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:

Infrastructure changes:

 o More prep work to support Intel PT: (Adrian Hunter)
   - Polishing 'script' BTS output
   - 'inject' can specify --kallsym
   - VDSO is per machine, not a global var
   - Expose data addr lookup functions previously private to 'script'
   - Large mmap fixes in events processing

 o Fix build on gcc 4.4.7 (Arnaldo Carvalho de Melo)

 o Event ordering fixes (Jiri Olsa)

 o Include standard stringify macros in power pc code (Sukadev Bhattiprolu)

Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>

29 files changed, 470 insertions, 115 deletions

diff --git a/tools/perf/Documentation/perf-inject.txt b/tools/perf/Documentation/perf-inject.txt
index a00a34276c5..dc7442cf3d7 100644
--- a/tools/perf/Documentation/perf-inject.txt
+++ b/tools/perf/Documentation/perf-inject.txt
@@ -41,6 +41,9 @@ OPTIONS
 	tasks slept. sched_switch contains a callchain where a task slept and
 	sched_stat contains a timeslice how long a task slept.
 
+--kallsyms=<file>::
+	kallsyms pathname
+
 SEE ALSO
 --------
 linkperf:perf-record[1], linkperf:perf-report[1], linkperf:perf-archive[1]
diff --git a/tools/perf/arch/powerpc/util/header.c b/tools/perf/arch/powerpc/util/header.c
index 2f7073d107f..6c1b8a75db0 100644
--- a/tools/perf/arch/powerpc/util/header.c
+++ b/tools/perf/arch/powerpc/util/header.c
@@ -5,9 +5,7 @@
 #include <string.h>
 
 #include "../../util/header.h"
-
-#define __stringify_1(x)        #x
-#define __stringify(x)          __stringify_1(x)
+#include "../../util/util.h"
 
 #define mfspr(rn)       ({unsigned long rval; \
 			 asm volatile("mfspr %0," __stringify(rn) \
diff --git a/tools/perf/arch/x86/util/tsc.c b/tools/perf/arch/x86/util/tsc.c
index 3655f24c317..fd2868490d0 100644
--- a/tools/perf/arch/x86/util/tsc.c
+++ b/tools/perf/arch/x86/util/tsc.c
@@ -37,3 +37,12 @@ int perf_read_tsc_conversion(const struct perf_event_mmap_page *pc,
 
 	return 0;
 }
+
+u64 rdtsc(void)
+{
+	unsigned int low, high;
+
+	asm volatile("rdtsc" : "=a" (low), "=d" (high));
+
+	return low | ((u64)high) << 32;
+}
diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c
index cf6a605a13e..9a02807387d 100644
--- a/tools/perf/builtin-inject.c
+++ b/tools/perf/builtin-inject.c
@@ -439,6 +439,8 @@ int cmd_inject(int argc, const char **argv, const char *prefix __maybe_unused)
 			    "where and how long tasks slept"),
 		OPT_INCR('v', "verbose", &verbose,
 			 "be more verbose (show build ids, etc)"),
+		OPT_STRING(0, "kallsyms", &symbol_conf.kallsyms_name, "file",
+			   "kallsyms pathname"),
 		OPT_END()
 	};
 	const char * const inject_usage[] = {
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 378b85b731a..4869050e719 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -238,6 +238,7 @@ static struct perf_event_header finished_round_event = {
 
 static int record__mmap_read_all(struct record *rec)
 {
+	u64 bytes_written = rec->bytes_written;
 	int i;
 	int rc = 0;
 
@@ -250,7 +251,11 @@ static int record__mmap_read_all(struct record *rec)
 		}
 	}
 
-	if (perf_header__has_feat(&rec->session->header, HEADER_TRACING_DATA))
+	/*
+	 * Mark the round finished in case we wrote
+	 * at least one event.
+	 */
+	if (bytes_written != rec->bytes_written)
 		rc = record__write(rec, &finished_round_event, sizeof(finished_round_event));
 
 out:
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 9e9c91f5b7f..f57035b89c1 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -358,27 +358,6 @@ static void print_sample_start(struct perf_sample *sample,
 	}
 }
 
-static bool is_bts_event(struct perf_event_attr *attr)
-{
-	return ((attr->type == PERF_TYPE_HARDWARE) &&
-		(attr->config & PERF_COUNT_HW_BRANCH_INSTRUCTIONS) &&
-		(attr->sample_period == 1));
-}
-
-static bool sample_addr_correlates_sym(struct perf_event_attr *attr)
-{
-	if ((attr->type == PERF_TYPE_SOFTWARE) &&
-	    ((attr->config == PERF_COUNT_SW_PAGE_FAULTS) ||
-	     (attr->config == PERF_COUNT_SW_PAGE_FAULTS_MIN) ||
-	     (attr->config == PERF_COUNT_SW_PAGE_FAULTS_MAJ)))
-		return true;
-
-	if (is_bts_event(attr))
-		return true;
-
-	return false;
-}
-
 static void print_sample_addr(union perf_event *event,
 			  struct perf_sample *sample,
 			  struct machine *machine,
@@ -386,24 +365,13 @@ static void print_sample_addr(union perf_event *event,
 			  struct perf_event_attr *attr)
 {
 	struct addr_location al;
-	u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
 
 	printf("%16" PRIx64, sample->addr);
 
 	if (!sample_addr_correlates_sym(attr))
 		return;
 
