| commit | 6cabe1f303b9d76458c00f00df7f477449a13b2f | |
| author | Jan Kiszka <jan.kiszka@siemens.com> | |
| Fri, 25 Jun 2010 14:56:53 +0000 (25 16:56 +0200) | ||
| committer | Aurelien Jarno <aurelien@aurel32.net> | |
| Thu, 22 Jul 2010 03:52:09 +0000 (22 05:52 +0200) | ||
| tree | 157c9fcfd0e40b426857f42278d872acee72a97c | treesnapshot (tar.gz zip) |
| parent | c629a4bc9725a1ec64c4c89894ef27c758024516 | commitdiff |
Fix qemu_wait_io_event processing in io-thread mode
When checking for I/O events in the tcg CPU loop, make sure that we
call qemu_wait_io_event_common for all CPUs, not only the current one.
Otherwise pause_all_vcpus may lock up or run_on_cpu requests may starve.
Rename qemu_wait_io_event to qemu_tcg_wait_io_event at this chance and
purge its argument list as it has no use for it.
Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
Acked-by: Paolo Bonzini <pbonzini@redhat.com>
Reviewed-by: Marcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: Aurelien Jarno <aurelien@aurel32.net>
When checking for I/O events in the tcg CPU loop, make sure that we
call qemu_wait_io_event_common for all CPUs, not only the current one.
Otherwise pause_all_vcpus may lock up or run_on_cpu requests may starve.
Rename qemu_wait_io_event to qemu_tcg_wait_io_event at this chance and
purge its argument list as it has no use for it.
Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
Acked-by: Paolo Bonzini <pbonzini@redhat.com>
Reviewed-by: Marcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: Aurelien Jarno <aurelien@aurel32.net>
| cpus.c | diffblobblamehistory |