Merge branch 'for-5.1/nfit/ars' into libnvdimm-for-next

Merge several updates to the ARS implementation. Highlights include:

* Support retrieval of short-ARS results if the ARS state is "requires
  continuation", and even if the "no_init_ars" module parameter is
  specified.
* Allow busy-polling of the kernel ARS state by allowing root to reset
  the exponential back-off timer.
* Filter potentially stale ARS results by tracking query-ARS relative to
  the previous start-ARS.

15 files changed, 115 insertions, 45 deletions

diff --git a/tools/perf/Documentation/perf-c2c.txt b/tools/perf/Documentation/perf-c2c.txt
index 095aebdc5bb7..e6150f21267d 100644
--- a/tools/perf/Documentation/perf-c2c.txt
+++ b/tools/perf/Documentation/perf-c2c.txt
@@ -19,8 +19,11 @@ C2C stands for Cache To Cache.
 The perf c2c tool provides means for Shared Data C2C/HITM analysis. It allows
 you to track down the cacheline contentions.
 
-The tool is based on x86's load latency and precise store facility events
-provided by Intel CPUs. These events provide:
+On x86, the tool is based on load latency and precise store facility events
+provided by Intel CPUs. On PowerPC, the tool uses random instruction sampling
+with thresholding feature.
+
+These events provide:
   - memory address of the access
   - type of the access (load and store details)
   - latency (in cycles) of the load access
@@ -46,7 +49,7 @@ RECORD OPTIONS
 
 -l::
 --ldlat::
-	Configure mem-loads latency.
+	Configure mem-loads latency. (x86 only)
 
 -k::
 --all-kernel::
@@ -119,11 +122,16 @@ Following perf record options are configured by default:
   -W,-d,--phys-data,--sample-cpu
 
 Unless specified otherwise with '-e' option, following events are monitored by
-default:
+default on x86:
 
   cpu/mem-loads,ldlat=30/P
   cpu/mem-stores/P
 
+and following on PowerPC:
+
+  cpu/mem-loads/
+  cpu/mem-stores/
+
 User can pass any 'perf record' option behind '--' mark, like (to enable
 callchains and system wide monitoring):
 
diff --git a/tools/perf/Documentation/perf-mem.txt b/tools/perf/Documentation/perf-mem.txt
index f8d2167cf3e7..199ea0f0a6c0 100644
--- a/tools/perf/Documentation/perf-mem.txt
+++ b/tools/perf/Documentation/perf-mem.txt
@@ -82,7 +82,7 @@ RECORD OPTIONS
 	Be more verbose (show counter open errors, etc)
 
 --ldlat <n>::
-	Specify desired latency for loads event.
+	Specify desired latency for loads event. (x86 only)
 
 In addition, for report all perf report options are valid, and for record
 all perf record options.
diff --git a/tools/perf/arch/powerpc/util/Build b/tools/perf/arch/powerpc/util/Build
index 2e6595310420..ba98bd006488 100644
--- a/tools/perf/arch/powerpc/util/Build
+++ b/tools/perf/arch/powerpc/util/Build
@@ -2,6 +2,7 @@ libperf-y += header.o
 libperf-y += sym-handling.o
 libperf-y += kvm-stat.o
 libperf-y += perf_regs.o
+libperf-y += mem-events.o
 
 libperf-$(CONFIG_DWARF) += dwarf-regs.o
 libperf-$(CONFIG_DWARF) += skip-callchain-idx.o
diff --git a/tools/perf/arch/powerpc/util/mem-events.c b/tools/perf/arch/powerpc/util/mem-events.c
new file mode 100644
index 000000000000..d08311f04e95
--- /dev/null
+++ b/tools/perf/arch/powerpc/util/mem-events.c
@@ -0,0 +1,11 @@
+// SPDX-License-Identifier: GPL-2.0
+#include "mem-events.h"
+
+/* PowerPC does not support 'ldlat' parameter. */
+char *perf_mem_events__name(int i)
+{
+	if (i == PERF_MEM_EVENTS__LOAD)
+		return (char *) "cpu/mem-loads/";
+
+	return (char *) "cpu/mem-stores/";
+}
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index d079f36d342d..ac221f137ed2 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -1681,13 +1681,8 @@ static void perf_sample__fprint_metric(struct perf_script *script,
 		.force_header = false,
 	};
 	struct perf_evsel *ev2;
-	static bool init;
 	u64 val;
 
