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, 295 insertions, 0 deletions

diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h
new file mode 100644
index 000000000..b14c832b0
--- /dev/null
+++ b/tools/perf/util/parse-events.h
@@ -0,0 +1,295 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __PERF_PARSE_EVENTS_H
+#define __PERF_PARSE_EVENTS_H
+/*
+ * Parse symbolic events/counts passed in as options:
+ */
+
+#include <linux/list.h>
+#include <stdbool.h>
+#include <linux/types.h>
+#include <linux/perf_event.h>
+#include <string.h>
+#include <sys/types.h>
+
+struct evsel;
+struct evlist;
+struct parse_events_error;
+
+struct option;
+struct perf_pmu;
+struct strbuf;
+
+const char *event_type(size_t type);
+
+/* Arguments encoded in opt->value. */
+struct parse_events_option_args {
+	struct evlist **evlistp;
+	const char *pmu_filter;
+	bool cputype_filter;
+};
+int parse_events_option(const struct option *opt, const char *str, int unset);
+int parse_events_option_new_evlist(const struct option *opt, const char *str, int unset);
+__attribute__((nonnull(1, 2, 5))) int
+__parse_events(struct evlist *evlist, const char *str, const char *pmu_filter,
+	       bool cputype_filter, struct parse_events_error *error,
+	       bool fake_pmu, bool warn_if_reordered, bool fake_tp);
+
+__attribute__((nonnull(1, 2, 3)))
+static inline int parse_events(struct evlist *evlist, const char *str,
+			       struct parse_events_error *err)
+{
+	return __parse_events(evlist, str, /*pmu_filter=*/NULL,
+			      /*cputype_filter=*/false, err, /*fake_pmu=*/false,
+			      /*warn_if_reordered=*/true,
+			      /*fake_tp=*/false);
+}
+
+int parse_event(struct evlist *evlist, const char *str);
+
+int parse_filter(const struct option *opt, const char *str, int unset);
+int parse_uid_filter(struct evlist *evlist, uid_t uid);
+int exclude_perf(const struct option *opt, const char *arg, int unset);
+
+enum parse_events__term_val_type {
+	PARSE_EVENTS__TERM_TYPE_NUM,
+	PARSE_EVENTS__TERM_TYPE_STR,
+};
+
+enum parse_events__term_type {
+	PARSE_EVENTS__TERM_TYPE_USER,
+	PARSE_EVENTS__TERM_TYPE_CONFIG,
+	PARSE_EVENTS__TERM_TYPE_CONFIG1,
+	PARSE_EVENTS__TERM_TYPE_CONFIG2,
+	PARSE_EVENTS__TERM_TYPE_CONFIG3,
+	PARSE_EVENTS__TERM_TYPE_CONFIG4,
+	PARSE_EVENTS__TERM_TYPE_NAME,
+	PARSE_EVENTS__TERM_TYPE_SAMPLE_PERIOD,
+	PARSE_EVENTS__TERM_TYPE_SAMPLE_FREQ,
+	PARSE_EVENTS__TERM_TYPE_BRANCH_SAMPLE_TYPE,
+	PARSE_EVENTS__TERM_TYPE_TIME,
+	PARSE_EVENTS__TERM_TYPE_CALLGRAPH,
+	PARSE_EVENTS__TERM_TYPE_STACKSIZE,
+	PARSE_EVENTS__TERM_TYPE_NOINHERIT,
+	PARSE_EVENTS__TERM_TYPE_INHERIT,
+	PARSE_EVENTS__TERM_TYPE_MAX_STACK,
+	PARSE_EVENTS__TERM_TYPE_MAX_EVENTS,
+	PARSE_EVENTS__TERM_TYPE_NOOVERWRITE,
+	PARSE_EVENTS__TERM_TYPE_OVERWRITE,
+	PARSE_EVENTS__TERM_TYPE_DRV_CFG,
+	PARSE_EVENTS__TERM_TYPE_PERCORE,
+	PARSE_EVENTS__TERM_TYPE_AUX_OUTPUT,
+	PARSE_EVENTS__TERM_TYPE_AUX_ACTION,
+	PARSE_EVENTS__TERM_TYPE_AUX_SAMPLE_SIZE,
+	PARSE_EVENTS__TERM_TYPE_METRIC_ID,
+	PARSE_EVENTS__TERM_TYPE_RAW,
+	PARSE_EVENTS__TERM_TYPE_CPU,
+	PARSE_EVENTS__TERM_TYPE_RATIO_TO_PREV,
+	PARSE_EVENTS__TERM_TYPE_LEGACY_HARDWARE_CONFIG,
+	PARSE_EVENTS__TERM_TYPE_LEGACY_CACHE_CONFIG,
+#define	__PARSE_EVENTS__TERM_TYPE_NR (PARSE_EVENTS__TERM_TYPE_LEGACY_CACHE_CONFIG + 1)
+};
+
+struct parse_events_term {
+	/** @list: The term list the term is a part of. */
+	struct list_head list;
+	/**
+	 * @config: The left-hand side of a term assignment, so the term
+	 * "event=8" would have the config be "event"
+	 */
+	const char *config;
+	/**
+	 * @val: The right-hand side of a term assignment that can either be a
+	 * string or a number depending on type_val.
