diff --git a/arch/x86/events/intel/pt.c b/arch/x86/events/intel/pt.c
index 3b993942a0e4..8d016ce5b80d 100644
--- a/arch/x86/events/intel/pt.c
+++ b/arch/x86/events/intel/pt.c
@@ -1194,7 +1194,7 @@ static int pt_event_addr_filters_validate(struct list_head *filters)
 		    filter->action == PERF_ADDR_FILTER_ACTION_START)
 			return -EOPNOTSUPP;
 
-		if (!filter->inode) {
+		if (!filter->path.dentry) {
 			if (!valid_kernel_ip(filter->offset))
 				return -EINVAL;
 
@@ -1221,7 +1221,7 @@ static void pt_event_addr_filters_sync(struct perf_event *event)
 		return;
 
 	list_for_each_entry(filter, &head->list, entry) {
-		if (filter->inode && !offs[range]) {
+		if (filter->path.dentry && !offs[range]) {
 			msr_a = msr_b = 0;
 		} else {
 			/* apply the offset */
diff --git a/arch/x86/events/intel/uncore.c b/arch/x86/events/intel/uncore.c
index a7956fc7ca1d..15b07379e72d 100644
--- a/arch/x86/events/intel/uncore.c
+++ b/arch/x86/events/intel/uncore.c
@@ -203,7 +203,7 @@ static void uncore_assign_hw_event(struct intel_uncore_box *box,
 	hwc->idx = idx;
 	hwc->last_tag = ++box->tags[idx];
 
-	if (hwc->idx == UNCORE_PMC_IDX_FIXED) {
+	if (uncore_pmc_fixed(hwc->idx)) {
 		hwc->event_base = uncore_fixed_ctr(box);
 		hwc->config_base = uncore_fixed_ctl(box);
 		return;
@@ -218,7 +218,9 @@ void uncore_perf_event_update(struct intel_uncore_box *box, struct perf_event *e
 	u64 prev_count, new_count, delta;
 	int shift;
 
-	if (event->hw.idx >= UNCORE_PMC_IDX_FIXED)
+	if (uncore_pmc_freerunning(event->hw.idx))
+		shift = 64 - uncore_freerunning_bits(box, event);
+	else if (uncore_pmc_fixed(event->hw.idx))
 		shift = 64 - uncore_fixed_ctr_bits(box);
 	else
 		shift = 64 - uncore_perf_ctr_bits(box);
@@ -449,15 +451,30 @@ static int uncore_assign_events(struct intel_uncore_box *box, int assign[], int
 	return ret ? -EINVAL : 0;
 }
 
-static void uncore_pmu_event_start(struct perf_event *event, int flags)
+void uncore_pmu_event_start(struct perf_event *event, int flags)
 {
 	struct intel_uncore_box *box = uncore_event_to_box(event);
 	int idx = event->hw.idx;
 
-	if (WARN_ON_ONCE(!(event->hw.state & PERF_HES_STOPPED)))
+	if (WARN_ON_ONCE(idx == -1 || idx >= UNCORE_PMC_IDX_MAX))
 		return;
 
-	if (WARN_ON_ONCE(idx == -1 || idx >= UNCORE_PMC_IDX_MAX))
+	/*
+	 * Free running counter is read-only and always active.
+	 * Use the current counter value as start point.
+	 * There is no overflow interrupt for free running counter.
+	 * Use hrtimer to periodically poll the counter to avoid overflow.
+	 */
+	if (uncore_pmc_freerunning(event->hw.idx)) {
+		list_add_tail(&event->active_entry, &box->active_list);
+		local64_set(&event->hw.prev_count,
+			    uncore_read_counter(box, event));
+		if (box->n_active++ == 0)
+			uncore_pmu_start_hrtimer(box);
+		return;
+	}
+
+	if (WARN_ON_ONCE(!(event->hw.state & PERF_HES_STOPPED)))
 		return;
 
 	event->hw.state = 0;
@@ -474,11 +491,20 @@ static void uncore_pmu_event_start(struct perf_event *event, int flags)
 	}
 }
 
-static void uncore_pmu_event_stop(struct perf_event *event, int flags)
+void uncore_pmu_event_stop(struct perf_event *event, int flags)
 {
 	struct intel_uncore_box *box = uncore_event_to_box(event);
 	struct hw_perf_event *hwc = &event->hw;
 
+	/* Cannot disable free running counter which is read-only */
+	if (uncore_pmc_freerunning(hwc->idx)) {
+		list_del(&event->active_entry);
+		if (--box->n_active == 0)
+			uncore_pmu_cancel_hrtimer(box);
+		uncore_perf_event_update(box, event);
+		return;
+	}
+
 	if (__test_and_clear_bit(hwc->idx, box->active_mask)) {
 		uncore_disable_event(box, event);
 		box->n_active--;
@@ -502,7 +528,7 @@ static void uncore_pmu_event_stop(struct perf_event *event, int flags)
 	}
 }
 
-static int uncore_pmu_event_add(struct perf_event *event, int flags)
+int uncore_pmu_event_add(struct perf_event *event, int flags)
 {
 	struct intel_uncore_box *box = uncore_event_to_box(event);
 	struct hw_perf_event *hwc = &event->hw;
@@ -512,6 +538,17 @@ static int uncore_pmu_event_add(struct perf_event *event, int flags)
 	if (!box)
 		return -ENODEV;
 
+	/*
+	 * The free funning counter is assigned in event_init().
+	 * The free running counter event and free running counter
+	 * are 1:1 mapped. It doesn't need to be tracked in event_list.
+	 */
+	if (uncore_pmc_freerunning(hwc->idx)) {
+		if (flags & PERF_EF_START)
+			uncore_pmu_event_start(event, 0);
+		return 0;
+	}
+
 	ret = n = uncore_collect_events(box, event, false);
 	if (ret < 0)
 		return ret;
@@ -563,13 +600,21 @@ static int uncore_pmu_event_add(struct perf_event *event, int flags)
 	return 0;
 }
 
-static void uncore_pmu_event_del(struct perf_event *event, int flags)
+void uncore_pmu_event_del(struct perf_event *event, int flags)
 {
 	struct intel_uncore_box *box = uncore_event_to_box(event);
 	int i;
 
 	uncore_pmu_event_stop(event, PERF_EF_UPDATE);
 
+	/*
+	 * The event for free running counter is not tracked by event_list.
+	 * It doesn't need to force event->hw.idx = -1 to reassign the counter.
+	 * Because the event and the free running counter are 1:1 mapped.
+	 */
+	if (uncore_pmc_freerunning(event->hw.idx))
+		return;
+
 	for (i = 0; i < box->n_events; i++) {
 		if (event == box->event_list[i]) {
 			uncore_put_event_constraint(box, event);
@@ -603,6 +648,10 @@ static int uncore_validate_group(struct intel_uncore_pmu *pmu,
 	struct intel_uncore_box *fake_box;
 	int ret = -EINVAL, n;
 
+	/* The free running counter is always active. */
+	if (uncore_pmc_freerunning(event->hw.idx))
+		return 0;
+
 	fake_box = uncore_alloc_box(pmu->type, NUMA_NO_NODE);
 	if (!fake_box)
 		return -ENOMEM;
@@ -690,6 +739,17 @@ static int uncore_pmu_event_init(struct perf_event *event)
 
 		/* fixed counters have event field hardcoded to zero */
 		hwc->config = 0ULL;
+	} else if (is_freerunning_event(event)) {
+		if (!check_valid_freerunning_event(box, event))
+			return -EINVAL;
+		event->hw.idx = UNCORE_PMC_IDX_FREERUNNING;
+		/*
+		 * The free running counter event and free running counter
+		 * are always 1:1 mapped.
+		 * The free running counter is always active.
+		 * Assign the free running counter here.
+		 */
+		event->hw.event_base = uncore_freerunning_counter(box, event);
 	} else {
 		hwc->config = event->attr.config &
 			      (pmu->type->event_mask | ((u64)pmu->type->event_mask_ext << 32));
diff --git a/arch/x86/events/intel/uncore.h b/arch/x86/events/intel/uncore.h
index 414dc7e7c950..c9e1e0bef3c3 100644
--- a/arch/x86/events/intel/uncore.h
+++ b/arch/x86/events/intel/uncore.h
@@ -12,8 +12,13 @@
 
 #define UNCORE_FIXED_EVENT		0xff
 #define UNCORE_PMC_IDX_MAX_GENERIC	8
+#define UNCORE_PMC_IDX_MAX_FIXED	1
+#define UNCORE_PMC_IDX_MAX_FREERUNNING	1
 #define UNCORE_PMC_IDX_FIXED		UNCORE_PMC_IDX_MAX_GENERIC
-#define UNCORE_PMC_IDX_MAX		(UNCORE_PMC_IDX_FIXED + 1)
+#define UNCORE_PMC_IDX_FREERUNNING	(UNCORE_PMC_IDX_FIXED + \
+					UNCORE_PMC_IDX_MAX_FIXED)
+#define UNCORE_PMC_IDX_MAX		(UNCORE_PMC_IDX_FREERUNNING + \
+					UNCORE_PMC_IDX_MAX_FREERUNNING)
 
 #define UNCORE_PCI_DEV_FULL_DATA(dev, func, type, idx)	\
 		((dev << 24) | (func << 16) | (type << 8) | idx)
@@ -35,6 +40,7 @@ struct intel_uncore_ops;
 struct intel_uncore_pmu;
 struct intel_uncore_box;
 struct uncore_event_desc;
+struct freerunning_counters;
 
 struct intel_uncore_type {
 	const char *name;
@@ -42,6 +48,7 @@ struct intel_uncore_type {
 	int num_boxes;
 	int perf_ctr_bits;
 	int fixed_ctr_bits;
+	int num_freerunning_types;
 	unsigned perf_ctr;
 	unsigned event_ctl;
 	unsigned event_mask;
@@ -59,6 +66,7 @@ struct intel_uncore_type {
 	struct intel_uncore_pmu *pmus;
 	struct intel_uncore_ops *ops;
 	struct uncore_event_desc *event_descs;
+	struct freerunning_counters *freerunning;
 	const struct attribute_group *attr_groups[4];
 	struct pmu *pmu; /* for custom pmu ops */
 };
@@ -129,6 +137,14 @@ struct uncore_event_desc {
 	const char *config;
 };
 
+struct freerunning_counters {
+	unsigned int counter_base;
+	unsigned int counter_offset;
+	unsigned int box_offset;
+	unsigned int num_counters;
+	unsigned int bits;
+};
+
 struct pci2phy_map {
 	struct list_head list;
 	int segment;
@@ -157,6 +173,16 @@ static ssize_t __uncore_##_var##_show(struct kobject *kobj,		\
 static struct kobj_attribute format_attr_##_var =			\
 	__ATTR(_name, 0444, __uncore_##_var##_show, NULL)
 
+static inline bool uncore_pmc_fixed(int idx)
+{
+	return idx == UNCORE_PMC_IDX_FIXED;
+}
+
+static inline bool uncore_pmc_freerunning(int idx)
+{
+	return idx == UNCORE_PMC_IDX_FREERUNNING;
+}
+
 static inline unsigned uncore_pci_box_ctl(struct intel_uncore_box *box)
 {
 	return box->pmu->type->box_ctl;
@@ -214,6 +240,60 @@ static inline unsigned uncore_msr_fixed_ctr(struct intel_uncore_box *box)
 	return box->pmu->type->fixed_ctr + uncore_msr_box_offset(box);
 }
 
+
+/*
+ * In the uncore document, there is no event-code assigned to free running
+ * counters. Some events need to be defined to indicate the free running
+ * counters. The events are encoded as event-code + umask-code.
+ *
+ * The event-code for all free running counters is 0xff, which is the same as
+ * the fixed counters.
+ *
+ * The umask-code is used to distinguish a fixed counter and a free running
+ * counter, and different types of free running counters.
+ * - For fixed counters, the umask-code is 0x0X.
+ *   X indicates the index of the fixed counter, which starts from 0.
+ * - For free running counters, the umask-code uses the rest of the space.
+ *   It would bare the format of 0xXY.
+ *   X stands for the type of free running counters, which starts from 1.
+ *   Y stands for the index of free running counters of same type, which
+ *   starts from 0.
+ *
+ * For example, there are three types of IIO free running counters on Skylake
+ * server, IO CLOCKS counters, BANDWIDTH counters and UTILIZATION counters.
+ * The event-code for all the free running counters is 0xff.
+ * 'ioclk' is the first counter of IO CLOCKS. IO CLOCKS is the first type,
+ * which umask-code starts from 0x10.
+ * So 'ioclk' is encoded as event=0xff,umask=0x10
+ * 'bw_in_port2' is the third counter of BANDWIDTH counters. BANDWIDTH is
+ * the second type, which umask-code starts from 0x20.
+ * So 'bw_in_port2' is encoded as event=0xff,umask=0x22
+ */
+static inline unsigned int uncore_freerunning_idx(u64 config)
+{
+	return ((config >> 8) & 0xf);
+}
+
+#define UNCORE_FREERUNNING_UMASK_START		0x10
+
+static inline unsigned int uncore_freerunning_type(u64 config)
+{
+	return ((((config >> 8) - UNCORE_FREERUNNING_UMASK_START) >> 4) & 0xf);
+}
+
+static inline
+unsigned int uncore_freerunning_counter(struct intel_uncore_box *box,
+					struct perf_event *event)
+{
+	unsigned int type = uncore_freerunning_type(event->attr.config);
+	unsigned int idx = uncore_freerunning_idx(event->attr.config);
+	struct intel_uncore_pmu *pmu = box->pmu;
+
+	return pmu->type->freerunning[type].counter_base +
+	       pmu->type->freerunning[type].counter_offset * idx +
+	       pmu->type->freerunning[type].box_offset * pmu->pmu_idx;
+}
+
 static inline
 unsigned uncore_msr_event_ctl(struct intel_uncore_box *box, int idx)
 {
@@ -276,11 +356,52 @@ static inline int uncore_fixed_ctr_bits(struct intel_uncore_box *box)
 	return box->pmu->type->fixed_ctr_bits;
 }
 
+static inline
+unsigned int uncore_freerunning_bits(struct intel_uncore_box *box,
+				     struct perf_event *event)
+{
+	unsigned int type = uncore_freerunning_type(event->attr.config);
+
+	return box->pmu->type->freerunning[type].bits;
+}
+
+static inline int uncore_num_freerunning(struct intel_uncore_box *box,
+					 struct perf_event *event)
+{
+	unsigned int type = uncore_freerunning_type(event->attr.config);
+
+	return box->pmu->type->freerunning[type].num_counters;
+}
+
+static inline int uncore_num_freerunning_types(struct intel_uncore_box *box,
+					       struct perf_event *event)
+{
+	return box->pmu->type->num_freerunning_types;
+}
+
+static inline bool check_valid_freerunning_event(struct intel_uncore_box *box,
+						 struct perf_event *event)
+{
+	unsigned int type = uncore_freerunning_type(event->attr.config);
+	unsigned int idx = uncore_freerunning_idx(event->attr.config);
+
+	return (type < uncore_num_freerunning_types(box, event)) &&
+	       (idx < uncore_num_freerunning(box, event));
+}
+
 static inline int uncore_num_counters(struct intel_uncore_box *box)
 {
 	return box->pmu->type->num_counters;
 }
 
+static inline bool is_freerunning_event(struct perf_event *event)
+{
+	u64 cfg = event->attr.config;
+
+	return ((cfg & UNCORE_FIXED_EVENT) == UNCORE_FIXED_EVENT) &&
+	       (((cfg >> 8) & 0xff) >= UNCORE_FREERUNNING_UMASK_START);
+}
+
 static inline void uncore_disable_box(struct intel_uncore_box *box)
 {
 	if (box->pmu->type->ops->disable_box)
@@ -346,6 +467,10 @@ struct intel_uncore_box *uncore_pmu_to_box(struct intel_uncore_pmu *pmu, int cpu
 u64 uncore_msr_read_counter(struct intel_uncore_box *box, struct perf_event *event);
 void uncore_pmu_start_hrtimer(struct intel_uncore_box *box);
 void uncore_pmu_cancel_hrtimer(struct intel_uncore_box *box);
+void uncore_pmu_event_start(struct perf_event *event, int flags);
+void uncore_pmu_event_stop(struct perf_event *event, int flags);
+int uncore_pmu_event_add(struct perf_event *event, int flags);
+void uncore_pmu_event_del(struct perf_event *event, int flags);
 void uncore_pmu_event_read(struct perf_event *event);
 void uncore_perf_event_update(struct intel_uncore_box *box, struct perf_event *event);
 struct event_constraint *
diff --git a/arch/x86/events/intel/uncore_nhmex.c b/arch/x86/events/intel/uncore_nhmex.c
index 93e7a8397cde..173e2674be6e 100644
--- a/arch/x86/events/intel/uncore_nhmex.c
+++ b/arch/x86/events/intel/uncore_nhmex.c
@@ -246,7 +246,7 @@ static void nhmex_uncore_msr_enable_event(struct intel_uncore_box *box, struct p
 {
 	struct hw_perf_event *hwc = &event->hw;
 
-	if (hwc->idx >= UNCORE_PMC_IDX_FIXED)
+	if (hwc->idx == UNCORE_PMC_IDX_FIXED)
 		wrmsrl(hwc->config_base, NHMEX_PMON_CTL_EN_BIT0);
 	else if (box->pmu->type->event_mask & NHMEX_PMON_CTL_EN_BIT0)
 		wrmsrl(hwc->config_base, hwc->config | NHMEX_PMON_CTL_EN_BIT22);
diff --git a/arch/x86/events/intel/uncore_snb.c b/arch/x86/events/intel/uncore_snb.c
index aee5e8496be4..8527c3e1038b 100644
--- a/arch/x86/events/intel/uncore_snb.c
+++ b/arch/x86/events/intel/uncore_snb.c
@@ -285,6 +285,15 @@ static struct uncore_event_desc snb_uncore_imc_events[] = {
 #define SNB_UNCORE_PCI_IMC_DATA_WRITES_BASE	0x5054
 #define SNB_UNCORE_PCI_IMC_CTR_BASE		SNB_UNCORE_PCI_IMC_DATA_READS_BASE
 
+enum perf_snb_uncore_imc_freerunning_types {
+	SNB_PCI_UNCORE_IMC_DATA		= 0,
+	SNB_PCI_UNCORE_IMC_FREERUNNING_TYPE_MAX,
+};
+
+static struct freerunning_counters snb_uncore_imc_freerunning[] = {
+	[SNB_PCI_UNCORE_IMC_DATA]     = { SNB_UNCORE_PCI_IMC_DATA_READS_BASE, 0x4, 0x0, 2, 32 },
+};
+
 static struct attribute *snb_uncore_imc_formats_attr[] = {
 	&format_attr_event.attr,
 	NULL,
@@ -341,9 +350,8 @@ static u64 snb_uncore_imc_read_counter(struct intel_uncore_box *box, struct perf
 }
 
 /*
- * custom event_init() function because we define our own fixed, free
- * running counters, so we do not want to conflict with generic uncore
- * logic. Also simplifies processing
+ * Keep the custom event_init() function compatible with old event
+ * encoding for free running counters.
  */
 static int snb_uncore_imc_event_init(struct perf_event *event)
 {
@@ -405,11 +413,11 @@ static int snb_uncore_imc_event_init(struct perf_event *event)
 	switch (cfg) {
 	case SNB_UNCORE_PCI_IMC_DATA_READS:
 		base = SNB_UNCORE_PCI_IMC_DATA_READS_BASE;
-		idx = UNCORE_PMC_IDX_FIXED;
+		idx = UNCORE_PMC_IDX_FREERUNNING;
 		break;
 	case SNB_UNCORE_PCI_IMC_DATA_WRITES:
 		base = SNB_UNCORE_PCI_IMC_DATA_WRITES_BASE;
-		idx = UNCORE_PMC_IDX_FIXED + 1;
+		idx = UNCORE_PMC_IDX_FREERUNNING;
 		break;
 	default:
 		return -EINVAL;
@@ -430,75 +438,6 @@ static int snb_uncore_imc_hw_config(struct intel_uncore_box *box, struct perf_ev
 	return 0;
 }
 
-static void snb_uncore_imc_event_start(struct perf_event *event, int flags)
-{
-	struct intel_uncore_box *box = uncore_event_to_box(event);
-	u64 count;
-
-	if (WARN_ON_ONCE(!(event->hw.state & PERF_HES_STOPPED)))
-		return;
-
-	event->hw.state = 0;
-	box->n_active++;
-
-	list_add_tail(&event->active_entry, &box->active_list);
-
-	count = snb_uncore_imc_read_counter(box, event);
-	local64_set(&event->hw.prev_count, count);
-
-	if (box->n_active == 1)
-		uncore_pmu_start_hrtimer(box);
-}
-
-static void snb_uncore_imc_event_stop(struct perf_event *event, int flags)
-{
-	struct intel_uncore_box *box = uncore_event_to_box(event);
-	struct hw_perf_event *hwc = &event->hw;
-
-	if (!(hwc->state & PERF_HES_STOPPED)) {
-		box->n_active--;
-
-		WARN_ON_ONCE(hwc->state & PERF_HES_STOPPED);
-		hwc->state |= PERF_HES_STOPPED;
-
-		list_del(&event->active_entry);
-
-		if (box->n_active == 0)
-			uncore_pmu_cancel_hrtimer(box);
-	}
-
-	if ((flags & PERF_EF_UPDATE) && !(hwc->state & PERF_HES_UPTODATE)) {
-		/*
-		 * Drain the remaining delta count out of a event
-		 * that we are disabling:
-		 */
-		uncore_perf_event_update(box, event);
-		hwc->state |= PERF_HES_UPTODATE;
-	}
-}
-
-static int snb_uncore_imc_event_add(struct perf_event *event, int flags)
-{
-	struct intel_uncore_box *box = uncore_event_to_box(event);
-	struct hw_perf_event *hwc = &event->hw;
-
-	if (!box)
-		return -ENODEV;
-
-	hwc->state = PERF_HES_UPTODATE | PERF_HES_STOPPED;
-	if (!(flags & PERF_EF_START))
-		hwc->state |= PERF_HES_ARCH;
-
-	snb_uncore_imc_event_start(event, 0);
-
-	return 0;
-}
-
-static void snb_uncore_imc_event_del(struct perf_event *event, int flags)
-{
-	snb_uncore_imc_event_stop(event, PERF_EF_UPDATE);
-}
-
 int snb_pci2phy_map_init(int devid)
 {
 	struct pci_dev *dev = NULL;
@@ -530,10 +469,10 @@ int snb_pci2phy_map_init(int devid)
 static struct pmu snb_uncore_imc_pmu = {
 	.task_ctx_nr	= perf_invalid_context,
 	.event_init	= snb_uncore_imc_event_init,
-	.add		= snb_uncore_imc_event_add,
-	.del		= snb_uncore_imc_event_del,
-	.start		= snb_uncore_imc_event_start,
-	.stop		= snb_uncore_imc_event_stop,
+	.add		= uncore_pmu_event_add,
+	.del		= uncore_pmu_event_del,
+	.start		= uncore_pmu_event_start,
+	.stop		= uncore_pmu_event_stop,
 	.read		= uncore_pmu_event_read,
 };
 
@@ -552,12 +491,10 @@ static struct intel_uncore_type snb_uncore_imc = {
 	.name		= "imc",
 	.num_counters   = 2,
 	.num_boxes	= 1,
-	.fixed_ctr_bits	= 32,
-	.fixed_ctr	= SNB_UNCORE_PCI_IMC_CTR_BASE,
+	.num_freerunning_types	= SNB_PCI_UNCORE_IMC_FREERUNNING_TYPE_MAX,
+	.freerunning	= snb_uncore_imc_freerunning,
 	.event_descs	= snb_uncore_imc_events,
 	.format_group	= &snb_uncore_imc_format_group,
-	.perf_ctr	= SNB_UNCORE_PCI_IMC_DATA_READS_BASE,
-	.event_mask	= SNB_UNCORE_PCI_IMC_EVENT_MASK,
 	.ops		= &snb_uncore_imc_ops,
 	.pmu		= &snb_uncore_imc_pmu,
 };
diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c
index 77076a102e34..87dc0263a2e1 100644
--- a/arch/x86/events/intel/uncore_snbep.c
+++ b/arch/x86/events/intel/uncore_snbep.c
@@ -3522,6 +3522,87 @@ static struct intel_uncore_type skx_uncore_iio = {
 	.format_group		= &skx_uncore_iio_format_group,
 };
 
+enum perf_uncore_iio_freerunning_type_id {
+	SKX_IIO_MSR_IOCLK			= 0,
+	SKX_IIO_MSR_BW				= 1,
+	SKX_IIO_MSR_UTIL			= 2,
+
+	SKX_IIO_FREERUNNING_TYPE_MAX,
+};
+
+
+static struct freerunning_counters skx_iio_freerunning[] = {
+	[SKX_IIO_MSR_IOCLK]	= { 0xa45, 0x1, 0x20, 1, 36 },
+	[SKX_IIO_MSR_BW]	= { 0xb00, 0x1, 0x10, 8, 36 },
+	[SKX_IIO_MSR_UTIL]	= { 0xb08, 0x1, 0x10, 8, 36 },
+};
+
+static struct uncore_event_desc skx_uncore_iio_freerunning_events[] = {
+	/* Free-Running IO CLOCKS Counter */
+	INTEL_UNCORE_EVENT_DESC(ioclk,			"event=0xff,umask=0x10"),
+	/* Free-Running IIO BANDWIDTH Counters */
+	INTEL_UNCORE_EVENT_DESC(bw_in_port0,		"event=0xff,umask=0x20"),
+	INTEL_UNCORE_EVENT_DESC(bw_in_port0.scale,	"3.814697266e-6"),
+	INTEL_UNCORE_EVENT_DESC(bw_in_port0.unit,	"MiB"),
+	INTEL_UNCORE_EVENT_DESC(bw_in_port1,		"event=0xff,umask=0x21"),
+	INTEL_UNCORE_EVENT_DESC(bw_in_port1.scale,	"3.814697266e-6"),
+	INTEL_UNCORE_EVENT_DESC(bw_in_port1.unit,	"MiB"),
+	INTEL_UNCORE_EVENT_DESC(bw_in_port2,		"event=0xff,umask=0x22"),
+	INTEL_UNCORE_EVENT_DESC(bw_in_port2.scale,	"3.814697266e-6"),
+	INTEL_UNCORE_EVENT_DESC(bw_in_port2.unit,	"MiB"),
+	INTEL_UNCORE_EVENT_DESC(bw_in_port3,		"event=0xff,umask=0x23"),
+	INTEL_UNCORE_EVENT_DESC(bw_in_port3.scale,	"3.814697266e-6"),
+	INTEL_UNCORE_EVENT_DESC(bw_in_port3.unit,	"MiB"),
+	INTEL_UNCORE_EVENT_DESC(bw_out_port0,		"event=0xff,umask=0x24"),
+	INTEL_UNCORE_EVENT_DESC(bw_out_port0.scale,	"3.814697266e-6"),
+	INTEL_UNCORE_EVENT_DESC(bw_out_port0.unit,	"MiB"),
+	INTEL_UNCORE_EVENT_DESC(bw_out_port1,		"event=0xff,umask=0x25"),
+	INTEL_UNCORE_EVENT_DESC(bw_out_port1.scale,	"3.814697266e-6"),
+	INTEL_UNCORE_EVENT_DESC(bw_out_port1.unit,	"MiB"),
+	INTEL_UNCORE_EVENT_DESC(bw_out_port2,		"event=0xff,umask=0x26"),
+	INTEL_UNCORE_EVENT_DESC(bw_out_port2.scale,	"3.814697266e-6"),
+	INTEL_UNCORE_EVENT_DESC(bw_out_port2.unit,	"MiB"),
+	INTEL_UNCORE_EVENT_DESC(bw_out_port3,		"event=0xff,umask=0x27"),
+	INTEL_UNCORE_EVENT_DESC(bw_out_port3.scale,	"3.814697266e-6"),
+	INTEL_UNCORE_EVENT_DESC(bw_out_port3.unit,	"MiB"),
+	/* Free-running IIO UTILIZATION Counters */
+	INTEL_UNCORE_EVENT_DESC(util_in_port0,		"event=0xff,umask=0x30"),
+	INTEL_UNCORE_EVENT_DESC(util_out_port0,		"event=0xff,umask=0x31"),
+	INTEL_UNCORE_EVENT_DESC(util_in_port1,		"event=0xff,umask=0x32"),
+	INTEL_UNCORE_EVENT_DESC(util_out_port1,		"event=0xff,umask=0x33"),
+	INTEL_UNCORE_EVENT_DESC(util_in_port2,		"event=0xff,umask=0x34"),
+	INTEL_UNCORE_EVENT_DESC(util_out_port2,		"event=0xff,umask=0x35"),
+	INTEL_UNCORE_EVENT_DESC(util_in_port3,		"event=0xff,umask=0x36"),
+	INTEL_UNCORE_EVENT_DESC(util_out_port3,		"event=0xff,umask=0x37"),
+	{ /* end: all zeroes */ },
+};
+
+static struct intel_uncore_ops skx_uncore_iio_freerunning_ops = {
+	.read_counter		= uncore_msr_read_counter,
+};
+
+static struct attribute *skx_uncore_iio_freerunning_formats_attr[] = {
+	&format_attr_event.attr,
+	&format_attr_umask.attr,
+	NULL,
+};
+
+static const struct attribute_group skx_uncore_iio_freerunning_format_group = {
+	.name = "format",
+	.attrs = skx_uncore_iio_freerunning_formats_attr,
+};
+
+static struct intel_uncore_type skx_uncore_iio_free_running = {
+	.name			= "iio_free_running",
+	.num_counters		= 17,
+	.num_boxes		= 6,
+	.num_freerunning_types	= SKX_IIO_FREERUNNING_TYPE_MAX,
+	.freerunning		= skx_iio_freerunning,
+	.ops			= &skx_uncore_iio_freerunning_ops,
+	.event_descs		= skx_uncore_iio_freerunning_events,
+	.format_group		= &skx_uncore_iio_freerunning_format_group,
+};
+
 static struct attribute *skx_uncore_formats_attr[] = {
 	&format_attr_event.attr,
 	&format_attr_umask.attr,
@@ -3595,6 +3676,7 @@ static struct intel_uncore_type *skx_msr_uncores[] = {
 	&skx_uncore_ubox,
 	&skx_uncore_chabox,
 	&skx_uncore_iio,
+	&skx_uncore_iio_free_running,
 	&skx_uncore_irp,
 	&skx_uncore_pcu,
 	NULL,
diff --git a/arch/x86/kernel/perf_regs.c b/arch/x86/kernel/perf_regs.c
index e47b2dbbdef3..c06c4c16c6b6 100644
--- a/arch/x86/kernel/perf_regs.c
+++ b/arch/x86/kernel/perf_regs.c
@@ -151,17 +151,19 @@ void perf_get_regs_user(struct perf_regs *regs_user,
 	regs_user_copy->sp = user_regs->sp;
 	regs_user_copy->cs = user_regs->cs;
 	regs_user_copy->ss = user_regs->ss;
-
 	/*
-	 * Most system calls don't save these registers, don't report them.
+	 * Store user space frame-pointer value on sample
+	 * to facilitate stack unwinding for cases when
+	 * user space executable code has such support
+	 * enabled at compile time:
 	 */
+	regs_user_copy->bp = user_regs->bp;
+
 	regs_user_copy->bx = -1;
-	regs_user_copy->bp = -1;
 	regs_user_copy->r12 = -1;
 	regs_user_copy->r13 = -1;
 	regs_user_copy->r14 = -1;
 	regs_user_copy->r15 = -1;
-
 	/*
 	 * For this to be at all useful, we need a reasonable guess for
 	 * the ABI.  Be careful: we're in NMI context, and we're
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index e71e99eb9a4e..bea0b0cd4bf7 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -467,7 +467,7 @@ enum perf_addr_filter_action_t {
  */
 struct perf_addr_filter {
 	struct list_head	entry;
-	struct inode		*inode;
+	struct path		path;
 	unsigned long		offset;
 	unsigned long		size;
 	enum perf_addr_filter_action_t	action;
@@ -1016,6 +1016,14 @@ static inline int is_software_event(struct perf_event *event)
 	return event->event_caps & PERF_EV_CAP_SOFTWARE;
 }
 
+/*
+ * Return 1 for event in sw context, 0 for event in hw context
+ */
+static inline int in_software_context(struct perf_event *event)
+{
+	return event->ctx->pmu->task_ctx_nr == perf_sw_context;
+}
+
 extern struct static_key perf_swevent_enabled[PERF_COUNT_SW_MAX];
 
 extern void ___perf_sw_event(u32, u64, struct pt_regs *, u64);
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 67612ce359ad..08f5e1b42b43 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -5120,6 +5120,8 @@ static long perf_compat_ioctl(struct file *file, unsigned int cmd,
 	switch (_IOC_NR(cmd)) {
 	case _IOC_NR(PERF_EVENT_IOC_SET_FILTER):
 	case _IOC_NR(PERF_EVENT_IOC_ID):
+	case _IOC_NR(PERF_EVENT_IOC_QUERY_BPF):
+	case _IOC_NR(PERF_EVENT_IOC_MODIFY_ATTRIBUTES):
 		/* Fix up pointer size (usually 4 -> 8 in 32-on-64-bit case */
 		if (_IOC_SIZE(cmd) == sizeof(compat_uptr_t)) {
 			cmd &= ~IOCSIZE_MASK;
@@ -6668,7 +6670,7 @@ static void perf_event_addr_filters_exec(struct perf_event *event, void *data)
 
 	raw_spin_lock_irqsave(&ifh->lock, flags);
 	list_for_each_entry(filter, &ifh->list, entry) {
-		if (filter->inode) {
+		if (filter->path.dentry) {
 			event->addr_filters_offs[count] = 0;
 			restart++;
 		}
@@ -7333,7 +7335,7 @@ static bool perf_addr_filter_match(struct perf_addr_filter *filter,
 				     struct file *file, unsigned long offset,
 				     unsigned long size)
 {
-	if (filter->inode != file_inode(file))
+	if (d_inode(filter->path.dentry) != file_inode(file))
 		return false;
 
 	if (filter->offset > offset + size)
@@ -8686,8 +8688,7 @@ static void free_filters_list(struct list_head *filters)
 	struct perf_addr_filter *filter, *iter;
 
 	list_for_each_entry_safe(filter, iter, filters, entry) {
-		if (filter->inode)
-			iput(filter->inode);
+		path_put(&filter->path);
 		list_del(&filter->entry);
 		kfree(filter);
 	}
@@ -8784,7 +8785,7 @@ static void perf_event_addr_filters_apply(struct perf_event *event)
 		 * Adjust base offset if the filter is associated to a binary
 		 * that needs to be mapped:
 		 */
-		if (filter->inode)
+		if (filter->path.dentry)
 			event->addr_filters_offs[count] =
 				perf_addr_filter_apply(filter, mm);
 
@@ -8858,7 +8859,6 @@ perf_event_parse_addr_filter(struct perf_event *event, char *fstr,
 {
 	struct perf_addr_filter *filter = NULL;
 	char *start, *orig, *filename = NULL;
-	struct path path;
 	substring_t args[MAX_OPT_ARGS];
 	int state = IF_STATE_ACTION, token;
 	unsigned int kernel = 0;
@@ -8971,19 +8971,18 @@ perf_event_parse_addr_filter(struct perf_event *event, char *fstr,
 					goto fail_free_name;
 
 				/* look up the path and grab its inode */
-				ret = kern_path(filename, LOOKUP_FOLLOW, &path);
+				ret = kern_path(filename, LOOKUP_FOLLOW,
+						&filter->path);
 				if (ret)
 					goto fail_free_name;
 
-				filter->inode = igrab(d_inode(path.dentry));
-				path_put(&path);
 				kfree(filename);
 				filename = NULL;
 
 				ret = -EINVAL;
-				if (!filter->inode ||
-				    !S_ISREG(filter->inode->i_mode))
-					/* free_filters_list() will iput() */
+				if (!filter->path.dentry ||
+				    !S_ISREG(d_inode(filter->path.dentry)
+					     ->i_mode))
 					goto fail;
 
 				event->addr_filters.nr_file_filters++;
@@ -10521,19 +10520,20 @@ SYSCALL_DEFINE5(perf_event_open,
 	if (pmu->task_ctx_nr == perf_sw_context)
 		event->event_caps |= PERF_EV_CAP_SOFTWARE;
 
