perf/x86/intel: Apply mid ACK for small core

A warning as below may be occasionally triggered in an ADL machine when
these conditions occur:

 - Two perf record commands run one by one. Both record a PEBS event.
 - Both runs on small cores.
 - They have different adaptive PEBS configuration (PEBS_DATA_CFG).

  [ ] WARNING: CPU: 4 PID: 9874 at arch/x86/events/intel/ds.c:1743 setup_pebs_adaptive_sample_data+0x55e/0x5b0
  [ ] RIP: 0010:setup_pebs_adaptive_sample_data+0x55e/0x5b0
  [ ] Call Trace:
  [ ]  <NMI>
  [ ]  intel_pmu_drain_pebs_icl+0x48b/0x810
  [ ]  perf_event_nmi_handler+0x41/0x80
  [ ]  </NMI>
  [ ]  __perf_event_task_sched_in+0x2c2/0x3a0

Different from the big core, the small core requires the ACK right
before re-enabling counters in the NMI handler, otherwise a stale PEBS
record may be dumped into the later NMI handler, which trigger the
warning.

Add a new mid_ack flag to track the case. Add all PMI handler bits in
the struct x86_hybrid_pmu to track the bits for different types of
PMUs.  Apply mid ACK for the small cores on an Alder Lake machine.

The existing hybrid() macro has a compile error when taking address of
a bit-field variable. Add a new macro hybrid_bit() to get the
bit-field value of a given PMU.

Fixes: f83d2f91d2 ("perf/x86/intel: Add Alder Lake Hybrid support")
Reported-by: Ammy Yi <ammy.yi@intel.com>
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Andi Kleen <ak@linux.intel.com>
Tested-by: Ammy Yi <ammy.yi@intel.com>
Link: https://lkml.kernel.org/r/1627997128-57891-1-git-send-email-kan.liang@linux.intel.com
This commit is contained in:
Kan Liang 2021-08-03 06:25:28 -07:00 committed by Peter Zijlstra
parent df51fe7ea1
commit acade63799
2 changed files with 30 additions and 8 deletions

View File

@ -2904,24 +2904,28 @@ static int handle_pmi_common(struct pt_regs *regs, u64 status)
*/
static int intel_pmu_handle_irq(struct pt_regs *regs)
{
struct cpu_hw_events *cpuc;
struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
bool late_ack = hybrid_bit(cpuc->pmu, late_ack);
bool mid_ack = hybrid_bit(cpuc->pmu, mid_ack);
int loops;
u64 status;
int handled;
int pmu_enabled;
cpuc = this_cpu_ptr(&cpu_hw_events);
/*
* Save the PMU state.
* It needs to be restored when leaving the handler.
*/
pmu_enabled = cpuc->enabled;
/*
* No known reason to not always do late ACK,
* but just in case do it opt-in.
* In general, the early ACK is only applied for old platforms.
* For the big core starts from Haswell, the late ACK should be
* applied.
* For the small core after Tremont, we have to do the ACK right
* before re-enabling counters, which is in the middle of the
* NMI handler.
*/
if (!x86_pmu.late_ack)
if (!late_ack && !mid_ack)
apic_write(APIC_LVTPC, APIC_DM_NMI);
intel_bts_disable_local();
cpuc->enabled = 0;
@ -2958,6 +2962,8 @@ again:
goto again;
done:
if (mid_ack)
apic_write(APIC_LVTPC, APIC_DM_NMI);
/* Only restore PMU state when it's active. See x86_pmu_disable(). */
cpuc->enabled = pmu_enabled;
if (pmu_enabled)
@ -2969,7 +2975,7 @@ done:
* have been reset. This avoids spurious NMIs on
* Haswell CPUs.
*/
if (x86_pmu.late_ack)
if (late_ack)
apic_write(APIC_LVTPC, APIC_DM_NMI);
return handled;
}
@ -6129,7 +6135,6 @@ __init int intel_pmu_init(void)
static_branch_enable(&perf_is_hybrid);
x86_pmu.num_hybrid_pmus = X86_HYBRID_NUM_PMUS;
x86_pmu.late_ack = true;
x86_pmu.pebs_aliases = NULL;
x86_pmu.pebs_prec_dist = true;
x86_pmu.pebs_block = true;
@ -6167,6 +6172,7 @@ __init int intel_pmu_init(void)
pmu = &x86_pmu.hybrid_pmu[X86_HYBRID_PMU_CORE_IDX];
pmu->name = "cpu_core";
pmu->cpu_type = hybrid_big;
pmu->late_ack = true;
if (cpu_feature_enabled(X86_FEATURE_HYBRID_CPU)) {
pmu->num_counters = x86_pmu.num_counters + 2;
pmu->num_counters_fixed = x86_pmu.num_counters_fixed + 1;
@ -6192,6 +6198,7 @@ __init int intel_pmu_init(void)
pmu = &x86_pmu.hybrid_pmu[X86_HYBRID_PMU_ATOM_IDX];
pmu->name = "cpu_atom";
pmu->cpu_type = hybrid_small;
pmu->mid_ack = true;
pmu->num_counters = x86_pmu.num_counters;
pmu->num_counters_fixed = x86_pmu.num_counters_fixed;
pmu->max_pebs_events = x86_pmu.max_pebs_events;

View File

@ -656,6 +656,10 @@ struct x86_hybrid_pmu {
struct event_constraint *event_constraints;
struct event_constraint *pebs_constraints;
struct extra_reg *extra_regs;
unsigned int late_ack :1,
mid_ack :1,
enabled_ack :1;
};
static __always_inline struct x86_hybrid_pmu *hybrid_pmu(struct pmu *pmu)
@ -686,6 +690,16 @@ extern struct static_key_false perf_is_hybrid;
__Fp; \
}))
#define hybrid_bit(_pmu, _field) \
({ \
bool __Fp = x86_pmu._field; \
\
if (is_hybrid() && (_pmu)) \
__Fp = hybrid_pmu(_pmu)->_field; \
\
__Fp; \
})
enum hybrid_pmu_type {
hybrid_big = 0x40,
hybrid_small = 0x20,
@ -755,6 +769,7 @@ struct x86_pmu {
/* PMI handler bits */
unsigned int late_ack :1,
mid_ack :1,
enabled_ack :1;
/*
* sysfs attrs