All of lore.kernel.org
 help / color / mirror / Atom feed
* PROBLEM: lk 4.5 oops on boot with Xeon D-1520
@ 2016-02-17 22:51 Tony Battersby
  2016-02-24  9:11 ` Thomas Gleixner
  0 siblings, 1 reply; 7+ messages in thread
From: Tony Battersby @ 2016-02-17 22:51 UTC (permalink / raw)
  To: Kan Liang, Peter Zijlstra (Intel),
	Arnaldo Carvalho de Melo, Jiri Olsa, Stephane Eranian,
	Thomas Gleixner, Vince Weaver, Ingo Molnar, linux-kernel

The following commit in 4.5 is causing a general protection fault during
early boot:

d6980ef32570 ("perf/x86/intel/uncore: Add Broadwell-EP uncore support")

With the commit reverted, the system boots fine.

CPU:         Intel(R) Xeon(R) CPU D-1520 @ 2.20GHz
Motherboard: Supermicro X10SDV-4C-TLN2F

The general protection fault occurs when
hswep_uncore_sbox_msr_init_box() calls wrmsrl().  I added a printk to
get the following values just before the oops:

box->pmu->type->box_ctl     = 1824
box->pmu->pmu_idx           = 0
box->pmu->type->msr_offset  = 10
box->pmu->type->msr_offsets = NULL
msr                         = 1824
(all values are decimal)

Here is the call trace:
  hswep_uncore_sbox_msr_init_box+0x7c/0xc0 (RIP)
  uncore_cpu_starting+0x8a/0x1c0
  ? uncore_change_context+0xe5/0x150
  ? uncore_types_init+0x1d6/0x1d6
  uncore_cpu_setup+0x10/0x12
  on_each_cpu+0x32/0x50
  intel_uncore_init+0x2e8/0x36d
  ? cstate_pmu_init+0x14f/0x195
  ? uncore_cpu_setup+0x12/0x12

I have a jpg image of the monitor displaying the full oops; let me know
if anyone wants that.

----------

/proc/cpuinfo:

processor    : 0
vendor_id    : GenuineIntel
cpu family    : 6
model        : 86
model name    : Intel(R) Xeon(R) CPU D-1520 @ 2.20GHz
stepping    : 2
microcode    : 0xa
cpu MHz        : 2200.000
tsc MHz        : 2199.998
cache size    : 6144 KB
physical id    : 0
siblings    : 8
core id        : 0
cpu cores    : 4
apicid        : 0
initial apicid    : 0
fpu        : yes
fpu_exception    : yes
cpuid level    : 20
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 pdpe1gb rdtscp lm constant_tsc arch_perfmon pebs bts rep_good nopl
xtopology nonstop_tsc aperfmperf eagerfpu pni pclmulqdq dtes64 monitor
ds_cpl vmx smx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid dca sse4_1
sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand
lahf_lm abm 3dnowprefetch epb intel_pt tpr_shadow vnmi flexpriority ept
vpid fsgsbase tsc_adjust bmi1 hle avx2 smep bmi2 erms invpcid rtm cqm
rdseed adx smap xsaveopt cqm_llc cqm_occup_llc dtherm arat pln pts
bugs        :
bogomips    : 4399.57
clflush size    : 64
cache_alignment    : 64
address sizes    : 46 bits physical, 48 bits virtual
power management:

processor    : 1
vendor_id    : GenuineIntel
cpu family    : 6
model        : 86
model name    : Intel(R) Xeon(R) CPU D-1520 @ 2.20GHz
stepping    : 2
microcode    : 0xa
cpu MHz        : 2200.000
tsc MHz        : 2199.998
cache size    : 6144 KB
physical id    : 0
siblings    : 8
core id        : 1
cpu cores    : 4
apicid        : 2
initial apicid    : 2
fpu        : yes
fpu_exception    : yes
cpuid level    : 20
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 pdpe1gb rdtscp lm constant_tsc arch_perfmon pebs bts rep_good nopl
xtopology nonstop_tsc aperfmperf eagerfpu pni pclmulqdq dtes64 monitor
ds_cpl vmx smx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid dca sse4_1
sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand
lahf_lm abm 3dnowprefetch epb intel_pt tpr_shadow vnmi flexpriority ept
vpid fsgsbase tsc_adjust bmi1 hle avx2 smep bmi2 erms invpcid rtm cqm
rdseed adx smap xsaveopt cqm_llc cqm_occup_llc dtherm arat pln pts
bugs        :
bogomips    : 4399.57
clflush size    : 64
cache_alignment    : 64
address sizes    : 46 bits physical, 48 bits virtual
power management:

processor    : 2
vendor_id    : GenuineIntel
cpu family    : 6
model        : 86
model name    : Intel(R) Xeon(R) CPU D-1520 @ 2.20GHz
stepping    : 2
microcode    : 0xa
cpu MHz        : 2200.000
tsc MHz        : 2199.998
cache size    : 6144 KB
physical id    : 0
siblings    : 8
core id        : 2
cpu cores    : 4
apicid        : 4
initial apicid    : 4
fpu        : yes
fpu_exception    : yes
cpuid level    : 20
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 pdpe1gb rdtscp lm constant_tsc arch_perfmon pebs bts rep_good nopl
xtopology nonstop_tsc aperfmperf eagerfpu pni pclmulqdq dtes64 monitor
ds_cpl vmx smx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid dca sse4_1
sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand
lahf_lm abm 3dnowprefetch epb intel_pt tpr_shadow vnmi flexpriority ept
vpid fsgsbase tsc_adjust bmi1 hle avx2 smep bmi2 erms invpcid rtm cqm
rdseed adx smap xsaveopt cqm_llc cqm_occup_llc dtherm arat pln pts
bugs        :
bogomips    : 4399.57
clflush size    : 64
cache_alignment    : 64
address sizes    : 46 bits physical, 48 bits virtual
power management:

processor    : 3
vendor_id    : GenuineIntel
cpu family    : 6
model        : 86
model name    : Intel(R) Xeon(R) CPU D-1520 @ 2.20GHz
stepping    : 2
microcode    : 0xa
cpu MHz        : 2200.000
tsc MHz        : 2199.998
cache size    : 6144 KB
physical id    : 0
siblings    : 8
core id        : 3
cpu cores    : 4
apicid        : 6
initial apicid    : 6
fpu        : yes
fpu_exception    : yes
cpuid level    : 20
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 pdpe1gb rdtscp lm constant_tsc arch_perfmon pebs bts rep_good nopl
xtopology nonstop_tsc aperfmperf eagerfpu pni pclmulqdq dtes64 monitor
ds_cpl vmx smx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid dca sse4_1
sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand
lahf_lm abm 3dnowprefetch epb intel_pt tpr_shadow vnmi flexpriority ept
vpid fsgsbase tsc_adjust bmi1 hle avx2 smep bmi2 erms invpcid rtm cqm
rdseed adx smap xsaveopt cqm_llc cqm_occup_llc dtherm arat pln pts
bugs        :
bogomips    : 4399.57
clflush size    : 64
cache_alignment    : 64
address sizes    : 46 bits physical, 48 bits virtual
power management:

