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:

User visible changes:

  - Use PERF_RECORD_SWITCH when available in intel-pt, instead of
    "sched:sched_switch" events, enabling an unprivileged user to trace
    multi-threaded or multi-process workloads. (Adrian Hunter)

  - Always use non inlined file name for 'srcfile' sort key. (Andi Kleen)

  - Quieten failed to read counter message, helps in systems without
    backend-stalled-cycles. (Andi Kleen)

Infrastructure changes:

  - Add a 'perf test' entry for decoding of new x86 instructions. (Adrian Hunter)

  - Add new instructions (sha, clflushopt, clwb, pcommit, rdpkru, wrpkru, xsavec,
    xsaves, xrstors) to the x86 instruction decoder. (Adrian Hunter)

  - Add a build test to warn when source code drifts happen for the
    instruction decoder files in the kernel and in tools/perf. (Adrian Hunter)

  - Copy linux/filter.h to tools/include. (He Kuang)

  - Support function __get_dynamic_array_len in libtraceevent. (He Kuanguuu)

  - Tracing path finding/mounting/error reporting refactorings. (Jiri Olsa)

  - Store CPU socket and core IDs in perf.data. (Kan Liang)

  - Reorganize add/del probe insertion routines in 'perf probe'. (Namhyung Kim, Wang Nan)

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

21 files changed, 391 insertions, 200 deletions

diff --git a/tools/perf/util/cpumap.c b/tools/perf/util/cpumap.c
index 3667e2123e5b..a05d76ab18d8 100644
--- a/tools/perf/util/cpumap.c
+++ b/tools/perf/util/cpumap.c
@@ -225,17 +225,12 @@ void cpu_map__put(struct cpu_map *map)
 		cpu_map__delete(map);
 }
 
-int cpu_map__get_socket(struct cpu_map *map, int idx)
+int cpu_map__get_socket_id(int cpu)
 {
 	FILE *fp;
 	const char *mnt;
 	char path[PATH_MAX];
-	int cpu, ret;
-
-	if (idx > map->nr)
-		return -1;
-
-	cpu = map->map[idx];
+	int socket_id, ret;
 
 	mnt = sysfs__mountpoint();
 	if (!mnt)
@@ -248,9 +243,22 @@ int cpu_map__get_socket(struct cpu_map *map, int idx)
 	fp = fopen(path, "r");
 	if (!fp)
 		return -1;
-	ret = fscanf(fp, "%d", &cpu);
+	ret = fscanf(fp, "%d", &socket_id);
 	fclose(fp);
-	return ret == 1 ? cpu : -1;
+
+	return ret == 1 ? socket_id : -1;
+}
+
+int cpu_map__get_socket(struct cpu_map *map, int idx)
+{
+	int cpu;
+
+	if (idx > map->nr)
+		return -1;
+
+	cpu = map->map[idx];
+
+	return cpu_map__get_socket_id(cpu);
 }
 
 static int cmp_ids(const void *a, const void *b)
@@ -289,17 +297,12 @@ static int cpu_map__build_map(struct cpu_map *cpus, struct cpu_map **res,
 	return 0;
 }
 
-int cpu_map__get_core(struct cpu_map *map, int idx)
+int cpu_map__get_core_id(int cpu)
 {
 	FILE *fp;
 	const char *mnt;
 	char path[PATH_MAX];
-	int cpu, ret, s;
-
-	if (idx > map->nr)
-		return -1;
-
-	cpu = map->map[idx];
+	int core_id, ret;
 
 	mnt = sysfs__mountpoint();
 	if (!mnt)
@@ -312,11 +315,23 @@ int cpu_map__get_core(struct cpu_map *map, int idx)
 	fp = fopen(path, "r");
 	if (!fp)
 		return -1;
-	ret = fscanf(fp, "%d", &cpu);
+	ret = fscanf(fp, "%d", &core_id);
 	fclose(fp);
-	if (ret != 1)
+
+	return ret == 1 ? core_id : -1;
+}
+
+int cpu_map__get_core(struct cpu_map *map, int idx)
+{
+	int cpu, s;
+
+	if (idx > map->nr)
 		return -1;
 
+	cpu = map->map[idx];
+
+	cpu = cpu_map__get_core_id(cpu);
+
 	s = cpu_map__get_socket(map, idx);
 	if (s == -1)
 		return -1;
diff --git a/tools/perf/util/cpumap.h b/tools/perf/util/cpumap.h
index 0af9cecb4c51..8982d538da83 100644
--- a/tools/perf/util/cpumap.h
+++ b/tools/perf/util/cpumap.h
@@ -18,7 +18,9 @@ struct cpu_map *cpu_map__new(const char *cpu_list);
 struct cpu_map *cpu_map__dummy_new(void);
 struct cpu_map *cpu_map__read(FILE *file);
 size_t cpu_map__fprintf(struct cpu_map *map, FILE *fp);
+int cpu_map__get_socket_id(int cpu);
 int cpu_map__get_socket(struct cpu_map *map, int idx);
+int cpu_map__get_core_id(int cpu);
 int cpu_map__get_core(struct cpu_map *map, int idx);
 int cpu_map__build_socket_map(struct cpu_map *cpus, struct cpu_map **sockp);
 int cpu_map__build_core_map(struct cpu_map *cpus, struct cpu_map **corep);
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 41814547da15..8fd7b7de1acd 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -88,6 +88,9 @@ int write_padded(int fd, const void *bf, size_t count, size_t count_aligned)
 	return err;
 }
 
+#define string_size(str)						\
+	(PERF_ALIGN((strlen(str) + 1), NAME_ALIGN) + sizeof(u32))
+
 static int do_write_string(int fd, const char *str)
 {
 	u32 len, olen;
@@ -441,10 +444,13 @@ static int write_cmdline(int fd, struct perf_header *h __maybe_unused,
 	"/sys/devices/system/cpu/cpu%d/topology/thread_siblings_list"
 
 struct cpu_topo {
+	u32 cpu_nr;
 	u32 core_sib;
 	u32 thread_sib;
 	char **core_siblings;
 	char **thread_siblings;
+	int *core_id;
+	int *phy_pkg_id;
 };
 
 static int build_cpu_topo(struct cpu_topo *tp, int cpu)
@@ -507,6 +513,9 @@ try_threads:
 	}
 	ret = 0;
 done:
+	tp->core_id[cpu] = cpu_map__get_core_id(cpu);
+	tp->phy_pkg_id[cpu] = cpu_map__get_socket_id(cpu);
+
 	if(fp)
 		fclose(fp);
 	free(buf);
@@ -534,7 +543,7 @@ static struct cpu_topo *build_cpu_topology(void)
 	struct cpu_topo *tp;
 	void *addr;
 	u32 nr, i;
-	size_t sz;
+	size_t sz, sz_id;
 	long ncpus;
 	int ret = -1;
 
