Merge branch 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull perf changes from Ingo Molnar:
 "Main changes:

  Kernel side changes:

   - Add SNB/IVB/HSW client uncore memory controller support (Stephane
     Eranian)

   - Fix various x86/P4 PMU driver bugs (Don Zickus)

  Tooling, user visible changes:

   - Add several futex 'perf bench' microbenchmarks (Davidlohr Bueso)

   - Speed up thread map generation (Don Zickus)

   - Introduce 'perf kvm --list-cmds' command line option for use by
     scripts (Ramkumar Ramachandra)

   - Print the evsel name in the annotate stdio output, prep to fix
     support outputting annotation for multiple events, not just for the
     first one (Arnaldo Carvalho de Melo)

   - Allow setting preferred callchain method in .perfconfig (Jiri Olsa)

   - Show in what binaries/modules 'perf probe's are set (Masami
     Hiramatsu)

   - Support distro-style debuginfo for uprobe in 'perf probe' (Masami
     Hiramatsu)

  Tooling, internal changes and fixes:

   - Use tid in mmap/mmap2 events to find maps (Don Zickus)

   - Record the reason for filtering an address_location (Namhyung Kim)

   - Apply all filters to an addr_location (Namhyung Kim)

   - Merge al->filtered with hist_entry->filtered in report/hists
     (Namhyung Kim)

   - Fix memory leak when synthesizing thread records (Namhyung Kim)

   - Use ui__has_annotation() in 'report' (Namhyung Kim)

   - hists browser refactorings to reuse code accross UIs (Namhyung Kim)

   - Add support for the new DWARF unwinder library in elfutils (Jiri
     Olsa)

   - Fix build race in the generation of bison files (Jiri Olsa)

   - Further streamline the feature detection display, trimming it a bit
     to show just the libraries detected, using VF=1 gets a more verbose
     output, showing the less interesting feature checks as well (Jiri
     Olsa).

   - Check compatible symtab type before loading dso (Namhyung Kim)

   - Check return value of filename__read_debuglink() (Stephane Eranian)

   - Move some hashing and fs related code from tools/perf/util/ to
     tools/lib/ so that it can be used by more tools/ living utilities
     (Borislav Petkov)

   - Prepare DWARF unwinding code for using an elfutils alternative
     unwinding library (Jiri Olsa)

   - Fix DWARF unwind max_stack processing (Jiri Olsa)

   - Add dwarf unwind 'perf test' entry (Jiri Olsa)

   - 'perf probe' improvements including memory leak fixes, sharing the
     intlist class with other tools, uprobes/kprobes code sharing and
     use of ref_reloc_sym (Masami Hiramatsu)

   - Shorten sample symbol resolving by adding cpumode to struct
     addr_location (Arnaldo Carvalho de Melo)

   - Fix synthesizing mmaps for threads (Don Zickus)

   - Fix invalid output on event group stdio report (Namhyung Kim)

   - Fixup header alignment in 'perf sched latency' output (Ramkumar
     Ramachandra)

   - Fix off-by-one error in 'perf timechart record' argv handling
     (Ramkumar Ramachandra)

  Tooling, cleanups:

   - Remove unused thread__find_map function (Jiri Olsa)

   - Remove unused simple_strtoul() function (Ramkumar Ramachandra)

  Tooling, documentation updates:

   - Update function names in debug messages (Ramkumar Ramachandra)

   - Update some code references in design.txt (Ramkumar Ramachandra)

   - Clarify load-latency information in the 'perf mem' docs (Andi
     Kleen)

   - Clarify x86 register naming in 'perf probe' docs (Andi Kleen)"

* 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (96 commits)
  perf tools: Remove unused simple_strtoul() function
  perf tools: Update some code references in design.txt
  perf evsel: Update function names in debug messages
  perf tools: Remove thread__find_map function
  perf annotate: Print the evsel name in the stdio output
  perf report: Use ui__has_annotation()
  perf tools: Fix memory leak when synthesizing thread records
  perf tools: Use tid in mmap/mmap2 events to find maps
  perf report: Merge al->filtered with hist_entry->filtered
  perf symbols: Apply all filters to an addr_location
  perf symbols: Record the reason for filtering an address_location
  perf sched: Fixup header alignment in 'latency' output
  perf timechart: Fix off-by-one error in 'record' argv handling
  perf machine: Factor machine__find_thread to take tid argument
  perf tools: Speed up thread map generation
  perf kvm: introduce --list-cmds for use by scripts
  perf ui hists: Pass evsel to hpp->header/width functions explicitly
  perf symbols: Introduce thread__find_cpumode_addr_location
  perf session: Change header.misc dump from decimal to hex
  perf ui/tui: Reuse generic __hpp__fmt() code
  ...

43 files changed, 1232 insertions, 947 deletions

diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 3aa555ff9d8..809b4c50bea 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -1236,6 +1236,7 @@ int symbol__annotate_printf(struct symbol *sym, struct map *map,
 	struct dso *dso = map->dso;
 	char *filename;
 	const char *d_filename;
+	const char *evsel_name = perf_evsel__name(evsel);
 	struct annotation *notes = symbol__annotation(sym);
 	struct disasm_line *pos, *queue = NULL;
 	u64 start = map__rip_2objdump(map, sym->start);
@@ -1243,7 +1244,7 @@ int symbol__annotate_printf(struct symbol *sym, struct map *map,
 	int more = 0;
 	u64 len;
 	int width = 8;
-	int namelen;
+	int namelen, evsel_name_len, graph_dotted_len;
 
 	filename = strdup(dso->long_name);
 	if (!filename)
@@ -1256,14 +1257,17 @@ int symbol__annotate_printf(struct symbol *sym, struct map *map,
 
 	len = symbol__size(sym);
 	namelen = strlen(d_filename);
+	evsel_name_len = strlen(evsel_name);
 
 	if (perf_evsel__is_group_event(evsel))
 		width *= evsel->nr_members;
 
-	printf(" %-*.*s|	Source code & Disassembly of %s\n",
-	       width, width, "Percent", d_filename);
-	printf("-%-*.*s-------------------------------------\n",
-	       width+namelen, width+namelen, graph_dotted_line);
+	printf(" %-*.*s|	Source code & Disassembly of %s for %s\n",
+	       width, width, "Percent", d_filename, evsel_name);
+
+	graph_dotted_len = width + namelen + evsel_name_len;
+	printf("-%-*.*s-----------------------------------------\n",
+	       graph_dotted_len, graph_dotted_len, graph_dotted_line);
 
 	if (verbose)
 		symbol__annotate_hits(sym, evsel);
diff --git a/tools/perf/util/cpumap.c b/tools/perf/util/cpumap.c
index a9b48c42e81..7fe4994eeb6 100644
--- a/tools/perf/util/cpumap.c
+++ b/tools/perf/util/cpumap.c
@@ -1,5 +1,5 @@
 #include "util.h"
-#include "fs.h"
+#include <api/fs/fs.h>
 #include "../perf.h"
 #include "cpumap.h"
 #include <assert.h>
diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c
index 4045d086d9d..64453d63b97 100644
--- a/tools/perf/util/dso.c
+++ b/tools/perf/util/dso.c
@@ -45,8 +45,8 @@ int dso__read_binary_type_filename(const struct dso *dso,
 			debuglink--;
 		if (*debuglink == '/')
 			debuglink++;
-		filename__read_debuglink(dso->long_name, debuglink,
-					 size - (debuglink - filename));
+		ret = filename__read_debuglink(dso->long_name, debuglink,
+					       size - (debuglink - filename));
 		}
 		break;
 	case DSO_BINARY_TYPE__BUILD_ID_CACHE:
diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h
index cd7d6f078cd..ab06f1c0365 100644
--- a/tools/perf/util/dso.h
+++ b/tools/perf/util/dso.h
@@ -102,6 +102,16 @@ struct dso {
 	char		 name[0];
 };
 
+/* dso__for_each_symbol - iterate over the symbols of given type
+ *
+ * @dso: the 'struct dso *' in which symbols itereated
+ * @pos: the 'struct symbol *' to use as a loop cursor
+ * @n: the 'struct rb_node *' to use as a temporary storage
+ * @type: the 'enum map_type' type of symbols
+ */
+#define dso__for_each_symbol(dso, pos, n, type)	\
+	symbols__for_each_entry(&(dso)->symbols[(type)], pos, n)
+
 static inline void dso__set_loaded(struct dso *dso, enum map_type type)
 {
 	dso->loaded |= (1 << type);
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index b0f3ca850e9..9d12aa6dd48 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -1,6 +1,7 @@
 #include <linux/types.h>
 #include "event.h"
 #include "debug.h"
+#include "hist.h"
 #include "machine.h"
 #include "sort.h"
 #include "string.h"
@@ -94,14 +95,10 @@ static pid_t perf_event__get_comm_tgid(pid_t pid, char *comm, size_t len)
 
 static pid_t perf_event__synthesize_comm(struct perf_tool *tool,
 					 union perf_event *event, pid_t pid,
-					 int full,
 					 perf_event__handler_t process,
 					 struct machine *machine)
 {
-	char filename[PATH_MAX];
 	size_t size;
-	DIR *tasks;
-	struct dirent dirent, *next;
 	pid_t tgid;
 
 	memset(&event->comm, 0, sizeof(event->comm));
@@ -124,55 +121,35 @@ static pid_t perf_event__synthesize_comm(struct perf_tool *tool,
 	event->comm.header.size = (sizeof(event->comm) -
 				(sizeof(event->comm.comm) - size) +
 				machine->id_hdr_size);
-	if (!full) {
-		event->comm.tid = pid;
+	event->comm.tid = pid;
 
-		if (process(tool, event, &synth_sample, machine) != 0)
-			return -1;
-
-		goto out;
-	}
-
-	if (machine__is_default_guest(machine))
-		return 0;
-
-	snprintf(filename, sizeof(filename), "%s/proc/%d/task",
-		 machine->root_dir, pid);
-
-	tasks = opendir(filename);
-	if (tasks == NULL) {
-		pr_debug("couldn't open %s\n", filename);
-		return 0;
-	}
+	if (process(tool, event, &synth_sample, machine) != 0)
+		return -1;
 
-	while (!readdir_r(tasks, &dirent, &next) && next) {
-		char *end;
-		pid = strtol(dirent.d_name, &end, 10);
-		if (*end)
-			continue;
+out:
+	return tgid;
+}
 
-		/* already have tgid; jut want to update the comm */
-		(void) perf_event__get_comm_tgid(pid, event->comm.comm,
-					 sizeof(event->comm.comm));
+static int perf_event__synthesize_fork(struct perf_tool *tool,
+				       union perf_event *event, pid_t pid,
+				       pid_t tgid, perf_event__handler_t process,
+				       struct machine *machine)
+{
+	memset(&event->fork, 0, sizeof(event->fork) + machine->id_hdr_size);
 
-		size = strlen(event->comm.comm) + 1;
-		size = PERF_ALIGN(size, sizeof(u64));
-		memset(event->comm.comm + size, 0, machine->id_hdr_size);
-		event->comm.header.size = (sizeof(event->comm) -
-					  (sizeof(event->comm.comm) - size) +
-					  machine->id_hdr_size);
+	/* this is really a clone event but we use fork to synthesize it */
+	event->fork.ppid = tgid;
+	event->fork.ptid = tgid;
+	event->fork.pid  = tgid;
+	event->fork.tid  = pid;
+	event->fork.header.type = PERF_RECORD_FORK;
 
-		event->comm.tid = pid;
+	event->fork.header.size = (sizeof(event->fork) + machine->id_hdr_size);
 
-		if (process(tool, event, &synth_sample, machine) != 0) {
-			tgid = -1;
-			break;
-		}
-	}
+	if (process(tool, event, &synth_sample, machine) != 0)
+		return -1;
 
-	closedir(tasks);
-out:
-	return tgid;
+	return 0;
 }
 
 int perf_event__synthesize_mmap_events(struct perf_tool *tool,
@@ -324,17 +301,71 @@ int perf_event__synthesize_modules(struct perf_tool *tool,
 
 static int __event__synthesize_thread(union perf_event *comm_event,
 				      union perf_event *mmap_event,
+				      union perf_event *fork_event,
 				      pid_t pid, int full,
 					  perf_event__handler_t process,
 				      struct perf_tool *tool,
 				      struct machine *machine, bool mmap_data)
 {
-	pid_t tgid = perf_event__synthesize_comm(tool, comm_event, pid, full,
+	char filename[PATH_MAX];
+	DIR *tasks;
+	struct dirent dirent, *next;
+	pid_t tgid;
+
+	/* special case: only send one comm event using passed in pid */
+	if (!full) {
+		tgid = perf_event__synthesize_comm(tool, comm_event, pid,
+						   process, machine);
+
+		if (tgid == -1)
+			return -1;
+
+		return perf_event__synthesize_mmap_events(tool, mmap_event, pid, tgid,
+							  process, machine, mmap_data);
+	}
+
+	if (machine__is_default_guest(machine))
+		return 0;
+
+	snprintf(filename, sizeof(filename), "%s/proc/%d/task",
+		 machine->root_dir, pid);
+
+	tasks = opendir(filename);
+	if (tasks == NULL) {
+		pr_debug("couldn't open %s\n", filename);
+		return 0;
+	}
+
+	while (!readdir_r(tasks, &dirent, &next) && next) {
+		char *end;
+		int rc = 0;
+		pid_t _pid;
+
+		_pid = strtol(dirent.d_name, &end, 10);
+		if (*end)
+			continue;
+
+		tgid = perf_event__synthesize_comm(tool, comm_event, _pid,
+						   process, machine);
+		if (tgid == -1)
+			return -1;
+
+		if (_pid == pid) {
+			/* process the parent's maps too */
+			rc = perf_event__synthesize_mmap_events(tool, mmap_event, pid, tgid,
+						process, machine, mmap_data);
+		} else {
+			/* only fork the tid's map, to save time */
+			rc = perf_event__synthesize_fork(tool, fork_event, _pid, tgid,
 						 process, machine);
-	if (tgid == -1)
-		return -1;
-	return perf_event__synthesize_mmap_events(tool, mmap_event, pid, tgid,
-						  process, machine, mmap_data);
+		}
+
+		if (rc)
+			return rc;
+	}
+
+	closedir(tasks);
+	return 0;
 }
 
 int perf_event__synthesize_thread_map(struct perf_tool *tool,
@@ -343,7 +374,7 @@ int perf_event__synthesize_thread_map(struct perf_tool *tool,
 				      struct machine *machine,
 				      bool mmap_data)
 {
-	union perf_event *comm_event, *mmap_event;
+	union perf_event *comm_event, *mmap_event, *fork_event;
 	int err = -1, thread, j;
 
 	comm_event = malloc(sizeof(comm_event->comm) + machine->id_hdr_size);
@@ -354,9 +385,14 @@ int perf_event__synthesize_thread_map(struct perf_tool *tool,
 	if (mmap_event == NULL)
 		goto out_free_comm;
 
+	fork_event = malloc(sizeof(fork_event->fork) + machine->id_hdr_size);
+	if (fork_event == NULL)
+		goto out_free_mmap;
+
 	err = 0;
 	for (thread = 0; thread < threads->nr; ++thread) {
 		if (__event__synthesize_thread(comm_event, mmap_event,
+					       fork_event,
 					       threads->map[thread], 0,
 					       process, tool, machine,
 					       mmap_data)) {
@@ -382,6 +418,7 @@ int perf_event__synthesize_thread_map(struct perf_tool *tool,
 			/* if not, generate events for it */
 			if (need_leader &&
 			    __event__synthesize_thread(comm_event, mmap_event,
+						       fork_event,
 						       comm_event->comm.pid, 0,
 						       process, tool, machine,
 						       mmap_data)) {
@@ -390,6 +427,8 @@ int perf_event__synthesize_thread_map(struct perf_tool *tool,
 			}
 		}
 	}
+	free(fork_event);
+out_free_mmap:
 	free(mmap_event);
 out_free_comm:
 	free(comm_event);
@@ -404,9 +443,12 @@ int perf_event__synthesize_threads(struct perf_tool *tool,
 	DIR *proc;
 	char proc_path[PATH_MAX];
 	struct dirent dirent, *next;
-	union perf_event *comm_event, *mmap_event;
+	union perf_event *comm_event, *mmap_event, *fork_event;
 	int err = -1;
 
+	if (machine__is_default_guest(machine))
+		return 0;
+
 	comm_event = malloc(sizeof(comm_event->comm) + machine->id_hdr_size);
 	if (comm_event == NULL)
 		goto out;
@@ -415,14 +457,15 @@ int perf_event__synthesize_threads(struct perf_tool *tool,
 	if (mmap_event == NULL)
 		goto out_free_comm;
 
