diff --git a/arch/x86/include/uapi/asm/msr-index.h b/arch/x86/include/uapi/asm/msr-index.h
index 892ce40..b31798d 100644
--- a/arch/x86/include/uapi/asm/msr-index.h
+++ b/arch/x86/include/uapi/asm/msr-index.h
@@ -71,6 +71,7 @@
 #define MSR_IA32_PEBS_ENABLE		0x000003f1
 #define MSR_IA32_DS_AREA		0x00000600
 #define MSR_IA32_PERF_CAPABILITIES	0x00000345
+#define MSR_PEBS_LD_LAT_THRESHOLD	0x000003f6
 
 #define MSR_MTRRfix64K_00000		0x00000250
 #define MSR_MTRRfix16K_80000		0x00000258
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index bf0f01a..5ed7a4c 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -1316,9 +1316,16 @@
  */
 static void __init filter_events(struct attribute **attrs)
 {
+	struct device_attribute *d;
+	struct perf_pmu_events_attr *pmu_attr;
 	int i, j;
 
 	for (i = 0; attrs[i]; i++) {
+		d = (struct device_attribute *)attrs[i];
+		pmu_attr = container_of(d, struct perf_pmu_events_attr, attr);
+		/* str trumps id */
+		if (pmu_attr->event_str)
+			continue;
 		if (x86_pmu.event_map(i))
 			continue;
 
@@ -1330,23 +1337,46 @@
 	}
 }
 
-static ssize_t events_sysfs_show(struct device *dev, struct device_attribute *attr,
+/* Merge two pointer arrays */
+static __init struct attribute **merge_attr(struct attribute **a, struct attribute **b)
+{
+	struct attribute **new;
+	int j, i;
+
+	for (j = 0; a[j]; j++)
+		;
+	for (i = 0; b[i]; i++)
+		j++;
+	j++;
+
+	new = kmalloc(sizeof(struct attribute *) * j, GFP_KERNEL);
+	if (!new)
+		return NULL;
+
+	j = 0;
+	for (i = 0; a[i]; i++)
+		new[j++] = a[i];
+	for (i = 0; b[i]; i++)
+		new[j++] = b[i];
+	new[j] = NULL;
+
+	return new;
+}
+
+ssize_t events_sysfs_show(struct device *dev, struct device_attribute *attr,
 			  char *page)
 {
 	struct perf_pmu_events_attr *pmu_attr = \
 		container_of(attr, struct perf_pmu_events_attr, attr);
-
 	u64 config = x86_pmu.event_map(pmu_attr->id);
+
+	/* string trumps id */
+	if (pmu_attr->event_str)
+		return sprintf(page, "%s", pmu_attr->event_str);
+
 	return x86_pmu.events_sysfs_show(page, config);
 }
 
-#define EVENT_VAR(_id)  event_attr_##_id
-#define EVENT_PTR(_id) &event_attr_##_id.attr.attr
-
-#define EVENT_ATTR(_name, _id)						\
-	PMU_EVENT_ATTR(_name, EVENT_VAR(_id), PERF_COUNT_HW_##_id,	\
-			events_sysfs_show)
-
 EVENT_ATTR(cpu-cycles,			CPU_CYCLES		);
 EVENT_ATTR(instructions,		INSTRUCTIONS		);
 EVENT_ATTR(cache-references,		CACHE_REFERENCES	);
@@ -1459,16 +1489,27 @@
 
 	unconstrained = (struct event_constraint)
 		__EVENT_CONSTRAINT(0, (1ULL << x86_pmu.num_counters) - 1,
-				   0, x86_pmu.num_counters, 0);
+				   0, x86_pmu.num_counters, 0, 0);
 
 	x86_pmu.attr_rdpmc = 1; /* enable userspace RDPMC usage by default */
 	x86_pmu_format_group.attrs = x86_pmu.format_attrs;
 
+	if (x86_pmu.event_attrs)
+		x86_pmu_events_group.attrs = x86_pmu.event_attrs;
+
 	if (!x86_pmu.events_sysfs_show)
 		x86_pmu_events_group.attrs = &empty_attrs;
 	else
 		filter_events(x86_pmu_events_group.attrs);
 
+	if (x86_pmu.cpu_events) {
+		struct attribute **tmp;
+
+		tmp = merge_attr(x86_pmu_events_group.attrs, x86_pmu.cpu_events);
+		if (!WARN_ON(!tmp))
+			x86_pmu_events_group.attrs = tmp;
+	}
+
 	pr_info("... version:                %d\n",     x86_pmu.version);
 	pr_info("... bit width:              %d\n",     x86_pmu.cntval_bits);
 	pr_info("... generic registers:      %d\n",     x86_pmu.num_counters);
diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h
index 7f5c75c..ba9aadf 100644
--- a/arch/x86/kernel/cpu/perf_event.h
+++ b/arch/x86/kernel/cpu/perf_event.h
@@ -46,6 +46,7 @@
 	EXTRA_REG_RSP_0 = 0,	/* offcore_response_0 */
 	EXTRA_REG_RSP_1 = 1,	/* offcore_response_1 */
 	EXTRA_REG_LBR   = 2,	/* lbr_select */
+	EXTRA_REG_LDLAT = 3,	/* ld_lat_threshold */
 
 	EXTRA_REG_MAX		/* number of entries needed */
 };
@@ -59,7 +60,13 @@
 	u64	cmask;
 	int	weight;
 	int	overlap;
+	int	flags;
 };
+/*
+ * struct event_constraint flags
+ */
+#define PERF_X86_EVENT_PEBS_LDLAT	0x1 /* ld+ldlat data address sampling */
+#define PERF_X86_EVENT_PEBS_ST		0x2 /* st data address sampling */
 
 struct amd_nb {
 	int nb_id;  /* NorthBridge id */
@@ -170,16 +177,17 @@
 	void				*kfree_on_online;
 };
 
-#define __EVENT_CONSTRAINT(c, n, m, w, o) {\
+#define __EVENT_CONSTRAINT(c, n, m, w, o, f) {\
 	{ .idxmsk64 = (n) },		\
 	.code = (c),			\
 	.cmask = (m),			\
 	.weight = (w),			\
 	.overlap = (o),			\
+	.flags = f,			\
 }
 
 #define EVENT_CONSTRAINT(c, n, m)	\
-	__EVENT_CONSTRAINT(c, n, m, HWEIGHT(n), 0)
+	__EVENT_CONSTRAINT(c, n, m, HWEIGHT(n), 0, 0)
 
 /*
  * The overlap flag marks event constraints with overlapping counter
@@ -203,7 +211,7 @@
  * and its counter masks must be kept at a minimum.
  */
 #define EVENT_CONSTRAINT_OVERLAP(c, n, m)	\
-	__EVENT_CONSTRAINT(c, n, m, HWEIGHT(n), 1)
+	__EVENT_CONSTRAINT(c, n, m, HWEIGHT(n), 1, 0)
 
 /*
  * Constraint on the Event code.
@@ -231,6 +239,14 @@
 #define INTEL_UEVENT_CONSTRAINT(c, n)	\
 	EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK)
 
+#define INTEL_PLD_CONSTRAINT(c, n)	\
+	__EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK, \
+			   HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_LDLAT)
+
+#define INTEL_PST_CONSTRAINT(c, n)	\
+	__EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK, \
+			  HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_ST)
+
 #define EVENT_CONSTRAINT_END		\
 	EVENT_CONSTRAINT(0, 0, 0)
 
@@ -260,12 +276,22 @@
 	.msr = (ms),		\
 	.config_mask = (m),	\
 	.valid_mask = (vm),	\
-	.idx = EXTRA_REG_##i	\
+	.idx = EXTRA_REG_##i,	\
 	}
 
 #define INTEL_EVENT_EXTRA_REG(event, msr, vm, idx)	\
 	EVENT_EXTRA_REG(event, msr, ARCH_PERFMON_EVENTSEL_EVENT, vm, idx)
 
+#define INTEL_UEVENT_EXTRA_REG(event, msr, vm, idx) \
+	EVENT_EXTRA_REG(event, msr, ARCH_PERFMON_EVENTSEL_EVENT | \
+			ARCH_PERFMON_EVENTSEL_UMASK, vm, idx)
+
+#define INTEL_UEVENT_PEBS_LDLAT_EXTRA_REG(c) \
+	INTEL_UEVENT_EXTRA_REG(c, \
+			       MSR_PEBS_LD_LAT_THRESHOLD, \
+			       0xffff, \
+			       LDLAT)
+
 #define EVENT_EXTRA_END EVENT_EXTRA_REG(0, 0, 0, 0, RSP_0)
 
 union perf_capabilities {
@@ -355,8 +381,10 @@
 	 */
 	int		attr_rdpmc;
 	struct attribute **format_attrs;
+	struct attribute **event_attrs;
 
 	ssize_t		(*events_sysfs_show)(char *page, u64 config);
+	struct attribute **cpu_events;
 
 	/*
 	 * CPU Hotplug hooks
@@ -421,6 +449,23 @@
 #define ERF_NO_HT_SHARING	1
 #define ERF_HAS_RSP_1		2
 
+#define EVENT_VAR(_id)  event_attr_##_id
+#define EVENT_PTR(_id) &event_attr_##_id.attr.attr
+
+#define EVENT_ATTR(_name, _id)						\
+static struct perf_pmu_events_attr EVENT_VAR(_id) = {			\
+	.attr		= __ATTR(_name, 0444, events_sysfs_show, NULL),	\
+	.id		= PERF_COUNT_HW_##_id,				\
+	.event_str	= NULL,						\
+};
+
+#define EVENT_ATTR_STR(_name, v, str)					\
+static struct perf_pmu_events_attr event_attr_##v = {			\
+	.attr		= __ATTR(_name, 0444, events_sysfs_show, NULL),	\
+	.id		= 0,						\
+	.event_str	= str,						\
+};
+
 extern struct x86_pmu x86_pmu __read_mostly;
 
 DECLARE_PER_CPU(struct cpu_hw_events, cpu_hw_events);
@@ -628,6 +673,9 @@
 
 int knc_pmu_init(void);
 
+ssize_t events_sysfs_show(struct device *dev, struct device_attribute *attr,
+			  char *page);
+
 #else /* CONFIG_CPU_SUP_INTEL */
 
 static inline void reserve_ds_buffers(void)
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index dab7580..e84c4ba 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -81,6 +81,7 @@
 static struct extra_reg intel_nehalem_extra_regs[] __read_mostly =
 {
 	INTEL_EVENT_EXTRA_REG(0xb7, MSR_OFFCORE_RSP_0, 0xffff, RSP_0),
+	INTEL_UEVENT_PEBS_LDLAT_EXTRA_REG(0x100b),
 	EVENT_EXTRA_END
 };
 
@@ -136,6 +137,7 @@
 {
 	INTEL_EVENT_EXTRA_REG(0xb7, MSR_OFFCORE_RSP_0, 0xffff, RSP_0),
 	INTEL_EVENT_EXTRA_REG(0xbb, MSR_OFFCORE_RSP_1, 0xffff, RSP_1),
+	INTEL_UEVENT_PEBS_LDLAT_EXTRA_REG(0x100b),
 	EVENT_EXTRA_END
 };
 
@@ -155,9 +157,25 @@
 static struct extra_reg intel_snb_extra_regs[] __read_mostly = {
 	INTEL_EVENT_EXTRA_REG(0xb7, MSR_OFFCORE_RSP_0, 0x3fffffffffull, RSP_0),
 	INTEL_EVENT_EXTRA_REG(0xbb, MSR_OFFCORE_RSP_1, 0x3fffffffffull, RSP_1),
+	INTEL_UEVENT_PEBS_LDLAT_EXTRA_REG(0x01cd),
 	EVENT_EXTRA_END
 };
 
+EVENT_ATTR_STR(mem-loads, mem_ld_nhm, "event=0x0b,umask=0x10,ldlat=3");
+EVENT_ATTR_STR(mem-loads, mem_ld_snb, "event=0xcd,umask=0x1,ldlat=3");
+EVENT_ATTR_STR(mem-stores, mem_st_snb, "event=0xcd,umask=0x2");
+
+struct attribute *nhm_events_attrs[] = {
+	EVENT_PTR(mem_ld_nhm),
+	NULL,
+};
+
+struct attribute *snb_events_attrs[] = {
+	EVENT_PTR(mem_ld_snb),
+	EVENT_PTR(mem_st_snb),
+	NULL,
+};
+
 static u64 intel_pmu_event_map(int hw_event)
 {
 	return intel_perfmon_event_map[hw_event];
@@ -1392,8 +1410,11 @@
 
 	if (x86_pmu.event_constraints) {
 		for_each_event_constraint(c, x86_pmu.event_constraints) {
-			if ((event->hw.config & c->cmask) == c->code)
+			if ((event->hw.config & c->cmask) == c->code) {
+				/* hw.flags zeroed at initialization */
+				event->hw.flags |= c->flags;
 				return c;
+			}
 		}
 	}
 
@@ -1438,6 +1459,7 @@
 static void intel_put_event_constraints(struct cpu_hw_events *cpuc,
 					struct perf_event *event)
 {
+	event->hw.flags = 0;
 	intel_put_shared_regs_event_constraints(cpuc, event);
 }
 
@@ -1761,6 +1783,8 @@
 
 PMU_FORMAT_ATTR(offcore_rsp, "config1:0-63");
 
+PMU_FORMAT_ATTR(ldlat, "config1:0-15");
+
 static struct attribute *intel_arch3_formats_attr[] = {
 	&format_attr_event.attr,
 	&format_attr_umask.attr,
@@ -1771,6 +1795,7 @@
 	&format_attr_cmask.attr,
 
 	&format_attr_offcore_rsp.attr, /* XXX do NHM/WSM + SNB breakout */
+	&format_attr_ldlat.attr, /* PEBS load latency */
 	NULL,
 };
 
@@ -2031,6 +2056,8 @@
 		x86_pmu.enable_all = intel_pmu_nhm_enable_all;
 		x86_pmu.extra_regs = intel_nehalem_extra_regs;
 
+		x86_pmu.cpu_events = nhm_events_attrs;
+
 		/* UOPS_ISSUED.STALLED_CYCLES */
 		intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] =
 			X86_CONFIG(.event=0x0e, .umask=0x01, .inv=1, .cmask=1);
@@ -2074,6 +2101,8 @@
 		x86_pmu.extra_regs = intel_westmere_extra_regs;
 		x86_pmu.er_flags |= ERF_HAS_RSP_1;
 
+		x86_pmu.cpu_events = nhm_events_attrs;
+
 		/* UOPS_ISSUED.STALLED_CYCLES */
 		intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] =
 			X86_CONFIG(.event=0x0e, .umask=0x01, .inv=1, .cmask=1);
@@ -2102,6 +2131,8 @@
 		x86_pmu.er_flags |= ERF_HAS_RSP_1;
 		x86_pmu.er_flags |= ERF_NO_HT_SHARING;
 
+		x86_pmu.cpu_events = snb_events_attrs;
+
 		/* UOPS_ISSUED.ANY,c=1,i=1 to count stall cycles */
 		intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] =
 			X86_CONFIG(.event=0x0e, .umask=0x01, .inv=1, .cmask=1);
@@ -2128,6 +2159,8 @@
 		x86_pmu.er_flags |= ERF_HAS_RSP_1;
 		x86_pmu.er_flags |= ERF_NO_HT_SHARING;
 
+		x86_pmu.cpu_events = snb_events_attrs;
+
 		/* UOPS_ISSUED.ANY,c=1,i=1 to count stall cycles */
 		intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] =
 			X86_CONFIG(.event=0x0e, .umask=0x01, .inv=1, .cmask=1);
diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c
index 826054a..36dc13d1 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_ds.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c
@@ -24,6 +24,130 @@
 
  */
 
+union intel_x86_pebs_dse {
+	u64 val;
+	struct {
+		unsigned int ld_dse:4;
+		unsigned int ld_stlb_miss:1;
+		unsigned int ld_locked:1;
+		unsigned int ld_reserved:26;
+	};
+	struct {
+		unsigned int st_l1d_hit:1;
+		unsigned int st_reserved1:3;
+		unsigned int st_stlb_miss:1;
+		unsigned int st_locked:1;
+		unsigned int st_reserved2:26;
+	};
+};
+
+
+/*
+ * Map PEBS Load Latency Data Source encodings to generic
+ * memory data source information
+ */
+#define P(a, b) PERF_MEM_S(a, b)
+#define OP_LH (P(OP, LOAD) | P(LVL, HIT))
+#define SNOOP_NONE_MISS (P(SNOOP, NONE) | P(SNOOP, MISS))
+
+static const u64 pebs_data_source[] = {
+	P(OP, LOAD) | P(LVL, MISS) | P(LVL, L3) | P(SNOOP, NA),/* 0x00:ukn L3 */
+	OP_LH | P(LVL, L1)  | P(SNOOP, NONE),	/* 0x01: L1 local */
+	OP_LH | P(LVL, LFB) | P(SNOOP, NONE),	/* 0x02: LFB hit */
+	OP_LH | P(LVL, L2)  | P(SNOOP, NONE),	/* 0x03: L2 hit */
+	OP_LH | P(LVL, L3)  | P(SNOOP, NONE),	/* 0x04: L3 hit */
+	OP_LH | P(LVL, L3)  | P(SNOOP, MISS),	/* 0x05: L3 hit, snoop miss */
+	OP_LH | P(LVL, L3)  | P(SNOOP, HIT),	/* 0x06: L3 hit, snoop hit */
+	OP_LH | P(LVL, L3)  | P(SNOOP, HITM),	/* 0x07: L3 hit, snoop hitm */
+	OP_LH | P(LVL, REM_CCE1) | P(SNOOP, HIT),  /* 0x08: L3 miss snoop hit */
+	OP_LH | P(LVL, REM_CCE1) | P(SNOOP, HITM), /* 0x09: L3 miss snoop hitm*/
+	OP_LH | P(LVL, LOC_RAM)  | P(SNOOP, HIT),  /* 0x0a: L3 miss, shared */
+	OP_LH | P(LVL, REM_RAM1) | P(SNOOP, HIT),  /* 0x0b: L3 miss, shared */
+	OP_LH | P(LVL, LOC_RAM)  | SNOOP_NONE_MISS,/* 0x0c: L3 miss, excl */
+	OP_LH | P(LVL, REM_RAM1) | SNOOP_NONE_MISS,/* 0x0d: L3 miss, excl */
+	OP_LH | P(LVL, IO)  | P(SNOOP, NONE), /* 0x0e: I/O */
+	OP_LH | P(LVL, UNC) | P(SNOOP, NONE), /* 0x0f: uncached */
+};
+
+static u64 precise_store_data(u64 status)
+{
+	union intel_x86_pebs_dse dse;
+	u64 val = P(OP, STORE) | P(SNOOP, NA) | P(LVL, L1) | P(TLB, L2);
+
+	dse.val = status;
+
+	/*
+	 * bit 4: TLB access
+	 * 1 = stored missed 2nd level TLB
+	 *
+	 * so it either hit the walker or the OS
+	 * otherwise hit 2nd level TLB
+	 */
+	if (dse.st_stlb_miss)
+		val |= P(TLB, MISS);
+	else
+		val |= P(TLB, HIT);
+
+	/*
+	 * bit 0: hit L1 data cache
+	 * if not set, then all we know is that
+	 * it missed L1D
+	 */
+	if (dse.st_l1d_hit)
+		val |= P(LVL, HIT);
+	else
+		val |= P(LVL, MISS);
+
+	/*
+	 * bit 5: Locked prefix
+	 */
+	if (dse.st_locked)
+		val |= P(LOCK, LOCKED);
+
+	return val;
+}
+
+static u64 load_latency_data(u64 status)
+{
+	union intel_x86_pebs_dse dse;
+	u64 val;
+	int model = boot_cpu_data.x86_model;
+	int fam = boot_cpu_data.x86;
+
+	dse.val = status;
+
+	/*
+	 * use the mapping table for bit 0-3
+	 */
+	val = pebs_data_source[dse.ld_dse];
+
+	/*
+	 * Nehalem models do not support TLB, Lock infos
+	 */
+	if (fam == 0x6 && (model == 26 || model == 30
+	    || model == 31 || model == 46)) {
+		val |= P(TLB, NA) | P(LOCK, NA);
+		return val;
+	}
+	/*
+	 * bit 4: TLB access
+	 * 0 = did not miss 2nd level TLB
+	 * 1 = missed 2nd level TLB
+	 */
+	if (dse.ld_stlb_miss)
+		val |= P(TLB, MISS) | P(TLB, L2);
+	else
+		val |= P(TLB, HIT) | P(TLB, L1) | P(TLB, L2);
+
+	/*
+	 * bit 5: locked prefix
+	 */
+	if (dse.ld_locked)
+		val |= P(LOCK, LOCKED);
+
+	return val;
+}
+
 struct pebs_record_core {
 	u64 flags, ip;
 	u64 ax, bx, cx, dx;
@@ -364,7 +488,7 @@
 };
 
 struct event_constraint intel_nehalem_pebs_event_constraints[] = {
-	INTEL_EVENT_CONSTRAINT(0x0b, 0xf),    /* MEM_INST_RETIRED.* */
+	INTEL_PLD_CONSTRAINT(0x100b, 0xf),      /* MEM_INST_RETIRED.* */
 	INTEL_EVENT_CONSTRAINT(0x0f, 0xf),    /* MEM_UNCORE_RETIRED.* */
 	INTEL_UEVENT_CONSTRAINT(0x010c, 0xf), /* MEM_STORE_RETIRED.DTLB_MISS */
 	INTEL_EVENT_CONSTRAINT(0xc0, 0xf),    /* INST_RETIRED.ANY */
@@ -379,7 +503,7 @@
 };
 
 struct event_constraint intel_westmere_pebs_event_constraints[] = {
-	INTEL_EVENT_CONSTRAINT(0x0b, 0xf),    /* MEM_INST_RETIRED.* */
+	INTEL_PLD_CONSTRAINT(0x100b, 0xf),      /* MEM_INST_RETIRED.* */
 	INTEL_EVENT_CONSTRAINT(0x0f, 0xf),    /* MEM_UNCORE_RETIRED.* */
 	INTEL_UEVENT_CONSTRAINT(0x010c, 0xf), /* MEM_STORE_RETIRED.DTLB_MISS */
 	INTEL_EVENT_CONSTRAINT(0xc0, 0xf),    /* INSTR_RETIRED.* */
@@ -399,7 +523,8 @@
 	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_EVENT_CONSTRAINT(0xcd, 0x8),    /* MEM_TRANS_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.* */
@@ -413,7 +538,8 @@
         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_EVENT_CONSTRAINT(0xcd, 0x8),    /* MEM_TRANS_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.* */
@@ -430,8 +556,10 @@
 
 	if (x86_pmu.pebs_constraints) {
 		for_each_event_constraint(c, x86_pmu.pebs_constraints) {
-			if ((event->hw.config & c->cmask) == c->code)
+			if ((event->hw.config & c->cmask) == c->code) {
+				event->hw.flags |= c->flags;
 				return c;
+			}
 		}
 	}
 
