Merge tag 'perf-tools-for-v6.12-1-2024-09-19' of git://git.kernel.org/pub/scm/linux/kernel/git/perf/perf-tools

Pull perf tools updates from Arnaldo Carvalho de Melo:

 - Use BPF + BTF to collect and pretty print syscall and tracepoint
   arguments in 'perf trace', done as an GSoC activity

 - Data-type profiling improvements:

     - Cache debuginfo to speed up data type resolution

     - Add the 'typecln' sort order, to show which cacheline in a target
       is hot or cold. The following shows members in the cfs_rq's first
       cache line:

         $ perf report -s type,typecln,typeoff -H
         ...
         -    2.67%        struct cfs_rq
            +    1.23%        struct cfs_rq: cache-line 2
            +    0.57%        struct cfs_rq: cache-line 4
            +    0.46%        struct cfs_rq: cache-line 6
            -    0.41%        struct cfs_rq: cache-line 0
                    0.39%        struct cfs_rq +0x14 (h_nr_running)
                    0.02%        struct cfs_rq +0x38 (tasks_timeline.rb_leftmost)

     - When a typedef resolves to a unnamed struct, use the typedef name

     - When a struct has just one basic type field (int, etc), resolve
       the type sort order to the name of the struct, not the type of
       the field

     - Support type folding/unfolding in the data-type annotation TUI

     - Fix bitfields offsets and sizes

     - Initial support for PowerPC, using libcapstone and the usual
       objdump disassembly parsing routines

 - Add support for disassembling and addr2line using the LLVM libraries,
   speeding up those operations

 - Support --addr2line option in 'perf script' as with other tools

 - Intel branch counters (LBR event logging) support, only available in
   recent Intel processors, for instance, the new "brcntr" field can be
   asked from 'perf script' to print the information collected from this
   feature:

     $ perf script -F +brstackinsn,+brcntr

     # Branch counter abbr list:
     # branch-instructions:ppp = A
     # branch-misses = B
     # '-' No event occurs
     # '+' Event occurrences may be lost due to branch counter saturated
         tchain_edit  332203 3366329.405674:  53030 branch-instructions:ppp:    401781 f3+0x2c (home/sdp/test/tchain_edit)
            f3+31:
         0000000000401774   insn: eb 04                  br_cntr: AA  # PRED 5 cycles [5]
         000000000040177a   insn: 81 7d fc 0f 27 00 00
         0000000000401781   insn: 7e e3                  br_cntr: A   # PRED 1 cycles [6] 2.00 IPC
         0000000000401766   insn: 8b 45 fc
         0000000000401769   insn: 83 e0 01
         000000000040176c   insn: 85 c0
         000000000040176e   insn: 74 06                  br_cntr: A   # PRED 1 cycles [7] 4.00 IPC
         0000000000401776   insn: 83 45 fc 01
         000000000040177a   insn: 81 7d fc 0f 27 00 00
         0000000000401781   insn: 7e e3                  br_cntr: A   # PRED 7 cycles [14] 0.43 IPC

 - Support Timed PEBS (Precise Event-Based Sampling), a recent hardware
   feature in Intel processors

 - Add 'perf ftrace profile' subcommand, using ftrace's function-graph
   tracer so that users can see the total, average, max execution time
   as well as the number of invocations easily, for instance:

     $ sudo perf ftrace profile -G __x64_sys_perf_event_open -- \
       perf stat -e cycles -C1 true 2> /dev/null | head
     # Total (us)  Avg (us)  Max (us)  Count  Function
           65.611    65.611    65.611      1  __x64_sys_perf_event_open
           30.527    30.527    30.527      1  anon_inode_getfile
           30.260    30.260    30.260      1  __anon_inode_getfile
           29.700    29.700    29.700      1  alloc_file_pseudo
           17.578    17.578    17.578      1  d_alloc_pseudo
           17.382    17.382    17.382      1  __d_alloc
           16.738    16.738    16.738      1  kmem_cache_alloc_lru
           15.686    15.686    15.686      1  perf_event_alloc
           14.012     7.006    11.264      2  obj_cgroup_charge