-	if (machine__is_default_guest(machine))
-		return 0;
+	fork_event = malloc(sizeof(fork_event->fork) + machine->id_hdr_size);
+	if (fork_event == NULL)
+		goto out_free_mmap;
 
 	snprintf(proc_path, sizeof(proc_path), "%s/proc", machine->root_dir);
 	proc = opendir(proc_path);
 
 	if (proc == NULL)
-		goto out_free_mmap;
+		goto out_free_fork;
 
 	while (!readdir_r(proc, &dirent, &next) && next) {
 		char *end;
@@ -434,12 +477,14 @@ int perf_event__synthesize_threads(struct perf_tool *tool,
  		 * We may race with exiting thread, so don't stop just because
  		 * one thread couldn't be synthesized.
  		 */
-		__event__synthesize_thread(comm_event, mmap_event, pid, 1,
-					   process, tool, machine, mmap_data);
+		__event__synthesize_thread(comm_event, mmap_event, fork_event, pid,
+					   1, process, tool, machine, mmap_data);
 	}
 
 	err = 0;
 	closedir(proc);
+out_free_fork:
+	free(fork_event);
 out_free_mmap:
 	free(mmap_event);
 out_free_comm:
@@ -661,7 +706,7 @@ void thread__find_addr_map(struct thread *thread,
 	al->thread = thread;
 	al->addr = addr;
 	al->cpumode = cpumode;
-	al->filtered = false;
+	al->filtered = 0;
 
 	if (machine == NULL) {
 		al->map = NULL;
@@ -687,11 +732,11 @@ void thread__find_addr_map(struct thread *thread,
 		if ((cpumode == PERF_RECORD_MISC_GUEST_USER ||
 			cpumode == PERF_RECORD_MISC_GUEST_KERNEL) &&
 			!perf_guest)
-			al->filtered = true;
+			al->filtered |= (1 << HIST_FILTER__GUEST);
 		if ((cpumode == PERF_RECORD_MISC_USER ||
 			cpumode == PERF_RECORD_MISC_KERNEL) &&
 			!perf_host)
-			al->filtered = true;
+			al->filtered |= (1 << HIST_FILTER__HOST);
 
 		return;
 	}
@@ -748,9 +793,6 @@ int perf_event__preprocess_sample(const union perf_event *event,
 	if (thread == NULL)
 		return -1;
 
-	if (thread__is_filtered(thread))
-		goto out_filtered;
-
 	dump_printf(" ... thread: %s:%d\n", thread__comm_str(thread), thread->tid);
 	/*
 	 * Have we already created the kernel maps for this machine?
@@ -768,6 +810,10 @@ int perf_event__preprocess_sample(const union perf_event *event,
 	dump_printf(" ...... dso: %s\n",
 		    al->map ? al->map->dso->long_name :
 			al->level == 'H' ? "[hypervisor]" : "<not found>");
+
+	if (thread__is_filtered(thread))
+		al->filtered |= (1 << HIST_FILTER__THREAD);
+
 	al->sym = NULL;
 	al->cpu = sample->cpu;
 
@@ -779,8 +825,9 @@ int perf_event__preprocess_sample(const union perf_event *event,
 						  dso->short_name) ||
 			       (dso->short_name != dso->long_name &&
 				strlist__has_entry(symbol_conf.dso_list,
-						   dso->long_name)))))
-			goto out_filtered;
+						   dso->long_name))))) {
+			al->filtered |= (1 << HIST_FILTER__DSO);
+		}
 
 		al->sym = map__find_symbol(al->map, al->addr,
 					   machine->symbol_filter);
@@ -788,12 +835,9 @@ int perf_event__preprocess_sample(const union perf_event *event,
 
 	if (symbol_conf.sym_list &&
 		(!al->sym || !strlist__has_entry(symbol_conf.sym_list,
-						al->sym->name)))
-		goto out_filtered;
-
-	return 0;
+						al->sym->name))) {
+		al->filtered |= (1 << HIST_FILTER__SYMBOL);
+	}
 
-out_filtered:
-	al->filtered = true;
 	return 0;
 }
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index 851fa06f4a4..38457d447a1 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -85,6 +85,7 @@ struct sample_event {
 
 struct regs_dump {
 	u64 abi;
+	u64 mask;
 	u64 *regs;
 };
 
@@ -259,9 +260,9 @@ int perf_event__preprocess_sample(const union perf_event *event,
 const char *perf_event__name(unsigned int id);
 
 size_t perf_event__sample_event_size(const struct perf_sample *sample, u64 type,
-				     u64 sample_regs_user, u64 read_format);
+				     u64 read_format);
 int perf_event__synthesize_sample(union perf_event *event, u64 type,
-				  u64 sample_regs_user, u64 read_format,
+				  u64 read_format,
 				  const struct perf_sample *sample,
 				  bool swapped);
 
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 55407c594b8..5c28d82b76c 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -500,6 +500,34 @@ int perf_evsel__group_desc(struct perf_evsel *evsel, char *buf, size_t size)
 	return ret;
 }
 
+static void
+perf_evsel__config_callgraph(struct perf_evsel *evsel,
+			     struct record_opts *opts)
+{
+	bool function = perf_evsel__is_function_event(evsel);
+	struct perf_event_attr *attr = &evsel->attr;
+
+	perf_evsel__set_sample_bit(evsel, CALLCHAIN);
+
+	if (opts->call_graph == CALLCHAIN_DWARF) {
+		if (!function) {
+			perf_evsel__set_sample_bit(evsel, REGS_USER);
+			perf_evsel__set_sample_bit(evsel, STACK_USER);
+			attr->sample_regs_user = PERF_REGS_MASK;
+			attr->sample_stack_user = opts->stack_dump_size;
+			attr->exclude_callchain_user = 1;
+		} else {
+			pr_info("Cannot use DWARF unwind for function trace event,"
+				" falling back to framepointers.\n");
+		}
+	}
+
+	if (function) {
+		pr_info("Disabling user space callchains for function trace event.\n");
+		attr->exclude_callchain_user = 1;
+	}
+}
+
 /*
  * The enable_on_exec/disabled value strategy:
  *
@@ -595,17 +623,8 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts)
 		attr->mmap_data = track;
 	}
 
-	if (opts->call_graph) {
-		perf_evsel__set_sample_bit(evsel, CALLCHAIN);
-
-		if (opts->call_graph == CALLCHAIN_DWARF) {
-			perf_evsel__set_sample_bit(evsel, REGS_USER);
-			perf_evsel__set_sample_bit(evsel, STACK_USER);
-			attr->sample_regs_user = PERF_REGS_MASK;
-			attr->sample_stack_user = opts->stack_dump_size;
-			attr->exclude_callchain_user = 1;
-		}
-	}
+	if (opts->call_graph_enabled)
+		perf_evsel__config_callgraph(evsel, opts);
 
 	if (target__has_cpu(&opts->target))
 		perf_evsel__set_sample_bit(evsel, CPU);
@@ -1004,7 +1023,7 @@ retry_sample_id:
 
 			group_fd = get_group_fd(evsel, cpu, thread);
 retry_open:
-			pr_debug2("perf_event_open: pid %d  cpu %d  group_fd %d  flags %#lx\n",
+			pr_debug2("sys_perf_event_open: pid %d  cpu %d  group_fd %d  flags %#lx\n",
 				  pid, cpus->map[cpu], group_fd, flags);
 
 			FD(evsel, cpu, thread) = sys_perf_event_open(&evsel->attr,
@@ -1013,7 +1032,7 @@ retry_open:
 								     group_fd, flags);
 			if (FD(evsel, cpu, thread) < 0) {
 				err = -errno;
-				pr_debug2("perf_event_open failed, error %d\n",
+				pr_debug2("sys_perf_event_open failed, error %d\n",
 					  err);
 				goto try_fallback;
 			}
@@ -1220,7 +1239,7 @@ int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event,
 	memset(data, 0, sizeof(*data));
 	data->cpu = data->pid = data->tid = -1;
 	data->stream_id = data->id = data->time = -1ULL;
-	data->period = 1;
+	data->period = evsel->attr.sample_period;
 	data->weight = 0;
 
 	if (event->header.type != PERF_RECORD_SAMPLE) {
@@ -1396,10 +1415,11 @@ int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event,
 		array++;
 
 		if (data->user_regs.abi) {
-			u64 regs_user = evsel->attr.sample_regs_user;
+			u64 mask = evsel->attr.sample_regs_user;
 
-			sz = hweight_long(regs_user) * sizeof(u64);
+			sz = hweight_long(mask) * sizeof(u64);
 			OVERFLOW_CHECK(array, sz, max_size);
+			data->user_regs.mask = mask;
 			data->user_regs.regs = (u64 *)array;
 			array = (void *)array + sz;
 		}
@@ -1451,7 +1471,7 @@ int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event,
 }
 
 size_t perf_event__sample_event_size(const struct perf_sample *sample, u64 type,
-				     u64 sample_regs_user, u64 read_format)
+				     u64 read_format)
 {
 	size_t sz, result = sizeof(struct sample_event);
 
@@ -1517,7 +1537,7 @@ size_t perf_event__sample_event_size(const struct perf_sample *sample, u64 type,
 	if (type & PERF_SAMPLE_REGS_USER) {
 		if (sample->user_regs.abi) {
 			result += sizeof(u64);
-			sz = hweight_long(sample_regs_user) * sizeof(u64);
+			sz = hweight_long(sample->user_regs.mask) * sizeof(u64);
 			result += sz;
 		} else {
 			result += sizeof(u64);
@@ -1546,7 +1566,7 @@ size_t perf_event__sample_event_size(const struct perf_sample *sample, u64 type,
 }
 
 int perf_event__synthesize_sample(union perf_event *event, u64 type,
-				  u64 sample_regs_user, u64 read_format,
+				  u64 read_format,
 				  const struct perf_sample *sample,
 				  bool swapped)
 {
@@ -1687,7 +1707,7 @@ int perf_event__synthesize_sample(union perf_event *event, u64 type,
 	if (type & PERF_SAMPLE_REGS_USER) {
 		if (sample->user_regs.abi) {
 			*array++ = sample->user_regs.abi;
-			sz = hweight_long(sample_regs_user) * sizeof(u64);
+			sz = hweight_long(sample->user_regs.mask) * sizeof(u64);
 			memcpy(array, sample->user_regs.regs, sz);
 			array = (void *)array + sz;
 		} else {
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index f1b325665aa..0c9926cfb29 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -315,6 +315,24 @@ static inline bool perf_evsel__is_group_event(struct perf_evsel *evsel)
 	return perf_evsel__is_group_leader(evsel) && evsel->nr_members > 1;
 }
 
+/**
+ * perf_evsel__is_function_event - Return whether given evsel is a function
+ * trace event
+ *
+ * @evsel - evsel selector to be tested
+ *
+ * Return %true if event is function trace event
+ */
+static inline bool perf_evsel__is_function_event(struct perf_evsel *evsel)
+{
+#define FUNCTION_EVENT "ftrace:function"
+
+	return evsel->name &&
+	       !strncmp(FUNCTION_EVENT, evsel->name, sizeof(FUNCTION_EVENT));
+
+#undef FUNCTION_EVENT
+}
+
 struct perf_attr_details {
 	bool freq;
 	bool verbose;
diff --git a/tools/perf/util/fs.c b/tools/perf/util/fs.c
deleted file mode 100644
index f5be1f26e72..00000000000
--- a/tools/perf/util/fs.c
+++ /dev/null
@@ -1,119 +0,0 @@
-
-/* TODO merge/factor into tools/lib/lk/debugfs.c */
-
-#include "util.h"
-#include "util/fs.h"
-
-static const char * const sysfs__fs_known_mountpoints[] = {
-	"/sys",
-	0,
-};
-
-static const char * const procfs__known_mountpoints[] = {
-	"/proc",
-	0,
-};
-
-struct fs {
-	const char		*name;
-	const char * const	*mounts;
-	char			 path[PATH_MAX + 1];
-	bool			 found;
-	long			 magic;
-};
-
-enum {
-	FS__SYSFS  = 0,
-	FS__PROCFS = 1,
-};
-
-static struct fs fs__entries[] = {
-	[FS__SYSFS] = {
-		.name	= "sysfs",
-		.mounts	= sysfs__fs_known_mountpoints,
-		.magic	= SYSFS_MAGIC,
-	},
-	[FS__PROCFS] = {
-		.name	= "proc",
-		.mounts	= procfs__known_mountpoints,
-		.magic	= PROC_SUPER_MAGIC,
-	},
-};
-
-static bool fs__read_mounts(struct fs *fs)
-{
-	bool found = false;
-	char type[100];
-	FILE *fp;
-
-	fp = fopen("/proc/mounts", "r");
-	if (fp == NULL)
-		return NULL;
-
-	while (!found &&
-	       fscanf(fp, "%*s %" STR(PATH_MAX) "s %99s %*s %*d %*d\n",
-		      fs->path, type) == 2) {
-
-		if (strcmp(type, fs->name) == 0)
-			found = true;
-	}
-
-	fclose(fp);
-	return fs->found = found;
-}
-
-static int fs__valid_mount(const char *fs, long magic)
-{
-	struct statfs st_fs;
-
-	if (statfs(fs, &st_fs) < 0)
-		return -ENOENT;
-	else if (st_fs.f_type != magic)
-		return -ENOENT;
-
-	return 0;
-}
-
-static bool fs__check_mounts(struct fs *fs)
-{
-	const char * const *ptr;
-
-	ptr = fs->mounts;
-	while (*ptr) {
-		if (fs__valid_mount(*ptr, fs->magic) == 0) {
-			fs->found = true;
-			strcpy(fs->path, *ptr);
-			return true;
-		}
-		ptr++;
-	}
-
-	return false;
-}
-
-static const char *fs__get_mountpoint(struct fs *fs)
-{
-	if (fs__check_mounts(fs))
-		return fs->path;
-
-	return fs__read_mounts(fs) ? fs->path : NULL;
-}
-
-static const char *fs__mountpoint(int idx)
-{
-	struct fs *fs = &fs__entries[idx];
-
-	if (fs->found)
-		return (const char *)fs->path;
-
-	return fs__get_mountpoint(fs);
-}
-
-#define FS__MOUNTPOINT(name, idx)	\
-const char *name##__mountpoint(void)	\
-{					\
-	return fs__mountpoint(idx);	\
-}
-
-FS__MOUNTPOINT(sysfs,  FS__SYSFS);
-FS__MOUNTPOINT(procfs, FS__PROCFS);
diff --git a/tools/perf/util/fs.h b/tools/perf/util/fs.h
deleted file mode 100644
index 5e09ce1bab0..00000000000
--- a/tools/perf/util/fs.h
+++ /dev/null
@@ -1,7 +0,0 @@
-#ifndef __PERF_FS
-#define __PERF_FS
-
-const char *sysfs__mountpoint(void);
-const char *procfs__mountpoint(void);
-
-#endif /* __PERF_FS */
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index e4e6249b87d..f38590d7561 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -13,13 +13,6 @@ static bool hists__filter_entry_by_thread(struct hists *hists,
 static bool hists__filter_entry_by_symbol(struct hists *hists,
 					  struct hist_entry *he);
 
-enum hist_filter {
-	HIST_FILTER__DSO,
-	HIST_FILTER__THREAD,
-	HIST_FILTER__PARENT,
-	HIST_FILTER__SYMBOL,
-};
-
 struct callchain_param	callchain_param = {
 	.mode	= CHAIN_GRAPH_REL,
 	.min_percent = 0.5,
@@ -290,7 +283,7 @@ static struct hist_entry *hist_entry__new(struct hist_entry *template)
 		if (he->branch_info) {
 			/*
 			 * This branch info is (a part of) allocated from
-			 * machine__resolve_bstack() and will be freed after
+			 * sample__resolve_bstack() and will be freed after
 			 * adding new entries.  So we need to save a copy.
 			 */
 			he->branch_info = malloc(sizeof(*he->branch_info));
@@ -369,7 +362,7 @@ static struct hist_entry *add_hist_entry(struct hists *hists,
 			he_stat__add_period(&he->stat, period, weight);
 
 			/*
-			 * This mem info was allocated from machine__resolve_mem
+			 * This mem info was allocated from sample__resolve_mem
 			 * and will not be used anymore.
 			 */
 			zfree(&entry->mem_info);
@@ -429,7 +422,7 @@ struct hist_entry *__hists__add_entry(struct hists *hists,
 			.weight = weight,
 		},
 		.parent = sym_parent,
-		.filtered = symbol__parent_filter(sym_parent),
+		.filtered = symbol__parent_filter(sym_parent) | al->filtered,
 		.hists	= hists,
 		.branch_info = bi,
 		.mem_info = mi,
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index a59743fa3ef..1f1f513dfe7 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -14,6 +14,15 @@ struct hist_entry;
 struct addr_location;
 struct symbol;
 
