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, 225 insertions, 0 deletions

diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h
new file mode 100644
index 000000000..5e03f884b
--- /dev/null
+++ b/tools/perf/util/header.h
@@ -0,0 +1,225 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __PERF_HEADER_H
+#define __PERF_HEADER_H
+
+#include <linux/stddef.h>
+#include <linux/perf_event.h>
+#include <sys/types.h>
+#include <stdio.h> // FILE
+#include <stdbool.h>
+#include <linux/bitmap.h>
+#include <linux/types.h>
+#include "env.h"
+#include <perf/cpumap.h>
+
+struct evlist;
+union perf_event;
+struct perf_header;
+struct perf_session;
+struct perf_tool;
+
+enum {
+	HEADER_RESERVED		= 0,	/* always cleared */
+	HEADER_FIRST_FEATURE	= 1,
+	HEADER_TRACING_DATA	= 1,
+	HEADER_BUILD_ID,
+
+	HEADER_HOSTNAME,
+	HEADER_OSRELEASE,
+	HEADER_VERSION,
+	HEADER_ARCH,
+	HEADER_NRCPUS,
+	HEADER_CPUDESC,
+	HEADER_CPUID,
+	HEADER_TOTAL_MEM,
+	HEADER_CMDLINE,
+	HEADER_EVENT_DESC,
+	HEADER_CPU_TOPOLOGY,
+	HEADER_NUMA_TOPOLOGY,
+	HEADER_BRANCH_STACK,
+	HEADER_PMU_MAPPINGS,
+	HEADER_GROUP_DESC,
+	HEADER_AUXTRACE,
+	HEADER_STAT,
+	HEADER_CACHE,
+	HEADER_SAMPLE_TIME,
+	HEADER_MEM_TOPOLOGY,
+	HEADER_CLOCKID,
+	HEADER_DIR_FORMAT,
+	HEADER_BPF_PROG_INFO,
+	HEADER_BPF_BTF,
+	HEADER_COMPRESSED,
+	HEADER_CPU_PMU_CAPS,
+	HEADER_CLOCK_DATA,
+	HEADER_HYBRID_TOPOLOGY,
+	HEADER_PMU_CAPS,
+	HEADER_CPU_DOMAIN_INFO,
+	HEADER_E_MACHINE,
+	HEADER_CLN_SIZE,
+	HEADER_LAST_FEATURE,
+	HEADER_FEAT_BITS	= 256,
+};
+
+enum perf_header_version {
+	PERF_HEADER_VERSION_1,
+	PERF_HEADER_VERSION_2,
+};
+
+struct perf_file_section {
+	u64 offset;
+	u64 size;
+};
+
+/**
+ * struct perf_file_header: Header representation on disk.
+ */
+struct perf_file_header {
+	/** @magic: Holds "PERFILE2". */
+	u64				magic;
+	/** @size: Size of this header - sizeof(struct perf_file_header). */
+	u64				size;
+	/**
+	 * @attr_size: Size of attrs entries - sizeof(struct perf_event_attr) +
+	 * sizeof(struct perf_file_section).
+	 */
+	u64				attr_size;
+	/** @attrs: Offset and size of file section holding attributes. */
+	struct perf_file_section	attrs;
+	/** @data: Offset and size of file section holding regular event data. */
+	struct perf_file_section	data;
+	/** @event_types: Ignored. */
+	struct perf_file_section	event_types;
+	/**
+	 * @adds_features: Bitmap of features. The features are immediately after the data section.
