8 files changed, 92 insertions, 28 deletions

diff --git a/tools/perf/Documentation/perf-script.txt b/tools/perf/Documentation/perf-script.txt
index cb0eda3925e6..3517e204a2b3 100644
--- a/tools/perf/Documentation/perf-script.txt
+++ b/tools/perf/Documentation/perf-script.txt
@@ -311,6 +311,10 @@ include::itrace.txt[]
         Set the maximum number of program blocks to print with brstackasm for
         each sample.
 
+--inline::
+        If a callgraph address belongs to an inlined function, the inline stack
+        will be printed. Each entry has function name and file/line.
+
 SEE ALSO
 --------
 linkperf:perf-record[1], linkperf:perf-script-perl[1],
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index d05aec491cff..4761b0d7fcb5 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -2494,6 +2494,8 @@ int cmd_script(int argc, const char **argv)
                         "Enable kernel symbol demangling"),
         OPT_STRING(0, "time", &script.time_str, "str",
                    "Time span of interest (start,stop)"),
+        OPT_BOOLEAN(0, "inline", &symbol_conf.inline_name,
+                    "Show inline function"),
         OPT_END()
         };
         const char * const script_subcommands[] = { "record", "report", NULL };
diff --git a/tools/perf/ui/hist.c b/tools/perf/ui/hist.c
index 59addd52d9cd..ddb2c6fbdf91 100644
--- a/tools/perf/ui/hist.c
+++ b/tools/perf/ui/hist.c
@@ -210,6 +210,8 @@ static int __hpp__sort_acc(struct hist_entry *a, struct hist_entry *b,
                         return 0;
 
                 ret = b->callchain->max_depth - a->callchain->max_depth;
+                if (callchain_param.order == ORDER_CALLER)
+                        ret = -ret;
         }
         return ret;
 }
diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c
index 81fc29ac798f..b4204b43ed58 100644
--- a/tools/perf/util/callchain.c
+++ b/tools/perf/util/callchain.c
@@ -621,14 +621,19 @@ enum match_result {
 static enum match_result match_chain_srcline(struct callchain_cursor_node *node,
                                              struct callchain_list *cnode)
 {
-        char *left = get_srcline(cnode->ms.map->dso,
+        char *left = NULL;
+        char *right = NULL;
+        enum match_result ret = MATCH_EQ;
+        int cmp;
+
+        if (cnode->ms.map)
+                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,
+        if (node->map)
+                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);
diff --git a/tools/perf/util/evsel_fprintf.c b/tools/perf/util/evsel_fprintf.c
index e415aee6a245..583f3a602506 100644
--- a/tools/perf/util/evsel_fprintf.c
+++ b/tools/perf/util/evsel_fprintf.c
@@ -7,6 +7,7 @@
 #include "map.h"
 #include "strlist.h"
 #include "symbol.h"
+#include "srcline.h"
 
 static int comma_fprintf(FILE *fp, bool *first, const char *fmt, ...)
 {
@@ -168,6 +169,38 @@ int sample__fprintf_callchain(struct perf_sample *sample, int left_alignment,
                         if (!print_oneline)
                                 printed += fprintf(fp, "\n");
 
+                        if (symbol_conf.inline_name && node->map) {
+                                struct inline_node *inode;
+
+                                addr = map__rip_2objdump(node->map, node->ip),
+                                inode = dso__parse_addr_inlines(node->map->dso, addr);
+
+                                if (inode) {
+                                        struct inline_list *ilist;
+
+                                        list_for_each_entry(ilist, &inode->val, list) {
+                                                if (print_arrow)
+                                                        printed += fprintf(fp, " <-");
+
+                                                /* IP is same, just skip it */
+                                                if (print_ip)
+                                                        printed += fprintf(fp, "%c%16s",
+                                                                           s, "");
+                                                if (print_sym)
+                                                        printed += fprintf(fp, " %s",
+                                                                           ilist->funcname);
+                                                if (print_srcline)
+                                                        printed += fprintf(fp, "\n  %s:%d",
+                                                                           ilist->filename,
+                                                                           ilist->line_nr);
+                                                if (!print_oneline)
+                                                        printed += fprintf(fp, "\n");
+                                        }
+
+                                        inline_node__delete(inode);
+                                }
+                        }
+
                         if (symbol_conf.bt_stop_list &&
                             node->sym &&
                             strlist__has_entry(symbol_conf.bt_stop_list,
diff --git a/tools/perf/util/srcline.c b/tools/perf/util/srcline.c
index df051a52393c..ebc88a74e67b 100644
--- a/tools/perf/util/srcline.c
+++ b/tools/perf/util/srcline.c
@@ -56,7 +56,10 @@ static int inline_list__append(char *filename, char *funcname, int line_nr,
                 }
         }
 
-        list_add_tail(&ilist->list, &node->val);
+        if (callchain_param.order == ORDER_CALLEE)
+                list_add_tail(&ilist->list, &node->val);
+        else
+                list_add(&ilist->list, &node->val);
 
         return 0;
 }
@@ -200,12 +203,14 @@ static void addr2line_cleanup(struct a2l_data *a2l)
 
