[PATCH 03/17] async: rework async event API for replay

Nicholas Piggin posted 17 patches 3 days, 13 hours ago
[PATCH 03/17] async: rework async event API for replay
Posted by Nicholas Piggin 3 days, 13 hours ago
Replace the functions replay_bh_schedule_event() and
replay_bh_schedule_oneshot_event() with qemu_bh_schedule_event() and
aio_bh_schedule_oneshot_event(), respectively.

Direct API conversions use QEMU_CLOCK_VIRTUAL, because the virtual
clocks then go via the replay path when replay is enabled.

Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
 docs/devel/replay.rst   |  7 ++++---
 include/block/aio.h     | 35 +++++++++++++++++++++++++++++++----
 include/sysemu/replay.h |  2 +-
 backends/rng-builtin.c  |  2 +-
 block/block-backend.c   | 24 ++++++++++++++----------
 block/io.c              |  5 +++--
 block/iscsi.c           |  5 +++--
 block/nfs.c             | 10 ++++++----
 block/null.c            |  4 ++--
 block/nvme.c            |  8 +++++---
 hw/ide/core.c           |  7 ++++---
 hw/net/virtio-net.c     | 14 +++++++-------
 replay/replay-events.c  |  2 +-
 stubs/replay-tools.c    |  2 +-
 util/async.c            | 39 +++++++++++++++++++++++++++++++++++++--
 15 files changed, 120 insertions(+), 46 deletions(-)

diff --git a/docs/devel/replay.rst b/docs/devel/replay.rst
index 40f58d9d4fc..ca816d87587 100644
--- a/docs/devel/replay.rst
+++ b/docs/devel/replay.rst
@@ -171,9 +171,10 @@ Bottom halves
 -------------
 
 Bottom half callbacks, that affect the guest state, should be invoked through
-``replay_bh_schedule_event`` or ``replay_bh_schedule_oneshot_event`` functions.
-Their invocations are saved in record mode and synchronized with the existing
-log in replay mode.
+``qemu_bh_schedule_event`` or ``aio_bh_schedule_oneshot_event`` functions
+the with the appropriate clock type (e.g., QEMU_CLOCK_VIRTUAL. Their
+invocations are saved in record mode and synchronized with the existing log in
+replay mode.
 
 Disk I/O events are completely deterministic in our model, because
 in both record and replay modes we start virtual machine from the same
diff --git a/include/block/aio.h b/include/block/aio.h
index 43883a8a33a..bc323b0d936 100644
--- a/include/block/aio.h
+++ b/include/block/aio.h
@@ -286,17 +286,30 @@ void aio_context_unref(AioContext *ctx);
  * @name: A human-readable identifier for debugging purposes.
  */
 void aio_bh_schedule_oneshot_full(AioContext *ctx, QEMUBHFunc *cb, void *opaque,
-                                  const char *name);
+                                  const char *name, QEMUClockType clock_type);
 
 /**
- * aio_bh_schedule_oneshot: Allocate a new bottom half structure that will run
- * only once and as soon as possible.
+ * aio_bh_schedule_oneshot_event: Allocate a new bottom half structure that
+ * will run only once and as soon as possible.
  *
  * A convenience wrapper for aio_bh_schedule_oneshot_full() that uses cb as the
  * name string.
  */
+#define aio_bh_schedule_oneshot_event(ctx, cb, opaque, clock_type) \
+    aio_bh_schedule_oneshot_full((ctx), (cb), (opaque), (stringify(cb)), \
+                                 clock_type)
+
+/**
+ * aio_bh_schedule_oneshot: Allocate a new bottom half structure that will run
+ * only once and as soon as possible.
+ *
+ * A legacy wrapper for aio_bh_schedule_oneshot_event() that uses realtime
+ * as the clock type. Callers should specify the clock time in order to be
+ * compatible with record/replay.
+ */
 #define aio_bh_schedule_oneshot(ctx, cb, opaque) \
-    aio_bh_schedule_oneshot_full((ctx), (cb), (opaque), (stringify(cb)))
+    aio_bh_schedule_oneshot_full((ctx), (cb), (opaque), (stringify(cb)), \
+                                 QEMU_CLOCK_REALTIME)
 
 /**
  * aio_bh_new_full: Allocate a new bottom half structure.
@@ -378,6 +391,20 @@ void aio_bh_call(QEMUBH *bh);
  */
 int aio_bh_poll(AioContext *ctx);
 
