kvm_intel fails to load on Conroe CPUs running Linux 4.12

kvm_intel fails to load on Conroe CPUs running Linux 4.12

[Sebastian Rachuj]

Dear linux developers,

since my upgrade from linux 4.11 to linux 4.12 the "kvm_intel" module does not load correctly anymore. "Modprobing" the kernel module gives an Input/Output error. It seems to be related to the CPU architecture and (to my knowledge) affects Conroe CPUs. I did a bisect and found the following commit as the guilty one:

commit 2c82878b0cb38fd516fd612c67852a6bbf282003
Author: Paolo Bonzini <pbonzini@redhat.com>
Date:   Mon Mar 27 14:37:28 2017 +0200

    KVM: VMX: require virtual NMI support
    
    Virtual NMIs are only missing in Prescott and Yonah chips.  Both are obsolete
    for virtualization usage---Yonah is 32-bit only even---so drop vNMI emulation.
    
    Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

Since the commit message only mentions Prescott and Yonah chips, I wanted to ask whether this commit is also intended to affect Conroe CPUs (which are probably still a bit more widespread). Do you see a solution to bring back support for Conroe chips?

Thank you for your hard work on the kernel!

Best regards,
Sebastian Rachuj

Re: kvm_intel fails to load on Conroe CPUs running Linux 4.12

[Paolo Bonzini]

On 05/08/2017 21:26, Sebastian Rachuj wrote:
> Dear linux developers,
> 
> since my upgrade from linux 4.11 to linux 4.12 the "kvm_intel" module
> does not load correctly anymore. "Modprobing" the kernel module gives an
> Input/Output error. It seems to be related to the CPU architecture and
> (to my knowledge) affects Conroe CPUs. I did a bisect and found the
> following commit as the guilty one:

What is your cpuinfo?  I tested on a Conroe Xeon X3220 (family 6,
model 15, stepping 11) when I posted that patch, and it did have virtual
NMIs.

Paolo

Re: kvm_intel fails to load on Conroe CPUs running Linux 4.12

[Sebastian Rachuj]

On 06.08.2017 23:10, Paolo Bonzini wrote:
> On 05/08/2017 21:26, Sebastian Rachuj wrote:
>> Dear linux developers,
>>
>> since my upgrade from linux 4.11 to linux 4.12 the "kvm_intel" module
>> does not load correctly anymore. "Modprobing" the kernel module gives an
>> Input/Output error. It seems to be related to the CPU architecture and
>> (to my knowledge) affects Conroe CPUs. I did a bisect and found the
>> following commit as the guilty one:
> 
> What is your cpuinfo?  I tested on a Conroe Xeon X3220 (family 6,
> model 15, stepping 11) when I posted that patch, and it did have virtual
> NMIs.

Thank you for looking into the issue. My cpuinfo is as follows:

$ cat /proc/cpuinfo
processor	: 0
vendor_id	: GenuineIntel
cpu family	: 6
model		: 15
model name	: Intel(R) Core(TM)2 CPU          6420  @ 2.13GHz
stepping	: 6
microcode	: 0xc6
cpu MHz		: 2128.000
cache size	: 4096 KB
physical id	: 0
siblings	: 2
core id		: 0
cpu cores	: 2
apicid		: 0
initial apicid	: 0
fpu		: yes
fpu_exception	: yes
cpuid level	: 10
wp		: yes
flags		: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov 
pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx lm 
constant_tsc arch_perfmon pebs bts rep_good nopl cpuid aperfmperf pni 
dtes64 monitor ds_cpl vmx est tm2 ssse3 cx16 xtpr pdcm lahf_lm 
tpr_shadow dtherm
bugs		:
bogomips	: 4275.23
clflush size	: 64
cache_alignment	: 64
address sizes	: 36 bits physical, 48 bits virtual
power management:

processor	: 1
vendor_id	: GenuineIntel
cpu family	: 6
model		: 15
model name	: Intel(R) Core(TM)2 CPU          6420  @ 2.13GHz
stepping	: 6
microcode	: 0xc6
cpu MHz		: 2128.000
cache size	: 4096 KB
physical id	: 0
siblings	: 2
core id		: 1
cpu cores	: 2
apicid		: 1
initial apicid	: 1
fpu		: yes
fpu_exception	: yes
cpuid level	: 10
wp		: yes
flags		: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov 
pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx lm 
constant_tsc arch_perfmon pebs bts rep_good nopl cpuid aperfmperf pni 
dtes64 monitor ds_cpl vmx est tm2 ssse3 cx16 xtpr pdcm lahf_lm 
tpr_shadow dtherm
bugs		:
bogomips	: 4275.05
clflush size	: 64
cache_alignment	: 64
address sizes	: 36 bits physical, 48 bits virtual
power management:

Re: kvm_intel fails to load on Conroe CPUs running Linux 4.12

[Paolo Bonzini]

[-- Attachment #1: Type: text/plain, Size: 2845 bytes --]

On 06/08/2017 23:23, Sebastian Rachuj wrote:
> On 06.08.2017 23:10, Paolo Bonzini wrote:
>> On 05/08/2017 21:26, Sebastian Rachuj wrote:
>>> Dear linux developers,
>>>
>>> since my upgrade from linux 4.11 to linux 4.12 the "kvm_intel" module
>>> does not load correctly anymore. "Modprobing" the kernel module gives an
>>> Input/Output error. It seems to be related to the CPU architecture and
>>> (to my knowledge) affects Conroe CPUs. I did a bisect and found the
>>> following commit as the guilty one:
>>
>> What is your cpuinfo?  I tested on a Conroe Xeon X3220 (family 6,
>> model 15, stepping 11) when I posted that patch, and it did have virtual
>> NMIs.
> 
> Thank you for looking into the issue. My cpuinfo is as follows:

Looks like Intel was already differentiating virtualization features
across SKUs.  Please run the attached script as root to see what other
things are different (apparently) between non-Xeon and Xeon Conroes.

