Merge tag 'perf-core-for-mingo' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/core

Pull perf/core improvements and fixes from Arnaldo Carvalho de Melo:

. Fix some leaks in exit paths.

. Use memdup where applicable

. Remove some die() calls, allowing callers to handle exit paths
  gracefully.

. Correct typo in tools Makefile, fix from Borislav Petkov.

. Add 'perf bench numa mem' NUMA performance measurement suite, from Ingo Molnar.

. Handle dynamic array's element size properly, fix from Jiri Olsa.

. Fix memory leaks on evsel->counts, from Namhyung Kim.

. Make numa benchmark optional, allowing the build in machines where required
  numa libraries are not present, fix from Peter Hurley.

. Add interval printing in 'perf stat', from Stephane Eranian.

. Fix compile warnings in tests/attr.c, from Sukadev Bhattiprolu.

. Fix double free, pclose instead of fclose, leaks and double fclose errors
  found with the cppcheck tool, from Thomas Jarosch.

Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

25 files changed, 2154 insertions, 160 deletions

diff --git a/tools/Makefile b/tools/Makefile
index 1f9a529..798fa0e 100644
--- a/tools/Makefile
+++ b/tools/Makefile
@@ -15,7 +15,7 @@ help:
 	@echo '  x86_energy_perf_policy - Intel energy policy tool'
 	@echo ''
 	@echo 'You can do:'
-	@echo ' $$ make -C tools/<tool>_install'
+	@echo ' $$ make -C tools/ <tool>_install'
 	@echo ''
 	@echo '  from the kernel command line to build and install one of'
 	@echo '  the tools above'
diff --git a/tools/lib/traceevent/event-parse.c b/tools/lib/traceevent/event-parse.c
index bb8b3db..82b0606 100644
--- a/tools/lib/traceevent/event-parse.c
+++ b/tools/lib/traceevent/event-parse.c
@@ -1223,6 +1223,34 @@ static int field_is_long(struct format_field *field)
 	return 0;
 }
 
+static unsigned int type_size(const char *name)
+{
+	/* This covers all FIELD_IS_STRING types. */
+	static struct {
+		const char *type;
+		unsigned int size;
+	} table[] = {
+		{ "u8",   1 },
+		{ "u16",  2 },
+		{ "u32",  4 },
+		{ "u64",  8 },
+		{ "s8",   1 },
+		{ "s16",  2 },
+		{ "s32",  4 },
+		{ "s64",  8 },
+		{ "char", 1 },
+		{ },
+	};
+	int i;
+
+	for (i = 0; table[i].type; i++) {
+		if (!strcmp(table[i].type, name))
+			return table[i].size;
+	}
+
+	return 0;
+}
+
 static int event_read_fields(struct event_format *event, struct format_field **fields)
 {
 	struct format_field *field = NULL;
@@ -1232,6 +1260,8 @@ static int event_read_fields(struct event_format *event, struct format_field **f
 	int count = 0;
 
 	do {
+		unsigned int size_dynamic = 0;
+
 		type = read_token(&token);
 		if (type == EVENT_NEWLINE) {
 			free_token(token);
@@ -1390,6 +1420,7 @@ static int event_read_fields(struct event_format *event, struct format_field **f
 				field->type = new_type;
 				strcat(field->type, " ");
 				strcat(field->type, field->name);
+				size_dynamic = type_size(field->name);
 				free_token(field->name);
 				strcat(field->type, brackets);
 				field->name = token;
@@ -1478,10 +1509,14 @@ static int event_read_fields(struct event_format *event, struct format_field **f
 		if (field->flags & FIELD_IS_ARRAY) {
 			if (field->arraylen)
 				field->elementsize = field->size / field->arraylen;
+			else if (field->flags & FIELD_IS_DYNAMIC)
+				field->elementsize = size_dynamic;
 			else if (field->flags & FIELD_IS_STRING)
 				field->elementsize = 1;
-			else
-				field->elementsize = event->pevent->long_size;
+			else if (field->flags & FIELD_IS_LONG)
+				field->elementsize = event->pevent ?
+						     event->pevent->long_size :
+						     sizeof(long);
 		} else
 			field->elementsize = field->size;
 
diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt
index cf0c310..5289da3 100644
--- a/tools/perf/Documentation/perf-stat.txt
+++ b/tools/perf/Documentation/perf-stat.txt
@@ -114,6 +114,10 @@ with it.  --append may be used here.  Examples:
 
 perf stat --repeat 10 --null --sync --pre 'make -s O=defconfig-build/clean' -- make -s -j64 O=defconfig-build/ bzImage
 
+-I msecs::
+--interval-print msecs::
+	print count deltas every N milliseconds (minimum: 100ms)
+	example: perf stat -I 1000 -e cycles -a sleep 5
 
 EXAMPLES
 --------
diff --git a/tools/perf/Makefile b/tools/perf/Makefile
index a84021a..4b1044c 100644
--- a/tools/perf/Makefile
+++ b/tools/perf/Makefile
@@ -47,6 +47,8 @@ include config/utilities.mak
 # backtrace post unwind.
 #
 # Define NO_BACKTRACE if you do not want stack backtrace debug feature
+#
+# Define NO_LIBNUMA if you do not want numa perf benchmark
 
 $(OUTPUT)PERF-VERSION-FILE: .FORCE-PERF-VERSION-FILE
 	@$(SHELL_PATH) util/PERF-VERSION-GEN $(OUTPUT)
@@ -838,6 +840,17 @@ ifndef NO_BACKTRACE
        endif
 endif
 
+ifndef NO_LIBNUMA
+	FLAGS_LIBNUMA = $(ALL_CFLAGS) $(ALL_LDFLAGS) -lnuma
+	ifneq ($(call try-cc,$(SOURCE_LIBNUMA),$(FLAGS_LIBNUMA),libnuma),y)
+		msg := $(warning No numa.h found, disables 'perf bench numa mem' benchmark, please install numa-libs-devel or libnuma-dev);
+	else
+		BASIC_CFLAGS += -DLIBNUMA_SUPPORT
+		BUILTIN_OBJS += $(OUTPUT)bench/numa.o
+		EXTLIBS += -lnuma
+	endif
+endif
+
 ifdef ASCIIDOC8
 	export ASCIIDOC8
 endif
diff --git a/tools/perf/arch/common.c b/tools/perf/arch/common.c
index 3e975cb..aacef07 100644
--- a/tools/perf/arch/common.c
+++ b/tools/perf/arch/common.c
@@ -155,6 +155,7 @@ static int perf_session_env__lookup_binutils_path(struct perf_session_env *env,
 		if (lookup_path(buf))
 			goto out;
 		free(buf);
+		buf = NULL;
 	}
 
 	if (!strcmp(arch, "arm"))
diff --git a/tools/perf/bench/bench.h b/tools/perf/bench/bench.h
index 8f89998..a5223e6 100644
--- a/tools/perf/bench/bench.h
+++ b/tools/perf/bench/bench.h
@@ -1,6 +1,7 @@
 #ifndef BENCH_H
 #define BENCH_H
 