+/**
+ * qemu_bh_schedule_event: Schedule a bottom half.
+ *
+ * Scheduling a bottom half interrupts the main loop and causes the
+ * execution of the callback that was passed to qemu_bh_new.
+ *
+ * Bottom halves that are scheduled from a bottom half handler are instantly
+ * invoked.  This can create an infinite loop if a bottom half handler
+ * schedules itself.
+ *
+ * @bh: The bottom half to be scheduled.
+ */
+void qemu_bh_schedule_event(QEMUBH *bh, QEMUClockType clock_type);
+
 /**
  * qemu_bh_schedule: Schedule a bottom half.
  *
diff --git a/include/sysemu/replay.h b/include/sysemu/replay.h
index cba74fa9bce..30a7ae47518 100644
--- a/include/sysemu/replay.h
+++ b/include/sysemu/replay.h
@@ -126,7 +126,7 @@ void replay_flush_events(void);
 /*! Adds bottom half event to the queue */
 void replay_bh_schedule_event(QEMUBH *bh);
 /* Adds oneshot bottom half event to the queue */
-void replay_bh_schedule_oneshot_event(AioContext *ctx,
+void replay_bh_oneshot_event(AioContext *ctx,
     QEMUBHFunc *cb, void *opaque);
 /*! Adds input event to the queue */
 void replay_input_event(QemuConsole *src, InputEvent *evt);
diff --git a/backends/rng-builtin.c b/backends/rng-builtin.c
index f367eb665cf..eef5c61f4f5 100644
--- a/backends/rng-builtin.c
+++ b/backends/rng-builtin.c
@@ -38,7 +38,7 @@ static void rng_builtin_request_entropy(RngBackend *b, RngRequest *req)
 {
     RngBuiltin *s = RNG_BUILTIN(b);
 
-    replay_bh_schedule_event(s->bh);
+    qemu_bh_schedule_event(s->bh, QEMU_CLOCK_VIRTUAL);
 }
 
 static void rng_builtin_init(Object *obj)
diff --git a/block/block-backend.c b/block/block-backend.c
index 85bcdedcef6..2168729340d 100644
--- a/block/block-backend.c
+++ b/block/block-backend.c
@@ -1530,8 +1530,8 @@ BlockAIOCB *blk_abort_aio_request(BlockBackend *blk,
     acb->blk = blk;
     acb->ret = ret;
 
-    replay_bh_schedule_oneshot_event(qemu_get_current_aio_context(),
-                                     error_callback_bh, acb);
+    aio_bh_schedule_oneshot_event(qemu_get_current_aio_context(),
+                                  error_callback_bh, acb, QEMU_CLOCK_VIRTUAL);
     return &acb->common;
 }
 
@@ -1588,8 +1588,9 @@ static BlockAIOCB *blk_aio_prwv(BlockBackend *blk, int64_t offset,
 
     acb->has_returned = true;
     if (acb->rwco.ret != NOT_DONE) {
-        replay_bh_schedule_oneshot_event(qemu_get_current_aio_context(),
-                                         blk_aio_complete_bh, acb);
+        aio_bh_schedule_oneshot_event(qemu_get_current_aio_context(),
+                                      blk_aio_complete_bh, acb,
+                                      QEMU_CLOCK_VIRTUAL);
     }
 
     return &acb->common;
@@ -1894,8 +1895,9 @@ BlockAIOCB *blk_aio_zone_report(BlockBackend *blk, int64_t offset,
 
     acb->has_returned = true;
     if (acb->rwco.ret != NOT_DONE) {
-        replay_bh_schedule_oneshot_event(qemu_get_current_aio_context(),
-                                         blk_aio_complete_bh, acb);
+        aio_bh_schedule_oneshot_event(qemu_get_current_aio_context(),
+                                      blk_aio_complete_bh, acb,
+                                      QEMU_CLOCK_VIRTUAL);
     }
 
     return &acb->common;
@@ -1935,8 +1937,9 @@ BlockAIOCB *blk_aio_zone_mgmt(BlockBackend *blk, BlockZoneOp op,
 
     acb->has_returned = true;
     if (acb->rwco.ret != NOT_DONE) {
-        replay_bh_schedule_oneshot_event(qemu_get_current_aio_context(),
-                                         blk_aio_complete_bh, acb);
+        aio_bh_schedule_oneshot_event(qemu_get_current_aio_context(),
+                                      blk_aio_complete_bh, acb,
+                                      QEMU_CLOCK_VIRTUAL);
     }
 