@@ -446,6 +574,11 @@
 	hwc->config &= ~ARCH_PERFMON_EVENTSEL_INT;
 
 	cpuc->pebs_enabled |= 1ULL << hwc->idx;
+
+	if (event->hw.flags & PERF_X86_EVENT_PEBS_LDLAT)
+		cpuc->pebs_enabled |= 1ULL << (hwc->idx + 32);
+	else if (event->hw.flags & PERF_X86_EVENT_PEBS_ST)
+		cpuc->pebs_enabled |= 1ULL << 63;
 }
 
 void intel_pmu_pebs_disable(struct perf_event *event)
@@ -558,20 +691,51 @@
 				   struct pt_regs *iregs, void *__pebs)
 {
 	/*
-	 * We cast to pebs_record_core since that is a subset of
-	 * both formats and we don't use the other fields in this
-	 * routine.
+	 * We cast to pebs_record_nhm to get the load latency data
+	 * if extra_reg MSR_PEBS_LD_LAT_THRESHOLD used
 	 */
 	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
-	struct pebs_record_core *pebs = __pebs;
+	struct pebs_record_nhm *pebs = __pebs;
 	struct perf_sample_data data;
 	struct pt_regs regs;
+	u64 sample_type;
+	int fll, fst;
 
 	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_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
+	 */
+	if (fll || fst) {
+		if (sample_type & PERF_SAMPLE_ADDR)
+			data.addr = pebs->dla;
+
+		/*
+		 * 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
+				data.data_src.val = precise_store_data(pebs->dse);
+		}
+	}
+
 	/*
 	 * We use the interrupt regs as a base because the PEBS record
 	 * does not contain a full regs set, specifically it seems to
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.c b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
index b43200d..75da9e1 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
@@ -2438,7 +2438,7 @@
 
 	type->unconstrainted = (struct event_constraint)
 		__EVENT_CONSTRAINT(0, (1ULL << type->num_counters) - 1,
-				0, type->num_counters, 0);
+				0, type->num_counters, 0, 0);
 
 	for (i = 0; i < type->num_boxes; i++) {
 		pmus[i].func_id = -1;
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 8737e1c..42a6daa 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -127,6 +127,7 @@
 			int		event_base_rdpmc;
 			int		idx;
 			int		last_cpu;
+			int		flags;
 
 			struct hw_perf_event_extra extra_reg;
 			struct hw_perf_event_extra branch_reg;
@@ -567,11 +568,13 @@
 		u32	reserved;
 	}				cpu_entry;
 	u64				period;
+	union  perf_mem_data_src	data_src;
 	struct perf_callchain_entry	*callchain;
 	struct perf_raw_record		*raw;
 	struct perf_branch_stack	*br_stack;
 	struct perf_regs_user		regs_user;
 	u64				stack_user_size;
+	u64				weight;
 };
 
 static inline void perf_sample_data_init(struct perf_sample_data *data,
@@ -585,6 +588,8 @@
 	data->regs_user.abi = PERF_SAMPLE_REGS_ABI_NONE;
 	data->regs_user.regs = NULL;
 	data->stack_user_size = 0;
+	data->weight = 0;
+	data->data_src.val = 0;
 }
 
 extern void perf_output_sample(struct perf_output_handle *handle,
@@ -809,6 +814,7 @@
 struct perf_pmu_events_attr {
 	struct device_attribute attr;
 	u64 id;
+	const char *event_str;
 };
 
 #define PMU_EVENT_ATTR(_name, _var, _id, _show)				\
diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h
index 9fa9c62..964a450 100644
--- a/include/uapi/linux/perf_event.h
+++ b/include/uapi/linux/perf_event.h
@@ -132,8 +132,10 @@
 	PERF_SAMPLE_BRANCH_STACK		= 1U << 11,
 	PERF_SAMPLE_REGS_USER			= 1U << 12,
 	PERF_SAMPLE_STACK_USER			= 1U << 13,
+	PERF_SAMPLE_WEIGHT			= 1U << 14,
+	PERF_SAMPLE_DATA_SRC			= 1U << 15,
 
-	PERF_SAMPLE_MAX = 1U << 14,		/* non-ABI */
+	PERF_SAMPLE_MAX = 1U << 16,		/* non-ABI */
 };
 
 /*
@@ -443,6 +445,7 @@
 #define PERF_RECORD_MISC_GUEST_KERNEL		(4 << 0)
 #define PERF_RECORD_MISC_GUEST_USER		(5 << 0)
 
+#define PERF_RECORD_MISC_MMAP_DATA		(1 << 13)
 /*
  * Indicates that the content of PERF_SAMPLE_IP points to
  * the actual instruction that triggered the event. See also
@@ -588,6 +591,9 @@
 	 * 	{ u64			size;
 	 * 	  char			data[size];
 	 * 	  u64			dyn_size; } && PERF_SAMPLE_STACK_USER
+	 *
+	 *	{ u64			weight;   } && PERF_SAMPLE_WEIGHT
+	 *	{ u64			data_src;     } && PERF_SAMPLE_DATA_SRC
 	 * };
 	 */
 	PERF_RECORD_SAMPLE			= 9,
@@ -613,4 +619,67 @@
 #define PERF_FLAG_FD_OUTPUT		(1U << 1)
 #define PERF_FLAG_PID_CGROUP		(1U << 2) /* pid=cgroup id, per-cpu mode only */
 
+union perf_mem_data_src {
+	__u64 val;
+	struct {
+		__u64   mem_op:5,	/* type of opcode */
+			mem_lvl:14,	/* memory hierarchy level */
+			mem_snoop:5,	/* snoop mode */
+			mem_lock:2,	/* lock instr */
+			mem_dtlb:7,	/* tlb access */
+			mem_rsvd:31;
+	};
+};
+
+/* type of opcode (load/store/prefetch,code) */
+#define PERF_MEM_OP_NA		0x01 /* not available */
+#define PERF_MEM_OP_LOAD	0x02 /* load instruction */
+#define PERF_MEM_OP_STORE	0x04 /* store instruction */
+#define PERF_MEM_OP_PFETCH	0x08 /* prefetch */
+#define PERF_MEM_OP_EXEC	0x10 /* code (execution) */
+#define PERF_MEM_OP_SHIFT	0
+
+/* memory hierarchy (memory level, hit or miss) */
+#define PERF_MEM_LVL_NA		0x01  /* not available */
+#define PERF_MEM_LVL_HIT	0x02  /* hit level */
+#define PERF_MEM_LVL_MISS	0x04  /* miss level  */
+#define PERF_MEM_LVL_L1		0x08  /* L1 */
+#define PERF_MEM_LVL_LFB	0x10  /* Line Fill Buffer */
+#define PERF_MEM_LVL_L2		0x20  /* L2 hit */
+#define PERF_MEM_LVL_L3		0x40  /* L3 hit */
+#define PERF_MEM_LVL_LOC_RAM	0x80  /* Local DRAM */
+#define PERF_MEM_LVL_REM_RAM1	0x100 /* Remote DRAM (1 hop) */
+#define PERF_MEM_LVL_REM_RAM2	0x200 /* Remote DRAM (2 hops) */
+#define PERF_MEM_LVL_REM_CCE1	0x400 /* Remote Cache (1 hop) */
+#define PERF_MEM_LVL_REM_CCE2	0x800 /* Remote Cache (2 hops) */
+#define PERF_MEM_LVL_IO		0x1000 /* I/O memory */
+#define PERF_MEM_LVL_UNC	0x2000 /* Uncached memory */
+#define PERF_MEM_LVL_SHIFT	5
+
+/* snoop mode */
+#define PERF_MEM_SNOOP_NA	0x01 /* not available */
+#define PERF_MEM_SNOOP_NONE	0x02 /* no snoop */
+#define PERF_MEM_SNOOP_HIT	0x04 /* snoop hit */
+#define PERF_MEM_SNOOP_MISS	0x08 /* snoop miss */
+#define PERF_MEM_SNOOP_HITM	0x10 /* snoop hit modified */
+#define PERF_MEM_SNOOP_SHIFT	19
+
+/* locked instruction */
+#define PERF_MEM_LOCK_NA	0x01 /* not available */
+#define PERF_MEM_LOCK_LOCKED	0x02 /* locked transaction */
+#define PERF_MEM_LOCK_SHIFT	24
+
+/* TLB access */
+#define PERF_MEM_TLB_NA		0x01 /* not available */
+#define PERF_MEM_TLB_HIT	0x02 /* hit level */
+#define PERF_MEM_TLB_MISS	0x04 /* miss level */
+#define PERF_MEM_TLB_L1		0x08 /* L1 */
+#define PERF_MEM_TLB_L2		0x10 /* L2 */
+#define PERF_MEM_TLB_WK		0x20 /* Hardware Walker*/
+#define PERF_MEM_TLB_OS		0x40 /* OS fault handler */
+#define PERF_MEM_TLB_SHIFT	26
+
+#define PERF_MEM_S(a, s) \
+	(((u64)PERF_MEM_##a##_##s) << PERF_MEM_##a##_SHIFT)
+
 #endif /* _UAPI_LINUX_PERF_EVENT_H */
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 7b4a55d..98c0845 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -976,9 +976,15 @@
 	if (sample_type & PERF_SAMPLE_PERIOD)
 		size += sizeof(data->period);
 
+	if (sample_type & PERF_SAMPLE_WEIGHT)
+		size += sizeof(data->weight);
+
 	if (sample_type & PERF_SAMPLE_READ)
 		size += event->read_size;
 
+	if (sample_type & PERF_SAMPLE_DATA_SRC)
+		size += sizeof(data->data_src.val);
+
 	event->header_size = size;
 }
 
@@ -4193,6 +4199,12 @@
 		perf_output_sample_ustack(handle,
 					  data->stack_user_size,
 					  data->regs_user.regs);
+
+	if (sample_type & PERF_SAMPLE_WEIGHT)
+		perf_output_put(handle, data->weight);
+
+	if (sample_type & PERF_SAMPLE_DATA_SRC)
+		perf_output_put(handle, data->data_src.val);
 }
 
 void perf_prepare_sample(struct perf_event_header *header,
@@ -4779,6 +4791,9 @@
 	mmap_event->file_name = name;
 	mmap_event->file_size = size;
 
+	if (!(vma->vm_flags & VM_EXEC))
+		mmap_event->event_id.header.misc |= PERF_RECORD_MISC_MMAP_DATA;
+
 	mmap_event->event_id.header.size = sizeof(mmap_event->event_id) + size;
 
 	rcu_read_lock();
diff --git a/tools/perf/Documentation/perf-mem.txt b/tools/perf/Documentation/perf-mem.txt
new file mode 100644
index 0000000..888d511
--- /dev/null
+++ b/tools/perf/Documentation/perf-mem.txt
@@ -0,0 +1,48 @@
+perf-mem(1)
+===========
+
+NAME
+----
+perf-mem - Profile memory accesses
+
+SYNOPSIS
+--------
+[verse]
+'perf mem' [<options>] (record [<command>] | report)
+
+DESCRIPTION
+-----------
+"perf mem -t <TYPE> record" runs a command and gathers memory operation data
+from it, into perf.data. Perf record options are accepted and are passed through.
+
+"perf mem -t <TYPE> report" displays the result. It invokes perf report with the
+right set of options to display a memory access profile.
+
+OPTIONS
+-------
+<command>...::
+	Any command you can specify in a shell.
+
+-t::
+--type=::
+	Select the memory operation type: load or store (default: load)
+
+-D::
+--dump-raw-samples=::
+	Dump the raw decoded samples on the screen in a format that is easy to parse with
+	one sample per line.
+
+-x::
+--field-separator::
+	Specify the field separator used when dump raw samples (-D option). By default,
+	The separator is the space character.
+
+-C::
+--cpu-list::
+	Restrict dump of raw samples to those provided via this option. Note that the same
+	option can be passed in record mode. It will be interpreted the same way as perf
+	record.
+
+SEE ALSO
+--------
+linkperf:perf-record[1], linkperf:perf-report[1]
diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt
index 938e890..d4da111 100644
--- a/tools/perf/Documentation/perf-record.txt
+++ b/tools/perf/Documentation/perf-record.txt
@@ -182,6 +182,12 @@
 The various filters must be specified as a comma separated list: --branch-filter any_ret,u,k
 Note that this feature may not be available on all processors.
 
+-W::
+--weight::
+Enable weightened sampling. An additional weight is recorded per sample and can be
+displayed with the weight and local_weight sort keys.  This currently works for TSX
+abort events and some memory events in precise mode on modern Intel CPUs.
+
 SEE ALSO
 --------
 linkperf:perf-stat[1], linkperf:perf-list[1]
diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt
index 02284a0..7d5f4f3 100644
--- a/tools/perf/Documentation/perf-report.txt
+++ b/tools/perf/Documentation/perf-report.txt
@@ -59,7 +59,7 @@
 --sort=::
 	Sort histogram entries by given key(s) - multiple keys can be specified
 	in CSV format.  Following sort keys are available:
-	pid, comm, dso, symbol, parent, cpu, srcline.
+	pid, comm, dso, symbol, parent, cpu, srcline, weight, local_weight.
 
 	Each key has following meaning:
 
@@ -206,6 +206,10 @@
 --group::
 	Show event group information together.
 
+--demangle::
+	Demangle symbol names to human readable form. It's enabled by default,
+	disable with --no-demangle.
+
 SEE ALSO
 --------
 linkperf:perf-stat[1], linkperf:perf-annotate[1]
diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt
index 23e587a..2fe87fb 100644
--- a/tools/perf/Documentation/perf-stat.txt
+++ b/tools/perf/Documentation/perf-stat.txt
@@ -119,13 +119,19 @@
 	Print count deltas every N milliseconds (minimum: 100ms)
 	example: perf stat -I 1000 -e cycles -a sleep 5
 
---aggr-socket::
+--per-socket::
 Aggregate counts per processor socket for system-wide mode measurements.  This
 is a useful mode to detect imbalance between sockets.  To enable this mode,
-use --aggr-socket in addition to -a. (system-wide).  The output includes the
+use --per-socket in addition to -a. (system-wide).  The output includes the
 socket number and the number of online processors on that socket. This is
 useful to gauge the amount of aggregation.
 
+--per-core::
+Aggregate counts per physical processor for system-wide mode measurements.  This
+is a useful mode to detect imbalance between physical cores.  To enable this mode,
+use --per-core in addition to -a. (system-wide).  The output includes the
+core number and the number of online logical processors on that physical processor.
+
 EXAMPLES
 --------
 
diff --git a/tools/perf/Documentation/perf-top.txt b/tools/perf/Documentation/perf-top.txt
index a414bc9..9f1a2fe 100644
--- a/tools/perf/Documentation/perf-top.txt
+++ b/tools/perf/Documentation/perf-top.txt
@@ -112,7 +112,7 @@
 
 -s::
 --sort::
-	Sort by key(s): pid, comm, dso, symbol, parent, srcline.
+	Sort by key(s): pid, comm, dso, symbol, parent, srcline, weight, local_weight.
 