 - 'perf sched timehist' improvements, including the addition of
   priority showing/filtering command line options

 - Varios improvements to the 'perf probe', including 'perf test'
   regression testings

 - Introduce the 'perf check', initially to check if some feature is
   in place, using it in 'perf test'

 - Various fixes for 32-bit systems

 - Address more leak sanitizer failures

 - Fix memory leaks (LBR, disasm lock ops, etc)

 - More reference counting fixes (branch_info, etc)

 - Constify 'struct perf_tool' parameters to improve code generation
   and reduce the chances of having its internals changed, which isn't
   expected

 - More constifications in various other places

 - Add more build tests, including for JEVENTS

 - Add more 'perf test' entries ('perf record LBR', pipe/inject,
   --setup-filter, 'perf ftrace', 'cgroup sampling', etc)

 - Inject build ids for all entries in a call chain in 'perf inject',
   not just for the main sample

 - Improve the BPF based sample filter, allowing root to setup filters
   in bpffs that then can be used by non-root users

 - Allow filtering by cgroups with the BPF based sample filter

 - Allow a more compact way for 'perf mem report' using the
   -T/--type-profile and also provide a --sort option similar to the one
   in 'perf report', 'perf top', to setup the sort order manually

 - Fix --group behavior in 'perf annotate' when leader has no samples,
   where it was not showing anything even when other events in the group
   had samples

 - Fix spinlock and rwlock accounting in 'perf lock contention'

 - Fix libsubcmd fixdep Makefile dependencies

 - Improve 'perf ftrace' error message when ftrace isn't available

 - Update various Intel JSON vendor event files

 - ARM64 CoreSight hardware tracing infrastructure improvements, mostly
   not visible to users

 - Update power10 JSON events

* tag 'perf-tools-for-v6.12-1-2024-09-19' of git://git.kernel.org/pub/scm/linux/kernel/git/perf/perf-tools: (310 commits)
  perf trace: Mark the 'head' arg in the set_robust_list syscall as coming from user space
  perf trace: Mark the 'rseq' arg in the rseq syscall as coming from user space
  perf env: Find correct branch counter info on hybrid
  perf evlist: Print hint for group
  tools: Drop nonsensical -O6
  perf pmu: To info add event_type_desc
  perf evsel: Add accessor for tool_event
  perf pmus: Fake PMU clean up
  perf list: Avoid potential out of bounds memory read
  perf help: Fix a typo ("bellow")
  perf ftrace: Detect whether ftrace is enabled on system
  perf test shell probe_vfs_getname: Remove extraneous '=' from probe line number regex
  perf build: Require at least clang 16.0.6 to build BPF skeletons
  perf trace: If a syscall arg is marked as 'const', assume it is coming _from_ userspace
  perf parse-events: Remove duplicated include in parse-events.c
  perf callchain: Allow symbols to be optional when resolving a callchain
  perf inject: Lazy build-id mmap2 event insertion
  perf inject: Add new mmap2-buildid-all option
  perf inject: Fix build ID injection
  perf annotate-data: Add pr_debug_scope()
  ...

1 files changed, 321 insertions, 39 deletions

diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 1451caf25e77..37ce43c4eb8f 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -25,6 +25,7 @@
 #include "srcline.h"
 #include "units.h"
 #include "debug.h"
+#include "debuginfo.h"
 #include "annotate.h"
 #include "annotate-data.h"
 #include "evsel.h"
@@ -40,6 +41,7 @@
 #include "namespaces.h"
 #include "thread.h"
 #include "hashmap.h"
+#include "strbuf.h"
 #include <regex.h>
 #include <linux/bitops.h>
 #include <linux/kernel.h>
@@ -47,6 +49,7 @@
 #include <linux/zalloc.h>
 #include <subcmd/parse-options.h>
 #include <subcmd/run-command.h>
+#include <math.h>
 
