Merge tag 'perf-core-for-mingo-20160505' 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:

- Order output of 'perf trace --summary' better, now the threads will
  appear ascending order of number of events, and then, for each, in
  descending order of syscalls by the time spent in the syscalls, so
  that the last page produced can be the one about the most interesting
  thread straced, suggested by Milian Wolff (Arnaldo Carvalho de Melo)

- Do not show the runtime_ms for a thread when not collecting it, that
  is done so far only with 'perf trace --sched' (Arnaldo Carvalho de Melo)

- Fix kallsyms perf test on ppc64le (Naveen N. Rao)

Infrastructure changes:

- Move global variables related to presence of some keys in the sort order to a
  per hist struct, to allow code like the hists browser to work with multiple
  hists with different lists of columns (Jiri Olsa)

- Add support for generating bpf prologue in powerpc (Naveen N. Rao)

- Fix kprobe and kretprobe handling with kallsyms on ppc64le (Naveen N. Rao)

- evlist mmap changes, prep work for supporting reading backwards (Wang Nan)

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

28 files changed, 382 insertions, 154 deletions

diff --git a/tools/perf/arch/powerpc/Makefile b/tools/perf/arch/powerpc/Makefile
index 56e05f126ad8..cc3930904d68 100644
--- a/tools/perf/arch/powerpc/Makefile
+++ b/tools/perf/arch/powerpc/Makefile
@@ -3,4 +3,5 @@ PERF_HAVE_DWARF_REGS := 1
 endif
 
 HAVE_KVM_STAT_SUPPORT := 1
+PERF_HAVE_ARCH_REGS_QUERY_REGISTER_OFFSET := 1
 PERF_HAVE_JITDUMP := 1
diff --git a/tools/perf/arch/powerpc/util/dwarf-regs.c b/tools/perf/arch/powerpc/util/dwarf-regs.c
index 733151cdf46e..41bdf9530d82 100644
--- a/tools/perf/arch/powerpc/util/dwarf-regs.c
+++ b/tools/perf/arch/powerpc/util/dwarf-regs.c
@@ -10,19 +10,26 @@
  */
 
 #include <stddef.h>
+#include <errno.h>
+#include <string.h>
 #include <dwarf-regs.h>
-
+#include <linux/ptrace.h>
+#include <linux/kernel.h>
+#include "util.h"
 
 struct pt_regs_dwarfnum {
 	const char *name;
 	unsigned int dwarfnum;
+	unsigned int ptregs_offset;
 };
 
-#define STR(s) #s
-#define REG_DWARFNUM_NAME(r, num) {.name = r, .dwarfnum = num}
-#define GPR_DWARFNUM_NAME(num)	\
-	{.name = STR(%gpr##num), .dwarfnum = num}
-#define REG_DWARFNUM_END {.name = NULL, .dwarfnum = 0}
+#define REG_DWARFNUM_NAME(r, num)					\
+		{.name = STR(%)STR(r), .dwarfnum = num,			\
+		.ptregs_offset = offsetof(struct pt_regs, r)}
+#define GPR_DWARFNUM_NAME(num)						\
+		{.name = STR(%gpr##num), .dwarfnum = num,		\
+		.ptregs_offset = offsetof(struct pt_regs, gpr[num])}
+#define REG_DWARFNUM_END {.name = NULL, .dwarfnum = 0, .ptregs_offset = 0}
 
