Merge tag 'perf-core-for-mingo' of...

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:

 * Add missing 'finished_round' event forwarding in 'perf inject', from Adrian Hunter.

 * Assorted tidy ups, from Adrian Hunter.

 * Fall back to sysfs event names when parsing fails, from Andi Kleen.

 * List pmu events in perf list, from Andi Kleen.

 * Cleanup some memory allocation/freeing uses, from David Ahern.

 * Add option to collapse undesired parts of call graph, from Greg Price.

 * Prep work for multi perf data file storage, from Jiri Olsa.

 * Add support for more than two files comparision in 'perf diff', from Jiri Olsa

 * A few more 'perf test' improvements, from Jiri Olsa

 * libtraceevent cleanups, from Namhyung Kim.

 * Remove odd build stall in 'perf sched' by moving a large struct initialization
   from a local variable to a global one, from Namhyung Kim.

 * Add support for callchains in the gtk UI, from Namhyung Kim.

 * Do not apply symfs for an absolute vmlinux path, fix from Namhyung Kim.

 * Use default include path notation for libtraceevent, from Robert Richter.

 * Fix 'make tools/perf', from Robert Richter.

 * Make Power7 events available, from Runzhen Wang.

 * Add --objdump option to 'perf top', from Sukadev Bhattiprolu.
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>

arch/powerpc/include/asm/perf_event_server.h

@@ -142,11 +142,11 @@ extern ssize_t power_events_sysfs_show(struct device *dev,
 #define	EVENT_PTR(_id, _suffix)		&EVENT_VAR(_id, _suffix).attr.attr
 
 #define	EVENT_ATTR(_name, _id, _suffix)					\
-	PMU_EVENT_ATTR(_name, EVENT_VAR(_id, _suffix), PME_PM_##_id,	\
+	PMU_EVENT_ATTR(_name, EVENT_VAR(_id, _suffix), PME_##_id,	\
 			power_events_sysfs_show)
 
 #define	GENERIC_EVENT_ATTR(_name, _id)	EVENT_ATTR(_name, _id, _g)
 #define	GENERIC_EVENT_PTR(_id)		EVENT_PTR(_id, _g)
 
-#define	POWER_EVENT_ATTR(_name, _id)	EVENT_ATTR(PM_##_name, _id, _p)
+#define	POWER_EVENT_ATTR(_name, _id)	EVENT_ATTR(_name, _id, _p)
 #define	POWER_EVENT_PTR(_id)		EVENT_PTR(_id, _p)

arch/powerpc/perf/power7-pmu.c

@@ -53,37 +53,13 @@
 /*
  * Power7 event codes.
  */
-#define	PME_PM_CYC			0x1e
-#define	PME_PM_GCT_NOSLOT_CYC		0x100f8
-#define	PME_PM_CMPLU_STALL		0x4000a
-#define	PME_PM_INST_CMPL		0x2
-#define	PME_PM_LD_REF_L1		0xc880
-#define	PME_PM_LD_MISS_L1		0x400f0
-#define	PME_PM_BRU_FIN			0x10068
-#define	PME_PM_BR_MPRED			0x400f6
-
-#define PME_PM_CMPLU_STALL_FXU			0x20014
-#define PME_PM_CMPLU_STALL_DIV			0x40014
-#define PME_PM_CMPLU_STALL_SCALAR		0x40012
-#define PME_PM_CMPLU_STALL_SCALAR_LONG		0x20018
-#define PME_PM_CMPLU_STALL_VECTOR		0x2001c
-#define PME_PM_CMPLU_STALL_VECTOR_LONG		0x4004a
-#define PME_PM_CMPLU_STALL_LSU			0x20012
-#define PME_PM_CMPLU_STALL_REJECT		0x40016
-#define PME_PM_CMPLU_STALL_ERAT_MISS		0x40018
-#define PME_PM_CMPLU_STALL_DCACHE_MISS		0x20016
-#define PME_PM_CMPLU_STALL_STORE		0x2004a
-#define PME_PM_CMPLU_STALL_THRD			0x1001c
-#define PME_PM_CMPLU_STALL_IFU			0x4004c
-#define PME_PM_CMPLU_STALL_BRU			0x4004e
-#define PME_PM_GCT_NOSLOT_IC_MISS		0x2001a
-#define PME_PM_GCT_NOSLOT_BR_MPRED		0x4001a
-#define PME_PM_GCT_NOSLOT_BR_MPRED_IC_MISS	0x4001c
-#define PME_PM_GRP_CMPL				0x30004
-#define PME_PM_1PLUS_PPC_CMPL			0x100f2
-#define PME_PM_CMPLU_STALL_DFU			0x2003c
-#define PME_PM_RUN_CYC				0x200f4
-#define PME_PM_RUN_INST_CMPL			0x400fa
+#define EVENT(_name, _code) \
+	PME_##_name = _code,
+
+enum {
+#include "power7-events-list.h"
+};
+#undef EVENT
 
 /*
  * Layout of constraint bits:
@@ -398,96 +374,36 @@ static int power7_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = {
 };
 
 
-GENERIC_EVENT_ATTR(cpu-cycles,			CYC);
-GENERIC_EVENT_ATTR(stalled-cycles-frontend,	GCT_NOSLOT_CYC);
-GENERIC_EVENT_ATTR(stalled-cycles-backend,	CMPLU_STALL);
-GENERIC_EVENT_ATTR(instructions,		INST_CMPL);
-GENERIC_EVENT_ATTR(cache-references,		LD_REF_L1);
-GENERIC_EVENT_ATTR(cache-misses,		LD_MISS_L1);
-GENERIC_EVENT_ATTR(branch-instructions,		BRU_FIN);
-GENERIC_EVENT_ATTR(branch-misses,		BR_MPRED);
-
-POWER_EVENT_ATTR(CYC,				CYC);
-POWER_EVENT_ATTR(GCT_NOSLOT_CYC,		GCT_NOSLOT_CYC);
-POWER_EVENT_ATTR(CMPLU_STALL,			CMPLU_STALL);
-POWER_EVENT_ATTR(INST_CMPL,			INST_CMPL);
-POWER_EVENT_ATTR(LD_REF_L1,			LD_REF_L1);
-POWER_EVENT_ATTR(LD_MISS_L1,			LD_MISS_L1);
-POWER_EVENT_ATTR(BRU_FIN,			BRU_FIN)
-POWER_EVENT_ATTR(BR_MPRED,			BR_MPRED);
-
-POWER_EVENT_ATTR(CMPLU_STALL_FXU,		CMPLU_STALL_FXU);
-POWER_EVENT_ATTR(CMPLU_STALL_DIV,		CMPLU_STALL_DIV);
-POWER_EVENT_ATTR(CMPLU_STALL_SCALAR,		CMPLU_STALL_SCALAR);
-POWER_EVENT_ATTR(CMPLU_STALL_SCALAR_LONG,	CMPLU_STALL_SCALAR_LONG);
-POWER_EVENT_ATTR(CMPLU_STALL_VECTOR,		CMPLU_STALL_VECTOR);
-POWER_EVENT_ATTR(CMPLU_STALL_VECTOR_LONG,	CMPLU_STALL_VECTOR_LONG);
-POWER_EVENT_ATTR(CMPLU_STALL_LSU,		CMPLU_STALL_LSU);
-POWER_EVENT_ATTR(CMPLU_STALL_REJECT,		CMPLU_STALL_REJECT);
-
-POWER_EVENT_ATTR(CMPLU_STALL_ERAT_MISS,		CMPLU_STALL_ERAT_MISS);
-POWER_EVENT_ATTR(CMPLU_STALL_DCACHE_MISS,	CMPLU_STALL_DCACHE_MISS);
-POWER_EVENT_ATTR(CMPLU_STALL_STORE,		CMPLU_STALL_STORE);
-POWER_EVENT_ATTR(CMPLU_STALL_THRD,		CMPLU_STALL_THRD);
-POWER_EVENT_ATTR(CMPLU_STALL_IFU,		CMPLU_STALL_IFU);
-POWER_EVENT_ATTR(CMPLU_STALL_BRU,		CMPLU_STALL_BRU);
-POWER_EVENT_ATTR(GCT_NOSLOT_IC_MISS,		GCT_NOSLOT_IC_MISS);
-
-POWER_EVENT_ATTR(GCT_NOSLOT_BR_MPRED,		GCT_NOSLOT_BR_MPRED);
-POWER_EVENT_ATTR(GCT_NOSLOT_BR_MPRED_IC_MISS,	GCT_NOSLOT_BR_MPRED_IC_MISS);
-POWER_EVENT_ATTR(GRP_CMPL,			GRP_CMPL);
-POWER_EVENT_ATTR(1PLUS_PPC_CMPL,		1PLUS_PPC_CMPL);
-POWER_EVENT_ATTR(CMPLU_STALL_DFU,		CMPLU_STALL_DFU);
-POWER_EVENT_ATTR(RUN_CYC,			RUN_CYC);
-POWER_EVENT_ATTR(RUN_INST_CMPL,			RUN_INST_CMPL);
+GENERIC_EVENT_ATTR(cpu-cycles,			PM_CYC);
+GENERIC_EVENT_ATTR(stalled-cycles-frontend,	PM_GCT_NOSLOT_CYC);
+GENERIC_EVENT_ATTR(stalled-cycles-backend,	PM_CMPLU_STALL);
+GENERIC_EVENT_ATTR(instructions,		PM_INST_CMPL);
+GENERIC_EVENT_ATTR(cache-references,		PM_LD_REF_L1);
+GENERIC_EVENT_ATTR(cache-misses,		PM_LD_MISS_L1);
+GENERIC_EVENT_ATTR(branch-instructions,		PM_BRU_FIN);
+GENERIC_EVENT_ATTR(branch-misses,		PM_BR_MPRED);
+
+#define EVENT(_name, _code)     POWER_EVENT_ATTR(_name, _name);
+#include "power7-events-list.h"
+#undef EVENT
+
+#define EVENT(_name, _code)     POWER_EVENT_PTR(_name),
 
 static struct attribute *power7_events_attr[] = {
-	GENERIC_EVENT_PTR(CYC),
-	GENERIC_EVENT_PTR(GCT_NOSLOT_CYC),
-	GENERIC_EVENT_PTR(CMPLU_STALL),
-	GENERIC_EVENT_PTR(INST_CMPL),
-	GENERIC_EVENT_PTR(LD_REF_L1),
-	GENERIC_EVENT_PTR(LD_MISS_L1),
-	GENERIC_EVENT_PTR(BRU_FIN),
-	GENERIC_EVENT_PTR(BR_MPRED),
-
-	POWER_EVENT_PTR(CYC),
-	POWER_EVENT_PTR(GCT_NOSLOT_CYC),
-	POWER_EVENT_PTR(CMPLU_STALL),
-	POWER_EVENT_PTR(INST_CMPL),
-	POWER_EVENT_PTR(LD_REF_L1),
-	POWER_EVENT_PTR(LD_MISS_L1),
-	POWER_EVENT_PTR(BRU_FIN),
-	POWER_EVENT_PTR(BR_MPRED),
-
-	POWER_EVENT_PTR(CMPLU_STALL_FXU),
-	POWER_EVENT_PTR(CMPLU_STALL_DIV),
-	POWER_EVENT_PTR(CMPLU_STALL_SCALAR),
-	POWER_EVENT_PTR(CMPLU_STALL_SCALAR_LONG),
-	POWER_EVENT_PTR(CMPLU_STALL_VECTOR),
-	POWER_EVENT_PTR(CMPLU_STALL_VECTOR_LONG),
-	POWER_EVENT_PTR(CMPLU_STALL_LSU),
-	POWER_EVENT_PTR(CMPLU_STALL_REJECT),
-
-	POWER_EVENT_PTR(CMPLU_STALL_ERAT_MISS),
-	POWER_EVENT_PTR(CMPLU_STALL_DCACHE_MISS),
-	POWER_EVENT_PTR(CMPLU_STALL_STORE),
-	POWER_EVENT_PTR(CMPLU_STALL_THRD),
-	POWER_EVENT_PTR(CMPLU_STALL_IFU),
-	POWER_EVENT_PTR(CMPLU_STALL_BRU),
-	POWER_EVENT_PTR(GCT_NOSLOT_IC_MISS),
-	POWER_EVENT_PTR(GCT_NOSLOT_BR_MPRED),
-
-	POWER_EVENT_PTR(GCT_NOSLOT_BR_MPRED_IC_MISS),
-	POWER_EVENT_PTR(GRP_CMPL),
-	POWER_EVENT_PTR(1PLUS_PPC_CMPL),
-	POWER_EVENT_PTR(CMPLU_STALL_DFU),
-	POWER_EVENT_PTR(RUN_CYC),
-	POWER_EVENT_PTR(RUN_INST_CMPL),
+	GENERIC_EVENT_PTR(PM_CYC),
+	GENERIC_EVENT_PTR(PM_GCT_NOSLOT_CYC),
+	GENERIC_EVENT_PTR(PM_CMPLU_STALL),
+	GENERIC_EVENT_PTR(PM_INST_CMPL),
+	GENERIC_EVENT_PTR(PM_LD_REF_L1),
+	GENERIC_EVENT_PTR(PM_LD_MISS_L1),
+	GENERIC_EVENT_PTR(PM_BRU_FIN),
+	GENERIC_EVENT_PTR(PM_BR_MPRED),
+
+	#include "power7-events-list.h"
+	#undef EVENT
 	NULL
 };
 
-
 static struct attribute_group power7_pmu_events_group = {
 	.name = "events",
 	.attrs = power7_events_attr,

tools/lib/traceevent/Makefile

@@ -39,13 +39,8 @@ bindir_relative = bin
 bindir = $(prefix)/$(bindir_relative)
 man_dir = $(prefix)/share/man
 man_dir_SQ = '$(subst ','\'',$(man_dir))'
-html_install = $(prefix)/share/kernelshark/html
-html_install_SQ = '$(subst ','\'',$(html_install))'
-img_install = $(prefix)/share/kernelshark/html/images
-img_install_SQ = '$(subst ','\'',$(img_install))'
 
-export man_dir man_dir_SQ html_install html_install_SQ INSTALL
-export img_install img_install_SQ
+export man_dir man_dir_SQ INSTALL
 export DESTDIR DESTDIR_SQ
 
 # copy a bit from Linux kbuild
@@ -76,10 +71,7 @@ $(if $(BUILD_OUTPUT),, \
 
 all: sub-make
 
-gui: force
-	$(call build_output, all_cmd)
-
-$(filter-out gui,$(MAKECMDGOALS)): sub-make
+$(MAKECMDGOALS): sub-make
 
 sub-make: force
 	$(call build_output, $(MAKECMDGOALS))
@@ -189,6 +181,7 @@ $(obj)/%.o: $(src)/%.c
 	$(Q)$(call do_compile)
 
 PEVENT_LIB_OBJS = event-parse.o trace-seq.o parse-filter.o parse-utils.o
+PEVENT_LIB_OBJS += kbuffer-parse.o
 
 ALL_OBJS = $(PEVENT_LIB_OBJS)
 
@@ -258,9 +251,6 @@ define check_deps
 		$(RM) $@.$$$$
 endef
 
-$(gui_deps): ks_version.h
-$(non_gui_deps): tc_version.h
-
 $(all_deps): .%.d: $(src)/%.c
 	$(Q)$(call check_deps)
 