 /* FIXME: For the HE_COLORSET */
 #include "ui/browser.h"
@@ -265,22 +268,30 @@ struct annotated_branch *annotation__get_branch(struct annotation *notes)
 	return notes->branch;
 }
 
-static struct cyc_hist *symbol__cycles_hist(struct symbol *sym)
+static struct annotated_branch *symbol__find_branch_hist(struct symbol *sym,
+							 unsigned int br_cntr_nr)
 {
 	struct annotation *notes = symbol__annotation(sym);
 	struct annotated_branch *branch;
+	const size_t size = symbol__size(sym);
 
 	branch = annotation__get_branch(notes);
 	if (branch == NULL)
 		return NULL;
 
 	if (branch->cycles_hist == NULL) {
-		const size_t size = symbol__size(sym);
-
 		branch->cycles_hist = calloc(size, sizeof(struct cyc_hist));
+		if (!branch->cycles_hist)
+			return NULL;
+	}
+
+	if (br_cntr_nr && branch->br_cntr == NULL) {
+		branch->br_cntr = calloc(br_cntr_nr * size, sizeof(u64));
+		if (!branch->br_cntr)
+			return NULL;
 	}
 
-	return branch->cycles_hist;
+	return branch;
 }
 
 struct annotated_source *symbol__hists(struct symbol *sym, int nr_hists)
@@ -315,16 +326,45 @@ static int symbol__inc_addr_samples(struct map_symbol *ms,
 	return src ? __symbol__inc_addr_samples(ms, src, evsel->core.idx, addr, sample) : 0;
 }
 
-static int symbol__account_cycles(u64 addr, u64 start,
-				  struct symbol *sym, unsigned cycles)
+static int symbol__account_br_cntr(struct annotated_branch *branch,
+				   struct evsel *evsel,
+				   unsigned offset,
+				   u64 br_cntr)
+{
+	unsigned int br_cntr_nr = evsel__leader(evsel)->br_cntr_nr;
+	unsigned int base = evsel__leader(evsel)->br_cntr_idx;
+	unsigned int off = offset * evsel->evlist->nr_br_cntr;
+	u64 *branch_br_cntr = branch->br_cntr;
+	unsigned int i, mask, width;
+
+	if (!br_cntr || !branch_br_cntr)
+		return 0;
+
+	perf_env__find_br_cntr_info(evsel__env(evsel), NULL, &width);
+	mask = (1L << width) - 1;
+	for (i = 0; i < br_cntr_nr; i++) {
+		u64 cntr = (br_cntr >> i * width) & mask;
+
+		branch_br_cntr[off + i + base] += cntr;
+		if (cntr == mask)
+			branch_br_cntr[off + i + base] |= ANNOTATION__BR_CNTR_SATURATED_FLAG;
+	}
+
+	return 0;
+}
+
+static int symbol__account_cycles(u64 addr, u64 start, struct symbol *sym,
+				  unsigned cycles, struct evsel *evsel,
+				  u64 br_cntr)
 {
-	struct cyc_hist *cycles_hist;
+	struct annotated_branch *branch;
 	unsigned offset;
+	int ret;
 
 	if (sym == NULL)
 		return 0;
-	cycles_hist = symbol__cycles_hist(sym);
-	if (cycles_hist == NULL)
+	branch = symbol__find_branch_hist(sym, evsel->evlist->nr_br_cntr);
+	if (!branch)
 		return -ENOMEM;
 	if (addr < sym->start || addr >= sym->end)
 		return -ERANGE;
@@ -336,15 +376,22 @@ static int symbol__account_cycles(u64 addr, u64 start,
 			start = 0;
 	}
 	offset = addr - sym->start;
-	return __symbol__account_cycles(cycles_hist,
+	ret = __symbol__account_cycles(branch->cycles_hist,
 					start ? start - sym->start : 0,
 					offset, cycles,
 					!!start);
+
+	if (ret)
+		return ret;
+
+	return symbol__account_br_cntr(branch, evsel, offset, br_cntr);
 }
 
