Merge branch 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull perf updates from Ingo Molnar: "Kernel side changes mostly consist of work on x86 PMU drivers: - x86 Intel PT (hardware CPU tracer) improvements (Alexander Shishkin) - x86 Intel CQM (cache quality monitoring) improvements (Thomas Gleixner) - x86 Intel PEBSv3 support (Peter Zijlstra) - x86 Intel PEBS interrupt batching support for lower overhead sampling (Zheng Yan, Kan Liang) - x86 PMU scheduler fixes and improvements (Peter Zijlstra) There's too many tooling improvements to list them all - here are a few select highlights: 'perf bench': - Introduce new 'perf bench futex' benchmark: 'wake-parallel', to measure parallel waker threads generating contention for kernel locks (hb->lock). (Davidlohr Bueso) 'perf top', 'perf report': - Allow disabling/enabling events dynamicaly in 'perf top': a 'perf top' session can instantly become a 'perf report' one, i.e. going from dynamic analysis to a static one, returning to a dynamic one is possible, to toogle the modes, just press 'f' to 'freeze/unfreeze' the sampling. (Arnaldo Carvalho de Melo) - Make Ctrl-C stop processing on TUI, allowing interrupting the load of big perf.data files (Namhyung Kim) 'perf probe': (Masami Hiramatsu) - Support glob wildcards for function name - Support $params special probe argument: Collect all function arguments - Make --line checks validate C-style function name. - Add --no-inlines option to avoid searching inline functions - Greatly speed up 'perf probe --list' by caching debuginfo. - Improve --filter support for 'perf probe', allowing using its arguments on other commands, as --add, --del, etc. 'perf sched': - Add option in 'perf sched' to merge like comms to lat output (Josef Bacik) Plus tons of infrastructure work - in particular preparation for upcoming threaded perf report support, but also lots of other work - and fixes and other improvements. See (much) more details in the shortlog and in the git log" * 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (305 commits) perf tools: Configurable per thread proc map processing time out perf tools: Add time out to force stop proc map processing perf report: Fix sort__sym_cmp to also compare end of symbol perf hists browser: React to unassigned hotkey pressing perf top: Tell the user how to unfreeze events after pressing 'f' perf hists browser: Honour the help line provided by builtin-{top,report}.c perf hists browser: Do not exit when 'f' is pressed in 'report' mode perf top: Replace CTRL+z with 'f' as hotkey for enable/disable events perf annotate: Rename source_line_percent to source_line_samples perf annotate: Display total number of samples with --show-total-period perf tools: Ensure thread-stack is flushed perf top: Allow disabling/enabling events dynamicly perf evlist: Add toggle_enable() method perf trace: Fix race condition at the end of started workloads perf probe: Speed up perf probe --list by caching debuginfo perf probe: Show usage even if the last event is skipped perf tools: Move libtraceevent dynamic list to separated LDFLAGS variable perf tools: Fix a problem when opening old perf.data with different byte order perf tools: Ignore .config-detected in .gitignore perf probe: Fix to return error if no probe is added ...
author: Linus Torvalds <torvalds@linux-foundation.org> 2015-06-22 15:19:21 -0700
committer: Linus Torvalds <torvalds@linux-foundation.org> 2015-06-22 15:19:21 -0700
commit: c58267e9fa7b0345dd9006939254701e3622ca6a (patch)
tree: 9a96adabaa1c61ecbb9e5e8653d5085dad27ef07
parent: 1bf7067c6e173dc10411704db48338ed69c05565 (diff)
parent: a9a3cd900fbbcbf837d65653105e7bfc583ced09 (diff)
download: lwn-c58267e9fa7b0345dd9006939254701e3622ca6a.tar.gz
lwn-c58267e9fa7b0345dd9006939254701e3622ca6a.zip
211 files changed, 10821 insertions, 2891 deletions
diff --git a/MAINTAINERS b/MAINTAINERS
index d8afd2953678..4303a642a2e5 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -7634,7 +7634,6 @@ F:	kernel/delayacct.c
 
 PERFORMANCE EVENTS SUBSYSTEM
 M:	Peter Zijlstra <a.p.zijlstra@chello.nl>
-M:	Paul Mackerras <paulus@samba.org>
 M:	Ingo Molnar <mingo@redhat.com>
 M:	Arnaldo Carvalho de Melo <acme@kernel.org>
 L:	linux-kernel@vger.kernel.org
diff --git a/Makefile b/Makefile
index f5c8983aeeb7..6c6f14628f32 100644
--- a/Makefile
+++ b/Makefile
@@ -215,7 +215,6 @@ VPATH		:= $(srctree)$(if $(KBUILD_EXTMOD),:$(KBUILD_EXTMOD))
 
 export srctree objtree VPATH
 
-
 # SUBARCH tells the usermode build what the underlying arch is.  That is set
 # first, and if a usermode build is happening, the "ARCH=um" on the command
 # line overrides the setting of ARCH below.  If a native build is happening,
@@ -1497,11 +1496,11 @@ image_name:
 # Clear a bunch of variables before executing the submake
 tools/: FORCE
 	$(Q)mkdir -p $(objtree)/tools
-	$(Q)$(MAKE) LDFLAGS= MAKEFLAGS="$(filter --j% -j,$(MAKEFLAGS))" O=$(objtree) subdir=tools -C $(src)/tools/
+	$(Q)$(MAKE) LDFLAGS= MAKEFLAGS="$(filter --j% -j,$(MAKEFLAGS))" O=$(O) subdir=tools -C $(src)/tools/
 
 tools/%: FORCE
 	$(Q)mkdir -p $(objtree)/tools
-	$(Q)$(MAKE) LDFLAGS= MAKEFLAGS="$(filter --j% -j,$(MAKEFLAGS))" O=$(objtree) subdir=tools -C $(src)/tools/ $*
+	$(Q)$(MAKE) LDFLAGS= MAKEFLAGS="$(filter --j% -j,$(MAKEFLAGS))" O=$(O) subdir=tools -C $(src)/tools/ $*
 
 # Single targets
 # ---------------------------------------------------------------------------
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index 4f7001f28936..9560d0fc6fa6 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -881,10 +881,7 @@ int x86_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign)
 			if (x86_pmu.commit_scheduling)
 				x86_pmu.commit_scheduling(cpuc, i, assign[i]);
 		}
-	}
-
-	if (!assign || unsched) {
-
+	} else {
 		for (i = 0; i < n; i++) {
 			e = cpuc->event_list[i];
 			/*
@@ -1097,13 +1094,16 @@ int x86_perf_event_set_period(struct perf_event *event)
 
 	per_cpu(pmc_prev_left[idx], smp_processor_id()) = left;
 
-	/*
-	 * The hw event starts counting from this event offset,
-	 * mark it to be able to extra future deltas:
-	 */
-	local64_set(&hwc->prev_count, (u64)-left);
+	if (!(hwc->flags & PERF_X86_EVENT_AUTO_RELOAD) ||
+	    local64_read(&hwc->prev_count) != (u64)-left) {
+		/*
+		 * The hw event starts counting from this event offset,
+		 * mark it to be able to extra future deltas:
+		 */
+		local64_set(&hwc->prev_count, (u64)-left);
 
-	wrmsrl(hwc->event_base, (u64)(-left) & x86_pmu.cntval_mask);
+		wrmsrl(hwc->event_base, (u64)(-left) & x86_pmu.cntval_mask);
+	}
 
 	/*
 	 * Due to erratum on certan cpu we need
diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h
index ef78516850fb..74089bcb6d74 100644
--- a/arch/x86/kernel/cpu/perf_event.h
+++ b/arch/x86/kernel/cpu/perf_event.h
@@ -75,6 +75,8 @@ struct event_constraint {
 #define PERF_X86_EVENT_DYNAMIC		0x0080 /* dynamic alloc'd constraint */
 #define PERF_X86_EVENT_RDPMC_ALLOWED	0x0100 /* grant rdpmc permission */
 #define PERF_X86_EVENT_EXCL_ACCT	0x0200 /* accounted EXCL event */
+#define PERF_X86_EVENT_AUTO_RELOAD	0x0400 /* use PEBS auto-reload */
+#define PERF_X86_EVENT_FREERUNNING	0x0800 /* use freerunning PEBS */
 
 
 struct amd_nb {
@@ -88,6 +90,18 @@ struct amd_nb {
 #define MAX_PEBS_EVENTS		8
 
 /*
+ * Flags PEBS can handle without an PMI.
+ *
+ * TID can only be handled by flushing at context switch.
+ *
+ */
+#define PEBS_FREERUNNING_FLAGS \
+	(PERF_SAMPLE_IP | PERF_SAMPLE_TID | PERF_SAMPLE_ADDR | \
+	PERF_SAMPLE_ID | PERF_SAMPLE_CPU | PERF_SAMPLE_STREAM_ID | \
+	PERF_SAMPLE_DATA_SRC | PERF_SAMPLE_IDENTIFIER | \
+	PERF_SAMPLE_TRANSACTION)
+
+/*
  * A debug store configuration.
  *
  * We only support architectures that use 64bit fields.
@@ -133,7 +147,6 @@ enum intel_excl_state_type {
 };
 
 struct intel_excl_states {
-	enum intel_excl_state_type init_state[X86_PMC_IDX_MAX];
 	enum intel_excl_state_type state[X86_PMC_IDX_MAX];
 	bool sched_started; /* true if scheduling has started */
 };
@@ -527,10 +540,10 @@ struct x86_pmu {
 	void		(*put_event_constraints)(struct cpu_hw_events *cpuc,
 						 struct perf_event *event);
 
-	void		(*commit_scheduling)(struct cpu_hw_events *cpuc, int idx, int cntr);
-
 	void		(*start_scheduling)(struct cpu_hw_events *cpuc);
 
+	void		(*commit_scheduling)(struct cpu_hw_events *cpuc, int idx, int cntr);
+
 	void		(*stop_scheduling)(struct cpu_hw_events *cpuc);
 
 	struct event_constraint *event_constraints;
@@ -866,6 +879,8 @@ void intel_pmu_pebs_enable_all(void);
 
 void intel_pmu_pebs_disable_all(void);
 
+void intel_pmu_pebs_sched_task(struct perf_event_context *ctx, bool sched_in);
+
 void intel_ds_init(void);
 
 void intel_pmu_lbr_sched_task(struct perf_event_context *ctx, bool sched_in);
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index a1e35c9f06b9..d455e2a61287 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -1903,9 +1903,8 @@ static void
 intel_start_scheduling(struct cpu_hw_events *cpuc)
 {
 	struct intel_excl_cntrs *excl_cntrs = cpuc->excl_cntrs;
-	struct intel_excl_states *xl, *xlo;
+	struct intel_excl_states *xl;
 	int tid = cpuc->excl_thread_id;
-	int o_tid = 1 - tid; /* sibling thread */
 
 	/*
 	 * nothing needed if in group validation mode
@@ -1916,10 +1915,9 @@ intel_start_scheduling(struct cpu_hw_events *cpuc)
 	/*
 	 * no exclusion needed
 	 */
-	if (!excl_cntrs)
+	if (WARN_ON_ONCE(!excl_cntrs))
 		return;
 
-	xlo = &excl_cntrs->states[o_tid];
 	xl = &excl_cntrs->states[tid];
 
 	xl->sched_started = true;
@@ -1928,22 +1926,41 @@ intel_start_scheduling(struct cpu_hw_events *cpuc)
 	 * in stop_event_scheduling()
 	 * makes scheduling appear as a transaction
 	 */
-	WARN_ON_ONCE(!irqs_disabled());
 	raw_spin_lock(&excl_cntrs->lock);
+}
 
-	/*
-	 * save initial state of sibling thread
-	 */
-	memcpy(xlo->init_state, xlo->state, sizeof(xlo->init_state));
+static void intel_commit_scheduling(struct cpu_hw_events *cpuc, int idx, int cntr)
+{
+	struct intel_excl_cntrs *excl_cntrs = cpuc->excl_cntrs;
+	struct event_constraint *c = cpuc->event_constraint[idx];
+	struct intel_excl_states *xl;
+	int tid = cpuc->excl_thread_id;
+
+	if (cpuc->is_fake || !is_ht_workaround_enabled())
+		return;
+
+	if (WARN_ON_ONCE(!excl_cntrs))
+		return;
+
+	if (!(c->flags & PERF_X86_EVENT_DYNAMIC))
+		return;
+
+	xl = &excl_cntrs->states[tid];
+
+	lockdep_assert_held(&excl_cntrs->lock);
+
+	if (c->flags & PERF_X86_EVENT_EXCL)
+		xl->state[cntr] = INTEL_EXCL_EXCLUSIVE;
+	else
+		xl->state[cntr] = INTEL_EXCL_SHARED;
 }
 
 static void
 intel_stop_scheduling(struct cpu_hw_events *cpuc)
 {
 	struct intel_excl_cntrs *excl_cntrs = cpuc->excl_cntrs;
-	struct intel_excl_states *xl, *xlo;
+	struct intel_excl_states *xl;
 	int tid = cpuc->excl_thread_id;
-	int o_tid = 1 - tid; /* sibling thread */
 
 	/*
 	 * nothing needed if in group validation mode
@@ -1953,17 +1970,11 @@ intel_stop_scheduling(struct cpu_hw_events *cpuc)
 	/*
 	 * no exclusion needed
 	 */
-	if (!excl_cntrs)
+	if (WARN_ON_ONCE(!excl_cntrs))
 		return;
 
-	xlo = &excl_cntrs->states[o_tid];
 	xl = &excl_cntrs->states[tid];
 
-	/*
-	 * make new sibling thread state visible
-	 */
-	memcpy(xlo->state, xlo->init_state, sizeof(xlo->state));
-
 	xl->sched_started = false;
 	/*
 	 * release shared state lock (acquired in intel_start_scheduling())
@@ -1975,12 +1986,10 @@ static struct event_constraint *
 intel_get_excl_constraints(struct cpu_hw_events *cpuc, struct perf_event *event,
 			   int idx, struct event_constraint *c)
 {
-	struct event_constraint *cx;
 	struct intel_excl_cntrs *excl_cntrs = cpuc->excl_cntrs;
-	struct intel_excl_states *xl, *xlo;
-	int is_excl, i;
+	struct intel_excl_states *xlo;
 	int tid = cpuc->excl_thread_id;
-	int o_tid = 1 - tid; /* alternate */
+	int is_excl, i;
 
 	/*
 	 * validating a group does not require
@@ -1992,27 +2001,8 @@ intel_get_excl_constraints(struct cpu_hw_events *cpuc, struct perf_event *event,
 	/*
 	 * no exclusion needed
 	 */
-	if (!excl_cntrs)
+	if (WARN_ON_ONCE(!excl_cntrs))
 		return c;
-	/*
-	 * event requires exclusive counter access
-	 * across HT threads
-	 */
-	is_excl = c->flags & PERF_X86_EVENT_EXCL;
-	if (is_excl && !(event->hw.flags & PERF_X86_EVENT_EXCL_ACCT)) {
-		event->hw.flags |= PERF_X86_EVENT_EXCL_ACCT;
-		if (!cpuc->n_excl++)
-			WRITE_ONCE(excl_cntrs->has_exclusive[tid], 1);
-	}
-
-	/*
-	 * xl = state of current HT
-	 * xlo = state of sibling HT
-	 */
-	xl = &excl_cntrs->states[tid];
-	xlo = &excl_cntrs->states[o_tid];
-
-	cx = c;
 
 	/*
 	 * because we modify the constraint, we need
@@ -2023,10 +2013,7 @@ intel_get_excl_constraints(struct cpu_hw_events *cpuc, struct perf_event *event,
 	 * been cloned (marked dynamic)
 	 */
 	if (!(c->flags & PERF_X86_EVENT_DYNAMIC)) {
-
-		/* sanity check */
-		if (idx < 0)
-			return &emptyconstraint;
+		struct event_constraint *cx;
 
 		/*
 		 * grab pre-allocated constraint entry
@@ -2037,13 +2024,14 @@ intel_get_excl_constraints(struct cpu_hw_events *cpuc, struct perf_event *event,
 		 * initialize dynamic constraint
 		 * with static constraint
 		 */
-		memcpy(cx, c, sizeof(*cx));
+		*cx = *c;
 
 		/*
 		 * mark constraint as dynamic, so we
 		 * can free it later on
 		 */
 		cx->flags |= PERF_X86_EVENT_DYNAMIC;
+		c = cx;
 	}
 
 	/*
@@ -2054,6 +2042,22 @@ intel_get_excl_constraints(struct cpu_hw_events *cpuc, struct perf_event *event,
 	 */
 
 	/*
+	 * state of sibling HT
+	 */
+	xlo = &excl_cntrs->states[tid ^ 1];
+
+	/*
+	 * event requires exclusive counter access
+	 * across HT threads
+	 */
+	is_excl = c->flags & PERF_X86_EVENT_EXCL;
+	if (is_excl && !(event->hw.flags & PERF_X86_EVENT_EXCL_ACCT)) {
+		event->hw.flags |= PERF_X86_EVENT_EXCL_ACCT;
+		if (!cpuc->n_excl++)
+			WRITE_ONCE(excl_cntrs->has_exclusive[tid], 1);
+	}
+
+	/*
 	 * Modify static constraint with current dynamic
 	 * state of thread
 	 *
@@ -2061,37 +2065,37 @@ intel_get_excl_constraints(struct cpu_hw_events *cpuc, struct perf_event *event,
 	 * SHARED   : sibling counter measuring non-exclusive event
 	 * UNUSED   : sibling counter unused
 	 */
-	for_each_set_bit(i, cx->idxmsk, X86_PMC_IDX_MAX) {
+	for_each_set_bit(i, c->idxmsk, X86_PMC_IDX_MAX) {
 		/*
 		 * exclusive event in sibling counter
 		 * our corresponding counter cannot be used
 		 * regardless of our event
 		 */
-		if (xl->state[i] == INTEL_EXCL_EXCLUSIVE)
-			__clear_bit(i, cx->idxmsk);
+		if (xlo->state[i] == INTEL_EXCL_EXCLUSIVE)
+			__clear_bit(i, c->idxmsk);
 		/*
 		 * if measuring an exclusive event, sibling
 		 * measuring non-exclusive, then counter cannot
 		 * be used
 		 */
-		if (is_excl && xl->state[i] == INTEL_EXCL_SHARED)
-			__clear_bit(i, cx->idxmsk);
+		if (is_excl && xlo->state[i] == INTEL_EXCL_SHARED)
+			__clear_bit(i, c->idxmsk);
 	}
 
 	/*
 	 * recompute actual bit weight for scheduling algorithm
 	 */
-	cx->weight = hweight64(cx->idxmsk64);
+	c->weight = hweight64(c->idxmsk64);
 
 	/*
 	 * if we return an empty mask, then switch
 	 * back to static empty constraint to avoid
 	 * the cost of freeing later on
 	 */
-	if (cx->weight == 0)
-		cx = &emptyconstraint;
+	if (c->weight == 0)
+		c = &emptyconstraint;
 
-	return cx;
+	return c;
 }
 
 static struct event_constraint *
@@ -2124,10 +2128,8 @@ static void intel_put_excl_constraints(struct cpu_hw_events *cpuc,
 {
 	struct hw_perf_event *hwc = &event->hw;
 	struct intel_excl_cntrs *excl_cntrs = cpuc->excl_cntrs;
-	struct intel_excl_states *xlo, *xl;
-	unsigned long flags = 0; /* keep compiler happy */
 	int tid = cpuc->excl_thread_id;
-	int o_tid = 1 - tid;
+	struct intel_excl_states *xl;
 
 	/*
 	 * nothing needed if in group validation mode
@@ -2135,13 +2137,9 @@ static void intel_put_excl_constraints(struct cpu_hw_events *cpuc,
 	if (cpuc->is_fake)
 		return;
 
-	WARN_ON_ONCE(!excl_cntrs);
-
-	if (!excl_cntrs)
+	if (WARN_ON_ONCE(!excl_cntrs))
 		return;
 
-	xl = &excl_cntrs->states[tid];
-	xlo = &excl_cntrs->states[o_tid];
 	if (hwc->flags & PERF_X86_EVENT_EXCL_ACCT) {
 		hwc->flags &= ~PERF_X86_EVENT_EXCL_ACCT;
 		if (!--cpuc->n_excl)
@@ -2149,22 +2147,25 @@ static void intel_put_excl_constraints(struct cpu_hw_events *cpuc,
 	}
 
 	/*
-	 * put_constraint may be called from x86_schedule_events()
-	 * which already has the lock held so here make locking
-	 * conditional
+	 * If event was actually assigned, then mark the counter state as
+	 * unused now.
 	 */
-	if (!xl->sched_started)
-		raw_spin_lock_irqsave(&excl_cntrs->lock, flags);
+	if (hwc->idx >= 0) {
+		xl = &excl_cntrs->states[tid];
 
-	/*
-	 * if event was actually assigned, then mark the
-	 * counter state as unused now
-	 */
-	if (hwc->idx >= 0)
-		xlo->state[hwc->idx] = INTEL_EXCL_UNUSED;
+		/*
+		 * put_constraint may be called from x86_schedule_events()
+		 * which already has the lock held so here make locking
+		 * conditional.
+		 */
+		if (!xl->sched_started)
+			raw_spin_lock(&excl_cntrs->lock);
 
-	if (!xl->sched_started)
-		raw_spin_unlock_irqrestore(&excl_cntrs->lock, flags);
+		xl->state[hwc->idx] = INTEL_EXCL_UNUSED;
+
+		if (!xl->sched_started)
+			raw_spin_unlock(&excl_cntrs->lock);
+	}
 }
 
 static void
@@ -2196,41 +2197,6 @@ static void intel_put_event_constraints(struct cpu_hw_events *cpuc,
 		intel_put_excl_constraints(cpuc, event);
 }
 
-static void intel_commit_scheduling(struct cpu_hw_events *cpuc, int idx, int cntr)
-{
-	struct intel_excl_cntrs *excl_cntrs = cpuc->excl_cntrs;
-	struct event_constraint *c = cpuc->event_constraint[idx];
-	struct intel_excl_states *xlo, *xl;
-	int tid = cpuc->excl_thread_id;
-	int o_tid = 1 - tid;
-	int is_excl;
-
-	if (cpuc->is_fake || !c)
-		return;
-
-	is_excl = c->flags & PERF_X86_EVENT_EXCL;
-
-	if (!(c->flags & PERF_X86_EVENT_DYNAMIC))
-		return;
-
-	WARN_ON_ONCE(!excl_cntrs);
-
-	if (!excl_cntrs)
-		return;
-
-	xl = &excl_cntrs->states[tid];
-	xlo = &excl_cntrs->states[o_tid];
-
-	WARN_ON_ONCE(!raw_spin_is_locked(&excl_cntrs->lock));
-
-	if (cntr >= 0) {
-		if (is_excl)
-			xlo->init_state[cntr] = INTEL_EXCL_EXCLUSIVE;
-		else
-			xlo->init_state[cntr] = INTEL_EXCL_SHARED;
-	}
-}
-
 static void intel_pebs_aliases_core2(struct perf_event *event)
 {
 	if ((event->hw.config & X86_RAW_EVENT_MASK) == 0x003c) {
@@ -2294,8 +2260,15 @@ static int intel_pmu_hw_config(struct perf_event *event)
 	if (ret)
 		return ret;
 
-	if (event->attr.precise_ip && x86_pmu.pebs_aliases)
-		x86_pmu.pebs_aliases(event);
+	if (event->attr.precise_ip) {
+		if (!event->attr.freq) {
+			event->hw.flags |= PERF_X86_EVENT_AUTO_RELOAD;
+			if (!(event->attr.sample_type & ~PEBS_FREERUNNING_FLAGS))
+				event->hw.flags |= PERF_X86_EVENT_FREERUNNING;
+		}
+		if (x86_pmu.pebs_aliases)
+			x86_pmu.pebs_aliases(event);
+	}
 
 	if (needs_branch_stack(event)) {
 		ret = intel_pmu_setup_lbr_filter(event);
@@ -2544,19 +2517,11 @@ struct intel_shared_regs *allocate_shared_regs(int cpu)
 static struct intel_excl_cntrs *allocate_excl_cntrs(int cpu)
 {
 	struct intel_excl_cntrs *c;
-	int i;
 
 	c = kzalloc_node(sizeof(struct intel_excl_cntrs),
 			 GFP_KERNEL, cpu_to_node(cpu));
 	if (c) {
 		raw_spin_lock_init(&c->lock);
-		for (i = 0; i < X86_PMC_IDX_MAX; i++) {
-			c->states[0].state[i] = INTEL_EXCL_UNUSED;
-			c->states[0].init_state[i] = INTEL_EXCL_UNUSED;
-
-			c->states[1].state[i] = INTEL_EXCL_UNUSED;
-			c->states[1].init_state[i] = INTEL_EXCL_UNUSED;
-		}
 		c->core_id = -1;
 	}
 	return c;
@@ -2677,6 +2642,15 @@ static void intel_pmu_cpu_dying(int cpu)
 	fini_debug_store_on_cpu(cpu);
 }
 
+static void intel_pmu_sched_task(struct perf_event_context *ctx,
+				 bool sched_in)
+{
+	if (x86_pmu.pebs_active)
+		intel_pmu_pebs_sched_task(ctx, sched_in);
+	if (x86_pmu.lbr_nr)
+		intel_pmu_lbr_sched_task(ctx, sched_in);
+}
+
 PMU_FORMAT_ATTR(offcore_rsp, "config1:0-63");
 
 PMU_FORMAT_ATTR(ldlat, "config1:0-15");
@@ -2766,7 +2740,7 @@ static __initconst const struct x86_pmu intel_pmu = {
 	.cpu_starting		= intel_pmu_cpu_starting,
 	.cpu_dying		= intel_pmu_cpu_dying,
 	.guest_get_msrs		= intel_guest_get_msrs,
-	.sched_task		= intel_pmu_lbr_sched_task,
+	.sched_task		= intel_pmu_sched_task,
 };
 
 static __init void intel_clovertown_quirk(void)
@@ -2939,8 +2913,8 @@ static __init void intel_ht_bug(void)
 {
 	x86_pmu.flags |= PMU_FL_EXCL_CNTRS | PMU_FL_EXCL_ENABLED;
 
-	x86_pmu.commit_scheduling = intel_commit_scheduling;
 	x86_pmu.start_scheduling = intel_start_scheduling;
+	x86_pmu.commit_scheduling = intel_commit_scheduling;
 	x86_pmu.stop_scheduling = intel_stop_scheduling;
 }
 
@@ -3396,8 +3370,8 @@ static __init int fixup_ht_bug(void)
 
 	x86_pmu.flags &= ~(PMU_FL_EXCL_CNTRS | PMU_FL_EXCL_ENABLED);
 
-	x86_pmu.commit_scheduling = NULL;
 	x86_pmu.start_scheduling = NULL;
+	x86_pmu.commit_scheduling = NULL;
 	x86_pmu.stop_scheduling = NULL;
 
 	watchdog_nmi_enable_all();
diff --git a/arch/x86/kernel/cpu/perf_event_intel_cqm.c b/arch/x86/kernel/cpu/perf_event_intel_cqm.c
index e4d1b8b738fa..188076161c1b 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_cqm.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_cqm.c
@@ -13,16 +13,35 @@
 #define MSR_IA32_QM_CTR		0x0c8e
 #define MSR_IA32_QM_EVTSEL	0x0c8d
 
-static unsigned int cqm_max_rmid = -1;
+static u32 cqm_max_rmid = -1;
 static unsigned int cqm_l3_scale; /* supposedly cacheline size */
 
-struct intel_cqm_state {
-	raw_spinlock_t		lock;
-	int			rmid;
-	int			cnt;
+/**
+ * struct intel_pqr_state - State cache for the PQR MSR
+ * @rmid:		The cached Resource Monitoring ID
+ * @closid:		The cached Class Of Service ID
+ * @rmid_usecnt:	The usage counter for rmid
+ *
+ * The upper 32 bits of MSR_IA32_PQR_ASSOC contain closid and the
+ * lower 10 bits rmid. The update to MSR_IA32_PQR_ASSOC always
+ * contains both parts, so we need to cache them.
+ *
+ * The cache also helps to avoid pointless updates if the value does
+ * not change.
+ */
+struct intel_pqr_state {
+	u32			rmid;
+	u32			closid;
+	int			rmid_usecnt;
 };
 
-static DEFINE_PER_CPU(struct intel_cqm_state, cqm_state);
+/*
+ * The cached intel_pqr_state is strictly per CPU and can never be
+ * updated from a remote CPU. Both functions which modify the state
+ * (intel_cqm_event_start and intel_cqm_event_stop) are called with
+ * interrupts disabled, which is sufficient for the protection.
+ */
+static DEFINE_PER_CPU(struct intel_pqr_state, pqr_state);
 
 /*
  * Protects cache_cgroups and cqm_rmid_free_lru and cqm_rmid_limbo_lru.
@@ -57,7 +76,7 @@ static cpumask_t cqm_cpumask;
  * near-zero occupancy value, i.e. no cachelines are tagged with this
  * RMID, once __intel_cqm_rmid_rotate() returns.
  */
-static unsigned int intel_cqm_rotation_rmid;
+static u32 intel_cqm_rotation_rmid;
 
 #define INVALID_RMID		(-1)
 
@@ -69,7 +88,7 @@ static unsigned int intel_cqm_rotation_rmid;
  * Likewise, an rmid value of -1 is used to indicate "no rmid currently
  * assigned" and is used as part of the rotation code.
  */
-static inline bool __rmid_valid(unsigned int rmid)
+static inline bool __rmid_valid(u32 rmid)
 {
 	if (!rmid || rmid == INVALID_RMID)
 		return false;
@@ -77,7 +96,7 @@ static inline bool __rmid_valid(unsigned int rmid)
 	return true;
 }
 
-static u64 __rmid_read(unsigned int rmid)
+static u64 __rmid_read(u32 rmid)
 {
 	u64 val;
 
@@ -102,7 +121,7 @@ enum rmid_recycle_state {
 };
 
 struct cqm_rmid_entry {
-	unsigned int rmid;
+	u32 rmid;
 	enum rmid_recycle_state state;
 	struct list_head list;
 	unsigned long queue_time;
@@ -147,7 +166,7 @@ static LIST_HEAD(cqm_rmid_limbo_lru);
  */
 static struct cqm_rmid_entry **cqm_rmid_ptrs;
 
-static inline struct cqm_rmid_entry *__rmid_entry(int rmid)
+static inline struct cqm_rmid_entry *__rmid_entry(u32 rmid)
 {
 	struct cqm_rmid_entry *entry;
 
@@ -162,7 +181,7 @@ static inline struct cqm_rmid_entry *__rmid_entry(int rmid)
  *
  * We expect to be called with cache_mutex held.
  */
-static int __get_rmid(void)
+static u32 __get_rmid(void)
 {
 	struct cqm_rmid_entry *entry;
 
@@ -177,7 +196,7 @@ static int __get_rmid(void)
 	return entry->rmid;
 }
 
-static void __put_rmid(unsigned int rmid)
+static void __put_rmid(u32 rmid)
 {
 	struct cqm_rmid_entry *entry;
 
@@ -372,7 +391,7 @@ static bool __conflict_event(struct perf_event *a, struct perf_event *b)
 }
 
 struct rmid_read {
-	unsigned int rmid;
+	u32 rmid;
 	atomic64_t value;
 };
 
@@ -381,12 +400,11 @@ static void __intel_cqm_event_count(void *info);
 /*
  * Exchange the RMID of a group of events.
  */
-static unsigned int
-intel_cqm_xchg_rmid(struct perf_event *group, unsigned int rmid)
+static u32 intel_cqm_xchg_rmid(struct perf_event *group, u32 rmid)
 {
 	struct perf_event *event;
-	unsigned int old_rmid = group->hw.cqm_rmid;
 	struct list_head *head = &group->hw.cqm_group_entry;
+	u32 old_rmid = group->hw.cqm_rmid;
 
 	lockdep_assert_held(&cache_mutex);
 
@@ -451,7 +469,7 @@ static void intel_cqm_stable(void *arg)
  * If we have group events waiting for an RMID that don't conflict with
  * events already running, assign @rmid.
  */
-static bool intel_cqm_sched_in_event(unsigned int rmid)
+static bool intel_cqm_sched_in_event(u32 rmid)
 {
 	struct perf_event *leader, *event;
 
@@ -598,7 +616,7 @@ static bool intel_cqm_rmid_stabilize(unsigned int *available)
 static void __intel_cqm_pick_and_rotate(struct perf_event *next)
 {
 	struct perf_event *rotor;
-	unsigned int rmid;
+	u32 rmid;
 
 	lockdep_assert_held(&cache_mutex);
 
@@ -626,7 +644,7 @@ static void __intel_cqm_pick_and_rotate(struct perf_event *next)
 static void intel_cqm_sched_out_conflicting_events(struct perf_event *event)
 {
 	struct perf_event *group, *g;
-	unsigned int rmid;
+	u32 rmid;
 
 	lockdep_assert_held(&cache_mutex);
 
@@ -828,8 +846,8 @@ static void intel_cqm_setup_event(struct perf_event *event,
 				  struct perf_event **group)
 {
 	struct perf_event *iter;
-	unsigned int rmid;
 	bool conflict = false;
+	u32 rmid;
 
 	list_for_each_entry(iter, &cache_groups, hw.cqm_groups_entry) {
 		rmid = iter->hw.cqm_rmid;
@@ -860,7 +878,7 @@ static void intel_cqm_setup_event(struct perf_event *event,
 static void intel_cqm_event_read(struct perf_event *event)
 {
 	unsigned long flags;
-	unsigned int rmid;
+	u32 rmid;
 	u64 val;
 
 	/*
@@ -961,55 +979,48 @@ out:
 
 static void intel_cqm_event_start(struct perf_event *event, int mode)
 {
-	struct intel_cqm_state *state = this_cpu_ptr(&cqm_state);
-	unsigned int rmid = event->hw.cqm_rmid;
-	unsigned long flags;
+	struct intel_pqr_state *state = this_cpu_ptr(&pqr_state);
+	u32 rmid = event->hw.cqm_rmid;
 
 	if (!(event->hw.cqm_state & PERF_HES_STOPPED))
 		return;
 
 	event->hw.cqm_state &= ~PERF_HES_STOPPED;
 
-	raw_spin_lock_irqsave(&state->lock, flags);
-
-	if (state->cnt++)
-		WARN_ON_ONCE(state->rmid != rmid);
-	else
+	if (state->rmid_usecnt++) {
+		if (!WARN_ON_ONCE(state->rmid != rmid))
+			return;
+	} else {
 		WARN_ON_ONCE(state->rmid);
+	}
 
 	state->rmid = rmid;
-	wrmsrl(MSR_IA32_PQR_ASSOC, state->rmid);
-
-	raw_spin_unlock_irqrestore(&state->lock, flags);
+	wrmsr(MSR_IA32_PQR_ASSOC, rmid, state->closid);
 }
 
 static void intel_cqm_event_stop(struct perf_event *event, int mode)
 {
-	struct intel_cqm_state *state = this_cpu_ptr(&cqm_state);
-	unsigned long flags;
+	struct intel_pqr_state *state = this_cpu_ptr(&pqr_state);
 
 	if (event->hw.cqm_state & PERF_HES_STOPPED)
 		return;
 
 	event->hw.cqm_state |= PERF_HES_STOPPED;
 
-	raw_spin_lock_irqsave(&state->lock, flags);
 	intel_cqm_event_read(event);
 
-	if (!--state->cnt) {
+	if (!--state->rmid_usecnt) {
 		state->rmid = 0;
-		wrmsrl(MSR_IA32_PQR_ASSOC, 0);
+		wrmsr(MSR_IA32_PQR_ASSOC, 0, state->closid);
 	} else {
 		WARN_ON_ONCE(!state->rmid);
 	}
-
-	raw_spin_unlock_irqrestore(&state->lock, flags);
 }
 
 static int intel_cqm_event_add(struct perf_event *event, int mode)
 {
 	unsigned long flags;
-	unsigned int rmid;
+	u32 rmid;
 
 	raw_spin_lock_irqsave(&cache_lock, flags);
 
@@ -1024,11 +1035,6 @@ static int intel_cqm_event_add(struct perf_event *event, int mode)
 	return 0;
 }
 
-static void intel_cqm_event_del(struct perf_event *event, int mode)
-{
-	intel_cqm_event_stop(event, mode);
-}
-
 static void intel_cqm_event_destroy(struct perf_event *event)
 {
 	struct perf_event *group_other = NULL;
@@ -1057,7 +1063,7 @@ static void intel_cqm_event_destroy(struct perf_event *event)
 			list_replace(&event->hw.cqm_groups_entry,
 				     &group_other->hw.cqm_groups_entry);
 		} else {
-			unsigned int rmid = event->hw.cqm_rmid;
+			u32 rmid = event->hw.cqm_rmid;
 
 			if (__rmid_valid(rmid))
 				__put_rmid(rmid);
@@ -1221,7 +1227,7 @@ static struct pmu intel_cqm_pmu = {
 	.task_ctx_nr	     = perf_sw_context,
 	.event_init	     = intel_cqm_event_init,
 	.add		     = intel_cqm_event_add,
-	.del		     = intel_cqm_event_del,
+	.del		     = intel_cqm_event_stop,
 	.start		     = intel_cqm_event_start,
 	.stop		     = intel_cqm_event_stop,
 	.read		     = intel_cqm_event_read,
@@ -1243,12 +1249,12 @@ static inline void cqm_pick_event_reader(int cpu)
 
 static void intel_cqm_cpu_prepare(unsigned int cpu)
 {
-	struct intel_cqm_state *state = &per_cpu(cqm_state, cpu);
+	struct intel_pqr_state *state = &per_cpu(pqr_state, cpu);
 	struct cpuinfo_x86 *c = &cpu_data(cpu);
 
-	raw_spin_lock_init(&state->lock);
 	state->rmid = 0;
-	state->cnt  = 0;
+	state->closid = 0;
+	state->rmid_usecnt = 0;
 
 	WARN_ON(c->x86_cache_max_rmid != cqm_max_rmid);
 	WARN_ON(c->x86_cache_occ_scale != cqm_l3_scale);
diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c
index 7f73b3553e2e..71fc40238843 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_ds.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c
@@ -11,7 +11,7 @@
 #define BTS_RECORD_SIZE		24
 
 #define BTS_BUFFER_SIZE		(PAGE_SIZE << 4)
-#define PEBS_BUFFER_SIZE	PAGE_SIZE
+#define PEBS_BUFFER_SIZE	(PAGE_SIZE << 4)
 #define PEBS_FIXUP_SIZE		PAGE_SIZE
 
 /*
@@ -250,7 +250,7 @@ static int alloc_pebs_buffer(int cpu)
 {
 	struct debug_store *ds = per_cpu(cpu_hw_events, cpu).ds;
 	int node = cpu_to_node(cpu);
-	int max, thresh = 1; /* always use a single PEBS record */
+	int max;
 	void *buffer, *ibuffer;
 
 	if (!x86_pmu.pebs)
@@ -280,9 +280,6 @@ static int alloc_pebs_buffer(int cpu)
 	ds->pebs_absolute_maximum = ds->pebs_buffer_base +
 		max * x86_pmu.pebs_record_size;
 
-	ds->pebs_interrupt_threshold = ds->pebs_buffer_base +
-		thresh * x86_pmu.pebs_record_size;
-
 	return 0;
 }
 
@@ -549,6 +546,19 @@ int intel_pmu_drain_bts_buffer(void)
 	return 1;
 }
 
+static inline void intel_pmu_drain_pebs_buffer(void)
+{
+	struct pt_regs regs;
+
+	x86_pmu.drain_pebs(&regs);
+}
+
+void intel_pmu_pebs_sched_task(struct perf_event_context *ctx, bool sched_in)
+{
+	if (!sched_in)
+		intel_pmu_drain_pebs_buffer();
+}
+
 /*
  * PEBS
  */
@@ -684,25 +694,66 @@ struct event_constraint *intel_pebs_constraints(struct perf_event *event)
 	return &emptyconstraint;
 }
 
+static inline bool pebs_is_enabled(struct cpu_hw_events *cpuc)
+{
+	return (cpuc->pebs_enabled & ((1ULL << MAX_PEBS_EVENTS) - 1));
+}
+
 void intel_pmu_pebs_enable(struct perf_event *event)
 {
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct hw_perf_event *hwc = &event->hw;
+	struct debug_store *ds = cpuc->ds;
+	bool first_pebs;
+	u64 threshold;
 
 	hwc->config &= ~ARCH_PERFMON_EVENTSEL_INT;
 
+	first_pebs = !pebs_is_enabled(cpuc);
 	cpuc->pebs_enabled |= 1ULL << hwc->idx;
 
 	if (event->hw.flags & PERF_X86_EVENT_PEBS_LDLAT)
 		cpuc->pebs_enabled |= 1ULL << (hwc->idx + 32);
 	else if (event->hw.flags & PERF_X86_EVENT_PEBS_ST)
 		cpuc->pebs_enabled |= 1ULL << 63;
+
+	/*
+	 * When the event is constrained enough we can use a larger
+	 * threshold and run the event with less frequent PMI.
+	 */
+	if (hwc->flags & PERF_X86_EVENT_FREERUNNING) {
+		threshold = ds->pebs_absolute_maximum -
+			x86_pmu.max_pebs_events * x86_pmu.pebs_record_size;
+
+		if (first_pebs)
+			perf_sched_cb_inc(event->ctx->pmu);
+	} else {
+		threshold = ds->pebs_buffer_base + x86_pmu.pebs_record_size;
+
+		/*
+		 * If not all events can use larger buffer,
+		 * roll back to threshold = 1
+		 */
+		if (!first_pebs &&
+		    (ds->pebs_interrupt_threshold > threshold))
+			perf_sched_cb_dec(event->ctx->pmu);
+	}
+
+	/* Use auto-reload if possible to save a MSR write in the PMI */
+	if (hwc->flags & PERF_X86_EVENT_AUTO_RELOAD) {
+		ds->pebs_event_reset[hwc->idx] =
+			(u64)(-hwc->sample_period) & x86_pmu.cntval_mask;
+	}
+
+	if (first_pebs || ds->pebs_interrupt_threshold > threshold)
+		ds->pebs_interrupt_threshold = threshold;
 }
 
 void intel_pmu_pebs_disable(struct perf_event *event)
 {
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct hw_perf_event *hwc = &event->hw;
+	struct debug_store *ds = cpuc->ds;
 
 	cpuc->pebs_enabled &= ~(1ULL << hwc->idx);
 
@@ -711,6 +762,13 @@ void intel_pmu_pebs_disable(struct perf_event *event)
 	else if (event->hw.flags & PERF_X86_EVENT_PEBS_ST)
 		cpuc->pebs_enabled &= ~(1ULL << 63);
 
+	if (ds->pebs_interrupt_threshold >
+	    ds->pebs_buffer_base + x86_pmu.pebs_record_size) {
+		intel_pmu_drain_pebs_buffer();
+		if (!pebs_is_enabled(cpuc))
+			perf_sched_cb_dec(event->ctx->pmu);
+	}
+
 	if (cpuc->enabled)
 		wrmsrl(MSR_IA32_PEBS_ENABLE, cpuc->pebs_enabled);
 
@@ -846,8 +904,10 @@ static inline u64 intel_hsw_transaction(struct pebs_record_hsw *pebs)
 	return txn;
 }
 
-static void __intel_pmu_pebs_event(struct perf_event *event,
-				   struct pt_regs *iregs, void *__pebs)
+static void setup_pebs_sample_data(struct perf_event *event,
+				   struct pt_regs *iregs, void *__pebs,
+				   struct perf_sample_data *data,
+				   struct pt_regs *regs)
 {
 #define PERF_X86_EVENT_PEBS_HSW_PREC \
 		(PERF_X86_EVENT_PEBS_ST_HSW | \
@@ -859,13 +919,11 @@ static void __intel_pmu_pebs_event(struct perf_event *event,
 	 */
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct pebs_record_hsw *pebs = __pebs;
-	struct perf_sample_data data;
-	struct pt_regs regs;
 	u64 sample_type;
 	int fll, fst, dsrc;
 	int fl = event->hw.flags;
 
-	if (!intel_pmu_save_and_restart(event))
+	if (pebs == NULL)
 		return;
 
 	sample_type = event->attr.sample_type;
@@ -874,15 +932,15 @@ static void __intel_pmu_pebs_event(struct perf_event *event,
 	fll = fl & PERF_X86_EVENT_PEBS_LDLAT;
 	fst = fl & (PERF_X86_EVENT_PEBS_ST | PERF_X86_EVENT_PEBS_HSW_PREC);
 
-	perf_sample_data_init(&data, 0, event->hw.last_period);
+	perf_sample_data_init(data, 0, event->hw.last_period);
 
-	data.period = event->hw.last_period;
+	data->period = event->hw.last_period;
 
 	/*
 	 * Use latency for weight (only avail with PEBS-LL)
 	 */
 	if (fll && (sample_type & PERF_SAMPLE_WEIGHT))
-		data.weight = pebs->lat;
+		data->weight = pebs->lat;
 
 	/*
 	 * data.data_src encodes the data source
@@ -895,7 +953,7 @@ static void __intel_pmu_pebs_event(struct perf_event *event,
 			val = precise_datala_hsw(event, pebs->dse);
 		else if (fst)
 			val = precise_store_data(pebs->dse);
-		data.data_src.val = val;
+		data->data_src.val = val;
 	}
 
 	/*
@@ -908,61 +966,123 @@ static void __intel_pmu_pebs_event(struct perf_event *event,
 	 * PERF_SAMPLE_IP and PERF_SAMPLE_CALLCHAIN to function properly.
 	 * A possible PERF_SAMPLE_REGS will have to transfer all regs.
 	 */
-	regs = *iregs;
-	regs.flags = pebs->flags;
-	set_linear_ip(&regs, pebs->ip);
-	regs.bp = pebs->bp;
-	regs.sp = pebs->sp;
+	*regs = *iregs;
+	regs->flags = pebs->flags;
+	set_linear_ip(regs, pebs->ip);
+	regs->bp = pebs->bp;
+	regs->sp = pebs->sp;
 
 	if (sample_type & PERF_SAMPLE_REGS_INTR) {
-		regs.ax = pebs->ax;
-		regs.bx = pebs->bx;
-		regs.cx = pebs->cx;
-		regs.dx = pebs->dx;
-		regs.si = pebs->si;
-		regs.di = pebs->di;
-		regs.bp = pebs->bp;
-		regs.sp = pebs->sp;
-
-		regs.flags = pebs->flags;
+		regs->ax = pebs->ax;
+		regs->bx = pebs->bx;
+		regs->cx = pebs->cx;
+		regs->dx = pebs->dx;
+		regs->si = pebs->si;
+		regs->di = pebs->di;
+		regs->bp = pebs->bp;
+		regs->sp = pebs->sp;
+
+		regs->flags = pebs->flags;
 #ifndef CONFIG_X86_32
-		regs.r8 = pebs->r8;
-		regs.r9 = pebs->r9;
-		regs.r10 = pebs->r10;
-		regs.r11 = pebs->r11;
-		regs.r12 = pebs->r12;
-		regs.r13 = pebs->r13;
-		regs.r14 = pebs->r14;
-		regs.r15 = pebs->r15;
+		regs->r8 = pebs->r8;
+		regs->r9 = pebs->r9;
+		regs->r10 = pebs->r10;
+		regs->r11 = pebs->r11;
+		regs->r12 = pebs->r12;
+		regs->r13 = pebs->r13;
+		regs->r14 = pebs->r14;
+		regs->r15 = pebs->r15;
 #endif
 	}
 
 	if (event->attr.precise_ip > 1 && x86_pmu.intel_cap.pebs_format >= 2) {
-		regs.ip = pebs->real_ip;
-		regs.flags |= PERF_EFLAGS_EXACT;
-	} else if (event->attr.precise_ip > 1 && intel_pmu_pebs_fixup_ip(&regs))
-		regs.flags |= PERF_EFLAGS_EXACT;
+		regs->ip = pebs->real_ip;
+		regs->flags |= PERF_EFLAGS_EXACT;
+	} else if (event->attr.precise_ip > 1 && intel_pmu_pebs_fixup_ip(regs))
+		regs->flags |= PERF_EFLAGS_EXACT;
 	else
-		regs.flags &= ~PERF_EFLAGS_EXACT;
+		regs->flags &= ~PERF_EFLAGS_EXACT;
 
 	if ((sample_type & PERF_SAMPLE_ADDR) &&
 	    x86_pmu.intel_cap.pebs_format >= 1)
-		data.addr = pebs->dla;
+		data->addr = pebs->dla;
 
 	if (x86_pmu.intel_cap.pebs_format >= 2) {
 		/* Only set the TSX weight when no memory weight. */
 		if ((sample_type & PERF_SAMPLE_WEIGHT) && !fll)
-			data.weight = intel_hsw_weight(pebs);
+			data->weight = intel_hsw_weight(pebs);
 
 		if (sample_type & PERF_SAMPLE_TRANSACTION)
-			data.txn = intel_hsw_transaction(pebs);
+			data->txn = intel_hsw_transaction(pebs);
 	}
 
 	if (has_branch_stack(event))
-		data.br_stack = &cpuc->lbr_stack;
+		data->br_stack = &cpuc->lbr_stack;
+}
+
+static inline void *
+get_next_pebs_record_by_bit(void *base, void *top, int bit)
+{
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+	void *at;
+	u64 pebs_status;
+
+	if (base == NULL)
+		return NULL;
+
+	for (at = base; at < top; at += x86_pmu.pebs_record_size) {
+		struct pebs_record_nhm *p = at;
+
+		if (test_bit(bit, (unsigned long *)&p->status)) {
+			/* PEBS v3 has accurate status bits */
+			if (x86_pmu.intel_cap.pebs_format >= 3)
+				return at;
 
-	if (perf_event_overflow(event, &data, &regs))
+			if (p->status == (1 << bit))
+				return at;
+
+			/* clear non-PEBS bit and re-check */
+			pebs_status = p->status & cpuc->pebs_enabled;
+			pebs_status &= (1ULL << MAX_PEBS_EVENTS) - 1;
+			if (pebs_status == (1 << bit))
+				return at;
+		}
+	}
+	return NULL;
+}
+
+static void __intel_pmu_pebs_event(struct perf_event *event,
+				   struct pt_regs *iregs,
+				   void *base, void *top,
+				   int bit, int count)
+{
+	struct perf_sample_data data;
+	struct pt_regs regs;
+	void *at = get_next_pebs_record_by_bit(base, top, bit);
+
+	if (!intel_pmu_save_and_restart(event) &&
+	    !(event->hw.flags & PERF_X86_EVENT_AUTO_RELOAD))
+		return;
+
+	while (count > 1) {
+		setup_pebs_sample_data(event, iregs, at, &data, &regs);
+		perf_event_output(event, &data, &regs);
+		at += x86_pmu.pebs_record_size;
+		at = get_next_pebs_record_by_bit(at, top, bit);
+		count--;
+	}
+
+	setup_pebs_sample_data(event, iregs, at, &data, &regs);
+
+	/*
+	 * All but the last records are processed.
+	 * The last one is left to be able to call the overflow handler.
+	 */
+	if (perf_event_overflow(event, &data, &regs)) {
 		x86_pmu_stop(event, 0);
+		return;
+	}
+
 }
 
 static void intel_pmu_drain_pebs_core(struct pt_regs *iregs)
@@ -992,72 +1112,99 @@ static void intel_pmu_drain_pebs_core(struct pt_regs *iregs)
 	if (!event->attr.precise_ip)
 		return;
 
-	n = top - at;
+	n = (top - at) / x86_pmu.pebs_record_size;
 	if (n <= 0)
 		return;
 
-	/*
-	 * Should not happen, we program the threshold at 1 and do not
-	 * set a reset value.
-	 */
-	WARN_ONCE(n > 1, "bad leftover pebs %d\n", n);
-	at += n - 1;
-
-	__intel_pmu_pebs_event(event, iregs, at);
+	__intel_pmu_pebs_event(event, iregs, at, top, 0, n);
 }
 
 static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs)
 {
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct debug_store *ds = cpuc->ds;
-	struct perf_event *event = NULL;
-	void *at, *top;
-	u64 status = 0;
-	int bit;
+	struct perf_event *event;
+	void *base, *at, *top;
+	short counts[MAX_PEBS_EVENTS] = {};
+	short error[MAX_PEBS_EVENTS] = {};
+	int bit, i;
 
 	if (!x86_pmu.pebs_active)
 		return;
 
-	at  = (struct pebs_record_nhm *)(unsigned long)ds->pebs_buffer_base;
+	base = (struct pebs_record_nhm *)(unsigned long)ds->pebs_buffer_base;
 	top = (struct pebs_record_nhm *)(unsigned long)ds->pebs_index;
 
 	ds->pebs_index = ds->pebs_buffer_base;
 
-	if (unlikely(at > top))
+	if (unlikely(base >= top))
 		return;
 
-	/*
-	 * Should not happen, we program the threshold at 1 and do not
-	 * set a reset value.
-	 */
-	WARN_ONCE(top - at > x86_pmu.max_pebs_events * x86_pmu.pebs_record_size,
-		  "Unexpected number of pebs records %ld\n",
-		  (long)(top - at) / x86_pmu.pebs_record_size);
-
-	for (; at < top; at += x86_pmu.pebs_record_size) {
+	for (at = base; at < top; at += x86_pmu.pebs_record_size) {
 		struct pebs_record_nhm *p = at;
 
-		for_each_set_bit(bit, (unsigned long *)&p->status,
-				 x86_pmu.max_pebs_events) {
-			event = cpuc->events[bit];
-			if (!test_bit(bit, cpuc->active_mask))
-				continue;
-
-			WARN_ON_ONCE(!event);
+		/* PEBS v3 has accurate status bits */
+		if (x86_pmu.intel_cap.pebs_format >= 3) {
+			for_each_set_bit(bit, (unsigned long *)&p->status,
+					 MAX_PEBS_EVENTS)
+				counts[bit]++;
 
-			if (!event->attr.precise_ip)
-				continue;
+			continue;
+		}
 
-			if (__test_and_set_bit(bit, (unsigned long *)&status))
+		bit = find_first_bit((unsigned long *)&p->status,
+					x86_pmu.max_pebs_events);
+		if (bit >= x86_pmu.max_pebs_events)
+			continue;
+		if (!test_bit(bit, cpuc->active_mask))
+			continue;
+		/*
+		 * The PEBS hardware does not deal well with the situation
+		 * when events happen near to each other and multiple bits
+		 * are set. But it should happen rarely.
+		 *
+		 * If these events include one PEBS and multiple non-PEBS
+		 * events, it doesn't impact PEBS record. The record will
+		 * be handled normally. (slow path)
+		 *
+		 * If these events include two or more PEBS events, the
+		 * records for the events can be collapsed into a single
+		 * one, and it's not possible to reconstruct all events
+		 * that caused the PEBS record. It's called collision.
+		 * If collision happened, the record will be dropped.
+		 *
+		 */
+		if (p->status != (1 << bit)) {
+			u64 pebs_status;
+
+			/* slow path */
+			pebs_status = p->status & cpuc->pebs_enabled;
+			pebs_status &= (1ULL << MAX_PEBS_EVENTS) - 1;
+			if (pebs_status != (1 << bit)) {
+				for_each_set_bit(i, (unsigned long *)&pebs_status,
+						 MAX_PEBS_EVENTS)
+					error[i]++;
 				continue;
-
-			break;
+			}
 		}
+		counts[bit]++;
+	}
 
-		if (!event || bit >= x86_pmu.max_pebs_events)
+	for (bit = 0; bit < x86_pmu.max_pebs_events; bit++) {
+		if ((counts[bit] == 0) && (error[bit] == 0))
 			continue;
+		event = cpuc->events[bit];
+		WARN_ON_ONCE(!event);
+		WARN_ON_ONCE(!event->attr.precise_ip);
 
-		__intel_pmu_pebs_event(event, iregs, at);
+		/* log dropped samples number */
+		if (error[bit])
+			perf_log_lost_samples(event, error[bit]);
+
+		if (counts[bit]) {
+			__intel_pmu_pebs_event(event, iregs, base,
+					       top, bit, counts[bit]);
+		}
 	}
 }
 
diff --git a/arch/x86/kernel/cpu/perf_event_intel_lbr.c b/arch/x86/kernel/cpu/perf_event_intel_lbr.c
index 94e5b506caa6..452a7bd2dedb 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_lbr.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_lbr.c
@@ -96,6 +96,7 @@ enum {
 	X86_BR_NO_TX		= 1 << 14,/* not in transaction */
 	X86_BR_ZERO_CALL	= 1 << 15,/* zero length call */
 	X86_BR_CALL_STACK	= 1 << 16,/* call stack */
+	X86_BR_IND_JMP		= 1 << 17,/* indirect jump */
 };
 
 #define X86_BR_PLM (X86_BR_USER | X86_BR_KERNEL)
@@ -113,6 +114,7 @@ enum {
 	 X86_BR_IRQ	 |\
 	 X86_BR_ABORT	 |\
 	 X86_BR_IND_CALL |\
+	 X86_BR_IND_JMP  |\
 	 X86_BR_ZERO_CALL)
 
 #define X86_BR_ALL (X86_BR_PLM | X86_BR_ANY)
@@ -262,9 +264,6 @@ void intel_pmu_lbr_sched_task(struct perf_event_context *ctx, bool sched_in)
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct x86_perf_task_context *task_ctx;
 
-	if (!x86_pmu.lbr_nr)
-		return;
-
 	/*
 	 * If LBR callstack feature is enabled and the stack was saved when
 	 * the task was scheduled out, restore the stack. Otherwise flush
@@ -523,6 +522,9 @@ static int intel_pmu_setup_sw_lbr_filter(struct perf_event *event)
 			X86_BR_CALL_STACK;
 	}
 
+	if (br_type & PERF_SAMPLE_BRANCH_IND_JUMP)
+		mask |= X86_BR_IND_JMP;
+
 	/*
 	 * stash actual user request into reg, it may
 	 * be used by fixup code for some CPU
@@ -736,7 +738,7 @@ static int branch_type(unsigned long from, unsigned long to, int abort)
 			break;
 		case 4:
 		case 5:
-			ret = X86_BR_JMP;
+			ret = X86_BR_IND_JMP;
 			break;
 		}
 		break;
@@ -844,6 +846,7 @@ static const int nhm_lbr_sel_map[PERF_SAMPLE_BRANCH_MAX_SHIFT] = {
 	 */
 	[PERF_SAMPLE_BRANCH_IND_CALL_SHIFT] = LBR_IND_CALL | LBR_IND_JMP,
 	[PERF_SAMPLE_BRANCH_COND_SHIFT]     = LBR_JCC,
+	[PERF_SAMPLE_BRANCH_IND_JUMP_SHIFT] = LBR_IND_JMP,
 };
 
 static const int snb_lbr_sel_map[PERF_SAMPLE_BRANCH_MAX_SHIFT] = {
@@ -856,6 +859,7 @@ static const int snb_lbr_sel_map[PERF_SAMPLE_BRANCH_MAX_SHIFT] = {
 						| LBR_FAR,
 	[PERF_SAMPLE_BRANCH_IND_CALL_SHIFT]	= LBR_IND_CALL,
 	[PERF_SAMPLE_BRANCH_COND_SHIFT]		= LBR_JCC,
+	[PERF_SAMPLE_BRANCH_IND_JUMP_SHIFT]	= LBR_IND_JMP,
 };
 
 static const int hsw_lbr_sel_map[PERF_SAMPLE_BRANCH_MAX_SHIFT] = {
@@ -870,6 +874,7 @@ static const int hsw_lbr_sel_map[PERF_SAMPLE_BRANCH_MAX_SHIFT] = {
 	[PERF_SAMPLE_BRANCH_COND_SHIFT]		= LBR_JCC,
 	[PERF_SAMPLE_BRANCH_CALL_STACK_SHIFT]	= LBR_REL_CALL | LBR_IND_CALL
 						| LBR_RETURN | LBR_CALL_STACK,
+	[PERF_SAMPLE_BRANCH_IND_JUMP_SHIFT]	= LBR_IND_JMP,
 };
 
 /* core */
diff --git a/arch/x86/kernel/cpu/perf_event_intel_pt.c b/arch/x86/kernel/cpu/perf_event_intel_pt.c
index 123ff1bb2f60..159887c3a89d 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_pt.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_pt.c
@@ -187,15 +187,6 @@ static bool pt_event_valid(struct perf_event *event)
  * These all are cpu affine and operate on a local PT
  */
 
-static bool pt_is_running(void)
-{
-	u64 ctl;
-
-	rdmsrl(MSR_IA32_RTIT_CTL, ctl);
-
-	return !!(ctl & RTIT_CTL_TRACEEN);
-}
-
 static void pt_config(struct perf_event *event)
 {
 	u64 reg;
@@ -609,7 +600,12 @@ static unsigned int pt_topa_next_entry(struct pt_buffer *buf, unsigned int pg)
  * @handle:	Current output handle.
  *
  * Place INT and STOP marks to prevent overwriting old data that the consumer
- * hasn't yet collected.
+ * hasn't yet collected and waking up the consumer after a certain fraction of
+ * the buffer has filled up. Only needed and sensible for non-snapshot counters.
+ *
+ * This obviously relies on buf::head to figure out buffer markers, so it has
+ * to be called after pt_buffer_reset_offsets() and before the hardware tracing
+ * is enabled.
  */
 static int pt_buffer_reset_markers(struct pt_buffer *buf,
 				   struct perf_output_handle *handle)
@@ -618,9 +614,6 @@ static int pt_buffer_reset_markers(struct pt_buffer *buf,
 	unsigned long head = local64_read(&buf->head);
 	unsigned long idx, npages, wakeup;
 
-	if (buf->snapshot)
-		return 0;
-
 	/* can't stop in the middle of an output region */
 	if (buf->output_off + handle->size + 1 <
 	    sizes(TOPA_ENTRY(buf->cur, buf->cur_idx)->size))
@@ -674,7 +667,7 @@ static void pt_buffer_setup_topa_index(struct pt_buffer *buf)
 	struct topa *cur = buf->first, *prev = buf->last;
 	struct topa_entry *te_cur = TOPA_ENTRY(cur, 0),
 		*te_prev = TOPA_ENTRY(prev, prev->last - 1);
-	int pg = 0, idx = 0, ntopa = 0;
+	int pg = 0, idx = 0;
 
 	while (pg < buf->nr_pages) {
 		int tidx;
@@ -689,9 +682,9 @@ static void pt_buffer_setup_topa_index(struct pt_buffer *buf)
 			/* advance to next topa table */
 			idx = 0;
 			cur = list_entry(cur->list.next, struct topa, list);
-			ntopa++;
-		} else
+		} else {
 			idx++;
+		}
 		te_cur = TOPA_ENTRY(cur, idx);
 	}
 
@@ -703,7 +696,14 @@ static void pt_buffer_setup_topa_index(struct pt_buffer *buf)
  * @head:	Write pointer (aux_head) from AUX buffer.
  *
  * Find the ToPA table and entry corresponding to given @head and set buffer's
- * "current" pointers accordingly.
+ * "current" pointers accordingly. This is done after we have obtained the
+ * current aux_head position from a successful call to perf_aux_output_begin()
+ * to make sure the hardware is writing to the right place.
+ *
+ * This function modifies buf::{cur,cur_idx,output_off} that will be programmed
+ * into PT msrs when the tracing is enabled and buf::head and buf::data_size,
+ * which are used to determine INT and STOP markers' locations by a subsequent
+ * call to pt_buffer_reset_markers().
  */
 static void pt_buffer_reset_offsets(struct pt_buffer *buf, unsigned long head)
 {
@@ -901,6 +901,7 @@ void intel_pt_interrupt(void)
 		}
 
 		pt_buffer_reset_offsets(buf, pt->handle.head);
+		/* snapshot counters don't use PMI, so it's safe */
 		ret = pt_buffer_reset_markers(buf, &pt->handle);
 		if (ret) {
 			perf_aux_output_end(&pt->handle, 0, true);
@@ -923,7 +924,7 @@ static void pt_event_start(struct perf_event *event, int mode)
 	struct pt *pt = this_cpu_ptr(&pt_ctx);
 	struct pt_buffer *buf = perf_get_aux(&pt->handle);
 
-	if (pt_is_running() || !buf || pt_buffer_is_full(buf, pt)) {
+	if (!buf || pt_buffer_is_full(buf, pt)) {
 		event->hw.state = PERF_HES_STOPPED;
 		return;
 	}
@@ -954,7 +955,6 @@ static void pt_event_stop(struct perf_event *event, int mode)
 	event->hw.state = PERF_HES_STOPPED;
 
 	if (mode & PERF_EF_UPDATE) {
-		struct pt *pt = this_cpu_ptr(&pt_ctx);
 		struct pt_buffer *buf = perf_get_aux(&pt->handle);
 
 		if (!buf)
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.c b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
index 90b7c501c95b..7c1de1610178 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
@@ -922,6 +922,9 @@ static int __init uncore_pci_init(void)
 	case 69: /* Haswell Celeron */
 		ret = hsw_uncore_pci_init();
 		break;
+	case 61: /* Broadwell */
+		ret = bdw_uncore_pci_init();
+		break;
 	default:
 		return 0;
 	}
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.h b/arch/x86/kernel/cpu/perf_event_intel_uncore.h
index ceac8f5dc018..0f77f0a196e4 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore.h
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.h
@@ -325,6 +325,7 @@ extern struct event_constraint uncore_constraint_empty;
 int snb_uncore_pci_init(void);
 int ivb_uncore_pci_init(void);
 int hsw_uncore_pci_init(void);
+int bdw_uncore_pci_init(void);
 void snb_uncore_cpu_init(void);
 void nhm_uncore_cpu_init(void);
 
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore_snb.c b/arch/x86/kernel/cpu/perf_event_intel_uncore_snb.c
index 4562e9e22c60..b005a78c7012 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore_snb.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore_snb.c
@@ -7,6 +7,7 @@
 #define PCI_DEVICE_ID_INTEL_IVB_E3_IMC	0x0150
 #define PCI_DEVICE_ID_INTEL_HSW_IMC	0x0c00
 #define PCI_DEVICE_ID_INTEL_HSW_U_IMC	0x0a04
+#define PCI_DEVICE_ID_INTEL_BDW_IMC	0x1604
 
 /* SNB event control */
 #define SNB_UNC_CTL_EV_SEL_MASK			0x000000ff
@@ -486,6 +487,14 @@ static const struct pci_device_id hsw_uncore_pci_ids[] = {
 	{ /* end: all zeroes */ },
 };
 
+static const struct pci_device_id bdw_uncore_pci_ids[] = {
+	{ /* IMC */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_BDW_IMC),
+		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+	},
+	{ /* end: all zeroes */ },
+};
+
 static struct pci_driver snb_uncore_pci_driver = {
 	.name		= "snb_uncore",
 	.id_table	= snb_uncore_pci_ids,
@@ -501,6 +510,11 @@ static struct pci_driver hsw_uncore_pci_driver = {
 	.id_table	= hsw_uncore_pci_ids,
 };
 
+static struct pci_driver bdw_uncore_pci_driver = {
+	.name		= "bdw_uncore",
+	.id_table	= bdw_uncore_pci_ids,
+};
+
 struct imc_uncore_pci_dev {
 	__u32 pci_id;
 	struct pci_driver *driver;
@@ -514,6 +528,7 @@ static const struct imc_uncore_pci_dev desktop_imc_pci_ids[] = {
 	IMC_DEV(IVB_E3_IMC, &ivb_uncore_pci_driver), /* Xeon E3-1200 v2/3rd Gen Core processor */
 	IMC_DEV(HSW_IMC, &hsw_uncore_pci_driver),    /* 4th Gen Core Processor */
 	IMC_DEV(HSW_U_IMC, &hsw_uncore_pci_driver),  /* 4th Gen Core ULT Mobile Processor */
+	IMC_DEV(BDW_IMC, &bdw_uncore_pci_driver),    /* 5th Gen Core U */
 	{  /* end marker */ }
 };
 
@@ -561,6 +576,11 @@ int hsw_uncore_pci_init(void)
 	return imc_uncore_pci_init();
 }
 
+int bdw_uncore_pci_init(void)
+{
+	return imc_uncore_pci_init();
+}
+
 /* end of Sandy Bridge uncore support */
 
 /* Nehalem uncore support */
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index d8a82a89f35a..a204d5266f5f 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -120,7 +120,7 @@ struct hw_perf_event {
 		};
 		struct { /* intel_cqm */
 			int			cqm_state;
-			int			cqm_rmid;
+			u32			cqm_rmid;
 			struct list_head	cqm_events_entry;
 			struct list_head	cqm_groups_entry;
 			struct list_head	cqm_group_entry;
@@ -730,6 +730,22 @@ extern int perf_event_overflow(struct perf_event *event,
 				 struct perf_sample_data *data,
 				 struct pt_regs *regs);
 
+extern void perf_event_output(struct perf_event *event,
+				struct perf_sample_data *data,
+				struct pt_regs *regs);
+
+extern void
+perf_event_header__init_id(struct perf_event_header *header,
+			   struct perf_sample_data *data,
+			   struct perf_event *event);
+extern void
+perf_event__output_id_sample(struct perf_event *event,
+			     struct perf_output_handle *handle,
+			     struct perf_sample_data *sample);
+
+extern void
+perf_log_lost_samples(struct perf_event *event, u64 lost);
+
 static inline bool is_sampling_event(struct perf_event *event)
 {
 	return event->attr.sample_period != 0;
@@ -794,11 +810,33 @@ perf_sw_event_sched(u32 event_id, u64 nr, u64 addr)
 
 extern struct static_key_deferred perf_sched_events;
 
+static __always_inline bool
+perf_sw_migrate_enabled(void)
+{
+	if (static_key_false(&perf_swevent_enabled[PERF_COUNT_SW_CPU_MIGRATIONS]))
+		return true;
+	return false;
+}
+
+static inline void perf_event_task_migrate(struct task_struct *task)
+{
+	if (perf_sw_migrate_enabled())
+		task->sched_migrated = 1;
+}
+
 static inline void perf_event_task_sched_in(struct task_struct *prev,
 					    struct task_struct *task)
 {
 	if (static_key_false(&perf_sched_events.key))
 		__perf_event_task_sched_in(prev, task);
+
+	if (perf_sw_migrate_enabled() && task->sched_migrated) {
+		struct pt_regs *regs = this_cpu_ptr(&__perf_regs[0]);
+
+		perf_fetch_caller_regs(regs);
+		___perf_sw_event(PERF_COUNT_SW_CPU_MIGRATIONS, 1, regs, 0);
+		task->sched_migrated = 0;
+	}
 }
 
 static inline void perf_event_task_sched_out(struct task_struct *prev,
@@ -921,6 +959,8 @@ perf_aux_output_skip(struct perf_output_handle *handle,
 static inline void *
 perf_get_aux(struct perf_output_handle *handle)				{ return NULL; }
 static inline void
+perf_event_task_migrate(struct task_struct *task)			{ }
+static inline void
 perf_event_task_sched_in(struct task_struct *prev,
 			 struct task_struct *task)			{ }
 static inline void
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 8ca95f6a9395..659f5729cacc 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1357,9 +1357,6 @@ struct task_struct {
 #endif
 
 	struct mm_struct *mm, *active_mm;
-#ifdef CONFIG_COMPAT_BRK
-	unsigned brk_randomized:1;
-#endif
 	/* per-thread vma caching */
 	u32 vmacache_seqnum;
 	struct vm_area_struct *vmacache[VMACACHE_SIZE];
@@ -1382,10 +1379,14 @@ struct task_struct {
 	/* Revert to default priority/policy when forking */
 	unsigned sched_reset_on_fork:1;
 	unsigned sched_contributes_to_load:1;
+	unsigned sched_migrated:1;
 
 #ifdef CONFIG_MEMCG_KMEM
 	unsigned memcg_kmem_skip_account:1;
 #endif
+#ifdef CONFIG_COMPAT_BRK
+	unsigned brk_randomized:1;
+#endif
 
 	unsigned long atomic_flags; /* Flags needing atomic access. */
 
diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h
index 309211b3eb67..d97f84c080da 100644
--- a/include/uapi/linux/perf_event.h
+++ b/include/uapi/linux/perf_event.h
@@ -167,6 +167,7 @@ enum perf_branch_sample_type_shift {
 	PERF_SAMPLE_BRANCH_COND_SHIFT		= 10, /* conditional branches */
 
 	PERF_SAMPLE_BRANCH_CALL_STACK_SHIFT	= 11, /* call/ret stack */
+	PERF_SAMPLE_BRANCH_IND_JUMP_SHIFT	= 12, /* indirect jumps */
 
 	PERF_SAMPLE_BRANCH_MAX_SHIFT		/* non-ABI */
 };
@@ -186,6 +187,7 @@ enum perf_branch_sample_type {
 	PERF_SAMPLE_BRANCH_COND		= 1U << PERF_SAMPLE_BRANCH_COND_SHIFT,
 
 	PERF_SAMPLE_BRANCH_CALL_STACK	= 1U << PERF_SAMPLE_BRANCH_CALL_STACK_SHIFT,
+	PERF_SAMPLE_BRANCH_IND_JUMP	= 1U << PERF_SAMPLE_BRANCH_IND_JUMP_SHIFT,
 
 	PERF_SAMPLE_BRANCH_MAX		= 1U << PERF_SAMPLE_BRANCH_MAX_SHIFT,
 };
@@ -564,6 +566,10 @@ struct perf_event_mmap_page {
 #define PERF_RECORD_MISC_GUEST_USER		(5 << 0)
 
 /*
+ * Indicates that /proc/PID/maps parsing are truncated by time out.
+ */
+#define PERF_RECORD_MISC_PROC_MAP_PARSE_TIMEOUT	(1 << 12)
+/*
  * PERF_RECORD_MISC_MMAP_DATA and PERF_RECORD_MISC_COMM_EXEC are used on
  * different events so can reuse the same bit position.
  */
@@ -800,6 +806,18 @@ enum perf_event_type {
 	 */
 	PERF_RECORD_ITRACE_START		= 12,
 
+	/*
+	 * Records the dropped/lost sample number.
+	 *
+	 * struct {
+	 *	struct perf_event_header	header;
+	 *
+	 *	u64				lost;
+	 *	struct sample_id		sample_id;
+	 * };
+	 */
+	PERF_RECORD_LOST_SAMPLES		= 13,
+
 	PERF_RECORD_MAX,			/* non-ABI */
 };
 
diff --git a/init/Kconfig b/init/Kconfig
index 4c08197044f1..b999fa381bf9 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -1623,7 +1623,7 @@ config PERF_EVENTS
 config DEBUG_PERF_USE_VMALLOC
 	default n
 	bool "Debug: use vmalloc to back perf mmap() buffers"
-	depends on PERF_EVENTS && DEBUG_KERNEL
+	depends on PERF_EVENTS && DEBUG_KERNEL && !PPC
 	select PERF_USE_VMALLOC
 	help
 	 Use vmalloc memory to back perf mmap() buffers.
diff --git a/kernel/events/core.c b/kernel/events/core.c
index eddf1ed4155e..9e0773d5d110 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -5381,9 +5381,9 @@ void perf_prepare_sample(struct perf_event_header *header,
 	}
 }
 
-static void perf_event_output(struct perf_event *event,
-				struct perf_sample_data *data,
-				struct pt_regs *regs)
+void perf_event_output(struct perf_event *event,
+			struct perf_sample_data *data,
+			struct pt_regs *regs)
 {
 	struct perf_output_handle handle;
 	struct perf_event_header header;
@@ -5975,6 +5975,39 @@ void perf_event_aux_event(struct perf_event *event, unsigned long head,
 }
 
 /*
+ * Lost/dropped samples logging
+ */
+void perf_log_lost_samples(struct perf_event *event, u64 lost)
+{
+	struct perf_output_handle handle;
+	struct perf_sample_data sample;
+	int ret;
+
+	struct {
+		struct perf_event_header	header;
+		u64				lost;
+	} lost_samples_event = {
+		.header = {
+			.type = PERF_RECORD_LOST_SAMPLES,
+			.misc = 0,
+			.size = sizeof(lost_samples_event),
+		},
+		.lost		= lost,
+	};
+
+	perf_event_header__init_id(&lost_samples_event.header, &sample, event);
+
+	ret = perf_output_begin(&handle, event,
+				lost_samples_event.header.size);
+	if (ret)
+		return;
+
+	perf_output_put(&handle, lost_samples_event);
+	perf_event__output_id_sample(event, &handle, &sample);
+	perf_output_end(&handle);
+}
+
+/*
  * IRQ throttle logging
  */
 
diff --git a/kernel/events/internal.h b/kernel/events/internal.h
index 9f6ce9ba4a04..2deb24c7a40d 100644
--- a/kernel/events/internal.h
+++ b/kernel/events/internal.h
@@ -72,15 +72,6 @@ static inline bool rb_has_aux(struct ring_buffer *rb)
 void perf_event_aux_event(struct perf_event *event, unsigned long head,
 			  unsigned long size, u64 flags);
 
-extern void
-perf_event_header__init_id(struct perf_event_header *header,
-			   struct perf_sample_data *data,
-			   struct perf_event *event);
-extern void
-perf_event__output_id_sample(struct perf_event *event,
-			     struct perf_output_handle *handle,
-			     struct perf_sample_data *sample);
-
 extern struct page *
 perf_mmap_to_page(struct ring_buffer *rb, unsigned long pgoff);
 
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 123673291ffb..db9b10a78d74 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1049,7 +1049,7 @@ void set_task_cpu(struct task_struct *p, unsigned int new_cpu)
 		if (p->sched_class->migrate_task_rq)
 			p->sched_class->migrate_task_rq(p, new_cpu);
 		p->se.nr_migrations++;
-		perf_sw_event_sched(PERF_COUNT_SW_CPU_MIGRATIONS, 1, 0);
+		perf_event_task_migrate(p);
 	}
 
 	__set_task_cpu(p, new_cpu);
diff --git a/tools/Makefile b/tools/Makefile
index 9a617adc6675..b35102721cbb 100644
--- a/tools/Makefile
+++ b/tools/Makefile
@@ -1,3 +1,8 @@
+# Some of the tools (perf) use same make variables
+# as in kernel build.
+export srctree=
+export objtree=
+
 include scripts/Makefile.include
 
 help:
@@ -47,11 +52,16 @@ cgroup firewire hv guest usb virtio vm net: FORCE
 liblockdep: FORCE
 	$(call descend,lib/lockdep)
 
-libapikfs: FORCE
+libapi: FORCE
 	$(call descend,lib/api)
 
-perf: libapikfs FORCE
-	$(call descend,$@)
+# The perf build does not follow the descend function setup,
+# invoking it via it's own make rule.
+PERF_O   = $(if $(O),$(O)/tools/perf,)
+
+perf: FORCE
+	$(Q)mkdir -p $(PERF_O) .
+	$(Q)$(MAKE) --no-print-directory -C perf O=$(PERF_O) subdir=
 
 selftests: FORCE
 	$(call descend,testing/$@)
@@ -97,10 +107,10 @@ cgroup_clean hv_clean firewire_clean lguest_clean usb_clean virtio_clean vm_clea
 liblockdep_clean:
 	$(call descend,lib/lockdep,clean)
 
-libapikfs_clean:
+libapi_clean:
 	$(call descend,lib/api,clean)
 
-perf_clean: libapikfs_clean
+perf_clean:
 	$(call descend,$(@:_clean=),clean)
 
 selftests_clean:
diff --git a/tools/arch/alpha/include/asm/barrier.h b/tools/arch/alpha/include/asm/barrier.h
new file mode 100644
index 000000000000..95df19c95482
--- /dev/null
+++ b/tools/arch/alpha/include/asm/barrier.h
@@ -0,0 +1,8 @@
+#ifndef __TOOLS_LINUX_ASM_ALPHA_BARRIER_H
+#define __TOOLS_LINUX_ASM_ALPHA_BARRIER_H
+
+#define mb()	__asm__ __volatile__("mb": : :"memory")
+#define rmb()	__asm__ __volatile__("mb": : :"memory")
+#define wmb()	__asm__ __volatile__("wmb": : :"memory")
+
+#endif		/* __TOOLS_LINUX_ASM_ALPHA_BARRIER_H */
diff --git a/tools/arch/arm/include/asm/barrier.h b/tools/arch/arm/include/asm/barrier.h
new file mode 100644
index 000000000000..005c618a0ab0
--- /dev/null
+++ b/tools/arch/arm/include/asm/barrier.h
@@ -0,0 +1,12 @@
+#ifndef _TOOLS_LINUX_ASM_ARM_BARRIER_H
+#define _TOOLS_LINUX_ASM_ARM_BARRIER_H
+
+/*
+ * Use the __kuser_memory_barrier helper in the CPU helper page. See
+ * arch/arm/kernel/entry-armv.S in the kernel source for details.
+ */
+#define mb()		((void(*)(void))0xffff0fa0)()
+#define wmb()		((void(*)(void))0xffff0fa0)()
+#define rmb()		((void(*)(void))0xffff0fa0)()
+
+#endif /* _TOOLS_LINUX_ASM_ARM_BARRIER_H */
diff --git a/tools/arch/arm64/include/asm/barrier.h b/tools/arch/arm64/include/asm/barrier.h
new file mode 100644
index 000000000000..a0483c8e0142
--- /dev/null
+++ b/tools/arch/arm64/include/asm/barrier.h
@@ -0,0 +1,16 @@
+#ifndef _TOOLS_LINUX_ASM_AARCH64_BARRIER_H
+#define _TOOLS_LINUX_ASM_AARCH64_BARRIER_H
+
+/*
+ * From tools/perf/perf-sys.h, last modified in:
+ * f428ebd184c82a7914b2aa7e9f868918aaf7ea78 perf tools: Fix AAAAARGH64 memory barriers
+ *
+ * XXX: arch/arm64/include/asm/barrier.h in the kernel sources use dsb, is this
+ * a case like for arm32 where we do things differently in userspace?
+ */
+
+#define mb()		asm volatile("dmb ish" ::: "memory")
+#define wmb()		asm volatile("dmb ishst" ::: "memory")
+#define rmb()		asm volatile("dmb ishld" ::: "memory")
+
+#endif /* _TOOLS_LINUX_ASM_AARCH64_BARRIER_H */
diff --git a/tools/arch/ia64/include/asm/barrier.h b/tools/arch/ia64/include/asm/barrier.h
new file mode 100644
index 000000000000..e4422b4b634e
--- /dev/null
+++ b/tools/arch/ia64/include/asm/barrier.h
@@ -0,0 +1,48 @@
+/*
+ * Copied from the kernel sources to tools/:
+ *
+ * Memory barrier definitions.  This is based on information published
+ * in the Processor Abstraction Layer and the System Abstraction Layer
+ * manual.
+ *
+ * Copyright (C) 1998-2003 Hewlett-Packard Co
+ *	David Mosberger-Tang <davidm@hpl.hp.com>
+ * Copyright (C) 1999 Asit Mallick <asit.k.mallick@intel.com>
+ * Copyright (C) 1999 Don Dugger <don.dugger@intel.com>
+ */
+#ifndef _TOOLS_LINUX_ASM_IA64_BARRIER_H
+#define _TOOLS_LINUX_ASM_IA64_BARRIER_H
+
+#include <linux/compiler.h>
+
+/*
+ * Macros to force memory ordering.  In these descriptions, "previous"
+ * and "subsequent" refer to program order; "visible" means that all
+ * architecturally visible effects of a memory access have occurred
+ * (at a minimum, this means the memory has been read or written).
+ *
+ *   wmb():	Guarantees that all preceding stores to memory-
+ *		like regions are visible before any subsequent
+ *		stores and that all following stores will be
+ *		visible only after all previous stores.
+ *   rmb():	Like wmb(), but for reads.
+ *   mb():	wmb()/rmb() combo, i.e., all previous memory
+ *		accesses are visible before all subsequent
+ *		accesses and vice versa.  This is also known as
+ *		a "fence."
+ *
+ * Note: "mb()" and its variants cannot be used as a fence to order
+ * accesses to memory mapped I/O registers.  For that, mf.a needs to
+ * be used.  However, we don't want to always use mf.a because (a)
+ * it's (presumably) much slower than mf and (b) mf.a is supported for
+ * sequential memory pages only.
+ */
+
+/* XXX From arch/ia64/include/uapi/asm/gcc_intrin.h */
+#define ia64_mf()       asm volatile ("mf" ::: "memory")
+
+#define mb()		ia64_mf()
+#define rmb()		mb()
+#define wmb()		mb()
+
+#endif /* _TOOLS_LINUX_ASM_IA64_BARRIER_H */
diff --git a/tools/arch/mips/include/asm/barrier.h b/tools/arch/mips/include/asm/barrier.h
new file mode 100644
index 000000000000..80f96f7556e3
--- /dev/null
+++ b/tools/arch/mips/include/asm/barrier.h
@@ -0,0 +1,20 @@
+#ifndef _TOOLS_LINUX_ASM_MIPS_BARRIER_H
+#define _TOOLS_LINUX_ASM_MIPS_BARRIER_H
+/*
+ * FIXME: This came from tools/perf/perf-sys.h, where it was first introduced
+ * in c1e028ef40b8d6943b767028ba17d4f2ba020edb, more work needed to make it
+ * more closely follow the Linux kernel arch/mips/include/asm/barrier.h file.
+ * Probably when we continue work on tools/ Kconfig support to have all the
+ * CONFIG_ needed for properly doing that.
+ */
+#define mb()		asm volatile(					\
+				".set	mips2\n\t"			\
+				"sync\n\t"				\
+				".set	mips0"				\
+				: /* no output */			\
+				: /* no input */			\
+				: "memory")
+#define wmb()	mb()
+#define rmb()	mb()
+
+#endif /* _TOOLS_LINUX_ASM_MIPS_BARRIER_H */
diff --git a/tools/arch/powerpc/include/asm/barrier.h b/tools/arch/powerpc/include/asm/barrier.h
new file mode 100644
index 000000000000..b23aee8e6d90
--- /dev/null
+++ b/tools/arch/powerpc/include/asm/barrier.h
@@ -0,0 +1,29 @@
+/*
+ * Copied from the kernel sources:
+ *
+ * Copyright (C) 1999 Cort Dougan <cort@cs.nmt.edu>
+ */
+#ifndef _TOOLS_LINUX_ASM_POWERPC_BARRIER_H
+#define _TOOLS_LINUX_ASM_POWERPC_BARRIER_H
+
+/*
+ * Memory barrier.
+ * The sync instruction guarantees that all memory accesses initiated
+ * by this processor have been performed (with respect to all other
+ * mechanisms that access memory).  The eieio instruction is a barrier
+ * providing an ordering (separately) for (a) cacheable stores and (b)
+ * loads and stores to non-cacheable memory (e.g. I/O devices).
+ *
+ * mb() prevents loads and stores being reordered across this point.
+ * rmb() prevents loads being reordered across this point.
+ * wmb() prevents stores being reordered across this point.
+ *
+ * *mb() variants without smp_ prefix must order all types of memory
+ * operations with one another. sync is the only instruction sufficient
+ * to do this.
+ */
+#define mb()   __asm__ __volatile__ ("sync" : : : "memory")
+#define rmb()  __asm__ __volatile__ ("sync" : : : "memory")
+#define wmb()  __asm__ __volatile__ ("sync" : : : "memory")
+
+#endif /* _TOOLS_LINUX_ASM_POWERPC_BARRIER_H */
diff --git a/tools/arch/s390/include/asm/barrier.h b/tools/arch/s390/include/asm/barrier.h
new file mode 100644
index 000000000000..f85141266b92
--- /dev/null
+++ b/tools/arch/s390/include/asm/barrier.h
@@ -0,0 +1,30 @@
+/*
+ * Copied from the kernel sources:
+ *
+ * Copyright IBM Corp. 1999, 2009
+ *
+ * Author(s): Martin Schwidefsky <schwidefsky@de.ibm.com>
+ */
+
+#ifndef __TOOLS_LINUX_ASM_BARRIER_H
+#define __TOOLS_LINUX_ASM_BARRIER_H
+
+/*
+ * Force strict CPU ordering.
+ * And yes, this is required on UP too when we're talking
+ * to devices.
+ */
+
+#ifdef CONFIG_HAVE_MARCH_Z196_FEATURES
+/* Fast-BCR without checkpoint synchronization */
+#define __ASM_BARRIER "bcr 14,0\n"
+#else
+#define __ASM_BARRIER "bcr 15,0\n"
+#endif
+
+#define mb() do {  asm volatile(__ASM_BARRIER : : : "memory"); } while (0)
+
+#define rmb()				mb()
+#define wmb()				mb()
+
+#endif /* __TOOLS_LIB_ASM_BARRIER_H */
diff --git a/tools/arch/sh/include/asm/barrier.h b/tools/arch/sh/include/asm/barrier.h
new file mode 100644
index 000000000000..c18fd7599b97
--- /dev/null
+++ b/tools/arch/sh/include/asm/barrier.h
@@ -0,0 +1,32 @@
+/*
+ * Copied from the kernel sources:
+ *
+ * Copyright (C) 1999, 2000  Niibe Yutaka  &  Kaz Kojima
+ * Copyright (C) 2002 Paul Mundt
+ */
+#ifndef __TOOLS_LINUX_ASM_SH_BARRIER_H
+#define __TOOLS_LINUX_ASM_SH_BARRIER_H
+
+/*
+ * A brief note on ctrl_barrier(), the control register write barrier.
+ *
+ * Legacy SH cores typically require a sequence of 8 nops after
+ * modification of a control register in order for the changes to take
+ * effect. On newer cores (like the sh4a and sh5) this is accomplished
+ * with icbi.
+ *
+ * Also note that on sh4a in the icbi case we can forego a synco for the
+ * write barrier, as it's not necessary for control registers.
+ *
+ * Historically we have only done this type of barrier for the MMUCR, but
+ * it's also necessary for the CCR, so we make it generic here instead.
+ */
+#if defined(__SH4A__) || defined(__SH5__)
+#define mb()		__asm__ __volatile__ ("synco": : :"memory")
+#define rmb()		mb()
+#define wmb()		mb()
+#endif
+
+#include <asm-generic/barrier.h>
+
+#endif /* __TOOLS_LINUX_ASM_SH_BARRIER_H */
diff --git a/tools/arch/sparc/include/asm/barrier.h b/tools/arch/sparc/include/asm/barrier.h
new file mode 100644
index 000000000000..8c017b3b1391
--- /dev/null
+++ b/tools/arch/sparc/include/asm/barrier.h
@@ -0,0 +1,8 @@
+#ifndef ___TOOLS_LINUX_ASM_SPARC_BARRIER_H
+#define ___TOOLS_LINUX_ASM_SPARC_BARRIER_H
+#if defined(__sparc__) && defined(__arch64__)
+#include "barrier_64.h"
+#else
+#include "barrier_32.h"
+#endif
+#endif
diff --git a/tools/arch/sparc/include/asm/barrier_32.h b/tools/arch/sparc/include/asm/barrier_32.h
new file mode 100644
index 000000000000..c5eadd0a7233
--- /dev/null
+++ b/tools/arch/sparc/include/asm/barrier_32.h
@@ -0,0 +1,6 @@
+#ifndef __TOOLS_PERF_SPARC_BARRIER_H
+#define __TOOLS_PERF_SPARC_BARRIER_H
+
+#include <asm-generic/barrier.h>
+
+#endif /* !(__TOOLS_PERF_SPARC_BARRIER_H) */
diff --git a/tools/arch/sparc/include/asm/barrier_64.h b/tools/arch/sparc/include/asm/barrier_64.h
new file mode 100644
index 000000000000..9a7d7322c3f7
--- /dev/null
+++ b/tools/arch/sparc/include/asm/barrier_64.h
@@ -0,0 +1,42 @@
+#ifndef __TOOLS_LINUX_SPARC64_BARRIER_H
+#define __TOOLS_LINUX_SPARC64_BARRIER_H
+
+/* Copied from the kernel sources to tools/:
+ *
+ * These are here in an effort to more fully work around Spitfire Errata
+ * #51.  Essentially, if a memory barrier occurs soon after a mispredicted
+ * branch, the chip can stop executing instructions until a trap occurs.
+ * Therefore, if interrupts are disabled, the chip can hang forever.
+ *
+ * It used to be believed that the memory barrier had to be right in the
+ * delay slot, but a case has been traced recently wherein the memory barrier
+ * was one instruction after the branch delay slot and the chip still hung.
+ * The offending sequence was the following in sym_wakeup_done() of the
+ * sym53c8xx_2 driver:
+ *
+ *	call	sym_ccb_from_dsa, 0
+ *	 movge	%icc, 0, %l0
+ *	brz,pn	%o0, .LL1303
+ *	 mov	%o0, %l2
+ *	membar	#LoadLoad
+ *
+ * The branch has to be mispredicted for the bug to occur.  Therefore, we put
+ * the memory barrier explicitly into a "branch always, predicted taken"
+ * delay slot to avoid the problem case.
+ */
+#define membar_safe(type) \
+do {	__asm__ __volatile__("ba,pt	%%xcc, 1f\n\t" \
+			     " membar	" type "\n" \
+			     "1:\n" \
+			     : : : "memory"); \
+} while (0)
+
+/* The kernel always executes in TSO memory model these days,
+ * and furthermore most sparc64 chips implement more stringent
+ * memory ordering than required by the specifications.
+ */
+#define mb()	membar_safe("#StoreLoad")
+#define rmb()	__asm__ __volatile__("":::"memory")
+#define wmb()	__asm__ __volatile__("":::"memory")
+
+#endif /* !(__TOOLS_LINUX_SPARC64_BARRIER_H) */
diff --git a/tools/arch/tile/include/asm/barrier.h b/tools/arch/tile/include/asm/barrier.h
new file mode 100644
index 000000000000..7d3692c3d4ac
--- /dev/null
+++ b/tools/arch/tile/include/asm/barrier.h
@@ -0,0 +1,15 @@
+#ifndef _TOOLS_LINUX_ASM_TILE_BARRIER_H
+#define _TOOLS_LINUX_ASM_TILE_BARRIER_H
+/*
+ * FIXME: This came from tools/perf/perf-sys.h, where it was first introduced
+ * in 620830b6954913647b7c7f68920cf48eddf6ad92, more work needed to make it
+ * more closely follow the Linux kernel arch/tile/include/asm/barrier.h file.
+ * Probably when we continue work on tools/ Kconfig support to have all the
+ * CONFIG_ needed for properly doing that.
+ */
+
+#define mb()		asm volatile ("mf" ::: "memory")
+#define wmb()		mb()
+#define rmb()		mb()
+
+#endif /* _TOOLS_LINUX_ASM_TILE_BARRIER_H */
diff --git a/tools/arch/x86/include/asm/atomic.h b/tools/arch/x86/include/asm/atomic.h
new file mode 100644
index 000000000000..059e33e94260
--- /dev/null
+++ b/tools/arch/x86/include/asm/atomic.h
@@ -0,0 +1,65 @@
+#ifndef _TOOLS_LINUX_ASM_X86_ATOMIC_H
+#define _TOOLS_LINUX_ASM_X86_ATOMIC_H
+
+#include <linux/compiler.h>
+#include <linux/types.h>
+#include "rmwcc.h"
+
+#define LOCK_PREFIX "\n\tlock; "
+
+/*
+ * Atomic operations that C can't guarantee us.  Useful for
+ * resource counting etc..
+ */
+
+#define ATOMIC_INIT(i)	{ (i) }
+
+/**
+ * atomic_read - read atomic variable
+ * @v: pointer of type atomic_t
+ *
+ * Atomically reads the value of @v.
+ */
+static inline int atomic_read(const atomic_t *v)
+{
+	return ACCESS_ONCE((v)->counter);
+}
+
+/**
+ * atomic_set - set atomic variable
+ * @v: pointer of type atomic_t
+ * @i: required value
+ *
+ * Atomically sets the value of @v to @i.
+ */
+static inline void atomic_set(atomic_t *v, int i)
+{
+	v->counter = i;
+}
+
+/**
+ * atomic_inc - increment atomic variable
+ * @v: pointer of type atomic_t
+ *
+ * Atomically increments @v by 1.
+ */
+static inline void atomic_inc(atomic_t *v)
+{
+	asm volatile(LOCK_PREFIX "incl %0"
+		     : "+m" (v->counter));
+}
+
+/**
+ * atomic_dec_and_test - decrement and test
+ * @v: pointer of type atomic_t
+ *
+ * Atomically decrements @v by 1 and
+ * returns true if the result is 0, or false for all other
+ * cases.
+ */
+static inline int atomic_dec_and_test(atomic_t *v)
+{
+	GEN_UNARY_RMWcc(LOCK_PREFIX "decl", v->counter, "%0", "e");
+}
+
+#endif /* _TOOLS_LINUX_ASM_X86_ATOMIC_H */
diff --git a/tools/arch/x86/include/asm/barrier.h b/tools/arch/x86/include/asm/barrier.h
new file mode 100644
index 000000000000..f366d8e550e4
--- /dev/null
+++ b/tools/arch/x86/include/asm/barrier.h
@@ -0,0 +1,28 @@
+#ifndef _TOOLS_LINUX_ASM_X86_BARRIER_H
+#define _TOOLS_LINUX_ASM_X86_BARRIER_H
+
+/*
+ * Copied from the Linux kernel sources, and also moving code
+ * out from tools/perf/perf-sys.h so as to make it be located
+ * in a place similar as in the kernel sources.
+ *
+ * Force strict CPU ordering.
+ * And yes, this is required on UP too when we're talking
+ * to devices.
+ */
+
+#if defined(__i386__)
+/*
+ * Some non-Intel clones support out of order store. wmb() ceases to be a
+ * nop for these.
+ */
+#define mb()	asm volatile("lock; addl $0,0(%%esp)" ::: "memory")
+#define rmb()	asm volatile("lock; addl $0,0(%%esp)" ::: "memory")
+#define wmb()	asm volatile("lock; addl $0,0(%%esp)" ::: "memory")
+#elif defined(__x86_64__)
+#define mb() 	asm volatile("mfence":::"memory")
+#define rmb()	asm volatile("lfence":::"memory")
+#define wmb()	asm volatile("sfence" ::: "memory")
+#endif
+
+#endif /* _TOOLS_LINUX_ASM_X86_BARRIER_H */
diff --git a/tools/arch/x86/include/asm/rmwcc.h b/tools/arch/x86/include/asm/rmwcc.h
new file mode 100644
index 000000000000..a6669bc06939
--- /dev/null
+++ b/tools/arch/x86/include/asm/rmwcc.h
@@ -0,0 +1,41 @@
+#ifndef _TOOLS_LINUX_ASM_X86_RMWcc
+#define _TOOLS_LINUX_ASM_X86_RMWcc
+
+#ifdef CC_HAVE_ASM_GOTO
+
+#define __GEN_RMWcc(fullop, var, cc, ...)				\
+do {									\
+	asm_volatile_goto (fullop "; j" cc " %l[cc_label]"		\
+			: : "m" (var), ## __VA_ARGS__ 			\
+			: "memory" : cc_label);				\
+	return 0;							\
+cc_label:								\
+	return 1;							\
+} while (0)
+
+#define GEN_UNARY_RMWcc(op, var, arg0, cc) 				\
+	__GEN_RMWcc(op " " arg0, var, cc)
+
+#define GEN_BINARY_RMWcc(op, var, vcon, val, arg0, cc)			\
+	__GEN_RMWcc(op " %1, " arg0, var, cc, vcon (val))
+
+#else /* !CC_HAVE_ASM_GOTO */
+
+#define __GEN_RMWcc(fullop, var, cc, ...)				\
+do {									\
+	char c;								\
+	asm volatile (fullop "; set" cc " %1"				\
+			: "+m" (var), "=qm" (c)				\
+			: __VA_ARGS__ : "memory");			\
+	return c != 0;							\
+} while (0)
+
+#define GEN_UNARY_RMWcc(op, var, arg0, cc)				\
+	__GEN_RMWcc(op " " arg0, var, cc)
+
+#define GEN_BINARY_RMWcc(op, var, vcon, val, arg0, cc)			\
+	__GEN_RMWcc(op " %2, " arg0, var, cc, vcon (val))
+
+#endif /* CC_HAVE_ASM_GOTO */
+
+#endif /* _TOOLS_LINUX_ASM_X86_RMWcc */
diff --git a/tools/arch/xtensa/include/asm/barrier.h b/tools/arch/xtensa/include/asm/barrier.h
new file mode 100644
index 000000000000..583800bd7259
--- /dev/null
+++ b/tools/arch/xtensa/include/asm/barrier.h
@@ -0,0 +1,18 @@
+/*
+ * Copied from the kernel sources to tools/:
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * Copyright (C) 2001 - 2012 Tensilica Inc.
+ */
+
+#ifndef _TOOLS_LINUX_XTENSA_SYSTEM_H
+#define _TOOLS_LINUX_XTENSA_SYSTEM_H
+
+#define mb()  ({ __asm__ __volatile__("memw" : : : "memory"); })
+#define rmb() barrier()
+#define wmb() mb()
+
+#endif /* _TOOLS_LINUX_XTENSA_SYSTEM_H */
diff --git a/tools/build/Makefile.build b/tools/build/Makefile.build
index 10df57237a66..69c35cf09cad 100644
--- a/tools/build/Makefile.build
+++ b/tools/build/Makefile.build
@@ -37,7 +37,7 @@ subdir-obj-y :=
 
 # Build definitions
 build-file := $(dir)/Build
-include $(build-file)
+-include $(build-file)
 
 quiet_cmd_flex  = FLEX     $@
 quiet_cmd_bison = BISON    $@
diff --git a/tools/build/Makefile.feature b/tools/build/Makefile.feature
index 3a0b0ca2a28c..2975632d51e2 100644
--- a/tools/build/Makefile.feature
+++ b/tools/build/Makefile.feature
@@ -27,7 +27,7 @@ endef
 #   the rule that uses them - an example for that is the 'bionic'
 #   feature check. ]
 #
-FEATURE_TESTS =			\
+FEATURE_TESTS ?=			\
 	backtrace			\
 	dwarf				\
 	fortify-source			\
@@ -53,7 +53,7 @@ FEATURE_TESTS =			\
 	zlib				\
 	lzma
 
-FEATURE_DISPLAY =			\
+FEATURE_DISPLAY ?=			\
 	dwarf				\
 	glibc				\
 	gtk2				\
diff --git a/tools/build/tests/ex/Build b/tools/build/tests/ex/Build
index 0e6c3e6767e6..70d876237c57 100644
--- a/tools/build/tests/ex/Build
+++ b/tools/build/tests/ex/Build
@@ -2,6 +2,7 @@ ex-y += ex.o
 ex-y += a.o
 ex-y += b.o
 ex-y += empty/
+ex-y += empty2/
 
 libex-y += c.o
 libex-y += d.o
diff --git a/tools/build/tests/ex/empty2/README b/tools/build/tests/ex/empty2/README
new file mode 100644
index 000000000000..2107cc5bf5a9
--- /dev/null
+++ b/tools/build/tests/ex/empty2/README
@@ -0,0 +1,2 @@
+This directory is left intentionally without Build file
+to test proper nesting into Build-less directories.
diff --git a/tools/include/asm-generic/atomic-gcc.h b/tools/include/asm-generic/atomic-gcc.h
new file mode 100644
index 000000000000..2ba78c9f5701
--- /dev/null
+++ b/tools/include/asm-generic/atomic-gcc.h
@@ -0,0 +1,63 @@
+#ifndef __TOOLS_ASM_GENERIC_ATOMIC_H
+#define __TOOLS_ASM_GENERIC_ATOMIC_H
+
+#include <linux/compiler.h>
+#include <linux/types.h>
+
+/*
+ * Atomic operations that C can't guarantee us.  Useful for
+ * resource counting etc..
+ *
+ * Excerpts obtained from the Linux kernel sources.
+ */
+
+#define ATOMIC_INIT(i)	{ (i) }
+
+/**
+ * atomic_read - read atomic variable
+ * @v: pointer of type atomic_t
+ *
+ * Atomically reads the value of @v.
+ */
+static inline int atomic_read(const atomic_t *v)
+{
+	return ACCESS_ONCE((v)->counter);
+}
+
+/**
+ * atomic_set - set atomic variable
+ * @v: pointer of type atomic_t
+ * @i: required value
+ *
+ * Atomically sets the value of @v to @i.
+ */
+static inline void atomic_set(atomic_t *v, int i)
+{
+        v->counter = i;
+}
+
+/**
+ * atomic_inc - increment atomic variable
+ * @v: pointer of type atomic_t
+ *
+ * Atomically increments @v by 1.
+ */
+static inline void atomic_inc(atomic_t *v)
+{
+	__sync_add_and_fetch(&v->counter, 1);
+}
+
+/**
+ * atomic_dec_and_test - decrement and test
+ * @v: pointer of type atomic_t
+ *
+ * Atomically decrements @v by 1 and
+ * returns true if the result is 0, or false for all other
+ * cases.
+ */
+static inline int atomic_dec_and_test(atomic_t *v)
+{
+	return __sync_sub_and_fetch(&v->counter, 1) == 0;
+}
+
+#endif /* __TOOLS_ASM_GENERIC_ATOMIC_H */
diff --git a/tools/include/asm-generic/barrier.h b/tools/include/asm-generic/barrier.h
new file mode 100644
index 000000000000..47b933903eaf
--- /dev/null
+++ b/tools/include/asm-generic/barrier.h
@@ -0,0 +1,44 @@
+/*
+ * Copied from the kernel sources to tools/perf/:
+ *
+ * Generic barrier definitions, originally based on MN10300 definitions.
+ *
+ * It should be possible to use these on really simple architectures,
+ * but it serves more as a starting point for new ports.
+ *
+ * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public Licence
+ * as published by the Free Software Foundation; either version
+ * 2 of the Licence, or (at your option) any later version.
+ */
+#ifndef __TOOLS_LINUX_ASM_GENERIC_BARRIER_H
+#define __TOOLS_LINUX_ASM_GENERIC_BARRIER_H
+
+#ifndef __ASSEMBLY__
+
+#include <linux/compiler.h>
+
+/*
+ * Force strict CPU ordering. And yes, this is required on UP too when we're
+ * talking to devices.
+ *
+ * Fall back to compiler barriers if nothing better is provided.
+ */
+
+#ifndef mb
+#define mb()	barrier()
+#endif
+
+#ifndef rmb
+#define rmb()	mb()
+#endif
+
+#ifndef wmb
+#define wmb()	mb()
+#endif
+
+#endif /* !__ASSEMBLY__ */
+#endif /* __TOOLS_LINUX_ASM_GENERIC_BARRIER_H */
diff --git a/tools/include/asm/atomic.h b/tools/include/asm/atomic.h
new file mode 100644
index 000000000000..70794f538a86
--- /dev/null
+++ b/tools/include/asm/atomic.h
@@ -0,0 +1,10 @@
+#ifndef __TOOLS_LINUX_ASM_ATOMIC_H
+#define __TOOLS_LINUX_ASM_ATOMIC_H
+
+#if defined(__i386__) || defined(__x86_64__)
+#include "../../arch/x86/include/asm/atomic.h"
+#else
+#include <asm-generic/atomic-gcc.h>
+#endif
+
+#endif /* __TOOLS_LINUX_ASM_ATOMIC_H */
diff --git a/tools/include/asm/barrier.h b/tools/include/asm/barrier.h
new file mode 100644
index 000000000000..ac66ac594685
--- /dev/null
+++ b/tools/include/asm/barrier.h
@@ -0,0 +1,27 @@
+#if defined(__i386__) || defined(__x86_64__)
+#include "../../arch/x86/include/asm/barrier.h"
+#elif defined(__arm__)
+#include "../../arch/arm/include/asm/barrier.h"
+#elif defined(__aarch64__)
+#include "../../arch/arm64/include/asm/barrier.h"
+#elif defined(__powerpc__)
+#include "../../arch/powerpc/include/asm/barrier.h"
+#elif defined(__s390__)
+#include "../../arch/s390/include/asm/barrier.h"
+#elif defined(__sh__)
+#include "../../arch/sh/include/asm/barrier.h"
+#elif defined(__sparc__)
+#include "../../arch/sparc/include/asm/barrier.h"
+#elif defined(__tile__)
+#include "../../arch/tile/include/asm/barrier.h"
+#elif defined(__alpha__)
+#include "../../arch/alpha/include/asm/barrier.h"
+#elif defined(__mips__)
+#include "../../arch/mips/include/asm/barrier.h"
+#elif defined(__ia64__)
+#include "../../arch/ia64/include/asm/barrier.h"
+#elif defined(__xtensa__)
+#include "../../arch/xtensa/include/asm/barrier.h"
+#else
+#include <asm-generic/barrier.h>
+#endif
diff --git a/tools/include/linux/atomic.h b/tools/include/linux/atomic.h
new file mode 100644
index 000000000000..4e3d3d18ebab
--- /dev/null
+++ b/tools/include/linux/atomic.h
@@ -0,0 +1,6 @@
+#ifndef __TOOLS_LINUX_ATOMIC_H
+#define __TOOLS_LINUX_ATOMIC_H
+
+#include <asm/atomic.h>
+
+#endif /* __TOOLS_LINUX_ATOMIC_H */
diff --git a/tools/include/linux/compiler.h b/tools/include/linux/compiler.h
index 88461f09cc86..f0e72674c52d 100644
--- a/tools/include/linux/compiler.h
+++ b/tools/include/linux/compiler.h
@@ -1,6 +1,10 @@
 #ifndef _TOOLS_LINUX_COMPILER_H_
 #define _TOOLS_LINUX_COMPILER_H_
 
+/* Optimization barrier */
+/* The "volatile" is due to gcc bugs */
+#define barrier() __asm__ __volatile__("": : :"memory")
+
 #ifndef __always_inline
 # define __always_inline	inline __attribute__((always_inline))
 #endif
diff --git a/tools/perf/util/include/linux/kernel.h b/tools/include/linux/kernel.h
index 09e8e7aea7c6..76df53539c2a 100644
--- a/tools/perf/util/include/linux/kernel.h
+++ b/tools/include/linux/kernel.h
@@ -1,5 +1,5 @@
-#ifndef PERF_LINUX_KERNEL_H_
-#define PERF_LINUX_KERNEL_H_
+#ifndef __TOOLS_LINUX_KERNEL_H
+#define __TOOLS_LINUX_KERNEL_H
 
 #include <stdarg.h>
 #include <stdio.h>
diff --git a/tools/perf/util/include/linux/list.h b/tools/include/linux/list.h
index 76ddbc726343..76b014c96893 100644
--- a/tools/perf/util/include/linux/list.h
+++ b/tools/include/linux/list.h
@@ -1,10 +1,10 @@
 #include <linux/kernel.h>
 #include <linux/types.h>
 
-#include "../../../../include/linux/list.h"
+#include "../../../include/linux/list.h"
 
-#ifndef PERF_LIST_H
-#define PERF_LIST_H
+#ifndef TOOLS_LIST_H
+#define TOOLS_LIST_H
 /**
  * list_del_range - deletes range of entries from list.
  * @begin: first element in the range to delete from the list.
diff --git a/tools/include/linux/poison.h b/tools/include/linux/poison.h
new file mode 100644
index 000000000000..0c27bdf14233
--- /dev/null
+++ b/tools/include/linux/poison.h
@@ -0,0 +1 @@
+#include "../../../include/linux/poison.h"
diff --git a/tools/include/linux/types.h b/tools/include/linux/types.h
index b5cf25e05df2..8ebf6278b2ef 100644
--- a/tools/include/linux/types.h
+++ b/tools/include/linux/types.h
@@ -60,6 +60,14 @@ typedef __u32 __bitwise __be32;
 typedef __u64 __bitwise __le64;
 typedef __u64 __bitwise __be64;
 
+typedef struct {
+	int counter;
+} atomic_t;
+
+#ifndef __aligned_u64
+# define __aligned_u64 __u64 __attribute__((aligned(8)))
+#endif
+
 struct list_head {
 	struct list_head *next, *prev;
 };
diff --git a/tools/lib/traceevent/.gitignore b/tools/lib/traceevent/.gitignore
index 35f56be5a4cd..3c60335fe7be 100644
--- a/tools/lib/traceevent/.gitignore
+++ b/tools/lib/traceevent/.gitignore
@@ -1 +1,2 @@
 TRACEEVENT-CFLAGS
+libtraceevent-dynamic-list
diff --git a/tools/lib/traceevent/Makefile b/tools/lib/traceevent/Makefile
index d410da335e3d..6daaff652aff 100644
--- a/tools/lib/traceevent/Makefile
+++ b/tools/lib/traceevent/Makefile
@@ -23,6 +23,7 @@ endef
 # Allow setting CC and AR, or setting CROSS_COMPILE as a prefix.
 $(call allow-override,CC,$(CROSS_COMPILE)gcc)
 $(call allow-override,AR,$(CROSS_COMPILE)ar)
+$(call allow-override,NM,$(CROSS_COMPILE)nm)
 
 EXT = -std=gnu99
 INSTALL = install
@@ -34,9 +35,15 @@ INSTALL = install
 DESTDIR ?=
 DESTDIR_SQ = '$(subst ','\'',$(DESTDIR))'
 
+LP64 := $(shell echo __LP64__ | ${CC} ${CFLAGS} -E -x c - | tail -n 1)
+ifeq ($(LP64), 1)
+  libdir_relative = lib64
+else
+  libdir_relative = lib
+endif
+
 prefix ?= /usr/local
-bindir_relative = bin
-bindir = $(prefix)/$(bindir_relative)
+libdir = $(prefix)/$(libdir_relative)
 man_dir = $(prefix)/share/man
 man_dir_SQ = '$(subst ','\'',$(man_dir))'
 
@@ -58,7 +65,7 @@ ifeq ($(prefix),$(HOME))
 override plugin_dir = $(HOME)/.traceevent/plugins
 set_plugin_dir := 0
 else
-override plugin_dir = $(prefix)/lib/traceevent/plugins
+override plugin_dir = $(libdir)/traceevent/plugins
 endif
 endif
 
@@ -85,11 +92,11 @@ srctree := $(patsubst %/,%,$(dir $(srctree)))
 #$(info Determined 'srctree' to be $(srctree))
 endif
 
-export prefix bindir src obj
+export prefix libdir src obj
 
 # Shell quotes
-bindir_SQ = $(subst ','\'',$(bindir))
-bindir_relative_SQ = $(subst ','\'',$(bindir_relative))
+libdir_SQ = $(subst ','\'',$(libdir))
+libdir_relative_SQ = $(subst ','\'',$(libdir_relative))
 plugin_dir_SQ = $(subst ','\'',$(plugin_dir))
 
 LIB_FILE = libtraceevent.a libtraceevent.so
@@ -151,8 +158,9 @@ PLUGINS_IN := $(PLUGINS:.so=-in.o)
 
 TE_IN    := $(OUTPUT)libtraceevent-in.o
 LIB_FILE := $(addprefix $(OUTPUT),$(LIB_FILE))
+DYNAMIC_LIST_FILE := $(OUTPUT)libtraceevent-dynamic-list
 
-CMD_TARGETS = $(LIB_FILE) $(PLUGINS)
+CMD_TARGETS = $(LIB_FILE) $(PLUGINS) $(DYNAMIC_LIST_FILE)
 
 TARGETS = $(CMD_TARGETS)
 
@@ -169,6 +177,9 @@ $(OUTPUT)libtraceevent.so: $(TE_IN)
 $(OUTPUT)libtraceevent.a: $(TE_IN)
 	$(QUIET_LINK)$(RM) $@; $(AR) rcs $@ $^
 
+$(OUTPUT)libtraceevent-dynamic-list: $(PLUGINS)
+	$(QUIET_GEN)$(call do_generate_dynamic_list_file, $(PLUGINS), $@)
+
 plugins: $(PLUGINS)
 
 __plugin_obj = $(notdir $@)
@@ -238,9 +249,16 @@ define do_install_plugins
 	done
 endef
 
+define do_generate_dynamic_list_file
+	(echo '{';							\
+	$(NM) -u -D $1 | awk 'NF>1 {print "\t"$$2";"}' | sort -u;	\
+	echo '};';							\
+	) > $2
+endef
+
 install_lib: all_cmd install_plugins
 	$(call QUIET_INSTALL, $(LIB_FILE)) \
-		$(call do_install,$(LIB_FILE),$(bindir_SQ))
+		$(call do_install,$(LIB_FILE),$(libdir_SQ))
 
 install_plugins: $(PLUGINS)
 	$(call QUIET_INSTALL, trace_plugins) \
diff --git a/tools/lib/traceevent/event-parse.c b/tools/lib/traceevent/event-parse.c
index 29f94f6f0d9e..cc25f059ab3d 100644
--- a/tools/lib/traceevent/event-parse.c
+++ b/tools/lib/traceevent/event-parse.c
@@ -1387,7 +1387,7 @@ static int event_read_fields(struct event_format *event, struct format_field **f
 			do_warning_event(event, "%s: no type found", __func__);
 			goto fail;
 		}
-		field->name = last_token;
+		field->name = field->alias = last_token;
 
 		if (test_type(type, EVENT_OP))
 			goto fail;
@@ -1469,7 +1469,7 @@ static int event_read_fields(struct event_format *event, struct format_field **f
 				size_dynamic = type_size(field->name);
 				free_token(field->name);
 				strcat(field->type, brackets);
-				field->name = token;
+				field->name = field->alias = token;
 				type = read_token(&token);
 			} else {
 				char *new_type;
@@ -6444,6 +6444,8 @@ void pevent_ref(struct pevent *pevent)
 void pevent_free_format_field(struct format_field *field)
 {
 	free(field->type);
+	if (field->alias != field->name)
+		free(field->alias);
 	free(field->name);
 	free(field);
 }
diff --git a/tools/lib/traceevent/event-parse.h b/tools/lib/traceevent/event-parse.h
index 86a5839fb048..063b1971eb35 100644
--- a/tools/lib/traceevent/event-parse.h
+++ b/tools/lib/traceevent/event-parse.h
@@ -191,6 +191,7 @@ struct format_field {
 	struct event_format	*event;
 	char			*type;
 	char			*name;
+	char			*alias;
 	int			offset;
 	int			size;
 	unsigned int		arraylen;
diff --git a/tools/lib/traceevent/plugin_cfg80211.c b/tools/lib/traceevent/plugin_cfg80211.c
index 4592d8438318..ec57d0c1fbc2 100644
--- a/tools/lib/traceevent/plugin_cfg80211.c
+++ b/tools/lib/traceevent/plugin_cfg80211.c
@@ -4,6 +4,19 @@
 #include <endian.h>
 #include "event-parse.h"
 
+/*
+ * From glibc endian.h, for older systems where it is not present, e.g.: RHEL5,
+ * Fedora6.
+ */
+#ifndef le16toh
+# if __BYTE_ORDER == __LITTLE_ENDIAN
+#  define le16toh(x) (x)
+# else
+#  define le16toh(x) __bswap_16 (x)
+# endif
+#endif
+
+
 static unsigned long long
 process___le16_to_cpup(struct trace_seq *s, unsigned long long *args)
 {
diff --git a/tools/perf/.gitignore b/tools/perf/.gitignore
index 812f904193e8..09db62ba5786 100644
--- a/tools/perf/.gitignore
+++ b/tools/perf/.gitignore
@@ -28,3 +28,4 @@ config.mak.autogen
 *-flex.*
 *.pyc
 *.pyo
+.config-detected
diff --git a/tools/perf/Documentation/callchain-overhead-calculation.txt b/tools/perf/Documentation/callchain-overhead-calculation.txt
new file mode 100644
index 000000000000..1a757927195e
--- /dev/null
+++ b/tools/perf/Documentation/callchain-overhead-calculation.txt
@@ -0,0 +1,108 @@
+Overhead calculation
+--------------------
+The overhead can be shown in two columns as 'Children' and 'Self' when
+perf collects callchains.  The 'self' overhead is simply calculated by
+adding all period values of the entry - usually a function (symbol).
+This is the value that perf shows traditionally and sum of all the
+'self' overhead values should be 100%.
+
+The 'children' overhead is calculated by adding all period values of
+the child functions so that it can show the total overhead of the
+higher level functions even if they don't directly execute much.
+'Children' here means functions that are called from another (parent)
+function.
+
+It might be confusing that the sum of all the 'children' overhead
+values exceeds 100% since each of them is already an accumulation of
+'self' overhead of its child functions.  But with this enabled, users
+can find which function has the most overhead even if samples are
+spread over the children.
+
+Consider the following example; there are three functions like below.
+
+-----------------------
+void foo(void) {
+    /* do something */
+}
+
+void bar(void) {
+    /* do something */
+    foo();
+}
+
+int main(void) {
+    bar()
+    return 0;
+}
+-----------------------
+
+In this case 'foo' is a child of 'bar', and 'bar' is an immediate
+child of 'main' so 'foo' also is a child of 'main'.  In other words,
+'main' is a parent of 'foo' and 'bar', and 'bar' is a parent of 'foo'.
+
+Suppose all samples are recorded in 'foo' and 'bar' only.  When it's
+recorded with callchains the output will show something like below
+in the usual (self-overhead-only) output of perf report:
+
+----------------------------------
+Overhead  Symbol
+........  .....................
+  60.00%  foo
+          |
+          --- foo
+              bar
+              main
+              __libc_start_main
+
+  40.00%  bar
+          |
+          --- bar
+              main
+              __libc_start_main
+----------------------------------
+
+When the --children option is enabled, the 'self' overhead values of
+child functions (i.e. 'foo' and 'bar') are added to the parents to
+calculate the 'children' overhead.  In this case the report could be
+displayed as:
+
+-------------------------------------------
+Children      Self  Symbol
+........  ........  ....................
+ 100.00%     0.00%  __libc_start_main
+          |
+          --- __libc_start_main
+
+ 100.00%     0.00%  main
+          |
+          --- main
+              __libc_start_main
+
+ 100.00%    40.00%  bar
+          |
+          --- bar
+              main
+              __libc_start_main
+
+  60.00%    60.00%  foo
+          |
+          --- foo
+              bar
+              main
+              __libc_start_main
+-------------------------------------------
+
+In the above output, the 'self' overhead of 'foo' (60%) was add to the
+'children' overhead of 'bar', 'main' and '\_\_libc_start_main'.
+Likewise, the 'self' overhead of 'bar' (40%) was added to the
+'children' overhead of 'main' and '\_\_libc_start_main'.
+
+So '\_\_libc_start_main' and 'main' are shown first since they have
+same (100%) 'children' overhead (even though they have zero 'self'
+overhead) and they are the parents of 'foo' and 'bar'.
+
+Since v3.16 the 'children' overhead is shown by default and the output
+is sorted by its values. The 'children' overhead is disabled by
+specifying --no-children option on the command line or by adding
+'report.children = false' or 'top.children = false' in the perf config
+file.
diff --git a/tools/perf/Documentation/perf-bench.txt b/tools/perf/Documentation/perf-bench.txt
index f6480cbf309b..bf3d0644bf10 100644
--- a/tools/perf/Documentation/perf-bench.txt
+++ b/tools/perf/Documentation/perf-bench.txt
@@ -210,6 +210,9 @@ Suite for evaluating hash tables.
 *wake*::
 Suite for evaluating wake calls.
 