@@ -545,17 +554,22 @@ static struct cpu_topo *build_cpu_topology(void)
 	nr = (u32)(ncpus & UINT_MAX);
 
 	sz = nr * sizeof(char *);
+	sz_id = nr * sizeof(int);
 
-	addr = calloc(1, sizeof(*tp) + 2 * sz);
+	addr = calloc(1, sizeof(*tp) + 2 * sz + 2 * sz_id);
 	if (!addr)
 		return NULL;
 
 	tp = addr;
-
+	tp->cpu_nr = nr;
 	addr += sizeof(*tp);
 	tp->core_siblings = addr;
 	addr += sz;
 	tp->thread_siblings = addr;
+	addr += sz;
+	tp->core_id = addr;
+	addr += sz_id;
+	tp->phy_pkg_id = addr;
 
 	for (i = 0; i < nr; i++) {
 		ret = build_cpu_topo(tp, i);
@@ -598,6 +612,15 @@ static int write_cpu_topology(int fd, struct perf_header *h __maybe_unused,
 		if (ret < 0)
 			break;
 	}
+
+	for (i = 0; i < tp->cpu_nr; i++) {
+		ret = do_write(fd, &tp->core_id[i], sizeof(int));
+		if (ret < 0)
+			return ret;
+		ret = do_write(fd, &tp->phy_pkg_id[i], sizeof(int));
+		if (ret < 0)
+			return ret;
+	}
 done:
 	free_cpu_topo(tp);
 	return ret;
@@ -938,6 +961,7 @@ static void print_cpu_topology(struct perf_header *ph, int fd __maybe_unused,
 {
 	int nr, i;
 	char *str;
+	int cpu_nr = ph->env.nr_cpus_online;
 
 	nr = ph->env.nr_sibling_cores;
 	str = ph->env.sibling_cores;
@@ -954,6 +978,13 @@ static void print_cpu_topology(struct perf_header *ph, int fd __maybe_unused,
 		fprintf(fp, "# sibling threads : %s\n", str);
 		str += strlen(str) + 1;
 	}
+
+	if (ph->env.cpu != NULL) {
+		for (i = 0; i < cpu_nr; i++)
+			fprintf(fp, "# CPU %d: Core ID %d, Socket ID %d\n", i,
+				ph->env.cpu[i].core_id, ph->env.cpu[i].socket_id);
+	} else
+		fprintf(fp, "# Core ID and Socket ID information is not available\n");
 }
 
 static void free_event_desc(struct perf_evsel *events)
@@ -1582,7 +1613,7 @@ error:
 	return -1;
 }
 
-static int process_cpu_topology(struct perf_file_section *section __maybe_unused,
+static int process_cpu_topology(struct perf_file_section *section,
 				struct perf_header *ph, int fd,
 				void *data __maybe_unused)
 {
@@ -1590,15 +1621,22 @@ static int process_cpu_topology(struct perf_file_section *section __maybe_unused
 	u32 nr, i;
 	char *str;
 	struct strbuf sb;
+	int cpu_nr = ph->env.nr_cpus_online;
+	u64 size = 0;
+
+	ph->env.cpu = calloc(cpu_nr, sizeof(*ph->env.cpu));
+	if (!ph->env.cpu)
+		return -1;
 
 	ret = readn(fd, &nr, sizeof(nr));
 	if (ret != sizeof(nr))
-		return -1;
+		goto free_cpu;
 
 	if (ph->needs_swap)
 		nr = bswap_32(nr);
 
 	ph->env.nr_sibling_cores = nr;
+	size += sizeof(u32);
 	strbuf_init(&sb, 128);
 
 	for (i = 0; i < nr; i++) {
@@ -1608,6 +1646,7 @@ static int process_cpu_topology(struct perf_file_section *section __maybe_unused
 
 		/* include a NULL character at the end */
 		strbuf_add(&sb, str, strlen(str) + 1);
+		size += string_size(str);
 		free(str);
 	}
 	ph->env.sibling_cores = strbuf_detach(&sb, NULL);
@@ -1620,6 +1659,7 @@ static int process_cpu_topology(struct perf_file_section *section __maybe_unused
 		nr = bswap_32(nr);
 
 	ph->env.nr_sibling_threads = nr;
+	size += sizeof(u32);
 
 	for (i = 0; i < nr; i++) {
 		str = do_read_string(fd, ph);
@@ -1628,13 +1668,57 @@ static int process_cpu_topology(struct perf_file_section *section __maybe_unused
 
 		/* include a NULL character at the end */
 		strbuf_add(&sb, str, strlen(str) + 1);
+		size += string_size(str);
 		free(str);
 	}
 	ph->env.sibling_threads = strbuf_detach(&sb, NULL);
+
+	/*
+	 * The header may be from old perf,
+	 * which doesn't include core id and socket id information.
+	 */
+	if (section->size <= size) {
+		zfree(&ph->env.cpu);
+		return 0;
+	}
+
+	for (i = 0; i < (u32)cpu_nr; i++) {
+		ret = readn(fd, &nr, sizeof(nr));
+		if (ret != sizeof(nr))
+			goto free_cpu;
+
+		if (ph->needs_swap)
+			nr = bswap_32(nr);
+
+		if (nr > (u32)cpu_nr) {
+			pr_debug("core_id number is too big."
+				 "You may need to upgrade the perf tool.\n");
+			goto free_cpu;
+		}
+		ph->env.cpu[i].core_id = nr;
+
+		ret = readn(fd, &nr, sizeof(nr));
+		if (ret != sizeof(nr))
+			goto free_cpu;
+
+		if (ph->needs_swap)
+			nr = bswap_32(nr);
+
+		if (nr > (u32)cpu_nr) {
+			pr_debug("socket_id number is too big."
+				 "You may need to upgrade the perf tool.\n");
+			goto free_cpu;
+		}
+
+		ph->env.cpu[i].socket_id = nr;
+	}
+
 	return 0;
 
 error:
 	strbuf_release(&sb);
+free_cpu:
+	zfree(&ph->env.cpu);
 	return -1;
 }
 
diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h
index 396e4965f0c9..975d803f46c8 100644
--- a/tools/perf/util/header.h
+++ b/tools/perf/util/header.h
@@ -66,6 +66,11 @@ struct perf_header;
 int perf_file_header__read(struct perf_file_header *header,
 			   struct perf_header *ph, int fd);
 
