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

Pull perf updates from Ingo Molnar:
 "On the kernel side the main changes in this cycle were:

   - Add Intel Kaby Lake CPU support (Srinivas Pandruvada)

   - AMD uncore driver updates for fam17 (Janakarajan Natarajan)

   - Intel/PT updates and core events optimizations and cleanups
     (Alexander Shishkin)

   - cgroups events fixes (David Carrillo-Cisneros)

   - kprobes improvements (Masami Hiramatsu)

   - ... plus misc fixes and updates.

  On the tooling side the main changes were:

   - Support clang build in tools/{perf,lib/{bpf,traceevent,api}} with
     CC=clang, to, for instance, take advantage of better warnings
     (Arnaldo Carvalho de Melo):

   - Introduce the 'delta-abs' 'perf diff' compute method, that orders
     the histogram entries by the absolute value of the percentage delta
     for a function in two perf.data files, i.e. the functions that
     changed the most (increase or decrease in samples) comes first
     (Namhyung Kim)

   - Add support for parsing Intel uncore vendor event files and add
     uncore vendor events for the Intel server processors (Haswell,
     Broadwell, IvyBridge), Xeon Phi (Knights Landing) and Broadwell DE
     (Andi Kleen)

   - Introduce 'perf ftrace' a perf front end to the kernel's ftrace
     function and function_graph tracer, defaulting to the
     "function_graph" tracer, more work will be done in reviving this
     effort, forward porting it from its initial patch submission
     (Namhyung Kim)

   - Add 'e' and 'c' hotkeys to expand/collapse call chains for a single
     hist entry in the 'perf report' and 'perf top' TUI (Jiri Olsa)

   - Account thread wait time (off CPU time) separately: sleep, iowait
     and preempt, based on the prev_state of the last event, show the
     breakdown when using "perf sched timehist --state" (Namhyumg Kim)

   - Add more triggers to switch the output file (perf.data.TIMESTAMP).

     Now, in addition to switching to a different output file when
     receiving a SIGUSR2, one can also specify file size and time based
     triggers:

           perf record -a --switch-output=signal

     is equivalent to what we had before:

           perf record -a --switch-output

     While we can also ask for the file to be "sliced" by size, taking
     into account that that will happen only when we get woken up by the
     kernel, i.e. one has to take into account the --mmap-pages (the
     size of the perf mmap ring buffer):

           perf record -a --switch-output=2G

     will break the perf.data output into multiple files limited to 2GB
     of samples, right when generating the output.

     For time based samples, alert() will be used, so to have 1 minute
     limited perf.data output files:

          perf record -a --switch-output=1m

     (Jiri Olsa)

   - Improve 'perf trace' (Arnaldo Carvalho de Melo)

   - 'perf kallsyms' toy tool to look for extended symbol information on
     the running kernel and demonstrate the machine/thread/symbol APIs
     for use in other tools, such as 'perf probe' (Arnaldo Carvalho de
     Melo)

   - ... plus tons of other changes, see the shortlog and Git log for
     details"

* 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (131 commits)
  perf tools: Add missing parse_events_error() prototype
  perf pmu: Fix check for unset alias->unit array
  perf tools: Be consistent on the type of map->symbols[] interator
  perf intel pt decoder: clang has no -Wno-override-init
  perf evsel: Do not put a variable sized type not at the end of a struct
  perf probe: Avoid accessing uninitialized 'map' variable
  perf tools: Do not put a variable sized type not at the end of a struct
  perf record: Do not put a variable sized type not at the end of a struct
  perf tests: Synthesize struct instead of using field after variable sized type
  perf bench numa: Make sure dprintf() is not defined
  Revert "perf bench futex: Sanitize numeric parameters"
  tools lib subcmd: Make it an error to pass a signed value to OPTION_UINTEGER
  tools: Set the maximum optimization level according to the compiler being used
  tools: Suppress request for warning options not existent in clang
  samples/bpf: Reset global variables
  samples/bpf: Ignore already processed ELF sections
  samples/bpf: Add missing header
  perf symbols: dso->name is an array, no need to check it against NULL
  perf tests record: No need to test an array against NULL
  perf symbols: No need to check if sym->name is NULL
  ...

1 files changed, 92 insertions, 28 deletions

diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 206bf72b77fc..40ef9b293d1b 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -40,6 +40,7 @@
 
 #include <libaudit.h> /* FIXME: Still needed for audit_errno_to_name */
 #include <stdlib.h>
+#include <string.h>
 #include <linux/err.h>
 #include <linux/filter.h>
 #include <linux/audit.h>
@@ -2699,6 +2700,91 @@ static void evlist__set_evsel_handler(struct perf_evlist *evlist, void *handler)
 		evsel->handler = handler;
 }
 
