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, 210 insertions, 0 deletions

diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h
new file mode 100644
index 000000000..e3598037a
--- /dev/null
+++ b/tools/perf/util/stat.h
@@ -0,0 +1,210 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __PERF_STATS_H
+#define __PERF_STATS_H
+
+#include <linux/types.h>
+#include <stdio.h>
+#include <sys/types.h>
+#include <sys/resource.h>
+#include "cpumap.h"
+#include "counts.h"
+
+struct perf_cpu_map;
+struct perf_stat_config;
+struct timespec;
+
+struct stats {
+	double n, mean, M2;
+	u64 max, min;
+};
+
+/* hold aggregated event info */
+struct perf_stat_aggr {
+	/* aggregated values */
+	struct perf_counts_values	counts;
+	/* number of entries (CPUs) aggregated */
+	int				nr;
+	/* whether any entry has failed to read/process event */
+	bool				failed;
+	/* to mark this data is processed already */
+	bool				used;
+};
+
+/* per-evsel event stats */
+struct perf_stat_evsel {
+	/* used for repeated runs */
+	struct stats		 res_stats;
+	/* number of allocated 'aggr' */
+	int			 nr_aggr;
+	/* aggregated event values */
+	struct perf_stat_aggr	*aggr;
+	/* used for group read */
+	u64			*group_data;
+};
+
+enum aggr_mode {
+	AGGR_NONE,
+	AGGR_GLOBAL,
+	AGGR_SOCKET,
+	AGGR_DIE,
+	AGGR_CLUSTER,
+	AGGR_CACHE,
+	AGGR_CORE,
+	AGGR_THREAD,
+	AGGR_UNSET,
+	AGGR_NODE,
+	AGGR_MAX
+};
+
+typedef struct aggr_cpu_id (*aggr_get_id_t)(struct perf_stat_config *config, struct perf_cpu cpu);
+
+struct perf_stat_config {
+	enum aggr_mode		 aggr_mode;
+	u32			 aggr_level;
+	bool			 scale;
+	bool			 no_inherit;
+	bool			 identifier;
+	bool			 csv_output;
+	bool			 json_output;
+	bool			 interval_clear;
+	bool			 metric_only;
+	bool			 null_run;
+	bool			 hide_zero;
+	bool			 ru_display;
+	bool			 big_num;
+	bool			 hybrid_merge;
+	bool			 walltime_run_table;
+	bool			 all_kernel;
+	bool			 all_user;
+	bool			 percore_show_thread;
+	bool			 summary;
+	bool			 no_csv_summary;
+	bool			 metric_no_group;
+	bool			 metric_no_merge;
+	bool			 metric_no_threshold;
+	bool			 hardware_aware_grouping;
+	bool			 stop_read_counter;
+	bool			 iostat_run;
+	char			 *user_requested_cpu_list;
+	bool			 system_wide;
+	FILE			*output;
+	unsigned int		 interval;
+	unsigned int		 timeout;
+	unsigned int		 unit_width;
+	unsigned int		 metric_only_len;
+	int			 times;
+	int			 run_count;
+	int			 print_free_counters_hint;
+	const char		*csv_sep;
+	struct stats		*walltime_nsecs_stats;
+	struct rusage		 ru_data;
+	struct cpu_aggr_map	*aggr_map;
+	aggr_get_id_t		 aggr_get_id;
+	struct cpu_aggr_map	*cpus_aggr_map;
+	u64			*walltime_run;
+	int			 ctl_fd;
+	int			 ctl_fd_ack;
+	bool			 ctl_fd_close;
+	const char		*cgroup_list;
+	unsigned int		topdown_level;
+};
+
+extern struct perf_stat_config stat_config;
+
+void perf_stat__set_big_num(int set);
+
+void update_stats(struct stats *stats, u64 val);
+double avg_stats(struct stats *stats);
+double stddev_stats(struct stats *stats);
+double rel_stddev_stats(double stddev, double avg);
+
+static inline void init_stats(struct stats *stats)
+{
+	stats->n    = 0.0;
+	stats->mean = 0.0;
+	stats->M2   = 0.0;
+	stats->min  = (u64) -1;
+	stats->max  = 0;
+}
+
+struct evsel;
+struct evlist;
+
+enum metric_threshold_classify {
+	METRIC_THRESHOLD_UNKNOWN,
+	METRIC_THRESHOLD_BAD,
+	METRIC_THRESHOLD_NEARLY_BAD,
+	METRIC_THRESHOLD_LESS_GOOD,
+	METRIC_THRESHOLD_GOOD,
+};
+const char *metric_threshold_classify__color(enum metric_threshold_classify thresh);
+
+typedef void (*print_metric_t)(struct perf_stat_config *config,
+			       void *ctx,
+			       enum metric_threshold_classify thresh,
+			       const char *fmt,
+			       const char *unit,
+			       double val);
+typedef void (*new_line_t)(struct perf_stat_config *config, void *ctx);
+
+/* Used to print the display name of the Default metricgroup for now. */
+typedef void (*print_metricgroup_header_t)(struct perf_stat_config *config,
+					   void *ctx, const char *metricgroup_name);
+
+void perf_stat__reset_shadow_stats(void);
+struct perf_stat_output_ctx {
+	void *ctx;
+	print_metric_t print_metric;
+	new_line_t new_line;
+	print_metricgroup_header_t print_metricgroup_header;
+	bool force_header;
+};
+
+void perf_stat__print_shadow_stats(struct perf_stat_config *config,
+				   struct evsel *evsel,
+				   int aggr_idx,
+				   struct perf_stat_output_ctx *out);
+bool perf_stat__skip_metric_event(struct evsel *evsel);
+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);
+
+int evlist__alloc_stats(struct perf_stat_config *config,
+			struct evlist *evlist, bool alloc_raw);
+void evlist__free_stats(struct evlist *evlist);
+void evlist__reset_stats(struct evlist *evlist);
+void evlist__reset_prev_raw_counts(struct evlist *evlist);
+void evlist__copy_prev_raw_counts(struct evlist *evlist);
+void evlist__save_aggr_prev_raw_counts(struct evlist *evlist);
+
+int evlist__alloc_aggr_stats(struct evlist *evlist, int nr_aggr);
+void evlist__reset_aggr_stats(struct evlist *evlist);
+void evlist__copy_res_stats(struct perf_stat_config *config, struct evlist *evlist);
+
+int perf_stat_process_counter(struct perf_stat_config *config,
+			      struct evsel *counter);
+void perf_stat_merge_counters(struct perf_stat_config *config, struct evlist *evlist);
+void perf_stat_process_percore(struct perf_stat_config *config, struct evlist *evlist);
+
+struct perf_tool;
+union perf_event;
+struct perf_session;
+struct target;
+
+int perf_event__process_stat_event(const struct perf_tool *tool,
+				   struct perf_session *session,
+				   union perf_event *event);
+
+size_t perf_event__fprintf_stat(union perf_event *event, FILE *fp);
+size_t perf_event__fprintf_stat_round(union perf_event *event, FILE *fp);
+size_t perf_event__fprintf_stat_config(union perf_event *event, FILE *fp);
+
+void evlist__print_counters(struct evlist *evlist, struct perf_stat_config *config,
+			    struct target *_target, struct timespec *ts, int argc, const char **argv);
+
+struct metric_expr;
+double test_generic_metric(struct metric_expr *mexp, int aggr_idx);
+#endif