 -n::
 --show-nr-samples::
diff --git a/tools/perf/Makefile b/tools/perf/Makefile
index 0230b75..b0f164b 100644
--- a/tools/perf/Makefile
+++ b/tools/perf/Makefile
@@ -35,7 +35,9 @@
 #
 # Define WERROR=0 to disable treating any warnings as errors.
 #
-# Define NO_NEWT if you do not want TUI support.
+# Define NO_NEWT if you do not want TUI support. (deprecated)
+#
+# Define NO_SLANG if you do not want TUI support.
 #
 # Define NO_GTK2 if you do not want GTK+ GUI support.
 #
@@ -104,6 +106,10 @@
 	PARSER_DEBUG_CFLAGS := -DPARSER_DEBUG
 endif
 
+ifdef NO_NEWT
+	NO_SLANG=1
+endif
+
 CFLAGS = -fno-omit-frame-pointer -ggdb3 -funwind-tables -Wall -Wextra -std=gnu99 $(CFLAGS_WERROR) $(CFLAGS_OPTIMIZE) $(EXTRA_WARNINGS) $(EXTRA_CFLAGS) $(PARSER_DEBUG_CFLAGS)
 EXTLIBS = -lpthread -lrt -lelf -lm
 ALL_CFLAGS = $(CFLAGS) -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64 -D_GNU_SOURCE
@@ -272,7 +278,7 @@
 python-clean := rm -rf $(PYTHON_EXTBUILD) $(OUTPUT)python/perf.so
 
 PYTHON_EXT_SRCS := $(shell grep -v ^\# util/python-ext-sources)
-PYTHON_EXT_DEPS := util/python-ext-sources util/setup.py
+PYTHON_EXT_DEPS := util/python-ext-sources util/setup.py $(LIBTRACEEVENT)
 
 $(OUTPUT)python/perf.so: $(PYTHON_EXT_SRCS) $(PYTHON_EXT_DEPS)
 	$(QUIET_GEN)CFLAGS='$(BASIC_CFLAGS)' $(PYTHON_WORD) util/setup.py \
@@ -547,6 +553,7 @@
 BUILTIN_OBJS += $(OUTPUT)builtin-kvm.o
 BUILTIN_OBJS += $(OUTPUT)builtin-inject.o
 BUILTIN_OBJS += $(OUTPUT)tests/builtin-test.o
+BUILTIN_OBJS += $(OUTPUT)builtin-mem.o
 
 PERFLIBS = $(LIB_FILE) $(LIBLK) $(LIBTRACEEVENT)
 
@@ -679,15 +686,15 @@
 	endif
 endif
 
-ifndef NO_NEWT
-	FLAGS_NEWT=$(ALL_CFLAGS) $(ALL_LDFLAGS) $(EXTLIBS) -lnewt
-	ifneq ($(call try-cc,$(SOURCE_NEWT),$(FLAGS_NEWT),libnewt),y)
-		msg := $(warning newt not found, disables TUI support. Please install newt-devel or libnewt-dev);
+ifndef NO_SLANG
+	FLAGS_SLANG=$(ALL_CFLAGS) $(ALL_LDFLAGS) $(EXTLIBS) -I/usr/include/slang -lslang
+	ifneq ($(call try-cc,$(SOURCE_SLANG),$(FLAGS_SLANG),libslang),y)
+		msg := $(warning slang not found, disables TUI support. Please install slang-devel or libslang-dev);
 	else
 		# Fedora has /usr/include/slang/slang.h, but ubuntu /usr/include/slang.h
 		BASIC_CFLAGS += -I/usr/include/slang
-		BASIC_CFLAGS += -DNEWT_SUPPORT
-		EXTLIBS += -lnewt -lslang
+		BASIC_CFLAGS += -DSLANG_SUPPORT
+		EXTLIBS += -lslang
 		LIB_OBJS += $(OUTPUT)ui/browser.o
 		LIB_OBJS += $(OUTPUT)ui/browsers/annotate.o
 		LIB_OBJS += $(OUTPUT)ui/browsers/hists.o
diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c
index ae36f3c..db491e9 100644
--- a/tools/perf/builtin-annotate.c
+++ b/tools/perf/builtin-annotate.c
@@ -63,7 +63,7 @@
 		return 0;
 	}
 
-	he = __hists__add_entry(&evsel->hists, al, NULL, 1);
+	he = __hists__add_entry(&evsel->hists, al, NULL, 1, 1);
 	if (he == NULL)
 		return -ENOMEM;
 
diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c
index d207a97..2d0462d 100644
--- a/tools/perf/builtin-diff.c
+++ b/tools/perf/builtin-diff.c
@@ -231,9 +231,10 @@
 }
 
 static int hists__add_entry(struct hists *self,
-			    struct addr_location *al, u64 period)
+			    struct addr_location *al, u64 period,
+			    u64 weight)
 {
-	if (__hists__add_entry(self, al, NULL, period) != NULL)
+	if (__hists__add_entry(self, al, NULL, period, weight) != NULL)
 		return 0;
 	return -ENOMEM;
 }
@@ -255,7 +256,7 @@
 	if (al.filtered)
 		return 0;
 
-	if (hists__add_entry(&evsel->hists, &al, sample->period)) {
+	if (hists__add_entry(&evsel->hists, &al, sample->period, sample->weight)) {
 		pr_warning("problem incrementing symbol period, skipping event\n");
 		return -1;
 	}
diff --git a/tools/perf/builtin-mem.c b/tools/perf/builtin-mem.c
new file mode 100644
index 0000000..a8ff6d2
--- /dev/null
+++ b/tools/perf/builtin-mem.c
@@ -0,0 +1,242 @@
+#include "builtin.h"
+#include "perf.h"
+
+#include "util/parse-options.h"
+#include "util/trace-event.h"
+#include "util/tool.h"
+#include "util/session.h"
+
+#define MEM_OPERATION_LOAD	"load"
+#define MEM_OPERATION_STORE	"store"
+
+static const char	*mem_operation		= MEM_OPERATION_LOAD;
+
+struct perf_mem {
+	struct perf_tool	tool;
+	char const		*input_name;
+	symbol_filter_t		annotate_init;
+	bool			hide_unresolved;
+	bool			dump_raw;
+	const char		*cpu_list;
+	DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS);
+};
+
+static const char * const mem_usage[] = {
+	"perf mem [<options>] {record <command> |report}",
+	NULL
+};
+
+static int __cmd_record(int argc, const char **argv)
+{
+	int rec_argc, i = 0, j;
+	const char **rec_argv;
+	char event[64];
+	int ret;
+
+	rec_argc = argc + 4;
+	rec_argv = calloc(rec_argc + 1, sizeof(char *));
+	if (!rec_argv)
+		return -1;
+
+	rec_argv[i++] = strdup("record");
+	if (!strcmp(mem_operation, MEM_OPERATION_LOAD))
+		rec_argv[i++] = strdup("-W");
+	rec_argv[i++] = strdup("-d");
+	rec_argv[i++] = strdup("-e");
+
+	if (strcmp(mem_operation, MEM_OPERATION_LOAD))
+		sprintf(event, "cpu/mem-stores/pp");
+	else
+		sprintf(event, "cpu/mem-loads/pp");
+
+	rec_argv[i++] = strdup(event);
+	for (j = 1; j < argc; j++, i++)
+		rec_argv[i] = argv[j];
+
+	ret = cmd_record(i, rec_argv, NULL);
+	free(rec_argv);
+	return ret;
+}
+
+static int
+dump_raw_samples(struct perf_tool *tool,
+		 union perf_event *event,
+		 struct perf_sample *sample,
+		 struct perf_evsel *evsel __maybe_unused,
+		 struct machine *machine)
+{
+	struct perf_mem *mem = container_of(tool, struct perf_mem, tool);
+	struct addr_location al;
+	const char *fmt;
+
+	if (perf_event__preprocess_sample(event, machine, &al, sample,
+				mem->annotate_init) < 0) {
+		fprintf(stderr, "problem processing %d event, skipping it.\n",
+				event->header.type);
+		return -1;
+	}
+
+	if (al.filtered || (mem->hide_unresolved && al.sym == NULL))
+		return 0;
+
+	if (al.map != NULL)
+		al.map->dso->hit = 1;
+
+	if (symbol_conf.field_sep) {
+		fmt = "%d%s%d%s0x%"PRIx64"%s0x%"PRIx64"%s%"PRIu64
+		      "%s0x%"PRIx64"%s%s:%s\n";
+	} else {
+		fmt = "%5d%s%5d%s0x%016"PRIx64"%s0x016%"PRIx64
+		      "%s%5"PRIu64"%s0x%06"PRIx64"%s%s:%s\n";
+		symbol_conf.field_sep = " ";
+	}
+
+	printf(fmt,
+		sample->pid,
+		symbol_conf.field_sep,
+		sample->tid,
+		symbol_conf.field_sep,
+		event->ip.ip,
+		symbol_conf.field_sep,
+		sample->addr,
+		symbol_conf.field_sep,
+		sample->weight,
+		symbol_conf.field_sep,
+		sample->data_src,
+		symbol_conf.field_sep,
+		al.map ? (al.map->dso ? al.map->dso->long_name : "???") : "???",
+		al.sym ? al.sym->name : "???");
+
+	return 0;
+}
+
+static int process_sample_event(struct perf_tool *tool,
+				union perf_event *event,
+				struct perf_sample *sample,
+				struct perf_evsel *evsel,
+				struct machine *machine)
+{
+	return dump_raw_samples(tool, event, sample, evsel, machine);
+}
+
+static int report_raw_events(struct perf_mem *mem)
+{
+	int err = -EINVAL;
+	int ret;
+	struct perf_session *session = perf_session__new(input_name, O_RDONLY,
+							 0, false, &mem->tool);
+
+	if (session == NULL)
+		return -ENOMEM;
+
+	if (mem->cpu_list) {
+		ret = perf_session__cpu_bitmap(session, mem->cpu_list,
+					       mem->cpu_bitmap);
+		if (ret)
+			goto out_delete;
+	}
+
+	if (symbol__init() < 0)
+		return -1;
+
+	printf("# PID, TID, IP, ADDR, LOCAL WEIGHT, DSRC, SYMBOL\n");
+
+	err = perf_session__process_events(session, &mem->tool);
+	if (err)
+		return err;
+
+	return 0;
+
+out_delete:
+	perf_session__delete(session);
+	return err;
+}
+
+static int report_events(int argc, const char **argv, struct perf_mem *mem)
+{
+	const char **rep_argv;
+	int ret, i = 0, j, rep_argc;
+
+	if (mem->dump_raw)
+		return report_raw_events(mem);
+
+	rep_argc = argc + 3;
+	rep_argv = calloc(rep_argc + 1, sizeof(char *));
+	if (!rep_argv)
+		return -1;
+
+	rep_argv[i++] = strdup("report");
+	rep_argv[i++] = strdup("--mem-mode");
+	rep_argv[i++] = strdup("-n"); /* display number of samples */
+
+	/*
+	 * there is no weight (cost) associated with stores, so don't print
+	 * the column
+	 */
+	if (strcmp(mem_operation, MEM_OPERATION_LOAD))
+		rep_argv[i++] = strdup("--sort=mem,sym,dso,symbol_daddr,"
+				       "dso_daddr,tlb,locked");
+
+	for (j = 1; j < argc; j++, i++)
+		rep_argv[i] = argv[j];
+
+	ret = cmd_report(i, rep_argv, NULL);
+	free(rep_argv);
+	return ret;
+}
+
+int cmd_mem(int argc, const char **argv, const char *prefix __maybe_unused)
+{
+	struct stat st;
+	struct perf_mem mem = {
+		.tool = {
+			.sample		= process_sample_event,
+			.mmap		= perf_event__process_mmap,
+			.comm		= perf_event__process_comm,
+			.lost		= perf_event__process_lost,
+			.fork		= perf_event__process_fork,
+			.build_id	= perf_event__process_build_id,
+			.ordered_samples = true,
+		},
+		.input_name		 = "perf.data",
+	};
+	const struct option mem_options[] = {
+	OPT_STRING('t', "type", &mem_operation,
+		   "type", "memory operations(load/store)"),
+	OPT_BOOLEAN('D', "dump-raw-samples", &mem.dump_raw,
+		    "dump raw samples in ASCII"),
+	OPT_BOOLEAN('U', "hide-unresolved", &mem.hide_unresolved,
+		    "Only display entries resolved to a symbol"),
+	OPT_STRING('i', "input", &input_name, "file",
+		   "input file name"),
+	OPT_STRING('C', "cpu", &mem.cpu_list, "cpu",
+		   "list of cpus to profile"),
+	OPT_STRING('x', "field-separator", &symbol_conf.field_sep,
+		   "separator",
+		   "separator for columns, no spaces will be added"
+		   " between columns '.' is reserved."),
+	OPT_END()
+	};
+
+	argc = parse_options(argc, argv, mem_options, mem_usage,
+			     PARSE_OPT_STOP_AT_NON_OPTION);
+
+	if (!argc || !(strncmp(argv[0], "rec", 3) || mem_operation))
+		usage_with_options(mem_usage, mem_options);
+
+	if (!mem.input_name || !strlen(mem.input_name)) {
+		if (!fstat(STDIN_FILENO, &st) && S_ISFIFO(st.st_mode))
+			mem.input_name = "-";
+		else
+			mem.input_name = "perf.data";
+	}
+
+	if (!strncmp(argv[0], "rec", 3))
+		return __cmd_record(argc, argv);
+	else if (!strncmp(argv[0], "rep", 3))
+		return report_events(argc, argv, &mem);
+	else
+		usage_with_options(mem_usage, mem_options);
+
+	return 0;
+}
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 9f2344a..cdf58ec 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -5,8 +5,6 @@
  * (or a CPU, or a PID) into the perf.data output file - for
  * later analysis via perf report.
  */
-#define _FILE_OFFSET_BITS 64
-
 #include "builtin.h"
 
 #include "perf.h"
@@ -955,6 +953,8 @@
 	OPT_CALLBACK('j', "branch-filter", &record.opts.branch_stack,
 		     "branch filter mask", "branch stack filter modes",
 		     parse_branch_stack),
+	OPT_BOOLEAN('W', "weight", &record.opts.sample_weight,
+		    "sample by weight (on special events only)"),
 	OPT_END()
 };
 
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 296bd21..bd0ca81 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -46,6 +46,7 @@
 	bool			show_full_info;
 	bool			show_threads;
 	bool			inverted_callchain;
+	bool			mem_mode;
 	struct perf_read_values	show_threads_values;
 	const char		*pretty_printing_style;
 	symbol_filter_t		annotate_init;
@@ -64,6 +65,99 @@
 	return perf_default_config(var, value, cb);
 }
 
+static int perf_report__add_mem_hist_entry(struct perf_tool *tool,
+					   struct addr_location *al,
+					   struct perf_sample *sample,
+					   struct perf_evsel *evsel,
+					   struct machine *machine,
+					   union perf_event *event)
+{
+	struct perf_report *rep = container_of(tool, struct perf_report, tool);
+	struct symbol *parent = NULL;
+	u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
+	int err = 0;
+	struct hist_entry *he;
+	struct mem_info *mi, *mx;
+	uint64_t cost;
+
+	if ((sort__has_parent || symbol_conf.use_callchain) &&
+	    sample->callchain) {
+		err = machine__resolve_callchain(machine, evsel, al->thread,
+						 sample, &parent);
+		if (err)
+			return err;
+	}
+
+	mi = machine__resolve_mem(machine, al->thread, sample, cpumode);
+	if (!mi)
+		return -ENOMEM;
+
+	if (rep->hide_unresolved && !al->sym)
+		return 0;
+
+	cost = sample->weight;
+	if (!cost)
+		cost = 1;
+
+	/*
+	 * must pass period=weight in order to get the correct
+	 * sorting from hists__collapse_resort() which is solely
+	 * based on periods. We want sorting be done on nr_events * weight
+	 * and this is indirectly achieved by passing period=weight here
+	 * and the he_stat__add_period() function.
+	 */
+	he = __hists__add_mem_entry(&evsel->hists, al, parent, mi, cost, cost);
+	if (!he)
+		return -ENOMEM;
+
+	/*
+	 * In the TUI browser, we are doing integrated annotation,
+	 * so we don't allocate the extra space needed because the stdio
+	 * code will not use it.
+	 */
+	if (sort__has_sym && he->ms.sym && use_browser > 0) {
+		struct annotation *notes = symbol__annotation(he->ms.sym);
+
+		assert(evsel != NULL);
+
+		if (notes->src == NULL && symbol__alloc_hist(he->ms.sym) < 0)
+			goto out;
+
+		err = hist_entry__inc_addr_samples(he, evsel->idx, al->addr);
+		if (err)
+			goto out;
+	}
+
+	if (sort__has_sym && he->mem_info->daddr.sym && use_browser > 0) {
+		struct annotation *notes;
+
+		mx = he->mem_info;
+
+		notes = symbol__annotation(mx->daddr.sym);
+		if (notes->src == NULL && symbol__alloc_hist(mx->daddr.sym) < 0)
+			goto out;
+
+		err = symbol__inc_addr_samples(mx->daddr.sym,
+					       mx->daddr.map,
+					       evsel->idx,
+					       mx->daddr.al_addr);
+		if (err)
+			goto out;
+	}
+
+	evsel->hists.stats.total_period += cost;
+	hists__inc_nr_events(&evsel->hists, PERF_RECORD_SAMPLE);
+	err = 0;
+
+	if (symbol_conf.use_callchain) {
+		err = callchain_append(he->callchain,
+				       &callchain_cursor,
+				       sample->period);
+	}
+out:
+	return err;
+}
+
 static int perf_report__add_branch_hist_entry(struct perf_tool *tool,
 					struct addr_location *al,
 					struct perf_sample *sample,
@@ -98,7 +192,7 @@
 		 * and not events sampled. Thus we use a pseudo period of 1.
 		 */
 		he = __hists__add_branch_entry(&evsel->hists, al, parent,
-				&bi[i], 1);
+				&bi[i], 1, 1);
 		if (he) {
 			struct annotation *notes;
 			err = -ENOMEM;
@@ -156,7 +250,8 @@
 			return err;
 	}
 
-	he = __hists__add_entry(&evsel->hists, al, parent, sample->period);
+	he = __hists__add_entry(&evsel->hists, al, parent, sample->period,
+					sample->weight);
 	if (he == NULL)
 		return -ENOMEM;
 
@@ -168,7 +263,7 @@
 			return err;
 	}
 	/*
-	 * Only in the newt browser we are doing integrated annotation,
+	 * Only in the TUI browser we are doing integrated annotation,
 	 * so we don't allocated the extra space needed because the stdio
 	 * code will not use it.
 	 */
@@ -219,6 +314,12 @@
 			pr_debug("problem adding lbr entry, skipping event\n");
 			return -1;
 		}
+	} else if (rep->mem_mode == 1) {
+		if (perf_report__add_mem_hist_entry(tool, &al, sample,
+						    evsel, machine, event)) {
+			pr_debug("problem adding mem entry, skipping event\n");
+			return -1;
+		}
 	} else {
 		if (al.map != NULL)
 			al.map->dso->hit = 1;
@@ -302,7 +403,8 @@
 	session_done = 1;
 }
 
-static size_t hists__fprintf_nr_sample_events(struct hists *self,
+static size_t hists__fprintf_nr_sample_events(struct perf_report *rep,
+					      struct hists *self,
 					      const char *evname, FILE *fp)
 {
 	size_t ret;
@@ -330,7 +432,11 @@
 	if (evname != NULL)
 		ret += fprintf(fp, " of event '%s'", evname);
 
-	ret += fprintf(fp, "\n# Event count (approx.): %" PRIu64, nr_events);
+	if (rep->mem_mode) {
+		ret += fprintf(fp, "\n# Total weight : %" PRIu64, nr_events);
+		ret += fprintf(fp, "\n# Sort order   : %s", sort_order);
+	} else
+		ret += fprintf(fp, "\n# Event count (approx.): %" PRIu64, nr_events);
 	return ret + fprintf(fp, "\n#\n");
 }
 
@@ -348,7 +454,7 @@
 		    !perf_evsel__is_group_leader(pos))
 			continue;
 
-		hists__fprintf_nr_sample_events(hists, evname, stdout);
+		hists__fprintf_nr_sample_events(rep, hists, evname, stdout);
 		hists__fprintf(hists, true, 0, 0, stdout);
 		fprintf(stdout, "\n\n");
 	}
@@ -644,7 +750,9 @@
 		    "Use the stdio interface"),
 	OPT_STRING('s', "sort", &sort_order, "key[,key2...]",
 		   "sort by key(s): pid, comm, dso, symbol, parent, cpu, srcline,"
-		   " dso_to, dso_from, symbol_to, symbol_from, mispredict"),
+		   " dso_to, dso_from, symbol_to, symbol_from, mispredict,"
+		   " weight, local_weight, mem, symbol_daddr, dso_daddr, tlb, "
+		   "snoop, locked"),
 	OPT_BOOLEAN(0, "showcpuutilization", &symbol_conf.show_cpu_utilization,
 		    "Show sample percentage for different cpu modes"),
 	OPT_STRING('p', "parent", &parent_pattern, "regex",
@@ -692,6 +800,9 @@
 		    "use branch records for histogram filling", parse_branch_mode),
 	OPT_STRING(0, "objdump", &objdump_path, "path",
 		   "objdump binary to use for disassembly and annotations"),
+	OPT_BOOLEAN(0, "demangle", &symbol_conf.demangle,
+		    "Disable symbol demangling"),
+	OPT_BOOLEAN(0, "mem-mode", &report.mem_mode, "mem access profile"),
 	OPT_END()
 	};
 
@@ -749,12 +860,24 @@
 				     "dso_to,symbol_to";
 
 	}
+	if (report.mem_mode) {
+		if (sort__branch_mode == 1) {
+			fprintf(stderr, "branch and mem mode incompatible\n");
+			goto error;
+		}
+		/*
+		 * if no sort_order is provided, then specify
+		 * branch-mode specific order
+		 */
+		if (sort_order == default_sort_order)
+			sort_order = "local_weight,mem,sym,dso,symbol_daddr,dso_daddr,snoop,tlb,locked";
+	}
 
 	if (setup_sorting() < 0)
 		usage_with_options(report_usage, options);
 
