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, 220 insertions, 0 deletions

diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h
new file mode 100644
index 000000000..ac5803d5f
--- /dev/null
+++ b/tools/perf/util/session.h
@@ -0,0 +1,220 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __PERF_SESSION_H
+#define __PERF_SESSION_H
+
+#include "trace-event.h"
+#include "event.h"
+#include "header.h"
+#include "machine.h"
+#include "data.h"
+#include "ordered-events.h"
+#include "util/compress.h"
+#include <linux/kernel.h>
+#include <linux/rbtree.h>
+#include <linux/perf_event.h>
+
+struct ip_callchain;
+struct symbol;
+struct thread;
+
+struct auxtrace;
+struct itrace_synth_opts;
+
+struct decomp_data {
+	struct decomp	 *decomp;
+	struct decomp	 *decomp_last;
+	struct zstd_data *zstd_decomp;
+};
+
+/**
+ * struct perf_session- A Perf session holds the main state when the program is
+ * working with live perf events or reading data from an input file.
+ *
+ * The rough organization of a perf_session is:
+ * ```
+ * +--------------+           +-----------+           +------------+
+ * |   Session    |1..* ----->|  Machine  |1..* ----->|   Thread   |
+ * +--------------+           +-----------+           +------------+
+ * ```
+ */
+struct perf_session {
+	/**
+	 * @header: The read version of a perf_file_header, or captures global
+	 * information from a live session.
+	 */
+	struct perf_header	header;
+	/** @machines: Machines within the session a host and 0 or more guests. */
+	struct machines		machines;
+	/** @evlist: List of evsels/events of the session. */
+	struct evlist	*evlist;
+	/** @auxtrace: callbacks to allow AUX area data decoding. */
+	const struct auxtrace	*auxtrace;
+	/** @itrace_synth_opts: AUX area tracing synthesis options. */
+	struct itrace_synth_opts *itrace_synth_opts;
+	/** @auxtrace_index: index of AUX area tracing events within a perf.data file. */
+	struct list_head	auxtrace_index;
+#ifdef HAVE_LIBTRACEEVENT
+	/** @tevent: handles for libtraceevent and plugins. */
+	struct trace_event	tevent;
+#endif
+	/** @time_conv: Holds contents of last PERF_RECORD_TIME_CONV event. */
+	struct perf_record_time_conv	time_conv;
+	/** @trace_event_repipe: When set causes read trace events to be written to stdout. */
+	bool			trace_event_repipe;
+	/**
+	 * @one_mmap: The reader will use a single mmap by default. There may be
+	 * multiple data files in particular for aux events. If this is true
+	 * then the single big mmap for the data file can be assumed.
+	 */
+	bool			one_mmap;
+	/** @one_mmap_addr: Address of initial perf data file reader mmap. */
+	void			*one_mmap_addr;
+	/** @one_mmap_offset: File offset in perf.data file when mapped. */
+	u64			one_mmap_offset;
+	/** @one_mmap_size: Size of the single mmap in bytes. */
+	u64			one_mmap_size;
+	/** @ordered_events: Used to turn unordered events into ordered ones. */
+	struct ordered_events	ordered_events;
+	/** @data: Optional perf data file being read from. */
+	struct perf_data	*data;
+	/** @tool: callbacks for event handling. */
+	const struct perf_tool	*tool;
+	/**
+	 * @bytes_transferred: Used by perf record to count written bytes before
+	 * compression.
+	 */
+	u64			bytes_transferred;
+	/**
+	 * @bytes_compressed: Used by perf record to count written bytes after
+	 * compression.