processor    : 4
vendor_id    : GenuineIntel
cpu family    : 6
model        : 86
model name    : Intel(R) Xeon(R) CPU D-1520 @ 2.20GHz
stepping    : 2
microcode    : 0xa
cpu MHz        : 2200.000
tsc MHz        : 2199.998
cache size    : 6144 KB
physical id    : 0
siblings    : 8
core id        : 0
cpu cores    : 4
apicid        : 1
initial apicid    : 1
fpu        : yes
fpu_exception    : yes
cpuid level    : 20
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 pdpe1gb rdtscp lm constant_tsc arch_perfmon pebs bts rep_good nopl
xtopology nonstop_tsc aperfmperf eagerfpu pni pclmulqdq dtes64 monitor
ds_cpl vmx smx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid dca sse4_1
sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand
lahf_lm abm 3dnowprefetch epb intel_pt tpr_shadow vnmi flexpriority ept
vpid fsgsbase tsc_adjust bmi1 hle avx2 smep bmi2 erms invpcid rtm cqm
rdseed adx smap xsaveopt cqm_llc cqm_occup_llc dtherm arat pln pts
bugs        :
bogomips    : 4399.57
clflush size    : 64
cache_alignment    : 64
address sizes    : 46 bits physical, 48 bits virtual
power management:

processor    : 5
vendor_id    : GenuineIntel
cpu family    : 6
model        : 86
model name    : Intel(R) Xeon(R) CPU D-1520 @ 2.20GHz
stepping    : 2
microcode    : 0xa
cpu MHz        : 2200.000
tsc MHz        : 2199.998
cache size    : 6144 KB
physical id    : 0
siblings    : 8
core id        : 1
cpu cores    : 4
apicid        : 3
initial apicid    : 3
fpu        : yes
fpu_exception    : yes
cpuid level    : 20
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 pdpe1gb rdtscp lm constant_tsc arch_perfmon pebs bts rep_good nopl
xtopology nonstop_tsc aperfmperf eagerfpu pni pclmulqdq dtes64 monitor
ds_cpl vmx smx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid dca sse4_1
sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand
lahf_lm abm 3dnowprefetch epb intel_pt tpr_shadow vnmi flexpriority ept
vpid fsgsbase tsc_adjust bmi1 hle avx2 smep bmi2 erms invpcid rtm cqm
rdseed adx smap xsaveopt cqm_llc cqm_occup_llc dtherm arat pln pts
bugs        :
bogomips    : 4399.57
clflush size    : 64
cache_alignment    : 64
address sizes    : 46 bits physical, 48 bits virtual
power management:

processor    : 6
vendor_id    : GenuineIntel
cpu family    : 6
model        : 86
model name    : Intel(R) Xeon(R) CPU D-1520 @ 2.20GHz
stepping    : 2
microcode    : 0xa
cpu MHz        : 2200.000
tsc MHz        : 2199.998
cache size    : 6144 KB
physical id    : 0
siblings    : 8
core id        : 2
cpu cores    : 4
apicid        : 5
initial apicid    : 5
fpu        : yes
fpu_exception    : yes
cpuid level    : 20
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 pdpe1gb rdtscp lm constant_tsc arch_perfmon pebs bts rep_good nopl
xtopology nonstop_tsc aperfmperf eagerfpu pni pclmulqdq dtes64 monitor
ds_cpl vmx smx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid dca sse4_1
sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand
lahf_lm abm 3dnowprefetch epb intel_pt tpr_shadow vnmi flexpriority ept
vpid fsgsbase tsc_adjust bmi1 hle avx2 smep bmi2 erms invpcid rtm cqm
rdseed adx smap xsaveopt cqm_llc cqm_occup_llc dtherm arat pln pts
bugs        :
bogomips    : 4399.57
clflush size    : 64
cache_alignment    : 64
address sizes    : 46 bits physical, 48 bits virtual
power management:

processor    : 7
vendor_id    : GenuineIntel
cpu family    : 6
model        : 86
model name    : Intel(R) Xeon(R) CPU D-1520 @ 2.20GHz
stepping    : 2
microcode    : 0xa
cpu MHz        : 2200.000
tsc MHz        : 2199.998
cache size    : 6144 KB
physical id    : 0
siblings    : 8
core id        : 3
cpu cores    : 4
apicid        : 7
initial apicid    : 7
fpu        : yes
fpu_exception    : yes
cpuid level    : 20
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 pdpe1gb rdtscp lm constant_tsc arch_perfmon pebs bts rep_good nopl
xtopology nonstop_tsc aperfmperf eagerfpu pni pclmulqdq dtes64 monitor
ds_cpl vmx smx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid dca sse4_1
sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand
lahf_lm abm 3dnowprefetch epb intel_pt tpr_shadow vnmi flexpriority ept
vpid fsgsbase tsc_adjust bmi1 hle avx2 smep bmi2 erms invpcid rtm cqm
rdseed adx smap xsaveopt cqm_llc cqm_occup_llc dtherm arat pln pts
bugs        :
bogomips    : 4399.57
clflush size    : 64
cache_alignment    : 64
address sizes    : 46 bits physical, 48 bits virtual
power management:

----------

^ permalink raw reply	[flat|nested] 7+ messages in thread

* Re: PROBLEM: lk 4.5 oops on boot with Xeon D-1520
  2016-02-17 22:51 PROBLEM: lk 4.5 oops on boot with Xeon D-1520 Tony Battersby
@ 2016-02-24  9:11 ` Thomas Gleixner
  2016-02-24 15:37   ` Liang, Kan
  0 siblings, 1 reply; 7+ messages in thread
From: Thomas Gleixner @ 2016-02-24  9:11 UTC (permalink / raw)
  To: Tony Battersby
  Cc: Kan Liang, Peter Zijlstra (Intel),
	Arnaldo Carvalho de Melo, Jiri Olsa, Stephane Eranian,
	Vince Weaver, Ingo Molnar, Kan Liang, linux-kernel

Added Liang to CC, preserved full mail for reference

On Wed, 17 Feb 2016, Tony Battersby wrote:

> The following commit in 4.5 is causing a general protection fault during
> early boot:
> 
> d6980ef32570 ("perf/x86/intel/uncore: Add Broadwell-EP uncore support")
> 
> With the commit reverted, the system boots fine.
> 
> CPU:         Intel(R) Xeon(R) CPU D-1520 @ 2.20GHz
> Motherboard: Supermicro X10SDV-4C-TLN2F
> 
> The general protection fault occurs when
> hswep_uncore_sbox_msr_init_box() calls wrmsrl().  I added a printk to
> get the following values just before the oops:
> 
> box->pmu->type->box_ctl     = 1824
> box->pmu->pmu_idx           = 0
> box->pmu->type->msr_offset  = 10
> box->pmu->type->msr_offsets = NULL
> msr                         = 1824
> (all values are decimal)
> 
> Here is the call trace:
>   hswep_uncore_sbox_msr_init_box+0x7c/0xc0 (RIP)
>   uncore_cpu_starting+0x8a/0x1c0
>   ? uncore_change_context+0xe5/0x150
>   ? uncore_types_init+0x1d6/0x1d6
>   uncore_cpu_setup+0x10/0x12
>   on_each_cpu+0x32/0x50
>   intel_uncore_init+0x2e8/0x36d
>   ? cstate_pmu_init+0x14f/0x195
>   ? uncore_cpu_setup+0x12/0x12
> 
> I have a jpg image of the monitor displaying the full oops; let me know
> if anyone wants that.
> 
> ----------
> 
> /proc/cpuinfo:
> 
> processor    : 0
> vendor_id    : GenuineIntel
> cpu family    : 6
> model        : 86
> model name    : Intel(R) Xeon(R) CPU D-1520 @ 2.20GHz
> stepping    : 2
> microcode    : 0xa
> cpu MHz        : 2200.000
> tsc MHz        : 2199.998
> cache size    : 6144 KB
> physical id    : 0
> siblings    : 8
> core id        : 0
> cpu cores    : 4
> apicid        : 0
> initial apicid    : 0
> fpu        : yes
> fpu_exception    : yes
> cpuid level    : 20
> 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 pdpe1gb rdtscp lm constant_tsc arch_perfmon pebs bts rep_good nopl
> xtopology nonstop_tsc aperfmperf eagerfpu pni pclmulqdq dtes64 monitor
> ds_cpl vmx smx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid dca sse4_1
> sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand
> lahf_lm abm 3dnowprefetch epb intel_pt tpr_shadow vnmi flexpriority ept
> vpid fsgsbase tsc_adjust bmi1 hle avx2 smep bmi2 erms invpcid rtm cqm
> rdseed adx smap xsaveopt cqm_llc cqm_occup_llc dtherm arat pln pts
> bugs        :
> bogomips    : 4399.57
> clflush size    : 64
> cache_alignment    : 64
> address sizes    : 46 bits physical, 48 bits virtual
> power management:
> 
> processor    : 1
> vendor_id    : GenuineIntel
> cpu family    : 6
> model        : 86
> model name    : Intel(R) Xeon(R) CPU D-1520 @ 2.20GHz
> stepping    : 2
> microcode    : 0xa
> cpu MHz        : 2200.000
> tsc MHz        : 2199.998
> cache size    : 6144 KB
> physical id    : 0
> siblings    : 8
> core id        : 1
> cpu cores    : 4
> apicid        : 2
> initial apicid    : 2
> fpu        : yes
> fpu_exception    : yes
> cpuid level    : 20
> 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 pdpe1gb rdtscp lm constant_tsc arch_perfmon pebs bts rep_good nopl
> xtopology nonstop_tsc aperfmperf eagerfpu pni pclmulqdq dtes64 monitor
> ds_cpl vmx smx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid dca sse4_1
> sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand
> lahf_lm abm 3dnowprefetch epb intel_pt tpr_shadow vnmi flexpriority ept
> vpid fsgsbase tsc_adjust bmi1 hle avx2 smep bmi2 erms invpcid rtm cqm
> rdseed adx smap xsaveopt cqm_llc cqm_occup_llc dtherm arat pln pts
> bugs        :
> bogomips    : 4399.57
> clflush size    : 64
> cache_alignment    : 64
> address sizes    : 46 bits physical, 48 bits virtual
> power management:
> 
> processor    : 2
> vendor_id    : GenuineIntel
> cpu family    : 6
> model        : 86
> model name    : Intel(R) Xeon(R) CPU D-1520 @ 2.20GHz
> stepping    : 2
> microcode    : 0xa
> cpu MHz        : 2200.000
> tsc MHz        : 2199.998
> cache size    : 6144 KB
> physical id    : 0
> siblings    : 8
> core id        : 2
> cpu cores    : 4
> apicid        : 4
> initial apicid    : 4
> fpu        : yes
> fpu_exception    : yes
> cpuid level    : 20
> 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 pdpe1gb rdtscp lm constant_tsc arch_perfmon pebs bts rep_good nopl
> xtopology nonstop_tsc aperfmperf eagerfpu pni pclmulqdq dtes64 monitor
> ds_cpl vmx smx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid dca sse4_1
> sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand
> lahf_lm abm 3dnowprefetch epb intel_pt tpr_shadow vnmi flexpriority ept
> vpid fsgsbase tsc_adjust bmi1 hle avx2 smep bmi2 erms invpcid rtm cqm
> rdseed adx smap xsaveopt cqm_llc cqm_occup_llc dtherm arat pln pts
> bugs        :
> bogomips    : 4399.57
> clflush size    : 64
> cache_alignment    : 64
> address sizes    : 46 bits physical, 48 bits virtual
> power management:
> 
> processor    : 3
> vendor_id    : GenuineIntel
> cpu family    : 6
> model        : 86
> model name    : Intel(R) Xeon(R) CPU D-1520 @ 2.20GHz
> stepping    : 2
> microcode    : 0xa
> cpu MHz        : 2200.000
> tsc MHz        : 2199.998
> cache size    : 6144 KB
> physical id    : 0
> siblings    : 8
> core id        : 3
> cpu cores    : 4
> apicid        : 6
> initial apicid    : 6
> fpu        : yes
> fpu_exception    : yes
> cpuid level    : 20
> 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 pdpe1gb rdtscp lm constant_tsc arch_perfmon pebs bts rep_good nopl
> xtopology nonstop_tsc aperfmperf eagerfpu pni pclmulqdq dtes64 monitor
> ds_cpl vmx smx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid dca sse4_1
> sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand
> lahf_lm abm 3dnowprefetch epb intel_pt tpr_shadow vnmi flexpriority ept
> vpid fsgsbase tsc_adjust bmi1 hle avx2 smep bmi2 erms invpcid rtm cqm
> rdseed adx smap xsaveopt cqm_llc cqm_occup_llc dtherm arat pln pts
> bugs        :
> bogomips    : 4399.57
> clflush size    : 64
> cache_alignment    : 64
> address sizes    : 46 bits physical, 48 bits virtual
> power management:
> 
> processor    : 4
> vendor_id    : GenuineIntel
> cpu family    : 6
> model        : 86
> model name    : Intel(R) Xeon(R) CPU D-1520 @ 2.20GHz
> stepping    : 2
> microcode    : 0xa
> cpu MHz        : 2200.000
> tsc MHz        : 2199.998
> cache size    : 6144 KB
> physical id    : 0
> siblings    : 8
> core id        : 0
> cpu cores    : 4
> apicid        : 1
> initial apicid    : 1
> fpu        : yes
> fpu_exception    : yes
> cpuid level    : 20
> 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 pdpe1gb rdtscp lm constant_tsc arch_perfmon pebs bts rep_good nopl
> xtopology nonstop_tsc aperfmperf eagerfpu pni pclmulqdq dtes64 monitor
> ds_cpl vmx smx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid dca sse4_1
> sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand
> lahf_lm abm 3dnowprefetch epb intel_pt tpr_shadow vnmi flexpriority ept
> vpid fsgsbase tsc_adjust bmi1 hle avx2 smep bmi2 erms invpcid rtm cqm
> rdseed adx smap xsaveopt cqm_llc cqm_occup_llc dtherm arat pln pts
> bugs        :
> bogomips    : 4399.57
> clflush size    : 64
> cache_alignment    : 64
> address sizes    : 46 bits physical, 48 bits virtual
> power management:
> 
> processor    : 5
> vendor_id    : GenuineIntel
> cpu family    : 6
> model        : 86
> model name    : Intel(R) Xeon(R) CPU D-1520 @ 2.20GHz
> stepping    : 2
> microcode    : 0xa
> cpu MHz        : 2200.000
> tsc MHz        : 2199.998
> cache size    : 6144 KB
> physical id    : 0
> siblings    : 8
> core id        : 1
> cpu cores    : 4
> apicid        : 3
> initial apicid    : 3
> fpu        : yes
> fpu_exception    : yes
> cpuid level    : 20
> 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 pdpe1gb rdtscp lm constant_tsc arch_perfmon pebs bts rep_good nopl
> xtopology nonstop_tsc aperfmperf eagerfpu pni pclmulqdq dtes64 monitor
> ds_cpl vmx smx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid dca sse4_1
> sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand
> lahf_lm abm 3dnowprefetch epb intel_pt tpr_shadow vnmi flexpriority ept
> vpid fsgsbase tsc_adjust bmi1 hle avx2 smep bmi2 erms invpcid rtm cqm
> rdseed adx smap xsaveopt cqm_llc cqm_occup_llc dtherm arat pln pts
> bugs        :
> bogomips    : 4399.57
> clflush size    : 64
> cache_alignment    : 64
> address sizes    : 46 bits physical, 48 bits virtual
> power management:
> 
> processor    : 6
> vendor_id    : GenuineIntel
> cpu family    : 6
> model        : 86
> model name    : Intel(R) Xeon(R) CPU D-1520 @ 2.20GHz
> stepping    : 2
> microcode    : 0xa
> cpu MHz        : 2200.000
> tsc MHz        : 2199.998
> cache size    : 6144 KB
> physical id    : 0
> siblings    : 8
> core id        : 2
> cpu cores    : 4
> apicid        : 5
> initial apicid    : 5
> fpu        : yes
> fpu_exception    : yes
> cpuid level    : 20
> 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 pdpe1gb rdtscp lm constant_tsc arch_perfmon pebs bts rep_good nopl
> xtopology nonstop_tsc aperfmperf eagerfpu pni pclmulqdq dtes64 monitor
> ds_cpl vmx smx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid dca sse4_1
> sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand
> lahf_lm abm 3dnowprefetch epb intel_pt tpr_shadow vnmi flexpriority ept
> vpid fsgsbase tsc_adjust bmi1 hle avx2 smep bmi2 erms invpcid rtm cqm
> rdseed adx smap xsaveopt cqm_llc cqm_occup_llc dtherm arat pln pts
> bugs        :
> bogomips    : 4399.57
> clflush size    : 64
> cache_alignment    : 64
> address sizes    : 46 bits physical, 48 bits virtual
> power management:
> 
> processor    : 7
> vendor_id    : GenuineIntel
> cpu family    : 6
> model        : 86
> model name    : Intel(R) Xeon(R) CPU D-1520 @ 2.20GHz
> stepping    : 2
> microcode    : 0xa
> cpu MHz        : 2200.000
> tsc MHz        : 2199.998
> cache size    : 6144 KB
> physical id    : 0
> siblings    : 8
> core id        : 3
> cpu cores    : 4
> apicid        : 7
> initial apicid    : 7
> fpu        : yes
> fpu_exception    : yes
> cpuid level    : 20
> 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 pdpe1gb rdtscp lm constant_tsc arch_perfmon pebs bts rep_good nopl
> xtopology nonstop_tsc aperfmperf eagerfpu pni pclmulqdq dtes64 monitor
> ds_cpl vmx smx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid dca sse4_1
> sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand
> lahf_lm abm 3dnowprefetch epb intel_pt tpr_shadow vnmi flexpriority ept
> vpid fsgsbase tsc_adjust bmi1 hle avx2 smep bmi2 erms invpcid rtm cqm
> rdseed adx smap xsaveopt cqm_llc cqm_occup_llc dtherm arat pln pts
> bugs        :
> bogomips    : 4399.57
> clflush size    : 64
> cache_alignment    : 64
> address sizes    : 46 bits physical, 48 bits virtual
> power management:
> 
> ----------
> 
> 

