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

Pull more perf updates from Thomas Gleixner:
 "A rather large set of perf updates:

  Kernel:

   - Fix various initialization issues

   - Prevent creating [ku]probes for not CAP_SYS_ADMIN users

  Tooling:

   - Show only failing syscalls with 'perf trace --failure' (Arnaldo
     Carvalho de Melo)

            e.g: See what 'openat' syscalls are failing:

        # perf trace --failure -e openat
         762.323 ( 0.007 ms): VideoCapture/4566 openat(dfd: CWD, filename: /dev/video2) = -1 ENOENT No such file or directory
         <SNIP N /dev/videoN open attempts... sigh, where is that improvised camera lid?!? >
         790.228 ( 0.008 ms): VideoCapture/4566 openat(dfd: CWD, filename: /dev/video63) = -1 ENOENT No such file or directory
        ^C#

   - Show information about the event (freq, nr_samples, total
     period/nr_events) in the annotate --tui and --stdio2 'perf
     annotate' output, similar to the first line in the 'perf report
     --tui', but just for the samples for a the annotated symbol
     (Arnaldo Carvalho de Melo)

   - Introduce 'perf version --build-options' to show what features were
     linked, aliased as well as a shorter 'perf -vv' (Jin Yao)

   - Add a "dso_size" sort order (Kim Phillips)

   - Remove redundant ')' in the tracepoint output in 'perf trace'
     (Changbin Du)

   - Synchronize x86's cpufeatures.h, no effect on toolss (Arnaldo
     Carvalho de Melo)

   - Show group details on the title line in the annotate browser and
     'perf annotate --stdio2' output, so that the per-event columns can
     have headers (Arnaldo Carvalho de Melo)

   - Fixup vertical line separating metrics from instructions and
     cleaning unused lines at the bottom, both in the annotate TUI
     browser (Arnaldo Carvalho de Melo)

   - Remove duplicated 'samples' in lost samples warning in
     'perf report' (Arnaldo Carvalho de Melo)

   - Synchronize i915_drm.h, silencing the perf build process,
     automagically adding support for the new DRM_I915_QUERY ioctl
     (Arnaldo Carvalho de Melo)

   - Make auxtrace_queues__add_buffer() allocate struct buffer, from a
     patchkit already applied (Adrian Hunter)

   - Fix the --stdio2/TUI annotate output to include group details, be
     it for a recorded '{a,b,f}' explicit event group or when forcing
     group display using 'perf report --group' for a set of events not
     recorded as a group (Arnaldo Carvalho de Melo)

   - Fix display artifacts in the ui browser (base class for the
     annotate and main report/top TUI browser) related to the extra
     title lines work (Arnaldo Carvalho de Melo)

   - perf auxtrace refactorings, leftovers from a previously partially
     processed patchset (Adrian Hunter)

   - Fix the builtin clang build (Sandipan Das, Arnaldo Carvalho de
     Melo)

   - Synchronize i915_drm.h, silencing a perf build warning and in the
     process automagically adding support for a new ioctl command
     (Arnaldo Carvalho de Melo)

   - Fix a strncpy issue in uprobe tracing"

* 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (36 commits)
  perf/core: Need CAP_SYS_ADMIN to create k/uprobe with perf_event_open()
  tracing/uprobe_event: Fix strncpy corner case
  perf/core: Fix perf_uprobe_init()
  perf/core: Fix perf_kprobe_init()
  perf/core: Fix use-after-free in uprobe_perf_close()
  perf tests clang: Fix function name for clang IR test
  perf clang: Add support for recent clang versions
  perf tools: Fix perf builds with clang support
  perf tools: No need to include namespaces.h in util.h
  perf hists browser: Remove leftover from row returned from refresh
  perf hists browser: Show extra_title_lines in the 'D' debug hotkey
  perf auxtrace: Make auxtrace_queues__add_buffer() do CPU filtering
  tools headers uapi: Synchronize i915_drm.h
  perf report: Remove duplicated 'samples' in lost samples warning
  perf ui browser: Fixup cleaning unused lines at the bottom
  perf annotate browser: Fixup vertical line separating metrics from instructions
  perf annotate: Show group details on the title line
  perf auxtrace: Make auxtrace_queues__add_buffer() allocate struct buffer
  perf/x86/intel: Move regs->flags EXACT bit init
  perf trace: Remove redundant ')'
  ...