+*wake-parallel*::
+Suite for evaluating parallel wake calls.
+
 *requeue*::
 Suite for evaluating requeue calls.
 
diff --git a/tools/perf/Documentation/perf-inject.txt b/tools/perf/Documentation/perf-inject.txt
index dc7442cf3d7f..b876ae312699 100644
--- a/tools/perf/Documentation/perf-inject.txt
+++ b/tools/perf/Documentation/perf-inject.txt
@@ -44,6 +44,33 @@ OPTIONS
 --kallsyms=<file>::
 	kallsyms pathname
 
+--itrace::
+	Decode Instruction Tracing data, replacing it with synthesized events.
+	Options are:
+
+		i	synthesize instructions events
+		b	synthesize branches events
+		c	synthesize branches events (calls only)
+		r	synthesize branches events (returns only)
+		x	synthesize transactions events
+		e	synthesize error events
+		d	create a debug log
+		g	synthesize a call chain (use with i or x)
+
+	The default is all events i.e. the same as --itrace=ibxe
+
+	In addition, the period (default 100000) for instructions events
+	can be specified in units of:
+
+		i	instructions
+		t	ticks
+		ms	milliseconds
+		us	microseconds
+		ns	nanoseconds (default)
+
+	Also the call chain size (default 16, max. 1024) for instructions or
+	transactions events can be specified.
+
 SEE ALSO
 --------
 linkperf:perf-record[1], linkperf:perf-report[1], linkperf:perf-archive[1]
diff --git a/tools/perf/Documentation/perf-kmem.txt b/tools/perf/Documentation/perf-kmem.txt
index 23219c65c16f..ff0f433b3fce 100644
--- a/tools/perf/Documentation/perf-kmem.txt
+++ b/tools/perf/Documentation/perf-kmem.txt
@@ -37,7 +37,11 @@ OPTIONS
 
 -s <key[,key2...]>::
 --sort=<key[,key2...]>::
-	Sort the output (default: frag,hit,bytes)
+	Sort the output (default: 'frag,hit,bytes' for slab and 'bytes,hit'
+	for page).  Available sort keys are 'ptr, callsite, bytes, hit,
+	pingpong, frag' for slab and 'page, callsite, bytes, hit, order,
+	migtype, gfp' for page.  This option should be preceded by one of the
+	mode selection options - i.e. --slab, --page, --alloc and/or --caller.
 
 -l <num>::
 --line=<num>::
@@ -52,6 +56,11 @@ OPTIONS
 --page::
 	Analyze page allocator events
 
+--live::
+	Show live page stat.  The perf kmem shows total allocation stat by
+	default, but this option shows live (currently allocated) pages
+	instead.  (This option works with --page option only)
+
 SEE ALSO
 --------
 linkperf:perf-record[1]
diff --git a/tools/perf/Documentation/perf-kvm.txt b/tools/perf/Documentation/perf-kvm.txt
index 6252e776009c..6a5bb2b17039 100644
--- a/tools/perf/Documentation/perf-kvm.txt
+++ b/tools/perf/Documentation/perf-kvm.txt
@@ -151,6 +151,12 @@ STAT LIVE OPTIONS
        Show events other than HLT (x86 only) or Wait state (s390 only)
        that take longer than duration usecs.
 
+--proc-map-timeout::
+	When processing pre-existing threads /proc/XXX/mmap, it may take
+	a long time, because the file may be huge. A time out is needed
+	in such cases.
+	This option sets the time out limit. The default value is 500 ms.
+
 SEE ALSO
 --------
 linkperf:perf-top[1], linkperf:perf-record[1], linkperf:perf-report[1],
diff --git a/tools/perf/Documentation/perf-probe.txt b/tools/perf/Documentation/perf-probe.txt
index 239609c09f83..3a8a9ba2b041 100644
--- a/tools/perf/Documentation/perf-probe.txt
+++ b/tools/perf/Documentation/perf-probe.txt
@@ -14,11 +14,13 @@ or
 or
 'perf probe' [options] --del='[GROUP:]EVENT' [...]
 or
-'perf probe' --list
+'perf probe' --list[=[GROUP:]EVENT]
 or
 'perf probe' [options] --line='LINE'
 or
 'perf probe' [options] --vars='PROBEPOINT'
+or
+'perf probe' [options] --funcs
 
 DESCRIPTION
 -----------
@@ -64,8 +66,8 @@ OPTIONS
 	classes(e.g. [a-z], [!A-Z]).
 
 -l::
---list::
-	List up current probe events.
+--list[=[GROUP:]EVENT]::
+	List up current probe events. This can also accept filtering patterns of event names.
 
 -L::
 --line=::
@@ -81,10 +83,15 @@ OPTIONS
 	(Only for --vars) Show external defined variables in addition to local
 	variables.
 
+--no-inlines::
+	(Only for --add) Search only for non-inlined functions. The functions
+	which do not have instances are ignored.
+
 -F::
---funcs::
+--funcs[=FILTER]::
 	Show available functions in given module or kernel. With -x/--exec,
 	can also list functions in a user space executable / shared library.
+	This also can accept a FILTER rule argument.
 
 --filter=FILTER::
 	(Only for --vars and --funcs) Set filter. FILTER is a combination of glob
@@ -148,7 +155,7 @@ Each probe argument follows below syntax.
  [NAME=]LOCALVAR|$retval|%REG|@SYMBOL[:TYPE]
 
 'NAME' specifies the name of this argument (optional). You can use the name of local variable, local data structure member (e.g. var->field, var.field2), local array with fixed index (e.g. array[1], var->array[0], var->pointer[2]), or kprobe-tracer argument format (e.g. $retval, %ax, etc). Note that the name of this argument will be set as the last member name if you specify a local data structure member (e.g. field2 for 'var->field1.field2'.)
-'$vars' special argument is also available for NAME, it is expanded to the local variables which can access at given probe point.
+'$vars' and '$params' special arguments are also available for NAME, '$vars' is expanded to the local variables (including function parameters) which can access at given probe point. '$params' is expanded to only the function parameters.
 'TYPE' casts the type of this argument (optional). If omitted, perf probe automatically set the type based on debuginfo. You can specify 'string' type only for the local variable or structure member which is an array of or a pointer to 'char' or 'unsigned char' type.
 
 On x86 systems %REG is always the short form of the register: for example %AX. %RAX or %EAX is not valid.
diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt
index 4847a793de65..9b9d9d086680 100644
--- a/tools/perf/Documentation/perf-record.txt
+++ b/tools/perf/Documentation/perf-record.txt
@@ -108,6 +108,8 @@ OPTIONS
 	Number of mmap data pages (must be a power of two) or size
 	specification with appended unit character - B/K/M/G. The
 	size is rounded up to have nearest pages power of two value.
+	Also, by adding a comma, the number of mmap pages for AUX
+	area tracing can be specified.
 
 --group::
 	Put all events in a single event group.  This precedes the --event
@@ -145,16 +147,21 @@ OPTIONS
 
 -s::
 --stat::
-	Per thread counts.
+	Record per-thread event counts.  Use it with 'perf report -T' to see
+	the values.
 
 -d::
 --data::
-	Sample addresses.
+	Record the sample addresses.
 
 -T::
 --timestamp::
-	Sample timestamps. Use it with 'perf report -D' to see the timestamps,
-	for instance.
+	Record the sample timestamps. Use it with 'perf report -D' to see the
+	timestamps, for instance.
+
+-P::
+--period::
+	Record the sample period.
 
 -n::
 --no-samples::
@@ -257,6 +264,18 @@ records. See clock_gettime(). In particular CLOCK_MONOTONIC and
 CLOCK_MONOTONIC_RAW are supported, some events might also allow
 CLOCK_BOOTTIME, CLOCK_REALTIME and CLOCK_TAI.
 
+-S::
+--snapshot::
+Select AUX area tracing Snapshot Mode. This option is valid only with an
+AUX area tracing event. Optionally the number of bytes to capture per
+snapshot can be specified. In Snapshot Mode, trace data is captured only when
+signal SIGUSR2 is received.
+
+--proc-map-timeout::
+When processing pre-existing threads /proc/XXX/mmap, it may take a long time,
+because the file may be huge. A time out is needed in such cases.
+This option sets the time out limit. The default value is 500 ms.
+
 SEE ALSO
 --------
 linkperf:perf-stat[1], linkperf:perf-list[1]
diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt
index 4879cf638824..c33b69f3374f 100644
--- a/tools/perf/Documentation/perf-report.txt
+++ b/tools/perf/Documentation/perf-report.txt
@@ -34,7 +34,8 @@ OPTIONS
 
 -T::
 --threads::
-	Show per-thread event counters
+	Show per-thread event counters.  The input data file should be recorded
+	with -s option.
 -c::
 --comms=::
 	Only consider symbols in these comms. CSV that understands
@@ -193,6 +194,7 @@ OPTIONS
 	Accumulate callchain of children to parent entry so that then can
 	show up in the output.  The output will have a new "Children" column
 	and will be sorted on the data.  It requires callchains are recorded.
+	See the `overhead calculation' section for more details.
 
 --max-stack::
 	Set the stack depth limit when parsing the callchain, anything
@@ -323,6 +325,37 @@ OPTIONS
 --header-only::
 	Show only perf.data header (forces --stdio).
 
+--itrace::
+	Options for decoding instruction tracing data. The options are:
+
+		i	synthesize instructions events
+		b	synthesize branches events
+		c	synthesize branches events (calls only)
+		r	synthesize branches events (returns only)
+		x	synthesize transactions events
+		e	synthesize error events
+		d	create a debug log
+		g	synthesize a call chain (use with i or x)
+
+	The default is all events i.e. the same as --itrace=ibxe
+
+	In addition, the period (default 100000) for instructions events
+	can be specified in units of:
+
+		i	instructions
+		t	ticks
+		ms	milliseconds
+		us	microseconds
+		ns	nanoseconds (default)
+
+	Also the call chain size (default 16, max. 1024) for instructions or
+	transactions events can be specified.
+
+	To disable decoding entirely, use --no-itrace.
+
+
+include::callchain-overhead-calculation.txt[]
+
 SEE ALSO
 --------
 linkperf:perf-stat[1], linkperf:perf-annotate[1]
diff --git a/tools/perf/Documentation/perf-script.txt b/tools/perf/Documentation/perf-script.txt
index 79445750fcb3..c82df572fac2 100644
--- a/tools/perf/Documentation/perf-script.txt
+++ b/tools/perf/Documentation/perf-script.txt
@@ -115,7 +115,8 @@ OPTIONS
 -f::
 --fields::
         Comma separated list of fields to print. Options are:
-        comm, tid, pid, time, cpu, event, trace, ip, sym, dso, addr, symoff, srcline, period.
+        comm, tid, pid, time, cpu, event, trace, ip, sym, dso, addr, symoff,
+	srcline, period, flags.
         Field list can be prepended with the type, trace, sw or hw,
         to indicate to which event type the field list applies.
         e.g., -f sw:comm,tid,time,ip,sym  and -f trace:time,cpu,trace
@@ -165,6 +166,12 @@ OPTIONS
 
 	At this point usage is displayed, and perf-script exits.
 
+	The flags field is synthesized and may have a value when Instruction
+	Trace decoding. The flags are "bcrosyiABEx" which stand for branch,
+	call, return, conditional, system, asynchronous, interrupt,
+	transaction abort, trace begin, trace end, and in transaction,
+	respectively.
+
 	Finally, a user may not set fields to none for all event types.
 	i.e., -f "" is not allowed.
 
@@ -221,6 +228,34 @@ OPTIONS
 --header-only
 	Show only perf.data header.
 
+--itrace::
+	Options for decoding instruction tracing data. The options are:
+
+		i	synthesize instructions events
+		b	synthesize branches events
+		c	synthesize branches events (calls only)
+		r	synthesize branches events (returns only)
+		x	synthesize transactions events
+		e	synthesize error events
+		d	create a debug log
+		g	synthesize a call chain (use with i or x)
+
+	The default is all events i.e. the same as --itrace=ibxe
+
+	In addition, the period (default 100000) for instructions events
+	can be specified in units of:
+
+		i	instructions
+		t	ticks
+		ms	milliseconds
+		us	microseconds
+		ns	nanoseconds (default)
+
+	Also the call chain size (default 16, max. 1024) for instructions or
+	transactions events can be specified.
+
+	To disable decoding entirely, use --no-itrace.
+
 SEE ALSO
 --------
 linkperf:perf-record[1], linkperf:perf-script-perl[1],
diff --git a/tools/perf/Documentation/perf-top.txt b/tools/perf/Documentation/perf-top.txt
index 3265b1070518..776aec4d0927 100644
--- a/tools/perf/Documentation/perf-top.txt
+++ b/tools/perf/Documentation/perf-top.txt
@@ -168,7 +168,7 @@ Default is to monitor all CPUS.
 	Accumulate callchain of children to parent entry so that then can
 	show up in the output.  The output will have a new "Children" column
 	and will be sorted on the data.  It requires -g/--call-graph option
-	enabled.
+	enabled.  See the `overhead calculation' section for more details.
 
 --max-stack::
 	Set the stack depth limit when parsing the callchain, anything
@@ -201,6 +201,12 @@ Default is to monitor all CPUS.
 	Force each column width to the provided list, for large terminal
 	readability.  0 means no limit (default behavior).
 
+--proc-map-timeout::
+	When processing pre-existing threads /proc/XXX/mmap, it may take
+	a long time, because the file may be huge. A time out is needed
+	in such cases.
+	This option sets the time out limit. The default value is 500 ms.
+
 
 INTERACTIVE PROMPTING KEYS
 --------------------------
@@ -234,6 +240,7 @@ INTERACTIVE PROMPTING KEYS
 
 Pressing any unmapped key displays a menu, and prompts for input.
 
+include::callchain-overhead-calculation.txt[]
 
 SEE ALSO
 --------
diff --git a/tools/perf/Documentation/perf-trace.txt b/tools/perf/Documentation/perf-trace.txt
index ba03fd5d1a54..7ea078658a87 100644
--- a/tools/perf/Documentation/perf-trace.txt
+++ b/tools/perf/Documentation/perf-trace.txt
@@ -35,7 +35,7 @@ OPTIONS
 
 -e::
 --expr::
-	List of events to show, currently only syscall names.
+	List of syscalls to show, currently only syscall names.
 	Prefixing with ! shows all syscalls but the ones specified.  You may
 	need to escape it.
 
@@ -121,6 +121,11 @@ the thread executes on the designated CPUs. Default is to monitor all CPUs.
 --event::
 	Trace other events, see 'perf list' for a complete list.
 
+--proc-map-timeout::
+	When processing pre-existing threads /proc/XXX/mmap, it may take a long time,
+	because the file may be huge. A time out is needed in such cases.
+	This option sets the time out limit. The default value is 500 ms.
+
 PAGEFAULTS
 ----------
 
diff --git a/tools/perf/MANIFEST b/tools/perf/MANIFEST
index 11ccbb22ea2b..fe50a1b34aa0 100644
--- a/tools/perf/MANIFEST
+++ b/tools/perf/MANIFEST
@@ -1,12 +1,30 @@
 tools/perf
+tools/arch/alpha/include/asm/barrier.h
+tools/arch/arm/include/asm/barrier.h
+tools/arch/ia64/include/asm/barrier.h
+tools/arch/mips/include/asm/barrier.h
+tools/arch/powerpc/include/asm/barrier.h
+tools/arch/s390/include/asm/barrier.h
+tools/arch/sh/include/asm/barrier.h
+tools/arch/sparc/include/asm/barrier.h
+tools/arch/sparc/include/asm/barrier_32.h
+tools/arch/sparc/include/asm/barrier_64.h
+tools/arch/tile/include/asm/barrier.h
+tools/arch/x86/include/asm/barrier.h
+tools/arch/xtensa/include/asm/barrier.h
 tools/scripts
 tools/build
+tools/arch/x86/include/asm/atomic.h
+tools/arch/x86/include/asm/rmwcc.h
 tools/lib/traceevent
 tools/lib/api
 tools/lib/symbol/kallsyms.c
 tools/lib/symbol/kallsyms.h
 tools/lib/util/find_next_bit.c
+tools/include/asm/atomic.h
+tools/include/asm/barrier.h
 tools/include/asm/bug.h
+tools/include/asm-generic/barrier.h
 tools/include/asm-generic/bitops/arch_hweight.h
 tools/include/asm-generic/bitops/atomic.h
 tools/include/asm-generic/bitops/const_hweight.h
@@ -17,35 +35,35 @@ tools/include/asm-generic/bitops/fls64.h
 tools/include/asm-generic/bitops/fls.h
 tools/include/asm-generic/bitops/hweight.h
 tools/include/asm-generic/bitops.h
+tools/include/linux/atomic.h
 tools/include/linux/bitops.h
 tools/include/linux/compiler.h
 tools/include/linux/export.h
 tools/include/linux/hash.h
+tools/include/linux/kernel.h
+tools/include/linux/list.h
 tools/include/linux/log2.h
+tools/include/linux/poison.h
 tools/include/linux/types.h
 include/asm-generic/bitops/arch_hweight.h
 include/asm-generic/bitops/const_hweight.h
 include/asm-generic/bitops/fls64.h
 include/asm-generic/bitops/__fls.h
 include/asm-generic/bitops/fls.h
-include/linux/const.h
 include/linux/perf_event.h
 include/linux/rbtree.h
 include/linux/list.h
 include/linux/hash.h
 include/linux/stringify.h
-lib/find_next_bit.c
 lib/hweight.c
 lib/rbtree.c
 include/linux/swab.h
 arch/*/include/asm/unistd*.h
-arch/*/include/asm/perf_regs.h
 arch/*/include/uapi/asm/unistd*.h
 arch/*/include/uapi/asm/perf_regs.h
 arch/*/lib/memcpy*.S
 arch/*/lib/memset*.S
 include/linux/poison.h
-include/linux/magic.h
 include/linux/hw_breakpoint.h
 include/linux/rbtree_augmented.h
 include/uapi/linux/perf_event.h
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index c43a20517591..1af0cfeb7a57 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -73,6 +73,8 @@ include config/utilities.mak
 # for CTF data format.
 #
 # Define NO_LZMA if you do not want to support compressed (xz) kernel modules
+#
+# Define NO_AUXTRACE if you do not want AUX area tracing support
 
 ifeq ($(srctree),)
 srctree := $(patsubst %/,%,$(dir $(shell pwd)))
@@ -171,6 +173,9 @@ endif
 LIBTRACEEVENT = $(TE_PATH)libtraceevent.a
 export LIBTRACEEVENT
 
+LIBTRACEEVENT_DYNAMIC_LIST = $(TE_PATH)libtraceevent-dynamic-list
+LIBTRACEEVENT_DYNAMIC_LIST_LDFLAGS = -Xlinker --dynamic-list=$(LIBTRACEEVENT_DYNAMIC_LIST)
+
 LIBAPI = $(LIB_PATH)libapi.a
 export LIBAPI
 
@@ -185,8 +190,9 @@ python-clean := $(call QUIET_CLEAN, python) $(RM) -r $(PYTHON_EXTBUILD) $(OUTPUT
 PYTHON_EXT_SRCS := $(shell grep -v ^\# util/python-ext-sources)
 PYTHON_EXT_DEPS := util/python-ext-sources util/setup.py $(LIBTRACEEVENT) $(LIBAPI)
 
-$(OUTPUT)python/perf.so: $(PYTHON_EXT_SRCS) $(PYTHON_EXT_DEPS)
-	$(QUIET_GEN)CFLAGS='$(CFLAGS)' $(PYTHON_WORD) util/setup.py \
+$(OUTPUT)python/perf.so: $(PYTHON_EXT_SRCS) $(PYTHON_EXT_DEPS) $(LIBTRACEEVENT_DYNAMIC_LIST)
+	$(QUIET_GEN)CFLAGS='$(CFLAGS)' LDFLAGS='$(LDFLAGS) $(LIBTRACEEVENT_DYNAMIC_LIST_LDFLAGS)' \
+	  $(PYTHON_WORD) util/setup.py \
 	  --quiet build_ext; \
 	mkdir -p $(OUTPUT)python && \
 	cp $(PYTHON_EXTBUILD_LIB)perf.so $(OUTPUT)python/
@@ -276,8 +282,9 @@ build := -f $(srctree)/tools/build/Makefile.build dir=. obj
 $(PERF_IN): $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)common-cmds.h FORCE
 	$(Q)$(MAKE) $(build)=perf
 
-$(OUTPUT)perf: $(PERFLIBS) $(PERF_IN)
-	$(QUIET_LINK)$(CC) $(CFLAGS) $(LDFLAGS) $(PERF_IN) $(LIBS) -o $@
+$(OUTPUT)perf: $(PERFLIBS) $(PERF_IN) $(LIBTRACEEVENT_DYNAMIC_LIST)
+	$(QUIET_LINK)$(CC) $(CFLAGS) $(LDFLAGS) $(LIBTRACEEVENT_DYNAMIC_LIST_LDFLAGS) \
+		$(PERF_IN) $(LIBS) -o $@
 
 $(GTK_IN): FORCE
 	$(Q)$(MAKE) $(build)=gtk
@@ -371,7 +378,13 @@ $(LIB_FILE): $(LIBPERF_IN)
 LIBTRACEEVENT_FLAGS += plugin_dir=$(plugindir_SQ)
 
 $(LIBTRACEEVENT): FORCE
-	$(Q)$(MAKE) -C $(TRACE_EVENT_DIR) $(LIBTRACEEVENT_FLAGS) O=$(OUTPUT) $(OUTPUT)libtraceevent.a plugins
+	$(Q)$(MAKE) -C $(TRACE_EVENT_DIR) $(LIBTRACEEVENT_FLAGS) O=$(OUTPUT) $(OUTPUT)libtraceevent.a
+
+libtraceevent_plugins: FORCE
+	$(Q)$(MAKE) -C $(TRACE_EVENT_DIR) $(LIBTRACEEVENT_FLAGS) O=$(OUTPUT) plugins
+
+$(LIBTRACEEVENT_DYNAMIC_LIST): libtraceevent_plugins
+	$(Q)$(MAKE) -C $(TRACE_EVENT_DIR) $(LIBTRACEEVENT_FLAGS) O=$(OUTPUT) $(OUTPUT)libtraceevent-dynamic-list
 
 $(LIBTRACEEVENT)-clean:
 	$(call QUIET_CLEAN, libtraceevent)
@@ -462,7 +475,7 @@ check: $(OUTPUT)common-cmds.h
 
 install-gtk:
 
-install-bin: all install-gtk
+install-tools: all install-gtk
 	$(call QUIET_INSTALL, binaries) \
 		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(bindir_SQ)'; \
 		$(INSTALL) $(OUTPUT)perf '$(DESTDIR_SQ)$(bindir_SQ)'; \
@@ -500,12 +513,16 @@ endif
 	$(call QUIET_INSTALL, perf_completion-script) \
 		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(sysconfdir_SQ)/bash_completion.d'; \
 		$(INSTALL) perf-completion.sh '$(DESTDIR_SQ)$(sysconfdir_SQ)/bash_completion.d/perf'
+
+install-tests: all install-gtk
 	$(call QUIET_INSTALL, tests) \
 		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests'; \
 		$(INSTALL) tests/attr.py '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests'; \
 		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/attr'; \
 		$(INSTALL) tests/attr/* '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/attr'
 
+install-bin: install-tools install-tests
+
 install: install-bin try-install-man install-traceevent-plugins
 
 install-python_ext:
@@ -549,4 +566,5 @@ FORCE:
 .PHONY: all install clean config-clean strip install-gtk
 .PHONY: shell_compatibility_test please_set_SHELL_PATH_to_a_more_modern_shell
 .PHONY: $(GIT-HEAD-PHONY) TAGS tags cscope FORCE single_dep
+.PHONY: libtraceevent_plugins
 
diff --git a/tools/perf/arch/arm64/Build b/tools/perf/arch/arm64/Build
index 54afe4a467e7..41bf61da476a 100644
--- a/tools/perf/arch/arm64/Build
+++ b/tools/perf/arch/arm64/Build
@@ -1 +1,2 @@
 libperf-y += util/
+libperf-$(CONFIG_DWARF_UNWIND) += tests/
diff --git a/tools/perf/arch/arm64/include/perf_regs.h b/tools/perf/arch/arm64/include/perf_regs.h
index 1d3f39c3aa56..4e5af27e3fbf 100644
--- a/tools/perf/arch/arm64/include/perf_regs.h
+++ b/tools/perf/arch/arm64/include/perf_regs.h
@@ -5,8 +5,11 @@
 #include <linux/types.h>
 #include <asm/perf_regs.h>
 
+void perf_regs_load(u64 *regs);
+
 #define PERF_REGS_MASK	((1ULL << PERF_REG_ARM64_MAX) - 1)
 #define PERF_REGS_MAX	PERF_REG_ARM64_MAX
+#define PERF_SAMPLE_REGS_ABI	PERF_SAMPLE_REGS_ABI_64
 
 #define PERF_REG_IP	PERF_REG_ARM64_PC
 #define PERF_REG_SP	PERF_REG_ARM64_SP
diff --git a/tools/perf/arch/arm64/tests/Build b/tools/perf/arch/arm64/tests/Build
new file mode 100644
index 000000000000..b30eff9bcc83
--- /dev/null
+++ b/tools/perf/arch/arm64/tests/Build
@@ -0,0 +1,2 @@
+libperf-y += regs_load.o
+libperf-y += dwarf-unwind.o
diff --git a/tools/perf/arch/arm64/tests/dwarf-unwind.c b/tools/perf/arch/arm64/tests/dwarf-unwind.c
new file mode 100644
index 000000000000..cf04a4c91c59
--- /dev/null
+++ b/tools/perf/arch/arm64/tests/dwarf-unwind.c
@@ -0,0 +1,61 @@
+#include <string.h>
+#include "perf_regs.h"
+#include "thread.h"
+#include "map.h"
+#include "event.h"
+#include "debug.h"
+#include "tests/tests.h"
+
+#define STACK_SIZE 8192
+
+static int sample_ustack(struct perf_sample *sample,
+		struct thread *thread, u64 *regs)
+{
+	struct stack_dump *stack = &sample->user_stack;
+	struct map *map;
+	unsigned long sp;
+	u64 stack_size, *buf;
+
+	buf = malloc(STACK_SIZE);
+	if (!buf) {
+		pr_debug("failed to allocate sample uregs data\n");
+		return -1;
+	}
+
+	sp = (unsigned long) regs[PERF_REG_ARM64_SP];
+
+	map = map_groups__find(thread->mg, MAP__VARIABLE, (u64) sp);
+	if (!map) {
+		pr_debug("failed to get stack map\n");
+		free(buf);
+		return -1;
+	}
+
+	stack_size = map->end - sp;
+	stack_size = stack_size > STACK_SIZE ? STACK_SIZE : stack_size;
+
+	memcpy(buf, (void *) sp, stack_size);
+	stack->data = (char *) buf;
+	stack->size = stack_size;
+	return 0;
+}
+
+int test__arch_unwind_sample(struct perf_sample *sample,
+		struct thread *thread)
+{
+	struct regs_dump *regs = &sample->user_regs;
+	u64 *buf;
+
+	buf = calloc(1, sizeof(u64) * PERF_REGS_MAX);
+	if (!buf) {
+		pr_debug("failed to allocate sample uregs data\n");
+		return -1;
+	}
+
+	perf_regs_load(buf);
+	regs->abi  = PERF_SAMPLE_REGS_ABI;
+	regs->regs = buf;
+	regs->mask = PERF_REGS_MASK;
+
+	return sample_ustack(sample, thread, buf);
+}
diff --git a/tools/perf/arch/arm64/tests/regs_load.S b/tools/perf/arch/arm64/tests/regs_load.S
new file mode 100644
index 000000000000..025b46e579a6
--- /dev/null
+++ b/tools/perf/arch/arm64/tests/regs_load.S
@@ -0,0 +1,46 @@
+#include <linux/linkage.h>
+
+.text
+.type perf_regs_load,%function
+#define STR_REG(r)	str x##r, [x0, 8 * r]
+#define LDR_REG(r)	ldr x##r, [x0, 8 * r]
+#define SP	(8 * 31)
+#define PC	(8 * 32)
+ENTRY(perf_regs_load)
+	STR_REG(0)
+	STR_REG(1)
+	STR_REG(2)
+	STR_REG(3)
+	STR_REG(4)
+	STR_REG(5)
+	STR_REG(6)
+	STR_REG(7)
+	STR_REG(8)
+	STR_REG(9)
+	STR_REG(10)
+	STR_REG(11)
+	STR_REG(12)
+	STR_REG(13)
+	STR_REG(14)
+	STR_REG(15)
+	STR_REG(16)
+	STR_REG(17)
+	STR_REG(18)
+	STR_REG(19)
+	STR_REG(20)
+	STR_REG(21)
+	STR_REG(22)
+	STR_REG(23)
+	STR_REG(24)
+	STR_REG(25)
+	STR_REG(26)
+	STR_REG(27)
+	STR_REG(28)
+	STR_REG(29)
+	STR_REG(30)
+	mov x1, sp
+	str x1, [x0, #SP]
+	str x30, [x0, #PC]
+	LDR_REG(1)
+	ret
+ENDPROC(perf_regs_load)
diff --git a/tools/perf/arch/common.c b/tools/perf/arch/common.c
index 49776f190abf..b7bb42c44694 100644
--- a/tools/perf/arch/common.c
+++ b/tools/perf/arch/common.c
@@ -61,7 +61,7 @@ const char *const mips_triplets[] = {
 static bool lookup_path(char *name)
 {
 	bool found = false;
-	char *path, *tmp;
+	char *path, *tmp = NULL;
 	char buf[PATH_MAX];
 	char *env = getenv("PATH");
 
diff --git a/tools/perf/arch/powerpc/util/Build b/tools/perf/arch/powerpc/util/Build
index 0af6e9b3f728..7b8b0d1a1b62 100644
--- a/tools/perf/arch/powerpc/util/Build
+++ b/tools/perf/arch/powerpc/util/Build
@@ -1,4 +1,5 @@
 libperf-y += header.o
+libperf-y += sym-handling.o
 
 libperf-$(CONFIG_DWARF) += dwarf-regs.o
 libperf-$(CONFIG_DWARF) += skip-callchain-idx.o
diff --git a/tools/perf/arch/powerpc/util/sym-handling.c b/tools/perf/arch/powerpc/util/sym-handling.c
new file mode 100644
index 000000000000..bbc1a50768dd
--- /dev/null
+++ b/tools/perf/arch/powerpc/util/sym-handling.c
@@ -0,0 +1,82 @@
+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, version 2, as
+ * published by the Free Software Foundation.
+ *
+ * Copyright (C) 2015 Naveen N. Rao, IBM Corporation
+ */
+
+#include "debug.h"
+#include "symbol.h"
+#include "map.h"
+#include "probe-event.h"
+
+#ifdef HAVE_LIBELF_SUPPORT
+bool elf__needs_adjust_symbols(GElf_Ehdr ehdr)
+{
+	return ehdr.e_type == ET_EXEC ||
+	       ehdr.e_type == ET_REL ||
+	       ehdr.e_type == ET_DYN;
+}
+
+#if defined(_CALL_ELF) && _CALL_ELF == 2
+void arch__elf_sym_adjust(GElf_Sym *sym)
+{
+	sym->st_value += PPC64_LOCAL_ENTRY_OFFSET(sym->st_other);
+}
+#endif
+#endif
+
+#if !defined(_CALL_ELF) || _CALL_ELF != 2
+int arch__choose_best_symbol(struct symbol *syma,
+			     struct symbol *symb __maybe_unused)
+{
+	char *sym = syma->name;
+
+	/* Skip over any initial dot */
+	if (*sym == '.')
+		sym++;
+
+	/* Avoid "SyS" kernel syscall aliases */
+	if (strlen(sym) >= 3 && !strncmp(sym, "SyS", 3))
+		return SYMBOL_B;
+	if (strlen(sym) >= 10 && !strncmp(sym, "compat_SyS", 10))
+		return SYMBOL_B;
+
+	return SYMBOL_A;
+}
+
+/* Allow matching against dot variants */
+int arch__compare_symbol_names(const char *namea, const char *nameb)
+{
+	/* Skip over initial dot */
+	if (*namea == '.')
+		namea++;
+	if (*nameb == '.')
+		nameb++;
+
+	return strcmp(namea, nameb);
+}
+#endif
+
+#if defined(_CALL_ELF) && _CALL_ELF == 2
+bool arch__prefers_symtab(void)
+{
+	return true;
+}
+
+#define PPC64LE_LEP_OFFSET	8
+
+void arch__fix_tev_from_maps(struct perf_probe_event *pev,
+			     struct probe_trace_event *tev, struct map *map)
+{
+	/*
+	 * ppc64 ABIv2 local entry point is currently always 2 instructions
+	 * (8 bytes) after the global entry point.
+	 */
+	if (!pev->uprobes && map->dso->symtab_type == DSO_BINARY_TYPE__KALLSYMS) {
+		tev->point.address += PPC64LE_LEP_OFFSET;
+		tev->point.offset += PPC64LE_LEP_OFFSET;
+	}
+}
+#endif
diff --git a/tools/perf/bench/Build b/tools/perf/bench/Build
index 5ce98023d518..c3ab760e06b4 100644
--- a/tools/perf/bench/Build
+++ b/tools/perf/bench/Build
@@ -3,6 +3,7 @@ perf-y += sched-pipe.o
 perf-y += mem-memcpy.o
 perf-y += futex-hash.o
 perf-y += futex-wake.o
+perf-y += futex-wake-parallel.o
 perf-y += futex-requeue.o
 
 perf-$(CONFIG_X86_64) += mem-memcpy-x86-64-asm.o
diff --git a/tools/perf/bench/bench.h b/tools/perf/bench/bench.h
index 3c4dd44d45cb..70b2f718cc21 100644
--- a/tools/perf/bench/bench.h
+++ b/tools/perf/bench/bench.h
@@ -33,6 +33,8 @@ extern int bench_mem_memcpy(int argc, const char **argv,
 extern int bench_mem_memset(int argc, const char **argv, const char *prefix);
 extern int bench_futex_hash(int argc, const char **argv, const char *prefix);
 extern int bench_futex_wake(int argc, const char **argv, const char *prefix);
+extern int bench_futex_wake_parallel(int argc, const char **argv,
+				     const char *prefix);
 extern int bench_futex_requeue(int argc, const char **argv, const char *prefix);
 
 #define BENCH_FORMAT_DEFAULT_STR	"default"
diff --git a/tools/perf/bench/futex-wake-parallel.c b/tools/perf/bench/futex-wake-parallel.c
new file mode 100644
index 000000000000..6d8c9fa2a16c
--- /dev/null
+++ b/tools/perf/bench/futex-wake-parallel.c
@@ -0,0 +1,294 @@
+/*
+ * Copyright (C) 2015 Davidlohr Bueso.
+ *
+ * Block a bunch of threads and let parallel waker threads wakeup an
+ * equal amount of them. The program output reflects the avg latency
+ * for each individual thread to service its share of work. Ultimately
+ * it can be used to measure futex_wake() changes.
+ */
+
+#include "../perf.h"
+#include "../util/util.h"
+#include "../util/stat.h"
+#include "../util/parse-options.h"
+#include "../util/header.h"
+#include "bench.h"
+#include "futex.h"
+
+#include <err.h>
+#include <stdlib.h>
+#include <sys/time.h>
+#include <pthread.h>
+
+struct thread_data {
+	pthread_t worker;
+	unsigned int nwoken;
+	struct timeval runtime;
+};
+
+static unsigned int nwakes = 1;
+
+/* all threads will block on the same futex -- hash bucket chaos ;) */
+static u_int32_t futex = 0;
+
+static pthread_t *blocked_worker;
+static bool done = false, silent = false, fshared = false;
+static unsigned int nblocked_threads = 0, nwaking_threads = 0;
+static pthread_mutex_t thread_lock;
+static pthread_cond_t thread_parent, thread_worker;
+static struct stats waketime_stats, wakeup_stats;
+static unsigned int ncpus, threads_starting;
+static int futex_flag = 0;
+
+static const struct option options[] = {
+	OPT_UINTEGER('t', "threads", &nblocked_threads, "Specify amount of threads"),
+	OPT_UINTEGER('w', "nwakers", &nwaking_threads, "Specify amount of waking threads"),
+	OPT_BOOLEAN( 's', "silent",  &silent,   "Silent mode: do not display data/details"),
+	OPT_BOOLEAN( 'S', "shared",  &fshared,  "Use shared futexes instead of private ones"),
+	OPT_END()
+};
+
+static const char * const bench_futex_wake_parallel_usage[] = {
+	"perf bench futex wake-parallel <options>",
+	NULL
+};
+
+static void *waking_workerfn(void *arg)
+{
+	struct thread_data *waker = (struct thread_data *) arg;
+	struct timeval start, end;
+
+	gettimeofday(&start, NULL);
+
+	waker->nwoken = futex_wake(&futex, nwakes, futex_flag);
+	if (waker->nwoken != nwakes)
+		warnx("couldn't wakeup all tasks (%d/%d)",
+		      waker->nwoken, nwakes);
+
+	gettimeofday(&end, NULL);
+	timersub(&end, &start, &waker->runtime);
+
+	pthread_exit(NULL);
+	return NULL;
+}
+
+static void wakeup_threads(struct thread_data *td, pthread_attr_t thread_attr)
+{
+	unsigned int i;
+
+	pthread_attr_setdetachstate(&thread_attr, PTHREAD_CREATE_JOINABLE);
+
+	/* create and block all threads */
+	for (i = 0; i < nwaking_threads; i++) {
+		/*
+		 * Thread creation order will impact per-thread latency
+		 * as it will affect the order to acquire the hb spinlock.
+		 * For now let the scheduler decide.
+		 */
+		if (pthread_create(&td[i].worker, &thread_attr,
+				   waking_workerfn, (void *)&td[i]))
+			err(EXIT_FAILURE, "pthread_create");
+	}
+
+	for (i = 0; i < nwaking_threads; i++)
+		if (pthread_join(td[i].worker, NULL))
+			err(EXIT_FAILURE, "pthread_join");
+}
+
+static void *blocked_workerfn(void *arg __maybe_unused)
+{
+	pthread_mutex_lock(&thread_lock);
+	threads_starting--;
+	if (!threads_starting)
+		pthread_cond_signal(&thread_parent);
+	pthread_cond_wait(&thread_worker, &thread_lock);
+	pthread_mutex_unlock(&thread_lock);
+
+	while (1) { /* handle spurious wakeups */
+		if (futex_wait(&futex, 0, NULL, futex_flag) != EINTR)
+			break;
+	}
+
+	pthread_exit(NULL);
+	return NULL;
+}
+
+static void block_threads(pthread_t *w, pthread_attr_t thread_attr)
+{
+	cpu_set_t cpu;
+	unsigned int i;
+
+	threads_starting = nblocked_threads;
+
+	/* create and block all threads */
+	for (i = 0; i < nblocked_threads; i++) {
+		CPU_ZERO(&cpu);
+		CPU_SET(i % ncpus, &cpu);
+
+		if (pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpu))
+			err(EXIT_FAILURE, "pthread_attr_setaffinity_np");
+
+		if (pthread_create(&w[i], &thread_attr, blocked_workerfn, NULL))
+			err(EXIT_FAILURE, "pthread_create");
+	}
+}
+
+static void print_run(struct thread_data *waking_worker, unsigned int run_num)
+{
+	unsigned int i, wakeup_avg;
+	double waketime_avg, waketime_stddev;
+	struct stats __waketime_stats, __wakeup_stats;
+
+	init_stats(&__wakeup_stats);
+	init_stats(&__waketime_stats);
+
+	for (i = 0; i < nwaking_threads; i++) {
+		update_stats(&__waketime_stats, waking_worker[i].runtime.tv_usec);
+		update_stats(&__wakeup_stats, waking_worker[i].nwoken);
+	}
+
+	waketime_avg = avg_stats(&__waketime_stats);
+	waketime_stddev = stddev_stats(&__waketime_stats);
+	wakeup_avg = avg_stats(&__wakeup_stats);
+
+	printf("[Run %d]: Avg per-thread latency (waking %d/%d threads) "
+	       "in %.4f ms (+-%.2f%%)\n", run_num + 1, wakeup_avg,
+	       nblocked_threads, waketime_avg/1e3,
+	       rel_stddev_stats(waketime_stddev, waketime_avg));
+}
+
+static void print_summary(void)
+{
+	unsigned int wakeup_avg;
+	double waketime_avg, waketime_stddev;
+
+	waketime_avg = avg_stats(&waketime_stats);
+	waketime_stddev = stddev_stats(&waketime_stats);
+	wakeup_avg = avg_stats(&wakeup_stats);
+
+	printf("Avg per-thread latency (waking %d/%d threads) in %.4f ms (+-%.2f%%)\n",
+	       wakeup_avg,
+	       nblocked_threads,
+	       waketime_avg/1e3,
+	       rel_stddev_stats(waketime_stddev, waketime_avg));
+}
+
+
+static void do_run_stats(struct thread_data *waking_worker)
+{
+	unsigned int i;
+
+	for (i = 0; i < nwaking_threads; i++) {
+		update_stats(&waketime_stats, waking_worker[i].runtime.tv_usec);
+		update_stats(&wakeup_stats, waking_worker[i].nwoken);
+	}
+
+}
+
+static void toggle_done(int sig __maybe_unused,
+			siginfo_t *info __maybe_unused,
+			void *uc __maybe_unused)
+{
+	done = true;
+}
+
+int bench_futex_wake_parallel(int argc, const char **argv,
+			      const char *prefix __maybe_unused)
+{
+	int ret = 0;
+	unsigned int i, j;
+	struct sigaction act;
+	pthread_attr_t thread_attr;
+	struct thread_data *waking_worker;
+
+	argc = parse_options(argc, argv, options,
+			     bench_futex_wake_parallel_usage, 0);
+	if (argc) {
+		usage_with_options(bench_futex_wake_parallel_usage, options);
+		exit(EXIT_FAILURE);
+	}
+
+	sigfillset(&act.sa_mask);
+	act.sa_sigaction = toggle_done;
+	sigaction(SIGINT, &act, NULL);
+
+	ncpus = sysconf(_SC_NPROCESSORS_ONLN);
+	if (!nblocked_threads)
+		nblocked_threads = ncpus;
+
+	/* some sanity checks */
+	if (nwaking_threads > nblocked_threads || !nwaking_threads)
+		nwaking_threads = nblocked_threads;
+
+	if (nblocked_threads % nwaking_threads)
+		errx(EXIT_FAILURE, "Must be perfectly divisible");
+	/*
+	 * Each thread will wakeup nwakes tasks in
+	 * a single futex_wait call.
+	 */
+	nwakes = nblocked_threads/nwaking_threads;
+
+	blocked_worker = calloc(nblocked_threads, sizeof(*blocked_worker));
+	if (!blocked_worker)
+		err(EXIT_FAILURE, "calloc");
+
+	if (!fshared)
+		futex_flag = FUTEX_PRIVATE_FLAG;
+
+	printf("Run summary [PID %d]: blocking on %d threads (at [%s] "
+	       "futex %p), %d threads waking up %d at a time.\n\n",
+	       getpid(), nblocked_threads, fshared ? "shared":"private",
+	       &futex, nwaking_threads, nwakes);
+
+	init_stats(&wakeup_stats);
+	init_stats(&waketime_stats);
+
+	pthread_attr_init(&thread_attr);
+	pthread_mutex_init(&thread_lock, NULL);
+	pthread_cond_init(&thread_parent, NULL);
+	pthread_cond_init(&thread_worker, NULL);
+
+	for (j = 0; j < bench_repeat && !done; j++) {
+		waking_worker = calloc(nwaking_threads, sizeof(*waking_worker));
+		if (!waking_worker)
+			err(EXIT_FAILURE, "calloc");
+
+		/* create, launch & block all threads */
+		block_threads(blocked_worker, thread_attr);
+
+		/* make sure all threads are already blocked */
+		pthread_mutex_lock(&thread_lock);
+		while (threads_starting)
+			pthread_cond_wait(&thread_parent, &thread_lock);
+		pthread_cond_broadcast(&thread_worker);
+		pthread_mutex_unlock(&thread_lock);
+
+		usleep(100000);
+
+		/* Ok, all threads are patiently blocked, start waking folks up */
+		wakeup_threads(waking_worker, thread_attr);
+
+		for (i = 0; i < nblocked_threads; i++) {
+			ret = pthread_join(blocked_worker[i], NULL);
+			if (ret)
+				err(EXIT_FAILURE, "pthread_join");
+		}
+
+		do_run_stats(waking_worker);
+		if (!silent)
+			print_run(waking_worker, j);
+
+		free(waking_worker);
+	}
+
+	/* cleanup & report results */
+	pthread_cond_destroy(&thread_parent);
+	pthread_cond_destroy(&thread_worker);
+	pthread_mutex_destroy(&thread_lock);
+	pthread_attr_destroy(&thread_attr);
+
+	print_summary();
+
+	free(blocked_worker);
+	return ret;
+}
diff --git a/tools/perf/bench/futex-wake.c b/tools/perf/bench/futex-wake.c
index 929f762be47e..e5e41d3bdce7 100644
--- a/tools/perf/bench/futex-wake.c
+++ b/tools/perf/bench/futex-wake.c
@@ -60,7 +60,12 @@ static void *workerfn(void *arg __maybe_unused)
 	pthread_cond_wait(&thread_worker, &thread_lock);
 	pthread_mutex_unlock(&thread_lock);
 
-	futex_wait(&futex1, 0, NULL, futex_flag);
+	while (1) {
+		if (futex_wait(&futex1, 0, NULL, futex_flag) != EINTR)
+			break;
+	}
+
+	pthread_exit(NULL);
 	return NULL;
 }
 
diff --git a/tools/perf/bench/numa.c b/tools/perf/bench/numa.c
index ba5efa4710b5..870b7e665a20 100644
--- a/tools/perf/bench/numa.c
+++ b/tools/perf/bench/numa.c
@@ -8,6 +8,7 @@
 #include "../builtin.h"
 #include "../util/util.h"
 #include "../util/parse-options.h"
+#include "../util/cloexec.h"
 
 #include "bench.h"
 
@@ -23,6 +24,7 @@
 #include <pthread.h>
 #include <sys/mman.h>
 #include <sys/time.h>
+#include <sys/resource.h>
 #include <sys/wait.h>
 #include <sys/prctl.h>
 #include <sys/types.h>
@@ -51,6 +53,9 @@ struct thread_data {
 	unsigned int		loops_done;
 	u64			val;
 	u64			runtime_ns;
+	u64			system_time_ns;
+	u64			user_time_ns;
+	double			speed_gbs;
 	pthread_mutex_t		*process_lock;
 };
 
@@ -1042,6 +1047,7 @@ static void *worker_thread(void *__tdata)
 	u64 bytes_done;
 	long work_done;
 	u32 l;
+	struct rusage rusage;
 
 	bind_to_cpumask(td->bind_cpumask);
 	bind_to_memnode(td->bind_node);
@@ -1194,6 +1200,13 @@ static void *worker_thread(void *__tdata)
 	timersub(&stop, &start0, &diff);
 	td->runtime_ns = diff.tv_sec * 1000000000ULL;
 	td->runtime_ns += diff.tv_usec * 1000ULL;
+	td->speed_gbs = bytes_done / (td->runtime_ns / 1e9) / 1e9;
+
+	getrusage(RUSAGE_THREAD, &rusage);
+	td->system_time_ns = rusage.ru_stime.tv_sec * 1000000000ULL;
+	td->system_time_ns += rusage.ru_stime.tv_usec * 1000ULL;
+	td->user_time_ns = rusage.ru_utime.tv_sec * 1000000000ULL;
+	td->user_time_ns += rusage.ru_utime.tv_usec * 1000ULL;
 
 	free_data(thread_data, g->p.bytes_thread);
 
@@ -1420,7 +1433,7 @@ static int __bench_numa(const char *name)
 	double runtime_sec_min;
 	int wait_stat;
 	double bytes;
-	int i, t;
+	int i, t, p;
 
 	if (init())
 		return -1;
@@ -1556,6 +1569,24 @@ static int __bench_numa(const char *name)
 	print_res(name, bytes / runtime_sec_max / 1e9,
 		"GB/sec,", "total-speed",	"GB/sec total speed");
 
+	if (g->p.show_details >= 2) {
+		char tname[32];
+		struct thread_data *td;
+		for (p = 0; p < g->p.nr_proc; p++) {
+			for (t = 0; t < g->p.nr_threads; t++) {
+				memset(tname, 0, 32);
+				td = g->threads + p*g->p.nr_threads + t;
+				snprintf(tname, 32, "process%d:thread%d", p, t);
+				print_res(tname, td->speed_gbs,
+					"GB/sec",	"thread-speed", "GB/sec/thread speed");
+				print_res(tname, td->system_time_ns / 1e9,
+					"secs",	"thread-system-time", "system CPU time/thread");
+				print_res(tname, td->user_time_ns / 1e9,
+					"secs",	"thread-user-time", "user CPU time/thread");
+			}
+		}
+	}
+
 	free(pids);
 
 	deinit();
diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c
index 71bf7451c0ca..2c1bec39c30e 100644
--- a/tools/perf/builtin-annotate.c
+++ b/tools/perf/builtin-annotate.c
@@ -59,6 +59,10 @@ static int perf_evsel__add_sample(struct perf_evsel *evsel,
 	    (al->sym == NULL ||
 	     strcmp(ann->sym_hist_filter, al->sym->name) != 0)) {
 		/* We're only interested in a symbol named sym_hist_filter */
+		/*
+		 * FIXME: why isn't this done in the symbol_filter when loading
+		 * the DSO?
+		 */
 		if (al->sym != NULL) {
 			rb_erase(&al->sym->rb_node,
 				 &al->map->dso->symbols[al->map->type]);
@@ -84,6 +88,7 @@ static int process_sample_event(struct perf_tool *tool,
 {
 	struct perf_annotate *ann = container_of(tool, struct perf_annotate, tool);
 	struct addr_location al;
+	int ret = 0;
 
 	if (perf_event__preprocess_sample(event, machine, &al, sample) < 0) {
 		pr_warning("problem processing %d event, skipping it.\n",
@@ -92,15 +97,16 @@ static int process_sample_event(struct perf_tool *tool,
 	}
 
 	if (ann->cpu_list && !test_bit(sample->cpu, ann->cpu_bitmap))
-		return 0;
+		goto out_put;
 
 	if (!al.filtered && perf_evsel__add_sample(evsel, sample, &al, ann)) {
 		pr_warning("problem incrementing symbol count, "
 			   "skipping event\n");
-		return -1;
+		ret = -1;
 	}
-
-	return 0;
+out_put:
+	addr_location__put(&al);
+	return ret;
 }
 
 static int hist_entry__tty_annotate(struct hist_entry *he,
@@ -283,7 +289,6 @@ int cmd_annotate(int argc, const char **argv, const char *prefix __maybe_unused)
 		},
 	};
 	struct perf_data_file file = {
-		.path  = input_name,
 		.mode  = PERF_DATA_MODE_READ,
 	};
 	const struct option options[] = {
@@ -324,6 +329,8 @@ int cmd_annotate(int argc, const char **argv, const char *prefix __maybe_unused)
 		   "objdump binary to use for disassembly and annotations"),
 	OPT_BOOLEAN(0, "group", &symbol_conf.event_group,
 		    "Show event group information together"),
+	OPT_BOOLEAN(0, "show-total-period", &symbol_conf.show_total_period,
+		    "Show a column with the sum of periods"),
 	OPT_END()
 	};
 	int ret = hists__init();
@@ -340,6 +347,8 @@ int cmd_annotate(int argc, const char **argv, const char *prefix __maybe_unused)
 	else if (annotate.use_gtk)
 		use_browser = 2;
 
+	file.path  = input_name;
+
 	setup_browser(true);
 
 	annotate.session = perf_session__new(&file, false, &annotate.tool);
diff --git a/tools/perf/builtin-bench.c b/tools/perf/builtin-bench.c
index b9a56fa83330..b5314e452ec7 100644
--- a/tools/perf/builtin-bench.c
+++ b/tools/perf/builtin-bench.c
@@ -58,6 +58,7 @@ static struct bench mem_benchmarks[] = {
 static struct bench futex_benchmarks[] = {
 	{ "hash",	"Benchmark for futex hash table",               bench_futex_hash	},
 	{ "wake",	"Benchmark for futex wake calls",               bench_futex_wake	},
+	{ "wake-parallel", "Benchmark for parallel futex wake calls",   bench_futex_wake_parallel },
 	{ "requeue",	"Benchmark for futex requeue calls",            bench_futex_requeue	},
 	{ "all",	"Test all futex benchmarks",			NULL			},
 	{ NULL,		NULL,						NULL			}
diff --git a/tools/perf/builtin-buildid-list.c b/tools/perf/builtin-buildid-list.c
index feb420f74c2d..9fe93c8d4fcf 100644
--- a/tools/perf/builtin-buildid-list.c
+++ b/tools/perf/builtin-buildid-list.c
@@ -69,6 +69,15 @@ static int perf_session__list_build_ids(bool force, bool with_hits)
 	session = perf_session__new(&file, false, &build_id__mark_dso_hit_ops);
 	if (session == NULL)
 		return -1;
+
+	/*
+	 * We take all buildids when the file contains AUX area tracing data
+	 * because we do not decode the trace because it would take too long.
+	 */
+	if (!perf_data_file__is_pipe(&file) &&
+	    perf_header__has_feat(&session->header, HEADER_AUXTRACE))
+		with_hits = false;
+
 	/*
 	 * in pipe-mode, the only way to get the buildids is to parse
 	 * the record stream. Buildids are stored as RECORD_HEADER_BUILD_ID
diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c
index df6307b4050a..daaa7dca9c3b 100644
--- a/tools/perf/builtin-diff.c
+++ b/tools/perf/builtin-diff.c
@@ -328,6 +328,7 @@ static int diff__process_sample_event(struct perf_tool *tool __maybe_unused,
 {
 	struct addr_location al;
 	struct hists *hists = evsel__hists(evsel);
+	int ret = -1;
 
 	if (perf_event__preprocess_sample(event, machine, &al, sample) < 0) {
 		pr_warning("problem processing %d event, skipping it.\n",
@@ -338,7 +339,7 @@ static int diff__process_sample_event(struct perf_tool *tool __maybe_unused,
 	if (hists__add_entry(hists, &al, sample->period,
 			     sample->weight, sample->transaction)) {
 		pr_warning("problem incrementing symbol period, skipping event\n");
-		return -1;
+		goto out_put;
 	}
 
 	/*
@@ -350,8 +351,10 @@ static int diff__process_sample_event(struct perf_tool *tool __maybe_unused,
 	hists->stats.total_period += sample->period;
 	if (!al.filtered)
 		hists->stats.total_non_filtered_period += sample->period;
-
-	return 0;
+	ret = 0;
+out_put:
+	addr_location__put(&al);
+	return ret;
 }
 
 static struct perf_tool tool = {
diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c
index 40a33d7334cc..52ec66b23607 100644
--- a/tools/perf/builtin-inject.c
+++ b/tools/perf/builtin-inject.c
@@ -16,6 +16,7 @@
 #include "util/debug.h"
 #include "util/build-id.h"
 #include "util/data.h"
+#include "util/auxtrace.h"
 
 #include "util/parse-options.h"
 
@@ -26,10 +27,12 @@ struct perf_inject {
 	struct perf_session	*session;
 	bool			build_ids;
 	bool			sched_stat;
+	bool			have_auxtrace;
 	const char		*input_name;
 	struct perf_data_file	output;
 	u64			bytes_written;
 	struct list_head	samples;
+	struct itrace_synth_opts itrace_synth_opts;
 };
 
 struct event_entry {
@@ -38,14 +41,11 @@ struct event_entry {
 	union perf_event event[0];
 };
 
-static int perf_event__repipe_synth(struct perf_tool *tool,
-				    union perf_event *event)
+static int output_bytes(struct perf_inject *inject, void *buf, size_t sz)
 {
-	struct perf_inject *inject = container_of(tool, struct perf_inject, tool);
 	ssize_t size;
 
-	size = perf_data_file__write(&inject->output, event,
-				     event->header.size);
+	size = perf_data_file__write(&inject->output, buf, sz);
 	if (size < 0)
 		return -errno;
 
@@ -53,6 +53,15 @@ static int perf_event__repipe_synth(struct perf_tool *tool,
 	return 0;
 }
 
+static int perf_event__repipe_synth(struct perf_tool *tool,
+				    union perf_event *event)
+{
+	struct perf_inject *inject = container_of(tool, struct perf_inject,
+						  tool);
+
+	return output_bytes(inject, event, event->header.size);
+}
+
 static int perf_event__repipe_oe_synth(struct perf_tool *tool,
 				       union perf_event *event,
 				       struct ordered_events *oe __maybe_unused)
@@ -86,6 +95,79 @@ static int perf_event__repipe_attr(struct perf_tool *tool,
 	return perf_event__repipe_synth(tool, event);
 }
 
+#ifdef HAVE_AUXTRACE_SUPPORT
+
+static int copy_bytes(struct perf_inject *inject, int fd, off_t size)
+{
+	char buf[4096];
+	ssize_t ssz;
+	int ret;
+
+	while (size > 0) {
+		ssz = read(fd, buf, min(size, (off_t)sizeof(buf)));
+		if (ssz < 0)
+			return -errno;
+		ret = output_bytes(inject, buf, ssz);
+		if (ret)
+			return ret;
+		size -= ssz;
+	}
+
+	return 0;
+}
+
+static s64 perf_event__repipe_auxtrace(struct perf_tool *tool,
+				       union perf_event *event,
+				       struct perf_session *session
+				       __maybe_unused)
+{
+	struct perf_inject *inject = container_of(tool, struct perf_inject,
+						  tool);
+	int ret;
+
+	inject->have_auxtrace = true;
+
+	if (!inject->output.is_pipe) {
+		off_t offset;
+
+		offset = lseek(inject->output.fd, 0, SEEK_CUR);
+		if (offset == -1)
+			return -errno;
+		ret = auxtrace_index__auxtrace_event(&session->auxtrace_index,
+						     event, offset);
+		if (ret < 0)
+			return ret;
+	}
+
+	if (perf_data_file__is_pipe(session->file) || !session->one_mmap) {
+		ret = output_bytes(inject, event, event->header.size);
+		if (ret < 0)
+			return ret;
+		ret = copy_bytes(inject, perf_data_file__fd(session->file),
+				 event->auxtrace.size);
+	} else {
+		ret = output_bytes(inject, event,
+				   event->header.size + event->auxtrace.size);
+	}
+	if (ret < 0)
+		return ret;
+
+	return event->auxtrace.size;
+}
+
+#else
+
+static s64
+perf_event__repipe_auxtrace(struct perf_tool *tool __maybe_unused,
+			    union perf_event *event __maybe_unused,
+			    struct perf_session *session __maybe_unused)
+{
+	pr_err("AUX area tracing not supported\n");
+	return -EINVAL;
+}
+
+#endif
+
 static int perf_event__repipe(struct perf_tool *tool,
 			      union perf_event *event,
 			      struct perf_sample *sample __maybe_unused,
@@ -155,6 +237,32 @@ static int perf_event__repipe_fork(struct perf_tool *tool,
 	return err;
 }
 
+static int perf_event__repipe_comm(struct perf_tool *tool,
+				   union perf_event *event,
+				   struct perf_sample *sample,
+				   struct machine *machine)
+{
+	int err;
+
+	err = perf_event__process_comm(tool, event, sample, machine);
+	perf_event__repipe(tool, event, sample, machine);
+
+	return err;
+}
+
+static int perf_event__repipe_exit(struct perf_tool *tool,
+				   union perf_event *event,
+				   struct perf_sample *sample,
+				   struct machine *machine)
+{
+	int err;
+
+	err = perf_event__process_exit(tool, event, sample, machine);
+	perf_event__repipe(tool, event, sample, machine);
+
+	return err;
+}
+
 static int perf_event__repipe_tracing_data(struct perf_tool *tool,
 					   union perf_event *event,
 					   struct perf_session *session)
@@ -167,6 +275,18 @@ static int perf_event__repipe_tracing_data(struct perf_tool *tool,
 	return err;
 }
 
+static int perf_event__repipe_id_index(struct perf_tool *tool,
+				       union perf_event *event,
+				       struct perf_session *session)
+{
+	int err;
+
+	perf_event__repipe_synth(tool, event);
+	err = perf_event__process_id_index(tool, event, session);
+
+	return err;
+}
+
 static int dso__read_build_id(struct dso *dso)
 {
 	if (dso->has_build_id)
@@ -245,6 +365,7 @@ static int perf_event__inject_buildid(struct perf_tool *tool,
 		}
 	}
 
+	thread__put(thread);
 repipe:
 	perf_event__repipe(tool, event, sample, machine);
 	return 0;
@@ -351,16 +472,20 @@ static int __cmd_inject(struct perf_inject *inject)
 	struct perf_session *session = inject->session;
 	struct perf_data_file *file_out = &inject->output;
 	int fd = perf_data_file__fd(file_out);
+	u64 output_data_offset;
 
 	signal(SIGINT, sig_handler);
 
-	if (inject->build_ids || inject->sched_stat) {
+	if (inject->build_ids || inject->sched_stat ||
+	    inject->itrace_synth_opts.set) {
 		inject->tool.mmap	  = perf_event__repipe_mmap;
 		inject->tool.mmap2	  = perf_event__repipe_mmap2;
 		inject->tool.fork	  = perf_event__repipe_fork;
 		inject->tool.tracing_data = perf_event__repipe_tracing_data;
 	}
 
+	output_data_offset = session->header.data_offset;
+
 	if (inject->build_ids) {
 		inject->tool.sample = perf_event__inject_buildid;
 	} else if (inject->sched_stat) {
@@ -379,17 +504,43 @@ static int __cmd_inject(struct perf_inject *inject)
 			else if (!strncmp(name, "sched:sched_stat_", 17))
 				evsel->handler = perf_inject__sched_stat;
 		}
+	} else if (inject->itrace_synth_opts.set) {
+		session->itrace_synth_opts = &inject->itrace_synth_opts;
+		inject->itrace_synth_opts.inject = true;
+		inject->tool.comm	    = perf_event__repipe_comm;
+		inject->tool.exit	    = perf_event__repipe_exit;
+		inject->tool.id_index	    = perf_event__repipe_id_index;
+		inject->tool.auxtrace_info  = perf_event__process_auxtrace_info;
+		inject->tool.auxtrace	    = perf_event__process_auxtrace;
+		inject->tool.ordered_events = true;
+		inject->tool.ordering_requires_timestamps = true;
+		/* Allow space in the header for new attributes */
+		output_data_offset = 4096;
 	}
 
+	if (!inject->itrace_synth_opts.set)
+		auxtrace_index__free(&session->auxtrace_index);
+
 	if (!file_out->is_pipe)
-		lseek(fd, session->header.data_offset, SEEK_SET);
+		lseek(fd, output_data_offset, SEEK_SET);
 
 	ret = perf_session__process_events(session);
 
 	if (!file_out->is_pipe) {
-		if (inject->build_ids)
+		if (inject->build_ids) {
 			perf_header__set_feat(&session->header,
 					      HEADER_BUILD_ID);
+			if (inject->have_auxtrace)
+				dsos__hit_all(session);
+		}
+		/*
+		 * The AUX areas have been removed and replaced with
+		 * synthesized hardware events, so clear the feature flag.
+		 */
+		if (inject->itrace_synth_opts.set)
+			perf_header__clear_feat(&session->header,
+						HEADER_AUXTRACE);
+		session->header.data_offset = output_data_offset;
 		session->header.data_size = inject->bytes_written;
 		perf_session__write_header(session, session->evlist, fd, true);
 	}
@@ -408,11 +559,16 @@ int cmd_inject(int argc, const char **argv, const char *prefix __maybe_unused)
 			.fork		= perf_event__repipe,
 			.exit		= perf_event__repipe,
 			.lost		= perf_event__repipe,
+			.aux		= perf_event__repipe,
+			.itrace_start	= perf_event__repipe,
 			.read		= perf_event__repipe_sample,
 			.throttle	= perf_event__repipe,
 			.unthrottle	= perf_event__repipe,
 			.attr		= perf_event__repipe_attr,
 			.tracing_data	= perf_event__repipe_op2_synth,
+			.auxtrace_info	= perf_event__repipe_op2_synth,
+			.auxtrace	= perf_event__repipe_auxtrace,
+			.auxtrace_error	= perf_event__repipe_op2_synth,
 			.finished_round	= perf_event__repipe_oe_synth,
 			.build_id	= perf_event__repipe_op2_synth,
 			.id_index	= perf_event__repipe_op2_synth,
@@ -444,6 +600,9 @@ int cmd_inject(int argc, const char **argv, const char *prefix __maybe_unused)
 		OPT_STRING(0, "kallsyms", &symbol_conf.kallsyms_name, "file",
 			   "kallsyms pathname"),
 		OPT_BOOLEAN('f', "force", &file.force, "don't complain, do it"),
+		OPT_CALLBACK_OPTARG(0, "itrace", &inject.itrace_synth_opts,
+				    NULL, "opts", "Instruction Tracing options",
+				    itrace_parse_synth_opts),
 		OPT_END()
 	};
 	const char * const inject_usage[] = {
diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c
index 1634186d537c..950f296dfcf7 100644
--- a/tools/perf/builtin-kmem.c
+++ b/tools/perf/builtin-kmem.c
@@ -10,6 +10,7 @@
 #include "util/header.h"
 #include "util/session.h"
 #include "util/tool.h"
+#include "util/callchain.h"
 
 #include "util/parse-options.h"
 #include "util/trace-event.h"
@@ -21,14 +22,19 @@
 #include <linux/rbtree.h>
 #include <linux/string.h>
 #include <locale.h>
+#include <regex.h>
 
 static int	kmem_slab;
 static int	kmem_page;
 
 static long	kmem_page_size;
+static enum {
+	KMEM_SLAB,
+	KMEM_PAGE,
+} kmem_default = KMEM_SLAB;  /* for backward compatibility */
 
 struct alloc_stat;
-typedef int (*sort_fn_t)(struct alloc_stat *, struct alloc_stat *);
+typedef int (*sort_fn_t)(void *, void *);
 
 static int			alloc_flag;
 static int			caller_flag;
@@ -179,8 +185,8 @@ static int perf_evsel__process_alloc_node_event(struct perf_evsel *evsel,
 	return ret;
 }
 
-static int ptr_cmp(struct alloc_stat *, struct alloc_stat *);
-static int callsite_cmp(struct alloc_stat *, struct alloc_stat *);
+static int ptr_cmp(void *, void *);
+static int slab_callsite_cmp(void *, void *);
 
 static struct alloc_stat *search_alloc_stat(unsigned long ptr,
 					    unsigned long call_site,
@@ -221,7 +227,8 @@ static int perf_evsel__process_free_event(struct perf_evsel *evsel,
 		s_alloc->pingpong++;
 
 		s_caller = search_alloc_stat(0, s_alloc->call_site,
-					     &root_caller_stat, callsite_cmp);
+					     &root_caller_stat,
+					     slab_callsite_cmp);
 		if (!s_caller)
 			return -1;
 		s_caller->pingpong++;
@@ -241,6 +248,8 @@ static unsigned long nr_page_fails;
 static unsigned long nr_page_nomatch;
 
 static bool use_pfn;
+static bool live_page;
+static struct perf_session *kmem_session;
 
 #define MAX_MIGRATE_TYPES  6
 #define MAX_PAGE_ORDER     11
@@ -250,6 +259,7 @@ static int order_stats[MAX_PAGE_ORDER][MAX_MIGRATE_TYPES];
 struct page_stat {
 	struct rb_node 	node;
 	u64 		page;
+	u64 		callsite;
 	int 		order;
 	unsigned 	gfp_flags;
 	unsigned 	migrate_type;
@@ -259,13 +269,158 @@ struct page_stat {
 	int 		nr_free;
 };
 
-static struct rb_root page_tree;
+static struct rb_root page_live_tree;
 static struct rb_root page_alloc_tree;
 static struct rb_root page_alloc_sorted;
+static struct rb_root page_caller_tree;
+static struct rb_root page_caller_sorted;
 
-static struct page_stat *search_page(unsigned long page, bool create)
+struct alloc_func {
+	u64 start;
+	u64 end;
+	char *name;
+};
+
+static int nr_alloc_funcs;
+static struct alloc_func *alloc_func_list;
+
+static int funcmp(const void *a, const void *b)
+{
+	const struct alloc_func *fa = a;
+	const struct alloc_func *fb = b;
+
+	if (fa->start > fb->start)
+		return 1;
+	else
+		return -1;
+}
+
+static int callcmp(const void *a, const void *b)
+{
+	const struct alloc_func *fa = a;
+	const struct alloc_func *fb = b;
+
+	if (fb->start <= fa->start && fa->end < fb->end)
+		return 0;
+
+	if (fa->start > fb->start)
+		return 1;
+	else
+		return -1;
+}
+
+static int build_alloc_func_list(void)
 {
-	struct rb_node **node = &page_tree.rb_node;
+	int ret;
+	struct map *kernel_map;
+	struct symbol *sym;
+	struct rb_node *node;
+	struct alloc_func *func;
+	struct machine *machine = &kmem_session->machines.host;
+	regex_t alloc_func_regex;
+	const char pattern[] = "^_?_?(alloc|get_free|get_zeroed)_pages?";
+
+	ret = regcomp(&alloc_func_regex, pattern, REG_EXTENDED);
+	if (ret) {
+		char err[BUFSIZ];
+
+		regerror(ret, &alloc_func_regex, err, sizeof(err));
+		pr_err("Invalid regex: %s\n%s", pattern, err);
+		return -EINVAL;
+	}
+
+	kernel_map = machine->vmlinux_maps[MAP__FUNCTION];
+	if (map__load(kernel_map, NULL) < 0) {
+		pr_err("cannot load kernel map\n");
+		return -ENOENT;
+	}
+
+	map__for_each_symbol(kernel_map, sym, node) {
+		if (regexec(&alloc_func_regex, sym->name, 0, NULL, 0))
+			continue;
+
+		func = realloc(alloc_func_list,
+			       (nr_alloc_funcs + 1) * sizeof(*func));
+		if (func == NULL)
+			return -ENOMEM;
+
+		pr_debug("alloc func: %s\n", sym->name);
+		func[nr_alloc_funcs].start = sym->start;
+		func[nr_alloc_funcs].end   = sym->end;
+		func[nr_alloc_funcs].name  = sym->name;
+
+		alloc_func_list = func;
+		nr_alloc_funcs++;
+	}
+
+	qsort(alloc_func_list, nr_alloc_funcs, sizeof(*func), funcmp);
+
+	regfree(&alloc_func_regex);
+	return 0;
+}
+
+/*
+ * Find first non-memory allocation function from callchain.
+ * The allocation functions are in the 'alloc_func_list'.
+ */
+static u64 find_callsite(struct perf_evsel *evsel, struct perf_sample *sample)
+{
+	struct addr_location al;
+	struct machine *machine = &kmem_session->machines.host;
+	struct callchain_cursor_node *node;
+
+	if (alloc_func_list == NULL) {
+		if (build_alloc_func_list() < 0)
+			goto out;
+	}
+
+	al.thread = machine__findnew_thread(machine, sample->pid, sample->tid);
+	sample__resolve_callchain(sample, NULL, evsel, &al, 16);
+
+	callchain_cursor_commit(&callchain_cursor);
+	while (true) {
+		struct alloc_func key, *caller;
+		u64 addr;
+
+		node = callchain_cursor_current(&callchain_cursor);
+		if (node == NULL)
+			break;
+
+		key.start = key.end = node->ip;
+		caller = bsearch(&key, alloc_func_list, nr_alloc_funcs,
+				 sizeof(key), callcmp);
+		if (!caller) {
+			/* found */
+			if (node->map)
+				addr = map__unmap_ip(node->map, node->ip);
+			else
+				addr = node->ip;
+
+			return addr;
+		} else
+			pr_debug3("skipping alloc function: %s\n", caller->name);
+
+		callchain_cursor_advance(&callchain_cursor);
+	}
+
+out:
+	pr_debug2("unknown callsite: %"PRIx64 "\n", sample->ip);
+	return sample->ip;
+}
+
+struct sort_dimension {
+	const char		name[20];
+	sort_fn_t		cmp;
+	struct list_head	list;
+};
+
+static LIST_HEAD(page_alloc_sort_input);
+static LIST_HEAD(page_caller_sort_input);
+
+static struct page_stat *
+__page_stat__findnew_page(struct page_stat *pstat, bool create)
+{
+	struct rb_node **node = &page_live_tree.rb_node;
 	struct rb_node *parent = NULL;
 	struct page_stat *data;
 
@@ -275,7 +430,7 @@ static struct page_stat *search_page(unsigned long page, bool create)
 		parent = *node;
 		data = rb_entry(*node, struct page_stat, node);
 
-		cmp = data->page - page;
+		cmp = data->page - pstat->page;
 		if (cmp < 0)
 			node = &parent->rb_left;
 		else if (cmp > 0)
@@ -289,49 +444,48 @@ static struct page_stat *search_page(unsigned long page, bool create)
 
 	data = zalloc(sizeof(*data));
 	if (data != NULL) {
-		data->page = page;
+		data->page = pstat->page;
+		data->order = pstat->order;
+		data->gfp_flags = pstat->gfp_flags;
+		data->migrate_type = pstat->migrate_type;
 
 		rb_link_node(&data->node, parent, node);
-		rb_insert_color(&data->node, &page_tree);
+		rb_insert_color(&data->node, &page_live_tree);
 	}
 
 	return data;
 }
 
-static int page_stat_cmp(struct page_stat *a, struct page_stat *b)
+static struct page_stat *page_stat__find_page(struct page_stat *pstat)
 {
-	if (a->page > b->page)
-		return -1;
-	if (a->page < b->page)
-		return 1;
-	if (a->order > b->order)
-		return -1;
-	if (a->order < b->order)
-		return 1;
-	if (a->migrate_type > b->migrate_type)
-		return -1;
-	if (a->migrate_type < b->migrate_type)
-		return 1;
-	if (a->gfp_flags > b->gfp_flags)
-		return -1;
-	if (a->gfp_flags < b->gfp_flags)
-		return 1;
-	return 0;
+	return __page_stat__findnew_page(pstat, false);
+}
+
+static struct page_stat *page_stat__findnew_page(struct page_stat *pstat)
+{
+	return __page_stat__findnew_page(pstat, true);
 }
 
-static struct page_stat *search_page_alloc_stat(struct page_stat *pstat, bool create)
+static struct page_stat *
+__page_stat__findnew_alloc(struct page_stat *pstat, bool create)
 {
 	struct rb_node **node = &page_alloc_tree.rb_node;
 	struct rb_node *parent = NULL;
 	struct page_stat *data;
+	struct sort_dimension *sort;
 
 	while (*node) {
-		s64 cmp;
+		int cmp = 0;
 
 		parent = *node;
 		data = rb_entry(*node, struct page_stat, node);
 
-		cmp = page_stat_cmp(data, pstat);
+		list_for_each_entry(sort, &page_alloc_sort_input, list) {
+			cmp = sort->cmp(pstat, data);
+			if (cmp)
+				break;
+		}
+
 		if (cmp < 0)
 			node = &parent->rb_left;
 		else if (cmp > 0)
@@ -357,6 +511,71 @@ static struct page_stat *search_page_alloc_stat(struct page_stat *pstat, bool cr
 	return data;
 }
 
+static struct page_stat *page_stat__find_alloc(struct page_stat *pstat)
+{
+	return __page_stat__findnew_alloc(pstat, false);
+}
+
+static struct page_stat *page_stat__findnew_alloc(struct page_stat *pstat)
+{
+	return __page_stat__findnew_alloc(pstat, true);
+}
+
+static struct page_stat *
+__page_stat__findnew_caller(struct page_stat *pstat, bool create)
+{
+	struct rb_node **node = &page_caller_tree.rb_node;
+	struct rb_node *parent = NULL;
+	struct page_stat *data;
+	struct sort_dimension *sort;
+
+	while (*node) {
+		int cmp = 0;
+
+		parent = *node;
+		data = rb_entry(*node, struct page_stat, node);
+
+		list_for_each_entry(sort, &page_caller_sort_input, list) {
+			cmp = sort->cmp(pstat, data);
+			if (cmp)
+				break;
+		}
+
+		if (cmp < 0)
+			node = &parent->rb_left;
+		else if (cmp > 0)
+			node = &parent->rb_right;
+		else
+			return data;
+	}
+
+	if (!create)
+		return NULL;
+
+	data = zalloc(sizeof(*data));
+	if (data != NULL) {
+		data->callsite = pstat->callsite;
+		data->order = pstat->order;
+		data->gfp_flags = pstat->gfp_flags;
+		data->migrate_type = pstat->migrate_type;
+
+		rb_link_node(&data->node, parent, node);
+		rb_insert_color(&data->node, &page_caller_tree);
+	}
+
+	return data;
+}
+
+static struct page_stat *page_stat__find_caller(struct page_stat *pstat)
+{
+	return __page_stat__findnew_caller(pstat, false);
+}
+
+static struct page_stat *page_stat__findnew_caller(struct page_stat *pstat)
+{
+	return __page_stat__findnew_caller(pstat, true);
+}
+
 static bool valid_page(u64 pfn_or_page)
 {
 	if (use_pfn && pfn_or_page == -1UL)
@@ -366,6 +585,176 @@ static bool valid_page(u64 pfn_or_page)
 	return true;
 }
 
+struct gfp_flag {
+	unsigned int flags;
+	char *compact_str;
+	char *human_readable;
+};
+
+static struct gfp_flag *gfps;
+static int nr_gfps;
+
+static int gfpcmp(const void *a, const void *b)
+{
+	const struct gfp_flag *fa = a;
+	const struct gfp_flag *fb = b;
+
+	return fa->flags - fb->flags;
+}
+
+/* see include/trace/events/gfpflags.h */
+static const struct {
+	const char *original;
+	const char *compact;
+} gfp_compact_table[] = {
+	{ "GFP_TRANSHUGE",		"THP" },
+	{ "GFP_HIGHUSER_MOVABLE",	"HUM" },
+	{ "GFP_HIGHUSER",		"HU" },
+	{ "GFP_USER",			"U" },
+	{ "GFP_TEMPORARY",		"TMP" },
+	{ "GFP_KERNEL",			"K" },
+	{ "GFP_NOFS",			"NF" },
+	{ "GFP_ATOMIC",			"A" },
+	{ "GFP_NOIO",			"NI" },
+	{ "GFP_HIGH",			"H" },
+	{ "GFP_WAIT",			"W" },
+	{ "GFP_IO",			"I" },
+	{ "GFP_COLD",			"CO" },
+	{ "GFP_NOWARN",			"NWR" },
+	{ "GFP_REPEAT",			"R" },
+	{ "GFP_NOFAIL",			"NF" },
+	{ "GFP_NORETRY",		"NR" },
+	{ "GFP_COMP",			"C" },
+	{ "GFP_ZERO",			"Z" },
+	{ "GFP_NOMEMALLOC",		"NMA" },
+	{ "GFP_MEMALLOC",		"MA" },
+	{ "GFP_HARDWALL",		"HW" },
+	{ "GFP_THISNODE",		"TN" },
+	{ "GFP_RECLAIMABLE",		"RC" },
+	{ "GFP_MOVABLE",		"M" },
+	{ "GFP_NOTRACK",		"NT" },
+	{ "GFP_NO_KSWAPD",		"NK" },
+	{ "GFP_OTHER_NODE",		"ON" },
+	{ "GFP_NOWAIT",			"NW" },
+};
+
+static size_t max_gfp_len;
+
+static char *compact_gfp_flags(char *gfp_flags)
+{
+	char *orig_flags = strdup(gfp_flags);
+	char *new_flags = NULL;
+	char *str, *pos = NULL;
+	size_t len = 0;
+
+	if (orig_flags == NULL)
+		return NULL;
+
+	str = strtok_r(orig_flags, "|", &pos);
+	while (str) {
+		size_t i;
+		char *new;
+		const char *cpt;
+
+		for (i = 0; i < ARRAY_SIZE(gfp_compact_table); i++) {
+			if (strcmp(gfp_compact_table[i].original, str))
+				continue;
+
+			cpt = gfp_compact_table[i].compact;
+			new = realloc(new_flags, len + strlen(cpt) + 2);
+			if (new == NULL) {
+				free(new_flags);
+				return NULL;
+			}
+
+			new_flags = new;
+
+			if (!len) {
+				strcpy(new_flags, cpt);
+			} else {
+				strcat(new_flags, "|");
+				strcat(new_flags, cpt);
+				len++;
+			}
+
+			len += strlen(cpt);
+		}
+
+		str = strtok_r(NULL, "|", &pos);
+	}
+
+	if (max_gfp_len < len)
+		max_gfp_len = len;
+
+	free(orig_flags);
+	return new_flags;
+}
+
+static char *compact_gfp_string(unsigned long gfp_flags)
+{
+	struct gfp_flag key = {
+		.flags = gfp_flags,
+	};
+	struct gfp_flag *gfp;
+
+	gfp = bsearch(&key, gfps, nr_gfps, sizeof(*gfps), gfpcmp);
+	if (gfp)
+		return gfp->compact_str;
+
+	return NULL;
+}
+
+static int parse_gfp_flags(struct perf_evsel *evsel, struct perf_sample *sample,
+			   unsigned int gfp_flags)
+{
+	struct pevent_record record = {
+		.cpu = sample->cpu,
+		.data = sample->raw_data,
+		.size = sample->raw_size,
+	};
+	struct trace_seq seq;
+	char *str, *pos = NULL;
+
+	if (nr_gfps) {
+		struct gfp_flag key = {
+			.flags = gfp_flags,
+		};
+
+		if (bsearch(&key, gfps, nr_gfps, sizeof(*gfps), gfpcmp))
+			return 0;
+	}
+
+	trace_seq_init(&seq);
+	pevent_event_info(&seq, evsel->tp_format, &record);
+
+	str = strtok_r(seq.buffer, " ", &pos);
+	while (str) {
+		if (!strncmp(str, "gfp_flags=", 10)) {
+			struct gfp_flag *new;
+
+			new = realloc(gfps, (nr_gfps + 1) * sizeof(*gfps));
+			if (new == NULL)
+				return -ENOMEM;
+
+			gfps = new;
+			new += nr_gfps++;
+
+			new->flags = gfp_flags;
+			new->human_readable = strdup(str + 10);
+			new->compact_str = compact_gfp_flags(str + 10);
+			if (!new->human_readable || !new->compact_str)
+				return -ENOMEM;
+
+			qsort(gfps, nr_gfps, sizeof(*gfps), gfpcmp);
+		}
+
+		str = strtok_r(NULL, " ", &pos);
+	}
+
+	trace_seq_destroy(&seq);
+	return 0;
+}
+
 static int perf_evsel__process_page_alloc_event(struct perf_evsel *evsel,
 						struct perf_sample *sample)
 {
@@ -375,6 +764,7 @@ static int perf_evsel__process_page_alloc_event(struct perf_evsel *evsel,
 	unsigned int migrate_type = perf_evsel__intval(evsel, sample,
 						       "migratetype");
 	u64 bytes = kmem_page_size << order;
+	u64 callsite;
 	struct page_stat *pstat;
 	struct page_stat this = {
 		.order = order,
@@ -397,20 +787,36 @@ static int perf_evsel__process_page_alloc_event(struct perf_evsel *evsel,
 		return 0;
 	}
 
+	if (parse_gfp_flags(evsel, sample, gfp_flags) < 0)
+		return -1;
+
+	callsite = find_callsite(evsel, sample);
+
 	/*
 	 * This is to find the current page (with correct gfp flags and
 	 * migrate type) at free event.
 	 */
-	pstat = search_page(page, true);
+	this.page = page;
+	pstat = page_stat__findnew_page(&this);
 	if (pstat == NULL)
 		return -ENOMEM;
 
-	pstat->order = order;
-	pstat->gfp_flags = gfp_flags;
-	pstat->migrate_type = migrate_type;
+	pstat->nr_alloc++;
+	pstat->alloc_bytes += bytes;
+	pstat->callsite = callsite;
+
+	if (!live_page) {
+		pstat = page_stat__findnew_alloc(&this);
+		if (pstat == NULL)
+			return -ENOMEM;
 
-	this.page = page;
-	pstat = search_page_alloc_stat(&this, true);
+		pstat->nr_alloc++;
+		pstat->alloc_bytes += bytes;
+		pstat->callsite = callsite;
+	}
+
+	this.callsite = callsite;
+	pstat = page_stat__findnew_caller(&this);
 	if (pstat == NULL)
 		return -ENOMEM;
 
@@ -441,7 +847,8 @@ static int perf_evsel__process_page_free_event(struct perf_evsel *evsel,
 	nr_page_frees++;
 	total_page_free_bytes += bytes;
 
-	pstat = search_page(page, false);
+	this.page = page;
+	pstat = page_stat__find_page(&this);
 	if (pstat == NULL) {
 		pr_debug2("missing free at page %"PRIx64" (order: %d)\n",
 			  page, order);
@@ -452,20 +859,41 @@ static int perf_evsel__process_page_free_event(struct perf_evsel *evsel,
 		return 0;
 	}
 
-	this.page = page;
 	this.gfp_flags = pstat->gfp_flags;
 	this.migrate_type = pstat->migrate_type;
+	this.callsite = pstat->callsite;
 
-	rb_erase(&pstat->node, &page_tree);
+	rb_erase(&pstat->node, &page_live_tree);
 	free(pstat);
 
-	pstat = search_page_alloc_stat(&this, false);
+	if (live_page) {
+		order_stats[this.order][this.migrate_type]--;
+	} else {
+		pstat = page_stat__find_alloc(&this);
+		if (pstat == NULL)
+			return -ENOMEM;
+
+		pstat->nr_free++;
+		pstat->free_bytes += bytes;
+	}
+
+	pstat = page_stat__find_caller(&this);
 	if (pstat == NULL)
 		return -ENOENT;
 
 	pstat->nr_free++;
 	pstat->free_bytes += bytes;
 
+	if (live_page) {
+		pstat->nr_alloc--;
+		pstat->alloc_bytes -= bytes;
+
+		if (pstat->nr_alloc == 0) {
+			rb_erase(&pstat->node, &page_caller_tree);
+			free(pstat);
+		}
+	}
+
 	return 0;
 }
 
@@ -478,6 +906,7 @@ static int process_sample_event(struct perf_tool *tool __maybe_unused,
 				struct perf_evsel *evsel,
 				struct machine *machine)
 {
+	int err = 0;
 	struct thread *thread = machine__findnew_thread(machine, sample->pid,
 							sample->tid);
 
@@ -491,10 +920,12 @@ static int process_sample_event(struct perf_tool *tool __maybe_unused,
 
 	if (evsel->handler != NULL) {
 		tracepoint_handler f = evsel->handler;
-		return f(evsel, sample);
+		err = f(evsel, sample);
 	}
 
-	return 0;
+	thread__put(thread);
+
+	return err;
 }
 
 static struct perf_tool perf_kmem = {
@@ -576,41 +1007,111 @@ static const char * const migrate_type_str[] = {
 	"UNKNOWN",
 };
 
-static void __print_page_result(struct rb_root *root,
-				struct perf_session *session __maybe_unused,
-				int n_lines)
+static void __print_page_alloc_result(struct perf_session *session, int n_lines)
 {
-	struct rb_node *next = rb_first(root);
+	struct rb_node *next = rb_first(&page_alloc_sorted);
+	struct machine *machine = &session->machines.host;
 	const char *format;
+	int gfp_len = max(strlen("GFP flags"), max_gfp_len);
 
-	printf("\n%.80s\n", graph_dotted_line);
-	printf(" %-16s | Total alloc (KB) | Hits      | Order | Mig.type | GFP flags\n",
-	       use_pfn ? "PFN" : "Page");
-	printf("%.80s\n", graph_dotted_line);
+	printf("\n%.105s\n", graph_dotted_line);
+	printf(" %-16s | %5s alloc (KB) | Hits      | Order | Mig.type | %-*s | Callsite\n",
+	       use_pfn ? "PFN" : "Page", live_page ? "Live" : "Total",
+	       gfp_len, "GFP flags");
+	printf("%.105s\n", graph_dotted_line);
 
 	if (use_pfn)
-		format = " %16llu | %'16llu | %'9d | %5d | %8s |  %08lx\n";
+		format = " %16llu | %'16llu | %'9d | %5d | %8s | %-*s | %s\n";
 	else
-		format = " %016llx | %'16llu | %'9d | %5d | %8s |  %08lx\n";
+		format = " %016llx | %'16llu | %'9d | %5d | %8s | %-*s | %s\n";
 
 	while (next && n_lines--) {
 		struct page_stat *data;
+		struct symbol *sym;
+		struct map *map;
+		char buf[32];
+		char *caller = buf;
 
 		data = rb_entry(next, struct page_stat, node);
+		sym = machine__find_kernel_function(machine, data->callsite,
+						    &map, NULL);
+		if (sym && sym->name)
+			caller = sym->name;
+		else
+			scnprintf(buf, sizeof(buf), "%"PRIx64, data->callsite);
 
 		printf(format, (unsigned long long)data->page,
 		       (unsigned long long)data->alloc_bytes / 1024,
 		       data->nr_alloc, data->order,
 		       migrate_type_str[data->migrate_type],
-		       (unsigned long)data->gfp_flags);
+		       gfp_len, compact_gfp_string(data->gfp_flags), caller);
 
 		next = rb_next(next);
 	}
 
-	if (n_lines == -1)
-		printf(" ...              | ...              | ...       | ...   | ...      | ...     \n");
+	if (n_lines == -1) {
+		printf(" ...              | ...              | ...       | ...   | ...      | %-*s | ...\n",
+		       gfp_len, "...");
+	}
+
+	printf("%.105s\n", graph_dotted_line);
+}
+
+static void __print_page_caller_result(struct perf_session *session, int n_lines)
+{
+	struct rb_node *next = rb_first(&page_caller_sorted);
+	struct machine *machine = &session->machines.host;
+	int gfp_len = max(strlen("GFP flags"), max_gfp_len);
+
+	printf("\n%.105s\n", graph_dotted_line);
+	printf(" %5s alloc (KB) | Hits      | Order | Mig.type | %-*s | Callsite\n",
+	       live_page ? "Live" : "Total", gfp_len, "GFP flags");
+	printf("%.105s\n", graph_dotted_line);
+
+	while (next && n_lines--) {
+		struct page_stat *data;
+		struct symbol *sym;
+		struct map *map;
+		char buf[32];
+		char *caller = buf;
+
+		data = rb_entry(next, struct page_stat, node);
+		sym = machine__find_kernel_function(machine, data->callsite,
+						    &map, NULL);
+		if (sym && sym->name)
+			caller = sym->name;
+		else
+			scnprintf(buf, sizeof(buf), "%"PRIx64, data->callsite);
+
+		printf(" %'16llu | %'9d | %5d | %8s | %-*s | %s\n",
+		       (unsigned long long)data->alloc_bytes / 1024,
+		       data->nr_alloc, data->order,
+		       migrate_type_str[data->migrate_type],
+		       gfp_len, compact_gfp_string(data->gfp_flags), caller);
+
+		next = rb_next(next);
+	}
+
+	if (n_lines == -1) {
+		printf(" ...              | ...       | ...   | ...      | %-*s | ...\n",
+		       gfp_len, "...");
+	}
 
-	printf("%.80s\n", graph_dotted_line);
+	printf("%.105s\n", graph_dotted_line);
+}
+
+static void print_gfp_flags(void)
+{
+	int i;
+
+	printf("#\n");
+	printf("# GFP flags\n");
+	printf("# ---------\n");
+	for (i = 0; i < nr_gfps; i++) {
+		printf("# %08x: %*s: %s\n", gfps[i].flags,
+		       (int) max_gfp_len, gfps[i].compact_str,
+		       gfps[i].human_readable);
+	}
 }
 
 static void print_slab_summary(void)
@@ -682,8 +1183,12 @@ static void print_slab_result(struct perf_session *session)
 
 static void print_page_result(struct perf_session *session)
 {
+	if (caller_flag || alloc_flag)
+		print_gfp_flags();
+	if (caller_flag)
+		__print_page_caller_result(session, caller_lines);
 	if (alloc_flag)
-		__print_page_result(&page_alloc_sorted, session, alloc_lines);
+		__print_page_alloc_result(session, alloc_lines);
 	print_page_summary();
 }
 
@@ -695,14 +1200,10 @@ static void print_result(struct perf_session *session)
 		print_page_result(session);
 }
 
-struct sort_dimension {
-	const char		name[20];
-	sort_fn_t		cmp;
-	struct list_head	list;
-};
-
-static LIST_HEAD(caller_sort);
-static LIST_HEAD(alloc_sort);
+static LIST_HEAD(slab_caller_sort);
+static LIST_HEAD(slab_alloc_sort);
+static LIST_HEAD(page_caller_sort);
+static LIST_HEAD(page_alloc_sort);
 
 static void sort_slab_insert(struct rb_root *root, struct alloc_stat *data,
 			     struct list_head *sort_list)
@@ -751,10 +1252,12 @@ static void __sort_slab_result(struct rb_root *root, struct rb_root *root_sorted
 	}
 }
 
-static void sort_page_insert(struct rb_root *root, struct page_stat *data)
+static void sort_page_insert(struct rb_root *root, struct page_stat *data,
+			     struct list_head *sort_list)
 {
 	struct rb_node **new = &root->rb_node;
 	struct rb_node *parent = NULL;
+	struct sort_dimension *sort;
 
 	while (*new) {
 		struct page_stat *this;
@@ -763,8 +1266,11 @@ static void sort_page_insert(struct rb_root *root, struct page_stat *data)
 		this = rb_entry(*new, struct page_stat, node);
 		parent = *new;
 
-		/* TODO: support more sort key */
-		cmp = data->alloc_bytes - this->alloc_bytes;
+		list_for_each_entry(sort, sort_list, list) {
+			cmp = sort->cmp(data, this);
+			if (cmp)
+				break;
+		}
 
 		if (cmp > 0)
 			new = &parent->rb_left;
@@ -776,7 +1282,8 @@ static void sort_page_insert(struct rb_root *root, struct page_stat *data)
 	rb_insert_color(&data->node, root);
 }
 
-static void __sort_page_result(struct rb_root *root, struct rb_root *root_sorted)
+static void __sort_page_result(struct rb_root *root, struct rb_root *root_sorted,
+			       struct list_head *sort_list)
 {
 	struct rb_node *node;
 	struct page_stat *data;
@@ -788,7 +1295,7 @@ static void __sort_page_result(struct rb_root *root, struct rb_root *root_sorted
 
 		rb_erase(node, root);
 		data = rb_entry(node, struct page_stat, node);
-		sort_page_insert(root_sorted, data);
+		sort_page_insert(root_sorted, data, sort_list);
 	}
 }
 
@@ -796,12 +1303,20 @@ static void sort_result(void)
 {
 	if (kmem_slab) {
 		__sort_slab_result(&root_alloc_stat, &root_alloc_sorted,
-				   &alloc_sort);
+				   &slab_alloc_sort);
 		__sort_slab_result(&root_caller_stat, &root_caller_sorted,
-				   &caller_sort);
+				   &slab_caller_sort);
 	}
 	if (kmem_page) {
-		__sort_page_result(&page_alloc_tree, &page_alloc_sorted);
+		if (live_page)
+			__sort_page_result(&page_live_tree, &page_alloc_sorted,
+					   &page_alloc_sort);
+		else
+			__sort_page_result(&page_alloc_tree, &page_alloc_sorted,
+					   &page_alloc_sort);
+
+		__sort_page_result(&page_caller_tree, &page_caller_sorted,
+				   &page_caller_sort);
 	}
 }
 
@@ -850,8 +1365,12 @@ out:
 	return err;
 }
 
-static int ptr_cmp(struct alloc_stat *l, struct alloc_stat *r)
+/* slab sort keys */
+static int ptr_cmp(void *a, void *b)
 {
+	struct alloc_stat *l = a;
+	struct alloc_stat *r = b;
+
 	if (l->ptr < r->ptr)
 		return -1;
 	else if (l->ptr > r->ptr)
@@ -864,8 +1383,11 @@ static struct sort_dimension ptr_sort_dimension = {
 	.cmp	= ptr_cmp,
 };
 
-static int callsite_cmp(struct alloc_stat *l, struct alloc_stat *r)
+static int slab_callsite_cmp(void *a, void *b)
 {
+	struct alloc_stat *l = a;
+	struct alloc_stat *r = b;
+
 	if (l->call_site < r->call_site)
 		return -1;
 	else if (l->call_site > r->call_site)
@@ -875,11 +1397,14 @@ static int callsite_cmp(struct alloc_stat *l, struct alloc_stat *r)
 
 static struct sort_dimension callsite_sort_dimension = {
 	.name	= "callsite",
-	.cmp	= callsite_cmp,
+	.cmp	= slab_callsite_cmp,
 };
 
-static int hit_cmp(struct alloc_stat *l, struct alloc_stat *r)
+static int hit_cmp(void *a, void *b)
 {
+	struct alloc_stat *l = a;
+	struct alloc_stat *r = b;
+
 	if (l->hit < r->hit)
 		return -1;
 	else if (l->hit > r->hit)
@@ -892,8 +1417,11 @@ static struct sort_dimension hit_sort_dimension = {
 	.cmp	= hit_cmp,
 };
 
-static int bytes_cmp(struct alloc_stat *l, struct alloc_stat *r)
+static int bytes_cmp(void *a, void *b)
 {
+	struct alloc_stat *l = a;
+	struct alloc_stat *r = b;
+
 	if (l->bytes_alloc < r->bytes_alloc)
 		return -1;
 	else if (l->bytes_alloc > r->bytes_alloc)
@@ -906,9 +1434,11 @@ static struct sort_dimension bytes_sort_dimension = {
 	.cmp	= bytes_cmp,
 };
 
-static int frag_cmp(struct alloc_stat *l, struct alloc_stat *r)
+static int frag_cmp(void *a, void *b)
 {
 	double x, y;
+	struct alloc_stat *l = a;
+	struct alloc_stat *r = b;
 
 	x = fragmentation(l->bytes_req, l->bytes_alloc);
 	y = fragmentation(r->bytes_req, r->bytes_alloc);
@@ -925,8 +1455,11 @@ static struct sort_dimension frag_sort_dimension = {
 	.cmp	= frag_cmp,
 };
 
-static int pingpong_cmp(struct alloc_stat *l, struct alloc_stat *r)
+static int pingpong_cmp(void *a, void *b)
 {
+	struct alloc_stat *l = a;
+	struct alloc_stat *r = b;
+
 	if (l->pingpong < r->pingpong)
 		return -1;
 	else if (l->pingpong > r->pingpong)
@@ -939,7 +1472,135 @@ static struct sort_dimension pingpong_sort_dimension = {
 	.cmp	= pingpong_cmp,
 };
 