-	if (group_leader &&
-	    (is_software_event(event) != is_software_event(group_leader))) {
-		if (is_software_event(event)) {
+	if (group_leader) {
+		if (is_software_event(event) &&
+		    !in_software_context(group_leader)) {
 			/*
-			 * If event and group_leader are not both a software
-			 * event, and event is, then group leader is not.
+			 * If the event is a sw event, but the group_leader
+			 * is on hw context.
 			 *
-			 * Allow the addition of software events to !software
-			 * groups, this is safe because software events never
-			 * fail to schedule.
+			 * Allow the addition of software events to hw
+			 * groups, this is safe because software events
+			 * never fail to schedule.
 			 */
-			pmu = group_leader->pmu;
-		} else if (is_software_event(group_leader) &&
+			pmu = group_leader->ctx->pmu;
+		} else if (!is_software_event(event) &&
+			   is_software_event(group_leader) &&
 			   (group_leader->group_caps & PERF_EV_CAP_SOFTWARE)) {
 			/*
 			 * In case the group is a pure software group, and we
diff --git a/tools/include/linux/compiler-gcc.h b/tools/include/linux/compiler-gcc.h
index a3a4427441bf..70fe61295733 100644
--- a/tools/include/linux/compiler-gcc.h
+++ b/tools/include/linux/compiler-gcc.h
@@ -21,6 +21,9 @@
 /* &a[0] degrades to a pointer: a different type from an array */
 #define __must_be_array(a)	BUILD_BUG_ON_ZERO(__same_type((a), &(a)[0]))
 
+#ifndef __pure
+#define  __pure		__attribute__((pure))
+#endif
 #define  noinline	__attribute__((noinline))
 #ifndef __packed
 #define __packed	__attribute__((packed))
diff --git a/tools/lib/api/fs/tracing_path.c b/tools/lib/api/fs/tracing_path.c
index 7b7fd0b18551..120037496f77 100644
--- a/tools/lib/api/fs/tracing_path.c
+++ b/tools/lib/api/fs/tracing_path.c
@@ -13,11 +13,9 @@
 
 #include "tracing_path.h"
 
-
-char tracing_mnt[PATH_MAX]         = "/sys/kernel/debug";
-char tracing_path[PATH_MAX]        = "/sys/kernel/debug/tracing";
-char tracing_events_path[PATH_MAX] = "/sys/kernel/debug/tracing/events";
-
+static char tracing_mnt[PATH_MAX]  = "/sys/kernel/debug";
+static char tracing_path[PATH_MAX]        = "/sys/kernel/debug/tracing";
+static char tracing_events_path[PATH_MAX] = "/sys/kernel/debug/tracing/events";
 
 static void __tracing_path_set(const char *tracing, const char *mountpoint)
 {
@@ -76,7 +74,7 @@ char *get_tracing_file(const char *name)
 {
 	char *file;
 
-	if (asprintf(&file, "%s/%s", tracing_path, name) < 0)
+	if (asprintf(&file, "%s/%s", tracing_path_mount(), name) < 0)
 		return NULL;
 
 	return file;
@@ -87,6 +85,34 @@ void put_tracing_file(char *file)
 	free(file);
 }
 
+char *get_events_file(const char *name)
+{
+	char *file;
+
+	if (asprintf(&file, "%s/events/%s", tracing_path_mount(), name) < 0)
+		return NULL;
+
+	return file;
+}
+
+void put_events_file(char *file)
+{
+	free(file);
+}
+
+DIR *tracing_events__opendir(void)
+{
+	DIR *dir = NULL;
+	char *path = get_tracing_file("events");
+
+	if (path) {
+		dir = opendir(path);
+		put_events_file(path);
+	}
+
+	return dir;
+}
+
 int tracing_path__strerror_open_tp(int err, char *buf, size_t size,
 				   const char *sys, const char *name)
 {
@@ -129,7 +155,7 @@ int tracing_path__strerror_open_tp(int err, char *buf, size_t size,
 		snprintf(buf, size,
 			 "Error:\tNo permissions to read %s/%s\n"
 			 "Hint:\tTry 'sudo mount -o remount,mode=755 %s'\n",
-			 tracing_events_path, filename, tracing_mnt);
+			 tracing_events_path, filename, tracing_path_mount());
 	}
 		break;
 	default:
diff --git a/tools/lib/api/fs/tracing_path.h b/tools/lib/api/fs/tracing_path.h
index 0066f06cc381..a19136b086dc 100644
--- a/tools/lib/api/fs/tracing_path.h
+++ b/tools/lib/api/fs/tracing_path.h
@@ -3,9 +3,9 @@
 #define __API_FS_TRACING_PATH_H
 
 #include <linux/types.h>
+#include <dirent.h>
 
-extern char tracing_path[];
-extern char tracing_events_path[];
+DIR *tracing_events__opendir(void);
 
 void tracing_path_set(const char *mountpoint);
 const char *tracing_path_mount(void);
@@ -13,5 +13,10 @@ const char *tracing_path_mount(void);
 char *get_tracing_file(const char *name);
 void put_tracing_file(char *file);
 
+char *get_events_file(const char *name);
+void put_events_file(char *file);
+
+#define zput_events_file(ptr) ({ free(*ptr); *ptr = NULL; })
+
 int tracing_path__strerror_open_tp(int err, char *buf, size_t size, const char *sys, const char *name);
 #endif /* __API_FS_TRACING_PATH_H */
diff --git a/tools/lib/symbol/kallsyms.c b/tools/lib/symbol/kallsyms.c
index 689b6a130dd7..96d830545bbb 100644
--- a/tools/lib/symbol/kallsyms.c
+++ b/tools/lib/symbol/kallsyms.c
@@ -10,6 +10,12 @@ u8 kallsyms2elf_type(char type)
 	return (type == 't' || type == 'w') ? STT_FUNC : STT_OBJECT;
 }
 
+bool kallsyms__is_function(char symbol_type)
+{
+	symbol_type = toupper(symbol_type);
+	return symbol_type == 'T' || symbol_type == 'W';
+}
+
 int kallsyms__parse(const char *filename, void *arg,
 		    int (*process_symbol)(void *arg, const char *name,
 					  char type, u64 start))
diff --git a/tools/lib/symbol/kallsyms.h b/tools/lib/symbol/kallsyms.h
index bc40101d72c1..72ab9870454b 100644
--- a/tools/lib/symbol/kallsyms.h
+++ b/tools/lib/symbol/kallsyms.h
@@ -20,6 +20,8 @@ static inline u8 kallsyms2elf_binding(char type)
 
 u8 kallsyms2elf_type(char type);
 
+bool kallsyms__is_function(char symbol_type);
+
 int kallsyms__parse(const char *filename, void *arg,
 		    int (*process_symbol)(void *arg, const char *name,
 					  char type, u64 start));
diff --git a/tools/perf/Documentation/Makefile b/tools/perf/Documentation/Makefile
index db11478e30b4..42261a9b280e 100644
--- a/tools/perf/Documentation/Makefile
+++ b/tools/perf/Documentation/Makefile
@@ -47,7 +47,8 @@ man5dir=$(mandir)/man5
 man7dir=$(mandir)/man7
 
 ASCIIDOC=asciidoc
-ASCIIDOC_EXTRA = --unsafe
+ASCIIDOC_EXTRA = --unsafe -f asciidoc.conf
+ASCIIDOC_HTML = xhtml11
 MANPAGE_XSL = manpage-normal.xsl
 XMLTO_EXTRA =
 INSTALL?=install
@@ -55,6 +56,14 @@ RM ?= rm -f
 DOC_REF = origin/man
 HTML_REF = origin/html
 
+ifdef USE_ASCIIDOCTOR
+ASCIIDOC = asciidoctor
+ASCIIDOC_EXTRA = -a compat-mode
+ASCIIDOC_EXTRA += -I. -rasciidoctor-extensions
+ASCIIDOC_EXTRA += -a mansource="perf" -a manmanual="perf Manual"
+ASCIIDOC_HTML = xhtml5
+endif
+
 infodir?=$(prefix)/share/info
 MAKEINFO=makeinfo
 INSTALL_INFO=install-info
@@ -73,10 +82,12 @@ ifeq ($(_tmp_tool_path),)
 	missing_tools = $(ASCIIDOC)
 endif
 
+ifndef USE_ASCIIDOCTOR
 _tmp_tool_path := $(call get-executable,$(XMLTO))
 ifeq ($(_tmp_tool_path),)
 	missing_tools += $(XMLTO)
 endif
+endif
 
 #
 # For asciidoc ...
@@ -264,17 +275,25 @@ clean:
 
 $(MAN_HTML): $(OUTPUT)%.html : %.txt
 	$(QUIET_ASCIIDOC)$(RM) $@+ $@ && \
-	$(ASCIIDOC) -b xhtml11 -d manpage -f asciidoc.conf \
+	$(ASCIIDOC) -b $(ASCIIDOC_HTML) -d manpage \
 		$(ASCIIDOC_EXTRA) -aperf_version=$(PERF_VERSION) -o $@+ $< && \
 	mv $@+ $@
 
+ifdef USE_ASCIIDOCTOR
+$(OUTPUT)%.1 $(OUTPUT)%.5 $(OUTPUT)%.7 : $(OUTPUT)%.txt
+	$(QUIET_ASCIIDOC)$(RM) $@+ $@ && \
+	$(ASCIIDOC) -b manpage -d manpage \
+		$(ASCIIDOC_EXTRA) -aperf_version=$(PERF_VERSION) -o $@+ $< && \
+	mv $@+ $@
+endif
+
 $(OUTPUT)%.1 $(OUTPUT)%.5 $(OUTPUT)%.7 : $(OUTPUT)%.xml
 	$(QUIET_XMLTO)$(RM) $@ && \
 	$(XMLTO) -o $(OUTPUT). -m $(MANPAGE_XSL) $(XMLTO_EXTRA) man $<
 
 $(OUTPUT)%.xml : %.txt
 	$(QUIET_ASCIIDOC)$(RM) $@+ $@ && \
-	$(ASCIIDOC) -b docbook -d manpage -f asciidoc.conf \
+	$(ASCIIDOC) -b docbook -d manpage \
 		$(ASCIIDOC_EXTRA) -aperf_version=$(PERF_VERSION) -o $@+ $< && \
 	mv $@+ $@
 
@@ -321,13 +340,13 @@ howto-index.txt: howto-index.sh $(wildcard howto/*.txt)
 	mv $@+ $@
 
 $(patsubst %,%.html,$(ARTICLES)) : %.html : %.txt
-	$(QUIET_ASCIIDOC)$(ASCIIDOC) -b xhtml11 $*.txt
+	$(QUIET_ASCIIDOC)$(ASCIIDOC) -b $(ASCIIDOC_HTML) $*.txt
 
 WEBDOC_DEST = /pub/software/tools/perf/docs
 
 $(patsubst %.txt,%.html,$(wildcard howto/*.txt)): %.html : %.txt
 	$(QUIET_ASCIIDOC)$(RM) $@+ $@ && \
-	sed -e '1,/^$$/d' $< | $(ASCIIDOC) -b xhtml11 - >$@+ && \
+	sed -e '1,/^$$/d' $< | $(ASCIIDOC) -b $(ASCIIDOC_HTML) - >$@+ && \
 	mv $@+ $@
 
 # UNIMPLEMENTED
diff --git a/tools/perf/Documentation/asciidoctor-extensions.rb b/tools/perf/Documentation/asciidoctor-extensions.rb
new file mode 100644
index 000000000000..d148fe95c0c4
--- /dev/null
+++ b/tools/perf/Documentation/asciidoctor-extensions.rb
@@ -0,0 +1,29 @@
+require 'asciidoctor'
+require 'asciidoctor/extensions'
+
+module Perf
+  module Documentation
+    class LinkPerfProcessor < Asciidoctor::Extensions::InlineMacroProcessor
+      use_dsl
+
+      named :chrome
+
+      def process(parent, target, attrs)
+        if parent.document.basebackend? 'html'
+          %(<a href="#{target}.html">#{target}(#{attrs[1]})</a>\n)
+        elsif parent.document.basebackend? 'manpage'
+          "#{target}(#{attrs[1]})"
+        elsif parent.document.basebackend? 'docbook'
+          "<citerefentry>\n" \
+            "<refentrytitle>#{target}</refentrytitle>" \
+            "<manvolnum>#{attrs[1]}</manvolnum>\n" \
+          "</citerefentry>\n"
+        end
+      end
+    end
+  end
+end
+
+Asciidoctor::Extensions.register do
+  inline_macro Perf::Documentation::LinkPerfProcessor, :linkperf
+end
diff --git a/tools/perf/Documentation/perf-buildid-cache.txt b/tools/perf/Documentation/perf-buildid-cache.txt
index 73c2650bd0db..f6de0952ff3c 100644
--- a/tools/perf/Documentation/perf-buildid-cache.txt
+++ b/tools/perf/Documentation/perf-buildid-cache.txt
@@ -48,6 +48,9 @@ OPTIONS
 --purge=::
         Purge all cached binaries including older caches which have specified
 	path from the cache.
+-P::
+--purge-all::
+	Purge all cached binaries. This will flush out entire cache.
 -M::
 --missing=::
 	List missing build ids in the cache for the specified file.
@@ -59,7 +62,9 @@ OPTIONS
 	exactly same build-id, that is replaced by new one. It can be used
 	to update kallsyms and kernel dso to vmlinux in order to support
 	annotation.
-
+-l::
+--list::
+	List all valid binaries from cache.
 -v::
 --verbose::
 	Be more verbose.
diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt
index e6c3b4e555c2..3a822f308e6d 100644
--- a/tools/perf/Documentation/perf-stat.txt
+++ b/tools/perf/Documentation/perf-stat.txt
@@ -116,6 +116,22 @@ Do not aggregate counts across all monitored CPUs.
 print counts using a CSV-style output to make it easy to import directly into
 spreadsheets. Columns are separated by the string specified in SEP.
 
+--table:: Display time for each run (-r option), in a table format, e.g.:
+
+  $ perf stat --null -r 5 --table perf bench sched pipe
+
+   Performance counter stats for 'perf bench sched pipe' (5 runs):
+
+             # Table of individual measurements:
+             5.189 (-0.293) #
+             5.189 (-0.294) #
+             5.186 (-0.296) #
+             5.663 (+0.181) ##
+             6.186 (+0.703) ####
+
+             # Final result:
+             5.483 +- 0.198 seconds time elapsed  ( +-  3.62% )
+
 -G name::
 --cgroup name::
 monitor only in the container (cgroup) called "name". This option is available only
diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config
index ae7dc46e8f8a..b5ac356ba323 100644
--- a/tools/perf/Makefile.config
+++ b/tools/perf/Makefile.config
@@ -885,6 +885,8 @@ endif
 
 # Among the variables below, these:
 #   perfexecdir
+#   perf_include_dir
+#   perf_examples_dir
 #   template_dir
 #   mandir
 #   infodir
@@ -904,6 +906,8 @@ bindir = $(abspath $(prefix)/$(bindir_relative))
 mandir = share/man
 infodir = share/info
 perfexecdir = libexec/perf-core
+perf_include_dir = lib/include/perf
+perf_examples_dir = lib/examples/perf
 sharedir = $(prefix)/share
 template_dir = share/perf-core/templates
 STRACE_GROUPS_DIR = share/perf-core/strace/groups
@@ -934,6 +938,8 @@ bindir_SQ = $(subst ','\'',$(bindir))
 mandir_SQ = $(subst ','\'',$(mandir))
 infodir_SQ = $(subst ','\'',$(infodir))
 perfexecdir_SQ = $(subst ','\'',$(perfexecdir))
+perf_include_dir_SQ = $(subst ','\'',$(perf_include_dir))
+perf_examples_dir_SQ = $(subst ','\'',$(perf_examples_dir))
 template_dir_SQ = $(subst ','\'',$(template_dir))
 htmldir_SQ = $(subst ','\'',$(htmldir))
 tipdir_SQ = $(subst ','\'',$(tipdir))
@@ -944,14 +950,20 @@ srcdir_SQ = $(subst ','\'',$(srcdir))
 
 ifneq ($(filter /%,$(firstword $(perfexecdir))),)
 perfexec_instdir = $(perfexecdir)
+perf_include_instdir = $(perf_include_dir)
+perf_examples_instdir = $(perf_examples_dir)
 STRACE_GROUPS_INSTDIR = $(STRACE_GROUPS_DIR)
 tip_instdir = $(tipdir)
 else
 perfexec_instdir = $(prefix)/$(perfexecdir)
+perf_include_instdir = $(prefix)/$(perf_include_dir)
+perf_examples_instdir = $(prefix)/$(perf_examples_dir)
 STRACE_GROUPS_INSTDIR = $(prefix)/$(STRACE_GROUPS_DIR)
 tip_instdir = $(prefix)/$(tipdir)
 endif
 perfexec_instdir_SQ = $(subst ','\'',$(perfexec_instdir))
+perf_include_instdir_SQ = $(subst ','\'',$(perf_include_instdir))
+perf_examples_instdir_SQ = $(subst ','\'',$(perf_examples_instdir))
 STRACE_GROUPS_INSTDIR_SQ = $(subst ','\'',$(STRACE_GROUPS_INSTDIR))
 tip_instdir_SQ = $(subst ','\'',$(tip_instdir))
 
@@ -999,6 +1011,8 @@ $(call detected_var,ETC_PERFCONFIG_SQ)
 $(call detected_var,STRACE_GROUPS_DIR_SQ)
 $(call detected_var,prefix_SQ)
 $(call detected_var,perfexecdir_SQ)
+$(call detected_var,perf_include_dir_SQ)
+$(call detected_var,perf_examples_dir_SQ)
 $(call detected_var,tipdir_SQ)
 $(call detected_var,srcdir_SQ)
 $(call detected_var,LIBDIR)
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index 83e453de36f8..ecc9fc952655 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -767,6 +767,16 @@ ifndef NO_JVMTI
 endif
 	$(call QUIET_INSTALL, libexec) \
 		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)'
+ifndef NO_LIBBPF
+	$(call QUIET_INSTALL, lib) \
+		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perf_include_instdir_SQ)/bpf'
+	$(call QUIET_INSTALL, include/bpf) \
+		$(INSTALL) include/bpf/*.h '$(DESTDIR_SQ)$(perf_include_instdir_SQ)/bpf'
+	$(call QUIET_INSTALL, lib) \
+		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perf_examples_instdir_SQ)/bpf'
+	$(call QUIET_INSTALL, examples/bpf) \
+		$(INSTALL) examples/bpf/*.c '$(DESTDIR_SQ)$(perf_examples_instdir_SQ)/bpf'
+endif
 	$(call QUIET_INSTALL, perf-archive) \
 		$(INSTALL) $(OUTPUT)perf-archive -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)'
 	$(call QUIET_INSTALL, perf-with-kcore) \
diff --git a/tools/perf/arch/arm/tests/dwarf-unwind.c b/tools/perf/arch/arm/tests/dwarf-unwind.c
index 8cb347760233..9a0242e74cfc 100644
--- a/tools/perf/arch/arm/tests/dwarf-unwind.c
+++ b/tools/perf/arch/arm/tests/dwarf-unwind.c
@@ -25,7 +25,7 @@ static int sample_ustack(struct perf_sample *sample,
 
 	sp = (unsigned long) regs[PERF_REG_ARM_SP];
 
-	map = map_groups__find(thread->mg, MAP__VARIABLE, (u64) sp);
+	map = map_groups__find(thread->mg, (u64)sp);
 	if (!map) {
 		pr_debug("failed to get stack map\n");
 		free(buf);
diff --git a/tools/perf/arch/arm64/tests/dwarf-unwind.c b/tools/perf/arch/arm64/tests/dwarf-unwind.c
index e907f0f4c20c..5522ce384723 100644
--- a/tools/perf/arch/arm64/tests/dwarf-unwind.c
+++ b/tools/perf/arch/arm64/tests/dwarf-unwind.c
@@ -25,7 +25,7 @@ static int sample_ustack(struct perf_sample *sample,
 
 	sp = (unsigned long) regs[PERF_REG_ARM64_SP];
 
-	map = map_groups__find(thread->mg, MAP__VARIABLE, (u64) sp);
+	map = map_groups__find(thread->mg, (u64)sp);
 	if (!map) {
 		pr_debug("failed to get stack map\n");
 		free(buf);
diff --git a/tools/perf/arch/powerpc/tests/dwarf-unwind.c b/tools/perf/arch/powerpc/tests/dwarf-unwind.c
index 30cbbd6d5be0..5f39efef0856 100644
--- a/tools/perf/arch/powerpc/tests/dwarf-unwind.c
+++ b/tools/perf/arch/powerpc/tests/dwarf-unwind.c
@@ -26,7 +26,7 @@ static int sample_ustack(struct perf_sample *sample,
 
 	sp = (unsigned long) regs[PERF_REG_POWERPC_R1];
 
-	map = map_groups__find(thread->mg, MAP__VARIABLE, (u64) sp);
+	map = map_groups__find(thread->mg, (u64)sp);
 	if (!map) {
 		pr_debug("failed to get stack map\n");
 		free(buf);
diff --git a/tools/perf/arch/powerpc/util/skip-callchain-idx.c b/tools/perf/arch/powerpc/util/skip-callchain-idx.c
index 0c370f81e002..3598b8b75d27 100644
--- a/tools/perf/arch/powerpc/util/skip-callchain-idx.c
+++ b/tools/perf/arch/powerpc/util/skip-callchain-idx.c
@@ -248,8 +248,7 @@ int arch_skip_callchain_idx(struct thread *thread, struct ip_callchain *chain)
 
 	ip = chain->ips[2];
 
-	thread__find_addr_location(thread, PERF_RECORD_MISC_USER,
-			MAP__FUNCTION, ip, &al);
+	thread__find_symbol(thread, PERF_RECORD_MISC_USER, ip, &al);
 
 	if (al.map)
 		dso = al.map->dso;
diff --git a/tools/perf/arch/x86/tests/dwarf-unwind.c b/tools/perf/arch/x86/tests/dwarf-unwind.c
index 95036c7a59e8..7879df34569a 100644
--- a/tools/perf/arch/x86/tests/dwarf-unwind.c
+++ b/tools/perf/arch/x86/tests/dwarf-unwind.c
@@ -26,7 +26,7 @@ static int sample_ustack(struct perf_sample *sample,
 
 	sp = (unsigned long) regs[PERF_REG_X86_SP];
 
-	map = map_groups__find(thread->mg, MAP__VARIABLE, (u64) sp);
+	map = map_groups__find(thread->mg, (u64)sp);
 	if (!map) {
 		pr_debug("failed to get stack map\n");
 		free(buf);
diff --git a/tools/perf/arch/x86/util/Build b/tools/perf/arch/x86/util/Build
index f95e6f46ef0d..844b8f335532 100644
--- a/tools/perf/arch/x86/util/Build
+++ b/tools/perf/arch/x86/util/Build
@@ -4,6 +4,8 @@ libperf-y += pmu.o
 libperf-y += kvm-stat.o
 libperf-y += perf_regs.o
 libperf-y += group.o
+libperf-y += machine.o
+libperf-y += event.o
 
 libperf-$(CONFIG_DWARF) += dwarf-regs.o
 libperf-$(CONFIG_BPF_PROLOGUE) += dwarf-regs.o
diff --git a/tools/perf/arch/x86/util/event.c b/tools/perf/arch/x86/util/event.c
new file mode 100644
index 000000000000..675a0213044d
--- /dev/null
+++ b/tools/perf/arch/x86/util/event.c
@@ -0,0 +1,76 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/types.h>
+#include <linux/string.h>
+
+#include "../../util/machine.h"
+#include "../../util/tool.h"
+#include "../../util/map.h"
+#include "../../util/util.h"
+#include "../../util/debug.h"
+
+#if defined(__x86_64__)
+
+int perf_event__synthesize_extra_kmaps(struct perf_tool *tool,
+				       perf_event__handler_t process,
+				       struct machine *machine)
+{
+	int rc = 0;
+	struct map *pos;
+	struct map_groups *kmaps = &machine->kmaps;
+	struct maps *maps = &kmaps->maps;
+	union perf_event *event = zalloc(sizeof(event->mmap) +
+					 machine->id_hdr_size);
+
+	if (!event) {
+		pr_debug("Not enough memory synthesizing mmap event "
+			 "for extra kernel maps\n");
+		return -1;
+	}
+
+	for (pos = maps__first(maps); pos; pos = map__next(pos)) {
+		struct kmap *kmap;
+		size_t size;
+
+		if (!__map__is_extra_kernel_map(pos))
+			continue;
+
+		kmap = map__kmap(pos);
+
+		size = sizeof(event->mmap) - sizeof(event->mmap.filename) +
+		       PERF_ALIGN(strlen(kmap->name) + 1, sizeof(u64)) +
+		       machine->id_hdr_size;
+
+		memset(event, 0, size);
+
+		event->mmap.header.type = PERF_RECORD_MMAP;
+
+		/*
+		 * kernel uses 0 for user space maps, see kernel/perf_event.c
+		 * __perf_event_mmap
+		 */
+		if (machine__is_host(machine))
+			event->header.misc = PERF_RECORD_MISC_KERNEL;
+		else
+			event->header.misc = PERF_RECORD_MISC_GUEST_KERNEL;
+
+		event->mmap.header.size = size;
+
+		event->mmap.start = pos->start;
+		event->mmap.len   = pos->end - pos->start;
+		event->mmap.pgoff = pos->pgoff;
+		event->mmap.pid   = machine->pid;
+
+		strlcpy(event->mmap.filename, kmap->name, PATH_MAX);
+
+		if (perf_tool__process_synth_event(tool, event, machine,
+						   process) != 0) {
+			rc = -1;
+			break;
+		}
+	}
+
+	free(event);
+	return rc;
+}
+
+#endif
diff --git a/tools/perf/arch/x86/util/machine.c b/tools/perf/arch/x86/util/machine.c
new file mode 100644
index 000000000000..4520ac53caa9
--- /dev/null
+++ b/tools/perf/arch/x86/util/machine.c
@@ -0,0 +1,103 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/types.h>
+#include <linux/string.h>
+#include <stdlib.h>
+
+#include "../../util/machine.h"
+#include "../../util/map.h"
+#include "../../util/symbol.h"
+#include "../../util/sane_ctype.h"
+
+#include <symbol/kallsyms.h>
+
+#if defined(__x86_64__)
+
+struct extra_kernel_map_info {
+	int cnt;
+	int max_cnt;
+	struct extra_kernel_map *maps;
+	bool get_entry_trampolines;
+	u64 entry_trampoline;
+};
+
+static int add_extra_kernel_map(struct extra_kernel_map_info *mi, u64 start,
+				u64 end, u64 pgoff, const char *name)
+{
+	if (mi->cnt >= mi->max_cnt) {
+		void *buf;
+		size_t sz;
+
+		mi->max_cnt = mi->max_cnt ? mi->max_cnt * 2 : 32;
+		sz = sizeof(struct extra_kernel_map) * mi->max_cnt;
+		buf = realloc(mi->maps, sz);
+		if (!buf)
+			return -1;
+		mi->maps = buf;
+	}
+
+	mi->maps[mi->cnt].start = start;
+	mi->maps[mi->cnt].end   = end;
+	mi->maps[mi->cnt].pgoff = pgoff;
+	strlcpy(mi->maps[mi->cnt].name, name, KMAP_NAME_LEN);
+
+	mi->cnt += 1;
+
+	return 0;
+}
+
+static int find_extra_kernel_maps(void *arg, const char *name, char type,
+				  u64 start)
+{
+	struct extra_kernel_map_info *mi = arg;
+
+	if (!mi->entry_trampoline && kallsyms2elf_binding(type) == STB_GLOBAL &&
+	    !strcmp(name, "_entry_trampoline")) {
+		mi->entry_trampoline = start;
+		return 0;
+	}
+
+	if (is_entry_trampoline(name)) {
+		u64 end = start + page_size;
+
+		return add_extra_kernel_map(mi, start, end, 0, name);
+	}
+
+	return 0;
+}
+
+int machine__create_extra_kernel_maps(struct machine *machine,
+				      struct dso *kernel)
+{
+	struct extra_kernel_map_info mi = { .cnt = 0, };
+	char filename[PATH_MAX];
+	int ret;
+	int i;
+
+	machine__get_kallsyms_filename(machine, filename, PATH_MAX);
+
+	if (symbol__restricted_filename(filename, "/proc/kallsyms"))
+		return 0;
+
+	ret = kallsyms__parse(filename, &mi, find_extra_kernel_maps);
+	if (ret)
+		goto out_free;
+
+	if (!mi.entry_trampoline)
+		goto out_free;
+
+	for (i = 0; i < mi.cnt; i++) {
+		struct extra_kernel_map *xm = &mi.maps[i];
+
+		xm->pgoff = mi.entry_trampoline;
+		ret = machine__create_extra_kernel_map(machine, kernel, xm);
+		if (ret)
+			goto out_free;
+	}
+
+	machine->trampolines_mapped = mi.cnt;
+out_free:
+	free(mi.maps);
+	return ret;
+}
+
+#endif
diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c
index 51709a961496..da5704240239 100644
--- a/tools/perf/builtin-annotate.c
+++ b/tools/perf/builtin-annotate.c
@@ -45,6 +45,7 @@ struct perf_annotate {
 	bool	   print_line;
 	bool	   skip_missing;
 	bool	   has_br_stack;
+	bool	   group_set;
 	const char *sym_hist_filter;
 	const char *cpu_list;
 	DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS);
@@ -228,7 +229,7 @@ static int perf_evsel__add_sample(struct perf_evsel *evsel,
 		 */
 		if (al->sym != NULL) {
 			rb_erase(&al->sym->rb_node,
-				 &al->map->dso->symbols[al->map->type]);
+				 &al->map->dso->symbols);
 			symbol__delete(al->sym);
 			dso__reset_find_symbol_cache(al->map->dso);
 		}
@@ -508,6 +509,9 @@ int cmd_annotate(int argc, const char **argv)
 		    "Don't shorten the displayed pathnames"),
 	OPT_BOOLEAN(0, "skip-missing", &annotate.skip_missing,
 		    "Skip symbols that cannot be annotated"),
+	OPT_BOOLEAN_SET(0, "group", &symbol_conf.event_group,
+			&annotate.group_set,
+			"Show event group information together"),
 	OPT_STRING('C', "cpu", &annotate.cpu_list, "cpu", "list of cpus to profile"),
 	OPT_CALLBACK(0, "symfs", NULL, "directory",
 		     "Look for files with symbols relative to this directory",
@@ -570,6 +574,9 @@ int cmd_annotate(int argc, const char **argv)
 	annotate.has_br_stack = perf_header__has_feat(&annotate.session->header,
 						      HEADER_BRANCH_STACK);
 
+	if (annotate.group_set)
+		perf_evlist__force_leader(annotate.session->evlist);
+
 	ret = symbol__annotation_init();
 	if (ret < 0)
 		goto out_delete;
diff --git a/tools/perf/builtin-buildid-cache.c b/tools/perf/builtin-buildid-cache.c
index 41db2cba77eb..115110a4796a 100644
--- a/tools/perf/builtin-buildid-cache.c
+++ b/tools/perf/builtin-buildid-cache.c
@@ -25,6 +25,7 @@
 #include "util/session.h"
 #include "util/symbol.h"
 #include "util/time-utils.h"
+#include "util/probe-file.h"
 
 static int build_id_cache__kcore_buildid(const char *proc_dir, char *sbuildid)
 {
@@ -239,6 +240,34 @@ out:
 	return err;
 }
 
+static int build_id_cache__purge_all(void)
+{
+	struct strlist *list;
+	struct str_node *pos;
+	int err = 0;
+	char *buf;
+
+	list = build_id_cache__list_all(false);
+	if (!list) {
+		pr_debug("Failed to get buildids: -%d\n", errno);
+		return -EINVAL;
+	}
+
+	strlist__for_each_entry(pos, list) {
+		buf = build_id_cache__origname(pos->s);
+		err = build_id_cache__remove_s(pos->s);
+		pr_debug("Removing %s (%s): %s\n", buf, pos->s,
+			 err ? "FAIL" : "Ok");
+		free(buf);
+		if (err)
+			break;
+	}
+	strlist__delete(list);
+
+	pr_debug("Purged all: %s\n", err ? "FAIL" : "Ok");
+	return err;
+}
+
 static bool dso__missing_buildid_cache(struct dso *dso, int parm __maybe_unused)
 {
 	char filename[PATH_MAX];
@@ -297,6 +326,26 @@ static int build_id_cache__update_file(const char *filename, struct nsinfo *nsi)
 	return err;
 }
 
+static int build_id_cache__show_all(void)
+{
+	struct strlist *bidlist;
+	struct str_node *nd;
+	char *buf;
+
+	bidlist = build_id_cache__list_all(true);
+	if (!bidlist) {
+		pr_debug("Failed to get buildids: -%d\n", errno);
+		return -1;
+	}
+	strlist__for_each_entry(nd, bidlist) {
+		buf = build_id_cache__origname(nd->s);
+		fprintf(stdout, "%s %s\n", nd->s, buf);
+		free(buf);
+	}
+	strlist__delete(bidlist);
+	return 0;
+}
+
 int cmd_buildid_cache(int argc, const char **argv)
 {
 	struct strlist *list;
@@ -304,6 +353,9 @@ int cmd_buildid_cache(int argc, const char **argv)
 	int ret = 0;
 	int ns_id = -1;
 	bool force = false;
+	bool list_files = false;
+	bool opts_flag = false;
+	bool purge_all = false;
 	char const *add_name_list_str = NULL,
 		   *remove_name_list_str = NULL,
 		   *purge_name_list_str = NULL,
@@ -327,6 +379,8 @@ int cmd_buildid_cache(int argc, const char **argv)
 		    "file(s) to remove"),
 	OPT_STRING('p', "purge", &purge_name_list_str, "file list",
 		    "file(s) to remove (remove old caches too)"),
+	OPT_BOOLEAN('P', "purge-all", &purge_all, "purge all cached files"),
+	OPT_BOOLEAN('l', "list", &list_files, "list all cached files"),
 	OPT_STRING('M', "missing", &missing_filename, "file",
 		   "to find missing build ids in the cache"),
 	OPT_BOOLEAN('f', "force", &force, "don't complain, do it"),
@@ -344,11 +398,20 @@ int cmd_buildid_cache(int argc, const char **argv)
 	argc = parse_options(argc, argv, buildid_cache_options,
 			     buildid_cache_usage, 0);
 
-	if (argc || (!add_name_list_str && !kcore_filename &&
-		     !remove_name_list_str && !purge_name_list_str &&
-		     !missing_filename && !update_name_list_str))
+	opts_flag = add_name_list_str || kcore_filename ||
+		remove_name_list_str || purge_name_list_str ||
+		missing_filename || update_name_list_str ||
+		purge_all;
+
+	if (argc || !(list_files || opts_flag))
 		usage_with_options(buildid_cache_usage, buildid_cache_options);
 
+	/* -l is exclusive. It can not be used with other options. */
+	if (list_files && opts_flag) {
+		usage_with_options_msg(buildid_cache_usage,
+			buildid_cache_options, "-l is exclusive.\n");
+	}
+
 	if (ns_id > 0)
 		nsi = nsinfo__new(ns_id);
 
@@ -366,6 +429,11 @@ int cmd_buildid_cache(int argc, const char **argv)
 
 	setup_pager();
 
+	if (list_files) {
+		ret = build_id_cache__show_all();
+		goto out;
+	}
+
 	if (add_name_list_str) {
 		list = strlist__new(add_name_list_str, NULL);
 		if (list) {
@@ -420,6 +488,13 @@ int cmd_buildid_cache(int argc, const char **argv)
 		}
 	}
 
+	if (purge_all) {
+		if (build_id_cache__purge_all()) {
+			pr_warning("Couldn't remove some caches. Error: %s.\n",
+				str_error_r(errno, sbuf, sizeof(sbuf)));
+		}
+	}
+
 	if (missing_filename)
 		ret = build_id_cache__fprintf_missing(session, stdout);
 
diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c
index 40fe919bbcf3..a3b346359ba0 100644
--- a/tools/perf/builtin-inject.c
+++ b/tools/perf/builtin-inject.c
@@ -440,9 +440,7 @@ static int perf_event__inject_buildid(struct perf_tool *tool,
 		goto repipe;
 	}
 
-	thread__find_addr_map(thread, sample->cpumode, MAP__FUNCTION, sample->ip, &al);
-
-	if (al.map != NULL) {
+	if (thread__find_map(thread, sample->cpumode, sample->ip, &al)) {
 		if (!al.map->dso->hit) {
 			al.map->dso->hit = 1;
 			if (map__load(al.map) >= 0) {
diff --git a/tools/perf/builtin-kallsyms.c b/tools/perf/builtin-kallsyms.c
index bcfb363112d3..90d1a2305b72 100644
--- a/tools/perf/builtin-kallsyms.c
+++ b/tools/perf/builtin-kallsyms.c
@@ -27,7 +27,7 @@ static int __cmd_kallsyms(int argc, const char **argv)
 
 	for (i = 0; i < argc; ++i) {
 		struct map *map;
-		struct symbol *symbol = machine__find_kernel_function_by_name(machine, argv[i], &map);
+		struct symbol *symbol = machine__find_kernel_symbol_by_name(machine, argv[i], &map);
 
 		if (symbol == NULL) {
 			printf("%s: not found\n", argv[i]);
diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c
index ae11e4c3516a..54d3f21b0e62 100644
--- a/tools/perf/builtin-kmem.c
+++ b/tools/perf/builtin-kmem.c
@@ -1004,7 +1004,7 @@ static void __print_slab_result(struct rb_root *root,
 		if (is_caller) {
 			addr = data->call_site;
 			if (!raw_ip)
-				sym = machine__find_kernel_function(machine, addr, &map);
+				sym = machine__find_kernel_symbol(machine, addr, &map);
 		} else
 			addr = data->ptr;
 