+extern int bench_numa(int argc, const char **argv, const char *prefix);
 extern int bench_sched_messaging(int argc, const char **argv, const char *prefix);
 extern int bench_sched_pipe(int argc, const char **argv, const char *prefix);
 extern int bench_mem_memcpy(int argc, const char **argv,
diff --git a/tools/perf/bench/numa.c b/tools/perf/bench/numa.c
new file mode 100644
index 0000000..30d1c322
--- /dev/null
+++ b/tools/perf/bench/numa.c
@@ -0,0 +1,1731 @@
+/*
+ * numa.c
+ *
+ * numa: Simulate NUMA-sensitive workload and measure their NUMA performance
+ */
+
+#include "../perf.h"
+#include "../builtin.h"
+#include "../util/util.h"
+#include "../util/parse-options.h"
+
+#include "bench.h"
+
+#include <errno.h>
+#include <sched.h>
+#include <stdio.h>
+#include <assert.h>
+#include <malloc.h>
+#include <signal.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+#include <pthread.h>
+#include <sys/mman.h>
+#include <sys/time.h>
+#include <sys/wait.h>
+#include <sys/prctl.h>
+#include <sys/types.h>
+
+#include <numa.h>
+#include <numaif.h>
+
+/*
+ * Regular printout to the terminal, supressed if -q is specified:
+ */
+#define tprintf(x...) do { if (g && g->p.show_details >= 0) printf(x); } while (0)
+
+/*
+ * Debug printf:
+ */
+#define dprintf(x...) do { if (g && g->p.show_details >= 1) printf(x); } while (0)
+
+struct thread_data {
+	int			curr_cpu;
+	cpu_set_t		bind_cpumask;
+	int			bind_node;
+	u8			*process_data;
+	int			process_nr;
+	int			thread_nr;
+	int			task_nr;
+	unsigned int		loops_done;
+	u64			val;
+	u64			runtime_ns;
+	pthread_mutex_t		*process_lock;
+};
+
+/* Parameters set by options: */
+
+struct params {
+	/* Startup synchronization: */
+	bool			serialize_startup;
+
+	/* Task hierarchy: */
+	int			nr_proc;
+	int			nr_threads;
+
+	/* Working set sizes: */
+	const char		*mb_global_str;
+	const char		*mb_proc_str;
+	const char		*mb_proc_locked_str;
+	const char		*mb_thread_str;
+
+	double			mb_global;
+	double			mb_proc;
+	double			mb_proc_locked;
+	double			mb_thread;
+
+	/* Access patterns to the working set: */
+	bool			data_reads;
+	bool			data_writes;
+	bool			data_backwards;
+	bool			data_zero_memset;
+	bool			data_rand_walk;
+	u32			nr_loops;
+	u32			nr_secs;
+	u32			sleep_usecs;
+
+	/* Working set initialization: */
+	bool			init_zero;
+	bool			init_random;
+	bool			init_cpu0;
+
+	/* Misc options: */
+	int			show_details;
+	int			run_all;
+	int			thp;
+
+	long			bytes_global;
+	long			bytes_process;
+	long			bytes_process_locked;
+	long			bytes_thread;
+
+	int			nr_tasks;
+	bool			show_quiet;
+
+	bool			show_convergence;
+	bool			measure_convergence;
+
+	int			perturb_secs;
+	int			nr_cpus;
+	int			nr_nodes;
+
+	/* Affinity options -C and -N: */
+	char			*cpu_list_str;
+	char			*node_list_str;
+};
+
+
+/* Global, read-writable area, accessible to all processes and threads: */
+
+struct global_info {
+	u8			*data;
+
+	pthread_mutex_t		startup_mutex;
+	int			nr_tasks_started;
+
+	pthread_mutex_t		startup_done_mutex;
+
+	pthread_mutex_t		start_work_mutex;
+	int			nr_tasks_working;
+
+	pthread_mutex_t		stop_work_mutex;
+	u64			bytes_done;
+
+	struct thread_data	*threads;
+
+	/* Convergence latency measurement: */
+	bool			all_converged;
+	bool			stop_work;
+
+	int			print_once;
+
+	struct params		p;
+};
+
+static struct global_info	*g = NULL;
+
+static int parse_cpus_opt(const struct option *opt, const char *arg, int unset);
+static int parse_nodes_opt(const struct option *opt, const char *arg, int unset);
+
+struct params p0;
+
+static const struct option options[] = {
+	OPT_INTEGER('p', "nr_proc"	, &p0.nr_proc,		"number of processes"),
+	OPT_INTEGER('t', "nr_threads"	, &p0.nr_threads,	"number of threads per process"),
+
+	OPT_STRING('G', "mb_global"	, &p0.mb_global_str,	"MB", "global  memory (MBs)"),
+	OPT_STRING('P', "mb_proc"	, &p0.mb_proc_str,	"MB", "process memory (MBs)"),
+	OPT_STRING('L', "mb_proc_locked", &p0.mb_proc_locked_str,"MB", "process serialized/locked memory access (MBs), <= process_memory"),
+	OPT_STRING('T', "mb_thread"	, &p0.mb_thread_str,	"MB", "thread  memory (MBs)"),
+
+	OPT_UINTEGER('l', "nr_loops"	, &p0.nr_loops,		"max number of loops to run"),
+	OPT_UINTEGER('s', "nr_secs"	, &p0.nr_secs,		"max number of seconds to run"),
+	OPT_UINTEGER('u', "usleep"	, &p0.sleep_usecs,	"usecs to sleep per loop iteration"),
+
+	OPT_BOOLEAN('R', "data_reads"	, &p0.data_reads,	"access the data via writes (can be mixed with -W)"),
+	OPT_BOOLEAN('W', "data_writes"	, &p0.data_writes,	"access the data via writes (can be mixed with -R)"),
+	OPT_BOOLEAN('B', "data_backwards", &p0.data_backwards,	"access the data backwards as well"),
+	OPT_BOOLEAN('Z', "data_zero_memset", &p0.data_zero_memset,"access the data via glibc bzero only"),
+	OPT_BOOLEAN('r', "data_rand_walk", &p0.data_rand_walk,	"access the data with random (32bit LFSR) walk"),
+
+
+	OPT_BOOLEAN('z', "init_zero"	, &p0.init_zero,	"bzero the initial allocations"),
+	OPT_BOOLEAN('I', "init_random"	, &p0.init_random,	"randomize the contents of the initial allocations"),
+	OPT_BOOLEAN('0', "init_cpu0"	, &p0.init_cpu0,	"do the initial allocations on CPU#0"),
+	OPT_INTEGER('x', "perturb_secs", &p0.perturb_secs,	"perturb thread 0/0 every X secs, to test convergence stability"),
+
+	OPT_INCR   ('d', "show_details"	, &p0.show_details,	"Show details"),
+	OPT_INCR   ('a', "all"		, &p0.run_all,		"Run all tests in the suite"),
+	OPT_INTEGER('H', "thp"		, &p0.thp,		"MADV_NOHUGEPAGE < 0 < MADV_HUGEPAGE"),
+	OPT_BOOLEAN('c', "show_convergence", &p0.show_convergence, "show convergence details"),
+	OPT_BOOLEAN('m', "measure_convergence",	&p0.measure_convergence, "measure convergence latency"),
+	OPT_BOOLEAN('q', "quiet"	, &p0.show_quiet,	"bzero the initial allocations"),
+	OPT_BOOLEAN('S', "serialize-startup", &p0.serialize_startup,"serialize thread startup"),
+
+	/* Special option string parsing callbacks: */
+        OPT_CALLBACK('C', "cpus", NULL, "cpu[,cpu2,...cpuN]",
+			"bind the first N tasks to these specific cpus (the rest is unbound)",
+			parse_cpus_opt),
+        OPT_CALLBACK('M', "memnodes", NULL, "node[,node2,...nodeN]",
+			"bind the first N tasks to these specific memory nodes (the rest is unbound)",
+			parse_nodes_opt),
+	OPT_END()
+};
+
+static const char * const bench_numa_usage[] = {
+	"perf bench numa <options>",
+	NULL
+};
+
+static const char * const numa_usage[] = {
+	"perf bench numa mem [<options>]",
+	NULL
+};
+
+static cpu_set_t bind_to_cpu(int target_cpu)
+{
+	cpu_set_t orig_mask, mask;
+	int ret;
+
+	ret = sched_getaffinity(0, sizeof(orig_mask), &orig_mask);
+	BUG_ON(ret);
+
+	CPU_ZERO(&mask);
+
+	if (target_cpu == -1) {
+		int cpu;
+
+		for (cpu = 0; cpu < g->p.nr_cpus; cpu++)
+			CPU_SET(cpu, &mask);
+	} else {
+		BUG_ON(target_cpu < 0 || target_cpu >= g->p.nr_cpus);
+		CPU_SET(target_cpu, &mask);
+	}
+
+	ret = sched_setaffinity(0, sizeof(mask), &mask);
+	BUG_ON(ret);
+
+	return orig_mask;
+}
+
+static cpu_set_t bind_to_node(int target_node)
+{
+	int cpus_per_node = g->p.nr_cpus/g->p.nr_nodes;
+	cpu_set_t orig_mask, mask;
+	int cpu;
+	int ret;
+
+	BUG_ON(cpus_per_node*g->p.nr_nodes != g->p.nr_cpus);
+	BUG_ON(!cpus_per_node);
+
+	ret = sched_getaffinity(0, sizeof(orig_mask), &orig_mask);
+	BUG_ON(ret);
+
+	CPU_ZERO(&mask);
+
+	if (target_node == -1) {
+		for (cpu = 0; cpu < g->p.nr_cpus; cpu++)
+			CPU_SET(cpu, &mask);
+	} else {
+		int cpu_start = (target_node + 0) * cpus_per_node;
+		int cpu_stop  = (target_node + 1) * cpus_per_node;
+
+		BUG_ON(cpu_stop > g->p.nr_cpus);
+
+		for (cpu = cpu_start; cpu < cpu_stop; cpu++)
+			CPU_SET(cpu, &mask);
+	}
+
+	ret = sched_setaffinity(0, sizeof(mask), &mask);
+	BUG_ON(ret);
+
+	return orig_mask;
+}
+
+static void bind_to_cpumask(cpu_set_t mask)
+{
+	int ret;
+
+	ret = sched_setaffinity(0, sizeof(mask), &mask);
+	BUG_ON(ret);
+}
+
+static void mempol_restore(void)
+{
+	int ret;
+
+	ret = set_mempolicy(MPOL_DEFAULT, NULL, g->p.nr_nodes-1);
+
+	BUG_ON(ret);
+}
+
+static void bind_to_memnode(int node)
+{
+	unsigned long nodemask;
+	int ret;
+
+	if (node == -1)
+		return;
+
+	BUG_ON(g->p.nr_nodes > (int)sizeof(nodemask));
+	nodemask = 1L << node;
+
+	ret = set_mempolicy(MPOL_BIND, &nodemask, sizeof(nodemask)*8);
+	dprintf("binding to node %d, mask: %016lx => %d\n", node, nodemask, ret);
+
+	BUG_ON(ret);
+}
+
+#define HPSIZE (2*1024*1024)
+
+#define set_taskname(fmt...)				\
+do {							\
+	char name[20];					\
+							\
+	snprintf(name, 20, fmt);			\
+	prctl(PR_SET_NAME, name);			\
+} while (0)
+
+static u8 *alloc_data(ssize_t bytes0, int map_flags,
+		      int init_zero, int init_cpu0, int thp, int init_random)
+{
+	cpu_set_t orig_mask;
+	ssize_t bytes;
+	u8 *buf;
+	int ret;
+
+	if (!bytes0)
+		return NULL;
+
+	/* Allocate and initialize all memory on CPU#0: */
+	if (init_cpu0) {
+		orig_mask = bind_to_node(0);
+		bind_to_memnode(0);
+	}
+
+	bytes = bytes0 + HPSIZE;
+
+	buf = (void *)mmap(0, bytes, PROT_READ|PROT_WRITE, MAP_ANON|map_flags, -1, 0);
+	BUG_ON(buf == (void *)-1);
+
+	if (map_flags == MAP_PRIVATE) {
+		if (thp > 0) {
+			ret = madvise(buf, bytes, MADV_HUGEPAGE);
+			if (ret && !g->print_once) {
+				g->print_once = 1;
+				printf("WARNING: Could not enable THP - do: 'echo madvise > /sys/kernel/mm/transparent_hugepage/enabled'\n");
+			}
+		}
+		if (thp < 0) {
+			ret = madvise(buf, bytes, MADV_NOHUGEPAGE);
+			if (ret && !g->print_once) {
+				g->print_once = 1;
+				printf("WARNING: Could not disable THP: run a CONFIG_TRANSPARENT_HUGEPAGE kernel?\n");
+			}
+		}
+	}
+
+	if (init_zero) {
+		bzero(buf, bytes);
+	} else {
+		/* Initialize random contents, different in each word: */
+		if (init_random) {
+			u64 *wbuf = (void *)buf;
+			long off = rand();
+			long i;
+
+			for (i = 0; i < bytes/8; i++)
+				wbuf[i] = i + off;
+		}
+	}
+
+	/* Align to 2MB boundary: */
+	buf = (void *)(((unsigned long)buf + HPSIZE-1) & ~(HPSIZE-1));
+
+	/* Restore affinity: */
+	if (init_cpu0) {
+		bind_to_cpumask(orig_mask);
+		mempol_restore();
+	}
+
+	return buf;
+}
+
+static void free_data(void *data, ssize_t bytes)
+{
+	int ret;
+
+	if (!data)
+		return;
+
+	ret = munmap(data, bytes);
+	BUG_ON(ret);
+}
+
+/*
+ * Create a shared memory buffer that can be shared between processes, zeroed:
+ */
+static void * zalloc_shared_data(ssize_t bytes)
+{
+	return alloc_data(bytes, MAP_SHARED, 1, g->p.init_cpu0,  g->p.thp, g->p.init_random);
+}
+
+/*
+ * Create a shared memory buffer that can be shared between processes:
+ */
+static void * setup_shared_data(ssize_t bytes)
+{
+	return alloc_data(bytes, MAP_SHARED, 0, g->p.init_cpu0,  g->p.thp, g->p.init_random);
+}
+
+/*
+ * Allocate process-local memory - this will either be shared between
+ * threads of this process, or only be accessed by this thread:
+ */
+static void * setup_private_data(ssize_t bytes)
+{
+	return alloc_data(bytes, MAP_PRIVATE, 0, g->p.init_cpu0,  g->p.thp, g->p.init_random);
+}
+
+/*
+ * Return a process-shared (global) mutex:
+ */
+static void init_global_mutex(pthread_mutex_t *mutex)
+{
+	pthread_mutexattr_t attr;
+
+	pthread_mutexattr_init(&attr);
+	pthread_mutexattr_setpshared(&attr, PTHREAD_PROCESS_SHARED);
+	pthread_mutex_init(mutex, &attr);
+}
+
+static int parse_cpu_list(const char *arg)
+{
+	p0.cpu_list_str = strdup(arg);
+
+	dprintf("got CPU list: {%s}\n", p0.cpu_list_str);
+
+	return 0;
+}
+
+static void parse_setup_cpu_list(void)
+{
+	struct thread_data *td;
+	char *str0, *str;
+	int t;
+
+	if (!g->p.cpu_list_str)
+		return;
+
+	dprintf("g->p.nr_tasks: %d\n", g->p.nr_tasks);
+
+	str0 = str = strdup(g->p.cpu_list_str);
+	t = 0;
+
+	BUG_ON(!str);
+
+	tprintf("# binding tasks to CPUs:\n");
+	tprintf("#  ");
+
+	while (true) {
+		int bind_cpu, bind_cpu_0, bind_cpu_1;
+		char *tok, *tok_end, *tok_step, *tok_len, *tok_mul;
+		int bind_len;
+		int step;
+		int mul;
+
+		tok = strsep(&str, ",");
+		if (!tok)
+			break;
+
+		tok_end = strstr(tok, "-");
+
+		dprintf("\ntoken: {%s}, end: {%s}\n", tok, tok_end);
+		if (!tok_end) {
+			/* Single CPU specified: */
+			bind_cpu_0 = bind_cpu_1 = atol(tok);
+		} else {
+			/* CPU range specified (for example: "5-11"): */
+			bind_cpu_0 = atol(tok);
+			bind_cpu_1 = atol(tok_end + 1);
+		}
+
+		step = 1;
+		tok_step = strstr(tok, "#");
+		if (tok_step) {
+			step = atol(tok_step + 1);
+			BUG_ON(step <= 0 || step >= g->p.nr_cpus);
+		}
+
+		/*
+		 * Mask length.
+		 * Eg: "--cpus 8_4-16#4" means: '--cpus 8_4,12_4,16_4',
+		 * where the _4 means the next 4 CPUs are allowed.
+		 */
+		bind_len = 1;
+		tok_len = strstr(tok, "_");
+		if (tok_len) {
+			bind_len = atol(tok_len + 1);
+			BUG_ON(bind_len <= 0 || bind_len > g->p.nr_cpus);
+		}
+
+		/* Multiplicator shortcut, "0x8" is a shortcut for: "0,0,0,0,0,0,0,0" */
+		mul = 1;
+		tok_mul = strstr(tok, "x");
+		if (tok_mul) {
+			mul = atol(tok_mul + 1);
+			BUG_ON(mul <= 0);
+		}
+
+		dprintf("CPUs: %d_%d-%d#%dx%d\n", bind_cpu_0, bind_len, bind_cpu_1, step, mul);
+
+		BUG_ON(bind_cpu_0 < 0 || bind_cpu_0 >= g->p.nr_cpus);
+		BUG_ON(bind_cpu_1 < 0 || bind_cpu_1 >= g->p.nr_cpus);
+		BUG_ON(bind_cpu_0 > bind_cpu_1);
+
+		for (bind_cpu = bind_cpu_0; bind_cpu <= bind_cpu_1; bind_cpu += step) {
+			int i;
+
+			for (i = 0; i < mul; i++) {
+				int cpu;
+
+				if (t >= g->p.nr_tasks) {
+					printf("\n# NOTE: ignoring bind CPUs starting at CPU#%d\n #", bind_cpu);
+					goto out;
+				}
+				td = g->threads + t;
+
+				if (t)
+					tprintf(",");
+				if (bind_len > 1) {
+					tprintf("%2d/%d", bind_cpu, bind_len);
+				} else {
+					tprintf("%2d", bind_cpu);
+				}
+
+				CPU_ZERO(&td->bind_cpumask);
+				for (cpu = bind_cpu; cpu < bind_cpu+bind_len; cpu++) {
+					BUG_ON(cpu < 0 || cpu >= g->p.nr_cpus);
+					CPU_SET(cpu, &td->bind_cpumask);
+				}
+				t++;
+			}
+		}
+	}
+out:
+
+	tprintf("\n");
+
+	if (t < g->p.nr_tasks)
+		printf("# NOTE: %d tasks bound, %d tasks unbound\n", t, g->p.nr_tasks - t);
+
+	free(str0);
+}
+
+static int parse_cpus_opt(const struct option *opt __maybe_unused,
+			  const char *arg, int unset __maybe_unused)
+{
+	if (!arg)
+		return -1;
+
+	return parse_cpu_list(arg);
+}
+
+static int parse_node_list(const char *arg)
+{
+	p0.node_list_str = strdup(arg);
+
+	dprintf("got NODE list: {%s}\n", p0.node_list_str);
+
+	return 0;
+}
+
+static void parse_setup_node_list(void)
+{
+	struct thread_data *td;
+	char *str0, *str;
+	int t;
+
+	if (!g->p.node_list_str)
+		return;
+
+	dprintf("g->p.nr_tasks: %d\n", g->p.nr_tasks);
+
+	str0 = str = strdup(g->p.node_list_str);
+	t = 0;
+
+	BUG_ON(!str);
+
+	tprintf("# binding tasks to NODEs:\n");
+	tprintf("# ");
+
+	while (true) {
+		int bind_node, bind_node_0, bind_node_1;
+		char *tok, *tok_end, *tok_step, *tok_mul;
+		int step;
+		int mul;
+
+		tok = strsep(&str, ",");
+		if (!tok)
+			break;
+
+		tok_end = strstr(tok, "-");
+
+		dprintf("\ntoken: {%s}, end: {%s}\n", tok, tok_end);
+		if (!tok_end) {