@@ -300,7 +290,7 @@ define do_install
 	$(INSTALL) $1 '$(DESTDIR_SQ)$2'
 endef
 
-install_lib: all_cmd install_plugins install_python
+install_lib: all_cmd
 	$(Q)$(call do_install,$(LIB_FILE),$(bindir_SQ))
 
 install: install_lib

tools/lib/traceevent/event-parse.c

@@ -5450,10 +5450,9 @@ int pevent_register_print_function(struct pevent *pevent,
  * If @id is >= 0, then it is used to find the event.
  * else @sys_name and @event_name are used.
  */
-int pevent_register_event_handler(struct pevent *pevent,
-				  int id, char *sys_name, char *event_name,
-				  pevent_event_handler_func func,
-				  void *context)
+int pevent_register_event_handler(struct pevent *pevent, int id,
+				  const char *sys_name, const char *event_name,
+				  pevent_event_handler_func func, void *context)
 {
 	struct event_format *event;
 	struct event_handler *handle;

tools/lib/traceevent/event-parse.h

@@ -69,6 +69,7 @@ struct trace_seq {
 };
 
 void trace_seq_init(struct trace_seq *s);
+void trace_seq_reset(struct trace_seq *s);
 void trace_seq_destroy(struct trace_seq *s);
 
 extern int trace_seq_printf(struct trace_seq *s, const char *fmt, ...)
@@ -399,6 +400,7 @@ struct pevent {
 
 	int cpus;
 	int long_size;
+	int page_size;
 
 	struct cmdline *cmdlines;
 	struct cmdline_list *cmdlist;
@@ -561,7 +563,8 @@ int pevent_print_num_field(struct trace_seq *s, const char *fmt,
 			   struct event_format *event, const char *name,
 			   struct pevent_record *record, int err);
 
-int pevent_register_event_handler(struct pevent *pevent, int id, char *sys_name, char *event_name,
+int pevent_register_event_handler(struct pevent *pevent, int id,
+				  const char *sys_name, const char *event_name,
 				  pevent_event_handler_func func, void *context);
 int pevent_register_print_function(struct pevent *pevent,
 				   pevent_func_handler func,
@@ -619,6 +622,16 @@ static inline void pevent_set_long_size(struct pevent *pevent, int long_size)
 	pevent->long_size = long_size;
 }
 
+static inline int pevent_get_page_size(struct pevent *pevent)
+{
+	return pevent->page_size;
+}
+
+static inline void pevent_set_page_size(struct pevent *pevent, int _page_size)
+{
+	pevent->page_size = _page_size;
+}
+
 static inline int pevent_is_file_bigendian(struct pevent *pevent)
 {
 	return pevent->file_bigendian;

tools/lib/traceevent/kbuffer.h

+/*
+ * Copyright (C) 2012 Red Hat Inc, Steven Rostedt <srostedt@redhat.com>
+ *
+ * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU Lesser General Public
+ * License as published by the Free Software Foundation;
+ * version 2.1 of the License (not later!)
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU Lesser General Public License for more details.
+ *
+ * You should have received a copy of the GNU Lesser General Public
+ * License along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
+ *
+ * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ */
+#ifndef _KBUFFER_H
+#define _KBUFFER_H
+
+#ifndef TS_SHIFT
+#define TS_SHIFT		27
+#endif
+
+enum kbuffer_endian {
+	KBUFFER_ENDIAN_BIG,
+	KBUFFER_ENDIAN_LITTLE,
+};
+
+enum kbuffer_long_size {
+	KBUFFER_LSIZE_4,
+	KBUFFER_LSIZE_8,
+};
+
+enum {
+	KBUFFER_TYPE_PADDING		= 29,
+	KBUFFER_TYPE_TIME_EXTEND	= 30,
+	KBUFFER_TYPE_TIME_STAMP		= 31,
+};
+
+struct kbuffer;
+
+struct kbuffer *kbuffer_alloc(enum kbuffer_long_size size, enum kbuffer_endian endian);
+void kbuffer_free(struct kbuffer *kbuf);
+int kbuffer_load_subbuffer(struct kbuffer *kbuf, void *subbuffer);
+void *kbuffer_read_event(struct kbuffer *kbuf, unsigned long long *ts);
+void *kbuffer_next_event(struct kbuffer *kbuf, unsigned long long *ts);
+unsigned long long kbuffer_timestamp(struct kbuffer *kbuf);
+
+void *kbuffer_translate_data(int swap, void *data, unsigned int *size);
+
+void *kbuffer_read_at_offset(struct kbuffer *kbuf, int offset, unsigned long long *ts);
+
+int kbuffer_curr_index(struct kbuffer *kbuf);
+
+int kbuffer_curr_offset(struct kbuffer *kbuf);
+int kbuffer_curr_size(struct kbuffer *kbuf);
+int kbuffer_event_size(struct kbuffer *kbuf);
+int kbuffer_missed_events(struct kbuffer *kbuf);
+int kbuffer_subbuffer_size(struct kbuffer *kbuf);
+
+void kbuffer_set_old_format(struct kbuffer *kbuf);
+
+#endif /* _K_BUFFER_H */

tools/lib/traceevent/trace-seq.c

@@ -48,6 +48,19 @@ void trace_seq_init(struct trace_seq *s)
 	s->buffer = malloc_or_die(s->buffer_size);
 }
 
+/**
+ * trace_seq_reset - re-initialize the trace_seq structure
+ * @s: a pointer to the trace_seq structure to reset
+ */
+void trace_seq_reset(struct trace_seq *s)
+{
+	if (!s)
+		return;
+	TRACE_SEQ_CHECK(s);
+	s->len = 0;
+	s->readpos = 0;
+}
+
 /**
  * trace_seq_destroy - free up memory of a trace_seq
  * @s: a pointer to the trace_seq to free the buffer

tools/perf/Documentation/perf-diff.txt

@@ -3,17 +3,17 @@ perf-diff(1)
 
 NAME
 ----
-perf-diff - Read two perf.data files and display the differential profile
+perf-diff - Read perf.data files and display the differential profile
 
 SYNOPSIS
 --------
 [verse]
-'perf diff' [oldfile] [newfile]
+'perf diff' [baseline file] [data file1] [[data file2] ... ]
 
 DESCRIPTION
 -----------
-This command displays the performance difference amongst two perf.data files
-captured via perf record.
+This command displays the performance difference amongst two or more perf.data
+files captured via perf record.
 
 If no parameters are passed it will assume perf.data.old and perf.data.
 
@@ -75,8 +75,6 @@ OPTIONS
 -c::
 --compute::
         Differential computation selection - delta,ratio,wdiff (default is delta).
-        If '+' is specified as a first character, the output is sorted based
-        on the computation results.
         See COMPARISON METHODS section for more info.
 
 -p::
@@ -87,6 +85,63 @@ OPTIONS
 --formula::
         Show formula for given computation.
 
+-o::
+--order::
+       Specify compute sorting column number.
+
+COMPARISON
+----------
+The comparison is governed by the baseline file. The baseline perf.data
+file is iterated for samples. All other perf.data files specified on
+the command line are searched for the baseline sample pair. If the pair
+is found, specified computation is made and result is displayed.
+
+All samples from non-baseline perf.data files, that do not match any
+baseline entry, are displayed with empty space within baseline column
+and possible computation results (delta) in their related column.
+
+Example files samples:
+- file A with samples f1, f2, f3, f4,    f6
+- file B with samples     f2,     f4, f5
+- file C with samples f1, f2,         f5
+
+Example output:
+  x - computation takes place for pair
+  b - baseline sample percentage
+
+- perf diff A B C
+
+  baseline/A compute/B compute/C  samples
+  ---------------------------------------
+  b                    x          f1
+  b          x         x          f2
+  b                               f3
+  b          x                    f4
+  b                               f6
+             x         x          f5
+
+- perf diff B A C
+
+  baseline/B compute/A compute/C  samples
+  ---------------------------------------
+  b          x         x          f2
+  b          x                    f4
+  b                    x          f5
+             x         x          f1
+             x                    f3
+             x                    f6
+
+- perf diff C B A
+
+  baseline/C compute/B compute/A  samples
+  ---------------------------------------
+  b                    x          f1
+  b          x         x          f2
+  b          x                    f5
+                       x          f3
+             x         x          f4
+                       x          f6
+
 COMPARISON METHODS
 ------------------
 delta
@@ -96,7 +151,7 @@ If specified the 'Delta' column is displayed with value 'd' computed as:
   d = A->period_percent - B->period_percent
 
 with:
-  - A/B being matching hist entry from first/second file specified
+  - A/B being matching hist entry from data/baseline file specified
     (or perf.data/perf.data.old) respectively.
 
   - period_percent being the % of the hist entry period value within
@@ -109,24 +164,26 @@ If specified the 'Ratio' column is displayed with value 'r' computed as:
   r = A->period / B->period
 
 with:
-  - A/B being matching hist entry from first/second file specified
+  - A/B being matching hist entry from data/baseline file specified
     (or perf.data/perf.data.old) respectively.
 
   - period being the hist entry period value
 
-wdiff
-~~~~~
+wdiff:WEIGHT-B,WEIGHT-A
+~~~~~~~~~~~~~~~~~~~~~~~
 If specified the 'Weighted diff' column is displayed with value 'd' computed as:
 
    d = B->period * WEIGHT-A - A->period * WEIGHT-B
 
-  - A/B being matching hist entry from first/second file specified
+  - A/B being matching hist entry from data/baseline file specified
     (or perf.data/perf.data.old) respectively.
 
   - period being the hist entry period value
 
   - WEIGHT-A/WEIGHT-B being user suplied weights in the the '-c' option
     behind ':' separator like '-c wdiff:1,2'.
+    - WIEGHT-A being the weight of the data file
+    - WIEGHT-B being the weight of the baseline data file
 
 SEE ALSO
 --------

tools/perf/Documentation/perf-list.txt

@@ -8,7 +8,7 @@ perf-list - List all symbolic event types
 SYNOPSIS
 --------
 [verse]
-'perf list' [hw|sw|cache|tracepoint|event_glob]
+'perf list' [hw|sw|cache|tracepoint|pmu|event_glob]
 
 DESCRIPTION
 -----------
@@ -104,6 +104,8 @@ To limit the list use:
   'subsys_glob:event_glob' to filter by tracepoint subsystems such as sched,
   block, etc.
 
+. 'pmu' to print the kernel supplied PMU events.
+
 . If none of the above is matched, it will apply the supplied glob to all
   events, printing the ones that match.
 

tools/perf/Documentation/perf-report.txt

@@ -135,6 +135,11 @@ OPTIONS
 --inverted::
         alias for inverted caller based call graph.
 
+--ignore-callees=<regex>::
+        Ignore callees of the function(s) matching the given regex.
+        This has the effect of collecting the callers of each such
+        function into one place in the call-graph tree.
+
 --pretty=<key>::
         Pretty printing style.  key: normal, raw
 

tools/perf/Documentation/perf-top.txt

@@ -155,6 +155,11 @@ Default is to monitor all CPUS.
 
 	Default: fractal,0.5,callee.
 
+--ignore-callees=<regex>::
+        Ignore callees of the function(s) matching the given regex.
+        This has the effect of collecting the callers of each such
+        function into one place in the call-graph tree.
+
 --percent-limit::
 	Do not show entries which have an overhead under that percent.
 	(Default: 0).

tools/perf/Makefile

@@ -124,7 +124,7 @@ strip-libs = $(filter-out -l%,$(1))
 ifneq ($(OUTPUT),)
   TE_PATH=$(OUTPUT)
 ifneq ($(subdir),)
-  LK_PATH=$(objtree)/lib/lk/
+  LK_PATH=$(OUTPUT)/../lib/lk/
 else
   LK_PATH=$(OUTPUT)
 endif
@@ -281,7 +281,7 @@ LIB_H += util/cpumap.h
 LIB_H += util/top.h
 LIB_H += $(ARCH_INCLUDE)
 LIB_H += util/cgroup.h
-LIB_H += $(TRACE_EVENT_DIR)event-parse.h
+LIB_H += $(LIB_INCLUDE)traceevent/event-parse.h
 LIB_H += util/target.h
 LIB_H += util/rblist.h
 LIB_H += util/intlist.h

tools/perf/builtin-inject.c

@@ -38,8 +38,7 @@ struct event_entry {
 };
 
 static int perf_event__repipe_synth(struct perf_tool *tool,
-				    union perf_event *event,
-				    struct machine *machine __maybe_unused)
+				    union perf_event *event)
 {
 	struct perf_inject *inject = container_of(tool, struct perf_inject, tool);
 	uint32_t size;
@@ -65,39 +64,28 @@ static int perf_event__repipe_op2_synth(struct perf_tool *tool,
 					struct perf_session *session
 					__maybe_unused)
 {
-	return perf_event__repipe_synth(tool, event, NULL);
+	return perf_event__repipe_synth(tool, event);
 }
 
-static int perf_event__repipe_event_type_synth(struct perf_tool *tool,
-					       union perf_event *event)
-{
-	return perf_event__repipe_synth(tool, event, NULL);
-}
-
-static int perf_event__repipe_tracing_data_synth(union perf_event *event,
-						 struct perf_session *session
-						 __maybe_unused)
-{
-	return perf_event__repipe_synth(NULL, event, NULL);
-}
-
-static int perf_event__repipe_attr(union perf_event *event,
-				   struct perf_evlist **pevlist __maybe_unused)
+static int perf_event__repipe_attr(struct perf_tool *tool,
+				   union perf_event *event,
+				   struct perf_evlist **pevlist)
 {
 	int ret;
-	ret = perf_event__process_attr(event, pevlist);
+
+	ret = perf_event__process_attr(tool, event, pevlist);
 	if (ret)
 		return ret;
 
-	return perf_event__repipe_synth(NULL, event, NULL);
+	return perf_event__repipe_synth(tool, event);
 }
 
 static int perf_event__repipe(struct perf_tool *tool,
 			      union perf_event *event,
 			      struct perf_sample *sample __maybe_unused,
-			      struct machine *machine)
+			      struct machine *machine __maybe_unused)
 {
-	return perf_event__repipe_synth(tool, event, machine);
+	return perf_event__repipe_synth(tool, event);
 }
 
 typedef int (*inject_handler)(struct perf_tool *tool,
@@ -119,7 +107,7 @@ static int perf_event__repipe_sample(struct perf_tool *tool,
 
 	build_id__mark_dso_hit(tool, event, sample, evsel, machine);
 
-	return perf_event__repipe_synth(tool, event, machine);
+	return perf_event__repipe_synth(tool, event);
 }
 
 static int perf_event__repipe_mmap(struct perf_tool *tool,
@@ -148,13 +136,14 @@ static int perf_event__repipe_fork(struct perf_tool *tool,
 	return err;
 }
 
-static int perf_event__repipe_tracing_data(union perf_event *event,
+static int perf_event__repipe_tracing_data(struct perf_tool *tool,
+					   union perf_event *event,
 					   struct perf_session *session)
 {
 	int err;
 
-	perf_event__repipe_synth(NULL, event, NULL);
-	err = perf_event__process_tracing_data(event, session);
+	perf_event__repipe_synth(tool, event);
+	err = perf_event__process_tracing_data(tool, event, session);
 
 	return err;
 }
@@ -407,8 +396,8 @@ int cmd_inject(int argc, const char **argv, const char *prefix __maybe_unused)
 			.throttle	= perf_event__repipe,
 			.unthrottle	= perf_event__repipe,
 			.attr		= perf_event__repipe_attr,
-			.event_type	= perf_event__repipe_event_type_synth,
-			.tracing_data	= perf_event__repipe_tracing_data_synth,
+			.tracing_data	= perf_event__repipe_op2_synth,
+			.finished_round	= perf_event__repipe_op2_synth,
 			.build_id	= perf_event__repipe_op2_synth,
 		},
 		.input_name  = "-",

tools/perf/builtin-kmem.c

@@ -313,7 +313,7 @@ static int process_sample_event(struct perf_tool *tool __maybe_unused,
 		return -1;
 	}
 