-	if (!init) {
-		perf_stat__init_shadow_stats();
-		init = true;
-	}
 	if (!evsel->stats)
 		perf_evlist__alloc_stats(script->session->evlist, false);
 	if (evsel_script(evsel->leader)->gnum++ == 0)
@@ -1794,7 +1789,7 @@ static void process_event(struct perf_script *script,
 		return;
 	}
 
-	if (PRINT_FIELD(TRACE)) {
+	if (PRINT_FIELD(TRACE) && sample->raw_data) {
 		event_format__fprintf(evsel->tp_format, sample->cpu,
 				      sample->raw_data, sample->raw_size, fp);
 	}
@@ -2359,6 +2354,8 @@ static int __cmd_script(struct perf_script *script)
 
 	signal(SIGINT, sig_handler);
 
+	perf_stat__init_shadow_stats();
+
 	/* override event processing functions */
 	if (script->show_task_events) {
 		script->tool.comm = process_comm_event;
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index ed4583128b9c..b36061cd1ab8 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -2514,19 +2514,30 @@ static size_t trace__fprintf_thread_summary(struct trace *trace, FILE *fp);
 
 static bool perf_evlist__add_vfs_getname(struct perf_evlist *evlist)
 {
-	struct perf_evsel *evsel = perf_evsel__newtp("probe", "vfs_getname");
+	bool found = false;
+	struct perf_evsel *evsel, *tmp;
+	struct parse_events_error err = { .idx = 0, };
+	int ret = parse_events(evlist, "probe:vfs_getname*", &err);
 
-	if (IS_ERR(evsel))
+	if (ret)
 		return false;
 
-	if (perf_evsel__field(evsel, "pathname") == NULL) {
+	evlist__for_each_entry_safe(evlist, evsel, tmp) {
+		if (!strstarts(perf_evsel__name(evsel), "probe:vfs_getname"))
+			continue;
+
+		if (perf_evsel__field(evsel, "pathname")) {
+			evsel->handler = trace__vfs_getname;
+			found = true;
+			continue;
+		}
+
+		list_del_init(&evsel->node);
+		evsel->evlist = NULL;
 		perf_evsel__delete(evsel);
-		return false;
 	}
 
-	evsel->handler = trace__vfs_getname;
-	perf_evlist__add(evlist, evsel);
-	return true;
+	return found;
 }
 
 static struct perf_evsel *perf_evsel__new_pgfault(u64 config)
diff --git a/tools/perf/tests/attr.py b/tools/perf/tests/attr.py
index 44090a9a19f3..e952127e4fb0 100644
--- a/tools/perf/tests/attr.py
+++ b/tools/perf/tests/attr.py
@@ -1,6 +1,8 @@
 #! /usr/bin/python
 # SPDX-License-Identifier: GPL-2.0
 
+from __future__ import print_function
+
 import os
 import sys
 import glob
@@ -8,7 +10,11 @@ import optparse
 import tempfile
 import logging
 import shutil
-import ConfigParser
+
+try:
+    import configparser
+except ImportError:
+    import ConfigParser as configparser
 
 def data_equal(a, b):
     # Allow multiple values in assignment separated by '|'
@@ -100,20 +106,20 @@ class Event(dict):
     def equal(self, other):
         for t in Event.terms:
             log.debug("      [%s] %s %s" % (t, self[t], other[t]));
-            if not self.has_key(t) or not other.has_key(t):
+            if t not in self or t not in other:
                 return False
             if not data_equal(self[t], other[t]):
                 return False
         return True
 