+struct cpu_topology_map {
+	int	socket_id;
+	int	core_id;
+};
+
 struct perf_env {
 	char			*hostname;
 	char			*os_release;
@@ -89,6 +94,7 @@ struct perf_env {
 	char			*sibling_threads;
 	char			*numa_nodes;
 	char			*pmu_mappings;
+	struct cpu_topology_map	*cpu;
 };
 
 struct perf_header {
diff --git a/tools/perf/util/intel-pt-decoder/Build b/tools/perf/util/intel-pt-decoder/Build
index 2386322ece4f..0611d619a42e 100644
--- a/tools/perf/util/intel-pt-decoder/Build
+++ b/tools/perf/util/intel-pt-decoder/Build
@@ -7,6 +7,17 @@ $(OUTPUT)util/intel-pt-decoder/inat-tables.c: $(inat_tables_script) $(inat_table
 	$(call rule_mkdir)
 	@$(call echo-cmd,gen)$(AWK) -f $(inat_tables_script) $(inat_tables_maps) > $@ || rm -f $@
 
-$(OUTPUT)util/intel-pt-decoder/intel-pt-insn-decoder.o: util/intel-pt-decoder/inat.c $(OUTPUT)util/intel-pt-decoder/inat-tables.c
+$(OUTPUT)util/intel-pt-decoder/intel-pt-insn-decoder.o: util/intel-pt-decoder/intel-pt-insn-decoder.c util/intel-pt-decoder/inat.c $(OUTPUT)util/intel-pt-decoder/inat-tables.c
+	@(test -d ../../kernel -a -d ../../tools -a -d ../perf && (( \
+	diff -B -I'^#include' util/intel-pt-decoder/insn.c ../../arch/x86/lib/insn.c >/dev/null && \
+	diff -B -I'^#include' util/intel-pt-decoder/inat.c ../../arch/x86/lib/inat.c >/dev/null && \
+	diff -B util/intel-pt-decoder/x86-opcode-map.txt ../../arch/x86/lib/x86-opcode-map.txt >/dev/null && \
+	diff -B util/intel-pt-decoder/gen-insn-attr-x86.awk ../../arch/x86/tools/gen-insn-attr-x86.awk >/dev/null && \
+	diff -B -I'^#include' util/intel-pt-decoder/insn.h ../../arch/x86/include/asm/insn.h >/dev/null && \
+	diff -B -I'^#include' util/intel-pt-decoder/inat.h ../../arch/x86/include/asm/inat.h >/dev/null && \
+	diff -B -I'^#include' util/intel-pt-decoder/inat_types.h ../../arch/x86/include/asm/inat_types.h >/dev/null) \
+	|| echo "Warning: Intel PT: x86 instruction decoder differs from kernel" >&2 )) || true
+	$(call rule_mkdir)
+	$(call if_changed_dep,cc_o_c)
 
 CFLAGS_intel-pt-insn-decoder.o += -I$(OUTPUT)util/intel-pt-decoder -Wno-override-init
diff --git a/tools/perf/util/intel-pt-decoder/x86-opcode-map.txt b/tools/perf/util/intel-pt-decoder/x86-opcode-map.txt
index 816488c0b97e..d388de72eaca 100644
--- a/tools/perf/util/intel-pt-decoder/x86-opcode-map.txt
+++ b/tools/perf/util/intel-pt-decoder/x86-opcode-map.txt
@@ -353,8 +353,12 @@ AVXcode: 1
 17: vmovhps Mq,Vq (v1) | vmovhpd Mq,Vq (66),(v1)
 18: Grp16 (1A)
 19:
-1a: BNDCL Ev,Gv | BNDCU Ev,Gv | BNDMOV Gv,Ev | BNDLDX Gv,Ev,Gv
-1b: BNDCN Ev,Gv | BNDMOV Ev,Gv | BNDMK Gv,Ev | BNDSTX Ev,GV,Gv
+# Intel SDM opcode map does not list MPX instructions. For now using Gv for
+# bnd registers and Ev for everything else is OK because the instruction
+# decoder does not use the information except as an indication that there is
+# a ModR/M byte.
+1a: BNDCL Gv,Ev (F3) | BNDCU Gv,Ev (F2) | BNDMOV Gv,Ev (66) | BNDLDX Gv,Ev
+1b: BNDCN Gv,Ev (F2) | BNDMOV Ev,Gv (66) | BNDMK Gv,Ev (F3) | BNDSTX Ev,Gv
 1c:
 1d:
 1e:
@@ -732,6 +736,12 @@ bd: vfnmadd231ss/d Vx,Hx,Wx (66),(v),(v1)
 be: vfnmsub231ps/d Vx,Hx,Wx (66),(v)
 bf: vfnmsub231ss/d Vx,Hx,Wx (66),(v),(v1)
 # 0x0f 0x38 0xc0-0xff
+c8: sha1nexte Vdq,Wdq
+c9: sha1msg1 Vdq,Wdq
+ca: sha1msg2 Vdq,Wdq
+cb: sha256rnds2 Vdq,Wdq
+cc: sha256msg1 Vdq,Wdq
+cd: sha256msg2 Vdq,Wdq
 db: VAESIMC Vdq,Wdq (66),(v1)
 dc: VAESENC Vdq,Hdq,Wdq (66),(v1)
 dd: VAESENCLAST Vdq,Hdq,Wdq (66),(v1)
@@ -790,6 +800,7 @@ AVXcode: 3
 61: vpcmpestri Vdq,Wdq,Ib (66),(v1)
 62: vpcmpistrm Vdq,Wdq,Ib (66),(v1)
 63: vpcmpistri Vdq,Wdq,Ib (66),(v1)
+cc: sha1rnds4 Vdq,Wdq,Ib
 df: VAESKEYGEN Vdq,Wdq,Ib (66),(v1)
 f0: RORX Gy,Ey,Ib (F2),(v)
 EndTable
@@ -874,7 +885,7 @@ GrpTable: Grp7
 2: LGDT Ms | XGETBV (000),(11B) | XSETBV (001),(11B) | VMFUNC (100),(11B) | XEND (101)(11B) | XTEST (110)(11B)
 3: LIDT Ms
 4: SMSW Mw/Rv
-5:
+5: rdpkru (110),(11B) | wrpkru (111),(11B)
 6: LMSW Ew
 7: INVLPG Mb | SWAPGS (o64),(000),(11B) | RDTSCP (001),(11B)
 EndTable
@@ -888,6 +899,9 @@ EndTable
 