-static struct sort_dimension *avail_sorts[] = {
+/* page sort keys */
+static int page_cmp(void *a, void *b)
+{
+	struct page_stat *l = a;
+	struct page_stat *r = b;
+
+	if (l->page < r->page)
+		return -1;
+	else if (l->page > r->page)
+		return 1;
+	return 0;
+}
+
+static struct sort_dimension page_sort_dimension = {
+	.name	= "page",
+	.cmp	= page_cmp,
+};
+
+static int page_callsite_cmp(void *a, void *b)
+{
+	struct page_stat *l = a;
+	struct page_stat *r = b;
+
+	if (l->callsite < r->callsite)
+		return -1;
+	else if (l->callsite > r->callsite)
+		return 1;
+	return 0;
+}
+
+static struct sort_dimension page_callsite_sort_dimension = {
+	.name	= "callsite",
+	.cmp	= page_callsite_cmp,
+};
+
+static int page_hit_cmp(void *a, void *b)
+{
+	struct page_stat *l = a;
+	struct page_stat *r = b;
+
+	if (l->nr_alloc < r->nr_alloc)
+		return -1;
+	else if (l->nr_alloc > r->nr_alloc)
+		return 1;
+	return 0;
+}
+
+static struct sort_dimension page_hit_sort_dimension = {
+	.name	= "hit",
+	.cmp	= page_hit_cmp,
+};
+
+static int page_bytes_cmp(void *a, void *b)
+{
+	struct page_stat *l = a;
+	struct page_stat *r = b;
+
+	if (l->alloc_bytes < r->alloc_bytes)
+		return -1;
+	else if (l->alloc_bytes > r->alloc_bytes)
+		return 1;
+	return 0;
+}
+
+static struct sort_dimension page_bytes_sort_dimension = {
+	.name	= "bytes",
+	.cmp	= page_bytes_cmp,
+};
+
+static int page_order_cmp(void *a, void *b)
+{
+	struct page_stat *l = a;
+	struct page_stat *r = b;
+
+	if (l->order < r->order)
+		return -1;
+	else if (l->order > r->order)
+		return 1;
+	return 0;
+}
+
+static struct sort_dimension page_order_sort_dimension = {
+	.name	= "order",
+	.cmp	= page_order_cmp,
+};
+
+static int migrate_type_cmp(void *a, void *b)
+{
+	struct page_stat *l = a;
+	struct page_stat *r = b;
+
+	/* for internal use to find free'd page */
+	if (l->migrate_type == -1U)
+		return 0;
+
+	if (l->migrate_type < r->migrate_type)
+		return -1;
+	else if (l->migrate_type > r->migrate_type)
+		return 1;
+	return 0;
+}
+
+static struct sort_dimension migrate_type_sort_dimension = {
+	.name	= "migtype",
+	.cmp	= migrate_type_cmp,
+};
+
+static int gfp_flags_cmp(void *a, void *b)
+{
+	struct page_stat *l = a;
+	struct page_stat *r = b;
+
+	/* for internal use to find free'd page */
+	if (l->gfp_flags == -1U)
+		return 0;
+
+	if (l->gfp_flags < r->gfp_flags)
+		return -1;
+	else if (l->gfp_flags > r->gfp_flags)
+		return 1;
+	return 0;
+}
+
+static struct sort_dimension gfp_flags_sort_dimension = {
+	.name	= "gfp",
+	.cmp	= gfp_flags_cmp,
+};
+
+static struct sort_dimension *slab_sorts[] = {
 	&ptr_sort_dimension,
 	&callsite_sort_dimension,
 	&hit_sort_dimension,
@@ -948,16 +1609,44 @@ static struct sort_dimension *avail_sorts[] = {
 	&pingpong_sort_dimension,
 };
 
-#define NUM_AVAIL_SORTS	((int)ARRAY_SIZE(avail_sorts))
+static struct sort_dimension *page_sorts[] = {
+	&page_sort_dimension,
+	&page_callsite_sort_dimension,
+	&page_hit_sort_dimension,
+	&page_bytes_sort_dimension,
+	&page_order_sort_dimension,
+	&migrate_type_sort_dimension,
+	&gfp_flags_sort_dimension,
+};
+
+static int slab_sort_dimension__add(const char *tok, struct list_head *list)
+{
+	struct sort_dimension *sort;
+	int i;
+
+	for (i = 0; i < (int)ARRAY_SIZE(slab_sorts); i++) {
+		if (!strcmp(slab_sorts[i]->name, tok)) {
+			sort = memdup(slab_sorts[i], sizeof(*slab_sorts[i]));
+			if (!sort) {
+				pr_err("%s: memdup failed\n", __func__);
+				return -1;
+			}
+			list_add_tail(&sort->list, list);
+			return 0;
+		}
+	}
+
+	return -1;
+}
 
-static int sort_dimension__add(const char *tok, struct list_head *list)
+static int page_sort_dimension__add(const char *tok, struct list_head *list)
 {
 	struct sort_dimension *sort;
 	int i;
 
-	for (i = 0; i < NUM_AVAIL_SORTS; i++) {
-		if (!strcmp(avail_sorts[i]->name, tok)) {
-			sort = memdup(avail_sorts[i], sizeof(*avail_sorts[i]));
+	for (i = 0; i < (int)ARRAY_SIZE(page_sorts); i++) {
+		if (!strcmp(page_sorts[i]->name, tok)) {
+			sort = memdup(page_sorts[i], sizeof(*page_sorts[i]));
 			if (!sort) {
 				pr_err("%s: memdup failed\n", __func__);
 				return -1;
@@ -970,7 +1659,33 @@ static int sort_dimension__add(const char *tok, struct list_head *list)
 	return -1;
 }
 
-static int setup_sorting(struct list_head *sort_list, const char *arg)
+static int setup_slab_sorting(struct list_head *sort_list, const char *arg)
+{
+	char *tok;
+	char *str = strdup(arg);
+	char *pos = str;
+
+	if (!str) {
+		pr_err("%s: strdup failed\n", __func__);
+		return -1;
+	}
+
+	while (true) {
+		tok = strsep(&pos, ",");
+		if (!tok)
+			break;
+		if (slab_sort_dimension__add(tok, sort_list) < 0) {
+			error("Unknown slab --sort key: '%s'", tok);
+			free(str);
+			return -1;
+		}
+	}
+
+	free(str);
+	return 0;
+}
+
+static int setup_page_sorting(struct list_head *sort_list, const char *arg)
 {
 	char *tok;
 	char *str = strdup(arg);
@@ -985,8 +1700,8 @@ static int setup_sorting(struct list_head *sort_list, const char *arg)
 		tok = strsep(&pos, ",");
 		if (!tok)
 			break;
-		if (sort_dimension__add(tok, sort_list) < 0) {
-			error("Unknown --sort key: '%s'", tok);
+		if (page_sort_dimension__add(tok, sort_list) < 0) {
+			error("Unknown page --sort key: '%s'", tok);
 			free(str);
 			return -1;
 		}
@@ -1002,10 +1717,18 @@ static int parse_sort_opt(const struct option *opt __maybe_unused,
 	if (!arg)
 		return -1;
 
-	if (caller_flag > alloc_flag)
-		return setup_sorting(&caller_sort, arg);
-	else
-		return setup_sorting(&alloc_sort, arg);
+	if (kmem_page > kmem_slab ||
+	    (kmem_page == 0 && kmem_slab == 0 && kmem_default == KMEM_PAGE)) {
+		if (caller_flag > alloc_flag)
+			return setup_page_sorting(&page_caller_sort, arg);
+		else
+			return setup_page_sorting(&page_alloc_sort, arg);
+	} else {
+		if (caller_flag > alloc_flag)
+			return setup_slab_sorting(&slab_caller_sort, arg);
+		else
+			return setup_slab_sorting(&slab_alloc_sort, arg);
+	}
 
 	return 0;
 }
@@ -1084,7 +1807,7 @@ static int __cmd_record(int argc, const char **argv)
 	if (kmem_slab)
 		rec_argc += ARRAY_SIZE(slab_events);
 	if (kmem_page)
-		rec_argc += ARRAY_SIZE(page_events);
+		rec_argc += ARRAY_SIZE(page_events) + 1; /* for -g */
 
 	rec_argv = calloc(rec_argc + 1, sizeof(char *));
 
@@ -1099,6 +1822,8 @@ static int __cmd_record(int argc, const char **argv)
 			rec_argv[i] = strdup(slab_events[j]);
 	}
 	if (kmem_page) {
+		rec_argv[i++] = strdup("-g");
+
 		for (j = 0; j < ARRAY_SIZE(page_events); j++, i++)
 			rec_argv[i] = strdup(page_events[j]);
 	}
@@ -1109,9 +1834,26 @@ static int __cmd_record(int argc, const char **argv)
 	return cmd_record(i, rec_argv, NULL);
 }
 
+static int kmem_config(const char *var, const char *value, void *cb)
+{
+	if (!strcmp(var, "kmem.default")) {
+		if (!strcmp(value, "slab"))
+			kmem_default = KMEM_SLAB;
+		else if (!strcmp(value, "page"))
+			kmem_default = KMEM_PAGE;
+		else
+			pr_err("invalid default value ('slab' or 'page' required): %s\n",
+			       value);
+		return 0;
+	}
+
+	return perf_default_config(var, value, cb);
+}
+
 int cmd_kmem(int argc, const char **argv, const char *prefix __maybe_unused)
 {
-	const char * const default_sort_order = "frag,hit,bytes";
+	const char * const default_slab_sort = "frag,hit,bytes";
+	const char * const default_page_sort = "bytes,hit";
 	struct perf_data_file file = {
 		.mode = PERF_DATA_MODE_READ,
 	};
@@ -1124,8 +1866,8 @@ int cmd_kmem(int argc, const char **argv, const char *prefix __maybe_unused)
 	OPT_CALLBACK_NOOPT(0, "alloc", NULL, NULL,
 			   "show per-allocation statistics", parse_alloc_opt),
 	OPT_CALLBACK('s', "sort", NULL, "key[,key2...]",
-		     "sort by keys: ptr, call_site, bytes, hit, pingpong, frag",
-		     parse_sort_opt),
+		     "sort by keys: ptr, callsite, bytes, hit, pingpong, frag, "
+		     "page, order, migtype, gfp", parse_sort_opt),
 	OPT_CALLBACK('l', "line", NULL, "num", "show n lines", parse_line_opt),
 	OPT_BOOLEAN(0, "raw-ip", &raw_ip, "show raw ip instead of symbol"),
 	OPT_BOOLEAN('f', "force", &file.force, "don't complain, do it"),
@@ -1133,6 +1875,7 @@ int cmd_kmem(int argc, const char **argv, const char *prefix __maybe_unused)
 			   parse_slab_opt),
 	OPT_CALLBACK_NOOPT(0, "page", NULL, NULL, "Analyze page allocator",
 			   parse_page_opt),
+	OPT_BOOLEAN(0, "live", &live_page, "Show live page stat"),
 	OPT_END()
 	};
 	const char *const kmem_subcommands[] = { "record", "stat", NULL };
@@ -1142,15 +1885,21 @@ int cmd_kmem(int argc, const char **argv, const char *prefix __maybe_unused)
 	};
 	struct perf_session *session;
 	int ret = -1;
+	const char errmsg[] = "No %s allocation events found.  Have you run 'perf kmem record --%s'?\n";
 
+	perf_config(kmem_config, NULL);
 	argc = parse_options_subcommand(argc, argv, kmem_options,
 					kmem_subcommands, kmem_usage, 0);
 
 	if (!argc)
 		usage_with_options(kmem_usage, kmem_options);
 
-	if (kmem_slab == 0 && kmem_page == 0)
-		kmem_slab = 1;  /* for backward compatibility */
+	if (kmem_slab == 0 && kmem_page == 0) {
+		if (kmem_default == KMEM_SLAB)
+			kmem_slab = 1;
+		else
+			kmem_page = 1;
+	}
 
 	if (!strncmp(argv[0], "rec", 3)) {
 		symbol__init(NULL);
@@ -1159,19 +1908,30 @@ int cmd_kmem(int argc, const char **argv, const char *prefix __maybe_unused)
 
 	file.path = input_name;
 
-	session = perf_session__new(&file, false, &perf_kmem);
+	kmem_session = session = perf_session__new(&file, false, &perf_kmem);
 	if (session == NULL)
 		return -1;
 
+	if (kmem_slab) {
+		if (!perf_evlist__find_tracepoint_by_name(session->evlist,
+							  "kmem:kmalloc")) {
+			pr_err(errmsg, "slab", "slab");
+			return -1;
+		}
+	}
+
 	if (kmem_page) {
-		struct perf_evsel *evsel = perf_evlist__first(session->evlist);
+		struct perf_evsel *evsel;
 
-		if (evsel == NULL || evsel->tp_format == NULL) {
-			pr_err("invalid event found.. aborting\n");
+		evsel = perf_evlist__find_tracepoint_by_name(session->evlist,
+							     "kmem:mm_page_alloc");
+		if (evsel == NULL) {
+			pr_err(errmsg, "page", "page");
 			return -1;
 		}
 
 		kmem_page_size = pevent_get_page_size(evsel->tp_format->pevent);
+		symbol_conf.use_callchain = true;
 	}
 
 	symbol__init(&session->header.env);
@@ -1182,11 +1942,21 @@ int cmd_kmem(int argc, const char **argv, const char *prefix __maybe_unused)
 		if (cpu__setup_cpunode_map())
 			goto out_delete;
 
-		if (list_empty(&caller_sort))
-			setup_sorting(&caller_sort, default_sort_order);
-		if (list_empty(&alloc_sort))
-			setup_sorting(&alloc_sort, default_sort_order);
-
+		if (list_empty(&slab_caller_sort))
+			setup_slab_sorting(&slab_caller_sort, default_slab_sort);
+		if (list_empty(&slab_alloc_sort))
+			setup_slab_sorting(&slab_alloc_sort, default_slab_sort);
+		if (list_empty(&page_caller_sort))
+			setup_page_sorting(&page_caller_sort, default_page_sort);
+		if (list_empty(&page_alloc_sort))
+			setup_page_sorting(&page_alloc_sort, default_page_sort);
+
+		if (kmem_page) {
+			setup_page_sorting(&page_alloc_sort_input,
+					   "page,order,migtype,gfp");
+			setup_page_sorting(&page_caller_sort_input,
+					   "callsite,order,migtype,gfp");
+		}
 		ret = __cmd_kmem(session);
 	} else
 		usage_with_options(kmem_usage, kmem_options);
diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c
index 1f9338f6109c..74878cd75078 100644
--- a/tools/perf/builtin-kvm.c
+++ b/tools/perf/builtin-kvm.c
@@ -651,6 +651,7 @@ static int process_sample_event(struct perf_tool *tool,
 				struct perf_evsel *evsel,
 				struct machine *machine)
 {
+	int err = 0;
 	struct thread *thread;
 	struct perf_kvm_stat *kvm = container_of(tool, struct perf_kvm_stat,
 						 tool);
@@ -666,9 +667,10 @@ static int process_sample_event(struct perf_tool *tool,
 	}
 
 	if (!handle_kvm_event(kvm, thread, evsel, sample))
-		return -1;
+		err = -1;
 
-	return 0;
+	thread__put(thread);
+	return err;
 }
 
 static int cpu_isa_config(struct perf_kvm_stat *kvm)
@@ -1309,6 +1311,8 @@ static int kvm_events_live(struct perf_kvm_stat *kvm,
 			"show events other than"
 			" HLT (x86 only) or Wait state (s390 only)"
 			" that take longer than duration usecs"),
+		OPT_UINTEGER(0, "proc-map-timeout", &kvm->opts.proc_map_timeout,
+				"per thread proc mmap processing timeout in ms"),
 		OPT_END()
 	};
 	const char * const live_usage[] = {
@@ -1336,6 +1340,7 @@ static int kvm_events_live(struct perf_kvm_stat *kvm,
 	kvm->opts.target.uses_mmap = false;
 	kvm->opts.target.uid_str = NULL;
 	kvm->opts.target.uid = UINT_MAX;
+	kvm->opts.proc_map_timeout = 500;
 
 	symbol__init(NULL);
 	disable_buildid_cache();
@@ -1391,7 +1396,7 @@ static int kvm_events_live(struct perf_kvm_stat *kvm,
 	perf_session__set_id_hdr_size(kvm->session);
 	ordered_events__set_copy_on_queue(&kvm->session->ordered_events, true);
 	machine__synthesize_threads(&kvm->session->machines.host, &kvm->opts.target,
-				    kvm->evlist->threads, false);
+				    kvm->evlist->threads, false, kvm->opts.proc_map_timeout);
 	err = kvm_live_open_events(kvm);
 	if (err)
 		goto out;
diff --git a/tools/perf/builtin-lock.c b/tools/perf/builtin-lock.c
index d49c2ab85fc2..de16aaed516e 100644
--- a/tools/perf/builtin-lock.c
+++ b/tools/perf/builtin-lock.c
@@ -769,6 +769,7 @@ static void dump_threads(void)
 		t = perf_session__findnew(session, st->tid);
 		pr_info("%10d: %s\n", st->tid, thread__comm_str(t));
 		node = rb_next(node);
+		thread__put(t);
 	};
 }
 
@@ -810,6 +811,7 @@ static int process_sample_event(struct perf_tool *tool __maybe_unused,
 				struct perf_evsel *evsel,
 				struct machine *machine)
 {
+	int err = 0;
 	struct thread *thread = machine__findnew_thread(machine, sample->pid,
 							sample->tid);
 
@@ -821,10 +823,12 @@ static int process_sample_event(struct perf_tool *tool __maybe_unused,
 
 	if (evsel->handler != NULL) {
 		tracepoint_handler f = evsel->handler;
-		return f(evsel, sample);
+		err = f(evsel, sample);
 	}
 
-	return 0;
+	thread__put(thread);
+
+	return err;
 }
 
 static void sort_result(void)
diff --git a/tools/perf/builtin-mem.c b/tools/perf/builtin-mem.c
index 675216e08bfc..da2ec06f0742 100644
--- a/tools/perf/builtin-mem.c
+++ b/tools/perf/builtin-mem.c
@@ -74,7 +74,7 @@ dump_raw_samples(struct perf_tool *tool,
 	}
 
 	if (al.filtered || (mem->hide_unresolved && al.sym == NULL))
-		return 0;
+		goto out_put;
 
 	if (al.map != NULL)
 		al.map->dso->hit = 1;
@@ -103,7 +103,8 @@ dump_raw_samples(struct perf_tool *tool,
 		symbol_conf.field_sep,
 		al.map ? (al.map->dso ? al.map->dso->long_name : "???") : "???",
 		al.sym ? al.sym->name : "???");
-
+out_put:
+	addr_location__put(&al);
 	return 0;
 }
 
diff --git a/tools/perf/builtin-probe.c b/tools/perf/builtin-probe.c
index f7b1af67e9f6..1272559fa22d 100644
--- a/tools/perf/builtin-probe.c
+++ b/tools/perf/builtin-probe.c
@@ -44,25 +44,19 @@
 
 #define DEFAULT_VAR_FILTER "!__k???tab_* & !__crc_*"
 #define DEFAULT_FUNC_FILTER "!_*"
+#define DEFAULT_LIST_FILTER "*:*"
 
 /* Session management structure */
 static struct {
+	int command;	/* Command short_name */
 	bool list_events;
-	bool force_add;
-	bool show_lines;
-	bool show_vars;
-	bool show_ext_vars;
-	bool show_funcs;
-	bool mod_events;
 	bool uprobes;
 	bool quiet;
 	bool target_used;
 	int nevents;
 	struct perf_probe_event events[MAX_PROBES];
-	struct strlist *dellist;
 	struct line_range line_range;
 	char *target;
-	int max_probe_points;
 	struct strfilter *filter;
 } params;
 
@@ -93,6 +87,28 @@ static int parse_probe_event(const char *str)
 	return ret;
 }
 
+static int params_add_filter(const char *str)
+{
+	const char *err = NULL;
+	int ret = 0;
+
+	pr_debug2("Add filter: %s\n", str);
+	if (!params.filter) {
+		params.filter = strfilter__new(str, &err);
+		if (!params.filter)
+			ret = err ? -EINVAL : -ENOMEM;
+	} else
+		ret = strfilter__or(params.filter, str, &err);
+
+	if (ret == -EINVAL) {
+		pr_err("Filter parse error at %td.\n", err - str + 1);
+		pr_err("Source: \"%s\"\n", str);
+		pr_err("         %*c\n", (int)(err - str + 1), '^');
+	}
+
+	return ret;
+}
+
 static int set_target(const char *ptr)
 {
 	int found = 0;
@@ -152,34 +168,11 @@ static int parse_probe_event_argv(int argc, const char **argv)
 
 		len += sprintf(&buf[len], "%s ", argv[i]);
 	}
-	params.mod_events = true;
 	ret = parse_probe_event(buf);
 	free(buf);
 	return ret;
 }
 
-static int opt_add_probe_event(const struct option *opt __maybe_unused,
-			      const char *str, int unset __maybe_unused)
-{
-	if (str) {
-		params.mod_events = true;
-		return parse_probe_event(str);
-	} else
-		return 0;
-}
-
-static int opt_del_probe_event(const struct option *opt __maybe_unused,
-			       const char *str, int unset __maybe_unused)
-{
-	if (str) {
-		params.mod_events = true;
-		if (!params.dellist)
-			params.dellist = strlist__new(true, NULL);
-		strlist__add(params.dellist, str);
-	}
-	return 0;
-}
-
 static int opt_set_target(const struct option *opt, const char *str,
 			int unset __maybe_unused)
 {
@@ -217,8 +210,10 @@ static int opt_set_target(const struct option *opt, const char *str,
 	return ret;
 }
 
+/* Command option callbacks */
+
 #ifdef HAVE_DWARF_SUPPORT
-static int opt_show_lines(const struct option *opt __maybe_unused,
+static int opt_show_lines(const struct option *opt,
 			  const char *str, int unset __maybe_unused)
 {
 	int ret = 0;
@@ -226,19 +221,19 @@ static int opt_show_lines(const struct option *opt __maybe_unused,
 	if (!str)
 		return 0;
 
-	if (params.show_lines) {
+	if (params.command == 'L') {
 		pr_warning("Warning: more than one --line options are"
 			   " detected. Only the first one is valid.\n");
 		return 0;
 	}
 
-	params.show_lines = true;
+	params.command = opt->short_name;
 	ret = parse_line_range_desc(str, &params.line_range);
 
 	return ret;
 }
 
-static int opt_show_vars(const struct option *opt __maybe_unused,
+static int opt_show_vars(const struct option *opt,
 			 const char *str, int unset __maybe_unused)
 {
 	struct perf_probe_event *pev = &params.events[params.nevents];
@@ -252,29 +247,39 @@ static int opt_show_vars(const struct option *opt __maybe_unused,
 		pr_err("  Error: '--vars' doesn't accept arguments.\n");
 		return -EINVAL;
 	}
-	params.show_vars = true;
+	params.command = opt->short_name;
 
 	return ret;
 }
 #endif
+static int opt_add_probe_event(const struct option *opt,
+			      const char *str, int unset __maybe_unused)
+{
+	if (str) {
+		params.command = opt->short_name;
+		return parse_probe_event(str);
+	}
+
+	return 0;
+}
+
+static int opt_set_filter_with_command(const struct option *opt,
+				       const char *str, int unset)
+{
+	if (!unset)
+		params.command = opt->short_name;
+
+	if (str)
+		return params_add_filter(str);
+
+	return 0;
+}
 
 static int opt_set_filter(const struct option *opt __maybe_unused,
 			  const char *str, int unset __maybe_unused)
 {
-	const char *err;
-
-	if (str) {
-		pr_debug2("Set filter: %s\n", str);
-		if (params.filter)
-			strfilter__delete(params.filter);
-		params.filter = strfilter__new(str, &err);
-		if (!params.filter) {
-			pr_err("Filter parse error at %td.\n", err - str + 1);
-			pr_err("Source: \"%s\"\n", str);
-			pr_err("         %*c\n", (int)(err - str + 1), '^');
-			return -EINVAL;
-		}
-	}
+	if (str)
+		return params_add_filter(str);
 
 	return 0;
 }
@@ -290,8 +295,6 @@ static void cleanup_params(void)
 
 	for (i = 0; i < params.nevents; i++)
 		clear_perf_probe_event(params.events + i);
-	if (params.dellist)
-		strlist__delete(params.dellist);
 	line_range__clear(&params.line_range);
 	free(params.target);
 	if (params.filter)
@@ -316,22 +319,24 @@ __cmd_probe(int argc, const char **argv, const char *prefix __maybe_unused)
 		"perf probe [<options>] 'PROBEDEF' ['PROBEDEF' ...]",
 		"perf probe [<options>] --add 'PROBEDEF' [--add 'PROBEDEF' ...]",
 		"perf probe [<options>] --del '[GROUP:]EVENT' ...",
-		"perf probe --list",
+		"perf probe --list [GROUP:]EVENT ...",
 #ifdef HAVE_DWARF_SUPPORT
 		"perf probe [<options>] --line 'LINEDESC'",
 		"perf probe [<options>] --vars 'PROBEPOINT'",
 #endif
+		"perf probe [<options>] --funcs",
 		NULL
-};
+	};
 	struct option options[] = {
 	OPT_INCR('v', "verbose", &verbose,
 		    "be more verbose (show parsed arguments, etc)"),
 	OPT_BOOLEAN('q', "quiet", &params.quiet,
 		    "be quiet (do not show any mesages)"),
-	OPT_BOOLEAN('l', "list", &params.list_events,
-		    "list up current probe events"),
+	OPT_CALLBACK_DEFAULT('l', "list", NULL, "[GROUP:]EVENT",
+			     "list up probe events",
+			     opt_set_filter_with_command, DEFAULT_LIST_FILTER),
 	OPT_CALLBACK('d', "del", NULL, "[GROUP:]EVENT", "delete a probe event.",
-		opt_del_probe_event),
+		     opt_set_filter_with_command),
 	OPT_CALLBACK('a', "add", NULL,
 #ifdef HAVE_DWARF_SUPPORT
 		"[EVENT=]FUNC[@SRC][+OFF|%return|:RL|;PT]|SRC:AL|SRC;PT"
@@ -356,7 +361,7 @@ __cmd_probe(int argc, const char **argv, const char *prefix __maybe_unused)
 		"\t\tARG:\tProbe argument (kprobe-tracer argument format.)\n",
 #endif
 		opt_add_probe_event),
-	OPT_BOOLEAN('f', "force", &params.force_add, "forcibly add events"
+	OPT_BOOLEAN('f', "force", &probe_conf.force_add, "forcibly add events"
 		    " with existing name"),
 #ifdef HAVE_DWARF_SUPPORT
 	OPT_CALLBACK('L', "line", NULL,
@@ -365,8 +370,10 @@ __cmd_probe(int argc, const char **argv, const char *prefix __maybe_unused)
 	OPT_CALLBACK('V', "vars", NULL,
 		     "FUNC[@SRC][+OFF|%return|:RL|;PT]|SRC:AL|SRC;PT",
 		     "Show accessible variables on PROBEDEF", opt_show_vars),
-	OPT_BOOLEAN('\0', "externs", &params.show_ext_vars,
+	OPT_BOOLEAN('\0', "externs", &probe_conf.show_ext_vars,
 		    "Show external variables too (with --vars only)"),
+	OPT_BOOLEAN('\0', "range", &probe_conf.show_location_range,
+		"Show variables location range in scope (with --vars only)"),
 	OPT_STRING('k', "vmlinux", &symbol_conf.vmlinux_name,
 		   "file", "vmlinux pathname"),
 	OPT_STRING('s', "source", &symbol_conf.source_prefix,
@@ -374,12 +381,15 @@ __cmd_probe(int argc, const char **argv, const char *prefix __maybe_unused)
 	OPT_CALLBACK('m', "module", NULL, "modname|path",
 		"target module name (for online) or path (for offline)",
 		opt_set_target),
+	OPT_BOOLEAN('\0', "no-inlines", &probe_conf.no_inlines,
+		"Don't search inlined functions"),
 #endif
 	OPT__DRY_RUN(&probe_event_dry_run),
-	OPT_INTEGER('\0', "max-probes", &params.max_probe_points,
+	OPT_INTEGER('\0', "max-probes", &probe_conf.max_probes,
 		 "Set how many probe points can be found for a probe."),
-	OPT_BOOLEAN('F', "funcs", &params.show_funcs,
-		    "Show potential probe-able functions."),
+	OPT_CALLBACK_DEFAULT('F', "funcs", NULL, "[FILTER]",
+			     "Show potential probe-able functions.",
+			     opt_set_filter_with_command, DEFAULT_FUNC_FILTER),
 	OPT_CALLBACK('\0', "filter", NULL,
 		     "[!]FILTER", "Set a filter (with --vars/funcs only)\n"
 		     "\t\t\t(default: \"" DEFAULT_VAR_FILTER "\" for --vars,\n"
@@ -402,6 +412,7 @@ __cmd_probe(int argc, const char **argv, const char *prefix __maybe_unused)
 	set_option_flag(options, 'L', "line", PARSE_OPT_EXCLUSIVE);
 	set_option_flag(options, 'V', "vars", PARSE_OPT_EXCLUSIVE);
 #endif
+	set_option_flag(options, 'F', "funcs", PARSE_OPT_EXCLUSIVE);
 
 	argc = parse_options(argc, argv, options, probe_usage,
 			     PARSE_OPT_STOP_AT_NON_OPTION);
@@ -410,11 +421,16 @@ __cmd_probe(int argc, const char **argv, const char *prefix __maybe_unused)
 			pr_warning("  Error: '-' is not supported.\n");
 			usage_with_options(probe_usage, options);
 		}
+		if (params.command && params.command != 'a') {
+			pr_warning("  Error: another command except --add is set.\n");
+			usage_with_options(probe_usage, options);
+		}
 		ret = parse_probe_event_argv(argc, argv);
 		if (ret < 0) {
 			pr_err_with_code("  Error: Command Parse Error.", ret);
 			return ret;
 		}
+		params.command = 'a';
 	}
 
 	if (params.quiet) {
@@ -425,89 +441,70 @@ __cmd_probe(int argc, const char **argv, const char *prefix __maybe_unused)
 		verbose = -1;
 	}
 
-	if (params.max_probe_points == 0)
-		params.max_probe_points = MAX_PROBES;
-
-	if ((!params.nevents && !params.dellist && !params.list_events &&
-	     !params.show_lines && !params.show_funcs))
-		usage_with_options(probe_usage, options);
+	if (probe_conf.max_probes == 0)
+		probe_conf.max_probes = MAX_PROBES;
 
 	/*
 	 * Only consider the user's kernel image path if given.
 	 */
 	symbol_conf.try_vmlinux_path = (symbol_conf.vmlinux_name == NULL);
 
-	if (params.list_events) {
+	switch (params.command) {
+	case 'l':
 		if (params.uprobes) {
 			pr_warning("  Error: Don't use --list with --exec.\n");
 			usage_with_options(probe_usage, options);
 		}
-		ret = show_perf_probe_events();
+		ret = show_perf_probe_events(params.filter);
 		if (ret < 0)
 			pr_err_with_code("  Error: Failed to show event list.", ret);
 		return ret;
-	}
-	if (params.show_funcs) {
-		if (!params.filter)
-			params.filter = strfilter__new(DEFAULT_FUNC_FILTER,
-						       NULL);
+	case 'F':
 		ret = show_available_funcs(params.target, params.filter,
 					params.uprobes);
-		strfilter__delete(params.filter);
-		params.filter = NULL;
 		if (ret < 0)
 			pr_err_with_code("  Error: Failed to show functions.", ret);
 		return ret;
-	}
-
 #ifdef HAVE_DWARF_SUPPORT
-	if (params.show_lines) {
+	case 'L':
 		ret = show_line_range(&params.line_range, params.target,
 				      params.uprobes);
 		if (ret < 0)
 			pr_err_with_code("  Error: Failed to show lines.", ret);
 		return ret;
-	}
-	if (params.show_vars) {
+	case 'V':
 		if (!params.filter)
 			params.filter = strfilter__new(DEFAULT_VAR_FILTER,
 						       NULL);
 
 		ret = show_available_vars(params.events, params.nevents,
-					  params.max_probe_points,
-					  params.target,
-					  params.filter,
-					  params.show_ext_vars);
-		strfilter__delete(params.filter);
-		params.filter = NULL;
+					  params.filter);
 		if (ret < 0)
 			pr_err_with_code("  Error: Failed to show vars.", ret);
 		return ret;
-	}
 #endif
-
-	if (params.dellist) {
-		ret = del_perf_probe_events(params.dellist);
+	case 'd':
+		ret = del_perf_probe_events(params.filter);
 		if (ret < 0) {
 			pr_err_with_code("  Error: Failed to delete events.", ret);
 			return ret;
 		}
-	}
-
-	if (params.nevents) {
+		break;
+	case 'a':
 		/* Ensure the last given target is used */
 		if (params.target && !params.target_used) {
 			pr_warning("  Error: -x/-m must follow the probe definitions.\n");
 			usage_with_options(probe_usage, options);
 		}
 
-		ret = add_perf_probe_events(params.events, params.nevents,
-					    params.max_probe_points,
-					    params.force_add);
+		ret = add_perf_probe_events(params.events, params.nevents);
 		if (ret < 0) {
 			pr_err_with_code("  Error: Failed to add events.", ret);
 			return ret;
 		}
+		break;
+	default:
+		usage_with_options(probe_usage, options);
 	}
 	return 0;
 }
@@ -522,5 +519,5 @@ int cmd_probe(int argc, const char **argv, const char *prefix)
 		cleanup_params();
 	}
 
-	return ret;
+	return ret < 0 ? ret : 0;
 }
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index c3efdfb630b5..de165a1b9240 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -27,6 +27,8 @@
 #include "util/cpumap.h"
 #include "util/thread_map.h"
 #include "util/data.h"
+#include "util/auxtrace.h"
+#include "util/parse-branch-options.h"
 
 #include <unistd.h>
 #include <sched.h>
@@ -38,6 +40,7 @@ struct record {
 	struct record_opts	opts;
 	u64			bytes_written;
 	struct perf_data_file	file;
+	struct auxtrace_record	*itr;
 	struct perf_evlist	*evlist;
 	struct perf_session	*session;
 	const char		*progname;
@@ -110,9 +113,12 @@ out:
 	return rc;
 }
 
-static volatile int done = 0;
+static volatile int done;
 static volatile int signr = -1;
-static volatile int child_finished = 0;
+static volatile int child_finished;
+static volatile int auxtrace_snapshot_enabled;
+static volatile int auxtrace_snapshot_err;
+static volatile int auxtrace_record__snapshot_started;
 
 static void sig_handler(int sig)
 {
@@ -133,6 +139,133 @@ static void record__sig_exit(void)
 	raise(signr);
 }
 
+#ifdef HAVE_AUXTRACE_SUPPORT
+
+static int record__process_auxtrace(struct perf_tool *tool,
+				    union perf_event *event, void *data1,
+				    size_t len1, void *data2, size_t len2)
+{
+	struct record *rec = container_of(tool, struct record, tool);
+	struct perf_data_file *file = &rec->file;
+	size_t padding;
+	u8 pad[8] = {0};
+
+	if (!perf_data_file__is_pipe(file)) {
+		off_t file_offset;
+		int fd = perf_data_file__fd(file);
+		int err;
+
+		file_offset = lseek(fd, 0, SEEK_CUR);
+		if (file_offset == -1)
+			return -1;
+		err = auxtrace_index__auxtrace_event(&rec->session->auxtrace_index,
+						     event, file_offset);
+		if (err)
+			return err;
+	}
+
+	/* event.auxtrace.size includes padding, see __auxtrace_mmap__read() */
+	padding = (len1 + len2) & 7;
+	if (padding)
+		padding = 8 - padding;
+
+	record__write(rec, event, event->header.size);
+	record__write(rec, data1, len1);
+	if (len2)
+		record__write(rec, data2, len2);
+	record__write(rec, &pad, padding);
+
+	return 0;
+}
+
+static int record__auxtrace_mmap_read(struct record *rec,
+				      struct auxtrace_mmap *mm)
+{
+	int ret;
+
+	ret = auxtrace_mmap__read(mm, rec->itr, &rec->tool,
+				  record__process_auxtrace);
+	if (ret < 0)
+		return ret;
+
+	if (ret)
+		rec->samples++;
+
+	return 0;
+}
+
+static int record__auxtrace_mmap_read_snapshot(struct record *rec,
+					       struct auxtrace_mmap *mm)
+{
+	int ret;
+
+	ret = auxtrace_mmap__read_snapshot(mm, rec->itr, &rec->tool,
+					   record__process_auxtrace,
+					   rec->opts.auxtrace_snapshot_size);
+	if (ret < 0)
+		return ret;
+
+	if (ret)
+		rec->samples++;
+
+	return 0;
+}
+
+static int record__auxtrace_read_snapshot_all(struct record *rec)
+{
+	int i;
+	int rc = 0;
+
+	for (i = 0; i < rec->evlist->nr_mmaps; i++) {
+		struct auxtrace_mmap *mm =
+				&rec->evlist->mmap[i].auxtrace_mmap;
+
+		if (!mm->base)
+			continue;
+
+		if (record__auxtrace_mmap_read_snapshot(rec, mm) != 0) {
+			rc = -1;
+			goto out;
+		}
+	}
+out:
+	return rc;
+}
+
+static void record__read_auxtrace_snapshot(struct record *rec)
+{
+	pr_debug("Recording AUX area tracing snapshot\n");
+	if (record__auxtrace_read_snapshot_all(rec) < 0) {
+		auxtrace_snapshot_err = -1;
+	} else {
+		auxtrace_snapshot_err = auxtrace_record__snapshot_finish(rec->itr);
+		if (!auxtrace_snapshot_err)
+			auxtrace_snapshot_enabled = 1;
+	}
+}
+
+#else
+
+static inline
+int record__auxtrace_mmap_read(struct record *rec __maybe_unused,
+			       struct auxtrace_mmap *mm __maybe_unused)
+{
+	return 0;
+}
+
+static inline
+void record__read_auxtrace_snapshot(struct record *rec __maybe_unused)
+{
+}
+
+static inline
+int auxtrace_record__snapshot_start(struct auxtrace_record *itr __maybe_unused)
+{
+	return 0;
+}
+
+#endif
+
 static int record__open(struct record *rec)
 {
 	char msg[512];
@@ -169,13 +302,16 @@ try_again:
 		goto out;
 	}
 
-	if (perf_evlist__mmap(evlist, opts->mmap_pages, false) < 0) {
+	if (perf_evlist__mmap_ex(evlist, opts->mmap_pages, false,
+				 opts->auxtrace_mmap_pages,
+				 opts->auxtrace_snapshot_mode) < 0) {
 		if (errno == EPERM) {
 			pr_err("Permission error mapping pages.\n"
 			       "Consider increasing "
 			       "/proc/sys/kernel/perf_event_mlock_kb,\n"
 			       "or try again with a smaller value of -m/--mmap_pages.\n"
-			       "(current value: %u)\n", opts->mmap_pages);
+			       "(current value: %u,%u)\n",
+			       opts->mmap_pages, opts->auxtrace_mmap_pages);
 			rc = -errno;
 		} else {
 			pr_err("failed to mmap with %d (%s)\n", errno,
@@ -209,12 +345,9 @@ static int process_buildids(struct record *rec)
 	struct perf_data_file *file  = &rec->file;
 	struct perf_session *session = rec->session;
 
-	u64 size = lseek(perf_data_file__fd(file), 0, SEEK_CUR);
-	if (size == 0)
+	if (file->size == 0)
 		return 0;
 
-	file->size = size;
-
 	/*
 	 * During this process, it'll load kernel map and replace the
 	 * dso->long_name to a real pathname it found.  In this case
@@ -270,12 +403,20 @@ static int record__mmap_read_all(struct record *rec)
 	int rc = 0;
 
 	for (i = 0; i < rec->evlist->nr_mmaps; i++) {
+		struct auxtrace_mmap *mm = &rec->evlist->mmap[i].auxtrace_mmap;
+
 		if (rec->evlist->mmap[i].base) {
 			if (record__mmap_read(rec, i) != 0) {
 				rc = -1;
 				goto out;
 			}
 		}
+
+		if (mm->base && !rec->opts.auxtrace_snapshot_mode &&
+		    record__auxtrace_mmap_read(rec, mm) != 0) {
+			rc = -1;
+			goto out;
+		}
 	}
 
 	/*
@@ -305,6 +446,9 @@ static void record__init_features(struct record *rec)
 
 	if (!rec->opts.branch_stack)
 		perf_header__clear_feat(&session->header, HEADER_BRANCH_STACK);
+
+	if (!rec->opts.full_auxtrace)
+		perf_header__clear_feat(&session->header, HEADER_AUXTRACE);
 }
 
 static volatile int workload_exec_errno;
@@ -323,6 +467,8 @@ static void workload_exec_failed_signal(int signo __maybe_unused,
 	child_finished = 1;
 }
 
+static void snapshot_sig_handler(int sig);
+
 static int __cmd_record(struct record *rec, int argc, const char **argv)
 {
 	int err;
@@ -343,6 +489,10 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 	signal(SIGCHLD, sig_handler);
 	signal(SIGINT, sig_handler);
 	signal(SIGTERM, sig_handler);
+	if (rec->opts.auxtrace_snapshot_mode)
+		signal(SIGUSR2, snapshot_sig_handler);
+	else
+		signal(SIGUSR2, SIG_IGN);
 
 	session = perf_session__new(file, false, tool);
 	if (session == NULL) {
@@ -421,6 +571,13 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 		}
 	}
 
+	if (rec->opts.full_auxtrace) {
+		err = perf_event__synthesize_auxtrace_info(rec->itr, tool,
+					session, process_synthesized_event);
+		if (err)
+			goto out_delete_session;
+	}
+
 	err = perf_event__synthesize_kernel_mmap(tool, process_synthesized_event,
 						 machine);
 	if (err < 0)
@@ -441,7 +598,8 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 	}
 
 	err = __machine__synthesize_threads(machine, tool, &opts->target, rec->evlist->threads,
-					    process_synthesized_event, opts->sample_address);
+					    process_synthesized_event, opts->sample_address,
+					    opts->proc_map_timeout);
 	if (err != 0)
 		goto out_child;
 
@@ -475,14 +633,27 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 		perf_evlist__enable(rec->evlist);
 	}
 
+	auxtrace_snapshot_enabled = 1;
 	for (;;) {
 		int hits = rec->samples;
 
 		if (record__mmap_read_all(rec) < 0) {
+			auxtrace_snapshot_enabled = 0;
 			err = -1;
 			goto out_child;
 		}
 
+		if (auxtrace_record__snapshot_started) {
+			auxtrace_record__snapshot_started = 0;
+			if (!auxtrace_snapshot_err)
+				record__read_auxtrace_snapshot(rec);
+			if (auxtrace_snapshot_err) {
+				pr_err("AUX area tracing snapshot failed\n");
+				err = -1;
+				goto out_child;
+			}
+		}
+
 		if (hits == rec->samples) {
 			if (done || draining)
 				break;
@@ -505,10 +676,12 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 		 * disable events in this case.
 		 */
 		if (done && !disabled && !target__none(&opts->target)) {
+			auxtrace_snapshot_enabled = 0;
 			perf_evlist__disable(rec->evlist);
 			disabled = true;
 		}
 	}
+	auxtrace_snapshot_enabled = 0;
 
 	if (forks && workload_exec_errno) {
 		char msg[STRERR_BUFSIZE];
@@ -544,16 +717,25 @@ out_child:
 
 	if (!err && !file->is_pipe) {
 		rec->session->header.data_size += rec->bytes_written;
+		file->size = lseek(perf_data_file__fd(file), 0, SEEK_CUR);
 
-		if (!rec->no_buildid)
+		if (!rec->no_buildid) {
 			process_buildids(rec);
+			/*
+			 * We take all buildids when the file contains
+			 * AUX area tracing data because we do not decode the
+			 * trace because it would take too long.
+			 */
+			if (rec->opts.full_auxtrace)
+				dsos__hit_all(rec->session);
+		}
 		perf_session__write_header(rec->session, rec->evlist, fd, true);
 	}
 
 	if (!err && !quiet) {
 		char samples[128];
 
-		if (rec->samples)
+		if (rec->samples && !rec->opts.full_auxtrace)
 			scnprintf(samples, sizeof(samples),
 				  " (%" PRIu64 " samples)", rec->samples);
 		else
@@ -569,94 +751,6 @@ out_delete_session:
 	return status;
 }
 
-#define BRANCH_OPT(n, m) \
-	{ .name = n, .mode = (m) }
-
-#define BRANCH_END { .name = NULL }
-
-struct branch_mode {
-	const char *name;
-	int mode;
-};
-
-static const struct branch_mode branch_modes[] = {
-	BRANCH_OPT("u", PERF_SAMPLE_BRANCH_USER),
-	BRANCH_OPT("k", PERF_SAMPLE_BRANCH_KERNEL),
-	BRANCH_OPT("hv", PERF_SAMPLE_BRANCH_HV),
-	BRANCH_OPT("any", PERF_SAMPLE_BRANCH_ANY),
-	BRANCH_OPT("any_call", PERF_SAMPLE_BRANCH_ANY_CALL),
-	BRANCH_OPT("any_ret", PERF_SAMPLE_BRANCH_ANY_RETURN),
-	BRANCH_OPT("ind_call", PERF_SAMPLE_BRANCH_IND_CALL),
-	BRANCH_OPT("abort_tx", PERF_SAMPLE_BRANCH_ABORT_TX),
-	BRANCH_OPT("in_tx", PERF_SAMPLE_BRANCH_IN_TX),
-	BRANCH_OPT("no_tx", PERF_SAMPLE_BRANCH_NO_TX),
-	BRANCH_OPT("cond", PERF_SAMPLE_BRANCH_COND),
-	BRANCH_END
-};
-
-static int
-parse_branch_stack(const struct option *opt, const char *str, int unset)
-{
-#define ONLY_PLM \
-	(PERF_SAMPLE_BRANCH_USER	|\
-	 PERF_SAMPLE_BRANCH_KERNEL	|\
-	 PERF_SAMPLE_BRANCH_HV)
-
-	uint64_t *mode = (uint64_t *)opt->value;
-	const struct branch_mode *br;
-	char *s, *os = NULL, *p;
-	int ret = -1;
-
-	if (unset)
-		return 0;
-
-	/*
-	 * cannot set it twice, -b + --branch-filter for instance
-	 */
-	if (*mode)
-		return -1;
-
-	/* str may be NULL in case no arg is passed to -b */
-	if (str) {
-		/* because str is read-only */
-		s = os = strdup(str);
-		if (!s)
-			return -1;
-
-		for (;;) {
-			p = strchr(s, ',');
-			if (p)
-				*p = '\0';
-
-			for (br = branch_modes; br->name; br++) {
-				if (!strcasecmp(s, br->name))
-					break;
-			}
-			if (!br->name) {
-				ui__warning("unknown branch filter %s,"
-					    " check man page\n", s);
-				goto error;
-			}
-
-			*mode |= br->mode;
-
-			if (!p)
-				break;
-
-			s = p + 1;
-		}
-	}
-	ret = 0;
-
-	/* default to any branch */
-	if ((*mode & ~ONLY_PLM) == 0) {
-		*mode = PERF_SAMPLE_BRANCH_ANY;
-	}
-error:
-	free(os);
-	return ret;
-}
-
 static void callchain_debug(void)
 {
 	static const char *str[CALLCHAIN_MAX] = { "NONE", "FP", "DWARF", "LBR" };
@@ -795,6 +889,49 @@ static int parse_clockid(const struct option *opt, const char *str, int unset)
 	return -1;
 }
 
+static int record__parse_mmap_pages(const struct option *opt,
+				    const char *str,
+				    int unset __maybe_unused)
+{
+	struct record_opts *opts = opt->value;
+	char *s, *p;
+	unsigned int mmap_pages;
+	int ret;
+
+	if (!str)
+		return -EINVAL;
+
+	s = strdup(str);
+	if (!s)
+		return -ENOMEM;
+
+	p = strchr(s, ',');
+	if (p)
+		*p = '\0';
+
+	if (*s) {
+		ret = __perf_evlist__parse_mmap_pages(&mmap_pages, s);
+		if (ret)
+			goto out_free;
+		opts->mmap_pages = mmap_pages;
+	}
+
+	if (!p) {
+		ret = 0;
+		goto out_free;
+	}
+
+	ret = __perf_evlist__parse_mmap_pages(&mmap_pages, p + 1);
+	if (ret)
+		goto out_free;
+
+	opts->auxtrace_mmap_pages = mmap_pages;
+
+out_free:
+	free(s);
+	return ret;
+}
+
 static const char * const __record_usage[] = {
 	"perf record [<options>] [<command>]",
 	"perf record [<options>] -- <command> [<options>]",
@@ -823,6 +960,7 @@ static struct record record = {
 			.uses_mmap   = true,
 			.default_per_cpu = true,
 		},
+		.proc_map_timeout     = 500,
 	},
 	.tool = {
 		.sample		= process_sample_event,
@@ -875,9 +1013,9 @@ struct option __record_options[] = {
 			&record.opts.no_inherit_set,
 			"child tasks do not inherit counters"),
 	OPT_UINTEGER('F', "freq", &record.opts.user_freq, "profile at this frequency"),
-	OPT_CALLBACK('m', "mmap-pages", &record.opts.mmap_pages, "pages",
-		     "number of mmap data pages",
-		     perf_evlist__parse_mmap_pages),
+	OPT_CALLBACK('m', "mmap-pages", &record.opts, "pages[,pages]",
+		     "number of mmap data pages and AUX area tracing mmap pages",
+		     record__parse_mmap_pages),
 	OPT_BOOLEAN(0, "group", &record.opts.group,
 		    "put the counters into a counter group"),
 	OPT_CALLBACK_NOOPT('g', NULL, &record.opts,
@@ -891,10 +1029,9 @@ struct option __record_options[] = {
 	OPT_BOOLEAN('q', "quiet", &quiet, "don't print any message"),
 	OPT_BOOLEAN('s', "stat", &record.opts.inherit_stat,
 		    "per thread counts"),
-	OPT_BOOLEAN('d', "data", &record.opts.sample_address,
-		    "Sample addresses"),
-	OPT_BOOLEAN('T', "timestamp", &record.opts.sample_time, "Sample timestamps"),
-	OPT_BOOLEAN('P', "period", &record.opts.period, "Sample period"),
+	OPT_BOOLEAN('d', "data", &record.opts.sample_address, "Record the sample addresses"),
+	OPT_BOOLEAN('T', "timestamp", &record.opts.sample_time, "Record the sample timestamps"),
+	OPT_BOOLEAN('P', "period", &record.opts.period, "Record the sample period"),
 	OPT_BOOLEAN('n', "no-samples", &record.opts.no_samples,
 		    "don't sample"),
 	OPT_BOOLEAN('N', "no-buildid-cache", &record.no_buildid_cache,
@@ -929,6 +1066,10 @@ struct option __record_options[] = {
 	OPT_CALLBACK('k', "clockid", &record.opts,
 	"clockid", "clockid to use for events, see clock_gettime()",
 	parse_clockid),
+	OPT_STRING_OPTARG('S', "snapshot", &record.opts.auxtrace_snapshot_opts,
+			  "opts", "AUX area tracing Snapshot Mode", ""),
+	OPT_UINTEGER(0, "proc-map-timeout", &record.opts.proc_map_timeout,
+			"per thread proc mmap processing timeout in ms"),
 	OPT_END()
 };
 
@@ -936,7 +1077,7 @@ struct option *record_options = __record_options;
 
 int cmd_record(int argc, const char **argv, const char *prefix __maybe_unused)
 {
-	int err = -ENOMEM;
+	int err;
 	struct record *rec = &record;
 	char errbuf[BUFSIZ];
 
@@ -957,6 +1098,19 @@ int cmd_record(int argc, const char **argv, const char *prefix __maybe_unused)
 		usage_with_options(record_usage, record_options);
 	}
 
+	if (!rec->itr) {
+		rec->itr = auxtrace_record__init(rec->evlist, &err);
+		if (err)
+			return err;
+	}
+
+	err = auxtrace_parse_snapshot_options(rec->itr, &rec->opts,
+					      rec->opts.auxtrace_snapshot_opts);
+	if (err)
+		return err;
+
+	err = -ENOMEM;
+
 	symbol__init(NULL);
 
 	if (symbol_conf.kptr_restrict)
@@ -1002,6 +1156,10 @@ int cmd_record(int argc, const char **argv, const char *prefix __maybe_unused)
 	if (perf_evlist__create_maps(rec->evlist, &rec->opts.target) < 0)
 		usage_with_options(record_usage, record_options);
 
+	err = auxtrace_record__options(rec->itr, rec->evlist, &rec->opts);
+	if (err)
+		goto out_symbol_exit;
+
 	if (record_opts__config(&rec->opts)) {
 		err = -EINVAL;
 		goto out_symbol_exit;
@@ -1011,5 +1169,15 @@ int cmd_record(int argc, const char **argv, const char *prefix __maybe_unused)
 out_symbol_exit:
 	perf_evlist__delete(rec->evlist);
 	symbol__exit();
+	auxtrace_record__free(rec->itr);
 	return err;
 }
+
+static void snapshot_sig_handler(int sig __maybe_unused)
+{
+	if (!auxtrace_snapshot_enabled)
+		return;
+	auxtrace_snapshot_enabled = 0;
+	auxtrace_snapshot_err = auxtrace_record__snapshot_start(record.itr);
+	auxtrace_record__snapshot_started = 1;
+}
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index b63aeda719be..32626ea3e227 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -36,6 +36,8 @@
 #include "util/data.h"
 #include "arch/common.h"
 
+#include "util/auxtrace.h"
+
 #include <dlfcn.h>
 #include <linux/bitmap.h>
 
@@ -137,10 +139,12 @@ static int process_sample_event(struct perf_tool *tool,
 	struct report *rep = container_of(tool, struct report, tool);
 	struct addr_location al;
 	struct hist_entry_iter iter = {
-		.hide_unresolved = rep->hide_unresolved,
-		.add_entry_cb = hist_iter__report_callback,
+		.evsel 			= evsel,
+		.sample 		= sample,
+		.hide_unresolved 	= rep->hide_unresolved,
+		.add_entry_cb 		= hist_iter__report_callback,
 	};
-	int ret;
+	int ret = 0;
 
 	if (perf_event__preprocess_sample(event, machine, &al, sample) < 0) {
 		pr_debug("problem processing %d event, skipping it.\n",
@@ -149,10 +153,10 @@ static int process_sample_event(struct perf_tool *tool,
 	}
 
 	if (rep->hide_unresolved && al.sym == NULL)
-		return 0;
+		goto out_put;
 
 	if (rep->cpu_list && !test_bit(sample->cpu, rep->cpu_bitmap))
-		return 0;
+		goto out_put;
 
 	if (sort__mode == SORT_MODE__BRANCH)
 		iter.ops = &hist_iter_branch;
@@ -166,11 +170,11 @@ static int process_sample_event(struct perf_tool *tool,
 	if (al.map != NULL)
 		al.map->dso->hit = 1;
 
-	ret = hist_entry_iter__add(&iter, &al, evsel, sample, rep->max_stack,
-				   rep);
+	ret = hist_entry_iter__add(&iter, &al, rep->max_stack, rep);
 	if (ret < 0)
 		pr_debug("problem adding hist entry, skipping event\n");
-
+out_put:
+	addr_location__put(&al);
 	return ret;
 }
 
@@ -316,6 +320,7 @@ static int perf_evlist__tty_browse_hists(struct perf_evlist *evlist,
 {
 	struct perf_evsel *pos;
 
+	fprintf(stdout, "#\n# Total Lost Samples: %" PRIu64 "\n#\n", evlist->stats.total_lost_samples);
 	evlist__for_each(evlist, pos) {
 		struct hists *hists = evsel__hists(pos);
 		const char *evname = perf_evsel__name(pos);
@@ -330,15 +335,14 @@ static int perf_evlist__tty_browse_hists(struct perf_evlist *evlist,
 	}
 
 	if (sort_order == NULL &&
-	    parent_pattern == default_parent_pattern) {
+	    parent_pattern == default_parent_pattern)
 		fprintf(stdout, "#\n# (%s)\n#\n", help);
 
-		if (rep->show_threads) {
-			bool style = !strcmp(rep->pretty_printing_style, "raw");
-			perf_read_values_display(stdout, &rep->show_threads_values,
-						 style);
-			perf_read_values_destroy(&rep->show_threads_values);
-		}
+	if (rep->show_threads) {
+		bool style = !strcmp(rep->pretty_printing_style, "raw");
+		perf_read_values_display(stdout, &rep->show_threads_values,
+					 style);
+		perf_read_values_destroy(&rep->show_threads_values);
 	}
 
 	return 0;
@@ -585,6 +589,7 @@ parse_percent_limit(const struct option *opt, const char *str,
 int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
 {
 	struct perf_session *session;
+	struct itrace_synth_opts itrace_synth_opts = { .set = 0, };
 	struct stat st;
 	bool has_br_stack = false;
 	int branch_mode = -1;
@@ -607,6 +612,9 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
 			.attr		 = perf_event__process_attr,
 			.tracing_data	 = perf_event__process_tracing_data,
 			.build_id	 = perf_event__process_build_id,
+			.id_index	 = perf_event__process_id_index,
+			.auxtrace_info	 = perf_event__process_auxtrace_info,
+			.auxtrace	 = perf_event__process_auxtrace,
 			.ordered_events	 = true,
 			.ordering_requires_timestamps = true,
 		},
@@ -717,6 +725,9 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
 		     "Don't show entries under that percent", parse_percent_limit),
 	OPT_CALLBACK(0, "percentage", NULL, "relative|absolute",
 		     "how to display percentage of filtered entries", parse_filter_percentage),
+	OPT_CALLBACK_OPTARG(0, "itrace", &itrace_synth_opts, NULL, "opts",
+			    "Instruction Tracing options",
+			    itrace_parse_synth_opts),
 	OPT_END()
 	};
 	struct perf_data_file file = {
@@ -761,6 +772,8 @@ repeat:
 					       report.queue_size);
 	}
 
+	session->itrace_synth_opts = &itrace_synth_opts;
+
 	report.session = session;
 
 	has_br_stack = perf_header__has_feat(&session->header,
@@ -803,8 +816,8 @@ repeat:
 		goto error;
 	}
 
-	/* Force tty output for header output. */
-	if (report.header || report.header_only)
+	/* Force tty output for header output and per-thread stat. */
+	if (report.header || report.header_only || report.show_threads)
 		use_browser = 0;
 
 	if (strcmp(input_name, "-") != 0)
diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c
index 5275bab70313..33962612a5e9 100644
--- a/tools/perf/builtin-sched.c
+++ b/tools/perf/builtin-sched.c
@@ -95,6 +95,7 @@ struct work_atoms {
 	u64			total_lat;
 	u64			nb_atoms;
 	u64			total_runtime;
+	int			num_merged;
 };
 
 typedef int (*sort_fn_t)(struct work_atoms *, struct work_atoms *);
@@ -168,9 +169,10 @@ struct perf_sched {
 	u64		 all_runtime;
 	u64		 all_count;
 	u64		 cpu_last_switched[MAX_CPUS];
-	struct rb_root	 atom_root, sorted_atom_root;
+	struct rb_root	 atom_root, sorted_atom_root, merged_atom_root;
 	struct list_head sort_list, cmp_pid;
 	bool force;
+	bool skip_merge;
 };
 
 static u64 get_nsecs(void)
@@ -770,7 +772,7 @@ static int replay_fork_event(struct perf_sched *sched,
 	if (child == NULL || parent == NULL) {
 		pr_debug("thread does not exist on fork event: child %p, parent %p\n",
 				 child, parent);
-		return 0;
+		goto out_put;
 	}
 
 	if (verbose) {
@@ -781,6 +783,9 @@ static int replay_fork_event(struct perf_sched *sched,
 
 	register_pid(sched, parent->tid, thread__comm_str(parent));
 	register_pid(sched, child->tid, thread__comm_str(child));
+out_put:
+	thread__put(child);
+	thread__put(parent);
 	return 0;
 }
 
@@ -957,7 +962,7 @@ static int latency_switch_event(struct perf_sched *sched,
 	struct work_atoms *out_events, *in_events;
 	struct thread *sched_out, *sched_in;
 	u64 timestamp0, timestamp = sample->time;
-	int cpu = sample->cpu;
+	int cpu = sample->cpu, err = -1;
 	s64 delta;
 
 	BUG_ON(cpu >= MAX_CPUS || cpu < 0);
@@ -976,15 +981,17 @@ static int latency_switch_event(struct perf_sched *sched,
 
 	sched_out = machine__findnew_thread(machine, -1, prev_pid);
 	sched_in = machine__findnew_thread(machine, -1, next_pid);
+	if (sched_out == NULL || sched_in == NULL)
+		goto out_put;
 
 	out_events = thread_atoms_search(&sched->atom_root, sched_out, &sched->cmp_pid);
 	if (!out_events) {
 		if (thread_atoms_insert(sched, sched_out))
-			return -1;
+			goto out_put;
 		out_events = thread_atoms_search(&sched->atom_root, sched_out, &sched->cmp_pid);
 		if (!out_events) {
 			pr_err("out-event: Internal tree error");
-			return -1;
+			goto out_put;
 		}
 	}
 	if (add_sched_out_event(out_events, sched_out_state(prev_state), timestamp))
@@ -993,22 +1000,25 @@ static int latency_switch_event(struct perf_sched *sched,
 	in_events = thread_atoms_search(&sched->atom_root, sched_in, &sched->cmp_pid);
 	if (!in_events) {
 		if (thread_atoms_insert(sched, sched_in))
-			return -1;
+			goto out_put;
 		in_events = thread_atoms_search(&sched->atom_root, sched_in, &sched->cmp_pid);
 		if (!in_events) {
 			pr_err("in-event: Internal tree error");
-			return -1;
+			goto out_put;
 		}
 		/*
 		 * Take came in we have not heard about yet,
 		 * add in an initial atom in runnable state:
 		 */
 		if (add_sched_out_event(in_events, 'R', timestamp))
-			return -1;
+			goto out_put;
 	}
 	add_sched_in_event(in_events, timestamp);
-
-	return 0;
+	err = 0;
+out_put:
+	thread__put(sched_out);
+	thread__put(sched_in);
+	return err;
 }
 
 static int latency_runtime_event(struct perf_sched *sched,
@@ -1021,23 +1031,29 @@ static int latency_runtime_event(struct perf_sched *sched,
 	struct thread *thread = machine__findnew_thread(machine, -1, pid);
 	struct work_atoms *atoms = thread_atoms_search(&sched->atom_root, thread, &sched->cmp_pid);
 	u64 timestamp = sample->time;
-	int cpu = sample->cpu;
+	int cpu = sample->cpu, err = -1;
+
+	if (thread == NULL)
+		return -1;
 
 	BUG_ON(cpu >= MAX_CPUS || cpu < 0);
 	if (!atoms) {
 		if (thread_atoms_insert(sched, thread))
-			return -1;
+			goto out_put;
 		atoms = thread_atoms_search(&sched->atom_root, thread, &sched->cmp_pid);
 		if (!atoms) {
 			pr_err("in-event: Internal tree error");
-			return -1;
+			goto out_put;
 		}
 		if (add_sched_out_event(atoms, 'R', timestamp))
-			return -1;
+			goto out_put;
 	}
 
 	add_runtime_event(atoms, runtime, timestamp);
-	return 0;
+	err = 0;
+out_put:
+	thread__put(thread);
+	return err;
 }
 
 static int latency_wakeup_event(struct perf_sched *sched,
@@ -1050,19 +1066,22 @@ static int latency_wakeup_event(struct perf_sched *sched,
 	struct work_atom *atom;
 	struct thread *wakee;
 	u64 timestamp = sample->time;
+	int err = -1;
 
 	wakee = machine__findnew_thread(machine, -1, pid);
+	if (wakee == NULL)
+		return -1;
 	atoms = thread_atoms_search(&sched->atom_root, wakee, &sched->cmp_pid);
 	if (!atoms) {
 		if (thread_atoms_insert(sched, wakee))
-			return -1;
+			goto out_put;
 		atoms = thread_atoms_search(&sched->atom_root, wakee, &sched->cmp_pid);
 		if (!atoms) {
 			pr_err("wakeup-event: Internal tree error");
-			return -1;
+			goto out_put;
 		}
 		if (add_sched_out_event(atoms, 'S', timestamp))
-			return -1;
+			goto out_put;
 	}
 
 	BUG_ON(list_empty(&atoms->work_list));
@@ -1081,17 +1100,21 @@ static int latency_wakeup_event(struct perf_sched *sched,
 	 * skip in this case.
 	 */
 	if (sched->profile_cpu == -1 && atom->state != THREAD_SLEEPING)
-		return 0;
+		goto out_ok;
 
 	sched->nr_timestamps++;
 	if (atom->sched_out_time > timestamp) {
 		sched->nr_unordered_timestamps++;
-		return 0;
+		goto out_ok;
 	}
 
 	atom->state = THREAD_WAIT_CPU;
 	atom->wake_up_time = timestamp;
-	return 0;
+out_ok:
+	err = 0;
+out_put:
+	thread__put(wakee);
+	return err;
 }
 
 static int latency_migrate_task_event(struct perf_sched *sched,
@@ -1104,6 +1127,7 @@ static int latency_migrate_task_event(struct perf_sched *sched,
 	struct work_atoms *atoms;
 	struct work_atom *atom;
 	struct thread *migrant;
+	int err = -1;
 
 	/*
 	 * Only need to worry about migration when profiling one CPU.
@@ -1112,18 +1136,20 @@ static int latency_migrate_task_event(struct perf_sched *sched,
 		return 0;
 
 	migrant = machine__findnew_thread(machine, -1, pid);
+	if (migrant == NULL)
+		return -1;
 	atoms = thread_atoms_search(&sched->atom_root, migrant, &sched->cmp_pid);
 	if (!atoms) {
 		if (thread_atoms_insert(sched, migrant))
-			return -1;
+			goto out_put;
 		register_pid(sched, migrant->tid, thread__comm_str(migrant));
 		atoms = thread_atoms_search(&sched->atom_root, migrant, &sched->cmp_pid);
 		if (!atoms) {
 			pr_err("migration-event: Internal tree error");
-			return -1;
+			goto out_put;
 		}
 		if (add_sched_out_event(atoms, 'R', timestamp))
-			return -1;
+			goto out_put;
 	}
 
 	BUG_ON(list_empty(&atoms->work_list));
@@ -1135,8 +1161,10 @@ static int latency_migrate_task_event(struct perf_sched *sched,
 
 	if (atom->sched_out_time > timestamp)
 		sched->nr_unordered_timestamps++;
-
-	return 0;
+	err = 0;
+out_put:
+	thread__put(migrant);
+	return err;
 }
 
 static void output_lat_thread(struct perf_sched *sched, struct work_atoms *work_list)
@@ -1156,7 +1184,10 @@ static void output_lat_thread(struct perf_sched *sched, struct work_atoms *work_
 	sched->all_runtime += work_list->total_runtime;
 	sched->all_count   += work_list->nb_atoms;
 
-	ret = printf("  %s:%d ", thread__comm_str(work_list->thread), work_list->thread->tid);
+	if (work_list->num_merged > 1)
+		ret = printf("  %s:(%d) ", thread__comm_str(work_list->thread), work_list->num_merged);
+	else
+		ret = printf("  %s:%d ", thread__comm_str(work_list->thread), work_list->thread->tid);
 
 	for (i = 0; i < 24 - ret; i++)
 		printf(" ");
@@ -1276,17 +1307,22 @@ static int sort_dimension__add(const char *tok, struct list_head *list)
 static void perf_sched__sort_lat(struct perf_sched *sched)
 {
 	struct rb_node *node;
-
+	struct rb_root *root = &sched->atom_root;
+again:
 	for (;;) {
 		struct work_atoms *data;
-		node = rb_first(&sched->atom_root);
+		node = rb_first(root);
 		if (!node)
 			break;
 
-		rb_erase(node, &sched->atom_root);
+		rb_erase(node, root);
 		data = rb_entry(node, struct work_atoms, node);
 		__thread_latency_insert(&sched->sorted_atom_root, data, &sched->sort_list);
 	}
+	if (root == &sched->atom_root) {
+		root = &sched->merged_atom_root;
+		goto again;
+	}
 }
 
 static int process_sched_wakeup_event(struct perf_tool *tool,
@@ -1330,8 +1366,10 @@ static int map_switch_event(struct perf_sched *sched, struct perf_evsel *evsel,
 	}
 
 	sched_in = machine__findnew_thread(machine, -1, next_pid);
+	if (sched_in == NULL)
+		return -1;
 
-	sched->curr_thread[this_cpu] = sched_in;
+	sched->curr_thread[this_cpu] = thread__get(sched_in);
 
 	printf("  ");
 
@@ -1381,6 +1419,8 @@ static int map_switch_event(struct perf_sched *sched, struct perf_evsel *evsel,
 		printf("\n");
 	}
 
+	thread__put(sched_in);
+
 	return 0;
 }
 
@@ -1542,6 +1582,59 @@ static void print_bad_events(struct perf_sched *sched)
 	}
 }
 
+static void __merge_work_atoms(struct rb_root *root, struct work_atoms *data)
+{
+	struct rb_node **new = &(root->rb_node), *parent = NULL;
+	struct work_atoms *this;
+	const char *comm = thread__comm_str(data->thread), *this_comm;
+
+	while (*new) {
+		int cmp;
+
+		this = container_of(*new, struct work_atoms, node);
+		parent = *new;
+
+		this_comm = thread__comm_str(this->thread);
+		cmp = strcmp(comm, this_comm);
+		if (cmp > 0) {
+			new = &((*new)->rb_left);
+		} else if (cmp < 0) {
+			new = &((*new)->rb_right);
+		} else {
+			this->num_merged++;
+			this->total_runtime += data->total_runtime;
+			this->nb_atoms += data->nb_atoms;
+			this->total_lat += data->total_lat;
+			list_splice(&data->work_list, &this->work_list);
+			if (this->max_lat < data->max_lat) {
+				this->max_lat = data->max_lat;
+				this->max_lat_at = data->max_lat_at;
+			}
+			zfree(&data);
+			return;
+		}
+	}
+
+	data->num_merged++;
+	rb_link_node(&data->node, parent, new);
+	rb_insert_color(&data->node, root);
+}
+
+static void perf_sched__merge_lat(struct perf_sched *sched)
+{
+	struct work_atoms *data;
+	struct rb_node *node;
+
+	if (sched->skip_merge)
+		return;
+
+	while ((node = rb_first(&sched->atom_root))) {
+		rb_erase(node, &sched->atom_root);
+		data = rb_entry(node, struct work_atoms, node);
+		__merge_work_atoms(&sched->merged_atom_root, data);
+	}
+}
+
 static int perf_sched__lat(struct perf_sched *sched)
 {
 	struct rb_node *next;
@@ -1551,6 +1644,7 @@ static int perf_sched__lat(struct perf_sched *sched)
 	if (perf_sched__read_events(sched))
 		return -1;
 
+	perf_sched__merge_lat(sched);
 	perf_sched__sort_lat(sched);
 
 	printf("\n -----------------------------------------------------------------------------------------------------------------\n");
@@ -1702,6 +1796,7 @@ int cmd_sched(int argc, const char **argv, const char *prefix __maybe_unused)
 		.profile_cpu	      = -1,
 		.next_shortname1      = 'A',
 		.next_shortname2      = '0',
+		.skip_merge           = 0,
 	};
 	const struct option latency_options[] = {
 	OPT_STRING('s', "sort", &sched.sort_order, "key[,key2...]",
@@ -1712,6 +1807,8 @@ int cmd_sched(int argc, const char **argv, const char *prefix __maybe_unused)
 		    "CPU to profile on"),
 	OPT_BOOLEAN('D', "dump-raw-trace", &dump_trace,
 		    "dump raw trace in ASCII"),
+	OPT_BOOLEAN('p', "pids", &sched.skip_merge,
+		    "latency stats per pid instead of per comm"),
 	OPT_END()
 	};
 	const struct option replay_options[] = {
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 58f10b8e6ff2..24809787369f 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -16,6 +16,7 @@
 #include "util/evsel.h"
 #include "util/sort.h"
 #include "util/data.h"
+#include "util/auxtrace.h"
 #include <linux/bitmap.h>
 
 static char const		*script_name;
@@ -26,6 +27,7 @@ static u64			nr_unordered;
 static bool			no_callchain;
 static bool			latency_format;
 static bool			system_wide;
+static bool			print_flags;
 static const char		*cpu_list;
 static DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS);
 
@@ -146,9 +148,10 @@ static const char *output_field2str(enum perf_output_field field)
 
 #define PRINT_FIELD(x)  (output[attr->type].fields & PERF_OUTPUT_##x)
 
-static int perf_evsel__check_stype(struct perf_evsel *evsel,
-				   u64 sample_type, const char *sample_msg,
-				   enum perf_output_field field)
+static int perf_evsel__do_check_stype(struct perf_evsel *evsel,
+				      u64 sample_type, const char *sample_msg,
+				      enum perf_output_field field,
+				      bool allow_user_set)
 {
 	struct perf_event_attr *attr = &evsel->attr;
 	int type = attr->type;
@@ -158,6 +161,8 @@ static int perf_evsel__check_stype(struct perf_evsel *evsel,
 		return 0;
 
 	if (output[type].user_set) {
+		if (allow_user_set)
+			return 0;
 		evname = perf_evsel__name(evsel);
 		pr_err("Samples for '%s' event do not have %s attribute set. "
 		       "Cannot print '%s' field.\n",
@@ -175,10 +180,22 @@ static int perf_evsel__check_stype(struct perf_evsel *evsel,
 	return 0;
 }
 
+static int perf_evsel__check_stype(struct perf_evsel *evsel,
+				   u64 sample_type, const char *sample_msg,
+				   enum perf_output_field field)
+{
+	return perf_evsel__do_check_stype(evsel, sample_type, sample_msg, field,
+					  false);
+}
+
 static int perf_evsel__check_attr(struct perf_evsel *evsel,
 				  struct perf_session *session)
 {
 	struct perf_event_attr *attr = &evsel->attr;
+	bool allow_user_set;
+
+	allow_user_set = perf_header__has_feat(&session->header,
+					       HEADER_AUXTRACE);
 
 	if (PRINT_FIELD(TRACE) &&
 		!perf_session__has_traces(session, "record -R"))
@@ -191,8 +208,8 @@ static int perf_evsel__check_attr(struct perf_evsel *evsel,
 	}
 
 	if (PRINT_FIELD(ADDR) &&
-		perf_evsel__check_stype(evsel, PERF_SAMPLE_ADDR, "ADDR",
-					PERF_OUTPUT_ADDR))
+		perf_evsel__do_check_stype(evsel, PERF_SAMPLE_ADDR, "ADDR",
+					   PERF_OUTPUT_ADDR, allow_user_set))
 		return -EINVAL;
 
 	if (PRINT_FIELD(SYM) && !PRINT_FIELD(IP) && !PRINT_FIELD(ADDR)) {
@@ -229,8 +246,8 @@ static int perf_evsel__check_attr(struct perf_evsel *evsel,
 		return -EINVAL;
 
 	if (PRINT_FIELD(CPU) &&
-		perf_evsel__check_stype(evsel, PERF_SAMPLE_CPU, "CPU",
-					PERF_OUTPUT_CPU))
+		perf_evsel__do_check_stype(evsel, PERF_SAMPLE_CPU, "CPU",
+					   PERF_OUTPUT_CPU, allow_user_set))
 		return -EINVAL;
 
 	if (PRINT_FIELD(PERIOD) &&
@@ -445,6 +462,25 @@ static void print_sample_bts(union perf_event *event,
 	printf("\n");
 }
 
+static void print_sample_flags(u32 flags)
+{
+	const char *chars = PERF_IP_FLAG_CHARS;
+	const int n = strlen(PERF_IP_FLAG_CHARS);
+	char str[33];
+	int i, pos = 0;
+
+	for (i = 0; i < n; i++, flags >>= 1) {
+		if (flags & 1)
+			str[pos++] = chars[i];
+	}
+	for (; i < 32; i++, flags >>= 1) {
+		if (flags & 1)
+			str[pos++] = '?';
+	}
+	str[pos] = 0;
+	printf("  %-4s ", str);
+}
+
 static void process_event(union perf_event *event, struct perf_sample *sample,
 			  struct perf_evsel *evsel, struct addr_location *al)
 {
@@ -464,6 +500,9 @@ static void process_event(union perf_event *event, struct perf_sample *sample,
 		printf("%s: ", evname ? evname : "[unknown]");
 	}
 
+	if (print_flags)
+		print_sample_flags(sample->flags);
+
 	if (is_bts_event(attr)) {
 		print_sample_bts(event, sample, evsel, thread, al);
 		return;
@@ -568,13 +607,14 @@ static int process_sample_event(struct perf_tool *tool __maybe_unused,
 	}
 
 	if (al.filtered)
-		return 0;
+		goto out_put;
 
 	if (cpu_list && !test_bit(sample->cpu, cpu_bitmap))
-		return 0;
+		goto out_put;
 
 	scripting_ops->process_event(event, sample, evsel, &al);
-
+out_put:
+	addr_location__put(&al);
 	return 0;
 }
 
@@ -642,8 +682,8 @@ static int process_comm_event(struct perf_tool *tool,
 	print_sample_start(sample, thread, evsel);
 	perf_event__fprintf(event, stdout);
 	ret = 0;
-
 out:
+	thread__put(thread);
 	return ret;
 }
 
@@ -674,6 +714,7 @@ static int process_fork_event(struct perf_tool *tool,
 	}
 	print_sample_start(sample, thread, evsel);
 	perf_event__fprintf(event, stdout);
+	thread__put(thread);
 
 	return 0;
 }
@@ -682,6 +723,7 @@ static int process_exit_event(struct perf_tool *tool,
 			      struct perf_sample *sample,
 			      struct machine *machine)
 {
+	int err = 0;
 	struct thread *thread;
 	struct perf_script *script = container_of(tool, struct perf_script, tool);
 	struct perf_session *session = script->session;
@@ -703,9 +745,10 @@ static int process_exit_event(struct perf_tool *tool,
 	perf_event__fprintf(event, stdout);
 
 	if (perf_event__process_exit(tool, event, sample, machine) < 0)
-		return -1;
+		err = -1;
 
-	return 0;
+	thread__put(thread);
+	return err;
 }
 
 static int process_mmap_event(struct perf_tool *tool,
@@ -735,7 +778,7 @@ static int process_mmap_event(struct perf_tool *tool,
 	}
 	print_sample_start(sample, thread, evsel);
 	perf_event__fprintf(event, stdout);
-
+	thread__put(thread);
 	return 0;
 }
 
@@ -766,7 +809,7 @@ static int process_mmap2_event(struct perf_tool *tool,
 	}
 	print_sample_start(sample, thread, evsel);
 	perf_event__fprintf(event, stdout);
-
+	thread__put(thread);
 	return 0;
 }
 
@@ -999,12 +1042,15 @@ static int parse_output_fields(const struct option *opt __maybe_unused,
 		}
 	}
 
-	tok = strtok(tok, ",");
-	while (tok) {
+	for (tok = strtok(tok, ","); tok; tok = strtok(NULL, ",")) {
 		for (i = 0; i < imax; ++i) {
 			if (strcmp(tok, all_output_options[i].str) == 0)
 				break;
 		}
+		if (i == imax && strcmp(tok, "flags") == 0) {
+			print_flags = true;
+			continue;
+		}
 		if (i == imax) {
 			fprintf(stderr, "Invalid field requested.\n");
 			rc = -EINVAL;
@@ -1032,8 +1078,6 @@ static int parse_output_fields(const struct option *opt __maybe_unused,
 			}
 			output[type].fields |= all_output_options[i].field;
 		}
-
-		tok = strtok(NULL, ",");
 	}
 
 	if (type >= 0) {
@@ -1497,6 +1541,7 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused)
 	char *rec_script_path = NULL;
 	char *rep_script_path = NULL;
 	struct perf_session *session;
+	struct itrace_synth_opts itrace_synth_opts = { .set = false, };
 	char *script_path = NULL;
 	const char **__argv;
 	int i, j, err = 0;
@@ -1511,6 +1556,10 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused)
 			.attr		 = process_attr,
 			.tracing_data	 = perf_event__process_tracing_data,
 			.build_id	 = perf_event__process_build_id,
+			.id_index	 = perf_event__process_id_index,
+			.auxtrace_info	 = perf_event__process_auxtrace_info,
+			.auxtrace	 = perf_event__process_auxtrace,
+			.auxtrace_error	 = perf_event__process_auxtrace_error,
 			.ordered_events	 = true,
 			.ordering_requires_timestamps = true,
 		},
@@ -1549,7 +1598,7 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused)
 		     "comma separated output fields prepend with 'type:'. "
 		     "Valid types: hw,sw,trace,raw. "
 		     "Fields: comm,tid,pid,time,cpu,event,trace,ip,sym,dso,"
-		     "addr,symoff,period", parse_output_fields),
+		     "addr,symoff,period,flags", parse_output_fields),
 	OPT_BOOLEAN('a', "all-cpus", &system_wide,
 		    "system-wide collection from all CPUs"),
 	OPT_STRING('S', "symbols", &symbol_conf.sym_list_str, "symbol[,symbol...]",
@@ -1570,6 +1619,9 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused)
 	OPT_BOOLEAN('\0', "show-mmap-events", &script.show_mmap_events,
 		    "Show the mmap events"),
 	OPT_BOOLEAN('f', "force", &file.force, "don't complain, do it"),
+	OPT_CALLBACK_OPTARG(0, "itrace", &itrace_synth_opts, NULL, "opts",
+			    "Instruction Tracing options",
+			    itrace_parse_synth_opts),
 	OPT_END()
 	};
 	const char * const script_subcommands[] = { "record", "report", NULL };
@@ -1765,6 +1817,8 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused)
 
 	script.session = session;
 
+	session->itrace_synth_opts = &itrace_synth_opts;
+
 	if (cpu_list) {
 		err = perf_session__cpu_bitmap(session, cpu_list, cpu_bitmap);
 		if (err < 0)
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index f7b8218785f6..fcf99bdeb19e 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -73,8 +73,8 @@ static void print_counter(struct perf_evsel *counter, char *prefix);
 static void print_aggr(char *prefix);
 
 /* Default events used for perf stat -T */
-static const char * const transaction_attrs[] = {
-	"task-clock",
+static const char *transaction_attrs = {
+	"task-clock,"
 	"{"
 	"instructions,"
 	"cycles,"
@@ -86,8 +86,8 @@ static const char * const transaction_attrs[] = {
 };
 
 /* More limited version when the CPU does not have all events. */
-static const char * const transaction_limited_attrs[] = {
-	"task-clock",
+static const char * transaction_limited_attrs = {
+	"task-clock,"
 	"{"
 	"instructions,"
 	"cycles,"
@@ -96,30 +96,12 @@ static const char * const transaction_limited_attrs[] = {
 	"}"
 };
 
-/* must match transaction_attrs and the beginning limited_attrs */
-enum {
-	T_TASK_CLOCK,
-	T_INSTRUCTIONS,
-	T_CYCLES,
-	T_CYCLES_IN_TX,
-	T_TRANSACTION_START,
-	T_ELISION_START,
-	T_CYCLES_IN_TX_CP,
-};
-
 static struct perf_evlist	*evsel_list;
 
 static struct target target = {
 	.uid	= UINT_MAX,
 };
 
-enum aggr_mode {
-	AGGR_NONE,
-	AGGR_GLOBAL,
-	AGGR_SOCKET,
-	AGGR_CORE,
-};
-
 static int			run_count			=  1;
 static bool			no_inherit			= false;
 static bool			scale				=  true;
@@ -147,10 +129,6 @@ static int			(*aggr_get_id)(struct cpu_map *m, int cpu);
 
 static volatile int done = 0;
 
-struct perf_stat {
-	struct stats	  res_stats[3];
-};
-
 static inline void diff_timespec(struct timespec *r, struct timespec *a,
 				 struct timespec *b)
 {
@@ -180,6 +158,8 @@ static void perf_evsel__reset_stat_priv(struct perf_evsel *evsel)
 
 	for (i = 0; i < 3; i++)
 		init_stats(&ps->res_stats[i]);
+
+	perf_stat_evsel_id_init(evsel);
 }
 
 static int perf_evsel__alloc_stat_priv(struct perf_evsel *evsel)
@@ -198,24 +178,19 @@ static void perf_evsel__free_stat_priv(struct perf_evsel *evsel)
 
 static int perf_evsel__alloc_prev_raw_counts(struct perf_evsel *evsel)
 {
-	void *addr;
-	size_t sz;
+	struct perf_counts *counts;
 
-	sz = sizeof(*evsel->counts) +
-	     (perf_evsel__nr_cpus(evsel) * sizeof(struct perf_counts_values));
+	counts = perf_counts__new(perf_evsel__nr_cpus(evsel));
+	if (counts)
+		evsel->prev_raw_counts = counts;
 
-	addr = zalloc(sz);
-	if (!addr)
-		return -ENOMEM;
-
-	evsel->prev_raw_counts =  addr;
-
-	return 0;
+	return counts ? 0 : -ENOMEM;
 }
 
 static void perf_evsel__free_prev_raw_counts(struct perf_evsel *evsel)
 {
-	zfree(&evsel->prev_raw_counts);
+	perf_counts__delete(evsel->prev_raw_counts);
+	evsel->prev_raw_counts = NULL;
 }
 
 static void perf_evlist__free_stats(struct perf_evlist *evlist)
@@ -247,22 +222,6 @@ out_free:
 	return -1;
 }
 
-static struct stats runtime_nsecs_stats[MAX_NR_CPUS];
-static struct stats runtime_cycles_stats[MAX_NR_CPUS];
-static struct stats runtime_stalled_cycles_front_stats[MAX_NR_CPUS];
-static struct stats runtime_stalled_cycles_back_stats[MAX_NR_CPUS];
-static struct stats runtime_branches_stats[MAX_NR_CPUS];
-static struct stats runtime_cacherefs_stats[MAX_NR_CPUS];
-static struct stats runtime_l1_dcache_stats[MAX_NR_CPUS];
-static struct stats runtime_l1_icache_stats[MAX_NR_CPUS];
-static struct stats runtime_ll_cache_stats[MAX_NR_CPUS];
-static struct stats runtime_itlb_cache_stats[MAX_NR_CPUS];
-static struct stats runtime_dtlb_cache_stats[MAX_NR_CPUS];
-static struct stats runtime_cycles_in_tx_stats[MAX_NR_CPUS];
-static struct stats walltime_nsecs_stats;
-static struct stats runtime_transaction_stats[MAX_NR_CPUS];
-static struct stats runtime_elision_stats[MAX_NR_CPUS];
-
 static void perf_stat__reset_stats(struct perf_evlist *evlist)
 {
 	struct perf_evsel *evsel;
@@ -272,23 +231,7 @@ static void perf_stat__reset_stats(struct perf_evlist *evlist)
 		perf_evsel__reset_counts(evsel, perf_evsel__nr_cpus(evsel));
 	}
 
-	memset(runtime_nsecs_stats, 0, sizeof(runtime_nsecs_stats));
-	memset(runtime_cycles_stats, 0, sizeof(runtime_cycles_stats));
-	memset(runtime_stalled_cycles_front_stats, 0, sizeof(runtime_stalled_cycles_front_stats));
-	memset(runtime_stalled_cycles_back_stats, 0, sizeof(runtime_stalled_cycles_back_stats));
-	memset(runtime_branches_stats, 0, sizeof(runtime_branches_stats));
-	memset(runtime_cacherefs_stats, 0, sizeof(runtime_cacherefs_stats));
-	memset(runtime_l1_dcache_stats, 0, sizeof(runtime_l1_dcache_stats));
-	memset(runtime_l1_icache_stats, 0, sizeof(runtime_l1_icache_stats));
-	memset(runtime_ll_cache_stats, 0, sizeof(runtime_ll_cache_stats));
-	memset(runtime_itlb_cache_stats, 0, sizeof(runtime_itlb_cache_stats));
-	memset(runtime_dtlb_cache_stats, 0, sizeof(runtime_dtlb_cache_stats));
-	memset(runtime_cycles_in_tx_stats, 0,
-			sizeof(runtime_cycles_in_tx_stats));
-	memset(runtime_transaction_stats, 0,
-		sizeof(runtime_transaction_stats));
-	memset(runtime_elision_stats, 0, sizeof(runtime_elision_stats));
-	memset(&walltime_nsecs_stats, 0, sizeof(walltime_nsecs_stats));
+	perf_stat__reset_shadow_stats();
 }
 
 static int create_perf_stat_counter(struct perf_evsel *evsel)
@@ -325,70 +268,6 @@ static inline int nsec_counter(struct perf_evsel *evsel)
 	return 0;
 }
 
-static struct perf_evsel *nth_evsel(int n)
-{
-	static struct perf_evsel **array;
-	static int array_len;
-	struct perf_evsel *ev;
-	int j;
-
-	/* Assumes this only called when evsel_list does not change anymore. */
-	if (!array) {
-		evlist__for_each(evsel_list, ev)
-			array_len++;
-		array = malloc(array_len * sizeof(void *));
-		if (!array)
-			exit(ENOMEM);
-		j = 0;
-		evlist__for_each(evsel_list, ev)
-			array[j++] = ev;
-	}
-	if (n < array_len)
-		return array[n];
-	return NULL;
-}
-
-/*
- * Update various tracking values we maintain to print
- * more semantic information such as miss/hit ratios,
- * instruction rates, etc:
- */
-static void update_shadow_stats(struct perf_evsel *counter, u64 *count,
-				int cpu)
-{
-	if (perf_evsel__match(counter, SOFTWARE, SW_TASK_CLOCK))
-		update_stats(&runtime_nsecs_stats[cpu], count[0]);
-	else if (perf_evsel__match(counter, HARDWARE, HW_CPU_CYCLES))
-		update_stats(&runtime_cycles_stats[cpu], count[0]);
-	else if (transaction_run &&
-		 perf_evsel__cmp(counter, nth_evsel(T_CYCLES_IN_TX)))
-		update_stats(&runtime_cycles_in_tx_stats[cpu], count[0]);
-	else if (transaction_run &&
-		 perf_evsel__cmp(counter, nth_evsel(T_TRANSACTION_START)))
-		update_stats(&runtime_transaction_stats[cpu], count[0]);
-	else if (transaction_run &&
-		 perf_evsel__cmp(counter, nth_evsel(T_ELISION_START)))
-		update_stats(&runtime_elision_stats[cpu], count[0]);
-	else if (perf_evsel__match(counter, HARDWARE, HW_STALLED_CYCLES_FRONTEND))
-		update_stats(&runtime_stalled_cycles_front_stats[cpu], count[0]);
-	else if (perf_evsel__match(counter, HARDWARE, HW_STALLED_CYCLES_BACKEND))
-		update_stats(&runtime_stalled_cycles_back_stats[cpu], count[0]);
-	else if (perf_evsel__match(counter, HARDWARE, HW_BRANCH_INSTRUCTIONS))
-		update_stats(&runtime_branches_stats[cpu], count[0]);
-	else if (perf_evsel__match(counter, HARDWARE, HW_CACHE_REFERENCES))
-		update_stats(&runtime_cacherefs_stats[cpu], count[0]);
-	else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_L1D))
-		update_stats(&runtime_l1_dcache_stats[cpu], count[0]);
-	else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_L1I))
-		update_stats(&runtime_l1_icache_stats[cpu], count[0]);
-	else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_LL))
-		update_stats(&runtime_ll_cache_stats[cpu], count[0]);
-	else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_DTLB))
-		update_stats(&runtime_dtlb_cache_stats[cpu], count[0]);
-	else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_ITLB))
-		update_stats(&runtime_itlb_cache_stats[cpu], count[0]);
-}
-
 static void zero_per_pkg(struct perf_evsel *counter)
 {
 	if (counter->per_pkg_mask)
@@ -449,7 +328,7 @@ static int read_cb(struct perf_evsel *evsel, int cpu, int thread __maybe_unused,
 		perf_counts_values__scale(count, scale, NULL);
 		evsel->counts->cpu[cpu] = *count;
 		if (aggr_mode == AGGR_NONE)
-			update_shadow_stats(evsel, count->values, cpu);
+			perf_stat__update_shadow_stats(evsel, count->values, cpu);
 		break;
 	case AGGR_GLOBAL:
 		aggr->val += count->val;
@@ -497,7 +376,7 @@ static int read_counter_aggr(struct perf_evsel *counter)
 	/*
 	 * Save the full runtime - to allow normalization during printout:
 	 */
-	update_shadow_stats(counter, count, 0);
+	perf_stat__update_shadow_stats(counter, count, 0);
 
 	return 0;
 }
@@ -665,7 +544,10 @@ static int __run_perf_stat(int argc, const char **argv)
 					ui__warning("%s event is not supported by the kernel.\n",
 						    perf_evsel__name(counter));
 				counter->supported = false;
-				continue;
+
+				if ((counter->leader != counter) ||
+				    !(counter->leader->nr_members > 1))
+					continue;
 			}
 
 			perf_evsel__open_strerror(counter, &target,
@@ -875,188 +757,8 @@ static void nsec_printout(int id, int nr, struct perf_evsel *evsel, double avg)
 		fprintf(output, "                                   ");
 }
 
-/* used for get_ratio_color() */
-enum grc_type {
-	GRC_STALLED_CYCLES_FE,
-	GRC_STALLED_CYCLES_BE,
-	GRC_CACHE_MISSES,
-	GRC_MAX_NR
-};
-
-static const char *get_ratio_color(enum grc_type type, double ratio)
-{
-	static const double grc_table[GRC_MAX_NR][3] = {
-		[GRC_STALLED_CYCLES_FE] = { 50.0, 30.0, 10.0 },
-		[GRC_STALLED_CYCLES_BE] = { 75.0, 50.0, 20.0 },
-		[GRC_CACHE_MISSES] 	= { 20.0, 10.0, 5.0 },
-	};
-	const char *color = PERF_COLOR_NORMAL;
-
-	if (ratio > grc_table[type][0])
-		color = PERF_COLOR_RED;
-	else if (ratio > grc_table[type][1])
-		color = PERF_COLOR_MAGENTA;
-	else if (ratio > grc_table[type][2])
-		color = PERF_COLOR_YELLOW;
-
-	return color;
-}
-
-static void print_stalled_cycles_frontend(int cpu,
-					  struct perf_evsel *evsel
-					  __maybe_unused, double avg)
-{
-	double total, ratio = 0.0;
-	const char *color;
-
-	total = avg_stats(&runtime_cycles_stats[cpu]);
-
-	if (total)
-		ratio = avg / total * 100.0;
-
-	color = get_ratio_color(GRC_STALLED_CYCLES_FE, ratio);
-
-	fprintf(output, " #  ");
-	color_fprintf(output, color, "%6.2f%%", ratio);
-	fprintf(output, " frontend cycles idle   ");
-}
-
-static void print_stalled_cycles_backend(int cpu,
-					 struct perf_evsel *evsel
-					 __maybe_unused, double avg)
-{
-	double total, ratio = 0.0;
-	const char *color;
-
-	total = avg_stats(&runtime_cycles_stats[cpu]);
-
-	if (total)
-		ratio = avg / total * 100.0;
-
-	color = get_ratio_color(GRC_STALLED_CYCLES_BE, ratio);
-
-	fprintf(output, " #  ");
-	color_fprintf(output, color, "%6.2f%%", ratio);
-	fprintf(output, " backend  cycles idle   ");
-}
-
-static void print_branch_misses(int cpu,
-				struct perf_evsel *evsel __maybe_unused,
-				double avg)
-{
-	double total, ratio = 0.0;
-	const char *color;
-
-	total = avg_stats(&runtime_branches_stats[cpu]);
-
-	if (total)
-		ratio = avg / total * 100.0;
-
-	color = get_ratio_color(GRC_CACHE_MISSES, ratio);
-
-	fprintf(output, " #  ");
-	color_fprintf(output, color, "%6.2f%%", ratio);
-	fprintf(output, " of all branches        ");
-}
-
-static void print_l1_dcache_misses(int cpu,
-				   struct perf_evsel *evsel __maybe_unused,
-				   double avg)
-{
-	double total, ratio = 0.0;
-	const char *color;
-
-	total = avg_stats(&runtime_l1_dcache_stats[cpu]);
-
-	if (total)
-		ratio = avg / total * 100.0;
-
-	color = get_ratio_color(GRC_CACHE_MISSES, ratio);
-
-	fprintf(output, " #  ");
-	color_fprintf(output, color, "%6.2f%%", ratio);
-	fprintf(output, " of all L1-dcache hits  ");
-}
-
-static void print_l1_icache_misses(int cpu,
-				   struct perf_evsel *evsel __maybe_unused,
-				   double avg)
-{
-	double total, ratio = 0.0;
-	const char *color;
-
-	total = avg_stats(&runtime_l1_icache_stats[cpu]);
-
-	if (total)
-		ratio = avg / total * 100.0;
-
-	color = get_ratio_color(GRC_CACHE_MISSES, ratio);
-
-	fprintf(output, " #  ");
-	color_fprintf(output, color, "%6.2f%%", ratio);
-	fprintf(output, " of all L1-icache hits  ");
-}
-
-static void print_dtlb_cache_misses(int cpu,
-				    struct perf_evsel *evsel __maybe_unused,
-				    double avg)
-{
-	double total, ratio = 0.0;
-	const char *color;
-
-	total = avg_stats(&runtime_dtlb_cache_stats[cpu]);
-
-	if (total)
-		ratio = avg / total * 100.0;
-
-	color = get_ratio_color(GRC_CACHE_MISSES, ratio);
-
-	fprintf(output, " #  ");
-	color_fprintf(output, color, "%6.2f%%", ratio);
-	fprintf(output, " of all dTLB cache hits ");
-}
-
-static void print_itlb_cache_misses(int cpu,
-				    struct perf_evsel *evsel __maybe_unused,
-				    double avg)
-{
-	double total, ratio = 0.0;
-	const char *color;
-
-	total = avg_stats(&runtime_itlb_cache_stats[cpu]);
-
-	if (total)
-		ratio = avg / total * 100.0;
-
-	color = get_ratio_color(GRC_CACHE_MISSES, ratio);
-
-	fprintf(output, " #  ");
-	color_fprintf(output, color, "%6.2f%%", ratio);
-	fprintf(output, " of all iTLB cache hits ");
-}
-
-static void print_ll_cache_misses(int cpu,
-				  struct perf_evsel *evsel __maybe_unused,
-				  double avg)
-{
-	double total, ratio = 0.0;
-	const char *color;
-
-	total = avg_stats(&runtime_ll_cache_stats[cpu]);
-
-	if (total)
-		ratio = avg / total * 100.0;
-
-	color = get_ratio_color(GRC_CACHE_MISSES, ratio);
-
-	fprintf(output, " #  ");
-	color_fprintf(output, color, "%6.2f%%", ratio);
-	fprintf(output, " of all LL-cache hits   ");
-}
-
 static void abs_printout(int id, int nr, struct perf_evsel *evsel, double avg)
 {
-	double total, ratio = 0.0, total2;
 	double sc =  evsel->scale;
 	const char *fmt;
 	int cpu = cpu_map__id_to_cpu(id);
@@ -1090,138 +792,7 @@ static void abs_printout(int id, int nr, struct perf_evsel *evsel, double avg)
 	if (csv_output || interval)
 		return;
 
-	if (perf_evsel__match(evsel, HARDWARE, HW_INSTRUCTIONS)) {
-		total = avg_stats(&runtime_cycles_stats[cpu]);
-		if (total) {
-			ratio = avg / total;
-			fprintf(output, " #   %5.2f  insns per cycle        ", ratio);
-		} else {
-			fprintf(output, "                                   ");
-		}
-		total = avg_stats(&runtime_stalled_cycles_front_stats[cpu]);
-		total = max(total, avg_stats(&runtime_stalled_cycles_back_stats[cpu]));
-
-		if (total && avg) {
-			ratio = total / avg;
-			fprintf(output, "\n");
-			if (aggr_mode == AGGR_NONE)
-				fprintf(output, "        ");
-			fprintf(output, "                                                  #   %5.2f  stalled cycles per insn", ratio);
-		}
-
-	} else if (perf_evsel__match(evsel, HARDWARE, HW_BRANCH_MISSES) &&
-			runtime_branches_stats[cpu].n != 0) {
-		print_branch_misses(cpu, evsel, avg);
-	} else if (
-		evsel->attr.type == PERF_TYPE_HW_CACHE &&
-		evsel->attr.config ==  ( PERF_COUNT_HW_CACHE_L1D |
-					((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
-					((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16)) &&
-			runtime_l1_dcache_stats[cpu].n != 0) {
-		print_l1_dcache_misses(cpu, evsel, avg);
-	} else if (
-		evsel->attr.type == PERF_TYPE_HW_CACHE &&
-		evsel->attr.config ==  ( PERF_COUNT_HW_CACHE_L1I |
-					((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
-					((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16)) &&
-			runtime_l1_icache_stats[cpu].n != 0) {
-		print_l1_icache_misses(cpu, evsel, avg);
-	} else if (
-		evsel->attr.type == PERF_TYPE_HW_CACHE &&
-		evsel->attr.config ==  ( PERF_COUNT_HW_CACHE_DTLB |
-					((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
-					((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16)) &&
-			runtime_dtlb_cache_stats[cpu].n != 0) {
-		print_dtlb_cache_misses(cpu, evsel, avg);
-	} else if (
-		evsel->attr.type == PERF_TYPE_HW_CACHE &&
-		evsel->attr.config ==  ( PERF_COUNT_HW_CACHE_ITLB |
-					((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
-					((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16)) &&
-			runtime_itlb_cache_stats[cpu].n != 0) {
-		print_itlb_cache_misses(cpu, evsel, avg);
-	} else if (
-		evsel->attr.type == PERF_TYPE_HW_CACHE &&
-		evsel->attr.config ==  ( PERF_COUNT_HW_CACHE_LL |
-					((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
-					((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16)) &&
-			runtime_ll_cache_stats[cpu].n != 0) {
-		print_ll_cache_misses(cpu, evsel, avg);
-	} else if (perf_evsel__match(evsel, HARDWARE, HW_CACHE_MISSES) &&
-			runtime_cacherefs_stats[cpu].n != 0) {
-		total = avg_stats(&runtime_cacherefs_stats[cpu]);
-
-		if (total)
-			ratio = avg * 100 / total;
-
-		fprintf(output, " # %8.3f %% of all cache refs    ", ratio);
-
-	} else if (perf_evsel__match(evsel, HARDWARE, HW_STALLED_CYCLES_FRONTEND)) {
-		print_stalled_cycles_frontend(cpu, evsel, avg);
-	} else if (perf_evsel__match(evsel, HARDWARE, HW_STALLED_CYCLES_BACKEND)) {
-		print_stalled_cycles_backend(cpu, evsel, avg);
-	} else if (perf_evsel__match(evsel, HARDWARE, HW_CPU_CYCLES)) {
-		total = avg_stats(&runtime_nsecs_stats[cpu]);
-
-		if (total) {
-			ratio = avg / total;
-			fprintf(output, " # %8.3f GHz                    ", ratio);
-		} else {
-			fprintf(output, "                                   ");
-		}
-	} else if (transaction_run &&
-		   perf_evsel__cmp(evsel, nth_evsel(T_CYCLES_IN_TX))) {
-		total = avg_stats(&runtime_cycles_stats[cpu]);
-		if (total)
-			fprintf(output,
-				" #   %5.2f%% transactional cycles   ",
-				100.0 * (avg / total));
-	} else if (transaction_run &&
-		   perf_evsel__cmp(evsel, nth_evsel(T_CYCLES_IN_TX_CP))) {
-		total = avg_stats(&runtime_cycles_stats[cpu]);
-		total2 = avg_stats(&runtime_cycles_in_tx_stats[cpu]);
-		if (total2 < avg)
-			total2 = avg;
-		if (total)
-			fprintf(output,
-				" #   %5.2f%% aborted cycles         ",
-				100.0 * ((total2-avg) / total));
-	} else if (transaction_run &&
-		   perf_evsel__cmp(evsel, nth_evsel(T_TRANSACTION_START)) &&
-		   avg > 0 &&
-		   runtime_cycles_in_tx_stats[cpu].n != 0) {
-		total = avg_stats(&runtime_cycles_in_tx_stats[cpu]);
-
-		if (total)
-			ratio = total / avg;
-
-		fprintf(output, " # %8.0f cycles / transaction   ", ratio);
-	} else if (transaction_run &&
-		   perf_evsel__cmp(evsel, nth_evsel(T_ELISION_START)) &&
-		   avg > 0 &&
-		   runtime_cycles_in_tx_stats[cpu].n != 0) {
-		total = avg_stats(&runtime_cycles_in_tx_stats[cpu]);
-
-		if (total)
-			ratio = total / avg;
-
-		fprintf(output, " # %8.0f cycles / elision       ", ratio);
-	} else if (runtime_nsecs_stats[cpu].n != 0) {
-		char unit = 'M';
-
-		total = avg_stats(&runtime_nsecs_stats[cpu]);
-
-		if (total)
-			ratio = 1000.0 * avg / total;
-		if (ratio < 0.001) {
-			ratio *= 1000;
-			unit = 'K';
-		}
-
-		fprintf(output, " # %8.3f %c/sec                  ", ratio, unit);
-	} else {
-		fprintf(output, "                                   ");
-	}
+	perf_stat__print_shadow_stats(output, evsel, avg, cpu, aggr_mode);
 }
 
 static void print_aggr(char *prefix)
@@ -1536,17 +1107,6 @@ static int perf_stat_init_aggr_mode(void)
 	return 0;
 }
 
-static int setup_events(const char * const *attrs, unsigned len)
-{
-	unsigned i;
-
-	for (i = 0; i < len; i++) {
-		if (parse_events(evsel_list, attrs[i]))
-			return -1;
-	}
-	return 0;
-}
-
 /*
  * Add default attributes, if there were no attributes specified or
  * if -d/--detailed, -d -d or -d -d -d is used:
@@ -1668,12 +1228,10 @@ static int add_default_attributes(void)
 		int err;
 		if (pmu_have_event("cpu", "cycles-ct") &&
 		    pmu_have_event("cpu", "el-start"))
-			err = setup_events(transaction_attrs,
-					ARRAY_SIZE(transaction_attrs));
+			err = parse_events(evsel_list, transaction_attrs, NULL);
 		else
-			err = setup_events(transaction_limited_attrs,
-				 ARRAY_SIZE(transaction_limited_attrs));
-		if (err < 0) {
+			err = parse_events(evsel_list, transaction_limited_attrs, NULL);
+		if (err) {
 			fprintf(stderr, "Cannot set up transaction events\n");
 			return -1;
 		}
diff --git a/tools/perf/builtin-timechart.c b/tools/perf/builtin-timechart.c
index e50fe1187b0b..30e59620179d 100644
--- a/tools/perf/builtin-timechart.c
+++ b/tools/perf/builtin-timechart.c
@@ -61,13 +61,13 @@ struct timechart {
 				tasks_only,
 				with_backtrace,
 				topology;
+	bool			force;
 	/* IO related settings */
-	u64			io_events;
 	bool			io_only,
 				skip_eagain;
+	u64			io_events;
 	u64			min_time,
 				merge_dist;
-	bool			force;
 };
 
 struct per_pidcomm;
@@ -523,7 +523,7 @@ static const char *cat_backtrace(union perf_event *event,
 				 * Discard all.
 				 */
 				zfree(&p);
-				goto exit;
+				goto exit_put;
 			}
 			continue;
 		}
@@ -538,7 +538,8 @@ static const char *cat_backtrace(union perf_event *event,
 		else
 			fprintf(f, "..... %016" PRIx64 "\n", ip);
 	}
-
+exit_put:
+	addr_location__put(&al);
 exit:
 	fclose(f);
 
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 6a4d5d41c671..619a8696fda7 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -235,10 +235,13 @@ static void perf_top__show_details(struct perf_top *top)
 
 	more = symbol__annotate_printf(symbol, he->ms.map, top->sym_evsel,
 				       0, top->sym_pcnt_filter, top->print_entries, 4);
-	if (top->zero)
-		symbol__annotate_zero_histogram(symbol, top->sym_evsel->idx);
-	else
-		symbol__annotate_decay_histogram(symbol, top->sym_evsel->idx);
+
+	if (top->evlist->enabled) {
+		if (top->zero)
+			symbol__annotate_zero_histogram(symbol, top->sym_evsel->idx);
+		else
+			symbol__annotate_decay_histogram(symbol, top->sym_evsel->idx);
+	}
 	if (more != 0)
 		printf("%d lines not displayed, maybe increase display entries [e]\n", more);
 out_unlock:
@@ -276,11 +279,13 @@ static void perf_top__print_sym_table(struct perf_top *top)
 		return;
 	}
 
-	if (top->zero) {
-		hists__delete_entries(hists);
-	} else {
-		hists__decay_entries(hists, top->hide_user_symbols,
-				     top->hide_kernel_symbols);
+	if (top->evlist->enabled) {
+		if (top->zero) {
+			hists__delete_entries(hists);
+		} else {
+			hists__decay_entries(hists, top->hide_user_symbols,
+					     top->hide_kernel_symbols);
+		}
 	}
 
 	hists__collapse_resort(hists, NULL);
@@ -545,11 +550,13 @@ static void perf_top__sort_new_samples(void *arg)
 
 	hists = evsel__hists(t->sym_evsel);
 
-	if (t->zero) {
-		hists__delete_entries(hists);
-	} else {
-		hists__decay_entries(hists, t->hide_user_symbols,
-				     t->hide_kernel_symbols);
+	if (t->evlist->enabled) {
+		if (t->zero) {
+			hists__delete_entries(hists);
+		} else {
+			hists__decay_entries(hists, t->hide_user_symbols,
+					     t->hide_kernel_symbols);
+		}
 	}
 
 	hists__collapse_resort(hists, NULL);
@@ -579,8 +586,27 @@ static void *display_thread_tui(void *arg)
 		hists->uid_filter_str = top->record_opts.target.uid_str;
 	}
 
-	perf_evlist__tui_browse_hists(top->evlist, help, &hbt, top->min_percent,
-				      &top->session->header.env);
+	while (true)  {
+		int key = perf_evlist__tui_browse_hists(top->evlist, help, &hbt,
+							top->min_percent,
+							&top->session->header.env);
+
+		if (key != 'f')
+			break;
+
+		perf_evlist__toggle_enable(top->evlist);
+		/*
+		 * No need to refresh, resort/decay histogram entries
+		 * if we are not collecting samples:
+		 */
+		if (top->evlist->enabled) {
+			hbt.refresh = top->delay_secs;
+			help = "Press 'f' to disable the events or 'h' to see other hotkeys";
+		} else {
+			help = "Press 'f' again to re-enable the events";
+			hbt.refresh = 0;
+		}
+	}
 
 	done = 1;
 	return NULL;
@@ -775,7 +801,9 @@ static void perf_event__process_sample(struct perf_tool *tool,
 	if (al.sym == NULL || !al.sym->ignore) {
 		struct hists *hists = evsel__hists(evsel);
 		struct hist_entry_iter iter = {
-			.add_entry_cb = hist_iter__top_callback,
+			.evsel		= evsel,
+			.sample 	= sample,
+			.add_entry_cb 	= hist_iter__top_callback,
 		};
 
 		if (symbol_conf.cumulate_callchain)
@@ -785,15 +813,14 @@ static void perf_event__process_sample(struct perf_tool *tool,
 
 		pthread_mutex_lock(&hists->lock);
 