13 files changed, 238 insertions, 52 deletions

diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 3a428d7c59b9..fbad8dfbb186 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -17,6 +17,7 @@
 #include "config.h"
 #include "cache.h"
 #include "symbol.h"
+#include "units.h"
 #include "debug.h"
 #include "annotate.h"
 #include "evsel.h"
@@ -2324,7 +2325,7 @@ int symbol__tty_annotate2(struct symbol *sym, struct map *map,
 	struct dso *dso = map->dso;
 	struct rb_root source_line = RB_ROOT;
 	struct annotation_options opts = annotation__default_options;
-	const char *ev_name = perf_evsel__name(evsel);
+	struct annotation *notes = symbol__annotation(sym);
 	char buf[1024];
 
 	if (symbol__annotate2(sym, map, evsel, &opts, NULL) < 0)
@@ -2336,12 +2337,8 @@ int symbol__tty_annotate2(struct symbol *sym, struct map *map,
 		print_summary(&source_line, dso->long_name);
 	}
 
-	if (perf_evsel__is_group_event(evsel)) {
-		perf_evsel__group_desc(evsel, buf, sizeof(buf));
-		ev_name = buf;
-	}
-
-	fprintf(stdout, "%s() %s\nEvent: %s\n\n", sym->name, dso->long_name, ev_name);
+	annotation__scnprintf_samples_period(notes, buf, sizeof(buf), evsel);
+	fprintf(stdout, "%s\n%s() %s\n", buf, sym->name, dso->long_name);
 	symbol__annotate_fprintf2(sym, stdout);
 
 	annotated_source__purge(symbol__annotation(sym)->src);
@@ -2597,6 +2594,46 @@ out_free_offsets:
 	return -1;
 }
 
+int __annotation__scnprintf_samples_period(struct annotation *notes,
+					   char *bf, size_t size,
+					   struct perf_evsel *evsel,
+					   bool show_freq)
+{
+	const char *ev_name = perf_evsel__name(evsel);
+	char buf[1024], ref[30] = " show reference callgraph, ";
+	char sample_freq_str[64] = "";
+	unsigned long nr_samples = 0;
+	int nr_members = 1;
+	bool enable_ref = false;
+	u64 nr_events = 0;
+	char unit;
+	int i;
+
+	if (perf_evsel__is_group_event(evsel)) {
+		perf_evsel__group_desc(evsel, buf, sizeof(buf));
+		ev_name = buf;
+                nr_members = evsel->nr_members;
+	}
+
+	for (i = 0; i < nr_members; i++) {
+		struct sym_hist *ah = annotation__histogram(notes, evsel->idx + i);
+
+		nr_samples += ah->nr_samples;
+		nr_events  += ah->period;
+	}
+
+	if (symbol_conf.show_ref_callgraph && strstr(ev_name, "call-graph=no"))
+		enable_ref = true;
+
+	if (show_freq)
+		scnprintf(sample_freq_str, sizeof(sample_freq_str), " %d Hz,", evsel->attr.sample_freq);
+
+	nr_samples = convert_unit(nr_samples, &unit);
+	return scnprintf(bf, size, "Samples: %lu%c of event%s '%s',%s%sEvent count (approx.): %" PRIu64,
+			 nr_samples, unit, evsel->nr_members > 1 ? "s" : "",
+			 ev_name, sample_freq_str, enable_ref ? ref : " ", nr_events);
+}
+
 #define ANNOTATION__CFG(n) \
 	{ .name = #n, .value = &annotation__default_options.n, }
 
diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h
index ff7e3df31efa..db8d09bea07e 100644
--- a/tools/perf/util/annotate.h
+++ b/tools/perf/util/annotate.h
@@ -151,6 +151,18 @@ double annotation_line__max_percent(struct annotation_line *al, struct annotatio
 void annotation_line__write(struct annotation_line *al, struct annotation *notes,
 			    struct annotation_write_ops *ops);
 
+int __annotation__scnprintf_samples_period(struct annotation *notes,
+					   char *bf, size_t size,
+					   struct perf_evsel *evsel,
+					   bool show_freq);
+
+static inline int annotation__scnprintf_samples_period(struct annotation *notes,
+						       char *bf, size_t size,
+						       struct perf_evsel *evsel)
+{
+	return __annotation__scnprintf_samples_period(notes, bf, size, evsel, true);
+}
+
 int disasm_line__scnprintf(struct disasm_line *dl, char *bf, size_t size, bool raw);
 size_t disasm__fprintf(struct list_head *head, FILE *fp);
 void symbol__calc_percent(struct symbol *sym, struct perf_evsel *evsel);
diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c
index fb357a00dd86..857de69a5361 100644
--- a/tools/perf/util/auxtrace.c
+++ b/tools/perf/util/auxtrace.c
@@ -302,13 +302,27 @@ static int auxtrace_queues__split_buffer(struct auxtrace_queues *queues,
 	return 0;
 }
 