Thanks,

Paolo

> $ cat /proc/cpuinfo
> processor    : 0
> vendor_id    : GenuineIntel
> cpu family    : 6
> model        : 15
> model name    : Intel(R) Core(TM)2 CPU          6420  @ 2.13GHz
> stepping    : 6
> microcode    : 0xc6
> cpu MHz        : 2128.000
> cache size    : 4096 KB
> physical id    : 0
> siblings    : 2
> core id        : 0
> cpu cores    : 2
> apicid        : 0
> initial apicid    : 0
> fpu        : yes
> fpu_exception    : yes
> cpuid level    : 10
> wp        : yes
> flags        : fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca
> cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall
> nx lm constant_tsc arch_perfmon pebs bts rep_good nopl cpuid aperfmperf
> pni dtes64 monitor ds_cpl vmx est tm2 ssse3 cx16 xtpr pdcm lahf_lm
> tpr_shadow dtherm
> bugs        :
> bogomips    : 4275.23
> clflush size    : 64
> cache_alignment    : 64
> address sizes    : 36 bits physical, 48 bits virtual
> power management:
> 
> processor    : 1
> vendor_id    : GenuineIntel
> cpu family    : 6
> model        : 15
> model name    : Intel(R) Core(TM)2 CPU          6420  @ 2.13GHz
> stepping    : 6
> microcode    : 0xc6
> cpu MHz        : 2128.000
> cache size    : 4096 KB
> physical id    : 0
> siblings    : 2
> core id        : 1
> cpu cores    : 2
> apicid        : 1
> initial apicid    : 1
> fpu        : yes
> fpu_exception    : yes
> cpuid level    : 10
> wp        : yes
> flags        : fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca
> cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall
> nx lm constant_tsc arch_perfmon pebs bts rep_good nopl cpuid aperfmperf
> pni dtes64 monitor ds_cpl vmx est tm2 ssse3 cx16 xtpr pdcm lahf_lm
> tpr_shadow dtherm
> bugs        :
> bogomips    : 4275.05
> clflush size    : 64
> cache_alignment    : 64
> address sizes    : 36 bits physical, 48 bits virtual
> power management:


[-- Attachment #2: vmxcap --]
[-- Type: text/plain, Size: 8741 bytes --]

#!/usr/bin/python
#
# tool for querying VMX capabilities
#
# Copyright 2009-2010 Red Hat, Inc.
#
# Authors:
#  Avi Kivity <avi@redhat.com>
#
# This work is licensed under the terms of the GNU GPL, version 2.  See
# the COPYING file in the top-level directory.

MSR_IA32_VMX_BASIC = 0x480
MSR_IA32_VMX_PINBASED_CTLS = 0x481
MSR_IA32_VMX_PROCBASED_CTLS = 0x482
MSR_IA32_VMX_EXIT_CTLS = 0x483
MSR_IA32_VMX_ENTRY_CTLS = 0x484
MSR_IA32_VMX_MISC_CTLS = 0x485
MSR_IA32_VMX_PROCBASED_CTLS2 = 0x48B
MSR_IA32_VMX_EPT_VPID_CAP = 0x48C
MSR_IA32_VMX_TRUE_PINBASED_CTLS = 0x48D
MSR_IA32_VMX_TRUE_PROCBASED_CTLS = 0x48E
MSR_IA32_VMX_TRUE_EXIT_CTLS = 0x48F
MSR_IA32_VMX_TRUE_ENTRY_CTLS = 0x490
MSR_IA32_VMX_VMFUNC = 0x491

class msr(object):
    def __init__(self):
        try:
            self.f = open('/dev/cpu/0/msr', 'rb', 0)
        except:
            self.f = open('/dev/msr0', 'rb', 0)
    def read(self, index, default = None):
        import struct
        self.f.seek(index)
        try:
            return struct.unpack('Q', self.f.read(8))[0]
        except:
            return default