+			/* Single NODE specified: */
+			bind_node_0 = bind_node_1 = atol(tok);
+		} else {
+			/* NODE range specified (for example: "5-11"): */
+			bind_node_0 = atol(tok);
+			bind_node_1 = atol(tok_end + 1);
+		}
+
+		step = 1;
+		tok_step = strstr(tok, "#");
+		if (tok_step) {
+			step = atol(tok_step + 1);
+			BUG_ON(step <= 0 || step >= g->p.nr_nodes);
+		}
+
+		/* Multiplicator shortcut, "0x8" is a shortcut for: "0,0,0,0,0,0,0,0" */
+		mul = 1;
+		tok_mul = strstr(tok, "x");
+		if (tok_mul) {
+			mul = atol(tok_mul + 1);
+			BUG_ON(mul <= 0);
+		}
+
+		dprintf("NODEs: %d-%d #%d\n", bind_node_0, bind_node_1, step);
+
+		BUG_ON(bind_node_0 < 0 || bind_node_0 >= g->p.nr_nodes);
+		BUG_ON(bind_node_1 < 0 || bind_node_1 >= g->p.nr_nodes);
+		BUG_ON(bind_node_0 > bind_node_1);
+
+		for (bind_node = bind_node_0; bind_node <= bind_node_1; bind_node += step) {
+			int i;
+
+			for (i = 0; i < mul; i++) {
+				if (t >= g->p.nr_tasks) {
+					printf("\n# NOTE: ignoring bind NODEs starting at NODE#%d\n", bind_node);
+					goto out;
+				}
+				td = g->threads + t;
+
+				if (!t)
+					tprintf(" %2d", bind_node);
+				else
+					tprintf(",%2d", bind_node);
+
+				td->bind_node = bind_node;
+				t++;
+			}
+		}
+	}
+out:
+
+	tprintf("\n");
+
+	if (t < g->p.nr_tasks)
+		printf("# NOTE: %d tasks mem-bound, %d tasks unbound\n", t, g->p.nr_tasks - t);
+
+	free(str0);
+}
+
+static int parse_nodes_opt(const struct option *opt __maybe_unused,
+			  const char *arg, int unset __maybe_unused)
+{
+	if (!arg)
+		return -1;
+
+	return parse_node_list(arg);
+
+	return 0;
+}
+
+#define BIT(x) (1ul << x)
+
+static inline uint32_t lfsr_32(uint32_t lfsr)
+{
+	const uint32_t taps = BIT(1) | BIT(5) | BIT(6) | BIT(31);
+	return (lfsr>>1) ^ ((0x0u - (lfsr & 0x1u)) & taps);
+}
+
+/*
+ * Make sure there's real data dependency to RAM (when read
+ * accesses are enabled), so the compiler, the CPU and the
+ * kernel (KSM, zero page, etc.) cannot optimize away RAM
+ * accesses:
+ */
+static inline u64 access_data(u64 *data __attribute__((unused)), u64 val)
+{
+	if (g->p.data_reads)
+		val += *data;
+	if (g->p.data_writes)
+		*data = val + 1;
+	return val;
+}
+
+/*
+ * The worker process does two types of work, a forwards going
+ * loop and a backwards going loop.
+ *
+ * We do this so that on multiprocessor systems we do not create
+ * a 'train' of processing, with highly synchronized processes,
+ * skewing the whole benchmark.
+ */
+static u64 do_work(u8 *__data, long bytes, int nr, int nr_max, int loop, u64 val)
+{
+	long words = bytes/sizeof(u64);
+	u64 *data = (void *)__data;
+	long chunk_0, chunk_1;
+	u64 *d0, *d, *d1;
+	long off;
+	long i;
+
+	BUG_ON(!data && words);
+	BUG_ON(data && !words);
+
+	if (!data)
+		return val;
+
+	/* Very simple memset() work variant: */
+	if (g->p.data_zero_memset && !g->p.data_rand_walk) {
+		bzero(data, bytes);
+		return val;
+	}
+
+	/* Spread out by PID/TID nr and by loop nr: */
+	chunk_0 = words/nr_max;
+	chunk_1 = words/g->p.nr_loops;
+	off = nr*chunk_0 + loop*chunk_1;
+
+	while (off >= words)
+		off -= words;
+
+	if (g->p.data_rand_walk) {
+		u32 lfsr = nr + loop + val;
+		int j;
+
+		for (i = 0; i < words/1024; i++) {
+			long start, end;
+
+			lfsr = lfsr_32(lfsr);
+
+			start = lfsr % words;
+			end = min(start + 1024, words-1);
+
+			if (g->p.data_zero_memset) {
+				bzero(data + start, (end-start) * sizeof(u64));
+			} else {
+				for (j = start; j < end; j++)
+					val = access_data(data + j, val);
+			}
+		}
+	} else if (!g->p.data_backwards || (nr + loop) & 1) {
+
+		d0 = data + off;
+		d  = data + off + 1;
+		d1 = data + words;
+
+		/* Process data forwards: */
+		for (;;) {
+			if (unlikely(d >= d1))
+				d = data;
+			if (unlikely(d == d0))
+				break;
+
+			val = access_data(d, val);
+
+			d++;
+		}
+	} else {
+		/* Process data backwards: */
+
+		d0 = data + off;
+		d  = data + off - 1;
+		d1 = data + words;
+
+		/* Process data forwards: */
+		for (;;) {
+			if (unlikely(d < data))
+				d = data + words-1;
+			if (unlikely(d == d0))
+				break;
+
+			val = access_data(d, val);
+
+			d--;
+		}
+	}
+
+	return val;
+}
+
+static void update_curr_cpu(int task_nr, unsigned long bytes_worked)
+{
+	unsigned int cpu;
+
+	cpu = sched_getcpu();
+
+	g->threads[task_nr].curr_cpu = cpu;
+	prctl(0, bytes_worked);
+}
+
+#define MAX_NR_NODES	64
+
+/*
+ * Count the number of nodes a process's threads
+ * are spread out on.
+ *
+ * A count of 1 means that the process is compressed
+ * to a single node. A count of g->p.nr_nodes means it's
+ * spread out on the whole system.
+ */
+static int count_process_nodes(int process_nr)
+{
+	char node_present[MAX_NR_NODES] = { 0, };
+	int nodes;
+	int n, t;
+
+	for (t = 0; t < g->p.nr_threads; t++) {
+		struct thread_data *td;
+		int task_nr;
+		int node;
+
+		task_nr = process_nr*g->p.nr_threads + t;
+		td = g->threads + task_nr;
+
+		node = numa_node_of_cpu(td->curr_cpu);
+		node_present[node] = 1;
+	}
+
+	nodes = 0;
+
+	for (n = 0; n < MAX_NR_NODES; n++)
+		nodes += node_present[n];
+
+	return nodes;
+}
+
+/*
+ * Count the number of distinct process-threads a node contains.
+ *
+ * A count of 1 means that the node contains only a single
+ * process. If all nodes on the system contain at most one
+ * process then we are well-converged.
+ */
+static int count_node_processes(int node)
+{
+	int processes = 0;
+	int t, p;
+
+	for (p = 0; p < g->p.nr_proc; p++) {
+		for (t = 0; t < g->p.nr_threads; t++) {
+			struct thread_data *td;
+			int task_nr;
+			int n;
+
+			task_nr = p*g->p.nr_threads + t;
+			td = g->threads + task_nr;
+
+			n = numa_node_of_cpu(td->curr_cpu);
+			if (n == node) {
+				processes++;
+				break;
+			}
+		}
+	}
+
+	return processes;
+}
+
+static void calc_convergence_compression(int *strong)
+{
+	unsigned int nodes_min, nodes_max;
+	int p;
+
+	nodes_min = -1;
+	nodes_max =  0;
+
+	for (p = 0; p < g->p.nr_proc; p++) {
+		unsigned int nodes = count_process_nodes(p);
+
+		nodes_min = min(nodes, nodes_min);
+		nodes_max = max(nodes, nodes_max);
+	}
+
+	/* Strong convergence: all threads compress on a single node: */
+	if (nodes_min == 1 && nodes_max == 1) {
+		*strong = 1;
+	} else {
+		*strong = 0;
+		tprintf(" {%d-%d}", nodes_min, nodes_max);
+	}
+}
+
+static void calc_convergence(double runtime_ns_max, double *convergence)
+{
+	unsigned int loops_done_min, loops_done_max;
+	int process_groups;
+	int nodes[MAX_NR_NODES];
+	int distance;
+	int nr_min;
+	int nr_max;
+	int strong;
+	int sum;
+	int nr;
+	int node;
+	int cpu;
+	int t;
+
+	if (!g->p.show_convergence && !g->p.measure_convergence)
+		return;
+
+	for (node = 0; node < g->p.nr_nodes; node++)
+		nodes[node] = 0;
+
+	loops_done_min = -1;
+	loops_done_max = 0;
+
+	for (t = 0; t < g->p.nr_tasks; t++) {
+		struct thread_data *td = g->threads + t;
+		unsigned int loops_done;
+
+		cpu = td->curr_cpu;
+
+		/* Not all threads have written it yet: */
+		if (cpu < 0)
+			continue;
+
+		node = numa_node_of_cpu(cpu);
+
+		nodes[node]++;
+
+		loops_done = td->loops_done;
+		loops_done_min = min(loops_done, loops_done_min);
+		loops_done_max = max(loops_done, loops_done_max);
+	}
+
+	nr_max = 0;
+	nr_min = g->p.nr_tasks;
+	sum = 0;
+
+	for (node = 0; node < g->p.nr_nodes; node++) {
+		nr = nodes[node];
+		nr_min = min(nr, nr_min);
+		nr_max = max(nr, nr_max);
+		sum += nr;
+	}
+	BUG_ON(nr_min > nr_max);
+
+	BUG_ON(sum > g->p.nr_tasks);
+
+	if (0 && (sum < g->p.nr_tasks))
+		return;
+
+	/*
+	 * Count the number of distinct process groups present
+	 * on nodes - when we are converged this will decrease
+	 * to g->p.nr_proc:
+	 */
+	process_groups = 0;
+
+	for (node = 0; node < g->p.nr_nodes; node++) {
+		int processes = count_node_processes(node);
+
+		nr = nodes[node];
+		tprintf(" %2d/%-2d", nr, processes);
+
+		process_groups += processes;
+	}
+
+	distance = nr_max - nr_min;
+
+	tprintf(" [%2d/%-2d]", distance, process_groups);
+
+	tprintf(" l:%3d-%-3d (%3d)",
+		loops_done_min, loops_done_max, loops_done_max-loops_done_min);
+
+	if (loops_done_min && loops_done_max) {
+		double skew = 1.0 - (double)loops_done_min/loops_done_max;
+
+		tprintf(" [%4.1f%%]", skew * 100.0);
+	}
+
+	calc_convergence_compression(&strong);
+
+	if (strong && process_groups == g->p.nr_proc) {
+		if (!*convergence) {
+			*convergence = runtime_ns_max;
+			tprintf(" (%6.1fs converged)\n", *convergence/1e9);
+			if (g->p.measure_convergence) {
+				g->all_converged = true;
+				g->stop_work = true;
+			}
+		}
+	} else {
+		if (*convergence) {
+			tprintf(" (%6.1fs de-converged)", runtime_ns_max/1e9);
+			*convergence = 0;
+		}
+		tprintf("\n");
+	}
+}
+
+static void show_summary(double runtime_ns_max, int l, double *convergence)
+{
+	tprintf("\r #  %5.1f%%  [%.1f mins]",
+		(double)(l+1)/g->p.nr_loops*100.0, runtime_ns_max/1e9 / 60.0);
+
+	calc_convergence(runtime_ns_max, convergence);
+
+	if (g->p.show_details >= 0)
+		fflush(stdout);
+}
+
+static void *worker_thread(void *__tdata)
+{
+	struct thread_data *td = __tdata;
+	struct timeval start0, start, stop, diff;
+	int process_nr = td->process_nr;
+	int thread_nr = td->thread_nr;
+	unsigned long last_perturbance;
+	int task_nr = td->task_nr;
+	int details = g->p.show_details;
+	int first_task, last_task;
+	double convergence = 0;
+	u64 val = td->val;
+	double runtime_ns_max;
+	u8 *global_data;
+	u8 *process_data;
+	u8 *thread_data;
+	u64 bytes_done;
+	long work_done;
+	u32 l;
+
+	bind_to_cpumask(td->bind_cpumask);
+	bind_to_memnode(td->bind_node);
+
+	set_taskname("thread %d/%d", process_nr, thread_nr);
+
+	global_data = g->data;
+	process_data = td->process_data;
+	thread_data = setup_private_data(g->p.bytes_thread);
+
+	bytes_done = 0;
+
+	last_task = 0;
+	if (process_nr == g->p.nr_proc-1 && thread_nr == g->p.nr_threads-1)
+		last_task = 1;
+
+	first_task = 0;
+	if (process_nr == 0 && thread_nr == 0)
+		first_task = 1;
+
+	if (details >= 2) {
+		printf("#  thread %2d / %2d global mem: %p, process mem: %p, thread mem: %p\n",
+			process_nr, thread_nr, global_data, process_data, thread_data);
+	}
+
+	if (g->p.serialize_startup) {
+		pthread_mutex_lock(&g->startup_mutex);
+		g->nr_tasks_started++;
+		pthread_mutex_unlock(&g->startup_mutex);
+
+		/* Here we will wait for the main process to start us all at once: */
+		pthread_mutex_lock(&g->start_work_mutex);
+		g->nr_tasks_working++;
+
+		/* Last one wake the main process: */
+		if (g->nr_tasks_working == g->p.nr_tasks)
+			pthread_mutex_unlock(&g->startup_done_mutex);
+
+		pthread_mutex_unlock(&g->start_work_mutex);
+	}
+
+	gettimeofday(&start0, NULL);
+
+	start = stop = start0;
+	last_perturbance = start.tv_sec;
+
+	for (l = 0; l < g->p.nr_loops; l++) {
+		start = stop;
+
+		if (g->stop_work)
+			break;
+
+		val += do_work(global_data,  g->p.bytes_global,  process_nr, g->p.nr_proc,	l, val);
+		val += do_work(process_data, g->p.bytes_process, thread_nr,  g->p.nr_threads,	l, val);
+		val += do_work(thread_data,  g->p.bytes_thread,  0,          1,		l, val);
+
+		if (g->p.sleep_usecs) {
+			pthread_mutex_lock(td->process_lock);
+			usleep(g->p.sleep_usecs);
+			pthread_mutex_unlock(td->process_lock);
+		}
+		/*
+		 * Amount of work to be done under a process-global lock:
+		 */
+		if (g->p.bytes_process_locked) {
+			pthread_mutex_lock(td->process_lock);
+			val += do_work(process_data, g->p.bytes_process_locked, thread_nr,  g->p.nr_threads,	l, val);
+			pthread_mutex_unlock(td->process_lock);
+		}
+
+		work_done = g->p.bytes_global + g->p.bytes_process +
+			    g->p.bytes_process_locked + g->p.bytes_thread;
+
+		update_curr_cpu(task_nr, work_done);
+		bytes_done += work_done;
+
+		if (details < 0 && !g->p.perturb_secs && !g->p.measure_convergence && !g->p.nr_secs)
+			continue;
+
+		td->loops_done = l;
+
+		gettimeofday(&stop, NULL);
+
+		/* Check whether our max runtime timed out: */
+		if (g->p.nr_secs) {
+			timersub(&stop, &start0, &diff);
+			if (diff.tv_sec >= g->p.nr_secs) {
+				g->stop_work = true;
+				break;
+			}
+		}
+
+		/* Update the summary at most once per second: */
+		if (start.tv_sec == stop.tv_sec)
+			continue;
+
+		/*
+		 * Perturb the first task's equilibrium every g->p.perturb_secs seconds,
+		 * by migrating to CPU#0:
+		 */
+		if (first_task && g->p.perturb_secs && (int)(stop.tv_sec - last_perturbance) >= g->p.perturb_secs) {
+			cpu_set_t orig_mask;
+			int target_cpu;
+			int this_cpu;
+
+			last_perturbance = stop.tv_sec;
+
+			/*
+			 * Depending on where we are running, move into
+			 * the other half of the system, to create some
+			 * real disturbance:
+			 */
+			this_cpu = g->threads[task_nr].curr_cpu;
+			if (this_cpu < g->p.nr_cpus/2)
+				target_cpu = g->p.nr_cpus-1;
+			else
+				target_cpu = 0;
+
+			orig_mask = bind_to_cpu(target_cpu);
+
+			/* Here we are running on the target CPU already */
+			if (details >= 1)
+				printf(" (injecting perturbalance, moved to CPU#%d)\n", target_cpu);
+
+			bind_to_cpumask(orig_mask);
+		}
+
+		if (details >= 3) {
+			timersub(&stop, &start, &diff);
+			runtime_ns_max = diff.tv_sec * 1000000000;
+			runtime_ns_max += diff.tv_usec * 1000;
+
+			if (details >= 0) {
+				printf(" #%2d / %2d: %14.2lf nsecs/op [val: %016lx]\n",
+					process_nr, thread_nr, runtime_ns_max / bytes_done, val);
+			}
+			fflush(stdout);
+		}
+		if (!last_task)
+			continue;
+
+		timersub(&stop, &start0, &diff);
+		runtime_ns_max = diff.tv_sec * 1000000000ULL;
+		runtime_ns_max += diff.tv_usec * 1000ULL;
+
+		show_summary(runtime_ns_max, l, &convergence);
+	}
+
+	gettimeofday(&stop, NULL);
+	timersub(&stop, &start0, &diff);
+	td->runtime_ns = diff.tv_sec * 1000000000ULL;
+	td->runtime_ns += diff.tv_usec * 1000ULL;
+
+	free_data(thread_data, g->p.bytes_thread);
+
+	pthread_mutex_lock(&g->stop_work_mutex);
+	g->bytes_done += bytes_done;
+	pthread_mutex_unlock(&g->stop_work_mutex);
+
+	return NULL;
+}
+
+/*
+ * A worker process starts a couple of threads:
+ */
+static void worker_process(int process_nr)
+{
+	pthread_mutex_t process_lock;
+	struct thread_data *td;
+	pthread_t *pthreads;
+	u8 *process_data;
+	int task_nr;
+	int ret;
+	int t;
+
+	pthread_mutex_init(&process_lock, NULL);
+	set_taskname("process %d", process_nr);
+
+	/*
+	 * Pick up the memory policy and the CPU binding of our first thread,
+	 * so that we initialize memory accordingly:
+	 */
+	task_nr = process_nr*g->p.nr_threads;
+	td = g->threads + task_nr;
+
+	bind_to_memnode(td->bind_node);
+	bind_to_cpumask(td->bind_cpumask);
+
+	pthreads = zalloc(g->p.nr_threads * sizeof(pthread_t));
+	process_data = setup_private_data(g->p.bytes_process);
+
+	if (g->p.show_details >= 3) {
+		printf(" # process %2d global mem: %p, process mem: %p\n",
+			process_nr, g->data, process_data);
+	}
+
+	for (t = 0; t < g->p.nr_threads; t++) {
+		task_nr = process_nr*g->p.nr_threads + t;
+		td = g->threads + task_nr;
+
+		td->process_data = process_data;
+		td->process_nr   = process_nr;