@@ -1068,7 +1068,7 @@ static void __print_page_alloc_result(struct perf_session *session, int n_lines)
 		char *caller = buf;
 
 		data = rb_entry(next, struct page_stat, node);
-		sym = machine__find_kernel_function(machine, data->callsite, &map);
+		sym = machine__find_kernel_symbol(machine, data->callsite, &map);
 		if (sym)
 			caller = sym->name;
 		else
@@ -1110,7 +1110,7 @@ static void __print_page_caller_result(struct perf_session *session, int n_lines
 		char *caller = buf;
 
 		data = rb_entry(next, struct page_stat, node);
-		sym = machine__find_kernel_function(machine, data->callsite, &map);
+		sym = machine__find_kernel_symbol(machine, data->callsite, &map);
 		if (sym)
 			caller = sym->name;
 		else
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 0f198f6d9b77..ad978e3ee2b8 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -194,20 +194,11 @@ out:
 	return err;
 }
 
-/*
- * Events in data file are not collect in groups, but we still want
- * the group display. Set the artificial group and set the leader's
- * forced_leader flag to notify the display code.
- */
 static void setup_forced_leader(struct report *report,
 				struct perf_evlist *evlist)
 {
-	if (report->group_set && !evlist->nr_groups) {
-		struct perf_evsel *leader = perf_evlist__first(evlist);
-
-		perf_evlist__set_leader(evlist);
-		leader->forced_leader = true;
-	}
+	if (report->group_set)
+		perf_evlist__force_leader(evlist);
 }
 
 static int process_feature_event(struct perf_tool *tool,
@@ -523,12 +514,9 @@ static void report__warn_kptr_restrict(const struct report *rep)
 		    "As no suitable kallsyms nor vmlinux was found, kernel samples\n"
 		    "can't be resolved.";
 
-		if (kernel_map) {
-			const struct dso *kdso = kernel_map->dso;
-			if (!RB_EMPTY_ROOT(&kdso->symbols[MAP__FUNCTION])) {
-				desc = "If some relocation was applied (e.g. "
-				       "kexec) symbols may be misresolved.";
-			}
+		if (kernel_map && map__has_symbols(kernel_map)) {
+			desc = "If some relocation was applied (e.g. "
+			       "kexec) symbols may be misresolved.";
 		}
 
 		ui__warning(
@@ -718,10 +706,7 @@ static size_t maps__fprintf_task(struct maps *maps, int indent, FILE *fp)
 
 static int map_groups__fprintf_task(struct map_groups *mg, int indent, FILE *fp)
 {
-	int printed = 0, i;
-	for (i = 0; i < MAP__NR_TYPES; ++i)
-		printed += maps__fprintf_task(&mg->maps[i], indent, fp);
-	return printed;
+	return maps__fprintf_task(&mg->maps, indent, fp);
 }
 
 static void task__print_level(struct task *task, FILE *fp, int level)
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index e0a9845b6cbc..cefc8813e91e 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -153,8 +153,8 @@ static struct {
 		.fields = PERF_OUTPUT_COMM | PERF_OUTPUT_TID |
 			      PERF_OUTPUT_CPU | PERF_OUTPUT_TIME |
 			      PERF_OUTPUT_EVNAME | PERF_OUTPUT_IP |
-			      PERF_OUTPUT_SYM | PERF_OUTPUT_DSO |
-			      PERF_OUTPUT_PERIOD,
+			      PERF_OUTPUT_SYM | PERF_OUTPUT_SYMOFFSET |
+			      PERF_OUTPUT_DSO | PERF_OUTPUT_PERIOD,
 
 		.invalid_fields = PERF_OUTPUT_TRACE | PERF_OUTPUT_BPF_OUTPUT,
 	},
@@ -165,8 +165,9 @@ static struct {
 		.fields = PERF_OUTPUT_COMM | PERF_OUTPUT_TID |
 			      PERF_OUTPUT_CPU | PERF_OUTPUT_TIME |
 			      PERF_OUTPUT_EVNAME | PERF_OUTPUT_IP |
-			      PERF_OUTPUT_SYM | PERF_OUTPUT_DSO |
-			      PERF_OUTPUT_PERIOD | PERF_OUTPUT_BPF_OUTPUT,
+			      PERF_OUTPUT_SYM | PERF_OUTPUT_SYMOFFSET |
+			      PERF_OUTPUT_DSO | PERF_OUTPUT_PERIOD |
+			      PERF_OUTPUT_BPF_OUTPUT,
 
 		.invalid_fields = PERF_OUTPUT_TRACE,
 	},
@@ -185,10 +186,10 @@ static struct {
 		.fields = PERF_OUTPUT_COMM | PERF_OUTPUT_TID |
 			      PERF_OUTPUT_CPU | PERF_OUTPUT_TIME |
 			      PERF_OUTPUT_EVNAME | PERF_OUTPUT_IP |
-			      PERF_OUTPUT_SYM | PERF_OUTPUT_DSO |
-			      PERF_OUTPUT_PERIOD |  PERF_OUTPUT_ADDR |
-			      PERF_OUTPUT_DATA_SRC | PERF_OUTPUT_WEIGHT |
-			      PERF_OUTPUT_PHYS_ADDR,
+			      PERF_OUTPUT_SYM | PERF_OUTPUT_SYMOFFSET |
+			      PERF_OUTPUT_DSO | PERF_OUTPUT_PERIOD |
+			      PERF_OUTPUT_ADDR | PERF_OUTPUT_DATA_SRC |
+			      PERF_OUTPUT_WEIGHT | PERF_OUTPUT_PHYS_ADDR,
 
 		.invalid_fields = PERF_OUTPUT_TRACE | PERF_OUTPUT_BPF_OUTPUT,
 	},
@@ -199,8 +200,8 @@ static struct {
 		.fields = PERF_OUTPUT_COMM | PERF_OUTPUT_TID |
 			      PERF_OUTPUT_CPU | PERF_OUTPUT_TIME |
 			      PERF_OUTPUT_EVNAME | PERF_OUTPUT_IP |
-			      PERF_OUTPUT_SYM | PERF_OUTPUT_DSO |
-			      PERF_OUTPUT_PERIOD,
+			      PERF_OUTPUT_SYM | PERF_OUTPUT_SYMOFFSET |
+			      PERF_OUTPUT_DSO | PERF_OUTPUT_PERIOD,
 
 		.invalid_fields = PERF_OUTPUT_TRACE | PERF_OUTPUT_BPF_OUTPUT,
 	},
@@ -211,8 +212,8 @@ static struct {
 		.fields = PERF_OUTPUT_COMM | PERF_OUTPUT_TID |
 			      PERF_OUTPUT_CPU | PERF_OUTPUT_TIME |
 			      PERF_OUTPUT_EVNAME | PERF_OUTPUT_IP |
-			      PERF_OUTPUT_SYM | PERF_OUTPUT_DSO |
-			      PERF_OUTPUT_SYNTH,
+			      PERF_OUTPUT_SYM | PERF_OUTPUT_SYMOFFSET |
+			      PERF_OUTPUT_DSO | PERF_OUTPUT_SYNTH,
 
 		.invalid_fields = PERF_OUTPUT_TRACE | PERF_OUTPUT_BPF_OUTPUT,
 	},
@@ -544,6 +545,7 @@ static int perf_session__check_output_opt(struct perf_session *session)
 			if (attr->sample_type & PERF_SAMPLE_CALLCHAIN) {
 				output[j].fields |= PERF_OUTPUT_IP;
 				output[j].fields |= PERF_OUTPUT_SYM;
+				output[j].fields |= PERF_OUTPUT_SYMOFFSET;
 				output[j].fields |= PERF_OUTPUT_DSO;
 				set_print_ip_opts(attr);
 				goto out;
@@ -717,8 +719,8 @@ static int perf_sample__fprintf_brstack(struct perf_sample *sample,
 		if (PRINT_FIELD(DSO)) {
 			memset(&alf, 0, sizeof(alf));
 			memset(&alt, 0, sizeof(alt));
-			thread__find_addr_map(thread, sample->cpumode, MAP__FUNCTION, from, &alf);
-			thread__find_addr_map(thread, sample->cpumode, MAP__FUNCTION, to, &alt);
+			thread__find_map(thread, sample->cpumode, from, &alf);
+			thread__find_map(thread, sample->cpumode, to, &alt);
 		}
 
 		printed += fprintf(fp, " 0x%"PRIx64, from);
@@ -764,13 +766,8 @@ static int perf_sample__fprintf_brstacksym(struct perf_sample *sample,
 		from = br->entries[i].from;
 		to   = br->entries[i].to;
 
-		thread__find_addr_map(thread, sample->cpumode, MAP__FUNCTION, from, &alf);
-		if (alf.map)
-			alf.sym = map__find_symbol(alf.map, alf.addr);
-
-		thread__find_addr_map(thread, sample->cpumode, MAP__FUNCTION, to, &alt);
-		if (alt.map)
-			alt.sym = map__find_symbol(alt.map, alt.addr);
+		thread__find_symbol(thread, sample->cpumode, from, &alf);
+		thread__find_symbol(thread, sample->cpumode, to, &alt);
 
 		printed += symbol__fprintf_symname_offs(alf.sym, &alf, fp);
 		if (PRINT_FIELD(DSO)) {
@@ -814,12 +811,12 @@ static int perf_sample__fprintf_brstackoff(struct perf_sample *sample,
 		from = br->entries[i].from;
 		to   = br->entries[i].to;
 
-		thread__find_addr_map(thread, sample->cpumode, MAP__FUNCTION, from, &alf);
-		if (alf.map && !alf.map->dso->adjust_symbols)
+		if (thread__find_map(thread, sample->cpumode, from, &alf) &&
+		    !alf.map->dso->adjust_symbols)
 			from = map__map_ip(alf.map, from);
 
-		thread__find_addr_map(thread, sample->cpumode, MAP__FUNCTION, to, &alt);
-		if (alt.map && !alt.map->dso->adjust_symbols)
+		if (thread__find_map(thread, sample->cpumode, to, &alt) &&
+		    !alt.map->dso->adjust_symbols)
 			to = map__map_ip(alt.map, to);
 
 		printed += fprintf(fp, " 0x%"PRIx64, from);
@@ -882,8 +879,7 @@ static int grab_bb(u8 *buffer, u64 start, u64 end,
 		return 0;
 	}
 
-	thread__find_addr_map(thread, *cpumode, MAP__FUNCTION, start, &al);
-	if (!al.map || !al.map->dso) {
+	if (!thread__find_map(thread, *cpumode, start, &al) || !al.map->dso) {
 		pr_debug("\tcannot resolve %" PRIx64 "-%" PRIx64 "\n", start, end);
 		return 0;
 	}
@@ -933,10 +929,8 @@ static int ip__fprintf_sym(uint64_t addr, struct thread *thread,
 
 	memset(&al, 0, sizeof(al));
 
-	thread__find_addr_map(thread, cpumode, MAP__FUNCTION, addr, &al);
-	if (!al.map)
-		thread__find_addr_map(thread, cpumode, MAP__VARIABLE,
-				      addr, &al);
+	thread__find_map(thread, cpumode, addr, &al);
+
 	if ((*lastsym) && al.addr >= (*lastsym)->start && al.addr < (*lastsym)->end)
 		return 0;
 
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index f17dc601b0f3..a4f662a462c6 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -164,6 +164,7 @@ static bool			forever				= false;
 static bool			metric_only			= false;
 static bool			force_metric_only		= false;
 static bool			no_merge			= false;
+static bool			walltime_run_table		= false;
 static struct timespec		ref_time;
 static struct cpu_map		*aggr_map;
 static aggr_get_id_t		aggr_get_id;
@@ -173,6 +174,7 @@ static const char		*output_name;
 static int			output_fd;
 static int			print_free_counters_hint;
 static int			print_mixed_hw_group_error;
+static u64			*walltime_run;
 
 struct perf_stat {
 	bool			 record;
@@ -569,7 +571,7 @@ static struct perf_evsel *perf_evsel__reset_weak_group(struct perf_evsel *evsel)
 	return leader;
 }
 
-static int __run_perf_stat(int argc, const char **argv)
+static int __run_perf_stat(int argc, const char **argv, int run_idx)
 {
 	int interval = stat_config.interval;
 	int times = stat_config.times;
@@ -752,6 +754,9 @@ try_again:
 
 	t1 = rdclock();
 
+	if (walltime_run_table)
+		walltime_run[run_idx] = t1 - t0;
+
 	update_stats(&walltime_nsecs_stats, t1 - t0);
 
 	/*
@@ -766,7 +771,7 @@ try_again:
 	return WEXITSTATUS(status);
 }
 
-static int run_perf_stat(int argc, const char **argv)
+static int run_perf_stat(int argc, const char **argv, int run_idx)
 {
 	int ret;
 
@@ -779,7 +784,7 @@ static int run_perf_stat(int argc, const char **argv)
 	if (sync_run)
 		sync();
 
-	ret = __run_perf_stat(argc, argv);
+	ret = __run_perf_stat(argc, argv, run_idx);
 	if (ret)
 		return ret;
 
@@ -1764,19 +1769,67 @@ static void print_header(int argc, const char **argv)
 	}
 }
 
+static int get_precision(double num)
+{
+	if (num > 1)
+		return 0;
+
+	return lround(ceil(-log10(num)));
+}
+
+static void print_table(FILE *output, int precision, double avg)
+{
+	char tmp[64];
+	int idx, indent = 0;
+
+	scnprintf(tmp, 64, " %17.*f", precision, avg);
+	while (tmp[indent] == ' ')
+		indent++;
+
+	fprintf(output, "%*s# Table of individual measurements:\n", indent, "");
+
+	for (idx = 0; idx < run_count; idx++) {
+		double run = (double) walltime_run[idx] / NSEC_PER_SEC;
+		int h, n = 1 + abs((int) (100.0 * (run - avg)/run) / 5);
+
+		fprintf(output, " %17.*f (%+.*f) ",
+			precision, run, precision, run - avg);
+
+		for (h = 0; h < n; h++)
+			fprintf(output, "#");
+
+		fprintf(output, "\n");
+	}
+
+	fprintf(output, "\n%*s# Final result:\n", indent, "");
+}
+
 static void print_footer(void)
 {
+	double avg = avg_stats(&walltime_nsecs_stats) / NSEC_PER_SEC;
 	FILE *output = stat_config.output;
 	int n;
 
 	if (!null_run)
 		fprintf(output, "\n");
-	fprintf(output, " %17.9f seconds time elapsed",
-			avg_stats(&walltime_nsecs_stats) / NSEC_PER_SEC);
-	if (run_count > 1) {
-		fprintf(output, "                                        ");
-		print_noise_pct(stddev_stats(&walltime_nsecs_stats),
-				avg_stats(&walltime_nsecs_stats));
+
+	if (run_count == 1) {
+		fprintf(output, " %17.9f seconds time elapsed", avg);
+	} else {
+		double sd = stddev_stats(&walltime_nsecs_stats) / NSEC_PER_SEC;
+		/*
+		 * Display at most 2 more significant
+		 * digits than the stddev inaccuracy.
+		 */
+		int precision = get_precision(sd) + 2;
+
+		if (walltime_run_table)
+			print_table(output, precision, avg);
+
+		fprintf(output, " %17.*f +- %.*f seconds time elapsed",
+			precision, avg, precision, sd);
+
+		print_noise_pct(sd, avg);
 	}
 	fprintf(output, "\n\n");
 
@@ -1952,6 +2005,8 @@ static const struct option stat_options[] = {
 		    "be more verbose (show counter open errors, etc)"),
 	OPT_INTEGER('r', "repeat", &run_count,
 		    "repeat command and print average + stddev (max: 100, forever: 0)"),
+	OPT_BOOLEAN(0, "table", &walltime_run_table,
+		    "display details about each run (only with -r option)"),
 	OPT_BOOLEAN('n', "null", &null_run,
 		    "null run - dont start any counters"),
 	OPT_INCR('d', "detailed", &detailed_run,
@@ -2843,6 +2898,13 @@ int cmd_stat(int argc, const char **argv)
 		goto out;
 	}
 
+	if (walltime_run_table && run_count <= 1) {
+		fprintf(stderr, "--table is only supported with -r\n");
+		parse_options_usage(stat_usage, stat_options, "r", 1);
+		parse_options_usage(NULL, stat_options, "table", 0);
+		goto out;
+	}
+
 	if (output_fd < 0) {
 		fprintf(stderr, "argument to --log-fd must be a > 0\n");
 		parse_options_usage(stat_usage, stat_options, "log-fd", 0);
@@ -2897,6 +2959,14 @@ int cmd_stat(int argc, const char **argv)
 		run_count = 1;
 	}
 
+	if (walltime_run_table) {
+		walltime_run = zalloc(run_count * sizeof(walltime_run[0]));
+		if (!walltime_run) {
+			pr_err("failed to setup -r option");
+			goto out;
+		}
+	}
+
 	if ((stat_config.aggr_mode == AGGR_THREAD) &&
 		!target__has_task(&target)) {
 		if (!target.system_wide || target.cpu_list) {
@@ -3012,7 +3082,7 @@ int cmd_stat(int argc, const char **argv)
 			fprintf(output, "[ perf stat: executing run #%d ... ]\n",
 				run_idx + 1);
 
-		status = run_perf_stat(argc, argv);
+		status = run_perf_stat(argc, argv, run_idx);
 		if (forever && status != -1) {
 			print_counters(NULL, argc, argv);
 			perf_stat__reset_stats();
@@ -3060,6 +3130,8 @@ int cmd_stat(int argc, const char **argv)
 	perf_stat__exit_aggr_mode();
 	perf_evlist__free_stats(evsel_list);
 out:
+	free(walltime_run);
+
 	if (smi_cost && smi_reset)
 		sysfs__write_int(FREEZE_ON_SMI_PATH, 0);
 
diff --git a/tools/perf/builtin-timechart.c b/tools/perf/builtin-timechart.c
index 813698a9b8c7..a827919c6263 100644
--- a/tools/perf/builtin-timechart.c
+++ b/tools/perf/builtin-timechart.c
@@ -533,12 +533,8 @@ static const char *cat_backtrace(union perf_event *event,
 		}
 
 		tal.filtered = 0;
-		thread__find_addr_location(al.thread, cpumode,
-					   MAP__FUNCTION, ip, &tal);
-
-		if (tal.sym)
-			fprintf(f, "..... %016" PRIx64 " %s\n", ip,
-				tal.sym->name);
+		if (thread__find_symbol(al.thread, cpumode, ip, &tal))
+			fprintf(f, "..... %016" PRIx64 " %s\n", ip, tal.sym->name);
 		else
 			fprintf(f, "..... %016" PRIx64 "\n", ip);
 	}
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index f39bd60d2708..7a349fcd3864 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -742,7 +742,7 @@ static void perf_event__process_sample(struct perf_tool *tool,
 "Kernel address maps (/proc/{kallsyms,modules}) are restricted.\n\n"
 "Check /proc/sys/kernel/kptr_restrict.\n\n"
 "Kernel%s samples will not be resolved.\n",
-			  al.map && !RB_EMPTY_ROOT(&al.map->dso->symbols[MAP__FUNCTION]) ?
+			  al.map && map__has_symbols(al.map) ?
 			  " modules" : "");
 			if (use_browser <= 0)
 				sleep(5);
@@ -750,7 +750,7 @@ static void perf_event__process_sample(struct perf_tool *tool,
 		machine->kptr_restrict_warned = true;
 	}
 
-	if (al.sym == NULL) {
+	if (al.sym == NULL && al.map != NULL) {
 		const char *msg = "Kernel samples will not be resolved.\n";
 		/*
 		 * As we do lazy loading of symtabs we only will know if the
@@ -764,8 +764,7 @@ static void perf_event__process_sample(struct perf_tool *tool,
 		 * invalid --vmlinux ;-)
 		 */
 		if (!machine->kptr_restrict_warned && !top->vmlinux_warned &&
-		    al.map == machine->vmlinux_maps[MAP__FUNCTION] &&
-		    RB_EMPTY_ROOT(&al.map->dso->symbols[MAP__FUNCTION])) {
+		    __map__is_kernel(al.map) && map__has_symbols(al.map)) {
 			if (symbol_conf.vmlinux_name) {
 				char serr[256];
 				dso__strerror_load(al.map->dso, serr, sizeof(serr));
@@ -1265,7 +1264,7 @@ int cmd_top(int argc, const char **argv)
 			.proc_map_timeout    = 500,
 			.overwrite	= 1,
 		},
-		.max_stack	     = sysctl_perf_event_max_stack,
+		.max_stack	     = sysctl__max_stack(),
 		.sym_pcnt_filter     = 5,
 		.nr_threads_synthesize = UINT_MAX,
 	};
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 3ad17ee89403..560aed7da36a 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -2024,8 +2024,7 @@ static int trace__pgfault(struct trace *trace,
 	if (trace->summary_only)
 		goto out;
 
-	thread__find_addr_location(thread, sample->cpumode, MAP__FUNCTION,
-			      sample->ip, &al);
+	thread__find_symbol(thread, sample->cpumode, sample->ip, &al);
 
 	trace__fprintf_entry_head(trace, thread, 0, true, sample->time, trace->output);
 
@@ -2037,12 +2036,10 @@ static int trace__pgfault(struct trace *trace,
 
 	fprintf(trace->output, "] => ");
 
-	thread__find_addr_location(thread, sample->cpumode, MAP__VARIABLE,
-				   sample->addr, &al);
+	thread__find_symbol(thread, sample->cpumode, sample->addr, &al);
 
 	if (!al.map) {
-		thread__find_addr_location(thread, sample->cpumode,
-					   MAP__FUNCTION, sample->addr, &al);
+		thread__find_symbol(thread, sample->cpumode, sample->addr, &al);
 
 		if (al.map)
 			map_type = 'x';
@@ -3165,7 +3162,7 @@ int cmd_trace(int argc, const char **argv)
 		mmap_pages_user_set = false;
 
 	if (trace.max_stack == UINT_MAX) {
-		trace.max_stack = input_name ? PERF_MAX_STACK_DEPTH : sysctl_perf_event_max_stack;
+		trace.max_stack = input_name ? PERF_MAX_STACK_DEPTH : sysctl__max_stack();
 		max_stack_user_set = false;
 	}
 
diff --git a/tools/perf/check-headers.sh b/tools/perf/check-headers.sh
index 9aff89bc7535..10f333e2e825 100755
--- a/tools/perf/check-headers.sh
+++ b/tools/perf/check-headers.sh
@@ -55,23 +55,27 @@ include/uapi/asm-generic/ioctls.h
 include/uapi/asm-generic/mman-common.h
 '
 
+check_2 () {
+  file1=$1
+  file2=$2
+
+  shift
+  shift
+
+  cmd="diff $* $file1 $file2 > /dev/null"
+
+  test -f $file2 &&
+  eval $cmd || echo "Warning: Kernel ABI header at 'tools/$file' differs from latest version at '$file'" >&2
+}
+
 check () {
   file=$1
 
   shift
-  opts=
-  while [ -n "$*" ]; do
-    opts="$opts \"$1\""
-    shift
-  done
 
-  cmd="diff $opts ../$file ../../$file > /dev/null"
-
-  test -f ../../$file &&
-  eval $cmd || echo "Warning: Kernel ABI header at 'tools/$file' differs from latest version at '$file'" >&2
+  check_2 ../$file ../../$file $*
 }
 
-
 # Check if we have the kernel headers (tools/perf/../../include), else
 # we're probably on a detached tarball, so no point in trying to check
 # differences.
@@ -83,7 +87,7 @@ for i in $HEADERS; do
 done
 
 # diff with extra ignore lines
-check arch/x86/lib/memcpy_64.S        -I "^EXPORT_SYMBOL" -I "^#include <asm/export.h>"
-check arch/x86/lib/memset_64.S        -I "^EXPORT_SYMBOL" -I "^#include <asm/export.h>"
-check include/uapi/asm-generic/mman.h -I "^#include <\(uapi/\)*asm-generic/mman-common.h>"
-check include/uapi/linux/mman.h       -I "^#include <\(uapi/\)*asm/mman.h>"
+check arch/x86/lib/memcpy_64.S        '-I "^EXPORT_SYMBOL" -I "^#include <asm/export.h>"'
+check arch/x86/lib/memset_64.S        '-I "^EXPORT_SYMBOL" -I "^#include <asm/export.h>"'
+check include/uapi/asm-generic/mman.h '-I "^#include <\(uapi/\)*asm-generic/mman-common.h>"'
+check include/uapi/linux/mman.h       '-I "^#include <\(uapi/\)*asm/mman.h>"'
diff --git a/tools/perf/examples/bpf/5sec.c b/tools/perf/examples/bpf/5sec.c
new file mode 100644
index 000000000000..b9c203219691
--- /dev/null
+++ b/tools/perf/examples/bpf/5sec.c
@@ -0,0 +1,49 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+    Description:
+
+    . Disable strace like syscall tracing (--no-syscalls), or try tracing
+      just some (-e *sleep).
+
+    . Attach a filter function to a kernel function, returning when it should
+      be considered, i.e. appear on the output.
+
+    . Run it system wide, so that any sleep of >= 5 seconds and < than 6
+      seconds gets caught.
+
+    . Ask for callgraphs using DWARF info, so that userspace can be unwound
+
+    . While this is running, run something like "sleep 5s".
+
+    . If we decide to add tv_nsec as well, then it becomes:
+
+      int probe(hrtimer_nanosleep, rqtp->tv_sec rqtp->tv_nsec)(void *ctx, int err, long sec, long nsec)
+
+      I.e. add where it comes from (rqtp->tv_nsec) and where it will be
+      accessible in the function body (nsec)
+
+    # perf trace --no-syscalls -e tools/perf/examples/bpf/5sec.c/call-graph=dwarf/
+         0.000 perf_bpf_probe:func:(ffffffff9811b5f0) tv_sec=5
+                                           hrtimer_nanosleep ([kernel.kallsyms])
+                                           __x64_sys_nanosleep ([kernel.kallsyms])
+                                           do_syscall_64 ([kernel.kallsyms])
+                                           entry_SYSCALL_64 ([kernel.kallsyms])
+                                           __GI___nanosleep (/usr/lib64/libc-2.26.so)
+                                           rpl_nanosleep (/usr/bin/sleep)
+                                           xnanosleep (/usr/bin/sleep)
+                                           main (/usr/bin/sleep)
+                                           __libc_start_main (/usr/lib64/libc-2.26.so)
+                                           _start (/usr/bin/sleep)
+    ^C#
+
+   Copyright (C) 2018 Red Hat, Inc., Arnaldo Carvalho de Melo <acme@redhat.com>
+*/
+
+#include <bpf.h>
+
+int probe(hrtimer_nanosleep, rqtp->tv_sec)(void *ctx, int err, long sec)
+{
+	return sec == 5;
+}
+
+license(GPL);
diff --git a/tools/perf/examples/bpf/empty.c b/tools/perf/examples/bpf/empty.c
new file mode 100644
index 000000000000..3776d26db9e7
--- /dev/null
+++ b/tools/perf/examples/bpf/empty.c
@@ -0,0 +1,3 @@
+#include <bpf.h>
+
+license(GPL);
diff --git a/tools/perf/include/bpf/bpf.h b/tools/perf/include/bpf/bpf.h
new file mode 100644
index 000000000000..dd764ad5efdf
--- /dev/null
+++ b/tools/perf/include/bpf/bpf.h
@@ -0,0 +1,13 @@
+// SPDX-License-Identifier: GPL-2.0
+#ifndef _PERF_BPF_H
+#define _PERF_BPF_H
+#define SEC(NAME) __attribute__((section(NAME),  used))
+
+#define probe(function, vars) \
+	SEC(#function "=" #function " " #vars) function
+
+#define license(name) \
+char _license[] SEC("license") = #name; \
+int _version SEC("version") = LINUX_VERSION_CODE;
+
+#endif /* _PERF_BPF_H */
diff --git a/tools/perf/perf.c b/tools/perf/perf.c
index 20a08cb32332..51c81509a315 100644
--- a/tools/perf/perf.c
+++ b/tools/perf/perf.c
@@ -238,7 +238,7 @@ static int handle_options(const char ***argv, int *argc, int *envchanged)
 			(*argc)--;
 		} else if (strstarts(cmd, CMD_DEBUGFS_DIR)) {
 			tracing_path_set(cmd + strlen(CMD_DEBUGFS_DIR));
-			fprintf(stderr, "dir: %s\n", tracing_path);
+			fprintf(stderr, "dir: %s\n", tracing_path_mount());
 			if (envchanged)
 				*envchanged = 1;
 		} else if (!strcmp(cmd, "--list-cmds")) {
@@ -421,22 +421,11 @@ void pthread__unblock_sigwinch(void)
 	pthread_sigmask(SIG_UNBLOCK, &set, NULL);
 }
 
-#ifdef _SC_LEVEL1_DCACHE_LINESIZE
-#define cache_line_size(cacheline_sizep) *cacheline_sizep = sysconf(_SC_LEVEL1_DCACHE_LINESIZE)
-#else
-static void cache_line_size(int *cacheline_sizep)
-{
-	if (sysfs__read_int("devices/system/cpu/cpu0/cache/index0/coherency_line_size", cacheline_sizep))
-		pr_debug("cannot determine cache line size");
-}
-#endif
-
 int main(int argc, const char **argv)
 {
 	int err;
 	const char *cmd;
 	char sbuf[STRERR_BUFSIZE];
-	int value;
 
 	/* libsubcmd init */
 	exec_cmd_init("perf", PREFIX, PERF_EXEC_PATH, EXEC_PATH_ENVIRONMENT);
@@ -444,13 +433,6 @@ int main(int argc, const char **argv)
 
 	/* The page_size is placed in util object. */
 	page_size = sysconf(_SC_PAGE_SIZE);
-	cache_line_size(&cacheline_size);
-
-	if (sysctl__read_int("kernel/perf_event_max_stack", &value) == 0)
-		sysctl_perf_event_max_stack = value;
-
-	if (sysctl__read_int("kernel/perf_event_max_contexts_per_stack", &value) == 0)
-		sysctl_perf_event_max_contexts_per_stack = value;
 
 	cmd = extract_argv0_path(argv[0]);
 	if (!cmd)
@@ -458,15 +440,11 @@ int main(int argc, const char **argv)
 
 	srandom(time(NULL));
 
-	perf_config__init();
 	err = perf_config(perf_default_config, NULL);
 	if (err)
 		return err;
 	set_buildid_dir(NULL);
 
-	/* get debugfs/tracefs mount point from /proc/mounts */
-	tracing_path_mount();
-
 	/*
 	 * "perf-xxxx" is the same as "perf xxxx", but we obviously:
 	 *
diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c
index cac8f8889bc3..2bde505e2e7e 100644
--- a/tools/perf/tests/builtin-test.c
+++ b/tools/perf/tests/builtin-test.c
@@ -654,6 +654,15 @@ static int perf_test__list(int argc, const char **argv)
 			continue;
 
 		pr_info("%2d: %s\n", i, t->desc);
+
+		if (t->subtest.get_nr) {
+			int subn = t->subtest.get_nr();
+			int subi;
+
+			for (subi = 0; subi < subn; subi++)
+				pr_info("%2d:%1d: %s\n", i, subi + 1,
+					t->subtest.get_desc(subi));
+		}
 	}
 
 	perf_test__list_shell(argc, argv, i);
diff --git a/tools/perf/tests/code-reading.c b/tools/perf/tests/code-reading.c
index 99936352df4f..afa4ce21ba7c 100644
--- a/tools/perf/tests/code-reading.c
+++ b/tools/perf/tests/code-reading.c
@@ -236,14 +236,13 @@ static int read_object_code(u64 addr, size_t len, u8 cpumode,
 
 	pr_debug("Reading object code for memory address: %#"PRIx64"\n", addr);
 
-	thread__find_addr_map(thread, cpumode, MAP__FUNCTION, addr, &al);
-	if (!al.map || !al.map->dso) {
+	if (!thread__find_map(thread, cpumode, addr, &al) || !al.map->dso) {
 		if (cpumode == PERF_RECORD_MISC_HYPERVISOR) {
 			pr_debug("Hypervisor address can not be resolved - skipping\n");
 			return 0;
 		}
 
-		pr_debug("thread__find_addr_map failed\n");
+		pr_debug("thread__find_map failed\n");
 		return -1;
 	}
 
diff --git a/tools/perf/tests/hists_common.c b/tools/perf/tests/hists_common.c
index f7c5b613d667..b889a28fd80b 100644
--- a/tools/perf/tests/hists_common.c
+++ b/tools/perf/tests/hists_common.c
@@ -131,20 +131,20 @@ struct machine *setup_fake_machine(struct machines *machines)
 			goto out;
 
 		/* emulate dso__load() */
-		dso__set_loaded(dso, MAP__FUNCTION);
+		dso__set_loaded(dso);
 
 		for (k = 0; k < fake_symbols[i].nr_syms; k++) {
 			struct symbol *sym;
 			struct fake_sym *fsym = &fake_symbols[i].syms[k];
 
 			sym = symbol__new(fsym->start, fsym->length,
-					  STB_GLOBAL, fsym->name);
+					  STB_GLOBAL, STT_FUNC, fsym->name);
 			if (sym == NULL) {
 				dso__put(dso);
 				goto out;
 			}
 
-			symbols__insert(&dso->symbols[MAP__FUNCTION], sym);
+			symbols__insert(&dso->symbols, sym);
 		}
 
 		dso__put(dso);
diff --git a/tools/perf/tests/mmap-thread-lookup.c b/tools/perf/tests/mmap-thread-lookup.c
index 868d82b501f4..b1af2499a3c9 100644
--- a/tools/perf/tests/mmap-thread-lookup.c
+++ b/tools/perf/tests/mmap-thread-lookup.c
@@ -188,9 +188,8 @@ static int mmap_events(synth_cb synth)
 
 		pr_debug("looking for map %p\n", td->map);
 
-		thread__find_addr_map(thread,
-				      PERF_RECORD_MISC_USER, MAP__FUNCTION,
-				      (unsigned long) (td->map + 1), &al);
+		thread__find_map(thread, PERF_RECORD_MISC_USER,
+				 (unsigned long) (td->map + 1), &al);
 
 		thread__put(thread);
 
@@ -218,7 +217,7 @@ static int mmap_events(synth_cb synth)
  *   perf_event__synthesize_threads    (global)
  *
  * We test we can find all memory maps via:
- *   thread__find_addr_map
+ *   thread__find_map
  *
  * by using all thread objects.
  */
diff --git a/tools/perf/tests/parse-events.c b/tools/perf/tests/parse-events.c
index 18b06444f230..b9ebe15afb13 100644
--- a/tools/perf/tests/parse-events.c
+++ b/tools/perf/tests/parse-events.c
@@ -1309,18 +1309,26 @@ static int test__checkevent_config_cache(struct perf_evlist *evlist)
 	return 0;
 }
 
+static int test__intel_pt(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel = perf_evlist__first(evlist);
+
+	TEST_ASSERT_VAL("wrong name setting", strcmp(evsel->name, "intel_pt//u") == 0);
+	return 0;
+}
+
 static int count_tracepoints(void)
 {
 	struct dirent *events_ent;
 	DIR *events_dir;
 	int cnt = 0;
 
-	events_dir = opendir(tracing_events_path);
+	events_dir = tracing_events__opendir();
 
 	TEST_ASSERT_VAL("Can't open events dir", events_dir);
 
 	while ((events_ent = readdir(events_dir))) {
-		char sys_path[PATH_MAX];
+		char *sys_path;
 		struct dirent *sys_ent;
 		DIR *sys_dir;
 
@@ -1331,8 +1339,8 @@ static int count_tracepoints(void)
 		    || !strcmp(events_ent->d_name, "header_page"))
 			continue;
 
