Merge branch 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull perf updates from Ingo Molnar:
 "The main kernel side changes were:

   - uprobes enhancements (Masami Hiramatsu)

   - Uncore group events enhancements (David Carrillo-Cisneros)

   - x86 Intel: Add support for Skylake server uncore PMUs (Kan Liang)

   - x86 Intel: LBR cleanups and enhancements, for better branch
     annotation tracking (Peter Zijlstra)

   - x86 Intel: Add support for PTWRITE and power event tracing
     (Alexander Shishkin)

   - ... various fixes, cleanups and smaller enhancements.

  Lots of tooling changes - a couple of highlights:

   - Support event group view with hierarchy mode in 'perf top' and
     'perf report' (Namhyung Kim)

     e.g.:

     $ perf record -e '{cycles,instructions}' make
     $ perf report --hierarchy --stdio
     ...
     #   Overhead  Command / Shared Object / Symbol
     # ......................  ..................................
     ...
     25.74%  27.18%sh
     19.96%  24.14%libc-2.24.so
      9.55%  14.64%[.] __strcmp_sse2
      1.54%   0.00%[.] __tfind
      1.07%   1.13%[.] _int_malloc
      0.95%   0.00%[.] __strchr_sse2
      0.89%   1.39%[.] __tsearch
      0.76%   0.00%[.] strlen

   - 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)

   - Add support for using symbols in address filters with Intel PT and
     ARM CoreSight (hardware assisted tracing facilities) (Adrian
     Hunter, Mathieu Poirier)

   - Add support for interacting with Coresight PMU ETMs/PTMs, that are
     IP blocks to perform hardware assisted tracing on a ARM CPU core
     (Mathieu Poirier)

   - Support generating cross arch probes, i.e. if you specify a vmlinux
     file for different arch than the one in the host machine,

        $ perf probe --definition function_name args

     will generate the probe definition string needed to append to the
     target machine /sys/kernel/debug/tracing/kprobes_events file, using
     scripting (Masami Hiramatsu).

   - Allow configuring the default 'perf report -s' sort order in
     ~/.perfconfig, for instance, "sym,dso" may be more fitting for
     kernel developers. (Arnaldo Carvalho de Melo)

   - ... plus lots of other changes, refactorings, features and fixes"

* 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (149 commits)
  perf tests: Add dwarf unwind test for powerpc
  perf probe: Match linkage name with mangled name
  perf probe: Fix to cut off incompatible chars from group name
  perf probe: Skip if the function address is 0
  perf probe: Ignore the error of finding inline instance
  perf intel-pt: Fix decoding when there are address filters
  perf intel-pt: Enable decoder to handle TIP.PGD with missing IP
  perf intel-pt: Read address filter from AUXTRACE_INFO event
  perf intel-pt: Record address filter in AUXTRACE_INFO event
  perf intel-pt: Add a helper function for processing AUXTRACE_INFO
  perf intel-pt: Fix missing error codes processing auxtrace_info
  perf intel-pt: Add support for recording the max non-turbo ratio
  perf intel-pt: Fix snapshot overlap detection decoder errors
  perf probe: Increase debug level of SDT debug messages
  perf record: Add support for using symbols in address filters
  perf symbols: Add dso__last_symbol()
  perf record: Fix error paths
  perf record: Rename label 'out_symbol_exit'
  perf script: Fix vanished idle symbols
  perf evsel: Add support for address filters
  ...

1 files changed, 108 insertions, 3 deletions

diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c
index 9c1034d81b4f..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;
 
@@ -204,8 +308,6 @@ static int __cmd_annotate(struct perf_annotate *ann)
 	struct perf_evsel *pos;
 	u64 total_nr_samples;
 
-	machines__set_symbol_filter(&session->machines, symbol__annotate_init);
-
 	if (ann->cpu_list) {
 		ret = perf_session__cpu_bitmap(session, ann->cpu_list,
 					       ann->cpu_bitmap);
@@ -367,7 +469,10 @@ int cmd_annotate(int argc, const char **argv, const char *prefix __maybe_unused)
 	if (annotate.session == NULL)
 		return -1;
 
-	symbol_conf.priv_size = sizeof(struct annotation);
+	ret = symbol__annotation_init();
+	if (ret < 0)
+		goto out_delete;
+
 	symbol_conf.try_vmlinux_path = true;
 
 	ret = symbol__init(&annotate.session->header.env);