-		err = hist_entry_iter__add(&iter, &al, evsel, sample,
-					   top->max_stack, top);
+		err = hist_entry_iter__add(&iter, &al, top->max_stack, top);
 		if (err < 0)
 			pr_err("Problem incrementing symbol period, skipping event\n");
 
 		pthread_mutex_unlock(&hists->lock);
 	}
 
-	return;
+	addr_location__put(&al);
 }
 
 static void perf_top__mmap_read_idx(struct perf_top *top, int idx)
@@ -950,7 +977,7 @@ static int __cmd_top(struct perf_top *top)
 		goto out_delete;
 
 	machine__synthesize_threads(&top->session->machines.host, &opts->target,
-				    top->evlist->threads, false);
+				    top->evlist->threads, false, opts->proc_map_timeout);
 	ret = perf_top__start_counters(top);
 	if (ret)
 		goto out_delete;
@@ -1060,6 +1087,7 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused)
 			.target		= {
 				.uses_mmap   = true,
 			},
+			.proc_map_timeout    = 500,
 		},
 		.max_stack	     = PERF_MAX_STACK_DEPTH,
 		.sym_pcnt_filter     = 5,
@@ -1159,6 +1187,8 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused)
 	OPT_STRING('w', "column-widths", &symbol_conf.col_width_list_str,
 		   "width[,width...]",
 		   "don't try to adjust column width, use these fixed values"),
+	OPT_UINTEGER(0, "proc-map-timeout", &opts->proc_map_timeout,
+			"per thread proc mmap processing timeout in ms"),
 	OPT_END()
 	};
 	const char * const top_usage[] = {
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index e122970361f2..de5d277d1ad7 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -16,7 +16,6 @@
 
 #include <libaudit.h>
 #include <stdlib.h>
-#include <sys/eventfd.h>
 #include <sys/mman.h>
 #include <linux/futex.h>
 
@@ -41,6 +40,51 @@
 # define EFD_SEMAPHORE		1
 #endif
 
+#ifndef EFD_NONBLOCK
+# define EFD_NONBLOCK		00004000
+#endif
+
+#ifndef EFD_CLOEXEC
+# define EFD_CLOEXEC		02000000
+#endif
+
+#ifndef O_CLOEXEC
+# define O_CLOEXEC		02000000
+#endif
+
+#ifndef SOCK_DCCP
+# define SOCK_DCCP		6
+#endif
+
+#ifndef SOCK_CLOEXEC
+# define SOCK_CLOEXEC		02000000
+#endif
+
+#ifndef SOCK_NONBLOCK
+# define SOCK_NONBLOCK		00004000
+#endif
+
+#ifndef MSG_CMSG_CLOEXEC
+# define MSG_CMSG_CLOEXEC	0x40000000
+#endif
+
+#ifndef PERF_FLAG_FD_NO_GROUP
+# define PERF_FLAG_FD_NO_GROUP		(1UL << 0)
+#endif
+
+#ifndef PERF_FLAG_FD_OUTPUT
+# define PERF_FLAG_FD_OUTPUT		(1UL << 1)
+#endif
+
+#ifndef PERF_FLAG_PID_CGROUP
+# define PERF_FLAG_PID_CGROUP		(1UL << 2) /* pid=cgroup id, per-cpu mode only */
+#endif
+
+#ifndef PERF_FLAG_FD_CLOEXEC
+# define PERF_FLAG_FD_CLOEXEC		(1UL << 3) /* O_CLOEXEC */
+#endif
+
+
 struct tp_field {
 	int offset;
 	union {
@@ -331,6 +375,14 @@ static size_t syscall_arg__scnprintf_hex(char *bf, size_t size,
 
 #define SCA_HEX syscall_arg__scnprintf_hex
 
+static size_t syscall_arg__scnprintf_int(char *bf, size_t size,
+					 struct syscall_arg *arg)
+{
+	return scnprintf(bf, size, "%d", arg->val);
+}
+
+#define SCA_INT syscall_arg__scnprintf_int
+
 static size_t syscall_arg__scnprintf_mmap_prot(char *bf, size_t size,
 					       struct syscall_arg *arg)
 {
@@ -783,6 +835,34 @@ static size_t syscall_arg__scnprintf_open_flags(char *bf, size_t size,
 
 #define SCA_OPEN_FLAGS syscall_arg__scnprintf_open_flags
 
+static size_t syscall_arg__scnprintf_perf_flags(char *bf, size_t size,
+						struct syscall_arg *arg)
+{
+	int printed = 0, flags = arg->val;
+
+	if (flags == 0)
+		return 0;
+
+#define	P_FLAG(n) \
+	if (flags & PERF_FLAG_##n) { \
+		printed += scnprintf(bf + printed, size - printed, "%s%s", printed ? "|" : "", #n); \
+		flags &= ~PERF_FLAG_##n; \
+	}
+
+	P_FLAG(FD_NO_GROUP);
+	P_FLAG(FD_OUTPUT);
+	P_FLAG(PID_CGROUP);
+	P_FLAG(FD_CLOEXEC);
+#undef P_FLAG
+
+	if (flags)
+		printed += scnprintf(bf + printed, size - printed, "%s%#x", printed ? "|" : "", flags);
+
+	return printed;
+}
+
+#define SCA_PERF_FLAGS syscall_arg__scnprintf_perf_flags
+
 static size_t syscall_arg__scnprintf_eventfd_flags(char *bf, size_t size,
 						   struct syscall_arg *arg)
 {
@@ -1050,6 +1130,11 @@ static struct syscall_fmt {
 	{ .name	    = "openat",	    .errmsg = true,
 	  .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */
 			     [2] = SCA_OPEN_FLAGS, /* flags */ }, },
+	{ .name	    = "perf_event_open", .errmsg = true,
+	  .arg_scnprintf = { [1] = SCA_INT, /* pid */
+			     [2] = SCA_INT, /* cpu */
+			     [3] = SCA_FD,  /* group_fd */
+			     [4] = SCA_PERF_FLAGS,  /* flags */ }, },
 	{ .name	    = "pipe2",	    .errmsg = true,
 	  .arg_scnprintf = { [1] = SCA_PIPE_FLAGS, /* flags */ }, },
 	{ .name	    = "poll",	    .errmsg = true, .timeout = true, },
@@ -1433,7 +1518,8 @@ static int trace__symbols_init(struct trace *trace, struct perf_evlist *evlist)
 		return -ENOMEM;
 
 	err = __machine__synthesize_threads(trace->host, &trace->tool, &trace->opts.target,
-					    evlist->threads, trace__tool_process, false);
+					    evlist->threads, trace__tool_process, false,
+					    trace->opts.proc_map_timeout);
 	if (err)
 		symbol__exit();
 
@@ -1712,7 +1798,7 @@ static int trace__sys_enter(struct trace *trace, struct perf_evsel *evsel,
 	void *args;
 	size_t printed = 0;
 	struct thread *thread;
-	int id = perf_evsel__sc_tp_uint(evsel, id, sample);
+	int id = perf_evsel__sc_tp_uint(evsel, id, sample), err = -1;
 	struct syscall *sc = trace__syscall_info(trace, evsel, id);
 	struct thread_trace *ttrace;
 
@@ -1725,14 +1811,14 @@ static int trace__sys_enter(struct trace *trace, struct perf_evsel *evsel,
 	thread = machine__findnew_thread(trace->host, sample->pid, sample->tid);
 	ttrace = thread__trace(thread, trace->output);
 	if (ttrace == NULL)
-		return -1;
+		goto out_put;
 
 	args = perf_evsel__sc_tp_ptr(evsel, args, sample);
 
 	if (ttrace->entry_str == NULL) {
 		ttrace->entry_str = malloc(1024);
 		if (!ttrace->entry_str)
-			return -1;
+			goto out_put;
 	}
 
 	if (!trace->summary_only)
@@ -1757,8 +1843,10 @@ static int trace__sys_enter(struct trace *trace, struct perf_evsel *evsel,
 		thread__put(trace->current);
 		trace->current = thread__get(thread);
 	}
-
-	return 0;
+	err = 0;
+out_put:
+	thread__put(thread);
+	return err;
 }
 
 static int trace__sys_exit(struct trace *trace, struct perf_evsel *evsel,
@@ -1768,7 +1856,7 @@ static int trace__sys_exit(struct trace *trace, struct perf_evsel *evsel,
 	long ret;
 	u64 duration = 0;
 	struct thread *thread;
-	int id = perf_evsel__sc_tp_uint(evsel, id, sample);
+	int id = perf_evsel__sc_tp_uint(evsel, id, sample), err = -1;
 	struct syscall *sc = trace__syscall_info(trace, evsel, id);
 	struct thread_trace *ttrace;
 
@@ -1781,7 +1869,7 @@ static int trace__sys_exit(struct trace *trace, struct perf_evsel *evsel,
 	thread = machine__findnew_thread(trace->host, sample->pid, sample->tid);
 	ttrace = thread__trace(thread, trace->output);
 	if (ttrace == NULL)
-		return -1;
+		goto out_put;
 
 	if (trace->summary)
 		thread__update_stats(ttrace, id, sample);
@@ -1835,8 +1923,10 @@ signed_print:
 	fputc('\n', trace->output);
 out:
 	ttrace->entry_pending = false;
-
-	return 0;
+	err = 0;
+out_put:
+	thread__put(thread);
+	return err;
 }
 
 static int trace__vfs_getname(struct trace *trace, struct perf_evsel *evsel,
@@ -1863,6 +1953,7 @@ static int trace__sched_stat_runtime(struct trace *trace, struct perf_evsel *evs
 
 	ttrace->runtime_ms += runtime_ms;
 	trace->runtime_ms += runtime_ms;
+	thread__put(thread);
 	return 0;
 
 out_dump:
@@ -1872,6 +1963,7 @@ out_dump:
 	       (pid_t)perf_evsel__intval(evsel, sample, "pid"),
 	       runtime,
 	       perf_evsel__intval(evsel, sample, "vruntime"));
+	thread__put(thread);
 	return 0;
 }
 
@@ -1924,11 +2016,12 @@ static int trace__pgfault(struct trace *trace,
 	struct addr_location al;
 	char map_type = 'd';
 	struct thread_trace *ttrace;
+	int err = -1;
 
 	thread = machine__findnew_thread(trace->host, sample->pid, sample->tid);
 	ttrace = thread__trace(thread, trace->output);
 	if (ttrace == NULL)
-		return -1;
+		goto out_put;
 
 	if (evsel->attr.config == PERF_COUNT_SW_PAGE_FAULTS_MAJ)
 		ttrace->pfmaj++;
@@ -1936,7 +2029,7 @@ static int trace__pgfault(struct trace *trace,
 		ttrace->pfmin++;
 
 	if (trace->summary_only)
-		return 0;
+		goto out;
 
 	thread__find_addr_location(thread, cpumode, MAP__FUNCTION,
 			      sample->ip, &al);
@@ -1967,8 +2060,11 @@ static int trace__pgfault(struct trace *trace,
 	print_location(trace->output, sample, &al, true, false);
 
 	fprintf(trace->output, " (%c%c)\n", map_type, al.level);
-
-	return 0;
+out:
+	err = 0;
+out_put:
+	thread__put(thread);
+	return err;
 }
 
 static bool skip_sample(struct trace *trace, struct perf_sample *sample)
@@ -2652,6 +2748,7 @@ int cmd_trace(int argc, const char **argv, const char *prefix __maybe_unused)
 			.user_interval = ULLONG_MAX,
 			.no_buffering  = true,
 			.mmap_pages    = UINT_MAX,
+			.proc_map_timeout  = 500,
 		},
 		.output = stdout,
 		.show_comm = true,
@@ -2666,16 +2763,15 @@ int cmd_trace(int argc, const char **argv, const char *prefix __maybe_unused)
 	OPT_BOOLEAN(0, "comm", &trace.show_comm,
 		    "show the thread COMM next to its id"),
 	OPT_BOOLEAN(0, "tool_stats", &trace.show_tool_stats, "show tool stats"),
-	OPT_STRING('e', "expr", &ev_qualifier_str, "expr",
-		    "list of events to trace"),
+	OPT_STRING('e', "expr", &ev_qualifier_str, "expr", "list of syscalls to trace"),
 	OPT_STRING('o', "output", &output_name, "file", "output file name"),
 	OPT_STRING('i', "input", &input_name, "file", "Analyze events in file"),
 	OPT_STRING('p', "pid", &trace.opts.target.pid, "pid",
 		    "trace events on existing process id"),
 	OPT_STRING('t', "tid", &trace.opts.target.tid, "tid",
 		    "trace events on existing thread id"),
-	OPT_CALLBACK(0, "filter-pids", &trace, "float",
-		     "show only events with duration > N.M ms", trace__set_filter_pids),
+	OPT_CALLBACK(0, "filter-pids", &trace, "CSV list of pids",
+		     "pids to filter (by the kernel)", trace__set_filter_pids),
 	OPT_BOOLEAN('a', "all-cpus", &trace.opts.target.system_wide,
 		    "system-wide collection from all CPUs"),
 	OPT_STRING('C', "cpu", &trace.opts.target.cpu_list, "cpu",
@@ -2702,6 +2798,8 @@ int cmd_trace(int argc, const char **argv, const char *prefix __maybe_unused)
 		     "Trace pagefaults", parse_pagefaults, "maj"),
 	OPT_BOOLEAN(0, "syscalls", &trace.trace_syscalls, "Trace syscalls"),
 	OPT_BOOLEAN('f', "force", &trace.force, "don't complain, do it"),
+	OPT_UINTEGER(0, "proc-map-timeout", &trace.opts.proc_map_timeout,
+			"per thread proc mmap processing timeout in ms"),
 	OPT_END()
 	};
 	const char * const trace_subcommands[] = { "record", NULL };
@@ -2712,11 +2810,10 @@ int cmd_trace(int argc, const char **argv, const char *prefix __maybe_unused)
 	signal(SIGFPE, sighandler_dump_stack);
 
 	trace.evlist = perf_evlist__new();
-	if (trace.evlist == NULL)
-		return -ENOMEM;
 
 	if (trace.evlist == NULL) {
 		pr_err("Not enough memory to run!\n");
+		err = -ENOMEM;
 		goto out;
 	}
 
diff --git a/tools/perf/config/Makefile b/tools/perf/config/Makefile
index 59a98c643240..317001c94660 100644
--- a/tools/perf/config/Makefile
+++ b/tools/perf/config/Makefile
@@ -32,7 +32,7 @@ ifeq ($(ARCH),x86)
     LIBUNWIND_LIBS = -lunwind -lunwind-x86_64
     $(call detected,CONFIG_X86_64)
   else
-    LIBUNWIND_LIBS = -lunwind -lunwind-x86
+    LIBUNWIND_LIBS = -lunwind-x86 -llzma -lunwind
   endif
   NO_PERF_REGS := 0
 endif
@@ -130,6 +130,8 @@ endif
 
 ifeq ($(DEBUG),0)
   CFLAGS += -O6
+else
+  CFLAGS += $(call cc-option,-Og,-O0)
 endif
 
 ifdef PARSER_DEBUG
@@ -268,6 +270,10 @@ else
   endif # libelf support
 endif # NO_LIBELF
 
+ifdef NO_DWARF
+  NO_LIBDW_DWARF_UNWIND := 1
+endif
+
 ifndef NO_LIBELF
   CFLAGS += -DHAVE_LIBELF_SUPPORT
   EXTLIBS += -lelf
@@ -610,6 +616,11 @@ ifdef LIBBABELTRACE
   endif
 endif
 
+ifndef NO_AUXTRACE
+  $(call detected,CONFIG_AUXTRACE)
+  CFLAGS += -DHAVE_AUXTRACE_SUPPORT
+endif
+
 # Among the variables below, these:
 #   perfexecdir
 #   template_dir
diff --git a/tools/perf/config/utilities.mak b/tools/perf/config/utilities.mak
index c16ce833079c..0ebef09c0842 100644
--- a/tools/perf/config/utilities.mak
+++ b/tools/perf/config/utilities.mak
@@ -177,3 +177,22 @@ $(if $($(1)),$(call _ge_attempt,$($(1)),$(1)),$(call _ge_attempt,$(2)))
 endef
 _ge_attempt = $(if $(get-executable),$(get-executable),$(call _gea_err,$(2)))
 _gea_err  = $(if $(1),$(error Please set '$(1)' appropriately))
+
+# try-run
+# Usage: option = $(call try-run, $(CC)...-o "$$TMP",option-ok,otherwise)
+# Exit code chooses option. "$$TMP" is can be used as temporary file and
+# is automatically cleaned up.
+try-run = $(shell set -e;		\
+	TMP="$(TMPOUT).$$$$.tmp";	\
+	TMPO="$(TMPOUT).$$$$.o";	\
+	if ($(1)) >/dev/null 2>&1;	\
+	then echo "$(2)";		\
+	else echo "$(3)";		\
+	fi;				\
+	rm -f "$$TMP" "$$TMPO")
+
+# cc-option
+# Usage: cflags-y += $(call cc-option,-march=winchip-c6,-march=i586)
+
+cc-option = $(call try-run,\
+	$(CC) $(KBUILD_CPPFLAGS) $(KBUILD_CFLAGS) $(1) -c -x c /dev/null -o "$$TMP",$(1),$(2))
diff --git a/tools/perf/perf-sys.h b/tools/perf/perf-sys.h
index 6ef68165c9db..83a25cef82fd 100644
--- a/tools/perf/perf-sys.h
+++ b/tools/perf/perf-sys.h
@@ -6,11 +6,9 @@
 #include <sys/syscall.h>
 #include <linux/types.h>
 #include <linux/perf_event.h>
+#include <asm/barrier.h>
 
 #if defined(__i386__)
-#define mb()		asm volatile("lock; addl $0,0(%%esp)" ::: "memory")
-#define wmb()		asm volatile("lock; addl $0,0(%%esp)" ::: "memory")
-#define rmb()		asm volatile("lock; addl $0,0(%%esp)" ::: "memory")
 #define cpu_relax()	asm volatile("rep; nop" ::: "memory");
 #define CPUINFO_PROC	{"model name"}
 #ifndef __NR_perf_event_open
@@ -25,9 +23,6 @@
 #endif
 
 #if defined(__x86_64__)
-#define mb()		asm volatile("mfence" ::: "memory")
-#define wmb()		asm volatile("sfence" ::: "memory")
-#define rmb()		asm volatile("lfence" ::: "memory")
 #define cpu_relax()	asm volatile("rep; nop" ::: "memory");
 #define CPUINFO_PROC	{"model name"}
 #ifndef __NR_perf_event_open
@@ -43,129 +38,63 @@
 
 #ifdef __powerpc__
 #include "../../arch/powerpc/include/uapi/asm/unistd.h"
-#define mb()		asm volatile ("sync" ::: "memory")
-#define wmb()		asm volatile ("sync" ::: "memory")
-#define rmb()		asm volatile ("sync" ::: "memory")
 #define CPUINFO_PROC	{"cpu"}
 #endif
 
 #ifdef __s390__
-#define mb()		asm volatile("bcr 15,0" ::: "memory")
-#define wmb()		asm volatile("bcr 15,0" ::: "memory")
-#define rmb()		asm volatile("bcr 15,0" ::: "memory")
 #define CPUINFO_PROC	{"vendor_id"}
 #endif
 
 #ifdef __sh__
-#if defined(__SH4A__) || defined(__SH5__)
-# define mb()		asm volatile("synco" ::: "memory")
-# define wmb()		asm volatile("synco" ::: "memory")
-# define rmb()		asm volatile("synco" ::: "memory")
-#else
-# define mb()		asm volatile("" ::: "memory")
-# define wmb()		asm volatile("" ::: "memory")
-# define rmb()		asm volatile("" ::: "memory")
-#endif
 #define CPUINFO_PROC	{"cpu type"}
 #endif
 
 #ifdef __hppa__
-#define mb()		asm volatile("" ::: "memory")
-#define wmb()		asm volatile("" ::: "memory")
-#define rmb()		asm volatile("" ::: "memory")
 #define CPUINFO_PROC	{"cpu"}
 #endif
 
 #ifdef __sparc__
-#ifdef __LP64__
-#define mb()		asm volatile("ba,pt %%xcc, 1f\n"	\
-				     "membar #StoreLoad\n"	\
-				     "1:\n":::"memory")
-#else
-#define mb()		asm volatile("":::"memory")
-#endif
-#define wmb()		asm volatile("":::"memory")
-#define rmb()		asm volatile("":::"memory")
 #define CPUINFO_PROC	{"cpu"}
 #endif
 
 #ifdef __alpha__
-#define mb()		asm volatile("mb" ::: "memory")
-#define wmb()		asm volatile("wmb" ::: "memory")
-#define rmb()		asm volatile("mb" ::: "memory")
 #define CPUINFO_PROC	{"cpu model"}
 #endif
 
 #ifdef __ia64__
-#define mb()		asm volatile ("mf" ::: "memory")
-#define wmb()		asm volatile ("mf" ::: "memory")
-#define rmb()		asm volatile ("mf" ::: "memory")
 #define cpu_relax()	asm volatile ("hint @pause" ::: "memory")
 #define CPUINFO_PROC	{"model name"}
 #endif
 
 #ifdef __arm__
-/*
- * Use the __kuser_memory_barrier helper in the CPU helper page. See
- * arch/arm/kernel/entry-armv.S in the kernel source for details.
- */
-#define mb()		((void(*)(void))0xffff0fa0)()
-#define wmb()		((void(*)(void))0xffff0fa0)()
-#define rmb()		((void(*)(void))0xffff0fa0)()
 #define CPUINFO_PROC	{"model name", "Processor"}
 #endif
 
 #ifdef __aarch64__
-#define mb()		asm volatile("dmb ish" ::: "memory")
-#define wmb()		asm volatile("dmb ishst" ::: "memory")
-#define rmb()		asm volatile("dmb ishld" ::: "memory")
 #define cpu_relax()	asm volatile("yield" ::: "memory")
 #endif
 
 #ifdef __mips__
-#define mb()		asm volatile(					\
-				".set	mips2\n\t"			\
-				"sync\n\t"				\
-				".set	mips0"				\
-				: /* no output */			\
-				: /* no input */			\
-				: "memory")
-#define wmb()	mb()
-#define rmb()	mb()
 #define CPUINFO_PROC	{"cpu model"}
 #endif
 
 #ifdef __arc__
-#define mb()		asm volatile("" ::: "memory")
-#define wmb()		asm volatile("" ::: "memory")
-#define rmb()		asm volatile("" ::: "memory")
 #define CPUINFO_PROC	{"Processor"}
 #endif
 
 #ifdef __metag__
-#define mb()		asm volatile("" ::: "memory")
-#define wmb()		asm volatile("" ::: "memory")
-#define rmb()		asm volatile("" ::: "memory")
 #define CPUINFO_PROC	{"CPU"}
 #endif
 
 #ifdef __xtensa__
-#define mb()		asm volatile("memw" ::: "memory")
-#define wmb()		asm volatile("memw" ::: "memory")
-#define rmb()		asm volatile("" ::: "memory")
 #define CPUINFO_PROC	{"core ID"}
 #endif
 
 #ifdef __tile__
-#define mb()		asm volatile ("mf" ::: "memory")
-#define wmb()		asm volatile ("mf" ::: "memory")
-#define rmb()		asm volatile ("mf" ::: "memory")
 #define cpu_relax()	asm volatile ("mfspr zero, PASS" ::: "memory")
 #define CPUINFO_PROC    {"model name"}
 #endif
 
-#define barrier() asm volatile ("" ::: "memory")
-
 #ifndef cpu_relax
 #define cpu_relax() barrier()
 #endif
diff --git a/tools/perf/perf.h b/tools/perf/perf.h
index e14bb637255c..4a5827fff799 100644
--- a/tools/perf/perf.h
+++ b/tools/perf/perf.h
@@ -54,16 +54,22 @@ struct record_opts {
 	bool	     period;
 	bool	     sample_intr_regs;
 	bool	     running_time;
+	bool	     full_auxtrace;
+	bool	     auxtrace_snapshot_mode;
 	unsigned int freq;
 	unsigned int mmap_pages;
+	unsigned int auxtrace_mmap_pages;
 	unsigned int user_freq;
 	u64          branch_stack;
 	u64	     default_interval;
 	u64	     user_interval;
+	size_t	     auxtrace_snapshot_size;
+	const char   *auxtrace_snapshot_opts;
 	bool	     sample_transaction;
 	unsigned     initial_delay;
 	bool         use_clockid;
 	clockid_t    clockid;
+	unsigned int proc_map_timeout;
 };
 
 struct option;
diff --git a/tools/perf/tests/Build b/tools/perf/tests/Build
index 6a8801b32017..ee41e705b2eb 100644
--- a/tools/perf/tests/Build
+++ b/tools/perf/tests/Build
@@ -3,9 +3,9 @@ perf-y += parse-events.o
 perf-y += dso-data.o
 perf-y += attr.o
 perf-y += vmlinux-kallsyms.o
-perf-y += open-syscall.o
-perf-y += open-syscall-all-cpus.o
-perf-y += open-syscall-tp-fields.o
+perf-y += openat-syscall.o
+perf-y += openat-syscall-all-cpus.o
+perf-y += openat-syscall-tp-fields.o
 perf-y += mmap-basic.o
 perf-y += perf-record.o
 perf-y += rdpmc.o
@@ -34,7 +34,7 @@ perf-y += kmod-path.o
 
 perf-$(CONFIG_X86) += perf-time-to-tsc.o
 
-ifeq ($(ARCH),$(filter $(ARCH),x86 arm))
+ifeq ($(ARCH),$(filter $(ARCH),x86 arm arm64))
 perf-$(CONFIG_DWARF_UNWIND) += dwarf-unwind.o
 endif
 
diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c
index 4f4098167112..87b9961646e4 100644
--- a/tools/perf/tests/builtin-test.c
+++ b/tools/perf/tests/builtin-test.c
@@ -23,12 +23,12 @@ static struct test {
 		.func = test__vmlinux_matches_kallsyms,
 	},
 	{
-		.desc = "detect open syscall event",
-		.func = test__open_syscall_event,
+		.desc = "detect openat syscall event",
+		.func = test__openat_syscall_event,
 	},
 	{
-		.desc = "detect open syscall event on all cpus",
-		.func = test__open_syscall_event_on_all_cpus,
+		.desc = "detect openat syscall event on all cpus",
+		.func = test__openat_syscall_event_on_all_cpus,
 	},
 	{
 		.desc = "read samples using the mmap interface",
@@ -73,8 +73,8 @@ static struct test {
 		.func = test__perf_evsel__tp_sched_test,
 	},
 	{
-		.desc = "Generate and check syscalls:sys_enter_open event fields",
-		.func = test__syscall_open_tp_fields,
+		.desc = "Generate and check syscalls:sys_enter_openat event fields",
+		.func = test__syscall_openat_tp_fields,
 	},
 	{
 		.desc = "struct perf_event_attr setup",
@@ -126,7 +126,7 @@ static struct test {
 		.desc = "Test parsing with no sample_id_all bit set",
 		.func = test__parse_no_sample_id_all,
 	},
-#if defined(__x86_64__) || defined(__i386__) || defined(__arm__)
+#if defined(__x86_64__) || defined(__i386__) || defined(__arm__) || defined(__aarch64__)
 #ifdef HAVE_DWARF_UNWIND_SUPPORT
 	{
 		.desc = "Test dwarf unwind",
@@ -219,7 +219,7 @@ static int run_test(struct test *test)
 	wait(&status);
 
 	if (WIFEXITED(status)) {
-		err = WEXITSTATUS(status);
+		err = (signed char)WEXITSTATUS(status);
 		pr_debug("test child finished with %d\n", err);
 	} else if (WIFSIGNALED(status)) {
 		err = -1;
diff --git a/tools/perf/tests/code-reading.c b/tools/perf/tests/code-reading.c
index f671ec37a7c4..22f8a00446e1 100644
--- a/tools/perf/tests/code-reading.c
+++ b/tools/perf/tests/code-reading.c
@@ -248,6 +248,7 @@ static int process_sample_event(struct machine *machine,
 	struct perf_sample sample;
 	struct thread *thread;
 	u8 cpumode;
+	int ret;
 
 	if (perf_evlist__parse_sample(evlist, event, &sample)) {
 		pr_debug("perf_evlist__parse_sample failed\n");
@@ -262,7 +263,9 @@ static int process_sample_event(struct machine *machine,
 
 	cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
 
-	return read_object_code(sample.ip, READLEN, cpumode, thread, state);
+	ret = read_object_code(sample.ip, READLEN, cpumode, thread, state);
+	thread__put(thread);
+	return ret;
 }
 
 static int process_event(struct machine *machine, struct perf_evlist *evlist,
@@ -448,7 +451,7 @@ static int do_test_code_reading(bool try_kcore)
 	}
 
 	ret = perf_event__synthesize_thread_map(NULL, threads,
-						perf_event__process, machine, false);
+						perf_event__process, machine, false, 500);
 	if (ret < 0) {
 		pr_debug("perf_event__synthesize_thread_map failed\n");
 		goto out_err;
@@ -457,13 +460,13 @@ static int do_test_code_reading(bool try_kcore)
 	thread = machine__findnew_thread(machine, pid, pid);
 	if (!thread) {
 		pr_debug("machine__findnew_thread failed\n");
-		goto out_err;
+		goto out_put;
 	}
 
 	cpus = cpu_map__new(NULL);
 	if (!cpus) {
 		pr_debug("cpu_map__new failed\n");
-		goto out_err;
+		goto out_put;
 	}
 
 	while (1) {
@@ -472,7 +475,7 @@ static int do_test_code_reading(bool try_kcore)
 		evlist = perf_evlist__new();
 		if (!evlist) {
 			pr_debug("perf_evlist__new failed\n");
-			goto out_err;
+			goto out_put;
 		}
 
 		perf_evlist__set_maps(evlist, cpus, threads);
@@ -482,10 +485,10 @@ static int do_test_code_reading(bool try_kcore)
 		else
 			str = "cycles";
 		pr_debug("Parsing event '%s'\n", str);
-		ret = parse_events(evlist, str);
+		ret = parse_events(evlist, str, NULL);
 		if (ret < 0) {
 			pr_debug("parse_events failed\n");
-			goto out_err;
+			goto out_put;
 		}
 
 		perf_evlist__config(evlist, &opts);
@@ -506,7 +509,7 @@ static int do_test_code_reading(bool try_kcore)
 				continue;
 			}
 			pr_debug("perf_evlist__open failed\n");
-			goto out_err;
+			goto out_put;
 		}
 		break;
 	}
@@ -514,7 +517,7 @@ static int do_test_code_reading(bool try_kcore)
 	ret = perf_evlist__mmap(evlist, UINT_MAX, false);
 	if (ret < 0) {
 		pr_debug("perf_evlist__mmap failed\n");
-		goto out_err;
+		goto out_put;
 	}
 
 	perf_evlist__enable(evlist);
@@ -525,7 +528,7 @@ static int do_test_code_reading(bool try_kcore)
 
 	ret = process_events(machine, evlist, &state);
 	if (ret < 0)
-		goto out_err;
+		goto out_put;
 
 	if (!have_vmlinux && !have_kcore && !try_kcore)
 		err = TEST_CODE_READING_NO_KERNEL_OBJ;
@@ -535,7 +538,10 @@ static int do_test_code_reading(bool try_kcore)
 		err = TEST_CODE_READING_NO_ACCESS;
 	else
 		err = TEST_CODE_READING_OK;
+out_put:
+	thread__put(thread);
 out_err:
+
 	if (evlist) {
 		perf_evlist__delete(evlist);
 	} else {
diff --git a/tools/perf/tests/dso-data.c b/tools/perf/tests/dso-data.c
index 513e5febbe5a..a218aeaf56a0 100644
--- a/tools/perf/tests/dso-data.c
+++ b/tools/perf/tests/dso-data.c
@@ -99,6 +99,17 @@ struct test_data_offset offsets[] = {
 	},
 };
 
+/* move it from util/dso.c for compatibility */
+static int dso__data_fd(struct dso *dso, struct machine *machine)
+{
+	int fd = dso__data_get_fd(dso, machine);
+
+	if (fd >= 0)
+		dso__data_put_fd(dso);
+
+	return fd;
+}
+
 int test__dso_data(void)
 {
 	struct machine machine;
@@ -155,7 +166,7 @@ int test__dso_data(void)
 		free(buf);
 	}
 
-	dso__delete(dso);
+	dso__put(dso);
 	unlink(file);
 	return 0;
 }
@@ -215,7 +226,7 @@ static void dsos__delete(int cnt)
 		struct dso *dso = dsos[i];
 
 		unlink(dso->name);
-		dso__delete(dso);
+		dso__put(dso);
 	}
 
 	free(dsos);
diff --git a/tools/perf/tests/dwarf-unwind.c b/tools/perf/tests/dwarf-unwind.c
index 0bf06bec68c7..40b36c462427 100644
--- a/tools/perf/tests/dwarf-unwind.c
+++ b/tools/perf/tests/dwarf-unwind.c
@@ -28,7 +28,7 @@ static int init_live_machine(struct machine *machine)
 	pid_t pid = getpid();
 
 	return perf_event__synthesize_mmap_events(NULL, &event, pid, pid,
-						  mmap_handler, machine, true);
+						  mmap_handler, machine, true, 500);
 }
 
 #define MAX_STACK 8
@@ -170,6 +170,7 @@ int test__dwarf_unwind(void)
 	}
 
 	err = krava_1(thread);
+	thread__put(thread);
 
  out:
 	machine__delete_threads(machine);
diff --git a/tools/perf/tests/evsel-roundtrip-name.c b/tools/perf/tests/evsel-roundtrip-name.c
index b8d8341b383e..3fa715987a5e 100644
--- a/tools/perf/tests/evsel-roundtrip-name.c
+++ b/tools/perf/tests/evsel-roundtrip-name.c
@@ -23,7 +23,7 @@ static int perf_evsel__roundtrip_cache_name_test(void)
 			for (i = 0; i < PERF_COUNT_HW_CACHE_RESULT_MAX; i++) {
 				__perf_evsel__hw_cache_type_op_res_name(type, op, i,
 									name, sizeof(name));
-				err = parse_events(evlist, name);
+				err = parse_events(evlist, name, NULL);
 				if (err)
 					ret = err;
 			}
@@ -71,7 +71,7 @@ static int __perf_evsel__name_array_test(const char *names[], int nr_names)
                 return -ENOMEM;
 
 	for (i = 0; i < nr_names; ++i) {
-		err = parse_events(evlist, names[i]);
+		err = parse_events(evlist, names[i], NULL);
 		if (err) {
 			pr_debug("failed to parse event '%s', err %d\n",
 				 names[i], err);
diff --git a/tools/perf/tests/hists_common.c b/tools/perf/tests/hists_common.c
index a62c09134516..ce80b274b097 100644
--- a/tools/perf/tests/hists_common.c
+++ b/tools/perf/tests/hists_common.c
@@ -96,6 +96,7 @@ struct machine *setup_fake_machine(struct machines *machines)
 			goto out;
 
 		thread__set_comm(thread, fake_threads[i].comm, 0);
+		thread__put(thread);
 	}
 
 	for (i = 0; i < ARRAY_SIZE(fake_mmap_info); i++) {
@@ -120,8 +121,7 @@ struct machine *setup_fake_machine(struct machines *machines)
 		size_t k;
 		struct dso *dso;
 
-		dso = __dsos__findnew(&machine->user_dsos,
-				      fake_symbols[i].dso_name);
+		dso = machine__findnew_dso(machine, fake_symbols[i].dso_name);
 		if (dso == NULL)
 			goto out;
 
@@ -134,11 +134,15 @@ struct machine *setup_fake_machine(struct machines *machines)
 
 			sym = symbol__new(fsym->start, fsym->length,
 					  STB_GLOBAL, fsym->name);
-			if (sym == NULL)
+			if (sym == NULL) {
+				dso__put(dso);
 				goto out;
+			}
 
 			symbols__insert(&dso->symbols[MAP__FUNCTION], sym);
 		}
+
+		dso__put(dso);
 	}
 
 	return machine;
diff --git a/tools/perf/tests/hists_cumulate.c b/tools/perf/tests/hists_cumulate.c
index 18619966454c..7d82c8be5e36 100644
--- a/tools/perf/tests/hists_cumulate.c
+++ b/tools/perf/tests/hists_cumulate.c
@@ -87,6 +87,8 @@ static int add_hist_entries(struct hists *hists, struct machine *machine)
 			},
 		};
 		struct hist_entry_iter iter = {
+			.evsel = evsel,
+			.sample	= &sample,
 			.hide_unresolved = false,
 		};
 
@@ -104,9 +106,11 @@ static int add_hist_entries(struct hists *hists, struct machine *machine)
 						  &sample) < 0)
 			goto out;
 
-		if (hist_entry_iter__add(&iter, &al, evsel, &sample,
-					 PERF_MAX_STACK_DEPTH, NULL) < 0)
+		if (hist_entry_iter__add(&iter, &al, PERF_MAX_STACK_DEPTH,
+					 NULL) < 0) {
+			addr_location__put(&al);
 			goto out;
+		}
 
 		fake_samples[i].thread = al.thread;
 		fake_samples[i].map = al.map;
@@ -695,7 +699,7 @@ int test__hists_cumulate(void)
 
 	TEST_ASSERT_VAL("No memory", evlist);
 
-	err = parse_events(evlist, "cpu-clock");
+	err = parse_events(evlist, "cpu-clock", NULL);
 	if (err)
 		goto out;
 
diff --git a/tools/perf/tests/hists_filter.c b/tools/perf/tests/hists_filter.c
index 59e53db7914c..ce48775e6ada 100644
--- a/tools/perf/tests/hists_filter.c
+++ b/tools/perf/tests/hists_filter.c
@@ -63,6 +63,8 @@ static int add_hist_entries(struct perf_evlist *evlist,
 				},
 			};
 			struct hist_entry_iter iter = {
+				.evsel = evsel,
+				.sample = &sample,
 				.ops = &hist_iter_normal,
 				.hide_unresolved = false,
 			};
@@ -81,9 +83,11 @@ static int add_hist_entries(struct perf_evlist *evlist,
 							  &sample) < 0)
 				goto out;
 
-			if (hist_entry_iter__add(&iter, &al, evsel, &sample,
-						 PERF_MAX_STACK_DEPTH, NULL) < 0)
+			if (hist_entry_iter__add(&iter, &al,
+						 PERF_MAX_STACK_DEPTH, NULL) < 0) {
+				addr_location__put(&al);
 				goto out;
+			}
 
 			fake_samples[i].thread = al.thread;
 			fake_samples[i].map = al.map;
@@ -108,10 +112,10 @@ int test__hists_filter(void)
 
 	TEST_ASSERT_VAL("No memory", evlist);
 
-	err = parse_events(evlist, "cpu-clock");
+	err = parse_events(evlist, "cpu-clock", NULL);
 	if (err)
 		goto out;
-	err = parse_events(evlist, "task-clock");
+	err = parse_events(evlist, "task-clock", NULL);
 	if (err)
 		goto out;
 
diff --git a/tools/perf/tests/hists_link.c b/tools/perf/tests/hists_link.c
index 278ba8344c23..8c102b011424 100644
--- a/tools/perf/tests/hists_link.c
+++ b/tools/perf/tests/hists_link.c
@@ -91,8 +91,10 @@ static int add_hist_entries(struct perf_evlist *evlist, struct machine *machine)
 
 			he = __hists__add_entry(hists, &al, NULL,
 						NULL, NULL, 1, 1, 0, true);
-			if (he == NULL)
+			if (he == NULL) {
+				addr_location__put(&al);
 				goto out;
+			}
 
 			fake_common_samples[k].thread = al.thread;
 			fake_common_samples[k].map = al.map;
@@ -115,8 +117,10 @@ static int add_hist_entries(struct perf_evlist *evlist, struct machine *machine)
 
 			he = __hists__add_entry(hists, &al, NULL,
 						NULL, NULL, 1, 1, 0, true);
-			if (he == NULL)
+			if (he == NULL) {
+				addr_location__put(&al);
 				goto out;
+			}
 
 			fake_samples[i][k].thread = al.thread;
 			fake_samples[i][k].map = al.map;
@@ -282,10 +286,10 @@ int test__hists_link(void)
 	if (evlist == NULL)
                 return -ENOMEM;
 
-	err = parse_events(evlist, "cpu-clock");
+	err = parse_events(evlist, "cpu-clock", NULL);
 	if (err)
 		goto out;
-	err = parse_events(evlist, "task-clock");
+	err = parse_events(evlist, "task-clock", NULL);
 	if (err)
 		goto out;
 
diff --git a/tools/perf/tests/hists_output.c b/tools/perf/tests/hists_output.c
index b52c9faea224..adbebc852cc8 100644
--- a/tools/perf/tests/hists_output.c
+++ b/tools/perf/tests/hists_output.c
@@ -57,6 +57,8 @@ static int add_hist_entries(struct hists *hists, struct machine *machine)
 			},
 		};
 		struct hist_entry_iter iter = {
+			.evsel = evsel,
+			.sample = &sample,
 			.ops = &hist_iter_normal,
 			.hide_unresolved = false,
 		};
@@ -70,9 +72,11 @@ static int add_hist_entries(struct hists *hists, struct machine *machine)
 						  &sample) < 0)
 			goto out;
 
-		if (hist_entry_iter__add(&iter, &al, evsel, &sample,
-					 PERF_MAX_STACK_DEPTH, NULL) < 0)
+		if (hist_entry_iter__add(&iter, &al, PERF_MAX_STACK_DEPTH,
+					 NULL) < 0) {
+			addr_location__put(&al);
 			goto out;
+		}
 
 		fake_samples[i].thread = al.thread;
 		fake_samples[i].map = al.map;
@@ -590,7 +594,7 @@ int test__hists_output(void)
 
 	TEST_ASSERT_VAL("No memory", evlist);
 
-	err = parse_events(evlist, "cpu-clock");
+	err = parse_events(evlist, "cpu-clock", NULL);
 	if (err)
 		goto out;
 
diff --git a/tools/perf/tests/keep-tracking.c b/tools/perf/tests/keep-tracking.c
index 7a5ab7b0b8f6..5b171d1e338b 100644
--- a/tools/perf/tests/keep-tracking.c
+++ b/tools/perf/tests/keep-tracking.c
@@ -78,8 +78,8 @@ int test__keep_tracking(void)
 
 	perf_evlist__set_maps(evlist, cpus, threads);
 
-	CHECK__(parse_events(evlist, "dummy:u"));
-	CHECK__(parse_events(evlist, "cycles:u"));
+	CHECK__(parse_events(evlist, "dummy:u", NULL));
+	CHECK__(parse_events(evlist, "cycles:u", NULL));
 
 	perf_evlist__config(evlist, &opts);
 
diff --git a/tools/perf/tests/kmod-path.c b/tools/perf/tests/kmod-path.c
index e8d7cbb9320c..08c433b4bf4f 100644
--- a/tools/perf/tests/kmod-path.c
+++ b/tools/perf/tests/kmod-path.c
@@ -34,9 +34,21 @@ static int test(const char *path, bool alloc_name, bool alloc_ext,
 	return 0;
 }
 
+static int test_is_kernel_module(const char *path, int cpumode, bool expect)
+{
+	TEST_ASSERT_VAL("is_kernel_module",
+			(!!is_kernel_module(path, cpumode)) == (!!expect));
+	pr_debug("%s (cpumode: %d) - is_kernel_module: %s\n",
+			path, cpumode, expect ? "true" : "false");
+	return 0;
+}
+
 #define T(path, an, ae, k, c, n, e) \
 	TEST_ASSERT_VAL("failed", !test(path, an, ae, k, c, n, e))
 
+#define M(path, c, e) \
+	TEST_ASSERT_VAL("failed", !test_is_kernel_module(path, c, e))
+
 int test__kmod_path__parse(void)
 {
 	/* path                alloc_name  alloc_ext   kmod  comp   name     ext */
@@ -44,30 +56,90 @@ int test__kmod_path__parse(void)
 	T("/xxxx/xxxx/x-x.ko", false     , true      , true, false, NULL   , NULL);
 	T("/xxxx/xxxx/x-x.ko", true      , false     , true, false, "[x_x]", NULL);
 	T("/xxxx/xxxx/x-x.ko", false     , false     , true, false, NULL   , NULL);
+	M("/xxxx/xxxx/x-x.ko", PERF_RECORD_MISC_CPUMODE_UNKNOWN, true);
+	M("/xxxx/xxxx/x-x.ko", PERF_RECORD_MISC_KERNEL, true);
+	M("/xxxx/xxxx/x-x.ko", PERF_RECORD_MISC_USER, false);
 
 	/* path                alloc_name  alloc_ext   kmod  comp  name   ext */
 	T("/xxxx/xxxx/x.ko.gz", true     , true      , true, true, "[x]", "gz");
 	T("/xxxx/xxxx/x.ko.gz", false    , true      , true, true, NULL , "gz");
 	T("/xxxx/xxxx/x.ko.gz", true     , false     , true, true, "[x]", NULL);
 	T("/xxxx/xxxx/x.ko.gz", false    , false     , true, true, NULL , NULL);
+	M("/xxxx/xxxx/x.ko.gz", PERF_RECORD_MISC_CPUMODE_UNKNOWN, true);
+	M("/xxxx/xxxx/x.ko.gz", PERF_RECORD_MISC_KERNEL, true);
+	M("/xxxx/xxxx/x.ko.gz", PERF_RECORD_MISC_USER, false);
 
 	/* path              alloc_name  alloc_ext  kmod   comp  name    ext */
 	T("/xxxx/xxxx/x.gz", true      , true     , false, true, "x.gz" ,"gz");
 	T("/xxxx/xxxx/x.gz", false     , true     , false, true, NULL   ,"gz");
 	T("/xxxx/xxxx/x.gz", true      , false    , false, true, "x.gz" , NULL);
 	T("/xxxx/xxxx/x.gz", false     , false    , false, true, NULL   , NULL);
+	M("/xxxx/xxxx/x.gz", PERF_RECORD_MISC_CPUMODE_UNKNOWN, false);
+	M("/xxxx/xxxx/x.gz", PERF_RECORD_MISC_KERNEL, false);
+	M("/xxxx/xxxx/x.gz", PERF_RECORD_MISC_USER, false);
 
 	/* path   alloc_name  alloc_ext  kmod   comp  name     ext */
 	T("x.gz", true      , true     , false, true, "x.gz", "gz");
 	T("x.gz", false     , true     , false, true, NULL  , "gz");
 	T("x.gz", true      , false    , false, true, "x.gz", NULL);
 	T("x.gz", false     , false    , false, true, NULL  , NULL);
+	M("x.gz", PERF_RECORD_MISC_CPUMODE_UNKNOWN, false);
+	M("x.gz", PERF_RECORD_MISC_KERNEL, false);
+	M("x.gz", PERF_RECORD_MISC_USER, false);
 
 	/* path      alloc_name  alloc_ext  kmod  comp  name  ext */
 	T("x.ko.gz", true      , true     , true, true, "[x]", "gz");
 	T("x.ko.gz", false     , true     , true, true, NULL , "gz");
 	T("x.ko.gz", true      , false    , true, true, "[x]", NULL);
 	T("x.ko.gz", false     , false    , true, true, NULL , NULL);
+	M("x.ko.gz", PERF_RECORD_MISC_CPUMODE_UNKNOWN, true);
+	M("x.ko.gz", PERF_RECORD_MISC_KERNEL, true);
+	M("x.ko.gz", PERF_RECORD_MISC_USER, false);
+
+	/* path            alloc_name  alloc_ext  kmod  comp   name             ext */
+	T("[test_module]", true      , true     , true, false, "[test_module]", NULL);
+	T("[test_module]", false     , true     , true, false, NULL           , NULL);
+	T("[test_module]", true      , false    , true, false, "[test_module]", NULL);
+	T("[test_module]", false     , false    , true, false, NULL           , NULL);
+	M("[test_module]", PERF_RECORD_MISC_CPUMODE_UNKNOWN, true);
+	M("[test_module]", PERF_RECORD_MISC_KERNEL, true);
+	M("[test_module]", PERF_RECORD_MISC_USER, false);
+
+	/* path            alloc_name  alloc_ext  kmod  comp   name             ext */
+	T("[test.module]", true      , true     , true, false, "[test.module]", NULL);
+	T("[test.module]", false     , true     , true, false, NULL           , NULL);
+	T("[test.module]", true      , false    , true, false, "[test.module]", NULL);
+	T("[test.module]", false     , false    , true, false, NULL           , NULL);
+	M("[test.module]", PERF_RECORD_MISC_CPUMODE_UNKNOWN, true);
+	M("[test.module]", PERF_RECORD_MISC_KERNEL, true);
+	M("[test.module]", PERF_RECORD_MISC_USER, false);
+
+	/* path     alloc_name  alloc_ext  kmod   comp   name      ext */
+	T("[vdso]", true      , true     , false, false, "[vdso]", NULL);
+	T("[vdso]", false     , true     , false, false, NULL    , NULL);
+	T("[vdso]", true      , false    , false, false, "[vdso]", NULL);
+	T("[vdso]", false     , false    , false, false, NULL    , NULL);
+	M("[vdso]", PERF_RECORD_MISC_CPUMODE_UNKNOWN, false);
+	M("[vdso]", PERF_RECORD_MISC_KERNEL, false);
+	M("[vdso]", PERF_RECORD_MISC_USER, false);
+
+	/* path         alloc_name  alloc_ext  kmod   comp   name          ext */
+	T("[vsyscall]", true      , true     , false, false, "[vsyscall]", NULL);
+	T("[vsyscall]", false     , true     , false, false, NULL        , NULL);
+	T("[vsyscall]", true      , false    , false, false, "[vsyscall]", NULL);
+	T("[vsyscall]", false     , false    , false, false, NULL        , NULL);
+	M("[vsyscall]", PERF_RECORD_MISC_CPUMODE_UNKNOWN, false);
+	M("[vsyscall]", PERF_RECORD_MISC_KERNEL, false);
+	M("[vsyscall]", PERF_RECORD_MISC_USER, false);
+
+	/* path                alloc_name  alloc_ext  kmod   comp   name      ext */
+	T("[kernel.kallsyms]", true      , true     , false, false, "[kernel.kallsyms]", NULL);
+	T("[kernel.kallsyms]", false     , true     , false, false, NULL               , NULL);
+	T("[kernel.kallsyms]", true      , false    , false, false, "[kernel.kallsyms]", NULL);
+	T("[kernel.kallsyms]", false     , false    , false, false, NULL               , NULL);
+	M("[kernel.kallsyms]", PERF_RECORD_MISC_CPUMODE_UNKNOWN, false);
+	M("[kernel.kallsyms]", PERF_RECORD_MISC_KERNEL, false);
+	M("[kernel.kallsyms]", PERF_RECORD_MISC_USER, false);
 
 	return 0;
 }
diff --git a/tools/perf/tests/make b/tools/perf/tests/make
index bff85324f799..65280d28662e 100644
--- a/tools/perf/tests/make
+++ b/tools/perf/tests/make
@@ -32,6 +32,7 @@ make_no_backtrace   := NO_BACKTRACE=1
 make_no_libnuma     := NO_LIBNUMA=1
 make_no_libaudit    := NO_LIBAUDIT=1
 make_no_libbionic   := NO_LIBBIONIC=1
+make_no_auxtrace    := NO_AUXTRACE=1
 make_tags           := tags
 make_cscope         := cscope
 make_help           := help
@@ -52,7 +53,7 @@ make_static         := LDFLAGS=-static
 make_minimal        := NO_LIBPERL=1 NO_LIBPYTHON=1 NO_NEWT=1 NO_GTK2=1
 make_minimal        += NO_DEMANGLE=1 NO_LIBELF=1 NO_LIBUNWIND=1 NO_BACKTRACE=1
 make_minimal        += NO_LIBNUMA=1 NO_LIBAUDIT=1 NO_LIBBIONIC=1
-make_minimal        += NO_LIBDW_DWARF_UNWIND=1
+make_minimal        += NO_LIBDW_DWARF_UNWIND=1 NO_AUXTRACE=1
 
 # $(run) contains all available tests
 run := make_pure
@@ -74,6 +75,7 @@ run += make_no_backtrace
 run += make_no_libnuma
 run += make_no_libaudit
 run += make_no_libbionic
+run += make_no_auxtrace
 run += make_help
 run += make_doc
 run += make_perf_o
@@ -223,7 +225,19 @@ tarpkg:
 	echo "- $@: $$cmd" && echo $$cmd > $@ && \
 	( eval $$cmd ) >> $@ 2>&1
 
-all: $(run) $(run_O) tarpkg
+make_kernelsrc:
+	@echo " - make -C <kernelsrc> tools/perf"
+	$(call clean); \
+	(make -C ../.. tools/perf) > $@ 2>&1 && \
+	test -x perf && rm -f $@ || (cat $@ ; false)
+
+make_kernelsrc_tools:
+	@echo " - make -C <kernelsrc>/tools perf"
+	$(call clean); \
+	(make -C ../../tools perf) > $@ 2>&1 && \
+	test -x perf && rm -f $@ || (cat $@ ; false)
+
+all: $(run) $(run_O) tarpkg make_kernelsrc make_kernelsrc_tools
 	@echo OK
 
 out: $(run_O)
diff --git a/tools/perf/tests/mmap-basic.c b/tools/perf/tests/mmap-basic.c
index 9b9622a33932..5855cf471210 100644
--- a/tools/perf/tests/mmap-basic.c
+++ b/tools/perf/tests/mmap-basic.c
@@ -23,10 +23,8 @@ int test__basic_mmap(void)
 	struct cpu_map *cpus;
 	struct perf_evlist *evlist;
 	cpu_set_t cpu_set;
-	const char *syscall_names[] = { "getsid", "getppid", "getpgrp",
-					"getpgid", };
-	pid_t (*syscalls[])(void) = { (void *)getsid, getppid, getpgrp,
-				      (void*)getpgid };
+	const char *syscall_names[] = { "getsid", "getppid", "getpgid", };
+	pid_t (*syscalls[])(void) = { (void *)getsid, getppid, (void*)getpgid };
 #define nsyscalls ARRAY_SIZE(syscall_names)
 	unsigned int nr_events[nsyscalls],
 		     expected_nr_events[nsyscalls], i, j;
diff --git a/tools/perf/tests/mmap-thread-lookup.c b/tools/perf/tests/mmap-thread-lookup.c
index 2113f1c8611f..7f48efa7e295 100644
--- a/tools/perf/tests/mmap-thread-lookup.c
+++ b/tools/perf/tests/mmap-thread-lookup.c
@@ -129,7 +129,7 @@ static int synth_all(struct machine *machine)
 {
 	return perf_event__synthesize_threads(NULL,
 					      perf_event__process,
-					      machine, 0);
+					      machine, 0, 500);
 }
 
 static int synth_process(struct machine *machine)
@@ -141,7 +141,7 @@ static int synth_process(struct machine *machine)
 
 	err = perf_event__synthesize_thread_map(NULL, map,
 						perf_event__process,
-						machine, 0);
+						machine, 0, 500);
 
 	thread_map__delete(map);
 	return err;
@@ -191,6 +191,8 @@ static int mmap_events(synth_cb synth)
 				      PERF_RECORD_MISC_USER, MAP__FUNCTION,
 				      (unsigned long) (td->map + 1), &al);
 
+		thread__put(thread);
+
 		if (!al.map) {
 			pr_debug("failed, couldn't find map\n");
 			err = -1;
diff --git a/tools/perf/tests/open-syscall-all-cpus.c b/tools/perf/tests/openat-syscall-all-cpus.c
index 3ec885c48f8f..9a7a116e09b8 100644
--- a/tools/perf/tests/open-syscall-all-cpus.c
+++ b/tools/perf/tests/openat-syscall-all-cpus.c
@@ -3,13 +3,14 @@
 #include "thread_map.h"
 #include "cpumap.h"
 #include "debug.h"
+#include "stat.h"
 
-int test__open_syscall_event_on_all_cpus(void)
+int test__openat_syscall_event_on_all_cpus(void)
 {
 	int err = -1, fd, cpu;
 	struct cpu_map *cpus;
 	struct perf_evsel *evsel;
-	unsigned int nr_open_calls = 111, i;
+	unsigned int nr_openat_calls = 111, i;
 	cpu_set_t cpu_set;
 	struct thread_map *threads = thread_map__new(-1, getpid(), UINT_MAX);
 	char sbuf[STRERR_BUFSIZE];
@@ -27,7 +28,7 @@ int test__open_syscall_event_on_all_cpus(void)
 
 	CPU_ZERO(&cpu_set);
 
-	evsel = perf_evsel__newtp("syscalls", "sys_enter_open");
+	evsel = perf_evsel__newtp("syscalls", "sys_enter_openat");
 	if (evsel == NULL) {
 		if (tracefs_configured())
 			pr_debug("is tracefs mounted on /sys/kernel/tracing?\n");
@@ -46,7 +47,7 @@ int test__open_syscall_event_on_all_cpus(void)
 	}
 
 	for (cpu = 0; cpu < cpus->nr; ++cpu) {
-		unsigned int ncalls = nr_open_calls + cpu;
+		unsigned int ncalls = nr_openat_calls + cpu;
 		/*
 		 * XXX eventually lift this restriction in a way that
 		 * keeps perf building on older glibc installations
@@ -66,7 +67,7 @@ int test__open_syscall_event_on_all_cpus(void)
 			goto out_close_fd;
 		}
 		for (i = 0; i < ncalls; ++i) {
-			fd = open("/etc/passwd", O_RDONLY);
+			fd = openat(0, "/etc/passwd", O_RDONLY);
 			close(fd);
 		}
 		CPU_CLR(cpus->map[cpu], &cpu_set);
@@ -96,7 +97,7 @@ int test__open_syscall_event_on_all_cpus(void)
 			break;
 		}
 
-		expected = nr_open_calls + cpu;
+		expected = nr_openat_calls + cpu;
 		if (evsel->counts->cpu[cpu].val != expected) {
 			pr_debug("perf_evsel__read_on_cpu: expected to intercept %d calls on cpu %d, got %" PRIu64 "\n",
 				 expected, cpus->map[cpu], evsel->counts->cpu[cpu].val);
diff --git a/tools/perf/tests/open-syscall-tp-fields.c b/tools/perf/tests/openat-syscall-tp-fields.c
index 127dcae0b760..6245221479d7 100644
--- a/tools/perf/tests/open-syscall-tp-fields.c
+++ b/tools/perf/tests/openat-syscall-tp-fields.c
@@ -5,7 +5,7 @@
 #include "tests.h"
 #include "debug.h"
 
-int test__syscall_open_tp_fields(void)
+int test__syscall_openat_tp_fields(void)
 {
 	struct record_opts opts = {
 		.target = {
@@ -29,7 +29,7 @@ int test__syscall_open_tp_fields(void)
 		goto out;
 	}
 
-	evsel = perf_evsel__newtp("syscalls", "sys_enter_open");
+	evsel = perf_evsel__newtp("syscalls", "sys_enter_openat");
 	if (evsel == NULL) {
 		pr_debug("%s: perf_evsel__newtp\n", __func__);
 		goto out_delete_evlist;
@@ -66,7 +66,7 @@ int test__syscall_open_tp_fields(void)
 	/*
 	 * Generate the event:
 	 */
-	open(filename, flags);
+	openat(AT_FDCWD, filename, flags);
 
 	while (1) {
 		int before = nr_events;
diff --git a/tools/perf/tests/open-syscall.c b/tools/perf/tests/openat-syscall.c
index 07aa319bf334..9f9491bb8e48 100644
--- a/tools/perf/tests/open-syscall.c
+++ b/tools/perf/tests/openat-syscall.c
@@ -3,11 +3,11 @@
 #include "debug.h"
 #include "tests.h"
 
-int test__open_syscall_event(void)
+int test__openat_syscall_event(void)
 {
 	int err = -1, fd;
 	struct perf_evsel *evsel;
-	unsigned int nr_open_calls = 111, i;
+	unsigned int nr_openat_calls = 111, i;
 	struct thread_map *threads = thread_map__new(-1, getpid(), UINT_MAX);
 	char sbuf[STRERR_BUFSIZE];
 
@@ -16,7 +16,7 @@ int test__open_syscall_event(void)
 		return -1;
 	}
 
-	evsel = perf_evsel__newtp("syscalls", "sys_enter_open");
+	evsel = perf_evsel__newtp("syscalls", "sys_enter_openat");
 	if (evsel == NULL) {
 		if (tracefs_configured())
 			pr_debug("is tracefs mounted on /sys/kernel/tracing?\n");
@@ -34,8 +34,8 @@ int test__open_syscall_event(void)
 		goto out_evsel_delete;
 	}
 
-	for (i = 0; i < nr_open_calls; ++i) {
-		fd = open("/etc/passwd", O_RDONLY);
+	for (i = 0; i < nr_openat_calls; ++i) {
+		fd = openat(0, "/etc/passwd", O_RDONLY);
 		close(fd);
 	}
 
@@ -44,9 +44,9 @@ int test__open_syscall_event(void)
 		goto out_close_fd;
 	}
 
-	if (evsel->counts->cpu[0].val != nr_open_calls) {
+	if (evsel->counts->cpu[0].val != nr_openat_calls) {
 		pr_debug("perf_evsel__read_on_cpu: expected to intercept %d calls, got %" PRIu64 "\n",
-			 nr_open_calls, evsel->counts->cpu[0].val);
+			 nr_openat_calls, evsel->counts->cpu[0].val);
 		goto out_close_fd;
 	}
 
diff --git a/tools/perf/tests/parse-events.c b/tools/perf/tests/parse-events.c
index 3de744961739..d76963f7ad3d 100644
--- a/tools/perf/tests/parse-events.c
+++ b/tools/perf/tests/parse-events.c
@@ -427,7 +427,7 @@ static int test__checkevent_list(struct perf_evlist *evlist)
 	TEST_ASSERT_VAL("wrong exclude_hv", !evsel->attr.exclude_hv);
 	TEST_ASSERT_VAL("wrong precise_ip", !evsel->attr.precise_ip);
 
-	/* syscalls:sys_enter_open:k */
+	/* syscalls:sys_enter_openat:k */
 	evsel = perf_evsel__next(evsel);
 	TEST_ASSERT_VAL("wrong type", PERF_TYPE_TRACEPOINT == evsel->attr.type);
 	TEST_ASSERT_VAL("wrong sample_type",
@@ -665,7 +665,7 @@ static int test__group3(struct perf_evlist *evlist __maybe_unused)
 	TEST_ASSERT_VAL("wrong number of entries", 5 == evlist->nr_entries);
 	TEST_ASSERT_VAL("wrong number of groups", 2 == evlist->nr_groups);
 
-	/* group1 syscalls:sys_enter_open:H */
+	/* group1 syscalls:sys_enter_openat:H */
 	evsel = leader = perf_evlist__first(evlist);
 	TEST_ASSERT_VAL("wrong type", PERF_TYPE_TRACEPOINT == evsel->attr.type);
 	TEST_ASSERT_VAL("wrong sample_type",
@@ -1293,7 +1293,7 @@ struct evlist_test {
 
 static struct evlist_test test__events[] = {
 	{
-		.name  = "syscalls:sys_enter_open",
+		.name  = "syscalls:sys_enter_openat",
 		.check = test__checkevent_tracepoint,
 		.id    = 0,
 	},
@@ -1353,7 +1353,7 @@ static struct evlist_test test__events[] = {
 		.id    = 11,
 	},
 	{
-		.name  = "syscalls:sys_enter_open:k",
+		.name  = "syscalls:sys_enter_openat:k",
 		.check = test__checkevent_tracepoint_modifier,
 		.id    = 12,
 	},
@@ -1408,7 +1408,7 @@ static struct evlist_test test__events[] = {
 		.id    = 22,
 	},
 	{
-		.name  = "r1,syscalls:sys_enter_open:k,1:1:hp",
+		.name  = "r1,syscalls:sys_enter_openat:k,1:1:hp",
 		.check = test__checkevent_list,
 		.id    = 23,
 	},
@@ -1443,7 +1443,7 @@ static struct evlist_test test__events[] = {
 		.id    = 29,
 	},
 	{
-		.name  = "group1{syscalls:sys_enter_open:H,cycles:kppp},group2{cycles,1:3}:G,instructions:u",
+		.name  = "group1{syscalls:sys_enter_openat:H,cycles:kppp},group2{cycles,1:3}:G,instructions:u",
 		.check = test__group3,
 		.id    = 30,
 	},
@@ -1571,7 +1571,7 @@ static int test_event(struct evlist_test *e)
 	if (evlist == NULL)
 		return -ENOMEM;
 
-	ret = parse_events(evlist, e->name);
+	ret = parse_events(evlist, e->name, NULL);
 	if (ret) {
 		pr_debug("failed to parse event '%s', err %d\n",
 			 e->name, ret);
diff --git a/tools/perf/tests/perf-time-to-tsc.c b/tools/perf/tests/perf-time-to-tsc.c
index f238442b238a..5f49484f1abc 100644
--- a/tools/perf/tests/perf-time-to-tsc.c
+++ b/tools/perf/tests/perf-time-to-tsc.c
@@ -68,7 +68,7 @@ int test__perf_time_to_tsc(void)
 
 	perf_evlist__set_maps(evlist, cpus, threads);
 
-	CHECK__(parse_events(evlist, "cycles:u"));
+	CHECK__(parse_events(evlist, "cycles:u", NULL));
 
 	perf_evlist__config(evlist, &opts);
 
diff --git a/tools/perf/tests/pmu.c b/tools/perf/tests/pmu.c
index eeb68bb1972d..faa04e9d5d5f 100644
--- a/tools/perf/tests/pmu.c
+++ b/tools/perf/tests/pmu.c
@@ -152,7 +152,8 @@ int test__pmu(void)
 		if (ret)
 			break;
 
-		ret = perf_pmu__config_terms(&formats, &attr, terms, false);
+		ret = perf_pmu__config_terms(&formats, &attr, terms,
+					     false, NULL);
 		if (ret)
 			break;
 
diff --git a/tools/perf/tests/switch-tracking.c b/tools/perf/tests/switch-tracking.c
index cc68648c7c55..0d31403ea593 100644
--- a/tools/perf/tests/switch-tracking.c
+++ b/tools/perf/tests/switch-tracking.c
@@ -347,7 +347,7 @@ int test__switch_tracking(void)
 	perf_evlist__set_maps(evlist, cpus, threads);
 
 	/* First event */
-	err = parse_events(evlist, "cpu-clock:u");
+	err = parse_events(evlist, "cpu-clock:u", NULL);
 	if (err) {
 		pr_debug("Failed to parse event dummy:u\n");
 		goto out_err;
@@ -356,7 +356,7 @@ int test__switch_tracking(void)
 	cpu_clocks_evsel = perf_evlist__last(evlist);
 
 	/* Second event */
-	err = parse_events(evlist, "cycles:u");
+	err = parse_events(evlist, "cycles:u", NULL);
 	if (err) {
 		pr_debug("Failed to parse event cycles:u\n");
 		goto out_err;
@@ -371,7 +371,7 @@ int test__switch_tracking(void)
 		goto out;
 	}
 
-	err = parse_events(evlist, sched_switch);
+	err = parse_events(evlist, sched_switch, NULL);
 	if (err) {
 		pr_debug("Failed to parse event %s\n", sched_switch);
 		goto out_err;
@@ -401,7 +401,7 @@ int test__switch_tracking(void)
 	perf_evsel__set_sample_bit(cycles_evsel, TIME);
 
 	/* Fourth event */
-	err = parse_events(evlist, "dummy:u");
+	err = parse_events(evlist, "dummy:u", NULL);
 	if (err) {
 		pr_debug("Failed to parse event dummy:u\n");
 		goto out_err;
diff --git a/tools/perf/tests/tests.h b/tools/perf/tests/tests.h
index 52758a33f64c..8e5038b48ba8 100644
--- a/tools/perf/tests/tests.h
+++ b/tools/perf/tests/tests.h
@@ -9,6 +9,15 @@ do {									 \
 	}								 \
 } while (0)
 
+#define TEST_ASSERT_EQUAL(text, val, expected)				 \
+do {									 \
+	if (val != expected) {						 \
+		pr_debug("FAILED %s:%d %s (%d != %d)\n",		 \
+			 __FILE__, __LINE__, text, val, expected);	 \
+		return -1;						 \
+	}								 \
+} while (0)
+
 enum {
 	TEST_OK   =  0,
 	TEST_FAIL = -1,
@@ -17,14 +26,14 @@ enum {
 
 /* Tests */
 int test__vmlinux_matches_kallsyms(void);
-int test__open_syscall_event(void);
-int test__open_syscall_event_on_all_cpus(void);
+int test__openat_syscall_event(void);
+int test__openat_syscall_event_on_all_cpus(void);
 int test__basic_mmap(void);
 int test__PERF_RECORD(void);
 int test__rdpmc(void);
 int test__perf_evsel__roundtrip_name_test(void);
 int test__perf_evsel__tp_sched_test(void);
-int test__syscall_open_tp_fields(void);
+int test__syscall_openat_tp_fields(void);
 int test__pmu(void);
 int test__attr(void);
 int test__dso_data(void);
@@ -53,7 +62,7 @@ int test__fdarray__filter(void);
 int test__fdarray__add(void);
 int test__kmod_path__parse(void);
 
-#if defined(__x86_64__) || defined(__i386__) || defined(__arm__)
+#if defined(__x86_64__) || defined(__i386__) || defined(__arm__) || defined(__aarch64__)
 #ifdef HAVE_DWARF_UNWIND_SUPPORT
 struct thread;
 struct perf_sample;
diff --git a/tools/perf/tests/thread-mg-share.c b/tools/perf/tests/thread-mg-share.c
index b028499dd3cf..01fabb19d746 100644
--- a/tools/perf/tests/thread-mg-share.c
+++ b/tools/perf/tests/thread-mg-share.c
@@ -43,7 +43,7 @@ int test__thread_mg_share(void)
 			leader && t1 && t2 && t3 && other);
 
 	mg = leader->mg;
-	TEST_ASSERT_VAL("wrong refcnt", mg->refcnt == 4);
+	TEST_ASSERT_EQUAL("wrong refcnt", atomic_read(&mg->refcnt), 4);
 
 	/* test the map groups pointer is shared */
 	TEST_ASSERT_VAL("map groups don't match", mg == t1->mg);
@@ -58,33 +58,40 @@ int test__thread_mg_share(void)
 	other_leader = machine__find_thread(machine, 4, 4);
 	TEST_ASSERT_VAL("failed to find other leader", other_leader);
 
+	/*
+	 * Ok, now that all the rbtree related operations were done,
+	 * lets remove all of them from there so that we can do the
+	 * refcounting tests.
+	 */
+	machine__remove_thread(machine, leader);
+	machine__remove_thread(machine, t1);
+	machine__remove_thread(machine, t2);
+	machine__remove_thread(machine, t3);
+	machine__remove_thread(machine, other);
+	machine__remove_thread(machine, other_leader);
+
 	other_mg = other->mg;
-	TEST_ASSERT_VAL("wrong refcnt", other_mg->refcnt == 2);
+	TEST_ASSERT_EQUAL("wrong refcnt", atomic_read(&other_mg->refcnt), 2);
 
 	TEST_ASSERT_VAL("map groups don't match", other_mg == other_leader->mg);
 
 	/* release thread group */
-	thread__delete(leader);
-	TEST_ASSERT_VAL("wrong refcnt", mg->refcnt == 3);
+	thread__put(leader);
+	TEST_ASSERT_EQUAL("wrong refcnt", atomic_read(&mg->refcnt), 3);
 
-	thread__delete(t1);
-	TEST_ASSERT_VAL("wrong refcnt", mg->refcnt == 2);
+	thread__put(t1);
+	TEST_ASSERT_EQUAL("wrong refcnt", atomic_read(&mg->refcnt), 2);
 
-	thread__delete(t2);
-	TEST_ASSERT_VAL("wrong refcnt", mg->refcnt == 1);
+	thread__put(t2);
+	TEST_ASSERT_EQUAL("wrong refcnt", atomic_read(&mg->refcnt), 1);
 
-	thread__delete(t3);
+	thread__put(t3);
 
 	/* release other group  */
-	thread__delete(other_leader);
-	TEST_ASSERT_VAL("wrong refcnt", other_mg->refcnt == 1);
+	thread__put(other_leader);
+	TEST_ASSERT_EQUAL("wrong refcnt", atomic_read(&other_mg->refcnt), 1);
 
-	thread__delete(other);
-
-	/*
-	 * Cannot call machine__delete_threads(machine) now,
-	 * because we've already released all the threads.
-	 */
+	thread__put(other);
 
 	machines__exit(&machines);
 	return 0;
diff --git a/tools/perf/tests/vmlinux-kallsyms.c b/tools/perf/tests/vmlinux-kallsyms.c
index 3d9088003a5b..b34c5fc829ae 100644
--- a/tools/perf/tests/vmlinux-kallsyms.c
+++ b/tools/perf/tests/vmlinux-kallsyms.c
@@ -23,9 +23,10 @@ int test__vmlinux_matches_kallsyms(void)
 	int err = -1;
 	struct rb_node *nd;
 	struct symbol *sym;
-	struct map *kallsyms_map, *vmlinux_map;
+	struct map *kallsyms_map, *vmlinux_map, *map;
 	struct machine kallsyms, vmlinux;
 	enum map_type type = MAP__FUNCTION;
+	struct maps *maps = &vmlinux.kmaps.maps[type];
 	u64 mem_start, mem_end;
 
 	/*
@@ -184,8 +185,8 @@ detour:
 
 	pr_info("Maps only in vmlinux:\n");
 
-	for (nd = rb_first(&vmlinux.kmaps.maps[type]); nd; nd = rb_next(nd)) {
-		struct map *pos = rb_entry(nd, struct map, rb_node), *pair;
+	for (map = maps__first(maps); map; map = map__next(map)) {
+		struct map *
 		/*
 		 * If it is the kernel, kallsyms is always "[kernel.kallsyms]", while
 		 * the kernel will have the path for the vmlinux file being used,
@@ -193,22 +194,22 @@ detour:
 		 * both cases.
 		 */
 		pair = map_groups__find_by_name(&kallsyms.kmaps, type,
-						(pos->dso->kernel ?
-							pos->dso->short_name :
-							pos->dso->name));
+						(map->dso->kernel ?
+							map->dso->short_name :
+							map->dso->name));
 		if (pair)
 			pair->priv = 1;
 		else
-			map__fprintf(pos, stderr);
+			map__fprintf(map, stderr);
 	}
 
 	pr_info("Maps in vmlinux with a different name in kallsyms:\n");
 
-	for (nd = rb_first(&vmlinux.kmaps.maps[type]); nd; nd = rb_next(nd)) {
-		struct map *pos = rb_entry(nd, struct map, rb_node), *pair;
+	for (map = maps__first(maps); map; map = map__next(map)) {
+		struct map *pair;
 
-		mem_start = vmlinux_map->unmap_ip(vmlinux_map, pos->start);
-		mem_end = vmlinux_map->unmap_ip(vmlinux_map, pos->end);
+		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);
 		if (pair == NULL || pair->priv)
@@ -217,7 +218,7 @@ detour:
 		if (pair->start == mem_start) {
 			pair->priv = 1;
 			pr_info(" %" PRIx64 "-%" PRIx64 " %" PRIx64 " %s in kallsyms as",
-				pos->start, pos->end, pos->pgoff, pos->dso->name);
+				map->start, map->end, map->pgoff, map->dso->name);
 			if (mem_end != pair->end)
 				pr_info(":\n*%" PRIx64 "-%" PRIx64 " %" PRIx64,
 					pair->start, pair->end, pair->pgoff);
@@ -228,12 +229,11 @@ detour:
 
 	pr_info("Maps only in kallsyms:\n");
 
-	for (nd = rb_first(&kallsyms.kmaps.maps[type]);
-	     nd; nd = rb_next(nd)) {
-		struct map *pos = rb_entry(nd, struct map, rb_node);
+	maps = &kallsyms.kmaps.maps[type];
 
-		if (!pos->priv)
-			map__fprintf(pos, stderr);
+	for (map = maps__first(maps); map; map = map__next(map)) {
+		if (!map->priv)
+			map__fprintf(map, stderr);
 	}
 out:
 	machine__exit(&kallsyms);
diff --git a/tools/perf/ui/browsers/annotate.c b/tools/perf/ui/browsers/annotate.c
index e5250eb2dd57..5995a8bd7c69 100644
--- a/tools/perf/ui/browsers/annotate.c
+++ b/tools/perf/ui/browsers/annotate.c
@@ -11,16 +11,21 @@
 #include "../../util/evsel.h"
 #include <pthread.h>
 
+struct disasm_line_samples {
+	double		percent;
+	u64		nr;
+};
+
 struct browser_disasm_line {
-	struct rb_node	rb_node;
-	u32		idx;
-	int		idx_asm;
-	int		jump_sources;
+	struct rb_node			rb_node;
+	u32				idx;
+	int				idx_asm;
+	int				jump_sources;
 	/*
 	 * actual length of this array is saved on the nr_events field
 	 * of the struct annotate_browser
 	 */
-	double		percent[1];
+	struct disasm_line_samples	samples[1];
 };
 
 static struct annotate_browser_opt {
@@ -28,7 +33,8 @@ static struct annotate_browser_opt {
 	     use_offset,
 	     jump_arrows,
 	     show_linenr,
-	     show_nr_jumps;
+	     show_nr_jumps,
+	     show_total_period;
 } annotate_browser__opts = {
 	.use_offset	= true,
 	.jump_arrows	= true,
@@ -105,15 +111,20 @@ static void annotate_browser__write(struct ui_browser *browser, void *entry, int
 	char bf[256];
 
 	for (i = 0; i < ab->nr_events; i++) {
-		if (bdl->percent[i] > percent_max)
-			percent_max = bdl->percent[i];
+		if (bdl->samples[i].percent > percent_max)
+			percent_max = bdl->samples[i].percent;
 	}
 
 	if (dl->offset != -1 && percent_max != 0.0) {
 		for (i = 0; i < ab->nr_events; i++) {
-			ui_browser__set_percent_color(browser, bdl->percent[i],
+			ui_browser__set_percent_color(browser,
+						      bdl->samples[i].percent,
 						      current_entry);
-			slsmg_printf("%6.2f ", bdl->percent[i]);
+			if (annotate_browser__opts.show_total_period)
+				slsmg_printf("%6" PRIu64 " ",
+					     bdl->samples[i].nr);
+			else
+				slsmg_printf("%6.2f ", bdl->samples[i].percent);
 		}
 	} else {
 		ui_browser__set_percent_color(browser, 0, current_entry);
@@ -273,9 +284,9 @@ static int disasm__cmp(struct browser_disasm_line *a,
 	int i;
 
 	for (i = 0; i < nr_pcnt; i++) {
-		if (a->percent[i] == b->percent[i])
+		if (a->samples[i].percent == b->samples[i].percent)
 			continue;
-		return a->percent[i] < b->percent[i];
+		return a->samples[i].percent < b->samples[i].percent;
 	}
 	return 0;
 }
@@ -366,14 +377,17 @@ static void annotate_browser__calc_percent(struct annotate_browser *browser,
 		next = disasm__get_next_ip_line(&notes->src->source, pos);
 
 		for (i = 0; i < browser->nr_events; i++) {
-			bpos->percent[i] = disasm__calc_percent(notes,
+			u64 nr_samples;
+
+			bpos->samples[i].percent = disasm__calc_percent(notes,
 						evsel->idx + i,
 						pos->offset,
 						next ? next->offset : len,
-					        &path);
+						&path, &nr_samples);
+			bpos->samples[i].nr = nr_samples;
 
-			if (max_percent < bpos->percent[i])
-				max_percent = bpos->percent[i];
+			if (max_percent < bpos->samples[i].percent)
+				max_percent = bpos->samples[i].percent;
 		}
 
 		if (max_percent < 0.01) {
@@ -737,6 +751,7 @@ static int annotate_browser__run(struct annotate_browser *browser,
 		"n             Search next string\n"
 		"o             Toggle disassembler output/simplified view\n"
 		"s             Toggle source code view\n"
+		"t             Toggle total period view\n"
 		"/             Search string\n"
 		"k             Toggle line numbers\n"
 		"r             Run available scripts\n"
@@ -812,6 +827,11 @@ show_sup_ins:
 				ui_helpline__puts("Actions are only available for 'callq', 'retq' & jump instructions.");
 			}
 			continue;
+		case 't':
+			annotate_browser__opts.show_total_period =
+			  !annotate_browser__opts.show_total_period;
+			annotate_browser__update_addr_width(browser);
+			continue;
 		case K_LEFT:
 		case K_ESC:
 		case 'q':
@@ -832,12 +852,20 @@ out:
 int map_symbol__tui_annotate(struct map_symbol *ms, struct perf_evsel *evsel,
 			     struct hist_browser_timer *hbt)
 {
+	/* Set default value for show_total_period.  */
+	annotate_browser__opts.show_total_period =
+	  symbol_conf.show_total_period;
+
 	return symbol__tui_annotate(ms->sym, ms->map, evsel, hbt);
 }
 
 int hist_entry__tui_annotate(struct hist_entry *he, struct perf_evsel *evsel,
 			     struct hist_browser_timer *hbt)
 {
+	/* reset abort key so that it can get Ctrl-C as a key */
+	SLang_reset_tty();
+	SLang_init_tty(0, 0, 0);
+
 	return map_symbol__tui_annotate(&he->ms, evsel, hbt);
 }
 
@@ -925,7 +953,8 @@ int symbol__tui_annotate(struct symbol *sym, struct map *map,
 
 	if (perf_evsel__is_group_event(evsel)) {
 		nr_pcnt = evsel->nr_members;
-		sizeof_bdl += sizeof(double) * (nr_pcnt - 1);
+		sizeof_bdl += sizeof(struct disasm_line_samples) *
+		  (nr_pcnt - 1);
 	}
 
 	if (symbol__annotate(sym, map, sizeof_bdl) < 0) {
@@ -1002,6 +1031,7 @@ static struct annotate_config {
 	ANNOTATE_CFG(show_linenr),
 	ANNOTATE_CFG(show_nr_jumps),
 	ANNOTATE_CFG(use_offset),
+	ANNOTATE_CFG(show_total_period),
 };
 
 #undef ANNOTATE_CFG
diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c
index 995b7a8596b1..c42adb600091 100644
--- a/tools/perf/ui/browsers/hists.c
+++ b/tools/perf/ui/browsers/hists.c
@@ -25,6 +25,9 @@ struct hist_browser {
 	struct hists	    *hists;
 	struct hist_entry   *he_selection;
 	struct map_symbol   *selection;
+	struct hist_browser_timer *hbt;
+	struct pstack	    *pstack;
+	struct perf_session_env *env;
 	int		     print_seq;
 	bool		     show_dso;
 	bool		     show_headers;
@@ -60,7 +63,7 @@ static int hist_browser__get_folding(struct hist_browser *browser)
 		struct hist_entry *he =
 			rb_entry(nd, struct hist_entry, rb_node);
 
-		if (he->ms.unfolded)
+		if (he->unfolded)
 			unfolded_rows += he->nr_rows;
 	}
 	return unfolded_rows;
@@ -136,24 +139,19 @@ static char tree__folded_sign(bool unfolded)
 	return unfolded ? '-' : '+';
 }
 
-static char map_symbol__folded(const struct map_symbol *ms)
-{
-	return ms->has_children ? tree__folded_sign(ms->unfolded) : ' ';
-}
-
 static char hist_entry__folded(const struct hist_entry *he)
 {
-	return map_symbol__folded(&he->ms);
+	return he->has_children ? tree__folded_sign(he->unfolded) : ' ';
 }
 
 static char callchain_list__folded(const struct callchain_list *cl)
 {
-	return map_symbol__folded(&cl->ms);
+	return cl->has_children ? tree__folded_sign(cl->unfolded) : ' ';
 }
 
-static void map_symbol__set_folding(struct map_symbol *ms, bool unfold)
+static void callchain_list__set_folding(struct callchain_list *cl, bool unfold)
 {
-	ms->unfolded = unfold ? ms->has_children : false;
+	cl->unfolded = unfold ? cl->has_children : false;
 }
 
 static int callchain_node__count_rows_rb_tree(struct callchain_node *node)
@@ -189,7 +187,7 @@ static int callchain_node__count_rows(struct callchain_node *node)
 
 	list_for_each_entry(chain, &node->val, list) {
 		++n;
-		unfolded = chain->ms.unfolded;
+		unfolded = chain->unfolded;
 	}
 
 	if (unfolded)
@@ -211,15 +209,27 @@ static int callchain__count_rows(struct rb_root *chain)
 	return n;
 }
 
-static bool map_symbol__toggle_fold(struct map_symbol *ms)
+static bool hist_entry__toggle_fold(struct hist_entry *he)
 {
-	if (!ms)
+	if (!he)
 		return false;
 
-	if (!ms->has_children)
+	if (!he->has_children)
 		return false;
 
-	ms->unfolded = !ms->unfolded;
+	he->unfolded = !he->unfolded;
+	return true;
+}
+
+static bool callchain_list__toggle_fold(struct callchain_list *cl)
+{
+	if (!cl)
+		return false;
+
+	if (!cl->has_children)
+		return false;
+
+	cl->unfolded = !cl->unfolded;
 	return true;
 }
 
@@ -235,10 +245,10 @@ static void callchain_node__init_have_children_rb_tree(struct callchain_node *no
 		list_for_each_entry(chain, &child->val, list) {
 			if (first) {
 				first = false;
-				chain->ms.has_children = chain->list.next != &child->val ||
+				chain->has_children = chain->list.next != &child->val ||
 							 !RB_EMPTY_ROOT(&child->rb_root);
 			} else
-				chain->ms.has_children = chain->list.next == &child->val &&
+				chain->has_children = chain->list.next == &child->val &&
 							 !RB_EMPTY_ROOT(&child->rb_root);
 		}
 
@@ -252,11 +262,11 @@ static void callchain_node__init_have_children(struct callchain_node *node,
 	struct callchain_list *chain;
 
 	chain = list_entry(node->val.next, struct callchain_list, list);
-	chain->ms.has_children = has_sibling;
+	chain->has_children = has_sibling;
 
 	if (!list_empty(&node->val)) {
 		chain = list_entry(node->val.prev, struct callchain_list, list);
-		chain->ms.has_children = !RB_EMPTY_ROOT(&node->rb_root);
+		chain->has_children = !RB_EMPTY_ROOT(&node->rb_root);
 	}
 
 	callchain_node__init_have_children_rb_tree(node);
@@ -276,7 +286,7 @@ static void callchain__init_have_children(struct rb_root *root)
 static void hist_entry__init_have_children(struct hist_entry *he)
 {
 	if (!he->init_have_children) {
-		he->ms.has_children = !RB_EMPTY_ROOT(&he->sorted_chain);
+		he->has_children = !RB_EMPTY_ROOT(&he->sorted_chain);
 		callchain__init_have_children(&he->sorted_chain);
 		he->init_have_children = true;
 	}
@@ -284,14 +294,22 @@ static void hist_entry__init_have_children(struct hist_entry *he)
 
 static bool hist_browser__toggle_fold(struct hist_browser *browser)
 {
-	if (map_symbol__toggle_fold(browser->selection)) {
-		struct hist_entry *he = browser->he_selection;
+	struct hist_entry *he = browser->he_selection;
+	struct map_symbol *ms = browser->selection;
+	struct callchain_list *cl = container_of(ms, struct callchain_list, ms);
+	bool has_children;
 
+	if (ms == &he->ms)
+		has_children = hist_entry__toggle_fold(he);
+	else
+		has_children = callchain_list__toggle_fold(cl);
+
+	if (has_children) {
 		hist_entry__init_have_children(he);
 		browser->b.nr_entries -= he->nr_rows;
 		browser->nr_callchain_rows -= he->nr_rows;
 
-		if (he->ms.unfolded)
+		if (he->unfolded)
 			he->nr_rows = callchain__count_rows(&he->sorted_chain);
 		else
 			he->nr_rows = 0;
@@ -318,8 +336,8 @@ static int callchain_node__set_folding_rb_tree(struct callchain_node *node, bool
 
 		list_for_each_entry(chain, &child->val, list) {
 			++n;
-			map_symbol__set_folding(&chain->ms, unfold);
-			has_children = chain->ms.has_children;
+			callchain_list__set_folding(chain, unfold);
+			has_children = chain->has_children;
 		}
 
 		if (has_children)
@@ -337,8 +355,8 @@ static int callchain_node__set_folding(struct callchain_node *node, bool unfold)
 
 	list_for_each_entry(chain, &node->val, list) {
 		++n;
-		map_symbol__set_folding(&chain->ms, unfold);
-		has_children = chain->ms.has_children;
+		callchain_list__set_folding(chain, unfold);
+		has_children = chain->has_children;
 	}
 
 	if (has_children)
@@ -363,9 +381,9 @@ static int callchain__set_folding(struct rb_root *chain, bool unfold)
 static void hist_entry__set_folding(struct hist_entry *he, bool unfold)
 {
 	hist_entry__init_have_children(he);
-	map_symbol__set_folding(&he->ms, unfold);
+	he->unfolded = unfold ? he->has_children : false;
 
-	if (he->ms.has_children) {
+	if (he->has_children) {
 		int n = callchain__set_folding(&he->sorted_chain, unfold);
 		he->nr_rows = unfold ? n : 0;
 	} else
@@ -406,11 +424,11 @@ static void ui_browser__warn_lost_events(struct ui_browser *browser)
 		"Or reduce the sampling frequency.");
 }
 
-static int hist_browser__run(struct hist_browser *browser,
-			     struct hist_browser_timer *hbt)
+static int hist_browser__run(struct hist_browser *browser, const char *help)
 {
 	int key;
 	char title[160];
+	struct hist_browser_timer *hbt = browser->hbt;
 	int delay_secs = hbt ? hbt->refresh : 0;
 
 	browser->b.entries = &browser->hists->entries;
@@ -418,8 +436,7 @@ static int hist_browser__run(struct hist_browser *browser,
 
 	hists__browser_title(browser->hists, hbt, title, sizeof(title));
 
-	if (ui_browser__show(&browser->b, title,
-			     "Press '?' for help on key bindings") < 0)
+	if (ui_browser__show(&browser->b, title, help) < 0)
 		return -1;
 
 	while (1) {
@@ -1016,7 +1033,7 @@ do_offset:
 	if (offset > 0) {
 		do {
 			h = rb_entry(nd, struct hist_entry, rb_node);
-			if (h->ms.unfolded) {
+			if (h->unfolded) {
 				u16 remaining = h->nr_rows - h->row_offset;
 				if (offset > remaining) {
 					offset -= remaining;
@@ -1037,7 +1054,7 @@ do_offset:
 	} else if (offset < 0) {
 		while (1) {
 			h = rb_entry(nd, struct hist_entry, rb_node);
-			if (h->ms.unfolded) {
+			if (h->unfolded) {
 				if (first) {
 					if (-offset > h->row_offset) {
 						offset += h->row_offset;
@@ -1074,7 +1091,7 @@ do_offset:
 				 * row_offset at its last entry.
 				 */
 				h = rb_entry(nd, struct hist_entry, rb_node);
-				if (h->ms.unfolded)
+				if (h->unfolded)
 					h->row_offset = h->nr_rows;
 				break;
 			}
@@ -1195,7 +1212,9 @@ static int hist_browser__dump(struct hist_browser *browser)
 	return 0;
 }
 
-static struct hist_browser *hist_browser__new(struct hists *hists)
+static struct hist_browser *hist_browser__new(struct hists *hists,
+					      struct hist_browser_timer *hbt,
+					      struct perf_session_env *env)
 {
 	struct hist_browser *browser = zalloc(sizeof(*browser));
 
@@ -1206,6 +1225,8 @@ static struct hist_browser *hist_browser__new(struct hists *hists)
 		browser->b.seek = ui_browser__hists_seek;
 		browser->b.use_navkeypressed = true;
 		browser->show_headers = symbol_conf.show_hist_headers;
+		browser->hbt = hbt;
+		browser->env = env;
 	}
 
 	return browser;
@@ -1395,6 +1416,257 @@ close_file_and_continue:
 	return ret;
 }
 
+struct popup_action {
+	struct thread 		*thread;
+	struct dso		*dso;
+	struct map_symbol 	ms;
+
+	int (*fn)(struct hist_browser *browser, struct popup_action *act);
+};
+
+static int
+do_annotate(struct hist_browser *browser, struct popup_action *act)
+{
+	struct perf_evsel *evsel;
+	struct annotation *notes;
+	struct hist_entry *he;
+	int err;
+
+	if (!objdump_path && perf_session_env__lookup_objdump(browser->env))
+		return 0;
+
+	notes = symbol__annotation(act->ms.sym);
+	if (!notes->src)
+		return 0;
+
+	evsel = hists_to_evsel(browser->hists);
+	err = map_symbol__tui_annotate(&act->ms, evsel, browser->hbt);
+	he = hist_browser__selected_entry(browser);
+	/*
+	 * offer option to annotate the other branch source or target
+	 * (if they exists) when returning from annotate
+	 */
+	if ((err == 'q' || err == CTRL('c')) && he->branch_info)
+		return 1;
+
+	ui_browser__update_nr_entries(&browser->b, browser->hists->nr_entries);
+	if (err)
+		ui_browser__handle_resize(&browser->b);
+	return 0;
+}
+
+static int
+add_annotate_opt(struct hist_browser *browser __maybe_unused,
+		 struct popup_action *act, char **optstr,
+		 struct map *map, struct symbol *sym)
+{
+	if (sym == NULL || map->dso->annotate_warned)
+		return 0;
+
+	if (asprintf(optstr, "Annotate %s", sym->name) < 0)
+		return 0;
+
+	act->ms.map = map;
+	act->ms.sym = sym;
+	act->fn = do_annotate;
+	return 1;
+}
+
+static int
+do_zoom_thread(struct hist_browser *browser, struct popup_action *act)
+{
+	struct thread *thread = act->thread;
+
+	if (browser->hists->thread_filter) {
+		pstack__remove(browser->pstack, &browser->hists->thread_filter);
+		perf_hpp__set_elide(HISTC_THREAD, false);
+		thread__zput(browser->hists->thread_filter);
+		ui_helpline__pop();
+	} else {
+		ui_helpline__fpush("To zoom out press <- or -> + \"Zoom out of %s(%d) thread\"",
+				   thread->comm_set ? thread__comm_str(thread) : "",
+				   thread->tid);
+		browser->hists->thread_filter = thread__get(thread);
+		perf_hpp__set_elide(HISTC_THREAD, false);
+		pstack__push(browser->pstack, &browser->hists->thread_filter);
+	}
+
+	hists__filter_by_thread(browser->hists);
+	hist_browser__reset(browser);
+	return 0;
+}
+
+static int
+add_thread_opt(struct hist_browser *browser, struct popup_action *act,
+	       char **optstr, struct thread *thread)
+{
+	if (thread == NULL)
+		return 0;
+
+	if (asprintf(optstr, "Zoom %s %s(%d) thread",
+		     browser->hists->thread_filter ? "out of" : "into",
+		     thread->comm_set ? thread__comm_str(thread) : "",
+		     thread->tid) < 0)
+		return 0;
+
+	act->thread = thread;
+	act->fn = do_zoom_thread;
+	return 1;
+}
+
+static int
+do_zoom_dso(struct hist_browser *browser, struct popup_action *act)
+{
+	struct dso *dso = act->dso;
+
+	if (browser->hists->dso_filter) {
+		pstack__remove(browser->pstack, &browser->hists->dso_filter);
+		perf_hpp__set_elide(HISTC_DSO, false);
+		browser->hists->dso_filter = NULL;
+		ui_helpline__pop();
+	} else {
+		if (dso == NULL)
+			return 0;
+		ui_helpline__fpush("To zoom out press <- or -> + \"Zoom out of %s DSO\"",
+				   dso->kernel ? "the Kernel" : dso->short_name);
+		browser->hists->dso_filter = dso;
+		perf_hpp__set_elide(HISTC_DSO, true);
+		pstack__push(browser->pstack, &browser->hists->dso_filter);
+	}
+
+	hists__filter_by_dso(browser->hists);
+	hist_browser__reset(browser);
+	return 0;
+}
+
+static int
+add_dso_opt(struct hist_browser *browser, struct popup_action *act,
+	    char **optstr, struct dso *dso)
+{
+	if (dso == NULL)
+		return 0;
+
+	if (asprintf(optstr, "Zoom %s %s DSO",
+		     browser->hists->dso_filter ? "out of" : "into",
+		     dso->kernel ? "the Kernel" : dso->short_name) < 0)
+		return 0;
+
+	act->dso = dso;
+	act->fn = do_zoom_dso;
+	return 1;
+}
+
+static int
+do_browse_map(struct hist_browser *browser __maybe_unused,
+	      struct popup_action *act)
+{
+	map__browse(act->ms.map);
+	return 0;
+}
+
+static int
+add_map_opt(struct hist_browser *browser __maybe_unused,
+	    struct popup_action *act, char **optstr, struct map *map)
+{
+	if (map == NULL)
+		return 0;
+
+	if (asprintf(optstr, "Browse map details") < 0)
+		return 0;
+
+	act->ms.map = map;
+	act->fn = do_browse_map;
+	return 1;
+}
+
+static int
+do_run_script(struct hist_browser *browser __maybe_unused,
+	      struct popup_action *act)
+{
+	char script_opt[64];
+	memset(script_opt, 0, sizeof(script_opt));
+
+	if (act->thread) {
+		scnprintf(script_opt, sizeof(script_opt), " -c %s ",
+			  thread__comm_str(act->thread));
+	} else if (act->ms.sym) {
+		scnprintf(script_opt, sizeof(script_opt), " -S %s ",
+			  act->ms.sym->name);
+	}
+
+	script_browse(script_opt);
+	return 0;
+}
+
+static int
+add_script_opt(struct hist_browser *browser __maybe_unused,
+	       struct popup_action *act, char **optstr,
+	       struct thread *thread, struct symbol *sym)
+{
+	if (thread) {
+		if (asprintf(optstr, "Run scripts for samples of thread [%s]",
+			     thread__comm_str(thread)) < 0)
+			return 0;
+	} else if (sym) {
+		if (asprintf(optstr, "Run scripts for samples of symbol [%s]",
+			     sym->name) < 0)
+			return 0;
+	} else {
+		if (asprintf(optstr, "Run scripts for all samples") < 0)
+			return 0;
+	}
+
+	act->thread = thread;
+	act->ms.sym = sym;
+	act->fn = do_run_script;
+	return 1;
+}
+
+static int
+do_switch_data(struct hist_browser *browser __maybe_unused,
+	       struct popup_action *act __maybe_unused)
+{
+	if (switch_data_file()) {
+		ui__warning("Won't switch the data files due to\n"
+			    "no valid data file get selected!\n");
+		return 0;
+	}
+
+	return K_SWITCH_INPUT_DATA;
+}
+
+static int
+add_switch_opt(struct hist_browser *browser,
+	       struct popup_action *act, char **optstr)
+{
+	if (!is_report_browser(browser->hbt))
+		return 0;
+
+	if (asprintf(optstr, "Switch to another data file in PWD") < 0)
+		return 0;
+
+	act->fn = do_switch_data;
+	return 1;
+}
+
+static int
+do_exit_browser(struct hist_browser *browser __maybe_unused,
+		struct popup_action *act __maybe_unused)
+{
+	return 0;
+}
+
+static int
+add_exit_opt(struct hist_browser *browser __maybe_unused,
+	     struct popup_action *act, char **optstr)
+{
+	if (asprintf(optstr, "Exit") < 0)
+		return 0;
+
+	act->fn = do_exit_browser;
+	return 1;
+}
+
 static void hist_browser__update_nr_entries(struct hist_browser *hb)
 {
 	u64 nr_entries = 0;
@@ -1421,14 +1693,14 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
 				    struct perf_session_env *env)
 {
 	struct hists *hists = evsel__hists(evsel);
-	struct hist_browser *browser = hist_browser__new(hists);
+	struct hist_browser *browser = hist_browser__new(hists, hbt, env);
 	struct branch_info *bi;
-	struct pstack *fstack;
-	char *options[16];
+#define MAX_OPTIONS  16
+	char *options[MAX_OPTIONS];
+	struct popup_action actions[MAX_OPTIONS];
 	int nr_options = 0;
 	int key = -1;
 	char buf[64];
-	char script_opt[64];
 	int delay_secs = hbt ? hbt->refresh : 0;
 	struct perf_hpp_fmt *fmt;
 
@@ -1463,23 +1735,29 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
 	"t             Zoom into current Thread\n"
 	"V             Verbose (DSO names in callchains, etc)\n"
 	"z             Toggle zeroing of samples\n"
+	"f             Enable/Disable events\n"
 	"/             Filter symbol by name";
 
 	if (browser == NULL)
 		return -1;
 
+	/* reset abort key so that it can get Ctrl-C as a key */
+	SLang_reset_tty();
+	SLang_init_tty(0, 0, 0);
+
 	if (min_pcnt) {
 		browser->min_pcnt = min_pcnt;
 		hist_browser__update_nr_entries(browser);
 	}
 
-	fstack = pstack__new(2);
-	if (fstack == NULL)
+	browser->pstack = pstack__new(2);
+	if (browser->pstack == NULL)
 		goto out;
 
 	ui_helpline__push(helpline);
 
 	memset(options, 0, sizeof(options));
+	memset(actions, 0, sizeof(actions));
 
 	perf_hpp__for_each_format(fmt)
 		perf_hpp__reset_width(fmt, hists);
@@ -1489,16 +1767,12 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
 
 	while (1) {
 		struct thread *thread = NULL;
-		const struct dso *dso = NULL;
-		int choice = 0,
-		    annotate = -2, zoom_dso = -2, zoom_thread = -2,
-		    annotate_f = -2, annotate_t = -2, browse_map = -2;
-		int scripts_comm = -2, scripts_symbol = -2,
-		    scripts_all = -2, switch_data = -2;
+		struct dso *dso = NULL;
+		int choice = 0;
 
 		nr_options = 0;
 
-		key = hist_browser__run(browser, hbt);
+		key = hist_browser__run(browser, helpline);
 
 		if (browser->he_selection != NULL) {
 			thread = hist_browser__selected_thread(browser);
@@ -1526,17 +1800,25 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
 			    browser->selection->sym == NULL ||
 			    browser->selection->map->dso->annotate_warned)
 				continue;
-			goto do_annotate;
+
+			actions->ms.map = browser->selection->map;
+			actions->ms.sym = browser->selection->sym;
+			do_annotate(browser, actions);
+			continue;
 		case 'P':
 			hist_browser__dump(browser);
 			continue;
 		case 'd':
-			goto zoom_dso;
+			actions->dso = dso;
+			do_zoom_dso(browser, actions);
+			continue;
 		case 'V':
 			browser->show_dso = !browser->show_dso;
 			continue;
 		case 't':
-			goto zoom_thread;
+			actions->thread = thread;
+			do_zoom_thread(browser, actions);
+			continue;
 		case '/':
 			if (ui_browser__input_window("Symbol to show",
 					"Please enter the name of symbol you want to see",
@@ -1548,12 +1830,18 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
 			}
 			continue;
 		case 'r':
-			if (is_report_browser(hbt))
-				goto do_scripts;
+			if (is_report_browser(hbt)) {
+				actions->thread = NULL;
+				actions->ms.sym = NULL;
+				do_run_script(browser, actions);
+			}
 			continue;
 		case 's':
-			if (is_report_browser(hbt))
-				goto do_data_switch;
+			if (is_report_browser(hbt)) {
+				key = do_switch_data(browser, actions);
+				if (key == K_SWITCH_INPUT_DATA)
+					goto out_free_stack;
+			}
 			continue;
 		case 'i':
 			/* env->arch is NULL for live-mode (i.e. perf top) */
@@ -1583,7 +1871,7 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
 		case K_LEFT: {
 			const void *top;
 
-			if (pstack__empty(fstack)) {
+			if (pstack__empty(browser->pstack)) {
 				/*
 				 * Go back to the perf_evsel_menu__run or other user
 				 */
@@ -1591,11 +1879,17 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
 					goto out_free_stack;
 				continue;
 			}
-			top = pstack__pop(fstack);
-			if (top == &browser->hists->dso_filter)
-				goto zoom_out_dso;
+			top = pstack__peek(browser->pstack);
+			if (top == &browser->hists->dso_filter) {
+				/*
+				 * No need to set actions->dso here since
+				 * it's just to remove the current filter.
+				 * Ditto for thread below.
+				 */
+				do_zoom_dso(browser, actions);
+			}
 			if (top == &browser->hists->thread_filter)
-				goto zoom_out_thread;
+				do_zoom_thread(browser, actions);
 			continue;
 		}
 		case K_ESC:
@@ -1607,7 +1901,12 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
 		case 'q':
 		case CTRL('c'):
 			goto out_free_stack;
+		case 'f':
+			if (!is_report_browser(hbt))
+				goto out_free_stack;
+			/* Fall thru */
 		default:
+			helpline = "Press '?' for help on key bindings";
 			continue;
 		}
 
@@ -1623,196 +1922,71 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
 			if (bi == NULL)
 				goto skip_annotation;
 
-			if (bi->from.sym != NULL &&
-			    !bi->from.map->dso->annotate_warned &&
-			    asprintf(&options[nr_options], "Annotate %s", bi->from.sym->name) > 0) {
-				annotate_f = nr_options++;
-			}
-
-			if (bi->to.sym != NULL &&
-			    !bi->to.map->dso->annotate_warned &&
-			    (bi->to.sym != bi->from.sym ||
-			     bi->to.map->dso != bi->from.map->dso) &&
-			    asprintf(&options[nr_options], "Annotate %s", bi->to.sym->name) > 0) {
-				annotate_t = nr_options++;
-			}
+			nr_options += add_annotate_opt(browser,
+						       &actions[nr_options],
+						       &options[nr_options],
+						       bi->from.map,
+						       bi->from.sym);
+			if (bi->to.sym != bi->from.sym)
+				nr_options += add_annotate_opt(browser,
+							&actions[nr_options],
+							&options[nr_options],
+							bi->to.map,
+							bi->to.sym);
 		} else {
-			if (browser->selection->sym != NULL &&
-			    !browser->selection->map->dso->annotate_warned) {
-				struct annotation *notes;
-
-				notes = symbol__annotation(browser->selection->sym);
-
-				if (notes->src &&
-				    asprintf(&options[nr_options], "Annotate %s",
-						 browser->selection->sym->name) > 0) {
-					annotate = nr_options++;
-				}
-			}
+			nr_options += add_annotate_opt(browser,
+						       &actions[nr_options],
+						       &options[nr_options],
+						       browser->selection->map,
+						       browser->selection->sym);
 		}
 skip_annotation:
-		if (thread != NULL &&
-		    asprintf(&options[nr_options], "Zoom %s %s(%d) thread",
-			     (browser->hists->thread_filter ? "out of" : "into"),
-			     (thread->comm_set ? thread__comm_str(thread) : ""),
-			     thread->tid) > 0)
-			zoom_thread = nr_options++;
-
-		if (dso != NULL &&
-		    asprintf(&options[nr_options], "Zoom %s %s DSO",
-			     (browser->hists->dso_filter ? "out of" : "into"),
-			     (dso->kernel ? "the Kernel" : dso->short_name)) > 0)
-			zoom_dso = nr_options++;
-
-		if (browser->selection != NULL &&
-		    browser->selection->map != NULL &&
-		    asprintf(&options[nr_options], "Browse map details") > 0)
-			browse_map = nr_options++;
+		nr_options += add_thread_opt(browser, &actions[nr_options],
+					     &options[nr_options], thread);
+		nr_options += add_dso_opt(browser, &actions[nr_options],
+					  &options[nr_options], dso);
+		nr_options += add_map_opt(browser, &actions[nr_options],
+					  &options[nr_options],
+					  browser->selection->map);
 
 		/* perf script support */
 		if (browser->he_selection) {
-			struct symbol *sym;
-
-			if (asprintf(&options[nr_options], "Run scripts for samples of thread [%s]",
-				     thread__comm_str(browser->he_selection->thread)) > 0)
-				scripts_comm = nr_options++;
-
-			sym = browser->he_selection->ms.sym;
-			if (sym && sym->namelen &&
-				asprintf(&options[nr_options], "Run scripts for samples of symbol [%s]",
-						sym->name) > 0)
-				scripts_symbol = nr_options++;
+			nr_options += add_script_opt(browser,
+						     &actions[nr_options],
+						     &options[nr_options],
+						     thread, NULL);
+			nr_options += add_script_opt(browser,
+						     &actions[nr_options],
+						     &options[nr_options],
+						     NULL, browser->selection->sym);
 		}
-
-		if (asprintf(&options[nr_options], "Run scripts for all samples") > 0)
-			scripts_all = nr_options++;
-
-		if (is_report_browser(hbt) && asprintf(&options[nr_options],
-				"Switch to another data file in PWD") > 0)
-			switch_data = nr_options++;
+		nr_options += add_script_opt(browser, &actions[nr_options],
+					     &options[nr_options], NULL, NULL);
+		nr_options += add_switch_opt(browser, &actions[nr_options],
+					     &options[nr_options]);
 add_exit_option:
-		options[nr_options++] = (char *)"Exit";
-retry_popup_menu:
-		choice = ui__popup_menu(nr_options, options);
-
-		if (choice == nr_options - 1)
-			break;
-
-		if (choice == -1) {
-			free_popup_options(options, nr_options - 1);
-			continue;
-		}
-
-		if (choice == annotate || choice == annotate_t || choice == annotate_f) {
-			struct hist_entry *he;
-			struct annotation *notes;
-			struct map_symbol ms;
-			int err;
-do_annotate:
-			if (!objdump_path && perf_session_env__lookup_objdump(env))
-				continue;
-
-			he = hist_browser__selected_entry(browser);
-			if (he == NULL)
-				continue;
-
-			if (choice == annotate_f) {
-				ms.map = he->branch_info->from.map;
-				ms.sym = he->branch_info->from.sym;
-			} else if (choice == annotate_t) {
-				ms.map = he->branch_info->to.map;
-				ms.sym = he->branch_info->to.sym;
-			} else {
-				ms = *browser->selection;
-			}
+		nr_options += add_exit_opt(browser, &actions[nr_options],
+					   &options[nr_options]);
 
-			notes = symbol__annotation(ms.sym);
-			if (!notes->src)
-				continue;
-
-			err = map_symbol__tui_annotate(&ms, evsel, hbt);
-			/*
-			 * offer option to annotate the other branch source or target
-			 * (if they exists) when returning from annotate
-			 */
-			if ((err == 'q' || err == CTRL('c'))
-			    && annotate_t != -2 && annotate_f != -2)
-				goto retry_popup_menu;
-
-			ui_browser__update_nr_entries(&browser->b, browser->hists->nr_entries);
-			if (err)
-				ui_browser__handle_resize(&browser->b);
-
-		} else if (choice == browse_map)
-			map__browse(browser->selection->map);
-		else if (choice == zoom_dso) {
-zoom_dso:
-			if (browser->hists->dso_filter) {
-				pstack__remove(fstack, &browser->hists->dso_filter);
-zoom_out_dso:
-				ui_helpline__pop();
-				browser->hists->dso_filter = NULL;
-				perf_hpp__set_elide(HISTC_DSO, false);
-			} else {
-				if (dso == NULL)
-					continue;
-				ui_helpline__fpush("To zoom out press <- or -> + \"Zoom out of %s DSO\"",
-						   dso->kernel ? "the Kernel" : dso->short_name);
-				browser->hists->dso_filter = dso;
-				perf_hpp__set_elide(HISTC_DSO, true);
-				pstack__push(fstack, &browser->hists->dso_filter);
-			}
-			hists__filter_by_dso(hists);
-			hist_browser__reset(browser);
-		} else if (choice == zoom_thread) {
-zoom_thread:
-			if (browser->hists->thread_filter) {
-				pstack__remove(fstack, &browser->hists->thread_filter);
-zoom_out_thread:
-				ui_helpline__pop();
-				thread__zput(browser->hists->thread_filter);
-				perf_hpp__set_elide(HISTC_THREAD, false);
-			} else {
-				ui_helpline__fpush("To zoom out press <- or -> + \"Zoom out of %s(%d) thread\"",
-						   thread->comm_set ? thread__comm_str(thread) : "",
-						   thread->tid);
-				browser->hists->thread_filter = thread__get(thread);
-				perf_hpp__set_elide(HISTC_THREAD, false);
-				pstack__push(fstack, &browser->hists->thread_filter);
-			}
-			hists__filter_by_thread(hists);
-			hist_browser__reset(browser);
-		}
-		/* perf scripts support */
-		else if (choice == scripts_all || choice == scripts_comm ||
-				choice == scripts_symbol) {
-do_scripts:
-			memset(script_opt, 0, 64);
+		do {
+			struct popup_action *act;
 