 	/*
-	 * Only in the newt browser we are doing integrated annotation,
+	 * Only in the TUI browser we are doing integrated annotation,
 	 * so don't allocate extra space that won't be used in the stdio
 	 * implementation.
 	 */
@@ -814,6 +937,14 @@
 		sort_entry__setup_elide(&sort_sym_from, symbol_conf.sym_from_list, "sym_from", stdout);
 		sort_entry__setup_elide(&sort_sym_to, symbol_conf.sym_to_list, "sym_to", stdout);
 	} else {
+		if (report.mem_mode) {
+			sort_entry__setup_elide(&sort_dso, symbol_conf.dso_list, "symbol_daddr", stdout);
+			sort_entry__setup_elide(&sort_dso, symbol_conf.dso_list, "dso_daddr", stdout);
+			sort_entry__setup_elide(&sort_dso, symbol_conf.dso_list, "mem", stdout);
+			sort_entry__setup_elide(&sort_dso, symbol_conf.dso_list, "local_weight", stdout);
+			sort_entry__setup_elide(&sort_dso, symbol_conf.dso_list, "tlb", stdout);
+			sort_entry__setup_elide(&sort_dso, symbol_conf.dso_list, "snoop", stdout);
+		}
 		sort_entry__setup_elide(&sort_dso, symbol_conf.dso_list, "dso", stdout);
 		sort_entry__setup_elide(&sort_sym, symbol_conf.sym_list, "symbol", stdout);
 	}
diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c
index 1382294..2da2a6c 100644
--- a/tools/perf/builtin-sched.c
+++ b/tools/perf/builtin-sched.c
@@ -1671,7 +1671,6 @@
 			.sample		 = perf_sched__process_tracepoint_sample,
 			.comm		 = perf_event__process_comm,
 			.lost		 = perf_event__process_lost,
-			.exit		 = perf_event__process_exit,
 			.fork		 = perf_event__process_fork,
 			.ordered_samples = true,
 		},
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index ba0bdd8..7e910ba 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -68,7 +68,7 @@
 static void print_stat(int argc, const char **argv);
 static void print_counter_aggr(struct perf_evsel *counter, char *prefix);
 static void print_counter(struct perf_evsel *counter, char *prefix);
-static void print_aggr_socket(char *prefix);
+static void print_aggr(char *prefix);
 
 static struct perf_evlist	*evsel_list;
 
@@ -76,11 +76,17 @@
 	.uid	= UINT_MAX,
 };
 
+enum aggr_mode {
+	AGGR_NONE,
+	AGGR_GLOBAL,
+	AGGR_SOCKET,
+	AGGR_CORE,
+};
+
 static int			run_count			=  1;
 static bool			no_inherit			= false;
 static bool			scale				=  true;
-static bool			no_aggr				= false;
-static bool			aggr_socket			= false;
+static enum aggr_mode		aggr_mode			= AGGR_GLOBAL;
 static pid_t			child_pid			= -1;
 static bool			null_run			=  false;
 static int			detailed_run			=  0;
@@ -96,7 +102,8 @@
 static unsigned int		interval			= 0;
 static bool			forever				= false;
 static struct timespec		ref_time;
-static struct cpu_map		*sock_map;
+static struct cpu_map		*aggr_map;
+static int			(*aggr_get_id)(struct cpu_map *m, int cpu);
 
 static volatile int done = 0;
 
@@ -355,41 +362,55 @@
 	struct timespec ts, rs;
 	char prefix[64];
 
-	if (no_aggr) {
-		list_for_each_entry(counter, &evsel_list->entries, node) {
-			ps = counter->priv;
-			memset(ps->res_stats, 0, sizeof(ps->res_stats));
-			read_counter(counter);
-		}
-	} else {
+	if (aggr_mode == AGGR_GLOBAL) {
 		list_for_each_entry(counter, &evsel_list->entries, node) {
 			ps = counter->priv;
 			memset(ps->res_stats, 0, sizeof(ps->res_stats));
 			read_counter_aggr(counter);
 		}
+	} else	{
+		list_for_each_entry(counter, &evsel_list->entries, node) {
+			ps = counter->priv;
+			memset(ps->res_stats, 0, sizeof(ps->res_stats));
+			read_counter(counter);
+		}
 	}
+
 	clock_gettime(CLOCK_MONOTONIC, &ts);
 	diff_timespec(&rs, &ts, &ref_time);
 	sprintf(prefix, "%6lu.%09lu%s", rs.tv_sec, rs.tv_nsec, csv_sep);
 
 	if (num_print_interval == 0 && !csv_output) {
-		if (aggr_socket)
+		switch (aggr_mode) {
+		case AGGR_SOCKET:
 			fprintf(output, "#           time socket cpus             counts events\n");
-		else if (no_aggr)
+			break;
+		case AGGR_CORE:
+			fprintf(output, "#           time core         cpus             counts events\n");
+			break;
+		case AGGR_NONE:
 			fprintf(output, "#           time CPU                 counts events\n");
-		else
+			break;
+		case AGGR_GLOBAL:
+		default:
 			fprintf(output, "#           time             counts events\n");
+		}
 	}
 
 	if (++num_print_interval == 25)
 		num_print_interval = 0;
 
-	if (aggr_socket)
-		print_aggr_socket(prefix);
-	else if (no_aggr) {
+	switch (aggr_mode) {
+	case AGGR_CORE:
+	case AGGR_SOCKET:
+		print_aggr(prefix);
+		break;
+	case AGGR_NONE:
 		list_for_each_entry(counter, &evsel_list->entries, node)
 			print_counter(counter, prefix);
-	} else {
+		break;
+	case AGGR_GLOBAL:
+	default:
 		list_for_each_entry(counter, &evsel_list->entries, node)
 			print_counter_aggr(counter, prefix);
 	}
@@ -412,12 +433,6 @@
 		ts.tv_nsec = 0;
 	}
 
-	if (aggr_socket
-	    && cpu_map__build_socket_map(evsel_list->cpus, &sock_map)) {
-		perror("cannot build socket map");
-		return -1;
-	}
-
 	if (forks) {
 		if (perf_evlist__prepare_workload(evsel_list, &target, argv,
 						  false, false) < 0) {
@@ -493,17 +508,17 @@
 
 	update_stats(&walltime_nsecs_stats, t1 - t0);
 
-	if (no_aggr) {
-		list_for_each_entry(counter, &evsel_list->entries, node) {
-			read_counter(counter);
-			perf_evsel__close_fd(counter, perf_evsel__nr_cpus(counter), 1);
-		}
-	} else {
+	if (aggr_mode == AGGR_GLOBAL) {
 		list_for_each_entry(counter, &evsel_list->entries, node) {
 			read_counter_aggr(counter);
 			perf_evsel__close_fd(counter, perf_evsel__nr_cpus(counter),
 					     thread_map__nr(evsel_list->threads));
 		}
+	} else {
+		list_for_each_entry(counter, &evsel_list->entries, node) {
+			read_counter(counter);
+			perf_evsel__close_fd(counter, perf_evsel__nr_cpus(counter), 1);
+		}
 	}
 
 	return WEXITSTATUS(status);
@@ -556,26 +571,47 @@
 	print_noise_pct(stddev_stats(&ps->res_stats[0]), avg);
 }
 
-static void nsec_printout(int cpu, int nr, struct perf_evsel *evsel, double avg)
+static void aggr_printout(struct perf_evsel *evsel, int id, int nr)
 {
-	double msecs = avg / 1e6;
-	char cpustr[16] = { '\0', };
-	const char *fmt = csv_output ? "%s%.6f%s%s" : "%s%18.6f%s%-25s";
-
-	if (aggr_socket)
-		sprintf(cpustr, "S%*d%s%*d%s",
-			csv_output ? 0 : -5,
-			cpu,
+	switch (aggr_mode) {
+	case AGGR_CORE:
+		fprintf(output, "S%d-C%*d%s%*d%s",
+			cpu_map__id_to_socket(id),
+			csv_output ? 0 : -8,
+			cpu_map__id_to_cpu(id),
 			csv_sep,
 			csv_output ? 0 : 4,
 			nr,
 			csv_sep);
-	else if (no_aggr)
-		sprintf(cpustr, "CPU%*d%s",
+		break;
+	case AGGR_SOCKET:
+		fprintf(output, "S%*d%s%*d%s",
+			csv_output ? 0 : -5,
+			id,
+			csv_sep,
+			csv_output ? 0 : 4,
+			nr,
+			csv_sep);
+			break;
+	case AGGR_NONE:
+		fprintf(output, "CPU%*d%s",
 			csv_output ? 0 : -4,
-			perf_evsel__cpus(evsel)->map[cpu], csv_sep);
+			perf_evsel__cpus(evsel)->map[id], csv_sep);
+		break;
+	case AGGR_GLOBAL:
+	default:
+		break;
+	}
+}
 
-	fprintf(output, fmt, cpustr, msecs, csv_sep, perf_evsel__name(evsel));
+static void nsec_printout(int cpu, int nr, struct perf_evsel *evsel, double avg)
+{
+	double msecs = avg / 1e6;
+	const char *fmt = csv_output ? "%.6f%s%s" : "%18.6f%s%-25s";
+
+	aggr_printout(evsel, cpu, nr);
+
+	fprintf(output, fmt, msecs, csv_sep, perf_evsel__name(evsel));
 
 	if (evsel->cgrp)
 		fprintf(output, "%s%s", csv_sep, evsel->cgrp->name);
@@ -772,32 +808,21 @@
 static void abs_printout(int cpu, int nr, struct perf_evsel *evsel, double avg)
 {
 	double total, ratio = 0.0;
-	char cpustr[16] = { '\0', };
 	const char *fmt;
 
 	if (csv_output)
-		fmt = "%s%.0f%s%s";
+		fmt = "%.0f%s%s";
 	else if (big_num)
-		fmt = "%s%'18.0f%s%-25s";
+		fmt = "%'18.0f%s%-25s";
 	else
-		fmt = "%s%18.0f%s%-25s";
+		fmt = "%18.0f%s%-25s";
 
-	if (aggr_socket)
-		sprintf(cpustr, "S%*d%s%*d%s",
-			csv_output ? 0 : -5,
-			cpu,
-			csv_sep,
-			csv_output ? 0 : 4,
-			nr,
-			csv_sep);
-	else if (no_aggr)
-		sprintf(cpustr, "CPU%*d%s",
-			csv_output ? 0 : -4,
-			perf_evsel__cpus(evsel)->map[cpu], csv_sep);
-	else
+	aggr_printout(evsel, cpu, nr);
+
+	if (aggr_mode == AGGR_GLOBAL)
 		cpu = 0;
 
-	fprintf(output, fmt, cpustr, avg, csv_sep, perf_evsel__name(evsel));
+	fprintf(output, fmt, avg, csv_sep, perf_evsel__name(evsel));
 
 	if (evsel->cgrp)
 		fprintf(output, "%s%s", csv_sep, evsel->cgrp->name);
@@ -896,23 +921,23 @@
 	}
 }
 
-static void print_aggr_socket(char *prefix)
+static void print_aggr(char *prefix)
 {
 	struct perf_evsel *counter;
+	int cpu, s, s2, id, nr;
 	u64 ena, run, val;
-	int cpu, s, s2, sock, nr;
 
-	if (!sock_map)
+	if (!(aggr_map || aggr_get_id))
 		return;
 
-	for (s = 0; s < sock_map->nr; s++) {
-		sock = cpu_map__socket(sock_map, s);
+	for (s = 0; s < aggr_map->nr; s++) {
+		id = aggr_map->map[s];
 		list_for_each_entry(counter, &evsel_list->entries, node) {
 			val = ena = run = 0;
 			nr = 0;
 			for (cpu = 0; cpu < perf_evsel__nr_cpus(counter); cpu++) {
-				s2 = cpu_map__get_socket(evsel_list->cpus, cpu);
-				if (s2 != sock)
+				s2 = aggr_get_id(evsel_list->cpus, cpu);
+				if (s2 != id)
 					continue;
 				val += counter->counts->cpu[cpu].val;
 				ena += counter->counts->cpu[cpu].ena;
@@ -923,18 +948,15 @@
 				fprintf(output, "%s", prefix);
 
 			if (run == 0 || ena == 0) {
-				fprintf(output, "S%*d%s%*d%s%*s%s%*s",
-					csv_output ? 0 : -5,
-					s,
-					csv_sep,
-					csv_output ? 0 : 4,
-					nr,
-					csv_sep,
+				aggr_printout(counter, cpu, nr);
+
+				fprintf(output, "%*s%s%*s",
 					csv_output ? 0 : 18,
 					counter->supported ? CNTR_NOT_COUNTED : CNTR_NOT_SUPPORTED,
 					csv_sep,
 					csv_output ? 0 : -24,
 					perf_evsel__name(counter));
+
 				if (counter->cgrp)
 					fprintf(output, "%s%s",
 						csv_sep, counter->cgrp->name);
@@ -944,9 +966,9 @@
 			}
 
 			if (nsec_counter(counter))
-				nsec_printout(sock, nr, counter, val);
+				nsec_printout(id, nr, counter, val);
 			else
-				abs_printout(sock, nr, counter, val);
+				abs_printout(id, nr, counter, val);
 
 			if (!csv_output) {
 				print_noise(counter, 1.0);
@@ -1087,14 +1109,21 @@
 		fprintf(output, ":\n\n");
 	}
 
-	if (aggr_socket)
-		print_aggr_socket(NULL);
-	else if (no_aggr) {
-		list_for_each_entry(counter, &evsel_list->entries, node)
-			print_counter(counter, NULL);
-	} else {
+	switch (aggr_mode) {
+	case AGGR_CORE:
+	case AGGR_SOCKET:
+		print_aggr(NULL);
+		break;
+	case AGGR_GLOBAL:
 		list_for_each_entry(counter, &evsel_list->entries, node)
 			print_counter_aggr(counter, NULL);
+		break;
+	case AGGR_NONE:
+		list_for_each_entry(counter, &evsel_list->entries, node)
+			print_counter(counter, NULL);
+		break;
+	default:
+		break;
 	}
 
 	if (!csv_output) {
@@ -1140,6 +1169,32 @@
 	return 0;
 }
 
+static int perf_stat_init_aggr_mode(void)
+{
+	switch (aggr_mode) {
+	case AGGR_SOCKET:
+		if (cpu_map__build_socket_map(evsel_list->cpus, &aggr_map)) {
+			perror("cannot build socket map");
+			return -1;
+		}
+		aggr_get_id = cpu_map__get_socket;
+		break;
+	case AGGR_CORE:
+		if (cpu_map__build_core_map(evsel_list->cpus, &aggr_map)) {
+			perror("cannot build core map");
+			return -1;
+		}
+		aggr_get_id = cpu_map__get_core;
+		break;
+	case AGGR_NONE:
+	case AGGR_GLOBAL:
+	default:
+		break;
+	}
+	return 0;
+}
+
+
 /*
  * Add default attributes, if there were no attributes specified or
  * if -d/--detailed, -d -d or -d -d -d is used:
@@ -1322,7 +1377,8 @@
 			   stat__set_big_num),
 	OPT_STRING('C', "cpu", &target.cpu_list, "cpu",
 		    "list of cpus to monitor in system-wide"),
-	OPT_BOOLEAN('A', "no-aggr", &no_aggr, "disable CPU count aggregation"),
+	OPT_SET_UINT('A', "no-aggr", &aggr_mode,
+		    "disable CPU count aggregation", AGGR_NONE),
 	OPT_STRING('x', "field-separator", &csv_sep, "separator",
 		   "print counts with custom separator"),
 	OPT_CALLBACK('G', "cgroup", &evsel_list, "name",
@@ -1337,7 +1393,10 @@
 			"command to run after to the measured command"),
 	OPT_UINTEGER('I', "interval-print", &interval,
 		    "print counts at regular interval in ms (>= 100)"),
-	OPT_BOOLEAN(0, "aggr-socket", &aggr_socket, "aggregate counts per processor socket"),
+	OPT_SET_UINT(0, "per-socket", &aggr_mode,
+		     "aggregate counts per processor socket", AGGR_SOCKET),
+	OPT_SET_UINT(0, "per-core", &aggr_mode,
+		     "aggregate counts per physical processor core", AGGR_CORE),
 	OPT_END()
 	};
 	const char * const stat_usage[] = {
@@ -1420,19 +1479,13 @@
 	}
 
 	/* no_aggr, cgroup are for system-wide only */
-	if ((no_aggr || nr_cgroups) && !perf_target__has_cpu(&target)) {
+	if ((aggr_mode != AGGR_GLOBAL || nr_cgroups)
+	     && !perf_target__has_cpu(&target)) {
 		fprintf(stderr, "both cgroup and no-aggregation "
 			"modes only available in system-wide mode\n");
 
 		usage_with_options(stat_usage, options);
-	}
-
-	if (aggr_socket) {
-		if (!perf_target__has_cpu(&target)) {
-			fprintf(stderr, "--aggr-socket only available in system-wide mode (-a)\n");
-			usage_with_options(stat_usage, options);
-		}
-		no_aggr = true;
+		return -1;
 	}
 
 	if (add_default_attributes())
@@ -1458,6 +1511,9 @@
 	if (perf_evlist__alloc_stats(evsel_list, interval))
 		goto out_free_maps;
 
+	if (perf_stat_init_aggr_mode())
+		goto out;
+
 	/*
 	 * We dont want to block the signals - that would cause
 	 * child tasks to inherit that and Ctrl-C would not work.
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index b5520ad..67bdb9f 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -251,7 +251,8 @@
 {
 	struct hist_entry *he;
 
-	he = __hists__add_entry(&evsel->hists, al, NULL, sample->period);
+	he = __hists__add_entry(&evsel->hists, al, NULL, sample->period,
+				sample->weight);
 	if (he == NULL)
 		return NULL;
 
@@ -1088,7 +1089,7 @@
 	OPT_INCR('v', "verbose", &verbose,
 		    "be more verbose (show counter open errors, etc)"),
 	OPT_STRING('s', "sort", &sort_order, "key[,key2...]",
-		   "sort by key(s): pid, comm, dso, symbol, parent"),
+		   "sort by key(s): pid, comm, dso, symbol, parent, weight, local_weight"),
 	OPT_BOOLEAN('n', "show-nr-samples", &symbol_conf.show_nr_samples,
 		    "Show a column with the number of samples"),
 	OPT_CALLBACK_DEFAULT('G', "call-graph", &top.record_opts,
diff --git a/tools/perf/builtin.h b/tools/perf/builtin.h
index 08143bd..b210d62 100644
--- a/tools/perf/builtin.h
+++ b/tools/perf/builtin.h
@@ -36,6 +36,7 @@
 extern int cmd_test(int argc, const char **argv, const char *prefix);
 extern int cmd_trace(int argc, const char **argv, const char *prefix);
 extern int cmd_inject(int argc, const char **argv, const char *prefix);
+extern int cmd_mem(int argc, const char **argv, const char *prefix);
 
 extern int find_scripts(char **scripts_array, char **scripts_path_array);
 #endif
diff --git a/tools/perf/command-list.txt b/tools/perf/command-list.txt
index a28e31b..0906fc4 100644
--- a/tools/perf/command-list.txt
+++ b/tools/perf/command-list.txt
@@ -14,6 +14,7 @@
 perf-kvm			mainporcelain common
 perf-list			mainporcelain common
 perf-lock			mainporcelain common
+perf-mem			mainporcelain common
 perf-probe			mainporcelain full
 perf-record			mainporcelain common
 perf-report			mainporcelain common
diff --git a/tools/perf/config/feature-tests.mak b/tools/perf/config/feature-tests.mak
index b4eabb4..708fb8e 100644
--- a/tools/perf/config/feature-tests.mak
+++ b/tools/perf/config/feature-tests.mak
@@ -61,15 +61,13 @@
 }
 endef
 
-ifndef NO_NEWT
-define SOURCE_NEWT
-#include <newt.h>
+ifndef NO_SLANG
+define SOURCE_SLANG
+#include <slang.h>
 
 int main(void)
 {
-	newtInit();
-	newtCls();
-	return newtFinished();
+	return SLsmg_init_smg();
 }
 endef
 endif
@@ -235,4 +233,4 @@
 	numa_available();
 	return 0;
 }
-endef
\ No newline at end of file
+endef
diff --git a/tools/perf/perf.c b/tools/perf/perf.c
index f6ba7b7..85e1aed 100644
--- a/tools/perf/perf.c
+++ b/tools/perf/perf.c
@@ -60,6 +60,7 @@
 	{ "trace",	cmd_trace,	0 },
 #endif
 	{ "inject",	cmd_inject,	0 },
+	{ "mem",	cmd_mem,	0 },
 };
 
 struct pager_config {
@@ -517,9 +518,8 @@
 
 	while (1) {
 		static int done_help;
-		static int was_alias;
+		int was_alias = run_argv(&argc, &argv);
 