+enum hist_filter {
+	HIST_FILTER__DSO,
+	HIST_FILTER__THREAD,
+	HIST_FILTER__PARENT,
+	HIST_FILTER__SYMBOL,
+	HIST_FILTER__GUEST,
+	HIST_FILTER__HOST,
+};
+
 /*
  * The kernel collects the number of events it couldn't send in a stretch and
  * when possible sends this number in a PERF_RECORD_LOST event. The number of
@@ -132,8 +141,10 @@ struct perf_hpp {
 };
 
 struct perf_hpp_fmt {
-	int (*header)(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp);
-	int (*width)(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp);
+	int (*header)(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
+		      struct perf_evsel *evsel);
+	int (*width)(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
+		     struct perf_evsel *evsel);
 	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,
@@ -166,6 +177,20 @@ void perf_hpp__init(void);
 void perf_hpp__column_register(struct perf_hpp_fmt *format);
 void perf_hpp__column_enable(unsigned col);
 
+typedef u64 (*hpp_field_fn)(struct hist_entry *he);
+typedef int (*hpp_callback_fn)(struct perf_hpp *hpp, bool front);
+typedef int (*hpp_snprint_fn)(struct perf_hpp *hpp, const char *fmt, ...);
+
+int __hpp__fmt(struct perf_hpp *hpp, struct hist_entry *he,
+	       hpp_field_fn get_field, hpp_callback_fn callback,
+	       const char *fmt, hpp_snprint_fn print_fn, bool fmt_percent);
+
+static inline void advance_hpp(struct perf_hpp *hpp, int inc)
+{
+	hpp->buf  += inc;
+	hpp->size -= inc;
+}
+
 static inline size_t perf_hpp__use_color(void)
 {
 	return !symbol_conf.field_sep;
diff --git a/tools/perf/util/include/linux/hash.h b/tools/perf/util/include/linux/hash.h
deleted file mode 100644
index 201f5739799..00000000000
--- a/tools/perf/util/include/linux/hash.h
+++ /dev/null
@@ -1,5 +0,0 @@
-#include "../../../../include/linux/hash.h"
-
-#ifndef PERF_HASH_H
-#define PERF_HASH_H
-#endif
diff --git a/tools/perf/util/include/linux/kernel.h b/tools/perf/util/include/linux/kernel.h
index d8c927c868e..9844c31b7c2 100644
--- a/tools/perf/util/include/linux/kernel.h
+++ b/tools/perf/util/include/linux/kernel.h
@@ -94,12 +94,6 @@ static inline int scnprintf(char * buf, size_t size, const char * fmt, ...)
 	return (i >= ssize) ? (ssize - 1) : i;
 }
 
-static inline unsigned long
-simple_strtoul(const char *nptr, char **endptr, int base)
-{
-	return strtoul(nptr, endptr, base);
-}
-
 int eprintf(int level,
 	    const char *fmt, ...) __attribute__((format(printf, 2, 3)));
 
diff --git a/tools/perf/util/include/linux/list.h b/tools/perf/util/include/linux/list.h
index 1d928a0ce99..bfe0a2afd0d 100644
--- a/tools/perf/util/include/linux/list.h
+++ b/tools/perf/util/include/linux/list.h
@@ -1,5 +1,4 @@
 #include <linux/kernel.h>
-#include <linux/prefetch.h>
 
 #include "../../../../include/linux/list.h"
 
diff --git a/tools/perf/util/include/linux/magic.h b/tools/perf/util/include/linux/magic.h
deleted file mode 100644
index 07d63cf3e0f..00000000000
--- a/tools/perf/util/include/linux/magic.h
+++ /dev/null
@@ -1,16 +0,0 @@
-#ifndef _PERF_LINUX_MAGIC_H_
-#define _PERF_LINUX_MAGIC_H_
-
-#ifndef DEBUGFS_MAGIC
-#define DEBUGFS_MAGIC          0x64626720
-#endif
-
-#ifndef SYSFS_MAGIC
-#define SYSFS_MAGIC            0x62656572
-#endif
-
-#ifndef PROC_SUPER_MAGIC
-#define PROC_SUPER_MAGIC       0x9fa0
-#endif
-
-#endif
diff --git a/tools/perf/util/include/linux/prefetch.h b/tools/perf/util/include/linux/prefetch.h
deleted file mode 100644
index 7841e485d8c..00000000000
--- a/tools/perf/util/include/linux/prefetch.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef PERF_LINUX_PREFETCH_H
-#define PERF_LINUX_PREFETCH_H
-
-static inline void prefetch(void *a __attribute__((unused))) { }
-
-#endif
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 620a1983b76..a53cd0b8c15 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -327,9 +327,10 @@ struct thread *machine__findnew_thread(struct machine *machine, pid_t pid,
 	return __machine__findnew_thread(machine, pid, tid, true);
 }
 
-struct thread *machine__find_thread(struct machine *machine, pid_t tid)
+struct thread *machine__find_thread(struct machine *machine, pid_t pid,
+				    pid_t tid)
 {
-	return __machine__findnew_thread(machine, 0, tid, false);
+	return __machine__findnew_thread(machine, pid, tid, false);
 }
 
 int machine__process_comm_event(struct machine *machine, union perf_event *event,
@@ -1026,7 +1027,7 @@ int machine__process_mmap2_event(struct machine *machine,
 	}
 
 	thread = machine__findnew_thread(machine, event->mmap2.pid,
-					event->mmap2.pid);
+					event->mmap2.tid);
 	if (thread == NULL)
 		goto out_problem;
 
@@ -1074,7 +1075,7 @@ int machine__process_mmap_event(struct machine *machine, union perf_event *event
 	}
 
 	thread = machine__findnew_thread(machine, event->mmap.pid,
-					 event->mmap.pid);
+					 event->mmap.tid);
 	if (thread == NULL)
 		goto out_problem;
 
@@ -1114,7 +1115,9 @@ static void machine__remove_thread(struct machine *machine, struct thread *th)
 int machine__process_fork_event(struct machine *machine, union perf_event *event,
 				struct perf_sample *sample)
 {
-	struct thread *thread = machine__find_thread(machine, event->fork.tid);
+	struct thread *thread = machine__find_thread(machine,
+						     event->fork.pid,
+						     event->fork.tid);
 	struct thread *parent = machine__findnew_thread(machine,
 							event->fork.ppid,
 							event->fork.ptid);
@@ -1140,7 +1143,9 @@ int machine__process_fork_event(struct machine *machine, union perf_event *event
 int machine__process_exit_event(struct machine *machine, union perf_event *event,
 				struct perf_sample *sample __maybe_unused)
 {
-	struct thread *thread = machine__find_thread(machine, event->fork.tid);
+	struct thread *thread = machine__find_thread(machine,
+						     event->fork.pid,
+						     event->fork.tid);
 
 	if (dump_trace)
 		perf_event__fprintf_task(event, stdout);
@@ -1184,39 +1189,22 @@ static bool symbol__match_regex(struct symbol *sym, regex_t *regex)
 	return 0;
 }
 
-static const u8 cpumodes[] = {
-	PERF_RECORD_MISC_USER,
-	PERF_RECORD_MISC_KERNEL,
-	PERF_RECORD_MISC_GUEST_USER,
-	PERF_RECORD_MISC_GUEST_KERNEL
-};
-#define NCPUMODES (sizeof(cpumodes)/sizeof(u8))
-
 static void ip__resolve_ams(struct machine *machine, struct thread *thread,
 			    struct addr_map_symbol *ams,
 			    u64 ip)
 {
 	struct addr_location al;
-	size_t i;
-	u8 m;
 
 	memset(&al, 0, sizeof(al));
+	/*
+	 * We cannot use the header.misc hint to determine whether a
+	 * branch stack address is user, kernel, guest, hypervisor.
+	 * Branches may straddle the kernel/user/hypervisor boundaries.
+	 * Thus, we have to try consecutively until we find a match
+	 * or else, the symbol is unknown
+	 */
+	thread__find_cpumode_addr_location(thread, machine, MAP__FUNCTION, ip, &al);
 
-	for (i = 0; i < NCPUMODES; i++) {
-		m = cpumodes[i];
-		/*
-		 * We cannot use the header.misc hint to determine whether a
-		 * branch stack address is user, kernel, guest, hypervisor.
-		 * Branches may straddle the kernel/user/hypervisor boundaries.
-		 * Thus, we have to try consecutively until we find a match
-		 * or else, the symbol is unknown
-		 */
-		thread__find_addr_location(thread, machine, m, MAP__FUNCTION,
-				ip, &al);
-		if (al.map)
-			goto found;
-	}
-found:
 	ams->addr = ip;
 	ams->al_addr = al.addr;
 	ams->sym = al.sym;
@@ -1238,37 +1226,35 @@ static void ip__resolve_data(struct machine *machine, struct thread *thread,
 	ams->map = al.map;
 }
 
-struct mem_info *machine__resolve_mem(struct machine *machine,
-				      struct thread *thr,
-				      struct perf_sample *sample,
-				      u8 cpumode)
+struct mem_info *sample__resolve_mem(struct perf_sample *sample,
+				     struct addr_location *al)
 {
 	struct mem_info *mi = zalloc(sizeof(*mi));
 
 	if (!mi)
 		return NULL;
 
-	ip__resolve_ams(machine, thr, &mi->iaddr, sample->ip);
-	ip__resolve_data(machine, thr, cpumode, &mi->daddr, sample->addr);
+	ip__resolve_ams(al->machine, al->thread, &mi->iaddr, sample->ip);
+	ip__resolve_data(al->machine, al->thread, al->cpumode,
+			 &mi->daddr, sample->addr);
 	mi->data_src.val = sample->data_src;
 
 	return mi;
 }
 
-struct branch_info *machine__resolve_bstack(struct machine *machine,
-					    struct thread *thr,
-					    struct branch_stack *bs)
+struct branch_info *sample__resolve_bstack(struct perf_sample *sample,
+					   struct addr_location *al)
 {
-	struct branch_info *bi;
 	unsigned int i;
+	const struct branch_stack *bs = sample->branch_stack;
+	struct branch_info *bi = calloc(bs->nr, sizeof(struct branch_info));
 
-	bi = calloc(bs->nr, sizeof(struct branch_info));
 	if (!bi)
 		return NULL;
 
 	for (i = 0; i < bs->nr; i++) {
-		ip__resolve_ams(machine, thr, &bi[i].to, bs->entries[i].to);
-		ip__resolve_ams(machine, thr, &bi[i].from, bs->entries[i].from);
+		ip__resolve_ams(al->machine, al->thread, &bi[i].to, bs->entries[i].to);
+		ip__resolve_ams(al->machine, al->thread, &bi[i].from, bs->entries[i].from);
 		bi[i].flags = bs->entries[i].flags;
 	}
 	return bi;
@@ -1326,7 +1312,7 @@ static int machine__resolve_callchain_sample(struct machine *machine,
 			continue;
 		}
 
-		al.filtered = false;
+		al.filtered = 0;
 		thread__find_addr_location(thread, machine, cpumode,
 					   MAP__FUNCTION, ip, &al);
 		if (al.sym != NULL) {
@@ -1385,8 +1371,7 @@ int machine__resolve_callchain(struct machine *machine,
 		return 0;
 
 	return unwind__get_entries(unwind_entry, &callchain_cursor, machine,
-				   thread, evsel->attr.sample_regs_user,
-				   sample, max_stack);
+				   thread, sample, max_stack);
 
 }
 
diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h
index f77e91e483d..c8c74a11939 100644
--- a/tools/perf/util/machine.h
+++ b/tools/perf/util/machine.h
@@ -41,7 +41,8 @@ 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 tid);
+struct thread *machine__find_thread(struct machine *machine, pid_t pid,
+				    pid_t tid);
 
 int machine__process_comm_event(struct machine *machine, union perf_event *event,
 				struct perf_sample *sample);
@@ -91,12 +92,10 @@ void machine__delete_dead_threads(struct machine *machine);
 void machine__delete_threads(struct machine *machine);
 void machine__delete(struct machine *machine);
 
-struct branch_info *machine__resolve_bstack(struct machine *machine,
-					    struct thread *thread,
-					    struct branch_stack *bs);
-struct mem_info *machine__resolve_mem(struct machine *machine,
-				      struct thread *thread,
-				      struct perf_sample *sample, u8 cpumode);
+struct branch_info *sample__resolve_bstack(struct perf_sample *sample,
+					   struct addr_location *al);
+struct mem_info *sample__resolve_mem(struct perf_sample *sample,
+				     struct addr_location *al);
 int machine__resolve_callchain(struct machine *machine,
 			       struct perf_evsel *evsel,
 			       struct thread *thread,
diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h
index 257e513205c..f00f058afb3 100644
--- a/tools/perf/util/map.h
+++ b/tools/perf/util/map.h
@@ -90,6 +90,16 @@ u64 map__objdump_2mem(struct map *map, u64 ip);
 
 struct symbol;
 
+/* map__for_each_symbol - iterate over the symbols in the given map
+ *
+ * @map: the 'struct map *' in which symbols itereated
+ * @pos: the 'struct symbol *' to use as a loop cursor
+ * @n: the 'struct rb_node *' to use as a temporary storage
+ * Note: caller must ensure map->dso is not NULL (map is loaded).
+ */
+#define map__for_each_symbol(map, pos, n)	\
+	dso__for_each_symbol(map->dso, pos, n, map->type)
+
 typedef int (*symbol_filter_t)(struct map *map, struct symbol *sym);
 
 void map__init(struct map *map, enum map_type type,
diff --git a/tools/perf/util/parse-options.c b/tools/perf/util/parse-options.c
index d22e3f8017d..bf48092983c 100644
--- a/tools/perf/util/parse-options.c
+++ b/tools/perf/util/parse-options.c
@@ -407,7 +407,9 @@ int parse_options_step(struct parse_opt_ctx_t *ctx,
 		if (internal_help && !strcmp(arg + 2, "help"))
 			return usage_with_options_internal(usagestr, options, 0);
 		if (!strcmp(arg + 2, "list-opts"))
-			return PARSE_OPT_LIST;
+			return PARSE_OPT_LIST_OPTS;
+		if (!strcmp(arg + 2, "list-cmds"))
+			return PARSE_OPT_LIST_SUBCMDS;
 		switch (parse_long_opt(ctx, arg + 2, options)) {
 		case -1:
 			return parse_options_usage(usagestr, options, arg + 2, 0);
@@ -433,25 +435,45 @@ int parse_options_end(struct parse_opt_ctx_t *ctx)
 	return ctx->cpidx + ctx->argc;
 }
 
-int parse_options(int argc, const char **argv, const struct option *options,
-		  const char * const usagestr[], int flags)
+int parse_options_subcommand(int argc, const char **argv, const struct option *options,
+			const char *const subcommands[], const char *usagestr[], int flags)
 {
 	struct parse_opt_ctx_t ctx;
 
 	perf_header__set_cmdline(argc, argv);
 
+	/* build usage string if it's not provided */
+	if (subcommands && !usagestr[0]) {
+		struct strbuf buf = STRBUF_INIT;
+
+		strbuf_addf(&buf, "perf %s [<options>] {", argv[0]);
+		for (int i = 0; subcommands[i]; i++) {
+			if (i)
+				strbuf_addstr(&buf, "|");
+			strbuf_addstr(&buf, subcommands[i]);
+		}
+		strbuf_addstr(&buf, "}");
+
+		usagestr[0] = strdup(buf.buf);
+		strbuf_release(&buf);
+	}
+
 	parse_options_start(&ctx, argc, argv, flags);
 	switch (parse_options_step(&ctx, options, usagestr)) {
 	case PARSE_OPT_HELP:
 		exit(129);
 	case PARSE_OPT_DONE:
 		break;
-	case PARSE_OPT_LIST:
+	case PARSE_OPT_LIST_OPTS:
 		while (options->type != OPTION_END) {
 			printf("--%s ", options->long_name);
 			options++;
 		}
 		exit(130);
+	case PARSE_OPT_LIST_SUBCMDS:
+		for (int i = 0; subcommands[i]; i++)
+			printf("%s ", subcommands[i]);
+		exit(130);
 	default: /* PARSE_OPT_UNKNOWN */
 		if (ctx.argv[0][1] == '-') {
 			error("unknown option `%s'", ctx.argv[0] + 2);
@@ -464,6 +486,13 @@ int parse_options(int argc, const char **argv, const struct option *options,
 	return parse_options_end(&ctx);
 }
 
+int parse_options(int argc, const char **argv, const struct option *options,
+		  const char * const usagestr[], int flags)
+{
+	return parse_options_subcommand(argc, argv, options, NULL,
+					(const char **) usagestr, flags);
+}
+
 #define USAGE_OPTS_WIDTH 24
 #define USAGE_GAP         2
 
diff --git a/tools/perf/util/parse-options.h b/tools/perf/util/parse-options.h
index cbf0149cf22..d8dac8ac5f3 100644
--- a/tools/perf/util/parse-options.h
+++ b/tools/perf/util/parse-options.h
@@ -140,6 +140,11 @@ extern int parse_options(int argc, const char **argv,
                          const struct option *options,
                          const char * const usagestr[], int flags);
 
