62 files changed, 739 insertions, 208 deletions

diff --git a/tools/perf/Documentation/perf-list.txt b/tools/perf/Documentation/perf-list.txt
index 143d98df2df9..f709de54707b 100644
--- a/tools/perf/Documentation/perf-list.txt
+++ b/tools/perf/Documentation/perf-list.txt
@@ -8,7 +8,7 @@ perf-list - List all symbolic event types
 SYNOPSIS
 --------
 [verse]
-'perf list' [--no-desc] [--long-desc] [hw|sw|cache|tracepoint|pmu|event_glob]
+'perf list' [--no-desc] [--long-desc] [hw|sw|cache|tracepoint|pmu|sdt|event_glob]
 
 DESCRIPTION
 -----------
@@ -244,6 +244,8 @@ To limit the list use:
 
 . 'pmu' to print the kernel supplied PMU events.
 
+. 'sdt' to list all Statically Defined Tracepoint events.
+
 . If none of the above is matched, it will apply the supplied glob to all
   events, printing the ones that match.
 
diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt
index e9a61f5485eb..37a175914157 100644
--- a/tools/perf/Documentation/perf-report.txt
+++ b/tools/perf/Documentation/perf-report.txt
@@ -235,6 +235,7 @@ OPTIONS
         sort_key can be:
         - function: compare on functions (default)
         - address: compare on individual code addresses
+        - srcline: compare on source filename and line number
 
         branch can be:
         - branch: include last branch information in callgraph when available.
@@ -430,6 +431,10 @@ include::itrace.txt[]
 --hierarchy::
         Enable hierarchical output.
 
+--inline::
+        If a callgraph address belongs to an inlined function, the inline stack
+        will be printed. Each entry is function name or file/line.
+
 include::callchain-overhead-calculation.txt[]
 
 SEE ALSO
diff --git a/tools/perf/bench/bench.h b/tools/perf/bench/bench.h
index 579a592990dd..842ab2781cdc 100644
--- a/tools/perf/bench/bench.h
+++ b/tools/perf/bench/bench.h
@@ -25,17 +25,17 @@
 # endif
 #endif
 
-int bench_numa(int argc, const char **argv, const char *prefix);
-int bench_sched_messaging(int argc, const char **argv, const char *prefix);
-int bench_sched_pipe(int argc, const char **argv, const char *prefix);
-int bench_mem_memcpy(int argc, const char **argv, const char *prefix);
-int bench_mem_memset(int argc, const char **argv, const char *prefix);
-int bench_futex_hash(int argc, const char **argv, const char *prefix);
-int bench_futex_wake(int argc, const char **argv, const char *prefix);
-int bench_futex_wake_parallel(int argc, const char **argv, const char *prefix);
-int bench_futex_requeue(int argc, const char **argv, const char *prefix);
+int bench_numa(int argc, const char **argv);
+int bench_sched_messaging(int argc, const char **argv);
+int bench_sched_pipe(int argc, const char **argv);
+int bench_mem_memcpy(int argc, const char **argv);
+int bench_mem_memset(int argc, const char **argv);
+int bench_futex_hash(int argc, const char **argv);
+int bench_futex_wake(int argc, const char **argv);
+int bench_futex_wake_parallel(int argc, const char **argv);
+int bench_futex_requeue(int argc, const char **argv);
 /* pi futexes */
-int bench_futex_lock_pi(int argc, const char **argv, const char *prefix);
+int bench_futex_lock_pi(int argc, const char **argv);
 
 #define BENCH_FORMAT_DEFAULT_STR        "default"
 #define BENCH_FORMAT_DEFAULT            0
diff --git a/tools/perf/bench/futex-hash.c b/tools/perf/bench/futex-hash.c
index 2499e1b0c6fb..fe16b310097f 100644
--- a/tools/perf/bench/futex-hash.c
+++ b/tools/perf/bench/futex-hash.c
@@ -114,8 +114,7 @@ static void print_summary(void)
                (int) runtime.tv_sec);
 }
 
-int bench_futex_hash(int argc, const char **argv,
-                     const char *prefix __maybe_unused)
+int bench_futex_hash(int argc, const char **argv)
 {
         int ret = 0;
         cpu_set_t cpu;
diff --git a/tools/perf/bench/futex-lock-pi.c b/tools/perf/bench/futex-lock-pi.c
index a20814d94af1..73a1c44ea63c 100644
--- a/tools/perf/bench/futex-lock-pi.c
+++ b/tools/perf/bench/futex-lock-pi.c
@@ -140,8 +140,7 @@ static void create_threads(struct worker *w, pthread_attr_t thread_attr)
         }
 }
 
-int bench_futex_lock_pi(int argc, const char **argv,
-                        const char *prefix __maybe_unused)
+int bench_futex_lock_pi(int argc, const char **argv)
 {
         int ret = 0;
         unsigned int i;
diff --git a/tools/perf/bench/futex-requeue.c b/tools/perf/bench/futex-requeue.c
index 9fad1e4fcd3e..41786cbea24c 100644
--- a/tools/perf/bench/futex-requeue.c
+++ b/tools/perf/bench/futex-requeue.c
@@ -109,8 +109,7 @@ static void toggle_done(int sig __maybe_unused,
         done = true;
 }
 
-int bench_futex_requeue(int argc, const char **argv,
-                        const char *prefix __maybe_unused)
+int bench_futex_requeue(int argc, const char **argv)
 {
         int ret = 0;
         unsigned int i, j;
diff --git a/tools/perf/bench/futex-wake-parallel.c b/tools/perf/bench/futex-wake-parallel.c
index 40f5fcf1d120..4ab12c8e016a 100644
--- a/tools/perf/bench/futex-wake-parallel.c
+++ b/tools/perf/bench/futex-wake-parallel.c
@@ -197,8 +197,7 @@ static void toggle_done(int sig __maybe_unused,
         done = true;
 }
 
-int bench_futex_wake_parallel(int argc, const char **argv,
-                              const char *prefix __maybe_unused)
+int bench_futex_wake_parallel(int argc, const char **argv)
 {
         int ret = 0;
         unsigned int i, j;
diff --git a/tools/perf/bench/futex-wake.c b/tools/perf/bench/futex-wake.c
index 789490281ae3..2fa49222ef8d 100644
--- a/tools/perf/bench/futex-wake.c
+++ b/tools/perf/bench/futex-wake.c
@@ -115,8 +115,7 @@ static void toggle_done(int sig __maybe_unused,
         done = true;
 }
 
-int bench_futex_wake(int argc, const char **argv,
-                     const char *prefix __maybe_unused)
+int bench_futex_wake(int argc, const char **argv)
 {
         int ret = 0;
         unsigned int i, j;
diff --git a/tools/perf/bench/mem-functions.c b/tools/perf/bench/mem-functions.c
index 52504a83b5a1..d1dea33dcfcf 100644
--- a/tools/perf/bench/mem-functions.c
+++ b/tools/perf/bench/mem-functions.c
@@ -284,7 +284,7 @@ static const char * const bench_mem_memcpy_usage[] = {
         NULL
 };
 
-int bench_mem_memcpy(int argc, const char **argv, const char *prefix __maybe_unused)
+int bench_mem_memcpy(int argc, const char **argv)
 {
         struct bench_mem_info info = {
                 .functions              = memcpy_functions,
@@ -358,7 +358,7 @@ static const struct function memset_functions[] = {
         { .name = NULL, }
 };
 
-int bench_mem_memset(int argc, const char **argv, const char *prefix __maybe_unused)
+int bench_mem_memset(int argc, const char **argv)
 {
         struct bench_mem_info info = {
                 .functions              = memset_functions,
diff --git a/tools/perf/bench/numa.c b/tools/perf/bench/numa.c
index 6bd0581de298..1fe43bd5a012 100644
--- a/tools/perf/bench/numa.c
+++ b/tools/perf/bench/numa.c
@@ -1767,7 +1767,7 @@ static int bench_all(void)
         return 0;
 }
 
-int bench_numa(int argc, const char **argv, const char *prefix __maybe_unused)
+int bench_numa(int argc, const char **argv)
 {
         init_params(&p0, "main,", argc, argv);
         argc = parse_options(argc, argv, options, bench_numa_usage, 0);
diff --git a/tools/perf/bench/sched-messaging.c b/tools/perf/bench/sched-messaging.c
index 6a111e775210..4f961e74535b 100644
--- a/tools/perf/bench/sched-messaging.c
+++ b/tools/perf/bench/sched-messaging.c
@@ -260,8 +260,7 @@ static const char * const bench_sched_message_usage[] = {
         NULL
 };
 
-int bench_sched_messaging(int argc, const char **argv,
-                    const char *prefix __maybe_unused)
+int bench_sched_messaging(int argc, const char **argv)
 {
         unsigned int i, total_children;
         struct timeval start, stop, diff;
diff --git a/tools/perf/bench/sched-pipe.c b/tools/perf/bench/sched-pipe.c
index 2243f0150d76..a152737370c5 100644
--- a/tools/perf/bench/sched-pipe.c
+++ b/tools/perf/bench/sched-pipe.c
@@ -76,7 +76,7 @@ static void *worker_thread(void *__tdata)
         return NULL;
 }
 
-int bench_sched_pipe(int argc, const char **argv, const char *prefix __maybe_unused)
+int bench_sched_pipe(int argc, const char **argv)
 {
         struct thread_data threads[2], *td;
         int pipe_1[2], pipe_2[2];
diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c
index e54b1f9fe1ee..56a7c8d210b9 100644
--- a/tools/perf/builtin-annotate.c
+++ b/tools/perf/builtin-annotate.c
@@ -383,7 +383,7 @@ static const char * const annotate_usage[] = {
         NULL
 };
 
-int cmd_annotate(int argc, const char **argv, const char *prefix __maybe_unused)
+int cmd_annotate(int argc, const char **argv)
 {
         struct perf_annotate annotate = {
                 .tool = {
diff --git a/tools/perf/builtin-bench.c b/tools/perf/builtin-bench.c
index a1cddc6bbf0f..445e62881254 100644
--- a/tools/perf/builtin-bench.c
+++ b/tools/perf/builtin-bench.c
@@ -25,7 +25,7 @@
 #include <string.h>
 #include <sys/prctl.h>
 
-typedef int (*bench_fn_t)(int argc, const char **argv, const char *prefix);
+typedef int (*bench_fn_t)(int argc, const char **argv);
 
 struct bench {
         const char      *name;
@@ -155,7 +155,7 @@ static int bench_str2int(const char *str)
  * to something meaningful:
  */
 static int run_bench(const char *coll_name, const char *bench_name, bench_fn_t fn,
-                     int argc, const char **argv, const char *prefix)
+                     int argc, const char **argv)
 {
         int size;
         char *name;
@@ -171,7 +171,7 @@ static int run_bench(const char *coll_name, const char *bench_name, bench_fn_t f
         prctl(PR_SET_NAME, name);
         argv[0] = name;
 
