Merge tag 'perf-core-for-mingo' 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 fixes and changes:

  * Show better error message in case we fail to open counters due to EBUSY error,
    for instance, when oprofile is running. (Jiri Olsa)

  * Honour -w in the report tools (report, top), allowing to specify the widths
    for the histogram entries columns. (Namhyung Kim)

  * Don't run workload if not told to, as happens when the user has no
    permission for profiling and even then the specified workload ends
    up running (Arnaldo Carvalho de Melo)

  * Do not ignore mmap events in 'perf kmem report'. This tool was using
    the kernel mmaps in the running machine instead of processing the mmap
    records from the perf.data file. (Namhyung Kim)

  * Properly show submicrosecond times in 'perf kvm stat' (Christian Borntraeger)

  * Honour existing 'perf record' --time/-T command line option (Andi Kleen)

  * Make sure --symfs usage includes the path separator (Arnaldo Carvalho de Melo)

Development infrastructure fixes and changes:

  * Fix arm64 build error (Mark Salter)

  * Fix make PYTHON override (Namhyung Kim)

  * Rename ordered_samples to ordered_events and allow setting a queue
    size for ordering events (Jiri Olsa)

  * Default to python version 2 (Thomas Ilsche)

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

46 files changed, 869 insertions, 440 deletions

diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt
index d2b59af..d561e02 100644
--- a/tools/perf/Documentation/perf-report.txt
+++ b/tools/perf/Documentation/perf-report.txt
@@ -147,7 +147,7 @@ OPTIONS
 -w::
 --column-widths=<width[,width...]>::
 	Force each column width to the provided list, for large terminal
-	readability.
+	readability.  0 means no limit (default behavior).
 
 -t::
 --field-separator=::
diff --git a/tools/perf/Documentation/perf-top.txt b/tools/perf/Documentation/perf-top.txt
index 180ae02..28fdee3 100644
--- a/tools/perf/Documentation/perf-top.txt
+++ b/tools/perf/Documentation/perf-top.txt
@@ -193,6 +193,12 @@ Default is to monitor all CPUS.
 	sum of shown entries will be always 100%. "absolute" means it retains
 	the original value before and after the filter is applied.
 
+-w::
+--column-widths=<width[,width...]>::
+	Force each column width to the provided list, for large terminal
+	readability.  0 means no limit (default behavior).
+
+
 INTERACTIVE PROMPTING KEYS
 --------------------------
 
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index 2240974..1ea31e2 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -263,6 +263,7 @@ LIB_H += util/xyarray.h
 LIB_H += util/header.h
 LIB_H += util/help.h
 LIB_H += util/session.h
+LIB_H += util/ordered-events.h
 LIB_H += util/strbuf.h
 LIB_H += util/strlist.h
 LIB_H += util/strfilter.h
@@ -347,6 +348,7 @@ LIB_OBJS += $(OUTPUT)util/machine.o
 LIB_OBJS += $(OUTPUT)util/map.o
 LIB_OBJS += $(OUTPUT)util/pstack.o
 LIB_OBJS += $(OUTPUT)util/session.o
+LIB_OBJS += $(OUTPUT)util/ordered-events.o
 LIB_OBJS += $(OUTPUT)util/comm.o
 LIB_OBJS += $(OUTPUT)util/thread.o
 LIB_OBJS += $(OUTPUT)util/thread_map.o
diff --git a/tools/perf/arch/arm64/include/perf_regs.h b/tools/perf/arch/arm64/include/perf_regs.h
index e9441b9..1d3f39c 100644
--- a/tools/perf/arch/arm64/include/perf_regs.h
+++ b/tools/perf/arch/arm64/include/perf_regs.h
@@ -6,6 +6,8 @@
 #include <asm/perf_regs.h>
 
 #define PERF_REGS_MASK	((1ULL << PERF_REG_ARM64_MAX) - 1)
+#define PERF_REGS_MAX	PERF_REG_ARM64_MAX
+
 #define PERF_REG_IP	PERF_REG_ARM64_PC
 #define PERF_REG_SP	PERF_REG_ARM64_SP
 
diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c
index 1ec429f..952b5ec 100644
--- a/tools/perf/builtin-annotate.c
+++ b/tools/perf/builtin-annotate.c
@@ -297,7 +297,7 @@ int cmd_annotate(int argc, const char **argv, const char *prefix __maybe_unused)
 			.comm	= perf_event__process_comm,
 			.exit	= perf_event__process_exit,
 			.fork	= perf_event__process_fork,
-			.ordered_samples = true,
+			.ordered_events = true,
 			.ordering_requires_timestamps = true,
 		},
 	};
diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c
index 9a5a035..c10cc44 100644
--- a/tools/perf/builtin-diff.c
+++ b/tools/perf/builtin-diff.c
@@ -360,7 +360,7 @@ static struct perf_tool tool = {
 	.exit	= perf_event__process_exit,
 	.fork	= perf_event__process_fork,
 	.lost	= perf_event__process_lost,
-	.ordered_samples = true,
+	.ordered_events = true,
 	.ordering_requires_timestamps = true,
 };
 
diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c
index 9a02807..ee875cc 100644
--- a/tools/perf/builtin-inject.c
+++ b/tools/perf/builtin-inject.c
@@ -366,7 +366,7 @@ static int __cmd_inject(struct perf_inject *inject)
 	} else if (inject->sched_stat) {
 		struct perf_evsel *evsel;
 
-		inject->tool.ordered_samples = true;
+		inject->tool.ordered_events = true;
 
 		evlist__for_each(session->evlist, evsel) {
 			const char *name = perf_evsel__name(evsel);
diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c
index bef3376..84b8239 100644
--- a/tools/perf/builtin-kmem.c
+++ b/tools/perf/builtin-kmem.c
@@ -256,7 +256,9 @@ static int process_sample_event(struct perf_tool *tool __maybe_unused,
 static struct perf_tool perf_kmem = {
 	.sample		 = process_sample_event,
 	.comm		 = perf_event__process_comm,
-	.ordered_samples = true,
+	.mmap		 = perf_event__process_mmap,
+	.mmap2		 = perf_event__process_mmap2,
+	.ordered_events	 = true,
 };
 
 static double fragmentation(unsigned long n_req, unsigned long n_alloc)
@@ -424,9 +426,6 @@ static int __cmd_kmem(void)
 	if (session == NULL)
 		return -ENOMEM;
 
-	if (perf_session__create_kernel_maps(session) < 0)
-		goto out_delete;
-
 	if (!perf_session__has_traces(session, "kmem record"))
 		goto out_delete;
 
diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c
index 43367eb..7cccead 100644
--- a/tools/perf/builtin-kvm.c
+++ b/tools/perf/builtin-kvm.c
@@ -592,8 +592,8 @@ static void print_result(struct perf_kvm_stat *kvm)
 	pr_info("%9s ", "Samples%");
 
 	pr_info("%9s ", "Time%");
-	pr_info("%10s ", "Min Time");
-	pr_info("%10s ", "Max Time");
+	pr_info("%11s ", "Min Time");
+	pr_info("%11s ", "Max Time");
 	pr_info("%16s ", "Avg time");
 	pr_info("\n\n");
 
@@ -610,8 +610,8 @@ static void print_result(struct perf_kvm_stat *kvm)
 		pr_info("%10llu ", (unsigned long long)ecount);
 		pr_info("%8.2f%% ", (double)ecount / kvm->total_count * 100);
 		pr_info("%8.2f%% ", (double)etime / kvm->total_time * 100);
-		pr_info("%8" PRIu64 "us ", min / 1000);
-		pr_info("%8" PRIu64 "us ", max / 1000);
+		pr_info("%9.2fus ", (double)min / 1e3);
+		pr_info("%9.2fus ", (double)max / 1e3);
 		pr_info("%9.2fus ( +-%7.2f%% )", (double)etime / ecount/1e3,
 			kvm_event_rel_stddev(vcpu, event));
 		pr_info("\n");
@@ -732,7 +732,7 @@ static s64 perf_kvm__mmap_read_idx(struct perf_kvm_stat *kvm, int idx,
 			return -1;
 		}
 
-		err = perf_session_queue_event(kvm->session, event, &sample, 0);
+		err = perf_session_queue_event(kvm->session, event, &kvm->tool, &sample, 0);
 		/*
 		 * FIXME: Here we can't consume the event, as perf_session_queue_event will
 		 *        point to it, and it'll get possibly overwritten by the kernel.
@@ -785,7 +785,7 @@ static int perf_kvm__mmap_read(struct perf_kvm_stat *kvm)
 
 	/* flush queue after each round in which we processed events */
 	if (ntotal) {
-		kvm->session->ordered_samples.next_flush = flush_time;
+		kvm->session->ordered_events.next_flush = flush_time;
 		err = kvm->tool.finished_round(&kvm->tool, NULL, kvm->session);
 		if (err) {
 			if (kvm->lost_events)
@@ -1058,7 +1058,7 @@ static int read_events(struct perf_kvm_stat *kvm)
 	struct perf_tool eops = {
 		.sample			= process_sample_event,
 		.comm			= perf_event__process_comm,
-		.ordered_samples	= true,
+		.ordered_events		= true,
 	};
 	struct perf_data_file file = {
 		.path = kvm->file_name,
@@ -1311,7 +1311,7 @@ static int kvm_events_live(struct perf_kvm_stat *kvm,
 	kvm->tool.exit   = perf_event__process_exit;
 	kvm->tool.fork   = perf_event__process_fork;
 	kvm->tool.lost   = process_lost_event;
-	kvm->tool.ordered_samples = true;
+	kvm->tool.ordered_events = true;
 	perf_tool__fill_defaults(&kvm->tool);
 
 	/* set defaults */
diff --git a/tools/perf/builtin-lock.c b/tools/perf/builtin-lock.c
index 6148afc..c8122d3 100644
--- a/tools/perf/builtin-lock.c
+++ b/tools/perf/builtin-lock.c
@@ -852,7 +852,7 @@ static int __cmd_report(bool display_info)
 	struct perf_tool eops = {
 		.sample		 = process_sample_event,
 		.comm		 = perf_event__process_comm,
-		.ordered_samples = true,
+		.ordered_events	 = true,
 	};
 	struct perf_data_file file = {
 		.path = input_name,
diff --git a/tools/perf/builtin-mem.c b/tools/perf/builtin-mem.c
index 4a1a6c9..80e57c8 100644
--- a/tools/perf/builtin-mem.c
+++ b/tools/perf/builtin-mem.c
@@ -194,7 +194,7 @@ int cmd_mem(int argc, const char **argv, const char *prefix __maybe_unused)
 			.lost		= perf_event__process_lost,
 			.fork		= perf_event__process_fork,
 			.build_id	= perf_event__process_build_id,
-			.ordered_samples = true,
+			.ordered_events	= true,
 		},
 		.input_name		 = "perf.data",
 	};
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 4869050..ca0251e 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -781,6 +781,7 @@ static const char * const record_usage[] = {
  */
 static struct record record = {
 	.opts = {
+		.sample_time	     = true,
 		.mmap_pages	     = UINT_MAX,
 		.user_freq	     = UINT_MAX,
 		.user_interval	     = ULLONG_MAX,
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 21d830b..041e93d 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -58,17 +58,19 @@ struct report {
 	const char		*symbol_filter_str;
 	float			min_percent;
 	u64			nr_entries;
+	u64			queue_size;
 	DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS);
 };
 
 static int report__config(const char *var, const char *value, void *cb)
 {
+	struct report *rep = cb;
+
 	if (!strcmp(var, "report.group")) {
 		symbol_conf.event_group = perf_config_bool(var, value);
 		return 0;
 	}
 	if (!strcmp(var, "report.percent-limit")) {
-		struct report *rep = cb;
 		rep->min_percent = strtof(value, NULL);
 		return 0;
 	}
@@ -76,6 +78,10 @@ static int report__config(const char *var, const char *value, void *cb)
 		symbol_conf.cumulate_callchain = perf_config_bool(var, value);
 		return 0;
 	}
+	if (!strcmp(var, "report.queue-size")) {
+		rep->queue_size = perf_config_u64(var, value);
+		return 0;
+	}
 
 	return perf_default_config(var, value, cb);
 }
@@ -578,7 +584,7 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
 			.attr		 = perf_event__process_attr,
 			.tracing_data	 = perf_event__process_tracing_data,
 			.build_id	 = perf_event__process_build_id,
-			.ordered_samples = true,
+			.ordered_events	 = true,
 			.ordering_requires_timestamps = true,
 		},
 		.max_stack		 = PERF_MAX_STACK_DEPTH,
@@ -714,6 +720,11 @@ repeat:
 	if (session == NULL)
 		return -ENOMEM;
 
