1 files changed, 144 insertions, 54 deletions

diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 2437fb0b463a..8cdd23239c90 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -15,6 +15,9 @@
 #include "util.h"
 #include "cpumap.h"
 #include "event-parse.h"
+#include "perf_regs.h"
+#include "unwind.h"
+#include "vdso.h"
 
 static int perf_session__open(struct perf_session *self, bool force)
 {
@@ -209,6 +212,7 @@ void perf_session__delete(struct perf_session *self)
         machine__exit(&self->host_machine);
         close(self->fd);
         free(self);
+        vdso__exit();
 }
 
 void machine__remove_thread(struct machine *self, struct thread *th)
@@ -288,10 +292,11 @@ struct branch_info *machine__resolve_bstack(struct machine *self,
         return bi;
 }
 
-int machine__resolve_callchain(struct machine *self,
-                               struct thread *thread,
-                               struct ip_callchain *chain,
-                               struct symbol **parent)
+static int machine__resolve_callchain_sample(struct machine *machine,
+                                             struct thread *thread,
+                                             struct ip_callchain *chain,
+                                             struct symbol **parent)
+
 {
         u8 cpumode = PERF_RECORD_MISC_USER;
         unsigned int i;
@@ -316,11 +321,14 @@ int machine__resolve_callchain(struct machine *self,
                 if (ip >= PERF_CONTEXT_MAX) {
                         switch (ip) {
                         case PERF_CONTEXT_HV:
-                                cpumode = PERF_RECORD_MISC_HYPERVISOR;  break;
+                                cpumode = PERF_RECORD_MISC_HYPERVISOR;
+                                break;
                         case PERF_CONTEXT_KERNEL:
-                                cpumode = PERF_RECORD_MISC_KERNEL;      break;
+                                cpumode = PERF_RECORD_MISC_KERNEL;
+                                break;
                         case PERF_CONTEXT_USER:
-                                cpumode = PERF_RECORD_MISC_USER;        break;
+                                cpumode = PERF_RECORD_MISC_USER;
+                                break;
                         default:
                                 pr_debug("invalid callchain context: "
                                          "%"PRId64"\n", (s64) ip);
@@ -335,7 +343,7 @@ int machine__resolve_callchain(struct machine *self,
                 }
 
                 al.filtered = false;
-                thread__find_addr_location(thread, self, cpumode,
+                thread__find_addr_location(thread, machine, cpumode,
                                            MAP__FUNCTION, ip, &al, NULL);
                 if (al.sym != NULL) {
                         if (sort__has_parent && !*parent &&
@@ -354,49 +362,92 @@ int machine__resolve_callchain(struct machine *self,
         return 0;
 }
 
-static int process_event_synth_tracing_data_stub(union perf_event *event __used,
-                                                 struct perf_session *session __used)
+static int unwind_entry(struct unwind_entry *entry, void *arg)
+{
+        struct callchain_cursor *cursor = arg;
+        return callchain_cursor_append(cursor, entry->ip,
+                                       entry->map, entry->sym);
+}
+
+int machine__resolve_callchain(struct machine *machine,
+                               struct perf_evsel *evsel,
+                               struct thread *thread,
+                               struct perf_sample *sample,
+                               struct symbol **parent)
+
+{
+        int ret;
+
+        callchain_cursor_reset(&callchain_cursor);
+
+        ret = machine__resolve_callchain_sample(machine, thread,
+                                                sample->callchain, parent);
+        if (ret)
+                return ret;
+
+        /* Can we do dwarf post unwind? */
+        if (!((evsel->attr.sample_type & PERF_SAMPLE_REGS_USER) &&
+              (evsel->attr.sample_type & PERF_SAMPLE_STACK_USER)))
+                return 0;
+
+        /* Bail out if nothing was captured. */
+        if ((!sample->user_regs.regs) ||
+            (!sample->user_stack.size))
+                return 0;
+
+        return unwind__get_entries(unwind_entry, &callchain_cursor, machine,
+                                   thread, evsel->attr.sample_regs_user,
+                                   sample);
+
+}
+
+static int process_event_synth_tracing_data_stub(union perf_event *event
+                                                 __maybe_unused,
+                                                 struct perf_session *session
+                                                __maybe_unused)
 {
         dump_printf(": unhandled!\n");
         return 0;
 }
 