+static bool filter_cpu(struct perf_session *session, int cpu)
+{
+	unsigned long *cpu_bitmap = session->itrace_synth_opts->cpu_bitmap;
+
+	return cpu_bitmap && cpu != -1 && !test_bit(cpu, cpu_bitmap);
+}
+
 static int auxtrace_queues__add_buffer(struct auxtrace_queues *queues,
 				       struct perf_session *session,
 				       unsigned int idx,
 				       struct auxtrace_buffer *buffer,
 				       struct auxtrace_buffer **buffer_ptr)
 {
-	int err;
+	int err = -ENOMEM;
+
+	if (filter_cpu(session, buffer->cpu))
+		return 0;
+
+	buffer = memdup(buffer, sizeof(*buffer));
+	if (!buffer)
+		return -ENOMEM;
 
 	if (session->one_mmap) {
 		buffer->data = buffer->data_offset - session->one_mmap_offset +
@@ -316,31 +330,28 @@ static int auxtrace_queues__add_buffer(struct auxtrace_queues *queues,
 	} else if (perf_data__is_pipe(session->data)) {
 		buffer->data = auxtrace_copy_data(buffer->size, session);
 		if (!buffer->data)
-			return -ENOMEM;
+			goto out_free;
 		buffer->data_needs_freeing = true;
 	} else if (BITS_PER_LONG == 32 &&
 		   buffer->size > BUFFER_LIMIT_FOR_32_BIT) {
 		err = auxtrace_queues__split_buffer(queues, idx, buffer);
 		if (err)
-			return err;
+			goto out_free;
 	}
 
 	err = auxtrace_queues__queue_buffer(queues, idx, buffer);
 	if (err)
-		return err;
+		goto out_free;
 
 	/* FIXME: Doesn't work for split buffer */
 	if (buffer_ptr)
 		*buffer_ptr = buffer;
 
 	return 0;
-}
 
-static bool filter_cpu(struct perf_session *session, int cpu)
-{
-	unsigned long *cpu_bitmap = session->itrace_synth_opts->cpu_bitmap;
-
-	return cpu_bitmap && cpu != -1 && !test_bit(cpu, cpu_bitmap);
+out_free:
+	auxtrace_buffer__free(buffer);
+	return err;
 }
 
 int auxtrace_queues__add_event(struct auxtrace_queues *queues,
@@ -348,36 +359,19 @@ int auxtrace_queues__add_event(struct auxtrace_queues *queues,
 			       union perf_event *event, off_t data_offset,
 			       struct auxtrace_buffer **buffer_ptr)
 {
-	struct auxtrace_buffer *buffer;
-	unsigned int idx;
-	int err;
-
-	if (filter_cpu(session, event->auxtrace.cpu))
-		return 0;
-
-	buffer = zalloc(sizeof(struct auxtrace_buffer));
-	if (!buffer)
-		return -ENOMEM;
-
-	buffer->pid = -1;
-	buffer->tid = event->auxtrace.tid;
-	buffer->cpu = event->auxtrace.cpu;
-	buffer->data_offset = data_offset;
-	buffer->offset = event->auxtrace.offset;
-	buffer->reference = event->auxtrace.reference;
-	buffer->size = event->auxtrace.size;
-	idx = event->auxtrace.idx;
-
-	err = auxtrace_queues__add_buffer(queues, session, idx, buffer,
-					  buffer_ptr);
-	if (err)
-		goto out_err;
-
-	return 0;
+	struct auxtrace_buffer buffer = {
+		.pid = -1,
+		.tid = event->auxtrace.tid,
+		.cpu = event->auxtrace.cpu,
+		.data_offset = data_offset,
+		.offset = event->auxtrace.offset,
+		.reference = event->auxtrace.reference,
+		.size = event->auxtrace.size,
+	};
+	unsigned int idx = event->auxtrace.idx;
 