 /*
  * Reference:
@@ -61,12 +68,12 @@ static const struct pt_regs_dwarfnum regdwarfnum_table[] = {
 	GPR_DWARFNUM_NAME(29),
 	GPR_DWARFNUM_NAME(30),
 	GPR_DWARFNUM_NAME(31),
-	REG_DWARFNUM_NAME("%msr",   66),
-	REG_DWARFNUM_NAME("%ctr",   109),
-	REG_DWARFNUM_NAME("%link",  108),
-	REG_DWARFNUM_NAME("%xer",   101),
-	REG_DWARFNUM_NAME("%dar",   119),
-	REG_DWARFNUM_NAME("%dsisr", 118),
+	REG_DWARFNUM_NAME(msr,   66),
+	REG_DWARFNUM_NAME(ctr,   109),
+	REG_DWARFNUM_NAME(link,  108),
+	REG_DWARFNUM_NAME(xer,   101),
+	REG_DWARFNUM_NAME(dar,   119),
+	REG_DWARFNUM_NAME(dsisr, 118),
 	REG_DWARFNUM_END,
 };
 
@@ -86,3 +93,12 @@ const char *get_arch_regstr(unsigned int n)
 			return roff->name;
 	return NULL;
 }
+
+int regs_query_register_offset(const char *name)
+{
+	const struct pt_regs_dwarfnum *roff;
+	for (roff = regdwarfnum_table; roff->name != NULL; roff++)
+		if (!strcmp(roff->name, name))
+			return roff->ptregs_offset;
+	return -EINVAL;
+}
diff --git a/tools/perf/arch/powerpc/util/sym-handling.c b/tools/perf/arch/powerpc/util/sym-handling.c
index bbc1a50768dd..c6d0f91731a1 100644
--- a/tools/perf/arch/powerpc/util/sym-handling.c
+++ b/tools/perf/arch/powerpc/util/sym-handling.c
@@ -19,12 +19,6 @@ bool elf__needs_adjust_symbols(GElf_Ehdr ehdr)
 	       ehdr.e_type == ET_DYN;
 }
 
-#if defined(_CALL_ELF) && _CALL_ELF == 2
-void arch__elf_sym_adjust(GElf_Sym *sym)
-{
-	sym->st_value += PPC64_LOCAL_ENTRY_OFFSET(sym->st_other);
-}
-#endif
 #endif
 
 #if !defined(_CALL_ELF) || _CALL_ELF != 2
@@ -65,18 +59,45 @@ bool arch__prefers_symtab(void)
 	return true;
 }
 
+#ifdef HAVE_LIBELF_SUPPORT
+void arch__sym_update(struct symbol *s, GElf_Sym *sym)
+{
+	s->arch_sym = sym->st_other;
+}
+#endif
+
 #define PPC64LE_LEP_OFFSET	8
 
 void arch__fix_tev_from_maps(struct perf_probe_event *pev,
-			     struct probe_trace_event *tev, struct map *map)
+			     struct probe_trace_event *tev, struct map *map,
+			     struct symbol *sym)
 {
+	int lep_offset;
+
 	/*
-	 * ppc64 ABIv2 local entry point is currently always 2 instructions
-	 * (8 bytes) after the global entry point.
+	 * When probing at a function entry point, we normally always want the
+	 * LEP since that catches calls to the function through both the GEP and
+	 * the LEP. Hence, we would like to probe at an offset of 8 bytes if
+	 * the user only specified the function entry.
+	 *
+	 * However, if the user specifies an offset, we fall back to using the
+	 * GEP since all userspace applications (objdump/readelf) show function
+	 * disassembly with offsets from the GEP.
+	 *
+	 * In addition, we shouldn't specify an offset for kretprobes.
 	 */
-	if (!pev->uprobes && map->dso->symtab_type == DSO_BINARY_TYPE__KALLSYMS) {
-		tev->point.address += PPC64LE_LEP_OFFSET;
+	if (pev->point.offset || pev->point.retprobe || !map || !sym)
+		return;
+
+	lep_offset = PPC64_LOCAL_ENTRY_OFFSET(sym->arch_sym);
+
+	if (map->dso->symtab_type == DSO_BINARY_TYPE__KALLSYMS)
 		tev->point.offset += PPC64LE_LEP_OFFSET;
+	else if (lep_offset) {
+		if (pev->uprobes)
+			tev->point.address += lep_offset;
+		else
+			tev->point.offset += lep_offset;
 	}
 }
 #endif
diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c
index 8053a8ceefda..9ce354f469dc 100644
--- a/tools/perf/builtin-diff.c
+++ b/tools/perf/builtin-diff.c
@@ -428,7 +428,7 @@ static void hists__baseline_only(struct hists *hists)
 	struct rb_root *root;
 	struct rb_node *next;
 