-	thread__find_addr_map(thread, machine, cpumode, MAP__FUNCTION,
-			      sample->addr, &al);
-	if (!al.map)
-		thread__find_addr_map(thread, machine, cpumode, MAP__VARIABLE,
-				      sample->addr, &al);
-
-	al.cpu = sample->cpu;
-	al.sym = NULL;
-
-	if (al.map)
-		al.sym = map__find_symbol(al.map, al.addr, NULL);
+	perf_event__preprocess_sample_addr(event, sample, machine, thread, &al);
 
 	if (PRINT_FIELD(SYM)) {
 		printf(" ");
@@ -427,25 +395,35 @@ static void print_sample_bts(union perf_event *event,
 			     struct addr_location *al)
 {
 	struct perf_event_attr *attr = &evsel->attr;
+	bool print_srcline_last = false;
 
 	/* print branch_from information */
 	if (PRINT_FIELD(IP)) {
-		if (!symbol_conf.use_callchain)
-			printf(" ");
-		else
+		unsigned int print_opts = output[attr->type].print_ip_opts;
+
+		if (symbol_conf.use_callchain && sample->callchain) {
 			printf("\n");
-		perf_evsel__print_ip(evsel, sample, al,
-				     output[attr->type].print_ip_opts,
+		} else {
+			printf(" ");
+			if (print_opts & PRINT_IP_OPT_SRCLINE) {
+				print_srcline_last = true;
+				print_opts &= ~PRINT_IP_OPT_SRCLINE;
+			}
+		}
+		perf_evsel__print_ip(evsel, sample, al, print_opts,
 				     PERF_MAX_STACK_DEPTH);
 	}
 
-	printf(" => ");
-
 	/* print branch_to information */
 	if (PRINT_FIELD(ADDR) ||
 	    ((evsel->attr.sample_type & PERF_SAMPLE_ADDR) &&
-	     !output[attr->type].user_set))
+	     !output[attr->type].user_set)) {
+		printf(" => ");
 		print_sample_addr(event, sample, al->machine, thread, attr);
+	}
+
+	if (print_srcline_last)
+		map__fprintf_srcline(al->map, al->addr, "\n  ", stdout);
 
 	printf("\n");
 }
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index c4a5a7d7b2c..a6c375224f4 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -1994,10 +1994,10 @@ static int perf_evlist__add_pgfault(struct perf_evlist *evlist,
 	struct perf_event_attr attr = {
 		.type = PERF_TYPE_SOFTWARE,
 		.mmap_data = 1,
-		.sample_period = 1,
 	};
 
 	attr.config = config;
+	attr.sample_period = 1;
 
 	event_attr_init(&attr);
 
diff --git a/tools/perf/tests/perf-time-to-tsc.c b/tools/perf/tests/perf-time-to-tsc.c
index 0372f6edca2..f238442b238 100644
--- a/tools/perf/tests/perf-time-to-tsc.c
+++ b/tools/perf/tests/perf-time-to-tsc.c
@@ -25,15 +25,6 @@
 	}					\
 }
 
-static u64 rdtsc(void)
-{
-	unsigned int low, high;
-
-	asm volatile("rdtsc" : "=a" (low), "=d" (high));
-
-	return low | ((u64)high) << 32;
-}
-
 /**
  * test__perf_time_to_tsc - test converting perf time to TSC.
  *
diff --git a/tools/perf/util/cloexec.c b/tools/perf/util/cloexec.c
index c5d05ec1722..6a37be53a5d 100644
--- a/tools/perf/util/cloexec.c
+++ b/tools/perf/util/cloexec.c
@@ -1,3 +1,4 @@
+#include <sched.h>
 #include "util.h"
 #include "../perf.h"
 #include "cloexec.h"
@@ -14,9 +15,13 @@ static int perf_flag_probe(void)
 	};
 	int fd;
 	int err;
+	int cpu = sched_getcpu();
+
+	if (cpu < 0)
+		cpu = 0;
 
 	/* check cloexec flag */
-	fd = sys_perf_event_open(&attr, 0, -1, -1,
+	fd = sys_perf_event_open(&attr, -1, cpu, -1,
 				 PERF_FLAG_FD_CLOEXEC);
 	err = errno;
 
@@ -30,7 +35,7 @@ static int perf_flag_probe(void)
 		  err, strerror(err));
 
 	/* not supported, confirm error related to PERF_FLAG_FD_CLOEXEC */
-	fd = sys_perf_event_open(&attr, 0, -1, -1, 0);
+	fd = sys_perf_event_open(&attr, -1, cpu, -1, 0);
 	err = errno;
 
 	if (WARN_ONCE(fd < 0,
diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c
index fc006fed887..90d02c661dd 100644
--- a/tools/perf/util/dso.c
+++ b/tools/perf/util/dso.c
@@ -216,7 +216,7 @@ static int open_dso(struct dso *dso, struct machine *machine)
 {
 	int fd = __open_dso(dso, machine);
 
-	if (fd > 0) {
+	if (fd >= 0) {
 		dso__list_add(dso);
 		/*
 		 * Check if we crossed the allowed number
@@ -331,26 +331,44 @@ int dso__data_fd(struct dso *dso, struct machine *machine)
 	};
 	int i = 0;
 
+	if (dso->data.status == DSO_DATA_STATUS_ERROR)
+		return -1;
+
 	if (dso->data.fd >= 0)
-		return dso->data.fd;
+		goto out;
 
 	if (dso->binary_type != DSO_BINARY_TYPE__NOT_FOUND) {
 		dso->data.fd = open_dso(dso, machine);
-		return dso->data.fd;
+		goto out;
 	}
 
 	do {
-		int fd;
-
 		dso->binary_type = binary_type_data[i++];
 
-		fd = open_dso(dso, machine);
-		if (fd >= 0)
-			return dso->data.fd = fd;
+		dso->data.fd = open_dso(dso, machine);
+		if (dso->data.fd >= 0)
+			goto out;
 
