Merge tag 'perf-core-for-mingo-20160908' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/core

Pull perf/core improvements and fixes from Arnaldo Carvalho de Melo:

User visible changes:

- Add branch stack / basic block info to 'perf annotate --stdio', where for
  each branch, we add an asm comment after the instruction with information on
  how often it was taken and predicted. See example with color output at:

    http://vger.kernel.org/~acme/perf/annotate_basic_blocks.png

  (Peter Zijlstra)

- Only open an evsel in CPUs in its cpu map, fixing some use cases in
  systems with multiple PMUs with different CPU maps (Mark Rutland)

- Fix handling of huge TLB maps, recognizing it as anonymous (Wang Nan)

Infrastructure changes:

- Remove the symbol filtering code, i.e. the callbacks passed to all functions
  that could end up loading a DSO symtab, simplifying the code, eventually
  allowing what we should have had since day one: removing the 'map' parameter
  from dso__load() functions (Arnaldo Carvalho de Melo)

Arch specific build fixes:

- Fix detached tarball build on powerpc, where we were still accessing a
  file outside tools/ (Ravi Bangoria)

Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>

1 files changed, 104 insertions, 0 deletions

diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c
index f07b23011b22..ebb628332a6e 100644
--- a/tools/perf/builtin-annotate.c
+++ b/tools/perf/builtin-annotate.c
@@ -30,6 +30,7 @@
 #include "util/tool.h"
 #include "util/data.h"
 #include "arch/common.h"
+#include "util/block-range.h"
 
 #include <dlfcn.h>
 #include <linux/bitmap.h>
@@ -46,6 +47,103 @@ struct perf_annotate {
 	DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS);
 };
 
+/*
+ * Given one basic block:
+ *
+ *	from	to		branch_i
+ *	* ----> *
+ *		|
+ *		| block
+ *		v
+ *		* ----> *
+ *		from	to	branch_i+1
+ *
+ * where the horizontal are the branches and the vertical is the executed
+ * block of instructions.
+ *
+ * We count, for each 'instruction', the number of blocks that covered it as
+ * well as count the ratio each branch is taken.
+ *
+ * We can do this without knowing the actual instruction stream by keeping
+ * track of the address ranges. We break down ranges such that there is no
+ * overlap and iterate from the start until the end.
+ *
+ * @acme: once we parse the objdump output _before_ processing the samples,
+ * we can easily fold the branch.cycles IPC bits in.
+ */
+static void process_basic_block(struct addr_map_symbol *start,
+				struct addr_map_symbol *end,
+				struct branch_flags *flags)
+{
+	struct symbol *sym = start->sym;
+	struct annotation *notes = sym ? symbol__annotation(sym) : NULL;
+	struct block_range_iter iter;
+	struct block_range *entry;
+
+	/*
+	 * Sanity; NULL isn't executable and the CPU cannot execute backwards
+	 */
+	if (!start->addr || start->addr > end->addr)
+		return;
+
+	iter = block_range__create(start->addr, end->addr);
+	if (!block_range_iter__valid(&iter))
+		return;
+
+	/*
+	 * First block in range is a branch target.
+	 */
+	entry = block_range_iter(&iter);
+	assert(entry->is_target);
+	entry->entry++;
+
+	do {
+		entry = block_range_iter(&iter);
+
+		entry->coverage++;
+		entry->sym = sym;
+
+		if (notes)
+			notes->max_coverage = max(notes->max_coverage, entry->coverage);
+
+	} while (block_range_iter__next(&iter));
+
+	/*
+	 * Last block in rage is a branch.
+	 */
+	entry = block_range_iter(&iter);
+	assert(entry->is_branch);
+	entry->taken++;
+	if (flags->predicted)
+		entry->pred++;
+}
+
+static void process_branch_stack(struct branch_stack *bs, struct addr_location *al,
+				 struct perf_sample *sample)
+{
+	struct addr_map_symbol *prev = NULL;
+	struct branch_info *bi;
+	int i;
+
+	if (!bs || !bs->nr)
+		return;
+
+	bi = sample__resolve_bstack(sample, al);
+	if (!bi)
+		return;
+
+	for (i = bs->nr - 1; i >= 0; i--) {
+		/*
+		 * XXX filter against symbol
+		 */
+		if (prev)
+			process_basic_block(prev, &bi[i].from, &bi[i].flags);
+		prev = &bi[i].to;
+	}
+
+	free(bi);
+}
+
 static int perf_evsel__add_sample(struct perf_evsel *evsel,
 				  struct perf_sample *sample,
 				  struct addr_location *al,
@@ -72,6 +170,12 @@ static int perf_evsel__add_sample(struct perf_evsel *evsel,
 		return 0;
 	}
 
+	/*
+	 * XXX filtered samples can still have branch entires pointing into our
+	 * symbol and are missed.
+	 */
+	process_branch_stack(sample->branch_stack, al, sample);
+
 	sample->period = 1;
 	sample->weight = 1;