-	dump_printf(" ... thread: %s:%d\n", thread->comm, thread->pid);
+	dump_printf(" ... thread: %s:%d\n", thread->comm, thread->tid);
 
 	if (evsel->handler.func != NULL) {
 		tracepoint_handler f = evsel->handler.func;

tools/perf/builtin-list.c

@@ -13,6 +13,7 @@
 
 #include "util/parse-events.h"
 #include "util/cache.h"
+#include "util/pmu.h"
 
 int cmd_list(int argc, const char **argv, const char *prefix __maybe_unused)
 {
@@ -37,6 +38,8 @@ int cmd_list(int argc, const char **argv, const char *prefix __maybe_unused)
 			else if (strcmp(argv[i], "cache") == 0 ||
 				 strcmp(argv[i], "hwcache") == 0)
 				print_hwcache_events(NULL, false);
+			else if (strcmp(argv[i], "pmu") == 0)
+				print_pmu_events(NULL, false);
 			else if (strcmp(argv[i], "--raw-dump") == 0)
 				print_events(NULL, true);
 			else {

tools/perf/builtin-record.c

@@ -474,13 +474,6 @@ static int __cmd_record(struct perf_record *rec, int argc, const char **argv)
 			goto out_delete_session;
 		}
 
-		err = perf_event__synthesize_event_types(tool, process_synthesized_event,
-							 machine);
-		if (err < 0) {
-			pr_err("Couldn't synthesize event_types.\n");
-			goto out_delete_session;
-		}
-
 		if (have_tracepoints(&evsel_list->entries)) {
 			/*
 			 * FIXME err <= 0 here actually means that
@@ -904,7 +897,6 @@ const struct option record_options[] = {
 int cmd_record(int argc, const char **argv, const char *prefix __maybe_unused)
 {
 	int err = -ENOMEM;
-	struct perf_evsel *pos;
 	struct perf_evlist *evsel_list;
 	struct perf_record *rec = &record;
 	char errbuf[BUFSIZ];
@@ -968,11 +960,6 @@ int cmd_record(int argc, const char **argv, const char *prefix __maybe_unused)
 	if (perf_evlist__create_maps(evsel_list, &rec->opts.target) < 0)
 		usage_with_options(record_usage, record_options);
 
-	list_for_each_entry(pos, &evsel_list->entries, node) {
-		if (perf_header__push_event(pos->attr.config, perf_evsel__name(pos)))
-			goto out_free_fd;
-	}
-
 	if (rec->opts.user_interval != ULLONG_MAX)
 		rec->opts.default_interval = rec->opts.user_interval;
 	if (rec->opts.user_freq != UINT_MAX)

tools/perf/builtin-report.c

@@ -89,7 +89,7 @@ static int perf_report__add_mem_hist_entry(struct perf_tool *tool,
 	if ((sort__has_parent || symbol_conf.use_callchain) &&
 	    sample->callchain) {
 		err = machine__resolve_callchain(machine, evsel, al->thread,
-						 sample, &parent);
+						 sample, &parent, al);
 		if (err)
 			return err;
 	}
@@ -180,7 +180,7 @@ static int perf_report__add_branch_hist_entry(struct perf_tool *tool,
 	if ((sort__has_parent || symbol_conf.use_callchain)
 	    && sample->callchain) {
 		err = machine__resolve_callchain(machine, evsel, al->thread,
-						 sample, &parent);
+						 sample, &parent, al);
 		if (err)
 			return err;
 	}
@@ -254,7 +254,7 @@ static int perf_evsel__add_hist_entry(struct perf_evsel *evsel,
 
 	if ((sort__has_parent || symbol_conf.use_callchain) && sample->callchain) {
 		err = machine__resolve_callchain(machine, evsel, al->thread,
-						 sample, &parent);
+						 sample, &parent, al);
 		if (err)
 			return err;
 	}
@@ -497,7 +497,7 @@ static int __cmd_report(struct perf_report *rep)
 		ret = perf_session__cpu_bitmap(session, rep->cpu_list,
 					       rep->cpu_bitmap);
 		if (ret)
-			goto out_delete;
+			return ret;
 	}
 
 	if (use_browser <= 0)
@@ -508,11 +508,11 @@ static int __cmd_report(struct perf_report *rep)
 
 	ret = perf_report__setup_sample_type(rep);
 	if (ret)
-		goto out_delete;
+		return ret;
 
 	ret = perf_session__process_events(session, &rep->tool);
 	if (ret)
-		goto out_delete;
+		return ret;
 
 	kernel_map = session->machines.host.vmlinux_maps[MAP__FUNCTION];
 	kernel_kmap = map__kmap(kernel_map);
@@ -547,7 +547,7 @@ static int __cmd_report(struct perf_report *rep)
 
 	if (dump_trace) {
 		perf_session__fprintf_nr_events(session, stdout);
-		goto out_delete;
+		return 0;
 	}
 
 	nr_samples = 0;
@@ -572,7 +572,7 @@ static int __cmd_report(struct perf_report *rep)
 
 	if (nr_samples == 0) {
 		ui__error("The %s file has no samples!\n", session->filename);
-		goto out_delete;
+		return 0;
 	}
 
 	list_for_each_entry(pos, &session->evlist->entries, node)
@@ -598,19 +598,6 @@ static int __cmd_report(struct perf_report *rep)
 	} else
 		perf_evlist__tty_browse_hists(session->evlist, rep, help);
 
-out_delete:
-	/*
-	 * Speed up the exit process, for large files this can
-	 * take quite a while.
-	 *
-	 * XXX Enable this when using valgrind or if we ever
-	 * librarize this command.
-	 *
-	 * Also experiment with obstacks to see how much speed
-	 * up we'll get here.
-	 *
- 	 * perf_session__delete(session);
- 	 */
 	return ret;
 }
 
@@ -694,6 +681,24 @@ parse_callchain_opt(const struct option *opt, const char *arg, int unset)
 	return 0;
 }
 
+int
+report_parse_ignore_callees_opt(const struct option *opt __maybe_unused,
+				const char *arg, int unset __maybe_unused)
+{
+	if (arg) {
+		int err = regcomp(&ignore_callees_regex, arg, REG_EXTENDED);
+		if (err) {
+			char buf[BUFSIZ];
+			regerror(err, &ignore_callees_regex, buf, sizeof(buf));
+			pr_err("Invalid --ignore-callees regex: %s\n%s", arg, buf);
+			return -1;
+		}
+		have_ignore_callees = 1;
+	}
+
+	return 0;
+}
+
 static int
 parse_branch_mode(const struct option *opt __maybe_unused,
 		  const char *str __maybe_unused, int unset)
@@ -736,7 +741,6 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
 			.lost		 = perf_event__process_lost,
 			.read		 = process_read_event,
 			.attr		 = perf_event__process_attr,
-			.event_type	 = perf_event__process_event_type,
 			.tracing_data	 = perf_event__process_tracing_data,
 			.build_id	 = perf_event__process_build_id,
 			.ordered_samples = true,
@@ -784,6 +788,9 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
 		     "Default: fractal,0.5,callee", &parse_callchain_opt, callchain_default_opt),
 	OPT_BOOLEAN('G', "inverted", &report.inverted_callchain,
 		    "alias for inverted call graph"),
+	OPT_CALLBACK(0, "ignore-callees", NULL, "regex",
+		   "ignore callees of these functions in call graphs",
+		   report_parse_ignore_callees_opt),
 	OPT_STRING('d', "dsos", &symbol_conf.dso_list_str, "dso[,dso...]",
 		   "only consider symbols in these dsos"),
 	OPT_STRING('c', "comms", &symbol_conf.comm_list_str, "comm[,comm...]",
@@ -853,7 +860,6 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
 		setup_browser(true);
 	else {
 		use_browser = 0;
-		perf_hpp__column_enable(PERF_HPP__OVERHEAD);
 		perf_hpp__init();
 	}
 
@@ -931,14 +937,6 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
 	if (parent_pattern != default_parent_pattern) {
 		if (sort_dimension__add("parent") < 0)
 			goto error;
-
-		/*
-		 * Only show the parent fields if we explicitly
-		 * sort that way. If we only use parent machinery
-		 * for filtering, we don't want it.
-		 */
-		if (!strstr(sort_order, "parent"))
-			sort_parent.elide = 1;
 	}
 
 	if (argc) {

tools/perf/builtin-sched.c

@@ -1075,7 +1075,7 @@ static int latency_migrate_task_event(struct perf_sched *sched,
 	if (!atoms) {
 		if (thread_atoms_insert(sched, migrant))
 			return -1;
-		register_pid(sched, migrant->pid, migrant->comm);
+		register_pid(sched, migrant->tid, migrant->comm);
 		atoms = thread_atoms_search(&sched->atom_root, migrant, &sched->cmp_pid);
 		if (!atoms) {
 			pr_err("migration-event: Internal tree error");
@@ -1115,7 +1115,7 @@ static void output_lat_thread(struct perf_sched *sched, struct work_atoms *work_
 	sched->all_runtime += work_list->total_runtime;
 	sched->all_count   += work_list->nb_atoms;
 
-	ret = printf("  %s:%d ", work_list->thread->comm, work_list->thread->pid);
+	ret = printf("  %s:%d ", work_list->thread->comm, work_list->thread->tid);
 
 	for (i = 0; i < 24 - ret; i++)
 		printf(" ");
@@ -1131,9 +1131,9 @@ static void output_lat_thread(struct perf_sched *sched, struct work_atoms *work_
 
 static int pid_cmp(struct work_atoms *l, struct work_atoms *r)
 {
-	if (l->thread->pid < r->thread->pid)
+	if (l->thread->tid < r->thread->tid)
 		return -1;
-	if (l->thread->pid > r->thread->pid)
+	if (l->thread->tid > r->thread->tid)
 		return 1;
 
 	return 0;
@@ -1321,7 +1321,7 @@ static int map_switch_event(struct perf_sched *sched, struct perf_evsel *evsel,
 			printf("*");
 
 		if (sched->curr_thread[cpu]) {
-			if (sched->curr_thread[cpu]->pid)
+			if (sched->curr_thread[cpu]->tid)
 				printf("%2s ", sched->curr_thread[cpu]->shortname);
 			else
 				printf(".  ");
@@ -1332,7 +1332,7 @@ static int map_switch_event(struct perf_sched *sched, struct perf_evsel *evsel,
 	printf("  %12.6f secs ", (double)timestamp/1e9);
 	if (new_shortname) {
 		printf("%s => %s:%d\n",
-			sched_in->shortname, sched_in->comm, sched_in->pid);
+			sched_in->shortname, sched_in->comm, sched_in->tid);
 	} else {
 		printf("\n");
 	}
@@ -1662,28 +1662,29 @@ static int __cmd_record(int argc, const char **argv)
 	return cmd_record(i, rec_argv, NULL);
 }
 
+static const char default_sort_order[] = "avg, max, switch, runtime";
+static struct perf_sched sched = {
+	.tool = {
+		.sample		 = perf_sched__process_tracepoint_sample,
+		.comm		 = perf_event__process_comm,
+		.lost		 = perf_event__process_lost,
+		.fork		 = perf_event__process_fork,
+		.ordered_samples = true,
+	},
+	.cmp_pid	      = LIST_HEAD_INIT(sched.cmp_pid),
+	.sort_list	      = LIST_HEAD_INIT(sched.sort_list),
+	.start_work_mutex     = PTHREAD_MUTEX_INITIALIZER,
+	.work_done_wait_mutex = PTHREAD_MUTEX_INITIALIZER,
+	.curr_pid	      = { [0 ... MAX_CPUS - 1] = -1 },
+	.sort_order	      = default_sort_order,
+	.replay_repeat	      = 10,
+	.profile_cpu	      = -1,
+	.next_shortname1      = 'A',
+	.next_shortname2      = '0',
+};
+
 int cmd_sched(int argc, const char **argv, const char *prefix __maybe_unused)
 {
-	const char default_sort_order[] = "avg, max, switch, runtime";
-	struct perf_sched sched = {
-		.tool = {
-			.sample		 = perf_sched__process_tracepoint_sample,
-			.comm		 = perf_event__process_comm,
-			.lost		 = perf_event__process_lost,
-			.fork		 = perf_event__process_fork,
-			.ordered_samples = true,
-		},
-		.cmp_pid	      = LIST_HEAD_INIT(sched.cmp_pid),
-		.sort_list	      = LIST_HEAD_INIT(sched.sort_list),
-		.start_work_mutex     = PTHREAD_MUTEX_INITIALIZER,
-		.work_done_wait_mutex = PTHREAD_MUTEX_INITIALIZER,
-		.curr_pid	      = { [0 ... MAX_CPUS - 1] = -1 },
-		.sort_order	      = default_sort_order,
-		.replay_repeat	      = 10,
-		.profile_cpu	      = -1,
-		.next_shortname1      = 'A',
-		.next_shortname2      = '0',
-	};
 	const struct option latency_options[] = {
 	OPT_STRING('s', "sort", &sched.sort_order, "key[,key2...]",
 		   "sort by key(s): runtime, switch, avg, max"),

tools/perf/builtin-script.c

@@ -24,6 +24,7 @@ static u64			last_timestamp;
 static u64			nr_unordered;
 extern const struct option	record_options[];
 static bool			no_callchain;
+static bool			latency_format;
 static bool			system_wide;
 static const char		*cpu_list;
 static DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS);
@@ -523,7 +524,6 @@ static struct perf_tool perf_script = {
 	.exit		 = perf_event__process_exit,
 	.fork		 = perf_event__process_fork,
 	.attr		 = perf_event__process_attr,
-	.event_type	 = perf_event__process_event_type,
 	.tracing_data	 = perf_event__process_tracing_data,
 	.build_id	 = perf_event__process_build_id,
 	.ordered_samples = true,

tools/perf/builtin-timechart.c

@@ -12,6 +12,8 @@
  * of the License.
  */
 
+#include <traceevent/event-parse.h>
+
 #include "builtin.h"
 
 #include "util/util.h"
@@ -19,6 +21,7 @@
 #include "util/color.h"
 #include <linux/list.h>
 #include "util/cache.h"
+#include "util/evlist.h"
 #include "util/evsel.h"
 #include <linux/rbtree.h>
 #include "util/symbol.h"
@@ -328,25 +331,6 @@ struct wakeup_entry {
 	int   success;
 };
 
-/*
- * trace_flag_type is an enumeration that holds different
- * states when a trace occurs. These are:
- *  IRQS_OFF            - interrupts were disabled
- *  IRQS_NOSUPPORT      - arch does not support irqs_disabled_flags
- *  NEED_RESCED         - reschedule is requested
- *  HARDIRQ             - inside an interrupt handler
- *  SOFTIRQ             - inside a softirq handler
- */
-enum trace_flag_type {
-	TRACE_FLAG_IRQS_OFF		= 0x01,
-	TRACE_FLAG_IRQS_NOSUPPORT	= 0x02,
-	TRACE_FLAG_NEED_RESCHED		= 0x04,
-	TRACE_FLAG_HARDIRQ		= 0x08,
-	TRACE_FLAG_SOFTIRQ		= 0x10,
-};
-
-
-
 struct sched_switch {
 	struct trace_entry te;
 	char prev_comm[TASK_COMM_LEN];
@@ -479,6 +463,8 @@ static void sched_switch(int cpu, u64 timestamp, struct trace_entry *te)
 	}
 }
 
