Merge branch 'perf/core'

105 files changed, 6561 insertions, 4782 deletions

diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h
index 8249df45d2f2b5..8dfc9fd094a3b3 100644
--- a/arch/x86/include/asm/perf_event.h
+++ b/arch/x86/include/asm/perf_event.h
@@ -51,6 +51,14 @@
 	 ARCH_PERFMON_EVENTSEL_EDGE  |	\
 	 ARCH_PERFMON_EVENTSEL_INV   |	\
 	 ARCH_PERFMON_EVENTSEL_CMASK)
+#define X86_ALL_EVENT_FLAGS  			\
+	(ARCH_PERFMON_EVENTSEL_EDGE |  		\
+	 ARCH_PERFMON_EVENTSEL_INV | 		\
+	 ARCH_PERFMON_EVENTSEL_CMASK | 		\
+	 ARCH_PERFMON_EVENTSEL_ANY | 		\
+	 ARCH_PERFMON_EVENTSEL_PIN_CONTROL | 	\
+	 HSW_IN_TX | 				\
+	 HSW_IN_TX_CHECKPOINTED)
 #define AMD64_RAW_EVENT_MASK		\
 	(X86_RAW_EVENT_MASK          |  \
 	 AMD64_EVENTSEL_EVENT)
diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile
index 7fd54f09b011e2..7e1fd4e08552e8 100644
--- a/arch/x86/kernel/cpu/Makefile
+++ b/arch/x86/kernel/cpu/Makefile
@@ -36,7 +36,9 @@ obj-$(CONFIG_CPU_SUP_AMD)		+= perf_event_amd_iommu.o
 endif
 obj-$(CONFIG_CPU_SUP_INTEL)		+= perf_event_p6.o perf_event_knc.o perf_event_p4.o
 obj-$(CONFIG_CPU_SUP_INTEL)		+= perf_event_intel_lbr.o perf_event_intel_ds.o perf_event_intel.o
-obj-$(CONFIG_CPU_SUP_INTEL)		+= perf_event_intel_uncore.o perf_event_intel_rapl.o
+obj-$(CONFIG_CPU_SUP_INTEL)		+= perf_event_intel_uncore.o perf_event_intel_uncore_snb.o
+obj-$(CONFIG_CPU_SUP_INTEL)		+= perf_event_intel_uncore_snbep.o perf_event_intel_uncore_nhmex.o
+obj-$(CONFIG_CPU_SUP_INTEL)		+= perf_event_intel_rapl.o
 endif
 
 
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index 2879ecdaac430c..0646d3b63b9d6f 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -387,7 +387,7 @@ int x86_pmu_hw_config(struct perf_event *event)
 			precise++;
 
 			/* Support for IP fixup */
-			if (x86_pmu.lbr_nr)
+			if (x86_pmu.lbr_nr || x86_pmu.intel_cap.pebs_format >= 2)
 				precise++;
 		}
 
diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h
index 8ade93111e0379..fc5eb390b3685d 100644
--- a/arch/x86/kernel/cpu/perf_event.h
+++ b/arch/x86/kernel/cpu/perf_event.h
@@ -67,8 +67,10 @@ struct event_constraint {
  */
 #define PERF_X86_EVENT_PEBS_LDLAT	0x1 /* ld+ldlat data address sampling */
 #define PERF_X86_EVENT_PEBS_ST		0x2 /* st data address sampling */
-#define PERF_X86_EVENT_PEBS_ST_HSW	0x4 /* haswell style st data sampling */
+#define PERF_X86_EVENT_PEBS_ST_HSW	0x4 /* haswell style datala, store */
 #define PERF_X86_EVENT_COMMITTED	0x8 /* event passed commit_txn */
+#define PERF_X86_EVENT_PEBS_LD_HSW	0x10 /* haswell style datala, load */
+#define PERF_X86_EVENT_PEBS_NA_HSW	0x20 /* haswell style datala, unknown */
 
 struct amd_nb {
 	int nb_id;  /* NorthBridge id */
@@ -252,18 +254,52 @@ struct cpu_hw_events {
 	EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK)
 
 #define INTEL_PLD_CONSTRAINT(c, n)	\
-	__EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK, \
+	__EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK|X86_ALL_EVENT_FLAGS, \
 			   HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_LDLAT)
 
 #define INTEL_PST_CONSTRAINT(c, n)	\
-	__EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK, \
+	__EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK|X86_ALL_EVENT_FLAGS, \
 			  HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_ST)
 
-/* DataLA version of store sampling without extra enable bit. */
-#define INTEL_PST_HSW_CONSTRAINT(c, n)	\
-	__EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK, \
+/* Event constraint, but match on all event flags too. */
+#define INTEL_FLAGS_EVENT_CONSTRAINT(c, n) \
+	EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK|X86_ALL_EVENT_FLAGS)
+
+/* Check only flags, but allow all event/umask */
+#define INTEL_ALL_EVENT_CONSTRAINT(code, n)	\
+	EVENT_CONSTRAINT(code, n, X86_ALL_EVENT_FLAGS)
+
+/* Check flags and event code, and set the HSW store flag */
+#define INTEL_FLAGS_EVENT_CONSTRAINT_DATALA_ST(code, n) \
+	__EVENT_CONSTRAINT(code, n, 			\
+			  ARCH_PERFMON_EVENTSEL_EVENT|X86_ALL_EVENT_FLAGS, \
+			  HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_ST_HSW)
+
+/* Check flags and event code, and set the HSW load flag */
+#define INTEL_FLAGS_EVENT_CONSTRAINT_DATALA_LD(code, n) \
+	__EVENT_CONSTRAINT(code, n, 			\
+			  ARCH_PERFMON_EVENTSEL_EVENT|X86_ALL_EVENT_FLAGS, \
+			  HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_LD_HSW)
+
+/* Check flags and event code/umask, and set the HSW store flag */
+#define INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(code, n) \
+	__EVENT_CONSTRAINT(code, n, 			\
+			  INTEL_ARCH_EVENT_MASK|X86_ALL_EVENT_FLAGS, \
 			  HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_ST_HSW)
 
+/* Check flags and event code/umask, and set the HSW load flag */
+#define INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(code, n) \
+	__EVENT_CONSTRAINT(code, n, 			\
+			  INTEL_ARCH_EVENT_MASK|X86_ALL_EVENT_FLAGS, \
+			  HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_LD_HSW)
+
+/* Check flags and event code/umask, and set the HSW N/A flag */
+#define INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_NA(code, n) \
+	__EVENT_CONSTRAINT(code, n, 			\
+			  INTEL_ARCH_EVENT_MASK|INTEL_ARCH_EVENT_MASK, \
+			  HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_NA_HSW)
+
+
 /*
  * We define the end marker as having a weight of -1
  * to enable blacklisting of events using a counter bitmask
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index 2502d0d9d246a1..89bc750efccb0d 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -2367,15 +2367,15 @@ __init int intel_pmu_init(void)
 	 * Install the hw-cache-events table:
 	 */
 	switch (boot_cpu_data.x86_model) {
-	case 14: /* 65 nm core solo/duo, "Yonah" */
+	case 14: /* 65nm Core "Yonah" */
 		pr_cont("Core events, ");
 		break;
 
-	case 15: /* original 65 nm celeron/pentium/core2/xeon, "Merom"/"Conroe" */
+	case 15: /* 65nm Core2 "Merom"          */
 		x86_add_quirk(intel_clovertown_quirk);
-	case 22: /* single-core 65 nm celeron/core2solo "Merom-L"/"Conroe-L" */
-	case 23: /* current 45 nm celeron/core2/xeon "Penryn"/"Wolfdale" */
-	case 29: /* six-core 45 nm xeon "Dunnington" */
+	case 22: /* 65nm Core2 "Merom-L"        */
+	case 23: /* 45nm Core2 "Penryn"         */
+	case 29: /* 45nm Core2 "Dunnington (MP) */
 		memcpy(hw_cache_event_ids, core2_hw_cache_event_ids,
 		       sizeof(hw_cache_event_ids));
 
@@ -2386,9 +2386,9 @@ __init int intel_pmu_init(void)
 		pr_cont("Core2 events, ");
 		break;
 
-	case 26: /* 45 nm nehalem, "Bloomfield" */
-	case 30: /* 45 nm nehalem, "Lynnfield" */
-	case 46: /* 45 nm nehalem-ex, "Beckton" */
+	case 30: /* 45nm Nehalem    */
+	case 26: /* 45nm Nehalem-EP */
+	case 46: /* 45nm Nehalem-EX */
 		memcpy(hw_cache_event_ids, nehalem_hw_cache_event_ids,
 		       sizeof(hw_cache_event_ids));
 		memcpy(hw_cache_extra_regs, nehalem_hw_cache_extra_regs,
@@ -2415,11 +2415,11 @@ __init int intel_pmu_init(void)
 		pr_cont("Nehalem events, ");
 		break;
 
-	case 28: /* Atom */
-	case 38: /* Lincroft */
-	case 39: /* Penwell */
-	case 53: /* Cloverview */
-	case 54: /* Cedarview */
+	case 28: /* 45nm Atom "Pineview"   */
+	case 38: /* 45nm Atom "Lincroft"   */
+	case 39: /* 32nm Atom "Penwell"    */
+	case 53: /* 32nm Atom "Cloverview" */
+	case 54: /* 32nm Atom "Cedarview"  */
 		memcpy(hw_cache_event_ids, atom_hw_cache_event_ids,
 		       sizeof(hw_cache_event_ids));
 
@@ -2430,8 +2430,8 @@ __init int intel_pmu_init(void)
 		pr_cont("Atom events, ");
 		break;
 
-	case 55: /* Atom 22nm "Silvermont" */
-	case 77: /* Avoton "Silvermont" */
+	case 55: /* 22nm Atom "Silvermont"                */
+	case 77: /* 22nm Atom "Silvermont Avoton/Rangely" */
 		memcpy(hw_cache_event_ids, slm_hw_cache_event_ids,
 			sizeof(hw_cache_event_ids));
 		memcpy(hw_cache_extra_regs, slm_hw_cache_extra_regs,
@@ -2446,9 +2446,9 @@ __init int intel_pmu_init(void)
 		pr_cont("Silvermont events, ");
 		break;
 
-	case 37: /* 32 nm nehalem, "Clarkdale" */
-	case 44: /* 32 nm nehalem, "Gulftown" */
-	case 47: /* 32 nm Xeon E7 */
+	case 37: /* 32nm Westmere    */
+	case 44: /* 32nm Westmere-EP */
+	case 47: /* 32nm Westmere-EX */
 		memcpy(hw_cache_event_ids, westmere_hw_cache_event_ids,
 		       sizeof(hw_cache_event_ids));
 		memcpy(hw_cache_extra_regs, nehalem_hw_cache_extra_regs,
@@ -2474,8 +2474,8 @@ __init int intel_pmu_init(void)
 		pr_cont("Westmere events, ");
 		break;
 
-	case 42: /* SandyBridge */
-	case 45: /* SandyBridge, "Romely-EP" */
+	case 42: /* 32nm SandyBridge         */
+	case 45: /* 32nm SandyBridge-E/EN/EP */
 		x86_add_quirk(intel_sandybridge_quirk);
 		memcpy(hw_cache_event_ids, snb_hw_cache_event_ids,
 		       sizeof(hw_cache_event_ids));
@@ -2506,8 +2506,9 @@ __init int intel_pmu_init(void)
 
 		pr_cont("SandyBridge events, ");
 		break;
-	case 58: /* IvyBridge */
-	case 62: /* IvyBridge EP */
+
+	case 58: /* 22nm IvyBridge       */
+	case 62: /* 22nm IvyBridge-EP/EX */
 		memcpy(hw_cache_event_ids, snb_hw_cache_event_ids,
 		       sizeof(hw_cache_event_ids));
 		/* dTLB-load-misses on IVB is different than SNB */
@@ -2539,11 +2540,11 @@ __init int intel_pmu_init(void)
 		break;
 
 
-	case 60: /* Haswell Client */
-	case 70:
-	case 71:
+	case 60: /* 22nm Haswell */
 	case 63:
 	case 69:
+	case 70:
+	case 71:
 		x86_pmu.late_ack = true;
 		memcpy(hw_cache_event_ids, snb_hw_cache_event_ids, sizeof(hw_cache_event_ids));
 		memcpy(hw_cache_extra_regs, snb_hw_cache_extra_regs, sizeof(hw_cache_extra_regs));
@@ -2552,7 +2553,7 @@ __init int intel_pmu_init(void)
 
 		x86_pmu.event_constraints = intel_hsw_event_constraints;
 		x86_pmu.pebs_constraints = intel_hsw_pebs_event_constraints;
-		x86_pmu.extra_regs = intel_snb_extra_regs;
+		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;
diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c
index 696ade311ded7d..9dc41999177270 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_ds.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c
@@ -108,14 +108,16 @@ static u64 precise_store_data(u64 status)
 	return val;
 }
 
-static u64 precise_store_data_hsw(struct perf_event *event, u64 status)
+static u64 precise_datala_hsw(struct perf_event *event, u64 status)
 {
 	union perf_mem_data_src dse;
-	u64 cfg = event->hw.config & INTEL_ARCH_EVENT_MASK;
 
-	dse.val = 0;
-	dse.mem_op = PERF_MEM_OP_STORE;
-	dse.mem_lvl = PERF_MEM_LVL_NA;
+	dse.val = PERF_MEM_NA;
+
+	if (event->hw.flags & PERF_X86_EVENT_PEBS_ST_HSW)
+		dse.mem_op = PERF_MEM_OP_STORE;
+	else if (event->hw.flags & PERF_X86_EVENT_PEBS_LD_HSW)
+		dse.mem_op = PERF_MEM_OP_LOAD;
 
 	/*
 	 * L1 info only valid for following events:
@@ -125,15 +127,12 @@ static u64 precise_store_data_hsw(struct perf_event *event, u64 status)
 	 * MEM_UOPS_RETIRED.SPLIT_STORES
 	 * MEM_UOPS_RETIRED.ALL_STORES
 	 */
-	if (cfg != 0x12d0 && cfg != 0x22d0 && cfg != 0x42d0 && cfg != 0x82d0)
-		return dse.mem_lvl;
-
-	if (status & 1)
-		dse.mem_lvl = PERF_MEM_LVL_L1 | PERF_MEM_LVL_HIT;
-	else
-		dse.mem_lvl = PERF_MEM_LVL_L1 | PERF_MEM_LVL_MISS;
-
-	/* Nothing else supported. Sorry. */
+	if (event->hw.flags & PERF_X86_EVENT_PEBS_ST_HSW) {
+		if (status & 1)
+			dse.mem_lvl = PERF_MEM_LVL_L1 | PERF_MEM_LVL_HIT;
+		else
+			dse.mem_lvl = PERF_MEM_LVL_L1 | PERF_MEM_LVL_MISS;
+	}
 	return dse.val;
 }
 
@@ -569,28 +568,10 @@ struct event_constraint intel_atom_pebs_event_constraints[] = {
 };
 
 struct event_constraint intel_slm_pebs_event_constraints[] = {
-	INTEL_UEVENT_CONSTRAINT(0x0103, 0x1), /* REHABQ.LD_BLOCK_ST_FORWARD_PS */
-	INTEL_UEVENT_CONSTRAINT(0x0803, 0x1), /* REHABQ.LD_SPLITS_PS */
-	INTEL_UEVENT_CONSTRAINT(0x0204, 0x1), /* MEM_UOPS_RETIRED.L2_HIT_LOADS_PS */
-	INTEL_UEVENT_CONSTRAINT(0x0404, 0x1), /* MEM_UOPS_RETIRED.L2_MISS_LOADS_PS */
-	INTEL_UEVENT_CONSTRAINT(0x0804, 0x1), /* MEM_UOPS_RETIRED.DTLB_MISS_LOADS_PS */
-	INTEL_UEVENT_CONSTRAINT(0x2004, 0x1), /* MEM_UOPS_RETIRED.HITM_PS */
-	INTEL_UEVENT_CONSTRAINT(0x00c0, 0x1), /* INST_RETIRED.ANY_PS */
-	INTEL_UEVENT_CONSTRAINT(0x00c4, 0x1), /* BR_INST_RETIRED.ALL_BRANCHES_PS */
-	INTEL_UEVENT_CONSTRAINT(0x7ec4, 0x1), /* BR_INST_RETIRED.JCC_PS */
-	INTEL_UEVENT_CONSTRAINT(0xbfc4, 0x1), /* BR_INST_RETIRED.FAR_BRANCH_PS */
-	INTEL_UEVENT_CONSTRAINT(0xebc4, 0x1), /* BR_INST_RETIRED.NON_RETURN_IND_PS */
-	INTEL_UEVENT_CONSTRAINT(0xf7c4, 0x1), /* BR_INST_RETIRED.RETURN_PS */
-	INTEL_UEVENT_CONSTRAINT(0xf9c4, 0x1), /* BR_INST_RETIRED.CALL_PS */
-	INTEL_UEVENT_CONSTRAINT(0xfbc4, 0x1), /* BR_INST_RETIRED.IND_CALL_PS */
-	INTEL_UEVENT_CONSTRAINT(0xfdc4, 0x1), /* BR_INST_RETIRED.REL_CALL_PS */
-	INTEL_UEVENT_CONSTRAINT(0xfec4, 0x1), /* BR_INST_RETIRED.TAKEN_JCC_PS */
-	INTEL_UEVENT_CONSTRAINT(0x00c5, 0x1), /* BR_INST_MISP_RETIRED.ALL_BRANCHES_PS */
-	INTEL_UEVENT_CONSTRAINT(0x7ec5, 0x1), /* BR_INST_MISP_RETIRED.JCC_PS */
-	INTEL_UEVENT_CONSTRAINT(0xebc5, 0x1), /* BR_INST_MISP_RETIRED.NON_RETURN_IND_PS */
-	INTEL_UEVENT_CONSTRAINT(0xf7c5, 0x1), /* BR_INST_MISP_RETIRED.RETURN_PS */
-	INTEL_UEVENT_CONSTRAINT(0xfbc5, 0x1), /* BR_INST_MISP_RETIRED.IND_CALL_PS */
-	INTEL_UEVENT_CONSTRAINT(0xfec5, 0x1), /* BR_INST_MISP_RETIRED.TAKEN_JCC_PS */
+	/* UOPS_RETIRED.ALL, inv=1, cmask=16 (cycles:p). */
+	INTEL_FLAGS_EVENT_CONSTRAINT(0x108001c2, 0xf),
+	/* Allow all events as PEBS with no flags */
+	INTEL_ALL_EVENT_CONSTRAINT(0, 0x1),
 	EVENT_CONSTRAINT_END
 };
 
@@ -626,68 +607,44 @@ struct event_constraint intel_westmere_pebs_event_constraints[] = {
 
 struct event_constraint intel_snb_pebs_event_constraints[] = {
 	INTEL_UEVENT_CONSTRAINT(0x01c0, 0x2), /* INST_RETIRED.PRECDIST */
-	INTEL_UEVENT_CONSTRAINT(0x01c2, 0xf), /* UOPS_RETIRED.ALL */
-	INTEL_UEVENT_CONSTRAINT(0x02c2, 0xf), /* UOPS_RETIRED.RETIRE_SLOTS */
-	INTEL_EVENT_CONSTRAINT(0xc4, 0xf),    /* BR_INST_RETIRED.* */
-	INTEL_EVENT_CONSTRAINT(0xc5, 0xf),    /* BR_MISP_RETIRED.* */
 	INTEL_PLD_CONSTRAINT(0x01cd, 0x8),    /* MEM_TRANS_RETIRED.LAT_ABOVE_THR */
 	INTEL_PST_CONSTRAINT(0x02cd, 0x8),    /* MEM_TRANS_RETIRED.PRECISE_STORES */
-	INTEL_EVENT_CONSTRAINT(0xd0, 0xf),    /* MEM_UOP_RETIRED.* */
-	INTEL_EVENT_CONSTRAINT(0xd1, 0xf),    /* MEM_LOAD_UOPS_RETIRED.* */
-	INTEL_EVENT_CONSTRAINT(0xd2, 0xf),    /* MEM_LOAD_UOPS_LLC_HIT_RETIRED.* */
-	INTEL_EVENT_CONSTRAINT(0xd3, 0xf),    /* MEM_LOAD_UOPS_LLC_MISS_RETIRED.* */
-	INTEL_UEVENT_CONSTRAINT(0x02d4, 0xf), /* MEM_LOAD_UOPS_MISC_RETIRED.LLC_MISS */
+	/* UOPS_RETIRED.ALL, inv=1, cmask=16 (cycles:p). */
+	INTEL_FLAGS_EVENT_CONSTRAINT(0x108001c2, 0xf),
+	/* Allow all events as PEBS with no flags */
+	INTEL_ALL_EVENT_CONSTRAINT(0, 0xf),
 	EVENT_CONSTRAINT_END
 };
 
 struct event_constraint intel_ivb_pebs_event_constraints[] = {
         INTEL_UEVENT_CONSTRAINT(0x01c0, 0x2), /* INST_RETIRED.PRECDIST */
-        INTEL_UEVENT_CONSTRAINT(0x01c2, 0xf), /* UOPS_RETIRED.ALL */
-        INTEL_UEVENT_CONSTRAINT(0x02c2, 0xf), /* UOPS_RETIRED.RETIRE_SLOTS */
-        INTEL_EVENT_CONSTRAINT(0xc4, 0xf),    /* BR_INST_RETIRED.* */
-        INTEL_EVENT_CONSTRAINT(0xc5, 0xf),    /* BR_MISP_RETIRED.* */
         INTEL_PLD_CONSTRAINT(0x01cd, 0x8),    /* MEM_TRANS_RETIRED.LAT_ABOVE_THR */
 	INTEL_PST_CONSTRAINT(0x02cd, 0x8),    /* MEM_TRANS_RETIRED.PRECISE_STORES */
-        INTEL_EVENT_CONSTRAINT(0xd0, 0xf),    /* MEM_UOP_RETIRED.* */
-        INTEL_EVENT_CONSTRAINT(0xd1, 0xf),    /* MEM_LOAD_UOPS_RETIRED.* */
-        INTEL_EVENT_CONSTRAINT(0xd2, 0xf),    /* MEM_LOAD_UOPS_LLC_HIT_RETIRED.* */
-        INTEL_EVENT_CONSTRAINT(0xd3, 0xf),    /* MEM_LOAD_UOPS_LLC_MISS_RETIRED.* */
+	/* UOPS_RETIRED.ALL, inv=1, cmask=16 (cycles:p). */
+	INTEL_FLAGS_EVENT_CONSTRAINT(0x108001c2, 0xf),
+	/* Allow all events as PEBS with no flags */
+	INTEL_ALL_EVENT_CONSTRAINT(0, 0xf),
         EVENT_CONSTRAINT_END
 };
 
 struct event_constraint intel_hsw_pebs_event_constraints[] = {
 	INTEL_UEVENT_CONSTRAINT(0x01c0, 0x2), /* INST_RETIRED.PRECDIST */
-	INTEL_PST_HSW_CONSTRAINT(0x01c2, 0xf), /* UOPS_RETIRED.ALL */
-	INTEL_UEVENT_CONSTRAINT(0x02c2, 0xf), /* UOPS_RETIRED.RETIRE_SLOTS */
-	INTEL_EVENT_CONSTRAINT(0xc4, 0xf),    /* BR_INST_RETIRED.* */
-	INTEL_UEVENT_CONSTRAINT(0x01c5, 0xf), /* BR_MISP_RETIRED.CONDITIONAL */
-	INTEL_UEVENT_CONSTRAINT(0x04c5, 0xf), /* BR_MISP_RETIRED.ALL_BRANCHES */
-	INTEL_UEVENT_CONSTRAINT(0x20c5, 0xf), /* BR_MISP_RETIRED.NEAR_TAKEN */
-	INTEL_PLD_CONSTRAINT(0x01cd, 0x8),    /* MEM_TRANS_RETIRED.* */
-	/* MEM_UOPS_RETIRED.STLB_MISS_LOADS */
-	INTEL_UEVENT_CONSTRAINT(0x11d0, 0xf),
-	/* MEM_UOPS_RETIRED.STLB_MISS_STORES */
-	INTEL_UEVENT_CONSTRAINT(0x12d0, 0xf),
-	INTEL_UEVENT_CONSTRAINT(0x21d0, 0xf), /* MEM_UOPS_RETIRED.LOCK_LOADS */
-	INTEL_UEVENT_CONSTRAINT(0x41d0, 0xf), /* MEM_UOPS_RETIRED.SPLIT_LOADS */
-	/* MEM_UOPS_RETIRED.SPLIT_STORES */
-	INTEL_UEVENT_CONSTRAINT(0x42d0, 0xf),
-	INTEL_UEVENT_CONSTRAINT(0x81d0, 0xf), /* MEM_UOPS_RETIRED.ALL_LOADS */
-	INTEL_PST_HSW_CONSTRAINT(0x82d0, 0xf), /* MEM_UOPS_RETIRED.ALL_STORES */
-	INTEL_UEVENT_CONSTRAINT(0x01d1, 0xf), /* MEM_LOAD_UOPS_RETIRED.L1_HIT */
-	INTEL_UEVENT_CONSTRAINT(0x02d1, 0xf), /* MEM_LOAD_UOPS_RETIRED.L2_HIT */
-	INTEL_UEVENT_CONSTRAINT(0x04d1, 0xf), /* MEM_LOAD_UOPS_RETIRED.L3_HIT */
-	/* MEM_LOAD_UOPS_RETIRED.HIT_LFB */
-	INTEL_UEVENT_CONSTRAINT(0x40d1, 0xf),
-	/* MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_MISS */
-	INTEL_UEVENT_CONSTRAINT(0x01d2, 0xf),
-	/* MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HIT */
-	INTEL_UEVENT_CONSTRAINT(0x02d2, 0xf),
-	/* MEM_LOAD_UOPS_LLC_MISS_RETIRED.LOCAL_DRAM */
-	INTEL_UEVENT_CONSTRAINT(0x01d3, 0xf),
-	INTEL_UEVENT_CONSTRAINT(0x04c8, 0xf), /* HLE_RETIRED.Abort */
-	INTEL_UEVENT_CONSTRAINT(0x04c9, 0xf), /* RTM_RETIRED.Abort */
-
+	INTEL_PLD_CONSTRAINT(0x01cd, 0xf),    /* MEM_TRANS_RETIRED.* */
+	/* UOPS_RETIRED.ALL, inv=1, cmask=16 (cycles:p). */
+	INTEL_FLAGS_EVENT_CONSTRAINT(0x108001c2, 0xf),
+	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
 };
 
@@ -864,6 +821,10 @@ static inline u64 intel_hsw_transaction(struct pebs_record_hsw *pebs)
 static void __intel_pmu_pebs_event(struct perf_event *event,
 				   struct pt_regs *iregs, void *__pebs)
 {
+#define PERF_X86_EVENT_PEBS_HSW_PREC \
+		(PERF_X86_EVENT_PEBS_ST_HSW | \
+		 PERF_X86_EVENT_PEBS_LD_HSW | \
+		 PERF_X86_EVENT_PEBS_NA_HSW)
 	/*
 	 * We cast to the biggest pebs_record but are careful not to
 	 * unconditionally access the 'extra' entries.
@@ -873,42 +834,40 @@ static void __intel_pmu_pebs_event(struct perf_event *event,
 	struct perf_sample_data data;
 	struct pt_regs regs;
 	u64 sample_type;
-	int fll, fst;
+	int fll, fst, dsrc;
+	int fl = event->hw.flags;
 
 	if (!intel_pmu_save_and_restart(event))
 		return;
 
-	fll = event->hw.flags & PERF_X86_EVENT_PEBS_LDLAT;
-	fst = event->hw.flags & (PERF_X86_EVENT_PEBS_ST |
-				 PERF_X86_EVENT_PEBS_ST_HSW);
+	sample_type = event->attr.sample_type;
+	dsrc = sample_type & PERF_SAMPLE_DATA_SRC;
+
+	fll = fl & PERF_X86_EVENT_PEBS_LDLAT;
+	fst = fl & (PERF_X86_EVENT_PEBS_ST | PERF_X86_EVENT_PEBS_HSW_PREC);
 
 	perf_sample_data_init(&data, 0, event->hw.last_period);
 
 	data.period = event->hw.last_period;
-	sample_type = event->attr.sample_type;
 
 	/*
-	 * if PEBS-LL or PreciseStore
+	 * Use latency for weight (only avail with PEBS-LL)
 	 */
-	if (fll || fst) {
-		/*
-		 * Use latency for weight (only avail with PEBS-LL)
-		 */
-		if (fll && (sample_type & PERF_SAMPLE_WEIGHT))
-			data.weight = pebs->lat;
-
-		/*
-		 * data.data_src encodes the data source
-		 */
-		if (sample_type & PERF_SAMPLE_DATA_SRC) {
-			if (fll)
-				data.data_src.val = load_latency_data(pebs->dse);
-			else if (event->hw.flags & PERF_X86_EVENT_PEBS_ST_HSW)
-				data.data_src.val =
-					precise_store_data_hsw(event, pebs->dse);
-			else
-				data.data_src.val = precise_store_data(pebs->dse);
-		}
+	if (fll && (sample_type & PERF_SAMPLE_WEIGHT))
+		data.weight = pebs->lat;
+
+	/*
+	 * data.data_src encodes the data source
+	 */
+	if (dsrc) {
+		u64 val = PERF_MEM_NA;
+		if (fll)
+			val = load_latency_data(pebs->dse);
+		else if (fst && (fl & PERF_X86_EVENT_PEBS_HSW_PREC))
+			val = precise_datala_hsw(event, pebs->dse);
+		else if (fst)
+			val = precise_store_data(pebs->dse);
+		data.data_src.val = val;
 	}
 
 	/*
@@ -935,16 +894,16 @@ static void __intel_pmu_pebs_event(struct perf_event *event,
 	else
 		regs.flags &= ~PERF_EFLAGS_EXACT;
 
-	if ((event->attr.sample_type & PERF_SAMPLE_ADDR) &&
+	if ((sample_type & PERF_SAMPLE_ADDR) &&
 	    x86_pmu.intel_cap.pebs_format >= 1)
 		data.addr = pebs->dla;
 
 	if (x86_pmu.intel_cap.pebs_format >= 2) {
 		/* Only set the TSX weight when no memory weight. */
-		if ((event->attr.sample_type & PERF_SAMPLE_WEIGHT) && !fll)
+		if ((sample_type & PERF_SAMPLE_WEIGHT) && !fll)
 			data.weight = intel_hsw_weight(pebs);
 
-		if (event->attr.sample_type & PERF_SAMPLE_TRANSACTION)
+		if (sample_type & PERF_SAMPLE_TRANSACTION)
 			data.txn = intel_hsw_transaction(pebs);
 	}
 
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.c b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
index 0939f86f543d04..4785ee8ac599b9 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
@@ -1,83 +1,39 @@
 #include "perf_event_intel_uncore.h"
 
 static struct intel_uncore_type *empty_uncore[] = { NULL, };
-static struct intel_uncore_type **msr_uncores = empty_uncore;
-static struct intel_uncore_type **pci_uncores = empty_uncore;
-/* pci bus to socket mapping */
-static int pcibus_to_physid[256] = { [0 ... 255] = -1, };
+struct intel_uncore_type **uncore_msr_uncores = empty_uncore;
+struct intel_uncore_type **uncore_pci_uncores = empty_uncore;
 
-static struct pci_dev *extra_pci_dev[UNCORE_SOCKET_MAX][UNCORE_EXTRA_PCI_DEV_MAX];
+static bool pcidrv_registered;
+struct pci_driver *uncore_pci_driver;
+/* pci bus to socket mapping */
+int uncore_pcibus_to_physid[256] = { [0 ... 255] = -1, };
+struct pci_dev *uncore_extra_pci_dev[UNCORE_SOCKET_MAX][UNCORE_EXTRA_PCI_DEV_MAX];
 
 static DEFINE_RAW_SPINLOCK(uncore_box_lock);
-
 /* mask of cpus that collect uncore events */
 static cpumask_t uncore_cpu_mask;
 
 /* constraint for the fixed counter */
-static struct event_constraint constraint_fixed =
+static struct event_constraint uncore_constraint_fixed =
 	EVENT_CONSTRAINT(~0ULL, 1 << UNCORE_PMC_IDX_FIXED, ~0ULL);
-static struct event_constraint constraint_empty =
+struct event_constraint uncore_constraint_empty =
 	EVENT_CONSTRAINT(0, 0, 0);
 
-#define __BITS_VALUE(x, i, n)  ((typeof(x))(((x) >> ((i) * (n))) & \
-				((1ULL << (n)) - 1)))
-
-DEFINE_UNCORE_FORMAT_ATTR(event, event, "config:0-7");
-DEFINE_UNCORE_FORMAT_ATTR(event_ext, event, "config:0-7,21");
-DEFINE_UNCORE_FORMAT_ATTR(umask, umask, "config:8-15");
-DEFINE_UNCORE_FORMAT_ATTR(edge, edge, "config:18");
-DEFINE_UNCORE_FORMAT_ATTR(tid_en, tid_en, "config:19");
-DEFINE_UNCORE_FORMAT_ATTR(inv, inv, "config:23");
-DEFINE_UNCORE_FORMAT_ATTR(cmask5, cmask, "config:24-28");
-DEFINE_UNCORE_FORMAT_ATTR(cmask8, cmask, "config:24-31");
-DEFINE_UNCORE_FORMAT_ATTR(thresh8, thresh, "config:24-31");
-DEFINE_UNCORE_FORMAT_ATTR(thresh5, thresh, "config:24-28");
-DEFINE_UNCORE_FORMAT_ATTR(occ_sel, occ_sel, "config:14-15");
-DEFINE_UNCORE_FORMAT_ATTR(occ_invert, occ_invert, "config:30");
-DEFINE_UNCORE_FORMAT_ATTR(occ_edge, occ_edge, "config:14-51");
-DEFINE_UNCORE_FORMAT_ATTR(filter_tid, filter_tid, "config1:0-4");
-DEFINE_UNCORE_FORMAT_ATTR(filter_link, filter_link, "config1:5-8");
-DEFINE_UNCORE_FORMAT_ATTR(filter_nid, filter_nid, "config1:10-17");
-DEFINE_UNCORE_FORMAT_ATTR(filter_nid2, filter_nid, "config1:32-47");
-DEFINE_UNCORE_FORMAT_ATTR(filter_state, filter_state, "config1:18-22");
-DEFINE_UNCORE_FORMAT_ATTR(filter_state2, filter_state, "config1:17-22");
-DEFINE_UNCORE_FORMAT_ATTR(filter_opc, filter_opc, "config1:23-31");
-DEFINE_UNCORE_FORMAT_ATTR(filter_opc2, filter_opc, "config1:52-60");
-DEFINE_UNCORE_FORMAT_ATTR(filter_band0, filter_band0, "config1:0-7");
-DEFINE_UNCORE_FORMAT_ATTR(filter_band1, filter_band1, "config1:8-15");
-DEFINE_UNCORE_FORMAT_ATTR(filter_band2, filter_band2, "config1:16-23");
-DEFINE_UNCORE_FORMAT_ATTR(filter_band3, filter_band3, "config1:24-31");
-DEFINE_UNCORE_FORMAT_ATTR(match_rds, match_rds, "config1:48-51");
-DEFINE_UNCORE_FORMAT_ATTR(match_rnid30, match_rnid30, "config1:32-35");
-DEFINE_UNCORE_FORMAT_ATTR(match_rnid4, match_rnid4, "config1:31");
-DEFINE_UNCORE_FORMAT_ATTR(match_dnid, match_dnid, "config1:13-17");
-DEFINE_UNCORE_FORMAT_ATTR(match_mc, match_mc, "config1:9-12");
-DEFINE_UNCORE_FORMAT_ATTR(match_opc, match_opc, "config1:5-8");
-DEFINE_UNCORE_FORMAT_ATTR(match_vnw, match_vnw, "config1:3-4");
-DEFINE_UNCORE_FORMAT_ATTR(match0, match0, "config1:0-31");
-DEFINE_UNCORE_FORMAT_ATTR(match1, match1, "config1:32-63");
-DEFINE_UNCORE_FORMAT_ATTR(mask_rds, mask_rds, "config2:48-51");
-DEFINE_UNCORE_FORMAT_ATTR(mask_rnid30, mask_rnid30, "config2:32-35");
-DEFINE_UNCORE_FORMAT_ATTR(mask_rnid4, mask_rnid4, "config2:31");
-DEFINE_UNCORE_FORMAT_ATTR(mask_dnid, mask_dnid, "config2:13-17");
-DEFINE_UNCORE_FORMAT_ATTR(mask_mc, mask_mc, "config2:9-12");
-DEFINE_UNCORE_FORMAT_ATTR(mask_opc, mask_opc, "config2:5-8");
-DEFINE_UNCORE_FORMAT_ATTR(mask_vnw, mask_vnw, "config2:3-4");
-DEFINE_UNCORE_FORMAT_ATTR(mask0, mask0, "config2:0-31");
-DEFINE_UNCORE_FORMAT_ATTR(mask1, mask1, "config2:32-63");
-
-static void uncore_pmu_start_hrtimer(struct intel_uncore_box *box);
-static void uncore_pmu_cancel_hrtimer(struct intel_uncore_box *box);
-static void uncore_perf_event_update(struct intel_uncore_box *box, struct perf_event *event);
-static void uncore_pmu_event_read(struct perf_event *event);
-
-static struct intel_uncore_pmu *uncore_event_to_pmu(struct perf_event *event)
+ssize_t uncore_event_show(struct kobject *kobj,
+			  struct kobj_attribute *attr, char *buf)
+{
+	struct uncore_event_desc *event =
+		container_of(attr, struct uncore_event_desc, attr);
+	return sprintf(buf, "%s", event->config);
+}
+
+struct intel_uncore_pmu *uncore_event_to_pmu(struct perf_event *event)
 {
 	return container_of(event->pmu, struct intel_uncore_pmu, pmu);
 }
 
-static struct intel_uncore_box *
-uncore_pmu_to_box(struct intel_uncore_pmu *pmu, int cpu)
+struct intel_uncore_box *uncore_pmu_to_box(struct intel_uncore_pmu *pmu, int cpu)
 {
 	struct intel_uncore_box *box;
 
@@ -98,7 +54,7 @@ uncore_pmu_to_box(struct intel_uncore_pmu *pmu, int cpu)
 	return *per_cpu_ptr(pmu->box, cpu);
 }
 
-static struct intel_uncore_box *uncore_event_to_box(struct perf_event *event)
+struct intel_uncore_box *uncore_event_to_box(struct perf_event *event)
 {
 	/*
 	 * perf core schedules event on the basis of cpu, uncore events are
@@ -107,7 +63,7 @@ static struct intel_uncore_box *uncore_event_to_box(struct perf_event *event)
 	return uncore_pmu_to_box(uncore_event_to_pmu(event), smp_processor_id());
 }
 
-static u64 uncore_msr_read_counter(struct intel_uncore_box *box, struct perf_event *event)
+u64 uncore_msr_read_counter(struct intel_uncore_box *box, struct perf_event *event)
 {
 	u64 count;
 
@@ -119,7 +75,7 @@ static u64 uncore_msr_read_counter(struct intel_uncore_box *box, struct perf_eve
 /*
  * generic get constraint function for shared match/mask registers.
  */
-static struct event_constraint *
+struct event_constraint *
 uncore_get_constraint(struct intel_uncore_box *box, struct perf_event *event)
 {
 	struct intel_uncore_extra_reg *er;
@@ -154,10 +110,10 @@ uncore_get_constraint(struct intel_uncore_box *box, struct perf_event *event)
 		return NULL;
 	}
 
-	return &constraint_empty;
+	return &uncore_constraint_empty;
 }
 
-static void uncore_put_constraint(struct intel_uncore_box *box, struct perf_event *event)
+void uncore_put_constraint(struct intel_uncore_box *box, struct perf_event *event)
 {
 	struct intel_uncore_extra_reg *er;
 	struct hw_perf_event_extra *reg1 = &event->hw.extra_reg;
@@ -178,7 +134,7 @@ static void uncore_put_constraint(struct intel_uncore_box *box, struct perf_even
 	reg1->alloc = 0;
 }
 
-static u64 uncore_shared_reg_config(struct intel_uncore_box *box, int idx)
+u64 uncore_shared_reg_config(struct intel_uncore_box *box, int idx)
 {
 	struct intel_uncore_extra_reg *er;
 	unsigned long flags;
@@ -193,2936 +149,6 @@ static u64 uncore_shared_reg_config(struct intel_uncore_box *box, int idx)
 	return config;
 }
 