+extern int parse_options_subcommand(int argc, const char **argv,
+				const struct option *options,
+				const char *const subcommands[],
+				const char *usagestr[], int flags);
+
 extern NORETURN void usage_with_options(const char * const *usagestr,
                                         const struct option *options);
 
@@ -148,7 +153,8 @@ extern NORETURN void usage_with_options(const char * const *usagestr,
 enum {
 	PARSE_OPT_HELP = -1,
 	PARSE_OPT_DONE,
-	PARSE_OPT_LIST,
+	PARSE_OPT_LIST_OPTS,
+	PARSE_OPT_LIST_SUBCMDS,
 	PARSE_OPT_UNKNOWN,
 };
 
diff --git a/tools/perf/util/perf_regs.c b/tools/perf/util/perf_regs.c
new file mode 100644
index 00000000000..a3539ef30b1
--- /dev/null
+++ b/tools/perf/util/perf_regs.c
@@ -0,0 +1,19 @@
+#include <errno.h>
+#include "perf_regs.h"
+
+int perf_reg_value(u64 *valp, struct regs_dump *regs, int id)
+{
+	int i, idx = 0;
+	u64 mask = regs->mask;
+
+	if (!(mask & (1 << id)))
+		return -EINVAL;
+
+	for (i = 0; i < id; i++) {
+		if (mask & (1 << i))
+			idx++;
+	}
+
+	*valp = regs->regs[idx];
+	return 0;
+}
diff --git a/tools/perf/util/perf_regs.h b/tools/perf/util/perf_regs.h
index a3d42cd7491..d6e8b6a8d7f 100644
--- a/tools/perf/util/perf_regs.h
+++ b/tools/perf/util/perf_regs.h
@@ -1,8 +1,14 @@
 #ifndef __PERF_REGS_H
 #define __PERF_REGS_H
 
+#include "types.h"
+#include "event.h"
+
 #ifdef HAVE_PERF_REGS_SUPPORT
 #include <perf_regs.h>
+
+int perf_reg_value(u64 *valp, struct regs_dump *regs, int id);
+
 #else
 #define PERF_REGS_MASK	0
 
@@ -10,5 +16,12 @@ static inline const char *perf_reg_name(int id __maybe_unused)
 {
 	return NULL;
 }
+
+static inline int perf_reg_value(u64 *valp __maybe_unused,
+				 struct regs_dump *regs __maybe_unused,
+				 int id __maybe_unused)
+{
+	return 0;
+}
 #endif /* HAVE_PERF_REGS_SUPPORT */
 #endif /* __PERF_REGS_H */
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index b752ecb40d8..00a7dcb2f55 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -3,7 +3,7 @@
 #include <unistd.h>
 #include <stdio.h>
 #include <dirent.h>
-#include "fs.h"
+#include <api/fs/fs.h>
 #include <locale.h>
 #include "util.h"
 #include "pmu.h"
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index d8b048c20cd..0d1542f33d8 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -70,34 +70,32 @@ static int e_snprintf(char *str, size_t size, const char *format, ...)
 }
 
 static char *synthesize_perf_probe_point(struct perf_probe_point *pp);
-static int convert_name_to_addr(struct perf_probe_event *pev,
-				const char *exec);
 static void clear_probe_trace_event(struct probe_trace_event *tev);
-static struct machine machine;
+static struct machine *host_machine;
 
 /* Initialize symbol maps and path of vmlinux/modules */
-static int init_vmlinux(void)
+static int init_symbol_maps(bool user_only)
 {
 	int ret;
 
 	symbol_conf.sort_by_name = true;
-	if (symbol_conf.vmlinux_name == NULL)
-		symbol_conf.try_vmlinux_path = true;
-	else
-		pr_debug("Use vmlinux: %s\n", symbol_conf.vmlinux_name);
 	ret = symbol__init();
 	if (ret < 0) {
 		pr_debug("Failed to init symbol map.\n");
 		goto out;
 	}
 
-	ret = machine__init(&machine, "", HOST_KERNEL_ID);
-	if (ret < 0)
-		goto out;
+	if (host_machine || user_only)	/* already initialized */
+		return 0;
 
-	if (machine__create_kernel_maps(&machine) < 0) {
-		pr_debug("machine__create_kernel_maps() failed.\n");
-		goto out;
+	if (symbol_conf.vmlinux_name)
+		pr_debug("Use vmlinux: %s\n", symbol_conf.vmlinux_name);
+
+	host_machine = machine__new_host();
+	if (!host_machine) {
+		pr_debug("machine__new_host() failed.\n");
+		symbol__exit();
+		ret = -1;
 	}
 out:
 	if (ret < 0)
@@ -105,21 +103,66 @@ out:
 	return ret;
 }
 
+static void exit_symbol_maps(void)
+{
+	if (host_machine) {
+		machine__delete(host_machine);
+		host_machine = NULL;
+	}
+	symbol__exit();
+}
+
 static struct symbol *__find_kernel_function_by_name(const char *name,
 						     struct map **mapp)
 {
-	return machine__find_kernel_function_by_name(&machine, name, mapp,
+	return machine__find_kernel_function_by_name(host_machine, name, mapp,
 						     NULL);
 }
 
+static struct symbol *__find_kernel_function(u64 addr, struct map **mapp)
+{
+	return machine__find_kernel_function(host_machine, addr, mapp, NULL);
+}
+
+static struct ref_reloc_sym *kernel_get_ref_reloc_sym(void)
+{
+	/* kmap->ref_reloc_sym should be set if host_machine is initialized */
+	struct kmap *kmap;
+
+	if (map__load(host_machine->vmlinux_maps[MAP__FUNCTION], NULL) < 0)
+		return NULL;
+
+	kmap = map__kmap(host_machine->vmlinux_maps[MAP__FUNCTION]);
+	return kmap->ref_reloc_sym;
+}
+
+static u64 kernel_get_symbol_address_by_name(const char *name, bool reloc)
+{
+	struct ref_reloc_sym *reloc_sym;
+	struct symbol *sym;
+	struct map *map;
+
+	/* ref_reloc_sym is just a label. Need a special fix*/
+	reloc_sym = kernel_get_ref_reloc_sym();
+	if (reloc_sym && strcmp(name, reloc_sym->name) == 0)
+		return (reloc) ? reloc_sym->addr : reloc_sym->unrelocated_addr;
+	else {
+		sym = __find_kernel_function_by_name(name, &map);
+		if (sym)
+			return map->unmap_ip(map, sym->start) -
+				(reloc) ? 0 : map->reloc;
+	}
+	return 0;
+}
+
 static struct map *kernel_get_module_map(const char *module)
 {
 	struct rb_node *nd;
-	struct map_groups *grp = &machine.kmaps;
+	struct map_groups *grp = &host_machine->kmaps;
 
 	/* A file path -- this is an offline module */
 	if (module && strchr(module, '/'))
-		return machine__new_module(&machine, 0, module);
+		return machine__new_module(host_machine, 0, module);
 
 	if (!module)
 		module = "kernel";
@@ -141,7 +184,7 @@ static struct dso *kernel_get_module_dso(const char *module)
 	const char *vmlinux_name;
 
 	if (module) {
-		list_for_each_entry(dso, &machine.kernel_dsos, node) {
+		list_for_each_entry(dso, &host_machine->kernel_dsos, node) {
 			if (strncmp(dso->short_name + 1, module,
 				    dso->short_name_len - 2) == 0)
 				goto found;
@@ -150,7 +193,7 @@ static struct dso *kernel_get_module_dso(const char *module)
 		return NULL;
 	}
 
-	map = machine.vmlinux_maps[MAP__FUNCTION];
+	map = host_machine->vmlinux_maps[MAP__FUNCTION];
 	dso = map->dso;
 
 	vmlinux_name = symbol_conf.vmlinux_name;
@@ -173,20 +216,6 @@ const char *kernel_get_module_path(const char *module)
 	return (dso) ? dso->long_name : NULL;
 }
 
-static int init_user_exec(void)
-{
-	int ret = 0;
-
-	symbol_conf.try_vmlinux_path = false;
-	symbol_conf.sort_by_name = true;
-	ret = symbol__init();
-
-	if (ret < 0)
-		pr_debug("Failed to init symbol map.\n");
-
-	return ret;
-}
-
 static int convert_exec_to_group(const char *exec, char **result)
 {
 	char *ptr1, *ptr2, *exec_copy;
@@ -218,32 +247,23 @@ out:
 	return ret;
 }
 
-static int convert_to_perf_probe_point(struct probe_trace_point *tp,
-					struct perf_probe_point *pp)
+static void clear_probe_trace_events(struct probe_trace_event *tevs, int ntevs)
 {
-	pp->function = strdup(tp->symbol);
-
-	if (pp->function == NULL)
-		return -ENOMEM;
-
-	pp->offset = tp->offset;
-	pp->retprobe = tp->retprobe;
+	int i;
 
-	return 0;
+	for (i = 0; i < ntevs; i++)
+		clear_probe_trace_event(tevs + i);
 }
 
 #ifdef HAVE_DWARF_SUPPORT
+
 /* Open new debuginfo of given module */
 static struct debuginfo *open_debuginfo(const char *module)
 {
-	const char *path;
+	const char *path = module;
 
-	/* A file path -- this is an offline module */
-	if (module && strchr(module, '/'))
-		path = module;
-	else {
+	if (!module || !strchr(module, '/')) {
 		path = kernel_get_module_path(module);
-
 		if (!path) {
 			pr_err("Failed to find path of %s module.\n",
 			       module ?: "kernel");
@@ -253,46 +273,6 @@ static struct debuginfo *open_debuginfo(const char *module)
 	return debuginfo__new(path);
 }
 
-/*
- * Convert trace point to probe point with debuginfo
- * Currently only handles kprobes.
- */
-static int kprobe_convert_to_perf_probe(struct probe_trace_point *tp,
-					struct perf_probe_point *pp)
-{
-	struct symbol *sym;
-	struct map *map;
-	u64 addr;
-	int ret = -ENOENT;
-	struct debuginfo *dinfo;
-
-	sym = __find_kernel_function_by_name(tp->symbol, &map);
-	if (sym) {
-		addr = map->unmap_ip(map, sym->start + tp->offset);
-		pr_debug("try to find %s+%ld@%" PRIx64 "\n", tp->symbol,
-			 tp->offset, addr);
-
-		dinfo = debuginfo__new_online_kernel(addr);
-		if (dinfo) {
-			ret = debuginfo__find_probe_point(dinfo,
-						 (unsigned long)addr, pp);
-			debuginfo__delete(dinfo);
-		} else {
-			pr_debug("Failed to open debuginfo at 0x%" PRIx64 "\n",
-				 addr);
-			ret = -ENOENT;
-		}
-	}
-	if (ret <= 0) {
-		pr_debug("Failed to find corresponding probes from "
-			 "debuginfo. Use kprobe event information.\n");
-		return convert_to_perf_probe_point(tp, pp);
-	}
-	pp->retprobe = tp->retprobe;
-
-	return 0;
-}
-
 static int get_text_start_address(const char *exec, unsigned long *address)
 {
 	Elf *elf;
@@ -321,12 +301,62 @@ out:
 	return ret;
 }
 
+/*
+ * Convert trace point to probe point with debuginfo
+ */
+static int find_perf_probe_point_from_dwarf(struct probe_trace_point *tp,
+					    struct perf_probe_point *pp,
+					    bool is_kprobe)
+{
+	struct debuginfo *dinfo = NULL;
+	unsigned long stext = 0;
+	u64 addr = tp->address;
+	int ret = -ENOENT;
+
+	/* convert the address to dwarf address */
+	if (!is_kprobe) {
+		if (!addr) {
+			ret = -EINVAL;
+			goto error;
+		}
+		ret = get_text_start_address(tp->module, &stext);
+		if (ret < 0)
+			goto error;
+		addr += stext;
+	} else {
+		addr = kernel_get_symbol_address_by_name(tp->symbol, false);
+		if (addr == 0)
+			goto error;
+		addr += tp->offset;
+	}
+
+	pr_debug("try to find information at %" PRIx64 " in %s\n", addr,
+		 tp->module ? : "kernel");
+
+	dinfo = open_debuginfo(tp->module);
+	if (dinfo) {
+		ret = debuginfo__find_probe_point(dinfo,
+						 (unsigned long)addr, pp);
+		debuginfo__delete(dinfo);
+	} else {
+		pr_debug("Failed to open debuginfo at 0x%" PRIx64 "\n", addr);
+		ret = -ENOENT;
+	}
+
+	if (ret > 0) {
+		pp->retprobe = tp->retprobe;
+		return 0;
+	}
+error:
+	pr_debug("Failed to find corresponding probes from debuginfo.\n");
+	return ret ? : -ENOENT;
+}
+
 static int add_exec_to_probe_trace_events(struct probe_trace_event *tevs,
 					  int ntevs, const char *exec)
 {
 	int i, ret = 0;
-	unsigned long offset, stext = 0;
-	char buf[32];
+	unsigned long stext = 0;
 
 	if (!exec)
 		return 0;
@@ -337,15 +367,9 @@ static int add_exec_to_probe_trace_events(struct probe_trace_event *tevs,
 
 	for (i = 0; i < ntevs && ret >= 0; i++) {
 		/* point.address is the addres of point.symbol + point.offset */
-		offset = tevs[i].point.address - stext;
-		tevs[i].point.offset = 0;
-		zfree(&tevs[i].point.symbol);
-		ret = e_snprintf(buf, 32, "0x%lx", offset);
-		if (ret < 0)
-			break;
+		tevs[i].point.address -= stext;
 		tevs[i].point.module = strdup(exec);
-		tevs[i].point.symbol = strdup(buf);
-		if (!tevs[i].point.symbol || !tevs[i].point.module) {
+		if (!tevs[i].point.module) {
 			ret = -ENOMEM;
 			break;
 		}
@@ -388,12 +412,40 @@ static int add_module_to_probe_trace_events(struct probe_trace_event *tevs,
 	return ret;
 }
 
-static void clear_probe_trace_events(struct probe_trace_event *tevs, int ntevs)
+/* Post processing the probe events */
+static int post_process_probe_trace_events(struct probe_trace_event *tevs,
+					   int ntevs, const char *module,
+					   bool uprobe)
 {
+	struct ref_reloc_sym *reloc_sym;
+	char *tmp;
 	int i;
 
-	for (i = 0; i < ntevs; i++)
-		clear_probe_trace_event(tevs + i);
+	if (uprobe)
+		return add_exec_to_probe_trace_events(tevs, ntevs, module);
+
+	/* Note that currently ref_reloc_sym based probe is not for drivers */
+	if (module)
+		return add_module_to_probe_trace_events(tevs, ntevs, module);
+
+	reloc_sym = kernel_get_ref_reloc_sym();
+	if (!reloc_sym) {
+		pr_warning("Relocated base symbol is not found!\n");
+		return -EINVAL;
+	}
+
+	for (i = 0; i < ntevs; i++) {
+		if (tevs[i].point.address) {
+			tmp = strdup(reloc_sym->name);
+			if (!tmp)
+				return -ENOMEM;
+			free(tevs[i].point.symbol);
+			tevs[i].point.symbol = tmp;
+			tevs[i].point.offset = tevs[i].point.address -
+					       reloc_sym->unrelocated_addr;
+		}
+	}
+	return 0;
 }
 
 /* Try to find perf_probe_event with debuginfo */
@@ -416,21 +468,16 @@ static int try_to_find_probe_trace_events(struct perf_probe_event *pev,
 		return 0;
 	}
 
+	pr_debug("Try to find probe point from debuginfo.\n");
 	/* Searching trace events corresponding to a probe event */
 	ntevs = debuginfo__find_trace_events(dinfo, pev, tevs, max_tevs);
 
 	debuginfo__delete(dinfo);
 
 	if (ntevs > 0) {	/* Succeeded to find trace events */
-		pr_debug("find %d probe_trace_events.\n", ntevs);
-		if (target) {
-			if (pev->uprobes)
-				ret = add_exec_to_probe_trace_events(*tevs,
-						 ntevs, target);
-			else
-				ret = add_module_to_probe_trace_events(*tevs,
-						 ntevs, target);
-		}
+		pr_debug("Found %d probe_trace_events.\n", ntevs);
+		ret = post_process_probe_trace_events(*tevs, ntevs,
+							target, pev->uprobes);
 		if (ret < 0) {
 			clear_probe_trace_events(*tevs, ntevs);
 			zfree(tevs);
@@ -563,20 +610,16 @@ static int _show_one_line(FILE *fp, int l, bool skip, bool show_num)
  * Show line-range always requires debuginfo to find source file and
  * line number.
  */
-int show_line_range(struct line_range *lr, const char *module)
+static int __show_line_range(struct line_range *lr, const char *module)
 {
 	int l = 1;
-	struct line_node *ln;
+	struct int_node *ln;
 	struct debuginfo *dinfo;
 	FILE *fp;
 	int ret;
 	char *tmp;
 
