Jan Kiszka ea64305139 KVM: x86: Restrict writeback of VCPU state ... Do not write nmi_pending, sipi_vector, and mpstate unless we at least go through a reset. And TSC as well as KVM wallclocks should only be written on full sync, otherwise we risk to drop some time on state read-modify-write. Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com> Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>		2010-03-04 00:29:30 -03:00
..
cpu.h	Add cpu model configuration support..	2010-02-22 16:16:17 -06:00
exec.h	target-i386: fix crash on x86 32bit linux host with hw breakpoint exceptions	2010-02-28 19:20:02 +01:00
helper_template.h	Update to a hopefully more future proof FSF address	2009-07-16 20:47:01 +00:00
helper.c	target-i386: fix crash on x86 32bit linux host with hw breakpoint exceptions	2010-02-28 19:20:02 +01:00
helper.h	target-i386: implement lzcnt emulation	2009-10-23 17:10:36 +02:00
kvm.c	KVM: x86: Restrict writeback of VCPU state	2010-03-04 00:29:30 -03:00
machine.c	KVM: Rework VCPU state writeback API	2010-03-04 00:29:28 -03:00
op_helper.c	Move ioport.h out of cpu-all.h	2010-03-01 03:29:21 +00:00
ops_sse_header.h	target-i386: add SSE4a instruction support	2009-10-04 14:09:41 +02:00
ops_sse.h	target-i386: add SSE4a instruction support	2009-10-04 14:09:41 +02:00
svm.h	reworked SVM interrupt handling logic - fixed vmrun EIP saved value - reworked cr8 handling - added CPUState.hflags2	2008-06-04 17:02:19 +00:00
TODO	Unbreak large mem support by removing kqemu	2009-08-24 08:02:55 -05:00
translate.c	remove two dead assignments in target-i386/translate.c	2010-02-05 18:13:14 +00:00