-/* Sandy Bridge-EP uncore support */
-static struct intel_uncore_type snbep_uncore_cbox;
-static struct intel_uncore_type snbep_uncore_pcu;
-
-static void snbep_uncore_pci_disable_box(struct intel_uncore_box *box)
-{
-	struct pci_dev *pdev = box->pci_dev;
-	int box_ctl = uncore_pci_box_ctl(box);
-	u32 config = 0;
-
-	if (!pci_read_config_dword(pdev, box_ctl, &config)) {
-		config |= SNBEP_PMON_BOX_CTL_FRZ;
-		pci_write_config_dword(pdev, box_ctl, config);
-	}
-}
-
-static void snbep_uncore_pci_enable_box(struct intel_uncore_box *box)
-{
-	struct pci_dev *pdev = box->pci_dev;
-	int box_ctl = uncore_pci_box_ctl(box);
-	u32 config = 0;
-
-	if (!pci_read_config_dword(pdev, box_ctl, &config)) {
-		config &= ~SNBEP_PMON_BOX_CTL_FRZ;
-		pci_write_config_dword(pdev, box_ctl, config);
-	}
-}
-
-static void snbep_uncore_pci_enable_event(struct intel_uncore_box *box, struct perf_event *event)
-{
-	struct pci_dev *pdev = box->pci_dev;
-	struct hw_perf_event *hwc = &event->hw;
-
-	pci_write_config_dword(pdev, hwc->config_base, hwc->config | SNBEP_PMON_CTL_EN);
-}
-
-static void snbep_uncore_pci_disable_event(struct intel_uncore_box *box, struct perf_event *event)
-{
-	struct pci_dev *pdev = box->pci_dev;
-	struct hw_perf_event *hwc = &event->hw;
-
-	pci_write_config_dword(pdev, hwc->config_base, hwc->config);
-}
-
-static u64 snbep_uncore_pci_read_counter(struct intel_uncore_box *box, struct perf_event *event)
-{
-	struct pci_dev *pdev = box->pci_dev;
-	struct hw_perf_event *hwc = &event->hw;
-	u64 count = 0;
-
-	pci_read_config_dword(pdev, hwc->event_base, (u32 *)&count);
-	pci_read_config_dword(pdev, hwc->event_base + 4, (u32 *)&count + 1);
-
-	return count;
-}
-
-static void snbep_uncore_pci_init_box(struct intel_uncore_box *box)
-{
-	struct pci_dev *pdev = box->pci_dev;
-
-	pci_write_config_dword(pdev, SNBEP_PCI_PMON_BOX_CTL, SNBEP_PMON_BOX_CTL_INT);
-}
-
-static void snbep_uncore_msr_disable_box(struct intel_uncore_box *box)
-{
-	u64 config;
-	unsigned msr;
-
-	msr = uncore_msr_box_ctl(box);
-	if (msr) {
-		rdmsrl(msr, config);
-		config |= SNBEP_PMON_BOX_CTL_FRZ;
-		wrmsrl(msr, config);
-	}
-}
-
-static void snbep_uncore_msr_enable_box(struct intel_uncore_box *box)
-{
-	u64 config;
-	unsigned msr;
-
-	msr = uncore_msr_box_ctl(box);
-	if (msr) {
-		rdmsrl(msr, config);
-		config &= ~SNBEP_PMON_BOX_CTL_FRZ;
-		wrmsrl(msr, config);
-	}
-}
-
-static void snbep_uncore_msr_enable_event(struct intel_uncore_box *box, struct perf_event *event)
-{
-	struct hw_perf_event *hwc = &event->hw;
-	struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
-
-	if (reg1->idx != EXTRA_REG_NONE)
-		wrmsrl(reg1->reg, uncore_shared_reg_config(box, 0));
-
-	wrmsrl(hwc->config_base, hwc->config | SNBEP_PMON_CTL_EN);
-}
-
-static void snbep_uncore_msr_disable_event(struct intel_uncore_box *box,
-					struct perf_event *event)
-{
-	struct hw_perf_event *hwc = &event->hw;
-
-	wrmsrl(hwc->config_base, hwc->config);
-}
-
-static void snbep_uncore_msr_init_box(struct intel_uncore_box *box)
-{
-	unsigned msr = uncore_msr_box_ctl(box);
-
-	if (msr)
-		wrmsrl(msr, SNBEP_PMON_BOX_CTL_INT);
-}
-
-static struct attribute *snbep_uncore_formats_attr[] = {
-	&format_attr_event.attr,
-	&format_attr_umask.attr,
-	&format_attr_edge.attr,
-	&format_attr_inv.attr,
-	&format_attr_thresh8.attr,
-	NULL,
-};
-
-static struct attribute *snbep_uncore_ubox_formats_attr[] = {
-	&format_attr_event.attr,
-	&format_attr_umask.attr,
-	&format_attr_edge.attr,
-	&format_attr_inv.attr,
-	&format_attr_thresh5.attr,
-	NULL,
-};
-
-static struct attribute *snbep_uncore_cbox_formats_attr[] = {
-	&format_attr_event.attr,
-	&format_attr_umask.attr,
-	&format_attr_edge.attr,
-	&format_attr_tid_en.attr,
-	&format_attr_inv.attr,
-	&format_attr_thresh8.attr,
-	&format_attr_filter_tid.attr,
-	&format_attr_filter_nid.attr,
-	&format_attr_filter_state.attr,
-	&format_attr_filter_opc.attr,
-	NULL,
-};
-
-static struct attribute *snbep_uncore_pcu_formats_attr[] = {
-	&format_attr_event_ext.attr,
-	&format_attr_occ_sel.attr,
-	&format_attr_edge.attr,
-	&format_attr_inv.attr,
-	&format_attr_thresh5.attr,
-	&format_attr_occ_invert.attr,
-	&format_attr_occ_edge.attr,
-	&format_attr_filter_band0.attr,
-	&format_attr_filter_band1.attr,
-	&format_attr_filter_band2.attr,
-	&format_attr_filter_band3.attr,
-	NULL,
-};
-
-static struct attribute *snbep_uncore_qpi_formats_attr[] = {
-	&format_attr_event_ext.attr,
-	&format_attr_umask.attr,
-	&format_attr_edge.attr,
-	&format_attr_inv.attr,
-	&format_attr_thresh8.attr,
-	&format_attr_match_rds.attr,
-	&format_attr_match_rnid30.attr,
-	&format_attr_match_rnid4.attr,
-	&format_attr_match_dnid.attr,
-	&format_attr_match_mc.attr,
-	&format_attr_match_opc.attr,
-	&format_attr_match_vnw.attr,
-	&format_attr_match0.attr,
-	&format_attr_match1.attr,
-	&format_attr_mask_rds.attr,
-	&format_attr_mask_rnid30.attr,
-	&format_attr_mask_rnid4.attr,
-	&format_attr_mask_dnid.attr,
-	&format_attr_mask_mc.attr,
-	&format_attr_mask_opc.attr,
-	&format_attr_mask_vnw.attr,
-	&format_attr_mask0.attr,
-	&format_attr_mask1.attr,
-	NULL,
-};
-
-static struct uncore_event_desc snbep_uncore_imc_events[] = {
-	INTEL_UNCORE_EVENT_DESC(clockticks,      "event=0xff,umask=0x00"),
-	INTEL_UNCORE_EVENT_DESC(cas_count_read,  "event=0x04,umask=0x03"),
-	INTEL_UNCORE_EVENT_DESC(cas_count_write, "event=0x04,umask=0x0c"),
-	{ /* end: all zeroes */ },
-};
-
-static struct uncore_event_desc snbep_uncore_qpi_events[] = {
-	INTEL_UNCORE_EVENT_DESC(clockticks,       "event=0x14"),
-	INTEL_UNCORE_EVENT_DESC(txl_flits_active, "event=0x00,umask=0x06"),
-	INTEL_UNCORE_EVENT_DESC(drs_data,         "event=0x102,umask=0x08"),
-	INTEL_UNCORE_EVENT_DESC(ncb_data,         "event=0x103,umask=0x04"),
-	{ /* end: all zeroes */ },
-};
-
-static struct attribute_group snbep_uncore_format_group = {
-	.name = "format",
-	.attrs = snbep_uncore_formats_attr,
-};
-
-static struct attribute_group snbep_uncore_ubox_format_group = {
-	.name = "format",
-	.attrs = snbep_uncore_ubox_formats_attr,
-};
-
-static struct attribute_group snbep_uncore_cbox_format_group = {
-	.name = "format",
-	.attrs = snbep_uncore_cbox_formats_attr,
-};
-
-static struct attribute_group snbep_uncore_pcu_format_group = {
-	.name = "format",
-	.attrs = snbep_uncore_pcu_formats_attr,
-};
-
-static struct attribute_group snbep_uncore_qpi_format_group = {
-	.name = "format",
-	.attrs = snbep_uncore_qpi_formats_attr,
-};
-
-#define SNBEP_UNCORE_MSR_OPS_COMMON_INIT()			\
-	.init_box	= snbep_uncore_msr_init_box,		\
-	.disable_box	= snbep_uncore_msr_disable_box,		\
-	.enable_box	= snbep_uncore_msr_enable_box,		\
-	.disable_event	= snbep_uncore_msr_disable_event,	\
-	.enable_event	= snbep_uncore_msr_enable_event,	\
-	.read_counter	= uncore_msr_read_counter
-
-static struct intel_uncore_ops snbep_uncore_msr_ops = {
-	SNBEP_UNCORE_MSR_OPS_COMMON_INIT(),
-};
-
-#define SNBEP_UNCORE_PCI_OPS_COMMON_INIT()			\
-	.init_box	= snbep_uncore_pci_init_box,		\
-	.disable_box	= snbep_uncore_pci_disable_box,		\
-	.enable_box	= snbep_uncore_pci_enable_box,		\
-	.disable_event	= snbep_uncore_pci_disable_event,	\
-	.read_counter	= snbep_uncore_pci_read_counter
-
-static struct intel_uncore_ops snbep_uncore_pci_ops = {
-	SNBEP_UNCORE_PCI_OPS_COMMON_INIT(),
-	.enable_event	= snbep_uncore_pci_enable_event,	\
-};
-
-static struct event_constraint snbep_uncore_cbox_constraints[] = {
-	UNCORE_EVENT_CONSTRAINT(0x01, 0x1),
-	UNCORE_EVENT_CONSTRAINT(0x02, 0x3),
-	UNCORE_EVENT_CONSTRAINT(0x04, 0x3),
-	UNCORE_EVENT_CONSTRAINT(0x05, 0x3),
-	UNCORE_EVENT_CONSTRAINT(0x07, 0x3),
-	UNCORE_EVENT_CONSTRAINT(0x09, 0x3),
-	UNCORE_EVENT_CONSTRAINT(0x11, 0x1),
-	UNCORE_EVENT_CONSTRAINT(0x12, 0x3),
-	UNCORE_EVENT_CONSTRAINT(0x13, 0x3),
-	UNCORE_EVENT_CONSTRAINT(0x1b, 0xc),
-	UNCORE_EVENT_CONSTRAINT(0x1c, 0xc),
-	UNCORE_EVENT_CONSTRAINT(0x1d, 0xc),
-	UNCORE_EVENT_CONSTRAINT(0x1e, 0xc),
-	EVENT_CONSTRAINT_OVERLAP(0x1f, 0xe, 0xff),
-	UNCORE_EVENT_CONSTRAINT(0x21, 0x3),
-	UNCORE_EVENT_CONSTRAINT(0x23, 0x3),
-	UNCORE_EVENT_CONSTRAINT(0x31, 0x3),
-	UNCORE_EVENT_CONSTRAINT(0x32, 0x3),
-	UNCORE_EVENT_CONSTRAINT(0x33, 0x3),
-	UNCORE_EVENT_CONSTRAINT(0x34, 0x3),
-	UNCORE_EVENT_CONSTRAINT(0x35, 0x3),
-	UNCORE_EVENT_CONSTRAINT(0x36, 0x1),
-	UNCORE_EVENT_CONSTRAINT(0x37, 0x3),
-	UNCORE_EVENT_CONSTRAINT(0x38, 0x3),
-	UNCORE_EVENT_CONSTRAINT(0x39, 0x3),
-	UNCORE_EVENT_CONSTRAINT(0x3b, 0x1),
-	EVENT_CONSTRAINT_END
-};
-
-static struct event_constraint snbep_uncore_r2pcie_constraints[] = {
-	UNCORE_EVENT_CONSTRAINT(0x10, 0x3),
-	UNCORE_EVENT_CONSTRAINT(0x11, 0x3),
-	UNCORE_EVENT_CONSTRAINT(0x12, 0x1),
-	UNCORE_EVENT_CONSTRAINT(0x23, 0x3),
-	UNCORE_EVENT_CONSTRAINT(0x24, 0x3),
-	UNCORE_EVENT_CONSTRAINT(0x25, 0x3),
-	UNCORE_EVENT_CONSTRAINT(0x26, 0x3),
-	UNCORE_EVENT_CONSTRAINT(0x32, 0x3),
-	UNCORE_EVENT_CONSTRAINT(0x33, 0x3),
-	UNCORE_EVENT_CONSTRAINT(0x34, 0x3),
-	EVENT_CONSTRAINT_END
-};
-
-static struct event_constraint snbep_uncore_r3qpi_constraints[] = {
-	UNCORE_EVENT_CONSTRAINT(0x10, 0x3),
-	UNCORE_EVENT_CONSTRAINT(0x11, 0x3),
-	UNCORE_EVENT_CONSTRAINT(0x12, 0x3),
-	UNCORE_EVENT_CONSTRAINT(0x13, 0x1),
-	UNCORE_EVENT_CONSTRAINT(0x20, 0x3),
-	UNCORE_EVENT_CONSTRAINT(0x21, 0x3),
-	UNCORE_EVENT_CONSTRAINT(0x22, 0x3),
-	UNCORE_EVENT_CONSTRAINT(0x23, 0x3),
-	UNCORE_EVENT_CONSTRAINT(0x24, 0x3),
-	UNCORE_EVENT_CONSTRAINT(0x25, 0x3),
-	UNCORE_EVENT_CONSTRAINT(0x26, 0x3),
-	UNCORE_EVENT_CONSTRAINT(0x28, 0x3),
-	UNCORE_EVENT_CONSTRAINT(0x29, 0x3),
-	UNCORE_EVENT_CONSTRAINT(0x2a, 0x3),
-	UNCORE_EVENT_CONSTRAINT(0x2b, 0x3),
-	UNCORE_EVENT_CONSTRAINT(0x2c, 0x3),
-	UNCORE_EVENT_CONSTRAINT(0x2d, 0x3),
-	UNCORE_EVENT_CONSTRAINT(0x2e, 0x3),
-	UNCORE_EVENT_CONSTRAINT(0x2f, 0x3),
-	UNCORE_EVENT_CONSTRAINT(0x30, 0x3),
-	UNCORE_EVENT_CONSTRAINT(0x31, 0x3),
-	UNCORE_EVENT_CONSTRAINT(0x32, 0x3),
-	UNCORE_EVENT_CONSTRAINT(0x33, 0x3),
-	UNCORE_EVENT_CONSTRAINT(0x34, 0x3),
-	UNCORE_EVENT_CONSTRAINT(0x36, 0x3),
-	UNCORE_EVENT_CONSTRAINT(0x37, 0x3),
-	UNCORE_EVENT_CONSTRAINT(0x38, 0x3),
-	UNCORE_EVENT_CONSTRAINT(0x39, 0x3),
-	EVENT_CONSTRAINT_END
-};
-
-static struct intel_uncore_type snbep_uncore_ubox = {
-	.name		= "ubox",
-	.num_counters   = 2,
-	.num_boxes	= 1,
-	.perf_ctr_bits	= 44,
-	.fixed_ctr_bits	= 48,
-	.perf_ctr	= SNBEP_U_MSR_PMON_CTR0,
-	.event_ctl	= SNBEP_U_MSR_PMON_CTL0,
-	.event_mask	= SNBEP_U_MSR_PMON_RAW_EVENT_MASK,
-	.fixed_ctr	= SNBEP_U_MSR_PMON_UCLK_FIXED_CTR,
-	.fixed_ctl	= SNBEP_U_MSR_PMON_UCLK_FIXED_CTL,
-	.ops		= &snbep_uncore_msr_ops,
-	.format_group	= &snbep_uncore_ubox_format_group,
-};
-
-static struct extra_reg snbep_uncore_cbox_extra_regs[] = {
-	SNBEP_CBO_EVENT_EXTRA_REG(SNBEP_CBO_PMON_CTL_TID_EN,
-				  SNBEP_CBO_PMON_CTL_TID_EN, 0x1),
-	SNBEP_CBO_EVENT_EXTRA_REG(0x0334, 0xffff, 0x4),
-	SNBEP_CBO_EVENT_EXTRA_REG(0x4334, 0xffff, 0x6),
-	SNBEP_CBO_EVENT_EXTRA_REG(0x0534, 0xffff, 0x4),
-	SNBEP_CBO_EVENT_EXTRA_REG(0x4534, 0xffff, 0x6),
-	SNBEP_CBO_EVENT_EXTRA_REG(0x0934, 0xffff, 0x4),
-	SNBEP_CBO_EVENT_EXTRA_REG(0x4934, 0xffff, 0x6),
-	SNBEP_CBO_EVENT_EXTRA_REG(0x4134, 0xffff, 0x6),
-	SNBEP_CBO_EVENT_EXTRA_REG(0x0135, 0xffff, 0x8),
-	SNBEP_CBO_EVENT_EXTRA_REG(0x0335, 0xffff, 0x8),
-	SNBEP_CBO_EVENT_EXTRA_REG(0x4135, 0xffff, 0xa),
-	SNBEP_CBO_EVENT_EXTRA_REG(0x4335, 0xffff, 0xa),
-	SNBEP_CBO_EVENT_EXTRA_REG(0x4435, 0xffff, 0x2),
-	SNBEP_CBO_EVENT_EXTRA_REG(0x4835, 0xffff, 0x2),
-	SNBEP_CBO_EVENT_EXTRA_REG(0x4a35, 0xffff, 0x2),
-	SNBEP_CBO_EVENT_EXTRA_REG(0x5035, 0xffff, 0x2),
-	SNBEP_CBO_EVENT_EXTRA_REG(0x0136, 0xffff, 0x8),
-	SNBEP_CBO_EVENT_EXTRA_REG(0x0336, 0xffff, 0x8),
-	SNBEP_CBO_EVENT_EXTRA_REG(0x4136, 0xffff, 0xa),
-	SNBEP_CBO_EVENT_EXTRA_REG(0x4336, 0xffff, 0xa),
-	SNBEP_CBO_EVENT_EXTRA_REG(0x4436, 0xffff, 0x2),
-	SNBEP_CBO_EVENT_EXTRA_REG(0x4836, 0xffff, 0x2),
-	SNBEP_CBO_EVENT_EXTRA_REG(0x4a36, 0xffff, 0x2),
-	SNBEP_CBO_EVENT_EXTRA_REG(0x4037, 0x40ff, 0x2),
-	EVENT_EXTRA_END
-};
-
-static void snbep_cbox_put_constraint(struct intel_uncore_box *box, struct perf_event *event)
-{
-	struct hw_perf_event_extra *reg1 = &event->hw.extra_reg;
-	struct intel_uncore_extra_reg *er = &box->shared_regs[0];
-	int i;
-
-	if (uncore_box_is_fake(box))
-		return;
-
-	for (i = 0; i < 5; i++) {
-		if (reg1->alloc & (0x1 << i))
-			atomic_sub(1 << (i * 6), &er->ref);
-	}
-	reg1->alloc = 0;
-}
-
-static struct event_constraint *
-__snbep_cbox_get_constraint(struct intel_uncore_box *box, struct perf_event *event,
-			    u64 (*cbox_filter_mask)(int fields))
-{
-	struct hw_perf_event_extra *reg1 = &event->hw.extra_reg;
-	struct intel_uncore_extra_reg *er = &box->shared_regs[0];
-	int i, alloc = 0;
-	unsigned long flags;
-	u64 mask;
-
-	if (reg1->idx == EXTRA_REG_NONE)
-		return NULL;
-
-	raw_spin_lock_irqsave(&er->lock, flags);
-	for (i = 0; i < 5; i++) {
-		if (!(reg1->idx & (0x1 << i)))
-			continue;
-		if (!uncore_box_is_fake(box) && (reg1->alloc & (0x1 << i)))
-			continue;
-
-		mask = cbox_filter_mask(0x1 << i);
-		if (!__BITS_VALUE(atomic_read(&er->ref), i, 6) ||
-		    !((reg1->config ^ er->config) & mask)) {
-			atomic_add(1 << (i * 6), &er->ref);
-			er->config &= ~mask;
-			er->config |= reg1->config & mask;
-			alloc |= (0x1 << i);
-		} else {
-			break;
-		}
-	}
-	raw_spin_unlock_irqrestore(&er->lock, flags);
-	if (i < 5)
-		goto fail;
-
-	if (!uncore_box_is_fake(box))
-		reg1->alloc |= alloc;
-
-	return NULL;
-fail:
-	for (; i >= 0; i--) {
-		if (alloc & (0x1 << i))
-			atomic_sub(1 << (i * 6), &er->ref);
-	}
-	return &constraint_empty;
-}
-
-static u64 snbep_cbox_filter_mask(int fields)
-{
-	u64 mask = 0;
-
-	if (fields & 0x1)
-		mask |= SNBEP_CB0_MSR_PMON_BOX_FILTER_TID;
-	if (fields & 0x2)
-		mask |= SNBEP_CB0_MSR_PMON_BOX_FILTER_NID;
-	if (fields & 0x4)
-		mask |= SNBEP_CB0_MSR_PMON_BOX_FILTER_STATE;
-	if (fields & 0x8)
-		mask |= SNBEP_CB0_MSR_PMON_BOX_FILTER_OPC;
-
-	return mask;
-}
-
-static struct event_constraint *
-snbep_cbox_get_constraint(struct intel_uncore_box *box, struct perf_event *event)
-{
-	return __snbep_cbox_get_constraint(box, event, snbep_cbox_filter_mask);
-}
-
-static int snbep_cbox_hw_config(struct intel_uncore_box *box, struct perf_event *event)
-{
-	struct hw_perf_event_extra *reg1 = &event->hw.extra_reg;
-	struct extra_reg *er;
-	int idx = 0;
-
-	for (er = snbep_uncore_cbox_extra_regs; er->msr; er++) {
-		if (er->event != (event->hw.config & er->config_mask))
-			continue;
-		idx |= er->idx;
-	}
-
-	if (idx) {
-		reg1->reg = SNBEP_C0_MSR_PMON_BOX_FILTER +
-			SNBEP_CBO_MSR_OFFSET * box->pmu->pmu_idx;
-		reg1->config = event->attr.config1 & snbep_cbox_filter_mask(idx);
-		reg1->idx = idx;
-	}
-	return 0;
-}
-
-static struct intel_uncore_ops snbep_uncore_cbox_ops = {
-	SNBEP_UNCORE_MSR_OPS_COMMON_INIT(),
-	.hw_config		= snbep_cbox_hw_config,
-	.get_constraint		= snbep_cbox_get_constraint,
-	.put_constraint		= snbep_cbox_put_constraint,
-};
-
-static struct intel_uncore_type snbep_uncore_cbox = {
-	.name			= "cbox",
-	.num_counters		= 4,
-	.num_boxes		= 8,
-	.perf_ctr_bits		= 44,
-	.event_ctl		= SNBEP_C0_MSR_PMON_CTL0,
-	.perf_ctr		= SNBEP_C0_MSR_PMON_CTR0,
-	.event_mask		= SNBEP_CBO_MSR_PMON_RAW_EVENT_MASK,
-	.box_ctl		= SNBEP_C0_MSR_PMON_BOX_CTL,
-	.msr_offset		= SNBEP_CBO_MSR_OFFSET,
-	.num_shared_regs	= 1,
-	.constraints		= snbep_uncore_cbox_constraints,
-	.ops			= &snbep_uncore_cbox_ops,
-	.format_group		= &snbep_uncore_cbox_format_group,
-};
-
-static u64 snbep_pcu_alter_er(struct perf_event *event, int new_idx, bool modify)
-{
-	struct hw_perf_event *hwc = &event->hw;
-	struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
-	u64 config = reg1->config;
-
-	if (new_idx > reg1->idx)
-		config <<= 8 * (new_idx - reg1->idx);
-	else
-		config >>= 8 * (reg1->idx - new_idx);
-
-	if (modify) {
-		hwc->config += new_idx - reg1->idx;
-		reg1->config = config;
-		reg1->idx = new_idx;
-	}
-	return config;
-}
-
-static struct event_constraint *
-snbep_pcu_get_constraint(struct intel_uncore_box *box, struct perf_event *event)
-{
-	struct hw_perf_event_extra *reg1 = &event->hw.extra_reg;
-	struct intel_uncore_extra_reg *er = &box->shared_regs[0];
-	unsigned long flags;
-	int idx = reg1->idx;
-	u64 mask, config1 = reg1->config;
-	bool ok = false;
-
-	if (reg1->idx == EXTRA_REG_NONE ||
-	    (!uncore_box_is_fake(box) && reg1->alloc))
-		return NULL;
-again:
-	mask = 0xffULL << (idx * 8);
-	raw_spin_lock_irqsave(&er->lock, flags);
-	if (!__BITS_VALUE(atomic_read(&er->ref), idx, 8) ||
-	    !((config1 ^ er->config) & mask)) {
-		atomic_add(1 << (idx * 8), &er->ref);
-		er->config &= ~mask;
-		er->config |= config1 & mask;
-		ok = true;
-	}
-	raw_spin_unlock_irqrestore(&er->lock, flags);
-
-	if (!ok) {
-		idx = (idx + 1) % 4;
-		if (idx != reg1->idx) {
-			config1 = snbep_pcu_alter_er(event, idx, false);
-			goto again;
-		}
-		return &constraint_empty;
-	}
-
-	if (!uncore_box_is_fake(box)) {
-		if (idx != reg1->idx)
-			snbep_pcu_alter_er(event, idx, true);
-		reg1->alloc = 1;
-	}
-	return NULL;
-}
-
-static void snbep_pcu_put_constraint(struct intel_uncore_box *box, struct perf_event *event)
-{
-	struct hw_perf_event_extra *reg1 = &event->hw.extra_reg;
-	struct intel_uncore_extra_reg *er = &box->shared_regs[0];
-
-	if (uncore_box_is_fake(box) || !reg1->alloc)
-		return;
-
-	atomic_sub(1 << (reg1->idx * 8), &er->ref);
-	reg1->alloc = 0;
-}
-
-static int snbep_pcu_hw_config(struct intel_uncore_box *box, struct perf_event *event)
-{
-	struct hw_perf_event *hwc = &event->hw;
-	struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
-	int ev_sel = hwc->config & SNBEP_PMON_CTL_EV_SEL_MASK;
-
-	if (ev_sel >= 0xb && ev_sel <= 0xe) {
-		reg1->reg = SNBEP_PCU_MSR_PMON_BOX_FILTER;
-		reg1->idx = ev_sel - 0xb;
-		reg1->config = event->attr.config1 & (0xff << reg1->idx);
-	}
-	return 0;
-}
-
-static struct intel_uncore_ops snbep_uncore_pcu_ops = {
-	SNBEP_UNCORE_MSR_OPS_COMMON_INIT(),
-	.hw_config		= snbep_pcu_hw_config,
-	.get_constraint		= snbep_pcu_get_constraint,
-	.put_constraint		= snbep_pcu_put_constraint,
-};
-
-static struct intel_uncore_type snbep_uncore_pcu = {
-	.name			= "pcu",
-	.num_counters		= 4,
-	.num_boxes		= 1,
-	.perf_ctr_bits		= 48,
-	.perf_ctr		= SNBEP_PCU_MSR_PMON_CTR0,
-	.event_ctl		= SNBEP_PCU_MSR_PMON_CTL0,
-	.event_mask		= SNBEP_PCU_MSR_PMON_RAW_EVENT_MASK,
-	.box_ctl		= SNBEP_PCU_MSR_PMON_BOX_CTL,
-	.num_shared_regs	= 1,
-	.ops			= &snbep_uncore_pcu_ops,
-	.format_group		= &snbep_uncore_pcu_format_group,
-};
-
-static struct intel_uncore_type *snbep_msr_uncores[] = {
-	&snbep_uncore_ubox,
-	&snbep_uncore_cbox,
-	&snbep_uncore_pcu,
-	NULL,
-};
-
-enum {
-	SNBEP_PCI_QPI_PORT0_FILTER,
-	SNBEP_PCI_QPI_PORT1_FILTER,
-};
-
-static int snbep_qpi_hw_config(struct intel_uncore_box *box, struct perf_event *event)
-{
-	struct hw_perf_event *hwc = &event->hw;
-	struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
-	struct hw_perf_event_extra *reg2 = &hwc->branch_reg;
-
-	if ((hwc->config & SNBEP_PMON_CTL_EV_SEL_MASK) == 0x38) {
-		reg1->idx = 0;
-		reg1->reg = SNBEP_Q_Py_PCI_PMON_PKT_MATCH0;
-		reg1->config = event->attr.config1;
-		reg2->reg = SNBEP_Q_Py_PCI_PMON_PKT_MASK0;
-		reg2->config = event->attr.config2;
-	}
-	return 0;
-}
-
-static void snbep_qpi_enable_event(struct intel_uncore_box *box, struct perf_event *event)
-{
-	struct pci_dev *pdev = box->pci_dev;
-	struct hw_perf_event *hwc = &event->hw;
-	struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
-	struct hw_perf_event_extra *reg2 = &hwc->branch_reg;
-
-	if (reg1->idx != EXTRA_REG_NONE) {
-		int idx = box->pmu->pmu_idx + SNBEP_PCI_QPI_PORT0_FILTER;
-		struct pci_dev *filter_pdev = extra_pci_dev[box->phys_id][idx];
-		WARN_ON_ONCE(!filter_pdev);
-		if (filter_pdev) {
-			pci_write_config_dword(filter_pdev, reg1->reg,
-						(u32)reg1->config);
-			pci_write_config_dword(filter_pdev, reg1->reg + 4,
-						(u32)(reg1->config >> 32));
-			pci_write_config_dword(filter_pdev, reg2->reg,
-						(u32)reg2->config);
-			pci_write_config_dword(filter_pdev, reg2->reg + 4,
-						(u32)(reg2->config >> 32));
-		}
-	}
-
-	pci_write_config_dword(pdev, hwc->config_base, hwc->config | SNBEP_PMON_CTL_EN);
-}
-
-static struct intel_uncore_ops snbep_uncore_qpi_ops = {
-	SNBEP_UNCORE_PCI_OPS_COMMON_INIT(),
-	.enable_event		= snbep_qpi_enable_event,
-	.hw_config		= snbep_qpi_hw_config,
-	.get_constraint		= uncore_get_constraint,
-	.put_constraint		= uncore_put_constraint,
-};
-
-#define SNBEP_UNCORE_PCI_COMMON_INIT()				\
-	.perf_ctr	= SNBEP_PCI_PMON_CTR0,			\
-	.event_ctl	= SNBEP_PCI_PMON_CTL0,			\
-	.event_mask	= SNBEP_PMON_RAW_EVENT_MASK,		\
-	.box_ctl	= SNBEP_PCI_PMON_BOX_CTL,		\
-	.ops		= &snbep_uncore_pci_ops,		\
-	.format_group	= &snbep_uncore_format_group
-
-static struct intel_uncore_type snbep_uncore_ha = {
-	.name		= "ha",
-	.num_counters   = 4,
-	.num_boxes	= 1,
-	.perf_ctr_bits	= 48,
-	SNBEP_UNCORE_PCI_COMMON_INIT(),
-};
-
-static struct intel_uncore_type snbep_uncore_imc = {
-	.name		= "imc",
-	.num_counters   = 4,
-	.num_boxes	= 4,
-	.perf_ctr_bits	= 48,
-	.fixed_ctr_bits	= 48,
-	.fixed_ctr	= SNBEP_MC_CHy_PCI_PMON_FIXED_CTR,
-	.fixed_ctl	= SNBEP_MC_CHy_PCI_PMON_FIXED_CTL,
-	.event_descs	= snbep_uncore_imc_events,
-	SNBEP_UNCORE_PCI_COMMON_INIT(),
-};
-
-static struct intel_uncore_type snbep_uncore_qpi = {
-	.name			= "qpi",
-	.num_counters		= 4,
-	.num_boxes		= 2,
-	.perf_ctr_bits		= 48,
-	.perf_ctr		= SNBEP_PCI_PMON_CTR0,
-	.event_ctl		= SNBEP_PCI_PMON_CTL0,
-	.event_mask		= SNBEP_QPI_PCI_PMON_RAW_EVENT_MASK,
-	.box_ctl		= SNBEP_PCI_PMON_BOX_CTL,
-	.num_shared_regs	= 1,
-	.ops			= &snbep_uncore_qpi_ops,
-	.event_descs		= snbep_uncore_qpi_events,
-	.format_group		= &snbep_uncore_qpi_format_group,
-};
-
-
-static struct intel_uncore_type snbep_uncore_r2pcie = {
-	.name		= "r2pcie",
-	.num_counters   = 4,
-	.num_boxes	= 1,
-	.perf_ctr_bits	= 44,
-	.constraints	= snbep_uncore_r2pcie_constraints,
-	SNBEP_UNCORE_PCI_COMMON_INIT(),
-};
-
-static struct intel_uncore_type snbep_uncore_r3qpi = {
-	.name		= "r3qpi",
-	.num_counters   = 3,
-	.num_boxes	= 2,
-	.perf_ctr_bits	= 44,
-	.constraints	= snbep_uncore_r3qpi_constraints,
-	SNBEP_UNCORE_PCI_COMMON_INIT(),
-};
-
-enum {
-	SNBEP_PCI_UNCORE_HA,
-	SNBEP_PCI_UNCORE_IMC,
-	SNBEP_PCI_UNCORE_QPI,
-	SNBEP_PCI_UNCORE_R2PCIE,
-	SNBEP_PCI_UNCORE_R3QPI,
-};
-
-static struct intel_uncore_type *snbep_pci_uncores[] = {
-	[SNBEP_PCI_UNCORE_HA]		= &snbep_uncore_ha,
-	[SNBEP_PCI_UNCORE_IMC]		= &snbep_uncore_imc,
-	[SNBEP_PCI_UNCORE_QPI]		= &snbep_uncore_qpi,
-	[SNBEP_PCI_UNCORE_R2PCIE]	= &snbep_uncore_r2pcie,
-	[SNBEP_PCI_UNCORE_R3QPI]	= &snbep_uncore_r3qpi,
-	NULL,
-};
-
-static const struct pci_device_id snbep_uncore_pci_ids[] = {
-	{ /* Home Agent */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_HA),
-		.driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_HA, 0),
-	},
-	{ /* MC Channel 0 */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_IMC0),
-		.driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_IMC, 0),
-	},
-	{ /* MC Channel 1 */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_IMC1),
-		.driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_IMC, 1),
-	},
-	{ /* MC Channel 2 */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_IMC2),
-		.driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_IMC, 2),
-	},
-	{ /* MC Channel 3 */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_IMC3),
-		.driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_IMC, 3),
-	},
-	{ /* QPI Port 0 */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_QPI0),
-		.driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_QPI, 0),
-	},
-	{ /* QPI Port 1 */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_QPI1),
-		.driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_QPI, 1),
-	},
-	{ /* R2PCIe */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_R2PCIE),
-		.driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_R2PCIE, 0),
-	},
-	{ /* R3QPI Link 0 */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_R3QPI0),
-		.driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_R3QPI, 0),
-	},
-	{ /* R3QPI Link 1 */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_R3QPI1),
-		.driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_R3QPI, 1),
-	},
-	{ /* QPI Port 0 filter  */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x3c86),
-		.driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV,
-						   SNBEP_PCI_QPI_PORT0_FILTER),
-	},
-	{ /* QPI Port 0 filter  */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x3c96),
-		.driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV,
-						   SNBEP_PCI_QPI_PORT1_FILTER),
-	},
-	{ /* end: all zeroes */ }
-};
-
-static struct pci_driver snbep_uncore_pci_driver = {
-	.name		= "snbep_uncore",
-	.id_table	= snbep_uncore_pci_ids,
-};
-
-/*
- * build pci bus to socket mapping
- */
-static int snbep_pci2phy_map_init(int devid)
-{
-	struct pci_dev *ubox_dev = NULL;
-	int i, bus, nodeid;
-	int err = 0;
-	u32 config = 0;
-
-	while (1) {
-		/* find the UBOX device */
-		ubox_dev = pci_get_device(PCI_VENDOR_ID_INTEL, devid, ubox_dev);
-		if (!ubox_dev)
-			break;
-		bus = ubox_dev->bus->number;
-		/* get the Node ID of the local register */
-		err = pci_read_config_dword(ubox_dev, 0x40, &config);
-		if (err)
-			break;
-		nodeid = config;
-		/* get the Node ID mapping */
-		err = pci_read_config_dword(ubox_dev, 0x54, &config);
-		if (err)
-			break;
-		/*
-		 * every three bits in the Node ID mapping register maps
-		 * to a particular node.
-		 */
-		for (i = 0; i < 8; i++) {
-			if (nodeid == ((config >> (3 * i)) & 0x7)) {
-				pcibus_to_physid[bus] = i;
-				break;
-			}
-		}
-	}
-
-	if (!err) {
-		/*
-		 * For PCI bus with no UBOX device, find the next bus
-		 * that has UBOX device and use its mapping.
-		 */
-		i = -1;
-		for (bus = 255; bus >= 0; bus--) {
-			if (pcibus_to_physid[bus] >= 0)
-				i = pcibus_to_physid[bus];
-			else
-				pcibus_to_physid[bus] = i;
-		}
-	}
-
-	if (ubox_dev)
-		pci_dev_put(ubox_dev);
-
-	return err ? pcibios_err_to_errno(err) : 0;
-}
-/* end of Sandy Bridge-EP uncore support */
-
-/* IvyTown uncore support */
-static void ivt_uncore_msr_init_box(struct intel_uncore_box *box)
-{
-	unsigned msr = uncore_msr_box_ctl(box);
-	if (msr)
-		wrmsrl(msr, IVT_PMON_BOX_CTL_INT);
-}
-
-static void ivt_uncore_pci_init_box(struct intel_uncore_box *box)
-{
-	struct pci_dev *pdev = box->pci_dev;
-
-	pci_write_config_dword(pdev, SNBEP_PCI_PMON_BOX_CTL, IVT_PMON_BOX_CTL_INT);
-}
-
-#define IVT_UNCORE_MSR_OPS_COMMON_INIT()			\
-	.init_box	= ivt_uncore_msr_init_box,		\
-	.disable_box	= snbep_uncore_msr_disable_box,		\
-	.enable_box	= snbep_uncore_msr_enable_box,		\
-	.disable_event	= snbep_uncore_msr_disable_event,	\
-	.enable_event	= snbep_uncore_msr_enable_event,	\
-	.read_counter	= uncore_msr_read_counter
-
-static struct intel_uncore_ops ivt_uncore_msr_ops = {
-	IVT_UNCORE_MSR_OPS_COMMON_INIT(),
-};
-
-static struct intel_uncore_ops ivt_uncore_pci_ops = {
-	.init_box	= ivt_uncore_pci_init_box,
-	.disable_box	= snbep_uncore_pci_disable_box,
-	.enable_box	= snbep_uncore_pci_enable_box,
-	.disable_event	= snbep_uncore_pci_disable_event,
-	.enable_event	= snbep_uncore_pci_enable_event,
-	.read_counter	= snbep_uncore_pci_read_counter,
-};
-
-#define IVT_UNCORE_PCI_COMMON_INIT()				\
-	.perf_ctr	= SNBEP_PCI_PMON_CTR0,			\
-	.event_ctl	= SNBEP_PCI_PMON_CTL0,			\
-	.event_mask	= IVT_PMON_RAW_EVENT_MASK,		\
-	.box_ctl	= SNBEP_PCI_PMON_BOX_CTL,		\
-	.ops		= &ivt_uncore_pci_ops,			\
-	.format_group	= &ivt_uncore_format_group
-
-static struct attribute *ivt_uncore_formats_attr[] = {
-	&format_attr_event.attr,
-	&format_attr_umask.attr,
-	&format_attr_edge.attr,
-	&format_attr_inv.attr,
-	&format_attr_thresh8.attr,
-	NULL,
-};
-
-static struct attribute *ivt_uncore_ubox_formats_attr[] = {
-	&format_attr_event.attr,
-	&format_attr_umask.attr,
-	&format_attr_edge.attr,
-	&format_attr_inv.attr,
-	&format_attr_thresh5.attr,
-	NULL,
-};
-
-static struct attribute *ivt_uncore_cbox_formats_attr[] = {
-	&format_attr_event.attr,
-	&format_attr_umask.attr,
-	&format_attr_edge.attr,
-	&format_attr_tid_en.attr,
-	&format_attr_thresh8.attr,
-	&format_attr_filter_tid.attr,
-	&format_attr_filter_link.attr,
-	&format_attr_filter_state2.attr,
-	&format_attr_filter_nid2.attr,
-	&format_attr_filter_opc2.attr,
-	NULL,
-};
-
-static struct attribute *ivt_uncore_pcu_formats_attr[] = {
-	&format_attr_event_ext.attr,
-	&format_attr_occ_sel.attr,
-	&format_attr_edge.attr,
-	&format_attr_thresh5.attr,
-	&format_attr_occ_invert.attr,
-	&format_attr_occ_edge.attr,
-	&format_attr_filter_band0.attr,
-	&format_attr_filter_band1.attr,
-	&format_attr_filter_band2.attr,
-	&format_attr_filter_band3.attr,
-	NULL,
-};
-
-static struct attribute *ivt_uncore_qpi_formats_attr[] = {
-	&format_attr_event_ext.attr,
-	&format_attr_umask.attr,
-	&format_attr_edge.attr,
-	&format_attr_thresh8.attr,
-	&format_attr_match_rds.attr,
-	&format_attr_match_rnid30.attr,
-	&format_attr_match_rnid4.attr,
-	&format_attr_match_dnid.attr,
-	&format_attr_match_mc.attr,
-	&format_attr_match_opc.attr,
-	&format_attr_match_vnw.attr,
-	&format_attr_match0.attr,
-	&format_attr_match1.attr,
-	&format_attr_mask_rds.attr,
-	&format_attr_mask_rnid30.attr,
-	&format_attr_mask_rnid4.attr,
-	&format_attr_mask_dnid.attr,
-	&format_attr_mask_mc.attr,
-	&format_attr_mask_opc.attr,
-	&format_attr_mask_vnw.attr,
-	&format_attr_mask0.attr,
-	&format_attr_mask1.attr,
-	NULL,
-};
-
-static struct attribute_group ivt_uncore_format_group = {
-	.name = "format",
-	.attrs = ivt_uncore_formats_attr,
-};
-
-static struct attribute_group ivt_uncore_ubox_format_group = {
-	.name = "format",
-	.attrs = ivt_uncore_ubox_formats_attr,
-};
-
-static struct attribute_group ivt_uncore_cbox_format_group = {
-	.name = "format",
-	.attrs = ivt_uncore_cbox_formats_attr,
-};
-
-static struct attribute_group ivt_uncore_pcu_format_group = {
-	.name = "format",
-	.attrs = ivt_uncore_pcu_formats_attr,
-};
-
-static struct attribute_group ivt_uncore_qpi_format_group = {
-	.name = "format",
-	.attrs = ivt_uncore_qpi_formats_attr,
-};
-
-static struct intel_uncore_type ivt_uncore_ubox = {
-	.name		= "ubox",
-	.num_counters   = 2,
-	.num_boxes	= 1,
-	.perf_ctr_bits	= 44,
-	.fixed_ctr_bits	= 48,
-	.perf_ctr	= SNBEP_U_MSR_PMON_CTR0,
-	.event_ctl	= SNBEP_U_MSR_PMON_CTL0,
-	.event_mask	= IVT_U_MSR_PMON_RAW_EVENT_MASK,
-	.fixed_ctr	= SNBEP_U_MSR_PMON_UCLK_FIXED_CTR,
-	.fixed_ctl	= SNBEP_U_MSR_PMON_UCLK_FIXED_CTL,
-	.ops		= &ivt_uncore_msr_ops,
-	.format_group	= &ivt_uncore_ubox_format_group,
-};
-
-static struct extra_reg ivt_uncore_cbox_extra_regs[] = {
-	SNBEP_CBO_EVENT_EXTRA_REG(SNBEP_CBO_PMON_CTL_TID_EN,
-				  SNBEP_CBO_PMON_CTL_TID_EN, 0x1),
-	SNBEP_CBO_EVENT_EXTRA_REG(0x1031, 0x10ff, 0x2),
-
-	SNBEP_CBO_EVENT_EXTRA_REG(0x1134, 0xffff, 0x4),
-	SNBEP_CBO_EVENT_EXTRA_REG(0x4134, 0xffff, 0xc),
-	SNBEP_CBO_EVENT_EXTRA_REG(0x5134, 0xffff, 0xc),
-	SNBEP_CBO_EVENT_EXTRA_REG(0x0334, 0xffff, 0x4),
-	SNBEP_CBO_EVENT_EXTRA_REG(0x4334, 0xffff, 0xc),
-	SNBEP_CBO_EVENT_EXTRA_REG(0x0534, 0xffff, 0x4),
-	SNBEP_CBO_EVENT_EXTRA_REG(0x4534, 0xffff, 0xc),
-	SNBEP_CBO_EVENT_EXTRA_REG(0x0934, 0xffff, 0x4),
-	SNBEP_CBO_EVENT_EXTRA_REG(0x4934, 0xffff, 0xc),
-	SNBEP_CBO_EVENT_EXTRA_REG(0x0135, 0xffff, 0x10),
-	SNBEP_CBO_EVENT_EXTRA_REG(0x0335, 0xffff, 0x10),
-	SNBEP_CBO_EVENT_EXTRA_REG(0x2135, 0xffff, 0x10),
-	SNBEP_CBO_EVENT_EXTRA_REG(0x2335, 0xffff, 0x10),
-	SNBEP_CBO_EVENT_EXTRA_REG(0x4135, 0xffff, 0x18),
-	SNBEP_CBO_EVENT_EXTRA_REG(0x4335, 0xffff, 0x18),
-	SNBEP_CBO_EVENT_EXTRA_REG(0x4435, 0xffff, 0x8),
-	SNBEP_CBO_EVENT_EXTRA_REG(0x4835, 0xffff, 0x8),
-	SNBEP_CBO_EVENT_EXTRA_REG(0x4a35, 0xffff, 0x8),
-	SNBEP_CBO_EVENT_EXTRA_REG(0x5035, 0xffff, 0x8),
-	SNBEP_CBO_EVENT_EXTRA_REG(0x8135, 0xffff, 0x10),
-	SNBEP_CBO_EVENT_EXTRA_REG(0x8335, 0xffff, 0x10),
-	SNBEP_CBO_EVENT_EXTRA_REG(0x0136, 0xffff, 0x10),
-	SNBEP_CBO_EVENT_EXTRA_REG(0x0336, 0xffff, 0x10),
-	SNBEP_CBO_EVENT_EXTRA_REG(0x2136, 0xffff, 0x10),
-	SNBEP_CBO_EVENT_EXTRA_REG(0x2336, 0xffff, 0x10),
-	SNBEP_CBO_EVENT_EXTRA_REG(0x4136, 0xffff, 0x18),
-	SNBEP_CBO_EVENT_EXTRA_REG(0x4336, 0xffff, 0x18),
-	SNBEP_CBO_EVENT_EXTRA_REG(0x4436, 0xffff, 0x8),
-	SNBEP_CBO_EVENT_EXTRA_REG(0x4836, 0xffff, 0x8),
-	SNBEP_CBO_EVENT_EXTRA_REG(0x4a36, 0xffff, 0x8),
-	SNBEP_CBO_EVENT_EXTRA_REG(0x5036, 0xffff, 0x8),
-	SNBEP_CBO_EVENT_EXTRA_REG(0x8136, 0xffff, 0x10),
-	SNBEP_CBO_EVENT_EXTRA_REG(0x8336, 0xffff, 0x10),
-	SNBEP_CBO_EVENT_EXTRA_REG(0x4037, 0x40ff, 0x8),
-	EVENT_EXTRA_END
-};
-
-static u64 ivt_cbox_filter_mask(int fields)
-{
-	u64 mask = 0;
-
-	if (fields & 0x1)
-		mask |= IVT_CB0_MSR_PMON_BOX_FILTER_TID;
-	if (fields & 0x2)
-		mask |= IVT_CB0_MSR_PMON_BOX_FILTER_LINK;
-	if (fields & 0x4)
-		mask |= IVT_CB0_MSR_PMON_BOX_FILTER_STATE;
-	if (fields & 0x8)
-		mask |= IVT_CB0_MSR_PMON_BOX_FILTER_NID;
-	if (fields & 0x10)
-		mask |= IVT_CB0_MSR_PMON_BOX_FILTER_OPC;
-
-	return mask;
-}
-
-static struct event_constraint *
-ivt_cbox_get_constraint(struct intel_uncore_box *box, struct perf_event *event)
-{
-	return __snbep_cbox_get_constraint(box, event, ivt_cbox_filter_mask);
-}
-
-static int ivt_cbox_hw_config(struct intel_uncore_box *box, struct perf_event *event)
-{
-	struct hw_perf_event_extra *reg1 = &event->hw.extra_reg;
-	struct extra_reg *er;
-	int idx = 0;
-
-	for (er = ivt_uncore_cbox_extra_regs; er->msr; er++) {
-		if (er->event != (event->hw.config & er->config_mask))
-			continue;
-		idx |= er->idx;
-	}
-
-	if (idx) {
-		reg1->reg = SNBEP_C0_MSR_PMON_BOX_FILTER +
-			SNBEP_CBO_MSR_OFFSET * box->pmu->pmu_idx;
-		reg1->config = event->attr.config1 & ivt_cbox_filter_mask(idx);
-		reg1->idx = idx;
-	}
-	return 0;
-}
-
-static void ivt_cbox_enable_event(struct intel_uncore_box *box, struct perf_event *event)
-{
-	struct hw_perf_event *hwc = &event->hw;
-	struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
-
-	if (reg1->idx != EXTRA_REG_NONE) {
-		u64 filter = uncore_shared_reg_config(box, 0);
-		wrmsrl(reg1->reg, filter & 0xffffffff);
-		wrmsrl(reg1->reg + 6, filter >> 32);
-	}
-
-	wrmsrl(hwc->config_base, hwc->config | SNBEP_PMON_CTL_EN);
-}
-
-static struct intel_uncore_ops ivt_uncore_cbox_ops = {
-	.init_box		= ivt_uncore_msr_init_box,
-	.disable_box		= snbep_uncore_msr_disable_box,
-	.enable_box		= snbep_uncore_msr_enable_box,
-	.disable_event		= snbep_uncore_msr_disable_event,
-	.enable_event		= ivt_cbox_enable_event,
-	.read_counter		= uncore_msr_read_counter,
-	.hw_config		= ivt_cbox_hw_config,
-	.get_constraint		= ivt_cbox_get_constraint,
-	.put_constraint		= snbep_cbox_put_constraint,
-};
-
-static struct intel_uncore_type ivt_uncore_cbox = {
-	.name			= "cbox",
-	.num_counters		= 4,
-	.num_boxes		= 15,
-	.perf_ctr_bits		= 44,
-	.event_ctl		= SNBEP_C0_MSR_PMON_CTL0,
-	.perf_ctr		= SNBEP_C0_MSR_PMON_CTR0,
-	.event_mask		= IVT_CBO_MSR_PMON_RAW_EVENT_MASK,
-	.box_ctl		= SNBEP_C0_MSR_PMON_BOX_CTL,
-	.msr_offset		= SNBEP_CBO_MSR_OFFSET,
-	.num_shared_regs	= 1,
-	.constraints		= snbep_uncore_cbox_constraints,
-	.ops			= &ivt_uncore_cbox_ops,
-	.format_group		= &ivt_uncore_cbox_format_group,
-};
-
-static struct intel_uncore_ops ivt_uncore_pcu_ops = {
-	IVT_UNCORE_MSR_OPS_COMMON_INIT(),
-	.hw_config		= snbep_pcu_hw_config,
-	.get_constraint		= snbep_pcu_get_constraint,
-	.put_constraint		= snbep_pcu_put_constraint,
-};
-
-static struct intel_uncore_type ivt_uncore_pcu = {
-	.name			= "pcu",
-	.num_counters		= 4,
-	.num_boxes		= 1,
-	.perf_ctr_bits		= 48,
-	.perf_ctr		= SNBEP_PCU_MSR_PMON_CTR0,
-	.event_ctl		= SNBEP_PCU_MSR_PMON_CTL0,
-	.event_mask		= IVT_PCU_MSR_PMON_RAW_EVENT_MASK,
-	.box_ctl		= SNBEP_PCU_MSR_PMON_BOX_CTL,
-	.num_shared_regs	= 1,
-	.ops			= &ivt_uncore_pcu_ops,
-	.format_group		= &ivt_uncore_pcu_format_group,
-};
-
-static struct intel_uncore_type *ivt_msr_uncores[] = {
-	&ivt_uncore_ubox,
-	&ivt_uncore_cbox,
-	&ivt_uncore_pcu,
-	NULL,
-};
-
-static struct intel_uncore_type ivt_uncore_ha = {
-	.name		= "ha",
-	.num_counters   = 4,
-	.num_boxes	= 2,
-	.perf_ctr_bits	= 48,
-	IVT_UNCORE_PCI_COMMON_INIT(),
-};
-
-static struct intel_uncore_type ivt_uncore_imc = {
-	.name		= "imc",
-	.num_counters   = 4,
-	.num_boxes	= 8,
-	.perf_ctr_bits	= 48,
-	.fixed_ctr_bits	= 48,
-	.fixed_ctr	= SNBEP_MC_CHy_PCI_PMON_FIXED_CTR,
-	.fixed_ctl	= SNBEP_MC_CHy_PCI_PMON_FIXED_CTL,
-	IVT_UNCORE_PCI_COMMON_INIT(),
-};
-
-/* registers in IRP boxes are not properly aligned */
-static unsigned ivt_uncore_irp_ctls[] = {0xd8, 0xdc, 0xe0, 0xe4};
-static unsigned ivt_uncore_irp_ctrs[] = {0xa0, 0xb0, 0xb8, 0xc0};
-
-static void ivt_uncore_irp_enable_event(struct intel_uncore_box *box, struct perf_event *event)
-{
-	struct pci_dev *pdev = box->pci_dev;
-	struct hw_perf_event *hwc = &event->hw;
-
-	pci_write_config_dword(pdev, ivt_uncore_irp_ctls[hwc->idx],
-			       hwc->config | SNBEP_PMON_CTL_EN);
-}
-
-static void ivt_uncore_irp_disable_event(struct intel_uncore_box *box, struct perf_event *event)
-{
-	struct pci_dev *pdev = box->pci_dev;
-	struct hw_perf_event *hwc = &event->hw;
-
-	pci_write_config_dword(pdev, ivt_uncore_irp_ctls[hwc->idx], hwc->config);
-}
-
-static u64 ivt_uncore_irp_read_counter(struct intel_uncore_box *box, struct perf_event *event)
-{
-	struct pci_dev *pdev = box->pci_dev;
-	struct hw_perf_event *hwc = &event->hw;
-	u64 count = 0;
-
-	pci_read_config_dword(pdev, ivt_uncore_irp_ctrs[hwc->idx], (u32 *)&count);
-	pci_read_config_dword(pdev, ivt_uncore_irp_ctrs[hwc->idx] + 4, (u32 *)&count + 1);
-
-	return count;
-}
-
-static struct intel_uncore_ops ivt_uncore_irp_ops = {
-	.init_box	= ivt_uncore_pci_init_box,
-	.disable_box	= snbep_uncore_pci_disable_box,
-	.enable_box	= snbep_uncore_pci_enable_box,
-	.disable_event	= ivt_uncore_irp_disable_event,
-	.enable_event	= ivt_uncore_irp_enable_event,
-	.read_counter	= ivt_uncore_irp_read_counter,
-};
-
-static struct intel_uncore_type ivt_uncore_irp = {
-	.name			= "irp",
-	.num_counters		= 4,
-	.num_boxes		= 1,
-	.perf_ctr_bits		= 48,
-	.event_mask		= IVT_PMON_RAW_EVENT_MASK,
-	.box_ctl		= SNBEP_PCI_PMON_BOX_CTL,
-	.ops			= &ivt_uncore_irp_ops,
-	.format_group		= &ivt_uncore_format_group,
-};
-
-static struct intel_uncore_ops ivt_uncore_qpi_ops = {
-	.init_box	= ivt_uncore_pci_init_box,
-	.disable_box	= snbep_uncore_pci_disable_box,
-	.enable_box	= snbep_uncore_pci_enable_box,
-	.disable_event	= snbep_uncore_pci_disable_event,
-	.enable_event	= snbep_qpi_enable_event,
-	.read_counter	= snbep_uncore_pci_read_counter,
-	.hw_config	= snbep_qpi_hw_config,
-	.get_constraint	= uncore_get_constraint,
-	.put_constraint	= uncore_put_constraint,
-};
-
-static struct intel_uncore_type ivt_uncore_qpi = {
-	.name			= "qpi",
-	.num_counters		= 4,
-	.num_boxes		= 3,
-	.perf_ctr_bits		= 48,
-	.perf_ctr		= SNBEP_PCI_PMON_CTR0,
-	.event_ctl		= SNBEP_PCI_PMON_CTL0,
-	.event_mask		= IVT_QPI_PCI_PMON_RAW_EVENT_MASK,
-	.box_ctl		= SNBEP_PCI_PMON_BOX_CTL,
-	.num_shared_regs	= 1,
-	.ops			= &ivt_uncore_qpi_ops,
-	.format_group		= &ivt_uncore_qpi_format_group,
-};
-
-static struct intel_uncore_type ivt_uncore_r2pcie = {
-	.name		= "r2pcie",
-	.num_counters   = 4,
-	.num_boxes	= 1,
-	.perf_ctr_bits	= 44,
-	.constraints	= snbep_uncore_r2pcie_constraints,
-	IVT_UNCORE_PCI_COMMON_INIT(),
-};
-
-static struct intel_uncore_type ivt_uncore_r3qpi = {
-	.name		= "r3qpi",
-	.num_counters   = 3,
-	.num_boxes	= 2,
-	.perf_ctr_bits	= 44,
-	.constraints	= snbep_uncore_r3qpi_constraints,
-	IVT_UNCORE_PCI_COMMON_INIT(),
-};
-
-enum {
-	IVT_PCI_UNCORE_HA,
-	IVT_PCI_UNCORE_IMC,
-	IVT_PCI_UNCORE_IRP,
-	IVT_PCI_UNCORE_QPI,
-	IVT_PCI_UNCORE_R2PCIE,
-	IVT_PCI_UNCORE_R3QPI,
-};
-
-static struct intel_uncore_type *ivt_pci_uncores[] = {
-	[IVT_PCI_UNCORE_HA]	= &ivt_uncore_ha,
-	[IVT_PCI_UNCORE_IMC]	= &ivt_uncore_imc,
-	[IVT_PCI_UNCORE_IRP]	= &ivt_uncore_irp,
-	[IVT_PCI_UNCORE_QPI]	= &ivt_uncore_qpi,
-	[IVT_PCI_UNCORE_R2PCIE]	= &ivt_uncore_r2pcie,
-	[IVT_PCI_UNCORE_R3QPI]	= &ivt_uncore_r3qpi,
-	NULL,
-};
-
-static const struct pci_device_id ivt_uncore_pci_ids[] = {
-	{ /* Home Agent 0 */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe30),
-		.driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_HA, 0),
-	},
-	{ /* Home Agent 1 */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe38),
-		.driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_HA, 1),
-	},
-	{ /* MC0 Channel 0 */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xeb4),
-		.driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_IMC, 0),
-	},
-	{ /* MC0 Channel 1 */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xeb5),
-		.driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_IMC, 1),
-	},
-	{ /* MC0 Channel 3 */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xeb0),
-		.driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_IMC, 2),
-	},
-	{ /* MC0 Channel 4 */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xeb1),
-		.driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_IMC, 3),
-	},
-	{ /* MC1 Channel 0 */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xef4),
-		.driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_IMC, 4),
-	},
-	{ /* MC1 Channel 1 */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xef5),
-		.driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_IMC, 5),
-	},
-	{ /* MC1 Channel 3 */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xef0),
-		.driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_IMC, 6),
-	},
-	{ /* MC1 Channel 4 */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xef1),
-		.driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_IMC, 7),
-	},
-	{ /* IRP */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe39),
-		.driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_IRP, 0),
-	},
-	{ /* QPI0 Port 0 */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe32),
-		.driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_QPI, 0),
-	},
-	{ /* QPI0 Port 1 */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe33),
-		.driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_QPI, 1),
-	},
-	{ /* QPI1 Port 2 */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe3a),
-		.driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_QPI, 2),
-	},
-	{ /* R2PCIe */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe34),
-		.driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_R2PCIE, 0),
-	},
-	{ /* R3QPI0 Link 0 */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe36),
-		.driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_R3QPI, 0),
-	},
-	{ /* R3QPI0 Link 1 */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe37),
-		.driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_R3QPI, 1),
-	},
-	{ /* R3QPI1 Link 2 */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe3e),
-		.driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_R3QPI, 2),
-	},
-	{ /* QPI Port 0 filter  */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe86),
-		.driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV,
-						   SNBEP_PCI_QPI_PORT0_FILTER),
-	},
-	{ /* QPI Port 0 filter  */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe96),
-		.driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV,
-						   SNBEP_PCI_QPI_PORT1_FILTER),
-	},
-	{ /* end: all zeroes */ }
-};
-
-static struct pci_driver ivt_uncore_pci_driver = {
-	.name		= "ivt_uncore",
-	.id_table	= ivt_uncore_pci_ids,
-};
-/* end of IvyTown uncore support */
-
-/* Sandy Bridge uncore support */
-static void snb_uncore_msr_enable_event(struct intel_uncore_box *box, struct perf_event *event)
-{
-	struct hw_perf_event *hwc = &event->hw;
-
-	if (hwc->idx < UNCORE_PMC_IDX_FIXED)
-		wrmsrl(hwc->config_base, hwc->config | SNB_UNC_CTL_EN);
-	else
-		wrmsrl(hwc->config_base, SNB_UNC_CTL_EN);
-}
-
-static void snb_uncore_msr_disable_event(struct intel_uncore_box *box, struct perf_event *event)
-{
-	wrmsrl(event->hw.config_base, 0);
-}
-
-static void snb_uncore_msr_init_box(struct intel_uncore_box *box)
-{
-	if (box->pmu->pmu_idx == 0) {
-		wrmsrl(SNB_UNC_PERF_GLOBAL_CTL,
-			SNB_UNC_GLOBAL_CTL_EN | SNB_UNC_GLOBAL_CTL_CORE_ALL);
-	}
-}
-
-static struct uncore_event_desc snb_uncore_events[] = {
-	INTEL_UNCORE_EVENT_DESC(clockticks, "event=0xff,umask=0x00"),
-	{ /* end: all zeroes */ },
-};
-
-static struct attribute *snb_uncore_formats_attr[] = {
-	&format_attr_event.attr,
-	&format_attr_umask.attr,
-	&format_attr_edge.attr,
-	&format_attr_inv.attr,
-	&format_attr_cmask5.attr,
-	NULL,
-};
-
-static struct attribute_group snb_uncore_format_group = {
-	.name		= "format",
-	.attrs		= snb_uncore_formats_attr,
-};
-
-static struct intel_uncore_ops snb_uncore_msr_ops = {
-	.init_box	= snb_uncore_msr_init_box,
-	.disable_event	= snb_uncore_msr_disable_event,
-	.enable_event	= snb_uncore_msr_enable_event,
-	.read_counter	= uncore_msr_read_counter,
-};
-
-static struct event_constraint snb_uncore_cbox_constraints[] = {
-	UNCORE_EVENT_CONSTRAINT(0x80, 0x1),
-	UNCORE_EVENT_CONSTRAINT(0x83, 0x1),
-	EVENT_CONSTRAINT_END
-};
-
-static struct intel_uncore_type snb_uncore_cbox = {
-	.name		= "cbox",
-	.num_counters   = 2,
-	.num_boxes	= 4,
-	.perf_ctr_bits	= 44,
-	.fixed_ctr_bits	= 48,
-	.perf_ctr	= SNB_UNC_CBO_0_PER_CTR0,
-	.event_ctl	= SNB_UNC_CBO_0_PERFEVTSEL0,
-	.fixed_ctr	= SNB_UNC_FIXED_CTR,
-	.fixed_ctl	= SNB_UNC_FIXED_CTR_CTRL,
-	.single_fixed	= 1,
-	.event_mask	= SNB_UNC_RAW_EVENT_MASK,
-	.msr_offset	= SNB_UNC_CBO_MSR_OFFSET,
-	.constraints	= snb_uncore_cbox_constraints,
-	.ops		= &snb_uncore_msr_ops,
-	.format_group	= &snb_uncore_format_group,
-	.event_descs	= snb_uncore_events,
-};
-
-static struct intel_uncore_type *snb_msr_uncores[] = {
-	&snb_uncore_cbox,
-	NULL,
-};
-
-enum {
-	SNB_PCI_UNCORE_IMC,
-};
-
-static struct uncore_event_desc snb_uncore_imc_events[] = {
-	INTEL_UNCORE_EVENT_DESC(data_reads,  "event=0x01"),
-	INTEL_UNCORE_EVENT_DESC(data_reads.scale, "6.103515625e-5"),
-	INTEL_UNCORE_EVENT_DESC(data_reads.unit, "MiB"),
-
-	INTEL_UNCORE_EVENT_DESC(data_writes, "event=0x02"),
-	INTEL_UNCORE_EVENT_DESC(data_writes.scale, "6.103515625e-5"),
-	INTEL_UNCORE_EVENT_DESC(data_writes.unit, "MiB"),
-
-	{ /* end: all zeroes */ },
-};
-
-#define SNB_UNCORE_PCI_IMC_EVENT_MASK		0xff
-#define SNB_UNCORE_PCI_IMC_BAR_OFFSET		0x48
-
-/* page size multiple covering all config regs */
-#define SNB_UNCORE_PCI_IMC_MAP_SIZE		0x6000
-
-#define SNB_UNCORE_PCI_IMC_DATA_READS		0x1
-#define SNB_UNCORE_PCI_IMC_DATA_READS_BASE	0x5050
-#define SNB_UNCORE_PCI_IMC_DATA_WRITES		0x2
-#define SNB_UNCORE_PCI_IMC_DATA_WRITES_BASE	0x5054
-#define SNB_UNCORE_PCI_IMC_CTR_BASE		SNB_UNCORE_PCI_IMC_DATA_READS_BASE
-
-static struct attribute *snb_uncore_imc_formats_attr[] = {
-	&format_attr_event.attr,
-	NULL,
-};
-
-static struct attribute_group snb_uncore_imc_format_group = {
-	.name = "format",
-	.attrs = snb_uncore_imc_formats_attr,
-};
-
-static void snb_uncore_imc_init_box(struct intel_uncore_box *box)
-{
-	struct pci_dev *pdev = box->pci_dev;
-	int where = SNB_UNCORE_PCI_IMC_BAR_OFFSET;
-	resource_size_t addr;
-	u32 pci_dword;
-
-	pci_read_config_dword(pdev, where, &pci_dword);
-	addr = pci_dword;
-
-#ifdef CONFIG_PHYS_ADDR_T_64BIT
-	pci_read_config_dword(pdev, where + 4, &pci_dword);
-	addr |= ((resource_size_t)pci_dword << 32);
-#endif
-
-	addr &= ~(PAGE_SIZE - 1);
-
-	box->io_addr = ioremap(addr, SNB_UNCORE_PCI_IMC_MAP_SIZE);
-	box->hrtimer_duration = UNCORE_SNB_IMC_HRTIMER_INTERVAL;
-}
-
-static void snb_uncore_imc_enable_box(struct intel_uncore_box *box)
-{}
-
-static void snb_uncore_imc_disable_box(struct intel_uncore_box *box)
-{}
-
-static void snb_uncore_imc_enable_event(struct intel_uncore_box *box, struct perf_event *event)
-{}
-
-static void snb_uncore_imc_disable_event(struct intel_uncore_box *box, struct perf_event *event)
-{}
-
-static u64 snb_uncore_imc_read_counter(struct intel_uncore_box *box, struct perf_event *event)
-{
-	struct hw_perf_event *hwc = &event->hw;
-
-	return (u64)*(unsigned int *)(box->io_addr + hwc->event_base);
-}
-
-/*
- * custom event_init() function because we define our own fixed, free
- * running counters, so we do not want to conflict with generic uncore
- * logic. Also simplifies processing
- */
-static int snb_uncore_imc_event_init(struct perf_event *event)
-{
-	struct intel_uncore_pmu *pmu;
-	struct intel_uncore_box *box;
-	struct hw_perf_event *hwc = &event->hw;
-	u64 cfg = event->attr.config & SNB_UNCORE_PCI_IMC_EVENT_MASK;
-	int idx, base;
-
-	if (event->attr.type != event->pmu->type)
-		return -ENOENT;
-
-	pmu = uncore_event_to_pmu(event);
-	/* no device found for this pmu */
-	if (pmu->func_id < 0)
-		return -ENOENT;
-
-	/* Sampling not supported yet */
-	if (hwc->sample_period)
-		return -EINVAL;
-
-	/* unsupported modes and filters */
-	if (event->attr.exclude_user   ||
-	    event->attr.exclude_kernel ||
-	    event->attr.exclude_hv     ||
-	    event->attr.exclude_idle   ||
-	    event->attr.exclude_host   ||
-	    event->attr.exclude_guest  ||
-	    event->attr.sample_period) /* no sampling */
-		return -EINVAL;
-
-	/*
-	 * Place all uncore events for a particular physical package
-	 * onto a single cpu
-	 */
-	if (event->cpu < 0)
-		return -EINVAL;
-
-	/* check only supported bits are set */
-	if (event->attr.config & ~SNB_UNCORE_PCI_IMC_EVENT_MASK)
-		return -EINVAL;
-
-	box = uncore_pmu_to_box(pmu, event->cpu);
-	if (!box || box->cpu < 0)
-		return -EINVAL;
-
-	event->cpu = box->cpu;
-
-	event->hw.idx = -1;
-	event->hw.last_tag = ~0ULL;
-	event->hw.extra_reg.idx = EXTRA_REG_NONE;
-	event->hw.branch_reg.idx = EXTRA_REG_NONE;
-	/*
-	 * check event is known (whitelist, determines counter)
-	 */
-	switch (cfg) {
-	case SNB_UNCORE_PCI_IMC_DATA_READS:
-		base = SNB_UNCORE_PCI_IMC_DATA_READS_BASE;
-		idx = UNCORE_PMC_IDX_FIXED;
-		break;
-	case SNB_UNCORE_PCI_IMC_DATA_WRITES:
-		base = SNB_UNCORE_PCI_IMC_DATA_WRITES_BASE;
-		idx = UNCORE_PMC_IDX_FIXED + 1;
-		break;
-	default:
-		return -EINVAL;
-	}
-
-	/* must be done before validate_group */
-	event->hw.event_base = base;
-	event->hw.config = cfg;
-	event->hw.idx = idx;
-
-	/* no group validation needed, we have free running counters */
-
-	return 0;
-}
-
-static int snb_uncore_imc_hw_config(struct intel_uncore_box *box, struct perf_event *event)
-{
-	return 0;
-}
-
-static void snb_uncore_imc_event_start(struct perf_event *event, int flags)
-{
-	struct intel_uncore_box *box = uncore_event_to_box(event);
-	u64 count;
-
-	if (WARN_ON_ONCE(!(event->hw.state & PERF_HES_STOPPED)))
-		return;
-
-	event->hw.state = 0;
-	box->n_active++;
-
-	list_add_tail(&event->active_entry, &box->active_list);
-
-	count = snb_uncore_imc_read_counter(box, event);
-	local64_set(&event->hw.prev_count, count);
-
-	if (box->n_active == 1)
-		uncore_pmu_start_hrtimer(box);
-}
-
-static void snb_uncore_imc_event_stop(struct perf_event *event, int flags)
-{
-	struct intel_uncore_box *box = uncore_event_to_box(event);
-	struct hw_perf_event *hwc = &event->hw;
-
-	if (!(hwc->state & PERF_HES_STOPPED)) {
-		box->n_active--;
-
-		WARN_ON_ONCE(hwc->state & PERF_HES_STOPPED);
-		hwc->state |= PERF_HES_STOPPED;
-
-		list_del(&event->active_entry);
-
-		if (box->n_active == 0)
-			uncore_pmu_cancel_hrtimer(box);
-	}
-
-	if ((flags & PERF_EF_UPDATE) && !(hwc->state & PERF_HES_UPTODATE)) {
-		/*
-		 * Drain the remaining delta count out of a event
-		 * that we are disabling:
-		 */
-		uncore_perf_event_update(box, event);
-		hwc->state |= PERF_HES_UPTODATE;
-	}
-}
-
-static int snb_uncore_imc_event_add(struct perf_event *event, int flags)
-{
-	struct intel_uncore_box *box = uncore_event_to_box(event);
-	struct hw_perf_event *hwc = &event->hw;
-
-	if (!box)
-		return -ENODEV;
-
-	hwc->state = PERF_HES_UPTODATE | PERF_HES_STOPPED;
-	if (!(flags & PERF_EF_START))
-		hwc->state |= PERF_HES_ARCH;
-
-	snb_uncore_imc_event_start(event, 0);
-
-	box->n_events++;
-
-	return 0;
-}
-
-static void snb_uncore_imc_event_del(struct perf_event *event, int flags)
-{
-	struct intel_uncore_box *box = uncore_event_to_box(event);
-	int i;
-
-	snb_uncore_imc_event_stop(event, PERF_EF_UPDATE);
-
-	for (i = 0; i < box->n_events; i++) {
-		if (event == box->event_list[i]) {
-			--box->n_events;
-			break;
-		}
-	}
-}
-
-static int snb_pci2phy_map_init(int devid)
-{
-	struct pci_dev *dev = NULL;
-	int bus;
-
-	dev = pci_get_device(PCI_VENDOR_ID_INTEL, devid, dev);
-	if (!dev)
-		return -ENOTTY;
-
-	bus = dev->bus->number;
-
-	pcibus_to_physid[bus] = 0;
-
-	pci_dev_put(dev);
-
-	return 0;
-}
-
-static struct pmu snb_uncore_imc_pmu = {
-	.task_ctx_nr	= perf_invalid_context,
-	.event_init	= snb_uncore_imc_event_init,
-	.add		= snb_uncore_imc_event_add,
-	.del		= snb_uncore_imc_event_del,
-	.start		= snb_uncore_imc_event_start,
-	.stop		= snb_uncore_imc_event_stop,
-	.read		= uncore_pmu_event_read,
-};
-
-static struct intel_uncore_ops snb_uncore_imc_ops = {
-	.init_box	= snb_uncore_imc_init_box,
-	.enable_box	= snb_uncore_imc_enable_box,
-	.disable_box	= snb_uncore_imc_disable_box,
-	.disable_event	= snb_uncore_imc_disable_event,
-	.enable_event	= snb_uncore_imc_enable_event,
-	.hw_config	= snb_uncore_imc_hw_config,
-	.read_counter	= snb_uncore_imc_read_counter,
-};
-
-static struct intel_uncore_type snb_uncore_imc = {
-	.name		= "imc",
-	.num_counters   = 2,
-	.num_boxes	= 1,
-	.fixed_ctr_bits	= 32,
-	.fixed_ctr	= SNB_UNCORE_PCI_IMC_CTR_BASE,
-	.event_descs	= snb_uncore_imc_events,
-	.format_group	= &snb_uncore_imc_format_group,
-	.perf_ctr	= SNB_UNCORE_PCI_IMC_DATA_READS_BASE,
-	.event_mask	= SNB_UNCORE_PCI_IMC_EVENT_MASK,
-	.ops		= &snb_uncore_imc_ops,
-	.pmu		= &snb_uncore_imc_pmu,
-};
-
-static struct intel_uncore_type *snb_pci_uncores[] = {
-	[SNB_PCI_UNCORE_IMC]	= &snb_uncore_imc,
-	NULL,
-};
-
-static const struct pci_device_id snb_uncore_pci_ids[] = {
-	{ /* IMC */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_SNB_IMC),
-		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
-	},
-	{ /* end: all zeroes */ },
-};
-
-static const struct pci_device_id ivb_uncore_pci_ids[] = {
-	{ /* IMC */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_IVB_IMC),
-		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
-	},
-	{ /* end: all zeroes */ },
-};
-
-static const struct pci_device_id hsw_uncore_pci_ids[] = {
-	{ /* IMC */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_HSW_IMC),
-		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
-	},
-	{ /* end: all zeroes */ },
-};
-
-static struct pci_driver snb_uncore_pci_driver = {
-	.name		= "snb_uncore",
-	.id_table	= snb_uncore_pci_ids,
-};
-
-static struct pci_driver ivb_uncore_pci_driver = {
-	.name		= "ivb_uncore",
-	.id_table	= ivb_uncore_pci_ids,
-};
-
-static struct pci_driver hsw_uncore_pci_driver = {
-	.name		= "hsw_uncore",
-	.id_table	= hsw_uncore_pci_ids,
-};
-
-/* end of Sandy Bridge uncore support */
-
-/* Nehalem uncore support */
-static void nhm_uncore_msr_disable_box(struct intel_uncore_box *box)
-{
-	wrmsrl(NHM_UNC_PERF_GLOBAL_CTL, 0);
-}
-
-static void nhm_uncore_msr_enable_box(struct intel_uncore_box *box)
-{
-	wrmsrl(NHM_UNC_PERF_GLOBAL_CTL, NHM_UNC_GLOBAL_CTL_EN_PC_ALL | NHM_UNC_GLOBAL_CTL_EN_FC);
-}
-
-static void nhm_uncore_msr_enable_event(struct intel_uncore_box *box, struct perf_event *event)
-{
-	struct hw_perf_event *hwc = &event->hw;
-
-	if (hwc->idx < UNCORE_PMC_IDX_FIXED)
-		wrmsrl(hwc->config_base, hwc->config | SNB_UNC_CTL_EN);
-	else
-		wrmsrl(hwc->config_base, NHM_UNC_FIXED_CTR_CTL_EN);
-}
-
-static struct attribute *nhm_uncore_formats_attr[] = {
-	&format_attr_event.attr,
-	&format_attr_umask.attr,
-	&format_attr_edge.attr,
-	&format_attr_inv.attr,
-	&format_attr_cmask8.attr,
-	NULL,
-};
-
-static struct attribute_group nhm_uncore_format_group = {
-	.name = "format",
-	.attrs = nhm_uncore_formats_attr,
-};
-
-static struct uncore_event_desc nhm_uncore_events[] = {
-	INTEL_UNCORE_EVENT_DESC(clockticks,                "event=0xff,umask=0x00"),
-	INTEL_UNCORE_EVENT_DESC(qmc_writes_full_any,       "event=0x2f,umask=0x0f"),
-	INTEL_UNCORE_EVENT_DESC(qmc_normal_reads_any,      "event=0x2c,umask=0x0f"),
-	INTEL_UNCORE_EVENT_DESC(qhl_request_ioh_reads,     "event=0x20,umask=0x01"),
-	INTEL_UNCORE_EVENT_DESC(qhl_request_ioh_writes,    "event=0x20,umask=0x02"),
-	INTEL_UNCORE_EVENT_DESC(qhl_request_remote_reads,  "event=0x20,umask=0x04"),
-	INTEL_UNCORE_EVENT_DESC(qhl_request_remote_writes, "event=0x20,umask=0x08"),
-	INTEL_UNCORE_EVENT_DESC(qhl_request_local_reads,   "event=0x20,umask=0x10"),
-	INTEL_UNCORE_EVENT_DESC(qhl_request_local_writes,  "event=0x20,umask=0x20"),
-	{ /* end: all zeroes */ },
-};
-
-static struct intel_uncore_ops nhm_uncore_msr_ops = {
-	.disable_box	= nhm_uncore_msr_disable_box,
-	.enable_box	= nhm_uncore_msr_enable_box,
-	.disable_event	= snb_uncore_msr_disable_event,
-	.enable_event	= nhm_uncore_msr_enable_event,
-	.read_counter	= uncore_msr_read_counter,
-};
-
-static struct intel_uncore_type nhm_uncore = {
-	.name		= "",
-	.num_counters   = 8,
-	.num_boxes	= 1,
-	.perf_ctr_bits	= 48,
-	.fixed_ctr_bits	= 48,
-	.event_ctl	= NHM_UNC_PERFEVTSEL0,
-	.perf_ctr	= NHM_UNC_UNCORE_PMC0,
-	.fixed_ctr	= NHM_UNC_FIXED_CTR,
-	.fixed_ctl	= NHM_UNC_FIXED_CTR_CTRL,
-	.event_mask	= NHM_UNC_RAW_EVENT_MASK,
-	.event_descs	= nhm_uncore_events,
-	.ops		= &nhm_uncore_msr_ops,
-	.format_group	= &nhm_uncore_format_group,
-};
-
-static struct intel_uncore_type *nhm_msr_uncores[] = {
-	&nhm_uncore,
-	NULL,
-};
-/* end of Nehalem uncore support */
-
-/* Nehalem-EX uncore support */
-DEFINE_UNCORE_FORMAT_ATTR(event5, event, "config:1-5");
-DEFINE_UNCORE_FORMAT_ATTR(counter, counter, "config:6-7");
-DEFINE_UNCORE_FORMAT_ATTR(match, match, "config1:0-63");
-DEFINE_UNCORE_FORMAT_ATTR(mask, mask, "config2:0-63");
-
-static void nhmex_uncore_msr_init_box(struct intel_uncore_box *box)
-{
-	wrmsrl(NHMEX_U_MSR_PMON_GLOBAL_CTL, NHMEX_U_PMON_GLOBAL_EN_ALL);
-}
-
-static void nhmex_uncore_msr_disable_box(struct intel_uncore_box *box)
-{
-	unsigned msr = uncore_msr_box_ctl(box);
-	u64 config;
-
-	if (msr) {
-		rdmsrl(msr, config);
-		config &= ~((1ULL << uncore_num_counters(box)) - 1);
-		/* WBox has a fixed counter */
-		if (uncore_msr_fixed_ctl(box))
-			config &= ~NHMEX_W_PMON_GLOBAL_FIXED_EN;
-		wrmsrl(msr, config);
-	}
-}
-
-static void nhmex_uncore_msr_enable_box(struct intel_uncore_box *box)
-{
-	unsigned msr = uncore_msr_box_ctl(box);
-	u64 config;
-
-	if (msr) {
-		rdmsrl(msr, config);
-		config |= (1ULL << uncore_num_counters(box)) - 1;
-		/* WBox has a fixed counter */
-		if (uncore_msr_fixed_ctl(box))
-			config |= NHMEX_W_PMON_GLOBAL_FIXED_EN;
-		wrmsrl(msr, config);
-	}
-}
-
-static void nhmex_uncore_msr_disable_event(struct intel_uncore_box *box, struct perf_event *event)
-{
-	wrmsrl(event->hw.config_base, 0);
-}
-
-static void nhmex_uncore_msr_enable_event(struct intel_uncore_box *box, struct perf_event *event)
-{
-	struct hw_perf_event *hwc = &event->hw;
-
-	if (hwc->idx >= UNCORE_PMC_IDX_FIXED)
-		wrmsrl(hwc->config_base, NHMEX_PMON_CTL_EN_BIT0);
-	else if (box->pmu->type->event_mask & NHMEX_PMON_CTL_EN_BIT0)
-		wrmsrl(hwc->config_base, hwc->config | NHMEX_PMON_CTL_EN_BIT22);
-	else
-		wrmsrl(hwc->config_base, hwc->config | NHMEX_PMON_CTL_EN_BIT0);
-}
-
-#define NHMEX_UNCORE_OPS_COMMON_INIT()				\
-	.init_box	= nhmex_uncore_msr_init_box,		\
-	.disable_box	= nhmex_uncore_msr_disable_box,		\
-	.enable_box	= nhmex_uncore_msr_enable_box,		\
-	.disable_event	= nhmex_uncore_msr_disable_event,	\
-	.read_counter	= uncore_msr_read_counter
-
-static struct intel_uncore_ops nhmex_uncore_ops = {
-	NHMEX_UNCORE_OPS_COMMON_INIT(),
-	.enable_event	= nhmex_uncore_msr_enable_event,
-};
-
-static struct attribute *nhmex_uncore_ubox_formats_attr[] = {
-	&format_attr_event.attr,
-	&format_attr_edge.attr,
-	NULL,
-};
-
-static struct attribute_group nhmex_uncore_ubox_format_group = {
-	.name		= "format",
-	.attrs		= nhmex_uncore_ubox_formats_attr,
-};
-
-static struct intel_uncore_type nhmex_uncore_ubox = {
-	.name		= "ubox",
-	.num_counters	= 1,
-	.num_boxes	= 1,
-	.perf_ctr_bits	= 48,
-	.event_ctl	= NHMEX_U_MSR_PMON_EV_SEL,
-	.perf_ctr	= NHMEX_U_MSR_PMON_CTR,
-	.event_mask	= NHMEX_U_PMON_RAW_EVENT_MASK,
-	.box_ctl	= NHMEX_U_MSR_PMON_GLOBAL_CTL,
-	.ops		= &nhmex_uncore_ops,
-	.format_group	= &nhmex_uncore_ubox_format_group
-};
-
-static struct attribute *nhmex_uncore_cbox_formats_attr[] = {
-	&format_attr_event.attr,
-	&format_attr_umask.attr,
-	&format_attr_edge.attr,
-	&format_attr_inv.attr,
-	&format_attr_thresh8.attr,
-	NULL,
-};
-
-static struct attribute_group nhmex_uncore_cbox_format_group = {
-	.name = "format",
-	.attrs = nhmex_uncore_cbox_formats_attr,
-};
-
-/* msr offset for each instance of cbox */
-static unsigned nhmex_cbox_msr_offsets[] = {
-	0x0, 0x80, 0x40, 0xc0, 0x20, 0xa0, 0x60, 0xe0, 0x240, 0x2c0,
-};
-
-static struct intel_uncore_type nhmex_uncore_cbox = {
-	.name			= "cbox",
-	.num_counters		= 6,
-	.num_boxes		= 10,
-	.perf_ctr_bits		= 48,
-	.event_ctl		= NHMEX_C0_MSR_PMON_EV_SEL0,
-	.perf_ctr		= NHMEX_C0_MSR_PMON_CTR0,
-	.event_mask		= NHMEX_PMON_RAW_EVENT_MASK,
-	.box_ctl		= NHMEX_C0_MSR_PMON_GLOBAL_CTL,
-	.msr_offsets		= nhmex_cbox_msr_offsets,
-	.pair_ctr_ctl		= 1,
-	.ops			= &nhmex_uncore_ops,
-	.format_group		= &nhmex_uncore_cbox_format_group
-};
-
-static struct uncore_event_desc nhmex_uncore_wbox_events[] = {
-	INTEL_UNCORE_EVENT_DESC(clockticks, "event=0xff,umask=0"),
-	{ /* end: all zeroes */ },
-};
-
-static struct intel_uncore_type nhmex_uncore_wbox = {
-	.name			= "wbox",
-	.num_counters		= 4,
-	.num_boxes		= 1,
-	.perf_ctr_bits		= 48,
-	.event_ctl		= NHMEX_W_MSR_PMON_CNT0,
-	.perf_ctr		= NHMEX_W_MSR_PMON_EVT_SEL0,
-	.fixed_ctr		= NHMEX_W_MSR_PMON_FIXED_CTR,
-	.fixed_ctl		= NHMEX_W_MSR_PMON_FIXED_CTL,
-	.event_mask		= NHMEX_PMON_RAW_EVENT_MASK,
-	.box_ctl		= NHMEX_W_MSR_GLOBAL_CTL,
-	.pair_ctr_ctl		= 1,
-	.event_descs		= nhmex_uncore_wbox_events,
-	.ops			= &nhmex_uncore_ops,
-	.format_group		= &nhmex_uncore_cbox_format_group
-};
-
-static int nhmex_bbox_hw_config(struct intel_uncore_box *box, struct perf_event *event)
-{
-	struct hw_perf_event *hwc = &event->hw;
-	struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
-	struct hw_perf_event_extra *reg2 = &hwc->branch_reg;
-	int ctr, ev_sel;
-
-	ctr = (hwc->config & NHMEX_B_PMON_CTR_MASK) >>
-		NHMEX_B_PMON_CTR_SHIFT;
-	ev_sel = (hwc->config & NHMEX_B_PMON_CTL_EV_SEL_MASK) >>
-		  NHMEX_B_PMON_CTL_EV_SEL_SHIFT;
-
-	/* events that do not use the match/mask registers */
-	if ((ctr == 0 && ev_sel > 0x3) || (ctr == 1 && ev_sel > 0x6) ||
-	    (ctr == 2 && ev_sel != 0x4) || ctr == 3)
-		return 0;
-
-	if (box->pmu->pmu_idx == 0)
-		reg1->reg = NHMEX_B0_MSR_MATCH;
-	else
-		reg1->reg = NHMEX_B1_MSR_MATCH;
-	reg1->idx = 0;
-	reg1->config = event->attr.config1;
-	reg2->config = event->attr.config2;
-	return 0;
-}
-
-static void nhmex_bbox_msr_enable_event(struct intel_uncore_box *box, struct perf_event *event)
-{
-	struct hw_perf_event *hwc = &event->hw;
-	struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
-	struct hw_perf_event_extra *reg2 = &hwc->branch_reg;
-
-	if (reg1->idx != EXTRA_REG_NONE) {
-		wrmsrl(reg1->reg, reg1->config);
-		wrmsrl(reg1->reg + 1, reg2->config);
-	}
-	wrmsrl(hwc->config_base, NHMEX_PMON_CTL_EN_BIT0 |
-		(hwc->config & NHMEX_B_PMON_CTL_EV_SEL_MASK));
-}
-
-/*
- * The Bbox has 4 counters, but each counter monitors different events.
- * Use bits 6-7 in the event config to select counter.
- */
-static struct event_constraint nhmex_uncore_bbox_constraints[] = {
-	EVENT_CONSTRAINT(0 , 1, 0xc0),
-	EVENT_CONSTRAINT(0x40, 2, 0xc0),
-	EVENT_CONSTRAINT(0x80, 4, 0xc0),
-	EVENT_CONSTRAINT(0xc0, 8, 0xc0),
-	EVENT_CONSTRAINT_END,
-};
-
-static struct attribute *nhmex_uncore_bbox_formats_attr[] = {
-	&format_attr_event5.attr,
-	&format_attr_counter.attr,
-	&format_attr_match.attr,
-	&format_attr_mask.attr,
-	NULL,
-};
-
-static struct attribute_group nhmex_uncore_bbox_format_group = {
-	.name = "format",
-	.attrs = nhmex_uncore_bbox_formats_attr,
-};
-
-static struct intel_uncore_ops nhmex_uncore_bbox_ops = {
-	NHMEX_UNCORE_OPS_COMMON_INIT(),
-	.enable_event		= nhmex_bbox_msr_enable_event,
-	.hw_config		= nhmex_bbox_hw_config,
-	.get_constraint		= uncore_get_constraint,
-	.put_constraint		= uncore_put_constraint,
-};
-
-static struct intel_uncore_type nhmex_uncore_bbox = {
-	.name			= "bbox",
-	.num_counters		= 4,
-	.num_boxes		= 2,
-	.perf_ctr_bits		= 48,
-	.event_ctl		= NHMEX_B0_MSR_PMON_CTL0,
-	.perf_ctr		= NHMEX_B0_MSR_PMON_CTR0,
-	.event_mask		= NHMEX_B_PMON_RAW_EVENT_MASK,
-	.box_ctl		= NHMEX_B0_MSR_PMON_GLOBAL_CTL,
-	.msr_offset		= NHMEX_B_MSR_OFFSET,
-	.pair_ctr_ctl		= 1,
-	.num_shared_regs	= 1,
-	.constraints		= nhmex_uncore_bbox_constraints,
-	.ops			= &nhmex_uncore_bbox_ops,
-	.format_group		= &nhmex_uncore_bbox_format_group
-};
-
-static int nhmex_sbox_hw_config(struct intel_uncore_box *box, struct perf_event *event)
-{
-	struct hw_perf_event *hwc = &event->hw;
-	struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
-	struct hw_perf_event_extra *reg2 = &hwc->branch_reg;
-
-	/* only TO_R_PROG_EV event uses the match/mask register */
-	if ((hwc->config & NHMEX_PMON_CTL_EV_SEL_MASK) !=
-	    NHMEX_S_EVENT_TO_R_PROG_EV)
-		return 0;
-
-	if (box->pmu->pmu_idx == 0)
-		reg1->reg = NHMEX_S0_MSR_MM_CFG;
-	else
-		reg1->reg = NHMEX_S1_MSR_MM_CFG;
-	reg1->idx = 0;
-	reg1->config = event->attr.config1;
-	reg2->config = event->attr.config2;
-	return 0;
-}
-
-static void nhmex_sbox_msr_enable_event(struct intel_uncore_box *box, struct perf_event *event)
-{
-	struct hw_perf_event *hwc = &event->hw;
-	struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
-	struct hw_perf_event_extra *reg2 = &hwc->branch_reg;
-
-	if (reg1->idx != EXTRA_REG_NONE) {
-		wrmsrl(reg1->reg, 0);
-		wrmsrl(reg1->reg + 1, reg1->config);
-		wrmsrl(reg1->reg + 2, reg2->config);
-		wrmsrl(reg1->reg, NHMEX_S_PMON_MM_CFG_EN);
-	}
-	wrmsrl(hwc->config_base, hwc->config | NHMEX_PMON_CTL_EN_BIT22);
-}
-
-static struct attribute *nhmex_uncore_sbox_formats_attr[] = {
-	&format_attr_event.attr,
-	&format_attr_umask.attr,
-	&format_attr_edge.attr,
-	&format_attr_inv.attr,
-	&format_attr_thresh8.attr,
-	&format_attr_match.attr,
-	&format_attr_mask.attr,
-	NULL,
-};
-
-static struct attribute_group nhmex_uncore_sbox_format_group = {
-	.name			= "format",
-	.attrs			= nhmex_uncore_sbox_formats_attr,
-};
-
-static struct intel_uncore_ops nhmex_uncore_sbox_ops = {
-	NHMEX_UNCORE_OPS_COMMON_INIT(),
-	.enable_event		= nhmex_sbox_msr_enable_event,
-	.hw_config		= nhmex_sbox_hw_config,
-	.get_constraint		= uncore_get_constraint,
-	.put_constraint		= uncore_put_constraint,
-};
-
-static struct intel_uncore_type nhmex_uncore_sbox = {
-	.name			= "sbox",
-	.num_counters		= 4,
-	.num_boxes		= 2,
-	.perf_ctr_bits		= 48,
-	.event_ctl		= NHMEX_S0_MSR_PMON_CTL0,
-	.perf_ctr		= NHMEX_S0_MSR_PMON_CTR0,
-	.event_mask		= NHMEX_PMON_RAW_EVENT_MASK,
-	.box_ctl		= NHMEX_S0_MSR_PMON_GLOBAL_CTL,
-	.msr_offset		= NHMEX_S_MSR_OFFSET,
-	.pair_ctr_ctl		= 1,
-	.num_shared_regs	= 1,
-	.ops			= &nhmex_uncore_sbox_ops,
-	.format_group		= &nhmex_uncore_sbox_format_group
-};
-
-enum {
-	EXTRA_REG_NHMEX_M_FILTER,
-	EXTRA_REG_NHMEX_M_DSP,
-	EXTRA_REG_NHMEX_M_ISS,
-	EXTRA_REG_NHMEX_M_MAP,
-	EXTRA_REG_NHMEX_M_MSC_THR,
-	EXTRA_REG_NHMEX_M_PGT,
-	EXTRA_REG_NHMEX_M_PLD,
-	EXTRA_REG_NHMEX_M_ZDP_CTL_FVC,
-};
-
-static struct extra_reg nhmex_uncore_mbox_extra_regs[] = {
-	MBOX_INC_SEL_EXTAR_REG(0x0, DSP),
-	MBOX_INC_SEL_EXTAR_REG(0x4, MSC_THR),
-	MBOX_INC_SEL_EXTAR_REG(0x5, MSC_THR),
-	MBOX_INC_SEL_EXTAR_REG(0x9, ISS),
-	/* event 0xa uses two extra registers */
-	MBOX_INC_SEL_EXTAR_REG(0xa, ISS),
-	MBOX_INC_SEL_EXTAR_REG(0xa, PLD),
-	MBOX_INC_SEL_EXTAR_REG(0xb, PLD),
-	/* events 0xd ~ 0x10 use the same extra register */
-	MBOX_INC_SEL_EXTAR_REG(0xd, ZDP_CTL_FVC),
-	MBOX_INC_SEL_EXTAR_REG(0xe, ZDP_CTL_FVC),
-	MBOX_INC_SEL_EXTAR_REG(0xf, ZDP_CTL_FVC),
-	MBOX_INC_SEL_EXTAR_REG(0x10, ZDP_CTL_FVC),
-	MBOX_INC_SEL_EXTAR_REG(0x16, PGT),
-	MBOX_SET_FLAG_SEL_EXTRA_REG(0x0, DSP),
-	MBOX_SET_FLAG_SEL_EXTRA_REG(0x1, ISS),
-	MBOX_SET_FLAG_SEL_EXTRA_REG(0x5, PGT),
-	MBOX_SET_FLAG_SEL_EXTRA_REG(0x6, MAP),
-	EVENT_EXTRA_END
-};
-
-/* Nehalem-EX or Westmere-EX ? */
-static bool uncore_nhmex;
-
-static bool nhmex_mbox_get_shared_reg(struct intel_uncore_box *box, int idx, u64 config)
-{
-	struct intel_uncore_extra_reg *er;
-	unsigned long flags;
-	bool ret = false;
-	u64 mask;
-
-	if (idx < EXTRA_REG_NHMEX_M_ZDP_CTL_FVC) {
-		er = &box->shared_regs[idx];
-		raw_spin_lock_irqsave(&er->lock, flags);
-		if (!atomic_read(&er->ref) || er->config == config) {
-			atomic_inc(&er->ref);
-			er->config = config;
-			ret = true;
-		}
-		raw_spin_unlock_irqrestore(&er->lock, flags);
-
-		return ret;
-	}
-	/*
-	 * The ZDP_CTL_FVC MSR has 4 fields which are used to control
-	 * events 0xd ~ 0x10. Besides these 4 fields, there are additional
-	 * fields which are shared.
-	 */
-	idx -= EXTRA_REG_NHMEX_M_ZDP_CTL_FVC;
-	if (WARN_ON_ONCE(idx >= 4))
-		return false;
-
-	/* mask of the shared fields */
-	if (uncore_nhmex)
-		mask = NHMEX_M_PMON_ZDP_CTL_FVC_MASK;
-	else
-		mask = WSMEX_M_PMON_ZDP_CTL_FVC_MASK;
-	er = &box->shared_regs[EXTRA_REG_NHMEX_M_ZDP_CTL_FVC];
-
-	raw_spin_lock_irqsave(&er->lock, flags);
-	/* add mask of the non-shared field if it's in use */
-	if (__BITS_VALUE(atomic_read(&er->ref), idx, 8)) {
-		if (uncore_nhmex)
-			mask |= NHMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(idx);
-		else
-			mask |= WSMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(idx);
-	}
-
-	if (!atomic_read(&er->ref) || !((er->config ^ config) & mask)) {
-		atomic_add(1 << (idx * 8), &er->ref);
-		if (uncore_nhmex)
-			mask = NHMEX_M_PMON_ZDP_CTL_FVC_MASK |
-				NHMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(idx);
-		else
-			mask = WSMEX_M_PMON_ZDP_CTL_FVC_MASK |
-				WSMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(idx);
-		er->config &= ~mask;
-		er->config |= (config & mask);
-		ret = true;
-	}
-	raw_spin_unlock_irqrestore(&er->lock, flags);
-
-	return ret;
-}
-
-static void nhmex_mbox_put_shared_reg(struct intel_uncore_box *box, int idx)
-{
-	struct intel_uncore_extra_reg *er;
-
-	if (idx < EXTRA_REG_NHMEX_M_ZDP_CTL_FVC) {
-		er = &box->shared_regs[idx];
-		atomic_dec(&er->ref);
-		return;
-	}
-
-	idx -= EXTRA_REG_NHMEX_M_ZDP_CTL_FVC;
-	er = &box->shared_regs[EXTRA_REG_NHMEX_M_ZDP_CTL_FVC];
-	atomic_sub(1 << (idx * 8), &er->ref);
-}
-
-static u64 nhmex_mbox_alter_er(struct perf_event *event, int new_idx, bool modify)
-{
-	struct hw_perf_event *hwc = &event->hw;
-	struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
-	u64 idx, orig_idx = __BITS_VALUE(reg1->idx, 0, 8);
-	u64 config = reg1->config;
-
-	/* get the non-shared control bits and shift them */
-	idx = orig_idx - EXTRA_REG_NHMEX_M_ZDP_CTL_FVC;
-	if (uncore_nhmex)
-		config &= NHMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(idx);
-	else
-		config &= WSMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(idx);
-	if (new_idx > orig_idx) {
-		idx = new_idx - orig_idx;
-		config <<= 3 * idx;
-	} else {
-		idx = orig_idx - new_idx;
-		config >>= 3 * idx;
-	}
-
-	/* add the shared control bits back */
-	if (uncore_nhmex)
-		config |= NHMEX_M_PMON_ZDP_CTL_FVC_MASK & reg1->config;
-	else
-		config |= WSMEX_M_PMON_ZDP_CTL_FVC_MASK & reg1->config;
-	config |= NHMEX_M_PMON_ZDP_CTL_FVC_MASK & reg1->config;
-	if (modify) {
-		/* adjust the main event selector */
-		if (new_idx > orig_idx)
-			hwc->config += idx << NHMEX_M_PMON_CTL_INC_SEL_SHIFT;
-		else
-			hwc->config -= idx << NHMEX_M_PMON_CTL_INC_SEL_SHIFT;
-		reg1->config = config;
-		reg1->idx = ~0xff | new_idx;
-	}
-	return config;
-}
-
-static struct event_constraint *
-nhmex_mbox_get_constraint(struct intel_uncore_box *box, struct perf_event *event)
-{
-	struct hw_perf_event_extra *reg1 = &event->hw.extra_reg;
-	struct hw_perf_event_extra *reg2 = &event->hw.branch_reg;
-	int i, idx[2], alloc = 0;
-	u64 config1 = reg1->config;
-
-	idx[0] = __BITS_VALUE(reg1->idx, 0, 8);
-	idx[1] = __BITS_VALUE(reg1->idx, 1, 8);
-again:
-	for (i = 0; i < 2; i++) {
-		if (!uncore_box_is_fake(box) && (reg1->alloc & (0x1 << i)))
-			idx[i] = 0xff;
-
-		if (idx[i] == 0xff)
-			continue;
-
-		if (!nhmex_mbox_get_shared_reg(box, idx[i],
-				__BITS_VALUE(config1, i, 32)))
-			goto fail;
-		alloc |= (0x1 << i);
-	}
-
-	/* for the match/mask registers */
-	if (reg2->idx != EXTRA_REG_NONE &&
-	    (uncore_box_is_fake(box) || !reg2->alloc) &&
-	    !nhmex_mbox_get_shared_reg(box, reg2->idx, reg2->config))
-		goto fail;
-
-	/*
-	 * If it's a fake box -- as per validate_{group,event}() we
-	 * shouldn't touch event state and we can avoid doing so
-	 * since both will only call get_event_constraints() once
-	 * on each event, this avoids the need for reg->alloc.
-	 */
-	if (!uncore_box_is_fake(box)) {
-		if (idx[0] != 0xff && idx[0] != __BITS_VALUE(reg1->idx, 0, 8))
-			nhmex_mbox_alter_er(event, idx[0], true);
-		reg1->alloc |= alloc;
-		if (reg2->idx != EXTRA_REG_NONE)
-			reg2->alloc = 1;
-	}
-	return NULL;
-fail:
-	if (idx[0] != 0xff && !(alloc & 0x1) &&
-	    idx[0] >= EXTRA_REG_NHMEX_M_ZDP_CTL_FVC) {
-		/*
-		 * events 0xd ~ 0x10 are functional identical, but are
-		 * controlled by different fields in the ZDP_CTL_FVC
-		 * register. If we failed to take one field, try the
-		 * rest 3 choices.
-		 */
-		BUG_ON(__BITS_VALUE(reg1->idx, 1, 8) != 0xff);
-		idx[0] -= EXTRA_REG_NHMEX_M_ZDP_CTL_FVC;
-		idx[0] = (idx[0] + 1) % 4;
-		idx[0] += EXTRA_REG_NHMEX_M_ZDP_CTL_FVC;
-		if (idx[0] != __BITS_VALUE(reg1->idx, 0, 8)) {
-			config1 = nhmex_mbox_alter_er(event, idx[0], false);
-			goto again;
-		}
-	}
-
-	if (alloc & 0x1)
-		nhmex_mbox_put_shared_reg(box, idx[0]);
-	if (alloc & 0x2)
-		nhmex_mbox_put_shared_reg(box, idx[1]);
-	return &constraint_empty;
-}
-
-static void nhmex_mbox_put_constraint(struct intel_uncore_box *box, struct perf_event *event)
-{
-	struct hw_perf_event_extra *reg1 = &event->hw.extra_reg;
-	struct hw_perf_event_extra *reg2 = &event->hw.branch_reg;
-
-	if (uncore_box_is_fake(box))
-		return;
-
-	if (reg1->alloc & 0x1)
-		nhmex_mbox_put_shared_reg(box, __BITS_VALUE(reg1->idx, 0, 8));
-	if (reg1->alloc & 0x2)
-		nhmex_mbox_put_shared_reg(box, __BITS_VALUE(reg1->idx, 1, 8));
-	reg1->alloc = 0;
-
-	if (reg2->alloc) {
-		nhmex_mbox_put_shared_reg(box, reg2->idx);
-		reg2->alloc = 0;
-	}
-}
-
-static int nhmex_mbox_extra_reg_idx(struct extra_reg *er)
-{
-	if (er->idx < EXTRA_REG_NHMEX_M_ZDP_CTL_FVC)
-		return er->idx;
-	return er->idx + (er->event >> NHMEX_M_PMON_CTL_INC_SEL_SHIFT) - 0xd;
-}
-
-static int nhmex_mbox_hw_config(struct intel_uncore_box *box, struct perf_event *event)
-{
-	struct intel_uncore_type *type = box->pmu->type;
-	struct hw_perf_event_extra *reg1 = &event->hw.extra_reg;
-	struct hw_perf_event_extra *reg2 = &event->hw.branch_reg;
-	struct extra_reg *er;
-	unsigned msr;
-	int reg_idx = 0;
-	/*
-	 * The mbox events may require 2 extra MSRs at the most. But only
-	 * the lower 32 bits in these MSRs are significant, so we can use
-	 * config1 to pass two MSRs' config.
-	 */
-	for (er = nhmex_uncore_mbox_extra_regs; er->msr; er++) {
-		if (er->event != (event->hw.config & er->config_mask))
-			continue;
-		if (event->attr.config1 & ~er->valid_mask)
-			return -EINVAL;
-
-		msr = er->msr + type->msr_offset * box->pmu->pmu_idx;
-		if (WARN_ON_ONCE(msr >= 0xffff || er->idx >= 0xff))
-			return -EINVAL;
-
-		/* always use the 32~63 bits to pass the PLD config */
-		if (er->idx == EXTRA_REG_NHMEX_M_PLD)
-			reg_idx = 1;
-		else if (WARN_ON_ONCE(reg_idx > 0))
-			return -EINVAL;
-
-		reg1->idx &= ~(0xff << (reg_idx * 8));
-		reg1->reg &= ~(0xffff << (reg_idx * 16));
-		reg1->idx |= nhmex_mbox_extra_reg_idx(er) << (reg_idx * 8);
-		reg1->reg |= msr << (reg_idx * 16);
-		reg1->config = event->attr.config1;
-		reg_idx++;
-	}
-	/*
-	 * The mbox only provides ability to perform address matching
-	 * for the PLD events.
-	 */
-	if (reg_idx == 2) {
-		reg2->idx = EXTRA_REG_NHMEX_M_FILTER;
-		if (event->attr.config2 & NHMEX_M_PMON_MM_CFG_EN)
-			reg2->config = event->attr.config2;
-		else
-			reg2->config = ~0ULL;
-		if (box->pmu->pmu_idx == 0)
-			reg2->reg = NHMEX_M0_MSR_PMU_MM_CFG;
-		else
-			reg2->reg = NHMEX_M1_MSR_PMU_MM_CFG;
-	}
-	return 0;
-}
-
-static u64 nhmex_mbox_shared_reg_config(struct intel_uncore_box *box, int idx)
-{
-	struct intel_uncore_extra_reg *er;
-	unsigned long flags;
-	u64 config;
-
-	if (idx < EXTRA_REG_NHMEX_M_ZDP_CTL_FVC)
-		return box->shared_regs[idx].config;
-
-	er = &box->shared_regs[EXTRA_REG_NHMEX_M_ZDP_CTL_FVC];
-	raw_spin_lock_irqsave(&er->lock, flags);
-	config = er->config;
-	raw_spin_unlock_irqrestore(&er->lock, flags);
-	return config;
-}
-
-static void nhmex_mbox_msr_enable_event(struct intel_uncore_box *box, struct perf_event *event)
-{
-	struct hw_perf_event *hwc = &event->hw;
-	struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
-	struct hw_perf_event_extra *reg2 = &hwc->branch_reg;
-	int idx;
-
-	idx = __BITS_VALUE(reg1->idx, 0, 8);
-	if (idx != 0xff)
-		wrmsrl(__BITS_VALUE(reg1->reg, 0, 16),
-			nhmex_mbox_shared_reg_config(box, idx));
-	idx = __BITS_VALUE(reg1->idx, 1, 8);
-	if (idx != 0xff)
-		wrmsrl(__BITS_VALUE(reg1->reg, 1, 16),
-			nhmex_mbox_shared_reg_config(box, idx));
-
-	if (reg2->idx != EXTRA_REG_NONE) {
-		wrmsrl(reg2->reg, 0);
-		if (reg2->config != ~0ULL) {
-			wrmsrl(reg2->reg + 1,
-				reg2->config & NHMEX_M_PMON_ADDR_MATCH_MASK);
-			wrmsrl(reg2->reg + 2, NHMEX_M_PMON_ADDR_MASK_MASK &
-				(reg2->config >> NHMEX_M_PMON_ADDR_MASK_SHIFT));
-			wrmsrl(reg2->reg, NHMEX_M_PMON_MM_CFG_EN);
-		}
-	}
-
-	wrmsrl(hwc->config_base, hwc->config | NHMEX_PMON_CTL_EN_BIT0);
-}
-
-DEFINE_UNCORE_FORMAT_ATTR(count_mode,		count_mode,	"config:2-3");
-DEFINE_UNCORE_FORMAT_ATTR(storage_mode,		storage_mode,	"config:4-5");
-DEFINE_UNCORE_FORMAT_ATTR(wrap_mode,		wrap_mode,	"config:6");
-DEFINE_UNCORE_FORMAT_ATTR(flag_mode,		flag_mode,	"config:7");
-DEFINE_UNCORE_FORMAT_ATTR(inc_sel,		inc_sel,	"config:9-13");
-DEFINE_UNCORE_FORMAT_ATTR(set_flag_sel,		set_flag_sel,	"config:19-21");
-DEFINE_UNCORE_FORMAT_ATTR(filter_cfg_en,	filter_cfg_en,	"config2:63");
-DEFINE_UNCORE_FORMAT_ATTR(filter_match,		filter_match,	"config2:0-33");
-DEFINE_UNCORE_FORMAT_ATTR(filter_mask,		filter_mask,	"config2:34-61");
-DEFINE_UNCORE_FORMAT_ATTR(dsp,			dsp,		"config1:0-31");
-DEFINE_UNCORE_FORMAT_ATTR(thr,			thr,		"config1:0-31");
-DEFINE_UNCORE_FORMAT_ATTR(fvc,			fvc,		"config1:0-31");
-DEFINE_UNCORE_FORMAT_ATTR(pgt,			pgt,		"config1:0-31");
-DEFINE_UNCORE_FORMAT_ATTR(map,			map,		"config1:0-31");
-DEFINE_UNCORE_FORMAT_ATTR(iss,			iss,		"config1:0-31");
-DEFINE_UNCORE_FORMAT_ATTR(pld,			pld,		"config1:32-63");
-
-static struct attribute *nhmex_uncore_mbox_formats_attr[] = {
-	&format_attr_count_mode.attr,
-	&format_attr_storage_mode.attr,
-	&format_attr_wrap_mode.attr,
-	&format_attr_flag_mode.attr,
-	&format_attr_inc_sel.attr,
-	&format_attr_set_flag_sel.attr,
-	&format_attr_filter_cfg_en.attr,
-	&format_attr_filter_match.attr,
-	&format_attr_filter_mask.attr,
-	&format_attr_dsp.attr,
-	&format_attr_thr.attr,
-	&format_attr_fvc.attr,
-	&format_attr_pgt.attr,
-	&format_attr_map.attr,
-	&format_attr_iss.attr,
-	&format_attr_pld.attr,
-	NULL,
-};
-
-static struct attribute_group nhmex_uncore_mbox_format_group = {
-	.name		= "format",
-	.attrs		= nhmex_uncore_mbox_formats_attr,
-};
-
-static struct uncore_event_desc nhmex_uncore_mbox_events[] = {
-	INTEL_UNCORE_EVENT_DESC(bbox_cmds_read, "inc_sel=0xd,fvc=0x2800"),
-	INTEL_UNCORE_EVENT_DESC(bbox_cmds_write, "inc_sel=0xd,fvc=0x2820"),
-	{ /* end: all zeroes */ },
-};
-
-static struct uncore_event_desc wsmex_uncore_mbox_events[] = {
-	INTEL_UNCORE_EVENT_DESC(bbox_cmds_read, "inc_sel=0xd,fvc=0x5000"),
-	INTEL_UNCORE_EVENT_DESC(bbox_cmds_write, "inc_sel=0xd,fvc=0x5040"),
-	{ /* end: all zeroes */ },
-};
-
-static struct intel_uncore_ops nhmex_uncore_mbox_ops = {
-	NHMEX_UNCORE_OPS_COMMON_INIT(),
-	.enable_event	= nhmex_mbox_msr_enable_event,
-	.hw_config	= nhmex_mbox_hw_config,
-	.get_constraint	= nhmex_mbox_get_constraint,
-	.put_constraint	= nhmex_mbox_put_constraint,
-};
-
-static struct intel_uncore_type nhmex_uncore_mbox = {
-	.name			= "mbox",
-	.num_counters		= 6,
-	.num_boxes		= 2,
-	.perf_ctr_bits		= 48,
-	.event_ctl		= NHMEX_M0_MSR_PMU_CTL0,
-	.perf_ctr		= NHMEX_M0_MSR_PMU_CNT0,
-	.event_mask		= NHMEX_M_PMON_RAW_EVENT_MASK,
-	.box_ctl		= NHMEX_M0_MSR_GLOBAL_CTL,
-	.msr_offset		= NHMEX_M_MSR_OFFSET,
-	.pair_ctr_ctl		= 1,
-	.num_shared_regs	= 8,
-	.event_descs		= nhmex_uncore_mbox_events,
-	.ops			= &nhmex_uncore_mbox_ops,
-	.format_group		= &nhmex_uncore_mbox_format_group,
-};
-
-static void nhmex_rbox_alter_er(struct intel_uncore_box *box, struct perf_event *event)
-{
-	struct hw_perf_event *hwc = &event->hw;
-	struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
-
-	/* adjust the main event selector and extra register index */
-	if (reg1->idx % 2) {
-		reg1->idx--;
-		hwc->config -= 1 << NHMEX_R_PMON_CTL_EV_SEL_SHIFT;
-	} else {
-		reg1->idx++;
-		hwc->config += 1 << NHMEX_R_PMON_CTL_EV_SEL_SHIFT;
-	}
-
-	/* adjust extra register config */
-	switch (reg1->idx % 6) {
-	case 2:
-		/* shift the 8~15 bits to the 0~7 bits */
-		reg1->config >>= 8;
-		break;
-	case 3:
-		/* shift the 0~7 bits to the 8~15 bits */
-		reg1->config <<= 8;
-		break;
-	};
-}
-
-/*
- * Each rbox has 4 event set which monitor PQI port 0~3 or 4~7.
- * An event set consists of 6 events, the 3rd and 4th events in
- * an event set use the same extra register. So an event set uses
- * 5 extra registers.
- */
-static struct event_constraint *
-nhmex_rbox_get_constraint(struct intel_uncore_box *box, struct perf_event *event)
-{
-	struct hw_perf_event *hwc = &event->hw;
-	struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
-	struct hw_perf_event_extra *reg2 = &hwc->branch_reg;
-	struct intel_uncore_extra_reg *er;
-	unsigned long flags;
-	int idx, er_idx;
-	u64 config1;
-	bool ok = false;
-
-	if (!uncore_box_is_fake(box) && reg1->alloc)
-		return NULL;
-
-	idx = reg1->idx % 6;
-	config1 = reg1->config;
-again:
-	er_idx = idx;
-	/* the 3rd and 4th events use the same extra register */
-	if (er_idx > 2)
-		er_idx--;
-	er_idx += (reg1->idx / 6) * 5;
-
-	er = &box->shared_regs[er_idx];
-	raw_spin_lock_irqsave(&er->lock, flags);
-	if (idx < 2) {
-		if (!atomic_read(&er->ref) || er->config == reg1->config) {
-			atomic_inc(&er->ref);
-			er->config = reg1->config;
-			ok = true;
-		}
-	} else if (idx == 2 || idx == 3) {
-		/*
-		 * these two events use different fields in a extra register,
-		 * the 0~7 bits and the 8~15 bits respectively.
-		 */
-		u64 mask = 0xff << ((idx - 2) * 8);
-		if (!__BITS_VALUE(atomic_read(&er->ref), idx - 2, 8) ||
-				!((er->config ^ config1) & mask)) {
-			atomic_add(1 << ((idx - 2) * 8), &er->ref);
-			er->config &= ~mask;
-			er->config |= config1 & mask;
-			ok = true;
-		}
-	} else {
-		if (!atomic_read(&er->ref) ||
-				(er->config == (hwc->config >> 32) &&
-				 er->config1 == reg1->config &&
-				 er->config2 == reg2->config)) {
-			atomic_inc(&er->ref);
-			er->config = (hwc->config >> 32);
-			er->config1 = reg1->config;
-			er->config2 = reg2->config;
-			ok = true;
-		}
-	}
-	raw_spin_unlock_irqrestore(&er->lock, flags);
-
-	if (!ok) {
-		/*
-		 * The Rbox events are always in pairs. The paired
-		 * events are functional identical, but use different
-		 * extra registers. If we failed to take an extra
-		 * register, try the alternative.
-		 */
-		idx ^= 1;
-		if (idx != reg1->idx % 6) {
-			if (idx == 2)
-				config1 >>= 8;
-			else if (idx == 3)
-				config1 <<= 8;
-			goto again;
-		}
-	} else {
-		if (!uncore_box_is_fake(box)) {
-			if (idx != reg1->idx % 6)
-				nhmex_rbox_alter_er(box, event);
-			reg1->alloc = 1;
-		}
-		return NULL;
-	}
-	return &constraint_empty;
-}
-
-static void nhmex_rbox_put_constraint(struct intel_uncore_box *box, struct perf_event *event)
-{
-	struct intel_uncore_extra_reg *er;
-	struct hw_perf_event_extra *reg1 = &event->hw.extra_reg;
-	int idx, er_idx;
-
-	if (uncore_box_is_fake(box) || !reg1->alloc)
-		return;
-
-	idx = reg1->idx % 6;
-	er_idx = idx;
-	if (er_idx > 2)
-		er_idx--;
-	er_idx += (reg1->idx / 6) * 5;
-
-	er = &box->shared_regs[er_idx];
-	if (idx == 2 || idx == 3)
-		atomic_sub(1 << ((idx - 2) * 8), &er->ref);
-	else
-		atomic_dec(&er->ref);
-
-	reg1->alloc = 0;
-}
-
-static int nhmex_rbox_hw_config(struct intel_uncore_box *box, struct perf_event *event)
-{
-	struct hw_perf_event *hwc = &event->hw;
-	struct hw_perf_event_extra *reg1 = &event->hw.extra_reg;
-	struct hw_perf_event_extra *reg2 = &event->hw.branch_reg;
-	int idx;
-
-	idx = (event->hw.config & NHMEX_R_PMON_CTL_EV_SEL_MASK) >>
-		NHMEX_R_PMON_CTL_EV_SEL_SHIFT;
-	if (idx >= 0x18)
-		return -EINVAL;
-
-	reg1->idx = idx;
-	reg1->config = event->attr.config1;
-
-	switch (idx % 6) {
-	case 4:
-	case 5:
-		hwc->config |= event->attr.config & (~0ULL << 32);
-		reg2->config = event->attr.config2;
-		break;
-	};
-	return 0;
-}
-
-static void nhmex_rbox_msr_enable_event(struct intel_uncore_box *box, struct perf_event *event)
-{
-	struct hw_perf_event *hwc = &event->hw;
-	struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
-	struct hw_perf_event_extra *reg2 = &hwc->branch_reg;
-	int idx, port;
-
-	idx = reg1->idx;
-	port = idx / 6 + box->pmu->pmu_idx * 4;
-
-	switch (idx % 6) {
-	case 0:
-		wrmsrl(NHMEX_R_MSR_PORTN_IPERF_CFG0(port), reg1->config);
-		break;
-	case 1:
-		wrmsrl(NHMEX_R_MSR_PORTN_IPERF_CFG1(port), reg1->config);
-		break;
-	case 2:
-	case 3:
-		wrmsrl(NHMEX_R_MSR_PORTN_QLX_CFG(port),
-			uncore_shared_reg_config(box, 2 + (idx / 6) * 5));
-		break;
-	case 4:
-		wrmsrl(NHMEX_R_MSR_PORTN_XBR_SET1_MM_CFG(port),
-			hwc->config >> 32);
-		wrmsrl(NHMEX_R_MSR_PORTN_XBR_SET1_MATCH(port), reg1->config);
-		wrmsrl(NHMEX_R_MSR_PORTN_XBR_SET1_MASK(port), reg2->config);
-		break;
-	case 5:
-		wrmsrl(NHMEX_R_MSR_PORTN_XBR_SET2_MM_CFG(port),
-			hwc->config >> 32);
-		wrmsrl(NHMEX_R_MSR_PORTN_XBR_SET2_MATCH(port), reg1->config);
-		wrmsrl(NHMEX_R_MSR_PORTN_XBR_SET2_MASK(port), reg2->config);
-		break;
-	};
-
-	wrmsrl(hwc->config_base, NHMEX_PMON_CTL_EN_BIT0 |
-		(hwc->config & NHMEX_R_PMON_CTL_EV_SEL_MASK));
-}
-
-DEFINE_UNCORE_FORMAT_ATTR(xbr_mm_cfg, xbr_mm_cfg, "config:32-63");
-DEFINE_UNCORE_FORMAT_ATTR(xbr_match, xbr_match, "config1:0-63");
-DEFINE_UNCORE_FORMAT_ATTR(xbr_mask, xbr_mask, "config2:0-63");
-DEFINE_UNCORE_FORMAT_ATTR(qlx_cfg, qlx_cfg, "config1:0-15");
-DEFINE_UNCORE_FORMAT_ATTR(iperf_cfg, iperf_cfg, "config1:0-31");
-
-static struct attribute *nhmex_uncore_rbox_formats_attr[] = {
-	&format_attr_event5.attr,
-	&format_attr_xbr_mm_cfg.attr,
-	&format_attr_xbr_match.attr,
-	&format_attr_xbr_mask.attr,
-	&format_attr_qlx_cfg.attr,
-	&format_attr_iperf_cfg.attr,
-	NULL,
-};
-
-static struct attribute_group nhmex_uncore_rbox_format_group = {
-	.name = "format",
-	.attrs = nhmex_uncore_rbox_formats_attr,
-};
-
-static struct uncore_event_desc nhmex_uncore_rbox_events[] = {
-	INTEL_UNCORE_EVENT_DESC(qpi0_flit_send,		"event=0x0,iperf_cfg=0x80000000"),
-	INTEL_UNCORE_EVENT_DESC(qpi1_filt_send,		"event=0x6,iperf_cfg=0x80000000"),
-	INTEL_UNCORE_EVENT_DESC(qpi0_idle_filt,		"event=0x0,iperf_cfg=0x40000000"),
-	INTEL_UNCORE_EVENT_DESC(qpi1_idle_filt,		"event=0x6,iperf_cfg=0x40000000"),
-	INTEL_UNCORE_EVENT_DESC(qpi0_date_response,	"event=0x0,iperf_cfg=0xc4"),
-	INTEL_UNCORE_EVENT_DESC(qpi1_date_response,	"event=0x6,iperf_cfg=0xc4"),
-	{ /* end: all zeroes */ },
-};
-
-static struct intel_uncore_ops nhmex_uncore_rbox_ops = {
-	NHMEX_UNCORE_OPS_COMMON_INIT(),
-	.enable_event		= nhmex_rbox_msr_enable_event,
-	.hw_config		= nhmex_rbox_hw_config,
-	.get_constraint		= nhmex_rbox_get_constraint,
-	.put_constraint		= nhmex_rbox_put_constraint,
-};
-
-static struct intel_uncore_type nhmex_uncore_rbox = {
-	.name			= "rbox",
-	.num_counters		= 8,
-	.num_boxes		= 2,
-	.perf_ctr_bits		= 48,
-	.event_ctl		= NHMEX_R_MSR_PMON_CTL0,
-	.perf_ctr		= NHMEX_R_MSR_PMON_CNT0,
-	.event_mask		= NHMEX_R_PMON_RAW_EVENT_MASK,
-	.box_ctl		= NHMEX_R_MSR_GLOBAL_CTL,
-	.msr_offset		= NHMEX_R_MSR_OFFSET,
-	.pair_ctr_ctl		= 1,
-	.num_shared_regs	= 20,
-	.event_descs		= nhmex_uncore_rbox_events,
-	.ops			= &nhmex_uncore_rbox_ops,
-	.format_group		= &nhmex_uncore_rbox_format_group
-};
-
-static struct intel_uncore_type *nhmex_msr_uncores[] = {
-	&nhmex_uncore_ubox,
-	&nhmex_uncore_cbox,
-	&nhmex_uncore_bbox,
-	&nhmex_uncore_sbox,
-	&nhmex_uncore_mbox,
-	&nhmex_uncore_rbox,
-	&nhmex_uncore_wbox,
-	NULL,
-};
-/* end of Nehalem-EX uncore support */
-
 static void uncore_assign_hw_event(struct intel_uncore_box *box, struct perf_event *event, int idx)
 {
 	struct hw_perf_event *hwc = &event->hw;
@@ -3140,7 +166,7 @@ static void uncore_assign_hw_event(struct intel_uncore_box *box, struct perf_eve
 	hwc->event_base  = uncore_perf_ctr(box, hwc->idx);
 }
 