+typedef int (*tracepoint_handler)(struct perf_evsel *evsel,
+				  struct perf_sample *sample);
 
 static int process_sample_event(struct perf_tool *tool __maybe_unused,
 				union perf_event *event __maybe_unused,
@@ -486,8 +472,6 @@ static int process_sample_event(struct perf_tool *tool __maybe_unused,
 				struct perf_evsel *evsel,
 				struct machine *machine __maybe_unused)
 {
-	struct trace_entry *te;
-
 	if (evsel->attr.sample_type & PERF_SAMPLE_TIME) {
 		if (!first_time || first_time > sample->time)
 			first_time = sample->time;
@@ -495,69 +479,90 @@ static int process_sample_event(struct perf_tool *tool __maybe_unused,
 			last_time = sample->time;
 	}
 
-	te = (void *)sample->raw_data;
-	if ((evsel->attr.sample_type & PERF_SAMPLE_RAW) && sample->raw_size > 0) {
-		char *event_str;
-#ifdef SUPPORT_OLD_POWER_EVENTS
-		struct power_entry_old *peo;
-		peo = (void *)te;
-#endif
-		/*
-		 * FIXME: use evsel, its already mapped from id to perf_evsel,
-		 * remove perf_header__find_event infrastructure bits.
-		 * Mapping all these "power:cpu_idle" strings to the tracepoint
-		 * ID and then just comparing against evsel->attr.config.
-		 *
-		 * e.g.:
-		 *
-		 * if (evsel->attr.config == power_cpu_idle_id)
-		 */
-		event_str = perf_header__find_event(te->type);
-
-		if (!event_str)
-			return 0;
-
-		if (sample->cpu > numcpus)
-			numcpus = sample->cpu;
-
-		if (strcmp(event_str, "power:cpu_idle") == 0) {
-			struct power_processor_entry *ppe = (void *)te;
-			if (ppe->state == (u32)PWR_EVENT_EXIT)
-				c_state_end(ppe->cpu_id, sample->time);
-			else
-				c_state_start(ppe->cpu_id, sample->time,
-					      ppe->state);
-		}
-		else if (strcmp(event_str, "power:cpu_frequency") == 0) {
-			struct power_processor_entry *ppe = (void *)te;
-			p_state_change(ppe->cpu_id, sample->time, ppe->state);
-		}
+	if (sample->cpu > numcpus)
+		numcpus = sample->cpu;
+
+	if (evsel->handler.func != NULL) {
+		tracepoint_handler f = evsel->handler.func;
+		return f(evsel, sample);
+	}
+
+	return 0;
+}
+
+static int
+process_sample_cpu_idle(struct perf_evsel *evsel __maybe_unused,
+			struct perf_sample *sample)
+{
+	struct power_processor_entry *ppe = sample->raw_data;
+
+	if (ppe->state == (u32) PWR_EVENT_EXIT)
+		c_state_end(ppe->cpu_id, sample->time);
+	else
+		c_state_start(ppe->cpu_id, sample->time, ppe->state);
+	return 0;
+}
+
+static int
+process_sample_cpu_frequency(struct perf_evsel *evsel __maybe_unused,
+			     struct perf_sample *sample)
+{
+	struct power_processor_entry *ppe = sample->raw_data;
+
+	p_state_change(ppe->cpu_id, sample->time, ppe->state);
+	return 0;
+}
+
+static int
+process_sample_sched_wakeup(struct perf_evsel *evsel __maybe_unused,
+			    struct perf_sample *sample)
+{
+	struct trace_entry *te = sample->raw_data;
+
+	sched_wakeup(sample->cpu, sample->time, sample->pid, te);
+	return 0;
+}
 
-		else if (strcmp(event_str, "sched:sched_wakeup") == 0)
-			sched_wakeup(sample->cpu, sample->time, sample->pid, te);
+static int
+process_sample_sched_switch(struct perf_evsel *evsel __maybe_unused,
+			    struct perf_sample *sample)
+{
+	struct trace_entry *te = sample->raw_data;
 
-		else if (strcmp(event_str, "sched:sched_switch") == 0)
-			sched_switch(sample->cpu, sample->time, te);
+	sched_switch(sample->cpu, sample->time, te);
+	return 0;
+}
 
 #ifdef SUPPORT_OLD_POWER_EVENTS
-		if (use_old_power_events) {
-			if (strcmp(event_str, "power:power_start") == 0)
-				c_state_start(peo->cpu_id, sample->time,
-					      peo->value);
-
-			else if (strcmp(event_str, "power:power_end") == 0)
-				c_state_end(sample->cpu, sample->time);
-
-			else if (strcmp(event_str,
-					"power:power_frequency") == 0)
-				p_state_change(peo->cpu_id, sample->time,
-					       peo->value);
-		}
-#endif
-	}
+static int
+process_sample_power_start(struct perf_evsel *evsel __maybe_unused,
+			   struct perf_sample *sample)
+{
+	struct power_entry_old *peo = sample->raw_data;
+
+	c_state_start(peo->cpu_id, sample->time, peo->value);
 	return 0;
 }
 
+static int
+process_sample_power_end(struct perf_evsel *evsel __maybe_unused,
+			 struct perf_sample *sample)
+{
+	c_state_end(sample->cpu, sample->time);
+	return 0;
+}
+
+static int
+process_sample_power_frequency(struct perf_evsel *evsel __maybe_unused,
+			       struct perf_sample *sample)
+{
+	struct power_entry_old *peo = sample->raw_data;
+
+	p_state_change(peo->cpu_id, sample->time, peo->value);
+	return 0;
+}
+#endif /* SUPPORT_OLD_POWER_EVENTS */
+
 /*
  * After the last sample we need to wrap up the current C/P state
  * and close out each CPU for these.
@@ -974,6 +979,17 @@ static int __cmd_timechart(const char *output_name)
 		.sample		 = process_sample_event,
 		.ordered_samples = true,
 	};
+	const struct perf_evsel_str_handler power_tracepoints[] = {
+		{ "power:cpu_idle",		process_sample_cpu_idle },
+		{ "power:cpu_frequency",	process_sample_cpu_frequency },
+		{ "sched:sched_wakeup",		process_sample_sched_wakeup },
+		{ "sched:sched_switch",		process_sample_sched_switch },
+#ifdef SUPPORT_OLD_POWER_EVENTS
+		{ "power:power_start",		process_sample_power_start },
+		{ "power:power_end",		process_sample_power_end },
+		{ "power:power_frequency",	process_sample_power_frequency },
+#endif
+	};
 	struct perf_session *session = perf_session__new(input_name, O_RDONLY,
 							 0, false, &perf_timechart);
 	int ret = -EINVAL;
@@ -984,6 +1000,12 @@ static int __cmd_timechart(const char *output_name)
 	if (!perf_session__has_traces(session, "timechart record"))
 		goto out_delete;
 
+	if (perf_session__set_tracepoints_handlers(session,
+						   power_tracepoints)) {
+		pr_err("Initializing session tracepoint handlers failed\n");
+		goto out_delete;
+	}
+
 	ret = perf_session__process_events(session, &perf_timechart);
 	if (ret)
 		goto out_delete;

tools/perf/builtin-top.c

@@ -40,6 +40,7 @@
 #include "util/xyarray.h"
 #include "util/sort.h"
 #include "util/intlist.h"
+#include "arch/common.h"
 
 #include "util/debug.h"
 
@@ -772,8 +773,7 @@ static void perf_event__process_sample(struct perf_tool *tool,
 		    sample->callchain) {
 			err = machine__resolve_callchain(machine, evsel,
 							 al.thread, sample,
-							 &parent);
-
+							 &parent, &al);
 			if (err)
 				return;
 		}
@@ -939,6 +939,12 @@ static int __cmd_top(struct perf_top *top)
 	if (top->session == NULL)
 		return -ENOMEM;
 
+	if (!objdump_path) {
+		ret = perf_session_env__lookup_objdump(&top->session->header.env);
+		if (ret)
+			goto out_delete;
+	}
+
 	ret = perf_top__setup_sample_type(top);
 	if (ret)
 		goto out_delete;
@@ -1102,6 +1108,9 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused)
 	OPT_CALLBACK_DEFAULT('G', "call-graph", &top.record_opts,
 			     "mode[,dump_size]", record_callchain_help,
 			     &parse_callchain_opt, "fp"),
+	OPT_CALLBACK(0, "ignore-callees", NULL, "regex",
+		   "ignore callees of these functions in call graphs",
+		   report_parse_ignore_callees_opt),
 	OPT_BOOLEAN(0, "show-total-period", &symbol_conf.show_total_period,
 		    "Show a column with the sum of periods"),
 	OPT_STRING(0, "dsos", &symbol_conf.dso_list_str, "dso[,dso...]",
@@ -1114,6 +1123,8 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused)
 		    "Interleave source code with assembly code (default)"),
 	OPT_BOOLEAN(0, "asm-raw", &symbol_conf.annotate_asm_raw,
 		    "Display raw encoding of assembly instructions (default)"),
+	OPT_STRING(0, "objdump", &objdump_path, "path",
+		    "objdump binary to use for disassembly and annotations"),
 	OPT_STRING('M', "disassembler-style", &disassembler_style, "disassembler style",
 		   "Specify disassembler style (e.g. -M intel for intel syntax)"),
 	OPT_STRING('u', "uid", &target->uid_str, "user", "user to profile"),

tools/perf/builtin-trace.c

+#include <traceevent/event-parse.h>
 #include "builtin.h"
 #include "util/color.h"
 #include "util/evlist.h"
@@ -5,7 +6,6 @@
 #include "util/thread.h"
 #include "util/parse-options.h"
 #include "util/thread_map.h"
-#include "event-parse.h"
 
 #include <libaudit.h>
 #include <stdlib.h>
@@ -142,7 +142,7 @@ static size_t trace__fprintf_entry_head(struct trace *trace, struct thread *thre
 	printed += fprintf_duration(duration, fp);
 
 	if (trace->multiple_threads)
-		printed += fprintf(fp, "%d ", thread->pid);
+		printed += fprintf(fp, "%d ", thread->tid);
 
 	return printed;
 }
@@ -593,7 +593,7 @@ static size_t trace__fprintf_thread_summary(struct trace *trace, FILE *fp)
 			color = PERF_COLOR_YELLOW;
 
 		printed += color_fprintf(fp, color, "%20s", thread->comm);
-		printed += fprintf(fp, " - %-5d :%11lu   [", thread->pid, ttrace->nr_events);
+		printed += fprintf(fp, " - %-5d :%11lu   [", thread->tid, ttrace->nr_events);
 		printed += color_fprintf(fp, color, "%5.1f%%", ratio);
 		printed += fprintf(fp, " ] %10.3f ms\n", ttrace->runtime_ms);
 	}

tools/perf/config/Makefile

@@ -46,6 +46,8 @@ ifneq ($(obj-perf),)
 obj-perf := $(abspath $(obj-perf))/
 endif
 
+LIB_INCLUDE := $(srctree)/tools/lib/
+
 # include ARCH specific config
 -include $(src-perf)/arch/$(ARCH)/Makefile
 
@@ -121,8 +123,7 @@ endif
 
 CFLAGS += -I$(src-perf)/util
 CFLAGS += -I$(src-perf)
-CFLAGS += -I$(TRACE_EVENT_DIR)
-CFLAGS += -I$(srctree)/tools/lib/
+CFLAGS += -I$(LIB_INCLUDE)
 
 CFLAGS += -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64 -D_GNU_SOURCE
 

tools/perf/tests/dso-data.c

@@ -10,14 +10,6 @@
 #include "symbol.h"
 #include "tests.h"
 
-#define TEST_ASSERT_VAL(text, cond) \
-do { \
-	if (!(cond)) { \
-		pr_debug("FAILED %s:%d %s\n", __FILE__, __LINE__, text); \
-		return -1; \
-	} \
-} while (0)
-
 static char *test_file(int size)
 {
 	static char buf_templ[] = "/tmp/test-XXXXXX";

tools/perf/tests/evsel-tp-sched.c

+#include <traceevent/event-parse.h>
 #include "evsel.h"
 #include "tests.h"
-#include "event-parse.h"
 
 static int perf_evsel__test_field(struct perf_evsel *evsel, const char *name,
 				  int size, bool should_be_signed)
@@ -49,7 +49,7 @@ int test__perf_evsel__tp_sched_test(void)
 	if (perf_evsel__test_field(evsel, "prev_prio", 4, true))
 		ret = -1;
 
-	if (perf_evsel__test_field(evsel, "prev_state", 8, true))
+	if (perf_evsel__test_field(evsel, "prev_state", sizeof(long), true))
 		ret = -1;
 
 	if (perf_evsel__test_field(evsel, "next_comm", 16, true))

tools/perf/tests/parse-events.c

@@ -7,14 +7,6 @@
 #include "tests.h"
 #include <linux/hw_breakpoint.h>
 
-#define TEST_ASSERT_VAL(text, cond) \
-do { \
-	if (!(cond)) { \
-		pr_debug("FAILED %s:%d %s\n", __FILE__, __LINE__, text); \
-		return -1; \
-	} \
-} while (0)
-
 #define PERF_TP_SAMPLE_TYPE (PERF_SAMPLE_RAW | PERF_SAMPLE_TIME | \
 			     PERF_SAMPLE_CPU | PERF_SAMPLE_PERIOD)
 
@@ -1254,24 +1246,20 @@ static int test_events(struct evlist_test *events, unsigned cnt)
 
 static int test_term(struct terms_test *t)
 {
-	struct list_head *terms;
+	struct list_head terms;
 	int ret;
 
-	terms = malloc(sizeof(*terms));
-	if (!terms)
-		return -ENOMEM;
-
-	INIT_LIST_HEAD(terms);
+	INIT_LIST_HEAD(&terms);
 
-	ret = parse_events_terms(terms, t->str);
+	ret = parse_events_terms(&terms, t->str);
 	if (ret) {
 		pr_debug("failed to parse terms '%s', err %d\n",
 			 t->str , ret);
 		return ret;
 	}
 
-	ret = t->check(terms);
-	parse_events__free_terms(terms);
+	ret = t->check(&terms);
+	parse_events__free_terms(&terms);
 
 	return ret;
 }

tools/perf/tests/tests.h

 #ifndef TESTS_H
 #define TESTS_H
 
+#define TEST_ASSERT_VAL(text, cond)					 \
+do {									 \
+	if (!(cond)) {							 \
+		pr_debug("FAILED %s:%d %s\n", __FILE__, __LINE__, text); \
+		return -1;						 \
+	}								 \
+} while (0)
+
 enum {
 	TEST_OK   =  0,
 	TEST_FAIL = -1,

tools/perf/tests/vmlinux-kallsyms.c

@@ -139,11 +139,18 @@ int test__vmlinux_matches_kallsyms(void)
 				 * _really_ have a problem.
 				 */
 				s64 skew = sym->end - pair->end;
-				if (llabs(skew) < page_size)
-					continue;
+				if (llabs(skew) >= page_size)
+					pr_debug("%#" PRIx64 ": diff end addr for %s v: %#" PRIx64 " k: %#" PRIx64 "\n",
+						 sym->start, sym->name, sym->end, pair->end);
+
+				/*
+				 * Do not count this as a failure, because we
+				 * could really find a case where it's not
+				 * possible to get proper function end from
+				 * kallsyms.
+				 */
+				continue;
 