-			if (choice == scripts_comm)
-				sprintf(script_opt, " -c %s ", thread__comm_str(browser->he_selection->thread));
+			choice = ui__popup_menu(nr_options, options);
+			if (choice == -1 || choice >= nr_options)
+				break;
 
-			if (choice == scripts_symbol)
-				sprintf(script_opt, " -S %s ", browser->he_selection->ms.sym->name);
+			act = &actions[choice];
+			key = act->fn(browser, act);
+		} while (key == 1);
 
-			script_browse(script_opt);
-		}
-		/* Switch to another data file */
-		else if (choice == switch_data) {
-do_data_switch:
-			if (!switch_data_file()) {
-				key = K_SWITCH_INPUT_DATA;
-				break;
-			} else
-				ui__warning("Won't switch the data files due to\n"
-					"no valid data file get selected!\n");
-		}
+		if (key == K_SWITCH_INPUT_DATA)
+			break;
 	}
 out_free_stack:
-	pstack__delete(fstack);
+	pstack__delete(browser->pstack);
 out:
 	hist_browser__delete(browser);
-	free_popup_options(options, nr_options - 1);
+	free_popup_options(options, MAX_OPTIONS);
 	return key;
 }
 
diff --git a/tools/perf/ui/tui/setup.c b/tools/perf/ui/tui/setup.c
index b77e1d771363..60d1f29b4b50 100644
--- a/tools/perf/ui/tui/setup.c
+++ b/tools/perf/ui/tui/setup.c
@@ -129,7 +129,7 @@ int ui__init(void)
 	err = SLsmg_init_smg();
 	if (err < 0)
 		goto out;
-	err = SLang_init_tty(0, 0, 0);
+	err = SLang_init_tty(-1, 0, 0);
 	if (err < 0)
 		goto out;
 
diff --git a/tools/perf/util/Build b/tools/perf/util/Build
index 797490a40075..586a59d46022 100644
--- a/tools/perf/util/Build
+++ b/tools/perf/util/Build
@@ -68,12 +68,15 @@ libperf-y += rblist.o
 libperf-y += intlist.o
 libperf-y += vdso.o
 libperf-y += stat.o
+libperf-y += stat-shadow.o
 libperf-y += record.o
 libperf-y += srcline.o
 libperf-y += data.o
 libperf-$(CONFIG_X86) += tsc.o
 libperf-y += cloexec.o
 libperf-y += thread-stack.o
+libperf-$(CONFIG_AUXTRACE) += auxtrace.o
+libperf-y += parse-branch-options.o
 
 libperf-$(CONFIG_LIBELF) += symbol-elf.o
 libperf-$(CONFIG_LIBELF) += probe-event.o
@@ -101,23 +104,23 @@ CFLAGS_exec_cmd.o += -DPERF_EXEC_PATH="BUILD_STR($(perfexecdir_SQ))" -DPREFIX="B
 
 $(OUTPUT)util/parse-events-flex.c: util/parse-events.l $(OUTPUT)util/parse-events-bison.c
 	$(call rule_mkdir)
-	@$(call echo-cmd,flex)$(FLEX) -o $@ --header-file=$(OUTPUT)util/parse-events-flex.h $(PARSER_DEBUG_FLEX) util/parse-events.l
+	$(Q)$(call echo-cmd,flex)$(FLEX) -o $@ --header-file=$(OUTPUT)util/parse-events-flex.h $(PARSER_DEBUG_FLEX) util/parse-events.l
 
 $(OUTPUT)util/parse-events-bison.c: util/parse-events.y
 	$(call rule_mkdir)
-	@$(call echo-cmd,bison)$(BISON) -v util/parse-events.y -d $(PARSER_DEBUG_BISON) -o $@ -p parse_events_
+	$(Q)$(call echo-cmd,bison)$(BISON) -v util/parse-events.y -d $(PARSER_DEBUG_BISON) -o $@ -p parse_events_
 
 $(OUTPUT)util/pmu-flex.c: util/pmu.l $(OUTPUT)util/pmu-bison.c
 	$(call rule_mkdir)
-	@$(call echo-cmd,flex)$(FLEX) -o $@ --header-file=$(OUTPUT)util/pmu-flex.h util/pmu.l
+	$(Q)$(call echo-cmd,flex)$(FLEX) -o $@ --header-file=$(OUTPUT)util/pmu-flex.h util/pmu.l
 
 $(OUTPUT)util/pmu-bison.c: util/pmu.y
 	$(call rule_mkdir)
-	@$(call echo-cmd,bison)$(BISON) -v util/pmu.y -d -o $@ -p perf_pmu_
+	$(Q)$(call echo-cmd,bison)$(BISON) -v util/pmu.y -d -o $@ -p perf_pmu_
 
 CFLAGS_parse-events-flex.o  += -w
 CFLAGS_pmu-flex.o           += -w
-CFLAGS_parse-events-bison.o += -DYYENABLE_NLS=0 -DYYLTYPE_IS_TRIVIAL=0 -w
+CFLAGS_parse-events-bison.o += -DYYENABLE_NLS=0 -w
 CFLAGS_pmu-bison.o          += -DYYENABLE_NLS=0 -DYYLTYPE_IS_TRIVIAL=0 -w
 
 $(OUTPUT)util/parse-events.o: $(OUTPUT)util/parse-events-flex.c $(OUTPUT)util/parse-events-bison.c
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 7f5bdfc9bc87..03b7bc70eb66 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -506,6 +506,17 @@ static int __symbol__inc_addr_samples(struct symbol *sym, struct map *map,
 	return 0;
 }
 
+static struct annotation *symbol__get_annotation(struct symbol *sym)
+{
+	struct annotation *notes = symbol__annotation(sym);
+
+	if (notes->src == NULL) {
+		if (symbol__alloc_hist(sym) < 0)
+			return NULL;
+	}
+	return notes;
+}
+
 static int symbol__inc_addr_samples(struct symbol *sym, struct map *map,
 				    int evidx, u64 addr)
 {
@@ -513,13 +524,9 @@ static int symbol__inc_addr_samples(struct symbol *sym, struct map *map,
 
 	if (sym == NULL)
 		return 0;
-
-	notes = symbol__annotation(sym);
-	if (notes->src == NULL) {
-		if (symbol__alloc_hist(sym) < 0)
-			return -ENOMEM;
-	}
-
+	notes = symbol__get_annotation(sym);
+	if (notes == NULL)
+		return -ENOMEM;
 	return __symbol__inc_addr_samples(sym, map, notes, evidx, addr);
 }
 
@@ -647,14 +654,15 @@ struct disasm_line *disasm__get_next_ip_line(struct list_head *head, struct disa
 }
 
 double disasm__calc_percent(struct annotation *notes, int evidx, s64 offset,
-			    s64 end, const char **path)
+			    s64 end, const char **path, u64 *nr_samples)
 {
 	struct source_line *src_line = notes->src->lines;
 	double percent = 0.0;
+	*nr_samples = 0;
 
 	if (src_line) {
 		size_t sizeof_src_line = sizeof(*src_line) +
-				sizeof(src_line->p) * (src_line->nr_pcnt - 1);
+				sizeof(src_line->samples) * (src_line->nr_pcnt - 1);
 
 		while (offset < end) {
 			src_line = (void *)notes->src->lines +
@@ -663,7 +671,8 @@ double disasm__calc_percent(struct annotation *notes, int evidx, s64 offset,
 			if (*path == NULL)
 				*path = src_line->path;
 
-			percent += src_line->p[evidx].percent;
+			percent += src_line->samples[evidx].percent;
+			*nr_samples += src_line->samples[evidx].nr;
 			offset++;
 		}
 	} else {
@@ -673,8 +682,10 @@ double disasm__calc_percent(struct annotation *notes, int evidx, s64 offset,
 		while (offset < end)
 			hits += h->addr[offset++];
 
-		if (h->sum)
+		if (h->sum) {
+			*nr_samples = hits;
 			percent = 100.0 * hits / h->sum;
+		}
 	}
 
 	return percent;
@@ -689,8 +700,10 @@ static int disasm_line__print(struct disasm_line *dl, struct symbol *sym, u64 st
 
 	if (dl->offset != -1) {
 		const char *path = NULL;
+		u64 nr_samples;
 		double percent, max_percent = 0.0;
 		double *ppercents = &percent;
+		u64 *psamples = &nr_samples;
 		int i, nr_percent = 1;
 		const char *color;
 		struct annotation *notes = symbol__annotation(sym);
@@ -703,8 +716,10 @@ static int disasm_line__print(struct disasm_line *dl, struct symbol *sym, u64 st
 		if (perf_evsel__is_group_event(evsel)) {
 			nr_percent = evsel->nr_members;
 			ppercents = calloc(nr_percent, sizeof(double));
-			if (ppercents == NULL)
+			psamples = calloc(nr_percent, sizeof(u64));
+			if (ppercents == NULL || psamples == NULL) {
 				return -1;
+			}
 		}
 
 		for (i = 0; i < nr_percent; i++) {
@@ -712,9 +727,10 @@ static int disasm_line__print(struct disasm_line *dl, struct symbol *sym, u64 st
 					notes->src->lines ? i : evsel->idx + i,
 					offset,
 					next ? next->offset : (s64) len,
-					&path);
+					&path, &nr_samples);
 
 			ppercents[i] = percent;
+			psamples[i] = nr_samples;
 			if (percent > max_percent)
 				max_percent = percent;
 		}
@@ -752,8 +768,14 @@ static int disasm_line__print(struct disasm_line *dl, struct symbol *sym, u64 st
 
 		for (i = 0; i < nr_percent; i++) {
 			percent = ppercents[i];
+			nr_samples = psamples[i];
 			color = get_percent_color(percent);
-			color_fprintf(stdout, color, " %7.2f", percent);
+
+			if (symbol_conf.show_total_period)
+				color_fprintf(stdout, color, " %7" PRIu64,
+					      nr_samples);
+			else
+				color_fprintf(stdout, color, " %7.2f", percent);
 		}
 
 		printf(" :	");
@@ -763,6 +785,9 @@ static int disasm_line__print(struct disasm_line *dl, struct symbol *sym, u64 st
 		if (ppercents != &percent)
 			free(ppercents);
 
+		if (psamples != &nr_samples)
+			free(psamples);
+
 	} else if (max_lines && printed >= max_lines)
 		return 1;
 	else {
@@ -1096,7 +1121,7 @@ static void insert_source_line(struct rb_root *root, struct source_line *src_lin
 		ret = strcmp(iter->path, src_line->path);
 		if (ret == 0) {
 			for (i = 0; i < src_line->nr_pcnt; i++)
-				iter->p[i].percent_sum += src_line->p[i].percent;
+				iter->samples[i].percent_sum += src_line->samples[i].percent;
 			return;
 		}
 
@@ -1107,7 +1132,7 @@ static void insert_source_line(struct rb_root *root, struct source_line *src_lin
 	}
 
 	for (i = 0; i < src_line->nr_pcnt; i++)
-		src_line->p[i].percent_sum = src_line->p[i].percent;
+		src_line->samples[i].percent_sum = src_line->samples[i].percent;
 
 	rb_link_node(&src_line->node, parent, p);
 	rb_insert_color(&src_line->node, root);
@@ -1118,9 +1143,9 @@ static int cmp_source_line(struct source_line *a, struct source_line *b)
 	int i;
 
 	for (i = 0; i < a->nr_pcnt; i++) {
-		if (a->p[i].percent_sum == b->p[i].percent_sum)
+		if (a->samples[i].percent_sum == b->samples[i].percent_sum)
 			continue;
-		return a->p[i].percent_sum > b->p[i].percent_sum;
+		return a->samples[i].percent_sum > b->samples[i].percent_sum;
 	}
 
 	return 0;
@@ -1172,7 +1197,7 @@ static void symbol__free_source_line(struct symbol *sym, int len)
 	int i;
 
 	sizeof_src_line = sizeof(*src_line) +
-			  (sizeof(src_line->p) * (src_line->nr_pcnt - 1));
+			  (sizeof(src_line->samples) * (src_line->nr_pcnt - 1));
 
 	for (i = 0; i < len; i++) {
 		free_srcline(src_line->path);
@@ -1204,7 +1229,7 @@ static int symbol__get_source_line(struct symbol *sym, struct map *map,
 			h_sum += h->sum;
 		}
 		nr_pcnt = evsel->nr_members;
-		sizeof_src_line += (nr_pcnt - 1) * sizeof(src_line->p);
+		sizeof_src_line += (nr_pcnt - 1) * sizeof(src_line->samples);
 	}
 
 	if (!h_sum)
@@ -1224,10 +1249,10 @@ static int symbol__get_source_line(struct symbol *sym, struct map *map,
 
 		for (k = 0; k < nr_pcnt; k++) {
 			h = annotation__histogram(notes, evidx + k);
-			src_line->p[k].percent = 100.0 * h->addr[i] / h->sum;
+			src_line->samples[k].percent = 100.0 * h->addr[i] / h->sum;
 
-			if (src_line->p[k].percent > percent_max)
-				percent_max = src_line->p[k].percent;
+			if (src_line->samples[k].percent > percent_max)
+				percent_max = src_line->samples[k].percent;
 		}
 
 		if (percent_max <= 0.5)
@@ -1267,7 +1292,7 @@ static void print_summary(struct rb_root *root, const char *filename)
 
 		src_line = rb_entry(node, struct source_line, node);
 		for (i = 0; i < src_line->nr_pcnt; i++) {
-			percent = src_line->p[i].percent_sum;
+			percent = src_line->samples[i].percent_sum;
 			color = get_percent_color(percent);
 			color_fprintf(stdout, color, " %7.2f", percent);
 
diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h
index cadbdc90a5cb..7e78e6c27078 100644
--- a/tools/perf/util/annotate.h
+++ b/tools/perf/util/annotate.h
@@ -72,23 +72,24 @@ struct disasm_line *disasm__get_next_ip_line(struct list_head *head, struct disa
 int disasm_line__scnprintf(struct disasm_line *dl, char *bf, size_t size, bool raw);
 size_t disasm__fprintf(struct list_head *head, FILE *fp);
 double disasm__calc_percent(struct annotation *notes, int evidx, s64 offset,
-			    s64 end, const char **path);
+			    s64 end, const char **path, u64 *nr_samples);
 
 struct sym_hist {
 	u64		sum;
 	u64		addr[0];
 };
 
-struct source_line_percent {
+struct source_line_samples {
 	double		percent;
 	double		percent_sum;
+	double          nr;
 };
 
 struct source_line {
 	struct rb_node	node;
 	char		*path;
 	int		nr_pcnt;
-	struct source_line_percent p[1];
+	struct source_line_samples samples[1];
 };
 
 /** struct annotated_source - symbols with hits have this attached as in sannotation
diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c
new file mode 100644
index 000000000000..df66966cfde7
--- /dev/null
+++ b/tools/perf/util/auxtrace.c
@@ -0,0 +1,1352 @@
+/*
+ * auxtrace.c: AUX area trace support
+ * Copyright (c) 2013-2015, Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ */
+
+#include <sys/types.h>
+#include <sys/mman.h>
+#include <stdbool.h>
+
+#include <linux/kernel.h>
+#include <linux/perf_event.h>
+#include <linux/types.h>
+#include <linux/bitops.h>
+#include <linux/log2.h>
+#include <linux/string.h>
+
+#include <sys/param.h>
+#include <stdlib.h>
+#include <stdio.h>
+#include <string.h>
+#include <limits.h>
+#include <errno.h>
+#include <linux/list.h>
+
+#include "../perf.h"
+#include "util.h"
+#include "evlist.h"
+#include "cpumap.h"
+#include "thread_map.h"
+#include "asm/bug.h"
+#include "auxtrace.h"
+
+#include <linux/hash.h>
+
+#include "event.h"
+#include "session.h"
+#include "debug.h"
+#include "parse-options.h"
+
+int auxtrace_mmap__mmap(struct auxtrace_mmap *mm,
+			struct auxtrace_mmap_params *mp,
+			void *userpg, int fd)
+{
+	struct perf_event_mmap_page *pc = userpg;
+
+#if BITS_PER_LONG != 64 && !defined(HAVE_SYNC_COMPARE_AND_SWAP_SUPPORT)
+	pr_err("Cannot use AUX area tracing mmaps\n");
+	return -1;
+#endif
+
+	WARN_ONCE(mm->base, "Uninitialized auxtrace_mmap\n");
+
+	mm->userpg = userpg;
+	mm->mask = mp->mask;
+	mm->len = mp->len;
+	mm->prev = 0;
+	mm->idx = mp->idx;
+	mm->tid = mp->tid;
+	mm->cpu = mp->cpu;
+
+	if (!mp->len) {
+		mm->base = NULL;
+		return 0;
+	}
+
+	pc->aux_offset = mp->offset;
+	pc->aux_size = mp->len;
+
+	mm->base = mmap(NULL, mp->len, mp->prot, MAP_SHARED, fd, mp->offset);
+	if (mm->base == MAP_FAILED) {
+		pr_debug2("failed to mmap AUX area\n");
+		mm->base = NULL;
+		return -1;
+	}
+
+	return 0;
+}
+
+void auxtrace_mmap__munmap(struct auxtrace_mmap *mm)
+{
+	if (mm->base) {
+		munmap(mm->base, mm->len);
+		mm->base = NULL;
+	}
+}
+
+void auxtrace_mmap_params__init(struct auxtrace_mmap_params *mp,
+				off_t auxtrace_offset,
+				unsigned int auxtrace_pages,
+				bool auxtrace_overwrite)
+{
+	if (auxtrace_pages) {
+		mp->offset = auxtrace_offset;
+		mp->len = auxtrace_pages * (size_t)page_size;
+		mp->mask = is_power_of_2(mp->len) ? mp->len - 1 : 0;
+		mp->prot = PROT_READ | (auxtrace_overwrite ? 0 : PROT_WRITE);
+		pr_debug2("AUX area mmap length %zu\n", mp->len);
+	} else {
+		mp->len = 0;
+	}
+}
+
+void auxtrace_mmap_params__set_idx(struct auxtrace_mmap_params *mp,
+				   struct perf_evlist *evlist, int idx,
+				   bool per_cpu)
+{
+	mp->idx = idx;
+
+	if (per_cpu) {
+		mp->cpu = evlist->cpus->map[idx];
+		if (evlist->threads)
+			mp->tid = evlist->threads->map[0];
+		else
+			mp->tid = -1;
+	} else {
+		mp->cpu = -1;
+		mp->tid = evlist->threads->map[idx];
+	}
+}
+
+#define AUXTRACE_INIT_NR_QUEUES	32
+
+static struct auxtrace_queue *auxtrace_alloc_queue_array(unsigned int nr_queues)
+{
+	struct auxtrace_queue *queue_array;
+	unsigned int max_nr_queues, i;
+
+	max_nr_queues = UINT_MAX / sizeof(struct auxtrace_queue);
+	if (nr_queues > max_nr_queues)
+		return NULL;
+
+	queue_array = calloc(nr_queues, sizeof(struct auxtrace_queue));
+	if (!queue_array)
+		return NULL;
+
+	for (i = 0; i < nr_queues; i++) {
+		INIT_LIST_HEAD(&queue_array[i].head);
+		queue_array[i].priv = NULL;
+	}
+
+	return queue_array;
+}
+
+int auxtrace_queues__init(struct auxtrace_queues *queues)
+{
+	queues->nr_queues = AUXTRACE_INIT_NR_QUEUES;
+	queues->queue_array = auxtrace_alloc_queue_array(queues->nr_queues);
+	if (!queues->queue_array)
+		return -ENOMEM;
+	return 0;
+}
+
+static int auxtrace_queues__grow(struct auxtrace_queues *queues,
+				 unsigned int new_nr_queues)
+{
+	unsigned int nr_queues = queues->nr_queues;
+	struct auxtrace_queue *queue_array;
+	unsigned int i;
+
+	if (!nr_queues)
+		nr_queues = AUXTRACE_INIT_NR_QUEUES;
+
+	while (nr_queues && nr_queues < new_nr_queues)
+		nr_queues <<= 1;
+
+	if (nr_queues < queues->nr_queues || nr_queues < new_nr_queues)
+		return -EINVAL;
+
+	queue_array = auxtrace_alloc_queue_array(nr_queues);
+	if (!queue_array)
+		return -ENOMEM;
+
+	for (i = 0; i < queues->nr_queues; i++) {
+		list_splice_tail(&queues->queue_array[i].head,
+				 &queue_array[i].head);
+		queue_array[i].priv = queues->queue_array[i].priv;
+	}
+
+	queues->nr_queues = nr_queues;
+	queues->queue_array = queue_array;
+
+	return 0;
+}
+
+static void *auxtrace_copy_data(u64 size, struct perf_session *session)
+{
+	int fd = perf_data_file__fd(session->file);
+	void *p;
+	ssize_t ret;
+
+	if (size > SSIZE_MAX)
+		return NULL;
+
+	p = malloc(size);
+	if (!p)
+		return NULL;
+
+	ret = readn(fd, p, size);
+	if (ret != (ssize_t)size) {
+		free(p);
+		return NULL;
+	}
+
+	return p;
+}
+
+static int auxtrace_queues__add_buffer(struct auxtrace_queues *queues,
+				       unsigned int idx,
+				       struct auxtrace_buffer *buffer)
+{
+	struct auxtrace_queue *queue;
+	int err;
+
+	if (idx >= queues->nr_queues) {
+		err = auxtrace_queues__grow(queues, idx + 1);
+		if (err)
+			return err;
+	}
+
+	queue = &queues->queue_array[idx];
+
+	if (!queue->set) {
+		queue->set = true;
+		queue->tid = buffer->tid;
+		queue->cpu = buffer->cpu;
+	} else if (buffer->cpu != queue->cpu || buffer->tid != queue->tid) {
+		pr_err("auxtrace queue conflict: cpu %d, tid %d vs cpu %d, tid %d\n",
+		       queue->cpu, queue->tid, buffer->cpu, buffer->tid);
+		return -EINVAL;
+	}
+
+	buffer->buffer_nr = queues->next_buffer_nr++;
+
+	list_add_tail(&buffer->list, &queue->head);
+
+	queues->new_data = true;
+	queues->populated = true;
+
+	return 0;
+}
+
+/* Limit buffers to 32MiB on 32-bit */
+#define BUFFER_LIMIT_FOR_32_BIT (32 * 1024 * 1024)
+
+static int auxtrace_queues__split_buffer(struct auxtrace_queues *queues,
+					 unsigned int idx,
+					 struct auxtrace_buffer *buffer)
+{
+	u64 sz = buffer->size;
+	bool consecutive = false;
+	struct auxtrace_buffer *b;
+	int err;
+
+	while (sz > BUFFER_LIMIT_FOR_32_BIT) {
+		b = memdup(buffer, sizeof(struct auxtrace_buffer));
+		if (!b)
+			return -ENOMEM;
+		b->size = BUFFER_LIMIT_FOR_32_BIT;
+		b->consecutive = consecutive;
+		err = auxtrace_queues__add_buffer(queues, idx, b);
+		if (err) {
+			auxtrace_buffer__free(b);
+			return err;
+		}
+		buffer->data_offset += BUFFER_LIMIT_FOR_32_BIT;
+		sz -= BUFFER_LIMIT_FOR_32_BIT;
+		consecutive = true;
+	}
+
+	buffer->size = sz;
+	buffer->consecutive = consecutive;
+
+	return 0;
+}
+
+static int auxtrace_queues__add_event_buffer(struct auxtrace_queues *queues,
+					     struct perf_session *session,
+					     unsigned int idx,
+					     struct auxtrace_buffer *buffer)
+{
+	if (session->one_mmap) {
+		buffer->data = buffer->data_offset - session->one_mmap_offset +
+			       session->one_mmap_addr;
+	} else if (perf_data_file__is_pipe(session->file)) {
+		buffer->data = auxtrace_copy_data(buffer->size, session);
+		if (!buffer->data)
+			return -ENOMEM;
+		buffer->data_needs_freeing = true;
+	} else if (BITS_PER_LONG == 32 &&
+		   buffer->size > BUFFER_LIMIT_FOR_32_BIT) {
+		int err;
+
+		err = auxtrace_queues__split_buffer(queues, idx, buffer);
+		if (err)
+			return err;
+	}
+
+	return auxtrace_queues__add_buffer(queues, idx, buffer);
+}
+
+int auxtrace_queues__add_event(struct auxtrace_queues *queues,
+			       struct perf_session *session,
+			       union perf_event *event, off_t data_offset,
+			       struct auxtrace_buffer **buffer_ptr)
+{
+	struct auxtrace_buffer *buffer;
+	unsigned int idx;
+	int err;
+
+	buffer = zalloc(sizeof(struct auxtrace_buffer));
+	if (!buffer)
+		return -ENOMEM;
+
+	buffer->pid = -1;
+	buffer->tid = event->auxtrace.tid;
+	buffer->cpu = event->auxtrace.cpu;
+	buffer->data_offset = data_offset;
+	buffer->offset = event->auxtrace.offset;
+	buffer->reference = event->auxtrace.reference;
+	buffer->size = event->auxtrace.size;
+	idx = event->auxtrace.idx;
+
+	err = auxtrace_queues__add_event_buffer(queues, session, idx, buffer);
+	if (err)
+		goto out_err;
+
+	if (buffer_ptr)
+		*buffer_ptr = buffer;
+
+	return 0;
+
+out_err:
+	auxtrace_buffer__free(buffer);
+	return err;
+}
+
+static int auxtrace_queues__add_indexed_event(struct auxtrace_queues *queues,
+					      struct perf_session *session,
+					      off_t file_offset, size_t sz)
+{
+	union perf_event *event;
+	int err;
+	char buf[PERF_SAMPLE_MAX_SIZE];
+
+	err = perf_session__peek_event(session, file_offset, buf,
+				       PERF_SAMPLE_MAX_SIZE, &event, NULL);
+	if (err)
+		return err;
+
+	if (event->header.type == PERF_RECORD_AUXTRACE) {
+		if (event->header.size < sizeof(struct auxtrace_event) ||
+		    event->header.size != sz) {
+			err = -EINVAL;
+			goto out;
+		}
+		file_offset += event->header.size;
+		err = auxtrace_queues__add_event(queues, session, event,
+						 file_offset, NULL);
+	}
+out:
+	return err;
+}
+
+void auxtrace_queues__free(struct auxtrace_queues *queues)
+{
+	unsigned int i;
+
+	for (i = 0; i < queues->nr_queues; i++) {
+		while (!list_empty(&queues->queue_array[i].head)) {
+			struct auxtrace_buffer *buffer;
+
+			buffer = list_entry(queues->queue_array[i].head.next,
+					    struct auxtrace_buffer, list);
+			list_del(&buffer->list);
+			auxtrace_buffer__free(buffer);
+		}
+	}
+
+	zfree(&queues->queue_array);
+	queues->nr_queues = 0;
+}
+
+static void auxtrace_heapify(struct auxtrace_heap_item *heap_array,
+			     unsigned int pos, unsigned int queue_nr,
+			     u64 ordinal)
+{
+	unsigned int parent;
+
+	while (pos) {
+		parent = (pos - 1) >> 1;
+		if (heap_array[parent].ordinal <= ordinal)
+			break;
+		heap_array[pos] = heap_array[parent];
+		pos = parent;
+	}
+	heap_array[pos].queue_nr = queue_nr;
+	heap_array[pos].ordinal = ordinal;
+}
+
+int auxtrace_heap__add(struct auxtrace_heap *heap, unsigned int queue_nr,
+		       u64 ordinal)
+{
+	struct auxtrace_heap_item *heap_array;
+
+	if (queue_nr >= heap->heap_sz) {
+		unsigned int heap_sz = AUXTRACE_INIT_NR_QUEUES;
+
+		while (heap_sz <= queue_nr)
+			heap_sz <<= 1;
+		heap_array = realloc(heap->heap_array,
+				     heap_sz * sizeof(struct auxtrace_heap_item));
+		if (!heap_array)
+			return -ENOMEM;
+		heap->heap_array = heap_array;
+		heap->heap_sz = heap_sz;
+	}
+
+	auxtrace_heapify(heap->heap_array, heap->heap_cnt++, queue_nr, ordinal);
+
+	return 0;
+}
+
+void auxtrace_heap__free(struct auxtrace_heap *heap)
+{
+	zfree(&heap->heap_array);
+	heap->heap_cnt = 0;
+	heap->heap_sz = 0;
+}
+
+void auxtrace_heap__pop(struct auxtrace_heap *heap)
+{
+	unsigned int pos, last, heap_cnt = heap->heap_cnt;
+	struct auxtrace_heap_item *heap_array;
+
+	if (!heap_cnt)
+		return;
+
+	heap->heap_cnt -= 1;
+
+	heap_array = heap->heap_array;
+
+	pos = 0;
+	while (1) {
+		unsigned int left, right;
+
+		left = (pos << 1) + 1;
+		if (left >= heap_cnt)
+			break;
+		right = left + 1;
+		if (right >= heap_cnt) {
+			heap_array[pos] = heap_array[left];
+			return;
+		}
+		if (heap_array[left].ordinal < heap_array[right].ordinal) {
+			heap_array[pos] = heap_array[left];
+			pos = left;
+		} else {
+			heap_array[pos] = heap_array[right];
+			pos = right;
+		}
+	}
+
+	last = heap_cnt - 1;
+	auxtrace_heapify(heap_array, pos, heap_array[last].queue_nr,
+			 heap_array[last].ordinal);
+}
+
+size_t auxtrace_record__info_priv_size(struct auxtrace_record *itr)
+{
+	if (itr)
+		return itr->info_priv_size(itr);
+	return 0;
+}
+
+static int auxtrace_not_supported(void)
+{
+	pr_err("AUX area tracing is not supported on this architecture\n");
+	return -EINVAL;
+}
+
+int auxtrace_record__info_fill(struct auxtrace_record *itr,
+			       struct perf_session *session,
+			       struct auxtrace_info_event *auxtrace_info,
+			       size_t priv_size)
+{
+	if (itr)
+		return itr->info_fill(itr, session, auxtrace_info, priv_size);
+	return auxtrace_not_supported();
+}
+
+void auxtrace_record__free(struct auxtrace_record *itr)
+{
+	if (itr)
+		itr->free(itr);
+}
+
+int auxtrace_record__snapshot_start(struct auxtrace_record *itr)
+{
+	if (itr && itr->snapshot_start)
+		return itr->snapshot_start(itr);
+	return 0;
+}
+
+int auxtrace_record__snapshot_finish(struct auxtrace_record *itr)
+{
+	if (itr && itr->snapshot_finish)
+		return itr->snapshot_finish(itr);
+	return 0;
+}
+
+int auxtrace_record__find_snapshot(struct auxtrace_record *itr, int idx,
+				   struct auxtrace_mmap *mm,
+				   unsigned char *data, u64 *head, u64 *old)
+{
+	if (itr && itr->find_snapshot)
+		return itr->find_snapshot(itr, idx, mm, data, head, old);
+	return 0;
+}
+
+int auxtrace_record__options(struct auxtrace_record *itr,
+			     struct perf_evlist *evlist,
+			     struct record_opts *opts)
+{
+	if (itr)
+		return itr->recording_options(itr, evlist, opts);
+	return 0;
+}
+
+u64 auxtrace_record__reference(struct auxtrace_record *itr)
+{
+	if (itr)
+		return itr->reference(itr);
+	return 0;
+}
+
+int auxtrace_parse_snapshot_options(struct auxtrace_record *itr,
+				    struct record_opts *opts, const char *str)
+{
+	if (!str)
+		return 0;
+
+	if (itr)
+		return itr->parse_snapshot_options(itr, opts, str);
+
+	pr_err("No AUX area tracing to snapshot\n");
+	return -EINVAL;
+}
+
+struct auxtrace_record *__weak
+auxtrace_record__init(struct perf_evlist *evlist __maybe_unused, int *err)
+{
+	*err = 0;
+	return NULL;
+}
+
+static int auxtrace_index__alloc(struct list_head *head)
+{
+	struct auxtrace_index *auxtrace_index;
+
+	auxtrace_index = malloc(sizeof(struct auxtrace_index));
+	if (!auxtrace_index)
+		return -ENOMEM;
+
+	auxtrace_index->nr = 0;
+	INIT_LIST_HEAD(&auxtrace_index->list);
+
+	list_add_tail(&auxtrace_index->list, head);
+
+	return 0;
+}
+
+void auxtrace_index__free(struct list_head *head)
+{
+	struct auxtrace_index *auxtrace_index, *n;
+
+	list_for_each_entry_safe(auxtrace_index, n, head, list) {
+		list_del(&auxtrace_index->list);
+		free(auxtrace_index);
+	}
+}
+
+static struct auxtrace_index *auxtrace_index__last(struct list_head *head)
+{
+	struct auxtrace_index *auxtrace_index;
+	int err;
+
+	if (list_empty(head)) {
+		err = auxtrace_index__alloc(head);
+		if (err)
+			return NULL;
+	}
+
+	auxtrace_index = list_entry(head->prev, struct auxtrace_index, list);
+
+	if (auxtrace_index->nr >= PERF_AUXTRACE_INDEX_ENTRY_COUNT) {
+		err = auxtrace_index__alloc(head);
+		if (err)
+			return NULL;
+		auxtrace_index = list_entry(head->prev, struct auxtrace_index,
+					    list);
+	}
+
+	return auxtrace_index;
+}
+
+int auxtrace_index__auxtrace_event(struct list_head *head,
+				   union perf_event *event, off_t file_offset)
+{
+	struct auxtrace_index *auxtrace_index;
+	size_t nr;
+
+	auxtrace_index = auxtrace_index__last(head);
+	if (!auxtrace_index)
+		return -ENOMEM;
+
+	nr = auxtrace_index->nr;
+	auxtrace_index->entries[nr].file_offset = file_offset;
+	auxtrace_index->entries[nr].sz = event->header.size;
+	auxtrace_index->nr += 1;
+
+	return 0;
+}
+
+static int auxtrace_index__do_write(int fd,
+				    struct auxtrace_index *auxtrace_index)
+{
+	struct auxtrace_index_entry ent;
+	size_t i;
+
+	for (i = 0; i < auxtrace_index->nr; i++) {
+		ent.file_offset = auxtrace_index->entries[i].file_offset;
+		ent.sz = auxtrace_index->entries[i].sz;
+		if (writen(fd, &ent, sizeof(ent)) != sizeof(ent))
+			return -errno;
+	}
+	return 0;
+}
+
+int auxtrace_index__write(int fd, struct list_head *head)
+{
+	struct auxtrace_index *auxtrace_index;
+	u64 total = 0;
+	int err;
+
+	list_for_each_entry(auxtrace_index, head, list)
+		total += auxtrace_index->nr;
+
+	if (writen(fd, &total, sizeof(total)) != sizeof(total))
+		return -errno;
+
+	list_for_each_entry(auxtrace_index, head, list) {
+		err = auxtrace_index__do_write(fd, auxtrace_index);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
+static int auxtrace_index__process_entry(int fd, struct list_head *head,
+					 bool needs_swap)
+{
+	struct auxtrace_index *auxtrace_index;
+	struct auxtrace_index_entry ent;
+	size_t nr;
+
+	if (readn(fd, &ent, sizeof(ent)) != sizeof(ent))
+		return -1;
+
+	auxtrace_index = auxtrace_index__last(head);
+	if (!auxtrace_index)
+		return -1;
+
+	nr = auxtrace_index->nr;
+	if (needs_swap) {
+		auxtrace_index->entries[nr].file_offset =
+						bswap_64(ent.file_offset);
+		auxtrace_index->entries[nr].sz = bswap_64(ent.sz);
+	} else {
+		auxtrace_index->entries[nr].file_offset = ent.file_offset;
+		auxtrace_index->entries[nr].sz = ent.sz;
+	}
+
+	auxtrace_index->nr = nr + 1;
+
+	return 0;
+}
+
+int auxtrace_index__process(int fd, u64 size, struct perf_session *session,
+			    bool needs_swap)
+{
+	struct list_head *head = &session->auxtrace_index;
+	u64 nr;
+
+	if (readn(fd, &nr, sizeof(u64)) != sizeof(u64))
+		return -1;
+
+	if (needs_swap)
+		nr = bswap_64(nr);
+
+	if (sizeof(u64) + nr * sizeof(struct auxtrace_index_entry) > size)
+		return -1;
+
+	while (nr--) {
+		int err;
+
+		err = auxtrace_index__process_entry(fd, head, needs_swap);
+		if (err)
+			return -1;
+	}
+
+	return 0;
+}
+
+static int auxtrace_queues__process_index_entry(struct auxtrace_queues *queues,
+						struct perf_session *session,
+						struct auxtrace_index_entry *ent)
+{
+	return auxtrace_queues__add_indexed_event(queues, session,
+						  ent->file_offset, ent->sz);
+}
+
+int auxtrace_queues__process_index(struct auxtrace_queues *queues,
+				   struct perf_session *session)
+{
+	struct auxtrace_index *auxtrace_index;
+	struct auxtrace_index_entry *ent;
+	size_t i;
+	int err;
+
+	list_for_each_entry(auxtrace_index, &session->auxtrace_index, list) {
+		for (i = 0; i < auxtrace_index->nr; i++) {
+			ent = &auxtrace_index->entries[i];
+			err = auxtrace_queues__process_index_entry(queues,
+								   session,
+								   ent);
+			if (err)
+				return err;
+		}
+	}
+	return 0;
+}
+
+struct auxtrace_buffer *auxtrace_buffer__next(struct auxtrace_queue *queue,
+					      struct auxtrace_buffer *buffer)
+{
+	if (buffer) {
+		if (list_is_last(&buffer->list, &queue->head))
+			return NULL;
+		return list_entry(buffer->list.next, struct auxtrace_buffer,
+				  list);
+	} else {
+		if (list_empty(&queue->head))
+			return NULL;
+		return list_entry(queue->head.next, struct auxtrace_buffer,
+				  list);
+	}
+}
+
+void *auxtrace_buffer__get_data(struct auxtrace_buffer *buffer, int fd)
+{
+	size_t adj = buffer->data_offset & (page_size - 1);
+	size_t size = buffer->size + adj;
+	off_t file_offset = buffer->data_offset - adj;
+	void *addr;
+
+	if (buffer->data)
+		return buffer->data;
+
+	addr = mmap(NULL, size, PROT_READ, MAP_SHARED, fd, file_offset);
+	if (addr == MAP_FAILED)
+		return NULL;
+
+	buffer->mmap_addr = addr;
+	buffer->mmap_size = size;
+
+	buffer->data = addr + adj;
+
+	return buffer->data;
+}
+
+void auxtrace_buffer__put_data(struct auxtrace_buffer *buffer)
+{
+	if (!buffer->data || !buffer->mmap_addr)
+		return;
+	munmap(buffer->mmap_addr, buffer->mmap_size);
+	buffer->mmap_addr = NULL;
+	buffer->mmap_size = 0;
+	buffer->data = NULL;
+	buffer->use_data = NULL;
+}
+
+void auxtrace_buffer__drop_data(struct auxtrace_buffer *buffer)
+{
+	auxtrace_buffer__put_data(buffer);
+	if (buffer->data_needs_freeing) {
+		buffer->data_needs_freeing = false;
+		zfree(&buffer->data);
+		buffer->use_data = NULL;
+		buffer->size = 0;
+	}
+}
+
+void auxtrace_buffer__free(struct auxtrace_buffer *buffer)
+{
+	auxtrace_buffer__drop_data(buffer);
+	free(buffer);
+}
+
+void auxtrace_synth_error(struct auxtrace_error_event *auxtrace_error, int type,
+			  int code, int cpu, pid_t pid, pid_t tid, u64 ip,
+			  const char *msg)
+{
+	size_t size;
+
+	memset(auxtrace_error, 0, sizeof(struct auxtrace_error_event));
+
+	auxtrace_error->header.type = PERF_RECORD_AUXTRACE_ERROR;
+	auxtrace_error->type = type;
+	auxtrace_error->code = code;
+	auxtrace_error->cpu = cpu;
+	auxtrace_error->pid = pid;
+	auxtrace_error->tid = tid;
+	auxtrace_error->ip = ip;
+	strlcpy(auxtrace_error->msg, msg, MAX_AUXTRACE_ERROR_MSG);
+
+	size = (void *)auxtrace_error->msg - (void *)auxtrace_error +
+	       strlen(auxtrace_error->msg) + 1;
+	auxtrace_error->header.size = PERF_ALIGN(size, sizeof(u64));
+}
+
+int perf_event__synthesize_auxtrace_info(struct auxtrace_record *itr,
+					 struct perf_tool *tool,
+					 struct perf_session *session,
+					 perf_event__handler_t process)
+{
+	union perf_event *ev;
+	size_t priv_size;
+	int err;
+
+	pr_debug2("Synthesizing auxtrace information\n");
+	priv_size = auxtrace_record__info_priv_size(itr);
+	ev = zalloc(sizeof(struct auxtrace_info_event) + priv_size);
+	if (!ev)
+		return -ENOMEM;
+
+	ev->auxtrace_info.header.type = PERF_RECORD_AUXTRACE_INFO;
+	ev->auxtrace_info.header.size = sizeof(struct auxtrace_info_event) +
+					priv_size;
+	err = auxtrace_record__info_fill(itr, session, &ev->auxtrace_info,
+					 priv_size);
+	if (err)
+		goto out_free;
+
+	err = process(tool, ev, NULL, NULL);
+out_free:
+	free(ev);
+	return err;
+}
+
+static bool auxtrace__dont_decode(struct perf_session *session)
+{
+	return !session->itrace_synth_opts ||
+	       session->itrace_synth_opts->dont_decode;
+}
+
+int perf_event__process_auxtrace_info(struct perf_tool *tool __maybe_unused,
+				      union perf_event *event,
+				      struct perf_session *session __maybe_unused)
+{
+	enum auxtrace_type type = event->auxtrace_info.type;
+
+	if (dump_trace)
+		fprintf(stdout, " type: %u\n", type);
+
+	switch (type) {
+	case PERF_AUXTRACE_UNKNOWN:
+	default:
+		return -EINVAL;
+	}
+}
+
+s64 perf_event__process_auxtrace(struct perf_tool *tool,
+				 union perf_event *event,
+				 struct perf_session *session)
+{
+	s64 err;
+
+	if (dump_trace)
+		fprintf(stdout, " size: %#"PRIx64"  offset: %#"PRIx64"  ref: %#"PRIx64"  idx: %u  tid: %d  cpu: %d\n",
+			event->auxtrace.size, event->auxtrace.offset,
+			event->auxtrace.reference, event->auxtrace.idx,
+			event->auxtrace.tid, event->auxtrace.cpu);
+
+	if (auxtrace__dont_decode(session))
+		return event->auxtrace.size;
+
+	if (!session->auxtrace || event->header.type != PERF_RECORD_AUXTRACE)
+		return -EINVAL;
+
+	err = session->auxtrace->process_auxtrace_event(session, event, tool);
+	if (err < 0)
+		return err;
+
+	return event->auxtrace.size;
+}
+
+#define PERF_ITRACE_DEFAULT_PERIOD_TYPE		PERF_ITRACE_PERIOD_NANOSECS
+#define PERF_ITRACE_DEFAULT_PERIOD		100000
+#define PERF_ITRACE_DEFAULT_CALLCHAIN_SZ	16
+#define PERF_ITRACE_MAX_CALLCHAIN_SZ		1024
+
+void itrace_synth_opts__set_default(struct itrace_synth_opts *synth_opts)
+{
+	synth_opts->instructions = true;
+	synth_opts->branches = true;
+	synth_opts->transactions = true;
+	synth_opts->errors = true;
+	synth_opts->period_type = PERF_ITRACE_DEFAULT_PERIOD_TYPE;
+	synth_opts->period = PERF_ITRACE_DEFAULT_PERIOD;
+	synth_opts->callchain_sz = PERF_ITRACE_DEFAULT_CALLCHAIN_SZ;
+}
+
+/*
+ * Please check tools/perf/Documentation/perf-script.txt for information
+ * about the options parsed here, which is introduced after this cset,
+ * when support in 'perf script' for these options is introduced.
+ */
+int itrace_parse_synth_opts(const struct option *opt, const char *str,
+			    int unset)
+{
+	struct itrace_synth_opts *synth_opts = opt->value;
+	const char *p;
+	char *endptr;
+
+	synth_opts->set = true;
+
+	if (unset) {
+		synth_opts->dont_decode = true;
+		return 0;
+	}
+
+	if (!str) {
+		itrace_synth_opts__set_default(synth_opts);
+		return 0;
+	}
+
+	for (p = str; *p;) {
+		switch (*p++) {
+		case 'i':
+			synth_opts->instructions = true;
+			while (*p == ' ' || *p == ',')
+				p += 1;
+			if (isdigit(*p)) {
+				synth_opts->period = strtoull(p, &endptr, 10);
+				p = endptr;
+				while (*p == ' ' || *p == ',')
+					p += 1;
+				switch (*p++) {
+				case 'i':
+					synth_opts->period_type =
+						PERF_ITRACE_PERIOD_INSTRUCTIONS;
+					break;
+				case 't':
+					synth_opts->period_type =
+						PERF_ITRACE_PERIOD_TICKS;
+					break;
+				case 'm':
+					synth_opts->period *= 1000;
+					/* Fall through */
+				case 'u':
+					synth_opts->period *= 1000;
+					/* Fall through */
+				case 'n':
+					if (*p++ != 's')
+						goto out_err;
+					synth_opts->period_type =
+						PERF_ITRACE_PERIOD_NANOSECS;
+					break;
+				case '\0':
+					goto out;
+				default:
+					goto out_err;
+				}
+			}
+			break;
+		case 'b':
+			synth_opts->branches = true;
+			break;
+		case 'x':
+			synth_opts->transactions = true;
+			break;
+		case 'e':
+			synth_opts->errors = true;
+			break;
+		case 'd':
+			synth_opts->log = true;
+			break;
+		case 'c':
+			synth_opts->branches = true;
+			synth_opts->calls = true;
+			break;
+		case 'r':
+			synth_opts->branches = true;
+			synth_opts->returns = true;
+			break;
+		case 'g':
+			synth_opts->callchain = true;
+			synth_opts->callchain_sz =
+					PERF_ITRACE_DEFAULT_CALLCHAIN_SZ;
+			while (*p == ' ' || *p == ',')
+				p += 1;
+			if (isdigit(*p)) {
+				unsigned int val;
+
+				val = strtoul(p, &endptr, 10);
+				p = endptr;
+				if (!val || val > PERF_ITRACE_MAX_CALLCHAIN_SZ)
+					goto out_err;
+				synth_opts->callchain_sz = val;
+			}
+			break;
+		case ' ':
+		case ',':
+			break;
+		default:
+			goto out_err;
+		}
+	}
+out:
+	if (synth_opts->instructions) {
+		if (!synth_opts->period_type)
+			synth_opts->period_type =
+					PERF_ITRACE_DEFAULT_PERIOD_TYPE;
+		if (!synth_opts->period)
+			synth_opts->period = PERF_ITRACE_DEFAULT_PERIOD;
+	}
+
+	return 0;
+
+out_err:
+	pr_err("Bad Instruction Tracing options '%s'\n", str);
+	return -EINVAL;
+}
+
+static const char * const auxtrace_error_type_name[] = {
+	[PERF_AUXTRACE_ERROR_ITRACE] = "instruction trace",
+};
+
+static const char *auxtrace_error_name(int type)
+{
+	const char *error_type_name = NULL;
+
+	if (type < PERF_AUXTRACE_ERROR_MAX)
+		error_type_name = auxtrace_error_type_name[type];
+	if (!error_type_name)
+		error_type_name = "unknown AUX";
+	return error_type_name;
+}
+
+size_t perf_event__fprintf_auxtrace_error(union perf_event *event, FILE *fp)
+{
+	struct auxtrace_error_event *e = &event->auxtrace_error;
+	int ret;
+
+	ret = fprintf(fp, " %s error type %u",
+		      auxtrace_error_name(e->type), e->type);
+	ret += fprintf(fp, " cpu %d pid %d tid %d ip %#"PRIx64" code %u: %s\n",
+		       e->cpu, e->pid, e->tid, e->ip, e->code, e->msg);
+	return ret;
+}
+
+void perf_session__auxtrace_error_inc(struct perf_session *session,
+				      union perf_event *event)
+{
+	struct auxtrace_error_event *e = &event->auxtrace_error;
+
+	if (e->type < PERF_AUXTRACE_ERROR_MAX)
+		session->evlist->stats.nr_auxtrace_errors[e->type] += 1;
+}
+
+void events_stats__auxtrace_error_warn(const struct events_stats *stats)
+{
+	int i;
+
+	for (i = 0; i < PERF_AUXTRACE_ERROR_MAX; i++) {
+		if (!stats->nr_auxtrace_errors[i])
+			continue;
+		ui__warning("%u %s errors\n",
+			    stats->nr_auxtrace_errors[i],
+			    auxtrace_error_name(i));
+	}
+}
+
+int perf_event__process_auxtrace_error(struct perf_tool *tool __maybe_unused,
+				       union perf_event *event,
+				       struct perf_session *session)
+{
+	if (auxtrace__dont_decode(session))
+		return 0;
+
+	perf_event__fprintf_auxtrace_error(event, stdout);
+	return 0;
+}
+
+static int __auxtrace_mmap__read(struct auxtrace_mmap *mm,
+				 struct auxtrace_record *itr,
+				 struct perf_tool *tool, process_auxtrace_t fn,
+				 bool snapshot, size_t snapshot_size)
+{
+	u64 head, old = mm->prev, offset, ref;
+	unsigned char *data = mm->base;
+	size_t size, head_off, old_off, len1, len2, padding;
+	union perf_event ev;
+	void *data1, *data2;
+
+	if (snapshot) {
+		head = auxtrace_mmap__read_snapshot_head(mm);
+		if (auxtrace_record__find_snapshot(itr, mm->idx, mm, data,
+						   &head, &old))
+			return -1;
+	} else {
+		head = auxtrace_mmap__read_head(mm);
+	}
+
+	if (old == head)
+		return 0;
+
+	pr_debug3("auxtrace idx %d old %#"PRIx64" head %#"PRIx64" diff %#"PRIx64"\n",
+		  mm->idx, old, head, head - old);
+
+	if (mm->mask) {
+		head_off = head & mm->mask;
+		old_off = old & mm->mask;
+	} else {
+		head_off = head % mm->len;
+		old_off = old % mm->len;
+	}
+
+	if (head_off > old_off)
+		size = head_off - old_off;
+	else
+		size = mm->len - (old_off - head_off);
+
+	if (snapshot && size > snapshot_size)
+		size = snapshot_size;
+
+	ref = auxtrace_record__reference(itr);
+
+	if (head > old || size <= head || mm->mask) {
+		offset = head - size;
+	} else {
+		/*
+		 * When the buffer size is not a power of 2, 'head' wraps at the
+		 * highest multiple of the buffer size, so we have to subtract
+		 * the remainder here.
+		 */
+		u64 rem = (0ULL - mm->len) % mm->len;
+
+		offset = head - size - rem;
+	}
+
+	if (size > head_off) {
+		len1 = size - head_off;
+		data1 = &data[mm->len - len1];
+		len2 = head_off;
+		data2 = &data[0];
+	} else {
+		len1 = size;
+		data1 = &data[head_off - len1];
+		len2 = 0;
+		data2 = NULL;
+	}
+
+	/* padding must be written by fn() e.g. record__process_auxtrace() */
+	padding = size & 7;
+	if (padding)
+		padding = 8 - padding;
+
+	memset(&ev, 0, sizeof(ev));
+	ev.auxtrace.header.type = PERF_RECORD_AUXTRACE;
+	ev.auxtrace.header.size = sizeof(ev.auxtrace);
+	ev.auxtrace.size = size + padding;
+	ev.auxtrace.offset = offset;
+	ev.auxtrace.reference = ref;
+	ev.auxtrace.idx = mm->idx;
+	ev.auxtrace.tid = mm->tid;
+	ev.auxtrace.cpu = mm->cpu;
+
+	if (fn(tool, &ev, data1, len1, data2, len2))
+		return -1;
+
+	mm->prev = head;
+
+	if (!snapshot) {
+		auxtrace_mmap__write_tail(mm, head);
+		if (itr->read_finish) {
+			int err;
+
+			err = itr->read_finish(itr, mm->idx);
+			if (err < 0)
+				return err;
+		}
+	}
+
+	return 1;
+}
+
+int auxtrace_mmap__read(struct auxtrace_mmap *mm, struct auxtrace_record *itr,
+			struct perf_tool *tool, process_auxtrace_t fn)
+{
+	return __auxtrace_mmap__read(mm, itr, tool, fn, false, 0);
+}
+
+int auxtrace_mmap__read_snapshot(struct auxtrace_mmap *mm,
+				 struct auxtrace_record *itr,
+				 struct perf_tool *tool, process_auxtrace_t fn,
+				 size_t snapshot_size)
+{
+	return __auxtrace_mmap__read(mm, itr, tool, fn, true, snapshot_size);
+}
+
+/**
+ * struct auxtrace_cache - hash table to implement a cache
+ * @hashtable: the hashtable
+ * @sz: hashtable size (number of hlists)
+ * @entry_size: size of an entry
+ * @limit: limit the number of entries to this maximum, when reached the cache
+ *         is dropped and caching begins again with an empty cache
+ * @cnt: current number of entries
+ * @bits: hashtable size (@sz = 2^@bits)
+ */
+struct auxtrace_cache {
+	struct hlist_head *hashtable;
+	size_t sz;
+	size_t entry_size;
+	size_t limit;
+	size_t cnt;
+	unsigned int bits;
+};
+
+struct auxtrace_cache *auxtrace_cache__new(unsigned int bits, size_t entry_size,
+					   unsigned int limit_percent)
+{
+	struct auxtrace_cache *c;
+	struct hlist_head *ht;
+	size_t sz, i;
+
+	c = zalloc(sizeof(struct auxtrace_cache));
+	if (!c)
+		return NULL;
+
+	sz = 1UL << bits;
+
+	ht = calloc(sz, sizeof(struct hlist_head));
+	if (!ht)
+		goto out_free;
+
+	for (i = 0; i < sz; i++)
+		INIT_HLIST_HEAD(&ht[i]);
+
+	c->hashtable = ht;
+	c->sz = sz;
+	c->entry_size = entry_size;
+	c->limit = (c->sz * limit_percent) / 100;
+	c->bits = bits;
+
+	return c;
+
+out_free:
+	free(c);
+	return NULL;
+}
+
+static void auxtrace_cache__drop(struct auxtrace_cache *c)
+{
+	struct auxtrace_cache_entry *entry;
+	struct hlist_node *tmp;
+	size_t i;
+
+	if (!c)
+		return;
+
+	for (i = 0; i < c->sz; i++) {
+		hlist_for_each_entry_safe(entry, tmp, &c->hashtable[i], hash) {
+			hlist_del(&entry->hash);
+			auxtrace_cache__free_entry(c, entry);
+		}
+	}
+
+	c->cnt = 0;
+}
+
+void auxtrace_cache__free(struct auxtrace_cache *c)
+{
+	if (!c)
+		return;
+
+	auxtrace_cache__drop(c);
+	free(c->hashtable);
+	free(c);
+}
+
+void *auxtrace_cache__alloc_entry(struct auxtrace_cache *c)
+{
+	return malloc(c->entry_size);
+}
+
+void auxtrace_cache__free_entry(struct auxtrace_cache *c __maybe_unused,
+				void *entry)
+{
+	free(entry);
+}
+
+int auxtrace_cache__add(struct auxtrace_cache *c, u32 key,
+			struct auxtrace_cache_entry *entry)
+{
+	if (c->limit && ++c->cnt > c->limit)
+		auxtrace_cache__drop(c);
+
+	entry->key = key;
+	hlist_add_head(&entry->hash, &c->hashtable[hash_32(key, c->bits)]);
+
+	return 0;
+}
+
+void *auxtrace_cache__lookup(struct auxtrace_cache *c, u32 key)
+{
+	struct auxtrace_cache_entry *entry;
+	struct hlist_head *hlist;
+
+	if (!c)
+		return NULL;
+
+	hlist = &c->hashtable[hash_32(key, c->bits)];
+	hlist_for_each_entry(entry, hlist, hash) {
+		if (entry->key == key)
+			return entry;
+	}
+
+	return NULL;
+}
diff --git a/tools/perf/util/auxtrace.h b/tools/perf/util/auxtrace.h
new file mode 100644
index 000000000000..a171abbe7301
--- /dev/null
+++ b/tools/perf/util/auxtrace.h
@@ -0,0 +1,643 @@
+/*
+ * auxtrace.h: AUX area trace support
+ * Copyright (c) 2013-2015, Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ */
+
+#ifndef __PERF_AUXTRACE_H
+#define __PERF_AUXTRACE_H
+
+#include <sys/types.h>
+#include <stdbool.h>
+#include <stddef.h>
+#include <linux/list.h>
+#include <linux/perf_event.h>
+#include <linux/types.h>
+
+#include "../perf.h"
+#include "event.h"
+#include "session.h"
+#include "debug.h"
+
+union perf_event;
+struct perf_session;
+struct perf_evlist;
+struct perf_tool;
+struct option;
+struct record_opts;
+struct auxtrace_info_event;
+struct events_stats;
+
+enum auxtrace_type {
+	PERF_AUXTRACE_UNKNOWN,
+};
+
+enum itrace_period_type {
+	PERF_ITRACE_PERIOD_INSTRUCTIONS,
+	PERF_ITRACE_PERIOD_TICKS,
+	PERF_ITRACE_PERIOD_NANOSECS,
+};
+
+/**
+ * struct itrace_synth_opts - AUX area tracing synthesis options.
+ * @set: indicates whether or not options have been set
+ * @inject: indicates the event (not just the sample) must be fully synthesized
+ *          because 'perf inject' will write it out
+ * @instructions: whether to synthesize 'instructions' events
+ * @branches: whether to synthesize 'branches' events
+ * @transactions: whether to synthesize events for transactions
+ * @errors: whether to synthesize decoder error events
+ * @dont_decode: whether to skip decoding entirely
+ * @log: write a decoding log
+ * @calls: limit branch samples to calls (can be combined with @returns)
+ * @returns: limit branch samples to returns (can be combined with @calls)
+ * @callchain: add callchain to 'instructions' events
+ * @callchain_sz: maximum callchain size
+ * @period: 'instructions' events period
+ * @period_type: 'instructions' events period type
+ */
+struct itrace_synth_opts {
+	bool			set;
+	bool			inject;
+	bool			instructions;
+	bool			branches;
+	bool			transactions;
+	bool			errors;
+	bool			dont_decode;
+	bool			log;
+	bool			calls;
+	bool			returns;
+	bool			callchain;
+	unsigned int		callchain_sz;
+	unsigned long long	period;
+	enum itrace_period_type	period_type;
+};
+
+/**
+ * struct auxtrace_index_entry - indexes a AUX area tracing event within a
+ *                               perf.data file.
+ * @file_offset: offset within the perf.data file
+ * @sz: size of the event
+ */
+struct auxtrace_index_entry {
+	u64			file_offset;
+	u64			sz;
+};
+
+#define PERF_AUXTRACE_INDEX_ENTRY_COUNT 256
+
+/**
+ * struct auxtrace_index - index of AUX area tracing events within a perf.data
+ *                         file.
+ * @list: linking a number of arrays of entries
+ * @nr: number of entries
+ * @entries: array of entries
+ */
+struct auxtrace_index {
+	struct list_head	list;
+	size_t			nr;
+	struct auxtrace_index_entry entries[PERF_AUXTRACE_INDEX_ENTRY_COUNT];
+};
+
+/**
+ * struct auxtrace - session callbacks to allow AUX area data decoding.
+ * @process_event: lets the decoder see all session events
+ * @flush_events: process any remaining data
+ * @free_events: free resources associated with event processing
+ * @free: free resources associated with the session
+ */
+struct auxtrace {
+	int (*process_event)(struct perf_session *session,
+			     union perf_event *event,
+			     struct perf_sample *sample,
+			     struct perf_tool *tool);
+	int (*process_auxtrace_event)(struct perf_session *session,
+				      union perf_event *event,
+				      struct perf_tool *tool);
+	int (*flush_events)(struct perf_session *session,
+			    struct perf_tool *tool);
+	void (*free_events)(struct perf_session *session);
+	void (*free)(struct perf_session *session);
+};
+
+/**
+ * struct auxtrace_buffer - a buffer containing AUX area tracing data.
+ * @list: buffers are queued in a list held by struct auxtrace_queue
+ * @size: size of the buffer in bytes
+ * @pid: in per-thread mode, the pid this buffer is associated with
+ * @tid: in per-thread mode, the tid this buffer is associated with
+ * @cpu: in per-cpu mode, the cpu this buffer is associated with
+ * @data: actual buffer data (can be null if the data has not been loaded)
+ * @data_offset: file offset at which the buffer can be read
+ * @mmap_addr: mmap address at which the buffer can be read
+ * @mmap_size: size of the mmap at @mmap_addr
+ * @data_needs_freeing: @data was malloc'd so free it when it is no longer
+ *                      needed
+ * @consecutive: the original data was split up and this buffer is consecutive
+ *               to the previous buffer
+ * @offset: offset as determined by aux_head / aux_tail members of struct
+ *          perf_event_mmap_page
+ * @reference: an implementation-specific reference determined when the data is
+ *             recorded
+ * @buffer_nr: used to number each buffer
+ * @use_size: implementation actually only uses this number of bytes
+ * @use_data: implementation actually only uses data starting at this address
+ */
+struct auxtrace_buffer {
+	struct list_head	list;
+	size_t			size;
+	pid_t			pid;
+	pid_t			tid;
+	int			cpu;
+	void			*data;
+	off_t			data_offset;
+	void			*mmap_addr;
+	size_t			mmap_size;
+	bool			data_needs_freeing;
+	bool			consecutive;
+	u64			offset;
+	u64			reference;
+	u64			buffer_nr;
+	size_t			use_size;
+	void			*use_data;
+};
+
+/**
+ * struct auxtrace_queue - a queue of AUX area tracing data buffers.
+ * @head: head of buffer list
+ * @tid: in per-thread mode, the tid this queue is associated with
+ * @cpu: in per-cpu mode, the cpu this queue is associated with
+ * @set: %true once this queue has been dedicated to a specific thread or cpu
+ * @priv: implementation-specific data
+ */
+struct auxtrace_queue {
+	struct list_head	head;
+	pid_t			tid;
+	int			cpu;
+	bool			set;
+	void			*priv;
+};
+
+/**
+ * struct auxtrace_queues - an array of AUX area tracing queues.
+ * @queue_array: array of queues
+ * @nr_queues: number of queues
+ * @new_data: set whenever new data is queued
+ * @populated: queues have been fully populated using the auxtrace_index
+ * @next_buffer_nr: used to number each buffer
+ */
+struct auxtrace_queues {
+	struct auxtrace_queue	*queue_array;
+	unsigned int		nr_queues;
+	bool			new_data;
+	bool			populated;
+	u64			next_buffer_nr;
+};
+
+/**
+ * struct auxtrace_heap_item - element of struct auxtrace_heap.
+ * @queue_nr: queue number
+ * @ordinal: value used for sorting (lowest ordinal is top of the heap) expected
+ *           to be a timestamp
+ */
+struct auxtrace_heap_item {
+	unsigned int		queue_nr;
+	u64			ordinal;
+};
+
+/**
+ * struct auxtrace_heap - a heap suitable for sorting AUX area tracing queues.
+ * @heap_array: the heap
+ * @heap_cnt: the number of elements in the heap
+ * @heap_sz: maximum number of elements (grows as needed)
+ */
+struct auxtrace_heap {
+	struct auxtrace_heap_item	*heap_array;
+	unsigned int		heap_cnt;
+	unsigned int		heap_sz;
+};
+
+/**
+ * struct auxtrace_mmap - records an mmap of the auxtrace buffer.
+ * @base: address of mapped area
+ * @userpg: pointer to buffer's perf_event_mmap_page
+ * @mask: %0 if @len is not a power of two, otherwise (@len - %1)
+ * @len: size of mapped area
+ * @prev: previous aux_head
+ * @idx: index of this mmap
+ * @tid: tid for a per-thread mmap (also set if there is only 1 tid on a per-cpu
+ *       mmap) otherwise %0
+ * @cpu: cpu number for a per-cpu mmap otherwise %-1
+ */
+struct auxtrace_mmap {
+	void		*base;
+	void		*userpg;
+	size_t		mask;
+	size_t		len;
+	u64		prev;
+	int		idx;
+	pid_t		tid;
+	int		cpu;
+};
+
+/**
+ * struct auxtrace_mmap_params - parameters to set up struct auxtrace_mmap.
+ * @mask: %0 if @len is not a power of two, otherwise (@len - %1)
+ * @offset: file offset of mapped area
+ * @len: size of mapped area
+ * @prot: mmap memory protection
+ * @idx: index of this mmap
+ * @tid: tid for a per-thread mmap (also set if there is only 1 tid on a per-cpu
+ *       mmap) otherwise %0
+ * @cpu: cpu number for a per-cpu mmap otherwise %-1
+ */
+struct auxtrace_mmap_params {
+	size_t		mask;
+	off_t		offset;
+	size_t		len;
+	int		prot;
+	int		idx;
+	pid_t		tid;
+	int		cpu;
+};
+
+/**
+ * struct auxtrace_record - callbacks for recording AUX area data.
+ * @recording_options: validate and process recording options
+ * @info_priv_size: return the size of the private data in auxtrace_info_event
+ * @info_fill: fill-in the private data in auxtrace_info_event
+ * @free: free this auxtrace record structure
+ * @snapshot_start: starting a snapshot
+ * @snapshot_finish: finishing a snapshot
+ * @find_snapshot: find data to snapshot within auxtrace mmap
+ * @parse_snapshot_options: parse snapshot options
+ * @reference: provide a 64-bit reference number for auxtrace_event
+ * @read_finish: called after reading from an auxtrace mmap
+ */
+struct auxtrace_record {
+	int (*recording_options)(struct auxtrace_record *itr,
+				 struct perf_evlist *evlist,
+				 struct record_opts *opts);
+	size_t (*info_priv_size)(struct auxtrace_record *itr);
+	int (*info_fill)(struct auxtrace_record *itr,
+			 struct perf_session *session,
+			 struct auxtrace_info_event *auxtrace_info,
+			 size_t priv_size);
+	void (*free)(struct auxtrace_record *itr);
+	int (*snapshot_start)(struct auxtrace_record *itr);
+	int (*snapshot_finish)(struct auxtrace_record *itr);
+	int (*find_snapshot)(struct auxtrace_record *itr, int idx,
+			     struct auxtrace_mmap *mm, unsigned char *data,
+			     u64 *head, u64 *old);
+	int (*parse_snapshot_options)(struct auxtrace_record *itr,
+				      struct record_opts *opts,
+				      const char *str);
+	u64 (*reference)(struct auxtrace_record *itr);
+	int (*read_finish)(struct auxtrace_record *itr, int idx);
+};
+
+#ifdef HAVE_AUXTRACE_SUPPORT
+
+/*
+ * In snapshot mode the mmapped page is read-only which makes using
+ * __sync_val_compare_and_swap() problematic.  However, snapshot mode expects
+ * the buffer is not updated while the snapshot is made (e.g. Intel PT disables
+ * the event) so there is not a race anyway.
+ */
+static inline u64 auxtrace_mmap__read_snapshot_head(struct auxtrace_mmap *mm)
+{
+	struct perf_event_mmap_page *pc = mm->userpg;
+	u64 head = ACCESS_ONCE(pc->aux_head);
+
+	/* Ensure all reads are done after we read the head */
+	rmb();
+	return head;
+}
+
+static inline u64 auxtrace_mmap__read_head(struct auxtrace_mmap *mm)
+{
+	struct perf_event_mmap_page *pc = mm->userpg;
+#if BITS_PER_LONG == 64 || !defined(HAVE_SYNC_COMPARE_AND_SWAP_SUPPORT)
+	u64 head = ACCESS_ONCE(pc->aux_head);
+#else
+	u64 head = __sync_val_compare_and_swap(&pc->aux_head, 0, 0);
+#endif
+
+	/* Ensure all reads are done after we read the head */
+	rmb();
+	return head;
+}
+
+static inline void auxtrace_mmap__write_tail(struct auxtrace_mmap *mm, u64 tail)
+{
+	struct perf_event_mmap_page *pc = mm->userpg;
+#if BITS_PER_LONG != 64 && defined(HAVE_SYNC_COMPARE_AND_SWAP_SUPPORT)
+	u64 old_tail;
+#endif
+
+	/* Ensure all reads are done before we write the tail out */
+	mb();
+#if BITS_PER_LONG == 64 || !defined(HAVE_SYNC_COMPARE_AND_SWAP_SUPPORT)
+	pc->aux_tail = tail;
+#else
+	do {
+		old_tail = __sync_val_compare_and_swap(&pc->aux_tail, 0, 0);
+	} while (!__sync_bool_compare_and_swap(&pc->aux_tail, old_tail, tail));
+#endif
+}
+
+int auxtrace_mmap__mmap(struct auxtrace_mmap *mm,
+			struct auxtrace_mmap_params *mp,
+			void *userpg, int fd);
+void auxtrace_mmap__munmap(struct auxtrace_mmap *mm);
+void auxtrace_mmap_params__init(struct auxtrace_mmap_params *mp,
+				off_t auxtrace_offset,
+				unsigned int auxtrace_pages,
+				bool auxtrace_overwrite);
+void auxtrace_mmap_params__set_idx(struct auxtrace_mmap_params *mp,
+				   struct perf_evlist *evlist, int idx,
+				   bool per_cpu);
+
+typedef int (*process_auxtrace_t)(struct perf_tool *tool,
+				  union perf_event *event, void *data1,
+				  size_t len1, void *data2, size_t len2);
+
+int auxtrace_mmap__read(struct auxtrace_mmap *mm, struct auxtrace_record *itr,
+			struct perf_tool *tool, process_auxtrace_t fn);
+
+int auxtrace_mmap__read_snapshot(struct auxtrace_mmap *mm,
+				 struct auxtrace_record *itr,
+				 struct perf_tool *tool, process_auxtrace_t fn,
+				 size_t snapshot_size);
+
+int auxtrace_queues__init(struct auxtrace_queues *queues);
+int auxtrace_queues__add_event(struct auxtrace_queues *queues,
+			       struct perf_session *session,
+			       union perf_event *event, off_t data_offset,
+			       struct auxtrace_buffer **buffer_ptr);
+void auxtrace_queues__free(struct auxtrace_queues *queues);
+int auxtrace_queues__process_index(struct auxtrace_queues *queues,
+				   struct perf_session *session);
+struct auxtrace_buffer *auxtrace_buffer__next(struct auxtrace_queue *queue,
+					      struct auxtrace_buffer *buffer);
+void *auxtrace_buffer__get_data(struct auxtrace_buffer *buffer, int fd);
+void auxtrace_buffer__put_data(struct auxtrace_buffer *buffer);
+void auxtrace_buffer__drop_data(struct auxtrace_buffer *buffer);
+void auxtrace_buffer__free(struct auxtrace_buffer *buffer);
+
+int auxtrace_heap__add(struct auxtrace_heap *heap, unsigned int queue_nr,
+		       u64 ordinal);
+void auxtrace_heap__pop(struct auxtrace_heap *heap);
+void auxtrace_heap__free(struct auxtrace_heap *heap);
+
+struct auxtrace_cache_entry {
+	struct hlist_node hash;
+	u32 key;
+};
+
+struct auxtrace_cache *auxtrace_cache__new(unsigned int bits, size_t entry_size,
+					   unsigned int limit_percent);
+void auxtrace_cache__free(struct auxtrace_cache *auxtrace_cache);
+void *auxtrace_cache__alloc_entry(struct auxtrace_cache *c);
+void auxtrace_cache__free_entry(struct auxtrace_cache *c, void *entry);
+int auxtrace_cache__add(struct auxtrace_cache *c, u32 key,
+			struct auxtrace_cache_entry *entry);
+void *auxtrace_cache__lookup(struct auxtrace_cache *c, u32 key);
+
+struct auxtrace_record *auxtrace_record__init(struct perf_evlist *evlist,
+					      int *err);
+
+int auxtrace_parse_snapshot_options(struct auxtrace_record *itr,
+				    struct record_opts *opts,
+				    const char *str);
+int auxtrace_record__options(struct auxtrace_record *itr,
+			     struct perf_evlist *evlist,
+			     struct record_opts *opts);
+size_t auxtrace_record__info_priv_size(struct auxtrace_record *itr);
+int auxtrace_record__info_fill(struct auxtrace_record *itr,
+			       struct perf_session *session,
+			       struct auxtrace_info_event *auxtrace_info,
+			       size_t priv_size);
+void auxtrace_record__free(struct auxtrace_record *itr);
+int auxtrace_record__snapshot_start(struct auxtrace_record *itr);
+int auxtrace_record__snapshot_finish(struct auxtrace_record *itr);
+int auxtrace_record__find_snapshot(struct auxtrace_record *itr, int idx,
+				   struct auxtrace_mmap *mm,
+				   unsigned char *data, u64 *head, u64 *old);
+u64 auxtrace_record__reference(struct auxtrace_record *itr);
+
+int auxtrace_index__auxtrace_event(struct list_head *head, union perf_event *event,
+				   off_t file_offset);
+int auxtrace_index__write(int fd, struct list_head *head);
+int auxtrace_index__process(int fd, u64 size, struct perf_session *session,
+			    bool needs_swap);
+void auxtrace_index__free(struct list_head *head);
+
+void auxtrace_synth_error(struct auxtrace_error_event *auxtrace_error, int type,
+			  int code, int cpu, pid_t pid, pid_t tid, u64 ip,
+			  const char *msg);
+
+int perf_event__synthesize_auxtrace_info(struct auxtrace_record *itr,
+					 struct perf_tool *tool,
+					 struct perf_session *session,
+					 perf_event__handler_t process);
+int perf_event__process_auxtrace_info(struct perf_tool *tool,
+				      union perf_event *event,
+				      struct perf_session *session);
+s64 perf_event__process_auxtrace(struct perf_tool *tool,
+				 union perf_event *event,
+				 struct perf_session *session);
+int perf_event__process_auxtrace_error(struct perf_tool *tool,
+				       union perf_event *event,
+				       struct perf_session *session);
+int itrace_parse_synth_opts(const struct option *opt, const char *str,
+			    int unset);
+void itrace_synth_opts__set_default(struct itrace_synth_opts *synth_opts);
+
+size_t perf_event__fprintf_auxtrace_error(union perf_event *event, FILE *fp);
+void perf_session__auxtrace_error_inc(struct perf_session *session,
+				      union perf_event *event);
+void events_stats__auxtrace_error_warn(const struct events_stats *stats);
+
+static inline int auxtrace__process_event(struct perf_session *session,
+					  union perf_event *event,
+					  struct perf_sample *sample,
+					  struct perf_tool *tool)
+{
+	if (!session->auxtrace)
+		return 0;
+
+	return session->auxtrace->process_event(session, event, sample, tool);
+}
+
+static inline int auxtrace__flush_events(struct perf_session *session,
+					 struct perf_tool *tool)
+{
+	if (!session->auxtrace)
+		return 0;
+
+	return session->auxtrace->flush_events(session, tool);
+}
+
+static inline void auxtrace__free_events(struct perf_session *session)
+{
+	if (!session->auxtrace)
+		return;
+
+	return session->auxtrace->free_events(session);
+}
+
+static inline void auxtrace__free(struct perf_session *session)
+{
+	if (!session->auxtrace)
+		return;
+
+	return session->auxtrace->free(session);
+}
+
+#else
+
+static inline struct auxtrace_record *
+auxtrace_record__init(struct perf_evlist *evlist __maybe_unused,
+		      int *err __maybe_unused)
+{
+	*err = 0;
+	return NULL;
+}
+
+static inline
+void auxtrace_record__free(struct auxtrace_record *itr __maybe_unused)
+{
+}
+
+static inline int
+perf_event__synthesize_auxtrace_info(struct auxtrace_record *itr __maybe_unused,
+				     struct perf_tool *tool __maybe_unused,
+				     struct perf_session *session __maybe_unused,
+				     perf_event__handler_t process __maybe_unused)
+{
+	return -EINVAL;
+}
+
+static inline
+int auxtrace_record__options(struct auxtrace_record *itr __maybe_unused,
+			     struct perf_evlist *evlist __maybe_unused,
+			     struct record_opts *opts __maybe_unused)
+{
+	return 0;
+}
+
+#define perf_event__process_auxtrace_info		0
+#define perf_event__process_auxtrace			0
+#define perf_event__process_auxtrace_error		0
+
+static inline
+void perf_session__auxtrace_error_inc(struct perf_session *session
+				      __maybe_unused,
+				      union perf_event *event
+				      __maybe_unused)
+{
+}
+
+static inline
+void events_stats__auxtrace_error_warn(const struct events_stats *stats
+				       __maybe_unused)
+{
+}
+
+static inline
+int itrace_parse_synth_opts(const struct option *opt __maybe_unused,
+			    const char *str __maybe_unused,
+			    int unset __maybe_unused)
+{
+	pr_err("AUX area tracing not supported\n");
+	return -EINVAL;
+}
+
+static inline
+int auxtrace_parse_snapshot_options(struct auxtrace_record *itr __maybe_unused,
+				    struct record_opts *opts __maybe_unused,
+				    const char *str)
+{
+	if (!str)
+		return 0;
+	pr_err("AUX area tracing not supported\n");
+	return -EINVAL;
+}
+
+static inline
+int auxtrace__process_event(struct perf_session *session __maybe_unused,
+			    union perf_event *event __maybe_unused,
+			    struct perf_sample *sample __maybe_unused,
+			    struct perf_tool *tool __maybe_unused)
+{
+	return 0;
+}
+
+static inline
+int auxtrace__flush_events(struct perf_session *session __maybe_unused,
+			   struct perf_tool *tool __maybe_unused)
+{
+	return 0;
+}
+
+static inline
+void auxtrace__free_events(struct perf_session *session __maybe_unused)
+{
+}
+
+static inline
+void auxtrace_cache__free(struct auxtrace_cache *auxtrace_cache __maybe_unused)
+{
+}
+
+static inline
+void auxtrace__free(struct perf_session *session __maybe_unused)
+{
+}
+
+static inline
+int auxtrace_index__write(int fd __maybe_unused,
+			  struct list_head *head __maybe_unused)
+{
+	return -EINVAL;
+}
+
+static inline
+int auxtrace_index__process(int fd __maybe_unused,
+			    u64 size __maybe_unused,
+			    struct perf_session *session __maybe_unused,
+			    bool needs_swap __maybe_unused)
+{
+	return -EINVAL;
+}
+
+static inline
+void auxtrace_index__free(struct list_head *head __maybe_unused)
+{
+}
+
+int auxtrace_mmap__mmap(struct auxtrace_mmap *mm,
+			struct auxtrace_mmap_params *mp,
+			void *userpg, int fd);
+void auxtrace_mmap__munmap(struct auxtrace_mmap *mm);
+void auxtrace_mmap_params__init(struct auxtrace_mmap_params *mp,
+				off_t auxtrace_offset,
+				unsigned int auxtrace_pages,
+				bool auxtrace_overwrite);
+void auxtrace_mmap_params__set_idx(struct auxtrace_mmap_params *mp,
+				   struct perf_evlist *evlist, int idx,
+				   bool per_cpu);
+
+#endif
+
+#endif
diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c
index 61867dff5d5a..1f6fc2323ef9 100644
--- a/tools/perf/util/build-id.c
+++ b/tools/perf/util/build-id.c
@@ -43,6 +43,7 @@ int build_id__mark_dso_hit(struct perf_tool *tool __maybe_unused,
 	if (al.map != NULL)
 		al.map->dso->hit = 1;
 
+	thread__put(thread);
 	return 0;
 }
 
@@ -59,8 +60,10 @@ static int perf_event__exit_del_thread(struct perf_tool *tool __maybe_unused,
 	dump_printf("(%d:%d):(%d:%d)\n", event->fork.pid, event->fork.tid,
 		    event->fork.ppid, event->fork.ptid);
 
-	if (thread)
+	if (thread) {
 		machine__remove_thread(machine, thread);
+		thread__put(thread);
+	}
 
 	return 0;
 }
@@ -159,15 +162,20 @@ static int write_buildid(const char *name, size_t name_len, u8 *build_id,
 	return write_padded(fd, name, name_len + 1, len);
 }
 
-static int __dsos__write_buildid_table(struct list_head *head,
-				       struct machine *machine,
-				       pid_t pid, u16 misc, int fd)
+static int machine__write_buildid_table(struct machine *machine, int fd)
 {
+	int err = 0;
 	char nm[PATH_MAX];
 	struct dso *pos;
+	u16 kmisc = PERF_RECORD_MISC_KERNEL,
+	    umisc = PERF_RECORD_MISC_USER;
 
-	dsos__for_each_with_build_id(pos, head) {
-		int err;
+	if (!machine__is_host(machine)) {
+		kmisc = PERF_RECORD_MISC_GUEST_KERNEL;
+		umisc = PERF_RECORD_MISC_GUEST_USER;
+	}
+
+	dsos__for_each_with_build_id(pos, &machine->dsos.head) {
 		const char *name;
 		size_t name_len;
 
@@ -186,32 +194,12 @@ static int __dsos__write_buildid_table(struct list_head *head,
 			name_len = pos->long_name_len + 1;
 		}
 
-		err = write_buildid(name, name_len, pos->build_id,
-				    pid, misc, fd);
+		err = write_buildid(name, name_len, pos->build_id, machine->pid,
+				    pos->kernel ? kmisc : umisc, fd);
 		if (err)
-			return err;
-	}
-
-	return 0;
-}
-
-static int machine__write_buildid_table(struct machine *machine, int fd)
-{
-	int err;
-	u16 kmisc = PERF_RECORD_MISC_KERNEL,
-	    umisc = PERF_RECORD_MISC_USER;
-
-	if (!machine__is_host(machine)) {
-		kmisc = PERF_RECORD_MISC_GUEST_KERNEL;
-		umisc = PERF_RECORD_MISC_GUEST_USER;
+			break;
 	}
 
-	err = __dsos__write_buildid_table(&machine->kernel_dsos.head, machine,
-					  machine->pid, kmisc, fd);
-	if (err == 0)
-		err = __dsos__write_buildid_table(&machine->user_dsos.head,
-						  machine, machine->pid, umisc,
-						  fd);
 	return err;
 }
 
@@ -244,13 +232,7 @@ static int __dsos__hit_all(struct list_head *head)
 
 static int machine__hit_all_dsos(struct machine *machine)
 {
-	int err;
-
-	err = __dsos__hit_all(&machine->kernel_dsos.head);
-	if (err)
-		return err;
-
-	return __dsos__hit_all(&machine->user_dsos.head);
+	return __dsos__hit_all(&machine->dsos.head);
 }
 
 int dsos__hit_all(struct perf_session *session)
@@ -490,9 +472,7 @@ static int __dsos__cache_build_ids(struct list_head *head,
 
 static int machine__cache_build_ids(struct machine *machine)
 {
-	int ret = __dsos__cache_build_ids(&machine->kernel_dsos.head, machine);
-	ret |= __dsos__cache_build_ids(&machine->user_dsos.head, machine);
-	return ret;
+	return __dsos__cache_build_ids(&machine->dsos.head, machine);
 }
 
 int perf_session__cache_build_ids(struct perf_session *session)
@@ -517,11 +497,7 @@ int perf_session__cache_build_ids(struct perf_session *session)
 
 static bool machine__read_build_ids(struct machine *machine, bool with_hits)
 {
-	bool ret;
-
-	ret  = __dsos__read_build_ids(&machine->kernel_dsos.head, with_hits);
-	ret |= __dsos__read_build_ids(&machine->user_dsos.head, with_hits);
-	return ret;
+	return __dsos__read_build_ids(&machine->dsos.head, with_hits);
 }
 
 bool perf_session__read_build_ids(struct perf_session *session, bool with_hits)
diff --git a/tools/perf/util/cache.h b/tools/perf/util/cache.h
index fbcca21d66ab..c861373aaed3 100644
--- a/tools/perf/util/cache.h
+++ b/tools/perf/util/cache.h
@@ -30,7 +30,6 @@ extern const char *perf_config_dirname(const char *, const char *);
 
 /* pager.c */
 extern void setup_pager(void);
-extern const char *pager_program;
 extern int pager_in_use(void);
 extern int pager_use_color;
 
diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h
index 6033a0a212ca..679c2c6d8ade 100644
--- a/tools/perf/util/callchain.h
+++ b/tools/perf/util/callchain.h
@@ -72,6 +72,10 @@ extern struct callchain_param callchain_param;
 struct callchain_list {
 	u64			ip;
 	struct map_symbol	ms;
+	struct /* for TUI */ {
+		bool		unfolded;
+		bool		has_children;
+	};
 	char		       *srcline;
 	struct list_head	list;
 };
diff --git a/tools/perf/util/cgroup.c b/tools/perf/util/cgroup.c
index 88f7be399432..32e12ecfe9c5 100644
--- a/tools/perf/util/cgroup.c
+++ b/tools/perf/util/cgroup.c
@@ -115,23 +115,19 @@ static int add_cgroup(struct perf_evlist *evlist, char *str)
 			goto found;
 		n++;
 	}
-	if (cgrp->refcnt == 0)
+	if (atomic_read(&cgrp->refcnt) == 0)
 		free(cgrp);
 
 	return -1;
 found:
-	cgrp->refcnt++;
+	atomic_inc(&cgrp->refcnt);
 	counter->cgrp = cgrp;
 	return 0;
 }
 
 void close_cgroup(struct cgroup_sel *cgrp)
 {
-	if (!cgrp)
-		return;
-
-	/* XXX: not reentrant */
-	if (--cgrp->refcnt == 0) {
+	if (cgrp && atomic_dec_and_test(&cgrp->refcnt)) {
 		close(cgrp->fd);
 		zfree(&cgrp->name);
 		free(cgrp);
diff --git a/tools/perf/util/cgroup.h b/tools/perf/util/cgroup.h
index 89acd6debdc5..b4b8cb42fe5e 100644
--- a/tools/perf/util/cgroup.h
+++ b/tools/perf/util/cgroup.h
@@ -1,12 +1,14 @@
 #ifndef __CGROUP_H__
 #define __CGROUP_H__
 
+#include <linux/atomic.h>
+
 struct option;
 
 struct cgroup_sel {
 	char *name;
 	int fd;
-	int refcnt;
+	atomic_t refcnt;
 };
 
 
diff --git a/tools/perf/util/comm.c b/tools/perf/util/comm.c
index b2bb59df65e1..21b7ff382c3f 100644
--- a/tools/perf/util/comm.c
+++ b/tools/perf/util/comm.c
@@ -2,24 +2,27 @@
 #include "util.h"
 #include <stdlib.h>
 #include <stdio.h>
+#include <linux/atomic.h>
 
 struct comm_str {
 	char *str;
 	struct rb_node rb_node;
-	int ref;
+	atomic_t refcnt;
 };
 
 /* Should perhaps be moved to struct machine */
 static struct rb_root comm_str_root;
 
-static void comm_str__get(struct comm_str *cs)
+static struct comm_str *comm_str__get(struct comm_str *cs)
 {
-	cs->ref++;
+	if (cs)
+		atomic_inc(&cs->refcnt);
+	return cs;
 }
 
 static void comm_str__put(struct comm_str *cs)
 {
-	if (!--cs->ref) {
+	if (cs && atomic_dec_and_test(&cs->refcnt)) {
 		rb_erase(&cs->rb_node, &comm_str_root);
 		zfree(&cs->str);
 		free(cs);
@@ -40,6 +43,8 @@ static struct comm_str *comm_str__alloc(const char *str)
 		return NULL;
 	}
 
+	atomic_set(&cs->refcnt, 0);
+
 	return cs;
 }
 
diff --git a/tools/perf/util/data-convert-bt.c b/tools/perf/util/data-convert-bt.c
index dd17c9a32fbc..5bfc1198ab46 100644
--- a/tools/perf/util/data-convert-bt.c
+++ b/tools/perf/util/data-convert-bt.c
@@ -14,6 +14,7 @@
 #include <babeltrace/ctf-writer/event.h>
 #include <babeltrace/ctf-writer/event-types.h>
 #include <babeltrace/ctf-writer/event-fields.h>
+#include <babeltrace/ctf-ir/utils.h>
 #include <babeltrace/ctf/events.h>
 #include <traceevent/event-parse.h>
 #include "asm/bug.h"
@@ -38,12 +39,21 @@ struct evsel_priv {
 	struct bt_ctf_event_class *event_class;
 };
 
+#define MAX_CPUS	4096
+
+struct ctf_stream {
+	struct bt_ctf_stream *stream;
+	int cpu;
+	u32 count;
+};
+
 struct ctf_writer {
 	/* writer primitives */
-	struct bt_ctf_writer		*writer;
-	struct bt_ctf_stream		*stream;
-	struct bt_ctf_stream_class	*stream_class;
-	struct bt_ctf_clock		*clock;
+	struct bt_ctf_writer		 *writer;
+	struct ctf_stream		**stream;
+	int				  stream_cnt;
+	struct bt_ctf_stream_class	 *stream_class;
+	struct bt_ctf_clock		 *clock;
 
 	/* data types */
 	union {
@@ -65,6 +75,9 @@ struct convert {
 
 	u64			events_size;
 	u64			events_count;
+
+	/* Ordered events configured queue size. */
+	u64			queue_size;
 };
 
 static int value_set(struct bt_ctf_field_type *type,
@@ -153,6 +166,43 @@ get_tracepoint_field_type(struct ctf_writer *cw, struct format_field *field)
 		return cw->data.u32;
 }
 
+static unsigned long long adjust_signedness(unsigned long long value_int, int size)
+{
+	unsigned long long value_mask;
+
+	/*
+	 * value_mask = (1 << (size * 8 - 1)) - 1.
+	 * Directly set value_mask for code readers.
+	 */
+	switch (size) {
+	case 1:
+		value_mask = 0x7fULL;
+		break;
+	case 2:
+		value_mask = 0x7fffULL;
+		break;
+	case 4:
+		value_mask = 0x7fffffffULL;
+		break;
+	case 8:
+		/*
+		 * For 64 bit value, return it self. There is no need
+		 * to fill high bit.
+		 */
+		/* Fall through */
+	default:
+		/* BUG! */
+		return value_int;
+	}
+
+	/* If it is a positive value, don't adjust. */
+	if ((value_int & (~0ULL - value_mask)) == 0)
+		return value_int;
+
+	/* Fill upper part of value_int with 1 to make it a negative long long. */
+	return (value_int & value_mask) | ~value_mask;
+}
+
 static int add_tracepoint_field_value(struct ctf_writer *cw,
 				      struct bt_ctf_event_class *event_class,
 				      struct bt_ctf_event *event,
@@ -164,7 +214,6 @@ static int add_tracepoint_field_value(struct ctf_writer *cw,
 	struct bt_ctf_field *field;
 	const char *name = fmtf->name;
 	void *data = sample->raw_data;
-	unsigned long long value_int;
 	unsigned long flags = fmtf->flags;
 	unsigned int n_items;
 	unsigned int i;
@@ -172,6 +221,7 @@ static int add_tracepoint_field_value(struct ctf_writer *cw,
 	unsigned int len;
 	int ret;
 
+	name = fmtf->alias;
 	offset = fmtf->offset;
 	len = fmtf->size;
 	if (flags & FIELD_IS_STRING)
@@ -208,11 +258,6 @@ static int add_tracepoint_field_value(struct ctf_writer *cw,
 	type = get_tracepoint_field_type(cw, fmtf);
 
 	for (i = 0; i < n_items; i++) {
-		if (!(flags & FIELD_IS_STRING))
-			value_int = pevent_read_number(
-					fmtf->event->pevent,
-					data + offset + i * len, len);
-
 		if (flags & FIELD_IS_ARRAY)
 			field = bt_ctf_field_array_get_field(array_field, i);
 		else
@@ -226,12 +271,21 @@ static int add_tracepoint_field_value(struct ctf_writer *cw,
 		if (flags & FIELD_IS_STRING)
 			ret = bt_ctf_field_string_set_value(field,
 					data + offset + i * len);
-		else if (!(flags & FIELD_IS_SIGNED))
-			ret = bt_ctf_field_unsigned_integer_set_value(
-					field, value_int);
-		else
-			ret = bt_ctf_field_signed_integer_set_value(
-					field, value_int);
+		else {
+			unsigned long long value_int;
+
+			value_int = pevent_read_number(
+					fmtf->event->pevent,
+					data + offset + i * len, len);
+
+			if (!(flags & FIELD_IS_SIGNED))
+				ret = bt_ctf_field_unsigned_integer_set_value(
+						field, value_int);
+			else
+				ret = bt_ctf_field_signed_integer_set_value(
+						field, adjust_signedness(value_int, len));
+		}
+
 		if (ret) {
 			pr_err("failed to set file value %s\n", name);
 			goto err_put_field;
@@ -346,12 +400,6 @@ static int add_generic_values(struct ctf_writer *cw,
 			return -1;
 	}
 
-	if (type & PERF_SAMPLE_CPU) {
-		ret = value_set_u32(cw, event, "perf_cpu", sample->cpu);
-		if (ret)
-			return -1;
-	}
-
 	if (type & PERF_SAMPLE_PERIOD) {
 		ret = value_set_u64(cw, event, "perf_period", sample->period);
 		if (ret)
@@ -381,6 +429,129 @@ static int add_generic_values(struct ctf_writer *cw,
 	return 0;
 }
 
+static int ctf_stream__flush(struct ctf_stream *cs)
+{
+	int err = 0;
+
+	if (cs) {
+		err = bt_ctf_stream_flush(cs->stream);
+		if (err)
+			pr_err("CTF stream %d flush failed\n", cs->cpu);
+
+		pr("Flush stream for cpu %d (%u samples)\n",
+		   cs->cpu, cs->count);
+
+		cs->count = 0;
+	}
+
+	return err;
+}
+
+static struct ctf_stream *ctf_stream__create(struct ctf_writer *cw, int cpu)
+{
+	struct ctf_stream *cs;
+	struct bt_ctf_field *pkt_ctx   = NULL;
+	struct bt_ctf_field *cpu_field = NULL;
+	struct bt_ctf_stream *stream   = NULL;
+	int ret;
+
+	cs = zalloc(sizeof(*cs));
+	if (!cs) {
+		pr_err("Failed to allocate ctf stream\n");
+		return NULL;
+	}
+
+	stream = bt_ctf_writer_create_stream(cw->writer, cw->stream_class);
+	if (!stream) {
+		pr_err("Failed to create CTF stream\n");
+		goto out;
+	}
+
+	pkt_ctx = bt_ctf_stream_get_packet_context(stream);
+	if (!pkt_ctx) {
+		pr_err("Failed to obtain packet context\n");
+		goto out;
+	}
+
+	cpu_field = bt_ctf_field_structure_get_field(pkt_ctx, "cpu_id");
+	bt_ctf_field_put(pkt_ctx);
+	if (!cpu_field) {
+		pr_err("Failed to obtain cpu field\n");
+		goto out;
+	}
+
+	ret = bt_ctf_field_unsigned_integer_set_value(cpu_field, (u32) cpu);
+	if (ret) {
+		pr_err("Failed to update CPU number\n");
+		goto out;
+	}
+
+	bt_ctf_field_put(cpu_field);
+
+	cs->cpu    = cpu;
+	cs->stream = stream;
+	return cs;
+
+out:
+	if (cpu_field)
+		bt_ctf_field_put(cpu_field);
+	if (stream)
+		bt_ctf_stream_put(stream);
+
+	free(cs);
+	return NULL;
+}
+
+static void ctf_stream__delete(struct ctf_stream *cs)
+{
+	if (cs) {
+		bt_ctf_stream_put(cs->stream);
+		free(cs);
+	}
+}
+
+static struct ctf_stream *ctf_stream(struct ctf_writer *cw, int cpu)
+{
+	struct ctf_stream *cs = cw->stream[cpu];
+
+	if (!cs) {
+		cs = ctf_stream__create(cw, cpu);
+		cw->stream[cpu] = cs;
+	}
+
+	return cs;
+}
+
+static int get_sample_cpu(struct ctf_writer *cw, struct perf_sample *sample,
+			  struct perf_evsel *evsel)
+{
+	int cpu = 0;
+
+	if (evsel->attr.sample_type & PERF_SAMPLE_CPU)
+		cpu = sample->cpu;
+
+	if (cpu > cw->stream_cnt) {
+		pr_err("Event was recorded for CPU %d, limit is at %d.\n",
+			cpu, cw->stream_cnt);
+		cpu = 0;
+	}
+
+	return cpu;
+}
+
+#define STREAM_FLUSH_COUNT 100000
+
+/*
+ * Currently we have no other way to determine the
+ * time for the stream flush other than keep track
+ * of the number of events and check it against
+ * threshold.
+ */
+static bool is_flush_needed(struct ctf_stream *cs)
+{
+	return cs->count >= STREAM_FLUSH_COUNT;
+}
+
 static int process_sample_event(struct perf_tool *tool,
 				union perf_event *_event __maybe_unused,
 				struct perf_sample *sample,
@@ -390,6 +561,7 @@ static int process_sample_event(struct perf_tool *tool,
 	struct convert *c = container_of(tool, struct convert, tool);
 	struct evsel_priv *priv = evsel->priv;
 	struct ctf_writer *cw = &c->writer;
+	struct ctf_stream *cs;
 	struct bt_ctf_event_class *event_class;
 	struct bt_ctf_event *event;
 	int ret;
@@ -424,9 +596,93 @@ static int process_sample_event(struct perf_tool *tool,
 			return -1;
 	}
 
-	bt_ctf_stream_append_event(cw->stream, event);
+	cs = ctf_stream(cw, get_sample_cpu(cw, sample, evsel));
+	if (cs) {
+		if (is_flush_needed(cs))
+			ctf_stream__flush(cs);
+
+		cs->count++;
+		bt_ctf_stream_append_event(cs->stream, event);
+	}
+
 	bt_ctf_event_put(event);
-	return 0;
+	return cs ? 0 : -1;
+}
+
+/* If dup < 0, add a prefix. Else, add _dupl_X suffix. */
+static char *change_name(char *name, char *orig_name, int dup)
+{
+	char *new_name = NULL;
+	size_t len;
+
+	if (!name)
+		name = orig_name;
+
+	if (dup >= 10)
+		goto out;
+	/*
+	 * Add '_' prefix to potential keywork.  According to
+	 * Mathieu Desnoyers (https://lkml.org/lkml/2015/1/23/652),
+	 * futher CTF spec updating may require us to use '$'.
+	 */
+	if (dup < 0)
+		len = strlen(name) + sizeof("_");
+	else
+		len = strlen(orig_name) + sizeof("_dupl_X");
+
+	new_name = malloc(len);
+	if (!new_name)
+		goto out;
+
+	if (dup < 0)
+		snprintf(new_name, len, "_%s", name);
+	else
+		snprintf(new_name, len, "%s_dupl_%d", orig_name, dup);
+
+out:
+	if (name != orig_name)
+		free(name);
+	return new_name;
+}
+
+static int event_class_add_field(struct bt_ctf_event_class *event_class,
+		struct bt_ctf_field_type *type,
+		struct format_field *field)
+{
+	struct bt_ctf_field_type *t = NULL;
+	char *name;
+	int dup = 1;
+	int ret;
+
+	/* alias was already assigned */
+	if (field->alias != field->name)
+		return bt_ctf_event_class_add_field(event_class, type,
+				(char *)field->alias);
+
+	name = field->name;
+
+	/* If 'name' is a keywork, add prefix. */
+	if (bt_ctf_validate_identifier(name))
+		name = change_name(name, field->name, -1);
+
+	if (!name) {
+		pr_err("Failed to fix invalid identifier.");
+		return -1;
+	}
+	while ((t = bt_ctf_event_class_get_field_by_name(event_class, name))) {
+		bt_ctf_field_type_put(t);
+		name = change_name(name, field->name, dup++);
+		if (!name) {
+			pr_err("Failed to create dup name for '%s'\n", field->name);
+			return -1;
+		}
+	}
+
+	ret = bt_ctf_event_class_add_field(event_class, type, name);
+	if (!ret)
+		field->alias = name;
+
+	return ret;
 }
 
 static int add_tracepoint_fields_types(struct ctf_writer *cw,
@@ -457,14 +713,14 @@ static int add_tracepoint_fields_types(struct ctf_writer *cw,
 		if (flags & FIELD_IS_ARRAY)
 			type = bt_ctf_field_type_array_create(type, field->arraylen);
 
-		ret = bt_ctf_event_class_add_field(event_class, type,
-				field->name);
+		ret = event_class_add_field(event_class, type, field);
 
 		if (flags & FIELD_IS_ARRAY)
 			bt_ctf_field_type_put(type);
 
 		if (ret) {
-			pr_err("Failed to add field '%s\n", field->name);
+			pr_err("Failed to add field '%s': %d\n",
+					field->name, ret);
 			return -1;
 		}
 	}
@@ -508,7 +764,7 @@ static int add_generic_types(struct ctf_writer *cw, struct perf_evsel *evsel,
 	do {								\
 		pr2("  field '%s'\n", n);				\
 		if (bt_ctf_event_class_add_field(cl, t, n)) {		\
-			pr_err("Failed to add field '%s;\n", n);	\
+			pr_err("Failed to add field '%s';\n", n);	\
 			return -1;					\
 		}							\
 	} while (0)
@@ -528,9 +784,6 @@ static int add_generic_types(struct ctf_writer *cw, struct perf_evsel *evsel,
 	if (type & PERF_SAMPLE_STREAM_ID)
 		ADD_FIELD(event_class, cw->data.u64, "perf_stream_id");
 
-	if (type & PERF_SAMPLE_CPU)
-		ADD_FIELD(event_class, cw->data.u32, "perf_cpu");
-
 	if (type & PERF_SAMPLE_PERIOD)
 		ADD_FIELD(event_class, cw->data.u64, "perf_period");
 
@@ -604,6 +857,39 @@ static int setup_events(struct ctf_writer *cw, struct perf_session *session)
 	return 0;
 }
 
+static int setup_streams(struct ctf_writer *cw, struct perf_session *session)
+{
+	struct ctf_stream **stream;
+	struct perf_header *ph = &session->header;
+	int ncpus;
+
+	/*
+	 * Try to get the number of cpus used in the data file,
+	 * if not present fallback to the MAX_CPUS.
+	 */
+	ncpus = ph->env.nr_cpus_avail ?: MAX_CPUS;
+
+	stream = zalloc(sizeof(*stream) * ncpus);
+	if (!stream) {
+		pr_err("Failed to allocate streams.\n");
+		return -ENOMEM;
+	}
+
+	cw->stream     = stream;
+	cw->stream_cnt = ncpus;
+	return 0;
+}
+
+static void free_streams(struct ctf_writer *cw)
+{
+	int cpu;
+
+	for (cpu = 0; cpu < cw->stream_cnt; cpu++)
+		ctf_stream__delete(cw->stream[cpu]);
+
+	free(cw->stream);
+}
+
 static int ctf_writer__setup_env(struct ctf_writer *cw,
 				 struct perf_session *session)
 {
@@ -713,7 +999,7 @@ static void ctf_writer__cleanup(struct ctf_writer *cw)
 	ctf_writer__cleanup_data(cw);
 
 	bt_ctf_clock_put(cw->clock);
-	bt_ctf_stream_put(cw->stream);
+	free_streams(cw);
 	bt_ctf_stream_class_put(cw->stream_class);
 	bt_ctf_writer_put(cw->writer);
 
@@ -725,8 +1011,9 @@ static int ctf_writer__init(struct ctf_writer *cw, const char *path)
 {
 	struct bt_ctf_writer		*writer;
 	struct bt_ctf_stream_class	*stream_class;
-	struct bt_ctf_stream		*stream;
 	struct bt_ctf_clock		*clock;
+	struct bt_ctf_field_type	*pkt_ctx_type;
+	int				ret;
 
 	/* CTF writer */
 	writer = bt_ctf_writer_create(path);
@@ -767,14 +1054,15 @@ static int ctf_writer__init(struct ctf_writer *cw, const char *path)
 	if (ctf_writer__init_data(cw))
 		goto err_cleanup;
 
-	/* CTF stream instance */
-	stream = bt_ctf_writer_create_stream(writer, stream_class);
-	if (!stream) {
-		pr("Failed to create CTF stream.\n");
+	/* Add cpu_id for packet context */
+	pkt_ctx_type = bt_ctf_stream_class_get_packet_context_type(stream_class);
+	if (!pkt_ctx_type)
 		goto err_cleanup;
-	}
 
-	cw->stream = stream;
+	ret = bt_ctf_field_type_structure_add_field(pkt_ctx_type, cw->data.u32, "cpu_id");
+	bt_ctf_field_type_put(pkt_ctx_type);
+	if (ret)
+		goto err_cleanup;
 
 	/* CTF clock writer setup */
 	if (bt_ctf_writer_add_clock(writer, clock)) {
@@ -791,6 +1079,28 @@ err:
 	return -1;
 }
 
+static int ctf_writer__flush_streams(struct ctf_writer *cw)
+{
+	int cpu, ret = 0;
+
+	for (cpu = 0; cpu < cw->stream_cnt && !ret; cpu++)
+		ret = ctf_stream__flush(cw->stream[cpu]);
+
+	return ret;
+}
+
+static int convert__config(const char *var, const char *value, void *cb)
+{
+	struct convert *c = cb;
+
+	if (!strcmp(var, "convert.queue-size")) {
+		c->queue_size = perf_config_u64(var, value);
+		return 0;
+	}
+
+	return perf_default_config(var, value, cb);
+}
+
 int bt_convert__perf2ctf(const char *input, const char *path, bool force)
 {
 	struct perf_session *session;
@@ -817,6 +1127,8 @@ int bt_convert__perf2ctf(const char *input, const char *path, bool force)
 	struct ctf_writer *cw = &c.writer;
 	int err = -1;
 
+	perf_config(convert__config, &c);
+
 	/* CTF writer */
 	if (ctf_writer__init(cw, path))
 		return -1;
@@ -826,6 +1138,11 @@ int bt_convert__perf2ctf(const char *input, const char *path, bool force)
 	if (!session)
 		goto free_writer;
 
+	if (c.queue_size) {
+		ordered_events__set_alloc_size(&session->ordered_events,
+					       c.queue_size);
+	}
+
 	/* CTF writer env/clock setup  */
 	if (ctf_writer__setup_env(cw, session))
 		goto free_session;
@@ -834,9 +1151,14 @@ int bt_convert__perf2ctf(const char *input, const char *path, bool force)
 	if (setup_events(cw, session))
 		goto free_session;
 
+	if (setup_streams(cw, session))
+		goto free_session;
+
 	err = perf_session__process_events(session);
 	if (!err)
-		err = bt_ctf_stream_flush(cw->stream);
+		err = ctf_writer__flush_streams(cw);
+	else
+		pr_err("Error during conversion.\n");
 
 	fprintf(stderr,
 		"[ perf data convert: Converted '%s' into CTF data '%s' ]\n",
@@ -847,11 +1169,15 @@ int bt_convert__perf2ctf(const char *input, const char *path, bool force)
 		(double) c.events_size / 1024.0 / 1024.0,
 		c.events_count);
 
-	/* its all good */
-free_session:
 	perf_session__delete(session);
+	ctf_writer__cleanup(cw);
+
+	return err;
 
+free_session:
+	perf_session__delete(session);
 free_writer:
 	ctf_writer__cleanup(cw);
+	pr_err("Error during conversion setup.\n");
 	return err;
 }
diff --git a/tools/perf/util/db-export.c b/tools/perf/util/db-export.c
index bb39a3ffc70b..1c9689e4cc17 100644
--- a/tools/perf/util/db-export.c
+++ b/tools/perf/util/db-export.c
@@ -122,6 +122,7 @@ int db_export__machine(struct db_export *dbe, struct machine *machine)
 int db_export__thread(struct db_export *dbe, struct thread *thread,
 		      struct machine *machine, struct comm *comm)
 {
+	struct thread *main_thread;
 	u64 main_thread_db_id = 0;
 	int err;
 
@@ -131,8 +132,6 @@ int db_export__thread(struct db_export *dbe, struct thread *thread,
 	thread->db_id = ++dbe->thread_last_db_id;
 
 	if (thread->pid_ != -1) {
-		struct thread *main_thread;
-
 		if (thread->pid_ == thread->tid) {
 			main_thread = thread;
 		} else {
@@ -144,14 +143,16 @@ int db_export__thread(struct db_export *dbe, struct thread *thread,
 			err = db_export__thread(dbe, main_thread, machine,
 						comm);
 			if (err)
-				return err;
+				goto out_put;
 			if (comm) {
 				err = db_export__comm_thread(dbe, comm, thread);
 				if (err)
-					return err;
+					goto out_put;
 			}
 		}
 		main_thread_db_id = main_thread->db_id;
+		if (main_thread != thread)
+			thread__put(main_thread);
 	}
 
 	if (dbe->export_thread)
@@ -159,6 +160,10 @@ int db_export__thread(struct db_export *dbe, struct thread *thread,
 					  machine);
 
 	return 0;
+
+out_put:
+	thread__put(main_thread);
+	return err;
 }
 
 int db_export__comm(struct db_export *dbe, struct comm *comm,
@@ -229,7 +234,7 @@ int db_export__symbol(struct db_export *dbe, struct symbol *sym,
 static struct thread *get_main_thread(struct machine *machine, struct thread *thread)
 {
 	if (thread->pid_ == thread->tid)
-		return thread;
+		return thread__get(thread);
 
 	if (thread->pid_ == -1)
 		return NULL;
@@ -309,12 +314,12 @@ int db_export__sample(struct db_export *dbe, union perf_event *event,
 
 	err = db_export__thread(dbe, thread, al->machine, comm);
 	if (err)
-		return err;
+		goto out_put;
 
 	if (comm) {
 		err = db_export__comm(dbe, comm, main_thread);
 		if (err)
-			return err;
+			goto out_put;
 		es.comm_db_id = comm->db_id;
 	}
 