+	if (report.queue_size) {
+		ordered_events__set_alloc_size(&session->ordered_events,
+					       report.queue_size);
+	}
+
 	report.session = session;
 
 	has_br_stack = perf_header__has_feat(&session->header,
diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c
index f83c08c..7c16aeb 100644
--- a/tools/perf/builtin-sched.c
+++ b/tools/perf/builtin-sched.c
@@ -1662,7 +1662,7 @@ int cmd_sched(int argc, const char **argv, const char *prefix __maybe_unused)
 			.comm		 = perf_event__process_comm,
 			.lost		 = perf_event__process_lost,
 			.fork		 = perf_sched__process_fork_event,
-			.ordered_samples = true,
+			.ordered_events = true,
 		},
 		.cmp_pid	      = LIST_HEAD_INIT(sched.cmp_pid),
 		.sort_list	      = LIST_HEAD_INIT(sched.sort_list),
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index f57035b..868c17d 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -1488,7 +1488,7 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused)
 			.attr		 = process_attr,
 			.tracing_data	 = perf_event__process_tracing_data,
 			.build_id	 = perf_event__process_build_id,
-			.ordered_samples = true,
+			.ordered_events	 = true,
 			.ordering_requires_timestamps = true,
 		},
 	};
diff --git a/tools/perf/builtin-timechart.c b/tools/perf/builtin-timechart.c
index 2f1a522..912e3b5 100644
--- a/tools/perf/builtin-timechart.c
+++ b/tools/perf/builtin-timechart.c
@@ -1920,7 +1920,7 @@ int cmd_timechart(int argc, const char **argv,
 			.fork		 = process_fork_event,
 			.exit		 = process_exit_event,
 			.sample		 = process_sample_event,
-			.ordered_samples = true,
+			.ordered_events	 = true,
 		},
 		.proc_num = 15,
 		.min_time = 1000000,
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 377971d..bde216b 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -1131,6 +1131,9 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused)
 		     "Don't show entries under that percent", parse_percent_limit),
 	OPT_CALLBACK(0, "percentage", NULL, "relative|absolute",
 		     "How to display percentage of filtered entries", parse_filter_percentage),
+	OPT_STRING('w', "column-widths", &symbol_conf.col_width_list_str,
+		   "width[,width...]",
+		   "don't try to adjust column width, use these fixed values"),
 	OPT_END()
 	};
 	const char * const top_usage[] = {
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index a6c3752..36ae51d 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -2209,7 +2209,7 @@ static int trace__replay(struct trace *trace)
 	trace->tool.tracing_data = perf_event__process_tracing_data;
 	trace->tool.build_id	  = perf_event__process_build_id;
 
-	trace->tool.ordered_samples = true;
+	trace->tool.ordered_events = true;
 	trace->tool.ordering_requires_timestamps = true;
 
 	/* add tid to output */
diff --git a/tools/perf/config/Makefile b/tools/perf/config/Makefile
index 1f67aa0..75d4c23 100644
--- a/tools/perf/config/Makefile
+++ b/tools/perf/config/Makefile
@@ -120,6 +120,29 @@ ifdef PARSER_DEBUG
   CFLAGS             += -DPARSER_DEBUG
 endif
 
+ifndef NO_LIBPYTHON
+  # Try different combinations to accommodate systems that only have
+  # python[2][-config] in weird combinations but always preferring
+  # python2 and python2-config as per pep-0394. If we catch a
+  # python[-config] in version 3, the version check will kill it.
+  PYTHON2 := $(if $(call get-executable,python2),python2,python)
+  override PYTHON := $(call get-executable-or-default,PYTHON,$(PYTHON2))
+  PYTHON2_CONFIG := \
+    $(if $(call get-executable,$(PYTHON)-config),$(PYTHON)-config,python-config)
+  override PYTHON_CONFIG := \
+    $(call get-executable-or-default,PYTHON_CONFIG,$(PYTHON2_CONFIG))
+
+  PYTHON_CONFIG_SQ := $(call shell-sq,$(PYTHON_CONFIG))
+
+  PYTHON_EMBED_LDOPTS := $(shell $(PYTHON_CONFIG_SQ) --ldflags 2>/dev/null)
+  PYTHON_EMBED_CCOPTS := $(shell $(PYTHON_CONFIG_SQ) --cflags 2>/dev/null)
+
+  FEATURE_CHECK_CFLAGS-libpython := $(PYTHON_EMBED_CCOPTS)
+  FEATURE_CHECK_LDFLAGS-libpython := $(PYTHON_EMBED_LDOPTS)
+  FEATURE_CHECK_CFLAGS-libpython-version := $(PYTHON_EMBED_CCOPTS)
+  FEATURE_CHECK_LDFLAGS-libpython-version := $(PYTHON_EMBED_LDOPTS)
+endif
+
 CFLAGS += -fno-omit-frame-pointer
 CFLAGS += -ggdb3
 CFLAGS += -funwind-tables
@@ -482,21 +505,14 @@ define disable-python_code
   NO_LIBPYTHON := 1
 endef
 
-override PYTHON := \
-  $(call get-executable-or-default,PYTHON,python)
-
-ifndef PYTHON
-  $(call disable-python,python interpreter)
+ifdef NO_LIBPYTHON
+  $(call disable-python)
 else
 
-  PYTHON_WORD := $(call shell-wordify,$(PYTHON))
-
-  ifdef NO_LIBPYTHON
-    $(call disable-python)
+  ifndef PYTHON
+    $(call disable-python,python interpreter)
   else
-
-    override PYTHON_CONFIG := \
-      $(call get-executable-or-default,PYTHON_CONFIG,$(PYTHON)-config)
+    PYTHON_WORD := $(call shell-wordify,$(PYTHON))
 
     ifndef PYTHON_CONFIG
       $(call disable-python,python-config tool)
diff --git a/tools/perf/config/feature-checks/Makefile b/tools/perf/config/feature-checks/Makefile
index 6088f8d..72ab298 100644
--- a/tools/perf/config/feature-checks/Makefile
+++ b/tools/perf/config/feature-checks/Makefile
@@ -101,25 +101,11 @@ FLAGS_PERL_EMBED=$(PERL_EMBED_CCOPTS) $(PERL_EMBED_LDOPTS)
 test-libperl.bin:
 	$(BUILD) $(FLAGS_PERL_EMBED)
 
-override PYTHON := python
-override PYTHON_CONFIG := python-config
-
-escape-for-shell-sq =  $(subst ','\'',$(1))
-shell-sq = '$(escape-for-shell-sq)'
-
-PYTHON_CONFIG_SQ = $(call shell-sq,$(PYTHON_CONFIG))
-
-PYTHON_EMBED_LDOPTS = $(shell $(PYTHON_CONFIG_SQ) --ldflags 2>/dev/null)
-PYTHON_EMBED_LDFLAGS = $(call strip-libs,$(PYTHON_EMBED_LDOPTS))
-PYTHON_EMBED_LIBADD = $(call grep-libs,$(PYTHON_EMBED_LDOPTS))
-PYTHON_EMBED_CCOPTS = $(shell $(PYTHON_CONFIG_SQ) --cflags 2>/dev/null)
-FLAGS_PYTHON_EMBED = $(PYTHON_EMBED_CCOPTS) $(PYTHON_EMBED_LDOPTS)
-
 test-libpython.bin:
-	$(BUILD) $(FLAGS_PYTHON_EMBED)
+	$(BUILD)
 
 test-libpython-version.bin:
-	$(BUILD) $(FLAGS_PYTHON_EMBED)
+	$(BUILD)
 
 test-libbfd.bin:
 	$(BUILD) -DPACKAGE='"perf"' -lbfd -lz -liberty -ldl
diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c
index a94b11fc..045c1e1 100644
--- a/tools/perf/ui/browsers/hists.c
+++ b/tools/perf/ui/browsers/hists.c
@@ -653,17 +653,18 @@ struct hpp_arg {
 static int __hpp__slsmg_color_printf(struct perf_hpp *hpp, const char *fmt, ...)
 {
 	struct hpp_arg *arg = hpp->ptr;
-	int ret;
+	int ret, len;
 	va_list args;
 	double percent;
 
 	va_start(args, fmt);
+	len = va_arg(args, int);
 	percent = va_arg(args, double);
 	va_end(args);
 
 	ui_browser__set_percent_color(arg->b, percent, arg->current_entry);
 
-	ret = scnprintf(hpp->buf, hpp->size, fmt, percent);
+	ret = scnprintf(hpp->buf, hpp->size, fmt, len, percent);
 	slsmg_printf("%s", hpp->buf);
 
 	advance_hpp(hpp, ret);
@@ -677,12 +678,12 @@ static u64 __hpp_get_##_field(struct hist_entry *he)			\
 }									\
 									\
 static int								\
-hist_browser__hpp_color_##_type(struct perf_hpp_fmt *fmt __maybe_unused,\
+hist_browser__hpp_color_##_type(struct perf_hpp_fmt *fmt,		\
 				struct perf_hpp *hpp,			\
 				struct hist_entry *he)			\
 {									\
-	return __hpp__fmt(hpp, he, __hpp_get_##_field, " %6.2f%%",	\
-			  __hpp__slsmg_color_printf, true);		\
+	return hpp__fmt(fmt, hpp, he, __hpp_get_##_field, " %*.2f%%",	\
+			__hpp__slsmg_color_printf, true);		\
 }
 
 #define __HPP_COLOR_ACC_PERCENT_FN(_type, _field)			\
@@ -692,18 +693,20 @@ static u64 __hpp_get_acc_##_field(struct hist_entry *he)		\
 }									\
 									\
 static int								\
-hist_browser__hpp_color_##_type(struct perf_hpp_fmt *fmt __maybe_unused,\
+hist_browser__hpp_color_##_type(struct perf_hpp_fmt *fmt,		\
 				struct perf_hpp *hpp,			\
 				struct hist_entry *he)			\
 {									\
 	if (!symbol_conf.cumulate_callchain) {				\
-		int ret = scnprintf(hpp->buf, hpp->size, "%8s", "N/A");	\
+		int len = fmt->user_len ?: fmt->len;			\
+		int ret = scnprintf(hpp->buf, hpp->size,		\
+				    "%*s", len, "N/A");			\
 		slsmg_printf("%s", hpp->buf);				\
 									\
 		return ret;						\
 	}								\
-	return __hpp__fmt(hpp, he, __hpp_get_acc_##_field, " %6.2f%%",	\
-			  __hpp__slsmg_color_printf, true);		\
+	return hpp__fmt(fmt, hpp, he, __hpp_get_acc_##_field,		\
+			" %*.2f%%", __hpp__slsmg_color_printf, true);	\
 }
 
 __HPP_COLOR_PERCENT_FN(overhead, period)
@@ -847,9 +850,6 @@ static int hists__scnprintf_headers(char *buf, size_t size, struct hists *hists)
 		if (perf_hpp__should_skip(fmt))
 			continue;
 
-		/* We need to add the length of the columns header. */
-		perf_hpp__reset_width(fmt, hists);
-
 		ret = fmt->header(fmt, &dummy_hpp, hists_to_evsel(hists));
 		if (advance_hpp_check(&dummy_hpp, ret))
 			break;
@@ -1498,6 +1498,7 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
 	char buf[64];
 	char script_opt[64];
 	int delay_secs = hbt ? hbt->refresh : 0;
+	struct perf_hpp_fmt *fmt;
 
 #define HIST_BROWSER_HELP_COMMON					\
 	"h/?/F1        Show this window\n"				\
@@ -1547,6 +1548,12 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
 
 	memset(options, 0, sizeof(options));
 
+	perf_hpp__for_each_format(fmt)
+		perf_hpp__reset_width(fmt, hists);
+
+	if (symbol_conf.col_width_list_str)
+		perf_hpp__set_user_width(symbol_conf.col_width_list_str);
+
 	while (1) {
 		const struct thread *thread = NULL;
 		const struct dso *dso = NULL;
diff --git a/tools/perf/ui/gtk/hists.c b/tools/perf/ui/gtk/hists.c
index 6ca60e4..f3fa425 100644
--- a/tools/perf/ui/gtk/hists.c
+++ b/tools/perf/ui/gtk/hists.c
@@ -11,6 +11,7 @@
 static int __percent_color_snprintf(struct perf_hpp *hpp, const char *fmt, ...)
 {
 	int ret = 0;
+	int len;
 	va_list args;
 	double percent;
 	const char *markup;
@@ -18,6 +19,7 @@ static int __percent_color_snprintf(struct perf_hpp *hpp, const char *fmt, ...)
 	size_t size = hpp->size;
 
 	va_start(args, fmt);
+	len = va_arg(args, int);
 	percent = va_arg(args, double);
 	va_end(args);
 
@@ -25,7 +27,7 @@ static int __percent_color_snprintf(struct perf_hpp *hpp, const char *fmt, ...)
 	if (markup)
 		ret += scnprintf(buf, size, markup);
 
