Series comparison

-[Qemu-devel] [PULL 0/1] Block patches
+[PULL 0/1] Block patches
-The following changes since commit b33afc415622e5eb26e0f14fd27eb86e32a5472e:
+The following changes since commit 887cba855bb6ff4775256f7968409281350b568c:
-  Merge remote-tracking branch 'remotes/stsquad/tags/pull-ci-updates-for-softfreeze-021117-2' into staging (2017-11-03 10:08:34 +0000)
+  configure: Fix cross-building for RISCV host (v5) (2023-07-11 17:56:09 +0100)
-are available in the git repository at:
+are available in the Git repository at:
-  git://github.com/stefanha/qemu.git tags/block-pull-request
+  https://gitlab.com/stefanha/qemu.git tags/block-pull-request
-for you to fetch changes up to ef9115dd7c82a196b18cac46784724bdebf01fbc:
+for you to fetch changes up to 75dcb4d790bbe5327169fd72b185960ca58e2fa6:
-  aio-posix: drop QEMU_AIO_POLL_MAX_NS env var (2017-11-06 11:04:38 +0000)
+  virtio-blk: fix host notifier issues during dataplane start/stop (2023-07-12 15:20:32 -0400)
 ----------------------------------------------------------------
+Pull request
 ----------------------------------------------------------------
 Stefan Hajnoczi (1):
-  aio-posix: drop QEMU_AIO_POLL_MAX_NS env var
+  virtio-blk: fix host notifier issues during dataplane start/stop
- util/aio-posix.c | 7 -------
+ hw/block/dataplane/virtio-blk.c | 67 +++++++++++++++++++--------------
-file changed, 7 deletions(-)
+file changed, 38 insertions(+), 29 deletions(-)
 --
-.13.6
+.40.1