 int addr_map_symbol__account_cycles(struct addr_map_symbol *ams,
 				    struct addr_map_symbol *start,
-				    unsigned cycles)
+				    unsigned cycles,
+				    struct evsel *evsel,
+				    u64 br_cntr)
 {
 	u64 saddr = 0;
 	int err;
@@ -370,7 +417,7 @@ int addr_map_symbol__account_cycles(struct addr_map_symbol *ams,
 			start ? start->addr : 0,
 			ams->ms.sym ? ams->ms.sym->start + map__start(ams->ms.map) : 0,
 			saddr);
-	err = symbol__account_cycles(ams->al_addr, saddr, ams->ms.sym, cycles);
+	err = symbol__account_cycles(ams->al_addr, saddr, ams->ms.sym, cycles, evsel, br_cntr);
 	if (err)
 		pr_debug2("account_cycles failed %d\n", err);
 	return err;
@@ -411,6 +458,7 @@ static void annotated_branch__delete(struct annotated_branch *branch)
 {
 	if (branch) {
 		zfree(&branch->cycles_hist);
+		free(branch->br_cntr);
 		free(branch);
 	}
 }
@@ -454,8 +502,10 @@ static void annotation__count_and_fill(struct annotation *notes, u64 start, u64
 	}
 }
 
-static int annotation__compute_ipc(struct annotation *notes, size_t size)
+static int annotation__compute_ipc(struct annotation *notes, size_t size,
+				   struct evsel *evsel)
 {
+	unsigned int br_cntr_nr = evsel->evlist->nr_br_cntr;
 	int err = 0;
 	s64 offset;
 
@@ -490,6 +540,20 @@ static int annotation__compute_ipc(struct annotation *notes, size_t size)
 				al->cycles->max = ch->cycles_max;
 				al->cycles->min = ch->cycles_min;
 			}
+			if (al && notes->branch->br_cntr) {
+				if (!al->br_cntr) {
+					al->br_cntr = calloc(br_cntr_nr, sizeof(u64));
+					if (!al->br_cntr) {
+						err = ENOMEM;
+						break;
+					}
+				}
+				al->num_aggr = ch->num_aggr;
+				al->br_cntr_nr = br_cntr_nr;
+				al->evsel = evsel;
+				memcpy(al->br_cntr, &notes->branch->br_cntr[offset * br_cntr_nr],
+				       br_cntr_nr * sizeof(u64));
+			}
 		}
 	}
 
@@ -501,8 +565,10 @@ static int annotation__compute_ipc(struct annotation *notes, size_t size)
 				struct annotation_line *al;
 
 				al = annotated_source__get_line(notes->src, offset);
-				if (al)
+				if (al) {
 					zfree(&al->cycles);
+					zfree(&al->br_cntr);
+				}
 			}
 		}
 	}
@@ -699,13 +765,13 @@ annotation_line__print(struct annotation_line *al, struct symbol *sym, u64 start
 		       int percent_type)
 {
 	struct disasm_line *dl = container_of(al, struct disasm_line, al);
+	struct annotation *notes = symbol__annotation(sym);
 	static const char *prev_line;
 
 	if (al->offset != -1) {
 		double max_percent = 0.0;
 		int i, nr_percent = 1;
 		const char *color;
-		struct annotation *notes = symbol__annotation(sym);
 
 		for (i = 0; i < al->data_nr; i++) {
 			double percent;
@@ -775,14 +841,11 @@ annotation_line__print(struct annotation_line *al, struct symbol *sym, u64 start
 	} else if (max_lines && printed >= max_lines)
 		return 1;
 	else {
-		int width = symbol_conf.show_total_period ? 12 : 8;
+		int width = annotation__pcnt_width(notes);
 
 		if (queue)
 			return -1;
 
-		if (evsel__is_group_event(evsel))
-			width *= evsel->core.nr_members;
-
 		if (!*al->line)
 			printf(" %*s:\n", width, " ");
 		else
@@ -851,6 +914,10 @@ static void annotation__calc_percent(struct annotation *notes,
 
