| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Date: Wed, 20 Mar 2019 10:20:57 -0400
From: "Liang, Kan" <kan.liang@...ux.intel.com>
To: Stephane Eranian <eranian@...gle.com>
Cc: Peter Zijlstra <peterz@...radead.org>,
Arnaldo Carvalho de Melo <acme@...nel.org>,
Ingo Molnar <mingo@...hat.com>,
LKML <linux-kernel@...r.kernel.org>,
Thomas Gleixner <tglx@...utronix.de>,
Jiri Olsa <jolsa@...nel.org>,
Alexander Shishkin <alexander.shishkin@...ux.intel.com>,
Andi Kleen <ak@...ux.intel.com>
Subject: Re: [PATCH 06/22] perf/x86/intel: Add Icelake support
On 3/19/2019 8:08 PM, Stephane Eranian wrote:
> On Mon, Mar 18, 2019 at 2:44 PM <kan.liang@...ux.intel.com> wrote:
>>
>> From: Kan Liang <kan.liang@...ux.intel.com>
>>
>> Add Icelake core PMU perf code, including constraint tables and the main
>> enable code.
>>
>> Icelake expanded the generic counters to always 8 even with HT on, but a
>> range of events cannot be scheduled on the extra 4 counters.
>> Add new constraint ranges to describe this to the scheduler.
>> The number of constraints that need to be checked is larger now than
>> with earlier CPUs.
>> At some point we may need a new data structure to look them up more
>> efficiently than with linear search. So far it still seems to be
>> acceptable however.
>>
>> Icelake added a new fixed counter SLOTS. Full support for it is added
>> later in the patch series.
>>
>> The cache events table is identical to Skylake.
>>
>> Compare to PEBS instruction event on generic counter, fixed counter 0
>> has less skid. Force instruction:ppp always in fixed counter 0.
>>
>> Originally-by: Andi Kleen <ak@...ux.intel.com>
>> Signed-off-by: Kan Liang <kan.liang@...ux.intel.com>
>> ---
>> arch/x86/events/intel/core.c | 111 ++++++++++++++++++++++++++++++
>> arch/x86/events/intel/ds.c | 26 ++++++-
>> arch/x86/events/perf_event.h | 2 +
>> arch/x86/include/asm/intel_ds.h | 2 +-
>> arch/x86/include/asm/perf_event.h | 2 +-
>> 5 files changed, 139 insertions(+), 4 deletions(-)
>>
>> diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
>> index 8486ab87f8f8..87dafac87520 100644
>> --- a/arch/x86/events/intel/core.c
>> +++ b/arch/x86/events/intel/core.c
>> @@ -239,6 +239,35 @@ static struct extra_reg intel_skl_extra_regs[] __read_mostly = {
>> EVENT_EXTRA_END
>> };
>>
>> +static struct event_constraint intel_icl_event_constraints[] = {
>> + FIXED_EVENT_CONSTRAINT(0x00c0, 0), /* INST_RETIRED.ANY */
>> + INTEL_UEVENT_CONSTRAINT(0x1c0, 0), /* INST_RETIRED.PREC_DIST */
>> + FIXED_EVENT_CONSTRAINT(0x003c, 1), /* CPU_CLK_UNHALTED.CORE */
>> + FIXED_EVENT_CONSTRAINT(0x0300, 2), /* CPU_CLK_UNHALTED.REF */
>> + FIXED_EVENT_CONSTRAINT(0x0400, 3), /* SLOTS */
>> + INTEL_EVENT_CONSTRAINT_RANGE(0x03, 0x0a, 0xf),
>> + INTEL_EVENT_CONSTRAINT_RANGE(0x1f, 0x28, 0xf),
>> + INTEL_EVENT_CONSTRAINT(0x32, 0xf), /* SW_PREFETCH_ACCESS.* */
>> + INTEL_EVENT_CONSTRAINT_RANGE(0x48, 0x54, 0xf),
>> + INTEL_EVENT_CONSTRAINT_RANGE(0x60, 0x8b, 0xf),
>> + INTEL_UEVENT_CONSTRAINT(0x04a3, 0xff), /* CYCLE_ACTIVITY.STALLS_TOTAL */
>> + INTEL_UEVENT_CONSTRAINT(0x10a3, 0xff), /* CYCLE_ACTIVITY.STALLS_MEM_ANY */
>> + INTEL_EVENT_CONSTRAINT(0xa3, 0xf), /* CYCLE_ACTIVITY.* */
>> + INTEL_EVENT_CONSTRAINT_RANGE(0xa8, 0xb0, 0xf),
>> + INTEL_EVENT_CONSTRAINT_RANGE(0xb7, 0xbd, 0xf),
>> + INTEL_EVENT_CONSTRAINT_RANGE(0xd0, 0xe6, 0xf),
>> + INTEL_EVENT_CONSTRAINT_RANGE(0xf0, 0xf4, 0xf),
>> + EVENT_CONSTRAINT_END
>> +};
>> +
>> +static struct extra_reg intel_icl_extra_regs[] __read_mostly = {
>> + INTEL_UEVENT_EXTRA_REG(0x01b7, MSR_OFFCORE_RSP_0, 0x3fffff9fffull, RSP_0),
>> + INTEL_UEVENT_EXTRA_REG(0x01bb, MSR_OFFCORE_RSP_1, 0x3fffff9fffull, RSP_1),
>> + INTEL_UEVENT_PEBS_LDLAT_EXTRA_REG(0x01cd),
>> + INTEL_UEVENT_EXTRA_REG(0x01c6, MSR_PEBS_FRONTEND, 0x7fff17, FE),
>> + EVENT_EXTRA_END
>> +};
>> +
>> EVENT_ATTR_STR(mem-loads, mem_ld_nhm, "event=0x0b,umask=0x10,ldlat=3");
>> EVENT_ATTR_STR(mem-loads, mem_ld_snb, "event=0xcd,umask=0x1,ldlat=3");
>> EVENT_ATTR_STR(mem-stores, mem_st_snb, "event=0xcd,umask=0x2");
>> @@ -3324,6 +3353,9 @@ static struct event_constraint counter0_constraint =
>> static struct event_constraint counter2_constraint =
>> EVENT_CONSTRAINT(0, 0x4, 0);
>>
>> +static struct event_constraint fixed_counter0_constraint =
>> + FIXED_EVENT_CONSTRAINT(0x00c0, 0);
>> +
>> static struct event_constraint *
>> hsw_get_event_constraints(struct cpu_hw_events *cpuc, int idx,
>> struct perf_event *event)
>> @@ -3342,6 +3374,21 @@ hsw_get_event_constraints(struct cpu_hw_events *cpuc, int idx,
>> return c;
>> }
>>
>> +static struct event_constraint *
>> +icl_get_event_constraints(struct cpu_hw_events *cpuc, int idx,
>> + struct perf_event *event)
>> +{
>> + /*
>> + * Fixed counter 0 has less skid.
>> + * Force instruction:ppp in Fixed counter 0
>> + */
>> + if ((event->attr.precise_ip == 3) &&
>> + ((event->hw.config & X86_RAW_EVENT_MASK) == 0x00c0))
>> + return &fixed_counter0_constraint;
>> +
> Not clear to me why you need to treat this one separately from the
> PEBS constraints, if you check that you have
> :ppp (precise_ip > 0)?
>
>
There is no model specific get_pebs_constrains, so I have to put the
checking here for Icelake.
We only want to force the :ppp case in fixed counter 0, which has less
skid.
Thanks,
Kan
Powered by blists - more mailing lists