-	if (sort__need_collapse)
+	if (hists__has(hists, need_collapse))
 		root = &hists->entries_collapsed;
 	else
 		root = hists->entries_in;
@@ -450,7 +450,7 @@ static void hists__precompute(struct hists *hists)
 	struct rb_root *root;
 	struct rb_node *next;
 
-	if (sort__need_collapse)
+	if (hists__has(hists, need_collapse))
 		root = &hists->entries_collapsed;
 	else
 		root = hists->entries_in;
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 8d9b88af901d..87d40e3c4078 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -234,7 +234,7 @@ static int report__setup_sample_type(struct report *rep)
 		sample_type |= PERF_SAMPLE_BRANCH_STACK;
 
 	if (!is_pipe && !(sample_type & PERF_SAMPLE_CALLCHAIN)) {
-		if (sort__has_parent) {
+		if (perf_hpp_list.parent) {
 			ui__error("Selected --sort parent, but no "
 				    "callchain data. Did you call "
 				    "'perf record' without -g?\n");
@@ -936,7 +936,7 @@ repeat:
 			goto error;
 		}
 
-		sort__need_collapse = true;
+		perf_hpp_list.need_collapse = true;
 	}
 
 	/* Force tty output for header output and per-thread stat. */
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index da18517b1d40..1793da585676 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -688,7 +688,7 @@ static int hist_iter__top_callback(struct hist_entry_iter *iter,
 	struct hist_entry *he = iter->he;
 	struct perf_evsel *evsel = iter->evsel;
 
-	if (sort__has_sym && single)
+	if (perf_hpp_list.sym && single)
 		perf_top__record_precise_ip(top, he, evsel->idx, al->addr);
 
 	hist__account_cycles(iter->sample->branch_stack, al, iter->sample,
@@ -919,7 +919,7 @@ out_err:
 
 static int callchain_param__setup_sample_type(struct callchain_param *callchain)
 {
-	if (!sort__has_sym) {
+	if (!perf_hpp_list.sym) {
 		if (callchain->enabled) {
 			ui__error("Selected -g but \"sym\" not present in --sort/-s.");
 			return -EINVAL;
@@ -962,7 +962,7 @@ static int __cmd_top(struct perf_top *top)
 	machine__synthesize_threads(&top->session->machines.host, &opts->target,
 				    top->evlist->threads, false, opts->proc_map_timeout);
 
-	if (sort__has_socket) {
+	if (perf_hpp_list.socket) {
 		ret = perf_env__read_cpu_topology_map(&perf_env);
 		if (ret < 0)
 			goto out_err_cpu_topo;
@@ -1255,7 +1255,7 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused)
 
 	sort__mode = SORT_MODE__TOP;
 	/* display thread wants entries to be collapsed in a different tree */
-	sort__need_collapse = 1;
+	perf_hpp_list.need_collapse = 1;
 
 	if (top.use_stdio)
 		use_browser = 0;
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 9e38fe973f0c..66aa2a00414b 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -36,6 +36,7 @@
 #include "util/bpf-loader.h"
 #include "callchain.h"
 #include "syscalltbl.h"
+#include "rb_resort.h"
 
 #include <libaudit.h> /* FIXME: Still needed for audit_errno_to_name */
 #include <stdlib.h>
@@ -2784,15 +2785,29 @@ static size_t trace__fprintf_threads_header(FILE *fp)
 	return printed;
 }
 