class Control(object):
    def __init__(self, name, bits, cap_msr, true_cap_msr = None):
        self.name = name
        self.bits = bits
        self.cap_msr = cap_msr
        self.true_cap_msr = true_cap_msr
    def read2(self, nr):
        m = msr()
        val = m.read(nr, 0)
        return (val & 0xffffffff, val >> 32)
    def show(self):
        print(self.name)
        mbz, mb1 = self.read2(self.cap_msr)
        tmbz, tmb1 = 0, 0
        if self.true_cap_msr:
            tmbz, tmb1 = self.read2(self.true_cap_msr)
        for bit in sorted(self.bits.keys()):
            zero = not (mbz & (1 << bit))
            one = mb1 & (1 << bit)
            true_zero = not (tmbz & (1 << bit))
            true_one = tmb1 & (1 << bit)
            s= '?'
            if (self.true_cap_msr and true_zero and true_one
                and one and not zero):
                s = 'default'
            elif zero and not one:
                s = 'no'
            elif one and not zero:
                s = 'forced'
            elif one and zero:
                s = 'yes'
            print('  %-40s %s' % (self.bits[bit], s))

class Misc(object):
    def __init__(self, name, bits, msr):
        self.name = name
        self.bits = bits
        self.msr = msr
    def show(self):
        print(self.name)
        value = msr().read(self.msr, 0)
        print('  Hex: 0x%x' % (value))
        def first_bit(key):
            if type(key) is tuple:
                return key[0]
            else:
                return key
        for bits in sorted(self.bits.keys(), key = first_bit):
            if type(bits) is tuple:
                lo, hi = bits
                fmt = int
            else:
                lo = hi = bits
                def fmt(x):
                    return { True: 'yes', False: 'no' }[x]
            v = (value >> lo) & ((1 << (hi - lo + 1)) - 1)
            print('  %-40s %s' % (self.bits[bits], fmt(v)))

controls = [
    Misc(
        name = 'Basic VMX Information',
        bits = {
            (0, 30): 'Revision',
            (32,44): 'VMCS size',
            48: 'VMCS restricted to 32 bit addresses',
            49: 'Dual-monitor support',
            (50, 53): 'VMCS memory type',
            54: 'INS/OUTS instruction information',
            55: 'IA32_VMX_TRUE_*_CTLS support',
            },
        msr = MSR_IA32_VMX_BASIC,
        ),
    Control(
        name = 'pin-based controls',
        bits = {
            0: 'External interrupt exiting',
            3: 'NMI exiting',
            5: 'Virtual NMIs',
            6: 'Activate VMX-preemption timer',
            7: 'Process posted interrupts',
            },
        cap_msr = MSR_IA32_VMX_PINBASED_CTLS,
        true_cap_msr = MSR_IA32_VMX_TRUE_PINBASED_CTLS,
        ),

    Control(
        name = 'primary processor-based controls',
        bits = {
            2: 'Interrupt window exiting',
            3: 'Use TSC offsetting',
            7: 'HLT exiting',
            9: 'INVLPG exiting',
            10: 'MWAIT exiting',
            11: 'RDPMC exiting',
            12: 'RDTSC exiting',
            15: 'CR3-load exiting',
            16: 'CR3-store exiting',
            19: 'CR8-load exiting',
            20: 'CR8-store exiting',
            21: 'Use TPR shadow',
            22: 'NMI-window exiting',
            23: 'MOV-DR exiting',
            24: 'Unconditional I/O exiting',
            25: 'Use I/O bitmaps',
            27: 'Monitor trap flag',
            28: 'Use MSR bitmaps',
            29: 'MONITOR exiting',
            30: 'PAUSE exiting',
            31: 'Activate secondary control',
            },
        cap_msr = MSR_IA32_VMX_PROCBASED_CTLS,
        true_cap_msr = MSR_IA32_VMX_TRUE_PROCBASED_CTLS,
        ),

    Control(
        name = 'secondary processor-based controls',
        bits = {
            0: 'Virtualize APIC accesses',
            1: 'Enable EPT',
            2: 'Descriptor-table exiting',
            3: 'Enable RDTSCP',
            4: 'Virtualize x2APIC mode',
            5: 'Enable VPID',
            6: 'WBINVD exiting',
            7: 'Unrestricted guest',
            8: 'APIC register emulation',
            9: 'Virtual interrupt delivery',
            10: 'PAUSE-loop exiting',
            11: 'RDRAND exiting',
            12: 'Enable INVPCID',
            13: 'Enable VM functions',
            14: 'VMCS shadowing',
            15: 'Enable ENCLS exiting',
            16: 'RDSEED exiting',
            17: 'Enable PML',
            18: 'EPT-violation #VE',
            19: 'Conceal non-root operation from PT',
            20: 'Enable XSAVES/XRSTORS',
            22: 'Mode-based execute control (XS/XU)',
            25: 'TSC scaling',
            },
        cap_msr = MSR_IA32_VMX_PROCBASED_CTLS2,
        ),

    Control(
        name = 'VM-Exit controls',
        bits = {
            2: 'Save debug controls',
            9: 'Host address-space size',
            12: 'Load IA32_PERF_GLOBAL_CTRL',
            15: 'Acknowledge interrupt on exit',
            18: 'Save IA32_PAT',
            19: 'Load IA32_PAT',
            20: 'Save IA32_EFER',
            21: 'Load IA32_EFER',
            22: 'Save VMX-preemption timer value',
            23: 'Clear IA32_BNDCFGS',
            24: 'Conceal VM exits from PT',
            },
        cap_msr = MSR_IA32_VMX_EXIT_CTLS,
        true_cap_msr = MSR_IA32_VMX_TRUE_EXIT_CTLS,
        ),