-static void uncore_perf_event_update(struct intel_uncore_box *box, struct perf_event *event)
+void uncore_perf_event_update(struct intel_uncore_box *box, struct perf_event *event)
 {
 	u64 prev_count, new_count, delta;
 	int shift;
@@ -3201,14 +227,14 @@ static enum hrtimer_restart uncore_pmu_hrtimer(struct hrtimer *hrtimer)
 	return HRTIMER_RESTART;
 }
 
-static void uncore_pmu_start_hrtimer(struct intel_uncore_box *box)
+void uncore_pmu_start_hrtimer(struct intel_uncore_box *box)
 {
 	__hrtimer_start_range_ns(&box->hrtimer,
 			ns_to_ktime(box->hrtimer_duration), 0,
 			HRTIMER_MODE_REL_PINNED, 0);
 }
 
-static void uncore_pmu_cancel_hrtimer(struct intel_uncore_box *box)
+void uncore_pmu_cancel_hrtimer(struct intel_uncore_box *box)
 {
 	hrtimer_cancel(&box->hrtimer);
 }
@@ -3291,7 +317,7 @@ uncore_get_event_constraint(struct intel_uncore_box *box, struct perf_event *eve
 	}
 
 	if (event->attr.config == UNCORE_FIXED_EVENT)
-		return &constraint_fixed;
+		return &uncore_constraint_fixed;
 
 	if (type->constraints) {
 		for_each_event_constraint(c, type->constraints) {
@@ -3496,7 +522,7 @@ static void uncore_pmu_event_del(struct perf_event *event, int flags)
 	event->hw.last_tag = ~0ULL;
 }
 
-static void uncore_pmu_event_read(struct perf_event *event)
+void uncore_pmu_event_read(struct perf_event *event)
 {
 	struct intel_uncore_box *box = uncore_event_to_box(event);
 	uncore_perf_event_update(box, event);
@@ -3758,9 +784,6 @@ fail:
 	return ret;
 }
 
-static struct pci_driver *uncore_pci_driver;
-static bool pcidrv_registered;
-
 /*
  * add a pci uncore device
  */
@@ -3771,17 +794,18 @@ static int uncore_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id
 	struct intel_uncore_type *type;
 	int phys_id;
 
-	phys_id = pcibus_to_physid[pdev->bus->number];
+	phys_id = uncore_pcibus_to_physid[pdev->bus->number];
 	if (phys_id < 0)
 		return -ENODEV;
 
 	if (UNCORE_PCI_DEV_TYPE(id->driver_data) == UNCORE_EXTRA_PCI_DEV) {
-		extra_pci_dev[phys_id][UNCORE_PCI_DEV_IDX(id->driver_data)] = pdev;
+		int idx = UNCORE_PCI_DEV_IDX(id->driver_data);
+		uncore_extra_pci_dev[phys_id][idx] = pdev;
 		pci_set_drvdata(pdev, NULL);
 		return 0;
 	}
 
-	type = pci_uncores[UNCORE_PCI_DEV_TYPE(id->driver_data)];
+	type = uncore_pci_uncores[UNCORE_PCI_DEV_TYPE(id->driver_data)];
 	box = uncore_alloc_box(type, NUMA_NO_NODE);
 	if (!box)
 		return -ENOMEM;
@@ -3813,13 +837,13 @@ static void uncore_pci_remove(struct pci_dev *pdev)
 {
 	struct intel_uncore_box *box = pci_get_drvdata(pdev);
 	struct intel_uncore_pmu *pmu;
-	int i, cpu, phys_id = pcibus_to_physid[pdev->bus->number];
+	int i, cpu, phys_id = uncore_pcibus_to_physid[pdev->bus->number];
 
 	box = pci_get_drvdata(pdev);
 	if (!box) {
 		for (i = 0; i < UNCORE_EXTRA_PCI_DEV_MAX; i++) {
-			if (extra_pci_dev[phys_id][i] == pdev) {
-				extra_pci_dev[phys_id][i] = NULL;
+			if (uncore_extra_pci_dev[phys_id][i] == pdev) {
+				uncore_extra_pci_dev[phys_id][i] = NULL;
 				break;
 			}
 		}
@@ -3854,46 +878,29 @@ static int __init uncore_pci_init(void)
 
 	switch (boot_cpu_data.x86_model) {
 	case 45: /* Sandy Bridge-EP */
-		ret = snbep_pci2phy_map_init(0x3ce0);
-		if (ret)
-			return ret;
-		pci_uncores = snbep_pci_uncores;
-		uncore_pci_driver = &snbep_uncore_pci_driver;
+		ret = snbep_uncore_pci_init();
 		break;
-	case 62: /* IvyTown */
-		ret = snbep_pci2phy_map_init(0x0e1e);
-		if (ret)
-			return ret;
-		pci_uncores = ivt_pci_uncores;
-		uncore_pci_driver = &ivt_uncore_pci_driver;
+	case 62: /* Ivy Bridge-EP */
+		ret = ivbep_uncore_pci_init();
 		break;
 	case 42: /* Sandy Bridge */
-		ret = snb_pci2phy_map_init(PCI_DEVICE_ID_INTEL_SNB_IMC);
-		if (ret)
-			return ret;
-		pci_uncores = snb_pci_uncores;
-		uncore_pci_driver = &snb_uncore_pci_driver;
+		ret = snb_uncore_pci_init();
 		break;
 	case 58: /* Ivy Bridge */
-		ret = snb_pci2phy_map_init(PCI_DEVICE_ID_INTEL_IVB_IMC);
-		if (ret)
-			return ret;
-		pci_uncores = snb_pci_uncores;
-		uncore_pci_driver = &ivb_uncore_pci_driver;
+		ret = ivb_uncore_pci_init();
 		break;
 	case 60: /* Haswell */
 	case 69: /* Haswell Celeron */
-		ret = snb_pci2phy_map_init(PCI_DEVICE_ID_INTEL_HSW_IMC);
-		if (ret)
-			return ret;
-		pci_uncores = snb_pci_uncores;
-		uncore_pci_driver = &hsw_uncore_pci_driver;
+		ret = hsw_uncore_pci_init();
 		break;
 	default:
 		return 0;
 	}
 
-	ret = uncore_types_init(pci_uncores);
+	if (ret)
+		return ret;
+
+	ret = uncore_types_init(uncore_pci_uncores);
 	if (ret)
 		return ret;
 
@@ -3904,7 +911,7 @@ static int __init uncore_pci_init(void)
 	if (ret == 0)
 		pcidrv_registered = true;
 	else
-		uncore_types_exit(pci_uncores);
+		uncore_types_exit(uncore_pci_uncores);
 
 	return ret;
 }
@@ -3914,7 +921,7 @@ static void __init uncore_pci_exit(void)
 	if (pcidrv_registered) {
 		pcidrv_registered = false;
 		pci_unregister_driver(uncore_pci_driver);
-		uncore_types_exit(pci_uncores);
+		uncore_types_exit(uncore_pci_uncores);
 	}
 }
 
@@ -3940,8 +947,8 @@ static void uncore_cpu_dying(int cpu)
 	struct intel_uncore_box *box;
 	int i, j;
 
-	for (i = 0; msr_uncores[i]; i++) {
-		type = msr_uncores[i];
+	for (i = 0; uncore_msr_uncores[i]; i++) {
+		type = uncore_msr_uncores[i];
 		for (j = 0; j < type->num_boxes; j++) {
 			pmu = &type->pmus[j];
 			box = *per_cpu_ptr(pmu->box, cpu);
@@ -3961,8 +968,8 @@ static int uncore_cpu_starting(int cpu)
 
 	phys_id = topology_physical_package_id(cpu);
 
-	for (i = 0; msr_uncores[i]; i++) {
-		type = msr_uncores[i];
+	for (i = 0; uncore_msr_uncores[i]; i++) {
+		type = uncore_msr_uncores[i];
 		for (j = 0; j < type->num_boxes; j++) {
 			pmu = &type->pmus[j];
 			box = *per_cpu_ptr(pmu->box, cpu);
@@ -4002,8 +1009,8 @@ static int uncore_cpu_prepare(int cpu, int phys_id)
 	struct intel_uncore_box *box;
 	int i, j;
 
-	for (i = 0; msr_uncores[i]; i++) {
-		type = msr_uncores[i];
+	for (i = 0; uncore_msr_uncores[i]; i++) {
+		type = uncore_msr_uncores[i];
 		for (j = 0; j < type->num_boxes; j++) {
 			pmu = &type->pmus[j];
 			if (pmu->func_id < 0)
@@ -4083,8 +1090,8 @@ static void uncore_event_exit_cpu(int cpu)
 	if (target >= 0)
 		cpumask_set_cpu(target, &uncore_cpu_mask);
 
-	uncore_change_context(msr_uncores, cpu, target);
-	uncore_change_context(pci_uncores, cpu, target);
+	uncore_change_context(uncore_msr_uncores, cpu, target);
+	uncore_change_context(uncore_pci_uncores, cpu, target);
 }
 
 static void uncore_event_init_cpu(int cpu)
@@ -4099,8 +1106,8 @@ static void uncore_event_init_cpu(int cpu)
 
 	cpumask_set_cpu(cpu, &uncore_cpu_mask);
 
-	uncore_change_context(msr_uncores, -1, cpu);
-	uncore_change_context(pci_uncores, -1, cpu);
+	uncore_change_context(uncore_msr_uncores, -1, cpu);
+	uncore_change_context(uncore_pci_uncores, -1, cpu);
 }
 
 static int uncore_cpu_notifier(struct notifier_block *self,
@@ -4160,47 +1167,35 @@ static void __init uncore_cpu_setup(void *dummy)
 
 static int __init uncore_cpu_init(void)
 {
-	int ret, max_cores;
+	int ret;
 
-	max_cores = boot_cpu_data.x86_max_cores;
 	switch (boot_cpu_data.x86_model) {
 	case 26: /* Nehalem */
 	case 30:
 	case 37: /* Westmere */
 	case 44:
-		msr_uncores = nhm_msr_uncores;
+		nhm_uncore_cpu_init();
 		break;
 	case 42: /* Sandy Bridge */
 	case 58: /* Ivy Bridge */
-		if (snb_uncore_cbox.num_boxes > max_cores)
-			snb_uncore_cbox.num_boxes = max_cores;
-		msr_uncores = snb_msr_uncores;
+		snb_uncore_cpu_init();
 		break;
 	case 45: /* Sandy Bridge-EP */
-		if (snbep_uncore_cbox.num_boxes > max_cores)
-			snbep_uncore_cbox.num_boxes = max_cores;
-		msr_uncores = snbep_msr_uncores;
+		snbep_uncore_cpu_init();
 		break;
 	case 46: /* Nehalem-EX */
-		uncore_nhmex = true;
 	case 47: /* Westmere-EX aka. Xeon E7 */
-		if (!uncore_nhmex)
-			nhmex_uncore_mbox.event_descs = wsmex_uncore_mbox_events;
-		if (nhmex_uncore_cbox.num_boxes > max_cores)
-			nhmex_uncore_cbox.num_boxes = max_cores;
-		msr_uncores = nhmex_msr_uncores;
+		nhmex_uncore_cpu_init();
 		break;
-	case 62: /* IvyTown */
-		if (ivt_uncore_cbox.num_boxes > max_cores)
-			ivt_uncore_cbox.num_boxes = max_cores;
-		msr_uncores = ivt_msr_uncores;
+	case 62: /* Ivy Bridge-EP */
+		ivbep_uncore_cpu_init();
 		break;
 
 	default:
 		return 0;
 	}
 
-	ret = uncore_types_init(msr_uncores);
+	ret = uncore_types_init(uncore_msr_uncores);
 	if (ret)
 		return ret;
 
@@ -4213,16 +1208,16 @@ static int __init uncore_pmus_register(void)
 	struct intel_uncore_type *type;
 	int i, j;
 
-	for (i = 0; msr_uncores[i]; i++) {
-		type = msr_uncores[i];
+	for (i = 0; uncore_msr_uncores[i]; i++) {
+		type = uncore_msr_uncores[i];
 		for (j = 0; j < type->num_boxes; j++) {
 			pmu = &type->pmus[j];
 			uncore_pmu_register(pmu);
 		}
 	}
 
-	for (i = 0; pci_uncores[i]; i++) {
-		type = pci_uncores[i];
+	for (i = 0; uncore_pci_uncores[i]; i++) {
+		type = uncore_pci_uncores[i];
 		for (j = 0; j < type->num_boxes; j++) {
 			pmu = &type->pmus[j];
 			uncore_pmu_register(pmu);
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.h b/arch/x86/kernel/cpu/perf_event_intel_uncore.h
index 90236f0c94a906..1d7e894160186b 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore.h
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.h
@@ -24,395 +24,6 @@
 
 #define UNCORE_EVENT_CONSTRAINT(c, n) EVENT_CONSTRAINT(c, n, 0xff)
 
-/* SNB event control */
-#define SNB_UNC_CTL_EV_SEL_MASK			0x000000ff
-#define SNB_UNC_CTL_UMASK_MASK			0x0000ff00
-#define SNB_UNC_CTL_EDGE_DET			(1 << 18)
-#define SNB_UNC_CTL_EN				(1 << 22)
-#define SNB_UNC_CTL_INVERT			(1 << 23)
-#define SNB_UNC_CTL_CMASK_MASK			0x1f000000
-#define NHM_UNC_CTL_CMASK_MASK			0xff000000
-#define NHM_UNC_FIXED_CTR_CTL_EN		(1 << 0)
-
-#define SNB_UNC_RAW_EVENT_MASK			(SNB_UNC_CTL_EV_SEL_MASK | \
-						 SNB_UNC_CTL_UMASK_MASK | \
-						 SNB_UNC_CTL_EDGE_DET | \
-						 SNB_UNC_CTL_INVERT | \
-						 SNB_UNC_CTL_CMASK_MASK)
-
-#define NHM_UNC_RAW_EVENT_MASK			(SNB_UNC_CTL_EV_SEL_MASK | \
-						 SNB_UNC_CTL_UMASK_MASK | \
-						 SNB_UNC_CTL_EDGE_DET | \
-						 SNB_UNC_CTL_INVERT | \
-						 NHM_UNC_CTL_CMASK_MASK)
-
-/* SNB global control register */
-#define SNB_UNC_PERF_GLOBAL_CTL                 0x391
-#define SNB_UNC_FIXED_CTR_CTRL                  0x394
-#define SNB_UNC_FIXED_CTR                       0x395
-
-/* SNB uncore global control */
-#define SNB_UNC_GLOBAL_CTL_CORE_ALL             ((1 << 4) - 1)
-#define SNB_UNC_GLOBAL_CTL_EN                   (1 << 29)
-
-/* SNB Cbo register */
-#define SNB_UNC_CBO_0_PERFEVTSEL0               0x700
-#define SNB_UNC_CBO_0_PER_CTR0                  0x706
-#define SNB_UNC_CBO_MSR_OFFSET                  0x10
-
-/* NHM global control register */
-#define NHM_UNC_PERF_GLOBAL_CTL                 0x391
-#define NHM_UNC_FIXED_CTR                       0x394
-#define NHM_UNC_FIXED_CTR_CTRL                  0x395
-
-/* NHM uncore global control */
-#define NHM_UNC_GLOBAL_CTL_EN_PC_ALL            ((1ULL << 8) - 1)
-#define NHM_UNC_GLOBAL_CTL_EN_FC                (1ULL << 32)
-
-/* NHM uncore register */
-#define NHM_UNC_PERFEVTSEL0                     0x3c0
-#define NHM_UNC_UNCORE_PMC0                     0x3b0
-
-/* SNB-EP Box level control */
-#define SNBEP_PMON_BOX_CTL_RST_CTRL	(1 << 0)
-#define SNBEP_PMON_BOX_CTL_RST_CTRS	(1 << 1)
-#define SNBEP_PMON_BOX_CTL_FRZ		(1 << 8)
-#define SNBEP_PMON_BOX_CTL_FRZ_EN	(1 << 16)
-#define SNBEP_PMON_BOX_CTL_INT		(SNBEP_PMON_BOX_CTL_RST_CTRL | \
-					 SNBEP_PMON_BOX_CTL_RST_CTRS | \
-					 SNBEP_PMON_BOX_CTL_FRZ_EN)
-/* SNB-EP event control */
-#define SNBEP_PMON_CTL_EV_SEL_MASK	0x000000ff
-#define SNBEP_PMON_CTL_UMASK_MASK	0x0000ff00
-#define SNBEP_PMON_CTL_RST		(1 << 17)
-#define SNBEP_PMON_CTL_EDGE_DET		(1 << 18)
-#define SNBEP_PMON_CTL_EV_SEL_EXT	(1 << 21)
-#define SNBEP_PMON_CTL_EN		(1 << 22)
-#define SNBEP_PMON_CTL_INVERT		(1 << 23)
-#define SNBEP_PMON_CTL_TRESH_MASK	0xff000000
-#define SNBEP_PMON_RAW_EVENT_MASK	(SNBEP_PMON_CTL_EV_SEL_MASK | \
-					 SNBEP_PMON_CTL_UMASK_MASK | \
-					 SNBEP_PMON_CTL_EDGE_DET | \
-					 SNBEP_PMON_CTL_INVERT | \
-					 SNBEP_PMON_CTL_TRESH_MASK)
-
-/* SNB-EP Ubox event control */
-#define SNBEP_U_MSR_PMON_CTL_TRESH_MASK		0x1f000000
-#define SNBEP_U_MSR_PMON_RAW_EVENT_MASK		\
-				(SNBEP_PMON_CTL_EV_SEL_MASK | \
-				 SNBEP_PMON_CTL_UMASK_MASK | \
-				 SNBEP_PMON_CTL_EDGE_DET | \
-				 SNBEP_PMON_CTL_INVERT | \
-				 SNBEP_U_MSR_PMON_CTL_TRESH_MASK)
-
-#define SNBEP_CBO_PMON_CTL_TID_EN		(1 << 19)
-#define SNBEP_CBO_MSR_PMON_RAW_EVENT_MASK	(SNBEP_PMON_RAW_EVENT_MASK | \
-						 SNBEP_CBO_PMON_CTL_TID_EN)
-
-/* SNB-EP PCU event control */
-#define SNBEP_PCU_MSR_PMON_CTL_OCC_SEL_MASK	0x0000c000
-#define SNBEP_PCU_MSR_PMON_CTL_TRESH_MASK	0x1f000000
-#define SNBEP_PCU_MSR_PMON_CTL_OCC_INVERT	(1 << 30)
-#define SNBEP_PCU_MSR_PMON_CTL_OCC_EDGE_DET	(1 << 31)
-#define SNBEP_PCU_MSR_PMON_RAW_EVENT_MASK	\
-				(SNBEP_PMON_CTL_EV_SEL_MASK | \
-				 SNBEP_PCU_MSR_PMON_CTL_OCC_SEL_MASK | \
-				 SNBEP_PMON_CTL_EDGE_DET | \
-				 SNBEP_PMON_CTL_EV_SEL_EXT | \
-				 SNBEP_PMON_CTL_INVERT | \
-				 SNBEP_PCU_MSR_PMON_CTL_TRESH_MASK | \
-				 SNBEP_PCU_MSR_PMON_CTL_OCC_INVERT | \
-				 SNBEP_PCU_MSR_PMON_CTL_OCC_EDGE_DET)
-
-#define SNBEP_QPI_PCI_PMON_RAW_EVENT_MASK	\
-				(SNBEP_PMON_RAW_EVENT_MASK | \
-				 SNBEP_PMON_CTL_EV_SEL_EXT)
-
-/* SNB-EP pci control register */
-#define SNBEP_PCI_PMON_BOX_CTL			0xf4
-#define SNBEP_PCI_PMON_CTL0			0xd8
-/* SNB-EP pci counter register */
-#define SNBEP_PCI_PMON_CTR0			0xa0
-
-/* SNB-EP home agent register */
-#define SNBEP_HA_PCI_PMON_BOX_ADDRMATCH0	0x40
-#define SNBEP_HA_PCI_PMON_BOX_ADDRMATCH1	0x44
-#define SNBEP_HA_PCI_PMON_BOX_OPCODEMATCH	0x48
-/* SNB-EP memory controller register */
-#define SNBEP_MC_CHy_PCI_PMON_FIXED_CTL		0xf0
-#define SNBEP_MC_CHy_PCI_PMON_FIXED_CTR		0xd0
-/* SNB-EP QPI register */
-#define SNBEP_Q_Py_PCI_PMON_PKT_MATCH0		0x228
-#define SNBEP_Q_Py_PCI_PMON_PKT_MATCH1		0x22c
-#define SNBEP_Q_Py_PCI_PMON_PKT_MASK0		0x238
-#define SNBEP_Q_Py_PCI_PMON_PKT_MASK1		0x23c
-
-/* SNB-EP Ubox register */
-#define SNBEP_U_MSR_PMON_CTR0			0xc16
-#define SNBEP_U_MSR_PMON_CTL0			0xc10
-
-#define SNBEP_U_MSR_PMON_UCLK_FIXED_CTL		0xc08
-#define SNBEP_U_MSR_PMON_UCLK_FIXED_CTR		0xc09
-
-/* SNB-EP Cbo register */
-#define SNBEP_C0_MSR_PMON_CTR0			0xd16
-#define SNBEP_C0_MSR_PMON_CTL0			0xd10
-#define SNBEP_C0_MSR_PMON_BOX_CTL		0xd04
-#define SNBEP_C0_MSR_PMON_BOX_FILTER		0xd14
-#define SNBEP_CBO_MSR_OFFSET			0x20
-
-#define SNBEP_CB0_MSR_PMON_BOX_FILTER_TID	0x1f
-#define SNBEP_CB0_MSR_PMON_BOX_FILTER_NID	0x3fc00
-#define SNBEP_CB0_MSR_PMON_BOX_FILTER_STATE	0x7c0000
-#define SNBEP_CB0_MSR_PMON_BOX_FILTER_OPC	0xff800000
-
-#define SNBEP_CBO_EVENT_EXTRA_REG(e, m, i) {	\
-	.event = (e),				\
-	.msr = SNBEP_C0_MSR_PMON_BOX_FILTER,	\
-	.config_mask = (m),			\
-	.idx = (i)				\
-}
-
-/* SNB-EP PCU register */
-#define SNBEP_PCU_MSR_PMON_CTR0			0xc36
-#define SNBEP_PCU_MSR_PMON_CTL0			0xc30
-#define SNBEP_PCU_MSR_PMON_BOX_CTL		0xc24
-#define SNBEP_PCU_MSR_PMON_BOX_FILTER		0xc34
-#define SNBEP_PCU_MSR_PMON_BOX_FILTER_MASK	0xffffffff
-#define SNBEP_PCU_MSR_CORE_C3_CTR		0x3fc
-#define SNBEP_PCU_MSR_CORE_C6_CTR		0x3fd
-
-/* IVT event control */
-#define IVT_PMON_BOX_CTL_INT		(SNBEP_PMON_BOX_CTL_RST_CTRL | \
-					 SNBEP_PMON_BOX_CTL_RST_CTRS)
-#define IVT_PMON_RAW_EVENT_MASK		(SNBEP_PMON_CTL_EV_SEL_MASK | \
-					 SNBEP_PMON_CTL_UMASK_MASK | \
-					 SNBEP_PMON_CTL_EDGE_DET | \
-					 SNBEP_PMON_CTL_TRESH_MASK)
-/* IVT Ubox */
-#define IVT_U_MSR_PMON_GLOBAL_CTL		0xc00
-#define IVT_U_PMON_GLOBAL_FRZ_ALL		(1 << 31)
-#define IVT_U_PMON_GLOBAL_UNFRZ_ALL		(1 << 29)
-
-#define IVT_U_MSR_PMON_RAW_EVENT_MASK	\
-				(SNBEP_PMON_CTL_EV_SEL_MASK | \
-				 SNBEP_PMON_CTL_UMASK_MASK | \
-				 SNBEP_PMON_CTL_EDGE_DET | \
-				 SNBEP_U_MSR_PMON_CTL_TRESH_MASK)
-/* IVT Cbo */
-#define IVT_CBO_MSR_PMON_RAW_EVENT_MASK		(IVT_PMON_RAW_EVENT_MASK | \
-						 SNBEP_CBO_PMON_CTL_TID_EN)
-
-#define IVT_CB0_MSR_PMON_BOX_FILTER_TID		(0x1fULL << 0)
-#define IVT_CB0_MSR_PMON_BOX_FILTER_LINK	(0xfULL << 5)
-#define IVT_CB0_MSR_PMON_BOX_FILTER_STATE	(0x3fULL << 17)
-#define IVT_CB0_MSR_PMON_BOX_FILTER_NID		(0xffffULL << 32)
-#define IVT_CB0_MSR_PMON_BOX_FILTER_OPC		(0x1ffULL << 52)
-#define IVT_CB0_MSR_PMON_BOX_FILTER_C6		(0x1ULL << 61)
-#define IVT_CB0_MSR_PMON_BOX_FILTER_NC		(0x1ULL << 62)
-#define IVT_CB0_MSR_PMON_BOX_FILTER_IOSC	(0x1ULL << 63)
-
-/* IVT home agent */
-#define IVT_HA_PCI_PMON_CTL_Q_OCC_RST		(1 << 16)
-#define IVT_HA_PCI_PMON_RAW_EVENT_MASK		\
-				(IVT_PMON_RAW_EVENT_MASK | \
-				 IVT_HA_PCI_PMON_CTL_Q_OCC_RST)
-/* IVT PCU */
-#define IVT_PCU_MSR_PMON_RAW_EVENT_MASK	\
-				(SNBEP_PMON_CTL_EV_SEL_MASK | \
-				 SNBEP_PMON_CTL_EV_SEL_EXT | \
-				 SNBEP_PCU_MSR_PMON_CTL_OCC_SEL_MASK | \
-				 SNBEP_PMON_CTL_EDGE_DET | \
-				 SNBEP_PCU_MSR_PMON_CTL_TRESH_MASK | \
-				 SNBEP_PCU_MSR_PMON_CTL_OCC_INVERT | \
-				 SNBEP_PCU_MSR_PMON_CTL_OCC_EDGE_DET)
-/* IVT QPI */
-#define IVT_QPI_PCI_PMON_RAW_EVENT_MASK	\
-				(IVT_PMON_RAW_EVENT_MASK | \
-				 SNBEP_PMON_CTL_EV_SEL_EXT)
-
-/* NHM-EX event control */
-#define NHMEX_PMON_CTL_EV_SEL_MASK	0x000000ff
-#define NHMEX_PMON_CTL_UMASK_MASK	0x0000ff00
-#define NHMEX_PMON_CTL_EN_BIT0		(1 << 0)
-#define NHMEX_PMON_CTL_EDGE_DET		(1 << 18)
-#define NHMEX_PMON_CTL_PMI_EN		(1 << 20)
-#define NHMEX_PMON_CTL_EN_BIT22		(1 << 22)
-#define NHMEX_PMON_CTL_INVERT		(1 << 23)
-#define NHMEX_PMON_CTL_TRESH_MASK	0xff000000
-#define NHMEX_PMON_RAW_EVENT_MASK	(NHMEX_PMON_CTL_EV_SEL_MASK | \
-					 NHMEX_PMON_CTL_UMASK_MASK | \
-					 NHMEX_PMON_CTL_EDGE_DET | \
-					 NHMEX_PMON_CTL_INVERT | \
-					 NHMEX_PMON_CTL_TRESH_MASK)
-
-/* NHM-EX Ubox */
-#define NHMEX_U_MSR_PMON_GLOBAL_CTL		0xc00
-#define NHMEX_U_MSR_PMON_CTR			0xc11
-#define NHMEX_U_MSR_PMON_EV_SEL			0xc10
-
-#define NHMEX_U_PMON_GLOBAL_EN			(1 << 0)
-#define NHMEX_U_PMON_GLOBAL_PMI_CORE_SEL	0x0000001e
-#define NHMEX_U_PMON_GLOBAL_EN_ALL		(1 << 28)
-#define NHMEX_U_PMON_GLOBAL_RST_ALL		(1 << 29)
-#define NHMEX_U_PMON_GLOBAL_FRZ_ALL		(1 << 31)
-
-#define NHMEX_U_PMON_RAW_EVENT_MASK		\
-		(NHMEX_PMON_CTL_EV_SEL_MASK |	\
-		 NHMEX_PMON_CTL_EDGE_DET)
-
-/* NHM-EX Cbox */
-#define NHMEX_C0_MSR_PMON_GLOBAL_CTL		0xd00
-#define NHMEX_C0_MSR_PMON_CTR0			0xd11
-#define NHMEX_C0_MSR_PMON_EV_SEL0		0xd10
-#define NHMEX_C_MSR_OFFSET			0x20
-
-/* NHM-EX Bbox */
-#define NHMEX_B0_MSR_PMON_GLOBAL_CTL		0xc20
-#define NHMEX_B0_MSR_PMON_CTR0			0xc31
-#define NHMEX_B0_MSR_PMON_CTL0			0xc30
-#define NHMEX_B_MSR_OFFSET			0x40
-#define NHMEX_B0_MSR_MATCH			0xe45
-#define NHMEX_B0_MSR_MASK			0xe46
-#define NHMEX_B1_MSR_MATCH			0xe4d
-#define NHMEX_B1_MSR_MASK			0xe4e
-
-#define NHMEX_B_PMON_CTL_EN			(1 << 0)
-#define NHMEX_B_PMON_CTL_EV_SEL_SHIFT		1
-#define NHMEX_B_PMON_CTL_EV_SEL_MASK		\
-		(0x1f << NHMEX_B_PMON_CTL_EV_SEL_SHIFT)
-#define NHMEX_B_PMON_CTR_SHIFT		6
-#define NHMEX_B_PMON_CTR_MASK		\
-		(0x3 << NHMEX_B_PMON_CTR_SHIFT)
-#define NHMEX_B_PMON_RAW_EVENT_MASK		\
-		(NHMEX_B_PMON_CTL_EV_SEL_MASK | \
-		 NHMEX_B_PMON_CTR_MASK)
-
-/* NHM-EX Sbox */
-#define NHMEX_S0_MSR_PMON_GLOBAL_CTL		0xc40
-#define NHMEX_S0_MSR_PMON_CTR0			0xc51
-#define NHMEX_S0_MSR_PMON_CTL0			0xc50
-#define NHMEX_S_MSR_OFFSET			0x80
-#define NHMEX_S0_MSR_MM_CFG			0xe48
-#define NHMEX_S0_MSR_MATCH			0xe49
-#define NHMEX_S0_MSR_MASK			0xe4a
-#define NHMEX_S1_MSR_MM_CFG			0xe58
-#define NHMEX_S1_MSR_MATCH			0xe59
-#define NHMEX_S1_MSR_MASK			0xe5a
-
-#define NHMEX_S_PMON_MM_CFG_EN			(0x1ULL << 63)
-#define NHMEX_S_EVENT_TO_R_PROG_EV		0
-
-/* NHM-EX Mbox */
-#define NHMEX_M0_MSR_GLOBAL_CTL			0xca0
-#define NHMEX_M0_MSR_PMU_DSP			0xca5
-#define NHMEX_M0_MSR_PMU_ISS			0xca6
-#define NHMEX_M0_MSR_PMU_MAP			0xca7
-#define NHMEX_M0_MSR_PMU_MSC_THR		0xca8
-#define NHMEX_M0_MSR_PMU_PGT			0xca9
-#define NHMEX_M0_MSR_PMU_PLD			0xcaa
-#define NHMEX_M0_MSR_PMU_ZDP_CTL_FVC		0xcab
-#define NHMEX_M0_MSR_PMU_CTL0			0xcb0
-#define NHMEX_M0_MSR_PMU_CNT0			0xcb1
-#define NHMEX_M_MSR_OFFSET			0x40
-#define NHMEX_M0_MSR_PMU_MM_CFG			0xe54
-#define NHMEX_M1_MSR_PMU_MM_CFG			0xe5c
-
-#define NHMEX_M_PMON_MM_CFG_EN			(1ULL << 63)
-#define NHMEX_M_PMON_ADDR_MATCH_MASK		0x3ffffffffULL
-#define NHMEX_M_PMON_ADDR_MASK_MASK		0x7ffffffULL
-#define NHMEX_M_PMON_ADDR_MASK_SHIFT		34
-
-#define NHMEX_M_PMON_CTL_EN			(1 << 0)
-#define NHMEX_M_PMON_CTL_PMI_EN			(1 << 1)
-#define NHMEX_M_PMON_CTL_COUNT_MODE_SHIFT	2
-#define NHMEX_M_PMON_CTL_COUNT_MODE_MASK	\
-	(0x3 << NHMEX_M_PMON_CTL_COUNT_MODE_SHIFT)
-#define NHMEX_M_PMON_CTL_STORAGE_MODE_SHIFT	4
-#define NHMEX_M_PMON_CTL_STORAGE_MODE_MASK	\
-	(0x3 << NHMEX_M_PMON_CTL_STORAGE_MODE_SHIFT)
-#define NHMEX_M_PMON_CTL_WRAP_MODE		(1 << 6)
-#define NHMEX_M_PMON_CTL_FLAG_MODE		(1 << 7)
-#define NHMEX_M_PMON_CTL_INC_SEL_SHIFT		9
-#define NHMEX_M_PMON_CTL_INC_SEL_MASK		\
-	(0x1f << NHMEX_M_PMON_CTL_INC_SEL_SHIFT)
-#define NHMEX_M_PMON_CTL_SET_FLAG_SEL_SHIFT	19
-#define NHMEX_M_PMON_CTL_SET_FLAG_SEL_MASK	\
-	(0x7 << NHMEX_M_PMON_CTL_SET_FLAG_SEL_SHIFT)
-#define NHMEX_M_PMON_RAW_EVENT_MASK			\
-		(NHMEX_M_PMON_CTL_COUNT_MODE_MASK |	\
-		 NHMEX_M_PMON_CTL_STORAGE_MODE_MASK |	\
-		 NHMEX_M_PMON_CTL_WRAP_MODE |		\
-		 NHMEX_M_PMON_CTL_FLAG_MODE |		\
-		 NHMEX_M_PMON_CTL_INC_SEL_MASK |	\
-		 NHMEX_M_PMON_CTL_SET_FLAG_SEL_MASK)
-
-#define NHMEX_M_PMON_ZDP_CTL_FVC_MASK		(((1 << 11) - 1) | (1 << 23))
-#define NHMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(n)	(0x7ULL << (11 + 3 * (n)))
-
-#define WSMEX_M_PMON_ZDP_CTL_FVC_MASK		(((1 << 12) - 1) | (1 << 24))
-#define WSMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(n)	(0x7ULL << (12 + 3 * (n)))
-
-/*
- * use the 9~13 bits to select event If the 7th bit is not set,
- * otherwise use the 19~21 bits to select event.
- */
-#define MBOX_INC_SEL(x) ((x) << NHMEX_M_PMON_CTL_INC_SEL_SHIFT)
-#define MBOX_SET_FLAG_SEL(x) (((x) << NHMEX_M_PMON_CTL_SET_FLAG_SEL_SHIFT) | \
-				NHMEX_M_PMON_CTL_FLAG_MODE)
-#define MBOX_INC_SEL_MASK (NHMEX_M_PMON_CTL_INC_SEL_MASK | \
-			   NHMEX_M_PMON_CTL_FLAG_MODE)
-#define MBOX_SET_FLAG_SEL_MASK (NHMEX_M_PMON_CTL_SET_FLAG_SEL_MASK | \
-				NHMEX_M_PMON_CTL_FLAG_MODE)
-#define MBOX_INC_SEL_EXTAR_REG(c, r) \
-		EVENT_EXTRA_REG(MBOX_INC_SEL(c), NHMEX_M0_MSR_PMU_##r, \
-				MBOX_INC_SEL_MASK, (u64)-1, NHMEX_M_##r)
-#define MBOX_SET_FLAG_SEL_EXTRA_REG(c, r) \
-		EVENT_EXTRA_REG(MBOX_SET_FLAG_SEL(c), NHMEX_M0_MSR_PMU_##r, \
-				MBOX_SET_FLAG_SEL_MASK, \
-				(u64)-1, NHMEX_M_##r)
-
-/* NHM-EX Rbox */
-#define NHMEX_R_MSR_GLOBAL_CTL			0xe00
-#define NHMEX_R_MSR_PMON_CTL0			0xe10
-#define NHMEX_R_MSR_PMON_CNT0			0xe11
-#define NHMEX_R_MSR_OFFSET			0x20
-
-#define NHMEX_R_MSR_PORTN_QLX_CFG(n)		\
-		((n) < 4 ? (0xe0c + (n)) : (0xe2c + (n) - 4))
-#define NHMEX_R_MSR_PORTN_IPERF_CFG0(n)		(0xe04 + (n))
-#define NHMEX_R_MSR_PORTN_IPERF_CFG1(n)		(0xe24 + (n))
-#define NHMEX_R_MSR_PORTN_XBR_OFFSET(n)		\
-		(((n) < 4 ? 0 : 0x10) + (n) * 4)
-#define NHMEX_R_MSR_PORTN_XBR_SET1_MM_CFG(n)	\
-		(0xe60 + NHMEX_R_MSR_PORTN_XBR_OFFSET(n))
-#define NHMEX_R_MSR_PORTN_XBR_SET1_MATCH(n)	\
-		(NHMEX_R_MSR_PORTN_XBR_SET1_MM_CFG(n) + 1)
-#define NHMEX_R_MSR_PORTN_XBR_SET1_MASK(n)	\
-		(NHMEX_R_MSR_PORTN_XBR_SET1_MM_CFG(n) + 2)
-#define NHMEX_R_MSR_PORTN_XBR_SET2_MM_CFG(n)	\
-		(0xe70 + NHMEX_R_MSR_PORTN_XBR_OFFSET(n))
-#define NHMEX_R_MSR_PORTN_XBR_SET2_MATCH(n)	\
-		(NHMEX_R_MSR_PORTN_XBR_SET2_MM_CFG(n) + 1)
-#define NHMEX_R_MSR_PORTN_XBR_SET2_MASK(n)	\
-		(NHMEX_R_MSR_PORTN_XBR_SET2_MM_CFG(n) + 2)
-
-#define NHMEX_R_PMON_CTL_EN			(1 << 0)
-#define NHMEX_R_PMON_CTL_EV_SEL_SHIFT		1
-#define NHMEX_R_PMON_CTL_EV_SEL_MASK		\
-		(0x1f << NHMEX_R_PMON_CTL_EV_SEL_SHIFT)
-#define NHMEX_R_PMON_CTL_PMI_EN			(1 << 6)
-#define NHMEX_R_PMON_RAW_EVENT_MASK		NHMEX_R_PMON_CTL_EV_SEL_MASK
-
-/* NHM-EX Wbox */
-#define NHMEX_W_MSR_GLOBAL_CTL			0xc80
-#define NHMEX_W_MSR_PMON_CNT0			0xc90
-#define NHMEX_W_MSR_PMON_EVT_SEL0		0xc91
-#define NHMEX_W_MSR_PMON_FIXED_CTR		0x394
-#define NHMEX_W_MSR_PMON_FIXED_CTL		0x395
-
-#define NHMEX_W_PMON_GLOBAL_FIXED_EN		(1ULL << 31)
-
 struct intel_uncore_ops;
 struct intel_uncore_pmu;
 struct intel_uncore_box;
@@ -505,6 +116,9 @@ struct uncore_event_desc {
 	const char *config;
 };
 
+ssize_t uncore_event_show(struct kobject *kobj,
+			  struct kobj_attribute *attr, char *buf);
+
 #define INTEL_UNCORE_EVENT_DESC(_name, _config)			\
 {								\
 	.attr	= __ATTR(_name, 0444, uncore_event_show, NULL),	\
@@ -522,15 +136,6 @@ static ssize_t __uncore_##_var##_show(struct kobject *kobj,		\
 static struct kobj_attribute format_attr_##_var =			\
 	__ATTR(_name, 0444, __uncore_##_var##_show, NULL)
 
