[Qemu-devel] [PULL 8/8] icount: decouple warp calls

[Paolo Bonzini]

From: Pavel Dovgalyuk <address@hidden>

qemu_clock_warp function is called to update virtual clock when CPU
is sleeping. This function includes replay checkpoint to make execution
deterministic in icount mode.
Record/replay module flushes async event queue at checkpoints.
Some of the events (e.g., block devices operations) include interaction
with hardware. E.g., APIC polled by block devices sets one of IRQ flags.
Flag to be set depends on currently executed thread (CPU or iothread).
Therefore in replay mode we have to process the checkpoints in the same thread
as they were recorded.
qemu_clock_warp function (and its checkpoint) may be called from different
thread. This patch decouples two different execution cases of this function:
call when CPU is sleeping from iothread and call from cpu thread to update
virtual clock.
First task is performed by qemu_start_warp_timer function. It sets warp
timer event to the moment of nearest pending virtual timer.
Second function (qemu_account_warp_timer) is called from cpu thread
before execution of the code. It advances virtual clock by adding the length
of period while CPU was sleeping.

Signed-off-by: Pavel Dovgalyuk <address@hidden>
Message-Id: <address@hidden>
[Update docs. - Paolo]
Signed-off-by: Paolo Bonzini <address@hidden>
---
 cpus.c                  | 58 ++++++++++++++++++++++++++++---------------------
 docs/replay.txt         | 21 +++++++++++++-----
 include/qemu/timer.h    |  7 +++---
 include/sysemu/replay.h |  3 ++-
 main-loop.c             |  2 +-
 qemu-timer.c            |  4 +++-
 stubs/clock-warp.c      |  2 +-
 7 files changed, 58 insertions(+), 39 deletions(-)

diff --git a/cpus.c b/cpus.c
index 85d0f87..4052be5 100644
--- a/cpus.c
+++ b/cpus.c
@@ -370,9 +370,12 @@ static void icount_warp_rt(void)
     }
 }
 
-static void icount_dummy_timer(void *opaque)
+static void icount_timer_cb(void *opaque)
 {
-    (void)opaque;
+    /* No need for a checkpoint because the timer already synchronizes
+     * with CHECKPOINT_CLOCK_VIRTUAL_RT.
+     */
+    icount_warp_rt();
 }
 
 void qtest_clock_warp(int64_t dest)
@@ -396,17 +399,12 @@ void qtest_clock_warp(int64_t dest)
     qemu_clock_notify(QEMU_CLOCK_VIRTUAL);
 }
 
-void qemu_clock_warp(QEMUClockType type)
+void qemu_start_warp_timer(void)
 {
     int64_t clock;
     int64_t deadline;
 
-    /*
-     * There are too many global variables to make the "warp" behavior
-     * applicable to other clocks.  But a clock argument removes the
-     * need for if statements all over the place.
-     */
-    if (type != QEMU_CLOCK_VIRTUAL || !use_icount) {
+    if (!use_icount) {
         return;
     }
 
@@ -418,29 +416,17 @@ void qemu_clock_warp(QEMUClockType type)
     }
 
     /* warp clock deterministically in record/replay mode */
-    if (!replay_checkpoint(CHECKPOINT_CLOCK_WARP)) {
+    if (!replay_checkpoint(CHECKPOINT_CLOCK_WARP_START)) {
         return;
     }
 
-    if (icount_sleep) {
-        /*
-         * If the CPUs have been sleeping, advance QEMU_CLOCK_VIRTUAL timer 
now.
-         * This ensures that the deadline for the timer is computed correctly
-         * below.
-         * This also makes sure that the insn counter is synchronized before
-         * the CPU starts running, in case the CPU is woken by an event other
-         * than the earliest QEMU_CLOCK_VIRTUAL timer.
-         */
-        icount_warp_rt();
-        timer_del(icount_warp_timer);
-    }
     if (!all_cpu_threads_idle()) {
         return;
     }
 
     if (qtest_enabled()) {
         /* When testing, qtest commands advance icount.  */
-       return;
+        return;
     }
 
     /* We want to use the earliest deadline from ALL vm_clocks */
@@ -496,6 +482,28 @@ void qemu_clock_warp(QEMUClockType type)
     }
 }
 
+static void qemu_account_warp_timer(void)
+{
+    if (!use_icount || !icount_sleep) {
+        return;
+    }
+
+    /* Nothing to do if the VM is stopped: QEMU_CLOCK_VIRTUAL timers
+     * do not fire, so computing the deadline does not make sense.
+     */
+    if (!runstate_is_running()) {
+        return;
+    }
+
+    /* warp clock deterministically in record/replay mode */
+    if (!replay_checkpoint(CHECKPOINT_CLOCK_WARP_ACCOUNT)) {
+        return;
+    }
+
+    timer_del(icount_warp_timer);
+    icount_warp_rt();
+}
+
 static bool icount_state_needed(void *opaque)
 {
     return use_icount;
@@ -624,7 +632,7 @@ void configure_icount(QemuOpts *opts, Error **errp)
     icount_sleep = qemu_opt_get_bool(opts, "sleep", true);
     if (icount_sleep) {
         icount_warp_timer = timer_new_ns(QEMU_CLOCK_VIRTUAL_RT,
-                                         icount_dummy_timer, NULL);
+                                         icount_timer_cb, NULL);
     }
 
     icount_align_option = qemu_opt_get_bool(opts, "align", false);
@@ -1496,7 +1504,7 @@ static void tcg_exec_all(void)
     int r;
 