-		scnprintf(sys_path, PATH_MAX, "%s/%s",
-			  tracing_events_path, events_ent->d_name);
+		sys_path = get_events_file(events_ent->d_name);
+		TEST_ASSERT_VAL("Can't get sys path", sys_path);
 
 		sys_dir = opendir(sys_path);
 		TEST_ASSERT_VAL("Can't open sys dir", sys_dir);
@@ -1348,6 +1356,7 @@ static int count_tracepoints(void)
 		}
 
 		closedir(sys_dir);
+		put_events_file(sys_path);
 	}
 
 	closedir(events_dir);
@@ -1637,6 +1646,11 @@ static struct evlist_test test__events[] = {
 		.check = test__checkevent_config_cache,
 		.id    = 51,
 	},
+	{
+		.name  = "intel_pt//u",
+		.check = test__intel_pt,
+		.id    = 52,
+	},
 };
 
 static struct evlist_test test__events_pmu[] = {
diff --git a/tools/perf/tests/shell/record+probe_libc_inet_pton.sh b/tools/perf/tests/shell/record+probe_libc_inet_pton.sh
index ee86473643be..650b208f700f 100755
--- a/tools/perf/tests/shell/record+probe_libc_inet_pton.sh
+++ b/tools/perf/tests/shell/record+probe_libc_inet_pton.sh
@@ -16,18 +16,18 @@ nm -g $libc 2>/dev/null | fgrep -q inet_pton || exit 254
 trace_libc_inet_pton_backtrace() {
 	idx=0
 	expected[0]="ping[][0-9 \.:]+probe_libc:inet_pton: \([[:xdigit:]]+\)"
-	expected[1]=".*inet_pton[[:space:]]\($libc|inlined\)$"
+	expected[1]=".*inet_pton\+0x[[:xdigit:]]+[[:space:]]\($libc|inlined\)$"
 	case "$(uname -m)" in
 	s390x)
 		eventattr='call-graph=dwarf,max-stack=4'
-		expected[2]="gaih_inet.*[[:space:]]\($libc|inlined\)$"
-		expected[3]="(__GI_)?getaddrinfo[[:space:]]\($libc|inlined\)$"
-		expected[4]="main[[:space:]]\(.*/bin/ping.*\)$"
+		expected[2]="gaih_inet.*\+0x[[:xdigit:]]+[[:space:]]\($libc|inlined\)$"
+		expected[3]="(__GI_)?getaddrinfo\+0x[[:xdigit:]]+[[:space:]]\($libc|inlined\)$"
+		expected[4]="main\+0x[[:xdigit:]]+[[:space:]]\(.*/bin/ping.*\)$"
 		;;
 	*)
 		eventattr='max-stack=3'
-		expected[2]="getaddrinfo[[:space:]]\($libc\)$"
-		expected[3]=".*\(.*/bin/ping.*\)$"
+		expected[2]="getaddrinfo\+0x[[:xdigit:]]+[[:space:]]\($libc\)$"
+		expected[3]=".*\+0x[[:xdigit:]]+[[:space:]]\(.*/bin/ping.*\)$"
 		;;
 	esac
 
diff --git a/tools/perf/tests/vmlinux-kallsyms.c b/tools/perf/tests/vmlinux-kallsyms.c
index 1e5adb65632a..7691980b7df1 100644
--- a/tools/perf/tests/vmlinux-kallsyms.c
+++ b/tools/perf/tests/vmlinux-kallsyms.c
@@ -19,8 +19,7 @@ int test__vmlinux_matches_kallsyms(struct test *test __maybe_unused, int subtest
 	struct symbol *sym;
 	struct map *kallsyms_map, *vmlinux_map, *map;
 	struct machine kallsyms, vmlinux;
-	enum map_type type = MAP__FUNCTION;
-	struct maps *maps = &vmlinux.kmaps.maps[type];
+	struct maps *maps = machine__kernel_maps(&vmlinux);
 	u64 mem_start, mem_end;
 	bool header_printed;
 
@@ -56,7 +55,7 @@ int test__vmlinux_matches_kallsyms(struct test *test __maybe_unused, int subtest
 	 * be compacted against the list of modules found in the "vmlinux"
 	 * code and with the one got from /proc/modules from the "kallsyms" code.
 	 */
-	if (machine__load_kallsyms(&kallsyms, "/proc/kallsyms", type) <= 0) {
+	if (machine__load_kallsyms(&kallsyms, "/proc/kallsyms") <= 0) {
 		pr_debug("dso__load_kallsyms ");
 		goto out;
 	}
@@ -94,7 +93,7 @@ int test__vmlinux_matches_kallsyms(struct test *test __maybe_unused, int subtest
 	 * maps__reloc_vmlinux will notice and set proper ->[un]map_ip routines
 	 * to fixup the symbols.
 	 */
-	if (machine__load_vmlinux_path(&vmlinux, type) <= 0) {
+	if (machine__load_vmlinux_path(&vmlinux) <= 0) {
 		pr_debug("Couldn't find a vmlinux that matches the kernel running on this machine, skipping test\n");
 		err = TEST_SKIP;
 		goto out;
@@ -108,7 +107,7 @@ int test__vmlinux_matches_kallsyms(struct test *test __maybe_unused, int subtest
 	 * in the kallsyms dso. For the ones that are in both, check its names and
 	 * end addresses too.
 	 */
-	for (nd = rb_first(&vmlinux_map->dso->symbols[type]); nd; nd = rb_next(nd)) {
+	map__for_each_symbol(vmlinux_map, sym, nd) {
 		struct symbol *pair, *first_pair;
 
 		sym  = rb_entry(nd, struct symbol, rb_node);
@@ -119,8 +118,7 @@ int test__vmlinux_matches_kallsyms(struct test *test __maybe_unused, int subtest
 		mem_start = vmlinux_map->unmap_ip(vmlinux_map, sym->start);
 		mem_end = vmlinux_map->unmap_ip(vmlinux_map, sym->end);
 
-		first_pair = machine__find_kernel_symbol(&kallsyms, type,
-							 mem_start, NULL);
+		first_pair = machine__find_kernel_symbol(&kallsyms, mem_start, NULL);
 		pair = first_pair;
 
 		if (pair && UM(pair->start) == mem_start) {
@@ -149,7 +147,7 @@ next_pair:
 				 */
 				continue;
 			} else {
-				pair = machine__find_kernel_symbol_by_name(&kallsyms, type, sym->name, NULL);
+				pair = machine__find_kernel_symbol_by_name(&kallsyms, sym->name, NULL);
 				if (pair) {
 					if (UM(pair->start) == mem_start)
 						goto next_pair;
@@ -183,7 +181,7 @@ next_pair:
 		 * so use the short name, less descriptive but the same ("[kernel]" in
 		 * both cases.
 		 */
-		pair = map_groups__find_by_name(&kallsyms.kmaps, type,
+		pair = map_groups__find_by_name(&kallsyms.kmaps,
 						(map->dso->kernel ?
 							map->dso->short_name :
 							map->dso->name));
@@ -206,7 +204,7 @@ next_pair:
 		mem_start = vmlinux_map->unmap_ip(vmlinux_map, map->start);
 		mem_end = vmlinux_map->unmap_ip(vmlinux_map, map->end);
 
-		pair = map_groups__find(&kallsyms.kmaps, type, mem_start);
+		pair = map_groups__find(&kallsyms.kmaps, mem_start);
 		if (pair == NULL || pair->priv)
 			continue;
 
@@ -228,7 +226,7 @@ next_pair:
 
 	header_printed = false;
 
-	maps = &kallsyms.kmaps.maps[type];
+	maps = machine__kernel_maps(&kallsyms);
 
 	for (map = maps__first(maps); map; map = map__next(map)) {
 		if (!map->priv) {
diff --git a/tools/perf/ui/browsers/annotate.c b/tools/perf/ui/browsers/annotate.c
index 3781d74088a7..8be40fa903aa 100644
--- a/tools/perf/ui/browsers/annotate.c
+++ b/tools/perf/ui/browsers/annotate.c
@@ -695,6 +695,7 @@ static int annotate_browser__run(struct annotate_browser *browser,
 		"O             Bump offset level (jump targets -> +call -> all -> cycle thru)\n"
 		"s             Toggle source code view\n"
 		"t             Circulate percent, total period, samples view\n"
+		"c             Show min/max cycle\n"
 		"/             Search string\n"
 		"k             Toggle line numbers\n"
 		"P             Print to [symbol_name].annotation file.\n"
@@ -791,6 +792,13 @@ show_sup_ins:
 				notes->options->show_total_period = true;
 			annotation__update_column_widths(notes);
 			continue;
+		case 'c':
+			if (notes->options->show_minmax_cycle)
+				notes->options->show_minmax_cycle = false;
+			else
+				notes->options->show_minmax_cycle = true;
+			annotation__update_column_widths(notes);
+			continue;
 		case K_LEFT:
 		case K_ESC:
 		case 'q':
diff --git a/tools/perf/ui/browsers/map.c b/tools/perf/ui/browsers/map.c
index e03fa75f108a..5b8b8c637686 100644
--- a/tools/perf/ui/browsers/map.c
+++ b/tools/perf/ui/browsers/map.c
@@ -104,7 +104,7 @@ int map__browse(struct map *map)
 {
 	struct map_browser mb = {
 		.b = {
-			.entries = &map->dso->symbols[map->type],
+			.entries = &map->dso->symbols,
 			.refresh = ui_browser__rb_tree_refresh,
 			.seek	 = ui_browser__rb_tree_seek,
 			.write	 = map_browser__write,
diff --git a/tools/perf/ui/stdio/hist.c b/tools/perf/ui/stdio/hist.c
index 6832fcb2e6ff..c1eb476da91b 100644
--- a/tools/perf/ui/stdio/hist.c
+++ b/tools/perf/ui/stdio/hist.c
@@ -819,8 +819,7 @@ size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows,
 		}
 
 		if (h->ms.map == NULL && verbose > 1) {
-			__map_groups__fprintf_maps(h->thread->mg,
-						   MAP__FUNCTION, fp);
+			map_groups__fprintf(h->thread->mg, fp);
 			fprintf(fp, "%.10s end\n", graph_dotted_line);
 		}
 	}
diff --git a/tools/perf/util/Build b/tools/perf/util/Build
index 8052373bcd6a..5d4c45b76895 100644
--- a/tools/perf/util/Build
+++ b/tools/perf/util/Build
@@ -152,6 +152,8 @@ libperf-y += perf-hooks.o
 libperf-$(CONFIG_CXX) += c++/
 
 CFLAGS_config.o   += -DETC_PERFCONFIG="BUILD_STR($(ETC_PERFCONFIG_SQ))"
+CFLAGS_llvm-utils.o += -DPERF_INCLUDE_DIR="BUILD_STR($(perf_include_dir_SQ))"
+
 # avoid compiler warnings in 32-bit mode
 CFLAGS_genelf_debug.o  += -Wno-packed
 
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 5d74a30fe00f..71897689dacf 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -760,6 +760,15 @@ static int __symbol__account_cycles(struct annotation *notes,
 	ch[offset].num_aggr++;
 	ch[offset].cycles_aggr += cycles;
 
+	if (cycles > ch[offset].cycles_max)
+		ch[offset].cycles_max = cycles;
+
+	if (ch[offset].cycles_min) {
+		if (cycles && cycles < ch[offset].cycles_min)
+			ch[offset].cycles_min = cycles;
+	} else
+		ch[offset].cycles_min = cycles;
+
 	if (!have_start && ch[offset].have_start)
 		return 0;
 	if (ch[offset].num) {
@@ -953,8 +962,11 @@ void annotation__compute_ipc(struct annotation *notes, size_t size)
 			if (ch->have_start)
 				annotation__count_and_fill(notes, ch->start, offset, ch);
 			al = notes->offsets[offset];
-			if (al && ch->num_aggr)
+			if (al && ch->num_aggr) {
 				al->cycles = ch->cycles_aggr / ch->num_aggr;
+				al->cycles_max = ch->cycles_max;
+				al->cycles_min = ch->cycles_min;
+			}
 			notes->have_cycles = true;
 		}
 	}
@@ -1953,6 +1965,7 @@ int symbol__annotate_printf(struct symbol *sym, struct map *map,
 	u64 len;
 	int width = symbol_conf.show_total_period ? 12 : 8;
 	int graph_dotted_len;
+	char buf[512];
 
 	filename = strdup(dso->long_name);
 	if (!filename)
@@ -1965,8 +1978,11 @@ int symbol__annotate_printf(struct symbol *sym, struct map *map,
 
 	len = symbol__size(sym);
 
-	if (perf_evsel__is_group_event(evsel))
+	if (perf_evsel__is_group_event(evsel)) {
 		width *= evsel->nr_members;
+		perf_evsel__group_desc(evsel, buf, sizeof(buf));
+		evsel_name = buf;
+	}
 
 	graph_dotted_len = printf(" %-*.*s|	Source code & Disassembly of %s for %s (%" PRIu64 " samples)\n",
 				  width, width, symbol_conf.show_total_period ? "Period" :
@@ -2486,13 +2502,38 @@ static void __annotation_line__write(struct annotation_line *al, struct annotati
 		else
 			obj__printf(obj, "%*s ", ANNOTATION__IPC_WIDTH - 1, "IPC");
 
-		if (al->cycles)
-			obj__printf(obj, "%*" PRIu64 " ",
+		if (!notes->options->show_minmax_cycle) {
+			if (al->cycles)
+				obj__printf(obj, "%*" PRIu64 " ",
 					   ANNOTATION__CYCLES_WIDTH - 1, al->cycles);
-		else if (!show_title)
-			obj__printf(obj, "%*s", ANNOTATION__CYCLES_WIDTH, " ");
-		else
-			obj__printf(obj, "%*s ", ANNOTATION__CYCLES_WIDTH - 1, "Cycle");
+			else if (!show_title)
+				obj__printf(obj, "%*s",
+					    ANNOTATION__CYCLES_WIDTH, " ");
+			else
+				obj__printf(obj, "%*s ",
+					    ANNOTATION__CYCLES_WIDTH - 1,
+					    "Cycle");
+		} else {
+			if (al->cycles) {
+				char str[32];
+
+				scnprintf(str, sizeof(str),
+					"%" PRIu64 "(%" PRIu64 "/%" PRIu64 ")",
+					al->cycles, al->cycles_min,
+					al->cycles_max);
+
+				obj__printf(obj, "%*s ",
+					    ANNOTATION__MINMAX_CYCLES_WIDTH - 1,
+					    str);
+			} else if (!show_title)
+				obj__printf(obj, "%*s",
+					    ANNOTATION__MINMAX_CYCLES_WIDTH,
+					    " ");
+			else
+				obj__printf(obj, "%*s ",
+					    ANNOTATION__MINMAX_CYCLES_WIDTH - 1,
+					    "Cycle(min/max)");
+		}
 	}
 
 	obj__printf(obj, " ");
diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h
index f28a9e43421d..5080b6dd98b8 100644
--- a/tools/perf/util/annotate.h
+++ b/tools/perf/util/annotate.h
@@ -61,6 +61,7 @@ bool ins__is_fused(struct arch *arch, const char *ins1, const char *ins2);
 
 #define ANNOTATION__IPC_WIDTH 6
 #define ANNOTATION__CYCLES_WIDTH 6
+#define ANNOTATION__MINMAX_CYCLES_WIDTH 19
 
 struct annotation_options {
 	bool hide_src_code,
@@ -69,7 +70,8 @@ struct annotation_options {
 	     show_linenr,
 	     show_nr_jumps,
 	     show_nr_samples,
-	     show_total_period;
+	     show_total_period,
+	     show_minmax_cycle;
 	u8   offset_level;
 };
 
@@ -105,6 +107,8 @@ struct annotation_line {
 	int			 jump_sources;
 	float			 ipc;
 	u64			 cycles;
+	u64			 cycles_max;
+	u64			 cycles_min;
 	size_t			 privsize;
 	char			*path;
 	u32			 idx;
@@ -186,6 +190,8 @@ struct cyc_hist {
 	u64	start;
 	u64	cycles;
 	u64	cycles_aggr;
+	u64	cycles_max;
+	u64	cycles_min;
 	u32	num;
 	u32	num_aggr;
 	u8	have_start;
@@ -239,6 +245,9 @@ struct annotation {
 
 static inline int annotation__cycles_width(struct annotation *notes)
 {
+	if (notes->have_cycles && notes->options->show_minmax_cycle)
+		return ANNOTATION__IPC_WIDTH + ANNOTATION__MINMAX_CYCLES_WIDTH;
+
 	return notes->have_cycles ? ANNOTATION__IPC_WIDTH + ANNOTATION__CYCLES_WIDTH : 0;
 }
 
diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c
index 857de69a5361..d056447520a2 100644
--- a/tools/perf/util/auxtrace.c
+++ b/tools/perf/util/auxtrace.c
@@ -1679,7 +1679,7 @@ struct sym_args {
 static bool kern_sym_match(struct sym_args *args, const char *name, char type)
 {
 	/* A function with the same name, and global or the n'th found or any */
-	return symbol_type__is_a(type, MAP__FUNCTION) &&
+	return kallsyms__is_function(type) &&
 	       !strcmp(name, args->name) &&
 	       ((args->global && isupper(type)) ||
 		(args->selected && ++(args->cnt) == args->idx) ||
@@ -1784,7 +1784,7 @@ static int find_entire_kern_cb(void *arg, const char *name __maybe_unused,
 {
 	struct sym_args *args = arg;
 
-	if (!symbol_type__is_a(type, MAP__FUNCTION))
+	if (!kallsyms__is_function(type))
 		return 0;
 
 	if (!args->started) {
@@ -1915,7 +1915,7 @@ static void print_duplicate_syms(struct dso *dso, const char *sym_name)
 
 	pr_err("Multiple symbols with name '%s'\n", sym_name);
 
-	sym = dso__first_symbol(dso, MAP__FUNCTION);
+	sym = dso__first_symbol(dso);
 	while (sym) {
 		if (dso_sym_match(sym, sym_name, &cnt, -1)) {
 			pr_err("#%d\t0x%"PRIx64"\t%c\t%s\n",
@@ -1945,7 +1945,7 @@ static int find_dso_sym(struct dso *dso, const char *sym_name, u64 *start,
 	*start = 0;
 	*size = 0;
 
-	sym = dso__first_symbol(dso, MAP__FUNCTION);
+	sym = dso__first_symbol(dso);
 	while (sym) {
 		if (*start) {
 			if (!*size)
@@ -1972,8 +1972,8 @@ static int find_dso_sym(struct dso *dso, const char *sym_name, u64 *start,
 
 static int addr_filter__entire_dso(struct addr_filter *filt, struct dso *dso)
 {
-	struct symbol *first_sym = dso__first_symbol(dso, MAP__FUNCTION);
-	struct symbol *last_sym = dso__last_symbol(dso, MAP__FUNCTION);
+	struct symbol *first_sym = dso__first_symbol(dso);
+	struct symbol *last_sym = dso__last_symbol(dso);
 
 	if (!first_sym || !last_sym) {
 		pr_err("Failed to determine filter for %s\nNo symbols found.\n",
diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c
index 537eadd81914..04b1d53e4bf9 100644
--- a/tools/perf/util/build-id.c
+++ b/tools/perf/util/build-id.c
@@ -47,9 +47,7 @@ int build_id__mark_dso_hit(struct perf_tool *tool __maybe_unused,
 		return -1;
 	}
 
-	thread__find_addr_map(thread, sample->cpumode, MAP__FUNCTION, sample->ip, &al);
-
-	if (al.map != NULL)
+	if (thread__find_map(thread, sample->cpumode, sample->ip, &al))
 		al.map->dso->hit = 1;
 
 	thread__put(thread);
diff --git a/tools/perf/util/config.c b/tools/perf/util/config.c
index 84eb9393c7db..5ac157056cdf 100644
--- a/tools/perf/util/config.c
+++ b/tools/perf/util/config.c
@@ -707,6 +707,14 @@ struct perf_config_set *perf_config_set__new(void)
 	return set;
 }
 
+static int perf_config__init(void)
+{
+	if (config_set == NULL)
+		config_set = perf_config_set__new();
+
+	return config_set == NULL;
+}
+
 int perf_config(config_fn_t fn, void *data)
 {
 	int ret = 0;
@@ -714,7 +722,7 @@ int perf_config(config_fn_t fn, void *data)
 	struct perf_config_section *section;
 	struct perf_config_item *item;
 
-	if (config_set == NULL)
+	if (config_set == NULL && perf_config__init())
 		return -1;
 
 	perf_config_set__for_each_entry(config_set, section, item) {
@@ -735,12 +743,6 @@ int perf_config(config_fn_t fn, void *data)
 	return ret;
 }
 
-void perf_config__init(void)
-{
-	if (config_set == NULL)
-		config_set = perf_config_set__new();
-}
-
 void perf_config__exit(void)
 {
 	perf_config_set__delete(config_set);
diff --git a/tools/perf/util/config.h b/tools/perf/util/config.h
index baf82bf227ac..bd0a5897c76a 100644
--- a/tools/perf/util/config.h
+++ b/tools/perf/util/config.h
@@ -38,7 +38,6 @@ struct perf_config_set *perf_config_set__new(void);
 void perf_config_set__delete(struct perf_config_set *set);
 int perf_config_set__collect(struct perf_config_set *set, const char *file_name,
 			     const char *var, const char *value);
-void perf_config__init(void);
 void perf_config__exit(void);
 void perf_config__refresh(void);
 
diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c
index bf16dc9ee507..822ba915d144 100644
--- a/tools/perf/util/cs-etm.c
+++ b/tools/perf/util/cs-etm.c
@@ -270,9 +270,7 @@ static u32 cs_etm__mem_access(struct cs_etm_queue *etmq, u64 address,
 		thread = etmq->etm->unknown_thread;
 	}
 
-	thread__find_addr_map(thread, cpumode, MAP__FUNCTION, address, &al);
-
-	if (!al.map || !al.map->dso)
+	if (!thread__find_map(thread, cpumode, address, &al) || !al.map->dso)
 		return 0;
 
 	if (al.map->dso->data.status == DSO_DATA_STATUS_ERROR &&
diff --git a/tools/perf/util/db-export.c b/tools/perf/util/db-export.c
index b0c2b5c5d337..7123746edcf4 100644
--- a/tools/perf/util/db-export.c
+++ b/tools/perf/util/db-export.c
@@ -247,9 +247,9 @@ static int db_ids_from_al(struct db_export *dbe, struct addr_location *al,
 		*dso_db_id = dso->db_id;
 
 		if (!al->sym) {
-			al->sym = symbol__new(al->addr, 0, 0, "unknown");
+			al->sym = symbol__new(al->addr, 0, 0, 0, "unknown");
 			if (al->sym)
-				dso__insert_symbol(dso, al->map->type, al->sym);
+				dso__insert_symbol(dso, al->sym);
 		}
 
 		if (al->sym) {
@@ -315,8 +315,7 @@ static struct call_path *call_path_from_sample(struct db_export *dbe,
 		al.addr = node->ip;
 
 		if (al.map && !al.sym)
-			al.sym = dso__find_symbol(al.map->dso, MAP__FUNCTION,
-						  al.addr);
+			al.sym = dso__find_symbol(al.map->dso, al.addr);
 
 		db_ids_from_al(dbe, &al, &dso_db_id, &sym_db_id, &offset);
 
diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c
index 36ef45b2e89d..cdfc2e5f55f5 100644
--- a/tools/perf/util/dso.c
+++ b/tools/perf/util/dso.c
@@ -1014,7 +1014,7 @@ struct map *dso__new_map(const char *name)
 	struct dso *dso = dso__new(name);
 
 	if (dso)
-		map = map__new2(0, dso, MAP__FUNCTION);
+		map = map__new2(0, dso);
 
 	return map;
 }
@@ -1176,19 +1176,19 @@ int dso__name_len(const struct dso *dso)
 	return dso->short_name_len;
 }
 
-bool dso__loaded(const struct dso *dso, enum map_type type)
+bool dso__loaded(const struct dso *dso)
 {
-	return dso->loaded & (1 << type);
+	return dso->loaded;
 }
 
-bool dso__sorted_by_name(const struct dso *dso, enum map_type type)
+bool dso__sorted_by_name(const struct dso *dso)
 {
-	return dso->sorted_by_name & (1 << type);
+	return dso->sorted_by_name;
 }
 
-void dso__set_sorted_by_name(struct dso *dso, enum map_type type)
+void dso__set_sorted_by_name(struct dso *dso)
 {
-	dso->sorted_by_name |= (1 << type);
+	dso->sorted_by_name = true;
 }
 
 struct dso *dso__new(const char *name)
@@ -1196,12 +1196,10 @@ struct dso *dso__new(const char *name)
 	struct dso *dso = calloc(1, sizeof(*dso) + strlen(name) + 1);
 
 	if (dso != NULL) {
-		int i;
 		strcpy(dso->name, name);
 		dso__set_long_name(dso, dso->name, false);
 		dso__set_short_name(dso, dso->name, false);
-		for (i = 0; i < MAP__NR_TYPES; ++i)
-			dso->symbols[i] = dso->symbol_names[i] = RB_ROOT;
+		dso->symbols = dso->symbol_names = RB_ROOT;
 		dso->data.cache = RB_ROOT;
 		dso->inlined_nodes = RB_ROOT;
 		dso->srclines = RB_ROOT;
@@ -1231,8 +1229,6 @@ struct dso *dso__new(const char *name)
 
 void dso__delete(struct dso *dso)
 {
-	int i;
-
 	if (!RB_EMPTY_NODE(&dso->rb_node))
 		pr_err("DSO %s is still in rbtree when being deleted!\n",
 		       dso->long_name);
@@ -1240,8 +1236,7 @@ void dso__delete(struct dso *dso)
 	/* free inlines first, as they reference symbols */
 	inlines__tree_delete(&dso->inlined_nodes);
 	srcline__tree_delete(&dso->srclines);
-	for (i = 0; i < MAP__NR_TYPES; ++i)
-		symbols__delete(&dso->symbols[i]);
+	symbols__delete(&dso->symbols);
 
 	if (dso->short_name_allocated) {
 		zfree((char **)&dso->short_name);
@@ -1451,9 +1446,7 @@ size_t __dsos__fprintf(struct list_head *head, FILE *fp)
 	size_t ret = 0;
 
 	list_for_each_entry(pos, head, node) {
-		int i;
-		for (i = 0; i < MAP__NR_TYPES; ++i)
-			ret += dso__fprintf(pos, i, fp);
+		ret += dso__fprintf(pos, fp);
 	}
 
 	return ret;
@@ -1467,18 +1460,17 @@ size_t dso__fprintf_buildid(struct dso *dso, FILE *fp)
 	return fprintf(fp, "%s", sbuild_id);
 }
 
-size_t dso__fprintf(struct dso *dso, enum map_type type, FILE *fp)
+size_t dso__fprintf(struct dso *dso, FILE *fp)
 {
 	struct rb_node *nd;
 	size_t ret = fprintf(fp, "dso: %s (", dso->short_name);
 
 	if (dso->short_name != dso->long_name)
 		ret += fprintf(fp, "%s, ", dso->long_name);
-	ret += fprintf(fp, "%s, %sloaded, ", map_type__name[type],
-		       dso__loaded(dso, type) ? "" : "NOT ");
+	ret += fprintf(fp, "%sloaded, ", dso__loaded(dso) ? "" : "NOT ");
 	ret += dso__fprintf_buildid(dso, fp);
 	ret += fprintf(fp, ")\n");
-	for (nd = rb_first(&dso->symbols[type]); nd; nd = rb_next(nd)) {
+	for (nd = rb_first(&dso->symbols); nd; nd = rb_next(nd)) {
 		struct symbol *pos = rb_entry(nd, struct symbol, rb_node);
 		ret += symbol__fprintf(pos, fp);
 	}
diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h
index c229dbe0277a..ef69de2e69ea 100644
--- a/tools/perf/util/dso.h
+++ b/tools/perf/util/dso.h
@@ -140,14 +140,14 @@ struct dso {
 	struct list_head node;
 	struct rb_node	 rb_node;	/* rbtree node sorted by long name */
 	struct rb_root	 *root;		/* root of rbtree that rb_node is in */
-	struct rb_root	 symbols[MAP__NR_TYPES];
-	struct rb_root	 symbol_names[MAP__NR_TYPES];
+	struct rb_root	 symbols;
+	struct rb_root	 symbol_names;
 	struct rb_root	 inlined_nodes;
 	struct rb_root	 srclines;
 	struct {
 		u64		addr;
 		struct symbol	*symbol;
-	} last_find_result[MAP__NR_TYPES];
+	} last_find_result;
 	void		 *a2l;
 	char		 *symsrc_filename;
 	unsigned int	 a2l_fails;
@@ -164,8 +164,8 @@ struct dso {
 	u8		 short_name_allocated:1;
 	u8		 long_name_allocated:1;
 	u8		 is_64_bit:1;
-	u8		 sorted_by_name;
-	u8		 loaded;
+	bool		 sorted_by_name;
+	bool		 loaded;
 	u8		 rel;
 	u8		 build_id[BUILD_ID_SIZE];
 	u64		 text_offset;
@@ -202,14 +202,13 @@ struct dso {
  * @dso: the 'struct dso *' in which symbols itereated
  * @pos: the 'struct symbol *' to use as a loop cursor
  * @n: the 'struct rb_node *' to use as a temporary storage
- * @type: the 'enum map_type' type of symbols
  */
-#define dso__for_each_symbol(dso, pos, n, type)	\
-	symbols__for_each_entry(&(dso)->symbols[(type)], pos, n)
+#define dso__for_each_symbol(dso, pos, n)	\
+	symbols__for_each_entry(&(dso)->symbols, pos, n)
 
-static inline void dso__set_loaded(struct dso *dso, enum map_type type)
+static inline void dso__set_loaded(struct dso *dso)
 {
-	dso->loaded |= (1 << type);
+	dso->loaded = true;
 }
 
 struct dso *dso__new(const char *name);
@@ -231,11 +230,16 @@ static inline void __dso__zput(struct dso **dso)
 
 #define dso__zput(dso) __dso__zput(&dso)
 
-bool dso__loaded(const struct dso *dso, enum map_type type);
+bool dso__loaded(const struct dso *dso);
 
-bool dso__sorted_by_name(const struct dso *dso, enum map_type type);
-void dso__set_sorted_by_name(struct dso *dso, enum map_type type);
-void dso__sort_by_name(struct dso *dso, enum map_type type);
+static inline bool dso__has_symbols(const struct dso *dso)
+{
+	return !RB_EMPTY_ROOT(&dso->symbols);
+}
+
+bool dso__sorted_by_name(const struct dso *dso);
+void dso__set_sorted_by_name(struct dso *dso);
+void dso__sort_by_name(struct dso *dso);
 
 void dso__set_build_id(struct dso *dso, void *build_id);
 bool dso__build_id_equal(const struct dso *dso, u8 *build_id);
@@ -349,9 +353,8 @@ size_t __dsos__fprintf_buildid(struct list_head *head, FILE *fp,
 size_t __dsos__fprintf(struct list_head *head, FILE *fp);
 
 size_t dso__fprintf_buildid(struct dso *dso, FILE *fp);
-size_t dso__fprintf_symbols_by_name(struct dso *dso,
-				    enum map_type type, FILE *fp);
-size_t dso__fprintf(struct dso *dso, enum map_type type, FILE *fp);
+size_t dso__fprintf_symbols_by_name(struct dso *dso, FILE *fp);
+size_t dso__fprintf(struct dso *dso, FILE *fp);
 
 static inline bool dso__is_vmlinux(struct dso *dso)
 {
diff --git a/tools/perf/util/env.c b/tools/perf/util/env.c
index 4c842762e3f2..59f38c7693f8 100644
--- a/tools/perf/util/env.c
+++ b/tools/perf/util/env.c
@@ -93,6 +93,37 @@ int perf_env__read_cpu_topology_map(struct perf_env *env)
 	return 0;
 }
 
+static int perf_env__read_arch(struct perf_env *env)
+{
+	struct utsname uts;
+
+	if (env->arch)
+		return 0;
+
+	if (!uname(&uts))
+		env->arch = strdup(uts.machine);
+
+	return env->arch ? 0 : -ENOMEM;
+}
+
+static int perf_env__read_nr_cpus_avail(struct perf_env *env)
+{
+	if (env->nr_cpus_avail == 0)
+		env->nr_cpus_avail = cpu__max_present_cpu();
+
+	return env->nr_cpus_avail ? 0 : -ENOENT;
+}
+
+const char *perf_env__raw_arch(struct perf_env *env)
+{
+	return env && !perf_env__read_arch(env) ? env->arch : "unknown";
+}
+
+int perf_env__nr_cpus_avail(struct perf_env *env)
+{
+	return env && !perf_env__read_nr_cpus_avail(env) ? env->nr_cpus_avail : 0;
+}
+
 void cpu_cache_level__free(struct cpu_cache_level *cache)
 {
 	free(cache->type);
diff --git a/tools/perf/util/env.h b/tools/perf/util/env.h
index c4ef2e523367..1f3ccc368530 100644
--- a/tools/perf/util/env.h
+++ b/tools/perf/util/env.h
@@ -76,4 +76,7 @@ int perf_env__read_cpu_topology_map(struct perf_env *env);
 void cpu_cache_level__free(struct cpu_cache_level *cache);
 
 const char *perf_env__arch(struct perf_env *env);
+const char *perf_env__raw_arch(struct perf_env *env);
+int perf_env__nr_cpus_avail(struct perf_env *env);
+
 #endif /* __PERF_ENV_H */
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index 98ff3a6a3d50..0c8ecf0c78a4 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -88,10 +88,10 @@ static const char *perf_ns__name(unsigned int id)
 	return perf_ns__names[id];
 }
 
-static int perf_tool__process_synth_event(struct perf_tool *tool,
-					  union perf_event *event,
-					  struct machine *machine,
-					  perf_event__handler_t process)
+int perf_tool__process_synth_event(struct perf_tool *tool,
+				   union perf_event *event,
+				   struct machine *machine,
+				   perf_event__handler_t process)
 {
 	struct perf_sample synth_sample = {
 	.pid	   = -1,
@@ -464,8 +464,7 @@ int perf_event__synthesize_modules(struct perf_tool *tool,
 {
 	int rc = 0;
 	struct map *pos;
-	struct map_groups *kmaps = &machine->kmaps;
-	struct maps *maps = &kmaps->maps[MAP__FUNCTION];
+	struct maps *maps = machine__kernel_maps(machine);
 	union perf_event *event = zalloc((sizeof(event->mmap) +
 					  machine->id_hdr_size));
 	if (event == NULL) {
@@ -488,7 +487,7 @@ int perf_event__synthesize_modules(struct perf_tool *tool,
 	for (pos = maps__first(maps); pos; pos = map__next(pos)) {
 		size_t size;
 
-		if (__map__is_kernel(pos))
+		if (!__map__is_kmodule(pos))
 			continue;
 
 		size = PERF_ALIGN(pos->dso->long_name_len + 1, sizeof(u64));
@@ -869,7 +868,7 @@ static int find_symbol_cb(void *arg, const char *name, char type,
 	 * Must be a function or at least an alias, as in PARISC64, where "_text" is
 	 * an 'A' to the same address as "_stext".
 	 */
-	if (!(symbol_type__is_a(type, MAP__FUNCTION) ||
+	if (!(kallsyms__is_function(type) ||
 	      type == 'A') || strcmp(name, args->name))
 		return 0;
 
@@ -889,9 +888,16 @@ int kallsyms__get_function_start(const char *kallsyms_filename,
 	return 0;
 }
 
-int perf_event__synthesize_kernel_mmap(struct perf_tool *tool,
-				       perf_event__handler_t process,
-				       struct machine *machine)
+int __weak perf_event__synthesize_extra_kmaps(struct perf_tool *tool __maybe_unused,
+					      perf_event__handler_t process __maybe_unused,
+					      struct machine *machine __maybe_unused)
+{
+	return 0;
+}
+
+static int __perf_event__synthesize_kernel_mmap(struct perf_tool *tool,
+						perf_event__handler_t process,
+						struct machine *machine)
 {
 	size_t size;
 	struct map *map = machine__kernel_map(machine);
@@ -944,6 +950,19 @@ int perf_event__synthesize_kernel_mmap(struct perf_tool *tool,
 	return err;
 }
 
+int perf_event__synthesize_kernel_mmap(struct perf_tool *tool,
+				       perf_event__handler_t process,
+				       struct machine *machine)
+{
+	int err;
+
+	err = __perf_event__synthesize_kernel_mmap(tool, process, machine);
+	if (err < 0)
+		return err;
+
+	return perf_event__synthesize_extra_kmaps(tool, process, machine);
+}
+
 int perf_event__synthesize_thread_map2(struct perf_tool *tool,
 				      struct thread_map *threads,
 				      perf_event__handler_t process,
@@ -1489,9 +1508,8 @@ int perf_event__process(struct perf_tool *tool __maybe_unused,
 	return machine__process_event(machine, event, sample);
 }
 
