Merge remote-tracking branch 'tip/auto-latest'

54 files changed, 1858 insertions, 311 deletions

diff --git a/tools/lib/lockdep/include/liblockdep/mutex.h b/tools/lib/lockdep/include/liblockdep/mutex.h
index c342f7087147..ee53a42818ca 100644
--- a/tools/lib/lockdep/include/liblockdep/mutex.h
+++ b/tools/lib/lockdep/include/liblockdep/mutex.h
@@ -35,7 +35,7 @@ static inline int __mutex_init(liblockdep_pthread_mutex_t *lock,
 
 static inline int liblockdep_pthread_mutex_lock(liblockdep_pthread_mutex_t *lock)
 {
-	lock_acquire(&lock->dep_map, 0, 0, 0, 2, NULL, (unsigned long)_RET_IP_);
+	lock_acquire(&lock->dep_map, 0, 0, 0, 1, NULL, (unsigned long)_RET_IP_);
 	return pthread_mutex_lock(&lock->mutex);
 }
 
@@ -47,7 +47,7 @@ static inline int liblockdep_pthread_mutex_unlock(liblockdep_pthread_mutex_t *lo
 
 static inline int liblockdep_pthread_mutex_trylock(liblockdep_pthread_mutex_t *lock)
 {
-	lock_acquire(&lock->dep_map, 0, 1, 0, 2, NULL, (unsigned long)_RET_IP_);
+	lock_acquire(&lock->dep_map, 0, 1, 0, 1, NULL, (unsigned long)_RET_IP_);
 	return pthread_mutex_trylock(&lock->mutex) == 0 ? 1 : 0;
 }
 
diff --git a/tools/lib/lockdep/include/liblockdep/rwlock.h b/tools/lib/lockdep/include/liblockdep/rwlock.h
index a680ab8c2e36..4ec03f861551 100644
--- a/tools/lib/lockdep/include/liblockdep/rwlock.h
+++ b/tools/lib/lockdep/include/liblockdep/rwlock.h
@@ -36,7 +36,7 @@ static inline int __rwlock_init(liblockdep_pthread_rwlock_t *lock,
 
 static inline int liblockdep_pthread_rwlock_rdlock(liblockdep_pthread_rwlock_t *lock)
 {
-	lock_acquire(&lock->dep_map, 0, 0, 2, 2, NULL, (unsigned long)_RET_IP_);
+	lock_acquire(&lock->dep_map, 0, 0, 2, 1, NULL, (unsigned long)_RET_IP_);
 	return pthread_rwlock_rdlock(&lock->rwlock);
 
 }
@@ -49,19 +49,19 @@ static inline int liblockdep_pthread_rwlock_unlock(liblockdep_pthread_rwlock_t *
 
 static inline int liblockdep_pthread_rwlock_wrlock(liblockdep_pthread_rwlock_t *lock)
 {
-	lock_acquire(&lock->dep_map, 0, 0, 0, 2, NULL, (unsigned long)_RET_IP_);
+	lock_acquire(&lock->dep_map, 0, 0, 0, 1, NULL, (unsigned long)_RET_IP_);
 	return pthread_rwlock_wrlock(&lock->rwlock);
 }
 
 static inline int liblockdep_pthread_rwlock_tryrdlock(liblockdep_pthread_rwlock_t *lock)
 {
-	lock_acquire(&lock->dep_map, 0, 1, 2, 2, NULL, (unsigned long)_RET_IP_);
+	lock_acquire(&lock->dep_map, 0, 1, 2, 1, NULL, (unsigned long)_RET_IP_);
 	return pthread_rwlock_tryrdlock(&lock->rwlock) == 0 ? 1 : 0;
 }
 
 static inline int liblockdep_pthread_rwlock_trywlock(liblockdep_pthread_rwlock_t *lock)
 {
-	lock_acquire(&lock->dep_map, 0, 1, 0, 2, NULL, (unsigned long)_RET_IP_);
+	lock_acquire(&lock->dep_map, 0, 1, 0, 1, NULL, (unsigned long)_RET_IP_);
 	return pthread_rwlock_trywlock(&lock->rwlock) == 0 ? 1 : 0;
 }
 
diff --git a/tools/lib/lockdep/preload.c b/tools/lib/lockdep/preload.c
index 23bd69cb5ade..6f803609e498 100644
--- a/tools/lib/lockdep/preload.c
+++ b/tools/lib/lockdep/preload.c
@@ -92,7 +92,7 @@ enum { none, prepare, done, } __init_state;
 static void init_preload(void);
 static void try_init_preload(void)
 {
-	if (!__init_state != done)
+	if (__init_state != done)
 		init_preload();
 }
 
@@ -252,7 +252,7 @@ int pthread_mutex_lock(pthread_mutex_t *mutex)
 
 	try_init_preload();
 
-	lock_acquire(&__get_lock(mutex)->dep_map, 0, 0, 0, 2, NULL,
+	lock_acquire(&__get_lock(mutex)->dep_map, 0, 0, 0, 1, NULL,
 			(unsigned long)_RET_IP_);
 	/*
 	 * Here's the thing with pthread mutexes: unlike the kernel variant,
@@ -281,7 +281,7 @@ int pthread_mutex_trylock(pthread_mutex_t *mutex)
 
 	try_init_preload();
 
-	lock_acquire(&__get_lock(mutex)->dep_map, 0, 1, 0, 2, NULL, (unsigned long)_RET_IP_);
+	lock_acquire(&__get_lock(mutex)->dep_map, 0, 1, 0, 1, NULL, (unsigned long)_RET_IP_);
 	r = ll_pthread_mutex_trylock(mutex);
 	if (r)
 		lock_release(&__get_lock(mutex)->dep_map, 0, (unsigned long)_RET_IP_);
@@ -303,7 +303,7 @@ int pthread_mutex_unlock(pthread_mutex_t *mutex)
 	 */
 	r = ll_pthread_mutex_unlock(mutex);
 	if (r)
-		lock_acquire(&__get_lock(mutex)->dep_map, 0, 0, 0, 2, NULL, (unsigned long)_RET_IP_);
+		lock_acquire(&__get_lock(mutex)->dep_map, 0, 0, 0, 1, NULL, (unsigned long)_RET_IP_);
 
 	return r;
 }
@@ -352,7 +352,7 @@ int pthread_rwlock_rdlock(pthread_rwlock_t *rwlock)
 
         init_preload();
 
-	lock_acquire(&__get_lock(rwlock)->dep_map, 0, 0, 2, 2, NULL, (unsigned long)_RET_IP_);
+	lock_acquire(&__get_lock(rwlock)->dep_map, 0, 0, 2, 1, NULL, (unsigned long)_RET_IP_);
 	r = ll_pthread_rwlock_rdlock(rwlock);
 	if (r)
 		lock_release(&__get_lock(rwlock)->dep_map, 0, (unsigned long)_RET_IP_);
@@ -366,7 +366,7 @@ int pthread_rwlock_tryrdlock(pthread_rwlock_t *rwlock)
 
         init_preload();
 
-	lock_acquire(&__get_lock(rwlock)->dep_map, 0, 1, 2, 2, NULL, (unsigned long)_RET_IP_);
+	lock_acquire(&__get_lock(rwlock)->dep_map, 0, 1, 2, 1, NULL, (unsigned long)_RET_IP_);
 	r = ll_pthread_rwlock_tryrdlock(rwlock);
 	if (r)
 		lock_release(&__get_lock(rwlock)->dep_map, 0, (unsigned long)_RET_IP_);
@@ -380,7 +380,7 @@ int pthread_rwlock_trywrlock(pthread_rwlock_t *rwlock)
 
         init_preload();
 
-	lock_acquire(&__get_lock(rwlock)->dep_map, 0, 1, 0, 2, NULL, (unsigned long)_RET_IP_);
+	lock_acquire(&__get_lock(rwlock)->dep_map, 0, 1, 0, 1, NULL, (unsigned long)_RET_IP_);
 	r = ll_pthread_rwlock_trywrlock(rwlock);
 	if (r)
                 lock_release(&__get_lock(rwlock)->dep_map, 0, (unsigned long)_RET_IP_);
@@ -394,7 +394,7 @@ int pthread_rwlock_wrlock(pthread_rwlock_t *rwlock)
 
         init_preload();
 
-	lock_acquire(&__get_lock(rwlock)->dep_map, 0, 0, 0, 2, NULL, (unsigned long)_RET_IP_);
+	lock_acquire(&__get_lock(rwlock)->dep_map, 0, 0, 0, 1, NULL, (unsigned long)_RET_IP_);
 	r = ll_pthread_rwlock_wrlock(rwlock);
 	if (r)
 		lock_release(&__get_lock(rwlock)->dep_map, 0, (unsigned long)_RET_IP_);
@@ -411,7 +411,7 @@ int pthread_rwlock_unlock(pthread_rwlock_t *rwlock)
 	lock_release(&__get_lock(rwlock)->dep_map, 0, (unsigned long)_RET_IP_);
 	r = ll_pthread_rwlock_unlock(rwlock);
 	if (r)
-		lock_acquire(&__get_lock(rwlock)->dep_map, 0, 0, 0, 2, NULL, (unsigned long)_RET_IP_);
+		lock_acquire(&__get_lock(rwlock)->dep_map, 0, 0, 0, 1, NULL, (unsigned long)_RET_IP_);
 
 	return r;
 }
@@ -439,8 +439,6 @@ __attribute__((constructor)) static void init_preload(void)
 	ll_pthread_rwlock_unlock = dlsym(RTLD_NEXT, "pthread_rwlock_unlock");
 #endif
 
-	printf("%p\n", ll_pthread_mutex_trylock);fflush(stdout);
-
 	lockdep_init();
 
 	__init_state = done;
diff --git a/tools/lib/traceevent/event-parse.c b/tools/lib/traceevent/event-parse.c
index 93825a17dcce..cf3a44bf1ec3 100644
--- a/tools/lib/traceevent/event-parse.c
+++ b/tools/lib/traceevent/event-parse.c
@@ -2395,7 +2395,7 @@ process_flags(struct event_format *event, struct print_arg *arg, char **tok)
 {
 	struct print_arg *field;
 	enum event_type type;
-	char *token;
+	char *token = NULL;
 
 	memset(arg, 0, sizeof(*arg));
 	arg->type = PRINT_FLAGS;
@@ -2448,7 +2448,7 @@ process_symbols(struct event_format *event, struct print_arg *arg, char **tok)
 {
 	struct print_arg *field;
 	enum event_type type;
-	char *token;
+	char *token = NULL;
 
 	memset(arg, 0, sizeof(*arg));
 	arg->type = PRINT_SYMBOL;
@@ -2487,7 +2487,7 @@ process_hex(struct event_format *event, struct print_arg *arg, char **tok)
 {
 	struct print_arg *field;
 	enum event_type type;
-	char *token;
+	char *token = NULL;
 
 	memset(arg, 0, sizeof(*arg));
 	arg->type = PRINT_HEX;
diff --git a/tools/lib/traceevent/plugin_cfg80211.c b/tools/lib/traceevent/plugin_cfg80211.c
index c066b25905f8..4592d8438318 100644
--- a/tools/lib/traceevent/plugin_cfg80211.c
+++ b/tools/lib/traceevent/plugin_cfg80211.c
@@ -5,8 +5,7 @@
 #include "event-parse.h"
 
 static unsigned long long
-process___le16_to_cpup(struct trace_seq *s,
-		       unsigned long long *args)
+process___le16_to_cpup(struct trace_seq *s, unsigned long long *args)
 {
 	uint16_t *val = (uint16_t *) (unsigned long) args[0];
 	return val ? (long long) le16toh(*val) : 0;
diff --git a/tools/lib/traceevent/plugin_jbd2.c b/tools/lib/traceevent/plugin_jbd2.c
index 0db714c721be..5c23d5bd27ce 100644
--- a/tools/lib/traceevent/plugin_jbd2.c
+++ b/tools/lib/traceevent/plugin_jbd2.c
@@ -30,8 +30,7 @@
 #define MINOR(dev)	((unsigned int) ((dev) & MINORMASK))
 
 static unsigned long long
-process_jbd2_dev_to_name(struct trace_seq *s,
-			 unsigned long long *args)
+process_jbd2_dev_to_name(struct trace_seq *s, unsigned long long *args)
 {
 	unsigned int dev = args[0];
 
@@ -40,8 +39,7 @@ process_jbd2_dev_to_name(struct trace_seq *s,
 }
 
 static unsigned long long
-process_jiffies_to_msecs(struct trace_seq *s,
-			 unsigned long long *args)
+process_jiffies_to_msecs(struct trace_seq *s, unsigned long long *args)
 {
 	unsigned long long jiffies = args[0];
 
diff --git a/tools/lib/traceevent/plugin_kvm.c b/tools/lib/traceevent/plugin_kvm.c
index 9e0e8c61b43b..88fe83dff7cd 100644
--- a/tools/lib/traceevent/plugin_kvm.c
+++ b/tools/lib/traceevent/plugin_kvm.c
@@ -240,25 +240,38 @@ static const char *find_exit_reason(unsigned isa, int val)
 	for (i = 0; strings[i].val >= 0; i++)
 		if (strings[i].val == val)
 			break;
-	if (strings[i].str)
-		return strings[i].str;
-	return "UNKNOWN";
+
+	return strings[i].str;
 }
 
-static int kvm_exit_handler(struct trace_seq *s, struct pevent_record *record,
-			    struct event_format *event, void *context)
+static int print_exit_reason(struct trace_seq *s, struct pevent_record *record,
+			     struct event_format *event, const char *field)
 {
 	unsigned long long isa;
 	unsigned long long val;
-	unsigned long long info1 = 0, info2 = 0;
+	const char *reason;
 
-	if (pevent_get_field_val(s, event, "exit_reason", record, &val, 1) < 0)
+	if (pevent_get_field_val(s, event, field, record, &val, 1) < 0)
 		return -1;
 
 	if (pevent_get_field_val(s, event, "isa", record, &isa, 0) < 0)
 		isa = 1;
 
-	trace_seq_printf(s, "reason %s", find_exit_reason(isa, val));
+	reason = find_exit_reason(isa, val);
+	if (reason)
+		trace_seq_printf(s, "reason %s", reason);
+	else
+		trace_seq_printf(s, "reason UNKNOWN (%llu)", val);
+	return 0;
+}
+
+static int kvm_exit_handler(struct trace_seq *s, struct pevent_record *record,
+			    struct event_format *event, void *context)
+{
+	unsigned long long info1 = 0, info2 = 0;
+
+	if (print_exit_reason(s, record, event, "exit_reason") < 0)
+		return -1;
 
 	pevent_print_num_field(s, " rip 0x%lx", event, "guest_rip", record, 1);
 
@@ -313,6 +326,29 @@ static int kvm_emulate_insn_handler(struct trace_seq *s,
 	return 0;
 }
 
+
+static int kvm_nested_vmexit_inject_handler(struct trace_seq *s, struct pevent_record *record,
+					    struct event_format *event, void *context)
+{
+	if (print_exit_reason(s, record, event, "exit_code") < 0)
+		return -1;
+
+	pevent_print_num_field(s, " info1 %llx", event, "exit_info1", record, 1);
+	pevent_print_num_field(s, " info2 %llx", event, "exit_info2", record, 1);
+	pevent_print_num_field(s, " int_info %llx", event, "exit_int_info", record, 1);
+	pevent_print_num_field(s, " int_info_err %llx", event, "exit_int_info_err", record, 1);
+
+	return 0;
+}
+
+static int kvm_nested_vmexit_handler(struct trace_seq *s, struct pevent_record *record,
+				     struct event_format *event, void *context)
+{
+	pevent_print_num_field(s, "rip %llx ", event, "rip", record, 1);
+
+	return kvm_nested_vmexit_inject_handler(s, record, event, context);
+}
+
 union kvm_mmu_page_role {
 	unsigned word;
 	struct {
@@ -409,6 +445,12 @@ int PEVENT_PLUGIN_LOADER(struct pevent *pevent)
 	pevent_register_event_handler(pevent, -1, "kvm", "kvm_emulate_insn",
 				      kvm_emulate_insn_handler, NULL);
 
+	pevent_register_event_handler(pevent, -1, "kvm", "kvm_nested_vmexit",
+				      kvm_nested_vmexit_handler, NULL);
+
+	pevent_register_event_handler(pevent, -1, "kvm", "kvm_nested_vmexit_inject",
+				      kvm_nested_vmexit_inject_handler, NULL);
+
 	pevent_register_event_handler(pevent, -1, "kvmmmu", "kvm_mmu_get_page",
 				      kvm_mmu_get_page_handler, NULL);
 
@@ -443,6 +485,12 @@ void PEVENT_PLUGIN_UNLOADER(struct pevent *pevent)
 	pevent_unregister_event_handler(pevent, -1, "kvm", "kvm_emulate_insn",
 					kvm_emulate_insn_handler, NULL);
 
+	pevent_unregister_event_handler(pevent, -1, "kvm", "kvm_nested_vmexit",
+					kvm_nested_vmexit_handler, NULL);
+
+	pevent_unregister_event_handler(pevent, -1, "kvm", "kvm_nested_vmexit_inject",
+					kvm_nested_vmexit_inject_handler, NULL);
+
 	pevent_unregister_event_handler(pevent, -1, "kvmmmu", "kvm_mmu_get_page",
 					kvm_mmu_get_page_handler, NULL);
 
diff --git a/tools/perf/Documentation/perf-bench.txt b/tools/perf/Documentation/perf-bench.txt
index 4464ad770d51..f6480cbf309b 100644
--- a/tools/perf/Documentation/perf-bench.txt
+++ b/tools/perf/Documentation/perf-bench.txt
@@ -16,6 +16,10 @@ This 'perf bench' command is a general framework for benchmark suites.
 
 COMMON OPTIONS
 --------------
+-r::
+--repeat=::
+Specify amount of times to repeat the run (default 10).
+
 -f::
 --format=::
 Specify format style.
diff --git a/tools/perf/Documentation/perf-timechart.txt b/tools/perf/Documentation/perf-timechart.txt
index 5e0f986dff38..df98d1c82688 100644
--- a/tools/perf/Documentation/perf-timechart.txt
+++ b/tools/perf/Documentation/perf-timechart.txt
@@ -15,10 +15,20 @@ DESCRIPTION
 There are two variants of perf timechart:
 
   'perf timechart record <command>' to record the system level events
-  of an arbitrary workload.
+  of an arbitrary workload. By default timechart records only scheduler
+  and CPU events (task switches, running times, CPU power states, etc),
+  but it's possible to record IO (disk, network) activity using -I argument.
 
   'perf timechart' to turn a trace into a Scalable Vector Graphics file,
-  that can be viewed with popular SVG viewers such as 'Inkscape'.
+  that can be viewed with popular SVG viewers such as 'Inkscape'. Depending
+  on the events in the perf.data file, timechart will contain scheduler/cpu
+  events or IO events.
+
+  In IO mode, every bar has two charts: upper and lower.
+  Upper bar shows incoming events (disk reads, ingress network packets).
+  Lower bar shows outgoing events (disk writes, egress network packets).
+  There are also poll bars which show how much time application spent
+  in poll/epoll/select syscalls.
 
 TIMECHART OPTIONS
 -----------------
@@ -54,6 +64,19 @@ TIMECHART OPTIONS
 	duration or tasks with given name. If number is given it's interpreted
 	as number of nanoseconds. If non-numeric string is given it's
 	interpreted as task name.
+--io-skip-eagain::
+	Don't draw EAGAIN IO events.
+--io-min-time=<nsecs>::
+	Draw small events as if they lasted min-time. Useful when you need
+	to see very small and fast IO. It's possible to specify ms or us
+	suffix to specify time in milliseconds or microseconds.
+	Default value is 1ms.
+--io-merge-dist=<nsecs>::
+	Merge events that are merge-dist nanoseconds apart.
+	Reduces number of figures on the SVG and makes it more render-friendly.
+	It's possible to specify ms or us suffix to specify time in
+	milliseconds or microseconds.
+	Default value is 1us.
 
 RECORD OPTIONS
 --------------
@@ -63,6 +86,9 @@ RECORD OPTIONS
 -T::
 --tasks-only::
         Record only tasks-related events
+-I::
+--io-only::
+        Record only io-related events
 -g::
 --callchain::
         Do call-graph (stack chain/backtrace) recording
@@ -87,6 +113,14 @@ Record system-wide timechart:
 
   $ perf timechart --highlight gcc
 
+Record system-wide IO events:
+
+  $ perf timechart record -I
+
+  then generate timechart:
+
+  $ perf timechart
+
 SEE ALSO
 --------
 linkperf:perf-record[1]
diff --git a/tools/perf/Documentation/perf-trace.txt b/tools/perf/Documentation/perf-trace.txt
index fae38d9a44a4..02aac831bdd9 100644
--- a/tools/perf/Documentation/perf-trace.txt
+++ b/tools/perf/Documentation/perf-trace.txt
@@ -107,6 +107,52 @@ the thread executes on the designated CPUs. Default is to monitor all CPUs.
 	Show tool stats such as number of times fd->pathname was discovered thru
 	hooking the open syscall return + vfs_getname or via reading /proc/pid/fd, etc.
 
