Merge tag 'perf-core-for-mingo-20160929' 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:

User visible changes:
---------------------

New features:

- Add support for using symbols in address filters with Intel PT and ARM
  CoreSight (hardware assisted tracing facilities) (Adrian Hunter, Mathieu Poirier)

Fixes:

- Fix MMAP event synthesis for pre-existing threads when no hugetlbfs
  mount is in place (Adrian Hunter)

- Don't ignore kernel idle symbols in 'perf script' (Adrian Hunter)

- Assorted Intel PT fixes (Adrian Hunter)

Improvements:

- Fix handling of C++ symbols in 'perf probe' (Masami Hiramatsu)

- Beautify sched_[gs]et_attr return value in 'perf trace' (Arnaldo Carvalho de Melo)

Infrastructure changes:
-----------------------

New features:

- Add dwarf unwind 'perf test' for powerpc (Ravi Bangoria)

Fixes:

- Fix error paths in 'perf record' (Adrian Hunter)

Documentation:

- Update documentation info about quipper, a C++ parser for converting
  to/from perf.data/chromium profiling format (Simon Que)

Build Fixes:

  Fix building in 32 bit platform with libbabeltrace (Wang Nan)

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

34 files changed, 1451 insertions, 62 deletions

diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt
index 1a24f4d64328..92335193dc33 100644
--- a/tools/perf/Documentation/perf-record.txt
+++ b/tools/perf/Documentation/perf-record.txt
@@ -35,15 +35,15 @@ OPTIONS
 
 	- a symbolically formed PMU event like 'pmu/param1=0x3,param2/' where
 	  'param1', 'param2', etc are defined as formats for the PMU in
-	  /sys/bus/event_sources/devices/<pmu>/format/*.
+	  /sys/bus/event_source/devices/<pmu>/format/*.
 
 	- a symbolically formed event like 'pmu/config=M,config1=N,config3=K/'
 
           where M, N, K are numbers (in decimal, hex, octal format). Acceptable
           values for each of 'config', 'config1' and 'config2' are defined by
-          corresponding entries in /sys/bus/event_sources/devices/<pmu>/format/*
+          corresponding entries in /sys/bus/event_source/devices/<pmu>/format/*
           param1 and param2 are defined as formats for the PMU in:
-          /sys/bus/event_sources/devices/<pmu>/format/*
+          /sys/bus/event_source/devices/<pmu>/format/*
 
 	  There are also some params which are not defined in .../<pmu>/format/*.
 	  These params can be used to overload default config values per event.
@@ -89,9 +89,62 @@ OPTIONS
 
 --filter=<filter>::
         Event filter. This option should follow a event selector (-e) which
-	selects tracepoint event(s). Multiple '--filter' options are combined
+	selects either tracepoint event(s) or a hardware trace PMU
+	(e.g. Intel PT or CoreSight).
+
+	- tracepoint filters
+
+	In the case of tracepoints, multiple '--filter' options are combined
 	using '&&'.
 
+	- address filters
+
+	A hardware trace PMU advertises its ability to accept a number of
+	address filters	by specifying a non-zero value in
+	/sys/bus/event_source/devices/<pmu>/nr_addr_filters.
+
+	Address filters have the format:
+
+	filter|start|stop|tracestop <start> [/ <size>] [@<file name>]
+
+	Where:
+	- 'filter': defines a region that will be traced.
+	- 'start': defines an address at which tracing will begin.
+	- 'stop': defines an address at which tracing will stop.
+	- 'tracestop': defines a region in which tracing will stop.
+
+	<file name> is the name of the object file, <start> is the offset to the
+	code to trace in that file, and <size> is the size of the region to
+	trace. 'start' and 'stop' filters need not specify a <size>.
+
+	If no object file is specified then the kernel is assumed, in which case
+	the start address must be a current kernel memory address.
+
+	<start> can also be specified by providing the name of a symbol. If the
+	symbol name is not unique, it can be disambiguated by inserting #n where
+	'n' selects the n'th symbol in address order. Alternately #0, #g or #G
+	select only a global symbol. <size> can also be specified by providing
+	the name of a symbol, in which case the size is calculated to the end
+	of that symbol. For 'filter' and 'tracestop' filters, if <size> is
+	omitted and <start> is a symbol, then the size is calculated to the end
+	of that symbol.
+
+	If <size> is omitted and <start> is '*', then the start and size will
+	be calculated from the first and last symbols, i.e. to trace the whole
+	file.
+
+	If symbol names (or '*') are provided, they must be surrounded by white
+	space.
+
+	The filter passed to the kernel is not necessarily the same as entered.
+	To see the filter that is passed, use the -v option.
+
+	The kernel may not be able to configure a trace region if it is not
+	within a single mapping.  MMAP events (or /proc/<pid>/maps) can be
+	examined to determine if that is a possibility.
+
+	Multiple filters can be separated with space or comma.
+
 --exclude-perf::
 	Don't record events issued by perf itself. This option should follow
 	a event selector (-e) which selects tracepoint event(s). It adds a
diff --git a/tools/perf/Documentation/perf.data-file-format.txt b/tools/perf/Documentation/perf.data-file-format.txt
index fdc99fe6bbc3..b664b18d3991 100644
--- a/tools/perf/Documentation/perf.data-file-format.txt
+++ b/tools/perf/Documentation/perf.data-file-format.txt
@@ -437,6 +437,10 @@ in pmu-tools parser. This allows to read perf.data from python and dump it.
 quipper
 