^ permalink raw reply	[flat|nested] 7+ messages in thread

* RE: PROBLEM: lk 4.5 oops on boot with Xeon D-1520
  2016-02-24  9:11 ` Thomas Gleixner
@ 2016-02-24 15:37   ` Liang, Kan
  2016-02-24 16:31     ` Tony Battersby
  2016-02-29 11:02     ` [tip:perf/core] perf/x86/intel/uncore: Remove SBOX support for BDX-DE tip-bot for Kan Liang
  0 siblings, 2 replies; 7+ messages in thread
From: Liang, Kan @ 2016-02-24 15:37 UTC (permalink / raw)
  To: Thomas Gleixner, Tony Battersby
  Cc: Peter Zijlstra (Intel),
	Arnaldo Carvalho de Melo, Jiri Olsa, Stephane Eranian,
	Vince Weaver, Ingo Molnar, linux-kernel


I have no idea why the original email was redirected to Junk folder.
Sorry for the late response. 

I extended BDX-DE uncore code to support BDX-EP. So they share
the same code path. But there is no sbox in BDX-DE.
I once tried the BDX-EP patch on my BDX-DE, it boots fine.
But it looks it doesn't work well for all machines. :(

Could you please try the patch as below? It specially handles the
BDX-DE by removing SBOX support.

Thanks,
Kan


>From 7e09100dda852de7263ba569dcfba737668c828e Mon Sep 17 00:00:00 2001
From: Kan Liang <kan.liang@intel.com>
Date: Wed, 24 Feb 2016 05:07:43 -0500
Subject: [PATCH 1/1] x86/perf/intel/uncore: remove SBOX support for BDX-DE

BDX-DE and BDX-EP share the same uncore code path. But there is no sbox
in BDX-DE. This patch remove SBOX support for BDX-DE.

