify_vqs = bitmap_new(conf->num_queues);
 
     *dataplane = s;
 
@@ -146,8 +111,6 @@ void virtio_blk_data_plane_destroy(VirtIOBlockDataPlane *s)
 
     vblk = VIRTIO_BLK(s->vdev);
     assert(!vblk->dataplane_started);
-    g_free(s->batch_notify_vqs);
-    qemu_bh_delete(s->bh);
     if (s->iothread) {
         object_unref(OBJECT(s->iothread));
     }
@@ -173,12 +136,6 @@ int virtio_blk_data_plane_start(VirtIODevice *vdev)
 
     s->starting = true;
 
-    if (!virtio_vdev_has_feature(vdev, VIRTIO_RING_F_EVENT_IDX)) {
-        s->batch_notifications = true;
-    } else {
-        s->batch_notifications = false;
-    }
-
     /* Set up guest notifier (irq) */
     r = k->set_guest_notifiers(qbus->parent, nvqs, true);
     if (r != 0) {
@@ -370,9 +327,6 @@ void virtio_blk_data_plane_stop(VirtIODevice *vdev)
 
     aio_context_release(s->ctx);
 
-    qemu_bh_cancel(s->bh);
-    notify_guest_bh(s); /* final chance to notify guest */
-
     /* Clean up guest notifier (irq) */
     k->set_guest_notifiers(qbus->parent, nvqs, false);
 
diff --git a/hw/block/dataplane/xen-block.c b/hw/block/dataplane/xen-block.c
index 3b6f2b0..c4bb28c 100644
--- a/hw/block/dataplane/xen-block.c
+++ b/hw/block/dataplane/xen-block.c
@@ -19,6 +19,7 @@
  */
 
 #include "qemu/osdep.h"
+#include "qemu/defer-call.h"
 #include "qemu/error-report.h"
 #include "qemu/main-loop.h"
 #include "qemu/memalign.h"
@@ -509,7 +510,7 @@ static int xen_block_get_request(XenBlockDataPlane *dataplane,
 
 /*
  * Threshold of in-flight requests above which we will start using
- * blk_io_plug()/blk_io_unplug() to batch requests.
+ * defer_call_begin()/defer_call_end() to batch requests.
  */
 #define IO_PLUG_THRESHOLD 1
 
@@ -537,7 +538,7 @@ static bool xen_block_handle_requests(XenBlockDataPlane *dataplane)
      * is below us.
      */
     if (inflight_atstart > IO_PLUG_THRESHOLD) {
-        blk_io_plug();
+        defer_call_begin();
     }
     while (rc != rp) {
         /* pull request from ring */
@@ -577,12 +578,12 @@ static bool xen_block_handle_requests(XenBlockDataPlane *dataplane)
 
         if (inflight_atstart > IO_PLUG_THRESHOLD &&
             batched >= inflight_atstart) {
-            blk_io_unplug();
+            defer_call_end();
         }
         xen_block_do_aio(request);
         if (inflight_atstart > IO_PLUG_THRESHOLD) {
             if (batched >= inflight_atstart) {
-                blk_io_plug();
+                defer_call_begin();
                 batched = 0;
             } else {
                 batched++;
@@ -590,7 +591,7 @@ static bool xen_block_handle_requests(XenBlockDataPlane *dataplane)
         }
     }
     if (inflight_atstart > IO_PLUG_THRESHOLD) {
-        blk_io_unplug();
+        defer_call_end();
     }
 
     return done_something;
diff --git a/hw/block/virtio-blk.c b/hw/block/virtio-blk.c
index 39e7f23..a1f8e15 100644
--- a/hw/block/virtio-blk.c
+++ b/hw/block/virtio-blk.c
@@ -12,6 +12,7 @@
  */
 
 #include "qemu/osdep.h"
+#include "qemu/defer-call.h"
 #include "qapi/error.h"
 #include "qemu/iov.h"
 #include "qemu/module.h"
@@ -1134,7 +1135,7 @@ void virtio_blk_handle_vq(VirtIOBlock *s, VirtQueue *vq)
     bool suppress_notifications = virtio_queue_get_notification(vq);
 
     aio_context_acquire(blk_get_aio_context(s->blk));
-    blk_io_plug();
+    defer_call_begin();
 
     do {
         if (suppress_notifications) {
@@ -1158,7 +1159,7 @@ void virtio_blk_handle_vq(VirtIOBlock *s, VirtQueue *vq)
         virtio_blk_submit_multireq(s, &mrb);
     }
 