 The quipper C++ parser is available at
-https://chromium.googlesource.com/chromiumos/platform/chromiumos-wide-profiling/
+https://chromium.googlesource.com/chromiumos/platform2
+
+It is under the chromiumos-wide-profiling/ subdirectory. This library can
+convert a perf data file to a protobuf and vice versa.
+
 Unfortunately this parser tends to be many versions behind and may not be able
 to parse data files generated by recent perf.
diff --git a/tools/perf/arch/powerpc/Build b/tools/perf/arch/powerpc/Build
index 54afe4a467e7..db52fa22d3a1 100644
--- a/tools/perf/arch/powerpc/Build
+++ b/tools/perf/arch/powerpc/Build
@@ -1 +1,2 @@
 libperf-y += util/
+libperf-y += tests/
diff --git a/tools/perf/arch/powerpc/include/arch-tests.h b/tools/perf/arch/powerpc/include/arch-tests.h
new file mode 100644
index 000000000000..84d8dedef2ed
--- /dev/null
+++ b/tools/perf/arch/powerpc/include/arch-tests.h
@@ -0,0 +1,13 @@
+#ifndef ARCH_TESTS_H
+#define ARCH_TESTS_H
+
+#ifdef HAVE_DWARF_UNWIND_SUPPORT
+struct thread;
+struct perf_sample;
+int test__arch_unwind_sample(struct perf_sample *sample,
+			     struct thread *thread);
+#endif
+
+extern struct test arch_tests[];
+
+#endif
diff --git a/tools/perf/arch/powerpc/include/perf_regs.h b/tools/perf/arch/powerpc/include/perf_regs.h
index 75de0e92e71e..c12f4e804f66 100644
--- a/tools/perf/arch/powerpc/include/perf_regs.h
+++ b/tools/perf/arch/powerpc/include/perf_regs.h
@@ -5,6 +5,8 @@
 #include <linux/types.h>
 #include <asm/perf_regs.h>
 