 	} while (dso->binary_type != DSO_BINARY_TYPE__NOT_FOUND);
+out:
+	if (dso->data.fd >= 0)
+		dso->data.status = DSO_DATA_STATUS_OK;
+	else
+		dso->data.status = DSO_DATA_STATUS_ERROR;
 
-	return -EINVAL;
+	return dso->data.fd;
+}
+
+bool dso__data_status_seen(struct dso *dso, enum dso_data_status_seen by)
+{
+	u32 flag = 1 << by;
+
+	if (dso->data.status_seen & flag)
+		return true;
+
+	dso->data.status_seen |= flag;
+
+	return false;
 }
 
 static void
@@ -526,6 +544,28 @@ static int data_file_size(struct dso *dso)
 	return 0;
 }
 
+/**
+ * dso__data_size - Return dso data size
+ * @dso: dso object
+ * @machine: machine object
+ *
+ * Return: dso data size
+ */
+off_t dso__data_size(struct dso *dso, struct machine *machine)
+{
+	int fd;
+
+	fd = dso__data_fd(dso, machine);
+	if (fd < 0)
+		return fd;
+
+	if (data_file_size(dso))
+		return -1;
+
+	/* For now just estimate dso data size is close to file size */
+	return dso->data.file_size;
+}
+
 static ssize_t data_read_offset(struct dso *dso, u64 offset,
 				u8 *data, ssize_t size)
 {
@@ -701,6 +741,7 @@ struct dso *dso__new(const char *name)
 			dso->symbols[i] = dso->symbol_names[i] = RB_ROOT;
 		dso->data.cache = RB_ROOT;
 		dso->data.fd = -1;
+		dso->data.status = DSO_DATA_STATUS_UNKNOWN;
 		dso->symtab_type = DSO_BINARY_TYPE__NOT_FOUND;
 		dso->binary_type = DSO_BINARY_TYPE__NOT_FOUND;
 		dso->is_64_bit = (sizeof(void *) == 8);
@@ -899,3 +940,14 @@ size_t dso__fprintf(struct dso *dso, enum map_type type, FILE *fp)
 
 	return ret;
 }
+
+enum dso_type dso__type(struct dso *dso, struct machine *machine)
+{
+	int fd;
+
+	fd = dso__data_fd(dso, machine);
+	if (fd < 0)
+		return DSO__TYPE_UNKNOWN;
+
+	return dso__type_fd(fd);
+}
diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h
index c239e86541a..5e463c0964d 100644
--- a/tools/perf/util/dso.h
+++ b/tools/perf/util/dso.h
@@ -5,6 +5,7 @@
 #include <linux/rbtree.h>
 #include <stdbool.h>
 #include <linux/types.h>
+#include <linux/bitops.h>
 #include "map.h"
 #include "build-id.h"
 
@@ -40,6 +41,23 @@ enum dso_swap_type {
 	DSO_SWAP__YES,
 };
 
+enum dso_data_status {
+	DSO_DATA_STATUS_ERROR	= -1,
+	DSO_DATA_STATUS_UNKNOWN	= 0,
+	DSO_DATA_STATUS_OK	= 1,
+};
+
+enum dso_data_status_seen {
+	DSO_DATA_STATUS_SEEN_ITRACE,
+};
+
+enum dso_type {
+	DSO__TYPE_UNKNOWN,
+	DSO__TYPE_64BIT,
+	DSO__TYPE_32BIT,
+	DSO__TYPE_X32BIT,
+};
+
 #define DSO__SWAP(dso, type, val)			\
 ({							\
 	type ____r = val;				\
@@ -104,6 +122,8 @@ struct dso {
 	struct {
 		struct rb_root	 cache;
 		int		 fd;
+		int		 status;
+		u32		 status_seen;
 		size_t		 file_size;
 		struct list_head open_entry;
 	} data;
@@ -154,6 +174,7 @@ int dso__read_binary_type_filename(const struct dso *dso, enum dso_binary_type t
  * The dso__data_* external interface provides following functions:
  *   dso__data_fd
  *   dso__data_close
+ *   dso__data_size
  *   dso__data_read_offset
  *   dso__data_read_addr
  *
@@ -191,11 +212,13 @@ int dso__read_binary_type_filename(const struct dso *dso, enum dso_binary_type t
 int dso__data_fd(struct dso *dso, struct machine *machine);
 void dso__data_close(struct dso *dso);
 
+off_t dso__data_size(struct dso *dso, struct machine *machine);
 ssize_t dso__data_read_offset(struct dso *dso, struct machine *machine,
 			      u64 offset, u8 *data, ssize_t size);
 ssize_t dso__data_read_addr(struct dso *dso, struct map *map,
 			    struct machine *machine, u64 addr,
 			    u8 *data, ssize_t size);
+bool dso__data_status_seen(struct dso *dso, enum dso_data_status_seen by);
 
 struct map *dso__new_map(const char *name);
 struct dso *dso__kernel_findnew(struct machine *machine, const char *name,
@@ -230,4 +253,6 @@ static inline bool dso__is_kcore(struct dso *dso)
 
 void dso__free_a2l(struct dso *dso);
 