+	 */
+	union {
+		char *str;
+		u64  num;
+	} val;
+	/** @type_val: The union variable in val to be used for the term. */
+	enum parse_events__term_val_type type_val;
+	/**
+	 * @type_term: A predefined term type or PARSE_EVENTS__TERM_TYPE_USER
+	 * when not inbuilt.
+	 */
+	enum parse_events__term_type type_term;
+	/**
+	 * @err_term: The column index of the term from parsing, used during
+	 * error output.
+	 */
+	int err_term;
+	/**
+	 * @err_val: The column index of the val from parsing, used during error
+	 * output.
+	 */
+	int err_val;
+	/** @used: Was the term used during parameterized-eval. */
+	bool used;
+	/**
+	 * @weak: A term from the sysfs or json encoding of an event that
+	 * shouldn't override terms coming from the command line.
+	 */
+	bool weak;
+	/**
+	 * @no_value: Is there no value. If a numeric term has no value then the
+	 * value is assumed to be 1. An event name also has no value.
+	 */
+	bool no_value;
+};
+
+struct parse_events_error {
+	/** @list: The head of a list of errors. */
+	struct list_head list;
+};
+
+/* A wrapper around a list of terms for the sake of better type safety. */
+struct parse_events_terms {
+	struct list_head terms;
+};
+
+struct parse_events_state {
+	/* The list parsed events are placed on. */
+	struct list_head	   list;
+	/* The updated index used by entries as they are added. */
+	int			   idx;
+	/* Error information. */
+	struct parse_events_error *error;
+	/* Holds returned terms for term parsing. */
+	struct parse_events_terms *terms;
+	/* Start token. */
+	int			   stoken;
+	/* Use the fake PMU marker for testing. */
+	bool			   fake_pmu;
+	/* Skip actual tracepoint processing for testing. */
+	bool			   fake_tp;
+	/* If non-null, when wildcard matching only match the given PMU. */
+	const char		  *pmu_filter;
+	/* If true, the pmu_filter was set by --cputype option. */
+	bool cputype_filter;
+	/* Should PE_LEGACY_NAME tokens be generated for config terms? */
+	bool			   match_legacy_cache_terms;
+	/* Were multiple PMUs scanned to find events? */
+	bool			   wild_card_pmus;
+};
+
+const char *parse_events__term_type_str(enum parse_events__term_type term_type);
+
+bool parse_events__filter_pmu(const struct parse_events_state *parse_state,
+			      const struct perf_pmu *pmu);
+void parse_events__shrink_config_terms(void);
+int parse_events__is_hardcoded_term(struct parse_events_term *term);
+int parse_events_term__num(struct parse_events_term **term,
+			   enum parse_events__term_type type_term,
+			   const char *config, u64 num,
+			   bool novalue,
+			   void *loc_term, void *loc_val);
+int parse_events_term__str(struct parse_events_term **term,
+			   enum parse_events__term_type type_term,
+			   char *config, char *str,
+			   void *loc_term, void *loc_val);
+int parse_events_term__term(struct parse_events_term **term,
+			    enum parse_events__term_type term_lhs,
+			    enum parse_events__term_type term_rhs,
+			    void *loc_term, void *loc_val);
+int parse_events_term__clone(struct parse_events_term **new,
+			     const struct parse_events_term *term);
+void parse_events_term__delete(struct parse_events_term *term);
+
+void parse_events_terms__delete(struct parse_events_terms *terms);
+void parse_events_terms__init(struct parse_events_terms *terms);
+void parse_events_terms__exit(struct parse_events_terms *terms);
+int parse_events_terms(struct parse_events_terms *terms, const char *str);