 			BUG_ON(i >= al->data_nr);
 
+			if (symbol_conf.skip_empty &&
+			    evsel__hists(evsel)->stats.nr_samples == 0)
+				continue;
+
 			data = &al->data[i++];
 
 			calc_percent(notes, evsel, data, al->offset, end);
@@ -904,7 +971,7 @@ int symbol__annotate(struct map_symbol *ms, struct evsel *evsel,
 		.options	= &annotate_opts,
 	};
 	struct arch *arch = NULL;
-	int err;
+	int err, nr;
 
 	err = evsel__get_arch(evsel, &arch);
 	if (err < 0)
@@ -925,6 +992,19 @@ int symbol__annotate(struct map_symbol *ms, struct evsel *evsel,
 			return -1;
 	}
 
+	nr = 0;
+	if (evsel__is_group_event(evsel)) {
+		struct evsel *pos;
+
+		for_each_group_evsel(pos, evsel) {
+			if (symbol_conf.skip_empty &&
+			    evsel__hists(pos)->stats.nr_samples == 0)
+				continue;
+			nr++;
+		}
+	}
+	notes->src->nr_events = nr ? nr : 1;
+
 	if (annotate_opts.full_addr)
 		notes->src->start = map__objdump_2mem(ms->map, ms->sym->start);
 	else
@@ -1106,7 +1186,7 @@ int symbol__annotate_printf(struct map_symbol *ms, struct evsel *evsel)
 	int more = 0;
 	bool context = opts->context;
 	u64 len;
-	int width = symbol_conf.show_total_period ? 12 : 8;
+	int width = annotation__pcnt_width(notes);
 	int graph_dotted_len;
 	char buf[512];
 
@@ -1122,7 +1202,6 @@ int symbol__annotate_printf(struct map_symbol *ms, struct evsel *evsel)
 	len = symbol__size(sym);
 
 	if (evsel__is_group_event(evsel)) {
-		width *= evsel->core.nr_members;
 		evsel__group_desc(evsel, buf, sizeof(buf));
 		evsel_name = buf;
 	}
@@ -1594,13 +1673,12 @@ bool ui__has_annotation(void)
 
 
 static double annotation_line__max_percent(struct annotation_line *al,
-					   struct annotation *notes,
 					   unsigned int percent_type)
 {
 	double percent_max = 0.0;
 	int i;
 
-	for (i = 0; i < notes->src->nr_events; i++) {
+	for (i = 0; i < al->data_nr; i++) {
 		double percent;
 
 		percent = annotation_data__percent(&al->data[i],
@@ -1662,6 +1740,149 @@ static void ipc_coverage_string(char *bf, int size, struct annotation *notes)
 		  ipc, coverage);
 }
 