+enum dso_type dso__type(struct dso *dso, struct machine *machine);
+
 #endif /* __PERF_DSO */
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index 7e0e8ae568e..1398c83d896 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -874,3 +874,45 @@ int perf_event__preprocess_sample(const union perf_event *event,
 
 	return 0;
 }
+
+bool is_bts_event(struct perf_event_attr *attr)
+{
+	return attr->type == PERF_TYPE_HARDWARE &&
+	       (attr->config & PERF_COUNT_HW_BRANCH_INSTRUCTIONS) &&
+	       attr->sample_period == 1;
+}
+
+bool sample_addr_correlates_sym(struct perf_event_attr *attr)
+{
+	if (attr->type == PERF_TYPE_SOFTWARE &&
+	    (attr->config == PERF_COUNT_SW_PAGE_FAULTS ||
+	     attr->config == PERF_COUNT_SW_PAGE_FAULTS_MIN ||
+	     attr->config == PERF_COUNT_SW_PAGE_FAULTS_MAJ))
+		return true;
+
+	if (is_bts_event(attr))
+		return true;
+
+	return false;
+}
+
+void perf_event__preprocess_sample_addr(union perf_event *event,
+					struct perf_sample *sample,
+					struct machine *machine,
+					struct thread *thread,
+					struct addr_location *al)
+{
+	u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
+
+	thread__find_addr_map(thread, machine, cpumode, MAP__FUNCTION,
+			      sample->addr, al);
+	if (!al->map)
+		thread__find_addr_map(thread, machine, cpumode, MAP__VARIABLE,
+				      sample->addr, al);
+
+	al->cpu = sample->cpu;
+	al->sym = NULL;
+
+	if (al->map)
+		al->sym = map__find_symbol(al->map, al->addr, NULL);
+}
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index e5dd40addb3..94d6976180d 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -288,6 +288,16 @@ int perf_event__preprocess_sample(const union perf_event *event,
 				  struct addr_location *al,
 				  struct perf_sample *sample);
 
+struct thread;
+
+bool is_bts_event(struct perf_event_attr *attr);
+bool sample_addr_correlates_sym(struct perf_event_attr *attr);
+void perf_event__preprocess_sample_addr(union perf_event *event,
+					struct perf_sample *sample,
+					struct machine *machine,
+					struct thread *thread,
+					struct addr_location *al);
+
 const char *perf_event__name(unsigned int id);
 
 size_t perf_event__sample_event_size(const struct perf_sample *sample, u64 type,
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 893f8e2df92..158c787ce0c 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -200,6 +200,47 @@ static int write_buildid(const char *name, size_t name_len, u8 *build_id,
 	return write_padded(fd, name, name_len + 1, len);
 }
 
+static int __dsos__hit_all(struct list_head *head)
+{
+	struct dso *pos;
+
+	list_for_each_entry(pos, head, node)
+		pos->hit = true;
+
+	return 0;
+}
+
+static int machine__hit_all_dsos(struct machine *machine)
+{
+	int err;
+
+	err = __dsos__hit_all(&machine->kernel_dsos);
+	if (err)
+		return err;
+
+	return __dsos__hit_all(&machine->user_dsos);
+}
+
+int dsos__hit_all(struct perf_session *session)
+{
+	struct rb_node *nd;
+	int err;
+
+	err = machine__hit_all_dsos(&session->machines.host);
+	if (err)
+		return err;
+
+	for (nd = rb_first(&session->machines.guests); nd; nd = rb_next(nd)) {
+		struct machine *pos = rb_entry(nd, struct machine, rb_node);
+
+		err = machine__hit_all_dsos(pos);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
 static int __dsos__write_buildid_table(struct list_head *head,
 				       struct machine *machine,
 				       pid_t pid, u16 misc, int fd)
@@ -215,9 +256,9 @@ static int __dsos__write_buildid_table(struct list_head *head,
 		if (!pos->hit)
 			continue;
 
-		if (is_vdso_map(pos->short_name)) {
-			name = (char *) VDSO__MAP_NAME;
-			name_len = sizeof(VDSO__MAP_NAME) + 1;
+		if (dso__is_vdso(pos)) {
+			name = pos->short_name;
+			name_len = pos->short_name_len + 1;
 		} else if (dso__is_kcore(pos)) {
 			machine__mmap_name(machine, nm, sizeof(nm));
 			name = nm;
@@ -298,7 +339,7 @@ int build_id_cache__add_s(const char *sbuild_id, const char *debugdir,
 
 	len = scnprintf(filename, size, "%s%s%s",
 		       debugdir, slash ? "/" : "",
-		       is_vdso ? VDSO__MAP_NAME : realname);
+		       is_vdso ? DSO__NAME_VDSO : realname);
 	if (mkdir_p(filename, 0755))
 		goto out_free;
 
@@ -386,7 +427,7 @@ static int dso__cache_build_id(struct dso *dso, struct machine *machine,
 			       const char *debugdir)
 {
 	bool is_kallsyms = dso->kernel && dso->long_name[0] != '/';
-	bool is_vdso = is_vdso_map(dso->short_name);
+	bool is_vdso = dso__is_vdso(dso);
 	const char *name = dso->long_name;
 	char nm[PATH_MAX];
 
diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h
index d08cfe49940..8f5cbaea64a 100644
--- a/tools/perf/util/header.h
+++ b/tools/perf/util/header.h
@@ -151,6 +151,8 @@ int perf_event__process_build_id(struct perf_tool *tool,
 				 struct perf_session *session);
 bool is_perf_magic(u64 magic);
 
+int dsos__hit_all(struct perf_session *session);
+
 /*
  * arch specific callback
  */
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 93c8b6fbc79..16bba9fff2c 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -8,6 +8,7 @@
 #include "sort.h"
 #include "strlist.h"
 #include "thread.h"
+#include "vdso.h"
 #include <stdbool.h>
 #include <symbol/kallsyms.h>
 #include "unwind.h"
@@ -23,6 +24,8 @@ int machine__init(struct machine *machine, const char *root_dir, pid_t pid)
 	INIT_LIST_HEAD(&machine->dead_threads);
 	machine->last_match = NULL;
 