-void thread__find_addr_map(struct thread *thread, u8 cpumode,
-			   enum map_type type, u64 addr,
-			   struct addr_location *al)
+struct map *thread__find_map(struct thread *thread, u8 cpumode, u64 addr,
+			     struct addr_location *al)
 {
 	struct map_groups *mg = thread->mg;
 	struct machine *machine = mg->machine;
@@ -1505,7 +1523,7 @@ void thread__find_addr_map(struct thread *thread, u8 cpumode,
 
 	if (machine == NULL) {
 		al->map = NULL;
-		return;
+		return NULL;
 	}
 
 	if (cpumode == PERF_RECORD_MISC_KERNEL && perf_host) {
@@ -1533,10 +1551,10 @@ void thread__find_addr_map(struct thread *thread, u8 cpumode,
 			!perf_host)
 			al->filtered |= (1 << HIST_FILTER__HOST);
 
-		return;
+		return NULL;
 	}
 try_again:
-	al->map = map_groups__find(mg, type, al->addr);
+	al->map = map_groups__find(mg, al->addr);
 	if (al->map == NULL) {
 		/*
 		 * If this is outside of all known maps, and is a negative
@@ -1563,17 +1581,17 @@ try_again:
 			map__load(al->map);
 		al->addr = al->map->map_ip(al->map, al->addr);
 	}
+
+	return al->map;
 }
 
-void thread__find_addr_location(struct thread *thread,
-				u8 cpumode, enum map_type type, u64 addr,
-				struct addr_location *al)
+struct symbol *thread__find_symbol(struct thread *thread, u8 cpumode,
+				   u64 addr, struct addr_location *al)
 {
-	thread__find_addr_map(thread, cpumode, type, addr, al);
-	if (al->map != NULL)
+	al->sym = NULL;
+	if (thread__find_map(thread, cpumode, addr, al))
 		al->sym = map__find_symbol(al->map, al->addr);
-	else
-		al->sym = NULL;
+	return al->sym;
 }
 
 /*
@@ -1590,7 +1608,7 @@ int machine__resolve(struct machine *machine, struct addr_location *al,
 		return -1;
 
 	dump_printf(" ... thread: %s:%d\n", thread__comm_str(thread), thread->tid);
-	thread__find_addr_map(thread, sample->cpumode, MAP__FUNCTION, sample->ip, al);
+	thread__find_map(thread, sample->cpumode, sample->ip, al);
 	dump_printf(" ...... dso: %s\n",
 		    al->map ? al->map->dso->long_name :
 			al->level == 'H' ? "[hypervisor]" : "<not found>");
@@ -1669,10 +1687,7 @@ bool sample_addr_correlates_sym(struct perf_event_attr *attr)
 void thread__resolve(struct thread *thread, struct addr_location *al,
 		     struct perf_sample *sample)
 {
-	thread__find_addr_map(thread, sample->cpumode, MAP__FUNCTION, sample->addr, al);
-	if (!al->map)
-		thread__find_addr_map(thread, sample->cpumode, MAP__VARIABLE,
-				      sample->addr, al);
+	thread__find_map(thread, sample->cpumode, sample->addr, al);
 
 	al->cpu = sample->cpu;
 	al->sym = NULL;
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index 0f794744919c..bfa60bcafbde 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -750,6 +750,10 @@ int perf_event__process_exit(struct perf_tool *tool,
 			     union perf_event *event,
 			     struct perf_sample *sample,
 			     struct machine *machine);
+int perf_tool__process_synth_event(struct perf_tool *tool,
+				   union perf_event *event,
+				   struct machine *machine,
+				   perf_event__handler_t process);
 int perf_event__process(struct perf_tool *tool,
 			union perf_event *event,
 			struct perf_sample *sample,
@@ -796,6 +800,10 @@ int perf_event__synthesize_mmap_events(struct perf_tool *tool,
 				       bool mmap_data,
 				       unsigned int proc_map_timeout);
 
+int perf_event__synthesize_extra_kmaps(struct perf_tool *tool,
+				       perf_event__handler_t process,
+				       struct machine *machine);
+
 size_t perf_event__fprintf_comm(union perf_event *event, FILE *fp);
 size_t perf_event__fprintf_mmap(union perf_event *event, FILE *fp);
 size_t perf_event__fprintf_mmap2(union perf_event *event, FILE *fp);
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index a59281d64368..e7a4b31a84fb 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -1795,3 +1795,18 @@ bool perf_evlist__exclude_kernel(struct perf_evlist *evlist)
 
 	return true;
 }
+
+/*
+ * Events in data file are not collect in groups, but we still want
+ * the group display. Set the artificial group and set the leader's
+ * forced_leader flag to notify the display code.
+ */
+void perf_evlist__force_leader(struct perf_evlist *evlist)
+{
+	if (!evlist->nr_groups) {
+		struct perf_evsel *leader = perf_evlist__first(evlist);
+
+		perf_evlist__set_leader(evlist);
+		leader->forced_leader = true;
+	}
+}
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index 6c41b2f78713..dc66436add98 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -309,4 +309,7 @@ struct perf_evsel *perf_evlist__event2evsel(struct perf_evlist *evlist,
 					    union perf_event *event);
 
 bool perf_evlist__exclude_kernel(struct perf_evlist *evlist);
+
+void perf_evlist__force_leader(struct perf_evlist *evlist);
+
 #endif /* __PERF_EVLIST_H */
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 4cd2cf93f726..150db5ed7400 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -2862,7 +2862,7 @@ int perf_evsel__open_strerror(struct perf_evsel *evsel, struct target *target,
 			return scnprintf(msg, size,
 					 "Not enough memory to setup event with callchain.\n"
 					 "Hint: Try tweaking /proc/sys/kernel/perf_event_max_stack\n"
-					 "Hint: Current value: %d", sysctl_perf_event_max_stack);
+					 "Hint: Current value: %d", sysctl__max_stack());
 		break;
 	case ENODEV:
 		if (target->cpu_list)
diff --git a/tools/perf/util/genelf.c b/tools/perf/util/genelf.c
index c540d47583e7..aafbe54fd3fa 100644
--- a/tools/perf/util/genelf.c
+++ b/tools/perf/util/genelf.c
@@ -114,7 +114,7 @@ gen_build_id(struct buildid_note *note,
 
 	fd = open("/dev/urandom", O_RDONLY);
 	if (fd == -1)
-		err(1, "cannot access /dev/urandom for builid");
+		err(1, "cannot access /dev/urandom for buildid");
 
 	sret = read(fd, note->build_id, sz);
 
diff --git a/tools/perf/util/intel-bts.c b/tools/perf/util/intel-bts.c
index 72db2744876d..7f0c83b6332b 100644
--- a/tools/perf/util/intel-bts.c
+++ b/tools/perf/util/intel-bts.c
@@ -335,8 +335,7 @@ static int intel_bts_get_next_insn(struct intel_bts_queue *btsq, u64 ip)
 	if (!thread)
 		return -1;
 
-	thread__find_addr_map(thread, cpumode, MAP__FUNCTION, ip, &al);
-	if (!al.map || !al.map->dso)
+	if (!thread__find_map(thread, cpumode, ip, &al) || !al.map->dso)
 		goto out_put;
 
 	len = dso__data_read_addr(al.map->dso, al.map, machine, ip, buf,
diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c
index 0effaff57020..492986a25ef6 100644
--- a/tools/perf/util/intel-pt.c
+++ b/tools/perf/util/intel-pt.c
@@ -442,8 +442,7 @@ static int intel_pt_walk_next_insn(struct intel_pt_insn *intel_pt_insn,
 	}
 
 	while (1) {
-		thread__find_addr_map(thread, cpumode, MAP__FUNCTION, *ip, &al);
-		if (!al.map || !al.map->dso)
+		if (!thread__find_map(thread, cpumode, *ip, &al) || !al.map->dso)
 			return -EINVAL;
 
 		if (al.map->dso->data.status == DSO_DATA_STATUS_ERROR &&
@@ -596,8 +595,7 @@ static int __intel_pt_pgd_ip(uint64_t ip, void *data)
 	if (!thread)
 		return -EINVAL;
 
-	thread__find_addr_map(thread, cpumode, MAP__FUNCTION, ip, &al);
-	if (!al.map || !al.map->dso)
+	if (!thread__find_map(thread, cpumode, ip, &al) || !al.map->dso)
 		return -EINVAL;
 
 	offset = al.map->map_ip(al.map, ip);
@@ -1565,7 +1563,7 @@ static u64 intel_pt_switch_ip(struct intel_pt *pt, u64 *ptss_ip)
 	if (map__load(map))
 		return 0;
 
-	start = dso__first_symbol(map->dso, MAP__FUNCTION);
+	start = dso__first_symbol(map->dso);
 
 	for (sym = start; sym; sym = dso__next_symbol(sym)) {
 		if (sym->binding == STB_GLOBAL &&
diff --git a/tools/perf/util/llvm-utils.c b/tools/perf/util/llvm-utils.c
index 1cca0a2fa641..976e658e38dc 100644
--- a/tools/perf/util/llvm-utils.c
+++ b/tools/perf/util/llvm-utils.c
@@ -14,11 +14,12 @@
 #include "config.h"
 #include "util.h"
 #include <sys/wait.h>
+#include <subcmd/exec-cmd.h>
 
 #define CLANG_BPF_CMD_DEFAULT_TEMPLATE				\
 		"$CLANG_EXEC -D__KERNEL__ -D__NR_CPUS__=$NR_CPUS "\
 		"-DLINUX_VERSION_CODE=$LINUX_VERSION_CODE "	\
-		"$CLANG_OPTIONS $KERNEL_INC_OPTIONS "		\
+		"$CLANG_OPTIONS $KERNEL_INC_OPTIONS $PERF_BPF_INC_OPTIONS " \
 		"-Wno-unused-value -Wno-pointer-sign "		\
 		"-working-directory $WORKING_DIR "		\
 		"-c \"$CLANG_SOURCE\" -target bpf -O2 -o -"
@@ -212,7 +213,7 @@ version_notice(void)
 "     \t\thttp://llvm.org/apt\n\n"
 "     \tIf you are using old version of clang, change 'clang-bpf-cmd-template'\n"
 "     \toption in [llvm] section of ~/.perfconfig to:\n\n"
-"     \t  \"$CLANG_EXEC $CLANG_OPTIONS $KERNEL_INC_OPTIONS \\\n"
+"     \t  \"$CLANG_EXEC $CLANG_OPTIONS $KERNEL_INC_OPTIONS $PERF_BPF_INC_OPTIONS \\\n"
 "     \t     -working-directory $WORKING_DIR -c $CLANG_SOURCE \\\n"
 "     \t     -emit-llvm -o - | /path/to/llc -march=bpf -filetype=obj -o -\"\n"
 "     \t(Replace /path/to/llc with path to your llc)\n\n"
@@ -431,9 +432,11 @@ int llvm__compile_bpf(const char *path, void **p_obj_buf,
 	const char *clang_opt = llvm_param.clang_opt;
 	char clang_path[PATH_MAX], abspath[PATH_MAX], nr_cpus_avail_str[64];
 	char serr[STRERR_BUFSIZE];
-	char *kbuild_dir = NULL, *kbuild_include_opts = NULL;
+	char *kbuild_dir = NULL, *kbuild_include_opts = NULL,
+	     *perf_bpf_include_opts = NULL;
 	const char *template = llvm_param.clang_bpf_cmd_template;
-	char *command_echo, *command_out;
+	char *command_echo = NULL, *command_out;
+	char *perf_include_dir = system_path(PERF_INCLUDE_DIR);
 
 	if (path[0] != '-' && realpath(path, abspath) == NULL) {
 		err = errno;
@@ -471,12 +474,14 @@ int llvm__compile_bpf(const char *path, void **p_obj_buf,
 
 	snprintf(linux_version_code_str, sizeof(linux_version_code_str),
 		 "0x%x", kernel_version);
-
+	if (asprintf(&perf_bpf_include_opts, "-I%s/bpf", perf_include_dir) < 0)
+		goto errout;
 	force_set_env("NR_CPUS", nr_cpus_avail_str);
 	force_set_env("LINUX_VERSION_CODE", linux_version_code_str);
 	force_set_env("CLANG_EXEC", clang_path);
 	force_set_env("CLANG_OPTIONS", clang_opt);
 	force_set_env("KERNEL_INC_OPTIONS", kbuild_include_opts);
+	force_set_env("PERF_BPF_INC_OPTIONS", perf_bpf_include_opts);
 	force_set_env("WORKING_DIR", kbuild_dir ? : ".");
 
 	/*
@@ -512,6 +517,8 @@ int llvm__compile_bpf(const char *path, void **p_obj_buf,
 	free(command_out);
 	free(kbuild_dir);
 	free(kbuild_include_opts);
+	free(perf_bpf_include_opts);
+	free(perf_include_dir);
 
 	if (!p_obj_buf)
 		free(obj_buf);
@@ -526,6 +533,8 @@ errout:
 	free(kbuild_dir);
 	free(kbuild_include_opts);
 	free(obj_buf);
+	free(perf_bpf_include_opts);
+	free(perf_include_dir);
 	if (p_obj_buf)
 		*p_obj_buf = NULL;
 	if (p_obj_buf_sz)
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 32d50492505d..e7b4a8b513f2 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -24,6 +24,7 @@
 
 #include "sane_ctype.h"
 #include <symbol/kallsyms.h>
+#include <linux/mman.h>
 
 static void __machine__remove_thread(struct machine *machine, struct thread *th, bool lock);
 
@@ -81,8 +82,7 @@ int machine__init(struct machine *machine, const char *root_dir, pid_t pid)
 	machine->kptr_restrict_warned = false;
 	machine->comm_exec = false;
 	machine->kernel_start = 0;
-
-	memset(machine->vmlinux_maps, 0, sizeof(machine->vmlinux_maps));
+	machine->vmlinux_map = NULL;
 
 	machine->root_dir = strdup(root_dir);
 	if (machine->root_dir == NULL)
@@ -137,13 +137,11 @@ struct machine *machine__new_kallsyms(void)
 	struct machine *machine = machine__new_host();
 	/*
 	 * FIXME:
-	 * 1) MAP__FUNCTION will go away when we stop loading separate maps for
-	 *    functions and data objects.
-	 * 2) We should switch to machine__load_kallsyms(), i.e. not explicitely
+	 * 1) We should switch to machine__load_kallsyms(), i.e. not explicitely
 	 *    ask for not using the kcore parsing code, once this one is fixed
 	 *    to create a map per module.
 	 */
-	if (machine && machine__load_kallsyms(machine, "/proc/kallsyms", MAP__FUNCTION) <= 0) {
+	if (machine && machine__load_kallsyms(machine, "/proc/kallsyms") <= 0) {
 		machine__delete(machine);
 		machine = NULL;
 	}
@@ -673,8 +671,7 @@ struct map *machine__findnew_module_map(struct machine *machine, u64 start,
 	if (kmod_path__parse_name(&m, filename))
 		return NULL;
 
-	map = map_groups__find_by_name(&machine->kmaps, MAP__FUNCTION,
-				       m.name);
+	map = map_groups__find_by_name(&machine->kmaps, m.name);
 	if (map) {
 		/*
 		 * If the map's dso is an offline module, give dso__load()
@@ -689,7 +686,7 @@ struct map *machine__findnew_module_map(struct machine *machine, u64 start,
 	if (dso == NULL)
 		goto out;
 
-	map = map__new2(start, dso, MAP__FUNCTION);
+	map = map__new2(start, dso);
 	if (map == NULL)
 		goto out;
 
@@ -810,8 +807,8 @@ struct process_args {
 	u64 start;
 };
 
-static void machine__get_kallsyms_filename(struct machine *machine, char *buf,
-					   size_t bufsz)
+void machine__get_kallsyms_filename(struct machine *machine, char *buf,
+				    size_t bufsz)
 {
 	if (machine__is_default_guest(machine))
 		scnprintf(buf, bufsz, "%s", symbol_conf.default_guest_kallsyms);
@@ -854,65 +851,171 @@ static int machine__get_running_kernel_start(struct machine *machine,
 	return 0;
 }
 
+int machine__create_extra_kernel_map(struct machine *machine,
+				     struct dso *kernel,
+				     struct extra_kernel_map *xm)
+{
+	struct kmap *kmap;
+	struct map *map;
+
+	map = map__new2(xm->start, kernel);
+	if (!map)
+		return -1;
+
+	map->end   = xm->end;
+	map->pgoff = xm->pgoff;
+
+	kmap = map__kmap(map);
+
+	kmap->kmaps = &machine->kmaps;
+	strlcpy(kmap->name, xm->name, KMAP_NAME_LEN);
+
+	map_groups__insert(&machine->kmaps, map);
+
+	pr_debug2("Added extra kernel map %s %" PRIx64 "-%" PRIx64 "\n",
+		  kmap->name, map->start, map->end);
+
+	map__put(map);
+
+	return 0;
+}
+
+static u64 find_entry_trampoline(struct dso *dso)
+{
+	/* Duplicates are removed so lookup all aliases */
+	const char *syms[] = {
+		"_entry_trampoline",
+		"__entry_trampoline_start",
+		"entry_SYSCALL_64_trampoline",
+	};
+	struct symbol *sym = dso__first_symbol(dso);
+	unsigned int i;
+
+	for (; sym; sym = dso__next_symbol(sym)) {
+		if (sym->binding != STB_GLOBAL)
+			continue;
+		for (i = 0; i < ARRAY_SIZE(syms); i++) {
+			if (!strcmp(sym->name, syms[i]))
+				return sym->start;
+		}
+	}
+
+	return 0;
+}
+
+/*
+ * These values can be used for kernels that do not have symbols for the entry
+ * trampolines in kallsyms.
+ */
+#define X86_64_CPU_ENTRY_AREA_PER_CPU	0xfffffe0000000000ULL
+#define X86_64_CPU_ENTRY_AREA_SIZE	0x2c000
+#define X86_64_ENTRY_TRAMPOLINE		0x6000
+
+/* Map x86_64 PTI entry trampolines */
+int machine__map_x86_64_entry_trampolines(struct machine *machine,
+					  struct dso *kernel)
+{
+	struct map_groups *kmaps = &machine->kmaps;
+	struct maps *maps = &kmaps->maps;
+	int nr_cpus_avail, cpu;
+	bool found = false;
+	struct map *map;
+	u64 pgoff;
+
+	/*
+	 * In the vmlinux case, pgoff is a virtual address which must now be
+	 * mapped to a vmlinux offset.
+	 */
+	for (map = maps__first(maps); map; map = map__next(map)) {
+		struct kmap *kmap = __map__kmap(map);
+		struct map *dest_map;
+
+		if (!kmap || !is_entry_trampoline(kmap->name))
+			continue;
+
+		dest_map = map_groups__find(kmaps, map->pgoff);
+		if (dest_map != map)
+			map->pgoff = dest_map->map_ip(dest_map, map->pgoff);
+		found = true;
+	}
+	if (found || machine->trampolines_mapped)
+		return 0;
+
+	pgoff = find_entry_trampoline(kernel);
+	if (!pgoff)
+		return 0;
+
+	nr_cpus_avail = machine__nr_cpus_avail(machine);
+
+	/* Add a 1 page map for each CPU's entry trampoline */
+	for (cpu = 0; cpu < nr_cpus_avail; cpu++) {
+		u64 va = X86_64_CPU_ENTRY_AREA_PER_CPU +
+			 cpu * X86_64_CPU_ENTRY_AREA_SIZE +
+			 X86_64_ENTRY_TRAMPOLINE;
+		struct extra_kernel_map xm = {
+			.start = va,
+			.end   = va + page_size,
+			.pgoff = pgoff,
+		};
+
+		strlcpy(xm.name, ENTRY_TRAMPOLINE_NAME, KMAP_NAME_LEN);
+
+		if (machine__create_extra_kernel_map(machine, kernel, &xm) < 0)
+			return -1;
+	}
+
+	machine->trampolines_mapped = nr_cpus_avail;
+
+	return 0;
+}
+
+int __weak machine__create_extra_kernel_maps(struct machine *machine __maybe_unused,
+					     struct dso *kernel __maybe_unused)
+{
+	return 0;
+}
+
 static int
 __machine__create_kernel_maps(struct machine *machine, struct dso *kernel)
 {
-	int type;
+	struct kmap *kmap;
+	struct map *map;
 
 	/* In case of renewal the kernel map, destroy previous one */
 	machine__destroy_kernel_maps(machine);
 
-	for (type = 0; type < MAP__NR_TYPES; ++type) {
-		struct kmap *kmap;
-		struct map *map;
+	machine->vmlinux_map = map__new2(0, kernel);
+	if (machine->vmlinux_map == NULL)
+		return -1;
 
-		machine->vmlinux_maps[type] = map__new2(0, kernel, type);
-		if (machine->vmlinux_maps[type] == NULL)
-			return -1;
+	machine->vmlinux_map->map_ip = machine->vmlinux_map->unmap_ip = identity__map_ip;
+	map = machine__kernel_map(machine);
+	kmap = map__kmap(map);
+	if (!kmap)
+		return -1;
 
-		machine->vmlinux_maps[type]->map_ip =
-			machine->vmlinux_maps[type]->unmap_ip =
-				identity__map_ip;
-		map = __machine__kernel_map(machine, type);
-		kmap = map__kmap(map);
-		if (!kmap)
-			return -1;
-
-		kmap->kmaps = &machine->kmaps;
-		map_groups__insert(&machine->kmaps, map);
-	}
+	kmap->kmaps = &machine->kmaps;
+	map_groups__insert(&machine->kmaps, map);
 
 	return 0;
 }
 
 void machine__destroy_kernel_maps(struct machine *machine)
 {
-	int type;
+	struct kmap *kmap;
+	struct map *map = machine__kernel_map(machine);
 
-	for (type = 0; type < MAP__NR_TYPES; ++type) {
-		struct kmap *kmap;
-		struct map *map = __machine__kernel_map(machine, type);
+	if (map == NULL)
+		return;
 
-		if (map == NULL)
-			continue;
-
-		kmap = map__kmap(map);
-		map_groups__remove(&machine->kmaps, map);
-		if (kmap && kmap->ref_reloc_sym) {
-			/*
-			 * ref_reloc_sym is shared among all maps, so free just
-			 * on one of them.
-			 */
-			if (type == MAP__FUNCTION) {
-				zfree((char **)&kmap->ref_reloc_sym->name);
-				zfree(&kmap->ref_reloc_sym);
-			} else
-				kmap->ref_reloc_sym = NULL;
-		}
-
-		map__put(machine->vmlinux_maps[type]);
-		machine->vmlinux_maps[type] = NULL;
+	kmap = map__kmap(map);
+	map_groups__remove(&machine->kmaps, map);
+	if (kmap && kmap->ref_reloc_sym) {
+		zfree((char **)&kmap->ref_reloc_sym->name);
+		zfree(&kmap->ref_reloc_sym);
 	}
+
+	map__zput(machine->vmlinux_map);
 }
 
 int machines__create_guest_kernel_maps(struct machines *machines)
@@ -989,32 +1092,31 @@ int machines__create_kernel_maps(struct machines *machines, pid_t pid)
 	return machine__create_kernel_maps(machine);
 }
 
-int machine__load_kallsyms(struct machine *machine, const char *filename,
-			     enum map_type type)
+int machine__load_kallsyms(struct machine *machine, const char *filename)
 {
 	struct map *map = machine__kernel_map(machine);
 	int ret = __dso__load_kallsyms(map->dso, filename, map, true);
 
 	if (ret > 0) {
-		dso__set_loaded(map->dso, type);
+		dso__set_loaded(map->dso);
 		/*
 		 * Since /proc/kallsyms will have multiple sessions for the
 		 * kernel, with modules between them, fixup the end of all
 		 * sections.
 		 */
-		__map_groups__fixup_end(&machine->kmaps, type);
+		map_groups__fixup_end(&machine->kmaps);
 	}
 
 	return ret;
 }
 
-int machine__load_vmlinux_path(struct machine *machine, enum map_type type)
+int machine__load_vmlinux_path(struct machine *machine)
 {
 	struct map *map = machine__kernel_map(machine);
 	int ret = dso__load_vmlinux_path(map->dso, map);
 
 	if (ret > 0)
-		dso__set_loaded(map->dso, type);
+		dso__set_loaded(map->dso);
 
 	return ret;
 }
@@ -1055,10 +1157,9 @@ static bool is_kmod_dso(struct dso *dso)
 static int map_groups__set_module_path(struct map_groups *mg, const char *path,
 				       struct kmod_path *m)
 {
-	struct map *map;
 	char *long_name;
+	struct map *map = map_groups__find_by_name(mg, m->name);
 
-	map = map_groups__find_by_name(mg, MAP__FUNCTION, m->name);
 	if (map == NULL)
 		return 0;
 
@@ -1207,19 +1308,14 @@ static int machine__create_modules(struct machine *machine)
 static void machine__set_kernel_mmap(struct machine *machine,
 				     u64 start, u64 end)
 {
-	int i;
-
-	for (i = 0; i < MAP__NR_TYPES; i++) {
-		machine->vmlinux_maps[i]->start = start;
-		machine->vmlinux_maps[i]->end   = end;
-
-		/*
-		 * Be a bit paranoid here, some perf.data file came with
-		 * a zero sized synthesized MMAP event for the kernel.
-		 */
-		if (start == 0 && end == 0)
-			machine->vmlinux_maps[i]->end = ~0ULL;
-	}
+	machine->vmlinux_map->start = start;
+	machine->vmlinux_map->end   = end;
+	/*
+	 * Be a bit paranoid here, some perf.data file came with
+	 * a zero sized synthesized MMAP event for the kernel.
+	 */
+	if (start == 0 && end == 0)
+		machine->vmlinux_map->end = ~0ULL;
 }
 
 int machine__create_kernel_maps(struct machine *machine)
@@ -1234,9 +1330,8 @@ int machine__create_kernel_maps(struct machine *machine)
 		return -1;
 
 	ret = __machine__create_kernel_maps(machine, kernel);
-	dso__put(kernel);
 	if (ret < 0)
-		return -1;
+		goto out_put;
 
 	if (symbol_conf.use_modules && machine__create_modules(machine) < 0) {
 		if (machine__is_host(machine))
@@ -1249,9 +1344,10 @@ int machine__create_kernel_maps(struct machine *machine)
 
 	if (!machine__get_running_kernel_start(machine, &name, &addr)) {
 		if (name &&
-		    maps__set_kallsyms_ref_reloc_sym(machine->vmlinux_maps, name, addr)) {
+		    map__set_kallsyms_ref_reloc_sym(machine->vmlinux_map, name, addr)) {
 			machine__destroy_kernel_maps(machine);
-			return -1;
+			ret = -1;
+			goto out_put;
 		}
 
 		/* we have a real start address now, so re-order the kmaps */
@@ -1267,12 +1363,16 @@ int machine__create_kernel_maps(struct machine *machine)
 		map__put(map);
 	}
 
+	if (machine__create_extra_kernel_maps(machine, kernel))
+		pr_debug("Problems creating extra kernel maps, continuing anyway...\n");
+
 	/* update end address of the kernel map using adjacent module address */
 	map = map__next(machine__kernel_map(machine));
 	if (map)
 		machine__set_kernel_mmap(machine, addr, map->start);
-
-	return 0;
+out_put:
+	dso__put(kernel);
+	return ret;
 }
 
 static bool machine__uses_kcore(struct machine *machine)
@@ -1287,6 +1387,32 @@ static bool machine__uses_kcore(struct machine *machine)
 	return false;
 }
 
+static bool perf_event__is_extra_kernel_mmap(struct machine *machine,
+					     union perf_event *event)
+{
+	return machine__is(machine, "x86_64") &&
+	       is_entry_trampoline(event->mmap.filename);
+}
+
+static int machine__process_extra_kernel_map(struct machine *machine,
+					     union perf_event *event)
+{
+	struct map *kernel_map = machine__kernel_map(machine);
+	struct dso *kernel = kernel_map ? kernel_map->dso : NULL;
+	struct extra_kernel_map xm = {
+		.start = event->mmap.start,
+		.end   = event->mmap.start + event->mmap.len,
+		.pgoff = event->mmap.pgoff,
+	};
+
+	if (kernel == NULL)
+		return -1;
+
+	strlcpy(xm.name, event->mmap.filename, KMAP_NAME_LEN);
+
+	return machine__create_extra_kernel_map(machine, kernel, &xm);
+}
+
 static int machine__process_kernel_mmap_event(struct machine *machine,
 					      union perf_event *event)
 {
@@ -1379,9 +1505,9 @@ static int machine__process_kernel_mmap_event(struct machine *machine,
 		 * time /proc/sys/kernel/kptr_restrict was non zero.
 		 */
 		if (event->mmap.pgoff != 0) {
-			maps__set_kallsyms_ref_reloc_sym(machine->vmlinux_maps,
-							 symbol_name,
-							 event->mmap.pgoff);
+			map__set_kallsyms_ref_reloc_sym(machine->vmlinux_map,
+							symbol_name,
+							event->mmap.pgoff);
 		}
 
 		if (machine__is_default_guest(machine)) {
@@ -1390,6 +1516,8 @@ static int machine__process_kernel_mmap_event(struct machine *machine,
 			 */
 			dso__load(kernel, machine__kernel_map(machine));
 		}
+	} else if (perf_event__is_extra_kernel_mmap(machine, event)) {
+		return machine__process_extra_kernel_map(machine, event);
 	}
 	return 0;
 out_problem:
@@ -1402,7 +1530,6 @@ int machine__process_mmap2_event(struct machine *machine,
 {
 	struct thread *thread;
 	struct map *map;
-	enum map_type type;
 	int ret = 0;
 
 	if (dump_trace)
@@ -1421,11 +1548,6 @@ int machine__process_mmap2_event(struct machine *machine,
 	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, event->mmap2.start,
 			event->mmap2.len, event->mmap2.pgoff,
 			event->mmap2.maj,
@@ -1433,7 +1555,7 @@ int machine__process_mmap2_event(struct machine *machine,
 			event->mmap2.ino_generation,
 			event->mmap2.prot,
 			event->mmap2.flags,
-			event->mmap2.filename, type, thread);
+			event->mmap2.filename, thread);
 
 	if (map == NULL)
 		goto out_problem_map;
@@ -1460,7 +1582,7 @@ int machine__process_mmap_event(struct machine *machine, union perf_event *event
 {
 	struct thread *thread;
 	struct map *map;
-	enum map_type type;
+	u32 prot = 0;
 	int ret = 0;
 
 	if (dump_trace)
@@ -1479,16 +1601,14 @@ int machine__process_mmap_event(struct machine *machine, union perf_event *event
 	if (thread == NULL)
 		goto out_problem;
 
-	if (event->header.misc & PERF_RECORD_MISC_MMAP_DATA)
-		type = MAP__VARIABLE;
-	else
-		type = MAP__FUNCTION;
+	if (!(event->header.misc & PERF_RECORD_MISC_MMAP_DATA))
+		prot = PROT_EXEC;
 
 	map = map__new(machine, event->mmap.start,
 			event->mmap.len, event->mmap.pgoff,
-			0, 0, 0, 0, 0, 0,
+			0, 0, 0, 0, prot, 0,
 			event->mmap.filename,
-			type, thread);
+			thread);
 
 	if (map == NULL)
 		goto out_problem_map;
@@ -1664,7 +1784,7 @@ static void ip__resolve_ams(struct thread *thread,
 	 * Thus, we have to try consecutively until we find a match
 	 * or else, the symbol is unknown
 	 */
-	thread__find_cpumode_addr_location(thread, MAP__FUNCTION, ip, &al);
+	thread__find_cpumode_addr_location(thread, ip, &al);
 
 	ams->addr = ip;
 	ams->al_addr = al.addr;
@@ -1681,15 +1801,7 @@ static void ip__resolve_data(struct thread *thread,
 
 	memset(&al, 0, sizeof(al));
 
-	thread__find_addr_location(thread, m, MAP__VARIABLE, addr, &al);
-	if (al.map == NULL) {
-		/*
-		 * some shared data regions have execute bit set which puts
-		 * their mapping in the MAP__FUNCTION type array.
-		 * Check there as a fallback option before dropping the sample.
-		 */
-		thread__find_addr_location(thread, m, MAP__FUNCTION, addr, &al);
-	}
+	thread__find_symbol(thread, m, addr, &al);
 
 	ams->addr = addr;
 	ams->al_addr = al.addr;
@@ -1758,8 +1870,7 @@ static int add_callchain_ip(struct thread *thread,
 	al.filtered = 0;
 	al.sym = NULL;
 	if (!cpumode) {
-		thread__find_cpumode_addr_location(thread, MAP__FUNCTION,
-						   ip, &al);
+		thread__find_cpumode_addr_location(thread, ip, &al);
 	} else {
 		if (ip >= PERF_CONTEXT_MAX) {
 			switch (ip) {
@@ -1784,8 +1895,7 @@ static int add_callchain_ip(struct thread *thread,
 			}
 			return 0;
 		}
-		thread__find_addr_location(thread, *cpumode, MAP__FUNCTION,
-					   ip, &al);
+		thread__find_symbol(thread, *cpumode, ip, &al);
 	}
 
 	if (al.sym != NULL) {
@@ -1810,7 +1920,7 @@ static int add_callchain_ip(struct thread *thread,
 	}
 
 	srcline = callchain_srcline(al.map, al.sym, al.addr);
-	return callchain_cursor_append(cursor, al.addr, al.map, al.sym,
+	return callchain_cursor_append(cursor, ip, al.map, al.sym,
 				       branch, flags, nr_loop_iter,
 				       iter_cycles, branch_from, srcline);
 }
@@ -2342,6 +2452,20 @@ int machine__set_current_tid(struct machine *machine, int cpu, pid_t pid,
 	return 0;
 }
 
+/*
+ * Compares the raw arch string. N.B. see instead perf_env__arch() if a
+ * normalized arch is needed.
+ */
+bool machine__is(struct machine *machine, const char *arch)
+{
+	return machine && !strcmp(perf_env__raw_arch(machine->env), arch);
+}
+
+int machine__nr_cpus_avail(struct machine *machine)
+{
+	return machine ? perf_env__nr_cpus_avail(machine->env) : 0;
+}
+
 int machine__get_kernel_start(struct machine *machine)
 {
 	struct map *map = machine__kernel_map(machine);
@@ -2358,7 +2482,12 @@ int machine__get_kernel_start(struct machine *machine)
 	machine->kernel_start = 1ULL << 63;
 	if (map) {
 		err = map__load(map);
-		if (!err)
+		/*
+		 * On x86_64, PTI entry trampolines are less than the
+		 * start of kernel text, but still above 2^63. So leave
+		 * kernel_start = 1ULL << 63 for x86_64.
+		 */
+		if (!err && !machine__is(machine, "x86_64"))
 			machine->kernel_start = map->start;
 	}
 	return err;
@@ -2373,7 +2502,7 @@ char *machine__resolve_kernel_addr(void *vmachine, unsigned long long *addrp, ch
 {
 	struct machine *machine = vmachine;
 	struct map *map;
-	struct symbol *sym = map_groups__find_symbol(&machine->kmaps, MAP__FUNCTION, *addrp, &map);
+	struct symbol *sym = machine__find_kernel_symbol(machine, *addrp, &map);
 
 	if (sym == NULL)
 		return NULL;
diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h
index 66cc200ef86f..1de7660d93e9 100644
--- a/tools/perf/util/machine.h
+++ b/tools/perf/util/machine.h
@@ -49,13 +49,14 @@ struct machine {
 	struct perf_env   *env;
 	struct dsos	  dsos;
 	struct map_groups kmaps;
-	struct map	  *vmlinux_maps[MAP__NR_TYPES];
+	struct map	  *vmlinux_map;
 	u64		  kernel_start;
 	pid_t		  *current_tid;
 	union { /* Tool specific area */
 		void	  *priv;
 		u64	  db_id;
 	};
+	bool		  trampolines_mapped;
 };
 
 static inline struct threads *machine__threads(struct machine *machine, pid_t tid)
@@ -64,16 +65,22 @@ static inline struct threads *machine__threads(struct machine *machine, pid_t ti
 	return &machine->threads[(unsigned int)tid % THREADS__TABLE_SIZE];
 }
 
-static inline
-struct map *__machine__kernel_map(struct machine *machine, enum map_type type)
-{
-	return machine->vmlinux_maps[type];
-}
-
+/*
+ * The main kernel (vmlinux) map
+ */
 static inline
 struct map *machine__kernel_map(struct machine *machine)
 {
-	return __machine__kernel_map(machine, MAP__FUNCTION);
+	return machine->vmlinux_map;
+}
+
+/*
+ * kernel (the one returned by machine__kernel_map()) plus kernel modules maps
+ */
+static inline
+struct maps *machine__kernel_maps(struct machine *machine)
+{
+	return &machine->kmaps.maps;
 }
 
 int machine__get_kernel_start(struct machine *machine);
@@ -182,6 +189,9 @@ static inline bool machine__is_host(struct machine *machine)
 	return machine ? machine->pid == HOST_KERNEL_ID : false;
 }
 
+bool machine__is(struct machine *machine, const char *arch);
+int machine__nr_cpus_avail(struct machine *machine);
+
 struct thread *__machine__findnew_thread(struct machine *machine, pid_t pid, pid_t tid);
 struct thread *machine__findnew_thread(struct machine *machine, pid_t pid, pid_t tid);
 
