Am 25.01.2012 17:00, schrieb Joerg Roedel: > On Tue, Jan 24, 2012 at 06:23:50PM +0200, Gleb Natapov wrote: >> On Tue, Jan 24, 2012 at 03:24:50PM +0100, Kevin Wolf wrote: > >>> However, task_switch_interception() itself does some more based on the >>> value of reason, for example it decides whether or not to call >>> skip_emulated_instruction(). >>> >> Joerg need to help us here. If intercept of task switch happens before >> rip is advanced past instruction that cause it we have to know somehow >> that task switch was caused by instruction. It is not enough that HW >> checks permission, we still lack essential info. > > Hmm, the RIP in the VMCB points to the instruction causing the task > switch. This is also true for lcall and ljmp. But in my experiments I > have seen exit_int_info.valid = 1 for task-switches that went through > the IDT. But I havn't tested the VM86 case, though. > > Kevin, can you please re-verify that exit_int_info.valid is always 0 in > your experiment? On what hardware have you tested this? I just retried. I use kvm-kmod and kvm.git with HEAD at ff92e9b5 plus the tree patches of this series plus a printk to output exit_int_info in task_switch_intercept(). I ran taskswitch2 from kvm-unittests and got two failures and my VM86 unit test which hung when trying to return from VM86. I also ran the kernel that made me aware of the issue initially. All debug messages show exit_int_info = 0. This is the /proc/cpuinfo snippet for the first core: processor : 0 vendor_id : AuthenticAMD cpu family : 15 model : 107 model name : AMD Athlon(tm) 64 X2 Dual Core Processor 5200+ stepping : 2 cpu MHz : 1800.000 cache size : 512 KB physical id : 0 siblings : 2 core id : 0 cpu cores : 2 apicid : 0 initial apicid : 0 fpu : yes fpu_exception : yes cpuid level : 1 wp : yes flags : fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ht syscall nx mmxext fxsr_opt rdtscp lm 3dnowext 3dnow rep_good nopl extd_apicid pni cx16 lahf_lm cmp_legacy svm extapic cr8_legacy 3dnowprefetch lbrv bogomips : 3592.64 TLB size : 1024 4K pages clflush size : 64 cache_alignment : 64 address sizes : 40 bits physical, 48 bits virtual power management: ts fid vid ttp tm stc 100mhzsteps Kevin -- To unsubscribe from this list: send the line "unsubscribe kvm" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