-[Qemu-devel] [PULL 1/1] aio-posix: drop QEMU_AIO_POLL_MAX_NS env var
+[PULL 1/1] virtio-blk: fix host notifier issues during dataplane start/stop
-This hunk should not have been merged but I forgot to remove it.  Let's
+The main loop thread can consume 100% CPU when using --device
-remove it before it slips into a QEMU release.
+virtio-blk-pci,iothread=<iothread>. ppoll() constantly returns but
 reading virtqueue host notifiers fails with EAGAIN. The file descriptors
 are stale and remain registered with the AioContext because of bugs in
 the virtio-blk dataplane start/stop code.
-¯\_(ツ)_/¯
+The problem is that the dataplane start/stop code involves drain
 operations, which call virtio_blk_drained_begin() and
 virtio_blk_drained_end() at points where the host notifier is not
 operational:
 - In virtio_blk_data_plane_start(), blk_set_aio_context() drains after
   vblk->dataplane_started has been set to true but the host notifier has
   not been attached yet.
 - In virtio_blk_data_plane_stop(), blk_drain() and blk_set_aio_context()
   drain after the host notifier has already been detached but with
   vblk->dataplane_started still set to true.
-Reviewed-by: Thomas Huth <thuth@redhat.com>
+I would like to simplify ->ioeventfd_start/stop() to avoid interactions
 with drain entirely, but couldn't find a way to do that. Instead, this
 patch accepts the fragile nature of the code and reorders it so that
 vblk->dataplane_started is false during drain operations. This way the
 virtio_blk_drained_begin() and virtio_blk_drained_end() calls don't
 touch the host notifier. The result is that
 virtio_blk_data_plane_start() and virtio_blk_data_plane_stop() have
 complete control over the host notifier and stale file descriptors are
 no longer left in the AioContext.
 This patch fixes the 100% CPU consumption in the main loop thread and
 correctly moves host notifier processing to the IOThread.
 Fixes: 1665d9326fd2 ("virtio-blk: implement BlockDevOps->drained_begin()")
 Reported-by: Lukáš Doktor <ldoktor@redhat.com>
 Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
-Message-id: 20171103154041.12617-1-stefanha@redhat.com
+Tested-by: Lukas Doktor <ldoktor@redhat.com>
 Message-id: 20230704151527.193586-1-stefanha@redhat.com
 Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
 ---
- util/aio-posix.c | 7 -------
+ hw/block/dataplane/virtio-blk.c | 67 +++++++++++++++++++--------------
-file changed, 7 deletions(-)
+file changed, 38 insertions(+), 29 deletions(-)
-diff --git a/util/aio-posix.c b/util/aio-posix.c
+diff --git a/hw/block/dataplane/virtio-blk.c b/hw/block/dataplane/virtio-blk.c
 index XXXXXXX..XXXXXXX 100644
---- a/util/aio-posix.c
+--- a/hw/block/dataplane/virtio-blk.c
-+++ b/util/aio-posix.c
++++ b/hw/block/dataplane/virtio-blk.c
-@@ -XXX,XX +XXX,XX @@ bool aio_poll(AioContext *ctx, bool blocking)
+@@ -XXX,XX +XXX,XX @@ int virtio_blk_data_plane_start(VirtIODevice *vdev)
- void aio_context_setup(AioContext *ctx)
+     memory_region_transaction_commit();
- {
--    /* TODO remove this in final patch submission */
+-    /*
--    if (getenv("QEMU_AIO_POLL_MAX_NS")) {
+-     * These fields are visible to the IOThread so we rely on implicit barriers
--        fprintf(stderr, "The QEMU_AIO_POLL_MAX_NS environment variable has "
+-     * in aio_context_acquire() on the write side and aio_notify_accept() on
--                "been replaced with -object iothread,poll-max-ns=NUM\n");
+-     * the read side.
--        exit(1);
+-     */
 -    s->starting = false;
 -    vblk->dataplane_started = true;
      trace_virtio_blk_data_plane_start(s);
      old_context = blk_get_aio_context(s->conf->conf.blk);
@@ -XXX,XX +XXX,XX @@ int virtio_blk_data_plane_start(VirtIODevice *vdev)
          event_notifier_set(virtio_queue_get_host_notifier(vq));
      }
 +    /*
 +     * These fields must be visible to the IOThread when it processes the
 +     * virtqueue, otherwise it will think dataplane has not started yet.
 +     *
 +     * Make sure ->dataplane_started is false when blk_set_aio_context() is
 +     * called above so that draining does not cause the host notifier to be
 +     * detached/attached prematurely.
 +     */
 +    s->starting = false;
 +    vblk->dataplane_started = true;
 +    smp_wmb(); /* paired with aio_notify_accept() on the read side */
 +
      /* Get this show started by hooking up our callbacks */
      if (!blk_in_drain(s->conf->conf.blk)) {
          aio_context_acquire(s->ctx);
@@ -XXX,XX +XXX,XX @@ int virtio_blk_data_plane_start(VirtIODevice *vdev)
    fail_guest_notifiers:
      vblk->dataplane_disabled = true;
      s->starting = false;
 -    vblk->dataplane_started = true;
      return -ENOSYS;
  }
@@ -XXX,XX +XXX,XX @@ void virtio_blk_data_plane_stop(VirtIODevice *vdev)
          aio_wait_bh_oneshot(s->ctx, virtio_blk_data_plane_stop_bh, s);
      }
 +    /*
 +     * Batch all the host notifiers in a single transaction to avoid
 +     * quadratic time complexity in address_space_update_ioeventfds().
 +     */
 +    memory_region_transaction_begin();
 +
 +    for (i = 0; i < nvqs; i++) {
 +        virtio_bus_set_host_notifier(VIRTIO_BUS(qbus), i, false);
 +    }
 +
 +    /*
 +     * The transaction expects the ioeventfds to be open when it
 +     * commits. Do it now, before the cleanup loop.
 +     */
 +    memory_region_transaction_commit();
 +
 +    for (i = 0; i < nvqs; i++) {
 +        virtio_bus_cleanup_host_notifier(VIRTIO_BUS(qbus), i);
 +    }
 +
 +    /*
 +     * Set ->dataplane_started to false before draining so that host notifiers
 +     * are not detached/attached anymore.
 +     */
 +    vblk->dataplane_started = false;
 +
      aio_context_acquire(s->ctx);
      /* Wait for virtio_blk_dma_restart_bh() and in flight I/O to complete */
@@ -XXX,XX +XXX,XX @@ void virtio_blk_data_plane_stop(VirtIODevice *vdev)
      aio_context_release(s->ctx);
 -    /*
 -     * Batch all the host notifiers in a single transaction to avoid
 -     * quadratic time complexity in address_space_update_ioeventfds().
 -     */
 -    memory_region_transaction_begin();
 -
 -    for (i = 0; i < nvqs; i++) {
 -        virtio_bus_set_host_notifier(VIRTIO_BUS(qbus), i, false);
 -    }
 -
- #ifdef CONFIG_EPOLL_CREATE1
+-    /*
-     assert(!ctx->epollfd);
+-     * The transaction expects the ioeventfds to be open when it
-     ctx->epollfd = epoll_create1(EPOLL_CLOEXEC);
+-     * commits. Do it now, before the cleanup loop.
 -     */
 -    memory_region_transaction_commit();
 -
 -    for (i = 0; i < nvqs; i++) {
 -        virtio_bus_cleanup_host_notifier(VIRTIO_BUS(qbus), i);
 -    }
 -
      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);
 -    vblk->dataplane_started = false;
      s->stopping = false;
  }
 --
-.13.6
+.40.1