@@ -190,44 +200,27 @@ struct dso *machine__findnew_dso(struct machine *machine, const char *filename);
 size_t machine__fprintf(struct machine *machine, FILE *fp);
 
 static inline
-struct symbol *machine__find_kernel_symbol(struct machine *machine,
-					   enum map_type type, u64 addr,
+struct symbol *machine__find_kernel_symbol(struct machine *machine, u64 addr,
 					   struct map **mapp)
 {
-	return map_groups__find_symbol(&machine->kmaps, type, addr, mapp);
+	return map_groups__find_symbol(&machine->kmaps, addr, mapp);
 }
 
 static inline
 struct symbol *machine__find_kernel_symbol_by_name(struct machine *machine,
-						   enum map_type type, const char *name,
+						   const char *name,
 						   struct map **mapp)
 {
-	return map_groups__find_symbol_by_name(&machine->kmaps, type, name, mapp);
-}
-
-static inline
-struct symbol *machine__find_kernel_function(struct machine *machine, u64 addr,
-					     struct map **mapp)
-{
-	return machine__find_kernel_symbol(machine, MAP__FUNCTION, addr,
-					   mapp);
-}
-
-static inline
-struct symbol *machine__find_kernel_function_by_name(struct machine *machine,
-						     const char *name,
-						     struct map **mapp)
-{
-	return map_groups__find_function_by_name(&machine->kmaps, name, mapp);
+	return map_groups__find_symbol_by_name(&machine->kmaps, name, mapp);
 }
 
 struct map *machine__findnew_module_map(struct machine *machine, u64 start,
 					const char *filename);
 int arch__fix_module_text_start(u64 *start, const char *name);
 
-int machine__load_kallsyms(struct machine *machine, const char *filename,
-			   enum map_type type);
-int machine__load_vmlinux_path(struct machine *machine, enum map_type type);
+int machine__load_kallsyms(struct machine *machine, const char *filename);
+
+int machine__load_vmlinux_path(struct machine *machine);
 
 size_t machine__fprintf_dsos_buildid(struct machine *machine, FILE *fp,
 				     bool (skip)(struct dso *dso, int parm), int parm);
@@ -276,4 +269,25 @@ int machine__set_current_tid(struct machine *machine, int cpu, pid_t pid,
  */
 char *machine__resolve_kernel_addr(void *vmachine, unsigned long long *addrp, char **modp);
 
+void machine__get_kallsyms_filename(struct machine *machine, char *buf,
+				    size_t bufsz);
+
+int machine__create_extra_kernel_maps(struct machine *machine,
+				      struct dso *kernel);
+
+/* Kernel-space maps for symbols that are outside the main kernel map and module maps */
+struct extra_kernel_map {
+	u64 start;
+	u64 end;
+	u64 pgoff;
+	char name[KMAP_NAME_LEN];
+};
+
+int machine__create_extra_kernel_map(struct machine *machine,
+				     struct dso *kernel,
+				     struct extra_kernel_map *xm);
+
+int machine__map_x86_64_entry_trampolines(struct machine *machine,
+					  struct dso *kernel);
+
 #endif /* __PERF_MACHINE_H */
diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c
index 8fe57031e1a8..6ae97eda370b 100644
--- a/tools/perf/util/map.c
+++ b/tools/perf/util/map.c
@@ -22,11 +22,6 @@
 
 static void __maps__insert(struct maps *maps, struct map *map);
 
-const char *map_type__name[MAP__NR_TYPES] = {
-	[MAP__FUNCTION] = "Functions",
-	[MAP__VARIABLE] = "Variables",
-};
-
 static inline int is_anon_memory(const char *filename, u32 flags)
 {
 	return flags & MAP_HUGETLB ||
@@ -129,10 +124,8 @@ static inline bool replace_android_lib(const char *filename, char *newfilename)
 	return false;
 }
 
-void map__init(struct map *map, enum map_type type,
-	       u64 start, u64 end, u64 pgoff, struct dso *dso)
+void map__init(struct map *map, u64 start, u64 end, u64 pgoff, struct dso *dso)
 {
-	map->type     = type;
 	map->start    = start;
 	map->end      = end;
 	map->pgoff    = pgoff;
@@ -149,7 +142,7 @@ void map__init(struct map *map, enum map_type type,
 struct map *map__new(struct machine *machine, u64 start, u64 len,
 		     u64 pgoff, u32 d_maj, u32 d_min, u64 ino,
 		     u64 ino_gen, u32 prot, u32 flags, char *filename,
-		     enum map_type type, struct thread *thread)
+		     struct thread *thread)
 {
 	struct map *map = malloc(sizeof(*map));
 	struct nsinfo *nsi = NULL;
@@ -173,7 +166,7 @@ struct map *map__new(struct machine *machine, u64 start, u64 len,
 		map->flags = flags;
 		nsi = nsinfo__get(thread->nsinfo);
 
-		if ((anon || no_dso) && nsi && type == MAP__FUNCTION) {
+		if ((anon || no_dso) && nsi && (prot & PROT_EXEC)) {
 			snprintf(newfilename, sizeof(newfilename),
 				 "/tmp/perf-%d.map", nsi->pid);
 			filename = newfilename;
@@ -203,7 +196,7 @@ struct map *map__new(struct machine *machine, u64 start, u64 len,
 		if (dso == NULL)
 			goto out_delete;
 
-		map__init(map, type, start, start + len, pgoff, dso);
+		map__init(map, start, start + len, pgoff, dso);
 
 		if (anon || no_dso) {
 			map->map_ip = map->unmap_ip = identity__map_ip;
@@ -213,8 +206,8 @@ struct map *map__new(struct machine *machine, u64 start, u64 len,
 			 * functions still return NULL, and we avoid the
 			 * unnecessary map__load warning.
 			 */
-			if (type != MAP__FUNCTION)
-				dso__set_loaded(dso, map->type);
+			if (!(prot & PROT_EXEC))
+				dso__set_loaded(dso);
 		}
 		dso->nsinfo = nsi;
 		dso__put(dso);
@@ -231,7 +224,7 @@ out_delete:
  * they are loaded) and for vmlinux, where only after we load all the
  * symbols we'll know where it starts and ends.
  */
-struct map *map__new2(u64 start, struct dso *dso, enum map_type type)
+struct map *map__new2(u64 start, struct dso *dso)
 {
 	struct map *map = calloc(1, (sizeof(*map) +
 				     (dso->kernel ? sizeof(struct kmap) : 0)));
@@ -239,7 +232,7 @@ struct map *map__new2(u64 start, struct dso *dso, enum map_type type)
 		/*
 		 * ->end will be filled after we load all the symbols
 		 */
-		map__init(map, type, start, 0, 0, dso);
+		map__init(map, start, 0, 0, dso);
 	}
 
 	return map;
@@ -256,7 +249,19 @@ struct map *map__new2(u64 start, struct dso *dso, enum map_type type)
  */
 bool __map__is_kernel(const struct map *map)
 {
-	return __machine__kernel_map(map->groups->machine, map->type) == map;
+	return machine__kernel_map(map->groups->machine) == map;
+}
+
+bool __map__is_extra_kernel_map(const struct map *map)
+{
+	struct kmap *kmap = __map__kmap((struct map *)map);
+
+	return kmap && kmap->name[0];
+}
+
+bool map__has_symbols(const struct map *map)
+{
+	return dso__has_symbols(map->dso);
 }
 
 static void map__exit(struct map *map)
@@ -279,7 +284,7 @@ void map__put(struct map *map)
 
 void map__fixup_start(struct map *map)
 {
-	struct rb_root *symbols = &map->dso->symbols[map->type];
+	struct rb_root *symbols = &map->dso->symbols;
 	struct rb_node *nd = rb_first(symbols);
 	if (nd != NULL) {
 		struct symbol *sym = rb_entry(nd, struct symbol, rb_node);
@@ -289,7 +294,7 @@ void map__fixup_start(struct map *map)
 
 void map__fixup_end(struct map *map)
 {
-	struct rb_root *symbols = &map->dso->symbols[map->type];
+	struct rb_root *symbols = &map->dso->symbols;
 	struct rb_node *nd = rb_last(symbols);
 	if (nd != NULL) {
 		struct symbol *sym = rb_entry(nd, struct symbol, rb_node);
@@ -304,7 +309,7 @@ int map__load(struct map *map)
 	const char *name = map->dso->long_name;
 	int nr;
 
-	if (dso__loaded(map->dso, map->type))
+	if (dso__loaded(map->dso))
 		return 0;
 
 	nr = dso__load(map->dso, map);
@@ -348,7 +353,7 @@ struct symbol *map__find_symbol(struct map *map, u64 addr)
 	if (map__load(map) < 0)
 		return NULL;
 
-	return dso__find_symbol(map->dso, map->type, addr);
+	return dso__find_symbol(map->dso, addr);
 }
 
 struct symbol *map__find_symbol_by_name(struct map *map, const char *name)
@@ -356,10 +361,10 @@ struct symbol *map__find_symbol_by_name(struct map *map, const char *name)
 	if (map__load(map) < 0)
 		return NULL;
 
-	if (!dso__sorted_by_name(map->dso, map->type))
-		dso__sort_by_name(map->dso, map->type);
+	if (!dso__sorted_by_name(map->dso))
+		dso__sort_by_name(map->dso);
 
-	return dso__find_symbol_by_name(map->dso, map->type, name);
+	return dso__find_symbol_by_name(map->dso, name);
 }
 
 struct map *map__clone(struct map *from)
@@ -494,10 +499,7 @@ static void maps__init(struct maps *maps)
 
 void map_groups__init(struct map_groups *mg, struct machine *machine)
 {
-	int i;
-	for (i = 0; i < MAP__NR_TYPES; ++i) {
-		maps__init(&mg->maps[i]);
-	}
+	maps__init(&mg->maps);
 	mg->machine = machine;
 	refcount_set(&mg->refcnt, 1);
 }
@@ -525,22 +527,12 @@ static void maps__exit(struct maps *maps)
 
 void map_groups__exit(struct map_groups *mg)
 {
-	int i;
-
-	for (i = 0; i < MAP__NR_TYPES; ++i)
-		maps__exit(&mg->maps[i]);
+	maps__exit(&mg->maps);
 }
 
 bool map_groups__empty(struct map_groups *mg)
 {
-	int i;
-
-	for (i = 0; i < MAP__NR_TYPES; ++i) {
-		if (maps__first(&mg->maps[i]))
-			return false;
-	}
-
-	return true;
+	return !maps__first(&mg->maps);
 }
 
 struct map_groups *map_groups__new(struct machine *machine)
@@ -566,10 +558,9 @@ void map_groups__put(struct map_groups *mg)
 }
 
 struct symbol *map_groups__find_symbol(struct map_groups *mg,
-				       enum map_type type, u64 addr,
-				       struct map **mapp)
+				       u64 addr, struct map **mapp)
 {
-	struct map *map = map_groups__find(mg, type, addr);
+	struct map *map = map_groups__find(mg, addr);
 
 	/* Ensure map is loaded before using map->map_ip */
 	if (map != NULL && map__load(map) >= 0) {
@@ -608,13 +599,10 @@ out:
 }
 
 struct symbol *map_groups__find_symbol_by_name(struct map_groups *mg,
-					       enum map_type type,
 					       const char *name,
 					       struct map **mapp)
 {
-	struct symbol *sym = maps__find_symbol_by_name(&mg->maps[type], name, mapp);
-
-	return sym;
+	return maps__find_symbol_by_name(&mg->maps, name, mapp);
 }
 
 int map_groups__find_ams(struct addr_map_symbol *ams)
@@ -622,8 +610,7 @@ int map_groups__find_ams(struct addr_map_symbol *ams)
 	if (ams->addr < ams->map->start || ams->addr >= ams->map->end) {
 		if (ams->map->groups == NULL)
 			return -1;
-		ams->map = map_groups__find(ams->map->groups, ams->map->type,
-					    ams->addr);
+		ams->map = map_groups__find(ams->map->groups, ams->addr);
 		if (ams->map == NULL)
 			return -1;
 	}
@@ -646,7 +633,7 @@ static size_t maps__fprintf(struct maps *maps, FILE *fp)
 		printed += fprintf(fp, "Map:");
 		printed += map__fprintf(pos, fp);
 		if (verbose > 2) {
-			printed += dso__fprintf(pos->dso, pos->type, fp);
+			printed += dso__fprintf(pos->dso, fp);
 			printed += fprintf(fp, "--\n");
 		}
 	}
@@ -656,24 +643,14 @@ static size_t maps__fprintf(struct maps *maps, FILE *fp)
 	return printed;
 }
 
-size_t __map_groups__fprintf_maps(struct map_groups *mg, enum map_type type,
-				  FILE *fp)
-{
-	size_t printed = fprintf(fp, "%s:\n", map_type__name[type]);
-	return printed += maps__fprintf(&mg->maps[type], fp);
-}
-
 size_t map_groups__fprintf(struct map_groups *mg, FILE *fp)
 {
-	size_t printed = 0, i;
-	for (i = 0; i < MAP__NR_TYPES; ++i)
-		printed += __map_groups__fprintf_maps(mg, i, fp);
-	return printed;
+	return maps__fprintf(&mg->maps, fp);
 }
 
 static void __map_groups__insert(struct map_groups *mg, struct map *map)
 {
-	__maps__insert(&mg->maps[map->type], map);
+	__maps__insert(&mg->maps, map);
 	map->groups = mg;
 }
 
@@ -758,19 +735,18 @@ out:
 int map_groups__fixup_overlappings(struct map_groups *mg, struct map *map,
 				   FILE *fp)
 {
-	return maps__fixup_overlappings(&mg->maps[map->type], map, fp);
+	return maps__fixup_overlappings(&mg->maps, map, fp);
 }
 
 /*
  * XXX This should not really _copy_ te maps, but refcount them.
  */
-int map_groups__clone(struct thread *thread,
-		      struct map_groups *parent, enum map_type type)
+int map_groups__clone(struct thread *thread, struct map_groups *parent)
 {
 	struct map_groups *mg = thread->mg;
 	int err = -ENOMEM;
 	struct map *map;
-	struct maps *maps = &parent->maps[type];
+	struct maps *maps = &parent->maps;
 
 	down_read(&maps->lock);
 
@@ -877,13 +853,20 @@ struct map *map__next(struct map *map)
 	return NULL;
 }
 
+struct kmap *__map__kmap(struct map *map)
+{
+	if (!map->dso || !map->dso->kernel)
+		return NULL;
+	return (struct kmap *)(map + 1);
+}
+
 struct kmap *map__kmap(struct map *map)
 {
-	if (!map->dso || !map->dso->kernel) {
+	struct kmap *kmap = __map__kmap(map);
+
+	if (!kmap)
 		pr_err("Internal error: map__kmap with a non-kernel map\n");
-		return NULL;
-	}
-	return (struct kmap *)(map + 1);
+	return kmap;
 }
 
 struct map_groups *map__kmaps(struct map *map)
diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h
index 0e9bbe01b0ab..97e2a063bd65 100644
--- a/tools/perf/util/map.h
+++ b/tools/perf/util/map.h
@@ -8,19 +8,11 @@
 #include <linux/rbtree.h>
 #include <pthread.h>
 #include <stdio.h>
+#include <string.h>
 #include <stdbool.h>
 #include <linux/types.h>
 #include "rwsem.h"
 
-enum map_type {
-	MAP__FUNCTION = 0,
-	MAP__VARIABLE,
-};
-
-#define MAP__NR_TYPES (MAP__VARIABLE + 1)
-
-extern const char *map_type__name[MAP__NR_TYPES];
-
 struct dso;
 struct ip_callchain;
 struct ref_reloc_sym;
@@ -35,7 +27,6 @@ struct map {
 	};
 	u64			start;
 	u64			end;
-	u8 /* enum map_type */	type;
 	bool			erange_warned;
 	u32			priv;
 	u32			prot;
@@ -56,9 +47,12 @@ struct map {
 	refcount_t		refcnt;
 };
 
+#define KMAP_NAME_LEN 256
+
 struct kmap {
 	struct ref_reloc_sym	*ref_reloc_sym;
 	struct map_groups	*kmaps;
+	char			name[KMAP_NAME_LEN];
 };
 
 struct maps {
@@ -67,7 +61,7 @@ struct maps {
 };
 
 struct map_groups {
-	struct maps	 maps[MAP__NR_TYPES];
+	struct maps	 maps;
 	struct machine	 *machine;
 	refcount_t	 refcnt;
 };
@@ -85,6 +79,7 @@ static inline struct map_groups *map_groups__get(struct map_groups *mg)
 
 void map_groups__put(struct map_groups *mg);
 
+struct kmap *__map__kmap(struct map *map);
 struct kmap *map__kmap(struct map *map);
 struct map_groups *map__kmaps(struct map *map);
 
@@ -125,7 +120,7 @@ struct thread;
  * Note: caller must ensure map->dso is not NULL (map is loaded).
  */
 #define map__for_each_symbol(map, pos, n)	\
-	dso__for_each_symbol(map->dso, pos, n, map->type)
+	dso__for_each_symbol(map->dso, pos, n)
 
 /* map__for_each_symbol_with_name - iterate over the symbols in the given map
  *                                  that have the given name
@@ -144,13 +139,13 @@ struct thread;
 #define map__for_each_symbol_by_name(map, sym_name, pos)		\
 	__map__for_each_symbol_by_name(map, sym_name, (pos))
 
-void map__init(struct map *map, enum map_type type,
+void map__init(struct map *map,
 	       u64 start, u64 end, u64 pgoff, struct dso *dso);
 struct map *map__new(struct machine *machine, u64 start, u64 len,
 		     u64 pgoff, u32 d_maj, u32 d_min, u64 ino,
 		     u64 ino_gen, u32 prot, u32 flags,
-		     char *filename, enum map_type type, struct thread *thread);
-struct map *map__new2(u64 start, struct dso *dso, enum map_type type);
+		     char *filename, struct thread *thread);
+struct map *map__new2(u64 start, struct dso *dso);
 void map__delete(struct map *map);
 struct map *map__clone(struct map *map);
 
@@ -185,8 +180,6 @@ void map__fixup_end(struct map *map);
 
 void map__reloc_vmlinux(struct map *map);
 
-size_t __map_groups__fprintf_maps(struct map_groups *mg, enum map_type type,
-				  FILE *fp);
 void maps__insert(struct maps *maps, struct map *map);
 void maps__remove(struct maps *maps, struct map *map);
 struct map *maps__find(struct maps *maps, u64 addr);
@@ -197,34 +190,29 @@ struct symbol *maps__find_symbol_by_name(struct maps *maps, const char *name,
 void map_groups__init(struct map_groups *mg, struct machine *machine);
 void map_groups__exit(struct map_groups *mg);
 int map_groups__clone(struct thread *thread,
-		      struct map_groups *parent, enum map_type type);
+		      struct map_groups *parent);
 size_t map_groups__fprintf(struct map_groups *mg, FILE *fp);
 
-int maps__set_kallsyms_ref_reloc_sym(struct map **maps, const char *symbol_name,
-				     u64 addr);
+int map__set_kallsyms_ref_reloc_sym(struct map *map, const char *symbol_name,
+				    u64 addr);
 
 static inline void map_groups__insert(struct map_groups *mg, struct map *map)
 {
-	maps__insert(&mg->maps[map->type], map);
+	maps__insert(&mg->maps, map);
 	map->groups = mg;
 }
 
 static inline void map_groups__remove(struct map_groups *mg, struct map *map)
 {
-	maps__remove(&mg->maps[map->type], map);
+	maps__remove(&mg->maps, map);
 }
 
-static inline struct map *map_groups__find(struct map_groups *mg,
-					   enum map_type type, u64 addr)
+static inline struct map *map_groups__find(struct map_groups *mg, u64 addr)
 {
-	return maps__find(&mg->maps[type], addr);
+	return maps__find(&mg->maps, addr);
 }
 
-static inline struct map *map_groups__first(struct map_groups *mg,
-					    enum map_type type)
-{
-	return maps__first(&mg->maps[type]);
-}
+struct map *map_groups__first(struct map_groups *mg);
 
 static inline struct map *map_groups__next(struct map *map)
 {
@@ -232,11 +220,9 @@ static inline struct map *map_groups__next(struct map *map)
 }
 
 struct symbol *map_groups__find_symbol(struct map_groups *mg,
-				       enum map_type type, u64 addr,
-				       struct map **mapp);
+				       u64 addr, struct map **mapp);
 
 struct symbol *map_groups__find_symbol_by_name(struct map_groups *mg,
-					       enum map_type type,
 					       const char *name,
 					       struct map **mapp);
 
@@ -244,24 +230,26 @@ struct addr_map_symbol;
 
 int map_groups__find_ams(struct addr_map_symbol *ams);
 
-static inline
-struct symbol *map_groups__find_function_by_name(struct map_groups *mg,
-						 const char *name, struct map **mapp)
-{
-	return map_groups__find_symbol_by_name(mg, MAP__FUNCTION, name, mapp);
-}
-
 int map_groups__fixup_overlappings(struct map_groups *mg, struct map *map,
 				   FILE *fp);
 
-struct map *map_groups__find_by_name(struct map_groups *mg,
-				     enum map_type type, const char *name);
+struct map *map_groups__find_by_name(struct map_groups *mg, const char *name);
 
 bool __map__is_kernel(const struct map *map);
+bool __map__is_extra_kernel_map(const struct map *map);
 
 static inline bool __map__is_kmodule(const struct map *map)
 {
-	return !__map__is_kernel(map);
+	return !__map__is_kernel(map) && !__map__is_extra_kernel_map(map);
+}
+
+bool map__has_symbols(const struct map *map);
+
+#define ENTRY_TRAMPOLINE_NAME "__entry_SYSCALL_64_trampoline"
+
+static inline bool is_entry_trampoline(const char *name)
+{
+	return !strcmp(name, ENTRY_TRAMPOLINE_NAME);
 }
 
 #endif /* __PERF_MAP_H */
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 2fc4ee8b86c1..15eec49e71a1 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -156,13 +156,12 @@ struct event_symbol event_symbols_sw[PERF_COUNT_SW_MAX] = {
 		    (strcmp(sys_dirent->d_name, ".")) &&	\
 		    (strcmp(sys_dirent->d_name, "..")))
 
-static int tp_event_has_id(struct dirent *sys_dir, struct dirent *evt_dir)
+static int tp_event_has_id(const char *dir_path, struct dirent *evt_dir)
 {
 	char evt_path[MAXPATHLEN];
 	int fd;
 
-	snprintf(evt_path, MAXPATHLEN, "%s/%s/%s/id", tracing_events_path,
-			sys_dir->d_name, evt_dir->d_name);
+	snprintf(evt_path, MAXPATHLEN, "%s/%s/id", dir_path, evt_dir->d_name);
 	fd = open(evt_path, O_RDONLY);
 	if (fd < 0)
 		return -EINVAL;
@@ -171,12 +170,12 @@ static int tp_event_has_id(struct dirent *sys_dir, struct dirent *evt_dir)
 	return 0;
 }
 
-#define for_each_event(sys_dirent, evt_dir, evt_dirent)		\
+#define for_each_event(dir_path, evt_dir, evt_dirent)		\
 	while ((evt_dirent = readdir(evt_dir)) != NULL)		\
 		if (evt_dirent->d_type == DT_DIR &&		\
 		    (strcmp(evt_dirent->d_name, ".")) &&	\
 		    (strcmp(evt_dirent->d_name, "..")) &&	\
-		    (!tp_event_has_id(sys_dirent, evt_dirent)))
+		    (!tp_event_has_id(dir_path, evt_dirent)))
 
 #define MAX_EVENT_LENGTH 512
 
@@ -190,21 +189,21 @@ struct tracepoint_path *tracepoint_id_to_path(u64 config)
 	int fd;
 	u64 id;
 	char evt_path[MAXPATHLEN];
-	char dir_path[MAXPATHLEN];
+	char *dir_path;
 
-	sys_dir = opendir(tracing_events_path);
+	sys_dir = tracing_events__opendir();
 	if (!sys_dir)
 		return NULL;
 
 	for_each_subsystem(sys_dir, sys_dirent) {
-
-		snprintf(dir_path, MAXPATHLEN, "%s/%s", tracing_events_path,
-			 sys_dirent->d_name);
+		dir_path = get_events_file(sys_dirent->d_name);
+		if (!dir_path)
+			continue;
 		evt_dir = opendir(dir_path);
 		if (!evt_dir)
-			continue;
+			goto next;
 
-		for_each_event(sys_dirent, evt_dir, evt_dirent) {
+		for_each_event(dir_path, evt_dir, evt_dirent) {
 
 			scnprintf(evt_path, MAXPATHLEN, "%s/%s/id", dir_path,
 				  evt_dirent->d_name);
@@ -218,6 +217,7 @@ struct tracepoint_path *tracepoint_id_to_path(u64 config)
 			close(fd);
 			id = atoll(id_buf);
 			if (id == config) {
+				put_events_file(dir_path);
 				closedir(evt_dir);
 				closedir(sys_dir);
 				path = zalloc(sizeof(*path));
@@ -242,6 +242,8 @@ struct tracepoint_path *tracepoint_id_to_path(u64 config)
 			}
 		}
 		closedir(evt_dir);
+next:
+		put_events_file(dir_path);
 	}
 
 	closedir(sys_dir);
@@ -512,14 +514,19 @@ static int add_tracepoint_multi_event(struct list_head *list, int *idx,
 				      struct parse_events_error *err,
 				      struct list_head *head_config)
 {
-	char evt_path[MAXPATHLEN];
+	char *evt_path;
 	struct dirent *evt_ent;
 	DIR *evt_dir;
 	int ret = 0, found = 0;
 
-	snprintf(evt_path, MAXPATHLEN, "%s/%s", tracing_events_path, sys_name);
+	evt_path = get_events_file(sys_name);
+	if (!evt_path) {
+		tracepoint_error(err, errno, sys_name, evt_name);
+		return -1;
+	}
 	evt_dir = opendir(evt_path);
 	if (!evt_dir) {
+		put_events_file(evt_path);
 		tracepoint_error(err, errno, sys_name, evt_name);
 		return -1;
 	}
@@ -545,6 +552,7 @@ static int add_tracepoint_multi_event(struct list_head *list, int *idx,
 		ret = -1;
 	}
 
+	put_events_file(evt_path);
 	closedir(evt_dir);
 	return ret;
 }
@@ -570,7 +578,7 @@ static int add_tracepoint_multi_sys(struct list_head *list, int *idx,
 	DIR *events_dir;
 	int ret = 0;
 
-	events_dir = opendir(tracing_events_path);
+	events_dir = tracing_events__opendir();
 	if (!events_dir) {
 		tracepoint_error(err, errno, sys_name, evt_name);
 		return -1;
@@ -2092,13 +2100,13 @@ void print_tracepoint_events(const char *subsys_glob, const char *event_glob,
 	DIR *sys_dir, *evt_dir;
 	struct dirent *sys_dirent, *evt_dirent;
 	char evt_path[MAXPATHLEN];
-	char dir_path[MAXPATHLEN];
+	char *dir_path;
 	char **evt_list = NULL;
 	unsigned int evt_i = 0, evt_num = 0;
 	bool evt_num_known = false;
 
 restart:
-	sys_dir = opendir(tracing_events_path);
+	sys_dir = tracing_events__opendir();
 	if (!sys_dir)
 		return;
 
@@ -2113,13 +2121,14 @@ restart:
 		    !strglobmatch(sys_dirent->d_name, subsys_glob))
 			continue;
 
-		snprintf(dir_path, MAXPATHLEN, "%s/%s", tracing_events_path,
-			 sys_dirent->d_name);
+		dir_path = get_events_file(sys_dirent->d_name);
+		if (!dir_path)
+			continue;
 		evt_dir = opendir(dir_path);
 		if (!evt_dir)
-			continue;
+			goto next;
 
-		for_each_event(sys_dirent, evt_dir, evt_dirent) {
+		for_each_event(dir_path, evt_dir, evt_dirent) {
 			if (event_glob != NULL &&
 			    !strglobmatch(evt_dirent->d_name, event_glob))
 				continue;
@@ -2133,11 +2142,15 @@ restart:
 				 sys_dirent->d_name, evt_dirent->d_name);
 
 			evt_list[evt_i] = strdup(evt_path);
-			if (evt_list[evt_i] == NULL)
+			if (evt_list[evt_i] == NULL) {
+				put_events_file(dir_path);
 				goto out_close_evt_dir;
+			}
 			evt_i++;
 		}
 		closedir(evt_dir);
+next:
+		put_events_file(dir_path);
 	}
 	closedir(sys_dir);
 
@@ -2185,21 +2198,21 @@ int is_valid_tracepoint(const char *event_string)
 	DIR *sys_dir, *evt_dir;
 	struct dirent *sys_dirent, *evt_dirent;
 	char evt_path[MAXPATHLEN];
-	char dir_path[MAXPATHLEN];
+	char *dir_path;
 
-	sys_dir = opendir(tracing_events_path);
+	sys_dir = tracing_events__opendir();
 	if (!sys_dir)
 		return 0;
 
 	for_each_subsystem(sys_dir, sys_dirent) {
-
-		snprintf(dir_path, MAXPATHLEN, "%s/%s", tracing_events_path,
-			 sys_dirent->d_name);
+		dir_path = get_events_file(sys_dirent->d_name);
+		if (!dir_path)
+			continue;
 		evt_dir = opendir(dir_path);
 		if (!evt_dir)
-			continue;
+			goto next;
 
-		for_each_event(sys_dirent, evt_dir, evt_dirent) {
+		for_each_event(dir_path, evt_dir, evt_dirent) {
 			snprintf(evt_path, MAXPATHLEN, "%s:%s",
 				 sys_dirent->d_name, evt_dirent->d_name);
 			if (!strcmp(evt_path, event_string)) {
@@ -2209,6 +2222,8 @@ int is_valid_tracepoint(const char *event_string)
 			}
 		}
 		closedir(evt_dir);
+next:
+		put_events_file(dir_path);
 	}
 	closedir(sys_dir);
 	return 0;
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index e1dbc9821617..3094f11e7d81 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -111,17 +111,6 @@ void exit_probe_symbol_maps(void)
 	symbol__exit();
 }
 
-static struct symbol *__find_kernel_function_by_name(const char *name,
-						     struct map **mapp)
-{
-	return machine__find_kernel_function_by_name(host_machine, name, mapp);
-}
-
-static struct symbol *__find_kernel_function(u64 addr, struct map **mapp)
-{
-	return machine__find_kernel_function(host_machine, addr, mapp);
-}
-
 static struct ref_reloc_sym *kernel_get_ref_reloc_sym(void)
 {
 	/* kmap->ref_reloc_sym should be set if host_machine is initialized */
@@ -149,7 +138,7 @@ static int kernel_get_symbol_address_by_name(const char *name, u64 *addr,
 	if (reloc_sym && strcmp(name, reloc_sym->name) == 0)
 		*addr = (reloc) ? reloc_sym->addr : reloc_sym->unrelocated_addr;
 	else {
-		sym = __find_kernel_function_by_name(name, &map);
+		sym = machine__find_kernel_symbol_by_name(host_machine, name, &map);
 		if (!sym)
 			return -ENOENT;
 		*addr = map->unmap_ip(map, sym->start) -
@@ -161,8 +150,7 @@ static int kernel_get_symbol_address_by_name(const char *name, u64 *addr,
 
 static struct map *kernel_get_module_map(const char *module)
 {
-	struct map_groups *grp = &host_machine->kmaps;
-	struct maps *maps = &grp->maps[MAP__FUNCTION];
+	struct maps *maps = machine__kernel_maps(host_machine);
 	struct map *pos;
 
 	/* A file path -- this is an offline module */
@@ -341,7 +329,7 @@ static int kernel_get_module_dso(const char *module, struct dso **pdso)
 		char module_name[128];
 
 		snprintf(module_name, sizeof(module_name), "[%s]", module);
-		map = map_groups__find_by_name(&host_machine->kmaps, MAP__FUNCTION, module_name);
+		map = map_groups__find_by_name(&host_machine->kmaps, module_name);
 		if (map) {
 			dso = map->dso;
 			goto found;
@@ -2098,7 +2086,7 @@ static int find_perf_probe_point_from_map(struct probe_trace_point *tp,
 		}
 		if (addr) {
 			addr += tp->offset;
-			sym = __find_kernel_function(addr, &map);
+			sym = machine__find_kernel_symbol(host_machine, addr, &map);
 		}
 	}
 
@@ -3504,19 +3492,18 @@ int show_available_funcs(const char *target, struct nsinfo *nsi,
 			       (target) ? : "kernel");
 		goto end;
 	}
-	if (!dso__sorted_by_name(map->dso, map->type))
-		dso__sort_by_name(map->dso, map->type);
+	if (!dso__sorted_by_name(map->dso))
+		dso__sort_by_name(map->dso);
 
 	/* Show all (filtered) symbols */
 	setup_pager();
 
-        for (nd = rb_first(&map->dso->symbol_names[map->type]); nd; nd = rb_next(nd)) {
+	for (nd = rb_first(&map->dso->symbol_names); nd; nd = rb_next(nd)) {
 		struct symbol_name_rb_node *pos = rb_entry(nd, struct symbol_name_rb_node, rb_node);
 
 		if (strfilter__compare(_filter, pos->sym.name))
 			printf("%s\n", pos->sym.name);
-        }
-
+	}
 end:
 	map__put(map);
 	exit_probe_symbol_maps();
diff --git a/tools/perf/util/probe-file.c b/tools/perf/util/probe-file.c
index 4ae1123c6794..b76088fadf3d 100644
--- a/tools/perf/util/probe-file.c
+++ b/tools/perf/util/probe-file.c
@@ -84,8 +84,7 @@ int open_trace_file(const char *trace_file, bool readwrite)
 	char buf[PATH_MAX];
 	int ret;
 
-	ret = e_snprintf(buf, PATH_MAX, "%s/%s",
-			 tracing_path, trace_file);
+	ret = e_snprintf(buf, PATH_MAX, "%s/%s", tracing_path_mount(), trace_file);
 	if (ret >= 0) {
 		pr_debug("Opening %s write=%d\n", buf, readwrite);
 		if (readwrite && !probe_event_dry_run)
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index f4a7a437ee87..b998bb475589 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -1973,12 +1973,11 @@ bool perf_session__has_traces(struct perf_session *session, const char *msg)
 	return false;
 }
 
-int maps__set_kallsyms_ref_reloc_sym(struct map **maps,
-				     const char *symbol_name, u64 addr)
+int map__set_kallsyms_ref_reloc_sym(struct map *map, const char *symbol_name, u64 addr)
 {
 	char *bracket;
-	int i;
 	struct ref_reloc_sym *ref;
+	struct kmap *kmap;
 
 	ref = zalloc(sizeof(struct ref_reloc_sym));
 	if (ref == NULL)
@@ -1996,13 +1995,9 @@ int maps__set_kallsyms_ref_reloc_sym(struct map **maps,
 
 	ref->addr = addr;
 
-	for (i = 0; i < MAP__NR_TYPES; ++i) {
-		struct kmap *kmap = map__kmap(maps[i]);
-
-		if (!kmap)
-			continue;
+	kmap = map__kmap(map);
+	if (kmap)
 		kmap->ref_reloc_sym = ref;
-	}
 
 	return 0;
 }
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index 26a68dfd8a4f..4058ade352a5 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -2,7 +2,7 @@
 #include <errno.h>
 #include <inttypes.h>
 #include <regex.h>
-#include <sys/mman.h>
+#include <linux/mman.h>
 #include "sort.h"
 #include "hist.h"
 #include "comm.h"
@@ -282,7 +282,7 @@ static int _hist_entry__sym_snprintf(struct map *map, struct symbol *sym,
 
 	ret += repsep_snprintf(bf + ret, size - ret, "[%c] ", level);
 	if (sym && map) {
-		if (map->type == MAP__VARIABLE) {
+		if (sym->type == STT_OBJECT) {
 			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));
@@ -1211,7 +1211,7 @@ static int hist_entry__dcacheline_snprintf(struct hist_entry *he, char *bf,
 
 		/* print [s] for shared data mmaps */
 		if ((he->cpumode != PERF_RECORD_MISC_KERNEL) &&
-		     map && (map->type == MAP__VARIABLE) &&
+		     map && !(map->prot & PROT_EXEC) &&
 		    (map->flags & MAP_SHARED) &&
 		    (map->maj || map->min || map->ino ||
 		     map->ino_generation))
@@ -2582,7 +2582,7 @@ int sort_dimension__add(struct perf_hpp_list *list, const char *tok,
 		if (sort__mode != SORT_MODE__MEMORY)
 			return -EINVAL;
 