-				pr_debug("%#" PRIx64 ": diff end addr for %s v: %#" PRIx64 " k: %#" PRIx64 "\n",
-					 sym->start, sym->name, sym->end, pair->end);
 			} else {
 				struct rb_node *nnd;
 detour:

tools/perf/ui/browsers/hists.c

@@ -685,8 +685,10 @@ static u64 __hpp_get_##_field(struct hist_entry *he)			\
 	return he->stat._field;						\
 }									\
 									\
-static int hist_browser__hpp_color_##_type(struct perf_hpp *hpp,	\
-					   struct hist_entry *he)	\
+static int								\
+hist_browser__hpp_color_##_type(struct perf_hpp_fmt *fmt __maybe_unused,\
+				struct perf_hpp *hpp,			\
+				struct hist_entry *he)			\
 {									\
 	return __hpp__color_fmt(hpp, he, __hpp_get_##_field, _cb);	\
 }
@@ -701,8 +703,6 @@ __HPP_COLOR_PERCENT_FN(overhead_guest_us, period_guest_us, NULL)
 
 void hist_browser__init_hpp(void)
 {
-	perf_hpp__column_enable(PERF_HPP__OVERHEAD);
-
 	perf_hpp__init();
 
 	perf_hpp__format[PERF_HPP__OVERHEAD].color =
@@ -762,9 +762,9 @@ static int hist_browser__show_entry(struct hist_browser *browser,
 			first = false;
 
 			if (fmt->color) {
-				width -= fmt->color(&hpp, entry);
+				width -= fmt->color(fmt, &hpp, entry);
 			} else {
-				width -= fmt->entry(&hpp, entry);
+				width -= fmt->entry(fmt, &hpp, entry);
 				slsmg_printf("%s", s);
 			}
 		}
@@ -1256,7 +1256,7 @@ static int hists__browser_title(struct hists *hists, char *bf, size_t size,
 		printed += scnprintf(bf + printed, size - printed,
 				    ", Thread: %s(%d)",
 				    (thread->comm_set ? thread->comm : ""),
-				    thread->pid);
+				    thread->tid);
 	if (dso)
 		printed += scnprintf(bf + printed, size - printed,
 				    ", DSO: %s", dso->short_name);
@@ -1579,7 +1579,7 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
 		    asprintf(&options[nr_options], "Zoom %s %s(%d) thread",
 			     (browser->hists->thread_filter ? "out of" : "into"),
 			     (thread->comm_set ? thread->comm : ""),
-			     thread->pid) > 0)
+			     thread->tid) > 0)
 			zoom_thread = nr_options++;
 
 		if (dso != NULL &&
@@ -1702,7 +1702,7 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
 			} else {
 				ui_helpline__fpush("To zoom out press <- or -> + \"Zoom out of %s(%d) thread\"",
 						   thread->comm_set ? thread->comm : "",
-						   thread->pid);
+						   thread->tid);
 				browser->hists->thread_filter = thread;
 				sort_thread.elide = true;
 				pstack__push(fstack, &browser->hists->thread_filter);

tools/perf/ui/gtk/hists.c

@@ -91,7 +91,8 @@ static u64 he_get_##_field(struct hist_entry *he)				\
 	return he->stat._field;							\
 }										\
 										\
-static int perf_gtk__hpp_color_##_type(struct perf_hpp *hpp,			\
+static int perf_gtk__hpp_color_##_type(struct perf_hpp_fmt *fmt __maybe_unused,	\
+				       struct perf_hpp *hpp,			\
 				       struct hist_entry *he)			\
 {										\
 	return __hpp__color_fmt(hpp, he, he_get_##_field);			\
@@ -124,6 +125,81 @@ void perf_gtk__init_hpp(void)
 				perf_gtk__hpp_color_overhead_guest_us;
 }
 
+static void callchain_list__sym_name(struct callchain_list *cl,
+				     char *bf, size_t bfsize)
+{
+	if (cl->ms.sym)
+		scnprintf(bf, bfsize, "%s", cl->ms.sym->name);
+	else
+		scnprintf(bf, bfsize, "%#" PRIx64, cl->ip);
+}
+
+static void perf_gtk__add_callchain(struct rb_root *root, GtkTreeStore *store,
+				    GtkTreeIter *parent, int col, u64 total)
+{
+	struct rb_node *nd;
+	bool has_single_node = (rb_first(root) == rb_last(root));
+
+	for (nd = rb_first(root); nd; nd = rb_next(nd)) {
+		struct callchain_node *node;
+		struct callchain_list *chain;
+		GtkTreeIter iter, new_parent;
+		bool need_new_parent;
+		double percent;
+		u64 hits, child_total;
+
+		node = rb_entry(nd, struct callchain_node, rb_node);
+
+		hits = callchain_cumul_hits(node);
+		percent = 100.0 * hits / total;
+
+		new_parent = *parent;
+		need_new_parent = !has_single_node && (node->val_nr > 1);
+
+		list_for_each_entry(chain, &node->val, list) {
+			char buf[128];
+
+			gtk_tree_store_append(store, &iter, &new_parent);
+
+			scnprintf(buf, sizeof(buf), "%5.2f%%", percent);
+			gtk_tree_store_set(store, &iter, 0, buf, -1);
+
+			callchain_list__sym_name(chain, buf, sizeof(buf));
+			gtk_tree_store_set(store, &iter, col, buf, -1);
+
+			if (need_new_parent) {
+				/*
+				 * Only show the top-most symbol in a callchain
+				 * if it's not the only callchain.
+				 */
+				new_parent = iter;
+				need_new_parent = false;
+			}
+		}
+
+		if (callchain_param.mode == CHAIN_GRAPH_REL)
+			child_total = node->children_hit;
+		else
+			child_total = total;
+
+		/* Now 'iter' contains info of the last callchain_list */
+		perf_gtk__add_callchain(&node->rb_root, store, &iter, col,
+					child_total);
+	}
+}
+
+static void on_row_activated(GtkTreeView *view, GtkTreePath *path,
+			     GtkTreeViewColumn *col __maybe_unused,
+			     gpointer user_data __maybe_unused)
+{
+	bool expanded = gtk_tree_view_row_expanded(view, path);
+
+	if (expanded)
+		gtk_tree_view_collapse_row(view, path);
+	else
+		gtk_tree_view_expand_row(view, path, FALSE);
+}
+
 static void perf_gtk__show_hists(GtkWidget *window, struct hists *hists,
 				 float min_pcnt)
 {
@@ -131,10 +207,11 @@ static void perf_gtk__show_hists(GtkWidget *window, struct hists *hists,
 	GType col_types[MAX_COLUMNS];
 	GtkCellRenderer *renderer;
 	struct sort_entry *se;
-	GtkListStore *store;
+	GtkTreeStore *store;
 	struct rb_node *nd;
 	GtkWidget *view;
 	int col_idx;
+	int sym_col = -1;
 	int nr_cols;
 	char s[512];
 
@@ -153,10 +230,13 @@ static void perf_gtk__show_hists(GtkWidget *window, struct hists *hists,
 		if (se->elide)
 			continue;
 
+		if (se == &sort_sym)
+			sym_col = nr_cols;
+
 		col_types[nr_cols++] = G_TYPE_STRING;
 	}
 
-	store = gtk_list_store_newv(nr_cols, col_types);
+	store = gtk_tree_store_newv(nr_cols, col_types);
 
 	view = gtk_tree_view_new();
 
@@ -165,7 +245,7 @@ static void perf_gtk__show_hists(GtkWidget *window, struct hists *hists,
 	col_idx = 0;
 
 	perf_hpp__for_each_format(fmt) {
-		fmt->header(&hpp);
+		fmt->header(fmt, &hpp);
 
 		gtk_tree_view_insert_column_with_attributes(GTK_TREE_VIEW(view),
 							    -1, ltrim(s),
@@ -183,6 +263,18 @@ static void perf_gtk__show_hists(GtkWidget *window, struct hists *hists,
 							    col_idx++, NULL);
 	}
 
+	for (col_idx = 0; col_idx < nr_cols; col_idx++) {
+		GtkTreeViewColumn *column;
+
+		column = gtk_tree_view_get_column(GTK_TREE_VIEW(view), col_idx);
+		gtk_tree_view_column_set_resizable(column, TRUE);
+
+		if (col_idx == sym_col) {
+			gtk_tree_view_set_expander_column(GTK_TREE_VIEW(view),
+							  column);
+		}
+	}
+
 	gtk_tree_view_set_model(GTK_TREE_VIEW(view), GTK_TREE_MODEL(store));
 
 	g_object_unref(GTK_TREE_MODEL(store));
@@ -199,17 +291,17 @@ static void perf_gtk__show_hists(GtkWidget *window, struct hists *hists,
 		if (percent < min_pcnt)
 			continue;
 
-		gtk_list_store_append(store, &iter);
+		gtk_tree_store_append(store, &iter, NULL);
 
 		col_idx = 0;
 
 		perf_hpp__for_each_format(fmt) {
 			if (fmt->color)
-				fmt->color(&hpp, h);
+				fmt->color(fmt, &hpp, h);
 			else
-				fmt->entry(&hpp, h);
+				fmt->entry(fmt, &hpp, h);
 
-			gtk_list_store_set(store, &iter, col_idx++, s, -1);
+			gtk_tree_store_set(store, &iter, col_idx++, s, -1);
 		}
 
 		list_for_each_entry(se, &hist_entry__sort_list, list) {
@@ -219,10 +311,26 @@ static void perf_gtk__show_hists(GtkWidget *window, struct hists *hists,
 			se->se_snprintf(h, s, ARRAY_SIZE(s),
 					hists__col_len(hists, se->se_width_idx));
 
-			gtk_list_store_set(store, &iter, col_idx++, s, -1);
+			gtk_tree_store_set(store, &iter, col_idx++, s, -1);
+		}
+
+		if (symbol_conf.use_callchain && sort__has_sym) {
+			u64 total;
+
+			if (callchain_param.mode == CHAIN_GRAPH_REL)
+				total = h->stat.period;
+			else
+				total = hists->stats.total_period;
+
+			perf_gtk__add_callchain(&h->sorted_chain, store, &iter,
+						sym_col, total);
 		}
 	}
 
+	gtk_tree_view_set_rules_hint(GTK_TREE_VIEW(view), TRUE);
+
+	g_signal_connect(view, "row-activated",
+			 G_CALLBACK(on_row_activated), NULL);
 	gtk_container_add(GTK_CONTAINER(window), view);
 }
 

tools/perf/ui/hist.c

 #include <math.h>
+#include <linux/compiler.h>
 
 #include "../util/hist.h"
 #include "../util/util.h"
@@ -79,7 +80,8 @@ static int __hpp__fmt(struct perf_hpp *hpp, struct hist_entry *he,
 }
 
 #define __HPP_HEADER_FN(_type, _str, _min_width, _unit_width) 		\
-static int hpp__header_##_type(struct perf_hpp *hpp)			\
+static int hpp__header_##_type(struct perf_hpp_fmt *fmt __maybe_unused,	\
+			       struct perf_hpp *hpp)			\
 {									\
 	int len = _min_width;						\
 									\
@@ -92,7 +94,8 @@ static int hpp__header_##_type(struct perf_hpp *hpp)			\
 }
 
 #define __HPP_WIDTH_FN(_type, _min_width, _unit_width) 			\
-static int hpp__width_##_type(struct perf_hpp *hpp __maybe_unused)	\
+static int hpp__width_##_type(struct perf_hpp_fmt *fmt __maybe_unused,	\
+			      struct perf_hpp *hpp __maybe_unused)	\
 {									\
 	int len = _min_width;						\
 									\
@@ -110,14 +113,16 @@ static u64 he_get_##_field(struct hist_entry *he)				\
 	return he->stat._field;							\
 }										\
 										\
-static int hpp__color_##_type(struct perf_hpp *hpp, struct hist_entry *he) 	\
+static int hpp__color_##_type(struct perf_hpp_fmt *fmt __maybe_unused,		\
+			      struct perf_hpp *hpp, struct hist_entry *he) 	\
 {										\
 	return __hpp__fmt(hpp, he, he_get_##_field, " %6.2f%%",			\
 			  (hpp_snprint_fn)percent_color_snprintf, true);	\
 }
 
 #define __HPP_ENTRY_PERCENT_FN(_type, _field)					\
-static int hpp__entry_##_type(struct perf_hpp *hpp, struct hist_entry *he) 	\
+static int hpp__entry_##_type(struct perf_hpp_fmt *_fmt __maybe_unused,		\
+			      struct perf_hpp *hpp, struct hist_entry *he) 	\
 {										\
 	const char *fmt = symbol_conf.field_sep ? " %.2f" : " %6.2f%%";		\
 	return __hpp__fmt(hpp, he, he_get_##_field, fmt,			\
@@ -130,7 +135,8 @@ static u64 he_get_raw_##_field(struct hist_entry *he)				\
 	return he->stat._field;							\
 }										\
 										\
-static int hpp__entry_##_type(struct perf_hpp *hpp, struct hist_entry *he) 	\
+static int hpp__entry_##_type(struct perf_hpp_fmt *_fmt __maybe_unused,		\
+			      struct perf_hpp *hpp, struct hist_entry *he) 	\
 {										\
 	const char *fmt = symbol_conf.field_sep ? " %"PRIu64 : " %11"PRIu64;	\
 	return __hpp__fmt(hpp, he, he_get_raw_##_field, fmt, scnprintf, false);	\
@@ -157,196 +163,6 @@ HPP_PERCENT_FNS(overhead_guest_us, "guest usr", period_guest_us, 9, 8)
 HPP_RAW_FNS(samples, "Samples", nr_events, 12, 12)
 HPP_RAW_FNS(period, "Period", period, 12, 12)
 