-        ret = fn(argc, argv, prefix);
+        ret = fn(argc, argv);
 
         free(name);
 
@@ -198,7 +198,7 @@ static void run_collection(struct collection *coll)
                 fflush(stdout);
 
                 argv[1] = bench->name;
-                run_bench(coll->name, bench->name, bench->fn, 1, argv, NULL);
+                run_bench(coll->name, bench->name, bench->fn, 1, argv);
                 printf("\n");
         }
 }
@@ -211,7 +211,7 @@ static void run_all_collections(void)
                 run_collection(coll);
 }
 
-int cmd_bench(int argc, const char **argv, const char *prefix __maybe_unused)
+int cmd_bench(int argc, const char **argv)
 {
         struct collection *coll;
         int ret = 0;
@@ -270,7 +270,7 @@ int cmd_bench(int argc, const char **argv, const char *prefix __maybe_unused)
                         if (bench_format == BENCH_FORMAT_DEFAULT)
                                 printf("# Running '%s/%s' benchmark:\n", coll->name, bench->name);
                         fflush(stdout);
-                        ret = run_bench(coll->name, bench->name, bench->fn, argc-1, argv+1, prefix);
+                        ret = run_bench(coll->name, bench->name, bench->fn, argc-1, argv+1);
                         goto end;
                 }
 
diff --git a/tools/perf/builtin-buildid-cache.c b/tools/perf/builtin-buildid-cache.c
index 30e2b2cb2421..94b55eee0d9b 100644
--- a/tools/perf/builtin-buildid-cache.c
+++ b/tools/perf/builtin-buildid-cache.c
@@ -276,8 +276,7 @@ static int build_id_cache__update_file(const char *filename)
         return err;
 }
 
-int cmd_buildid_cache(int argc, const char **argv,
-                      const char *prefix __maybe_unused)
+int cmd_buildid_cache(int argc, const char **argv)
 {
         struct strlist *list;
         struct str_node *pos;
diff --git a/tools/perf/builtin-buildid-list.c b/tools/perf/builtin-buildid-list.c
index 5e914ee79eb3..26f4e608207f 100644
--- a/tools/perf/builtin-buildid-list.c
+++ b/tools/perf/builtin-buildid-list.c
@@ -87,8 +87,7 @@ out:
         return 0;
 }
 
-int cmd_buildid_list(int argc, const char **argv,
-                     const char *prefix __maybe_unused)
+int cmd_buildid_list(int argc, const char **argv)
 {
         bool show_kernel = false;
         bool with_hits = false;
diff --git a/tools/perf/builtin-c2c.c b/tools/perf/builtin-c2c.c
index 5cd6d7a047b9..70c2c773a2b8 100644
--- a/tools/perf/builtin-c2c.c
+++ b/tools/perf/builtin-c2c.c
@@ -2755,12 +2755,12 @@ static int perf_c2c__record(int argc, const char **argv)
                 pr_debug("\n");
         }
 
-        ret = cmd_record(i, rec_argv, NULL);
+        ret = cmd_record(i, rec_argv);
         free(rec_argv);
         return ret;
 }
 
-int cmd_c2c(int argc, const char **argv, const char *prefix __maybe_unused)
+int cmd_c2c(int argc, const char **argv)
 {
         argc = parse_options(argc, argv, c2c_options, c2c_usage,
                              PARSE_OPT_STOP_AT_NON_OPTION);
diff --git a/tools/perf/builtin-config.c b/tools/perf/builtin-config.c
index 8c0d93b7c2f0..55f04f85b049 100644
--- a/tools/perf/builtin-config.c
+++ b/tools/perf/builtin-config.c
@@ -154,7 +154,7 @@ static int parse_config_arg(char *arg, char **var, char **value)
         return 0;
 }
 
-int cmd_config(int argc, const char **argv, const char *prefix __maybe_unused)
+int cmd_config(int argc, const char **argv)
 {
         int i, ret = 0;
         struct perf_config_set *set;
diff --git a/tools/perf/builtin-data.c b/tools/perf/builtin-data.c
index 7ad6e17ac6b3..0adb5f82335a 100644
--- a/tools/perf/builtin-data.c
+++ b/tools/perf/builtin-data.c
@@ -6,7 +6,7 @@
 #include "data-convert.h"
 #include "data-convert-bt.h"
 
-typedef int (*data_cmd_fn_t)(int argc, const char **argv, const char *prefix);
+typedef int (*data_cmd_fn_t)(int argc, const char **argv);
 
 struct data_cmd {
         const char      *name;
@@ -50,8 +50,7 @@ static const char * const data_convert_usage[] = {
         NULL
 };
 
-static int cmd_data_convert(int argc, const char **argv,
-                            const char *prefix __maybe_unused)
+static int cmd_data_convert(int argc, const char **argv)
 {
         const char *to_ctf     = NULL;
         struct perf_data_convert_opts opts = {
@@ -98,7 +97,7 @@ static struct data_cmd data_cmds[] = {
         { .name = NULL, },
 };
 
-int cmd_data(int argc, const char **argv, const char *prefix)
+int cmd_data(int argc, const char **argv)
 {
         struct data_cmd *cmd;
         const char *cmdstr;
@@ -118,7 +117,7 @@ int cmd_data(int argc, const char **argv, const char *prefix)
                 if (strcmp(cmd->name, cmdstr))
                         continue;
 
-                return cmd->fn(argc, argv, prefix);
+                return cmd->fn(argc, argv);
         }
 
         pr_err("Unknown command: %s\n", cmdstr);
diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c
index 5e4803158672..cd2605d86984 100644
--- a/tools/perf/builtin-diff.c
+++ b/tools/perf/builtin-diff.c
@@ -1321,7 +1321,7 @@ static int diff__config(const char *var, const char *value,
         return 0;
 }
 
-int cmd_diff(int argc, const char **argv, const char *prefix __maybe_unused)
+int cmd_diff(int argc, const char **argv)
 {
         int ret = hists__init();
 
diff --git a/tools/perf/builtin-evlist.c b/tools/perf/builtin-evlist.c
index e09c4287fe87..6d210e40d611 100644
--- a/tools/perf/builtin-evlist.c
+++ b/tools/perf/builtin-evlist.c
@@ -46,7 +46,7 @@ static int __cmd_evlist(const char *file_name, struct perf_attr_details *details
         return 0;
 }
 
-int cmd_evlist(int argc, const char **argv, const char *prefix __maybe_unused)
+int cmd_evlist(int argc, const char **argv)
 {
         struct perf_attr_details details = { .verbose = false, };
         const struct option options[] = {
diff --git a/tools/perf/builtin-ftrace.c b/tools/perf/builtin-ftrace.c
index 6087295f8827..f80fb60b00b0 100644
--- a/tools/perf/builtin-ftrace.c
+++ b/tools/perf/builtin-ftrace.c
@@ -304,7 +304,7 @@ static int perf_ftrace_config(const char *var, const char *value, void *cb)
         return -1;
 }
 
-int cmd_ftrace(int argc, const char **argv, const char *prefix __maybe_unused)
+int cmd_ftrace(int argc, const char **argv)
 {
         int ret;
         struct perf_ftrace ftrace = {
diff --git a/tools/perf/builtin-help.c b/tools/perf/builtin-help.c
index aed0d844e8c2..7ae238929e95 100644
--- a/tools/perf/builtin-help.c
+++ b/tools/perf/builtin-help.c
@@ -418,7 +418,7 @@ static int show_html_page(const char *perf_cmd)
         return 0;
 }
 
-int cmd_help(int argc, const char **argv, const char *prefix __maybe_unused)
+int cmd_help(int argc, const char **argv)
 {
         bool show_all = false;
         enum help_format help_format = HELP_FORMAT_MAN;
diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c
index 8d1d13b9bab6..42dff0b1375a 100644
--- a/tools/perf/builtin-inject.c
+++ b/tools/perf/builtin-inject.c
@@ -738,7 +738,7 @@ static int __cmd_inject(struct perf_inject *inject)
         return ret;
 }
 
-int cmd_inject(int argc, const char **argv, const char *prefix __maybe_unused)
+int cmd_inject(int argc, const char **argv)
 {
         struct perf_inject inject = {
                 .tool = {
diff --git a/tools/perf/builtin-kallsyms.c b/tools/perf/builtin-kallsyms.c
index 224bfc454b4a..8ff38c4eb2c0 100644
--- a/tools/perf/builtin-kallsyms.c
+++ b/tools/perf/builtin-kallsyms.c
@@ -43,7 +43,7 @@ static int __cmd_kallsyms(int argc, const char **argv)
         return 0;
 }
 
-int cmd_kallsyms(int argc, const char **argv, const char *prefix __maybe_unused)
+int cmd_kallsyms(int argc, const char **argv)
 {
         const struct option options[] = {
         OPT_INCR('v', "verbose", &verbose, "be more verbose (show counter open errors, etc)"),
diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c
index d509e74bc6e8..515587825af4 100644
--- a/tools/perf/builtin-kmem.c
+++ b/tools/perf/builtin-kmem.c
@@ -1866,7 +1866,7 @@ static int __cmd_record(int argc, const char **argv)
         for (j = 1; j < (unsigned int)argc; j++, i++)
                 rec_argv[i] = argv[j];
 
-        return cmd_record(i, rec_argv, NULL);
+        return cmd_record(i, rec_argv);
 }
 
 static int kmem_config(const char *var, const char *value, void *cb __maybe_unused)
@@ -1885,7 +1885,7 @@ static int kmem_config(const char *var, const char *value, void *cb __maybe_unus
         return 0;
 }
 
-int cmd_kmem(int argc, const char **argv, const char *prefix __maybe_unused)
+int cmd_kmem(int argc, const char **argv)
 {
         const char * const default_slab_sort = "frag,hit,bytes";
         const char * const default_page_sort = "bytes,hit";
diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c
index 18e6c38864bc..38b409173693 100644
--- a/tools/perf/builtin-kvm.c
+++ b/tools/perf/builtin-kvm.c
@@ -1209,7 +1209,7 @@ kvm_events_record(struct perf_kvm_stat *kvm, int argc, const char **argv)
         set_option_flag(record_options, 0, "transaction", PARSE_OPT_DISABLED);
 
         record_usage = kvm_stat_record_usage;
-        return cmd_record(i, rec_argv, NULL);
+        return cmd_record(i, rec_argv);
 }
 
 static int
@@ -1477,7 +1477,7 @@ static int kvm_cmd_stat(const char *file_name, int argc, const char **argv)
 #endif
 
 perf_stat:
-        return cmd_stat(argc, argv, NULL);
+        return cmd_stat(argc, argv);
 }
 #endif /* HAVE_KVM_STAT_SUPPORT */
 