+DEFINE_RESORT_RB(syscall_stats, a->msecs > b->msecs,
+	struct stats 	*stats;
+	double		msecs;
+	int		syscall;
+)
+{
+	struct int_node *source = rb_entry(nd, struct int_node, rb_node);
+	struct stats *stats = source->priv;
+
+	entry->syscall = source->i;
+	entry->stats   = stats;
+	entry->msecs   = stats ? (u64)stats->n * (avg_stats(stats) / NSEC_PER_MSEC) : 0;
+}
+
 static size_t thread__dump_stats(struct thread_trace *ttrace,
 				 struct trace *trace, FILE *fp)
 {
-	struct stats *stats;
 	size_t printed = 0;
 	struct syscall *sc;
-	struct int_node *inode = intlist__first(ttrace->syscall_stats);
+	struct rb_node *nd;
+	DECLARE_RESORT_RB_INTLIST(syscall_stats, ttrace->syscall_stats);
 
-	if (inode == NULL)
+	if (syscall_stats == NULL)
 		return 0;
 
 	printed += fprintf(fp, "\n");
@@ -2801,9 +2816,8 @@ static size_t thread__dump_stats(struct thread_trace *ttrace,
 	printed += fprintf(fp, "                               (msec)    (msec)    (msec)    (msec)        (%%)\n");
 	printed += fprintf(fp, "   --------------- -------- --------- --------- --------- ---------     ------\n");
 
-	/* each int_node is a syscall */
-	while (inode) {
-		stats = inode->priv;
+	resort_rb__for_each(nd, syscall_stats) {
+		struct stats *stats = syscall_stats_entry->stats;
 		if (stats) {
 			double min = (double)(stats->min) / NSEC_PER_MSEC;
 			double max = (double)(stats->max) / NSEC_PER_MSEC;
@@ -2814,34 +2828,23 @@ static size_t thread__dump_stats(struct thread_trace *ttrace,
 			pct = avg ? 100.0 * stddev_stats(stats)/avg : 0.0;
 			avg /= NSEC_PER_MSEC;
 
-			sc = &trace->syscalls.table[inode->i];
+			sc = &trace->syscalls.table[syscall_stats_entry->syscall];
 			printed += fprintf(fp, "   %-15s", sc->name);
 			printed += fprintf(fp, " %8" PRIu64 " %9.3f %9.3f %9.3f",
-					   n, avg * n, min, avg);
+					   n, syscall_stats_entry->msecs, min, avg);
 			printed += fprintf(fp, " %9.3f %9.2f%%\n", max, pct);
 		}
-
-		inode = intlist__next(inode);
 	}
 
+	resort_rb__delete(syscall_stats);
 	printed += fprintf(fp, "\n\n");
 
 	return printed;
 }
 
-/* struct used to pass data to per-thread function */
-struct summary_data {
-	FILE *fp;
-	struct trace *trace;
-	size_t printed;
-};
-
-static int trace__fprintf_one_thread(struct thread *thread, void *priv)
+static size_t trace__fprintf_thread(FILE *fp, struct thread *thread, struct trace *trace)
 {
-	struct summary_data *data = priv;
-	FILE *fp = data->fp;
-	size_t printed = data->printed;
-	struct trace *trace = data->trace;
+	size_t printed = 0;
 	struct thread_trace *ttrace = thread__priv(thread);
 	double ratio;
 
@@ -2857,25 +2860,45 @@ static int trace__fprintf_one_thread(struct thread *thread, void *priv)
 		printed += fprintf(fp, ", %lu majfaults", ttrace->pfmaj);
 	if (ttrace->pfmin)
 		printed += fprintf(fp, ", %lu minfaults", ttrace->pfmin);
-	printed += fprintf(fp, ", %.3f msec\n", ttrace->runtime_ms);
+	if (trace->sched)
+		printed += fprintf(fp, ", %.3f msec\n", ttrace->runtime_ms);
+	else if (fputc('\n', fp) != EOF)
+		++printed;
+
 	printed += thread__dump_stats(ttrace, trace, fp);
 
