Merge tag 'trace-v7.3-2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-tracegrafted

Pull tracing fixes from Steven Rostedt:

 - Fix error output of boot instance creation failure

   Currently if a boot instance creation fails, instead of printing out
   the name of the instance that failed, it prints "(null)". That is
   because it prints "cur_str" that had already been processed by
   strsep(). Print the saved name instead.

   While at it, print the error code of the failure.

 - Fix use-after-free for same named historgrams

   Histograms can be named so that they can be used in multiple events.
   But if the named histogram has a variable attached, the second event
   that uses the named histogram which duplicates it and needs to free
   the original after duplication leaves the old variable in place and
   still visible. If another histogram uses than variable, it will use
   the stale one which will try to reference the freed duplicate
   histogram and crash the kernel.

   Free the duplicate variables along with the duplicated histogram
   data.

 - Check return value of kthread_run() in event self test

   The events self tests uses a kthread for testing but does not check
   if it succeeded in creating a kthread. If the kthread creation were
   to fail, the code will still try to call kthread_stop() on the error
   returned.

 - Fix race between reading trace_pipe and updating subbuffer size

   If a user is reading the trace_pipe file at the same time they update
   the ring buffer sub-buffer size, can cause the trace_pipe read to
   read stale data. Add trace_access_lock() around updating the ring
   buffer sub-buffer size.

 - Fix eventfs_inode on failure path in creation of the events directory

   In the creation of the "events" directory, if after allocating the
   eventfs_inode a failure is detected, it calls cleanup_ei() which
   calls free_ei(). The free_ei() will test if eventfs_inode being freed
   has no children. It is a bug if it does. But on the failure case of
   the creation of the "events" directory, the children lists have not
   yet been initialized and the free will trigger a warning because
   list_empty() on an uninitialized list returns false.

   Move the initialization into init_ei() where it makes more sense and
   makes sure that a created eventfs_inode has its lists initialized
   upon creation.

 - Check return value of kthread_run() in ftrace direct sample code

   The sample code that shows how to use the ftrace direct calls does
   not test the return of kthread_run() to see if it succeeds. Return a
   failure if the kthread_run() doesn't succeed.

 - Clear user events state on fork in case of alloc failure

   On fork, the child gets a pointer to the parent's user events state.
   It makes a copy of it then updates the child's pointer to it. But if
   the allocation fails, the duplication function leaves the child with
   a pointer to its parent's descriptor. When the child cleans up its
   data, it will free the parent's descriptor while the parent is still
   using it.

   In the duplication function, set the child's user_event_mm to NULL
   before testing if the allocation succeeded, and when it exits it will
   not free the parent's descriptor.

 - Fix retry exhaustion in simple ring buffer reader swap

   simple_ring_buffer_swap_reader_page() starts with retry set to 8 and
   post-decrements it only after a failed link replacement. On the final
   attempt, a successful replacement leaves retry at zero, while a
   failed replacement leaves it at -1.

   But the check for success expects the retry value to be non-zero and
   exits with an error on zero. This is the opposite result. Fix it.

 - Fail nicely when the remote swap_reader_page() returns an error

   Currently, if the swap_reader_page() of a remote buffer fails, it
   triggers a WARN_ON_ONCE() and continues normally. Instead, have it
   exit with an error and a pr_warn() print instead of a full WARNING.

* tag 'trace-v7.3-2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace:
  ring-buffer: Stop remote reader update when page swap fails
  tracing: Fix retry exhaustion in simple ring buffer reader swap
  tracing/user_events: Clear copied tracing state before fork duplication
  samples/ftrace: Fix kthread_stop() on ERR_PTR in ftrace-direct-multi-modify
  samples/ftrace: Fix kthread_stop() on ERR_PTR in ftrace-direct-modify
  eventfs: Initialize ei->children and ei->list in init_ei()
  tracing: Fix use-after-free in trace_pipe read on sub-buffer order change
  tracing: Fix crash passing ERR_PTR to kthread_stop()
  tracing: Fix use-after-free with same-name named triggers
  tracing: Fix logged instance name on creation failure