-
-static int hpp__header_baseline(struct perf_hpp *hpp)
-{
-	return scnprintf(hpp->buf, hpp->size, "Baseline");
-}
-
-static int hpp__width_baseline(struct perf_hpp *hpp __maybe_unused)
-{
-	return 8;
-}
-
-static double baseline_percent(struct hist_entry *he)
-{
-	struct hist_entry *pair = hist_entry__next_pair(he);
-	struct hists *pair_hists = pair ? pair->hists : NULL;
-	double percent = 0.0;
-
-	if (pair) {
-		u64 total_period = pair_hists->stats.total_period;
-		u64 base_period  = pair->stat.period;
-
-		percent = 100.0 * base_period / total_period;
-	}
-
-	return percent;
-}
-
-static int hpp__color_baseline(struct perf_hpp *hpp, struct hist_entry *he)
-{
-	double percent = baseline_percent(he);
-
-	if (hist_entry__has_pairs(he) || symbol_conf.field_sep)
-		return percent_color_snprintf(hpp->buf, hpp->size, " %6.2f%%", percent);
-	else
-		return scnprintf(hpp->buf, hpp->size, "        ");
-}
-
-static int hpp__entry_baseline(struct perf_hpp *hpp, struct hist_entry *he)
-{
-	double percent = baseline_percent(he);
-	const char *fmt = symbol_conf.field_sep ? "%.2f" : " %6.2f%%";
-
-	if (hist_entry__has_pairs(he) || symbol_conf.field_sep)
-		return scnprintf(hpp->buf, hpp->size, fmt, percent);
-	else
-		return scnprintf(hpp->buf, hpp->size, "            ");
-}
-
-static int hpp__header_period_baseline(struct perf_hpp *hpp)
-{
-	const char *fmt = symbol_conf.field_sep ? "%s" : "%12s";
-
-	return scnprintf(hpp->buf, hpp->size, fmt, "Period Base");
-}
-
-static int hpp__width_period_baseline(struct perf_hpp *hpp __maybe_unused)
-{
-	return 12;
-}
-
-static int hpp__entry_period_baseline(struct perf_hpp *hpp, struct hist_entry *he)
-{
-	struct hist_entry *pair = hist_entry__next_pair(he);
-	u64 period = pair ? pair->stat.period : 0;
-	const char *fmt = symbol_conf.field_sep ? "%" PRIu64 : "%12" PRIu64;
-
-	return scnprintf(hpp->buf, hpp->size, fmt, period);
-}
-
-static int hpp__header_delta(struct perf_hpp *hpp)
-{
-	const char *fmt = symbol_conf.field_sep ? "%s" : "%7s";
-
-	return scnprintf(hpp->buf, hpp->size, fmt, "Delta");
-}
-
-static int hpp__width_delta(struct perf_hpp *hpp __maybe_unused)
-{
-	return 7;
-}
-
-static int hpp__entry_delta(struct perf_hpp *hpp, struct hist_entry *he)
-{
-	struct hist_entry *pair = hist_entry__next_pair(he);
-	const char *fmt = symbol_conf.field_sep ? "%s" : "%7.7s";
-	char buf[32] = " ";
-	double diff = 0.0;
-
-	if (pair) {
-		if (he->diff.computed)
-			diff = he->diff.period_ratio_delta;
-		else
-			diff = perf_diff__compute_delta(he, pair);
-	} else
-		diff = perf_diff__period_percent(he, he->stat.period);
-
-	if (fabs(diff) >= 0.01)
-		scnprintf(buf, sizeof(buf), "%+4.2F%%", diff);
-
-	return scnprintf(hpp->buf, hpp->size, fmt, buf);
-}
-
-static int hpp__header_ratio(struct perf_hpp *hpp)
-{
-	const char *fmt = symbol_conf.field_sep ? "%s" : "%14s";
-
-	return scnprintf(hpp->buf, hpp->size, fmt, "Ratio");
-}
-
-static int hpp__width_ratio(struct perf_hpp *hpp __maybe_unused)
-{
-	return 14;
-}
-
-static int hpp__entry_ratio(struct perf_hpp *hpp, struct hist_entry *he)
-{
-	struct hist_entry *pair = hist_entry__next_pair(he);
-	const char *fmt = symbol_conf.field_sep ? "%s" : "%14s";
-	char buf[32] = " ";
-	double ratio = 0.0;
-
-	if (pair) {
-		if (he->diff.computed)
-			ratio = he->diff.period_ratio;
-		else
-			ratio = perf_diff__compute_ratio(he, pair);
-	}
-
-	if (ratio > 0.0)
-		scnprintf(buf, sizeof(buf), "%+14.6F", ratio);
-
-	return scnprintf(hpp->buf, hpp->size, fmt, buf);
-}
-
-static int hpp__header_wdiff(struct perf_hpp *hpp)
-{
-	const char *fmt = symbol_conf.field_sep ? "%s" : "%14s";
-
-	return scnprintf(hpp->buf, hpp->size, fmt, "Weighted diff");
-}
-
-static int hpp__width_wdiff(struct perf_hpp *hpp __maybe_unused)
-{
-	return 14;
-}
-
-static int hpp__entry_wdiff(struct perf_hpp *hpp, struct hist_entry *he)
-{
-	struct hist_entry *pair = hist_entry__next_pair(he);
-	const char *fmt = symbol_conf.field_sep ? "%s" : "%14s";
-	char buf[32] = " ";
-	s64 wdiff = 0;
-
-	if (pair) {
-		if (he->diff.computed)
-			wdiff = he->diff.wdiff;
-		else
-			wdiff = perf_diff__compute_wdiff(he, pair);
-	}
-
-	if (wdiff != 0)
-		scnprintf(buf, sizeof(buf), "%14ld", wdiff);
-
-	return scnprintf(hpp->buf, hpp->size, fmt, buf);
-}
-
-static int hpp__header_formula(struct perf_hpp *hpp)
-{
-	const char *fmt = symbol_conf.field_sep ? "%s" : "%70s";
-
-	return scnprintf(hpp->buf, hpp->size, fmt, "Formula");
-}
-
-static int hpp__width_formula(struct perf_hpp *hpp __maybe_unused)
-{
-	return 70;
-}
-
-static int hpp__entry_formula(struct perf_hpp *hpp, struct hist_entry *he)
-{
-	struct hist_entry *pair = hist_entry__next_pair(he);
-	const char *fmt = symbol_conf.field_sep ? "%s" : "%-70s";
-	char buf[96] = " ";
-
-	if (pair)
-		perf_diff__formula(he, pair, buf, sizeof(buf));
-
-	return scnprintf(hpp->buf, hpp->size, fmt, buf);
-}
-
 #define HPP__COLOR_PRINT_FNS(_name)			\
 	{						\
 		.header	= hpp__header_ ## _name,	\
@@ -363,19 +179,13 @@ static int hpp__entry_formula(struct perf_hpp *hpp, struct hist_entry *he)
 	}
 
 struct perf_hpp_fmt perf_hpp__format[] = {
-	HPP__COLOR_PRINT_FNS(baseline),
 	HPP__COLOR_PRINT_FNS(overhead),
 	HPP__COLOR_PRINT_FNS(overhead_sys),
 	HPP__COLOR_PRINT_FNS(overhead_us),
 	HPP__COLOR_PRINT_FNS(overhead_guest_sys),
 	HPP__COLOR_PRINT_FNS(overhead_guest_us),
 	HPP__PRINT_FNS(samples),
-	HPP__PRINT_FNS(period),
-	HPP__PRINT_FNS(period_baseline),
-	HPP__PRINT_FNS(delta),
-	HPP__PRINT_FNS(ratio),
-	HPP__PRINT_FNS(wdiff),
-	HPP__PRINT_FNS(formula)
+	HPP__PRINT_FNS(period)
 };
 
 LIST_HEAD(perf_hpp__list);
@@ -396,6 +206,8 @@ LIST_HEAD(perf_hpp__list);
 
 void perf_hpp__init(void)
 {
+	perf_hpp__column_enable(PERF_HPP__OVERHEAD);
+
 	if (symbol_conf.show_cpu_utilization) {
 		perf_hpp__column_enable(PERF_HPP__OVERHEAD_SYS);
 		perf_hpp__column_enable(PERF_HPP__OVERHEAD_US);
@@ -424,46 +236,6 @@ void perf_hpp__column_enable(unsigned col)
 	perf_hpp__column_register(&perf_hpp__format[col]);
 }
 
-static inline void advance_hpp(struct perf_hpp *hpp, int inc)
-{
-	hpp->buf  += inc;
-	hpp->size -= inc;
-}
-
-int hist_entry__period_snprintf(struct perf_hpp *hpp, struct hist_entry *he,
-				bool color)
-{
-	const char *sep = symbol_conf.field_sep;
-	struct perf_hpp_fmt *fmt;
-	char *start = hpp->buf;
-	int ret;
-	bool first = true;
-
-	if (symbol_conf.exclude_other && !he->parent)
-		return 0;
-
-	perf_hpp__for_each_format(fmt) {
-		/*
-		 * If there's no field_sep, we still need
-		 * to display initial '  '.
-		 */
-		if (!sep || !first) {
-			ret = scnprintf(hpp->buf, hpp->size, "%s", sep ?: "  ");
-			advance_hpp(hpp, ret);
-		} else
-			first = false;
-
-		if (color && fmt->color)
-			ret = fmt->color(hpp, he);
-		else
-			ret = fmt->entry(hpp, he);
-
-		advance_hpp(hpp, ret);
-	}
-
-	return hpp->buf - start;
-}
-
 int hist_entry__sort_snprintf(struct hist_entry *he, char *s, size_t size,
 			      struct hists *hists)
 {
@@ -499,7 +271,7 @@ unsigned int hists__sort_list_width(struct hists *hists)
 		if (i)
 			ret += 2;
 
-		ret += fmt->width(&dummy_hpp);
+		ret += fmt->width(fmt, &dummy_hpp);
 	}
 
 	list_for_each_entry(se, &hist_entry__sort_list, list)

tools/perf/ui/setup.c

@@ -30,7 +30,6 @@ void setup_browser(bool fallback_to_pager)
 		if (fallback_to_pager)
 			setup_pager();
 
-		perf_hpp__column_enable(PERF_HPP__OVERHEAD);
 		perf_hpp__init();
 		break;
 	}

tools/perf/ui/stdio/hist.c

@@ -308,6 +308,47 @@ static size_t hist_entry__callchain_fprintf(struct hist_entry *he,
 	return hist_entry_callchain__fprintf(he, total_period, left_margin, fp);
 }
 
+static inline void advance_hpp(struct perf_hpp *hpp, int inc)
+{
+	hpp->buf  += inc;
+	hpp->size -= inc;
+}
+
+static int hist_entry__period_snprintf(struct perf_hpp *hpp,
+				       struct hist_entry *he,
+				       bool color)
+{
+	const char *sep = symbol_conf.field_sep;
+	struct perf_hpp_fmt *fmt;
+	char *start = hpp->buf;
+	int ret;
+	bool first = true;
+
+	if (symbol_conf.exclude_other && !he->parent)
+		return 0;
+
+	perf_hpp__for_each_format(fmt) {
+		/*
+		 * If there's no field_sep, we still need
+		 * to display initial '  '.
+		 */
+		if (!sep || !first) {
+			ret = scnprintf(hpp->buf, hpp->size, "%s", sep ?: "  ");
+			advance_hpp(hpp, ret);
+		} else
+			first = false;
+
+		if (color && fmt->color)
+			ret = fmt->color(fmt, hpp, he);
+		else
+			ret = fmt->entry(fmt, hpp, he);
+
+		advance_hpp(hpp, ret);
+	}
+
+	return hpp->buf - start;
+}
+
 static int hist_entry__fprintf(struct hist_entry *he, size_t size,
 			       struct hists *hists, FILE *fp)
 {
@@ -365,7 +406,7 @@ size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows,
 		else
 			first = false;
 
-		fmt->header(&dummy_hpp);
+		fmt->header(fmt, &dummy_hpp);
 		fprintf(fp, "%s", bf);
 	}
 
@@ -410,7 +451,7 @@ size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows,
 		else
 			first = false;
 
-		width = fmt->width(&dummy_hpp);
+		width = fmt->width(fmt, &dummy_hpp);
 		for (i = 0; i < width; i++)
 			fprintf(fp, ".");
 	}

tools/perf/util/cpumap.h

@@ -41,7 +41,7 @@ static inline int cpu_map__nr(const struct cpu_map *map)
 	return map ? map->nr : 1;
 }
 
-static inline bool cpu_map__all(const struct cpu_map *map)
+static inline bool cpu_map__empty(const struct cpu_map *map)
 {
 	return map ? map->map[0] == -1 : true;
 }

tools/perf/util/event.c

@@ -686,7 +686,7 @@ int perf_event__preprocess_sample(const union perf_event *event,
 	    !strlist__has_entry(symbol_conf.comm_list, thread->comm))
 		goto out_filtered;
 
-	dump_printf(" ... thread: %s:%d\n", thread->comm, thread->pid);
+	dump_printf(" ... thread: %s:%d\n", thread->comm, thread->tid);
 	/*
 	 * Have we already created the kernel maps for this machine?
 	 *

tools/perf/util/event.h

@@ -116,7 +116,7 @@ struct build_id_event {
 enum perf_user_event_type { /* above any possible kernel type */
 	PERF_RECORD_USER_TYPE_START		= 64,
 	PERF_RECORD_HEADER_ATTR			= 64,
-	PERF_RECORD_HEADER_EVENT_TYPE		= 65,
+	PERF_RECORD_HEADER_EVENT_TYPE		= 65, /* depreceated */
 	PERF_RECORD_HEADER_TRACING_DATA		= 66,
 	PERF_RECORD_HEADER_BUILD_ID		= 67,
 	PERF_RECORD_FINISHED_ROUND		= 68,

tools/perf/util/evlist.c

@@ -403,16 +403,20 @@ union perf_event *perf_evlist__mmap_read(struct perf_evlist *evlist, int idx)
 	return event;
 }
 
+static void __perf_evlist__munmap(struct perf_evlist *evlist, int idx)
+{
+	if (evlist->mmap[idx].base != NULL) {
+		munmap(evlist->mmap[idx].base, evlist->mmap_len);
+		evlist->mmap[idx].base = NULL;
+	}
+}
+
 void perf_evlist__munmap(struct perf_evlist *evlist)
 {
 	int i;
 
-	for (i = 0; i < evlist->nr_mmaps; i++) {
-		if (evlist->mmap[i].base != NULL) {
-			munmap(evlist->mmap[i].base, evlist->mmap_len);
-			evlist->mmap[i].base = NULL;
-		}
-	}
+	for (i = 0; i < evlist->nr_mmaps; i++)
+		__perf_evlist__munmap(evlist, i);
 
 	free(evlist->mmap);
 	evlist->mmap = NULL;
@@ -421,7 +425,7 @@ void perf_evlist__munmap(struct perf_evlist *evlist)
 static int perf_evlist__alloc_mmap(struct perf_evlist *evlist)
 {
 	evlist->nr_mmaps = cpu_map__nr(evlist->cpus);
-	if (cpu_map__all(evlist->cpus))
+	if (cpu_map__empty(evlist->cpus))
 		evlist->nr_mmaps = thread_map__nr(evlist->threads);
 	evlist->mmap = zalloc(evlist->nr_mmaps * sizeof(struct perf_mmap));
 	return evlist->mmap != NULL ? 0 : -ENOMEM;
@@ -477,12 +481,8 @@ static int perf_evlist__mmap_per_cpu(struct perf_evlist *evlist, int prot, int m
 	return 0;
 
 out_unmap:
-	for (cpu = 0; cpu < nr_cpus; cpu++) {
-		if (evlist->mmap[cpu].base != NULL) {
-			munmap(evlist->mmap[cpu].base, evlist->mmap_len);
-			evlist->mmap[cpu].base = NULL;
-		}
-	}
+	for (cpu = 0; cpu < nr_cpus; cpu++)
+		__perf_evlist__munmap(evlist, cpu);
 	return -1;
 }
 
@@ -517,12 +517,8 @@ static int perf_evlist__mmap_per_thread(struct perf_evlist *evlist, int prot, in
 	return 0;
 
 out_unmap:
-	for (thread = 0; thread < nr_threads; thread++) {
-		if (evlist->mmap[thread].base != NULL) {
-			munmap(evlist->mmap[thread].base, evlist->mmap_len);
-			evlist->mmap[thread].base = NULL;
-		}
-	}
+	for (thread = 0; thread < nr_threads; thread++)
+		__perf_evlist__munmap(evlist, thread);
 	return -1;
 }
 
@@ -573,7 +569,7 @@ int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages,
 			return -ENOMEM;
 	}
 
-	if (cpu_map__all(cpus))
+	if (cpu_map__empty(cpus))
 		return perf_evlist__mmap_per_thread(evlist, prot, mask);
 
 	return perf_evlist__mmap_per_cpu(evlist, prot, mask);
@@ -838,7 +834,7 @@ int perf_evlist__prepare_workload(struct perf_evlist *evlist,
 int perf_evlist__start_workload(struct perf_evlist *evlist)
 {
 	if (evlist->workload.cork_fd > 0) {
-		char bf;
+		char bf = 0;
 		int ret;
 		/*
 		 * Remove the cork, let it rip!

tools/perf/util/evsel.c

@@ -9,17 +9,17 @@
 
 #include <byteswap.h>
 #include <linux/bitops.h>
-#include "asm/bug.h"
 #include <lk/debugfs.h>
-#include "event-parse.h"
+#include <traceevent/event-parse.h>
+#include <linux/hw_breakpoint.h>
+#include <linux/perf_event.h>
+#include "asm/bug.h"
 #include "evsel.h"
 #include "evlist.h"
 #include "util.h"
 #include "cpumap.h"
 #include "thread_map.h"
 #include "target.h"
-#include <linux/hw_breakpoint.h>
-#include <linux/perf_event.h>
 #include "perf_regs.h"
 
 static struct {

tools/perf/util/header.c

@@ -25,41 +25,9 @@
 
 static bool no_buildid_cache = false;
 