@@ -1496,7 +1496,7 @@ static int __cmd_record(const char *file_name, int argc, const char **argv)
 
         BUG_ON(i != rec_argc);
 
-        return cmd_record(i, rec_argv, NULL);
+        return cmd_record(i, rec_argv);
 }
 
 static int __cmd_report(const char *file_name, int argc, const char **argv)
@@ -1514,7 +1514,7 @@ static int __cmd_report(const char *file_name, int argc, const char **argv)
 
         BUG_ON(i != rec_argc);
 
-        return cmd_report(i, rec_argv, NULL);
+        return cmd_report(i, rec_argv);
 }
 
 static int
@@ -1533,10 +1533,10 @@ __cmd_buildid_list(const char *file_name, int argc, const char **argv)
 
         BUG_ON(i != rec_argc);
 
-        return cmd_buildid_list(i, rec_argv, NULL);
+        return cmd_buildid_list(i, rec_argv);
 }
 
-int cmd_kvm(int argc, const char **argv, const char *prefix __maybe_unused)
+int cmd_kvm(int argc, const char **argv)
 {
         const char *file_name = NULL;
         const struct option kvm_options[] = {
@@ -1591,9 +1591,9 @@ int cmd_kvm(int argc, const char **argv, const char *prefix __maybe_unused)
         else if (!strncmp(argv[0], "rep", 3))
                 return __cmd_report(file_name, argc, argv);
         else if (!strncmp(argv[0], "diff", 4))
-                return cmd_diff(argc, argv, NULL);
+                return cmd_diff(argc, argv);
         else if (!strncmp(argv[0], "top", 3))
-                return cmd_top(argc, argv, NULL);
+                return cmd_top(argc, argv);
         else if (!strncmp(argv[0], "buildid-list", 12))
                 return __cmd_buildid_list(file_name, argc, argv);
 #ifdef HAVE_KVM_STAT_SUPPORT
diff --git a/tools/perf/builtin-list.c b/tools/perf/builtin-list.c
index be9195e95c78..4bf2cb4d25aa 100644
--- a/tools/perf/builtin-list.c
+++ b/tools/perf/builtin-list.c
@@ -20,7 +20,7 @@
 static bool desc_flag = true;
 static bool details_flag;
 
-int cmd_list(int argc, const char **argv, const char *prefix __maybe_unused)
+int cmd_list(int argc, const char **argv)
 {
         int i;
         bool raw_dump = false;
diff --git a/tools/perf/builtin-lock.c b/tools/perf/builtin-lock.c
index e992e7206993..b686fb6759da 100644
--- a/tools/perf/builtin-lock.c
+++ b/tools/perf/builtin-lock.c
@@ -941,12 +941,12 @@ static int __cmd_record(int argc, const char **argv)
 
         BUG_ON(i != rec_argc);
 
-        ret = cmd_record(i, rec_argv, NULL);
+        ret = cmd_record(i, rec_argv);
         free(rec_argv);
         return ret;
 }
 
-int cmd_lock(int argc, const char **argv, const char *prefix __maybe_unused)
+int cmd_lock(int argc, const char **argv)
 {
         const struct option lock_options[] = {
         OPT_STRING('i', "input", &input_name, "file", "input file name"),
@@ -1009,7 +1009,7 @@ int cmd_lock(int argc, const char **argv, const char *prefix __maybe_unused)
                 rc = __cmd_report(false);
         } else if (!strcmp(argv[0], "script")) {
                 /* Aliased to 'perf script' */
-                return cmd_script(argc, argv, prefix);
+                return cmd_script(argc, argv);
         } else if (!strcmp(argv[0], "info")) {
                 if (argc) {
                         argc = parse_options(argc, argv,
diff --git a/tools/perf/builtin-mem.c b/tools/perf/builtin-mem.c
index 030a6cfdda59..643f4faac0d0 100644
--- a/tools/perf/builtin-mem.c
+++ b/tools/perf/builtin-mem.c
@@ -129,7 +129,7 @@ static int __cmd_record(int argc, const char **argv, struct perf_mem *mem)
                 pr_debug("\n");
         }
 
-        ret = cmd_record(i, rec_argv, NULL);
+        ret = cmd_record(i, rec_argv);
         free(rec_argv);
         return ret;
 }
@@ -256,7 +256,7 @@ static int report_events(int argc, const char **argv, struct perf_mem *mem)
         for (j = 1; j < argc; j++, i++)
                 rep_argv[i] = argv[j];
 
-        ret = cmd_report(i, rep_argv, NULL);
+        ret = cmd_report(i, rep_argv);
         free(rep_argv);
         return ret;
 }
@@ -330,7 +330,7 @@ error:
         return ret;
 }
 
-int cmd_mem(int argc, const char **argv, const char *prefix __maybe_unused)
+int cmd_mem(int argc, const char **argv)
 {
         struct stat st;
         struct perf_mem mem = {
diff --git a/tools/perf/builtin-probe.c b/tools/perf/builtin-probe.c
index 51cdc230f6ca..d7360c2bda13 100644
--- a/tools/perf/builtin-probe.c
+++ b/tools/perf/builtin-probe.c
@@ -468,7 +468,7 @@ out:
 
 
 static int
-__cmd_probe(int argc, const char **argv, const char *prefix __maybe_unused)
+__cmd_probe(int argc, const char **argv)
 {
         const char * const probe_usage[] = {
                 "perf probe [<options>] 'PROBEDEF' ['PROBEDEF' ...]",
@@ -687,13 +687,13 @@ __cmd_probe(int argc, const char **argv, const char *prefix __maybe_unused)
         return 0;
 }
 
-int cmd_probe(int argc, const char **argv, const char *prefix)
+int cmd_probe(int argc, const char **argv)
 {
         int ret;
 
         ret = init_params();
         if (!ret) {
-                ret = __cmd_probe(argc, argv, prefix);
+                ret = __cmd_probe(argc, argv);
                 cleanup_params();
         }
 
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 04faef79a548..3191ab063852 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -1667,7 +1667,7 @@ static struct option __record_options[] = {
 
 struct option *record_options = __record_options;
 
-int cmd_record(int argc, const char **argv, const char *prefix __maybe_unused)
+int cmd_record(int argc, const char **argv)
 {
         int err;
         struct record *rec = &record;
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 5ab8117c3bfd..c18158b83eb1 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -681,7 +681,7 @@ const char report_callchain_help[] = "Display call graph (stack chain/backtrace)
                                      CALLCHAIN_REPORT_HELP
                                      "\n\t\t\t\tDefault: " CALLCHAIN_DEFAULT_OPT;
 
-int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
+int cmd_report(int argc, const char **argv)
 {
         struct perf_session *session;
         struct itrace_synth_opts itrace_synth_opts = { .set = 0, };
@@ -845,6 +845,8 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
                              stdio__config_color, "always"),
         OPT_STRING(0, "time", &report.time_str, "str",
                    "Time span of interest (start,stop)"),
+        OPT_BOOLEAN(0, "inline", &symbol_conf.inline_name,
+                    "Show inline function"),
         OPT_END()
         };
         struct perf_data_file file = {
diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c
index b92c4d97192c..79833e226789 100644
--- a/tools/perf/builtin-sched.c
+++ b/tools/perf/builtin-sched.c
@@ -3272,10 +3272,10 @@ static int __cmd_record(int argc, const char **argv)
 
         BUG_ON(i != rec_argc);
 
-        return cmd_record(i, rec_argv, NULL);
+        return cmd_record(i, rec_argv);
 }
 
-int cmd_sched(int argc, const char **argv, const char *prefix __maybe_unused)
+int cmd_sched(int argc, const char **argv)
 {
         const char default_sort_order[] = "avg, max, switch, runtime";
         struct perf_sched sched = {
@@ -3412,7 +3412,7 @@ int cmd_sched(int argc, const char **argv, const char *prefix __maybe_unused)
          * Aliased to 'perf script' for now:
          */
         if (!strcmp(argv[0], "script"))
-                return cmd_script(argc, argv, prefix);
+                return cmd_script(argc, argv);
 
         if (!strncmp(argv[0], "rec", 3)) {
                 return __cmd_record(argc, argv);
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index c98e16689b57..46acc8ece41f 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -2359,7 +2359,7 @@ int process_cpu_map_event(struct perf_tool *tool __maybe_unused,
         return set_maps(script);
 }
 
-int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused)
+int cmd_script(int argc, const char **argv)
 {
         bool show_full_info = false;
         bool header = false;
@@ -2504,7 +2504,7 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused)
         if (argc > 1 && !strncmp(argv[0], "rec", strlen("rec"))) {
                 rec_script_path = get_script_path(argv[1], RECORD_SUFFIX);
                 if (!rec_script_path)
-                        return cmd_record(argc, argv, NULL);
+                        return cmd_record(argc, argv);
         }
 
         if (argc > 1 && !strncmp(argv[0], "rep", strlen("rep"))) {
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 01b589e3c3a6..2158ea14da57 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -2478,7 +2478,7 @@ static void setup_system_wide(int forks)
         }
 }
 
-int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused)
+int cmd_stat(int argc, const char **argv)
 {
         const char * const stat_usage[] = {
                 "perf stat [<options>] [<command>]",
diff --git a/tools/perf/builtin-timechart.c b/tools/perf/builtin-timechart.c
index fbd7c6c695b8..fafdb44b8bcb 100644
--- a/tools/perf/builtin-timechart.c
+++ b/tools/perf/builtin-timechart.c
@@ -1773,7 +1773,7 @@ static int timechart__io_record(int argc, const char **argv)
         for (i = 0; i < (unsigned int)argc; i++)
                 *p++ = argv[i];
 
-        return cmd_record(rec_argc, rec_argv, NULL);
+        return cmd_record(rec_argc, rec_argv);
 }
 
 
@@ -1864,7 +1864,7 @@ static int timechart__record(struct timechart *tchart, int argc, const char **ar
         for (j = 0; j < (unsigned int)argc; j++)
                 *p++ = argv[j];
 
-        return cmd_record(rec_argc, rec_argv, NULL);
+        return cmd_record(rec_argc, rec_argv);
 }
 
 static int
@@ -1917,8 +1917,7 @@ parse_time(const struct option *opt, const char *arg, int __maybe_unused unset)
         return 0;
 }
 
