Any suggestion? Or new design idea for this? Thanks Pingfan
On Sun, Nov 25, 2012 at 10:02 AM, Liu Ping Fan <qemul...@gmail.com> wrote: > From: Liu Ping Fan <pingf...@linux.vnet.ibm.com> > > v1: > https://lists.gnu.org/archive/html/qemu-devel/2012-07/msg03312.html > > v2: > http://lists.gnu.org/archive/html/qemu-devel/2012-08/msg01275.html > > v3: > http://lists.nongnu.org/archive/html/qemu-devel/2012-09/msg01474.html > > v4: > http://lists.gnu.org/archive/html/qemu-devel/2012-10/msg03857.html > > v5: > https://lists.gnu.org/archive/html/qemu-devel/2012-10/msg04867.html > > v6: > http://lists.gnu.org/archive/html/qemu-devel/2012-11/msg00542.html > -- > changes v5->v6: > Apply fine-grain lock for all address space. > Introduce separated interface to allow mmio dispatcher called with/without > big lock. > > changes v6->v7: > drop wrapper of gcc atomic builtin > > > Liu Ping Fan (7): > qom: apply atomic on object's refcount > hotplug: introduce qdev_unplug_complete() to remove device from views > pci: remove pci device from mem view when unplug > memory: introduce local lock for address space > memory: make mmio dispatch able to be out of biglock > memory: introduce tls context to trace nested mmio request issue > vcpu: push mmio dispatcher out of big lock > > cpu-common.h | 3 + > docs/memory.txt | 4 + > exec.c | 206 > ++++++++++++++++++++++++++++++++++++++++++++++++----- > hw/acpi_piix4.c | 2 +- > hw/pci.c | 13 +++- > hw/pci.h | 1 + > hw/qdev.c | 26 +++++++ > hw/qdev.h | 3 +- > kvm-all.c | 4 +- > memory-internal.h | 1 + > memory.c | 1 + > memory.h | 5 ++ > qom/object.c | 5 +- > 13 files changed, 250 insertions(+), 24 deletions(-) > > -- > 1.7.4.4 >