     def optional(self):
-        if self.has_key('optional') and self['optional'] == '1':
+        if 'optional' in self and self['optional'] == '1':
             return True
         return False
 
     def diff(self, other):
         for t in Event.terms:
-            if not self.has_key(t) or not other.has_key(t):
+            if t not in self or t not in other:
                 continue
             if not data_equal(self[t], other[t]):
                 log.warning("expected %s=%s, got %s" % (t, self[t], other[t]))
@@ -134,7 +140,7 @@ class Event(dict):
 #   - expected values assignments
 class Test(object):
     def __init__(self, path, options):
-        parser = ConfigParser.SafeConfigParser()
+        parser = configparser.SafeConfigParser()
         parser.read(path)
 
         log.warning("running '%s'" % path)
@@ -193,7 +199,7 @@ class Test(object):
         return True
 
     def load_events(self, path, events):
-        parser_event = ConfigParser.SafeConfigParser()
+        parser_event = configparser.SafeConfigParser()
         parser_event.read(path)
 
         # The event record section header contains 'event' word,
@@ -207,7 +213,7 @@ class Test(object):
             # Read parent event if there's any
             if (':' in section):
                 base = section[section.index(':') + 1:]
-                parser_base = ConfigParser.SafeConfigParser()
+                parser_base = configparser.SafeConfigParser()
                 parser_base.read(self.test_dir + '/' + base)
                 base_items = parser_base.items('event')
 
@@ -322,9 +328,9 @@ def run_tests(options):
     for f in glob.glob(options.test_dir + '/' + options.test):
         try:
             Test(f, options).run()
-        except Unsup, obj:
+        except Unsup as obj:
             log.warning("unsupp  %s" % obj.getMsg())
-        except Notest, obj:
+        except Notest as obj:
             log.warning("skipped %s" % obj.getMsg())
 
 def setup_log(verbose):
@@ -363,7 +369,7 @@ def main():
     parser.add_option("-p", "--perf",
                       action="store", type="string", dest="perf")
     parser.add_option("-v", "--verbose",
-                      action="count", dest="verbose")
+                      default=0, action="count", dest="verbose")
 
     options, args = parser.parse_args()
     if args:
@@ -373,7 +379,7 @@ def main():
     setup_log(options.verbose)
 
     if not options.test_dir:
-        print 'FAILED no -d option specified'
+        print('FAILED no -d option specified')
         sys.exit(-1)
 
     if not options.test:
@@ -382,8 +388,8 @@ def main():
     try:
         run_tests(options)
 
-    except Fail, obj:
-        print "FAILED %s" % obj.getMsg();
+    except Fail as obj:
+        print("FAILED %s" % obj.getMsg())
         sys.exit(-1)
 
     sys.exit(0)
diff --git a/tools/perf/tests/evsel-tp-sched.c b/tools/perf/tests/evsel-tp-sched.c
index 5f8501c68da4..5cbba70bcdd0 100644
--- a/tools/perf/tests/evsel-tp-sched.c
+++ b/tools/perf/tests/evsel-tp-sched.c
@@ -17,7 +17,7 @@ static int perf_evsel__test_field(struct perf_evsel *evsel, const char *name,
 		return -1;
 	}
 
-	is_signed = !!(field->flags | TEP_FIELD_IS_SIGNED);
+	is_signed = !!(field->flags & TEP_FIELD_IS_SIGNED);
 	if (should_be_signed && !is_signed) {
 		pr_debug("%s: \"%s\" signedness(%d) is wrong, should be %d\n",
 			 evsel->name, name, is_signed, should_be_signed);
diff --git a/tools/perf/ui/browsers/annotate.c b/tools/perf/ui/browsers/annotate.c
index 1d00e5ec7906..82e16bf84466 100644
--- a/tools/perf/ui/browsers/annotate.c
+++ b/tools/perf/ui/browsers/annotate.c
@@ -224,20 +224,24 @@ static unsigned int annotate_browser__refresh(struct ui_browser *browser)
 	return ret;
 }
 