-	data->printed += printed;
+	return printed;
+}
+
+static unsigned long thread__nr_events(struct thread_trace *ttrace)
+{
+	return ttrace ? ttrace->nr_events : 0;
+}
 
-	return 0;
+DEFINE_RESORT_RB(threads, (thread__nr_events(a->thread->priv) < thread__nr_events(b->thread->priv)),
+	struct thread *thread;
+)
+{
+	entry->thread = rb_entry(nd, struct thread, rb_node);
 }
 
 static size_t trace__fprintf_thread_summary(struct trace *trace, FILE *fp)
 {
-	struct summary_data data = {
-		.fp = fp,
-		.trace = trace
-	};
-	data.printed = trace__fprintf_threads_header(fp);
+	DECLARE_RESORT_RB_MACHINE_THREADS(threads, trace->host);
+	size_t printed = trace__fprintf_threads_header(fp);
+	struct rb_node *nd;
+
+	if (threads == NULL) {
+		fprintf(fp, "%s", "Error sorting output by nr_events!\n");
+		return 0;
+	}
+
+	resort_rb__for_each(nd, threads)
+		printed += trace__fprintf_thread(fp, threads_entry->thread, trace);
 
-	machine__for_each_thread(trace->host, trace__fprintf_one_thread, &data);
+	resort_rb__delete(threads);
 
-	return data.printed;
+	return printed;
 }
 
 static int trace__set_duration(const struct option *opt, const char *str,
diff --git a/tools/perf/tests/hists_common.c b/tools/perf/tests/hists_common.c
index f55f4bd47932..6b21746d6eec 100644
--- a/tools/perf/tests/hists_common.c
+++ b/tools/perf/tests/hists_common.c
@@ -161,7 +161,7 @@ void print_hists_in(struct hists *hists)
 	struct rb_root *root;
 	struct rb_node *node;
 
-	if (sort__need_collapse)
+	if (hists__has(hists, need_collapse))
 		root = &hists->entries_collapsed;
 	else
 		root = hists->entries_in;
diff --git a/tools/perf/tests/hists_cumulate.c b/tools/perf/tests/hists_cumulate.c
index 4a2bbff9b1ee..a9e3db3afac4 100644
--- a/tools/perf/tests/hists_cumulate.c
+++ b/tools/perf/tests/hists_cumulate.c
@@ -126,7 +126,7 @@ static void del_hist_entries(struct hists *hists)
 	struct rb_root *root_out;
 	struct rb_node *node;
 
-	if (sort__need_collapse)
+	if (hists__has(hists, need_collapse))
 		root_in = &hists->entries_collapsed;
 	else
 		root_in = hists->entries_in;
diff --git a/tools/perf/tests/hists_link.c b/tools/perf/tests/hists_link.c
index 358324e47805..acf5a1301c07 100644
--- a/tools/perf/tests/hists_link.c
+++ b/tools/perf/tests/hists_link.c
@@ -145,7 +145,7 @@ static int __validate_match(struct hists *hists)
 	/*
 	 * Only entries from fake_common_samples should have a pair.
 	 */
-	if (sort__need_collapse)
+	if (hists__has(hists, need_collapse))
 		root = &hists->entries_collapsed;
 	else
 		root = hists->entries_in;
@@ -197,7 +197,7 @@ static int __validate_link(struct hists *hists, int idx)
 	 * and some entries will have no pair.  However every entry
 	 * in other hists should have (dummy) pair.
 	 */
-	if (sort__need_collapse)
+	if (hists__has(hists, need_collapse))
 		root = &hists->entries_collapsed;
 	else
 		root = hists->entries_in;
diff --git a/tools/perf/tests/hists_output.c b/tools/perf/tests/hists_output.c
index 7cd8738e842f..63c5efaba1b5 100644
--- a/tools/perf/tests/hists_output.c
+++ b/tools/perf/tests/hists_output.c
@@ -92,7 +92,7 @@ static void del_hist_entries(struct hists *hists)
 	struct rb_root *root_out;
 	struct rb_node *node;
 