+void perf_regs_load(u64 *regs);
+
 #define PERF_REGS_MASK  ((1ULL << PERF_REG_POWERPC_MAX) - 1)
 #define PERF_REGS_MAX   PERF_REG_POWERPC_MAX
 #ifdef __powerpc64__
diff --git a/tools/perf/arch/powerpc/tests/Build b/tools/perf/arch/powerpc/tests/Build
new file mode 100644
index 000000000000..d827ef384b33
--- /dev/null
+++ b/tools/perf/arch/powerpc/tests/Build
@@ -0,0 +1,4 @@
+libperf-$(CONFIG_DWARF_UNWIND) += regs_load.o
+libperf-$(CONFIG_DWARF_UNWIND) += dwarf-unwind.o
+
+libperf-y += arch-tests.o
diff --git a/tools/perf/arch/powerpc/tests/arch-tests.c b/tools/perf/arch/powerpc/tests/arch-tests.c
new file mode 100644
index 000000000000..e24f46241f40
--- /dev/null
+++ b/tools/perf/arch/powerpc/tests/arch-tests.c
@@ -0,0 +1,15 @@
+#include <string.h>
+#include "tests/tests.h"
+#include "arch-tests.h"
+
+struct test arch_tests[] = {
+#ifdef HAVE_DWARF_UNWIND_SUPPORT
+	{
+		.desc = "Test dwarf unwind",
+		.func = test__dwarf_unwind,
+	},
+#endif
+	{
+		.func = NULL,
+	},
+};
diff --git a/tools/perf/arch/powerpc/tests/dwarf-unwind.c b/tools/perf/arch/powerpc/tests/dwarf-unwind.c
new file mode 100644
index 000000000000..0bac3137ccbd
--- /dev/null
+++ b/tools/perf/arch/powerpc/tests/dwarf-unwind.c
@@ -0,0 +1,62 @@
+#include <string.h>
+#include "perf_regs.h"
+#include "thread.h"
+#include "map.h"
+#include "event.h"
+#include "debug.h"
+#include "tests/tests.h"
+#include "arch-tests.h"
+
+#define STACK_SIZE 8192
+
+static int sample_ustack(struct perf_sample *sample,
+			 struct thread *thread, u64 *regs)
+{
+	struct stack_dump *stack = &sample->user_stack;
+	struct map *map;
+	unsigned long sp;
+	u64 stack_size, *buf;
+
+	buf = malloc(STACK_SIZE);
+	if (!buf) {
+		pr_debug("failed to allocate sample uregs data\n");
+		return -1;
+	}
+
+	sp = (unsigned long) regs[PERF_REG_POWERPC_R1];
+
+	map = map_groups__find(thread->mg, MAP__VARIABLE, (u64) sp);
+	if (!map) {
+		pr_debug("failed to get stack map\n");
+		free(buf);
+		return -1;
+	}
+
+	stack_size = map->end - sp;
+	stack_size = stack_size > STACK_SIZE ? STACK_SIZE : stack_size;
+
+	memcpy(buf, (void *) sp, stack_size);
+	stack->data = (char *) buf;
+	stack->size = stack_size;
+	return 0;
+}
+
+int test__arch_unwind_sample(struct perf_sample *sample,
+			     struct thread *thread)
+{
+	struct regs_dump *regs = &sample->user_regs;
+	u64 *buf;
+
+	buf = calloc(1, sizeof(u64) * PERF_REGS_MAX);
+	if (!buf) {
+		pr_debug("failed to allocate sample uregs data\n");
+		return -1;
+	}
+
+	perf_regs_load(buf);
+	regs->abi  = PERF_SAMPLE_REGS_ABI;
+	regs->regs = buf;
+	regs->mask = PERF_REGS_MASK;
+
+	return sample_ustack(sample, thread, buf);
+}
diff --git a/tools/perf/arch/powerpc/tests/regs_load.S b/tools/perf/arch/powerpc/tests/regs_load.S
new file mode 100644
index 000000000000..d76c9a32f327
--- /dev/null
+++ b/tools/perf/arch/powerpc/tests/regs_load.S
@@ -0,0 +1,94 @@
+#include <linux/linkage.h>
+
+/* Offset is based on macros from arch/powerpc/include/uapi/asm/ptrace.h. */
+#define R0	 0
+#define R1	 1 * 8
+#define R2	 2 * 8
+#define R3	 3 * 8
+#define R4	 4 * 8
+#define R5	 5 * 8
+#define R6	 6 * 8
+#define R7	 7 * 8
+#define R8	 8 * 8
+#define R9	 9 * 8
+#define R10	10 * 8
+#define R11	11 * 8
+#define R12	12 * 8
+#define R13	13 * 8
+#define R14	14 * 8
+#define R15	15 * 8
+#define R16	16 * 8
+#define R17	17 * 8
+#define R18	18 * 8
+#define R19	19 * 8
+#define R20	20 * 8
+#define R21	21 * 8
+#define R22	22 * 8
+#define R23	23 * 8
+#define R24	24 * 8
+#define R25	25 * 8
+#define R26	26 * 8
+#define R27	27 * 8
+#define R28	28 * 8
+#define R29	29 * 8
+#define R30	30 * 8
+#define R31	31 * 8
+#define NIP	32 * 8
+#define CTR	35 * 8
+#define LINK	36 * 8
+#define XER	37 * 8
+
+.globl perf_regs_load
+perf_regs_load:
+	std 0, R0(3)
+	std 1, R1(3)
+	std 2, R2(3)
+	std 3, R3(3)
+	std 4, R4(3)
+	std 5, R5(3)
+	std 6, R6(3)
+	std 7, R7(3)
+	std 8, R8(3)
+	std 9, R9(3)
+	std 10, R10(3)
+	std 11, R11(3)
+	std 12, R12(3)
+	std 13, R13(3)
+	std 14, R14(3)
+	std 15, R15(3)
+	std 16, R16(3)
+	std 17, R17(3)
+	std 18, R18(3)
+	std 19, R19(3)
+	std 20, R20(3)
+	std 21, R21(3)
+	std 22, R22(3)
+	std 23, R23(3)
+	std 24, R24(3)
+	std 25, R25(3)
+	std 26, R26(3)
+	std 27, R27(3)
+	std 28, R28(3)
+	std 29, R29(3)
+	std 30, R30(3)
+	std 31, R31(3)
+
+	/* store NIP */
+	mflr 4
+	std 4, NIP(3)
+
+	/* Store LR */
+	std 4, LINK(3)
+
+	/* Store XER */
+	mfxer 4
+	std 4, XER(3)
+
+	/* Store CTR */
+	mfctr 4
+	std 4, CTR(3)
+
+	/* Restore original value of r4 */
+	ld 4, R4(3)
+
+	blr
diff --git a/tools/perf/arch/x86/util/intel-pt.c b/tools/perf/arch/x86/util/intel-pt.c
index a2412e9d883b..90fa2286edcf 100644
--- a/tools/perf/arch/x86/util/intel-pt.c
+++ b/tools/perf/arch/x86/util/intel-pt.c
@@ -62,6 +62,7 @@ struct intel_pt_recording {
 	size_t				snapshot_ref_buf_size;
 	int				snapshot_ref_cnt;
 	struct intel_pt_snapshot_ref	*snapshot_refs;
+	size_t				priv_size;
 };
 
