公开(公告)号：US09552250B2

公开(公告)日：2017-01-24

申请号：US14669049

申请日：2015-03-26

Applicant: VMware, Inc.

Inventor： Hariprakash Govindarajalu ,  Yujie Chen ,  Sowgandh Sunil Gadi ,  Ravi Parimi

IPC: G06F11/00 ,  G06F11/07

CPC classification number: G06F11/079 ,  G06F11/0721 ,  G06F11/0751 ,  G06F11/0766 ,  G06F11/0778

Abstract: Discovering a hardware failure in a processor is disclosed. When an operating system or application fails, a function containing the instruction that failed along with the register set of the CPU at the failure is recorded. The function is analyzed into its basic blocks. The failing instruction, the failing basic block, the definitions that reach the failing instruction, and the CPU register set at the failure provide information to determine whether the failure was caused by hardware or software. If, after a complete search of the definitions reaching the failing instruction, the search discovers a first definition defining the failing instruction and a second definition defining the first definition such that the second definition reaches the failing instruction and the first definition assigns a register value that does not match a register value in the failing instruction, then a hardware failure is the cause of the crash.

Abstract translation: 发现在处理器中发现硬件故障。 当操作系统或应用程序发生故障时，将记录包含失败的指令失败的功能以及故障时CPU的寄存器组。 该功能被分析成其基本块。 失败的指令，失败的基本块，到达故障指令的定义以及故障时设置的CPU寄存器提供信息，以确定故障是由硬件还是软件引起。 如果在对达到故障指令的定义的完整搜索完成之后，搜索发现定义故障指令的第一定义和定义第一定义的第二定义，使得第二定义到达故障指令，并且第一定义分配一个寄存器值， 在失败的指令中与寄存器值不匹配，则硬件故障是崩溃的原因。