     return &acb->common;
@@ -1974,8 +1977,9 @@ BlockAIOCB *blk_aio_zone_append(BlockBackend *blk, int64_t *offset,
     aio_co_enter(qemu_get_current_aio_context(), co);
     acb->has_returned = true;
     if (acb->rwco.ret != NOT_DONE) {
-        replay_bh_schedule_oneshot_event(qemu_get_current_aio_context(),
-                                         blk_aio_complete_bh, acb);
+        aio_bh_schedule_oneshot_event(qemu_get_current_aio_context(),
+                                      blk_aio_complete_bh, acb,
+                                      QEMU_CLOCK_VIRTUAL);
     }
 
     return &acb->common;
diff --git a/block/io.c b/block/io.c
index 301514c8808..fcce0710824 100644
--- a/block/io.c
+++ b/block/io.c
@@ -335,8 +335,9 @@ static void coroutine_fn bdrv_co_yield_to_drain(BlockDriverState *bs,
         bdrv_inc_in_flight(bs);
     }
 
-    replay_bh_schedule_oneshot_event(qemu_get_aio_context(),
-                                     bdrv_co_drain_bh_cb, &data);
+    aio_bh_schedule_oneshot_event(qemu_get_aio_context(),
+                                  bdrv_co_drain_bh_cb, &data,
+                                  QEMU_CLOCK_VIRTUAL);
 
     qemu_coroutine_yield();
     /* If we are resumed from some other event (such as an aio completion or a
diff --git a/block/iscsi.c b/block/iscsi.c
index 979bf90cb79..98ed86b9831 100644
--- a/block/iscsi.c
+++ b/block/iscsi.c
@@ -285,8 +285,9 @@ iscsi_co_generic_cb(struct iscsi_context *iscsi, int status,
     }
 
     if (iTask->co) {
-        replay_bh_schedule_oneshot_event(iTask->iscsilun->aio_context,
-                                         iscsi_co_generic_bh_cb, iTask);
+        aio_bh_schedule_oneshot_event(iTask->iscsilun->aio_context,
+                                      iscsi_co_generic_bh_cb, iTask,
+                                      QEMU_CLOCK_VIRTUAL);
     } else {
         iTask->complete = 1;
     }
diff --git a/block/nfs.c b/block/nfs.c
index 0500f60c08f..66d9df0d89b 100644
--- a/block/nfs.c
+++ b/block/nfs.c
@@ -256,8 +256,9 @@ nfs_co_generic_cb(int ret, struct nfs_context *nfs, void *data,
     if (task->ret < 0) {
         error_report("NFS Error: %s", nfs_get_error(nfs));
     }
-    replay_bh_schedule_oneshot_event(task->client->aio_context,
-                                     nfs_co_generic_bh_cb, task);
+    aio_bh_schedule_oneshot_event(task->client->aio_context,
+                                  nfs_co_generic_bh_cb, task,
+                                  QEMU_CLOCK_VIRTUAL);
 }
 
 static int coroutine_fn nfs_co_preadv(BlockDriverState *bs, int64_t offset,
@@ -723,8 +724,9 @@ nfs_get_allocated_file_size_cb(int ret, struct nfs_context *nfs, void *data,
     if (task->ret < 0) {
         error_report("NFS Error: %s", nfs_get_error(nfs));
     }
-    replay_bh_schedule_oneshot_event(task->client->aio_context,
-                                     nfs_co_generic_bh_cb, task);
+    aio_bh_schedule_oneshot_event(task->client->aio_context,
+                                  nfs_co_generic_bh_cb, task,
+                                  QEMU_CLOCK_VIRTUAL);
 }
 
 static int64_t coroutine_fn nfs_co_get_allocated_file_size(BlockDriverState *bs)
diff --git a/block/null.c b/block/null.c
index 4730acc1eb2..d35b42cbb44 100644
--- a/block/null.c
+++ b/block/null.c
@@ -183,8 +183,8 @@ static inline BlockAIOCB *null_aio_common(BlockDriverState *bs,
         timer_mod_ns(&acb->timer,
                      qemu_clock_get_ns(QEMU_CLOCK_REALTIME) + s->latency_ns);
     } else {
-        replay_bh_schedule_oneshot_event(bdrv_get_aio_context(bs),
-                                         null_bh_cb, acb);
+        aio_bh_schedule_oneshot_event(bdrv_get_aio_context(bs),
+                                      null_bh_cb, acb, QEMU_CLOCK_VIRTUAL);
     }
     return &acb->common;
 }
diff --git a/block/nvme.c b/block/nvme.c
index 3b588b139f6..4069639dc7a 100644
--- a/block/nvme.c
+++ b/block/nvme.c
@@ -344,8 +344,9 @@ static void nvme_put_free_req_locked(NVMeQueuePair *q, NVMeRequest *req)
 static void nvme_wake_free_req_locked(NVMeQueuePair *q)
 {
     if (!qemu_co_queue_empty(&q->free_req_queue)) {
-        replay_bh_schedule_oneshot_event(q->s->aio_context,
-                nvme_free_req_queue_cb, q);
+        aio_bh_schedule_oneshot_event(q->s->aio_context,
+                                      nvme_free_req_queue_cb, q,
+                                      QEMU_CLOCK_VIRTUAL);
     }
 }
 