    Control(
        name = 'VM-Entry controls',
        bits = {
            2: 'Load debug controls',
            9: 'IA-32e mode guest',
            10: 'Entry to SMM',
            11: 'Deactivate dual-monitor treatment',
            13: 'Load IA32_PERF_GLOBAL_CTRL',
            14: 'Load IA32_PAT',
            15: 'Load IA32_EFER',
            16: 'Load IA32_BNDCFGS',
            17: 'Conceal VM entries from PT',
            },
        cap_msr = MSR_IA32_VMX_ENTRY_CTLS,
        true_cap_msr = MSR_IA32_VMX_TRUE_ENTRY_CTLS,
        ),

    Misc(
        name = 'Miscellaneous data',
        bits = {
            (0,4): 'VMX-preemption timer scale (log2)',
            5: 'Store EFER.LMA into IA-32e mode guest control',
            6: 'HLT activity state',
            7: 'Shutdown activity state',
            8: 'Wait-for-SIPI activity state',
            15: 'IA32_SMBASE support',
            (16,24): 'Number of CR3-target values',
            (25,27): 'MSR-load/store count recommendation',
            28: 'IA32_SMM_MONITOR_CTL[2] can be set to 1',
            29: 'VMWRITE to VM-exit information fields',
            30: 'Inject event with insn length=0',
            (32,63): 'MSEG revision identifier',
            },
        msr = MSR_IA32_VMX_MISC_CTLS,
        ),

    Misc(
        name = 'VPID and EPT capabilities',
        bits = {
            0: 'Execute-only EPT translations',
            6: 'Page-walk length 4',
            8: 'Paging-structure memory type UC',
            14: 'Paging-structure memory type WB',
            16: '2MB EPT pages',
            17: '1GB EPT pages',
            20: 'INVEPT supported',
            21: 'EPT accessed and dirty flags',
            25: 'Single-context INVEPT',
            26: 'All-context INVEPT',
            32: 'INVVPID supported',
            40: 'Individual-address INVVPID',
            41: 'Single-context INVVPID',
            42: 'All-context INVVPID',
            43: 'Single-context-retaining-globals INVVPID',
            },
        msr = MSR_IA32_VMX_EPT_VPID_CAP,
        ),
    Misc(
        name = 'VM Functions',
        bits = {
            0: 'EPTP Switching',
            },
        msr = MSR_IA32_VMX_VMFUNC,
        ),
    ]

for c in controls:
    c.show()

Re: kvm_intel fails to load on Conroe CPUs running Linux 4.12

[Nadav Amit]

Paolo Bonzini <pbonzini@redhat.com> wrote:

> On 06/08/2017 23:23, Sebastian Rachuj wrote:
>> On 06.08.2017 23:10, Paolo Bonzini wrote:
>>> On 05/08/2017 21:26, Sebastian Rachuj wrote:
>>>> Dear linux developers,
>>>> 
>>>> since my upgrade from linux 4.11 to linux 4.12 the "kvm_intel" module
>>>> does not load correctly anymore. "Modprobing" the kernel module gives an
>>>> Input/Output error. It seems to be related to the CPU architecture and
>>>> (to my knowledge) affects Conroe CPUs. I did a bisect and found the
>>>> following commit as the guilty one:
>>> 
>>> What is your cpuinfo?  I tested on a Conroe Xeon X3220 (family 6,
>>> model 15, stepping 11) when I posted that patch, and it did have virtual
>>> NMIs.
>> 
>> Thank you for looking into the issue. My cpuinfo is as follows:
> 
> Looks like Intel was already differentiating virtualization features
> across SKUs.  Please run the attached script as root to see what other
> things are different (apparently) between non-Xeon and Xeon Conroes.

There may be another explanation. If I remember correctly from my days in
Intel, Intel initially sold CMWA (Conroe) B-step. The next step, E-step,
introduced a couple of new features, which may have included vNMI.

The CPU of Sebastian appears to be B1 according to cpuinfo.

Nadav

Re: kvm_intel fails to load on Conroe CPUs running Linux 4.12

[Sebastian Rachuj]

On 07.08.2017 11:43, Paolo Bonzini wrote:
> On 06/08/2017 23:23, Sebastian Rachuj wrote:
>> On 06.08.2017 23:10, Paolo Bonzini wrote:
>>> On 05/08/2017 21:26, Sebastian Rachuj wrote:
>>>> Dear linux developers,
>>>>
>>>> since my upgrade from linux 4.11 to linux 4.12 the "kvm_intel" module
>>>> does not load correctly anymore. "Modprobing" the kernel module gives an
>>>> Input/Output error. It seems to be related to the CPU architecture and
>>>> (to my knowledge) affects Conroe CPUs. I did a bisect and found the
>>>> following commit as the guilty one:
>>>
>>> What is your cpuinfo?  I tested on a Conroe Xeon X3220 (family 6,
>>> model 15, stepping 11) when I posted that patch, and it did have virtual
>>> NMIs.
>>
>> Thank you for looking into the issue. My cpuinfo is as follows:
> 
> Looks like Intel was already differentiating virtualization features
> across SKUs.  Please run the attached script as root to see what other
> things are different (apparently) between non-Xeon and Xeon Conroes.