@@ -322,7 +327,7 @@ int db_export__sample(struct db_export *dbe, union perf_event *event,
 
 	err = db_ids_from_al(dbe, al, &es.dso_db_id, &es.sym_db_id, &es.offset);
 	if (err)
-		return err;
+		goto out_put;
 
 	if ((evsel->attr.sample_type & PERF_SAMPLE_ADDR) &&
 	    sample_addr_correlates_sym(&evsel->attr)) {
@@ -332,20 +337,22 @@ int db_export__sample(struct db_export *dbe, union perf_event *event,
 		err = db_ids_from_al(dbe, &addr_al, &es.addr_dso_db_id,
 				     &es.addr_sym_db_id, &es.addr_offset);
 		if (err)
-			return err;
+			goto out_put;
 		if (dbe->crp) {
 			err = thread_stack__process(thread, comm, sample, al,
 						    &addr_al, es.db_id,
 						    dbe->crp);
 			if (err)
-				return err;
+				goto out_put;
 		}
 	}
 
 	if (dbe->export_sample)
-		return dbe->export_sample(dbe, &es);
+		err = dbe->export_sample(dbe, &es);
 
-	return 0;
+out_put:
+	thread__put(main_thread);
+	return err;
 }
 
 static struct {
diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c
index fc0ddd5792a9..7c0c08386a1d 100644
--- a/tools/perf/util/dso.c
+++ b/tools/perf/util/dso.c
@@ -4,6 +4,7 @@
 #include "symbol.h"
 #include "dso.h"
 #include "machine.h"
+#include "auxtrace.h"
 #include "util.h"
 #include "debug.h"
 
@@ -165,12 +166,28 @@ bool is_supported_compression(const char *ext)
 	return false;
 }
 
-bool is_kernel_module(const char *pathname)
+bool is_kernel_module(const char *pathname, int cpumode)
 {
 	struct kmod_path m;
-
-	if (kmod_path__parse(&m, pathname))
-		return NULL;
+	int mode = cpumode & PERF_RECORD_MISC_CPUMODE_MASK;
+
+	WARN_ONCE(mode != cpumode,
+		  "Internal error: passing unmasked cpumode (%x) to is_kernel_module",
+		  cpumode);
+
+	switch (mode) {
+	case PERF_RECORD_MISC_USER:
+	case PERF_RECORD_MISC_HYPERVISOR:
+	case PERF_RECORD_MISC_GUEST_USER:
+		return false;
+	/* Treat PERF_RECORD_MISC_CPUMODE_UNKNOWN as kernel */
+	default:
+		if (kmod_path__parse(&m, pathname)) {
+			pr_err("Failed to check whether %s is a kernel module or not. Assume it is.",
+					pathname);
+			return true;
+		}
+	}
 
 	return m.kmod;
 }
@@ -214,12 +231,33 @@ int __kmod_path__parse(struct kmod_path *m, const char *path,
 {
 	const char *name = strrchr(path, '/');
 	const char *ext  = strrchr(path, '.');
+	bool is_simple_name = false;
 
 	memset(m, 0x0, sizeof(*m));
 	name = name ? name + 1 : path;
 
+	/*
+	 * '.' is also a valid character for module name. For example:
+	 * [aaa.bbb] is a valid module name. '[' should have higher
+	 * priority than '.ko' suffix.
+	 *
+	 * The kernel names are from machine__mmap_name. Such
+	 * name should belong to kernel itself, not kernel module.
+	 */
+	if (name[0] == '[') {
+		is_simple_name = true;
+		if ((strncmp(name, "[kernel.kallsyms]", 17) == 0) ||
+		    (strncmp(name, "[guest.kernel.kallsyms", 22) == 0) ||
+		    (strncmp(name, "[vdso]", 6) == 0) ||
+		    (strncmp(name, "[vsyscall]", 10) == 0)) {
+			m->kmod = false;
+
+		} else
+			m->kmod = true;
+	}
+
 	/* No extension, just return name. */
-	if (ext == NULL) {
+	if ((ext == NULL) || is_simple_name) {
 		if (alloc_name) {
 			m->name = strdup(name);
 			return m->name ? 0 : -ENOMEM;
@@ -264,6 +302,7 @@ int __kmod_path__parse(struct kmod_path *m, const char *path,
  */
 static LIST_HEAD(dso__data_open);
 static long dso__data_open_cnt;
+static pthread_mutex_t dso__data_open_lock = PTHREAD_MUTEX_INITIALIZER;
 
 static void dso__list_add(struct dso *dso)
 {
@@ -433,18 +472,12 @@ static void check_data_close(void)
  */
 void dso__data_close(struct dso *dso)
 {
+	pthread_mutex_lock(&dso__data_open_lock);
 	close_dso(dso);
+	pthread_mutex_unlock(&dso__data_open_lock);
 }
 
-/**
- * dso__data_fd - Get dso's data file descriptor
- * @dso: dso object
- * @machine: machine object
- *
- * External interface to find dso's file, open it and
- * returns file descriptor.
- */
-int dso__data_fd(struct dso *dso, struct machine *machine)
+static void try_to_open_dso(struct dso *dso, struct machine *machine)
 {
 	enum dso_binary_type binary_type_data[] = {
 		DSO_BINARY_TYPE__BUILD_ID_CACHE,
@@ -453,11 +486,8 @@ int dso__data_fd(struct dso *dso, struct machine *machine)
 	};
 	int i = 0;
 
-	if (dso->data.status == DSO_DATA_STATUS_ERROR)
-		return -1;
-
 	if (dso->data.fd >= 0)
-		goto out;
+		return;
 
 	if (dso->binary_type != DSO_BINARY_TYPE__NOT_FOUND) {
 		dso->data.fd = open_dso(dso, machine);
@@ -477,10 +507,38 @@ out:
 		dso->data.status = DSO_DATA_STATUS_OK;
 	else
 		dso->data.status = DSO_DATA_STATUS_ERROR;
+}
+
+/**
+ * dso__data_get_fd - Get dso's data file descriptor
+ * @dso: dso object
+ * @machine: machine object
+ *
+ * External interface to find dso's file, open it and
+ * returns file descriptor.  It should be paired with
+ * dso__data_put_fd() if it returns non-negative value.
+ */
+int dso__data_get_fd(struct dso *dso, struct machine *machine)
+{
+	if (dso->data.status == DSO_DATA_STATUS_ERROR)
+		return -1;
+
+	if (pthread_mutex_lock(&dso__data_open_lock) < 0)
+		return -1;
+
+	try_to_open_dso(dso, machine);
+
+	if (dso->data.fd < 0)
+		pthread_mutex_unlock(&dso__data_open_lock);
 
 	return dso->data.fd;
 }
 
+void dso__data_put_fd(struct dso *dso __maybe_unused)
+{
+	pthread_mutex_unlock(&dso__data_open_lock);
+}
+
 bool dso__data_status_seen(struct dso *dso, enum dso_data_status_seen by)
 {
 	u32 flag = 1 << by;
@@ -494,10 +552,12 @@ bool dso__data_status_seen(struct dso *dso, enum dso_data_status_seen by)
 }
 
 static void
-dso_cache__free(struct rb_root *root)
+dso_cache__free(struct dso *dso)
 {
+	struct rb_root *root = &dso->data.cache;
 	struct rb_node *next = rb_first(root);
 
+	pthread_mutex_lock(&dso->lock);
 	while (next) {
 		struct dso_cache *cache;
 
@@ -506,10 +566,12 @@ dso_cache__free(struct rb_root *root)
 		rb_erase(&cache->rb_node, root);
 		free(cache);
 	}
+	pthread_mutex_unlock(&dso->lock);
 }
 
-static struct dso_cache *dso_cache__find(const struct rb_root *root, u64 offset)
+static struct dso_cache *dso_cache__find(struct dso *dso, u64 offset)
 {
+	const struct rb_root *root = &dso->data.cache;
 	struct rb_node * const *p = &root->rb_node;
 	const struct rb_node *parent = NULL;
 	struct dso_cache *cache;
@@ -528,17 +590,20 @@ static struct dso_cache *dso_cache__find(const struct rb_root *root, u64 offset)
 		else
 			return cache;
 	}
+
 	return NULL;
 }
 
-static void
-dso_cache__insert(struct rb_root *root, struct dso_cache *new)
+static struct dso_cache *
+dso_cache__insert(struct dso *dso, struct dso_cache *new)
 {
+	struct rb_root *root = &dso->data.cache;
 	struct rb_node **p = &root->rb_node;
 	struct rb_node *parent = NULL;
 	struct dso_cache *cache;
 	u64 offset = new->offset;
 
+	pthread_mutex_lock(&dso->lock);
 	while (*p != NULL) {
 		u64 end;
 
@@ -550,10 +615,17 @@ dso_cache__insert(struct rb_root *root, struct dso_cache *new)
 			p = &(*p)->rb_left;
 		else if (offset >= end)
 			p = &(*p)->rb_right;
+		else
+			goto out;
 	}
 
 	rb_link_node(&new->rb_node, parent, p);
 	rb_insert_color(&new->rb_node, root);
+
+	cache = NULL;
+out:
+	pthread_mutex_unlock(&dso->lock);
+	return cache;
 }
 
 static ssize_t
@@ -568,19 +640,33 @@ dso_cache__memcpy(struct dso_cache *cache, u64 offset,
 }
 
 static ssize_t
-dso_cache__read(struct dso *dso, u64 offset, u8 *data, ssize_t size)
+dso_cache__read(struct dso *dso, struct machine *machine,
+		u64 offset, u8 *data, ssize_t size)
 {
 	struct dso_cache *cache;
+	struct dso_cache *old;
 	ssize_t ret;
 
 	do {
 		u64 cache_offset;
 
-		ret = -ENOMEM;
-
 		cache = zalloc(sizeof(*cache) + DSO__DATA_CACHE_SIZE);
 		if (!cache)
+			return -ENOMEM;
+
+		pthread_mutex_lock(&dso__data_open_lock);
+
+		/*
+		 * dso->data.fd might be closed if other thread opened another
+		 * file (dso) due to open file limit (RLIMIT_NOFILE).
+		 */
+		try_to_open_dso(dso, machine);
+
+		if (dso->data.fd < 0) {
+			ret = -errno;
+			dso->data.status = DSO_DATA_STATUS_ERROR;
 			break;
+		}
 
 		cache_offset = offset & DSO__DATA_CACHE_MASK;
 
@@ -590,11 +676,20 @@ dso_cache__read(struct dso *dso, u64 offset, u8 *data, ssize_t size)
 
 		cache->offset = cache_offset;
 		cache->size   = ret;
-		dso_cache__insert(&dso->data.cache, cache);
+	} while (0);
 
-		ret = dso_cache__memcpy(cache, offset, data, size);
+	pthread_mutex_unlock(&dso__data_open_lock);
 
-	} while (0);
+	if (ret > 0) {
+		old = dso_cache__insert(dso, cache);
+		if (old) {
+			/* we lose the race */
+			free(cache);
+			cache = old;
+		}
+
+		ret = dso_cache__memcpy(cache, offset, data, size);
+	}
 
 	if (ret <= 0)
 		free(cache);
@@ -602,16 +697,16 @@ dso_cache__read(struct dso *dso, u64 offset, u8 *data, ssize_t size)
 	return ret;
 }
 
-static ssize_t dso_cache_read(struct dso *dso, u64 offset,
-			      u8 *data, ssize_t size)
+static ssize_t dso_cache_read(struct dso *dso, struct machine *machine,
+			      u64 offset, u8 *data, ssize_t size)
 {
 	struct dso_cache *cache;
 
-	cache = dso_cache__find(&dso->data.cache, offset);
+	cache = dso_cache__find(dso, offset);
 	if (cache)
 		return dso_cache__memcpy(cache, offset, data, size);
 	else
-		return dso_cache__read(dso, offset, data, size);
+		return dso_cache__read(dso, machine, offset, data, size);
 }
 
 /*
@@ -619,7 +714,8 @@ static ssize_t dso_cache_read(struct dso *dso, u64 offset,
  * in the rb_tree. Any read to already cached data is served
  * by cached data.
  */
-static ssize_t cached_read(struct dso *dso, u64 offset, u8 *data, ssize_t size)
+static ssize_t cached_read(struct dso *dso, struct machine *machine,
+			   u64 offset, u8 *data, ssize_t size)
 {
 	ssize_t r = 0;
 	u8 *p = data;
@@ -627,7 +723,7 @@ static ssize_t cached_read(struct dso *dso, u64 offset, u8 *data, ssize_t size)
 	do {
 		ssize_t ret;
 
-		ret = dso_cache_read(dso, offset, p, size);
+		ret = dso_cache_read(dso, machine, offset, p, size);
 		if (ret < 0)
 			return ret;
 
@@ -647,21 +743,44 @@ static ssize_t cached_read(struct dso *dso, u64 offset, u8 *data, ssize_t size)
 	return r;
 }
 
-static int data_file_size(struct dso *dso)
+static int data_file_size(struct dso *dso, struct machine *machine)
 {
+	int ret = 0;
 	struct stat st;
 	char sbuf[STRERR_BUFSIZE];
 
-	if (!dso->data.file_size) {
-		if (fstat(dso->data.fd, &st)) {
-			pr_err("dso mmap failed, fstat: %s\n",
-				strerror_r(errno, sbuf, sizeof(sbuf)));
-			return -1;
-		}
-		dso->data.file_size = st.st_size;
+	if (dso->data.file_size)
+		return 0;
+
+	if (dso->data.status == DSO_DATA_STATUS_ERROR)
+		return -1;
+
+	pthread_mutex_lock(&dso__data_open_lock);
+
+	/*
+	 * dso->data.fd might be closed if other thread opened another
+	 * file (dso) due to open file limit (RLIMIT_NOFILE).
+	 */
+	try_to_open_dso(dso, machine);
+
+	if (dso->data.fd < 0) {
+		ret = -errno;
+		dso->data.status = DSO_DATA_STATUS_ERROR;
+		goto out;
 	}
 
-	return 0;
+	if (fstat(dso->data.fd, &st) < 0) {
+		ret = -errno;
+		pr_err("dso cache fstat failed: %s\n",
+		       strerror_r(errno, sbuf, sizeof(sbuf)));
+		dso->data.status = DSO_DATA_STATUS_ERROR;
+		goto out;
+	}
+	dso->data.file_size = st.st_size;
+
+out:
+	pthread_mutex_unlock(&dso__data_open_lock);
+	return ret;
 }
 
 /**
@@ -673,23 +792,17 @@ static int data_file_size(struct dso *dso)
  */
 off_t dso__data_size(struct dso *dso, struct machine *machine)
 {
-	int fd;
-
-	fd = dso__data_fd(dso, machine);
-	if (fd < 0)
-		return fd;
-
-	if (data_file_size(dso))
+	if (data_file_size(dso, machine))
 		return -1;
 
 	/* For now just estimate dso data size is close to file size */
 	return dso->data.file_size;
 }
 
-static ssize_t data_read_offset(struct dso *dso, u64 offset,
-				u8 *data, ssize_t size)
+static ssize_t data_read_offset(struct dso *dso, struct machine *machine,
+				u64 offset, u8 *data, ssize_t size)
 {
-	if (data_file_size(dso))
+	if (data_file_size(dso, machine))
 		return -1;
 
 	/* Check the offset sanity. */
@@ -699,7 +812,7 @@ static ssize_t data_read_offset(struct dso *dso, u64 offset,
 	if (offset + size < offset)
 		return -1;
 
-	return cached_read(dso, offset, data, size);
+	return cached_read(dso, machine, offset, data, size);
 }
 
 /**
@@ -716,10 +829,10 @@ static ssize_t data_read_offset(struct dso *dso, u64 offset,
 ssize_t dso__data_read_offset(struct dso *dso, struct machine *machine,
 			      u64 offset, u8 *data, ssize_t size)
 {
-	if (dso__data_fd(dso, machine) < 0)
+	if (dso->data.status == DSO_DATA_STATUS_ERROR)
 		return -1;
 
-	return data_read_offset(dso, offset, data, size);
+	return data_read_offset(dso, machine, offset, data, size);
 }
 
 /**
@@ -751,13 +864,13 @@ struct map *dso__new_map(const char *name)
 	return map;
 }
 
-struct dso *dso__kernel_findnew(struct machine *machine, const char *name,
-		    const char *short_name, int dso_type)
+struct dso *machine__findnew_kernel(struct machine *machine, const char *name,
+				    const char *short_name, int dso_type)
 {
 	/*
 	 * The kernel dso could be created by build_id processing.
 	 */
-	struct dso *dso = __dsos__findnew(&machine->kernel_dsos, name);
+	struct dso *dso = machine__findnew_dso(machine, name);
 
 	/*
 	 * We need to run this in all cases, since during the build_id
@@ -776,8 +889,8 @@ struct dso *dso__kernel_findnew(struct machine *machine, const char *name,
  * Either one of the dso or name parameter must be non-NULL or the
  * function will not work.
  */
-static struct dso *dso__findlink_by_longname(struct rb_root *root,
-					     struct dso *dso, const char *name)
+static struct dso *__dso__findlink_by_longname(struct rb_root *root,
+					       struct dso *dso, const char *name)
 {
 	struct rb_node **p = &root->rb_node;
 	struct rb_node  *parent = NULL;
@@ -824,10 +937,10 @@ static struct dso *dso__findlink_by_longname(struct rb_root *root,
 	return NULL;
 }
 
-static inline struct dso *
-dso__find_by_longname(const struct rb_root *root, const char *name)
+static inline struct dso *__dso__find_by_longname(struct rb_root *root,
+						  const char *name)
 {
-	return dso__findlink_by_longname((struct rb_root *)root, NULL, name);
+	return __dso__findlink_by_longname(root, NULL, name);
 }
 
 void dso__set_long_name(struct dso *dso, const char *name, bool name_allocated)
@@ -935,6 +1048,8 @@ struct dso *dso__new(const char *name)
 		RB_CLEAR_NODE(&dso->rb_node);
 		INIT_LIST_HEAD(&dso->node);
 		INIT_LIST_HEAD(&dso->data.open_entry);
+		pthread_mutex_init(&dso->lock, NULL);
+		atomic_set(&dso->refcnt, 1);
 	}
 
 	return dso;
@@ -961,12 +1076,27 @@ void dso__delete(struct dso *dso)
 	}
 
 	dso__data_close(dso);
-	dso_cache__free(&dso->data.cache);
+	auxtrace_cache__free(dso->auxtrace_cache);
+	dso_cache__free(dso);
 	dso__free_a2l(dso);
 	zfree(&dso->symsrc_filename);
+	pthread_mutex_destroy(&dso->lock);
 	free(dso);
 }
 
+struct dso *dso__get(struct dso *dso)
+{
+	if (dso)
+		atomic_inc(&dso->refcnt);
+	return dso;
+}
+
+void dso__put(struct dso *dso)
+{
+	if (dso && atomic_dec_and_test(&dso->refcnt))
+		dso__delete(dso);
+}
+
 void dso__set_build_id(struct dso *dso, void *build_id)
 {
 	memcpy(dso->build_id, build_id, sizeof(dso->build_id));
@@ -1033,14 +1163,41 @@ bool __dsos__read_build_ids(struct list_head *head, bool with_hits)
 	return have_build_id;
 }
 
-void dsos__add(struct dsos *dsos, struct dso *dso)
+void __dsos__add(struct dsos *dsos, struct dso *dso)
 {
 	list_add_tail(&dso->node, &dsos->head);
-	dso__findlink_by_longname(&dsos->root, dso, NULL);
+	__dso__findlink_by_longname(&dsos->root, dso, NULL);
+	/*
+	 * It is now in the linked list, grab a reference, then garbage collect
+	 * this when needing memory, by looking at LRU dso instances in the
+	 * list with atomic_read(&dso->refcnt) == 1, i.e. no references
+	 * anywhere besides the one for the list, do, under a lock for the
+	 * list: remove it from the list, then a dso__put(), that probably will
+	 * be the last and will then call dso__delete(), end of life.
+	 *
+	 * That, or at the end of the 'struct machine' lifetime, when all
+	 * 'struct dso' instances will be removed from the list, in
+	 * dsos__exit(), if they have no other reference from some other data
+	 * structure.
+	 *
+	 * E.g.: after processing a 'perf.data' file and storing references
+	 * to objects instantiated while processing events, we will have
+	 * references to the 'thread', 'map', 'dso' structs all from 'struct
+	 * hist_entry' instances, but we may not need anything not referenced,
+	 * so we might as well call machines__exit()/machines__delete() and
+	 * garbage collect it.
+	 */
+	dso__get(dso);
+}
+
+void dsos__add(struct dsos *dsos, struct dso *dso)
+{
+	pthread_rwlock_wrlock(&dsos->lock);
+	__dsos__add(dsos, dso);
+	pthread_rwlock_unlock(&dsos->lock);
 }
 
-struct dso *dsos__find(const struct dsos *dsos, const char *name,
-		       bool cmp_short)
+struct dso *__dsos__find(struct dsos *dsos, const char *name, bool cmp_short)
 {
 	struct dso *pos;
 
@@ -1050,15 +1207,24 @@ struct dso *dsos__find(const struct dsos *dsos, const char *name,
 				return pos;
 		return NULL;
 	}
-	return dso__find_by_longname(&dsos->root, name);
+	return __dso__find_by_longname(&dsos->root, name);
+}
+
+struct dso *dsos__find(struct dsos *dsos, const char *name, bool cmp_short)
+{
+	struct dso *dso;
+	pthread_rwlock_rdlock(&dsos->lock);
+	dso = __dsos__find(dsos, name, cmp_short);
+	pthread_rwlock_unlock(&dsos->lock);
+	return dso;
 }
 
-struct dso *dsos__addnew(struct dsos *dsos, const char *name)
+struct dso *__dsos__addnew(struct dsos *dsos, const char *name)
 {
 	struct dso *dso = dso__new(name);
 
 	if (dso != NULL) {
-		dsos__add(dsos, dso);
+		__dsos__add(dsos, dso);
 		dso__set_basename(dso);
 	}
 	return dso;
@@ -1066,9 +1232,18 @@ struct dso *dsos__addnew(struct dsos *dsos, const char *name)
 
 struct dso *__dsos__findnew(struct dsos *dsos, const char *name)
 {
-	struct dso *dso = dsos__find(dsos, name, false);
+	struct dso *dso = __dsos__find(dsos, name, false);
 
-	return dso ? dso : dsos__addnew(dsos, name);
+	return dso ? dso : __dsos__addnew(dsos, name);
+}
+
+struct dso *dsos__findnew(struct dsos *dsos, const char *name)
+{
+	struct dso *dso;
+	pthread_rwlock_wrlock(&dsos->lock);
+	dso = dso__get(__dsos__findnew(dsos, name));
+	pthread_rwlock_unlock(&dsos->lock);
+	return dso;
 }
 
 size_t __dsos__fprintf_buildid(struct list_head *head, FILE *fp,
@@ -1130,12 +1305,15 @@ size_t dso__fprintf(struct dso *dso, enum map_type type, FILE *fp)
 enum dso_type dso__type(struct dso *dso, struct machine *machine)
 {
 	int fd;
+	enum dso_type type = DSO__TYPE_UNKNOWN;
 
-	fd = dso__data_fd(dso, machine);
-	if (fd < 0)
-		return DSO__TYPE_UNKNOWN;
+	fd = dso__data_get_fd(dso, machine);
+	if (fd >= 0) {
+		type = dso__type_fd(fd);
+		dso__data_put_fd(dso);
+	}
 
-	return dso__type_fd(fd);
+	return type;
 }
 
 int dso__strerror_load(struct dso *dso, char *buf, size_t buflen)
diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h
index e0901b4ed8de..2fe98bb0e95b 100644
--- a/tools/perf/util/dso.h
+++ b/tools/perf/util/dso.h
@@ -1,9 +1,11 @@
 #ifndef __PERF_DSO
 #define __PERF_DSO
 
+#include <linux/atomic.h>
 #include <linux/types.h>
 #include <linux/rbtree.h>
 #include <stdbool.h>
+#include <pthread.h>
 #include <linux/types.h>
 #include <linux/bitops.h>
 #include "map.h"
@@ -124,9 +126,13 @@ struct dso_cache {
 struct dsos {
 	struct list_head head;
 	struct rb_root	 root;	/* rbtree root sorted by long name */
+	pthread_rwlock_t lock;
 };
 
+struct auxtrace_cache;
+
 struct dso {
+	pthread_mutex_t	 lock;
 	struct list_head node;
 	struct rb_node	 rb_node;	/* rbtree node sorted by long name */
 	struct rb_root	 symbols[MAP__NR_TYPES];
@@ -156,6 +162,7 @@ struct dso {
 	u16		 long_name_len;
 	u16		 short_name_len;
 	void		*dwfl;			/* DWARF debug info */
+	struct auxtrace_cache *auxtrace_cache;
 
 	/* dso data file */
 	struct {
@@ -173,7 +180,7 @@ struct dso {
 		void	 *priv;
 		u64	 db_id;
 	};
-
+	atomic_t	 refcnt;
 	char		 name[0];
 };
 
@@ -200,6 +207,17 @@ void dso__set_long_name(struct dso *dso, const char *name, bool name_allocated);
 
 int dso__name_len(const struct dso *dso);
 
+struct dso *dso__get(struct dso *dso);
+void dso__put(struct dso *dso);
+
+static inline void __dso__zput(struct dso **dso)
+{
+	dso__put(*dso);
+	*dso = NULL;
+}
+
+#define dso__zput(dso) __dso__zput(&dso)
+
 bool dso__loaded(const struct dso *dso, enum map_type type);
 
 bool dso__sorted_by_name(const struct dso *dso, enum map_type type);
@@ -216,7 +234,7 @@ char dso__symtab_origin(const struct dso *dso);
 int dso__read_binary_type_filename(const struct dso *dso, enum dso_binary_type type,
 				   char *root_dir, char *filename, size_t size);
 bool is_supported_compression(const char *ext);
-bool is_kernel_module(const char *pathname);
+bool is_kernel_module(const char *pathname, int cpumode);
 bool decompress_to_file(const char *ext, const char *filename, int output_fd);
 bool dso__needs_decompress(struct dso *dso);
 
@@ -236,7 +254,8 @@ int __kmod_path__parse(struct kmod_path *m, const char *path,
 
 /*
  * The dso__data_* external interface provides following functions:
- *   dso__data_fd
+ *   dso__data_get_fd
+ *   dso__data_put_fd
  *   dso__data_close
  *   dso__data_size
  *   dso__data_read_offset
@@ -253,8 +272,11 @@ int __kmod_path__parse(struct kmod_path *m, const char *path,
  * The current usage of the dso__data_* interface is as follows:
  *
  * Get DSO's fd:
- *   int fd = dso__data_fd(dso, machine);
- *   USE 'fd' SOMEHOW
+ *   int fd = dso__data_get_fd(dso, machine);
+ *   if (fd >= 0) {
+ *       USE 'fd' SOMEHOW
+ *       dso__data_put_fd(dso);
+ *   }
  *
  * Read DSO's data:
  *   n = dso__data_read_offset(dso_0, &machine, 0, buf, BUFSIZE);
@@ -273,7 +295,8 @@ int __kmod_path__parse(struct kmod_path *m, const char *path,
  *
  * TODO
 */
-int dso__data_fd(struct dso *dso, struct machine *machine);
+int dso__data_get_fd(struct dso *dso, struct machine *machine);
+void dso__data_put_fd(struct dso *dso __maybe_unused);
 void dso__data_close(struct dso *dso);
 
 off_t dso__data_size(struct dso *dso, struct machine *machine);
@@ -285,14 +308,16 @@ ssize_t dso__data_read_addr(struct dso *dso, struct map *map,
 bool dso__data_status_seen(struct dso *dso, enum dso_data_status_seen by);
 
 struct map *dso__new_map(const char *name);
-struct dso *dso__kernel_findnew(struct machine *machine, const char *name,
-				const char *short_name, int dso_type);
+struct dso *machine__findnew_kernel(struct machine *machine, const char *name,
+				    const char *short_name, int dso_type);
 
+void __dsos__add(struct dsos *dsos, struct dso *dso);
 void dsos__add(struct dsos *dsos, struct dso *dso);
-struct dso *dsos__addnew(struct dsos *dsos, const char *name);
-struct dso *dsos__find(const struct dsos *dsos, const char *name,
-		       bool cmp_short);
+struct dso *__dsos__addnew(struct dsos *dsos, const char *name);
+struct dso *__dsos__find(struct dsos *dsos, const char *name, bool cmp_short);
+struct dso *dsos__find(struct dsos *dsos, const char *name, bool cmp_short);
 struct dso *__dsos__findnew(struct dsos *dsos, const char *name);
+struct dso *dsos__findnew(struct dsos *dsos, const char *name);
 bool __dsos__read_build_ids(struct list_head *head, bool with_hits);
 
 size_t __dsos__fprintf_buildid(struct list_head *head, FILE *fp,
diff --git a/tools/perf/util/dwarf-aux.c b/tools/perf/util/dwarf-aux.c
index c34e024020c7..57f3ef41c2bc 100644
--- a/tools/perf/util/dwarf-aux.c
+++ b/tools/perf/util/dwarf-aux.c
@@ -139,11 +139,27 @@ int cu_walk_functions_at(Dwarf_Die *cu_die, Dwarf_Addr addr,
 bool die_compare_name(Dwarf_Die *dw_die, const char *tname)
 {
 	const char *name;
+
 	name = dwarf_diename(dw_die);
 	return name ? (strcmp(tname, name) == 0) : false;
 }
 
 /**
+ * die_match_name - Match diename and glob
+ * @dw_die: a DIE
+ * @glob: a string of target glob pattern
+ *
+ * Glob matching the name of @dw_die and @glob. Return false if matching fail.
+ */
+bool die_match_name(Dwarf_Die *dw_die, const char *glob)
+{
+	const char *name;
+
+	name = dwarf_diename(dw_die);
+	return name ? strglobmatch(name, glob) : false;
+}
+
+/**
  * die_get_call_lineno - Get callsite line number of inline-function instance
  * @in_die: a DIE of an inlined function instance
  *
@@ -417,6 +433,43 @@ struct __addr_die_search_param {
 	Dwarf_Die	*die_mem;
 };
 
+static int __die_search_func_tail_cb(Dwarf_Die *fn_die, void *data)
+{
+	struct __addr_die_search_param *ad = data;
+	Dwarf_Addr addr = 0;
+
+	if (dwarf_tag(fn_die) == DW_TAG_subprogram &&
+	    !dwarf_highpc(fn_die, &addr) &&
+	    addr == ad->addr) {
+		memcpy(ad->die_mem, fn_die, sizeof(Dwarf_Die));
+		return DWARF_CB_ABORT;
+	}
+	return DWARF_CB_OK;
+}
+
+/**
+ * die_find_tailfunc - Search for a non-inlined function with tail call at
+ * given address
+ * @cu_die: a CU DIE which including @addr
+ * @addr: target address
+ * @die_mem: a buffer for result DIE
+ *
+ * Search for a non-inlined function DIE with tail call at @addr. Stores the
+ * DIE to @die_mem and returns it if found. Returns NULL if failed.
+ */
+Dwarf_Die *die_find_tailfunc(Dwarf_Die *cu_die, Dwarf_Addr addr,
+				    Dwarf_Die *die_mem)
+{
+	struct __addr_die_search_param ad;
+	ad.addr = addr;
+	ad.die_mem = die_mem;
+	/* dwarf_getscopes can't find subprogram. */
+	if (!dwarf_getfuncs(cu_die, __die_search_func_tail_cb, &ad, 0))
+		return NULL;
+	else
+		return die_mem;
+}
+
 /* die_find callback for non-inlined function search */
 static int __die_search_func_cb(Dwarf_Die *fn_die, void *data)
 {
@@ -832,19 +885,17 @@ Dwarf_Die *die_find_member(Dwarf_Die *st_die, const char *name,
 /**
  * die_get_typename - Get the name of given variable DIE
  * @vr_die: a variable DIE
- * @buf: a buffer for result type name
- * @len: a max-length of @buf
+ * @buf: a strbuf for result type name
  *
- * Get the name of @vr_die and stores it to @buf. Return the actual length
- * of type name if succeeded. Return -E2BIG if @len is not enough long, and
- * Return -ENOENT if failed to find type name.
+ * Get the name of @vr_die and stores it to @buf. Return 0 if succeeded.
+ * and Return -ENOENT if failed to find type name.
  * Note that the result will stores typedef name if possible, and stores
  * "*(function_type)" if the type is a function pointer.
  */
-int die_get_typename(Dwarf_Die *vr_die, char *buf, int len)
+int die_get_typename(Dwarf_Die *vr_die, struct strbuf *buf)
 {
 	Dwarf_Die type;
-	int tag, ret, ret2;
+	int tag, ret;
 	const char *tmp = "";
 
 	if (__die_get_real_type(vr_die, &type) == NULL)
@@ -855,8 +906,8 @@ int die_get_typename(Dwarf_Die *vr_die, char *buf, int len)
 		tmp = "*";
 	else if (tag == DW_TAG_subroutine_type) {
 		/* Function pointer */
-		ret = snprintf(buf, len, "(function_type)");
-		return (ret >= len) ? -E2BIG : ret;
+		strbuf_addf(buf, "(function_type)");
+		return 0;
 	} else {
 		if (!dwarf_diename(&type))
 			return -ENOENT;
@@ -867,39 +918,156 @@ int die_get_typename(Dwarf_Die *vr_die, char *buf, int len)
 		else if (tag == DW_TAG_enumeration_type)
 			tmp = "enum ";
 		/* Write a base name */
-		ret = snprintf(buf, len, "%s%s", tmp, dwarf_diename(&type));
-		return (ret >= len) ? -E2BIG : ret;
-	}
-	ret = die_get_typename(&type, buf, len);
-	if (ret > 0) {
-		ret2 = snprintf(buf + ret, len - ret, "%s", tmp);
-		ret = (ret2 >= len - ret) ? -E2BIG : ret2 + ret;
+		strbuf_addf(buf, "%s%s", tmp, dwarf_diename(&type));
+		return 0;
 	}
+	ret = die_get_typename(&type, buf);
+	if (ret == 0)
+		strbuf_addf(buf, "%s", tmp);
+
 	return ret;
 }
 
 /**
  * die_get_varname - Get the name and type of given variable DIE
  * @vr_die: a variable DIE
- * @buf: a buffer for type and variable name
- * @len: the max-length of @buf
+ * @buf: a strbuf for type and variable name
  *
  * Get the name and type of @vr_die and stores it in @buf as "type\tname".
  */
-int die_get_varname(Dwarf_Die *vr_die, char *buf, int len)
+int die_get_varname(Dwarf_Die *vr_die, struct strbuf *buf)
 {
-	int ret, ret2;
+	int ret;
 
-	ret = die_get_typename(vr_die, buf, len);
+	ret = die_get_typename(vr_die, buf);
 	if (ret < 0) {
 		pr_debug("Failed to get type, make it unknown.\n");
-		ret = snprintf(buf, len, "(unknown_type)");
+		strbuf_addf(buf, "(unknown_type)");
 	}
-	if (ret > 0) {
-		ret2 = snprintf(buf + ret, len - ret, "\t%s",
-				dwarf_diename(vr_die));
-		ret = (ret2 >= len - ret) ? -E2BIG : ret2 + ret;
+
+	strbuf_addf(buf, "\t%s", dwarf_diename(vr_die));
+
+	return 0;
+}
+
+/**
+ * die_get_var_innermost_scope - Get innermost scope range of given variable DIE
+ * @sp_die: a subprogram DIE
+ * @vr_die: a variable DIE
+ * @buf: a strbuf for variable byte offset range
+ *
+ * Get the innermost scope range of @vr_die and stores it in @buf as
+ * "@<function_name+[NN-NN,NN-NN]>".
+ */
+static int die_get_var_innermost_scope(Dwarf_Die *sp_die, Dwarf_Die *vr_die,
+				struct strbuf *buf)
+{
+	Dwarf_Die *scopes;
+	int count;
+	size_t offset = 0;
+	Dwarf_Addr base;
+	Dwarf_Addr start, end;
+	Dwarf_Addr entry;
+	int ret;
+	bool first = true;
+	const char *name;
+
+	ret = dwarf_entrypc(sp_die, &entry);
+	if (ret)
+		return ret;
+
+	name = dwarf_diename(sp_die);
+	if (!name)
+		return -ENOENT;
+
+	count = dwarf_getscopes_die(vr_die, &scopes);
+
+	/* (*SCOPES)[1] is the DIE for the scope containing that scope */
+	if (count <= 1) {
+		ret = -EINVAL;
+		goto out;
 	}
+
+	while ((offset = dwarf_ranges(&scopes[1], offset, &base,
+				&start, &end)) > 0) {
+		start -= entry;
+		end -= entry;
+
+		if (first) {
+			strbuf_addf(buf, "@<%s+[%" PRIu64 "-%" PRIu64,
+				name, start, end);
+			first = false;
+		} else {
+			strbuf_addf(buf, ",%" PRIu64 "-%" PRIu64,
+				start, end);
+		}
+	}
+
+	if (!first)
+		strbuf_addf(buf, "]>");
+
+out:
+	free(scopes);
 	return ret;
 }
 
+/**
+ * die_get_var_range - Get byte offset range of given variable DIE
+ * @sp_die: a subprogram DIE
+ * @vr_die: a variable DIE
+ * @buf: a strbuf for type and variable name and byte offset range
+ *
+ * Get the byte offset range of @vr_die and stores it in @buf as
+ * "@<function_name+[NN-NN,NN-NN]>".
+ */
+int die_get_var_range(Dwarf_Die *sp_die, Dwarf_Die *vr_die, struct strbuf *buf)
+{
+	int ret = 0;
+	Dwarf_Addr base;
+	Dwarf_Addr start, end;
+	Dwarf_Addr entry;
+	Dwarf_Op *op;
+	size_t nops;
+	size_t offset = 0;
+	Dwarf_Attribute attr;
+	bool first = true;
+	const char *name;
+
+	ret = dwarf_entrypc(sp_die, &entry);
+	if (ret)
+		return ret;
+
+	name = dwarf_diename(sp_die);
+	if (!name)
+		return -ENOENT;
+
+	if (dwarf_attr(vr_die, DW_AT_location, &attr) == NULL)
+		return -EINVAL;
+
+	while ((offset = dwarf_getlocations(
+				&attr, offset, &base,
+				&start, &end, &op, &nops)) > 0) {
+		if (start == 0) {
+			/* Single Location Descriptions */
+			ret = die_get_var_innermost_scope(sp_die, vr_die, buf);
+			return ret;
+		}
+
+		/* Location Lists */
+		start -= entry;
+		end -= entry;
+		if (first) {
+			strbuf_addf(buf, "@<%s+[%" PRIu64 "-%" PRIu64,
+				name, start, end);
+			first = false;
+		} else {
+			strbuf_addf(buf, ",%" PRIu64 "-%" PRIu64,
+				start, end);
+		}
+	}
+
+	if (!first)
+		strbuf_addf(buf, "]>");
+
+	return ret;
+}
diff --git a/tools/perf/util/dwarf-aux.h b/tools/perf/util/dwarf-aux.h
index af7dbcd5f929..c42ec366f2a7 100644
--- a/tools/perf/util/dwarf-aux.h
+++ b/tools/perf/util/dwarf-aux.h
@@ -47,6 +47,9 @@ extern bool die_is_func_instance(Dwarf_Die *dw_die);
 /* Compare diename and tname */
 extern bool die_compare_name(Dwarf_Die *dw_die, const char *tname);
 
+/* Matching diename with glob pattern */
+extern bool die_match_name(Dwarf_Die *dw_die, const char *glob);
+
 /* Get callsite line number of inline-function instance */
 extern int die_get_call_lineno(Dwarf_Die *in_die);
 
@@ -82,6 +85,10 @@ extern Dwarf_Die *die_find_child(Dwarf_Die *rt_die,
 extern Dwarf_Die *die_find_realfunc(Dwarf_Die *cu_die, Dwarf_Addr addr,
 				    Dwarf_Die *die_mem);
 
+/* Search a non-inlined function with tail call at given address */
+Dwarf_Die *die_find_tailfunc(Dwarf_Die *cu_die, Dwarf_Addr addr,
+				    Dwarf_Die *die_mem);
+
 /* Search the top inlined function including given address */
 extern Dwarf_Die *die_find_top_inlinefunc(Dwarf_Die *sp_die, Dwarf_Addr addr,
 					  Dwarf_Die *die_mem);
@@ -114,8 +121,10 @@ extern Dwarf_Die *die_find_member(Dwarf_Die *st_die, const char *name,
 				  Dwarf_Die *die_mem);
 
 /* Get the name of given variable DIE */
-extern int die_get_typename(Dwarf_Die *vr_die, char *buf, int len);
+extern int die_get_typename(Dwarf_Die *vr_die, struct strbuf *buf);
 
 /* Get the name and type of given variable DIE, stored as "type\tname" */
-extern int die_get_varname(Dwarf_Die *vr_die, char *buf, int len);
+extern int die_get_varname(Dwarf_Die *vr_die, struct strbuf *buf);
+extern int die_get_var_range(Dwarf_Die *sp_die, Dwarf_Die *vr_die,
+			struct strbuf *buf);
 #endif
diff --git a/tools/perf/util/environment.c b/tools/perf/util/environment.c
index 275b0ee345f5..7405123692f1 100644
--- a/tools/perf/util/environment.c
+++ b/tools/perf/util/environment.c
@@ -5,5 +5,4 @@
  */
 #include "cache.h"
 
-const char *pager_program;
 int pager_use_color = 1;
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index ff866c4d2e2f..d7d986d8f23e 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -23,12 +23,18 @@ static const char *perf_event__names[] = {
 	[PERF_RECORD_FORK]			= "FORK",
 	[PERF_RECORD_READ]			= "READ",
 	[PERF_RECORD_SAMPLE]			= "SAMPLE",
+	[PERF_RECORD_AUX]			= "AUX",
+	[PERF_RECORD_ITRACE_START]		= "ITRACE_START",
+	[PERF_RECORD_LOST_SAMPLES]		= "LOST_SAMPLES",
 	[PERF_RECORD_HEADER_ATTR]		= "ATTR",
 	[PERF_RECORD_HEADER_EVENT_TYPE]		= "EVENT_TYPE",
 	[PERF_RECORD_HEADER_TRACING_DATA]	= "TRACING_DATA",
 	[PERF_RECORD_HEADER_BUILD_ID]		= "BUILD_ID",
 	[PERF_RECORD_FINISHED_ROUND]		= "FINISHED_ROUND",
 	[PERF_RECORD_ID_INDEX]			= "ID_INDEX",
+	[PERF_RECORD_AUXTRACE_INFO]		= "AUXTRACE_INFO",
+	[PERF_RECORD_AUXTRACE]			= "AUXTRACE",
+	[PERF_RECORD_AUXTRACE_ERROR]		= "AUXTRACE_ERROR",
 };
 
 const char *perf_event__name(unsigned int id)
@@ -212,10 +218,14 @@ int perf_event__synthesize_mmap_events(struct perf_tool *tool,
 				       pid_t pid, pid_t tgid,
 				       perf_event__handler_t process,
 				       struct machine *machine,
-				       bool mmap_data)
+				       bool mmap_data,
+				       unsigned int proc_map_timeout)
 {
 	char filename[PATH_MAX];
 	FILE *fp;
+	unsigned long long t;
+	bool truncation = false;
+	unsigned long long timeout = proc_map_timeout * 1000000ULL;
 	int rc = 0;
 
 	if (machine__is_default_guest(machine))
@@ -234,6 +244,7 @@ int perf_event__synthesize_mmap_events(struct perf_tool *tool,
 	}
 
 	event->header.type = PERF_RECORD_MMAP2;
+	t = rdclock();
 
 	while (1) {
 		char bf[BUFSIZ];
@@ -247,6 +258,15 @@ int perf_event__synthesize_mmap_events(struct perf_tool *tool,
 		if (fgets(bf, sizeof(bf), fp) == NULL)
 			break;
 
+		if ((rdclock() - t) > timeout) {
+			pr_warning("Reading %s time out. "
+				   "You may want to increase "
+				   "the time limit by --proc-map-timeout\n",
+				   filename);
+			truncation = true;
+			goto out;
+		}
+
 		/* ensure null termination since stack will be reused. */
 		strcpy(execname, "");
 
@@ -295,6 +315,10 @@ int perf_event__synthesize_mmap_events(struct perf_tool *tool,
 			event->header.misc |= PERF_RECORD_MISC_MMAP_DATA;
 		}
 
+out:
+		if (truncation)
+			event->header.misc |= PERF_RECORD_MISC_PROC_MAP_PARSE_TIMEOUT;
+
 		if (!strcmp(execname, ""))
 			strcpy(execname, anonstr);
 
@@ -313,6 +337,9 @@ int perf_event__synthesize_mmap_events(struct perf_tool *tool,
 			rc = -1;
 			break;
 		}
+
+		if (truncation)
+			break;
 	}
 
 	fclose(fp);
@@ -324,8 +351,9 @@ int perf_event__synthesize_modules(struct perf_tool *tool,
 				   struct machine *machine)
 {
 	int rc = 0;
-	struct rb_node *nd;
+	struct map *pos;
 	struct map_groups *kmaps = &machine->kmaps;
+	struct maps *maps = &kmaps->maps[MAP__FUNCTION];
 	union perf_event *event = zalloc((sizeof(event->mmap) +
 					  machine->id_hdr_size));
 	if (event == NULL) {
@@ -345,10 +373,8 @@ int perf_event__synthesize_modules(struct perf_tool *tool,
 	else
 		event->header.misc = PERF_RECORD_MISC_GUEST_KERNEL;
 
-	for (nd = rb_first(&kmaps->maps[MAP__FUNCTION]);
-	     nd; nd = rb_next(nd)) {
+	for (pos = maps__first(maps); pos; pos = map__next(pos)) {
 		size_t size;
-		struct map *pos = rb_entry(nd, struct map, rb_node);
 
 		if (pos->dso->kernel)
 			continue;
@@ -381,7 +407,9 @@ static int __event__synthesize_thread(union perf_event *comm_event,
 				      pid_t pid, int full,
 					  perf_event__handler_t process,
 				      struct perf_tool *tool,
-				      struct machine *machine, bool mmap_data)
+				      struct machine *machine,
+				      bool mmap_data,
+				      unsigned int proc_map_timeout)
 {
 	char filename[PATH_MAX];
 	DIR *tasks;
@@ -398,7 +426,8 @@ static int __event__synthesize_thread(union perf_event *comm_event,
 			return -1;
 
 		return perf_event__synthesize_mmap_events(tool, mmap_event, pid, tgid,
-							  process, machine, mmap_data);
+							  process, machine, mmap_data,
+							  proc_map_timeout);
 	}
 
 	if (machine__is_default_guest(machine))
@@ -439,7 +468,7 @@ static int __event__synthesize_thread(union perf_event *comm_event,
 		if (_pid == pid) {
 			/* process the parent's maps too */
 			rc = perf_event__synthesize_mmap_events(tool, mmap_event, pid, tgid,
-						process, machine, mmap_data);
+						process, machine, mmap_data, proc_map_timeout);
 			if (rc)
 				break;
 		}
@@ -453,7 +482,8 @@ int perf_event__synthesize_thread_map(struct perf_tool *tool,
 				      struct thread_map *threads,
 				      perf_event__handler_t process,
 				      struct machine *machine,
-				      bool mmap_data)
+				      bool mmap_data,
+				      unsigned int proc_map_timeout)
 {
 	union perf_event *comm_event, *mmap_event, *fork_event;
 	int err = -1, thread, j;
@@ -476,7 +506,7 @@ int perf_event__synthesize_thread_map(struct perf_tool *tool,
 					       fork_event,
 					       threads->map[thread], 0,
 					       process, tool, machine,
-					       mmap_data)) {
+					       mmap_data, proc_map_timeout)) {
 			err = -1;
 			break;
 		}
@@ -502,7 +532,7 @@ int perf_event__synthesize_thread_map(struct perf_tool *tool,
 						       fork_event,
 						       comm_event->comm.pid, 0,
 						       process, tool, machine,
-						       mmap_data)) {
+						       mmap_data, proc_map_timeout)) {
 				err = -1;
 				break;
 			}
@@ -519,7 +549,9 @@ out:
 
 int perf_event__synthesize_threads(struct perf_tool *tool,
 				   perf_event__handler_t process,
-				   struct machine *machine, bool mmap_data)
+				   struct machine *machine,
+				   bool mmap_data,
+				   unsigned int proc_map_timeout)
 {
 	DIR *proc;
 	char proc_path[PATH_MAX];
@@ -559,7 +591,8 @@ int perf_event__synthesize_threads(struct perf_tool *tool,
  		 * one thread couldn't be synthesized.
  		 */
 		__event__synthesize_thread(comm_event, mmap_event, fork_event, pid,
-					   1, process, tool, machine, mmap_data);
+					   1, process, tool, machine, mmap_data,
+					   proc_map_timeout);
 	}
 
 	err = 0;
@@ -692,6 +725,30 @@ int perf_event__process_lost(struct perf_tool *tool __maybe_unused,
 	return machine__process_lost_event(machine, event, sample);
 }
 
+int perf_event__process_aux(struct perf_tool *tool __maybe_unused,
+			    union perf_event *event,
+			    struct perf_sample *sample __maybe_unused,
+			    struct machine *machine)
+{
+	return machine__process_aux_event(machine, event);
+}
+
+int perf_event__process_itrace_start(struct perf_tool *tool __maybe_unused,
+				     union perf_event *event,
+				     struct perf_sample *sample __maybe_unused,
+				     struct machine *machine)
+{
+	return machine__process_itrace_start_event(machine, event);
+}
+
+int perf_event__process_lost_samples(struct perf_tool *tool __maybe_unused,
+				     union perf_event *event,
+				     struct perf_sample *sample,
+				     struct machine *machine)
+{
+	return machine__process_lost_samples_event(machine, event, sample);
+}
+
 size_t perf_event__fprintf_mmap(union perf_event *event, FILE *fp)
 {
 	return fprintf(fp, " %d/%d: [%#" PRIx64 "(%#" PRIx64 ") @ %#" PRIx64 "]: %c %s\n",
@@ -755,6 +812,21 @@ int perf_event__process_exit(struct perf_tool *tool __maybe_unused,
 	return machine__process_exit_event(machine, event, sample);
 }
 
+size_t perf_event__fprintf_aux(union perf_event *event, FILE *fp)
+{
+	return fprintf(fp, " offset: %#"PRIx64" size: %#"PRIx64" flags: %#"PRIx64" [%s%s]\n",
+		       event->aux.aux_offset, event->aux.aux_size,
+		       event->aux.flags,
+		       event->aux.flags & PERF_AUX_FLAG_TRUNCATED ? "T" : "",
+		       event->aux.flags & PERF_AUX_FLAG_OVERWRITE ? "O" : "");
+}
+
+size_t perf_event__fprintf_itrace_start(union perf_event *event, FILE *fp)
+{
+	return fprintf(fp, " pid: %u tid: %u\n",
+		       event->itrace_start.pid, event->itrace_start.tid);
+}
+
 size_t perf_event__fprintf(union perf_event *event, FILE *fp)
 {
 	size_t ret = fprintf(fp, "PERF_RECORD_%s",
@@ -774,6 +846,12 @@ size_t perf_event__fprintf(union perf_event *event, FILE *fp)
 	case PERF_RECORD_MMAP2:
 		ret += perf_event__fprintf_mmap2(event, fp);
 		break;
+	case PERF_RECORD_AUX:
+		ret += perf_event__fprintf_aux(event, fp);
+		break;
+	case PERF_RECORD_ITRACE_START:
+		ret += perf_event__fprintf_itrace_start(event, fp);
+		break;
 	default:
 		ret += fprintf(fp, "\n");
 	}
@@ -877,6 +955,10 @@ void thread__find_addr_location(struct thread *thread,
 		al->sym = NULL;
 }
 
+/*
+ * Callers need to drop the reference to al->thread, obtained in
+ * machine__findnew_thread()
+ */
 int perf_event__preprocess_sample(const union perf_event *event,
 				  struct machine *machine,
 				  struct addr_location *al,
@@ -937,6 +1019,17 @@ int perf_event__preprocess_sample(const union perf_event *event,
 	return 0;
 }
 
+/*
+ * The preprocess_sample method will return with reference counts for the
+ * in it, when done using (and perhaps getting ref counts if needing to
+ * keep a pointer to one of those entries) it must be paired with
+ * addr_location__put(), so that the refcounts can be decremented.
+ */
+void addr_location__put(struct addr_location *al)
+{
+	thread__zput(al->thread);
+}
+
 bool is_bts_event(struct perf_event_attr *attr)
 {
 	return attr->type == PERF_TYPE_HARDWARE &&
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index 09b9e8d3fcf7..c53f36384b64 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -52,6 +52,11 @@ struct lost_event {
 	u64 lost;
 };
 
+struct lost_samples_event {
+	struct perf_event_header header;
+	u64 lost;
+};
+
 /*
  * PERF_FORMAT_ENABLED | PERF_FORMAT_RUNNING | PERF_FORMAT_ID
  */
@@ -157,6 +162,8 @@ enum {
 	PERF_IP_FLAG_IN_TX		= 1ULL << 10,
 };
 
+#define PERF_IP_FLAG_CHARS "bcrosyiABEx"
+
 #define PERF_BRANCH_MASK		(\
 	PERF_IP_FLAG_BRANCH		|\
 	PERF_IP_FLAG_CALL		|\
@@ -215,9 +222,17 @@ enum perf_user_event_type { /* above any possible kernel type */
 	PERF_RECORD_HEADER_BUILD_ID		= 67,
 	PERF_RECORD_FINISHED_ROUND		= 68,
 	PERF_RECORD_ID_INDEX			= 69,
+	PERF_RECORD_AUXTRACE_INFO		= 70,
+	PERF_RECORD_AUXTRACE			= 71,
+	PERF_RECORD_AUXTRACE_ERROR		= 72,
 	PERF_RECORD_HEADER_MAX
 };
 
+enum auxtrace_error_type {
+	PERF_AUXTRACE_ERROR_ITRACE  = 1,
+	PERF_AUXTRACE_ERROR_MAX
+};
+
 /*
  * The kernel collects the number of events it couldn't send in a stretch and
  * when possible sends this number in a PERF_RECORD_LOST event. The number of
@@ -225,6 +240,12 @@ enum perf_user_event_type { /* above any possible kernel type */
  * total_lost tells exactly how many events the kernel in fact lost, i.e. it is
  * the sum of all struct lost_event.lost fields reported.
  *
+ * The kernel discards mixed up samples and sends the number in a
+ * PERF_RECORD_LOST_SAMPLES event. The number of lost-samples events is stored
+ * in .nr_events[PERF_RECORD_LOST_SAMPLES] while total_lost_samples tells
+ * exactly how many samples the kernel in fact dropped, i.e. it is the sum of
+ * all struct lost_samples_event.lost fields reported.
+ *
  * The total_period is needed because by default auto-freq is used, so
  * multipling nr_events[PERF_EVENT_SAMPLE] by a frequency isn't possible to get
  * the total number of low level events, it is necessary to to sum all struct
@@ -234,6 +255,7 @@ struct events_stats {
 	u64 total_period;
 	u64 total_non_filtered_period;
 	u64 total_lost;
+	u64 total_lost_samples;
 	u64 total_invalid_chains;
 	u32 nr_events[PERF_RECORD_HEADER_MAX];
 	u32 nr_non_filtered_samples;
@@ -242,6 +264,8 @@ struct events_stats {
 	u32 nr_invalid_chains;
 	u32 nr_unknown_id;
 	u32 nr_unprocessable_samples;
+	u32 nr_auxtrace_errors[PERF_AUXTRACE_ERROR_MAX];
+	u32 nr_proc_map_timeout;
 };
 
 struct attr_event {
@@ -280,6 +304,50 @@ struct id_index_event {
 	struct id_index_entry entries[0];
 };
 
+struct auxtrace_info_event {
+	struct perf_event_header header;
+	u32 type;
+	u32 reserved__; /* For alignment */
+	u64 priv[];
+};
+
+struct auxtrace_event {
+	struct perf_event_header header;
+	u64 size;
+	u64 offset;
+	u64 reference;
+	u32 idx;
+	u32 tid;
+	u32 cpu;
+	u32 reserved__; /* For alignment */
+};
+
+#define MAX_AUXTRACE_ERROR_MSG 64
+
+struct auxtrace_error_event {
+	struct perf_event_header header;
+	u32 type;
+	u32 code;
+	u32 cpu;
+	u32 pid;
+	u32 tid;
+	u32 reserved__; /* For alignment */
+	u64 ip;
+	char msg[MAX_AUXTRACE_ERROR_MSG];
+};
+
+struct aux_event {
+	struct perf_event_header header;
+	u64	aux_offset;
+	u64	aux_size;
+	u64	flags;
+};
+
+struct itrace_start_event {
+	struct perf_event_header header;
+	u32 pid, tid;
+};
+
 union perf_event {
 	struct perf_event_header	header;
 	struct mmap_event		mmap;
@@ -287,6 +355,7 @@ union perf_event {
 	struct comm_event		comm;
 	struct fork_event		fork;
 	struct lost_event		lost;
+	struct lost_samples_event	lost_samples;
 	struct read_event		read;
 	struct throttle_event		throttle;
 	struct sample_event		sample;
@@ -295,6 +364,11 @@ union perf_event {
 	struct tracing_data_event	tracing_data;
 	struct build_id_event		build_id;
 	struct id_index_event		id_index;
+	struct auxtrace_info_event	auxtrace_info;
+	struct auxtrace_event		auxtrace;
+	struct auxtrace_error_event	auxtrace_error;
+	struct aux_event		aux;
+	struct itrace_start_event	itrace_start;
 };
 
 void perf_event__print_totals(void);
@@ -310,10 +384,12 @@ typedef int (*perf_event__handler_t)(struct perf_tool *tool,
 int perf_event__synthesize_thread_map(struct perf_tool *tool,
 				      struct thread_map *threads,
 				      perf_event__handler_t process,
-				      struct machine *machine, bool mmap_data);
+				      struct machine *machine, bool mmap_data,
+				      unsigned int proc_map_timeout);
 int perf_event__synthesize_threads(struct perf_tool *tool,
 				   perf_event__handler_t process,
-				   struct machine *machine, bool mmap_data);
+				   struct machine *machine, bool mmap_data,
+				   unsigned int proc_map_timeout);
 int perf_event__synthesize_kernel_mmap(struct perf_tool *tool,
 				       perf_event__handler_t process,
 				       struct machine *machine);
@@ -330,6 +406,18 @@ int perf_event__process_lost(struct perf_tool *tool,
 			     union perf_event *event,
 			     struct perf_sample *sample,
 			     struct machine *machine);
+int perf_event__process_lost_samples(struct perf_tool *tool,
+				     union perf_event *event,
+				     struct perf_sample *sample,
+				     struct machine *machine);
+int perf_event__process_aux(struct perf_tool *tool,
+			    union perf_event *event,
+			    struct perf_sample *sample,
+			    struct machine *machine);
+int perf_event__process_itrace_start(struct perf_tool *tool,
+				     union perf_event *event,
+				     struct perf_sample *sample,
+				     struct machine *machine);
 int perf_event__process_mmap(struct perf_tool *tool,
 			     union perf_event *event,
 			     struct perf_sample *sample,
@@ -358,6 +446,8 @@ int perf_event__preprocess_sample(const union perf_event *event,
 				  struct addr_location *al,
 				  struct perf_sample *sample);
 
+void addr_location__put(struct addr_location *al);
+
 struct thread;
 
 bool is_bts_event(struct perf_event_attr *attr);
@@ -381,12 +471,15 @@ int perf_event__synthesize_mmap_events(struct perf_tool *tool,
 				       pid_t pid, pid_t tgid,
 				       perf_event__handler_t process,
 				       struct machine *machine,
-				       bool mmap_data);
+				       bool mmap_data,
+				       unsigned int proc_map_timeout);
 
 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);
 size_t perf_event__fprintf_task(union perf_event *event, FILE *fp);
+size_t perf_event__fprintf_aux(union perf_event *event, FILE *fp);
+size_t perf_event__fprintf_itrace_start(union perf_event *event, FILE *fp);
 size_t perf_event__fprintf(union perf_event *event, FILE *fp);
 
 u64 kallsyms__get_function_start(const char *kallsyms_filename,
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index 080be93eea96..8366511b45f8 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -297,6 +297,8 @@ void perf_evlist__disable(struct perf_evlist *evlist)
 				      PERF_EVENT_IOC_DISABLE, 0);
 		}
 	}
+
+	evlist->enabled = false;
 }
 
 void perf_evlist__enable(struct perf_evlist *evlist)
@@ -316,6 +318,13 @@ void perf_evlist__enable(struct perf_evlist *evlist)
 				      PERF_EVENT_IOC_ENABLE, 0);
 		}
 	}
+
+	evlist->enabled = true;
+}
+
+void perf_evlist__toggle_enable(struct perf_evlist *evlist)
+{
+	(evlist->enabled ? perf_evlist__disable : perf_evlist__enable)(evlist);
 }
 
 int perf_evlist__disable_event(struct perf_evlist *evlist,
@@ -634,11 +643,18 @@ static struct perf_evsel *perf_evlist__event2evsel(struct perf_evlist *evlist,
 union perf_event *perf_evlist__mmap_read(struct perf_evlist *evlist, int idx)
 {
 	struct perf_mmap *md = &evlist->mmap[idx];
-	u64 head = perf_mmap__read_head(md);
+	u64 head;
 	u64 old = md->prev;
 	unsigned char *data = md->base + page_size;
 	union perf_event *event = NULL;
 
+	/*
+	 * Check if event was unmapped due to a POLLHUP/POLLERR.
+	 */
+	if (!atomic_read(&md->refcnt))
+		return NULL;
+
+	head = perf_mmap__read_head(md);
 	if (evlist->overwrite) {
 		/*
 		 * If we're further behind than half the buffer, there's a chance
@@ -695,19 +711,19 @@ union perf_event *perf_evlist__mmap_read(struct perf_evlist *evlist, int idx)
 
 static bool perf_mmap__empty(struct perf_mmap *md)
 {
-	return perf_mmap__read_head(md) == md->prev;
+	return perf_mmap__read_head(md) == md->prev && !md->auxtrace_mmap.base;
 }
 
 static void perf_evlist__mmap_get(struct perf_evlist *evlist, int idx)
 {
-	++evlist->mmap[idx].refcnt;
+	atomic_inc(&evlist->mmap[idx].refcnt);
 }
 
 static void perf_evlist__mmap_put(struct perf_evlist *evlist, int idx)
 {
-	BUG_ON(evlist->mmap[idx].refcnt == 0);
+	BUG_ON(atomic_read(&evlist->mmap[idx].refcnt) == 0);
 
-	if (--evlist->mmap[idx].refcnt == 0)
+	if (atomic_dec_and_test(&evlist->mmap[idx].refcnt))
 		__perf_evlist__munmap(evlist, idx);
 }
 
@@ -721,17 +737,46 @@ void perf_evlist__mmap_consume(struct perf_evlist *evlist, int idx)
 		perf_mmap__write_tail(md, old);
 	}
 
-	if (md->refcnt == 1 && perf_mmap__empty(md))
+	if (atomic_read(&md->refcnt) == 1 && perf_mmap__empty(md))
 		perf_evlist__mmap_put(evlist, idx);
 }
 
+int __weak auxtrace_mmap__mmap(struct auxtrace_mmap *mm __maybe_unused,
+			       struct auxtrace_mmap_params *mp __maybe_unused,
+			       void *userpg __maybe_unused,
+			       int fd __maybe_unused)
+{
+	return 0;
+}
+
+void __weak auxtrace_mmap__munmap(struct auxtrace_mmap *mm __maybe_unused)
+{
+}
+
+void __weak auxtrace_mmap_params__init(
+			struct auxtrace_mmap_params *mp __maybe_unused,
+			off_t auxtrace_offset __maybe_unused,
+			unsigned int auxtrace_pages __maybe_unused,
+			bool auxtrace_overwrite __maybe_unused)
+{
+}
+
+void __weak auxtrace_mmap_params__set_idx(
+			struct auxtrace_mmap_params *mp __maybe_unused,
+			struct perf_evlist *evlist __maybe_unused,
+			int idx __maybe_unused,
+			bool per_cpu __maybe_unused)
+{
+}
+
 static void __perf_evlist__munmap(struct perf_evlist *evlist, int idx)
 {
 	if (evlist->mmap[idx].base != NULL) {
 		munmap(evlist->mmap[idx].base, evlist->mmap_len);
 		evlist->mmap[idx].base = NULL;
-		evlist->mmap[idx].refcnt = 0;
+		atomic_set(&evlist->mmap[idx].refcnt, 0);
 	}
+	auxtrace_mmap__munmap(&evlist->mmap[idx].auxtrace_mmap);
 }
 
 void perf_evlist__munmap(struct perf_evlist *evlist)
@@ -759,6 +804,7 @@ static int perf_evlist__alloc_mmap(struct perf_evlist *evlist)
 struct mmap_params {
 	int prot;
 	int mask;
+	struct auxtrace_mmap_params auxtrace_mp;
 };
 
 static int __perf_evlist__mmap(struct perf_evlist *evlist, int idx,
@@ -777,7 +823,7 @@ static int __perf_evlist__mmap(struct perf_evlist *evlist, int idx,
 	 * evlist layer can't just drop it when filtering events in
 	 * perf_evlist__filter_pollfd().
 	 */
-	evlist->mmap[idx].refcnt = 2;
+	atomic_set(&evlist->mmap[idx].refcnt, 2);
 	evlist->mmap[idx].prev = 0;
 	evlist->mmap[idx].mask = mp->mask;
 	evlist->mmap[idx].base = mmap(NULL, evlist->mmap_len, mp->prot,
@@ -789,6 +835,10 @@ static int __perf_evlist__mmap(struct perf_evlist *evlist, int idx,
 		return -1;
 	}
 
+	if (auxtrace_mmap__mmap(&evlist->mmap[idx].auxtrace_mmap,
+				&mp->auxtrace_mp, evlist->mmap[idx].base, fd))
+		return -1;
+
 	return 0;
 }
 
@@ -853,6 +903,9 @@ static int perf_evlist__mmap_per_cpu(struct perf_evlist *evlist,
 	for (cpu = 0; cpu < nr_cpus; cpu++) {
 		int output = -1;
 
+		auxtrace_mmap_params__set_idx(&mp->auxtrace_mp, evlist, cpu,
+					      true);
+
 		for (thread = 0; thread < nr_threads; thread++) {
 			if (perf_evlist__mmap_per_evsel(evlist, cpu, mp, cpu,
 							thread, &output))
@@ -878,6 +931,9 @@ static int perf_evlist__mmap_per_thread(struct perf_evlist *evlist,
 	for (thread = 0; thread < nr_threads; thread++) {
 		int output = -1;
 
+		auxtrace_mmap_params__set_idx(&mp->auxtrace_mp, evlist, thread,
+					      false);
+
 		if (perf_evlist__mmap_per_evsel(evlist, thread, mp, 0, thread,
 						&output))
 			goto out_unmap;
@@ -960,10 +1016,8 @@ static long parse_pages_arg(const char *str, unsigned long min,
 	return pages;
 }
 
-int perf_evlist__parse_mmap_pages(const struct option *opt, const char *str,
-				  int unset __maybe_unused)
+int __perf_evlist__parse_mmap_pages(unsigned int *mmap_pages, const char *str)
 {
-	unsigned int *mmap_pages = opt->value;
 	unsigned long max = UINT_MAX;
 	long pages;
 
@@ -980,20 +1034,32 @@ int perf_evlist__parse_mmap_pages(const struct option *opt, const char *str,
 	return 0;
 }
 
+int perf_evlist__parse_mmap_pages(const struct option *opt, const char *str,
+				  int unset __maybe_unused)
+{
+	return __perf_evlist__parse_mmap_pages(opt->value, str);
+}
+
 /**
- * perf_evlist__mmap - Create mmaps to receive events.
+ * perf_evlist__mmap_ex - Create mmaps to receive events.
  * @evlist: list of events
  * @pages: map length in pages
  * @overwrite: overwrite older events?
+ * @auxtrace_pages - auxtrace map length in pages
+ * @auxtrace_overwrite - overwrite older auxtrace data?
  *
  * If @overwrite is %false the user needs to signal event consumption using
  * perf_mmap__write_tail().  Using perf_evlist__mmap_read() does this
  * automatically.
  *
+ * Similarly, if @auxtrace_overwrite is %false the user needs to signal data
+ * consumption using auxtrace_mmap__write_tail().
+ *
  * Return: %0 on success, negative error code otherwise.
  */
-int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages,
-		      bool overwrite)
+int perf_evlist__mmap_ex(struct perf_evlist *evlist, unsigned int pages,
+			 bool overwrite, unsigned int auxtrace_pages,
+			 bool auxtrace_overwrite)
 {
 	struct perf_evsel *evsel;
 	const struct cpu_map *cpus = evlist->cpus;
@@ -1013,6 +1079,9 @@ int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages,
 	pr_debug("mmap size %zuB\n", evlist->mmap_len);
 	mp.mask = evlist->mmap_len - page_size - 1;
 
+	auxtrace_mmap_params__init(&mp.auxtrace_mp, evlist->mmap_len,
+				   auxtrace_pages, auxtrace_overwrite);
+
 	evlist__for_each(evlist, evsel) {
 		if ((evsel->attr.read_format & PERF_FORMAT_ID) &&
 		    evsel->sample_id == NULL &&
@@ -1026,6 +1095,12 @@ int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages,
 	return perf_evlist__mmap_per_cpu(evlist, &mp);
 }
 
+int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages,
+		      bool overwrite)
+{
+	return perf_evlist__mmap_ex(evlist, pages, overwrite, 0, false);
+}
+
 int perf_evlist__create_maps(struct perf_evlist *evlist, struct target *target)
 {
 	evlist->threads = thread_map__new_str(target->pid, target->tid,
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index b5cce95d644e..a8489b9d2812 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -1,6 +1,7 @@
 #ifndef __PERF_EVLIST_H
 #define __PERF_EVLIST_H 1
 
+#include <linux/atomic.h>
 #include <linux/list.h>
 #include <api/fd/array.h>
 #include <stdio.h>
@@ -8,6 +9,7 @@
 #include "event.h"
 #include "evsel.h"
 #include "util.h"
+#include "auxtrace.h"
 #include <unistd.h>
 
 struct pollfd;
@@ -26,8 +28,9 @@ struct record_opts;
 struct perf_mmap {
 	void		 *base;
 	int		 mask;
-	int		 refcnt;
+	atomic_t	 refcnt;
 	u64		 prev;
+	struct auxtrace_mmap auxtrace_mmap;
 	char		 event_copy[PERF_SAMPLE_MAX_SIZE] __attribute__((aligned(8)));
 };
 
@@ -37,6 +40,8 @@ struct perf_evlist {
 	int		 nr_entries;
 	int		 nr_groups;
 	int		 nr_mmaps;
+	bool		 overwrite;
+	bool		 enabled;
 	size_t		 mmap_len;
 	int		 id_pos;
 	int		 is_pos;
@@ -45,7 +50,6 @@ struct perf_evlist {
 		int	cork_fd;
 		pid_t	pid;
 	} workload;
-	bool		 overwrite;
 	struct fdarray	 pollfd;
 	struct perf_mmap *mmap;
 	struct thread_map *threads;
@@ -122,16 +126,21 @@ int perf_evlist__start_workload(struct perf_evlist *evlist);
 
 struct option;
 
+int __perf_evlist__parse_mmap_pages(unsigned int *mmap_pages, const char *str);
 int perf_evlist__parse_mmap_pages(const struct option *opt,
 				  const char *str,
 				  int unset);
 
+int perf_evlist__mmap_ex(struct perf_evlist *evlist, unsigned int pages,
+			 bool overwrite, unsigned int auxtrace_pages,
+			 bool auxtrace_overwrite);
 int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages,
 		      bool overwrite);
 void perf_evlist__munmap(struct perf_evlist *evlist);
 
 void perf_evlist__disable(struct perf_evlist *evlist);
 void perf_evlist__enable(struct perf_evlist *evlist);
+void perf_evlist__toggle_enable(struct perf_evlist *evlist);
 
 int perf_evlist__disable_event(struct perf_evlist *evlist,
 			       struct perf_evsel *evsel);
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 33e3fd8c2e68..33449decf7bd 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -26,6 +26,7 @@
 #include "perf_regs.h"
 #include "debug.h"
 #include "trace-event.h"
+#include "stat.h"
 
 static struct {
 	bool sample_id_all;
@@ -851,19 +852,6 @@ int perf_evsel__alloc_id(struct perf_evsel *evsel, int ncpus, int nthreads)
 	return 0;
 }
 
-void perf_evsel__reset_counts(struct perf_evsel *evsel, int ncpus)
-{
-	memset(evsel->counts, 0, (sizeof(*evsel->counts) +
-				 (ncpus * sizeof(struct perf_counts_values))));
-}
-
-int perf_evsel__alloc_counts(struct perf_evsel *evsel, int ncpus)
-{
-	evsel->counts = zalloc((sizeof(*evsel->counts) +
-				(ncpus * sizeof(struct perf_counts_values))));
-	return evsel->counts != NULL ? 0 : -ENOMEM;
-}
-
 static void perf_evsel__free_fd(struct perf_evsel *evsel)
 {
 	xyarray__delete(evsel->fd);
@@ -891,11 +879,6 @@ void perf_evsel__close_fd(struct perf_evsel *evsel, int ncpus, int nthreads)
 		}
 }
 
-void perf_evsel__free_counts(struct perf_evsel *evsel)
-{
-	zfree(&evsel->counts);
-}
-
 void perf_evsel__exit(struct perf_evsel *evsel)
 {
 	assert(list_empty(&evsel->node));
@@ -1058,7 +1041,7 @@ static void __p_read_format(char *buf, size_t size, u64 value)
 
 #define BUF_SIZE		1024
 
-#define p_hex(val)		snprintf(buf, BUF_SIZE, "%"PRIx64, (uint64_t)(val))
+#define p_hex(val)		snprintf(buf, BUF_SIZE, "%#"PRIx64, (uint64_t)(val))
 #define p_unsigned(val)		snprintf(buf, BUF_SIZE, "%"PRIu64, (uint64_t)(val))
 #define p_signed(val)		snprintf(buf, BUF_SIZE, "%"PRId64, (int64_t)(val))
 #define p_sample_type(val)	__p_sample_type(buf, BUF_SIZE, val)
@@ -1121,6 +1104,7 @@ int perf_event_attr__fprintf(FILE *fp, struct perf_event_attr *attr,
 	PRINT_ATTRf(sample_stack_user, p_unsigned);
 	PRINT_ATTRf(clockid, p_signed);
 	PRINT_ATTRf(sample_regs_intr, p_hex);
+	PRINT_ATTRf(aux_watermark, p_unsigned);
 
 	return ret;
 }
@@ -2148,7 +2132,9 @@ int perf_evsel__open_strerror(struct perf_evsel *evsel, struct target *target,
 	case EMFILE:
 		return scnprintf(msg, size, "%s",
 			 "Too many events are opened.\n"
-			 "Try again after reducing the number of events.");
+			 "Probably the maximum number of open file descriptors has been reached.\n"
+			 "Hint: Try again after reducing the number of events.\n"
+			 "Hint: Try increasing the limit with 'ulimit -n <limit>'");
 	case ENODEV:
 		if (target->cpu_list)
 			return scnprintf(msg, size, "%s",
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index e486151b0308..bb0579e8a10a 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -73,7 +73,6 @@ struct perf_evsel {
 	char			*name;
 	double			scale;
 	const char		*unit;
-	bool			snapshot;
 	struct event_format	*tp_format;
 	union {
 		void		*priv;
@@ -86,6 +85,7 @@ struct perf_evsel {
 	unsigned int		sample_size;
 	int			id_pos;
 	int			is_pos;
+	bool			snapshot;
 	bool 			supported;
 	bool 			needs_swap;
 	bool			no_aux_samples;
@@ -93,11 +93,11 @@ struct perf_evsel {
 	bool			system_wide;
 	bool			tracking;
 	bool			per_pkg;
-	unsigned long		*per_pkg_mask;
 	/* parse modifier helper */
 	int			exclude_GH;
 	int			nr_members;
 	int			sample_read;
+	unsigned long		*per_pkg_mask;
 	struct perf_evsel	*leader;
 	char			*group_name;
 };
@@ -170,9 +170,6 @@ const char *perf_evsel__group_name(struct perf_evsel *evsel);
 int perf_evsel__group_desc(struct perf_evsel *evsel, char *buf, size_t size);
 
 int perf_evsel__alloc_id(struct perf_evsel *evsel, int ncpus, int nthreads);
-int perf_evsel__alloc_counts(struct perf_evsel *evsel, int ncpus);
-void perf_evsel__reset_counts(struct perf_evsel *evsel, int ncpus);
-void perf_evsel__free_counts(struct perf_evsel *evsel);
 void perf_evsel__close_fd(struct perf_evsel *evsel, int ncpus, int nthreads);
 
 void __perf_evsel__set_sample_bit(struct perf_evsel *evsel,
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 918fd8ae2d80..21a77e7a171e 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -869,6 +869,20 @@ static int write_branch_stack(int fd __maybe_unused,
 	return 0;
 }
 
+static int write_auxtrace(int fd, struct perf_header *h,
+			  struct perf_evlist *evlist __maybe_unused)
+{
+	struct perf_session *session;
+	int err;
+
+	session = container_of(h, struct perf_session, header);
+
+	err = auxtrace_index__write(fd, &session->auxtrace_index);
+	if (err < 0)
+		pr_err("Failed to write auxtrace index\n");
+	return err;
+}
+
 static void print_hostname(struct perf_header *ph, int fd __maybe_unused,
 			   FILE *fp)
 {
@@ -1151,6 +1165,12 @@ static void print_branch_stack(struct perf_header *ph __maybe_unused,
 	fprintf(fp, "# contains samples with branch stack\n");
 }
 
+static void print_auxtrace(struct perf_header *ph __maybe_unused,
+			   int fd __maybe_unused, FILE *fp)
+{
+	fprintf(fp, "# contains AUX area data (e.g. instruction trace)\n");
+}
+
 static void print_pmu_mappings(struct perf_header *ph, int fd __maybe_unused,
 			       FILE *fp)
 {
@@ -1218,9 +1238,8 @@ static int __event_process_build_id(struct build_id_event *bev,
 				    struct perf_session *session)
 {
 	int err = -1;
-	struct dsos *dsos;
 	struct machine *machine;
-	u16 misc;
+	u16 cpumode;
 	struct dso *dso;
 	enum dso_kernel_type dso_type;
 
@@ -1228,39 +1247,37 @@ static int __event_process_build_id(struct build_id_event *bev,
 	if (!machine)
 		goto out;
 
-	misc = bev->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
+	cpumode = bev->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
 
-	switch (misc) {
+	switch (cpumode) {
 	case PERF_RECORD_MISC_KERNEL:
 		dso_type = DSO_TYPE_KERNEL;
-		dsos = &machine->kernel_dsos;
 		break;
 	case PERF_RECORD_MISC_GUEST_KERNEL:
 		dso_type = DSO_TYPE_GUEST_KERNEL;
-		dsos = &machine->kernel_dsos;
 		break;
 	case PERF_RECORD_MISC_USER:
 	case PERF_RECORD_MISC_GUEST_USER:
 		dso_type = DSO_TYPE_USER;
-		dsos = &machine->user_dsos;
 		break;
 	default:
 		goto out;
 	}
 
-	dso = __dsos__findnew(dsos, filename);
+	dso = machine__findnew_dso(machine, filename);
 	if (dso != NULL) {
 		char sbuild_id[BUILD_ID_SIZE * 2 + 1];
 
 		dso__set_build_id(dso, &bev->build_id);
 
-		if (!is_kernel_module(filename))
+		if (!is_kernel_module(filename, cpumode))
 			dso->kernel = dso_type;
 
 		build_id__sprintf(dso->build_id, sizeof(dso->build_id),
 				  sbuild_id);
 		pr_debug("build id event received for %s: %s\n",
 			 dso->long_name, sbuild_id);
+		dso__put(dso);
 	}
 
 	err = 0;
@@ -1821,6 +1838,22 @@ out_free:
 	return ret;
 }
 
+static int process_auxtrace(struct perf_file_section *section,
+			    struct perf_header *ph, int fd,
+			    void *data __maybe_unused)
+{
+	struct perf_session *session;
+	int err;
+
+	session = container_of(ph, struct perf_session, header);
+
+	err = auxtrace_index__process(fd, section->size, session,
+				      ph->needs_swap);
+	if (err < 0)
+		pr_err("Failed to process auxtrace index\n");
+	return err;
+}
+
 struct feature_ops {
 	int (*write)(int fd, struct perf_header *h, struct perf_evlist *evlist);
 	void (*print)(struct perf_header *h, int fd, FILE *fp);
@@ -1861,6 +1894,7 @@ static const struct feature_ops feat_ops[HEADER_LAST_FEATURE] = {
 	FEAT_OPA(HEADER_BRANCH_STACK,	branch_stack),
 	FEAT_OPP(HEADER_PMU_MAPPINGS,	pmu_mappings),
 	FEAT_OPP(HEADER_GROUP_DESC,	group_desc),
+	FEAT_OPP(HEADER_AUXTRACE,	auxtrace),
 };
 
 struct header_print_data {
diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h
index 3bb90ac172a1..d4d57962c591 100644
--- a/tools/perf/util/header.h
+++ b/tools/perf/util/header.h
@@ -30,6 +30,7 @@ enum {
 	HEADER_BRANCH_STACK,
 	HEADER_PMU_MAPPINGS,
 	HEADER_GROUP_DESC,
+	HEADER_AUXTRACE,
 	HEADER_LAST_FEATURE,
 	HEADER_FEAT_BITS	= 256,
 };
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index cc22b9158b93..6f28d53d4e46 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -313,8 +313,7 @@ static struct hist_entry *hist_entry__new(struct hist_entry *template,
 				memset(&he->stat, 0, sizeof(he->stat));
 		}
 
-		if (he->ms.map)
-			he->ms.map->referenced = true;
+		map__get(he->ms.map);
 
 		if (he->branch_info) {
 			/*
@@ -324,6 +323,7 @@ static struct hist_entry *hist_entry__new(struct hist_entry *template,
 			 */
 			he->branch_info = malloc(sizeof(*he->branch_info));
 			if (he->branch_info == NULL) {
+				map__zput(he->ms.map);
 				free(he->stat_acc);
 				free(he);
 				return NULL;
@@ -332,17 +332,13 @@ static struct hist_entry *hist_entry__new(struct hist_entry *template,
 			memcpy(he->branch_info, template->branch_info,
 			       sizeof(*he->branch_info));
 
-			if (he->branch_info->from.map)
-				he->branch_info->from.map->referenced = true;
-			if (he->branch_info->to.map)
-				he->branch_info->to.map->referenced = true;
+			map__get(he->branch_info->from.map);
+			map__get(he->branch_info->to.map);
 		}
 
 		if (he->mem_info) {
-			if (he->mem_info->iaddr.map)
-				he->mem_info->iaddr.map->referenced = true;
-			if (he->mem_info->daddr.map)
-				he->mem_info->daddr.map->referenced = true;
+			map__get(he->mem_info->iaddr.map);
+			map__get(he->mem_info->daddr.map);
 		}
 
 		if (symbol_conf.use_callchain)
@@ -362,10 +358,10 @@ static u8 symbol__parent_filter(const struct symbol *parent)
 	return 0;
 }
 
-static struct hist_entry *add_hist_entry(struct hists *hists,
-					 struct hist_entry *entry,
-					 struct addr_location *al,
-					 bool sample_self)
+static struct hist_entry *hists__findnew_entry(struct hists *hists,
+					       struct hist_entry *entry,
+					       struct addr_location *al,
+					       bool sample_self)
 {
 	struct rb_node **p;
 	struct rb_node *parent = NULL;
@@ -407,9 +403,8 @@ static struct hist_entry *add_hist_entry(struct hists *hists,
 			 * the history counter to increment.
 			 */
 			if (he->ms.map != entry->ms.map) {
-				he->ms.map = entry->ms.map;
-				if (he->ms.map)
-					he->ms.map->referenced = true;
+				map__put(he->ms.map);
+				he->ms.map = map__get(entry->ms.map);
 			}
 			goto out;
 		}
@@ -468,7 +463,7 @@ struct hist_entry *__hists__add_entry(struct hists *hists,
 		.transaction = transaction,
 	};
 
-	return add_hist_entry(hists, &entry, al, sample_self);
+	return hists__findnew_entry(hists, &entry, al, sample_self);
 }
 
 static int
@@ -548,9 +543,9 @@ iter_finish_mem_entry(struct hist_entry_iter *iter,
 
 out:
 	/*
-	 * We don't need to free iter->priv (mem_info) here since
-	 * the mem info was either already freed in add_hist_entry() or
-	 * passed to a new hist entry by hist_entry__new().
+	 * We don't need to free iter->priv (mem_info) here since the mem info
+	 * was either already freed in hists__findnew_entry() or passed to a
+	 * new hist entry by hist_entry__new().
 	 */
 	iter->priv = NULL;
 
@@ -851,19 +846,15 @@ const struct hist_iter_ops hist_iter_cumulative = {
 };
 
 int hist_entry_iter__add(struct hist_entry_iter *iter, struct addr_location *al,
-			 struct perf_evsel *evsel, struct perf_sample *sample,
 			 int max_stack_depth, void *arg)
 {
 	int err, err2;
 
-	err = sample__resolve_callchain(sample, &iter->parent, evsel, al,
-					max_stack_depth);
+	err = sample__resolve_callchain(iter->sample, &iter->parent,
+					iter->evsel, al, max_stack_depth);
 	if (err)
 		return err;
 
-	iter->evsel = evsel;
-	iter->sample = sample;
-
 	err = iter->ops->prepare_entry(iter, al);
 	if (err)
 		goto out;
@@ -937,8 +928,20 @@ hist_entry__collapse(struct hist_entry *left, struct hist_entry *right)
 void hist_entry__delete(struct hist_entry *he)
 {
 	thread__zput(he->thread);
-	zfree(&he->branch_info);
-	zfree(&he->mem_info);
+	map__zput(he->ms.map);
+
+	if (he->branch_info) {
+		map__zput(he->branch_info->from.map);
+		map__zput(he->branch_info->to.map);
+		zfree(&he->branch_info);
+	}
+
+	if (he->mem_info) {
+		map__zput(he->mem_info->iaddr.map);
+		map__zput(he->mem_info->daddr.map);
+		zfree(&he->mem_info);
+	}
+
 	zfree(&he->stat_acc);
 	free_srcline(he->srcline);
 	free_callchain(he->callchain);
@@ -1163,7 +1166,7 @@ static void hists__remove_entry_filter(struct hists *hists, struct hist_entry *h
 		return;
 
 	/* force fold unfiltered entry for simplicity */
-	h->ms.unfolded = false;
+	h->unfolded = false;
 	h->row_offset = 0;
 	h->nr_rows = 0;
 
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index 9f31b89a527a..5ed8d9c22981 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -111,7 +111,6 @@ struct hist_entry *__hists__add_entry(struct hists *hists,
 				      u64 weight, u64 transaction,
 				      bool sample_self);
 int hist_entry_iter__add(struct hist_entry_iter *iter, struct addr_location *al,
-			 struct perf_evsel *evsel, struct perf_sample *sample,
 			 int max_stack_depth, void *arg);
 
 int64_t hist_entry__cmp(struct hist_entry *left, struct hist_entry *right);
diff --git a/tools/perf/util/include/linux/poison.h b/tools/perf/util/include/linux/poison.h
deleted file mode 100644
index fef6dbc9ce13..000000000000
--- a/tools/perf/util/include/linux/poison.h
+++ /dev/null
@@ -1 +0,0 @@
-#include "../../../../include/linux/poison.h"
diff --git a/tools/perf/util/include/linux/rbtree.h b/tools/perf/util/include/linux/rbtree.h
index 2a030c5af3aa..f06d89f0b867 100644
--- a/tools/perf/util/include/linux/rbtree.h
+++ b/tools/perf/util/include/linux/rbtree.h
@@ -1,2 +1,16 @@
+#ifndef __TOOLS_LINUX_PERF_RBTREE_H
+#define __TOOLS_LINUX_PERF_RBTREE_H
 #include <stdbool.h>
 #include "../../../../include/linux/rbtree.h"
+
+/*
+ * Handy for checking that we are not deleting an entry that is
+ * already in a list, found in block/{blk-throttle,cfq-iosched}.c,
+ * probably should be moved to lib/rbtree.c...
+ */
+static inline void rb_erase_init(struct rb_node *n, struct rb_root *root)
+{
+	rb_erase(n, root);
+	RB_CLEAR_NODE(n);
+}
+#endif /* __TOOLS_LINUX_PERF_RBTREE_H */
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 527e032e24f6..4744673aff1b 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -14,20 +14,23 @@
 #include "unwind.h"
 #include "linux/hash.h"
 
+static void __machine__remove_thread(struct machine *machine, struct thread *th, bool lock);
+
 static void dsos__init(struct dsos *dsos)
 {
 	INIT_LIST_HEAD(&dsos->head);
 	dsos->root = RB_ROOT;
+	pthread_rwlock_init(&dsos->lock, NULL);
 }
 
 int machine__init(struct machine *machine, const char *root_dir, pid_t pid)
 {
 	map_groups__init(&machine->kmaps, machine);
 	RB_CLEAR_NODE(&machine->rb_node);
-	dsos__init(&machine->user_dsos);
-	dsos__init(&machine->kernel_dsos);
+	dsos__init(&machine->dsos);
 
 	machine->threads = RB_ROOT;
+	pthread_rwlock_init(&machine->threads_lock, NULL);
 	INIT_LIST_HEAD(&machine->dead_threads);
 	machine->last_match = NULL;
 
@@ -54,6 +57,7 @@ int machine__init(struct machine *machine, const char *root_dir, pid_t pid)
 
 		snprintf(comm, sizeof(comm), "[guest/%d]", pid);
 		thread__set_comm(thread, comm, 0);
+		thread__put(thread);
 	}
 
 	machine->current_tid = NULL;
@@ -78,37 +82,50 @@ out_delete:
 	return NULL;
 }
 
-static void dsos__delete(struct dsos *dsos)
+static void dsos__purge(struct dsos *dsos)
 {
 	struct dso *pos, *n;
 
+	pthread_rwlock_wrlock(&dsos->lock);
+
 	list_for_each_entry_safe(pos, n, &dsos->head, node) {
 		RB_CLEAR_NODE(&pos->rb_node);
-		list_del(&pos->node);
-		dso__delete(pos);
+		list_del_init(&pos->node);
+		dso__put(pos);
 	}
+
+	pthread_rwlock_unlock(&dsos->lock);
+}
+
+static void dsos__exit(struct dsos *dsos)
+{
+	dsos__purge(dsos);
+	pthread_rwlock_destroy(&dsos->lock);
 }
 
 void machine__delete_threads(struct machine *machine)
 {
-	struct rb_node *nd = rb_first(&machine->threads);
+	struct rb_node *nd;
 
+	pthread_rwlock_wrlock(&machine->threads_lock);
+	nd = rb_first(&machine->threads);
 	while (nd) {
 		struct thread *t = rb_entry(nd, struct thread, rb_node);
 
 		nd = rb_next(nd);
-		machine__remove_thread(machine, t);
+		__machine__remove_thread(machine, t, false);
 	}
+	pthread_rwlock_unlock(&machine->threads_lock);
 }
 
 void machine__exit(struct machine *machine)
 {
 	map_groups__exit(&machine->kmaps);
-	dsos__delete(&machine->user_dsos);
-	dsos__delete(&machine->kernel_dsos);
-	vdso__exit(machine);
+	dsos__exit(&machine->dsos);
+	machine__exit_vdso(machine);
 	zfree(&machine->root_dir);
 	zfree(&machine->current_tid);
+	pthread_rwlock_destroy(&machine->threads_lock);
 }
 
 void machine__delete(struct machine *machine)
@@ -303,7 +320,7 @@ static void machine__update_thread_pid(struct machine *machine,
 	if (th->pid_ == th->tid)
 		return;
 
-	leader = machine__findnew_thread(machine, th->pid_, th->pid_);
+	leader = __machine__findnew_thread(machine, th->pid_, th->pid_);
 	if (!leader)
 		goto out_err;
 
@@ -325,7 +342,7 @@ static void machine__update_thread_pid(struct machine *machine,
 		if (!map_groups__empty(th->mg))
 			pr_err("Discarding thread maps for %d:%d\n",
 			       th->pid_, th->tid);
-		map_groups__delete(th->mg);
+		map_groups__put(th->mg);
 	}
 
 	th->mg = map_groups__get(leader->mg);
@@ -336,9 +353,9 @@ out_err:
 	pr_err("Failed to join map groups for %d:%d\n", th->pid_, th->tid);
 }
 
-static struct thread *__machine__findnew_thread(struct machine *machine,
-						pid_t pid, pid_t tid,
-						bool create)
+static struct thread *____machine__findnew_thread(struct machine *machine,
+						  pid_t pid, pid_t tid,
+						  bool create)
 {
 	struct rb_node **p = &machine->threads.rb_node;
 	struct rb_node *parent = NULL;
@@ -356,7 +373,7 @@ static struct thread *__machine__findnew_thread(struct machine *machine,
 			return th;
 		}
 
-		thread__zput(machine->last_match);
+		machine->last_match = NULL;
 	}
 
 	while (*p != NULL) {
@@ -364,7 +381,7 @@ static struct thread *__machine__findnew_thread(struct machine *machine,
 		th = rb_entry(parent, struct thread, rb_node);
 
 		if (th->tid == tid) {
-			machine->last_match = thread__get(th);
+			machine->last_match = th;
 			machine__update_thread_pid(machine, th, pid);
 			return th;
 		}
@@ -392,7 +409,8 @@ static struct thread *__machine__findnew_thread(struct machine *machine,
 		 * leader and that would screwed the rb tree.
 		 */
 		if (thread__init_map_groups(th, machine)) {
-			rb_erase(&th->rb_node, &machine->threads);
+			rb_erase_init(&th->rb_node, &machine->threads);
+			RB_CLEAR_NODE(&th->rb_node);
 			thread__delete(th);
 			return NULL;
 		}
@@ -400,22 +418,36 @@ static struct thread *__machine__findnew_thread(struct machine *machine,
 		 * It is now in the rbtree, get a ref
 		 */
 		thread__get(th);
-		machine->last_match = thread__get(th);
+		machine->last_match = th;
 	}
 
 	return th;
 }
 
+struct thread *__machine__findnew_thread(struct machine *machine, pid_t pid, pid_t tid)
+{
+	return ____machine__findnew_thread(machine, pid, tid, true);
+}
+
 struct thread *machine__findnew_thread(struct machine *machine, pid_t pid,
 				       pid_t tid)
 {
-	return __machine__findnew_thread(machine, pid, tid, true);
+	struct thread *th;
+
+	pthread_rwlock_wrlock(&machine->threads_lock);
+	th = thread__get(__machine__findnew_thread(machine, pid, tid));
+	pthread_rwlock_unlock(&machine->threads_lock);
+	return th;
 }
 
 struct thread *machine__find_thread(struct machine *machine, pid_t pid,
 				    pid_t tid)
 {
-	return __machine__findnew_thread(machine, pid, tid, false);
+	struct thread *th;
+	pthread_rwlock_rdlock(&machine->threads_lock);
+	th =  thread__get(____machine__findnew_thread(machine, pid, tid, false));
+	pthread_rwlock_unlock(&machine->threads_lock);
+	return th;
 }
 
 struct comm *machine__thread_exec_comm(struct machine *machine,
@@ -434,6 +466,7 @@ int machine__process_comm_event(struct machine *machine, union perf_event *event
 							event->comm.pid,
 							event->comm.tid);
 	bool exec = event->header.misc & PERF_RECORD_MISC_COMM_EXEC;
+	int err = 0;
 
 	if (exec)
 		machine->comm_exec = true;
@@ -444,10 +477,12 @@ int machine__process_comm_event(struct machine *machine, union perf_event *event
 	if (thread == NULL ||
 	    __thread__set_comm(thread, event->comm.comm, sample->time, exec)) {
 		dump_printf("problem processing PERF_RECORD_COMM, skipping event.\n");
-		return -1;
+		err = -1;
 	}
 
-	return 0;
+	thread__put(thread);
+
+	return err;
 }
 
 int machine__process_lost_event(struct machine *machine __maybe_unused,
@@ -458,17 +493,27 @@ int machine__process_lost_event(struct machine *machine __maybe_unused,
 	return 0;
 }
 
-static struct dso*
-machine__module_dso(struct machine *machine, struct kmod_path *m,
-		    const char *filename)
+int machine__process_lost_samples_event(struct machine *machine __maybe_unused,
+					union perf_event *event, struct perf_sample *sample)
+{
+	dump_printf(": id:%" PRIu64 ": lost samples :%" PRIu64 "\n",
+		    sample->id, event->lost_samples.lost);
+	return 0;
+}
+
+static struct dso *machine__findnew_module_dso(struct machine *machine,
+					       struct kmod_path *m,
+					       const char *filename)
 {
 	struct dso *dso;
 
-	dso = dsos__find(&machine->kernel_dsos, m->name, true);
+	pthread_rwlock_wrlock(&machine->dsos.lock);
+
+	dso = __dsos__find(&machine->dsos, m->name, true);
 	if (!dso) {
-		dso = dsos__addnew(&machine->kernel_dsos, m->name);
+		dso = __dsos__addnew(&machine->dsos, m->name);
 		if (dso == NULL)
-			return NULL;
+			goto out_unlock;
 
 		if (machine__is_host(machine))
 			dso->symtab_type = DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE;
@@ -483,11 +528,30 @@ machine__module_dso(struct machine *machine, struct kmod_path *m,
 		dso__set_long_name(dso, strdup(filename), true);
 	}
 
+	dso__get(dso);
+out_unlock:
+	pthread_rwlock_unlock(&machine->dsos.lock);
 	return dso;
 }
 
-struct map *machine__new_module(struct machine *machine, u64 start,
-				const char *filename)
+int machine__process_aux_event(struct machine *machine __maybe_unused,
+			       union perf_event *event)
+{
+	if (dump_trace)
+		perf_event__fprintf_aux(event, stdout);
+	return 0;
+}
+
+int machine__process_itrace_start_event(struct machine *machine __maybe_unused,
+					union perf_event *event)
+{
+	if (dump_trace)
+		perf_event__fprintf_itrace_start(event, stdout);
+	return 0;
+}
+
+struct map *machine__findnew_module_map(struct machine *machine, u64 start,
+					const char *filename)
 {
 	struct map *map = NULL;
 	struct dso *dso;
@@ -501,7 +565,7 @@ struct map *machine__new_module(struct machine *machine, u64 start,
 	if (map)
 		goto out;
 
-	dso = machine__module_dso(machine, &m, filename);
+	dso = machine__findnew_module_dso(machine, &m, filename);
 	if (dso == NULL)
 		goto out;
 
@@ -519,13 +583,11 @@ out:
 size_t machines__fprintf_dsos(struct machines *machines, FILE *fp)
 {
 	struct rb_node *nd;
-	size_t ret = __dsos__fprintf(&machines->host.kernel_dsos.head, fp) +
-		     __dsos__fprintf(&machines->host.user_dsos.head, fp);
+	size_t ret = __dsos__fprintf(&machines->host.dsos.head, fp);
 
 	for (nd = rb_first(&machines->guests); nd; nd = rb_next(nd)) {
 		struct machine *pos = rb_entry(nd, struct machine, rb_node);
-		ret += __dsos__fprintf(&pos->kernel_dsos.head, fp);
-		ret += __dsos__fprintf(&pos->user_dsos.head, fp);
+		ret += __dsos__fprintf(&pos->dsos.head, fp);
 	}
 
 	return ret;
@@ -534,8 +596,7 @@ size_t machines__fprintf_dsos(struct machines *machines, FILE *fp)
 size_t machine__fprintf_dsos_buildid(struct machine *m, FILE *fp,
 				     bool (skip)(struct dso *dso, int parm), int parm)
 {
-	return __dsos__fprintf_buildid(&m->kernel_dsos.head, fp, skip, parm) +
-	       __dsos__fprintf_buildid(&m->user_dsos.head, fp, skip, parm);
+	return __dsos__fprintf_buildid(&m->dsos.head, fp, skip, parm);
 }
 
 size_t machines__fprintf_dsos_buildid(struct machines *machines, FILE *fp,
@@ -575,12 +636,16 @@ size_t machine__fprintf(struct machine *machine, FILE *fp)
 	size_t ret = 0;
 	struct rb_node *nd;
 
+	pthread_rwlock_rdlock(&machine->threads_lock);
+
 	for (nd = rb_first(&machine->threads); nd; nd = rb_next(nd)) {
 		struct thread *pos = rb_entry(nd, struct thread, rb_node);
 
 		ret += thread__fprintf(pos, fp);
 	}
 
+	pthread_rwlock_unlock(&machine->threads_lock);
+
 	return ret;
 }
 
@@ -594,9 +659,8 @@ static struct dso *machine__get_kernel(struct machine *machine)
 		if (!vmlinux_name)
 			vmlinux_name = "[kernel.kallsyms]";
 
-		kernel = dso__kernel_findnew(machine, vmlinux_name,
-					     "[kernel]",
-					     DSO_TYPE_KERNEL);
+		kernel = machine__findnew_kernel(machine, vmlinux_name,
+						 "[kernel]", DSO_TYPE_KERNEL);
 	} else {
 		char bf[PATH_MAX];
 
@@ -606,9 +670,9 @@ static struct dso *machine__get_kernel(struct machine *machine)
 			vmlinux_name = machine__mmap_name(machine, bf,
 							  sizeof(bf));
 
-		kernel = dso__kernel_findnew(machine, vmlinux_name,
-					     "[guest.kernel]",
-					     DSO_TYPE_GUEST_KERNEL);
+		kernel = machine__findnew_kernel(machine, vmlinux_name,
+						 "[guest.kernel]",
+						 DSO_TYPE_GUEST_KERNEL);
 	}
 
 	if (kernel != NULL && (!kernel->has_build_id))
@@ -713,7 +777,6 @@ void machine__destroy_kernel_maps(struct machine *machine)
 				kmap->ref_reloc_sym = NULL;
 		}
 
-		map__delete(machine->vmlinux_maps[type]);
 		machine->vmlinux_maps[type] = NULL;
 	}
 }
@@ -970,7 +1033,7 @@ static int machine__create_module(void *arg, const char *name, u64 start)
 	struct machine *machine = arg;
 	struct map *map;
 
-	map = machine__new_module(machine, start, name);
+	map = machine__findnew_module_map(machine, start, name);
 	if (map == NULL)
 		return -1;
 
@@ -1062,7 +1125,7 @@ static bool machine__uses_kcore(struct machine *machine)
 {
 	struct dso *dso;
 
-	list_for_each_entry(dso, &machine->kernel_dsos.head, node) {
+	list_for_each_entry(dso, &machine->dsos.head, node) {
 		if (dso__is_kcore(dso))
 			return true;
 	}
@@ -1093,8 +1156,8 @@ static int machine__process_kernel_mmap_event(struct machine *machine,
 				strlen(kmmap_prefix) - 1) == 0;
 	if (event->mmap.filename[0] == '/' ||
 	    (!is_kernel_mmap && event->mmap.filename[0] == '[')) {
-		map = machine__new_module(machine, event->mmap.start,
-					  event->mmap.filename);
+		map = machine__findnew_module_map(machine, event->mmap.start,
+						  event->mmap.filename);
 		if (map == NULL)
 			goto out_problem;
 
@@ -1109,23 +1172,48 @@ static int machine__process_kernel_mmap_event(struct machine *machine,
 		struct dso *kernel = NULL;
 		struct dso *dso;
 
-		list_for_each_entry(dso, &machine->kernel_dsos.head, node) {
-			if (is_kernel_module(dso->long_name))
+		pthread_rwlock_rdlock(&machine->dsos.lock);
+
+		list_for_each_entry(dso, &machine->dsos.head, node) {
+
+			/*
+			 * The cpumode passed to is_kernel_module is not the
+			 * cpumode of *this* event. If we insist on passing
+			 * correct cpumode to is_kernel_module, we should
+			 * record the cpumode when we adding this dso to the
+			 * linked list.
+			 *
+			 * However we don't really need passing correct
+			 * cpumode.  We know the correct cpumode must be kernel
+			 * mode (if not, we should not link it onto kernel_dsos
+			 * list).
+			 *
+			 * Therefore, we pass PERF_RECORD_MISC_CPUMODE_UNKNOWN.
+			 * is_kernel_module() treats it as a kernel cpumode.
+			 */
+
+			if (!dso->kernel ||
+			    is_kernel_module(dso->long_name,
+					     PERF_RECORD_MISC_CPUMODE_UNKNOWN))
 				continue;
 
+
 			kernel = dso;
 			break;
 		}
 
+		pthread_rwlock_unlock(&machine->dsos.lock);
+
 		if (kernel == NULL)
-			kernel = __dsos__findnew(&machine->kernel_dsos,
-						 kmmap_prefix);
+			kernel = machine__findnew_dso(machine, kmmap_prefix);
 		if (kernel == NULL)
 			goto out_problem;
 
 		kernel->kernel = kernel_type;
-		if (__machine__create_kernel_maps(machine, kernel) < 0)
+		if (__machine__create_kernel_maps(machine, kernel) < 0) {
+			dso__put(kernel);
 			goto out_problem;
+		}
 
 		if (strstr(kernel->long_name, "vmlinux"))
 			dso__set_short_name(kernel, "[kernel.vmlinux]", false);
@@ -1197,11 +1285,15 @@ int machine__process_mmap2_event(struct machine *machine,
 			event->mmap2.filename, type, thread);
 
 	if (map == NULL)
-		goto out_problem;
+		goto out_problem_map;
 
 	thread__insert_map(thread, map);
+	thread__put(thread);
+	map__put(map);
 	return 0;
 
+out_problem_map:
+	thread__put(thread);
 out_problem:
 	dump_printf("problem processing PERF_RECORD_MMAP2, skipping event.\n");
 	return 0;
@@ -1244,31 +1336,46 @@ int machine__process_mmap_event(struct machine *machine, union perf_event *event
 			type, thread);
 
 	if (map == NULL)
-		goto out_problem;
+		goto out_problem_map;
 
 	thread__insert_map(thread, map);
+	thread__put(thread);
+	map__put(map);
 	return 0;
 
+out_problem_map:
+	thread__put(thread);
 out_problem:
 	dump_printf("problem processing PERF_RECORD_MMAP, skipping event.\n");
 	return 0;
 }
 
-void machine__remove_thread(struct machine *machine, struct thread *th)
+static void __machine__remove_thread(struct machine *machine, struct thread *th, bool lock)
 {
 	if (machine->last_match == th)
-		thread__zput(machine->last_match);
+		machine->last_match = NULL;
 
-	rb_erase(&th->rb_node, &machine->threads);
+	BUG_ON(atomic_read(&th->refcnt) == 0);
+	if (lock)
+		pthread_rwlock_wrlock(&machine->threads_lock);
+	rb_erase_init(&th->rb_node, &machine->threads);
+	RB_CLEAR_NODE(&th->rb_node);
 	/*
 	 * Move it first to the dead_threads list, then drop the reference,
 	 * if this is the last reference, then the thread__delete destructor
 	 * will be called and we will remove it from the dead_threads list.
 	 */
 	list_add_tail(&th->node, &machine->dead_threads);
+	if (lock)
+		pthread_rwlock_unlock(&machine->threads_lock);
 	thread__put(th);
 }
 
+void machine__remove_thread(struct machine *machine, struct thread *th)
+{
+	return __machine__remove_thread(machine, th, true);
+}
+
 int machine__process_fork_event(struct machine *machine, union perf_event *event,
 				struct perf_sample *sample)
 {
@@ -1278,10 +1385,13 @@ int machine__process_fork_event(struct machine *machine, union perf_event *event
 	struct thread *parent = machine__findnew_thread(machine,
 							event->fork.ppid,
 							event->fork.ptid);
+	int err = 0;
 
 	/* if a thread currently exists for the thread id remove it */
-	if (thread != NULL)
+	if (thread != NULL) {
 		machine__remove_thread(machine, thread);
+		thread__put(thread);
+	}
 
 	thread = machine__findnew_thread(machine, event->fork.pid,
 					 event->fork.tid);
@@ -1291,10 +1401,12 @@ int machine__process_fork_event(struct machine *machine, union perf_event *event
 	if (thread == NULL || parent == NULL ||
 	    thread__fork(thread, parent, sample->time) < 0) {
 		dump_printf("problem processing PERF_RECORD_FORK, skipping event.\n");
-		return -1;
+		err = -1;
 	}
+	thread__put(thread);
+	thread__put(parent);
 
-	return 0;
+	return err;
 }
 
 int machine__process_exit_event(struct machine *machine, union perf_event *event,
@@ -1307,8 +1419,10 @@ int machine__process_exit_event(struct machine *machine, union perf_event *event
 	if (dump_trace)
 		perf_event__fprintf_task(event, stdout);
 
-	if (thread != NULL)
+	if (thread != NULL) {
 		thread__exited(thread);
+		thread__put(thread);
+	}
 
 	return 0;
 }
@@ -1331,6 +1445,13 @@ int machine__process_event(struct machine *machine, union perf_event *event,
 		ret = machine__process_exit_event(machine, event, sample); break;
 	case PERF_RECORD_LOST:
 		ret = machine__process_lost_event(machine, event, sample); break;
+	case PERF_RECORD_AUX:
+		ret = machine__process_aux_event(machine, event); break;
+	case PERF_RECORD_ITRACE_START:
+		ret = machine__process_itrace_start_event(machine, event);
+	case PERF_RECORD_LOST_SAMPLES:
+		ret = machine__process_lost_samples_event(machine, event, sample); break;
+		break;
 	default:
 		ret = -1;
 		break;
@@ -1769,14 +1890,36 @@ int machine__for_each_thread(struct machine *machine,
 	return rc;
 }
 