-	if (sort__need_collapse)
+	if (hists__has(hists, need_collapse))
 		root_in = &hists->entries_collapsed;
 	else
 		root_in = hists->entries_in;
diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c
index 6a4681932ba5..538bae880bfe 100644
--- a/tools/perf/ui/browsers/hists.c
+++ b/tools/perf/ui/browsers/hists.c
@@ -2135,7 +2135,7 @@ static int hists__browser_title(struct hists *hists,
 		printed += snprintf(bf + printed, size - printed,
 				    ", UID: %s", hists->uid_filter_str);
 	if (thread) {
-		if (sort__has_thread) {
+		if (hists__has(hists, thread)) {
 			printed += scnprintf(bf + printed, size - printed,
 				    ", Thread: %s(%d)",
 				     (thread->comm_set ? thread__comm_str(thread) : ""),
@@ -2320,7 +2320,8 @@ do_zoom_thread(struct hist_browser *browser, struct popup_action *act)
 {
 	struct thread *thread = act->thread;
 
-	if ((!sort__has_thread && !sort__has_comm) || thread == NULL)
+	if ((!hists__has(browser->hists, thread) &&
+	     !hists__has(browser->hists, comm)) || thread == NULL)
 		return 0;
 
 	if (browser->hists->thread_filter) {
@@ -2329,7 +2330,7 @@ do_zoom_thread(struct hist_browser *browser, struct popup_action *act)
 		thread__zput(browser->hists->thread_filter);
 		ui_helpline__pop();
 	} else {
-		if (sort__has_thread) {
+		if (hists__has(browser->hists, thread)) {
 			ui_helpline__fpush("To zoom out press ESC or ENTER + \"Zoom out of %s(%d) thread\"",
 					   thread->comm_set ? thread__comm_str(thread) : "",
 					   thread->tid);
@@ -2354,10 +2355,11 @@ add_thread_opt(struct hist_browser *browser, struct popup_action *act,
 {
 	int ret;
 
-	if ((!sort__has_thread && !sort__has_comm) || thread == NULL)
+	if ((!hists__has(browser->hists, thread) &&
+	     !hists__has(browser->hists, comm)) || thread == NULL)
 		return 0;
 
-	if (sort__has_thread) {
+	if (hists__has(browser->hists, thread)) {
 		ret = asprintf(optstr, "Zoom %s %s(%d) thread",
 			       browser->hists->thread_filter ? "out of" : "into",
 			       thread->comm_set ? thread__comm_str(thread) : "",
@@ -2380,7 +2382,7 @@ do_zoom_dso(struct hist_browser *browser, struct popup_action *act)
 {
 	struct map *map = act->ms.map;
 
-	if (!sort__has_dso || map == NULL)
+	if (!hists__has(browser->hists, dso) || map == NULL)
 		return 0;
 
 	if (browser->hists->dso_filter) {
@@ -2407,7 +2409,7 @@ static int
 add_dso_opt(struct hist_browser *browser, struct popup_action *act,
 	    char **optstr, struct map *map)
 {
-	if (!sort__has_dso || map == NULL)
+	if (!hists__has(browser->hists, dso) || map == NULL)
 		return 0;
 
 	if (asprintf(optstr, "Zoom %s %s DSO",
@@ -2429,10 +2431,10 @@ do_browse_map(struct hist_browser *browser __maybe_unused,
 }
 
 static int
-add_map_opt(struct hist_browser *browser __maybe_unused,
+add_map_opt(struct hist_browser *browser,
 	    struct popup_action *act, char **optstr, struct map *map)
 {
-	if (!sort__has_dso || map == NULL)
+	if (!hists__has(browser->hists, dso) || map == NULL)
 		return 0;
 