+-F=[all|min|maj]::
+--pf=[all|min|maj]::
+	Trace pagefaults. Optionally, you can specify whether you want minor,
+	major or all pagefaults. Default value is maj.
+
+--syscalls::
+	Trace system calls. This options is enabled by default.
+
+PAGEFAULTS
+----------
+
+When tracing pagefaults, the format of the trace is as follows:
+
+<min|maj>fault [<ip.symbol>+<ip.offset>] => <addr.dso@addr.offset> (<map type><addr level>).
+
+- min/maj indicates whether fault event is minor or major;
+- ip.symbol shows symbol for instruction pointer (the code that generated the
+  fault); if no debug symbols available, perf trace will print raw IP;
+- addr.dso shows DSO for the faulted address;
+- map type is either 'd' for non-executable maps or 'x' for executable maps;
+- addr level is either 'k' for kernel dso or '.' for user dso.
+
+For symbols resolution you may need to install debugging symbols.
+
+Please be aware that duration is currently always 0 and doesn't reflect actual
+time it took for fault to be handled!
+
+When --verbose specified, perf trace tries to print all available information
+for both IP and fault address in the form of dso@symbol+offset.
+
+EXAMPLES
+--------
+
+Trace only major pagefaults:
+
+ $ perf trace --no-syscalls -F
+
+Trace syscalls, major and minor pagefaults:
+
+ $ perf trace -F all
+
+  1416.547 ( 0.000 ms): python/20235 majfault [CRYPTO_push_info_+0x0] => /lib/x86_64-linux-gnu/libcrypto.so.1.0.0@0x61be0 (x.)
+
+  As you can see, there was major pagefault in python process, from
+  CRYPTO_push_info_ routine which faulted somewhere in libcrypto.so.
+
 SEE ALSO
 --------
 linkperf:perf-record[1], linkperf:perf-script[1]
diff --git a/tools/perf/arch/powerpc/Makefile b/tools/perf/arch/powerpc/Makefile
index 744e629797be..b92219b1900d 100644
--- a/tools/perf/arch/powerpc/Makefile
+++ b/tools/perf/arch/powerpc/Makefile
@@ -3,3 +3,4 @@ PERF_HAVE_DWARF_REGS := 1
 LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/dwarf-regs.o
 endif
 LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/header.o
+LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/skip-callchain-idx.o
diff --git a/tools/perf/arch/powerpc/util/skip-callchain-idx.c b/tools/perf/arch/powerpc/util/skip-callchain-idx.c
new file mode 100644
index 000000000000..a7c23a4b3778
--- /dev/null
+++ b/tools/perf/arch/powerpc/util/skip-callchain-idx.c
@@ -0,0 +1,266 @@
+/*
+ * Use DWARF Debug information to skip unnecessary callchain entries.
+ *
+ * Copyright (C) 2014 Sukadev Bhattiprolu, IBM Corporation.
+ * Copyright (C) 2014 Ulrich Weigand, IBM Corporation.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+#include <inttypes.h>
+#include <dwarf.h>
+#include <elfutils/libdwfl.h>
+
+#include "util/thread.h"
+#include "util/callchain.h"
+
+/*
+ * When saving the callchain on Power, the kernel conservatively saves
+ * excess entries in the callchain. A few of these entries are needed
+ * in some cases but not others. If the unnecessary entries are not
+ * ignored, we end up with duplicate arcs in the call-graphs. Use
+ * DWARF debug information to skip over any unnecessary callchain
+ * entries.
+ *
+ * See function header for arch_adjust_callchain() below for more details.
+ *
+ * The libdwfl code in this file is based on code from elfutils
+ * (libdwfl/argp-std.c, libdwfl/tests/addrcfi.c, etc).
+ */
+static char *debuginfo_path;
+
+static const Dwfl_Callbacks offline_callbacks = {
+	.debuginfo_path = &debuginfo_path,
+	.find_debuginfo = dwfl_standard_find_debuginfo,
+	.section_address = dwfl_offline_section_address,
+};
+
+
+/*
+ * Use the DWARF expression for the Call-frame-address and determine
+ * if return address is in LR and if a new frame was allocated.
+ */
+static int check_return_reg(int ra_regno, Dwarf_Frame *frame)
+{
+	Dwarf_Op ops_mem[2];
+	Dwarf_Op dummy;
+	Dwarf_Op *ops = &dummy;
+	size_t nops;
+	int result;
+
+	result = dwarf_frame_register(frame, ra_regno, ops_mem, &ops, &nops);
+	if (result < 0) {
+		pr_debug("dwarf_frame_register() %s\n", dwarf_errmsg(-1));
+		return -1;
+	}
+
+	/*
+	 * Check if return address is on the stack.
+	 */
+	if (nops != 0 || ops != NULL)
+		return 0;
+
+	/*
+	 * Return address is in LR. Check if a frame was allocated
+	 * but not-yet used.
+	 */
+	result = dwarf_frame_cfa(frame, &ops, &nops);
+	if (result < 0) {
+		pr_debug("dwarf_frame_cfa() returns %d, %s\n", result,
+					dwarf_errmsg(-1));
+		return -1;
+	}
+
+	/*
+	 * If call frame address is in r1, no new frame was allocated.
+	 */
+	if (nops == 1 && ops[0].atom == DW_OP_bregx && ops[0].number == 1 &&
+				ops[0].number2 == 0)
+		return 1;
+
+	/*
+	 * A new frame was allocated but has not yet been used.
+	 */
+	return 2;
+}
+
+/*
+ * Get the DWARF frame from the .eh_frame section.
+ */
+static Dwarf_Frame *get_eh_frame(Dwfl_Module *mod, Dwarf_Addr pc)
+{
+	int		result;
+	Dwarf_Addr	bias;
+	Dwarf_CFI	*cfi;
+	Dwarf_Frame	*frame;
+
+	cfi = dwfl_module_eh_cfi(mod, &bias);
+	if (!cfi) {
+		pr_debug("%s(): no CFI - %s\n", __func__, dwfl_errmsg(-1));
+		return NULL;
+	}
+
+	result = dwarf_cfi_addrframe(cfi, pc, &frame);
+	if (result) {
+		pr_debug("%s(): %s\n", __func__, dwfl_errmsg(-1));
+		return NULL;
+	}
+
+	return frame;
+}
+
+/*
+ * Get the DWARF frame from the .debug_frame section.
+ */
+static Dwarf_Frame *get_dwarf_frame(Dwfl_Module *mod, Dwarf_Addr pc)
+{
+	Dwarf_CFI       *cfi;
+	Dwarf_Addr      bias;
+	Dwarf_Frame     *frame;
+	int             result;
+
+	cfi = dwfl_module_dwarf_cfi(mod, &bias);
+	if (!cfi) {
+		pr_debug("%s(): no CFI - %s\n", __func__, dwfl_errmsg(-1));
+		return NULL;
+	}
+
+	result = dwarf_cfi_addrframe(cfi, pc, &frame);
+	if (result) {
+		pr_debug("%s(): %s\n", __func__, dwfl_errmsg(-1));
+		return NULL;
+	}
+
+	return frame;
+}
+
+/*
+ * Return:
+ *	0 if return address for the program counter @pc is on stack
+ *	1 if return address is in LR and no new stack frame was allocated
+ *	2 if return address is in LR and a new frame was allocated (but not
+ *		yet used)
+ *	-1 in case of errors
+ */
+static int check_return_addr(const char *exec_file, Dwarf_Addr pc)
+{
+	int		rc = -1;
+	Dwfl		*dwfl;
+	Dwfl_Module	*mod;
+	Dwarf_Frame	*frame;
+	int		ra_regno;
+	Dwarf_Addr	start = pc;
+	Dwarf_Addr	end = pc;
+	bool		signalp;
+
+	dwfl = dwfl_begin(&offline_callbacks);
+	if (!dwfl) {
+		pr_debug("dwfl_begin() failed: %s\n", dwarf_errmsg(-1));
+		return -1;
+	}
+
+	if (dwfl_report_offline(dwfl, "",  exec_file, -1) == NULL) {
+		pr_debug("dwfl_report_offline() failed %s\n", dwarf_errmsg(-1));
+		goto out;
+	}
+
+	mod = dwfl_addrmodule(dwfl, pc);
+	if (!mod) {
+		pr_debug("dwfl_addrmodule() failed, %s\n", dwarf_errmsg(-1));
+		goto out;
+	}
+
+	/*
+	 * To work with split debug info files (eg: glibc), check both
+	 * .eh_frame and .debug_frame sections of the ELF header.
+	 */
+	frame = get_eh_frame(mod, pc);
+	if (!frame) {
+		frame = get_dwarf_frame(mod, pc);
+		if (!frame)
+			goto out;
+	}
+
+	ra_regno = dwarf_frame_info(frame, &start, &end, &signalp);
+	if (ra_regno < 0) {
+		pr_debug("Return address register unavailable: %s\n",
+				dwarf_errmsg(-1));
+		goto out;
+	}
+
+	rc = check_return_reg(ra_regno, frame);
+
+out:
+	dwfl_end(dwfl);
+	return rc;
+}
+
+/*
+ * The callchain saved by the kernel always includes the link register (LR).
+ *
+ *	0:	PERF_CONTEXT_USER
+ *	1:	Program counter (Next instruction pointer)
+ *	2:	LR value
+ *	3:	Caller's caller
+ *	4:	...
+ *
+ * The value in LR is only needed when it holds a return address. If the
+ * return address is on the stack, we should ignore the LR value.
+ *
+ * Further, when the return address is in the LR, if a new frame was just
+ * allocated but the LR was not saved into it, then the LR contains the
+ * caller, slot 4: contains the caller's caller and the contents of slot 3:
+ * (chain->ips[3]) is undefined and must be ignored.
+ *
+ * Use DWARF debug information to determine if any entries need to be skipped.
+ *
+ * Return:
+ *	index:	of callchain entry that needs to be ignored (if any)
+ *	-1	if no entry needs to be ignored or in case of errors
+ */
+int arch_skip_callchain_idx(struct machine *machine, struct thread *thread,
+				struct ip_callchain *chain)
+{
+	struct addr_location al;
+	struct dso *dso = NULL;
+	int rc;
+	u64 ip;
+	u64 skip_slot = -1;
+
+	if (chain->nr < 3)
+		return skip_slot;
+
+	ip = chain->ips[2];
+
+	thread__find_addr_location(thread, machine, PERF_RECORD_MISC_USER,
+			MAP__FUNCTION, ip, &al);
+
+	if (al.map)
+		dso = al.map->dso;
+
+	if (!dso) {
+		pr_debug("%" PRIx64 " dso is NULL\n", ip);
+		return skip_slot;
+	}
+
+	rc = check_return_addr(dso->long_name, ip);
+
+	pr_debug("DSO %s, nr %" PRIx64 ", ip 0x%" PRIx64 "rc %d\n",
+				dso->long_name, chain->nr, ip, rc);
+
+	if (rc == 0) {
+		/*
+		 * Return address on stack. Ignore LR value in callchain
+		 */
+		skip_slot = 2;
+	} else if (rc == 2) {
+		/*
+		 * New frame allocated but return address still in LR.
+		 * Ignore the caller's caller entry in callchain.
+		 */
+		skip_slot = 3;
+	}
+	return skip_slot;
+}
diff --git a/tools/perf/arch/s390/Makefile b/tools/perf/arch/s390/Makefile
index 15130b50dfe3..744e629797be 100644
--- a/tools/perf/arch/s390/Makefile
+++ b/tools/perf/arch/s390/Makefile
@@ -2,3 +2,4 @@ ifndef NO_DWARF
 PERF_HAVE_DWARF_REGS := 1
 LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/dwarf-regs.o
 endif
+LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/header.o
diff --git a/tools/perf/arch/s390/util/header.c b/tools/perf/arch/s390/util/header.c
new file mode 100644
index 000000000000..9fa6c3e5782c
--- /dev/null
+++ b/tools/perf/arch/s390/util/header.c
@@ -0,0 +1,28 @@
+/*
+ * Implementation of get_cpuid().
+ *
+ * Copyright 2014 IBM Corp.
+ * Author(s): Alexander Yarygin <yarygin@linux.vnet.ibm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License (version 2 only)
+ * as published by the Free Software Foundation.
+ */
+
+#include <sys/types.h>
+#include <unistd.h>
+#include <stdio.h>
+#include <string.h>
+
+#include "../../util/header.h"
+
+int get_cpuid(char *buffer, size_t sz)
+{
+	const char *cpuid = "IBM/S390";
+
+	if (strlen(cpuid) + 1 > sz)
+		return -1;
+
+	strcpy(buffer, cpuid);
+	return 0;
+}
diff --git a/tools/perf/arch/x86/Makefile b/tools/perf/arch/x86/Makefile
index 1641542e3636..d3939014a877 100644
--- a/tools/perf/arch/x86/Makefile
+++ b/tools/perf/arch/x86/Makefile
@@ -15,3 +15,4 @@ endif
 LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/header.o
 LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/tsc.o
 LIB_H += arch/$(ARCH)/util/tsc.h
+HAVE_KVM_STAT_SUPPORT := 1
diff --git a/tools/perf/bench/bench.h b/tools/perf/bench/bench.h
index eba46709b279..3c4dd44d45cb 100644
--- a/tools/perf/bench/bench.h
+++ b/tools/perf/bench/bench.h
@@ -43,5 +43,6 @@ extern int bench_futex_requeue(int argc, const char **argv, const char *prefix);
 #define BENCH_FORMAT_UNKNOWN		-1
 
 extern int bench_format;
+extern unsigned int bench_repeat;
 
 #endif
diff --git a/tools/perf/bench/futex-requeue.c b/tools/perf/bench/futex-requeue.c
index a16255876f1d..732403bfd31a 100644
--- a/tools/perf/bench/futex-requeue.c
+++ b/tools/perf/bench/futex-requeue.c
@@ -29,13 +29,6 @@ static u_int32_t futex1 = 0, futex2 = 0;
  */
 static unsigned int nrequeue = 1;
 
-/*
- * There can be significant variance from run to run,
- * the more repeats, the more exact the overall avg and
- * the better idea of the futex latency.
- */
-static unsigned int repeat = 10;
-
 static pthread_t *worker;
 static bool done = 0, silent = 0;
 static pthread_mutex_t thread_lock;
@@ -46,7 +39,6 @@ static unsigned int ncpus, threads_starting, nthreads = 0;
 static const struct option options[] = {
 	OPT_UINTEGER('t', "threads",  &nthreads, "Specify amount of threads"),
 	OPT_UINTEGER('q', "nrequeue", &nrequeue, "Specify amount of threads to requeue at once"),
-	OPT_UINTEGER('r', "repeat",   &repeat,   "Specify amount of times to repeat the run"),
 	OPT_BOOLEAN( 's', "silent",   &silent,   "Silent mode: do not display data/details"),
 	OPT_END()
 };
@@ -146,7 +138,7 @@ int bench_futex_requeue(int argc, const char **argv,
 	pthread_cond_init(&thread_parent, NULL);
 	pthread_cond_init(&thread_worker, NULL);
 
-	for (j = 0; j < repeat && !done; j++) {
+	for (j = 0; j < bench_repeat && !done; j++) {
 		unsigned int nrequeued = 0;
 		struct timeval start, end, runtime;
 
diff --git a/tools/perf/bench/futex-wake.c b/tools/perf/bench/futex-wake.c
index d096169b161e..50022cbce87e 100644
--- a/tools/perf/bench/futex-wake.c
+++ b/tools/perf/bench/futex-wake.c
@@ -30,15 +30,8 @@ static u_int32_t futex1 = 0;
  */
 static unsigned int nwakes = 1;
 
-/*
- * There can be significant variance from run to run,
- * the more repeats, the more exact the overall avg and
- * the better idea of the futex latency.
- */
-static unsigned int repeat = 10;
-
 pthread_t *worker;
-static bool done = 0, silent = 0;
+static bool done = false, silent = false;
 static pthread_mutex_t thread_lock;
 static pthread_cond_t thread_parent, thread_worker;
 static struct stats waketime_stats, wakeup_stats;
@@ -47,7 +40,6 @@ static unsigned int ncpus, threads_starting, nthreads = 0;
 static const struct option options[] = {
 	OPT_UINTEGER('t', "threads", &nthreads, "Specify amount of threads"),
 	OPT_UINTEGER('w', "nwakes",  &nwakes,   "Specify amount of threads to wake at once"),
-	OPT_UINTEGER('r', "repeat",  &repeat,   "Specify amount of times to repeat the run"),
 	OPT_BOOLEAN( 's', "silent",  &silent,   "Silent mode: do not display data/details"),
 	OPT_END()
 };
@@ -149,7 +141,7 @@ int bench_futex_wake(int argc, const char **argv,
 	pthread_cond_init(&thread_parent, NULL);
 	pthread_cond_init(&thread_worker, NULL);
 
-	for (j = 0; j < repeat && !done; j++) {
+	for (j = 0; j < bench_repeat && !done; j++) {
 		unsigned int nwoken = 0;
 		struct timeval start, end, runtime;
 
diff --git a/tools/perf/bench/mem-memcpy.c b/tools/perf/bench/mem-memcpy.c
index 5ce71d3b72cf..e622c3e96efc 100644
--- a/tools/perf/bench/mem-memcpy.c
+++ b/tools/perf/bench/mem-memcpy.c
@@ -189,6 +189,11 @@ int bench_mem_memcpy(int argc, const char **argv,
 	argc = parse_options(argc, argv, options,
 			     bench_mem_memcpy_usage, 0);
 
+	if (no_prefault && only_prefault) {
+		fprintf(stderr, "Invalid options: -o and -n are mutually exclusive\n");
+		return 1;
+	}
+
 	if (use_cycle)
 		init_cycle();
 
diff --git a/tools/perf/bench/mem-memset.c b/tools/perf/bench/mem-memset.c
index 9af79d2b18e5..2a65468619f0 100644
--- a/tools/perf/bench/mem-memset.c
+++ b/tools/perf/bench/mem-memset.c
@@ -181,6 +181,11 @@ int bench_mem_memset(int argc, const char **argv,
 	argc = parse_options(argc, argv, options,
 			     bench_mem_memset_usage, 0);
 
+	if (no_prefault && only_prefault) {
+		fprintf(stderr, "Invalid options: -o and -n are mutually exclusive\n");
+		return 1;
+	}
+
 	if (use_cycle)
 		init_cycle();
 
diff --git a/tools/perf/bench/sched-messaging.c b/tools/perf/bench/sched-messaging.c
index cc1190a0849b..52a56599a543 100644
--- a/tools/perf/bench/sched-messaging.c
+++ b/tools/perf/bench/sched-messaging.c
@@ -28,6 +28,7 @@
 #include <sys/time.h>
 #include <sys/poll.h>
 #include <limits.h>
+#include <err.h>
 
 #define DATASIZE 100
 
@@ -50,12 +51,6 @@ struct receiver_context {
 	int wakefd;
 };
 
-static void barf(const char *msg)
-{
-	fprintf(stderr, "%s (error: %s)\n", msg, strerror(errno));
-	exit(1);
-}
-
 static void fdpair(int fds[2])
 {
 	if (use_pipes) {
@@ -66,7 +61,7 @@ static void fdpair(int fds[2])
 			return;
 	}
 
-	barf(use_pipes ? "pipe()" : "socketpair()");
+	err(EXIT_FAILURE, use_pipes ? "pipe()" : "socketpair()");
 }
 
 /* Block until we're ready to go */
@@ -77,11 +72,11 @@ static void ready(int ready_out, int wakefd)
 
 	/* Tell them we're ready. */
 	if (write(ready_out, &dummy, 1) != 1)
-		barf("CLIENT: ready write");
+		err(EXIT_FAILURE, "CLIENT: ready write");
 
 	/* Wait for "GO" signal */
 	if (poll(&pollfd, 1, -1) != 1)
-		barf("poll");
+		err(EXIT_FAILURE, "poll");
 }
 
 /* Sender sprays loops messages down each file descriptor */
@@ -101,7 +96,7 @@ again:
 			ret = write(ctx->out_fds[j], data + done,
 				    sizeof(data)-done);
 			if (ret < 0)
-				barf("SENDER: write");
+				err(EXIT_FAILURE, "SENDER: write");
 			done += ret;
 			if (done < DATASIZE)
 				goto again;
@@ -131,7 +126,7 @@ static void *receiver(struct receiver_context* ctx)
 again:
 		ret = read(ctx->in_fds[0], data + done, DATASIZE - done);
 		if (ret < 0)
-			barf("SERVER: read");
+			err(EXIT_FAILURE, "SERVER: read");
 		done += ret;
 		if (done < DATASIZE)
 			goto again;
@@ -144,14 +139,14 @@ static pthread_t create_worker(void *ctx, void *(*func)(void *))
 {
 	pthread_attr_t attr;
 	pthread_t childid;
-	int err;
+	int ret;
 
 	if (!thread_mode) {
 		/* process mode */
 		/* Fork the receiver. */
 		switch (fork()) {
 		case -1:
-			barf("fork()");
+			err(EXIT_FAILURE, "fork()");
 			break;
 		case 0:
 			(*func) (ctx);
@@ -165,19 +160,17 @@ static pthread_t create_worker(void *ctx, void *(*func)(void *))
 	}
 
 	if (pthread_attr_init(&attr) != 0)
-		barf("pthread_attr_init:");
+		err(EXIT_FAILURE, "pthread_attr_init:");
 
 #ifndef __ia64__
 	if (pthread_attr_setstacksize(&attr, PTHREAD_STACK_MIN) != 0)
-		barf("pthread_attr_setstacksize");
+		err(EXIT_FAILURE, "pthread_attr_setstacksize");
 #endif
 
-	err = pthread_create(&childid, &attr, func, ctx);
-	if (err != 0) {
-		fprintf(stderr, "pthread_create failed: %s (%d)\n",
-			strerror(err), err);
-		exit(-1);
-	}
+	ret = pthread_create(&childid, &attr, func, ctx);
+	if (ret != 0)
+		err(EXIT_FAILURE, "pthread_create failed");
+
 	return childid;
 }
 