-static int process_event_synth_attr_stub(union perf_event *event __used,
-                                         struct perf_evlist **pevlist __used)
+static int process_event_synth_attr_stub(union perf_event *event __maybe_unused,
+                                         struct perf_evlist **pevlist
+                                         __maybe_unused)
 {
         dump_printf(": unhandled!\n");
         return 0;
 }
 
-static int process_event_sample_stub(struct perf_tool *tool __used,
-                                     union perf_event *event __used,
-                                     struct perf_sample *sample __used,
-                                     struct perf_evsel *evsel __used,
-                                     struct machine *machine __used)
+static int process_event_sample_stub(struct perf_tool *tool __maybe_unused,
+                                     union perf_event *event __maybe_unused,
+                                     struct perf_sample *sample __maybe_unused,
+                                     struct perf_evsel *evsel __maybe_unused,
+                                     struct machine *machine __maybe_unused)
 {
         dump_printf(": unhandled!\n");
         return 0;
 }
 
-static int process_event_stub(struct perf_tool *tool __used,
-                              union perf_event *event __used,
-                              struct perf_sample *sample __used,
-                              struct machine *machine __used)
+static int process_event_stub(struct perf_tool *tool __maybe_unused,
+                              union perf_event *event __maybe_unused,
+                              struct perf_sample *sample __maybe_unused,
+                              struct machine *machine __maybe_unused)
 {
         dump_printf(": unhandled!\n");
         return 0;
 }
 
-static int process_finished_round_stub(struct perf_tool *tool __used,
-                                       union perf_event *event __used,
-                                       struct perf_session *perf_session __used)
+static int process_finished_round_stub(struct perf_tool *tool __maybe_unused,
+                                       union perf_event *event __maybe_unused,
+                                       struct perf_session *perf_session
+                                       __maybe_unused)
 {
         dump_printf(": unhandled!\n");
         return 0;
 }
 
-static int process_event_type_stub(struct perf_tool *tool __used,
-                                   union perf_event *event __used)
+static int process_event_type_stub(struct perf_tool *tool __maybe_unused,
+                                   union perf_event *event __maybe_unused)
 {
         dump_printf(": unhandled!\n");
         return 0;
@@ -473,7 +524,7 @@ static void swap_sample_id_all(union perf_event *event, void *data)
 }
 
 static void perf_event__all64_swap(union perf_event *event,
-                                   bool sample_id_all __used)
+                                   bool sample_id_all __maybe_unused)
 {
         struct perf_event_header *hdr = &event->header;
         mem_bswap_64(hdr + 1, event->header.size - sizeof(*hdr));
@@ -487,7 +538,7 @@ static void perf_event__comm_swap(union perf_event *event, bool sample_id_all)
         if (sample_id_all) {
                 void *data = &event->comm.comm;
 
-                data += ALIGN(strlen(data) + 1, sizeof(u64));
+                data += PERF_ALIGN(strlen(data) + 1, sizeof(u64));
                 swap_sample_id_all(event, data);
         }
 }
@@ -504,7 +555,7 @@ static void perf_event__mmap_swap(union perf_event *event,
         if (sample_id_all) {
                 void *data = &event->mmap.filename;
 
-                data += ALIGN(strlen(data) + 1, sizeof(u64));
+                data += PERF_ALIGN(strlen(data) + 1, sizeof(u64));
                 swap_sample_id_all(event, data);
         }
 }
@@ -584,7 +635,7 @@ void perf_event__attr_swap(struct perf_event_attr *attr)
 }
 
 static void perf_event__hdr_attr_swap(union perf_event *event,
-                                      bool sample_id_all __used)
+                                      bool sample_id_all __maybe_unused)
 {
         size_t size;
 
