[tip:perf/core] perf/x86: Implement cycles:p for SNB/IVB

From: tip-bot for Peter Zijlstra
Date: Wed Jun 06 2012 - 11:58:56 EST


Commit-ID: cccb9ba9e4ee0d750265f53de9258df69655c40b
Gitweb: http://git.kernel.org/tip/cccb9ba9e4ee0d750265f53de9258df69655c40b
Author: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
AuthorDate: Tue, 5 Jun 2012 10:26:43 +0200
Committer: Ingo Molnar <mingo@xxxxxxxxxx>
CommitDate: Wed, 6 Jun 2012 16:59:47 +0200

perf/x86: Implement cycles:p for SNB/IVB

Now that there's finally a chip with working PEBS (IvyBridge), we can
enable the hardware and implement cycles:p for SNB/IVB.

Cc: Stephane Eranian <eranian@xxxxxxxxxx>
Requested-and-tested-by: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@xxxxxxxxx>
Link: http://lkml.kernel.org/r/1338884803.28282.153.camel@twins
Signed-off-by: Ingo Molnar <mingo@xxxxxxxxxx>
---
arch/x86/kernel/cpu/perf_event.h | 1 +
arch/x86/kernel/cpu/perf_event_intel.c | 50 ++++++++++++++++++++++++++-----
2 files changed, 43 insertions(+), 8 deletions(-)

diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h
index 83794d8..7241e2f 100644
--- a/arch/x86/kernel/cpu/perf_event.h
+++ b/arch/x86/kernel/cpu/perf_event.h
@@ -365,6 +365,7 @@ struct x86_pmu {
int pebs_record_size;
void (*drain_pebs)(struct pt_regs *regs);
struct event_constraint *pebs_constraints;
+ void (*pebs_aliases)(struct perf_event *event);

/*
* Intel LBR
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index 965baa2..2312c1f 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -1336,15 +1336,9 @@ static void intel_put_event_constraints(struct cpu_hw_events *cpuc,
intel_put_shared_regs_event_constraints(cpuc, event);
}

-static int intel_pmu_hw_config(struct perf_event *event)
+static void intel_pebs_aliases_core2(struct perf_event *event)
{
- int ret = x86_pmu_hw_config(event);
-
- if (ret)
- return ret;
-
- if (event->attr.precise_ip &&
- (event->hw.config & X86_RAW_EVENT_MASK) == 0x003c) {
+ if ((event->hw.config & X86_RAW_EVENT_MASK) == 0x003c) {
/*
* Use an alternative encoding for CPU_CLK_UNHALTED.THREAD_P
* (0x003c) so that we can use it with PEBS.
@@ -1365,10 +1359,48 @@ static int intel_pmu_hw_config(struct perf_event *event)
*/
u64 alt_config = X86_CONFIG(.event=0xc0, .inv=1, .cmask=16);

+ alt_config |= (event->hw.config & ~X86_RAW_EVENT_MASK);
+ event->hw.config = alt_config;
+ }
+}
+
+static void intel_pebs_aliases_snb(struct perf_event *event)
+{
+ if ((event->hw.config & X86_RAW_EVENT_MASK) == 0x003c) {
+ /*
+ * Use an alternative encoding for CPU_CLK_UNHALTED.THREAD_P
+ * (0x003c) so that we can use it with PEBS.
+ *
+ * The regular CPU_CLK_UNHALTED.THREAD_P event (0x003c) isn't
+ * PEBS capable. However we can use UOPS_RETIRED.ALL
+ * (0x01c2), which is a PEBS capable event, to get the same
+ * count.
+ *
+ * UOPS_RETIRED.ALL counts the number of cycles that retires
+ * CNTMASK micro-ops. By setting CNTMASK to a value (16)
+ * larger than the maximum number of micro-ops that can be
+ * retired per cycle (4) and then inverting the condition, we
+ * count all cycles that retire 16 or less micro-ops, which
+ * is every cycle.
+ *
+ * Thereby we gain a PEBS capable cycle counter.
+ */
+ u64 alt_config = X86_CONFIG(.event=0xc2, .umask=0x01, .inv=1, .cmask=16);

alt_config |= (event->hw.config & ~X86_RAW_EVENT_MASK);
event->hw.config = alt_config;
}
+}
+
+static int intel_pmu_hw_config(struct perf_event *event)
+{
+ int ret = x86_pmu_hw_config(event);
+
+ if (ret)
+ return ret;
+
+ if (event->attr.precise_ip && x86_pmu.pebs_aliases)
+ x86_pmu.pebs_aliases(event);

if (intel_pmu_needs_lbr_smpl(event)) {
ret = intel_pmu_setup_lbr_filter(event);
@@ -1643,6 +1675,7 @@ static __initconst const struct x86_pmu intel_pmu = {
.max_period = (1ULL << 31) - 1,
.get_event_constraints = intel_get_event_constraints,
.put_event_constraints = intel_put_event_constraints,
+ .pebs_aliases = intel_pebs_aliases_core2,

.format_attrs = intel_arch3_formats_attr,

@@ -1885,6 +1918,7 @@ __init int intel_pmu_init(void)

x86_pmu.event_constraints = intel_snb_event_constraints;
x86_pmu.pebs_constraints = intel_snb_pebs_event_constraints;
+ x86_pmu.pebs_aliases = intel_pebs_aliases_snb;
x86_pmu.extra_regs = intel_snb_extra_regs;
/* all extra regs are per-cpu when HT is on */
x86_pmu.er_flags |= ERF_HAS_RSP_1;
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/