@@ -1177,7 +1178,8 @@ static void nvme_rw_cb(void *opaque, int ret)
         /* The rw coroutine hasn't yielded, don't try to enter. */
         return;
     }
-    replay_bh_schedule_oneshot_event(data->ctx, nvme_rw_cb_bh, data);
+    aio_bh_schedule_oneshot_event(data->ctx, nvme_rw_cb_bh, data,
+                                  QEMU_CLOCK_VIRTUAL);
 }
 
 static coroutine_fn int nvme_co_prw_aligned(BlockDriverState *bs,
diff --git a/hw/ide/core.c b/hw/ide/core.c
index 08d92184554..c527caf3d69 100644
--- a/hw/ide/core.c
+++ b/hw/ide/core.c
@@ -516,7 +516,7 @@ static void ide_issue_trim_cb(void *opaque, int ret)
 done:
     iocb->aiocb = NULL;
     if (iocb->bh) {
-        replay_bh_schedule_event(iocb->bh);
+        qemu_bh_schedule_event(iocb->bh, QEMU_CLOCK_VIRTUAL);
     }
 }
 
@@ -2368,8 +2368,9 @@ void ide_ctrl_write(void *opaque, uint32_t addr, uint32_t val)
             s = &bus->ifs[i];
             s->status |= BUSY_STAT;
         }
-        replay_bh_schedule_oneshot_event(qemu_get_aio_context(),
-                                         ide_bus_perform_srst, bus);
+        aio_bh_schedule_oneshot_event(qemu_get_aio_context(),
+                                      ide_bus_perform_srst, bus,
+                                      QEMU_CLOCK_VIRTUAL);
     }
 
     bus->cmd = val;
diff --git a/hw/net/virtio-net.c b/hw/net/virtio-net.c
index 4fd1f9accab..ecbf274cb04 100644
--- a/hw/net/virtio-net.c
+++ b/hw/net/virtio-net.c
@@ -415,10 +415,10 @@ static void virtio_net_set_status(struct VirtIODevice *vdev, uint8_t status)
 
         if (queue_started) {
             if (q->tx_timer) {
-                timer_mod(q->tx_timer,
-                               qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL) + n->tx_timeout);
+                timer_mod(q->tx_timer, qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL) +
+                                       n->tx_timeout);
             } else {
-                replay_bh_schedule_event(q->tx_bh);
+                qemu_bh_schedule_event(q->tx_bh, QEMU_CLOCK_VIRTUAL);
             }
         } else {
             if (q->tx_timer) {
@@ -2705,7 +2705,7 @@ static void virtio_net_tx_complete(NetClientState *nc, ssize_t len)
          */
         virtio_queue_set_notification(q->tx_vq, 0);
         if (q->tx_bh) {
-            replay_bh_schedule_event(q->tx_bh);
+            qemu_bh_schedule_event(q->tx_bh, QEMU_CLOCK_VIRTUAL);
         } else {
             timer_mod(q->tx_timer,
                       qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL) + n->tx_timeout);
@@ -2871,7 +2871,7 @@ static void virtio_net_handle_tx_bh(VirtIODevice *vdev, VirtQueue *vq)
         return;
     }
     virtio_queue_set_notification(vq, 0);
-    replay_bh_schedule_event(q->tx_bh);
+    qemu_bh_schedule_event(q->tx_bh, QEMU_CLOCK_VIRTUAL);
 }
 
