ESXi host fails with a purple diagnostic screen that displays: "BackMap_Lookup" and "#PF Exception 14 in world wwww:VMName"

Products

VMware vSphere ESXi

Issue/Introduction

This article describes a specific issue. If you experience all of the above symptoms, consult the sections below. If you experience some but not all of these symptoms, your issue is not related to this article. Search for your symptoms in the Knowledge Base or file a Support Request. For more information, see Filing a Support Request in Customer Connect (2006985).

Symptoms:

An ESXi/ESX host stops responding and displays a purple diagnostic screen indicating a Page Fault (#PF) exception has occurred.
You see a backtrace similar to:

#PF Exception 14 in world wwww:VMName IP 0xnnnnnn addr 0xnnnnn BackMap_Lookup@vmkernel#nover+0xnn stack: 0xnn BackMap_CanMonitorMapMPN@vmkernel#nover+0xnn stack: 0xnn UWVMKSyscall_ReadPage64@vmkernel#nover+0xnn stack: 0xnn
Immediately preceding the failure, a virtual machine failed with a page fault (#PF 14) or general protection fault (#GP 13).
In the VMkernel logs, you see entries similar to:

WARNING: World: vm WWWW: 9241: vmm0:VirtualMachineName:vcpu-0:VMM fault FF: src=MONITOR rip=0xnnnn regs=0xnnnn Backtrace for current CPU #cc, worldID=WWWW , ebp=0xnnnn 0xnnnn:[0xnnnn]World_VMMPanic@vmkernel#nover+0x25 stack: 0xnnnn, 0xnnnn 0xnnnn:[0xnnnn]World_VMMPanic@vmkernel#nover+0x25 stack: 0x4100318c32a4, 0x2b907ff0 0xnnnn:[0xnnnn]VMMVMKCall_Call@vmkernel#nover+0x186 stack: 0x0, 0x0, 0x0, 0x0, 0x0 0xnnnn:[0xnnnn]<unknown> stack: 0x0, 0x0, 0x0, 0x0, 0x0 WARNING: World: vm WWWW : 9276: Couldn't awake worldWWWW
The world cited in the purple diagnostic screen may differ from the world cited in the virtual machine failure. However, they are two worlds comprising the same virtual machine, and cite the same virtual machine name.
The RDI and/or RBX register contains the value 0xd100000 or 0x3100000. For example:

cpuC:WWWW)rax=0xnnnn rbx=0xn100000 rcx=0xnnnn cpuC:WWWW)rdx=0xnnnn rbp=0xnnnn rsi=0xnnnn cpuC:WWWW)rdi=0xn100000 r8=0xnnnn r9=0xnnnn cpuC:WWWW)r10=0xnnnn r11=0xnnnn r12=0xnnnn cpuC:WWWW)r13=0xnnnn r14=0xnnnn r15=0xnnnn
The ESXi/ESX host is using Intel Xeon CPUs that support Intel FlexPriority.

Environment

VMware vSphere ESXi 5.1
VMware ESX 4.1.x
VMware ESXi 4.1.x Installable
VMware ESXi 4.1.x Embedded
VMware vSphere ESXi 5.0

Resolution

This is a known issue affecting ESXi/ESX 4.1 and ESXi 5.0/5.1.

To resolve this issue, upgrade the system BIOS or firmware. For more information, review the hardware vendor's advisory or BIOS release notes:

HP customer advisory c03898077 and system ROM dated 9/8/2013 or later.
IBM RETAIN tip H21370 and UFI firmware dated August 2013 or later.
Dell BIOS 2.0.19 for Dell PowerEdge R720(-xd) systems dated 9/26/2013 or later.
Dell BIOS 2.9.0 for Dell PowerEdge R910 systems dated 9/26/2013 or later.
Dell BIOS 6.4.0 for Dell PowerEdge M610(x) systems dated 10/9/2013 or later.
Dell BIOS 2.2.2 for Dell PowerEdge R620 systems dated 03/06/2014 or later.
Cisco BIOS 2.1(3a) for Cisco UCS B-Series systems dated 09/18/2013 or later.

Note: The preceding links were correct as of May 27, 2014. If you find a link is broken, provide feedback and a VMware employee will update the link.

Workaround

To work around this issue on your version of ESXi/ESX when you cannot upgrade the BIOS on the server, install the applicable patch to disable Intel FlexPriority.

To disable Intel FlexPriority, install one of these patches:

For systems running ESXi 5.0/5.1

VMware has released a patch which prevents the failure from occurring. No failures have been observed with FlexPriority disabled. For more information, see the release notes:
- VMware ESXi 5.0, Patch ESXi500-201305401-BG: Updates esx-base (2051212)
- VMware ESXi 5.1, Patch ESXi510-201305401-BG: Updates esx-base (2051208)
Note: If the system had hyperthreading previously disabled as a workaround, re-enable it.
For systems running ESXi/ESX 4.0/4.1

VMware has released a patch which prevents the failure from occurring. No failures have been observed with FlexPriority disabled. For more information, see the release notes:
Note: If the system had hyperthreading previously disabled as a workaround, re-enable it.

Additional Information

For more information, see Interpreting an ESX/ESXi host purple diagnostic screen (1004250).

To be alerted when this document is updated, click the Subscribe to Article link in the Actions box
Interpreting an ESX/ESXi host purple diagnostic screen
VMware ESXi 5.1, Patch ESXi510-201305401-BG: Updates esx-base
VMware ESXi 5.0, Patch ESXi500-201305401-BG: Updates esx-base
VMware ESX 4.1, Patch Release ESX410-201307001
VMware ESXi 4.1, Patch Release ESXi410-201307001
VMware ESX 4.0, Patch Release ESX400-201310001
VMware ESXi 4.0, Patch Release ESXi400-201310001