-		was_alias = run_argv(&argc, &argv);
 		if (errno != ENOENT)
 			break;
 
diff --git a/tools/perf/perf.h b/tools/perf/perf.h
index 74659ec..32bd102 100644
--- a/tools/perf/perf.h
+++ b/tools/perf/perf.h
@@ -218,6 +218,7 @@
 	bool	     pipe_output;
 	bool	     raw_samples;
 	bool	     sample_address;
+	bool	     sample_weight;
 	bool	     sample_time;
 	bool	     period;
 	unsigned int freq;
diff --git a/tools/perf/tests/hists_link.c b/tools/perf/tests/hists_link.c
index e0c0267..89085a9 100644
--- a/tools/perf/tests/hists_link.c
+++ b/tools/perf/tests/hists_link.c
@@ -223,7 +223,7 @@
 							  &sample, 0) < 0)
 				goto out;
 
-			he = __hists__add_entry(&evsel->hists, &al, NULL, 1);
+			he = __hists__add_entry(&evsel->hists, &al, NULL, 1, 1);
 			if (he == NULL)
 				goto out;
 
@@ -247,7 +247,7 @@
 							  &sample, 0) < 0)
 				goto out;
 
-			he = __hists__add_entry(&evsel->hists, &al, NULL, 1);
+			he = __hists__add_entry(&evsel->hists, &al, NULL, 1, 1);
 			if (he == NULL)
 				goto out;
 
diff --git a/tools/perf/ui/browser.c b/tools/perf/ui/browser.c
index 809ea463..bbc782e 100644
--- a/tools/perf/ui/browser.c
+++ b/tools/perf/ui/browser.c
@@ -2,7 +2,6 @@
 #include "../cache.h"
 #include "../../perf.h"
 #include "libslang.h"
-#include <newt.h>
 #include "ui.h"
 #include "util.h"
 #include <linux/compiler.h>
@@ -234,7 +233,7 @@
 void __ui_browser__show_title(struct ui_browser *browser, const char *title)
 {
 	SLsmg_gotorc(0, 0);
-	ui_browser__set_color(browser, NEWT_COLORSET_ROOT);
+	ui_browser__set_color(browser, HE_COLORSET_ROOT);
 	slsmg_write_nstring(title, browser->width + 1);
 }
 
@@ -514,6 +513,12 @@
 		.bg	  = "default",
 	},
 	{
+		.colorset = HE_COLORSET_ROOT,
+		.name	  = "root",
+		.fg	  = "white",
+		.bg	  = "blue",
+	},
+	{
 		.name = NULL,
 	}
 };
diff --git a/tools/perf/ui/browser.h b/tools/perf/ui/browser.h
index af70314..404ff66a 100644
--- a/tools/perf/ui/browser.h
+++ b/tools/perf/ui/browser.h
@@ -11,6 +11,7 @@
 #define HE_COLORSET_SELECTED	53
 #define HE_COLORSET_CODE	54
 #define HE_COLORSET_ADDR	55
+#define HE_COLORSET_ROOT	56
 
 struct ui_browser {
 	u64	      index, top_idx;
diff --git a/tools/perf/ui/browsers/annotate.c b/tools/perf/ui/browsers/annotate.c
index f56247a..cc64d3f 100644
--- a/tools/perf/ui/browsers/annotate.c
+++ b/tools/perf/ui/browsers/annotate.c
@@ -10,7 +10,6 @@
 #include "../../util/symbol.h"
 #include "../../util/evsel.h"
 #include <pthread.h>
-#include <newt.h>
 
 struct browser_disasm_line {
 	struct rb_node	rb_node;
diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c
index a5843fd..d88a2d0 100644
--- a/tools/perf/ui/browsers/hists.c
+++ b/tools/perf/ui/browsers/hists.c
@@ -2,7 +2,6 @@
 #include "../libslang.h"
 #include <stdlib.h>
 #include <string.h>
-#include <newt.h>
 #include <linux/rbtree.h>
 
 #include "../../util/evsel.h"
diff --git a/tools/perf/ui/browsers/map.c b/tools/perf/ui/browsers/map.c
index 98851d5..95c7cfb 100644
--- a/tools/perf/ui/browsers/map.c
+++ b/tools/perf/ui/browsers/map.c
@@ -1,6 +1,5 @@
 #include "../libslang.h"
 #include <elf.h>
-#include <newt.h>
 #include <inttypes.h>
 #include <sys/ttydefaults.h>
 #include <string.h>
@@ -10,41 +9,9 @@
 #include "../../util/symbol.h"
 #include "../browser.h"
 #include "../helpline.h"
+#include "../keysyms.h"
 #include "map.h"
 
-static int ui_entry__read(const char *title, char *bf, size_t size, int width)
-{
-	struct newtExitStruct es;
-	newtComponent form, entry;
-	const char *result;
-	int err = -1;
-
-	newtCenteredWindow(width, 1, title);
-	form = newtForm(NULL, NULL, 0);
-	if (form == NULL)
-		return -1;
-
-	entry = newtEntry(0, 0, "0x", width, &result, NEWT_FLAG_SCROLL);
-	if (entry == NULL)
-		goto out_free_form;
-
-	newtFormAddComponent(form, entry);
-	newtFormAddHotKey(form, NEWT_KEY_ENTER);
-	newtFormAddHotKey(form, NEWT_KEY_ESCAPE);
-	newtFormAddHotKey(form, NEWT_KEY_LEFT);
-	newtFormAddHotKey(form, CTRL('c'));
-	newtFormRun(form, &es);
-
-	if (result != NULL) {
-		strncpy(bf, result, size);
-		err = 0;
-	}
-out_free_form:
-	newtPopWindow();
-	newtFormDestroy(form);
-	return err;
-}
-
 struct map_browser {
 	struct ui_browser b;
 	struct map	  *map;
@@ -78,10 +45,11 @@
 {
 	char target[512];
 	struct symbol *sym;
-	int err = ui_entry__read("Search by name/addr", target, sizeof(target), 40);
-
-	if (err)
-		return err;
+	int err = ui_browser__input_window("Search by name/addr",
+					   "Prefix with 0x to search by address",
+					   target, "ENTER: OK, ESC: Cancel", 0);
+	if (err != K_ENTER)
+		return -1;
 
 	if (target[0] == '0' && tolower(target[1]) == 'x') {
 		u64 addr = strtoull(target, NULL, 16);
@@ -112,12 +80,20 @@
 	while (1) {
 		key = ui_browser__run(&self->b, 0);
 
-		if (verbose && key == '/')
-			map_browser__search(self);
-		else
+		switch (key) {
+		case '/':
+			if (verbose)
+				map_browser__search(self);
+		default:
 			break;
+                case K_LEFT:
+                case K_ESC:
+                case 'q':
+                case CTRL('c'):
+                        goto out;
+		}
 	}
-
+out:
 	ui_browser__hide(&self->b);
 	return key;
 }
diff --git a/tools/perf/ui/browsers/scripts.c b/tools/perf/ui/browsers/scripts.c
index cbbd44b..12f009e 100644
--- a/tools/perf/ui/browsers/scripts.c
+++ b/tools/perf/ui/browsers/scripts.c
@@ -1,5 +1,4 @@
 #include <elf.h>
-#include <newt.h>
 #include <inttypes.h>
 #include <sys/ttydefaults.h>
 #include <string.h>
diff --git a/tools/perf/ui/tui/setup.c b/tools/perf/ui/tui/setup.c
index 81efa19..b940148 100644
--- a/tools/perf/ui/tui/setup.c
+++ b/tools/perf/ui/tui/setup.c
@@ -1,4 +1,3 @@
-#include <newt.h>
 #include <signal.h>
 #include <stdbool.h>
 
@@ -88,13 +87,6 @@
 	return SLkp_getkey();
 }
 
-static void newt_suspend(void *d __maybe_unused)
-{
-	newtSuspend();
-	raise(SIGTSTP);
-	newtResume();
-}
-
 static void ui__signal(int sig)
 {
 	ui__exit(false);
@@ -106,7 +98,17 @@
 {
 	int err;
 
-	newtInit();
+	SLutf8_enable(-1);
+	SLtt_get_terminfo();
+	SLtt_get_screen_size();
+
+	err = SLsmg_init_smg();
+	if (err < 0)
+		goto out;
+	err = SLang_init_tty(0, 0, 0);
+	if (err < 0)
+		goto out;
+
 	err = SLkp_init();
 	if (err < 0) {
 		pr_err("TUI initialization failed.\n");
@@ -115,7 +117,6 @@
 
 	SLkp_define_keysym((char *)"^(kB)", SL_KEY_UNTAB);
 
-	newtSetSuspendCallback(newt_suspend, NULL);
 	ui_helpline__init();
 	ui_browser__init();
 	ui_progress__init();
diff --git a/tools/perf/ui/ui.h b/tools/perf/ui/ui.h
index d86359c..70cb0d4 100644
--- a/tools/perf/ui/ui.h
+++ b/tools/perf/ui/ui.h
@@ -12,7 +12,7 @@
 void setup_browser(bool fallback_to_pager);
 void exit_browser(bool wait_for_ok);
 
-#ifdef NEWT_SUPPORT
+#ifdef SLANG_SUPPORT
 int ui__init(void);
 void ui__exit(bool wait_for_ok);
 #else
diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h
index 6f3c16f..af75515 100644
--- a/tools/perf/util/annotate.h
+++ b/tools/perf/util/annotate.h
@@ -150,7 +150,7 @@
 			 struct perf_evsel *evsel, bool print_lines,
 			 bool full_paths, int min_pcnt, int max_lines);
 
-#ifdef NEWT_SUPPORT
+#ifdef SLANG_SUPPORT
 int symbol__tui_annotate(struct symbol *sym, struct map *map,
 			 struct perf_evsel *evsel,
 			 struct hist_browser_timer *hbt);
diff --git a/tools/perf/util/cpumap.c b/tools/perf/util/cpumap.c
index f817046..beb8cf9 100644
--- a/tools/perf/util/cpumap.c
+++ b/tools/perf/util/cpumap.c
@@ -4,6 +4,7 @@
 #include "cpumap.h"
 #include <assert.h>
 #include <stdio.h>
+#include <stdlib.h>
 
 static struct cpu_map *cpu_map__default_new(void)
 {
@@ -219,7 +220,7 @@
 	if (!mnt)
 		return -1;
 
-	sprintf(path,
+	snprintf(path, PATH_MAX,
 		"%s/devices/system/cpu/cpu%d/topology/physical_package_id",
 		mnt, cpu);
 
@@ -231,27 +232,88 @@
 	return ret == 1 ? cpu : -1;
 }
 
-int cpu_map__build_socket_map(struct cpu_map *cpus, struct cpu_map **sockp)
+static int cmp_ids(const void *a, const void *b)
 {
-	struct cpu_map *sock;
+	return *(int *)a - *(int *)b;
+}
+
+static int cpu_map__build_map(struct cpu_map *cpus, struct cpu_map **res,
+			      int (*f)(struct cpu_map *map, int cpu))
+{
+	struct cpu_map *c;
 	int nr = cpus->nr;
 	int cpu, s1, s2;
 
-	sock = calloc(1, sizeof(*sock) + nr * sizeof(int));
-	if (!sock)
+	/* allocate as much as possible */
+	c = calloc(1, sizeof(*c) + nr * sizeof(int));
+	if (!c)
 		return -1;
 
 	for (cpu = 0; cpu < nr; cpu++) {
-		s1 = cpu_map__get_socket(cpus, cpu);
-		for (s2 = 0; s2 < sock->nr; s2++) {
-			if (s1 == sock->map[s2])
+		s1 = f(cpus, cpu);
+		for (s2 = 0; s2 < c->nr; s2++) {
+			if (s1 == c->map[s2])
 				break;
 		}
-		if (s2 == sock->nr) {
-			sock->map[sock->nr] = s1;
-			sock->nr++;
+		if (s2 == c->nr) {
+			c->map[c->nr] = s1;
+			c->nr++;
 		}
 	}
-	*sockp = sock;
+	/* ensure we process id in increasing order */
+	qsort(c->map, c->nr, sizeof(int), cmp_ids);
+
+	*res = c;
 	return 0;
 }
+
+int cpu_map__get_core(struct cpu_map *map, int idx)
+{
+	FILE *fp;
+	const char *mnt;
+	char path[PATH_MAX];
+	int cpu, ret, s;
+
+	if (idx > map->nr)
+		return -1;
+
+	cpu = map->map[idx];
+
+	mnt = sysfs_find_mountpoint();
+	if (!mnt)
+		return -1;
+
+	snprintf(path, PATH_MAX,
+		"%s/devices/system/cpu/cpu%d/topology/core_id",
+		mnt, cpu);
+
+	fp = fopen(path, "r");
+	if (!fp)
+		return -1;
+	ret = fscanf(fp, "%d", &cpu);
+	fclose(fp);
+	if (ret != 1)
+		return -1;
+
+	s = cpu_map__get_socket(map, idx);
+	if (s == -1)
+		return -1;
+
+	/*
+	 * encode socket in upper 16 bits
+	 * core_id is relative to socket, and
+	 * we need a global id. So we combine
+	 * socket+ core id
+	 */
+	return (s << 16) | (cpu & 0xffff);
+}
+
+int cpu_map__build_socket_map(struct cpu_map *cpus, struct cpu_map **sockp)
+{
+	return cpu_map__build_map(cpus, sockp, cpu_map__get_socket);
+}
+
+int cpu_map__build_core_map(struct cpu_map *cpus, struct cpu_map **corep)
+{
+	return cpu_map__build_map(cpus, corep, cpu_map__get_core);
+}
diff --git a/tools/perf/util/cpumap.h b/tools/perf/util/cpumap.h
index 161b007..9bed02e 100644
--- a/tools/perf/util/cpumap.h
+++ b/tools/perf/util/cpumap.h
@@ -15,7 +15,9 @@
 struct cpu_map *cpu_map__read(FILE *file);
 size_t cpu_map__fprintf(struct cpu_map *map, FILE *fp);
 int cpu_map__get_socket(struct cpu_map *map, int idx);
+int cpu_map__get_core(struct cpu_map *map, int idx);
 int cpu_map__build_socket_map(struct cpu_map *cpus, struct cpu_map **sockp);
+int cpu_map__build_core_map(struct cpu_map *cpus, struct cpu_map **corep);
 
 static inline int cpu_map__socket(struct cpu_map *sock, int s)
 {
@@ -24,6 +26,16 @@
 	return sock->map[s];
 }
 
+static inline int cpu_map__id_to_socket(int id)
+{
+	return id >> 16;
+}
+
+static inline int cpu_map__id_to_cpu(int id)
+{
+	return id & 0xffff;
+}
+
 static inline int cpu_map__nr(const struct cpu_map *map)
 {
 	return map ? map->nr : 1;
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index 0d573ff..1813895 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -88,8 +88,10 @@
 	u64 id;
 	u64 stream_id;
 	u64 period;
+	u64 weight;
 	u32 cpu;
 	u32 raw_size;
+	u64 data_src;
 	void *raw_data;
 	struct ip_callchain *callchain;
 	struct branch_stack *branch_stack;
@@ -97,6 +99,13 @@
 	struct stack_dump user_stack;
 };
 
+#define PERF_MEM_DATA_SRC_NONE \
+	(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))
+
 struct build_id_event {
 	struct perf_event_header header;
 	pid_t			 pid;
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 1adb824..07b1a3a 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -554,6 +554,9 @@
 		perf_evsel__set_sample_bit(evsel, CPU);
 	}
 
+	if (opts->sample_address)
+		attr->sample_type	|= PERF_SAMPLE_DATA_SRC;
+
 	if (opts->no_delay) {
 		attr->watermark = 0;
 		attr->wakeup_events = 1;
@@ -563,6 +566,9 @@
 		attr->branch_sample_type = opts->branch_stack;
 	}
 
+	if (opts->sample_weight)
+		attr->sample_type	|= PERF_SAMPLE_WEIGHT;
+
 	attr->mmap = track;
 	attr->comm = track;
 
@@ -1017,6 +1023,7 @@
 	data->cpu = data->pid = data->tid = -1;
 	data->stream_id = data->id = data->time = -1ULL;
 	data->period = 1;
+	data->weight = 0;
 
 	if (event->header.type != PERF_RECORD_SAMPLE) {
 		if (!evsel->attr.sample_id_all)
@@ -1167,6 +1174,18 @@
 		}
 	}
 
+	data->weight = 0;
+	if (type & PERF_SAMPLE_WEIGHT) {
+		data->weight = *array;
+		array++;
+	}
+
+	data->data_src = PERF_MEM_DATA_SRC_NONE;
+	if (type & PERF_SAMPLE_DATA_SRC) {
+		data->data_src = *array;
+		array++;
+	}
+
 	return 0;
 }
 
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index a9b7349..326068a 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -1,5 +1,3 @@
-#define _FILE_OFFSET_BITS 64
-
 #include "util.h"
 #include <sys/types.h>
 #include <byteswap.h>
@@ -1672,8 +1670,8 @@
 				struct perf_header *ph __maybe_unused,
 				int fd, void *data)
 {
-	trace_report(fd, data, false);
-	return 0;
+	ssize_t ret = trace_report(fd, data, false);
+	return ret < 0 ? -1 : 0;
 }
 
 static int process_build_id(struct perf_file_section *section,
@@ -2752,6 +2750,11 @@
 	if (evsel->tp_format)
 		return 0;
 
+	if (pevent == NULL) {
+		pr_debug("broken or missing trace data\n");
+		return -1;
+	}
+
 	event = pevent_find_event(pevent, evsel->attr.config);
 	if (event == NULL)
 		return -1;
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index f855941..6b32721 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -67,12 +67,16 @@
 void hists__calc_col_len(struct hists *hists, struct hist_entry *h)
 {
 	const unsigned int unresolved_col_width = BITS_PER_LONG / 4;
+	int symlen;
 	u16 len;
 
 	if (h->ms.sym)
 		hists__new_col_len(hists, HISTC_SYMBOL, h->ms.sym->namelen + 4);
-	else
+	else {
+		symlen = unresolved_col_width + 4 + 2;
+		hists__new_col_len(hists, HISTC_SYMBOL, symlen);
 		hists__set_unres_dso_col_len(hists, HISTC_DSO);
+	}
 
 	len = thread__comm_len(h->thread);
 	if (hists__new_col_len(hists, HISTC_COMM, len))
@@ -87,7 +91,6 @@
 		hists__new_col_len(hists, HISTC_PARENT, h->parent->namelen);
 
 	if (h->branch_info) {
-		int symlen;
 		/*
 		 * +4 accounts for '[x] ' priv level info
 		 * +2 account of 0x prefix on raw addresses
@@ -116,6 +119,42 @@
 			hists__set_unres_dso_col_len(hists, HISTC_DSO_TO);
 		}
 	}
+
+	if (h->mem_info) {
+		/*
+		 * +4 accounts for '[x] ' priv level info
+		 * +2 account of 0x prefix on raw addresses
+		 */
+		if (h->mem_info->daddr.sym) {
+			symlen = (int)h->mem_info->daddr.sym->namelen + 4
+			       + unresolved_col_width + 2;
+			hists__new_col_len(hists, HISTC_MEM_DADDR_SYMBOL,
+					   symlen);
+		} else {
+			symlen = unresolved_col_width + 4 + 2;
+			hists__new_col_len(hists, HISTC_MEM_DADDR_SYMBOL,
+					   symlen);
+		}
+		if (h->mem_info->daddr.map) {
+			symlen = dso__name_len(h->mem_info->daddr.map->dso);
+			hists__new_col_len(hists, HISTC_MEM_DADDR_DSO,
+					   symlen);
+		} else {
+			symlen = unresolved_col_width + 4 + 2;
+			hists__set_unres_dso_col_len(hists, HISTC_MEM_DADDR_DSO);
+		}
+	} else {
+		symlen = unresolved_col_width + 4 + 2;
+		hists__new_col_len(hists, HISTC_MEM_DADDR_SYMBOL, symlen);
+		hists__set_unres_dso_col_len(hists, HISTC_MEM_DADDR_DSO);
+	}
+
+	hists__new_col_len(hists, HISTC_MEM_LOCKED, 6);
+	hists__new_col_len(hists, HISTC_MEM_TLB, 22);
+	hists__new_col_len(hists, HISTC_MEM_SNOOP, 12);
+	hists__new_col_len(hists, HISTC_MEM_LVL, 21 + 3);
+	hists__new_col_len(hists, HISTC_LOCAL_WEIGHT, 12);
+	hists__new_col_len(hists, HISTC_GLOBAL_WEIGHT, 12);
 }
 
 void hists__output_recalc_col_len(struct hists *hists, int max_rows)
@@ -155,9 +194,12 @@
 	}
 }
 