-static int trace_event_count;
-static struct perf_trace_event_type *trace_events;
-
 static u32 header_argc;
 static const char **header_argv;
 
-int perf_header__push_event(u64 id, const char *name)
-{
-	struct perf_trace_event_type *nevents;
-
-	if (strlen(name) > MAX_EVENT_NAME)
-		pr_warning("Event %s will be truncated\n", name);
-
-	nevents = realloc(trace_events, (trace_event_count + 1) * sizeof(*trace_events));
-	if (nevents == NULL)
-		return -ENOMEM;
-	trace_events = nevents;
-
-	memset(&trace_events[trace_event_count], 0, sizeof(struct perf_trace_event_type));
-	trace_events[trace_event_count].event_id = id;
-	strncpy(trace_events[trace_event_count].name, name, MAX_EVENT_NAME - 1);
-	trace_event_count++;
-	return 0;
-}
-
-char *perf_header__find_event(u64 id)
-{
-	int i;
-	for (i = 0 ; i < trace_event_count; i++) {
-		if (trace_events[i].event_id == id)
-			return trace_events[i].name;
-	}
-	return NULL;
-}
-
 /*
  * magic2 = "PERFILE2"
  * must be a numerical value to let the endianness
@@ -2257,7 +2225,7 @@ static int perf_header__adds_write(struct perf_header *header,
 
 	sec_size = sizeof(*feat_sec) * nr_sections;
 
-	sec_start = header->data_offset + header->data_size;
+	sec_start = header->feat_offset;
 	lseek(fd, sec_start + sec_size, SEEK_SET);
 
 	for_each_set_bit(feat, header->adds_features, HEADER_FEAT_BITS) {
@@ -2304,6 +2272,7 @@ int perf_session__write_header(struct perf_session *session,
 	struct perf_file_attr   f_attr;
 	struct perf_header *header = &session->header;
 	struct perf_evsel *evsel;
+	u64 attr_offset;
 	int err;
 
 	lseek(fd, sizeof(f_header), SEEK_SET);
@@ -2317,7 +2286,7 @@ int perf_session__write_header(struct perf_session *session,
 		}
 	}
 
-	header->attr_offset = lseek(fd, 0, SEEK_CUR);
+	attr_offset = lseek(fd, 0, SEEK_CUR);
 
 	list_for_each_entry(evsel, &evlist->entries, node) {
 		f_attr = (struct perf_file_attr){
@@ -2334,17 +2303,8 @@ int perf_session__write_header(struct perf_session *session,
 		}
 	}
 
-	header->event_offset = lseek(fd, 0, SEEK_CUR);
-	header->event_size = trace_event_count * sizeof(struct perf_trace_event_type);
-	if (trace_events) {
-		err = do_write(fd, trace_events, header->event_size);
-		if (err < 0) {
-			pr_debug("failed to write perf header events\n");
-			return err;
-		}
-	}
-
 	header->data_offset = lseek(fd, 0, SEEK_CUR);
+	header->feat_offset = header->data_offset + header->data_size;
 
 	if (at_exit) {
 		err = perf_header__adds_write(header, evlist, fd);
@@ -2357,17 +2317,14 @@ int perf_session__write_header(struct perf_session *session,
 		.size	   = sizeof(f_header),
 		.attr_size = sizeof(f_attr),
 		.attrs = {
-			.offset = header->attr_offset,
+			.offset = attr_offset,
 			.size   = evlist->nr_entries * sizeof(f_attr),
 		},
 		.data = {
 			.offset = header->data_offset,
 			.size	= header->data_size,
 		},
-		.event_types = {
-			.offset = header->event_offset,
-			.size	= header->event_size,
-		},
+		/* event_types is ignored, store zeros */
 	};
 
 	memcpy(&f_header.adds_features, &header->adds_features, sizeof(header->adds_features));
@@ -2417,7 +2374,7 @@ int perf_header__process_sections(struct perf_header *header, int fd,
 
 	sec_size = sizeof(*feat_sec) * nr_sections;
 
-	lseek(fd, header->data_offset + header->data_size, SEEK_SET);
+	lseek(fd, header->feat_offset, SEEK_SET);
 
 	err = perf_header__getbuffer64(header, fd, feat_sec, sec_size);
 	if (err < 0)
@@ -2523,6 +2480,7 @@ static int check_magic_endian(u64 magic, uint64_t hdr_sz,
 	/* check for legacy format */
 	ret = memcmp(&magic, __perf_magic1, sizeof(magic));
 	if (ret == 0) {
+		ph->version = PERF_HEADER_VERSION_1;
 		pr_debug("legacy perf.data format\n");
 		if (is_pipe)
 			return try_all_pipe_abis(hdr_sz, ph);
@@ -2544,6 +2502,7 @@ static int check_magic_endian(u64 magic, uint64_t hdr_sz,
 		return -1;
 
 	ph->needs_swap = true;
+	ph->version = PERF_HEADER_VERSION_2;
 
 	return 0;
 }
@@ -2614,10 +2573,9 @@ int perf_file_header__read(struct perf_file_header *header,
 	memcpy(&ph->adds_features, &header->adds_features,
 	       sizeof(ph->adds_features));
 
-	ph->event_offset = header->event_types.offset;
-	ph->event_size   = header->event_types.size;
 	ph->data_offset  = header->data.offset;
 	ph->data_size	 = header->data.size;
+	ph->feat_offset  = header->data.offset + header->data.size;
 	return 0;
 }
 
@@ -2666,19 +2624,17 @@ static int perf_file_header__read_pipe(struct perf_pipe_file_header *header,
 	return 0;
 }
 
-static int perf_header__read_pipe(struct perf_session *session, int fd)
+static int perf_header__read_pipe(struct perf_session *session)
 {
 	struct perf_header *header = &session->header;
 	struct perf_pipe_file_header f_header;
 
-	if (perf_file_header__read_pipe(&f_header, header, fd,
+	if (perf_file_header__read_pipe(&f_header, header, session->fd,
 					session->repipe) < 0) {
 		pr_debug("incompatible file format\n");
 		return -EINVAL;
 	}
 
-	session->fd = fd;
-
 	return 0;
 }
 
@@ -2772,20 +2728,21 @@ static int perf_evlist__prepare_tracepoint_events(struct perf_evlist *evlist,
 	return 0;
 }
 
-int perf_session__read_header(struct perf_session *session, int fd)
+int perf_session__read_header(struct perf_session *session)
 {
 	struct perf_header *header = &session->header;
 	struct perf_file_header	f_header;
 	struct perf_file_attr	f_attr;
 	u64			f_id;
 	int nr_attrs, nr_ids, i, j;
+	int fd = session->fd;
 
 	session->evlist = perf_evlist__new();
 	if (session->evlist == NULL)
 		return -ENOMEM;
 
 	if (session->fd_pipe)
-		return perf_header__read_pipe(session, fd);
+		return perf_header__read_pipe(session);
 
 	if (perf_file_header__read(&f_header, header, fd) < 0)
 		return -EINVAL;
@@ -2839,22 +2796,9 @@ int perf_session__read_header(struct perf_session *session, int fd)
 
 	symbol_conf.nr_events = nr_attrs;
 
-	if (f_header.event_types.size) {
-		lseek(fd, f_header.event_types.offset, SEEK_SET);
-		trace_events = malloc(f_header.event_types.size);
-		if (trace_events == NULL)
-			return -ENOMEM;
-		if (perf_header__getbuffer64(header, fd, trace_events,
-					     f_header.event_types.size))
-			goto out_errno;
-		trace_event_count =  f_header.event_types.size / sizeof(struct perf_trace_event_type);
-	}
-
 	perf_header__process_sections(header, fd, &session->pevent,
 				      perf_file_section__process);
 
-	lseek(fd, header->data_offset, SEEK_SET);
-
 	if (perf_evlist__prepare_tracepoint_events(session->evlist,
 						   session->pevent))
 		goto out_delete_evlist;
@@ -2922,7 +2866,8 @@ int perf_event__synthesize_attrs(struct perf_tool *tool,
 	return err;
 }
 
-int perf_event__process_attr(union perf_event *event,
+int perf_event__process_attr(struct perf_tool *tool __maybe_unused,
+			     union perf_event *event,
 			     struct perf_evlist **pevlist)
 {
 	u32 i, ids, n_ids;
@@ -2961,64 +2906,6 @@ int perf_event__process_attr(union perf_event *event,
 	return 0;
 }
 
-int perf_event__synthesize_event_type(struct perf_tool *tool,
-				      u64 event_id, char *name,
-				      perf_event__handler_t process,
-				      struct machine *machine)
-{
-	union perf_event ev;
-	size_t size = 0;
-	int err = 0;
-
-	memset(&ev, 0, sizeof(ev));
-
-	ev.event_type.event_type.event_id = event_id;
-	memset(ev.event_type.event_type.name, 0, MAX_EVENT_NAME);
-	strncpy(ev.event_type.event_type.name, name, MAX_EVENT_NAME - 1);
-
-	ev.event_type.header.type = PERF_RECORD_HEADER_EVENT_TYPE;
-	size = strlen(ev.event_type.event_type.name);
-	size = PERF_ALIGN(size, sizeof(u64));
-	ev.event_type.header.size = sizeof(ev.event_type) -
-		(sizeof(ev.event_type.event_type.name) - size);
-
-	err = process(tool, &ev, NULL, machine);
-
-	return err;
-}
-
-int perf_event__synthesize_event_types(struct perf_tool *tool,
-				       perf_event__handler_t process,
-				       struct machine *machine)
-{
-	struct perf_trace_event_type *type;
-	int i, err = 0;
-
-	for (i = 0; i < trace_event_count; i++) {
-		type = &trace_events[i];
-
-		err = perf_event__synthesize_event_type(tool, type->event_id,
-							type->name, process,
-							machine);
-		if (err) {
-			pr_debug("failed to create perf header event type\n");
-			return err;
-		}
-	}
-
-	return err;
-}
-
-int perf_event__process_event_type(struct perf_tool *tool __maybe_unused,
-				   union perf_event *event)
-{
-	if (perf_header__push_event(event->event_type.event_type.event_id,
-				    event->event_type.event_type.name) < 0)
-		return -ENOMEM;
-
-	return 0;
-}
-
 int perf_event__synthesize_tracing_data(struct perf_tool *tool, int fd,
 					struct perf_evlist *evlist,
 					perf_event__handler_t process)
@@ -3065,7 +2952,8 @@ int perf_event__synthesize_tracing_data(struct perf_tool *tool, int fd,
 	return aligned_size;
 }
 
-int perf_event__process_tracing_data(union perf_event *event,
+int perf_event__process_tracing_data(struct perf_tool *tool __maybe_unused,
+				     union perf_event *event,
 				     struct perf_session *session)
 {
 	ssize_t size_read, padding, size = event->tracing_data.size;

tools/perf/util/header.h

@@ -34,6 +34,11 @@ enum {
 	HEADER_FEAT_BITS	= 256,
 };
 
+enum perf_header_version {
+	PERF_HEADER_VERSION_1,
+	PERF_HEADER_VERSION_2,
+};
+
 struct perf_file_section {
 	u64 offset;
 	u64 size;
@@ -45,6 +50,7 @@ struct perf_file_header {
 	u64				attr_size;
 	struct perf_file_section	attrs;
 	struct perf_file_section	data;
+	/* event_types is ignored */
 	struct perf_file_section	event_types;
 	DECLARE_BITMAP(adds_features, HEADER_FEAT_BITS);
 };
@@ -84,28 +90,24 @@ struct perf_session_env {
 };
 
 struct perf_header {
-	bool			needs_swap;
-	s64			attr_offset;
-	u64			data_offset;
-	u64			data_size;
-	u64			event_offset;
-	u64			event_size;
+	enum perf_header_version	version;
+	bool				needs_swap;
+	u64				data_offset;
+	u64				data_size;
+	u64				feat_offset;
 	DECLARE_BITMAP(adds_features, HEADER_FEAT_BITS);
-	struct perf_session_env env;
+	struct perf_session_env 	env;
 };
 
 struct perf_evlist;
 struct perf_session;
 
-int perf_session__read_header(struct perf_session *session, int fd);
+int perf_session__read_header(struct perf_session *session);
 int perf_session__write_header(struct perf_session *session,
 			       struct perf_evlist *evlist,
 			       int fd, bool at_exit);
 int perf_header__write_pipe(int fd);
 
-int perf_header__push_event(u64 id, const char *name);
-char *perf_header__find_event(u64 id);
-
 void perf_header__set_feat(struct perf_header *header, int feat);
 void perf_header__clear_feat(struct perf_header *header, int feat);
 bool perf_header__has_feat(const struct perf_header *header, int feat);
@@ -130,22 +132,14 @@ int perf_event__synthesize_attr(struct perf_tool *tool,
 int perf_event__synthesize_attrs(struct perf_tool *tool,
 				 struct perf_session *session,
 				 perf_event__handler_t process);
-int perf_event__process_attr(union perf_event *event, struct perf_evlist **pevlist);
-
-int perf_event__synthesize_event_type(struct perf_tool *tool,
-				      u64 event_id, char *name,
-				      perf_event__handler_t process,
-				      struct machine *machine);
-int perf_event__synthesize_event_types(struct perf_tool *tool,
-				       perf_event__handler_t process,
-				       struct machine *machine);
-int perf_event__process_event_type(struct perf_tool *tool,
-				   union perf_event *event);
+int perf_event__process_attr(struct perf_tool *tool, union perf_event *event,
+			     struct perf_evlist **pevlist);
 
 int perf_event__synthesize_tracing_data(struct perf_tool *tool,
 					int fd, struct perf_evlist *evlist,
 					perf_event__handler_t process);
-int perf_event__process_tracing_data(union perf_event *event,
+int perf_event__process_tracing_data(struct perf_tool *tool,
+				     union perf_event *event,
 				     struct perf_session *session);
 
 int perf_event__synthesize_build_id(struct perf_tool *tool,

tools/perf/util/hist.c

@@ -912,6 +912,7 @@ static struct hist_entry *hists__add_dummy_entry(struct hists *hists,
 		rb_link_node(&he->rb_node_in, parent, p);
 		rb_insert_color(&he->rb_node_in, root);
 		hists__inc_nr_entries(hists, he);
+		he->dummy = true;
 	}
 out:
 	return he;

tools/perf/util/hist.h

@@ -141,10 +141,12 @@ struct perf_hpp {
 };
 
 struct perf_hpp_fmt {
-	int (*header)(struct perf_hpp *hpp);
-	int (*width)(struct perf_hpp *hpp);
-	int (*color)(struct perf_hpp *hpp, struct hist_entry *he);
-	int (*entry)(struct perf_hpp *hpp, struct hist_entry *he);
+	int (*header)(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp);
+	int (*width)(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp);
+	int (*color)(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
+		     struct hist_entry *he);
+	int (*entry)(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
+		     struct hist_entry *he);
 
 	struct list_head list;
 };
@@ -157,7 +159,7 @@ extern struct list_head perf_hpp__list;
 extern struct perf_hpp_fmt perf_hpp__format[];
 
 enum {
-	PERF_HPP__BASELINE,
+	/* Matches perf_hpp__format array. */
 	PERF_HPP__OVERHEAD,
 	PERF_HPP__OVERHEAD_SYS,
 	PERF_HPP__OVERHEAD_US,
@@ -165,11 +167,6 @@ enum {
 	PERF_HPP__OVERHEAD_GUEST_US,
 	PERF_HPP__SAMPLES,
 	PERF_HPP__PERIOD,
-	PERF_HPP__PERIOD_BASELINE,
-	PERF_HPP__DELTA,
-	PERF_HPP__RATIO,
-	PERF_HPP__WEIGHTED_DIFF,
-	PERF_HPP__FORMULA,
 