 	/* Search a line range */
-	ret = init_vmlinux();
-	if (ret < 0)
-		return ret;
-
 	dinfo = open_debuginfo(module);
 	if (!dinfo) {
 		pr_warning("Failed to open debuginfo file.\n");
@@ -623,8 +666,8 @@ int show_line_range(struct line_range *lr, const char *module)
 			goto end;
 	}
 
-	list_for_each_entry(ln, &lr->line_list, list) {
-		for (; ln->line > l; l++) {
+	intlist__for_each(ln, lr->line_list) {
+		for (; ln->i > l; l++) {
 			ret = show_one_line(fp, l - lr->offset);
 			if (ret < 0)
 				goto end;
@@ -646,6 +689,19 @@ end:
 	return ret;
 }
 
+int show_line_range(struct line_range *lr, const char *module)
+{
+	int ret;
+
+	ret = init_symbol_maps(false);
+	if (ret < 0)
+		return ret;
+	ret = __show_line_range(lr, module);
+	exit_symbol_maps();
+
+	return ret;
+}
+
 static int show_available_vars_at(struct debuginfo *dinfo,
 				  struct perf_probe_event *pev,
 				  int max_vls, struct strfilter *_filter,
@@ -707,14 +763,15 @@ int show_available_vars(struct perf_probe_event *pevs, int npevs,
 	int i, ret = 0;
 	struct debuginfo *dinfo;
 
-	ret = init_vmlinux();
+	ret = init_symbol_maps(false);
 	if (ret < 0)
 		return ret;
 
 	dinfo = open_debuginfo(module);
 	if (!dinfo) {
 		pr_warning("Failed to open debuginfo file.\n");
-		return -ENOENT;
+		ret = -ENOENT;
+		goto out;
 	}
 
 	setup_pager();
@@ -724,23 +781,19 @@ int show_available_vars(struct perf_probe_event *pevs, int npevs,
 					     externs);
 
 	debuginfo__delete(dinfo);
+out:
+	exit_symbol_maps();
 	return ret;
 }
 
 #else	/* !HAVE_DWARF_SUPPORT */
 
-static int kprobe_convert_to_perf_probe(struct probe_trace_point *tp,
-					struct perf_probe_point *pp)
+static int
+find_perf_probe_point_from_dwarf(struct probe_trace_point *tp __maybe_unused,
+				 struct perf_probe_point *pp __maybe_unused,
+				 bool is_kprobe __maybe_unused)
 {
-	struct symbol *sym;
-
-	sym = __find_kernel_function_by_name(tp->symbol, NULL);
-	if (!sym) {
-		pr_err("Failed to find symbol %s in kernel.\n", tp->symbol);
-		return -ENOENT;
-	}
-
-	return convert_to_perf_probe_point(tp, pp);
+	return -ENOSYS;
 }
 
 static int try_to_find_probe_trace_events(struct perf_probe_event *pev,
@@ -776,24 +829,22 @@ int show_available_vars(struct perf_probe_event *pevs __maybe_unused,
 
 void line_range__clear(struct line_range *lr)
 {
-	struct line_node *ln;
-
 	free(lr->function);
 	free(lr->file);
 	free(lr->path);
 	free(lr->comp_dir);
-	while (!list_empty(&lr->line_list)) {
-		ln = list_first_entry(&lr->line_list, struct line_node, list);
-		list_del(&ln->list);
-		free(ln);
-	}
+	intlist__delete(lr->line_list);
 	memset(lr, 0, sizeof(*lr));
 }
 
-void line_range__init(struct line_range *lr)
+int line_range__init(struct line_range *lr)
 {
 	memset(lr, 0, sizeof(*lr));
-	INIT_LIST_HEAD(&lr->line_list);
+	lr->line_list = intlist__new(NULL);
+	if (!lr->line_list)
+		return -ENOMEM;
+	else
+		return 0;
 }
 
 static int parse_line_num(char **ptr, int *val, const char *what)
@@ -1267,16 +1318,21 @@ static int parse_probe_trace_command(const char *cmd,
 	} else
 		p = argv[1];
 	fmt1_str = strtok_r(p, "+", &fmt);
-	tp->symbol = strdup(fmt1_str);
-	if (tp->symbol == NULL) {
-		ret = -ENOMEM;
-		goto out;
+	if (fmt1_str[0] == '0')	/* only the address started with 0x */
+		tp->address = strtoul(fmt1_str, NULL, 0);
+	else {
+		/* Only the symbol-based probe has offset */
+		tp->symbol = strdup(fmt1_str);
+		if (tp->symbol == NULL) {
+			ret = -ENOMEM;
+			goto out;
+		}
+		fmt2_str = strtok_r(NULL, "", &fmt);
+		if (fmt2_str == NULL)
+			tp->offset = 0;
+		else
+			tp->offset = strtoul(fmt2_str, NULL, 10);
 	}
-	fmt2_str = strtok_r(NULL, "", &fmt);
-	if (fmt2_str == NULL)
-		tp->offset = 0;
-	else
-		tp->offset = strtoul(fmt2_str, NULL, 10);
 
 	tev->nargs = argc - 2;
 	tev->args = zalloc(sizeof(struct probe_trace_arg) * tev->nargs);
@@ -1518,20 +1574,27 @@ char *synthesize_probe_trace_command(struct probe_trace_event *tev)
 	if (buf == NULL)
 		return NULL;
 
+	len = e_snprintf(buf, MAX_CMDLEN, "%c:%s/%s ", tp->retprobe ? 'r' : 'p',
+			 tev->group, tev->event);
+	if (len <= 0)
+		goto error;
+
+	/* Uprobes must have tp->address and tp->module */
+	if (tev->uprobes && (!tp->address || !tp->module))
+		goto error;
+
+	/* Use the tp->address for uprobes */
 	if (tev->uprobes)
-		len = e_snprintf(buf, MAX_CMDLEN, "%c:%s/%s %s:%s",
-				 tp->retprobe ? 'r' : 'p',
-				 tev->group, tev->event,
-				 tp->module, tp->symbol);
+		ret = e_snprintf(buf + len, MAX_CMDLEN - len, "%s:0x%lx",
+				 tp->module, tp->address);
 	else
-		len = e_snprintf(buf, MAX_CMDLEN, "%c:%s/%s %s%s%s+%lu",
-				 tp->retprobe ? 'r' : 'p',
-				 tev->group, tev->event,
+		ret = e_snprintf(buf + len, MAX_CMDLEN - len, "%s%s%s+%lu",
 				 tp->module ?: "", tp->module ? ":" : "",
 				 tp->symbol, tp->offset);
 
-	if (len <= 0)
+	if (ret <= 0)
 		goto error;
+	len += ret;
 
 	for (i = 0; i < tev->nargs; i++) {
 		ret = synthesize_probe_trace_arg(&tev->args[i], buf + len,
@@ -1547,6 +1610,79 @@ error:
 	return NULL;
 }
 
+static int find_perf_probe_point_from_map(struct probe_trace_point *tp,
+					  struct perf_probe_point *pp,
+					  bool is_kprobe)
+{
+	struct symbol *sym = NULL;
+	struct map *map;
+	u64 addr;
+	int ret = -ENOENT;
+
+	if (!is_kprobe) {
+		map = dso__new_map(tp->module);
+		if (!map)
+			goto out;
+		addr = tp->address;
+		sym = map__find_symbol(map, addr, NULL);
+	} else {
+		addr = kernel_get_symbol_address_by_name(tp->symbol, true);
+		if (addr) {
+			addr += tp->offset;
+			sym = __find_kernel_function(addr, &map);
+		}
+	}
+	if (!sym)
+		goto out;
+
+	pp->retprobe = tp->retprobe;
+	pp->offset = addr - map->unmap_ip(map, sym->start);
+	pp->function = strdup(sym->name);
+	ret = pp->function ? 0 : -ENOMEM;
+
+out:
+	if (map && !is_kprobe) {
+		dso__delete(map->dso);
+		map__delete(map);
+	}
+
+	return ret;
+}
+
+static int convert_to_perf_probe_point(struct probe_trace_point *tp,
+					struct perf_probe_point *pp,
+					bool is_kprobe)
+{
+	char buf[128];
+	int ret;
+
+	ret = find_perf_probe_point_from_dwarf(tp, pp, is_kprobe);
+	if (!ret)
+		return 0;
+	ret = find_perf_probe_point_from_map(tp, pp, is_kprobe);
+	if (!ret)
+		return 0;
+
+	pr_debug("Failed to find probe point from both of dwarf and map.\n");
+
+	if (tp->symbol) {
+		pp->function = strdup(tp->symbol);
+		pp->offset = tp->offset;
+	} else if (!tp->module && !is_kprobe) {
+		ret = e_snprintf(buf, 128, "0x%" PRIx64, (u64)tp->address);
+		if (ret < 0)
+			return ret;
+		pp->function = strdup(buf);
+		pp->offset = 0;
+	}
+	if (pp->function == NULL)
+		return -ENOMEM;
+
+	pp->retprobe = tp->retprobe;
+
+	return 0;
+}
+
 static int convert_to_perf_probe_event(struct probe_trace_event *tev,
 			       struct perf_probe_event *pev, bool is_kprobe)
 {
@@ -1560,11 +1696,7 @@ static int convert_to_perf_probe_event(struct probe_trace_event *tev,
 		return -ENOMEM;
 
 	/* Convert trace_point to probe_point */
-	if (is_kprobe)
-		ret = kprobe_convert_to_perf_probe(&tev->point, &pev->point);
-	else
-		ret = convert_to_perf_probe_point(&tev->point, &pev->point);
-
+	ret = convert_to_perf_probe_point(&tev->point, &pev->point, is_kprobe);
 	if (ret < 0)
 		return ret;
 
@@ -1731,7 +1863,8 @@ static struct strlist *get_probe_trace_command_rawlist(int fd)
 }
 
 /* Show an event */
-static int show_perf_probe_event(struct perf_probe_event *pev)
+static int show_perf_probe_event(struct perf_probe_event *pev,
+				 const char *module)
 {
 	int i, ret;
 	char buf[128];
@@ -1747,6 +1880,8 @@ static int show_perf_probe_event(struct perf_probe_event *pev)
 		return ret;
 
 	printf("  %-20s (on %s", buf, place);
+	if (module)
+		printf(" in %s", module);
 
 	if (pev->nargs > 0) {
 		printf(" with");
@@ -1784,7 +1919,8 @@ static int __show_perf_probe_events(int fd, bool is_kprobe)
 			ret = convert_to_perf_probe_event(&tev, &pev,
 								is_kprobe);
 			if (ret >= 0)
-				ret = show_perf_probe_event(&pev);
+				ret = show_perf_probe_event(&pev,
+							    tev.point.module);
 		}
 		clear_perf_probe_event(&pev);
 		clear_probe_trace_event(&tev);
@@ -1807,7 +1943,7 @@ int show_perf_probe_events(void)
 	if (fd < 0)
 		return fd;
 
-	ret = init_vmlinux();
+	ret = init_symbol_maps(false);
 	if (ret < 0)
 		return ret;
 
@@ -1820,6 +1956,7 @@ int show_perf_probe_events(void)
 		close(fd);
 	}
 
+	exit_symbol_maps();
 	return ret;
 }
 
@@ -1982,7 +2119,7 @@ static int __add_probe_trace_events(struct perf_probe_event *pev,
 		group = pev->group;
 		pev->event = tev->event;
 		pev->group = tev->group;
-		show_perf_probe_event(pev);
+		show_perf_probe_event(pev, tev->point.module);
 		/* Trick here - restore current event/group */
 		pev->event = (char *)event;
 		pev->group = (char *)group;
@@ -2008,113 +2145,175 @@ static int __add_probe_trace_events(struct perf_probe_event *pev,
 	return ret;
 }
 
-static int convert_to_probe_trace_events(struct perf_probe_event *pev,
-					  struct probe_trace_event **tevs,
-					  int max_tevs, const char *target)
+static char *looking_function_name;
+static int num_matched_functions;
+
+static int probe_function_filter(struct map *map __maybe_unused,
+				      struct symbol *sym)
 {
+	if ((sym->binding == STB_GLOBAL || sym->binding == STB_LOCAL) &&
+	    strcmp(looking_function_name, sym->name) == 0) {
+		num_matched_functions++;
+		return 0;
+	}
+	return 1;
+}
+
+#define strdup_or_goto(str, label)	\
+	({ char *__p = strdup(str); if (!__p) goto label; __p; })
+
+/*
+ * Find probe function addresses from map.
+ * Return an error or the number of found probe_trace_event
+ */
+static int find_probe_trace_events_from_map(struct perf_probe_event *pev,
+					    struct probe_trace_event **tevs,
+					    int max_tevs, const char *target)
+{
+	struct map *map = NULL;
+	struct kmap *kmap = NULL;
+	struct ref_reloc_sym *reloc_sym = NULL;
 	struct symbol *sym;
-	int ret, i;
+	struct rb_node *nd;
 	struct probe_trace_event *tev;
+	struct perf_probe_point *pp = &pev->point;
+	struct probe_trace_point *tp;
+	int ret, i;
 
-	if (pev->uprobes && !pev->group) {
-		/* Replace group name if not given */
-		ret = convert_exec_to_group(target, &pev->group);
-		if (ret != 0) {
-			pr_warning("Failed to make a group name.\n");
-			return ret;
-		}
+	/* Init maps of given executable or kernel */
+	if (pev->uprobes)
+		map = dso__new_map(target);
+	else
+		map = kernel_get_module_map(target);
+	if (!map) {
+		ret = -EINVAL;
+		goto out;
 	}
 
-	/* Convert perf_probe_event with debuginfo */
-	ret = try_to_find_probe_trace_events(pev, tevs, max_tevs, target);
-	if (ret != 0)
-		return ret;	/* Found in debuginfo or got an error */
-
-	if (pev->uprobes) {
-		ret = convert_name_to_addr(pev, target);
-		if (ret < 0)
-			return ret;
+	/*
+	 * Load matched symbols: Since the different local symbols may have
+	 * same name but different addresses, this lists all the symbols.
+	 */
+	num_matched_functions = 0;
+	looking_function_name = pp->function;
+	ret = map__load(map, probe_function_filter);
+	if (ret || num_matched_functions == 0) {
+		pr_err("Failed to find symbol %s in %s\n", pp->function,
+			target ? : "kernel");
+		ret = -ENOENT;
+		goto out;
+	} else if (num_matched_functions > max_tevs) {
+		pr_err("Too many functions matched in %s\n",
+			target ? : "kernel");
+		ret = -E2BIG;
+		goto out;
 	}
 
-	/* Allocate trace event buffer */
-	tev = *tevs = zalloc(sizeof(struct probe_trace_event));
-	if (tev == NULL)
-		return -ENOMEM;
+	if (!pev->uprobes) {
+		kmap = map__kmap(map);
+		reloc_sym = kmap->ref_reloc_sym;
+		if (!reloc_sym) {
+			pr_warning("Relocated base symbol is not found!\n");
+			ret = -EINVAL;
+			goto out;
+		}
+	}
 
-	/* Copy parameters */
-	tev->point.symbol = strdup(pev->point.function);
-	if (tev->point.symbol == NULL) {
+	/* Setup result trace-probe-events */
+	*tevs = zalloc(sizeof(*tev) * num_matched_functions);
+	if (!*tevs) {
 		ret = -ENOMEM;
-		goto error;
+		goto out;
 	}
 
-	if (target) {
-		tev->point.module = strdup(target);
-		if (tev->point.module == NULL) {
-			ret = -ENOMEM;
-			goto error;
+	ret = 0;
+	map__for_each_symbol(map, sym, nd) {
+		tev = (*tevs) + ret;
+		tp = &tev->point;
+		if (ret == num_matched_functions) {
+			pr_warning("Too many symbols are listed. Skip it.\n");
+			break;
 		}
-	}
-
-	tev->point.offset = pev->point.offset;
-	tev->point.retprobe = pev->point.retprobe;
-	tev->nargs = pev->nargs;
-	tev->uprobes = pev->uprobes;
+		ret++;
 