 static int intel_pt_parse_terms_with_default(struct list_head *formats,
@@ -273,11 +274,37 @@ intel_pt_pmu_default_config(struct perf_pmu *intel_pt_pmu)
 	return attr;
 }
 
+static const char *intel_pt_find_filter(struct perf_evlist *evlist,
+					struct perf_pmu *intel_pt_pmu)
+{
+	struct perf_evsel *evsel;
+
+	evlist__for_each_entry(evlist, evsel) {
+		if (evsel->attr.type == intel_pt_pmu->type)
+			return evsel->filter;
+	}
+
+	return NULL;
+}
+
+static size_t intel_pt_filter_bytes(const char *filter)
+{
+	size_t len = filter ? strlen(filter) : 0;
+
+	return len ? roundup(len + 1, 8) : 0;
+}
+
 static size_t
-intel_pt_info_priv_size(struct auxtrace_record *itr __maybe_unused,
-			struct perf_evlist *evlist __maybe_unused)
+intel_pt_info_priv_size(struct auxtrace_record *itr, struct perf_evlist *evlist)
 {
-	return INTEL_PT_AUXTRACE_PRIV_SIZE;
+	struct intel_pt_recording *ptr =
+			container_of(itr, struct intel_pt_recording, itr);
+	const char *filter = intel_pt_find_filter(evlist, ptr->intel_pt_pmu);
+
+	ptr->priv_size = (INTEL_PT_AUXTRACE_PRIV_MAX * sizeof(u64)) +
+			 intel_pt_filter_bytes(filter);
+
+	return ptr->priv_size;
 }
 
 static void intel_pt_tsc_ctc_ratio(u32 *n, u32 *d)
@@ -302,9 +329,13 @@ static int intel_pt_info_fill(struct auxtrace_record *itr,
 	bool cap_user_time_zero = false, per_cpu_mmaps;
 	u64 tsc_bit, mtc_bit, mtc_freq_bits, cyc_bit, noretcomp_bit;
 	u32 tsc_ctc_ratio_n, tsc_ctc_ratio_d;
+	unsigned long max_non_turbo_ratio;
+	size_t filter_str_len;
+	const char *filter;
+	u64 *info;
 	int err;
 
-	if (priv_size != INTEL_PT_AUXTRACE_PRIV_SIZE)
+	if (priv_size != ptr->priv_size)
 		return -EINVAL;
 
 	intel_pt_parse_terms(&intel_pt_pmu->format, "tsc", &tsc_bit);
@@ -317,6 +348,13 @@ static int intel_pt_info_fill(struct auxtrace_record *itr,
 
 	intel_pt_tsc_ctc_ratio(&tsc_ctc_ratio_n, &tsc_ctc_ratio_d);
 