+	 */
+	DECLARE_BITMAP(adds_features, HEADER_FEAT_BITS);
+};
+
+struct perf_pipe_file_header {
+	u64				magic;
+	u64				size;
+};
+
+int perf_file_header__read(struct perf_file_header *header,
+			   struct perf_header *ph, int fd);
+
+struct perf_header {
+	enum perf_header_version	version;
+	bool				needs_swap;
+	u64				data_offset;
+	u64				data_size;
+	u64				feat_offset;
+	DECLARE_BITMAP(adds_features, HEADER_FEAT_BITS);
+	int				last_feat;
+	struct perf_env 	env;
+};
+
+struct feat_fd {
+	struct perf_header *ph;
+	int		   fd;
+	void		   *buf;	/* Either buf != NULL or fd >= 0 */
+	ssize_t		   offset;
+	size_t		   size;
+	struct evsel	   *events;
+};
+
+struct perf_header_feature_ops {
+	int	   (*write)(struct feat_fd *ff, struct evlist *evlist);
+	void	   (*print)(struct feat_fd *ff, FILE *fp);
+	int	   (*process)(struct feat_fd *ff, void *data);
+	const char *name;
+	bool	   full_only;
+	bool	   synthesize;
+};
+
+extern const char perf_version_string[];
+
+const char *header_feat__name(unsigned int id);
+
+int perf_session__read_header(struct perf_session *session);
+int perf_session__write_header(struct perf_session *session,
+			       struct evlist *evlist,
+			       int fd, bool at_exit);
+int perf_header__write_pipe(int fd);
+
+/* feat_writer writes a feature section to output */
+struct feat_writer {
+	int (*write)(struct feat_writer *fw, void *buf, size_t sz);
+};
+
+/* feat_copier copies a feature section using feat_writer to output */
+struct feat_copier {
+	int (*copy)(struct feat_copier *fc, int feat, struct feat_writer *fw);
+};
+
+int perf_session__inject_header(struct perf_session *session,
+				struct evlist *evlist,
+				int fd,
+				struct feat_copier *fc,
+				bool write_attrs_after_data);
+
+size_t perf_session__data_offset(struct evlist *evlist);
+
+void perf_header__set_feat(struct perf_header *header, int feat);
+void perf_header__clear_feat(struct perf_header *header, int feat);
+bool perf_header__has_feat(const struct perf_header *header, int feat);
+
+int perf_header__set_cmdline(int argc, const char **argv);
+
+int perf_header__process_sections(struct perf_header *header, int fd,
+				  void *data,
+				  int (*process)(struct perf_file_section *section,
+				  struct perf_header *ph,
+				  int feat, int fd, void *data));
+
+int perf_header__fprintf_info(struct perf_session *s, FILE *fp, bool full);
+
+int perf_event__process_feature(const struct perf_tool *tool,
+				struct perf_session *session,
+				union perf_event *event);
+int perf_event__process_attr(const struct perf_tool *tool, union perf_event *event,
+			     struct evlist **pevlist);
+int perf_event__process_event_update(const struct perf_tool *tool,
+				     union perf_event *event,
+				     struct evlist **pevlist);
+size_t perf_event__fprintf_attr(union perf_event *event, FILE *fp);
+size_t perf_event__fprintf_event_update(union perf_event *event, FILE *fp);
+#ifdef HAVE_LIBTRACEEVENT
+int perf_event__process_tracing_data(const struct perf_tool *tool,
+				     struct perf_session *session,
+				     union perf_event *event);
+#endif
+int perf_event__process_build_id(const struct perf_tool *tool,
+				 struct perf_session *session,
+				 union perf_event *event);
+bool is_perf_magic(u64 magic);
+
+#define NAME_ALIGN 64
+
+struct feat_fd;
+
+int do_write(struct feat_fd *fd, const void *buf, size_t size);
+
+int write_padded(struct feat_fd *fd, const void *bf,
+		 size_t count, size_t count_aligned);
+
+#define MAX_CACHE_LVL 4
+
+int build_caches_for_cpu(u32 cpu, struct cpu_cache_level caches[], u32 *cntp);
+
+#define DEFAULT_CACHELINE_SIZE 64
+
+/*
+ * arch specific callback
+ */
+int get_cpuid(char *buffer, size_t sz, struct perf_cpu cpu);
+
+char *get_cpuid_str(struct perf_cpu cpu);
+
+char *get_cpuid_allow_env_override(struct perf_cpu cpu);
+
+int strcmp_cpuid_str(const char *s1, const char *s2);
+
+struct cpu_domain_map **build_cpu_domain_map(u32 *schedstat_version, u32 *max_sched_domains,
+					     u32 nr);
+#endif /* __PERF_HEADER_H */