|
 |
5d360b |
From 6baaf82a7742a1de9160146b08ba0cc86b3d4e79 Mon Sep 17 00:00:00 2001
|
|
|
5d360b |
From: Paolo Bonzini <pbonzini@redhat.com>
|
|
|
5d360b |
Date: Wed, 10 Jan 2018 17:02:21 +0100
|
|
|
5d360b |
Subject: [PATCH 2/2] main-loop: Acquire main_context lock around
|
|
|
5d360b |
os_host_main_loop_wait.
|
|
|
5d360b |
|
|
|
5d360b |
RH-Author: Paolo Bonzini <pbonzini@redhat.com>
|
|
|
5d360b |
Message-id: <20180110170221.28975-1-pbonzini@redhat.com>
|
|
|
5d360b |
Patchwork-id: 78541
|
|
|
5d360b |
O-Subject: [RHEL7.5 qemu-kvm PATCH] main-loop: Acquire main_context lock around os_host_main_loop_wait.
|
|
|
5d360b |
Bugzilla: 1473536
|
|
|
5d360b |
RH-Acked-by: Jeffrey Cody <jcody@redhat.com>
|
|
|
5d360b |
RH-Acked-by: John Snow <jsnow@redhat.com>
|
|
|
5d360b |
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
|
|
|
5d360b |
|
|
|
5d360b |
Bugzilla: 1473536
|
|
|
5d360b |
|
|
|
5d360b |
Brew build: https://brewweb.engineering.redhat.com/brew/taskinfo?taskID=14912977
|
|
|
5d360b |
|
|
|
5d360b |
When running virt-rescue the serial console hangs from time to time.
|
|
|
5d360b |
Virt-rescue runs an ordinary Linux kernel "appliance", but there is
|
|
|
5d360b |
only a single idle process running inside, so the qemu main loop is
|
|
|
5d360b |
largely idle. With virt-rescue >= 1.37 you may be able to observe the
|
|
|
5d360b |
hang by doing:
|
|
|
5d360b |
|
|
|
5d360b |
$ virt-rescue -e ^] --scratch
|
|
|
5d360b |
><rescue> while true; do ls -l /usr/bin; done
|
|
|
5d360b |
|
|
|
5d360b |
The hang in virt-rescue can be resolved by pressing a key on the
|
|
|
5d360b |
serial console.
|
|
|
5d360b |
|
|
|
5d360b |
Possibly with the same root cause, we also observed hangs during very
|
|
|
5d360b |
early boot of regular Linux VMs with a serial console. Those hangs
|
|
|
5d360b |
are extremely rare, but you may be able to observe them by running
|
|
|
5d360b |
this command on baremetal for a sufficiently long time:
|
|
|
5d360b |
|
|
|
5d360b |
$ while libguestfs-test-tool -t 60 >& /tmp/log ; do echo -n . ; done
|
|
|
5d360b |
|
|
|
5d360b |
(Check in /tmp/log that the failure was caused by a hang during early
|
|
|
5d360b |
boot, and not some other reason)
|
|
|
5d360b |
|
|
|
5d360b |
During investigation of this bug, Paolo Bonzini wrote:
|
|
|
5d360b |
|
|
|
5d360b |
> glib is expecting QEMU to use g_main_context_acquire around accesses to
|
|
|
5d360b |
> GMainContext. However QEMU is not doing that, instead it is taking its
|
|
|
5d360b |
> own mutex. So we should add g_main_context_acquire and
|
|
|
5d360b |
> g_main_context_release in the two implementations of
|
|
|
5d360b |
> os_host_main_loop_wait; these should undo the effect of Frediano's
|
|
|
5d360b |
> glib patch.
|
|
|
5d360b |
|
|
|
5d360b |
This patch exactly implements Paolo's suggestion in that paragraph.
|
|
|
5d360b |
|
|
|
5d360b |
This fixes the serial console hang in my testing, across 3 different
|
|
|
5d360b |
physical machines (AMD, Intel Core i7 and Intel Xeon), over many hours
|
|
|
5d360b |
of automated testing. I wasn't able to reproduce the early boot hangs
|
|
|
5d360b |
(but as noted above, these are extremely rare in any case).