-		if (sd->entry == &sort_mem_dcacheline && cacheline_size == 0)
+		if (sd->entry == &sort_mem_dcacheline && cacheline_size() == 0)
 			return -EINVAL;
 
 		if (sd->entry == &sort_mem_daddr_sym)
@@ -2628,7 +2628,7 @@ static int setup_sort_list(struct perf_hpp_list *list, char *str,
 		if (*tok) {
 			ret = sort_dimension__add(list, tok, evlist, level);
 			if (ret == -EINVAL) {
-				if (!cacheline_size && !strncasecmp(tok, "dcacheline", strlen(tok)))
+				if (!cacheline_size() && !strncasecmp(tok, "dcacheline", strlen(tok)))
 					pr_err("The \"dcacheline\" --sort key needs to know the cacheline size and it couldn't be determined on this system");
 				else
 					pr_err("Invalid --sort key: `%s'", tok);
diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h
index 035b62e2c60b..9e6896293bbd 100644
--- a/tools/perf/util/sort.h
+++ b/tools/perf/util/sort.h
@@ -186,13 +186,13 @@ static inline float hist_entry__get_percent_limit(struct hist_entry *he)
 static inline u64 cl_address(u64 address)
 {
 	/* return the cacheline of the address */
-	return (address & ~(cacheline_size - 1));
+	return (address & ~(cacheline_size() - 1));
 }
 
 static inline u64 cl_offset(u64 address)
 {
 	/* return the cacheline of the address */
-	return (address & (cacheline_size - 1));
+	return (address & (cacheline_size() - 1));
 }
 
 enum sort_mode {
diff --git a/tools/perf/util/srcline.c b/tools/perf/util/srcline.c
index 3c21fd059b64..09d6746e6ec8 100644
--- a/tools/perf/util/srcline.c
+++ b/tools/perf/util/srcline.c
@@ -103,6 +103,7 @@ static struct symbol *new_inline_sym(struct dso *dso,
 		inline_sym = symbol__new(base_sym ? base_sym->start : 0,
 					 base_sym ? base_sym->end : 0,
 					 base_sym ? base_sym->binding : 0,
+					 base_sym ? base_sym->type : 0,
 					 funcname);
 		if (inline_sym)
 			inline_sym->inlined = 1;
diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h
index 8f56ba4fd258..36efb986f7fc 100644
--- a/tools/perf/util/stat.h
+++ b/tools/perf/util/stat.h
@@ -7,8 +7,7 @@
 #include "xyarray.h"
 #include "rblist.h"
 
-struct stats
-{
+struct stats {
 	double n, mean, M2;
 	u64 max, min;
 };
diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c
index 2de770511e70..29770ea61768 100644
--- a/tools/perf/util/symbol-elf.c
+++ b/tools/perf/util/symbol-elf.c
@@ -114,16 +114,9 @@ static inline int elf_sym__is_label(const GElf_Sym *sym)
 		sym->st_shndx != SHN_ABS;
 }
 
-static bool elf_sym__is_a(GElf_Sym *sym, enum map_type type)
+static bool elf_sym__filter(GElf_Sym *sym)
 {
-	switch (type) {
-	case MAP__FUNCTION:
-		return elf_sym__is_function(sym);
-	case MAP__VARIABLE:
-		return elf_sym__is_object(sym);
-	default:
-		return false;
-	}
+	return elf_sym__is_function(sym) || elf_sym__is_object(sym);
 }
 
 static inline const char *elf_sym__name(const GElf_Sym *sym,
@@ -150,17 +143,10 @@ static inline bool elf_sec__is_data(const GElf_Shdr *shdr,
 	return strstr(elf_sec__name(shdr, secstrs), "data") != NULL;
 }
 
-static bool elf_sec__is_a(GElf_Shdr *shdr, Elf_Data *secstrs,
-			  enum map_type type)
+static bool elf_sec__filter(GElf_Shdr *shdr, Elf_Data *secstrs)
 {
-	switch (type) {
-	case MAP__FUNCTION:
-		return elf_sec__is_text(shdr, secstrs);
-	case MAP__VARIABLE:
-		return elf_sec__is_data(shdr, secstrs);
-	default:
-		return false;
-	}
+	return elf_sec__is_text(shdr, secstrs) || 
+	       elf_sec__is_data(shdr, secstrs);
 }
 
 static size_t elf_addr_to_index(Elf *elf, GElf_Addr addr)
@@ -256,7 +242,7 @@ static char *demangle_sym(struct dso *dso, int kmodule, const char *elf_name)
  * And always look at the original dso, not at debuginfo packages, that
  * have the PLT data stripped out (shdr_rel_plt.sh_type == SHT_NOBITS).
  */
-int dso__synthesize_plt_symbols(struct dso *dso, struct symsrc *ss, struct map *map)
+int dso__synthesize_plt_symbols(struct dso *dso, struct symsrc *ss)
 {
 	uint32_t nr_rel_entries, idx;
 	GElf_Sym sym;
@@ -364,12 +350,12 @@ int dso__synthesize_plt_symbols(struct dso *dso, struct symsrc *ss, struct map *
 			free(demangled);
 
 			f = symbol__new(plt_offset, plt_entry_size,
-					STB_GLOBAL, sympltname);
+					STB_GLOBAL, STT_FUNC, sympltname);
 			if (!f)
 				goto out_elf_end;
 
 			plt_offset += plt_entry_size;
-			symbols__insert(&dso->symbols[map->type], f);
+			symbols__insert(&dso->symbols, f);
 			++nr;
 		}
 	} else if (shdr_rel_plt.sh_type == SHT_REL) {
@@ -390,12 +376,12 @@ int dso__synthesize_plt_symbols(struct dso *dso, struct symsrc *ss, struct map *
 			free(demangled);
 
 			f = symbol__new(plt_offset, plt_entry_size,
-					STB_GLOBAL, sympltname);
+					STB_GLOBAL, STT_FUNC, sympltname);
 			if (!f)
 				goto out_elf_end;
 
 			plt_offset += plt_entry_size;
-			symbols__insert(&dso->symbols[map->type], f);
+			symbols__insert(&dso->symbols, f);
 			++nr;
 		}
 	}
@@ -811,6 +797,110 @@ static u64 ref_reloc(struct kmap *kmap)
 void __weak arch__sym_update(struct symbol *s __maybe_unused,
 		GElf_Sym *sym __maybe_unused) { }
 
+static int dso__process_kernel_symbol(struct dso *dso, struct map *map,
+				      GElf_Sym *sym, GElf_Shdr *shdr,
+				      struct map_groups *kmaps, struct kmap *kmap,
+				      struct dso **curr_dsop, struct map **curr_mapp,
+				      const char *section_name,
+				      bool adjust_kernel_syms, bool kmodule, bool *remap_kernel)
+{
+	struct dso *curr_dso = *curr_dsop;
+	struct map *curr_map;
+	char dso_name[PATH_MAX];
+
+	/* Adjust symbol to map to file offset */
+	if (adjust_kernel_syms)
+		sym->st_value -= shdr->sh_addr - shdr->sh_offset;
+
+	if (strcmp(section_name, (curr_dso->short_name + dso->short_name_len)) == 0)
+		return 0;
+
+	if (strcmp(section_name, ".text") == 0) {
+		/*
+		 * The initial kernel mapping is based on
+		 * kallsyms and identity maps.  Overwrite it to
+		 * map to the kernel dso.
+		 */
+		if (*remap_kernel && dso->kernel) {
+			*remap_kernel = false;
+			map->start = shdr->sh_addr + ref_reloc(kmap);
+			map->end = map->start + shdr->sh_size;
+			map->pgoff = shdr->sh_offset;
+			map->map_ip = map__map_ip;
+			map->unmap_ip = map__unmap_ip;
+			/* Ensure maps are correctly ordered */
+			if (kmaps) {
+				map__get(map);
+				map_groups__remove(kmaps, map);
+				map_groups__insert(kmaps, map);
+				map__put(map);
+			}
+		}
+
+		/*
+		 * The initial module mapping is based on
+		 * /proc/modules mapped to offset zero.
+		 * Overwrite it to map to the module dso.
+		 */
+		if (*remap_kernel && kmodule) {
+			*remap_kernel = false;
+			map->pgoff = shdr->sh_offset;
+		}
+
+		*curr_mapp = map;
+		*curr_dsop = dso;
+		return 0;
+	}
+
+	if (!kmap)
+		return 0;
+
+	snprintf(dso_name, sizeof(dso_name), "%s%s", dso->short_name, section_name);
+
+	curr_map = map_groups__find_by_name(kmaps, dso_name);
+	if (curr_map == NULL) {
+		u64 start = sym->st_value;
+
+		if (kmodule)
+			start += map->start + shdr->sh_offset;
+
+		curr_dso = dso__new(dso_name);
+		if (curr_dso == NULL)
+			return -1;
+		curr_dso->kernel = dso->kernel;
+		curr_dso->long_name = dso->long_name;
+		curr_dso->long_name_len = dso->long_name_len;
+		curr_map = map__new2(start, curr_dso);
+		dso__put(curr_dso);
+		if (curr_map == NULL)
+			return -1;
+
+		if (adjust_kernel_syms) {
+			curr_map->start  = shdr->sh_addr + ref_reloc(kmap);
+			curr_map->end	 = curr_map->start + shdr->sh_size;
+			curr_map->pgoff	 = shdr->sh_offset;
+		} else {
+			curr_map->map_ip = curr_map->unmap_ip = identity__map_ip;
+		}
+		curr_dso->symtab_type = dso->symtab_type;
+		map_groups__insert(kmaps, curr_map);
+		/*
+		 * Add it before we drop the referece to curr_map, i.e. while
+		 * we still are sure to have a reference to this DSO via
+		 * *curr_map->dso.
+		 */
+		dsos__add(&map->groups->machine->dsos, curr_dso);
+		/* kmaps already got it */
+		map__put(curr_map);
+		dso__set_loaded(curr_dso);
+		*curr_mapp = curr_map;
+		*curr_dsop = curr_dso;
+	} else
+		*curr_dsop = curr_map->dso;
+
+	return 0;
+}
+
 int dso__load_sym(struct dso *dso, struct map *map, struct symsrc *syms_ss,
 		  struct symsrc *runtime_ss, int kmodule)
 {
@@ -844,7 +934,7 @@ int dso__load_sym(struct dso *dso, struct map *map, struct symsrc *syms_ss,
 	 * have the wrong values for the dso maps, so remove them.
 	 */
 	if (kmodule && syms_ss->symtab)
-		symbols__delete(&dso->symbols[map->type]);
+		symbols__delete(&dso->symbols);
 
 	if (!syms_ss->symtab) {
 		/*
@@ -921,10 +1011,10 @@ int dso__load_sym(struct dso *dso, struct map *map, struct symsrc *syms_ss,
 
 	dso->adjust_symbols = runtime_ss->adjust_symbols || ref_reloc(kmap);
 	/*
-	 * Initial kernel and module mappings do not map to the dso.  For
-	 * function mappings, flag the fixups.
+	 * Initial kernel and module mappings do not map to the dso.
+	 * Flag the fixups.
 	 */
-	if (map->type == MAP__FUNCTION && (dso->kernel || kmodule)) {
+	if (dso->kernel || kmodule) {
 		remap_kernel = true;
 		adjust_kernel_syms = dso->adjust_symbols;
 	}
@@ -936,7 +1026,7 @@ int dso__load_sym(struct dso *dso, struct map *map, struct symsrc *syms_ss,
 		const char *section_name;
 		bool used_opd = false;
 
-		if (!is_label && !elf_sym__is_a(&sym, map->type))
+		if (!is_label && !elf_sym__filter(&sym))
 			continue;
 
 		/* Reject ARM ELF "mapping symbols": these aren't unique and
@@ -974,7 +1064,7 @@ int dso__load_sym(struct dso *dso, struct map *map, struct symsrc *syms_ss,
 
 		gelf_getshdr(sec, &shdr);
 
-		if (is_label && !elf_sec__is_a(&shdr, secstrs, map->type))
+		if (is_label && !elf_sec__filter(&shdr, secstrs))
 			continue;
 
 		section_name = elf_sec__name(&shdr, secstrs);
@@ -982,134 +1072,37 @@ int dso__load_sym(struct dso *dso, struct map *map, struct symsrc *syms_ss,
 		/* On ARM, symbols for thumb functions have 1 added to
 		 * the symbol address as a flag - remove it */
 		if ((ehdr.e_machine == EM_ARM) &&
-		    (map->type == MAP__FUNCTION) &&
+		    (GELF_ST_TYPE(sym.st_info) == STT_FUNC) &&
 		    (sym.st_value & 1))
 			--sym.st_value;
 
 		if (dso->kernel || kmodule) {
-			char dso_name[PATH_MAX];
-
-			/* Adjust symbol to map to file offset */
-			if (adjust_kernel_syms)
-				sym.st_value -= shdr.sh_addr - shdr.sh_offset;
-
-			if (strcmp(section_name,
-				   (curr_dso->short_name +
-				    dso->short_name_len)) == 0)
-				goto new_symbol;
-
-			if (strcmp(section_name, ".text") == 0) {
-				/*
-				 * The initial kernel mapping is based on
-				 * kallsyms and identity maps.  Overwrite it to
-				 * map to the kernel dso.
-				 */
-				if (remap_kernel && dso->kernel) {
-					remap_kernel = false;
-					map->start = shdr.sh_addr +
-						     ref_reloc(kmap);
-					map->end = map->start + shdr.sh_size;
-					map->pgoff = shdr.sh_offset;
-					map->map_ip = map__map_ip;
-					map->unmap_ip = map__unmap_ip;
-					/* Ensure maps are correctly ordered */
-					if (kmaps) {
-						map__get(map);
-						map_groups__remove(kmaps, map);
-						map_groups__insert(kmaps, map);
-						map__put(map);
-					}
-				}
-
-				/*
-				 * The initial module mapping is based on
-				 * /proc/modules mapped to offset zero.
-				 * Overwrite it to map to the module dso.
-				 */
-				if (remap_kernel && kmodule) {
-					remap_kernel = false;
-					map->pgoff = shdr.sh_offset;
-				}
-
-				curr_map = map;
-				curr_dso = dso;
-				goto new_symbol;
-			}
-
-			if (!kmap)
-				goto new_symbol;
-
-			snprintf(dso_name, sizeof(dso_name),
-				 "%s%s", dso->short_name, section_name);
-
-			curr_map = map_groups__find_by_name(kmaps, map->type, dso_name);
-			if (curr_map == NULL) {
-				u64 start = sym.st_value;
-
-				if (kmodule)
-					start += map->start + shdr.sh_offset;
-
-				curr_dso = dso__new(dso_name);
-				if (curr_dso == NULL)
-					goto out_elf_end;
-				curr_dso->kernel = dso->kernel;
-				curr_dso->long_name = dso->long_name;
-				curr_dso->long_name_len = dso->long_name_len;
-				curr_map = map__new2(start, curr_dso,
-						     map->type);
-				dso__put(curr_dso);
-				if (curr_map == NULL) {
-					goto out_elf_end;
-				}
-				if (adjust_kernel_syms) {
-					curr_map->start = shdr.sh_addr +
-							  ref_reloc(kmap);
-					curr_map->end = curr_map->start +
-							shdr.sh_size;
-					curr_map->pgoff = shdr.sh_offset;
-				} else {
-					curr_map->map_ip = identity__map_ip;
-					curr_map->unmap_ip = identity__map_ip;
-				}
-				curr_dso->symtab_type = dso->symtab_type;
-				map_groups__insert(kmaps, curr_map);
-				/*
-				 * Add it before we drop the referece to curr_map,
-				 * i.e. while we still are sure to have a reference
-				 * to this DSO via curr_map->dso.
-				 */
-				dsos__add(&map->groups->machine->dsos, curr_dso);
-				/* kmaps already got it */
-				map__put(curr_map);
-				dso__set_loaded(curr_dso, map->type);
-			} else
-				curr_dso = curr_map->dso;
-
-			goto new_symbol;
-		}
-
-		if ((used_opd && runtime_ss->adjust_symbols)
-				|| (!used_opd && syms_ss->adjust_symbols)) {
+			if (dso__process_kernel_symbol(dso, map, &sym, &shdr, kmaps, kmap, &curr_dso, &curr_map,
+						       section_name, adjust_kernel_syms, kmodule, &remap_kernel))
+				goto out_elf_end;
+		} else if ((used_opd && runtime_ss->adjust_symbols) ||
+			   (!used_opd && syms_ss->adjust_symbols)) {
 			pr_debug4("%s: adjusting symbol: st_value: %#" PRIx64 " "
 				  "sh_addr: %#" PRIx64 " sh_offset: %#" PRIx64 "\n", __func__,
 				  (u64)sym.st_value, (u64)shdr.sh_addr,
 				  (u64)shdr.sh_offset);
 			sym.st_value -= shdr.sh_addr - shdr.sh_offset;
 		}
-new_symbol:
+
 		demangled = demangle_sym(dso, kmodule, elf_name);
 		if (demangled != NULL)
 			elf_name = demangled;
 
 		f = symbol__new(sym.st_value, sym.st_size,
-				GELF_ST_BIND(sym.st_info), elf_name);
+				GELF_ST_BIND(sym.st_info),
+				GELF_ST_TYPE(sym.st_info), elf_name);
 		free(demangled);
 		if (!f)
 			goto out_elf_end;
 
 		arch__sym_update(f, &sym);
 
-		__symbols__insert(&curr_dso->symbols[curr_map->type], f, dso->kernel);
+		__symbols__insert(&curr_dso->symbols, f, dso->kernel);
 		nr++;
 	}
 
@@ -1117,14 +1110,14 @@ new_symbol:
 	 * For misannotated, zeroed, ASM function sizes.
 	 */
 	if (nr > 0) {
-		symbols__fixup_end(&dso->symbols[map->type]);
-		symbols__fixup_duplicate(&dso->symbols[map->type]);
+		symbols__fixup_end(&dso->symbols);
+		symbols__fixup_duplicate(&dso->symbols);
 		if (kmap) {
 			/*
 			 * We need to fixup this here too because we create new
 			 * maps here, for things like vsyscall sections.
 			 */
-			__map_groups__fixup_end(kmaps, map->type);
+			map_groups__fixup_end(kmaps);
 		}
 	}
 	err = nr;
@@ -1393,8 +1386,16 @@ static off_t kcore__write(struct kcore *kcore)
 
 struct phdr_data {
 	off_t offset;
+	off_t rel;
 	u64 addr;
 	u64 len;
+	struct list_head node;
+	struct phdr_data *remaps;
+};
+
+struct sym_data {
+	u64 addr;
+	struct list_head node;
 };
 
 struct kcore_copy_info {
@@ -1404,16 +1405,78 @@ struct kcore_copy_info {
 	u64 last_symbol;
 	u64 first_module;
 	u64 last_module_symbol;
-	struct phdr_data kernel_map;
-	struct phdr_data modules_map;
+	size_t phnum;
+	struct list_head phdrs;
+	struct list_head syms;
 };
 
+#define kcore_copy__for_each_phdr(k, p) \
+	list_for_each_entry((p), &(k)->phdrs, node)
+
+static struct phdr_data *phdr_data__new(u64 addr, u64 len, off_t offset)
+{
+	struct phdr_data *p = zalloc(sizeof(*p));
+
+	if (p) {
+		p->addr   = addr;
+		p->len    = len;
+		p->offset = offset;
+	}
+
+	return p;
+}
+
+static struct phdr_data *kcore_copy_info__addnew(struct kcore_copy_info *kci,
+						 u64 addr, u64 len,
+						 off_t offset)
+{
+	struct phdr_data *p = phdr_data__new(addr, len, offset);
+
+	if (p)
+		list_add_tail(&p->node, &kci->phdrs);
+
+	return p;
+}
+
+static void kcore_copy__free_phdrs(struct kcore_copy_info *kci)
+{
+	struct phdr_data *p, *tmp;
+
+	list_for_each_entry_safe(p, tmp, &kci->phdrs, node) {
+		list_del(&p->node);
+		free(p);
+	}
+}
+
+static struct sym_data *kcore_copy__new_sym(struct kcore_copy_info *kci,
+					    u64 addr)
+{
+	struct sym_data *s = zalloc(sizeof(*s));
+
+	if (s) {
+		s->addr = addr;
+		list_add_tail(&s->node, &kci->syms);
+	}
+
+	return s;
+}
+
+static void kcore_copy__free_syms(struct kcore_copy_info *kci)
+{
+	struct sym_data *s, *tmp;
+
+	list_for_each_entry_safe(s, tmp, &kci->syms, node) {
+		list_del(&s->node);
+		free(s);
+	}
+}
+
 static int kcore_copy__process_kallsyms(void *arg, const char *name, char type,
 					u64 start)
 {
 	struct kcore_copy_info *kci = arg;
 
-	if (!symbol_type__is_a(type, MAP__FUNCTION))
+	if (!kallsyms__is_function(type))
 		return 0;
 
 	if (strchr(name, '[')) {
@@ -1438,6 +1501,9 @@ static int kcore_copy__process_kallsyms(void *arg, const char *name, char type,
 		return 0;
 	}
 
+	if (is_entry_trampoline(name) && !kcore_copy__new_sym(kci, start))
+		return -1;
+
 	return 0;
 }
 
@@ -1487,27 +1553,39 @@ static int kcore_copy__parse_modules(struct kcore_copy_info *kci,
 	return 0;
 }
 
-static void kcore_copy__map(struct phdr_data *p, u64 start, u64 end, u64 pgoff,
-			    u64 s, u64 e)
+static int kcore_copy__map(struct kcore_copy_info *kci, u64 start, u64 end,
+			   u64 pgoff, u64 s, u64 e)
 {
-	if (p->addr || s < start || s >= end)
-		return;
+	u64 len, offset;
 
-	p->addr = s;
-	p->offset = (s - start) + pgoff;
-	p->len = e < end ? e - s : end - s;
+	if (s < start || s >= end)
+		return 0;
+
+	offset = (s - start) + pgoff;
+	len = e < end ? e - s : end - s;
+
+	return kcore_copy_info__addnew(kci, s, len, offset) ? 0 : -1;
 }
 
 static int kcore_copy__read_map(u64 start, u64 len, u64 pgoff, void *data)
 {
 	struct kcore_copy_info *kci = data;
 	u64 end = start + len;
+	struct sym_data *sdat;
 
-	kcore_copy__map(&kci->kernel_map, start, end, pgoff, kci->stext,
-			kci->etext);
+	if (kcore_copy__map(kci, start, end, pgoff, kci->stext, kci->etext))
+		return -1;
 
-	kcore_copy__map(&kci->modules_map, start, end, pgoff, kci->first_module,
-			kci->last_module_symbol);
+	if (kcore_copy__map(kci, start, end, pgoff, kci->first_module,
+			    kci->last_module_symbol))
+		return -1;
+
+	list_for_each_entry(sdat, &kci->syms, node) {
+		u64 s = round_down(sdat->addr, page_size);
+
+		if (kcore_copy__map(kci, start, end, pgoff, s, s + len))
+			return -1;
+	}
 
 	return 0;
 }
@@ -1520,6 +1598,64 @@ static int kcore_copy__read_maps(struct kcore_copy_info *kci, Elf *elf)
 	return 0;
 }
 
+static void kcore_copy__find_remaps(struct kcore_copy_info *kci)
+{
+	struct phdr_data *p, *k = NULL;
+	u64 kend;
+
+	if (!kci->stext)
+		return;
+
+	/* Find phdr that corresponds to the kernel map (contains stext) */
+	kcore_copy__for_each_phdr(kci, p) {
+		u64 pend = p->addr + p->len - 1;
+
+		if (p->addr <= kci->stext && pend >= kci->stext) {
+			k = p;
+			break;
+		}
+	}
+
+	if (!k)
+		return;
+
+	kend = k->offset + k->len;
+
+	/* Find phdrs that remap the kernel */
+	kcore_copy__for_each_phdr(kci, p) {
+		u64 pend = p->offset + p->len;
+
+		if (p == k)
+			continue;
+
+		if (p->offset >= k->offset && pend <= kend)
+			p->remaps = k;
+	}
+}
+
+static void kcore_copy__layout(struct kcore_copy_info *kci)
+{
+	struct phdr_data *p;
+	off_t rel = 0;
+
+	kcore_copy__find_remaps(kci);
+
+	kcore_copy__for_each_phdr(kci, p) {
+		if (!p->remaps) {
+			p->rel = rel;
+			rel += p->len;
+		}
+		kci->phnum += 1;
+	}
+
+	kcore_copy__for_each_phdr(kci, p) {
+		struct phdr_data *k = p->remaps;
+
+		if (k)
+			p->rel = p->offset - k->offset + k->rel;
+	}
+}
+
 static int kcore_copy__calc_maps(struct kcore_copy_info *kci, const char *dir,
 				 Elf *elf)
 {
@@ -1555,7 +1691,12 @@ static int kcore_copy__calc_maps(struct kcore_copy_info *kci, const char *dir,
 	if (kci->first_module && !kci->last_module_symbol)
 		return -1;
 
-	return kcore_copy__read_maps(kci, elf);
+	if (kcore_copy__read_maps(kci, elf))
+		return -1;
+
+	kcore_copy__layout(kci);
+
+	return 0;
 }
 
 static int kcore_copy__copy_file(const char *from_dir, const char *to_dir,
@@ -1678,12 +1819,15 @@ int kcore_copy(const char *from_dir, const char *to_dir)
 {
 	struct kcore kcore;
 	struct kcore extract;
-	size_t count = 2;
 	int idx = 0, err = -1;
-	off_t offset = page_size, sz, modules_offset = 0;
+	off_t offset, sz;
 	struct kcore_copy_info kci = { .stext = 0, };
 	char kcore_filename[PATH_MAX];
 	char extract_filename[PATH_MAX];
+	struct phdr_data *p;
+
+	INIT_LIST_HEAD(&kci.phdrs);
+	INIT_LIST_HEAD(&kci.syms);
 
 	if (kcore_copy__copy_file(from_dir, to_dir, "kallsyms"))
 		return -1;
@@ -1703,20 +1847,17 @@ int kcore_copy(const char *from_dir, const char *to_dir)
 	if (kcore__init(&extract, extract_filename, kcore.elfclass, false))
 		goto out_kcore_close;
 
-	if (!kci.modules_map.addr)
-		count -= 1;
-
-	if (kcore__copy_hdr(&kcore, &extract, count))
+	if (kcore__copy_hdr(&kcore, &extract, kci.phnum))
 		goto out_extract_close;
 
-	if (kcore__add_phdr(&extract, idx++, offset, kci.kernel_map.addr,
-			    kci.kernel_map.len))
-		goto out_extract_close;
+	offset = gelf_fsize(extract.elf, ELF_T_EHDR, 1, EV_CURRENT) +
+		 gelf_fsize(extract.elf, ELF_T_PHDR, kci.phnum, EV_CURRENT);
+	offset = round_up(offset, page_size);
 
-	if (kci.modules_map.addr) {
-		modules_offset = offset + kci.kernel_map.len;
-		if (kcore__add_phdr(&extract, idx, modules_offset,
-				    kci.modules_map.addr, kci.modules_map.len))
+	kcore_copy__for_each_phdr(&kci, p) {
+		off_t offs = p->rel + offset;
+
+		if (kcore__add_phdr(&extract, idx++, offs, p->addr, p->len))
 			goto out_extract_close;
 	}
 
@@ -1724,14 +1865,14 @@ int kcore_copy(const char *from_dir, const char *to_dir)
 	if (sz < 0 || sz > offset)
 		goto out_extract_close;
 
-	if (copy_bytes(kcore.fd, kci.kernel_map.offset, extract.fd, offset,
-		       kci.kernel_map.len))
-		goto out_extract_close;
+	kcore_copy__for_each_phdr(&kci, p) {
+		off_t offs = p->rel + offset;
 
-	if (modules_offset && copy_bytes(kcore.fd, kci.modules_map.offset,
-					 extract.fd, modules_offset,
-					 kci.modules_map.len))
-		goto out_extract_close;
+		if (p->remaps)
+			continue;
+		if (copy_bytes(kcore.fd, p->offset, extract.fd, offs, p->len))
+			goto out_extract_close;
+	}
 
 	if (kcore_copy__compare_file(from_dir, to_dir, "modules"))
 		goto out_extract_close;
@@ -1754,6 +1895,9 @@ out_unlink_kallsyms:
 	if (err)
 		kcore_copy__unlink(to_dir, "kallsyms");
 
+	kcore_copy__free_phdrs(&kci);
+	kcore_copy__free_syms(&kci);
+
 	return err;
 }
 
diff --git a/tools/perf/util/symbol-minimal.c b/tools/perf/util/symbol-minimal.c
index ff48d0d49584..7119df77dc0b 100644
--- a/tools/perf/util/symbol-minimal.c
+++ b/tools/perf/util/symbol-minimal.c
@@ -288,8 +288,7 @@ void symsrc__destroy(struct symsrc *ss)
 }
 
 int dso__synthesize_plt_symbols(struct dso *dso __maybe_unused,
-				struct symsrc *ss __maybe_unused,
-				struct map *map __maybe_unused)
+				struct symsrc *ss __maybe_unused)
 {
 	return 0;
 }
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 1466814ebada..8c84437f2a10 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -5,6 +5,7 @@
 #include <stdio.h>
 #include <string.h>
 #include <linux/kernel.h>
+#include <linux/mman.h>
 #include <sys/types.h>
 #include <sys/stat.h>
 #include <sys/param.h>
@@ -70,18 +71,10 @@ static enum dso_binary_type binary_type_symtab[] = {
 
 #define DSO_BINARY_TYPE__SYMTAB_CNT ARRAY_SIZE(binary_type_symtab)
 
-bool symbol_type__is_a(char symbol_type, enum map_type map_type)
+static bool symbol_type__filter(char symbol_type)
 {
 	symbol_type = toupper(symbol_type);
-
-	switch (map_type) {
-	case MAP__FUNCTION:
-		return symbol_type == 'T' || symbol_type == 'W';
-	case MAP__VARIABLE:
-		return symbol_type == 'D';
-	default:
-		return false;
-	}
+	return symbol_type == 'T' || symbol_type == 'W' || symbol_type == 'D';
 }
 
 static int prefix_underscores_count(const char *str)
@@ -228,9 +221,9 @@ void symbols__fixup_end(struct rb_root *symbols)
 		curr->end = roundup(curr->start, 4096) + 4096;
 }
 
-void __map_groups__fixup_end(struct map_groups *mg, enum map_type type)
+void map_groups__fixup_end(struct map_groups *mg)
 {
-	struct maps *maps = &mg->maps[type];
+	struct maps *maps = &mg->maps;
 	struct map *next, *curr;
 
 	down_write(&maps->lock);
@@ -256,7 +249,7 @@ out_unlock:
 	up_write(&maps->lock);
 }
 
-struct symbol *symbol__new(u64 start, u64 len, u8 binding, const char *name)
+struct symbol *symbol__new(u64 start, u64 len, u8 binding, u8 type, const char *name)
 {
 	size_t namelen = strlen(name) + 1;
 	struct symbol *sym = calloc(1, (symbol_conf.priv_size +
@@ -274,6 +267,7 @@ struct symbol *symbol__new(u64 start, u64 len, u8 binding, const char *name)
 
 	sym->start   = start;
 	sym->end     = len ? start + len : start;
+	sym->type    = type;
 	sym->binding = binding;
 	sym->namelen = namelen - 1;
 
@@ -484,45 +478,40 @@ static struct symbol *symbols__find_by_name(struct rb_root *symbols,
 
 void dso__reset_find_symbol_cache(struct dso *dso)
 {
-	enum map_type type;
-
-	for (type = MAP__FUNCTION; type <= MAP__VARIABLE; ++type) {
-		dso->last_find_result[type].addr   = 0;
-		dso->last_find_result[type].symbol = NULL;
-	}
+	dso->last_find_result.addr   = 0;
+	dso->last_find_result.symbol = NULL;
 }
 
-void dso__insert_symbol(struct dso *dso, enum map_type type, struct symbol *sym)
+void dso__insert_symbol(struct dso *dso, struct symbol *sym)
 {
-	__symbols__insert(&dso->symbols[type], sym, dso->kernel);
+	__symbols__insert(&dso->symbols, sym, dso->kernel);
 
 	/* update the symbol cache if necessary */
-	if (dso->last_find_result[type].addr >= sym->start &&
-	    (dso->last_find_result[type].addr < sym->end ||
+	if (dso->last_find_result.addr >= sym->start &&
+	    (dso->last_find_result.addr < sym->end ||
 	    sym->start == sym->end)) {
-		dso->last_find_result[type].symbol = sym;
+		dso->last_find_result.symbol = sym;
 	}
 }
 
-struct symbol *dso__find_symbol(struct dso *dso,
-				enum map_type type, u64 addr)
+struct symbol *dso__find_symbol(struct dso *dso, u64 addr)
 {
-	if (dso->last_find_result[type].addr != addr || dso->last_find_result[type].symbol == NULL) {
-		dso->last_find_result[type].addr   = addr;
-		dso->last_find_result[type].symbol = symbols__find(&dso->symbols[type], addr);
+	if (dso->last_find_result.addr != addr || dso->last_find_result.symbol == NULL) {
+		dso->last_find_result.addr   = addr;
+		dso->last_find_result.symbol = symbols__find(&dso->symbols, addr);
 	}
 
-	return dso->last_find_result[type].symbol;
+	return dso->last_find_result.symbol;
 }
 
-struct symbol *dso__first_symbol(struct dso *dso, enum map_type type)
+struct symbol *dso__first_symbol(struct dso *dso)
 {
-	return symbols__first(&dso->symbols[type]);
+	return symbols__first(&dso->symbols);
 }
 
-struct symbol *dso__last_symbol(struct dso *dso, enum map_type type)
+struct symbol *dso__last_symbol(struct dso *dso)
 {
-	return symbols__last(&dso->symbols[type]);
+	return symbols__last(&dso->symbols);
 }
 
 struct symbol *dso__next_symbol(struct symbol *sym)
@@ -539,24 +528,22 @@ struct symbol *symbol__next_by_name(struct symbol *sym)
 }
 
  /*
-  * Teturns first symbol that matched with @name.
+  * Returns first symbol that matched with @name.
   */
-struct symbol *dso__find_symbol_by_name(struct dso *dso, enum map_type type,
-					const char *name)
+struct symbol *dso__find_symbol_by_name(struct dso *dso, const char *name)
 {
-	struct symbol *s = symbols__find_by_name(&dso->symbol_names[type], name,
+	struct symbol *s = symbols__find_by_name(&dso->symbol_names, name,
 						 SYMBOL_TAG_INCLUDE__NONE);
 	if (!s)
-		s = symbols__find_by_name(&dso->symbol_names[type], name,
+		s = symbols__find_by_name(&dso->symbol_names, name,
 					  SYMBOL_TAG_INCLUDE__DEFAULT_ONLY);
 	return s;
 }
 
-void dso__sort_by_name(struct dso *dso, enum map_type type)
+void dso__sort_by_name(struct dso *dso)
 {
-	dso__set_sorted_by_name(dso, type);
-	return symbols__sort_by_name(&dso->symbol_names[type],
-				     &dso->symbols[type]);
+	dso__set_sorted_by_name(dso);
+	return symbols__sort_by_name(&dso->symbol_names, &dso->symbols);
 }
 
 int modules__parse(const char *filename, void *arg,
@@ -621,11 +608,6 @@ out:
 	return err;
 }
 
-struct process_kallsyms_args {
-	struct map *map;
-	struct dso *dso;
-};
-
 /*
  * These are symbols in the kernel image, so make sure that
  * sym is from a kernel DSO.
@@ -661,10 +643,10 @@ static int map__process_kallsym_symbol(void *arg, const char *name,
 				       char type, u64 start)
 {
 	struct symbol *sym;
-	struct process_kallsyms_args *a = arg;
-	struct rb_root *root = &a->dso->symbols[a->map->type];
+	struct dso *dso = arg;
+	struct rb_root *root = &dso->symbols;
 
-	if (!symbol_type__is_a(type, a->map->type))
+	if (!symbol_type__filter(type))
 		return 0;
 
 	/*
@@ -672,7 +654,7 @@ static int map__process_kallsym_symbol(void *arg, const char *name,
 	 * symbols, setting length to 0, and rely on
 	 * symbols__fixup_end() to fix it up.
 	 */
-	sym = symbol__new(start, 0, kallsyms2elf_binding(type), name);
+	sym = symbol__new(start, 0, kallsyms2elf_binding(type), kallsyms2elf_type(type), name);
 	if (sym == NULL)
 		return -ENOMEM;
 	/*
@@ -689,21 +671,18 @@ static int map__process_kallsym_symbol(void *arg, const char *name,
  * so that we can in the next step set the symbol ->end address and then
  * call kernel_maps__split_kallsyms.
  */
-static int dso__load_all_kallsyms(struct dso *dso, const char *filename,
-				  struct map *map)
+static int dso__load_all_kallsyms(struct dso *dso, const char *filename)
 {
-	struct process_kallsyms_args args = { .map = map, .dso = dso, };
-	return kallsyms__parse(filename, &args, map__process_kallsym_symbol);
+	return kallsyms__parse(filename, dso, map__process_kallsym_symbol);
 }
 