+	if (perf_pmu__scan_file(intel_pt_pmu, "max_nonturbo_ratio",
+				"%lu", &max_non_turbo_ratio) != 1)
+		max_non_turbo_ratio = 0;
+
+	filter = intel_pt_find_filter(session->evlist, ptr->intel_pt_pmu);
+	filter_str_len = filter ? strlen(filter) : 0;
+
 	if (!session->evlist->nr_mmaps)
 		return -EINVAL;
 
@@ -351,6 +389,17 @@ static int intel_pt_info_fill(struct auxtrace_record *itr,
 	auxtrace_info->priv[INTEL_PT_TSC_CTC_N] = tsc_ctc_ratio_n;
 	auxtrace_info->priv[INTEL_PT_TSC_CTC_D] = tsc_ctc_ratio_d;
 	auxtrace_info->priv[INTEL_PT_CYC_BIT] = cyc_bit;
+	auxtrace_info->priv[INTEL_PT_MAX_NONTURBO_RATIO] = max_non_turbo_ratio;
+	auxtrace_info->priv[INTEL_PT_FILTER_STR_LEN] = filter_str_len;
+
+	info = &auxtrace_info->priv[INTEL_PT_FILTER_STR_LEN] + 1;
+
+	if (filter_str_len) {
+		size_t len = intel_pt_filter_bytes(filter);
+
+		strncpy((char *)info, filter, len);
+		info += len >> 3;
+	}
 
 	return 0;
 }
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 2d0d69be3bf8..67d2a9003294 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -1573,29 +1573,39 @@ int cmd_record(int argc, const char **argv, const char *prefix __maybe_unused)
 	if (!rec->itr) {
 		rec->itr = auxtrace_record__init(rec->evlist, &err);
 		if (err)
-			return err;
+			goto out;
 	}
 
 	err = auxtrace_parse_snapshot_options(rec->itr, &rec->opts,
 					      rec->opts.auxtrace_snapshot_opts);
 	if (err)
-		return err;
+		goto out;
+
+	/*
+	 * Allow aliases to facilitate the lookup of symbols for address
+	 * filters. Refer to auxtrace_parse_filters().
+	 */
+	symbol_conf.allow_aliases = true;
+
+	symbol__init(NULL);
+
+	err = auxtrace_parse_filters(rec->evlist);
+	if (err)
+		goto out;
 
 	if (dry_run)
-		return 0;
+		goto out;
 
 	err = bpf__setup_stdout(rec->evlist);
 	if (err) {
 		bpf__strerror_setup_stdout(rec->evlist, err, errbuf, sizeof(errbuf));
 		pr_err("ERROR: Setup BPF stdout failed: %s\n",
 			 errbuf);
-		return err;
+		goto out;
 	}
 
 	err = -ENOMEM;
 
-	symbol__init(NULL);
-
 	if (symbol_conf.kptr_restrict)
 		pr_warning(
 "WARNING: Kernel address maps (/proc/{kallsyms,modules}) are restricted,\n"
@@ -1643,7 +1653,7 @@ int cmd_record(int argc, const char **argv, const char *prefix __maybe_unused)
 	if (rec->evlist->nr_entries == 0 &&
 	    perf_evlist__add_default(rec->evlist) < 0) {
 		pr_err("Not enough memory for event selector list\n");
-		goto out_symbol_exit;
+		goto out;
 	}
 
 	if (rec->opts.target.tid && !rec->opts.no_inherit_set)
@@ -1663,7 +1673,7 @@ int cmd_record(int argc, const char **argv, const char *prefix __maybe_unused)
 		ui__error("%s", errbuf);
 
 		err = -saved_errno;
-		goto out_symbol_exit;
+		goto out;
 	}
 
 	err = -ENOMEM;
@@ -1672,7 +1682,7 @@ int cmd_record(int argc, const char **argv, const char *prefix __maybe_unused)
 
 	err = auxtrace_record__options(rec->itr, rec->evlist, &rec->opts);
 	if (err)
-		goto out_symbol_exit;
+		goto out;
 