-
-static ssize_t uncore_event_show(struct kobject *kobj,
-				struct kobj_attribute *attr, char *buf)
-{
-	struct uncore_event_desc *event =
-		container_of(attr, struct uncore_event_desc, attr);
-	return sprintf(buf, "%s", event->config);
-}
-
 static inline unsigned uncore_pci_box_ctl(struct intel_uncore_box *box)
 {
 	return box->pmu->type->box_ctl;
@@ -694,3 +299,39 @@ static inline bool uncore_box_is_fake(struct intel_uncore_box *box)
 {
 	return (box->phys_id < 0);
 }
+
+struct intel_uncore_pmu *uncore_event_to_pmu(struct perf_event *event);
+struct intel_uncore_box *uncore_pmu_to_box(struct intel_uncore_pmu *pmu, int cpu);
+struct intel_uncore_box *uncore_event_to_box(struct perf_event *event);
+u64 uncore_msr_read_counter(struct intel_uncore_box *box, struct perf_event *event);
+void uncore_pmu_start_hrtimer(struct intel_uncore_box *box);
+void uncore_pmu_cancel_hrtimer(struct intel_uncore_box *box);
+void uncore_pmu_event_read(struct perf_event *event);
+void uncore_perf_event_update(struct intel_uncore_box *box, struct perf_event *event);
+struct event_constraint *
+uncore_get_constraint(struct intel_uncore_box *box, struct perf_event *event);
+void uncore_put_constraint(struct intel_uncore_box *box, struct perf_event *event);
+u64 uncore_shared_reg_config(struct intel_uncore_box *box, int idx);
+
+extern struct intel_uncore_type **uncore_msr_uncores;
+extern struct intel_uncore_type **uncore_pci_uncores;
+extern struct pci_driver *uncore_pci_driver;
+extern int uncore_pcibus_to_physid[256];
+extern struct pci_dev *uncore_extra_pci_dev[UNCORE_SOCKET_MAX][UNCORE_EXTRA_PCI_DEV_MAX];
+extern struct event_constraint uncore_constraint_empty;
+
+/* perf_event_intel_uncore_snb.c */
+int snb_uncore_pci_init(void);
+int ivb_uncore_pci_init(void);
+int hsw_uncore_pci_init(void);
+void snb_uncore_cpu_init(void);
+void nhm_uncore_cpu_init(void);
+
+/* perf_event_intel_uncore_snbep.c */
+int snbep_uncore_pci_init(void);
+void snbep_uncore_cpu_init(void);
+int ivbep_uncore_pci_init(void);
+void ivbep_uncore_cpu_init(void);
+
+/* perf_event_intel_uncore_nhmex.c */
+void nhmex_uncore_cpu_init(void);
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore_nhmex.c b/arch/x86/kernel/cpu/perf_event_intel_uncore_nhmex.c
new file mode 100644
index 00000000000000..2749965afed0b0
--- /dev/null
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore_nhmex.c
@@ -0,0 +1,1221 @@
+/* Nehalem-EX/Westmere-EX uncore support */
+#include "perf_event_intel_uncore.h"
+
+/* NHM-EX event control */
+#define NHMEX_PMON_CTL_EV_SEL_MASK	0x000000ff
+#define NHMEX_PMON_CTL_UMASK_MASK	0x0000ff00
+#define NHMEX_PMON_CTL_EN_BIT0		(1 << 0)
+#define NHMEX_PMON_CTL_EDGE_DET		(1 << 18)
+#define NHMEX_PMON_CTL_PMI_EN		(1 << 20)
+#define NHMEX_PMON_CTL_EN_BIT22		(1 << 22)
+#define NHMEX_PMON_CTL_INVERT		(1 << 23)
+#define NHMEX_PMON_CTL_TRESH_MASK	0xff000000
+#define NHMEX_PMON_RAW_EVENT_MASK	(NHMEX_PMON_CTL_EV_SEL_MASK | \
+					 NHMEX_PMON_CTL_UMASK_MASK | \
+					 NHMEX_PMON_CTL_EDGE_DET | \
+					 NHMEX_PMON_CTL_INVERT | \
+					 NHMEX_PMON_CTL_TRESH_MASK)
+
+/* NHM-EX Ubox */
+#define NHMEX_U_MSR_PMON_GLOBAL_CTL		0xc00
+#define NHMEX_U_MSR_PMON_CTR			0xc11
+#define NHMEX_U_MSR_PMON_EV_SEL			0xc10
+
+#define NHMEX_U_PMON_GLOBAL_EN			(1 << 0)
+#define NHMEX_U_PMON_GLOBAL_PMI_CORE_SEL	0x0000001e
+#define NHMEX_U_PMON_GLOBAL_EN_ALL		(1 << 28)
+#define NHMEX_U_PMON_GLOBAL_RST_ALL		(1 << 29)
+#define NHMEX_U_PMON_GLOBAL_FRZ_ALL		(1 << 31)
+
+#define NHMEX_U_PMON_RAW_EVENT_MASK		\
+		(NHMEX_PMON_CTL_EV_SEL_MASK |	\
+		 NHMEX_PMON_CTL_EDGE_DET)
+
+/* NHM-EX Cbox */
+#define NHMEX_C0_MSR_PMON_GLOBAL_CTL		0xd00
+#define NHMEX_C0_MSR_PMON_CTR0			0xd11
+#define NHMEX_C0_MSR_PMON_EV_SEL0		0xd10
+#define NHMEX_C_MSR_OFFSET			0x20
+
+/* NHM-EX Bbox */
+#define NHMEX_B0_MSR_PMON_GLOBAL_CTL		0xc20
+#define NHMEX_B0_MSR_PMON_CTR0			0xc31
+#define NHMEX_B0_MSR_PMON_CTL0			0xc30
+#define NHMEX_B_MSR_OFFSET			0x40
+#define NHMEX_B0_MSR_MATCH			0xe45
+#define NHMEX_B0_MSR_MASK			0xe46
+#define NHMEX_B1_MSR_MATCH			0xe4d
+#define NHMEX_B1_MSR_MASK			0xe4e
+
+#define NHMEX_B_PMON_CTL_EN			(1 << 0)
+#define NHMEX_B_PMON_CTL_EV_SEL_SHIFT		1
+#define NHMEX_B_PMON_CTL_EV_SEL_MASK		\
+		(0x1f << NHMEX_B_PMON_CTL_EV_SEL_SHIFT)
+#define NHMEX_B_PMON_CTR_SHIFT		6
+#define NHMEX_B_PMON_CTR_MASK		\
+		(0x3 << NHMEX_B_PMON_CTR_SHIFT)
+#define NHMEX_B_PMON_RAW_EVENT_MASK		\
+		(NHMEX_B_PMON_CTL_EV_SEL_MASK | \
+		 NHMEX_B_PMON_CTR_MASK)
+
+/* NHM-EX Sbox */
+#define NHMEX_S0_MSR_PMON_GLOBAL_CTL		0xc40
+#define NHMEX_S0_MSR_PMON_CTR0			0xc51
+#define NHMEX_S0_MSR_PMON_CTL0			0xc50
+#define NHMEX_S_MSR_OFFSET			0x80
+#define NHMEX_S0_MSR_MM_CFG			0xe48
+#define NHMEX_S0_MSR_MATCH			0xe49
+#define NHMEX_S0_MSR_MASK			0xe4a
+#define NHMEX_S1_MSR_MM_CFG			0xe58
+#define NHMEX_S1_MSR_MATCH			0xe59
+#define NHMEX_S1_MSR_MASK			0xe5a
+
+#define NHMEX_S_PMON_MM_CFG_EN			(0x1ULL << 63)
+#define NHMEX_S_EVENT_TO_R_PROG_EV		0
+
+/* NHM-EX Mbox */
+#define NHMEX_M0_MSR_GLOBAL_CTL			0xca0
+#define NHMEX_M0_MSR_PMU_DSP			0xca5
+#define NHMEX_M0_MSR_PMU_ISS			0xca6
+#define NHMEX_M0_MSR_PMU_MAP			0xca7
+#define NHMEX_M0_MSR_PMU_MSC_THR		0xca8
+#define NHMEX_M0_MSR_PMU_PGT			0xca9
+#define NHMEX_M0_MSR_PMU_PLD			0xcaa
+#define NHMEX_M0_MSR_PMU_ZDP_CTL_FVC		0xcab
+#define NHMEX_M0_MSR_PMU_CTL0			0xcb0
+#define NHMEX_M0_MSR_PMU_CNT0			0xcb1
+#define NHMEX_M_MSR_OFFSET			0x40
+#define NHMEX_M0_MSR_PMU_MM_CFG			0xe54
+#define NHMEX_M1_MSR_PMU_MM_CFG			0xe5c
+
+#define NHMEX_M_PMON_MM_CFG_EN			(1ULL << 63)
+#define NHMEX_M_PMON_ADDR_MATCH_MASK		0x3ffffffffULL
+#define NHMEX_M_PMON_ADDR_MASK_MASK		0x7ffffffULL
+#define NHMEX_M_PMON_ADDR_MASK_SHIFT		34
+
+#define NHMEX_M_PMON_CTL_EN			(1 << 0)
+#define NHMEX_M_PMON_CTL_PMI_EN			(1 << 1)
+#define NHMEX_M_PMON_CTL_COUNT_MODE_SHIFT	2
+#define NHMEX_M_PMON_CTL_COUNT_MODE_MASK	\
+	(0x3 << NHMEX_M_PMON_CTL_COUNT_MODE_SHIFT)
+#define NHMEX_M_PMON_CTL_STORAGE_MODE_SHIFT	4
+#define NHMEX_M_PMON_CTL_STORAGE_MODE_MASK	\
+	(0x3 << NHMEX_M_PMON_CTL_STORAGE_MODE_SHIFT)
+#define NHMEX_M_PMON_CTL_WRAP_MODE		(1 << 6)
+#define NHMEX_M_PMON_CTL_FLAG_MODE		(1 << 7)
+#define NHMEX_M_PMON_CTL_INC_SEL_SHIFT		9
+#define NHMEX_M_PMON_CTL_INC_SEL_MASK		\
+	(0x1f << NHMEX_M_PMON_CTL_INC_SEL_SHIFT)
+#define NHMEX_M_PMON_CTL_SET_FLAG_SEL_SHIFT	19
+#define NHMEX_M_PMON_CTL_SET_FLAG_SEL_MASK	\
+	(0x7 << NHMEX_M_PMON_CTL_SET_FLAG_SEL_SHIFT)
+#define NHMEX_M_PMON_RAW_EVENT_MASK			\
+		(NHMEX_M_PMON_CTL_COUNT_MODE_MASK |	\
+		 NHMEX_M_PMON_CTL_STORAGE_MODE_MASK |	\
+		 NHMEX_M_PMON_CTL_WRAP_MODE |		\
+		 NHMEX_M_PMON_CTL_FLAG_MODE |		\
+		 NHMEX_M_PMON_CTL_INC_SEL_MASK |	\
+		 NHMEX_M_PMON_CTL_SET_FLAG_SEL_MASK)
+
+#define NHMEX_M_PMON_ZDP_CTL_FVC_MASK		(((1 << 11) - 1) | (1 << 23))
+#define NHMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(n)	(0x7ULL << (11 + 3 * (n)))
+
+#define WSMEX_M_PMON_ZDP_CTL_FVC_MASK		(((1 << 12) - 1) | (1 << 24))
+#define WSMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(n)	(0x7ULL << (12 + 3 * (n)))
+
+/*
+ * use the 9~13 bits to select event If the 7th bit is not set,
+ * otherwise use the 19~21 bits to select event.
+ */
+#define MBOX_INC_SEL(x) ((x) << NHMEX_M_PMON_CTL_INC_SEL_SHIFT)
+#define MBOX_SET_FLAG_SEL(x) (((x) << NHMEX_M_PMON_CTL_SET_FLAG_SEL_SHIFT) | \
+				NHMEX_M_PMON_CTL_FLAG_MODE)
+#define MBOX_INC_SEL_MASK (NHMEX_M_PMON_CTL_INC_SEL_MASK | \
+			   NHMEX_M_PMON_CTL_FLAG_MODE)
+#define MBOX_SET_FLAG_SEL_MASK (NHMEX_M_PMON_CTL_SET_FLAG_SEL_MASK | \
+				NHMEX_M_PMON_CTL_FLAG_MODE)
+#define MBOX_INC_SEL_EXTAR_REG(c, r) \
+		EVENT_EXTRA_REG(MBOX_INC_SEL(c), NHMEX_M0_MSR_PMU_##r, \
+				MBOX_INC_SEL_MASK, (u64)-1, NHMEX_M_##r)
+#define MBOX_SET_FLAG_SEL_EXTRA_REG(c, r) \
+		EVENT_EXTRA_REG(MBOX_SET_FLAG_SEL(c), NHMEX_M0_MSR_PMU_##r, \
+				MBOX_SET_FLAG_SEL_MASK, \
+				(u64)-1, NHMEX_M_##r)
+
+/* NHM-EX Rbox */
+#define NHMEX_R_MSR_GLOBAL_CTL			0xe00
+#define NHMEX_R_MSR_PMON_CTL0			0xe10
+#define NHMEX_R_MSR_PMON_CNT0			0xe11
+#define NHMEX_R_MSR_OFFSET			0x20
+
+#define NHMEX_R_MSR_PORTN_QLX_CFG(n)		\
+		((n) < 4 ? (0xe0c + (n)) : (0xe2c + (n) - 4))
+#define NHMEX_R_MSR_PORTN_IPERF_CFG0(n)		(0xe04 + (n))
+#define NHMEX_R_MSR_PORTN_IPERF_CFG1(n)		(0xe24 + (n))
+#define NHMEX_R_MSR_PORTN_XBR_OFFSET(n)		\
+		(((n) < 4 ? 0 : 0x10) + (n) * 4)
+#define NHMEX_R_MSR_PORTN_XBR_SET1_MM_CFG(n)	\
+		(0xe60 + NHMEX_R_MSR_PORTN_XBR_OFFSET(n))
+#define NHMEX_R_MSR_PORTN_XBR_SET1_MATCH(n)	\
+		(NHMEX_R_MSR_PORTN_XBR_SET1_MM_CFG(n) + 1)
+#define NHMEX_R_MSR_PORTN_XBR_SET1_MASK(n)	\
+		(NHMEX_R_MSR_PORTN_XBR_SET1_MM_CFG(n) + 2)
+#define NHMEX_R_MSR_PORTN_XBR_SET2_MM_CFG(n)	\
+		(0xe70 + NHMEX_R_MSR_PORTN_XBR_OFFSET(n))
+#define NHMEX_R_MSR_PORTN_XBR_SET2_MATCH(n)	\
+		(NHMEX_R_MSR_PORTN_XBR_SET2_MM_CFG(n) + 1)
+#define NHMEX_R_MSR_PORTN_XBR_SET2_MASK(n)	\
+		(NHMEX_R_MSR_PORTN_XBR_SET2_MM_CFG(n) + 2)
+
+#define NHMEX_R_PMON_CTL_EN			(1 << 0)
+#define NHMEX_R_PMON_CTL_EV_SEL_SHIFT		1
+#define NHMEX_R_PMON_CTL_EV_SEL_MASK		\
+		(0x1f << NHMEX_R_PMON_CTL_EV_SEL_SHIFT)
+#define NHMEX_R_PMON_CTL_PMI_EN			(1 << 6)
+#define NHMEX_R_PMON_RAW_EVENT_MASK		NHMEX_R_PMON_CTL_EV_SEL_MASK
+
+/* NHM-EX Wbox */
+#define NHMEX_W_MSR_GLOBAL_CTL			0xc80
+#define NHMEX_W_MSR_PMON_CNT0			0xc90
+#define NHMEX_W_MSR_PMON_EVT_SEL0		0xc91
+#define NHMEX_W_MSR_PMON_FIXED_CTR		0x394
+#define NHMEX_W_MSR_PMON_FIXED_CTL		0x395
+
+#define NHMEX_W_PMON_GLOBAL_FIXED_EN		(1ULL << 31)
+
+#define __BITS_VALUE(x, i, n)  ((typeof(x))(((x) >> ((i) * (n))) & \
+				((1ULL << (n)) - 1)))
+
+DEFINE_UNCORE_FORMAT_ATTR(event, event, "config:0-7");
+DEFINE_UNCORE_FORMAT_ATTR(event5, event, "config:1-5");
+DEFINE_UNCORE_FORMAT_ATTR(umask, umask, "config:8-15");
+DEFINE_UNCORE_FORMAT_ATTR(edge, edge, "config:18");
+DEFINE_UNCORE_FORMAT_ATTR(inv, inv, "config:23");
+DEFINE_UNCORE_FORMAT_ATTR(thresh8, thresh, "config:24-31");
+DEFINE_UNCORE_FORMAT_ATTR(counter, counter, "config:6-7");
+DEFINE_UNCORE_FORMAT_ATTR(match, match, "config1:0-63");
+DEFINE_UNCORE_FORMAT_ATTR(mask, mask, "config2:0-63");
+
+static void nhmex_uncore_msr_init_box(struct intel_uncore_box *box)
+{
+	wrmsrl(NHMEX_U_MSR_PMON_GLOBAL_CTL, NHMEX_U_PMON_GLOBAL_EN_ALL);
+}
+
+static void nhmex_uncore_msr_disable_box(struct intel_uncore_box *box)
+{
+	unsigned msr = uncore_msr_box_ctl(box);
+	u64 config;
+
+	if (msr) {
+		rdmsrl(msr, config);
+		config &= ~((1ULL << uncore_num_counters(box)) - 1);
+		/* WBox has a fixed counter */
+		if (uncore_msr_fixed_ctl(box))
+			config &= ~NHMEX_W_PMON_GLOBAL_FIXED_EN;
+		wrmsrl(msr, config);
+	}
+}
+
+static void nhmex_uncore_msr_enable_box(struct intel_uncore_box *box)
+{
+	unsigned msr = uncore_msr_box_ctl(box);
+	u64 config;
+
+	if (msr) {
+		rdmsrl(msr, config);
+		config |= (1ULL << uncore_num_counters(box)) - 1;
+		/* WBox has a fixed counter */
+		if (uncore_msr_fixed_ctl(box))
+			config |= NHMEX_W_PMON_GLOBAL_FIXED_EN;
+		wrmsrl(msr, config);
+	}
+}
+
+static void nhmex_uncore_msr_disable_event(struct intel_uncore_box *box, struct perf_event *event)
+{
+	wrmsrl(event->hw.config_base, 0);
+}
+
+static void nhmex_uncore_msr_enable_event(struct intel_uncore_box *box, struct perf_event *event)
+{
+	struct hw_perf_event *hwc = &event->hw;
+
+	if (hwc->idx >= UNCORE_PMC_IDX_FIXED)
+		wrmsrl(hwc->config_base, NHMEX_PMON_CTL_EN_BIT0);
+	else if (box->pmu->type->event_mask & NHMEX_PMON_CTL_EN_BIT0)
+		wrmsrl(hwc->config_base, hwc->config | NHMEX_PMON_CTL_EN_BIT22);
+	else
+		wrmsrl(hwc->config_base, hwc->config | NHMEX_PMON_CTL_EN_BIT0);
+}
+
+#define NHMEX_UNCORE_OPS_COMMON_INIT()				\
+	.init_box	= nhmex_uncore_msr_init_box,		\
+	.disable_box	= nhmex_uncore_msr_disable_box,		\
+	.enable_box	= nhmex_uncore_msr_enable_box,		\
+	.disable_event	= nhmex_uncore_msr_disable_event,	\
+	.read_counter	= uncore_msr_read_counter
+
+static struct intel_uncore_ops nhmex_uncore_ops = {
+	NHMEX_UNCORE_OPS_COMMON_INIT(),
+	.enable_event	= nhmex_uncore_msr_enable_event,
+};
+
+static struct attribute *nhmex_uncore_ubox_formats_attr[] = {
+	&format_attr_event.attr,
+	&format_attr_edge.attr,
+	NULL,
+};
+
+static struct attribute_group nhmex_uncore_ubox_format_group = {
+	.name		= "format",
+	.attrs		= nhmex_uncore_ubox_formats_attr,
+};
+
+static struct intel_uncore_type nhmex_uncore_ubox = {
+	.name		= "ubox",
+	.num_counters	= 1,
+	.num_boxes	= 1,
+	.perf_ctr_bits	= 48,
+	.event_ctl	= NHMEX_U_MSR_PMON_EV_SEL,
+	.perf_ctr	= NHMEX_U_MSR_PMON_CTR,
+	.event_mask	= NHMEX_U_PMON_RAW_EVENT_MASK,
+	.box_ctl	= NHMEX_U_MSR_PMON_GLOBAL_CTL,
+	.ops		= &nhmex_uncore_ops,
+	.format_group	= &nhmex_uncore_ubox_format_group
+};
+
+static struct attribute *nhmex_uncore_cbox_formats_attr[] = {
+	&format_attr_event.attr,
+	&format_attr_umask.attr,
+	&format_attr_edge.attr,
+	&format_attr_inv.attr,
+	&format_attr_thresh8.attr,
+	NULL,
+};
+
+static struct attribute_group nhmex_uncore_cbox_format_group = {
+	.name = "format",
+	.attrs = nhmex_uncore_cbox_formats_attr,
+};
+
+/* msr offset for each instance of cbox */
+static unsigned nhmex_cbox_msr_offsets[] = {
+	0x0, 0x80, 0x40, 0xc0, 0x20, 0xa0, 0x60, 0xe0, 0x240, 0x2c0,
+};
+
+static struct intel_uncore_type nhmex_uncore_cbox = {
+	.name			= "cbox",
+	.num_counters		= 6,
+	.num_boxes		= 10,
+	.perf_ctr_bits		= 48,
+	.event_ctl		= NHMEX_C0_MSR_PMON_EV_SEL0,
+	.perf_ctr		= NHMEX_C0_MSR_PMON_CTR0,
+	.event_mask		= NHMEX_PMON_RAW_EVENT_MASK,
+	.box_ctl		= NHMEX_C0_MSR_PMON_GLOBAL_CTL,
+	.msr_offsets		= nhmex_cbox_msr_offsets,
+	.pair_ctr_ctl		= 1,
+	.ops			= &nhmex_uncore_ops,
+	.format_group		= &nhmex_uncore_cbox_format_group
+};
+
+static struct uncore_event_desc nhmex_uncore_wbox_events[] = {
+	INTEL_UNCORE_EVENT_DESC(clockticks, "event=0xff,umask=0"),
+	{ /* end: all zeroes */ },
+};
+
+static struct intel_uncore_type nhmex_uncore_wbox = {
+	.name			= "wbox",
+	.num_counters		= 4,
+	.num_boxes		= 1,
+	.perf_ctr_bits		= 48,
+	.event_ctl		= NHMEX_W_MSR_PMON_CNT0,
+	.perf_ctr		= NHMEX_W_MSR_PMON_EVT_SEL0,
+	.fixed_ctr		= NHMEX_W_MSR_PMON_FIXED_CTR,
+	.fixed_ctl		= NHMEX_W_MSR_PMON_FIXED_CTL,
+	.event_mask		= NHMEX_PMON_RAW_EVENT_MASK,
+	.box_ctl		= NHMEX_W_MSR_GLOBAL_CTL,
+	.pair_ctr_ctl		= 1,
+	.event_descs		= nhmex_uncore_wbox_events,
+	.ops			= &nhmex_uncore_ops,
+	.format_group		= &nhmex_uncore_cbox_format_group
+};
+
+static int nhmex_bbox_hw_config(struct intel_uncore_box *box, struct perf_event *event)
+{
+	struct hw_perf_event *hwc = &event->hw;
+	struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
+	struct hw_perf_event_extra *reg2 = &hwc->branch_reg;
+	int ctr, ev_sel;
+
+	ctr = (hwc->config & NHMEX_B_PMON_CTR_MASK) >>
+		NHMEX_B_PMON_CTR_SHIFT;
+	ev_sel = (hwc->config & NHMEX_B_PMON_CTL_EV_SEL_MASK) >>
+		  NHMEX_B_PMON_CTL_EV_SEL_SHIFT;
+
+	/* events that do not use the match/mask registers */
+	if ((ctr == 0 && ev_sel > 0x3) || (ctr == 1 && ev_sel > 0x6) ||
+	    (ctr == 2 && ev_sel != 0x4) || ctr == 3)
+		return 0;
+
+	if (box->pmu->pmu_idx == 0)
+		reg1->reg = NHMEX_B0_MSR_MATCH;
+	else
+		reg1->reg = NHMEX_B1_MSR_MATCH;
+	reg1->idx = 0;
+	reg1->config = event->attr.config1;
+	reg2->config = event->attr.config2;
+	return 0;
+}
+
+static void nhmex_bbox_msr_enable_event(struct intel_uncore_box *box, struct perf_event *event)
+{
+	struct hw_perf_event *hwc = &event->hw;
+	struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
+	struct hw_perf_event_extra *reg2 = &hwc->branch_reg;
+
+	if (reg1->idx != EXTRA_REG_NONE) {
+		wrmsrl(reg1->reg, reg1->config);
+		wrmsrl(reg1->reg + 1, reg2->config);
+	}
+	wrmsrl(hwc->config_base, NHMEX_PMON_CTL_EN_BIT0 |
+		(hwc->config & NHMEX_B_PMON_CTL_EV_SEL_MASK));
+}
+
+/*
+ * The Bbox has 4 counters, but each counter monitors different events.
+ * Use bits 6-7 in the event config to select counter.
+ */
+static struct event_constraint nhmex_uncore_bbox_constraints[] = {
+	EVENT_CONSTRAINT(0 , 1, 0xc0),
+	EVENT_CONSTRAINT(0x40, 2, 0xc0),
+	EVENT_CONSTRAINT(0x80, 4, 0xc0),
+	EVENT_CONSTRAINT(0xc0, 8, 0xc0),
+	EVENT_CONSTRAINT_END,
+};
+
+static struct attribute *nhmex_uncore_bbox_formats_attr[] = {
+	&format_attr_event5.attr,
+	&format_attr_counter.attr,
+	&format_attr_match.attr,
+	&format_attr_mask.attr,
+	NULL,
+};
+
+static struct attribute_group nhmex_uncore_bbox_format_group = {
+	.name = "format",
+	.attrs = nhmex_uncore_bbox_formats_attr,
+};
+
+static struct intel_uncore_ops nhmex_uncore_bbox_ops = {
+	NHMEX_UNCORE_OPS_COMMON_INIT(),
+	.enable_event		= nhmex_bbox_msr_enable_event,
+	.hw_config		= nhmex_bbox_hw_config,
+	.get_constraint		= uncore_get_constraint,
+	.put_constraint		= uncore_put_constraint,
+};
+
+static struct intel_uncore_type nhmex_uncore_bbox = {
+	.name			= "bbox",
+	.num_counters		= 4,
+	.num_boxes		= 2,
+	.perf_ctr_bits		= 48,
+	.event_ctl		= NHMEX_B0_MSR_PMON_CTL0,
+	.perf_ctr		= NHMEX_B0_MSR_PMON_CTR0,
+	.event_mask		= NHMEX_B_PMON_RAW_EVENT_MASK,
+	.box_ctl		= NHMEX_B0_MSR_PMON_GLOBAL_CTL,
+	.msr_offset		= NHMEX_B_MSR_OFFSET,
+	.pair_ctr_ctl		= 1,
+	.num_shared_regs	= 1,
+	.constraints		= nhmex_uncore_bbox_constraints,
+	.ops			= &nhmex_uncore_bbox_ops,
+	.format_group		= &nhmex_uncore_bbox_format_group
+};
+
+static int nhmex_sbox_hw_config(struct intel_uncore_box *box, struct perf_event *event)
+{
+	struct hw_perf_event *hwc = &event->hw;
+	struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
+	struct hw_perf_event_extra *reg2 = &hwc->branch_reg;
+
+	/* only TO_R_PROG_EV event uses the match/mask register */
+	if ((hwc->config & NHMEX_PMON_CTL_EV_SEL_MASK) !=
+	    NHMEX_S_EVENT_TO_R_PROG_EV)
+		return 0;
+
+	if (box->pmu->pmu_idx == 0)
+		reg1->reg = NHMEX_S0_MSR_MM_CFG;
+	else
+		reg1->reg = NHMEX_S1_MSR_MM_CFG;
+	reg1->idx = 0;
+	reg1->config = event->attr.config1;
+	reg2->config = event->attr.config2;
+	return 0;
+}
+
+static void nhmex_sbox_msr_enable_event(struct intel_uncore_box *box, struct perf_event *event)
+{
+	struct hw_perf_event *hwc = &event->hw;
+	struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
+	struct hw_perf_event_extra *reg2 = &hwc->branch_reg;
+
+	if (reg1->idx != EXTRA_REG_NONE) {
+		wrmsrl(reg1->reg, 0);
+		wrmsrl(reg1->reg + 1, reg1->config);
+		wrmsrl(reg1->reg + 2, reg2->config);
+		wrmsrl(reg1->reg, NHMEX_S_PMON_MM_CFG_EN);
+	}
+	wrmsrl(hwc->config_base, hwc->config | NHMEX_PMON_CTL_EN_BIT22);
+}
+
+static struct attribute *nhmex_uncore_sbox_formats_attr[] = {
+	&format_attr_event.attr,
+	&format_attr_umask.attr,
+	&format_attr_edge.attr,
+	&format_attr_inv.attr,
+	&format_attr_thresh8.attr,
+	&format_attr_match.attr,
+	&format_attr_mask.attr,
+	NULL,
+};
+
+static struct attribute_group nhmex_uncore_sbox_format_group = {
+	.name			= "format",
+	.attrs			= nhmex_uncore_sbox_formats_attr,
+};
+
+static struct intel_uncore_ops nhmex_uncore_sbox_ops = {
+	NHMEX_UNCORE_OPS_COMMON_INIT(),
+	.enable_event		= nhmex_sbox_msr_enable_event,
+	.hw_config		= nhmex_sbox_hw_config,
+	.get_constraint		= uncore_get_constraint,
+	.put_constraint		= uncore_put_constraint,
+};
+
+static struct intel_uncore_type nhmex_uncore_sbox = {
+	.name			= "sbox",
+	.num_counters		= 4,
+	.num_boxes		= 2,
+	.perf_ctr_bits		= 48,
+	.event_ctl		= NHMEX_S0_MSR_PMON_CTL0,
+	.perf_ctr		= NHMEX_S0_MSR_PMON_CTR0,
+	.event_mask		= NHMEX_PMON_RAW_EVENT_MASK,
+	.box_ctl		= NHMEX_S0_MSR_PMON_GLOBAL_CTL,
+	.msr_offset		= NHMEX_S_MSR_OFFSET,
+	.pair_ctr_ctl		= 1,
+	.num_shared_regs	= 1,
+	.ops			= &nhmex_uncore_sbox_ops,
+	.format_group		= &nhmex_uncore_sbox_format_group
+};
+
+enum {
+	EXTRA_REG_NHMEX_M_FILTER,
+	EXTRA_REG_NHMEX_M_DSP,
+	EXTRA_REG_NHMEX_M_ISS,
+	EXTRA_REG_NHMEX_M_MAP,
+	EXTRA_REG_NHMEX_M_MSC_THR,
+	EXTRA_REG_NHMEX_M_PGT,
+	EXTRA_REG_NHMEX_M_PLD,
+	EXTRA_REG_NHMEX_M_ZDP_CTL_FVC,
+};
+
+static struct extra_reg nhmex_uncore_mbox_extra_regs[] = {
+	MBOX_INC_SEL_EXTAR_REG(0x0, DSP),
+	MBOX_INC_SEL_EXTAR_REG(0x4, MSC_THR),
+	MBOX_INC_SEL_EXTAR_REG(0x5, MSC_THR),
+	MBOX_INC_SEL_EXTAR_REG(0x9, ISS),
+	/* event 0xa uses two extra registers */
+	MBOX_INC_SEL_EXTAR_REG(0xa, ISS),
+	MBOX_INC_SEL_EXTAR_REG(0xa, PLD),
+	MBOX_INC_SEL_EXTAR_REG(0xb, PLD),
+	/* events 0xd ~ 0x10 use the same extra register */
+	MBOX_INC_SEL_EXTAR_REG(0xd, ZDP_CTL_FVC),
+	MBOX_INC_SEL_EXTAR_REG(0xe, ZDP_CTL_FVC),
+	MBOX_INC_SEL_EXTAR_REG(0xf, ZDP_CTL_FVC),
+	MBOX_INC_SEL_EXTAR_REG(0x10, ZDP_CTL_FVC),
+	MBOX_INC_SEL_EXTAR_REG(0x16, PGT),
+	MBOX_SET_FLAG_SEL_EXTRA_REG(0x0, DSP),
+	MBOX_SET_FLAG_SEL_EXTRA_REG(0x1, ISS),
+	MBOX_SET_FLAG_SEL_EXTRA_REG(0x5, PGT),
+	MBOX_SET_FLAG_SEL_EXTRA_REG(0x6, MAP),
+	EVENT_EXTRA_END
+};
+
+/* Nehalem-EX or Westmere-EX ? */
+static bool uncore_nhmex;
+
+static bool nhmex_mbox_get_shared_reg(struct intel_uncore_box *box, int idx, u64 config)
+{
+	struct intel_uncore_extra_reg *er;
+	unsigned long flags;
+	bool ret = false;
+	u64 mask;
+
+	if (idx < EXTRA_REG_NHMEX_M_ZDP_CTL_FVC) {
+		er = &box->shared_regs[idx];
+		raw_spin_lock_irqsave(&er->lock, flags);
+		if (!atomic_read(&er->ref) || er->config == config) {
+			atomic_inc(&er->ref);
+			er->config = config;
+			ret = true;
+		}
+		raw_spin_unlock_irqrestore(&er->lock, flags);
+
+		return ret;
+	}
+	/*
+	 * The ZDP_CTL_FVC MSR has 4 fields which are used to control
+	 * events 0xd ~ 0x10. Besides these 4 fields, there are additional
+	 * fields which are shared.
+	 */
+	idx -= EXTRA_REG_NHMEX_M_ZDP_CTL_FVC;
+	if (WARN_ON_ONCE(idx >= 4))
+		return false;
+
+	/* mask of the shared fields */
+	if (uncore_nhmex)
+		mask = NHMEX_M_PMON_ZDP_CTL_FVC_MASK;
+	else
+		mask = WSMEX_M_PMON_ZDP_CTL_FVC_MASK;
+	er = &box->shared_regs[EXTRA_REG_NHMEX_M_ZDP_CTL_FVC];
+
+	raw_spin_lock_irqsave(&er->lock, flags);
+	/* add mask of the non-shared field if it's in use */
+	if (__BITS_VALUE(atomic_read(&er->ref), idx, 8)) {
+		if (uncore_nhmex)
+			mask |= NHMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(idx);
+		else
+			mask |= WSMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(idx);
+	}
+
+	if (!atomic_read(&er->ref) || !((er->config ^ config) & mask)) {
+		atomic_add(1 << (idx * 8), &er->ref);
+		if (uncore_nhmex)
+			mask = NHMEX_M_PMON_ZDP_CTL_FVC_MASK |
+				NHMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(idx);
+		else
+			mask = WSMEX_M_PMON_ZDP_CTL_FVC_MASK |
+				WSMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(idx);
+		er->config &= ~mask;
+		er->config |= (config & mask);
+		ret = true;
+	}
+	raw_spin_unlock_irqrestore(&er->lock, flags);
+
+	return ret;
+}
+
+static void nhmex_mbox_put_shared_reg(struct intel_uncore_box *box, int idx)
+{
+	struct intel_uncore_extra_reg *er;
+
+	if (idx < EXTRA_REG_NHMEX_M_ZDP_CTL_FVC) {
+		er = &box->shared_regs[idx];
+		atomic_dec(&er->ref);
+		return;
+	}
+
+	idx -= EXTRA_REG_NHMEX_M_ZDP_CTL_FVC;
+	er = &box->shared_regs[EXTRA_REG_NHMEX_M_ZDP_CTL_FVC];
+	atomic_sub(1 << (idx * 8), &er->ref);
+}
+
+static u64 nhmex_mbox_alter_er(struct perf_event *event, int new_idx, bool modify)
+{
+	struct hw_perf_event *hwc = &event->hw;
+	struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
+	u64 idx, orig_idx = __BITS_VALUE(reg1->idx, 0, 8);
+	u64 config = reg1->config;
+
+	/* get the non-shared control bits and shift them */
+	idx = orig_idx - EXTRA_REG_NHMEX_M_ZDP_CTL_FVC;
+	if (uncore_nhmex)
+		config &= NHMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(idx);
+	else
+		config &= WSMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(idx);
+	if (new_idx > orig_idx) {
+		idx = new_idx - orig_idx;
+		config <<= 3 * idx;
+	} else {
+		idx = orig_idx - new_idx;
+		config >>= 3 * idx;
+	}
+
+	/* add the shared control bits back */
+	if (uncore_nhmex)
+		config |= NHMEX_M_PMON_ZDP_CTL_FVC_MASK & reg1->config;
+	else
+		config |= WSMEX_M_PMON_ZDP_CTL_FVC_MASK & reg1->config;
+	config |= NHMEX_M_PMON_ZDP_CTL_FVC_MASK & reg1->config;
+	if (modify) {
+		/* adjust the main event selector */
+		if (new_idx > orig_idx)
+			hwc->config += idx << NHMEX_M_PMON_CTL_INC_SEL_SHIFT;
+		else
+			hwc->config -= idx << NHMEX_M_PMON_CTL_INC_SEL_SHIFT;
+		reg1->config = config;
+		reg1->idx = ~0xff | new_idx;
+	}
+	return config;
+}
+
+static struct event_constraint *
+nhmex_mbox_get_constraint(struct intel_uncore_box *box, struct perf_event *event)
+{
+	struct hw_perf_event_extra *reg1 = &event->hw.extra_reg;
+	struct hw_perf_event_extra *reg2 = &event->hw.branch_reg;
+	int i, idx[2], alloc = 0;
+	u64 config1 = reg1->config;
+
+	idx[0] = __BITS_VALUE(reg1->idx, 0, 8);
+	idx[1] = __BITS_VALUE(reg1->idx, 1, 8);
+again:
+	for (i = 0; i < 2; i++) {
+		if (!uncore_box_is_fake(box) && (reg1->alloc & (0x1 << i)))
+			idx[i] = 0xff;
+
+		if (idx[i] == 0xff)
+			continue;
+
+		if (!nhmex_mbox_get_shared_reg(box, idx[i],
+				__BITS_VALUE(config1, i, 32)))
+			goto fail;
+		alloc |= (0x1 << i);
+	}
+
+	/* for the match/mask registers */
+	if (reg2->idx != EXTRA_REG_NONE &&
+	    (uncore_box_is_fake(box) || !reg2->alloc) &&
+	    !nhmex_mbox_get_shared_reg(box, reg2->idx, reg2->config))
+		goto fail;
+
+	/*
+	 * If it's a fake box -- as per validate_{group,event}() we
+	 * shouldn't touch event state and we can avoid doing so
+	 * since both will only call get_event_constraints() once
+	 * on each event, this avoids the need for reg->alloc.
+	 */
+	if (!uncore_box_is_fake(box)) {
+		if (idx[0] != 0xff && idx[0] != __BITS_VALUE(reg1->idx, 0, 8))
+			nhmex_mbox_alter_er(event, idx[0], true);
+		reg1->alloc |= alloc;
+		if (reg2->idx != EXTRA_REG_NONE)
+			reg2->alloc = 1;
+	}
+	return NULL;
+fail:
+	if (idx[0] != 0xff && !(alloc & 0x1) &&
+	    idx[0] >= EXTRA_REG_NHMEX_M_ZDP_CTL_FVC) {
+		/*
+		 * events 0xd ~ 0x10 are functional identical, but are
+		 * controlled by different fields in the ZDP_CTL_FVC
+		 * register. If we failed to take one field, try the
+		 * rest 3 choices.
+		 */
+		BUG_ON(__BITS_VALUE(reg1->idx, 1, 8) != 0xff);
+		idx[0] -= EXTRA_REG_NHMEX_M_ZDP_CTL_FVC;
+		idx[0] = (idx[0] + 1) % 4;
+		idx[0] += EXTRA_REG_NHMEX_M_ZDP_CTL_FVC;
+		if (idx[0] != __BITS_VALUE(reg1->idx, 0, 8)) {
+			config1 = nhmex_mbox_alter_er(event, idx[0], false);
+			goto again;
+		}
+	}
+
+	if (alloc & 0x1)
+		nhmex_mbox_put_shared_reg(box, idx[0]);
+	if (alloc & 0x2)
+		nhmex_mbox_put_shared_reg(box, idx[1]);
+	return &uncore_constraint_empty;
+}
+
+static void nhmex_mbox_put_constraint(struct intel_uncore_box *box, struct perf_event *event)
+{
+	struct hw_perf_event_extra *reg1 = &event->hw.extra_reg;
+	struct hw_perf_event_extra *reg2 = &event->hw.branch_reg;
+
+	if (uncore_box_is_fake(box))
+		return;
+
+	if (reg1->alloc & 0x1)
+		nhmex_mbox_put_shared_reg(box, __BITS_VALUE(reg1->idx, 0, 8));
+	if (reg1->alloc & 0x2)
+		nhmex_mbox_put_shared_reg(box, __BITS_VALUE(reg1->idx, 1, 8));
+	reg1->alloc = 0;
+
+	if (reg2->alloc) {
+		nhmex_mbox_put_shared_reg(box, reg2->idx);
+		reg2->alloc = 0;
+	}
+}
+
+static int nhmex_mbox_extra_reg_idx(struct extra_reg *er)
+{
+	if (er->idx < EXTRA_REG_NHMEX_M_ZDP_CTL_FVC)
+		return er->idx;
+	return er->idx + (er->event >> NHMEX_M_PMON_CTL_INC_SEL_SHIFT) - 0xd;
+}
+
+static int nhmex_mbox_hw_config(struct intel_uncore_box *box, struct perf_event *event)
+{
+	struct intel_uncore_type *type = box->pmu->type;
+	struct hw_perf_event_extra *reg1 = &event->hw.extra_reg;
+	struct hw_perf_event_extra *reg2 = &event->hw.branch_reg;
+	struct extra_reg *er;
+	unsigned msr;
+	int reg_idx = 0;
+	/*
+	 * The mbox events may require 2 extra MSRs at the most. But only
+	 * the lower 32 bits in these MSRs are significant, so we can use
+	 * config1 to pass two MSRs' config.
+	 */
+	for (er = nhmex_uncore_mbox_extra_regs; er->msr; er++) {
+		if (er->event != (event->hw.config & er->config_mask))
+			continue;
+		if (event->attr.config1 & ~er->valid_mask)
+			return -EINVAL;
+
+		msr = er->msr + type->msr_offset * box->pmu->pmu_idx;
+		if (WARN_ON_ONCE(msr >= 0xffff || er->idx >= 0xff))
+			return -EINVAL;
+
+		/* always use the 32~63 bits to pass the PLD config */
+		if (er->idx == EXTRA_REG_NHMEX_M_PLD)
+			reg_idx = 1;
+		else if (WARN_ON_ONCE(reg_idx > 0))
+			return -EINVAL;
+
+		reg1->idx &= ~(0xff << (reg_idx * 8));
+		reg1->reg &= ~(0xffff << (reg_idx * 16));
+		reg1->idx |= nhmex_mbox_extra_reg_idx(er) << (reg_idx * 8);
+		reg1->reg |= msr << (reg_idx * 16);
+		reg1->config = event->attr.config1;
+		reg_idx++;
+	}
+	/*
+	 * The mbox only provides ability to perform address matching
+	 * for the PLD events.
+	 */
+	if (reg_idx == 2) {
+		reg2->idx = EXTRA_REG_NHMEX_M_FILTER;
+		if (event->attr.config2 & NHMEX_M_PMON_MM_CFG_EN)
+			reg2->config = event->attr.config2;
+		else
+			reg2->config = ~0ULL;
+		if (box->pmu->pmu_idx == 0)
+			reg2->reg = NHMEX_M0_MSR_PMU_MM_CFG;
+		else
+			reg2->reg = NHMEX_M1_MSR_PMU_MM_CFG;
+	}
+	return 0;
+}
+
+static u64 nhmex_mbox_shared_reg_config(struct intel_uncore_box *box, int idx)
+{
+	struct intel_uncore_extra_reg *er;
+	unsigned long flags;
+	u64 config;
+
+	if (idx < EXTRA_REG_NHMEX_M_ZDP_CTL_FVC)
+		return box->shared_regs[idx].config;
+
+	er = &box->shared_regs[EXTRA_REG_NHMEX_M_ZDP_CTL_FVC];
+	raw_spin_lock_irqsave(&er->lock, flags);
+	config = er->config;
+	raw_spin_unlock_irqrestore(&er->lock, flags);
+	return config;
+}
+
+static void nhmex_mbox_msr_enable_event(struct intel_uncore_box *box, struct perf_event *event)
+{
+	struct hw_perf_event *hwc = &event->hw;
+	struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
+	struct hw_perf_event_extra *reg2 = &hwc->branch_reg;
+	int idx;
+
+	idx = __BITS_VALUE(reg1->idx, 0, 8);
+	if (idx != 0xff)
+		wrmsrl(__BITS_VALUE(reg1->reg, 0, 16),
+			nhmex_mbox_shared_reg_config(box, idx));
+	idx = __BITS_VALUE(reg1->idx, 1, 8);
+	if (idx != 0xff)
+		wrmsrl(__BITS_VALUE(reg1->reg, 1, 16),
+			nhmex_mbox_shared_reg_config(box, idx));
+
+	if (reg2->idx != EXTRA_REG_NONE) {
+		wrmsrl(reg2->reg, 0);
+		if (reg2->config != ~0ULL) {
+			wrmsrl(reg2->reg + 1,
+				reg2->config & NHMEX_M_PMON_ADDR_MATCH_MASK);
+			wrmsrl(reg2->reg + 2, NHMEX_M_PMON_ADDR_MASK_MASK &
+				(reg2->config >> NHMEX_M_PMON_ADDR_MASK_SHIFT));
+			wrmsrl(reg2->reg, NHMEX_M_PMON_MM_CFG_EN);
+		}
+	}
+
+	wrmsrl(hwc->config_base, hwc->config | NHMEX_PMON_CTL_EN_BIT0);
+}
+
+DEFINE_UNCORE_FORMAT_ATTR(count_mode,		count_mode,	"config:2-3");
+DEFINE_UNCORE_FORMAT_ATTR(storage_mode,		storage_mode,	"config:4-5");
+DEFINE_UNCORE_FORMAT_ATTR(wrap_mode,		wrap_mode,	"config:6");
+DEFINE_UNCORE_FORMAT_ATTR(flag_mode,		flag_mode,	"config:7");
+DEFINE_UNCORE_FORMAT_ATTR(inc_sel,		inc_sel,	"config:9-13");
+DEFINE_UNCORE_FORMAT_ATTR(set_flag_sel,		set_flag_sel,	"config:19-21");
+DEFINE_UNCORE_FORMAT_ATTR(filter_cfg_en,	filter_cfg_en,	"config2:63");
+DEFINE_UNCORE_FORMAT_ATTR(filter_match,		filter_match,	"config2:0-33");
+DEFINE_UNCORE_FORMAT_ATTR(filter_mask,		filter_mask,	"config2:34-61");
+DEFINE_UNCORE_FORMAT_ATTR(dsp,			dsp,		"config1:0-31");
+DEFINE_UNCORE_FORMAT_ATTR(thr,			thr,		"config1:0-31");
+DEFINE_UNCORE_FORMAT_ATTR(fvc,			fvc,		"config1:0-31");
+DEFINE_UNCORE_FORMAT_ATTR(pgt,			pgt,		"config1:0-31");
+DEFINE_UNCORE_FORMAT_ATTR(map,			map,		"config1:0-31");
+DEFINE_UNCORE_FORMAT_ATTR(iss,			iss,		"config1:0-31");
+DEFINE_UNCORE_FORMAT_ATTR(pld,			pld,		"config1:32-63");
+
+static struct attribute *nhmex_uncore_mbox_formats_attr[] = {
+	&format_attr_count_mode.attr,
+	&format_attr_storage_mode.attr,
+	&format_attr_wrap_mode.attr,
+	&format_attr_flag_mode.attr,
+	&format_attr_inc_sel.attr,
+	&format_attr_set_flag_sel.attr,
+	&format_attr_filter_cfg_en.attr,
+	&format_attr_filter_match.attr,
+	&format_attr_filter_mask.attr,
+	&format_attr_dsp.attr,
+	&format_attr_thr.attr,
+	&format_attr_fvc.attr,
+	&format_attr_pgt.attr,
+	&format_attr_map.attr,
+	&format_attr_iss.attr,
+	&format_attr_pld.attr,
+	NULL,
+};
+
+static struct attribute_group nhmex_uncore_mbox_format_group = {
+	.name		= "format",
+	.attrs		= nhmex_uncore_mbox_formats_attr,
+};
+
+static struct uncore_event_desc nhmex_uncore_mbox_events[] = {
+	INTEL_UNCORE_EVENT_DESC(bbox_cmds_read, "inc_sel=0xd,fvc=0x2800"),
+	INTEL_UNCORE_EVENT_DESC(bbox_cmds_write, "inc_sel=0xd,fvc=0x2820"),
+	{ /* end: all zeroes */ },
+};
+
+static struct uncore_event_desc wsmex_uncore_mbox_events[] = {
+	INTEL_UNCORE_EVENT_DESC(bbox_cmds_read, "inc_sel=0xd,fvc=0x5000"),
+	INTEL_UNCORE_EVENT_DESC(bbox_cmds_write, "inc_sel=0xd,fvc=0x5040"),
+	{ /* end: all zeroes */ },
+};
+
+static struct intel_uncore_ops nhmex_uncore_mbox_ops = {
+	NHMEX_UNCORE_OPS_COMMON_INIT(),
+	.enable_event	= nhmex_mbox_msr_enable_event,
+	.hw_config	= nhmex_mbox_hw_config,
+	.get_constraint	= nhmex_mbox_get_constraint,
+	.put_constraint	= nhmex_mbox_put_constraint,
+};
+
+static struct intel_uncore_type nhmex_uncore_mbox = {
+	.name			= "mbox",
+	.num_counters		= 6,
+	.num_boxes		= 2,
+	.perf_ctr_bits		= 48,
+	.event_ctl		= NHMEX_M0_MSR_PMU_CTL0,
+	.perf_ctr		= NHMEX_M0_MSR_PMU_CNT0,
+	.event_mask		= NHMEX_M_PMON_RAW_EVENT_MASK,
+	.box_ctl		= NHMEX_M0_MSR_GLOBAL_CTL,
+	.msr_offset		= NHMEX_M_MSR_OFFSET,
+	.pair_ctr_ctl		= 1,
+	.num_shared_regs	= 8,
+	.event_descs		= nhmex_uncore_mbox_events,
+	.ops			= &nhmex_uncore_mbox_ops,
+	.format_group		= &nhmex_uncore_mbox_format_group,
+};
+
+static void nhmex_rbox_alter_er(struct intel_uncore_box *box, struct perf_event *event)
+{
+	struct hw_perf_event *hwc = &event->hw;
+	struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
+
+	/* adjust the main event selector and extra register index */
+	if (reg1->idx % 2) {
+		reg1->idx--;
+		hwc->config -= 1 << NHMEX_R_PMON_CTL_EV_SEL_SHIFT;
+	} else {
+		reg1->idx++;
+		hwc->config += 1 << NHMEX_R_PMON_CTL_EV_SEL_SHIFT;
+	}
+
+	/* adjust extra register config */
+	switch (reg1->idx % 6) {
+	case 2:
+		/* shift the 8~15 bits to the 0~7 bits */
+		reg1->config >>= 8;
+		break;
+	case 3:
+		/* shift the 0~7 bits to the 8~15 bits */
+		reg1->config <<= 8;
+		break;
+	}
+}
+
+/*
+ * Each rbox has 4 event set which monitor PQI port 0~3 or 4~7.
+ * An event set consists of 6 events, the 3rd and 4th events in
+ * an event set use the same extra register. So an event set uses
+ * 5 extra registers.
+ */
+static struct event_constraint *
+nhmex_rbox_get_constraint(struct intel_uncore_box *box, struct perf_event *event)
+{
+	struct hw_perf_event *hwc = &event->hw;
+	struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
+	struct hw_perf_event_extra *reg2 = &hwc->branch_reg;
+	struct intel_uncore_extra_reg *er;
+	unsigned long flags;
+	int idx, er_idx;
+	u64 config1;
+	bool ok = false;
+
+	if (!uncore_box_is_fake(box) && reg1->alloc)
+		return NULL;
+
+	idx = reg1->idx % 6;
+	config1 = reg1->config;
+again:
+	er_idx = idx;
+	/* the 3rd and 4th events use the same extra register */
+	if (er_idx > 2)
+		er_idx--;
+	er_idx += (reg1->idx / 6) * 5;
+
+	er = &box->shared_regs[er_idx];
+	raw_spin_lock_irqsave(&er->lock, flags);
+	if (idx < 2) {
+		if (!atomic_read(&er->ref) || er->config == reg1->config) {
+			atomic_inc(&er->ref);
+			er->config = reg1->config;
+			ok = true;
+		}
+	} else if (idx == 2 || idx == 3) {
+		/*
+		 * these two events use different fields in a extra register,
+		 * the 0~7 bits and the 8~15 bits respectively.
+		 */
+		u64 mask = 0xff << ((idx - 2) * 8);
+		if (!__BITS_VALUE(atomic_read(&er->ref), idx - 2, 8) ||
+				!((er->config ^ config1) & mask)) {
+			atomic_add(1 << ((idx - 2) * 8), &er->ref);
+			er->config &= ~mask;
+			er->config |= config1 & mask;
+			ok = true;
+		}
+	} else {
+		if (!atomic_read(&er->ref) ||
+				(er->config == (hwc->config >> 32) &&
+				 er->config1 == reg1->config &&
+				 er->config2 == reg2->config)) {
+			atomic_inc(&er->ref);
+			er->config = (hwc->config >> 32);
+			er->config1 = reg1->config;
+			er->config2 = reg2->config;
+			ok = true;
+		}
+	}
+	raw_spin_unlock_irqrestore(&er->lock, flags);
+
+	if (!ok) {
+		/*
+		 * The Rbox events are always in pairs. The paired
+		 * events are functional identical, but use different
+		 * extra registers. If we failed to take an extra
+		 * register, try the alternative.
+		 */
+		idx ^= 1;
+		if (idx != reg1->idx % 6) {
+			if (idx == 2)
+				config1 >>= 8;
+			else if (idx == 3)
+				config1 <<= 8;
+			goto again;
+		}
+	} else {
+		if (!uncore_box_is_fake(box)) {
+			if (idx != reg1->idx % 6)
+				nhmex_rbox_alter_er(box, event);
+			reg1->alloc = 1;
+		}
+		return NULL;
+	}
+	return &uncore_constraint_empty;
+}
+
+static void nhmex_rbox_put_constraint(struct intel_uncore_box *box, struct perf_event *event)
+{
+	struct intel_uncore_extra_reg *er;
+	struct hw_perf_event_extra *reg1 = &event->hw.extra_reg;
+	int idx, er_idx;
+
+	if (uncore_box_is_fake(box) || !reg1->alloc)
+		return;
+
+	idx = reg1->idx % 6;
+	er_idx = idx;
+	if (er_idx > 2)
+		er_idx--;
+	er_idx += (reg1->idx / 6) * 5;
+
+	er = &box->shared_regs[er_idx];
+	if (idx == 2 || idx == 3)
+		atomic_sub(1 << ((idx - 2) * 8), &er->ref);
+	else
+		atomic_dec(&er->ref);
+
+	reg1->alloc = 0;
+}
+
+static int nhmex_rbox_hw_config(struct intel_uncore_box *box, struct perf_event *event)
+{
+	struct hw_perf_event *hwc = &event->hw;
+	struct hw_perf_event_extra *reg1 = &event->hw.extra_reg;
+	struct hw_perf_event_extra *reg2 = &event->hw.branch_reg;
+	int idx;
+
+	idx = (event->hw.config & NHMEX_R_PMON_CTL_EV_SEL_MASK) >>
+		NHMEX_R_PMON_CTL_EV_SEL_SHIFT;
+	if (idx >= 0x18)
+		return -EINVAL;
+
+	reg1->idx = idx;
+	reg1->config = event->attr.config1;
+
+	switch (idx % 6) {
+	case 4:
+	case 5:
+		hwc->config |= event->attr.config & (~0ULL << 32);
+		reg2->config = event->attr.config2;
+		break;
+	}
+	return 0;
+}
+
+static void nhmex_rbox_msr_enable_event(struct intel_uncore_box *box, struct perf_event *event)
+{
+	struct hw_perf_event *hwc = &event->hw;
+	struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
+	struct hw_perf_event_extra *reg2 = &hwc->branch_reg;
+	int idx, port;
+
+	idx = reg1->idx;
+	port = idx / 6 + box->pmu->pmu_idx * 4;
+
+	switch (idx % 6) {
+	case 0:
+		wrmsrl(NHMEX_R_MSR_PORTN_IPERF_CFG0(port), reg1->config);
+		break;
+	case 1:
+		wrmsrl(NHMEX_R_MSR_PORTN_IPERF_CFG1(port), reg1->config);
+		break;
+	case 2:
+	case 3:
+		wrmsrl(NHMEX_R_MSR_PORTN_QLX_CFG(port),
+			uncore_shared_reg_config(box, 2 + (idx / 6) * 5));
+		break;
+	case 4:
+		wrmsrl(NHMEX_R_MSR_PORTN_XBR_SET1_MM_CFG(port),
+			hwc->config >> 32);
+		wrmsrl(NHMEX_R_MSR_PORTN_XBR_SET1_MATCH(port), reg1->config);
+		wrmsrl(NHMEX_R_MSR_PORTN_XBR_SET1_MASK(port), reg2->config);
+		break;
+	case 5:
+		wrmsrl(NHMEX_R_MSR_PORTN_XBR_SET2_MM_CFG(port),
+			hwc->config >> 32);
+		wrmsrl(NHMEX_R_MSR_PORTN_XBR_SET2_MATCH(port), reg1->config);
+		wrmsrl(NHMEX_R_MSR_PORTN_XBR_SET2_MASK(port), reg2->config);
+		break;
+	}
+
+	wrmsrl(hwc->config_base, NHMEX_PMON_CTL_EN_BIT0 |
+		(hwc->config & NHMEX_R_PMON_CTL_EV_SEL_MASK));
+}
+
+DEFINE_UNCORE_FORMAT_ATTR(xbr_mm_cfg, xbr_mm_cfg, "config:32-63");
+DEFINE_UNCORE_FORMAT_ATTR(xbr_match, xbr_match, "config1:0-63");
+DEFINE_UNCORE_FORMAT_ATTR(xbr_mask, xbr_mask, "config2:0-63");
+DEFINE_UNCORE_FORMAT_ATTR(qlx_cfg, qlx_cfg, "config1:0-15");
+DEFINE_UNCORE_FORMAT_ATTR(iperf_cfg, iperf_cfg, "config1:0-31");
+
+static struct attribute *nhmex_uncore_rbox_formats_attr[] = {
+	&format_attr_event5.attr,
+	&format_attr_xbr_mm_cfg.attr,
+	&format_attr_xbr_match.attr,
+	&format_attr_xbr_mask.attr,
+	&format_attr_qlx_cfg.attr,
+	&format_attr_iperf_cfg.attr,
+	NULL,
+};
+
+static struct attribute_group nhmex_uncore_rbox_format_group = {
+	.name = "format",
+	.attrs = nhmex_uncore_rbox_formats_attr,
+};
+
+static struct uncore_event_desc nhmex_uncore_rbox_events[] = {
+	INTEL_UNCORE_EVENT_DESC(qpi0_flit_send,		"event=0x0,iperf_cfg=0x80000000"),
+	INTEL_UNCORE_EVENT_DESC(qpi1_filt_send,		"event=0x6,iperf_cfg=0x80000000"),
+	INTEL_UNCORE_EVENT_DESC(qpi0_idle_filt,		"event=0x0,iperf_cfg=0x40000000"),
+	INTEL_UNCORE_EVENT_DESC(qpi1_idle_filt,		"event=0x6,iperf_cfg=0x40000000"),
+	INTEL_UNCORE_EVENT_DESC(qpi0_date_response,	"event=0x0,iperf_cfg=0xc4"),
+	INTEL_UNCORE_EVENT_DESC(qpi1_date_response,	"event=0x6,iperf_cfg=0xc4"),
+	{ /* end: all zeroes */ },
+};
+
+static struct intel_uncore_ops nhmex_uncore_rbox_ops = {
+	NHMEX_UNCORE_OPS_COMMON_INIT(),
+	.enable_event		= nhmex_rbox_msr_enable_event,
+	.hw_config		= nhmex_rbox_hw_config,
+	.get_constraint		= nhmex_rbox_get_constraint,
+	.put_constraint		= nhmex_rbox_put_constraint,
+};
+
+static struct intel_uncore_type nhmex_uncore_rbox = {
+	.name			= "rbox",
+	.num_counters		= 8,
+	.num_boxes		= 2,
+	.perf_ctr_bits		= 48,
+	.event_ctl		= NHMEX_R_MSR_PMON_CTL0,
+	.perf_ctr		= NHMEX_R_MSR_PMON_CNT0,
+	.event_mask		= NHMEX_R_PMON_RAW_EVENT_MASK,
+	.box_ctl		= NHMEX_R_MSR_GLOBAL_CTL,
+	.msr_offset		= NHMEX_R_MSR_OFFSET,
+	.pair_ctr_ctl		= 1,
+	.num_shared_regs	= 20,
+	.event_descs		= nhmex_uncore_rbox_events,
+	.ops			= &nhmex_uncore_rbox_ops,
+	.format_group		= &nhmex_uncore_rbox_format_group
+};
+
+static struct intel_uncore_type *nhmex_msr_uncores[] = {
+	&nhmex_uncore_ubox,
+	&nhmex_uncore_cbox,
+	&nhmex_uncore_bbox,
+	&nhmex_uncore_sbox,
+	&nhmex_uncore_mbox,
+	&nhmex_uncore_rbox,
+	&nhmex_uncore_wbox,
+	NULL,
+};
+
+void nhmex_uncore_cpu_init(void)
+{
+	if (boot_cpu_data.x86_model == 46)
+		uncore_nhmex = true;
+	else
+		nhmex_uncore_mbox.event_descs = wsmex_uncore_mbox_events;
+	if (nhmex_uncore_cbox.num_boxes > boot_cpu_data.x86_max_cores)
+		nhmex_uncore_cbox.num_boxes = boot_cpu_data.x86_max_cores;
+	uncore_msr_uncores = nhmex_msr_uncores;
+}
+/* end of Nehalem-EX uncore support */
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore_snb.c b/arch/x86/kernel/cpu/perf_event_intel_uncore_snb.c
new file mode 100644
index 00000000000000..e0e934c8ee771e
--- /dev/null
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore_snb.c
@@ -0,0 +1,603 @@
+/* Nehalem/SandBridge/Haswell uncore support */
+#include "perf_event_intel_uncore.h"
+
+/* SNB event control */
+#define SNB_UNC_CTL_EV_SEL_MASK			0x000000ff
+#define SNB_UNC_CTL_UMASK_MASK			0x0000ff00
+#define SNB_UNC_CTL_EDGE_DET			(1 << 18)
+#define SNB_UNC_CTL_EN				(1 << 22)
+#define SNB_UNC_CTL_INVERT			(1 << 23)
+#define SNB_UNC_CTL_CMASK_MASK			0x1f000000
+#define NHM_UNC_CTL_CMASK_MASK			0xff000000
+#define NHM_UNC_FIXED_CTR_CTL_EN		(1 << 0)
+
+#define SNB_UNC_RAW_EVENT_MASK			(SNB_UNC_CTL_EV_SEL_MASK | \
+						 SNB_UNC_CTL_UMASK_MASK | \
+						 SNB_UNC_CTL_EDGE_DET | \
+						 SNB_UNC_CTL_INVERT | \
+						 SNB_UNC_CTL_CMASK_MASK)
+
+#define NHM_UNC_RAW_EVENT_MASK			(SNB_UNC_CTL_EV_SEL_MASK | \
+						 SNB_UNC_CTL_UMASK_MASK | \
+						 SNB_UNC_CTL_EDGE_DET | \
+						 SNB_UNC_CTL_INVERT | \
+						 NHM_UNC_CTL_CMASK_MASK)
+
+/* SNB global control register */
+#define SNB_UNC_PERF_GLOBAL_CTL                 0x391
+#define SNB_UNC_FIXED_CTR_CTRL                  0x394
+#define SNB_UNC_FIXED_CTR                       0x395
+
+/* SNB uncore global control */
+#define SNB_UNC_GLOBAL_CTL_CORE_ALL             ((1 << 4) - 1)
+#define SNB_UNC_GLOBAL_CTL_EN                   (1 << 29)
+
+/* SNB Cbo register */
+#define SNB_UNC_CBO_0_PERFEVTSEL0               0x700
+#define SNB_UNC_CBO_0_PER_CTR0                  0x706
+#define SNB_UNC_CBO_MSR_OFFSET                  0x10
+
+/* NHM global control register */
+#define NHM_UNC_PERF_GLOBAL_CTL                 0x391
+#define NHM_UNC_FIXED_CTR                       0x394
+#define NHM_UNC_FIXED_CTR_CTRL                  0x395
+
+/* NHM uncore global control */
+#define NHM_UNC_GLOBAL_CTL_EN_PC_ALL            ((1ULL << 8) - 1)
+#define NHM_UNC_GLOBAL_CTL_EN_FC                (1ULL << 32)
+
+/* NHM uncore register */
+#define NHM_UNC_PERFEVTSEL0                     0x3c0
+#define NHM_UNC_UNCORE_PMC0                     0x3b0
+
+DEFINE_UNCORE_FORMAT_ATTR(event, event, "config:0-7");
+DEFINE_UNCORE_FORMAT_ATTR(umask, umask, "config:8-15");
+DEFINE_UNCORE_FORMAT_ATTR(edge, edge, "config:18");
+DEFINE_UNCORE_FORMAT_ATTR(inv, inv, "config:23");
+DEFINE_UNCORE_FORMAT_ATTR(cmask5, cmask, "config:24-28");
+DEFINE_UNCORE_FORMAT_ATTR(cmask8, cmask, "config:24-31");
+
+/* Sandy Bridge uncore support */
+static void snb_uncore_msr_enable_event(struct intel_uncore_box *box, struct perf_event *event)
+{
+	struct hw_perf_event *hwc = &event->hw;
+
+	if (hwc->idx < UNCORE_PMC_IDX_FIXED)
+		wrmsrl(hwc->config_base, hwc->config | SNB_UNC_CTL_EN);
+	else
+		wrmsrl(hwc->config_base, SNB_UNC_CTL_EN);
+}
+
+static void snb_uncore_msr_disable_event(struct intel_uncore_box *box, struct perf_event *event)
+{
+	wrmsrl(event->hw.config_base, 0);
+}
+
+static void snb_uncore_msr_init_box(struct intel_uncore_box *box)
+{
+	if (box->pmu->pmu_idx == 0) {
+		wrmsrl(SNB_UNC_PERF_GLOBAL_CTL,
+			SNB_UNC_GLOBAL_CTL_EN | SNB_UNC_GLOBAL_CTL_CORE_ALL);
+	}
+}
+
+static struct uncore_event_desc snb_uncore_events[] = {
+	INTEL_UNCORE_EVENT_DESC(clockticks, "event=0xff,umask=0x00"),
+	{ /* end: all zeroes */ },
+};
+
+static struct attribute *snb_uncore_formats_attr[] = {
+	&format_attr_event.attr,
+	&format_attr_umask.attr,
+	&format_attr_edge.attr,
+	&format_attr_inv.attr,
+	&format_attr_cmask5.attr,
+	NULL,
+};
+
+static struct attribute_group snb_uncore_format_group = {
+	.name		= "format",
+	.attrs		= snb_uncore_formats_attr,
+};
+
+static struct intel_uncore_ops snb_uncore_msr_ops = {
+	.init_box	= snb_uncore_msr_init_box,
+	.disable_event	= snb_uncore_msr_disable_event,
+	.enable_event	= snb_uncore_msr_enable_event,
+	.read_counter	= uncore_msr_read_counter,
+};
+
+static struct event_constraint snb_uncore_cbox_constraints[] = {
+	UNCORE_EVENT_CONSTRAINT(0x80, 0x1),
+	UNCORE_EVENT_CONSTRAINT(0x83, 0x1),
+	EVENT_CONSTRAINT_END
+};
+
+static struct intel_uncore_type snb_uncore_cbox = {
+	.name		= "cbox",
+	.num_counters   = 2,
+	.num_boxes	= 4,
+	.perf_ctr_bits	= 44,
+	.fixed_ctr_bits	= 48,
+	.perf_ctr	= SNB_UNC_CBO_0_PER_CTR0,
+	.event_ctl	= SNB_UNC_CBO_0_PERFEVTSEL0,
+	.fixed_ctr	= SNB_UNC_FIXED_CTR,
+	.fixed_ctl	= SNB_UNC_FIXED_CTR_CTRL,
+	.single_fixed	= 1,
+	.event_mask	= SNB_UNC_RAW_EVENT_MASK,
+	.msr_offset	= SNB_UNC_CBO_MSR_OFFSET,
+	.constraints	= snb_uncore_cbox_constraints,
+	.ops		= &snb_uncore_msr_ops,
+	.format_group	= &snb_uncore_format_group,
+	.event_descs	= snb_uncore_events,
+};
+
+static struct intel_uncore_type *snb_msr_uncores[] = {
+	&snb_uncore_cbox,
+	NULL,
+};
+
+void snb_uncore_cpu_init(void)
+{
+	uncore_msr_uncores = snb_msr_uncores;
+	if (snb_uncore_cbox.num_boxes > boot_cpu_data.x86_max_cores)
+		snb_uncore_cbox.num_boxes = boot_cpu_data.x86_max_cores;
+}
+
+enum {
+	SNB_PCI_UNCORE_IMC,
+};
+
+static struct uncore_event_desc snb_uncore_imc_events[] = {
+	INTEL_UNCORE_EVENT_DESC(data_reads,  "event=0x01"),
+	INTEL_UNCORE_EVENT_DESC(data_reads.scale, "6.103515625e-5"),
+	INTEL_UNCORE_EVENT_DESC(data_reads.unit, "MiB"),
+
+	INTEL_UNCORE_EVENT_DESC(data_writes, "event=0x02"),
+	INTEL_UNCORE_EVENT_DESC(data_writes.scale, "6.103515625e-5"),
+	INTEL_UNCORE_EVENT_DESC(data_writes.unit, "MiB"),
+
+	{ /* end: all zeroes */ },
+};
+
+#define SNB_UNCORE_PCI_IMC_EVENT_MASK		0xff
+#define SNB_UNCORE_PCI_IMC_BAR_OFFSET		0x48
+
+/* page size multiple covering all config regs */
+#define SNB_UNCORE_PCI_IMC_MAP_SIZE		0x6000
+
+#define SNB_UNCORE_PCI_IMC_DATA_READS		0x1
+#define SNB_UNCORE_PCI_IMC_DATA_READS_BASE	0x5050
+#define SNB_UNCORE_PCI_IMC_DATA_WRITES		0x2
+#define SNB_UNCORE_PCI_IMC_DATA_WRITES_BASE	0x5054
+#define SNB_UNCORE_PCI_IMC_CTR_BASE		SNB_UNCORE_PCI_IMC_DATA_READS_BASE
+
+static struct attribute *snb_uncore_imc_formats_attr[] = {
+	&format_attr_event.attr,
+	NULL,
+};
+
+static struct attribute_group snb_uncore_imc_format_group = {
+	.name = "format",
+	.attrs = snb_uncore_imc_formats_attr,
+};
+
+static void snb_uncore_imc_init_box(struct intel_uncore_box *box)
+{
+	struct pci_dev *pdev = box->pci_dev;
+	int where = SNB_UNCORE_PCI_IMC_BAR_OFFSET;
+	resource_size_t addr;
+	u32 pci_dword;
+
+	pci_read_config_dword(pdev, where, &pci_dword);
+	addr = pci_dword;
+
+#ifdef CONFIG_PHYS_ADDR_T_64BIT
+	pci_read_config_dword(pdev, where + 4, &pci_dword);
+	addr |= ((resource_size_t)pci_dword << 32);
+#endif
+
+	addr &= ~(PAGE_SIZE - 1);
+
+	box->io_addr = ioremap(addr, SNB_UNCORE_PCI_IMC_MAP_SIZE);
+	box->hrtimer_duration = UNCORE_SNB_IMC_HRTIMER_INTERVAL;
+}
+
+static void snb_uncore_imc_enable_box(struct intel_uncore_box *box)
+{}
+
+static void snb_uncore_imc_disable_box(struct intel_uncore_box *box)
+{}
+
+static void snb_uncore_imc_enable_event(struct intel_uncore_box *box, struct perf_event *event)
+{}
+
+static void snb_uncore_imc_disable_event(struct intel_uncore_box *box, struct perf_event *event)
+{}
+
+static u64 snb_uncore_imc_read_counter(struct intel_uncore_box *box, struct perf_event *event)
+{
+	struct hw_perf_event *hwc = &event->hw;
+
+	return (u64)*(unsigned int *)(box->io_addr + hwc->event_base);
+}
+
+/*
+ * custom event_init() function because we define our own fixed, free
+ * running counters, so we do not want to conflict with generic uncore
+ * logic. Also simplifies processing
+ */
+static int snb_uncore_imc_event_init(struct perf_event *event)
+{
+	struct intel_uncore_pmu *pmu;
+	struct intel_uncore_box *box;
+	struct hw_perf_event *hwc = &event->hw;
+	u64 cfg = event->attr.config & SNB_UNCORE_PCI_IMC_EVENT_MASK;
+	int idx, base;
+
+	if (event->attr.type != event->pmu->type)
+		return -ENOENT;
+
+	pmu = uncore_event_to_pmu(event);
+	/* no device found for this pmu */
+	if (pmu->func_id < 0)
+		return -ENOENT;
+
+	/* Sampling not supported yet */
+	if (hwc->sample_period)
+		return -EINVAL;
+
+	/* unsupported modes and filters */
+	if (event->attr.exclude_user   ||
+	    event->attr.exclude_kernel ||
+	    event->attr.exclude_hv     ||
+	    event->attr.exclude_idle   ||
+	    event->attr.exclude_host   ||
+	    event->attr.exclude_guest  ||
+	    event->attr.sample_period) /* no sampling */
+		return -EINVAL;
+
+	/*
+	 * Place all uncore events for a particular physical package
+	 * onto a single cpu
+	 */
+	if (event->cpu < 0)
+		return -EINVAL;
+
+	/* check only supported bits are set */
+	if (event->attr.config & ~SNB_UNCORE_PCI_IMC_EVENT_MASK)
+		return -EINVAL;
+
+	box = uncore_pmu_to_box(pmu, event->cpu);
+	if (!box || box->cpu < 0)
+		return -EINVAL;
+
+	event->cpu = box->cpu;
+
+	event->hw.idx = -1;
+	event->hw.last_tag = ~0ULL;
+	event->hw.extra_reg.idx = EXTRA_REG_NONE;
+	event->hw.branch_reg.idx = EXTRA_REG_NONE;
+	/*
+	 * check event is known (whitelist, determines counter)
+	 */
+	switch (cfg) {
+	case SNB_UNCORE_PCI_IMC_DATA_READS:
+		base = SNB_UNCORE_PCI_IMC_DATA_READS_BASE;
+		idx = UNCORE_PMC_IDX_FIXED;
+		break;
+	case SNB_UNCORE_PCI_IMC_DATA_WRITES:
+		base = SNB_UNCORE_PCI_IMC_DATA_WRITES_BASE;
+		idx = UNCORE_PMC_IDX_FIXED + 1;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	/* must be done before validate_group */
+	event->hw.event_base = base;
+	event->hw.config = cfg;
+	event->hw.idx = idx;
+
+	/* no group validation needed, we have free running counters */
+
+	return 0;
+}
+
+static int snb_uncore_imc_hw_config(struct intel_uncore_box *box, struct perf_event *event)
+{
+	return 0;
+}
+
+static void snb_uncore_imc_event_start(struct perf_event *event, int flags)
+{
+	struct intel_uncore_box *box = uncore_event_to_box(event);
+	u64 count;
+
+	if (WARN_ON_ONCE(!(event->hw.state & PERF_HES_STOPPED)))
+		return;
+
+	event->hw.state = 0;
+	box->n_active++;
+
+	list_add_tail(&event->active_entry, &box->active_list);
+
+	count = snb_uncore_imc_read_counter(box, event);
+	local64_set(&event->hw.prev_count, count);
+
+	if (box->n_active == 1)
+		uncore_pmu_start_hrtimer(box);
+}
+
+static void snb_uncore_imc_event_stop(struct perf_event *event, int flags)
+{
+	struct intel_uncore_box *box = uncore_event_to_box(event);
+	struct hw_perf_event *hwc = &event->hw;
+
+	if (!(hwc->state & PERF_HES_STOPPED)) {
+		box->n_active--;
+
+		WARN_ON_ONCE(hwc->state & PERF_HES_STOPPED);
+		hwc->state |= PERF_HES_STOPPED;
+
+		list_del(&event->active_entry);
+
+		if (box->n_active == 0)
+			uncore_pmu_cancel_hrtimer(box);
+	}
+
+	if ((flags & PERF_EF_UPDATE) && !(hwc->state & PERF_HES_UPTODATE)) {
+		/*
+		 * Drain the remaining delta count out of a event
+		 * that we are disabling:
+		 */
+		uncore_perf_event_update(box, event);
+		hwc->state |= PERF_HES_UPTODATE;
+	}
+}
+
+static int snb_uncore_imc_event_add(struct perf_event *event, int flags)
+{
+	struct intel_uncore_box *box = uncore_event_to_box(event);
+	struct hw_perf_event *hwc = &event->hw;
+
+	if (!box)
+		return -ENODEV;
+
+	hwc->state = PERF_HES_UPTODATE | PERF_HES_STOPPED;
+	if (!(flags & PERF_EF_START))
+		hwc->state |= PERF_HES_ARCH;
+
+	snb_uncore_imc_event_start(event, 0);
+
+	box->n_events++;
+
+	return 0;
+}
+
+static void snb_uncore_imc_event_del(struct perf_event *event, int flags)
+{
+	struct intel_uncore_box *box = uncore_event_to_box(event);
+	int i;
+
+	snb_uncore_imc_event_stop(event, PERF_EF_UPDATE);
+
+	for (i = 0; i < box->n_events; i++) {
+		if (event == box->event_list[i]) {
+			--box->n_events;
+			break;
+		}
+	}
+}
+
+static int snb_pci2phy_map_init(int devid)
+{
+	struct pci_dev *dev = NULL;
+	int bus;
+
+	dev = pci_get_device(PCI_VENDOR_ID_INTEL, devid, dev);
+	if (!dev)
+		return -ENOTTY;
+
+	bus = dev->bus->number;
+
+	uncore_pcibus_to_physid[bus] = 0;
+
+	pci_dev_put(dev);
+
+	return 0;
+}
+
+static struct pmu snb_uncore_imc_pmu = {
+	.task_ctx_nr	= perf_invalid_context,
+	.event_init	= snb_uncore_imc_event_init,
+	.add		= snb_uncore_imc_event_add,
+	.del		= snb_uncore_imc_event_del,
+	.start		= snb_uncore_imc_event_start,
+	.stop		= snb_uncore_imc_event_stop,
+	.read		= uncore_pmu_event_read,
+};
+
+static struct intel_uncore_ops snb_uncore_imc_ops = {
+	.init_box	= snb_uncore_imc_init_box,
+	.enable_box	= snb_uncore_imc_enable_box,
+	.disable_box	= snb_uncore_imc_disable_box,
+	.disable_event	= snb_uncore_imc_disable_event,
+	.enable_event	= snb_uncore_imc_enable_event,
+	.hw_config	= snb_uncore_imc_hw_config,
+	.read_counter	= snb_uncore_imc_read_counter,
+};
+
+static struct intel_uncore_type snb_uncore_imc = {
+	.name		= "imc",
+	.num_counters   = 2,
+	.num_boxes	= 1,
+	.fixed_ctr_bits	= 32,
+	.fixed_ctr	= SNB_UNCORE_PCI_IMC_CTR_BASE,
+	.event_descs	= snb_uncore_imc_events,
+	.format_group	= &snb_uncore_imc_format_group,
+	.perf_ctr	= SNB_UNCORE_PCI_IMC_DATA_READS_BASE,
+	.event_mask	= SNB_UNCORE_PCI_IMC_EVENT_MASK,
+	.ops		= &snb_uncore_imc_ops,
+	.pmu		= &snb_uncore_imc_pmu,
+};
+
+static struct intel_uncore_type *snb_pci_uncores[] = {
+	[SNB_PCI_UNCORE_IMC]	= &snb_uncore_imc,
+	NULL,
+};
+
+static const struct pci_device_id snb_uncore_pci_ids[] = {
+	{ /* IMC */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_SNB_IMC),
+		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+	},
+	{ /* end: all zeroes */ },
+};
+
+static const struct pci_device_id ivb_uncore_pci_ids[] = {
+	{ /* IMC */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_IVB_IMC),
+		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+	},
+	{ /* end: all zeroes */ },
+};
+
+static const struct pci_device_id hsw_uncore_pci_ids[] = {
+	{ /* IMC */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_HSW_IMC),
+		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+	},
+	{ /* end: all zeroes */ },
+};
+
+static struct pci_driver snb_uncore_pci_driver = {
+	.name		= "snb_uncore",
+	.id_table	= snb_uncore_pci_ids,
+};
+
+static struct pci_driver ivb_uncore_pci_driver = {
+	.name		= "ivb_uncore",
+	.id_table	= ivb_uncore_pci_ids,
+};
+
+static struct pci_driver hsw_uncore_pci_driver = {
+	.name		= "hsw_uncore",
+	.id_table	= hsw_uncore_pci_ids,
+};
+
+int snb_uncore_pci_init(void)
+{
+	int ret = snb_pci2phy_map_init(PCI_DEVICE_ID_INTEL_SNB_IMC);
+	if (ret)
+		return ret;
+	uncore_pci_uncores = snb_pci_uncores;
+	uncore_pci_driver = &snb_uncore_pci_driver;
+	return 0;
+}
+
+int ivb_uncore_pci_init(void)
+{
+	int ret = snb_pci2phy_map_init(PCI_DEVICE_ID_INTEL_IVB_IMC);
+	if (ret)
+		return ret;
+	uncore_pci_uncores = snb_pci_uncores;
+	uncore_pci_driver = &ivb_uncore_pci_driver;
+	return 0;
+}
+
+int hsw_uncore_pci_init(void)
+{
+	int ret = snb_pci2phy_map_init(PCI_DEVICE_ID_INTEL_HSW_IMC);
+	if (ret)
+		return ret;
+	uncore_pci_uncores = snb_pci_uncores;
+	uncore_pci_driver = &hsw_uncore_pci_driver;
+	return 0;
+}
+
+/* end of Sandy Bridge uncore support */
+
+/* Nehalem uncore support */
+static void nhm_uncore_msr_disable_box(struct intel_uncore_box *box)
+{
+	wrmsrl(NHM_UNC_PERF_GLOBAL_CTL, 0);
+}
+
+static void nhm_uncore_msr_enable_box(struct intel_uncore_box *box)
+{
+	wrmsrl(NHM_UNC_PERF_GLOBAL_CTL, NHM_UNC_GLOBAL_CTL_EN_PC_ALL | NHM_UNC_GLOBAL_CTL_EN_FC);
+}
+
+static void nhm_uncore_msr_enable_event(struct intel_uncore_box *box, struct perf_event *event)
+{
+	struct hw_perf_event *hwc = &event->hw;
+
+	if (hwc->idx < UNCORE_PMC_IDX_FIXED)
+		wrmsrl(hwc->config_base, hwc->config | SNB_UNC_CTL_EN);
+	else
+		wrmsrl(hwc->config_base, NHM_UNC_FIXED_CTR_CTL_EN);
+}
+
+static struct attribute *nhm_uncore_formats_attr[] = {
+	&format_attr_event.attr,
+	&format_attr_umask.attr,
+	&format_attr_edge.attr,
+	&format_attr_inv.attr,
+	&format_attr_cmask8.attr,
+	NULL,
+};
+
+static struct attribute_group nhm_uncore_format_group = {
+	.name = "format",
+	.attrs = nhm_uncore_formats_attr,
+};
+
+static struct uncore_event_desc nhm_uncore_events[] = {
+	INTEL_UNCORE_EVENT_DESC(clockticks,                "event=0xff,umask=0x00"),
+	INTEL_UNCORE_EVENT_DESC(qmc_writes_full_any,       "event=0x2f,umask=0x0f"),
+	INTEL_UNCORE_EVENT_DESC(qmc_normal_reads_any,      "event=0x2c,umask=0x0f"),
+	INTEL_UNCORE_EVENT_DESC(qhl_request_ioh_reads,     "event=0x20,umask=0x01"),
+	INTEL_UNCORE_EVENT_DESC(qhl_request_ioh_writes,    "event=0x20,umask=0x02"),
+	INTEL_UNCORE_EVENT_DESC(qhl_request_remote_reads,  "event=0x20,umask=0x04"),
+	INTEL_UNCORE_EVENT_DESC(qhl_request_remote_writes, "event=0x20,umask=0x08"),
+	INTEL_UNCORE_EVENT_DESC(qhl_request_local_reads,   "event=0x20,umask=0x10"),
+	INTEL_UNCORE_EVENT_DESC(qhl_request_local_writes,  "event=0x20,umask=0x20"),
+	{ /* end: all zeroes */ },
+};
+
+static struct intel_uncore_ops nhm_uncore_msr_ops = {
+	.disable_box	= nhm_uncore_msr_disable_box,
+	.enable_box	= nhm_uncore_msr_enable_box,
+	.disable_event	= snb_uncore_msr_disable_event,
+	.enable_event	= nhm_uncore_msr_enable_event,
+	.read_counter	= uncore_msr_read_counter,
+};
+
+static struct intel_uncore_type nhm_uncore = {
+	.name		= "",
+	.num_counters   = 8,
+	.num_boxes	= 1,
+	.perf_ctr_bits	= 48,
+	.fixed_ctr_bits	= 48,
+	.event_ctl	= NHM_UNC_PERFEVTSEL0,
+	.perf_ctr	= NHM_UNC_UNCORE_PMC0,
+	.fixed_ctr	= NHM_UNC_FIXED_CTR,
+	.fixed_ctl	= NHM_UNC_FIXED_CTR_CTRL,
+	.event_mask	= NHM_UNC_RAW_EVENT_MASK,
+	.event_descs	= nhm_uncore_events,
+	.ops		= &nhm_uncore_msr_ops,
+	.format_group	= &nhm_uncore_format_group,
+};
+
+static struct intel_uncore_type *nhm_msr_uncores[] = {
+	&nhm_uncore,
+	NULL,
+};
+
+void nhm_uncore_cpu_init(void)
+{
+	uncore_msr_uncores = nhm_msr_uncores;
+}
+
+/* end of Nehalem uncore support */
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c b/arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c
new file mode 100644
index 00000000000000..6606ed05d31196
--- /dev/null
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c
@@ -0,0 +1,1645 @@
+/* SandyBridge-EP/IvyTown uncore support */
+#include "perf_event_intel_uncore.h"
+
+
+/* SNB-EP Box level control */
+#define SNBEP_PMON_BOX_CTL_RST_CTRL	(1 << 0)
+#define SNBEP_PMON_BOX_CTL_RST_CTRS	(1 << 1)
+#define SNBEP_PMON_BOX_CTL_FRZ		(1 << 8)
+#define SNBEP_PMON_BOX_CTL_FRZ_EN	(1 << 16)
+#define SNBEP_PMON_BOX_CTL_INT		(SNBEP_PMON_BOX_CTL_RST_CTRL | \
+					 SNBEP_PMON_BOX_CTL_RST_CTRS | \
+					 SNBEP_PMON_BOX_CTL_FRZ_EN)
+/* SNB-EP event control */
+#define SNBEP_PMON_CTL_EV_SEL_MASK	0x000000ff
+#define SNBEP_PMON_CTL_UMASK_MASK	0x0000ff00
+#define SNBEP_PMON_CTL_RST		(1 << 17)
+#define SNBEP_PMON_CTL_EDGE_DET		(1 << 18)
+#define SNBEP_PMON_CTL_EV_SEL_EXT	(1 << 21)
+#define SNBEP_PMON_CTL_EN		(1 << 22)
+#define SNBEP_PMON_CTL_INVERT		(1 << 23)
+#define SNBEP_PMON_CTL_TRESH_MASK	0xff000000
+#define SNBEP_PMON_RAW_EVENT_MASK	(SNBEP_PMON_CTL_EV_SEL_MASK | \
+					 SNBEP_PMON_CTL_UMASK_MASK | \
+					 SNBEP_PMON_CTL_EDGE_DET | \
+					 SNBEP_PMON_CTL_INVERT | \
+					 SNBEP_PMON_CTL_TRESH_MASK)
+
+/* SNB-EP Ubox event control */
+#define SNBEP_U_MSR_PMON_CTL_TRESH_MASK		0x1f000000
+#define SNBEP_U_MSR_PMON_RAW_EVENT_MASK		\
+				(SNBEP_PMON_CTL_EV_SEL_MASK | \
+				 SNBEP_PMON_CTL_UMASK_MASK | \
+				 SNBEP_PMON_CTL_EDGE_DET | \
+				 SNBEP_PMON_CTL_INVERT | \
+				 SNBEP_U_MSR_PMON_CTL_TRESH_MASK)
+
+#define SNBEP_CBO_PMON_CTL_TID_EN		(1 << 19)
+#define SNBEP_CBO_MSR_PMON_RAW_EVENT_MASK	(SNBEP_PMON_RAW_EVENT_MASK | \
+						 SNBEP_CBO_PMON_CTL_TID_EN)
+
+/* SNB-EP PCU event control */
+#define SNBEP_PCU_MSR_PMON_CTL_OCC_SEL_MASK	0x0000c000
+#define SNBEP_PCU_MSR_PMON_CTL_TRESH_MASK	0x1f000000
+#define SNBEP_PCU_MSR_PMON_CTL_OCC_INVERT	(1 << 30)
+#define SNBEP_PCU_MSR_PMON_CTL_OCC_EDGE_DET	(1 << 31)
+#define SNBEP_PCU_MSR_PMON_RAW_EVENT_MASK	\
+				(SNBEP_PMON_CTL_EV_SEL_MASK | \
+				 SNBEP_PCU_MSR_PMON_CTL_OCC_SEL_MASK | \
+				 SNBEP_PMON_CTL_EDGE_DET | \
+				 SNBEP_PMON_CTL_EV_SEL_EXT | \
+				 SNBEP_PMON_CTL_INVERT | \
+				 SNBEP_PCU_MSR_PMON_CTL_TRESH_MASK | \
+				 SNBEP_PCU_MSR_PMON_CTL_OCC_INVERT | \
+				 SNBEP_PCU_MSR_PMON_CTL_OCC_EDGE_DET)
+
+#define SNBEP_QPI_PCI_PMON_RAW_EVENT_MASK	\
+				(SNBEP_PMON_RAW_EVENT_MASK | \
+				 SNBEP_PMON_CTL_EV_SEL_EXT)
+
+/* SNB-EP pci control register */
+#define SNBEP_PCI_PMON_BOX_CTL			0xf4
+#define SNBEP_PCI_PMON_CTL0			0xd8
+/* SNB-EP pci counter register */
+#define SNBEP_PCI_PMON_CTR0			0xa0
+
+/* SNB-EP home agent register */
+#define SNBEP_HA_PCI_PMON_BOX_ADDRMATCH0	0x40
+#define SNBEP_HA_PCI_PMON_BOX_ADDRMATCH1	0x44
+#define SNBEP_HA_PCI_PMON_BOX_OPCODEMATCH	0x48
+/* SNB-EP memory controller register */
+#define SNBEP_MC_CHy_PCI_PMON_FIXED_CTL		0xf0
+#define SNBEP_MC_CHy_PCI_PMON_FIXED_CTR		0xd0
+/* SNB-EP QPI register */
+#define SNBEP_Q_Py_PCI_PMON_PKT_MATCH0		0x228
+#define SNBEP_Q_Py_PCI_PMON_PKT_MATCH1		0x22c
+#define SNBEP_Q_Py_PCI_PMON_PKT_MASK0		0x238
+#define SNBEP_Q_Py_PCI_PMON_PKT_MASK1		0x23c
+
+/* SNB-EP Ubox register */
+#define SNBEP_U_MSR_PMON_CTR0			0xc16
+#define SNBEP_U_MSR_PMON_CTL0			0xc10
+
+#define SNBEP_U_MSR_PMON_UCLK_FIXED_CTL		0xc08
+#define SNBEP_U_MSR_PMON_UCLK_FIXED_CTR		0xc09
+
+/* SNB-EP Cbo register */
+#define SNBEP_C0_MSR_PMON_CTR0			0xd16
+#define SNBEP_C0_MSR_PMON_CTL0			0xd10
+#define SNBEP_C0_MSR_PMON_BOX_CTL		0xd04
+#define SNBEP_C0_MSR_PMON_BOX_FILTER		0xd14
+#define SNBEP_CBO_MSR_OFFSET			0x20
+
+#define SNBEP_CB0_MSR_PMON_BOX_FILTER_TID	0x1f
+#define SNBEP_CB0_MSR_PMON_BOX_FILTER_NID	0x3fc00
+#define SNBEP_CB0_MSR_PMON_BOX_FILTER_STATE	0x7c0000
+#define SNBEP_CB0_MSR_PMON_BOX_FILTER_OPC	0xff800000
+
+#define SNBEP_CBO_EVENT_EXTRA_REG(e, m, i) {	\
+	.event = (e),				\
+	.msr = SNBEP_C0_MSR_PMON_BOX_FILTER,	\
+	.config_mask = (m),			\
+	.idx = (i)				\
+}
+
+/* SNB-EP PCU register */
+#define SNBEP_PCU_MSR_PMON_CTR0			0xc36
+#define SNBEP_PCU_MSR_PMON_CTL0			0xc30
+#define SNBEP_PCU_MSR_PMON_BOX_CTL		0xc24
+#define SNBEP_PCU_MSR_PMON_BOX_FILTER		0xc34
+#define SNBEP_PCU_MSR_PMON_BOX_FILTER_MASK	0xffffffff
+#define SNBEP_PCU_MSR_CORE_C3_CTR		0x3fc
+#define SNBEP_PCU_MSR_CORE_C6_CTR		0x3fd
+
+/* IVBEP event control */
+#define IVBEP_PMON_BOX_CTL_INT		(SNBEP_PMON_BOX_CTL_RST_CTRL | \
+					 SNBEP_PMON_BOX_CTL_RST_CTRS)
+#define IVBEP_PMON_RAW_EVENT_MASK		(SNBEP_PMON_CTL_EV_SEL_MASK | \
+					 SNBEP_PMON_CTL_UMASK_MASK | \
+					 SNBEP_PMON_CTL_EDGE_DET | \
+					 SNBEP_PMON_CTL_TRESH_MASK)
+/* IVBEP Ubox */
+#define IVBEP_U_MSR_PMON_GLOBAL_CTL		0xc00
+#define IVBEP_U_PMON_GLOBAL_FRZ_ALL		(1 << 31)
+#define IVBEP_U_PMON_GLOBAL_UNFRZ_ALL		(1 << 29)
+
+#define IVBEP_U_MSR_PMON_RAW_EVENT_MASK	\
+				(SNBEP_PMON_CTL_EV_SEL_MASK | \
+				 SNBEP_PMON_CTL_UMASK_MASK | \
+				 SNBEP_PMON_CTL_EDGE_DET | \
+				 SNBEP_U_MSR_PMON_CTL_TRESH_MASK)
+/* IVBEP Cbo */
+#define IVBEP_CBO_MSR_PMON_RAW_EVENT_MASK		(IVBEP_PMON_RAW_EVENT_MASK | \
+						 SNBEP_CBO_PMON_CTL_TID_EN)
+
+#define IVBEP_CB0_MSR_PMON_BOX_FILTER_TID		(0x1fULL << 0)
+#define IVBEP_CB0_MSR_PMON_BOX_FILTER_LINK	(0xfULL << 5)
+#define IVBEP_CB0_MSR_PMON_BOX_FILTER_STATE	(0x3fULL << 17)
+#define IVBEP_CB0_MSR_PMON_BOX_FILTER_NID		(0xffffULL << 32)
+#define IVBEP_CB0_MSR_PMON_BOX_FILTER_OPC		(0x1ffULL << 52)
+#define IVBEP_CB0_MSR_PMON_BOX_FILTER_C6		(0x1ULL << 61)
+#define IVBEP_CB0_MSR_PMON_BOX_FILTER_NC		(0x1ULL << 62)
+#define IVBEP_CB0_MSR_PMON_BOX_FILTER_IOSC	(0x1ULL << 63)
+
+/* IVBEP home agent */
+#define IVBEP_HA_PCI_PMON_CTL_Q_OCC_RST		(1 << 16)
+#define IVBEP_HA_PCI_PMON_RAW_EVENT_MASK		\
+				(IVBEP_PMON_RAW_EVENT_MASK | \
+				 IVBEP_HA_PCI_PMON_CTL_Q_OCC_RST)
+/* IVBEP PCU */
+#define IVBEP_PCU_MSR_PMON_RAW_EVENT_MASK	\
+				(SNBEP_PMON_CTL_EV_SEL_MASK | \
+				 SNBEP_PMON_CTL_EV_SEL_EXT | \
+				 SNBEP_PCU_MSR_PMON_CTL_OCC_SEL_MASK | \
+				 SNBEP_PMON_CTL_EDGE_DET | \
+				 SNBEP_PCU_MSR_PMON_CTL_TRESH_MASK | \
+				 SNBEP_PCU_MSR_PMON_CTL_OCC_INVERT | \
+				 SNBEP_PCU_MSR_PMON_CTL_OCC_EDGE_DET)
+/* IVBEP QPI */
+#define IVBEP_QPI_PCI_PMON_RAW_EVENT_MASK	\
+				(IVBEP_PMON_RAW_EVENT_MASK | \
+				 SNBEP_PMON_CTL_EV_SEL_EXT)
+
+#define __BITS_VALUE(x, i, n)  ((typeof(x))(((x) >> ((i) * (n))) & \
+				((1ULL << (n)) - 1)))
+
+DEFINE_UNCORE_FORMAT_ATTR(event, event, "config:0-7");
+DEFINE_UNCORE_FORMAT_ATTR(event_ext, event, "config:0-7,21");
+DEFINE_UNCORE_FORMAT_ATTR(umask, umask, "config:8-15");
+DEFINE_UNCORE_FORMAT_ATTR(edge, edge, "config:18");
+DEFINE_UNCORE_FORMAT_ATTR(tid_en, tid_en, "config:19");
+DEFINE_UNCORE_FORMAT_ATTR(inv, inv, "config:23");
+DEFINE_UNCORE_FORMAT_ATTR(thresh8, thresh, "config:24-31");
+DEFINE_UNCORE_FORMAT_ATTR(thresh5, thresh, "config:24-28");
+DEFINE_UNCORE_FORMAT_ATTR(occ_sel, occ_sel, "config:14-15");
+DEFINE_UNCORE_FORMAT_ATTR(occ_invert, occ_invert, "config:30");
+DEFINE_UNCORE_FORMAT_ATTR(occ_edge, occ_edge, "config:14-51");
+DEFINE_UNCORE_FORMAT_ATTR(filter_tid, filter_tid, "config1:0-4");
+DEFINE_UNCORE_FORMAT_ATTR(filter_link, filter_link, "config1:5-8");
+DEFINE_UNCORE_FORMAT_ATTR(filter_nid, filter_nid, "config1:10-17");
+DEFINE_UNCORE_FORMAT_ATTR(filter_nid2, filter_nid, "config1:32-47");
+DEFINE_UNCORE_FORMAT_ATTR(filter_state, filter_state, "config1:18-22");
+DEFINE_UNCORE_FORMAT_ATTR(filter_state2, filter_state, "config1:17-22");
+DEFINE_UNCORE_FORMAT_ATTR(filter_opc, filter_opc, "config1:23-31");
+DEFINE_UNCORE_FORMAT_ATTR(filter_opc2, filter_opc, "config1:52-60");
+DEFINE_UNCORE_FORMAT_ATTR(filter_band0, filter_band0, "config1:0-7");
+DEFINE_UNCORE_FORMAT_ATTR(filter_band1, filter_band1, "config1:8-15");
+DEFINE_UNCORE_FORMAT_ATTR(filter_band2, filter_band2, "config1:16-23");
+DEFINE_UNCORE_FORMAT_ATTR(filter_band3, filter_band3, "config1:24-31");
+DEFINE_UNCORE_FORMAT_ATTR(match_rds, match_rds, "config1:48-51");
+DEFINE_UNCORE_FORMAT_ATTR(match_rnid30, match_rnid30, "config1:32-35");
+DEFINE_UNCORE_FORMAT_ATTR(match_rnid4, match_rnid4, "config1:31");
+DEFINE_UNCORE_FORMAT_ATTR(match_dnid, match_dnid, "config1:13-17");
+DEFINE_UNCORE_FORMAT_ATTR(match_mc, match_mc, "config1:9-12");
+DEFINE_UNCORE_FORMAT_ATTR(match_opc, match_opc, "config1:5-8");
+DEFINE_UNCORE_FORMAT_ATTR(match_vnw, match_vnw, "config1:3-4");
+DEFINE_UNCORE_FORMAT_ATTR(match0, match0, "config1:0-31");
+DEFINE_UNCORE_FORMAT_ATTR(match1, match1, "config1:32-63");
+DEFINE_UNCORE_FORMAT_ATTR(mask_rds, mask_rds, "config2:48-51");
+DEFINE_UNCORE_FORMAT_ATTR(mask_rnid30, mask_rnid30, "config2:32-35");
+DEFINE_UNCORE_FORMAT_ATTR(mask_rnid4, mask_rnid4, "config2:31");
+DEFINE_UNCORE_FORMAT_ATTR(mask_dnid, mask_dnid, "config2:13-17");
+DEFINE_UNCORE_FORMAT_ATTR(mask_mc, mask_mc, "config2:9-12");
+DEFINE_UNCORE_FORMAT_ATTR(mask_opc, mask_opc, "config2:5-8");
+DEFINE_UNCORE_FORMAT_ATTR(mask_vnw, mask_vnw, "config2:3-4");
+DEFINE_UNCORE_FORMAT_ATTR(mask0, mask0, "config2:0-31");
+DEFINE_UNCORE_FORMAT_ATTR(mask1, mask1, "config2:32-63");
+
+static void snbep_uncore_pci_disable_box(struct intel_uncore_box *box)
+{
+	struct pci_dev *pdev = box->pci_dev;
+	int box_ctl = uncore_pci_box_ctl(box);
+	u32 config = 0;
+
+	if (!pci_read_config_dword(pdev, box_ctl, &config)) {
+		config |= SNBEP_PMON_BOX_CTL_FRZ;
+		pci_write_config_dword(pdev, box_ctl, config);
+	}
+}
+
+static void snbep_uncore_pci_enable_box(struct intel_uncore_box *box)
+{
+	struct pci_dev *pdev = box->pci_dev;
+	int box_ctl = uncore_pci_box_ctl(box);
+	u32 config = 0;
+
+	if (!pci_read_config_dword(pdev, box_ctl, &config)) {
+		config &= ~SNBEP_PMON_BOX_CTL_FRZ;
+		pci_write_config_dword(pdev, box_ctl, config);
+	}
+}
+
+static void snbep_uncore_pci_enable_event(struct intel_uncore_box *box, struct perf_event *event)
+{
+	struct pci_dev *pdev = box->pci_dev;
+	struct hw_perf_event *hwc = &event->hw;
+
+	pci_write_config_dword(pdev, hwc->config_base, hwc->config | SNBEP_PMON_CTL_EN);
+}
+
+static void snbep_uncore_pci_disable_event(struct intel_uncore_box *box, struct perf_event *event)
+{
+	struct pci_dev *pdev = box->pci_dev;
+	struct hw_perf_event *hwc = &event->hw;
+
+	pci_write_config_dword(pdev, hwc->config_base, hwc->config);
+}
+
+static u64 snbep_uncore_pci_read_counter(struct intel_uncore_box *box, struct perf_event *event)
+{
+	struct pci_dev *pdev = box->pci_dev;
+	struct hw_perf_event *hwc = &event->hw;
+	u64 count = 0;
+
+	pci_read_config_dword(pdev, hwc->event_base, (u32 *)&count);
+	pci_read_config_dword(pdev, hwc->event_base + 4, (u32 *)&count + 1);
+
+	return count;
+}
+
+static void snbep_uncore_pci_init_box(struct intel_uncore_box *box)
+{
+	struct pci_dev *pdev = box->pci_dev;
+
+	pci_write_config_dword(pdev, SNBEP_PCI_PMON_BOX_CTL, SNBEP_PMON_BOX_CTL_INT);
+}
+
+static void snbep_uncore_msr_disable_box(struct intel_uncore_box *box)
+{
+	u64 config;
+	unsigned msr;
+
+	msr = uncore_msr_box_ctl(box);
+	if (msr) {
+		rdmsrl(msr, config);
+		config |= SNBEP_PMON_BOX_CTL_FRZ;
+		wrmsrl(msr, config);
+	}
+}
+
+static void snbep_uncore_msr_enable_box(struct intel_uncore_box *box)
+{
+	u64 config;
+	unsigned msr;
+
+	msr = uncore_msr_box_ctl(box);
+	if (msr) {
+		rdmsrl(msr, config);
+		config &= ~SNBEP_PMON_BOX_CTL_FRZ;
+		wrmsrl(msr, config);
+	}
+}
+
+static void snbep_uncore_msr_enable_event(struct intel_uncore_box *box, struct perf_event *event)
+{
+	struct hw_perf_event *hwc = &event->hw;
+	struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
+
+	if (reg1->idx != EXTRA_REG_NONE)
+		wrmsrl(reg1->reg, uncore_shared_reg_config(box, 0));
+
+	wrmsrl(hwc->config_base, hwc->config | SNBEP_PMON_CTL_EN);
+}
+
+static void snbep_uncore_msr_disable_event(struct intel_uncore_box *box,
+					struct perf_event *event)
+{
+	struct hw_perf_event *hwc = &event->hw;
+
+	wrmsrl(hwc->config_base, hwc->config);
+}
+
+static void snbep_uncore_msr_init_box(struct intel_uncore_box *box)
+{
+	unsigned msr = uncore_msr_box_ctl(box);
+
+	if (msr)
+		wrmsrl(msr, SNBEP_PMON_BOX_CTL_INT);
+}
+
+static struct attribute *snbep_uncore_formats_attr[] = {
+	&format_attr_event.attr,
+	&format_attr_umask.attr,
+	&format_attr_edge.attr,
+	&format_attr_inv.attr,
+	&format_attr_thresh8.attr,
+	NULL,
+};
+
+static struct attribute *snbep_uncore_ubox_formats_attr[] = {
+	&format_attr_event.attr,
+	&format_attr_umask.attr,
+	&format_attr_edge.attr,
+	&format_attr_inv.attr,
+	&format_attr_thresh5.attr,
+	NULL,
+};
+
+static struct attribute *snbep_uncore_cbox_formats_attr[] = {
+	&format_attr_event.attr,
+	&format_attr_umask.attr,
+	&format_attr_edge.attr,
+	&format_attr_tid_en.attr,
+	&format_attr_inv.attr,
+	&format_attr_thresh8.attr,
+	&format_attr_filter_tid.attr,
+	&format_attr_filter_nid.attr,
+	&format_attr_filter_state.attr,
+	&format_attr_filter_opc.attr,
+	NULL,
+};
+
+static struct attribute *snbep_uncore_pcu_formats_attr[] = {
+	&format_attr_event_ext.attr,
+	&format_attr_occ_sel.attr,
+	&format_attr_edge.attr,
+	&format_attr_inv.attr,
+	&format_attr_thresh5.attr,
+	&format_attr_occ_invert.attr,
+	&format_attr_occ_edge.attr,
+	&format_attr_filter_band0.attr,
+	&format_attr_filter_band1.attr,
+	&format_attr_filter_band2.attr,
+	&format_attr_filter_band3.attr,
+	NULL,
+};
+
+static struct attribute *snbep_uncore_qpi_formats_attr[] = {
+	&format_attr_event_ext.attr,
+	&format_attr_umask.attr,
+	&format_attr_edge.attr,
+	&format_attr_inv.attr,
+	&format_attr_thresh8.attr,
+	&format_attr_match_rds.attr,
+	&format_attr_match_rnid30.attr,
+	&format_attr_match_rnid4.attr,
+	&format_attr_match_dnid.attr,
+	&format_attr_match_mc.attr,
+	&format_attr_match_opc.attr,
+	&format_attr_match_vnw.attr,
+	&format_attr_match0.attr,
+	&format_attr_match1.attr,
+	&format_attr_mask_rds.attr,
+	&format_attr_mask_rnid30.attr,
+	&format_attr_mask_rnid4.attr,
+	&format_attr_mask_dnid.attr,
+	&format_attr_mask_mc.attr,
+	&format_attr_mask_opc.attr,
+	&format_attr_mask_vnw.attr,
+	&format_attr_mask0.attr,
+	&format_attr_mask1.attr,
+	NULL,
+};
+
+static struct uncore_event_desc snbep_uncore_imc_events[] = {
+	INTEL_UNCORE_EVENT_DESC(clockticks,      "event=0xff,umask=0x00"),
+	INTEL_UNCORE_EVENT_DESC(cas_count_read,  "event=0x04,umask=0x03"),
+	INTEL_UNCORE_EVENT_DESC(cas_count_write, "event=0x04,umask=0x0c"),
+	{ /* end: all zeroes */ },
+};
+
+static struct uncore_event_desc snbep_uncore_qpi_events[] = {
+	INTEL_UNCORE_EVENT_DESC(clockticks,       "event=0x14"),
+	INTEL_UNCORE_EVENT_DESC(txl_flits_active, "event=0x00,umask=0x06"),
+	INTEL_UNCORE_EVENT_DESC(drs_data,         "event=0x102,umask=0x08"),
+	INTEL_UNCORE_EVENT_DESC(ncb_data,         "event=0x103,umask=0x04"),
+	{ /* end: all zeroes */ },
+};
+
+static struct attribute_group snbep_uncore_format_group = {
+	.name = "format",
+	.attrs = snbep_uncore_formats_attr,
+};
+
+static struct attribute_group snbep_uncore_ubox_format_group = {
+	.name = "format",
+	.attrs = snbep_uncore_ubox_formats_attr,
+};
+
+static struct attribute_group snbep_uncore_cbox_format_group = {
+	.name = "format",
+	.attrs = snbep_uncore_cbox_formats_attr,
+};
+
+static struct attribute_group snbep_uncore_pcu_format_group = {
+	.name = "format",
+	.attrs = snbep_uncore_pcu_formats_attr,
+};
+
+static struct attribute_group snbep_uncore_qpi_format_group = {
+	.name = "format",
+	.attrs = snbep_uncore_qpi_formats_attr,
+};
+
+#define SNBEP_UNCORE_MSR_OPS_COMMON_INIT()			\
+	.init_box	= snbep_uncore_msr_init_box,		\
+	.disable_box	= snbep_uncore_msr_disable_box,		\
+	.enable_box	= snbep_uncore_msr_enable_box,		\
+	.disable_event	= snbep_uncore_msr_disable_event,	\
+	.enable_event	= snbep_uncore_msr_enable_event,	\
+	.read_counter	= uncore_msr_read_counter
+
+static struct intel_uncore_ops snbep_uncore_msr_ops = {
+	SNBEP_UNCORE_MSR_OPS_COMMON_INIT(),
+};
+
+#define SNBEP_UNCORE_PCI_OPS_COMMON_INIT()			\
+	.init_box	= snbep_uncore_pci_init_box,		\
+	.disable_box	= snbep_uncore_pci_disable_box,		\
+	.enable_box	= snbep_uncore_pci_enable_box,		\
+	.disable_event	= snbep_uncore_pci_disable_event,	\
+	.read_counter	= snbep_uncore_pci_read_counter
+
+static struct intel_uncore_ops snbep_uncore_pci_ops = {
+	SNBEP_UNCORE_PCI_OPS_COMMON_INIT(),
+	.enable_event	= snbep_uncore_pci_enable_event,	\
+};
+
+static struct event_constraint snbep_uncore_cbox_constraints[] = {
+	UNCORE_EVENT_CONSTRAINT(0x01, 0x1),
+	UNCORE_EVENT_CONSTRAINT(0x02, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x04, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x05, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x07, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x09, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x11, 0x1),
+	UNCORE_EVENT_CONSTRAINT(0x12, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x13, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x1b, 0xc),
+	UNCORE_EVENT_CONSTRAINT(0x1c, 0xc),
+	UNCORE_EVENT_CONSTRAINT(0x1d, 0xc),
+	UNCORE_EVENT_CONSTRAINT(0x1e, 0xc),
+	EVENT_CONSTRAINT_OVERLAP(0x1f, 0xe, 0xff),
+	UNCORE_EVENT_CONSTRAINT(0x21, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x23, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x31, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x32, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x33, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x34, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x35, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x36, 0x1),
+	UNCORE_EVENT_CONSTRAINT(0x37, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x38, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x39, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x3b, 0x1),
+	EVENT_CONSTRAINT_END
+};
+
+static struct event_constraint snbep_uncore_r2pcie_constraints[] = {
+	UNCORE_EVENT_CONSTRAINT(0x10, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x11, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x12, 0x1),
+	UNCORE_EVENT_CONSTRAINT(0x23, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x24, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x25, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x26, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x32, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x33, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x34, 0x3),
+	EVENT_CONSTRAINT_END
+};
+
+static struct event_constraint snbep_uncore_r3qpi_constraints[] = {
+	UNCORE_EVENT_CONSTRAINT(0x10, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x11, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x12, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x13, 0x1),
+	UNCORE_EVENT_CONSTRAINT(0x20, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x21, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x22, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x23, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x24, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x25, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x26, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x28, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x29, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x2a, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x2b, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x2c, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x2d, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x2e, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x2f, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x30, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x31, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x32, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x33, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x34, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x36, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x37, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x38, 0x3),
+	UNCORE_EVENT_CONSTRAINT(0x39, 0x3),
+	EVENT_CONSTRAINT_END
+};
+
+static struct intel_uncore_type snbep_uncore_ubox = {
+	.name		= "ubox",
+	.num_counters   = 2,
+	.num_boxes	= 1,
+	.perf_ctr_bits	= 44,
+	.fixed_ctr_bits	= 48,
+	.perf_ctr	= SNBEP_U_MSR_PMON_CTR0,
+	.event_ctl	= SNBEP_U_MSR_PMON_CTL0,
+	.event_mask	= SNBEP_U_MSR_PMON_RAW_EVENT_MASK,
+	.fixed_ctr	= SNBEP_U_MSR_PMON_UCLK_FIXED_CTR,
+	.fixed_ctl	= SNBEP_U_MSR_PMON_UCLK_FIXED_CTL,
+	.ops		= &snbep_uncore_msr_ops,
+	.format_group	= &snbep_uncore_ubox_format_group,
+};
+
+static struct extra_reg snbep_uncore_cbox_extra_regs[] = {
+	SNBEP_CBO_EVENT_EXTRA_REG(SNBEP_CBO_PMON_CTL_TID_EN,
+				  SNBEP_CBO_PMON_CTL_TID_EN, 0x1),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x0334, 0xffff, 0x4),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x4334, 0xffff, 0x6),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x0534, 0xffff, 0x4),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x4534, 0xffff, 0x6),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x0934, 0xffff, 0x4),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x4934, 0xffff, 0x6),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x4134, 0xffff, 0x6),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x0135, 0xffff, 0x8),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x0335, 0xffff, 0x8),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x4135, 0xffff, 0xa),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x4335, 0xffff, 0xa),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x4435, 0xffff, 0x2),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x4835, 0xffff, 0x2),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x4a35, 0xffff, 0x2),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x5035, 0xffff, 0x2),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x0136, 0xffff, 0x8),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x0336, 0xffff, 0x8),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x4136, 0xffff, 0xa),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x4336, 0xffff, 0xa),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x4436, 0xffff, 0x2),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x4836, 0xffff, 0x2),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x4a36, 0xffff, 0x2),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x4037, 0x40ff, 0x2),
+	EVENT_EXTRA_END
+};
+
+static void snbep_cbox_put_constraint(struct intel_uncore_box *box, struct perf_event *event)
+{
+	struct hw_perf_event_extra *reg1 = &event->hw.extra_reg;
+	struct intel_uncore_extra_reg *er = &box->shared_regs[0];
+	int i;
+
+	if (uncore_box_is_fake(box))
+		return;
+
+	for (i = 0; i < 5; i++) {
+		if (reg1->alloc & (0x1 << i))
+			atomic_sub(1 << (i * 6), &er->ref);
+	}
+	reg1->alloc = 0;
+}
+
+static struct event_constraint *
+__snbep_cbox_get_constraint(struct intel_uncore_box *box, struct perf_event *event,
+			    u64 (*cbox_filter_mask)(int fields))
+{
+	struct hw_perf_event_extra *reg1 = &event->hw.extra_reg;
+	struct intel_uncore_extra_reg *er = &box->shared_regs[0];
+	int i, alloc = 0;
+	unsigned long flags;
+	u64 mask;
+
+	if (reg1->idx == EXTRA_REG_NONE)
+		return NULL;
+
+	raw_spin_lock_irqsave(&er->lock, flags);
+	for (i = 0; i < 5; i++) {
+		if (!(reg1->idx & (0x1 << i)))
+			continue;
+		if (!uncore_box_is_fake(box) && (reg1->alloc & (0x1 << i)))
+			continue;
+
+		mask = cbox_filter_mask(0x1 << i);
+		if (!__BITS_VALUE(atomic_read(&er->ref), i, 6) ||
+		    !((reg1->config ^ er->config) & mask)) {
+			atomic_add(1 << (i * 6), &er->ref);
+			er->config &= ~mask;
+			er->config |= reg1->config & mask;
+			alloc |= (0x1 << i);
+		} else {
+			break;
+		}
+	}
+	raw_spin_unlock_irqrestore(&er->lock, flags);
+	if (i < 5)
+		goto fail;
+
+	if (!uncore_box_is_fake(box))
+		reg1->alloc |= alloc;
+
+	return NULL;
+fail:
+	for (; i >= 0; i--) {
+		if (alloc & (0x1 << i))
+			atomic_sub(1 << (i * 6), &er->ref);
+	}
+	return &uncore_constraint_empty;
+}
+
+static u64 snbep_cbox_filter_mask(int fields)
+{
+	u64 mask = 0;
+
+	if (fields & 0x1)
+		mask |= SNBEP_CB0_MSR_PMON_BOX_FILTER_TID;
+	if (fields & 0x2)
+		mask |= SNBEP_CB0_MSR_PMON_BOX_FILTER_NID;
+	if (fields & 0x4)
+		mask |= SNBEP_CB0_MSR_PMON_BOX_FILTER_STATE;
+	if (fields & 0x8)
+		mask |= SNBEP_CB0_MSR_PMON_BOX_FILTER_OPC;
+
+	return mask;
+}
+
+static struct event_constraint *
+snbep_cbox_get_constraint(struct intel_uncore_box *box, struct perf_event *event)
+{
+	return __snbep_cbox_get_constraint(box, event, snbep_cbox_filter_mask);
+}
+
+static int snbep_cbox_hw_config(struct intel_uncore_box *box, struct perf_event *event)
+{
+	struct hw_perf_event_extra *reg1 = &event->hw.extra_reg;
+	struct extra_reg *er;
+	int idx = 0;
+
+	for (er = snbep_uncore_cbox_extra_regs; er->msr; er++) {
+		if (er->event != (event->hw.config & er->config_mask))
+			continue;
+		idx |= er->idx;
+	}
+
+	if (idx) {
+		reg1->reg = SNBEP_C0_MSR_PMON_BOX_FILTER +
+			SNBEP_CBO_MSR_OFFSET * box->pmu->pmu_idx;
+		reg1->config = event->attr.config1 & snbep_cbox_filter_mask(idx);
+		reg1->idx = idx;
+	}
+	return 0;
+}
+
+static struct intel_uncore_ops snbep_uncore_cbox_ops = {
+	SNBEP_UNCORE_MSR_OPS_COMMON_INIT(),
+	.hw_config		= snbep_cbox_hw_config,
+	.get_constraint		= snbep_cbox_get_constraint,
+	.put_constraint		= snbep_cbox_put_constraint,
+};
+
+static struct intel_uncore_type snbep_uncore_cbox = {
+	.name			= "cbox",
+	.num_counters		= 4,
+	.num_boxes		= 8,
+	.perf_ctr_bits		= 44,
+	.event_ctl		= SNBEP_C0_MSR_PMON_CTL0,
+	.perf_ctr		= SNBEP_C0_MSR_PMON_CTR0,
+	.event_mask		= SNBEP_CBO_MSR_PMON_RAW_EVENT_MASK,
+	.box_ctl		= SNBEP_C0_MSR_PMON_BOX_CTL,
+	.msr_offset		= SNBEP_CBO_MSR_OFFSET,
+	.num_shared_regs	= 1,
+	.constraints		= snbep_uncore_cbox_constraints,
+	.ops			= &snbep_uncore_cbox_ops,
+	.format_group		= &snbep_uncore_cbox_format_group,
+};
+
+static u64 snbep_pcu_alter_er(struct perf_event *event, int new_idx, bool modify)
+{
+	struct hw_perf_event *hwc = &event->hw;
+	struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
+	u64 config = reg1->config;
+
+	if (new_idx > reg1->idx)
+		config <<= 8 * (new_idx - reg1->idx);
+	else
+		config >>= 8 * (reg1->idx - new_idx);
+
+	if (modify) {
+		hwc->config += new_idx - reg1->idx;
+		reg1->config = config;
+		reg1->idx = new_idx;
+	}
+	return config;
+}
+
+static struct event_constraint *
+snbep_pcu_get_constraint(struct intel_uncore_box *box, struct perf_event *event)
+{
+	struct hw_perf_event_extra *reg1 = &event->hw.extra_reg;
+	struct intel_uncore_extra_reg *er = &box->shared_regs[0];
+	unsigned long flags;
+	int idx = reg1->idx;
+	u64 mask, config1 = reg1->config;
+	bool ok = false;
+
+	if (reg1->idx == EXTRA_REG_NONE ||
+	    (!uncore_box_is_fake(box) && reg1->alloc))
+		return NULL;
+again:
+	mask = 0xffULL << (idx * 8);
+	raw_spin_lock_irqsave(&er->lock, flags);
+	if (!__BITS_VALUE(atomic_read(&er->ref), idx, 8) ||
+	    !((config1 ^ er->config) & mask)) {
+		atomic_add(1 << (idx * 8), &er->ref);
+		er->config &= ~mask;
+		er->config |= config1 & mask;
+		ok = true;
+	}
+	raw_spin_unlock_irqrestore(&er->lock, flags);
+
+	if (!ok) {
+		idx = (idx + 1) % 4;
+		if (idx != reg1->idx) {
+			config1 = snbep_pcu_alter_er(event, idx, false);
+			goto again;
+		}
+		return &uncore_constraint_empty;
+	}
+
+	if (!uncore_box_is_fake(box)) {
+		if (idx != reg1->idx)
+			snbep_pcu_alter_er(event, idx, true);
+		reg1->alloc = 1;
+	}
+	return NULL;
+}
+
+static void snbep_pcu_put_constraint(struct intel_uncore_box *box, struct perf_event *event)
+{
+	struct hw_perf_event_extra *reg1 = &event->hw.extra_reg;
+	struct intel_uncore_extra_reg *er = &box->shared_regs[0];
+
+	if (uncore_box_is_fake(box) || !reg1->alloc)
+		return;
+
+	atomic_sub(1 << (reg1->idx * 8), &er->ref);
+	reg1->alloc = 0;
+}
+
+static int snbep_pcu_hw_config(struct intel_uncore_box *box, struct perf_event *event)
+{
+	struct hw_perf_event *hwc = &event->hw;
+	struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
+	int ev_sel = hwc->config & SNBEP_PMON_CTL_EV_SEL_MASK;
+
+	if (ev_sel >= 0xb && ev_sel <= 0xe) {
+		reg1->reg = SNBEP_PCU_MSR_PMON_BOX_FILTER;
+		reg1->idx = ev_sel - 0xb;
+		reg1->config = event->attr.config1 & (0xff << reg1->idx);
+	}
+	return 0;
+}
+
+static struct intel_uncore_ops snbep_uncore_pcu_ops = {
+	SNBEP_UNCORE_MSR_OPS_COMMON_INIT(),
+	.hw_config		= snbep_pcu_hw_config,
+	.get_constraint		= snbep_pcu_get_constraint,
+	.put_constraint		= snbep_pcu_put_constraint,
+};
+
+static struct intel_uncore_type snbep_uncore_pcu = {
+	.name			= "pcu",
+	.num_counters		= 4,
+	.num_boxes		= 1,
+	.perf_ctr_bits		= 48,
+	.perf_ctr		= SNBEP_PCU_MSR_PMON_CTR0,
+	.event_ctl		= SNBEP_PCU_MSR_PMON_CTL0,
+	.event_mask		= SNBEP_PCU_MSR_PMON_RAW_EVENT_MASK,
+	.box_ctl		= SNBEP_PCU_MSR_PMON_BOX_CTL,
+	.num_shared_regs	= 1,
+	.ops			= &snbep_uncore_pcu_ops,
+	.format_group		= &snbep_uncore_pcu_format_group,
+};
+
+static struct intel_uncore_type *snbep_msr_uncores[] = {
+	&snbep_uncore_ubox,
+	&snbep_uncore_cbox,
+	&snbep_uncore_pcu,
+	NULL,
+};
+
+void snbep_uncore_cpu_init(void)
+{
+	if (snbep_uncore_cbox.num_boxes > boot_cpu_data.x86_max_cores)
+		snbep_uncore_cbox.num_boxes = boot_cpu_data.x86_max_cores;
+	uncore_msr_uncores = snbep_msr_uncores;
+}
+
+enum {
+	SNBEP_PCI_QPI_PORT0_FILTER,
+	SNBEP_PCI_QPI_PORT1_FILTER,
+};
+
+static int snbep_qpi_hw_config(struct intel_uncore_box *box, struct perf_event *event)
+{
+	struct hw_perf_event *hwc = &event->hw;
+	struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
+	struct hw_perf_event_extra *reg2 = &hwc->branch_reg;
+
+	if ((hwc->config & SNBEP_PMON_CTL_EV_SEL_MASK) == 0x38) {
+		reg1->idx = 0;
+		reg1->reg = SNBEP_Q_Py_PCI_PMON_PKT_MATCH0;
+		reg1->config = event->attr.config1;
+		reg2->reg = SNBEP_Q_Py_PCI_PMON_PKT_MASK0;
+		reg2->config = event->attr.config2;
+	}
+	return 0;
+}
+
+static void snbep_qpi_enable_event(struct intel_uncore_box *box, struct perf_event *event)
+{
+	struct pci_dev *pdev = box->pci_dev;
+	struct hw_perf_event *hwc = &event->hw;
+	struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
+	struct hw_perf_event_extra *reg2 = &hwc->branch_reg;
+
+	if (reg1->idx != EXTRA_REG_NONE) {
+		int idx = box->pmu->pmu_idx + SNBEP_PCI_QPI_PORT0_FILTER;
+		struct pci_dev *filter_pdev = uncore_extra_pci_dev[box->phys_id][idx];
+		WARN_ON_ONCE(!filter_pdev);
+		if (filter_pdev) {
+			pci_write_config_dword(filter_pdev, reg1->reg,
+						(u32)reg1->config);
+			pci_write_config_dword(filter_pdev, reg1->reg + 4,
+						(u32)(reg1->config >> 32));
+			pci_write_config_dword(filter_pdev, reg2->reg,
+						(u32)reg2->config);
+			pci_write_config_dword(filter_pdev, reg2->reg + 4,
+						(u32)(reg2->config >> 32));
+		}
+	}
+
+	pci_write_config_dword(pdev, hwc->config_base, hwc->config | SNBEP_PMON_CTL_EN);
+}
+
+static struct intel_uncore_ops snbep_uncore_qpi_ops = {
+	SNBEP_UNCORE_PCI_OPS_COMMON_INIT(),
+	.enable_event		= snbep_qpi_enable_event,
+	.hw_config		= snbep_qpi_hw_config,
+	.get_constraint		= uncore_get_constraint,
+	.put_constraint		= uncore_put_constraint,
+};
+
+#define SNBEP_UNCORE_PCI_COMMON_INIT()				\
+	.perf_ctr	= SNBEP_PCI_PMON_CTR0,			\
+	.event_ctl	= SNBEP_PCI_PMON_CTL0,			\
+	.event_mask	= SNBEP_PMON_RAW_EVENT_MASK,		\
+	.box_ctl	= SNBEP_PCI_PMON_BOX_CTL,		\
+	.ops		= &snbep_uncore_pci_ops,		\
+	.format_group	= &snbep_uncore_format_group
+
+static struct intel_uncore_type snbep_uncore_ha = {
+	.name		= "ha",
+	.num_counters   = 4,
+	.num_boxes	= 1,
+	.perf_ctr_bits	= 48,
+	SNBEP_UNCORE_PCI_COMMON_INIT(),
+};
+
+static struct intel_uncore_type snbep_uncore_imc = {
+	.name		= "imc",
+	.num_counters   = 4,
+	.num_boxes	= 4,
+	.perf_ctr_bits	= 48,
+	.fixed_ctr_bits	= 48,
+	.fixed_ctr	= SNBEP_MC_CHy_PCI_PMON_FIXED_CTR,
+	.fixed_ctl	= SNBEP_MC_CHy_PCI_PMON_FIXED_CTL,
+	.event_descs	= snbep_uncore_imc_events,
+	SNBEP_UNCORE_PCI_COMMON_INIT(),
+};
+
+static struct intel_uncore_type snbep_uncore_qpi = {
+	.name			= "qpi",
+	.num_counters		= 4,
+	.num_boxes		= 2,
+	.perf_ctr_bits		= 48,
+	.perf_ctr		= SNBEP_PCI_PMON_CTR0,
+	.event_ctl		= SNBEP_PCI_PMON_CTL0,
+	.event_mask		= SNBEP_QPI_PCI_PMON_RAW_EVENT_MASK,
+	.box_ctl		= SNBEP_PCI_PMON_BOX_CTL,
+	.num_shared_regs	= 1,
+	.ops			= &snbep_uncore_qpi_ops,
+	.event_descs		= snbep_uncore_qpi_events,
+	.format_group		= &snbep_uncore_qpi_format_group,
+};
+
+
+static struct intel_uncore_type snbep_uncore_r2pcie = {
+	.name		= "r2pcie",
+	.num_counters   = 4,
+	.num_boxes	= 1,
+	.perf_ctr_bits	= 44,
+	.constraints	= snbep_uncore_r2pcie_constraints,
+	SNBEP_UNCORE_PCI_COMMON_INIT(),
+};
+
+static struct intel_uncore_type snbep_uncore_r3qpi = {
+	.name		= "r3qpi",
+	.num_counters   = 3,
+	.num_boxes	= 2,
+	.perf_ctr_bits	= 44,
+	.constraints	= snbep_uncore_r3qpi_constraints,
+	SNBEP_UNCORE_PCI_COMMON_INIT(),
+};
+
+enum {
+	SNBEP_PCI_UNCORE_HA,
+	SNBEP_PCI_UNCORE_IMC,
+	SNBEP_PCI_UNCORE_QPI,
+	SNBEP_PCI_UNCORE_R2PCIE,
+	SNBEP_PCI_UNCORE_R3QPI,
+};
+
+static struct intel_uncore_type *snbep_pci_uncores[] = {
+	[SNBEP_PCI_UNCORE_HA]		= &snbep_uncore_ha,
+	[SNBEP_PCI_UNCORE_IMC]		= &snbep_uncore_imc,
+	[SNBEP_PCI_UNCORE_QPI]		= &snbep_uncore_qpi,
+	[SNBEP_PCI_UNCORE_R2PCIE]	= &snbep_uncore_r2pcie,
+	[SNBEP_PCI_UNCORE_R3QPI]	= &snbep_uncore_r3qpi,
+	NULL,
+};
+
+static const struct pci_device_id snbep_uncore_pci_ids[] = {
+	{ /* Home Agent */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_HA),
+		.driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_HA, 0),
+	},
+	{ /* MC Channel 0 */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_IMC0),
+		.driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_IMC, 0),
+	},
+	{ /* MC Channel 1 */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_IMC1),
+		.driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_IMC, 1),
+	},
+	{ /* MC Channel 2 */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_IMC2),
+		.driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_IMC, 2),
+	},
+	{ /* MC Channel 3 */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_IMC3),
+		.driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_IMC, 3),
+	},
+	{ /* QPI Port 0 */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_QPI0),
+		.driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_QPI, 0),
+	},
+	{ /* QPI Port 1 */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_QPI1),
+		.driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_QPI, 1),
+	},
+	{ /* R2PCIe */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_R2PCIE),
+		.driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_R2PCIE, 0),
+	},
+	{ /* R3QPI Link 0 */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_R3QPI0),
+		.driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_R3QPI, 0),
+	},
+	{ /* R3QPI Link 1 */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_R3QPI1),
+		.driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_R3QPI, 1),
+	},
+	{ /* QPI Port 0 filter  */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x3c86),
+		.driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV,
+						   SNBEP_PCI_QPI_PORT0_FILTER),
+	},
+	{ /* QPI Port 0 filter  */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x3c96),
+		.driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV,
+						   SNBEP_PCI_QPI_PORT1_FILTER),
+	},
+	{ /* end: all zeroes */ }
+};
+
+static struct pci_driver snbep_uncore_pci_driver = {
+	.name		= "snbep_uncore",
+	.id_table	= snbep_uncore_pci_ids,
+};
+
+/*
+ * build pci bus to socket mapping
+ */
+static int snbep_pci2phy_map_init(int devid)
+{
+	struct pci_dev *ubox_dev = NULL;
+	int i, bus, nodeid;
+	int err = 0;
+	u32 config = 0;
+
+	while (1) {
+		/* find the UBOX device */
+		ubox_dev = pci_get_device(PCI_VENDOR_ID_INTEL, devid, ubox_dev);
+		if (!ubox_dev)
+			break;
+		bus = ubox_dev->bus->number;
+		/* get the Node ID of the local register */
+		err = pci_read_config_dword(ubox_dev, 0x40, &config);
+		if (err)
+			break;
+		nodeid = config;
+		/* get the Node ID mapping */
+		err = pci_read_config_dword(ubox_dev, 0x54, &config);
+		if (err)
+			break;
+		/*
+		 * every three bits in the Node ID mapping register maps
+		 * to a particular node.
+		 */
+		for (i = 0; i < 8; i++) {
+			if (nodeid == ((config >> (3 * i)) & 0x7)) {
+				uncore_pcibus_to_physid[bus] = i;
+				break;
+			}
+		}
+	}
+
+	if (!err) {
+		/*
+		 * For PCI bus with no UBOX device, find the next bus
+		 * that has UBOX device and use its mapping.
+		 */
+		i = -1;
+		for (bus = 255; bus >= 0; bus--) {
+			if (uncore_pcibus_to_physid[bus] >= 0)
+				i = uncore_pcibus_to_physid[bus];
+			else
+				uncore_pcibus_to_physid[bus] = i;
+		}
+	}
+
+	if (ubox_dev)
+		pci_dev_put(ubox_dev);
+
+	return err ? pcibios_err_to_errno(err) : 0;
+}
+
+int snbep_uncore_pci_init(void)
+{
+	int ret = snbep_pci2phy_map_init(0x3ce0);
+	if (ret)
+		return ret;
+	uncore_pci_uncores = snbep_pci_uncores;
+	uncore_pci_driver = &snbep_uncore_pci_driver;
+	return 0;
+}
+/* end of Sandy Bridge-EP uncore support */
+
+/* IvyTown uncore support */
+static void ivbep_uncore_msr_init_box(struct intel_uncore_box *box)
+{
+	unsigned msr = uncore_msr_box_ctl(box);
+	if (msr)
+		wrmsrl(msr, IVBEP_PMON_BOX_CTL_INT);
+}
+
+static void ivbep_uncore_pci_init_box(struct intel_uncore_box *box)
+{
+	struct pci_dev *pdev = box->pci_dev;
+
+	pci_write_config_dword(pdev, SNBEP_PCI_PMON_BOX_CTL, IVBEP_PMON_BOX_CTL_INT);
+}
+
+#define IVBEP_UNCORE_MSR_OPS_COMMON_INIT()			\
+	.init_box	= ivbep_uncore_msr_init_box,		\
+	.disable_box	= snbep_uncore_msr_disable_box,		\
+	.enable_box	= snbep_uncore_msr_enable_box,		\
+	.disable_event	= snbep_uncore_msr_disable_event,	\
+	.enable_event	= snbep_uncore_msr_enable_event,	\
+	.read_counter	= uncore_msr_read_counter
+
+static struct intel_uncore_ops ivbep_uncore_msr_ops = {
+	IVBEP_UNCORE_MSR_OPS_COMMON_INIT(),
+};
+
+static struct intel_uncore_ops ivbep_uncore_pci_ops = {
+	.init_box	= ivbep_uncore_pci_init_box,
+	.disable_box	= snbep_uncore_pci_disable_box,
+	.enable_box	= snbep_uncore_pci_enable_box,
+	.disable_event	= snbep_uncore_pci_disable_event,
+	.enable_event	= snbep_uncore_pci_enable_event,
+	.read_counter	= snbep_uncore_pci_read_counter,
+};
+
+#define IVBEP_UNCORE_PCI_COMMON_INIT()				\
+	.perf_ctr	= SNBEP_PCI_PMON_CTR0,			\
+	.event_ctl	= SNBEP_PCI_PMON_CTL0,			\
+	.event_mask	= IVBEP_PMON_RAW_EVENT_MASK,		\
+	.box_ctl	= SNBEP_PCI_PMON_BOX_CTL,		\
+	.ops		= &ivbep_uncore_pci_ops,			\
+	.format_group	= &ivbep_uncore_format_group
+
+static struct attribute *ivbep_uncore_formats_attr[] = {
+	&format_attr_event.attr,
+	&format_attr_umask.attr,
+	&format_attr_edge.attr,
+	&format_attr_inv.attr,
+	&format_attr_thresh8.attr,
+	NULL,
+};
+
+static struct attribute *ivbep_uncore_ubox_formats_attr[] = {
+	&format_attr_event.attr,
+	&format_attr_umask.attr,
+	&format_attr_edge.attr,
+	&format_attr_inv.attr,
+	&format_attr_thresh5.attr,
+	NULL,
+};
+
+static struct attribute *ivbep_uncore_cbox_formats_attr[] = {
+	&format_attr_event.attr,
+	&format_attr_umask.attr,
+	&format_attr_edge.attr,
+	&format_attr_tid_en.attr,
+	&format_attr_thresh8.attr,
+	&format_attr_filter_tid.attr,
+	&format_attr_filter_link.attr,
+	&format_attr_filter_state2.attr,
+	&format_attr_filter_nid2.attr,
+	&format_attr_filter_opc2.attr,
+	NULL,
+};
+
+static struct attribute *ivbep_uncore_pcu_formats_attr[] = {
+	&format_attr_event_ext.attr,
+	&format_attr_occ_sel.attr,
+	&format_attr_edge.attr,
+	&format_attr_thresh5.attr,
+	&format_attr_occ_invert.attr,
+	&format_attr_occ_edge.attr,
+	&format_attr_filter_band0.attr,
+	&format_attr_filter_band1.attr,
+	&format_attr_filter_band2.attr,
+	&format_attr_filter_band3.attr,
+	NULL,
+};
+
+static struct attribute *ivbep_uncore_qpi_formats_attr[] = {
+	&format_attr_event_ext.attr,
+	&format_attr_umask.attr,
+	&format_attr_edge.attr,
+	&format_attr_thresh8.attr,
+	&format_attr_match_rds.attr,
+	&format_attr_match_rnid30.attr,
+	&format_attr_match_rnid4.attr,
+	&format_attr_match_dnid.attr,
+	&format_attr_match_mc.attr,
+	&format_attr_match_opc.attr,
+	&format_attr_match_vnw.attr,
+	&format_attr_match0.attr,
+	&format_attr_match1.attr,
+	&format_attr_mask_rds.attr,
+	&format_attr_mask_rnid30.attr,
+	&format_attr_mask_rnid4.attr,
+	&format_attr_mask_dnid.attr,
+	&format_attr_mask_mc.attr,
+	&format_attr_mask_opc.attr,
+	&format_attr_mask_vnw.attr,
+	&format_attr_mask0.attr,
+	&format_attr_mask1.attr,
+	NULL,
+};
+
+static struct attribute_group ivbep_uncore_format_group = {
+	.name = "format",
+	.attrs = ivbep_uncore_formats_attr,
+};
+
+static struct attribute_group ivbep_uncore_ubox_format_group = {
+	.name = "format",
+	.attrs = ivbep_uncore_ubox_formats_attr,
+};
+
+static struct attribute_group ivbep_uncore_cbox_format_group = {
+	.name = "format",
+	.attrs = ivbep_uncore_cbox_formats_attr,
+};
+
+static struct attribute_group ivbep_uncore_pcu_format_group = {
+	.name = "format",
+	.attrs = ivbep_uncore_pcu_formats_attr,
+};
+
+static struct attribute_group ivbep_uncore_qpi_format_group = {
+	.name = "format",
+	.attrs = ivbep_uncore_qpi_formats_attr,
+};
+
+static struct intel_uncore_type ivbep_uncore_ubox = {
+	.name		= "ubox",
+	.num_counters   = 2,
+	.num_boxes	= 1,
+	.perf_ctr_bits	= 44,
+	.fixed_ctr_bits	= 48,
+	.perf_ctr	= SNBEP_U_MSR_PMON_CTR0,
+	.event_ctl	= SNBEP_U_MSR_PMON_CTL0,
+	.event_mask	= IVBEP_U_MSR_PMON_RAW_EVENT_MASK,
+	.fixed_ctr	= SNBEP_U_MSR_PMON_UCLK_FIXED_CTR,
+	.fixed_ctl	= SNBEP_U_MSR_PMON_UCLK_FIXED_CTL,
+	.ops		= &ivbep_uncore_msr_ops,
+	.format_group	= &ivbep_uncore_ubox_format_group,
+};
+
+static struct extra_reg ivbep_uncore_cbox_extra_regs[] = {
+	SNBEP_CBO_EVENT_EXTRA_REG(SNBEP_CBO_PMON_CTL_TID_EN,
+				  SNBEP_CBO_PMON_CTL_TID_EN, 0x1),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x1031, 0x10ff, 0x2),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x1134, 0xffff, 0x4),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x4134, 0xffff, 0xc),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x5134, 0xffff, 0xc),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x0334, 0xffff, 0x4),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x4334, 0xffff, 0xc),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x0534, 0xffff, 0x4),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x4534, 0xffff, 0xc),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x0934, 0xffff, 0x4),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x4934, 0xffff, 0xc),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x0135, 0xffff, 0x10),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x0335, 0xffff, 0x10),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x2135, 0xffff, 0x10),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x2335, 0xffff, 0x10),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x4135, 0xffff, 0x18),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x4335, 0xffff, 0x18),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x4435, 0xffff, 0x8),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x4835, 0xffff, 0x8),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x4a35, 0xffff, 0x8),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x5035, 0xffff, 0x8),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x8135, 0xffff, 0x10),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x8335, 0xffff, 0x10),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x0136, 0xffff, 0x10),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x0336, 0xffff, 0x10),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x2136, 0xffff, 0x10),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x2336, 0xffff, 0x10),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x4136, 0xffff, 0x18),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x4336, 0xffff, 0x18),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x4436, 0xffff, 0x8),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x4836, 0xffff, 0x8),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x4a36, 0xffff, 0x8),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x5036, 0xffff, 0x8),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x8136, 0xffff, 0x10),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x8336, 0xffff, 0x10),
+	SNBEP_CBO_EVENT_EXTRA_REG(0x4037, 0x40ff, 0x8),
+	EVENT_EXTRA_END
+};
+
+static u64 ivbep_cbox_filter_mask(int fields)
+{
+	u64 mask = 0;
+
+	if (fields & 0x1)
+		mask |= IVBEP_CB0_MSR_PMON_BOX_FILTER_TID;
+	if (fields & 0x2)
+		mask |= IVBEP_CB0_MSR_PMON_BOX_FILTER_LINK;
+	if (fields & 0x4)
+		mask |= IVBEP_CB0_MSR_PMON_BOX_FILTER_STATE;
+	if (fields & 0x8)
+		mask |= IVBEP_CB0_MSR_PMON_BOX_FILTER_NID;
+	if (fields & 0x10)
+		mask |= IVBEP_CB0_MSR_PMON_BOX_FILTER_OPC;
+
+	return mask;
+}
+
+static struct event_constraint *
+ivbep_cbox_get_constraint(struct intel_uncore_box *box, struct perf_event *event)
+{
+	return __snbep_cbox_get_constraint(box, event, ivbep_cbox_filter_mask);
+}
+
+static int ivbep_cbox_hw_config(struct intel_uncore_box *box, struct perf_event *event)
+{
+	struct hw_perf_event_extra *reg1 = &event->hw.extra_reg;
+	struct extra_reg *er;
+	int idx = 0;
+
+	for (er = ivbep_uncore_cbox_extra_regs; er->msr; er++) {
+		if (er->event != (event->hw.config & er->config_mask))
+			continue;
+		idx |= er->idx;
+	}
+
+	if (idx) {
+		reg1->reg = SNBEP_C0_MSR_PMON_BOX_FILTER +
+			SNBEP_CBO_MSR_OFFSET * box->pmu->pmu_idx;
+		reg1->config = event->attr.config1 & ivbep_cbox_filter_mask(idx);
+		reg1->idx = idx;
+	}
+	return 0;
+}
+
+static void ivbep_cbox_enable_event(struct intel_uncore_box *box, struct perf_event *event)
+{
+	struct hw_perf_event *hwc = &event->hw;
+	struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
+
+	if (reg1->idx != EXTRA_REG_NONE) {
+		u64 filter = uncore_shared_reg_config(box, 0);
+		wrmsrl(reg1->reg, filter & 0xffffffff);
+		wrmsrl(reg1->reg + 6, filter >> 32);
+	}
+
+	wrmsrl(hwc->config_base, hwc->config | SNBEP_PMON_CTL_EN);
+}
+
+static struct intel_uncore_ops ivbep_uncore_cbox_ops = {
+	.init_box		= ivbep_uncore_msr_init_box,
+	.disable_box		= snbep_uncore_msr_disable_box,
+	.enable_box		= snbep_uncore_msr_enable_box,
+	.disable_event		= snbep_uncore_msr_disable_event,
+	.enable_event		= ivbep_cbox_enable_event,
+	.read_counter		= uncore_msr_read_counter,
+	.hw_config		= ivbep_cbox_hw_config,
+	.get_constraint		= ivbep_cbox_get_constraint,
+	.put_constraint		= snbep_cbox_put_constraint,
+};
+
+static struct intel_uncore_type ivbep_uncore_cbox = {
+	.name			= "cbox",
+	.num_counters		= 4,
+	.num_boxes		= 15,
+	.perf_ctr_bits		= 44,
+	.event_ctl		= SNBEP_C0_MSR_PMON_CTL0,
+	.perf_ctr		= SNBEP_C0_MSR_PMON_CTR0,
+	.event_mask		= IVBEP_CBO_MSR_PMON_RAW_EVENT_MASK,
+	.box_ctl		= SNBEP_C0_MSR_PMON_BOX_CTL,
+	.msr_offset		= SNBEP_CBO_MSR_OFFSET,
+	.num_shared_regs	= 1,
+	.constraints		= snbep_uncore_cbox_constraints,
+	.ops			= &ivbep_uncore_cbox_ops,
+	.format_group		= &ivbep_uncore_cbox_format_group,
+};
+
+static struct intel_uncore_ops ivbep_uncore_pcu_ops = {
+	IVBEP_UNCORE_MSR_OPS_COMMON_INIT(),
+	.hw_config		= snbep_pcu_hw_config,
+	.get_constraint		= snbep_pcu_get_constraint,
+	.put_constraint		= snbep_pcu_put_constraint,
+};
+
+static struct intel_uncore_type ivbep_uncore_pcu = {
+	.name			= "pcu",
+	.num_counters		= 4,
+	.num_boxes		= 1,
+	.perf_ctr_bits		= 48,
+	.perf_ctr		= SNBEP_PCU_MSR_PMON_CTR0,
+	.event_ctl		= SNBEP_PCU_MSR_PMON_CTL0,
+	.event_mask		= IVBEP_PCU_MSR_PMON_RAW_EVENT_MASK,
+	.box_ctl		= SNBEP_PCU_MSR_PMON_BOX_CTL,
+	.num_shared_regs	= 1,
+	.ops			= &ivbep_uncore_pcu_ops,
+	.format_group		= &ivbep_uncore_pcu_format_group,
+};
+
+static struct intel_uncore_type *ivbep_msr_uncores[] = {
+	&ivbep_uncore_ubox,
+	&ivbep_uncore_cbox,
+	&ivbep_uncore_pcu,
+	NULL,
+};
+
+void ivbep_uncore_cpu_init(void)
+{
+	if (ivbep_uncore_cbox.num_boxes > boot_cpu_data.x86_max_cores)
+		ivbep_uncore_cbox.num_boxes = boot_cpu_data.x86_max_cores;
+	uncore_msr_uncores = ivbep_msr_uncores;
+}
+
+static struct intel_uncore_type ivbep_uncore_ha = {
+	.name		= "ha",
+	.num_counters   = 4,
+	.num_boxes	= 2,
+	.perf_ctr_bits	= 48,
+	IVBEP_UNCORE_PCI_COMMON_INIT(),
+};
+
+static struct intel_uncore_type ivbep_uncore_imc = {
+	.name		= "imc",
+	.num_counters   = 4,
+	.num_boxes	= 8,
+	.perf_ctr_bits	= 48,
+	.fixed_ctr_bits	= 48,
+	.fixed_ctr	= SNBEP_MC_CHy_PCI_PMON_FIXED_CTR,
+	.fixed_ctl	= SNBEP_MC_CHy_PCI_PMON_FIXED_CTL,
+	.event_descs	= snbep_uncore_imc_events,
+	IVBEP_UNCORE_PCI_COMMON_INIT(),
+};
+
+/* registers in IRP boxes are not properly aligned */
+static unsigned ivbep_uncore_irp_ctls[] = {0xd8, 0xdc, 0xe0, 0xe4};
+static unsigned ivbep_uncore_irp_ctrs[] = {0xa0, 0xb0, 0xb8, 0xc0};
+
+static void ivbep_uncore_irp_enable_event(struct intel_uncore_box *box, struct perf_event *event)
+{
+	struct pci_dev *pdev = box->pci_dev;
+	struct hw_perf_event *hwc = &event->hw;
+
+	pci_write_config_dword(pdev, ivbep_uncore_irp_ctls[hwc->idx],
+			       hwc->config | SNBEP_PMON_CTL_EN);
+}
+
+static void ivbep_uncore_irp_disable_event(struct intel_uncore_box *box, struct perf_event *event)
+{
+	struct pci_dev *pdev = box->pci_dev;
+	struct hw_perf_event *hwc = &event->hw;
+
+	pci_write_config_dword(pdev, ivbep_uncore_irp_ctls[hwc->idx], hwc->config);
+}
+
+static u64 ivbep_uncore_irp_read_counter(struct intel_uncore_box *box, struct perf_event *event)
+{
+	struct pci_dev *pdev = box->pci_dev;
+	struct hw_perf_event *hwc = &event->hw;
+	u64 count = 0;
+
+	pci_read_config_dword(pdev, ivbep_uncore_irp_ctrs[hwc->idx], (u32 *)&count);
+	pci_read_config_dword(pdev, ivbep_uncore_irp_ctrs[hwc->idx] + 4, (u32 *)&count + 1);
+
+	return count;
+}
+
+static struct intel_uncore_ops ivbep_uncore_irp_ops = {
+	.init_box	= ivbep_uncore_pci_init_box,
+	.disable_box	= snbep_uncore_pci_disable_box,
+	.enable_box	= snbep_uncore_pci_enable_box,
+	.disable_event	= ivbep_uncore_irp_disable_event,
+	.enable_event	= ivbep_uncore_irp_enable_event,
+	.read_counter	= ivbep_uncore_irp_read_counter,
+};
+
+static struct intel_uncore_type ivbep_uncore_irp = {
+	.name			= "irp",
+	.num_counters		= 4,
+	.num_boxes		= 1,
+	.perf_ctr_bits		= 48,
+	.event_mask		= IVBEP_PMON_RAW_EVENT_MASK,
+	.box_ctl		= SNBEP_PCI_PMON_BOX_CTL,
+	.ops			= &ivbep_uncore_irp_ops,
+	.format_group		= &ivbep_uncore_format_group,
+};
+
+static struct intel_uncore_ops ivbep_uncore_qpi_ops = {
+	.init_box	= ivbep_uncore_pci_init_box,
+	.disable_box	= snbep_uncore_pci_disable_box,
+	.enable_box	= snbep_uncore_pci_enable_box,
+	.disable_event	= snbep_uncore_pci_disable_event,
+	.enable_event	= snbep_qpi_enable_event,
+	.read_counter	= snbep_uncore_pci_read_counter,
+	.hw_config	= snbep_qpi_hw_config,
+	.get_constraint	= uncore_get_constraint,
+	.put_constraint	= uncore_put_constraint,
+};
+
+static struct intel_uncore_type ivbep_uncore_qpi = {
+	.name			= "qpi",
+	.num_counters		= 4,
+	.num_boxes		= 3,
+	.perf_ctr_bits		= 48,
+	.perf_ctr		= SNBEP_PCI_PMON_CTR0,
+	.event_ctl		= SNBEP_PCI_PMON_CTL0,
+	.event_mask		= IVBEP_QPI_PCI_PMON_RAW_EVENT_MASK,
+	.box_ctl		= SNBEP_PCI_PMON_BOX_CTL,
+	.num_shared_regs	= 1,
+	.ops			= &ivbep_uncore_qpi_ops,
+	.format_group		= &ivbep_uncore_qpi_format_group,
+};
+
+static struct intel_uncore_type ivbep_uncore_r2pcie = {
+	.name		= "r2pcie",
+	.num_counters   = 4,
+	.num_boxes	= 1,
+	.perf_ctr_bits	= 44,
+	.constraints	= snbep_uncore_r2pcie_constraints,
+	IVBEP_UNCORE_PCI_COMMON_INIT(),
+};
+
+static struct intel_uncore_type ivbep_uncore_r3qpi = {
+	.name		= "r3qpi",
+	.num_counters   = 3,
+	.num_boxes	= 2,
+	.perf_ctr_bits	= 44,
+	.constraints	= snbep_uncore_r3qpi_constraints,
+	IVBEP_UNCORE_PCI_COMMON_INIT(),
+};
+
+enum {
+	IVBEP_PCI_UNCORE_HA,
+	IVBEP_PCI_UNCORE_IMC,
+	IVBEP_PCI_UNCORE_IRP,
+	IVBEP_PCI_UNCORE_QPI,
+	IVBEP_PCI_UNCORE_R2PCIE,
+	IVBEP_PCI_UNCORE_R3QPI,
+};
+
+static struct intel_uncore_type *ivbep_pci_uncores[] = {
+	[IVBEP_PCI_UNCORE_HA]	= &ivbep_uncore_ha,
+	[IVBEP_PCI_UNCORE_IMC]	= &ivbep_uncore_imc,
+	[IVBEP_PCI_UNCORE_IRP]	= &ivbep_uncore_irp,
+	[IVBEP_PCI_UNCORE_QPI]	= &ivbep_uncore_qpi,
+	[IVBEP_PCI_UNCORE_R2PCIE]	= &ivbep_uncore_r2pcie,
+	[IVBEP_PCI_UNCORE_R3QPI]	= &ivbep_uncore_r3qpi,
+	NULL,
+};
+
+static const struct pci_device_id ivbep_uncore_pci_ids[] = {
+	{ /* Home Agent 0 */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe30),
+		.driver_data = UNCORE_PCI_DEV_DATA(IVBEP_PCI_UNCORE_HA, 0),
+	},
+	{ /* Home Agent 1 */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe38),
+		.driver_data = UNCORE_PCI_DEV_DATA(IVBEP_PCI_UNCORE_HA, 1),
+	},
+	{ /* MC0 Channel 0 */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xeb4),
+		.driver_data = UNCORE_PCI_DEV_DATA(IVBEP_PCI_UNCORE_IMC, 0),
+	},
+	{ /* MC0 Channel 1 */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xeb5),
+		.driver_data = UNCORE_PCI_DEV_DATA(IVBEP_PCI_UNCORE_IMC, 1),
+	},
+	{ /* MC0 Channel 3 */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xeb0),
+		.driver_data = UNCORE_PCI_DEV_DATA(IVBEP_PCI_UNCORE_IMC, 2),
+	},
+	{ /* MC0 Channel 4 */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xeb1),
+		.driver_data = UNCORE_PCI_DEV_DATA(IVBEP_PCI_UNCORE_IMC, 3),
+	},
+	{ /* MC1 Channel 0 */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xef4),
+		.driver_data = UNCORE_PCI_DEV_DATA(IVBEP_PCI_UNCORE_IMC, 4),
+	},
+	{ /* MC1 Channel 1 */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xef5),
+		.driver_data = UNCORE_PCI_DEV_DATA(IVBEP_PCI_UNCORE_IMC, 5),
+	},
+	{ /* MC1 Channel 3 */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xef0),
+		.driver_data = UNCORE_PCI_DEV_DATA(IVBEP_PCI_UNCORE_IMC, 6),
+	},
+	{ /* MC1 Channel 4 */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xef1),
+		.driver_data = UNCORE_PCI_DEV_DATA(IVBEP_PCI_UNCORE_IMC, 7),
+	},
+	{ /* IRP */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe39),
+		.driver_data = UNCORE_PCI_DEV_DATA(IVBEP_PCI_UNCORE_IRP, 0),
+	},
+	{ /* QPI0 Port 0 */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe32),
+		.driver_data = UNCORE_PCI_DEV_DATA(IVBEP_PCI_UNCORE_QPI, 0),
+	},
+	{ /* QPI0 Port 1 */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe33),
+		.driver_data = UNCORE_PCI_DEV_DATA(IVBEP_PCI_UNCORE_QPI, 1),
+	},
+	{ /* QPI1 Port 2 */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe3a),
+		.driver_data = UNCORE_PCI_DEV_DATA(IVBEP_PCI_UNCORE_QPI, 2),
+	},
+	{ /* R2PCIe */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe34),
+		.driver_data = UNCORE_PCI_DEV_DATA(IVBEP_PCI_UNCORE_R2PCIE, 0),
+	},
+	{ /* R3QPI0 Link 0 */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe36),
+		.driver_data = UNCORE_PCI_DEV_DATA(IVBEP_PCI_UNCORE_R3QPI, 0),
+	},
+	{ /* R3QPI0 Link 1 */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe37),
+		.driver_data = UNCORE_PCI_DEV_DATA(IVBEP_PCI_UNCORE_R3QPI, 1),
+	},
+	{ /* R3QPI1 Link 2 */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe3e),
+		.driver_data = UNCORE_PCI_DEV_DATA(IVBEP_PCI_UNCORE_R3QPI, 2),
+	},
+	{ /* QPI Port 0 filter  */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe86),
+		.driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV,
+						   SNBEP_PCI_QPI_PORT0_FILTER),
+	},
+	{ /* QPI Port 0 filter  */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe96),
+		.driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV,
+						   SNBEP_PCI_QPI_PORT1_FILTER),
+	},
+	{ /* end: all zeroes */ }
+};
+
+static struct pci_driver ivbep_uncore_pci_driver = {
+	.name		= "ivbep_uncore",
+	.id_table	= ivbep_uncore_pci_ids,
+};
+
+int ivbep_uncore_pci_init(void)
+{
+	int ret = snbep_pci2phy_map_init(0x0e1e);
+	if (ret)
+		return ret;
+	uncore_pci_uncores = ivbep_pci_uncores;
+	uncore_pci_driver = &ivbep_uncore_pci_driver;
+	return 0;
+}
+/* end of IvyTown uncore support */
diff --git a/include/linux/jump_label.h b/include/linux/jump_label.h
index 784304b222b3e6..98f923b6a0eaa7 100644
--- a/include/linux/jump_label.h
+++ b/include/linux/jump_label.h
@@ -8,28 +8,28 @@
  * Copyright (C) 2011-2012 Peter Zijlstra <pzijlstr@redhat.com>
  *
  * Jump labels provide an interface to generate dynamic branches using
- * self-modifying code. Assuming toolchain and architecture support the result
- * of a "if (static_key_false(&key))" statement is a unconditional branch (which
+ * self-modifying code. Assuming toolchain and architecture support, the result
+ * of a "if (static_key_false(&key))" statement is an unconditional branch (which
  * defaults to false - and the true block is placed out of line).
  *
  * However at runtime we can change the branch target using
  * static_key_slow_{inc,dec}(). These function as a 'reference' count on the key
- * object and for as long as there are references all branches referring to
+ * object, and for as long as there are references all branches referring to
  * that particular key will point to the (out of line) true block.
  *
- * Since this relies on modifying code the static_key_slow_{inc,dec}() functions
+ * Since this relies on modifying code, the static_key_slow_{inc,dec}() functions
  * must be considered absolute slow paths (machine wide synchronization etc.).
- * OTOH, since the affected branches are unconditional their runtime overhead
+ * OTOH, since the affected branches are unconditional, their runtime overhead
  * will be absolutely minimal, esp. in the default (off) case where the total
  * effect is a single NOP of appropriate size. The on case will patch in a jump
  * to the out-of-line block.
  *
- * When the control is directly exposed to userspace it is prudent to delay the
+ * When the control is directly exposed to userspace, it is prudent to delay the
  * decrement to avoid high frequency code modifications which can (and do)
  * cause significant performance degradation. Struct static_key_deferred and
  * static_key_slow_dec_deferred() provide for this.
  *
- * Lacking toolchain and or architecture support, it falls back to a simple
+ * Lacking toolchain and or architecture support, jump labels fall back to a simple
  * conditional branch.
  *
  * struct static_key my_key = STATIC_KEY_INIT_TRUE;
@@ -43,8 +43,7 @@
  *
  * Not initializing the key (static data is initialized to 0s anyway) is the
  * same as using STATIC_KEY_INIT_FALSE.
- *
-*/
+ */
 