 	PERF_HPP__MAX_INDEX
 };
@@ -177,8 +174,6 @@ enum {
 void perf_hpp__init(void);
 void perf_hpp__column_register(struct perf_hpp_fmt *format);
 void perf_hpp__column_enable(unsigned col);
-int hist_entry__period_snprintf(struct perf_hpp *hpp, struct hist_entry *he,
-				bool color);
 
 struct perf_evlist;
 
@@ -245,11 +240,4 @@ int perf_evlist__gtk_browse_hists(struct perf_evlist *evlist __maybe_unused,
 #endif
 
 unsigned int hists__sort_list_width(struct hists *self);
-
-double perf_diff__compute_delta(struct hist_entry *he, struct hist_entry *pair);
-double perf_diff__compute_ratio(struct hist_entry *he, struct hist_entry *pair);
-s64 perf_diff__compute_wdiff(struct hist_entry *he, struct hist_entry *pair);
-int perf_diff__formula(struct hist_entry *he, struct hist_entry *pair,
-		       char *buf, size_t size);
-double perf_diff__period_percent(struct hist_entry *he, u64 period);
 #endif	/* __PERF_HIST_H */

tools/perf/util/include/linux/string.h

 #include <string.h>
 
 void *memdup(const void *src, size_t len);
+int str_append(char **s, int *len, const char *a);

tools/perf/util/machine.c

@@ -233,7 +233,7 @@ void machines__set_id_hdr_size(struct machines *machines, u16 id_hdr_size)
 	return;
 }
 
-static struct thread *__machine__findnew_thread(struct machine *machine, pid_t pid,
+static struct thread *__machine__findnew_thread(struct machine *machine, pid_t tid,
 						bool create)
 {
 	struct rb_node **p = &machine->threads.rb_node;
@@ -241,23 +241,23 @@ static struct thread *__machine__findnew_thread(struct machine *machine, pid_t p
 	struct thread *th;
 
 	/*
-	 * Font-end cache - PID lookups come in blocks,
+	 * Front-end cache - TID lookups come in blocks,
 	 * so most of the time we dont have to look up
 	 * the full rbtree:
 	 */
-	if (machine->last_match && machine->last_match->pid == pid)
+	if (machine->last_match && machine->last_match->tid == tid)
 		return machine->last_match;
 
 	while (*p != NULL) {
 		parent = *p;
 		th = rb_entry(parent, struct thread, rb_node);
 
-		if (th->pid == pid) {
+		if (th->tid == tid) {
 			machine->last_match = th;
 			return th;
 		}
 
-		if (pid < th->pid)
+		if (tid < th->tid)
 			p = &(*p)->rb_left;
 		else
 			p = &(*p)->rb_right;
@@ -266,7 +266,7 @@ static struct thread *__machine__findnew_thread(struct machine *machine, pid_t p
 	if (!create)
 		return NULL;
 
-	th = thread__new(pid);
+	th = thread__new(tid);
 	if (th != NULL) {
 		rb_link_node(&th->rb_node, parent, p);
 		rb_insert_color(&th->rb_node, &machine->threads);
@@ -276,14 +276,14 @@ static struct thread *__machine__findnew_thread(struct machine *machine, pid_t p
 	return th;
 }
 
-struct thread *machine__findnew_thread(struct machine *machine, pid_t pid)
+struct thread *machine__findnew_thread(struct machine *machine, pid_t tid)
 {
-	return __machine__findnew_thread(machine, pid, true);
+	return __machine__findnew_thread(machine, tid, true);
 }
 
-struct thread *machine__find_thread(struct machine *machine, pid_t pid)
+struct thread *machine__find_thread(struct machine *machine, pid_t tid)
 {
-	return __machine__findnew_thread(machine, pid, false);
+	return __machine__findnew_thread(machine, tid, false);
 }
 
 int machine__process_comm_event(struct machine *machine, union perf_event *event)
@@ -1058,11 +1058,10 @@ int machine__process_event(struct machine *machine, union perf_event *event)
 	return ret;
 }
 
-static bool symbol__match_parent_regex(struct symbol *sym)
+static bool symbol__match_regex(struct symbol *sym, regex_t *regex)
 {
-	if (sym->name && !regexec(&parent_regex, sym->name, 0, NULL, 0))
+	if (sym->name && !regexec(regex, sym->name, 0, NULL, 0))
 		return 1;
-
 	return 0;
 }
 
@@ -1159,8 +1158,8 @@ struct branch_info *machine__resolve_bstack(struct machine *machine,
 static int machine__resolve_callchain_sample(struct machine *machine,
 					     struct thread *thread,
 					     struct ip_callchain *chain,
-					     struct symbol **parent)
-
+					     struct symbol **parent,
+					     struct addr_location *root_al)
 {
 	u8 cpumode = PERF_RECORD_MISC_USER;
 	unsigned int i;
@@ -1211,8 +1210,15 @@ static int machine__resolve_callchain_sample(struct machine *machine,
 					   MAP__FUNCTION, ip, &al, NULL);
 		if (al.sym != NULL) {
 			if (sort__has_parent && !*parent &&
-			    symbol__match_parent_regex(al.sym))
+			    symbol__match_regex(al.sym, &parent_regex))
 				*parent = al.sym;
+			else if (have_ignore_callees && root_al &&
+			  symbol__match_regex(al.sym, &ignore_callees_regex)) {
+				/* Treat this symbol as the root,
+				   forgetting its callees. */
+				*root_al = al;
+				callchain_cursor_reset(&callchain_cursor);
+			}
 			if (!symbol_conf.use_callchain)
 				break;
 		}
@@ -1237,15 +1243,13 @@ int machine__resolve_callchain(struct machine *machine,
 			       struct perf_evsel *evsel,
 			       struct thread *thread,
 			       struct perf_sample *sample,
-			       struct symbol **parent)
-
+			       struct symbol **parent,
+			       struct addr_location *root_al)
 {
 	int ret;
 
-	callchain_cursor_reset(&callchain_cursor);
-
 	ret = machine__resolve_callchain_sample(machine, thread,
-						sample->callchain, parent);
+						sample->callchain, parent, root_al);
 	if (ret)
 		return ret;
 

tools/perf/util/machine.h

@@ -5,6 +5,7 @@
 #include <linux/rbtree.h>
 #include "map.h"
 
+struct addr_location;
 struct branch_stack;
 struct perf_evsel;
 struct perf_sample;
@@ -36,7 +37,7 @@ struct map *machine__kernel_map(struct machine *machine, enum map_type type)
 	return machine->vmlinux_maps[type];
 }
 
-struct thread *machine__find_thread(struct machine *machine, pid_t pid);
+struct thread *machine__find_thread(struct machine *machine, pid_t tid);
 
 int machine__process_comm_event(struct machine *machine, union perf_event *event);
 int machine__process_exit_event(struct machine *machine, union perf_event *event);
@@ -83,7 +84,8 @@ int machine__resolve_callchain(struct machine *machine,
 			       struct perf_evsel *evsel,
 			       struct thread *thread,
 			       struct perf_sample *sample,
-			       struct symbol **parent);
+			       struct symbol **parent,
+			       struct addr_location *root_al);
 
 /*
  * Default guest kernel is defined by parameter --guestkallsyms
@@ -99,7 +101,7 @@ static inline bool machine__is_host(struct machine *machine)
 	return machine ? machine->pid == HOST_KERNEL_ID : false;
 }
 
-struct thread *machine__findnew_thread(struct machine *machine, pid_t pid);
+struct thread *machine__findnew_thread(struct machine *machine, pid_t tid);
 
 size_t machine__fprintf(struct machine *machine, FILE *fp);
 

tools/perf/util/parse-events.h

@@ -23,6 +23,7 @@ struct tracepoint_path {
 };
 
 extern struct tracepoint_path *tracepoint_id_to_path(u64 config);
+extern struct tracepoint_path *tracepoint_name_to_path(const char *name);
 extern bool have_tracepoints(struct list_head *evlist);
 
 const char *event_type(int type);
@@ -84,16 +85,16 @@ void parse_events__free_terms(struct list_head *terms);
 int parse_events__modifier_event(struct list_head *list, char *str, bool add);
 int parse_events__modifier_group(struct list_head *list, char *event_mod);
 int parse_events_name(struct list_head *list, char *name);
-int parse_events_add_tracepoint(struct list_head **list, int *idx,
+int parse_events_add_tracepoint(struct list_head *list, int *idx,
 				char *sys, char *event);
-int parse_events_add_numeric(struct list_head **list, int *idx,
+int parse_events_add_numeric(struct list_head *list, int *idx,
 			     u32 type, u64 config,
 			     struct list_head *head_config);
-int parse_events_add_cache(struct list_head **list, int *idx,
+int parse_events_add_cache(struct list_head *list, int *idx,
 			   char *type, char *op_result1, char *op_result2);
-int parse_events_add_breakpoint(struct list_head **list, int *idx,
+int parse_events_add_breakpoint(struct list_head *list, int *idx,
 				void *ptr, char *type);
-int parse_events_add_pmu(struct list_head **list, int *idx,
+int parse_events_add_pmu(struct list_head *list, int *idx,
 			 char *pmu , struct list_head *head_config);
 void parse_events__set_leader(char *name, struct list_head *list);
 void parse_events_update_lists(struct list_head *list_event,

tools/perf/util/parse-events.y

@@ -22,6 +22,13 @@ do { \
 		YYABORT; \
 } while (0)
 
+#define ALLOC_LIST(list) \
+do { \
+	list = malloc(sizeof(*list)); \
+	ABORT_ON(!list);              \
+	INIT_LIST_HEAD(list);         \
+} while (0)
+
 static inc_group_count(struct list_head *list,
 		       struct parse_events_evlist *data)
 {
@@ -196,9 +203,10 @@ event_pmu:
 PE_NAME '/' event_config '/'
 {
 	struct parse_events_evlist *data = _data;
-	struct list_head *list = NULL;
+	struct list_head *list;
 
-	ABORT_ON(parse_events_add_pmu(&list, &data->idx, $1, $3));
+	ALLOC_LIST(list);
+	ABORT_ON(parse_events_add_pmu(list, &data->idx, $1, $3));
 	parse_events__free_terms($3);
 	$$ = list;
 }
@@ -212,11 +220,12 @@ event_legacy_symbol:
 value_sym '/' event_config '/'
 {
 	struct parse_events_evlist *data = _data;
-	struct list_head *list = NULL;
+	struct list_head *list;
 	int type = $1 >> 16;
 	int config = $1 & 255;
 
-	ABORT_ON(parse_events_add_numeric(&list, &data->idx,
+	ALLOC_LIST(list);
+	ABORT_ON(parse_events_add_numeric(list, &data->idx,
 					  type, config, $3));
 	parse_events__free_terms($3);
 	$$ = list;
@@ -225,11 +234,12 @@ value_sym '/' event_config '/'
 value_sym sep_slash_dc
 {
 	struct parse_events_evlist *data = _data;
-	struct list_head *list = NULL;
+	struct list_head *list;
 	int type = $1 >> 16;
 	int config = $1 & 255;
 
-	ABORT_ON(parse_events_add_numeric(&list, &data->idx,
+	ALLOC_LIST(list);
+	ABORT_ON(parse_events_add_numeric(list, &data->idx,
 					  type, config, NULL));
 	$$ = list;
 }
@@ -238,27 +248,30 @@ event_legacy_cache:
 PE_NAME_CACHE_TYPE '-' PE_NAME_CACHE_OP_RESULT '-' PE_NAME_CACHE_OP_RESULT
 {
 	struct parse_events_evlist *data = _data;
-	struct list_head *list = NULL;
+	struct list_head *list;
 
-	ABORT_ON(parse_events_add_cache(&list, &data->idx, $1, $3, $5));
+	ALLOC_LIST(list);
+	ABORT_ON(parse_events_add_cache(list, &data->idx, $1, $3, $5));
 	$$ = list;
 }
 |
 PE_NAME_CACHE_TYPE '-' PE_NAME_CACHE_OP_RESULT
 {
 	struct parse_events_evlist *data = _data;
-	struct list_head *list = NULL;
+	struct list_head *list;
 
-	ABORT_ON(parse_events_add_cache(&list, &data->idx, $1, $3, NULL));
+	ALLOC_LIST(list);
+	ABORT_ON(parse_events_add_cache(list, &data->idx, $1, $3, NULL));
 	$$ = list;
 }
 |
 PE_NAME_CACHE_TYPE
 {
 	struct parse_events_evlist *data = _data;
-	struct list_head *list = NULL;
+	struct list_head *list;
 
-	ABORT_ON(parse_events_add_cache(&list, &data->idx, $1, NULL, NULL));
+	ALLOC_LIST(list);
+	ABORT_ON(parse_events_add_cache(list, &data->idx, $1, NULL, NULL));
 	$$ = list;
 }
 
@@ -266,9 +279,10 @@ event_legacy_mem:
 PE_PREFIX_MEM PE_VALUE ':' PE_MODIFIER_BP sep_dc
 {
 	struct parse_events_evlist *data = _data;
-	struct list_head *list = NULL;
+	struct list_head *list;
 
-	ABORT_ON(parse_events_add_breakpoint(&list, &data->idx,
+	ALLOC_LIST(list);
+	ABORT_ON(parse_events_add_breakpoint(list, &data->idx,
 					     (void *) $2, $4));
 	$$ = list;
 }
@@ -276,9 +290,10 @@ PE_PREFIX_MEM PE_VALUE ':' PE_MODIFIER_BP sep_dc
 PE_PREFIX_MEM PE_VALUE sep_dc
 {
 	struct parse_events_evlist *data = _data;
-	struct list_head *list = NULL;
+	struct list_head *list;
 
-	ABORT_ON(parse_events_add_breakpoint(&list, &data->idx,
+	ALLOC_LIST(list);
+	ABORT_ON(parse_events_add_breakpoint(list, &data->idx,
 					     (void *) $2, NULL));
 	$$ = list;
 }
@@ -287,9 +302,10 @@ event_legacy_tracepoint:
 PE_NAME ':' PE_NAME
 {
 	struct parse_events_evlist *data = _data;
-	struct list_head *list = NULL;
+	struct list_head *list;
 
-	ABORT_ON(parse_events_add_tracepoint(&list, &data->idx, $1, $3));
+	ALLOC_LIST(list);
+	ABORT_ON(parse_events_add_tracepoint(list, &data->idx, $1, $3));
 	$$ = list;
 }
 
@@ -297,9 +313,10 @@ event_legacy_numeric:
 PE_VALUE ':' PE_VALUE
 {
 	struct parse_events_evlist *data = _data;
-	struct list_head *list = NULL;
+	struct list_head *list;
 
-	ABORT_ON(parse_events_add_numeric(&list, &data->idx, (u32)$1, $3, NULL));
+	ALLOC_LIST(list);
+	ABORT_ON(parse_events_add_numeric(list, &data->idx, (u32)$1, $3, NULL));
 	$$ = list;
 }
 
@@ -307,9 +324,10 @@ event_legacy_raw:
 PE_RAW
 {
 	struct parse_events_evlist *data = _data;
-	struct list_head *list = NULL;
+	struct list_head *list;
 
-	ABORT_ON(parse_events_add_numeric(&list, &data->idx,
+	ALLOC_LIST(list);
+	ABORT_ON(parse_events_add_numeric(list, &data->idx,
 					  PERF_TYPE_RAW, $1, NULL));
 	$$ = list;
 }