+	 */
+	u64			bytes_compressed;
+	/** @zstd_data: Owner of global compression state, buffers, etc. */
+	struct zstd_data	zstd_data;
+	struct decomp_data	decomp_data;
+	struct decomp_data	*active_decomp;
+};
+
+struct decomp {
+	struct decomp *next;
+	u64 file_pos;
+	const char *file_path;
+	size_t mmap_len;
+	u64 head;
+	size_t size;
+	char data[];
+};
+
+struct perf_tool;
+
+struct perf_session *__perf_session__new(struct perf_data *data,
+					 struct perf_tool *tool,
+					 bool trace_event_repipe,
+					 struct perf_env *host_env);
+
+static inline struct perf_session *perf_session__new(struct perf_data *data,
+						     struct perf_tool *tool)
+{
+	return __perf_session__new(data, tool, /*trace_event_repipe=*/false, /*host_env=*/NULL);
+}
+
+void perf_session__delete(struct perf_session *session);
+
+void perf_event_header__bswap(struct perf_event_header *hdr);
+
+bool perf_event__too_small(const union perf_event *event, u32 *min);
+
+int perf_session__peek_event(struct perf_session *session, off_t file_offset,
+			     void *buf, size_t buf_sz,
+			     union perf_event **event_ptr,
+			     struct perf_sample *sample);
+typedef int (*peek_events_cb_t)(struct perf_session *session,
+				union perf_event *event, u64 offset,
+				void *data);
+int perf_session__peek_events(struct perf_session *session, u64 offset,
+			      u64 size, peek_events_cb_t cb, void *data);
+
+int perf_session__process_events(struct perf_session *session);
+
+int perf_session__queue_event(struct perf_session *s, union perf_event *event,
+			      u64 timestamp, u64 file_offset, const char *file_path);
+
+int perf_session__resolve_callchain(struct perf_session *session,
+				    struct evsel *evsel,
+				    struct thread *thread,
+				    struct ip_callchain *chain,
+				    struct symbol **parent);
+
+bool perf_session__has_traces(struct perf_session *session, const char *msg);
+bool perf_session__has_switch_events(struct perf_session *session);
+
+void perf_event__attr_swap(struct perf_event_attr *attr);
+
+int perf_session__create_kernel_maps(struct perf_session *session);
+
+void perf_session__set_id_hdr_size(struct perf_session *session);
+
+static inline
+struct machine *perf_session__find_machine(struct perf_session *session, pid_t pid)
+{
+	return machines__find(&session->machines, pid);
+}
+
+static inline
+struct machine *perf_session__findnew_machine(struct perf_session *session, pid_t pid)
+{
+	return machines__findnew(&session->machines, pid);
+}
+
+struct thread *perf_session__findnew(struct perf_session *session, pid_t pid);
+int perf_session__register_idle_thread(struct perf_session *session);
+
+size_t perf_session__fprintf(struct perf_session *session, FILE *fp);
+
+size_t perf_session__fprintf_dsos(struct perf_session *session, FILE *fp);
+
+size_t perf_session__fprintf_dsos_buildid(struct perf_session *session, FILE *fp,
+					  bool (fn)(struct dso *dso, int parm), int parm);
+
+size_t perf_session__fprintf_nr_events(struct perf_session *session, FILE *fp);
+
+void perf_session__dump_kmaps(struct perf_session *session);
+
+struct evsel *perf_session__find_first_evtype(struct perf_session *session,
+					    unsigned int type);
+
+int perf_session__cpu_bitmap(struct perf_session *session,
+			     const char *cpu_list, unsigned long *cpu_bitmap);
+
+void perf_session__fprintf_info(struct perf_session *s, FILE *fp, bool full);
+
+struct evsel_str_handler;
+
+#define perf_session__set_tracepoints_handlers(session, array) \
+	__evlist__set_tracepoints_handlers(session->evlist, array, ARRAY_SIZE(array))
+
+extern volatile int session_done;
+
+#define session_done()	READ_ONCE(session_done)
+
+int perf_session__deliver_synth_event(struct perf_session *session,
+				      union perf_event *event,
+				      struct perf_sample *sample);
+int perf_session__deliver_synth_attr_event(struct perf_session *session,
+					   const struct perf_event_attr *attr,
+					   u64 id);
+
+int perf_session__dsos_hit_all(struct perf_session *session);
+
+int perf_event__process_id_index(const struct perf_tool *tool,
+				 struct perf_session *session,
+				 union perf_event *event);
+
+int perf_event__process_finished_round(const struct perf_tool *tool,
+				       union perf_event *event,
+				       struct ordered_events *oe);
+
+struct perf_env *perf_session__env(struct perf_session *session);
+uint16_t perf_session__e_machine(struct perf_session *session, uint32_t *e_flags);
+
+#endif /* __PERF_SESSION_H */