Here you are, I hope it helps:

# python vmxcap
Basic VMX Information
   Hex: 0x1a040000000007
   Revision                                 7
   VMCS size                                1024
   VMCS restricted to 32 bit addresses      no
   Dual-monitor support                     yes
   VMCS memory type                         6
   INS/OUTS instruction information         no
   IA32_VMX_TRUE_*_CTLS support             no
pin-based controls
   External interrupt exiting               yes
   NMI exiting                              yes
   Virtual NMIs                             no
   Activate VMX-preemption timer            no
   Process posted interrupts                no
primary processor-based controls
   Interrupt window exiting                 yes
   Use TSC offsetting                       yes
   HLT exiting                              yes
   INVLPG exiting                           yes
   MWAIT exiting                            yes
   RDPMC exiting                            yes
   RDTSC exiting                            yes
   CR3-load exiting                         forced
   CR3-store exiting                        forced
   CR8-load exiting                         yes
   CR8-store exiting                        yes
   Use TPR shadow                           yes
   NMI-window exiting                       no
   MOV-DR exiting                           yes
   Unconditional I/O exiting                yes
   Use I/O bitmaps                          yes
   Monitor trap flag                        no
   Use MSR bitmaps                          yes
   MONITOR exiting                          yes
   PAUSE exiting                            yes
   Activate secondary control               no
secondary processor-based controls
   Virtualize APIC accesses                 no
   Enable EPT                               no
   Descriptor-table exiting                 no
   Enable RDTSCP                            no
   Virtualize x2APIC mode                   no
   Enable VPID                              no
   WBINVD exiting                           no
   Unrestricted guest                       no
   APIC register emulation                  no
   Virtual interrupt delivery               no
   PAUSE-loop exiting                       no
   RDRAND exiting                           no
   Enable INVPCID                           no
   Enable VM functions                      no
   VMCS shadowing                           no
   Enable ENCLS exiting                     no
   RDSEED exiting                           no
   Enable PML                               no
   EPT-violation #VE                        no
   Conceal non-root operation from PT       no
   Enable XSAVES/XRSTORS                    no
   Mode-based execute control (XS/XU)       no
   TSC scaling                              no
VM-Exit controls
   Save debug controls                      forced
   Host address-space size                  yes
   Load IA32_PERF_GLOBAL_CTRL               no
   Acknowledge interrupt on exit            yes
   Save IA32_PAT                            no
   Load IA32_PAT                            no
   Save IA32_EFER                           no
   Load IA32_EFER                           no
   Save VMX-preemption timer value          no
   Clear IA32_BNDCFGS                       no
   Conceal VM exits from PT                 no
VM-Entry controls
   Load debug controls                      forced
   IA-32e mode guest                        yes
   Entry to SMM                             yes
   Deactivate dual-monitor treatment        yes
   Load IA32_PERF_GLOBAL_CTRL               no
   Load IA32_PAT                            no
   Load IA32_EFER                           no
   Load IA32_BNDCFGS                        no
   Conceal VM entries from PT               no
Miscellaneous data
   Hex: 0x403c0
   VMX-preemption timer scale (log2)        0
   Store EFER.LMA into IA-32e mode guest control no
   HLT activity state                       yes
   Shutdown activity state                  yes
   Wait-for-SIPI activity state             yes
   IA32_SMBASE support                      no
   Number of CR3-target values              4
   MSR-load/store count recommendation      0
   IA32_SMM_MONITOR_CTL[2] can be set to 1  no
   VMWRITE to VM-exit information fields    no
   Inject event with insn length=0          no
   MSEG revision identifier                 0
VPID and EPT capabilities
   Hex: 0x0
   Execute-only EPT translations            no
   Page-walk length 4                       no
   Paging-structure memory type UC          no
   Paging-structure memory type WB          no
   2MB EPT pages                            no
   1GB EPT pages                            no
   INVEPT supported                         no
   EPT accessed and dirty flags             no
   Single-context INVEPT                    no
   All-context INVEPT                       no
   INVVPID supported                        no
   Individual-address INVVPID               no
   Single-context INVVPID                   no
   All-context INVVPID                      no
   Single-context-retaining-globals INVVPID no
VM Functions
   Hex: 0x0
   EPTP Switching                           no

Re: kvm_intel fails to load on Conroe CPUs running Linux 4.12

[Paolo Bonzini]

On 07/08/2017 19:17, Sebastian Rachuj wrote:
>>>
>>> Thank you for looking into the issue. My cpuinfo is as follows:
>>
>> Looks like Intel was already differentiating virtualization features
>> across SKUs.  Please run the attached script as root to see what other
>> things are different (apparently) between non-Xeon and Xeon Conroes.
> 
> Here you are, I hope it helps:

Not much to say, unfortunately.  It's pretty much the same capabilities
as a Prescott/Cedar Mill processor, except that it has MSR bitmaps.  It
also lacks FlexPriority compared to the Conroe I had checked.

It's not great that even the revert patch doesn't apply cleanly---this
is *not* necessarily a boring area of the hypervisor...