-static int disasm__cmp(struct annotation_line *a, struct annotation_line *b)
+static double disasm__cmp(struct annotation_line *a, struct annotation_line *b,
+						  int percent_type)
 {
 	int i;
 
 	for (i = 0; i < a->data_nr; i++) {
-		if (a->data[i].percent == b->data[i].percent)
+		if (a->data[i].percent[percent_type] == b->data[i].percent[percent_type])
 			continue;
-		return a->data[i].percent < b->data[i].percent;
+		return a->data[i].percent[percent_type] -
+			   b->data[i].percent[percent_type];
 	}
 	return 0;
 }
 
-static void disasm_rb_tree__insert(struct rb_root *root, struct annotation_line *al)
+static void disasm_rb_tree__insert(struct annotate_browser *browser,
+				struct annotation_line *al)
 {
+	struct rb_root *root = &browser->entries;
 	struct rb_node **p = &root->rb_node;
 	struct rb_node *parent = NULL;
 	struct annotation_line *l;
@@ -246,7 +250,7 @@ static void disasm_rb_tree__insert(struct rb_root *root, struct annotation_line
 		parent = *p;
 		l = rb_entry(parent, struct annotation_line, rb_node);
 
-		if (disasm__cmp(al, l))
+		if (disasm__cmp(al, l, browser->opts->percent_type) < 0)
 			p = &(*p)->rb_left;
 		else
 			p = &(*p)->rb_right;
@@ -329,7 +333,7 @@ static void annotate_browser__calc_percent(struct annotate_browser *browser,
 			RB_CLEAR_NODE(&pos->al.rb_node);
 			continue;
 		}
-		disasm_rb_tree__insert(&browser->entries, &pos->al);
+		disasm_rb_tree__insert(browser, &pos->al);
 	}
 	pthread_mutex_unlock(&notes->lock);
 
diff --git a/tools/perf/util/c++/clang.cpp b/tools/perf/util/c++/clang.cpp
index 89512504551b..39c0004f2886 100644
--- a/tools/perf/util/c++/clang.cpp
+++ b/tools/perf/util/c++/clang.cpp
@@ -160,7 +160,7 @@ getBPFObjectFromModule(llvm::Module *Module)
 	}
 	PM.run(*Module);
 
-	return std::move(Buffer);
+	return Buffer;
 }
 
 }
diff --git a/tools/perf/util/cpumap.c b/tools/perf/util/cpumap.c
index 1ccbd3342069..383674f448fc 100644
--- a/tools/perf/util/cpumap.c
+++ b/tools/perf/util/cpumap.c
@@ -134,7 +134,12 @@ struct cpu_map *cpu_map__new(const char *cpu_list)
 	if (!cpu_list)
 		return cpu_map__read_all_cpu_map();
 
-	if (!isdigit(*cpu_list))
+	/*
+	 * must handle the case of empty cpumap to cover
+	 * TOPOLOGY header for NUMA nodes with no CPU
+	 * ( e.g., because of CPU hotplug)
+	 */
+	if (!isdigit(*cpu_list) && *cpu_list != '\0')
 		goto out;
 
 	while (isdigit(*cpu_list)) {
@@ -181,8 +186,10 @@ struct cpu_map *cpu_map__new(const char *cpu_list)
 
 	if (nr_cpus > 0)
 		cpus = cpu_map__trim_new(nr_cpus, tmp_cpus);
-	else
+	else if (*cpu_list != '\0')
 		cpus = cpu_map__default_new();
+	else
+		cpus = cpu_map__dummy_new();
 invalid:
 	free(tmp_cpus);
 out:
diff --git a/tools/perf/util/mem-events.c b/tools/perf/util/mem-events.c
index 93f74d8d3cdd..42c3e5a229d2 100644
--- a/tools/perf/util/mem-events.c
+++ b/tools/perf/util/mem-events.c
@@ -28,7 +28,7 @@ struct perf_mem_event perf_mem_events[PERF_MEM_EVENTS__MAX] = {
 static char mem_loads_name[100];
 static bool mem_loads_name__init;
 