-	ret += scnprintf(buf + ret, size - ret, fmt, percent);
+	ret += scnprintf(buf + ret, size - ret, fmt, len, percent);
 
 	if (markup)
 		ret += scnprintf(buf + ret, size - ret, "</span>");
@@ -39,12 +41,12 @@ static u64 he_get_##_field(struct hist_entry *he)				\
 	return he->stat._field;							\
 }										\
 										\
-static int perf_gtk__hpp_color_##_type(struct perf_hpp_fmt *fmt __maybe_unused,	\
+static int perf_gtk__hpp_color_##_type(struct perf_hpp_fmt *fmt,		\
 				       struct perf_hpp *hpp,			\
 				       struct hist_entry *he)			\
 {										\
-	return __hpp__fmt(hpp, he, he_get_##_field, " %6.2f%%",			\
-			  __percent_color_snprintf, true);			\
+	return hpp__fmt(fmt, hpp, he, he_get_##_field, " %*.2f%%",		\
+			__percent_color_snprintf, true);			\
 }
 
 #define __HPP_COLOR_ACC_PERCENT_FN(_type, _field)				\
@@ -57,8 +59,8 @@ static int perf_gtk__hpp_color_##_type(struct perf_hpp_fmt *fmt __maybe_unused,
 				       struct perf_hpp *hpp,			\
 				       struct hist_entry *he)			\
 {										\
-	return __hpp__fmt_acc(hpp, he, he_get_acc_##_field, " %6.2f%%",		\
-			      __percent_color_snprintf, true);			\
+	return hpp__fmt_acc(fmt, hpp, he, he_get_acc_##_field, " %*.2f%%", 	\
+			    __percent_color_snprintf, true);			\
 }
 
 __HPP_COLOR_PERCENT_FN(overhead, period)
@@ -205,10 +207,8 @@ static void perf_gtk__show_hists(GtkWidget *window, struct hists *hists,
 		if (perf_hpp__is_sort_entry(fmt))
 			sym_col = col_idx;
 
-		fmt->header(fmt, &hpp, hists_to_evsel(hists));
-
 		gtk_tree_view_insert_column_with_attributes(GTK_TREE_VIEW(view),
-							    -1, ltrim(s),
+							    -1, fmt->name,
 							    renderer, "markup",
 							    col_idx++, NULL);
 	}
diff --git a/tools/perf/ui/hist.c b/tools/perf/ui/hist.c
index 498adb2..b5fa701 100644
--- a/tools/perf/ui/hist.c
+++ b/tools/perf/ui/hist.c
@@ -15,9 +15,9 @@
 	__ret;							\
 })
 
-int __hpp__fmt(struct perf_hpp *hpp, struct hist_entry *he,
-	       hpp_field_fn get_field, const char *fmt,
-	       hpp_snprint_fn print_fn, bool fmt_percent)
+static int __hpp__fmt(struct perf_hpp *hpp, struct hist_entry *he,
+		      hpp_field_fn get_field, const char *fmt, int len,
+		      hpp_snprint_fn print_fn, bool fmt_percent)
 {
 	int ret;
 	struct hists *hists = he->hists;
@@ -32,9 +32,9 @@ int __hpp__fmt(struct perf_hpp *hpp, struct hist_entry *he,
 		if (total)
 			percent = 100.0 * get_field(he) / total;
 
-		ret = hpp__call_print_fn(hpp, print_fn, fmt, percent);
+		ret = hpp__call_print_fn(hpp, print_fn, fmt, len, percent);
 	} else
-		ret = hpp__call_print_fn(hpp, print_fn, fmt, get_field(he));
+		ret = hpp__call_print_fn(hpp, print_fn, fmt, len, get_field(he));
 
 	if (perf_evsel__is_group_event(evsel)) {
 		int prev_idx, idx_delta;
@@ -60,19 +60,19 @@ int __hpp__fmt(struct perf_hpp *hpp, struct hist_entry *he,
 				 */
 				if (fmt_percent) {
 					ret += hpp__call_print_fn(hpp, print_fn,
-								  fmt, 0.0);
+								  fmt, len, 0.0);
 				} else {
 					ret += hpp__call_print_fn(hpp, print_fn,
-								  fmt, 0ULL);
+								  fmt, len, 0ULL);
 				}
 			}
 
 			if (fmt_percent) {
-				ret += hpp__call_print_fn(hpp, print_fn, fmt,
+				ret += hpp__call_print_fn(hpp, print_fn, fmt, len,
 							  100.0 * period / total);
 			} else {
 				ret += hpp__call_print_fn(hpp, print_fn, fmt,
-							  period);
+							  len, period);
 			}
 
 			prev_idx = perf_evsel__group_idx(evsel);
@@ -86,10 +86,10 @@ int __hpp__fmt(struct perf_hpp *hpp, struct hist_entry *he,
 			 */
 			if (fmt_percent) {
 				ret += hpp__call_print_fn(hpp, print_fn,
-							  fmt, 0.0);
+							  fmt, len, 0.0);
 			} else {
 				ret += hpp__call_print_fn(hpp, print_fn,
-							  fmt, 0ULL);
+							  fmt, len, 0ULL);
 			}
 		}
 	}
@@ -104,16 +104,35 @@ int __hpp__fmt(struct perf_hpp *hpp, struct hist_entry *he,
 	return ret;
 }
 
-int __hpp__fmt_acc(struct perf_hpp *hpp, struct hist_entry *he,
-		   hpp_field_fn get_field, const char *fmt,
-		   hpp_snprint_fn print_fn, bool fmt_percent)
+int hpp__fmt(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
+	     struct hist_entry *he, hpp_field_fn get_field,
+	     const char *fmtstr, hpp_snprint_fn print_fn, bool fmt_percent)
+{
+	int len = fmt->user_len ?: fmt->len;
+
+	if (symbol_conf.field_sep) {
+		return __hpp__fmt(hpp, he, get_field, fmtstr, 1,
+				  print_fn, fmt_percent);
+	}
+
+	if (fmt_percent)
+		len -= 2; /* 2 for a space and a % sign */
+	else
+		len -= 1;
+
+	return  __hpp__fmt(hpp, he, get_field, fmtstr, len, print_fn, fmt_percent);
+}
+
+int hpp__fmt_acc(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
+		 struct hist_entry *he, hpp_field_fn get_field,
+		 const char *fmtstr, hpp_snprint_fn print_fn, bool fmt_percent)
 {
 	if (!symbol_conf.cumulate_callchain) {
-		return snprintf(hpp->buf, hpp->size, "%*s",
-				fmt_percent ? 8 : 12, "N/A");
+		int len = fmt->user_len ?: fmt->len;
+		return snprintf(hpp->buf, hpp->size, " %*s", len - 1, "N/A");
 	}
 
-	return __hpp__fmt(hpp, he, get_field, fmt, print_fn, fmt_percent);
+	return hpp__fmt(fmt, hpp, he, get_field, fmtstr, print_fn, fmt_percent);
 }
 
 static int field_cmp(u64 field_a, u64 field_b)
@@ -190,30 +209,26 @@ static int __hpp__sort_acc(struct hist_entry *a, struct hist_entry *b,
 	return ret;
 }
 
-#define __HPP_HEADER_FN(_type, _str, _min_width, _unit_width) 		\
-static int hpp__header_##_type(struct perf_hpp_fmt *fmt __maybe_unused,	\
-			       struct perf_hpp *hpp,			\
-			       struct perf_evsel *evsel)		\
-{									\
-	int len = _min_width;						\
-									\
-	if (symbol_conf.event_group)					\
-		len = max(len, evsel->nr_members * _unit_width);	\
-									\
-	return scnprintf(hpp->buf, hpp->size, "%*s", len, _str);	\
-}
-
-#define __HPP_WIDTH_FN(_type, _min_width, _unit_width) 			\
-static int hpp__width_##_type(struct perf_hpp_fmt *fmt __maybe_unused,	\
-			      struct perf_hpp *hpp __maybe_unused,	\
-			      struct perf_evsel *evsel)			\
-{									\
-	int len = _min_width;						\
-									\
-	if (symbol_conf.event_group)					\
-		len = max(len, evsel->nr_members * _unit_width);	\
-									\
-	return len;							\
+static int hpp__width_fn(struct perf_hpp_fmt *fmt,
+			 struct perf_hpp *hpp __maybe_unused,
+			 struct perf_evsel *evsel)
+{
+	int len = fmt->user_len ?: fmt->len;
+
+	if (symbol_conf.event_group)
+		len = max(len, evsel->nr_members * fmt->len);
+
+	if (len < (int)strlen(fmt->name))
+		len = strlen(fmt->name);
+
+	return len;
+}
+
+static int hpp__header_fn(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
+			  struct perf_evsel *evsel)
+{
+	int len = hpp__width_fn(fmt, hpp, evsel);
+	return scnprintf(hpp->buf, hpp->size, "%*s", len, fmt->name);
 }
 
 static int hpp_color_scnprintf(struct perf_hpp *hpp, const char *fmt, ...)
@@ -221,11 +236,12 @@ static int hpp_color_scnprintf(struct perf_hpp *hpp, const char *fmt, ...)
 	va_list args;
 	ssize_t ssize = hpp->size;
 	double percent;
-	int ret;
+	int ret, len;
 
 	va_start(args, fmt);
+	len = va_arg(args, int);
 	percent = va_arg(args, double);
-	ret = value_color_snprintf(hpp->buf, hpp->size, fmt, percent);
+	ret = percent_color_len_snprintf(hpp->buf, hpp->size, fmt, len, percent);
 	va_end(args);
 
 	return (ret >= ssize) ? (ssize - 1) : ret;
@@ -250,20 +266,19 @@ static u64 he_get_##_field(struct hist_entry *he)				\
 	return he->stat._field;							\
 }										\
 										\
-static int hpp__color_##_type(struct perf_hpp_fmt *fmt __maybe_unused,		\
+static int hpp__color_##_type(struct perf_hpp_fmt *fmt,				\
 			      struct perf_hpp *hpp, struct hist_entry *he) 	\
 {										\
-	return __hpp__fmt(hpp, he, he_get_##_field, " %6.2f%%",			\
-			  hpp_color_scnprintf, true);				\
+	return hpp__fmt(fmt, hpp, he, he_get_##_field, " %*.2f%%",		\
+			hpp_color_scnprintf, true);				\
 }
 
 #define __HPP_ENTRY_PERCENT_FN(_type, _field)					\
-static int hpp__entry_##_type(struct perf_hpp_fmt *_fmt __maybe_unused,		\
+static int hpp__entry_##_type(struct perf_hpp_fmt *fmt,				\
 			      struct perf_hpp *hpp, struct hist_entry *he) 	\
 {										\
-	const char *fmt = symbol_conf.field_sep ? " %.2f" : " %6.2f%%";		\
-	return __hpp__fmt(hpp, he, he_get_##_field, fmt,			\
-			  hpp_entry_scnprintf, true);				\
+	return hpp__fmt(fmt, hpp, he, he_get_##_field, " %*.2f%%",		\
+			hpp_entry_scnprintf, true);				\
 }
 
 #define __HPP_SORT_FN(_type, _field)						\
@@ -278,20 +293,19 @@ static u64 he_get_acc_##_field(struct hist_entry *he)				\
 	return he->stat_acc->_field;						\
 }										\
 										\
-static int hpp__color_##_type(struct perf_hpp_fmt *fmt __maybe_unused,		\
+static int hpp__color_##_type(struct perf_hpp_fmt *fmt,				\
 			      struct perf_hpp *hpp, struct hist_entry *he) 	\
 {										\
-	return __hpp__fmt_acc(hpp, he, he_get_acc_##_field, " %6.2f%%",		\
-			      hpp_color_scnprintf, true);			\
+	return hpp__fmt_acc(fmt, hpp, he, he_get_acc_##_field, " %*.2f%%", 	\
+			    hpp_color_scnprintf, true);				\
 }
 
 #define __HPP_ENTRY_ACC_PERCENT_FN(_type, _field)				\
-static int hpp__entry_##_type(struct perf_hpp_fmt *_fmt __maybe_unused,		\
+static int hpp__entry_##_type(struct perf_hpp_fmt *fmt,				\
 			      struct perf_hpp *hpp, struct hist_entry *he) 	\
 {										\
-	const char *fmt = symbol_conf.field_sep ? " %.2f" : " %6.2f%%";		\
-	return __hpp__fmt_acc(hpp, he, he_get_acc_##_field, fmt,		\
-			      hpp_entry_scnprintf, true);			\
+	return hpp__fmt_acc(fmt, hpp, he, he_get_##_field, " %*.2f%%",		\
+			    hpp_entry_scnprintf, true);				\
 }
 