-static int dso__split_kallsyms_for_kcore(struct dso *dso, struct map *map)
+static int map_groups__split_kallsyms_for_kcore(struct map_groups *kmaps, struct dso *dso)
 {
-	struct map_groups *kmaps = map__kmaps(map);
 	struct map *curr_map;
 	struct symbol *pos;
 	int count = 0;
-	struct rb_root old_root = dso->symbols[map->type];
-	struct rb_root *root = &dso->symbols[map->type];
+	struct rb_root old_root = dso->symbols;
+	struct rb_root *root = &dso->symbols;
 	struct rb_node *next = rb_first(root);
 
 	if (!kmaps)
@@ -723,7 +702,7 @@ static int dso__split_kallsyms_for_kcore(struct dso *dso, struct map *map)
 		if (module)
 			*module = '\0';
 
-		curr_map = map_groups__find(kmaps, map->type, pos->start);
+		curr_map = map_groups__find(kmaps, pos->start);
 
 		if (!curr_map) {
 			symbol__delete(pos);
@@ -733,7 +712,7 @@ static int dso__split_kallsyms_for_kcore(struct dso *dso, struct map *map)
 		pos->start -= curr_map->start - curr_map->pgoff;
 		if (pos->end)
 			pos->end -= curr_map->start - curr_map->pgoff;
-		symbols__insert(&curr_map->dso->symbols[curr_map->type], pos);
+		symbols__insert(&curr_map->dso->symbols, pos);
 		++count;
 	}
 
@@ -748,22 +727,25 @@ static int dso__split_kallsyms_for_kcore(struct dso *dso, struct map *map)
  * kernel range is broken in several maps, named [kernel].N, as we don't have
  * the original ELF section names vmlinux have.
  */
-static int dso__split_kallsyms(struct dso *dso, struct map *map, u64 delta)
+static int map_groups__split_kallsyms(struct map_groups *kmaps, struct dso *dso, u64 delta,
+				      struct map *initial_map)
 {
-	struct map_groups *kmaps = map__kmaps(map);
 	struct machine *machine;
-	struct map *curr_map = map;
+	struct map *curr_map = initial_map;
 	struct symbol *pos;
 	int count = 0, moved = 0;
-	struct rb_root *root = &dso->symbols[map->type];
+	struct rb_root *root = &dso->symbols;
 	struct rb_node *next = rb_first(root);
 	int kernel_range = 0;
+	bool x86_64;
 
 	if (!kmaps)
 		return -1;
 
 	machine = kmaps->machine;
 
+	x86_64 = machine__is(machine, "x86_64");
+
 	while (next) {
 		char *module;
 
@@ -778,7 +760,7 @@ static int dso__split_kallsyms(struct dso *dso, struct map *map, u64 delta)
 			*module++ = '\0';
 
 			if (strcmp(curr_map->dso->short_name, module)) {
-				if (curr_map != map &&
+				if (curr_map != initial_map &&
 				    dso->kernel == DSO_TYPE_GUEST_KERNEL &&
 				    machine__is_default_guest(machine)) {
 					/*
@@ -788,18 +770,16 @@ static int dso__split_kallsyms(struct dso *dso, struct map *map, u64 delta)
 					 * symbols are in its kmap. Mark it as
 					 * loaded.
 					 */
-					dso__set_loaded(curr_map->dso,
-							curr_map->type);
+					dso__set_loaded(curr_map->dso);
 				}
 
-				curr_map = map_groups__find_by_name(kmaps,
-							map->type, module);
+				curr_map = map_groups__find_by_name(kmaps, module);
 				if (curr_map == NULL) {
 					pr_debug("%s/proc/{kallsyms,modules} "
 					         "inconsistency while looking "
 						 "for \"%s\" module!\n",
 						 machine->root_dir, module);
-					curr_map = map;
+					curr_map = initial_map;
 					goto discard_symbol;
 				}
 
@@ -809,11 +789,21 @@ static int dso__split_kallsyms(struct dso *dso, struct map *map, u64 delta)
 			}
 			/*
 			 * So that we look just like we get from .ko files,
-			 * i.e. not prelinked, relative to map->start.
+			 * i.e. not prelinked, relative to initial_map->start.
 			 */
 			pos->start = curr_map->map_ip(curr_map, pos->start);
 			pos->end   = curr_map->map_ip(curr_map, pos->end);
-		} else if (curr_map != map) {
+		} else if (x86_64 && is_entry_trampoline(pos->name)) {
+			/*
+			 * These symbols are not needed anymore since the
+			 * trampoline maps refer to the text section and it's
+			 * symbols instead. Avoid having to deal with
+			 * relocations, and the assumption that the first symbol
+			 * is the start of kernel text, by simply removing the
+			 * symbols at this point.
+			 */
+			goto discard_symbol;
+		} else if (curr_map != initial_map) {
 			char dso_name[PATH_MAX];
 			struct dso *ndso;
 
@@ -824,7 +814,7 @@ static int dso__split_kallsyms(struct dso *dso, struct map *map, u64 delta)
 			}
 
 			if (count == 0) {
-				curr_map = map;
+				curr_map = initial_map;
 				goto add_symbol;
 			}
 
@@ -843,7 +833,7 @@ static int dso__split_kallsyms(struct dso *dso, struct map *map, u64 delta)
 
 			ndso->kernel = dso->kernel;
 
-			curr_map = map__new2(pos->start, ndso, map->type);
+			curr_map = map__new2(pos->start, ndso);
 			if (curr_map == NULL) {
 				dso__put(ndso);
 				return -1;
@@ -858,9 +848,9 @@ static int dso__split_kallsyms(struct dso *dso, struct map *map, u64 delta)
 			pos->end -= delta;
 		}
 add_symbol:
-		if (curr_map != map) {
+		if (curr_map != initial_map) {
 			rb_erase(&pos->rb_node, root);
-			symbols__insert(&curr_map->dso->symbols[curr_map->type], pos);
+			symbols__insert(&curr_map->dso->symbols, pos);
 			++moved;
 		} else
 			++count;
@@ -871,10 +861,10 @@ discard_symbol:
 		symbol__delete(pos);
 	}
 
-	if (curr_map != map &&
+	if (curr_map != initial_map &&
 	    dso->kernel == DSO_TYPE_GUEST_KERNEL &&
 	    machine__is_default_guest(kmaps->machine)) {
-		dso__set_loaded(curr_map->dso, curr_map->type);
+		dso__set_loaded(curr_map->dso);
 	}
 
 	return count + moved;
@@ -1035,7 +1025,12 @@ out_delete_from:
 	return ret;
 }
 
-static int do_validate_kcore_modules(const char *filename, struct map *map,
+struct map *map_groups__first(struct map_groups *mg)
+{
+	return maps__first(&mg->maps);
+}
+
+static int do_validate_kcore_modules(const char *filename,
 				  struct map_groups *kmaps)
 {
 	struct rb_root modules = RB_ROOT;
@@ -1046,13 +1041,12 @@ static int do_validate_kcore_modules(const char *filename, struct map *map,
 	if (err)
 		return err;
 
-	old_map = map_groups__first(kmaps, map->type);
+	old_map = map_groups__first(kmaps);
 	while (old_map) {
 		struct map *next = map_groups__next(old_map);
 		struct module_info *mi;
 
-		if (old_map == map || old_map->start == map->start) {
-			/* The kernel map */
+		if (!__map__is_kmodule(old_map)) {
 			old_map = next;
 			continue;
 		}
@@ -1109,7 +1103,7 @@ static int validate_kcore_modules(const char *kallsyms_filename,
 					     kallsyms_filename))
 		return -EINVAL;
 
-	if (do_validate_kcore_modules(modules_filename, map, kmaps))
+	if (do_validate_kcore_modules(modules_filename, kmaps))
 		return -EINVAL;
 
 	return 0;
@@ -1138,7 +1132,6 @@ static int validate_kcore_addresses(const char *kallsyms_filename,
 
 struct kcore_mapfn_data {
 	struct dso *dso;
-	enum map_type type;
 	struct list_head maps;
 };
 
@@ -1147,7 +1140,7 @@ static int kcore_mapfn(u64 start, u64 len, u64 pgoff, void *data)
 	struct kcore_mapfn_data *md = data;
 	struct map *map;
 
-	map = map__new2(start, md->dso, md->type);
+	map = map__new2(start, md->dso);
 	if (map == NULL)
 		return -ENOMEM;
 
@@ -1163,13 +1156,13 @@ static int dso__load_kcore(struct dso *dso, struct map *map,
 			   const char *kallsyms_filename)
 {
 	struct map_groups *kmaps = map__kmaps(map);
-	struct machine *machine;
 	struct kcore_mapfn_data md;
 	struct map *old_map, *new_map, *replacement_map = NULL;
+	struct machine *machine;
 	bool is_64_bit;
 	int err, fd;
 	char kcore_filename[PATH_MAX];
-	struct symbol *sym;
+	u64 stext;
 
 	if (!kmaps)
 		return -EINVAL;
@@ -1177,7 +1170,7 @@ static int dso__load_kcore(struct dso *dso, struct map *map,
 	machine = kmaps->machine;
 
 	/* This function requires that the map is the kernel map */
-	if (map != machine->vmlinux_maps[map->type])
+	if (!__map__is_kernel(map))
 		return -EINVAL;
 
 	if (!filename_from_kallsyms_filename(kcore_filename, "kcore",
@@ -1189,7 +1182,6 @@ static int dso__load_kcore(struct dso *dso, struct map *map,
 		return -EINVAL;
 
 	md.dso = dso;
-	md.type = map->type;
 	INIT_LIST_HEAD(&md.maps);
 
 	fd = open(kcore_filename, O_RDONLY);
@@ -1200,7 +1192,7 @@ static int dso__load_kcore(struct dso *dso, struct map *map,
 	}
 
 	/* Read new maps into temporary lists */
-	err = file__read_maps(fd, md.type == MAP__FUNCTION, kcore_mapfn, &md,
+	err = file__read_maps(fd, map->prot & PROT_EXEC, kcore_mapfn, &md,
 			      &is_64_bit);
 	if (err)
 		goto out_err;
@@ -1212,7 +1204,7 @@ static int dso__load_kcore(struct dso *dso, struct map *map,
 	}
 
 	/* Remove old maps */
-	old_map = map_groups__first(kmaps, map->type);
+	old_map = map_groups__first(kmaps);
 	while (old_map) {
 		struct map *next = map_groups__next(old_map);
 
@@ -1220,14 +1212,15 @@ static int dso__load_kcore(struct dso *dso, struct map *map,
 			map_groups__remove(kmaps, old_map);
 		old_map = next;
 	}
+	machine->trampolines_mapped = false;
 
-	/* Find the kernel map using the first symbol */
-	sym = dso__first_symbol(dso, map->type);
-	list_for_each_entry(new_map, &md.maps, node) {
-		if (sym && sym->start >= new_map->start &&
-		    sym->start < new_map->end) {
-			replacement_map = new_map;
-			break;
+	/* Find the kernel map using the '_stext' symbol */
+	if (!kallsyms__get_function_start(kallsyms_filename, "_stext", &stext)) {
+		list_for_each_entry(new_map, &md.maps, node) {
+			if (stext >= new_map->start && stext < new_map->end) {
+				replacement_map = new_map;
+				break;
+			}
 		}
 	}
 
@@ -1256,6 +1249,19 @@ static int dso__load_kcore(struct dso *dso, struct map *map,
 		map__put(new_map);
 	}
 
+	if (machine__is(machine, "x86_64")) {
+		u64 addr;
+
+		/*
+		 * If one of the corresponding symbols is there, assume the
+		 * entry trampoline maps are too.
+		 */
+		if (!kallsyms__get_function_start(kallsyms_filename,
+						  ENTRY_TRAMPOLINE_NAME,
+						  &addr))
+			machine->trampolines_mapped = true;
+	}
+
 	/*
 	 * Set the data type and long name so that kcore can be read via
 	 * dso__data_read_addr().
@@ -1268,7 +1274,7 @@ static int dso__load_kcore(struct dso *dso, struct map *map,
 
 	close(fd);
 
-	if (map->type == MAP__FUNCTION)
+	if (map->prot & PROT_EXEC)
 		pr_debug("Using %s for kernel object code\n", kcore_filename);
 	else
 		pr_debug("Using %s for kernel data\n", kcore_filename);
@@ -1289,14 +1295,10 @@ out_err:
  * If the kernel is relocated at boot time, kallsyms won't match.  Compute the
  * delta based on the relocation reference symbol.
  */
-static int kallsyms__delta(struct map *map, const char *filename, u64 *delta)
+static int kallsyms__delta(struct kmap *kmap, const char *filename, u64 *delta)
 {
-	struct kmap *kmap = map__kmap(map);
 	u64 addr;
 
-	if (!kmap)
-		return -1;
-
 	if (!kmap->ref_reloc_sym || !kmap->ref_reloc_sym->name)
 		return 0;
 
@@ -1310,19 +1312,23 @@ static int kallsyms__delta(struct map *map, const char *filename, u64 *delta)
 int __dso__load_kallsyms(struct dso *dso, const char *filename,
 			 struct map *map, bool no_kcore)
 {
+	struct kmap *kmap = map__kmap(map);
 	u64 delta = 0;
 
 	if (symbol__restricted_filename(filename, "/proc/kallsyms"))
 		return -1;
 
-	if (dso__load_all_kallsyms(dso, filename, map) < 0)
+	if (!kmap || !kmap->kmaps)
 		return -1;
 
-	if (kallsyms__delta(map, filename, &delta))
+	if (dso__load_all_kallsyms(dso, filename) < 0)
 		return -1;
 
-	symbols__fixup_end(&dso->symbols[map->type]);
-	symbols__fixup_duplicate(&dso->symbols[map->type]);
+	if (kallsyms__delta(kmap, filename, &delta))
+		return -1;
+
+	symbols__fixup_end(&dso->symbols);
+	symbols__fixup_duplicate(&dso->symbols);
 
 	if (dso->kernel == DSO_TYPE_GUEST_KERNEL)
 		dso->symtab_type = DSO_BINARY_TYPE__GUEST_KALLSYMS;
@@ -1330,9 +1336,9 @@ int __dso__load_kallsyms(struct dso *dso, const char *filename,
 		dso->symtab_type = DSO_BINARY_TYPE__KALLSYMS;
 
 	if (!no_kcore && !dso__load_kcore(dso, map, filename))
-		return dso__split_kallsyms_for_kcore(dso, map);
+		return map_groups__split_kallsyms_for_kcore(kmap->kmaps, dso);
 	else
-		return dso__split_kallsyms(dso, map, delta);
+		return map_groups__split_kallsyms(kmap->kmaps, dso, delta, map);
 }
 
 int dso__load_kallsyms(struct dso *dso, const char *filename,
@@ -1341,8 +1347,7 @@ int dso__load_kallsyms(struct dso *dso, const char *filename,
 	return __dso__load_kallsyms(dso, filename, map, false);
 }
 
-static int dso__load_perf_map(const char *map_path, struct dso *dso,
-			      struct map *map)
+static int dso__load_perf_map(const char *map_path, struct dso *dso)
 {
 	char *line = NULL;
 	size_t n;
@@ -1379,12 +1384,12 @@ static int dso__load_perf_map(const char *map_path, struct dso *dso,
 		if (len + 2 >= line_len)
 			continue;
 
-		sym = symbol__new(start, size, STB_GLOBAL, line + len);
+		sym = symbol__new(start, size, STB_GLOBAL, STT_FUNC, line + len);
 
 		if (sym == NULL)
 			goto out_delete_line;
 
-		symbols__insert(&dso->symbols[map->type], sym);
+		symbols__insert(&dso->symbols, sym);
 		nr_syms++;
 	}
 
@@ -1509,25 +1514,27 @@ int dso__load(struct dso *dso, struct map *map)
 	pthread_mutex_lock(&dso->lock);
 
 	/* check again under the dso->lock */
-	if (dso__loaded(dso, map->type)) {
+	if (dso__loaded(dso)) {
 		ret = 1;
 		goto out;
 	}
 
-	if (dso->kernel) {
-		if (dso->kernel == DSO_TYPE_KERNEL)
-			ret = dso__load_kernel_sym(dso, map);
-		else if (dso->kernel == DSO_TYPE_GUEST_KERNEL)
-			ret = dso__load_guest_kernel_sym(dso, map);
-
-		goto out;
-	}
-
 	if (map->groups && map->groups->machine)
 		machine = map->groups->machine;
 	else
 		machine = NULL;
 
+	if (dso->kernel) {
+		if (dso->kernel == DSO_TYPE_KERNEL)
+			ret = dso__load_kernel_sym(dso, map);
+		else if (dso->kernel == DSO_TYPE_GUEST_KERNEL)
+			ret = dso__load_guest_kernel_sym(dso, map);
+
+		if (machine__is(machine, "x86_64"))
+			machine__map_x86_64_entry_trampolines(machine, dso);
+		goto out;
+	}
+
 	dso->adjust_symbols = 0;
 
 	if (perfmap) {
@@ -1542,7 +1549,7 @@ int dso__load(struct dso *dso, struct map *map)
 			goto out;
 		}
 
-		ret = dso__load_perf_map(map_path, dso, map);
+		ret = dso__load_perf_map(map_path, dso);
 		dso->symtab_type = ret > 0 ? DSO_BINARY_TYPE__JAVA_JIT :
 					     DSO_BINARY_TYPE__NOT_FOUND;
 		goto out;
@@ -1651,7 +1658,7 @@ int dso__load(struct dso *dso, struct map *map)
 	if (ret > 0) {
 		int nr_plt;
 
-		nr_plt = dso__synthesize_plt_symbols(dso, runtime_ss, map);
+		nr_plt = dso__synthesize_plt_symbols(dso, runtime_ss);
 		if (nr_plt > 0)
 			ret += nr_plt;
 	}
@@ -1663,17 +1670,16 @@ out_free:
 	if (ret < 0 && strstr(dso->name, " (deleted)") != NULL)
 		ret = 0;
 out:
-	dso__set_loaded(dso, map->type);
+	dso__set_loaded(dso);
 	pthread_mutex_unlock(&dso->lock);
 	nsinfo__mountns_exit(&nsc);
 
 	return ret;
 }
 
-struct map *map_groups__find_by_name(struct map_groups *mg,
-				     enum map_type type, const char *name)
+struct map *map_groups__find_by_name(struct map_groups *mg, const char *name)
 {
-	struct maps *maps = &mg->maps[type];
+	struct maps *maps = &mg->maps;
 	struct map *map;
 
 	down_read(&maps->lock);
@@ -1720,7 +1726,7 @@ int dso__load_vmlinux(struct dso *dso, struct map *map,
 		else
 			dso->binary_type = DSO_BINARY_TYPE__VMLINUX;
 		dso__set_long_name(dso, vmlinux, vmlinux_allocated);
-		dso__set_loaded(dso, map->type);
+		dso__set_loaded(dso);
 		pr_debug("Using %s for symbols\n", symfs_vmlinux);
 	}
 
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index 70c16741f50a..1a16438eb3ce 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -57,7 +57,8 @@ struct symbol {
 	u64		start;
 	u64		end;
 	u16		namelen;
-	u8		binding;
+	u8		type:4;
+	u8		binding:4;
 	u8		idle:1;
 	u8		ignore:1;
 	u8		inlined:1;
@@ -259,17 +260,16 @@ int __dso__load_kallsyms(struct dso *dso, const char *filename, struct map *map,
 			 bool no_kcore);
 int dso__load_kallsyms(struct dso *dso, const char *filename, struct map *map);
 
-void dso__insert_symbol(struct dso *dso, enum map_type type,
+void dso__insert_symbol(struct dso *dso,
 			struct symbol *sym);
 
-struct symbol *dso__find_symbol(struct dso *dso, enum map_type type,
-				u64 addr);
-struct symbol *dso__find_symbol_by_name(struct dso *dso, enum map_type type,
-					const char *name);
+struct symbol *dso__find_symbol(struct dso *dso, u64 addr);
+struct symbol *dso__find_symbol_by_name(struct dso *dso, const char *name);
+
 struct symbol *symbol__next_by_name(struct symbol *sym);
 
-struct symbol *dso__first_symbol(struct dso *dso, enum map_type type);
-struct symbol *dso__last_symbol(struct dso *dso, enum map_type type);
+struct symbol *dso__first_symbol(struct dso *dso);
+struct symbol *dso__last_symbol(struct dso *dso);
 struct symbol *dso__next_symbol(struct symbol *sym);
 
 enum dso_type dso__type_fd(int fd);
@@ -288,7 +288,7 @@ void symbol__exit(void);
 void symbol__elf_init(void);
 int symbol__annotation_init(void);
 
-struct symbol *symbol__new(u64 start, u64 len, u8 binding, const char *name);
+struct symbol *symbol__new(u64 start, u64 len, u8 binding, u8 type, const char *name);
 size_t __symbol__fprintf_symname_offs(const struct symbol *sym,
 				      const struct addr_location *al,
 				      bool unknown_as_addr,
@@ -300,7 +300,6 @@ size_t __symbol__fprintf_symname(const struct symbol *sym,
 				 bool unknown_as_addr, FILE *fp);
 size_t symbol__fprintf_symname(const struct symbol *sym, FILE *fp);
 size_t symbol__fprintf(struct symbol *sym, FILE *fp);
-bool symbol_type__is_a(char symbol_type, enum map_type map_type);
 bool symbol__restricted_filename(const char *filename,
 				 const char *restricted_filename);
 int symbol__config_symfs(const struct option *opt __maybe_unused,
@@ -308,8 +307,7 @@ int symbol__config_symfs(const struct option *opt __maybe_unused,
 
 int dso__load_sym(struct dso *dso, struct map *map, struct symsrc *syms_ss,
 		  struct symsrc *runtime_ss, int kmodule);
-int dso__synthesize_plt_symbols(struct dso *dso, struct symsrc *ss,
-				struct map *map);
+int dso__synthesize_plt_symbols(struct dso *dso, struct symsrc *ss);
 
 char *dso__demangle_sym(struct dso *dso, int kmodule, const char *elf_name);
 
@@ -317,7 +315,7 @@ void __symbols__insert(struct rb_root *symbols, struct symbol *sym, bool kernel)
 void symbols__insert(struct rb_root *symbols, struct symbol *sym);
 void symbols__fixup_duplicate(struct rb_root *symbols);
 void symbols__fixup_end(struct rb_root *symbols);
-void __map_groups__fixup_end(struct map_groups *mg, enum map_type type);
+void map_groups__fixup_end(struct map_groups *mg);
 
 typedef int (*mapfn_t)(u64 start, u64 len, u64 pgoff, void *data);
 int file__read_maps(int fd, bool exe, mapfn_t mapfn, void *data,
diff --git a/tools/perf/util/symbol_fprintf.c b/tools/perf/util/symbol_fprintf.c
index 6dd2cb88ccbe..ed0205cc7942 100644
--- a/tools/perf/util/symbol_fprintf.c
+++ b/tools/perf/util/symbol_fprintf.c
@@ -58,13 +58,13 @@ size_t symbol__fprintf_symname(const struct symbol *sym, FILE *fp)
 }
 
 size_t dso__fprintf_symbols_by_name(struct dso *dso,
-				    enum map_type type, FILE *fp)
+				    FILE *fp)
 {
 	size_t ret = 0;
 	struct rb_node *nd;
 	struct symbol_name_rb_node *pos;
 
-	for (nd = rb_first(&dso->symbol_names[type]); nd; nd = rb_next(nd)) {
+	for (nd = rb_first(&dso->symbol_names); nd; nd = rb_next(nd)) {
 		pos = rb_entry(nd, struct symbol_name_rb_node, rb_node);
 		fprintf(fp, "%s\n", pos->sym.name);
 	}
diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c
index 68b65b10579b..2048d393ece6 100644
--- a/tools/perf/util/thread.c
+++ b/tools/perf/util/thread.c
@@ -302,23 +302,20 @@ int thread__insert_map(struct thread *thread, struct map *map)
 static int __thread__prepare_access(struct thread *thread)
 {
 	bool initialized = false;
-	int i, err = 0;
+	int err = 0;
+	struct maps *maps = &thread->mg->maps;
+	struct map *map;
 
-	for (i = 0; i < MAP__NR_TYPES; ++i) {
-		struct maps *maps = &thread->mg->maps[i];
-		struct map *map;
+	down_read(&maps->lock);
 
-		down_read(&maps->lock);
-
-		for (map = maps__first(maps); map; map = map__next(map)) {
-			err = unwind__prepare_access(thread, map, &initialized);
-			if (err || initialized)
-				break;
-		}
-
-		up_read(&maps->lock);
+	for (map = maps__first(maps); map; map = map__next(map)) {
+		err = unwind__prepare_access(thread, map, &initialized);
+		if (err || initialized)
+			break;
 	}
 
+	up_read(&maps->lock);
+
 	return err;
 }
 
@@ -335,8 +332,6 @@ static int thread__prepare_access(struct thread *thread)
 static int thread__clone_map_groups(struct thread *thread,
 				    struct thread *parent)
 {
-	int i;
-
 	/* This is new thread, we share map groups for process. */
 	if (thread->pid_ == parent->pid_)
 		return thread__prepare_access(thread);
@@ -348,9 +343,8 @@ static int thread__clone_map_groups(struct thread *thread,
 	}
 
 	/* But this one is new process, copy maps. */
-	for (i = 0; i < MAP__NR_TYPES; ++i)
-		if (map_groups__clone(thread, parent->mg, i) < 0)
-			return -ENOMEM;
+	if (map_groups__clone(thread, parent->mg) < 0)
+		return -ENOMEM;
 
 	return 0;
 }
@@ -371,8 +365,7 @@ int thread__fork(struct thread *thread, struct thread *parent, u64 timestamp)
 	return thread__clone_map_groups(thread, parent);
 }
 
-void thread__find_cpumode_addr_location(struct thread *thread,
-					enum map_type type, u64 addr,
+void thread__find_cpumode_addr_location(struct thread *thread, u64 addr,
 					struct addr_location *al)
 {
 	size_t i;
@@ -384,7 +377,7 @@ void thread__find_cpumode_addr_location(struct thread *thread,
 	};
 
 	for (i = 0; i < ARRAY_SIZE(cpumodes); i++) {
-		thread__find_addr_location(thread, cpumodes[i], type, addr, al);
+		thread__find_symbol(thread, cpumodes[i], addr, al);
 		if (al->map)
 			break;
 	}
diff --git a/tools/perf/util/thread.h b/tools/perf/util/thread.h
index 14d44c3235b8..07606aa6998d 100644
--- a/tools/perf/util/thread.h
+++ b/tools/perf/util/thread.h
@@ -92,16 +92,13 @@ size_t thread__fprintf(struct thread *thread, FILE *fp);
 
 struct thread *thread__main_thread(struct machine *machine, struct thread *thread);
 
-void thread__find_addr_map(struct thread *thread,
-			   u8 cpumode, enum map_type type, u64 addr,
-			   struct addr_location *al);
+struct map *thread__find_map(struct thread *thread, u8 cpumode, u64 addr,
+			     struct addr_location *al);
 
-void thread__find_addr_location(struct thread *thread,
-				u8 cpumode, enum map_type type, u64 addr,
-				struct addr_location *al);
+struct symbol *thread__find_symbol(struct thread *thread, u8 cpumode,
+				   u64 addr, struct addr_location *al);
 
-void thread__find_cpumode_addr_location(struct thread *thread,
-					enum map_type type, u64 addr,
+void thread__find_cpumode_addr_location(struct thread *thread, u64 addr,
 					struct addr_location *al);
 
 static inline void *thread__priv(struct thread *thread)
diff --git a/tools/perf/util/trace-event-info.c b/tools/perf/util/trace-event-info.c
index d7f2113462fb..c85d0d1a65ed 100644
--- a/tools/perf/util/trace-event-info.c
+++ b/tools/perf/util/trace-event-info.c
@@ -103,11 +103,10 @@ out:
 
 static int record_header_files(void)
 {
-	char *path;
+	char *path = get_events_file("header_page");
 	struct stat st;
 	int err = -EIO;
 
-	path = get_tracing_file("events/header_page");
 	if (!path) {
 		pr_debug("can't get tracing/events/header_page");
 		return -ENOMEM;
@@ -128,9 +127,9 @@ static int record_header_files(void)
 		goto out;
 	}
 
-	put_tracing_file(path);
+	put_events_file(path);
 
-	path = get_tracing_file("events/header_event");
+	path = get_events_file("header_event");
 	if (!path) {
 		pr_debug("can't get tracing/events/header_event");
 		err = -ENOMEM;
@@ -154,7 +153,7 @@ static int record_header_files(void)
 
 	err = 0;
 out:
-	put_tracing_file(path);
+	put_events_file(path);
 	return err;
 }
 
@@ -243,7 +242,7 @@ static int record_ftrace_files(struct tracepoint_path *tps)
 	char *path;
 	int ret;
 
-	path = get_tracing_file("events/ftrace");
+	path = get_events_file("ftrace");
 	if (!path) {
 		pr_debug("can't get tracing/events/ftrace");
 		return -ENOMEM;
diff --git a/tools/perf/util/trace-event.c b/tools/perf/util/trace-event.c
index 16a776371d03..1aa368603268 100644
--- a/tools/perf/util/trace-event.c
+++ b/tools/perf/util/trace-event.c
@@ -75,6 +75,7 @@ void trace_event__cleanup(struct trace_event *t)
 static struct event_format*
 tp_format(const char *sys, const char *name)
 {
+	char *tp_dir = get_events_file(sys);
 	struct pevent *pevent = tevent.pevent;
 	struct event_format *event = NULL;
 	char path[PATH_MAX];
@@ -82,8 +83,11 @@ tp_format(const char *sys, const char *name)
 	char *data;
 	int err;
 
-	scnprintf(path, PATH_MAX, "%s/%s/%s/format",
-		  tracing_events_path, sys, name);
+	if (!tp_dir)
+		return ERR_PTR(-errno);
+
+	scnprintf(path, PATH_MAX, "%s/%s/format", tp_dir, name);
+	put_events_file(tp_dir);
 
 	err = filename__read_str(path, &data, &size);
 	if (err)
diff --git a/tools/perf/util/unwind-libdw.c b/tools/perf/util/unwind-libdw.c
index 7bdd239c795c..538db4e5d1e6 100644
--- a/tools/perf/util/unwind-libdw.c
+++ b/tools/perf/util/unwind-libdw.c
@@ -28,10 +28,11 @@ static int __report_module(struct addr_location *al, u64 ip,
 {
 	Dwfl_Module *mod;
 	struct dso *dso = NULL;
-
-	thread__find_addr_location(ui->thread,
-				   PERF_RECORD_MISC_USER,
-				   MAP__FUNCTION, ip, al);
+	/*
+	 * Some callers will use al->sym, so we can't just use the
+	 * cheaper thread__find_map() here.
+	 */
+	thread__find_symbol(ui->thread, PERF_RECORD_MISC_USER, ip, al);
 
 	if (al->map)
 		dso = al->map->dso;
@@ -103,19 +104,7 @@ static int access_dso_mem(struct unwind_info *ui, Dwarf_Addr addr,
 	struct addr_location al;
 	ssize_t size;
 
-	thread__find_addr_map(ui->thread, PERF_RECORD_MISC_USER,
-			      MAP__FUNCTION, addr, &al);
-	if (!al.map) {
-		/*
-		 * We've seen cases (softice) where DWARF unwinder went
-		 * through non executable mmaps, which we need to lookup
-		 * in MAP__VARIABLE tree.
-		 */
-		thread__find_addr_map(ui->thread, PERF_RECORD_MISC_USER,
-				      MAP__VARIABLE, addr, &al);
-	}
-
-	if (!al.map) {
+	if (!thread__find_map(ui->thread, PERF_RECORD_MISC_USER, addr, &al)) {
 		pr_debug("unwind: no map for %lx\n", (unsigned long)addr);
 		return -1;
 	}
diff --git a/tools/perf/util/unwind-libunwind-local.c b/tools/perf/util/unwind-libunwind-local.c
index af873044d33a..6a11bc7e6b27 100644
--- a/tools/perf/util/unwind-libunwind-local.c
+++ b/tools/perf/util/unwind-libunwind-local.c
@@ -366,19 +366,7 @@ static int read_unwind_spec_debug_frame(struct dso *dso,
 static struct map *find_map(unw_word_t ip, struct unwind_info *ui)
 {
 	struct addr_location al;
-
-	thread__find_addr_map(ui->thread, PERF_RECORD_MISC_USER,
-			      MAP__FUNCTION, ip, &al);
-	if (!al.map) {
-		/*
-		 * We've seen cases (softice) where DWARF unwinder went
-		 * through non executable mmaps, which we need to lookup
-		 * in MAP__VARIABLE tree.
-		 */
-		thread__find_addr_map(ui->thread, PERF_RECORD_MISC_USER,
-				      MAP__VARIABLE, ip, &al);
-	}
-	return al.map;
+	return thread__find_map(ui->thread, PERF_RECORD_MISC_USER, ip, &al);
 }
 
 static int
@@ -586,12 +574,9 @@ static int entry(u64 ip, struct thread *thread,
 	struct unwind_entry e;
 	struct addr_location al;
 
-	thread__find_addr_location(thread, PERF_RECORD_MISC_USER,
-				   MAP__FUNCTION, ip, &al);
-
+	e.sym = thread__find_symbol(thread, PERF_RECORD_MISC_USER, ip, &al);
 	e.ip = al.addr;
 	e.map = al.map;
-	e.sym = al.sym;
 
 	pr_debug("unwind: %s:ip = 0x%" PRIx64 " (0x%" PRIx64 ")\n",
 		 al.sym ? al.sym->name : "''",
diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c
index 1019bbc5dbd8..eac5b858a371 100644
--- a/tools/perf/util/util.c
+++ b/tools/perf/util/util.c
@@ -38,11 +38,43 @@ void perf_set_multithreaded(void)
 }
 
 unsigned int page_size;
-int cacheline_size;
+
+#ifdef _SC_LEVEL1_DCACHE_LINESIZE
+#define cache_line_size(cacheline_sizep) *cacheline_sizep = sysconf(_SC_LEVEL1_DCACHE_LINESIZE)
+#else
+static void cache_line_size(int *cacheline_sizep)
+{
+	if (sysfs__read_int("devices/system/cpu/cpu0/cache/index0/coherency_line_size", cacheline_sizep))
+		pr_debug("cannot determine cache line size");
+}
+#endif
+
+int cacheline_size(void)
+{
+	static int size;
+
+	if (!size)
+		cache_line_size(&size);
+
+	return size;
+}
 
 int sysctl_perf_event_max_stack = PERF_MAX_STACK_DEPTH;
 int sysctl_perf_event_max_contexts_per_stack = PERF_MAX_CONTEXTS_PER_STACK;
 
+int sysctl__max_stack(void)
+{
+	int value;
+
+	if (sysctl__read_int("kernel/perf_event_max_stack", &value) == 0)
+		sysctl_perf_event_max_stack = value;
+
+	if (sysctl__read_int("kernel/perf_event_max_contexts_per_stack", &value) == 0)
+		sysctl_perf_event_max_contexts_per_stack = value;
+
+	return sysctl_perf_event_max_stack;
+}
+
 bool test_attr__enabled;
 
 bool perf_host  = true;
diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h
index c9626c206208..dc58254a2b69 100644
--- a/tools/perf/util/util.h
+++ b/tools/perf/util/util.h
@@ -43,7 +43,9 @@ size_t hex_width(u64 v);
 int hex2u64(const char *ptr, u64 *val);
 
 extern unsigned int page_size;
-extern int cacheline_size;
+int __pure cacheline_size(void);
+
+int sysctl__max_stack(void);
 
 int fetch_kernel_version(unsigned int *puint,
 			 char *str, size_t str_sz);
diff --git a/tools/perf/util/vdso.c b/tools/perf/util/vdso.c
index 0acb1ec0e2f0..741af209b19d 100644
--- a/tools/perf/util/vdso.c
+++ b/tools/perf/util/vdso.c
@@ -139,12 +139,10 @@ static enum dso_type machine__thread_dso_type(struct machine *machine,
 					      struct thread *thread)
 {
 	enum dso_type dso_type = DSO__TYPE_UNKNOWN;
-	struct map *map;
-	struct dso *dso;
+	struct map *map = map_groups__first(thread->mg);
 
-	map = map_groups__first(thread->mg, MAP__FUNCTION);
 	for (; map ; map = map_groups__next(map)) {
-		dso = map->dso;
+		struct dso *dso = map->dso;
 		if (!dso || dso->long_name[0] != '/')
 			continue;
 		dso_type = dso__type(dso, machine);