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/ui/stdio/hist.c

@@ -531,6 +531,30 @@ out:
 	return printed;
 }
 
+static int hist_entry__block_fprintf(struct hist_entry *he,
+				     char *bf, size_t size,
+				     FILE *fp)
+{
+	struct block_hist *bh = container_of(he, struct block_hist, he);
+	int ret = 0;
+
+	for (unsigned int i = 0; i < bh->block_hists.nr_entries; i++) {
+		struct perf_hpp hpp = {
+			.buf		= bf,
+			.size		= size,
+			.skip		= false,
+		};
+
+		bh->block_idx = i;
+		hist_entry__snprintf(he, &hpp);
+
+		if (!hpp.skip)
+			ret += fprintf(fp, "%s\n", bf);
+	}
+
+	return ret;
+}
+
 static int hist_entry__fprintf(struct hist_entry *he, size_t size,
 			       char *bf, size_t bfsz, FILE *fp,
 			       bool ignore_callchains)
@@ -550,6 +574,9 @@ static int hist_entry__fprintf(struct hist_entry *he, size_t size,
 	if (symbol_conf.report_hierarchy)
 		return hist_entry__hierarchy_fprintf(he, &hpp, hists, fp);
 
+	if (symbol_conf.report_block)
+		return hist_entry__block_fprintf(he, bf, size, fp);
+
 	hist_entry__snprintf(he, &hpp);
 
 	ret = fprintf(fp, "%s\n", bf);