|
|
|
5d360b |
|
|
|
5d360b |
Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=1435432
|
|
|
5d360b |
Reported-by: Richard W.M. Jones <rjones@redhat.com>
|
|
|
5d360b |
Tested-by: Richard W.M. Jones <rjones@redhat.com>
|
|
|
5d360b |
Signed-off-by: Richard W.M. Jones <rjones@redhat.com>
|
|
|
5d360b |
Message-Id: <20170331205133.23906-1-rjones@redhat.com>
|
|
|
5d360b |
[Paolo: this is actually a glib bug: recent glib versions are also
|
|
|
5d360b |
expecting g_main_context_acquire around g_poll---but that is not
|
|
|
5d360b |
documented and probably not even intended].
|
|
|
5d360b |
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
|
5d360b |
(cherry picked from commit ecbddbb106114f90008024b4e6c3ba1c38d7ca0e)
|
|
|
5d360b |
|
|
|
5d360b |
Signed-off-by: Miroslav Rezanina <mrezanin@redhat.com>
|
|
|
5d360b |
---
|
|
|
5d360b |
main-loop.c | 11 +++++++++++
|
|
|
5d360b |
1 file changed, 11 insertions(+)
|
|
|
5d360b |
|
|
|
5d360b |
diff --git a/main-loop.c b/main-loop.c
|
|
|
5d360b |
index cf36645..a93d37b 100644
|
|
|
5d360b |
--- a/main-loop.c
|
|
|
5d360b |
+++ b/main-loop.c
|
|
|
5d360b |
@@ -192,9 +192,12 @@ static void glib_pollfds_poll(void)
|
|
|
5d360b |
|
|
|
5d360b |
static int os_host_main_loop_wait(uint32_t timeout)
|
|
|
5d360b |
{
|
|
|
5d360b |
+ GMainContext *context = g_main_context_default();
|
|
|
5d360b |
int ret;
|
|
|
5d360b |
static int spin_counter;
|
|
|
5d360b |
|
|
|
5d360b |
+ g_main_context_acquire(context);
|
|
|
5d360b |
+
|
|
|
5d360b |
glib_pollfds_fill(&timeout);
|
|
|
5d360b |
|
|
|
5d360b |
/* If the I/O thread is very busy or we are incorrectly busy waiting in
|
|
|
5d360b |
@@ -230,6 +233,9 @@ static int os_host_main_loop_wait(uint32_t timeout)
|
|
|
5d360b |
}
|
|
|
5d360b |
|
|
|
5d360b |
glib_pollfds_poll();
|
|
|
5d360b |
+
|
|
|
5d360b |
+ g_main_context_release(context);
|
|
|
5d360b |
+
|
|
|
5d360b |
return ret;
|
|
|
5d360b |
}
|
|
|
5d360b |
#else
|
|
|
5d360b |
@@ -385,12 +391,15 @@ static int os_host_main_loop_wait(uint32_t timeout)
|
|
|
5d360b |
fd_set rfds, wfds, xfds;
|
|
|
5d360b |
int nfds;
|
|
|
5d360b |
|
|
|
5d360b |
+ g_main_context_acquire(context);
|
|
|
5d360b |
+
|
|
|
5d360b |
/* XXX: need to suppress polling by better using win32 events */
|
|
|
5d360b |
ret = 0;
|
|
|
5d360b |
for (pe = first_polling_entry; pe != NULL; pe = pe->next) {
|
|
|
5d360b |
ret |= pe->func(pe->opaque);
|
|
|
5d360b |
}
|
|
|
5d360b |
if (ret != 0) {
|
|
|
5d360b |
+ g_main_context_release(context);
|
|
|
5d360b |
return ret;
|
|
|
5d360b |
}
|
|
|
5d360b |
|
|
|
5d360b |
@@ -440,6 +449,8 @@ static int os_host_main_loop_wait(uint32_t timeout)
|
|
|
5d360b |
g_main_context_dispatch(context);
|
|
|
5d360b |
}
|
|
|
5d360b |
|
|
|
5d360b |
+ g_main_context_release(context);
|
|
|
5d360b |
+
|
|
|
5d360b |
return select_ret || g_poll_ret;
|
|
|
5d360b |
}
|
|
|
5d360b |
#endif
|
|
|
5d360b |
--
|
|
|
5d360b |
1.8.3.1
|
|
|
5d360b |
|