Signed-off-by: Kan Liang <kan.liang@intel.com>
---
 arch/x86/events/intel/uncore_snbep.c | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c
index 0c801f7..d967fcc 100644
--- a/arch/x86/events/intel/uncore_snbep.c
+++ b/arch/x86/events/intel/uncore_snbep.c
@@ -2874,11 +2874,13 @@ static struct intel_uncore_type bdx_uncore_sbox = {
 	.format_group		= &hswep_uncore_sbox_format_group,
 };
 
+#define BDX_MSR_UNCORE_SBOX	3
+
 static struct intel_uncore_type *bdx_msr_uncores[] = {
 	&bdx_uncore_ubox,
 	&bdx_uncore_cbox,
-	&bdx_uncore_sbox,
 	&hswep_uncore_pcu,
+	&bdx_uncore_sbox,
 	NULL,
 };
 
@@ -2887,6 +2889,10 @@ void bdx_uncore_cpu_init(void)
 	if (bdx_uncore_cbox.num_boxes > boot_cpu_data.x86_max_cores)
 		bdx_uncore_cbox.num_boxes = boot_cpu_data.x86_max_cores;
 	uncore_msr_uncores = bdx_msr_uncores;
+
+	/* BDX-DE doesn't have SBOX */
+	if (boot_cpu_data.x86_model == 86)
+		uncore_msr_uncores[BDX_MSR_UNCORE_SBOX] = NULL;
 }
 