@@ -207,14 +200,14 @@ static unsigned int group(pthread_t *pth,
 			+ num_fds * sizeof(int));
 
 	if (!snd_ctx)
-		barf("malloc()");
+		err(EXIT_FAILURE, "malloc()");
 
 	for (i = 0; i < num_fds; i++) {
 		int fds[2];
 		struct receiver_context *ctx = malloc(sizeof(*ctx));
 
 		if (!ctx)
-			barf("malloc()");
+			err(EXIT_FAILURE, "malloc()");
 
 
 		/* Create the pipe between client and server */
@@ -281,7 +274,7 @@ int bench_sched_messaging(int argc, const char **argv,
 
 	pth_tab = malloc(num_fds * 2 * num_groups * sizeof(pthread_t));
 	if (!pth_tab)
-		barf("main:malloc()");
+		err(EXIT_FAILURE, "main:malloc()");
 
 	fdpair(readyfds);
 	fdpair(wakefds);
@@ -294,13 +287,13 @@ int bench_sched_messaging(int argc, const char **argv,
 	/* Wait for everyone to be ready */
 	for (i = 0; i < total_children; i++)
 		if (read(readyfds[0], &dummy, 1) != 1)
-			barf("Reading for readyfds");
+			err(EXIT_FAILURE, "Reading for readyfds");
 
 	gettimeofday(&start, NULL);
 
 	/* Kick them off */
 	if (write(wakefds[1], &dummy, 1) != 1)
-		barf("Writing to start them");
+		err(EXIT_FAILURE, "Writing to start them");
 
 	/* Reap them all */
 	for (i = 0; i < total_children; i++)
@@ -332,5 +325,7 @@ int bench_sched_messaging(int argc, const char **argv,
 		break;
 	}
 
+	free(pth_tab);
+
 	return 0;
 }
diff --git a/tools/perf/builtin-bench.c b/tools/perf/builtin-bench.c
index 1e6e77710545..b9a56fa83330 100644
--- a/tools/perf/builtin-bench.c
+++ b/tools/perf/builtin-bench.c
@@ -104,9 +104,11 @@ static const char *bench_format_str;
 
 /* Output/formatting style, exported to benchmark modules: */
 int bench_format = BENCH_FORMAT_DEFAULT;
+unsigned int bench_repeat = 10; /* default number of times to repeat the run */
 
 static const struct option bench_options[] = {
 	OPT_STRING('f', "format", &bench_format_str, "default", "Specify format style"),
+	OPT_UINTEGER('r', "repeat",  &bench_repeat,   "Specify amount of times to repeat the run"),
 	OPT_END()
 };
 
@@ -226,6 +228,11 @@ int cmd_bench(int argc, const char **argv, const char *prefix __maybe_unused)
 		goto end;
 	}
 
+	if (bench_repeat == 0) {
+		printf("Invalid repeat option: Must specify a positive value\n");
+		goto end;
+	}
+
 	if (argc < 1) {
 		print_usage();
 		goto end;
diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c
index 0f1e5a2f6ad7..41dbeaf8cc11 100644
--- a/tools/perf/builtin-kvm.c
+++ b/tools/perf/builtin-kvm.c
@@ -29,7 +29,7 @@
 #include <pthread.h>
 #include <math.h>
 
-#if defined(__i386__) || defined(__x86_64__)
+#ifdef HAVE_KVM_STAT_SUPPORT
 #include <asm/svm.h>
 #include <asm/vmx.h>
 #include <asm/kvm.h>
@@ -99,7 +99,6 @@ struct perf_kvm_stat {
 	int trace_vcpu;
 
 	struct exit_reasons_table *exit_reasons;
-	int exit_reasons_size;
 	const char *exit_reasons_isa;
 
 	struct kvm_events_ops *events_ops;
@@ -158,20 +157,19 @@ static bool exit_event_end(struct perf_evsel *evsel,
 	return kvm_entry_event(evsel);
 }
 
-static struct exit_reasons_table vmx_exit_reasons[] = {
-	VMX_EXIT_REASONS
-};
+#define define_exit_reasons_table(name, symbols)	\
+	static struct exit_reasons_table name[] = {	\
+		symbols, { -1, NULL }			\
+	}
 
-static struct exit_reasons_table svm_exit_reasons[] = {
-	SVM_EXIT_REASONS
-};
+define_exit_reasons_table(vmx_exit_reasons, VMX_EXIT_REASONS);
+define_exit_reasons_table(svm_exit_reasons, SVM_EXIT_REASONS);
 
-static const char *get_exit_reason(struct perf_kvm_stat *kvm, u64 exit_code)
+static const char *get_exit_reason(struct perf_kvm_stat *kvm,
+				   struct exit_reasons_table *tbl,
+				   u64 exit_code)
 {
-	int i = kvm->exit_reasons_size;
-	struct exit_reasons_table *tbl = kvm->exit_reasons;
-
-	while (i--) {
+	while (tbl->reason != NULL) {
 		if (tbl->exit_code == exit_code)
 			return tbl->reason;
 		tbl++;
@@ -186,7 +184,8 @@ static void exit_event_decode_key(struct perf_kvm_stat *kvm,
 				  struct event_key *key,
 				  char decode[20])
 {
-	const char *exit_reason = get_exit_reason(kvm, key->key);
+	const char *exit_reason = get_exit_reason(kvm, kvm->exit_reasons,
+						  key->key);
 
 	scnprintf(decode, 20, "%s", exit_reason);
 }
@@ -836,37 +835,45 @@ static int process_sample_event(struct perf_tool *tool,
 	return 0;
 }
 
+static int cpu_isa_init(struct perf_kvm_stat *kvm, const char *cpuid)
+{
+	if (strstr(cpuid, "Intel")) {
+		kvm->exit_reasons = vmx_exit_reasons;
+		kvm->exit_reasons_isa = "VMX";
+	} else if (strstr(cpuid, "AMD")) {
+		kvm->exit_reasons = svm_exit_reasons;
+		kvm->exit_reasons_isa = "SVM";
+	} else
+		return -ENOTSUP;
+
+	return 0;
+}
+
 static int cpu_isa_config(struct perf_kvm_stat *kvm)
 {
 	char buf[64], *cpuid;
-	int err, isa;
+	int err;
 
 	if (kvm->live) {
 		err = get_cpuid(buf, sizeof(buf));
 		if (err != 0) {
-			pr_err("Failed to look up CPU type (Intel or AMD)\n");
+			pr_err("Failed to look up CPU type\n");
 			return err;
 		}
 		cpuid = buf;
 	} else
 		cpuid = kvm->session->header.env.cpuid;
 
-	if (strstr(cpuid, "Intel"))
-		isa = 1;
-	else if (strstr(cpuid, "AMD"))
-		isa = 0;
-	else {
-		pr_err("CPU %s is not supported.\n", cpuid);
-		return -ENOTSUP;
+	if (!cpuid) {
+		pr_err("Failed to look up CPU type\n");
+		return -EINVAL;
 	}
 
-	if (isa == 1) {
-		kvm->exit_reasons = vmx_exit_reasons;
-		kvm->exit_reasons_size = ARRAY_SIZE(vmx_exit_reasons);
-		kvm->exit_reasons_isa = "VMX";
-	}
+	err = cpu_isa_init(kvm, cpuid);
+	if (err == -ENOTSUP)
+		pr_err("CPU %s is not supported.\n", cpuid);
 
-	return 0;
+	return err;
 }
 
 static bool verify_vcpu(int vcpu)
@@ -1585,9 +1592,6 @@ static int kvm_cmd_stat(const char *file_name, int argc, const char **argv)
 		.report_event	= "vmexit",
 		.sort_key	= "sample",
 
-		.exit_reasons = svm_exit_reasons,
-		.exit_reasons_size = ARRAY_SIZE(svm_exit_reasons),
-		.exit_reasons_isa = "SVM",
 	};
 
 	if (argc == 1) {
@@ -1609,7 +1613,7 @@ static int kvm_cmd_stat(const char *file_name, int argc, const char **argv)
 perf_stat:
 	return cmd_stat(argc, argv, NULL);
 }
-#endif
+#endif /* HAVE_KVM_STAT_SUPPORT */
 
 static int __cmd_record(const char *file_name, int argc, const char **argv)
 {
@@ -1726,7 +1730,7 @@ int cmd_kvm(int argc, const char **argv, const char *prefix __maybe_unused)
 		return cmd_top(argc, argv, NULL);
 	else if (!strncmp(argv[0], "buildid-list", 12))
 		return __cmd_buildid_list(file_name, argc, argv);
-#if defined(__i386__) || defined(__x86_64__)
+#ifdef HAVE_KVM_STAT_SUPPORT
 	else if (!strncmp(argv[0], "stat", 4))
 		return kvm_cmd_stat(file_name, argc, argv);
 #endif
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 65a151e36067..3e80aa10cfd8 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -184,7 +184,7 @@ static void perf_evsel__reset_stat_priv(struct perf_evsel *evsel)
 static int perf_evsel__alloc_stat_priv(struct perf_evsel *evsel)
 {
 	evsel->priv = zalloc(sizeof(struct perf_stat));
-	if (evsel == NULL)
+	if (evsel->priv == NULL)
 		return -ENOMEM;
 	perf_evsel__reset_stat_priv(evsel);
 	return 0;
diff --git a/tools/perf/builtin-timechart.c b/tools/perf/builtin-timechart.c
index 74db2568b867..04c9c53becad 100644
--- a/tools/perf/builtin-timechart.c
+++ b/tools/perf/builtin-timechart.c
@@ -60,10 +60,17 @@ struct timechart {
 				tasks_only,
 				with_backtrace,
 				topology;
+	/* IO related settings */
+	u64			io_events;
+	bool			io_only,
+				skip_eagain;
+	u64			min_time,
+				merge_dist;
 };
 
 struct per_pidcomm;
 struct cpu_sample;
+struct io_sample;
 
 /*
  * Datastructure layout:
@@ -84,6 +91,7 @@ struct per_pid {
 	u64		start_time;
 	u64		end_time;
 	u64		total_time;
+	u64		total_bytes;
 	int		display;
 
 	struct per_pidcomm *all;
@@ -97,6 +105,8 @@ struct per_pidcomm {
 	u64		start_time;
 	u64		end_time;
 	u64		total_time;
+	u64		max_bytes;
+	u64		total_bytes;
 
 	int		Y;
 	int		display;
@@ -107,6 +117,7 @@ struct per_pidcomm {
 	char		*comm;
 
 	struct cpu_sample *samples;
+	struct io_sample  *io_samples;
 };
 
 struct sample_wrapper {
@@ -131,6 +142,27 @@ struct cpu_sample {
 	const char *backtrace;
 };
 
+enum {
+	IOTYPE_READ,
+	IOTYPE_WRITE,
+	IOTYPE_SYNC,
+	IOTYPE_TX,
+	IOTYPE_RX,
+	IOTYPE_POLL,
+};
+
+struct io_sample {
+	struct io_sample *next;
+
+	u64 start_time;
+	u64 end_time;
+	u64 bytes;
+	int type;
+	int fd;
+	int err;
+	int merges;
+};
+
 #define CSTATE 1
 #define PSTATE 2
 
@@ -213,7 +245,7 @@ static void pid_fork(struct timechart *tchart, int pid, int ppid, u64 timestamp)
 		pid_set_comm(tchart, pid, pp->current->comm);
 
 	p->start_time = timestamp;
-	if (p->current) {
+	if (p->current && !p->current->start_time) {
 		p->current->start_time = timestamp;
 		p->current->state_since = timestamp;
 	}
@@ -682,6 +714,249 @@ static void end_sample_processing(struct timechart *tchart)
 	}
 }
 
+static int pid_begin_io_sample(struct timechart *tchart, int pid, int type,
+			       u64 start, int fd)
+{
+	struct per_pid *p = find_create_pid(tchart, pid);
+	struct per_pidcomm *c = p->current;
+	struct io_sample *sample;
+	struct io_sample *prev;
+
+	if (!c) {
+		c = zalloc(sizeof(*c));
+		if (!c)
+			return -ENOMEM;
+		p->current = c;
+		c->next = p->all;
+		p->all = c;
+	}
+
+	prev = c->io_samples;
+
+	if (prev && prev->start_time && !prev->end_time) {
+		pr_warning("Skip invalid start event: "
+			   "previous event already started!\n");
+
+		/* remove previous event that has been started,
+		 * we are not sure we will ever get an end for it */
+		c->io_samples = prev->next;
+		free(prev);
+		return 0;
+	}
+
+	sample = zalloc(sizeof(*sample));
+	if (!sample)
+		return -ENOMEM;
+	sample->start_time = start;
+	sample->type = type;
+	sample->fd = fd;
+	sample->next = c->io_samples;
+	c->io_samples = sample;
+
+	if (c->start_time == 0 || c->start_time > start)
+		c->start_time = start;
+
+	return 0;
+}
+
+static int pid_end_io_sample(struct timechart *tchart, int pid, int type,
+			     u64 end, long ret)
+{
+	struct per_pid *p = find_create_pid(tchart, pid);
+	struct per_pidcomm *c = p->current;
+	struct io_sample *sample, *prev;
+
+	if (!c) {
+		pr_warning("Invalid pidcomm!\n");
+		return -1;
+	}
+
+	sample = c->io_samples;
+
+	if (!sample) /* skip partially captured events */
+		return 0;
+
+	if (sample->end_time) {
+		pr_warning("Skip invalid end event: "
+			   "previous event already ended!\n");
+		return 0;
+	}
+
+	if (sample->type != type) {
+		pr_warning("Skip invalid end event: invalid event type!\n");
+		return 0;
+	}
+
+	sample->end_time = end;
+	prev = sample->next;
+
+	/* we want to be able to see small and fast transfers, so make them
+	 * at least min_time long, but don't overlap them */
+	if (sample->end_time - sample->start_time < tchart->min_time)
+		sample->end_time = sample->start_time + tchart->min_time;
+	if (prev && sample->start_time < prev->end_time) {
+		if (prev->err) /* try to make errors more visible */
+			sample->start_time = prev->end_time;
+		else
+			prev->end_time = sample->start_time;
+	}
+
+	if (ret < 0) {
+		sample->err = ret;
+	} else if (type == IOTYPE_READ || type == IOTYPE_WRITE ||
+		   type == IOTYPE_TX || type == IOTYPE_RX) {
+
+		if ((u64)ret > c->max_bytes)
+			c->max_bytes = ret;
+
+		c->total_bytes += ret;
+		p->total_bytes += ret;
+		sample->bytes = ret;
+	}
+
+	/* merge two requests to make svg smaller and render-friendly */
+	if (prev &&
+	    prev->type == sample->type &&
+	    prev->err == sample->err &&
+	    prev->fd == sample->fd &&
+	    prev->end_time + tchart->merge_dist >= sample->start_time) {
+
+		sample->bytes += prev->bytes;
+		sample->merges += prev->merges + 1;
+
+		sample->start_time = prev->start_time;
+		sample->next = prev->next;
+		free(prev);
+
+		if (!sample->err && sample->bytes > c->max_bytes)
+			c->max_bytes = sample->bytes;
+	}
+
+	tchart->io_events++;
+
+	return 0;
+}
+
+static int
+process_enter_read(struct timechart *tchart,
+		   struct perf_evsel *evsel,
+		   struct perf_sample *sample)
+{
+	long fd = perf_evsel__intval(evsel, sample, "fd");
+	return pid_begin_io_sample(tchart, sample->tid, IOTYPE_READ,
+				   sample->time, fd);
+}
+
+static int
+process_exit_read(struct timechart *tchart,
+		  struct perf_evsel *evsel,
+		  struct perf_sample *sample)
+{
+	long ret = perf_evsel__intval(evsel, sample, "ret");
+	return pid_end_io_sample(tchart, sample->tid, IOTYPE_READ,
+				 sample->time, ret);
+}
+
+static int
+process_enter_write(struct timechart *tchart,
+		    struct perf_evsel *evsel,
+		    struct perf_sample *sample)
+{
+	long fd = perf_evsel__intval(evsel, sample, "fd");
+	return pid_begin_io_sample(tchart, sample->tid, IOTYPE_WRITE,
+				   sample->time, fd);
+}
+
+static int
+process_exit_write(struct timechart *tchart,
+		   struct perf_evsel *evsel,
+		   struct perf_sample *sample)
+{
+	long ret = perf_evsel__intval(evsel, sample, "ret");
+	return pid_end_io_sample(tchart, sample->tid, IOTYPE_WRITE,
+				 sample->time, ret);
+}
+
+static int
+process_enter_sync(struct timechart *tchart,
+		   struct perf_evsel *evsel,
+		   struct perf_sample *sample)
+{
+	long fd = perf_evsel__intval(evsel, sample, "fd");
+	return pid_begin_io_sample(tchart, sample->tid, IOTYPE_SYNC,
+				   sample->time, fd);
+}
+
+static int
+process_exit_sync(struct timechart *tchart,
+		  struct perf_evsel *evsel,
+		  struct perf_sample *sample)
+{
+	long ret = perf_evsel__intval(evsel, sample, "ret");
+	return pid_end_io_sample(tchart, sample->tid, IOTYPE_SYNC,
+				 sample->time, ret);
+}
+
+static int
+process_enter_tx(struct timechart *tchart,
+		 struct perf_evsel *evsel,
+		 struct perf_sample *sample)
+{
+	long fd = perf_evsel__intval(evsel, sample, "fd");
+	return pid_begin_io_sample(tchart, sample->tid, IOTYPE_TX,
+				   sample->time, fd);
+}
+
+static int
+process_exit_tx(struct timechart *tchart,
+		struct perf_evsel *evsel,
+		struct perf_sample *sample)
+{
+	long ret = perf_evsel__intval(evsel, sample, "ret");
+	return pid_end_io_sample(tchart, sample->tid, IOTYPE_TX,
+				 sample->time, ret);
+}
+
+static int
+process_enter_rx(struct timechart *tchart,
+		 struct perf_evsel *evsel,
+		 struct perf_sample *sample)
+{
+	long fd = perf_evsel__intval(evsel, sample, "fd");
+	return pid_begin_io_sample(tchart, sample->tid, IOTYPE_RX,
+				   sample->time, fd);
+}
+
+static int
+process_exit_rx(struct timechart *tchart,
+		struct perf_evsel *evsel,
+		struct perf_sample *sample)
+{
+	long ret = perf_evsel__intval(evsel, sample, "ret");
+	return pid_end_io_sample(tchart, sample->tid, IOTYPE_RX,
+				 sample->time, ret);
+}
+
+static int
+process_enter_poll(struct timechart *tchart,
+		   struct perf_evsel *evsel,
+		   struct perf_sample *sample)
+{
+	long fd = perf_evsel__intval(evsel, sample, "fd");
+	return pid_begin_io_sample(tchart, sample->tid, IOTYPE_POLL,
+				   sample->time, fd);
+}
+
+static int
+process_exit_poll(struct timechart *tchart,
+		  struct perf_evsel *evsel,
+		  struct perf_sample *sample)
+{
+	long ret = perf_evsel__intval(evsel, sample, "ret");
+	return pid_end_io_sample(tchart, sample->tid, IOTYPE_POLL,
+				 sample->time, ret);
+}
+
 /*
  * Sort the pid datastructure
  */
@@ -852,6 +1127,121 @@ static void draw_cpu_usage(struct timechart *tchart)
 	}
 }
 
+static void draw_io_bars(struct timechart *tchart)
+{
+	const char *suf;
+	double bytes;
+	char comm[256];
+	struct per_pid *p;
+	struct per_pidcomm *c;
+	struct io_sample *sample;
+	int Y = 1;
+
+	p = tchart->all_data;
+	while (p) {
+		c = p->all;
+		while (c) {
+			if (!c->display) {
+				c->Y = 0;
+				c = c->next;
+				continue;
+			}
+
+			svg_box(Y, c->start_time, c->end_time, "process3");
+			sample = c->io_samples;
+			for (sample = c->io_samples; sample; sample = sample->next) {
+				double h = (double)sample->bytes / c->max_bytes;
+
+				if (tchart->skip_eagain &&
+				    sample->err == -EAGAIN)
+					continue;
+
+				if (sample->err)
+					h = 1;
+
+				if (sample->type == IOTYPE_SYNC)
+					svg_fbox(Y,
+						sample->start_time,
+						sample->end_time,
+						1,
+						sample->err ? "error" : "sync",
+						sample->fd,
+						sample->err,
+						sample->merges);
+				else if (sample->type == IOTYPE_POLL)
+					svg_fbox(Y,
+						sample->start_time,
+						sample->end_time,
+						1,
+						sample->err ? "error" : "poll",
+						sample->fd,
+						sample->err,
+						sample->merges);
+				else if (sample->type == IOTYPE_READ)
+					svg_ubox(Y,
+						sample->start_time,
+						sample->end_time,
+						h,
+						sample->err ? "error" : "disk",
+						sample->fd,
+						sample->err,
+						sample->merges);
+				else if (sample->type == IOTYPE_WRITE)
+					svg_lbox(Y,
+						sample->start_time,
+						sample->end_time,
+						h,
+						sample->err ? "error" : "disk",
+						sample->fd,
+						sample->err,
+						sample->merges);
+				else if (sample->type == IOTYPE_RX)
+					svg_ubox(Y,
+						sample->start_time,
+						sample->end_time,
+						h,
+						sample->err ? "error" : "net",
+						sample->fd,
+						sample->err,
+						sample->merges);
+				else if (sample->type == IOTYPE_TX)
+					svg_lbox(Y,
+						sample->start_time,
+						sample->end_time,
+						h,
+						sample->err ? "error" : "net",
+						sample->fd,
+						sample->err,
+						sample->merges);
+			}
+
+			suf = "";
+			bytes = c->total_bytes;
+			if (bytes > 1024) {
+				bytes = bytes / 1024;
+				suf = "K";
+			}
+			if (bytes > 1024) {
+				bytes = bytes / 1024;
+				suf = "M";
+			}
+			if (bytes > 1024) {
+				bytes = bytes / 1024;
+				suf = "G";
+			}
+
+
+			sprintf(comm, "%s:%i (%3.1f %sbytes)", c->comm ?: "", p->pid, bytes, suf);
+			svg_text(Y, c->start_time, comm);
+
+			c->Y = Y;
+			Y++;
+			c = c->next;
+		}
+		p = p->next;
+	}
+}
+
 static void draw_process_bars(struct timechart *tchart)
 {
 	struct per_pid *p;
@@ -987,9 +1377,6 @@ static int determine_display_tasks(struct timechart *tchart, u64 threshold)
 	struct per_pidcomm *c;
 	int count = 0;
 