 #define __HPP_SORT_ACC_FN(_type, _field)					\
@@ -306,12 +320,11 @@ static u64 he_get_raw_##_field(struct hist_entry *he)				\
 	return he->stat._field;							\
 }										\
 										\
-static int hpp__entry_##_type(struct perf_hpp_fmt *_fmt __maybe_unused,		\
+static int hpp__entry_##_type(struct perf_hpp_fmt *fmt,				\
 			      struct perf_hpp *hpp, struct hist_entry *he) 	\
 {										\
-	const char *fmt = symbol_conf.field_sep ? " %"PRIu64 : " %11"PRIu64;	\
-	return __hpp__fmt(hpp, he, he_get_raw_##_field, fmt,			\
-			  hpp_entry_scnprintf, false);				\
+	return hpp__fmt(fmt, hpp, he, he_get_raw_##_field, " %*"PRIu64, 	\
+			hpp_entry_scnprintf, false);				\
 }
 
 #define __HPP_SORT_RAW_FN(_type, _field)					\
@@ -321,37 +334,29 @@ static int64_t hpp__sort_##_type(struct hist_entry *a, struct hist_entry *b)	\
 }
 
 
-#define HPP_PERCENT_FNS(_type, _str, _field, _min_width, _unit_width)	\
-__HPP_HEADER_FN(_type, _str, _min_width, _unit_width)			\
-__HPP_WIDTH_FN(_type, _min_width, _unit_width)				\
+#define HPP_PERCENT_FNS(_type, _field)					\
 __HPP_COLOR_PERCENT_FN(_type, _field)					\
 __HPP_ENTRY_PERCENT_FN(_type, _field)					\
 __HPP_SORT_FN(_type, _field)
 
-#define HPP_PERCENT_ACC_FNS(_type, _str, _field, _min_width, _unit_width)\
-__HPP_HEADER_FN(_type, _str, _min_width, _unit_width)			\
-__HPP_WIDTH_FN(_type, _min_width, _unit_width)				\
+#define HPP_PERCENT_ACC_FNS(_type, _field)				\
 __HPP_COLOR_ACC_PERCENT_FN(_type, _field)				\
 __HPP_ENTRY_ACC_PERCENT_FN(_type, _field)				\
 __HPP_SORT_ACC_FN(_type, _field)
 
-#define HPP_RAW_FNS(_type, _str, _field, _min_width, _unit_width)	\
-__HPP_HEADER_FN(_type, _str, _min_width, _unit_width)			\
-__HPP_WIDTH_FN(_type, _min_width, _unit_width)				\
+#define HPP_RAW_FNS(_type, _field)					\
 __HPP_ENTRY_RAW_FN(_type, _field)					\
 __HPP_SORT_RAW_FN(_type, _field)
 
-__HPP_HEADER_FN(overhead_self, "Self", 8, 8)
-
-HPP_PERCENT_FNS(overhead, "Overhead", period, 8, 8)
-HPP_PERCENT_FNS(overhead_sys, "sys", period_sys, 8, 8)
-HPP_PERCENT_FNS(overhead_us, "usr", period_us, 8, 8)
-HPP_PERCENT_FNS(overhead_guest_sys, "guest sys", period_guest_sys, 9, 8)
-HPP_PERCENT_FNS(overhead_guest_us, "guest usr", period_guest_us, 9, 8)
-HPP_PERCENT_ACC_FNS(overhead_acc, "Children", period, 8, 8)
+HPP_PERCENT_FNS(overhead, period)
+HPP_PERCENT_FNS(overhead_sys, period_sys)
+HPP_PERCENT_FNS(overhead_us, period_us)
+HPP_PERCENT_FNS(overhead_guest_sys, period_guest_sys)
+HPP_PERCENT_FNS(overhead_guest_us, period_guest_us)
+HPP_PERCENT_ACC_FNS(overhead_acc, period)
 
-HPP_RAW_FNS(samples, "Samples", nr_events, 12, 12)
-HPP_RAW_FNS(period, "Period", period, 12, 12)
+HPP_RAW_FNS(samples, nr_events)
+HPP_RAW_FNS(period, period)
 
 static int64_t hpp__nop_cmp(struct hist_entry *a __maybe_unused,
 			    struct hist_entry *b __maybe_unused)
@@ -359,47 +364,50 @@ static int64_t hpp__nop_cmp(struct hist_entry *a __maybe_unused,
 	return 0;
 }
 
-#define HPP__COLOR_PRINT_FNS(_name)			\
+#define HPP__COLOR_PRINT_FNS(_name, _fn)		\
 	{						\
-		.header	= hpp__header_ ## _name,	\
-		.width	= hpp__width_ ## _name,		\
-		.color	= hpp__color_ ## _name,		\
-		.entry	= hpp__entry_ ## _name,		\
+		.name   = _name,			\
+		.header	= hpp__header_fn,		\
+		.width	= hpp__width_fn,		\
+		.color	= hpp__color_ ## _fn,		\
+		.entry	= hpp__entry_ ## _fn,		\
 		.cmp	= hpp__nop_cmp,			\
 		.collapse = hpp__nop_cmp,		\
-		.sort	= hpp__sort_ ## _name,		\
+		.sort	= hpp__sort_ ## _fn,		\
 	}
 
-#define HPP__COLOR_ACC_PRINT_FNS(_name)			\
+#define HPP__COLOR_ACC_PRINT_FNS(_name, _fn)		\
 	{						\
-		.header	= hpp__header_ ## _name,	\
-		.width	= hpp__width_ ## _name,		\
-		.color	= hpp__color_ ## _name,		\
-		.entry	= hpp__entry_ ## _name,		\
+		.name   = _name,			\
+		.header	= hpp__header_fn,		\
+		.width	= hpp__width_fn,		\
+		.color	= hpp__color_ ## _fn,		\
+		.entry	= hpp__entry_ ## _fn,		\
 		.cmp	= hpp__nop_cmp,			\
 		.collapse = hpp__nop_cmp,		\
-		.sort	= hpp__sort_ ## _name,		\
+		.sort	= hpp__sort_ ## _fn,		\
 	}
 
-#define HPP__PRINT_FNS(_name)				\
+#define HPP__PRINT_FNS(_name, _fn)			\
 	{						\
-		.header	= hpp__header_ ## _name,	\
-		.width	= hpp__width_ ## _name,		\
-		.entry	= hpp__entry_ ## _name,		\
+		.name   = _name,			\
+		.header	= hpp__header_fn,		\
+		.width	= hpp__width_fn,		\
+		.entry	= hpp__entry_ ## _fn,		\
 		.cmp	= hpp__nop_cmp,			\
 		.collapse = hpp__nop_cmp,		\
-		.sort	= hpp__sort_ ## _name,		\
+		.sort	= hpp__sort_ ## _fn,		\
 	}
 
 struct perf_hpp_fmt perf_hpp__format[] = {
-	HPP__COLOR_PRINT_FNS(overhead),
-	HPP__COLOR_PRINT_FNS(overhead_sys),
-	HPP__COLOR_PRINT_FNS(overhead_us),
-	HPP__COLOR_PRINT_FNS(overhead_guest_sys),
-	HPP__COLOR_PRINT_FNS(overhead_guest_us),
-	HPP__COLOR_ACC_PRINT_FNS(overhead_acc),
-	HPP__PRINT_FNS(samples),
-	HPP__PRINT_FNS(period)
+	HPP__COLOR_PRINT_FNS("Overhead", overhead),
+	HPP__COLOR_PRINT_FNS("sys", overhead_sys),
+	HPP__COLOR_PRINT_FNS("usr", overhead_us),
+	HPP__COLOR_PRINT_FNS("guest sys", overhead_guest_sys),
+	HPP__COLOR_PRINT_FNS("guest usr", overhead_guest_us),
+	HPP__COLOR_ACC_PRINT_FNS("Children", overhead_acc),
+	HPP__PRINT_FNS("Samples", samples),
+	HPP__PRINT_FNS("Period", period)
 };
 
 LIST_HEAD(perf_hpp__list);
@@ -449,9 +457,7 @@ void perf_hpp__init(void)
 
 	if (symbol_conf.cumulate_callchain) {
 		perf_hpp__column_enable(PERF_HPP__OVERHEAD_ACC);
-
-		perf_hpp__format[PERF_HPP__OVERHEAD].header =
-						hpp__header_overhead_self;
+		perf_hpp__format[PERF_HPP__OVERHEAD].name = "Self";
 	}
 
 	perf_hpp__column_enable(PERF_HPP__OVERHEAD);
@@ -517,7 +523,7 @@ void perf_hpp__cancel_cumulate(void)
 		return;
 
 	perf_hpp__column_disable(PERF_HPP__OVERHEAD_ACC);
-	perf_hpp__format[PERF_HPP__OVERHEAD].header = hpp__header_overhead;
+	perf_hpp__format[PERF_HPP__OVERHEAD].name = "Overhead";
 }
 
 void perf_hpp__setup_output_field(void)
@@ -622,3 +628,59 @@ unsigned int hists__sort_list_width(struct hists *hists)
 
 	return ret;
 }
+
+void perf_hpp__reset_width(struct perf_hpp_fmt *fmt, struct hists *hists)
+{
+	int idx;
+
+	if (perf_hpp__is_sort_entry(fmt))
+		return perf_hpp__reset_sort_width(fmt, hists);
+
+	for (idx = 0; idx < PERF_HPP__MAX_INDEX; idx++) {
+		if (fmt == &perf_hpp__format[idx])
+			break;
+	}
+
+	if (idx == PERF_HPP__MAX_INDEX)
+		return;
+
+	switch (idx) {
+	case PERF_HPP__OVERHEAD:
+	case PERF_HPP__OVERHEAD_SYS:
+	case PERF_HPP__OVERHEAD_US:
+	case PERF_HPP__OVERHEAD_ACC:
+		fmt->len = 8;
+		break;
+
+	case PERF_HPP__OVERHEAD_GUEST_SYS:
+	case PERF_HPP__OVERHEAD_GUEST_US:
+		fmt->len = 9;
+		break;
+
+	case PERF_HPP__SAMPLES:
+	case PERF_HPP__PERIOD:
+		fmt->len = 12;
+		break;
+
+	default:
+		break;
+	}
+}
+
+void perf_hpp__set_user_width(const char *width_list_str)
+{
+	struct perf_hpp_fmt *fmt;
+	const char *ptr = width_list_str;
+
+	perf_hpp__for_each_format(fmt) {
+		char *p;
+
+		int len = strtol(ptr, &p, 10);
+		fmt->user_len = len;
+
+		if (*p == ',')
+			ptr = p + 1;
+		else
+			break;
+	}
+}
diff --git a/tools/perf/ui/stdio/hist.c b/tools/perf/ui/stdio/hist.c
index 40af0ac..15b451a 100644
--- a/tools/perf/ui/stdio/hist.c
+++ b/tools/perf/ui/stdio/hist.c
@@ -395,10 +395,12 @@ size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows,
 
 	init_rem_hits();
 
-
 	perf_hpp__for_each_format(fmt)
 		perf_hpp__reset_width(fmt, hists);
 
+	if (symbol_conf.col_width_list_str)
+		perf_hpp__set_user_width(symbol_conf.col_width_list_str);
+
 	if (!show_header)
 		goto print_entries;
 
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 809b4c5..7745fec 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -899,10 +899,8 @@ int symbol__annotate(struct symbol *sym, struct map *map, size_t privsize)
 	struct kcore_extract kce;
 	bool delete_extract = false;
 
-	if (filename) {
-		snprintf(symfs_filename, sizeof(symfs_filename), "%s%s",
-			 symbol_conf.symfs, filename);
-	}
+	if (filename)
+		symbol__join_symfs(symfs_filename, filename);
 
 	if (filename == NULL) {
 		if (dso->has_build_id) {
@@ -922,8 +920,7 @@ fallback:
 		 * DSO is the same as when 'perf record' ran.
 		 */
 		filename = (char *)dso->long_name;
-		snprintf(symfs_filename, sizeof(symfs_filename), "%s%s",
-			 symbol_conf.symfs, filename);
+		symbol__join_symfs(symfs_filename, filename);
 		free_filename = false;
 	}
 
diff --git a/tools/perf/util/cache.h b/tools/perf/util/cache.h
index 7b176dd..5cf9e1b 100644
--- a/tools/perf/util/cache.h
+++ b/tools/perf/util/cache.h
@@ -22,6 +22,7 @@ typedef int (*config_fn_t)(const char *, const char *, void *);
 extern int perf_default_config(const char *, const char *, void *);
 extern int perf_config(config_fn_t fn, void *);
 extern int perf_config_int(const char *, const char *);
+extern u64 perf_config_u64(const char *, const char *);
 extern int perf_config_bool(const char *, const char *);
 extern int config_error_nonbool(const char *);
 extern const char *perf_config_dirname(const char *, const char *);
diff --git a/tools/perf/util/cloexec.c b/tools/perf/util/cloexec.c
index c5d05ec..5073c01 100644
--- a/tools/perf/util/cloexec.c
+++ b/tools/perf/util/cloexec.c
@@ -9,7 +9,7 @@ static int perf_flag_probe(void)
 {
 	/* use 'safest' configuration as used in perf_evsel__fallback() */
 	struct perf_event_attr attr = {
-		.type = PERF_COUNT_SW_CPU_CLOCK,
+		.type = PERF_TYPE_SOFTWARE,
 		.config = PERF_COUNT_SW_CPU_CLOCK,
 	};
 	int fd;
@@ -25,7 +25,7 @@ static int perf_flag_probe(void)
 		return 1;
 	}
 