-out_err:
-	auxtrace_buffer__free(buffer);
-	return err;
+	return auxtrace_queues__add_buffer(queues, session, idx, &buffer,
+					   buffer_ptr);
 }
 
 static int auxtrace_queues__add_indexed_event(struct auxtrace_queues *queues,
diff --git a/tools/perf/util/c++/clang-test.cpp b/tools/perf/util/c++/clang-test.cpp
index a4014d786676..7b042a5ebc68 100644
--- a/tools/perf/util/c++/clang-test.cpp
+++ b/tools/perf/util/c++/clang-test.cpp
@@ -41,7 +41,7 @@ int test__clang_to_IR(void)
 	if (!M)
 		return -1;
 	for (llvm::Function& F : *M)
-		if (F.getName() == "bpf_func__SyS_epoll_wait")
+		if (F.getName() == "bpf_func__SyS_epoll_pwait")
 			return 0;
 	return -1;
 }
diff --git a/tools/perf/util/c++/clang.cpp b/tools/perf/util/c++/clang.cpp
index 1bfc946e37dc..bf31ceab33bd 100644
--- a/tools/perf/util/c++/clang.cpp
+++ b/tools/perf/util/c++/clang.cpp
@@ -9,6 +9,7 @@
  * Copyright (C) 2016 Huawei Inc.
  */
 
+#include "clang/Basic/Version.h"
 #include "clang/CodeGen/CodeGenAction.h"
 #include "clang/Frontend/CompilerInvocation.h"
 #include "clang/Frontend/CompilerInstance.h"
@@ -58,7 +59,8 @@ createCompilerInvocation(llvm::opt::ArgStringList CFlags, StringRef& Path,
 
 	FrontendOptions& Opts = CI->getFrontendOpts();
 	Opts.Inputs.clear();
-	Opts.Inputs.emplace_back(Path, IK_C);
+	Opts.Inputs.emplace_back(Path,
+			FrontendOptions::getInputKindForExtension("c"));
 	return CI;
 }
 
@@ -71,10 +73,17 @@ getModuleFromSource(llvm::opt::ArgStringList CFlags,
 
 	Clang.setVirtualFileSystem(&*VFS);
 
+#if CLANG_VERSION_MAJOR < 4
 	IntrusiveRefCntPtr<CompilerInvocation> CI =
 		createCompilerInvocation(std::move(CFlags), Path,
 					 Clang.getDiagnostics());
 	Clang.setInvocation(&*CI);
+#else
+	std::shared_ptr<CompilerInvocation> CI(
+		createCompilerInvocation(std::move(CFlags), Path,
+					 Clang.getDiagnostics()));
+	Clang.setInvocation(CI);
+#endif
 
 	std::unique_ptr<CodeGenAction> Act(new EmitLLVMOnlyAction(&*LLVMCtx));
 	if (!Clang.ExecuteAction(*Act))
diff --git a/tools/perf/util/dwarf-aux.c b/tools/perf/util/dwarf-aux.c
index f5acda13dcfa..7eb7de5aee44 100644
--- a/tools/perf/util/dwarf-aux.c
+++ b/tools/perf/util/dwarf-aux.c
@@ -979,7 +979,7 @@ int die_get_varname(Dwarf_Die *vr_die, struct strbuf *buf)
 	return ret < 0 ? ret : strbuf_addf(buf, "\t%s", dwarf_diename(vr_die));
 }
 
-#ifdef HAVE_DWARF_GETLOCATIONS
+#ifdef HAVE_DWARF_GETLOCATIONS_SUPPORT
 /**
  * die_get_var_innermost_scope - Get innermost scope range of given variable DIE
  * @sp_die: a subprogram DIE
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index 7d968892ee39..4d602fba40b2 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -6,6 +6,7 @@
 #include "session.h"
 #include "namespaces.h"
 #include "sort.h"
+#include "units.h"
 #include "evlist.h"
 #include "evsel.h"
 #include "annotate.h"
@@ -14,6 +15,7 @@
 #include "ui/progress.h"
 #include <errno.h>
 #include <math.h>
+#include <inttypes.h>
 #include <sys/param.h>
 
 static bool hists__filter_entry_by_dso(struct hists *hists,
@@ -2454,6 +2456,85 @@ u64 hists__total_period(struct hists *hists)
 		hists->stats.total_period;
 }
 