-	if (process_filter)
-		return determine_display_tasks_filtered(tchart);
-
 	p = tchart->all_data;
 	while (p) {
 		p->display = 0;
@@ -1025,15 +1412,46 @@ static int determine_display_tasks(struct timechart *tchart, u64 threshold)
 	return count;
 }
 
+static int determine_display_io_tasks(struct timechart *timechart, u64 threshold)
+{
+	struct per_pid *p;
+	struct per_pidcomm *c;
+	int count = 0;
+
+	p = timechart->all_data;
+	while (p) {
+		/* no exit marker, task kept running to the end */
+		if (p->end_time == 0)
+			p->end_time = timechart->last_time;
 
+		c = p->all;
 
+		while (c) {
+			c->display = 0;
+
+			if (c->total_bytes >= threshold) {
+				c->display = 1;
+				count++;
+			}
+
+			if (c->end_time == 0)
+				c->end_time = timechart->last_time;
+
+			c = c->next;
+		}
+		p = p->next;
+	}
+	return count;
+}
+
+#define BYTES_THRESH (1 * 1024 * 1024)
 #define TIME_THRESH 10000000
 
 static void write_svg_file(struct timechart *tchart, const char *filename)
 {
 	u64 i;
 	int count;
-	int thresh = TIME_THRESH;
+	int thresh = tchart->io_events ? BYTES_THRESH : TIME_THRESH;
 
 	if (tchart->power_only)
 		tchart->proc_num = 0;
@@ -1041,28 +1459,43 @@ static void write_svg_file(struct timechart *tchart, const char *filename)
 	/* We'd like to show at least proc_num tasks;
 	 * be less picky if we have fewer */
 	do {
-		count = determine_display_tasks(tchart, thresh);
+		if (process_filter)
+			count = determine_display_tasks_filtered(tchart);
+		else if (tchart->io_events)
+			count = determine_display_io_tasks(tchart, thresh);
+		else
+			count = determine_display_tasks(tchart, thresh);
 		thresh /= 10;
 	} while (!process_filter && thresh && count < tchart->proc_num);
 
 	if (!tchart->proc_num)
 		count = 0;
 
-	open_svg(filename, tchart->numcpus, count, tchart->first_time, tchart->last_time);
+	if (tchart->io_events) {
+		open_svg(filename, 0, count, tchart->first_time, tchart->last_time);
 
-	svg_time_grid();
-	svg_legenda();
+		svg_time_grid(0.5);
+		svg_io_legenda();
+
+		draw_io_bars(tchart);
+	} else {
+		open_svg(filename, tchart->numcpus, count, tchart->first_time, tchart->last_time);
 
-	for (i = 0; i < tchart->numcpus; i++)
-		svg_cpu_box(i, tchart->max_freq, tchart->turbo_frequency);
+		svg_time_grid(0);
 
-	draw_cpu_usage(tchart);
-	if (tchart->proc_num)
-		draw_process_bars(tchart);
-	if (!tchart->tasks_only)
-		draw_c_p_states(tchart);
-	if (tchart->proc_num)
-		draw_wakeups(tchart);
+		svg_legenda();
+
+		for (i = 0; i < tchart->numcpus; i++)
+			svg_cpu_box(i, tchart->max_freq, tchart->turbo_frequency);
+
+		draw_cpu_usage(tchart);
+		if (tchart->proc_num)
+			draw_process_bars(tchart);
+		if (!tchart->tasks_only)
+			draw_c_p_states(tchart);
+		if (tchart->proc_num)
+			draw_wakeups(tchart);
+	}
 
 	svg_close();
 }
@@ -1110,6 +1543,56 @@ static int __cmd_timechart(struct timechart *tchart, const char *output_name)
 		{ "power:power_end",		process_sample_power_end },
 		{ "power:power_frequency",	process_sample_power_frequency },
 #endif
+
+		{ "syscalls:sys_enter_read",		process_enter_read },
+		{ "syscalls:sys_enter_pread64",		process_enter_read },
+		{ "syscalls:sys_enter_readv",		process_enter_read },
+		{ "syscalls:sys_enter_preadv",		process_enter_read },
+		{ "syscalls:sys_enter_write",		process_enter_write },
+		{ "syscalls:sys_enter_pwrite64",	process_enter_write },
+		{ "syscalls:sys_enter_writev",		process_enter_write },
+		{ "syscalls:sys_enter_pwritev",		process_enter_write },
+		{ "syscalls:sys_enter_sync",		process_enter_sync },
+		{ "syscalls:sys_enter_sync_file_range",	process_enter_sync },
+		{ "syscalls:sys_enter_fsync",		process_enter_sync },
+		{ "syscalls:sys_enter_msync",		process_enter_sync },
+		{ "syscalls:sys_enter_recvfrom",	process_enter_rx },
+		{ "syscalls:sys_enter_recvmmsg",	process_enter_rx },
+		{ "syscalls:sys_enter_recvmsg",		process_enter_rx },
+		{ "syscalls:sys_enter_sendto",		process_enter_tx },
+		{ "syscalls:sys_enter_sendmsg",		process_enter_tx },
+		{ "syscalls:sys_enter_sendmmsg",	process_enter_tx },
+		{ "syscalls:sys_enter_epoll_pwait",	process_enter_poll },
+		{ "syscalls:sys_enter_epoll_wait",	process_enter_poll },
+		{ "syscalls:sys_enter_poll",		process_enter_poll },
+		{ "syscalls:sys_enter_ppoll",		process_enter_poll },
+		{ "syscalls:sys_enter_pselect6",	process_enter_poll },
+		{ "syscalls:sys_enter_select",		process_enter_poll },
+
+		{ "syscalls:sys_exit_read",		process_exit_read },
+		{ "syscalls:sys_exit_pread64",		process_exit_read },
+		{ "syscalls:sys_exit_readv",		process_exit_read },
+		{ "syscalls:sys_exit_preadv",		process_exit_read },
+		{ "syscalls:sys_exit_write",		process_exit_write },
+		{ "syscalls:sys_exit_pwrite64",		process_exit_write },
+		{ "syscalls:sys_exit_writev",		process_exit_write },
+		{ "syscalls:sys_exit_pwritev",		process_exit_write },
+		{ "syscalls:sys_exit_sync",		process_exit_sync },
+		{ "syscalls:sys_exit_sync_file_range",	process_exit_sync },
+		{ "syscalls:sys_exit_fsync",		process_exit_sync },
+		{ "syscalls:sys_exit_msync",		process_exit_sync },
+		{ "syscalls:sys_exit_recvfrom",		process_exit_rx },
+		{ "syscalls:sys_exit_recvmmsg",		process_exit_rx },
+		{ "syscalls:sys_exit_recvmsg",		process_exit_rx },
+		{ "syscalls:sys_exit_sendto",		process_exit_tx },
+		{ "syscalls:sys_exit_sendmsg",		process_exit_tx },
+		{ "syscalls:sys_exit_sendmmsg",		process_exit_tx },
+		{ "syscalls:sys_exit_epoll_pwait",	process_exit_poll },
+		{ "syscalls:sys_exit_epoll_wait",	process_exit_poll },
+		{ "syscalls:sys_exit_poll",		process_exit_poll },
+		{ "syscalls:sys_exit_ppoll",		process_exit_poll },
+		{ "syscalls:sys_exit_pselect6",		process_exit_poll },
+		{ "syscalls:sys_exit_select",		process_exit_poll },
 	};
 	struct perf_data_file file = {
 		.path = input_name,
@@ -1154,6 +1637,139 @@ out_delete:
 	return ret;
 }
 
+static int timechart__io_record(int argc, const char **argv)
+{
+	unsigned int rec_argc, i;
+	const char **rec_argv;
+	const char **p;
+	char *filter = NULL;
+
+	const char * const common_args[] = {
+		"record", "-a", "-R", "-c", "1",
+	};
+	unsigned int common_args_nr = ARRAY_SIZE(common_args);
+
+	const char * const disk_events[] = {
+		"syscalls:sys_enter_read",
+		"syscalls:sys_enter_pread64",
+		"syscalls:sys_enter_readv",
+		"syscalls:sys_enter_preadv",
+		"syscalls:sys_enter_write",
+		"syscalls:sys_enter_pwrite64",
+		"syscalls:sys_enter_writev",
+		"syscalls:sys_enter_pwritev",
+		"syscalls:sys_enter_sync",
+		"syscalls:sys_enter_sync_file_range",
+		"syscalls:sys_enter_fsync",
+		"syscalls:sys_enter_msync",
+
+		"syscalls:sys_exit_read",
+		"syscalls:sys_exit_pread64",
+		"syscalls:sys_exit_readv",
+		"syscalls:sys_exit_preadv",
+		"syscalls:sys_exit_write",
+		"syscalls:sys_exit_pwrite64",
+		"syscalls:sys_exit_writev",
+		"syscalls:sys_exit_pwritev",
+		"syscalls:sys_exit_sync",
+		"syscalls:sys_exit_sync_file_range",
+		"syscalls:sys_exit_fsync",
+		"syscalls:sys_exit_msync",
+	};
+	unsigned int disk_events_nr = ARRAY_SIZE(disk_events);
+
+	const char * const net_events[] = {
+		"syscalls:sys_enter_recvfrom",
+		"syscalls:sys_enter_recvmmsg",
+		"syscalls:sys_enter_recvmsg",
+		"syscalls:sys_enter_sendto",
+		"syscalls:sys_enter_sendmsg",
+		"syscalls:sys_enter_sendmmsg",
+
+		"syscalls:sys_exit_recvfrom",
+		"syscalls:sys_exit_recvmmsg",
+		"syscalls:sys_exit_recvmsg",
+		"syscalls:sys_exit_sendto",
+		"syscalls:sys_exit_sendmsg",
+		"syscalls:sys_exit_sendmmsg",
+	};
+	unsigned int net_events_nr = ARRAY_SIZE(net_events);
+
+	const char * const poll_events[] = {
+		"syscalls:sys_enter_epoll_pwait",
+		"syscalls:sys_enter_epoll_wait",
+		"syscalls:sys_enter_poll",
+		"syscalls:sys_enter_ppoll",
+		"syscalls:sys_enter_pselect6",
+		"syscalls:sys_enter_select",
+
+		"syscalls:sys_exit_epoll_pwait",
+		"syscalls:sys_exit_epoll_wait",
+		"syscalls:sys_exit_poll",
+		"syscalls:sys_exit_ppoll",
+		"syscalls:sys_exit_pselect6",
+		"syscalls:sys_exit_select",
+	};
+	unsigned int poll_events_nr = ARRAY_SIZE(poll_events);
+
+	rec_argc = common_args_nr +
+		disk_events_nr * 4 +
+		net_events_nr * 4 +
+		poll_events_nr * 4 +
+		argc;
+	rec_argv = calloc(rec_argc + 1, sizeof(char *));
+
+	if (rec_argv == NULL)
+		return -ENOMEM;
+
+	if (asprintf(&filter, "common_pid != %d", getpid()) < 0)
+		return -ENOMEM;
+
+	p = rec_argv;
+	for (i = 0; i < common_args_nr; i++)
+		*p++ = strdup(common_args[i]);
+
+	for (i = 0; i < disk_events_nr; i++) {
+		if (!is_valid_tracepoint(disk_events[i])) {
+			rec_argc -= 4;
+			continue;
+		}
+
+		*p++ = "-e";
+		*p++ = strdup(disk_events[i]);
+		*p++ = "--filter";
+		*p++ = filter;
+	}
+	for (i = 0; i < net_events_nr; i++) {
+		if (!is_valid_tracepoint(net_events[i])) {
+			rec_argc -= 4;
+			continue;
+		}
+
+		*p++ = "-e";
+		*p++ = strdup(net_events[i]);
+		*p++ = "--filter";
+		*p++ = filter;
+	}
+	for (i = 0; i < poll_events_nr; i++) {
+		if (!is_valid_tracepoint(poll_events[i])) {
+			rec_argc -= 4;
+			continue;
+		}
+
+		*p++ = "-e";
+		*p++ = strdup(poll_events[i]);
+		*p++ = "--filter";
+		*p++ = filter;
+	}
+
+	for (i = 0; i < (unsigned int)argc; i++)
+		*p++ = argv[i];
+
+	return cmd_record(rec_argc, rec_argv, NULL);
+}
+
+
 static int timechart__record(struct timechart *tchart, int argc, const char **argv)
 {
 	unsigned int rec_argc, i, j;
@@ -1270,6 +1886,30 @@ parse_highlight(const struct option *opt __maybe_unused, const char *arg,
 	return 0;
 }
 
+static int
+parse_time(const struct option *opt, const char *arg, int __maybe_unused unset)
+{
+	char unit = 'n';
+	u64 *value = opt->value;
+
+	if (sscanf(arg, "%" PRIu64 "%cs", value, &unit) > 0) {
+		switch (unit) {
+		case 'm':
+			*value *= 1000000;
+			break;
+		case 'u':
+			*value *= 1000;
+			break;
+		case 'n':
+			break;
+		default:
+			return -1;
+		}
+	}
+
+	return 0;
+}
+
 int cmd_timechart(int argc, const char **argv,
 		  const char *prefix __maybe_unused)
 {
@@ -1282,6 +1922,8 @@ int cmd_timechart(int argc, const char **argv,
 			.ordered_samples = true,
 		},
 		.proc_num = 15,
+		.min_time = 1000000,
+		.merge_dist = 1000,
 	};
 	const char *output_name = "output.svg";
 	const struct option timechart_options[] = {
@@ -1303,6 +1945,14 @@ int cmd_timechart(int argc, const char **argv,
 		    "min. number of tasks to print"),
 	OPT_BOOLEAN('t', "topology", &tchart.topology,
 		    "sort CPUs according to topology"),
+	OPT_BOOLEAN(0, "io-skip-eagain", &tchart.skip_eagain,
+		    "skip EAGAIN errors"),
+	OPT_CALLBACK(0, "io-min-time", &tchart.min_time, "time",
+		     "all IO faster than min-time will visually appear longer",
+		     parse_time),
+	OPT_CALLBACK(0, "io-merge-dist", &tchart.merge_dist, "time",
+		     "merge events that are merge-dist us apart",
+		     parse_time),
 	OPT_END()
 	};
 	const char * const timechart_usage[] = {
@@ -1314,6 +1964,8 @@ int cmd_timechart(int argc, const char **argv,
 	OPT_BOOLEAN('P', "power-only", &tchart.power_only, "output power data only"),
 	OPT_BOOLEAN('T', "tasks-only", &tchart.tasks_only,
 		    "output processes data only"),
+	OPT_BOOLEAN('I', "io-only", &tchart.io_only,
+		    "record only IO data"),
 	OPT_BOOLEAN('g', "callchain", &tchart.with_backtrace, "record callchain"),
 	OPT_END()
 	};
@@ -1340,7 +1992,10 @@ int cmd_timechart(int argc, const char **argv,
 			return -1;
 		}
 
-		return timechart__record(&tchart, argc, argv);
+		if (tchart.io_only)
+			return timechart__io_record(argc, argv);
+		else
+			return timechart__record(&tchart, argc, argv);
 	} else if (argc)
 		usage_with_options(timechart_usage, timechart_options);
 
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index f954c26de231..c4a5a7d7b2cf 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -1108,6 +1108,7 @@ struct syscall {
 	struct event_format *tp_format;
 	const char	    *name;
 	bool		    filtered;
+	bool		    is_exit;
 	struct syscall_fmt  *fmt;
 	size_t		    (**arg_scnprintf)(char *bf, size_t size, struct syscall_arg *arg);
 	void		    **arg_parm;
@@ -1132,6 +1133,7 @@ struct thread_trace {
 	u64		  exit_time;
 	bool		  entry_pending;
 	unsigned long	  nr_events;
+	unsigned long	  pfmaj, pfmin;
 	char		  *entry_str;
 	double		  runtime_ms;
 	struct {
@@ -1177,6 +1179,9 @@ fail:
 	return NULL;
 }
 
+#define TRACE_PFMAJ		(1 << 0)
+#define TRACE_PFMIN		(1 << 1)
+
 struct trace {
 	struct perf_tool	tool;
 	struct {
@@ -1211,6 +1216,8 @@ struct trace {
 	bool			summary_only;
 	bool			show_comm;
 	bool			show_tool_stats;
+	bool			trace_syscalls;
+	int			trace_pgfaults;
 };
 
 static int trace__set_fd_pathname(struct thread *thread, int fd, const char *pathname)
@@ -1276,11 +1283,11 @@ static const char *thread__fd_path(struct thread *thread, int fd,
 	if (fd < 0)
 		return NULL;
 
-	if ((fd > ttrace->paths.max || ttrace->paths.table[fd] == NULL))
+	if ((fd > ttrace->paths.max || ttrace->paths.table[fd] == NULL)) {
 		if (!trace->live)
 			return NULL;
 		++trace->stats.proc_getname;
-		if (thread__read_fd_path(thread, fd)) {
+		if (thread__read_fd_path(thread, fd))
 			return NULL;
 	}
 
@@ -1473,6 +1480,8 @@ static int trace__read_syscall_info(struct trace *trace, int id)
 	if (sc->tp_format == NULL)
 		return -1;
 
+	sc->is_exit = !strcmp(name, "exit_group") || !strcmp(name, "exit");
+
 	return syscall__set_arg_fmts(sc);
 }
 
@@ -1535,6 +1544,7 @@ static size_t syscall__scnprintf_args(struct syscall *sc, char *bf, size_t size,
 }
 
 typedef int (*tracepoint_handler)(struct trace *trace, struct perf_evsel *evsel,
+				  union perf_event *event,
 				  struct perf_sample *sample);
 
 static struct syscall *trace__syscall_info(struct trace *trace,
@@ -1607,6 +1617,7 @@ static void thread__update_stats(struct thread_trace *ttrace,
 }
 
 static int trace__sys_enter(struct trace *trace, struct perf_evsel *evsel,
+			    union perf_event *event __maybe_unused,
 			    struct perf_sample *sample)
 {
 	char *msg;
@@ -1629,7 +1640,6 @@ static int trace__sys_enter(struct trace *trace, struct perf_evsel *evsel,
 		return -1;
 
 	args = perf_evsel__sc_tp_ptr(evsel, args, sample);
-	ttrace = thread->priv;
 
 	if (ttrace->entry_str == NULL) {
 		ttrace->entry_str = malloc(1024);
@@ -1644,7 +1654,7 @@ static int trace__sys_enter(struct trace *trace, struct perf_evsel *evsel,
 	printed += syscall__scnprintf_args(sc, msg + printed, 1024 - printed,
 					   args, trace, thread);
 
-	if (!strcmp(sc->name, "exit_group") || !strcmp(sc->name, "exit")) {
+	if (sc->is_exit) {
 		if (!trace->duration_filter && !trace->summary_only) {
 			trace__fprintf_entry_head(trace, thread, 1, sample->time, trace->output);
 			fprintf(trace->output, "%-70s\n", ttrace->entry_str);
@@ -1656,6 +1666,7 @@ static int trace__sys_enter(struct trace *trace, struct perf_evsel *evsel,
 }
 
 static int trace__sys_exit(struct trace *trace, struct perf_evsel *evsel,
+			   union perf_event *event __maybe_unused,
 			   struct perf_sample *sample)
 {
 	int ret;
@@ -1687,8 +1698,6 @@ static int trace__sys_exit(struct trace *trace, struct perf_evsel *evsel,
 		++trace->stats.vfs_getname;
 	}
 
-	ttrace = thread->priv;
-
 	ttrace->exit_time = sample->time;
 
 	if (ttrace->entry_time) {
@@ -1735,6 +1744,7 @@ out:
 }
 
 static int trace__vfs_getname(struct trace *trace, struct perf_evsel *evsel,
+			      union perf_event *event __maybe_unused,
 			      struct perf_sample *sample)
 {
 	trace->last_vfs_getname = perf_evsel__rawptr(evsel, sample, "pathname");
@@ -1742,6 +1752,7 @@ static int trace__vfs_getname(struct trace *trace, struct perf_evsel *evsel,
 }
 
 static int trace__sched_stat_runtime(struct trace *trace, struct perf_evsel *evsel,
+				     union perf_event *event __maybe_unused,
 				     struct perf_sample *sample)
 {
         u64 runtime = perf_evsel__intval(evsel, sample, "runtime");
@@ -1768,6 +1779,80 @@ out_dump:
 	return 0;
 }
 