This hunk should not have been merged but I forgot to remove it.  Let's
remove it before it slips into a QEMU release.

¯\_(ツ)_/¯

Reviewed-by: Thomas Huth <thuth@redhat.com>
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
Message-id: 20171103154041.12617-1-stefanha@redhat.com
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
---
 util/aio-posix.c | 7 -------
 1 file changed, 7 deletions(-)

diff --git a/util/aio-posix.c b/util/aio-posix.c
index XXXXXXX..XXXXXXX 100644
--- a/util/aio-posix.c
+++ b/util/aio-posix.c
@@ -XXX,XX +XXX,XX @@ bool aio_poll(AioContext *ctx, bool blocking)
 
 void aio_context_setup(AioContext *ctx)
 {
-    /* TODO remove this in final patch submission */
-    if (getenv("QEMU_AIO_POLL_MAX_NS")) {
-        fprintf(stderr, "The QEMU_AIO_POLL_MAX_NS environment variable has "
-                "been replaced with -object iothread,poll-max-ns=NUM\n");
-        exit(1);
-    }
-
 #ifdef CONFIG_EPOLL_CREATE1
     assert(!ctx->epollfd);
     ctx->epollfd = epoll_create1(EPOLL_CLOEXEC);
-- 
2.13.6

The main loop thread can consume 100% CPU when using --device
virtio-blk-pci,iothread=<iothread>. ppoll() constantly returns but
reading virtqueue host notifiers fails with EAGAIN. The file descriptors
are stale and remain registered with the AioContext because of bugs in
the virtio-blk dataplane start/stop code.

The problem is that the dataplane start/stop code involves drain
operations, which call virtio_blk_drained_begin() and
virtio_blk_drained_end() at points where the host notifier is not
operational:
- In virtio_blk_data_plane_start(), blk_set_aio_context() drains after
  vblk->dataplane_started has been set to true but the host notifier has
  not been attached yet.
- In virtio_blk_data_plane_stop(), blk_drain() and blk_set_aio_context()
  drain after the host notifier has already been detached but with
  vblk->dataplane_started still set to true.

I would like to simplify ->ioeventfd_start/stop() to avoid interactions
with drain entirely, but couldn't find a way to do that. Instead, this
patch accepts the fragile nature of the code and reorders it so that
vblk->dataplane_started is false during drain operations. This way the
virtio_blk_drained_begin() and virtio_blk_drained_end() calls don't
touch the host notifier. The result is that
virtio_blk_data_plane_start() and virtio_blk_data_plane_stop() have
complete control over the host notifier and stale file descriptors are
no longer left in the AioContext.

This patch fixes the 100% CPU consumption in the main loop thread and
correctly moves host notifier processing to the IOThread.