+int annotation_br_cntr_abbr_list(char **str, struct evsel *evsel, bool header)
+{
+	struct evsel *pos;
+	struct strbuf sb;
+
+	if (evsel->evlist->nr_br_cntr <= 0)
+		return -ENOTSUP;
+
+	strbuf_init(&sb, /*hint=*/ 0);
+
+	if (header && strbuf_addf(&sb, "# Branch counter abbr list:\n"))
+		goto err;
+
+	evlist__for_each_entry(evsel->evlist, pos) {
+		if (!(pos->core.attr.branch_sample_type & PERF_SAMPLE_BRANCH_COUNTERS))
+			continue;
+		if (header && strbuf_addf(&sb, "#"))
+			goto err;
+
+		if (strbuf_addf(&sb, " %s = %s\n", pos->name, pos->abbr_name))
+			goto err;
+	}
+
+	if (header && strbuf_addf(&sb, "#"))
+		goto err;
+	if (strbuf_addf(&sb, " '-' No event occurs\n"))
+		goto err;
+
+	if (header && strbuf_addf(&sb, "#"))
+		goto err;
+	if (strbuf_addf(&sb, " '+' Event occurrences may be lost due to branch counter saturated\n"))
+		goto err;
+
+	*str = strbuf_detach(&sb, NULL);
+
+	return 0;
+err:
+	strbuf_release(&sb);
+	return -ENOMEM;
+}
+
+/* Assume the branch counter saturated at 3 */
+#define ANNOTATION_BR_CNTR_SATURATION		3
+
+int annotation_br_cntr_entry(char **str, int br_cntr_nr,
+			     u64 *br_cntr, int num_aggr,
+			     struct evsel *evsel)
+{
+	struct evsel *pos = evsel ? evlist__first(evsel->evlist) : NULL;
+	bool saturated = false;
+	int i, j, avg, used;
+	struct strbuf sb;
+
+	strbuf_init(&sb, /*hint=*/ 0);
+	for (i = 0; i < br_cntr_nr; i++) {
+		used = 0;
+		avg = ceil((double)(br_cntr[i] & ~ANNOTATION__BR_CNTR_SATURATED_FLAG) /
+			   (double)num_aggr);
+
+		/*
+		 * A histogram with the abbr name is displayed by default.
+		 * With -v, the exact number of branch counter is displayed.
+		 */
+		if (verbose) {
+			evlist__for_each_entry_from(evsel->evlist, pos) {
+				if ((pos->core.attr.branch_sample_type & PERF_SAMPLE_BRANCH_COUNTERS) &&
+				    (pos->br_cntr_idx == i))
+				break;
+			}
+			if (strbuf_addstr(&sb, pos->abbr_name))
+				goto err;
+
+			if (!br_cntr[i]) {
+				if (strbuf_addstr(&sb, "=-"))
+					goto err;
+			} else {
+				if (strbuf_addf(&sb, "=%d", avg))
+					goto err;
+			}
+			if (br_cntr[i] & ANNOTATION__BR_CNTR_SATURATED_FLAG) {
+				if (strbuf_addch(&sb, '+'))
+					goto err;
+			} else {
+				if (strbuf_addch(&sb, ' '))
+					goto err;
+			}
+
+			if ((i < br_cntr_nr - 1) && strbuf_addch(&sb, ','))
+				goto err;
+			continue;
+		}
+
+		if (strbuf_addch(&sb, '|'))
+			goto err;
+
+		if (!br_cntr[i]) {
+			if (strbuf_addch(&sb, '-'))
+				goto err;
+			used++;
+		} else {
+			evlist__for_each_entry_from(evsel->evlist, pos) {
+				if ((pos->core.attr.branch_sample_type & PERF_SAMPLE_BRANCH_COUNTERS) &&
+				    (pos->br_cntr_idx == i))
+					break;
+			}
+			if (br_cntr[i] & ANNOTATION__BR_CNTR_SATURATED_FLAG)
+				saturated = true;
+
+			for (j = 0; j < avg; j++, used++) {
+				/* Print + if the number of logged events > 3 */
+				if (j >= ANNOTATION_BR_CNTR_SATURATION) {
+					saturated = true;
+					break;
+				}
+				if (strbuf_addstr(&sb, pos->abbr_name))
+					goto err;
+			}
+
+			if (saturated) {
+				if (strbuf_addch(&sb, '+'))
+					goto err;
+				used++;
+			}
+			pos = list_next_entry(pos, core.node);
+		}
+
+		for (j = used; j < ANNOTATION_BR_CNTR_SATURATION + 1; j++) {
+			if (strbuf_addch(&sb, ' '))
+				goto err;
+		}
+	}
+
+	if (!verbose && strbuf_addch(&sb, br_cntr_nr ? '|' : ' '))
+		goto err;
+
+	*str = strbuf_detach(&sb, NULL);
+
+	return 0;
+err:
+	strbuf_release(&sb);
+	return -ENOMEM;
+}
+
 static void __annotation_line__write(struct annotation_line *al, struct annotation *notes,
 				     bool first_line, bool current_entry, bool change_color, int width,
 				     void *obj, unsigned int percent_type,
@@ -1672,7 +1893,7 @@ static void __annotation_line__write(struct annotation_line *al, struct annotati
 				     void (*obj__write_graph)(void *obj, int graph))
 