+		td->thread_nr    = t;
+		td->task_nr	 = task_nr;
+		td->val          = rand();
+		td->curr_cpu	 = -1;
+		td->process_lock = &process_lock;
+
+		ret = pthread_create(pthreads + t, NULL, worker_thread, td);
+		BUG_ON(ret);
+	}
+
+	for (t = 0; t < g->p.nr_threads; t++) {
+                ret = pthread_join(pthreads[t], NULL);
+		BUG_ON(ret);
+	}
+
+	free_data(process_data, g->p.bytes_process);
+	free(pthreads);
+}
+
+static void print_summary(void)
+{
+	if (g->p.show_details < 0)
+		return;
+
+	printf("\n ###\n");
+	printf(" # %d %s will execute (on %d nodes, %d CPUs):\n",
+		g->p.nr_tasks, g->p.nr_tasks == 1 ? "task" : "tasks", g->p.nr_nodes, g->p.nr_cpus);
+	printf(" #      %5dx %5ldMB global  shared mem operations\n",
+			g->p.nr_loops, g->p.bytes_global/1024/1024);
+	printf(" #      %5dx %5ldMB process shared mem operations\n",
+			g->p.nr_loops, g->p.bytes_process/1024/1024);
+	printf(" #      %5dx %5ldMB thread  local  mem operations\n",
+			g->p.nr_loops, g->p.bytes_thread/1024/1024);
+
+	printf(" ###\n");
+
+	printf("\n ###\n"); fflush(stdout);
+}
+
+static void init_thread_data(void)
+{
+	ssize_t size = sizeof(*g->threads)*g->p.nr_tasks;
+	int t;
+
+	g->threads = zalloc_shared_data(size);
+
+	for (t = 0; t < g->p.nr_tasks; t++) {
+		struct thread_data *td = g->threads + t;
+		int cpu;
+
+		/* Allow all nodes by default: */
+		td->bind_node = -1;
+
+		/* Allow all CPUs by default: */
+		CPU_ZERO(&td->bind_cpumask);
+		for (cpu = 0; cpu < g->p.nr_cpus; cpu++)
+			CPU_SET(cpu, &td->bind_cpumask);
+	}
+}
+
+static void deinit_thread_data(void)
+{
+	ssize_t size = sizeof(*g->threads)*g->p.nr_tasks;
+
+	free_data(g->threads, size);
+}
+
+static int init(void)
+{
+	g = (void *)alloc_data(sizeof(*g), MAP_SHARED, 1, 0, 0 /* THP */, 0);
+
+	/* Copy over options: */
+	g->p = p0;
+
+	g->p.nr_cpus = numa_num_configured_cpus();
+
+	g->p.nr_nodes = numa_max_node() + 1;
+
+	/* char array in count_process_nodes(): */
+	BUG_ON(g->p.nr_nodes > MAX_NR_NODES || g->p.nr_nodes < 0);
+
+	if (g->p.show_quiet && !g->p.show_details)
+		g->p.show_details = -1;
+
+	/* Some memory should be specified: */
+	if (!g->p.mb_global_str && !g->p.mb_proc_str && !g->p.mb_thread_str)
+		return -1;
+
+	if (g->p.mb_global_str) {
+		g->p.mb_global = atof(g->p.mb_global_str);
+		BUG_ON(g->p.mb_global < 0);
+	}
+
+	if (g->p.mb_proc_str) {
+		g->p.mb_proc = atof(g->p.mb_proc_str);
+		BUG_ON(g->p.mb_proc < 0);
+	}
+
+	if (g->p.mb_proc_locked_str) {
+		g->p.mb_proc_locked = atof(g->p.mb_proc_locked_str);
+		BUG_ON(g->p.mb_proc_locked < 0);
+		BUG_ON(g->p.mb_proc_locked > g->p.mb_proc);
+	}
+
+	if (g->p.mb_thread_str) {
+		g->p.mb_thread = atof(g->p.mb_thread_str);
+		BUG_ON(g->p.mb_thread < 0);
+	}
+
+	BUG_ON(g->p.nr_threads <= 0);
+	BUG_ON(g->p.nr_proc <= 0);
+
+	g->p.nr_tasks = g->p.nr_proc*g->p.nr_threads;
+
+	g->p.bytes_global		= g->p.mb_global	*1024L*1024L;
+	g->p.bytes_process		= g->p.mb_proc		*1024L*1024L;
+	g->p.bytes_process_locked	= g->p.mb_proc_locked	*1024L*1024L;
+	g->p.bytes_thread		= g->p.mb_thread	*1024L*1024L;
+
+	g->data = setup_shared_data(g->p.bytes_global);
+
+	/* Startup serialization: */
+	init_global_mutex(&g->start_work_mutex);
+	init_global_mutex(&g->startup_mutex);
+	init_global_mutex(&g->startup_done_mutex);
+	init_global_mutex(&g->stop_work_mutex);
+
+	init_thread_data();
+
+	tprintf("#\n");
+	parse_setup_cpu_list();
+	parse_setup_node_list();
+	tprintf("#\n");
+
+	print_summary();
+
+	return 0;
+}
+
+static void deinit(void)
+{
+	free_data(g->data, g->p.bytes_global);
+	g->data = NULL;
+
+	deinit_thread_data();
+
+	free_data(g, sizeof(*g));
+	g = NULL;
+}
+
+/*
+ * Print a short or long result, depending on the verbosity setting:
+ */
+static void print_res(const char *name, double val,
+		      const char *txt_unit, const char *txt_short, const char *txt_long)
+{
+	if (!name)
+		name = "main,";
+
+	if (g->p.show_quiet)
+		printf(" %-30s %15.3f, %-15s %s\n", name, val, txt_unit, txt_short);
+	else
+		printf(" %14.3f %s\n", val, txt_long);
+}
+
+static int __bench_numa(const char *name)
+{
+	struct timeval start, stop, diff;
+	u64 runtime_ns_min, runtime_ns_sum;
+	pid_t *pids, pid, wpid;
+	double delta_runtime;
+	double runtime_avg;
+	double runtime_sec_max;
+	double runtime_sec_min;
+	int wait_stat;
+	double bytes;
+	int i, t;
+
+	if (init())
+		return -1;
+
+	pids = zalloc(g->p.nr_proc * sizeof(*pids));
+	pid = -1;
+
+	/* All threads try to acquire it, this way we can wait for them to start up: */
+	pthread_mutex_lock(&g->start_work_mutex);
+
+	if (g->p.serialize_startup) {
+		tprintf(" #\n");
+		tprintf(" # Startup synchronization: ..."); fflush(stdout);
+	}
+
+	gettimeofday(&start, NULL);
+
+	for (i = 0; i < g->p.nr_proc; i++) {
+		pid = fork();
+		dprintf(" # process %2d: PID %d\n", i, pid);
+
+		BUG_ON(pid < 0);
+		if (!pid) {
+			/* Child process: */
+			worker_process(i);
+
+			exit(0);
+		}
+		pids[i] = pid;
+
+	}
+	/* Wait for all the threads to start up: */
+	while (g->nr_tasks_started != g->p.nr_tasks)
+		usleep(1000);
+
+	BUG_ON(g->nr_tasks_started != g->p.nr_tasks);
+
+	if (g->p.serialize_startup) {
+		double startup_sec;
+
+		pthread_mutex_lock(&g->startup_done_mutex);
+
+		/* This will start all threads: */
+		pthread_mutex_unlock(&g->start_work_mutex);
+
+		/* This mutex is locked - the last started thread will wake us: */
+		pthread_mutex_lock(&g->startup_done_mutex);
+
+		gettimeofday(&stop, NULL);
+
+		timersub(&stop, &start, &diff);
+
+		startup_sec = diff.tv_sec * 1000000000.0;
+		startup_sec += diff.tv_usec * 1000.0;
+		startup_sec /= 1e9;
+
+		tprintf(" threads initialized in %.6f seconds.\n", startup_sec);
+		tprintf(" #\n");
+
+		start = stop;
+		pthread_mutex_unlock(&g->startup_done_mutex);
+	} else {
+		gettimeofday(&start, NULL);
+	}
+
+	/* Parent process: */
+
+
+	for (i = 0; i < g->p.nr_proc; i++) {
+		wpid = waitpid(pids[i], &wait_stat, 0);
+		BUG_ON(wpid < 0);
+		BUG_ON(!WIFEXITED(wait_stat));
+
+	}
+
+	runtime_ns_sum = 0;
+	runtime_ns_min = -1LL;
+
+	for (t = 0; t < g->p.nr_tasks; t++) {
+		u64 thread_runtime_ns = g->threads[t].runtime_ns;
+
+		runtime_ns_sum += thread_runtime_ns;
+		runtime_ns_min = min(thread_runtime_ns, runtime_ns_min);
+	}
+
+	gettimeofday(&stop, NULL);
+	timersub(&stop, &start, &diff);
+
+	BUG_ON(bench_format != BENCH_FORMAT_DEFAULT);
+
+	tprintf("\n ###\n");
+	tprintf("\n");
+
+	runtime_sec_max = diff.tv_sec * 1000000000.0;
+	runtime_sec_max += diff.tv_usec * 1000.0;
+	runtime_sec_max /= 1e9;
+
+	runtime_sec_min = runtime_ns_min/1e9;
+
+	bytes = g->bytes_done;
+	runtime_avg = (double)runtime_ns_sum / g->p.nr_tasks / 1e9;
+
+	if (g->p.measure_convergence) {
+		print_res(name, runtime_sec_max,
+			"secs,", "NUMA-convergence-latency", "secs latency to NUMA-converge");
+	}
+
+	print_res(name, runtime_sec_max,
+		"secs,", "runtime-max/thread",	"secs slowest (max) thread-runtime");
+
+	print_res(name, runtime_sec_min,
+		"secs,", "runtime-min/thread",	"secs fastest (min) thread-runtime");
+
+	print_res(name, runtime_avg,
+		"secs,", "runtime-avg/thread",	"secs average thread-runtime");
+
+	delta_runtime = (runtime_sec_max - runtime_sec_min)/2.0;
+	print_res(name, delta_runtime / runtime_sec_max * 100.0,
+		"%,", "spread-runtime/thread",	"% difference between max/avg runtime");
+
+	print_res(name, bytes / g->p.nr_tasks / 1e9,
+		"GB,", "data/thread",		"GB data processed, per thread");
+
+	print_res(name, bytes / 1e9,
+		"GB,", "data-total",		"GB data processed, total");
+
+	print_res(name, runtime_sec_max * 1e9 / (bytes / g->p.nr_tasks),
+		"nsecs,", "runtime/byte/thread","nsecs/byte/thread runtime");
+
+	print_res(name, bytes / g->p.nr_tasks / 1e9 / runtime_sec_max,
+		"GB/sec,", "thread-speed",	"GB/sec/thread speed");
+
+	print_res(name, bytes / runtime_sec_max / 1e9,
+		"GB/sec,", "total-speed",	"GB/sec total speed");
+
+	free(pids);
+
+	deinit();
+
+	return 0;
+}
+
+#define MAX_ARGS 50
+
+static int command_size(const char **argv)
+{
+	int size = 0;
+
+	while (*argv) {
+		size++;
+		argv++;
+	}
+
+	BUG_ON(size >= MAX_ARGS);
+
+	return size;
+}
+
+static void init_params(struct params *p, const char *name, int argc, const char **argv)
+{
+	int i;
+
+	printf("\n # Running %s \"perf bench numa", name);
+
+	for (i = 0; i < argc; i++)
+		printf(" %s", argv[i]);
+
+	printf("\"\n");
+
+	memset(p, 0, sizeof(*p));
+
+	/* Initialize nonzero defaults: */
+
+	p->serialize_startup		= 1;
+	p->data_reads			= true;
+	p->data_writes			= true;
+	p->data_backwards		= true;
+	p->data_rand_walk		= true;
+	p->nr_loops			= -1;
+	p->init_random			= true;
+}
+
+static int run_bench_numa(const char *name, const char **argv)
+{
+	int argc = command_size(argv);
+
+	init_params(&p0, name, argc, argv);
+	argc = parse_options(argc, argv, options, bench_numa_usage, 0);
+	if (argc)
+		goto err;
+
+	if (__bench_numa(name))
+		goto err;
+
+	return 0;
+
+err:
+	usage_with_options(numa_usage, options);
+	return -1;
+}
+
+#define OPT_BW_RAM		"-s",  "20", "-zZq",    "--thp", " 1", "--no-data_rand_walk"
+#define OPT_BW_RAM_NOTHP	OPT_BW_RAM,		"--thp", "-1"
+
+#define OPT_CONV		"-s", "100", "-zZ0qcm", "--thp", " 1"
+#define OPT_CONV_NOTHP		OPT_CONV,		"--thp", "-1"
+
+#define OPT_BW			"-s",  "20", "-zZ0q",   "--thp", " 1"
+#define OPT_BW_NOTHP		OPT_BW,			"--thp", "-1"
+
+/*
+ * The built-in test-suite executed by "perf bench numa -a".
+ *
+ * (A minimum of 4 nodes and 16 GB of RAM is recommended.)
+ */
+static const char *tests[][MAX_ARGS] = {
+   /* Basic single-stream NUMA bandwidth measurements: */
+   { "RAM-bw-local,",	  "mem",  "-p",  "1",  "-t",  "1", "-P", "1024",
+			  "-C" ,   "0", "-M",   "0", OPT_BW_RAM },
+   { "RAM-bw-local-NOTHP,",
+			  "mem",  "-p",  "1",  "-t",  "1", "-P", "1024",
+			  "-C" ,   "0", "-M",   "0", OPT_BW_RAM_NOTHP },
+   { "RAM-bw-remote,",	  "mem",  "-p",  "1",  "-t",  "1", "-P", "1024",
+			  "-C" ,   "0", "-M",   "1", OPT_BW_RAM },
+
+   /* 2-stream NUMA bandwidth measurements: */
+   { "RAM-bw-local-2x,",  "mem",  "-p",  "2",  "-t",  "1", "-P", "1024",
+			   "-C", "0,2", "-M", "0x2", OPT_BW_RAM },
+   { "RAM-bw-remote-2x,", "mem",  "-p",  "2",  "-t",  "1", "-P", "1024",
+		 	   "-C", "0,2", "-M", "1x2", OPT_BW_RAM },
+
+   /* Cross-stream NUMA bandwidth measurement: */
+   { "RAM-bw-cross,",     "mem",  "-p",  "2",  "-t",  "1", "-P", "1024",
+		 	   "-C", "0,8", "-M", "1,0", OPT_BW_RAM },
+
+   /* Convergence latency measurements: */
+   { " 1x3-convergence,", "mem",  "-p",  "1", "-t",  "3", "-P",  "512", OPT_CONV },
+   { " 1x4-convergence,", "mem",  "-p",  "1", "-t",  "4", "-P",  "512", OPT_CONV },
+   { " 1x6-convergence,", "mem",  "-p",  "1", "-t",  "6", "-P", "1020", OPT_CONV },
+   { " 2x3-convergence,", "mem",  "-p",  "3", "-t",  "3", "-P", "1020", OPT_CONV },
+   { " 3x3-convergence,", "mem",  "-p",  "3", "-t",  "3", "-P", "1020", OPT_CONV },
+   { " 4x4-convergence,", "mem",  "-p",  "4", "-t",  "4", "-P",  "512", OPT_CONV },
+   { " 4x4-convergence-NOTHP,",
+			  "mem",  "-p",  "4", "-t",  "4", "-P",  "512", OPT_CONV_NOTHP },
+   { " 4x6-convergence,", "mem",  "-p",  "4", "-t",  "6", "-P", "1020", OPT_CONV },
+   { " 4x8-convergence,", "mem",  "-p",  "4", "-t",  "8", "-P",  "512", OPT_CONV },
+   { " 8x4-convergence,", "mem",  "-p",  "8", "-t",  "4", "-P",  "512", OPT_CONV },
+   { " 8x4-convergence-NOTHP,",
+			  "mem",  "-p",  "8", "-t",  "4", "-P",  "512", OPT_CONV_NOTHP },
+   { " 3x1-convergence,", "mem",  "-p",  "3", "-t",  "1", "-P",  "512", OPT_CONV },
+   { " 4x1-convergence,", "mem",  "-p",  "4", "-t",  "1", "-P",  "512", OPT_CONV },
+   { " 8x1-convergence,", "mem",  "-p",  "8", "-t",  "1", "-P",  "512", OPT_CONV },
+   { "16x1-convergence,", "mem",  "-p", "16", "-t",  "1", "-P",  "256", OPT_CONV },
+   { "32x1-convergence,", "mem",  "-p", "32", "-t",  "1", "-P",  "128", OPT_CONV },
+
+   /* Various NUMA process/thread layout bandwidth measurements: */
+   { " 2x1-bw-process,",  "mem",  "-p",  "2", "-t",  "1", "-P", "1024", OPT_BW },
+   { " 3x1-bw-process,",  "mem",  "-p",  "3", "-t",  "1", "-P", "1024", OPT_BW },
+   { " 4x1-bw-process,",  "mem",  "-p",  "4", "-t",  "1", "-P", "1024", OPT_BW },
+   { " 8x1-bw-process,",  "mem",  "-p",  "8", "-t",  "1", "-P", " 512", OPT_BW },
+   { " 8x1-bw-process-NOTHP,",
+			  "mem",  "-p",  "8", "-t",  "1", "-P", " 512", OPT_BW_NOTHP },
+   { "16x1-bw-process,",  "mem",  "-p", "16", "-t",  "1", "-P",  "256", OPT_BW },
+
+   { " 4x1-bw-thread,",	  "mem",  "-p",  "1", "-t",  "4", "-T",  "256", OPT_BW },
+   { " 8x1-bw-thread,",	  "mem",  "-p",  "1", "-t",  "8", "-T",  "256", OPT_BW },
+   { "16x1-bw-thread,",   "mem",  "-p",  "1", "-t", "16", "-T",  "128", OPT_BW },
+   { "32x1-bw-thread,",   "mem",  "-p",  "1", "-t", "32", "-T",   "64", OPT_BW },
+
+   { " 2x3-bw-thread,",	  "mem",  "-p",  "2", "-t",  "3", "-P",  "512", OPT_BW },
+   { " 4x4-bw-thread,",	  "mem",  "-p",  "4", "-t",  "4", "-P",  "512", OPT_BW },
+   { " 4x6-bw-thread,",	  "mem",  "-p",  "4", "-t",  "6", "-P",  "512", OPT_BW },
+   { " 4x8-bw-thread,",	  "mem",  "-p",  "4", "-t",  "8", "-P",  "512", OPT_BW },
+   { " 4x8-bw-thread-NOTHP,",
+			  "mem",  "-p",  "4", "-t",  "8", "-P",  "512", OPT_BW_NOTHP },
+   { " 3x3-bw-thread,",	  "mem",  "-p",  "3", "-t",  "3", "-P",  "512", OPT_BW },
+   { " 5x5-bw-thread,",	  "mem",  "-p",  "5", "-t",  "5", "-P",  "512", OPT_BW },
+
+   { "2x16-bw-thread,",   "mem",  "-p",  "2", "-t", "16", "-P",  "512", OPT_BW },
+   { "1x32-bw-thread,",   "mem",  "-p",  "1", "-t", "32", "-P", "2048", OPT_BW },
+
+   { "numa02-bw,",	  "mem",  "-p",  "1", "-t", "32", "-T",   "32", OPT_BW },
+   { "numa02-bw-NOTHP,",  "mem",  "-p",  "1", "-t", "32", "-T",   "32", OPT_BW_NOTHP },
+   { "numa01-bw-thread,", "mem",  "-p",  "2", "-t", "16", "-T",  "192", OPT_BW },
+   { "numa01-bw-thread-NOTHP,",
+			  "mem",  "-p",  "2", "-t", "16", "-T",  "192", OPT_BW_NOTHP },
+};
+
+static int bench_all(void)
+{
+	int nr = ARRAY_SIZE(tests);
+	int ret;
+	int i;
+
+	ret = system("echo ' #'; echo ' # Running test on: '$(uname -a); echo ' #'");
+	BUG_ON(ret < 0);
+
+	for (i = 0; i < nr; i++) {
+		if (run_bench_numa(tests[i][0], tests[i] + 1))
+			return -1;
+	}
+
+	printf("\n");
+
+	return 0;
+}
+
+int bench_numa(int argc, const char **argv, const char *prefix __maybe_unused)
+{
+	init_params(&p0, "main,", argc, argv);
+	argc = parse_options(argc, argv, options, bench_numa_usage, 0);
+	if (argc)
+		goto err;
+
+	if (p0.run_all)
+		return bench_all();
+
+	if (__bench_numa(NULL))
+		goto err;
+
+	return 0;
+
+err:
+	usage_with_options(numa_usage, options);
+	return -1;
+}
diff --git a/tools/perf/builtin-bench.c b/tools/perf/builtin-bench.c
index afd1255..77298bf 100644
--- a/tools/perf/builtin-bench.c
+++ b/tools/perf/builtin-bench.c
@@ -35,6 +35,18 @@ struct bench_suite {
 /* sentinel: easy for help */
 #define suite_all { "all", "Test all benchmark suites", NULL }
 