-	WARN_ONCE(err != EINVAL,
+	WARN_ONCE(err != EINVAL && err != EBUSY,
 		  "perf_event_open(..., PERF_FLAG_FD_CLOEXEC) failed with unexpected error %d (%s)\n",
 		  err, strerror(err));
 
@@ -33,7 +33,7 @@ static int perf_flag_probe(void)
 	fd = sys_perf_event_open(&attr, 0, -1, -1, 0);
 	err = errno;
 
-	if (WARN_ONCE(fd < 0,
+	if (WARN_ONCE(fd < 0 && err != EBUSY,
 		      "perf_event_open(..., 0) failed unexpectedly with error %d (%s)\n",
 		      err, strerror(err)))
 		return -1;
diff --git a/tools/perf/util/color.c b/tools/perf/util/color.c
index 87b8672..f465418 100644
--- a/tools/perf/util/color.c
+++ b/tools/perf/util/color.c
@@ -335,3 +335,19 @@ int percent_color_snprintf(char *bf, size_t size, const char *fmt, ...)
 	va_end(args);
 	return value_color_snprintf(bf, size, fmt, percent);
 }
+
+int percent_color_len_snprintf(char *bf, size_t size, const char *fmt, ...)
+{
+	va_list args;
+	int len;
+	double percent;
+	const char *color;
+
+	va_start(args, fmt);
+	len = va_arg(args, int);
+	percent = va_arg(args, double);
+	va_end(args);
+
+	color = get_percent_color(percent);
+	return color_snprintf(bf, size, color, fmt, len, percent);
+}
diff --git a/tools/perf/util/color.h b/tools/perf/util/color.h
index 7ff30a6..0a594b8 100644
--- a/tools/perf/util/color.h
+++ b/tools/perf/util/color.h
@@ -41,6 +41,7 @@ int color_fprintf_ln(FILE *fp, const char *color, const char *fmt, ...);
 int color_fwrite_lines(FILE *fp, const char *color, size_t count, const char *buf);
 int value_color_snprintf(char *bf, size_t size, const char *fmt, double value);
 int percent_color_snprintf(char *bf, size_t size, const char *fmt, ...);
+int percent_color_len_snprintf(char *bf, size_t size, const char *fmt, ...);
 int percent_color_fprintf(FILE *fp, const char *fmt, double percent);
 const char *get_percent_color(double percent);
 
diff --git a/tools/perf/util/config.c b/tools/perf/util/config.c
index 1e5e2e5..9970b8b 100644
--- a/tools/perf/util/config.c
+++ b/tools/perf/util/config.c
@@ -286,6 +286,21 @@ static int parse_unit_factor(const char *end, unsigned long *val)
 	return 0;
 }
 
+static int perf_parse_llong(const char *value, long long *ret)
+{
+	if (value && *value) {
+		char *end;
+		long long val = strtoll(value, &end, 0);
+		unsigned long factor = 1;
+
+		if (!parse_unit_factor(end, &factor))
+			return 0;
+		*ret = val * factor;
+		return 1;
+	}
+	return 0;
+}
+
 static int perf_parse_long(const char *value, long *ret)
 {
 	if (value && *value) {
@@ -307,6 +322,15 @@ static void die_bad_config(const char *name)
 	die("bad config value for '%s'", name);
 }
 
+u64 perf_config_u64(const char *name, const char *value)
+{
+	long long ret = 0;
+
+	if (!perf_parse_llong(value, &ret))
+		die_bad_config(name);
+	return (u64) ret;
+}
+
 int perf_config_int(const char *name, const char *value)
 {
 	long ret = 0;
diff --git a/tools/perf/util/debug.c b/tools/perf/util/debug.c
index 71d4193..ba357f3 100644
--- a/tools/perf/util/debug.c
+++ b/tools/perf/util/debug.c
@@ -13,8 +13,12 @@
 #include "util.h"
 #include "target.h"
 
+#define NSECS_PER_SEC  1000000000ULL
+#define NSECS_PER_USEC 1000ULL
+
 int verbose;
 bool dump_trace = false, quiet = false;
+int debug_ordered_events;
 
 static int _eprintf(int level, int var, const char *fmt, va_list args)
 {
@@ -42,6 +46,35 @@ int eprintf(int level, int var, const char *fmt, ...)
 	return ret;
 }
 
+static int __eprintf_time(u64 t, const char *fmt, va_list args)
+{
+	int ret = 0;
+	u64 secs, usecs, nsecs = t;
+
+	secs   = nsecs / NSECS_PER_SEC;
+	nsecs -= secs  * NSECS_PER_SEC;
+	usecs  = nsecs / NSECS_PER_USEC;
+
+	ret = fprintf(stderr, "[%13" PRIu64 ".%06" PRIu64 "] ",
+		      secs, usecs);
+	ret += vfprintf(stderr, fmt, args);
+	return ret;
+}
+
+int eprintf_time(int level, int var, u64 t, const char *fmt, ...)
+{
+	int ret = 0;
+	va_list args;
+
+	if (var >= level) {
+		va_start(args, fmt);
+		ret = __eprintf_time(t, fmt, args);
+		va_end(args);
+	}
+
+	return ret;
+}
+
 /*
  * Overloading libtraceevent standard info print
  * function, display with -v in perf.
@@ -110,7 +143,8 @@ static struct debug_variable {
 	const char *name;
 	int *ptr;
 } debug_variables[] = {
-	{ .name = "verbose", .ptr = &verbose },
+	{ .name = "verbose",		.ptr = &verbose },
+	{ .name = "ordered-events",	.ptr = &debug_ordered_events},
 	{ .name = NULL, }
 };
 
diff --git a/tools/perf/util/debug.h b/tools/perf/util/debug.h
index 89fb6b0..6944ea3 100644
--- a/tools/perf/util/debug.h
+++ b/tools/perf/util/debug.h
@@ -10,6 +10,7 @@
 
 extern int verbose;
 extern bool quiet, dump_trace;
+extern int debug_ordered_events;
 
 #ifndef pr_fmt
 #define pr_fmt(fmt) fmt
@@ -29,6 +30,12 @@ extern bool quiet, dump_trace;
 #define pr_debug3(fmt, ...) pr_debugN(3, pr_fmt(fmt), ##__VA_ARGS__)
 #define pr_debug4(fmt, ...) pr_debugN(4, pr_fmt(fmt), ##__VA_ARGS__)
 
+#define pr_time_N(n, var, t, fmt, ...) \
+	eprintf_time(n, var, t, fmt, ##__VA_ARGS__)
+
+#define pr_oe_time(t, fmt, ...)  pr_time_N(1, debug_ordered_events, t, pr_fmt(fmt), ##__VA_ARGS__)
+#define pr_oe_time2(t, fmt, ...) pr_time_N(2, debug_ordered_events, t, pr_fmt(fmt), ##__VA_ARGS__)
+
 int dump_printf(const char *fmt, ...) __attribute__((format(printf, 1, 2)));
 void trace_event(union perf_event *event);
 
@@ -38,6 +45,7 @@ int ui__warning(const char *format, ...) __attribute__((format(printf, 1, 2)));
 void pr_stat(const char *fmt, ...);
 
 int eprintf(int level, int var, const char *fmt, ...) __attribute__((format(printf, 3, 4)));
+int eprintf_time(int level, int var, u64 t, const char *fmt, ...) __attribute__((format(printf, 4, 5)));
 
 int perf_debug_option(const char *str);
 
diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c
index 90d02c66..bdafd30 100644
--- a/tools/perf/util/dso.c
+++ b/tools/perf/util/dso.c
@@ -37,6 +37,7 @@ int dso__read_binary_type_filename(const struct dso *dso,
 {
 	char build_id_hex[BUILD_ID_SIZE * 2 + 1];
 	int ret = 0;
+	size_t len;
 
 	switch (type) {
 	case DSO_BINARY_TYPE__DEBUGLINK: {
@@ -60,26 +61,25 @@ int dso__read_binary_type_filename(const struct dso *dso,
 		break;
 
 	case DSO_BINARY_TYPE__FEDORA_DEBUGINFO:
-		snprintf(filename, size, "%s/usr/lib/debug%s.debug",
-			 symbol_conf.symfs, dso->long_name);
+		len = __symbol__join_symfs(filename, size, "/usr/lib/debug");
+		snprintf(filename + len, size - len, "%s.debug", dso->long_name);
 		break;
 
 	case DSO_BINARY_TYPE__UBUNTU_DEBUGINFO:
-		snprintf(filename, size, "%s/usr/lib/debug%s",
-			 symbol_conf.symfs, dso->long_name);
+		len = __symbol__join_symfs(filename, size, "/usr/lib/debug");
+		snprintf(filename + len, size - len, "%s", dso->long_name);
 		break;
 
 	case DSO_BINARY_TYPE__OPENEMBEDDED_DEBUGINFO:
 	{
 		const char *last_slash;
-		size_t len;
 		size_t dir_size;
 
 		last_slash = dso->long_name + dso->long_name_len;
 		while (last_slash != dso->long_name && *last_slash != '/')
 			last_slash--;
 
-		len = scnprintf(filename, size, "%s", symbol_conf.symfs);
+		len = __symbol__join_symfs(filename, size, "");
 		dir_size = last_slash - dso->long_name + 2;
 		if (dir_size > (size - len)) {
 			ret = -1;
@@ -100,26 +100,24 @@ int dso__read_binary_type_filename(const struct dso *dso,
 		build_id__sprintf(dso->build_id,
 				  sizeof(dso->build_id),
 				  build_id_hex);
-		snprintf(filename, size,
-			 "%s/usr/lib/debug/.build-id/%.2s/%s.debug",
-			 symbol_conf.symfs, build_id_hex, build_id_hex + 2);
+		len = __symbol__join_symfs(filename, size, "/usr/lib/debug/.build-id/");
+		snprintf(filename + len, size - len, "%.2s/%s.debug",
+			 build_id_hex, build_id_hex + 2);
 		break;
 
 	case DSO_BINARY_TYPE__VMLINUX:
 	case DSO_BINARY_TYPE__GUEST_VMLINUX:
 	case DSO_BINARY_TYPE__SYSTEM_PATH_DSO:
-		snprintf(filename, size, "%s%s",
-			 symbol_conf.symfs, dso->long_name);
+		__symbol__join_symfs(filename, size, dso->long_name);
 		break;
 
 	case DSO_BINARY_TYPE__GUEST_KMODULE:
-		snprintf(filename, size, "%s%s%s", symbol_conf.symfs,
-			 root_dir, dso->long_name);
+		path__join3(filename, size, symbol_conf.symfs,
+			    root_dir, dso->long_name);
 		break;
 
 	case DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE:
-		snprintf(filename, size, "%s%s", symbol_conf.symfs,
-			 dso->long_name);
+		__symbol__join_symfs(filename, size, dso->long_name);
 		break;
 
 	case DSO_BINARY_TYPE__KCORE:
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index 814e954..3b366c0 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -1061,6 +1061,8 @@ int perf_evlist__prepare_workload(struct perf_evlist *evlist, struct target *tar
 	}
 
 	if (!evlist->workload.pid) {
+		int ret;
+
 		if (pipe_output)
 			dup2(2, 1);
 
@@ -1078,8 +1080,22 @@ int perf_evlist__prepare_workload(struct perf_evlist *evlist, struct target *tar
 		/*
 		 * Wait until the parent tells us to go.
 		 */
-		if (read(go_pipe[0], &bf, 1) == -1)
-			perror("unable to read pipe");
+		ret = read(go_pipe[0], &bf, 1);
+		/*
+		 * The parent will ask for the execvp() to be performed by
+		 * writing exactly one byte, in workload.cork_fd, usually via
+		 * perf_evlist__start_workload().
+		 *
+		 * For cancelling the workload without actuallin running it,
+		 * the parent will just close workload.cork_fd, without writing
+		 * anything, i.e. read will return zero and we just exit()
+		 * here.
+		 */
+		if (ret != 1) {
+			if (ret == -1)
+				perror("unable to read pipe");
+			exit(ret);
+		}
 
 		execvp(argv[0], (char **)argv);
 