+static void print_location(FILE *f, struct perf_sample *sample,
+			   struct addr_location *al,
+			   bool print_dso, bool print_sym)
+{
+
+	if ((verbose || print_dso) && al->map)
+		fprintf(f, "%s@", al->map->dso->long_name);
+
+	if ((verbose || print_sym) && al->sym)
+		fprintf(f, "%s+0x%" PRIx64, al->sym->name,
+			al->addr - al->sym->start);
+	else if (al->map)
+		fprintf(f, "0x%" PRIx64, al->addr);
+	else
+		fprintf(f, "0x%" PRIx64, sample->addr);
+}
+
+static int trace__pgfault(struct trace *trace,
+			  struct perf_evsel *evsel,
+			  union perf_event *event,
+			  struct perf_sample *sample)
+{
+	struct thread *thread;
+	u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
+	struct addr_location al;
+	char map_type = 'd';
+	struct thread_trace *ttrace;
+
+	thread = machine__findnew_thread(trace->host, sample->pid, sample->tid);
+	ttrace = thread__trace(thread, trace->output);
+	if (ttrace == NULL)
+		return -1;
+
+	if (evsel->attr.config == PERF_COUNT_SW_PAGE_FAULTS_MAJ)
+		ttrace->pfmaj++;
+	else
+		ttrace->pfmin++;
+
+	if (trace->summary_only)
+		return 0;
+
+	thread__find_addr_location(thread, trace->host, cpumode, MAP__FUNCTION,
+			      sample->ip, &al);
+
+	trace__fprintf_entry_head(trace, thread, 0, sample->time, trace->output);
+
+	fprintf(trace->output, "%sfault [",
+		evsel->attr.config == PERF_COUNT_SW_PAGE_FAULTS_MAJ ?
+		"maj" : "min");
+
+	print_location(trace->output, sample, &al, false, true);
+
+	fprintf(trace->output, "] => ");
+
+	thread__find_addr_location(thread, trace->host, cpumode, MAP__VARIABLE,
+				   sample->addr, &al);
+
+	if (!al.map) {
+		thread__find_addr_location(thread, trace->host, cpumode,
+					   MAP__FUNCTION, sample->addr, &al);
+
+		if (al.map)
+			map_type = 'x';
+		else
+			map_type = '?';
+	}
+
+	print_location(trace->output, sample, &al, true, false);
+
+	fprintf(trace->output, " (%c%c)\n", map_type, al.level);
+
+	return 0;
+}
+
 static bool skip_sample(struct trace *trace, struct perf_sample *sample)
 {
 	if ((trace->pid_list && intlist__find(trace->pid_list, sample->pid)) ||
@@ -1781,7 +1866,7 @@ static bool skip_sample(struct trace *trace, struct perf_sample *sample)
 }
 
 static int trace__process_sample(struct perf_tool *tool,
-				 union perf_event *event __maybe_unused,
+				 union perf_event *event,
 				 struct perf_sample *sample,
 				 struct perf_evsel *evsel,
 				 struct machine *machine __maybe_unused)
@@ -1799,7 +1884,7 @@ static int trace__process_sample(struct perf_tool *tool,
 
 	if (handler) {
 		++trace->nr_events;
-		handler(trace, evsel, sample);
+		handler(trace, evsel, event, sample);
 	}
 
 	return err;
@@ -1826,7 +1911,7 @@ static int parse_target_str(struct trace *trace)
 	return 0;
 }
 
-static int trace__record(int argc, const char **argv)
+static int trace__record(struct trace *trace, int argc, const char **argv)
 {
 	unsigned int rec_argc, i, j;
 	const char **rec_argv;
@@ -1835,34 +1920,54 @@ static int trace__record(int argc, const char **argv)
 		"-R",
 		"-m", "1024",
 		"-c", "1",
-		"-e",
 	};
 
+	const char * const sc_args[] = { "-e", };
+	unsigned int sc_args_nr = ARRAY_SIZE(sc_args);
+	const char * const majpf_args[] = { "-e", "major-faults" };
+	unsigned int majpf_args_nr = ARRAY_SIZE(majpf_args);
+	const char * const minpf_args[] = { "-e", "minor-faults" };
+	unsigned int minpf_args_nr = ARRAY_SIZE(minpf_args);
+
 	/* +1 is for the event string below */
-	rec_argc = ARRAY_SIZE(record_args) + 1 + argc;
+	rec_argc = ARRAY_SIZE(record_args) + sc_args_nr + 1 +
+		majpf_args_nr + minpf_args_nr + argc;
 	rec_argv = calloc(rec_argc + 1, sizeof(char *));
 
 	if (rec_argv == NULL)
 		return -ENOMEM;
 
+	j = 0;
 	for (i = 0; i < ARRAY_SIZE(record_args); i++)
-		rec_argv[i] = record_args[i];
-
-	/* event string may be different for older kernels - e.g., RHEL6 */
-	if (is_valid_tracepoint("raw_syscalls:sys_enter"))
-		rec_argv[i] = "raw_syscalls:sys_enter,raw_syscalls:sys_exit";
-	else if (is_valid_tracepoint("syscalls:sys_enter"))
-		rec_argv[i] = "syscalls:sys_enter,syscalls:sys_exit";
-	else {
-		pr_err("Neither raw_syscalls nor syscalls events exist.\n");
-		return -1;
+		rec_argv[j++] = record_args[i];
+
+	if (trace->trace_syscalls) {
+		for (i = 0; i < sc_args_nr; i++)
+			rec_argv[j++] = sc_args[i];
+
+		/* event string may be different for older kernels - e.g., RHEL6 */
+		if (is_valid_tracepoint("raw_syscalls:sys_enter"))
+			rec_argv[j++] = "raw_syscalls:sys_enter,raw_syscalls:sys_exit";
+		else if (is_valid_tracepoint("syscalls:sys_enter"))
+			rec_argv[j++] = "syscalls:sys_enter,syscalls:sys_exit";
+		else {
+			pr_err("Neither raw_syscalls nor syscalls events exist.\n");
+			return -1;
+		}
 	}
-	i++;
 
-	for (j = 0; j < (unsigned int)argc; j++, i++)
-		rec_argv[i] = argv[j];
+	if (trace->trace_pgfaults & TRACE_PFMAJ)
+		for (i = 0; i < majpf_args_nr; i++)
+			rec_argv[j++] = majpf_args[i];
+
+	if (trace->trace_pgfaults & TRACE_PFMIN)
+		for (i = 0; i < minpf_args_nr; i++)
+			rec_argv[j++] = minpf_args[i];
+
+	for (i = 0; i < (unsigned int)argc; i++)
+		rec_argv[j++] = argv[i];
 
-	return cmd_record(i, rec_argv, NULL);
+	return cmd_record(j, rec_argv, NULL);
 }
 
 static size_t trace__fprintf_thread_summary(struct trace *trace, FILE *fp);
@@ -1882,6 +1987,30 @@ static void perf_evlist__add_vfs_getname(struct perf_evlist *evlist)
 	perf_evlist__add(evlist, evsel);
 }
 
+static int perf_evlist__add_pgfault(struct perf_evlist *evlist,
+				    u64 config)
+{
+	struct perf_evsel *evsel;
+	struct perf_event_attr attr = {
+		.type = PERF_TYPE_SOFTWARE,
+		.mmap_data = 1,
+		.sample_period = 1,
+	};
+
+	attr.config = config;
+
+	event_attr_init(&attr);
+
+	evsel = perf_evsel__new(&attr);
+	if (!evsel)
+		return -ENOMEM;
+
+	evsel->handler = trace__pgfault;
+	perf_evlist__add(evlist, evsel);
+
+	return 0;
+}
+
 static int trace__run(struct trace *trace, int argc, const char **argv)
 {
 	struct perf_evlist *evlist = perf_evlist__new();
@@ -1897,10 +2026,21 @@ static int trace__run(struct trace *trace, int argc, const char **argv)
 		goto out;
 	}
 
-	if (perf_evlist__add_syscall_newtp(evlist, trace__sys_enter, trace__sys_exit))
+	if (trace->trace_syscalls &&
+	    perf_evlist__add_syscall_newtp(evlist, trace__sys_enter,
+					   trace__sys_exit))
 		goto out_error_tp;
 
-	perf_evlist__add_vfs_getname(evlist);
+	if (trace->trace_syscalls)
+		perf_evlist__add_vfs_getname(evlist);
+
+	if ((trace->trace_pgfaults & TRACE_PFMAJ) &&
+	    perf_evlist__add_pgfault(evlist, PERF_COUNT_SW_PAGE_FAULTS_MAJ))
+		goto out_error_tp;
+
+	if ((trace->trace_pgfaults & TRACE_PFMIN) &&
+	    perf_evlist__add_pgfault(evlist, PERF_COUNT_SW_PAGE_FAULTS_MIN))
+		goto out_error_tp;
 
 	if (trace->sched &&
 		perf_evlist__add_newtp(evlist, "sched", "sched_stat_runtime",
@@ -1982,7 +2122,8 @@ again:
 				goto next_event;
 			}
 
-			if (sample.raw_data == NULL) {
+			if (evsel->attr.type == PERF_TYPE_TRACEPOINT &&
+			    sample.raw_data == NULL) {
 				fprintf(trace->output, "%s sample with no payload for tid: %d, cpu %d, raw_size=%d, skipping...\n",
 				       perf_evsel__name(evsel), sample.tid,
 				       sample.cpu, sample.raw_size);
@@ -1990,7 +2131,7 @@ again:
 			}
 
 			handler = evsel->handler;
-			handler(trace, evsel, &sample);
+			handler(trace, evsel, event, &sample);
 next_event:
 			perf_evlist__mmap_consume(evlist, i);
 
@@ -2093,13 +2234,10 @@ static int trace__replay(struct trace *trace)
 	if (evsel == NULL)
 		evsel = perf_evlist__find_tracepoint_by_name(session->evlist,
 							     "syscalls:sys_enter");
-	if (evsel == NULL) {
-		pr_err("Data file does not have raw_syscalls:sys_enter event\n");
-		goto out;
-	}
 
-	if (perf_evsel__init_syscall_tp(evsel, trace__sys_enter) < 0 ||
-	    perf_evsel__init_sc_tp_ptr_field(evsel, args)) {
+	if (evsel &&
+	    (perf_evsel__init_syscall_tp(evsel, trace__sys_enter) < 0 ||
+	    perf_evsel__init_sc_tp_ptr_field(evsel, args))) {
 		pr_err("Error during initialize raw_syscalls:sys_enter event\n");
 		goto out;
 	}
@@ -2109,15 +2247,19 @@ static int trace__replay(struct trace *trace)
 	if (evsel == NULL)
 		evsel = perf_evlist__find_tracepoint_by_name(session->evlist,
 							     "syscalls:sys_exit");
-	if (evsel == NULL) {
-		pr_err("Data file does not have raw_syscalls:sys_exit event\n");
+	if (evsel &&
+	    (perf_evsel__init_syscall_tp(evsel, trace__sys_exit) < 0 ||
+	    perf_evsel__init_sc_tp_uint_field(evsel, ret))) {
+		pr_err("Error during initialize raw_syscalls:sys_exit event\n");
 		goto out;
 	}
 
-	if (perf_evsel__init_syscall_tp(evsel, trace__sys_exit) < 0 ||
-	    perf_evsel__init_sc_tp_uint_field(evsel, ret)) {
-		pr_err("Error during initialize raw_syscalls:sys_exit event\n");
-		goto out;
+	evlist__for_each(session->evlist, evsel) {
+		if (evsel->attr.type == PERF_TYPE_SOFTWARE &&
+		    (evsel->attr.config == PERF_COUNT_SW_PAGE_FAULTS_MAJ ||
+		     evsel->attr.config == PERF_COUNT_SW_PAGE_FAULTS_MIN ||
+		     evsel->attr.config == PERF_COUNT_SW_PAGE_FAULTS))
+			evsel->handler = trace__pgfault;
 	}
 
 	err = parse_target_str(trace);
@@ -2217,6 +2359,10 @@ static int trace__fprintf_one_thread(struct thread *thread, void *priv)
 	printed += fprintf(fp, " %s (%d), ", thread__comm_str(thread), thread->tid);
 	printed += fprintf(fp, "%lu events, ", ttrace->nr_events);
 	printed += fprintf(fp, "%.1f%%", ratio);
+	if (ttrace->pfmaj)
+		printed += fprintf(fp, ", %lu majfaults", ttrace->pfmaj);
+	if (ttrace->pfmin)
+		printed += fprintf(fp, ", %lu minfaults", ttrace->pfmin);
 	printed += fprintf(fp, ", %.3f msec\n", ttrace->runtime_ms);
 	printed += thread__dump_stats(ttrace, trace, fp);
 
@@ -2264,6 +2410,23 @@ static int trace__open_output(struct trace *trace, const char *filename)
 	return trace->output == NULL ? -errno : 0;
 }
 
+static int parse_pagefaults(const struct option *opt, const char *str,
+			    int unset __maybe_unused)
+{
+	int *trace_pgfaults = opt->value;
+
+	if (strcmp(str, "all") == 0)
+		*trace_pgfaults |= TRACE_PFMAJ | TRACE_PFMIN;
+	else if (strcmp(str, "maj") == 0)
+		*trace_pgfaults |= TRACE_PFMAJ;
+	else if (strcmp(str, "min") == 0)
+		*trace_pgfaults |= TRACE_PFMIN;
+	else
+		return -1;
+
+	return 0;
+}
+
 int cmd_trace(int argc, const char **argv, const char *prefix __maybe_unused)
 {
 	const char * const trace_usage[] = {
@@ -2293,6 +2456,7 @@ int cmd_trace(int argc, const char **argv, const char *prefix __maybe_unused)
 		},
 		.output = stdout,
 		.show_comm = true,
+		.trace_syscalls = true,
 	};
 	const char *output_name = NULL;
 	const char *ev_qualifier_str = NULL;
@@ -2330,20 +2494,34 @@ int cmd_trace(int argc, const char **argv, const char *prefix __maybe_unused)
 		    "Show only syscall summary with statistics"),
 	OPT_BOOLEAN('S', "with-summary", &trace.summary,
 		    "Show all syscalls and summary with statistics"),
+	OPT_CALLBACK_DEFAULT('F', "pf", &trace.trace_pgfaults, "all|maj|min",
+		     "Trace pagefaults", parse_pagefaults, "maj"),
+	OPT_BOOLEAN(0, "syscalls", &trace.trace_syscalls, "Trace syscalls"),
 	OPT_END()
 	};
 	int err;
 	char bf[BUFSIZ];
 
-	if ((argc > 1) && (strcmp(argv[1], "record") == 0))
-		return trace__record(argc-2, &argv[2]);
+	argc = parse_options(argc, argv, trace_options, trace_usage,
+			     PARSE_OPT_STOP_AT_NON_OPTION);
 
-	argc = parse_options(argc, argv, trace_options, trace_usage, 0);
+	if (trace.trace_pgfaults) {
+		trace.opts.sample_address = true;
+		trace.opts.sample_time = true;
+	}
+
+	if ((argc >= 1) && (strcmp(argv[0], "record") == 0))
+		return trace__record(&trace, argc-1, &argv[1]);
 
 	/* summary_only implies summary option, but don't overwrite summary if set */
 	if (trace.summary_only)
 		trace.summary = trace.summary_only;
 
+	if (!trace.trace_syscalls && !trace.trace_pgfaults) {
+		pr_err("Please specify something to trace.\n");
+		return -1;
+	}
+
 	if (output_name != NULL) {
 		err = trace__open_output(&trace, output_name);
 		if (err < 0) {
diff --git a/tools/perf/config/Makefile b/tools/perf/config/Makefile
index f30ac5e5d271..b7f42d577c4e 100644
--- a/tools/perf/config/Makefile
+++ b/tools/perf/config/Makefile
@@ -48,6 +48,10 @@ ifneq ($(ARCH),$(filter $(ARCH),x86 arm))
   NO_LIBDW_DWARF_UNWIND := 1
 endif
 
+ifeq ($(ARCH),powerpc)
+  CFLAGS += -DHAVE_SKIP_CALLCHAIN_IDX
+endif
+
 ifeq ($(LIBUNWIND_LIBS),)
   NO_LIBUNWIND := 1
 else
@@ -590,6 +594,10 @@ ifndef NO_LIBNUMA
   endif
 endif
 
+ifdef HAVE_KVM_STAT_SUPPORT
+    CFLAGS += -DHAVE_KVM_STAT_SUPPORT
+endif
+
 # Among the variables below, these:
 #   perfexecdir
 #   template_dir
diff --git a/tools/perf/perf-sys.h b/tools/perf/perf-sys.h
index 5268a1481d23..937e4324ad94 100644
--- a/tools/perf/perf-sys.h
+++ b/tools/perf/perf-sys.h
@@ -54,6 +54,7 @@
 #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__
diff --git a/tools/perf/scripts/perl/bin/failed-syscalls-record b/tools/perf/scripts/perl/bin/failed-syscalls-record
index 8104895a7b67..74685f318379 100644
--- a/tools/perf/scripts/perl/bin/failed-syscalls-record
+++ b/tools/perf/scripts/perl/bin/failed-syscalls-record
@@ -1,2 +1,3 @@
 #!/bin/bash
-perf record -e raw_syscalls:sys_exit $@
+(perf record -e raw_syscalls:sys_exit $@ || \
+ perf record -e syscalls:sys_exit $@) 2> /dev/null
diff --git a/tools/perf/scripts/perl/failed-syscalls.pl b/tools/perf/scripts/perl/failed-syscalls.pl
index 94bc25a347eb..55e7ae4c5c88 100644
--- a/tools/perf/scripts/perl/failed-syscalls.pl
+++ b/tools/perf/scripts/perl/failed-syscalls.pl
@@ -26,6 +26,11 @@ sub raw_syscalls::sys_exit
 	}
 }
 
+sub syscalls::sys_exit
+{
+	raw_syscalls::sys_exit(@_)
+}
+
 sub trace_end
 {
     printf("\nfailed syscalls by comm:\n\n");
diff --git a/tools/perf/scripts/python/bin/failed-syscalls-by-pid-record b/tools/perf/scripts/python/bin/failed-syscalls-by-pid-record
index 8104895a7b67..74685f318379 100644
--- a/tools/perf/scripts/python/bin/failed-syscalls-by-pid-record
+++ b/tools/perf/scripts/python/bin/failed-syscalls-by-pid-record
@@ -1,2 +1,3 @@
 #!/bin/bash
-perf record -e raw_syscalls:sys_exit $@
+(perf record -e raw_syscalls:sys_exit $@ || \
+ perf record -e syscalls:sys_exit $@) 2> /dev/null
diff --git a/tools/perf/scripts/python/bin/sctop-record b/tools/perf/scripts/python/bin/sctop-record
index 4efbfaa7f6a5..d6940841e54f 100644
--- a/tools/perf/scripts/python/bin/sctop-record
+++ b/tools/perf/scripts/python/bin/sctop-record
@@ -1,2 +1,3 @@
 #!/bin/bash
-perf record -e raw_syscalls:sys_enter $@
+(perf record -e raw_syscalls:sys_enter $@ || \
+ perf record -e syscalls:sys_enter $@) 2> /dev/null
diff --git a/tools/perf/scripts/python/bin/syscall-counts-by-pid-record b/tools/perf/scripts/python/bin/syscall-counts-by-pid-record
index 4efbfaa7f6a5..d6940841e54f 100644
--- a/tools/perf/scripts/python/bin/syscall-counts-by-pid-record
+++ b/tools/perf/scripts/python/bin/syscall-counts-by-pid-record
@@ -1,2 +1,3 @@
 #!/bin/bash
-perf record -e raw_syscalls:sys_enter $@
+(perf record -e raw_syscalls:sys_enter $@ || \
+ perf record -e syscalls:sys_enter $@) 2> /dev/null
diff --git a/tools/perf/scripts/python/bin/syscall-counts-record b/tools/perf/scripts/python/bin/syscall-counts-record
index 4efbfaa7f6a5..d6940841e54f 100644
--- a/tools/perf/scripts/python/bin/syscall-counts-record
+++ b/tools/perf/scripts/python/bin/syscall-counts-record
@@ -1,2 +1,3 @@
 #!/bin/bash
-perf record -e raw_syscalls:sys_enter $@
+(perf record -e raw_syscalls:sys_enter $@ || \
+ perf record -e syscalls:sys_enter $@) 2> /dev/null
diff --git a/tools/perf/scripts/python/failed-syscalls-by-pid.py b/tools/perf/scripts/python/failed-syscalls-by-pid.py
index 85805fac4116..266a8364bce5 100644
--- a/tools/perf/scripts/python/failed-syscalls-by-pid.py
+++ b/tools/perf/scripts/python/failed-syscalls-by-pid.py
@@ -50,6 +50,11 @@ def raw_syscalls__sys_exit(event_name, context, common_cpu,
 		except TypeError:
 			syscalls[common_comm][common_pid][id][ret] = 1
 
+def syscalls__sys_exit(event_name, context, common_cpu,
+	common_secs, common_nsecs, common_pid, common_comm,
+	id, ret):
+	raw_syscalls__sys_exit(**locals())
+
 def print_error_totals():
     if for_comm is not None:
 	    print "\nsyscall errors for %s:\n\n" % (for_comm),
diff --git a/tools/perf/scripts/python/sctop.py b/tools/perf/scripts/python/sctop.py
index 42c267e292fa..c9f3058b7dd4 100644
--- a/tools/perf/scripts/python/sctop.py
+++ b/tools/perf/scripts/python/sctop.py
@@ -53,6 +53,11 @@ def raw_syscalls__sys_enter(event_name, context, common_cpu,
 	except TypeError:
 		syscalls[id] = 1
 