+#ifdef LIBNUMA_SUPPORT
+static struct bench_suite numa_suites[] = {
+	{ "mem",
+	  "Benchmark for NUMA workloads",
+	  bench_numa },
+	suite_all,
+	{ NULL,
+	  NULL,
+	  NULL                  }
+};
+#endif
+
 static struct bench_suite sched_suites[] = {
 	{ "messaging",
 	  "Benchmark for scheduler and IPC mechanisms",
@@ -68,6 +80,11 @@ struct bench_subsys {
 };
 
 static struct bench_subsys subsystems[] = {
+#ifdef LIBNUMA_SUPPORT
+	{ "numa",
+	  "NUMA scheduling and MM behavior",
+	  numa_suites },
+#endif
 	{ "sched",
 	  "scheduler and IPC mechanism",
 	  sched_suites },
diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c
index c746108..46878da 100644
--- a/tools/perf/builtin-kmem.c
+++ b/tools/perf/builtin-kmem.c
@@ -17,6 +17,7 @@
 #include "util/debug.h"
 
 #include <linux/rbtree.h>
+#include <linux/string.h>
 
 struct alloc_stat;
 typedef int (*sort_fn_t)(struct alloc_stat *, struct alloc_stat *);
@@ -618,12 +619,11 @@ static int sort_dimension__add(const char *tok, struct list_head *list)
 
 	for (i = 0; i < NUM_AVAIL_SORTS; i++) {
 		if (!strcmp(avail_sorts[i]->name, tok)) {
-			sort = malloc(sizeof(*sort));
+			sort = memdup(avail_sorts[i], sizeof(*avail_sorts[i]));
 			if (!sort) {
-				pr_err("%s: malloc failed\n", __func__);
+				pr_err("%s: memdup failed\n", __func__);
 				return -1;
 			}
-			memcpy(sort, avail_sorts[i], sizeof(*sort));
 			list_add_tail(&sort->list, list);
 			return 0;
 		}
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 1c2ac14..0368a10 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -65,6 +65,10 @@
 #define CNTR_NOT_SUPPORTED	"<not supported>"
 #define CNTR_NOT_COUNTED	"<not counted>"
 
+static void print_stat(int argc, const char **argv);
+static void print_counter_aggr(struct perf_evsel *counter, char *prefix);
+static void print_counter(struct perf_evsel *counter, char *prefix);
+
 static struct perf_evlist	*evsel_list;
 
 static struct perf_target	target = {
@@ -87,6 +91,8 @@ static FILE			*output				= NULL;
 static const char		*pre_cmd			= NULL;
 static const char		*post_cmd			= NULL;
 static bool			sync_run			= false;
+static unsigned int		interval			= 0;
+static struct timespec		ref_time;
 
 static volatile int done = 0;
 