-	if (tev->nargs) {
-		tev->args = zalloc(sizeof(struct probe_trace_arg)
-				   * tev->nargs);
-		if (tev->args == NULL) {
-			ret = -ENOMEM;
-			goto error;
+		if (pp->offset > sym->end - sym->start) {
+			pr_warning("Offset %ld is bigger than the size of %s\n",
+				   pp->offset, sym->name);
+			ret = -ENOENT;
+			goto err_out;
+		}
+		/* Add one probe point */
+		tp->address = map->unmap_ip(map, sym->start) + pp->offset;
+		if (reloc_sym) {
+			tp->symbol = strdup_or_goto(reloc_sym->name, nomem_out);
+			tp->offset = tp->address - reloc_sym->addr;
+		} else {
+			tp->symbol = strdup_or_goto(sym->name, nomem_out);
+			tp->offset = pp->offset;
+		}
+		tp->retprobe = pp->retprobe;
+		if (target)
+			tev->point.module = strdup_or_goto(target, nomem_out);
+		tev->uprobes = pev->uprobes;
+		tev->nargs = pev->nargs;
+		if (tev->nargs) {
+			tev->args = zalloc(sizeof(struct probe_trace_arg) *
+					   tev->nargs);
+			if (tev->args == NULL)
+				goto nomem_out;
 		}
 		for (i = 0; i < tev->nargs; i++) {
-			if (pev->args[i].name) {
-				tev->args[i].name = strdup(pev->args[i].name);
-				if (tev->args[i].name == NULL) {
-					ret = -ENOMEM;
-					goto error;
-				}
-			}
-			tev->args[i].value = strdup(pev->args[i].var);
-			if (tev->args[i].value == NULL) {
-				ret = -ENOMEM;
-				goto error;
-			}
-			if (pev->args[i].type) {
-				tev->args[i].type = strdup(pev->args[i].type);
-				if (tev->args[i].type == NULL) {
-					ret = -ENOMEM;
-					goto error;
-				}
-			}
+			if (pev->args[i].name)
+				tev->args[i].name =
+					strdup_or_goto(pev->args[i].name,
+							nomem_out);
+
+			tev->args[i].value = strdup_or_goto(pev->args[i].var,
+							    nomem_out);
+			if (pev->args[i].type)
+				tev->args[i].type =
+					strdup_or_goto(pev->args[i].type,
+							nomem_out);
 		}
 	}
 
-	if (pev->uprobes)
-		return 1;
+out:
+	if (map && pev->uprobes) {
+		/* Only when using uprobe(exec) map needs to be released */
+		dso__delete(map->dso);
+		map__delete(map);
+	}
+	return ret;
 
-	/* Currently just checking function name from symbol map */
-	sym = __find_kernel_function_by_name(tev->point.symbol, NULL);
-	if (!sym) {
-		pr_warning("Kernel symbol \'%s\' not found.\n",
-			   tev->point.symbol);
-		ret = -ENOENT;
-		goto error;
-	} else if (tev->point.offset > sym->end - sym->start) {
-		pr_warning("Offset specified is greater than size of %s\n",
-			   tev->point.symbol);
-		ret = -ENOENT;
-		goto error;
+nomem_out:
+	ret = -ENOMEM;
+err_out:
+	clear_probe_trace_events(*tevs, num_matched_functions);
+	zfree(tevs);
+	goto out;
+}
+
+static int convert_to_probe_trace_events(struct perf_probe_event *pev,
+					  struct probe_trace_event **tevs,
+					  int max_tevs, const char *target)
+{
+	int ret;
 
+	if (pev->uprobes && !pev->group) {
+		/* Replace group name if not given */
+		ret = convert_exec_to_group(target, &pev->group);
+		if (ret != 0) {
+			pr_warning("Failed to make a group name.\n");
+			return ret;
+		}
 	}
 
-	return 1;
-error:
-	clear_probe_trace_event(tev);
-	free(tev);
-	*tevs = NULL;
-	return ret;
+	/* Convert perf_probe_event with debuginfo */
+	ret = try_to_find_probe_trace_events(pev, tevs, max_tevs, target);
+	if (ret != 0)
+		return ret;	/* Found in debuginfo or got an error */
+
+	return find_probe_trace_events_from_map(pev, tevs, max_tevs, target);
 }
 
 struct __event_package {
@@ -2135,12 +2334,7 @@ int add_perf_probe_events(struct perf_probe_event *pevs, int npevs,
 	if (pkgs == NULL)
 		return -ENOMEM;
 
-	if (!pevs->uprobes)
-		/* Init vmlinux path */
-		ret = init_vmlinux();
-	else
-		ret = init_user_exec();
-
+	ret = init_symbol_maps(pevs->uprobes);
 	if (ret < 0) {
 		free(pkgs);
 		return ret;
@@ -2174,6 +2368,7 @@ end:
 		zfree(&pkgs[i].tevs);
 	}
 	free(pkgs);
+	exit_symbol_maps();
 
 	return ret;
 }
@@ -2323,159 +2518,51 @@ static struct strfilter *available_func_filter;
 static int filter_available_functions(struct map *map __maybe_unused,
 				      struct symbol *sym)
 {
-	if (sym->binding == STB_GLOBAL &&
+	if ((sym->binding == STB_GLOBAL || sym->binding == STB_LOCAL) &&
 	    strfilter__compare(available_func_filter, sym->name))
 		return 0;
 	return 1;
 }
 
-static int __show_available_funcs(struct map *map)
-{
-	if (map__load(map, filter_available_functions)) {
-		pr_err("Failed to load map.\n");
-		return -EINVAL;
-	}
-	if (!dso__sorted_by_name(map->dso, map->type))
-		dso__sort_by_name(map->dso, map->type);
-
-	dso__fprintf_symbols_by_name(map->dso, map->type, stdout);
-	return 0;
-}
-
-static int available_kernel_funcs(const char *module)
+int show_available_funcs(const char *target, struct strfilter *_filter,
+					bool user)
 {
 	struct map *map;
 	int ret;
 
-	ret = init_vmlinux();
+	ret = init_symbol_maps(user);
 	if (ret < 0)
 		return ret;
 
-	map = kernel_get_module_map(module);
+	/* Get a symbol map */
+	if (user)
+		map = dso__new_map(target);
+	else
+		map = kernel_get_module_map(target);
 	if (!map) {
-		pr_err("Failed to find %s map.\n", (module) ? : "kernel");
+		pr_err("Failed to get a map for %s\n", (target) ? : "kernel");
 		return -EINVAL;
 	}
-	return __show_available_funcs(map);
-}
-
-static int available_user_funcs(const char *target)
-{
-	struct map *map;
-	int ret;
-
-	ret = init_user_exec();
-	if (ret < 0)
-		return ret;
-
-	map = dso__new_map(target);
-	ret = __show_available_funcs(map);
-	dso__delete(map->dso);
-	map__delete(map);
-	return ret;
-}
 
-int show_available_funcs(const char *target, struct strfilter *_filter,
-					bool user)
-{
-	setup_pager();
+	/* Load symbols with given filter */
 	available_func_filter = _filter;
-
-	if (!user)
-		return available_kernel_funcs(target);
-
-	return available_user_funcs(target);
-}
-
-/*
- * uprobe_events only accepts address:
- * Convert function and any offset to address
- */
-static int convert_name_to_addr(struct perf_probe_event *pev, const char *exec)
-{
-	struct perf_probe_point *pp = &pev->point;
-	struct symbol *sym;
-	struct map *map = NULL;
-	char *function = NULL;
-	int ret = -EINVAL;
-	unsigned long long vaddr = 0;
-
-	if (!pp->function) {
-		pr_warning("No function specified for uprobes");
-		goto out;
-	}
-
-	function = strdup(pp->function);
-	if (!function) {
-		pr_warning("Failed to allocate memory by strdup.\n");
-		ret = -ENOMEM;
-		goto out;
-	}
-
-	map = dso__new_map(exec);
-	if (!map) {
-		pr_warning("Cannot find appropriate DSO for %s.\n", exec);
-		goto out;
-	}
-	available_func_filter = strfilter__new(function, NULL);
 	if (map__load(map, filter_available_functions)) {
-		pr_err("Failed to load map.\n");
-		goto out;
-	}
-
-	sym = map__find_symbol_by_name(map, function, NULL);
-	if (!sym) {
-		pr_warning("Cannot find %s in DSO %s\n", function, exec);
-		goto out;
-	}
-
-	if (map->start > sym->start)
-		vaddr = map->start;
-	vaddr += sym->start + pp->offset + map->pgoff;
-	pp->offset = 0;
-
-	if (!pev->event) {
-		pev->event = function;
-		function = NULL;
-	}
-	if (!pev->group) {
-		char *ptr1, *ptr2, *exec_copy;
-
-		pev->group = zalloc(sizeof(char *) * 64);
-		exec_copy = strdup(exec);
-		if (!exec_copy) {
-			ret = -ENOMEM;
-			pr_warning("Failed to copy exec string.\n");
-			goto out;
-		}
-
-		ptr1 = strdup(basename(exec_copy));
-		if (ptr1) {
-			ptr2 = strpbrk(ptr1, "-._");
-			if (ptr2)
-				*ptr2 = '\0';
-			e_snprintf(pev->group, 64, "%s_%s", PERFPROBE_GROUP,
-					ptr1);
-			free(ptr1);
-		}
-		free(exec_copy);
-	}
-	free(pp->function);
-	pp->function = zalloc(sizeof(char *) * MAX_PROBE_ARGS);
-	if (!pp->function) {
-		ret = -ENOMEM;
-		pr_warning("Failed to allocate memory by zalloc.\n");
-		goto out;
+		pr_err("Failed to load symbols in %s\n", (target) ? : "kernel");
+		goto end;
 	}
-	e_snprintf(pp->function, MAX_PROBE_ARGS, "0x%llx", vaddr);
-	ret = 0;
+	if (!dso__sorted_by_name(map->dso, map->type))
+		dso__sort_by_name(map->dso, map->type);
 
-out:
-	if (map) {
+	/* Show all (filtered) symbols */
+	setup_pager();
+	dso__fprintf_symbols_by_name(map->dso, map->type, stdout);
+end:
+	if (user) {
 		dso__delete(map->dso);
 		map__delete(map);
 	}
-	if (function)
-		free(function);
+	exit_symbol_maps();
+
 	return ret;
 }
+
diff --git a/tools/perf/util/probe-event.h b/tools/perf/util/probe-event.h
index fcaf7273e85..776c9347a3b 100644
--- a/tools/perf/util/probe-event.h
+++ b/tools/perf/util/probe-event.h
@@ -2,6 +2,7 @@
 #define _PROBE_EVENT_H
 
 #include <stdbool.h>
+#include "intlist.h"
 #include "strlist.h"
 #include "strfilter.h"
 
@@ -76,13 +77,6 @@ struct perf_probe_event {
 	struct perf_probe_arg	*args;	/* Arguments */
 };
 
-
-/* Line number container */
-struct line_node {
-	struct list_head	list;
-	int			line;
-};
-
 /* Line range */
 struct line_range {
 	char			*file;		/* File name */
@@ -92,7 +86,7 @@ struct line_range {
 	int			offset;		/* Start line offset */
 	char			*path;		/* Real path name */
 	char			*comp_dir;	/* Compile directory */
-	struct list_head	line_list;	/* Visible lines */
+	struct intlist		*line_list;	/* Visible lines */
 };
 
 /* List of variables */
@@ -124,7 +118,7 @@ extern int parse_line_range_desc(const char *cmd, struct line_range *lr);
 extern void line_range__clear(struct line_range *lr);
 
 /* Initialize line range */
-extern void line_range__init(struct line_range *lr);
+extern int line_range__init(struct line_range *lr);
 
 /* Internal use: Return kernel/module path */
 extern const char *kernel_get_module_path(const char *module);
diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c
index 061edb162b5..df023865469 100644
--- a/tools/perf/util/probe-finder.c
+++ b/tools/perf/util/probe-finder.c
@@ -34,7 +34,9 @@
 
 #include <linux/bitops.h>
 #include "event.h"
+#include "dso.h"
 #include "debug.h"
+#include "intlist.h"
 #include "util.h"
 #include "symbol.h"
 #include "probe-finder.h"
@@ -42,65 +44,6 @@
 /* Kprobe tracer basic type is up to u64 */
 #define MAX_BASIC_TYPE_BITS	64
 
-/* Line number list operations */
-
-/* Add a line to line number list */
-static int line_list__add_line(struct list_head *head, int line)
-{
-	struct line_node *ln;
-	struct list_head *p;
-
-	/* Reverse search, because new line will be the last one */
-	list_for_each_entry_reverse(ln, head, list) {
-		if (ln->line < line) {
-			p = &ln->list;
-			goto found;
-		} else if (ln->line == line)	/* Already exist */
-			return 1;
-	}
-	/* List is empty, or the smallest entry */
-	p = head;
-found:
-	pr_debug("line list: add a line %u\n", line);
-	ln = zalloc(sizeof(struct line_node));
-	if (ln == NULL)
-		return -ENOMEM;
-	ln->line = line;
-	INIT_LIST_HEAD(&ln->list);
-	list_add(&ln->list, p);
-	return 0;
-}
-
-/* Check if the line in line number list */
-static int line_list__has_line(struct list_head *head, int line)
-{
-	struct line_node *ln;
-
-	/* Reverse search, because new line will be the last one */
-	list_for_each_entry(ln, head, list)
-		if (ln->line == line)
-			return 1;
-
-	return 0;
-}
-
-/* Init line number list */
-static void line_list__init(struct list_head *head)
-{
-	INIT_LIST_HEAD(head);
-}
-
-/* Free line number list */
-static void line_list__free(struct list_head *head)
-{
-	struct line_node *ln;
-	while (!list_empty(head)) {
-		ln = list_first_entry(head, struct line_node, list);
-		list_del(&ln->list);
-		free(ln);
-	}
-}
-
 /* Dwarf FL wrappers */
 static char *debuginfo_path;	/* Currently dummy */
 
@@ -147,80 +90,7 @@ error:
 	return -ENOENT;
 }
 
-#if _ELFUTILS_PREREQ(0, 148)
-/* This method is buggy if elfutils is older than 0.148 */
-static int __linux_kernel_find_elf(Dwfl_Module *mod,
-				   void **userdata,
-				   const char *module_name,
-				   Dwarf_Addr base,
-				   char **file_name, Elf **elfp)
-{
-	int fd;
-	const char *path = kernel_get_module_path(module_name);
-
-	pr_debug2("Use file %s for %s\n", path, module_name);
-	if (path) {
-		fd = open(path, O_RDONLY);
-		if (fd >= 0) {
-			*file_name = strdup(path);
-			return fd;
-		}
-	}
-	/* If failed, try to call standard method */
-	return dwfl_linux_kernel_find_elf(mod, userdata, module_name, base,
-					  file_name, elfp);
-}
-
-static const Dwfl_Callbacks kernel_callbacks = {
-	.find_debuginfo = dwfl_standard_find_debuginfo,
-	.debuginfo_path = &debuginfo_path,
-
-	.find_elf = __linux_kernel_find_elf,
-	.section_address = dwfl_linux_kernel_module_section_address,
-};
-
-/* Get a Dwarf from live kernel image */
-static int debuginfo__init_online_kernel_dwarf(struct debuginfo *dbg,
-					       Dwarf_Addr addr)
-{
-	dbg->dwfl = dwfl_begin(&kernel_callbacks);
-	if (!dbg->dwfl)
-		return -EINVAL;
-
-	/* Load the kernel dwarves: Don't care the result here */
-	dwfl_linux_kernel_report_kernel(dbg->dwfl);
-	dwfl_linux_kernel_report_modules(dbg->dwfl);
-
-	dbg->dbg = dwfl_addrdwarf(dbg->dwfl, addr, &dbg->bias);
-	/* Here, check whether we could get a real dwarf */
-	if (!dbg->dbg) {
-		pr_debug("Failed to find kernel dwarf at %lx\n",
-			 (unsigned long)addr);
-		dwfl_end(dbg->dwfl);
-		memset(dbg, 0, sizeof(*dbg));
-		return -ENOENT;
-	}
-
-	return 0;
-}
-#else
-/* With older elfutils, this just support kernel module... */
-static int debuginfo__init_online_kernel_dwarf(struct debuginfo *dbg,
-					       Dwarf_Addr addr __maybe_unused)
-{
-	const char *path = kernel_get_module_path("kernel");
-
-	if (!path) {
-		pr_err("Failed to find vmlinux path\n");
-		return -ENOENT;
-	}
-
-	pr_debug2("Use file %s for debuginfo\n", path);
-	return debuginfo__init_offline_dwarf(dbg, path);
-}
-#endif
-
-struct debuginfo *debuginfo__new(const char *path)
+static struct debuginfo *__debuginfo__new(const char *path)
 {
 	struct debuginfo *dbg = zalloc(sizeof(*dbg));
 	if (!dbg)
@@ -228,21 +98,44 @@ struct debuginfo *debuginfo__new(const char *path)
 
 	if (debuginfo__init_offline_dwarf(dbg, path) < 0)
 		zfree(&dbg);
-
+	if (dbg)
+		pr_debug("Open Debuginfo file: %s\n", path);
 	return dbg;
 }
 