 	if (asprintf(optstr, "Browse map details") < 0)
@@ -2534,7 +2536,7 @@ add_exit_opt(struct hist_browser *browser __maybe_unused,
 static int
 do_zoom_socket(struct hist_browser *browser, struct popup_action *act)
 {
-	if (!sort__has_socket || act->socket < 0)
+	if (!hists__has(browser->hists, socket) || act->socket < 0)
 		return 0;
 
 	if (browser->hists->socket_filter > -1) {
@@ -2556,7 +2558,7 @@ static int
 add_socket_opt(struct hist_browser *browser, struct popup_action *act,
 	       char **optstr, int socket_id)
 {
-	if (!sort__has_socket || socket_id < 0)
+	if (!hists__has(browser->hists, socket) || socket_id < 0)
 		return 0;
 
 	if (asprintf(optstr, "Zoom %s Processor Socket %d",
@@ -2747,7 +2749,7 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
 			 */
 			goto out_free_stack;
 		case 'a':
-			if (!sort__has_sym) {
+			if (!hists__has(hists, sym)) {
 				ui_browser__warning(&browser->b, delay_secs * 2,
 			"Annotation is only available for symbolic views, "
 			"include \"sym*\" in --sort to use it.");
@@ -2910,7 +2912,7 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
 			continue;
 		}
 
-		if (!sort__has_sym || browser->selection == NULL)
+		if (!hists__has(hists, sym) || browser->selection == NULL)
 			goto skip_annotation;
 
 		if (sort__mode == SORT_MODE__BRANCH) {
@@ -2954,7 +2956,7 @@ skip_annotation:
 			goto skip_scripting;
 
 		if (browser->he_selection) {
-			if (sort__has_thread && thread) {
+			if (hists__has(hists, thread) && thread) {
 				nr_options += add_script_opt(browser,
 							     &actions[nr_options],
 							     &options[nr_options],
@@ -2969,7 +2971,7 @@ skip_annotation:
 			 *
 			 * See hist_browser__show_entry.
 			 */
-			if (sort__has_sym && browser->selection->sym) {
+			if (hists__has(hists, sym) && browser->selection->sym) {
 				nr_options += add_script_opt(browser,
 							     &actions[nr_options],
 							     &options[nr_options],
diff --git a/tools/perf/ui/gtk/hists.c b/tools/perf/ui/gtk/hists.c
index 2aa45b606fa4..932adfaa05af 100644
--- a/tools/perf/ui/gtk/hists.c
+++ b/tools/perf/ui/gtk/hists.c
@@ -379,7 +379,7 @@ static void perf_gtk__show_hists(GtkWidget *window, struct hists *hists,
 			gtk_tree_store_set(store, &iter, col_idx++, s, -1);
 		}
 
-		if (symbol_conf.use_callchain && sort__has_sym) {
+		if (symbol_conf.use_callchain && hists__has(hists, sym)) {
 			if (callchain_param.mode == CHAIN_GRAPH_REL)
 				total = symbol_conf.cumulate_callchain ?
 					h->stat_acc->period : h->stat.period;
diff --git a/tools/perf/ui/hist.c b/tools/perf/ui/hist.c
index 3baeaa6e71b5..af07ffb129ca 100644
--- a/tools/perf/ui/hist.c
+++ b/tools/perf/ui/hist.c
@@ -635,7 +635,7 @@ unsigned int hists__sort_list_width(struct hists *hists)
 		ret += fmt->width(fmt, &dummy_hpp, hists_to_evsel(hists));
 	}
 