+int machines__for_each_thread(struct machines *machines,
+			      int (*fn)(struct thread *thread, void *p),
+			      void *priv)
+{
+	struct rb_node *nd;
+	int rc = 0;
+
+	rc = machine__for_each_thread(&machines->host, fn, priv);
+	if (rc != 0)
+		return rc;
+
+	for (nd = rb_first(&machines->guests); nd; nd = rb_next(nd)) {
+		struct machine *machine = rb_entry(nd, struct machine, rb_node);
+
+		rc = machine__for_each_thread(machine, fn, priv);
+		if (rc != 0)
+			return rc;
+	}
+	return rc;
+}
+
 int __machine__synthesize_threads(struct machine *machine, struct perf_tool *tool,
 				  struct target *target, struct thread_map *threads,
-				  perf_event__handler_t process, bool data_mmap)
+				  perf_event__handler_t process, bool data_mmap,
+				  unsigned int proc_map_timeout)
 {
 	if (target__has_task(target))
-		return perf_event__synthesize_thread_map(tool, threads, process, machine, data_mmap);
+		return perf_event__synthesize_thread_map(tool, threads, process, machine, data_mmap, proc_map_timeout);
 	else if (target__has_cpu(target))
-		return perf_event__synthesize_threads(tool, process, machine, data_mmap);
+		return perf_event__synthesize_threads(tool, process, machine, data_mmap, proc_map_timeout);
 	/* command specified */
 	return 0;
 }
@@ -1820,6 +1963,7 @@ int machine__set_current_tid(struct machine *machine, int cpu, pid_t pid,
 		return -ENOMEM;
 
 	thread->cpu = cpu;
+	thread__put(thread);
 
 	return 0;
 }
@@ -1845,3 +1989,8 @@ int machine__get_kernel_start(struct machine *machine)
 	}
 	return err;
 }
+
+struct dso *machine__findnew_dso(struct machine *machine, const char *filename)
+{
+	return dsos__findnew(&machine->dsos, filename);
+}
diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h
index 6d64cedb9d1e..887798e511e9 100644
--- a/tools/perf/util/machine.h
+++ b/tools/perf/util/machine.h
@@ -30,11 +30,11 @@ struct machine {
 	bool		  comm_exec;
 	char		  *root_dir;
 	struct rb_root	  threads;
+	pthread_rwlock_t  threads_lock;
 	struct list_head  dead_threads;
 	struct thread	  *last_match;
 	struct vdso_info  *vdso_info;
-	struct dsos	  user_dsos;
-	struct dsos	  kernel_dsos;
+	struct dsos	  dsos;
 	struct map_groups kmaps;
 	struct map	  *vmlinux_maps[MAP__NR_TYPES];
 	u64		  kernel_start;
@@ -81,6 +81,12 @@ int machine__process_fork_event(struct machine *machine, union perf_event *event
 				struct perf_sample *sample);
 int machine__process_lost_event(struct machine *machine, union perf_event *event,
 				struct perf_sample *sample);
+int machine__process_lost_samples_event(struct machine *machine, union perf_event *event,
+					struct perf_sample *sample);
+int machine__process_aux_event(struct machine *machine,
+			       union perf_event *event);
+int machine__process_itrace_start_event(struct machine *machine,
+					union perf_event *event);
 int machine__process_mmap_event(struct machine *machine, union perf_event *event,
 				struct perf_sample *sample);
 int machine__process_mmap2_event(struct machine *machine, union perf_event *event,
@@ -147,8 +153,10 @@ static inline bool machine__is_host(struct machine *machine)
 	return machine ? machine->pid == HOST_KERNEL_ID : false;
 }
 
-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);
+struct thread *machine__findnew_thread(struct machine *machine, pid_t pid, pid_t tid);
+
+struct dso *machine__findnew_dso(struct machine *machine, const char *filename);
 
 size_t machine__fprintf(struct machine *machine, FILE *fp);
 
@@ -181,8 +189,8 @@ struct symbol *machine__find_kernel_function_by_name(struct machine *machine,
 						 filter);
 }
 
-struct map *machine__new_module(struct machine *machine, u64 start,
-				const char *filename);
+struct map *machine__findnew_module_map(struct machine *machine, u64 start,
+					const char *filename);
 
 int machine__load_kallsyms(struct machine *machine, const char *filename,
 			   enum map_type type, symbol_filter_t filter);
@@ -208,16 +216,22 @@ size_t machine__fprintf_vmlinux_path(struct machine *machine, FILE *fp);
 int machine__for_each_thread(struct machine *machine,
 			     int (*fn)(struct thread *thread, void *p),
 			     void *priv);
+int machines__for_each_thread(struct machines *machines,
+			      int (*fn)(struct thread *thread, void *p),
+			      void *priv);
 
 int __machine__synthesize_threads(struct machine *machine, struct perf_tool *tool,
 				  struct target *target, struct thread_map *threads,
-				  perf_event__handler_t process, bool data_mmap);
+				  perf_event__handler_t process, bool data_mmap,
+				  unsigned int proc_map_timeout);
 static inline
 int machine__synthesize_threads(struct machine *machine, struct target *target,
-				struct thread_map *threads, bool data_mmap)
+				struct thread_map *threads, bool data_mmap,
+				unsigned int proc_map_timeout)
 {
 	return __machine__synthesize_threads(machine, NULL, target, threads,
-					     perf_event__process, data_mmap);
+					     perf_event__process, data_mmap,
+					     proc_map_timeout);
 }
 
 pid_t machine__get_current_tid(struct machine *machine, int cpu);
diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c
index a14f08f41686..b5a5e9c02437 100644
--- a/tools/perf/util/map.c
+++ b/tools/perf/util/map.c
@@ -16,6 +16,8 @@
 #include "machine.h"
 #include <linux/string.h>
 
+static void __maps__insert(struct maps *maps, struct map *map);
+
 const char *map_type__name[MAP__NR_TYPES] = {
 	[MAP__FUNCTION] = "Functions",
 	[MAP__VARIABLE] = "Variables",
@@ -130,13 +132,13 @@ void map__init(struct map *map, enum map_type type,
 	map->end      = end;
 	map->pgoff    = pgoff;
 	map->reloc    = 0;
-	map->dso      = dso;
+	map->dso      = dso__get(dso);
 	map->map_ip   = map__map_ip;
 	map->unmap_ip = map__unmap_ip;
 	RB_CLEAR_NODE(&map->rb_node);
 	map->groups   = NULL;
-	map->referenced = false;
 	map->erange_warned = false;
+	atomic_set(&map->refcnt, 1);
 }
 
 struct map *map__new(struct machine *machine, u64 start, u64 len,
@@ -175,9 +177,9 @@ struct map *map__new(struct machine *machine, u64 start, u64 len,
 
 		if (vdso) {
 			pgoff = 0;
-			dso = vdso__dso_findnew(machine, thread);
+			dso = machine__findnew_vdso(machine, thread);
 		} else
-			dso = __dsos__findnew(&machine->user_dsos, filename);
+			dso = machine__findnew_dso(machine, filename);
 
 		if (dso == NULL)
 			goto out_delete;
@@ -195,6 +197,7 @@ struct map *map__new(struct machine *machine, u64 start, u64 len,
 			if (type != MAP__FUNCTION)
 				dso__set_loaded(dso, map->type);
 		}
+		dso__put(dso);
 	}
 	return map;
 out_delete:
@@ -221,11 +224,24 @@ struct map *map__new2(u64 start, struct dso *dso, enum map_type type)
 	return map;
 }
 
+static void map__exit(struct map *map)
+{
+	BUG_ON(!RB_EMPTY_NODE(&map->rb_node));
+	dso__zput(map->dso);
+}
+
 void map__delete(struct map *map)
 {
+	map__exit(map);
 	free(map);
 }
 
+void map__put(struct map *map)
+{
+	if (map && atomic_dec_and_test(&map->refcnt))
+		map__delete(map);
+}
+
 void map__fixup_start(struct map *map)
 {
 	struct rb_root *symbols = &map->dso->symbols[map->type];
@@ -292,6 +308,11 @@ int map__load(struct map *map, symbol_filter_t filter)
 	return 0;
 }
 
+int __weak arch__compare_symbol_names(const char *namea, const char *nameb)
+{
+	return strcmp(namea, nameb);
+}
+
 struct symbol *map__find_symbol(struct map *map, u64 addr,
 				symbol_filter_t filter)
 {
@@ -413,48 +434,49 @@ u64 map__objdump_2mem(struct map *map, u64 ip)
 	return ip + map->reloc;
 }
 
+static void maps__init(struct maps *maps)
+{
+	maps->entries = RB_ROOT;
+	pthread_rwlock_init(&maps->lock, NULL);
+}
+
 void map_groups__init(struct map_groups *mg, struct machine *machine)
 {
 	int i;
 	for (i = 0; i < MAP__NR_TYPES; ++i) {
-		mg->maps[i] = RB_ROOT;
-		INIT_LIST_HEAD(&mg->removed_maps[i]);
+		maps__init(&mg->maps[i]);
 	}
 	mg->machine = machine;
-	mg->refcnt = 1;
+	atomic_set(&mg->refcnt, 1);
 }
 
-static void maps__delete(struct rb_root *maps)
+static void __maps__purge(struct maps *maps)
 {
-	struct rb_node *next = rb_first(maps);
+	struct rb_root *root = &maps->entries;
+	struct rb_node *next = rb_first(root);
 
 	while (next) {
 		struct map *pos = rb_entry(next, struct map, rb_node);
 
 		next = rb_next(&pos->rb_node);
-		rb_erase(&pos->rb_node, maps);
-		map__delete(pos);
+		rb_erase_init(&pos->rb_node, root);
+		map__put(pos);
 	}
 }
 
-static void maps__delete_removed(struct list_head *maps)
+static void maps__exit(struct maps *maps)
 {
-	struct map *pos, *n;
-
-	list_for_each_entry_safe(pos, n, maps, node) {
-		list_del(&pos->node);
-		map__delete(pos);
-	}
+	pthread_rwlock_wrlock(&maps->lock);
+	__maps__purge(maps);
+	pthread_rwlock_unlock(&maps->lock);
 }
 
 void map_groups__exit(struct map_groups *mg)
 {
 	int i;
 
-	for (i = 0; i < MAP__NR_TYPES; ++i) {
-		maps__delete(&mg->maps[i]);
-		maps__delete_removed(&mg->removed_maps[i]);
-	}
+	for (i = 0; i < MAP__NR_TYPES; ++i)
+		maps__exit(&mg->maps[i]);
 }
 
 bool map_groups__empty(struct map_groups *mg)
@@ -464,8 +486,6 @@ bool map_groups__empty(struct map_groups *mg)
 	for (i = 0; i < MAP__NR_TYPES; ++i) {
 		if (maps__first(&mg->maps[i]))
 			return false;
-		if (!list_empty(&mg->removed_maps[i]))
-			return false;
 	}
 
 	return true;
@@ -489,32 +509,10 @@ void map_groups__delete(struct map_groups *mg)
 
 void map_groups__put(struct map_groups *mg)
 {
-	if (--mg->refcnt == 0)
+	if (mg && atomic_dec_and_test(&mg->refcnt))
 		map_groups__delete(mg);
 }
 
-void map_groups__flush(struct map_groups *mg)
-{
-	int type;
-
-	for (type = 0; type < MAP__NR_TYPES; type++) {
-		struct rb_root *root = &mg->maps[type];
-		struct rb_node *next = rb_first(root);
-
-		while (next) {
-			struct map *pos = rb_entry(next, struct map, rb_node);
-			next = rb_next(&pos->rb_node);
-			rb_erase(&pos->rb_node, root);
-			/*
-			 * We may have references to this map, for
-			 * instance in some hist_entry instances, so
-			 * just move them to a separate list.
-			 */
-			list_add_tail(&pos->node, &mg->removed_maps[pos->type]);
-		}
-	}
-}
-
 struct symbol *map_groups__find_symbol(struct map_groups *mg,
 				       enum map_type type, u64 addr,
 				       struct map **mapp,
@@ -538,20 +536,28 @@ struct symbol *map_groups__find_symbol_by_name(struct map_groups *mg,
 					       struct map **mapp,
 					       symbol_filter_t filter)
 {
+	struct maps *maps = &mg->maps[type];
+	struct symbol *sym;
 	struct rb_node *nd;
 
-	for (nd = rb_first(&mg->maps[type]); nd; nd = rb_next(nd)) {
+	pthread_rwlock_rdlock(&maps->lock);
+
+	for (nd = rb_first(&maps->entries); nd; nd = rb_next(nd)) {
 		struct map *pos = rb_entry(nd, struct map, rb_node);
-		struct symbol *sym = map__find_symbol_by_name(pos, name, filter);
+
+		sym = map__find_symbol_by_name(pos, name, filter);
 
 		if (sym == NULL)
 			continue;
 		if (mapp != NULL)
 			*mapp = pos;
-		return sym;
+		goto out;
 	}
 
-	return NULL;
+	sym = NULL;
+out:
+	pthread_rwlock_unlock(&maps->lock);
+	return sym;
 }
 
 int map_groups__find_ams(struct addr_map_symbol *ams, symbol_filter_t filter)
@@ -571,73 +577,54 @@ int map_groups__find_ams(struct addr_map_symbol *ams, symbol_filter_t filter)
 	return ams->sym ? 0 : -1;
 }
 
-size_t __map_groups__fprintf_maps(struct map_groups *mg, enum map_type type,
-				  FILE *fp)
+static size_t maps__fprintf(struct maps *maps, FILE *fp)
 {
-	size_t printed = fprintf(fp, "%s:\n", map_type__name[type]);
+	size_t printed = 0;
 	struct rb_node *nd;
 
-	for (nd = rb_first(&mg->maps[type]); nd; nd = rb_next(nd)) {
+	pthread_rwlock_rdlock(&maps->lock);
+
+	for (nd = rb_first(&maps->entries); nd; nd = rb_next(nd)) {
 		struct map *pos = rb_entry(nd, struct map, rb_node);
 		printed += fprintf(fp, "Map:");
 		printed += map__fprintf(pos, fp);
 		if (verbose > 2) {
-			printed += dso__fprintf(pos->dso, type, fp);
+			printed += dso__fprintf(pos->dso, pos->type, fp);
 			printed += fprintf(fp, "--\n");
 		}
 	}
 
-	return printed;
-}
+	pthread_rwlock_unlock(&maps->lock);
 
-static size_t map_groups__fprintf_maps(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;
 }
 
-static size_t __map_groups__fprintf_removed_maps(struct map_groups *mg,
-						 enum map_type type, FILE *fp)
+size_t __map_groups__fprintf_maps(struct map_groups *mg, enum map_type type,
+				  FILE *fp)
 {
-	struct map *pos;
-	size_t printed = 0;
-
-	list_for_each_entry(pos, &mg->removed_maps[type], node) {
-		printed += fprintf(fp, "Map:");
-		printed += map__fprintf(pos, fp);
-		if (verbose > 1) {
-			printed += dso__fprintf(pos->dso, type, fp);
-			printed += fprintf(fp, "--\n");
-		}
-	}
-	return printed;
+	size_t printed = fprintf(fp, "%s:\n", map_type__name[type]);
+	return printed += maps__fprintf(&mg->maps[type], fp);
 }
 
-static size_t map_groups__fprintf_removed_maps(struct map_groups *mg,
-					       FILE *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_removed_maps(mg, i, fp);
+		printed += __map_groups__fprintf_maps(mg, i, fp);
 	return printed;
 }
 
-size_t map_groups__fprintf(struct map_groups *mg, FILE *fp)
+static int maps__fixup_overlappings(struct maps *maps, struct map *map, FILE *fp)
 {
-	size_t printed = map_groups__fprintf_maps(mg, fp);
-	printed += fprintf(fp, "Removed maps:\n");
-	return printed + map_groups__fprintf_removed_maps(mg, fp);
-}
-
-int map_groups__fixup_overlappings(struct map_groups *mg, struct map *map,
-				   FILE *fp)
-{
-	struct rb_root *root = &mg->maps[map->type];
-	struct rb_node *next = rb_first(root);
+	struct rb_root *root;
+	struct rb_node *next;
 	int err = 0;
 
+	pthread_rwlock_wrlock(&maps->lock);
+
+	root = &maps->entries;
+	next = rb_first(root);
+
 	while (next) {
 		struct map *pos = rb_entry(next, struct map, rb_node);
 		next = rb_next(&pos->rb_node);
@@ -651,7 +638,7 @@ int map_groups__fixup_overlappings(struct map_groups *mg, struct map *map,
 			map__fprintf(pos, fp);
 		}
 
-		rb_erase(&pos->rb_node, root);
+		rb_erase_init(&pos->rb_node, root);
 		/*
 		 * Now check if we need to create new maps for areas not
 		 * overlapped by the new map:
@@ -661,11 +648,11 @@ int map_groups__fixup_overlappings(struct map_groups *mg, struct map *map,
 
 			if (before == NULL) {
 				err = -ENOMEM;
-				goto move_map;
+				goto put_map;
 			}
 
 			before->end = map->start;
-			map_groups__insert(mg, before);
+			__maps__insert(maps, before);
 			if (verbose >= 2)
 				map__fprintf(before, fp);
 		}
@@ -675,28 +662,31 @@ int map_groups__fixup_overlappings(struct map_groups *mg, struct map *map,
 
 			if (after == NULL) {
 				err = -ENOMEM;
-				goto move_map;
+				goto put_map;
 			}
 
 			after->start = map->end;
-			map_groups__insert(mg, after);
+			__maps__insert(maps, after);
 			if (verbose >= 2)
 				map__fprintf(after, fp);
 		}
-move_map:
-		/*
-		 * If we have references, just move them to a separate list.
-		 */
-		if (pos->referenced)
-			list_add_tail(&pos->node, &mg->removed_maps[map->type]);
-		else
-			map__delete(pos);
+put_map:
+		map__put(pos);
 
 		if (err)
-			return err;
+			goto out;
 	}
 
-	return 0;
+	err = 0;
+out:
+	pthread_rwlock_unlock(&maps->lock);
+	return err;
+}
+
+int map_groups__fixup_overlappings(struct map_groups *mg, struct map *map,
+				   FILE *fp)
+{
+	return maps__fixup_overlappings(&mg->maps[map->type], map, fp);
 }
 
 /*
@@ -705,20 +695,28 @@ move_map:
 int map_groups__clone(struct map_groups *mg,
 		      struct map_groups *parent, enum map_type type)
 {
-	struct rb_node *nd;
-	for (nd = rb_first(&parent->maps[type]); nd; nd = rb_next(nd)) {
-		struct map *map = rb_entry(nd, struct map, rb_node);
+	int err = -ENOMEM;
+	struct map *map;
+	struct maps *maps = &parent->maps[type];
+
+	pthread_rwlock_rdlock(&maps->lock);
+
+	for (map = maps__first(maps); map; map = map__next(map)) {
 		struct map *new = map__clone(map);
 		if (new == NULL)
-			return -ENOMEM;
+			goto out_unlock;
 		map_groups__insert(mg, new);
 	}
-	return 0;
+
+	err = 0;
+out_unlock:
+	pthread_rwlock_unlock(&maps->lock);
+	return err;
 }
 
-void maps__insert(struct rb_root *maps, struct map *map)
+static void __maps__insert(struct maps *maps, struct map *map)
 {
-	struct rb_node **p = &maps->rb_node;
+	struct rb_node **p = &maps->entries.rb_node;
 	struct rb_node *parent = NULL;
 	const u64 ip = map->start;
 	struct map *m;
@@ -733,20 +731,38 @@ void maps__insert(struct rb_root *maps, struct map *map)
 	}
 
 	rb_link_node(&map->rb_node, parent, p);
-	rb_insert_color(&map->rb_node, maps);
+	rb_insert_color(&map->rb_node, &maps->entries);
+	map__get(map);
 }
 
-void maps__remove(struct rb_root *maps, struct map *map)
+void maps__insert(struct maps *maps, struct map *map)
 {
-	rb_erase(&map->rb_node, maps);
+	pthread_rwlock_wrlock(&maps->lock);
+	__maps__insert(maps, map);
+	pthread_rwlock_unlock(&maps->lock);
 }
 
-struct map *maps__find(struct rb_root *maps, u64 ip)
+static void __maps__remove(struct maps *maps, struct map *map)
 {
-	struct rb_node **p = &maps->rb_node;
-	struct rb_node *parent = NULL;
+	rb_erase_init(&map->rb_node, &maps->entries);
+	map__put(map);
+}
+
+void maps__remove(struct maps *maps, struct map *map)
+{
+	pthread_rwlock_wrlock(&maps->lock);
+	__maps__remove(maps, map);
+	pthread_rwlock_unlock(&maps->lock);
+}
+
+struct map *maps__find(struct maps *maps, u64 ip)
+{
+	struct rb_node **p, *parent = NULL;
 	struct map *m;
 
+	pthread_rwlock_rdlock(&maps->lock);
+
+	p = &maps->entries.rb_node;
 	while (*p != NULL) {
 		parent = *p;
 		m = rb_entry(parent, struct map, rb_node);
@@ -755,22 +771,25 @@ struct map *maps__find(struct rb_root *maps, u64 ip)
 		else if (ip >= m->end)
 			p = &(*p)->rb_right;
 		else
-			return m;
+			goto out;
 	}
 
-	return NULL;
+	m = NULL;
+out:
+	pthread_rwlock_unlock(&maps->lock);
+	return m;
 }
 
-struct map *maps__first(struct rb_root *maps)
+struct map *maps__first(struct maps *maps)
 {
-	struct rb_node *first = rb_first(maps);
+	struct rb_node *first = rb_first(&maps->entries);
 
 	if (first)
 		return rb_entry(first, struct map, rb_node);
 	return NULL;
 }
 
-struct map *maps__next(struct map *map)
+struct map *map__next(struct map *map)
 {
 	struct rb_node *next = rb_next(&map->rb_node);
 
diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h
index ec19c59ca38e..d73e687b224e 100644
--- a/tools/perf/util/map.h
+++ b/tools/perf/util/map.h
@@ -1,9 +1,11 @@
 #ifndef __PERF_MAP_H
 #define __PERF_MAP_H
 
+#include <linux/atomic.h>
 #include <linux/compiler.h>
 #include <linux/list.h>
 #include <linux/rbtree.h>
+#include <pthread.h>
 #include <stdio.h>
 #include <stdbool.h>
 #include <linux/types.h>
@@ -32,7 +34,6 @@ struct map {
 	u64			start;
 	u64			end;
 	u8 /* enum map_type */	type;
-	bool			referenced;
 	bool			erange_warned;
 	u32			priv;
 	u32			prot;
@@ -50,6 +51,7 @@ struct map {
 
 	struct dso		*dso;
 	struct map_groups	*groups;
+	atomic_t		refcnt;
 };
 
 struct kmap {
@@ -57,11 +59,15 @@ struct kmap {
 	struct map_groups	*kmaps;
 };
 
+struct maps {
+	struct rb_root	 entries;
+	pthread_rwlock_t lock;
+};
+
 struct map_groups {
-	struct rb_root	 maps[MAP__NR_TYPES];
-	struct list_head removed_maps[MAP__NR_TYPES];
+	struct maps	 maps[MAP__NR_TYPES];
 	struct machine	 *machine;
-	int		 refcnt;
+	atomic_t	 refcnt;
 };
 
 struct map_groups *map_groups__new(struct machine *machine);
@@ -70,7 +76,8 @@ bool map_groups__empty(struct map_groups *mg);
 
 static inline struct map_groups *map_groups__get(struct map_groups *mg)
 {
-	++mg->refcnt;
+	if (mg)
+		atomic_inc(&mg->refcnt);
 	return mg;
 }
 
@@ -124,7 +131,7 @@ struct thread;
  */
 #define __map__for_each_symbol_by_name(map, sym_name, pos, filter)	\
 	for (pos = map__find_symbol_by_name(map, sym_name, filter);	\
-	     pos && strcmp(pos->name, sym_name) == 0;		\
+	     pos && arch__compare_symbol_names(pos->name, sym_name) == 0;	\
 	     pos = symbol__next_by_name(pos))
 
 #define map__for_each_symbol_by_name(map, sym_name, pos)		\
@@ -132,6 +139,7 @@ struct thread;
 
 typedef int (*symbol_filter_t)(struct map *map, struct symbol *sym);
 
+int arch__compare_symbol_names(const char *namea, const char *nameb);
 void map__init(struct map *map, enum map_type type,
 	       u64 start, u64 end, u64 pgoff, struct dso *dso);
 struct map *map__new(struct machine *machine, u64 start, u64 len,
@@ -141,6 +149,24 @@ struct map *map__new(struct machine *machine, u64 start, u64 len,
 struct map *map__new2(u64 start, struct dso *dso, enum map_type type);
 void map__delete(struct map *map);
 struct map *map__clone(struct map *map);
+
+static inline struct map *map__get(struct map *map)
+{
+	if (map)
+		atomic_inc(&map->refcnt);
+	return map;
+}
+
+void map__put(struct map *map);
+
+static inline void __map__zput(struct map **map)
+{
+	map__put(*map);
+	*map = NULL;
+}
+
+#define map__zput(map) __map__zput(&map)
+
 int map__overlap(struct map *l, struct map *r);
 size_t map__fprintf(struct map *map, FILE *fp);
 size_t map__fprintf_dsoname(struct map *map, FILE *fp);
@@ -159,11 +185,11 @@ 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 rb_root *maps, struct map *map);
-void maps__remove(struct rb_root *maps, struct map *map);
-struct map *maps__find(struct rb_root *maps, u64 addr);
-struct map *maps__first(struct rb_root *maps);
-struct map *maps__next(struct map *map);
+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);
+struct map *maps__first(struct maps *maps);
+struct map *map__next(struct map *map);
 void map_groups__init(struct map_groups *mg, struct machine *machine);
 void map_groups__exit(struct map_groups *mg);
 int map_groups__clone(struct map_groups *mg,
@@ -198,7 +224,7 @@ static inline struct map *map_groups__first(struct map_groups *mg,
 
 static inline struct map *map_groups__next(struct map *map)
 {
-	return maps__next(map);
+	return map__next(map);
 }
 
 struct symbol *map_groups__find_symbol(struct map_groups *mg,
@@ -230,6 +256,4 @@ int map_groups__fixup_overlappings(struct map_groups *mg, struct map *map,
 struct map *map_groups__find_by_name(struct map_groups *mg,
 				     enum map_type type, const char *name);
 
-void map_groups__flush(struct map_groups *mg);
-
 #endif /* __PERF_MAP_H */
diff --git a/tools/perf/util/pager.c b/tools/perf/util/pager.c
index 31ee02d4e988..53ef006a951c 100644
--- a/tools/perf/util/pager.c
+++ b/tools/perf/util/pager.c
@@ -50,11 +50,6 @@ void setup_pager(void)
 
 	if (!isatty(1))
 		return;
-	if (!pager) {
-		if (!pager_program)
-			perf_config(perf_default_config, NULL);
-		pager = pager_program;
-	}
 	if (!pager)
 		pager = getenv("PAGER");
 	if (!(pager || access("/usr/bin/pager", X_OK)))
diff --git a/tools/perf/util/parse-branch-options.c b/tools/perf/util/parse-branch-options.c
new file mode 100644
index 000000000000..a3b1e13a05c0
--- /dev/null
+++ b/tools/perf/util/parse-branch-options.c
@@ -0,0 +1,94 @@
+#include "perf.h"
+#include "util/util.h"
+#include "util/debug.h"
+#include "util/parse-options.h"
+#include "util/parse-branch-options.h"
+
+#define BRANCH_OPT(n, m) \
+	{ .name = n, .mode = (m) }
+
+#define BRANCH_END { .name = NULL }
+
+struct branch_mode {
+	const char *name;
+	int mode;
+};
+
+static const struct branch_mode branch_modes[] = {
+	BRANCH_OPT("u", PERF_SAMPLE_BRANCH_USER),
+	BRANCH_OPT("k", PERF_SAMPLE_BRANCH_KERNEL),
+	BRANCH_OPT("hv", PERF_SAMPLE_BRANCH_HV),
+	BRANCH_OPT("any", PERF_SAMPLE_BRANCH_ANY),
+	BRANCH_OPT("any_call", PERF_SAMPLE_BRANCH_ANY_CALL),
+	BRANCH_OPT("any_ret", PERF_SAMPLE_BRANCH_ANY_RETURN),
+	BRANCH_OPT("ind_call", PERF_SAMPLE_BRANCH_IND_CALL),
+	BRANCH_OPT("abort_tx", PERF_SAMPLE_BRANCH_ABORT_TX),
+	BRANCH_OPT("in_tx", PERF_SAMPLE_BRANCH_IN_TX),
+	BRANCH_OPT("no_tx", PERF_SAMPLE_BRANCH_NO_TX),
+	BRANCH_OPT("cond", PERF_SAMPLE_BRANCH_COND),
+	BRANCH_OPT("ind_jmp", PERF_SAMPLE_BRANCH_IND_JUMP),
+	BRANCH_END
+};
+
+int
+parse_branch_stack(const struct option *opt, const char *str, int unset)
+{
+#define ONLY_PLM \
+	(PERF_SAMPLE_BRANCH_USER	|\
+	 PERF_SAMPLE_BRANCH_KERNEL	|\
+	 PERF_SAMPLE_BRANCH_HV)
+
+	uint64_t *mode = (uint64_t *)opt->value;
+	const struct branch_mode *br;
+	char *s, *os = NULL, *p;
+	int ret = -1;
+
+	if (unset)
+		return 0;
+
+	/*
+	 * cannot set it twice, -b + --branch-filter for instance
+	 */
+	if (*mode)
+		return -1;
+
+	/* str may be NULL in case no arg is passed to -b */
+	if (str) {
+		/* because str is read-only */
+		s = os = strdup(str);
+		if (!s)
+			return -1;
+
+		for (;;) {
+			p = strchr(s, ',');
+			if (p)
+				*p = '\0';
+
+			for (br = branch_modes; br->name; br++) {
+				if (!strcasecmp(s, br->name))
+					break;
+			}
+			if (!br->name) {
+				ui__warning("unknown branch filter %s,"
+					    " check man page\n", s);
+				goto error;
+			}
+
+			*mode |= br->mode;
+
+			if (!p)
+				break;
+
+			s = p + 1;
+		}
+	}
+	ret = 0;
+
+	/* default to any branch */
+	if ((*mode & ~ONLY_PLM) == 0) {
+		*mode = PERF_SAMPLE_BRANCH_ANY;
+	}
+error:
+	free(os);
+	return ret;
+}
diff --git a/tools/perf/util/parse-branch-options.h b/tools/perf/util/parse-branch-options.h
new file mode 100644
index 000000000000..b9d9470c2e82
--- /dev/null
+++ b/tools/perf/util/parse-branch-options.h
@@ -0,0 +1,5 @@
+#ifndef _PERF_PARSE_BRANCH_OPTIONS_H
+#define _PERF_PARSE_BRANCH_OPTIONS_H 1
+struct option;
+int parse_branch_stack(const struct option *opt, const char *str, int unset);
+#endif /* _PERF_PARSE_BRANCH_OPTIONS_H */
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index be0655388b38..2a4d1ec02846 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -17,6 +17,7 @@
 #include "parse-events-flex.h"
 #include "pmu.h"
 #include "thread_map.h"
+#include "asm/bug.h"
 
 #define MAX_NAME_LEN 100
 
@@ -538,16 +539,40 @@ int parse_events_add_breakpoint(struct list_head *list, int *idx,
 	return add_event(list, idx, &attr, NULL);
 }
 
+static int check_type_val(struct parse_events_term *term,
+			  struct parse_events_error *err,
+			  int type)
+{
+	if (type == term->type_val)
+		return 0;
+
+	if (err) {
+		err->idx = term->err_val;
+		if (type == PARSE_EVENTS__TERM_TYPE_NUM)
+			err->str = strdup("expected numeric value");
+		else
+			err->str = strdup("expected string value");
+	}
+	return -EINVAL;
+}
+
 static int config_term(struct perf_event_attr *attr,
-		       struct parse_events_term *term)
+		       struct parse_events_term *term,
+		       struct parse_events_error *err)
 {
-#define CHECK_TYPE_VAL(type)					\
-do {								\
-	if (PARSE_EVENTS__TERM_TYPE_ ## type != term->type_val)	\
-		return -EINVAL;					\
+#define CHECK_TYPE_VAL(type)						   \
+do {									   \
+	if (check_type_val(term, err, PARSE_EVENTS__TERM_TYPE_ ## type)) \
+		return -EINVAL;						   \
 } while (0)
 
 	switch (term->type_term) {
+	case PARSE_EVENTS__TERM_TYPE_USER:
+		/*
+		 * Always succeed for sysfs terms, as we dont know
+		 * at this point what type they need to have.
+		 */
+		return 0;
 	case PARSE_EVENTS__TERM_TYPE_CONFIG:
 		CHECK_TYPE_VAL(NUM);
 		attr->config = term->val.num;
@@ -582,18 +607,20 @@ do {								\
 }
 
 static int config_attr(struct perf_event_attr *attr,
-		       struct list_head *head, int fail)
+		       struct list_head *head,
+		       struct parse_events_error *err)
 {
 	struct parse_events_term *term;
 
 	list_for_each_entry(term, head, list)
-		if (config_term(attr, term) && fail)
+		if (config_term(attr, term, err))
 			return -EINVAL;
 
 	return 0;
 }
 
-int parse_events_add_numeric(struct list_head *list, int *idx,
+int parse_events_add_numeric(struct parse_events_evlist *data,
+			     struct list_head *list,
 			     u32 type, u64 config,
 			     struct list_head *head_config)
 {
@@ -604,10 +631,10 @@ int parse_events_add_numeric(struct list_head *list, int *idx,
 	attr.config = config;
 
 	if (head_config &&
-	    config_attr(&attr, head_config, 1))
+	    config_attr(&attr, head_config, data->error))
 		return -EINVAL;
 
-	return add_event(list, idx, &attr, NULL);
+	return add_event(list, &data->idx, &attr, NULL);
 }
 
 static int parse_events__is_name_term(struct parse_events_term *term)
@@ -626,8 +653,9 @@ static char *pmu_event_name(struct list_head *head_terms)
 	return NULL;
 }
 
-int parse_events_add_pmu(struct list_head *list, int *idx,
-			 char *name, struct list_head *head_config)
+int parse_events_add_pmu(struct parse_events_evlist *data,
+			 struct list_head *list, char *name,
+			 struct list_head *head_config)
 {
 	struct perf_event_attr attr;
 	struct perf_pmu_info info;
@@ -647,7 +675,7 @@ int parse_events_add_pmu(struct list_head *list, int *idx,
 
 	if (!head_config) {
 		attr.type = pmu->type;
-		evsel = __add_event(list, idx, &attr, NULL, pmu->cpus);
+		evsel = __add_event(list, &data->idx, &attr, NULL, pmu->cpus);
 		return evsel ? 0 : -ENOMEM;
 	}
 
@@ -658,13 +686,14 @@ int parse_events_add_pmu(struct list_head *list, int *idx,
 	 * Configure hardcoded terms first, no need to check
 	 * return value when called with fail == 0 ;)
 	 */
-	config_attr(&attr, head_config, 0);
+	if (config_attr(&attr, head_config, data->error))
+		return -EINVAL;
 
-	if (perf_pmu__config(pmu, &attr, head_config))
+	if (perf_pmu__config(pmu, &attr, head_config, data->error))
 		return -EINVAL;
 
-	evsel = __add_event(list, idx, &attr, pmu_event_name(head_config),
-			    pmu->cpus);
+	evsel = __add_event(list, &data->idx, &attr,
+			    pmu_event_name(head_config), pmu->cpus);
 	if (evsel) {
 		evsel->unit = info.unit;
 		evsel->scale = info.scale;
@@ -1019,11 +1048,13 @@ int parse_events_terms(struct list_head *terms, const char *str)
 	return ret;
 }
 
-int parse_events(struct perf_evlist *evlist, const char *str)
+int parse_events(struct perf_evlist *evlist, const char *str,
+		 struct parse_events_error *err)
 {
 	struct parse_events_evlist data = {
-		.list = LIST_HEAD_INIT(data.list),
-		.idx  = evlist->nr_entries,
+		.list  = LIST_HEAD_INIT(data.list),
+		.idx   = evlist->nr_entries,
+		.error = err,
 	};
 	int ret;
 
@@ -1044,16 +1075,87 @@ int parse_events(struct perf_evlist *evlist, const char *str)
 	return ret;
 }
 
+#define MAX_WIDTH 1000
+static int get_term_width(void)
+{
+	struct winsize ws;
+
+	get_term_dimensions(&ws);
+	return ws.ws_col > MAX_WIDTH ? MAX_WIDTH : ws.ws_col;
+}
+
+static void parse_events_print_error(struct parse_events_error *err,
+				     const char *event)
+{
+	const char *str = "invalid or unsupported event: ";
+	char _buf[MAX_WIDTH];
+	char *buf = (char *) event;
+	int idx = 0;
+
+	if (err->str) {
+		/* -2 for extra '' in the final fprintf */
+		int width       = get_term_width() - 2;
+		int len_event   = strlen(event);
+		int len_str, max_len, cut = 0;
+
+		/*
+		 * Maximum error index indent, we will cut
+		 * the event string if it's bigger.
+		 */
+		int max_err_idx = 10;
+
+		/*
+		 * Let's be specific with the message when
+		 * we have the precise error.
+		 */
+		str     = "event syntax error: ";
+		len_str = strlen(str);
+		max_len = width - len_str;
+
+		buf = _buf;
+
+		/* We're cutting from the beggining. */
+		if (err->idx > max_err_idx)
+			cut = err->idx - max_err_idx;
+
+		strncpy(buf, event + cut, max_len);
+
+		/* Mark cut parts with '..' on both sides. */
+		if (cut)
+			buf[0] = buf[1] = '.';
+
+		if ((len_event - cut) > max_len) {
+			buf[max_len - 1] = buf[max_len - 2] = '.';
+			buf[max_len] = 0;
+		}
+
+		idx = len_str + err->idx - cut;
+	}
+
+	fprintf(stderr, "%s'%s'\n", str, buf);
+	if (idx) {
+		fprintf(stderr, "%*s\\___ %s\n", idx + 1, "", err->str);
+		if (err->help)
+			fprintf(stderr, "\n%s\n", err->help);
+		free(err->str);
+		free(err->help);
+	}
+
+	fprintf(stderr, "Run 'perf list' for a list of valid events\n");
+}
+
+#undef MAX_WIDTH
+
 int parse_events_option(const struct option *opt, const char *str,
 			int unset __maybe_unused)
 {
 	struct perf_evlist *evlist = *(struct perf_evlist **)opt->value;
-	int ret = parse_events(evlist, str);
+	struct parse_events_error err = { .idx = 0, };
+	int ret = parse_events(evlist, str, &err);
+
+	if (ret)
+		parse_events_print_error(&err, str);
 
-	if (ret) {
-		fprintf(stderr, "invalid or unsupported event: '%s'\n", str);
-		fprintf(stderr, "Run 'perf list' for a list of valid events\n");
-	}
 	return ret;
 }
 
@@ -1460,7 +1562,7 @@ int parse_events__is_hardcoded_term(struct parse_events_term *term)
 
 static int new_term(struct parse_events_term **_term, int type_val,
 		    int type_term, char *config,
-		    char *str, u64 num)
+		    char *str, u64 num, int err_term, int err_val)
 {
 	struct parse_events_term *term;
 
@@ -1472,6 +1574,8 @@ static int new_term(struct parse_events_term **_term, int type_val,
 	term->type_val  = type_val;
 	term->type_term = type_term;
 	term->config = config;
+	term->err_term = err_term;
+	term->err_val  = err_val;
 
 	switch (type_val) {
 	case PARSE_EVENTS__TERM_TYPE_NUM:
@@ -1490,17 +1594,29 @@ static int new_term(struct parse_events_term **_term, int type_val,
 }
 
 int parse_events_term__num(struct parse_events_term **term,
-			   int type_term, char *config, u64 num)
+			   int type_term, char *config, u64 num,
+			   void *loc_term_, void *loc_val_)
 {
+	YYLTYPE *loc_term = loc_term_;
+	YYLTYPE *loc_val = loc_val_;
+
 	return new_term(term, PARSE_EVENTS__TERM_TYPE_NUM, type_term,
-			config, NULL, num);
+			config, NULL, num,
+			loc_term ? loc_term->first_column : 0,
+			loc_val ? loc_val->first_column : 0);
 }
 
 int parse_events_term__str(struct parse_events_term **term,
-			   int type_term, char *config, char *str)
+			   int type_term, char *config, char *str,
+			   void *loc_term_, void *loc_val_)
 {
+	YYLTYPE *loc_term = loc_term_;
+	YYLTYPE *loc_val = loc_val_;
+
 	return new_term(term, PARSE_EVENTS__TERM_TYPE_STR, type_term,
-			config, str, 0);
+			config, str, 0,
+			loc_term ? loc_term->first_column : 0,
+			loc_val ? loc_val->first_column : 0);
 }
 
 int parse_events_term__sym_hw(struct parse_events_term **term,
@@ -1514,18 +1630,20 @@ int parse_events_term__sym_hw(struct parse_events_term **term,
 	if (config)
 		return new_term(term, PARSE_EVENTS__TERM_TYPE_STR,
 				PARSE_EVENTS__TERM_TYPE_USER, config,
-				(char *) sym->symbol, 0);
+				(char *) sym->symbol, 0, 0, 0);
 	else
 		return new_term(term, PARSE_EVENTS__TERM_TYPE_STR,
 				PARSE_EVENTS__TERM_TYPE_USER,
-				(char *) "event", (char *) sym->symbol, 0);
+				(char *) "event", (char *) sym->symbol,
+				0, 0, 0);
 }
 
 int parse_events_term__clone(struct parse_events_term **new,
 			     struct parse_events_term *term)
 {
 	return new_term(new, term->type_val, term->type_term, term->config,
-			term->val.str, term->val.num);
+			term->val.str, term->val.num,
+			term->err_term, term->err_val);
 }
 
 void parse_events__free_terms(struct list_head *terms)
@@ -1535,3 +1653,15 @@ void parse_events__free_terms(struct list_head *terms)
 	list_for_each_entry_safe(term, h, terms, list)
 		free(term);
 }
+
+void parse_events_evlist_error(struct parse_events_evlist *data,
+			       int idx, const char *str)
+{
+	struct parse_events_error *err = data->error;
+
+	if (!err)
+		return;
+	err->idx = idx;
+	err->str = strdup(str);
+	WARN_ONCE(!err->str, "WARNING: failed to allocate error string");
+}
diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h
index 52a2dda4f954..131f29b2f132 100644
--- a/tools/perf/util/parse-events.h
+++ b/tools/perf/util/parse-events.h
@@ -12,6 +12,7 @@
 struct list_head;
 struct perf_evsel;
 struct perf_evlist;
+struct parse_events_error;
 
 struct option;
 
@@ -29,7 +30,8 @@ const char *event_type(int type);
 
 extern int parse_events_option(const struct option *opt, const char *str,
 			       int unset);
-extern int parse_events(struct perf_evlist *evlist, const char *str);
+extern int parse_events(struct perf_evlist *evlist, const char *str,
+			struct parse_events_error *error);
 extern int parse_events_terms(struct list_head *terms, const char *str);
 extern int parse_filter(const struct option *opt, const char *str, int unset);
 
@@ -72,12 +74,23 @@ struct parse_events_term {
 	int type_term;
 	struct list_head list;
 	bool used;
+
+	/* error string indexes for within parsed string */
+	int err_term;
+	int err_val;
+};
+
+struct parse_events_error {
+	int   idx;	/* index in the parsed string */
+	char *str;      /* string to display at the index */
+	char *help;	/* optional help string */
 };
 
 struct parse_events_evlist {
-	struct list_head list;
-	int idx;
-	int nr_groups;
+	struct list_head	   list;
+	int			   idx;
+	int			   nr_groups;
+	struct parse_events_error *error;
 };
 
 struct parse_events_terms {
@@ -85,10 +98,12 @@ struct parse_events_terms {
 };
 
 int parse_events__is_hardcoded_term(struct parse_events_term *term);
-int parse_events_term__num(struct parse_events_term **_term,
-			   int type_term, char *config, u64 num);
-int parse_events_term__str(struct parse_events_term **_term,
-			   int type_term, char *config, char *str);
+int parse_events_term__num(struct parse_events_term **term,
+			   int type_term, char *config, u64 num,
+			   void *loc_term, void *loc_val);
+int parse_events_term__str(struct parse_events_term **term,
+			   int type_term, char *config, char *str,
+			   void *loc_term, void *loc_val);
 int parse_events_term__sym_hw(struct parse_events_term **term,
 			      char *config, unsigned idx);
 int parse_events_term__clone(struct parse_events_term **new,
@@ -99,21 +114,24 @@ int parse_events__modifier_group(struct list_head *list, char *event_mod);
 int parse_events_name(struct list_head *list, char *name);
 int parse_events_add_tracepoint(struct list_head *list, int *idx,
 				char *sys, char *event);
-int parse_events_add_numeric(struct list_head *list, int *idx,
+int parse_events_add_numeric(struct parse_events_evlist *data,
+			     struct list_head *list,
 			     u32 type, u64 config,
 			     struct list_head *head_config);
 int parse_events_add_cache(struct list_head *list, int *idx,
 			   char *type, char *op_result1, char *op_result2);
 int parse_events_add_breakpoint(struct list_head *list, int *idx,
 				void *ptr, char *type, u64 len);
-int parse_events_add_pmu(struct list_head *list, int *idx,
-			 char *pmu , struct list_head *head_config);
+int parse_events_add_pmu(struct parse_events_evlist *data,
+			 struct list_head *list, char *name,
+			 struct list_head *head_config);
 enum perf_pmu_event_symbol_type
 perf_pmu__parse_check(const char *name);
 void parse_events__set_leader(char *name, struct list_head *list);
 void parse_events_update_lists(struct list_head *list_event,
 			       struct list_head *list_all);
-void parse_events_error(void *data, void *scanner, char const *msg);
+void parse_events_evlist_error(struct parse_events_evlist *data,
+			       int idx, const char *str);
 
 void print_events(const char *event_glob, bool name_only);
 
diff --git a/tools/perf/util/parse-events.l b/tools/perf/util/parse-events.l
index 8895cf3132ab..09e738fe9ea2 100644
--- a/tools/perf/util/parse-events.l
+++ b/tools/perf/util/parse-events.l
@@ -3,6 +3,8 @@
 %option bison-bridge
 %option prefix="parse_events_"
 %option stack
+%option bison-locations
+%option yylineno
 
 %{
 #include <errno.h>
@@ -51,6 +53,18 @@ static int str(yyscan_t scanner, int token)
 	return token;
 }
 
+#define REWIND(__alloc)				\
+do {								\
+	YYSTYPE *__yylval = parse_events_get_lval(yyscanner);	\
+	char *text = parse_events_get_text(yyscanner);		\
+								\
+	if (__alloc)						\
+		__yylval->str = strdup(text);			\
+								\
+	yycolumn -= strlen(text);				\
+	yyless(0);						\
+} while (0)
+
 static int pmu_str_check(yyscan_t scanner)
 {
 	YYSTYPE *yylval = parse_events_get_lval(scanner);
@@ -85,6 +99,13 @@ static int term(yyscan_t scanner, int type)
 	return PE_TERM;
 }
 
+#define YY_USER_ACTION					\
+do {							\
+	yylloc->last_column  = yylloc->first_column;	\
+	yylloc->first_column = yycolumn;		\
+	yycolumn += yyleng;				\
+} while (0);
+
 %}
 
 %x mem
@@ -119,6 +140,12 @@ modifier_bp	[rwx]{1,3}
 
 		if (start_token) {
 			parse_events_set_extra(NULL, yyscanner);
+			/*
+			 * The flex parser does not init locations variable
+			 * via the scan_string interface, so we need do the
+			 * init in here.
+			 */
+			yycolumn = 0;
 			return start_token;
 		}
          }
@@ -127,24 +154,30 @@ modifier_bp	[rwx]{1,3}
 <event>{
 
 {group}		{
-			BEGIN(INITIAL); yyless(0);
+			BEGIN(INITIAL);
+			REWIND(0);
 		}
 
 {event_pmu}	|
 {event}		{
-			str(yyscanner, PE_EVENT_NAME);
-			BEGIN(INITIAL); yyless(0);
+			BEGIN(INITIAL);
+			REWIND(1);
 			return PE_EVENT_NAME;
 		}
 
 .		|
 <<EOF>>		{
-			BEGIN(INITIAL); yyless(0);
+			BEGIN(INITIAL);
+			REWIND(0);
 		}
 
 }
 
 <config>{
+	/*
+	 * Please update formats_error_string any time
+	 * new static term is added.
+	 */
 config			{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_CONFIG); }
 config1			{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_CONFIG1); }
 config2			{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_CONFIG2); }
diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y
index 72def077dbbf..591905a02b92 100644
--- a/tools/perf/util/parse-events.y
+++ b/tools/perf/util/parse-events.y
@@ -2,6 +2,7 @@
 %parse-param {void *_data}
 %parse-param {void *scanner}
 %lex-param {void* scanner}
+%locations
 
 %{
 
@@ -14,8 +15,6 @@
 #include "parse-events.h"
 #include "parse-events-bison.h"
 
-extern int parse_events_lex (YYSTYPE* lvalp, void* scanner);
-
 #define ABORT_ON(val) \
 do { \
 	if (val) \
@@ -208,7 +207,7 @@ PE_NAME '/' event_config '/'
 	struct list_head *list;
 
 	ALLOC_LIST(list);
-	ABORT_ON(parse_events_add_pmu(list, &data->idx, $1, $3));
+	ABORT_ON(parse_events_add_pmu(data, list, $1, $3));
 	parse_events__free_terms($3);
 	$$ = list;
 }
@@ -219,7 +218,7 @@ PE_NAME '/' '/'
 	struct list_head *list;
 
 	ALLOC_LIST(list);
-	ABORT_ON(parse_events_add_pmu(list, &data->idx, $1, NULL));
+	ABORT_ON(parse_events_add_pmu(data, list, $1, NULL));
 	$$ = list;
 }
 |
@@ -232,11 +231,11 @@ PE_KERNEL_PMU_EVENT sep_dc
 
 	ALLOC_LIST(head);
 	ABORT_ON(parse_events_term__num(&term, PARSE_EVENTS__TERM_TYPE_USER,
-					$1, 1));
+					$1, 1, &@1, NULL));
 	list_add_tail(&term->list, head);
 
 	ALLOC_LIST(list);
-	ABORT_ON(parse_events_add_pmu(list, &data->idx, "cpu", head));
+	ABORT_ON(parse_events_add_pmu(data, list, "cpu", head));
 	parse_events__free_terms(head);
 	$$ = list;
 }
@@ -252,7 +251,7 @@ PE_PMU_EVENT_PRE '-' PE_PMU_EVENT_SUF sep_dc
 
 	ALLOC_LIST(head);
 	ABORT_ON(parse_events_term__num(&term, PARSE_EVENTS__TERM_TYPE_USER,
-					&pmu_name, 1));
+					&pmu_name, 1, &@1, NULL));
 	list_add_tail(&term->list, head);
 
 	ALLOC_LIST(list);
@@ -275,8 +274,7 @@ value_sym '/' event_config '/'
 	int config = $1 & 255;
 
 	ALLOC_LIST(list);
-	ABORT_ON(parse_events_add_numeric(list, &data->idx,
-					  type, config, $3));
+	ABORT_ON(parse_events_add_numeric(data, list, type, config, $3));
 	parse_events__free_terms($3);
 	$$ = list;
 }
@@ -289,8 +287,7 @@ value_sym sep_slash_dc
 	int config = $1 & 255;
 
 	ALLOC_LIST(list);
-	ABORT_ON(parse_events_add_numeric(list, &data->idx,
-					  type, config, NULL));
+	ABORT_ON(parse_events_add_numeric(data, list, type, config, NULL));
 	$$ = list;
 }
 
@@ -389,7 +386,15 @@ PE_NAME ':' PE_NAME
 	struct list_head *list;
 
 	ALLOC_LIST(list);
-	ABORT_ON(parse_events_add_tracepoint(list, &data->idx, $1, $3));
+	if (parse_events_add_tracepoint(list, &data->idx, $1, $3)) {
+		struct parse_events_error *error = data->error;
+
+		if (error) {
+			error->idx = @1.first_column;
+			error->str = strdup("unknown tracepoint");
+		}
+		return -1;
+	}
 	$$ = list;
 }
 
@@ -400,7 +405,7 @@ PE_VALUE ':' PE_VALUE
 	struct list_head *list;
 
 	ALLOC_LIST(list);
-	ABORT_ON(parse_events_add_numeric(list, &data->idx, (u32)$1, $3, NULL));
+	ABORT_ON(parse_events_add_numeric(data, list, (u32)$1, $3, NULL));
 	$$ = list;
 }
 
@@ -411,8 +416,7 @@ PE_RAW
 	struct list_head *list;
 
 	ALLOC_LIST(list);
-	ABORT_ON(parse_events_add_numeric(list, &data->idx,
-					  PERF_TYPE_RAW, $1, NULL));
+	ABORT_ON(parse_events_add_numeric(data, list, PERF_TYPE_RAW, $1, NULL));
 	$$ = list;
 }
 
@@ -450,7 +454,7 @@ PE_NAME '=' PE_NAME
 	struct parse_events_term *term;
 
 	ABORT_ON(parse_events_term__str(&term, PARSE_EVENTS__TERM_TYPE_USER,
-					$1, $3));
+					$1, $3, &@1, &@3));
 	$$ = term;
 }
 |
@@ -459,7 +463,7 @@ PE_NAME '=' PE_VALUE
 	struct parse_events_term *term;
 
 	ABORT_ON(parse_events_term__num(&term, PARSE_EVENTS__TERM_TYPE_USER,
-					$1, $3));
+					$1, $3, &@1, &@3));
 	$$ = term;
 }
 |
@@ -477,7 +481,7 @@ PE_NAME
 	struct parse_events_term *term;
 
 	ABORT_ON(parse_events_term__num(&term, PARSE_EVENTS__TERM_TYPE_USER,
-					$1, 1));
+					$1, 1, &@1, NULL));
 	$$ = term;
 }
 |
@@ -494,7 +498,7 @@ PE_TERM '=' PE_NAME
 {
 	struct parse_events_term *term;
 
-	ABORT_ON(parse_events_term__str(&term, (int)$1, NULL, $3));
+	ABORT_ON(parse_events_term__str(&term, (int)$1, NULL, $3, &@1, &@3));
 	$$ = term;
 }
 |
@@ -502,7 +506,7 @@ PE_TERM '=' PE_VALUE
 {
 	struct parse_events_term *term;
 
-	ABORT_ON(parse_events_term__num(&term, (int)$1, NULL, $3));
+	ABORT_ON(parse_events_term__num(&term, (int)$1, NULL, $3, &@1, &@3));
 	$$ = term;
 }
 |
@@ -510,7 +514,7 @@ PE_TERM
 {
 	struct parse_events_term *term;
 
-	ABORT_ON(parse_events_term__num(&term, (int)$1, NULL, 1));
+	ABORT_ON(parse_events_term__num(&term, (int)$1, NULL, 1, &@1, NULL));
 	$$ = term;
 }
 
@@ -520,7 +524,9 @@ sep_slash_dc: '/' | ':' |
 
 %%
 
-void parse_events_error(void *data __maybe_unused, void *scanner __maybe_unused,
+void parse_events_error(YYLTYPE *loc, void *data,
+			void *scanner __maybe_unused,
 			char const *msg __maybe_unused)
 {
+	parse_events_evlist_error(data, loc->last_column, "parser error");
 }
diff --git a/tools/perf/util/parse-options.h b/tools/perf/util/parse-options.h
index 59561fd86278..367d8b816cc7 100644
--- a/tools/perf/util/parse-options.h
+++ b/tools/perf/util/parse-options.h
@@ -123,6 +123,10 @@ struct option {
 #define OPT_LONG(s, l, v, h)        { .type = OPTION_LONG, .short_name = (s), .long_name = (l), .value = check_vtype(v, long *), .help = (h) }
 #define OPT_U64(s, l, v, h)         { .type = OPTION_U64, .short_name = (s), .long_name = (l), .value = check_vtype(v, u64 *), .help = (h) }
 #define OPT_STRING(s, l, v, a, h)   { .type = OPTION_STRING,  .short_name = (s), .long_name = (l), .value = check_vtype(v, const char **), (a), .help = (h) }
+#define OPT_STRING_OPTARG(s, l, v, a, h, d) \
+	{ .type = OPTION_STRING,  .short_name = (s), .long_name = (l), \
+	  .value = check_vtype(v, const char **), (a), .help = (h), \
+	  .flags = PARSE_OPT_OPTARG, .defval = (intptr_t)(d) }
 #define OPT_STRING_NOEMPTY(s, l, v, a, h)   { .type = OPTION_STRING,  .short_name = (s), .long_name = (l), .value = check_vtype(v, const char **), (a), .help = (h), .flags = PARSE_OPT_NOEMPTY}
 #define OPT_DATE(s, l, v, h) \
 	{ .type = OPTION_CALLBACK, .short_name = (s), .long_name = (l), .value = (v), .argh = "time", .help = (h), .callback = parse_opt_approxidate_cb }
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index 48411674da0f..0fcc624eb767 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -112,7 +112,11 @@ static int perf_pmu__parse_scale(struct perf_pmu_alias *alias, char *dir, char *
 	if (sret < 0)
 		goto error;
 
-	scale[sret] = '\0';
+	if (scale[sret - 1] == '\n')
+		scale[sret - 1] = '\0';
+	else
+		scale[sret] = '\0';
+
 	/*
 	 * save current locale
 	 */
@@ -154,7 +158,10 @@ static int perf_pmu__parse_unit(struct perf_pmu_alias *alias, char *dir, char *n
 
 	close(fd);
 
-	alias->unit[sret] = '\0';
+	if (alias->unit[sret - 1] == '\n')
+		alias->unit[sret - 1] = '\0';
+	else
+		alias->unit[sret] = '\0';
 
 	return 0;
 error:
@@ -442,6 +449,10 @@ static struct perf_pmu *pmu_lookup(const char *name)
 	LIST_HEAD(aliases);
 	__u32 type;
 
+	/* No support for intel_bts or intel_pt so disallow them */
+	if (!strcmp(name, "intel_bts") || !strcmp(name, "intel_pt"))
+		return NULL;
+
 	/*
 	 * The pmu data we store & need consists of the pmu
 	 * type value and format definitions. Load both right
@@ -579,6 +590,38 @@ static int pmu_resolve_param_term(struct parse_events_term *term,
 	return -1;
 }
 
+static char *formats_error_string(struct list_head *formats)
+{
+	struct perf_pmu_format *format;
+	char *err, *str;
+	static const char *static_terms = "config,config1,config2,name,period,branch_type\n";
+	unsigned i = 0;
+
+	if (!asprintf(&str, "valid terms:"))
+		return NULL;
+
+	/* sysfs exported terms */
+	list_for_each_entry(format, formats, list) {
+		char c = i++ ? ',' : ' ';
+
+		err = str;
+		if (!asprintf(&str, "%s%c%s", err, c, format->name))
+			goto fail;
+		free(err);
+	}
+
+	/* static terms */
+	err = str;
+	if (!asprintf(&str, "%s,%s", err, static_terms))
+		goto fail;
+
+	free(err);
+	return str;
+fail:
+	free(err);
+	return NULL;
+}
+
 /*
  * Setup one of config[12] attr members based on the
  * user input data - term parameter.
@@ -587,7 +630,7 @@ static int pmu_config_term(struct list_head *formats,
 			   struct perf_event_attr *attr,
 			   struct parse_events_term *term,
 			   struct list_head *head_terms,
-			   bool zero)
+			   bool zero, struct parse_events_error *err)
 {
 	struct perf_pmu_format *format;
 	__u64 *vp;
@@ -611,6 +654,11 @@ static int pmu_config_term(struct list_head *formats,
 	if (!format) {
 		if (verbose)
 			printf("Invalid event/parameter '%s'\n", term->config);
+		if (err) {
+			err->idx  = term->err_term;
+			err->str  = strdup("unknown term");
+			err->help = formats_error_string(formats);
+		}
 		return -EINVAL;
 	}
 
@@ -636,9 +684,14 @@ static int pmu_config_term(struct list_head *formats,
 		val = term->val.num;
 	else if (term->type_val == PARSE_EVENTS__TERM_TYPE_STR) {
 		if (strcmp(term->val.str, "?")) {
-			if (verbose)
+			if (verbose) {
 				pr_info("Invalid sysfs entry %s=%s\n",
 						term->config, term->val.str);
+			}
+			if (err) {
+				err->idx = term->err_val;
+				err->str = strdup("expected numeric value");
+			}
 			return -EINVAL;
 		}
 
@@ -654,12 +707,13 @@ static int pmu_config_term(struct list_head *formats,
 int perf_pmu__config_terms(struct list_head *formats,
 			   struct perf_event_attr *attr,
 			   struct list_head *head_terms,
-			   bool zero)
+			   bool zero, struct parse_events_error *err)
 {
 	struct parse_events_term *term;
 
 	list_for_each_entry(term, head_terms, list) {
-		if (pmu_config_term(formats, attr, term, head_terms, zero))
+		if (pmu_config_term(formats, attr, term, head_terms,
+				    zero, err))
 			return -EINVAL;
 	}
 
@@ -672,12 +726,14 @@ int perf_pmu__config_terms(struct list_head *formats,
  * 2) pmu format definitions - specified by pmu parameter
  */
 int perf_pmu__config(struct perf_pmu *pmu, struct perf_event_attr *attr,
-		     struct list_head *head_terms)
+		     struct list_head *head_terms,
+		     struct parse_events_error *err)
 {
 	bool zero = !!pmu->default_config;
 
 	attr->type = pmu->type;
-	return perf_pmu__config_terms(&pmu->format, attr, head_terms, zero);
+	return perf_pmu__config_terms(&pmu->format, attr, head_terms,
+				      zero, err);
 }
 
 static struct perf_pmu_alias *pmu_find_alias(struct perf_pmu *pmu,
diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h
index 6b1249fbdb5f..7b9c8cf8ae3e 100644
--- a/tools/perf/util/pmu.h
+++ b/tools/perf/util/pmu.h
@@ -4,6 +4,7 @@
 #include <linux/bitmap.h>
 #include <linux/perf_event.h>
 #include <stdbool.h>
+#include "parse-events.h"
 
 enum {
 	PERF_PMU_FORMAT_VALUE_CONFIG,
@@ -47,11 +48,12 @@ struct perf_pmu_alias {
 
 struct perf_pmu *perf_pmu__find(const char *name);
 int perf_pmu__config(struct perf_pmu *pmu, struct perf_event_attr *attr,
-		     struct list_head *head_terms);
+		     struct list_head *head_terms,
+		     struct parse_events_error *error);
 int perf_pmu__config_terms(struct list_head *formats,
 			   struct perf_event_attr *attr,
 			   struct list_head *head_terms,
-			   bool zero);
+			   bool zero, struct parse_events_error *error);
 int perf_pmu__check_alias(struct perf_pmu *pmu, struct list_head *head_terms,
 			  struct perf_pmu_info *info);
 struct list_head *perf_pmu__alias(struct perf_pmu *pmu,
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index d05b77cf35f7..076527b639bd 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -51,6 +51,7 @@
 #define PERFPROBE_GROUP "probe"
 
 bool probe_event_dry_run;	/* Dry run flag */
+struct probe_conf probe_conf;
 
 #define semantic_error(msg ...) pr_err("Semantic error :" msg)
 
@@ -161,18 +162,18 @@ static u64 kernel_get_symbol_address_by_name(const char *name, bool reloc)
 
 static struct map *kernel_get_module_map(const char *module)
 {
-	struct rb_node *nd;
 	struct map_groups *grp = &host_machine->kmaps;
+	struct maps *maps = &grp->maps[MAP__FUNCTION];
+	struct map *pos;
 
 	/* A file path -- this is an offline module */
 	if (module && strchr(module, '/'))
-		return machine__new_module(host_machine, 0, module);
+		return machine__findnew_module_map(host_machine, 0, module);
 
 	if (!module)
 		module = "kernel";
 
-	for (nd = rb_first(&grp->maps[MAP__FUNCTION]); nd; nd = rb_next(nd)) {
-		struct map *pos = rb_entry(nd, struct map, rb_node);
+	for (pos = maps__first(maps); pos; pos = map__next(pos)) {
 		if (strncmp(pos->dso->short_name + 1, module,
 			    pos->dso->short_name_len - 2) == 0) {
 			return pos;
@@ -194,52 +195,11 @@ static void put_target_map(struct map *map, bool user)
 {
 	if (map && user) {
 		/* Only the user map needs to be released */
-		dso__delete(map->dso);
-		map__delete(map);
+		map__put(map);
 	}
 }
 
 
-static struct dso *kernel_get_module_dso(const char *module)
-{
-	struct dso *dso;
-	struct map *map;
-	const char *vmlinux_name;
-
-	if (module) {
-		list_for_each_entry(dso, &host_machine->kernel_dsos.head,
-				    node) {
-			if (strncmp(dso->short_name + 1, module,
-				    dso->short_name_len - 2) == 0)
-				goto found;
-		}
-		pr_debug("Failed to find module %s.\n", module);
-		return NULL;
-	}
-
-	map = host_machine->vmlinux_maps[MAP__FUNCTION];
-	dso = map->dso;
-
-	vmlinux_name = symbol_conf.vmlinux_name;
-	if (vmlinux_name) {
-		if (dso__load_vmlinux(dso, map, vmlinux_name, false, NULL) <= 0)
-			return NULL;
-	} else {
-		if (dso__load_vmlinux_path(dso, map, NULL) <= 0) {
-			pr_debug("Failed to load kernel map.\n");
-			return NULL;
-		}
-	}
-found:
-	return dso;
-}
-
-const char *kernel_get_module_path(const char *module)
-{
-	struct dso *dso = kernel_get_module_dso(module);
-	return (dso) ? dso->long_name : NULL;
-}
-
 static int convert_exec_to_group(const char *exec, char **result)
 {
 	char *ptr1, *ptr2, *exec_copy;
@@ -286,7 +246,55 @@ static void clear_probe_trace_events(struct probe_trace_event *tevs, int ntevs)
 		clear_probe_trace_event(tevs + i);
 }
 
+static bool kprobe_blacklist__listed(unsigned long address);
+static bool kprobe_warn_out_range(const char *symbol, unsigned long address)
+{
+	/* Get the address of _etext for checking non-probable text symbol */
+	if (kernel_get_symbol_address_by_name("_etext", false) < address)
+		pr_warning("%s is out of .text, skip it.\n", symbol);
+	else if (kprobe_blacklist__listed(address))
+		pr_warning("%s is blacklisted function, skip it.\n", symbol);
+	else
+		return false;
+
+	return true;
+}
+
 #ifdef HAVE_DWARF_SUPPORT
+
+static int kernel_get_module_dso(const char *module, struct dso **pdso)
+{
+	struct dso *dso;
+	struct map *map;
+	const char *vmlinux_name;
+	int ret = 0;
+
+	if (module) {
+		list_for_each_entry(dso, &host_machine->dsos.head, node) {
+			if (!dso->kernel)
+				continue;
+			if (strncmp(dso->short_name + 1, module,
+				    dso->short_name_len - 2) == 0)
+				goto found;
+		}
+		pr_debug("Failed to find module %s.\n", module);
+		return -ENOENT;
+	}
+
+	map = host_machine->vmlinux_maps[MAP__FUNCTION];
+	dso = map->dso;
+
+	vmlinux_name = symbol_conf.vmlinux_name;
+	dso->load_errno = 0;
+	if (vmlinux_name)
+		ret = dso__load_vmlinux(dso, map, vmlinux_name, false, NULL);
+	else
+		ret = dso__load_vmlinux_path(dso, map, NULL);
+found:
+	*pdso = dso;
+	return ret;
+}
+
 /*
  * Some binaries like glibc have special symbols which are on the symbol
  * table, but not in the debuginfo. If we can find the address of the
@@ -344,15 +352,14 @@ out:
 
 static int get_alternative_probe_event(struct debuginfo *dinfo,
 				       struct perf_probe_event *pev,
-				       struct perf_probe_point *tmp,
-				       const char *target)
+				       struct perf_probe_point *tmp)
 {
 	int ret;
 
 	memcpy(tmp, &pev->point, sizeof(*tmp));
 	memset(&pev->point, 0, sizeof(pev->point));
 	ret = find_alternative_probe_point(dinfo, tmp, &pev->point,
-					   target, pev->uprobes);
+					   pev->target, pev->uprobes);
 	if (ret < 0)
 		memcpy(&pev->point, tmp, sizeof(*tmp));
 
@@ -390,16 +397,25 @@ static int get_alternative_line_range(struct debuginfo *dinfo,
 static struct debuginfo *open_debuginfo(const char *module, bool silent)
 {
 	const char *path = module;
-	struct debuginfo *ret;
+	char reason[STRERR_BUFSIZE];
+	struct debuginfo *ret = NULL;
+	struct dso *dso = NULL;
+	int err;
 
 	if (!module || !strchr(module, '/')) {
-		path = kernel_get_module_path(module);
-		if (!path) {
+		err = kernel_get_module_dso(module, &dso);
+		if (err < 0) {
+			if (!dso || dso->load_errno == 0) {
+				if (!strerror_r(-err, reason, STRERR_BUFSIZE))
+					strcpy(reason, "(unknown)");
+			} else
+				dso__strerror_load(dso, reason, STRERR_BUFSIZE);
 			if (!silent)
-				pr_err("Failed to find path of %s module.\n",
-				       module ?: "kernel");
+				pr_err("Failed to find the path for %s: %s\n",
+					module ?: "kernel", reason);
 			return NULL;
 		}
+		path = dso->long_name;
 	}
 	ret = debuginfo__new(path);
 	if (!ret && !silent) {
@@ -413,6 +429,41 @@ static struct debuginfo *open_debuginfo(const char *module, bool silent)
 	return ret;
 }
 
+/* For caching the last debuginfo */
+static struct debuginfo *debuginfo_cache;
+static char *debuginfo_cache_path;
+
+static struct debuginfo *debuginfo_cache__open(const char *module, bool silent)
+{
+	if ((debuginfo_cache_path && !strcmp(debuginfo_cache_path, module)) ||
+	    (!debuginfo_cache_path && !module && debuginfo_cache))
+		goto out;
+
+	/* Copy module path */
+	free(debuginfo_cache_path);
+	if (module) {
+		debuginfo_cache_path = strdup(module);
+		if (!debuginfo_cache_path) {
+			debuginfo__delete(debuginfo_cache);
+			debuginfo_cache = NULL;
+			goto out;
+		}
+	}
+
+	debuginfo_cache = open_debuginfo(module, silent);
+	if (!debuginfo_cache)
+		zfree(&debuginfo_cache_path);
+out:
+	return debuginfo_cache;
+}
+
+static void debuginfo_cache__exit(void)
+{
+	debuginfo__delete(debuginfo_cache);
+	debuginfo_cache = NULL;
+	zfree(&debuginfo_cache_path);
+}
+
 
 static int get_text_start_address(const char *exec, unsigned long *address)
 {
@@ -474,12 +525,11 @@ static int find_perf_probe_point_from_dwarf(struct probe_trace_point *tp,
 	pr_debug("try to find information at %" PRIx64 " in %s\n", addr,
 		 tp->module ? : "kernel");
 
-	dinfo = open_debuginfo(tp->module, verbose == 0);
-	if (dinfo) {
+	dinfo = debuginfo_cache__open(tp->module, verbose == 0);
+	if (dinfo)
 		ret = debuginfo__find_probe_point(dinfo,
 						 (unsigned long)addr, pp);
-		debuginfo__delete(dinfo);
-	} else
+	else
 		ret = -ENOENT;
 
 	if (ret > 0) {
@@ -558,7 +608,7 @@ static int post_process_probe_trace_events(struct probe_trace_event *tevs,
 {
 	struct ref_reloc_sym *reloc_sym;
 	char *tmp;
-	int i;
+	int i, skipped = 0;
 
 	if (uprobe)
 		return add_exec_to_probe_trace_events(tevs, ntevs, module);
@@ -574,31 +624,40 @@ static int post_process_probe_trace_events(struct probe_trace_event *tevs,
 	}
 
 	for (i = 0; i < ntevs; i++) {
-		if (tevs[i].point.address && !tevs[i].point.retprobe) {
+		if (!tevs[i].point.address || tevs[i].point.retprobe)
+			continue;
+		/* If we found a wrong one, mark it by NULL symbol */
+		if (kprobe_warn_out_range(tevs[i].point.symbol,
+					  tevs[i].point.address)) {
+			tmp = NULL;
+			skipped++;
+		} else {
 			tmp = strdup(reloc_sym->name);
 			if (!tmp)
 				return -ENOMEM;
-			free(tevs[i].point.symbol);
-			tevs[i].point.symbol = tmp;
-			tevs[i].point.offset = tevs[i].point.address -
-					       reloc_sym->unrelocated_addr;
 		}
+		/* If we have no realname, use symbol for it */
+		if (!tevs[i].point.realname)
+			tevs[i].point.realname = tevs[i].point.symbol;
+		else
+			free(tevs[i].point.symbol);
+		tevs[i].point.symbol = tmp;
+		tevs[i].point.offset = tevs[i].point.address -
+				       reloc_sym->unrelocated_addr;
 	}
-	return 0;
+	return skipped;
 }
 
 /* Try to find perf_probe_event with debuginfo */
 static int try_to_find_probe_trace_events(struct perf_probe_event *pev,
-					  struct probe_trace_event **tevs,
-					  int max_tevs, const char *target)
+					  struct probe_trace_event **tevs)
 {
 	bool need_dwarf = perf_probe_event_need_dwarf(pev);
 	struct perf_probe_point tmp;
 	struct debuginfo *dinfo;
 	int ntevs, ret = 0;
 
-	dinfo = open_debuginfo(target, !need_dwarf);
-
+	dinfo = open_debuginfo(pev->target, !need_dwarf);
 	if (!dinfo) {
 		if (need_dwarf)
 			return -ENOENT;
@@ -608,13 +667,12 @@ static int try_to_find_probe_trace_events(struct perf_probe_event *pev,
 
 	pr_debug("Try to find probe point from debuginfo.\n");
 	/* Searching trace events corresponding to a probe event */
-	ntevs = debuginfo__find_trace_events(dinfo, pev, tevs, max_tevs);
+	ntevs = debuginfo__find_trace_events(dinfo, pev, tevs);
 
 	if (ntevs == 0)	{  /* Not found, retry with an alternative */
-		ret = get_alternative_probe_event(dinfo, pev, &tmp, target);
+		ret = get_alternative_probe_event(dinfo, pev, &tmp);
 		if (!ret) {
-			ntevs = debuginfo__find_trace_events(dinfo, pev,
-							     tevs, max_tevs);
+			ntevs = debuginfo__find_trace_events(dinfo, pev, tevs);
 			/*
 			 * Write back to the original probe_event for
 			 * setting appropriate (user given) event name
@@ -629,12 +687,15 @@ static int try_to_find_probe_trace_events(struct perf_probe_event *pev,
 	if (ntevs > 0) {	/* Succeeded to find trace events */
 		pr_debug("Found %d probe_trace_events.\n", ntevs);
 		ret = post_process_probe_trace_events(*tevs, ntevs,
-							target, pev->uprobes);
-		if (ret < 0) {
+						pev->target, pev->uprobes);
+		if (ret < 0 || ret == ntevs) {
 			clear_probe_trace_events(*tevs, ntevs);
 			zfree(tevs);
 		}
-		return ret < 0 ? ret : ntevs;
+		if (ret != ntevs)
+			return ret < 0 ? ret : ntevs;
+		ntevs = 0;
+		/* Fall through */
 	}
 
 	if (ntevs == 0)	{	/* No error but failed to find probe point. */
@@ -809,8 +870,7 @@ int show_line_range(struct line_range *lr, const char *module, bool user)
 
 static int show_available_vars_at(struct debuginfo *dinfo,
 				  struct perf_probe_event *pev,
-				  int max_vls, struct strfilter *_filter,
-				  bool externs, const char *target)
+				  struct strfilter *_filter)
 {
 	char *buf;
 	int ret, i, nvars;
@@ -824,13 +884,12 @@ static int show_available_vars_at(struct debuginfo *dinfo,
 		return -EINVAL;
 	pr_debug("Searching variables at %s\n", buf);
 
-	ret = debuginfo__find_available_vars_at(dinfo, pev, &vls,
-						max_vls, externs);
+	ret = debuginfo__find_available_vars_at(dinfo, pev, &vls);
 	if (!ret) {  /* Not found, retry with an alternative */
-		ret = get_alternative_probe_event(dinfo, pev, &tmp, target);
+		ret = get_alternative_probe_event(dinfo, pev, &tmp);
 		if (!ret) {
 			ret = debuginfo__find_available_vars_at(dinfo, pev,
-						&vls, max_vls, externs);
+								&vls);
 			/* Release the old probe_point */
 			clear_perf_probe_point(&tmp);
 		}
@@ -877,8 +936,7 @@ end:
 
 /* Show available variables on given probe point */
 int show_available_vars(struct perf_probe_event *pevs, int npevs,
-			int max_vls, const char *module,
-			struct strfilter *_filter, bool externs)
+			struct strfilter *_filter)
 {
 	int i, ret = 0;
 	struct debuginfo *dinfo;
@@ -887,7 +945,7 @@ int show_available_vars(struct perf_probe_event *pevs, int npevs,
 	if (ret < 0)
 		return ret;
 
-	dinfo = open_debuginfo(module, false);
+	dinfo = open_debuginfo(pevs->target, false);
 	if (!dinfo) {
 		ret = -ENOENT;
 		goto out;
@@ -896,8 +954,7 @@ int show_available_vars(struct perf_probe_event *pevs, int npevs,
 	setup_pager();
 
 	for (i = 0; i < npevs && ret >= 0; i++)
-		ret = show_available_vars_at(dinfo, &pevs[i], max_vls, _filter,
-					     externs, module);
+		ret = show_available_vars_at(dinfo, &pevs[i], _filter);
 
 	debuginfo__delete(dinfo);
 out:
@@ -907,6 +964,10 @@ out:
 
 #else	/* !HAVE_DWARF_SUPPORT */
 
+static void debuginfo_cache__exit(void)
+{
+}
+
 static int
 find_perf_probe_point_from_dwarf(struct probe_trace_point *tp __maybe_unused,
 				 struct perf_probe_point *pp __maybe_unused,
@@ -916,9 +977,7 @@ find_perf_probe_point_from_dwarf(struct probe_trace_point *tp __maybe_unused,
 }
 
 static int try_to_find_probe_trace_events(struct perf_probe_event *pev,
-				struct probe_trace_event **tevs __maybe_unused,
-				int max_tevs __maybe_unused,
-				const char *target __maybe_unused)
+				struct probe_trace_event **tevs __maybe_unused)
 {
 	if (perf_probe_event_need_dwarf(pev)) {
 		pr_warning("Debuginfo-analysis is not supported.\n");
@@ -937,10 +996,8 @@ int show_line_range(struct line_range *lr __maybe_unused,
 }
 
 int show_available_vars(struct perf_probe_event *pevs __maybe_unused,
-			int npevs __maybe_unused, int max_vls __maybe_unused,
-			const char *module __maybe_unused,
-			struct strfilter *filter __maybe_unused,
-			bool externs __maybe_unused)
+			int npevs __maybe_unused,
+			struct strfilter *filter __maybe_unused)
 {
 	pr_warning("Debuginfo-analysis is not supported.\n");
 	return -ENOSYS;
@@ -980,6 +1037,18 @@ static int parse_line_num(char **ptr, int *val, const char *what)
 	return 0;
 }
 
+/* Check the name is good for event, group or function */
+static bool is_c_func_name(const char *name)
+{
+	if (!isalpha(*name) && *name != '_')
+		return false;
+	while (*++name != '\0') {
+		if (!isalpha(*name) && !isdigit(*name) && *name != '_')
+			return false;
+	}
+	return true;
+}
+
 /*
  * Stuff 'lr' according to the line range described by 'arg'.
  * The line range syntax is described by:
@@ -1048,10 +1117,15 @@ int parse_line_range_desc(const char *arg, struct line_range *lr)
 			goto err;
 		}
 		lr->function = name;
-	} else if (strchr(name, '.'))
+	} else if (strchr(name, '/') || strchr(name, '.'))
 		lr->file = name;
-	else
+	else if (is_c_func_name(name))/* We reuse it for checking funcname */
 		lr->function = name;
+	else {	/* Invalid name */
+		semantic_error("'%s' is not a valid function name.\n", name);
+		err = -EINVAL;
+		goto err;
+	}
 
 	return 0;
 err:
@@ -1059,24 +1133,13 @@ err:
 	return err;
 }
 
-/* Check the name is good for event/group */
-static bool check_event_name(const char *name)
-{
-	if (!isalpha(*name) && *name != '_')
-		return false;
-	while (*++name != '\0') {
-		if (!isalpha(*name) && !isdigit(*name) && *name != '_')
-			return false;
-	}
-	return true;
-}
-
 /* Parse probepoint definition. */
 static int parse_perf_probe_point(char *arg, struct perf_probe_event *pev)
 {
 	struct perf_probe_point *pp = &pev->point;
 	char *ptr, *tmp;
 	char c, nc = 0;
+	bool file_spec = false;
 	/*
 	 * <Syntax>
 	 * perf probe [EVENT=]SRC[:LN|;PTN]
@@ -1095,7 +1158,7 @@ static int parse_perf_probe_point(char *arg, struct perf_probe_event *pev)
 			semantic_error("Group name is not supported yet.\n");
 			return -ENOTSUP;
 		}
-		if (!check_event_name(arg)) {
+		if (!is_c_func_name(arg)) {
 			semantic_error("%s is bad for event name -it must "
 				       "follow C symbol-naming rule.\n", arg);
 			return -EINVAL;
@@ -1107,6 +1170,23 @@ static int parse_perf_probe_point(char *arg, struct perf_probe_event *pev)
 		arg = tmp;
 	}
 
+	/*
+	 * Check arg is function or file name and copy it.
+	 *
+	 * We consider arg to be a file spec if and only if it satisfies
+	 * all of the below criteria::
+	 * - it does not include any of "+@%",
+	 * - it includes one of ":;", and
+	 * - it has a period '.' in the name.
+	 *
+	 * Otherwise, we consider arg to be a function specification.
+	 */
+	if (!strpbrk(arg, "+@%") && (ptr = strpbrk(arg, ";:")) != NULL) {
+		/* This is a file spec if it includes a '.' before ; or : */
+		if (memchr(arg, '.', ptr - arg))
+			file_spec = true;
+	}
+
 	ptr = strpbrk(arg, ";:+@%");
 	if (ptr) {
 		nc = *ptr;
@@ -1117,10 +1197,9 @@ static int parse_perf_probe_point(char *arg, struct perf_probe_event *pev)
 	if (tmp == NULL)
 		return -ENOMEM;
 
-	/* Check arg is function or file and copy it */
-	if (strchr(tmp, '.'))	/* File */
+	if (file_spec)
 		pp->file = tmp;
-	else			/* Function */
+	else
 		pp->function = tmp;
 
 	/* Parse other options */
@@ -1762,8 +1841,7 @@ static int find_perf_probe_point_from_map(struct probe_trace_point *tp,
 
 out:
 	if (map && !is_kprobe) {
-		dso__delete(map->dso);
-		map__delete(map);
+		map__put(map);
 	}
 
 	return ret;
@@ -1877,6 +1955,7 @@ static void clear_probe_trace_event(struct probe_trace_event *tev)
 	free(tev->event);
 	free(tev->group);
 	free(tev->point.symbol);
+	free(tev->point.realname);
 	free(tev->point.module);
 	for (i = 0; i < tev->nargs; i++) {
 		free(tev->args[i].name);
@@ -1954,7 +2033,7 @@ static int open_probe_events(const char *trace_file, bool readwrite)
 	if (ret >= 0) {
 		pr_debug("Opening %s write=%d\n", buf, readwrite);
 		if (readwrite && !probe_event_dry_run)
-			ret = open(buf, O_RDWR, O_APPEND);
+			ret = open(buf, O_RDWR | O_APPEND, 0);
 		else
 			ret = open(buf, O_RDONLY, 0);
 
@@ -2095,9 +2174,31 @@ kprobe_blacklist__find_by_address(struct list_head *blacklist,
 	return NULL;
 }
 
-/* Show an event */
-static int show_perf_probe_event(struct perf_probe_event *pev,
-				 const char *module)
+static LIST_HEAD(kprobe_blacklist);
+
+static void kprobe_blacklist__init(void)
+{
+	if (!list_empty(&kprobe_blacklist))
+		return;
+
+	if (kprobe_blacklist__load(&kprobe_blacklist) < 0)
+		pr_debug("No kprobe blacklist support, ignored\n");
+}
+
+static void kprobe_blacklist__release(void)
+{
+	kprobe_blacklist__delete(&kprobe_blacklist);
+}
+
+static bool kprobe_blacklist__listed(unsigned long address)
+{
+	return !!kprobe_blacklist__find_by_address(&kprobe_blacklist, address);
+}
+
+static int perf_probe_event__sprintf(const char *group, const char *event,
+				     struct perf_probe_event *pev,
+				     const char *module,
+				     struct strbuf *result)
 {
 	int i, ret;
 	char buf[128];
@@ -2108,30 +2209,67 @@ static int show_perf_probe_event(struct perf_probe_event *pev,
 	if (!place)
 		return -EINVAL;
 
-	ret = e_snprintf(buf, 128, "%s:%s", pev->group, pev->event);
+	ret = e_snprintf(buf, 128, "%s:%s", group, event);
 	if (ret < 0)
-		return ret;
+		goto out;
 
-	pr_info("  %-20s (on %s", buf, place);
+	strbuf_addf(result, "  %-20s (on %s", buf, place);
 	if (module)
-		pr_info(" in %s", module);
+		strbuf_addf(result, " in %s", module);
 
 	if (pev->nargs > 0) {
-		pr_info(" with");
+		strbuf_addstr(result, " with");
 		for (i = 0; i < pev->nargs; i++) {
 			ret = synthesize_perf_probe_arg(&pev->args[i],
 							buf, 128);
 			if (ret < 0)
-				break;
-			pr_info(" %s", buf);
+				goto out;
+			strbuf_addf(result, " %s", buf);
 		}
 	}
-	pr_info(")\n");
+	strbuf_addch(result, ')');
+out:
 	free(place);
 	return ret;
 }
 
-static int __show_perf_probe_events(int fd, bool is_kprobe)
+/* Show an event */
+static int show_perf_probe_event(const char *group, const char *event,
+				 struct perf_probe_event *pev,
+				 const char *module, bool use_stdout)
+{
+	struct strbuf buf = STRBUF_INIT;
+	int ret;
+
+	ret = perf_probe_event__sprintf(group, event, pev, module, &buf);
+	if (ret >= 0) {
+		if (use_stdout)
+			printf("%s\n", buf.buf);
+		else
+			pr_info("%s\n", buf.buf);
+	}
+	strbuf_release(&buf);
+
+	return ret;
+}
+
+static bool filter_probe_trace_event(struct probe_trace_event *tev,
+				     struct strfilter *filter)
+{
+	char tmp[128];
+
+	/* At first, check the event name itself */
+	if (strfilter__compare(filter, tev->event))
+		return true;
+
+	/* Next, check the combination of name and group */
+	if (e_snprintf(tmp, 128, "%s:%s", tev->group, tev->event) < 0)
+		return false;
+	return strfilter__compare(filter, tmp);
+}
+
+static int __show_perf_probe_events(int fd, bool is_kprobe,
+				    struct strfilter *filter)
 {
 	int ret = 0;
 	struct probe_trace_event tev;
@@ -2149,24 +2287,31 @@ static int __show_perf_probe_events(int fd, bool is_kprobe)
 	strlist__for_each(ent, rawlist) {
 		ret = parse_probe_trace_command(ent->s, &tev);
 		if (ret >= 0) {
+			if (!filter_probe_trace_event(&tev, filter))
+				goto next;
 			ret = convert_to_perf_probe_event(&tev, &pev,
 								is_kprobe);
-			if (ret >= 0)
-				ret = show_perf_probe_event(&pev,
-							    tev.point.module);
+			if (ret < 0)
+				goto next;
+			ret = show_perf_probe_event(pev.group, pev.event,
+						    &pev, tev.point.module,
+						    true);
 		}
+next:
 		clear_perf_probe_event(&pev);
 		clear_probe_trace_event(&tev);
 		if (ret < 0)
 			break;
 	}
 	strlist__delete(rawlist);
+	/* Cleanup cached debuginfo if needed */
+	debuginfo_cache__exit();
 
 	return ret;
 }
 
 /* List up current perf-probe events */
-int show_perf_probe_events(void)
+int show_perf_probe_events(struct strfilter *filter)
 {
 	int kp_fd, up_fd, ret;
 
@@ -2178,7 +2323,7 @@ int show_perf_probe_events(void)
 
 	kp_fd = open_kprobe_events(false);
 	if (kp_fd >= 0) {
-		ret = __show_perf_probe_events(kp_fd, true);
+		ret = __show_perf_probe_events(kp_fd, true, filter);
 		close(kp_fd);
 		if (ret < 0)
 			goto out;
@@ -2192,7 +2337,7 @@ int show_perf_probe_events(void)
 	}
 
 	if (up_fd >= 0) {
-		ret = __show_perf_probe_events(up_fd, false);
+		ret = __show_perf_probe_events(up_fd, false, filter);
 		close(up_fd);
 	}
 out:
@@ -2266,6 +2411,10 @@ static int get_new_event_name(char *buf, size_t len, const char *base,
 			      struct strlist *namelist, bool allow_suffix)
 {
 	int i, ret;
+	char *p;
+
+	if (*base == '.')
+		base++;
 
 	/* Try no suffix */
 	ret = e_snprintf(buf, len, "%s", base);
@@ -2273,6 +2422,10 @@ static int get_new_event_name(char *buf, size_t len, const char *base,
 		pr_debug("snprintf() failed: %d\n", ret);
 		return ret;
 	}
+	/* Cut off the postfixes (e.g. .const, .isra)*/
+	p = strchr(buf, '.');
+	if (p && p != buf)
+		*p = '\0';
 	if (!strlist__has_entry(namelist, buf))
 		return 0;
 
@@ -2328,10 +2481,9 @@ static int __add_probe_trace_events(struct perf_probe_event *pev,
 	int i, fd, ret;
 	struct probe_trace_event *tev = NULL;
 	char buf[64];
-	const char *event, *group;
+	const char *event = NULL, *group = NULL;
 	struct strlist *namelist;
-	LIST_HEAD(blacklist);
-	struct kprobe_blacklist_node *node;
+	bool safename;
 
 	if (pev->uprobes)
 		fd = open_uprobe_events(true);
@@ -2347,34 +2499,26 @@ static int __add_probe_trace_events(struct perf_probe_event *pev,
 	namelist = get_probe_trace_event_names(fd, false);
 	if (!namelist) {
 		pr_debug("Failed to get current event list.\n");
-		return -EIO;
-	}
-	/* Get kprobe blacklist if exists */
-	if (!pev->uprobes) {
-		ret = kprobe_blacklist__load(&blacklist);
-		if (ret < 0)
-			pr_debug("No kprobe blacklist support, ignored\n");
+		ret = -ENOMEM;
+		goto close_out;
 	}
 
+	safename = (pev->point.function && !strisglob(pev->point.function));
 	ret = 0;
 	pr_info("Added new event%s\n", (ntevs > 1) ? "s:" : ":");
 	for (i = 0; i < ntevs; i++) {
 		tev = &tevs[i];
-		/* Ensure that the address is NOT blacklisted */
-		node = kprobe_blacklist__find_by_address(&blacklist,
-							 tev->point.address);
-		if (node) {
-			pr_warning("Warning: Skipped probing on blacklisted function: %s\n", node->symbol);
+		/* Skip if the symbol is out of .text or blacklisted */
+		if (!tev->point.symbol)
 			continue;
-		}
 
 		if (pev->event)
 			event = pev->event;
 		else
-			if (pev->point.function)
+			if (safename)
 				event = pev->point.function;
 			else
-				event = tev->point.symbol;
+				event = tev->point.realname;
 		if (pev->group)
 			group = pev->group;
 		else
@@ -2399,15 +2543,12 @@ static int __add_probe_trace_events(struct perf_probe_event *pev,
 		/* Add added event name to namelist */
 		strlist__add(namelist, event);
 
-		/* Trick here - save current event/group */
-		event = pev->event;
-		group = pev->group;
-		pev->event = tev->event;
-		pev->group = tev->group;
-		show_perf_probe_event(pev, tev->point.module);
-		/* Trick here - restore current event/group */
-		pev->event = (char *)event;
-		pev->group = (char *)group;
+		/* We use tev's name for showing new events */
+		show_perf_probe_event(tev->group, tev->event, pev,
+				      tev->point.module, false);
+		/* Save the last valid name */
+		event = tev->event;
+		group = tev->group;
 
 		/*
 		 * Probes after the first probe which comes from same
@@ -2421,26 +2562,34 @@ static int __add_probe_trace_events(struct perf_probe_event *pev,
 		warn_uprobe_event_compat(tev);
 
 	/* Note that it is possible to skip all events because of blacklist */
-	if (ret >= 0 && tev->event) {
+	if (ret >= 0 && event) {
 		/* Show how to use the event. */
 		pr_info("\nYou can now use it in all perf tools, such as:\n\n");
-		pr_info("\tperf record -e %s:%s -aR sleep 1\n\n", tev->group,
-			 tev->event);
+		pr_info("\tperf record -e %s:%s -aR sleep 1\n\n", group, event);
 	}
 
-	kprobe_blacklist__delete(&blacklist);
 	strlist__delete(namelist);
+close_out:
 	close(fd);
 	return ret;
 }
 
-static int find_probe_functions(struct map *map, char *name)
+static int find_probe_functions(struct map *map, char *name,
+				struct symbol **syms)
 {
 	int found = 0;
 	struct symbol *sym;
+	struct rb_node *tmp;
+
+	if (map__load(map, NULL) < 0)
+		return 0;
 
-	map__for_each_symbol_by_name(map, name, sym) {
-		found++;
+	map__for_each_symbol(map, sym, tmp) {
+		if (strglobmatch(sym->name, name)) {
+			found++;
+			if (syms && found < probe_conf.max_probes)
+				syms[found - 1] = sym;
+		}
 	}
 
 	return found;
@@ -2449,42 +2598,52 @@ static int find_probe_functions(struct map *map, char *name)
 #define strdup_or_goto(str, label)	\
 	({ char *__p = strdup(str); if (!__p) goto label; __p; })
 
+void __weak arch__fix_tev_from_maps(struct perf_probe_event *pev __maybe_unused,
+				struct probe_trace_event *tev __maybe_unused,
+				struct map *map __maybe_unused) { }
+
 /*
  * Find probe function addresses from map.
  * Return an error or the number of found probe_trace_event
  */
 static int find_probe_trace_events_from_map(struct perf_probe_event *pev,
-					    struct probe_trace_event **tevs,
-					    int max_tevs, const char *target)
+					    struct probe_trace_event **tevs)
 {
 	struct map *map = NULL;
 	struct ref_reloc_sym *reloc_sym = NULL;
 	struct symbol *sym;
+	struct symbol **syms = NULL;
 	struct probe_trace_event *tev;
 	struct perf_probe_point *pp = &pev->point;
 	struct probe_trace_point *tp;
 	int num_matched_functions;
-	int ret, i;
+	int ret, i, j, skipped = 0;
 
-	map = get_target_map(target, pev->uprobes);
+	map = get_target_map(pev->target, pev->uprobes);
 	if (!map) {
 		ret = -EINVAL;
 		goto out;
 	}
 
+	syms = malloc(sizeof(struct symbol *) * probe_conf.max_probes);
+	if (!syms) {
+		ret = -ENOMEM;
+		goto out;
+	}
+
 	/*
 	 * Load matched symbols: Since the different local symbols may have
 	 * same name but different addresses, this lists all the symbols.
 	 */
-	num_matched_functions = find_probe_functions(map, pp->function);
+	num_matched_functions = find_probe_functions(map, pp->function, syms);
 	if (num_matched_functions == 0) {
 		pr_err("Failed to find symbol %s in %s\n", pp->function,
-			target ? : "kernel");
+			pev->target ? : "kernel");
 		ret = -ENOENT;
 		goto out;
-	} else if (num_matched_functions > max_tevs) {
+	} else if (num_matched_functions > probe_conf.max_probes) {
 		pr_err("Too many functions matched in %s\n",
-			target ? : "kernel");
+			pev->target ? : "kernel");
 		ret = -E2BIG;
 		goto out;
 	}
@@ -2507,7 +2666,9 @@ static int find_probe_trace_events_from_map(struct perf_probe_event *pev,
 
 	ret = 0;
 
-	map__for_each_symbol_by_name(map, pp->function, sym) {
+	for (j = 0; j < num_matched_functions; j++) {
+		sym = syms[j];
+
 		tev = (*tevs) + ret;
 		tp = &tev->point;
 		if (ret == num_matched_functions) {
@@ -2524,16 +2685,24 @@ static int find_probe_trace_events_from_map(struct perf_probe_event *pev,
 		}
 		/* Add one probe point */
 		tp->address = map->unmap_ip(map, sym->start) + pp->offset;
-		if (reloc_sym) {
+		/* If we found a wrong one, mark it by NULL symbol */
+		if (!pev->uprobes &&
+		    kprobe_warn_out_range(sym->name, tp->address)) {
+			tp->symbol = NULL;	/* Skip it */
+			skipped++;
+		} else if (reloc_sym) {
 			tp->symbol = strdup_or_goto(reloc_sym->name, nomem_out);
 			tp->offset = tp->address - reloc_sym->addr;
 		} else {
 			tp->symbol = strdup_or_goto(sym->name, nomem_out);
 			tp->offset = pp->offset;
 		}
+		tp->realname = strdup_or_goto(sym->name, nomem_out);
+
 		tp->retprobe = pp->retprobe;
-		if (target)
-			tev->point.module = strdup_or_goto(target, nomem_out);
+		if (pev->target)
+			tev->point.module = strdup_or_goto(pev->target,
+							   nomem_out);
 		tev->uprobes = pev->uprobes;
 		tev->nargs = pev->nargs;
 		if (tev->nargs) {
@@ -2555,10 +2724,16 @@ static int find_probe_trace_events_from_map(struct perf_probe_event *pev,
 					strdup_or_goto(pev->args[i].type,
 							nomem_out);
 		}
+		arch__fix_tev_from_maps(pev, tev, map);
+	}
+	if (ret == skipped) {
+		ret = -ENOENT;
+		goto err_out;
 	}
 
 out:
 	put_target_map(map, pev->uprobes);
+	free(syms);
 	return ret;
 
 nomem_out:
@@ -2569,27 +2744,34 @@ err_out:
 	goto out;
 }
 
+bool __weak arch__prefers_symtab(void) { return false; }
+
 static int convert_to_probe_trace_events(struct perf_probe_event *pev,
-					  struct probe_trace_event **tevs,
-					  int max_tevs, const char *target)
+					 struct probe_trace_event **tevs)
 {
 	int ret;
 
 	if (pev->uprobes && !pev->group) {
 		/* Replace group name if not given */
-		ret = convert_exec_to_group(target, &pev->group);
+		ret = convert_exec_to_group(pev->target, &pev->group);
 		if (ret != 0) {
 			pr_warning("Failed to make a group name.\n");
 			return ret;
 		}
 	}
 
+	if (arch__prefers_symtab() && !perf_probe_event_need_dwarf(pev)) {
+		ret = find_probe_trace_events_from_map(pev, tevs);
+		if (ret > 0)
+			return ret; /* Found in symbol table */
+	}
+
 	/* Convert perf_probe_event with debuginfo */
-	ret = try_to_find_probe_trace_events(pev, tevs, max_tevs, target);
+	ret = try_to_find_probe_trace_events(pev, tevs);
 	if (ret != 0)
 		return ret;	/* Found in debuginfo or got an error */
 
-	return find_probe_trace_events_from_map(pev, tevs, max_tevs, target);
+	return find_probe_trace_events_from_map(pev, tevs);
 }
 
 struct __event_package {
@@ -2598,8 +2780,7 @@ struct __event_package {
 	int				ntevs;
 };
 
-int add_perf_probe_events(struct perf_probe_event *pevs, int npevs,
-			  int max_tevs, bool force_add)
+int add_perf_probe_events(struct perf_probe_event *pevs, int npevs)
 {
 	int i, j, ret;
 	struct __event_package *pkgs;
@@ -2619,20 +2800,24 @@ int add_perf_probe_events(struct perf_probe_event *pevs, int npevs,
 	/* Loop 1: convert all events */
 	for (i = 0; i < npevs; i++) {
 		pkgs[i].pev = &pevs[i];
+		/* Init kprobe blacklist if needed */
+		if (!pkgs[i].pev->uprobes)
+			kprobe_blacklist__init();
 		/* Convert with or without debuginfo */
 		ret  = convert_to_probe_trace_events(pkgs[i].pev,
-						     &pkgs[i].tevs,
-						     max_tevs,
-						     pkgs[i].pev->target);
+						     &pkgs[i].tevs);
 		if (ret < 0)
 			goto end;
 		pkgs[i].ntevs = ret;
 	}
+	/* This just release blacklist only if allocated */
+	kprobe_blacklist__release();
 
 	/* Loop 2: add all events */
 	for (i = 0; i < npevs; i++) {
 		ret = __add_probe_trace_events(pkgs[i].pev, pkgs[i].tevs,
-						pkgs[i].ntevs, force_add);
+					       pkgs[i].ntevs,
+					       probe_conf.force_add);
 		if (ret < 0)
 			break;
 	}
@@ -2684,40 +2869,39 @@ error:
 	return ret;
 }
 
-static int del_trace_probe_event(int fd, const char *buf,
-						  struct strlist *namelist)
+static int del_trace_probe_events(int fd, struct strfilter *filter,
+				  struct strlist *namelist)
 {
-	struct str_node *ent, *n;
-	int ret = -1;
+	struct str_node *ent;
+	const char *p;
+	int ret = -ENOENT;
 
-	if (strpbrk(buf, "*?")) { /* Glob-exp */
-		strlist__for_each_safe(ent, n, namelist)
-			if (strglobmatch(ent->s, buf)) {
-				ret = __del_trace_probe_event(fd, ent);
-				if (ret < 0)
-					break;
-				strlist__remove(namelist, ent);
-			}
-	} else {
-		ent = strlist__find(namelist, buf);
-		if (ent) {
+	if (!namelist)
+		return -ENOENT;
+
+	strlist__for_each(ent, namelist) {
+		p = strchr(ent->s, ':');
+		if ((p && strfilter__compare(filter, p + 1)) ||
+		    strfilter__compare(filter, ent->s)) {
 			ret = __del_trace_probe_event(fd, ent);
-			if (ret >= 0)
-				strlist__remove(namelist, ent);
+			if (ret < 0)
+				break;
 		}
 	}
 
 	return ret;
 }
 
-int del_perf_probe_events(struct strlist *dellist)
+int del_perf_probe_events(struct strfilter *filter)
 {
-	int ret = -1, ufd = -1, kfd = -1;
-	char buf[128];
-	const char *group, *event;
-	char *p, *str;
-	struct str_node *ent;
+	int ret, ret2, ufd = -1, kfd = -1;
 	struct strlist *namelist = NULL, *unamelist = NULL;
+	char *str = strfilter__string(filter);
+
+	if (!str)
+		return -EINVAL;
+
+	pr_debug("Delete filter: \'%s\'\n", str);
 
 	/* Get current event names */
 	kfd = open_kprobe_events(true);
@@ -2730,49 +2914,23 @@ int del_perf_probe_events(struct strlist *dellist)
 
 	if (kfd < 0 && ufd < 0) {
 		print_both_open_warning(kfd, ufd);
+		ret = kfd;
 		goto error;
 	}
 
-	if (namelist == NULL && unamelist == NULL)
+	ret = del_trace_probe_events(kfd, filter, namelist);
+	if (ret < 0 && ret != -ENOENT)
 		goto error;
 
-	strlist__for_each(ent, dellist) {
-		str = strdup(ent->s);
-		if (str == NULL) {
-			ret = -ENOMEM;
-			goto error;
-		}
-		pr_debug("Parsing: %s\n", str);
-		p = strchr(str, ':');
-		if (p) {
-			group = str;
-			*p = '\0';
-			event = p + 1;
-		} else {
-			group = "*";
-			event = str;
-		}
-
-		ret = e_snprintf(buf, 128, "%s:%s", group, event);
-		if (ret < 0) {
-			pr_err("Failed to copy event.");
-			free(str);
-			goto error;
-		}
-
-		pr_debug("Group: %s, Event: %s\n", group, event);
-
-		if (namelist)
-			ret = del_trace_probe_event(kfd, buf, namelist);
-
-		if (unamelist && ret != 0)
-			ret = del_trace_probe_event(ufd, buf, unamelist);
-
-		if (ret != 0)
-			pr_info("Info: Event \"%s\" does not exist.\n", buf);
-
-		free(str);
+	ret2 = del_trace_probe_events(ufd, filter, unamelist);
+	if (ret2 < 0 && ret2 != -ENOENT) {
+		ret = ret2;
+		goto error;
 	}
+	if (ret == -ENOENT && ret2 == -ENOENT)
+		pr_debug("\"%s\" does not hit any event.\n", str);
+		/* Note that this is silently ignored */
+	ret = 0;
 
 error:
 	if (kfd >= 0) {
@@ -2784,6 +2942,7 @@ error:
 		strlist__delete(unamelist);
 		close(ufd);
 	}
+	free(str);
 
 	return ret;
 }
@@ -2837,8 +2996,7 @@ int show_available_funcs(const char *target, struct strfilter *_filter,
 	dso__fprintf_symbols_by_name(map->dso, map->type, stdout);
 end:
 	if (user) {
-		dso__delete(map->dso);
-		map__delete(map);
+		map__put(map);
 	}
 	exit_symbol_maps();
 
diff --git a/tools/perf/util/probe-event.h b/tools/perf/util/probe-event.h
index d6b783447be9..31db6ee7db54 100644
--- a/tools/perf/util/probe-event.h
+++ b/tools/perf/util/probe-event.h
@@ -6,10 +6,20 @@
 #include "strlist.h"
 #include "strfilter.h"
 
+/* Probe related configurations */
+struct probe_conf {
+	bool	show_ext_vars;
+	bool	show_location_range;
+	bool	force_add;
+	bool	no_inlines;
+	int	max_probes;
+};
+extern struct probe_conf probe_conf;
 extern bool probe_event_dry_run;
 
 /* kprobe-tracer and uprobe-tracer tracing point */
 struct probe_trace_point {
+	char		*realname;	/* function real name (if needed) */
 	char		*symbol;	/* Base symbol */
 	char		*module;	/* Module name */
 	unsigned long	offset;		/* Offset from symbol */
@@ -121,20 +131,18 @@ extern void line_range__clear(struct line_range *lr);
 /* Initialize line range */
 extern int line_range__init(struct line_range *lr);
 
-/* Internal use: Return kernel/module path */
-extern const char *kernel_get_module_path(const char *module);
-
-extern int add_perf_probe_events(struct perf_probe_event *pevs, int npevs,
-				 int max_probe_points, bool force_add);
-extern int del_perf_probe_events(struct strlist *dellist);
-extern int show_perf_probe_events(void);
+extern int add_perf_probe_events(struct perf_probe_event *pevs, int npevs);
+extern int del_perf_probe_events(struct strfilter *filter);
+extern int show_perf_probe_events(struct strfilter *filter);
 extern int show_line_range(struct line_range *lr, const char *module,
 			   bool user);
 extern int show_available_vars(struct perf_probe_event *pevs, int npevs,
-			       int max_probe_points, const char *module,
-			       struct strfilter *filter, bool externs);
+			       struct strfilter *filter);
 extern int show_available_funcs(const char *module, struct strfilter *filter,
 				bool user);
+bool arch__prefers_symtab(void);
+void arch__fix_tev_from_maps(struct perf_probe_event *pev,
+			     struct probe_trace_event *tev, struct map *map);
 
 /* Maximum index number of event-name postfix */
 #define MAX_EVENT_INDEX	1024
diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c
index 2a76e14db732..2da65a710893 100644
--- a/tools/perf/util/probe-finder.c
+++ b/tools/perf/util/probe-finder.c
@@ -130,7 +130,7 @@ struct debuginfo *debuginfo__new(const char *path)
 			continue;
 		dinfo = __debuginfo__new(buf);
 	}
-	dso__delete(dso);
+	dso__put(dso);
 
 out:
 	/* if failed to open all distro debuginfo, open given binary */
@@ -177,7 +177,7 @@ static int convert_variable_location(Dwarf_Die *vr_die, Dwarf_Addr addr,
 	Dwarf_Word offs = 0;
 	bool ref = false;
 	const char *regs;
-	int ret;
+	int ret, ret2 = 0;
 
 	if (dwarf_attr(vr_die, DW_AT_external, &attr) != NULL)
 		goto static_var;
@@ -187,9 +187,19 @@ static int convert_variable_location(Dwarf_Die *vr_die, Dwarf_Addr addr,
 		return -EINVAL;	/* Broken DIE ? */
 	if (dwarf_getlocation_addr(&attr, addr, &op, &nops, 1) <= 0) {
 		ret = dwarf_entrypc(sp_die, &tmp);
-		if (ret || addr != tmp ||
-		    dwarf_tag(vr_die) != DW_TAG_formal_parameter ||
-		    dwarf_highpc(sp_die, &tmp))
+		if (ret)
+			return -ENOENT;
+
+		if (probe_conf.show_location_range &&
+			(dwarf_tag(vr_die) == DW_TAG_variable)) {
+			ret2 = -ERANGE;
+		} else if (addr != tmp ||
+			dwarf_tag(vr_die) != DW_TAG_formal_parameter) {
+			return -ENOENT;
+		}
+
+		ret = dwarf_highpc(sp_die, &tmp);
+		if (ret)
 			return -ENOENT;
 		/*
 		 * This is fuzzed by fentry mcount. We try to find the
@@ -210,7 +220,7 @@ found:
 	if (op->atom == DW_OP_addr) {
 static_var:
 		if (!tvar)
-			return 0;
+			return ret2;
 		/* Static variables on memory (not stack), make @varname */
 		ret = strlen(dwarf_diename(vr_die));
 		tvar->value = zalloc(ret + 2);
@@ -220,7 +230,7 @@ static_var:
 		tvar->ref = alloc_trace_arg_ref((long)offs);
 		if (tvar->ref == NULL)
 			return -ENOMEM;
-		return 0;
+		return ret2;
 	}
 
 	/* If this is based on frame buffer, set the offset */
@@ -250,14 +260,14 @@ static_var:
 	}
 
 	if (!tvar)
-		return 0;
+		return ret2;
 
 	regs = get_arch_regstr(regn);
 	if (!regs) {
 		/* This should be a bug in DWARF or this tool */
 		pr_warning("Mapping for the register number %u "
 			   "missing on this architecture.\n", regn);
-		return -ERANGE;
+		return -ENOTSUP;
 	}
 
 	tvar->value = strdup(regs);
@@ -269,7 +279,7 @@ static_var:
 		if (tvar->ref == NULL)
 			return -ENOMEM;
 	}
-	return 0;
+	return ret2;
 }
 
 #define BYTES_TO_BITS(nb)	((nb) * BITS_PER_LONG / sizeof(long))
@@ -517,10 +527,12 @@ static int convert_variable(Dwarf_Die *vr_die, struct probe_finder *pf)
 
 	ret = convert_variable_location(vr_die, pf->addr, pf->fb_ops,
 					&pf->sp_die, pf->tvar);
-	if (ret == -ENOENT || ret == -EINVAL)
-		pr_err("Failed to find the location of %s at this address.\n"
-		       " Perhaps, it has been optimized out.\n", pf->pvar->var);
-	else if (ret == -ENOTSUP)
+	if (ret == -ENOENT || ret == -EINVAL) {
+		pr_err("Failed to find the location of the '%s' variable at this address.\n"
+		       " Perhaps it has been optimized out.\n"
+		       " Use -V with the --range option to show '%s' location range.\n",
+		       pf->pvar->var, pf->pvar->var);
+	} else if (ret == -ENOTSUP)
 		pr_err("Sorry, we don't support this variable location yet.\n");
 	else if (ret == 0 && pf->pvar->field) {
 		ret = convert_variable_fields(vr_die, pf->pvar->var,
@@ -662,9 +674,15 @@ static int call_probe_finder(Dwarf_Die *sc_die, struct probe_finder *pf)
 	/* If not a real subprogram, find a real one */
 	if (!die_is_func_def(sc_die)) {
 		if (!die_find_realfunc(&pf->cu_die, pf->addr, &pf->sp_die)) {
-			pr_warning("Failed to find probe point in any "
-				   "functions.\n");
-			return -ENOENT;
+			if (die_find_tailfunc(&pf->cu_die, pf->addr, &pf->sp_die)) {
+				pr_warning("Ignoring tail call from %s\n",
+						dwarf_diename(&pf->sp_die));
+				return 0;
+			} else {
+				pr_warning("Failed to find probe point in any "
+					   "functions.\n");
+				return -ENOENT;
+			}
 		}
 	} else
 		memcpy(&pf->sp_die, sc_die, sizeof(Dwarf_Die));
@@ -719,7 +737,7 @@ static int find_best_scope_cb(Dwarf_Die *fn_die, void *data)
 	}
 	/* If the function name is given, that's what user expects */
 	if (fsp->function) {
-		if (die_compare_name(fn_die, fsp->function)) {
+		if (die_match_name(fn_die, fsp->function)) {
 			memcpy(fsp->die_mem, fn_die, sizeof(Dwarf_Die));
 			fsp->found = true;
 			return 1;
@@ -922,13 +940,14 @@ static int probe_point_search_cb(Dwarf_Die *sp_die, void *data)
 