-int cmd_timechart(int argc, const char **argv,
-                  const char *prefix __maybe_unused)
+int cmd_timechart(int argc, const char **argv)
 {
         struct timechart tchart = {
                 .tool = {
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index ab9077915763..a0c97c70ec81 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -1075,7 +1075,7 @@ parse_percent_limit(const struct option *opt, const char *arg,
 const char top_callchain_help[] = CALLCHAIN_RECORD_HELP CALLCHAIN_REPORT_HELP
         "\n\t\t\t\tDefault: fp,graph,0.5,caller,function";
 
-int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused)
+int cmd_top(int argc, const char **argv)
 {
         char errbuf[BUFSIZ];
         struct perf_top top = {
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 912fedc5b42d..c88f9f215e6f 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -1653,15 +1653,17 @@ static int trace__vfs_getname(struct trace *trace, struct perf_evsel *evsel,
 
         ttrace = thread__priv(thread);
         if (!ttrace)
-                goto out;
+                goto out_put;
 
         filename_len = strlen(filename);
+        if (filename_len == 0)
+                goto out_put;
 
         if (ttrace->filename.namelen < filename_len) {
                 char *f = realloc(ttrace->filename.name, filename_len + 1);
 
                 if (f == NULL)
-                                goto out;
+                        goto out_put;
 
                 ttrace->filename.namelen = filename_len;
                 ttrace->filename.name = f;
@@ -1671,12 +1673,12 @@ static int trace__vfs_getname(struct trace *trace, struct perf_evsel *evsel,
         ttrace->filename.pending_open = true;
 
         if (!ttrace->filename.ptr)
-                goto out;
+                goto out_put;
 
         entry_str_len = strlen(ttrace->entry_str);
         remaining_space = trace__entry_str_size - entry_str_len - 1; /* \0 */
         if (remaining_space <= 0)
-                goto out;
+                goto out_put;
 
         if (filename_len > (size_t)remaining_space) {
                 filename += filename_len - remaining_space;
@@ -1690,6 +1692,8 @@ static int trace__vfs_getname(struct trace *trace, struct perf_evsel *evsel,
 
         ttrace->filename.ptr = 0;
         ttrace->filename.entry_str_pos = 0;
+out_put:
+        thread__put(thread);
 out:
         return 0;
 }
@@ -1710,6 +1714,7 @@ static int trace__sched_stat_runtime(struct trace *trace, struct perf_evsel *evs
 
         ttrace->runtime_ms += runtime_ms;
         trace->runtime_ms += runtime_ms;
+out_put:
         thread__put(thread);
         return 0;
 
@@ -1720,8 +1725,7 @@ out_dump:
                (pid_t)perf_evsel__intval(evsel, sample, "pid"),
                runtime,
                perf_evsel__intval(evsel, sample, "vruntime"));
-        thread__put(thread);
-        return 0;
+        goto out_put;
 }
 
 static void bpf_output__printer(enum binary_printer_ops op,
@@ -1920,7 +1924,7 @@ static int trace__process_sample(struct perf_tool *tool,
 
         thread = machine__findnew_thread(trace->host, sample->pid, sample->tid);
         if (thread && thread__is_filtered(thread))
-                return 0;
+                goto out;
 
         trace__set_base_time(trace, evsel, sample);
 
@@ -1928,7 +1932,8 @@ static int trace__process_sample(struct perf_tool *tool,
                 ++trace->nr_events;
                 handler(trace, evsel, event, sample);
         }
-
+out:
+        thread__put(thread);
         return err;
 }
 
@@ -1988,7 +1993,7 @@ static int trace__record(struct trace *trace, int argc, const char **argv)
         for (i = 0; i < (unsigned int)argc; i++)
                 rec_argv[j++] = argv[i];
 
-        return cmd_record(j, rec_argv, NULL);
+        return cmd_record(j, rec_argv);
 }
 
 static size_t trace__fprintf_thread_summary(struct trace *trace, FILE *fp);
@@ -2786,7 +2791,7 @@ out:
         return err;
 }
 
-int cmd_trace(int argc, const char **argv, const char *prefix __maybe_unused)
+int cmd_trace(int argc, const char **argv)
 {
         const char *trace_usage[] = {
                 "perf trace [<options>] [<command>]",
diff --git a/tools/perf/builtin-version.c b/tools/perf/builtin-version.c
index 9b10cda6b6dc..b9a095b1db99 100644
--- a/tools/perf/builtin-version.c
+++ b/tools/perf/builtin-version.c
@@ -2,8 +2,7 @@
 #include "builtin.h"
 #include "perf.h"
 
-int cmd_version(int argc __maybe_unused, const char **argv __maybe_unused,
-                const char *prefix __maybe_unused)
+int cmd_version(int argc __maybe_unused, const char **argv __maybe_unused)
 {
         printf("perf version %s\n", perf_version_string);
         return 0;
diff --git a/tools/perf/builtin.h b/tools/perf/builtin.h
index 036e1e35b1a8..26669bf9129c 100644
--- a/tools/perf/builtin.h
+++ b/tools/perf/builtin.h
@@ -13,35 +13,35 @@ void prune_packed_objects(int);
 int read_line_with_nul(char *buf, int size, FILE *file);
 int check_pager_config(const char *cmd);
 
-int cmd_annotate(int argc, const char **argv, const char *prefix);
-int cmd_bench(int argc, const char **argv, const char *prefix);
-int cmd_buildid_cache(int argc, const char **argv, const char *prefix);
-int cmd_buildid_list(int argc, const char **argv, const char *prefix);
-int cmd_config(int argc, const char **argv, const char *prefix);
-int cmd_c2c(int argc, const char **argv, const char *prefix);
-int cmd_diff(int argc, const char **argv, const char *prefix);
-int cmd_evlist(int argc, const char **argv, const char *prefix);
-int cmd_help(int argc, const char **argv, const char *prefix);
-int cmd_sched(int argc, const char **argv, const char *prefix);
-int cmd_kallsyms(int argc, const char **argv, const char *prefix);
-int cmd_list(int argc, const char **argv, const char *prefix);
-int cmd_record(int argc, const char **argv, const char *prefix);
-int cmd_report(int argc, const char **argv, const char *prefix);
-int cmd_stat(int argc, const char **argv, const char *prefix);
-int cmd_timechart(int argc, const char **argv, const char *prefix);
-int cmd_top(int argc, const char **argv, const char *prefix);
-int cmd_script(int argc, const char **argv, const char *prefix);
-int cmd_version(int argc, const char **argv, const char *prefix);
-int cmd_probe(int argc, const char **argv, const char *prefix);
-int cmd_kmem(int argc, const char **argv, const char *prefix);
-int cmd_lock(int argc, const char **argv, const char *prefix);
-int cmd_kvm(int argc, const char **argv, const char *prefix);
-int cmd_test(int argc, const char **argv, const char *prefix);
-int cmd_trace(int argc, const char **argv, const char *prefix);
-int cmd_inject(int argc, const char **argv, const char *prefix);
-int cmd_mem(int argc, const char **argv, const char *prefix);
-int cmd_data(int argc, const char **argv, const char *prefix);
-int cmd_ftrace(int argc, const char **argv, const char *prefix);
+int cmd_annotate(int argc, const char **argv);
+int cmd_bench(int argc, const char **argv);
+int cmd_buildid_cache(int argc, const char **argv);
+int cmd_buildid_list(int argc, const char **argv);
+int cmd_config(int argc, const char **argv);
+int cmd_c2c(int argc, const char **argv);
+int cmd_diff(int argc, const char **argv);
+int cmd_evlist(int argc, const char **argv);
+int cmd_help(int argc, const char **argv);
+int cmd_sched(int argc, const char **argv);
+int cmd_kallsyms(int argc, const char **argv);
+int cmd_list(int argc, const char **argv);
+int cmd_record(int argc, const char **argv);
+int cmd_report(int argc, const char **argv);
+int cmd_stat(int argc, const char **argv);
+int cmd_timechart(int argc, const char **argv);
+int cmd_top(int argc, const char **argv);
+int cmd_script(int argc, const char **argv);
+int cmd_version(int argc, const char **argv);
+int cmd_probe(int argc, const char **argv);
+int cmd_kmem(int argc, const char **argv);
+int cmd_lock(int argc, const char **argv);
+int cmd_kvm(int argc, const char **argv);
+int cmd_test(int argc, const char **argv);
+int cmd_trace(int argc, const char **argv);
+int cmd_inject(int argc, const char **argv);
+int cmd_mem(int argc, const char **argv);
+int cmd_data(int argc, const char **argv);
+int cmd_ftrace(int argc, const char **argv);
 
 int find_scripts(char **scripts_array, char **scripts_path_array);
 #endif
diff --git a/tools/perf/perf.c b/tools/perf/perf.c
index 6d5479e03e0d..4b283d18e158 100644
--- a/tools/perf/perf.c
+++ b/tools/perf/perf.c
@@ -34,7 +34,7 @@ const char *input_name;
 
 struct cmd_struct {
         const char *cmd;
-        int (*fn)(int, const char **, const char *);
+        int (*fn)(int, const char **);
         int option;
 };
 
@@ -339,13 +339,8 @@ static int run_builtin(struct cmd_struct *p, int argc, const char **argv)
 {
         int status;
         struct stat st;
-        const char *prefix;
         char sbuf[STRERR_BUFSIZE];
 
-        prefix = NULL;
-        if (p->option & RUN_SETUP)
-                prefix = NULL; /* setup_perf_directory(); */
-
         if (use_browser == -1)
                 use_browser = check_browser_config(p->cmd);
 
@@ -356,7 +351,7 @@ static int run_builtin(struct cmd_struct *p, int argc, const char **argv)
         commit_pager_choice();
 
         perf_env__set_cmdline(&perf_env, argc, argv);
-        status = p->fn(argc, argv, prefix);
+        status = p->fn(argc, argv);
         perf_config__exit();
         exit_browser(status);
         perf_env__exit(&perf_env);
@@ -566,7 +561,7 @@ int main(int argc, const char **argv)
 #ifdef HAVE_LIBAUDIT_SUPPORT
                 setup_path();
                 argv[0] = "trace";
-                return cmd_trace(argc, argv, NULL);
+                return cmd_trace(argc, argv);
 #else
                 fprintf(stderr,
                         "trace command not available: missing audit-libs devel package at build time.\n");
diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c
index 86822969e8a8..e6d7876c94c2 100644
--- a/tools/perf/tests/builtin-test.c
+++ b/tools/perf/tests/builtin-test.c
@@ -464,7 +464,7 @@ static int perf_test__list(int argc, const char **argv)
         return 0;
 }
 