 GrpTable: Grp9
 1: CMPXCHG8B/16B Mq/Mdq
+3: xrstors
+4: xsavec
+5: xsaves
 6: VMPTRLD Mq | VMCLEAR Mq (66) | VMXON Mq (F3) | RDRAND Rv (11B)
 7: VMPTRST Mq | VMPTRST Mq (F3) | RDSEED Rv (11B)
 EndTable
@@ -932,8 +946,8 @@ GrpTable: Grp15
 3: vstmxcsr Md (v1) | WRGSBASE Ry (F3),(11B)
 4: XSAVE
 5: XRSTOR | lfence (11B)
-6: XSAVEOPT | mfence (11B)
-7: clflush | sfence (11B)
+6: XSAVEOPT | clwb (66) | mfence (11B)
+7: clflush | clflushopt (66) | sfence (11B) | pcommit (66),(11B)
 EndTable
 
 GrpTable: Grp16
diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c
index 535d86f8e4d1..38942e1eac8f 100644
--- a/tools/perf/util/intel-pt.c
+++ b/tools/perf/util/intel-pt.c
@@ -1145,11 +1145,13 @@ static int intel_pt_sample(struct intel_pt_queue *ptq)
 	return 0;
 }
 
-static u64 intel_pt_switch_ip(struct machine *machine, u64 *ptss_ip)
+static u64 intel_pt_switch_ip(struct intel_pt *pt, u64 *ptss_ip)
 {
+	struct machine *machine = pt->machine;
 	struct map *map;
 	struct symbol *sym, *start;
 	u64 ip, switch_ip = 0;
+	const char *ptss;
 
 	if (ptss_ip)
 		*ptss_ip = 0;
@@ -1177,8 +1179,13 @@ static u64 intel_pt_switch_ip(struct machine *machine, u64 *ptss_ip)
 	if (!switch_ip || !ptss_ip)
 		return 0;
 
+	if (pt->have_sched_switch == 1)
+		ptss = "perf_trace_sched_switch";
+	else
+		ptss = "__perf_event_task_sched_out";
+
 	for (sym = start; sym; sym = dso__next_symbol(sym)) {
-		if (!strcmp(sym->name, "perf_trace_sched_switch")) {
+		if (!strcmp(sym->name, ptss)) {
 			ip = map->unmap_ip(map, sym->start);
 			if (ip >= map->start && ip < map->end) {
 				*ptss_ip = ip;
@@ -1198,11 +1205,11 @@ static int intel_pt_run_decoder(struct intel_pt_queue *ptq, u64 *timestamp)
 
 	if (!pt->kernel_start) {
 		pt->kernel_start = machine__kernel_start(pt->machine);
-		if (pt->per_cpu_mmaps && pt->have_sched_switch &&
+		if (pt->per_cpu_mmaps &&
+		    (pt->have_sched_switch == 1 || pt->have_sched_switch == 3) &&
 		    !pt->timeless_decoding && intel_pt_tracing_kernel(pt) &&
 		    !pt->sampling_mode) {
-			pt->switch_ip = intel_pt_switch_ip(pt->machine,
-							   &pt->ptss_ip);
+			pt->switch_ip = intel_pt_switch_ip(pt, &pt->ptss_ip);
 			if (pt->switch_ip) {
 				intel_pt_log("switch_ip: %"PRIx64" ptss_ip: %"PRIx64"\n",
 					     pt->switch_ip, pt->ptss_ip);
@@ -1387,31 +1394,18 @@ static struct intel_pt_queue *intel_pt_cpu_to_ptq(struct intel_pt *pt, int cpu)
 	return NULL;
 }
 
-static int intel_pt_process_switch(struct intel_pt *pt,
-				   struct perf_sample *sample)
+static int intel_pt_sync_switch(struct intel_pt *pt, int cpu, pid_t tid,
+				u64 timestamp)
 {
 	struct intel_pt_queue *ptq;
-	struct perf_evsel *evsel;
-	pid_t tid;
-	int cpu, err;
-
-	evsel = perf_evlist__id2evsel(pt->session->evlist, sample->id);
-	if (evsel != pt->switch_evsel)
-		return 0;
-
-	tid = perf_evsel__intval(evsel, sample, "next_pid");
-	cpu = sample->cpu;
-
-	intel_pt_log("sched_switch: cpu %d tid %d time %"PRIu64" tsc %#"PRIx64"\n",
-		     cpu, tid, sample->time, perf_time_to_tsc(sample->time,
-		     &pt->tc));
+	int err;
 
 	if (!pt->sync_switch)
-		goto out;
+		return 1;
 
 	ptq = intel_pt_cpu_to_ptq(pt, cpu);
 	if (!ptq)
-		goto out;
+		return 1;
 
 	switch (ptq->switch_state) {
 	case INTEL_PT_SS_NOT_TRACING:
@@ -1424,7 +1418,7 @@ static int intel_pt_process_switch(struct intel_pt *pt,
 		return 0;
 	case INTEL_PT_SS_EXPECTING_SWITCH_EVENT:
 		if (!ptq->on_heap) {
-			ptq->timestamp = perf_time_to_tsc(sample->time,
+			ptq->timestamp = perf_time_to_tsc(timestamp,
 							  &pt->tc);
 			err = auxtrace_heap__add(&pt->heap, ptq->queue_nr,
 						 ptq->timestamp);
@@ -1441,10 +1435,76 @@ static int intel_pt_process_switch(struct intel_pt *pt,
 	default:
 		break;
 	}
-out:
+
+	return 1;
+}
+
+static int intel_pt_process_switch(struct intel_pt *pt,
+				   struct perf_sample *sample)
+{
+	struct perf_evsel *evsel;
+	pid_t tid;
+	int cpu, ret;
+
+	evsel = perf_evlist__id2evsel(pt->session->evlist, sample->id);
+	if (evsel != pt->switch_evsel)
+		return 0;
+
+	tid = perf_evsel__intval(evsel, sample, "next_pid");
+	cpu = sample->cpu;
+
+	intel_pt_log("sched_switch: cpu %d tid %d time %"PRIu64" tsc %#"PRIx64"\n",
+		     cpu, tid, sample->time, perf_time_to_tsc(sample->time,
+		     &pt->tc));
+
+	ret = intel_pt_sync_switch(pt, cpu, tid, sample->time);
+	if (ret <= 0)
+		return ret;
+
 	return machine__set_current_tid(pt->machine, cpu, -1, tid);
 }
 
