perf diff: Print the basic block cycles diff

$ perf record -b ./div
 $ perf record -b ./div

Following is the default perf diff output

 $ perf diff

 # Event 'cycles'
 #
 # Baseline  Delta Abs  Shared Object     Symbol
 # ........  .........  ................  ..................................
 #
     48.75%     +0.33%  div               [.] main
      8.21%     -0.20%  div               [.] compute_flag
     19.02%     -0.12%  libc-2.23.so      [.] __random_r
     16.17%     -0.09%  libc-2.23.so      [.] __random
      2.27%     -0.03%  div               [.] rand@plt
                +0.02%  [i915]            [k] gen8_irq_handler
      5.52%     +0.02%  libc-2.23.so      [.] rand

This patch creates a new computation selection 'cycles'.

 $ perf diff -c cycles

 # Event 'cycles'
 #
 # Baseline       [Program Block Range] Cycles Diff Shared Object Symbol
 # ........ ....................................... .........................................
 #
     48.75%             [div.c:42 -> div.c:45]  147 div           [.] main
     48.75%             [div.c:31 -> div.c:40]    4 div           [.] main
     48.75%             [div.c:40 -> div.c:40]    0 div           [.] main
     48.75%             [div.c:42 -> div.c:42]    0 div           [.] main
     48.75%             [div.c:42 -> div.c:44]    0 div           [.] main
     19.02% [random_r.c:357 -> random_r.c:360]    0 libc-2.23.so  [.] __random_r
     19.02% [random_r.c:357 -> random_r.c:373]    0 libc-2.23.so  [.] __random_r
     19.02% [random_r.c:357 -> random_r.c:376]    0 libc-2.23.so  [.] __random_r
     19.02% [random_r.c:357 -> random_r.c:380]    0 libc-2.23.so  [.] __random_r
     19.02% [random_r.c:357 -> random_r.c:392]    0 libc-2.23.so  [.] __random_r
     16.17%     [random.c:288 -> random.c:291]    0 libc-2.23.so  [.] __random
     16.17%     [random.c:288 -> random.c:291]    0 libc-2.23.so  [.] __random
     16.17%     [random.c:288 -> random.c:295]    0 libc-2.23.so  [.] __random
     16.17%     [random.c:288 -> random.c:297]    0 libc-2.23.so  [.] __random
     16.17%     [random.c:291 -> random.c:291]    0 libc-2.23.so  [.] __random
     16.17%     [random.c:293 -> random.c:293]    0 libc-2.23.so  [.] __random
      8.21%             [div.c:22 -> div.c:22]  148 div           [.] compute_flag
      8.21%             [div.c:22 -> div.c:25]    0 div           [.] compute_flag
      8.21%             [div.c:27 -> div.c:28]    0 div           [.] compute_flag
      5.52%           [rand.c:26 -> rand.c:27]    0 libc-2.23.so  [.] rand
      5.52%           [rand.c:26 -> rand.c:28]    0 libc-2.23.so  [.] rand
      2.27%         [rand@plt+0 -> rand@plt+0]    0 div           [.] rand@plt
      0.01% [entry_64.S:694 -> entry_64.S:694]   16 [vmlinux]     [k] native_irq_return_iret
      0.00%       [fair.c:7676 -> fair.c:7665]  162 [vmlinux]     [k] update_blocked_averages

"[Program Block Range]" indicates the range of program basic block
(start -> end). If we can find the source line it prints the source line
otherwise it prints the symbol+offset instead.

 v4:
 ---
 Use source lines or symbol+offset to indicate the basic block. It should
 be easier to understand.

 v3:
 ---
 Cast 'struct hist_entry' to 'struct block_hist' in hist_entry__block_fprintf.
 Use symbol_conf.report_block to check if executing hist_entry__block_fprintf.

 v2:
 ---
 Keep standard perf diff format and display the 'Baseline' and
 'Shared Object'.

The output is sorted by "Baseline" and the basic blocks in the same
function are sorted by cycles diff.

Signed-off-by: Jin Yao <yao.jin@linux.intel.com>
Reviewed-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jin Yao <yao.jin@intel.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1561713784-30533-7-git-send-email-yao.jin@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

tools/perf/util/hist.c

@@ -376,6 +376,24 @@ void hists__delete_entries(struct hists *hists)
 	}
 }
 
+struct hist_entry *hists__get_entry(struct hists *hists, int idx)
+{
+	struct rb_node *next = rb_first_cached(&hists->entries);
+	struct hist_entry *n;
+	int i = 0;
+
+	while (next) {
+		n = rb_entry(next, struct hist_entry, rb_node);
+		if (i == idx)
+			return n;
+
+		next = rb_next(&n->rb_node);
+		i++;
+	}
+
+	return NULL;
+}
+
 /*
  * histogram, sorted on item, collects periods
  */

tools/perf/util/hist.h

@@ -183,6 +183,8 @@ void hists__decay_entries(struct hists *hists, bool zap_user, bool zap_kernel);
 void hists__delete_entries(struct hists *hists);
 void hists__output_recalc_col_len(struct hists *hists, int max_rows);
 
+struct hist_entry *hists__get_entry(struct hists *hists, int idx);
+
 u64 hists__total_period(struct hists *hists);
 void hists__reset_stats(struct hists *hists);
 void hists__inc_stats(struct hists *hists, struct hist_entry *h);
@@ -248,6 +250,7 @@ struct perf_hpp {
 	size_t size;
 	const char *sep;
 	void *ptr;
+	bool skip;
 };
 
 struct perf_hpp_fmt {

tools/perf/util/srcline.c

@@ -11,6 +11,7 @@
 #include "util/util.h"
 #include "util/debug.h"
 #include "util/callchain.h"
+#include "util/symbol_conf.h"
 #include "srcline.h"
 #include "string2.h"
 #include "symbol.h"
@@ -288,7 +289,8 @@ static int addr2line(const char *dso_name, u64 addr,
 	}
 
 	if (a2l == NULL) {
-		pr_warning("addr2line_init failed for %s\n", dso_name);
+		if (!symbol_conf.disable_add2line_warn)
+			pr_warning("addr2line_init failed for %s\n", dso_name);
 		return 0;
 	}
 

tools/perf/util/symbol_conf.h

@@ -39,7 +39,9 @@ struct symbol_conf {
 			hide_unresolved,
 			raw_trace,
 			report_hierarchy,
-			inline_name;
+			report_block,
+			inline_name,
+			disable_add2line_warn;
 	const char	*vmlinux_name,
 			*kallsyms_name,
 			*source_prefix,