+	machine->vdso_info = NULL;
+
 	machine->kmaps.machine = machine;
 	machine->pid = pid;
 
@@ -45,6 +48,8 @@ int machine__init(struct machine *machine, const char *root_dir, pid_t pid)
 		thread__set_comm(thread, comm, 0);
 	}
 
+	machine->current_tid = NULL;
+
 	return 0;
 }
 
@@ -103,7 +108,9 @@ void machine__exit(struct machine *machine)
 	map_groups__exit(&machine->kmaps);
 	dsos__delete(&machine->user_dsos);
 	dsos__delete(&machine->kernel_dsos);
+	vdso__exit(machine);
 	zfree(&machine->root_dir);
+	zfree(&machine->current_tid);
 }
 
 void machine__delete(struct machine *machine)
@@ -1092,14 +1099,14 @@ int machine__process_mmap2_event(struct machine *machine,
 	else
 		type = MAP__FUNCTION;
 
-	map = map__new(&machine->user_dsos, event->mmap2.start,
+	map = map__new(machine, event->mmap2.start,
 			event->mmap2.len, event->mmap2.pgoff,
 			event->mmap2.pid, event->mmap2.maj,
 			event->mmap2.min, event->mmap2.ino,
 			event->mmap2.ino_generation,
 			event->mmap2.prot,
 			event->mmap2.flags,
-			event->mmap2.filename, type);
+			event->mmap2.filename, type, thread);
 
 	if (map == NULL)
 		goto out_problem;
@@ -1142,11 +1149,11 @@ int machine__process_mmap_event(struct machine *machine, union perf_event *event
 	else
 		type = MAP__FUNCTION;
 
-	map = map__new(&machine->user_dsos, event->mmap.start,
+	map = map__new(machine, event->mmap.start,
 			event->mmap.len, event->mmap.pgoff,
 			event->mmap.pid, 0, 0, 0, 0, 0, 0,
 			event->mmap.filename,
-			type);
+			type, thread);
 
 	if (map == NULL)
 		goto out_problem;
@@ -1481,3 +1488,46 @@ int __machine__synthesize_threads(struct machine *machine, struct perf_tool *too
 	/* command specified */
 	return 0;
 }
+
+pid_t machine__get_current_tid(struct machine *machine, int cpu)
+{
+	if (cpu < 0 || cpu >= MAX_NR_CPUS || !machine->current_tid)
+		return -1;
+
+	return machine->current_tid[cpu];
+}
+
+int machine__set_current_tid(struct machine *machine, int cpu, pid_t pid,
+			     pid_t tid)
+{
+	struct thread *thread;
+
+	if (cpu < 0)
+		return -EINVAL;
+
+	if (!machine->current_tid) {
+		int i;
+
+		machine->current_tid = calloc(MAX_NR_CPUS, sizeof(pid_t));
+		if (!machine->current_tid)
+			return -ENOMEM;
+		for (i = 0; i < MAX_NR_CPUS; i++)
+			machine->current_tid[i] = -1;
+	}
+
+	if (cpu >= MAX_NR_CPUS) {
+		pr_err("Requested CPU %d too large. ", cpu);
+		pr_err("Consider raising MAX_NR_CPUS\n");
+		return -EINVAL;
+	}
+
+	machine->current_tid[cpu] = tid;
+
+	thread = machine__findnew_thread(machine, pid, tid);
+	if (!thread)
+		return -ENOMEM;
+
+	thread->cpu = cpu;
+
+	return 0;
+}
diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h
index c8c74a11939..b972824e629 100644
--- a/tools/perf/util/machine.h
+++ b/tools/perf/util/machine.h
@@ -20,6 +20,8 @@ union perf_event;
 
 extern const char *ref_reloc_sym_names[];
 
+struct vdso_info;
+
 struct machine {
 	struct rb_node	  rb_node;
 	pid_t		  pid;
@@ -28,11 +30,13 @@ struct machine {
 	struct rb_root	  threads;
 	struct list_head  dead_threads;
 	struct thread	  *last_match;
+	struct vdso_info  *vdso_info;
 	struct list_head  user_dsos;
 	struct list_head  kernel_dsos;
 	struct map_groups kmaps;
 	struct map	  *vmlinux_maps[MAP__NR_TYPES];
 	symbol_filter_t	  symbol_filter;
+	pid_t		  *current_tid;
 };
 
 static inline
@@ -191,4 +195,8 @@ int machine__synthesize_threads(struct machine *machine, struct target *target,
 					     perf_event__process, data_mmap);
 }
 
+pid_t machine__get_current_tid(struct machine *machine, int cpu);
+int machine__set_current_tid(struct machine *machine, int cpu, pid_t pid,
+			     pid_t tid);
+
 #endif /* __PERF_MACHINE_H */
diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c
index 845f627e45f..31b8905dd86 100644
--- a/tools/perf/util/map.c
+++ b/tools/perf/util/map.c
@@ -13,6 +13,7 @@
 #include "build-id.h"
 #include "util.h"
 #include "debug.h"
+#include "machine.h"
 #include <linux/string.h>
 
 const char *map_type__name[MAP__NR_TYPES] = {
@@ -137,10 +138,10 @@ void map__init(struct map *map, enum map_type type,
 	map->erange_warned = false;
 }
 
-struct map *map__new(struct list_head *dsos__list, u64 start, u64 len,
+struct map *map__new(struct machine *machine, u64 start, u64 len,
 		     u64 pgoff, u32 pid, u32 d_maj, u32 d_min, u64 ino,
 		     u64 ino_gen, u32 prot, u32 flags, char *filename,
-		     enum map_type type)
+		     enum map_type type, struct thread *thread)
 {
 	struct map *map = malloc(sizeof(*map));
 