1 files changed, 359 insertions, 0 deletions

diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c
new file mode 100644
index 000000000..525a3fe4a
--- /dev/null
+++ b/tools/perf/util/stat-shadow.c
@@ -0,0 +1,359 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <errno.h>
+#include <math.h>
+#include <stdio.h>
+
+#include <linux/zalloc.h>
+
+#include "cgroup.h"
+#include "color.h"
+#include "debug.h"
+#include "evlist.h"
+#include "evsel.h"
+#include "expr.h"
+#include "hashmap.h"
+#include "iostat.h"
+#include "metricgroup.h"
+#include "pmu.h"
+#include "pmus.h"
+#include "rblist.h"
+#include "stat.h"
+#include "tool_pmu.h"
+#include "units.h"
+
+static bool tool_pmu__is_time_event(const struct perf_stat_config *config,
+				   const struct evsel *evsel, int *tool_aggr_idx)
+{
+	enum tool_pmu_event event = evsel__tool_event(evsel);
+	int aggr_idx;
+
+	if (event != TOOL_PMU__EVENT_DURATION_TIME &&
+	    event != TOOL_PMU__EVENT_USER_TIME &&
+	    event != TOOL_PMU__EVENT_SYSTEM_TIME)
+		return false;
+
+	if (config) {
+		cpu_aggr_map__for_each_idx(aggr_idx, config->aggr_map) {
+			if (config->aggr_map->map[aggr_idx].cpu.cpu == 0) {
+				*tool_aggr_idx = aggr_idx;
+				return true;
+			}
+		}
+		pr_debug("Unexpected CPU0 missing in aggregation for tool event.\n");
+	}
+	*tool_aggr_idx = 0; /* Assume the first aggregation index works. */
+	return true;
+}
+
+static int prepare_metric(struct perf_stat_config *config,
+			  const struct metric_expr *mexp,
+			  const struct evsel *evsel,
+			  struct expr_parse_ctx *pctx,
+			  int aggr_idx)
+{
+	struct evsel * const *metric_events = mexp->metric_events;
+	struct metric_ref *metric_refs = mexp->metric_refs;
+	int i;
+
+	for (i = 0; metric_events[i]; i++) {
+		int source_count = 0, tool_aggr_idx;
+		int aggr_nr = 1;
+		bool is_tool_time =
+			tool_pmu__is_time_event(config, metric_events[i], &tool_aggr_idx);
+		struct perf_stat_evsel *ps = metric_events[i]->stats;
+		char *n;
+		double val;
+
+		/*
+		 * If there are multiple uncore PMUs and we're not reading the
+		 * leader's stats, determine the stats for the appropriate
+		 * uncore PMU.
+		 */
+		if (evsel && evsel->metric_leader &&
+		    evsel->pmu != evsel->metric_leader->pmu &&
+		    mexp->metric_events[i]->pmu == evsel->metric_leader->pmu) {
+			struct evsel *pos;
+
+			evlist__for_each_entry(evsel->evlist, pos) {
+				if (pos->pmu != evsel->pmu)
+					continue;
+				if (pos->metric_leader != mexp->metric_events[i])
+					continue;
+				ps = pos->stats;
+				source_count = 1;
+				break;
+			}
+		}
+		/* Time events are always on CPU0, the first aggregation index. */
+		if (!ps || !metric_events[i]->supported) {
+			/*
+			 * Not supported events will have a count of 0, which
+			 * can be confusing in a metric. Explicitly set the
+			 * value to NAN. Not counted events (enable time of 0)
+			 * are read as 0.
+			 */
+			val = NAN;
+			source_count = 0;
+			aggr_nr = 0;
+		} else {
+			struct perf_stat_aggr *aggr =
+				&ps->aggr[is_tool_time ? tool_aggr_idx : aggr_idx];
+
+			if (aggr->counts.run == 0) {
+				val = NAN;
+				source_count = 0;
+				aggr_nr = 0;
+			} else {
+				val = aggr->counts.val;
+				if (is_tool_time) {
+					/* Convert time event nanoseconds to seconds. */
+					val *= 1e-9;
+				}
+				if (!source_count)
+					source_count = evsel__source_count(metric_events[i]);
+				aggr_nr = aggr->nr ?: 1;
+			}
+		}
+		n = strdup(evsel__metric_id(metric_events[i]));
+		if (!n)