-int cmd_test(int argc, const char **argv, const char *prefix __maybe_unused)
+int cmd_test(int argc, const char **argv)
 {
         const char *test_usage[] = {
         "perf test [<options>] [{list <test-name-fragment>|[<test-name-fragments>|<test-numbers>]}]",
diff --git a/tools/perf/tests/sdt.c b/tools/perf/tests/sdt.c
index f59d210e1baf..26e5b7a0b839 100644
--- a/tools/perf/tests/sdt.c
+++ b/tools/perf/tests/sdt.c
@@ -43,7 +43,7 @@ static char *get_self_path(void)
 {
         char *buf = calloc(PATH_MAX, sizeof(char));
 
-        if (buf && readlink("/proc/self/exe", buf, PATH_MAX) < 0) {
+        if (buf && readlink("/proc/self/exe", buf, PATH_MAX - 1) < 0) {
                 pr_debug("Failed to get correct path of perf\n");
                 free(buf);
                 return NULL;
diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c
index 2dc82bec10c0..da24072bb76e 100644
--- a/tools/perf/ui/browsers/hists.c
+++ b/tools/perf/ui/browsers/hists.c
@@ -144,9 +144,60 @@ static void callchain_list__set_folding(struct callchain_list *cl, bool unfold)
         cl->unfolded = unfold ? cl->has_children : false;
 }
 
+static struct inline_node *inline_node__create(struct map *map, u64 ip)
+{
+        struct dso *dso;
+        struct inline_node *node;
+
+        if (map == NULL)
+                return NULL;
+
+        dso = map->dso;
+        if (dso == NULL)
+                return NULL;
+
+        if (dso->kernel != DSO_TYPE_USER)
+                return NULL;
+
+        node = dso__parse_addr_inlines(dso,
+                                       map__rip_2objdump(map, ip));
+
+        return node;
+}
+
+static int inline__count_rows(struct inline_node *node)
+{
+        struct inline_list *ilist;
+        int i = 0;
+
+        if (node == NULL)
+                return 0;
+
+        list_for_each_entry(ilist, &node->val, list) {
+                if ((ilist->filename != NULL) || (ilist->funcname != NULL))
+                        i++;
+        }
+
+        return i;
+}
+
+static int callchain_list__inline_rows(struct callchain_list *chain)
+{
+        struct inline_node *node;
+        int rows;
+
+        node = inline_node__create(chain->ms.map, chain->ip);
+        if (node == NULL)
+                return 0;
+
+        rows = inline__count_rows(node);
+        inline_node__delete(node);
+        return rows;
+}
+
 static int callchain_node__count_rows_rb_tree(struct callchain_node *node)
 {
-        int n = 0;
+        int n = 0, inline_rows;
         struct rb_node *nd;
 
         for (nd = rb_first(&node->rb_root); nd; nd = rb_next(nd)) {
@@ -156,6 +207,13 @@ static int callchain_node__count_rows_rb_tree(struct callchain_node *node)
 
                 list_for_each_entry(chain, &child->val, list) {
                         ++n;
+
+                        if (symbol_conf.inline_name) {
+                                inline_rows =
+                                        callchain_list__inline_rows(chain);
+                                n += inline_rows;
+                        }
+
                         /* We need this because we may not have children */
                         folded_sign = callchain_list__folded(chain);
                         if (folded_sign == '+')
@@ -207,7 +265,7 @@ static int callchain_node__count_rows(struct callchain_node *node)
 {
         struct callchain_list *chain;
         bool unfolded = false;
-        int n = 0;
+        int n = 0, inline_rows;
 
         if (callchain_param.mode == CHAIN_FLAT)
                 return callchain_node__count_flat_rows(node);
@@ -216,6 +274,11 @@ static int callchain_node__count_rows(struct callchain_node *node)
 
         list_for_each_entry(chain, &node->val, list) {
                 ++n;
+                if (symbol_conf.inline_name) {
+                        inline_rows = callchain_list__inline_rows(chain);
+                        n += inline_rows;
+                }
+
                 unfolded = chain->unfolded;
         }
 
@@ -362,6 +425,19 @@ static void hist_entry__init_have_children(struct hist_entry *he)
         he->init_have_children = true;
 }
 
+static void hist_entry_init_inline_node(struct hist_entry *he)
+{
+        if (he->inline_node)
+                return;
+
+        he->inline_node = inline_node__create(he->ms.map, he->ip);
+
+        if (he->inline_node == NULL)
+                return;
+
+        he->has_children = true;
+}
+
 static bool hist_browser__toggle_fold(struct hist_browser *browser)
 {
         struct hist_entry *he = browser->he_selection;
@@ -393,7 +469,12 @@ static bool hist_browser__toggle_fold(struct hist_browser *browser)
 
                 if (he->unfolded) {
                         if (he->leaf)
-                                he->nr_rows = callchain__count_rows(&he->sorted_chain);
+                                if (he->inline_node)
+                                        he->nr_rows = inline__count_rows(
+                                                        he->inline_node);
+                                else
+                                        he->nr_rows = callchain__count_rows(
+                                                        &he->sorted_chain);
                         else
                                 he->nr_rows = hierarchy_count_rows(browser, he, false);
 
@@ -753,6 +834,71 @@ static bool hist_browser__check_dump_full(struct hist_browser *browser __maybe_u
 
 #define LEVEL_OFFSET_STEP 3
 
+static int hist_browser__show_inline(struct hist_browser *browser,
+                                     struct inline_node *node,
+                                     unsigned short row,
+                                     int offset)
+{
+        struct inline_list *ilist;
+        char buf[1024];
+        int color, width, first_row;
+
+        first_row = row;
+        width = browser->b.width - (LEVEL_OFFSET_STEP + 2);
+        list_for_each_entry(ilist, &node->val, list) {
+                if ((ilist->filename != NULL) || (ilist->funcname != NULL)) {
+                        color = HE_COLORSET_NORMAL;
+                        if (ui_browser__is_current_entry(&browser->b, row))
+                                color = HE_COLORSET_SELECTED;
+
+                        if (callchain_param.key == CCKEY_ADDRESS ||
+                            callchain_param.key == CCKEY_SRCLINE) {
+                                if (ilist->filename != NULL)
+                                        scnprintf(buf, sizeof(buf),
+                                                  "%s:%d (inline)",
+                                                  ilist->filename,
+                                                  ilist->line_nr);
+                                else
+                                        scnprintf(buf, sizeof(buf), "??");
+                        } else if (ilist->funcname != NULL)
+                                scnprintf(buf, sizeof(buf), "%s (inline)",
+                                          ilist->funcname);
+                        else if (ilist->filename != NULL)
+                                scnprintf(buf, sizeof(buf),
+                                          "%s:%d (inline)",
+                                          ilist->filename,
+                                          ilist->line_nr);
+                        else
+                                scnprintf(buf, sizeof(buf), "??");
+
+                        ui_browser__set_color(&browser->b, color);
+                        hist_browser__gotorc(browser, row, 0);
+                        ui_browser__write_nstring(&browser->b, " ",
+                                LEVEL_OFFSET_STEP + offset);
+                        ui_browser__write_nstring(&browser->b, buf, width);
+                        row++;
+                }
+        }
+
+        return row - first_row;
+}
+
+static size_t show_inline_list(struct hist_browser *browser, struct map *map,
+                               u64 ip, int row, int offset)
+{
+        struct inline_node *node;
+        int ret;
+
+        node = inline_node__create(map, ip);
+        if (node == NULL)
+                return 0;
+
+        ret = hist_browser__show_inline(browser, node, row, offset);
+
+        inline_node__delete(node);
+        return ret;
+}
+
 static int hist_browser__show_callchain_list(struct hist_browser *browser,
                                              struct callchain_node *node,
                                              struct callchain_list *chain,
@@ -764,6 +910,7 @@ static int hist_browser__show_callchain_list(struct hist_browser *browser,
         char bf[1024], *alloc_str;
         char buf[64], *alloc_str2;
         const char *str;
+        int inline_rows = 0, ret = 1;
 
         if (arg->row_offset != 0) {
                 arg->row_offset--;
@@ -801,10 +948,15 @@ static int hist_browser__show_callchain_list(struct hist_browser *browser,
         }
 
         print(browser, chain, str, offset, row, arg);
-
         free(alloc_str);
         free(alloc_str2);
-        return 1;
+
+        if (symbol_conf.inline_name) {
+                inline_rows = show_inline_list(browser, chain->ms.map,
+                                               chain->ip, row + 1, offset);
+        }
+
+        return ret + inline_rows;
 }
 
 static bool check_percent_display(struct rb_node *node, u64 parent_total)
@@ -1228,6 +1380,12 @@ static int hist_browser__show_entry(struct hist_browser *browser,
                 folded_sign = hist_entry__folded(entry);
         }
 
+        if (symbol_conf.inline_name &&
+            (!entry->has_children)) {
+                hist_entry_init_inline_node(entry);
+                folded_sign = hist_entry__folded(entry);
+        }
+
         if (row_offset == 0) {
                 struct hpp_arg arg = {
                         .b              = &browser->b,
@@ -1259,7 +1417,8 @@ static int hist_browser__show_entry(struct hist_browser *browser,
                         }
 
                         if (first) {
-                                if (symbol_conf.use_callchain) {
+                                if (symbol_conf.use_callchain ||
+                                        symbol_conf.inline_name) {
                                         ui_browser__printf(&browser->b, "%c ", folded_sign);
                                         width -= 2;
                                 }
@@ -1301,8 +1460,14 @@ static int hist_browser__show_entry(struct hist_browser *browser,
                         .is_current_entry = current_entry,
                 };
 
-                printed += hist_browser__show_callchain(browser, entry, 1, row,
-                                        hist_browser__show_callchain_entry, &arg,
+                if (entry->inline_node)
+                        printed += hist_browser__show_inline(browser,
+                                        entry->inline_node, row, 0);
+                else
+                        printed += hist_browser__show_callchain(browser,
+                                        entry, 1, row,
+                                        hist_browser__show_callchain_entry,
+                                        &arg,
                                         hist_browser__check_output_full);
         }
 
diff --git a/tools/perf/ui/stdio/hist.c b/tools/perf/ui/stdio/hist.c
index 668f4aecf2e6..d52d5f64ea89 100644
--- a/tools/perf/ui/stdio/hist.c
+++ b/tools/perf/ui/stdio/hist.c
@@ -17,6 +17,67 @@ static size_t callchain__fprintf_left_margin(FILE *fp, int left_margin)
         return ret;
 }
 
