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

Pull perf updates from Ingo Molnar:
 "Kernel side updates:

   - Fix and enhance poll support (Jiri Olsa)

   - Re-enable inheritance optimization (Jiri Olsa)

   - Enhance Intel memory events support (Stephane Eranian)

   - Refactor the Intel uncore driver to be more maintainable (Zheng
     Yan)

   - Enhance and fix Intel CPU and uncore PMU drivers (Peter Zijlstra,
     Andi Kleen)

   - [ plus various smaller fixes/cleanups ]

  User visible tooling updates:

   - Add +field argument support for --field option, so that one can add
     fields to the default list of fields to show, ie now one can just
     do:

         perf report --fields +pid

     And the pid will appear in addition to the default fields (Jiri
     Olsa)

   - Add +field argument support for --sort option (Jiri Olsa)

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

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

   - Add beautifier for mremap flags param in 'trace' (Alex Snast)

   - perf script: Allow callchains if any event samples them

   - Don't truncate Intel style addresses in 'annotate' (Alex Converse)

   - Allow profiling when kptr_restrict == 1 for non root users, kernel
     samples will just remain unresolved (Andi Kleen)

   - Allow configuring default options for callchains in config file
     (Namhyung Kim)

   - Support operations for shared futexes.  (Davidlohr Bueso)

   - "perf kvm stat report" improvements by Alexander Yarygin:
       -  Save pid string in opts.target.pid
       -  Enable the target.system_wide flag
       -  Unify the title bar output

   - [ plus lots of other fixes and small improvements.  ]

  Tooling infrastructure changes:

   - Refactor unit and scale function parameters for PMU parsing
     routines (Matt Fleming)

   - Improve DSO long names lookup with rbtree, resulting in great
     speedup for workloads with lots of DSOs (Waiman Long)

   - We were not handling POLLHUP notifications for event file
     descriptors

     Fix it by filtering entries in the events file descriptor array
     after poll() returns, refcounting mmaps so that when the last fd
     pointing to a perf mmap goes away we do the unmap (Arnaldo Carvalho
     de Melo)

   - Intel PT prep work, from Adrian Hunter, including:
       - Let a user specify a PMU event without any config terms
       - Add perf-with-kcore script
       - Let default config be defined for a PMU
       - Add perf_pmu__scan_file()
       - Add a 'perf test' for tracking with sched_switch
       - Add 'flush' callback to scripting API

   - Use ring buffer consume method to look like other tools (Arnaldo
     Carvalho de Melo)

   - hists browser (used in top and report) refactorings, getting rid of
     unused variables and reducing source code size by handling similar
     cases in a fewer functions (Namhyung Kim).

   - Replace thread unsafe strerror() with strerror_r() accross the
     whole tools/perf/ tree (Masami Hiramatsu)

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

   - [ plus lots of fixes, cleanups and other improvements ]"

* 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (198 commits)
  perf/x86: Tone down kernel messages when the PMU check fails in a virtual environment
  perf/x86/intel/uncore: Fix minor race in box set up
  perf record: Fix error message for --filter option not coming after tracepoint
  perf tools: Fix build breakage on arm64 targets
  perf symbols: Improve DSO long names lookup speed with rbtree
  perf symbols: Encapsulate dsos list head into struct dsos
  perf bench futex: Sanitize -q option in requeue
  perf bench futex: Support operations for shared futexes
  perf trace: Fix mmap return address truncation to 32-bit
  perf tools: Refactor unit and scale function parameters
  perf tools: Fix line number in the config file error message
  perf tools: Convert {record,top}.call-graph option to call-graph.record-mode
  perf tools: Introduce perf_callchain_config()
  perf callchain: Move some parser functions to callchain.c
  perf tools: Move callchain config from record_opts to callchain_param
  perf hists browser: Fix callchain print bug on TUI
  perf tools: Use ACCESS_ONCE() instead of volatile cast
  perf tools: Modify error code for when perf_session__new() fails
  perf tools: Fix perf record as non root with kptr_restrict == 1
  perf stat: Fix --per-core on multi socket systems
  ...

