perf_events: Add Intel Sandy Bridge offcore_response low-level support

This patch adds Intel Sandy Bridge offcore_response support by
providing the low-level constraint table for those events.

On Sandy Bridge, there are two offcore_response events. Each uses
its own dedictated extra register. But those registers are NOT shared
between sibling CPUs when HT is on unlike Nehalem/Westmere. They are
always private to each CPU. But they still need to be controlled within
an event group. All events within an event group must use the same
value for the extra MSR. That's not controlled by the second patch in
this series.

Furthermore on Sandy Bridge, the offcore_response events have NO
counter constraints contrary to what the official documentation
indicates, so drop the events from the contraint table.

Signed-off-by: Stephane Eranian <eranian@google.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/20110606145712.GA7304@quad
Signed-off-by: Ingo Molnar <mingo@elte.hu>

arch/x86/kernel/cpu/perf_event.c

@@ -327,6 +327,7 @@ struct x86_pmu {
 	 * Extra registers for events
 	 */
 	struct extra_reg *extra_regs;
+	bool regs_no_ht_sharing;
 };
 
 static struct x86_pmu x86_pmu __read_mostly;

arch/x86/kernel/cpu/perf_event_intel.c

@@ -100,8 +100,6 @@ static struct event_constraint intel_snb_event_constraints[] __read_mostly =
 	FIXED_EVENT_CONSTRAINT(0x003c, 1), /* CPU_CLK_UNHALTED.CORE */
 	/* FIXED_EVENT_CONSTRAINT(0x013c, 2), CPU_CLK_UNHALTED.REF */
 	INTEL_EVENT_CONSTRAINT(0x48, 0x4), /* L1D_PEND_MISS.PENDING */
-	INTEL_EVENT_CONSTRAINT(0xb7, 0x1), /* OFF_CORE_RESPONSE_0 */
-	INTEL_EVENT_CONSTRAINT(0xbb, 0x8), /* OFF_CORE_RESPONSE_1 */
 	INTEL_UEVENT_CONSTRAINT(0x01c0, 0x2), /* INST_RETIRED.PREC_DIST */
 	INTEL_EVENT_CONSTRAINT(0xcd, 0x8), /* MEM_TRANS_RETIRED.LOAD_LATENCY */
 	EVENT_CONSTRAINT_END
@@ -122,6 +120,12 @@ static struct event_constraint intel_gen_event_constraints[] __read_mostly =
 	EVENT_CONSTRAINT_END
 };
 
+static struct extra_reg intel_snb_extra_regs[] __read_mostly = {
+	INTEL_EVENT_EXTRA_REG(0xb7, MSR_OFFCORE_RSP_0, 0x3fffffffffull, RSP_0),
+	INTEL_EVENT_EXTRA_REG(0xbb, MSR_OFFCORE_RSP_1, 0x3fffffffffull, RSP_1),
+	EVENT_EXTRA_END
+};
+
 static u64 intel_pmu_event_map(int hw_event)
 {
 	return intel_perfmon_event_map[hw_event];
@@ -1260,7 +1264,7 @@ static void intel_pmu_cpu_starting(int cpu)
 	 */
 	intel_pmu_lbr_reset();
 
-	if (!cpuc->shared_regs)
+	if (!cpuc->shared_regs || x86_pmu.regs_no_ht_sharing)
 		return;
 
 	for_each_cpu(i, topology_thread_cpumask(cpu)) {
@@ -1502,6 +1506,9 @@ static __init int intel_pmu_init(void)
 
 		x86_pmu.event_constraints = intel_snb_event_constraints;
 		x86_pmu.pebs_constraints = intel_snb_pebs_events;
+		x86_pmu.extra_regs = intel_snb_extra_regs;
+		/* all extra regs are per-cpu when HT is on */
+		x86_pmu.regs_no_ht_sharing = true;
 
 		/* UOPS_ISSUED.ANY,c=1,i=1 to count stall cycles */
 		intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = 0x180010e;