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 21a373e..0c8919d 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -633,9 +633,12 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts)
 	if (opts->period)
 		perf_evsel__set_sample_bit(evsel, PERIOD);
 
-	if (!perf_missing_features.sample_id_all &&
-	    (opts->sample_time || !opts->no_inherit ||
-	     target__has_cpu(&opts->target) || per_cpu))
+	/*
+	 * When the user explicitely disabled time don't force it here.
+	 */
+	if (opts->sample_time &&
+	    (!perf_missing_features.sample_id_all &&
+	    (!opts->no_inherit || target__has_cpu(&opts->target) || per_cpu)))
 		perf_evsel__set_sample_bit(evsel, TIME);
 
 	if (opts->raw_samples && !evsel->no_aux_samples) {
@@ -2036,6 +2039,12 @@ int perf_evsel__open_strerror(struct perf_evsel *evsel, struct target *target,
 	"No APIC? If so then you can boot the kernel with the \"lapic\" boot parameter to force-enable it.");
 #endif
 		break;
+	case EBUSY:
+		if (find_process("oprofiled"))
+			return scnprintf(msg, size,
+	"The PMU counters are busy/taken by another profiler.\n"
+	"We found oprofile daemon running, please stop it and try again.");
+		break;
 	default:
 		break;
 	}
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index 742f49a..95405a8 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -192,6 +192,7 @@ struct perf_hpp {
 };
 
 struct perf_hpp_fmt {
+	const char *name;
 	int (*header)(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
 		      struct perf_evsel *evsel);
 	int (*width)(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
@@ -207,6 +208,8 @@ struct perf_hpp_fmt {
 	struct list_head list;
 	struct list_head sort_list;
 	bool elide;
+	int len;
+	int user_len;
 };
 
 extern struct list_head perf_hpp__list;
@@ -261,17 +264,19 @@ static inline bool perf_hpp__should_skip(struct perf_hpp_fmt *format)
 }
 
 void perf_hpp__reset_width(struct perf_hpp_fmt *fmt, struct hists *hists);
+void perf_hpp__reset_sort_width(struct perf_hpp_fmt *fmt, struct hists *hists);
+void perf_hpp__set_user_width(const char *width_list_str);
 
 typedef u64 (*hpp_field_fn)(struct hist_entry *he);
 typedef int (*hpp_callback_fn)(struct perf_hpp *hpp, bool front);
 typedef int (*hpp_snprint_fn)(struct perf_hpp *hpp, const char *fmt, ...);
 
-int __hpp__fmt(struct perf_hpp *hpp, struct hist_entry *he,
-	       hpp_field_fn get_field, const char *fmt,
-	       hpp_snprint_fn print_fn, bool fmt_percent);
-int __hpp__fmt_acc(struct perf_hpp *hpp, struct hist_entry *he,
-		   hpp_field_fn get_field, const char *fmt,
-		   hpp_snprint_fn print_fn, bool fmt_percent);
+int hpp__fmt(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
+	     struct hist_entry *he, hpp_field_fn get_field,
+	     const char *fmtstr, hpp_snprint_fn print_fn, bool fmt_percent);
+int hpp__fmt_acc(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
+		 struct hist_entry *he, hpp_field_fn get_field,
+		 const char *fmtstr, hpp_snprint_fn print_fn, bool fmt_percent);
 
 static inline void advance_hpp(struct perf_hpp *hpp, int inc)
 {
diff --git a/tools/perf/util/ordered-events.c b/tools/perf/util/ordered-events.c
new file mode 100644
index 0000000..706ce1a
--- /dev/null
+++ b/tools/perf/util/ordered-events.c
@@ -0,0 +1,245 @@
+#include <linux/list.h>
+#include <linux/compiler.h>
+#include "ordered-events.h"
+#include "evlist.h"
+#include "session.h"
+#include "asm/bug.h"
+#include "debug.h"
+
+#define pr_N(n, fmt, ...) \
+	eprintf(n, debug_ordered_events, fmt, ##__VA_ARGS__)
+
+#define pr(fmt, ...) pr_N(1, pr_fmt(fmt), ##__VA_ARGS__)
+
+static void queue_event(struct ordered_events *oe, struct ordered_event *new)
+{
+	struct ordered_event *last = oe->last;
+	u64 timestamp = new->timestamp;
+	struct list_head *p;
+
+	++oe->nr_events;
+	oe->last = new;
+
+	pr_oe_time2(timestamp, "queue_event nr_events %u\n", oe->nr_events);
+
+	if (!last) {
+		list_add(&new->list, &oe->events);
+		oe->max_timestamp = timestamp;
+		return;
+	}
+
+	/*
+	 * last event might point to some random place in the list as it's
+	 * the last queued event. We expect that the new event is close to
+	 * this.
+	 */
+	if (last->timestamp <= timestamp) {
+		while (last->timestamp <= timestamp) {
+			p = last->list.next;
+			if (p == &oe->events) {
+				list_add_tail(&new->list, &oe->events);
+				oe->max_timestamp = timestamp;
+				return;
+			}
+			last = list_entry(p, struct ordered_event, list);
+		}
+		list_add_tail(&new->list, &last->list);
+	} else {
+		while (last->timestamp > timestamp) {
+			p = last->list.prev;
+			if (p == &oe->events) {
+				list_add(&new->list, &oe->events);
+				return;
+			}
+			last = list_entry(p, struct ordered_event, list);
+		}
+		list_add(&new->list, &last->list);
+	}
+}
+
+#define MAX_SAMPLE_BUFFER	(64 * 1024 / sizeof(struct ordered_event))
+static struct ordered_event *alloc_event(struct ordered_events *oe)
+{
+	struct list_head *cache = &oe->cache;
+	struct ordered_event *new = NULL;
+
+	if (!list_empty(cache)) {
+		new = list_entry(cache->next, struct ordered_event, list);
+		list_del(&new->list);
+	} else if (oe->buffer) {
+		new = oe->buffer + oe->buffer_idx;
+		if (++oe->buffer_idx == MAX_SAMPLE_BUFFER)
+			oe->buffer = NULL;
+	} else if (oe->cur_alloc_size < oe->max_alloc_size) {
+		size_t size = MAX_SAMPLE_BUFFER * sizeof(*new);
+
+		oe->buffer = malloc(size);
+		if (!oe->buffer)
+			return NULL;
+
+		pr("alloc size %" PRIu64 "B (+%zu), max %" PRIu64 "B\n",
+		   oe->cur_alloc_size, size, oe->max_alloc_size);
+
+		oe->cur_alloc_size += size;
+		list_add(&oe->buffer->list, &oe->to_free);
+
+		/* First entry is abused to maintain the to_free list. */
+		oe->buffer_idx = 2;
+		new = oe->buffer + 1;
+	} else {
+		pr("allocation limit reached %" PRIu64 "B\n", oe->max_alloc_size);
+	}
+
+	return new;
+}
+
+struct ordered_event *
+ordered_events__new(struct ordered_events *oe, u64 timestamp)
+{
+	struct ordered_event *new;
+
+	new = alloc_event(oe);
+	if (new) {
+		new->timestamp = timestamp;
+		queue_event(oe, new);
+	}
+
+	return new;
+}
+
+void ordered_events__delete(struct ordered_events *oe, struct ordered_event *event)
+{
+	list_move(&event->list, &oe->cache);
+	oe->nr_events--;
+}
+
+static int __ordered_events__flush(struct perf_session *s,
+				   struct perf_tool *tool)
+{
+	struct ordered_events *oe = &s->ordered_events;
+	struct list_head *head = &oe->events;
+	struct ordered_event *tmp, *iter;
+	struct perf_sample sample;
+	u64 limit = oe->next_flush;
+	u64 last_ts = oe->last ? oe->last->timestamp : 0ULL;
+	bool show_progress = limit == ULLONG_MAX;
+	struct ui_progress prog;
+	int ret;
+
+	if (!tool->ordered_events || !limit)
+		return 0;
+
+	if (show_progress)
+		ui_progress__init(&prog, oe->nr_events, "Processing time ordered events...");
+
+	list_for_each_entry_safe(iter, tmp, head, list) {
+		if (session_done())
+			return 0;
+
+		if (iter->timestamp > limit)
+			break;
+
+		ret = perf_evlist__parse_sample(s->evlist, iter->event, &sample);
+		if (ret)
+			pr_err("Can't parse sample, err = %d\n", ret);
+		else {
+			ret = perf_session__deliver_event(s, iter->event, &sample, tool,
+							  iter->file_offset);
+			if (ret)
+				return ret;
+		}
+
+		ordered_events__delete(oe, iter);
+		oe->last_flush = iter->timestamp;
+
+		if (show_progress)
+			ui_progress__update(&prog, 1);
+	}
+
+	if (list_empty(head))
+		oe->last = NULL;
+	else if (last_ts <= limit)
+		oe->last = list_entry(head->prev, struct ordered_event, list);
+
+	return 0;
+}
+
+int ordered_events__flush(struct perf_session *s, struct perf_tool *tool,
+			  enum oe_flush how)
+{
+	struct ordered_events *oe = &s->ordered_events;
+	static const char * const str[] = {
+		"NONE",
+		"FINAL",
+		"ROUND",
+		"HALF ",
+	};
+	int err;
+
+	switch (how) {
+	case OE_FLUSH__FINAL:
+		oe->next_flush = ULLONG_MAX;
+		break;
+
+	case OE_FLUSH__HALF:
+	{
+		struct ordered_event *first, *last;
+		struct list_head *head = &oe->events;
+
+		first = list_entry(head->next, struct ordered_event, list);
+		last = oe->last;
+
+		/* Warn if we are called before any event got allocated. */
+		if (WARN_ONCE(!last || list_empty(head), "empty queue"))
+			return 0;
+
+		oe->next_flush  = first->timestamp;
+		oe->next_flush += (last->timestamp - first->timestamp) / 2;
+		break;
+	}
+
+	case OE_FLUSH__ROUND:
+	case OE_FLUSH__NONE:
+	default:
+		break;
+	};
+
+	pr_oe_time(oe->next_flush, "next_flush - ordered_events__flush PRE  %s, nr_events %u\n",
+		   str[how], oe->nr_events);
+	pr_oe_time(oe->max_timestamp, "max_timestamp\n");
+
+	err = __ordered_events__flush(s, tool);
+
+	if (!err) {
+		if (how == OE_FLUSH__ROUND)
+			oe->next_flush = oe->max_timestamp;
+
+		oe->last_flush_type = how;
+	}
+
+	pr_oe_time(oe->next_flush, "next_flush - ordered_events__flush POST %s, nr_events %u\n",
+		   str[how], oe->nr_events);
+	pr_oe_time(oe->last_flush, "last_flush\n");
+
+	return err;
+}
+
+void ordered_events__init(struct ordered_events *oe)
+{
+	INIT_LIST_HEAD(&oe->events);
+	INIT_LIST_HEAD(&oe->cache);
+	INIT_LIST_HEAD(&oe->to_free);
+	oe->max_alloc_size = (u64) -1;
+	oe->cur_alloc_size = 0;
+}
+
+void ordered_events__free(struct ordered_events *oe)
+{
+	while (!list_empty(&oe->to_free)) {
+		struct ordered_event *event;
+
+		event = list_entry(oe->to_free.next, struct ordered_event, list);
+		list_del(&event->list);
+		free(event);
+	}
+}
diff --git a/tools/perf/util/ordered-events.h b/tools/perf/util/ordered-events.h
new file mode 100644
index 0000000..3b2f205
--- /dev/null
+++ b/tools/perf/util/ordered-events.h
@@ -0,0 +1,51 @@
+#ifndef __ORDERED_EVENTS_H
+#define __ORDERED_EVENTS_H
+
+#include <linux/types.h>
+#include "tool.h"
+
+struct perf_session;
+
+struct ordered_event {
+	u64			timestamp;
+	u64			file_offset;
+	union perf_event	*event;
+	struct list_head	list;
+};
+
+enum oe_flush {
+	OE_FLUSH__NONE,
+	OE_FLUSH__FINAL,
+	OE_FLUSH__ROUND,
+	OE_FLUSH__HALF,
+};
+
+struct ordered_events {
+	u64			last_flush;
+	u64			next_flush;
+	u64			max_timestamp;
+	u64			max_alloc_size;
+	u64			cur_alloc_size;
+	struct list_head	events;
+	struct list_head	cache;
+	struct list_head	to_free;
+	struct ordered_event	*buffer;
+	struct ordered_event	*last;
+	int			buffer_idx;
+	unsigned int		nr_events;
+	enum oe_flush		last_flush_type;
+};
+
+struct ordered_event *ordered_events__new(struct ordered_events *oe, u64 timestamp);
+void ordered_events__delete(struct ordered_events *oe, struct ordered_event *event);
+int ordered_events__flush(struct perf_session *s, struct perf_tool *tool,
+			  enum oe_flush how);
+void ordered_events__init(struct ordered_events *oe);
+void ordered_events__free(struct ordered_events *oe);
+
+static inline
+void ordered_events__set_alloc_size(struct ordered_events *oe, u64 size)
+{
+	oe->max_alloc_size = size;
+}
+#endif /* __ORDERED_EVENTS_H */
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 88dfef7..7e27f1e 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -14,6 +14,7 @@
 #include "util.h"
 #include "cpumap.h"
 #include "perf_regs.h"
+#include "asm/bug.h"
 