 	/*
 	 * We take all buildids when the file contains
@@ -1684,11 +1694,11 @@ int cmd_record(int argc, const char **argv, const char *prefix __maybe_unused)
 
 	if (record_opts__config(&rec->opts)) {
 		err = -EINVAL;
-		goto out_symbol_exit;
+		goto out;
 	}
 
 	err = __cmd_record(&record, argc, argv);
-out_symbol_exit:
+out:
 	perf_evlist__delete(rec->evlist);
 	symbol__exit();
 	auxtrace_record__free(rec->itr);
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index b4fc1ab3d2a7..c298bd3e1d90 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -742,6 +742,8 @@ static struct syscall_fmt {
 	  .arg_scnprintf = { [1] = SCA_SIGNUM, /* sig */ }, },
 	{ .name	    = "rt_tgsigqueueinfo", .errmsg = true,
 	  .arg_scnprintf = { [2] = SCA_SIGNUM, /* sig */ }, },
+	{ .name	    = "sched_getattr",	      .errmsg = true, },
+	{ .name	    = "sched_setattr",	      .errmsg = true, },
 	{ .name	    = "sched_setscheduler",   .errmsg = true,
 	  .arg_scnprintf = { [1] = SCA_SCHED_POLICY, /* policy */ }, },
 	{ .name	    = "seccomp", .errmsg = true,
@@ -2141,6 +2143,7 @@ out_delete_sys_enter:
 static int trace__set_ev_qualifier_filter(struct trace *trace)
 {
 	int err = -1;
+	struct perf_evsel *sys_exit;
 	char *filter = asprintf_expr_inout_ints("id", !trace->not_ev_qualifier,
 						trace->ev_qualifier_ids.nr,
 						trace->ev_qualifier_ids.entries);
@@ -2148,8 +2151,11 @@ static int trace__set_ev_qualifier_filter(struct trace *trace)
 	if (filter == NULL)
 		goto out_enomem;
 
-	if (!perf_evsel__append_filter(trace->syscalls.events.sys_enter, "&&", filter))
-		err = perf_evsel__append_filter(trace->syscalls.events.sys_exit, "&&", filter);
+	if (!perf_evsel__append_tp_filter(trace->syscalls.events.sys_enter,
+					  filter)) {
+		sys_exit = trace->syscalls.events.sys_exit;
+		err = perf_evsel__append_tp_filter(sys_exit, filter);
+	}
 
 	free(filter);
 out:
diff --git a/tools/perf/tests/Build b/tools/perf/tests/Build
index dc51bc570e51..8a4ce492f7b2 100644
--- a/tools/perf/tests/Build
+++ b/tools/perf/tests/Build
@@ -71,7 +71,7 @@ $(OUTPUT)tests/llvm-src-relocation.c: tests/bpf-script-test-relocation.c tests/B
 	$(Q)sed -e 's/"/\\"/g' -e 's/\(.*\)/"\1\\n"/g' $< >> $@
 	$(Q)echo ';' >> $@
 
-ifeq ($(ARCH),$(filter $(ARCH),x86 arm arm64))
+ifeq ($(ARCH),$(filter $(ARCH),x86 arm arm64 powerpc))
 perf-$(CONFIG_DWARF_UNWIND) += dwarf-unwind.o
 endif
 
diff --git a/tools/perf/tests/dwarf-unwind.c b/tools/perf/tests/dwarf-unwind.c
index 8f6eb853aaf7..1046491de4b2 100644
--- a/tools/perf/tests/dwarf-unwind.c
+++ b/tools/perf/tests/dwarf-unwind.c
@@ -11,7 +11,7 @@
 #include "thread.h"
 #include "callchain.h"
 
-#if defined (__x86_64__) || defined (__i386__)
+#if defined (__x86_64__) || defined (__i386__) || defined (__powerpc__)
 #include "arch-tests.h"
 #endif
 
diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c
index c0aba8e839aa..c5a6e0b12452 100644
--- a/tools/perf/util/auxtrace.c
+++ b/tools/perf/util/auxtrace.c
@@ -16,6 +16,10 @@
 #include <sys/types.h>
 #include <sys/mman.h>
 #include <stdbool.h>
+#include <ctype.h>
+#include <string.h>
+#include <limits.h>
+#include <errno.h>
 
 #include <linux/kernel.h>
 #include <linux/perf_event.h>
@@ -35,9 +39,14 @@
 #include "../perf.h"
 #include "util.h"
 #include "evlist.h"
+#include "dso.h"
+#include "map.h"
+#include "pmu.h"
+#include "evsel.h"
 #include "cpumap.h"
 #include "thread_map.h"
 #include "asm/bug.h"
+#include "symbol/kallsyms.h"
 #include "auxtrace.h"
 