+static int intel_pt_context_switch(struct intel_pt *pt, union perf_event *event,
+				   struct perf_sample *sample)
+{
+	bool out = event->header.misc & PERF_RECORD_MISC_SWITCH_OUT;
+	pid_t pid, tid;
+	int cpu, ret;
+
+	cpu = sample->cpu;
+
+	if (pt->have_sched_switch == 3) {
+		if (!out)
+			return 0;
+		if (event->header.type != PERF_RECORD_SWITCH_CPU_WIDE) {
+			pr_err("Expecting CPU-wide context switch event\n");
+			return -EINVAL;
+		}
+		pid = event->context_switch.next_prev_pid;
+		tid = event->context_switch.next_prev_tid;
+	} else {
+		if (out)
+			return 0;
+		pid = sample->pid;
+		tid = sample->tid;
+	}
+
+	if (tid == -1) {
+		pr_err("context_switch event has no tid\n");
+		return -EINVAL;
+	}
+
+	intel_pt_log("context_switch: cpu %d pid %d tid %d time %"PRIu64" tsc %#"PRIx64"\n",
+		     cpu, pid, tid, sample->time, perf_time_to_tsc(sample->time,
+		     &pt->tc));
+
+	ret = intel_pt_sync_switch(pt, cpu, tid, sample->time);
+	if (ret <= 0)
+		return ret;
+
+	return machine__set_current_tid(pt->machine, cpu, pid, tid);
+}
+
 static int intel_pt_process_itrace_start(struct intel_pt *pt,
 					 union perf_event *event,
 					 struct perf_sample *sample)
@@ -1515,6 +1575,9 @@ static int intel_pt_process_event(struct perf_session *session,
 		err = intel_pt_process_switch(pt, sample);
 	else if (event->header.type == PERF_RECORD_ITRACE_START)
 		err = intel_pt_process_itrace_start(pt, event, sample);
+	else if (event->header.type == PERF_RECORD_SWITCH ||
+		 event->header.type == PERF_RECORD_SWITCH_CPU_WIDE)
+		err = intel_pt_context_switch(pt, event, sample);
 
 	intel_pt_log("event %s (%u): cpu %d time %"PRIu64" tsc %#"PRIx64"\n",
 		     perf_event__name(event->header.type), event->header.type,
@@ -1777,6 +1840,18 @@ static struct perf_evsel *intel_pt_find_sched_switch(struct perf_evlist *evlist)
 	return NULL;
 }
 
+static bool intel_pt_find_switch(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel;
+
+	evlist__for_each(evlist, evsel) {
+		if (evsel->attr.context_switch)
+			return true;
+	}
+
+	return false;
+}
+
 static const char * const intel_pt_info_fmts[] = {
 	[INTEL_PT_PMU_TYPE]		= "  PMU Type            %"PRId64"\n",
 	[INTEL_PT_TIME_SHIFT]		= "  Time Shift          %"PRIu64"\n",
@@ -1888,6 +1963,10 @@ int intel_pt_process_auxtrace_info(union perf_event *event,
 			pr_err("%s: missing sched_switch event\n", __func__);
 			goto err_delete_thread;
 		}
+	} else if (pt->have_sched_switch == 2 &&
+		   !intel_pt_find_switch(session->evlist)) {
+		pr_err("%s: missing context_switch attribute flag\n", __func__);
+		goto err_delete_thread;
 	}
 
 	if (session->itrace_synth_opts && session->itrace_synth_opts->set) {
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index d826e6f515db..3840176642f8 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -11,7 +11,7 @@
 #include "cache.h"
 #include "header.h"
 #include "debug.h"
-#include <api/fs/debugfs.h>
+#include <api/fs/tracing_path.h>
 #include "parse-events-bison.h"
 #define YY_EXTRA_TYPE int
 #include "parse-events-flex.h"
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index eb5f18b75402..3da9e1c792fa 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -2180,9 +2180,9 @@ out:
 }
 
 /* Show an event */
-static int show_perf_probe_event(const char *group, const char *event,
-				 struct perf_probe_event *pev,
-				 const char *module, bool use_stdout)
+int show_perf_probe_event(const char *group, const char *event,
+			  struct perf_probe_event *pev,
+			  const char *module, bool use_stdout)
 {
 	struct strbuf buf = STRBUF_INIT;
 	int ret;
@@ -2399,7 +2399,6 @@ static int __add_probe_trace_events(struct perf_probe_event *pev,
 {
 	int i, fd, ret;
 	struct probe_trace_event *tev = NULL;
-	const char *event = NULL, *group = NULL;
 	struct strlist *namelist;
 
 	fd = probe_file__open(PF_FL_RW | (pev->uprobes ? PF_FL_UPROBE : 0));
@@ -2415,7 +2414,6 @@ static int __add_probe_trace_events(struct perf_probe_event *pev,
 	}
 
 	ret = 0;
-	pr_info("Added new event%s\n", (ntevs > 1) ? "s:" : ":");
 	for (i = 0; i < ntevs; i++) {
 		tev = &tevs[i];
 		/* Skip if the symbol is out of .text or blacklisted */
@@ -2432,13 +2430,6 @@ static int __add_probe_trace_events(struct perf_probe_event *pev,
 		if (ret < 0)
 			break;
 
-		/* We use tev's name for showing new events */
-		show_perf_probe_event(tev->group, tev->event, pev,
-				      tev->point.module, false);
-		/* Save the last valid name */
-		event = tev->event;
-		group = tev->group;
-
 		/*
 		 * Probes after the first probe which comes from same
 		 * user input are always allowed to add suffix, because
@@ -2450,13 +2441,6 @@ static int __add_probe_trace_events(struct perf_probe_event *pev,
 	if (ret == -EINVAL && pev->uprobes)
 		warn_uprobe_event_compat(tev);
 