+
+struct parse_events_modifier {
+	u8 precise;	/* Number of repeated 'p' for precision. */
+	bool precise_max : 1;	/* 'P' */
+	bool non_idle : 1;	/* 'I' */
+	bool sample_read : 1;	/* 'S' */
+	bool pinned : 1;	/* 'D' */
+	bool exclusive : 1;	/* 'e' */
+	bool weak : 1;		/* 'W' */
+	bool bpf : 1;		/* 'b' */
+	bool user : 1;		/* 'u' */
+	bool kernel : 1;	/* 'k' */
+	bool hypervisor : 1;	/* 'h' */
+	bool guest : 1;		/* 'G' */
+	bool host : 1;		/* 'H' */
+	bool retire_lat : 1;	/* 'R' */
+	bool dont_regroup : 1;	/* 'X' */
+};
+
+int parse_events__modifier_event(struct parse_events_state *parse_state, void *loc,
+				 struct list_head *list, struct parse_events_modifier mod);
+int parse_events__modifier_group(struct parse_events_state *parse_state, void *loc,
+				 struct list_head *list, struct parse_events_modifier mod);
+int parse_events__set_default_name(struct list_head *list, char *name);
+int parse_events_add_tracepoint(struct parse_events_state *parse_state,
+				struct list_head *list,
+				const char *sys, const char *event,
+				struct parse_events_error *error,
+				struct parse_events_terms *head_config, void *loc);
+int parse_events_add_numeric(struct parse_events_state *parse_state,
+			     struct list_head *list,
+			     u32 type, u64 config,
+			     const struct parse_events_terms *head_config,
+			     bool wildcard);
+int parse_events__decode_legacy_cache(const char *name, int pmu_type, __u64 *config);
+int parse_events_add_breakpoint(struct parse_events_state *parse_state,
+				struct list_head *list,
+				u64 addr, char *type, u64 len,
+				struct parse_events_terms *head_config);
+
+struct evsel *parse_events__add_event(int idx, struct perf_event_attr *attr,
+				      const char *name, const char *metric_id,
+				      struct perf_pmu *pmu);
+
+int parse_events_multi_pmu_add(struct parse_events_state *parse_state,
+			       const char *event_name,
+			       const struct parse_events_terms *const_parsed_terms,
+			       struct list_head **listp, void *loc);
+
+int parse_events_multi_pmu_add_or_add_pmu(struct parse_events_state *parse_state,
+					const char *event_or_pmu,
+					const struct parse_events_terms *const_parsed_terms,
+					struct list_head **listp,
+					void *loc_);
+
+void parse_events__set_leader(char *name, struct list_head *list);
+
+struct event_symbol {
+	const char	*symbol;
+	const char	*alias;
+};
+
+char *parse_events_formats_error_string(char *additional_terms);
+
+void parse_events_error__init(struct parse_events_error *err);
+void parse_events_error__exit(struct parse_events_error *err);
+void parse_events_error__handle(struct parse_events_error *err, int idx,
+				char *str, char *help);
+void parse_events_error__print(const struct parse_events_error *err,
+			       const char *event);
+bool parse_events_error__contains(const struct parse_events_error *err,
+				  const char *needle);
+#ifdef HAVE_LIBELF_SUPPORT
+/*
+ * If the probe point starts with '%',
+ * or starts with "sdt_" and has a ':' but no '=',
+ * then it should be a SDT/cached probe point.
+ */
+static inline bool is_sdt_event(char *str)
+{
+	return (str[0] == '%' ||
+		(!strncmp(str, "sdt_", 4) &&
+		 !!strchr(str, ':') && !strchr(str, '=')));
+}
+#else
+static inline bool is_sdt_event(char *str __maybe_unused)
+{
+	return false;
+}
+#endif /* HAVE_LIBELF_SUPPORT */
+
+size_t default_breakpoint_len(void);
+
+#endif /* __PERF_PARSE_EVENTS_H */