 static struct intel_uncore_type bdx_uncore_ha = {
-- 
2.4.3


> 
> Added Liang to CC, preserved full mail for reference
> 
> On Wed, 17 Feb 2016, Tony Battersby wrote:
> 
> > The following commit in 4.5 is causing a general protection fault
> > during early boot:
> >
> > d6980ef32570 ("perf/x86/intel/uncore: Add Broadwell-EP uncore
> > support")
> >
> > With the commit reverted, the system boots fine.
> >
> > CPU:         Intel(R) Xeon(R) CPU D-1520 @ 2.20GHz
> > Motherboard: Supermicro X10SDV-4C-TLN2F
> >
> > The general protection fault occurs when
> > hswep_uncore_sbox_msr_init_box() calls wrmsrl().  I added a printk to
> > get the following values just before the oops:
> >
> > box->pmu->type->box_ctl     = 1824
> > box->pmu->pmu_idx           = 0
> > box->pmu->type->msr_offset  = 10
> > box->pmu->type->msr_offsets = NULL
> > msr                         = 1824
> > (all values are decimal)
> >
> > Here is the call trace:
> >   hswep_uncore_sbox_msr_init_box+0x7c/0xc0 (RIP)
> >   uncore_cpu_starting+0x8a/0x1c0
> >   ? uncore_change_context+0xe5/0x150
> >   ? uncore_types_init+0x1d6/0x1d6
> >   uncore_cpu_setup+0x10/0x12
> >   on_each_cpu+0x32/0x50
> >   intel_uncore_init+0x2e8/0x36d
> >   ? cstate_pmu_init+0x14f/0x195
> >   ? uncore_cpu_setup+0x12/0x12
> >
> > I have a jpg image of the monitor displaying the full oops; let me
> > know if anyone wants that.
> >
> > ----------
> >
> > /proc/cpuinfo:
> >
> > processor    : 0
> > vendor_id    : GenuineIntel
> > cpu family    : 6
> > model        : 86
> > model name    : Intel(R) Xeon(R) CPU D-1520 @ 2.20GHz
> > stepping    : 2
> > microcode    : 0xa
> > cpu MHz        : 2200.000
> > tsc MHz        : 2199.998
> > cache size    : 6144 KB
> > physical id    : 0
> > siblings    : 8
> > core id        : 0
> > cpu cores    : 4
> > apicid        : 0
> > initial apicid    : 0
> > fpu        : yes
> > fpu_exception    : yes
> > cpuid level    : 20
> > 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 pdpe1gb rdtscp lm constant_tsc arch_perfmon pebs bts rep_good
> nopl
> > xtopology nonstop_tsc aperfmperf eagerfpu pni pclmulqdq dtes64
> monitor
> > ds_cpl vmx smx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid dca sse4_1
> > sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c
> > rdrand lahf_lm abm 3dnowprefetch epb intel_pt tpr_shadow vnmi
> > flexpriority ept vpid fsgsbase tsc_adjust bmi1 hle avx2 smep bmi2 erms
> > invpcid rtm cqm rdseed adx smap xsaveopt cqm_llc cqm_occup_llc
> dtherm arat pln pts
> > bugs        :
> > bogomips    : 4399.57
> > clflush size    : 64
> > cache_alignment    : 64
> > address sizes    : 46 bits physical, 48 bits virtual
> > power management:
> >
> > processor    : 1
> > vendor_id    : GenuineIntel
> > cpu family    : 6
> > model        : 86
> > model name    : Intel(R) Xeon(R) CPU D-1520 @ 2.20GHz
> > stepping    : 2
> > microcode    : 0xa
> > cpu MHz        : 2200.000
> > tsc MHz        : 2199.998
> > cache size    : 6144 KB
> > physical id    : 0
> > siblings    : 8
> > core id        : 1
> > cpu cores    : 4
> > apicid        : 2
> > initial apicid    : 2
> > fpu        : yes
> > fpu_exception    : yes
> > cpuid level    : 20
> > 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 pdpe1gb rdtscp lm constant_tsc arch_perfmon pebs bts rep_good
> nopl
> > xtopology nonstop_tsc aperfmperf eagerfpu pni pclmulqdq dtes64
> monitor
> > ds_cpl vmx smx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid dca sse4_1
> > sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c
> > rdrand lahf_lm abm 3dnowprefetch epb intel_pt tpr_shadow vnmi
> > flexpriority ept vpid fsgsbase tsc_adjust bmi1 hle avx2 smep bmi2 erms
> > invpcid rtm cqm rdseed adx smap xsaveopt cqm_llc cqm_occup_llc
> dtherm arat pln pts
> > bugs        :
> > bogomips    : 4399.57
> > clflush size    : 64
> > cache_alignment    : 64
> > address sizes    : 46 bits physical, 48 bits virtual
> > power management:
> >
> > processor    : 2
> > vendor_id    : GenuineIntel
> > cpu family    : 6
> > model        : 86
> > model name    : Intel(R) Xeon(R) CPU D-1520 @ 2.20GHz
> > stepping    : 2
> > microcode    : 0xa
> > cpu MHz        : 2200.000
> > tsc MHz        : 2199.998
> > cache size    : 6144 KB
> > physical id    : 0
> > siblings    : 8
> > core id        : 2
> > cpu cores    : 4
> > apicid        : 4
> > initial apicid    : 4
> > fpu        : yes
> > fpu_exception    : yes
> > cpuid level    : 20
> > 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 pdpe1gb rdtscp lm constant_tsc arch_perfmon pebs bts rep_good
> nopl
> > xtopology nonstop_tsc aperfmperf eagerfpu pni pclmulqdq dtes64
> monitor
> > ds_cpl vmx smx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid dca sse4_1
> > sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c
> > rdrand lahf_lm abm 3dnowprefetch epb intel_pt tpr_shadow vnmi
> > flexpriority ept vpid fsgsbase tsc_adjust bmi1 hle avx2 smep bmi2 erms
> > invpcid rtm cqm rdseed adx smap xsaveopt cqm_llc cqm_occup_llc
> dtherm arat pln pts
> > bugs        :
> > bogomips    : 4399.57
> > clflush size    : 64
> > cache_alignment    : 64
> > address sizes    : 46 bits physical, 48 bits virtual
> > power management:
> >
> > processor    : 3
> > vendor_id    : GenuineIntel
> > cpu family    : 6
> > model        : 86
> > model name    : Intel(R) Xeon(R) CPU D-1520 @ 2.20GHz
> > stepping    : 2
> > microcode    : 0xa
> > cpu MHz        : 2200.000
> > tsc MHz        : 2199.998
> > cache size    : 6144 KB
> > physical id    : 0
> > siblings    : 8
> > core id        : 3
> > cpu cores    : 4
> > apicid        : 6
> > initial apicid    : 6
> > fpu        : yes
> > fpu_exception    : yes
> > cpuid level    : 20
> > 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 pdpe1gb rdtscp lm constant_tsc arch_perfmon pebs bts rep_good
> nopl
> > xtopology nonstop_tsc aperfmperf eagerfpu pni pclmulqdq dtes64
> monitor
> > ds_cpl vmx smx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid dca sse4_1
> > sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c
> > rdrand lahf_lm abm 3dnowprefetch epb intel_pt tpr_shadow vnmi
> > flexpriority ept vpid fsgsbase tsc_adjust bmi1 hle avx2 smep bmi2 erms
> > invpcid rtm cqm rdseed adx smap xsaveopt cqm_llc cqm_occup_llc
> dtherm arat pln pts
> > bugs        :
> > bogomips    : 4399.57
> > clflush size    : 64
> > cache_alignment    : 64
> > address sizes    : 46 bits physical, 48 bits virtual
> > power management:
> >
> > processor    : 4
> > vendor_id    : GenuineIntel
> > cpu family    : 6
> > model        : 86
> > model name    : Intel(R) Xeon(R) CPU D-1520 @ 2.20GHz
> > stepping    : 2
> > microcode    : 0xa
> > cpu MHz        : 2200.000
> > tsc MHz        : 2199.998
> > cache size    : 6144 KB
> > physical id    : 0
> > siblings    : 8
> > core id        : 0
> > cpu cores    : 4
> > apicid        : 1
> > initial apicid    : 1
> > fpu        : yes
> > fpu_exception    : yes
> > cpuid level    : 20
> > 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 pdpe1gb rdtscp lm constant_tsc arch_perfmon pebs bts rep_good
> nopl
> > xtopology nonstop_tsc aperfmperf eagerfpu pni pclmulqdq dtes64
> monitor
> > ds_cpl vmx smx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid dca sse4_1
> > sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c
> > rdrand lahf_lm abm 3dnowprefetch epb intel_pt tpr_shadow vnmi
> > flexpriority ept vpid fsgsbase tsc_adjust bmi1 hle avx2 smep bmi2 erms
> > invpcid rtm cqm rdseed adx smap xsaveopt cqm_llc cqm_occup_llc
> dtherm arat pln pts
> > bugs        :
> > bogomips    : 4399.57
> > clflush size    : 64
> > cache_alignment    : 64
> > address sizes    : 46 bits physical, 48 bits virtual
> > power management:
> >
> > processor    : 5
> > vendor_id    : GenuineIntel
> > cpu family    : 6
> > model        : 86
> > model name    : Intel(R) Xeon(R) CPU D-1520 @ 2.20GHz
> > stepping    : 2
> > microcode    : 0xa
> > cpu MHz        : 2200.000
> > tsc MHz        : 2199.998
> > cache size    : 6144 KB
> > physical id    : 0
> > siblings    : 8
> > core id        : 1
> > cpu cores    : 4
> > apicid        : 3
> > initial apicid    : 3
> > fpu        : yes
> > fpu_exception    : yes
> > cpuid level    : 20
> > 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 pdpe1gb rdtscp lm constant_tsc arch_perfmon pebs bts rep_good
> nopl
> > xtopology nonstop_tsc aperfmperf eagerfpu pni pclmulqdq dtes64
> monitor
> > ds_cpl vmx smx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid dca sse4_1
> > sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c
> > rdrand lahf_lm abm 3dnowprefetch epb intel_pt tpr_shadow vnmi
> > flexpriority ept vpid fsgsbase tsc_adjust bmi1 hle avx2 smep bmi2 erms
> > invpcid rtm cqm rdseed adx smap xsaveopt cqm_llc cqm_occup_llc
> dtherm arat pln pts
> > bugs        :
> > bogomips    : 4399.57
> > clflush size    : 64
> > cache_alignment    : 64
> > address sizes    : 46 bits physical, 48 bits virtual
> > power management:
> >
> > processor    : 6
> > vendor_id    : GenuineIntel
> > cpu family    : 6
> > model        : 86
> > model name    : Intel(R) Xeon(R) CPU D-1520 @ 2.20GHz
> > stepping    : 2
> > microcode    : 0xa
> > cpu MHz        : 2200.000
> > tsc MHz        : 2199.998
> > cache size    : 6144 KB
> > physical id    : 0
> > siblings    : 8
> > core id        : 2
> > cpu cores    : 4
> > apicid        : 5
> > initial apicid    : 5
> > fpu        : yes
> > fpu_exception    : yes
> > cpuid level    : 20
> > 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 pdpe1gb rdtscp lm constant_tsc arch_perfmon pebs bts rep_good
> nopl
> > xtopology nonstop_tsc aperfmperf eagerfpu pni pclmulqdq dtes64
> monitor
> > ds_cpl vmx smx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid dca sse4_1
> > sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c
> > rdrand lahf_lm abm 3dnowprefetch epb intel_pt tpr_shadow vnmi
> > flexpriority ept vpid fsgsbase tsc_adjust bmi1 hle avx2 smep bmi2 erms
> > invpcid rtm cqm rdseed adx smap xsaveopt cqm_llc cqm_occup_llc
> dtherm arat pln pts
> > bugs        :
> > bogomips    : 4399.57
> > clflush size    : 64
> > cache_alignment    : 64
> > address sizes    : 46 bits physical, 48 bits virtual
> > power management:
> >
> > processor    : 7
> > vendor_id    : GenuineIntel
> > cpu family    : 6
> > model        : 86
> > model name    : Intel(R) Xeon(R) CPU D-1520 @ 2.20GHz
> > stepping    : 2
> > microcode    : 0xa
> > cpu MHz        : 2200.000
> > tsc MHz        : 2199.998
> > cache size    : 6144 KB
> > physical id    : 0
> > siblings    : 8
> > core id        : 3
> > cpu cores    : 4
> > apicid        : 7
> > initial apicid    : 7
> > fpu        : yes
> > fpu_exception    : yes
> > cpuid level    : 20
> > 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 pdpe1gb rdtscp lm constant_tsc arch_perfmon pebs bts rep_good
> nopl
> > xtopology nonstop_tsc aperfmperf eagerfpu pni pclmulqdq dtes64
> monitor
> > ds_cpl vmx smx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid dca sse4_1
> > sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c
> > rdrand lahf_lm abm 3dnowprefetch epb intel_pt tpr_shadow vnmi
> > flexpriority ept vpid fsgsbase tsc_adjust bmi1 hle avx2 smep bmi2 erms
> > invpcid rtm cqm rdseed adx smap xsaveopt cqm_llc cqm_occup_llc
> dtherm arat pln pts
> > bugs        :
> > bogomips    : 4399.57
> > clflush size    : 64
> > cache_alignment    : 64
> > address sizes    : 46 bits physical, 48 bits virtual
> > power management:
> >
> > ----------
> >
> >