@@ -173,9 +174,9 @@ struct map *map__new(struct list_head *dsos__list, u64 start, u64 len,
 
 		if (vdso) {
 			pgoff = 0;
-			dso = vdso__dso_findnew(dsos__list);
+			dso = vdso__dso_findnew(machine, thread);
 		} else
-			dso = __dsos__findnew(dsos__list, filename);
+			dso = __dsos__findnew(&machine->user_dsos, filename);
 
 		if (dso == NULL)
 			goto out_delete;
diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h
index 22d13a21959..2f83954af05 100644
--- a/tools/perf/util/map.h
+++ b/tools/perf/util/map.h
@@ -104,6 +104,7 @@ u64 map__rip_2objdump(struct map *map, u64 rip);
 u64 map__objdump_2mem(struct map *map, u64 ip);
 
 struct symbol;
+struct thread;
 
 /* map__for_each_symbol - iterate over the symbols in the given map
  *
@@ -119,10 +120,10 @@ typedef int (*symbol_filter_t)(struct map *map, struct symbol *sym);
 
 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,
+struct map *map__new(struct machine *machine, u64 start, u64 len,
 		     u64 pgoff, u32 pid, u32 d_maj, u32 d_min, u64 ino,
 		     u64 ino_gen, u32 prot, u32 flags,
-		     char *filename, enum map_type type);
+		     char *filename, enum map_type type, struct thread *thread);
 struct map *map__new2(u64 start, struct dso *dso, enum map_type type);
 void map__delete(struct map *map);
 struct map *map__clone(struct map *map);
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index eac14ce0ae8..88dfef70c13 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -14,7 +14,6 @@
 #include "util.h"
 #include "cpumap.h"
 #include "perf_regs.h"
-#include "vdso.h"
 
 static int perf_session__open(struct perf_session *session)
 {
@@ -156,7 +155,6 @@ void perf_session__delete(struct perf_session *session)
 	if (session->file)
 		perf_data_file__close(session->file);
 	free(session);
-	vdso__exit();
 }
 
 static int process_event_synth_tracing_data_stub(struct perf_tool *tool
@@ -511,6 +509,7 @@ static int flush_sample_queue(struct perf_session *s,
 		os->last_flush = iter->timestamp;
 		list_del(&iter->list);
 		list_add(&iter->list, &os->sample_cache);
+		os->nr_samples--;
 
 		if (show_progress)
 			ui_progress__update(&prog, 1);
@@ -523,8 +522,6 @@ static int flush_sample_queue(struct perf_session *s,
 			list_entry(head->prev, struct sample_queue, list);
 	}
 
-	os->nr_samples = 0;
-
 	return 0;
 }
 
@@ -994,8 +991,10 @@ static int perf_session_deliver_event(struct perf_session *session,
 	}
 }
 
-static int perf_session__process_user_event(struct perf_session *session, union perf_event *event,
-					    struct perf_tool *tool, u64 file_offset)
+static s64 perf_session__process_user_event(struct perf_session *session,
+					    union perf_event *event,
+					    struct perf_tool *tool,
+					    u64 file_offset)
 {
 	int fd = perf_data_file__fd(session->file);
 	int err;
@@ -1037,7 +1036,7 @@ static void event_swap(union perf_event *event, bool sample_id_all)
 		swap(event, sample_id_all);
 }
 
-static int perf_session__process_event(struct perf_session *session,
+static s64 perf_session__process_event(struct perf_session *session,
 				       union perf_event *event,
 				       struct perf_tool *tool,
 				       u64 file_offset)
@@ -1148,7 +1147,7 @@ static int __perf_session__process_pipe_events(struct perf_session *session,
 	union perf_event *event;
 	uint32_t size, cur_size = 0;
 	void *buf = NULL;
-	int skip = 0;
+	s64 skip = 0;
 	u64 head;
 	ssize_t err;
 	void *p;
@@ -1277,13 +1276,13 @@ int __perf_session__process_events(struct perf_session *session,
 				   u64 file_size, struct perf_tool *tool)
 {
 	int fd = perf_data_file__fd(session->file);
-	u64 head, page_offset, file_offset, file_pos;
+	u64 head, page_offset, file_offset, file_pos, size;
 	int err, mmap_prot, mmap_flags, map_idx = 0;
 	size_t	mmap_size;
 	char *buf, *mmaps[NUM_MMAPS];
 	union perf_event *event;
-	uint32_t size;
 	struct ui_progress prog;
+	s64 skip;
 
 	perf_tool__fill_defaults(tool);
 
@@ -1344,7 +1343,8 @@ more:
 	size = event->header.size;
 
 	if (size < sizeof(struct perf_event_header) ||
-	    perf_session__process_event(session, event, tool, file_pos) < 0) {
+	    (skip = perf_session__process_event(session, event, tool, file_pos))
+									< 0) {
 		pr_err("%#" PRIx64 " [%#x]: failed to process type: %d\n",
 		       file_offset + head, event->header.size,
 		       event->header.type);
@@ -1352,6 +1352,9 @@ more:
 		goto out_err;
 	}
 
