cpus-common.c | 9 ++++++++- include/sysemu/replay.h | 1 + replay/replay-internal.h | 1 - stubs/replay-tools.c | 5 +++++ 4 files changed, 14 insertions(+), 2 deletions(-)
In record/replay mode waiting for vCPU to execute
the task scheduled by run_on_cpu may lead to deadlock,
because when run_on_cpu is executed in main_loop
(e.g., in loadvm processing) it holds replay mutex.
This patch allows running scheduled task in iothread
when it holds the replay mutex.
Signed-off-by: Pavel Dovgalyuk <Pavel.Dovgalyuk@ispras.ru>
---
cpus-common.c | 9 ++++++++-
include/sysemu/replay.h | 1 +
replay/replay-internal.h | 1 -
stubs/replay-tools.c | 5 +++++
4 files changed, 14 insertions(+), 2 deletions(-)
diff --git a/cpus-common.c b/cpus-common.c
index 6e73d3e58d..38ff510175 100644
--- a/cpus-common.c
+++ b/cpus-common.c
@@ -23,6 +23,7 @@
#include "hw/core/cpu.h"
#include "sysemu/cpus.h"
#include "qemu/lockable.h"
+#include "sysemu/replay.h"
static QemuMutex qemu_cpu_list_lock;
static QemuCond exclusive_cond;
@@ -136,7 +137,13 @@ void do_run_on_cpu(CPUState *cpu, run_on_cpu_func func, run_on_cpu_data data,
{
struct qemu_work_item wi;
- if (qemu_cpu_is_self(cpu)) {
+ if (qemu_cpu_is_self(cpu)
+ /*
+ * vCPU thread is waiting when replay mutex is locked
+ * and the task is not exclusive, the function may be called
+ * without other synchronization.
+ */
+ || (replay_mode != REPLAY_MODE_NONE && replay_mutex_locked())) {
func(cpu, data);
return;
}
diff --git a/include/sysemu/replay.h b/include/sysemu/replay.h
index 0f3b0f7eac..032256533b 100644
--- a/include/sysemu/replay.h
+++ b/include/sysemu/replay.h
@@ -62,6 +62,7 @@ extern char *replay_snapshot;
void replay_mutex_lock(void);
void replay_mutex_unlock(void);
+bool replay_mutex_locked(void);
/* Replay process control functions */
diff --git a/replay/replay-internal.h b/replay/replay-internal.h
index 97649ed8d7..dada623527 100644
--- a/replay/replay-internal.h
+++ b/replay/replay-internal.h
@@ -117,7 +117,6 @@ void replay_get_array_alloc(uint8_t **buf, size_t *size);
* synchronisation between vCPU and main-loop threads. */
void replay_mutex_init(void);
-bool replay_mutex_locked(void);
/*! Checks error status of the file. */
void replay_check_error(void);
diff --git a/stubs/replay-tools.c b/stubs/replay-tools.c
index 43296b3d4e..a42f2483d5 100644
--- a/stubs/replay-tools.c
+++ b/stubs/replay-tools.c
@@ -48,6 +48,11 @@ void replay_mutex_unlock(void)
{
}
+bool replay_mutex_locked(void)
+{
+ return false;
+}
+
void replay_register_char_driver(Chardev *chr)
{
}
On 29/03/21 10:05, Pavel Dovgalyuk wrote: > @@ -136,7 +137,13 @@ void do_run_on_cpu(CPUState *cpu, run_on_cpu_func func, run_on_cpu_data data, > { > struct qemu_work_item wi; > > - if (qemu_cpu_is_self(cpu)) { > + if (qemu_cpu_is_self(cpu) > + /* > + * vCPU thread is waiting when replay mutex is locked > + * and the task is not exclusive, the function may be called > + * without other synchronization. > + */ > + || (replay_mode != REPLAY_MODE_NONE && replay_mutex_locked())) { > func(cpu, data); > return; > } Is the "or" saying that the execution is using the lockstep mode? If so, can you put it in a separate function so that it's more self-explanatory and check if it should be used elsewhere? Thanks, Paolo
On 29.03.2021 12:42, Paolo Bonzini wrote: > On 29/03/21 10:05, Pavel Dovgalyuk wrote: >> @@ -136,7 +137,13 @@ void do_run_on_cpu(CPUState *cpu, run_on_cpu_func >> func, run_on_cpu_data data, >> { >> struct qemu_work_item wi; >> - if (qemu_cpu_is_self(cpu)) { >> + if (qemu_cpu_is_self(cpu) >> + /* >> + * vCPU thread is waiting when replay mutex is locked >> + * and the task is not exclusive, the function may be called >> + * without other synchronization. >> + */ >> + || (replay_mode != REPLAY_MODE_NONE && replay_mutex_locked())) { >> func(cpu, data); >> return; >> } > > Is the "or" saying that the execution is using the lockstep mode? If > so, can you put it in a separate function so that it's more > self-explanatory and check if it should be used elsewhere? It was replay (is that lockstep that you mentioned?). I check that the mutex is already locked, which means, that vCPU does nothing at this moment. Pavel Dovgalyuk
On 29/03/21 12:55, Pavel Dovgalyuk wrote: >>> >> >> Is the "or" saying that the execution is using the lockstep mode? If >> so, can you put it in a separate function so that it's more >> self-explanatory and check if it should be used elsewhere? > > It was replay (is that lockstep that you mentioned?). Lockstep in the sense that (as is the case in record/replay mode) the I/O thread and vCPU thread execute in turns. Paolo > I check that the mutex is already locked, which means, that vCPU > does nothing at this moment.
© 2016 - 2024 Red Hat, Inc.