1 files changed, 31 insertions, 115 deletions

diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 4869050..44c6f3d 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -65,8 +65,9 @@ static int process_synthesized_event(struct perf_tool *tool,
 	return record__write(rec, event, event->header.size);
 }
 
-static int record__mmap_read(struct record *rec, struct perf_mmap *md)
+static int record__mmap_read(struct record *rec, int idx)
 {
+	struct perf_mmap *md = &rec->evlist->mmap[idx];
 	unsigned int head = perf_mmap__read_head(md);
 	unsigned int old = md->prev;
 	unsigned char *data = md->base + page_size;
@@ -102,8 +103,7 @@ static int record__mmap_read(struct record *rec, struct perf_mmap *md)
 	}
 
 	md->prev = old;
-	perf_mmap__write_tail(md, old);
-
+	perf_evlist__mmap_consume(rec->evlist, idx);
 out:
 	return rc;
 }
@@ -161,7 +161,7 @@ try_again:
 
 	if (perf_evlist__apply_filters(evlist)) {
 		error("failed to set filter with %d (%s)\n", errno,
-			strerror(errno));
+			strerror_r(errno, msg, sizeof(msg)));
 		rc = -1;
 		goto out;
 	}
@@ -175,7 +175,8 @@ try_again:
 			       "(current value: %u)\n", opts->mmap_pages);
 			rc = -errno;
 		} else {
-			pr_err("failed to mmap with %d (%s)\n", errno, strerror(errno));
+			pr_err("failed to mmap with %d (%s)\n", errno,
+				strerror_r(errno, msg, sizeof(msg)));
 			rc = -errno;
 		}
 		goto out;
@@ -244,7 +245,7 @@ static int record__mmap_read_all(struct record *rec)
 
 	for (i = 0; i < rec->evlist->nr_mmaps; i++) {
 		if (rec->evlist->mmap[i].base) {
-			if (record__mmap_read(rec, &rec->evlist->mmap[i]) != 0) {
+			if (record__mmap_read(rec, i) != 0) {
 				rc = -1;
 				goto out;
 			}
@@ -307,7 +308,7 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 	struct record_opts *opts = &rec->opts;
 	struct perf_data_file *file = &rec->file;
 	struct perf_session *session;
-	bool disabled = false;
+	bool disabled = false, draining = false;
 
 	rec->progname = argv[0];
 
@@ -456,9 +457,9 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 		}
 
 		if (hits == rec->samples) {
-			if (done)
+			if (done || draining)
 				break;
-			err = poll(rec->evlist->pollfd, rec->evlist->nr_fds, -1);
+			err = perf_evlist__poll(rec->evlist, -1);
 			/*
 			 * Propagate error, only if there's any. Ignore positive
 			 * number of returned events and interrupt error.
@@ -466,6 +467,9 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 			if (err > 0 || (err < 0 && errno == EINTR))
 				err = 0;
 			waking++;
+
+			if (perf_evlist__filter_pollfd(rec->evlist, POLLERR | POLLHUP) == 0)
+				draining = true;
 		}
 
 		/*
@@ -480,7 +484,7 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 	}
 
 	if (forks && workload_exec_errno) {
-		char msg[512];
+		char msg[STRERR_BUFSIZE];
 		const char *emsg = strerror_r(workload_exec_errno, msg, sizeof(msg));
 		pr_err("Workload failed: %s\n", emsg);
 		err = -1;
@@ -620,145 +624,56 @@ error:
 	return ret;
 }
 