+def syscalls__sys_enter(event_name, context, common_cpu,
+	common_secs, common_nsecs, common_pid, common_comm,
+	id, args):
+	raw_syscalls__sys_enter(**locals())
+
 def print_syscall_totals(interval):
 	while 1:
 		clear_term()
diff --git a/tools/perf/scripts/python/syscall-counts-by-pid.py b/tools/perf/scripts/python/syscall-counts-by-pid.py
index c64d1c55d745..cf2054c529c9 100644
--- a/tools/perf/scripts/python/syscall-counts-by-pid.py
+++ b/tools/perf/scripts/python/syscall-counts-by-pid.py
@@ -48,6 +48,11 @@ def raw_syscalls__sys_enter(event_name, context, common_cpu,
 	except TypeError:
 		syscalls[common_comm][common_pid][id] = 1
 
+def syscalls__sys_enter(event_name, context, common_cpu,
+	common_secs, common_nsecs, common_pid, common_comm,
+	id, args):
+	raw_syscalls__sys_enter(**locals())
+
 def print_syscall_totals():
     if for_comm is not None:
 	    print "\nsyscall events for %s:\n\n" % (for_comm),
diff --git a/tools/perf/scripts/python/syscall-counts.py b/tools/perf/scripts/python/syscall-counts.py
index b435d3f188e8..92b29381bd39 100644
--- a/tools/perf/scripts/python/syscall-counts.py
+++ b/tools/perf/scripts/python/syscall-counts.py
@@ -44,6 +44,11 @@ def raw_syscalls__sys_enter(event_name, context, common_cpu,
 	except TypeError:
 		syscalls[id] = 1
 
+def syscalls__sys_enter(event_name, context, common_cpu,
+	common_secs, common_nsecs, common_pid, common_comm,
+	id, args):
+	raw_syscalls__sys_enter(**locals())
+
 def print_syscall_totals():
     if for_comm is not None:
 	    print "\nsyscall events for %s:\n\n" % (for_comm),
diff --git a/tools/perf/ui/browser.c b/tools/perf/ui/browser.c
index 3ccf6e14f89b..6680fa5cb9dd 100644
--- a/tools/perf/ui/browser.c
+++ b/tools/perf/ui/browser.c
@@ -150,7 +150,7 @@ unsigned int ui_browser__rb_tree_refresh(struct ui_browser *browser)
 	while (nd != NULL) {
 		ui_browser__gotorc(browser, row, 0);
 		browser->write(browser, nd, row);
-		if (++row == browser->height)
+		if (++row == browser->rows)
 			break;
 		nd = rb_next(nd);
 	}
@@ -166,7 +166,7 @@ bool ui_browser__is_current_entry(struct ui_browser *browser, unsigned row)
 void ui_browser__refresh_dimensions(struct ui_browser *browser)
 {
 	browser->width = SLtt_Screen_Cols - 1;
-	browser->height = SLtt_Screen_Rows - 2;
+	browser->height = browser->rows = SLtt_Screen_Rows - 2;
 	browser->y = 1;
 	browser->x = 0;
 }
@@ -250,7 +250,10 @@ int ui_browser__show(struct ui_browser *browser, const char *title,
 	int err;
 	va_list ap;
 
-	ui_browser__refresh_dimensions(browser);
+	if (browser->refresh_dimensions == NULL)
+		browser->refresh_dimensions = ui_browser__refresh_dimensions;
+
+	browser->refresh_dimensions(browser);
 
 	pthread_mutex_lock(&ui__lock);
 	__ui_browser__show_title(browser, title);
@@ -279,7 +282,7 @@ static void ui_browser__scrollbar_set(struct ui_browser *browser)
 {
 	int height = browser->height, h = 0, pct = 0,
 	    col = browser->width,
-	    row = browser->y - 1;
+	    row = 0;
 
 	if (browser->nr_entries > 1) {
 		pct = ((browser->index * (browser->height - 1)) /
@@ -367,7 +370,7 @@ int ui_browser__run(struct ui_browser *browser, int delay_secs)
 
 		if (key == K_RESIZE) {
 			ui__refresh_dimensions(false);
-			ui_browser__refresh_dimensions(browser);
+			browser->refresh_dimensions(browser);
 			__ui_browser__show_title(browser, browser->title);
 			ui_helpline__puts(browser->helpline);
 			continue;
@@ -389,7 +392,7 @@ int ui_browser__run(struct ui_browser *browser, int delay_secs)
 			if (browser->index == browser->nr_entries - 1)
 				break;
 			++browser->index;
-			if (browser->index == browser->top_idx + browser->height) {
+			if (browser->index == browser->top_idx + browser->rows) {
 				++browser->top_idx;
 				browser->seek(browser, +1, SEEK_CUR);
 			}
@@ -405,10 +408,10 @@ int ui_browser__run(struct ui_browser *browser, int delay_secs)
 			break;
 		case K_PGDN:
 		case ' ':
-			if (browser->top_idx + browser->height > browser->nr_entries - 1)
+			if (browser->top_idx + browser->rows > browser->nr_entries - 1)
 				break;
 
-			offset = browser->height;
+			offset = browser->rows;
 			if (browser->index + offset > browser->nr_entries - 1)
 				offset = browser->nr_entries - 1 - browser->index;
 			browser->index += offset;
@@ -419,10 +422,10 @@ int ui_browser__run(struct ui_browser *browser, int delay_secs)
 			if (browser->top_idx == 0)
 				break;
 
-			if (browser->top_idx < browser->height)
+			if (browser->top_idx < browser->rows)
 				offset = browser->top_idx;
 			else
-				offset = browser->height;
+				offset = browser->rows;
 
 			browser->index -= offset;
 			browser->top_idx -= offset;
@@ -432,7 +435,7 @@ int ui_browser__run(struct ui_browser *browser, int delay_secs)
 			ui_browser__reset_index(browser);
 			break;
 		case K_END:
-			offset = browser->height - 1;
+			offset = browser->rows - 1;
 			if (offset >= browser->nr_entries)
 				offset = browser->nr_entries - 1;
 
@@ -462,7 +465,7 @@ unsigned int ui_browser__list_head_refresh(struct ui_browser *browser)
 		if (!browser->filter || !browser->filter(browser, pos)) {
 			ui_browser__gotorc(browser, row, 0);
 			browser->write(browser, pos, row);
-			if (++row == browser->height)
+			if (++row == browser->rows)
 				break;
 		}
 	}
@@ -587,7 +590,7 @@ unsigned int ui_browser__argv_refresh(struct ui_browser *browser)
 		if (!browser->filter || !browser->filter(browser, *pos)) {
 			ui_browser__gotorc(browser, row, 0);
 			browser->write(browser, pos, row);
-			if (++row == browser->height)
+			if (++row == browser->rows)
 				break;
 		}
 
@@ -623,7 +626,7 @@ static void __ui_browser__line_arrow_up(struct ui_browser *browser,
 
 	SLsmg_set_char_set(1);
 
-	if (start < browser->top_idx + browser->height) {
+	if (start < browser->top_idx + browser->rows) {
 		row = start - browser->top_idx;
 		ui_browser__gotorc(browser, row, column);
 		SLsmg_write_char(SLSMG_LLCORN_CHAR);
@@ -633,7 +636,7 @@ static void __ui_browser__line_arrow_up(struct ui_browser *browser,
 		if (row-- == 0)
 			goto out;
 	} else
-		row = browser->height - 1;
+		row = browser->rows - 1;
 
 	if (end > browser->top_idx)
 		end_row = end - browser->top_idx;
@@ -675,8 +678,8 @@ static void __ui_browser__line_arrow_down(struct ui_browser *browser,
 	} else
 		row = 0;
 
-	if (end >= browser->top_idx + browser->height)
-		end_row = browser->height - 1;
+	if (end >= browser->top_idx + browser->rows)
+		end_row = browser->rows - 1;
 	else
 		end_row = end - browser->top_idx;
 
@@ -684,7 +687,7 @@ static void __ui_browser__line_arrow_down(struct ui_browser *browser,
 	SLsmg_draw_vline(end_row - row + 1);
 
 	ui_browser__gotorc(browser, end_row, column);
-	if (end < browser->top_idx + browser->height) {
+	if (end < browser->top_idx + browser->rows) {
 		SLsmg_write_char(SLSMG_LLCORN_CHAR);
 		ui_browser__gotorc(browser, end_row, column + 1);
 		SLsmg_write_char(SLSMG_HLINE_CHAR);
diff --git a/tools/perf/ui/browser.h b/tools/perf/ui/browser.h
index 03d4d6295f10..92ae72113965 100644
--- a/tools/perf/ui/browser.h
+++ b/tools/perf/ui/browser.h
@@ -14,11 +14,12 @@
 struct ui_browser {
 	u64	      index, top_idx;
 	void	      *top, *entries;
-	u16	      y, x, width, height;
+	u16	      y, x, width, height, rows;
 	int	      current_color;
 	void	      *priv;
 	const char    *title;
 	char	      *helpline;
+	void 	      (*refresh_dimensions)(struct ui_browser *browser);
 	unsigned int  (*refresh)(struct ui_browser *browser);
 	void	      (*write)(struct ui_browser *browser, void *entry, int row);
 	void	      (*seek)(struct ui_browser *browser, off_t offset, int whence);
diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c
index 04a229aa5c0f..a94b11fc5e00 100644
--- a/tools/perf/ui/browsers/hists.c
+++ b/tools/perf/ui/browsers/hists.c
@@ -26,6 +26,7 @@ struct hist_browser {
 	struct map_symbol   *selection;
 	int		     print_seq;
 	bool		     show_dso;
+	bool		     show_headers;
 	float		     min_pcnt;
 	u64		     nr_non_filtered_entries;
 	u64		     nr_callchain_rows;
@@ -33,8 +34,7 @@ struct hist_browser {
 
 extern void hist_browser__init_hpp(void);
 
-static int hists__browser_title(struct hists *hists, char *bf, size_t size,
-				const char *ev_name);
+static int hists__browser_title(struct hists *hists, char *bf, size_t size);
 static void hist_browser__update_nr_entries(struct hist_browser *hb);
 
 static struct rb_node *hists__filter_entries(struct rb_node *nd,
@@ -57,11 +57,42 @@ static u32 hist_browser__nr_entries(struct hist_browser *hb)
 	return nr_entries + hb->nr_callchain_rows;
 }
 
-static void hist_browser__refresh_dimensions(struct hist_browser *browser)
+static void hist_browser__update_rows(struct hist_browser *hb)
 {
+	struct ui_browser *browser = &hb->b;
+	u16 header_offset = hb->show_headers ? 1 : 0, index_row;
+
+	browser->rows = browser->height - header_offset;
+	/*
+	 * Verify if we were at the last line and that line isn't
+	 * visibe because we now show the header line(s).
+	 */
+	index_row = browser->index - browser->top_idx;
+	if (index_row >= browser->rows)
+		browser->index -= index_row - browser->rows + 1;
+}
+
+static void hist_browser__refresh_dimensions(struct ui_browser *browser)
+{
+	struct hist_browser *hb = container_of(browser, struct hist_browser, b);
+
 	/* 3 == +/- toggle symbol before actual hist_entry rendering */
-	browser->b.width = 3 + (hists__sort_list_width(browser->hists) +
-			     sizeof("[k]"));
+	browser->width = 3 + (hists__sort_list_width(hb->hists) + sizeof("[k]"));
+	/*
+ 	 * FIXME: Just keeping existing behaviour, but this really should be
+ 	 *	  before updating browser->width, as it will invalidate the
+ 	 *	  calculation above. Fix this and the fallout in another
+ 	 *	  changeset.
+ 	 */
+	ui_browser__refresh_dimensions(browser);
+	hist_browser__update_rows(hb);
+}
+
+static void hist_browser__gotorc(struct hist_browser *browser, int row, int column)
+{
+	u16 header_offset = browser->show_headers ? 1 : 0;
+
+	ui_browser__gotorc(&browser->b, row + header_offset, column);
 }
 
 static void hist_browser__reset(struct hist_browser *browser)
@@ -74,7 +105,7 @@ static void hist_browser__reset(struct hist_browser *browser)
 
 	hist_browser__update_nr_entries(browser);
 	browser->b.nr_entries = hist_browser__nr_entries(browser);
-	hist_browser__refresh_dimensions(browser);
+	hist_browser__refresh_dimensions(&browser->b);
 	ui_browser__reset_index(&browser->b);
 }
 
@@ -346,7 +377,7 @@ 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, const char *ev_name,
+static int hist_browser__run(struct hist_browser *browser,
 			     struct hist_browser_timer *hbt)
 {
 	int key;
@@ -356,8 +387,7 @@ static int hist_browser__run(struct hist_browser *browser, const char *ev_name,
 	browser->b.entries = &browser->hists->entries;
 	browser->b.nr_entries = hist_browser__nr_entries(browser);
 
-	hist_browser__refresh_dimensions(browser);
-	hists__browser_title(browser->hists, title, sizeof(title), ev_name);
+	hists__browser_title(browser->hists, title, sizeof(title));
 
 	if (ui_browser__show(&browser->b, title,
 			     "Press '?' for help on key bindings") < 0)
@@ -384,7 +414,7 @@ static int hist_browser__run(struct hist_browser *browser, const char *ev_name,
 				ui_browser__warn_lost_events(&browser->b);
 			}
 
-			hists__browser_title(browser->hists, title, sizeof(title), ev_name);
+			hists__browser_title(browser->hists, title, sizeof(title));
 			ui_browser__show_title(&browser->b, title);
 			continue;
 		}
@@ -393,10 +423,10 @@ static int hist_browser__run(struct hist_browser *browser, const char *ev_name,
 			struct hist_entry *h = rb_entry(browser->b.top,
 							struct hist_entry, rb_node);
 			ui_helpline__pop();
-			ui_helpline__fpush("%d: nr_ent=(%d,%d), height=%d, idx=%d, fve: idx=%d, row_off=%d, nrows=%d",
+			ui_helpline__fpush("%d: nr_ent=(%d,%d), rows=%d, idx=%d, fve: idx=%d, row_off=%d, nrows=%d",
 					   seq++, browser->b.nr_entries,
 					   browser->hists->nr_entries,
-					   browser->b.height,
+					   browser->b.rows,
 					   browser->b.index,
 					   browser->b.top_idx,
 					   h->row_offset, h->nr_rows);
@@ -410,6 +440,10 @@ static int hist_browser__run(struct hist_browser *browser, const char *ev_name,
 			/* Expand the whole world. */
 			hist_browser__set_folding(browser, true);
 			break;
+		case 'H':
+			browser->show_headers = !browser->show_headers;
+			hist_browser__update_rows(browser);
+			break;
 		case K_ENTER:
 			if (hist_browser__toggle_fold(browser))
 				break;
@@ -509,13 +543,13 @@ static int hist_browser__show_callchain_node_rb_tree(struct hist_browser *browse
 			}
 
 			ui_browser__set_color(&browser->b, color);
-			ui_browser__gotorc(&browser->b, row, 0);
+			hist_browser__gotorc(browser, row, 0);
 			slsmg_write_nstring(" ", offset + extra_offset);
 			slsmg_printf("%c ", folded_sign);
 			slsmg_write_nstring(str, width);
 			free(alloc_str);
 
-			if (++row == browser->b.height)
+			if (++row == browser->b.rows)
 				goto out;
 do_next:
 			if (folded_sign == '+')
@@ -528,7 +562,7 @@ do_next:
 									 new_level, row, row_offset,
 									 is_current_entry);
 		}
-		if (row == browser->b.height)
+		if (row == browser->b.rows)
 			goto out;
 		node = next;
 	}
@@ -568,13 +602,13 @@ static int hist_browser__show_callchain_node(struct hist_browser *browser,
 
 		s = callchain_list__sym_name(chain, bf, sizeof(bf),
 					     browser->show_dso);
-		ui_browser__gotorc(&browser->b, row, 0);
+		hist_browser__gotorc(browser, row, 0);
 		ui_browser__set_color(&browser->b, color);
 		slsmg_write_nstring(" ", offset);
 		slsmg_printf("%c ", folded_sign);
 		slsmg_write_nstring(s, width - 2);
 
-		if (++row == browser->b.height)
+		if (++row == browser->b.rows)
 			goto out;
 	}
 
@@ -603,7 +637,7 @@ static int hist_browser__show_callchain(struct hist_browser *browser,
 		row += hist_browser__show_callchain_node(browser, node, level,
 							 row, row_offset,
 							 is_current_entry);
-		if (row == browser->b.height)
+		if (row == browser->b.rows)
 			break;
 	}
 
@@ -733,7 +767,7 @@ static int hist_browser__show_entry(struct hist_browser *browser,
 			.ptr		= &arg,
 		};
 
-		ui_browser__gotorc(&browser->b, row, 0);
+		hist_browser__gotorc(browser, row, 0);
 
 		perf_hpp__for_each_format(fmt) {
 			if (perf_hpp__should_skip(fmt))
@@ -777,7 +811,7 @@ static int hist_browser__show_entry(struct hist_browser *browser,
 	} else
 		--row_offset;
 
-	if (folded_sign == '-' && row != browser->b.height) {
+	if (folded_sign == '-' && row != browser->b.rows) {
 		printed += hist_browser__show_callchain(browser, &entry->sorted_chain,
 							1, row, &row_offset,
 							&current_entry);
@@ -788,6 +822,56 @@ static int hist_browser__show_entry(struct hist_browser *browser,
 	return printed;
 }
 
+static int advance_hpp_check(struct perf_hpp *hpp, int inc)
+{
+	advance_hpp(hpp, inc);
+	return hpp->size <= 0;
+}
+
+static int hists__scnprintf_headers(char *buf, size_t size, struct hists *hists)
+{
+	struct perf_hpp dummy_hpp = {
+		.buf    = buf,
+		.size   = size,
+	};
+	struct perf_hpp_fmt *fmt;
+	size_t ret = 0;
+
+	if (symbol_conf.use_callchain) {
+		ret = scnprintf(buf, size, "  ");
+		if (advance_hpp_check(&dummy_hpp, ret))
+			return ret;
+	}
+
+	perf_hpp__for_each_format(fmt) {
+		if (perf_hpp__should_skip(fmt))
+			continue;
+
+		/* We need to add the length of the columns header. */
+		perf_hpp__reset_width(fmt, hists);
+
+		ret = fmt->header(fmt, &dummy_hpp, hists_to_evsel(hists));
+		if (advance_hpp_check(&dummy_hpp, ret))
+			break;
+
+		ret = scnprintf(dummy_hpp.buf, dummy_hpp.size, "  ");
+		if (advance_hpp_check(&dummy_hpp, ret))
+			break;
+	}
+
+	return ret;
+}
+
+static void hist_browser__show_headers(struct hist_browser *browser)
+{
+	char headers[1024];
+
+	hists__scnprintf_headers(headers, sizeof(headers), browser->hists);
+	ui_browser__gotorc(&browser->b, 0, 0);
+	ui_browser__set_color(&browser->b, HE_COLORSET_ROOT);
+	slsmg_write_nstring(headers, browser->b.width + 1);
+}
+
 static void ui_browser__hists_init_top(struct ui_browser *browser)
 {
 	if (browser->top == NULL) {
@@ -801,9 +885,15 @@ static void ui_browser__hists_init_top(struct ui_browser *browser)
 static unsigned int hist_browser__refresh(struct ui_browser *browser)
 {
 	unsigned row = 0;
+	u16 header_offset = 0;
 	struct rb_node *nd;
 	struct hist_browser *hb = container_of(browser, struct hist_browser, b);
 
+	if (hb->show_headers) {
+		hist_browser__show_headers(hb);
+		header_offset = 1;
+	}
+
 	ui_browser__hists_init_top(browser);
 
 	for (nd = browser->top; nd; nd = rb_next(nd)) {
@@ -818,11 +908,11 @@ static unsigned int hist_browser__refresh(struct ui_browser *browser)
 			continue;
 
 		row += hist_browser__show_entry(hb, h, row);
-		if (row == browser->height)
+		if (row == browser->rows)
 			break;
 	}
 
-	return row;
+	return row + header_offset;
 }
 
 static struct rb_node *hists__filter_entries(struct rb_node *nd,
@@ -1191,8 +1281,10 @@ static struct hist_browser *hist_browser__new(struct hists *hists)
 	if (browser) {
 		browser->hists = hists;
 		browser->b.refresh = hist_browser__refresh;
+		browser->b.refresh_dimensions = hist_browser__refresh_dimensions;
 		browser->b.seek = ui_browser__hists_seek;
 		browser->b.use_navkeypressed = true;
+		browser->show_headers = symbol_conf.show_hist_headers;
 	}
 
 	return browser;
@@ -1213,8 +1305,7 @@ static struct thread *hist_browser__selected_thread(struct hist_browser *browser
 	return browser->he_selection->thread;
 }
 
-static int hists__browser_title(struct hists *hists, char *bf, size_t size,
-				const char *ev_name)
+static int hists__browser_title(struct hists *hists, char *bf, size_t size)
 {
 	char unit;
 	int printed;
@@ -1223,6 +1314,7 @@ static int hists__browser_title(struct hists *hists, char *bf, size_t size,
 	unsigned long nr_samples = hists->stats.nr_events[PERF_RECORD_SAMPLE];
 	u64 nr_events = hists->stats.total_period;
 	struct perf_evsel *evsel = hists_to_evsel(hists);
+	const char *ev_name = perf_evsel__name(evsel);
 	char buf[512];
 	size_t buflen = sizeof(buf);
 