+	if (skip)
+		size += skip;
+
 	head += size;
 	file_pos += size;
 
diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c
index cef8f426356..d75349979e6 100644
--- a/tools/perf/util/symbol-elf.c
+++ b/tools/perf/util/symbol-elf.c
@@ -622,7 +622,7 @@ int symsrc__init(struct symsrc *ss, struct dso *dso, const char *name,
 		GElf_Shdr shdr;
 		ss->adjust_symbols = (ehdr.e_type == ET_EXEC ||
 				ehdr.e_type == ET_REL ||
-				is_vdso_map(dso->short_name) ||
+				dso__is_vdso(dso) ||
 				elf_section_by_name(elf, &ehdr, &shdr,
 						     ".gnu.prelink_undo",
 						     NULL) != NULL);
@@ -1028,6 +1028,39 @@ int file__read_maps(int fd, bool exe, mapfn_t mapfn, void *data,
 	return err;
 }
 
+enum dso_type dso__type_fd(int fd)
+{
+	enum dso_type dso_type = DSO__TYPE_UNKNOWN;
+	GElf_Ehdr ehdr;
+	Elf_Kind ek;
+	Elf *elf;
+
+	elf = elf_begin(fd, PERF_ELF_C_READ_MMAP, NULL);
+	if (elf == NULL)
+		goto out;
+
+	ek = elf_kind(elf);
+	if (ek != ELF_K_ELF)
+		goto out_end;
+
+	if (gelf_getclass(elf) == ELFCLASS64) {
+		dso_type = DSO__TYPE_64BIT;
+		goto out_end;
+	}
+
+	if (gelf_getehdr(elf, &ehdr) == NULL)
+		goto out_end;
+
+	if (ehdr.e_machine == EM_X86_64)
+		dso_type = DSO__TYPE_X32BIT;
+	else
+		dso_type = DSO__TYPE_32BIT;
+out_end:
+	elf_end(elf);
+out:
+	return dso_type;
+}
+
 static int copy_bytes(int from, off_t from_offs, int to, off_t to_offs, u64 len)
 {
 	ssize_t r;
diff --git a/tools/perf/util/symbol-minimal.c b/tools/perf/util/symbol-minimal.c
index 101f55d407d..c9541fea951 100644
--- a/tools/perf/util/symbol-minimal.c
+++ b/tools/perf/util/symbol-minimal.c
@@ -305,6 +305,27 @@ static int fd__is_64_bit(int fd)
 	return e_ident[EI_CLASS] == ELFCLASS64;
 }
 
+enum dso_type dso__type_fd(int fd)
+{
+	Elf64_Ehdr ehdr;
+	int ret;
+
+	ret = fd__is_64_bit(fd);
+	if (ret < 0)
+		return DSO__TYPE_UNKNOWN;
+
+	if (ret)
+		return DSO__TYPE_64BIT;
+
+	if (readn(fd, &ehdr, sizeof(ehdr)) != sizeof(ehdr))
+		return DSO__TYPE_UNKNOWN;
+
+	if (ehdr.e_machine == EM_X86_64)
+		return DSO__TYPE_X32BIT;
+
+	return DSO__TYPE_32BIT;
+}
+
 int dso__load_sym(struct dso *dso, struct map *map __maybe_unused,
 		  struct symsrc *ss,
 		  struct symsrc *runtime_ss __maybe_unused,
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index ee2d3ccd3ad..e7295e93cff 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -243,6 +243,8 @@ struct symbol *dso__find_symbol_by_name(struct dso *dso, enum map_type type,
 struct symbol *dso__first_symbol(struct dso *dso, enum map_type type);
 struct symbol *dso__next_symbol(struct symbol *sym);
 
+enum dso_type dso__type_fd(int fd);
+
 int filename__read_build_id(const char *filename, void *bf, size_t size);
 int sysfs__read_build_id(const char *filename, void *bf, size_t size);
 int modules__parse(const char *filename, void *arg,
diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c
index 9692c06a9e2..12c7a253a63 100644
--- a/tools/perf/util/thread.c
+++ b/tools/perf/util/thread.c
@@ -34,6 +34,7 @@ struct thread *thread__new(pid_t pid, pid_t tid)
 		thread->pid_ = pid;
 		thread->tid = tid;
 		thread->ppid = -1;
+		thread->cpu = -1;
 		INIT_LIST_HEAD(&thread->comm_list);
 
 		comm_str = malloc(32);
diff --git a/tools/perf/util/thread.h b/tools/perf/util/thread.h
index 3c0c2724f82..716b7723cce 100644
--- a/tools/perf/util/thread.h
+++ b/tools/perf/util/thread.h
@@ -17,6 +17,7 @@ struct thread {
 	pid_t			pid_; /* Not all tools update this */
 	pid_t			tid;
 	pid_t			ppid;
+	int			cpu;
 	char			shortname[3];
 	bool			comm_set;
 	bool			dead; /* if set thread has exited */
diff --git a/tools/perf/util/tsc.c b/tools/perf/util/tsc.c
index ef4749836ce..4d4210d4e13 100644
--- a/tools/perf/util/tsc.c
+++ b/tools/perf/util/tsc.c
@@ -23,3 +23,8 @@ u64 tsc_to_perf_time(u64 cyc, struct perf_tsc_conversion *tc)
 	return tc->time_zero + quot * tc->time_mult +
 	       ((rem * tc->time_mult) >> tc->time_shift);
 }
+
+u64 __weak rdtsc(void)
+{
+	return 0;
+}
diff --git a/tools/perf/util/tsc.h b/tools/perf/util/tsc.h
index 4eca84887c8..a8b78f1b324 100644
--- a/tools/perf/util/tsc.h
+++ b/tools/perf/util/tsc.h
@@ -7,5 +7,6 @@
 
 u64 perf_time_to_tsc(u64 ns, struct perf_tsc_conversion *tc);
 u64 tsc_to_perf_time(u64 cyc, struct perf_tsc_conversion *tc);
+u64 rdtsc(void);
 