-struct debuginfo *debuginfo__new_online_kernel(unsigned long addr)
-{
-	struct debuginfo *dbg = zalloc(sizeof(*dbg));
+enum dso_binary_type distro_dwarf_types[] = {
+	DSO_BINARY_TYPE__FEDORA_DEBUGINFO,
+	DSO_BINARY_TYPE__UBUNTU_DEBUGINFO,
+	DSO_BINARY_TYPE__OPENEMBEDDED_DEBUGINFO,
+	DSO_BINARY_TYPE__BUILDID_DEBUGINFO,
+	DSO_BINARY_TYPE__NOT_FOUND,
+};
 
-	if (!dbg)
-		return NULL;
+struct debuginfo *debuginfo__new(const char *path)
+{
+	enum dso_binary_type *type;
+	char buf[PATH_MAX], nil = '\0';
+	struct dso *dso;
+	struct debuginfo *dinfo = NULL;
+
+	/* Try to open distro debuginfo files */
+	dso = dso__new(path);
+	if (!dso)
+		goto out;
 
-	if (debuginfo__init_online_kernel_dwarf(dbg, (Dwarf_Addr)addr) < 0)
-		zfree(&dbg);
+	for (type = distro_dwarf_types;
+	     !dinfo && *type != DSO_BINARY_TYPE__NOT_FOUND;
+	     type++) {
+		if (dso__read_binary_type_filename(dso, *type, &nil,
+						   buf, PATH_MAX) < 0)
+			continue;
+		dinfo = __debuginfo__new(buf);
+	}
+	dso__delete(dso);
 
-	return dbg;
+out:
+	/* if failed to open all distro debuginfo, open given binary */
+	return dinfo ? : __debuginfo__new(path);
 }
 
 void debuginfo__delete(struct debuginfo *dbg)
@@ -880,7 +773,7 @@ static int find_probe_point_by_line(struct probe_finder *pf)
 }
 
 /* Find lines which match lazy pattern */
-static int find_lazy_match_lines(struct list_head *head,
+static int find_lazy_match_lines(struct intlist *list,
 				 const char *fname, const char *pat)
 {
 	FILE *fp;
@@ -901,7 +794,7 @@ static int find_lazy_match_lines(struct list_head *head,
 			line[len - 1] = '\0';
 
 		if (strlazymatch(line, pat)) {
-			line_list__add_line(head, linenum);
+			intlist__add(list, linenum);
 			count++;
 		}
 		linenum++;
@@ -924,7 +817,7 @@ static int probe_point_lazy_walker(const char *fname, int lineno,
 	Dwarf_Die *sc_die, die_mem;
 	int ret;
 
-	if (!line_list__has_line(&pf->lcache, lineno) ||
+	if (!intlist__has_entry(pf->lcache, lineno) ||
 	    strtailcmp(fname, pf->fname) != 0)
 		return 0;
 
@@ -952,9 +845,9 @@ static int find_probe_point_lazy(Dwarf_Die *sp_die, struct probe_finder *pf)
 {
 	int ret = 0;
 
-	if (list_empty(&pf->lcache)) {
+	if (intlist__empty(pf->lcache)) {
 		/* Matching lazy line pattern */
-		ret = find_lazy_match_lines(&pf->lcache, pf->fname,
+		ret = find_lazy_match_lines(pf->lcache, pf->fname,
 					    pf->pev->point.lazy_line);
 		if (ret <= 0)
 			return ret;
@@ -1096,7 +989,9 @@ static int debuginfo__find_probes(struct debuginfo *dbg,
 #endif
 
 	off = 0;
-	line_list__init(&pf->lcache);
+	pf->lcache = intlist__new(NULL);
+	if (!pf->lcache)
+		return -ENOMEM;
 
 	/* Fastpath: lookup by function name from .debug_pubnames section */
 	if (pp->function) {
@@ -1149,7 +1044,8 @@ static int debuginfo__find_probes(struct debuginfo *dbg,
 	}
 
 found:
-	line_list__free(&pf->lcache);
+	intlist__delete(pf->lcache);
+	pf->lcache = NULL;
 
 	return ret;
 }
@@ -1537,7 +1433,7 @@ static int line_range_add_line(const char *src, unsigned int lineno,
 		if (lr->path == NULL)
 			return -ENOMEM;
 	}
-	return line_list__add_line(&lr->line_list, lineno);
+	return intlist__add(lr->line_list, lineno);
 }
 
 static int line_range_walk_cb(const char *fname, int lineno,
@@ -1565,7 +1461,7 @@ static int find_line_range_by_line(Dwarf_Die *sp_die, struct line_finder *lf)
 
 	/* Update status */
 	if (ret >= 0)
-		if (!list_empty(&lf->lr->line_list))
+		if (!intlist__empty(lf->lr->line_list))
 			ret = lf->found = 1;
 		else
 			ret = 0;	/* Lines are not found */
diff --git a/tools/perf/util/probe-finder.h b/tools/perf/util/probe-finder.h
index ffc33cdd25c..92590b2c7e1 100644
--- a/tools/perf/util/probe-finder.h
+++ b/tools/perf/util/probe-finder.h
@@ -3,6 +3,7 @@
 
 #include <stdbool.h>
 #include "util.h"
+#include "intlist.h"
 #include "probe-event.h"
 
 #define MAX_PROBE_BUFFER	1024
@@ -29,8 +30,8 @@ struct debuginfo {
 	Dwarf_Addr	bias;
 };
 
+/* This also tries to open distro debuginfo */
 extern struct debuginfo *debuginfo__new(const char *path);
-extern struct debuginfo *debuginfo__new_online_kernel(unsigned long addr);
 extern void debuginfo__delete(struct debuginfo *dbg);
 
 /* Find probe_trace_events specified by perf_probe_event from debuginfo */
@@ -66,7 +67,7 @@ struct probe_finder {
 	const char		*fname;		/* Real file name */
 	Dwarf_Die		cu_die;		/* Current CU */
 	Dwarf_Die		sp_die;
-	struct list_head	lcache;		/* Line cache for lazy match */
+	struct intlist		*lcache;	/* Line cache for lazy match */
 
 	/* For variable searching */
 #if _ELFUTILS_PREREQ(0, 142)
diff --git a/tools/perf/util/python-ext-sources b/tools/perf/util/python-ext-sources
index 595bfc73d2e..16a475a7d49 100644
--- a/tools/perf/util/python-ext-sources
+++ b/tools/perf/util/python-ext-sources
@@ -17,6 +17,6 @@ util/xyarray.c
 util/cgroup.c
 util/rblist.c
 util/strlist.c
-util/fs.c
+../lib/api/fs/fs.c
 util/trace-event.c
 ../../lib/rbtree.c
diff --git a/tools/perf/util/record.c b/tools/perf/util/record.c
index 373762501da..049e0a09ccd 100644
--- a/tools/perf/util/record.c
+++ b/tools/perf/util/record.c
@@ -2,7 +2,7 @@
 #include "evsel.h"
 #include "cpumap.h"
 #include "parse-events.h"
-#include "fs.h"
+#include <api/fs/fs.h>
 #include "util.h"
 
 typedef void (*setup_probe_fn_t)(struct perf_evsel *evsel);
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 5da6ce74c67..55960f22233 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -702,11 +702,12 @@ static void regs_dump__printf(u64 mask, u64 *regs)
 	}
 }
 
-static void regs_user__printf(struct perf_sample *sample, u64 mask)
+static void regs_user__printf(struct perf_sample *sample)
 {
 	struct regs_dump *user_regs = &sample->user_regs;
 
 	if (user_regs->regs) {
+		u64 mask = user_regs->mask;
 		printf("... user regs: mask 0x%" PRIx64 "\n", mask);
 		regs_dump__printf(mask, user_regs->regs);
 	}
@@ -793,7 +794,7 @@ static void dump_sample(struct perf_evsel *evsel, union perf_event *event,
 	if (!dump_trace)
 		return;
 
-	printf("(IP, %d): %d/%d: %#" PRIx64 " period: %" PRIu64 " addr: %#" PRIx64 "\n",
+	printf("(IP, 0x%x): %d/%d: %#" PRIx64 " period: %" PRIu64 " addr: %#" PRIx64 "\n",
 	       event->header.misc, sample->pid, sample->tid, sample->ip,
 	       sample->period, sample->addr);
 
@@ -806,7 +807,7 @@ static void dump_sample(struct perf_evsel *evsel, union perf_event *event,
 		branch_stack__printf(sample);
 
 	if (sample_type & PERF_SAMPLE_REGS_USER)
-		regs_user__printf(sample, evsel->attr.sample_regs_user);
+		regs_user__printf(sample);
 
 	if (sample_type & PERF_SAMPLE_STACK_USER)
 		stack_user__printf(&sample->user_stack);
diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c
index 516d19fb999..3b7dbf51d4a 100644
--- a/tools/perf/util/symbol-elf.c
+++ b/tools/perf/util/symbol-elf.c
@@ -506,6 +506,8 @@ int filename__read_debuglink(const char *filename, char *debuglink,
 	/* the start of this section is a zero-terminated string */
 	strncpy(debuglink, data->d_buf, size);
 
+	err = 0;
+
 out_elf_end:
 	elf_end(elf);
 out_close:
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index e89afc097d8..95e24977993 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -410,7 +410,7 @@ struct symbol *dso__find_symbol(struct dso *dso,
 	return symbols__find(&dso->symbols[type], addr);
 }
 
-struct symbol *dso__first_symbol(struct dso *dso, enum map_type type)
+static struct symbol *dso__first_symbol(struct dso *dso, enum map_type type)
 {
 	return symbols__first(&dso->symbols[type]);
 }
@@ -1251,6 +1251,46 @@ out_failure:
 	return -1;
 }
 
+static bool dso__is_compatible_symtab_type(struct dso *dso, bool kmod,
+					   enum dso_binary_type type)
+{
+	switch (type) {
+	case DSO_BINARY_TYPE__JAVA_JIT:
+	case DSO_BINARY_TYPE__DEBUGLINK:
+	case DSO_BINARY_TYPE__SYSTEM_PATH_DSO:
+	case DSO_BINARY_TYPE__FEDORA_DEBUGINFO:
+	case DSO_BINARY_TYPE__UBUNTU_DEBUGINFO:
+	case DSO_BINARY_TYPE__BUILDID_DEBUGINFO:
+	case DSO_BINARY_TYPE__OPENEMBEDDED_DEBUGINFO:
+		return !kmod && dso->kernel == DSO_TYPE_USER;
+
+	case DSO_BINARY_TYPE__KALLSYMS:
+	case DSO_BINARY_TYPE__VMLINUX:
+	case DSO_BINARY_TYPE__KCORE:
+		return dso->kernel == DSO_TYPE_KERNEL;
+
+	case DSO_BINARY_TYPE__GUEST_KALLSYMS:
+	case DSO_BINARY_TYPE__GUEST_VMLINUX:
+	case DSO_BINARY_TYPE__GUEST_KCORE:
+		return dso->kernel == DSO_TYPE_GUEST_KERNEL;
+
+	case DSO_BINARY_TYPE__GUEST_KMODULE:
+	case DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE:
+		/*
+		 * kernel modules know their symtab type - it's set when
+		 * creating a module dso in machine__new_module().
+		 */
+		return kmod && dso->symtab_type == type;
+
+	case DSO_BINARY_TYPE__BUILD_ID_CACHE:
+		return true;
+
+	case DSO_BINARY_TYPE__NOT_FOUND:
+	default:
+		return false;
+	}
+}
+
 int dso__load(struct dso *dso, struct map *map, symbol_filter_t filter)
 {
 	char *name;
@@ -1261,6 +1301,7 @@ int dso__load(struct dso *dso, struct map *map, symbol_filter_t filter)
 	int ss_pos = 0;
 	struct symsrc ss_[2];
 	struct symsrc *syms_ss = NULL, *runtime_ss = NULL;
+	bool kmod;
 
 	dso__set_loaded(dso, map->type);
 
@@ -1301,7 +1342,11 @@ int dso__load(struct dso *dso, struct map *map, symbol_filter_t filter)
 	if (!name)
 		return -1;
 
-	/* Iterate over candidate debug images.
+	kmod = dso->symtab_type == DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE ||
+		dso->symtab_type == DSO_BINARY_TYPE__GUEST_KMODULE;
+
+	/*
+	 * Iterate over candidate debug images.
 	 * Keep track of "interesting" ones (those which have a symtab, dynsym,
 	 * and/or opd section) for processing.
 	 */
@@ -1311,6 +1356,9 @@ int dso__load(struct dso *dso, struct map *map, symbol_filter_t filter)
 
 		enum dso_binary_type symtab_type = binary_type_symtab[i];
 
+		if (!dso__is_compatible_symtab_type(dso, kmod, symtab_type))
+			continue;
+
 		if (dso__read_binary_type_filename(dso, symtab_type,
 						   root_dir, name, PATH_MAX))
 			continue;
@@ -1353,15 +1401,10 @@ int dso__load(struct dso *dso, struct map *map, symbol_filter_t filter)
 	if (!runtime_ss && syms_ss)
 		runtime_ss = syms_ss;
 
-	if (syms_ss) {
-		int km;
-
-		km = dso->symtab_type == DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE ||
-		     dso->symtab_type == DSO_BINARY_TYPE__GUEST_KMODULE;
-		ret = dso__load_sym(dso, map, syms_ss, runtime_ss, filter, km);
-	} else {
+	if (syms_ss)
+		ret = dso__load_sym(dso, map, syms_ss, runtime_ss, filter, kmod);
+	else
 		ret = -1;
-	}
 
 	if (ret > 0) {
 		int nr_plt;
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index fffe2888a1c..501e4e722e8 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -79,6 +79,17 @@ struct symbol {
 void symbol__delete(struct symbol *sym);
 void symbols__delete(struct rb_root *symbols);
 
+/* symbols__for_each_entry - iterate over symbols (rb_root)
+ *
+ * @symbols: the rb_root of symbols
+ * @pos: the 'struct symbol *' to use as a loop cursor
+ * @nd: the 'struct rb_node *' to use as a temporary storage
+ */
+#define symbols__for_each_entry(symbols, pos, nd)			\
+	for (nd = rb_first(symbols);					\
+	     nd && (pos = rb_entry(nd, struct symbol, rb_node));	\
+	     nd = rb_next(nd))
+
 static inline size_t symbol__size(const struct symbol *sym)
 {
 	return sym->end - sym->start + 1;
@@ -175,7 +186,7 @@ struct addr_location {
 	struct symbol *sym;
 	u64	      addr;
 	char	      level;
-	bool	      filtered;
+	u8	      filtered;
 	u8	      cpumode;
 	s32	      cpu;
 };
@@ -223,7 +234,6 @@ struct symbol *dso__find_symbol(struct dso *dso, enum map_type type,
 				u64 addr);
 struct symbol *dso__find_symbol_by_name(struct dso *dso, enum map_type type,
 					const char *name);
-struct symbol *dso__first_symbol(struct dso *dso, enum map_type type);
 
 int filename__read_build_id(const char *filename, void *bf, size_t size);
 int sysfs__read_build_id(const char *filename, void *bf, size_t size);
diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c
index 0358882c891..3ce0498bdae 100644
--- a/tools/perf/util/thread.c
+++ b/tools/perf/util/thread.c
@@ -142,3 +142,24 @@ int thread__fork(struct thread *thread, struct thread *parent, u64 timestamp)
 
 	return 0;
 }
+
+void thread__find_cpumode_addr_location(struct thread *thread,
+					struct machine *machine,
+					enum map_type type, u64 addr,
+					struct addr_location *al)
+{
+	size_t i;
+	const u8 const cpumodes[] = {
+		PERF_RECORD_MISC_USER,
+		PERF_RECORD_MISC_KERNEL,
+		PERF_RECORD_MISC_GUEST_USER,
+		PERF_RECORD_MISC_GUEST_KERNEL
+	};
+
+	for (i = 0; i < ARRAY_SIZE(cpumodes); i++) {
+		thread__find_addr_location(thread, machine, cpumodes[i], type,
+					   addr, al);
+		if (al->map)
+			break;
+	}
+}
diff --git a/tools/perf/util/thread.h b/tools/perf/util/thread.h
index 5b856bf942e..9b29f085aed 100644
--- a/tools/perf/util/thread.h
+++ b/tools/perf/util/thread.h
@@ -44,12 +44,6 @@ void thread__insert_map(struct thread *thread, struct map *map);
 int thread__fork(struct thread *thread, struct thread *parent, u64 timestamp);
 size_t thread__fprintf(struct thread *thread, FILE *fp);
 