 #include <linux/types.h>
 #include <linux/compiler.h>
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 707617a8c0f6c6..893a0d07986f52 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -52,6 +52,7 @@ struct perf_guest_info_callbacks {
 #include <linux/atomic.h>
 #include <linux/sysfs.h>
 #include <linux/perf_regs.h>
+#include <linux/workqueue.h>
 #include <asm/local.h>
 
 struct perf_callchain_entry {
@@ -268,6 +269,7 @@ struct pmu {
  * enum perf_event_active_state - the states of a event
  */
 enum perf_event_active_state {
+	PERF_EVENT_STATE_EXIT		= -3,
 	PERF_EVENT_STATE_ERROR		= -2,
 	PERF_EVENT_STATE_OFF		= -1,
 	PERF_EVENT_STATE_INACTIVE	=  0,
@@ -507,6 +509,9 @@ struct perf_event_context {
 	int				nr_cgroups;	 /* cgroup evts */
 	int				nr_branch_stack; /* branch_stack evt */
 	struct rcu_head			rcu_head;
+
+	struct delayed_work		orphans_remove;
+	bool				orphans_remove_sched;
 };
 
 /*
@@ -604,6 +609,13 @@ struct perf_sample_data {
 	u64				txn;
 };
 
+/* default value for data source */
+#define PERF_MEM_NA (PERF_MEM_S(OP, NA)   |\
+		    PERF_MEM_S(LVL, NA)   |\
+		    PERF_MEM_S(SNOOP, NA) |\
+		    PERF_MEM_S(LOCK, NA)  |\
+		    PERF_MEM_S(TLB, NA))
+
 static inline void perf_sample_data_init(struct perf_sample_data *data,
 					 u64 addr, u64 period)
 {
@@ -616,7 +628,7 @@ static inline void perf_sample_data_init(struct perf_sample_data *data,
 	data->regs_user.regs = NULL;
 	data->stack_user_size = 0;
 	data->weight = 0;
-	data->data_src.val = 0;
+	data->data_src.val = PERF_MEM_NA;
 	data->txn = 0;
 }
 
diff --git a/kernel/events/core.c b/kernel/events/core.c
index f9c1ed002dbc81..01bd42ed516c1a 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -47,6 +47,8 @@
 
 #include <asm/irq_regs.h>
 
+static struct workqueue_struct *perf_wq;
+
 struct remote_function_call {
 	struct task_struct	*p;
 	int			(*func)(void *info);
@@ -120,6 +122,13 @@ static int cpu_function_call(int cpu, int (*func) (void *info), void *info)
 	return data.ret;
 }
 
+#define EVENT_OWNER_KERNEL ((void *) -1)
+
+static bool is_kernel_event(struct perf_event *event)
+{
+	return event->owner == EVENT_OWNER_KERNEL;
+}
+
 #define PERF_FLAG_ALL (PERF_FLAG_FD_NO_GROUP |\
 		       PERF_FLAG_FD_OUTPUT  |\
 		       PERF_FLAG_PID_CGROUP |\
@@ -1375,6 +1384,45 @@ out:
 		perf_event__header_size(tmp);
 }
 
+/*
+ * User event without the task.
+ */
+static bool is_orphaned_event(struct perf_event *event)
+{
+	return event && !is_kernel_event(event) && !event->owner;
+}
+
+/*
+ * Event has a parent but parent's task finished and it's
+ * alive only because of children holding refference.
+ */
+static bool is_orphaned_child(struct perf_event *event)
+{
+	return is_orphaned_event(event->parent);
+}
+
+static void orphans_remove_work(struct work_struct *work);
+
+static void schedule_orphans_remove(struct perf_event_context *ctx)
+{
+	if (!ctx->task || ctx->orphans_remove_sched || !perf_wq)
+		return;
+
+	if (queue_delayed_work(perf_wq, &ctx->orphans_remove, 1)) {
+		get_ctx(ctx);
+		ctx->orphans_remove_sched = true;
+	}
+}
+
+static int __init perf_workqueue_init(void)
+{
+	perf_wq = create_singlethread_workqueue("perf");
+	WARN(!perf_wq, "failed to create perf workqueue\n");
+	return perf_wq ? 0 : -1;
+}
+
+core_initcall(perf_workqueue_init);
+
 static inline int
 event_filter_match(struct perf_event *event)
 {
@@ -1424,6 +1472,9 @@ event_sched_out(struct perf_event *event,
 	if (event->attr.exclusive || !cpuctx->active_oncpu)
 		cpuctx->exclusive = 0;
 
+	if (is_orphaned_child(event))
+		schedule_orphans_remove(ctx);
+
 	perf_pmu_enable(event->pmu);
 }
 
@@ -1726,6 +1777,9 @@ event_sched_in(struct perf_event *event,
 	if (event->attr.exclusive)
 		cpuctx->exclusive = 1;
 
+	if (is_orphaned_child(event))
+		schedule_orphans_remove(ctx);
+
 out:
 	perf_pmu_enable(event->pmu);
 
@@ -3068,6 +3122,7 @@ static void __perf_event_init_context(struct perf_event_context *ctx)
 	INIT_LIST_HEAD(&ctx->flexible_groups);
 	INIT_LIST_HEAD(&ctx->event_list);
 	atomic_set(&ctx->refcount, 1);
+	INIT_DELAYED_WORK(&ctx->orphans_remove, orphans_remove_work);
 }
 
 static struct perf_event_context *
@@ -3313,16 +3368,12 @@ static void free_event(struct perf_event *event)
 }
 
 /*
- * Called when the last reference to the file is gone.
+ * Remove user event from the owner task.
  */
-static void put_event(struct perf_event *event)
+static void perf_remove_from_owner(struct perf_event *event)
 {
-	struct perf_event_context *ctx = event->ctx;
 	struct task_struct *owner;
 
-	if (!atomic_long_dec_and_test(&event->refcount))
-		return;
-
 	rcu_read_lock();
 	owner = ACCESS_ONCE(event->owner);
 	/*
@@ -3355,6 +3406,20 @@ static void put_event(struct perf_event *event)
 		mutex_unlock(&owner->perf_event_mutex);
 		put_task_struct(owner);
 	}
+}
+
+/*
+ * Called when the last reference to the file is gone.
+ */
+static void put_event(struct perf_event *event)
+{
+	struct perf_event_context *ctx = event->ctx;
+
+	if (!atomic_long_dec_and_test(&event->refcount))
+		return;
+
+	if (!is_kernel_event(event))
+		perf_remove_from_owner(event);
 
 	WARN_ON_ONCE(ctx->parent_ctx);
 	/*
@@ -3389,6 +3454,42 @@ static int perf_release(struct inode *inode, struct file *file)
 	return 0;
 }
 
+/*
+ * Remove all orphanes events from the context.
+ */
+static void orphans_remove_work(struct work_struct *work)
+{
+	struct perf_event_context *ctx;
+	struct perf_event *event, *tmp;
+
+	ctx = container_of(work, struct perf_event_context,
+			   orphans_remove.work);
+
+	mutex_lock(&ctx->mutex);
+	list_for_each_entry_safe(event, tmp, &ctx->event_list, event_entry) {
+		struct perf_event *parent_event = event->parent;
+
+		if (!is_orphaned_child(event))
+			continue;
+
+		perf_remove_from_context(event, true);
+
+		mutex_lock(&parent_event->child_mutex);
+		list_del_init(&event->child_list);
+		mutex_unlock(&parent_event->child_mutex);
+
+		free_event(event);
+		put_event(parent_event);
+	}
+
+	raw_spin_lock_irq(&ctx->lock);
+	ctx->orphans_remove_sched = false;
+	raw_spin_unlock_irq(&ctx->lock);
+	mutex_unlock(&ctx->mutex);
+
+	put_ctx(ctx);
+}
+
 u64 perf_event_read_value(struct perf_event *event, u64 *enabled, u64 *running)
 {
 	struct perf_event *child;
@@ -3500,7 +3601,8 @@ perf_read_hw(struct perf_event *event, char __user *buf, size_t count)
 	 * error state (i.e. because it was pinned but it couldn't be
 	 * scheduled on to the CPU at some point).
 	 */
-	if (event->state == PERF_EVENT_STATE_ERROR)
+	if ((event->state == PERF_EVENT_STATE_ERROR) ||
+	    (event->state == PERF_EVENT_STATE_EXIT))
 		return 0;
 
 	if (count < event->read_size)
@@ -3527,7 +3629,12 @@ static unsigned int perf_poll(struct file *file, poll_table *wait)
 {
 	struct perf_event *event = file->private_data;
 	struct ring_buffer *rb;
-	unsigned int events = POLL_HUP;
+	unsigned int events = POLLHUP;
+
+	poll_wait(file, &event->waitq, wait);
+
+	if (event->state == PERF_EVENT_STATE_EXIT)
+		return events;
 
 	/*
 	 * Pin the event->rb by taking event->mmap_mutex; otherwise
@@ -3538,9 +3645,6 @@ static unsigned int perf_poll(struct file *file, poll_table *wait)
 	if (rb)
 		events = atomic_xchg(&rb->poll, 0);
 	mutex_unlock(&event->mmap_mutex);
-
-	poll_wait(file, &event->waitq, wait);
-
 	return events;
 }
 
@@ -7387,6 +7491,9 @@ perf_event_create_kernel_counter(struct perf_event_attr *attr, int cpu,
 		goto err;
 	}
 
+	/* Mark owner so we could distinguish it from user events. */
+	event->owner = EVENT_OWNER_KERNEL;
+
 	account_event(event);
 
 	ctx = find_get_context(event->pmu, task, cpu);
@@ -7507,6 +7614,9 @@ __perf_event_exit_task(struct perf_event *child_event,
 	if (child_event->parent) {
 		sync_child_event(child_event, child);
 		free_event(child_event);
+	} else {
+		child_event->state = PERF_EVENT_STATE_EXIT;
+		perf_event_wakeup(child_event);
 	}
 }
 
@@ -7710,7 +7820,8 @@ inherit_event(struct perf_event *parent_event,
 	if (IS_ERR(child_event))
 		return child_event;
 
-	if (!atomic_long_inc_not_zero(&parent_event->refcount)) {
+	if (is_orphaned_event(parent_event) ||
+	    !atomic_long_inc_not_zero(&parent_event->refcount)) {
 		free_event(child_event);
 		return NULL;
 	}
diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt
index d2b59af62bc0ad..d561e0214f52fb 100644
--- a/tools/perf/Documentation/perf-report.txt
+++ b/tools/perf/Documentation/perf-report.txt
@@ -147,7 +147,7 @@ OPTIONS
 -w::
 --column-widths=<width[,width...]>::
 	Force each column width to the provided list, for large terminal
-	readability.
+	readability.  0 means no limit (default behavior).
 
 -t::
 --field-separator=::
diff --git a/tools/perf/Documentation/perf-top.txt b/tools/perf/Documentation/perf-top.txt
index 180ae02137a519..28fdee39488068 100644
--- a/tools/perf/Documentation/perf-top.txt
+++ b/tools/perf/Documentation/perf-top.txt
@@ -193,6 +193,12 @@ Default is to monitor all CPUS.
 	sum of shown entries will be always 100%. "absolute" means it retains
 	the original value before and after the filter is applied.
 
+-w::
+--column-widths=<width[,width...]>::
+	Force each column width to the provided list, for large terminal
+	readability.  0 means no limit (default behavior).
+
+
 INTERACTIVE PROMPTING KEYS
 --------------------------
 
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index 2240974b774587..95e832b1bc3cf2 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -263,6 +263,7 @@ LIB_H += util/xyarray.h
 LIB_H += util/header.h
 LIB_H += util/help.h
 LIB_H += util/session.h
+LIB_H += util/ordered-events.h
 LIB_H += util/strbuf.h
 LIB_H += util/strlist.h
 LIB_H += util/strfilter.h
@@ -347,6 +348,7 @@ LIB_OBJS += $(OUTPUT)util/machine.o
 LIB_OBJS += $(OUTPUT)util/map.o
 LIB_OBJS += $(OUTPUT)util/pstack.o
 LIB_OBJS += $(OUTPUT)util/session.o
+LIB_OBJS += $(OUTPUT)util/ordered-events.o
 LIB_OBJS += $(OUTPUT)util/comm.o
 LIB_OBJS += $(OUTPUT)util/thread.o
 LIB_OBJS += $(OUTPUT)util/thread_map.o
@@ -423,6 +425,7 @@ endif
 endif
 LIB_OBJS += $(OUTPUT)tests/mmap-thread-lookup.o
 LIB_OBJS += $(OUTPUT)tests/thread-mg-share.o
+LIB_OBJS += $(OUTPUT)tests/switch-tracking.o
 
 BUILTIN_OBJS += $(OUTPUT)builtin-annotate.o
 BUILTIN_OBJS += $(OUTPUT)builtin-bench.o
diff --git a/tools/perf/arch/arm64/include/perf_regs.h b/tools/perf/arch/arm64/include/perf_regs.h
index e9441b9e2a302a..1d3f39c3aa564f 100644
--- a/tools/perf/arch/arm64/include/perf_regs.h
+++ b/tools/perf/arch/arm64/include/perf_regs.h
@@ -6,6 +6,8 @@
 #include <asm/perf_regs.h>
 
 #define PERF_REGS_MASK	((1ULL << PERF_REG_ARM64_MAX) - 1)
+#define PERF_REGS_MAX	PERF_REG_ARM64_MAX
+
 #define PERF_REG_IP	PERF_REG_ARM64_PC
 #define PERF_REG_SP	PERF_REG_ARM64_SP
 
diff --git a/tools/perf/arch/common.c b/tools/perf/arch/common.c
index 42faf369211c85..49776f190abfab 100644
--- a/tools/perf/arch/common.c
+++ b/tools/perf/arch/common.c
@@ -12,6 +12,11 @@ const char *const arm_triplets[] = {
 	NULL
 };
 
+const char *const arm64_triplets[] = {
+	"aarch64-linux-android-",
+	NULL
+};
+
 const char *const powerpc_triplets[] = {
 	"powerpc-unknown-linux-gnu-",
 	"powerpc64-unknown-linux-gnu-",
@@ -105,6 +110,8 @@ static const char *normalize_arch(char *arch)
 		return "x86";
 	if (!strcmp(arch, "sun4u") || !strncmp(arch, "sparc", 5))
 		return "sparc";
+	if (!strcmp(arch, "aarch64") || !strcmp(arch, "arm64"))
+		return "arm64";
 	if (!strncmp(arch, "arm", 3) || !strcmp(arch, "sa110"))
 		return "arm";
 	if (!strncmp(arch, "s390", 4))
@@ -159,6 +166,8 @@ static int perf_session_env__lookup_binutils_path(struct perf_session_env *env,
 
 	if (!strcmp(arch, "arm"))
 		path_list = arm_triplets;
+	else if (!strcmp(arch, "arm64"))
+		path_list = arm64_triplets;
 	else if (!strcmp(arch, "powerpc"))
 		path_list = powerpc_triplets;
 	else if (!strcmp(arch, "sh"))
diff --git a/tools/perf/arch/powerpc/util/skip-callchain-idx.c b/tools/perf/arch/powerpc/util/skip-callchain-idx.c
index a7c23a4b377802..d73ef8bb08c76a 100644
--- a/tools/perf/arch/powerpc/util/skip-callchain-idx.c
+++ b/tools/perf/arch/powerpc/util/skip-callchain-idx.c
@@ -15,6 +15,7 @@
 
 #include "util/thread.h"
 #include "util/callchain.h"
+#include "util/debug.h"
 
 /*
  * When saving the callchain on Power, the kernel conservatively saves
diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c
index 1ec429fef2be93..d4da6929597fa5 100644
--- a/tools/perf/builtin-annotate.c
+++ b/tools/perf/builtin-annotate.c
@@ -36,7 +36,8 @@
 
 struct perf_annotate {
 	struct perf_tool tool;
-	bool	   force, use_tui, use_stdio, use_gtk;
+	struct perf_session *session;
+	bool	   use_tui, use_stdio, use_gtk;
 	bool	   full_paths;
 	bool	   print_line;
 	bool	   skip_missing;
@@ -188,18 +189,9 @@ find_next:
 static int __cmd_annotate(struct perf_annotate *ann)
 {
 	int ret;
-	struct perf_session *session;
+	struct perf_session *session = ann->session;
 	struct perf_evsel *pos;
 	u64 total_nr_samples;
-	struct perf_data_file file = {
-		.path  = input_name,
-		.mode  = PERF_DATA_MODE_READ,
-		.force = ann->force,
-	};
-
-	session = perf_session__new(&file, false, &ann->tool);
-	if (session == NULL)
-		return -ENOMEM;
 
 	machines__set_symbol_filter(&session->machines, symbol__annotate_init);
 
@@ -207,22 +199,22 @@ static int __cmd_annotate(struct perf_annotate *ann)
 		ret = perf_session__cpu_bitmap(session, ann->cpu_list,
 					       ann->cpu_bitmap);
 		if (ret)
-			goto out_delete;
+			goto out;
 	}
 
 	if (!objdump_path) {
 		ret = perf_session_env__lookup_objdump(&session->header.env);
 		if (ret)
-			goto out_delete;
+			goto out;
 	}
 
 	ret = perf_session__process_events(session, &ann->tool);
 	if (ret)
-		goto out_delete;
+		goto out;
 
 	if (dump_trace) {
 		perf_session__fprintf_nr_events(session, stdout);
-		goto out_delete;
+		goto out;
 	}
 
 	if (verbose > 3)
@@ -250,8 +242,8 @@ static int __cmd_annotate(struct perf_annotate *ann)
 	}
 
 	if (total_nr_samples == 0) {
-		ui__error("The %s file has no samples!\n", file.path);
-		goto out_delete;
+		ui__error("The %s file has no samples!\n", session->file->path);
+		goto out;
 	}
 
 	if (use_browser == 2) {
@@ -261,24 +253,12 @@ static int __cmd_annotate(struct perf_annotate *ann)
 					 "perf_gtk__show_annotations");
 		if (show_annotations == NULL) {
 			ui__error("GTK browser not found!\n");
-			goto out_delete;
+			goto out;
 		}
 		show_annotations();
 	}
 
-out_delete:
-	/*
-	 * Speed up the exit process, for large files this can
-	 * take quite a while.
-	 *
-	 * XXX Enable this when using valgrind or if we ever
-	 * librarize this command.
-	 *
-	 * Also experiment with obstacks to see how much speed
-	 * up we'll get here.
-	 *
-	 * perf_session__delete(session);
-	 */
+out:
 	return ret;
 }
 
@@ -297,10 +277,14 @@ int cmd_annotate(int argc, const char **argv, const char *prefix __maybe_unused)
 			.comm	= perf_event__process_comm,
 			.exit	= perf_event__process_exit,
 			.fork	= perf_event__process_fork,
-			.ordered_samples = true,
+			.ordered_events = true,
 			.ordering_requires_timestamps = true,
 		},
 	};
+	struct perf_data_file file = {
+		.path  = input_name,
+		.mode  = PERF_DATA_MODE_READ,
+	};
 	const struct option options[] = {
 	OPT_STRING('i', "input", &input_name, "file",
 		    "input file name"),
@@ -308,7 +292,7 @@ int cmd_annotate(int argc, const char **argv, const char *prefix __maybe_unused)
 		   "only consider symbols in these dsos"),
 	OPT_STRING('s', "symbol", &annotate.sym_hist_filter, "symbol",
 		    "symbol to annotate"),
-	OPT_BOOLEAN('f', "force", &annotate.force, "don't complain, do it"),
+	OPT_BOOLEAN('f', "force", &file.force, "don't complain, do it"),
 	OPT_INCR('v', "verbose", &verbose,
 		    "be more verbose (show symbol address, etc)"),
 	OPT_BOOLEAN('D', "dump-raw-trace", &dump_trace,
@@ -341,6 +325,7 @@ int cmd_annotate(int argc, const char **argv, const char *prefix __maybe_unused)
 		    "Show event group information together"),
 	OPT_END()
 	};
+	int ret;
 
 	argc = parse_options(argc, argv, options, annotate_usage, 0);
 
@@ -353,11 +338,16 @@ int cmd_annotate(int argc, const char **argv, const char *prefix __maybe_unused)
 
 	setup_browser(true);
 
+	annotate.session = perf_session__new(&file, false, &annotate.tool);
+	if (annotate.session == NULL)
+		return -ENOMEM;
+
 	symbol_conf.priv_size = sizeof(struct annotation);
 	symbol_conf.try_vmlinux_path = true;
 
-	if (symbol__init() < 0)
-		return -1;
+	ret = symbol__init(&annotate.session->header.env);
+	if (ret < 0)
+		goto out_delete;
 
 	if (setup_sorting() < 0)
 		usage_with_options(annotate_usage, options);
@@ -373,5 +363,20 @@ int cmd_annotate(int argc, const char **argv, const char *prefix __maybe_unused)
 		annotate.sym_hist_filter = argv[0];
 	}
 
-	return __cmd_annotate(&annotate);
+	ret = __cmd_annotate(&annotate);
+
+out_delete:
+	/*
+	 * Speed up the exit process, for large files this can
+	 * take quite a while.
+	 *
+	 * XXX Enable this when using valgrind or if we ever
+	 * librarize this command.
+	 *
+	 * Also experiment with obstacks to see how much speed
+	 * up we'll get here.
+	 *
+	 * perf_session__delete(session);
+	 */
+	return ret;
 }
diff --git a/tools/perf/builtin-buildid-cache.c b/tools/perf/builtin-buildid-cache.c
index 2a2c78f8087663..70385756da63f1 100644
--- a/tools/perf/builtin-buildid-cache.c
+++ b/tools/perf/builtin-buildid-cache.c
@@ -246,20 +246,9 @@ static bool dso__missing_buildid_cache(struct dso *dso, int parm __maybe_unused)
 	return true;
 }
 
-static int build_id_cache__fprintf_missing(const char *filename, bool force, FILE *fp)
+static int build_id_cache__fprintf_missing(struct perf_session *session, FILE *fp)
 {
-	struct perf_data_file file = {
-		.path  = filename,
-		.mode  = PERF_DATA_MODE_READ,
-		.force = force,
-	};
-	struct perf_session *session = perf_session__new(&file, false, NULL);
-	if (session == NULL)
-		return -1;
-
 	perf_session__fprintf_dsos_buildid(session, fp, dso__missing_buildid_cache, 0);
-	perf_session__delete(session);
-
 	return 0;
 }
 
@@ -302,6 +291,12 @@ int cmd_buildid_cache(int argc, const char **argv,
 		   *missing_filename = NULL,
 		   *update_name_list_str = NULL,
 		   *kcore_filename;
+	char sbuf[STRERR_BUFSIZE];
+
+	struct perf_data_file file = {
+		.mode  = PERF_DATA_MODE_READ,
+	};
+	struct perf_session *session = NULL;
 
 	const struct option buildid_cache_options[] = {
 	OPT_STRING('a', "add", &add_name_list_str,
@@ -326,8 +321,17 @@ int cmd_buildid_cache(int argc, const char **argv,
 	argc = parse_options(argc, argv, buildid_cache_options,
 			     buildid_cache_usage, 0);
 
-	if (symbol__init() < 0)
-		return -1;
+	if (missing_filename) {
+		file.path = missing_filename;
+		file.force = force;
+
+		session = perf_session__new(&file, false, NULL);
+		if (session == NULL)
+			return -1;
+	}
+
+	if (symbol__init(session ? &session->header.env : NULL) < 0)
+		goto out;
 
 	setup_pager();
 
@@ -344,7 +348,7 @@ int cmd_buildid_cache(int argc, const char **argv,
 						continue;
 					}
 					pr_warning("Couldn't add %s: %s\n",
-						   pos->s, strerror(errno));
+						   pos->s, strerror_r(errno, sbuf, sizeof(sbuf)));
 				}
 
 			strlist__delete(list);
@@ -362,7 +366,7 @@ int cmd_buildid_cache(int argc, const char **argv,
 						continue;
 					}
 					pr_warning("Couldn't remove %s: %s\n",
-						   pos->s, strerror(errno));
+						   pos->s, strerror_r(errno, sbuf, sizeof(sbuf)));
 				}
 
 			strlist__delete(list);
@@ -370,7 +374,7 @@ int cmd_buildid_cache(int argc, const char **argv,
 	}
 
 	if (missing_filename)
-		ret = build_id_cache__fprintf_missing(missing_filename, force, stdout);
+		ret = build_id_cache__fprintf_missing(session, stdout);
 
 	if (update_name_list_str) {
 		list = strlist__new(true, update_name_list_str);
@@ -383,7 +387,7 @@ int cmd_buildid_cache(int argc, const char **argv,
 						continue;
 					}
 					pr_warning("Couldn't update %s: %s\n",
-						   pos->s, strerror(errno));
+						   pos->s, strerror_r(errno, sbuf, sizeof(sbuf)));
 				}
 
 			strlist__delete(list);
@@ -394,5 +398,9 @@ int cmd_buildid_cache(int argc, const char **argv,
 	    build_id_cache__add_kcore(kcore_filename, debugdir, force))
 		pr_warning("Couldn't add %s\n", kcore_filename);
 
+out:
+	if (session)
+		perf_session__delete(session);
+
 	return ret;
 }
diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c
index 9a5a035cb4262a..190d0b6b28cce6 100644
--- a/tools/perf/builtin-diff.c
+++ b/tools/perf/builtin-diff.c
@@ -360,7 +360,7 @@ static struct perf_tool tool = {
 	.exit	= perf_event__process_exit,
 	.fork	= perf_event__process_fork,
 	.lost	= perf_event__process_lost,
-	.ordered_samples = true,
+	.ordered_events = true,
 	.ordering_requires_timestamps = true,
 };
 
@@ -1143,7 +1143,7 @@ int cmd_diff(int argc, const char **argv, const char *prefix __maybe_unused)
 
 	argc = parse_options(argc, argv, options, diff_usage, 0);
 
-	if (symbol__init() < 0)
+	if (symbol__init(NULL) < 0)
 		return -1;
 
 	if (data_init(argc, argv) < 0)
diff --git a/tools/perf/builtin-help.c b/tools/perf/builtin-help.c
index 0384d930480b47..25d20628212ed4 100644
--- a/tools/perf/builtin-help.c
+++ b/tools/perf/builtin-help.c
@@ -103,6 +103,8 @@ static int check_emacsclient_version(void)
 
 static void exec_woman_emacs(const char *path, const char *page)
 {
+	char sbuf[STRERR_BUFSIZE];
+
 	if (!check_emacsclient_version()) {
 		/* This works only with emacsclient version >= 22. */
 		struct strbuf man_page = STRBUF_INIT;
@@ -111,16 +113,19 @@ static void exec_woman_emacs(const char *path, const char *page)
 			path = "emacsclient";
 		strbuf_addf(&man_page, "(woman \"%s\")", page);
 		execlp(path, "emacsclient", "-e", man_page.buf, NULL);
-		warning("failed to exec '%s': %s", path, strerror(errno));
+		warning("failed to exec '%s': %s", path,
+			strerror_r(errno, sbuf, sizeof(sbuf)));
 	}
 }
 
 static void exec_man_konqueror(const char *path, const char *page)
 {
 	const char *display = getenv("DISPLAY");
+
 	if (display && *display) {
 		struct strbuf man_page = STRBUF_INIT;
 		const char *filename = "kfmclient";
+		char sbuf[STRERR_BUFSIZE];
 
 		/* It's simpler to launch konqueror using kfmclient. */
 		if (path) {
@@ -139,24 +144,31 @@ static void exec_man_konqueror(const char *path, const char *page)
 			path = "kfmclient";
 		strbuf_addf(&man_page, "man:%s(1)", page);
 		execlp(path, filename, "newTab", man_page.buf, NULL);
-		warning("failed to exec '%s': %s", path, strerror(errno));
+		warning("failed to exec '%s': %s", path,
+			strerror_r(errno, sbuf, sizeof(sbuf)));
 	}
 }
 
 static void exec_man_man(const char *path, const char *page)
 {
+	char sbuf[STRERR_BUFSIZE];
+
 	if (!path)
 		path = "man";
 	execlp(path, "man", page, NULL);
-	warning("failed to exec '%s': %s", path, strerror(errno));
+	warning("failed to exec '%s': %s", path,
+		strerror_r(errno, sbuf, sizeof(sbuf)));
 }
 
 static void exec_man_cmd(const char *cmd, const char *page)
 {
 	struct strbuf shell_cmd = STRBUF_INIT;
+	char sbuf[STRERR_BUFSIZE];
+
 	strbuf_addf(&shell_cmd, "%s %s", cmd, page);
 	execl("/bin/sh", "sh", "-c", shell_cmd.buf, NULL);
-	warning("failed to exec '%s': %s", cmd, strerror(errno));
+	warning("failed to exec '%s': %s", cmd,
+		strerror_r(errno, sbuf, sizeof(sbuf)));
 }
 
 static void add_man_viewer(const char *name)
diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c
index 9a02807387d6c2..3a62b6b3c8fdcc 100644
--- a/tools/perf/builtin-inject.c
+++ b/tools/perf/builtin-inject.c
@@ -23,6 +23,7 @@
 
 struct perf_inject {
 	struct perf_tool	tool;
+	struct perf_session	*session;
 	bool			build_ids;
 	bool			sched_stat;
 	const char		*input_name;
@@ -340,12 +341,8 @@ static int perf_evsel__check_stype(struct perf_evsel *evsel,
 
 static int __cmd_inject(struct perf_inject *inject)
 {
-	struct perf_session *session;
 	int ret = -EINVAL;
-	struct perf_data_file file = {
-		.path = inject->input_name,
-		.mode = PERF_DATA_MODE_READ,
-	};
+	struct perf_session *session = inject->session;
 	struct perf_data_file *file_out = &inject->output;
 
 	signal(SIGINT, sig_handler);
@@ -357,16 +354,12 @@ static int __cmd_inject(struct perf_inject *inject)
 		inject->tool.tracing_data = perf_event__repipe_tracing_data;
 	}
 
-	session = perf_session__new(&file, true, &inject->tool);
-	if (session == NULL)
-		return -ENOMEM;
-
 	if (inject->build_ids) {
 		inject->tool.sample = perf_event__inject_buildid;
 	} else if (inject->sched_stat) {
 		struct perf_evsel *evsel;
 
-		inject->tool.ordered_samples = true;
+		inject->tool.ordered_events = true;
 
 		evlist__for_each(session->evlist, evsel) {
 			const char *name = perf_evsel__name(evsel);
@@ -396,8 +389,6 @@ static int __cmd_inject(struct perf_inject *inject)
 		perf_session__write_header(session, session->evlist, file_out->fd, true);
 	}
 
-	perf_session__delete(session);
-
 	return ret;
 }
 
@@ -427,6 +418,11 @@ int cmd_inject(int argc, const char **argv, const char *prefix __maybe_unused)
 			.mode = PERF_DATA_MODE_WRITE,
 		},
 	};
+	struct perf_data_file file = {
+		.mode = PERF_DATA_MODE_READ,
+	};
+	int ret;
+
 	const struct option options[] = {
 		OPT_BOOLEAN('b', "build-ids", &inject.build_ids,
 			    "Inject build-ids into the output stream"),
@@ -461,8 +457,17 @@ int cmd_inject(int argc, const char **argv, const char *prefix __maybe_unused)
 		return -1;
 	}
 
-	if (symbol__init() < 0)
+	file.path = inject.input_name;
+	inject.session = perf_session__new(&file, true, &inject.tool);
+	if (inject.session == NULL)
+		return -ENOMEM;
+
+	if (symbol__init(&inject.session->header.env) < 0)
 		return -1;
 
-	return __cmd_inject(&inject);
+	ret = __cmd_inject(&inject);
+
+	perf_session__delete(inject.session);
+
+	return ret;
 }
diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c
index bef3376bfaf3a6..23762187a2191d 100644
--- a/tools/perf/builtin-kmem.c
+++ b/tools/perf/builtin-kmem.c
@@ -256,7 +256,9 @@ static int process_sample_event(struct perf_tool *tool __maybe_unused,
 static struct perf_tool perf_kmem = {
 	.sample		 = process_sample_event,
 	.comm		 = perf_event__process_comm,
-	.ordered_samples = true,
+	.mmap		 = perf_event__process_mmap,
+	.mmap2		 = perf_event__process_mmap2,
+	.ordered_events	 = true,
 };
 
 static double fragmentation(unsigned long n_req, unsigned long n_alloc)
@@ -403,10 +405,9 @@ static void sort_result(void)
 	__sort_result(&root_caller_stat, &root_caller_sorted, &caller_sort);
 }
 
-static int __cmd_kmem(void)
+static int __cmd_kmem(struct perf_session *session)
 {
 	int err = -EINVAL;
-	struct perf_session *session;
 	const struct perf_evsel_str_handler kmem_tracepoints[] = {
 		{ "kmem:kmalloc",		perf_evsel__process_alloc_event, },
     		{ "kmem:kmem_cache_alloc",	perf_evsel__process_alloc_event, },
@@ -415,34 +416,22 @@ static int __cmd_kmem(void)
 		{ "kmem:kfree",			perf_evsel__process_free_event, },
     		{ "kmem:kmem_cache_free",	perf_evsel__process_free_event, },
 	};
-	struct perf_data_file file = {
-		.path = input_name,
-		.mode = PERF_DATA_MODE_READ,
-	};
-
-	session = perf_session__new(&file, false, &perf_kmem);
-	if (session == NULL)
-		return -ENOMEM;
-
-	if (perf_session__create_kernel_maps(session) < 0)
-		goto out_delete;
 
 	if (!perf_session__has_traces(session, "kmem record"))
-		goto out_delete;
+		goto out;
 
 	if (perf_session__set_tracepoints_handlers(session, kmem_tracepoints)) {
 		pr_err("Initializing perf session tracepoint handlers failed\n");
-		return -1;
+		goto out;
 	}
 
 	setup_pager();
 	err = perf_session__process_events(session, &perf_kmem);
 	if (err != 0)
-		goto out_delete;
+		goto out;
 	sort_result();
 	print_result(session);
-out_delete:
-	perf_session__delete(session);
+out:
 	return err;
 }
 
@@ -689,29 +678,46 @@ int cmd_kmem(int argc, const char **argv, const char *prefix __maybe_unused)
 		NULL,
 		NULL
 	};
+	struct perf_session *session;
+	struct perf_data_file file = {
+		.path = input_name,
+		.mode = PERF_DATA_MODE_READ,
+	};
+	int ret = -1;
+
 	argc = parse_options_subcommand(argc, argv, kmem_options,
 					kmem_subcommands, kmem_usage, 0);
 
 	if (!argc)
 		usage_with_options(kmem_usage, kmem_options);
 
-	symbol__init();
-
 	if (!strncmp(argv[0], "rec", 3)) {
+		symbol__init(NULL);
 		return __cmd_record(argc, argv);
-	} else if (!strcmp(argv[0], "stat")) {
+	}
+
+	session = perf_session__new(&file, false, &perf_kmem);
+	if (session == NULL)
+		return -ENOMEM;
+
+	symbol__init(&session->header.env);
+
+	if (!strcmp(argv[0], "stat")) {
 		if (cpu__setup_cpunode_map())
-			return -1;
+			goto out_delete;
 
 		if (list_empty(&caller_sort))
 			setup_sorting(&caller_sort, default_sort_order);
 		if (list_empty(&alloc_sort))
 			setup_sorting(&alloc_sort, default_sort_order);
 
-		return __cmd_kmem();
+		ret = __cmd_kmem(session);
 	} else
 		usage_with_options(kmem_usage, kmem_options);
 
-	return 0;
+out_delete:
+	perf_session__delete(session);
+
+	return ret;
 }
 
diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c
index 43367eb005100a..1a4ef9cd9d5f7a 100644
--- a/tools/perf/builtin-kvm.c
+++ b/tools/perf/builtin-kvm.c
@@ -592,8 +592,8 @@ static void print_result(struct perf_kvm_stat *kvm)
 	pr_info("%9s ", "Samples%");
 
 	pr_info("%9s ", "Time%");
-	pr_info("%10s ", "Min Time");
-	pr_info("%10s ", "Max Time");
+	pr_info("%11s ", "Min Time");
+	pr_info("%11s ", "Max Time");
 	pr_info("%16s ", "Avg time");
 	pr_info("\n\n");
 
@@ -610,8 +610,8 @@ static void print_result(struct perf_kvm_stat *kvm)
 		pr_info("%10llu ", (unsigned long long)ecount);
 		pr_info("%8.2f%% ", (double)ecount / kvm->total_count * 100);
 		pr_info("%8.2f%% ", (double)etime / kvm->total_time * 100);
-		pr_info("%8" PRIu64 "us ", min / 1000);
-		pr_info("%8" PRIu64 "us ", max / 1000);
+		pr_info("%9.2fus ", (double)min / 1e3);
+		pr_info("%9.2fus ", (double)max / 1e3);
 		pr_info("%9.2fus ( +-%7.2f%% )", (double)etime / ecount/1e3,
 			kvm_event_rel_stddev(vcpu, event));
 		pr_info("\n");
@@ -732,7 +732,7 @@ static s64 perf_kvm__mmap_read_idx(struct perf_kvm_stat *kvm, int idx,
 			return -1;
 		}
 
-		err = perf_session_queue_event(kvm->session, event, &sample, 0);
+		err = perf_session_queue_event(kvm->session, event, &kvm->tool, &sample, 0);
 		/*
 		 * FIXME: Here we can't consume the event, as perf_session_queue_event will
 		 *        point to it, and it'll get possibly overwritten by the kernel.
@@ -785,7 +785,7 @@ static int perf_kvm__mmap_read(struct perf_kvm_stat *kvm)
 
 	/* flush queue after each round in which we processed events */
 	if (ntotal) {
-		kvm->session->ordered_samples.next_flush = flush_time;
+		kvm->session->ordered_events.next_flush = flush_time;
 		err = kvm->tool.finished_round(&kvm->tool, NULL, kvm->session);
 		if (err) {
 			if (kvm->lost_events)
@@ -885,15 +885,11 @@ static int fd_set_nonblock(int fd)
 	return 0;
 }
 
-static
-int perf_kvm__handle_stdin(struct termios *tc_now, struct termios *tc_save)
+static int perf_kvm__handle_stdin(void)
 {
 	int c;
 
-	tcsetattr(0, TCSANOW, tc_now);
 	c = getc(stdin);
-	tcsetattr(0, TCSAFLUSH, tc_save);
-
 	if (c == 'q')
 		return 1;
 
@@ -904,7 +900,7 @@ static int kvm_events_live_report(struct perf_kvm_stat *kvm)
 {
 	struct pollfd *pollfds = NULL;
 	int nr_fds, nr_stdin, ret, err = -EINVAL;
-	struct termios tc, save;
+	struct termios save;
 
 	/* live flag must be set first */
 	kvm->live = true;
@@ -919,14 +915,9 @@ static int kvm_events_live_report(struct perf_kvm_stat *kvm)
 		goto out;
 	}
 
+	set_term_quiet_input(&save);
 	init_kvm_event_record(kvm);
 
-	tcgetattr(0, &save);
-	tc = save;
-	tc.c_lflag &= ~(ICANON | ECHO);
-	tc.c_cc[VMIN] = 0;
-	tc.c_cc[VTIME] = 0;
-
 	signal(SIGINT, sig_handler);
 	signal(SIGTERM, sig_handler);
 
@@ -972,7 +963,7 @@ static int kvm_events_live_report(struct perf_kvm_stat *kvm)
 			goto out;
 
 		if (pollfds[nr_stdin].revents & POLLIN)
-			done = perf_kvm__handle_stdin(&tc, &save);
+			done = perf_kvm__handle_stdin();
 
 		if (!rc && !done)
 			err = poll(pollfds, nr_fds, 100);
@@ -989,6 +980,7 @@ out:
 	if (kvm->timerfd >= 0)
 		close(kvm->timerfd);
 
+	tcsetattr(0, TCSAFLUSH, &save);
 	free(pollfds);
 	return err;
 }
@@ -998,6 +990,7 @@ static int kvm_live_open_events(struct perf_kvm_stat *kvm)
 	int err, rc = -1;
 	struct perf_evsel *pos;
 	struct perf_evlist *evlist = kvm->evlist;
+	char sbuf[STRERR_BUFSIZE];
 
 	perf_evlist__config(evlist, &kvm->opts);
 
@@ -1034,12 +1027,14 @@ static int kvm_live_open_events(struct perf_kvm_stat *kvm)
 
 	err = perf_evlist__open(evlist);
 	if (err < 0) {
-		printf("Couldn't create the events: %s\n", strerror(errno));
+		printf("Couldn't create the events: %s\n",
+		       strerror_r(errno, sbuf, sizeof(sbuf)));
 		goto out;
 	}
 
 	if (perf_evlist__mmap(evlist, kvm->opts.mmap_pages, false) < 0) {
-		ui__error("Failed to mmap the events: %s\n", strerror(errno));
+		ui__error("Failed to mmap the events: %s\n",
+			  strerror_r(errno, sbuf, sizeof(sbuf)));
 		perf_evlist__close(evlist);
 		goto out;
 	}
@@ -1058,7 +1053,7 @@ static int read_events(struct perf_kvm_stat *kvm)
 	struct perf_tool eops = {
 		.sample			= process_sample_event,
 		.comm			= perf_event__process_comm,
-		.ordered_samples	= true,
+		.ordered_events		= true,
 	};
 	struct perf_data_file file = {
 		.path = kvm->file_name,
@@ -1072,6 +1067,8 @@ static int read_events(struct perf_kvm_stat *kvm)
 		return -EINVAL;
 	}
 
+	symbol__init(&kvm->session->header.env);
+
 	if (!perf_session__has_traces(kvm->session, "kvm record"))
 		return -EINVAL;
 
@@ -1201,8 +1198,6 @@ kvm_events_report(struct perf_kvm_stat *kvm, int argc, const char **argv)
 		NULL
 	};
 
-	symbol__init();
-
 	if (argc) {
 		argc = parse_options(argc, argv,
 				     kvm_events_report_options,
@@ -1311,7 +1306,7 @@ static int kvm_events_live(struct perf_kvm_stat *kvm,
 	kvm->tool.exit   = perf_event__process_exit;
 	kvm->tool.fork   = perf_event__process_fork;
 	kvm->tool.lost   = process_lost_event;
-	kvm->tool.ordered_samples = true;
+	kvm->tool.ordered_events = true;
 	perf_tool__fill_defaults(&kvm->tool);
 
 	/* set defaults */
@@ -1322,7 +1317,7 @@ static int kvm_events_live(struct perf_kvm_stat *kvm,
 	kvm->opts.target.uid_str = NULL;
 	kvm->opts.target.uid = UINT_MAX;
 
-	symbol__init();
+	symbol__init(NULL);
 	disable_buildid_cache();
 
 	use_browser = 0;
diff --git a/tools/perf/builtin-lock.c b/tools/perf/builtin-lock.c
index 6148afc995c68a..92790ed7af45d4 100644
--- a/tools/perf/builtin-lock.c
+++ b/tools/perf/builtin-lock.c
@@ -852,7 +852,7 @@ static int __cmd_report(bool display_info)
 	struct perf_tool eops = {
 		.sample		 = process_sample_event,
 		.comm		 = perf_event__process_comm,
-		.ordered_samples = true,
+		.ordered_events	 = true,
 	};
 	struct perf_data_file file = {
 		.path = input_name,
@@ -865,6 +865,8 @@ static int __cmd_report(bool display_info)
 		return -ENOMEM;
 	}
 