@@ -94,6 +100,28 @@ struct perf_stat {
 	struct stats	  res_stats[3];
 };
 
+static inline void diff_timespec(struct timespec *r, struct timespec *a,
+				 struct timespec *b)
+{
+	r->tv_sec = a->tv_sec - b->tv_sec;
+	if (a->tv_nsec < b->tv_nsec) {
+		r->tv_nsec = a->tv_nsec + 1000000000L - b->tv_nsec;
+		r->tv_sec--;
+	} else {
+		r->tv_nsec = a->tv_nsec - b->tv_nsec ;
+	}
+}
+
+static inline struct cpu_map *perf_evsel__cpus(struct perf_evsel *evsel)
+{
+	return (evsel->cpus && !target.cpu_list) ? evsel->cpus : evsel_list->cpus;
+}
+
+static inline int perf_evsel__nr_cpus(struct perf_evsel *evsel)
+{
+	return perf_evsel__cpus(evsel)->nr;
+}
+
 static int perf_evsel__alloc_stat_priv(struct perf_evsel *evsel)
 {
 	evsel->priv = zalloc(sizeof(struct perf_stat));
@@ -106,14 +134,27 @@ static void perf_evsel__free_stat_priv(struct perf_evsel *evsel)
 	evsel->priv = NULL;
 }
 
-static inline struct cpu_map *perf_evsel__cpus(struct perf_evsel *evsel)
+static int perf_evsel__alloc_prev_raw_counts(struct perf_evsel *evsel)
 {
-	return (evsel->cpus && !target.cpu_list) ? evsel->cpus : evsel_list->cpus;
+	void *addr;
+	size_t sz;
+
+	sz = sizeof(*evsel->counts) +
+	     (perf_evsel__nr_cpus(evsel) * sizeof(struct perf_counts_values));
+
+	addr = zalloc(sz);
+	if (!addr)
+		return -ENOMEM;
+
+	evsel->prev_raw_counts =  addr;
+
+	return 0;
 }
 
-static inline int perf_evsel__nr_cpus(struct perf_evsel *evsel)
+static void perf_evsel__free_prev_raw_counts(struct perf_evsel *evsel)
 {
-	return perf_evsel__cpus(evsel)->nr;
+	free(evsel->prev_raw_counts);
+	evsel->prev_raw_counts = NULL;
 }
 
 static struct stats runtime_nsecs_stats[MAX_NR_CPUS];
@@ -245,16 +286,69 @@ static int read_counter(struct perf_evsel *counter)
 	return 0;
 }
 
+static void print_interval(void)
+{
+	static int num_print_interval;
+	struct perf_evsel *counter;
+	struct perf_stat *ps;
+	struct timespec ts, rs;
+	char prefix[64];
+
+	if (no_aggr) {
+		list_for_each_entry(counter, &evsel_list->entries, node) {
+			ps = counter->priv;
+			memset(ps->res_stats, 0, sizeof(ps->res_stats));
+			read_counter(counter);
+		}
+	} else {
+		list_for_each_entry(counter, &evsel_list->entries, node) {
+			ps = counter->priv;
+			memset(ps->res_stats, 0, sizeof(ps->res_stats));
+			read_counter_aggr(counter);
+		}
+	}
+	clock_gettime(CLOCK_MONOTONIC, &ts);
+	diff_timespec(&rs, &ts, &ref_time);
+	sprintf(prefix, "%6lu.%09lu%s", rs.tv_sec, rs.tv_nsec, csv_sep);
+
+	if (num_print_interval == 0 && !csv_output) {
+		if (no_aggr)
+			fprintf(output, "#           time CPU                 counts events\n");
+		else
+			fprintf(output, "#           time             counts events\n");
+	}
+
+	if (++num_print_interval == 25)
+		num_print_interval = 0;
+
+	if (no_aggr) {
+		list_for_each_entry(counter, &evsel_list->entries, node)
+			print_counter(counter, prefix);
+	} else {
+		list_for_each_entry(counter, &evsel_list->entries, node)
+			print_counter_aggr(counter, prefix);
+	}
+}
+
 static int __run_perf_stat(int argc __maybe_unused, const char **argv)
 {
 	char msg[512];
 	unsigned long long t0, t1;
 	struct perf_evsel *counter;
+	struct timespec ts;
 	int status = 0;
 	int child_ready_pipe[2], go_pipe[2];
 	const bool forks = (argc > 0);
 	char buf;
 
+	if (interval) {
+		ts.tv_sec  = interval / 1000;
+		ts.tv_nsec = (interval % 1000) * 1000000;
+	} else {
+		ts.tv_sec  = 1;
+		ts.tv_nsec = 0;
+	}
+
 	if (forks && (pipe(child_ready_pipe) < 0 || pipe(go_pipe) < 0)) {
 		perror("failed to create pipes");
 		return -1;
@@ -347,14 +441,25 @@ static int __run_perf_stat(int argc __maybe_unused, const char **argv)
 	 * Enable counters and exec the command:
 	 */
 	t0 = rdclock();
+	clock_gettime(CLOCK_MONOTONIC, &ref_time);
 
 	if (forks) {
 		close(go_pipe[1]);
+		if (interval) {
+			while (!waitpid(child_pid, &status, WNOHANG)) {
+				nanosleep(&ts, NULL);
+				print_interval();
+			}
+		}
 		wait(&status);
 		if (WIFSIGNALED(status))
 			psignal(WTERMSIG(status), argv[0]);
 	} else {
-		while(!done) sleep(1);
+		while (!done) {
+			nanosleep(&ts, NULL);
+			if (interval)
+				print_interval();
+		}
 	}
 
 	t1 = rdclock();
@@ -440,7 +545,7 @@ static void nsec_printout(int cpu, struct perf_evsel *evsel, double avg)
 	if (evsel->cgrp)
 		fprintf(output, "%s%s", csv_sep, evsel->cgrp->name);
 
-	if (csv_output)
+	if (csv_output || interval)
 		return;
 
 	if (perf_evsel__match(evsel, SOFTWARE, SW_TASK_CLOCK))
@@ -654,12 +759,11 @@ static void abs_printout(int cpu, struct perf_evsel *evsel, double avg)
 	if (evsel->cgrp)
 		fprintf(output, "%s%s", csv_sep, evsel->cgrp->name);
 
-	if (csv_output)
+	if (csv_output || interval)
 		return;
 
 	if (perf_evsel__match(evsel, HARDWARE, HW_INSTRUCTIONS)) {
 		total = avg_stats(&runtime_cycles_stats[cpu]);
-
 		if (total)
 			ratio = avg / total;
 
@@ -753,12 +857,15 @@ static void abs_printout(int cpu, struct perf_evsel *evsel, double avg)
  * Print out the results of a single counter:
  * aggregated counts in system-wide mode
  */
-static void print_counter_aggr(struct perf_evsel *counter)
+static void print_counter_aggr(struct perf_evsel *counter, char *prefix)
 {
 	struct perf_stat *ps = counter->priv;
 	double avg = avg_stats(&ps->res_stats[0]);
 	int scaled = counter->counts->scaled;
 
+	if (prefix)
+		fprintf(output, "%s", prefix);
+
 	if (scaled == -1) {
 		fprintf(output, "%*s%s%*s",
 			csv_output ? 0 : 18,
@@ -801,7 +908,7 @@ static void print_counter_aggr(struct perf_evsel *counter)
  * Print out the results of a single counter:
  * does not use aggregated count in system-wide
  */
-static void print_counter(struct perf_evsel *counter)
+static void print_counter(struct perf_evsel *counter, char *prefix)
 {
 	u64 ena, run, val;
 	int cpu;
@@ -810,6 +917,10 @@ static void print_counter(struct perf_evsel *counter)
 		val = counter->counts->cpu[cpu].val;
 		ena = counter->counts->cpu[cpu].ena;
 		run = counter->counts->cpu[cpu].run;
+
+		if (prefix)
+			fprintf(output, "%s", prefix);
+
 		if (run == 0 || ena == 0) {
 			fprintf(output, "CPU%*d%s%*s%s%*s",
 				csv_output ? 0 : -4,
@@ -871,10 +982,10 @@ static void print_stat(int argc, const char **argv)
 
 	if (no_aggr) {
 		list_for_each_entry(counter, &evsel_list->entries, node)
-			print_counter(counter);
+			print_counter(counter, NULL);
 	} else {
 		list_for_each_entry(counter, &evsel_list->entries, node)
-			print_counter_aggr(counter);
+			print_counter_aggr(counter, NULL);
 	}
 
 	if (!csv_output) {
@@ -895,7 +1006,7 @@ static volatile int signr = -1;
 
 static void skip_signal(int signo)
 {
-	if(child_pid == -1)
+	if ((child_pid == -1) || interval)
 		done = 1;
 
 	signr = signo;
@@ -1115,6 +1226,8 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused)
 			"command to run prior to the measured command"),
 	OPT_STRING(0, "post", &post_cmd, "command",
 			"command to run after to the measured command"),
+	OPT_UINTEGER('I', "interval-print", &interval,
+		    "print counts at regular interval in ms (>= 100)"),
 	OPT_END()
 	};
 	const char * const stat_usage[] = {
@@ -1215,12 +1328,23 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused)
 		usage_with_options(stat_usage, options);
 		return -1;
 	}
+	if (interval && interval < 100) {
+		pr_err("print interval must be >= 100ms\n");
+		usage_with_options(stat_usage, options);
+		return -1;
+	}
 
 	list_for_each_entry(pos, &evsel_list->entries, node) {
 		if (perf_evsel__alloc_stat_priv(pos) < 0 ||
 		    perf_evsel__alloc_counts(pos, perf_evsel__nr_cpus(pos)) < 0)
 			goto out_free_fd;
 	}
+	if (interval) {
+		list_for_each_entry(pos, &evsel_list->entries, node) {
+			if (perf_evsel__alloc_prev_raw_counts(pos) < 0)
+				goto out_free_fd;
+		}
+	}
 
 	/*
 	 * We dont want to block the signals - that would cause
@@ -1230,6 +1354,7 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused)
 	 */
 	atexit(sig_atexit);
 	signal(SIGINT,  skip_signal);
+	signal(SIGCHLD, skip_signal);
 	signal(SIGALRM, skip_signal);
 	signal(SIGABRT, skip_signal);
 
@@ -1242,11 +1367,14 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused)
 		status = run_perf_stat(argc, argv);
 	}
 
-	if (status != -1)
+	if (status != -1 && !interval)
 		print_stat(argc, argv);
 out_free_fd:
-	list_for_each_entry(pos, &evsel_list->entries, node)
+	list_for_each_entry(pos, &evsel_list->entries, node) {
 		perf_evsel__free_stat_priv(pos);
+		perf_evsel__free_counts(pos);
+		perf_evsel__free_prev_raw_counts(pos);
+	}
 	perf_evlist__delete_maps(evsel_list);
 out:
 	perf_evlist__delete(evsel_list);
diff --git a/tools/perf/config/feature-tests.mak b/tools/perf/config/feature-tests.mak
index f5ac774..b4eabb4 100644
--- a/tools/perf/config/feature-tests.mak
+++ b/tools/perf/config/feature-tests.mak
@@ -225,3 +225,14 @@ int main(void)
 	return on_exit(NULL, NULL);
 }
 endef
+
+define SOURCE_LIBNUMA
+#include <numa.h>
+#include <numaif.h>
+
+int main(void)
+{
+	numa_available();
+	return 0;
+}
+endef
\ No newline at end of file
diff --git a/tools/perf/tests/attr.c b/tools/perf/tests/attr.c
index f61dd3f..bdcceb8 100644
--- a/tools/perf/tests/attr.c
+++ b/tools/perf/tests/attr.c
@@ -19,6 +19,11 @@
  * permissions. All the event text files are stored there.
  */
 
+/*
+ * Powerpc needs __SANE_USERSPACE_TYPES__ before <linux/types.h> to select
+ * 'int-ll64.h' and avoid compile warnings when printing __u64 with %llu.
+ */
+#define __SANE_USERSPACE_TYPES__
 #include <stdlib.h>
 #include <stdio.h>
 #include <inttypes.h>
diff --git a/tools/perf/tests/open-syscall-all-cpus.c b/tools/perf/tests/open-syscall-all-cpus.c
index 9b920a0..b0657a9 100644
--- a/tools/perf/tests/open-syscall-all-cpus.c
+++ b/tools/perf/tests/open-syscall-all-cpus.c
@@ -98,6 +98,7 @@ int test__open_syscall_event_on_all_cpus(void)
 		}
 	}
 
+	perf_evsel__free_counts(evsel);
 out_close_fd:
 	perf_evsel__close_fd(evsel, 1, threads->nr);
 out_evsel_delete:
diff --git a/tools/perf/tests/perf-record.c b/tools/perf/tests/perf-record.c
index 6ea66cf..1e8e512 100644
--- a/tools/perf/tests/perf-record.c
+++ b/tools/perf/tests/perf-record.c
@@ -96,7 +96,7 @@ int test__PERF_RECORD(void)
 	err = perf_evlist__prepare_workload(evlist, &opts, argv);
 	if (err < 0) {
 		pr_debug("Couldn't run the workload!\n");
-		goto out_delete_evlist;
+		goto out_delete_maps;
 	}
 
 	/*
@@ -111,7 +111,7 @@ int test__PERF_RECORD(void)
 	err = sched__get_first_possible_cpu(evlist->workload.pid, &cpu_mask);
 	if (err < 0) {
 		pr_debug("sched__get_first_possible_cpu: %s\n", strerror(errno));
-		goto out_delete_evlist;
+		goto out_delete_maps;
 	}
 
 	cpu = err;
@@ -121,7 +121,7 @@ int test__PERF_RECORD(void)
 	 */
 	if (sched_setaffinity(evlist->workload.pid, cpu_mask_size, &cpu_mask) < 0) {
 		pr_debug("sched_setaffinity: %s\n", strerror(errno));
-		goto out_delete_evlist;
+		goto out_delete_maps;
 	}
 