-	if (verbose && sort__has_sym) /* Addr + origin */
+	if (verbose && hists__has(hists, sym)) /* Addr + origin */
 		ret += 3 + BITS_PER_LONG / 4;
 
 	return ret;
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index b795b6994144..d4b3d034c503 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -1665,5 +1665,5 @@ int hist_entry__annotate(struct hist_entry *he, size_t privsize)
 
 bool ui__has_annotation(void)
 {
-	return use_browser == 1 && sort__has_sym;
+	return use_browser == 1 && perf_hpp_list.sym;
 }
diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c
index aa248dcb4440..07fd30bc2f81 100644
--- a/tools/perf/util/callchain.c
+++ b/tools/perf/util/callchain.c
@@ -799,7 +799,7 @@ int sample__resolve_callchain(struct perf_sample *sample,
 		return 0;
 
 	if (symbol_conf.use_callchain || symbol_conf.cumulate_callchain ||
-	    sort__has_parent) {
+	    perf_hpp_list.parent) {
 		return thread__resolve_callchain(al->thread, cursor, evsel, sample,
 						 parent, al, max_stack);
 	}
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index 85271e54a63b..17cd01421e7f 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -679,39 +679,31 @@ static struct perf_evsel *perf_evlist__event2evsel(struct perf_evlist *evlist,
 	return NULL;
 }
 
-union perf_event *perf_evlist__mmap_read(struct perf_evlist *evlist, int idx)
+/* When check_messup is true, 'end' must points to a good entry */
+static union perf_event *
+perf_mmap__read(struct perf_mmap *md, bool check_messup, u64 start,
+		u64 end, u64 *prev)
 {
-	struct perf_mmap *md = &evlist->mmap[idx];
-	u64 head;
-	u64 old = md->prev;
-	int diff;
 	unsigned char *data = md->base + page_size;
 	union perf_event *event = NULL;
+	int diff = end - start;
 
-	/*
-	 * Check if event was unmapped due to a POLLHUP/POLLERR.
-	 */
-	if (!atomic_read(&md->refcnt))
-		return NULL;
-
-	head = perf_mmap__read_head(md);
-	diff = head - old;
-	if (evlist->overwrite) {
+	if (check_messup) {
 		/*
 		 * If we're further behind than half the buffer, there's a chance
 		 * the writer will bite our tail and mess up the samples under us.
 		 *
-		 * If we somehow ended up ahead of the head, we got messed up.
+		 * If we somehow ended up ahead of the 'end', we got messed up.
 		 *
-		 * In either case, truncate and restart at head.
+		 * In either case, truncate and restart at 'end'.
 		 */
 		if (diff > md->mask / 2 || diff < 0) {
 			fprintf(stderr, "WARNING: failed to keep up with mmap data.\n");
 
 			/*
-			 * head points to a known good entry, start there.
+			 * 'end' points to a known good entry, start there.
 			 */
-			old = head;
+			start = end;
 			diff = 0;
 		}
 	}
@@ -719,7 +711,7 @@ union perf_event *perf_evlist__mmap_read(struct perf_evlist *evlist, int idx)
 	if (diff >= (int)sizeof(event->header)) {
 		size_t size;
 
-		event = (union perf_event *)&data[old & md->mask];
+		event = (union perf_event *)&data[start & md->mask];
 		size = event->header.size;
 
 		if (size < sizeof(event->header) || diff < (int)size) {
@@ -731,8 +723,8 @@ union perf_event *perf_evlist__mmap_read(struct perf_evlist *evlist, int idx)
 		 * Event straddles the mmap boundary -- header should always
 		 * be inside due to u64 alignment of output.
 		 */
-		if ((old & md->mask) + size != ((old + size) & md->mask)) {
-			unsigned int offset = old;
+		if ((start & md->mask) + size != ((start + size) & md->mask)) {
+			unsigned int offset = start;
 			unsigned int len = min(sizeof(*event), size), cpy;
 			void *dst = md->event_copy;
 
@@ -747,15 +739,33 @@ union perf_event *perf_evlist__mmap_read(struct perf_evlist *evlist, int idx)
 			event = (union perf_event *) md->event_copy;
 		}
 
-		old += size;
+		start += size;
 	}
 
 broken_event:
-	md->prev = old;
+	if (prev)
+		*prev = s