[PATCH 2/3] perf, x86: Add Broadwell core support

[Andi Kleen]

From: Andi Kleen <ak@xxxxxxxxxxxxxxx>

Add Broadwell support for Broadwell to perf.

The basic support is very similar to Haswell. We use the new cache
event list added for Haswell earlier. The only differences
are a few bits related to remote nodes. To avoid an extra,
mostly identical, table these are patched up in the initialization code.

The constraint list has one new event that needs to be handled over Haswell.

Includes code and testing from Kan Liang.

v2: Remove unnamed model numbers.
v3: Rename cache event list to hsw_*. Change names.
v4: Use symbolic names for cache events. Improve comments and description.
    Fix sparse warnings (Fengguang Wu)
    Add Xeon D model number.
    Remove cache event table (in separate patch)
    Patch up remote node differences (Kan Liang)
Signed-off-by: Andi Kleen <ak@xxxxxxxxxxxxxxx>
---
 arch/x86/kernel/cpu/perf_event_intel.c | 48 ++++++++++++++++++++++++++++++++++
 1 file changed, 48 insertions(+)

diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index 387f580..7c480e8 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -220,6 +220,15 @@ static struct event_constraint intel_hsw_event_constraints[] = {
 	EVENT_CONSTRAINT_END
 };
 
+struct event_constraint intel_bdw_event_constraints[] = {
+	FIXED_EVENT_CONSTRAINT(0x00c0, 0),	/* INST_RETIRED.ANY */
+	FIXED_EVENT_CONSTRAINT(0x003c, 1),	/* CPU_CLK_UNHALTED.CORE */
+	FIXED_EVENT_CONSTRAINT(0x0300, 2),	/* CPU_CLK_UNHALTED.REF */
+	INTEL_UEVENT_CONSTRAINT(0x148, 0x4),	/* L1D_PEND_MISS.PENDING */
+	INTEL_EVENT_CONSTRAINT(0xa3, 0x4),	/* CYCLE_ACTIVITY.* */
+	EVENT_CONSTRAINT_END
+};
+
 static u64 intel_pmu_event_map(int hw_event)
 {
 	return intel_perfmon_event_map[hw_event];
@@ -433,12 +442,16 @@ static __initconst const u64 snb_hw_cache_event_ids
 #define HSW_ANY_RESPONSE		BIT(16)
 #define HSW_SUPPLIER_NONE		BIT(17)
 #define HSW_L3_MISS_LOCAL		BIT(22)
+#define BDW_L3_MISS_LOCAL		BIT(26)
 #define HSW_L3_MISS_REMOTE_HOP0		BIT(27)
 #define HSW_L3_MISS_REMOTE_HOP1		BIT(28)
 #define HSW_L3_MISS_REMOTE_HOP2P	BIT(29)
 #define HSW_L3_MISS			(HSW_L3_MISS_LOCAL| \
 					 HSW_L3_MISS_REMOTE_HOP0|HSW_L3_MISS_REMOTE_HOP1| \
 					 HSW_L3_MISS_REMOTE_HOP2P)
+#define BDW_L3_MISS			(BDW_L3_MISS_LOCAL| \
+					 HSW_L3_MISS_REMOTE_HOP0|HSW_L3_MISS_REMOTE_HOP1| \
+					 HSW_L3_MISS_REMOTE_HOP2P)
 #define HSW_SNOOP_NONE			BIT(31)
 #define HSW_SNOOP_NOT_NEEDED		BIT(32)
 #define HSW_SNOOP_MISS			BIT(33)
@@ -2759,6 +2772,41 @@ __init int intel_pmu_init(void)
 		pr_cont("Haswell events, ");
 		break;
 
+	case 61: /* 14nm Broadwell Core-M */
+	case 86: /* 14nm Broadwell Xeon D */
+		x86_pmu.late_ack = true;
+		memcpy(hw_cache_event_ids, hsw_hw_cache_event_ids, sizeof(hw_cache_event_ids));
+		memcpy(hw_cache_extra_regs, hsw_hw_cache_extra_regs, sizeof(hw_cache_extra_regs));
+
+		/* L3_MISS_LOCAL_DRAM is BIT(26) in Broadwell */
+		hw_cache_extra_regs[C(LL)][C(OP_READ)][C(RESULT_MISS)] = HSW_DEMAND_DATA_RD |
+									 BDW_L3_MISS|HSW_ANY_SNOOP|
+									 HSW_SUPPLIER_NONE;
+		hw_cache_extra_regs[C(LL)][C(OP_WRITE)][C(RESULT_MISS)] = HSW_ALL_RFO|BDW_L3_MISS|
+									  HSW_ANY_SNOOP|HSW_SUPPLIER_NONE;
+		hw_cache_extra_regs[C(NODE)][C(OP_READ)][C(RESULT_ACCESS)] = HSW_DEMAND_DATA_RD|
+									     BDW_L3_MISS_LOCAL|HSW_SUPPLIER_NONE|
+									     HSW_ANY_SNOOP;
+		hw_cache_extra_regs[C(NODE)][C(OP_WRITE)][C(RESULT_ACCESS)] = HSW_DEMAND_RFO|
+									      BDW_L3_MISS_LOCAL|HSW_SUPPLIER_NONE|
+									      HSW_ANY_SNOOP;
+
+		intel_pmu_lbr_init_snb();
+
+		x86_pmu.event_constraints = intel_bdw_event_constraints;
+		x86_pmu.pebs_constraints = intel_hsw_pebs_event_constraints;
+		x86_pmu.extra_regs = intel_snbep_extra_regs;
+		x86_pmu.pebs_aliases = intel_pebs_aliases_snb;
+		/* all extra regs are per-cpu when HT is on */
+		x86_pmu.er_flags |= ERF_HAS_RSP_1;
+		x86_pmu.er_flags |= ERF_NO_HT_SHARING;
+
+		x86_pmu.hw_config = hsw_hw_config;
+		x86_pmu.get_event_constraints = hsw_get_event_constraints;
+		x86_pmu.cpu_events = hsw_events_attrs;
+		pr_cont("Broadwell events, ");
+		break;
+
 	default:
 		switch (x86_pmu.version) {
 		case 1:
-- 
1.9.3

--
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/