+			return -ENOMEM;
+
+		expr__add_id_val_source_count_aggr_nr(pctx, n, val, source_count, aggr_nr);
+	}
+
+	for (int j = 0; metric_refs && metric_refs[j].metric_name; j++) {
+		int ret = expr__add_ref(pctx, &metric_refs[j]);
+
+		if (ret)
+			return ret;
+	}
+
+	return i;
+}
+
+static void generic_metric(struct perf_stat_config *config,
+			   struct metric_expr *mexp,
+			   struct evsel *evsel,
+			   int aggr_idx,
+			   struct perf_stat_output_ctx *out)
+{
+	print_metric_t print_metric = out->print_metric;
+	const char *metric_name = mexp->metric_name;
+	const char *metric_expr = mexp->metric_expr;
+	const char *metric_threshold = mexp->metric_threshold;
+	const char *metric_unit = mexp->metric_unit;
+	struct evsel * const *metric_events = mexp->metric_events;
+	int runtime = mexp->runtime;
+	struct expr_parse_ctx *pctx;
+	double ratio, scale, threshold;
+	int i;
+	void *ctxp = out->ctx;
+	enum metric_threshold_classify thresh = METRIC_THRESHOLD_UNKNOWN;
+
+	pctx = expr__ctx_new();
+	if (!pctx)
+		return;
+
+	if (config->user_requested_cpu_list)
+		pctx->sctx.user_requested_cpu_list = strdup(config->user_requested_cpu_list);
+	pctx->sctx.runtime = runtime;
+	pctx->sctx.system_wide = config->system_wide;
+	i = prepare_metric(config, mexp, evsel, pctx, aggr_idx);
+	if (i < 0) {
+		expr__ctx_free(pctx);
+		return;
+	}
+	if (!metric_events[i]) {
+		if (expr__parse(&ratio, pctx, metric_expr) == 0) {
+			char *unit;
+			char metric_bf[128];
+
+			if (metric_threshold &&
+			    expr__parse(&threshold, pctx, metric_threshold) == 0 &&
+			    !isnan(threshold)) {
+				thresh = fpclassify(threshold) == FP_ZERO
+					? METRIC_THRESHOLD_GOOD : METRIC_THRESHOLD_BAD;
+			}
+
+			if (metric_unit && metric_name) {
+				if (perf_pmu__convert_scale(metric_unit,
+					&unit, &scale) >= 0) {
+					ratio *= scale;
+				}
+				if (strstr(metric_expr, "?"))
+					scnprintf(metric_bf, sizeof(metric_bf),
+					  "%s  %s_%d", unit, metric_name, runtime);
+				else
+					scnprintf(metric_bf, sizeof(metric_bf),
+					  "%s  %s", unit, metric_name);
+
+				print_metric(config, ctxp, thresh, "%8.1f",
+					     metric_bf, ratio);
+			} else {
+				print_metric(config, ctxp, thresh, "%8.2f",
+					metric_name ?
+					metric_name :
+					out->force_header ?  evsel->name : "",
+					ratio);
+			}
+		} else {
+			print_metric(config, ctxp, thresh, /*fmt=*/NULL,
+				     out->force_header ?
+				     (metric_name ?: evsel->name) : "", 0);
+		}
+	} else {
+		print_metric(config, ctxp, thresh, /*fmt=*/NULL,
+			     out->force_header ?
+			     (metric_name ?: evsel->name) : "", 0);
+	}
+
+	expr__ctx_free(pctx);
+}
+
+double test_generic_metric(struct metric_expr *mexp, int aggr_idx)
+{
+	struct expr_parse_ctx *pctx;
+	double ratio = 0.0;
+
+	pctx = expr__ctx_new();
+	if (!pctx)
+		return NAN;
+
+	if (prepare_metric(/*config=*/NULL, mexp, /*evsel=*/NULL, pctx, aggr_idx) < 0)
+		goto out;
+
+	if (expr__parse(&ratio, pctx, mexp->metric_expr))
+		ratio = 0.0;
+
+out:
+	expr__ctx_free(pctx);
+	return ratio;
+}
+
+static void perf_stat__print_metricgroup_header(struct perf_stat_config *config,
+						struct evsel *evsel,
+						void *ctxp,
+						const char *name,
+						struct perf_stat_output_ctx *out)
+{
+	bool need_full_name = perf_pmus__num_core_pmus() > 1;
+	static const char *last_name;
+	static const struct perf_pmu *last_pmu;
+	char full_name[64];
+
+	/*
+	 * A metricgroup may have several metric events,
+	 * e.g.,TopdownL1 on e-core of ADL.