     /* Account partial waits to QEMU_CLOCK_VIRTUAL.  */
-    qemu_clock_warp(QEMU_CLOCK_VIRTUAL);
+    qemu_account_warp_timer();
 
     if (next_cpu == NULL) {
         next_cpu = first_cpu;
diff --git a/docs/replay.txt b/docs/replay.txt
index 149727e..3cedc25 100644
--- a/docs/replay.txt
+++ b/docs/replay.txt
@@ -107,7 +107,7 @@ at the specified moments of time. There are several kinds 
of timers:
    sources (e.g. real time clock chip). Host clock is the one of the sources
    of non-determinism. Host clock read operations should be logged to
    make the execution deterministic.
- * Real time clock for icount. This clock is similar to real time clock but
+ * Virtual real time clock. This clock is similar to real time clock but
    it is used only for increasing virtual clock while virtual machine is
    sleeping. Due to its nature it is also non-deterministic as the host clock
    and has to be logged too.
@@ -134,11 +134,20 @@ of time. That's why we do not process a group of timers 
until the checkpoint
 event will be read from the log. Such an event allows synchronizing CPU
 execution and timer events.
 
-Another checkpoints application in record/replay is instruction counting
-while the virtual machine is idle. This function (qemu_clock_warp) is called
-from the wait loop. It changes virtual machine state and must be deterministic
-then. That is why we added checkpoint to this function to prevent its
-operation in replay mode when it does not correspond to record mode.
+Two other checkpoints govern the "warping" of the virtual clock.
+While the virtual machine is idle, the virtual clock increments at
+1 ns per *real time* nanosecond.  This is done by setting up a timer
+(called the warp timer) on the virtual real time clock, so that the
+timer fires at the next deadline of the virtual clock; the virtual clock
+is then incremented (which is called "warping" the virtual clock) as
+soon as the timer fires or the CPUs need to go out of the idle state.
+Two functions are used for this purpose; because these actions change
+virtual machine state and must be deterministic, each of them creates a
+checkpoint.  qemu_start_warp_timer checks if the CPUs are idle and if so
+starts accounting real time to virtual clock.  qemu_account_warp_timer
+is called when the CPUs get an interrupt or when the warp timer fires,
+and it warps the virtual clock by the amount of real time that has passed
+since qemu_start_warp_timer.
 
 Bottom halves
 -------------
diff --git a/include/qemu/timer.h b/include/qemu/timer.h
index d0946cb..7197d08 100644
--- a/include/qemu/timer.h
+++ b/include/qemu/timer.h
@@ -210,12 +210,11 @@ void qemu_clock_notify(QEMUClockType type);
 void qemu_clock_enable(QEMUClockType type, bool enabled);
 
 /**
- * qemu_clock_warp:
- * @type: the clock type
+ * qemu_start_warp_timer:
  *
- * Warp a clock to a new value
+ * Starts a timer for virtual clock update
  */
-void qemu_clock_warp(QEMUClockType type);
+void qemu_start_warp_timer(void);
 
 /**
  * qemu_clock_register_reset_notifier:
diff --git a/include/sysemu/replay.h b/include/sysemu/replay.h
index d24d502..e798919 100644
--- a/include/sysemu/replay.h
+++ b/include/sysemu/replay.h
@@ -27,7 +27,8 @@ typedef enum ReplayClockKind ReplayClockKind;
 
 /* IDs of the checkpoints */
 enum ReplayCheckpoint {
-    CHECKPOINT_CLOCK_WARP,
+    CHECKPOINT_CLOCK_WARP_START,
+    CHECKPOINT_CLOCK_WARP_ACCOUNT,
     CHECKPOINT_RESET_REQUESTED,
     CHECKPOINT_SUSPEND_REQUESTED,
     CHECKPOINT_CLOCK_VIRTUAL,
diff --git a/main-loop.c b/main-loop.c
index 19beae7..3a7f4cd 100644
--- a/main-loop.c
+++ b/main-loop.c
@@ -509,7 +509,7 @@ int main_loop_wait(int nonblocking)
 
     /* CPU thread can infinitely wait for event after
        missing the warp */
-    qemu_clock_warp(QEMU_CLOCK_VIRTUAL);
+    qemu_start_warp_timer();
     qemu_clock_run_all_timers();
 
     return ret;
diff --git a/qemu-timer.c b/qemu-timer.c
index e98ecc9..4441fe6 100644
--- a/qemu-timer.c
+++ b/qemu-timer.c
@@ -394,7 +394,9 @@ static bool timer_mod_ns_locked(QEMUTimerList *timer_list,
 static void timerlist_rearm(QEMUTimerList *timer_list)
 {
     /* Interrupt execution to force deadline recalculation.  */
-    qemu_clock_warp(timer_list->clock->type);
+    if (timer_list->clock->type == QEMU_CLOCK_VIRTUAL) {
+        qemu_start_warp_timer();
+    }
     timerlist_notify(timer_list);
 }
 
diff --git a/stubs/clock-warp.c b/stubs/clock-warp.c
index 5ae32b9..8acb58a 100644
--- a/stubs/clock-warp.c
+++ b/stubs/clock-warp.c
@@ -2,7 +2,7 @@
 #include "qemu-common.h"
 #include "qemu/timer.h"
 
-void qemu_clock_warp(QEMUClockType type)
+void qemu_start_warp_timer(void)
 {
 }
 
-- 
1.8.3.1