29 files changed, 470 insertions, 115 deletions

diff --git a/tools/perf/Documentation/perf-inject.txt b/tools/perf/Documentation/perf-inject.txt
index a00a34276c54..dc7442cf3d7f 100644
--- a/tools/perf/Documentation/perf-inject.txt
+++ b/tools/perf/Documentation/perf-inject.txt
@@ -41,6 +41,9 @@ OPTIONS
         tasks slept. sched_switch contains a callchain where a task slept and
         sched_stat contains a timeslice how long a task slept.
 
+--kallsyms=<file>::
+        kallsyms pathname
+
 SEE ALSO
 --------
 linkperf:perf-record[1], linkperf:perf-report[1], linkperf:perf-archive[1]
diff --git a/tools/perf/arch/powerpc/util/header.c b/tools/perf/arch/powerpc/util/header.c
index 2f7073d107fd..6c1b8a75db09 100644
--- a/tools/perf/arch/powerpc/util/header.c
+++ b/tools/perf/arch/powerpc/util/header.c
@@ -5,9 +5,7 @@
 #include <string.h>
 
 #include "../../util/header.h"
-
-#define __stringify_1(x)        #x
-#define __stringify(x)          __stringify_1(x)
+#include "../../util/util.h"
 
 #define mfspr(rn)       ({unsigned long rval; \
                          asm volatile("mfspr %0," __stringify(rn) \
diff --git a/tools/perf/arch/x86/util/tsc.c b/tools/perf/arch/x86/util/tsc.c
index 3655f24c3170..fd2868490d00 100644
--- a/tools/perf/arch/x86/util/tsc.c
+++ b/tools/perf/arch/x86/util/tsc.c
@@ -37,3 +37,12 @@ int perf_read_tsc_conversion(const struct perf_event_mmap_page *pc,
 
         return 0;
 }
+
+u64 rdtsc(void)
+{
+        unsigned int low, high;
+
+        asm volatile("rdtsc" : "=a" (low), "=d" (high));
+
+        return low | ((u64)high) << 32;
+}
diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c
index cf6a605a13e8..9a02807387d6 100644
--- a/tools/perf/builtin-inject.c
+++ b/tools/perf/builtin-inject.c
@@ -439,6 +439,8 @@ int cmd_inject(int argc, const char **argv, const char *prefix __maybe_unused)
                             "where and how long tasks slept"),
                 OPT_INCR('v', "verbose", &verbose,
                          "be more verbose (show build ids, etc)"),
+                OPT_STRING(0, "kallsyms", &symbol_conf.kallsyms_name, "file",
+                           "kallsyms pathname"),
                 OPT_END()
         };
         const char * const inject_usage[] = {
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 378b85b731a7..4869050e7194 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -238,6 +238,7 @@ static struct perf_event_header finished_round_event = {
 
 static int record__mmap_read_all(struct record *rec)
 {
+        u64 bytes_written = rec->bytes_written;
         int i;
         int rc = 0;
 
@@ -250,7 +251,11 @@ static int record__mmap_read_all(struct record *rec)
                 }
         }
 
-        if (perf_header__has_feat(&rec->session->header, HEADER_TRACING_DATA))
+        /*
+         * Mark the round finished in case we wrote
+         * at least one event.
+         */
+        if (bytes_written != rec->bytes_written)
                 rc = record__write(rec, &finished_round_event, sizeof(finished_round_event));
 
 out:
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 9e9c91f5b7fa..f57035b89c15 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -358,27 +358,6 @@ static void print_sample_start(struct perf_sample *sample,
         }
 }
 
-static bool is_bts_event(struct perf_event_attr *attr)
-{
-        return ((attr->type == PERF_TYPE_HARDWARE) &&
-                (attr->config & PERF_COUNT_HW_BRANCH_INSTRUCTIONS) &&
-                (attr->sample_period == 1));
-}
-
-static bool sample_addr_correlates_sym(struct perf_event_attr *attr)
-{
-        if ((attr->type == PERF_TYPE_SOFTWARE) &&
-            ((attr->config == PERF_COUNT_SW_PAGE_FAULTS) ||
-             (attr->config == PERF_COUNT_SW_PAGE_FAULTS_MIN) ||
-             (attr->config == PERF_COUNT_SW_PAGE_FAULTS_MAJ)))
-                return true;
-
-        if (is_bts_event(attr))
-                return true;
-
-        return false;
-}
-
 static void print_sample_addr(union perf_event *event,
                           struct perf_sample *sample,
                           struct machine *machine,
@@ -386,24 +365,13 @@ static void print_sample_addr(union perf_event *event,
                           struct perf_event_attr *attr)
 {
         struct addr_location al;
-        u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
 
         printf("%16" PRIx64, sample->addr);
 
         if (!sample_addr_correlates_sym(attr))
                 return;
 
-        thread__find_addr_map(thread, machine, cpumode, MAP__FUNCTION,
-                              sample->addr, &al);
-        if (!al.map)
-                thread__find_addr_map(thread, machine, cpumode, MAP__VARIABLE,
-                                      sample->addr, &al);
-
-        al.cpu = sample->cpu;
-        al.sym = NULL;
-
-        if (al.map)
-                al.sym = map__find_symbol(al.map, al.addr, NULL);
+        perf_event__preprocess_sample_addr(event, sample, machine, thread, &al);
 
         if (PRINT_FIELD(SYM)) {
                 printf(" ");
@@ -427,25 +395,35 @@ static void print_sample_bts(union perf_event *event,
                              struct addr_location *al)