+static size_t inline__fprintf(struct map *map, u64 ip, int left_margin,
+                              int depth, int depth_mask, FILE *fp)
+{
+        struct dso *dso;
+        struct inline_node *node;
+        struct inline_list *ilist;
+        int ret = 0, i;
+
+        if (map == NULL)
+                return 0;
+
+        dso = map->dso;
+        if (dso == NULL)
+                return 0;
+
+        if (dso->kernel != DSO_TYPE_USER)
+                return 0;
+
+        node = dso__parse_addr_inlines(dso,
+                                       map__rip_2objdump(map, ip));
+        if (node == NULL)
+                return 0;
+
+        list_for_each_entry(ilist, &node->val, list) {
+                if ((ilist->filename != NULL) || (ilist->funcname != NULL)) {
+                        ret += callchain__fprintf_left_margin(fp, left_margin);
+
+                        for (i = 0; i < depth; i++) {
+                                if (depth_mask & (1 << i))
+                                        ret += fprintf(fp, "|");
+                                else
+                                        ret += fprintf(fp, " ");
+                                ret += fprintf(fp, "          ");
+                        }
+
+                        if (callchain_param.key == CCKEY_ADDRESS ||
+                            callchain_param.key == CCKEY_SRCLINE) {
+                                if (ilist->filename != NULL)
+                                        ret += fprintf(fp, "%s:%d (inline)",
+                                                       ilist->filename,
+                                                       ilist->line_nr);
+                                else
+                                        ret += fprintf(fp, "??");
+                        } else if (ilist->funcname != NULL)
+                                ret += fprintf(fp, "%s (inline)",
+                                               ilist->funcname);
+                        else if (ilist->filename != NULL)
+                                ret += fprintf(fp, "%s:%d (inline)",
+                                               ilist->filename,
+                                               ilist->line_nr);
+                        else
+                                ret += fprintf(fp, "??");
+
+                        ret += fprintf(fp, "\n");
+                }
+        }
+
+        inline_node__delete(node);
+        return ret;
+}
+
 static size_t ipchain__fprintf_graph_line(FILE *fp, int depth, int depth_mask,
                                           int left_margin)
 {
@@ -78,6 +139,10 @@ static size_t ipchain__fprintf_graph(FILE *fp, struct callchain_node *node,
         fputs(str, fp);
         fputc('\n', fp);
         free(alloc_str);
+
+        if (symbol_conf.inline_name)
+                ret += inline__fprintf(chain->ms.map, chain->ip,
+                                       left_margin, depth, depth_mask, fp);
         return ret;
 }
 
@@ -229,6 +294,7 @@ static size_t callchain__fprintf_graph(FILE *fp, struct rb_root *root,
                         if (!i++ && field_order == NULL &&
                             sort_order && !prefixcmp(sort_order, "sym"))
                                 continue;
+
                         if (!printed) {
                                 ret += callchain__fprintf_left_margin(fp, left_margin);
                                 ret += fprintf(fp, "|\n");
@@ -251,6 +317,13 @@ static size_t callchain__fprintf_graph(FILE *fp, struct rb_root *root,
 
                         if (++entries_printed == callchain_param.print_limit)
                                 break;
+
+                        if (symbol_conf.inline_name)
+                                ret += inline__fprintf(chain->ms.map,
+                                                       chain->ip,
+                                                       left_margin,
+                                                       0, 0,
+                                                       fp);
                 }
                 root = &cnode->rb_root;
         }
@@ -529,6 +602,8 @@ static int hist_entry__fprintf(struct hist_entry *he, size_t size,
                                bool use_callchain)
 {
         int ret;
+        int callchain_ret = 0;
+        int inline_ret = 0;
         struct perf_hpp hpp = {
                 .buf            = bf,
                 .size           = size,
@@ -547,7 +622,16 @@ static int hist_entry__fprintf(struct hist_entry *he, size_t size,
         ret = fprintf(fp, "%s\n", bf);
 
         if (use_callchain)
-                ret += hist_entry_callchain__fprintf(he, total_period, 0, fp);
+                callchain_ret = hist_entry_callchain__fprintf(he, total_period,
+                                                              0, fp);
+
+        if (callchain_ret == 0 && symbol_conf.inline_name) {
+                inline_ret = inline__fprintf(he->ms.map, he->ip, 0, 0, 0, fp);
+                ret += inline_ret;
+                if (inline_ret > 0)
+                        ret += fprintf(fp, "\n");
+        } else
+                ret += callchain_ret;
 
         return ret;
 }
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 22cd1dbe724b..11af5f0d56cc 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -1307,6 +1307,7 @@ static int dso__disassemble_filename(struct dso *dso, char *filename, size_t fil
 {
         char linkname[PATH_MAX];
         char *build_id_filename;
+        char *build_id_path = NULL;
 
         if (dso->symtab_type == DSO_BINARY_TYPE__KALLSYMS &&
             !dso__is_kcore(dso))
@@ -1322,8 +1323,14 @@ static int dso__disassemble_filename(struct dso *dso, char *filename, size_t fil
                 goto fallback;
         }
 
+        build_id_path = strdup(filename);
+        if (!build_id_path)
+                return -1;
+
+        dirname(build_id_path);
+
         if (dso__is_kcore(dso) ||
-            readlink(filename, linkname, sizeof(linkname)) < 0 ||
+            readlink(build_id_path, linkname, sizeof(linkname)) < 0 ||
             strstr(linkname, DSO__NAME_KALLSYMS) ||
             access(filename, R_OK)) {
 fallback:
@@ -1335,6 +1342,7 @@ fallback:
                 __symbol__join_symfs(filename, filename_size, dso->long_name);
         }
 
+        free(build_id_path);
         return 0;
 }
 
@@ -1663,18 +1671,23 @@ static int symbol__get_source_line(struct symbol *sym, struct map *map,
                 src_line->nr_pcnt = nr_pcnt;
 
                 for (k = 0; k < nr_pcnt; k++) {
+                        double percent = 0.0;
+
                         h = annotation__histogram(notes, evidx + k);
-                        src_line->samples[k].percent = 100.0 * h->addr[i] / h->sum;
+                        if (h->sum)
+                                percent = 100.0 * h->addr[i] / h->sum;
 
-                        if (src_line->samples[k].percent > percent_max)
-                                percent_max = src_line->samples[k].percent;
+                        if (percent > percent_max)
+                                percent_max = percent;
+                        src_line->samples[k].percent = percent;
                 }
 
                 if (percent_max <= 0.5)
                         goto next;
 
                 offset = start + i;
-                src_line->path = get_srcline(map->dso, offset, NULL, false);
+                src_line->path = get_srcline(map->dso, offset, NULL,
+                                             false, true);
                 insert_source_line(&tmp_root, src_line);
 
         next:
diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c
index c5a6e0b12452..78bd632f144d 100644
--- a/tools/perf/util/auxtrace.c
+++ b/tools/perf/util/auxtrace.c
@@ -1826,7 +1826,7 @@ static int addr_filter__resolve_kernel_syms(struct addr_filter *filt)
                 filt->addr = start;
                 if (filt->range && !filt->size && !filt->sym_to) {
                         filt->size = size;
-                        no_size = !!size;
+                        no_size = !size;
                 }
         }
 
@@ -1840,7 +1840,7 @@ static int addr_filter__resolve_kernel_syms(struct addr_filter *filt)
                 if (err)
                         return err;
                 filt->size = start + size - filt->addr;
-                no_size = !!size;
+                no_size = !size;
         }
 
         /* The very last symbol in kallsyms does not imply a particular size */
diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c
index e528c40739cc..33af67530d30 100644
--- a/tools/perf/util/build-id.c
+++ b/tools/perf/util/build-id.c
@@ -182,13 +182,17 @@ char *build_id_cache__origname(const char *sbuild_id)
         char buf[PATH_MAX];
         char *ret = NULL, *p;
         size_t offs = 5;        /* == strlen("../..") */
+        ssize_t len;
 
         linkname = build_id_cache__linkname(sbuild_id, NULL, 0);
         if (!linkname)
                 return NULL;
 
-        if (readlink(linkname, buf, PATH_MAX) < 0)
+        len = readlink(linkname, buf, sizeof(buf) - 1);
+        if (len <= 0)
                 goto out;
+        buf[len] = '\0';
+
         /* The link should be "../..<origpath>/<sbuild_id>" */
         p = strrchr(buf, '/');  /* Cut off the "/<sbuild_id>" */
         if (p && (p > buf + offs)) {
@@ -690,7 +694,7 @@ int build_id_cache__add_s(const char *sbuild_id, const char *name,
                 err = 0;
 
         /* Update SDT cache : error is just warned */
-        if (build_id_cache__add_sdt_cache(sbuild_id, realname) < 0)
+        if (realname && build_id_cache__add_sdt_cache(sbuild_id, realname) < 0)
                 pr_debug4("Failed to update/scan SDT cache for %s\n", realname);
 
 out_free:
diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c
index aba953421a03..d78776a20e80 100644
--- a/tools/perf/util/callchain.c
+++ b/tools/perf/util/callchain.c
@@ -80,6 +80,10 @@ static int parse_callchain_sort_key(const char *value)
                 callchain_param.key = CCKEY_ADDRESS;
                 return 0;
         }
+        if (!strncmp(value, "srcline", strlen(value))) {
+                callchain_param.key = CCKEY_SRCLINE;
+                return 0;
+        }
         if (!strncmp(value, "branch", strlen(value))) {
                 callchain_param.branch_callstack = 1;
                 return 0;
@@ -510,14 +514,51 @@ enum match_result {
         MATCH_GT,
 };
 
+static enum match_result match_chain_srcline(struct callchain_cursor_node *node,
+                                             struct callchain_list *cnode)
+{
+        char *left = get_srcline(cnode->ms.map->dso,
+                                 map__rip_2objdump(cnode->ms.map, cnode->ip),
+                                 cnode->ms.sym, true, false);
+        char *right = get_srcline(node->map->dso,
+                                  map__rip_2objdump(node->map, node->ip),
+                                  node->sym, true, false);
+        enum match_result ret = MATCH_EQ;
+        int cmp;
+
+        if (left && right)
+                cmp = strcmp(left, right);
+        else if (!left && right)
+                cmp = 1;
+        else if (left && !right)
+                cmp = -1;
+        else if (cnode->ip == node->ip)
+                cmp = 0;
+        else
+                cmp = (cnode->ip < node->ip) ? -1 : 1;
+
+        if (cmp != 0)
+                ret = cmp < 0 ? MATCH_LT : MATCH_GT;
+
+        free_srcline(left);
+        free_srcline(right);
+        return ret;
+}
+
 static enum match_result match_chain(struct callchain_cursor_node *node,
                                      struct callchain_list *cnode)
 {
         struct symbol *sym = node->sym;
         u64 left, right;
 