 static void virtio_net_tx_timer(void *opaque)
@@ -2954,7 +2954,7 @@ static void virtio_net_tx_bh(void *opaque)
     /* If we flush a full burst of packets, assume there are
      * more coming and immediately reschedule */
     if (ret >= n->tx_burst) {
-        replay_bh_schedule_event(q->tx_bh);
+        qemu_bh_schedule_event(q->tx_bh, QEMU_CLOCK_VIRTUAL);
         q->tx_waiting = 1;
         return;
     }
@@ -2968,7 +2968,7 @@ static void virtio_net_tx_bh(void *opaque)
         return;
     } else if (ret > 0) {
         virtio_queue_set_notification(q->tx_vq, 0);
-        replay_bh_schedule_event(q->tx_bh);
+        qemu_bh_schedule_event(q->tx_bh, QEMU_CLOCK_VIRTUAL);
         q->tx_waiting = 1;
     }
 }
diff --git a/replay/replay-events.c b/replay/replay-events.c
index 2e46eda6bf8..d4b095b2097 100644
--- a/replay/replay-events.c
+++ b/replay/replay-events.c
@@ -131,7 +131,7 @@ void replay_bh_schedule_event(QEMUBH *bh)
     }
 }
 
-void replay_bh_schedule_oneshot_event(AioContext *ctx,
+void replay_bh_oneshot_event(AioContext *ctx,
     QEMUBHFunc *cb, void *opaque)
 {
     if (events_enabled) {
diff --git a/stubs/replay-tools.c b/stubs/replay-tools.c
index 3e8ca3212d9..31985af35f7 100644
--- a/stubs/replay-tools.c
+++ b/stubs/replay-tools.c
@@ -30,7 +30,7 @@ void replay_bh_schedule_event(QEMUBH *bh)
     qemu_bh_schedule(bh);
 }
 
-void replay_bh_schedule_oneshot_event(AioContext *ctx,
+void replay_bh_oneshot_event(AioContext *ctx,
      QEMUBHFunc *cb, void *opaque)
 {
     aio_bh_schedule_oneshot(ctx, cb, opaque);
diff --git a/util/async.c b/util/async.c
index 99db28389f6..b88083ecbe7 100644
--- a/util/async.c
+++ b/util/async.c
@@ -36,6 +36,7 @@
 #include "qemu/coroutine_int.h"
 #include "qemu/coroutine-tls.h"
 #include "sysemu/cpu-timers.h"
+#include "sysemu/replay.h"
 #include "trace.h"
 
 /***********************************************************/
@@ -126,8 +127,8 @@ static QEMUBH *aio_bh_dequeue(BHList *head, unsigned *flags)
     return bh;
 }
 
-void aio_bh_schedule_oneshot_full(AioContext *ctx, QEMUBHFunc *cb,
-                                  void *opaque, const char *name)
+static void do_aio_bh_schedule_oneshot_full(AioContext *ctx, QEMUBHFunc *cb,
+                                            void *opaque, const char *name)
 {
     QEMUBH *bh;
     bh = g_new(QEMUBH, 1);
@@ -140,6 +141,24 @@ void aio_bh_schedule_oneshot_full(AioContext *ctx, QEMUBHFunc *cb,
     aio_bh_enqueue(bh, BH_SCHEDULED | BH_ONESHOT);
 }
 
+void aio_bh_schedule_oneshot_full(AioContext *ctx, QEMUBHFunc *cb,
+                                  void *opaque, const char *name,
+                                  QEMUClockType clock_type)
+{
+    switch (clock_type) {
+    case QEMU_CLOCK_VIRTUAL:
+    case QEMU_CLOCK_VIRTUAL_RT:
+        if (replay_mode != REPLAY_MODE_NONE) {
+            /* Record/replay must intercept bh events */
+            replay_bh_oneshot_event(ctx, cb, opaque);
+            break;
+        }
+        /* fallthrough */
+    default:
+        do_aio_bh_schedule_oneshot_full(ctx, cb, opaque, name);
+    }
+}
+
 QEMUBH *aio_bh_new_full(AioContext *ctx, QEMUBHFunc *cb, void *opaque,
                         const char *name, MemReentrancyGuard *reentrancy_guard)
 {
@@ -226,6 +245,22 @@ int aio_bh_poll(AioContext *ctx)
     return ret;
 }
 
+void qemu_bh_schedule_event(QEMUBH *bh, QEMUClockType clock_type)
+{
+    switch (clock_type) {
+    case QEMU_CLOCK_VIRTUAL:
+    case QEMU_CLOCK_VIRTUAL_RT:
+        if (replay_mode != REPLAY_MODE_NONE) {
+            /* Record/replay must intercept bh events */
+            replay_bh_schedule_event(bh);
+            break;
+        }
+        /* fallthrough */
+    default:
+        aio_bh_enqueue(bh, BH_SCHEDULED);
+    }
+}
+
 void qemu_bh_schedule_idle(QEMUBH *bh)
 {
     aio_bh_enqueue(bh, BH_SCHEDULED | BH_IDLE);
-- 
2.45.2