Given the rarity of your machine I'm currently leaning towards _not_
reverting the change.  I'll check another non-Xeon Core 2 tomorrow that
is from December 2008 (IIRC).  If that one also lacks vNMI, or if I get
other reports, I suppose I will have to reconsider that.

Paolo

Re: kvm_intel fails to load on Conroe CPUs running Linux 4.12

[Sebastian Rachuj]

On 07.08.2017 19:50, Paolo Bonzini wrote:
> On 07/08/2017 19:17, Sebastian Rachuj wrote:
>>>>
>>>> Thank you for looking into the issue. My cpuinfo is as follows:
>>>
>>> Looks like Intel was already differentiating virtualization features
>>> across SKUs.  Please run the attached script as root to see what other
>>> things are different (apparently) between non-Xeon and Xeon Conroes.
>>
>> Here you are, I hope it helps:
> 
> Not much to say, unfortunately.  It's pretty much the same capabilities
> as a Prescott/Cedar Mill processor, except that it has MSR bitmaps.  It
> also lacks FlexPriority compared to the Conroe I had checked.
> 
> It's not great that even the revert patch doesn't apply cleanly---this
> is *not* necessarily a boring area of the hypervisor...
> 
> Given the rarity of your machine I'm currently leaning towards _not_
> reverting the change.  I'll check another non-Xeon Core 2 tomorrow that
> is from December 2008 (IIRC).  If that one also lacks vNMI, or if I get
> other reports, I suppose I will have to reconsider that.

That's unfortunate to hear. Just for completeness, I want to mention a 
thread in the Archlinux forum, I created, where two other people (Sadar 
and losko) also complained about not working KVM [1]. Additionally, 
Linux 4.12 has not reached yet reached distributions with a greater 
amount of users.

If supporting these chips is too much of a hassle, I will probably have 
to buy a new CPU to enjoy KVM support with a current linux kernel.

Anyway, thanks again for figuring this out!


[1]: https://bbs.archlinux.org/viewtopic.php?id=228645

Re: Re: kvm_intel fails to load on Conroe CPUs running Linux 4.12

[Niall Walsh]

[-- Attachment #1: Type: text/plain, Size: 530 bytes --]

Hi,

On 07/08/17 18:50, Paolo Bonzini wrote:
> Given the rarity of your machine I'm currently leaning towards _not_
> reverting the change.  I'll check another non-Xeon Core 2 tomorrow that
> is from December 2008 (IIRC).  If that one also lacks vNMI, or if I get
> other reports, I suppose I will have to reconsider that.

afraid I've the same issue with 4.12, kvm_intel doesn't load and won't 
(but does on 4.11) on my Dell XPS M1210 with a Core 2 Duo T7200 from 
April 2007.

cpuinfo and vmxcap output attached

Thanks,

Niall

[-- Attachment #2: cpuinfo --]
[-- Type: text/plain, Size: 1544 bytes --]

processor	: 0
vendor_id	: GenuineIntel
cpu family	: 6
model		: 15
model name	: Intel(R) Core(TM)2 CPU         T7200  @ 2.00GHz
stepping	: 6
microcode	: 0xc7
cpu MHz		: 1000.000
cache size	: 4096 KB
physical id	: 0
siblings	: 2
core id		: 0
cpu cores	: 2
apicid		: 0
initial apicid	: 0
fpu		: yes
fpu_exception	: yes
cpuid level	: 10
wp		: yes
flags		: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx lm constant_tsc arch_perfmon pebs bts rep_good nopl cpuid aperfmperf pni dtes64 monitor ds_cpl vmx est tm2 ssse3 cx16 xtpr pdcm lahf_lm tpr_shadow dtherm
bugs		:
bogomips	: 3994.63
clflush size	: 64
cache_alignment	: 64
address sizes	: 36 bits physical, 48 bits virtual
power management:

processor	: 1
vendor_id	: GenuineIntel
cpu family	: 6
model		: 15
model name	: Intel(R) Core(TM)2 CPU         T7200  @ 2.00GHz
stepping	: 6
microcode	: 0xc7
cpu MHz		: 1000.000
cache size	: 4096 KB
physical id	: 0
siblings	: 2
core id		: 1
cpu cores	: 2
apicid		: 1
initial apicid	: 1
fpu		: yes
fpu_exception	: yes
cpuid level	: 10
wp		: yes
flags		: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx lm constant_tsc arch_perfmon pebs bts rep_good nopl cpuid aperfmperf pni dtes64 monitor ds_cpl vmx est tm2 ssse3 cx16 xtpr pdcm lahf_lm tpr_shadow dtherm
bugs		:
bogomips	: 3994.45
clflush size	: 64
cache_alignment	: 64
address sizes	: 36 bits physical, 48 bits virtual
power management:


[-- Attachment #3: vmxcap.out --]
[-- Type: text/plain, Size: 5091 bytes --]

