1 files changed, 53 insertions, 8 deletions

diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/events/intel/ds.c
index 10602f0a438f..8584b90d8e0b 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -5,7 +5,7 @@
 #include <asm/perf_event.h>
 #include <asm/insn.h>
 
-#include "perf_event.h"
+#include "../perf_event.h"
 
 /* The size of a BTS record in bytes: */
 #define BTS_RECORD_SIZE		24
@@ -51,7 +51,8 @@ union intel_x86_pebs_dse {
 #define OP_LH (P(OP, LOAD) | P(LVL, HIT))
 #define SNOOP_NONE_MISS (P(SNOOP, NONE) | P(SNOOP, MISS))
 
-static const u64 pebs_data_source[] = {
+/* Version for Sandy Bridge and later */
+static u64 pebs_data_source[] = {
 	P(OP, LOAD) | P(LVL, MISS) | P(LVL, L3) | P(SNOOP, NA),/* 0x00:ukn L3 */
 	OP_LH | P(LVL, L1)  | P(SNOOP, NONE),	/* 0x01: L1 local */
 	OP_LH | P(LVL, LFB) | P(SNOOP, NONE),	/* 0x02: LFB hit */
@@ -70,6 +71,14 @@ static const u64 pebs_data_source[] = {
 	OP_LH | P(LVL, UNC) | P(SNOOP, NONE), /* 0x0f: uncached */
 };
 
+/* Patch up minor differences in the bits */
+void __init intel_pmu_pebs_data_source_nhm(void)
+{
+	pebs_data_source[0x05] = OP_LH | P(LVL, L3)  | P(SNOOP, HIT);
+	pebs_data_source[0x06] = OP_LH | P(LVL, L3)  | P(SNOOP, HITM);
+	pebs_data_source[0x07] = OP_LH | P(LVL, L3)  | P(SNOOP, HITM);
+}
+
 static u64 precise_store_data(u64 status)
 {
 	union intel_x86_pebs_dse dse;
@@ -269,7 +278,7 @@ static int alloc_pebs_buffer(int cpu)
 	if (!x86_pmu.pebs)
 		return 0;
 
-	buffer = kzalloc_node(PEBS_BUFFER_SIZE, GFP_KERNEL, node);
+	buffer = kzalloc_node(x86_pmu.pebs_buffer_size, GFP_KERNEL, node);
 	if (unlikely(!buffer))
 		return -ENOMEM;
 
@@ -286,7 +295,7 @@ static int alloc_pebs_buffer(int cpu)
 		per_cpu(insn_buffer, cpu) = ibuffer;
 	}
 
-	max = PEBS_BUFFER_SIZE / x86_pmu.pebs_record_size;
+	max = x86_pmu.pebs_buffer_size / x86_pmu.pebs_record_size;
 
 	ds->pebs_buffer_base = (u64)(unsigned long)buffer;
 	ds->pebs_index = ds->pebs_buffer_base;
@@ -561,11 +570,12 @@ int intel_pmu_drain_bts_buffer(void)
 	 * We will overwrite the from and to address before we output
 	 * the sample.
 	 */
+	rcu_read_lock();
 	perf_prepare_sample(&header, &data, event, &regs);
 
 	if (perf_output_begin(&handle, event, header.size *
 			      (top - base - skip)))
-		return 1;
+		goto unlock;
 
 	for (at = base; at < top; at++) {
 		/* Filter out any records that contain kernel addresses. */
@@ -584,6 +594,8 @@ int intel_pmu_drain_bts_buffer(void)
 	/* There's new data available. */
 	event->hw.interrupts++;
 	event->pending_kill = POLL_IN;
+unlock:
+	rcu_read_unlock();
 	return 1;
 }
 
@@ -722,6 +734,30 @@ struct event_constraint intel_hsw_pebs_event_constraints[] = {
 	EVENT_CONSTRAINT_END
 };
 