+/*
+ * XXX: Hackish, just splitting the combined -e+--event (syscalls
+ * (raw_syscalls:{sys_{enter,exit}} + events (tracepoints, HW, SW, etc) to use
+ * existing facilities unchanged (trace->ev_qualifier + parse_options()).
+ *
+ * It'd be better to introduce a parse_options() variant that would return a
+ * list with the terms it didn't match to an event...
+ */
+static int trace__parse_events_option(const struct option *opt, const char *str,
+				      int unset __maybe_unused)
+{
+	struct trace *trace = (struct trace *)opt->value;
+	const char *s = str;
+	char *sep = NULL, *lists[2] = { NULL, NULL, };
+	int len = strlen(str), err = -1, list;
+	char *strace_groups_dir = system_path(STRACE_GROUPS_DIR);
+	char group_name[PATH_MAX];
+
+	if (strace_groups_dir == NULL)
+		return -1;
+
+	if (*s == '!') {
+		++s;
+		trace->not_ev_qualifier = true;
+	}
+
+	while (1) {
+		if ((sep = strchr(s, ',')) != NULL)
+			*sep = '\0';
+
+		list = 0;
+		if (syscalltbl__id(trace->sctbl, s) >= 0) {
+			list = 1;
+		} else {
+			path__join(group_name, sizeof(group_name), strace_groups_dir, s);
+			if (access(group_name, R_OK) == 0)
+				list = 1;
+		}
+
+		if (lists[list]) {
+			sprintf(lists[list] + strlen(lists[list]), ",%s", s);
+		} else {
+			lists[list] = malloc(len);
+			if (lists[list] == NULL)
+				goto out;
+			strcpy(lists[list], s);
+		}
+
+		if (!sep)
+			break;
+
+		*sep = ',';
+		s = sep + 1;
+	}
+
+	if (lists[1] != NULL) {
+		struct strlist_config slist_config = {
+			.dirname = strace_groups_dir,
+		};
+
+		trace->ev_qualifier = strlist__new(lists[1], &slist_config);
+		if (trace->ev_qualifier == NULL) {
+			fputs("Not enough memory to parse event qualifier", trace->output);
+			goto out;
+		}
+
+		if (trace__validate_ev_qualifier(trace))
+			goto out;
+	}
+
+	err = 0;
+
+	if (lists[0]) {
+		struct option o = OPT_CALLBACK('e', "event", &trace->evlist, "event",
+					       "event selector. use 'perf list' to list available events",
+					       parse_events_option);
+		err = parse_events_option(&o, lists[0], 0);
+	}
+out:
+	if (sep)
+		*sep = ',';
+
+	return err;
+}
+
 int cmd_trace(int argc, const char **argv, const char *prefix __maybe_unused)
 {
 	const char *trace_usage[] = {
@@ -2730,15 +2816,15 @@ int cmd_trace(int argc, const char **argv, const char *prefix __maybe_unused)
 		.max_stack = UINT_MAX,
 	};
 	const char *output_name = NULL;
-	const char *ev_qualifier_str = NULL;
 	const struct option trace_options[] = {
-	OPT_CALLBACK(0, "event", &trace.evlist, "event",
-		     "event selector. use 'perf list' to list available events",
-		     parse_events_option),
+	OPT_CALLBACK('e', "event", &trace, "event",
+		     "event/syscall selector. use 'perf list' to list available events",
+		     trace__parse_events_option),
 	OPT_BOOLEAN(0, "comm", &trace.show_comm,
 		    "show the thread COMM next to its id"),
 	OPT_BOOLEAN(0, "tool_stats", &trace.show_tool_stats, "show tool stats"),
-	OPT_STRING('e', "expr", &ev_qualifier_str, "expr", "list of syscalls to trace"),
+	OPT_CALLBACK(0, "expr", &trace, "expr", "list of syscalls/events to trace",
+		     trace__parse_events_option),
 	OPT_STRING('o', "output", &output_name, "file", "output file name"),
 	OPT_STRING('i', "input", &input_name, "file", "Analyze events in file"),
 	OPT_STRING('p', "pid", &trace.opts.target.pid, "pid",
@@ -2863,7 +2949,7 @@ int cmd_trace(int argc, const char **argv, const char *prefix __maybe_unused)
 		return -1;
 	}
 
-	if (!trace.trace_syscalls && ev_qualifier_str) {
+	if (!trace.trace_syscalls && trace.ev_qualifier) {
 		pr_err("The -e option can't be used with --no-syscalls.\n");
 		goto out;
 	}
@@ -2878,28 +2964,6 @@ int cmd_trace(int argc, const char **argv, const char *prefix __maybe_unused)
 
 	trace.open_id = syscalltbl__id(trace.sctbl, "open");
 
-	if (ev_qualifier_str != NULL) {
-		const char *s = ev_qualifier_str;
-		struct strlist_config slist_config = {
-			.dirname = system_path(STRACE_GROUPS_DIR),
-		};
-
-		trace.not_ev_qualifier = *s == '!';
-		if (trace.not_ev_qualifier)
-			++s;
-		trace.ev_qualifier = strlist__new(s, &slist_config);
-		if (trace.ev_qualifier == NULL) {
-			fputs("Not enough memory to parse event qualifier",
-			      trace.output);
-			err = -ENOMEM;
-			goto out_close;
-		}
-
-		err = trace__validate_ev_qualifier(&trace);
-		if (err)
-			goto out_close;
-	}
-
 	err = target__validate(&trace.opts.target);
 	if (err) {
 		target__strerror(&trace.opts.target, err, bf, sizeof(bf));