Jan Kiszka ab5ea55805 x86: svm: Always clear event_inj on vmexit ... We currently only clear SVM_EVTINJ_VALID after successful interrupt delivery. This apparently does not match real hardware which clears the whole event_inj field on every vmexit, including unsuccessful interrupt delivery. Reported-by: Erik van der Kouwe <vdkouwe@cs.vu.nl> Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com> Signed-off-by: Aurelien Jarno <aurelien@aurel32.net>		2010-06-30 20:59:53 +02:00
..
TODO	Unbreak large mem support by removing kqemu	2009-08-24 08:02:55 -05:00
cpu.h	kvm: Enable XSAVE live migration support	2010-06-28 13:06:03 -03:00
cpuid.c	Enable XSAVE related CPUID	2010-06-28 13:06:03 -03:00
exec.h	target-i386: fix crash on x86 32bit linux host with hw breakpoint exceptions	2010-02-28 19:20:02 +01:00
helper.c	x86: Fix INIT processing	2010-06-27 19:07:45 +03:00
helper.h	target-i386: implement lzcnt emulation	2009-10-23 17:10:36 +02:00
helper_template.h	Update to a hopefully more future proof FSF address	2009-07-16 20:47:01 +00:00
kvm.c	kvm: Fix cpu_is_bsp() compilation warning	2010-06-28 13:06:03 -03:00
machine.c	kvm: Enable XSAVE live migration support	2010-06-28 13:06:03 -03:00
op_helper.c	x86: svm: Always clear event_inj on vmexit	2010-06-30 20:59:53 +02:00
ops_sse.h	target-i386: add SSE4a instruction support	2009-10-04 14:09:41 +02:00
ops_sse_header.h	tcg: Optionally sign-extend 32-bit arguments for 64-bit hosts.	2010-06-16 11:29:11 +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
translate.c	target-i386: fix decoding of negative 4-byte displacements	2010-06-04 19:48:53 +00:00