+struct event_constraint intel_bdw_pebs_event_constraints[] = {
+	INTEL_FLAGS_UEVENT_CONSTRAINT(0x01c0, 0x2), /* INST_RETIRED.PRECDIST */
+	INTEL_PLD_CONSTRAINT(0x01cd, 0xf),    /* MEM_TRANS_RETIRED.* */
+	/* UOPS_RETIRED.ALL, inv=1, cmask=16 (cycles:p). */
+	INTEL_FLAGS_EVENT_CONSTRAINT(0x108001c2, 0xf),
+	/* INST_RETIRED.PREC_DIST, inv=1, cmask=16 (cycles:ppp). */
+	INTEL_FLAGS_EVENT_CONSTRAINT(0x108001c0, 0x2),
+	INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_NA(0x01c2, 0xf), /* UOPS_RETIRED.ALL */
+	INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x11d0, 0xf), /* MEM_UOPS_RETIRED.STLB_MISS_LOADS */
+	INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x21d0, 0xf), /* MEM_UOPS_RETIRED.LOCK_LOADS */
+	INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x41d0, 0xf), /* MEM_UOPS_RETIRED.SPLIT_LOADS */
+	INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x81d0, 0xf), /* MEM_UOPS_RETIRED.ALL_LOADS */
+	INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x12d0, 0xf), /* MEM_UOPS_RETIRED.STLB_MISS_STORES */
+	INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x42d0, 0xf), /* MEM_UOPS_RETIRED.SPLIT_STORES */
+	INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x82d0, 0xf), /* MEM_UOPS_RETIRED.ALL_STORES */
+	INTEL_FLAGS_EVENT_CONSTRAINT_DATALA_LD(0xd1, 0xf),    /* MEM_LOAD_UOPS_RETIRED.* */
+	INTEL_FLAGS_EVENT_CONSTRAINT_DATALA_LD(0xd2, 0xf),    /* MEM_LOAD_UOPS_L3_HIT_RETIRED.* */
+	INTEL_FLAGS_EVENT_CONSTRAINT_DATALA_LD(0xd3, 0xf),    /* MEM_LOAD_UOPS_L3_MISS_RETIRED.* */
+	/* Allow all events as PEBS with no flags */
+	INTEL_ALL_EVENT_CONSTRAINT(0, 0xf),
+	EVENT_CONSTRAINT_END
+};
+
+
 struct event_constraint intel_skl_pebs_event_constraints[] = {
 	INTEL_FLAGS_UEVENT_CONSTRAINT(0x1c0, 0x2),	/* INST_RETIRED.PREC_DIST */
 	/* INST_RETIRED.PREC_DIST, inv=1, cmask=16 (cycles:ppp). */
@@ -1319,19 +1355,28 @@ void __init intel_ds_init(void)
 
 	x86_pmu.bts  = boot_cpu_has(X86_FEATURE_BTS);
 	x86_pmu.pebs = boot_cpu_has(X86_FEATURE_PEBS);
+	x86_pmu.pebs_buffer_size = PEBS_BUFFER_SIZE;
 	if (x86_pmu.pebs) {
 		char pebs_type = x86_pmu.intel_cap.pebs_trap ?  '+' : '-';
 		int format = x86_pmu.intel_cap.pebs_format;
 
 		switch (format) {
 		case 0:
-			printk(KERN_CONT "PEBS fmt0%c, ", pebs_type);
+			pr_cont("PEBS fmt0%c, ", pebs_type);
 			x86_pmu.pebs_record_size = sizeof(struct pebs_record_core);
+			/*
+			 * Using >PAGE_SIZE buffers makes the WRMSR to
+			 * PERF_GLOBAL_CTRL in intel_pmu_enable_all()
+			 * mysteriously hang on Core2.
+			 *
+			 * As a workaround, we don't do this.
+			 */
+			x86_pmu.pebs_buffer_size = PAGE_SIZE;
 			x86_pmu.drain_pebs = intel_pmu_drain_pebs_core;
 			break;
 
 		case 1:
-			printk(KERN_CONT "PEBS fmt1%c, ", pebs_type);
+			pr_cont("PEBS fmt1%c, ", pebs_type);
 			x86_pmu.pebs_record_size = sizeof(struct pebs_record_nhm);
 			x86_pmu.drain_pebs = intel_pmu_drain_pebs_nhm;
 			break;
@@ -1351,7 +1396,7 @@ void __init intel_ds_init(void)
 			break;
 
 		default:
-			printk(KERN_CONT "no PEBS fmt%d%c, ", format, pebs_type);
+			pr_cont("no PEBS fmt%d%c, ", format, pebs_type);
 			x86_pmu.pebs = 0;
 		}
 	}