^ permalink raw reply related	[flat|nested] 7+ messages in thread

* Re: PROBLEM: lk 4.5 oops on boot with Xeon D-1520
  2016-02-24 15:37   ` Liang, Kan
@ 2016-02-24 16:31     ` Tony Battersby
  2016-02-24 16:36       ` Liang, Kan
  2016-02-29 11:02     ` [tip:perf/core] perf/x86/intel/uncore: Remove SBOX support for BDX-DE tip-bot for Kan Liang
  1 sibling, 1 reply; 7+ messages in thread
From: Tony Battersby @ 2016-02-24 16:31 UTC (permalink / raw)
  To: Liang, Kan, Thomas Gleixner
  Cc: Peter Zijlstra (Intel),
	Arnaldo Carvalho de Melo, Jiri Olsa, Stephane Eranian,
	Vince Weaver, Ingo Molnar, linux-kernel

Thanks, that fixes it.

Note: your patch appears to be against linux-next.  I had to change
"arch/x86/events/intel/uncore_snbep.c" to
"arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c" for the patch to
apply against current linux-git.

Tested-by: Tony Battersby <tonyb@cybernetics.com>

On 02/24/2016 10:37 AM, Liang, Kan wrote:
> I have no idea why the original email was redirected to Junk folder.
> Sorry for the late response. 
>
> I extended BDX-DE uncore code to support BDX-EP. So they share
> the same code path. But there is no sbox in BDX-DE.
> I once tried the BDX-EP patch on my BDX-DE, it boots fine.
> But it looks it doesn't work well for all machines. :(
>
> Could you please try the patch as below? It specially handles the
> BDX-DE by removing SBOX support.
>
> Thanks,
> Kan
>
>
> >From 7e09100dda852de7263ba569dcfba737668c828e Mon Sep 17 00:00:00 2001
> From: Kan Liang <kan.liang@intel.com>
> Date: Wed, 24 Feb 2016 05:07:43 -0500
> Subject: [PATCH 1/1] x86/perf/intel/uncore: remove SBOX support for BDX-DE
>
> BDX-DE and BDX-EP share the same uncore code path. But there is no sbox
> in BDX-DE. This patch remove SBOX support for BDX-DE.
>
> Signed-off-by: Kan Liang <kan.liang@intel.com>
> ---
>  arch/x86/events/intel/uncore_snbep.c | 8 +++++++-
>  1 file changed, 7 insertions(+), 1 deletion(-)
>
> diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c
> index 0c801f7..d967fcc 100644
> --- a/arch/x86/events/intel/uncore_snbep.c
> +++ b/arch/x86/events/intel/uncore_snbep.c
> @@ -2874,11 +2874,13 @@ static struct intel_uncore_type bdx_uncore_sbox = {
>  	.format_group		= &hswep_uncore_sbox_format_group,
>  };
>  
> +#define BDX_MSR_UNCORE_SBOX	3
> +
>  static struct intel_uncore_type *bdx_msr_uncores[] = {
>  	&bdx_uncore_ubox,
>  	&bdx_uncore_cbox,
> -	&bdx_uncore_sbox,
>  	&hswep_uncore_pcu,
> +	&bdx_uncore_sbox,
>  	NULL,
>  };
>  
> @@ -2887,6 +2889,10 @@ void bdx_uncore_cpu_init(void)
>  	if (bdx_uncore_cbox.num_boxes > boot_cpu_data.x86_max_cores)
>  		bdx_uncore_cbox.num_boxes = boot_cpu_data.x86_max_cores;
>  	uncore_msr_uncores = bdx_msr_uncores;
> +
> +	/* BDX-DE doesn't have SBOX */
> +	if (boot_cpu_data.x86_model == 86)
> +		uncore_msr_uncores[BDX_MSR_UNCORE_SBOX] = NULL;
>  }
>  
>  static struct intel_uncore_type bdx_uncore_ha = {

^ permalink raw reply	[flat|nested] 7+ messages in thread

* RE: PROBLEM: lk 4.5 oops on boot with Xeon D-1520
  2016-02-24 16:31     ` Tony Battersby
@ 2016-02-24 16:36       ` Liang, Kan
  2016-02-24 17:41         ` Peter Zijlstra
  0 siblings, 1 reply; 7+ messages in thread
From: Liang, Kan @ 2016-02-24 16:36 UTC (permalink / raw)
  To: Tony Battersby, Thomas Gleixner, peterz
  Cc: Arnaldo Carvalho de Melo, Jiri Olsa, Stephane Eranian,
	Vince Weaver, Ingo Molnar, linux-kernel

> 
> Thanks, that fixes it.
> 
> Note: your patch appears to be against linux-next.  I had to change
> "arch/x86/events/intel/uncore_snbep.c" to
> "arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c" for the patch to
> apply against current linux-git.

Thanks for the verification.

I think the perf related code just moved to a new place "arch/x86/events/".
So the patch is based on that new place.

Peter, should I resend the patch for the old place?