 {
-	double percent_max = annotation_line__max_percent(al, notes, percent_type);
+	double percent_max = annotation_line__max_percent(al, percent_type);
 	int pcnt_width = annotation__pcnt_width(notes),
 	    cycles_width = annotation__cycles_width(notes);
 	bool show_title = false;
@@ -1690,7 +1911,7 @@ static void __annotation_line__write(struct annotation_line *al, struct annotati
 	if (al->offset != -1 && percent_max != 0.0) {
 		int i;
 
-		for (i = 0; i < notes->src->nr_events; i++) {
+		for (i = 0; i < al->data_nr; i++) {
 			double percent;
 
 			percent = annotation_data__percent(&al->data[i], percent_type);
@@ -1699,10 +1920,10 @@ static void __annotation_line__write(struct annotation_line *al, struct annotati
 			if (symbol_conf.show_total_period) {
 				obj__printf(obj, "%11" PRIu64 " ", al->data[i].he.period);
 			} else if (symbol_conf.show_nr_samples) {
-				obj__printf(obj, "%6" PRIu64 " ",
+				obj__printf(obj, "%7" PRIu64 " ",
 						   al->data[i].he.nr_samples);
 			} else {
-				obj__printf(obj, "%6.2f ", percent);
+				obj__printf(obj, "%7.2f ", percent);
 			}
 		}
 	} else {
@@ -1758,6 +1979,22 @@ static void __annotation_line__write(struct annotation_line *al, struct annotati
 					    "Cycle(min/max)");
 		}
 
+		if (annotate_opts.show_br_cntr) {
+			if (show_title) {
+				obj__printf(obj, "%*s ",
+					    ANNOTATION__BR_CNTR_WIDTH,
+					    "Branch Counter");
+			} else {
+				char *buf;
+
+				if (!annotation_br_cntr_entry(&buf, al->br_cntr_nr, al->br_cntr,
+							      al->num_aggr, al->evsel)) {
+					obj__printf(obj, "%*s ", ANNOTATION__BR_CNTR_WIDTH, buf);
+					free(buf);
+				}
+			}
+		}
+
 		if (show_title && !*al->line) {
 			ipc_coverage_string(bf, sizeof(bf), notes);
 			obj__printf(obj, "%*s", ANNOTATION__AVG_IPC_WIDTH, bf);
@@ -1843,10 +2080,7 @@ int symbol__annotate2(struct map_symbol *ms, struct evsel *evsel,
 	struct symbol *sym = ms->sym;
 	struct annotation *notes = symbol__annotation(sym);
 	size_t size = symbol__size(sym);
-	int nr_pcnt = 1, err;
-
-	if (evsel__is_group_event(evsel))
-		nr_pcnt = evsel->core.nr_members;
+	int err;
 
 	err = symbol__annotate(ms, evsel, parch);
 	if (err)
@@ -1857,13 +2091,11 @@ int symbol__annotate2(struct map_symbol *ms, struct evsel *evsel,
 	annotation__set_index(notes);
 	annotation__mark_jump_targets(notes, sym);
 
-	err = annotation__compute_ipc(notes, size);
+	err = annotation__compute_ipc(notes, size, evsel);
 	if (err)
 		return err;
 
 	annotation__init_column_widths(notes, sym);
-	notes->src->nr_events = nr_pcnt;
-
 	annotation__update_column_widths(notes);
 	sym->annotate2 = 1;
 
@@ -2123,20 +2355,33 @@ int annotate_get_insn_location(struct arch *arch, struct disasm_line *dl,
 	for_each_insn_op_loc(loc, i, op_loc) {
 		const char *insn_str = ops->source.raw;
 		bool multi_regs = ops->source.multi_regs;
+		bool mem_ref = ops->source.mem_ref;
 
 		if (i == INSN_OP_TARGET) {
 			insn_str = ops->target.raw;
 			multi_regs = ops->target.multi_regs;
+			mem_ref = ops->target.mem_ref;
 		}
 