 static int perf_session__open(struct perf_session *session)
 {
@@ -75,9 +76,7 @@ struct perf_session *perf_session__new(struct perf_data_file *file,
 		goto out;
 
 	session->repipe = repipe;
-	INIT_LIST_HEAD(&session->ordered_samples.samples);
-	INIT_LIST_HEAD(&session->ordered_samples.sample_cache);
-	INIT_LIST_HEAD(&session->ordered_samples.to_free);
+	ordered_events__init(&session->ordered_events);
 	machines__init(&session->machines);
 
 	if (file) {
@@ -104,9 +103,9 @@ struct perf_session *perf_session__new(struct perf_data_file *file,
 	}
 
 	if (tool && tool->ordering_requires_timestamps &&
-	    tool->ordered_samples && !perf_evlist__sample_id_all(session->evlist)) {
+	    tool->ordered_events && !perf_evlist__sample_id_all(session->evlist)) {
 		dump_printf("WARNING: No sample_id_all support, falling back to unordered processing\n");
-		tool->ordered_samples = false;
+		tool->ordered_events = false;
 	}
 
 	return session;
@@ -238,7 +237,7 @@ void perf_tool__fill_defaults(struct perf_tool *tool)
 	if (tool->build_id == NULL)
 		tool->build_id = process_finished_round_stub;
 	if (tool->finished_round == NULL) {
-		if (tool->ordered_samples)
+		if (tool->ordered_events)
 			tool->finished_round = process_finished_round;
 		else
 			tool->finished_round = process_finished_round_stub;
@@ -444,87 +443,6 @@ static perf_event__swap_op perf_event__swap_ops[] = {
 	[PERF_RECORD_HEADER_MAX]	  = NULL,
 };
 
-struct sample_queue {
-	u64			timestamp;
-	u64			file_offset;
-	union perf_event	*event;
-	struct list_head	list;
-};
-
-static void perf_session_free_sample_buffers(struct perf_session *session)
-{
-	struct ordered_samples *os = &session->ordered_samples;
-
-	while (!list_empty(&os->to_free)) {
-		struct sample_queue *sq;
-
-		sq = list_entry(os->to_free.next, struct sample_queue, list);
-		list_del(&sq->list);
-		free(sq);
-	}
-}
-
-static int perf_session_deliver_event(struct perf_session *session,
-				      union perf_event *event,
-				      struct perf_sample *sample,
-				      struct perf_tool *tool,
-				      u64 file_offset);
-
-static int flush_sample_queue(struct perf_session *s,
-		       struct perf_tool *tool)
-{
-	struct ordered_samples *os = &s->ordered_samples;
-	struct list_head *head = &os->samples;
-	struct sample_queue *tmp, *iter;
-	struct perf_sample sample;
-	u64 limit = os->next_flush;
-	u64 last_ts = os->last_sample ? os->last_sample->timestamp : 0ULL;
-	bool show_progress = limit == ULLONG_MAX;
-	struct ui_progress prog;
-	int ret;
-
-	if (!tool->ordered_samples || !limit)
-		return 0;
-
-	if (show_progress)
-		ui_progress__init(&prog, os->nr_samples, "Processing time ordered events...");
-
-	list_for_each_entry_safe(iter, tmp, head, list) {
-		if (session_done())
-			return 0;
-
-		if (iter->timestamp > limit)
-			break;
-
-		ret = perf_evlist__parse_sample(s->evlist, iter->event, &sample);
-		if (ret)
-			pr_err("Can't parse sample, err = %d\n", ret);
-		else {
-			ret = perf_session_deliver_event(s, iter->event, &sample, tool,
-							 iter->file_offset);
-			if (ret)
-				return ret;
-		}
-
-		os->last_flush = iter->timestamp;
-		list_del(&iter->list);
-		list_add(&iter->list, &os->sample_cache);
-		os->nr_samples--;
-
-		if (show_progress)
-			ui_progress__update(&prog, 1);
-	}
-
-	if (list_empty(head)) {
-		os->last_sample = NULL;
-	} else if (last_ts <= limit) {
-		os->last_sample =
-			list_entry(head->prev, struct sample_queue, list);
-	}
-
-	return 0;
-}
-
 /*
  * When perf record finishes a pass on every buffers, it records this pseudo
  * event.
@@ -568,99 +486,43 @@ static int process_finished_round(struct perf_tool *tool,
 				  union perf_event *event __maybe_unused,
 				  struct perf_session *session)
 {
-	int ret = flush_sample_queue(session, tool);
-	if (!ret)
-		session->ordered_samples.next_flush = session->ordered_samples.max_timestamp;
-
-	return ret;
-}
-
-/* The queue is ordered by time */
-static void __queue_event(struct sample_queue *new, struct perf_session *s)
-{
-	struct ordered_samples *os = &s->ordered_samples;
-	struct sample_queue *sample = os->last_sample;
-	u64 timestamp = new->timestamp;
-	struct list_head *p;
-
-	++os->nr_samples;
-	os->last_sample = new;
-
-	if (!sample) {
-		list_add(&new->list, &os->samples);
-		os->max_timestamp = timestamp;
-		return;
-	}
-
-	/*
-	 * last_sample might point to some random place in the list as it's
-	 * the last queued event. We expect that the new event is close to
-	 * this.
-	 */
-	if (sample->timestamp <= timestamp) {
-		while (sample->timestamp <= timestamp) {
-			p = sample->list.next;
-			if (p == &os->samples) {
-				list_add_tail(&new->list, &os->samples);
-				os->max_timestamp = timestamp;
-				return;
-			}
-			sample = list_entry(p, struct sample_queue, list);
-		}
-		list_add_tail(&new->list, &sample->list);
-	} else {
-		while (sample->timestamp > timestamp) {
-			p = sample->list.prev;
-			if (p == &os->samples) {
-				list_add(&new->list, &os->samples);
-				return;
-			}
-			sample = list_entry(p, struct sample_queue, list);
-		}
-		list_add(&new->list, &sample->list);
-	}
+	return ordered_events__flush(session, tool, OE_FLUSH__ROUND);
 }
 
-#define MAX_SAMPLE_BUFFER	(64 * 1024 / sizeof(struct sample_queue))
-
 int perf_session_queue_event(struct perf_session *s, union perf_event *event,
-				    struct perf_sample *sample, u64 file_offset)
+			     struct perf_tool *tool, struct perf_sample *sample,
+			     u64 file_offset)
 {
-	struct ordered_samples *os = &s->ordered_samples;
-	struct list_head *sc = &os->sample_cache;
+	struct ordered_events *oe = &s->ordered_events;
 	u64 timestamp = sample->time;
-	struct sample_queue *new;
+	struct ordered_event *new;
 
 	if (!timestamp || timestamp == ~0ULL)
 		return -ETIME;
 
-	if (timestamp < s->ordered_samples.last_flush) {
-		printf("Warning: Timestamp below last timeslice flush\n");
-		return -EINVAL;
+	if (timestamp < oe->last_flush) {
+		WARN_ONCE(1, "Timestamp below last timeslice flush\n");
+
+		pr_oe_time(timestamp,      "out of order event");
+		pr_oe_time(oe->last_flush, "last flush, last_flush_type %d\n",
+			   oe->last_flush_type);
+
+		/* We could get out of order messages after forced flush. */
+		if (oe->last_flush_type != OE_FLUSH__HALF)
+			return -EINVAL;
 	}
 
-	if (!list_empty(sc)) {
-		new = list_entry(sc->next, struct sample_queue, list);
-		list_del(&new->list);
-	} else if (os->sample_buffer) {
-		new = os->sample_buffer + os->sample_buffer_idx;
-		if (++os->sample_buffer_idx == MAX_SAMPLE_BUFFER)
-			os->sample_buffer = NULL;
-	} else {
-		os->sample_buffer = malloc(MAX_SAMPLE_BUFFER * sizeof(*new));
-		if (!os->sample_buffer)
-			return -ENOMEM;
-		list_add(&os->sample_buffer->list, &os->to_free);
-		os->sample_buffer_idx = 2;
-		new = os->sample_buffer + 1;
+	new = ordered_events__new(oe, timestamp);
+	if (!new) {
+		ordered_events__flush(s, tool, OE_FLUSH__HALF);
+		new = ordered_events__new(oe, timestamp);
 	}
 
-	new->timestamp = timestamp;
+	if (!new)
+		return -ENOMEM;
+
 	new->file_offset = file_offset;
 	new->event = event;
-
-	__queue_event(new, s);
-
 	return 0;
 }
 
@@ -920,11 +782,10 @@ perf_session__deliver_sample(struct perf_session *session,
 					    &sample->read.one, machine);
 }
 
-static int perf_session_deliver_event(struct perf_session *session,
-				      union perf_event *event,
-				      struct perf_sample *sample,
-				      struct perf_tool *tool,
-				      u64 file_offset)
+int perf_session__deliver_event(struct perf_session *session,
+				union perf_event *event,
+				struct perf_sample *sample,
+				struct perf_tool *tool, u64 file_offset)
 {
 	struct perf_evsel *evsel;
 	struct machine *machine;
@@ -1062,15 +923,15 @@ static s64 perf_session__process_event(struct perf_session *session,
 	if (ret)
 		return ret;
 
-	if (tool->ordered_samples) {
-		ret = perf_session_queue_event(session, event, &sample,
+	if (tool->ordered_events) {
+		ret = perf_session_queue_event(session, event, tool, &sample,
 					       file_offset);
 		if (ret != -ETIME)
 			return ret;
 	}
 
-	return perf_session_deliver_event(session, event, &sample, tool,
-					  file_offset);
+	return perf_session__deliver_event(session, event, &sample, tool,
+					   file_offset);
 }
 
 void perf_event_header__bswap(struct perf_event_header *hdr)
@@ -1222,12 +1083,11 @@ more:
 		goto more;
 done:
 	/* do the final flush for ordered samples */
-	session->ordered_samples.next_flush = ULLONG_MAX;
-	err = flush_sample_queue(session, tool);
+	err = ordered_events__flush(session, tool, OE_FLUSH__FINAL);
 out_err:
 	free(buf);
 	perf_session__warn_about_errors(session, tool);
-	perf_session_free_sample_buffers(session);
+	ordered_events__free(&session->ordered_events);
 	return err;
 }
 
@@ -1368,12 +1228,11 @@ more:
 
 out:
 	/* do the final flush for ordered samples */
-	session->ordered_samples.next_flush = ULLONG_MAX;
-	err = flush_sample_queue(session, tool);
+	err = ordered_events__flush(session, tool, OE_FLUSH__FINAL);
 out_err:
 	ui_progress__finish();
 	perf_session__warn_about_errors(session, tool);
-	perf_session_free_sample_buffers(session);
+	ordered_events__free(&session->ordered_events);
 	session->one_mmap = false;
 	return err;
 }
diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h
index 0321013..0630e65 100644
--- a/tools/perf/util/session.h
+++ b/tools/perf/util/session.h
@@ -9,26 +9,13 @@
 #include "symbol.h"
 #include "thread.h"
 #include "data.h"
+#include "ordered-events.h"
 #include <linux/rbtree.h>
 #include <linux/perf_event.h>
 
-struct sample_queue;
 struct ip_callchain;
 struct thread;
 
-struct ordered_samples {
-	u64			last_flush;
-	u64			next_flush;
-	u64			max_timestamp;
-	struct list_head	samples;
-	struct list_head	sample_cache;
-	struct list_head	to_free;
-	struct sample_queue	*sample_buffer;
-	struct sample_queue	*last_sample;
-	int			sample_buffer_idx;
-	unsigned int		nr_samples;
-};
-
 struct perf_session {
 	struct perf_header	header;
 	struct machines		machines;
@@ -39,7 +26,7 @@ struct perf_session {
 	bool			one_mmap;
 	void			*one_mmap_addr;
 	u64			one_mmap_offset;
-	struct ordered_samples	ordered_samples;
+	struct ordered_events	ordered_events;
 	struct perf_data_file	*file;
 };
 
@@ -65,10 +52,16 @@ int perf_session__process_events(struct perf_session *session,
 				 struct perf_tool *tool);
 
 int perf_session_queue_event(struct perf_session *s, union perf_event *event,
-			     struct perf_sample *sample, u64 file_offset);
+			     struct perf_tool *tool, struct perf_sample *sample,
+			     u64 file_offset);
 
 void perf_tool__fill_defaults(struct perf_tool *tool);
 