-static void he_stat__add_period(struct he_stat *he_stat, u64 period)
+static void he_stat__add_period(struct he_stat *he_stat, u64 period,
+				u64 weight)
 {
+
 	he_stat->period		+= period;
+	he_stat->weight		+= weight;
 	he_stat->nr_events	+= 1;
 }
 
@@ -169,12 +211,14 @@
 	dest->period_guest_sys	+= src->period_guest_sys;
 	dest->period_guest_us	+= src->period_guest_us;
 	dest->nr_events		+= src->nr_events;
+	dest->weight		+= src->weight;
 }
 
 static void hist_entry__decay(struct hist_entry *he)
 {
 	he->stat.period = (he->stat.period * 7) / 8;
 	he->stat.nr_events = (he->stat.nr_events * 7) / 8;
+	/* XXX need decay for weight too? */
 }
 
 static bool hists__decay_entry(struct hists *hists, struct hist_entry *he)
@@ -239,7 +283,7 @@
 static struct hist_entry *hist_entry__new(struct hist_entry *template)
 {
 	size_t callchain_size = symbol_conf.use_callchain ? sizeof(struct callchain_root) : 0;
-	struct hist_entry *he = malloc(sizeof(*he) + callchain_size);
+	struct hist_entry *he = zalloc(sizeof(*he) + callchain_size);
 
 	if (he != NULL) {
 		*he = *template;
@@ -254,6 +298,13 @@
 				he->branch_info->to.map->referenced = true;
 		}
 
+		if (he->mem_info) {
+			if (he->mem_info->iaddr.map)
+				he->mem_info->iaddr.map->referenced = true;
+			if (he->mem_info->daddr.map)
+				he->mem_info->daddr.map->referenced = true;
+		}
+
 		if (symbol_conf.use_callchain)
 			callchain_init(he->callchain);
 
@@ -282,7 +333,8 @@
 static struct hist_entry *add_hist_entry(struct hists *hists,
 				      struct hist_entry *entry,
 				      struct addr_location *al,
-				      u64 period)
+				      u64 period,
+				      u64 weight)
 {
 	struct rb_node **p;
 	struct rb_node *parent = NULL;
@@ -306,7 +358,7 @@
 		cmp = hist_entry__cmp(he, entry);
 
 		if (!cmp) {
-			he_stat__add_period(&he->stat, period);
+			he_stat__add_period(&he->stat, period, weight);
 
 			/* If the map of an existing hist_entry has
 			 * become out-of-date due to an exec() or
@@ -341,11 +393,42 @@
 	return he;
 }
 
+struct hist_entry *__hists__add_mem_entry(struct hists *self,
+					  struct addr_location *al,
+					  struct symbol *sym_parent,
+					  struct mem_info *mi,
+					  u64 period,
+					  u64 weight)
+{
+	struct hist_entry entry = {
+		.thread	= al->thread,
+		.ms = {
+			.map	= al->map,
+			.sym	= al->sym,
+		},
+		.stat = {
+			.period	= period,
+			.weight = weight,
+			.nr_events = 1,
+		},
+		.cpu	= al->cpu,
+		.ip	= al->addr,
+		.level	= al->level,
+		.parent = sym_parent,
+		.filtered = symbol__parent_filter(sym_parent),
+		.hists = self,
+		.mem_info = mi,
+		.branch_info = NULL,
+	};
+	return add_hist_entry(self, &entry, al, period, weight);
+}
+
 struct hist_entry *__hists__add_branch_entry(struct hists *self,
 					     struct addr_location *al,
 					     struct symbol *sym_parent,
 					     struct branch_info *bi,
-					     u64 period)
+					     u64 period,
+					     u64 weight)
 {
 	struct hist_entry entry = {
 		.thread	= al->thread,
@@ -359,19 +442,22 @@
 		.stat = {
 			.period	= period,
 			.nr_events = 1,
+			.weight = weight,
 		},
 		.parent = sym_parent,
 		.filtered = symbol__parent_filter(sym_parent),
 		.branch_info = bi,
 		.hists	= self,
+		.mem_info = NULL,
 	};
 
-	return add_hist_entry(self, &entry, al, period);
+	return add_hist_entry(self, &entry, al, period, weight);
 }
 
 struct hist_entry *__hists__add_entry(struct hists *self,
 				      struct addr_location *al,
-				      struct symbol *sym_parent, u64 period)
+				      struct symbol *sym_parent, u64 period,
+				      u64 weight)
 {
 	struct hist_entry entry = {
 		.thread	= al->thread,
@@ -385,13 +471,16 @@
 		.stat = {
 			.period	= period,
 			.nr_events = 1,
+			.weight = weight,
 		},
 		.parent = sym_parent,
 		.filtered = symbol__parent_filter(sym_parent),
 		.hists	= self,
+		.branch_info = NULL,
+		.mem_info = NULL,
 	};
 
-	return add_hist_entry(self, &entry, al, period);
+	return add_hist_entry(self, &entry, al, period, weight);
 }
 
 int64_t
@@ -431,6 +520,7 @@
 void hist_entry__free(struct hist_entry *he)
 {
 	free(he->branch_info);
+	free(he->mem_info);
 	free(he);
 }
 
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index 8483313..14c2fe2 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -49,6 +49,14 @@
 	HISTC_DSO_FROM,
 	HISTC_DSO_TO,
 	HISTC_SRCLINE,
+	HISTC_LOCAL_WEIGHT,
+	HISTC_GLOBAL_WEIGHT,
+	HISTC_MEM_DADDR_SYMBOL,
+	HISTC_MEM_DADDR_DSO,
+	HISTC_MEM_LOCKED,
+	HISTC_MEM_TLB,
+	HISTC_MEM_LVL,
+	HISTC_MEM_SNOOP,
 	HISTC_NR_COLS, /* Last entry */
 };
 
@@ -73,7 +81,8 @@
 
 struct hist_entry *__hists__add_entry(struct hists *self,
 				      struct addr_location *al,
-				      struct symbol *parent, u64 period);
+				      struct symbol *parent, u64 period,
+				      u64 weight);
 int64_t hist_entry__cmp(struct hist_entry *left, struct hist_entry *right);
 int64_t hist_entry__collapse(struct hist_entry *left, struct hist_entry *right);
 int hist_entry__sort_snprintf(struct hist_entry *self, char *bf, size_t size,
@@ -84,7 +93,15 @@
 					     struct addr_location *al,
 					     struct symbol *sym_parent,
 					     struct branch_info *bi,
-					     u64 period);
+					     u64 period,
+					     u64 weight);
+
+struct hist_entry *__hists__add_mem_entry(struct hists *self,
+					  struct addr_location *al,
+					  struct symbol *sym_parent,
+					  struct mem_info *mi,
+					  u64 period,
+					  u64 weight);
 
 void hists__output_resort(struct hists *self);
 void hists__output_resort_threaded(struct hists *hists);
@@ -175,7 +192,7 @@
 	int refresh;
 };
 
-#ifdef NEWT_SUPPORT
+#ifdef SLANG_SUPPORT
 #include "../ui/keysyms.h"
 int hist_entry__tui_annotate(struct hist_entry *he, struct perf_evsel *evsel,
 			     struct hist_browser_timer *hbt);
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index c5e3b12..b2ecad6 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -955,6 +955,7 @@
 	u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
 	struct thread *thread;
 	struct map *map;
+	enum map_type type;
 	int ret = 0;
 
 	if (dump_trace)
@@ -971,10 +972,17 @@
 	thread = machine__findnew_thread(machine, event->mmap.pid);
 	if (thread == NULL)
 		goto out_problem;
+
+	if (event->header.misc & PERF_RECORD_MISC_MMAP_DATA)
+		type = MAP__VARIABLE;
+	else
+		type = MAP__FUNCTION;
+
 	map = map__new(&machine->user_dsos, event->mmap.start,
 			event->mmap.len, event->mmap.pgoff,
 			event->mmap.pid, event->mmap.filename,
-			MAP__FUNCTION);
+			type);
+
 	if (map == NULL)
 		goto out_problem;
 
@@ -1097,6 +1105,38 @@
 	ams->map = al.map;
 }
 
+static void ip__resolve_data(struct machine *machine, struct thread *thread,
+			     u8 m, struct addr_map_symbol *ams, u64 addr)
+{
+	struct addr_location al;
+
+	memset(&al, 0, sizeof(al));
+
+	thread__find_addr_location(thread, machine, m, MAP__VARIABLE, addr, &al,
+				   NULL);
+	ams->addr = addr;
+	ams->al_addr = al.addr;
+	ams->sym = al.sym;
+	ams->map = al.map;
+}
+
+struct mem_info *machine__resolve_mem(struct machine *machine,
+				      struct thread *thr,
+				      struct perf_sample *sample,
+				      u8 cpumode)
+{
+	struct mem_info *mi = zalloc(sizeof(*mi));
+
+	if (!mi)
+		return NULL;
+
+	ip__resolve_ams(machine, thr, &mi->iaddr, sample->ip);
+	ip__resolve_data(machine, thr, cpumode, &mi->daddr, sample->addr);
+	mi->data_src.val = sample->data_src;
+
+	return mi;
+}
+
 struct branch_info *machine__resolve_bstack(struct machine *machine,
 					    struct thread *thr,
 					    struct branch_stack *bs)
diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h
index e0b2c00..7794068 100644
--- a/tools/perf/util/machine.h
+++ b/tools/perf/util/machine.h
@@ -76,6 +76,9 @@
 struct branch_info *machine__resolve_bstack(struct machine *machine,
 					    struct thread *thread,
 					    struct branch_stack *bs);
+struct mem_info *machine__resolve_mem(struct machine *machine,
+				      struct thread *thread,
+				      struct perf_sample *sample, u8 cpumode);
 int machine__resolve_callchain(struct machine *machine,
 			       struct perf_evsel *evsel,
 			       struct thread *thread,
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index ab265c2..cf1fe01 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -1,5 +1,3 @@
-#define _FILE_OFFSET_BITS 64
-
 #include <linux/kernel.h>
 
 #include <byteswap.h>
@@ -800,6 +798,12 @@
 
 	if (sample_type & PERF_SAMPLE_STACK_USER)
 		stack_user__printf(&sample->user_stack);
+
+	if (sample_type & PERF_SAMPLE_WEIGHT)
+		printf("... weight: %" PRIu64 "\n", sample->weight);
+
+	if (sample_type & PERF_SAMPLE_DATA_SRC)
+		printf(" . data_src: 0x%"PRIx64"\n", sample->data_src);
 }
 
 static struct machine *
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index d41926c..5f52d49 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -198,11 +198,19 @@
 	}
 
 	ret += repsep_snprintf(bf + ret, size - ret, "[%c] ", level);
-	if (sym)
-		ret += repsep_snprintf(bf + ret, size - ret, "%-*s",
-				       width - ret,
-				       sym->name);
-	else {
+	if (sym && map) {
+		if (map->type == MAP__VARIABLE) {
+			ret += repsep_snprintf(bf + ret, size - ret, "%s", sym->name);
+			ret += repsep_snprintf(bf + ret, size - ret, "+0x%llx",
+					ip - map->unmap_ip(map, sym->start));
+			ret += repsep_snprintf(bf + ret, size - ret, "%-*s",
+				       width - ret, "");
+		} else {
+			ret += repsep_snprintf(bf + ret, size - ret, "%-*s",
+					       width - ret,
+					       sym->name);
+		}
+	} else {
 		size_t len = BITS_PER_LONG / 4;
 		ret += repsep_snprintf(bf + ret, size - ret, "%-#.*llx",
 				       len, ip);
@@ -457,6 +465,304 @@
 	return repsep_snprintf(bf, size, "%-*s", width, out);
 }
 
+/* --sort daddr_sym */
+static int64_t
+sort__daddr_cmp(struct hist_entry *left, struct hist_entry *right)
+{
+	uint64_t l = 0, r = 0;
+
+	if (left->mem_info)
+		l = left->mem_info->daddr.addr;
+	if (right->mem_info)
+		r = right->mem_info->daddr.addr;
+
+	return (int64_t)(r - l);
+}
+
+static int hist_entry__daddr_snprintf(struct hist_entry *self, char *bf,
+				    size_t size, unsigned int width)
+{
+	uint64_t addr = 0;
+	struct map *map = NULL;
+	struct symbol *sym = NULL;
+
+	if (self->mem_info) {
+		addr = self->mem_info->daddr.addr;
+		map = self->mem_info->daddr.map;
+		sym = self->mem_info->daddr.sym;
+	}
+	return _hist_entry__sym_snprintf(map, sym, addr, self->level, bf, size,
+					 width);
+}
+
+static int64_t
+sort__dso_daddr_cmp(struct hist_entry *left, struct hist_entry *right)
+{
+	struct map *map_l = NULL;
+	struct map *map_r = NULL;
+
+	if (left->mem_info)
+		map_l = left->mem_info->daddr.map;
+	if (right->mem_info)
+		map_r = right->mem_info->daddr.map;
+
+	return _sort__dso_cmp(map_l, map_r);
+}
+
+static int hist_entry__dso_daddr_snprintf(struct hist_entry *self, char *bf,
+				    size_t size, unsigned int width)
+{
+	struct map *map = NULL;
+
+	if (self->mem_info)
+		map = self->mem_info->daddr.map;
+
+	return _hist_entry__dso_snprintf(map, bf, size, width);
+}
+
+static int64_t
+sort__locked_cmp(struct hist_entry *left, struct hist_entry *right)
+{
+	union perf_mem_data_src data_src_l;
+	union perf_mem_data_src data_src_r;
+
+	if (left->mem_info)
+		data_src_l = left->mem_info->data_src;
+	else
+		data_src_l.mem_lock = PERF_MEM_LOCK_NA;
+
+	if (right->mem_info)
+		data_src_r = right->mem_info->data_src;
+	else
+		data_src_r.mem_lock = PERF_MEM_LOCK_NA;
+
+	return (int64_t)(data_src_r.mem_lock - data_src_l.mem_lock);
+}
+
+static int hist_entry__locked_snprintf(struct hist_entry *self, char *bf,
+				    size_t size, unsigned int width)
+{
+	const char *out;
+	u64 mask = PERF_MEM_LOCK_NA;
+
+	if (self->mem_info)
+		mask = self->mem_info->data_src.mem_lock;
+
+	if (mask & PERF_MEM_LOCK_NA)
+		out = "N/A";
+	else if (mask & PERF_MEM_LOCK_LOCKED)
+		out = "Yes";
+	else
+		out = "No";
+
+	return repsep_snprintf(bf, size, "%-*s", width, out);
+}
+
+static int64_t
+sort__tlb_cmp(struct hist_entry *left, struct hist_entry *right)
+{
+	union perf_mem_data_src data_src_l;
+	union perf_mem_data_src data_src_r;
+
+	if (left->mem_info)
+		data_src_l = left->mem_info->data_src;
+	else
+		data_src_l.mem_dtlb = PERF_MEM_TLB_NA;
+
+	if (right->mem_info)
+		data_src_r = right->mem_info->data_src;
+	else
+		data_src_r.mem_dtlb = PERF_MEM_TLB_NA;
+
+	return (int64_t)(data_src_r.mem_dtlb - data_src_l.mem_dtlb);
+}
+
+static const char * const tlb_access[] = {
+	"N/A",
+	"HIT",
+	"MISS",
+	"L1",
+	"L2",
+	"Walker",
+	"Fault",
+};
+#define NUM_TLB_ACCESS (sizeof(tlb_access)/sizeof(const char *))
+
+static int hist_entry__tlb_snprintf(struct hist_entry *self, char *bf,
+				    size_t size, unsigned int width)
+{
+	char out[64];
+	size_t sz = sizeof(out) - 1; /* -1 for null termination */
+	size_t l = 0, i;
+	u64 m = PERF_MEM_TLB_NA;
+	u64 hit, miss;
+
+	out[0] = '\0';
+
+	if (self->mem_info)
+		m = self->mem_info->data_src.mem_dtlb;
+
+	hit = m & PERF_MEM_TLB_HIT;
+	miss = m & PERF_MEM_TLB_MISS;
+
+	/* already taken care of */
+	m &= ~(PERF_MEM_TLB_HIT|PERF_MEM_TLB_MISS);
+
+	for (i = 0; m && i < NUM_TLB_ACCESS; i++, m >>= 1) {
+		if (!(m & 0x1))
+			continue;
+		if (l) {
+			strcat(out, " or ");
+			l += 4;
+		}
+		strncat(out, tlb_access[i], sz - l);
+		l += strlen(tlb_access[i]);
+	}
+	if (*out == '\0')
+		strcpy(out, "N/A");
+	if (hit)
+		strncat(out, " hit", sz - l);
+	if (miss)
+		strncat(out, " miss", sz - l);
+
+	return repsep_snprintf(bf, size, "%-*s", width, out);
+}
+
+static int64_t
+sort__lvl_cmp(struct hist_entry *left, struct hist_entry *right)
+{
+	union perf_mem_data_src data_src_l;
+	union perf_mem_data_src data_src_r;
+
+	if (left->mem_info)
+		data_src_l = left->mem_info->data_src;
+	else
+		data_src_l.mem_lvl = PERF_MEM_LVL_NA;
+
+	if (right->mem_info)
+		data_src_r = right->mem_info->data_src;
+	else
+		data_src_r.mem_lvl = PERF_MEM_LVL_NA;
+
+	return (int64_t)(data_src_r.mem_lvl - data_src_l.mem_lvl);
+}
+
+static const char * const mem_lvl[] = {
+	"N/A",
+	"HIT",
+	"MISS",
+	"L1",
+	"LFB",
+	"L2",
+	"L3",
+	"Local RAM",
+	"Remote RAM (1 hop)",
+	"Remote RAM (2 hops)",
+	"Remote Cache (1 hop)",
+	"Remote Cache (2 hops)",
+	"I/O",
+	"Uncached",
+};
+#define NUM_MEM_LVL (sizeof(mem_lvl)/sizeof(const char *))
+
+static int hist_entry__lvl_snprintf(struct hist_entry *self, char *bf,
+				    size_t size, unsigned int width)
+{
+	char out[64];
+	size_t sz = sizeof(out) - 1; /* -1 for null termination */
+	size_t i, l = 0;
+	u64 m =  PERF_MEM_LVL_NA;
+	u64 hit, miss;
+
+	if (self->mem_info)
+		m  = self->mem_info->data_src.mem_lvl;
+
+	out[0] = '\0';
+
+	hit = m & PERF_MEM_LVL_HIT;
+	miss = m & PERF_MEM_LVL_MISS;
+
+	/* already taken care of */
+	m &= ~(PERF_MEM_LVL_HIT|PERF_MEM_LVL_MISS);
+
+	for (i = 0; m && i < NUM_MEM_LVL; i++, m >>= 1) {
+		if (!(m & 0x1))
+			continue;
+		if (l) {
+			strcat(out, " or ");
+			l += 4;
+		}
+		strncat(out, mem_lvl[i], sz - l);
+		l += strlen(mem_lvl[i]);
+	}
+	if (*out == '\0')
+		strcpy(out, "N/A");
+	if (hit)
+		strncat(out, " hit", sz - l);
+	if (miss)
+		strncat(out, " miss", sz - l);
+
+	return repsep_snprintf(bf, size, "%-*s", width, out);
+}
+
+static int64_t
+sort__snoop_cmp(struct hist_entry *left, struct hist_entry *right)
+{
+	union perf_mem_data_src data_src_l;
+	union perf_mem_data_src data_src_r;
+
+	if (left->mem_info)
+		data_src_l = left->mem_info->data_src;
+	else
+		data_src_l.mem_snoop = PERF_MEM_SNOOP_NA;
+
+	if (right->mem_info)
+		data_src_r = right->mem_info->data_src;
+	else
+		data_src_r.mem_snoop = PERF_MEM_SNOOP_NA;
+
+	return (int64_t)(data_src_r.mem_snoop - data_src_l.mem_snoop);
+}
+
+static const char * const snoop_access[] = {
+	"N/A",
+	"None",
+	"Miss",
+	"Hit",
+	"HitM",
+};
+#define NUM_SNOOP_ACCESS (sizeof(snoop_access)/sizeof(const char *))
+
+static int hist_entry__snoop_snprintf(struct hist_entry *self, char *bf,
+				    size_t size, unsigned int width)
+{
+	char out[64];
+	size_t sz = sizeof(out) - 1; /* -1 for null termination */
+	size_t i, l = 0;
+	u64 m = PERF_MEM_SNOOP_NA;
+
+	out[0] = '\0';
+
+	if (self->mem_info)
+		m = self->mem_info->data_src.mem_snoop;
+
+	for (i = 0; m && i < NUM_SNOOP_ACCESS; i++, m >>= 1) {
+		if (!(m & 0x1))
+			continue;
+		if (l) {
+			strcat(out, " or ");
+			l += 4;
+		}
+		strncat(out, snoop_access[i], sz - l);
+		l += strlen(snoop_access[i]);
+	}
+
+	if (*out == '\0')
+		strcpy(out, "N/A");
+
+	return repsep_snprintf(bf, size, "%-*s", width, out);
+}
+
 struct sort_entry sort_mispredict = {
 	.se_header	= "Branch Mispredicted",
 	.se_cmp		= sort__mispredict_cmp,
@@ -464,6 +770,91 @@
 	.se_width_idx	= HISTC_MISPREDICT,
 };
 