Basic VMX Information
  Hex: 0x1a040000000007
  Revision                                 7
  VMCS size                                1024
  VMCS restricted to 32 bit addresses      no
  Dual-monitor support                     yes
  VMCS memory type                         6
  INS/OUTS instruction information         no
  IA32_VMX_TRUE_*_CTLS support             no
pin-based controls
  External interrupt exiting               yes
  NMI exiting                              yes
  Virtual NMIs                             no
  Activate VMX-preemption timer            no
  Process posted interrupts                no
primary processor-based controls
  Interrupt window exiting                 yes
  Use TSC offsetting                       yes
  HLT exiting                              yes
  INVLPG exiting                           yes
  MWAIT exiting                            yes
  RDPMC exiting                            yes
  RDTSC exiting                            yes
  CR3-load exiting                         forced
  CR3-store exiting                        forced
  CR8-load exiting                         yes
  CR8-store exiting                        yes
  Use TPR shadow                           yes
  NMI-window exiting                       no
  MOV-DR exiting                           yes
  Unconditional I/O exiting                yes
  Use I/O bitmaps                          yes
  Monitor trap flag                        no
  Use MSR bitmaps                          yes
  MONITOR exiting                          yes
  PAUSE exiting                            yes
  Activate secondary control               no
secondary processor-based controls
  Virtualize APIC accesses                 no
  Enable EPT                               no
  Descriptor-table exiting                 no
  Enable RDTSCP                            no
  Virtualize x2APIC mode                   no
  Enable VPID                              no
  WBINVD exiting                           no
  Unrestricted guest                       no
  APIC register emulation                  no
  Virtual interrupt delivery               no
  PAUSE-loop exiting                       no
  RDRAND exiting                           no
  Enable INVPCID                           no
  Enable VM functions                      no
  VMCS shadowing                           no
  Enable ENCLS exiting                     no
  RDSEED exiting                           no
  Enable PML                               no
  EPT-violation #VE                        no
  Conceal non-root operation from PT       no
  Enable XSAVES/XRSTORS                    no
  Mode-based execute control (XS/XU)       no
  TSC scaling                              no
VM-Exit controls
  Save debug controls                      forced
  Host address-space size                  yes
  Load IA32_PERF_GLOBAL_CTRL               no
  Acknowledge interrupt on exit            yes
  Save IA32_PAT                            no
  Load IA32_PAT                            no
  Save IA32_EFER                           no
  Load IA32_EFER                           no
  Save VMX-preemption timer value          no
  Clear IA32_BNDCFGS                       no
  Conceal VM exits from PT                 no
VM-Entry controls
  Load debug controls                      forced
  IA-32e mode guest                        yes
  Entry to SMM                             yes
  Deactivate dual-monitor treatment        yes
  Load IA32_PERF_GLOBAL_CTRL               no
  Load IA32_PAT                            no
  Load IA32_EFER                           no
  Load IA32_BNDCFGS                        no
  Conceal VM entries from PT               no
Miscellaneous data
  Hex: 0x403c0
  VMX-preemption timer scale (log2)        0
  Store EFER.LMA into IA-32e mode guest control no
  HLT activity state                       yes
  Shutdown activity state                  yes
  Wait-for-SIPI activity state             yes
  IA32_SMBASE support                      no
  Number of CR3-target values              4
  MSR-load/store count recommendation      0
  IA32_SMM_MONITOR_CTL[2] can be set to 1  no
  VMWRITE to VM-exit information fields    no
  Inject event with insn length=0          no
  MSEG revision identifier                 0
VPID and EPT capabilities
  Hex: 0x0
  Execute-only EPT translations            no
  Page-walk length 4                       no
  Paging-structure memory type UC          no
  Paging-structure memory type WB          no
  2MB EPT pages                            no
  1GB EPT pages                            no
  INVEPT supported                         no
  EPT accessed and dirty flags             no
  Single-context INVEPT                    no
  All-context INVEPT                       no
  INVVPID supported                        no
  Individual-address INVVPID               no
  Single-context INVVPID                   no
  All-context INVVPID                      no
  Single-context-retaining-globals INVVPID no
VM Functions
  Hex: 0x0
  EPTP Switching                           no

Re: kvm_intel fails to load on Conroe CPUs running Linux 4.12

[Gerhard Wiesinger]

On 17.08.2017 22:58, Gerhard Wiesinger wrote:
 >
 > On 07.08.2017 19:50, Paolo Bonzini wrote:
 >
 > >Not much to say, unfortunately. It's pretty much the same capabilities
 > >as a Prescott/Cedar Mill processor, except that it has MSR bitmaps. It
 > >also lacks FlexPriority compared to the Conroe I had checked.
 > >
 > >It's not great that even the revert patch doesn't apply cleanly---this
 > >is *not* necessarily a boring area of the hypervisor...
 > >
 > >Given the rarity of your machine I'm currently leaning towards _not_
 > >reverting the change. I'll check another non-Xeon Core 2 tomorrow that
 > >is from December 2008 (IIRC). If that one also lacks vNMI, or if I get
 > >other reports, I suppose I will have to reconsider that.

Hello Paolo,

Can you please revert the patch.

CPU is a Core 2 Extreme QX6700: SL9UL (B3) running VERY stable with ECC 
RAM for years now.
https://ark.intel.com/products/28028/Intel-Core2-Extreme-Processor-QX6700-8M-Cache-2_66-GHz-1066-MHz-FSB?q=Core%202%20Extreme%20QX6700
https://en.wikipedia.org/wiki/List_of_Intel_Core_2_microprocessors

CPU details below.

Thank you.