-        if (cnode->ms.sym && sym &&
-            callchain_param.key == CCKEY_FUNCTION) {
+        if (callchain_param.key == CCKEY_SRCLINE) {
+                enum match_result match = match_chain_srcline(node, cnode);
+
+                if (match != MATCH_ERROR)
+                        return match;
+        }
+
+        if (cnode->ms.sym && sym && callchain_param.key == CCKEY_FUNCTION) {
                 left = cnode->ms.sym->start;
                 right = sym->start;
         } else {
@@ -911,15 +952,16 @@ out:
 char *callchain_list__sym_name(struct callchain_list *cl,
                                char *bf, size_t bfsize, bool show_dso)
 {
+        bool show_addr = callchain_param.key == CCKEY_ADDRESS;
+        bool show_srcline = show_addr || callchain_param.key == CCKEY_SRCLINE;
         int printed;
 
         if (cl->ms.sym) {
-                if (callchain_param.key == CCKEY_ADDRESS &&
-                    cl->ms.map && !cl->srcline)
+                if (show_srcline && cl->ms.map && !cl->srcline)
                         cl->srcline = get_srcline(cl->ms.map->dso,
                                                   map__rip_2objdump(cl->ms.map,
                                                                     cl->ip),
-                                                  cl->ms.sym, false);
+                                                  cl->ms.sym, false, show_addr);
                 if (cl->srcline)
                         printed = scnprintf(bf, bfsize, "%s %s",
                                         cl->ms.sym->name, cl->srcline);
diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h
index 4f4b60f1558a..c56c23dbbf72 100644
--- a/tools/perf/util/callchain.h
+++ b/tools/perf/util/callchain.h
@@ -77,7 +77,8 @@ typedef void (*sort_chain_func_t)(struct rb_root *, struct callchain_root *,
 
 enum chain_key {
         CCKEY_FUNCTION,
-        CCKEY_ADDRESS
+        CCKEY_ADDRESS,
+        CCKEY_SRCLINE
 };
 
 enum chain_value {
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 05714d548584..ef09f26e67da 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -370,15 +370,11 @@ static int write_cmdline(int fd, struct perf_header *h __maybe_unused,
                          struct perf_evlist *evlist __maybe_unused)
 {
         char buf[MAXPATHLEN];
-        char proc[32];
         u32 n;
         int i, ret;
 
-        /*
-         * actual atual path to perf binary
-         */
-        sprintf(proc, "/proc/%d/exe", getpid());
-        ret = readlink(proc, buf, sizeof(buf));
+        /* actual path to perf binary */
+        ret = readlink("/proc/self/exe", buf, sizeof(buf) - 1);
         if (ret <= 0)
                 return -1;
 
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index e3b38f629504..3c4d4d00cb2c 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -1136,6 +1136,11 @@ void hist_entry__delete(struct hist_entry *he)
                 zfree(&he->mem_info);
         }
 
+        if (he->inline_node) {
+                inline_node__delete(he->inline_node);
+                he->inline_node = NULL;
+        }
+
         zfree(&he->stat_acc);
         free_srcline(he->srcline);
         if (he->srcfile && he->srcfile[0])
diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c
index 1d9ebcf9e38e..c1870ac365a3 100644
--- a/tools/perf/util/map.c
+++ b/tools/perf/util/map.c
@@ -405,7 +405,8 @@ int map__fprintf_srcline(struct map *map, u64 addr, const char *prefix,
 
         if (map && map->dso) {
                 srcline = get_srcline(map->dso,
-                                      map__rip_2objdump(map, addr), NULL, true);
+                                      map__rip_2objdump(map, addr), NULL,
+                                      true, true);
                 if (srcline != SRCLINE_UNKNOWN)
                         ret = fprintf(fp, "%s%s", prefix, srcline);
                 free_srcline(srcline);
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index 8b0d4e39f640..73f3ec1cf2a0 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -323,7 +323,7 @@ char *hist_entry__get_srcline(struct hist_entry *he)
                 return SRCLINE_UNKNOWN;
 
         return get_srcline(map->dso, map__rip_2objdump(map, he->ip),
-                           he->ms.sym, true);
+                           he->ms.sym, true, true);
 }
 
 static int64_t
@@ -366,7 +366,8 @@ sort__srcline_from_cmp(struct hist_entry *left, struct hist_entry *right)
                         left->branch_info->srcline_from = get_srcline(map->dso,
                                            map__rip_2objdump(map,
                                                              left->branch_info->from.al_addr),
-                                                         left->branch_info->from.sym, true);
+                                                         left->branch_info->from.sym,
+                                                         true, true);
         }
         if (!right->branch_info->srcline_from) {
                 struct map *map = right->branch_info->from.map;
@@ -376,7 +377,8 @@ sort__srcline_from_cmp(struct hist_entry *left, struct hist_entry *right)
                         right->branch_info->srcline_from = get_srcline(map->dso,
                                              map__rip_2objdump(map,
                                                                right->branch_info->from.al_addr),
-                                                     right->branch_info->from.sym, true);
+                                                     right->branch_info->from.sym,
+                                                     true, true);
         }
         return strcmp(right->branch_info->srcline_from, left->branch_info->srcline_from);
 }
@@ -407,7 +409,8 @@ sort__srcline_to_cmp(struct hist_entry *left, struct hist_entry *right)
                         left->branch_info->srcline_to = get_srcline(map->dso,
                                            map__rip_2objdump(map,
                                                              left->branch_info->to.al_addr),
-                                                         left->branch_info->from.sym, true);
+                                                         left->branch_info->from.sym,
+                                                         true, true);
         }
         if (!right->branch_info->srcline_to) {
                 struct map *map = right->branch_info->to.map;
@@ -417,7 +420,8 @@ sort__srcline_to_cmp(struct hist_entry *left, struct hist_entry *right)
                         right->branch_info->srcline_to = get_srcline(map->dso,
                                              map__rip_2objdump(map,
                                                                right->branch_info->to.al_addr),
-                                                     right->branch_info->to.sym, true);
+                                                     right->branch_info->to.sym,
+                                                     true, true);
         }
         return strcmp(right->branch_info->srcline_to, left->branch_info->srcline_to);
 }
@@ -448,7 +452,7 @@ static char *hist_entry__get_srcfile(struct hist_entry *e)
                 return no_srcfile;
 
         sf = __get_srcline(map->dso, map__rip_2objdump(map, e->ip),
-                         e->ms.sym, false, true);
+                         e->ms.sym, false, true, true);
         if (!strcmp(sf, SRCLINE_UNKNOWN))
                 return no_srcfile;
         p = strchr(sf, ':');
diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h
index baf20a399f34..e35fb186d048 100644
--- a/tools/perf/util/sort.h
+++ b/tools/perf/util/sort.h
@@ -128,6 +128,7 @@ struct hist_entry {
         };
         char                    *srcline;
         char                    *srcfile;
+        struct inline_node      *inline_node;
         struct symbol           *parent;
         struct branch_info      *branch_info;
         struct hists            *hists;
diff --git a/tools/perf/util/srcline.c b/tools/perf/util/srcline.c
index b4db3f48e3b0..778ccb5d99d1 100644
--- a/tools/perf/util/srcline.c
+++ b/tools/perf/util/srcline.c
@@ -7,11 +7,58 @@
 #include "util/dso.h"
 #include "util/util.h"
 #include "util/debug.h"
+#include "util/callchain.h"
 
 #include "symbol.h"
 
 bool srcline_full_filename;
 
+static const char *dso__name(struct dso *dso)
+{
+        const char *dso_name;
+
+        if (dso->symsrc_filename)
+                dso_name = dso->symsrc_filename;
+        else
+                dso_name = dso->long_name;
+
+        if (dso_name[0] == '[')
+                return NULL;
+
+        if (!strncmp(dso_name, "/tmp/perf-", 10))
+                return NULL;
+
+        return dso_name;
+}
+
+static int inline_list__append(char *filename, char *funcname, int line_nr,
+                               struct inline_node *node, struct dso *dso)
+{
+        struct inline_list *ilist;
+        char *demangled;
+
+        ilist = zalloc(sizeof(*ilist));
+        if (ilist == NULL)
+                return -1;
+
+        ilist->filename = filename;
+        ilist->line_nr = line_nr;
+
+        if (dso != NULL) {
+                demangled = dso__demangle_sym(dso, 0, funcname);
+                if (demangled == NULL) {
+                        ilist->funcname = funcname;
+                } else {
+                        ilist->funcname = demangled;
+                        free(funcname);
+                }
+        }
+
+        list_add_tail(&ilist->list, &node->val);
+
+        return 0;
+}
+
 #ifdef HAVE_LIBBFD_SUPPORT
 
 /*
@@ -151,9 +198,17 @@ static void addr2line_cleanup(struct a2l_data *a2l)
 
 #define MAX_INLINE_NEST 1024
 
+static void inline_list__reverse(struct inline_node *node)
+{
+        struct inline_list *ilist, *n;
+
+        list_for_each_entry_safe_reverse(ilist, n, &node->val, list)
+                list_move_tail(&ilist->list, &node->val);
+}
+
 static int addr2line(const char *dso_name, u64 addr,
                      char **file, unsigned int *line, struct dso *dso,
-                     bool unwind_inlines)
+                     bool unwind_inlines, struct inline_node *node)
 {
         int ret = 0;
         struct a2l_data *a2l = dso->a2l;
@@ -178,8 +233,21 @@ static int addr2line(const char *dso_name, u64 addr,
 
                 while (bfd_find_inliner_info(a2l->abfd, &a2l->filename,
                                              &a2l->funcname, &a2l->line) &&
-                       cnt++ < MAX_INLINE_NEST)
-                        ;
+                       cnt++ < MAX_INLINE_NEST) {
+
+                        if (node != NULL) {
+                                if (inline_list__append(strdup(a2l->filename),
+                                                        strdup(a2l->funcname),
+                                                        a2l->line, node,
+                                                        dso) != 0)
+                                        return 0;
+                        }
+                }
+
+                if ((node != NULL) &&
+                    (callchain_param.order != ORDER_CALLEE)) {
+                        inline_list__reverse(node);
+                }
         }
 
         if (a2l->found && a2l->filename) {
@@ -205,18 +273,68 @@ void dso__free_a2l(struct dso *dso)
         dso->a2l = NULL;
 }
 