-    blk_io_unplug();
+    defer_call_end();
     aio_context_release(blk_get_aio_context(s->blk));
 }
 
diff --git a/hw/scsi/virtio-scsi.c b/hw/scsi/virtio-scsi.c
index fa53f09..9c751bf 100644
--- a/hw/scsi/virtio-scsi.c
+++ b/hw/scsi/virtio-scsi.c
@@ -18,6 +18,7 @@
 #include "standard-headers/linux/virtio_ids.h"
 #include "hw/virtio/virtio-scsi.h"
 #include "migration/qemu-file-types.h"
+#include "qemu/defer-call.h"
 #include "qemu/error-report.h"
 #include "qemu/iov.h"
 #include "qemu/module.h"
@@ -799,7 +800,7 @@ static int virtio_scsi_handle_cmd_req_prepare(VirtIOSCSI *s, VirtIOSCSIReq *req)
         return -ENOBUFS;
     }
     scsi_req_ref(req->sreq);
-    blk_io_plug();
+    defer_call_begin();
     object_unref(OBJECT(d));
     return 0;
 }
@@ -810,7 +811,7 @@ static void virtio_scsi_handle_cmd_req_submit(VirtIOSCSI *s, VirtIOSCSIReq *req)
     if (scsi_req_enqueue(sreq)) {
         scsi_req_continue(sreq);
     }
-    blk_io_unplug();
+    defer_call_end();
     scsi_req_unref(sreq);
 }
 
@@ -836,7 +837,7 @@ static void virtio_scsi_handle_cmd_vq(VirtIOSCSI *s, VirtQueue *vq)
                 while (!QTAILQ_EMPTY(&reqs)) {
                     req = QTAILQ_FIRST(&reqs);
                     QTAILQ_REMOVE(&reqs, req, next);
-                    blk_io_unplug();
+                    defer_call_end();
                     scsi_req_unref(req->sreq);
                     virtqueue_detach_element(req->vq, &req->elem, 0);
                     virtio_scsi_free_req(req);
diff --git a/hw/virtio/trace-events b/hw/virtio/trace-events
index 1cb9027..0af7a28 100644
--- a/hw/virtio/trace-events
+++ b/hw/virtio/trace-events
@@ -73,6 +73,7 @@ virtqueue_fill(void *vq, const void *elem, unsigned int len, unsigned int idx) "
 virtqueue_flush(void *vq, unsigned int count) "vq %p count %u"
 virtqueue_pop(void *vq, void *elem, unsigned int in_num, unsigned int out_num) "vq %p elem %p in_num %u out_num %u"
 virtio_queue_notify(void *vdev, int n, void *vq) "vdev %p n %d vq %p"
+virtio_notify_irqfd_deferred_fn(void *vdev, void *vq) "vdev %p vq %p"
 virtio_notify_irqfd(void *vdev, void *vq) "vdev %p vq %p"
 virtio_notify(void *vdev, void *vq) "vdev %p vq %p"
 virtio_set_status(void *vdev, uint8_t val) "vdev %p val %u"
diff --git a/hw/virtio/virtio.c b/hw/virtio/virtio.c
index fb24bc9..e510557 100644
--- a/hw/virtio/virtio.c
+++ b/hw/virtio/virtio.c
@@ -15,6 +15,7 @@
 #include "qapi/error.h"
 #include "qapi/qapi-commands-virtio.h"
 #include "trace.h"
+#include "qemu/defer-call.h"
 #include "qemu/error-report.h"
 #include "qemu/log.h"
 #include "qemu/main-loop.h"
@@ -2445,6 +2446,16 @@ static bool virtio_should_notify(VirtIODevice *vdev, VirtQueue *vq)
     }
 }
 
+/* Batch irqs while inside a defer_call_begin()/defer_call_end() section */
+static void virtio_notify_irqfd_deferred_fn(void *opaque)
+{
+    EventNotifier *notifier = opaque;
+    VirtQueue *vq = container_of(notifier, VirtQueue, guest_notifier);
+
+    trace_virtio_notify_irqfd_deferred_fn(vq->vdev, vq);
+    event_notifier_set(notifier);
+}
+
 void virtio_notify_irqfd(VirtIODevice *vdev, VirtQueue *vq)
 {
     WITH_RCU_READ_LOCK_GUARD() {
@@ -2471,7 +2482,7 @@ void virtio_notify_irqfd(VirtIODevice *vdev, VirtQueue *vq)
      * to an atomic operation.
      */
     virtio_set_isr(vq->vdev, 0x1);
-    event_notifier_set(&vq->guest_notifier);
+    defer_call(virtio_notify_irqfd_deferred_fn, &vq->guest_notifier);
 }
 
 static void virtio_irq(VirtQueue *vq)