 	/* Check tag and diename */
 	if (!die_is_func_def(sp_die) ||
-	    !die_compare_name(sp_die, pp->function))
+	    !die_match_name(sp_die, pp->function))
 		return DWARF_CB_OK;
 
 	/* Check declared file */
 	if (pp->file && strtailcmp(pp->file, dwarf_decl_file(sp_die)))
 		return DWARF_CB_OK;
 
+	pr_debug("Matched function: %s\n", dwarf_diename(sp_die));
 	pf->fname = dwarf_decl_file(sp_die);
 	if (pp->line) { /* Function relative line */
 		dwarf_decl_line(sp_die, &pf->lno);
@@ -945,10 +964,20 @@ static int probe_point_search_cb(Dwarf_Die *sp_die, void *data)
 			/* TODO: Check the address in this function */
 			param->retval = call_probe_finder(sp_die, pf);
 		}
-	} else
+	} else if (!probe_conf.no_inlines) {
 		/* Inlined function: search instances */
 		param->retval = die_walk_instances(sp_die,
 					probe_point_inline_cb, (void *)pf);
+		/* This could be a non-existed inline definition */
+		if (param->retval == -ENOENT && strisglob(pp->function))
+			param->retval = 0;
+	}
+
+	/* We need to find other candidates */
+	if (strisglob(pp->function) && param->retval >= 0) {
+		param->retval = 0;	/* We have to clear the result */
+		return DWARF_CB_OK;
+	}
 
 	return DWARF_CB_ABORT; /* Exit; no same symbol in this CU. */
 }
@@ -977,7 +1006,7 @@ static int pubname_search_cb(Dwarf *dbg, Dwarf_Global *gl, void *data)
 		if (dwarf_tag(param->sp_die) != DW_TAG_subprogram)
 			return DWARF_CB_OK;
 
-		if (die_compare_name(param->sp_die, param->function)) {
+		if (die_match_name(param->sp_die, param->function)) {
 			if (!dwarf_offdie(dbg, gl->cu_offset, param->cu_die))
 				return DWARF_CB_OK;
 
@@ -1030,7 +1059,7 @@ static int debuginfo__find_probes(struct debuginfo *dbg,
 		return -ENOMEM;
 
 	/* Fastpath: lookup by function name from .debug_pubnames section */
-	if (pp->function) {
+	if (pp->function && !strisglob(pp->function)) {
 		struct pubname_callback_param pubname_param = {
 			.function = pp->function,
 			.file	  = pp->file,
@@ -1089,6 +1118,7 @@ found:
 struct local_vars_finder {
 	struct probe_finder *pf;
 	struct perf_probe_arg *args;
+	bool vars;
 	int max_args;
 	int nargs;
 	int ret;
@@ -1103,7 +1133,7 @@ static int copy_variables_cb(Dwarf_Die *die_mem, void *data)
 
 	tag = dwarf_tag(die_mem);
 	if (tag == DW_TAG_formal_parameter ||
-	    tag == DW_TAG_variable) {
+	    (tag == DW_TAG_variable && vf->vars)) {
 		if (convert_variable_location(die_mem, vf->pf->addr,
 					      vf->pf->fb_ops, &pf->sp_die,
 					      NULL) == 0) {
@@ -1129,26 +1159,28 @@ static int expand_probe_args(Dwarf_Die *sc_die, struct probe_finder *pf,
 	Dwarf_Die die_mem;
 	int i;
 	int n = 0;
-	struct local_vars_finder vf = {.pf = pf, .args = args,
+	struct local_vars_finder vf = {.pf = pf, .args = args, .vars = false,
 				.max_args = MAX_PROBE_ARGS, .ret = 0};
 
 	for (i = 0; i < pf->pev->nargs; i++) {
 		/* var never be NULL */
-		if (strcmp(pf->pev->args[i].var, "$vars") == 0) {
-			pr_debug("Expanding $vars into:");
-			vf.nargs = n;
-			/* Special local variables */
-			die_find_child(sc_die, copy_variables_cb, (void *)&vf,
-				       &die_mem);
-			pr_debug(" (%d)\n", vf.nargs - n);
-			if (vf.ret < 0)
-				return vf.ret;
-			n = vf.nargs;
-		} else {
+		if (strcmp(pf->pev->args[i].var, PROBE_ARG_VARS) == 0)
+			vf.vars = true;
+		else if (strcmp(pf->pev->args[i].var, PROBE_ARG_PARAMS) != 0) {
 			/* Copy normal argument */
 			args[n] = pf->pev->args[i];
 			n++;
+			continue;
 		}
+		pr_debug("Expanding %s into:", pf->pev->args[i].var);
+		vf.nargs = n;
+		/* Special local variables */
+		die_find_child(sc_die, copy_variables_cb, (void *)&vf,
+			       &die_mem);
+		pr_debug(" (%d)\n", vf.nargs - n);
+		if (vf.ret < 0)
+			return vf.ret;
+		n = vf.nargs;
 	}
 	return n;
 }
@@ -1176,6 +1208,10 @@ static int add_probe_trace_event(Dwarf_Die *sc_die, struct probe_finder *pf)
 	if (ret < 0)
 		return ret;
 
+	tev->point.realname = strdup(dwarf_diename(sc_die));
+	if (!tev->point.realname)
+		return -ENOMEM;
+
 	pr_debug("Probe point found: %s+%lu\n", tev->point.symbol,
 		 tev->point.offset);
 
@@ -1213,15 +1249,15 @@ end:
 /* Find probe_trace_events specified by perf_probe_event from debuginfo */
 int debuginfo__find_trace_events(struct debuginfo *dbg,
 				 struct perf_probe_event *pev,
-				 struct probe_trace_event **tevs, int max_tevs)
+				 struct probe_trace_event **tevs)
 {
 	struct trace_event_finder tf = {
 			.pf = {.pev = pev, .callback = add_probe_trace_event},
-			.mod = dbg->mod, .max_tevs = max_tevs};
+			.max_tevs = probe_conf.max_probes, .mod = dbg->mod};
 	int ret;
 
 	/* Allocate result tevs array */
-	*tevs = zalloc(sizeof(struct probe_trace_event) * max_tevs);
+	*tevs = zalloc(sizeof(struct probe_trace_event) * tf.max_tevs);
 	if (*tevs == NULL)
 		return -ENOMEM;
 
@@ -1237,14 +1273,11 @@ int debuginfo__find_trace_events(struct debuginfo *dbg,
 	return (ret < 0) ? ret : tf.ntevs;
 }
 
-#define MAX_VAR_LEN 64
-
 /* Collect available variables in this scope */
 static int collect_variables_cb(Dwarf_Die *die_mem, void *data)
 {
 	struct available_var_finder *af = data;
 	struct variable_list *vl;
-	char buf[MAX_VAR_LEN];
 	int tag, ret;
 
 	vl = &af->vls[af->nvls - 1];
@@ -1255,11 +1288,38 @@ static int collect_variables_cb(Dwarf_Die *die_mem, void *data)
 		ret = convert_variable_location(die_mem, af->pf.addr,
 						af->pf.fb_ops, &af->pf.sp_die,
 						NULL);
-		if (ret == 0) {
-			ret = die_get_varname(die_mem, buf, MAX_VAR_LEN);
-			pr_debug2("Add new var: %s\n", buf);
-			if (ret > 0)
-				strlist__add(vl->vars, buf);
+		if (ret == 0 || ret == -ERANGE) {
+			int ret2;
+			bool externs = !af->child;
+			struct strbuf buf;
+
+			strbuf_init(&buf, 64);
+
+			if (probe_conf.show_location_range) {
+				if (!externs) {
+					if (ret)
+						strbuf_addf(&buf, "[INV]\t");
+					else
+						strbuf_addf(&buf, "[VAL]\t");
+				} else
+					strbuf_addf(&buf, "[EXT]\t");
+			}
+
+			ret2 = die_get_varname(die_mem, &buf);
+
+			if (!ret2 && probe_conf.show_location_range &&
+				!externs) {
+				strbuf_addf(&buf, "\t");
+				ret2 = die_get_var_range(&af->pf.sp_die,
+							die_mem, &buf);
+			}
+
+			pr_debug("Add new var: %s\n", buf.buf);
+			if (ret2 == 0) {
+				strlist__add(vl->vars,
+					strbuf_detach(&buf, NULL));
+			}
+			strbuf_release(&buf);
 		}
 	}
 
@@ -1302,9 +1362,9 @@ static int add_available_vars(Dwarf_Die *sc_die, struct probe_finder *pf)
 	die_find_child(sc_die, collect_variables_cb, (void *)af, &die_mem);
 
 	/* Find external variables */
-	if (!af->externs)
+	if (!probe_conf.show_ext_vars)
 		goto out;
-	/* Don't need to search child DIE for externs. */
+	/* Don't need to search child DIE for external vars. */
 	af->child = false;
 	die_find_child(&pf->cu_die, collect_variables_cb, (void *)af, &die_mem);
 
@@ -1324,17 +1384,16 @@ out:
  */
 int debuginfo__find_available_vars_at(struct debuginfo *dbg,
 				      struct perf_probe_event *pev,
-				      struct variable_list **vls,
-				      int max_vls, bool externs)
+				      struct variable_list **vls)
 {
 	struct available_var_finder af = {
 			.pf = {.pev = pev, .callback = add_available_vars},
 			.mod = dbg->mod,
-			.max_vls = max_vls, .externs = externs};
+			.max_vls = probe_conf.max_probes};
 	int ret;
 
 	/* Allocate result vls array */
-	*vls = zalloc(sizeof(struct variable_list) * max_vls);
+	*vls = zalloc(sizeof(struct variable_list) * af.max_vls);
 	if (*vls == NULL)
 		return -ENOMEM;
 
@@ -1535,7 +1594,7 @@ static int line_range_search_cb(Dwarf_Die *sp_die, void *data)
 		return DWARF_CB_OK;
 
 	if (die_is_func_def(sp_die) &&
-	    die_compare_name(sp_die, lr->function)) {
+	    die_match_name(sp_die, lr->function)) {
 		lf->fname = dwarf_decl_file(sp_die);
 		dwarf_decl_line(sp_die, &lr->offset);
 		pr_debug("fname: %s, lineno:%d\n", lf->fname, lr->offset);
diff --git a/tools/perf/util/probe-finder.h b/tools/perf/util/probe-finder.h
index ebf8c8c81453..bed82716e1b4 100644
--- a/tools/perf/util/probe-finder.h
+++ b/tools/perf/util/probe-finder.h
@@ -10,6 +10,9 @@
 #define MAX_PROBES		 128
 #define MAX_PROBE_ARGS		 128
 
+#define PROBE_ARG_VARS		"$vars"
+#define PROBE_ARG_PARAMS	"$params"
+
 static inline int is_c_varname(const char *name)
 {
 	/* TODO */
@@ -37,8 +40,7 @@ extern void debuginfo__delete(struct debuginfo *dbg);
 /* Find probe_trace_events specified by perf_probe_event from debuginfo */
 extern int debuginfo__find_trace_events(struct debuginfo *dbg,
 					struct perf_probe_event *pev,
-					struct probe_trace_event **tevs,
-					int max_tevs);
+					struct probe_trace_event **tevs);
 
 /* Find a perf_probe_point from debuginfo */
 extern int debuginfo__find_probe_point(struct debuginfo *dbg,
@@ -52,8 +54,7 @@ extern int debuginfo__find_line_range(struct debuginfo *dbg,
 /* Find available variables */
 extern int debuginfo__find_available_vars_at(struct debuginfo *dbg,
 					     struct perf_probe_event *pev,
-					     struct variable_list **vls,
-					     int max_points, bool externs);
+					     struct variable_list **vls);
 
 /* Find a src file from a DWARF tag path */
 int get_real_path(const char *raw_path, const char *comp_dir,
@@ -96,7 +97,6 @@ struct available_var_finder {
 	struct variable_list	*vls;		/* Found variable lists */
 	int			nvls;		/* Number of variable lists */
 	int			max_vls;	/* Max no. of variable lists */
-	bool			externs;	/* Find external vars too */
 	bool			child;		/* Search child scopes */
 };
 
diff --git a/tools/perf/util/pstack.c b/tools/perf/util/pstack.c
index a126e6cc6e73..b234a6e3d0d4 100644
--- a/tools/perf/util/pstack.c
+++ b/tools/perf/util/pstack.c
@@ -74,3 +74,10 @@ void *pstack__pop(struct pstack *pstack)
 	pstack->entries[pstack->top] = NULL;
 	return ret;
 }
+
+void *pstack__peek(struct pstack *pstack)
+{
+	if (pstack->top == 0)
+		return NULL;
+	return pstack->entries[pstack->top - 1];
+}
diff --git a/tools/perf/util/pstack.h b/tools/perf/util/pstack.h
index c3cb6584d527..ded7f2e36624 100644
--- a/tools/perf/util/pstack.h
+++ b/tools/perf/util/pstack.h
@@ -10,5 +10,6 @@ bool pstack__empty(const struct pstack *pstack);
 void pstack__remove(struct pstack *pstack, void *key);
 void pstack__push(struct pstack *pstack, void *key);
 void *pstack__pop(struct pstack *pstack);
+void *pstack__peek(struct pstack *pstack);
 
 #endif /* _PERF_PSTACK_ */
diff --git a/tools/perf/util/python-ext-sources b/tools/perf/util/python-ext-sources
index 4d28624a1eca..5925fec90562 100644
--- a/tools/perf/util/python-ext-sources
+++ b/tools/perf/util/python-ext-sources
@@ -16,6 +16,7 @@ util/util.c
 util/xyarray.c
 util/cgroup.c
 util/rblist.c
+util/stat.c
 util/strlist.c
 util/trace-event.c
 ../../lib/rbtree.c
diff --git a/tools/perf/util/record.c b/tools/perf/util/record.c
index 8acd0df88b5c..d457c523a33d 100644
--- a/tools/perf/util/record.c
+++ b/tools/perf/util/record.c
@@ -20,7 +20,7 @@ static int perf_do_probe_api(setup_probe_fn_t fn, int cpu, const char *str)
 	if (!evlist)
 		return -ENOMEM;
 
-	if (parse_events(evlist, str))
+	if (parse_events(evlist, str, NULL))
 		goto out_delete;
 
 	evsel = perf_evlist__first(evlist);
@@ -119,7 +119,16 @@ void perf_evlist__config(struct perf_evlist *evlist, struct record_opts *opts)
 			evsel->attr.comm_exec = 1;
 	}
 
-	if (evlist->nr_entries > 1) {
+	if (opts->full_auxtrace) {
+		/*
+		 * Need to be able to synthesize and parse selected events with
+		 * arbitrary sample types, which requires always being able to
+		 * match the id.
+		 */
+		use_sample_identifier = perf_can_sample_identifier();
+		evlist__for_each(evlist, evsel)
+			perf_evsel__set_sample_id(evsel, use_sample_identifier);
+	} else if (evlist->nr_entries > 1) {
 		struct perf_evsel *first = perf_evlist__first(evlist);
 
 		evlist__for_each(evlist, evsel) {
@@ -207,7 +216,7 @@ bool perf_evlist__can_select_event(struct perf_evlist *evlist, const char *str)
 	if (!temp_evlist)
 		return false;
 
-	err = parse_events(temp_evlist, str);
+	err = parse_events(temp_evlist, str, NULL);
 	if (err)
 		goto out_delete;
 
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 0c74012575ac..aa482c10469d 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -15,12 +15,14 @@
 #include "cpumap.h"
 #include "perf_regs.h"
 #include "asm/bug.h"
+#include "auxtrace.h"
+#include "thread-stack.h"
 
-static int machines__deliver_event(struct machines *machines,
-				   struct perf_evlist *evlist,
-				   union perf_event *event,
-				   struct perf_sample *sample,
-				   struct perf_tool *tool, u64 file_offset);
+static int perf_session__deliver_event(struct perf_session *session,
+				       union perf_event *event,
+				       struct perf_sample *sample,
+				       struct perf_tool *tool,
+				       u64 file_offset);
 
 static int perf_session__open(struct perf_session *session)
 {
@@ -105,8 +107,8 @@ static int ordered_events__deliver_event(struct ordered_events *oe,
 		return ret;
 	}
 
-	return machines__deliver_event(&session->machines, session->evlist, event->event,
-				       &sample, session->tool, event->file_offset);
+	return perf_session__deliver_event(session, event->event, &sample,
+					   session->tool, event->file_offset);
 }
 
 struct perf_session *perf_session__new(struct perf_data_file *file,
@@ -119,6 +121,7 @@ struct perf_session *perf_session__new(struct perf_data_file *file,
 
 	session->repipe = repipe;
 	session->tool   = tool;
+	INIT_LIST_HEAD(&session->auxtrace_index);
 	machines__init(&session->machines);
 	ordered_events__init(&session->ordered_events, ordered_events__deliver_event);
 
@@ -185,6 +188,8 @@ static void perf_session_env__delete(struct perf_session_env *env)
 
 void perf_session__delete(struct perf_session *session)
 {
+	auxtrace__free(session);
+	auxtrace_index__free(&session->auxtrace_index);
 	perf_session__destroy_kernel_maps(session);
 	perf_session__delete_threads(session);
 	perf_session_env__delete(&session->header.env);
@@ -262,6 +267,49 @@ static int process_id_index_stub(struct perf_tool *tool __maybe_unused,
 	return 0;
 }
 
+static int process_event_auxtrace_info_stub(struct perf_tool *tool __maybe_unused,
+				union perf_event *event __maybe_unused,
+				struct perf_session *session __maybe_unused)
+{
+	dump_printf(": unhandled!\n");
+	return 0;
+}
+
+static int skipn(int fd, off_t n)
+{
+	char buf[4096];
+	ssize_t ret;
+
+	while (n > 0) {
+		ret = read(fd, buf, min(n, (off_t)sizeof(buf)));
+		if (ret <= 0)
+			return ret;
+		n -= ret;
+	}
+
+	return 0;
+}
+
+static s64 process_event_auxtrace_stub(struct perf_tool *tool __maybe_unused,
+				       union perf_event *event,
+				       struct perf_session *session
+				       __maybe_unused)
+{
+	dump_printf(": unhandled!\n");
+	if (perf_data_file__is_pipe(session->file))
+		skipn(perf_data_file__fd(session->file), event->auxtrace.size);
+	return event->auxtrace.size;
+}
+
+static
+int process_event_auxtrace_error_stub(struct perf_tool *tool __maybe_unused,
+				      union perf_event *event __maybe_unused,
+				      struct perf_session *session __maybe_unused)
+{
+	dump_printf(": unhandled!\n");
+	return 0;
+}
+
 void perf_tool__fill_defaults(struct perf_tool *tool)
 {
 	if (tool->sample == NULL)
@@ -278,6 +326,12 @@ void perf_tool__fill_defaults(struct perf_tool *tool)
 		tool->exit = process_event_stub;
 	if (tool->lost == NULL)
 		tool->lost = perf_event__process_lost;
+	if (tool->lost_samples == NULL)
+		tool->lost_samples = perf_event__process_lost_samples;
+	if (tool->aux == NULL)
+		tool->aux = perf_event__process_aux;
+	if (tool->itrace_start == NULL)
+		tool->itrace_start = perf_event__process_itrace_start;
 	if (tool->read == NULL)
 		tool->read = process_event_sample_stub;
 	if (tool->throttle == NULL)
@@ -298,6 +352,12 @@ void perf_tool__fill_defaults(struct perf_tool *tool)
 	}
 	if (tool->id_index == NULL)
 		tool->id_index = process_id_index_stub;
+	if (tool->auxtrace_info == NULL)
+		tool->auxtrace_info = process_event_auxtrace_info_stub;
+	if (tool->auxtrace == NULL)
+		tool->auxtrace = process_event_auxtrace_stub;
+	if (tool->auxtrace_error == NULL)
+		tool->auxtrace_error = process_event_auxtrace_error_stub;
 }
 
 static void swap_sample_id_all(union perf_event *event, void *data)
@@ -390,6 +450,26 @@ static void perf_event__read_swap(union perf_event *event, bool sample_id_all)
 		swap_sample_id_all(event, &event->read + 1);
 }
 
+static void perf_event__aux_swap(union perf_event *event, bool sample_id_all)
+{
+	event->aux.aux_offset = bswap_64(event->aux.aux_offset);
+	event->aux.aux_size   = bswap_64(event->aux.aux_size);
+	event->aux.flags      = bswap_64(event->aux.flags);
+
+	if (sample_id_all)
+		swap_sample_id_all(event, &event->aux + 1);
+}
+
+static void perf_event__itrace_start_swap(union perf_event *event,
+					  bool sample_id_all)
+{
+	event->itrace_start.pid	 = bswap_32(event->itrace_start.pid);
+	event->itrace_start.tid	 = bswap_32(event->itrace_start.tid);
+
+	if (sample_id_all)
+		swap_sample_id_all(event, &event->itrace_start + 1);
+}
+
 static void perf_event__throttle_swap(union perf_event *event,
 				      bool sample_id_all)
 {
@@ -438,19 +518,42 @@ void perf_event__attr_swap(struct perf_event_attr *attr)
 {
 	attr->type		= bswap_32(attr->type);
 	attr->size		= bswap_32(attr->size);
-	attr->config		= bswap_64(attr->config);
-	attr->sample_period	= bswap_64(attr->sample_period);
-	attr->sample_type	= bswap_64(attr->sample_type);
-	attr->read_format	= bswap_64(attr->read_format);
-	attr->wakeup_events	= bswap_32(attr->wakeup_events);
-	attr->bp_type		= bswap_32(attr->bp_type);
-	attr->bp_addr		= bswap_64(attr->bp_addr);
-	attr->bp_len		= bswap_64(attr->bp_len);
-	attr->branch_sample_type = bswap_64(attr->branch_sample_type);
-	attr->sample_regs_user	 = bswap_64(attr->sample_regs_user);
-	attr->sample_stack_user  = bswap_32(attr->sample_stack_user);
 
-	swap_bitfield((u8 *) (&attr->read_format + 1), sizeof(u64));
+#define bswap_safe(f, n) 					\
+	(attr->size > (offsetof(struct perf_event_attr, f) + 	\
+		       sizeof(attr->f) * (n)))
+#define bswap_field(f, sz) 			\
+do { 						\
+	if (bswap_safe(f, 0))			\
+		attr->f = bswap_##sz(attr->f);	\
+} while(0)
+#define bswap_field_32(f) bswap_field(f, 32)
+#define bswap_field_64(f) bswap_field(f, 64)
+
+	bswap_field_64(config);
+	bswap_field_64(sample_period);
+	bswap_field_64(sample_type);
+	bswap_field_64(read_format);
+	bswap_field_32(wakeup_events);
+	bswap_field_32(bp_type);
+	bswap_field_64(bp_addr);
+	bswap_field_64(bp_len);
+	bswap_field_64(branch_sample_type);
+	bswap_field_64(sample_regs_user);
+	bswap_field_32(sample_stack_user);
+	bswap_field_32(aux_watermark);
+
+	/*
+	 * After read_format are bitfields. Check read_format because
+	 * we are unable to use offsetof on bitfield.
+	 */
+	if (bswap_safe(read_format, 1))
+		swap_bitfield((u8 *) (&attr->read_format + 1),
+			      sizeof(u64));
+#undef bswap_field_64
+#undef bswap_field_32
+#undef bswap_field
+#undef bswap_safe
 }
 
 static void perf_event__hdr_attr_swap(union perf_event *event,
@@ -478,6 +581,40 @@ static void perf_event__tracing_data_swap(union perf_event *event,
 	event->tracing_data.size = bswap_32(event->tracing_data.size);
 }
 
+static void perf_event__auxtrace_info_swap(union perf_event *event,
+					   bool sample_id_all __maybe_unused)
+{
+	size_t size;
+
+	event->auxtrace_info.type = bswap_32(event->auxtrace_info.type);
+
+	size = event->header.size;
+	size -= (void *)&event->auxtrace_info.priv - (void *)event;
+	mem_bswap_64(event->auxtrace_info.priv, size);
+}
+
+static void perf_event__auxtrace_swap(union perf_event *event,
+				      bool sample_id_all __maybe_unused)
+{
+	event->auxtrace.size      = bswap_64(event->auxtrace.size);
+	event->auxtrace.offset    = bswap_64(event->auxtrace.offset);
+	event->auxtrace.reference = bswap_64(event->auxtrace.reference);
+	event->auxtrace.idx       = bswap_32(event->auxtrace.idx);
+	event->auxtrace.tid       = bswap_32(event->auxtrace.tid);
+	event->auxtrace.cpu       = bswap_32(event->auxtrace.cpu);
+}
+
+static void perf_event__auxtrace_error_swap(union perf_event *event,
+					    bool sample_id_all __maybe_unused)
+{
+	event->auxtrace_error.type = bswap_32(event->auxtrace_error.type);
+	event->auxtrace_error.code = bswap_32(event->auxtrace_error.code);
+	event->auxtrace_error.cpu  = bswap_32(event->auxtrace_error.cpu);
+	event->auxtrace_error.pid  = bswap_32(event->auxtrace_error.pid);
+	event->auxtrace_error.tid  = bswap_32(event->auxtrace_error.tid);
+	event->auxtrace_error.ip   = bswap_64(event->auxtrace_error.ip);
+}
+
 typedef void (*perf_event__swap_op)(union perf_event *event,
 				    bool sample_id_all);
 
@@ -492,11 +629,17 @@ static perf_event__swap_op perf_event__swap_ops[] = {
 	[PERF_RECORD_THROTTLE]		  = perf_event__throttle_swap,
 	[PERF_RECORD_UNTHROTTLE]	  = perf_event__throttle_swap,
 	[PERF_RECORD_SAMPLE]		  = perf_event__all64_swap,
+	[PERF_RECORD_AUX]		  = perf_event__aux_swap,
+	[PERF_RECORD_ITRACE_START]	  = perf_event__itrace_start_swap,
+	[PERF_RECORD_LOST_SAMPLES]	  = perf_event__all64_swap,
 	[PERF_RECORD_HEADER_ATTR]	  = perf_event__hdr_attr_swap,
 	[PERF_RECORD_HEADER_EVENT_TYPE]	  = perf_event__event_type_swap,
 	[PERF_RECORD_HEADER_TRACING_DATA] = perf_event__tracing_data_swap,
 	[PERF_RECORD_HEADER_BUILD_ID]	  = NULL,
 	[PERF_RECORD_ID_INDEX]		  = perf_event__all64_swap,
+	[PERF_RECORD_AUXTRACE_INFO]	  = perf_event__auxtrace_info_swap,
+	[PERF_RECORD_AUXTRACE]		  = perf_event__auxtrace_swap,
+	[PERF_RECORD_AUXTRACE_ERROR]	  = perf_event__auxtrace_error_swap,
 	[PERF_RECORD_HEADER_MAX]	  = NULL,
 };
 
@@ -921,6 +1064,8 @@ static int machines__deliver_event(struct machines *machines,
 	case PERF_RECORD_MMAP:
 		return tool->mmap(tool, event, sample, machine);
 	case PERF_RECORD_MMAP2:
+		if (event->header.misc & PERF_RECORD_MISC_PROC_MAP_PARSE_TIMEOUT)
+			++evlist->stats.nr_proc_map_timeout;
 		return tool->mmap2(tool, event, sample, machine);
 	case PERF_RECORD_COMM:
 		return tool->comm(tool, event, sample, machine);
@@ -932,18 +1077,44 @@ static int machines__deliver_event(struct machines *machines,
 		if (tool->lost == perf_event__process_lost)
 			evlist->stats.total_lost += event->lost.lost;
 		return tool->lost(tool, event, sample, machine);
+	case PERF_RECORD_LOST_SAMPLES:
+		if (tool->lost_samples == perf_event__process_lost_samples)
+			evlist->stats.total_lost_samples += event->lost_samples.lost;
+		return tool->lost_samples(tool, event, sample, machine);
 	case PERF_RECORD_READ:
 		return tool->read(tool, event, sample, evsel, machine);
 	case PERF_RECORD_THROTTLE:
 		return tool->throttle(tool, event, sample, machine);
 	case PERF_RECORD_UNTHROTTLE:
 		return tool->unthrottle(tool, event, sample, machine);
+	case PERF_RECORD_AUX:
+		return tool->aux(tool, event, sample, machine);
+	case PERF_RECORD_ITRACE_START:
+		return tool->itrace_start(tool, event, sample, machine);
 	default:
 		++evlist->stats.nr_unknown_events;
 		return -1;
 	}
 }
 
+static int perf_session__deliver_event(struct perf_session *session,
+				       union perf_event *event,
+				       struct perf_sample *sample,
+				       struct perf_tool *tool,
+				       u64 file_offset)
+{
+	int ret;
+
+	ret = auxtrace__process_event(session, event, sample, tool);
+	if (ret < 0)
+		return ret;
+	if (ret > 0)
+		return 0;
+
+	return machines__deliver_event(&session->machines, session->evlist,
+				       event, sample, tool, file_offset);
+}
+
 static s64 perf_session__process_user_event(struct perf_session *session,
 					    union perf_event *event,
 					    u64 file_offset)
@@ -980,6 +1151,15 @@ static s64 perf_session__process_user_event(struct perf_session *session,
 		return tool->finished_round(tool, event, oe);
 	case PERF_RECORD_ID_INDEX:
 		return tool->id_index(tool, event, session);
+	case PERF_RECORD_AUXTRACE_INFO:
+		return tool->auxtrace_info(tool, event, session);
+	case PERF_RECORD_AUXTRACE:
+		/* setup for reading amidst mmap */
+		lseek(fd, file_offset + event->header.size, SEEK_SET);
+		return tool->auxtrace(tool, event, session);
+	case PERF_RECORD_AUXTRACE_ERROR:
+		perf_session__auxtrace_error_inc(session, event);
+		return tool->auxtrace_error(tool, event, session);
 	default:
 		return -EINVAL;
 	}
@@ -1034,7 +1214,7 @@ int perf_session__peek_event(struct perf_session *session, off_t file_offset,
 		return -1;
 
 	if (lseek(fd, file_offset, SEEK_SET) == (off_t)-1 ||
-	    readn(fd, &buf, hdr_sz) != (ssize_t)hdr_sz)
+	    readn(fd, buf, hdr_sz) != (ssize_t)hdr_sz)
 		return -1;
 
 	event = (union perf_event *)buf;
@@ -1042,12 +1222,12 @@ int perf_session__peek_event(struct perf_session *session, off_t file_offset,
 	if (session->header.needs_swap)
 		perf_event_header__bswap(&event->header);
 
-	if (event->header.size < hdr_sz)
+	if (event->header.size < hdr_sz || event->header.size > buf_sz)
 		return -1;
 
 	rest = event->header.size - hdr_sz;
 
-	if (readn(fd, &buf, rest) != (ssize_t)rest)
+	if (readn(fd, buf, rest) != (ssize_t)rest)
 		return -1;
 
 	if (session->header.needs_swap)
@@ -1096,8 +1276,8 @@ static s64 perf_session__process_event(struct perf_session *session,
 			return ret;
 	}
 
-	return machines__deliver_event(&session->machines, evlist, event,
-				       &sample, tool, file_offset);
+	return perf_session__deliver_event(session, event, &sample, tool,
+					   file_offset);
 }
 
 void perf_event_header__bswap(struct perf_event_header *hdr)
@@ -1138,6 +1318,18 @@ static void perf_session__warn_about_errors(const struct perf_session *session)
 			    stats->nr_events[PERF_RECORD_LOST]);
 	}
 
+	if (session->tool->lost_samples == perf_event__process_lost_samples) {
+		double drop_rate;
+
+		drop_rate = (double)stats->total_lost_samples /
+			    (double) (stats->nr_events[PERF_RECORD_SAMPLE] + stats->total_lost_samples);
+		if (drop_rate > 0.05) {
+			ui__warning("Processed %" PRIu64 " samples and lost %3.2f%% samples!\n\n",
+				    stats->nr_events[PERF_RECORD_SAMPLE] + stats->total_lost_samples,
+				    drop_rate * 100.0);
+		}
+	}
+
 	if (stats->nr_unknown_events != 0) {
 		ui__warning("Found %u unknown events!\n\n"
 			    "Is this an older tool processing a perf.data "
@@ -1168,6 +1360,32 @@ static void perf_session__warn_about_errors(const struct perf_session *session)
 
 	if (oe->nr_unordered_events != 0)
 		ui__warning("%u out of order events recorded.\n", oe->nr_unordered_events);
+
+	events_stats__auxtrace_error_warn(stats);
+
+	if (stats->nr_proc_map_timeout != 0) {
+		ui__warning("%d map information files for pre-existing threads were\n"
+			    "not processed, if there are samples for addresses they\n"
+			    "will not be resolved, you may find out which are these\n"
+			    "threads by running with -v and redirecting the output\n"
+			    "to a file.\n"
+			    "The time limit to process proc map is too short?\n"
+			    "Increase it by --proc-map-timeout\n",
+			    stats->nr_proc_map_timeout);
+	}
+}
+
+static int perf_session__flush_thread_stack(struct thread *thread,
+					    void *p __maybe_unused)
+{
+	return thread_stack__flush(thread);
+}
+
+static int perf_session__flush_thread_stacks(struct perf_session *session)
+{
+	return machines__for_each_thread(&session->machines,
+					 perf_session__flush_thread_stack,
+					 NULL);
 }
 
 volatile int session_done;
@@ -1256,10 +1474,17 @@ more:
 done:
 	/* do the final flush for ordered samples */
 	err = ordered_events__flush(oe, OE_FLUSH__FINAL);
+	if (err)
+		goto out_err;
+	err = auxtrace__flush_events(session, tool);
+	if (err)
+		goto out_err;
+	err = perf_session__flush_thread_stacks(session);
 out_err:
 	free(buf);
 	perf_session__warn_about_errors(session);
 	ordered_events__free(&session->ordered_events);
+	auxtrace__free_events(session);
 	return err;
 }
 
@@ -1402,10 +1627,17 @@ more:
 out:
 	/* do the final flush for ordered samples */
 	err = ordered_events__flush(oe, OE_FLUSH__FINAL);
+	if (err)
+		goto out_err;
+	err = auxtrace__flush_events(session, tool);
+	if (err)
+		goto out_err;
+	err = perf_session__flush_thread_stacks(session);
 out_err:
 	ui_progress__finish();
 	perf_session__warn_about_errors(session);
 	ordered_events__free(&session->ordered_events);
+	auxtrace__free_events(session);
 	session->one_mmap = false;
 	return err;
 }
@@ -1488,7 +1720,13 @@ size_t perf_session__fprintf_dsos_buildid(struct perf_session *session, FILE *fp
 
 size_t perf_session__fprintf_nr_events(struct perf_session *session, FILE *fp)
 {
-	size_t ret = fprintf(fp, "Aggregated stats:\n");
+	size_t ret;
+	const char *msg = "";
+
+	if (perf_header__has_feat(&session->header, HEADER_AUXTRACE))
+		msg = " (excludes AUX area (e.g. instruction trace) decoded / synthesized events)";
+
+	ret = fprintf(fp, "Aggregated stats:%s\n", msg);
 
 	ret += events_stats__fprintf(&session->evlist->stats, fp);
 	return ret;
diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h
index d5fa7b7916ef..b44afc75d1cc 100644
--- a/tools/perf/util/session.h
+++ b/tools/perf/util/session.h
@@ -15,10 +15,16 @@
 struct ip_callchain;
 struct thread;
 
+struct auxtrace;
+struct itrace_synth_opts;
+
 struct perf_session {
 	struct perf_header	header;
 	struct machines		machines;
 	struct perf_evlist	*evlist;
+	struct auxtrace		*auxtrace;
+	struct itrace_synth_opts *itrace_synth_opts;
+	struct list_head	auxtrace_index;
 	struct trace_event	tevent;
 	bool			repipe;
 	bool			one_mmap;
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index 4593f36ecc4c..4c65a143a34c 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -89,14 +89,14 @@ static int64_t
 sort__comm_cmp(struct hist_entry *left, struct hist_entry *right)
 {
 	/* Compare the addr that should be unique among comm */
-	return comm__str(right->comm) - comm__str(left->comm);
+	return strcmp(comm__str(right->comm), comm__str(left->comm));
 }
 
 static int64_t
 sort__comm_collapse(struct hist_entry *left, struct hist_entry *right)
 {
 	/* Compare the addr that should be unique among comm */
-	return comm__str(right->comm) - comm__str(left->comm);
+	return strcmp(comm__str(right->comm), comm__str(left->comm));
 }
 
 static int64_t
@@ -182,18 +182,16 @@ static int64_t _sort__addr_cmp(u64 left_ip, u64 right_ip)
 
 static int64_t _sort__sym_cmp(struct symbol *sym_l, struct symbol *sym_r)
 {
-	u64 ip_l, ip_r;
-
 	if (!sym_l || !sym_r)
 		return cmp_null(sym_l, sym_r);
 
 	if (sym_l == sym_r)
 		return 0;
 
-	ip_l = sym_l->start;
-	ip_r = sym_r->start;
+	if (sym_l->start != sym_r->start)
+		return (int64_t)(sym_r->start - sym_l->start);
 
-	return (int64_t)(ip_r - ip_l);
+	return (int64_t)(sym_r->end - sym_l->end);
 }
 
 static int64_t
diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h
index 846036a921dc..e97cd476d336 100644
--- a/tools/perf/util/sort.h
+++ b/tools/perf/util/sort.h
@@ -58,15 +58,16 @@ struct he_stat {
 
 struct hist_entry_diff {
 	bool	computed;
+	union {
+		/* PERF_HPP__DELTA */
+		double	period_ratio_delta;
 
-	/* PERF_HPP__DELTA */
-	double	period_ratio_delta;
-
-	/* PERF_HPP__RATIO */
-	double	period_ratio;
+		/* PERF_HPP__RATIO */
+		double	period_ratio;
 
-	/* HISTC_WEIGHTED_DIFF */
-	s64	wdiff;
+		/* HISTC_WEIGHTED_DIFF */
+		s64	wdiff;
+	};
 };
 
 /**
@@ -92,21 +93,28 @@ struct hist_entry {
 	s32			cpu;
 	u8			cpumode;
 
-	struct hist_entry_diff	diff;
-
 	/* We are added by hists__add_dummy_entry. */
 	bool			dummy;
 
-	/* XXX These two should move to some tree widget lib */
-	u16			row_offset;
-	u16			nr_rows;
-
-	bool			init_have_children;
 	char			level;
 	u8			filtered;
+	union {
+		/*
+		 * Since perf diff only supports the stdio output, TUI
+		 * fields are only accessed from perf report (or perf
+		 * top).  So make it an union to reduce memory usage.
+		 */
+		struct hist_entry_diff	diff;
+		struct /* for TUI */ {
+			u16	row_offset;
+			u16	nr_rows;
+			bool	init_have_children;
+			bool	unfolded;
+			bool	has_children;
+		};
+	};
 	char			*srcline;
 	struct symbol		*parent;
-	unsigned long		position;
 	struct rb_root		sorted_chain;
 	struct branch_info	*branch_info;
 	struct hists		*hists;
diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c
new file mode 100644
index 000000000000..53e8bb7bc852
--- /dev/null
+++ b/tools/perf/util/stat-shadow.c
@@ -0,0 +1,434 @@
+#include <stdio.h>
+#include "evsel.h"
+#include "stat.h"
+#include "color.h"
+
+enum {
+	CTX_BIT_USER	= 1 << 0,
+	CTX_BIT_KERNEL	= 1 << 1,
+	CTX_BIT_HV	= 1 << 2,
+	CTX_BIT_HOST	= 1 << 3,
+	CTX_BIT_IDLE	= 1 << 4,
+	CTX_BIT_MAX	= 1 << 5,
+};
+
+#define NUM_CTX CTX_BIT_MAX
+
+static struct stats runtime_nsecs_stats[MAX_NR_CPUS];
+static struct stats runtime_cycles_stats[NUM_CTX][MAX_NR_CPUS];
+static struct stats runtime_stalled_cycles_front_stats[NUM_CTX][MAX_NR_CPUS];
+static struct stats runtime_stalled_cycles_back_stats[NUM_CTX][MAX_NR_CPUS];
+static struct stats runtime_branches_stats[NUM_CTX][MAX_NR_CPUS];
+static struct stats runtime_cacherefs_stats[NUM_CTX][MAX_NR_CPUS];
+static struct stats runtime_l1_dcache_stats[NUM_CTX][MAX_NR_CPUS];
+static struct stats runtime_l1_icache_stats[NUM_CTX][MAX_NR_CPUS];
+static struct stats runtime_ll_cache_stats[NUM_CTX][MAX_NR_CPUS];
+static struct stats runtime_itlb_cache_stats[NUM_CTX][MAX_NR_CPUS];
+static struct stats runtime_dtlb_cache_stats[NUM_CTX][MAX_NR_CPUS];
+static struct stats runtime_cycles_in_tx_stats[NUM_CTX][MAX_NR_CPUS];
+static struct stats runtime_transaction_stats[NUM_CTX][MAX_NR_CPUS];
+static struct stats runtime_elision_stats[NUM_CTX][MAX_NR_CPUS];
+
+struct stats walltime_nsecs_stats;
+
+static int evsel_context(struct perf_evsel *evsel)
+{
+	int ctx = 0;
+
+	if (evsel->attr.exclude_kernel)
+		ctx |= CTX_BIT_KERNEL;
+	if (evsel->attr.exclude_user)
+		ctx |= CTX_BIT_USER;
+	if (evsel->attr.exclude_hv)
+		ctx |= CTX_BIT_HV;
+	if (evsel->attr.exclude_host)
+		ctx |= CTX_BIT_HOST;
+	if (evsel->attr.exclude_idle)
+		ctx |= CTX_BIT_IDLE;
+
+	return ctx;
+}
+
+void perf_stat__reset_shadow_stats(void)
+{
+	memset(runtime_nsecs_stats, 0, sizeof(runtime_nsecs_stats));
+	memset(runtime_cycles_stats, 0, sizeof(runtime_cycles_stats));
+	memset(runtime_stalled_cycles_front_stats, 0, sizeof(runtime_stalled_cycles_front_stats));
+	memset(runtime_stalled_cycles_back_stats, 0, sizeof(runtime_stalled_cycles_back_stats));
+	memset(runtime_branches_stats, 0, sizeof(runtime_branches_stats));
+	memset(runtime_cacherefs_stats, 0, sizeof(runtime_cacherefs_stats));
+	memset(runtime_l1_dcache_stats, 0, sizeof(runtime_l1_dcache_stats));
+	memset(runtime_l1_icache_stats, 0, sizeof(runtime_l1_icache_stats));
+	memset(runtime_ll_cache_stats, 0, sizeof(runtime_ll_cache_stats));
+	memset(runtime_itlb_cache_stats, 0, sizeof(runtime_itlb_cache_stats));
+	memset(runtime_dtlb_cache_stats, 0, sizeof(runtime_dtlb_cache_stats));
+	memset(runtime_cycles_in_tx_stats, 0,
+			sizeof(runtime_cycles_in_tx_stats));
+	memset(runtime_transaction_stats, 0,
+		sizeof(runtime_transaction_stats));
+	memset(runtime_elision_stats, 0, sizeof(runtime_elision_stats));
+	memset(&walltime_nsecs_stats, 0, sizeof(walltime_nsecs_stats));
+}
+
+/*
+ * Update various tracking values we maintain to print
+ * more semantic information such as miss/hit ratios,
+ * instruction rates, etc:
+ */
+void perf_stat__update_shadow_stats(struct perf_evsel *counter, u64 *count,
+				    int cpu)
+{
+	int ctx = evsel_context(counter);
+
+	if (perf_evsel__match(counter, SOFTWARE, SW_TASK_CLOCK))
+		update_stats(&runtime_nsecs_stats[cpu], count[0]);
+	else if (perf_evsel__match(counter, HARDWARE, HW_CPU_CYCLES))
+		update_stats(&runtime_cycles_stats[ctx][cpu], count[0]);
+	else if (perf_stat_evsel__is(counter, CYCLES_IN_TX))
+		update_stats(&runtime_transaction_stats[ctx][cpu], count[0]);
+	else if (perf_stat_evsel__is(counter, TRANSACTION_START))
+		update_stats(&runtime_transaction_stats[ctx][cpu], count[0]);
+	else if (perf_stat_evsel__is(counter, ELISION_START))
+		update_stats(&runtime_elision_stats[ctx][cpu], count[0]);
+	else if (perf_evsel__match(counter, HARDWARE, HW_STALLED_CYCLES_FRONTEND))
+		update_stats(&runtime_stalled_cycles_front_stats[ctx][cpu], count[0]);
+	else if (perf_evsel__match(counter, HARDWARE, HW_STALLED_CYCLES_BACKEND))
+		update_stats(&runtime_stalled_cycles_back_stats[ctx][cpu], count[0]);
+	else if (perf_evsel__match(counter, HARDWARE, HW_BRANCH_INSTRUCTIONS))
+		update_stats(&runtime_branches_stats[ctx][cpu], count[0]);
+	else if (perf_evsel__match(counter, HARDWARE, HW_CACHE_REFERENCES))
+		update_stats(&runtime_cacherefs_stats[ctx][cpu], count[0]);
+	else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_L1D))
+		update_stats(&runtime_l1_dcache_stats[ctx][cpu], count[0]);
+	else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_L1I))
+		update_stats(&runtime_ll_cache_stats[ctx][cpu], count[0]);
+	else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_LL))
+		update_stats(&runtime_ll_cache_stats[ctx][cpu], count[0]);
+	else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_DTLB))
+		update_stats(&runtime_dtlb_cache_stats[ctx][cpu], count[0]);
+	else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_ITLB))
+		update_stats(&runtime_itlb_cache_stats[ctx][cpu], count[0]);
+}
+
+/* used for get_ratio_color() */
+enum grc_type {
+	GRC_STALLED_CYCLES_FE,
+	GRC_STALLED_CYCLES_BE,
+	GRC_CACHE_MISSES,
+	GRC_MAX_NR
+};
+
+static const char *get_ratio_color(enum grc_type type, double ratio)
+{
+	static const double grc_table[GRC_MAX_NR][3] = {
+		[GRC_STALLED_CYCLES_FE] = { 50.0, 30.0, 10.0 },
+		[GRC_STALLED_CYCLES_BE] = { 75.0, 50.0, 20.0 },
+		[GRC_CACHE_MISSES] 	= { 20.0, 10.0, 5.0 },
+	};
+	const char *color = PERF_COLOR_NORMAL;
+
+	if (ratio > grc_table[type][0])
+		color = PERF_COLOR_RED;
+	else if (ratio > grc_table[type][1])
+		color = PERF_COLOR_MAGENTA;
+	else if (ratio > grc_table[type][2])
+		color = PERF_COLOR_YELLOW;
+
+	return color;
+}
+
+static void print_stalled_cycles_frontend(FILE *out, int cpu,
+					  struct perf_evsel *evsel
+					  __maybe_unused, double avg)
+{
+	double total, ratio = 0.0;
+	const char *color;
+	int ctx = evsel_context(evsel);
+
+	total = avg_stats(&runtime_cycles_stats[ctx][cpu]);
+
+	if (total)
+		ratio = avg / total * 100.0;
+
+	color = get_ratio_color(GRC_STALLED_CYCLES_FE, ratio);
+
+	fprintf(out, " #  ");
+	color_fprintf(out, color, "%6.2f%%", ratio);
+	fprintf(out, " frontend cycles idle   ");
+}
+
+static void print_stalled_cycles_backend(FILE *out, int cpu,
+					 struct perf_evsel *evsel
+					 __maybe_unused, double avg)
+{
+	double total, ratio = 0.0;
+	const char *color;
+	int ctx = evsel_context(evsel);
+
+	total = avg_stats(&runtime_cycles_stats[ctx][cpu]);
+
+	if (total)
+		ratio = avg / total * 100.0;
+
+	color = get_ratio_color(GRC_STALLED_CYCLES_BE, ratio);
+
+	fprintf(out, " #  ");
+	color_fprintf(out, color, "%6.2f%%", ratio);
+	fprintf(out, " backend  cycles idle   ");
+}
+
+static void print_branch_misses(FILE *out, int cpu,
+				struct perf_evsel *evsel __maybe_unused,
+				double avg)
+{
+	double total, ratio = 0.0;
+	const char *color;
+	int ctx = evsel_context(evsel);
+
+	total = avg_stats(&runtime_branches_stats[ctx][cpu]);
+
+	if (total)
+		ratio = avg / total * 100.0;
+
+	color = get_ratio_color(GRC_CACHE_MISSES, ratio);
+
+	fprintf(out, " #  ");
+	color_fprintf(out, color, "%6.2f%%", ratio);
+	fprintf(out, " of all branches        ");
+}
+
+static void print_l1_dcache_misses(FILE *out, int cpu,
+				   struct perf_evsel *evsel __maybe_unused,
+				   double avg)
+{
+	double total, ratio = 0.0;
+	const char *color;
+	int ctx = evsel_context(evsel);
+
+	total = avg_stats(&runtime_l1_dcache_stats[ctx][cpu]);
+
+	if (total)
+		ratio = avg / total * 100.0;
+
+	color = get_ratio_color(GRC_CACHE_MISSES, ratio);
+
+	fprintf(out, " #  ");
+	color_fprintf(out, color, "%6.2f%%", ratio);
+	fprintf(out, " of all L1-dcache hits  ");
+}
+
+static void print_l1_icache_misses(FILE *out, int cpu,
+				   struct perf_evsel *evsel __maybe_unused,
+				   double avg)
+{
+	double total, ratio = 0.0;
+	const char *color;
+	int ctx = evsel_context(evsel);
+
+	total = avg_stats(&runtime_l1_icache_stats[ctx][cpu]);
+
+	if (total)
+		ratio = avg / total * 100.0;
+
+	color = get_ratio_color(GRC_CACHE_MISSES, ratio);
+
+	fprintf(out, " #  ");
+	color_fprintf(out, color, "%6.2f%%", ratio);
+	fprintf(out, " of all L1-icache hits  ");
+}
+
+static void print_dtlb_cache_misses(FILE *out, int cpu,
+				    struct perf_evsel *evsel __maybe_unused,
+				    double avg)
+{
+	double total, ratio = 0.0;
+	const char *color;
+	int ctx = evsel_context(evsel);
+
+	total = avg_stats(&runtime_dtlb_cache_stats[ctx][cpu]);
+
+	if (total)
+		ratio = avg / total * 100.0;
+
+	color = get_ratio_color(GRC_CACHE_MISSES, ratio);
+
+	fprintf(out, " #  ");
+	color_fprintf(out, color, "%6.2f%%", ratio);
+	fprintf(out, " of all dTLB cache hits ");
+}
+
+static void print_itlb_cache_misses(FILE *out, int cpu,
+				    struct perf_evsel *evsel __maybe_unused,
+				    double avg)
+{
+	double total, ratio = 0.0;
+	const char *color;
+	int ctx = evsel_context(evsel);
+
+	total = avg_stats(&runtime_itlb_cache_stats[ctx][cpu]);
+
+	if (total)
+		ratio = avg / total * 100.0;
+
+	color = get_ratio_color(GRC_CACHE_MISSES, ratio);
+
+	fprintf(out, " #  ");
+	color_fprintf(out, color, "%6.2f%%", ratio);
+	fprintf(out, " of all iTLB cache hits ");
+}
+
+static void print_ll_cache_misses(FILE *out, int cpu,
+				  struct perf_evsel *evsel __maybe_unused,
+				  double avg)
+{
+	double total, ratio = 0.0;
+	const char *color;
+	int ctx = evsel_context(evsel);
+
+	total = avg_stats(&runtime_ll_cache_stats[ctx][cpu]);
+
+	if (total)
+		ratio = avg / total * 100.0;
+
+	color = get_ratio_color(GRC_CACHE_MISSES, ratio);
+
+	fprintf(out, " #  ");
+	color_fprintf(out, color, "%6.2f%%", ratio);
+	fprintf(out, " of all LL-cache hits   ");
+}
+
+void perf_stat__print_shadow_stats(FILE *out, struct perf_evsel *evsel,
+				   double avg, int cpu, enum aggr_mode aggr)
+{
+	double total, ratio = 0.0, total2;
+	int ctx = evsel_context(evsel);
+
+	if (perf_evsel__match(evsel, HARDWARE, HW_INSTRUCTIONS)) {
+		total = avg_stats(&runtime_cycles_stats[ctx][cpu]);
+		if (total) {
+			ratio = avg / total;
+			fprintf(out, " #   %5.2f  insns per cycle        ", ratio);
+		} else {
+			fprintf(out, "                                   ");
+		}
+		total = avg_stats(&runtime_stalled_cycles_front_stats[ctx][cpu]);
+		total = max(total, avg_stats(&runtime_stalled_cycles_back_stats[ctx][cpu]));
+
+		if (total && avg) {
+			ratio = total / avg;
+			fprintf(out, "\n");
+			if (aggr == AGGR_NONE)
+				fprintf(out, "        ");
+			fprintf(out, "                                                  #   %5.2f  stalled cycles per insn", ratio);
+		}
+
+	} else if (perf_evsel__match(evsel, HARDWARE, HW_BRANCH_MISSES) &&
+			runtime_branches_stats[ctx][cpu].n != 0) {
+		print_branch_misses(out, cpu, evsel, avg);
+	} else if (
+		evsel->attr.type == PERF_TYPE_HW_CACHE &&
+		evsel->attr.config ==  ( PERF_COUNT_HW_CACHE_L1D |
+					((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
+					((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16)) &&
+			runtime_l1_dcache_stats[ctx][cpu].n != 0) {
+		print_l1_dcache_misses(out, cpu, evsel, avg);
+	} else if (
+		evsel->attr.type == PERF_TYPE_HW_CACHE &&
+		evsel->attr.config ==  ( PERF_COUNT_HW_CACHE_L1I |
+					((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
+					((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16)) &&
+			runtime_l1_icache_stats[ctx][cpu].n != 0) {
+		print_l1_icache_misses(out, cpu, evsel, avg);
+	} else if (
+		evsel->attr.type == PERF_TYPE_HW_CACHE &&
+		evsel->attr.config ==  ( PERF_COUNT_HW_CACHE_DTLB |
+					((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
+					((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16)) &&
+			runtime_dtlb_cache_stats[ctx][cpu].n != 0) {
+		print_dtlb_cache_misses(out, cpu, evsel, avg);
+	} else if (
+		evsel->attr.type == PERF_TYPE_HW_CACHE &&
+		evsel->attr.config ==  ( PERF_COUNT_HW_CACHE_ITLB |
+					((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
+					((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16)) &&
+			runtime_itlb_cache_stats[ctx][cpu].n != 0) {
+		print_itlb_cache_misses(out, cpu, evsel, avg);
+	} else if (
+		evsel->attr.type == PERF_TYPE_HW_CACHE &&
+		evsel->attr.config ==  ( PERF_COUNT_HW_CACHE_LL |
+					((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
+					((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16)) &&
+			runtime_ll_cache_stats[ctx][cpu].n != 0) {
+		print_ll_cache_misses(out, cpu, evsel, avg);
+	} else if (perf_evsel__match(evsel, HARDWARE, HW_CACHE_MISSES) &&
+			runtime_cacherefs_stats[ctx][cpu].n != 0) {
+		total = avg_stats(&runtime_cacherefs_stats[ctx][cpu]);
+
+		if (total)
+			ratio = avg * 100 / total;
+
+		fprintf(out, " # %8.3f %% of all cache refs    ", ratio);
+
+	} else if (perf_evsel__match(evsel, HARDWARE, HW_STALLED_CYCLES_FRONTEND)) {
+		print_stalled_cycles_frontend(out, cpu, evsel, avg);
+	} else if (perf_evsel__match(evsel, HARDWARE, HW_STALLED_CYCLES_BACKEND)) {
+		print_stalled_cycles_backend(out, cpu, evsel, avg);
+	} else if (perf_evsel__match(evsel, HARDWARE, HW_CPU_CYCLES)) {
+		total = avg_stats(&runtime_nsecs_stats[cpu]);
+
+		if (total) {
+			ratio = avg / total;
+			fprintf(out, " # %8.3f GHz                    ", ratio);
+		} else {
+			fprintf(out, "                                   ");
+		}
+	} else if (perf_stat_evsel__is(evsel, CYCLES_IN_TX)) {
+		total = avg_stats(&runtime_cycles_stats[ctx][cpu]);
+		if (total)
+			fprintf(out,
+				" #   %5.2f%% transactional cycles   ",
+				100.0 * (avg / total));
+	} else if (perf_stat_evsel__is(evsel, CYCLES_IN_TX_CP)) {
+		total = avg_stats(&runtime_cycles_stats[ctx][cpu]);
+		total2 = avg_stats(&runtime_cycles_in_tx_stats[ctx][cpu]);
+		if (total2 < avg)
+			total2 = avg;
+		if (total)
+			fprintf(out,
+				" #   %5.2f%% aborted cycles         ",
+				100.0 * ((total2-avg) / total));
+	} else if (perf_stat_evsel__is(evsel, TRANSACTION_START) &&
+		   avg > 0 &&
+		   runtime_cycles_in_tx_stats[ctx][cpu].n != 0) {
+		total = avg_stats(&runtime_cycles_in_tx_stats[ctx][cpu]);
+
+		if (total)
+			ratio = total / avg;
+
+		fprintf(out, " # %8.0f cycles / transaction   ", ratio);
+	} else if (perf_stat_evsel__is(evsel, ELISION_START) &&
+		   avg > 0 &&
+		   runtime_cycles_in_tx_stats[ctx][cpu].n != 0) {
+		total = avg_stats(&runtime_cycles_in_tx_stats[ctx][cpu]);
+
+		if (total)
+			ratio = total / avg;
+
+		fprintf(out, " # %8.0f cycles / elision       ", ratio);
+	} else if (runtime_nsecs_stats[cpu].n != 0) {
+		char unit = 'M';
+
+		total = avg_stats(&runtime_nsecs_stats[cpu]);
+
+		if (total)
+			ratio = 1000.0 * avg / total;
+		if (ratio < 0.001) {
+			ratio *= 1000;
+			unit = 'K';
+		}
+
+		fprintf(out, " # %8.3f %c/sec                  ", ratio, unit);
+	} else {
+		fprintf(out, "                                   ");
+	}
+}
diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c
index 6506b3dfb605..4014b709f956 100644
--- a/tools/perf/util/stat.c
+++ b/tools/perf/util/stat.c
@@ -1,6 +1,6 @@
 #include <math.h>
-
 #include "stat.h"
+#include "evsel.h"
 
 void update_stats(struct stats *stats, u64 val)
 {
@@ -61,3 +61,72 @@ double rel_stddev_stats(double stddev, double avg)
 
 	return pct;
 }
+
+bool __perf_evsel_stat__is(struct perf_evsel *evsel,
+			   enum perf_stat_evsel_id id)
+{
+	struct perf_stat *ps = evsel->priv;
+
+	return ps->id == id;
+}
+
+#define ID(id, name) [PERF_STAT_EVSEL_ID__##id] = #name
+static const char *id_str[PERF_STAT_EVSEL_ID__MAX] = {
+	ID(NONE,		x),
+	ID(CYCLES_IN_TX,	cpu/cycles-t/),
+	ID(TRANSACTION_START,	cpu/tx-start/),
+	ID(ELISION_START,	cpu/el-start/),
+	ID(CYCLES_IN_TX_CP,	cpu/cycles-ct/),
+};
+#undef ID
+
+void perf_stat_evsel_id_init(struct perf_evsel *evsel)
+{
+	struct perf_stat *ps = evsel->priv;
+	int i;
+
+	/* ps->id is 0 hence PERF_STAT_EVSEL_ID__NONE by default */
+
+	for (i = 0; i < PERF_STAT_EVSEL_ID__MAX; i++) {
+		if (!strcmp(perf_evsel__name(evsel), id_str[i])) {
+			ps->id = i;
+			break;
+		}
+	}
+}
+
+struct perf_counts *perf_counts__new(int ncpus)
+{
+	int size = sizeof(struct perf_counts) +
+		   ncpus * sizeof(struct perf_counts_values);
+
+	return zalloc(size);
+}
+
+void perf_counts__delete(struct perf_counts *counts)
+{
+	free(counts);
+}
+
+static void perf_counts__reset(struct perf_counts *counts, int ncpus)
+{
+	memset(counts, 0, (sizeof(*counts) +
+	       (ncpus * sizeof(struct perf_counts_values))));
+}
+
+void perf_evsel__reset_counts(struct perf_evsel *evsel, int ncpus)
+{
+	perf_counts__reset(evsel->counts, ncpus);
+}
+
+int perf_evsel__alloc_counts(struct perf_evsel *evsel, int ncpus)
+{
+	evsel->counts = perf_counts__new(ncpus);
+	return evsel->counts != NULL ? 0 : -ENOMEM;
+}
+
+void perf_evsel__free_counts(struct perf_evsel *evsel)
+{
+	perf_counts__delete(evsel->counts);
+	evsel->counts = NULL;
+}
diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h
index 5667fc3e39cf..093dc3cb28dd 100644
--- a/tools/perf/util/stat.h
+++ b/tools/perf/util/stat.h
@@ -2,6 +2,7 @@
 #define __PERF_STATS_H
 
 #include <linux/types.h>
+#include <stdio.h>
 
 struct stats
 {
@@ -9,6 +10,27 @@ struct stats
 	u64 max, min;
 };
 
+enum perf_stat_evsel_id {
+	PERF_STAT_EVSEL_ID__NONE = 0,
+	PERF_STAT_EVSEL_ID__CYCLES_IN_TX,
+	PERF_STAT_EVSEL_ID__TRANSACTION_START,
+	PERF_STAT_EVSEL_ID__ELISION_START,
+	PERF_STAT_EVSEL_ID__CYCLES_IN_TX_CP,
+	PERF_STAT_EVSEL_ID__MAX,
+};
+
+struct perf_stat {
+	struct stats		res_stats[3];
+	enum perf_stat_evsel_id	id;
+};
+
+enum aggr_mode {
+	AGGR_NONE,
+	AGGR_GLOBAL,
+	AGGR_SOCKET,
+	AGGR_CORE,
+};
+
 void update_stats(struct stats *stats, u64 val);
 double avg_stats(struct stats *stats);
 double stddev_stats(struct stats *stats);
@@ -22,4 +44,28 @@ static inline void init_stats(struct stats *stats)
 	stats->min  = (u64) -1;
 	stats->max  = 0;
 }
+
+struct perf_evsel;
+bool __perf_evsel_stat__is(struct perf_evsel *evsel,
+			   enum perf_stat_evsel_id id);
+
+#define perf_stat_evsel__is(evsel, id) \
+	__perf_evsel_stat__is(evsel, PERF_STAT_EVSEL_ID__ ## id)
+
+void perf_stat_evsel_id_init(struct perf_evsel *evsel);
+
+extern struct stats walltime_nsecs_stats;
+
+void perf_stat__reset_shadow_stats(void);
+void perf_stat__update_shadow_stats(struct perf_evsel *counter, u64 *count,
+				    int cpu);
+void perf_stat__print_shadow_stats(FILE *out, struct perf_evsel *evsel,
+				   double avg, int cpu, enum aggr_mode aggr);
+
+struct perf_counts *perf_counts__new(int ncpus);
+void perf_counts__delete(struct perf_counts *counts);
+
+void perf_evsel__reset_counts(struct perf_evsel *evsel, int ncpus);
+int perf_evsel__alloc_counts(struct perf_evsel *evsel, int ncpus);
+void perf_evsel__free_counts(struct perf_evsel *evsel);
 #endif
diff --git a/tools/perf/util/strfilter.c b/tools/perf/util/strfilter.c
index 79a757a2a15c..bcae659b6546 100644
--- a/tools/perf/util/strfilter.c
+++ b/tools/perf/util/strfilter.c
@@ -170,6 +170,46 @@ struct strfilter *strfilter__new(const char *rules, const char **err)
 	return filter;
 }
 
+static int strfilter__append(struct strfilter *filter, bool _or,
+			     const char *rules, const char **err)
+{
+	struct strfilter_node *right, *root;
+	const char *ep = NULL;
+
+	if (!filter || !rules)
+		return -EINVAL;
+
+	right = strfilter_node__new(rules, &ep);
+	if (!right || *ep != '\0') {
+		if (err)
+			*err = ep;
+		goto error;
+	}
+	root = strfilter_node__alloc(_or ? OP_or : OP_and, filter->root, right);
+	if (!root) {
+		ep = NULL;
+		goto error;
+	}
+
+	filter->root = root;
+	return 0;
+
+error:
+	strfilter_node__delete(right);
+	return ep ? -EINVAL : -ENOMEM;
+}
+
+int strfilter__or(struct strfilter *filter, const char *rules, const char **err)
+{
+	return strfilter__append(filter, true, rules, err);
+}
+
+int strfilter__and(struct strfilter *filter, const char *rules,
+		   const char **err)
+{
+	return strfilter__append(filter, false, rules, err);
+}
+
 static bool strfilter_node__compare(struct strfilter_node *node,
 				    const char *str)
 {
@@ -197,3 +237,70 @@ bool strfilter__compare(struct strfilter *filter, const char *str)
 		return false;
 	return strfilter_node__compare(filter->root, str);
 }
+
+static int strfilter_node__sprint(struct strfilter_node *node, char *buf);
+
+/* sprint node in parenthesis if needed */
+static int strfilter_node__sprint_pt(struct strfilter_node *node, char *buf)
+{
+	int len;
+	int pt = node->r ? 2 : 0;	/* don't need to check node->l */
+
+	if (buf && pt)
+		*buf++ = '(';
+	len = strfilter_node__sprint(node, buf);
+	if (len < 0)
+		return len;
+	if (buf && pt)
+		*(buf + len) = ')';
+	return len + pt;
+}
+
+static int strfilter_node__sprint(struct strfilter_node *node, char *buf)
+{
+	int len = 0, rlen;
+
+	if (!node || !node->p)
+		return -EINVAL;
+
+	switch (*node->p) {
+	case '|':
+	case '&':
+		len = strfilter_node__sprint_pt(node->l, buf);
+		if (len < 0)
+			return len;
+	case '!':
+		if (buf) {
+			*(buf + len++) = *node->p;
+			buf += len;
+		} else
+			len++;
+		rlen = strfilter_node__sprint_pt(node->r, buf);
+		if (rlen < 0)
+			return rlen;
+		len += rlen;
+		break;
+	default:
+		len = strlen(node->p);
+		if (buf)
+			strcpy(buf, node->p);
+	}
+
+	return len;
+}
+
+char *strfilter__string(struct strfilter *filter)
+{
+	int len;
+	char *ret = NULL;
+
+	len = strfilter_node__sprint(filter->root, NULL);
+	if (len < 0)
+		return NULL;
+
+	ret = malloc(len + 1);
+	if (ret)
+		strfilter_node__sprint(filter->root, ret);
+
+	return ret;
+}
diff --git a/tools/perf/util/strfilter.h b/tools/perf/util/strfilter.h
index fe611f3c9e39..cff5eda88728 100644
--- a/tools/perf/util/strfilter.h
+++ b/tools/perf/util/strfilter.h
@@ -29,6 +29,32 @@ struct strfilter {
 struct strfilter *strfilter__new(const char *rules, const char **err);
 
 /**
+ * strfilter__or - Append an additional rule by logical-or
+ * @filter: Original string filter
+ * @rules: Filter rule to be appended at left of the root of
+ *         @filter by using logical-or.
+ * @err: Pointer which points an error detected on @rules
+ *
+ * Parse @rules and join it to the @filter by using logical-or.
+ * Return 0 if success, or return the error code.
+ */
+int strfilter__or(struct strfilter *filter,
+		  const char *rules, const char **err);
+
+/**
+ * strfilter__add - Append an additional rule by logical-and
+ * @filter: Original string filter
+ * @rules: Filter rule to be appended at left of the root of
+ *         @filter by using logical-and.
+ * @err: Pointer which points an error detected on @rules
+ *
+ * Parse @rules and join it to the @filter by using logical-and.
+ * Return 0 if success, or return the error code.
+ */
+int strfilter__and(struct strfilter *filter,
+		   const char *rules, const char **err);
+
+/**
  * strfilter__compare - compare given string and a string filter
  * @filter: String filter
  * @str: target string
@@ -45,4 +71,13 @@ bool strfilter__compare(struct strfilter *filter, const char *str);
  */
 void strfilter__delete(struct strfilter *filter);
 
+/**
+ * strfilter__string - Reconstruct a rule string from filter
+ * @filter: String filter to reconstruct
+ *
+ * Reconstruct a rule string from @filter. This will be good for
+ * debug messages. Note that returning string must be freed afterward.
+ */
+char *strfilter__string(struct strfilter *filter);
+
 #endif
diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c
index a7ab6063e038..65f7e389ae09 100644
--- a/tools/perf/util/symbol-elf.c
+++ b/tools/perf/util/symbol-elf.c
@@ -630,6 +630,11 @@ void symsrc__destroy(struct symsrc *ss)
 	close(ss->fd);
 }
 
+bool __weak elf__needs_adjust_symbols(GElf_Ehdr ehdr)
+{
+	return ehdr.e_type == ET_EXEC || ehdr.e_type == ET_REL;
+}
+
 int symsrc__init(struct symsrc *ss, struct dso *dso, const char *name,
 		 enum dso_binary_type type)
 {
@@ -678,6 +683,7 @@ int symsrc__init(struct symsrc *ss, struct dso *dso, const char *name,
 		}
 
 		if (!dso__build_id_equal(dso, build_id)) {
+			pr_debug("%s: build id mismatch for %s.\n", __func__, name);
 			dso->load_errno = DSO_LOAD_ERRNO__MISMATCHING_BUILDID;
 			goto out_elf_end;
 		}
@@ -711,8 +717,7 @@ int symsrc__init(struct symsrc *ss, struct dso *dso, const char *name,
 						     ".gnu.prelink_undo",
 						     NULL) != NULL);
 	} else {
-		ss->adjust_symbols = ehdr.e_type == ET_EXEC ||
-				     ehdr.e_type == ET_REL;
+		ss->adjust_symbols = elf__needs_adjust_symbols(ehdr);
 	}
 
 	ss->name   = strdup(name);
@@ -771,6 +776,8 @@ static bool want_demangle(bool is_kernel_sym)
 	return is_kernel_sym ? symbol_conf.demangle_kernel : symbol_conf.demangle;
 }
 
+void __weak arch__elf_sym_adjust(GElf_Sym *sym __maybe_unused) { }
+
 int dso__load_sym(struct dso *dso, struct map *map,
 		  struct symsrc *syms_ss, struct symsrc *runtime_ss,
 		  symbol_filter_t filter, int kmodule)
@@ -935,6 +942,8 @@ int dso__load_sym(struct dso *dso, struct map *map,
 		    (sym.st_value & 1))
 			--sym.st_value;
 
+		arch__elf_sym_adjust(&sym);
+
 		if (dso->kernel || kmodule) {
 			char dso_name[PATH_MAX];
 
@@ -963,8 +972,10 @@ int dso__load_sym(struct dso *dso, struct map *map,
 					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);
 					}
 				}
 
@@ -1005,7 +1016,7 @@ int dso__load_sym(struct dso *dso, struct map *map,
 				curr_map = map__new2(start, curr_dso,
 						     map->type);
 				if (curr_map == NULL) {
-					dso__delete(curr_dso);
+					dso__put(curr_dso);
 					goto out_elf_end;
 				}
 				if (adjust_kernel_syms) {
@@ -1020,11 +1031,7 @@ int dso__load_sym(struct dso *dso, struct map *map,
 				}
 				curr_dso->symtab_type = dso->symtab_type;
 				map_groups__insert(kmaps, curr_map);
-				/*
-				 * The new DSO should go to the kernel DSOS
-				 */
-				dsos__add(&map->groups->machine->kernel_dsos,
-					  curr_dso);
+				dsos__add(&map->groups->machine->dsos, curr_dso);
 				dso__set_loaded(curr_dso, map->type);
 			} else
 				curr_dso = curr_map->dso;
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 201f6c4ca738..504f2d73b7ee 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -85,8 +85,17 @@ static int prefix_underscores_count(const char *str)
 	return tail - str;
 }
 
-#define SYMBOL_A 0
-#define SYMBOL_B 1
+int __weak arch__choose_best_symbol(struct symbol *syma,
+				    struct symbol *symb __maybe_unused)
+{
+	/* Avoid "SyS" kernel syscall aliases */
+	if (strlen(syma->name) >= 3 && !strncmp(syma->name, "SyS", 3))
+		return SYMBOL_B;
+	if (strlen(syma->name) >= 10 && !strncmp(syma->name, "compat_SyS", 10))
+		return SYMBOL_B;
+
+	return SYMBOL_A;
+}
 
 static int choose_best_symbol(struct symbol *syma, struct symbol *symb)
 {
@@ -134,13 +143,7 @@ static int choose_best_symbol(struct symbol *syma, struct symbol *symb)
 	else if (na < nb)
 		return SYMBOL_B;
 
-	/* Avoid "SyS" kernel syscall aliases */
-	if (na >= 3 && !strncmp(syma->name, "SyS", 3))
-		return SYMBOL_B;
-	if (na >= 10 && !strncmp(syma->name, "compat_SyS", 10))
-		return SYMBOL_B;
-
-	return SYMBOL_A;
+	return arch__choose_best_symbol(syma, symb);
 }
 
 void symbols__fixup_duplicate(struct rb_root *symbols)
@@ -199,18 +202,18 @@ void symbols__fixup_end(struct rb_root *symbols)
 
 void __map_groups__fixup_end(struct map_groups *mg, enum map_type type)
 {
-	struct map *prev, *curr;
-	struct rb_node *nd, *prevnd = rb_first(&mg->maps[type]);
+	struct maps *maps = &mg->maps[type];
+	struct map *next, *curr;
 
-	if (prevnd == NULL)
-		return;
+	pthread_rwlock_wrlock(&maps->lock);
 
-	curr = rb_entry(prevnd, struct map, rb_node);
+	curr = maps__first(maps);
+	if (curr == NULL)
+		goto out_unlock;
 
-	for (nd = rb_next(prevnd); nd; nd = rb_next(nd)) {
-		prev = curr;
-		curr = rb_entry(nd, struct map, rb_node);
-		prev->end = curr->start;
+	for (next = map__next(curr); next; next = map__next(curr)) {
+		curr->end = next->start;
+		curr = next;
 	}
 
 	/*
@@ -218,6 +221,9 @@ void __map_groups__fixup_end(struct map_groups *mg, enum map_type type)
 	 * last map final address.
 	 */
 	curr->end = ~0ULL;
+
+out_unlock:
+	pthread_rwlock_unlock(&maps->lock);
 }
 
 struct symbol *symbol__new(u64 start, u64 len, u8 binding, const char *name)
@@ -397,7 +403,7 @@ static struct symbol *symbols__find_by_name(struct rb_root *symbols,
 					    const char *name)
 {
 	struct rb_node *n;
-	struct symbol_name_rb_node *s;
+	struct symbol_name_rb_node *s = NULL;
 
 	if (symbols == NULL)
 		return NULL;
@@ -408,7 +414,7 @@ static struct symbol *symbols__find_by_name(struct rb_root *symbols,
 		int cmp;
 
 		s = rb_entry(n, struct symbol_name_rb_node, rb_node);
-		cmp = strcmp(name, s->sym.name);
+		cmp = arch__compare_symbol_names(name, s->sym.name);
 
 		if (cmp < 0)
 			n = n->rb_left;
@@ -426,7 +432,7 @@ static struct symbol *symbols__find_by_name(struct rb_root *symbols,
 		struct symbol_name_rb_node *tmp;
 
 		tmp = rb_entry(n, struct symbol_name_rb_node, rb_node);
-		if (strcmp(tmp->sym.name, s->sym.name))
+		if (arch__compare_symbol_names(tmp->sym.name, s->sym.name))
 			break;
 
 		s = tmp;
@@ -653,14 +659,14 @@ static int dso__split_kallsyms_for_kcore(struct dso *dso, struct map *map,
 		curr_map = map_groups__find(kmaps, map->type, pos->start);
 
 		if (!curr_map || (filter && filter(curr_map, pos))) {
-			rb_erase(&pos->rb_node, root);
+			rb_erase_init(&pos->rb_node, root);
 			symbol__delete(pos);
 		} else {
 			pos->start -= curr_map->start - curr_map->pgoff;
 			if (pos->end)
 				pos->end -= curr_map->start - curr_map->pgoff;
 			if (curr_map != map) {
-				rb_erase(&pos->rb_node, root);
+				rb_erase_init(&pos->rb_node, root);
 				symbols__insert(
 					&curr_map->dso->symbols[curr_map->type],
 					pos);
@@ -780,7 +786,7 @@ static int dso__split_kallsyms(struct dso *dso, struct map *map, u64 delta,
 
 			curr_map = map__new2(pos->start, ndso, map->type);
 			if (curr_map == NULL) {
-				dso__delete(ndso);
+				dso__put(ndso);
 				return -1;
 			}
 
@@ -1167,20 +1173,23 @@ static int dso__load_kcore(struct dso *dso, struct map *map,
 	/* Add new maps */
 	while (!list_empty(&md.maps)) {
 		new_map = list_entry(md.maps.next, struct map, node);
-		list_del(&new_map->node);
+		list_del_init(&new_map->node);
 		if (new_map == replacement_map) {
 			map->start	= new_map->start;
 			map->end	= new_map->end;
 			map->pgoff	= new_map->pgoff;
 			map->map_ip	= new_map->map_ip;
 			map->unmap_ip	= new_map->unmap_ip;
-			map__delete(new_map);
 			/* Ensure maps are correctly ordered */
+			map__get(map);
 			map_groups__remove(kmaps, map);
 			map_groups__insert(kmaps, map);
+			map__put(map);
 		} else {
 			map_groups__insert(kmaps, new_map);
 		}
+
+		map__put(new_map);
 	}
 
 	/*
@@ -1205,8 +1214,8 @@ static int dso__load_kcore(struct dso *dso, struct map *map,
 out_err:
 	while (!list_empty(&md.maps)) {
 		map = list_entry(md.maps.next, struct map, node);
-		list_del(&map->node);
-		map__delete(map);
+		list_del_init(&map->node);
+		map__put(map);
 	}
 	close(fd);
 	return -EINVAL;
@@ -1355,7 +1364,7 @@ static bool dso__is_compatible_symtab_type(struct dso *dso, bool kmod,
 	case DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE_COMP:
 		/*
 		 * kernel modules know their symtab type - it's set when
-		 * creating a module dso in machine__new_module().
+		 * creating a module dso in machine__findnew_module_map().
 		 */
 		return kmod && dso->symtab_type == type;
 
@@ -1380,12 +1389,22 @@ int dso__load(struct dso *dso, struct map *map, symbol_filter_t filter)
 	struct symsrc *syms_ss = NULL, *runtime_ss = NULL;
 	bool kmod;
 
-	dso__set_loaded(dso, map->type);
+	pthread_mutex_lock(&dso->lock);
+
+	/* check again under the dso->lock */
+	if (dso__loaded(dso, map->type)) {
+		ret = 1;
+		goto out;
+	}
 
-	if (dso->kernel == DSO_TYPE_KERNEL)
-		return dso__load_kernel_sym(dso, map, filter);
-	else if (dso->kernel == DSO_TYPE_GUEST_KERNEL)
-		return dso__load_guest_kernel_sym(dso, map, filter);
+	if (dso->kernel) {
+		if (dso->kernel == DSO_TYPE_KERNEL)
+			ret = dso__load_kernel_sym(dso, map, filter);
+		else if (dso->kernel == DSO_TYPE_GUEST_KERNEL)
+			ret = dso__load_guest_kernel_sym(dso, map, filter);
+
+		goto out;
+	}
 
 	if (map->groups && map->groups->machine)
 		machine = map->groups->machine;
@@ -1398,18 +1417,18 @@ int dso__load(struct dso *dso, struct map *map, symbol_filter_t filter)
 		struct stat st;
 
 		if (lstat(dso->name, &st) < 0)
-			return -1;
+			goto out;
 
 		if (st.st_uid && (st.st_uid != geteuid())) {
 			pr_warning("File %s not owned by current user or root, "
 				"ignoring it.\n", dso->name);
-			return -1;
+			goto out;
 		}
 
 		ret = dso__load_perf_map(dso, map, filter);
 		dso->symtab_type = ret > 0 ? DSO_BINARY_TYPE__JAVA_JIT :
 					     DSO_BINARY_TYPE__NOT_FOUND;
-		return ret;
+		goto out;
 	}
 
 	if (machine)
@@ -1417,7 +1436,7 @@ int dso__load(struct dso *dso, struct map *map, symbol_filter_t filter)
 
 	name = malloc(PATH_MAX);
 	if (!name)
-		return -1;
+		goto out;
 
 	kmod = dso->symtab_type == DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE ||
 		dso->symtab_type == DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE_COMP ||
@@ -1498,23 +1517,32 @@ int dso__load(struct dso *dso, struct map *map, symbol_filter_t filter)
 out_free:
 	free(name);
 	if (ret < 0 && strstr(dso->name, " (deleted)") != NULL)
-		return 0;
+		ret = 0;
+out:
+	dso__set_loaded(dso, map->type);
+	pthread_mutex_unlock(&dso->lock);
+
 	return ret;
 }
 
 struct map *map_groups__find_by_name(struct map_groups *mg,
 				     enum map_type type, const char *name)
 {
-	struct rb_node *nd;
+	struct maps *maps = &mg->maps[type];
+	struct map *map;
 
-	for (nd = rb_first(&mg->maps[type]); nd; nd = rb_next(nd)) {
-		struct map *map = rb_entry(nd, struct map, rb_node);
+	pthread_rwlock_rdlock(&maps->lock);
 
+	for (map = maps__first(maps); map; map = map__next(map)) {
 		if (map->dso && strcmp(map->dso->short_name, name) == 0)
-			return map;
+			goto out_unlock;
 	}
 
-	return NULL;
+	map = NULL;
+
+out_unlock:
+	pthread_rwlock_unlock(&maps->lock);
+	return map;
 }
 
 int dso__load_vmlinux(struct dso *dso, struct map *map,
@@ -1802,6 +1830,7 @@ static void vmlinux_path__exit(void)
 {
 	while (--vmlinux_path__nr_entries >= 0)
 		zfree(&vmlinux_path[vmlinux_path__nr_entries]);
+	vmlinux_path__nr_entries = 0;
 
 	zfree(&vmlinux_path);
 }
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index 09561500164a..bef47ead1d9b 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -158,8 +158,6 @@ struct ref_reloc_sym {
 struct map_symbol {
 	struct map    *map;
 	struct symbol *sym;
-	bool	      unfolded;
-	bool	      has_children;
 };
 
 struct addr_map_symbol {
@@ -303,4 +301,14 @@ int setup_list(struct strlist **list, const char *list_str,
 int setup_intlist(struct intlist **list, const char *list_str,
 		  const char *list_name);
 
+#ifdef HAVE_LIBELF_SUPPORT
+bool elf__needs_adjust_symbols(GElf_Ehdr ehdr);
+void arch__elf_sym_adjust(GElf_Sym *sym);
+#endif
+
+#define SYMBOL_A 0
+#define SYMBOL_B 1
+
+int arch__choose_best_symbol(struct symbol *syma, struct symbol *symb);
+
 #endif /* __PERF_SYMBOL */
diff --git a/tools/perf/util/thread-stack.c b/tools/perf/util/thread-stack.c
index 9ed59a452d1f..679688e70ae7 100644
--- a/tools/perf/util/thread-stack.c
+++ b/tools/perf/util/thread-stack.c
@@ -219,7 +219,7 @@ static int thread_stack__call_return(struct thread *thread,
 	return crp->process(&cr, crp->data);
 }
 
-static int thread_stack__flush(struct thread *thread, struct thread_stack *ts)
+static int __thread_stack__flush(struct thread *thread, struct thread_stack *ts)
 {
 	struct call_return_processor *crp = ts->crp;
 	int err;
@@ -242,6 +242,14 @@ static int thread_stack__flush(struct thread *thread, struct thread_stack *ts)
 	return 0;
 }
 
+int thread_stack__flush(struct thread *thread)
+{
+	if (thread->ts)
+		return __thread_stack__flush(thread, thread->ts);
+
+	return 0;
+}
+
 int thread_stack__event(struct thread *thread, u32 flags, u64 from_ip,
 			u64 to_ip, u16 insn_len, u64 trace_nr)
 {
@@ -264,7 +272,7 @@ int thread_stack__event(struct thread *thread, u32 flags, u64 from_ip,
 	 */
 	if (trace_nr != thread->ts->trace_nr) {
 		if (thread->ts->trace_nr)
-			thread_stack__flush(thread, thread->ts);
+			__thread_stack__flush(thread, thread->ts);
 		thread->ts->trace_nr = trace_nr;
 	}
 
@@ -297,7 +305,7 @@ void thread_stack__set_trace_nr(struct thread *thread, u64 trace_nr)
 
 	if (trace_nr != thread->ts->trace_nr) {
 		if (thread->ts->trace_nr)
-			thread_stack__flush(thread, thread->ts);
+			__thread_stack__flush(thread, thread->ts);
 		thread->ts->trace_nr = trace_nr;
 	}
 }
@@ -305,7 +313,7 @@ void thread_stack__set_trace_nr(struct thread *thread, u64 trace_nr)
 void thread_stack__free(struct thread *thread)
 {
 	if (thread->ts) {
-		thread_stack__flush(thread, thread->ts);
+		__thread_stack__flush(thread, thread->ts);
 		zfree(&thread->ts->stack);
 		zfree(&thread->ts);
 	}
@@ -689,7 +697,7 @@ int thread_stack__process(struct thread *thread, struct comm *comm,
 
 	/* Flush stack on exec */
 	if (ts->comm != comm && thread->pid_ == thread->tid) {
-		err = thread_stack__flush(thread, ts);
+		err = __thread_stack__flush(thread, ts);
 		if (err)
 			return err;
 		ts->comm = comm;
diff --git a/tools/perf/util/thread-stack.h b/tools/perf/util/thread-stack.h
index b843bbef8ba2..e1528f1374c3 100644
--- a/tools/perf/util/thread-stack.h
+++ b/tools/perf/util/thread-stack.h
@@ -96,6 +96,7 @@ int thread_stack__event(struct thread *thread, u32 flags, u64 from_ip,
 void thread_stack__set_trace_nr(struct thread *thread, u64 trace_nr);
 void thread_stack__sample(struct thread *thread, struct ip_callchain *chain,
 			  size_t sz, u64 ip);
+int thread_stack__flush(struct thread *thread);
 void thread_stack__free(struct thread *thread);
 
 struct call_return_processor *
diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c
index 1c8fbc9588c5..28c4b746baa1 100644
--- a/tools/perf/util/thread.c
+++ b/tools/perf/util/thread.c
@@ -18,7 +18,7 @@ int thread__init_map_groups(struct thread *thread, struct machine *machine)
 	if (pid == thread->tid || pid == -1) {
 		thread->mg = map_groups__new(machine);
 	} else {
-		leader = machine__findnew_thread(machine, pid, pid);
+		leader = __machine__findnew_thread(machine, pid, pid);
 		if (leader)
 			thread->mg = map_groups__get(leader->mg);
 	}
@@ -53,7 +53,8 @@ struct thread *thread__new(pid_t pid, pid_t tid)
 			goto err_thread;
 
 		list_add(&comm->list, &thread->comm_list);
-
+		atomic_set(&thread->refcnt, 0);
+		RB_CLEAR_NODE(&thread->rb_node);
 	}
 
 	return thread;
@@ -67,6 +68,8 @@ void thread__delete(struct thread *thread)
 {
 	struct comm *comm, *tmp;
 
+	BUG_ON(!RB_EMPTY_NODE(&thread->rb_node));
+
 	thread_stack__free(thread);
 
 	if (thread->mg) {
@@ -84,13 +87,14 @@ void thread__delete(struct thread *thread)
 
 struct thread *thread__get(struct thread *thread)
 {
-	++thread->refcnt;
+	if (thread)
+		atomic_inc(&thread->refcnt);
 	return thread;
 }
 
 void thread__put(struct thread *thread)
 {
-	if (thread && --thread->refcnt == 0) {
+	if (thread && atomic_dec_and_test(&thread->refcnt)) {
 		list_del_init(&thread->node);
 		thread__delete(thread);
 	}
diff --git a/tools/perf/util/thread.h b/tools/perf/util/thread.h
index 9b8a54dc34a8..a0ac0317affb 100644
--- a/tools/perf/util/thread.h
+++ b/tools/perf/util/thread.h
@@ -1,6 +1,7 @@
 #ifndef __PERF_THREAD_H
 #define __PERF_THREAD_H
 
+#include <linux/atomic.h>
 #include <linux/rbtree.h>
 #include <linux/list.h>
 #include <unistd.h>
@@ -21,12 +22,12 @@ struct thread {
 	pid_t			tid;
 	pid_t			ppid;
 	int			cpu;
-	int			refcnt;
+	atomic_t		refcnt;
 	char			shortname[3];
 	bool			comm_set;
+	int			comm_len;
 	bool			dead; /* if set thread has exited */
 	struct list_head	comm_list;
-	int			comm_len;
 	u64			db_id;
 
 	void			*priv;
diff --git a/tools/perf/util/thread_map.c b/tools/perf/util/thread_map.c
index f93b9734735b..f4822bd03709 100644
--- a/tools/perf/util/thread_map.c
+++ b/tools/perf/util/thread_map.c
@@ -20,6 +20,15 @@ static int filter(const struct dirent *dir)
 		return 1;
 }
 
+static struct thread_map *thread_map__realloc(struct thread_map *map, int nr)
+{
+	size_t size = sizeof(*map) + sizeof(pid_t) * nr;
+
+	return realloc(map, size);
+}
+
+#define thread_map__alloc(__nr) thread_map__realloc(NULL, __nr)
+
 struct thread_map *thread_map__new_by_pid(pid_t pid)
 {
 	struct thread_map *threads;
@@ -33,7 +42,7 @@ struct thread_map *thread_map__new_by_pid(pid_t pid)
 	if (items <= 0)
 		return NULL;
 
-	threads = malloc(sizeof(*threads) + sizeof(pid_t) * items);
+	threads = thread_map__alloc(items);
 	if (threads != NULL) {
 		for (i = 0; i < items; i++)
 			threads->map[i] = atoi(namelist[i]->d_name);
@@ -49,7 +58,7 @@ struct thread_map *thread_map__new_by_pid(pid_t pid)
 
 struct thread_map *thread_map__new_by_tid(pid_t tid)
 {
-	struct thread_map *threads = malloc(sizeof(*threads) + sizeof(pid_t));
+	struct thread_map *threads = thread_map__alloc(1);
 
 	if (threads != NULL) {
 		threads->map[0] = tid;
@@ -65,8 +74,8 @@ struct thread_map *thread_map__new_by_uid(uid_t uid)
 	int max_threads = 32, items, i;
 	char path[256];
 	struct dirent dirent, *next, **namelist = NULL;
-	struct thread_map *threads = malloc(sizeof(*threads) +
-					    max_threads * sizeof(pid_t));
+	struct thread_map *threads = thread_map__alloc(max_threads);
+
 	if (threads == NULL)
 		goto out;
 
@@ -185,8 +194,7 @@ static struct thread_map *thread_map__new_by_pid_str(const char *pid_str)
 			goto out_free_threads;
 
 		total_tasks += items;
-		nt = realloc(threads, (sizeof(*threads) +
-				       sizeof(pid_t) * total_tasks));
+		nt = thread_map__realloc(threads, total_tasks);
 		if (nt == NULL)
 			goto out_free_namelist;
 
@@ -216,7 +224,7 @@ out_free_threads:
 
 struct thread_map *thread_map__new_dummy(void)
 {
-	struct thread_map *threads = malloc(sizeof(*threads) + sizeof(pid_t));
+	struct thread_map *threads = thread_map__alloc(1);
 
 	if (threads != NULL) {
 		threads->map[0]	= -1;
@@ -253,7 +261,7 @@ static struct thread_map *thread_map__new_by_tid_str(const char *tid_str)
 			continue;
 
 		ntasks++;
-		nt = realloc(threads, sizeof(*threads) + sizeof(pid_t) * ntasks);
+		nt = thread_map__realloc(threads, ntasks);
 
 		if (nt == NULL)
 			goto out_free_threads;
diff --git a/tools/perf/util/tool.h b/tools/perf/util/tool.h
index 51d9e56c0f84..c307dd438286 100644
--- a/tools/perf/util/tool.h
+++ b/tools/perf/util/tool.h
@@ -3,6 +3,8 @@
 
 #include <stdbool.h>
 
+#include <linux/types.h>
+
 struct perf_session;
 union perf_event;
 struct perf_evlist;
@@ -29,6 +31,9 @@ typedef int (*event_op2)(struct perf_tool *tool, union perf_event *event,
 typedef int (*event_oe)(struct perf_tool *tool, union perf_event *event,
 			struct ordered_events *oe);
 
+typedef s64 (*event_op3)(struct perf_tool *tool, union perf_event *event,
+			 struct perf_session *session);
+
 struct perf_tool {
 	event_sample	sample,
 			read;
@@ -38,13 +43,19 @@ struct perf_tool {
 			fork,
 			exit,
 			lost,
+			lost_samples,
+			aux,
+			itrace_start,
 			throttle,
 			unthrottle;
 	event_attr_op	attr;
 	event_op2	tracing_data;
 	event_oe	finished_round;
 	event_op2	build_id,
-			id_index;
+			id_index,
+			auxtrace_info,
+			auxtrace_error;
+	event_op3	auxtrace;
 	bool		ordered_events;
 	bool		ordering_requires_timestamps;
 };
diff --git a/tools/perf/util/trace-event-parse.c b/tools/perf/util/trace-event-parse.c
index 25d6c737be3e..d4957418657e 100644
--- a/tools/perf/util/trace-event-parse.c
+++ b/tools/perf/util/trace-event-parse.c
@@ -173,7 +173,7 @@ void parse_ftrace_printk(struct pevent *pevent,
 	char *line;
 	char *next = NULL;
 	char *addr_str;
-	char *fmt;
+	char *fmt = NULL;
 
 	line = strtok_r(file, "\n", &next);
 	while (line) {
diff --git a/tools/perf/util/unwind-libunwind.c b/tools/perf/util/unwind-libunwind.c
index 7b09a443a280..4c00507ee3fd 100644
--- a/tools/perf/util/unwind-libunwind.c
+++ b/tools/perf/util/unwind-libunwind.c
@@ -269,13 +269,14 @@ static int read_unwind_spec_eh_frame(struct dso *dso, struct machine *machine,
 	u64 offset = dso->data.eh_frame_hdr_offset;
 
 	if (offset == 0) {
-		fd = dso__data_fd(dso, machine);
+		fd = dso__data_get_fd(dso, machine);
 		if (fd < 0)
 			return -EINVAL;
 
 		/* Check the .eh_frame section for unwinding info */
 		offset = elf_section_offset(fd, ".eh_frame_hdr");
 		dso->data.eh_frame_hdr_offset = offset;
+		dso__data_put_fd(dso);
 	}
 
 	if (offset)
@@ -294,13 +295,14 @@ static int read_unwind_spec_debug_frame(struct dso *dso,
 	u64 ofs = dso->data.debug_frame_offset;
 
 	if (ofs == 0) {
-		fd = dso__data_fd(dso, machine);
+		fd = dso__data_get_fd(dso, machine);
 		if (fd < 0)
 			return -EINVAL;
 
 		/* Check the .debug_frame section for unwinding info */
 		ofs = elf_section_offset(fd, ".debug_frame");
 		dso->data.debug_frame_offset = ofs;
+		dso__data_put_fd(dso);
 	}
 
 	*offset = ofs;
@@ -353,10 +355,13 @@ find_proc_info(unw_addr_space_t as, unw_word_t ip, unw_proc_info_t *pi,
 #ifndef NO_LIBUNWIND_DEBUG_FRAME
 	/* Check the .debug_frame section for unwinding info */
 	if (!read_unwind_spec_debug_frame(map->dso, ui->machine, &segbase)) {
-		int fd = dso__data_fd(map->dso, ui->machine);
+		int fd = dso__data_get_fd(map->dso, ui->machine);
 		int is_exec = elf_is_exec(fd, map->dso->name);
 		unw_word_t base = is_exec ? 0 : map->start;
 
+		if (fd >= 0)
+			dso__data_put_fd(map->dso);
+
 		memset(&di, 0, sizeof(di));
 		if (dwarf_find_debug_frame(0, &di, ip, base, map->dso->name,
 					   map->start, map->end))
diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c
index 4ee6d0d4c993..edc2d633b332 100644
--- a/tools/perf/util/util.c
+++ b/tools/perf/util/util.c
@@ -72,20 +72,60 @@ int mkdir_p(char *path, mode_t mode)
 	return (stat(path, &st) && mkdir(path, mode)) ? -1 : 0;
 }
 
-static int slow_copyfile(const char *from, const char *to, mode_t mode)
+int rm_rf(char *path)
+{
+	DIR *dir;
+	int ret = 0;
+	struct dirent *d;
+	char namebuf[PATH_MAX];
+
+	dir = opendir(path);
+	if (dir == NULL)
+		return 0;
+
+	while ((d = readdir(dir)) != NULL && !ret) {
+		struct stat statbuf;
+
+		if (!strcmp(d->d_name, ".") || !strcmp(d->d_name, ".."))
+			continue;
+
+		scnprintf(namebuf, sizeof(namebuf), "%s/%s",
+			  path, d->d_name);
+
+		ret = stat(namebuf, &statbuf);
+		if (ret < 0) {
+			pr_debug("stat failed: %s\n", namebuf);
+			break;
+		}
+
+		if (S_ISREG(statbuf.st_mode))
+			ret = unlink(namebuf);
+		else if (S_ISDIR(statbuf.st_mode))
+			ret = rm_rf(namebuf);
+		else {
+			pr_debug("unknown file: %s\n", namebuf);
+			ret = -1;
+		}
+	}
+	closedir(dir);
+
+	if (ret < 0)
+		return ret;
+
+	return rmdir(path);
+}
+
+static int slow_copyfile(const char *from, const char *to)
 {
 	int err = -1;
 	char *line = NULL;
 	size_t n;
 	FILE *from_fp = fopen(from, "r"), *to_fp;
-	mode_t old_umask;
 
 	if (from_fp == NULL)
 		goto out;
 
-	old_umask = umask(mode ^ 0777);
 	to_fp = fopen(to, "w");
-	umask(old_umask);
 	if (to_fp == NULL)
 		goto out_fclose_from;
 
@@ -102,42 +142,81 @@ out:
 	return err;
 }
 
+int copyfile_offset(int ifd, loff_t off_in, int ofd, loff_t off_out, u64 size)
+{
+	void *ptr;
+	loff_t pgoff;
+
+	pgoff = off_in & ~(page_size - 1);
+	off_in -= pgoff;
+
+	ptr = mmap(NULL, off_in + size, PROT_READ, MAP_PRIVATE, ifd, pgoff);
+	if (ptr == MAP_FAILED)
+		return -1;
+
+	while (size) {
+		ssize_t ret = pwrite(ofd, ptr + off_in, size, off_out);
+		if (ret < 0 && errno == EINTR)
+			continue;
+		if (ret <= 0)
+			break;
+
+		size -= ret;
+		off_in += ret;
+		off_out -= ret;
+	}
+	munmap(ptr, off_in + size);
+
+	return size ? -1 : 0;
+}
+
 int copyfile_mode(const char *from, const char *to, mode_t mode)
 {
 	int fromfd, tofd;
 	struct stat st;
-	void *addr;
 	int err = -1;
+	char *tmp = NULL, *ptr = NULL;
 
 	if (stat(from, &st))
 		goto out;
 
-	if (st.st_size == 0) /* /proc? do it slowly... */
-		return slow_copyfile(from, to, mode);
-
-	fromfd = open(from, O_RDONLY);
-	if (fromfd < 0)
+	/* extra 'x' at the end is to reserve space for '.' */
+	if (asprintf(&tmp, "%s.XXXXXXx", to) < 0) {
+		tmp = NULL;
 		goto out;
+	}
+	ptr = strrchr(tmp, '/');
+	if (!ptr)
+		goto out;
+	ptr = memmove(ptr + 1, ptr, strlen(ptr) - 1);
+	*ptr = '.';
 
-	tofd = creat(to, mode);
+	tofd = mkstemp(tmp);
 	if (tofd < 0)
-		goto out_close_from;
+		goto out;
+
+	if (fchmod(tofd, mode))
+		goto out_close_to;
+
+	if (st.st_size == 0) { /* /proc? do it slowly... */
+		err = slow_copyfile(from, tmp);
+		goto out_close_to;
+	}
 
-	addr = mmap(NULL, st.st_size, PROT_READ, MAP_PRIVATE, fromfd, 0);
-	if (addr == MAP_FAILED)
+	fromfd = open(from, O_RDONLY);
+	if (fromfd < 0)
 		goto out_close_to;
 
-	if (write(tofd, addr, st.st_size) == st.st_size)
-		err = 0;
+	err = copyfile_offset(fromfd, 0, tofd, 0, st.st_size);
 
-	munmap(addr, st.st_size);
+	close(fromfd);
 out_close_to:
 	close(tofd);
-	if (err)
-		unlink(to);
-out_close_from:
-	close(fromfd);
+	if (!err)
+		err = link(tmp, to);
+	unlink(tmp);
 out:
+	free(tmp);
 	return err;
 }
 
diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h
index 1ff23e04ad27..8bce58b47a82 100644
--- a/tools/perf/util/util.h
+++ b/tools/perf/util/util.h
@@ -249,14 +249,20 @@ static inline int sane_case(int x, int high)
 }
 
 int mkdir_p(char *path, mode_t mode);
+int rm_rf(char *path);
 int copyfile(const char *from, const char *to);
 int copyfile_mode(const char *from, const char *to, mode_t mode);
+int copyfile_offset(int fromfd, loff_t from_ofs, int tofd, loff_t to_ofs, u64 size);
 
 s64 perf_atoll(const char *str);
 char **argv_split(const char *str, int *argcp);
 void argv_free(char **argv);
 bool strglobmatch(const char *str, const char *pat);
 bool strlazymatch(const char *str, const char *pat);
+static inline bool strisglob(const char *str)
+{
+	return strpbrk(str, "*?[") != NULL;
+}
 int strtailcmp(const char *s1, const char *s2);
 char *strxfrchar(char *s, char from, char to);
 unsigned long convert_unit(unsigned long value, char *unit);
diff --git a/tools/perf/util/vdso.c b/tools/perf/util/vdso.c
index 5c7dd796979d..4b89118f158d 100644
--- a/tools/perf/util/vdso.c
+++ b/tools/perf/util/vdso.c
@@ -101,7 +101,7 @@ static char *get_file(struct vdso_file *vdso_file)
 	return vdso;
 }
 
-void vdso__exit(struct machine *machine)
+void machine__exit_vdso(struct machine *machine)
 {
 	struct vdso_info *vdso_info = machine->vdso_info;
 
@@ -120,14 +120,14 @@ void vdso__exit(struct machine *machine)
 	zfree(&machine->vdso_info);
 }
 
-static struct dso *vdso__new(struct machine *machine, const char *short_name,
-			     const char *long_name)
+static struct dso *__machine__addnew_vdso(struct machine *machine, const char *short_name,
+					  const char *long_name)
 {
 	struct dso *dso;
 
 	dso = dso__new(short_name);
 	if (dso != NULL) {
-		dsos__add(&machine->user_dsos, dso);
+		__dsos__add(&machine->dsos, dso);
 		dso__set_long_name(dso, long_name, false);
 	}
 
@@ -230,27 +230,31 @@ static const char *vdso__get_compat_file(struct vdso_file *vdso_file)
 	return vdso_file->temp_file_name;
 }
 
-static struct dso *vdso__findnew_compat(struct machine *machine,
-					struct vdso_file *vdso_file)
+static struct dso *__machine__findnew_compat(struct machine *machine,
+					     struct vdso_file *vdso_file)
 {
 	const char *file_name;
 	struct dso *dso;
 
-	dso = dsos__find(&machine->user_dsos, vdso_file->dso_name, true);
+	pthread_rwlock_wrlock(&machine->dsos.lock);
+	dso = __dsos__find(&machine->dsos, vdso_file->dso_name, true);
 	if (dso)
-		return dso;
+		goto out_unlock;
 
 	file_name = vdso__get_compat_file(vdso_file);
 	if (!file_name)
-		return NULL;
+		goto out_unlock;
 
-	return vdso__new(machine, vdso_file->dso_name, file_name);
+	dso = __machine__addnew_vdso(machine, vdso_file->dso_name, file_name);
+out_unlock:
+	pthread_rwlock_unlock(&machine->dsos.lock);
+	return dso;
 }
 
-static int vdso__dso_findnew_compat(struct machine *machine,
-				    struct thread *thread,
-				    struct vdso_info *vdso_info,
-				    struct dso **dso)
+static int __machine__findnew_vdso_compat(struct machine *machine,
+					  struct thread *thread,
+					  struct vdso_info *vdso_info,
+					  struct dso **dso)
 {
 	enum dso_type dso_type;
 
@@ -267,10 +271,10 @@ static int vdso__dso_findnew_compat(struct machine *machine,
 
 	switch (dso_type) {
 	case DSO__TYPE_32BIT:
-		*dso = vdso__findnew_compat(machine, &vdso_info->vdso32);
+		*dso = __machine__findnew_compat(machine, &vdso_info->vdso32);
 		return 1;
 	case DSO__TYPE_X32BIT:
-		*dso = vdso__findnew_compat(machine, &vdso_info->vdsox32);
+		*dso = __machine__findnew_compat(machine, &vdso_info->vdsox32);
 		return 1;
 	case DSO__TYPE_UNKNOWN:
 	case DSO__TYPE_64BIT:
@@ -281,35 +285,37 @@ static int vdso__dso_findnew_compat(struct machine *machine,
 
 #endif
 
-struct dso *vdso__dso_findnew(struct machine *machine,
-			      struct thread *thread __maybe_unused)
+struct dso *machine__findnew_vdso(struct machine *machine,
+				  struct thread *thread __maybe_unused)
 {
 	struct vdso_info *vdso_info;
-	struct dso *dso;
+	struct dso *dso = NULL;
 
+	pthread_rwlock_wrlock(&machine->dsos.lock);
 	if (!machine->vdso_info)
 		machine->vdso_info = vdso_info__new();
 
 	vdso_info = machine->vdso_info;
 	if (!vdso_info)
-		return NULL;
+		goto out_unlock;
 
 #if BITS_PER_LONG == 64
-	if (vdso__dso_findnew_compat(machine, thread, vdso_info, &dso))
-		return dso;
+	if (__machine__findnew_vdso_compat(machine, thread, vdso_info, &dso))
+		goto out_unlock;
 #endif
 
-	dso = dsos__find(&machine->user_dsos, DSO__NAME_VDSO, true);
+	dso = __dsos__find(&machine->dsos, DSO__NAME_VDSO, true);
 	if (!dso) {
 		char *file;
 
 		file = get_file(&vdso_info->vdso);
-		if (!file)
-			return NULL;
-
-		dso = vdso__new(machine, DSO__NAME_VDSO, file);
+		if (file)
+			dso = __machine__addnew_vdso(machine, DSO__NAME_VDSO, file);
 	}
 
+out_unlock:
+	dso__get(dso);
+	pthread_rwlock_unlock(&machine->dsos.lock);
 	return dso;
 }
 
diff --git a/tools/perf/util/vdso.h b/tools/perf/util/vdso.h
index d97da1616f0c..cdc4fabfc212 100644
--- a/tools/perf/util/vdso.h
+++ b/tools/perf/util/vdso.h
@@ -23,7 +23,7 @@ bool dso__is_vdso(struct dso *dso);
 struct machine;
 struct thread;
 
-struct dso *vdso__dso_findnew(struct machine *machine, struct thread *thread);
-void vdso__exit(struct machine *machine);
+struct dso *machine__findnew_vdso(struct machine *machine, struct thread *thread);
+void machine__exit_vdso(struct machine *machine);
 
 #endif /* __PERF_VDSO__ */
diff --git a/tools/perf/util/xyarray.c b/tools/perf/util/xyarray.c
index 22afbf6c536a..c10ba41ef3f6 100644
--- a/tools/perf/util/xyarray.c
+++ b/tools/perf/util/xyarray.c
@@ -9,11 +9,19 @@ struct xyarray *xyarray__new(int xlen, int ylen, size_t entry_size)
 	if (xy != NULL) {
 		xy->entry_size = entry_size;
 		xy->row_size   = row_size;
+		xy->entries    = xlen * ylen;
 	}
 
 	return xy;
 }
 
+void xyarray__reset(struct xyarray *xy)
+{
+	size_t n = xy->entries * xy->entry_size;
+
+	memset(xy->contents, 0, n);
+}
+
 void xyarray__delete(struct xyarray *xy)
 {
 	free(xy);
diff --git a/tools/perf/util/xyarray.h b/tools/perf/util/xyarray.h
index c488a07275dd..7f30af371b7e 100644
--- a/tools/perf/util/xyarray.h
+++ b/tools/perf/util/xyarray.h
@@ -6,11 +6,13 @@
 struct xyarray {
 	size_t row_size;
 	size_t entry_size;
+	size_t entries;
 	char contents[];
 };
 
 struct xyarray *xyarray__new(int xlen, int ylen, size_t entry_size);
 void xyarray__delete(struct xyarray *xy);
+void xyarray__reset(struct xyarray *xy);
 
 static inline void *xyarray__entry(struct xyarray *xy, int x, int y)
 {
author	Linus Torvalds <torvalds@linux-foundation.org>	2015-06-22 15:19:21 -0700
committer	Linus Torvalds <torvalds@linux-foundation.org>	2015-06-22 15:19:21 -0700
commit	c58267e9fa7b0345dd9006939254701e3622ca6a (patch)
tree	9a96adabaa1c61ecbb9e5e8653d5085dad27ef07
parent	1bf7067c6e173dc10411704db48338ed69c05565 (diff)
parent	a9a3cd900fbbcbf837d65653105e7bfc583ced09 (diff)
download	lwn-c58267e9fa7b0345dd9006939254701e3622ca6a.tar.gz lwn-c58267e9fa7b0345dd9006939254701e3622ca6a.zip