-	/* Note that it is possible to skip all events because of blacklist */
-	if (ret >= 0 && event) {
-		/* Show how to use the event. */
-		pr_info("\nYou can now use it in all perf tools, such as:\n\n");
-		pr_info("\tperf record -e %s:%s -aR sleep 1\n\n", group, event);
-	}
-
 	strlist__delete(namelist);
 close_out:
 	close(fd);
@@ -2759,62 +2743,70 @@ static int convert_to_probe_trace_events(struct perf_probe_event *pev,
 	return find_probe_trace_events_from_map(pev, tevs);
 }
 
-struct __event_package {
-	struct perf_probe_event		*pev;
-	struct probe_trace_event	*tevs;
-	int				ntevs;
-};
-
-int add_perf_probe_events(struct perf_probe_event *pevs, int npevs)
+int convert_perf_probe_events(struct perf_probe_event *pevs, int npevs)
 {
-	int i, j, ret;
-	struct __event_package *pkgs;
-
-	ret = 0;
-	pkgs = zalloc(sizeof(struct __event_package) * npevs);
-
-	if (pkgs == NULL)
-		return -ENOMEM;
+	int i, ret;
 
 	ret = init_symbol_maps(pevs->uprobes);
-	if (ret < 0) {
-		free(pkgs);
+	if (ret < 0)
 		return ret;
-	}
 
 	/* Loop 1: convert all events */
 	for (i = 0; i < npevs; i++) {
-		pkgs[i].pev = &pevs[i];
 		/* Init kprobe blacklist if needed */
-		if (!pkgs[i].pev->uprobes)
+		if (!pevs[i].uprobes)
 			kprobe_blacklist__init();
 		/* Convert with or without debuginfo */
-		ret  = convert_to_probe_trace_events(pkgs[i].pev,
-						     &pkgs[i].tevs);
+		ret  = convert_to_probe_trace_events(&pevs[i], &pevs[i].tevs);
 		if (ret < 0)
-			goto end;
-		pkgs[i].ntevs = ret;
+			return ret;
+		pevs[i].ntevs = ret;
 	}
 	/* This just release blacklist only if allocated */
 	kprobe_blacklist__release();
 
+	return 0;
+}
+
+int apply_perf_probe_events(struct perf_probe_event *pevs, int npevs)
+{
+	int i, ret = 0;
+
 	/* Loop 2: add all events */
 	for (i = 0; i < npevs; i++) {
-		ret = __add_probe_trace_events(pkgs[i].pev, pkgs[i].tevs,
-					       pkgs[i].ntevs,
+		ret = __add_probe_trace_events(&pevs[i], pevs[i].tevs,
+					       pevs[i].ntevs,
 					       probe_conf.force_add);
 		if (ret < 0)
 			break;
 	}
-end:
+	return ret;
+}
+
+void cleanup_perf_probe_events(struct perf_probe_event *pevs, int npevs)
+{
+	int i, j;
+
 	/* Loop 3: cleanup and free trace events  */
 	for (i = 0; i < npevs; i++) {
-		for (j = 0; j < pkgs[i].ntevs; j++)
-			clear_probe_trace_event(&pkgs[i].tevs[j]);
-		zfree(&pkgs[i].tevs);
+		for (j = 0; j < pevs[i].ntevs; j++)
+			clear_probe_trace_event(&pevs[i].tevs[j]);
+		zfree(&pevs[i].tevs);
+		pevs[i].ntevs = 0;
 	}
-	free(pkgs);
+
 	exit_symbol_maps();
+}
+
+int add_perf_probe_events(struct perf_probe_event *pevs, int npevs)
+{
+	int ret;
+
+	ret = convert_perf_probe_events(pevs, npevs);
+	if (ret == 0)
+		ret = apply_perf_probe_events(pevs, npevs);
+
+	cleanup_perf_probe_events(pevs, npevs);
 
 	return ret;
 }
@@ -2827,8 +2819,6 @@ int del_perf_probe_events(struct strfilter *filter)
 	if (!str)
 		return -EINVAL;
 
-	pr_debug("Delete filter: \'%s\'\n", str);
-
 	/* Get current event names */
 	ret = probe_file__open_both(&kfd, &ufd, PF_FL_RW);
 	if (ret < 0)
@@ -2843,9 +2833,6 @@ int del_perf_probe_events(struct strfilter *filter)
 		ret = ret2;
 		goto error;
 	}
-	if (ret == -ENOENT && ret2 == -ENOENT)
-		pr_debug("\"%s\" does not hit any event.\n", str);
-		/* Note that this is silently ignored */
 	ret = 0;
 
 error:
diff --git a/tools/perf/util/probe-event.h b/tools/perf/util/probe-event.h
index 6e7ec68a4aa8..9bcea36359f2 100644
--- a/tools/perf/util/probe-event.h
+++ b/tools/perf/util/probe-event.h
@@ -87,6 +87,8 @@ struct perf_probe_event {
 	bool			uprobes;	/* Uprobe event flag */
 	char			*target;	/* Target binary */
 	struct perf_probe_arg	*args;	/* Arguments */
+	struct probe_trace_event *tevs;
+	int			ntevs;
 };
 
 /* Line range */
@@ -138,7 +140,14 @@ extern void line_range__clear(struct line_range *lr);
 extern int line_range__init(struct line_range *lr);
 
 extern int add_perf_probe_events(struct perf_probe_event *pevs, int npevs);
+extern int convert_perf_probe_events(struct perf_probe_event *pevs, int npevs);
+extern int apply_perf_probe_events(struct perf_probe_event *pevs, int npevs);
+extern void cleanup_perf_probe_events(struct perf_probe_event *pevs, int npevs);
 extern int del_perf_probe_events(struct strfilter *filter);
+
+extern int show_perf_probe_event(const char *group, const char *event,
+				 struct perf_probe_event *pev,
+				 const char *module, bool use_stdout);
 extern int show_perf_probe_events(struct strfilter *filter);
 extern int show_line_range(struct line_range *lr, const char *module,
 			   bool user);
diff --git a/tools/perf/util/probe-file.c b/tools/perf/util/probe-file.c
index bbb243717ec8..38c0a62039cc 100644
--- a/tools/perf/util/probe-file.c
+++ b/tools/perf/util/probe-file.c
@@ -267,7 +267,6 @@ static int __del_trace_probe_event(int fd, struct str_node *ent)
 		goto error;
 	}
 