Ciao,
Gerhard

cat /proc/cpuinfo
processor       : 0
vendor_id       : GenuineIntel
cpu family      : 6
model           : 15
model name      : Intel(R) Core(TM)2 Quad CPU           @ 2.66GHz
stepping        : 7
microcode       : 0x6a
cpu MHz         : 1596.000
cache size      : 4096 KB
physical id     : 0
siblings        : 4
core id         : 0
cpu cores       : 4
apicid          : 0
initial apicid  : 0
fpu             : yes
fpu_exception   : yes
cpuid level     : 10
wp              : yes
flags           : fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge 
mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe 
syscall nx lm constant_tsc arch_perfmon pebs bts rep_good nopl cpuid
aperfmperf pni dtes64 monitor ds_cpl vmx est tm2 ssse3 cx16 xtpr pdcm 
lahf_lm tpr_shadow dtherm
bugs            :
bogomips        : 5333.45
clflush size    : 64
cache_alignment : 64
address sizes   : 36 bits physical, 48 bits virtual
power management:

Script output:
Basic VMX Information
   Hex: 0x1a040000000007
   Revision                                 7
   VMCS size                                1024
   VMCS restricted to 32 bit addresses      no
   Dual-monitor support                     yes
   VMCS memory type                         6
   INS/OUTS instruction information         no
   IA32_VMX_TRUE_*_CTLS support             no
pin-based controls
   External interrupt exiting               yes
   NMI exiting                              yes
   Virtual NMIs                             no
   Activate VMX-preemption timer            no
   Process posted interrupts                no
primary processor-based controls
   Interrupt window exiting                 yes
   Use TSC offsetting                       yes
   HLT exiting                              yes
   INVLPG exiting                           yes
   MWAIT exiting                            yes
   RDPMC exiting                            yes
   RDTSC exiting                            yes
   CR3-load exiting                         forced
   CR3-store exiting                        forced
   CR8-load exiting                         yes
   CR8-store exiting                        yes
   Use TPR shadow                           yes
   NMI-window exiting                       no
   MOV-DR exiting                           yes
   Unconditional I/O exiting                yes
   Use I/O bitmaps                          yes
   Monitor trap flag                        no
   Use MSR bitmaps                          yes
   MONITOR exiting                          yes
   PAUSE exiting                            yes
   Activate secondary control               no
secondary processor-based controls
   Virtualize APIC accesses                 no
   Enable EPT                               no
   Descriptor-table exiting                 no
   Enable RDTSCP                            no
   Virtualize x2APIC mode                   no
   Enable VPID                              no
   WBINVD exiting                           no
   Unrestricted guest                       no
   APIC register emulation                  no
   Virtual interrupt delivery               no
   PAUSE-loop exiting                       no
   RDRAND exiting                           no
   Enable INVPCID                           no
   Enable VM functions                      no
   VMCS shadowing                           no
   Enable ENCLS exiting                     no
   RDSEED exiting                           no
   Enable PML                               no
   EPT-violation #VE                        no
   Conceal non-root operation from PT       no
   Enable XSAVES/XRSTORS                    no
   Mode-based execute control (XS/XU)       no
   TSC scaling                              no
VM-Exit controls
   Save debug controls                      forced
   Host address-space size                  yes
   Load IA32_PERF_GLOBAL_CTRL               no
   Acknowledge interrupt on exit            yes
   Save IA32_PAT                            no
   Load IA32_PAT                            no
   Save IA32_EFER                           no
   Load IA32_EFER                           no
   Save VMX-preemption timer value          no
   Clear IA32_BNDCFGS                       no
   Conceal VM exits from PT                 no
VM-Entry controls
   Load debug controls                      forced
   IA-32e mode guest                        yes
   Entry to SMM                             yes
   Deactivate dual-monitor treatment        yes
   Load IA32_PERF_GLOBAL_CTRL               no
   Load IA32_PAT                            no
   Load IA32_EFER                           no
   Load IA32_BNDCFGS                        no
   Conceal VM entries from PT               no
Miscellaneous data
   Hex: 0x403c0
   VMX-preemption timer scale (log2)        0
   Store EFER.LMA into IA-32e mode guest control no
   HLT activity state                       yes
   Shutdown activity state                  yes
   Wait-for-SIPI activity state             yes
   IA32_SMBASE support                      no
   Number of CR3-target values              4
   MSR-load/store count recommendation      0
   IA32_SMM_MONITOR_CTL[2] can be set to 1  no
   VMWRITE to VM-exit information fields    no
   Inject event with insn length=0          no
   MSEG revision identifier                 0
VPID and EPT capabilities
   Hex: 0x0
   Execute-only EPT translations            no
   Page-walk length 4                       no
   Paging-structure memory type UC          no
   Paging-structure memory type WB          no
   2MB EPT pages                            no
   1GB EPT pages                            no
   INVEPT supported                         no
   EPT accessed and dirty flags             no
   Single-context INVEPT                    no
   All-context INVEPT                       no
   INVVPID supported                        no
   Individual-address INVVPID               no
   Single-context INVVPID                   no
   All-context INVVPID                      no
   Single-context-retaining-globals INVVPID no
VM Functions
   Hex: 0x0
   EPTP Switching                           no