 #endif
diff --git a/tools/perf/util/vdso.c b/tools/perf/util/vdso.c
index 290582452da..adca69384fc 100644
--- a/tools/perf/util/vdso.c
+++ b/tools/perf/util/vdso.c
@@ -11,11 +11,34 @@
 #include "vdso.h"
 #include "util.h"
 #include "symbol.h"
+#include "machine.h"
 #include "linux/string.h"
 #include "debug.h"
 
-static bool vdso_found;
-static char vdso_file[] = "/tmp/perf-vdso.so-XXXXXX";
+#define VDSO__TEMP_FILE_NAME "/tmp/perf-vdso.so-XXXXXX"
+
+struct vdso_file {
+	bool found;
+	bool error;
+	char temp_file_name[sizeof(VDSO__TEMP_FILE_NAME)];
+	const char *dso_name;
+};
+
+struct vdso_info {
+	struct vdso_file vdso;
+};
+
+static struct vdso_info *vdso_info__new(void)
+{
+	static const struct vdso_info vdso_info_init = {
+		.vdso    = {
+			.temp_file_name = VDSO__TEMP_FILE_NAME,
+			.dso_name = DSO__NAME_VDSO,
+		},
+	};
+
+	return memdup(&vdso_info_init, sizeof(vdso_info_init));
+}
 
 static int find_vdso_map(void **start, void **end)
 {
@@ -48,7 +71,7 @@ static int find_vdso_map(void **start, void **end)
 	return !found;
 }
 
-static char *get_file(void)
+static char *get_file(struct vdso_file *vdso_file)
 {
 	char *vdso = NULL;
 	char *buf = NULL;
@@ -56,10 +79,10 @@ static char *get_file(void)
 	size_t size;
 	int fd;
 
-	if (vdso_found)
-		return vdso_file;
+	if (vdso_file->found)
+		return vdso_file->temp_file_name;
 
-	if (find_vdso_map(&start, &end))
+	if (vdso_file->error || find_vdso_map(&start, &end))
 		return NULL;
 
 	size = end - start;
@@ -68,45 +91,78 @@ static char *get_file(void)
 	if (!buf)
 		return NULL;
 
-	fd = mkstemp(vdso_file);
+	fd = mkstemp(vdso_file->temp_file_name);
 	if (fd < 0)
 		goto out;
 
 	if (size == (size_t) write(fd, buf, size))
-		vdso = vdso_file;
+		vdso = vdso_file->temp_file_name;
 
 	close(fd);
 
  out:
 	free(buf);
 
-	vdso_found = (vdso != NULL);
+	vdso_file->found = (vdso != NULL);
+	vdso_file->error = !vdso_file->found;
 	return vdso;
 }
 
-void vdso__exit(void)
+void vdso__exit(struct machine *machine)
 {
-	if (vdso_found)
-		unlink(vdso_file);
+	struct vdso_info *vdso_info = machine->vdso_info;
+
+	if (!vdso_info)
+		return;
+
+	if (vdso_info->vdso.found)
+		unlink(vdso_info->vdso.temp_file_name);
+
+	zfree(&machine->vdso_info);
 }
 
-struct dso *vdso__dso_findnew(struct list_head *head)
+static struct dso *vdso__new(struct machine *machine, const char *short_name,
+			     const char *long_name)
 {
-	struct dso *dso = dsos__find(head, VDSO__MAP_NAME, true);
+	struct dso *dso;
 
+	dso = dso__new(short_name);
+	if (dso != NULL) {
+		dsos__add(&machine->user_dsos, dso);
+		dso__set_long_name(dso, long_name, false);
+	}
+
+	return dso;
+}
+
+struct dso *vdso__dso_findnew(struct machine *machine,
+			      struct thread *thread __maybe_unused)
+{
+	struct vdso_info *vdso_info;
+	struct dso *dso;
+
+	if (!machine->vdso_info)
+		machine->vdso_info = vdso_info__new();
+
+	vdso_info = machine->vdso_info;
+	if (!vdso_info)
+		return NULL;
+
+	dso = dsos__find(&machine->user_dsos, DSO__NAME_VDSO, true);
 	if (!dso) {
 		char *file;
 
-		file = get_file();
+		file = get_file(&vdso_info->vdso);
 		if (!file)
 			return NULL;
 
-		dso = dso__new(VDSO__MAP_NAME);
-		if (dso != NULL) {
-			dsos__add(head, dso);
-			dso__set_long_name(dso, file, false);
-		}
+		dso = vdso__new(machine, DSO__NAME_VDSO, file);
 	}
 
 	return dso;
 }
+
+bool dso__is_vdso(struct dso *dso)
+{
+	return !strcmp(dso->short_name, DSO__NAME_VDSO);
+}
diff --git a/tools/perf/util/vdso.h b/tools/perf/util/vdso.h
index 0f76e7caf6f..af9d6929a21 100644
--- a/tools/perf/util/vdso.h
+++ b/tools/perf/util/vdso.h
@@ -7,12 +7,21 @@
 
 #define VDSO__MAP_NAME "[vdso]"
 
+#define DSO__NAME_VDSO "[vdso]"
+
 static inline bool is_vdso_map(const char *filename)
 {
 	return !strcmp(filename, VDSO__MAP_NAME);
 }
 
-struct dso *vdso__dso_findnew(struct list_head *head);
-void vdso__exit(void);
+struct dso;
+
+bool dso__is_vdso(struct dso *dso);
+
+struct machine;
+struct thread;
+
+struct dso *vdso__dso_findnew(struct machine *machine, struct thread *thread);
+void vdso__exit(struct machine *machine);
 
 #endif /* __PERF_VDSO__ */