@@ -596,14 +647,14 @@ static void perf_event__hdr_attr_swap(union perf_event *event,
 }
 
 static void perf_event__event_type_swap(union perf_event *event,
-                                        bool sample_id_all __used)
+                                        bool sample_id_all __maybe_unused)
 {
         event->event_type.event_type.event_id =
                 bswap_64(event->event_type.event_type.event_id);
 }
 
 static void perf_event__tracing_data_swap(union perf_event *event,
-                                          bool sample_id_all __used)
+                                          bool sample_id_all __maybe_unused)
 {
         event->tracing_data.size = bswap_32(event->tracing_data.size);
 }
@@ -652,7 +703,7 @@ static int perf_session_deliver_event(struct perf_session *session,
                                       struct perf_tool *tool,
                                       u64 file_offset);
 
-static void flush_sample_queue(struct perf_session *s,
+static int flush_sample_queue(struct perf_session *s,
                                struct perf_tool *tool)
 {
         struct ordered_samples *os = &s->ordered_samples;
@@ -665,19 +716,21 @@ static void flush_sample_queue(struct perf_session *s,
         int ret;
 
         if (!tool->ordered_samples || !limit)
-                return;
+                return 0;
 
         list_for_each_entry_safe(iter, tmp, head, list) {
                 if (iter->timestamp > limit)
                         break;
 
-                ret = perf_evlist__parse_sample(s->evlist, iter->event, &sample,
-                                                s->header.needs_swap);
+                ret = perf_evlist__parse_sample(s->evlist, iter->event, &sample);
                 if (ret)
                         pr_err("Can't parse sample, err = %d\n", ret);
-                else
-                        perf_session_deliver_event(s, iter->event, &sample, tool,
-                                                   iter->file_offset);
+                else {
+                        ret = perf_session_deliver_event(s, iter->event, &sample, tool,
+                                                         iter->file_offset);
+                        if (ret)
+                                return ret;
+                }
 
                 os->last_flush = iter->timestamp;
                 list_del(&iter->list);
@@ -697,6 +750,8 @@ static void flush_sample_queue(struct perf_session *s,
         }
 
         os->nr_samples = 0;
+
+        return 0;
 }
 
 /*
@@ -739,13 +794,14 @@ static void flush_sample_queue(struct perf_session *s,
  *      etc...
  */
 static int process_finished_round(struct perf_tool *tool,
-                                  union perf_event *event __used,
+                                  union perf_event *event __maybe_unused,
                                   struct perf_session *session)
 {
-        flush_sample_queue(session, tool);
-        session->ordered_samples.next_flush = session->ordered_samples.max_timestamp;
+        int ret = flush_sample_queue(session, tool);
+        if (!ret)
+                session->ordered_samples.next_flush = session->ordered_samples.max_timestamp;
 
-        return 0;
+        return ret;
 }
 
 /* The queue is ordered by time */
@@ -860,6 +916,34 @@ static void branch_stack__printf(struct perf_sample *sample)
                         sample->branch_stack->entries[i].to);
 }
 
+static void regs_dump__printf(u64 mask, u64 *regs)
+{
+        unsigned rid, i = 0;
+
+        for_each_set_bit(rid, (unsigned long *) &mask, sizeof(mask) * 8) {
+                u64 val = regs[i++];
+
+                printf(".... %-5s 0x%" PRIx64 "\n",
+                       perf_reg_name(rid), val);
+        }
+}
+
+static void regs_user__printf(struct perf_sample *sample, u64 mask)
+{
+        struct regs_dump *user_regs = &sample->user_regs;
+
+        if (user_regs->regs) {
+                printf("... user regs: mask 0x%" PRIx64 "\n", mask);
+                regs_dump__printf(mask, user_regs->regs);
+        }
+}
+
+static void stack_user__printf(struct stack_dump *dump)
+{
+        printf("... ustack: size %" PRIu64 ", offset 0x%x\n",
+               dump->size, dump->offset);
+}
+
 static void perf_session__print_tstamp(struct perf_session *session,
                                        union perf_event *event,
                                        struct perf_sample *sample)
@@ -897,7 +981,7 @@ static void dump_event(struct perf_session *session, union perf_event *event,
                event->header.size, perf_event__name(event->header.type));
 }
 