 #include <linux/hash.h>
@@ -1399,3 +1408,731 @@ void *auxtrace_cache__lookup(struct auxtrace_cache *c, u32 key)
 
 	return NULL;
 }
+
+static void addr_filter__free_str(struct addr_filter *filt)
+{
+	free(filt->str);
+	filt->action   = NULL;
+	filt->sym_from = NULL;
+	filt->sym_to   = NULL;
+	filt->filename = NULL;
+	filt->str      = NULL;
+}
+
+static struct addr_filter *addr_filter__new(void)
+{
+	struct addr_filter *filt = zalloc(sizeof(*filt));
+
+	if (filt)
+		INIT_LIST_HEAD(&filt->list);
+
+	return filt;
+}
+
+static void addr_filter__free(struct addr_filter *filt)
+{
+	if (filt)
+		addr_filter__free_str(filt);
+	free(filt);
+}
+
+static void addr_filters__add(struct addr_filters *filts,
+			      struct addr_filter *filt)
+{
+	list_add_tail(&filt->list, &filts->head);
+	filts->cnt += 1;
+}
+
+static void addr_filters__del(struct addr_filters *filts,
+			      struct addr_filter *filt)
+{
+	list_del_init(&filt->list);
+	filts->cnt -= 1;
+}
+
+void addr_filters__init(struct addr_filters *filts)
+{
+	INIT_LIST_HEAD(&filts->head);
+	filts->cnt = 0;
+}
+
+void addr_filters__exit(struct addr_filters *filts)
+{
+	struct addr_filter *filt, *n;
+
+	list_for_each_entry_safe(filt, n, &filts->head, list) {
+		addr_filters__del(filts, filt);
+		addr_filter__free(filt);
+	}
+}
+
+static int parse_num_or_str(char **inp, u64 *num, const char **str,
+			    const char *str_delim)
+{
+	*inp += strspn(*inp, " ");
+
+	if (isdigit(**inp)) {
+		char *endptr;
+
+		if (!num)
+			return -EINVAL;
+		errno = 0;
+		*num = strtoull(*inp, &endptr, 0);
+		if (errno)
+			return -errno;
+		if (endptr == *inp)
+			return -EINVAL;
+		*inp = endptr;
+	} else {
+		size_t n;
+
+		if (!str)
+			return -EINVAL;
+		*inp += strspn(*inp, " ");
+		*str = *inp;
+		n = strcspn(*inp, str_delim);
+		if (!n)
+			return -EINVAL;
+		*inp += n;
+		if (**inp) {
+			**inp = '\0';
+			*inp += 1;
+		}
+	}
+	return 0;
+}
+
+static int parse_action(struct addr_filter *filt)
+{
+	if (!strcmp(filt->action, "filter")) {
+		filt->start = true;
+		filt->range = true;
+	} else if (!strcmp(filt->action, "start")) {
+		filt->start = true;
+	} else if (!strcmp(filt->action, "stop")) {
+		filt->start = false;
+	} else if (!strcmp(filt->action, "tracestop")) {
+		filt->start = false;
+		filt->range = true;
+		filt->action += 5; /* Change 'tracestop' to 'stop' */
+	} else {
+		return -EINVAL;
+	}
+	return 0;
+}
+
+static int parse_sym_idx(char **inp, int *idx)
+{
+	*idx = -1;
+
+	*inp += strspn(*inp, " ");
+
+	if (**inp != '#')
+		return 0;
+
+	*inp += 1;
+
+	if (**inp == 'g' || **inp == 'G') {
+		*inp += 1;
+		*idx = 0;
+	} else {
+		unsigned long num;
+		char *endptr;
+
+		errno = 0;
+		num = strtoul(*inp, &endptr, 0);
+		if (errno)
+			return -errno;
+		if (endptr == *inp || num > INT_MAX)
+			return -EINVAL;
+		*inp = endptr;
+		*idx = num;
+	}
+
+	return 0;
+}
+
+static int parse_addr_size(char **inp, u64 *num, const char **str, int *idx)
+{
+	int err = parse_num_or_str(inp, num, str, " ");
+
+	if (!err && *str)
+		err = parse_sym_idx(inp, idx);
+
+	return err;
+}
+
+static int parse_one_filter(struct addr_filter *filt, const char **filter_inp)
+{
+	char *fstr;