@@ -1390,7 +1482,7 @@ static void hist_browser__update_nr_entries(struct hist_browser *hb)
 }
 
 static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
-				    const char *helpline, const char *ev_name,
+				    const char *helpline,
 				    bool left_exits,
 				    struct hist_browser_timer *hbt,
 				    float min_pcnt,
@@ -1422,6 +1514,7 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
 	"d             Zoom into current DSO\n"				\
 	"E             Expand all callchains\n"				\
 	"F             Toggle percentage of filtered entries\n"		\
+	"H             Display column headers\n"			\
 
 	/* help messages are sorted by lexical order of the hotkey */
 	const char report_help[] = HIST_BROWSER_HELP_COMMON
@@ -1465,7 +1558,7 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
 
 		nr_options = 0;
 
-		key = hist_browser__run(browser, ev_name, hbt);
+		key = hist_browser__run(browser, hbt);
 
 		if (browser->he_selection != NULL) {
 			thread = hist_browser__selected_thread(browser);
@@ -1843,7 +1936,7 @@ static int perf_evsel_menu__run(struct perf_evsel_menu *menu,
 {
 	struct perf_evlist *evlist = menu->b.priv;
 	struct perf_evsel *pos;
-	const char *ev_name, *title = "Available samples";
+	const char *title = "Available samples";
 	int delay_secs = hbt ? hbt->refresh : 0;
 	int key;
 
@@ -1876,9 +1969,8 @@ browse_hists:
 			 */
 			if (hbt)
 				hbt->timer(hbt->arg);
-			ev_name = perf_evsel__name(pos);
 			key = perf_evsel__hists_browse(pos, nr_events, help,
-						       ev_name, true, hbt,
+						       true, hbt,
 						       menu->min_pcnt,
 						       menu->env);
 			ui_browser__show_title(&menu->b, title);
@@ -1982,10 +2074,9 @@ int perf_evlist__tui_browse_hists(struct perf_evlist *evlist, const char *help,
 single_entry:
 	if (nr_entries == 1) {
 		struct perf_evsel *first = perf_evlist__first(evlist);
-		const char *ev_name = perf_evsel__name(first);
 
 		return perf_evsel__hists_browse(first, nr_entries, help,
-						ev_name, false, hbt, min_pcnt,
+						false, hbt, min_pcnt,
 						env);
 	}
 
diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h
index 8f84423a75da..da43619d6173 100644
--- a/tools/perf/util/callchain.h
+++ b/tools/perf/util/callchain.h
@@ -176,4 +176,17 @@ static inline void callchain_cursor_snapshot(struct callchain_cursor *dest,
 	dest->first = src->curr;
 	dest->nr -= src->pos;
 }
+
+#ifdef HAVE_SKIP_CALLCHAIN_IDX
+extern int arch_skip_callchain_idx(struct machine *machine,
+			struct thread *thread, struct ip_callchain *chain);
+#else
+static inline int arch_skip_callchain_idx(struct machine *machine __maybe_unused,
+			struct thread *thread __maybe_unused,
+			struct ip_callchain *chain __maybe_unused)
+{
+	return -1;
+}
+#endif
+
 #endif	/* __PERF_CALLCHAIN_H */
diff --git a/tools/perf/util/config.c b/tools/perf/util/config.c
index 24519e14ac56..1e5e2e5af6b1 100644
--- a/tools/perf/util/config.c
+++ b/tools/perf/util/config.c
@@ -350,6 +350,16 @@ static int perf_default_core_config(const char *var __maybe_unused,
 	return 0;
 }
 
+static int perf_ui_config(const char *var, const char *value)
+{
+	/* Add other config variables here. */
+	if (!strcmp(var, "ui.show-headers")) {
+		symbol_conf.show_hist_headers = perf_config_bool(var, value);
+		return 0;
+	}
+	return 0;
+}
+
 int perf_default_config(const char *var, const char *value,
 			void *dummy __maybe_unused)
 {
@@ -359,6 +369,9 @@ int perf_default_config(const char *var, const char *value,
 	if (!prefixcmp(var, "hist."))
 		return perf_hist_config(var, value);
 
+	if (!prefixcmp(var, "ui."))
+		return perf_ui_config(var, value);
+
 	/* Add other config variables here. */
 	return 0;
 }
diff --git a/tools/perf/util/data.c b/tools/perf/util/data.c
index 55de44ecebef..ee370a7f2444 100644
--- a/tools/perf/util/data.c
+++ b/tools/perf/util/data.c
@@ -65,7 +65,7 @@ static int open_file_read(struct perf_data_file *file)
 		goto out_close;
 
 	if (!file->force && st.st_uid && (st.st_uid != geteuid())) {
-		pr_err("file %s not owned by current user or root\n",
+		pr_err("File %s not owned by current user or root (use -f to override)\n",
 		       file->path);
 		goto out_close;
 	}
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index 59ef2802fcf6..c51223ac25f4 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -1214,10 +1214,11 @@ int perf_evlist__strerror_open(struct perf_evlist *evlist __maybe_unused,
 					     "For your workloads it needs to be <= 1\nHint:\t");
 		}
 		printed += scnprintf(buf + printed, size - printed,
-				     "For system wide tracing it needs to be set to -1");
+				     "For system wide tracing it needs to be set to -1.\n");
 
 		printed += scnprintf(buf + printed, size - printed,
-				    ".\nHint:\tThe current value is %d.", value);
+				    "Hint:\tTry: 'sudo sh -c \"echo -1 > /proc/sys/kernel/perf_event_paranoid\"'\n"
+				    "Hint:\tThe current value is %d.", value);
 		break;
 	default:
 		scnprintf(buf, size, "%s", emsg);
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index c73e1fc12e53..e9b943acaa5e 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -1281,7 +1281,9 @@ static int machine__resolve_callchain_sample(struct machine *machine,
 	u8 cpumode = PERF_RECORD_MISC_USER;
 	int chain_nr = min(max_stack, (int)chain->nr);
 	int i;
+	int j;
 	int err;
+	int skip_idx __maybe_unused;
 
 	callchain_cursor_reset(&callchain_cursor);
 
@@ -1290,14 +1292,26 @@ static int machine__resolve_callchain_sample(struct machine *machine,
 		return 0;
 	}
 
+	/*
+	 * Based on DWARF debug information, some architectures skip
+	 * a callchain entry saved by the kernel.
+	 */
+	skip_idx = arch_skip_callchain_idx(machine, thread, chain);
+
 	for (i = 0; i < chain_nr; i++) {
 		u64 ip;
 		struct addr_location al;
 
 		if (callchain_param.order == ORDER_CALLEE)
-			ip = chain->ips[i];
+			j = i;
 		else
-			ip = chain->ips[chain->nr - i - 1];
+			j = chain->nr - i - 1;
+
+#ifdef HAVE_SKIP_CALLCHAIN_IDX
+		if (j == skip_idx)
+			continue;
+#endif
+		ip = chain->ips[j];
 
 		if (ip >= PERF_CONTEXT_MAX) {
 			switch (ip) {
diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index 1c419321f707..e55b65a65558 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -231,6 +231,47 @@ static inline struct event_format *find_cache_event(struct perf_evsel *evsel)
 	return event;
 }
 
+static PyObject *get_field_numeric_entry(struct event_format *event,
+		struct format_field *field, void *data)
+{
+	bool is_array = field->flags & FIELD_IS_ARRAY;
+	PyObject *obj, *list = NULL;
+	unsigned long long val;
+	unsigned int item_size, n_items, i;
+
+	if (is_array) {
+		list = PyList_New(field->arraylen);
+		item_size = field->size / field->arraylen;
+		n_items = field->arraylen;
+	} else {
+		item_size = field->size;
+		n_items = 1;
+	}
+
+	for (i = 0; i < n_items; i++) {
+
+		val = read_size(event, data + field->offset + i * item_size,
+				item_size);
+		if (field->flags & FIELD_IS_SIGNED) {
+			if ((long long)val >= LONG_MIN &&
+					(long long)val <= LONG_MAX)
+				obj = PyInt_FromLong(val);
+			else
+				obj = PyLong_FromLongLong(val);
+		} else {
+			if (val <= LONG_MAX)
+				obj = PyInt_FromLong(val);
+			else
+				obj = PyLong_FromUnsignedLongLong(val);
+		}
+		if (is_array)
+			PyList_SET_ITEM(list, i, obj);
+	}
+	if (is_array)
+		obj = list;
+	return obj;
+}
+
 static void python_process_tracepoint(struct perf_sample *sample,
 				      struct perf_evsel *evsel,
 				      struct thread *thread,
@@ -239,7 +280,6 @@ static void python_process_tracepoint(struct perf_sample *sample,
 	PyObject *handler, *retval, *context, *t, *obj, *dict = NULL;
 	static char handler_name[256];
 	struct format_field *field;
-	unsigned long long val;
 	unsigned long s, ns;
 	struct event_format *event;
 	unsigned n = 0;
@@ -303,20 +343,7 @@ static void python_process_tracepoint(struct perf_sample *sample,
 				offset = field->offset;
 			obj = PyString_FromString((char *)data + offset);
 		} else { /* FIELD_IS_NUMERIC */
-			val = read_size(event, data + field->offset,
-					field->size);
-			if (field->flags & FIELD_IS_SIGNED) {
-				if ((long long)val >= LONG_MIN &&
-				    (long long)val <= LONG_MAX)
-					obj = PyInt_FromLong(val);
-				else
-					obj = PyLong_FromLongLong(val);
-			} else {
-				if (val <= LONG_MAX)
-					obj = PyInt_FromLong(val);
-				else
-					obj = PyLong_FromUnsignedLongLong(val);
-			}
+			obj = get_field_numeric_entry(event, field, data);
 		}
 		if (handler)
 			PyTuple_SetItem(t, n++, obj);
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index 1ec57dd82284..14e5a039bc45 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -1215,7 +1215,7 @@ static int __sort__hpp_header(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
 	hse = container_of(fmt, struct hpp_sort_entry, hpp);
 	len = hists__col_len(&evsel->hists, hse->se->se_width_idx);
 
-	return scnprintf(hpp->buf, hpp->size, "%*s", len, hse->se->se_header);
+	return scnprintf(hpp->buf, hpp->size, "%-*s", len, hse->se->se_header);
 }
 
 static int __sort__hpp_width(struct perf_hpp_fmt *fmt,
diff --git a/tools/perf/util/svghelper.c b/tools/perf/util/svghelper.c
index 6a0a13d07a28..283d3e73e2f2 100644
--- a/tools/perf/util/svghelper.c
+++ b/tools/perf/util/svghelper.c
@@ -30,6 +30,7 @@ static u64 turbo_frequency, max_freq;
 
 #define SLOT_MULT 30.0
 #define SLOT_HEIGHT 25.0
+#define SLOT_HALF (SLOT_HEIGHT / 2)
 
 int svg_page_width = 1000;
 u64 svg_highlight;
@@ -114,8 +115,14 @@ void open_svg(const char *filename, int cpus, int rows, u64 start, u64 end)
 	fprintf(svgfile, "      rect          { stroke-width: 1; }\n");
 	fprintf(svgfile, "      rect.process  { fill:rgb(180,180,180); fill-opacity:0.9; stroke-width:1;   stroke:rgb(  0,  0,  0); } \n");
 	fprintf(svgfile, "      rect.process2 { fill:rgb(180,180,180); fill-opacity:0.9; stroke-width:0;   stroke:rgb(  0,  0,  0); } \n");
+	fprintf(svgfile, "      rect.process3 { fill:rgb(180,180,180); fill-opacity:0.5; stroke-width:0;   stroke:rgb(  0,  0,  0); } \n");
 	fprintf(svgfile, "      rect.sample   { fill:rgb(  0,  0,255); fill-opacity:0.8; stroke-width:0;   stroke:rgb(  0,  0,  0); } \n");
 	fprintf(svgfile, "      rect.sample_hi{ fill:rgb(255,128,  0); fill-opacity:0.8; stroke-width:0;   stroke:rgb(  0,  0,  0); } \n");
+	fprintf(svgfile, "      rect.error    { fill:rgb(255,  0,  0); fill-opacity:0.5; stroke-width:0;   stroke:rgb(  0,  0,  0); } \n");
+	fprintf(svgfile, "      rect.net      { fill:rgb(  0,128,  0); fill-opacity:0.5; stroke-width:0;   stroke:rgb(  0,  0,  0); } \n");
+	fprintf(svgfile, "      rect.disk     { fill:rgb(  0,  0,255); fill-opacity:0.5; stroke-width:0;   stroke:rgb(  0,  0,  0); } \n");
+	fprintf(svgfile, "      rect.sync     { fill:rgb(128,128,  0); fill-opacity:0.5; stroke-width:0;   stroke:rgb(  0,  0,  0); } \n");
+	fprintf(svgfile, "      rect.poll     { fill:rgb(  0,128,128); fill-opacity:0.2; stroke-width:0;   stroke:rgb(  0,  0,  0); } \n");
 	fprintf(svgfile, "      rect.blocked  { fill:rgb(255,  0,  0); fill-opacity:0.5; stroke-width:0;   stroke:rgb(  0,  0,  0); } \n");
 	fprintf(svgfile, "      rect.waiting  { fill:rgb(224,214,  0); fill-opacity:0.8; stroke-width:0;   stroke:rgb(  0,  0,  0); } \n");
 	fprintf(svgfile, "      rect.WAITING  { fill:rgb(255,214, 48); fill-opacity:0.6; stroke-width:0;   stroke:rgb(  0,  0,  0); } \n");
@@ -132,12 +139,81 @@ void open_svg(const char *filename, int cpus, int rows, u64 start, u64 end)
 	fprintf(svgfile, "    ]]>\n   </style>\n</defs>\n");
 }
 
+static double normalize_height(double height)
+{
+	if (height < 0.25)
+		return 0.25;
+	else if (height < 0.50)
+		return 0.50;
+	else if (height < 0.75)
+		return 0.75;
+	else
+		return 0.100;
+}
+
+void svg_ubox(int Yslot, u64 start, u64 end, double height, const char *type, int fd, int err, int merges)
+{
+	double w = time2pixels(end) - time2pixels(start);
+	height = normalize_height(height);
+
+	if (!svgfile)
+		return;
+
+	fprintf(svgfile, "<g>\n");
+	fprintf(svgfile, "<title>fd=%d error=%d merges=%d</title>\n", fd, err, merges);
+	fprintf(svgfile, "<rect x=\"%.8f\" width=\"%.8f\" y=\"%.1f\" height=\"%.1f\" class=\"%s\"/>\n",
+		time2pixels(start),
+		w,
+		Yslot * SLOT_MULT,
+		SLOT_HALF * height,
+		type);
+	fprintf(svgfile, "</g>\n");
+}
+
+void svg_lbox(int Yslot, u64 start, u64 end, double height, const char *type, int fd, int err, int merges)
+{
+	double w = time2pixels(end) - time2pixels(start);
+	height = normalize_height(height);
+
+	if (!svgfile)
+		return;
+
+	fprintf(svgfile, "<g>\n");
+	fprintf(svgfile, "<title>fd=%d error=%d merges=%d</title>\n", fd, err, merges);
+	fprintf(svgfile, "<rect x=\"%.8f\" width=\"%.8f\" y=\"%.1f\" height=\"%.1f\" class=\"%s\"/>\n",
+		time2pixels(start),
+		w,
+		Yslot * SLOT_MULT + SLOT_HEIGHT - SLOT_HALF * height,
+		SLOT_HALF * height,
+		type);
+	fprintf(svgfile, "</g>\n");
+}
+
+void svg_fbox(int Yslot, u64 start, u64 end, double height, const char *type, int fd, int err, int merges)
+{
+	double w = time2pixels(end) - time2pixels(start);
+	height = normalize_height(height);
+
+	if (!svgfile)
+		return;
+
+	fprintf(svgfile, "<g>\n");
+	fprintf(svgfile, "<title>fd=%d error=%d merges=%d</title>\n", fd, err, merges);
+	fprintf(svgfile, "<rect x=\"%.8f\" width=\"%.8f\" y=\"%.1f\" height=\"%.1f\" class=\"%s\"/>\n",
+		time2pixels(start),
+		w,
+		Yslot * SLOT_MULT + SLOT_HEIGHT - SLOT_HEIGHT * height,
+		SLOT_HEIGHT * height,
+		type);
+	fprintf(svgfile, "</g>\n");
+}
+
 void svg_box(int Yslot, u64 start, u64 end, const char *type)
 {
 	if (!svgfile)
 		return;
 
-	fprintf(svgfile, "<rect x=\"%4.8f\" width=\"%4.8f\" y=\"%4.1f\" height=\"%4.1f\" class=\"%s\"/>\n",
+	fprintf(svgfile, "<rect x=\"%.8f\" width=\"%.8f\" y=\"%.1f\" height=\"%.1f\" class=\"%s\"/>\n",
 		time2pixels(start), time2pixels(end)-time2pixels(start), Yslot * SLOT_MULT, SLOT_HEIGHT, type);
 }
 
@@ -174,7 +250,7 @@ void svg_running(int Yslot, int cpu, u64 start, u64 end, const char *backtrace)
 		cpu, time_to_string(end - start));
 	if (backtrace)
 		fprintf(svgfile, "<desc>Switched because:\n%s</desc>\n", backtrace);
-	fprintf(svgfile, "<rect x=\"%4.8f\" width=\"%4.8f\" y=\"%4.1f\" height=\"%4.1f\" class=\"%s\"/>\n",
+	fprintf(svgfile, "<rect x=\"%.8f\" width=\"%.8f\" y=\"%.1f\" height=\"%.1f\" class=\"%s\"/>\n",
 		time2pixels(start), time2pixels(end)-time2pixels(start), Yslot * SLOT_MULT, SLOT_HEIGHT,
 		type);
 
@@ -186,7 +262,7 @@ void svg_running(int Yslot, int cpu, u64 start, u64 end, const char *backtrace)
 	text_size = round_text_size(text_size);
 
 	if (text_size > MIN_TEXT_SIZE)
-		fprintf(svgfile, "<text x=\"%1.8f\" y=\"%1.8f\" font-size=\"%1.8fpt\">%i</text>\n",
+		fprintf(svgfile, "<text x=\"%.8f\" y=\"%.8f\" font-size=\"%.8fpt\">%i</text>\n",
 			time2pixels(start), Yslot *  SLOT_MULT + SLOT_HEIGHT - 1, text_size,  cpu + 1);
 
 	fprintf(svgfile, "</g>\n");
@@ -202,10 +278,10 @@ static char *time_to_string(u64 duration)
 		return text;
 
 	if (duration < 1000 * 1000) { /* less than 1 msec */
-		sprintf(text, "%4.1f us", duration / 1000.0);
+		sprintf(text, "%.1f us", duration / 1000.0);
 		return text;
 	}
-	sprintf(text, "%4.1f ms", duration / 1000.0 / 1000);
+	sprintf(text, "%.1f ms", duration / 1000.0 / 1000);
 
 	return text;
 }
@@ -233,14 +309,14 @@ void svg_waiting(int Yslot, int cpu, u64 start, u64 end, const char *backtrace)
 
 	font_size = round_text_size(font_size);
 
-	fprintf(svgfile, "<g transform=\"translate(%4.8f,%4.8f)\">\n", time2pixels(start), Yslot * SLOT_MULT);
+	fprintf(svgfile, "<g transform=\"translate(%.8f,%.8f)\">\n", time2pixels(start), Yslot * SLOT_MULT);
 	fprintf(svgfile, "<title>#%d waiting %s</title>\n", cpu, time_to_string(end - start));
 	if (backtrace)
 		fprintf(svgfile, "<desc>Waiting on:\n%s</desc>\n", backtrace);
-	fprintf(svgfile, "<rect x=\"0\" width=\"%4.8f\" y=\"0\" height=\"%4.1f\" class=\"%s\"/>\n",
+	fprintf(svgfile, "<rect x=\"0\" width=\"%.8f\" y=\"0\" height=\"%.1f\" class=\"%s\"/>\n",
 		time2pixels(end)-time2pixels(start), SLOT_HEIGHT, style);
 	if (font_size > MIN_TEXT_SIZE)
-		fprintf(svgfile, "<text transform=\"rotate(90)\" font-size=\"%1.8fpt\"> %s</text>\n",
+		fprintf(svgfile, "<text transform=\"rotate(90)\" font-size=\"%.8fpt\"> %s</text>\n",
 			font_size, text);
 	fprintf(svgfile, "</g>\n");
 }
@@ -289,16 +365,16 @@ void svg_cpu_box(int cpu, u64 __max_freq, u64 __turbo_freq)
 
 	fprintf(svgfile, "<g>\n");
 
-	fprintf(svgfile, "<rect x=\"%4.8f\" width=\"%4.8f\" y=\"%4.1f\" height=\"%4.1f\" class=\"cpu\"/>\n",
+	fprintf(svgfile, "<rect x=\"%.8f\" width=\"%.8f\" y=\"%.1f\" height=\"%.1f\" class=\"cpu\"/>\n",
 		time2pixels(first_time),
 		time2pixels(last_time)-time2pixels(first_time),
 		cpu2y(cpu), SLOT_MULT+SLOT_HEIGHT);
 
 	sprintf(cpu_string, "CPU %i", (int)cpu);
-	fprintf(svgfile, "<text x=\"%4.8f\" y=\"%4.8f\">%s</text>\n",
+	fprintf(svgfile, "<text x=\"%.8f\" y=\"%.8f\">%s</text>\n",
 		10+time2pixels(first_time), cpu2y(cpu) + SLOT_HEIGHT/2, cpu_string);
 