+int __hists__scnprintf_title(struct hists *hists, char *bf, size_t size, bool show_freq)
+{
+	char unit;
+	int printed;
+	const struct dso *dso = hists->dso_filter;
+	const struct thread *thread = hists->thread_filter;
+	int socket_id = hists->socket_filter;
+	unsigned long nr_samples = hists->stats.nr_events[PERF_RECORD_SAMPLE];
+	u64 nr_events = hists->stats.total_period;
+	struct perf_evsel *evsel = hists_to_evsel(hists);
+	const char *ev_name = perf_evsel__name(evsel);
+	char buf[512], sample_freq_str[64] = "";
+	size_t buflen = sizeof(buf);
+	char ref[30] = " show reference callgraph, ";
+	bool enable_ref = false;
+
+	if (symbol_conf.filter_relative) {
+		nr_samples = hists->stats.nr_non_filtered_samples;
+		nr_events = hists->stats.total_non_filtered_period;
+	}
+
+	if (perf_evsel__is_group_event(evsel)) {
+		struct perf_evsel *pos;
+
+		perf_evsel__group_desc(evsel, buf, buflen);
+		ev_name = buf;
+
+		for_each_group_member(pos, evsel) {
+			struct hists *pos_hists = evsel__hists(pos);
+
+			if (symbol_conf.filter_relative) {
+				nr_samples += pos_hists->stats.nr_non_filtered_samples;
+				nr_events += pos_hists->stats.total_non_filtered_period;
+			} else {
+				nr_samples += pos_hists->stats.nr_events[PERF_RECORD_SAMPLE];
+				nr_events += pos_hists->stats.total_period;
+			}
+		}
+	}
+
+	if (symbol_conf.show_ref_callgraph &&
+	    strstr(ev_name, "call-graph=no"))
+		enable_ref = true;
+
+	if (show_freq)
+		scnprintf(sample_freq_str, sizeof(sample_freq_str), " %d Hz,", evsel->attr.sample_freq);
+
+	nr_samples = convert_unit(nr_samples, &unit);
+	printed = scnprintf(bf, size,
+			   "Samples: %lu%c of event%s '%s',%s%sEvent count (approx.): %" PRIu64,
+			   nr_samples, unit, evsel->nr_members > 1 ? "s" : "",
+			   ev_name, sample_freq_str, enable_ref ? ref : " ", nr_events);
+
+
+	if (hists->uid_filter_str)
+		printed += snprintf(bf + printed, size - printed,
+				    ", UID: %s", hists->uid_filter_str);
+	if (thread) {
+		if (hists__has(hists, thread)) {
+			printed += scnprintf(bf + printed, size - printed,
+				    ", Thread: %s(%d)",
+				     (thread->comm_set ? thread__comm_str(thread) : ""),
+				    thread->tid);
+		} else {
+			printed += scnprintf(bf + printed, size - printed,
+				    ", Thread: %s",
+				     (thread->comm_set ? thread__comm_str(thread) : ""));
+		}
+	}
+	if (dso)
+		printed += scnprintf(bf + printed, size - printed,
+				    ", DSO: %s", dso->short_name);
+	if (socket_id > -1)
+		printed += scnprintf(bf + printed, size - printed,
+				    ", Processor Socket: %d", socket_id);
+
+	return printed;
+}
+
 int parse_filter_percentage(const struct option *opt __maybe_unused,
 			    const char *arg, int unset __maybe_unused)
 {
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index e869cad4d89f..fbabfd8a215d 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -61,6 +61,7 @@ enum hist_column {
 	HISTC_SRCLINE_TO,
 	HISTC_TRACE,
 	HISTC_SYM_SIZE,
+	HISTC_DSO_SIZE,
 	HISTC_NR_COLS, /* Last entry */
 };
 
@@ -503,5 +504,11 @@ int __hpp__slsmg_color_printf(struct perf_hpp *hpp, const char *fmt, ...);
 int __hist_entry__snprintf(struct hist_entry *he, struct perf_hpp *hpp,
 			   struct perf_hpp_list *hpp_list);
 int hists__fprintf_headers(struct hists *hists, FILE *fp);
+int __hists__scnprintf_title(struct hists *hists, char *bf, size_t size, bool show_freq);
+
+static inline int hists__scnprintf_title(struct hists *hists, char *bf, size_t size)
+{
+	return __hists__scnprintf_title(hists, bf, size, true);
+}
 
 #endif	/* __PERF_HIST_H */
diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h
index edeb7291c8e1..0e9bbe01b0ab 100644
--- a/tools/perf/util/map.h
+++ b/tools/perf/util/map.h
@@ -103,6 +103,10 @@ static inline u64 identity__map_ip(struct map *map __maybe_unused, u64 ip)
 	return ip;
 }
 