+int perf_session__deliver_event(struct perf_session *session,
+				union perf_event *event,
+				struct perf_sample *sample,
+				struct perf_tool *tool, u64 file_offset);
+
 int perf_session__resolve_callchain(struct perf_session *session,
 				    struct perf_evsel *evsel,
 				    struct thread *thread,
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index 14e5a03..b4a805e 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -70,12 +70,14 @@ static int hist_entry__thread_snprintf(struct hist_entry *he, char *bf,
 				       size_t size, unsigned int width)
 {
 	const char *comm = thread__comm_str(he->thread);
-	return repsep_snprintf(bf, size, "%*s:%5d", width - 6,
-			       comm ?: "", he->thread->tid);
+
+	width = max(7U, width) - 6;
+	return repsep_snprintf(bf, size, "%5d:%-*.*s", he->thread->tid,
+			       width, width, comm ?: "");
 }
 
 struct sort_entry sort_thread = {
-	.se_header	= "Command:  Pid",
+	.se_header	= "  Pid:Command",
 	.se_cmp		= sort__thread_cmp,
 	.se_snprintf	= hist_entry__thread_snprintf,
 	.se_width_idx	= HISTC_THREAD,
@@ -106,7 +108,7 @@ sort__comm_sort(struct hist_entry *left, struct hist_entry *right)
 static int hist_entry__comm_snprintf(struct hist_entry *he, char *bf,
 				     size_t size, unsigned int width)
 {
-	return repsep_snprintf(bf, size, "%*s", width, comm__str(he->comm));
+	return repsep_snprintf(bf, size, "%-*.*s", width, width, comm__str(he->comm));
 }
 
 struct sort_entry sort_comm = {
@@ -152,10 +154,10 @@ static int _hist_entry__dso_snprintf(struct map *map, char *bf,
 	if (map && map->dso) {
 		const char *dso_name = !verbose ? map->dso->short_name :
 			map->dso->long_name;
-		return repsep_snprintf(bf, size, "%-*s", width, dso_name);
+		return repsep_snprintf(bf, size, "%-*.*s", width, width, dso_name);
 	}
 
-	return repsep_snprintf(bf, size, "%-*s", width, "[unknown]");
+	return repsep_snprintf(bf, size, "%-*.*s", width, width, "[unknown]");
 }
 
 static int hist_entry__dso_snprintf(struct hist_entry *he, char *bf,
@@ -257,7 +259,10 @@ static int _hist_entry__sym_snprintf(struct map *map, struct symbol *sym,
 				       width - ret, "");
 	}
 
-	return ret;
+	if (ret > width)
+		bf[width] = '\0';
+
+	return width;
 }
 
 static int hist_entry__sym_snprintf(struct hist_entry *he, char *bf,
@@ -302,10 +307,9 @@ sort__srcline_cmp(struct hist_entry *left, struct hist_entry *right)
 }
 
 static int hist_entry__srcline_snprintf(struct hist_entry *he, char *bf,
-					size_t size,
-					unsigned int width __maybe_unused)
+					size_t size, unsigned int width)
 {
-	return repsep_snprintf(bf, size, "%s", he->srcline);
+	return repsep_snprintf(bf, size, "%*.*-s", width, width, he->srcline);
 }
 
 struct sort_entry sort_srcline = {
@@ -332,7 +336,7 @@ sort__parent_cmp(struct hist_entry *left, struct hist_entry *right)
 static int hist_entry__parent_snprintf(struct hist_entry *he, char *bf,
 				       size_t size, unsigned int width)
 {
-	return repsep_snprintf(bf, size, "%-*s", width,
+	return repsep_snprintf(bf, size, "%-*.*s", width, width,
 			      he->parent ? he->parent->name : "[other]");
 }
 
@@ -354,7 +358,7 @@ sort__cpu_cmp(struct hist_entry *left, struct hist_entry *right)
 static int hist_entry__cpu_snprintf(struct hist_entry *he, char *bf,
 				    size_t size, unsigned int width)
 {
-	return repsep_snprintf(bf, size, "%*d", width, he->cpu);
+	return repsep_snprintf(bf, size, "%*.*d", width, width, he->cpu);
 }
 
 struct sort_entry sort_cpu = {
@@ -484,7 +488,7 @@ static int hist_entry__mispredict_snprintf(struct hist_entry *he, char *bf,
 	else if (he->branch_info->flags.mispred)
 		out = "Y";
 
-	return repsep_snprintf(bf, size, "%-*s", width, out);
+	return repsep_snprintf(bf, size, "%-*.*s", width, width, out);
 }
 
 /* --sort daddr_sym */
@@ -1194,7 +1198,7 @@ bool perf_hpp__same_sort_entry(struct perf_hpp_fmt *a, struct perf_hpp_fmt *b)
 	return hse_a->se == hse_b->se;
 }
 
-void perf_hpp__reset_width(struct perf_hpp_fmt *fmt, struct hists *hists)
+void perf_hpp__reset_sort_width(struct perf_hpp_fmt *fmt, struct hists *hists)
 {
 	struct hpp_sort_entry *hse;
 
@@ -1202,20 +1206,21 @@ void perf_hpp__reset_width(struct perf_hpp_fmt *fmt, struct hists *hists)
 		return;
 
 	hse = container_of(fmt, struct hpp_sort_entry, hpp);
-	hists__new_col_len(hists, hse->se->se_width_idx,
-			   strlen(hse->se->se_header));
+	hists__new_col_len(hists, hse->se->se_width_idx, strlen(fmt->name));
 }
 
 static int __sort__hpp_header(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
 			      struct perf_evsel *evsel)
 {
 	struct hpp_sort_entry *hse;
-	size_t len;
+	size_t len = fmt->user_len;
 
 	hse = container_of(fmt, struct hpp_sort_entry, hpp);
-	len = hists__col_len(&evsel->hists, hse->se->se_width_idx);
 
-	return scnprintf(hpp->buf, hpp->size, "%-*s", len, hse->se->se_header);
+	if (!len)
+		len = hists__col_len(&evsel->hists, hse->se->se_width_idx);
+
+	return scnprintf(hpp->buf, hpp->size, "%-*.*s", len, len, fmt->name);
 }
 
 static int __sort__hpp_width(struct perf_hpp_fmt *fmt,
@@ -1223,20 +1228,26 @@ static int __sort__hpp_width(struct perf_hpp_fmt *fmt,
 			     struct perf_evsel *evsel)
 {
 	struct hpp_sort_entry *hse;
+	size_t len = fmt->user_len;
 
 	hse = container_of(fmt, struct hpp_sort_entry, hpp);
 
-	return hists__col_len(&evsel->hists, hse->se->se_width_idx);
+	if (!len)
+		len = hists__col_len(&evsel->hists, hse->se->se_width_idx);
+
+	return len;
 }
 
 static int __sort__hpp_entry(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
 			     struct hist_entry *he)
 {
 	struct hpp_sort_entry *hse;
-	size_t len;
+	size_t len = fmt->user_len;
 
 	hse = container_of(fmt, struct hpp_sort_entry, hpp);
-	len = hists__col_len(he->hists, hse->se->se_width_idx);
+
+	if (!len)
+		len = hists__col_len(he->hists, hse->se->se_width_idx);
 
 	return hse->se->se_snprintf(he, hpp->buf, hpp->size, len);
 }
@@ -1253,6 +1264,7 @@ __sort_dimension__alloc_hpp(struct sort_dimension *sd)
 	}
 
 	hse->se = sd->entry;
+	hse->hpp.name = sd->entry->se_header;
 	hse->hpp.header = __sort__hpp_header;
 	hse->hpp.width = __sort__hpp_width;
 	hse->hpp.entry = __sort__hpp_entry;
@@ -1265,6 +1277,8 @@ __sort_dimension__alloc_hpp(struct sort_dimension *sd)
 	INIT_LIST_HEAD(&hse->hpp.list);
 	INIT_LIST_HEAD(&hse->hpp.sort_list);
 	hse->hpp.elide = false;
+	hse->hpp.len = 0;
+	hse->hpp.user_len = 0;
 
 	return hse;
 }
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index eb06746..f134ec1 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -1468,8 +1468,7 @@ int dso__load_vmlinux(struct dso *dso, struct map *map,
 	if (vmlinux[0] == '/')
 		snprintf(symfs_vmlinux, sizeof(symfs_vmlinux), "%s", vmlinux);
 	else
-		snprintf(symfs_vmlinux, sizeof(symfs_vmlinux), "%s%s",
-			 symbol_conf.symfs, vmlinux);
+		symbol__join_symfs(symfs_vmlinux, vmlinux);
 
 	if (dso->kernel == DSO_TYPE_GUEST_KERNEL)
 		symtab_type = DSO_BINARY_TYPE__GUEST_VMLINUX;
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index e7295e9..196b291 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -13,6 +13,7 @@
 #include <libgen.h>
 #include "build-id.h"
 #include "event.h"
+#include "util.h"
 
 #ifdef HAVE_LIBELF_SUPPORT
 #include <libelf.h>
@@ -143,6 +144,14 @@ struct symbol_conf {
 };
 
 extern struct symbol_conf symbol_conf;
+
+static inline int __symbol__join_symfs(char *bf, size_t size, const char *path)
+{
+	return path__join(bf, size, symbol_conf.symfs, path);
+}
+
+#define symbol__join_symfs(bf, path) __symbol__join_symfs(bf, sizeof(bf), path)
+
 extern int vmlinux_path__nr_entries;
 extern char **vmlinux_path;
 
diff --git a/tools/perf/util/tool.h b/tools/perf/util/tool.h
index 4385816..f116369 100644
--- a/tools/perf/util/tool.h
+++ b/tools/perf/util/tool.h
@@ -40,7 +40,7 @@ struct perf_tool {
 	event_op2	tracing_data;
 	event_op2	finished_round,
 			build_id;
-	bool		ordered_samples;
+	bool		ordered_events;
 	bool		ordering_requires_timestamps;
 };
 
diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c
index e52e746..b82a93c 100644
--- a/tools/perf/util/util.c
+++ b/tools/perf/util/util.c
@@ -536,3 +536,39 @@ void mem_bswap_64(void *src, int byte_size)
 		++m;
 	}
 }
+
+bool find_process(const char *name)
+{
+	size_t len = strlen(name);
+	DIR *dir;
+	struct dirent *d;
+	int ret = -1;
+
+	dir = opendir(procfs__mountpoint());
+	if (!dir)
+		return -1;
+
+	/* Walk through the directory. */
+	while (ret && (d = readdir(dir)) != NULL) {
+		char path[PATH_MAX];
+		char *data;
+		size_t size;
+
+		if ((d->d_type != DT_DIR) ||
+		     !strcmp(".", d->d_name) ||
+		     !strcmp("..", d->d_name))
+			continue;
+
+		scnprintf(path, sizeof(path), "%s/%s/comm",
+			  procfs__mountpoint(), d->d_name);
+
+		if (filename__read_str(path, &data, &size))
+			continue;
+
+		ret = strncmp(name, data, len);
+		free(data);
+	}
+
+	closedir(dir);
+	return ret ? false : true;
+}
diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h
index 6686436..03a1ea2 100644
--- a/tools/perf/util/util.h
+++ b/tools/perf/util/util.h
@@ -68,6 +68,7 @@
 #include <sys/socket.h>
 #include <sys/ioctl.h>
 #include <inttypes.h>
+#include <linux/kernel.h>
 #include <linux/magic.h>
 #include <linux/types.h>
 #include <sys/ttydefaults.h>
@@ -317,6 +318,21 @@ unsigned long parse_tag_value(const char *str, struct parse_tag *tags);
 
 #define SRCLINE_UNKNOWN  ((char *) "??:0")
 
+static inline int path__join(char *bf, size_t size,
+			     const char *path1, const char *path2)
+{
+	return scnprintf(bf, size, "%s%s%s", path1, path1[0] ? "/" : "", path2);
+}
+
+static inline int path__join3(char *bf, size_t size,
+			      const char *path1, const char *path2,
+			      const char *path3)
+{
+	return scnprintf(bf, size, "%s%s%s%s%s",
+			 path1, path1[0] ? "/" : "",
+			 path2, path2[0] ? "/" : "", path3);
+}
+
 struct dso;
 
 char *get_srcline(struct dso *dso, unsigned long addr);
@@ -330,4 +346,5 @@ void mem_bswap_64(void *src, int byte_size);
 void mem_bswap_32(void *src, int byte_size);
 
 const char *get_filename_for_perf_kvm(void);
+bool find_process(const char *name);
 #endif /* GIT_COMPAT_UTIL_H */