-	fprintf(svgfile, "<text transform=\"translate(%4.8f,%4.8f)\" font-size=\"1.25pt\">%s</text>\n",
+	fprintf(svgfile, "<text transform=\"translate(%.8f,%.8f)\" font-size=\"1.25pt\">%s</text>\n",
 		10+time2pixels(first_time), cpu2y(cpu) + SLOT_MULT + SLOT_HEIGHT - 4, cpu_model());
 
 	fprintf(svgfile, "</g>\n");
@@ -319,11 +395,11 @@ void svg_process(int cpu, u64 start, u64 end, int pid, const char *name, const c
 	else
 		type = "sample";
 
-	fprintf(svgfile, "<g transform=\"translate(%4.8f,%4.8f)\">\n", time2pixels(start), cpu2y(cpu));
+	fprintf(svgfile, "<g transform=\"translate(%.8f,%.8f)\">\n", time2pixels(start), cpu2y(cpu));
 	fprintf(svgfile, "<title>%d %s running %s</title>\n", pid, name, time_to_string(end - start));
 	if (backtrace)
 		fprintf(svgfile, "<desc>Switched because:\n%s</desc>\n", backtrace);
-	fprintf(svgfile, "<rect x=\"0\" width=\"%4.8f\" y=\"0\" height=\"%4.1f\" class=\"%s\"/>\n",
+	fprintf(svgfile, "<rect x=\"0\" width=\"%.8f\" y=\"0\" height=\"%.1f\" class=\"%s\"/>\n",
 		time2pixels(end)-time2pixels(start), SLOT_MULT+SLOT_HEIGHT, type);
 	width = time2pixels(end)-time2pixels(start);
 	if (width > 6)
@@ -332,7 +408,7 @@ void svg_process(int cpu, u64 start, u64 end, int pid, const char *name, const c
 	width = round_text_size(width);
 
 	if (width > MIN_TEXT_SIZE)
-		fprintf(svgfile, "<text transform=\"rotate(90)\" font-size=\"%3.8fpt\">%s</text>\n",
+		fprintf(svgfile, "<text transform=\"rotate(90)\" font-size=\"%.8fpt\">%s</text>\n",
 			width, name);
 
 	fprintf(svgfile, "</g>\n");
@@ -353,7 +429,7 @@ void svg_cstate(int cpu, u64 start, u64 end, int type)
 		type = 6;
 	sprintf(style, "c%i", type);
 
-	fprintf(svgfile, "<rect class=\"%s\" x=\"%4.8f\" width=\"%4.8f\" y=\"%4.1f\" height=\"%4.1f\"/>\n",
+	fprintf(svgfile, "<rect class=\"%s\" x=\"%.8f\" width=\"%.8f\" y=\"%.1f\" height=\"%.1f\"/>\n",
 		style,
 		time2pixels(start), time2pixels(end)-time2pixels(start),
 		cpu2y(cpu), SLOT_MULT+SLOT_HEIGHT);
@@ -365,7 +441,7 @@ void svg_cstate(int cpu, u64 start, u64 end, int type)
 	width = round_text_size(width);
 
 	if (width > MIN_TEXT_SIZE)
-		fprintf(svgfile, "<text x=\"%4.8f\" y=\"%4.8f\" font-size=\"%3.8fpt\">C%i</text>\n",
+		fprintf(svgfile, "<text x=\"%.8f\" y=\"%.8f\" font-size=\"%.8fpt\">C%i</text>\n",
 			time2pixels(start), cpu2y(cpu)+width, width, type);
 
 	fprintf(svgfile, "</g>\n");
@@ -407,9 +483,9 @@ void svg_pstate(int cpu, u64 start, u64 end, u64 freq)
 	if (max_freq)
 		height = freq * 1.0 / max_freq * (SLOT_HEIGHT + SLOT_MULT);
 	height = 1 + cpu2y(cpu) + SLOT_MULT + SLOT_HEIGHT - height;
-	fprintf(svgfile, "<line x1=\"%4.8f\" x2=\"%4.8f\" y1=\"%4.1f\" y2=\"%4.1f\" class=\"pstate\"/>\n",
+	fprintf(svgfile, "<line x1=\"%.8f\" x2=\"%.8f\" y1=\"%.1f\" y2=\"%.1f\" class=\"pstate\"/>\n",
 		time2pixels(start), time2pixels(end), height, height);
-	fprintf(svgfile, "<text x=\"%4.8f\" y=\"%4.8f\" font-size=\"0.25pt\">%s</text>\n",
+	fprintf(svgfile, "<text x=\"%.8f\" y=\"%.8f\" font-size=\"0.25pt\">%s</text>\n",
 		time2pixels(start), height+0.9, HzToHuman(freq));
 
 	fprintf(svgfile, "</g>\n");
@@ -435,32 +511,32 @@ void svg_partial_wakeline(u64 start, int row1, char *desc1, int row2, char *desc
 
 	if (row1 < row2) {
 		if (row1) {
-			fprintf(svgfile, "<line x1=\"%4.8f\" y1=\"%4.2f\" x2=\"%4.8f\" y2=\"%4.2f\" style=\"stroke:rgb(32,255,32);stroke-width:0.009\"/>\n",
+			fprintf(svgfile, "<line x1=\"%.8f\" y1=\"%.2f\" x2=\"%.8f\" y2=\"%.2f\" style=\"stroke:rgb(32,255,32);stroke-width:0.009\"/>\n",
 				time2pixels(start), row1 * SLOT_MULT + SLOT_HEIGHT,  time2pixels(start), row1 * SLOT_MULT + SLOT_HEIGHT + SLOT_MULT/32);
 			if (desc2)
-				fprintf(svgfile, "<g transform=\"translate(%4.8f,%4.8f)\"><text transform=\"rotate(90)\" font-size=\"0.02pt\">%s &gt;</text></g>\n",
+				fprintf(svgfile, "<g transform=\"translate(%.8f,%.8f)\"><text transform=\"rotate(90)\" font-size=\"0.02pt\">%s &gt;</text></g>\n",
 					time2pixels(start), row1 * SLOT_MULT + SLOT_HEIGHT + SLOT_HEIGHT/48, desc2);
 		}
 		if (row2) {
-			fprintf(svgfile, "<line x1=\"%4.8f\" y1=\"%4.2f\" x2=\"%4.8f\" y2=\"%4.2f\" style=\"stroke:rgb(32,255,32);stroke-width:0.009\"/>\n",
+			fprintf(svgfile, "<line x1=\"%.8f\" y1=\"%.2f\" x2=\"%.8f\" y2=\"%.2f\" style=\"stroke:rgb(32,255,32);stroke-width:0.009\"/>\n",
 				time2pixels(start), row2 * SLOT_MULT - SLOT_MULT/32,  time2pixels(start), row2 * SLOT_MULT);
 			if (desc1)
-				fprintf(svgfile, "<g transform=\"translate(%4.8f,%4.8f)\"><text transform=\"rotate(90)\" font-size=\"0.02pt\">%s &gt;</text></g>\n",
+				fprintf(svgfile, "<g transform=\"translate(%.8f,%.8f)\"><text transform=\"rotate(90)\" font-size=\"0.02pt\">%s &gt;</text></g>\n",
 					time2pixels(start), row2 * SLOT_MULT - SLOT_MULT/32, desc1);
 		}
 	} else {
 		if (row2) {
-			fprintf(svgfile, "<line x1=\"%4.8f\" y1=\"%4.2f\" x2=\"%4.8f\" y2=\"%4.2f\" style=\"stroke:rgb(32,255,32);stroke-width:0.009\"/>\n",
+			fprintf(svgfile, "<line x1=\"%.8f\" y1=\"%.2f\" x2=\"%.8f\" y2=\"%.2f\" style=\"stroke:rgb(32,255,32);stroke-width:0.009\"/>\n",
 				time2pixels(start), row2 * SLOT_MULT + SLOT_HEIGHT,  time2pixels(start), row2 * SLOT_MULT + SLOT_HEIGHT + SLOT_MULT/32);
 			if (desc1)
-				fprintf(svgfile, "<g transform=\"translate(%4.8f,%4.8f)\"><text transform=\"rotate(90)\" font-size=\"0.02pt\">%s &lt;</text></g>\n",
+				fprintf(svgfile, "<g transform=\"translate(%.8f,%.8f)\"><text transform=\"rotate(90)\" font-size=\"0.02pt\">%s &lt;</text></g>\n",
 					time2pixels(start), row2 * SLOT_MULT + SLOT_HEIGHT + SLOT_MULT/48, desc1);
 		}
 		if (row1) {
-			fprintf(svgfile, "<line x1=\"%4.8f\" y1=\"%4.2f\" x2=\"%4.8f\" y2=\"%4.2f\" style=\"stroke:rgb(32,255,32);stroke-width:0.009\"/>\n",
+			fprintf(svgfile, "<line x1=\"%.8f\" y1=\"%.2f\" x2=\"%.8f\" y2=\"%.2f\" style=\"stroke:rgb(32,255,32);stroke-width:0.009\"/>\n",
 				time2pixels(start), row1 * SLOT_MULT - SLOT_MULT/32,  time2pixels(start), row1 * SLOT_MULT);
 			if (desc2)
-				fprintf(svgfile, "<g transform=\"translate(%4.8f,%4.8f)\"><text transform=\"rotate(90)\" font-size=\"0.02pt\">%s &lt;</text></g>\n",
+				fprintf(svgfile, "<g transform=\"translate(%.8f,%.8f)\"><text transform=\"rotate(90)\" font-size=\"0.02pt\">%s &lt;</text></g>\n",
 					time2pixels(start), row1 * SLOT_MULT - SLOT_HEIGHT/32, desc2);
 		}
 	}
@@ -468,7 +544,7 @@ void svg_partial_wakeline(u64 start, int row1, char *desc1, int row2, char *desc
 	if (row2 > row1)
 		height += SLOT_HEIGHT;
 	if (row1)
-		fprintf(svgfile, "<circle  cx=\"%4.8f\" cy=\"%4.2f\" r = \"0.01\"  style=\"fill:rgb(32,255,32)\"/>\n",
+		fprintf(svgfile, "<circle  cx=\"%.8f\" cy=\"%.2f\" r = \"0.01\"  style=\"fill:rgb(32,255,32)\"/>\n",
 			time2pixels(start), height);
 
 	fprintf(svgfile, "</g>\n");
@@ -488,16 +564,16 @@ void svg_wakeline(u64 start, int row1, int row2, const char *backtrace)
 		fprintf(svgfile, "<desc>%s</desc>\n", backtrace);
 
 	if (row1 < row2)
-		fprintf(svgfile, "<line x1=\"%4.8f\" y1=\"%4.2f\" x2=\"%4.8f\" y2=\"%4.2f\" style=\"stroke:rgb(32,255,32);stroke-width:0.009\"/>\n",
+		fprintf(svgfile, "<line x1=\"%.8f\" y1=\"%.2f\" x2=\"%.8f\" y2=\"%.2f\" style=\"stroke:rgb(32,255,32);stroke-width:0.009\"/>\n",
 			time2pixels(start), row1 * SLOT_MULT + SLOT_HEIGHT,  time2pixels(start), row2 * SLOT_MULT);
 	else
-		fprintf(svgfile, "<line x1=\"%4.8f\" y1=\"%4.2f\" x2=\"%4.8f\" y2=\"%4.2f\" style=\"stroke:rgb(32,255,32);stroke-width:0.009\"/>\n",
+		fprintf(svgfile, "<line x1=\"%.8f\" y1=\"%.2f\" x2=\"%.8f\" y2=\"%.2f\" style=\"stroke:rgb(32,255,32);stroke-width:0.009\"/>\n",
 			time2pixels(start), row2 * SLOT_MULT + SLOT_HEIGHT,  time2pixels(start), row1 * SLOT_MULT);
 
 	height = row1 * SLOT_MULT;
 	if (row2 > row1)
 		height += SLOT_HEIGHT;
-	fprintf(svgfile, "<circle  cx=\"%4.8f\" cy=\"%4.2f\" r = \"0.01\"  style=\"fill:rgb(32,255,32)\"/>\n",
+	fprintf(svgfile, "<circle  cx=\"%.8f\" cy=\"%.2f\" r = \"0.01\"  style=\"fill:rgb(32,255,32)\"/>\n",
 			time2pixels(start), height);
 
 	fprintf(svgfile, "</g>\n");
@@ -515,9 +591,9 @@ void svg_interrupt(u64 start, int row, const char *backtrace)
 	if (backtrace)
 		fprintf(svgfile, "<desc>%s</desc>\n", backtrace);
 
-	fprintf(svgfile, "<circle  cx=\"%4.8f\" cy=\"%4.2f\" r = \"0.01\"  style=\"fill:rgb(255,128,128)\"/>\n",
+	fprintf(svgfile, "<circle  cx=\"%.8f\" cy=\"%.2f\" r = \"0.01\"  style=\"fill:rgb(255,128,128)\"/>\n",
 			time2pixels(start), row * SLOT_MULT);
-	fprintf(svgfile, "<circle  cx=\"%4.8f\" cy=\"%4.2f\" r = \"0.01\"  style=\"fill:rgb(255,128,128)\"/>\n",
+	fprintf(svgfile, "<circle  cx=\"%.8f\" cy=\"%.2f\" r = \"0.01\"  style=\"fill:rgb(255,128,128)\"/>\n",
 			time2pixels(start), row * SLOT_MULT + SLOT_HEIGHT);
 
 	fprintf(svgfile, "</g>\n");
@@ -528,7 +604,7 @@ void svg_text(int Yslot, u64 start, const char *text)
 	if (!svgfile)
 		return;
 
-	fprintf(svgfile, "<text x=\"%4.8f\" y=\"%4.8f\">%s</text>\n",
+	fprintf(svgfile, "<text x=\"%.8f\" y=\"%.8f\">%s</text>\n",
 		time2pixels(start), Yslot * SLOT_MULT+SLOT_HEIGHT/2, text);
 }
 
@@ -537,12 +613,26 @@ static void svg_legenda_box(int X, const char *text, const char *style)
 	double boxsize;
 	boxsize = SLOT_HEIGHT / 2;
 
-	fprintf(svgfile, "<rect x=\"%i\" width=\"%4.8f\" y=\"0\" height=\"%4.1f\" class=\"%s\"/>\n",
+	fprintf(svgfile, "<rect x=\"%i\" width=\"%.8f\" y=\"0\" height=\"%.1f\" class=\"%s\"/>\n",
 		X, boxsize, boxsize, style);
-	fprintf(svgfile, "<text transform=\"translate(%4.8f, %4.8f)\" font-size=\"%4.8fpt\">%s</text>\n",
+	fprintf(svgfile, "<text transform=\"translate(%.8f, %.8f)\" font-size=\"%.8fpt\">%s</text>\n",
 		X + boxsize + 5, boxsize, 0.8 * boxsize, text);
 }
 
+void svg_io_legenda(void)
+{
+	if (!svgfile)
+		return;
+
+	fprintf(svgfile, "<g>\n");
+	svg_legenda_box(0,	"Disk", "disk");
+	svg_legenda_box(100,	"Network", "net");
+	svg_legenda_box(200,	"Sync", "sync");
+	svg_legenda_box(300,	"Poll", "poll");
+	svg_legenda_box(400,	"Error", "error");
+	fprintf(svgfile, "</g>\n");
+}
+
 void svg_legenda(void)
 {
 	if (!svgfile)
@@ -559,7 +649,7 @@ void svg_legenda(void)
 	fprintf(svgfile, "</g>\n");
 }
 
-void svg_time_grid(void)
+void svg_time_grid(double min_thickness)
 {
 	u64 i;
 
@@ -579,8 +669,10 @@ void svg_time_grid(void)
 			color = 128;
 		}
 
-		fprintf(svgfile, "<line x1=\"%4.8f\" y1=\"%4.2f\" x2=\"%4.8f\" y2=\"%" PRIu64 "\" style=\"stroke:rgb(%i,%i,%i);stroke-width:%1.3f\"/>\n",
-			time2pixels(i), SLOT_MULT/2, time2pixels(i), total_height, color, color, color, thickness);
+		if (thickness >= min_thickness)
+			fprintf(svgfile, "<line x1=\"%.8f\" y1=\"%.2f\" x2=\"%.8f\" y2=\"%" PRIu64 "\" style=\"stroke:rgb(%i,%i,%i);stroke-width:%.3f\"/>\n",
+				time2pixels(i), SLOT_MULT/2, time2pixels(i),
+				total_height, color, color, color, thickness);
 
 		i += 10000000;
 	}
diff --git a/tools/perf/util/svghelper.h b/tools/perf/util/svghelper.h
index e3aff5332e30..9292a5291445 100644
--- a/tools/perf/util/svghelper.h
+++ b/tools/perf/util/svghelper.h
@@ -4,6 +4,9 @@
 #include <linux/types.h>
 
 extern void open_svg(const char *filename, int cpus, int rows, u64 start, u64 end);
+extern void svg_ubox(int Yslot, u64 start, u64 end, double height, const char *type, int fd, int err, int merges);
+extern void svg_lbox(int Yslot, u64 start, u64 end, double height, const char *type, int fd, int err, int merges);
+extern void svg_fbox(int Yslot, u64 start, u64 end, double height, const char *type, int fd, int err, int merges);
 extern void svg_box(int Yslot, u64 start, u64 end, const char *type);
 extern void svg_blocked(int Yslot, int cpu, u64 start, u64 end, const char *backtrace);
 extern void svg_running(int Yslot, int cpu, u64 start, u64 end, const char *backtrace);
@@ -16,7 +19,8 @@ extern void svg_cstate(int cpu, u64 start, u64 end, int type);
 extern void svg_pstate(int cpu, u64 start, u64 end, u64 freq);
 
 
-extern void svg_time_grid(void);
+extern void svg_time_grid(double min_thickness);
+extern void svg_io_legenda(void);
 extern void svg_legenda(void);
 extern void svg_wakeline(u64 start, int row1, int row2, const char *backtrace);
 extern void svg_partial_wakeline(u64 start, int row1, char *desc1, int row2, char *desc2, const char *backtrace);
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 7b9096f29cdb..2e6a2e219eb9 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -34,6 +34,7 @@ struct symbol_conf symbol_conf = {
 	.annotate_src		= true,
 	.demangle		= true,
 	.cumulate_callchain	= true,
+	.show_hist_headers	= true,
 	.symfs			= "",
 };
 
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index 615c752dd767..a81877b1dee0 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -118,7 +118,8 @@ struct symbol_conf {
 			annotate_src,
 			event_group,
 			demangle,
-			filter_relative;
+			filter_relative,
+			show_hist_headers;
 	const char	*vmlinux_name,
 			*kallsyms_name,
 			*source_prefix,
diff --git a/tools/perf/util/trace-event-info.c b/tools/perf/util/trace-event-info.c
index 7e6fcfe8b438..c3bba883f5c3 100644
--- a/tools/perf/util/trace-event-info.c
+++ b/tools/perf/util/trace-event-info.c
@@ -191,12 +191,10 @@ static int copy_event_system(const char *sys, struct tracepoint_path *tps)
 		    strcmp(dent->d_name, "..") == 0 ||
 		    !name_in_tp_list(dent->d_name, tps))
 			continue;
-		format = malloc(strlen(sys) + strlen(dent->d_name) + 10);
-		if (!format) {
+		if (asprintf(&format, "%s/%s/format", sys, dent->d_name) < 0) {
 			err = -ENOMEM;
 			goto out;
 		}
-		sprintf(format, "%s/%s/format", sys, dent->d_name);
 		ret = stat(format, &st);
 		free(format);
 		if (ret < 0)
@@ -217,12 +215,10 @@ static int copy_event_system(const char *sys, struct tracepoint_path *tps)
 		    strcmp(dent->d_name, "..") == 0 ||
 		    !name_in_tp_list(dent->d_name, tps))
 			continue;
-		format = malloc(strlen(sys) + strlen(dent->d_name) + 10);
-		if (!format) {
+		if (asprintf(&format, "%s/%s/format", sys, dent->d_name) < 0) {
 			err = -ENOMEM;
 			goto out;
 		}
-		sprintf(format, "%s/%s/format", sys, dent->d_name);
 		ret = stat(format, &st);
 
 		if (ret >= 0) {
@@ -317,12 +313,10 @@ static int record_event_files(struct tracepoint_path *tps)
 		    strcmp(dent->d_name, "ftrace") == 0 ||
 		    !system_in_tp_list(dent->d_name, tps))
 			continue;
-		sys = malloc(strlen(path) + strlen(dent->d_name) + 2);
-		if (!sys) {
+		if (asprintf(&sys, "%s/%s", path, dent->d_name) < 0) {
 			err = -ENOMEM;
 			goto out;
 		}
-		sprintf(sys, "%s/%s", path, dent->d_name);
 		ret = stat(sys, &st);
 		if (ret >= 0) {
 			ssize_t size = strlen(dent->d_name) + 1;
diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c
index 95aefa78bb07..e4132aeeb780 100644
--- a/tools/perf/util/util.c
+++ b/tools/perf/util/util.c
@@ -333,12 +333,9 @@ const char *find_tracing_dir(void)
 	if (!debugfs)
 		return NULL;
 
-	tracing = malloc(strlen(debugfs) + 9);
-	if (!tracing)
+	if (asprintf(&tracing, "%s/tracing", debugfs) < 0)
 		return NULL;
 
-	sprintf(tracing, "%s/tracing", debugfs);
-
 	tracing_found = 1;
 	return tracing;
 }
@@ -352,11 +349,9 @@ char *get_tracing_file(const char *name)
 	if (!tracing)
 		return NULL;
 
-	file = malloc(strlen(tracing) + strlen(name) + 2);
-	if (!file)
+	if (asprintf(&file, "%s/%s", tracing, name) < 0)
 		return NULL;
 
-	sprintf(file, "%s/%s", tracing, name);
 	return file;
 }