-	pr_info("Removed event: %s\n", ent->s);
 	return 0;
 error:
 	pr_warning("Failed to delete event: %s\n",
@@ -275,7 +274,8 @@ error:
 	return ret;
 }
 
-int probe_file__del_events(int fd, struct strfilter *filter)
+int probe_file__get_events(int fd, struct strfilter *filter,
+			   struct strlist *plist)
 {
 	struct strlist *namelist;
 	struct str_node *ent;
@@ -290,12 +290,43 @@ int probe_file__del_events(int fd, struct strfilter *filter)
 		p = strchr(ent->s, ':');
 		if ((p && strfilter__compare(filter, p + 1)) ||
 		    strfilter__compare(filter, ent->s)) {
-			ret = __del_trace_probe_event(fd, ent);
-			if (ret < 0)
-				break;
+			strlist__add(plist, ent->s);
+			ret = 0;
 		}
 	}
 	strlist__delete(namelist);
 
 	return ret;
 }
+
+int probe_file__del_strlist(int fd, struct strlist *namelist)
+{
+	int ret = 0;
+	struct str_node *ent;
+
+	strlist__for_each(ent, namelist) {
+		ret = __del_trace_probe_event(fd, ent);
+		if (ret < 0)
+			break;
+	}
+	return ret;
+}
+
+int probe_file__del_events(int fd, struct strfilter *filter)
+{
+	struct strlist *namelist;
+	int ret;
+
+	namelist = strlist__new(NULL, NULL);
+	if (!namelist)
+		return -ENOMEM;
+
+	ret = probe_file__get_events(fd, filter, namelist);
+	if (ret < 0)
+		return ret;
+
+	ret = probe_file__del_strlist(fd, namelist);
+	strlist__delete(namelist);
+
+	return ret;
+}
diff --git a/tools/perf/util/probe-file.h b/tools/perf/util/probe-file.h
index ada94a242a17..18ac9cf51c34 100644
--- a/tools/perf/util/probe-file.h
+++ b/tools/perf/util/probe-file.h
@@ -14,5 +14,9 @@ struct strlist *probe_file__get_namelist(int fd);
 struct strlist *probe_file__get_rawlist(int fd);
 int probe_file__add_event(int fd, struct probe_trace_event *tev);
 int probe_file__del_events(int fd, struct strfilter *filter);
+int probe_file__get_events(int fd, struct strfilter *filter,
+				  struct strlist *plist);
+int probe_file__del_strlist(int fd, struct strlist *namelist);
+
 
 #endif
diff --git a/tools/perf/util/scripting-engines/trace-event-perl.c b/tools/perf/util/scripting-engines/trace-event-perl.c
index 1bd593bbf7a5..544509c159ce 100644
--- a/tools/perf/util/scripting-engines/trace-event-perl.c
+++ b/tools/perf/util/scripting-engines/trace-event-perl.c
@@ -221,6 +221,7 @@ static void define_event_symbols(struct event_format *event,
 		break;
 	case PRINT_BSTRING:
 	case PRINT_DYNAMIC_ARRAY:
+	case PRINT_DYNAMIC_ARRAY_LEN:
 	case PRINT_STRING:
 	case PRINT_BITMASK:
 		break;
diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index ace2484985cb..aa9e1257c1ee 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -251,6 +251,7 @@ static void define_event_symbols(struct event_format *event,
 		/* gcc warns for these? */
 	case PRINT_BSTRING:
 	case PRINT_DYNAMIC_ARRAY:
+	case PRINT_DYNAMIC_ARRAY_LEN:
 	case PRINT_FUNC:
 	case PRINT_BITMASK:
 		/* we should warn... */
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 8a4537ee9bc3..23fed17307ff 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -185,6 +185,7 @@ static void perf_session_env__exit(struct perf_env *env)
 	zfree(&env->sibling_threads);
 	zfree(&env->numa_nodes);
 	zfree(&env->pmu_mappings);
+	zfree(&env->cpu);
 }
 
 void perf_session__delete(struct perf_session *session)
@@ -1079,11 +1080,11 @@ static int machines__deliver_event(struct machines *machines,
 
 	switch (event->header.type) {
 	case PERF_RECORD_SAMPLE:
-		dump_sample(evsel, event, sample);
 		if (evsel == NULL) {
 			++evlist->stats.nr_unknown_id;
 			return 0;
 		}
+		dump_sample(evsel, event, sample);
 		if (machine == NULL) {
 			++evlist->stats.nr_unprocessable_samples;
 			return 0;
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index 7e3871606df3..a97bceeac0e7 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -328,8 +328,8 @@ static char *get_srcfile(struct hist_entry *e)
 	char *sf, *p;
 	struct map *map = e->ms.map;
 
-	sf = get_srcline(map->dso, map__rip_2objdump(map, e->ip),
-			 e->ms.sym, true);
+	sf = __get_srcline(map->dso, map__rip_2objdump(map, e->ip),
+			 e->ms.sym, false, true);
 	if (!strcmp(sf, SRCLINE_UNKNOWN))
 		return no_srcfile;
 	p = strchr(sf, ':');
diff --git a/tools/perf/util/srcline.c b/tools/perf/util/srcline.c
index fc08248f08ca..b4db3f48e3b0 100644
--- a/tools/perf/util/srcline.c
+++ b/tools/perf/util/srcline.c
@@ -149,8 +149,11 @@ static void addr2line_cleanup(struct a2l_data *a2l)
 	free(a2l);
 }
 
+#define MAX_INLINE_NEST 1024
+
 static int addr2line(const char *dso_name, u64 addr,
-		     char **file, unsigned int *line, struct dso *dso)
+		     char **file, unsigned int *line, struct dso *dso,
+		     bool unwind_inlines)
 {
 	int ret = 0;
 	struct a2l_data *a2l = dso->a2l;
@@ -170,6 +173,15 @@ static int addr2line(const char *dso_name, u64 addr,
 
 	bfd_map_over_sections(a2l->abfd, find_address_in_section, a2l);
 