-char *perf_mem_events__name(int i)
+char * __weak perf_mem_events__name(int i)
 {
 	if (i == PERF_MEM_EVENTS__LOAD) {
 		if (!mem_loads_name__init) {
diff --git a/tools/perf/util/ordered-events.c b/tools/perf/util/ordered-events.c
index 897589507d97..ea523d3b248f 100644
--- a/tools/perf/util/ordered-events.c
+++ b/tools/perf/util/ordered-events.c
@@ -391,8 +391,10 @@ void ordered_events__free(struct ordered_events *oe)
 	 * Current buffer might not have all the events allocated
 	 * yet, we need to free only allocated ones ...
 	 */
-	list_del(&oe->buffer->list);
-	ordered_events_buffer__free(oe->buffer, oe->buffer_idx, oe);
+	if (oe->buffer) {
+		list_del(&oe->buffer->list);
+		ordered_events_buffer__free(oe->buffer, oe->buffer_idx, oe);
+	}
 
 	/* ... and continue with the rest */
 	list_for_each_entry_safe(buffer, tmp, &oe->to_free, list) {
diff --git a/tools/perf/util/setup.py b/tools/perf/util/setup.py
index 63f758c655d5..64d1f36dee99 100644
--- a/tools/perf/util/setup.py
+++ b/tools/perf/util/setup.py
@@ -17,6 +17,8 @@ if cc == "clang":
             vars[var] = sub("-mcet", "", vars[var])
         if not clang_has_option("-fcf-protection"):
             vars[var] = sub("-fcf-protection", "", vars[var])
+        if not clang_has_option("-fstack-clash-protection"):
+            vars[var] = sub("-fstack-clash-protection", "", vars[var])
 
 from distutils.core import setup, Extension
 
diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c
index 66a84d5846c8..dca7dfae69ad 100644
--- a/tools/perf/util/symbol-elf.c
+++ b/tools/perf/util/symbol-elf.c
@@ -19,6 +19,20 @@
 #define EM_AARCH64	183  /* ARM 64 bit */
 #endif
 
+#ifndef ELF32_ST_VISIBILITY
+#define ELF32_ST_VISIBILITY(o)	((o) & 0x03)
+#endif
+
+/* For ELF64 the definitions are the same.  */
+#ifndef ELF64_ST_VISIBILITY
+#define ELF64_ST_VISIBILITY(o)	ELF32_ST_VISIBILITY (o)
+#endif
+
+/* How to extract information held in the st_other field.  */
+#ifndef GELF_ST_VISIBILITY
+#define GELF_ST_VISIBILITY(val)	ELF64_ST_VISIBILITY (val)
+#endif
+
 typedef Elf64_Nhdr GElf_Nhdr;
 
 #ifdef HAVE_CPLUS_DEMANGLE_SUPPORT
@@ -87,6 +101,11 @@ static inline uint8_t elf_sym__type(const GElf_Sym *sym)
 	return GELF_ST_TYPE(sym->st_info);
 }
 
+static inline uint8_t elf_sym__visibility(const GElf_Sym *sym)
+{
+	return GELF_ST_VISIBILITY(sym->st_other);
+}
+
 #ifndef STT_GNU_IFUNC
 #define STT_GNU_IFUNC 10
 #endif
@@ -111,7 +130,9 @@ static inline int elf_sym__is_label(const GElf_Sym *sym)
 	return elf_sym__type(sym) == STT_NOTYPE &&
 		sym->st_name != 0 &&
 		sym->st_shndx != SHN_UNDEF &&
-		sym->st_shndx != SHN_ABS;
+		sym->st_shndx != SHN_ABS &&
+		elf_sym__visibility(sym) != STV_HIDDEN &&
+		elf_sym__visibility(sym) != STV_INTERNAL;
 }
 
 static bool elf_sym__filter(GElf_Sym *sym)