-#ifdef HAVE_DWARF_UNWIND_SUPPORT
-static int get_stack_size(char *str, unsigned long *_size)
-{
-	char *endptr;
-	unsigned long size;
-	unsigned long max_size = round_down(USHRT_MAX, sizeof(u64));
-
-	size = strtoul(str, &endptr, 0);
-
-	do {
-		if (*endptr)
-			break;
-
-		size = round_up(size, sizeof(u64));
-		if (!size || size > max_size)
-			break;
-
-		*_size = size;
-		return 0;
-
-	} while (0);
-
-	pr_err("callchain: Incorrect stack dump size (max %ld): %s\n",
-	       max_size, str);
-	return -1;
-}
-#endif /* HAVE_DWARF_UNWIND_SUPPORT */
-
-int record_parse_callchain(const char *arg, struct record_opts *opts)
-{
-	char *tok, *name, *saveptr = NULL;
-	char *buf;
-	int ret = -1;
-
-	/* We need buffer that we know we can write to. */
-	buf = malloc(strlen(arg) + 1);
-	if (!buf)
-		return -ENOMEM;
-
-	strcpy(buf, arg);
-
-	tok = strtok_r((char *)buf, ",", &saveptr);
-	name = tok ? : (char *)buf;
-
-	do {
-		/* Framepointer style */
-		if (!strncmp(name, "fp", sizeof("fp"))) {
-			if (!strtok_r(NULL, ",", &saveptr)) {
-				opts->call_graph = CALLCHAIN_FP;
-				ret = 0;
-			} else
-				pr_err("callchain: No more arguments "
-				       "needed for -g fp\n");
-			break;
-
-#ifdef HAVE_DWARF_UNWIND_SUPPORT
-		/* Dwarf style */
-		} else if (!strncmp(name, "dwarf", sizeof("dwarf"))) {
-			const unsigned long default_stack_dump_size = 8192;
-
-			ret = 0;
-			opts->call_graph = CALLCHAIN_DWARF;
-			opts->stack_dump_size = default_stack_dump_size;
-
-			tok = strtok_r(NULL, ",", &saveptr);
-			if (tok) {
-				unsigned long size = 0;
-
-				ret = get_stack_size(tok, &size);
-				opts->stack_dump_size = size;
-			}
-#endif /* HAVE_DWARF_UNWIND_SUPPORT */
-		} else {
-			pr_err("callchain: Unknown --call-graph option "
-			       "value: %s\n", arg);
-			break;
-		}
-
-	} while (0);
-
-	free(buf);
-	return ret;
-}
-
-static void callchain_debug(struct record_opts *opts)
+static void callchain_debug(void)
 {
 	static const char *str[CALLCHAIN_MAX] = { "NONE", "FP", "DWARF" };
 
-	pr_debug("callchain: type %s\n", str[opts->call_graph]);
+	pr_debug("callchain: type %s\n", str[callchain_param.record_mode]);
 
-	if (opts->call_graph == CALLCHAIN_DWARF)
+	if (callchain_param.record_mode == CALLCHAIN_DWARF)
 		pr_debug("callchain: stack dump size %d\n",
-			 opts->stack_dump_size);
+			 callchain_param.dump_size);
 }
 
-int record_parse_callchain_opt(const struct option *opt,
+int record_parse_callchain_opt(const struct option *opt __maybe_unused,
 			       const char *arg,
 			       int unset)
 {
-	struct record_opts *opts = opt->value;
 	int ret;
 
-	opts->call_graph_enabled = !unset;
+	callchain_param.enabled = !unset;
 
 	/* --no-call-graph */
 	if (unset) {
-		opts->call_graph = CALLCHAIN_NONE;
+		callchain_param.record_mode = CALLCHAIN_NONE;
 		pr_debug("callchain: disabled\n");
 		return 0;
 	}
 
-	ret = record_parse_callchain(arg, opts);
+	ret = parse_callchain_record_opt(arg);
 	if (!ret)
-		callchain_debug(opts);
+		callchain_debug();
 
 	return ret;
 }
 
-int record_callchain_opt(const struct option *opt,
+int record_callchain_opt(const struct option *opt __maybe_unused,
 			 const char *arg __maybe_unused,
 			 int unset __maybe_unused)
 {
-	struct record_opts *opts = opt->value;
+	callchain_param.enabled = true;
 
-	opts->call_graph_enabled = !unset;
+	if (callchain_param.record_mode == CALLCHAIN_NONE)
+		callchain_param.record_mode = CALLCHAIN_FP;
 
-	if (opts->call_graph == CALLCHAIN_NONE)
-		opts->call_graph = CALLCHAIN_FP;
-
-	callchain_debug(opts);
+	callchain_debug();
 	return 0;
 }
 
 static int perf_record_config(const char *var, const char *value, void *cb)
 {
-	struct record *rec = cb;
-
 	if (!strcmp(var, "record.call-graph"))
-		return record_parse_callchain(value, &rec->opts);
+		var = "call-graph.record-mode"; /* fall-through */
 
 	return perf_default_config(var, value, cb);
 }
@@ -781,6 +696,7 @@ 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,
@@ -907,7 +823,7 @@ int cmd_record(int argc, const char **argv, const char *prefix __maybe_unused)
 		usage_with_options(record_usage, record_options);
 	}
 
-	symbol__init();
+	symbol__init(NULL);
 
 	if (symbol_conf.kptr_restrict)
 		pr_warning(