+	 * The name has been output by the first metric
+	 * event. Only align with other metics from
+	 * different metric events.
+	 */
+	if (last_name && !strcmp(last_name, name) && last_pmu == evsel->pmu) {
+		out->print_metricgroup_header(config, ctxp, NULL);
+		return;
+	}
+
+	if (need_full_name && evsel->pmu)
+		scnprintf(full_name, sizeof(full_name), "%s (%s)", name, evsel->pmu->name);
+	else
+		scnprintf(full_name, sizeof(full_name), "%s", name);
+
+	out->print_metricgroup_header(config, ctxp, full_name);
+
+	last_name = name;
+	last_pmu = evsel->pmu;
+}
+
+/**
+ * perf_stat__print_shadow_stats_metricgroup - Print out metrics associated with the evsel
+ *					       For the non-default, all metrics associated
+ *					       with the evsel are printed.
+ *					       For the default mode, only the metrics from
+ *					       the same metricgroup and the name of the
+ *					       metricgroup are printed. To print the metrics
+ *					       from the next metricgroup (if available),
+ *					       invoke the function with correspoinding
+ *					       metric_expr.
+ */
+void *perf_stat__print_shadow_stats_metricgroup(struct perf_stat_config *config,
+						struct evsel *evsel,
+						int aggr_idx,
+						int *num,
+						void *from,
+						struct perf_stat_output_ctx *out)
+{
+	struct metric_event *me;
+	struct metric_expr *mexp = from;
+	void *ctxp = out->ctx;
+	bool header_printed = false;
+	const char *name = NULL;
+	struct rblist *metric_events = evlist__metric_events(evsel->evlist);
+
+	me = metricgroup__lookup(metric_events, evsel, false);
+	if (me == NULL)
+		return NULL;
+
+	if (!mexp)
+		mexp = list_first_entry(&me->head, typeof(*mexp), nd);
+
+	list_for_each_entry_from(mexp, &me->head, nd) {
+		/* Print the display name of the Default metricgroup */
+		if (!config->metric_only && me->is_default) {
+			if (!name)
+				name = mexp->default_metricgroup_name;
+			/*
+			 * Two or more metricgroup may share the same metric
+			 * event, e.g., TopdownL1 and TopdownL2 on SPR.
+			 * Return and print the prefix, e.g., noise, running
+			 * for the next metricgroup.
+			 */
+			if (strcmp(name, mexp->default_metricgroup_name))
+				return (void *)mexp;
+			/* Only print the name of the metricgroup once */
+			if (!header_printed && !evsel->default_show_events) {
+				header_printed = true;
+				perf_stat__print_metricgroup_header(config, evsel, ctxp,
+								    name, out);
+			}
+		}
+
+		if ((*num)++ > 0 && out->new_line)
+			out->new_line(config, ctxp);
+		generic_metric(config, mexp, evsel, aggr_idx, out);
+	}
+
+	return NULL;
+}
+
+void perf_stat__print_shadow_stats(struct perf_stat_config *config,
+				   struct evsel *evsel,
+				   int aggr_idx,
+				   struct perf_stat_output_ctx *out)
+{
+	print_metric_t print_metric = out->print_metric;
+	void *ctxp = out->ctx;
+	int num = 0;
+
+	if (config->iostat_run)
+		iostat_print_metric(config, evsel, out);
+
+	perf_stat__print_shadow_stats_metricgroup(config, evsel, aggr_idx,
+						  &num, NULL, out);
+
+	if (num == 0) {
+		print_metric(config, ctxp, METRIC_THRESHOLD_UNKNOWN,
+			     /*fmt=*/NULL, /*unit=*/NULL, 0);
+	}
+}
+
+/**
+ * perf_stat__skip_metric_event - Skip the evsel in the Default metricgroup,
+ *				  if it's not running or not the metric event.
+ */
+bool perf_stat__skip_metric_event(struct evsel *evsel)
+{
+	if (!evsel->default_metricgroup)
+		return false;
+
+	return !metricgroup__lookup(evlist__metric_events(evsel->evlist), evsel, false);
+}