+	symbol__init(&session->header.env);
+
 	if (!perf_session__has_traces(session, "lock record"))
 		goto out_delete;
 
@@ -974,7 +976,6 @@ int cmd_lock(int argc, const char **argv, const char *prefix __maybe_unused)
 	unsigned int i;
 	int rc = 0;
 
-	symbol__init();
 	for (i = 0; i < LOCKHASH_SIZE; i++)
 		INIT_LIST_HEAD(lockhash_table + i);
 
diff --git a/tools/perf/builtin-mem.c b/tools/perf/builtin-mem.c
index 4a1a6c94a5ebcb..8b4a87fe385836 100644
--- a/tools/perf/builtin-mem.c
+++ b/tools/perf/builtin-mem.c
@@ -133,7 +133,7 @@ static int report_raw_events(struct perf_mem *mem)
 			goto out_delete;
 	}
 
-	if (symbol__init() < 0)
+	if (symbol__init(&session->header.env) < 0)
 		return -1;
 
 	printf("# PID, TID, IP, ADDR, LOCAL WEIGHT, DSRC, SYMBOL\n");
@@ -194,7 +194,7 @@ int cmd_mem(int argc, const char **argv, const char *prefix __maybe_unused)
 			.lost		= perf_event__process_lost,
 			.fork		= perf_event__process_fork,
 			.build_id	= perf_event__process_build_id,
-			.ordered_samples = true,
+			.ordered_events	= true,
 		},
 		.input_name		 = "perf.data",
 	};
diff --git a/tools/perf/builtin-probe.c b/tools/perf/builtin-probe.c
index c63fa29250753b..347729e29a9297 100644
--- a/tools/perf/builtin-probe.c
+++ b/tools/perf/builtin-probe.c
@@ -290,8 +290,11 @@ static void cleanup_params(void)
 
 static void pr_err_with_code(const char *msg, int err)
 {
+	char sbuf[STRERR_BUFSIZE];
+
 	pr_err("%s", msg);
-	pr_debug(" Reason: %s (Code: %d)", strerror(-err), err);
+	pr_debug(" Reason: %s (Code: %d)",
+		 strerror_r(-err, sbuf, sizeof(sbuf)), err);
 	pr_err("\n");
 }
 
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 4869050e7194c1..87e28a4e33ba29 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -161,7 +161,7 @@ try_again:
 
 	if (perf_evlist__apply_filters(evlist)) {
 		error("failed to set filter with %d (%s)\n", errno,
-			strerror(errno));
+			strerror_r(errno, msg, sizeof(msg)));
 		rc = -1;
 		goto out;
 	}
@@ -175,7 +175,8 @@ try_again:
 			       "(current value: %u)\n", opts->mmap_pages);
 			rc = -errno;
 		} else {
-			pr_err("failed to mmap with %d (%s)\n", errno, strerror(errno));
+			pr_err("failed to mmap with %d (%s)\n", errno,
+				strerror_r(errno, msg, sizeof(msg)));
 			rc = -errno;
 		}
 		goto out;
@@ -480,7 +481,7 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 	}
 
 	if (forks && workload_exec_errno) {
-		char msg[512];
+		char msg[STRERR_BUFSIZE];
 		const char *emsg = strerror_r(workload_exec_errno, msg, sizeof(msg));
 		pr_err("Workload failed: %s\n", emsg);
 		err = -1;
@@ -781,6 +782,7 @@ static const char * const record_usage[] = {
  */
 static struct record record = {
 	.opts = {
+		.sample_time	     = true,
 		.mmap_pages	     = UINT_MAX,
 		.user_freq	     = UINT_MAX,
 		.user_interval	     = ULLONG_MAX,
@@ -907,7 +909,7 @@ int cmd_record(int argc, const char **argv, const char *prefix __maybe_unused)
 		usage_with_options(record_usage, record_options);
 	}
 
-	symbol__init();
+	symbol__init(NULL);
 
 	if (symbol_conf.kptr_restrict)
 		pr_warning(
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 21d830bafff32a..3da59a87ec7c48 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -58,17 +58,19 @@ struct report {
 	const char		*symbol_filter_str;
 	float			min_percent;
 	u64			nr_entries;
+	u64			queue_size;
 	DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS);
 };
 
 static int report__config(const char *var, const char *value, void *cb)
 {
+	struct report *rep = cb;
+
 	if (!strcmp(var, "report.group")) {
 		symbol_conf.event_group = perf_config_bool(var, value);
 		return 0;
 	}
 	if (!strcmp(var, "report.percent-limit")) {
-		struct report *rep = cb;
 		rep->min_percent = strtof(value, NULL);
 		return 0;
 	}
@@ -76,6 +78,10 @@ static int report__config(const char *var, const char *value, void *cb)
 		symbol_conf.cumulate_callchain = perf_config_bool(var, value);
 		return 0;
 	}
+	if (!strcmp(var, "report.queue-size")) {
+		rep->queue_size = perf_config_u64(var, value);
+		return 0;
+	}
 
 	return perf_default_config(var, value, cb);
 }
@@ -578,7 +584,7 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
 			.attr		 = perf_event__process_attr,
 			.tracing_data	 = perf_event__process_tracing_data,
 			.build_id	 = perf_event__process_build_id,
-			.ordered_samples = true,
+			.ordered_events	 = true,
 			.ordering_requires_timestamps = true,
 		},
 		.max_stack		 = PERF_MAX_STACK_DEPTH,
@@ -714,12 +720,17 @@ repeat:
 	if (session == NULL)
 		return -ENOMEM;
 
+	if (report.queue_size) {
+		ordered_events__set_alloc_size(&session->ordered_events,
+					       report.queue_size);
+	}
+
 	report.session = session;
 
 	has_br_stack = perf_header__has_feat(&session->header,
 					     HEADER_BRANCH_STACK);
 
-	if (branch_mode == -1 && has_br_stack) {
+	if ((branch_mode == -1 && has_br_stack) || branch_mode == 1) {
 		sort__mode = SORT_MODE__BRANCH;
 		symbol_conf.cumulate_callchain = false;
 	}
@@ -787,7 +798,7 @@ repeat:
 		}
 	}
 
-	if (symbol__init() < 0)
+	if (symbol__init(&session->header.env) < 0)
 		goto error;
 
 	if (argc) {
diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c
index f83c08c0dd87ca..9c9287fbf8e98d 100644
--- a/tools/perf/builtin-sched.c
+++ b/tools/perf/builtin-sched.c
@@ -428,6 +428,7 @@ static u64 get_cpu_usage_nsec_parent(void)
 static int self_open_counters(void)
 {
 	struct perf_event_attr attr;
+	char sbuf[STRERR_BUFSIZE];
 	int fd;
 
 	memset(&attr, 0, sizeof(attr));
@@ -440,7 +441,8 @@ static int self_open_counters(void)
 
 	if (fd < 0)
 		pr_err("Error: sys_perf_event_open() syscall returned "
-		       "with %d (%s)\n", fd, strerror(errno));
+		       "with %d (%s)\n", fd,
+		       strerror_r(errno, sbuf, sizeof(sbuf)));
 	return fd;
 }
 
@@ -1462,6 +1464,8 @@ static int perf_sched__read_events(struct perf_sched *sched,
 		return -1;
 	}
 
+	symbol__init(&session->header.env);
+
 	if (perf_session__set_tracepoints_handlers(session, handlers))
 		goto out_delete;
 
@@ -1662,7 +1666,7 @@ int cmd_sched(int argc, const char **argv, const char *prefix __maybe_unused)
 			.comm		 = perf_event__process_comm,
 			.lost		 = perf_event__process_lost,
 			.fork		 = perf_sched__process_fork_event,
-			.ordered_samples = true,
+			.ordered_events = true,
 		},
 		.cmp_pid	      = LIST_HEAD_INIT(sched.cmp_pid),
 		.sort_list	      = LIST_HEAD_INIT(sched.sort_list),
@@ -1747,7 +1751,6 @@ int cmd_sched(int argc, const char **argv, const char *prefix __maybe_unused)
 	if (!strcmp(argv[0], "script"))
 		return cmd_script(argc, argv, prefix);
 
-	symbol__init();
 	if (!strncmp(argv[0], "rec", 3)) {
 		return __cmd_record(argc, argv);
 	} else if (!strncmp(argv[0], "lat", 3)) {
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index f57035b89c15d1..02dce9295e2c7e 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -184,10 +184,6 @@ static int perf_evsel__check_attr(struct perf_evsel *evsel,
 		if (perf_evsel__check_stype(evsel, PERF_SAMPLE_IP, "IP",
 					    PERF_OUTPUT_IP))
 			return -EINVAL;
-
-		if (!no_callchain &&
-		    !(attr->sample_type & PERF_SAMPLE_CALLCHAIN))
-			symbol_conf.use_callchain = false;
 	}
 
 	if (PRINT_FIELD(ADDR) &&
@@ -290,6 +286,19 @@ static int perf_session__check_output_opt(struct perf_session *session)
 		set_print_ip_opts(&evsel->attr);
 	}
 
+	if (!no_callchain) {
+		bool use_callchain = false;
+
+		evlist__for_each(session->evlist, evsel) {
+			if (evsel->attr.sample_type & PERF_SAMPLE_CALLCHAIN) {
+				use_callchain = true;
+				break;
+			}
+		}
+		if (!use_callchain)
+			symbol_conf.use_callchain = false;
+	}
+
 	/*
 	 * set default for tracepoints to print symbols only
 	 * if callchains are present
@@ -476,6 +485,11 @@ static int default_start_script(const char *script __maybe_unused,
 	return 0;
 }
 
+static int default_flush_script(void)
+{
+	return 0;
+}
+
 static int default_stop_script(void)
 {
 	return 0;
@@ -489,6 +503,7 @@ static int default_generate_script(struct pevent *pevent __maybe_unused,
 
 static struct scripting_ops default_scripting_ops = {
 	.start_script		= default_start_script,
+	.flush_script		= default_flush_script,
 	.stop_script		= default_stop_script,
 	.process_event		= process_event,
 	.generate_script	= default_generate_script,
@@ -504,6 +519,11 @@ static void setup_scripting(void)
 	scripting_ops = &default_scripting_ops;
 }
 
+static int flush_scripting(void)
+{
+	return scripting_ops->flush_script();
+}
+
 static int cleanup_scripting(void)
 {
 	pr_debug("\nperf script stopped\n");
@@ -1471,12 +1491,13 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused)
 	bool show_full_info = false;
 	bool header = false;
 	bool header_only = false;
+	bool script_started = false;
 	char *rec_script_path = NULL;
 	char *rep_script_path = NULL;
 	struct perf_session *session;
 	char *script_path = NULL;
 	const char **__argv;
-	int i, j, err;
+	int i, j, err = 0;
 	struct perf_script script = {
 		.tool = {
 			.sample		 = process_sample_event,
@@ -1488,7 +1509,7 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused)
 			.attr		 = process_attr,
 			.tracing_data	 = perf_event__process_tracing_data,
 			.build_id	 = perf_event__process_build_id,
-			.ordered_samples = true,
+			.ordered_events	 = true,
 			.ordering_requires_timestamps = true,
 		},
 	};
@@ -1718,8 +1739,6 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused)
 		exit(-1);
 	}
 
-	if (symbol__init() < 0)
-		return -1;
 	if (!script_name)
 		setup_pager();
 
@@ -1730,14 +1749,18 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused)
 	if (header || header_only) {
 		perf_session__fprintf_info(session, stdout, show_full_info);
 		if (header_only)
-			return 0;
+			goto out_delete;
 	}
 
+	if (symbol__init(&session->header.env) < 0)
+		goto out_delete;
+
 	script.session = session;
 
 	if (cpu_list) {
-		if (perf_session__cpu_bitmap(session, cpu_list, cpu_bitmap))
-			return -1;
+		err = perf_session__cpu_bitmap(session, cpu_list, cpu_bitmap);
+		if (err < 0)
+			goto out_delete;
 	}
 
 	if (!no_callchain)
@@ -1752,53 +1775,62 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused)
 		if (output_set_by_user()) {
 			fprintf(stderr,
 				"custom fields not supported for generated scripts");
-			return -1;
+			err = -EINVAL;
+			goto out_delete;
 		}
 
 		input = open(file.path, O_RDONLY);	/* input_name */
 		if (input < 0) {
+			err = -errno;
 			perror("failed to open file");
-			return -1;
+			goto out_delete;
 		}
 
 		err = fstat(input, &perf_stat);
 		if (err < 0) {
 			perror("failed to stat file");
-			return -1;
+			goto out_delete;
 		}
 
 		if (!perf_stat.st_size) {
 			fprintf(stderr, "zero-sized file, nothing to do!\n");
-			return 0;
+			goto out_delete;
 		}
 
 		scripting_ops = script_spec__lookup(generate_script_lang);
 		if (!scripting_ops) {
 			fprintf(stderr, "invalid language specifier");
-			return -1;
+			err = -ENOENT;
+			goto out_delete;
 		}
 
 		err = scripting_ops->generate_script(session->tevent.pevent,
 						     "perf-script");
-		goto out;
+		goto out_delete;
 	}
 
 	if (script_name) {
 		err = scripting_ops->start_script(script_name, argc, argv);
 		if (err)
-			goto out;
+			goto out_delete;
 		pr_debug("perf script started with script %s\n\n", script_name);
+		script_started = true;
 	}
 
 
 	err = perf_session__check_output_opt(session);
 	if (err < 0)
-		goto out;
+		goto out_delete;
 
 	err = __cmd_script(&script);
 
+	flush_scripting();
+
+out_delete:
 	perf_session__delete(session);
-	cleanup_scripting();
+
+	if (script_started)
+		cleanup_scripting();
 out:
 	return err;
 }
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 3e80aa10cfd8d7..5fe0edb1de5dc1 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -593,7 +593,7 @@ static int __run_perf_stat(int argc, const char **argv)
 
 	if (perf_evlist__apply_filters(evsel_list)) {
 		error("failed to set filter with %d (%s)\n", errno,
-			strerror(errno));
+			strerror_r(errno, msg, sizeof(msg)));
 		return -1;
 	}
 
diff --git a/tools/perf/builtin-timechart.c b/tools/perf/builtin-timechart.c
index 2f1a5220c090f4..48eea6cd2f5be4 100644
--- a/tools/perf/builtin-timechart.c
+++ b/tools/perf/builtin-timechart.c
@@ -1607,6 +1607,8 @@ static int __cmd_timechart(struct timechart *tchart, const char *output_name)
 	if (session == NULL)
 		return -ENOMEM;
 
+	symbol__init(&session->header.env);
+
 	(void)perf_header__process_sections(&session->header,
 					    perf_data_file__fd(session->file),
 					    tchart,
@@ -1920,7 +1922,7 @@ int cmd_timechart(int argc, const char **argv,
 			.fork		 = process_fork_event,
 			.exit		 = process_exit_event,
 			.sample		 = process_sample_event,
-			.ordered_samples = true,
+			.ordered_events	 = true,
 		},
 		.proc_num = 15,
 		.min_time = 1000000,
@@ -1982,8 +1984,6 @@ int cmd_timechart(int argc, const char **argv,
 		return -1;
 	}
 
-	symbol__init();
-
 	if (argc && !strncmp(argv[0], "rec", 3)) {
 		argc = parse_options(argc, argv, record_options, record_usage,
 				     PARSE_OPT_STOP_AT_NON_OPTION);
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 377971dc89a3b2..9848e270b92cd5 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -276,11 +276,17 @@ static void perf_top__print_sym_table(struct perf_top *top)
 		return;
 	}
 
+	if (top->zero) {
+		hists__delete_entries(&top->sym_evsel->hists);
+	} else {
+		hists__decay_entries(&top->sym_evsel->hists,
+				     top->hide_user_symbols,
+				     top->hide_kernel_symbols);
+	}
+
 	hists__collapse_resort(&top->sym_evsel->hists, NULL);
 	hists__output_resort(&top->sym_evsel->hists);
-	hists__decay_entries(&top->sym_evsel->hists,
-			     top->hide_user_symbols,
-			     top->hide_kernel_symbols);
+
 	hists__output_recalc_col_len(&top->sym_evsel->hists,
 				     top->print_entries - printed);
 	putchar('\n');
@@ -427,18 +433,13 @@ static bool perf_top__handle_keypress(struct perf_top *top, int c)
 
 	if (!perf_top__key_mapped(top, c)) {
 		struct pollfd stdin_poll = { .fd = 0, .events = POLLIN };
-		struct termios tc, save;
+		struct termios save;
 
 		perf_top__print_mapped_keys(top);
 		fprintf(stdout, "\nEnter selection, or unmapped key to continue: ");
 		fflush(stdout);
 
-		tcgetattr(0, &save);
-		tc = save;
-		tc.c_lflag &= ~(ICANON | ECHO);
-		tc.c_cc[VMIN] = 0;
-		tc.c_cc[VTIME] = 0;
-		tcsetattr(0, TCSANOW, &tc);
+		set_term_quiet_input(&save);
 
 		poll(&stdin_poll, 1, -1);
 		c = getc(stdin);
@@ -542,11 +543,16 @@ static void perf_top__sort_new_samples(void *arg)
 	if (t->evlist->selected != NULL)
 		t->sym_evsel = t->evlist->selected;
 
+	if (t->zero) {
+		hists__delete_entries(&t->sym_evsel->hists);
+	} else {
+		hists__decay_entries(&t->sym_evsel->hists,
+				     t->hide_user_symbols,
+				     t->hide_kernel_symbols);
+	}
+
 	hists__collapse_resort(&t->sym_evsel->hists, NULL);
 	hists__output_resort(&t->sym_evsel->hists);
-	hists__decay_entries(&t->sym_evsel->hists,
-			     t->hide_user_symbols,
-			     t->hide_kernel_symbols);
 }
 
 static void *display_thread_tui(void *arg)
@@ -577,23 +583,32 @@ static void *display_thread_tui(void *arg)
 	return NULL;
 }
 
+static void display_sig(int sig __maybe_unused)
+{
+	done = 1;
+}
+
+static void display_setup_sig(void)
+{
+	signal(SIGSEGV, display_sig);
+	signal(SIGFPE,  display_sig);
+	signal(SIGINT,  display_sig);
+	signal(SIGQUIT, display_sig);
+	signal(SIGTERM, display_sig);
+}
+
 static void *display_thread(void *arg)
 {
 	struct pollfd stdin_poll = { .fd = 0, .events = POLLIN };
-	struct termios tc, save;
+	struct termios save;
 	struct perf_top *top = arg;
 	int delay_msecs, c;
 
-	tcgetattr(0, &save);
-	tc = save;
-	tc.c_lflag &= ~(ICANON | ECHO);
-	tc.c_cc[VMIN] = 0;
-	tc.c_cc[VTIME] = 0;
-
+	display_setup_sig();
 	pthread__unblock_sigwinch();
 repeat:
 	delay_msecs = top->delay_secs * 1000;
-	tcsetattr(0, TCSANOW, &tc);
+	set_term_quiet_input(&save);
 	/* trash return*/
 	getc(stdin);
 
@@ -620,13 +635,16 @@ repeat:
 		}
 	}
 
+	tcsetattr(0, TCSAFLUSH, &save);
 	return NULL;
 }
 
-static int symbol_filter(struct map *map __maybe_unused, struct symbol *sym)
+static int symbol_filter(struct map *map, struct symbol *sym)
 {
 	const char *name = sym->name;
 
+	if (!map->dso->kernel)
+		return 0;
 	/*
 	 * ppc64 uses function descriptors and appends a '.' to the
 	 * start of every instruction address. Remove it.
@@ -876,7 +894,7 @@ try_again:
 
 	if (perf_evlist__mmap(evlist, opts->mmap_pages, false) < 0) {
 		ui__error("Failed to mmap with %d (%s)\n",
-			    errno, strerror(errno));
+			    errno, strerror_r(errno, msg, sizeof(msg)));
 		goto out_err;
 	}
 
@@ -963,7 +981,7 @@ static int __cmd_top(struct perf_top *top)
 		param.sched_priority = top->realtime_prio;
 		if (sched_setscheduler(0, SCHED_FIFO, &param)) {
 			ui__error("Could not set realtime priority.\n");
-			goto out_delete;
+			goto out_join;
 		}
 	}
 
@@ -977,6 +995,8 @@ static int __cmd_top(struct perf_top *top)
 	}
 
 	ret = 0;
+out_join:
+	pthread_join(thread, NULL);
 out_delete:
 	perf_session__delete(top->session);
 	top->session = NULL;
@@ -1131,6 +1151,9 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused)
 		     "Don't show entries under that percent", parse_percent_limit),
 	OPT_CALLBACK(0, "percentage", NULL, "relative|absolute",
 		     "How to display percentage of filtered entries", parse_filter_percentage),
+	OPT_STRING('w', "column-widths", &symbol_conf.col_width_list_str,
+		   "width[,width...]",
+		   "don't try to adjust column width, use these fixed values"),
 	OPT_END()
 	};
 	const char * const top_usage[] = {
@@ -1217,7 +1240,7 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused)
 	symbol_conf.priv_size = sizeof(struct annotation);
 
 	symbol_conf.try_vmlinux_path = (symbol_conf.vmlinux_name == NULL);
-	if (symbol__init() < 0)
+	if (symbol__init(NULL) < 0)
 		return -1;
 
 	sort__setup_elide(stdout);
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index a6c375224f4613..a9e96ff49c7f36 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -402,6 +402,31 @@ static size_t syscall_arg__scnprintf_mmap_flags(char *bf, size_t size,
 
 #define SCA_MMAP_FLAGS syscall_arg__scnprintf_mmap_flags
 
+static size_t syscall_arg__scnprintf_mremap_flags(char *bf, size_t size,
+						  struct syscall_arg *arg)
+{
+	int printed = 0, flags = arg->val;
+
+#define P_MREMAP_FLAG(n) \
+	if (flags & MREMAP_##n) { \
+		printed += scnprintf(bf + printed, size - printed, "%s%s", printed ? "|" : "", #n); \
+		flags &= ~MREMAP_##n; \
+	}
+
+	P_MREMAP_FLAG(MAYMOVE);
+#ifdef MREMAP_FIXED
+	P_MREMAP_FLAG(FIXED);
+#endif
+#undef P_MREMAP_FLAG
+
+	if (flags)
+		printed += scnprintf(bf + printed, size - printed, "%s%#x", printed ? "|" : "", flags);
+
+	return printed;
+}
+
+#define SCA_MREMAP_FLAGS syscall_arg__scnprintf_mremap_flags
+
 static size_t syscall_arg__scnprintf_madvise_behavior(char *bf, size_t size,
 						      struct syscall_arg *arg)
 {
@@ -1004,6 +1029,7 @@ static struct syscall_fmt {
 			     [2] = SCA_MMAP_PROT, /* prot */ }, },
 	{ .name	    = "mremap",	    .hexret = true,
 	  .arg_scnprintf = { [0] = SCA_HEX, /* addr */
+			     [3] = SCA_MREMAP_FLAGS, /* flags */
 			     [4] = SCA_HEX, /* new_addr */ }, },
 	{ .name	    = "munlock",    .errmsg = true,
 	  .arg_scnprintf = { [0] = SCA_HEX, /* addr */ }, },
@@ -1385,7 +1411,7 @@ static int trace__tool_process(struct perf_tool *tool,
 
 static int trace__symbols_init(struct trace *trace, struct perf_evlist *evlist)
 {
-	int err = symbol__init();
+	int err = symbol__init(NULL);
 
 	if (err)
 		return err;
@@ -1724,7 +1750,7 @@ static int trace__sys_exit(struct trace *trace, struct perf_evsel *evsel,
 signed_print:
 		fprintf(trace->output, ") = %d", ret);
 	} else if (ret < 0 && sc->fmt->errmsg) {
-		char bf[256];
+		char bf[STRERR_BUFSIZE];
 		const char *emsg = strerror_r(-ret, bf, sizeof(bf)),
 			   *e = audit_errno_to_name(-ret);
 
@@ -2018,6 +2044,7 @@ static int trace__run(struct trace *trace, int argc, const char **argv)
 	int err = -1, i;
 	unsigned long before;
 	const bool forks = argc > 0;
+	char sbuf[STRERR_BUFSIZE];
 
 	trace->live = true;
 
@@ -2079,7 +2106,8 @@ static int trace__run(struct trace *trace, int argc, const char **argv)
 
 	err = perf_evlist__mmap(evlist, trace->opts.mmap_pages, false);
 	if (err < 0) {
-		fprintf(trace->output, "Couldn't mmap the events: %s\n", strerror(errno));
+		fprintf(trace->output, "Couldn't mmap the events: %s\n",
+			strerror_r(errno, sbuf, sizeof(sbuf)));
 		goto out_delete_evlist;
 	}
 
@@ -2209,19 +2237,19 @@ static int trace__replay(struct trace *trace)
 	trace->tool.tracing_data = perf_event__process_tracing_data;
 	trace->tool.build_id	  = perf_event__process_build_id;
 
-	trace->tool.ordered_samples = true;
+	trace->tool.ordered_events = true;
 	trace->tool.ordering_requires_timestamps = true;
 
 	/* add tid to output */
 	trace->multiple_threads = true;
 
-	if (symbol__init() < 0)
-		return -1;
-
 	session = perf_session__new(&file, false, &trace->tool);
 	if (session == NULL)
 		return -ENOMEM;
 
+	if (symbol__init(&session->header.env) < 0)
+		goto out;
+
 	trace->host = &session->machines.host;
 
 	err = perf_session__set_tracepoints_handlers(session, handlers);
diff --git a/tools/perf/config/Makefile b/tools/perf/config/Makefile
index 1f67aa02d240b0..75d4c237b03d00 100644
--- a/tools/perf/config/Makefile
+++ b/tools/perf/config/Makefile
@@ -120,6 +120,29 @@ ifdef PARSER_DEBUG
   CFLAGS             += -DPARSER_DEBUG
 endif
 
+ifndef NO_LIBPYTHON
+  # Try different combinations to accommodate systems that only have
+  # python[2][-config] in weird combinations but always preferring
+  # python2 and python2-config as per pep-0394. If we catch a
+  # python[-config] in version 3, the version check will kill it.
+  PYTHON2 := $(if $(call get-executable,python2),python2,python)
+  override PYTHON := $(call get-executable-or-default,PYTHON,$(PYTHON2))
+  PYTHON2_CONFIG := \
+    $(if $(call get-executable,$(PYTHON)-config),$(PYTHON)-config,python-config)
+  override PYTHON_CONFIG := \
+    $(call get-executable-or-default,PYTHON_CONFIG,$(PYTHON2_CONFIG))
+
+  PYTHON_CONFIG_SQ := $(call shell-sq,$(PYTHON_CONFIG))
+
+  PYTHON_EMBED_LDOPTS := $(shell $(PYTHON_CONFIG_SQ) --ldflags 2>/dev/null)
+  PYTHON_EMBED_CCOPTS := $(shell $(PYTHON_CONFIG_SQ) --cflags 2>/dev/null)
+
+  FEATURE_CHECK_CFLAGS-libpython := $(PYTHON_EMBED_CCOPTS)
+  FEATURE_CHECK_LDFLAGS-libpython := $(PYTHON_EMBED_LDOPTS)
+  FEATURE_CHECK_CFLAGS-libpython-version := $(PYTHON_EMBED_CCOPTS)
+  FEATURE_CHECK_LDFLAGS-libpython-version := $(PYTHON_EMBED_LDOPTS)
+endif
+
 CFLAGS += -fno-omit-frame-pointer
 CFLAGS += -ggdb3
 CFLAGS += -funwind-tables
@@ -482,21 +505,14 @@ define disable-python_code
   NO_LIBPYTHON := 1
 endef
 
-override PYTHON := \
-  $(call get-executable-or-default,PYTHON,python)
-
-ifndef PYTHON
-  $(call disable-python,python interpreter)
+ifdef NO_LIBPYTHON
+  $(call disable-python)
 else
 
-  PYTHON_WORD := $(call shell-wordify,$(PYTHON))
-
-  ifdef NO_LIBPYTHON
-    $(call disable-python)
+  ifndef PYTHON
+    $(call disable-python,python interpreter)
   else
-
-    override PYTHON_CONFIG := \
-      $(call get-executable-or-default,PYTHON_CONFIG,$(PYTHON)-config)
+    PYTHON_WORD := $(call shell-wordify,$(PYTHON))
 
     ifndef PYTHON_CONFIG
       $(call disable-python,python-config tool)
diff --git a/tools/perf/config/feature-checks/Makefile b/tools/perf/config/feature-checks/Makefile
index 6088f8d8a434a2..72ab2984718e34 100644
--- a/tools/perf/config/feature-checks/Makefile
+++ b/tools/perf/config/feature-checks/Makefile
@@ -101,25 +101,11 @@ FLAGS_PERL_EMBED=$(PERL_EMBED_CCOPTS) $(PERL_EMBED_LDOPTS)
 test-libperl.bin:
 	$(BUILD) $(FLAGS_PERL_EMBED)
 
-override PYTHON := python
-override PYTHON_CONFIG := python-config
-
-escape-for-shell-sq =  $(subst ','\'',$(1))
-shell-sq = '$(escape-for-shell-sq)'
-
-PYTHON_CONFIG_SQ = $(call shell-sq,$(PYTHON_CONFIG))
-
-PYTHON_EMBED_LDOPTS = $(shell $(PYTHON_CONFIG_SQ) --ldflags 2>/dev/null)
-PYTHON_EMBED_LDFLAGS = $(call strip-libs,$(PYTHON_EMBED_LDOPTS))
-PYTHON_EMBED_LIBADD = $(call grep-libs,$(PYTHON_EMBED_LDOPTS))
-PYTHON_EMBED_CCOPTS = $(shell $(PYTHON_CONFIG_SQ) --cflags 2>/dev/null)
-FLAGS_PYTHON_EMBED = $(PYTHON_EMBED_CCOPTS) $(PYTHON_EMBED_LDOPTS)
-
 test-libpython.bin:
-	$(BUILD) $(FLAGS_PYTHON_EMBED)
+	$(BUILD)
 
 test-libpython-version.bin:
-	$(BUILD) $(FLAGS_PYTHON_EMBED)
+	$(BUILD)
 
 test-libbfd.bin:
 	$(BUILD) -DPACKAGE='"perf"' -lbfd -lz -liberty -ldl
diff --git a/tools/perf/perf.c b/tools/perf/perf.c
index 2282d41879a2b2..452a8474d29d8c 100644
--- a/tools/perf/perf.c
+++ b/tools/perf/perf.c
@@ -313,6 +313,7 @@ static int run_builtin(struct cmd_struct *p, int argc, const char **argv)
 	int status;
 	struct stat st;
 	const char *prefix;
+	char sbuf[STRERR_BUFSIZE];
 
 	prefix = NULL;
 	if (p->option & RUN_SETUP)
@@ -343,7 +344,8 @@ static int run_builtin(struct cmd_struct *p, int argc, const char **argv)
 	status = 1;
 	/* Check for ENOSPC and EIO errors.. */
 	if (fflush(stdout)) {
-		fprintf(stderr, "write failure on standard output: %s", strerror(errno));
+		fprintf(stderr, "write failure on standard output: %s",
+			strerror_r(errno, sbuf, sizeof(sbuf)));
 		goto out;
 	}
 	if (ferror(stdout)) {
@@ -351,7 +353,8 @@ static int run_builtin(struct cmd_struct *p, int argc, const char **argv)
 		goto out;
 	}
 	if (fclose(stdout)) {
-		fprintf(stderr, "close failed on standard output: %s", strerror(errno));
+		fprintf(stderr, "close failed on standard output: %s",
+			strerror_r(errno, sbuf, sizeof(sbuf)));
 		goto out;
 	}
 	status = 0;
@@ -466,6 +469,7 @@ void pthread__unblock_sigwinch(void)
 int main(int argc, const char **argv)
 {
 	const char *cmd;
+	char sbuf[STRERR_BUFSIZE];
 
 	/* The page_size is placed in util object. */
 	page_size = sysconf(_SC_PAGE_SIZE);
@@ -561,7 +565,7 @@ int main(int argc, const char **argv)
 	}
 
 	fprintf(stderr, "Failed to run command '%s': %s\n",
-		cmd, strerror(errno));
+		cmd, strerror_r(errno, sbuf, sizeof(sbuf)));
 out:
 	return 1;
 }
diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c
index 6f8b01bc60330c..6a4145e5ad2cdf 100644
--- a/tools/perf/tests/builtin-test.c
+++ b/tools/perf/tests/builtin-test.c
@@ -154,6 +154,10 @@ static struct test {
 		.func = test__hists_cumulate,
 	},
 	{
+		.desc = "Test tracking with sched_switch",
+		.func = test__switch_tracking,
+	},
+	{
 		.func = NULL,
 	},
 };
@@ -185,9 +189,11 @@ static bool perf_test__matches(int curr, int argc, const char *argv[])
 static int run_test(struct test *test)
 {
 	int status, err = -1, child = fork();
+	char sbuf[STRERR_BUFSIZE];
 
 	if (child < 0) {
-		pr_err("failed to fork test: %s\n", strerror(errno));
+		pr_err("failed to fork test: %s\n",
+			strerror_r(errno, sbuf, sizeof(sbuf)));
 		return -1;
 	}
 
@@ -297,7 +303,7 @@ int cmd_test(int argc, const char **argv, const char *prefix __maybe_unused)
 	symbol_conf.sort_by_name = true;
 	symbol_conf.try_vmlinux_path = true;
 
-	if (symbol__init() < 0)
+	if (symbol__init(NULL) < 0)
 		return -1;
 
 	if (skip != NULL)
diff --git a/tools/perf/tests/mmap-basic.c b/tools/perf/tests/mmap-basic.c
index 142263492f6fe9..9b9622a33932da 100644
--- a/tools/perf/tests/mmap-basic.c
+++ b/tools/perf/tests/mmap-basic.c
@@ -31,6 +31,7 @@ int test__basic_mmap(void)
 	unsigned int nr_events[nsyscalls],
 		     expected_nr_events[nsyscalls], i, j;
 	struct perf_evsel *evsels[nsyscalls], *evsel;
+	char sbuf[STRERR_BUFSIZE];
 
 	threads = thread_map__new(-1, getpid(), UINT_MAX);
 	if (threads == NULL) {
@@ -49,7 +50,7 @@ int test__basic_mmap(void)
 	sched_setaffinity(0, sizeof(cpu_set), &cpu_set);
 	if (sched_setaffinity(0, sizeof(cpu_set), &cpu_set) < 0) {
 		pr_debug("sched_setaffinity() failed on CPU %d: %s ",
-			 cpus->map[0], strerror(errno));
+			 cpus->map[0], strerror_r(errno, sbuf, sizeof(sbuf)));
 		goto out_free_cpus;
 	}
 
@@ -79,7 +80,7 @@ int test__basic_mmap(void)
 		if (perf_evsel__open(evsels[i], cpus, threads) < 0) {
 			pr_debug("failed to open counter: %s, "
 				 "tweak /proc/sys/kernel/perf_event_paranoid?\n",
-				 strerror(errno));
+				 strerror_r(errno, sbuf, sizeof(sbuf)));
 			goto out_delete_evlist;
 		}
 
@@ -89,7 +90,7 @@ int test__basic_mmap(void)
 
 	if (perf_evlist__mmap(evlist, 128, true) < 0) {
 		pr_debug("failed to mmap events: %d (%s)\n", errno,
-			 strerror(errno));
+			 strerror_r(errno, sbuf, sizeof(sbuf)));
 		goto out_delete_evlist;
 	}
 
diff --git a/tools/perf/tests/open-syscall-all-cpus.c b/tools/perf/tests/open-syscall-all-cpus.c
index 5fecdbd2f5f772..8fa82d1700c725 100644
--- a/tools/perf/tests/open-syscall-all-cpus.c
+++ b/tools/perf/tests/open-syscall-all-cpus.c
@@ -12,6 +12,7 @@ int test__open_syscall_event_on_all_cpus(void)
 	unsigned int nr_open_calls = 111, i;
 	cpu_set_t cpu_set;
 	struct thread_map *threads = thread_map__new(-1, getpid(), UINT_MAX);
+	char sbuf[STRERR_BUFSIZE];
 
 	if (threads == NULL) {
 		pr_debug("thread_map__new\n");
@@ -35,7 +36,7 @@ int test__open_syscall_event_on_all_cpus(void)
 	if (perf_evsel__open(evsel, cpus, threads) < 0) {
 		pr_debug("failed to open counter: %s, "
 			 "tweak /proc/sys/kernel/perf_event_paranoid?\n",
-			 strerror(errno));
+			 strerror_r(errno, sbuf, sizeof(sbuf)));
 		goto out_evsel_delete;
 	}
 
@@ -56,7 +57,7 @@ int test__open_syscall_event_on_all_cpus(void)
 		if (sched_setaffinity(0, sizeof(cpu_set), &cpu_set) < 0) {
 			pr_debug("sched_setaffinity() failed on CPU %d: %s ",
 				 cpus->map[cpu],
-				 strerror(errno));
+				 strerror_r(errno, sbuf, sizeof(sbuf)));
 			goto out_close_fd;
 		}
 		for (i = 0; i < ncalls; ++i) {
diff --git a/tools/perf/tests/open-syscall-tp-fields.c b/tools/perf/tests/open-syscall-tp-fields.c
index 0785b64ffd6cd8..922bdb627950f0 100644
--- a/tools/perf/tests/open-syscall-tp-fields.c
+++ b/tools/perf/tests/open-syscall-tp-fields.c
@@ -22,6 +22,7 @@ int test__syscall_open_tp_fields(void)
 	struct perf_evlist *evlist = perf_evlist__new();
 	struct perf_evsel *evsel;
 	int err = -1, i, nr_events = 0, nr_polls = 0;
+	char sbuf[STRERR_BUFSIZE];
 
 	if (evlist == NULL) {
 		pr_debug("%s: perf_evlist__new\n", __func__);
@@ -48,13 +49,15 @@ int test__syscall_open_tp_fields(void)
 
 	err = perf_evlist__open(evlist);
 	if (err < 0) {
-		pr_debug("perf_evlist__open: %s\n", strerror(errno));
+		pr_debug("perf_evlist__open: %s\n",
+			 strerror_r(errno, sbuf, sizeof(sbuf)));
 		goto out_delete_evlist;
 	}
 
 	err = perf_evlist__mmap(evlist, UINT_MAX, false);
 	if (err < 0) {
-		pr_debug("perf_evlist__mmap: %s\n", strerror(errno));
+		pr_debug("perf_evlist__mmap: %s\n",
+			 strerror_r(errno, sbuf, sizeof(sbuf)));
 		goto out_delete_evlist;
 	}
 
diff --git a/tools/perf/tests/open-syscall.c b/tools/perf/tests/open-syscall.c
index c1dc7d25f38c61..a33b2daae40f52 100644
--- a/tools/perf/tests/open-syscall.c
+++ b/tools/perf/tests/open-syscall.c
@@ -9,6 +9,7 @@ int test__open_syscall_event(void)
 	struct perf_evsel *evsel;
 	unsigned int nr_open_calls = 111, i;
 	struct thread_map *threads = thread_map__new(-1, getpid(), UINT_MAX);
+	char sbuf[STRERR_BUFSIZE];
 
 	if (threads == NULL) {
 		pr_debug("thread_map__new\n");
@@ -24,7 +25,7 @@ int test__open_syscall_event(void)
 	if (perf_evsel__open_per_thread(evsel, threads) < 0) {
 		pr_debug("failed to open counter: %s, "
 			 "tweak /proc/sys/kernel/perf_event_paranoid?\n",
-			 strerror(errno));
+			 strerror_r(errno, sbuf, sizeof(sbuf)));
 		goto out_evsel_delete;
 	}
 
diff --git a/tools/perf/tests/perf-record.c b/tools/perf/tests/perf-record.c
index aca1a83dd13a94..2ce753c1db63f4 100644
--- a/tools/perf/tests/perf-record.c
+++ b/tools/perf/tests/perf-record.c
@@ -59,6 +59,7 @@ int test__PERF_RECORD(void)
 	int err = -1, errs = 0, i, wakeups = 0;
 	u32 cpu;
 	int total_events = 0, nr_events[PERF_RECORD_MAX] = { 0, };
+	char sbuf[STRERR_BUFSIZE];
 
 	if (evlist == NULL || argv == NULL) {
 		pr_debug("Not enough memory to create evlist\n");
@@ -100,7 +101,8 @@ int test__PERF_RECORD(void)
 
 	err = sched__get_first_possible_cpu(evlist->workload.pid, &cpu_mask);
 	if (err < 0) {
-		pr_debug("sched__get_first_possible_cpu: %s\n", strerror(errno));
+		pr_debug("sched__get_first_possible_cpu: %s\n",
+			 strerror_r(errno, sbuf, sizeof(sbuf)));
 		goto out_delete_evlist;
 	}
 
@@ -110,7 +112,8 @@ int test__PERF_RECORD(void)
 	 * So that we can check perf_sample.cpu on all the samples.
 	 */
 	if (sched_setaffinity(evlist->workload.pid, cpu_mask_size, &cpu_mask) < 0) {
-		pr_debug("sched_setaffinity: %s\n", strerror(errno));
+		pr_debug("sched_setaffinity: %s\n",
+			 strerror_r(errno, sbuf, sizeof(sbuf)));
 		goto out_delete_evlist;
 	}
 
@@ -120,7 +123,8 @@ int test__PERF_RECORD(void)
 	 */
 	err = perf_evlist__open(evlist);
 	if (err < 0) {
-		pr_debug("perf_evlist__open: %s\n", strerror(errno));
+		pr_debug("perf_evlist__open: %s\n",
+			 strerror_r(errno, sbuf, sizeof(sbuf)));
 		goto out_delete_evlist;
 	}
 
@@ -131,7 +135,8 @@ int test__PERF_RECORD(void)
 	 */
 	err = perf_evlist__mmap(evlist, opts.mmap_pages, false);
 	if (err < 0) {
-		pr_debug("perf_evlist__mmap: %s\n", strerror(errno));
+		pr_debug("perf_evlist__mmap: %s\n",
+			 strerror_r(errno, sbuf, sizeof(sbuf)));
 		goto out_delete_evlist;
 	}
 
diff --git a/tools/perf/tests/rdpmc.c b/tools/perf/tests/rdpmc.c
index c04d1f26857656..d31f2c4d9f6491 100644
--- a/tools/perf/tests/rdpmc.c
+++ b/tools/perf/tests/rdpmc.c
@@ -100,6 +100,7 @@ static int __test__rdpmc(void)
 	};
 	u64 delta_sum = 0;
         struct sigaction sa;
+	char sbuf[STRERR_BUFSIZE];
 
 	sigfillset(&sa.sa_mask);
 	sa.sa_sigaction = segfault_handler;
@@ -109,14 +110,15 @@ static int __test__rdpmc(void)
 				 perf_event_open_cloexec_flag());
 	if (fd < 0) {
 		pr_err("Error: sys_perf_event_open() syscall returned "
-		       "with %d (%s)\n", fd, strerror(errno));
+		       "with %d (%s)\n", fd,
+		       strerror_r(errno, sbuf, sizeof(sbuf)));
 		return -1;
 	}
 
 	addr = mmap(NULL, page_size, PROT_READ, MAP_SHARED, fd, 0);
 	if (addr == (void *)(-1)) {
 		pr_err("Error: mmap() syscall returned with (%s)\n",
-		       strerror(errno));
+		       strerror_r(errno, sbuf, sizeof(sbuf)));
 		goto out_close;
 	}
 
diff --git a/tools/perf/tests/sw-clock.c b/tools/perf/tests/sw-clock.c
index 983d6b8562a89f..1aa21c90731b3e 100644
--- a/tools/perf/tests/sw-clock.c
+++ b/tools/perf/tests/sw-clock.c
@@ -22,6 +22,7 @@ static int __test__sw_clock_freq(enum perf_sw_ids clock_id)
 	volatile int tmp = 0;
 	u64 total_periods = 0;
 	int nr_samples = 0;
+	char sbuf[STRERR_BUFSIZE];
 	union perf_event *event;
 	struct perf_evsel *evsel;
 	struct perf_evlist *evlist;
@@ -62,14 +63,15 @@ static int __test__sw_clock_freq(enum perf_sw_ids clock_id)
 
 		err = -errno;
 		pr_debug("Couldn't open evlist: %s\nHint: check %s, using %" PRIu64 " in this test.\n",
-			 strerror(errno), knob, (u64)attr.sample_freq);
+			 strerror_r(errno, sbuf, sizeof(sbuf)),
+			 knob, (u64)attr.sample_freq);
 		goto out_delete_evlist;
 	}
 
 	err = perf_evlist__mmap(evlist, 128, true);
 	if (err < 0) {
 		pr_debug("failed to mmap event: %d (%s)\n", errno,
-			 strerror(errno));
+			 strerror_r(errno, sbuf, sizeof(sbuf)));
 		goto out_delete_evlist;
 	}
 
diff --git a/tools/perf/tests/switch-tracking.c b/tools/perf/tests/switch-tracking.c
new file mode 100644
index 00000000000000..cc68648c7c5552
--- /dev/null
+++ b/tools/perf/tests/switch-tracking.c
@@ -0,0 +1,572 @@
+#include <sys/time.h>
+#include <sys/prctl.h>
+#include <time.h>
+#include <stdlib.h>
+
+#include "parse-events.h"
+#include "evlist.h"
+#include "evsel.h"
+#include "thread_map.h"
+#include "cpumap.h"
+#include "tests.h"
+
+static int spin_sleep(void)
+{
+	struct timeval start, now, diff, maxtime;
+	struct timespec ts;
+	int err, i;
+
+	maxtime.tv_sec = 0;
+	maxtime.tv_usec = 50000;
+
+	err = gettimeofday(&start, NULL);
+	if (err)
+		return err;
+
+	/* Spin for 50ms */
+	while (1) {
+		for (i = 0; i < 1000; i++)
+			barrier();
+
+		err = gettimeofday(&now, NULL);
+		if (err)
+			return err;
+
+		timersub(&now, &start, &diff);
+		if (timercmp(&diff, &maxtime, > /* For checkpatch */))
+			break;
+	}
+
+	ts.tv_nsec = 50 * 1000 * 1000;
+	ts.tv_sec = 0;
+
+	/* Sleep for 50ms */
+	err = nanosleep(&ts, NULL);
+	if (err == EINTR)
+		err = 0;
+
+	return err;
+}
+
+struct switch_tracking {
+	struct perf_evsel *switch_evsel;
+	struct perf_evsel *cycles_evsel;
+	pid_t *tids;
+	int nr_tids;
+	int comm_seen[4];
+	int cycles_before_comm_1;
+	int cycles_between_comm_2_and_comm_3;
+	int cycles_after_comm_4;
+};
+
+static int check_comm(struct switch_tracking *switch_tracking,
+		      union perf_event *event, const char *comm, int nr)
+{
+	if (event->header.type == PERF_RECORD_COMM &&
+	    (pid_t)event->comm.pid == getpid() &&
+	    (pid_t)event->comm.tid == getpid() &&
+	    strcmp(event->comm.comm, comm) == 0) {
+		if (switch_tracking->comm_seen[nr]) {
+			pr_debug("Duplicate comm event\n");
+			return -1;
+		}
+		switch_tracking->comm_seen[nr] = 1;
+		pr_debug3("comm event: %s nr: %d\n", event->comm.comm, nr);
+		return 1;
+	}
+	return 0;
+}
+
+static int check_cpu(struct switch_tracking *switch_tracking, int cpu)
+{
+	int i, nr = cpu + 1;
+
+	if (cpu < 0)
+		return -1;
+
+	if (!switch_tracking->tids) {
+		switch_tracking->tids = calloc(nr, sizeof(pid_t));
+		if (!switch_tracking->tids)
+			return -1;
+		for (i = 0; i < nr; i++)
+			switch_tracking->tids[i] = -1;
+		switch_tracking->nr_tids = nr;
+		return 0;
+	}
+
+	if (cpu >= switch_tracking->nr_tids) {
+		void *addr;
+
+		addr = realloc(switch_tracking->tids, nr * sizeof(pid_t));
+		if (!addr)
+			return -1;
+		switch_tracking->tids = addr;
+		for (i = switch_tracking->nr_tids; i < nr; i++)
+			switch_tracking->tids[i] = -1;
+		switch_tracking->nr_tids = nr;
+		return 0;
+	}
+
+	return 0;
+}
+
+static int process_sample_event(struct perf_evlist *evlist,
+				union perf_event *event,
+				struct switch_tracking *switch_tracking)
+{
+	struct perf_sample sample;
+	struct perf_evsel *evsel;
+	pid_t next_tid, prev_tid;
+	int cpu, err;
+
+	if (perf_evlist__parse_sample(evlist, event, &sample)) {
+		pr_debug("perf_evlist__parse_sample failed\n");
+		return -1;
+	}
+
+	evsel = perf_evlist__id2evsel(evlist, sample.id);
+	if (evsel == switch_tracking->switch_evsel) {
+		next_tid = perf_evsel__intval(evsel, &sample, "next_pid");
+		prev_tid = perf_evsel__intval(evsel, &sample, "prev_pid");
+		cpu = sample.cpu;
+		pr_debug3("sched_switch: cpu: %d prev_tid %d next_tid %d\n",
+			  cpu, prev_tid, next_tid);
+		err = check_cpu(switch_tracking, cpu);
+		if (err)
+			return err;
+		/*
+		 * Check for no missing sched_switch events i.e. that the
+		 * evsel->system_wide flag has worked.
+		 */
+		if (switch_tracking->tids[cpu] != -1 &&
+		    switch_tracking->tids[cpu] != prev_tid) {
+			pr_debug("Missing sched_switch events\n");
+			return -1;
+		}
+		switch_tracking->tids[cpu] = next_tid;
+	}
+
+	if (evsel == switch_tracking->cycles_evsel) {
+		pr_debug3("cycles event\n");
+		if (!switch_tracking->comm_seen[0])
+			switch_tracking->cycles_before_comm_1 = 1;
+		if (switch_tracking->comm_seen[1] &&
+		    !switch_tracking->comm_seen[2])
+			switch_tracking->cycles_between_comm_2_and_comm_3 = 1;
+		if (switch_tracking->comm_seen[3])
+			switch_tracking->cycles_after_comm_4 = 1;
+	}
+
+	return 0;
+}
+
+static int process_event(struct perf_evlist *evlist, union perf_event *event,
+			 struct switch_tracking *switch_tracking)
+{
+	if (event->header.type == PERF_RECORD_SAMPLE)
+		return process_sample_event(evlist, event, switch_tracking);
+
+	if (event->header.type == PERF_RECORD_COMM) {
+		int err, done = 0;
+
+		err = check_comm(switch_tracking, event, "Test COMM 1", 0);
+		if (err < 0)
+			return -1;
+		done += err;
+		err = check_comm(switch_tracking, event, "Test COMM 2", 1);
+		if (err < 0)
+			return -1;
+		done += err;
+		err = check_comm(switch_tracking, event, "Test COMM 3", 2);
+		if (err < 0)
+			return -1;
+		done += err;
+		err = check_comm(switch_tracking, event, "Test COMM 4", 3);
+		if (err < 0)
+			return -1;
+		done += err;
+		if (done != 1) {
+			pr_debug("Unexpected comm event\n");
+			return -1;
+		}
+	}
+
+	return 0;
+}
+
+struct event_node {
+	struct list_head list;
+	union perf_event *event;
+	u64 event_time;
+};
+
+static int add_event(struct perf_evlist *evlist, struct list_head *events,
+		     union perf_event *event)
+{
+	struct perf_sample sample;
+	struct event_node *node;
+
+	node = malloc(sizeof(struct event_node));
+	if (!node) {
+		pr_debug("malloc failed\n");
+		return -1;
+	}
+	node->event = event;
+	list_add(&node->list, events);
+
+	if (perf_evlist__parse_sample(evlist, event, &sample)) {
+		pr_debug("perf_evlist__parse_sample failed\n");
+		return -1;
+	}
+
+	if (!sample.time) {
+		pr_debug("event with no time\n");
+		return -1;
+	}
+
+	node->event_time = sample.time;
+
+	return 0;
+}
+
+static void free_event_nodes(struct list_head *events)
+{
+	struct event_node *node;
+
+	while (!list_empty(events)) {
+		node = list_entry(events->next, struct event_node, list);
+		list_del(&node->list);
+		free(node);
+	}
+}
+
+static int compar(const void *a, const void *b)
+{
+	const struct event_node *nodea = a;
+	const struct event_node *nodeb = b;
+	s64 cmp = nodea->event_time - nodeb->event_time;
+
+	return cmp;
+}
+
+static int process_events(struct perf_evlist *evlist,
+			  struct switch_tracking *switch_tracking)
+{
+	union perf_event *event;
+	unsigned pos, cnt = 0;
+	LIST_HEAD(events);
+	struct event_node *events_array, *node;
+	int i, ret;
+
+	for (i = 0; i < evlist->nr_mmaps; i++) {
+		while ((event = perf_evlist__mmap_read(evlist, i)) != NULL) {
+			cnt += 1;
+			ret = add_event(evlist, &events, event);
+			perf_evlist__mmap_consume(evlist, i);
+			if (ret < 0)
+				goto out_free_nodes;
+		}
+	}
+
+	events_array = calloc(cnt, sizeof(struct event_node));
+	if (!events_array) {
+		pr_debug("calloc failed\n");
+		ret = -1;
+		goto out_free_nodes;
+	}
+
+	pos = 0;
+	list_for_each_entry(node, &events, list)
+		events_array[pos++] = *node;
+
+	qsort(events_array, cnt, sizeof(struct event_node), compar);
+
+	for (pos = 0; pos < cnt; pos++) {
+		ret = process_event(evlist, events_array[pos].event,
+				    switch_tracking);
+		if (ret < 0)
+			goto out_free;
+	}
+
+	ret = 0;
+out_free:
+	pr_debug("%u events recorded\n", cnt);
+	free(events_array);
+out_free_nodes:
+	free_event_nodes(&events);
+	return ret;
+}
+
+/**
+ * test__switch_tracking - test using sched_switch and tracking events.
+ *
+ * This function implements a test that checks that sched_switch events and
+ * tracking events can be recorded for a workload (current process) using the
+ * evsel->system_wide and evsel->tracking flags (respectively) with other events
+ * sometimes enabled or disabled.
+ */
+int test__switch_tracking(void)
+{
+	const char *sched_switch = "sched:sched_switch";
+	struct switch_tracking switch_tracking = { .tids = NULL, };
+	struct record_opts opts = {
+		.mmap_pages	     = UINT_MAX,
+		.user_freq	     = UINT_MAX,
+		.user_interval	     = ULLONG_MAX,
+		.freq		     = 4000,
+		.target		     = {
+			.uses_mmap   = true,
+		},
+	};
+	struct thread_map *threads = NULL;
+	struct cpu_map *cpus = NULL;
+	struct perf_evlist *evlist = NULL;
+	struct perf_evsel *evsel, *cpu_clocks_evsel, *cycles_evsel;
+	struct perf_evsel *switch_evsel, *tracking_evsel;
+	const char *comm;
+	int err = -1;
+
+	threads = thread_map__new(-1, getpid(), UINT_MAX);
+	if (!threads) {
+		pr_debug("thread_map__new failed!\n");
+		goto out_err;
+	}
+
+	cpus = cpu_map__new(NULL);
+	if (!cpus) {
+		pr_debug("cpu_map__new failed!\n");
+		goto out_err;
+	}
+
+	evlist = perf_evlist__new();
+	if (!evlist) {
+		pr_debug("perf_evlist__new failed!\n");
+		goto out_err;
+	}
+
+	perf_evlist__set_maps(evlist, cpus, threads);
+
+	/* First event */
+	err = parse_events(evlist, "cpu-clock:u");
+	if (err) {
+		pr_debug("Failed to parse event dummy:u\n");
+		goto out_err;
+	}
+
+	cpu_clocks_evsel = perf_evlist__last(evlist);
+
+	/* Second event */
+	err = parse_events(evlist, "cycles:u");
+	if (err) {
+		pr_debug("Failed to parse event cycles:u\n");
+		goto out_err;
+	}
+
+	cycles_evsel = perf_evlist__last(evlist);
+
+	/* Third event */
+	if (!perf_evlist__can_select_event(evlist, sched_switch)) {
+		fprintf(stderr, " (no sched_switch)");
+		err = 0;
+		goto out;
+	}
+
+	err = parse_events(evlist, sched_switch);
+	if (err) {
+		pr_debug("Failed to parse event %s\n", sched_switch);
+		goto out_err;
+	}
+
+	switch_evsel = perf_evlist__last(evlist);
+
+	perf_evsel__set_sample_bit(switch_evsel, CPU);
+	perf_evsel__set_sample_bit(switch_evsel, TIME);
+
+	switch_evsel->system_wide = true;
+	switch_evsel->no_aux_samples = true;
+	switch_evsel->immediate = true;
+
+	/* Test moving an event to the front */
+	if (cycles_evsel == perf_evlist__first(evlist)) {
+		pr_debug("cycles event already at front");
+		goto out_err;
+	}
+	perf_evlist__to_front(evlist, cycles_evsel);
+	if (cycles_evsel != perf_evlist__first(evlist)) {
+		pr_debug("Failed to move cycles event to front");
+		goto out_err;
+	}
+
+	perf_evsel__set_sample_bit(cycles_evsel, CPU);
+	perf_evsel__set_sample_bit(cycles_evsel, TIME);
+
+	/* Fourth event */
+	err = parse_events(evlist, "dummy:u");
+	if (err) {
+		pr_debug("Failed to parse event dummy:u\n");
+		goto out_err;
+	}
+
+	tracking_evsel = perf_evlist__last(evlist);
+
+	perf_evlist__set_tracking_event(evlist, tracking_evsel);
+
+	tracking_evsel->attr.freq = 0;
+	tracking_evsel->attr.sample_period = 1;
+
+	perf_evsel__set_sample_bit(tracking_evsel, TIME);
+
+	/* Config events */
+	perf_evlist__config(evlist, &opts);
+
+	/* Check moved event is still at the front */
+	if (cycles_evsel != perf_evlist__first(evlist)) {
+		pr_debug("Front event no longer at front");
+		goto out_err;
+	}
+
+	/* Check tracking event is tracking */
+	if (!tracking_evsel->attr.mmap || !tracking_evsel->attr.comm) {
+		pr_debug("Tracking event not tracking\n");
+		goto out_err;
+	}
+
+	/* Check non-tracking events are not tracking */
+	evlist__for_each(evlist, evsel) {
+		if (evsel != tracking_evsel) {
+			if (evsel->attr.mmap || evsel->attr.comm) {
+				pr_debug("Non-tracking event is tracking\n");
+				goto out_err;
+			}
+		}
+	}
+
+	if (perf_evlist__open(evlist) < 0) {
+		fprintf(stderr, " (not supported)");
+		err = 0;
+		goto out;
+	}
+
+	err = perf_evlist__mmap(evlist, UINT_MAX, false);
+	if (err) {
+		pr_debug("perf_evlist__mmap failed!\n");
+		goto out_err;
+	}
+
+	perf_evlist__enable(evlist);
+
+	err = perf_evlist__disable_event(evlist, cpu_clocks_evsel);
+	if (err) {
+		pr_debug("perf_evlist__disable_event failed!\n");
+		goto out_err;
+	}
+
+	err = spin_sleep();
+	if (err) {
+		pr_debug("spin_sleep failed!\n");
+		goto out_err;
+	}
+
+	comm = "Test COMM 1";
+	err = prctl(PR_SET_NAME, (unsigned long)comm, 0, 0, 0);
+	if (err) {
+		pr_debug("PR_SET_NAME failed!\n");
+		goto out_err;
+	}
+
+	err = perf_evlist__disable_event(evlist, cycles_evsel);
+	if (err) {
+		pr_debug("perf_evlist__disable_event failed!\n");
+		goto out_err;
+	}
+
+	comm = "Test COMM 2";
+	err = prctl(PR_SET_NAME, (unsigned long)comm, 0, 0, 0);
+	if (err) {
+		pr_debug("PR_SET_NAME failed!\n");
+		goto out_err;
+	}
+
+	err = spin_sleep();
+	if (err) {
+		pr_debug("spin_sleep failed!\n");
+		goto out_err;
+	}
+
+	comm = "Test COMM 3";
+	err = prctl(PR_SET_NAME, (unsigned long)comm, 0, 0, 0);
+	if (err) {
+		pr_debug("PR_SET_NAME failed!\n");
+		goto out_err;
+	}
+
+	err = perf_evlist__enable_event(evlist, cycles_evsel);
+	if (err) {
+		pr_debug("perf_evlist__disable_event failed!\n");
+		goto out_err;
+	}
+
+	comm = "Test COMM 4";
+	err = prctl(PR_SET_NAME, (unsigned long)comm, 0, 0, 0);
+	if (err) {
+		pr_debug("PR_SET_NAME failed!\n");
+		goto out_err;
+	}
+
+	err = spin_sleep();
+	if (err) {
+		pr_debug("spin_sleep failed!\n");
+		goto out_err;
+	}
+
+	perf_evlist__disable(evlist);
+
+	switch_tracking.switch_evsel = switch_evsel;
+	switch_tracking.cycles_evsel = cycles_evsel;
+
+	err = process_events(evlist, &switch_tracking);
+
+	zfree(&switch_tracking.tids);
+
+	if (err)
+		goto out_err;
+
+	/* Check all 4 comm events were seen i.e. that evsel->tracking works */
+	if (!switch_tracking.comm_seen[0] || !switch_tracking.comm_seen[1] ||
+	    !switch_tracking.comm_seen[2] || !switch_tracking.comm_seen[3]) {
+		pr_debug("Missing comm events\n");
+		goto out_err;
+	}
+
+	/* Check cycles event got enabled */
+	if (!switch_tracking.cycles_before_comm_1) {
+		pr_debug("Missing cycles events\n");
+		goto out_err;
+	}
+
+	/* Check cycles event got disabled */
+	if (switch_tracking.cycles_between_comm_2_and_comm_3) {
+		pr_debug("cycles events even though event was disabled\n");
+		goto out_err;
+	}
+
+	/* Check cycles event got enabled again */
+	if (!switch_tracking.cycles_after_comm_4) {
+		pr_debug("Missing cycles events\n");
+		goto out_err;
+	}
+out:
+	if (evlist) {
+		perf_evlist__disable(evlist);
+		perf_evlist__delete(evlist);
+	} else {
+		cpu_map__delete(cpus);
+		thread_map__delete(threads);
+	}
+
+	return err;
+
+out_err:
+	err = -1;
+	goto out;
+}
diff --git a/tools/perf/tests/task-exit.c b/tools/perf/tests/task-exit.c
index 5ff3db318f12ae..87522f01c7ad0c 100644
--- a/tools/perf/tests/task-exit.c
+++ b/tools/perf/tests/task-exit.c
@@ -42,6 +42,7 @@ int test__task_exit(void)
 		.uses_mmap	= true,
 	};
 	const char *argv[] = { "true", NULL };
+	char sbuf[STRERR_BUFSIZE];
 
 	signal(SIGCHLD, sig_handler);
 
@@ -82,13 +83,14 @@ int test__task_exit(void)
 
 	err = perf_evlist__open(evlist);
 	if (err < 0) {
-		pr_debug("Couldn't open the evlist: %s\n", strerror(-err));
+		pr_debug("Couldn't open the evlist: %s\n",
+			 strerror_r(-err, sbuf, sizeof(sbuf)));
 		goto out_delete_evlist;
 	}
 
 	if (perf_evlist__mmap(evlist, 128, true) < 0) {
 		pr_debug("failed to mmap events: %d (%s)\n", errno,
-			 strerror(errno));
+			 strerror_r(errno, sbuf, sizeof(sbuf)));
 		goto out_delete_evlist;
 	}
 
diff --git a/tools/perf/tests/tests.h b/tools/perf/tests/tests.h
index ed64790a395f16..be8be10e395752 100644
--- a/tools/perf/tests/tests.h
+++ b/tools/perf/tests/tests.h
@@ -48,6 +48,7 @@ int test__mmap_thread_lookup(void);
 int test__thread_mg_share(void);
 int test__hists_output(void);
 int test__hists_cumulate(void);
+int test__switch_tracking(void);
 
 #if defined(__x86_64__) || defined(__i386__) || defined(__arm__)
 #ifdef HAVE_DWARF_UNWIND_SUPPORT
diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c
index a94b11fc5e0026..d4cef68176da66 100644
--- a/tools/perf/ui/browsers/hists.c
+++ b/tools/perf/ui/browsers/hists.c
@@ -10,6 +10,7 @@
 #include "../../util/pstack.h"
 #include "../../util/sort.h"
 #include "../../util/util.h"
+#include "../../util/top.h"
 #include "../../arch/common.h"
 
 #include "../browser.h"
@@ -228,8 +229,10 @@ static void callchain_node__init_have_children(struct callchain_node *node)
 {
 	struct callchain_list *chain;
 
-	list_for_each_entry(chain, &node->val, list)
+	if (!list_empty(&node->val)) {
+		chain = list_entry(node->val.prev, struct callchain_list, list);
 		chain->ms.has_children = !RB_EMPTY_ROOT(&node->rb_root);
+	}
 
 	callchain_node__init_have_children_rb_tree(node);
 }
@@ -474,26 +477,87 @@ static char *callchain_list__sym_name(struct callchain_list *cl,
 	return bf;
 }
 
+struct callchain_print_arg {
+	/* for hists browser */
+	off_t	row_offset;
+	bool	is_current_entry;
+
+	/* for file dump */
+	FILE	*fp;
+	int	printed;
+};
+
+typedef void (*print_callchain_entry_fn)(struct hist_browser *browser,
+					 struct callchain_list *chain,
+					 const char *str, int offset,
+					 unsigned short row,
+					 struct callchain_print_arg *arg);
+
+static void hist_browser__show_callchain_entry(struct hist_browser *browser,
+					       struct callchain_list *chain,
+					       const char *str, int offset,
+					       unsigned short row,
+					       struct callchain_print_arg *arg)
+{
+	int color, width;
+	char folded_sign = callchain_list__folded(chain);
+
+	color = HE_COLORSET_NORMAL;
+	width = browser->b.width - (offset + 2);
+	if (ui_browser__is_current_entry(&browser->b, row)) {
+		browser->selection = &chain->ms;
+		color = HE_COLORSET_SELECTED;
+		arg->is_current_entry = true;
+	}
+
+	ui_browser__set_color(&browser->b, color);
+	hist_browser__gotorc(browser, row, 0);
+	slsmg_write_nstring(" ", offset);
+	slsmg_printf("%c ", folded_sign);
+	slsmg_write_nstring(str, width);
+}
+
+static void hist_browser__fprintf_callchain_entry(struct hist_browser *b __maybe_unused,
+						  struct callchain_list *chain,
+						  const char *str, int offset,
+						  unsigned short row __maybe_unused,
+						  struct callchain_print_arg *arg)
+{
+	char folded_sign = callchain_list__folded(chain);
+
+	arg->printed += fprintf(arg->fp, "%*s%c %s\n", offset, " ",
+				folded_sign, str);
+}
+
+typedef bool (*check_output_full_fn)(struct hist_browser *browser,
+				     unsigned short row);
+
+static bool hist_browser__check_output_full(struct hist_browser *browser,
+					    unsigned short row)
+{
+	return browser->b.rows == row;
+}
+
+static bool hist_browser__check_dump_full(struct hist_browser *browser __maybe_unused,
+					  unsigned short row __maybe_unused)
+{
+	return false;
+}
+
 #define LEVEL_OFFSET_STEP 3
 
-static int hist_browser__show_callchain_node_rb_tree(struct hist_browser *browser,
-						     struct callchain_node *chain_node,
-						     u64 total, int level,
-						     unsigned short row,
-						     off_t *row_offset,
-						     bool *is_current_entry)
+static int hist_browser__show_callchain(struct hist_browser *browser,
+					struct rb_root *root, int level,
+					unsigned short row, u64 total,
+					print_callchain_entry_fn print,
+					struct callchain_print_arg *arg,
+					check_output_full_fn is_output_full)
 {
 	struct rb_node *node;
-	int first_row = row, width, offset = level * LEVEL_OFFSET_STEP;
-	u64 new_total, remaining;
-
-	if (callchain_param.mode == CHAIN_GRAPH_REL)
-		new_total = chain_node->children_hit;
-	else
-		new_total = total;
+	int first_row = row, offset = level * LEVEL_OFFSET_STEP;
+	u64 new_total;
 
-	remaining = new_total;
-	node = rb_first(&chain_node->rb_root);
+	node = rb_first(root);
 	while (node) {
 		struct callchain_node *child = rb_entry(node, struct callchain_node, rb_node);
 		struct rb_node *next = rb_next(node);
@@ -503,30 +567,28 @@ static int hist_browser__show_callchain_node_rb_tree(struct hist_browser *browse
 		int first = true;
 		int extra_offset = 0;
 
-		remaining -= cumul;
-
 		list_for_each_entry(chain, &child->val, list) {
 			char bf[1024], *alloc_str;
 			const char *str;
-			int color;
 			bool was_first = first;
 
 			if (first)
 				first = false;
-			else
+			else if (level > 1)
 				extra_offset = LEVEL_OFFSET_STEP;
 
 			folded_sign = callchain_list__folded(chain);
-			if (*row_offset != 0) {
-				--*row_offset;
+			if (arg->row_offset != 0) {
+				arg->row_offset--;
 				goto do_next;
 			}
 
 			alloc_str = NULL;
 			str = callchain_list__sym_name(chain, bf, sizeof(bf),
 						       browser->show_dso);
-			if (was_first) {
-				double percent = cumul * 100.0 / new_total;
+
+			if (was_first && level > 1) {
+				double percent = cumul * 100.0 / total;
 
 				if (asprintf(&alloc_str, "%2.2f%% %s", percent, str) < 0)
 					str = "Not enough memory!";
@@ -534,22 +596,11 @@ static int hist_browser__show_callchain_node_rb_tree(struct hist_browser *browse
 					str = alloc_str;
 			}
 
-			color = HE_COLORSET_NORMAL;
-			width = browser->b.width - (offset + extra_offset + 2);
-			if (ui_browser__is_current_entry(&browser->b, row)) {
-				browser->selection = &chain->ms;
-				color = HE_COLORSET_SELECTED;
-				*is_current_entry = true;
-			}
+			print(browser, chain, str, offset + extra_offset, row, arg);
 
-			ui_browser__set_color(&browser->b, color);
-			hist_browser__gotorc(browser, row, 0);
-			slsmg_write_nstring(" ", offset + extra_offset);
-			slsmg_printf("%c ", folded_sign);
-			slsmg_write_nstring(str, width);
 			free(alloc_str);
 
-			if (++row == browser->b.rows)
+			if (is_output_full(browser, ++row))
 				goto out;
 do_next:
 			if (folded_sign == '+')
@@ -558,89 +609,21 @@ do_next:
 
 		if (folded_sign == '-') {
 			const int new_level = level + (extra_offset ? 2 : 1);
-			row += hist_browser__show_callchain_node_rb_tree(browser, child, new_total,
-									 new_level, row, row_offset,
-									 is_current_entry);
-		}
-		if (row == browser->b.rows)
-			goto out;
-		node = next;
-	}
-out:
-	return row - first_row;
-}
 
-static int hist_browser__show_callchain_node(struct hist_browser *browser,
-					     struct callchain_node *node,
-					     int level, unsigned short row,
-					     off_t *row_offset,
-					     bool *is_current_entry)
-{
-	struct callchain_list *chain;
-	int first_row = row,
-	     offset = level * LEVEL_OFFSET_STEP,
-	     width = browser->b.width - offset;
-	char folded_sign = ' ';
-
-	list_for_each_entry(chain, &node->val, list) {
-		char bf[1024], *s;
-		int color;
-
-		folded_sign = callchain_list__folded(chain);
-
-		if (*row_offset != 0) {
-			--*row_offset;
-			continue;
-		}
+			if (callchain_param.mode == CHAIN_GRAPH_REL)
+				new_total = child->children_hit;
+			else
+				new_total = total;
 
-		color = HE_COLORSET_NORMAL;
-		if (ui_browser__is_current_entry(&browser->b, row)) {
-			browser->selection = &chain->ms;
-			color = HE_COLORSET_SELECTED;
-			*is_current_entry = true;
+			row += hist_browser__show_callchain(browser, &child->rb_root,
+							    new_level, row, new_total,
+							    print, arg, is_output_full);
 		}
-
-		s = callchain_list__sym_name(chain, bf, sizeof(bf),
-					     browser->show_dso);
-		hist_browser__gotorc(browser, row, 0);
-		ui_browser__set_color(&browser->b, color);
-		slsmg_write_nstring(" ", offset);
-		slsmg_printf("%c ", folded_sign);
-		slsmg_write_nstring(s, width - 2);
-
-		if (++row == browser->b.rows)
-			goto out;
-	}
-
-	if (folded_sign == '-')
-		row += hist_browser__show_callchain_node_rb_tree(browser, node,
-								 browser->hists->stats.total_period,
-								 level + 1, row,
-								 row_offset,
-								 is_current_entry);
-out:
-	return row - first_row;
-}
-
-static int hist_browser__show_callchain(struct hist_browser *browser,
-					struct rb_root *chain,
-					int level, unsigned short row,
-					off_t *row_offset,
-					bool *is_current_entry)
-{
-	struct rb_node *nd;
-	int first_row = row;
-
-	for (nd = rb_first(chain); nd; nd = rb_next(nd)) {
-		struct callchain_node *node = rb_entry(nd, struct callchain_node, rb_node);
-
-		row += hist_browser__show_callchain_node(browser, node, level,
-							 row, row_offset,
-							 is_current_entry);
-		if (row == browser->b.rows)
+		if (is_output_full(browser, row))
 			break;
+		node = next;
 	}
-
+out:
 	return row - first_row;
 }
 
@@ -653,17 +636,18 @@ struct hpp_arg {
 static int __hpp__slsmg_color_printf(struct perf_hpp *hpp, const char *fmt, ...)
 {
 	struct hpp_arg *arg = hpp->ptr;
-	int ret;
+	int ret, len;
 	va_list args;
 	double percent;
 
 	va_start(args, fmt);
+	len = va_arg(args, int);
 	percent = va_arg(args, double);
 	va_end(args);
 
 	ui_browser__set_percent_color(arg->b, percent, arg->current_entry);
 
-	ret = scnprintf(hpp->buf, hpp->size, fmt, percent);
+	ret = scnprintf(hpp->buf, hpp->size, fmt, len, percent);
 	slsmg_printf("%s", hpp->buf);
 
 	advance_hpp(hpp, ret);
@@ -677,12 +661,12 @@ static u64 __hpp_get_##_field(struct hist_entry *he)			\
 }									\
 									\
 static int								\
-hist_browser__hpp_color_##_type(struct perf_hpp_fmt *fmt __maybe_unused,\
+hist_browser__hpp_color_##_type(struct perf_hpp_fmt *fmt,		\
 				struct perf_hpp *hpp,			\
 				struct hist_entry *he)			\
 {									\
-	return __hpp__fmt(hpp, he, __hpp_get_##_field, " %6.2f%%",	\
-			  __hpp__slsmg_color_printf, true);		\
+	return hpp__fmt(fmt, hpp, he, __hpp_get_##_field, " %*.2f%%",	\
+			__hpp__slsmg_color_printf, true);		\
 }
 
 #define __HPP_COLOR_ACC_PERCENT_FN(_type, _field)			\
@@ -692,18 +676,20 @@ static u64 __hpp_get_acc_##_field(struct hist_entry *he)		\
 }									\
 									\
 static int								\
-hist_browser__hpp_color_##_type(struct perf_hpp_fmt *fmt __maybe_unused,\
+hist_browser__hpp_color_##_type(struct perf_hpp_fmt *fmt,		\
 				struct perf_hpp *hpp,			\
 				struct hist_entry *he)			\
 {									\
 	if (!symbol_conf.cumulate_callchain) {				\
-		int ret = scnprintf(hpp->buf, hpp->size, "%8s", "N/A");	\
+		int len = fmt->user_len ?: fmt->len;			\
+		int ret = scnprintf(hpp->buf, hpp->size,		\
+				    "%*s", len, "N/A");			\
 		slsmg_printf("%s", hpp->buf);				\
 									\
 		return ret;						\
 	}								\
-	return __hpp__fmt(hpp, he, __hpp_get_acc_##_field, " %6.2f%%",	\
-			  __hpp__slsmg_color_printf, true);		\
+	return hpp__fmt(fmt, hpp, he, __hpp_get_acc_##_field,		\
+			" %*.2f%%", __hpp__slsmg_color_printf, true);	\
 }
 
 __HPP_COLOR_PERCENT_FN(overhead, period)
@@ -812,10 +798,21 @@ static int hist_browser__show_entry(struct hist_browser *browser,
 		--row_offset;
 
 	if (folded_sign == '-' && row != browser->b.rows) {
-		printed += hist_browser__show_callchain(browser, &entry->sorted_chain,
-							1, row, &row_offset,
-							&current_entry);
-		if (current_entry)
+		u64 total = hists__total_period(entry->hists);
+		struct callchain_print_arg arg = {
+			.row_offset = row_offset,
+			.is_current_entry = current_entry,
+		};
+
+		if (symbol_conf.cumulate_callchain)
+			total = entry->stat_acc->period;
+
+		printed += hist_browser__show_callchain(browser,
+					&entry->sorted_chain, 1, row, total,
+					hist_browser__show_callchain_entry, &arg,
+					hist_browser__check_output_full);
+
+		if (arg.is_current_entry)
 			browser->he_selection = entry;
 	}
 
@@ -847,9 +844,6 @@ static int hists__scnprintf_headers(char *buf, size_t size, struct hists *hists)
 		if (perf_hpp__should_skip(fmt))
 			continue;
 
-		/* We need to add the length of the columns header. */
-		perf_hpp__reset_width(fmt, hists);
-
 		ret = fmt->header(fmt, &dummy_hpp, hists_to_evsel(hists));
 		if (advance_hpp_check(&dummy_hpp, ret))
 			break;
@@ -1074,113 +1068,21 @@ do_offset:
 	}
 }
 
-static int hist_browser__fprintf_callchain_node_rb_tree(struct hist_browser *browser,
-							struct callchain_node *chain_node,
-							u64 total, int level,
-							FILE *fp)
-{
-	struct rb_node *node;
-	int offset = level * LEVEL_OFFSET_STEP;
-	u64 new_total, remaining;
-	int printed = 0;
-
-	if (callchain_param.mode == CHAIN_GRAPH_REL)
-		new_total = chain_node->children_hit;
-	else
-		new_total = total;
-
-	remaining = new_total;
-	node = rb_first(&chain_node->rb_root);
-	while (node) {
-		struct callchain_node *child = rb_entry(node, struct callchain_node, rb_node);
-		struct rb_node *next = rb_next(node);
-		u64 cumul = callchain_cumul_hits(child);
-		struct callchain_list *chain;
-		char folded_sign = ' ';
-		int first = true;
-		int extra_offset = 0;
-
-		remaining -= cumul;
-
-		list_for_each_entry(chain, &child->val, list) {
-			char bf[1024], *alloc_str;
-			const char *str;
-			bool was_first = first;
-
-			if (first)
-				first = false;
-			else
-				extra_offset = LEVEL_OFFSET_STEP;
-
-			folded_sign = callchain_list__folded(chain);
-
-			alloc_str = NULL;
-			str = callchain_list__sym_name(chain, bf, sizeof(bf),
-						       browser->show_dso);
-			if (was_first) {
-				double percent = cumul * 100.0 / new_total;
-
-				if (asprintf(&alloc_str, "%2.2f%% %s", percent, str) < 0)
-					str = "Not enough memory!";
-				else
-					str = alloc_str;
-			}
-
-			printed += fprintf(fp, "%*s%c %s\n", offset + extra_offset, " ", folded_sign, str);
-			free(alloc_str);
-			if (folded_sign == '+')
-				break;
-		}
-
-		if (folded_sign == '-') {
-			const int new_level = level + (extra_offset ? 2 : 1);
-			printed += hist_browser__fprintf_callchain_node_rb_tree(browser, child, new_total,
-										new_level, fp);
-		}
-
-		node = next;
-	}
-
-	return printed;
-}
-
-static int hist_browser__fprintf_callchain_node(struct hist_browser *browser,
-						struct callchain_node *node,
-						int level, FILE *fp)
-{
-	struct callchain_list *chain;
-	int offset = level * LEVEL_OFFSET_STEP;
-	char folded_sign = ' ';
-	int printed = 0;
-
-	list_for_each_entry(chain, &node->val, list) {
-		char bf[1024], *s;
-
-		folded_sign = callchain_list__folded(chain);
-		s = callchain_list__sym_name(chain, bf, sizeof(bf), browser->show_dso);
-		printed += fprintf(fp, "%*s%c %s\n", offset, " ", folded_sign, s);
-	}
-
-	if (folded_sign == '-')
-		printed += hist_browser__fprintf_callchain_node_rb_tree(browser, node,
-									browser->hists->stats.total_period,
-									level + 1,  fp);
-	return printed;
-}
-
 static int hist_browser__fprintf_callchain(struct hist_browser *browser,
-					   struct rb_root *chain, int level, FILE *fp)
+					   struct hist_entry *he, FILE *fp)
 {
-	struct rb_node *nd;
-	int printed = 0;
+	u64 total = hists__total_period(he->hists);
+	struct callchain_print_arg arg  = {
+		.fp = fp,
+	};
 
-	for (nd = rb_first(chain); nd; nd = rb_next(nd)) {
-		struct callchain_node *node = rb_entry(nd, struct callchain_node, rb_node);
+	if (symbol_conf.cumulate_callchain)
+		total = he->stat_acc->period;
 
-		printed += hist_browser__fprintf_callchain_node(browser, node, level, fp);
-	}
-
-	return printed;
+	hist_browser__show_callchain(browser, &he->sorted_chain, 1, 0, total,
+				     hist_browser__fprintf_callchain_entry, &arg,
+				     hist_browser__check_dump_full);
+	return arg.printed;
 }
 
 static int hist_browser__fprintf_entry(struct hist_browser *browser,
@@ -1219,7 +1121,7 @@ static int hist_browser__fprintf_entry(struct hist_browser *browser,
 	printed += fprintf(fp, "%s\n", rtrim(s));
 
 	if (folded_sign == '-')
-		printed += hist_browser__fprintf_callchain(browser, &he->sorted_chain, 1, fp);
+		printed += hist_browser__fprintf_callchain(browser, he, fp);
 
 	return printed;
 }
@@ -1498,6 +1400,7 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
 	char buf[64];
 	char script_opt[64];
 	int delay_secs = hbt ? hbt->refresh : 0;
+	struct perf_hpp_fmt *fmt;
 