 #define MAX_INLINE_NEST 1024
 
-static void inline_list__reverse(struct inline_node *node)
+static int inline_list__append_dso_a2l(struct dso *dso,
+                                       struct inline_node *node)
 {
-        struct inline_list *ilist, *n;
+        struct a2l_data *a2l = dso->a2l;
+        char *funcname = a2l->funcname ? strdup(a2l->funcname) : NULL;
+        char *filename = a2l->filename ? strdup(a2l->filename) : NULL;
 
-        list_for_each_entry_safe_reverse(ilist, n, &node->val, list)
-                list_move_tail(&ilist->list, &node->val);
+        return inline_list__append(filename, funcname, a2l->line, node, dso);
 }
 
 static int addr2line(const char *dso_name, u64 addr,
@@ -230,36 +235,36 @@ static int addr2line(const char *dso_name, u64 addr,
 
         bfd_map_over_sections(a2l->abfd, find_address_in_section, a2l);
 
-        if (a2l->found && unwind_inlines) {
+        if (!a2l->found)
+                return 0;
+
+        if (unwind_inlines) {
                 int cnt = 0;
 
+                if (node && inline_list__append_dso_a2l(dso, node))
+                        return 0;
+
                 while (bfd_find_inliner_info(a2l->abfd, &a2l->filename,
                                              &a2l->funcname, &a2l->line) &&
                        cnt++ < MAX_INLINE_NEST) {
 
                         if (node != NULL) {
-                                if (inline_list__append(strdup(a2l->filename),
-                                                        strdup(a2l->funcname),
-                                                        a2l->line, node,
-                                                        dso) != 0)
+                                if (inline_list__append_dso_a2l(dso, node))
                                         return 0;
+                                // found at least one inline frame
+                                ret = 1;
                         }
                 }
+        }
 
-                if ((node != NULL) &&
-                    (callchain_param.order != ORDER_CALLEE)) {
-                        inline_list__reverse(node);
-                }
+        if (file) {
+                *file = a2l->filename ? strdup(a2l->filename) : NULL;
+                ret = *file ? 1 : 0;
         }
 
-        if (a2l->found && a2l->filename) {
-                *file = strdup(a2l->filename);
+        if (line)
                 *line = a2l->line;
 
-                if (*file)
-                        ret = 1;
-        }
-
         return ret;
 }
 
@@ -278,8 +283,6 @@ void dso__free_a2l(struct dso *dso)
 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));
@@ -291,7 +294,7 @@ static struct inline_node *addr2inlines(const char *dso_name, u64 addr,
         INIT_LIST_HEAD(&node->val);
         node->addr = addr;
 
-        if (!addr2line(dso_name, addr, &file, &line, dso, TRUE, node))
+        if (!addr2line(dso_name, addr, NULL, NULL, dso, TRUE, node))
                 goto out_free_inline_node;
 
         if (list_empty(&node->val))
diff --git a/tools/perf/util/unwind-libdw.c b/tools/perf/util/unwind-libdw.c
index f90e11a555b2..943a06291587 100644
--- a/tools/perf/util/unwind-libdw.c
+++ b/tools/perf/util/unwind-libdw.c
@@ -168,12 +168,16 @@ frame_callback(Dwfl_Frame *state, void *arg)
 {
         struct unwind_info *ui = arg;
         Dwarf_Addr pc;
+        bool isactivation;
 
-        if (!dwfl_frame_pc(state, &pc, NULL)) {
+        if (!dwfl_frame_pc(state, &pc, &isactivation)) {
                 pr_err("%s", dwfl_errmsg(-1));
                 return DWARF_CB_ABORT;
         }
 
+        if (!isactivation)
+                --pc;
+
         return entry(pc, ui) || !(--ui->max_stack) ?
                DWARF_CB_ABORT : DWARF_CB_OK;
 }
diff --git a/tools/perf/util/unwind-libunwind-local.c b/tools/perf/util/unwind-libunwind-local.c
index f8455bed6e65..672c2ada9357 100644
--- a/tools/perf/util/unwind-libunwind-local.c
+++ b/tools/perf/util/unwind-libunwind-local.c
@@ -692,6 +692,17 @@ static int get_entries(struct unwind_info *ui, unwind_entry_cb_t cb,
 
                 while (!ret && (unw_step(&c) > 0) && i < max_stack) {
                         unw_get_reg(&c, UNW_REG_IP, &ips[i]);
+
+                        /*
+                         * Decrement the IP for any non-activation frames.
+                         * this is required to properly find the srcline
+                         * for caller frames.
+                         * See also the documentation for dwfl_frame_pc(),
+                         * which this code tries to replicate.
+                         */
+                        if (unw_is_signal_frame(&c) <= 0)
+                                --ips[i];
+
                         ++i;
                 }