 	/*
@@ -131,7 +131,7 @@ int test__PERF_RECORD(void)
 	err = perf_evlist__open(evlist);
 	if (err < 0) {
 		pr_debug("perf_evlist__open: %s\n", strerror(errno));
-		goto out_delete_evlist;
+		goto out_delete_maps;
 	}
 
 	/*
@@ -142,7 +142,7 @@ int test__PERF_RECORD(void)
 	err = perf_evlist__mmap(evlist, opts.mmap_pages, false);
 	if (err < 0) {
 		pr_debug("perf_evlist__mmap: %s\n", strerror(errno));
-		goto out_delete_evlist;
+		goto out_delete_maps;
 	}
 
 	/*
@@ -305,6 +305,8 @@ found_exit:
 	}
 out_err:
 	perf_evlist__munmap(evlist);
+out_delete_maps:
+	perf_evlist__delete_maps(evlist);
 out_delete_evlist:
 	perf_evlist__delete(evlist);
 out:
diff --git a/tools/perf/tests/vmlinux-kallsyms.c b/tools/perf/tests/vmlinux-kallsyms.c
index a1a8442..7b4c4d2 100644
--- a/tools/perf/tests/vmlinux-kallsyms.c
+++ b/tools/perf/tests/vmlinux-kallsyms.c
@@ -44,7 +44,7 @@ int test__vmlinux_matches_kallsyms(void)
 	 */
 	if (machine__create_kernel_maps(&kallsyms) < 0) {
 		pr_debug("machine__create_kernel_maps ");
-		return -1;
+		goto out;
 	}
 
 	/*
@@ -227,5 +227,7 @@ detour:
 			map__fprintf(pos, stderr);
 	}
 out:
+	machine__exit(&kallsyms);
+	machine__exit(&vmlinux);
 	return err;
 }
diff --git a/tools/perf/ui/browser.c b/tools/perf/ui/browser.c
index 588bcb2..809ea463 100644
--- a/tools/perf/ui/browser.c
+++ b/tools/perf/ui/browser.c
@@ -273,6 +273,8 @@ void ui_browser__hide(struct ui_browser *browser __maybe_unused)
 {
 	pthread_mutex_lock(&ui__lock);
 	ui_helpline__pop();
+	free(browser->helpline);
+	browser->helpline = NULL;
 	pthread_mutex_unlock(&ui__lock);
 }
 
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index 3cf2c3e..5cd13d7 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -476,8 +476,10 @@ int perf_event__synthesize_kernel_mmap(struct perf_tool *tool,
 		}
 	}
 
-	if (kallsyms__parse(filename, &args, find_symbol_cb) <= 0)
+	if (kallsyms__parse(filename, &args, find_symbol_cb) <= 0) {
+		free(event);
 		return -ENOENT;
+	}
 
 	map = machine->vmlinux_maps[MAP__FUNCTION];
 	size = snprintf(event->mmap.filename, sizeof(event->mmap.filename),
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index e45332d..baa26dd 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -640,6 +640,11 @@ void perf_evsel__close_fd(struct perf_evsel *evsel, int ncpus, int nthreads)
 		}
 }
 
+void perf_evsel__free_counts(struct perf_evsel *evsel)
+{
+	free(evsel->counts);
+}
+
 void perf_evsel__exit(struct perf_evsel *evsel)
 {
 	assert(list_empty(&evsel->node));
@@ -659,6 +664,28 @@ void perf_evsel__delete(struct perf_evsel *evsel)
 	free(evsel);
 }
 
+static inline void compute_deltas(struct perf_evsel *evsel,
+				  int cpu,
+				  struct perf_counts_values *count)
+{
+	struct perf_counts_values tmp;
+
+	if (!evsel->prev_raw_counts)
+		return;
+
+	if (cpu == -1) {
+		tmp = evsel->prev_raw_counts->aggr;
+		evsel->prev_raw_counts->aggr = *count;
+	} else {
+		tmp = evsel->prev_raw_counts->cpu[cpu];
+		evsel->prev_raw_counts->cpu[cpu] = *count;
+	}
+
+	count->val = count->val - tmp.val;
+	count->ena = count->ena - tmp.ena;
+	count->run = count->run - tmp.run;
+}
+
 int __perf_evsel__read_on_cpu(struct perf_evsel *evsel,
 			      int cpu, int thread, bool scale)
 {
@@ -674,6 +701,8 @@ int __perf_evsel__read_on_cpu(struct perf_evsel *evsel,
 	if (readn(FD(evsel, cpu, thread), &count, nv * sizeof(u64)) < 0)
 		return -errno;
 
+	compute_deltas(evsel, cpu, &count);
+
 	if (scale) {
 		if (count.run == 0)
 			count.val = 0;
@@ -712,6 +741,8 @@ int __perf_evsel__read(struct perf_evsel *evsel,
 		}
 	}
 
+	compute_deltas(evsel, -1, aggr);
+
 	evsel->counts->scaled = 0;
 	if (scale) {
 		if (aggr->run == 0) {
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index c68d1b8..cbf4232 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -53,6 +53,7 @@ struct perf_evsel {
 	struct xyarray		*sample_id;
 	u64			*id;
 	struct perf_counts	*counts;
+	struct perf_counts	*prev_raw_counts;
 	int			idx;
 	u32			ids;
 	struct hists		hists;
@@ -116,6 +117,7 @@ int perf_evsel__alloc_id(struct perf_evsel *evsel, int ncpus, int nthreads);
 int perf_evsel__alloc_counts(struct perf_evsel *evsel, int ncpus);
 void perf_evsel__free_fd(struct perf_evsel *evsel);
 void perf_evsel__free_id(struct perf_evsel *evsel);
+void perf_evsel__free_counts(struct perf_evsel *evsel);
 void perf_evsel__close_fd(struct perf_evsel *evsel, int ncpus, int nthreads);
 
 void __perf_evsel__set_sample_bit(struct perf_evsel *evsel,
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index fccd69d..f6081cb 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -313,7 +313,8 @@ int build_id_cache__add_s(const char *sbuild_id, const char *debugdir,
 	if (is_kallsyms) {
 		if (symbol_conf.kptr_restrict) {
 			pr_debug("Not caching a kptr_restrict'ed /proc/kallsyms\n");
-			return 0;
+			err = 0;
+			goto out_free;
 		}
 		realname = (char *) name;
 	} else
@@ -954,6 +955,7 @@ static int write_topo_node(int fd, int node)
 	}
 
 	fclose(fp);
+	fp = NULL;
 
 	ret = do_write(fd, &mem_total, sizeof(u64));
 	if (ret)
@@ -980,7 +982,8 @@ static int write_topo_node(int fd, int node)
 	ret = do_write_string(fd, buf);
 done:
 	free(buf);
-	fclose(fp);
+	if (fp)
+		fclose(fp);
 	return ret;
 }
 
@@ -2921,16 +2924,22 @@ int perf_event__process_tracing_data(union perf_event *event,
 				 session->repipe);
 	padding = PERF_ALIGN(size_read, sizeof(u64)) - size_read;
 
-	if (readn(session->fd, buf, padding) < 0)
-		die("reading input file");
+	if (readn(session->fd, buf, padding) < 0) {
+		pr_err("%s: reading input file", __func__);
+		return -1;
+	}
 	if (session->repipe) {
 		int retw = write(STDOUT_FILENO, buf, padding);
-		if (retw <= 0 || retw != padding)
-			die("repiping tracing data padding");
+		if (retw <= 0 || retw != padding) {
+			pr_err("%s: repiping tracing data padding", __func__);
+			return -1;
+		}
 	}
 
-	if (size_read + padding != size)
-		die("tracing data size mismatch");
+	if (size_read + padding != size) {
+		pr_err("%s: tracing data size mismatch", __func__);
+		return -1;
+	}
 
 	perf_evlist__prepare_tracepoint_events(session->evlist,
 					       session->pevent);
diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c
index ff94425..6fcb9de 100644
--- a/tools/perf/util/map.c
+++ b/tools/perf/util/map.c
@@ -11,6 +11,7 @@
 #include "strlist.h"
 #include "vdso.h"
 #include "build-id.h"
+#include <linux/string.h>
 
 const char *map_type__name[MAP__NR_TYPES] = {
 	[MAP__FUNCTION] = "Functions",
@@ -29,29 +30,29 @@ static inline int is_no_dso_memory(const char *filename)
 	       !strcmp(filename, "[heap]");
 }
 
-void map__init(struct map *self, enum map_type type,
+void map__init(struct map *map, enum map_type type,
 	       u64 start, u64 end, u64 pgoff, struct dso *dso)
 {
-	self->type     = type;
-	self->start    = start;
-	self->end      = end;
-	self->pgoff    = pgoff;
-	self->dso      = dso;
-	self->map_ip   = map__map_ip;
-	self->unmap_ip = map__unmap_ip;
-	RB_CLEAR_NODE(&self->rb_node);
-	self->groups   = NULL;
-	self->referenced = false;
-	self->erange_warned = false;
+	map->type     = type;
+	map->start    = start;
+	map->end      = end;
+	map->pgoff    = pgoff;
+	map->dso      = dso;
+	map->map_ip   = map__map_ip;
+	map->unmap_ip = map__unmap_ip;
+	RB_CLEAR_NODE(&map->rb_node);
+	map->groups   = NULL;
+	map->referenced = false;
+	map->erange_warned = false;
 }
 
 struct map *map__new(struct list_head *dsos__list, u64 start, u64 len,
 		     u64 pgoff, u32 pid, char *filename,
 		     enum map_type type)
 {
-	struct map *self = malloc(sizeof(*self));
+	struct map *map = malloc(sizeof(*map));
 
-	if (self != NULL) {
+	if (map != NULL) {
 		char newfilename[PATH_MAX];
 		struct dso *dso;
 		int anon, no_dso, vdso;
@@ -74,10 +75,10 @@ struct map *map__new(struct list_head *dsos__list, u64 start, u64 len,
 		if (dso == NULL)
 			goto out_delete;
 
-		map__init(self, type, start, start + len, pgoff, dso);
+		map__init(map, type, start, start + len, pgoff, dso);
 
 		if (anon || no_dso) {
-			self->map_ip = self->unmap_ip = identity__map_ip;
+			map->map_ip = map->unmap_ip = identity__map_ip;
 
 			/*
 			 * Set memory without DSO as loaded. All map__find_*
@@ -85,12 +86,12 @@ struct map *map__new(struct list_head *dsos__list, u64 start, u64 len,
 			 * unnecessary map__load warning.
 			 */
 			if (no_dso)
-				dso__set_loaded(dso, self->type);
+				dso__set_loaded(dso, map->type);
 		}
 	}
-	return self;
+	return map;
 out_delete:
-	free(self);
+	free(map);
 	return NULL;
 }
 
@@ -113,48 +114,48 @@ struct map *map__new2(u64 start, struct dso *dso, enum map_type type)
 	return map;
 }
 
-void map__delete(struct map *self)
+void map__delete(struct map *map)
 {
-	free(self);
+	free(map);
 }
 
-void map__fixup_start(struct map *self)
+void map__fixup_start(struct map *map)
 {
-	struct rb_root *symbols = &self->dso->symbols[self->type];
+	struct rb_root *symbols = &map->dso->symbols[map->type];
 	struct rb_node *nd = rb_first(symbols);
 	if (nd != NULL) {
 		struct symbol *sym = rb_entry(nd, struct symbol, rb_node);
-		self->start = sym->start;
+		map->start = sym->start;
 	}
 }
 
-void map__fixup_end(struct map *self)
+void map__fixup_end(struct map *map)
 {
-	struct rb_root *symbols = &self->dso->symbols[self->type];
+	struct rb_root *symbols = &map->dso->symbols[map->type];
 	struct rb_node *nd = rb_last(symbols);
 	if (nd != NULL) {
 		struct symbol *sym = rb_entry(nd, struct symbol, rb_node);
-		self->end = sym->end;
+		map->end = sym->end;
 	}
 }
 
 #define DSO__DELETED "(deleted)"
 
-int map__load(struct map *self, symbol_filter_t filter)
+int map__load(struct map *map, symbol_filter_t filter)
 {
-	const char *name = self->dso->long_name;
+	const char *name = map->dso->long_name;
 	int nr;
 
-	if (dso__loaded(self->dso, self->type))
+	if (dso__loaded(map->dso, map->type))
 		return 0;
 
-	nr = dso__load(self->dso, self, filter);
+	nr = dso__load(map->dso, map, filter);
 	if (nr < 0) {
-		if (self->dso->has_build_id) {
+		if (map->dso->has_build_id) {
 			char sbuild_id[BUILD_ID_SIZE * 2 + 1];
 
-			build_id__sprintf(self->dso->build_id,
-					  sizeof(self->dso->build_id),
+			build_id__sprintf(map->dso->build_id,
+					  sizeof(map->dso->build_id),
 					  sbuild_id);
 			pr_warning("%s with build id %s not found",
 				   name, sbuild_id);
@@ -184,43 +185,36 @@ int map__load(struct map *self, symbol_filter_t filter)
 	 * Only applies to the kernel, as its symtabs aren't relative like the
 	 * module ones.
 	 */
-	if (self->dso->kernel)
-		map__reloc_vmlinux(self);
+	if (map->dso->kernel)
+		map__reloc_vmlinux(map);
 
 	return 0;
 }
 
-struct symbol *map__find_symbol(struct map *self, u64 addr,
+struct symbol *map__find_symbol(struct map *map, u64 addr,
 				symbol_filter_t filter)
 {
-	if (map__load(self, filter) < 0)
+	if (map__load(map, filter) < 0)
 		return NULL;
 
-	return dso__find_symbol(self->dso, self->type, addr);
+	return dso__find_symbol(map->dso, map->type, addr);
 }
 
-struct symbol *map__find_symbol_by_name(struct map *self, const char *name,
+struct symbol *map__find_symbol_by_name(struct map *map, const char *name,
 					symbol_filter_t filter)
 {
-	if (map__load(self, filter) < 0)
+	if (map__load(map, filter) < 0)
 		return NULL;
 