+static inline size_t map__size(const struct map *map)
+{
+	return map->end - map->start;
+}
 
 /* rip/ip <-> addr suitable for passing to `objdump --start-address=` */
 u64 map__rip_2objdump(struct map *map, u64 rip);
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index c71ced7db152..f4a7a437ee87 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -1591,7 +1591,7 @@ static void perf_session__warn_about_errors(const struct perf_session *session)
 		drop_rate = (double)stats->total_lost_samples /
 			    (double) (stats->nr_events[PERF_RECORD_SAMPLE] + stats->total_lost_samples);
 		if (drop_rate > 0.05) {
-			ui__warning("Processed %" PRIu64 " samples and lost %3.2f%% samples!\n\n",
+			ui__warning("Processed %" PRIu64 " samples and lost %3.2f%%!\n\n",
 				    stats->nr_events[PERF_RECORD_SAMPLE] + stats->total_lost_samples,
 				    drop_rate * 100.0);
 		}
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index e8514f651865..26a68dfd8a4f 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -1545,6 +1545,46 @@ struct sort_entry sort_sym_size = {
 	.se_width_idx	= HISTC_SYM_SIZE,
 };
 
+/* --sort dso_size */
+
+static int64_t _sort__dso_size_cmp(struct map *map_l, struct map *map_r)
+{
+	int64_t size_l = map_l != NULL ? map__size(map_l) : 0;
+	int64_t size_r = map_r != NULL ? map__size(map_r) : 0;
+
+	return size_l < size_r ? -1 :
+		size_l == size_r ? 0 : 1;
+}
+
+static int64_t
+sort__dso_size_cmp(struct hist_entry *left, struct hist_entry *right)
+{
+	return _sort__dso_size_cmp(right->ms.map, left->ms.map);
+}
+
+static int _hist_entry__dso_size_snprintf(struct map *map, char *bf,
+					  size_t bf_size, unsigned int width)
+{
+	if (map && map->dso)
+		return repsep_snprintf(bf, bf_size, "%*d", width,
+				       map__size(map));
+
+	return repsep_snprintf(bf, bf_size, "%*s", width, "unknown");
+}
+
+static int hist_entry__dso_size_snprintf(struct hist_entry *he, char *bf,
+					 size_t size, unsigned int width)
+{
+	return _hist_entry__dso_size_snprintf(he->ms.map, bf, size, width);
+}
+
+struct sort_entry sort_dso_size = {
+	.se_header	= "DSO size",
+	.se_cmp		= sort__dso_size_cmp,
+	.se_snprintf	= hist_entry__dso_size_snprintf,
+	.se_width_idx	= HISTC_DSO_SIZE,
+};
+
 
 struct sort_dimension {
 	const char		*name;
@@ -1569,6 +1609,7 @@ static struct sort_dimension common_sort_dimensions[] = {
 	DIM(SORT_TRANSACTION, "transaction", sort_transaction),
 	DIM(SORT_TRACE, "trace", sort_trace),
 	DIM(SORT_SYM_SIZE, "symbol_size", sort_sym_size),
+	DIM(SORT_DSO_SIZE, "dso_size", sort_dso_size),
 	DIM(SORT_CGROUP_ID, "cgroup_id", sort_cgroup_id),
 };
 
diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h
index f5901c10a563..035b62e2c60b 100644
--- a/tools/perf/util/sort.h
+++ b/tools/perf/util/sort.h
@@ -220,6 +220,7 @@ enum sort_type {
 	SORT_TRANSACTION,
 	SORT_TRACE,
 	SORT_SYM_SIZE,
+	SORT_DSO_SIZE,
 	SORT_CGROUP_ID,
 
 	/* branch stack specific sort keys */
diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h
index 9496365da3d7..c9626c206208 100644
--- a/tools/perf/util/util.h
+++ b/tools/perf/util/util.h
@@ -11,8 +11,7 @@
 #include <stdlib.h>
 #include <stdarg.h>
 #include <linux/compiler.h>
-#include <linux/types.h>
-#include "namespaces.h"
+#include <sys/types.h>
 
 /* General helper functions */
 void usage(const char *err) __noreturn;
@@ -26,6 +25,7 @@ static inline void *zalloc(size_t size)
 #define zfree(ptr) ({ free(*ptr); *ptr = NULL; })
 
 struct dirent;
+struct nsinfo;
 struct strlist;
 
 int mkdir_p(char *path, mode_t mode);