 #define HIST_BROWSER_HELP_COMMON					\
 	"h/?/F1        Show this window\n"				\
@@ -1529,6 +1432,7 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
 	"P             Print histograms to perf.hist.N\n"
 	"t             Zoom into current Thread\n"
 	"V             Verbose (DSO names in callchains, etc)\n"
+	"z             Toggle zeroing of samples\n"
 	"/             Filter symbol by name";
 
 	if (browser == NULL)
@@ -1547,6 +1451,12 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
 
 	memset(options, 0, sizeof(options));
 
+	perf_hpp__for_each_format(fmt)
+		perf_hpp__reset_width(fmt, hists);
+
+	if (symbol_conf.col_width_list_str)
+		perf_hpp__set_user_width(symbol_conf.col_width_list_str);
+
 	while (1) {
 		const struct thread *thread = NULL;
 		const struct dso *dso = NULL;
@@ -1623,6 +1533,13 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
 		case 'F':
 			symbol_conf.filter_relative ^= 1;
 			continue;
+		case 'z':
+			if (!is_report_browser(hbt)) {
+				struct perf_top *top = hbt->arg;
+
+				top->zero = !top->zero;
+			}
+			continue;
 		case K_F1:
 		case 'h':
 		case '?':
diff --git a/tools/perf/ui/gtk/hists.c b/tools/perf/ui/gtk/hists.c
index 6ca60e482cdc25..f3fa4258b256b9 100644
--- a/tools/perf/ui/gtk/hists.c
+++ b/tools/perf/ui/gtk/hists.c
@@ -11,6 +11,7 @@
 static int __percent_color_snprintf(struct perf_hpp *hpp, const char *fmt, ...)
 {
 	int ret = 0;
+	int len;
 	va_list args;
 	double percent;
 	const char *markup;
@@ -18,6 +19,7 @@ static int __percent_color_snprintf(struct perf_hpp *hpp, const char *fmt, ...)
 	size_t size = hpp->size;
 
 	va_start(args, fmt);
+	len = va_arg(args, int);
 	percent = va_arg(args, double);
 	va_end(args);
 
@@ -25,7 +27,7 @@ static int __percent_color_snprintf(struct perf_hpp *hpp, const char *fmt, ...)
 	if (markup)
 		ret += scnprintf(buf, size, markup);
 
-	ret += scnprintf(buf + ret, size - ret, fmt, percent);
+	ret += scnprintf(buf + ret, size - ret, fmt, len, percent);
 
 	if (markup)
 		ret += scnprintf(buf + ret, size - ret, "</span>");
@@ -39,12 +41,12 @@ static u64 he_get_##_field(struct hist_entry *he)				\
 	return he->stat._field;							\
 }										\
 										\
-static int perf_gtk__hpp_color_##_type(struct perf_hpp_fmt *fmt __maybe_unused,	\
+static int perf_gtk__hpp_color_##_type(struct perf_hpp_fmt *fmt,		\
 				       struct perf_hpp *hpp,			\
 				       struct hist_entry *he)			\
 {										\
-	return __hpp__fmt(hpp, he, he_get_##_field, " %6.2f%%",			\
-			  __percent_color_snprintf, true);			\
+	return hpp__fmt(fmt, hpp, he, he_get_##_field, " %*.2f%%",		\
+			__percent_color_snprintf, true);			\
 }
 
 #define __HPP_COLOR_ACC_PERCENT_FN(_type, _field)				\
@@ -57,8 +59,8 @@ static int perf_gtk__hpp_color_##_type(struct perf_hpp_fmt *fmt __maybe_unused,
 				       struct perf_hpp *hpp,			\
 				       struct hist_entry *he)			\
 {										\
-	return __hpp__fmt_acc(hpp, he, he_get_acc_##_field, " %6.2f%%",		\
-			      __percent_color_snprintf, true);			\
+	return hpp__fmt_acc(fmt, hpp, he, he_get_acc_##_field, " %*.2f%%", 	\
+			    __percent_color_snprintf, true);			\
 }
 
 __HPP_COLOR_PERCENT_FN(overhead, period)
@@ -205,10 +207,8 @@ static void perf_gtk__show_hists(GtkWidget *window, struct hists *hists,
 		if (perf_hpp__is_sort_entry(fmt))
 			sym_col = col_idx;
 
-		fmt->header(fmt, &hpp, hists_to_evsel(hists));
-
 		gtk_tree_view_insert_column_with_attributes(GTK_TREE_VIEW(view),
-							    -1, ltrim(s),
+							    -1, fmt->name,
 							    renderer, "markup",
 							    col_idx++, NULL);
 	}
diff --git a/tools/perf/ui/hist.c b/tools/perf/ui/hist.c
index 498adb23c02ef9..2af18376b0772e 100644
--- a/tools/perf/ui/hist.c
+++ b/tools/perf/ui/hist.c
@@ -15,9 +15,9 @@
 	__ret;							\
 })
 
-int __hpp__fmt(struct perf_hpp *hpp, struct hist_entry *he,
-	       hpp_field_fn get_field, const char *fmt,
-	       hpp_snprint_fn print_fn, bool fmt_percent)
+static int __hpp__fmt(struct perf_hpp *hpp, struct hist_entry *he,
+		      hpp_field_fn get_field, const char *fmt, int len,
+		      hpp_snprint_fn print_fn, bool fmt_percent)
 {
 	int ret;
 	struct hists *hists = he->hists;
@@ -32,9 +32,9 @@ int __hpp__fmt(struct perf_hpp *hpp, struct hist_entry *he,
 		if (total)
 			percent = 100.0 * get_field(he) / total;
 
-		ret = hpp__call_print_fn(hpp, print_fn, fmt, percent);
+		ret = hpp__call_print_fn(hpp, print_fn, fmt, len, percent);
 	} else
-		ret = hpp__call_print_fn(hpp, print_fn, fmt, get_field(he));
+		ret = hpp__call_print_fn(hpp, print_fn, fmt, len, get_field(he));
 
 	if (perf_evsel__is_group_event(evsel)) {
 		int prev_idx, idx_delta;
@@ -60,19 +60,19 @@ int __hpp__fmt(struct perf_hpp *hpp, struct hist_entry *he,
 				 */
 				if (fmt_percent) {
 					ret += hpp__call_print_fn(hpp, print_fn,
-								  fmt, 0.0);
+								  fmt, len, 0.0);
 				} else {
 					ret += hpp__call_print_fn(hpp, print_fn,
-								  fmt, 0ULL);
+								  fmt, len, 0ULL);
 				}
 			}
 
 			if (fmt_percent) {
-				ret += hpp__call_print_fn(hpp, print_fn, fmt,
+				ret += hpp__call_print_fn(hpp, print_fn, fmt, len,
 							  100.0 * period / total);
 			} else {
 				ret += hpp__call_print_fn(hpp, print_fn, fmt,
-							  period);
+							  len, period);
 			}
 
 			prev_idx = perf_evsel__group_idx(evsel);
@@ -86,10 +86,10 @@ int __hpp__fmt(struct perf_hpp *hpp, struct hist_entry *he,
 			 */
 			if (fmt_percent) {
 				ret += hpp__call_print_fn(hpp, print_fn,
-							  fmt, 0.0);
+							  fmt, len, 0.0);
 			} else {
 				ret += hpp__call_print_fn(hpp, print_fn,
-							  fmt, 0ULL);
+							  fmt, len, 0ULL);
 			}
 		}
 	}
@@ -104,16 +104,35 @@ int __hpp__fmt(struct perf_hpp *hpp, struct hist_entry *he,
 	return ret;
 }
 
-int __hpp__fmt_acc(struct perf_hpp *hpp, struct hist_entry *he,
-		   hpp_field_fn get_field, const char *fmt,
-		   hpp_snprint_fn print_fn, bool fmt_percent)
+int hpp__fmt(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
+	     struct hist_entry *he, hpp_field_fn get_field,
+	     const char *fmtstr, hpp_snprint_fn print_fn, bool fmt_percent)
+{
+	int len = fmt->user_len ?: fmt->len;
+
+	if (symbol_conf.field_sep) {
+		return __hpp__fmt(hpp, he, get_field, fmtstr, 1,
+				  print_fn, fmt_percent);
+	}
+
+	if (fmt_percent)
+		len -= 2; /* 2 for a space and a % sign */
+	else
+		len -= 1;
+
+	return  __hpp__fmt(hpp, he, get_field, fmtstr, len, print_fn, fmt_percent);
+}
+
+int hpp__fmt_acc(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
+		 struct hist_entry *he, hpp_field_fn get_field,
+		 const char *fmtstr, hpp_snprint_fn print_fn, bool fmt_percent)
 {
 	if (!symbol_conf.cumulate_callchain) {
-		return snprintf(hpp->buf, hpp->size, "%*s",
-				fmt_percent ? 8 : 12, "N/A");
+		int len = fmt->user_len ?: fmt->len;
+		return snprintf(hpp->buf, hpp->size, " %*s", len - 1, "N/A");
 	}
 
-	return __hpp__fmt(hpp, he, get_field, fmt, print_fn, fmt_percent);
+	return hpp__fmt(fmt, hpp, he, get_field, fmtstr, print_fn, fmt_percent);
 }
 
 static int field_cmp(u64 field_a, u64 field_b)
@@ -190,30 +209,26 @@ static int __hpp__sort_acc(struct hist_entry *a, struct hist_entry *b,
 	return ret;
 }
 
-#define __HPP_HEADER_FN(_type, _str, _min_width, _unit_width) 		\
-static int hpp__header_##_type(struct perf_hpp_fmt *fmt __maybe_unused,	\
-			       struct perf_hpp *hpp,			\
-			       struct perf_evsel *evsel)		\
-{									\
-	int len = _min_width;						\
-									\
-	if (symbol_conf.event_group)					\
-		len = max(len, evsel->nr_members * _unit_width);	\
-									\
-	return scnprintf(hpp->buf, hpp->size, "%*s", len, _str);	\
-}
-
-#define __HPP_WIDTH_FN(_type, _min_width, _unit_width) 			\
-static int hpp__width_##_type(struct perf_hpp_fmt *fmt __maybe_unused,	\
-			      struct perf_hpp *hpp __maybe_unused,	\
-			      struct perf_evsel *evsel)			\
-{									\
-	int len = _min_width;						\
-									\
-	if (symbol_conf.event_group)					\
-		len = max(len, evsel->nr_members * _unit_width);	\
-									\
-	return len;							\
+static int hpp__width_fn(struct perf_hpp_fmt *fmt,
+			 struct perf_hpp *hpp __maybe_unused,
+			 struct perf_evsel *evsel)
+{
+	int len = fmt->user_len ?: fmt->len;
+
+	if (symbol_conf.event_group)
+		len = max(len, evsel->nr_members * fmt->len);
+
+	if (len < (int)strlen(fmt->name))
+		len = strlen(fmt->name);
+
+	return len;
+}
+
+static int hpp__header_fn(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
+			  struct perf_evsel *evsel)
+{
+	int len = hpp__width_fn(fmt, hpp, evsel);
+	return scnprintf(hpp->buf, hpp->size, "%*s", len, fmt->name);
 }
 
 static int hpp_color_scnprintf(struct perf_hpp *hpp, const char *fmt, ...)
@@ -221,11 +236,12 @@ static int hpp_color_scnprintf(struct perf_hpp *hpp, const char *fmt, ...)
 	va_list args;
 	ssize_t ssize = hpp->size;
 	double percent;
-	int ret;
+	int ret, len;
 
 	va_start(args, fmt);
+	len = va_arg(args, int);
 	percent = va_arg(args, double);
-	ret = value_color_snprintf(hpp->buf, hpp->size, fmt, percent);
+	ret = percent_color_len_snprintf(hpp->buf, hpp->size, fmt, len, percent);
 	va_end(args);
 
 	return (ret >= ssize) ? (ssize - 1) : ret;
@@ -250,20 +266,19 @@ static u64 he_get_##_field(struct hist_entry *he)				\
 	return he->stat._field;							\
 }										\
 										\
-static int hpp__color_##_type(struct perf_hpp_fmt *fmt __maybe_unused,		\
+static int hpp__color_##_type(struct perf_hpp_fmt *fmt,				\
 			      struct perf_hpp *hpp, struct hist_entry *he) 	\
 {										\
-	return __hpp__fmt(hpp, he, he_get_##_field, " %6.2f%%",			\
-			  hpp_color_scnprintf, true);				\
+	return hpp__fmt(fmt, hpp, he, he_get_##_field, " %*.2f%%",		\
+			hpp_color_scnprintf, true);				\
 }
 
 #define __HPP_ENTRY_PERCENT_FN(_type, _field)					\
-static int hpp__entry_##_type(struct perf_hpp_fmt *_fmt __maybe_unused,		\
+static int hpp__entry_##_type(struct perf_hpp_fmt *fmt,				\
 			      struct perf_hpp *hpp, struct hist_entry *he) 	\
 {										\
-	const char *fmt = symbol_conf.field_sep ? " %.2f" : " %6.2f%%";		\
-	return __hpp__fmt(hpp, he, he_get_##_field, fmt,			\
-			  hpp_entry_scnprintf, true);				\
+	return hpp__fmt(fmt, hpp, he, he_get_##_field, " %*.2f%%",		\
+			hpp_entry_scnprintf, true);				\
 }
 
 #define __HPP_SORT_FN(_type, _field)						\
@@ -278,20 +293,19 @@ static u64 he_get_acc_##_field(struct hist_entry *he)				\
 	return he->stat_acc->_field;						\
 }										\
 										\
-static int hpp__color_##_type(struct perf_hpp_fmt *fmt __maybe_unused,		\
+static int hpp__color_##_type(struct perf_hpp_fmt *fmt,				\
 			      struct perf_hpp *hpp, struct hist_entry *he) 	\
 {										\
-	return __hpp__fmt_acc(hpp, he, he_get_acc_##_field, " %6.2f%%",		\
-			      hpp_color_scnprintf, true);			\
+	return hpp__fmt_acc(fmt, hpp, he, he_get_acc_##_field, " %*.2f%%", 	\
+			    hpp_color_scnprintf, true);				\
 }
 
 #define __HPP_ENTRY_ACC_PERCENT_FN(_type, _field)				\
-static int hpp__entry_##_type(struct perf_hpp_fmt *_fmt __maybe_unused,		\
+static int hpp__entry_##_type(struct perf_hpp_fmt *fmt,				\
 			      struct perf_hpp *hpp, struct hist_entry *he) 	\
 {										\
-	const char *fmt = symbol_conf.field_sep ? " %.2f" : " %6.2f%%";		\
-	return __hpp__fmt_acc(hpp, he, he_get_acc_##_field, fmt,		\
-			      hpp_entry_scnprintf, true);			\
+	return hpp__fmt_acc(fmt, hpp, he, he_get_acc_##_field, " %*.2f%%",	\
+			    hpp_entry_scnprintf, true);				\
 }
 
 #define __HPP_SORT_ACC_FN(_type, _field)					\
@@ -306,12 +320,11 @@ static u64 he_get_raw_##_field(struct hist_entry *he)				\
 	return he->stat._field;							\
 }										\
 										\
-static int hpp__entry_##_type(struct perf_hpp_fmt *_fmt __maybe_unused,		\
+static int hpp__entry_##_type(struct perf_hpp_fmt *fmt,				\
 			      struct perf_hpp *hpp, struct hist_entry *he) 	\
 {										\
-	const char *fmt = symbol_conf.field_sep ? " %"PRIu64 : " %11"PRIu64;	\
-	return __hpp__fmt(hpp, he, he_get_raw_##_field, fmt,			\
-			  hpp_entry_scnprintf, false);				\
+	return hpp__fmt(fmt, hpp, he, he_get_raw_##_field, " %*"PRIu64, 	\
+			hpp_entry_scnprintf, false);				\
 }
 
 #define __HPP_SORT_RAW_FN(_type, _field)					\
@@ -321,37 +334,29 @@ static int64_t hpp__sort_##_type(struct hist_entry *a, struct hist_entry *b)	\
 }
 
 
-#define HPP_PERCENT_FNS(_type, _str, _field, _min_width, _unit_width)	\
-__HPP_HEADER_FN(_type, _str, _min_width, _unit_width)			\
-__HPP_WIDTH_FN(_type, _min_width, _unit_width)				\
+#define HPP_PERCENT_FNS(_type, _field)					\
 __HPP_COLOR_PERCENT_FN(_type, _field)					\
 __HPP_ENTRY_PERCENT_FN(_type, _field)					\
 __HPP_SORT_FN(_type, _field)
 
-#define HPP_PERCENT_ACC_FNS(_type, _str, _field, _min_width, _unit_width)\
-__HPP_HEADER_FN(_type, _str, _min_width, _unit_width)			\
-__HPP_WIDTH_FN(_type, _min_width, _unit_width)				\
+#define HPP_PERCENT_ACC_FNS(_type, _field)				\
 __HPP_COLOR_ACC_PERCENT_FN(_type, _field)				\
 __HPP_ENTRY_ACC_PERCENT_FN(_type, _field)				\
 __HPP_SORT_ACC_FN(_type, _field)
 
-#define HPP_RAW_FNS(_type, _str, _field, _min_width, _unit_width)	\
-__HPP_HEADER_FN(_type, _str, _min_width, _unit_width)			\
-__HPP_WIDTH_FN(_type, _min_width, _unit_width)				\
+#define HPP_RAW_FNS(_type, _field)					\
 __HPP_ENTRY_RAW_FN(_type, _field)					\
 __HPP_SORT_RAW_FN(_type, _field)
 
-__HPP_HEADER_FN(overhead_self, "Self", 8, 8)
-
-HPP_PERCENT_FNS(overhead, "Overhead", period, 8, 8)
-HPP_PERCENT_FNS(overhead_sys, "sys", period_sys, 8, 8)
-HPP_PERCENT_FNS(overhead_us, "usr", period_us, 8, 8)
-HPP_PERCENT_FNS(overhead_guest_sys, "guest sys", period_guest_sys, 9, 8)
-HPP_PERCENT_FNS(overhead_guest_us, "guest usr", period_guest_us, 9, 8)
-HPP_PERCENT_ACC_FNS(overhead_acc, "Children", period, 8, 8)
+HPP_PERCENT_FNS(overhead, period)
+HPP_PERCENT_FNS(overhead_sys, period_sys)
+HPP_PERCENT_FNS(overhead_us, period_us)
+HPP_PERCENT_FNS(overhead_guest_sys, period_guest_sys)
+HPP_PERCENT_FNS(overhead_guest_us, period_guest_us)
+HPP_PERCENT_ACC_FNS(overhead_acc, period)
 
-HPP_RAW_FNS(samples, "Samples", nr_events, 12, 12)
-HPP_RAW_FNS(period, "Period", period, 12, 12)
+HPP_RAW_FNS(samples, nr_events)
+HPP_RAW_FNS(period, period)
 
 static int64_t hpp__nop_cmp(struct hist_entry *a __maybe_unused,
 			    struct hist_entry *b __maybe_unused)
@@ -359,47 +364,50 @@ static int64_t hpp__nop_cmp(struct hist_entry *a __maybe_unused,
 	return 0;
 }
 
-#define HPP__COLOR_PRINT_FNS(_name)			\
+#define HPP__COLOR_PRINT_FNS(_name, _fn)		\
 	{						\
-		.header	= hpp__header_ ## _name,	\
-		.width	= hpp__width_ ## _name,		\
-		.color	= hpp__color_ ## _name,		\
-		.entry	= hpp__entry_ ## _name,		\
+		.name   = _name,			\
+		.header	= hpp__header_fn,		\
+		.width	= hpp__width_fn,		\
+		.color	= hpp__color_ ## _fn,		\
+		.entry	= hpp__entry_ ## _fn,		\
 		.cmp	= hpp__nop_cmp,			\
 		.collapse = hpp__nop_cmp,		\
-		.sort	= hpp__sort_ ## _name,		\
+		.sort	= hpp__sort_ ## _fn,		\
 	}
 
-#define HPP__COLOR_ACC_PRINT_FNS(_name)			\
+#define HPP__COLOR_ACC_PRINT_FNS(_name, _fn)		\
 	{						\
-		.header	= hpp__header_ ## _name,	\
-		.width	= hpp__width_ ## _name,		\
-		.color	= hpp__color_ ## _name,		\
-		.entry	= hpp__entry_ ## _name,		\
+		.name   = _name,			\
+		.header	= hpp__header_fn,		\
+		.width	= hpp__width_fn,		\
+		.color	= hpp__color_ ## _fn,		\
+		.entry	= hpp__entry_ ## _fn,		\
 		.cmp	= hpp__nop_cmp,			\
 		.collapse = hpp__nop_cmp,		\
-		.sort	= hpp__sort_ ## _name,		\
+		.sort	= hpp__sort_ ## _fn,		\
 	}
 
-#define HPP__PRINT_FNS(_name)				\
+#define HPP__PRINT_FNS(_name, _fn)			\
 	{						\
-		.header	= hpp__header_ ## _name,	\
-		.width	= hpp__width_ ## _name,		\
-		.entry	= hpp__entry_ ## _name,		\
+		.name   = _name,			\
+		.header	= hpp__header_fn,		\
+		.width	= hpp__width_fn,		\
+		.entry	= hpp__entry_ ## _fn,		\
 		.cmp	= hpp__nop_cmp,			\
 		.collapse = hpp__nop_cmp,		\
-		.sort	= hpp__sort_ ## _name,		\
+		.sort	= hpp__sort_ ## _fn,		\
 	}
 
 struct perf_hpp_fmt perf_hpp__format[] = {
-	HPP__COLOR_PRINT_FNS(overhead),
-	HPP__COLOR_PRINT_FNS(overhead_sys),
-	HPP__COLOR_PRINT_FNS(overhead_us),
-	HPP__COLOR_PRINT_FNS(overhead_guest_sys),
-	HPP__COLOR_PRINT_FNS(overhead_guest_us),
-	HPP__COLOR_ACC_PRINT_FNS(overhead_acc),
-	HPP__PRINT_FNS(samples),
-	HPP__PRINT_FNS(period)
+	HPP__COLOR_PRINT_FNS("Overhead", overhead),
+	HPP__COLOR_PRINT_FNS("sys", overhead_sys),
+	HPP__COLOR_PRINT_FNS("usr", overhead_us),
+	HPP__COLOR_PRINT_FNS("guest sys", overhead_guest_sys),
+	HPP__COLOR_PRINT_FNS("guest usr", overhead_guest_us),
+	HPP__COLOR_ACC_PRINT_FNS("Children", overhead_acc),
+	HPP__PRINT_FNS("Samples", samples),
+	HPP__PRINT_FNS("Period", period)
 };
 
 LIST_HEAD(perf_hpp__list);
@@ -444,14 +452,12 @@ void perf_hpp__init(void)
 	/*
 	 * If user specified field order, no need to setup default fields.
 	 */
-	if (field_order)
+	if (is_strict_order(field_order))
 		return;
 
 	if (symbol_conf.cumulate_callchain) {
 		perf_hpp__column_enable(PERF_HPP__OVERHEAD_ACC);
-
-		perf_hpp__format[PERF_HPP__OVERHEAD].header =
-						hpp__header_overhead_self;
+		perf_hpp__format[PERF_HPP__OVERHEAD].name = "Self";
 	}
 
 	perf_hpp__column_enable(PERF_HPP__OVERHEAD);
@@ -513,11 +519,11 @@ void perf_hpp__column_disable(unsigned col)
 
 void perf_hpp__cancel_cumulate(void)
 {
-	if (field_order)
+	if (is_strict_order(field_order))
 		return;
 
 	perf_hpp__column_disable(PERF_HPP__OVERHEAD_ACC);
-	perf_hpp__format[PERF_HPP__OVERHEAD].header = hpp__header_overhead;
+	perf_hpp__format[PERF_HPP__OVERHEAD].name = "Overhead";
 }
 
 void perf_hpp__setup_output_field(void)
@@ -622,3 +628,59 @@ unsigned int hists__sort_list_width(struct hists *hists)
 
 	return ret;
 }
+
+void perf_hpp__reset_width(struct perf_hpp_fmt *fmt, struct hists *hists)
+{
+	int idx;
+
+	if (perf_hpp__is_sort_entry(fmt))
+		return perf_hpp__reset_sort_width(fmt, hists);
+
+	for (idx = 0; idx < PERF_HPP__MAX_INDEX; idx++) {
+		if (fmt == &perf_hpp__format[idx])
+			break;
+	}
+
+	if (idx == PERF_HPP__MAX_INDEX)
+		return;
+
+	switch (idx) {
+	case PERF_HPP__OVERHEAD:
+	case PERF_HPP__OVERHEAD_SYS:
+	case PERF_HPP__OVERHEAD_US:
+	case PERF_HPP__OVERHEAD_ACC:
+		fmt->len = 8;
+		break;
+
+	case PERF_HPP__OVERHEAD_GUEST_SYS:
+	case PERF_HPP__OVERHEAD_GUEST_US:
+		fmt->len = 9;
+		break;
+
+	case PERF_HPP__SAMPLES:
+	case PERF_HPP__PERIOD:
+		fmt->len = 12;
+		break;
+
+	default:
+		break;
+	}
+}
+
+void perf_hpp__set_user_width(const char *width_list_str)
+{
+	struct perf_hpp_fmt *fmt;
+	const char *ptr = width_list_str;
+
+	perf_hpp__for_each_format(fmt) {
+		char *p;
+
+		int len = strtol(ptr, &p, 10);
+		fmt->user_len = len;
+
+		if (*p == ',')
+			ptr = p + 1;
+		else
+			break;
+	}
+}
diff --git a/tools/perf/ui/stdio/hist.c b/tools/perf/ui/stdio/hist.c
index 40af0acb4fe95d..15b451acbde610 100644
--- a/tools/perf/ui/stdio/hist.c
+++ b/tools/perf/ui/stdio/hist.c
@@ -395,10 +395,12 @@ size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows,
 
 	init_rem_hits();
 
-
 	perf_hpp__for_each_format(fmt)
 		perf_hpp__reset_width(fmt, hists);
 
+	if (symbol_conf.col_width_list_str)
+		perf_hpp__set_user_width(symbol_conf.col_width_list_str);
+
 	if (!show_header)
 		goto print_entries;
 
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 809b4c50beaed3..36437527dbb347 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -232,9 +232,16 @@ static int mov__parse(struct ins_operands *ops)
 		return -1;
 
 	target = ++s;
+	comment = strchr(s, '#');
 
-	while (s[0] != '\0' && !isspace(s[0]))
-		++s;
+	if (comment != NULL)
+		s = comment - 1;
+	else
+		s = strchr(s, '\0') - 1;
+
+	while (s > target && isspace(s[0]))
+		--s;
+	s++;
 	prev = *s;
 	*s = '\0';
 
@@ -244,7 +251,6 @@ static int mov__parse(struct ins_operands *ops)
 	if (ops->target.raw == NULL)
 		goto out_free_source;
 
-	comment = strchr(s, '#');
 	if (comment == NULL)
 		return 0;
 
@@ -899,10 +905,8 @@ int symbol__annotate(struct symbol *sym, struct map *map, size_t privsize)
 	struct kcore_extract kce;
 	bool delete_extract = false;
 
-	if (filename) {
-		snprintf(symfs_filename, sizeof(symfs_filename), "%s%s",
-			 symbol_conf.symfs, filename);
-	}
+	if (filename)
+		symbol__join_symfs(symfs_filename, filename);
 
 	if (filename == NULL) {
 		if (dso->has_build_id) {
@@ -922,8 +926,7 @@ fallback:
 		 * DSO is the same as when 'perf record' ran.
 		 */
 		filename = (char *)dso->long_name;
-		snprintf(symfs_filename, sizeof(symfs_filename), "%s%s",
-			 symbol_conf.symfs, filename);
+		symbol__join_symfs(symfs_filename, filename);
 		free_filename = false;
 	}
 
diff --git a/tools/perf/util/cache.h b/tools/perf/util/cache.h
index 7b176dd02e1ae9..5cf9e1b5989de4 100644
--- a/tools/perf/util/cache.h
+++ b/tools/perf/util/cache.h
@@ -22,6 +22,7 @@ typedef int (*config_fn_t)(const char *, const char *, void *);
 extern int perf_default_config(const char *, const char *, void *);
 extern int perf_config(config_fn_t fn, void *);
 extern int perf_config_int(const char *, const char *);
+extern u64 perf_config_u64(const char *, const char *);
 extern int perf_config_bool(const char *, const char *);
 extern int config_error_nonbool(const char *);
 extern const char *perf_config_dirname(const char *, const char *);
diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c
index 437ee09727e605..08f0fbf5527c35 100644
--- a/tools/perf/util/callchain.c
+++ b/tools/perf/util/callchain.c
@@ -28,74 +28,55 @@ __thread struct callchain_cursor callchain_cursor;
 int
 parse_callchain_report_opt(const char *arg)
 {
-	char *tok, *tok2;
+	char *tok;
 	char *endptr;
+	bool minpcnt_set = false;
 
 	symbol_conf.use_callchain = true;
 
 	if (!arg)
 		return 0;
 
-	tok = strtok((char *)arg, ",");
-	if (!tok)
-		return -1;
-
-	/* get the output mode */
-	if (!strncmp(tok, "graph", strlen(arg))) {
-		callchain_param.mode = CHAIN_GRAPH_ABS;
-
-	} else if (!strncmp(tok, "flat", strlen(arg))) {
-		callchain_param.mode = CHAIN_FLAT;
-	} else if (!strncmp(tok, "fractal", strlen(arg))) {
-		callchain_param.mode = CHAIN_GRAPH_REL;
-	} else if (!strncmp(tok, "none", strlen(arg))) {
-		callchain_param.mode = CHAIN_NONE;
-		symbol_conf.use_callchain = false;
-		return 0;
-	} else {
-		return -1;
-	}
-
-	/* get the min percentage */
-	tok = strtok(NULL, ",");
-	if (!tok)
-		goto setup;
-
-	callchain_param.min_percent = strtod(tok, &endptr);
-	if (tok == endptr)
-		return -1;
+	while ((tok = strtok((char *)arg, ",")) != NULL) {
+		if (!strncmp(tok, "none", strlen(tok))) {
+			callchain_param.mode = CHAIN_NONE;
+			symbol_conf.use_callchain = false;
+			return 0;
+		}
 
-	/* get the print limit */
-	tok2 = strtok(NULL, ",");
-	if (!tok2)
-		goto setup;
+		/* try to get the output mode */
+		if (!strncmp(tok, "graph", strlen(tok)))
+			callchain_param.mode = CHAIN_GRAPH_ABS;
+		else if (!strncmp(tok, "flat", strlen(tok)))
+			callchain_param.mode = CHAIN_FLAT;
+		else if (!strncmp(tok, "fractal", strlen(tok)))
+			callchain_param.mode = CHAIN_GRAPH_REL;
+		/* try to get the call chain order */
+		else if (!strncmp(tok, "caller", strlen(tok)))
+			callchain_param.order = ORDER_CALLER;
+		else if (!strncmp(tok, "callee", strlen(tok)))
+			callchain_param.order = ORDER_CALLEE;
+		/* try to get the sort key */
+		else if (!strncmp(tok, "function", strlen(tok)))
+			callchain_param.key = CCKEY_FUNCTION;
+		else if (!strncmp(tok, "address", strlen(tok)))
+			callchain_param.key = CCKEY_ADDRESS;
+		/* try to get the min percent */
+		else if (!minpcnt_set) {
+			callchain_param.min_percent = strtod(tok, &endptr);
+			if (tok == endptr)
+				return -1;
+			minpcnt_set = true;
+		} else {
+			/* try print limit at last */
+			callchain_param.print_limit = strtoul(tok, &endptr, 0);
+			if (tok == endptr)
+				return -1;
+		}
 
-	if (tok2[0] != 'c') {
-		callchain_param.print_limit = strtoul(tok2, &endptr, 0);
-		tok2 = strtok(NULL, ",");
-		if (!tok2)
-			goto setup;
+		arg = NULL;
 	}
 
-	/* get the call chain order */
-	if (!strncmp(tok2, "caller", strlen("caller")))
-		callchain_param.order = ORDER_CALLER;
-	else if (!strncmp(tok2, "callee", strlen("callee")))
-		callchain_param.order = ORDER_CALLEE;
-	else
-		return -1;
-
-	/* Get the sort key */
-	tok2 = strtok(NULL, ",");
-	if (!tok2)
-		goto setup;
-	if (!strncmp(tok2, "function", strlen("function")))
-		callchain_param.key = CCKEY_FUNCTION;
-	else if (!strncmp(tok2, "address", strlen("address")))
-		callchain_param.key = CCKEY_ADDRESS;
-	else
-		return -1;
-setup:
 	if (callchain_register_param(&callchain_param) < 0) {
 		pr_err("Can't register callchain params\n");
 		return -1;
diff --git a/tools/perf/util/cloexec.c b/tools/perf/util/cloexec.c
index c5d05ec172206d..47b78b3f032573 100644
--- a/tools/perf/util/cloexec.c
+++ b/tools/perf/util/cloexec.c
@@ -1,7 +1,9 @@
+#include <sched.h>
 #include "util.h"
 #include "../perf.h"
 #include "cloexec.h"
 #include "asm/bug.h"
+#include "debug.h"
 
 static unsigned long flag = PERF_FLAG_FD_CLOEXEC;
 
@@ -9,15 +11,30 @@ static int perf_flag_probe(void)
 {
 	/* use 'safest' configuration as used in perf_evsel__fallback() */
 	struct perf_event_attr attr = {
-		.type = PERF_COUNT_SW_CPU_CLOCK,
+		.type = PERF_TYPE_SOFTWARE,
 		.config = PERF_COUNT_SW_CPU_CLOCK,
+		.exclude_kernel = 1,
 	};
 	int fd;
 	int err;
+	int cpu;
+	pid_t pid = -1;
+	char sbuf[STRERR_BUFSIZE];
 
-	/* check cloexec flag */
-	fd = sys_perf_event_open(&attr, 0, -1, -1,
-				 PERF_FLAG_FD_CLOEXEC);
+	cpu = sched_getcpu();
+	if (cpu < 0)
+		cpu = 0;
+
+	while (1) {
+		/* check cloexec flag */
+		fd = sys_perf_event_open(&attr, pid, cpu, -1,
+					 PERF_FLAG_FD_CLOEXEC);
+		if (fd < 0 && pid == -1 && errno == EACCES) {
+			pid = 0;
+			continue;
+		}
+		break;
+	}
 	err = errno;
 
 	if (fd >= 0) {
@@ -25,17 +42,17 @@ static int perf_flag_probe(void)
 		return 1;
 	}
 
-	WARN_ONCE(err != EINVAL,
+	WARN_ONCE(err != EINVAL && err != EBUSY,
 		  "perf_event_open(..., PERF_FLAG_FD_CLOEXEC) failed with unexpected error %d (%s)\n",
-		  err, strerror(err));
+		  err, strerror_r(err, sbuf, sizeof(sbuf)));
 
 	/* not supported, confirm error related to PERF_FLAG_FD_CLOEXEC */
-	fd = sys_perf_event_open(&attr, 0, -1, -1, 0);
+	fd = sys_perf_event_open(&attr, pid, cpu, -1, 0);
 	err = errno;
 
-	if (WARN_ONCE(fd < 0,
+	if (WARN_ONCE(fd < 0 && err != EBUSY,
 		      "perf_event_open(..., 0) failed unexpectedly with error %d (%s)\n",
-		      err, strerror(err)))
+		      err, strerror_r(err, sbuf, sizeof(sbuf))))
 		return -1;
 
 	close(fd);
diff --git a/tools/perf/util/color.c b/tools/perf/util/color.c
index 87b8672eb4134c..f4654183d391a4 100644
--- a/tools/perf/util/color.c
+++ b/tools/perf/util/color.c
@@ -335,3 +335,19 @@ int percent_color_snprintf(char *bf, size_t size, const char *fmt, ...)
 	va_end(args);
 	return value_color_snprintf(bf, size, fmt, percent);
 }
+
+int percent_color_len_snprintf(char *bf, size_t size, const char *fmt, ...)
+{
+	va_list args;
+	int len;
+	double percent;
+	const char *color;
+
+	va_start(args, fmt);
+	len = va_arg(args, int);
+	percent = va_arg(args, double);
+	va_end(args);
+
+	color = get_percent_color(percent);
+	return color_snprintf(bf, size, color, fmt, len, percent);
+}
diff --git a/tools/perf/util/color.h b/tools/perf/util/color.h
index 7ff30a62a13229..0a594b8a0c26ab 100644
--- a/tools/perf/util/color.h
+++ b/tools/perf/util/color.h
@@ -41,6 +41,7 @@ int color_fprintf_ln(FILE *fp, const char *color, const char *fmt, ...);
 int color_fwrite_lines(FILE *fp, const char *color, size_t count, const char *buf);
 int value_color_snprintf(char *bf, size_t size, const char *fmt, double value);
 int percent_color_snprintf(char *bf, size_t size, const char *fmt, ...);
+int percent_color_len_snprintf(char *bf, size_t size, const char *fmt, ...);
 int percent_color_fprintf(FILE *fp, const char *fmt, double percent);
 const char *get_percent_color(double percent);
 
diff --git a/tools/perf/util/comm.c b/tools/perf/util/comm.c
index f9e777629e21cd..b2bb59df65e10c 100644
--- a/tools/perf/util/comm.c
+++ b/tools/perf/util/comm.c
@@ -74,7 +74,7 @@ static struct comm_str *comm_str__findnew(const char *str, struct rb_root *root)
 	return new;
 }
 
-struct comm *comm__new(const char *str, u64 timestamp)
+struct comm *comm__new(const char *str, u64 timestamp, bool exec)
 {
 	struct comm *comm = zalloc(sizeof(*comm));
 
@@ -82,6 +82,7 @@ struct comm *comm__new(const char *str, u64 timestamp)
 		return NULL;
 
 	comm->start = timestamp;
+	comm->exec = exec;
 
 	comm->comm_str = comm_str__findnew(str, &comm_str_root);
 	if (!comm->comm_str) {
@@ -94,7 +95,7 @@ struct comm *comm__new(const char *str, u64 timestamp)
 	return comm;
 }
 
-int comm__override(struct comm *comm, const char *str, u64 timestamp)
+int comm__override(struct comm *comm, const char *str, u64 timestamp, bool exec)
 {
 	struct comm_str *new, *old = comm->comm_str;
 
@@ -106,6 +107,8 @@ int comm__override(struct comm *comm, const char *str, u64 timestamp)
 	comm_str__put(old);
 	comm->comm_str = new;
 	comm->start = timestamp;
+	if (exec)
+		comm->exec = true;
 
 	return 0;
 }
diff --git a/tools/perf/util/comm.h b/tools/perf/util/comm.h
index fac5bd51befc4c..51c10ab257f8b2 100644
--- a/tools/perf/util/comm.h
+++ b/tools/perf/util/comm.h
@@ -11,11 +11,13 @@ struct comm {
 	struct comm_str *comm_str;
 	u64 start;
 	struct list_head list;
+	bool exec;
 };
 
 void comm__free(struct comm *comm);
-struct comm *comm__new(const char *str, u64 timestamp);
+struct comm *comm__new(const char *str, u64 timestamp, bool exec);
 const char *comm__str(const struct comm *comm);
-int comm__override(struct comm *comm, const char *str, u64 timestamp);
+int comm__override(struct comm *comm, const char *str, u64 timestamp,
+		   bool exec);
 
 #endif  /* __PERF_COMM_H */
diff --git a/tools/perf/util/config.c b/tools/perf/util/config.c
index 1e5e2e5af6b1d0..9970b8b0190bbd 100644
--- a/tools/perf/util/config.c
+++ b/tools/perf/util/config.c
@@ -286,6 +286,21 @@ static int parse_unit_factor(const char *end, unsigned long *val)
 	return 0;
 }
 
+static int perf_parse_llong(const char *value, long long *ret)
+{
+	if (value && *value) {
+		char *end;
+		long long val = strtoll(value, &end, 0);
+		unsigned long factor = 1;
+
+		if (!parse_unit_factor(end, &factor))
+			return 0;
+		*ret = val * factor;
+		return 1;
+	}
+	return 0;
+}
+
 static int perf_parse_long(const char *value, long *ret)
 {
 	if (value && *value) {
@@ -307,6 +322,15 @@ static void die_bad_config(const char *name)
 	die("bad config value for '%s'", name);
 }
 
+u64 perf_config_u64(const char *name, const char *value)
+{
+	long long ret = 0;
+
+	if (!perf_parse_llong(value, &ret))
+		die_bad_config(name);
+	return (u64) ret;
+}
+
 int perf_config_int(const char *name, const char *value)
 {
 	long ret = 0;
diff --git a/tools/perf/util/data.c b/tools/perf/util/data.c
index 29d720cf584476..1921942fc2e035 100644
--- a/tools/perf/util/data.c
+++ b/tools/perf/util/data.c
@@ -50,12 +50,14 @@ static int open_file_read(struct perf_data_file *file)
 {
 	struct stat st;
 	int fd;
+	char sbuf[STRERR_BUFSIZE];
 
 	fd = open(file->path, O_RDONLY);
 	if (fd < 0) {
 		int err = errno;
 
-		pr_err("failed to open %s: %s", file->path, strerror(err));
+		pr_err("failed to open %s: %s", file->path,
+			strerror_r(err, sbuf, sizeof(sbuf)));
 		if (err == ENOENT && !strcmp(file->path, "perf.data"))
 			pr_err("  (try 'perf record' first)");
 		pr_err("\n");
@@ -88,6 +90,7 @@ static int open_file_read(struct perf_data_file *file)
 static int open_file_write(struct perf_data_file *file)
 {
 	int fd;
+	char sbuf[STRERR_BUFSIZE];
 
 	if (check_backup(file))
 		return -1;
@@ -95,7 +98,8 @@ static int open_file_write(struct perf_data_file *file)
 	fd = open(file->path, O_CREAT|O_RDWR|O_TRUNC, S_IRUSR|S_IWUSR);
 
 	if (fd < 0)
-		pr_err("failed to open %s : %s\n", file->path, strerror(errno));
+		pr_err("failed to open %s : %s\n", file->path,
+			strerror_r(errno, sbuf, sizeof(sbuf)));
 
 	return fd;
 }
diff --git a/tools/perf/util/debug.c b/tools/perf/util/debug.c
index 71d41936263476..ba357f3226c695 100644
--- a/tools/perf/util/debug.c
+++ b/tools/perf/util/debug.c
@@ -13,8 +13,12 @@
 #include "util.h"
 #include "target.h"
 
+#define NSECS_PER_SEC  1000000000ULL
+#define NSECS_PER_USEC 1000ULL
+
 int verbose;
 bool dump_trace = false, quiet = false;
+int debug_ordered_events;
 
 static int _eprintf(int level, int var, const char *fmt, va_list args)
 {
@@ -42,6 +46,35 @@ int eprintf(int level, int var, const char *fmt, ...)
 	return ret;
 }
 
+static int __eprintf_time(u64 t, const char *fmt, va_list args)
+{
+	int ret = 0;
+	u64 secs, usecs, nsecs = t;
+
+	secs   = nsecs / NSECS_PER_SEC;
+	nsecs -= secs  * NSECS_PER_SEC;
+	usecs  = nsecs / NSECS_PER_USEC;
+
+	ret = fprintf(stderr, "[%13" PRIu64 ".%06" PRIu64 "] ",
+		      secs, usecs);
+	ret += vfprintf(stderr, fmt, args);
+	return ret;
+}
+
+int eprintf_time(int level, int var, u64 t, const char *fmt, ...)
+{
+	int ret = 0;
+	va_list args;
+
+	if (var >= level) {
+		va_start(args, fmt);
+		ret = __eprintf_time(t, fmt, args);
+		va_end(args);
+	}
+
+	return ret;
+}
+
 /*
  * Overloading libtraceevent standard info print
  * function, display with -v in perf.
@@ -110,7 +143,8 @@ static struct debug_variable {
 	const char *name;
 	int *ptr;
 } debug_variables[] = {
-	{ .name = "verbose", .ptr = &verbose },
+	{ .name = "verbose",		.ptr = &verbose },
+	{ .name = "ordered-events",	.ptr = &debug_ordered_events},
 	{ .name = NULL, }
 };
 
diff --git a/tools/perf/util/debug.h b/tools/perf/util/debug.h
index 89fb6b0f7ab221..be264d6f3b3049 100644
--- a/tools/perf/util/debug.h
+++ b/tools/perf/util/debug.h
@@ -3,6 +3,7 @@
 #define __PERF_DEBUG_H
 
 #include <stdbool.h>
+#include <string.h>
 #include "event.h"
 #include "../ui/helpline.h"
 #include "../ui/progress.h"
@@ -10,6 +11,7 @@
 
 extern int verbose;
 extern bool quiet, dump_trace;
+extern int debug_ordered_events;
 
 #ifndef pr_fmt
 #define pr_fmt(fmt) fmt
@@ -29,6 +31,14 @@ extern bool quiet, dump_trace;
 #define pr_debug3(fmt, ...) pr_debugN(3, pr_fmt(fmt), ##__VA_ARGS__)
 #define pr_debug4(fmt, ...) pr_debugN(4, pr_fmt(fmt), ##__VA_ARGS__)
 
+#define pr_time_N(n, var, t, fmt, ...) \
+	eprintf_time(n, var, t, fmt, ##__VA_ARGS__)
+
+#define pr_oe_time(t, fmt, ...)  pr_time_N(1, debug_ordered_events, t, pr_fmt(fmt), ##__VA_ARGS__)
+#define pr_oe_time2(t, fmt, ...) pr_time_N(2, debug_ordered_events, t, pr_fmt(fmt), ##__VA_ARGS__)
+
+#define STRERR_BUFSIZE	128	/* For the buffer size of strerror_r */
+
 int dump_printf(const char *fmt, ...) __attribute__((format(printf, 1, 2)));
 void trace_event(union perf_event *event);
 
@@ -38,6 +48,7 @@ int ui__warning(const char *format, ...) __attribute__((format(printf, 1, 2)));
 void pr_stat(const char *fmt, ...);
 
 int eprintf(int level, int var, const char *fmt, ...) __attribute__((format(printf, 3, 4)));
+int eprintf_time(int level, int var, u64 t, const char *fmt, ...) __attribute__((format(printf, 4, 5)));
 
 int perf_debug_option(const char *str);
 
diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c
index 90d02c661dd4b5..55e39dc1bcda70 100644
--- a/tools/perf/util/dso.c
+++ b/tools/perf/util/dso.c
@@ -37,6 +37,7 @@ int dso__read_binary_type_filename(const struct dso *dso,
 {
 	char build_id_hex[BUILD_ID_SIZE * 2 + 1];
 	int ret = 0;
+	size_t len;
 
 	switch (type) {
 	case DSO_BINARY_TYPE__DEBUGLINK: {
@@ -60,26 +61,25 @@ int dso__read_binary_type_filename(const struct dso *dso,
 		break;
 
 	case DSO_BINARY_TYPE__FEDORA_DEBUGINFO:
-		snprintf(filename, size, "%s/usr/lib/debug%s.debug",
-			 symbol_conf.symfs, dso->long_name);
+		len = __symbol__join_symfs(filename, size, "/usr/lib/debug");
+		snprintf(filename + len, size - len, "%s.debug", dso->long_name);
 		break;
 
 	case DSO_BINARY_TYPE__UBUNTU_DEBUGINFO:
-		snprintf(filename, size, "%s/usr/lib/debug%s",
-			 symbol_conf.symfs, dso->long_name);
+		len = __symbol__join_symfs(filename, size, "/usr/lib/debug");
+		snprintf(filename + len, size - len, "%s", dso->long_name);
 		break;
 
 	case DSO_BINARY_TYPE__OPENEMBEDDED_DEBUGINFO:
 	{
 		const char *last_slash;
-		size_t len;
 		size_t dir_size;
 
 		last_slash = dso->long_name + dso->long_name_len;
 		while (last_slash != dso->long_name && *last_slash != '/')
 			last_slash--;
 
-		len = scnprintf(filename, size, "%s", symbol_conf.symfs);
+		len = __symbol__join_symfs(filename, size, "");
 		dir_size = last_slash - dso->long_name + 2;
 		if (dir_size > (size - len)) {
 			ret = -1;
@@ -100,26 +100,24 @@ int dso__read_binary_type_filename(const struct dso *dso,
 		build_id__sprintf(dso->build_id,
 				  sizeof(dso->build_id),
 				  build_id_hex);
-		snprintf(filename, size,
-			 "%s/usr/lib/debug/.build-id/%.2s/%s.debug",
-			 symbol_conf.symfs, build_id_hex, build_id_hex + 2);
+		len = __symbol__join_symfs(filename, size, "/usr/lib/debug/.build-id/");
+		snprintf(filename + len, size - len, "%.2s/%s.debug",
+			 build_id_hex, build_id_hex + 2);
 		break;
 
 	case DSO_BINARY_TYPE__VMLINUX:
 	case DSO_BINARY_TYPE__GUEST_VMLINUX:
 	case DSO_BINARY_TYPE__SYSTEM_PATH_DSO:
-		snprintf(filename, size, "%s%s",
-			 symbol_conf.symfs, dso->long_name);
+		__symbol__join_symfs(filename, size, dso->long_name);
 		break;
 
 	case DSO_BINARY_TYPE__GUEST_KMODULE:
-		snprintf(filename, size, "%s%s%s", symbol_conf.symfs,
-			 root_dir, dso->long_name);
+		path__join3(filename, size, symbol_conf.symfs,
+			    root_dir, dso->long_name);
 		break;
 
 	case DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE:
-		snprintf(filename, size, "%s%s", symbol_conf.symfs,
-			 dso->long_name);
+		__symbol__join_symfs(filename, size, dso->long_name);
 		break;
 
 	case DSO_BINARY_TYPE__KCORE:
@@ -164,13 +162,15 @@ static void close_first_dso(void);
 static int do_open(char *name)
 {
 	int fd;
+	char sbuf[STRERR_BUFSIZE];
 
 	do {
 		fd = open(name, O_RDONLY);
 		if (fd >= 0)
 			return fd;
 
-		pr_debug("dso open failed, mmap: %s\n", strerror(errno));
+		pr_debug("dso open failed, mmap: %s\n",
+			 strerror_r(errno, sbuf, sizeof(sbuf)));
 		if (!dso__data_open_cnt || errno != EMFILE)
 			break;
 
@@ -532,10 +532,12 @@ static ssize_t cached_read(struct dso *dso, u64 offset, u8 *data, ssize_t size)
 static int data_file_size(struct dso *dso)
 {
 	struct stat st;
+	char sbuf[STRERR_BUFSIZE];
 
 	if (!dso->data.file_size) {
 		if (fstat(dso->data.fd, &st)) {
-			pr_err("dso mmap failed, fstat: %s\n", strerror(errno));
+			pr_err("dso mmap failed, fstat: %s\n",
+				strerror_r(errno, sbuf, sizeof(sbuf)));
 			return -1;
 		}
 		dso->data.file_size = st.st_size;
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index 1398c83d896dff..ed558191c0b303 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -784,9 +784,9 @@ try_again:
 		 * "[vdso]" dso, but for now lets use the old trick of looking
 		 * in the whole kernel symbol list.
 		 */
-		if ((long long)al->addr < 0 &&
-		    cpumode == PERF_RECORD_MISC_USER &&
-		    machine && mg != &machine->kmaps) {
+		if (cpumode == PERF_RECORD_MISC_USER && machine &&
+		    mg != &machine->kmaps &&
+		    machine__kernel_ip(machine, al->addr)) {
 			mg = &machine->kmaps;
 			load_map = true;
 			goto try_again;
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index 94d6976180daa5..7eb7107731eca8 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -156,6 +156,8 @@ struct perf_sample {
 	u32 cpu;
 	u32 raw_size;
 	u64 data_src;
+	u32 flags;
+	u16 insn_len;
 	void *raw_data;
 	struct ip_callchain *callchain;
 	struct branch_stack *branch_stack;
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index 814e954c1318ed..a3e28b49128ab3 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -122,6 +122,7 @@ void perf_evlist__add(struct perf_evlist *evlist, struct perf_evsel *entry)
 {
 	list_add_tail(&entry->node, &evlist->entries);
 	entry->idx = evlist->nr_entries;
+	entry->tracking = !entry->idx;
 
 	if (!evlist->nr_entries++)
 		perf_evlist__set_id_pos(evlist);
@@ -265,17 +266,27 @@ int perf_evlist__add_newtp(struct perf_evlist *evlist,
 	return 0;
 }
 
+static int perf_evlist__nr_threads(struct perf_evlist *evlist,
+				   struct perf_evsel *evsel)
+{
+	if (evsel->system_wide)
+		return 1;
+	else
+		return thread_map__nr(evlist->threads);
+}
+
 void perf_evlist__disable(struct perf_evlist *evlist)
 {
 	int cpu, thread;
 	struct perf_evsel *pos;
 	int nr_cpus = cpu_map__nr(evlist->cpus);
-	int nr_threads = thread_map__nr(evlist->threads);
+	int nr_threads;
 
 	for (cpu = 0; cpu < nr_cpus; cpu++) {
 		evlist__for_each(evlist, pos) {
 			if (!perf_evsel__is_group_leader(pos) || !pos->fd)
 				continue;
+			nr_threads = perf_evlist__nr_threads(evlist, pos);
 			for (thread = 0; thread < nr_threads; thread++)
 				ioctl(FD(pos, cpu, thread),
 				      PERF_EVENT_IOC_DISABLE, 0);
@@ -288,12 +299,13 @@ void perf_evlist__enable(struct perf_evlist *evlist)
 	int cpu, thread;
 	struct perf_evsel *pos;
 	int nr_cpus = cpu_map__nr(evlist->cpus);
-	int nr_threads = thread_map__nr(evlist->threads);
+	int nr_threads;
 
 	for (cpu = 0; cpu < nr_cpus; cpu++) {
 		evlist__for_each(evlist, pos) {
 			if (!perf_evsel__is_group_leader(pos) || !pos->fd)
 				continue;
+			nr_threads = perf_evlist__nr_threads(evlist, pos);
 			for (thread = 0; thread < nr_threads; thread++)
 				ioctl(FD(pos, cpu, thread),
 				      PERF_EVENT_IOC_ENABLE, 0);
@@ -305,12 +317,14 @@ int perf_evlist__disable_event(struct perf_evlist *evlist,
 			       struct perf_evsel *evsel)
 {
 	int cpu, thread, err;
+	int nr_cpus = cpu_map__nr(evlist->cpus);
+	int nr_threads = perf_evlist__nr_threads(evlist, evsel);
 
 	if (!evsel->fd)
 		return 0;
 
-	for (cpu = 0; cpu < evlist->cpus->nr; cpu++) {
-		for (thread = 0; thread < evlist->threads->nr; thread++) {
+	for (cpu = 0; cpu < nr_cpus; cpu++) {
+		for (thread = 0; thread < nr_threads; thread++) {
 			err = ioctl(FD(evsel, cpu, thread),
 				    PERF_EVENT_IOC_DISABLE, 0);
 			if (err)
@@ -324,12 +338,14 @@ int perf_evlist__enable_event(struct perf_evlist *evlist,
 			      struct perf_evsel *evsel)
 {
 	int cpu, thread, err;
+	int nr_cpus = cpu_map__nr(evlist->cpus);
+	int nr_threads = perf_evlist__nr_threads(evlist, evsel);
 
 	if (!evsel->fd)
 		return -EINVAL;
 
-	for (cpu = 0; cpu < evlist->cpus->nr; cpu++) {
-		for (thread = 0; thread < evlist->threads->nr; thread++) {
+	for (cpu = 0; cpu < nr_cpus; cpu++) {
+		for (thread = 0; thread < nr_threads; thread++) {
 			err = ioctl(FD(evsel, cpu, thread),
 				    PERF_EVENT_IOC_ENABLE, 0);
 			if (err)
@@ -339,11 +355,67 @@ int perf_evlist__enable_event(struct perf_evlist *evlist,
 	return 0;
 }
 
+static int perf_evlist__enable_event_cpu(struct perf_evlist *evlist,
+					 struct perf_evsel *evsel, int cpu)
+{
+	int thread, err;
+	int nr_threads = perf_evlist__nr_threads(evlist, evsel);
+
+	if (!evsel->fd)
+		return -EINVAL;
+
+	for (thread = 0; thread < nr_threads; thread++) {
+		err = ioctl(FD(evsel, cpu, thread),
+			    PERF_EVENT_IOC_ENABLE, 0);
+		if (err)
+			return err;
+	}
+	return 0;
+}
+
+static int perf_evlist__enable_event_thread(struct perf_evlist *evlist,
+					    struct perf_evsel *evsel,
+					    int thread)
+{
+	int cpu, err;
+	int nr_cpus = cpu_map__nr(evlist->cpus);
+
+	if (!evsel->fd)
+		return -EINVAL;
+
+	for (cpu = 0; cpu < nr_cpus; cpu++) {
+		err = ioctl(FD(evsel, cpu, thread), PERF_EVENT_IOC_ENABLE, 0);
+		if (err)
+			return err;
+	}
+	return 0;
+}
+
+int perf_evlist__enable_event_idx(struct perf_evlist *evlist,
+				  struct perf_evsel *evsel, int idx)
+{
+	bool per_cpu_mmaps = !cpu_map__empty(evlist->cpus);
+
+	if (per_cpu_mmaps)
+		return perf_evlist__enable_event_cpu(evlist, evsel, idx);
+	else
+		return perf_evlist__enable_event_thread(evlist, evsel, idx);
+}
+
 static int perf_evlist__alloc_pollfd(struct perf_evlist *evlist)
 {
 	int nr_cpus = cpu_map__nr(evlist->cpus);
 	int nr_threads = thread_map__nr(evlist->threads);
-	int nfds = nr_cpus * nr_threads * evlist->nr_entries;
+	int nfds = 0;
+	struct perf_evsel *evsel;
+
+	list_for_each_entry(evsel, &evlist->entries, node) {
+		if (evsel->system_wide)
+			nfds += nr_cpus;
+		else
+			nfds += nr_cpus * nr_threads;
+	}
+
 	evlist->pollfd = malloc(sizeof(struct pollfd) * nfds);
 	return evlist->pollfd != NULL ? 0 : -ENOMEM;
 }
@@ -636,7 +708,12 @@ static int perf_evlist__mmap_per_evsel(struct perf_evlist *evlist, int idx,
 	struct perf_evsel *evsel;
 
 	evlist__for_each(evlist, evsel) {
-		int fd = FD(evsel, cpu, thread);
+		int fd;
+
+		if (evsel->system_wide && thread)
+			continue;
+
+		fd = FD(evsel, cpu, thread);
 
 		if (*output == -1) {
 			*output = fd;
@@ -1061,6 +1138,8 @@ int perf_evlist__prepare_workload(struct perf_evlist *evlist, struct target *tar
 	}
 
 	if (!evlist->workload.pid) {
+		int ret;
+
 		if (pipe_output)
 			dup2(2, 1);
 
@@ -1078,8 +1157,22 @@ int perf_evlist__prepare_workload(struct perf_evlist *evlist, struct target *tar
 		/*
 		 * Wait until the parent tells us to go.
 		 */
-		if (read(go_pipe[0], &bf, 1) == -1)
-			perror("unable to read pipe");
+		ret = read(go_pipe[0], &bf, 1);
+		/*
+		 * The parent will ask for the execvp() to be performed by
+		 * writing exactly one byte, in workload.cork_fd, usually via
+		 * perf_evlist__start_workload().
+		 *
+		 * For cancelling the workload without actuallin running it,
+		 * the parent will just close workload.cork_fd, without writing
+		 * anything, i.e. read will return zero and we just exit()
+		 * here.
+		 */
+		if (ret != 1) {
+			if (ret == -1)
+				perror("unable to read pipe");
+			exit(ret);
+		}
 
 		execvp(argv[0], (char **)argv);
 
@@ -1202,7 +1295,7 @@ int perf_evlist__strerror_open(struct perf_evlist *evlist __maybe_unused,
 			       int err, char *buf, size_t size)
 {
 	int printed, value;
-	char sbuf[128], *emsg = strerror_r(err, sbuf, sizeof(sbuf));
+	char sbuf[STRERR_BUFSIZE], *emsg = strerror_r(err, sbuf, sizeof(sbuf));
 
 	switch (err) {
 	case EACCES:
@@ -1250,3 +1343,19 @@ void perf_evlist__to_front(struct perf_evlist *evlist,
 
 	list_splice(&move, &evlist->entries);
 }
+
+void perf_evlist__set_tracking_event(struct perf_evlist *evlist,
+				     struct perf_evsel *tracking_evsel)
+{
+	struct perf_evsel *evsel;
+
+	if (tracking_evsel->tracking)
+		return;
+
+	evlist__for_each(evlist, evsel) {
+		if (evsel != tracking_evsel)
+			evsel->tracking = false;
+	}
+
+	tracking_evsel->tracking = true;
+}
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index f5173cd63693cc..106de53a6a74bc 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -122,6 +122,8 @@ int perf_evlist__disable_event(struct perf_evlist *evlist,
 			       struct perf_evsel *evsel);
 int perf_evlist__enable_event(struct perf_evlist *evlist,
 			      struct perf_evsel *evsel);
+int perf_evlist__enable_event_idx(struct perf_evlist *evlist,
+				  struct perf_evsel *evsel, int idx);
 
 void perf_evlist__set_selected(struct perf_evlist *evlist,
 			       struct perf_evsel *evsel);
@@ -262,4 +264,7 @@ void perf_evlist__to_front(struct perf_evlist *evlist,
 #define evlist__for_each_safe(evlist, tmp, evsel) \
 	__evlist__for_each_safe(&(evlist)->entries, tmp, evsel)
 
+void perf_evlist__set_tracking_event(struct perf_evlist *evlist,
+				     struct perf_evsel *tracking_evsel);
+
 #endif /* __PERF_EVLIST_H */
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 21a373ebea226a..b38de581932380 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -162,6 +162,7 @@ void perf_evsel__init(struct perf_evsel *evsel,
 		      struct perf_event_attr *attr, int idx)
 {
 	evsel->idx	   = idx;
+	evsel->tracking	   = !idx;
 	evsel->attr	   = *attr;
 	evsel->leader	   = evsel;
 	evsel->unit	   = "";
@@ -561,7 +562,7 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts)
 {
 	struct perf_evsel *leader = evsel->leader;
 	struct perf_event_attr *attr = &evsel->attr;
-	int track = !evsel->idx; /* only the first counter needs these */
+	int track = evsel->tracking;
 	bool per_cpu = opts->target.default_per_cpu && !opts->target.per_thread;
 
 	attr->sample_id_all = perf_missing_features.sample_id_all ? 0 : 1;
@@ -633,9 +634,12 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts)
 	if (opts->period)
 		perf_evsel__set_sample_bit(evsel, PERIOD);
 
-	if (!perf_missing_features.sample_id_all &&
-	    (opts->sample_time || !opts->no_inherit ||
-	     target__has_cpu(&opts->target) || per_cpu))
+	/*
+	 * When the user explicitely disabled time don't force it here.
+	 */
+	if (opts->sample_time &&
+	    (!perf_missing_features.sample_id_all &&
+	    (!opts->no_inherit || target__has_cpu(&opts->target) || per_cpu)))
 		perf_evsel__set_sample_bit(evsel, TIME);
 
 	if (opts->raw_samples && !evsel->no_aux_samples) {
@@ -692,6 +696,10 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts)
 int perf_evsel__alloc_fd(struct perf_evsel *evsel, int ncpus, int nthreads)
 {
 	int cpu, thread;
+
+	if (evsel->system_wide)
+		nthreads = 1;
+
 	evsel->fd = xyarray__new(ncpus, nthreads, sizeof(int));
 
 	if (evsel->fd) {
@@ -710,6 +718,9 @@ static int perf_evsel__run_ioctl(struct perf_evsel *evsel, int ncpus, int nthrea
 {
 	int cpu, thread;
 
+	if (evsel->system_wide)
+		nthreads = 1;
+
 	for (cpu = 0; cpu < ncpus; cpu++) {
 		for (thread = 0; thread < nthreads; thread++) {
 			int fd = FD(evsel, cpu, thread),
@@ -740,6 +751,9 @@ int perf_evsel__enable(struct perf_evsel *evsel, int ncpus, int nthreads)
 
 int perf_evsel__alloc_id(struct perf_evsel *evsel, int ncpus, int nthreads)
 {
+	if (evsel->system_wide)
+		nthreads = 1;
+
 	evsel->sample_id = xyarray__new(ncpus, nthreads, sizeof(struct perf_sample_id));
 	if (evsel->sample_id == NULL)
 		return -ENOMEM;
@@ -784,6 +798,9 @@ void perf_evsel__close_fd(struct perf_evsel *evsel, int ncpus, int nthreads)
 {
 	int cpu, thread;
 
+	if (evsel->system_wide)
+		nthreads = 1;
+
 	for (cpu = 0; cpu < ncpus; cpu++)
 		for (thread = 0; thread < nthreads; ++thread) {
 			close(FD(evsel, cpu, thread));
@@ -872,6 +889,9 @@ int __perf_evsel__read(struct perf_evsel *evsel,
 	int cpu, thread;
 	struct perf_counts_values *aggr = &evsel->counts->aggr, count;
 
+	if (evsel->system_wide)
+		nthreads = 1;
+
 	aggr->val = aggr->ena = aggr->run = 0;
 
 	for (cpu = 0; cpu < ncpus; cpu++) {
@@ -994,13 +1014,18 @@ static size_t perf_event_attr__fprintf(struct perf_event_attr *attr, FILE *fp)
 static int __perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus,
 			      struct thread_map *threads)
 {
-	int cpu, thread;
+	int cpu, thread, nthreads;
 	unsigned long flags = PERF_FLAG_FD_CLOEXEC;
 	int pid = -1, err;
 	enum { NO_CHANGE, SET_TO_MAX, INCREASED_MAX } set_rlimit = NO_CHANGE;
 
+	if (evsel->system_wide)
+		nthreads = 1;
+	else
+		nthreads = threads->nr;
+
 	if (evsel->fd == NULL &&
-	    perf_evsel__alloc_fd(evsel, cpus->nr, threads->nr) < 0)
+	    perf_evsel__alloc_fd(evsel, cpus->nr, nthreads) < 0)
 		return -ENOMEM;
 
 	if (evsel->cgrp) {
@@ -1024,10 +1049,10 @@ retry_sample_id:
 
 	for (cpu = 0; cpu < cpus->nr; cpu++) {
 
-		for (thread = 0; thread < threads->nr; thread++) {
+		for (thread = 0; thread < nthreads; thread++) {
 			int group_fd;
 
-			if (!evsel->cgrp)
+			if (!evsel->cgrp && !evsel->system_wide)
 				pid = threads->map[thread];
 
 			group_fd = get_group_fd(evsel, cpu, thread);
@@ -1100,7 +1125,7 @@ out_close:
 			close(FD(evsel, cpu, thread));
 			FD(evsel, cpu, thread) = -1;
 		}
-		thread = threads->nr;
+		thread = nthreads;
 	} while (--cpu >= 0);
 	return err;
 }
@@ -2002,6 +2027,8 @@ bool perf_evsel__fallback(struct perf_evsel *evsel, int err,
 int perf_evsel__open_strerror(struct perf_evsel *evsel, struct target *target,
 			      int err, char *msg, size_t size)
 {
+	char sbuf[STRERR_BUFSIZE];
+
 	switch (err) {
 	case EPERM:
 	case EACCES:
@@ -2036,13 +2063,20 @@ int perf_evsel__open_strerror(struct perf_evsel *evsel, struct target *target,
 	"No APIC? If so then you can boot the kernel with the \"lapic\" boot parameter to force-enable it.");
 #endif
 		break;
+	case EBUSY:
+		if (find_process("oprofiled"))
+			return scnprintf(msg, size,
+	"The PMU counters are busy/taken by another profiler.\n"
+	"We found oprofile daemon running, please stop it and try again.");
+		break;
 	default:
 		break;
 	}
 
 	return scnprintf(msg, size,
-	"The sys_perf_event_open() syscall returned with %d (%s) for event (%s).  \n"
+	"The sys_perf_event_open() syscall returned with %d (%s) for event (%s).\n"
 	"/bin/dmesg may provide additional information.\n"
 	"No CONFIG_PERF_EVENTS=y kernel support configured?\n",
-			 err, strerror(err), perf_evsel__name(evsel));
+			 err, strerror_r(err, sbuf, sizeof(sbuf)),
+			 perf_evsel__name(evsel));
 }
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index d7f93ce0ebc12b..7bc314be6a7bea 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -85,6 +85,8 @@ struct perf_evsel {
 	bool 			needs_swap;
 	bool			no_aux_samples;
 	bool			immediate;
+	bool			system_wide;
+	bool			tracking;
 	/* parse modifier helper */
 	int			exclude_GH;
 	int			nr_members;
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index 30df6187ee026a..86569fa3651d00 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -277,6 +277,28 @@ void hists__decay_entries(struct hists *hists, bool zap_user, bool zap_kernel)
 	}
 }
 
+void hists__delete_entries(struct hists *hists)
+{
+	struct rb_node *next = rb_first(&hists->entries);
+	struct hist_entry *n;
+
+	while (next) {
+		n = rb_entry(next, struct hist_entry, rb_node);
+		next = rb_next(&n->rb_node);
+
+		rb_erase(&n->rb_node, &hists->entries);
+
+		if (sort__need_collapse)
+			rb_erase(&n->rb_node_in, &hists->entries_collapsed);
+
+		--hists->nr_entries;
+		if (!n->filtered)
+			--hists->nr_non_filtered_entries;
+
+		hist_entry__free(n);
+	}
+}
+
 /*
  * histogram, sorted on item, collects periods
  */
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index 742f49a8572573..8c9c70e18cbbc3 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -152,6 +152,7 @@ void hists__output_resort(struct hists *hists);
 void hists__collapse_resort(struct hists *hists, struct ui_progress *prog);
 
 void hists__decay_entries(struct hists *hists, bool zap_user, bool zap_kernel);
+void hists__delete_entries(struct hists *hists);
 void hists__output_recalc_col_len(struct hists *hists, int max_rows);
 
 u64 hists__total_period(struct hists *hists);
@@ -192,6 +193,7 @@ struct perf_hpp {
 };
 
 struct perf_hpp_fmt {
+	const char *name;
 	int (*header)(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
 		      struct perf_evsel *evsel);
 	int (*width)(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
@@ -207,6 +209,8 @@ struct perf_hpp_fmt {
 	struct list_head list;
 	struct list_head sort_list;
 	bool elide;
+	int len;
+	int user_len;
 };
 
 extern struct list_head perf_hpp__list;
@@ -261,17 +265,19 @@ static inline bool perf_hpp__should_skip(struct perf_hpp_fmt *format)
 }
 
 void perf_hpp__reset_width(struct perf_hpp_fmt *fmt, struct hists *hists);
+void perf_hpp__reset_sort_width(struct perf_hpp_fmt *fmt, struct hists *hists);
+void perf_hpp__set_user_width(const char *width_list_str);
 
 typedef u64 (*hpp_field_fn)(struct hist_entry *he);
 typedef int (*hpp_callback_fn)(struct perf_hpp *hpp, bool front);
 typedef int (*hpp_snprint_fn)(struct perf_hpp *hpp, const char *fmt, ...);
 
-int __hpp__fmt(struct perf_hpp *hpp, struct hist_entry *he,
-	       hpp_field_fn get_field, const char *fmt,
-	       hpp_snprint_fn print_fn, bool fmt_percent);
-int __hpp__fmt_acc(struct perf_hpp *hpp, struct hist_entry *he,
-		   hpp_field_fn get_field, const char *fmt,
-		   hpp_snprint_fn print_fn, bool fmt_percent);
+int hpp__fmt(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
+	     struct hist_entry *he, hpp_field_fn get_field,
+	     const char *fmtstr, hpp_snprint_fn print_fn, bool fmt_percent);
+int hpp__fmt_acc(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
+		 struct hist_entry *he, hpp_field_fn get_field,
+		 const char *fmtstr, hpp_snprint_fn print_fn, bool fmt_percent);
 
 static inline void advance_hpp(struct perf_hpp *hpp, int inc)
 {
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 16bba9fff2c87b..b2ec38bf211ebc 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -31,6 +31,8 @@ int machine__init(struct machine *machine, const char *root_dir, pid_t pid)
 
 	machine->symbol_filter = NULL;
 	machine->id_hdr_size = 0;
+	machine->comm_exec = false;
+	machine->kernel_start = 0;
 
 	machine->root_dir = strdup(root_dir);
 	if (machine->root_dir == NULL)
@@ -179,6 +181,19 @@ void machines__set_symbol_filter(struct machines *machines,
 	}
 }
 
+void machines__set_comm_exec(struct machines *machines, bool comm_exec)
+{
+	struct rb_node *nd;
+
+	machines->host.comm_exec = comm_exec;
+
+	for (nd = rb_first(&machines->guests); nd; nd = rb_next(nd)) {
+		struct machine *machine = rb_entry(nd, struct machine, rb_node);
+
+		machine->comm_exec = comm_exec;
+	}
+}
+
 struct machine *machines__find(struct machines *machines, pid_t pid)
 {
 	struct rb_node **p = &machines->guests.rb_node;
@@ -398,17 +413,31 @@ struct thread *machine__find_thread(struct machine *machine, pid_t pid,
 	return __machine__findnew_thread(machine, pid, tid, false);
 }
 
+struct comm *machine__thread_exec_comm(struct machine *machine,
+				       struct thread *thread)
+{
+	if (machine->comm_exec)
+		return thread__exec_comm(thread);
+	else
+		return thread__comm(thread);
+}
+
 int machine__process_comm_event(struct machine *machine, union perf_event *event,
 				struct perf_sample *sample)
 {
 	struct thread *thread = machine__findnew_thread(machine,
 							event->comm.pid,
 							event->comm.tid);
+	bool exec = event->header.misc & PERF_RECORD_MISC_COMM_EXEC;
+
+	if (exec)
+		machine->comm_exec = true;
 
 	if (dump_trace)
 		perf_event__fprintf_comm(event, stdout);
 
-	if (thread == NULL || thread__set_comm(thread, event->comm.comm, sample->time)) {
+	if (thread == NULL ||
+	    __thread__set_comm(thread, event->comm.comm, sample->time, exec)) {
 		dump_printf("problem processing PERF_RECORD_COMM, skipping event.\n");
 		return -1;
 	}
@@ -565,8 +594,8 @@ const char *ref_reloc_sym_names[] = {"_text", "_stext", NULL};
  * Returns the name of the start symbol in *symbol_name. Pass in NULL as
  * symbol_name if it's not that important.
  */
-static u64 machine__get_kernel_start_addr(struct machine *machine,
-					  const char **symbol_name)
+static u64 machine__get_running_kernel_start(struct machine *machine,
+					     const char **symbol_name)
 {
 	char filename[PATH_MAX];
 	int i;
@@ -593,7 +622,7 @@ static u64 machine__get_kernel_start_addr(struct machine *machine,
 int __machine__create_kernel_maps(struct machine *machine, struct dso *kernel)
 {
 	enum map_type type;
-	u64 start = machine__get_kernel_start_addr(machine, NULL);
+	u64 start = machine__get_running_kernel_start(machine, NULL);
 
 	for (type = 0; type < MAP__NR_TYPES; ++type) {
 		struct kmap *kmap;
@@ -912,7 +941,7 @@ int machine__create_kernel_maps(struct machine *machine)
 {
 	struct dso *kernel = machine__get_kernel(machine);
 	const char *name;
-	u64 addr = machine__get_kernel_start_addr(machine, &name);
+	u64 addr = machine__get_running_kernel_start(machine, &name);
 	if (!addr)
 		return -1;
 
@@ -1285,6 +1314,16 @@ static void ip__resolve_data(struct machine *machine, struct thread *thread,
 
 	thread__find_addr_location(thread, machine, m, MAP__VARIABLE, addr,
 				   &al);
+	if (al.map == NULL) {
+		/*
+		 * some shared data regions have execute bit set which puts
+		 * their mapping in the MAP__FUNCTION type array.
+		 * Check there as a fallback option before dropping the sample.
+		 */
+		thread__find_addr_location(thread, machine, m, MAP__FUNCTION, addr,
+					   &al);
+	}
+
 	ams->addr = addr;
 	ams->al_addr = al.addr;
 	ams->sym = al.sym;
@@ -1531,3 +1570,25 @@ int machine__set_current_tid(struct machine *machine, int cpu, pid_t pid,
 
 	return 0;
 }
+
+int machine__get_kernel_start(struct machine *machine)
+{
+	struct map *map = machine__kernel_map(machine, MAP__FUNCTION);
+	int err = 0;
+
+	/*
+	 * The only addresses above 2^63 are kernel addresses of a 64-bit
+	 * kernel.  Note that addresses are unsigned so that on a 32-bit system
+	 * all addresses including kernel addresses are less than 2^32.  In
+	 * that case (32-bit system), if the kernel mapping is unknown, all
+	 * addresses will be assumed to be in user space - see
+	 * machine__kernel_ip().
+	 */
+	machine->kernel_start = 1ULL << 63;
+	if (map) {
+		err = map__load(map, machine->symbol_filter);
+		if (map->start)
+			machine->kernel_start = map->start;
+	}
+	return err;
+}
diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h
index b972824e62941f..6a6bcc1cff5444 100644
--- a/tools/perf/util/machine.h
+++ b/tools/perf/util/machine.h
@@ -26,6 +26,7 @@ struct machine {
 	struct rb_node	  rb_node;
 	pid_t		  pid;
 	u16		  id_hdr_size;
+	bool		  comm_exec;
 	char		  *root_dir;
 	struct rb_root	  threads;
 	struct list_head  dead_threads;
@@ -35,6 +36,7 @@ struct machine {
 	struct list_head  kernel_dsos;
 	struct map_groups kmaps;
 	struct map	  *vmlinux_maps[MAP__NR_TYPES];
+	u64		  kernel_start;
 	symbol_filter_t	  symbol_filter;
 	pid_t		  *current_tid;
 };
@@ -45,8 +47,26 @@ struct map *machine__kernel_map(struct machine *machine, enum map_type type)
 	return machine->vmlinux_maps[type];
 }
 