+static u64 he_weight(struct hist_entry *he)
+{
+	return he->stat.nr_events ? he->stat.weight / he->stat.nr_events : 0;
+}
+
+static int64_t
+sort__local_weight_cmp(struct hist_entry *left, struct hist_entry *right)
+{
+	return he_weight(left) - he_weight(right);
+}
+
+static int hist_entry__local_weight_snprintf(struct hist_entry *self, char *bf,
+				    size_t size, unsigned int width)
+{
+	return repsep_snprintf(bf, size, "%-*llu", width, he_weight(self));
+}
+
+struct sort_entry sort_local_weight = {
+	.se_header	= "Local Weight",
+	.se_cmp		= sort__local_weight_cmp,
+	.se_snprintf	= hist_entry__local_weight_snprintf,
+	.se_width_idx	= HISTC_LOCAL_WEIGHT,
+};
+
+static int64_t
+sort__global_weight_cmp(struct hist_entry *left, struct hist_entry *right)
+{
+	return left->stat.weight - right->stat.weight;
+}
+
+static int hist_entry__global_weight_snprintf(struct hist_entry *self, char *bf,
+					      size_t size, unsigned int width)
+{
+	return repsep_snprintf(bf, size, "%-*llu", width, self->stat.weight);
+}
+
+struct sort_entry sort_global_weight = {
+	.se_header	= "Weight",
+	.se_cmp		= sort__global_weight_cmp,
+	.se_snprintf	= hist_entry__global_weight_snprintf,
+	.se_width_idx	= HISTC_GLOBAL_WEIGHT,
+};
+
+struct sort_entry sort_mem_daddr_sym = {
+	.se_header	= "Data Symbol",
+	.se_cmp		= sort__daddr_cmp,
+	.se_snprintf	= hist_entry__daddr_snprintf,
+	.se_width_idx	= HISTC_MEM_DADDR_SYMBOL,
+};
+
+struct sort_entry sort_mem_daddr_dso = {
+	.se_header	= "Data Object",
+	.se_cmp		= sort__dso_daddr_cmp,
+	.se_snprintf	= hist_entry__dso_daddr_snprintf,
+	.se_width_idx	= HISTC_MEM_DADDR_SYMBOL,
+};
+
+struct sort_entry sort_mem_locked = {
+	.se_header	= "Locked",
+	.se_cmp		= sort__locked_cmp,
+	.se_snprintf	= hist_entry__locked_snprintf,
+	.se_width_idx	= HISTC_MEM_LOCKED,
+};
+
+struct sort_entry sort_mem_tlb = {
+	.se_header	= "TLB access",
+	.se_cmp		= sort__tlb_cmp,
+	.se_snprintf	= hist_entry__tlb_snprintf,
+	.se_width_idx	= HISTC_MEM_TLB,
+};
+
+struct sort_entry sort_mem_lvl = {
+	.se_header	= "Memory access",
+	.se_cmp		= sort__lvl_cmp,
+	.se_snprintf	= hist_entry__lvl_snprintf,
+	.se_width_idx	= HISTC_MEM_LVL,
+};
+
+struct sort_entry sort_mem_snoop = {
+	.se_header	= "Snoop",
+	.se_cmp		= sort__snoop_cmp,
+	.se_snprintf	= hist_entry__snoop_snprintf,
+	.se_width_idx	= HISTC_MEM_SNOOP,
+};
+
 struct sort_dimension {
 	const char		*name;
 	struct sort_entry	*entry;
@@ -480,6 +871,14 @@
 	DIM(SORT_PARENT, "parent", sort_parent),
 	DIM(SORT_CPU, "cpu", sort_cpu),
 	DIM(SORT_SRCLINE, "srcline", sort_srcline),
+	DIM(SORT_LOCAL_WEIGHT, "local_weight", sort_local_weight),
+	DIM(SORT_GLOBAL_WEIGHT, "weight", sort_global_weight),
+	DIM(SORT_MEM_DADDR_SYMBOL, "symbol_daddr", sort_mem_daddr_sym),
+	DIM(SORT_MEM_DADDR_DSO, "dso_daddr", sort_mem_daddr_dso),
+	DIM(SORT_MEM_LOCKED, "locked", sort_mem_locked),
+	DIM(SORT_MEM_TLB, "tlb", sort_mem_tlb),
+	DIM(SORT_MEM_LVL, "mem", sort_mem_lvl),
+	DIM(SORT_MEM_SNOOP, "snoop", sort_mem_snoop),
 };
 
 #undef DIM
@@ -516,7 +915,10 @@
 				return -EINVAL;
 			}
 			sort__has_parent = 1;
-		} else if (sd->entry == &sort_sym) {
+		} else if (sd->entry == &sort_sym ||
+			   sd->entry == &sort_sym_from ||
+			   sd->entry == &sort_sym_to ||
+			   sd->entry == &sort_mem_daddr_sym) {
 			sort__has_sym = 1;
 		}
 
diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h
index b13e56f..f24bdf6 100644
--- a/tools/perf/util/sort.h
+++ b/tools/perf/util/sort.h
@@ -49,6 +49,7 @@
 	u64			period_us;
 	u64			period_guest_sys;
 	u64			period_guest_us;
+	u64			weight;
 	u32			nr_events;
 };
 
@@ -100,7 +101,8 @@
 	struct rb_root		sorted_chain;
 	struct branch_info	*branch_info;
 	struct hists		*hists;
-	struct callchain_root	callchain[0];
+	struct mem_info		*mem_info;
+	struct callchain_root	callchain[0]; /* must be last member */
 };
 
 static inline bool hist_entry__has_pairs(struct hist_entry *he)
@@ -130,6 +132,14 @@
 	SORT_PARENT,
 	SORT_CPU,
 	SORT_SRCLINE,
+	SORT_LOCAL_WEIGHT,
+	SORT_GLOBAL_WEIGHT,
+	SORT_MEM_DADDR_SYMBOL,
+	SORT_MEM_DADDR_DSO,
+	SORT_MEM_LOCKED,
+	SORT_MEM_TLB,
+	SORT_MEM_LVL,
+	SORT_MEM_SNOOP,
 
 	/* branch stack specific sort keys */
 	__SORT_BRANCH_STACK,
diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c
index 54efcb5..4b12bf8 100644
--- a/tools/perf/util/symbol-elf.c
+++ b/tools/perf/util/symbol-elf.c
@@ -806,9 +806,12 @@
 		 * DWARF DW_compile_unit has this, but we don't always have access
 		 * to it...
 		 */
-		demangled = bfd_demangle(NULL, elf_name, DMGL_PARAMS | DMGL_ANSI);
-		if (demangled != NULL)
-			elf_name = demangled;
+		if (symbol_conf.demangle) {
+			demangled = bfd_demangle(NULL, elf_name,
+						 DMGL_PARAMS | DMGL_ANSI);
+			if (demangled != NULL)
+				elf_name = demangled;
+		}
 new_symbol:
 		f = symbol__new(sym.st_value, sym.st_size,
 				GELF_ST_BIND(sym.st_info), elf_name);
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index e6432d8..8cf3b54 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -36,6 +36,7 @@
 	.use_modules	  = true,
 	.try_vmlinux_path = true,
 	.annotate_src	  = true,
+	.demangle	  = true,
 	.symfs            = "",
 };
 
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index b62ca37..5f720dc 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -97,7 +97,8 @@
 			kptr_restrict,
 			annotate_asm_raw,
 			annotate_src,
-			event_group;
+			event_group,
+			demangle;
 	const char	*vmlinux_name,
 			*kallsyms_name,
 			*source_prefix,
@@ -155,6 +156,12 @@
 	struct branch_flags flags;
 };
 
+struct mem_info {
+	struct addr_map_symbol iaddr;
+	struct addr_map_symbol daddr;
+	union perf_mem_data_src data_src;
+};
+
 struct addr_location {
 	struct thread *thread;
 	struct map    *map;
diff --git a/tools/perf/util/trace-event-info.c b/tools/perf/util/trace-event-info.c
index 5729f43..3917eb9 100644
--- a/tools/perf/util/trace-event-info.c
+++ b/tools/perf/util/trace-event-info.c
@@ -43,26 +43,15 @@
 
 #define VERSION "0.5"
 
-static const char *output_file = "trace.info";
 static int output_fd;
 
 
-static void *malloc_or_die(unsigned int size)
-{
-	void *data;
-
-	data = malloc(size);
-	if (!data)
-		die("malloc");
-	return data;
-}
-
 static const char *find_debugfs(void)
 {
 	const char *path = perf_debugfs_mount(NULL);
 
 	if (!path)
-		die("Your kernel not support debugfs filesystem");
+		pr_debug("Your kernel does not support the debugfs filesystem");
 
 	return path;
 }
@@ -81,8 +70,12 @@
 		return tracing;
 
 	debugfs = find_debugfs();
+	if (!debugfs)
+		return NULL;
 
-	tracing = malloc_or_die(strlen(debugfs) + 9);
+	tracing = malloc(strlen(debugfs) + 9);
+	if (!tracing)
+		return NULL;
 
 	sprintf(tracing, "%s/tracing", debugfs);
 
@@ -99,7 +92,9 @@
 	if (!tracing)
 		return NULL;
 
-	file = malloc_or_die(strlen(tracing) + strlen(name) + 2);
+	file = malloc(strlen(tracing) + strlen(name) + 2);
+	if (!file)
+		return NULL;
 
 	sprintf(file, "%s/%s", tracing, name);
 	return file;
@@ -110,17 +105,6 @@
 	free(file);
 }
 
-static ssize_t write_or_die(const void *buf, size_t len)
-{
-	int ret;
-
-	ret = write(output_fd, buf, len);
-	if (ret < 0)
-		die("writing to '%s'", output_file);
-
-	return ret;
-}
-
 int bigendian(void)
 {
 	unsigned char str[] = { 0x1, 0x2, 0x3, 0x4, 0x0, 0x0, 0x0, 0x0};
@@ -131,59 +115,106 @@
 }
 
 /* unfortunately, you can not stat debugfs or proc files for size */
-static void record_file(const char *file, size_t hdr_sz)
+static int record_file(const char *file, ssize_t hdr_sz)
 {
 	unsigned long long size = 0;
 	char buf[BUFSIZ], *sizep;
 	off_t hdr_pos = lseek(output_fd, 0, SEEK_CUR);
 	int r, fd;
+	int err = -EIO;
 
 	fd = open(file, O_RDONLY);
-	if (fd < 0)
-		die("Can't read '%s'", file);
+	if (fd < 0) {
+		pr_debug("Can't read '%s'", file);
+		return -errno;
+	}
 
 	/* put in zeros for file size, then fill true size later */
-	if (hdr_sz)
-		write_or_die(&size, hdr_sz);
+	if (hdr_sz) {
+		if (write(output_fd, &size, hdr_sz) != hdr_sz)
+			goto out;
+	}
 
 	do {
 		r = read(fd, buf, BUFSIZ);
 		if (r > 0) {
 			size += r;
-			write_or_die(buf, r);
+			if (write(output_fd, buf, r) != r)
+				goto out;
 		}
 	} while (r > 0);
-	close(fd);
 
 	/* ugh, handle big-endian hdr_size == 4 */
 	sizep = (char*)&size;
 	if (bigendian())
 		sizep += sizeof(u64) - hdr_sz;
 
-	if (hdr_sz && pwrite(output_fd, sizep, hdr_sz, hdr_pos) < 0)
-		die("writing to %s", output_file);
+	if (hdr_sz && pwrite(output_fd, sizep, hdr_sz, hdr_pos) < 0) {
+		pr_debug("writing file size failed\n");
+		goto out;
+	}
+
+	err = 0;
+out:
+	close(fd);
+	return err;
 }
 
-static void read_header_files(void)
+static int read_header_files(void)
 {
 	char *path;
 	struct stat st;
+	int err = -EIO;
 
 	path = get_tracing_file("events/header_page");
-	if (stat(path, &st) < 0)
-		die("can't read '%s'", path);
+	if (!path) {
+		pr_debug("can't get tracing/events/header_page");
+		return -ENOMEM;
+	}
 
-	write_or_die("header_page", 12);
-	record_file(path, 8);
+	if (stat(path, &st) < 0) {
+		pr_debug("can't read '%s'", path);
+		goto out;
+	}
+
+	if (write(output_fd, "header_page", 12) != 12) {
+		pr_debug("can't write header_page\n");
+		goto out;
+	}
+
+	if (record_file(path, 8) < 0) {
+		pr_debug("can't record header_page file\n");
+		goto out;
+	}
+
 	put_tracing_file(path);
 
 	path = get_tracing_file("events/header_event");
-	if (stat(path, &st) < 0)
-		die("can't read '%s'", path);
+	if (!path) {
+		pr_debug("can't get tracing/events/header_event");
+		err = -ENOMEM;
+		goto out;
+	}
 
-	write_or_die("header_event", 13);
-	record_file(path, 8);
+	if (stat(path, &st) < 0) {
+		pr_debug("can't read '%s'", path);
+		goto out;
+	}
+
+	if (write(output_fd, "header_event", 13) != 13) {
+		pr_debug("can't write header_event\n");
+		goto out;
+	}
+
+	if (record_file(path, 8) < 0) {
+		pr_debug("can't record header_event file\n");
+		goto out;
+	}
+
+	err = 0;
+out:
 	put_tracing_file(path);
+	return err;
 }
 
 static bool name_in_tp_list(char *sys, struct tracepoint_path *tps)
@@ -197,7 +228,7 @@
 	return false;
 }
 
-static void copy_event_system(const char *sys, struct tracepoint_path *tps)
+static int copy_event_system(const char *sys, struct tracepoint_path *tps)
 {
 	struct dirent *dent;
 	struct stat st;
@@ -205,10 +236,13 @@
 	DIR *dir;
 	int count = 0;
 	int ret;
+	int err;
 
 	dir = opendir(sys);
-	if (!dir)
-		die("can't read directory '%s'", sys);
+	if (!dir) {
+		pr_debug("can't read directory '%s'", sys);
+		return -errno;
+	}
 
 	while ((dent = readdir(dir))) {
 		if (dent->d_type != DT_DIR ||
@@ -216,7 +250,11 @@
 		    strcmp(dent->d_name, "..") == 0 ||
 		    !name_in_tp_list(dent->d_name, tps))
 			continue;
-		format = malloc_or_die(strlen(sys) + strlen(dent->d_name) + 10);
+		format = malloc(strlen(sys) + strlen(dent->d_name) + 10);
+		if (!format) {
+			err = -ENOMEM;
+			goto out;
+		}
 		sprintf(format, "%s/%s/format", sys, dent->d_name);
 		ret = stat(format, &st);
 		free(format);
@@ -225,7 +263,11 @@
 		count++;
 	}
 
-	write_or_die(&count, 4);
+	if (write(output_fd, &count, 4) != 4) {
+		err = -EIO;
+		pr_debug("can't write count\n");
+		goto out;
+	}
 
 	rewinddir(dir);
 	while ((dent = readdir(dir))) {
@@ -234,27 +276,45 @@
 		    strcmp(dent->d_name, "..") == 0 ||
 		    !name_in_tp_list(dent->d_name, tps))
 			continue;
-		format = malloc_or_die(strlen(sys) + strlen(dent->d_name) + 10);
+		format = malloc(strlen(sys) + strlen(dent->d_name) + 10);
+		if (!format) {
+			err = -ENOMEM;
+			goto out;
+		}
 		sprintf(format, "%s/%s/format", sys, dent->d_name);
 		ret = stat(format, &st);
 
-		if (ret >= 0)
-			record_file(format, 8);
-
+		if (ret >= 0) {
+			err = record_file(format, 8);
+			if (err) {
+				free(format);
+				goto out;
+			}
+		}
 		free(format);
 	}
+	err = 0;
+out:
 	closedir(dir);
+	return err;
 }
 
-static void read_ftrace_files(struct tracepoint_path *tps)
+static int read_ftrace_files(struct tracepoint_path *tps)
 {
 	char *path;
+	int ret;
 
 	path = get_tracing_file("events/ftrace");
+	if (!path) {
+		pr_debug("can't get tracing/events/ftrace");
+		return -ENOMEM;
+	}
 
-	copy_event_system(path, tps);
+	ret = copy_event_system(path, tps);
 
 	put_tracing_file(path);
+
+	return ret;
 }
 
 static bool system_in_tp_list(char *sys, struct tracepoint_path *tps)
@@ -268,7 +328,7 @@
 	return false;
 }
 
-static void read_event_files(struct tracepoint_path *tps)
+static int read_event_files(struct tracepoint_path *tps)
 {
 	struct dirent *dent;
 	struct stat st;
@@ -277,12 +337,20 @@
 	DIR *dir;
 	int count = 0;
 	int ret;
+	int err;
 
 	path = get_tracing_file("events");
+	if (!path) {
+		pr_debug("can't get tracing/events");
+		return -ENOMEM;
+	}
 
 	dir = opendir(path);
-	if (!dir)
-		die("can't read directory '%s'", path);
+	if (!dir) {
+		err = -errno;
+		pr_debug("can't read directory '%s'", path);
+		goto out;
+	}
 
 	while ((dent = readdir(dir))) {
 		if (dent->d_type != DT_DIR ||
@@ -294,7 +362,11 @@
 		count++;
 	}
 
-	write_or_die(&count, 4);
+	if (write(output_fd, &count, 4) != 4) {
+		err = -EIO;
+		pr_debug("can't write count\n");
+		goto out;
+	}
 
 	rewinddir(dir);
 	while ((dent = readdir(dir))) {
@@ -304,76 +376,77 @@
 		    strcmp(dent->d_name, "ftrace") == 0 ||
 		    !system_in_tp_list(dent->d_name, tps))
 			continue;
-		sys = malloc_or_die(strlen(path) + strlen(dent->d_name) + 2);
+		sys = malloc(strlen(path) + strlen(dent->d_name) + 2);
+		if (!sys) {
+			err = -ENOMEM;
+			goto out;
+		}
 		sprintf(sys, "%s/%s", path, dent->d_name);
 		ret = stat(sys, &st);
 		if (ret >= 0) {
-			write_or_die(dent->d_name, strlen(dent->d_name) + 1);
-			copy_event_system(sys, tps);
+			ssize_t size = strlen(dent->d_name) + 1;
+
+			if (write(output_fd, dent->d_name, size) != size ||
+			    copy_event_system(sys, tps) < 0) {
+				err = -EIO;
+				free(sys);
+				goto out;
+			}
 		}
 		free(sys);
 	}
-
+	err = 0;
+out:
 	closedir(dir);
 	put_tracing_file(path);
+
+	return err;
 }
 