-	if (!dso__sorted_by_name(self->dso, self->type))
-		dso__sort_by_name(self->dso, self->type);
+	if (!dso__sorted_by_name(map->dso, map->type))
+		dso__sort_by_name(map->dso, map->type);
 
-	return dso__find_symbol_by_name(self->dso, self->type, name);
+	return dso__find_symbol_by_name(map->dso, map->type, name);
 }
 
-struct map *map__clone(struct map *self)
+struct map *map__clone(struct map *map)
 {
-	struct map *map = malloc(sizeof(*self));
-
-	if (!map)
-		return NULL;
-
-	memcpy(map, self, sizeof(*self));
-
-	return map;
+	return memdup(map, sizeof(*map));
 }
 
 int map__overlap(struct map *l, struct map *r)
@@ -237,10 +231,10 @@ int map__overlap(struct map *l, struct map *r)
 	return 0;
 }
 
-size_t map__fprintf(struct map *self, FILE *fp)
+size_t map__fprintf(struct map *map, FILE *fp)
 {
 	return fprintf(fp, " %" PRIx64 "-%" PRIx64 " %" PRIx64 " %s\n",
-		       self->start, self->end, self->pgoff, self->dso->name);
+		       map->start, map->end, map->pgoff, map->dso->name);
 }
 
 size_t map__fprintf_dsoname(struct map *map, FILE *fp)
@@ -528,9 +522,9 @@ static u64 map__reloc_unmap_ip(struct map *map, u64 ip)
 	return ip - (s64)map->pgoff;
 }
 
-void map__reloc_vmlinux(struct map *self)
+void map__reloc_vmlinux(struct map *map)
 {
-	struct kmap *kmap = map__kmap(self);
+	struct kmap *kmap = map__kmap(map);
 	s64 reloc;
 
 	if (!kmap->ref_reloc_sym || !kmap->ref_reloc_sym->unrelocated_addr)
@@ -542,9 +536,9 @@ void map__reloc_vmlinux(struct map *self)
 	if (!reloc)
 		return;
 
-	self->map_ip   = map__reloc_map_ip;
-	self->unmap_ip = map__reloc_unmap_ip;
-	self->pgoff    = reloc;
+	map->map_ip   = map__reloc_map_ip;
+	map->unmap_ip = map__reloc_unmap_ip;
+	map->pgoff    = reloc;
 }
 
 void maps__insert(struct rb_root *maps, struct map *map)
@@ -567,9 +561,9 @@ void maps__insert(struct rb_root *maps, struct map *map)
 	rb_insert_color(&map->rb_node, maps);
 }
 
-void maps__remove(struct rb_root *self, struct map *map)
+void maps__remove(struct rb_root *maps, struct map *map)
 {
-	rb_erase(&map->rb_node, self);
+	rb_erase(&map->rb_node, maps);
 }
 
 struct map *maps__find(struct rb_root *maps, u64 ip)
diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h
index bcb39e2..a887f2c 100644
--- a/tools/perf/util/map.h
+++ b/tools/perf/util/map.h
@@ -57,9 +57,9 @@ struct map_groups {
 	struct machine	 *machine;
 };
 
-static inline struct kmap *map__kmap(struct map *self)
+static inline struct kmap *map__kmap(struct map *map)
 {
-	return (struct kmap *)(self + 1);
+	return (struct kmap *)(map + 1);
 }
 
 static inline u64 map__map_ip(struct map *map, u64 ip)
@@ -85,27 +85,27 @@ struct symbol;
 
 typedef int (*symbol_filter_t)(struct map *map, struct symbol *sym);
 
-void map__init(struct map *self, enum map_type type,
+void map__init(struct map *map, enum map_type type,
 	       u64 start, u64 end, u64 pgoff, struct dso *dso);
 struct map *map__new(struct list_head *dsos__list, u64 start, u64 len,
 		     u64 pgoff, u32 pid, char *filename,
 		     enum map_type type);
 struct map *map__new2(u64 start, struct dso *dso, enum map_type type);
-void map__delete(struct map *self);
-struct map *map__clone(struct map *self);
+void map__delete(struct map *map);
+struct map *map__clone(struct map *map);
 int map__overlap(struct map *l, struct map *r);
-size_t map__fprintf(struct map *self, FILE *fp);
+size_t map__fprintf(struct map *map, FILE *fp);
 size_t map__fprintf_dsoname(struct map *map, FILE *fp);
 
-int map__load(struct map *self, symbol_filter_t filter);
-struct symbol *map__find_symbol(struct map *self,
+int map__load(struct map *map, symbol_filter_t filter);
+struct symbol *map__find_symbol(struct map *map,
 				u64 addr, symbol_filter_t filter);
-struct symbol *map__find_symbol_by_name(struct map *self, const char *name,
+struct symbol *map__find_symbol_by_name(struct map *map, const char *name,
 					symbol_filter_t filter);
-void map__fixup_start(struct map *self);
-void map__fixup_end(struct map *self);
+void map__fixup_start(struct map *map);
+void map__fixup_end(struct map *map);
 
-void map__reloc_vmlinux(struct map *self);
+void map__reloc_vmlinux(struct map *map);
 
 size_t __map_groups__fprintf_maps(struct map_groups *mg,
 				  enum map_type type, int verbose, FILE *fp);
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index 7ad6239..8333661 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -249,7 +249,7 @@ static int hist_entry__srcline_snprintf(struct hist_entry *self, char *bf,
 					size_t size,
 					unsigned int width __maybe_unused)
 {
-	FILE *fp;
+	FILE *fp = NULL;
 	char cmd[PATH_MAX + 2], *path = self->srcline, *nl;
 	size_t line_len;
 
@@ -270,7 +270,6 @@ static int hist_entry__srcline_snprintf(struct hist_entry *self, char *bf,
 
 	if (getline(&path, &line_len, fp) < 0 || !line_len)
 		goto out_ip;
-	fclose(fp);
 	self->srcline = strdup(path);
 	if (self->srcline == NULL)
 		goto out_ip;
@@ -280,8 +279,12 @@ static int hist_entry__srcline_snprintf(struct hist_entry *self, char *bf,
 		*nl = '\0';
 	path = self->srcline;
 out_path:
+	if (fp)
+		pclose(fp);
 	return repsep_snprintf(bf, size, "%s", path);
 out_ip:
+	if (fp)
+		pclose(fp);
 	return repsep_snprintf(bf, size, "%-#*llx", BITS_PER_LONG / 4, self->ip);
 }
 
diff --git a/tools/perf/util/strlist.c b/tools/perf/util/strlist.c
index 155d8b7..55433aa4 100644
--- a/tools/perf/util/strlist.c
+++ b/tools/perf/util/strlist.c
@@ -35,11 +35,11 @@ out_delete:
 	return NULL;
 }
 
-static void str_node__delete(struct str_node *self, bool dupstr)
+static void str_node__delete(struct str_node *snode, bool dupstr)
 {
 	if (dupstr)
-		free((void *)self->s);
-	free(self);
+		free((void *)snode->s);
+	free(snode);
 }
 
 static
@@ -59,12 +59,12 @@ static int strlist__node_cmp(struct rb_node *rb_node, const void *entry)
 	return strcmp(snode->s, str);
 }
 
-int strlist__add(struct strlist *self, const char *new_entry)
+int strlist__add(struct strlist *slist, const char *new_entry)
 {
-	return rblist__add_node(&self->rblist, new_entry);
+	return rblist__add_node(&slist->rblist, new_entry);
 }
 
-int strlist__load(struct strlist *self, const char *filename)
+int strlist__load(struct strlist *slist, const char *filename)
 {
 	char entry[1024];
 	int err;
@@ -80,7 +80,7 @@ int strlist__load(struct strlist *self, const char *filename)
 			continue;
 		entry[len - 1] = '\0';
 
-		err = strlist__add(self, entry);
+		err = strlist__add(slist, entry);
 		if (err != 0)
 			goto out;
 	}
@@ -107,56 +107,56 @@ struct str_node *strlist__find(struct strlist *slist, const char *entry)
 	return snode;
 }
 
-static int strlist__parse_list_entry(struct strlist *self, const char *s)
+static int strlist__parse_list_entry(struct strlist *slist, const char *s)
 {
 	if (strncmp(s, "file://", 7) == 0)
-		return strlist__load(self, s + 7);
+		return strlist__load(slist, s + 7);
 
-	return strlist__add(self, s);
+	return strlist__add(slist, s);
 }
 
-int strlist__parse_list(struct strlist *self, const char *s)
+int strlist__parse_list(struct strlist *slist, const char *s)
 {
 	char *sep;
 	int err;
 
 	while ((sep = strchr(s, ',')) != NULL) {
 		*sep = '\0';
-		err = strlist__parse_list_entry(self, s);
+		err = strlist__parse_list_entry(slist, s);
 		*sep = ',';
 		if (err != 0)
 			return err;
 		s = sep + 1;
 	}
 
-	return *s ? strlist__parse_list_entry(self, s) : 0;
+	return *s ? strlist__parse_list_entry(slist, s) : 0;
 }
 
-struct strlist *strlist__new(bool dupstr, const char *slist)
+struct strlist *strlist__new(bool dupstr, const char *list)
 {
-	struct strlist *self = malloc(sizeof(*self));
+	struct strlist *slist = malloc(sizeof(*slist));
 
-	if (self != NULL) {
-		rblist__init(&self->rblist);
-		self->rblist.node_cmp    = strlist__node_cmp;
-		self->rblist.node_new    = strlist__node_new;
-		self->rblist.node_delete = strlist__node_delete;
+	if (slist != NULL) {
+		rblist__init(&slist->rblist);
+		slist->rblist.node_cmp    = strlist__node_cmp;
+		slist->rblist.node_new    = strlist__node_new;
+		slist->rblist.node_delete = strlist__node_delete;
 
-		self->dupstr	 = dupstr;
-		if (slist && strlist__parse_list(self, slist) != 0)
+		slist->dupstr	 = dupstr;
+		if (slist && strlist__parse_list(slist, list) != 0)
 			goto out_error;
 	}
 
-	return self;
+	return slist;
 out_error:
-	free(self);
+	free(slist);
 	return NULL;
 }
 
-void strlist__delete(struct strlist *self)
+void strlist__delete(struct strlist *slist)
 {
-	if (self != NULL)
-		rblist__delete(&self->rblist);
+	if (slist != NULL)
+		rblist__delete(&slist->rblist);
 }
 
 struct str_node *strlist__entry(const struct strlist *slist, unsigned int idx)
diff --git a/tools/perf/util/strlist.h b/tools/perf/util/strlist.h
index dd9f922..5c7f870 100644
--- a/tools/perf/util/strlist.h
+++ b/tools/perf/util/strlist.h
@@ -17,34 +17,34 @@ struct strlist {
 };
 
 struct strlist *strlist__new(bool dupstr, const char *slist);
-void strlist__delete(struct strlist *self);
+void strlist__delete(struct strlist *slist);
 
-void strlist__remove(struct strlist *self, struct str_node *sn);
-int strlist__load(struct strlist *self, const char *filename);
-int strlist__add(struct strlist *self, const char *str);
+void strlist__remove(struct strlist *slist, struct str_node *sn);
+int strlist__load(struct strlist *slist, const char *filename);
+int strlist__add(struct strlist *slist, const char *str);
 
-struct str_node *strlist__entry(const struct strlist *self, unsigned int idx);
-struct str_node *strlist__find(struct strlist *self, const char *entry);
+struct str_node *strlist__entry(const struct strlist *slist, unsigned int idx);
+struct str_node *strlist__find(struct strlist *slist, const char *entry);
 
-static inline bool strlist__has_entry(struct strlist *self, const char *entry)
+static inline bool strlist__has_entry(struct strlist *slist, const char *entry)
 {
-	return strlist__find(self, entry) != NULL;
+	return strlist__find(slist, entry) != NULL;
 }
 
-static inline bool strlist__empty(const struct strlist *self)
+static inline bool strlist__empty(const struct strlist *slist)
 {
-	return rblist__empty(&self->rblist);
+	return rblist__empty(&slist->rblist);
 }
 
-static inline unsigned int strlist__nr_entries(const struct strlist *self)
+static inline unsigned int strlist__nr_entries(const struct strlist *slist)
 {
-	return rblist__nr_entries(&self->rblist);
+	return rblist__nr_entries(&slist->rblist);
 }
 
 /* For strlist iteration */
-static inline struct str_node *strlist__first(struct strlist *self)
+static inline struct str_node *strlist__first(struct strlist *slist)
 {
-	struct rb_node *rn = rb_first(&self->rblist.entries);
+	struct rb_node *rn = rb_first(&slist->rblist.entries);
 	return rn ? rb_entry(rn, struct str_node, rb_node) : NULL;
 }
 static inline struct str_node *strlist__next(struct str_node *sn)
@@ -59,21 +59,21 @@ static inline struct str_node *strlist__next(struct str_node *sn)
 /**
  * strlist_for_each      - iterate over a strlist
  * @pos:	the &struct str_node to use as a loop cursor.
- * @self:	the &struct strlist for loop.
+ * @slist:	the &struct strlist for loop.
  */
-#define strlist__for_each(pos, self)	\
-	for (pos = strlist__first(self); pos; pos = strlist__next(pos))
+#define strlist__for_each(pos, slist)	\
+	for (pos = strlist__first(slist); pos; pos = strlist__next(pos))
 
 /**
  * strlist_for_each_safe - iterate over a strlist safe against removal of
  *                         str_node
  * @pos:	the &struct str_node to use as a loop cursor.
  * @n:		another &struct str_node to use as temporary storage.
- * @self:	the &struct strlist for loop.
+ * @slist:	the &struct strlist for loop.
  */
-#define strlist__for_each_safe(pos, n, self)	\
-	for (pos = strlist__first(self), n = strlist__next(pos); pos;\
+#define strlist__for_each_safe(pos, n, slist)	\
+	for (pos = strlist__first(slist), n = strlist__next(pos); pos;\
 	     pos = n, n = strlist__next(n))
 
-int strlist__parse_list(struct strlist *self, const char *s);
+int strlist__parse_list(struct strlist *slist, const char *s);
 #endif /* __PERF_STRLIST_H */