Thanks,
Kan
> 
> Tested-by: Tony Battersby <tonyb@cybernetics.com>
> 
> On 02/24/2016 10:37 AM, Liang, Kan wrote:
> > I have no idea why the original email was redirected to Junk folder.
> > Sorry for the late response.
> >
> > I extended BDX-DE uncore code to support BDX-EP. So they share the
> > same code path. But there is no sbox in BDX-DE.
> > I once tried the BDX-EP patch on my BDX-DE, it boots fine.
> > But it looks it doesn't work well for all machines. :(
> >
> > Could you please try the patch as below? It specially handles the
> > BDX-DE by removing SBOX support.
> >
> > Thanks,
> > Kan
> >
> >
> > >From 7e09100dda852de7263ba569dcfba737668c828e Mon Sep 17
> 00:00:00
> > >2001
> > From: Kan Liang <kan.liang@intel.com>
> > Date: Wed, 24 Feb 2016 05:07:43 -0500
> > Subject: [PATCH 1/1] x86/perf/intel/uncore: remove SBOX support for
> > BDX-DE
> >
> > BDX-DE and BDX-EP share the same uncore code path. But there is no
> > sbox in BDX-DE. This patch remove SBOX support for BDX-DE.
> >
> > Signed-off-by: Kan Liang <kan.liang@intel.com>
> > ---
> >  arch/x86/events/intel/uncore_snbep.c | 8 +++++++-
> >  1 file changed, 7 insertions(+), 1 deletion(-)
> >
> > diff --git a/arch/x86/events/intel/uncore_snbep.c
> > b/arch/x86/events/intel/uncore_snbep.c
> > index 0c801f7..d967fcc 100644
> > --- a/arch/x86/events/intel/uncore_snbep.c
> > +++ b/arch/x86/events/intel/uncore_snbep.c
> > @@ -2874,11 +2874,13 @@ static struct intel_uncore_type
> bdx_uncore_sbox = {
> >  	.format_group		= &hswep_uncore_sbox_format_group,
> >  };
> >
> > +#define BDX_MSR_UNCORE_SBOX	3
> > +
> >  static struct intel_uncore_type *bdx_msr_uncores[] = {
> >  	&bdx_uncore_ubox,
> >  	&bdx_uncore_cbox,
> > -	&bdx_uncore_sbox,
> >  	&hswep_uncore_pcu,
> > +	&bdx_uncore_sbox,
> >  	NULL,
> >  };
> >
> > @@ -2887,6 +2889,10 @@ void bdx_uncore_cpu_init(void)
> >  	if (bdx_uncore_cbox.num_boxes >
> boot_cpu_data.x86_max_cores)
> >  		bdx_uncore_cbox.num_boxes =
> boot_cpu_data.x86_max_cores;
> >  	uncore_msr_uncores = bdx_msr_uncores;
> > +
> > +	/* BDX-DE doesn't have SBOX */
> > +	if (boot_cpu_data.x86_model == 86)
> > +		uncore_msr_uncores[BDX_MSR_UNCORE_SBOX] = NULL;
> >  }
> >
> >  static struct intel_uncore_type bdx_uncore_ha = {

^ permalink raw reply	[flat|nested] 7+ messages in thread

* Re: PROBLEM: lk 4.5 oops on boot with Xeon D-1520
  2016-02-24 16:36       ` Liang, Kan
@ 2016-02-24 17:41         ` Peter Zijlstra
  0 siblings, 0 replies; 7+ messages in thread
From: Peter Zijlstra @ 2016-02-24 17:41 UTC (permalink / raw)
  To: Liang, Kan
  Cc: Tony Battersby, Thomas Gleixner, Arnaldo Carvalho de Melo,
	Jiri Olsa, Stephane Eranian, Vince Weaver, Ingo Molnar,
	linux-kernel

On Wed, Feb 24, 2016 at 04:36:33PM +0000, Liang, Kan wrote:
> > 
> > Thanks, that fixes it.
> > 
> > Note: your patch appears to be against linux-next.  I had to change
> > "arch/x86/events/intel/uncore_snbep.c" to
> > "arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c" for the patch to
> > apply against current linux-git.
> 
> Thanks for the verification.
> 
> I think the perf related code just moved to a new place "arch/x86/events/".
> So the patch is based on that new place.
> 
> Peter, should I resend the patch for the old place?

Nah, I'll sort it out. Thanks!

^ permalink raw reply	[flat|nested] 7+ messages in thread

* [tip:perf/core] perf/x86/intel/uncore: Remove SBOX support for BDX-DE
  2016-02-24 15:37   ` Liang, Kan
  2016-02-24 16:31     ` Tony Battersby
@ 2016-02-29 11:02     ` tip-bot for Kan Liang
  1 sibling, 0 replies; 7+ messages in thread
From: tip-bot for Kan Liang @ 2016-02-29 11:02 UTC (permalink / raw)
  To: linux-tip-commits
  Cc: hpa, acme, tonyb, kan.liang, stable, mingo, peterz, eranian,
	torvalds, vincent.weaver, linux-kernel, tglx, jolsa

Commit-ID:  6cb2f1d9af5b0f0afdd4e689d969df4b5c76a4c2
Gitweb:     http://git.kernel.org/tip/6cb2f1d9af5b0f0afdd4e689d969df4b5c76a4c2
Author:     Kan Liang <kan.liang@intel.com>
AuthorDate: Wed, 24 Feb 2016 05:07:43 -0500
Committer:  Ingo Molnar <mingo@kernel.org>
CommitDate: Mon, 29 Feb 2016 09:35:11 +0100

perf/x86/intel/uncore: Remove SBOX support for BDX-DE

BDX-DE and BDX-EP share the same uncore code path. But there is no sbox
in BDX-DE. This patch remove SBOX support for BDX-DE.

Signed-off-by: Kan Liang <kan.liang@intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: <stable@vger.kernel.org>
Cc: <tonyb@cybernetics.com>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Tony Battersby <tonyb@cybernetics.com>
Cc: Vince Weaver <vincent.weaver@maine.edu>
Link: http://lkml.kernel.org/r/37D7C6CF3E00A74B8858931C1DB2F0770589D336@SHSMSX103.ccr.corp.intel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/x86/events/intel/uncore_snbep.c | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c
index 0c801f7..d967fcc 100644
--- a/arch/x86/events/intel/uncore_snbep.c
+++ b/arch/x86/events/intel/uncore_snbep.c
@@ -2874,11 +2874,13 @@ static struct intel_uncore_type bdx_uncore_sbox = {
 	.format_group		= &hswep_uncore_sbox_format_group,
 };
 
+#define BDX_MSR_UNCORE_SBOX	3
+
 static struct intel_uncore_type *bdx_msr_uncores[] = {
 	&bdx_uncore_ubox,
 	&bdx_uncore_cbox,
-	&bdx_uncore_sbox,
 	&hswep_uncore_pcu,
+	&bdx_uncore_sbox,
 	NULL,
 };
 
@@ -2887,6 +2889,10 @@ void bdx_uncore_cpu_init(void)
 	if (bdx_uncore_cbox.num_boxes > boot_cpu_data.x86_max_cores)
 		bdx_uncore_cbox.num_boxes = boot_cpu_data.x86_max_cores;
 	uncore_msr_uncores = bdx_msr_uncores;
+
+	/* BDX-DE doesn't have SBOX */
+	if (boot_cpu_data.x86_model == 86)
+		uncore_msr_uncores[BDX_MSR_UNCORE_SBOX] = NULL;
 }
 
 static struct intel_uncore_type bdx_uncore_ha = {

^ permalink raw reply related	[flat|nested] 7+ messages in thread

end of thread, other threads:[~2016-02-29 11:03 UTC | newest]

Thread overview: 7+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2016-02-17 22:51 PROBLEM: lk 4.5 oops on boot with Xeon D-1520 Tony Battersby
2016-02-24  9:11 ` Thomas Gleixner
2016-02-24 15:37   ` Liang, Kan
2016-02-24 16:31     ` Tony Battersby
2016-02-24 16:36       ` Liang, Kan
2016-02-24 17:41         ` Peter Zijlstra
2016-02-29 11:02     ` [tip:perf/core] perf/x86/intel/uncore: Remove SBOX support for BDX-DE tip-bot for Kan Liang

This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.