-static inline struct map *thread__find_map(struct thread *thread,
-					   enum map_type type, u64 addr)
-{
-	return thread ? map_groups__find(&thread->mg, type, addr) : NULL;
-}
-
 void thread__find_addr_map(struct thread *thread, struct machine *machine,
 			   u8 cpumode, enum map_type type, u64 addr,
 			   struct addr_location *al);
@@ -58,6 +52,11 @@ void thread__find_addr_location(struct thread *thread, struct machine *machine,
 				u8 cpumode, enum map_type type, u64 addr,
 				struct addr_location *al);
 
+void thread__find_cpumode_addr_location(struct thread *thread,
+					struct machine *machine,
+					enum map_type type, u64 addr,
+					struct addr_location *al);
+
 static inline void *thread__priv(struct thread *thread)
 {
 	return thread->priv;
diff --git a/tools/perf/util/trace-event-parse.c b/tools/perf/util/trace-event-parse.c
index e0d6d07f684..c36636fd825 100644
--- a/tools/perf/util/trace-event-parse.c
+++ b/tools/perf/util/trace-event-parse.c
@@ -126,6 +126,7 @@ void event_format__print(struct event_format *event,
 	trace_seq_init(&s);
 	pevent_event_info(&s, event, &record);
 	trace_seq_do_printf(&s);
+	trace_seq_destroy(&s);
 }
 
 void parse_proc_kallsyms(struct pevent *pevent,
diff --git a/tools/perf/util/unwind-libdw.c b/tools/perf/util/unwind-libdw.c
new file mode 100644
index 00000000000..67db73ec3da
--- /dev/null
+++ b/tools/perf/util/unwind-libdw.c
@@ -0,0 +1,210 @@
+#include <linux/compiler.h>
+#include <elfutils/libdw.h>
+#include <elfutils/libdwfl.h>
+#include <inttypes.h>
+#include <errno.h>
+#include "unwind.h"
+#include "unwind-libdw.h"
+#include "machine.h"
+#include "thread.h"
+#include "types.h"
+#include "event.h"
+#include "perf_regs.h"
+
+static char *debuginfo_path;
+
+static const Dwfl_Callbacks offline_callbacks = {
+	.find_debuginfo		= dwfl_standard_find_debuginfo,
+	.debuginfo_path		= &debuginfo_path,
+	.section_address	= dwfl_offline_section_address,
+};
+
+static int __report_module(struct addr_location *al, u64 ip,
+			    struct unwind_info *ui)
+{
+	Dwfl_Module *mod;
+	struct dso *dso = NULL;
+
+	thread__find_addr_location(ui->thread, ui->machine,
+				   PERF_RECORD_MISC_USER,
+				   MAP__FUNCTION, ip, al);
+
+	if (al->map)
+		dso = al->map->dso;
+
+	if (!dso)
+		return 0;
+
+	mod = dwfl_addrmodule(ui->dwfl, ip);
+	if (!mod)
+		mod = dwfl_report_elf(ui->dwfl, dso->short_name,
+				      dso->long_name, -1, al->map->start,
+				      false);
+
+	return mod && dwfl_addrmodule(ui->dwfl, ip) == mod ? 0 : -1;
+}
+
+static int report_module(u64 ip, struct unwind_info *ui)
+{
+	struct addr_location al;
+
+	return __report_module(&al, ip, ui);
+}
+
+static int entry(u64 ip, struct unwind_info *ui)
+
+{
+	struct unwind_entry e;
+	struct addr_location al;
+
+	if (__report_module(&al, ip, ui))
+		return -1;
+
+	e.ip  = ip;
+	e.map = al.map;
+	e.sym = al.sym;
+
+	pr_debug("unwind: %s:ip = 0x%" PRIx64 " (0x%" PRIx64 ")\n",
+		 al.sym ? al.sym->name : "''",
+		 ip,
+		 al.map ? al.map->map_ip(al.map, ip) : (u64) 0);
+
+	return ui->cb(&e, ui->arg);
+}
+
+static pid_t next_thread(Dwfl *dwfl, void *arg, void **thread_argp)
+{
+	/* We want only single thread to be processed. */
+	if (*thread_argp != NULL)
+		return 0;
+
+	*thread_argp = arg;
+	return dwfl_pid(dwfl);
+}
+
+static int access_dso_mem(struct unwind_info *ui, Dwarf_Addr addr,
+			  Dwarf_Word *data)
+{
+	struct addr_location al;
+	ssize_t size;
+
+	thread__find_addr_map(ui->thread, ui->machine, PERF_RECORD_MISC_USER,
+			      MAP__FUNCTION, addr, &al);
+	if (!al.map) {
+		pr_debug("unwind: no map for %lx\n", (unsigned long)addr);
+		return -1;
+	}
+
+	if (!al.map->dso)
+		return -1;
+
+	size = dso__data_read_addr(al.map->dso, al.map, ui->machine,
+				   addr, (u8 *) data, sizeof(*data));
+
+	return !(size == sizeof(*data));
+}
+
+static bool memory_read(Dwfl *dwfl __maybe_unused, Dwarf_Addr addr, Dwarf_Word *result,
+			void *arg)
+{
+	struct unwind_info *ui = arg;
+	struct stack_dump *stack = &ui->sample->user_stack;
+	u64 start, end;
+	int offset;
+	int ret;
+
+	ret = perf_reg_value(&start, &ui->sample->user_regs, PERF_REG_SP);
+	if (ret)
+		return false;
+
+	end = start + stack->size;
+
+	/* Check overflow. */
+	if (addr + sizeof(Dwarf_Word) < addr)
+		return false;
+
+	if (addr < start || addr + sizeof(Dwarf_Word) > end) {
+		ret = access_dso_mem(ui, addr, result);
+		if (ret) {
+			pr_debug("unwind: access_mem 0x%" PRIx64 " not inside range"
+				 " 0x%" PRIx64 "-0x%" PRIx64 "\n",
+				addr, start, end);
+			return false;
+		}
+		return true;
+	}
+
+	offset  = addr - start;
+	*result = *(Dwarf_Word *)&stack->data[offset];
+	pr_debug("unwind: access_mem addr 0x%" PRIx64 ", val %lx, offset %d\n",
+		 addr, (unsigned long)*result, offset);
+	return true;
+}
+
+static const Dwfl_Thread_Callbacks callbacks = {
+	.next_thread		= next_thread,
+	.memory_read		= memory_read,
+	.set_initial_registers	= libdw__arch_set_initial_registers,
+};
+
+static int
+frame_callback(Dwfl_Frame *state, void *arg)
+{
+	struct unwind_info *ui = arg;
+	Dwarf_Addr pc;
+
+	if (!dwfl_frame_pc(state, &pc, NULL)) {
+		pr_err("%s", dwfl_errmsg(-1));
+		return DWARF_CB_ABORT;
+	}
+
+	return entry(pc, ui) || !(--ui->max_stack) ?
+	       DWARF_CB_ABORT : DWARF_CB_OK;
+}
+
+int unwind__get_entries(unwind_entry_cb_t cb, void *arg,
+			struct machine *machine, struct thread *thread,
+			struct perf_sample *data,
+			int max_stack)
+{
+	struct unwind_info ui = {
+		.sample		= data,
+		.thread		= thread,
+		.machine	= machine,
+		.cb		= cb,
+		.arg		= arg,
+		.max_stack	= max_stack,
+	};
+	Dwarf_Word ip;
+	int err = -EINVAL;
+
+	if (!data->user_regs.regs)
+		return -EINVAL;
+
+	ui.dwfl = dwfl_begin(&offline_callbacks);
+	if (!ui.dwfl)
+		goto out;
+
+	err = perf_reg_value(&ip, &data->user_regs, PERF_REG_IP);
+	if (err)
+		goto out;
+
+	err = report_module(ip, &ui);
+	if (err)
+		goto out;
+
+	if (!dwfl_attach_state(ui.dwfl, EM_NONE, thread->tid, &callbacks, &ui))
+		goto out;
+
+	err = dwfl_getthread_frames(ui.dwfl, thread->tid, frame_callback, &ui);
+
+	if (err && !ui.max_stack)
+		err = 0;
+
+ out:
+	if (err)
+		pr_debug("unwind: failed with '%s'\n", dwfl_errmsg(-1));
+
+	dwfl_end(ui.dwfl);
+	return 0;
+}
diff --git a/tools/perf/util/unwind-libdw.h b/tools/perf/util/unwind-libdw.h
new file mode 100644
index 00000000000..417a1426f3a
--- /dev/null
+++ b/tools/perf/util/unwind-libdw.h
@@ -0,0 +1,21 @@
+#ifndef __PERF_UNWIND_LIBDW_H
+#define __PERF_UNWIND_LIBDW_H
+
+#include <elfutils/libdwfl.h>
+#include "event.h"
+#include "thread.h"
+#include "unwind.h"
+
+bool libdw__arch_set_initial_registers(Dwfl_Thread *thread, void *arg);
+
+struct unwind_info {
+	Dwfl			*dwfl;
+	struct perf_sample      *sample;
+	struct machine          *machine;
+	struct thread           *thread;
+	unwind_entry_cb_t	cb;
+	void			*arg;
+	int			max_stack;
+};
+
+#endif /* __PERF_UNWIND_LIBDW_H */
diff --git a/tools/perf/util/unwind.c b/tools/perf/util/unwind-libunwind.c
index 742f23bf35f..bd5768d74f0 100644
--- a/tools/perf/util/unwind.c
+++ b/tools/perf/util/unwind-libunwind.c
@@ -86,7 +86,6 @@ struct unwind_info {
 	struct perf_sample	*sample;
 	struct machine		*machine;
 	struct thread		*thread;
-	u64			sample_uregs;
 };
 
 #define dw_read(ptr, type, end) ({	\
@@ -391,30 +390,13 @@ static int access_dso_mem(struct unwind_info *ui, unw_word_t addr,
 	return !(size == sizeof(*data));
 }
 
-static int reg_value(unw_word_t *valp, struct regs_dump *regs, int id,
-		     u64 sample_regs)
-{
-	int i, idx = 0;
-
-	if (!(sample_regs & (1 << id)))
-		return -EINVAL;
-
-	for (i = 0; i < id; i++) {
-		if (sample_regs & (1 << i))
-			idx++;
-	}
-
-	*valp = regs->regs[idx];
-	return 0;
-}
-
 static int access_mem(unw_addr_space_t __maybe_unused as,
 		      unw_word_t addr, unw_word_t *valp,
 		      int __write, void *arg)
 {
 	struct unwind_info *ui = arg;
 	struct stack_dump *stack = &ui->sample->user_stack;
-	unw_word_t start, end;
+	u64 start, end;
 	int offset;
 	int ret;
 
@@ -424,8 +406,7 @@ static int access_mem(unw_addr_space_t __maybe_unused as,
 		return 0;
 	}
 
-	ret = reg_value(&start, &ui->sample->user_regs, PERF_REG_SP,
-			ui->sample_uregs);
+	ret = perf_reg_value(&start, &ui->sample->user_regs, PERF_REG_SP);
 	if (ret)
 		return ret;
 
@@ -438,8 +419,9 @@ static int access_mem(unw_addr_space_t __maybe_unused as,
 	if (addr < start || addr + sizeof(unw_word_t) >= end) {
 		ret = access_dso_mem(ui, addr, valp);
 		if (ret) {
-			pr_debug("unwind: access_mem %p not inside range %p-%p\n",
-				(void *)addr, (void *)start, (void *)end);
+			pr_debug("unwind: access_mem %p not inside range"
+				 " 0x%" PRIx64 "-0x%" PRIx64 "\n",
+				 (void *) addr, start, end);
 			*valp = 0;
 			return ret;
 		}
@@ -448,8 +430,8 @@ static int access_mem(unw_addr_space_t __maybe_unused as,
 
 	offset = addr - start;
 	*valp  = *(unw_word_t *)&stack->data[offset];
-	pr_debug("unwind: access_mem addr %p, val %lx, offset %d\n",
-		 (void *)addr, (unsigned long)*valp, offset);
+	pr_debug("unwind: access_mem addr %p val %lx, offset %d\n",
+		 (void *) addr, (unsigned long)*valp, offset);
 	return 0;
 }
 
@@ -459,6 +441,7 @@ static int access_reg(unw_addr_space_t __maybe_unused as,
 {
 	struct unwind_info *ui = arg;
 	int id, ret;
+	u64 val;
 
 	/* Don't support write, I suspect we don't need it. */
 	if (__write) {
@@ -471,16 +454,17 @@ static int access_reg(unw_addr_space_t __maybe_unused as,
 		return 0;
 	}
 
-	id = unwind__arch_reg_id(regnum);
+	id = libunwind__arch_reg_id(regnum);
 	if (id < 0)
 		return -EINVAL;
 
-	ret = reg_value(valp, &ui->sample->user_regs, id, ui->sample_uregs);
+	ret = perf_reg_value(&val, &ui->sample->user_regs, id);
 	if (ret) {
 		pr_err("unwind: can't read reg %d\n", regnum);
 		return ret;
 	}
 
+	*valp = (unw_word_t) val;
 	pr_debug("unwind: reg %d, val %lx\n", regnum, (unsigned long)*valp);
 	return 0;
 }
@@ -563,7 +547,7 @@ static int get_entries(struct unwind_info *ui, unwind_entry_cb_t cb,
 		unw_word_t ip;
 
 		unw_get_reg(&c, UNW_REG_IP, &ip);
-		ret = entry(ip, ui->thread, ui->machine, cb, arg);
+		ret = ip ? entry(ip, ui->thread, ui->machine, cb, arg) : 0;
 	}
 
 	unw_destroy_addr_space(addr_space);
@@ -572,13 +556,11 @@ static int get_entries(struct unwind_info *ui, unwind_entry_cb_t cb,
 
 int unwind__get_entries(unwind_entry_cb_t cb, void *arg,
 			struct machine *machine, struct thread *thread,
-			u64 sample_uregs, struct perf_sample *data,
-			int max_stack)
+			struct perf_sample *data, int max_stack)
 {
-	unw_word_t ip;
+	u64 ip;
 	struct unwind_info ui = {
 		.sample       = data,
-		.sample_uregs = sample_uregs,
 		.thread       = thread,
 		.machine      = machine,
 	};
@@ -587,7 +569,7 @@ int unwind__get_entries(unwind_entry_cb_t cb, void *arg,
 	if (!data->user_regs.regs)
 		return -EINVAL;
 
-	ret = reg_value(&ip, &data->user_regs, PERF_REG_IP, sample_uregs);
+	ret = perf_reg_value(&ip, &data->user_regs, PERF_REG_IP);
 	if (ret)
 		return ret;
 
@@ -595,5 +577,5 @@ int unwind__get_entries(unwind_entry_cb_t cb, void *arg,
 	if (ret)
 		return -ENOMEM;
 
-	return get_entries(&ui, cb, arg, max_stack);
+	return --max_stack > 0 ? get_entries(&ui, cb, arg, max_stack) : 0;
 }
diff --git a/tools/perf/util/unwind.h b/tools/perf/util/unwind.h
index d5966f49e22..b031316f221 100644
--- a/tools/perf/util/unwind.h
+++ b/tools/perf/util/unwind.h
@@ -13,24 +13,25 @@ struct unwind_entry {
 
 typedef int (*unwind_entry_cb_t)(struct unwind_entry *entry, void *arg);
 
-#ifdef HAVE_LIBUNWIND_SUPPORT
+#ifdef HAVE_DWARF_UNWIND_SUPPORT
 int unwind__get_entries(unwind_entry_cb_t cb, void *arg,
 			struct machine *machine,
 			struct thread *thread,
-			u64 sample_uregs,
 			struct perf_sample *data, int max_stack);
-int unwind__arch_reg_id(int regnum);
+/* libunwind specific */
+#ifdef HAVE_LIBUNWIND_SUPPORT
+int libunwind__arch_reg_id(int regnum);
+#endif
 #else
 static inline int
 unwind__get_entries(unwind_entry_cb_t cb __maybe_unused,
 		    void *arg __maybe_unused,
 		    struct machine *machine __maybe_unused,
 		    struct thread *thread __maybe_unused,
-		    u64 sample_uregs __maybe_unused,
 		    struct perf_sample *data __maybe_unused,
 		    int max_stack __maybe_unused)
 {
 	return 0;
 }
-#endif /* HAVE_LIBUNWIND_SUPPORT */
+#endif /* HAVE_DWARF_UNWIND_SUPPORT */
 #endif /* __UNWIND_H */
diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c
index 42ad667bb31..9f66549562b 100644
--- a/tools/perf/util/util.c
+++ b/tools/perf/util/util.c
@@ -1,6 +1,6 @@
 #include "../perf.h"
 #include "util.h"
-#include "fs.h"
+#include <api/fs/fs.h>
 #include <sys/mman.h>
 #ifdef HAVE_BACKTRACE_SUPPORT
 #include <execinfo.h>