Fixes: 1665d9326fd2 ("virtio-blk: implement BlockDevOps->drained_begin()")
Reported-by: Lukáš Doktor <ldoktor@redhat.com>
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
Tested-by: Lukas Doktor <ldoktor@redhat.com>
Message-id: 20230704151527.193586-1-stefanha@redhat.com
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
---
 hw/block/dataplane/virtio-blk.c | 67 +++++++++++++++++++--------------
 1 file changed, 38 insertions(+), 29 deletions(-)

diff --git a/hw/block/dataplane/virtio-blk.c b/hw/block/dataplane/virtio-blk.c
index XXXXXXX..XXXXXXX 100644
--- a/hw/block/dataplane/virtio-blk.c
+++ b/hw/block/dataplane/virtio-blk.c
@@ -XXX,XX +XXX,XX @@ int virtio_blk_data_plane_start(VirtIODevice *vdev)
 
     memory_region_transaction_commit();
 
-    /*
-     * These fields are visible to the IOThread so we rely on implicit barriers
-     * in aio_context_acquire() on the write side and aio_notify_accept() on
-     * the read side.
-     */
-    s->starting = false;
-    vblk->dataplane_started = true;
     trace_virtio_blk_data_plane_start(s);
 
     old_context = blk_get_aio_context(s->conf->conf.blk);
@@ -XXX,XX +XXX,XX @@ int virtio_blk_data_plane_start(VirtIODevice *vdev)
         event_notifier_set(virtio_queue_get_host_notifier(vq));
     }
 
+    /*
+     * These fields must be visible to the IOThread when it processes the
+     * virtqueue, otherwise it will think dataplane has not started yet.
+     *
+     * Make sure ->dataplane_started is false when blk_set_aio_context() is
+     * called above so that draining does not cause the host notifier to be
+     * detached/attached prematurely.
+     */
+    s->starting = false;
+    vblk->dataplane_started = true;
+    smp_wmb(); /* paired with aio_notify_accept() on the read side */
+
     /* Get this show started by hooking up our callbacks */
     if (!blk_in_drain(s->conf->conf.blk)) {
         aio_context_acquire(s->ctx);
@@ -XXX,XX +XXX,XX @@ int virtio_blk_data_plane_start(VirtIODevice *vdev)
   fail_guest_notifiers:
     vblk->dataplane_disabled = true;
     s->starting = false;
-    vblk->dataplane_started = true;
     return -ENOSYS;
 }
 
@@ -XXX,XX +XXX,XX @@ void virtio_blk_data_plane_stop(VirtIODevice *vdev)
         aio_wait_bh_oneshot(s->ctx, virtio_blk_data_plane_stop_bh, s);
     }
 
+    /*
+     * Batch all the host notifiers in a single transaction to avoid
+     * quadratic time complexity in address_space_update_ioeventfds().
+     */
+    memory_region_transaction_begin();
+
+    for (i = 0; i < nvqs; i++) {
+        virtio_bus_set_host_notifier(VIRTIO_BUS(qbus), i, false);
+    }
+
+    /*
+     * The transaction expects the ioeventfds to be open when it
+     * commits. Do it now, before the cleanup loop.
+     */
+    memory_region_transaction_commit();
+
+    for (i = 0; i < nvqs; i++) {
+        virtio_bus_cleanup_host_notifier(VIRTIO_BUS(qbus), i);
+    }
+
+    /*
+     * Set ->dataplane_started to false before draining so that host notifiers
+     * are not detached/attached anymore.
+     */
+    vblk->dataplane_started = false;
+
     aio_context_acquire(s->ctx);
 
     /* Wait for virtio_blk_dma_restart_bh() and in flight I/O to complete */
@@ -XXX,XX +XXX,XX @@ void virtio_blk_data_plane_stop(VirtIODevice *vdev)
 
     aio_context_release(s->ctx);
 
-    /*
-     * Batch all the host notifiers in a single transaction to avoid
-     * quadratic time complexity in address_space_update_ioeventfds().
-     */
-    memory_region_transaction_begin();
-
-    for (i = 0; i < nvqs; i++) {
-        virtio_bus_set_host_notifier(VIRTIO_BUS(qbus), i, false);
-    }
-
-    /*
-     * The transaction expects the ioeventfds to be open when it
-     * commits. Do it now, before the cleanup loop.
-     */
-    memory_region_transaction_commit();
-
-    for (i = 0; i < nvqs; i++) {
-        virtio_bus_cleanup_host_notifier(VIRTIO_BUS(qbus), i);
-    }
-
     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);
 
-    vblk->dataplane_started = false;
     s->stopping = false;
 }
-- 
2.40.1