-static void dump_sample(struct perf_session *session, union perf_event *event,
+static void dump_sample(struct perf_evsel *evsel, union perf_event *event,
                         struct perf_sample *sample)
 {
         u64 sample_type;
@@ -909,13 +993,19 @@ static void dump_sample(struct perf_session *session, union perf_event *event,
                event->header.misc, sample->pid, sample->tid, sample->ip,
                sample->period, sample->addr);
 
-        sample_type = perf_evlist__sample_type(session->evlist);
+        sample_type = evsel->attr.sample_type;
 
         if (sample_type & PERF_SAMPLE_CALLCHAIN)
                 callchain__printf(sample);
 
         if (sample_type & PERF_SAMPLE_BRANCH_STACK)
                 branch_stack__printf(sample);
+
+        if (sample_type & PERF_SAMPLE_REGS_USER)
+                regs_user__printf(sample, evsel->attr.sample_regs_user);
+
+        if (sample_type & PERF_SAMPLE_STACK_USER)
+                stack_user__printf(&sample->user_stack);
 }
 
 static struct machine *
@@ -973,7 +1063,7 @@ static int perf_session_deliver_event(struct perf_session *session,
 
         switch (event->header.type) {
         case PERF_RECORD_SAMPLE:
-                dump_sample(session, event, sample);
+                dump_sample(evsel, event, sample);
                 if (evsel == NULL) {
                         ++session->hists.stats.nr_unknown_id;
                         return 0;
@@ -1083,8 +1173,7 @@ static int perf_session__process_event(struct perf_session *session,
         /*
          * For all kernel events we get the sample data
          */
-        ret = perf_evlist__parse_sample(session->evlist, event, &sample,
-                                        session->header.needs_swap);
+        ret = perf_evlist__parse_sample(session->evlist, event, &sample);
         if (ret)
                 return ret;
 
@@ -1369,7 +1458,7 @@ more:
         err = 0;
         /* do the final flush for ordered samples */
         session->ordered_samples.next_flush = ULLONG_MAX;
-        flush_sample_queue(session, tool);
+        err = flush_sample_queue(session, tool);
 out_err:
         perf_session__warn_about_errors(session, tool);
         perf_session_free_sample_buffers(session);
@@ -1498,9 +1587,9 @@ struct perf_evsel *perf_session__find_first_evtype(struct perf_session *session,
         return NULL;
 }
 
-void perf_event__print_ip(union perf_event *event, struct perf_sample *sample,
-                          struct machine *machine, int print_sym,
-                          int print_dso, int print_symoffset)
+void perf_evsel__print_ip(struct perf_evsel *evsel, union perf_event *event,
+                          struct perf_sample *sample, struct machine *machine,
+                          int print_sym, int print_dso, int print_symoffset)
 {
         struct addr_location al;
         struct callchain_cursor_node *node;
@@ -1514,8 +1603,9 @@ void perf_event__print_ip(union perf_event *event, struct perf_sample *sample,
 
         if (symbol_conf.use_callchain && sample->callchain) {
 
-                if (machine__resolve_callchain(machine, al.thread,
-                                                sample->callchain, NULL) != 0) {
+
+                if (machine__resolve_callchain(machine, evsel, al.thread,
+                                               sample, NULL) != 0) {
                         if (verbose)
                                 error("Failed to resolve callchain. Skipping\n");
                         return;