+	if (a2l->found && unwind_inlines) {
+		int cnt = 0;
+
+		while (bfd_find_inliner_info(a2l->abfd, &a2l->filename,
+					     &a2l->funcname, &a2l->line) &&
+		       cnt++ < MAX_INLINE_NEST)
+			;
+	}
+
 	if (a2l->found && a2l->filename) {
 		*file = strdup(a2l->filename);
 		*line = a2l->line;
@@ -197,7 +209,8 @@ void dso__free_a2l(struct dso *dso)
 
 static int addr2line(const char *dso_name, u64 addr,
 		     char **file, unsigned int *line_nr,
-		     struct dso *dso __maybe_unused)
+		     struct dso *dso __maybe_unused,
+		     bool unwind_inlines __maybe_unused)
 {
 	FILE *fp;
 	char cmd[PATH_MAX];
@@ -254,8 +267,8 @@ void dso__free_a2l(struct dso *dso __maybe_unused)
  */
 #define A2L_FAIL_LIMIT 123
 
-char *get_srcline(struct dso *dso, u64 addr, struct symbol *sym,
-		  bool show_sym)
+char *__get_srcline(struct dso *dso, u64 addr, struct symbol *sym,
+		  bool show_sym, bool unwind_inlines)
 {
 	char *file = NULL;
 	unsigned line = 0;
@@ -276,7 +289,7 @@ char *get_srcline(struct dso *dso, u64 addr, struct symbol *sym,
 	if (!strncmp(dso_name, "/tmp/perf-", 10))
 		goto out;
 
-	if (!addr2line(dso_name, addr, &file, &line, dso))
+	if (!addr2line(dso_name, addr, &file, &line, dso, unwind_inlines))
 		goto out;
 
 	if (asprintf(&srcline, "%s:%u",
@@ -310,3 +323,9 @@ void free_srcline(char *srcline)
 	if (srcline && strcmp(srcline, SRCLINE_UNKNOWN) != 0)
 		free(srcline);
 }
+
+char *get_srcline(struct dso *dso, u64 addr, struct symbol *sym,
+		  bool show_sym)
+{
+	return __get_srcline(dso, addr, sym, show_sym, false);
+}
diff --git a/tools/perf/util/trace-event-info.c b/tools/perf/util/trace-event-info.c
index 22245986e59e..d995743cb673 100644
--- a/tools/perf/util/trace-event-info.c
+++ b/tools/perf/util/trace-event-info.c
@@ -38,7 +38,7 @@
 
 #include "../perf.h"
 #include "trace-event.h"
-#include <api/fs/debugfs.h>
+#include <api/fs/tracing_path.h>
 #include "evsel.h"
 #include "debug.h"
 
diff --git a/tools/perf/util/trace-event.c b/tools/perf/util/trace-event.c
index b90e646c7a91..2f4996ab313d 100644
--- a/tools/perf/util/trace-event.c
+++ b/tools/perf/util/trace-event.c
@@ -8,6 +8,7 @@
 #include <fcntl.h>
 #include <linux/kernel.h>
 #include <traceevent/event-parse.h>
+#include <api/fs/tracing_path.h>
 #include "trace-event.h"
 #include "machine.h"
 #include "util.h"
diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c
index 7acafb3c5592..49a5c6ad55f5 100644
--- a/tools/perf/util/util.c
+++ b/tools/perf/util/util.c
@@ -34,9 +34,6 @@ bool test_attr__enabled;
 bool perf_host  = true;
 bool perf_guest = false;
 
-char tracing_path[PATH_MAX + 1]        = "/sys/kernel/debug/tracing";
-char tracing_events_path[PATH_MAX + 1] = "/sys/kernel/debug/tracing/events";
-
 void event_attr_init(struct perf_event_attr *attr)
 {
 	if (!perf_host)
@@ -390,73 +387,6 @@ void set_term_quiet_input(struct termios *old)
 	tcsetattr(0, TCSANOW, &tc);
 }
 
-static void set_tracing_events_path(const char *tracing, const char *mountpoint)
-{
-	snprintf(tracing_path, sizeof(tracing_path), "%s/%s",
-		 mountpoint, tracing);
-	snprintf(tracing_events_path, sizeof(tracing_events_path), "%s/%s%s",
-		 mountpoint, tracing, "events");
-}
-
-static const char *__perf_tracefs_mount(const char *mountpoint)
-{
-	const char *mnt;
-
-	mnt = tracefs_mount(mountpoint);
-	if (!mnt)
-		return NULL;
-
-	set_tracing_events_path("", mnt);
-
-	return mnt;
-}
-
-static const char *__perf_debugfs_mount(const char *mountpoint)
-{
-	const char *mnt;
-
-	mnt = debugfs_mount(mountpoint);
-	if (!mnt)
-		return NULL;
-
-	set_tracing_events_path("tracing/", mnt);
-
-	return mnt;
-}
-
-const char *perf_debugfs_mount(const char *mountpoint)
-{
-	const char *mnt;
-
-	mnt = __perf_tracefs_mount(mountpoint);
-	if (mnt)
-		return mnt;
-
-	mnt = __perf_debugfs_mount(mountpoint);
-
-	return mnt;
-}
-
-void perf_debugfs_set_path(const char *mntpt)
-{
-	set_tracing_events_path("tracing/", mntpt);
-}
-
-char *get_tracing_file(const char *name)
-{
-	char *file;
-
-	if (asprintf(&file, "%s/%s", tracing_path, name) < 0)
-		return NULL;
-
-	return file;
-}
-
-void put_tracing_file(char *file)
-{
-	free(file);
-}
-
 int parse_nsec_time(const char *str, u64 *ptime)
 {
 	u64 time_sec, time_nsec;
diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h
index 291be1d84bc3..495b99ccb588 100644
--- a/tools/perf/util/util.h
+++ b/tools/perf/util/util.h
@@ -83,12 +83,6 @@
 extern const char *graph_line;
 extern const char *graph_dotted_line;
 extern char buildid_dir[];
-extern char tracing_path[];
-extern char tracing_events_path[];
-extern void perf_debugfs_set_path(const char *mountpoint);
-const char *perf_debugfs_mount(const char *mountpoint);
-char *get_tracing_file(const char *name);
-void put_tracing_file(char *file);
 
 /* On most systems <limits.h> would have given us this, but
  * not on some systems (e.g. GNU/Hurd).
@@ -321,6 +315,8 @@ struct symbol;
 extern bool srcline_full_filename;
 char *get_srcline(struct dso *dso, u64 addr, struct symbol *sym,
 		  bool show_sym);
+char *__get_srcline(struct dso *dso, u64 addr, struct symbol *sym,
+		  bool show_sym, bool unwind_inlines);
 void free_srcline(char *srcline);
 
 int filename__read_str(const char *filename, char **buf, size_t *sizep);