+static struct inline_node *addr2inlines(const char *dso_name, u64 addr,
+        struct dso *dso)
+{
+        char *file = NULL;
+        unsigned int line = 0;
+        struct inline_node *node;
+
+        node = zalloc(sizeof(*node));
+        if (node == NULL) {
+                perror("not enough memory for the inline node");
+                return NULL;
+        }
+
+        INIT_LIST_HEAD(&node->val);
+        node->addr = addr;
+
+        if (!addr2line(dso_name, addr, &file, &line, dso, TRUE, node))
+                goto out_free_inline_node;
+
+        if (list_empty(&node->val))
+                goto out_free_inline_node;
+
+        return node;
+
+out_free_inline_node:
+        inline_node__delete(node);
+        return NULL;
+}
+
 #else /* HAVE_LIBBFD_SUPPORT */
 
+static int filename_split(char *filename, unsigned int *line_nr)
+{
+        char *sep;
+
+        sep = strchr(filename, '\n');
+        if (sep)
+                *sep = '\0';
+
+        if (!strcmp(filename, "??:0"))
+                return 0;
+
+        sep = strchr(filename, ':');
+        if (sep) {
+                *sep++ = '\0';
+                *line_nr = strtoul(sep, NULL, 0);
+                return 1;
+        }
+
+        return 0;
+}
+
 static int addr2line(const char *dso_name, u64 addr,
                      char **file, unsigned int *line_nr,
                      struct dso *dso __maybe_unused,
-                     bool unwind_inlines __maybe_unused)
+                     bool unwind_inlines __maybe_unused,
+                     struct inline_node *node __maybe_unused)
 {
         FILE *fp;
         char cmd[PATH_MAX];
         char *filename = NULL;
         size_t len;
-        char *sep;
         int ret = 0;
 
         scnprintf(cmd, sizeof(cmd), "addr2line -e %s %016"PRIx64,
@@ -233,23 +351,14 @@ static int addr2line(const char *dso_name, u64 addr,
                 goto out;
         }
 
-        sep = strchr(filename, '\n');
-        if (sep)
-                *sep = '\0';
-
-        if (!strcmp(filename, "??:0")) {
-                pr_debug("no debugging info in %s\n", dso_name);
+        ret = filename_split(filename, line_nr);
+        if (ret != 1) {
                 free(filename);
                 goto out;
         }
 
-        sep = strchr(filename, ':');
-        if (sep) {
-                *sep++ = '\0';
-                *file = filename;
-                *line_nr = strtoul(sep, NULL, 0);
-                ret = 1;
-        }
+        *file = filename;
+
 out:
         pclose(fp);
         return ret;
@@ -259,6 +368,58 @@ void dso__free_a2l(struct dso *dso __maybe_unused)
 {
 }
 
+static struct inline_node *addr2inlines(const char *dso_name, u64 addr,
+        struct dso *dso __maybe_unused)
+{
+        FILE *fp;
+        char cmd[PATH_MAX];
+        struct inline_node *node;
+        char *filename = NULL;
+        size_t len;
+        unsigned int line_nr = 0;
+
+        scnprintf(cmd, sizeof(cmd), "addr2line -e %s -i %016"PRIx64,
+                  dso_name, addr);
+
+        fp = popen(cmd, "r");
+        if (fp == NULL) {
+                pr_err("popen failed for %s\n", dso_name);
+                return NULL;
+        }
+
+        node = zalloc(sizeof(*node));
+        if (node == NULL) {
+                perror("not enough memory for the inline node");
+                goto out;
+        }
+
+        INIT_LIST_HEAD(&node->val);
+        node->addr = addr;
+
+        while (getline(&filename, &len, fp) != -1) {
+                if (filename_split(filename, &line_nr) != 1) {
+                        free(filename);
+                        goto out;
+                }
+
+                if (inline_list__append(filename, NULL, line_nr, node,
+                                        NULL) != 0)
+                        goto out;
+
+                filename = NULL;
+        }
+
+out:
+        pclose(fp);
+
+        if (list_empty(&node->val)) {
+                inline_node__delete(node);
+                return NULL;
+        }
+
+        return node;
+}
+
 #endif /* HAVE_LIBBFD_SUPPORT */
 
 /*
@@ -268,7 +429,7 @@ void dso__free_a2l(struct dso *dso __maybe_unused)
 #define A2L_FAIL_LIMIT 123
 
 char *__get_srcline(struct dso *dso, u64 addr, struct symbol *sym,
-                  bool show_sym, bool unwind_inlines)
+                  bool show_sym, bool show_addr, bool unwind_inlines)
 {
         char *file = NULL;
         unsigned line = 0;
@@ -278,18 +439,11 @@ char *__get_srcline(struct dso *dso, u64 addr, struct symbol *sym,
         if (!dso->has_srcline)
                 goto out;
 
-        if (dso->symsrc_filename)
-                dso_name = dso->symsrc_filename;
-        else
-                dso_name = dso->long_name;
-
-        if (dso_name[0] == '[')
-                goto out;
-
-        if (!strncmp(dso_name, "/tmp/perf-", 10))
+        dso_name = dso__name(dso);
+        if (dso_name == NULL)
                 goto out;
 
-        if (!addr2line(dso_name, addr, &file, &line, dso, unwind_inlines))
+        if (!addr2line(dso_name, addr, &file, &line, dso, unwind_inlines, NULL))
                 goto out;
 
         if (asprintf(&srcline, "%s:%u",
@@ -309,6 +463,11 @@ out:
                 dso->has_srcline = 0;
                 dso__free_a2l(dso);
         }
+
+        if (!show_addr)
+                return (show_sym && sym) ?
+                            strndup(sym->name, sym->namelen) : NULL;
+
         if (sym) {
                 if (asprintf(&srcline, "%s+%" PRIu64, show_sym ? sym->name : "",
                                         addr - sym->start) < 0)
@@ -325,7 +484,32 @@ void free_srcline(char *srcline)
 }
 
 char *get_srcline(struct dso *dso, u64 addr, struct symbol *sym,
-                  bool show_sym)
+                  bool show_sym, bool show_addr)
+{
+        return __get_srcline(dso, addr, sym, show_sym, show_addr, false);
+}
+
+struct inline_node *dso__parse_addr_inlines(struct dso *dso, u64 addr)
 {
-        return __get_srcline(dso, addr, sym, show_sym, false);
+        const char *dso_name;
+
+        dso_name = dso__name(dso);
+        if (dso_name == NULL)
+                return NULL;
+
+        return addr2inlines(dso_name, addr, dso);
+}
+
+void inline_node__delete(struct inline_node *node)
+{
+        struct inline_list *ilist, *tmp;
+
+        list_for_each_entry_safe(ilist, tmp, &node->val, list) {
+                list_del_init(&ilist->list);
+                zfree(&ilist->filename);
+                zfree(&ilist->funcname);
+                free(ilist);
+        }
+
+        free(node);
 }
diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c
index 0e660dba58ad..d1a40bb642ff 100644
--- a/tools/perf/util/symbol-elf.c
+++ b/tools/perf/util/symbol-elf.c
@@ -390,6 +390,11 @@ out_elf_end:
         return 0;
 }
 
+char *dso__demangle_sym(struct dso *dso, int kmodule, char *elf_name)
+{
+        return demangle_sym(dso, kmodule, elf_name);
+}
+
 /*
  * Align offset to 4 bytes as needed for note name and descriptor data.
  */
diff --git a/tools/perf/util/symbol-minimal.c b/tools/perf/util/symbol-minimal.c
index 11cdde980545..870ef0f0659c 100644
--- a/tools/perf/util/symbol-minimal.c
+++ b/tools/perf/util/symbol-minimal.c
@@ -373,3 +373,10 @@ int kcore_copy(const char *from_dir __maybe_unused,
 void symbol__elf_init(void)
 {
 }
+
+char *dso__demangle_sym(struct dso *dso __maybe_unused,
+                        int kmodule __maybe_unused,
+                        char *elf_name __maybe_unused)
+{
+        return NULL;
+}
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index 9222c7e702f3..5245d2fb1a0a 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -118,7 +118,8 @@ struct symbol_conf {
                         show_ref_callgraph,
                         hide_unresolved,
                         raw_trace,
-                        report_hierarchy;
+                        report_hierarchy,
+                        inline_name;
         const char      *vmlinux_name,
                         *kallsyms_name,
                         *source_prefix,
@@ -305,6 +306,8 @@ int dso__load_sym(struct dso *dso, struct map *map, struct symsrc *syms_ss,
 int dso__synthesize_plt_symbols(struct dso *dso, struct symsrc *ss,
                                 struct map *map);
 
+char *dso__demangle_sym(struct dso *dso, int kmodule, char *elf_name);
+
 void __symbols__insert(struct rb_root *symbols, struct symbol *sym, bool kernel);
 void symbols__insert(struct rb_root *symbols, struct symbol *sym);
 void symbols__fixup_duplicate(struct rb_root *symbols);
diff --git a/tools/perf/util/trace-event-read.c b/tools/perf/util/trace-event-read.c
index 27420159bf69..8a9a677f7576 100644
--- a/tools/perf/util/trace-event-read.c
+++ b/tools/perf/util/trace-event-read.c
@@ -192,7 +192,7 @@ static int read_ftrace_printk(struct pevent *pevent)
         if (!size)
                 return 0;
 
-        buf = malloc(size);
+        buf = malloc(size + 1);
         if (buf == NULL)
                 return -1;
 
@@ -201,6 +201,8 @@ static int read_ftrace_printk(struct pevent *pevent)
                 return -1;
         }
 
+        buf[size] = '\0';
+
         parse_ftrace_printk(pevent, buf, size);
 
         free(buf);
diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h
index b2cfa47990dc..7cf5752b38fd 100644
--- a/tools/perf/util/util.h
+++ b/tools/perf/util/util.h
@@ -287,9 +287,9 @@ struct symbol;
 
 extern bool srcline_full_filename;
 char *get_srcline(struct dso *dso, u64 addr, struct symbol *sym,
-                  bool show_sym);
+                  bool show_sym, bool show_addr);
 char *__get_srcline(struct dso *dso, u64 addr, struct symbol *sym,
-                  bool show_sym, bool unwind_inlines);
+                  bool show_sym, bool show_addr, bool unwind_inlines);
 void free_srcline(char *srcline);
 
 int perf_event_paranoid(void);
@@ -364,4 +364,20 @@ int is_printable_array(char *p, unsigned int len);
 int timestamp__scnprintf_usec(u64 timestamp, char *buf, size_t sz);
 
 int unit_number__scnprintf(char *buf, size_t size, u64 n);
+
+struct inline_list {
+        char                    *filename;
+        char                    *funcname;
+        unsigned int            line_nr;
+        struct list_head        list;
+};
+
+struct inline_node {
+        u64                     addr;
+        struct list_head        val;
+};
+
+struct inline_node *dso__parse_addr_inlines(struct dso *dso, u64 addr);
+void inline_node__delete(struct inline_node *node);
+
 #endif /* GIT_COMPAT_UTIL_H */