+int machine__get_kernel_start(struct machine *machine);
+
+static inline u64 machine__kernel_start(struct machine *machine)
+{
+	if (!machine->kernel_start)
+		machine__get_kernel_start(machine);
+	return machine->kernel_start;
+}
+
+static inline bool machine__kernel_ip(struct machine *machine, u64 ip)
+{
+	u64 kernel_start = machine__kernel_start(machine);
+
+	return ip >= kernel_start;
+}
+
 struct thread *machine__find_thread(struct machine *machine, pid_t pid,
 				    pid_t tid);
+struct comm *machine__thread_exec_comm(struct machine *machine,
+				       struct thread *thread);
 
 int machine__process_comm_event(struct machine *machine, union perf_event *event,
 				struct perf_sample *sample);
@@ -88,6 +108,7 @@ char *machine__mmap_name(struct machine *machine, char *bf, size_t size);
 
 void machines__set_symbol_filter(struct machines *machines,
 				 symbol_filter_t symbol_filter);
+void machines__set_comm_exec(struct machines *machines, bool comm_exec);
 
 struct machine *machine__new_host(void);
 int machine__init(struct machine *machine, const char *root_dir, pid_t pid);
diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c
index 31b8905dd863db..b7090596ac5086 100644
--- a/tools/perf/util/map.c
+++ b/tools/perf/util/map.c
@@ -31,6 +31,7 @@ static inline int is_anon_memory(const char *filename)
 static inline int is_no_dso_memory(const char *filename)
 {
 	return !strncmp(filename, "[stack", 6) ||
+	       !strncmp(filename, "/SYSV",5)   ||
 	       !strcmp(filename, "[heap]");
 }
 
diff --git a/tools/perf/util/ordered-events.c b/tools/perf/util/ordered-events.c
new file mode 100644
index 00000000000000..706ce1a6616926
--- /dev/null
+++ b/tools/perf/util/ordered-events.c
@@ -0,0 +1,245 @@
+#include <linux/list.h>
+#include <linux/compiler.h>
+#include "ordered-events.h"
+#include "evlist.h"
+#include "session.h"
+#include "asm/bug.h"
+#include "debug.h"
+
+#define pr_N(n, fmt, ...) \
+	eprintf(n, debug_ordered_events, fmt, ##__VA_ARGS__)
+
+#define pr(fmt, ...) pr_N(1, pr_fmt(fmt), ##__VA_ARGS__)
+
+static void queue_event(struct ordered_events *oe, struct ordered_event *new)
+{
+	struct ordered_event *last = oe->last;
+	u64 timestamp = new->timestamp;
+	struct list_head *p;
+
+	++oe->nr_events;
+	oe->last = new;
+
+	pr_oe_time2(timestamp, "queue_event nr_events %u\n", oe->nr_events);
+
+	if (!last) {
+		list_add(&new->list, &oe->events);
+		oe->max_timestamp = timestamp;
+		return;
+	}
+
+	/*
+	 * last event might point to some random place in the list as it's
+	 * the last queued event. We expect that the new event is close to
+	 * this.
+	 */
+	if (last->timestamp <= timestamp) {
+		while (last->timestamp <= timestamp) {
+			p = last->list.next;
+			if (p == &oe->events) {
+				list_add_tail(&new->list, &oe->events);
+				oe->max_timestamp = timestamp;
+				return;
+			}
+			last = list_entry(p, struct ordered_event, list);
+		}
+		list_add_tail(&new->list, &last->list);
+	} else {
+		while (last->timestamp > timestamp) {
+			p = last->list.prev;
+			if (p == &oe->events) {
+				list_add(&new->list, &oe->events);
+				return;
+			}
+			last = list_entry(p, struct ordered_event, list);
+		}
+		list_add(&new->list, &last->list);
+	}
+}
+
+#define MAX_SAMPLE_BUFFER	(64 * 1024 / sizeof(struct ordered_event))
+static struct ordered_event *alloc_event(struct ordered_events *oe)
+{
+	struct list_head *cache = &oe->cache;
+	struct ordered_event *new = NULL;
+
+	if (!list_empty(cache)) {
+		new = list_entry(cache->next, struct ordered_event, list);
+		list_del(&new->list);
+	} else if (oe->buffer) {
+		new = oe->buffer + oe->buffer_idx;
+		if (++oe->buffer_idx == MAX_SAMPLE_BUFFER)
+			oe->buffer = NULL;
+	} else if (oe->cur_alloc_size < oe->max_alloc_size) {
+		size_t size = MAX_SAMPLE_BUFFER * sizeof(*new);
+
+		oe->buffer = malloc(size);
+		if (!oe->buffer)
+			return NULL;
+
+		pr("alloc size %" PRIu64 "B (+%zu), max %" PRIu64 "B\n",
+		   oe->cur_alloc_size, size, oe->max_alloc_size);
+
+		oe->cur_alloc_size += size;
+		list_add(&oe->buffer->list, &oe->to_free);
+
+		/* First entry is abused to maintain the to_free list. */
+		oe->buffer_idx = 2;
+		new = oe->buffer + 1;
+	} else {
+		pr("allocation limit reached %" PRIu64 "B\n", oe->max_alloc_size);
+	}
+
+	return new;
+}
+
+struct ordered_event *
+ordered_events__new(struct ordered_events *oe, u64 timestamp)
+{
+	struct ordered_event *new;
+
+	new = alloc_event(oe);
+	if (new) {
+		new->timestamp = timestamp;
+		queue_event(oe, new);
+	}
+
+	return new;
+}
+
+void ordered_events__delete(struct ordered_events *oe, struct ordered_event *event)
+{
+	list_move(&event->list, &oe->cache);
+	oe->nr_events--;
+}
+
+static int __ordered_events__flush(struct perf_session *s,
+				   struct perf_tool *tool)
+{
+	struct ordered_events *oe = &s->ordered_events;
+	struct list_head *head = &oe->events;
+	struct ordered_event *tmp, *iter;
+	struct perf_sample sample;
+	u64 limit = oe->next_flush;
+	u64 last_ts = oe->last ? oe->last->timestamp : 0ULL;
+	bool show_progress = limit == ULLONG_MAX;
+	struct ui_progress prog;
+	int ret;
+
+	if (!tool->ordered_events || !limit)
+		return 0;
+
+	if (show_progress)
+		ui_progress__init(&prog, oe->nr_events, "Processing time ordered events...");
+
+	list_for_each_entry_safe(iter, tmp, head, list) {
+		if (session_done())
+			return 0;
+
+		if (iter->timestamp > limit)
+			break;
+
+		ret = perf_evlist__parse_sample(s->evlist, iter->event, &sample);
+		if (ret)
+			pr_err("Can't parse sample, err = %d\n", ret);
+		else {
+			ret = perf_session__deliver_event(s, iter->event, &sample, tool,
+							  iter->file_offset);
+			if (ret)
+				return ret;
+		}
+
+		ordered_events__delete(oe, iter);
+		oe->last_flush = iter->timestamp;
+
+		if (show_progress)
+			ui_progress__update(&prog, 1);
+	}
+
+	if (list_empty(head))
+		oe->last = NULL;
+	else if (last_ts <= limit)
+		oe->last = list_entry(head->prev, struct ordered_event, list);
+
+	return 0;
+}
+
+int ordered_events__flush(struct perf_session *s, struct perf_tool *tool,
+			  enum oe_flush how)
+{
+	struct ordered_events *oe = &s->ordered_events;
+	static const char * const str[] = {
+		"NONE",
+		"FINAL",
+		"ROUND",
+		"HALF ",
+	};
+	int err;
+
+	switch (how) {
+	case OE_FLUSH__FINAL:
+		oe->next_flush = ULLONG_MAX;
+		break;
+
+	case OE_FLUSH__HALF:
+	{
+		struct ordered_event *first, *last;
+		struct list_head *head = &oe->events;
+
+		first = list_entry(head->next, struct ordered_event, list);
+		last = oe->last;
+
+		/* Warn if we are called before any event got allocated. */
+		if (WARN_ONCE(!last || list_empty(head), "empty queue"))
+			return 0;
+
+		oe->next_flush  = first->timestamp;
+		oe->next_flush += (last->timestamp - first->timestamp) / 2;
+		break;
+	}
+
+	case OE_FLUSH__ROUND:
+	case OE_FLUSH__NONE:
+	default:
+		break;
+	};
+
+	pr_oe_time(oe->next_flush, "next_flush - ordered_events__flush PRE  %s, nr_events %u\n",
+		   str[how], oe->nr_events);
+	pr_oe_time(oe->max_timestamp, "max_timestamp\n");
+
+	err = __ordered_events__flush(s, tool);
+
+	if (!err) {
+		if (how == OE_FLUSH__ROUND)
+			oe->next_flush = oe->max_timestamp;
+
+		oe->last_flush_type = how;
+	}
+
+	pr_oe_time(oe->next_flush, "next_flush - ordered_events__flush POST %s, nr_events %u\n",
+		   str[how], oe->nr_events);
+	pr_oe_time(oe->last_flush, "last_flush\n");
+
+	return err;
+}
+
+void ordered_events__init(struct ordered_events *oe)
+{
+	INIT_LIST_HEAD(&oe->events);
+	INIT_LIST_HEAD(&oe->cache);
+	INIT_LIST_HEAD(&oe->to_free);
+	oe->max_alloc_size = (u64) -1;
+	oe->cur_alloc_size = 0;
+}
+
+void ordered_events__free(struct ordered_events *oe)
+{
+	while (!list_empty(&oe->to_free)) {
+		struct ordered_event *event;
+
+		event = list_entry(oe->to_free.next, struct ordered_event, list);
+		list_del(&event->list);
+		free(event);
+	}
+}
diff --git a/tools/perf/util/ordered-events.h b/tools/perf/util/ordered-events.h
new file mode 100644
index 00000000000000..3b2f20542a01c9
--- /dev/null
+++ b/tools/perf/util/ordered-events.h
@@ -0,0 +1,51 @@
+#ifndef __ORDERED_EVENTS_H
+#define __ORDERED_EVENTS_H
+
+#include <linux/types.h>
+#include "tool.h"
+
+struct perf_session;
+
+struct ordered_event {
+	u64			timestamp;
+	u64			file_offset;
+	union perf_event	*event;
+	struct list_head	list;
+};
+
+enum oe_flush {
+	OE_FLUSH__NONE,
+	OE_FLUSH__FINAL,
+	OE_FLUSH__ROUND,
+	OE_FLUSH__HALF,
+};
+
+struct ordered_events {
+	u64			last_flush;
+	u64			next_flush;
+	u64			max_timestamp;
+	u64			max_alloc_size;
+	u64			cur_alloc_size;
+	struct list_head	events;
+	struct list_head	cache;
+	struct list_head	to_free;
+	struct ordered_event	*buffer;
+	struct ordered_event	*last;
+	int			buffer_idx;
+	unsigned int		nr_events;
+	enum oe_flush		last_flush_type;
+};
+
+struct ordered_event *ordered_events__new(struct ordered_events *oe, u64 timestamp);
+void ordered_events__delete(struct ordered_events *oe, struct ordered_event *event);
+int ordered_events__flush(struct perf_session *s, struct perf_tool *tool,
+			  enum oe_flush how);
+void ordered_events__init(struct ordered_events *oe);
+void ordered_events__free(struct ordered_events *oe);
+
+static inline
+void ordered_events__set_alloc_size(struct ordered_events *oe, u64 size)
+{
+	oe->max_alloc_size = size;
+}
+#endif /* __ORDERED_EVENTS_H */
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 1e15df10a88c2c..e34c81a0bcf353 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -10,6 +10,7 @@
 #include "symbol.h"
 #include "cache.h"
 #include "header.h"
+#include "debug.h"
 #include <api/fs/debugfs.h>
 #include "parse-events-bison.h"
 #define YY_EXTRA_TYPE int
@@ -1006,9 +1007,11 @@ void print_tracepoint_events(const char *subsys_glob, const char *event_glob,
 	struct dirent *sys_next, *evt_next, sys_dirent, evt_dirent;
 	char evt_path[MAXPATHLEN];
 	char dir_path[MAXPATHLEN];
+	char sbuf[STRERR_BUFSIZE];
 
 	if (debugfs_valid_mountpoint(tracing_events_path)) {
-		printf("  [ Tracepoints not available: %s ]\n", strerror(errno));
+		printf("  [ Tracepoints not available: %s ]\n",
+			strerror_r(errno, sbuf, sizeof(sbuf)));
 		return;
 	}
 
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index 7a811eb61f75fc..9bf5827505616c 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -14,8 +14,8 @@
 
 struct perf_pmu_alias {
 	char *name;
-	struct list_head terms;
-	struct list_head list;
+	struct list_head terms; /* HEAD struct parse_events_term -> list */
+	struct list_head list;  /* ELEM */
 	char unit[UNIT_MAX_LEN+1];
 	double scale;
 };
diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h
index c14a543ce1f3b5..1c1e2eecbe1fb5 100644
--- a/tools/perf/util/pmu.h
+++ b/tools/perf/util/pmu.h
@@ -17,9 +17,9 @@ struct perf_pmu {
 	char *name;
 	__u32 type;
 	struct cpu_map *cpus;
-	struct list_head format;
-	struct list_head aliases;
-	struct list_head list;
+	struct list_head format;  /* HEAD struct perf_pmu_format -> list */
+	struct list_head aliases; /* HEAD struct perf_pmu_alias -> list */
+	struct list_head list;    /* ELEM */
 };
 
 struct perf_pmu *perf_pmu__find(const char *name);
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index 9a0a1839a37726..f73595fc06276a 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -79,7 +79,7 @@ static int init_symbol_maps(bool user_only)
 	int ret;
 
 	symbol_conf.sort_by_name = true;
-	ret = symbol__init();
+	ret = symbol__init(NULL);
 	if (ret < 0) {
 		pr_debug("Failed to init symbol map.\n");
 		goto out;
@@ -258,21 +258,33 @@ static void clear_probe_trace_events(struct probe_trace_event *tevs, int ntevs)
 #ifdef HAVE_DWARF_SUPPORT
 
 /* Open new debuginfo of given module */
-static struct debuginfo *open_debuginfo(const char *module)
+static struct debuginfo *open_debuginfo(const char *module, bool silent)
 {
 	const char *path = module;
+	struct debuginfo *ret;
 
 	if (!module || !strchr(module, '/')) {
 		path = kernel_get_module_path(module);
 		if (!path) {
-			pr_err("Failed to find path of %s module.\n",
-			       module ?: "kernel");
+			if (!silent)
+				pr_err("Failed to find path of %s module.\n",
+				       module ?: "kernel");
 			return NULL;
 		}
 	}
-	return debuginfo__new(path);
+	ret = debuginfo__new(path);
+	if (!ret && !silent) {
+		pr_warning("The %s file has no debug information.\n", path);
+		if (!module || !strtailcmp(path, ".ko"))
+			pr_warning("Rebuild with CONFIG_DEBUG_INFO=y, ");
+		else
+			pr_warning("Rebuild with -g, ");
+		pr_warning("or install an appropriate debuginfo package.\n");
+	}
+	return ret;
 }
 
+
 static int get_text_start_address(const char *exec, unsigned long *address)
 {
 	Elf *elf;
@@ -333,15 +345,13 @@ static int find_perf_probe_point_from_dwarf(struct probe_trace_point *tp,
 	pr_debug("try to find information at %" PRIx64 " in %s\n", addr,
 		 tp->module ? : "kernel");
 
-	dinfo = open_debuginfo(tp->module);
+	dinfo = open_debuginfo(tp->module, verbose == 0);
 	if (dinfo) {
 		ret = debuginfo__find_probe_point(dinfo,
 						 (unsigned long)addr, pp);
 		debuginfo__delete(dinfo);
-	} else {
-		pr_debug("Failed to open debuginfo at 0x%" PRIx64 "\n", addr);
+	} else
 		ret = -ENOENT;
-	}
 
 	if (ret > 0) {
 		pp->retprobe = tp->retprobe;
@@ -457,13 +467,11 @@ static int try_to_find_probe_trace_events(struct perf_probe_event *pev,
 	struct debuginfo *dinfo;
 	int ntevs, ret = 0;
 
-	dinfo = open_debuginfo(target);
+	dinfo = open_debuginfo(target, !need_dwarf);
 
 	if (!dinfo) {
-		if (need_dwarf) {
-			pr_warning("Failed to open debuginfo file.\n");
+		if (need_dwarf)
 			return -ENOENT;
-		}
 		pr_debug("Could not open debuginfo. Try to use symbols.\n");
 		return 0;
 	}
@@ -565,7 +573,7 @@ static int get_real_path(const char *raw_path, const char *comp_dir,
 
 static int __show_one_line(FILE *fp, int l, bool skip, bool show_num)
 {
-	char buf[LINEBUF_SIZE];
+	char buf[LINEBUF_SIZE], sbuf[STRERR_BUFSIZE];
 	const char *color = show_num ? "" : PERF_COLOR_BLUE;
 	const char *prefix = NULL;
 
@@ -585,7 +593,8 @@ static int __show_one_line(FILE *fp, int l, bool skip, bool show_num)
 	return 1;
 error:
 	if (ferror(fp)) {
-		pr_warning("File read error: %s\n", strerror(errno));
+		pr_warning("File read error: %s\n",
+			   strerror_r(errno, sbuf, sizeof(sbuf)));
 		return -1;
 	}
 	return 0;
@@ -618,13 +627,12 @@ static int __show_line_range(struct line_range *lr, const char *module)
 	FILE *fp;
 	int ret;
 	char *tmp;
+	char sbuf[STRERR_BUFSIZE];
 
 	/* Search a line range */
-	dinfo = open_debuginfo(module);
-	if (!dinfo) {
-		pr_warning("Failed to open debuginfo file.\n");
+	dinfo = open_debuginfo(module, false);
+	if (!dinfo)
 		return -ENOENT;
-	}
 
 	ret = debuginfo__find_line_range(dinfo, lr);
 	debuginfo__delete(dinfo);
@@ -656,7 +664,7 @@ static int __show_line_range(struct line_range *lr, const char *module)
 	fp = fopen(lr->path, "r");
 	if (fp == NULL) {
 		pr_warning("Failed to open %s: %s\n", lr->path,
-			   strerror(errno));
+			   strerror_r(errno, sbuf, sizeof(sbuf)));
 		return -errno;
 	}
 	/* Skip to starting line number */
@@ -772,9 +780,8 @@ int show_available_vars(struct perf_probe_event *pevs, int npevs,
 	if (ret < 0)
 		return ret;
 
-	dinfo = open_debuginfo(module);
+	dinfo = open_debuginfo(module, false);
 	if (!dinfo) {
-		pr_warning("Failed to open debuginfo file.\n");
 		ret = -ENOENT;
 		goto out;
 	}
@@ -1405,8 +1412,7 @@ int synthesize_perf_probe_arg(struct perf_probe_arg *pa, char *buf, size_t len)
 
 	return tmp - buf;
 error:
-	pr_debug("Failed to synthesize perf probe argument: %s\n",
-		 strerror(-ret));
+	pr_debug("Failed to synthesize perf probe argument: %d\n", ret);
 	return ret;
 }
 
@@ -1455,8 +1461,7 @@ static char *synthesize_perf_probe_point(struct perf_probe_point *pp)
 
 	return buf;
 error:
-	pr_debug("Failed to synthesize perf probe point: %s\n",
-		 strerror(-ret));
+	pr_debug("Failed to synthesize perf probe point: %d\n", ret);
 	free(buf);
 	return NULL;
 }
@@ -1780,10 +1785,11 @@ static void clear_probe_trace_event(struct probe_trace_event *tev)
 	memset(tev, 0, sizeof(*tev));
 }
 
-static void print_warn_msg(const char *file, bool is_kprobe)
+static void print_open_warning(int err, bool is_kprobe)
 {
+	char sbuf[STRERR_BUFSIZE];
 
-	if (errno == ENOENT) {
+	if (err == -ENOENT) {
 		const char *config;
 
 		if (!is_kprobe)
@@ -1791,25 +1797,43 @@ static void print_warn_msg(const char *file, bool is_kprobe)
 		else
 			config = "CONFIG_KPROBE_EVENTS";
 
-		pr_warning("%s file does not exist - please rebuild kernel"
-				" with %s.\n", file, config);
-	} else
-		pr_warning("Failed to open %s file: %s\n", file,
-				strerror(errno));
+		pr_warning("%cprobe_events file does not exist"
+			   " - please rebuild kernel with %s.\n",
+			   is_kprobe ? 'k' : 'u', config);
+	} else if (err == -ENOTSUP)
+		pr_warning("Debugfs is not mounted.\n");
+	else
+		pr_warning("Failed to open %cprobe_events: %s\n",
+			   is_kprobe ? 'k' : 'u',
+			   strerror_r(-err, sbuf, sizeof(sbuf)));
 }
 
-static int open_probe_events(const char *trace_file, bool readwrite,
-				bool is_kprobe)
+static void print_both_open_warning(int kerr, int uerr)
+{
+	/* Both kprobes and uprobes are disabled, warn it. */
+	if (kerr == -ENOTSUP && uerr == -ENOTSUP)
+		pr_warning("Debugfs is not mounted.\n");
+	else if (kerr == -ENOENT && uerr == -ENOENT)
+		pr_warning("Please rebuild kernel with CONFIG_KPROBE_EVENTS "
+			   "or/and CONFIG_UPROBE_EVENTS.\n");
+	else {
+		char sbuf[STRERR_BUFSIZE];
+		pr_warning("Failed to open kprobe events: %s.\n",
+			   strerror_r(-kerr, sbuf, sizeof(sbuf)));
+		pr_warning("Failed to open uprobe events: %s.\n",
+			   strerror_r(-uerr, sbuf, sizeof(sbuf)));
+	}
+}
+
+static int open_probe_events(const char *trace_file, bool readwrite)
 {
 	char buf[PATH_MAX];
 	const char *__debugfs;
 	int ret;
 
 	__debugfs = debugfs_find_mountpoint();
-	if (__debugfs == NULL) {
-		pr_warning("Debugfs is not mounted.\n");
-		return -ENOENT;
-	}
+	if (__debugfs == NULL)
+		return -ENOTSUP;
 
 	ret = e_snprintf(buf, PATH_MAX, "%s/%s", __debugfs, trace_file);
 	if (ret >= 0) {
@@ -1820,19 +1844,19 @@ static int open_probe_events(const char *trace_file, bool readwrite,
 			ret = open(buf, O_RDONLY, 0);
 
 		if (ret < 0)
-			print_warn_msg(buf, is_kprobe);
+			ret = -errno;
 	}
 	return ret;
 }
 
 static int open_kprobe_events(bool readwrite)
 {
-	return open_probe_events("tracing/kprobe_events", readwrite, true);
+	return open_probe_events("tracing/kprobe_events", readwrite);
 }
 
 static int open_uprobe_events(bool readwrite)
 {
-	return open_probe_events("tracing/uprobe_events", readwrite, false);
+	return open_probe_events("tracing/uprobe_events", readwrite);
 }
 
 /* Get raw string list of current kprobe_events  or uprobe_events */
@@ -1857,7 +1881,7 @@ static struct strlist *get_probe_trace_command_rawlist(int fd)
 			p[idx] = '\0';
 		ret = strlist__add(sl, buf);
 		if (ret < 0) {
-			pr_debug("strlist__add failed: %s\n", strerror(-ret));
+			pr_debug("strlist__add failed (%d)\n", ret);
 			strlist__delete(sl);
 			return NULL;
 		}
@@ -1916,7 +1940,7 @@ static int __show_perf_probe_events(int fd, bool is_kprobe)
 
 	rawlist = get_probe_trace_command_rawlist(fd);
 	if (!rawlist)
-		return -ENOENT;
+		return -ENOMEM;
 
 	strlist__for_each(ent, rawlist) {
 		ret = parse_probe_trace_command(ent->s, &tev);
@@ -1940,27 +1964,34 @@ static int __show_perf_probe_events(int fd, bool is_kprobe)
 /* List up current perf-probe events */
 int show_perf_probe_events(void)
 {
-	int fd, ret;
+	int kp_fd, up_fd, ret;
 
 	setup_pager();
-	fd = open_kprobe_events(false);
-
-	if (fd < 0)
-		return fd;
 
 	ret = init_symbol_maps(false);
 	if (ret < 0)
 		return ret;
 
-	ret = __show_perf_probe_events(fd, true);
-	close(fd);
+	kp_fd = open_kprobe_events(false);
+	if (kp_fd >= 0) {
+		ret = __show_perf_probe_events(kp_fd, true);
+		close(kp_fd);
+		if (ret < 0)
+			goto out;
+	}
 
-	fd = open_uprobe_events(false);
-	if (fd >= 0) {
-		ret = __show_perf_probe_events(fd, false);
-		close(fd);
+	up_fd = open_uprobe_events(false);
+	if (kp_fd < 0 && up_fd < 0) {
+		print_both_open_warning(kp_fd, up_fd);
+		ret = kp_fd;
+		goto out;
 	}
 
+	if (up_fd >= 0) {
+		ret = __show_perf_probe_events(up_fd, false);
+		close(up_fd);
+	}
+out:
 	exit_symbol_maps();
 	return ret;
 }
@@ -1976,6 +2007,8 @@ static struct strlist *get_probe_trace_event_names(int fd, bool include_group)
 
 	memset(&tev, 0, sizeof(tev));
 	rawlist = get_probe_trace_command_rawlist(fd);
+	if (!rawlist)
+		return NULL;
 	sl = strlist__new(true, NULL);
 	strlist__for_each(ent, rawlist) {
 		ret = parse_probe_trace_command(ent->s, &tev);
@@ -2005,6 +2038,7 @@ static int write_probe_trace_event(int fd, struct probe_trace_event *tev)
 {
 	int ret = 0;
 	char *buf = synthesize_probe_trace_command(tev);
+	char sbuf[STRERR_BUFSIZE];
 
 	if (!buf) {
 		pr_debug("Failed to synthesize probe trace event.\n");
@@ -2016,7 +2050,7 @@ static int write_probe_trace_event(int fd, struct probe_trace_event *tev)
 		ret = write(fd, buf, strlen(buf));
 		if (ret <= 0)
 			pr_warning("Failed to write event: %s\n",
-				   strerror(errno));
+				   strerror_r(errno, sbuf, sizeof(sbuf)));
 	}
 	free(buf);
 	return ret;
@@ -2030,7 +2064,7 @@ static int get_new_event_name(char *buf, size_t len, const char *base,
 	/* Try no suffix */
 	ret = e_snprintf(buf, len, "%s", base);
 	if (ret < 0) {
-		pr_debug("snprintf() failed: %s\n", strerror(-ret));
+		pr_debug("snprintf() failed: %d\n", ret);
 		return ret;
 	}
 	if (!strlist__has_entry(namelist, buf))
@@ -2046,7 +2080,7 @@ static int get_new_event_name(char *buf, size_t len, const char *base,
 	for (i = 1; i < MAX_EVENT_INDEX; i++) {
 		ret = e_snprintf(buf, len, "%s_%d", base, i);
 		if (ret < 0) {
-			pr_debug("snprintf() failed: %s\n", strerror(-ret));
+			pr_debug("snprintf() failed: %d\n", ret);
 			return ret;
 		}
 		if (!strlist__has_entry(namelist, buf))
@@ -2075,8 +2109,11 @@ static int __add_probe_trace_events(struct perf_probe_event *pev,
 	else
 		fd = open_kprobe_events(true);
 
-	if (fd < 0)
+	if (fd < 0) {
+		print_open_warning(fd, !pev->uprobes);
 		return fd;
+	}
+
 	/* Get current event names */
 	namelist = get_probe_trace_event_names(fd, false);
 	if (!namelist) {
@@ -2408,7 +2445,8 @@ static int __del_trace_probe_event(int fd, struct str_node *ent)
 	printf("Removed event: %s\n", ent->s);
 	return 0;
 error:
-	pr_warning("Failed to delete event: %s\n", strerror(-ret));
+	pr_warning("Failed to delete event: %s\n",
+		   strerror_r(-ret, buf, sizeof(buf)));
 	return ret;
 }
 
@@ -2449,15 +2487,18 @@ int del_perf_probe_events(struct strlist *dellist)
 
 	/* Get current event names */
 	kfd = open_kprobe_events(true);
-	if (kfd < 0)
-		return kfd;
+	if (kfd >= 0)
+		namelist = get_probe_trace_event_names(kfd, true);
 
-	namelist = get_probe_trace_event_names(kfd, true);
 	ufd = open_uprobe_events(true);
-
 	if (ufd >= 0)
 		unamelist = get_probe_trace_event_names(ufd, true);
 
+	if (kfd < 0 && ufd < 0) {
+		print_both_open_warning(kfd, ufd);
+		goto error;
+	}
+
 	if (namelist == NULL && unamelist == NULL)
 		goto error;
 
diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c
index dca9145d704c94..9c593561aa71d4 100644
--- a/tools/perf/util/probe-finder.c
+++ b/tools/perf/util/probe-finder.c
@@ -281,6 +281,7 @@ static int convert_variable_type(Dwarf_Die *vr_die,
 	struct probe_trace_arg_ref **ref_ptr = &tvar->ref;
 	Dwarf_Die type;
 	char buf[16];
+	char sbuf[STRERR_BUFSIZE];
 	int bsize, boffs, total;
 	int ret;
 
@@ -367,7 +368,7 @@ formatted:
 		if (ret >= 16)
 			ret = -E2BIG;
 		pr_warning("Failed to convert variable type: %s\n",
-			   strerror(-ret));
+			   strerror_r(-ret, sbuf, sizeof(sbuf)));
 		return ret;
 	}
 	tvar->type = strdup(buf);
@@ -779,10 +780,12 @@ static int find_lazy_match_lines(struct intlist *list,
 	size_t line_len;
 	ssize_t len;
 	int count = 0, linenum = 1;
+	char sbuf[STRERR_BUFSIZE];
 
 	fp = fopen(fname, "r");
 	if (!fp) {
-		pr_warning("Failed to open %s: %s\n", fname, strerror(errno));
+		pr_warning("Failed to open %s: %s\n", fname,
+			   strerror_r(errno, sbuf, sizeof(sbuf)));
 		return -errno;
 	}
 
diff --git a/tools/perf/util/record.c b/tools/perf/util/record.c
index fe8079edbdc11a..cf69325b985f15 100644
--- a/tools/perf/util/record.c
+++ b/tools/perf/util/record.c
@@ -14,6 +14,7 @@ static int perf_do_probe_api(setup_probe_fn_t fn, int cpu, const char *str)
 	struct perf_evsel *evsel;
 	unsigned long flags = perf_event_open_cloexec_flag();
 	int err = -EAGAIN, fd;
+	static pid_t pid = -1;
 
 	evlist = perf_evlist__new();
 	if (!evlist)
@@ -24,14 +25,22 @@ static int perf_do_probe_api(setup_probe_fn_t fn, int cpu, const char *str)
 
 	evsel = perf_evlist__first(evlist);
 
-	fd = sys_perf_event_open(&evsel->attr, -1, cpu, -1, flags);
-	if (fd < 0)
-		goto out_delete;
+	while (1) {
+		fd = sys_perf_event_open(&evsel->attr, pid, cpu, -1, flags);
+		if (fd < 0) {
+			if (pid == -1 && errno == EACCES) {
+				pid = 0;
+				continue;
+			}
+			goto out_delete;
+		}
+		break;
+	}
 	close(fd);
 
 	fn(evsel);
 
-	fd = sys_perf_event_open(&evsel->attr, -1, cpu, -1, flags);
+	fd = sys_perf_event_open(&evsel->attr, pid, cpu, -1, flags);
 	if (fd < 0) {
 		if (errno == EINVAL)
 			err = -EINVAL;
@@ -47,7 +56,7 @@ out_delete:
 
 static bool perf_probe_api(setup_probe_fn_t fn)
 {
-	const char *try[] = {"cycles:u", "instructions:u", "cpu-clock", NULL};
+	const char *try[] = {"cycles:u", "instructions:u", "cpu-clock:u", NULL};
 	struct cpu_map *cpus;
 	int cpu, ret, i = 0;
 
@@ -106,7 +115,7 @@ void perf_evlist__config(struct perf_evlist *evlist, struct record_opts *opts)
 
 	evlist__for_each(evlist, evsel) {
 		perf_evsel__config(evsel, opts);
-		if (!evsel->idx && use_comm_exec)
+		if (evsel->tracking && use_comm_exec)
 			evsel->attr.comm_exec = 1;
 	}
 
@@ -201,6 +210,7 @@ bool perf_evlist__can_select_event(struct perf_evlist *evlist, const char *str)
 	struct perf_evsel *evsel;
 	int err, fd, cpu;
 	bool ret = false;
+	pid_t pid = -1;
 
 	temp_evlist = perf_evlist__new();
 	if (!temp_evlist)
@@ -221,12 +231,20 @@ bool perf_evlist__can_select_event(struct perf_evlist *evlist, const char *str)
 		cpu = evlist->cpus->map[0];
 	}
 
-	fd = sys_perf_event_open(&evsel->attr, -1, cpu, -1,
-				 perf_event_open_cloexec_flag());
-	if (fd >= 0) {
-		close(fd);
-		ret = true;
+	while (1) {
+		fd = sys_perf_event_open(&evsel->attr, pid, cpu, -1,
+					 perf_event_open_cloexec_flag());
+		if (fd < 0) {
+			if (pid == -1 && errno == EACCES) {
+				pid = 0;
+				continue;
+			}
+			goto out_delete;
+		}
+		break;
 	}
+	close(fd);
+	ret = true;
 
 out_delete:
 	perf_evlist__delete(temp_evlist);
diff --git a/tools/perf/util/run-command.c b/tools/perf/util/run-command.c
index da8e9b285f5158..34622b53e733b5 100644
--- a/tools/perf/util/run-command.c
+++ b/tools/perf/util/run-command.c
@@ -1,6 +1,7 @@
 #include "cache.h"
 #include "run-command.h"
 #include "exec_cmd.h"
+#include "debug.h"
 
 static inline void close_pair(int fd[2])
 {
@@ -19,6 +20,7 @@ int start_command(struct child_process *cmd)
 {
 	int need_in, need_out, need_err;
 	int fdin[2], fdout[2], fderr[2];
+	char sbuf[STRERR_BUFSIZE];
 
 	/*
 	 * In case of errors we must keep the promise to close FDs
@@ -99,7 +101,7 @@ int start_command(struct child_process *cmd)
 
 		if (cmd->dir && chdir(cmd->dir))
 			die("exec %s: cd to %s failed (%s)", cmd->argv[0],
-			    cmd->dir, strerror(errno));
+			    cmd->dir, strerror_r(errno, sbuf, sizeof(sbuf)));
 		if (cmd->env) {
 			for (; *cmd->env; cmd->env++) {
 				if (strchr(*cmd->env, '='))
@@ -153,6 +155,8 @@ int start_command(struct child_process *cmd)
 
 static int wait_or_whine(pid_t pid)
 {
+	char sbuf[STRERR_BUFSIZE];
+
 	for (;;) {
 		int status, code;
 		pid_t waiting = waitpid(pid, &status, 0);
@@ -160,7 +164,8 @@ static int wait_or_whine(pid_t pid)
 		if (waiting < 0) {
 			if (errno == EINTR)
 				continue;
-			error("waitpid failed (%s)", strerror(errno));
+			error("waitpid failed (%s)",
+			      strerror_r(errno, sbuf, sizeof(sbuf)));
 			return -ERR_RUN_COMMAND_WAITPID;
 		}
 		if (waiting != pid)
diff --git a/tools/perf/util/scripting-engines/trace-event-perl.c b/tools/perf/util/scripting-engines/trace-event-perl.c
index b2dba9c0a3a184..0a01bac4ce023e 100644
--- a/tools/perf/util/scripting-engines/trace-event-perl.c
+++ b/tools/perf/util/scripting-engines/trace-event-perl.c
@@ -432,6 +432,11 @@ error:
 	return err;
 }
 
+static int perl_flush_script(void)
+{
+	return 0;
+}
+
 /*
  * Stop trace script
  */
@@ -633,6 +638,7 @@ static int perl_generate_script(struct pevent *pevent, const char *outfile)
 struct scripting_ops perl_scripting_ops = {
 	.name = "Perl",
 	.start_script = perl_start_script,
+	.flush_script = perl_flush_script,
 	.stop_script = perl_stop_script,
 	.process_event = perl_process_event,
 	.generate_script = perl_generate_script,
diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index cbce2545da455f..56ba07cce549ef 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -73,6 +73,35 @@ static void pydict_set_item_string_decref(PyObject *dict, const char *key, PyObj
 	Py_DECREF(val);
 }
 
+static PyObject *get_handler(const char *handler_name)
+{
+	PyObject *handler;
+
+	handler = PyDict_GetItemString(main_dict, handler_name);
+	if (handler && !PyCallable_Check(handler))
+		return NULL;
+	return handler;
+}
+
+static void call_object(PyObject *handler, PyObject *args, const char *die_msg)
+{
+	PyObject *retval;
+
+	retval = PyObject_CallObject(handler, args);
+	if (retval == NULL)
+		handler_call_die(die_msg);
+	Py_DECREF(retval);
+}
+
+static void try_call_object(const char *handler_name, PyObject *args)
+{
+	PyObject *handler;
+
+	handler = get_handler(handler_name);
+	if (handler)
+		call_object(handler, args, handler_name);
+}
+
 static void define_value(enum print_arg_type field_type,
 			 const char *ev_name,
 			 const char *field_name,
@@ -80,7 +109,7 @@ static void define_value(enum print_arg_type field_type,
 			 const char *field_str)
 {
 	const char *handler_name = "define_flag_value";
-	PyObject *handler, *t, *retval;
+	PyObject *t;
 	unsigned long long value;
 	unsigned n = 0;
 
@@ -98,13 +127,7 @@ static void define_value(enum print_arg_type field_type,
 	PyTuple_SetItem(t, n++, PyInt_FromLong(value));
 	PyTuple_SetItem(t, n++, PyString_FromString(field_str));
 
-	handler = PyDict_GetItemString(main_dict, handler_name);
-	if (handler && PyCallable_Check(handler)) {
-		retval = PyObject_CallObject(handler, t);
-		if (retval == NULL)
-			handler_call_die(handler_name);
-		Py_DECREF(retval);
-	}
+	try_call_object(handler_name, t);
 
 	Py_DECREF(t);
 }
@@ -127,7 +150,7 @@ static void define_field(enum print_arg_type field_type,
 			 const char *delim)
 {
 	const char *handler_name = "define_flag_field";
-	PyObject *handler, *t, *retval;
+	PyObject *t;
 	unsigned n = 0;
 
 	if (field_type == PRINT_SYMBOL)
@@ -145,13 +168,7 @@ static void define_field(enum print_arg_type field_type,
 	if (field_type == PRINT_FLAGS)
 		PyTuple_SetItem(t, n++, PyString_FromString(delim));
 
-	handler = PyDict_GetItemString(main_dict, handler_name);
-	if (handler && PyCallable_Check(handler)) {
-		retval = PyObject_CallObject(handler, t);
-		if (retval == NULL)
-			handler_call_die(handler_name);
-		Py_DECREF(retval);
-	}
+	try_call_object(handler_name, t);
 
 	Py_DECREF(t);
 }
@@ -362,7 +379,7 @@ static void python_process_tracepoint(struct perf_sample *sample,
 				      struct thread *thread,
 				      struct addr_location *al)
 {
-	PyObject *handler, *retval, *context, *t, *obj, *callchain;
+	PyObject *handler, *context, *t, *obj, *callchain;
 	PyObject *dict = NULL;
 	static char handler_name[256];
 	struct format_field *field;
@@ -387,9 +404,7 @@ static void python_process_tracepoint(struct perf_sample *sample,
 
 	sprintf(handler_name, "%s__%s", event->system, event->name);
 
-	handler = PyDict_GetItemString(main_dict, handler_name);
-	if (handler && !PyCallable_Check(handler))
-		handler = NULL;
+	handler = get_handler(handler_name);
 	if (!handler) {
 		dict = PyDict_New();
 		if (!dict)
@@ -450,19 +465,9 @@ static void python_process_tracepoint(struct perf_sample *sample,
 		Py_FatalError("error resizing Python tuple");
 
 	if (handler) {
-		retval = PyObject_CallObject(handler, t);
-		if (retval == NULL)
-			handler_call_die(handler_name);
-		Py_DECREF(retval);
+		call_object(handler, t, handler_name);
 	} else {
-		handler = PyDict_GetItemString(main_dict, "trace_unhandled");
-		if (handler && PyCallable_Check(handler)) {
-
-			retval = PyObject_CallObject(handler, t);
-			if (retval == NULL)
-				handler_call_die("trace_unhandled");
-			Py_DECREF(retval);
-		}
+		try_call_object("trace_unhandled", t);
 		Py_DECREF(dict);
 	}
 
@@ -474,7 +479,7 @@ static void python_process_general_event(struct perf_sample *sample,
 					 struct thread *thread,
 					 struct addr_location *al)
 {
-	PyObject *handler, *retval, *t, *dict, *callchain, *dict_sample;
+	PyObject *handler, *t, *dict, *callchain, *dict_sample;
 	static char handler_name[64];
 	unsigned n = 0;
 
@@ -496,8 +501,8 @@ static void python_process_general_event(struct perf_sample *sample,
 
 	snprintf(handler_name, sizeof(handler_name), "%s", "process_event");
 
-	handler = PyDict_GetItemString(main_dict, handler_name);
-	if (!handler || !PyCallable_Check(handler))
+	handler = get_handler(handler_name);
+	if (!handler)
 		goto exit;
 
 	pydict_set_item_string_decref(dict, "ev_name", PyString_FromString(perf_evsel__name(evsel)));
@@ -539,10 +544,7 @@ static void python_process_general_event(struct perf_sample *sample,
 	if (_PyTuple_Resize(&t, n) == -1)
 		Py_FatalError("error resizing Python tuple");
 
-	retval = PyObject_CallObject(handler, t);
-	if (retval == NULL)
-		handler_call_die(handler_name);
-	Py_DECREF(retval);
+	call_object(handler, t, handler_name);
 exit:
 	Py_DECREF(dict);
 	Py_DECREF(t);
@@ -566,36 +568,24 @@ static void python_process_event(union perf_event *event __maybe_unused,
 
 static int run_start_sub(void)
 {
-	PyObject *handler, *retval;
-	int err = 0;
-
 	main_module = PyImport_AddModule("__main__");
 	if (main_module == NULL)
 		return -1;
 	Py_INCREF(main_module);
 
 	main_dict = PyModule_GetDict(main_module);
-	if (main_dict == NULL) {
-		err = -1;
+	if (main_dict == NULL)
 		goto error;
-	}
 	Py_INCREF(main_dict);
 
-	handler = PyDict_GetItemString(main_dict, "trace_begin");
-	if (handler == NULL || !PyCallable_Check(handler))
-		goto out;
+	try_call_object("trace_begin", NULL);
 
-	retval = PyObject_CallObject(handler, NULL);
-	if (retval == NULL)
-		handler_call_die("trace_begin");
+	return 0;
 
-	Py_DECREF(retval);
-	return err;
 error:
 	Py_XDECREF(main_dict);
 	Py_XDECREF(main_module);
-out:
-	return err;
+	return -1;
 }
 
 /*
@@ -649,28 +639,23 @@ error:
 	return err;
 }
 
+static int python_flush_script(void)
+{
+	return 0;
+}
+
 /*
  * Stop trace script
  */
 static int python_stop_script(void)
 {
-	PyObject *handler, *retval;
-	int err = 0;
+	try_call_object("trace_end", NULL);
 
-	handler = PyDict_GetItemString(main_dict, "trace_end");
-	if (handler == NULL || !PyCallable_Check(handler))
-		goto out;
-
-	retval = PyObject_CallObject(handler, NULL);
-	if (retval == NULL)
-		handler_call_die("trace_end");
-	Py_DECREF(retval);
-out:
 	Py_XDECREF(main_dict);
 	Py_XDECREF(main_module);
 	Py_Finalize();
 
-	return err;
+	return 0;
 }
 
 static int python_generate_script(struct pevent *pevent, const char *outfile)
@@ -843,6 +828,7 @@ static int python_generate_script(struct pevent *pevent, const char *outfile)
 struct scripting_ops python_scripting_ops = {
 	.name = "Python",
 	.start_script = python_start_script,
+	.flush_script = python_flush_script,
 	.stop_script = python_stop_script,
 	.process_event = python_process_event,
 	.generate_script = python_generate_script,
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 88dfef70c13dbe..6d2d50dea1d811 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -14,6 +14,7 @@
 #include "util.h"
 #include "cpumap.h"
 #include "perf_regs.h"
+#include "asm/bug.h"
 
 static int perf_session__open(struct perf_session *session)
 {
@@ -66,6 +67,25 @@ static void perf_session__destroy_kernel_maps(struct perf_session *session)
 	machines__destroy_kernel_maps(&session->machines);
 }
 
+static bool perf_session__has_comm_exec(struct perf_session *session)
+{
+	struct perf_evsel *evsel;
+
+	evlist__for_each(session->evlist, evsel) {
+		if (evsel->attr.comm_exec)
+			return true;
+	}
+
+	return false;
+}
+
+static void perf_session__set_comm_exec(struct perf_session *session)
+{
+	bool comm_exec = perf_session__has_comm_exec(session);
+
+	machines__set_comm_exec(&session->machines, comm_exec);
+}
+
 struct perf_session *perf_session__new(struct perf_data_file *file,
 				       bool repipe, struct perf_tool *tool)
 {
@@ -75,9 +95,7 @@ struct perf_session *perf_session__new(struct perf_data_file *file,
 		goto out;
 
 	session->repipe = repipe;
-	INIT_LIST_HEAD(&session->ordered_samples.samples);
-	INIT_LIST_HEAD(&session->ordered_samples.sample_cache);
-	INIT_LIST_HEAD(&session->ordered_samples.to_free);
+	ordered_events__init(&session->ordered_events);
 	machines__init(&session->machines);
 
 	if (file) {
@@ -91,6 +109,7 @@ struct perf_session *perf_session__new(struct perf_data_file *file,
 				goto out_close;
 
 			perf_session__set_id_hdr_size(session);
+			perf_session__set_comm_exec(session);
 		}
 	}
 
@@ -104,9 +123,9 @@ struct perf_session *perf_session__new(struct perf_data_file *file,
 	}
 
 	if (tool && tool->ordering_requires_timestamps &&
-	    tool->ordered_samples && !perf_evlist__sample_id_all(session->evlist)) {
+	    tool->ordered_events && !perf_evlist__sample_id_all(session->evlist)) {
 		dump_printf("WARNING: No sample_id_all support, falling back to unordered processing\n");
-		tool->ordered_samples = false;
+		tool->ordered_events = false;
 	}
 
 	return session;
@@ -238,7 +257,7 @@ void perf_tool__fill_defaults(struct perf_tool *tool)
 	if (tool->build_id == NULL)
 		tool->build_id = process_finished_round_stub;
 	if (tool->finished_round == NULL) {
-		if (tool->ordered_samples)
+		if (tool->ordered_events)
 			tool->finished_round = process_finished_round;
 		else
 			tool->finished_round = process_finished_round_stub;
@@ -444,87 +463,6 @@ static perf_event__swap_op perf_event__swap_ops[] = {
 	[PERF_RECORD_HEADER_MAX]	  = NULL,
 };
 
-struct sample_queue {
-	u64			timestamp;
-	u64			file_offset;
-	union perf_event	*event;
-	struct list_head	list;
-};
-
-static void perf_session_free_sample_buffers(struct perf_session *session)
-{
-	struct ordered_samples *os = &session->ordered_samples;
-
-	while (!list_empty(&os->to_free)) {
-		struct sample_queue *sq;
-
-		sq = list_entry(os->to_free.next, struct sample_queue, list);
-		list_del(&sq->list);
-		free(sq);
-	}
-}
-
-static int perf_session_deliver_event(struct perf_session *session,
-				      union perf_event *event,
-				      struct perf_sample *sample,
-				      struct perf_tool *tool,
-				      u64 file_offset);
-
-static int flush_sample_queue(struct perf_session *s,
-		       struct perf_tool *tool)
-{
-	struct ordered_samples *os = &s->ordered_samples;
-	struct list_head *head = &os->samples;
-	struct sample_queue *tmp, *iter;
-	struct perf_sample sample;
-	u64 limit = os->next_flush;
-	u64 last_ts = os->last_sample ? os->last_sample->timestamp : 0ULL;
-	bool show_progress = limit == ULLONG_MAX;
-	struct ui_progress prog;
-	int ret;
-
-	if (!tool->ordered_samples || !limit)
-		return 0;
-
-	if (show_progress)
-		ui_progress__init(&prog, os->nr_samples, "Processing time ordered events...");
-
-	list_for_each_entry_safe(iter, tmp, head, list) {
-		if (session_done())
-			return 0;
-
-		if (iter->timestamp > limit)
-			break;
-
-		ret = perf_evlist__parse_sample(s->evlist, iter->event, &sample);
-		if (ret)
-			pr_err("Can't parse sample, err = %d\n", ret);
-		else {
-			ret = perf_session_deliver_event(s, iter->event, &sample, tool,
-							 iter->file_offset);
-			if (ret)
-				return ret;
-		}
-
-		os->last_flush = iter->timestamp;
-		list_del(&iter->list);
-		list_add(&iter->list, &os->sample_cache);
-		os->nr_samples--;
-
-		if (show_progress)
-			ui_progress__update(&prog, 1);
-	}
-
-	if (list_empty(head)) {
-		os->last_sample = NULL;
-	} else if (last_ts <= limit) {
-		os->last_sample =
-			list_entry(head->prev, struct sample_queue, list);
-	}
-
-	return 0;
-}
-
 /*
  * When perf record finishes a pass on every buffers, it records this pseudo
  * event.
@@ -568,99 +506,43 @@ static int process_finished_round(struct perf_tool *tool,
 				  union perf_event *event __maybe_unused,
 				  struct perf_session *session)
 {
-	int ret = flush_sample_queue(session, tool);
-	if (!ret)
-		session->ordered_samples.next_flush = session->ordered_samples.max_timestamp;
-
-	return ret;
+	return ordered_events__flush(session, tool, OE_FLUSH__ROUND);
 }
 
-/* The queue is ordered by time */
-static void __queue_event(struct sample_queue *new, struct perf_session *s)
-{
-	struct ordered_samples *os = &s->ordered_samples;
-	struct sample_queue *sample = os->last_sample;
-	u64 timestamp = new->timestamp;
-	struct list_head *p;
-
-	++os->nr_samples;
-	os->last_sample = new;
-
-	if (!sample) {
-		list_add(&new->list, &os->samples);
-		os->max_timestamp = timestamp;
-		return;
-	}
-
-	/*
-	 * last_sample might point to some random place in the list as it's
-	 * the last queued event. We expect that the new event is close to
-	 * this.
-	 */
-	if (sample->timestamp <= timestamp) {
-		while (sample->timestamp <= timestamp) {
-			p = sample->list.next;
-			if (p == &os->samples) {
-				list_add_tail(&new->list, &os->samples);
-				os->max_timestamp = timestamp;
-				return;
-			}
-			sample = list_entry(p, struct sample_queue, list);
-		}
-		list_add_tail(&new->list, &sample->list);
-	} else {
-		while (sample->timestamp > timestamp) {
-			p = sample->list.prev;
-			if (p == &os->samples) {
-				list_add(&new->list, &os->samples);
-				return;
-			}
-			sample = list_entry(p, struct sample_queue, list);
-		}
-		list_add(&new->list, &sample->list);
-	}
-}
-
-#define MAX_SAMPLE_BUFFER	(64 * 1024 / sizeof(struct sample_queue))
-
 int perf_session_queue_event(struct perf_session *s, union perf_event *event,
-				    struct perf_sample *sample, u64 file_offset)
+			     struct perf_tool *tool, struct perf_sample *sample,
+			     u64 file_offset)
 {
-	struct ordered_samples *os = &s->ordered_samples;
-	struct list_head *sc = &os->sample_cache;
+	struct ordered_events *oe = &s->ordered_events;
 	u64 timestamp = sample->time;
-	struct sample_queue *new;
+	struct ordered_event *new;
 
 	if (!timestamp || timestamp == ~0ULL)
 		return -ETIME;
 
-	if (timestamp < s->ordered_samples.last_flush) {
-		printf("Warning: Timestamp below last timeslice flush\n");
-		return -EINVAL;
+	if (timestamp < oe->last_flush) {
+		WARN_ONCE(1, "Timestamp below last timeslice flush\n");
+
+		pr_oe_time(timestamp,      "out of order event");
+		pr_oe_time(oe->last_flush, "last flush, last_flush_type %d\n",
+			   oe->last_flush_type);
+
+		/* We could get out of order messages after forced flush. */
+		if (oe->last_flush_type != OE_FLUSH__HALF)
+			return -EINVAL;
 	}
 
-	if (!list_empty(sc)) {
-		new = list_entry(sc->next, struct sample_queue, list);
-		list_del(&new->list);
-	} else if (os->sample_buffer) {
-		new = os->sample_buffer + os->sample_buffer_idx;
-		if (++os->sample_buffer_idx == MAX_SAMPLE_BUFFER)
-			os->sample_buffer = NULL;
-	} else {
-		os->sample_buffer = malloc(MAX_SAMPLE_BUFFER * sizeof(*new));
-		if (!os->sample_buffer)
-			return -ENOMEM;
-		list_add(&os->sample_buffer->list, &os->to_free);
-		os->sample_buffer_idx = 2;
-		new = os->sample_buffer + 1;
+	new = ordered_events__new(oe, timestamp);
+	if (!new) {
+		ordered_events__flush(s, tool, OE_FLUSH__HALF);
+		new = ordered_events__new(oe, timestamp);
 	}
 
-	new->timestamp = timestamp;
+	if (!new)
+		return -ENOMEM;
+
 	new->file_offset = file_offset;
 	new->event = event;
-
-	__queue_event(new, s);
-
 	return 0;
 }
 
@@ -920,11 +802,10 @@ perf_session__deliver_sample(struct perf_session *session,
 					    &sample->read.one, machine);
 }
 
-static int perf_session_deliver_event(struct perf_session *session,
-				      union perf_event *event,
-				      struct perf_sample *sample,
-				      struct perf_tool *tool,
-				      u64 file_offset)
+int perf_session__deliver_event(struct perf_session *session,
+				union perf_event *event,
+				struct perf_sample *sample,
+				struct perf_tool *tool, u64 file_offset)
 {
 	struct perf_evsel *evsel;
 	struct machine *machine;
@@ -1005,8 +886,10 @@ static s64 perf_session__process_user_event(struct perf_session *session,
 	switch (event->header.type) {
 	case PERF_RECORD_HEADER_ATTR:
 		err = tool->attr(tool, event, &session->evlist);
-		if (err == 0)
+		if (err == 0) {
 			perf_session__set_id_hdr_size(session);
+			perf_session__set_comm_exec(session);
+		}
 		return err;
 	case PERF_RECORD_HEADER_EVENT_TYPE:
 		/*
@@ -1036,6 +919,61 @@ static void event_swap(union perf_event *event, bool sample_id_all)
 		swap(event, sample_id_all);
 }
 
+int perf_session__peek_event(struct perf_session *session, off_t file_offset,
+			     void *buf, size_t buf_sz,
+			     union perf_event **event_ptr,
+			     struct perf_sample *sample)
+{
+	union perf_event *event;
+	size_t hdr_sz, rest;
+	int fd;
+
+	if (session->one_mmap && !session->header.needs_swap) {
+		event = file_offset - session->one_mmap_offset +
+			session->one_mmap_addr;
+		goto out_parse_sample;
+	}
+
+	if (perf_data_file__is_pipe(session->file))
+		return -1;
+
+	fd = perf_data_file__fd(session->file);
+	hdr_sz = sizeof(struct perf_event_header);
+
+	if (buf_sz < hdr_sz)
+		return -1;
+
+	if (lseek(fd, file_offset, SEEK_SET) == (off_t)-1 ||
+	    readn(fd, &buf, hdr_sz) != (ssize_t)hdr_sz)
+		return -1;
+
+	event = (union perf_event *)buf;
+
+	if (session->header.needs_swap)
+		perf_event_header__bswap(&event->header);
+
+	if (event->header.size < hdr_sz)
+		return -1;
+
+	rest = event->header.size - hdr_sz;
+
+	if (readn(fd, &buf, rest) != (ssize_t)rest)
+		return -1;
+
+	if (session->header.needs_swap)
+		event_swap(event, perf_evlist__sample_id_all(session->evlist));
+
+out_parse_sample:
+
+	if (sample && event->header.type < PERF_RECORD_USER_TYPE_START &&
+	    perf_evlist__parse_sample(session->evlist, event, sample))
+		return -1;
+
+	*event_ptr = event;
+
+	return 0;
+}
+
 static s64 perf_session__process_event(struct perf_session *session,
 				       union perf_event *event,
 				       struct perf_tool *tool,
@@ -1062,15 +1000,15 @@ static s64 perf_session__process_event(struct perf_session *session,
 	if (ret)
 		return ret;
 
-	if (tool->ordered_samples) {
-		ret = perf_session_queue_event(session, event, &sample,
+	if (tool->ordered_events) {
+		ret = perf_session_queue_event(session, event, tool, &sample,
 					       file_offset);
 		if (ret != -ETIME)
 			return ret;
 	}
 
-	return perf_session_deliver_event(session, event, &sample, tool,
-					  file_offset);
+	return perf_session__deliver_event(session, event, &sample, tool,
+					   file_offset);
 }
 
 void perf_event_header__bswap(struct perf_event_header *hdr)
@@ -1222,12 +1160,11 @@ more:
 		goto more;
 done:
 	/* do the final flush for ordered samples */
-	session->ordered_samples.next_flush = ULLONG_MAX;
-	err = flush_sample_queue(session, tool);
+	err = ordered_events__flush(session, tool, OE_FLUSH__FINAL);
 out_err:
 	free(buf);
 	perf_session__warn_about_errors(session, tool);
-	perf_session_free_sample_buffers(session);
+	ordered_events__free(&session->ordered_events);
 	return err;
 }
 
@@ -1368,12 +1305,11 @@ more:
 
 out:
 	/* do the final flush for ordered samples */
-	session->ordered_samples.next_flush = ULLONG_MAX;
-	err = flush_sample_queue(session, tool);
+	err = ordered_events__flush(session, tool, OE_FLUSH__FINAL);
 out_err:
 	ui_progress__finish();
 	perf_session__warn_about_errors(session, tool);
-	perf_session_free_sample_buffers(session);
+	ordered_events__free(&session->ordered_events);
 	session->one_mmap = false;
 	return err;
 }
diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h
index 0321013bd9fde6..8dd41cad2d59d9 100644
--- a/tools/perf/util/session.h
+++ b/tools/perf/util/session.h
@@ -9,26 +9,13 @@
 #include "symbol.h"
 #include "thread.h"
 #include "data.h"
+#include "ordered-events.h"
 #include <linux/rbtree.h>
 #include <linux/perf_event.h>
 
-struct sample_queue;
 struct ip_callchain;
 struct thread;
 
-struct ordered_samples {
-	u64			last_flush;
-	u64			next_flush;
-	u64			max_timestamp;
-	struct list_head	samples;
-	struct list_head	sample_cache;
-	struct list_head	to_free;
-	struct sample_queue	*sample_buffer;
-	struct sample_queue	*last_sample;
-	int			sample_buffer_idx;
-	unsigned int		nr_samples;
-};
-
 struct perf_session {
 	struct perf_header	header;
 	struct machines		machines;
@@ -39,7 +26,7 @@ struct perf_session {
 	bool			one_mmap;
 	void			*one_mmap_addr;
 	u64			one_mmap_offset;
-	struct ordered_samples	ordered_samples;
+	struct ordered_events	ordered_events;
 	struct perf_data_file	*file;
 };
 
@@ -58,6 +45,11 @@ void perf_session__delete(struct perf_session *session);
 
 void perf_event_header__bswap(struct perf_event_header *hdr);
 
+int perf_session__peek_event(struct perf_session *session, off_t file_offset,
+			     void *buf, size_t buf_sz,
+			     union perf_event **event_ptr,
+			     struct perf_sample *sample);
+
 int __perf_session__process_events(struct perf_session *session,
 				   u64 data_offset, u64 data_size, u64 size,
 				   struct perf_tool *tool);
@@ -65,10 +57,16 @@ int perf_session__process_events(struct perf_session *session,
 				 struct perf_tool *tool);
 
 int perf_session_queue_event(struct perf_session *s, union perf_event *event,
-			     struct perf_sample *sample, u64 file_offset);
+			     struct perf_tool *tool, struct perf_sample *sample,
+			     u64 file_offset);
 
 void perf_tool__fill_defaults(struct perf_tool *tool);
 
+int perf_session__deliver_event(struct perf_session *session,
+				union perf_event *event,
+				struct perf_sample *sample,
+				struct perf_tool *tool, u64 file_offset);
+
 int perf_session__resolve_callchain(struct perf_session *session,
 				    struct perf_evsel *evsel,
 				    struct thread *thread,
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index 14e5a039bc4546..1958637cf13675 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -70,12 +70,14 @@ static int hist_entry__thread_snprintf(struct hist_entry *he, char *bf,
 				       size_t size, unsigned int width)
 {
 	const char *comm = thread__comm_str(he->thread);
-	return repsep_snprintf(bf, size, "%*s:%5d", width - 6,
-			       comm ?: "", he->thread->tid);
+
+	width = max(7U, width) - 6;
+	return repsep_snprintf(bf, size, "%5d:%-*.*s", he->thread->tid,
+			       width, width, comm ?: "");
 }
 
 struct sort_entry sort_thread = {
-	.se_header	= "Command:  Pid",
+	.se_header	= "  Pid:Command",
 	.se_cmp		= sort__thread_cmp,
 	.se_snprintf	= hist_entry__thread_snprintf,
 	.se_width_idx	= HISTC_THREAD,
@@ -106,7 +108,7 @@ sort__comm_sort(struct hist_entry *left, struct hist_entry *right)
 static int hist_entry__comm_snprintf(struct hist_entry *he, char *bf,
 				     size_t size, unsigned int width)
 {
-	return repsep_snprintf(bf, size, "%*s", width, comm__str(he->comm));
+	return repsep_snprintf(bf, size, "%-*.*s", width, width, comm__str(he->comm));
 }
 
 struct sort_entry sort_comm = {
@@ -152,10 +154,10 @@ static int _hist_entry__dso_snprintf(struct map *map, char *bf,
 	if (map && map->dso) {
 		const char *dso_name = !verbose ? map->dso->short_name :
 			map->dso->long_name;
-		return repsep_snprintf(bf, size, "%-*s", width, dso_name);
+		return repsep_snprintf(bf, size, "%-*.*s", width, width, dso_name);
 	}
 
-	return repsep_snprintf(bf, size, "%-*s", width, "[unknown]");
+	return repsep_snprintf(bf, size, "%-*.*s", width, width, "[unknown]");
 }
 
 static int hist_entry__dso_snprintf(struct hist_entry *he, char *bf,
@@ -257,7 +259,10 @@ static int _hist_entry__sym_snprintf(struct map *map, struct symbol *sym,
 				       width - ret, "");
 	}
 
-	return ret;
+	if (ret > width)
+		bf[width] = '\0';
+
+	return width;
 }
 
 static int hist_entry__sym_snprintf(struct hist_entry *he, char *bf,
@@ -302,10 +307,9 @@ sort__srcline_cmp(struct hist_entry *left, struct hist_entry *right)
 }
 
 static int hist_entry__srcline_snprintf(struct hist_entry *he, char *bf,
-					size_t size,
-					unsigned int width __maybe_unused)
+					size_t size, unsigned int width)
 {
-	return repsep_snprintf(bf, size, "%s", he->srcline);
+	return repsep_snprintf(bf, size, "%*.*-s", width, width, he->srcline);
 }
 
 struct sort_entry sort_srcline = {
@@ -332,7 +336,7 @@ sort__parent_cmp(struct hist_entry *left, struct hist_entry *right)
 static int hist_entry__parent_snprintf(struct hist_entry *he, char *bf,
 				       size_t size, unsigned int width)
 {
-	return repsep_snprintf(bf, size, "%-*s", width,
+	return repsep_snprintf(bf, size, "%-*.*s", width, width,
 			      he->parent ? he->parent->name : "[other]");
 }
 
@@ -354,7 +358,7 @@ sort__cpu_cmp(struct hist_entry *left, struct hist_entry *right)
 static int hist_entry__cpu_snprintf(struct hist_entry *he, char *bf,
 				    size_t size, unsigned int width)
 {
-	return repsep_snprintf(bf, size, "%*d", width, he->cpu);
+	return repsep_snprintf(bf, size, "%*.*d", width, width, he->cpu);
 }
 
 struct sort_entry sort_cpu = {
@@ -484,7 +488,7 @@ static int hist_entry__mispredict_snprintf(struct hist_entry *he, char *bf,
 	else if (he->branch_info->flags.mispred)
 		out = "Y";
 
-	return repsep_snprintf(bf, size, "%-*s", width, out);
+	return repsep_snprintf(bf, size, "%-*.*s", width, width, out);
 }
 
 /* --sort daddr_sym */
@@ -1194,7 +1198,7 @@ bool perf_hpp__same_sort_entry(struct perf_hpp_fmt *a, struct perf_hpp_fmt *b)
 	return hse_a->se == hse_b->se;
 }
 
-void perf_hpp__reset_width(struct perf_hpp_fmt *fmt, struct hists *hists)
+void perf_hpp__reset_sort_width(struct perf_hpp_fmt *fmt, struct hists *hists)
 {
 	struct hpp_sort_entry *hse;
 
@@ -1202,20 +1206,21 @@ void perf_hpp__reset_width(struct perf_hpp_fmt *fmt, struct hists *hists)
 		return;
 
 	hse = container_of(fmt, struct hpp_sort_entry, hpp);
-	hists__new_col_len(hists, hse->se->se_width_idx,
-			   strlen(hse->se->se_header));
+	hists__new_col_len(hists, hse->se->se_width_idx, strlen(fmt->name));
 }
 
 static int __sort__hpp_header(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
 			      struct perf_evsel *evsel)
 {
 	struct hpp_sort_entry *hse;
-	size_t len;
+	size_t len = fmt->user_len;
 
 	hse = container_of(fmt, struct hpp_sort_entry, hpp);
-	len = hists__col_len(&evsel->hists, hse->se->se_width_idx);
 
-	return scnprintf(hpp->buf, hpp->size, "%-*s", len, hse->se->se_header);
+	if (!len)
+		len = hists__col_len(&evsel->hists, hse->se->se_width_idx);
+
+	return scnprintf(hpp->buf, hpp->size, "%-*.*s", len, len, fmt->name);
 }
 
 static int __sort__hpp_width(struct perf_hpp_fmt *fmt,
@@ -1223,20 +1228,26 @@ static int __sort__hpp_width(struct perf_hpp_fmt *fmt,
 			     struct perf_evsel *evsel)
 {
 	struct hpp_sort_entry *hse;
+	size_t len = fmt->user_len;
 
 	hse = container_of(fmt, struct hpp_sort_entry, hpp);
 
-	return hists__col_len(&evsel->hists, hse->se->se_width_idx);
+	if (!len)
+		len = hists__col_len(&evsel->hists, hse->se->se_width_idx);
+
+	return len;
 }
 
 static int __sort__hpp_entry(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
 			     struct hist_entry *he)
 {
 	struct hpp_sort_entry *hse;
-	size_t len;
+	size_t len = fmt->user_len;
 
 	hse = container_of(fmt, struct hpp_sort_entry, hpp);
-	len = hists__col_len(he->hists, hse->se->se_width_idx);
+
+	if (!len)
+		len = hists__col_len(he->hists, hse->se->se_width_idx);
 
 	return hse->se->se_snprintf(he, hpp->buf, hpp->size, len);
 }
@@ -1253,6 +1264,7 @@ __sort_dimension__alloc_hpp(struct sort_dimension *sd)
 	}
 
 	hse->se = sd->entry;
+	hse->hpp.name = sd->entry->se_header;
 	hse->hpp.header = __sort__hpp_header;
 	hse->hpp.width = __sort__hpp_width;
 	hse->hpp.entry = __sort__hpp_entry;
@@ -1265,6 +1277,8 @@ __sort_dimension__alloc_hpp(struct sort_dimension *sd)
 	INIT_LIST_HEAD(&hse->hpp.list);
 	INIT_LIST_HEAD(&hse->hpp.sort_list);
 	hse->hpp.elide = false;
+	hse->hpp.len = 0;
+	hse->hpp.user_len = 0;
 
 	return hse;
 }
@@ -1439,7 +1453,7 @@ static int __setup_sorting(void)
 	int ret = 0;
 
 	if (sort_keys == NULL) {
-		if (field_order) {
+		if (is_strict_order(field_order)) {
 			/*
 			 * If user specified field order but no sort order,
 			 * we'll honor it and not add default sort orders.
@@ -1625,23 +1639,36 @@ static void reset_dimensions(void)
 		memory_sort_dimensions[i].taken = 0;
 }
 
+bool is_strict_order(const char *order)
+{
+	return order && (*order != '+');
+}
+
 static int __setup_output_field(void)
 {
-	char *tmp, *tok, *str;
-	int ret = 0;
+	char *tmp, *tok, *str, *strp;
+	int ret = -EINVAL;
 
 	if (field_order == NULL)
 		return 0;
 
 	reset_dimensions();
 
-	str = strdup(field_order);
+	strp = str = strdup(field_order);
 	if (str == NULL) {
 		error("Not enough memory to setup output fields");
 		return -ENOMEM;
 	}
 
-	for (tok = strtok_r(str, ", ", &tmp);
+	if (!is_strict_order(field_order))
+		strp++;
+
+	if (!strlen(strp)) {
+		error("Invalid --fields key: `+'");
+		goto out;
+	}
+
+	for (tok = strtok_r(strp, ", ", &tmp);
 			tok; tok = strtok_r(NULL, ", ", &tmp)) {
 		ret = output_field_add(tok);
 		if (ret == -EINVAL) {
@@ -1653,6 +1680,7 @@ static int __setup_output_field(void)
 		}
 	}
 
+out:
 	free(str);
 	return ret;
 }
diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h
index 041f0c9cea2b4f..c03e4ff8beffe0 100644
--- a/tools/perf/util/sort.h
+++ b/tools/perf/util/sort.h
@@ -218,4 +218,5 @@ void perf_hpp__set_elide(int idx, bool elide);
 
 int report_parse_ignore_callees_opt(const struct option *opt, const char *arg, int unset);
 
+bool is_strict_order(const char *order);
 #endif	/* __PERF_SORT_H */
diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c
index d75349979e65e8..9fb5e9e9f1617b 100644
--- a/tools/perf/util/symbol-elf.c
+++ b/tools/perf/util/symbol-elf.c
@@ -736,7 +736,7 @@ int dso__load_sym(struct dso *dso, struct map *map,
 	if (symstrs == NULL)
 		goto out_elf_end;
 
-	sec_strndx = elf_getscn(elf, ehdr.e_shstrndx);
+	sec_strndx = elf_getscn(runtime_ss->elf, runtime_ss->ehdr.e_shstrndx);
 	if (sec_strndx == NULL)
 		goto out_elf_end;
 
@@ -939,8 +939,11 @@ new_symbol:
 		 * to it...
 		 */
 		if (symbol_conf.demangle) {
-			demangled = bfd_demangle(NULL, elf_name,
-						 DMGL_PARAMS | DMGL_ANSI);
+			int demangle_flags = DMGL_NO_OPTS;
+			if (verbose)
+				demangle_flags = DMGL_PARAMS | DMGL_ANSI;
+
+			demangled = bfd_demangle(NULL, elf_name, demangle_flags);
 			if (demangled != NULL)
 				elf_name = demangled;
 		}
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index eb06746b06b291..ac098a3c2a318b 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -15,6 +15,7 @@
 #include "machine.h"
 #include "symbol.h"
 #include "strlist.h"
+#include "header.h"
 
 #include <elf.h>
 #include <limits.h>
@@ -523,10 +524,15 @@ struct process_kallsyms_args {
 	struct dso *dso;
 };
 
+/*
+ * These are symbols in the kernel image, so make sure that
+ * sym is from a kernel DSO.
+ */
 bool symbol__is_idle(struct symbol *sym)
 {
 	const char * const idle_symbols[] = {
 		"cpu_idle",
+		"cpu_startup_entry",
 		"intel_idle",
 		"default_idle",
 		"native_safe_halt",
@@ -1468,8 +1474,7 @@ int dso__load_vmlinux(struct dso *dso, struct map *map,
 	if (vmlinux[0] == '/')
 		snprintf(symfs_vmlinux, sizeof(symfs_vmlinux), "%s", vmlinux);
 	else
-		snprintf(symfs_vmlinux, sizeof(symfs_vmlinux), "%s%s",
-			 symbol_conf.symfs, vmlinux);
+		symbol__join_symfs(symfs_vmlinux, vmlinux);
 
 	if (dso->kernel == DSO_TYPE_GUEST_KERNEL)
 		symtab_type = DSO_BINARY_TYPE__GUEST_VMLINUX;
@@ -1745,10 +1750,11 @@ static void vmlinux_path__exit(void)
 	zfree(&vmlinux_path);
 }
 
-static int vmlinux_path__init(void)
+static int vmlinux_path__init(struct perf_session_env *env)
 {
 	struct utsname uts;
 	char bf[PATH_MAX];
+	char *kernel_version;
 
 	vmlinux_path = malloc(sizeof(char *) * 5);
 	if (vmlinux_path == NULL)
@@ -1763,25 +1769,31 @@ static int vmlinux_path__init(void)
 		goto out_fail;
 	++vmlinux_path__nr_entries;
 
-	/* only try running kernel version if no symfs was given */
+	/* only try kernel version if no symfs was given */
 	if (symbol_conf.symfs[0] != 0)
 		return 0;
 
-	if (uname(&uts) < 0)
-		return -1;
+	if (env) {
+		kernel_version = env->os_release;
+	} else {
+		if (uname(&uts) < 0)
+			goto out_fail;
+
+		kernel_version = uts.release;
+	}
 
-	snprintf(bf, sizeof(bf), "/boot/vmlinux-%s", uts.release);
+	snprintf(bf, sizeof(bf), "/boot/vmlinux-%s", kernel_version);
 	vmlinux_path[vmlinux_path__nr_entries] = strdup(bf);
 	if (vmlinux_path[vmlinux_path__nr_entries] == NULL)
 		goto out_fail;
 	++vmlinux_path__nr_entries;
-	snprintf(bf, sizeof(bf), "/lib/modules/%s/build/vmlinux", uts.release);
+	snprintf(bf, sizeof(bf), "/lib/modules/%s/build/vmlinux", kernel_version);
 	vmlinux_path[vmlinux_path__nr_entries] = strdup(bf);
 	if (vmlinux_path[vmlinux_path__nr_entries] == NULL)
 		goto out_fail;
 	++vmlinux_path__nr_entries;
 	snprintf(bf, sizeof(bf), "/usr/lib/debug/lib/modules/%s/vmlinux",
-		 uts.release);
+		 kernel_version);
 	vmlinux_path[vmlinux_path__nr_entries] = strdup(bf);
 	if (vmlinux_path[vmlinux_path__nr_entries] == NULL)
 		goto out_fail;
@@ -1827,7 +1839,7 @@ static bool symbol__read_kptr_restrict(void)
 	return value;
 }
 
-int symbol__init(void)
+int symbol__init(struct perf_session_env *env)
 {
 	const char *symfs;
 
@@ -1842,7 +1854,7 @@ int symbol__init(void)
 		symbol_conf.priv_size += (sizeof(struct symbol_name_rb_node) -
 					  sizeof(struct symbol));
 
-	if (symbol_conf.try_vmlinux_path && vmlinux_path__init() < 0)
+	if (symbol_conf.try_vmlinux_path && vmlinux_path__init(env) < 0)
 		return -1;
 
 	if (symbol_conf.field_sep && *symbol_conf.field_sep == '.') {
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index e7295e93cff9bf..3f95ea0357e38e 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -13,6 +13,7 @@
 #include <libgen.h>
 #include "build-id.h"
 #include "event.h"
+#include "util.h"
 
 #ifdef HAVE_LIBELF_SUPPORT
 #include <libelf.h>
@@ -59,6 +60,7 @@ extern Elf_Scn *elf_section_by_name(Elf *elf, GElf_Ehdr *ep,
 #endif
 
 #ifndef DMGL_PARAMS
+#define DMGL_NO_OPTS     0              /* For readability... */
 #define DMGL_PARAMS      (1 << 0)       /* Include function args */
 #define DMGL_ANSI        (1 << 1)       /* Include const, volatile, etc */
 #endif
@@ -143,6 +145,14 @@ struct symbol_conf {
 };
 
 extern struct symbol_conf symbol_conf;
+
+static inline int __symbol__join_symfs(char *bf, size_t size, const char *path)
+{
+	return path__join(bf, size, symbol_conf.symfs, path);
+}
+
+#define symbol__join_symfs(bf, path) __symbol__join_symfs(bf, sizeof(bf), path)
+
 extern int vmlinux_path__nr_entries;
 extern char **vmlinux_path;
 
@@ -253,7 +263,8 @@ int modules__parse(const char *filename, void *arg,
 int filename__read_debuglink(const char *filename, char *debuglink,
 			     size_t size);
 
-int symbol__init(void);
+struct perf_session_env;
+int symbol__init(struct perf_session_env *env);
 void symbol__exit(void);
 void symbol__elf_init(void);
 struct symbol *symbol__new(u64 start, u64 len, u8 binding, const char *name);
diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c
index 12c7a253a63cee..a9df7f2c6dc934 100644
--- a/tools/perf/util/thread.c
+++ b/tools/perf/util/thread.c
@@ -42,7 +42,7 @@ struct thread *thread__new(pid_t pid, pid_t tid)
 			goto err_thread;
 
 		snprintf(comm_str, 32, ":%d", tid);
-		comm = comm__new(comm_str, 0);
+		comm = comm__new(comm_str, 0, false);
 		free(comm_str);
 		if (!comm)
 			goto err_thread;
@@ -81,19 +81,33 @@ struct comm *thread__comm(const struct thread *thread)
 	return list_first_entry(&thread->comm_list, struct comm, list);
 }
 
+struct comm *thread__exec_comm(const struct thread *thread)
+{
+	struct comm *comm, *last = NULL;
+
+	list_for_each_entry(comm, &thread->comm_list, list) {
+		if (comm->exec)
+			return comm;
+		last = comm;
+	}
+
+	return last;
+}
+
 /* CHECKME: time should always be 0 if event aren't ordered */
-int thread__set_comm(struct thread *thread, const char *str, u64 timestamp)
+int __thread__set_comm(struct thread *thread, const char *str, u64 timestamp,
+		       bool exec)
 {
 	struct comm *new, *curr = thread__comm(thread);
 	int err;
 
 	/* Override latest entry if it had no specific time coverage */
-	if (!curr->start) {
-		err = comm__override(curr, str, timestamp);
+	if (!curr->start && !curr->exec) {
+		err = comm__override(curr, str, timestamp, exec);
 		if (err)
 			return err;
 	} else {
-		new = comm__new(str, timestamp);
+		new = comm__new(str, timestamp, exec);
 		if (!new)
 			return -ENOMEM;
 		list_add(&new->list, &thread->comm_list);
diff --git a/tools/perf/util/thread.h b/tools/perf/util/thread.h
index 716b7723cce27e..8c75fa77470635 100644
--- a/tools/perf/util/thread.h
+++ b/tools/perf/util/thread.h
@@ -38,9 +38,17 @@ static inline void thread__exited(struct thread *thread)
 	thread->dead = true;
 }
 
-int thread__set_comm(struct thread *thread, const char *comm, u64 timestamp);
+int __thread__set_comm(struct thread *thread, const char *comm, u64 timestamp,
+		       bool exec);
+static inline int thread__set_comm(struct thread *thread, const char *comm,
+				   u64 timestamp)
+{
+	return __thread__set_comm(thread, comm, timestamp, false);
+}
+
 int thread__comm_len(struct thread *thread);
 struct comm *thread__comm(const struct thread *thread);
+struct comm *thread__exec_comm(const struct thread *thread);
 const char *thread__comm_str(const struct thread *thread);
 void thread__insert_map(struct thread *thread, struct map *map);
 int thread__fork(struct thread *thread, struct thread *parent, u64 timestamp);
diff --git a/tools/perf/util/tool.h b/tools/perf/util/tool.h
index 4385816d3d4964..f11636966a0f19 100644
--- a/tools/perf/util/tool.h
+++ b/tools/perf/util/tool.h
@@ -40,7 +40,7 @@ struct perf_tool {
 	event_op2	tracing_data;
 	event_op2	finished_round,
 			build_id;
-	bool		ordered_samples;
+	bool		ordered_events;
 	bool		ordering_requires_timestamps;
 };
 
diff --git a/tools/perf/util/trace-event-scripting.c b/tools/perf/util/trace-event-scripting.c
index 57aaccc1692e61..5c9bdd1591a975 100644
--- a/tools/perf/util/trace-event-scripting.c
+++ b/tools/perf/util/trace-event-scripting.c
@@ -30,6 +30,11 @@
 
 struct scripting_context *scripting_context;
 
+static int flush_script_unsupported(void)
+{
+	return 0;
+}
+
 static int stop_script_unsupported(void)
 {
 	return 0;
@@ -74,6 +79,7 @@ static int python_generate_script_unsupported(struct pevent *pevent
 struct scripting_ops python_scripting_unsupported_ops = {
 	.name = "Python",
 	.start_script = python_start_script_unsupported,
+	.flush_script = flush_script_unsupported,
 	.stop_script = stop_script_unsupported,
 	.process_event = process_event_unsupported,
 	.generate_script = python_generate_script_unsupported,
@@ -137,6 +143,7 @@ static int perl_generate_script_unsupported(struct pevent *pevent
 struct scripting_ops perl_scripting_unsupported_ops = {
 	.name = "Perl",
 	.start_script = perl_start_script_unsupported,
+	.flush_script = flush_script_unsupported,
 	.stop_script = stop_script_unsupported,
 	.process_event = process_event_unsupported,
 	.generate_script = perl_generate_script_unsupported,
diff --git a/tools/perf/util/trace-event.h b/tools/perf/util/trace-event.h
index 7b6d68688327a7..52aaa19e1eb131 100644
--- a/tools/perf/util/trace-event.h
+++ b/tools/perf/util/trace-event.h
@@ -64,6 +64,7 @@ struct perf_session;
 struct scripting_ops {
 	const char *name;
 	int (*start_script) (const char *script, int argc, const char **argv);
+	int (*flush_script) (void);
 	int (*stop_script) (void);
 	void (*process_event) (union perf_event *event,
 			       struct perf_sample *sample,
diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c
index e52e7461911b97..24e8d871b74e51 100644
--- a/tools/perf/util/util.c
+++ b/tools/perf/util/util.c
@@ -13,6 +13,7 @@
 #include <limits.h>
 #include <byteswap.h>
 #include <linux/kernel.h>
+#include <unistd.h>
 
 /*
  * XXX We need to find a better place for these things...
@@ -282,6 +283,18 @@ void get_term_dimensions(struct winsize *ws)
 	ws->ws_col = 80;
 }
 
+void set_term_quiet_input(struct termios *old)
+{
+	struct termios tc;
+
+	tcgetattr(0, old);
+	tc = *old;
+	tc.c_lflag &= ~(ICANON | ECHO);
+	tc.c_cc[VMIN] = 0;
+	tc.c_cc[VTIME] = 0;
+	tcsetattr(0, TCSANOW, &tc);
+}
+
 static void set_tracing_events_path(const char *mountpoint)
 {
 	snprintf(tracing_events_path, sizeof(tracing_events_path), "%s/%s",
@@ -443,6 +456,7 @@ int filename__read_str(const char *filename, char **buf, size_t *sizep)
 	size_t size = 0, alloc_size = 0;
 	void *bf = NULL, *nbf;
 	int fd, n, err = 0;
+	char sbuf[STRERR_BUFSIZE];
 
 	fd = open(filename, O_RDONLY);
 	if (fd < 0)
@@ -463,8 +477,8 @@ int filename__read_str(const char *filename, char **buf, size_t *sizep)
 		n = read(fd, bf + size, alloc_size - size);
 		if (n < 0) {
 			if (size) {
-				pr_warning("read failed %d: %s\n",
-					   errno, strerror(errno));
+				pr_warning("read failed %d: %s\n", errno,
+					 strerror_r(errno, sbuf, sizeof(sbuf)));
 				err = 0;
 			} else
 				err = -errno;
@@ -536,3 +550,39 @@ void mem_bswap_64(void *src, int byte_size)
 		++m;
 	}
 }
+
+bool find_process(const char *name)
+{
+	size_t len = strlen(name);
+	DIR *dir;
+	struct dirent *d;
+	int ret = -1;
+
+	dir = opendir(procfs__mountpoint());
+	if (!dir)
+		return -1;
+
+	/* Walk through the directory. */
+	while (ret && (d = readdir(dir)) != NULL) {
+		char path[PATH_MAX];
+		char *data;
+		size_t size;
+
+		if ((d->d_type != DT_DIR) ||
+		     !strcmp(".", d->d_name) ||
+		     !strcmp("..", d->d_name))
+			continue;
+
+		scnprintf(path, sizeof(path), "%s/%s/comm",
+			  procfs__mountpoint(), d->d_name);
+
+		if (filename__read_str(path, &data, &size))
+			continue;
+
+		ret = strncmp(name, data, len);
+		free(data);
+	}
+
+	closedir(dir);
+	return ret ? false : true;
+}
diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h
index 66864364ccb482..d6a79b1fb28ced 100644
--- a/tools/perf/util/util.h
+++ b/tools/perf/util/util.h
@@ -68,12 +68,14 @@
 #include <sys/socket.h>
 #include <sys/ioctl.h>
 #include <inttypes.h>
+#include <linux/kernel.h>
 #include <linux/magic.h>
 #include <linux/types.h>
 #include <sys/ttydefaults.h>
 #include <api/fs/debugfs.h>
 #include <termios.h>
 #include <linux/bitops.h>
+#include <termios.h>
 
 extern const char *graph_line;
 extern const char *graph_dotted_line;
@@ -307,6 +309,7 @@ extern unsigned int page_size;
 extern int cacheline_size;
 
 void get_term_dimensions(struct winsize *ws);
+void set_term_quiet_input(struct termios *old);
 
 struct parse_tag {
 	char tag;
@@ -317,6 +320,21 @@ unsigned long parse_tag_value(const char *str, struct parse_tag *tags);
 
 #define SRCLINE_UNKNOWN  ((char *) "??:0")
 
+static inline int path__join(char *bf, size_t size,
+			     const char *path1, const char *path2)
+{
+	return scnprintf(bf, size, "%s%s%s", path1, path1[0] ? "/" : "", path2);
+}
+
+static inline int path__join3(char *bf, size_t size,
+			      const char *path1, const char *path2,
+			      const char *path3)
+{
+	return scnprintf(bf, size, "%s%s%s%s%s",
+			 path1, path1[0] ? "/" : "",
+			 path2, path2[0] ? "/" : "", path3);
+}
+
 struct dso;
 
 char *get_srcline(struct dso *dso, unsigned long addr);
@@ -330,4 +348,5 @@ void mem_bswap_64(void *src, int byte_size);
 void mem_bswap_32(void *src, int byte_size);
 
 const char *get_filename_for_perf_kvm(void);
+bool find_process(const char *name);
 #endif /* GIT_COMPAT_UTIL_H */