 		/* Invalidate the register by default */
 		op_loc->reg1 = -1;
 		op_loc->reg2 = -1;
 
-		if (insn_str == NULL)
-			continue;
+		if (insn_str == NULL) {
+			if (!arch__is(arch, "powerpc"))
+				continue;
+		}
 
-		if (strchr(insn_str, arch->objdump.memory_ref_char)) {
+		/*
+		 * For powerpc, call get_powerpc_regs function which extracts the
+		 * required fields for op_loc, ie reg1, reg2, offset from the
+		 * raw instruction.
+		 */
+		if (arch__is(arch, "powerpc")) {
+			op_loc->mem_ref = mem_ref;
+			op_loc->multi_regs = multi_regs;
+			get_powerpc_regs(dl->raw.raw_insn, !i, op_loc);
+		} else if (strchr(insn_str, arch->objdump.memory_ref_char)) {
 			op_loc->mem_ref = true;
 			op_loc->multi_regs = multi_regs;
 			extract_reg_offset(arch, insn_str, op_loc);
@@ -2216,7 +2461,7 @@ static struct annotated_item_stat *annotate_data_stat(struct list_head *head,
 		return NULL;
 
 	istat->name = strdup(name);
-	if (istat->name == NULL) {
+	if ((istat->name == NULL) || (!strlen(istat->name))) {
 		free(istat);
 		return NULL;
 	}
@@ -2230,6 +2475,7 @@ static bool is_stack_operation(struct arch *arch, struct disasm_line *dl)
 	if (arch__is(arch, "x86")) {
 		if (!strncmp(dl->ins.name, "push", 4) ||
 		    !strncmp(dl->ins.name, "pop", 3) ||
+		    !strncmp(dl->ins.name, "call", 4) ||
 		    !strncmp(dl->ins.name, "ret", 3))
 			return true;
 	}
@@ -2313,6 +2559,20 @@ u64 annotate_calc_pcrel(struct map_symbol *ms, u64 ip, int offset,
 	return map__rip_2objdump(ms->map, addr);
 }
 
+static struct debuginfo_cache {
+	struct dso *dso;
+	struct debuginfo *dbg;
+} di_cache;
+
+void debuginfo_cache__delete(void)
+{
+	dso__put(di_cache.dso);
+	di_cache.dso = NULL;
+
+	debuginfo__delete(di_cache.dbg);
+	di_cache.dbg = NULL;
+}
+
 /**
  * hist_entry__get_data_type - find data type for given hist entry
  * @he: hist entry
@@ -2347,6 +2607,27 @@ struct annotated_data_type *hist_entry__get_data_type(struct hist_entry *he)
 		return NULL;
 	}
 
+	/*
+	 * di_cache holds a pair of values, but code below assumes
+	 * di_cache.dso can be compared/updated and di_cache.dbg can be
+	 * read/updated independently from each other. That assumption only
+	 * holds in single threaded code.
+	 */
+	assert(perf_singlethreaded);
+
+	if (map__dso(ms->map) != di_cache.dso) {
+		dso__put(di_cache.dso);
+		di_cache.dso = dso__get(map__dso(ms->map));
+
+		debuginfo__delete(di_cache.dbg);
+		di_cache.dbg = debuginfo__new(dso__long_name(di_cache.dso));
+	}
+
+	if (di_cache.dbg == NULL) {
+		ann_data_stat.no_dbginfo++;
+		return NULL;
+	}
+
 	/* Make sure it has the disasm of the function */
 	if (symbol__annotate(ms, evsel, &arch) < 0) {
 		ann_data_stat.no_insn++;
@@ -2391,6 +2672,7 @@ retry:
 			.ip = ms->sym->start + dl->al.offset,
 			.cpumode = he->cpumode,
 			.op = op_loc,
+			.di = di_cache.dbg,
 		};
 
 		if (!op_loc->mem_ref && op_loc->segment == INSN_SEG_NONE)