-static void read_proc_kallsyms(void)
+static int read_proc_kallsyms(void)
 {
 	unsigned int size;
 	const char *path = "/proc/kallsyms";
 	struct stat st;
-	int ret;
+	int ret, err = 0;
 
 	ret = stat(path, &st);
 	if (ret < 0) {
 		/* not found */
 		size = 0;
-		write_or_die(&size, 4);
-		return;
+		if (write(output_fd, &size, 4) != 4)
+			err = -EIO;
+		return err;
 	}
-	record_file(path, 4);
+	return record_file(path, 4);
 }
 
-static void read_ftrace_printk(void)
+static int read_ftrace_printk(void)
 {
 	unsigned int size;
 	char *path;
 	struct stat st;
-	int ret;
+	int ret, err = 0;
 
 	path = get_tracing_file("printk_formats");
+	if (!path) {
+		pr_debug("can't get tracing/printk_formats");
+		return -ENOMEM;
+	}
+
 	ret = stat(path, &st);
 	if (ret < 0) {
 		/* not found */
 		size = 0;
-		write_or_die(&size, 4);
+		if (write(output_fd, &size, 4) != 4)
+			err = -EIO;
 		goto out;
 	}
-	record_file(path, 4);
+	err = record_file(path, 4);
 
 out:
 	put_tracing_file(path);
-}
-
-static struct tracepoint_path *
-get_tracepoints_path(struct list_head *pattrs)
-{
-	struct tracepoint_path path, *ppath = &path;
-	struct perf_evsel *pos;
-	int nr_tracepoints = 0;
-
-	list_for_each_entry(pos, pattrs, node) {
-		if (pos->attr.type != PERF_TYPE_TRACEPOINT)
-			continue;
-		++nr_tracepoints;
-		ppath->next = tracepoint_id_to_path(pos->attr.config);
-		if (!ppath->next)
-			die("%s\n", "No memory to alloc tracepoints list");
-		ppath = ppath->next;
-	}
-
-	return nr_tracepoints > 0 ? path.next : NULL;
+	return err;
 }
 
 static void
@@ -389,6 +462,29 @@
 	}
 }
 
+static struct tracepoint_path *
+get_tracepoints_path(struct list_head *pattrs)
+{
+	struct tracepoint_path path, *ppath = &path;
+	struct perf_evsel *pos;
+	int nr_tracepoints = 0;
+
+	list_for_each_entry(pos, pattrs, node) {
+		if (pos->attr.type != PERF_TYPE_TRACEPOINT)
+			continue;
+		++nr_tracepoints;
+		ppath->next = tracepoint_id_to_path(pos->attr.config);
+		if (!ppath->next) {
+			pr_debug("No memory to alloc tracepoints list\n");
+			put_tracepoints_path(&path);
+			return NULL;
+		}
+		ppath = ppath->next;
+	}
+
+	return nr_tracepoints > 0 ? path.next : NULL;
+}
+
 bool have_tracepoints(struct list_head *pattrs)
 {
 	struct perf_evsel *pos;
@@ -400,9 +496,10 @@
 	return false;
 }
 
-static void tracing_data_header(void)
+static int tracing_data_header(void)
 {
 	char buf[20];
+	ssize_t size;
 
 	/* just guessing this is someone's birthday.. ;) */
 	buf[0] = 23;
@@ -410,9 +507,12 @@
 	buf[2] = 68;
 	memcpy(buf + 3, "tracing", 7);
 
-	write_or_die(buf, 10);
+	if (write(output_fd, buf, 10) != 10)
+		return -1;
 
-	write_or_die(VERSION, strlen(VERSION) + 1);
+	size = strlen(VERSION) + 1;
+	if (write(output_fd, VERSION, size) != size)
+		return -1;
 
 	/* save endian */
 	if (bigendian())
@@ -422,14 +522,19 @@
 
 	read_trace_init(buf[0], buf[0]);
 
-	write_or_die(buf, 1);
+	if (write(output_fd, buf, 1) != 1)
+		return -1;
 
 	/* save size of long */
 	buf[0] = sizeof(long);
-	write_or_die(buf, 1);
+	if (write(output_fd, buf, 1) != 1)
+		return -1;
 
 	/* save page_size */
-	write_or_die(&page_size, 4);
+	if (write(output_fd, &page_size, 4) != 4)
+		return -1;
+
+	return 0;
 }
 
 struct tracing_data *tracing_data_get(struct list_head *pattrs,
@@ -437,6 +542,7 @@
 {
 	struct tracepoint_path *tps;
 	struct tracing_data *tdata;
+	int err;
 
 	output_fd = fd;
 
@@ -444,7 +550,10 @@
 	if (!tps)
 		return NULL;
 
-	tdata = malloc_or_die(sizeof(*tdata));
+	tdata = malloc(sizeof(*tdata));
+	if (!tdata)
+		return NULL;
+
 	tdata->temp = temp;
 	tdata->size = 0;
 
@@ -453,12 +562,16 @@
 
 		snprintf(tdata->temp_file, sizeof(tdata->temp_file),
 			 "/tmp/perf-XXXXXX");
-		if (!mkstemp(tdata->temp_file))
-			die("Can't make temp file");
+		if (!mkstemp(tdata->temp_file)) {
+			pr_debug("Can't make temp file");
+			return NULL;
+		}
 
 		temp_fd = open(tdata->temp_file, O_RDWR);
-		if (temp_fd < 0)
-			die("Can't read '%s'", tdata->temp_file);
+		if (temp_fd < 0) {
+			pr_debug("Can't read '%s'", tdata->temp_file);
+			return NULL;
+		}
 
 		/*
 		 * Set the temp file the default output, so all the
@@ -467,13 +580,24 @@
 		output_fd = temp_fd;
 	}
 
-	tracing_data_header();
-	read_header_files();
-	read_ftrace_files(tps);
-	read_event_files(tps);
-	read_proc_kallsyms();
-	read_ftrace_printk();
+	err = tracing_data_header();
+	if (err)
+		goto out;
+	err = read_header_files();
+	if (err)
+		goto out;
+	err = read_ftrace_files(tps);
+	if (err)
+		goto out;
+	err = read_event_files(tps);
+	if (err)
+		goto out;
+	err = read_proc_kallsyms();
+	if (err)
+		goto out;
+	err = read_ftrace_printk();
 
+out:
 	/*
 	 * All tracing data are stored by now, we can restore
 	 * the default output file in case we used temp file.
@@ -484,22 +608,31 @@
 		output_fd = fd;
 	}
 
+	if (err) {
+		free(tdata);
+		tdata = NULL;
+	}
+
 	put_tracepoints_path(tps);
 	return tdata;
 }
 
-void tracing_data_put(struct tracing_data *tdata)
+int tracing_data_put(struct tracing_data *tdata)
 {
+	int err = 0;
+
 	if (tdata->temp) {
-		record_file(tdata->temp_file, 0);
+		err = record_file(tdata->temp_file, 0);
 		unlink(tdata->temp_file);
 	}
 
 	free(tdata);
+	return err;
 }
 
 int read_tracing_data(int fd, struct list_head *pattrs)
 {
+	int err;
 	struct tracing_data *tdata;
 
 	/*
@@ -510,6 +643,6 @@
 	if (!tdata)
 		return -ENOMEM;
 
-	tracing_data_put(tdata);
-	return 0;
+	err = tracing_data_put(tdata);
+	return err;
 }
diff --git a/tools/perf/util/trace-event-read.c b/tools/perf/util/trace-event-read.c
index 7cb2463..af215c0 100644
--- a/tools/perf/util/trace-event-read.c
+++ b/tools/perf/util/trace-event-read.c
@@ -18,8 +18,6 @@
  *
  * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
  */
-#define _FILE_OFFSET_BITS 64
-
 #include <dirent.h>
 #include <stdio.h>
 #include <stdlib.h>
@@ -45,20 +43,10 @@
 int host_bigendian;
 static int long_size;
 
-static ssize_t calc_data_size;
+static ssize_t trace_data_size;
 static bool repipe;
 
-static void *malloc_or_die(int size)
-{
-	void *ret;
-
-	ret = malloc(size);
-	if (!ret)
-		die("malloc");
-	return ret;
-}
-
-static int do_read(int fd, void *buf, int size)
+static int __do_read(int fd, void *buf, int size)
 {
 	int rsize = size;
 
@@ -71,8 +59,10 @@
 		if (repipe) {
 			int retw = write(STDOUT_FILENO, buf, ret);
 
-			if (retw <= 0 || retw != ret)
-				die("repiping input file");
+			if (retw <= 0 || retw != ret) {
+				pr_debug("repiping input file");
+				return -1;
+			}
 		}
 
 		size -= ret;
@@ -82,17 +72,18 @@
 	return rsize;
 }
 
-static int read_or_die(void *data, int size)
+static int do_read(void *data, int size)
 {
 	int r;
 
-	r = do_read(input_fd, data, size);
-	if (r <= 0)
-		die("reading input file (size expected=%d received=%d)",
-		    size, r);
+	r = __do_read(input_fd, data, size);
+	if (r <= 0) {
+		pr_debug("reading input file (size expected=%d received=%d)",
+			 size, r);
+		return -1;
+	}
 
-	if (calc_data_size)
-		calc_data_size += r;
+	trace_data_size += r;
 
 	return r;
 }
@@ -105,7 +96,7 @@
 
 	while (size) {
 		r = size > BUFSIZ ? BUFSIZ : size;
-		read_or_die(buf, r);
+		do_read(buf, r);
 		size -= r;
 	};
 }
@@ -114,7 +105,8 @@
 {
 	unsigned int data;
 
-	read_or_die(&data, 4);
+	if (do_read(&data, 4) < 0)
+		return 0;
 	return __data2host4(pevent, data);
 }
 
@@ -122,7 +114,8 @@
 {
 	unsigned long long data;
 
-	read_or_die(&data, 8);
+	if (do_read(&data, 8) < 0)
+		return 0;
 	return __data2host8(pevent, data);
 }
 
@@ -136,17 +129,23 @@
 
 	for (;;) {
 		r = read(input_fd, &c, 1);
-		if (r < 0)
-			die("reading input file");
+		if (r < 0) {
+			pr_debug("reading input file");
+			goto out;
+		}
 
-		if (!r)
-			die("no data");
+		if (!r) {
+			pr_debug("no data");
+			goto out;
+		}
 
 		if (repipe) {
 			int retw = write(STDOUT_FILENO, &c, 1);
 
-			if (retw <= 0 || retw != r)
-				die("repiping input file string");
+			if (retw <= 0 || retw != r) {
+				pr_debug("repiping input file string");
+				goto out;
+			}
 		}
 
 		buf[size++] = c;
@@ -155,60 +154,79 @@
 			break;
 	}
 
-	if (calc_data_size)
-		calc_data_size += size;
+	trace_data_size += size;
 
-	str = malloc_or_die(size);
-	memcpy(str, buf, size);
-
+	str = malloc(size);
+	if (str)
+		memcpy(str, buf, size);
+out:
 	return str;
 }
 
-static void read_proc_kallsyms(struct pevent *pevent)
+static int read_proc_kallsyms(struct pevent *pevent)
 {
 	unsigned int size;
 	char *buf;
 
 	size = read4(pevent);
 	if (!size)
-		return;
+		return 0;
 
-	buf = malloc_or_die(size + 1);
-	read_or_die(buf, size);
+	buf = malloc(size + 1);
+	if (buf == NULL)
+		return -1;
+
+	if (do_read(buf, size) < 0) {
+		free(buf);
+		return -1;
+	}
 	buf[size] = '\0';
 
 	parse_proc_kallsyms(pevent, buf, size);
 
 	free(buf);
+	return 0;
 }
 
-static void read_ftrace_printk(struct pevent *pevent)
+static int read_ftrace_printk(struct pevent *pevent)
 {
 	unsigned int size;
 	char *buf;
 
+	/* it can have 0 size */
 	size = read4(pevent);
 	if (!size)
-		return;
+		return 0;
 
-	buf = malloc_or_die(size);
-	read_or_die(buf, size);
+	buf = malloc(size);
+	if (buf == NULL)
+		return -1;
+
+	if (do_read(buf, size) < 0) {
+		free(buf);
+		return -1;
+	}
 
 	parse_ftrace_printk(pevent, buf, size);
 
 	free(buf);
+	return 0;
 }
 
-static void read_header_files(struct pevent *pevent)
+static int read_header_files(struct pevent *pevent)
 {
 	unsigned long long size;
 	char *header_event;
 	char buf[BUFSIZ];
+	int ret = 0;
 
-	read_or_die(buf, 12);
+	if (do_read(buf, 12) < 0)
+		return -1;
 
-	if (memcmp(buf, "header_page", 12) != 0)
-		die("did not read header page");
+	if (memcmp(buf, "header_page", 12) != 0) {
+		pr_debug("did not read header page");
+		return -1;
+	}
 
 	size = read8(pevent);
 	skip(size);
@@ -219,70 +237,107 @@
 	 */
 	long_size = header_page_size_size;
 
-	read_or_die(buf, 13);
-	if (memcmp(buf, "header_event", 13) != 0)
-		die("did not read header event");
+	if (do_read(buf, 13) < 0)
+		return -1;
+
+	if (memcmp(buf, "header_event", 13) != 0) {
+		pr_debug("did not read header event");
+		return -1;
+	}
 
 	size = read8(pevent);
-	header_event = malloc_or_die(size);
-	read_or_die(header_event, size);
+	header_event = malloc(size);
+	if (header_event == NULL)
+		return -1;
+
+	if (do_read(header_event, size) < 0)
+		ret = -1;
+
 	free(header_event);
+	return ret;
 }
 
-static void read_ftrace_file(struct pevent *pevent, unsigned long long size)
+static int read_ftrace_file(struct pevent *pevent, unsigned long long size)
 {
 	char *buf;
 
-	buf = malloc_or_die(size);
-	read_or_die(buf, size);
+	buf = malloc(size);
+	if (buf == NULL)
+		return -1;
+
+	if (do_read(buf, size) < 0) {
+		free(buf);
+		return -1;
+	}
+
 	parse_ftrace_file(pevent, buf, size);
 	free(buf);
+	return 0;
 }
 
-static void read_event_file(struct pevent *pevent, char *sys,
+static int read_event_file(struct pevent *pevent, char *sys,
 			    unsigned long long size)
 {
 	char *buf;
 
-	buf = malloc_or_die(size);
-	read_or_die(buf, size);
+	buf = malloc(size);
+	if (buf == NULL)
+		return -1;
+
+	if (do_read(buf, size) < 0) {
+		free(buf);
+		return -1;
+	}
+
 	parse_event_file(pevent, buf, size, sys);
 	free(buf);
+	return 0;
 }
 
-static void read_ftrace_files(struct pevent *pevent)
+static int read_ftrace_files(struct pevent *pevent)
 {
 	unsigned long long size;
 	int count;
 	int i;
+	int ret;
 
 	count = read4(pevent);
 
 	for (i = 0; i < count; i++) {
 		size = read8(pevent);
-		read_ftrace_file(pevent, size);
+		ret = read_ftrace_file(pevent, size);
+		if (ret)
+			return ret;
 	}
+	return 0;
 }
 
-static void read_event_files(struct pevent *pevent)
+static int read_event_files(struct pevent *pevent)
 {
 	unsigned long long size;
 	char *sys;
 	int systems;
 	int count;
 	int i,x;
+	int ret;
 
 	systems = read4(pevent);
 
 	for (i = 0; i < systems; i++) {
 		sys = read_string();
+		if (sys == NULL)
+			return -1;
 
 		count = read4(pevent);
+
 		for (x=0; x < count; x++) {
 			size = read8(pevent);
-			read_event_file(pevent, sys, size);
+			ret = read_event_file(pevent, sys, size);
+			if (ret)
+				return ret;
 		}
 	}
+	return 0;
 }
 
 ssize_t trace_report(int fd, struct pevent **ppevent, bool __repipe)
@@ -293,58 +348,85 @@
 	int show_version = 0;
 	int show_funcs = 0;
 	int show_printk = 0;
-	ssize_t size;
+	ssize_t size = -1;
+	struct pevent *pevent;
+	int err;
 
-	calc_data_size = 1;
+	*ppevent = NULL;
+
 	repipe = __repipe;
-
 	input_fd = fd;
 
-	read_or_die(buf, 3);
-	if (memcmp(buf, test, 3) != 0)
-		die("no trace data in the file");
+	if (do_read(buf, 3) < 0)
+		return -1;
+	if (memcmp(buf, test, 3) != 0) {
+		pr_debug("no trace data in the file");
+		return -1;
+	}
 
-	read_or_die(buf, 7);
-	if (memcmp(buf, "tracing", 7) != 0)
-		die("not a trace file (missing 'tracing' tag)");
+	if (do_read(buf, 7) < 0)
+		return -1;
+	if (memcmp(buf, "tracing", 7) != 0) {
+		pr_debug("not a trace file (missing 'tracing' tag)");
+		return -1;
+	}
 
 	version = read_string();
+	if (version == NULL)
+		return -1;
 	if (show_version)
 		printf("version = %s\n", version);
 	free(version);
 
-	read_or_die(buf, 1);
+	if (do_read(buf, 1) < 0)
+		return -1;
 	file_bigendian = buf[0];
 	host_bigendian = bigendian();
 
-	*ppevent = read_trace_init(file_bigendian, host_bigendian);
-	if (*ppevent == NULL)
-		die("read_trace_init failed");
+	pevent = read_trace_init(file_bigendian, host_bigendian);
+	if (pevent == NULL) {
+		pr_debug("read_trace_init failed");
+		goto out;
+	}
 
-	read_or_die(buf, 1);
+	if (do_read(buf, 1) < 0)
+		goto out;
 	long_size = buf[0];
 
-	page_size = read4(*ppevent);
+	page_size = read4(pevent);
+	if (!page_size)
+		goto out;
 
-	read_header_files(*ppevent);
+	err = read_header_files(pevent);
+	if (err)
+		goto out;
+	err = read_ftrace_files(pevent);
+	if (err)
+		goto out;
+	err = read_event_files(pevent);
+	if (err)
+		goto out;
+	err = read_proc_kallsyms(pevent);
+	if (err)
+		goto out;
+	err = read_ftrace_printk(pevent);
+	if (err)
+		goto out;
 
-	read_ftrace_files(*ppevent);
-	read_event_files(*ppevent);
-	read_proc_kallsyms(*ppevent);
-	read_ftrace_printk(*ppevent);
-
-	size = calc_data_size - 1;
-	calc_data_size = 0;
+	size = trace_data_size;
 	repipe = false;
 
 	if (show_funcs) {
-		pevent_print_funcs(*ppevent);
-		return size;
-	}
-	if (show_printk) {
-		pevent_print_printk(*ppevent);
-		return size;
+		pevent_print_funcs(pevent);
+	} else if (show_printk) {
+		pevent_print_printk(pevent);
 	}
 
+	*ppevent = pevent;
+	pevent = NULL;
+
+out:
+	if (pevent)
+		pevent_free(pevent);
 	return size;
 }
diff --git a/tools/perf/util/trace-event.h b/tools/perf/util/trace-event.h
index 28ccde8..1978c39 100644
--- a/tools/perf/util/trace-event.h
+++ b/tools/perf/util/trace-event.h
@@ -68,7 +68,7 @@
 
 struct tracing_data *tracing_data_get(struct list_head *pattrs,
 				      int fd, bool temp);
-void tracing_data_put(struct tracing_data *tdata);
+int tracing_data_put(struct tracing_data *tdata);
 
 
 struct addr_location;
diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h
index 6a0781c..a45710b 100644
--- a/tools/perf/util/util.h
+++ b/tools/perf/util/util.h
@@ -1,8 +1,6 @@
 #ifndef GIT_COMPAT_UTIL_H
 #define GIT_COMPAT_UTIL_H
 
-#define _FILE_OFFSET_BITS 64
-
 #ifndef FLEX_ARRAY
 /*
  * See if our compiler is known to support flexible array members.