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, 944 insertions, 0 deletions

diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
new file mode 100644
index 000000000..ea75816d1
--- /dev/null
+++ b/tools/perf/util/event.c
@@ -0,0 +1,944 @@
+#include <errno.h>
+#include <fcntl.h>
+#include <inttypes.h>
+#include <linux/compiler.h>
+#include <linux/kernel.h>
+#include <linux/types.h>
+#include <perf/cpumap.h>
+#include <perf/event.h>
+#include <stdio.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <unistd.h>
+#include <uapi/linux/mman.h> /* To get things like MAP_HUGETLB even on older libc headers */
+#include <linux/perf_event.h>
+#include "cpumap.h"
+#include "dso.h"
+#include "env.h"
+#include "event.h"
+#include "debug.h"
+#include "hist.h"
+#include "machine.h"
+#include "sort.h"
+#include "string2.h"
+#include "strlist.h"
+#include "thread.h"
+#include "thread_map.h"
+#include "time-utils.h"
+#include <linux/ctype.h>
+#include "map.h"
+#include "util/namespaces.h"
+#include "symbol.h"
+#include "symbol/kallsyms.h"
+#include "asm/bug.h"
+#include "stat.h"
+#include "session.h"
+#include "bpf-event.h"
+#include "print_binary.h"
+#include "tool.h"
+#include "util.h"
+
+static const char *perf_event__names[] = {
+	[0]					= "TOTAL",
+	[PERF_RECORD_MMAP]			= "MMAP",
+	[PERF_RECORD_MMAP2]			= "MMAP2",
+	[PERF_RECORD_LOST]			= "LOST",
+	[PERF_RECORD_COMM]			= "COMM",
+	[PERF_RECORD_EXIT]			= "EXIT",
+	[PERF_RECORD_THROTTLE]			= "THROTTLE",
+	[PERF_RECORD_UNTHROTTLE]		= "UNTHROTTLE",
+	[PERF_RECORD_FORK]			= "FORK",
+	[PERF_RECORD_READ]			= "READ",
+	[PERF_RECORD_SAMPLE]			= "SAMPLE",
+	[PERF_RECORD_AUX]			= "AUX",
+	[PERF_RECORD_ITRACE_START]		= "ITRACE_START",
+	[PERF_RECORD_LOST_SAMPLES]		= "LOST_SAMPLES",
+	[PERF_RECORD_SWITCH]			= "SWITCH",
+	[PERF_RECORD_SWITCH_CPU_WIDE]		= "SWITCH_CPU_WIDE",
+	[PERF_RECORD_NAMESPACES]		= "NAMESPACES",
+	[PERF_RECORD_KSYMBOL]			= "KSYMBOL",
+	[PERF_RECORD_BPF_EVENT]			= "BPF_EVENT",
+	[PERF_RECORD_CGROUP]			= "CGROUP",
+	[PERF_RECORD_TEXT_POKE]			= "TEXT_POKE",
+	[PERF_RECORD_AUX_OUTPUT_HW_ID]		= "AUX_OUTPUT_HW_ID",
+	[PERF_RECORD_CALLCHAIN_DEFERRED]	= "CALLCHAIN_DEFERRED",
+	[PERF_RECORD_HEADER_ATTR]		= "ATTR",
+	[PERF_RECORD_HEADER_EVENT_TYPE]		= "EVENT_TYPE",
+	[PERF_RECORD_HEADER_TRACING_DATA]	= "TRACING_DATA",
+	[PERF_RECORD_HEADER_BUILD_ID]		= "BUILD_ID",
+	[PERF_RECORD_FINISHED_ROUND]		= "FINISHED_ROUND",
+	[PERF_RECORD_ID_INDEX]			= "ID_INDEX",
+	[PERF_RECORD_AUXTRACE_INFO]		= "AUXTRACE_INFO",
+	[PERF_RECORD_AUXTRACE]			= "AUXTRACE",
+	[PERF_RECORD_AUXTRACE_ERROR]		= "AUXTRACE_ERROR",
+	[PERF_RECORD_THREAD_MAP]		= "THREAD_MAP",
+	[PERF_RECORD_CPU_MAP]			= "CPU_MAP",
+	[PERF_RECORD_STAT_CONFIG]		= "STAT_CONFIG",
+	[PERF_RECORD_STAT]			= "STAT",
+	[PERF_RECORD_STAT_ROUND]		= "STAT_ROUND",
+	[PERF_RECORD_EVENT_UPDATE]		= "EVENT_UPDATE",
+	[PERF_RECORD_TIME_CONV]			= "TIME_CONV",
+	[PERF_RECORD_HEADER_FEATURE]		= "FEATURE",
+	[PERF_RECORD_COMPRESSED]		= "COMPRESSED",
+	[PERF_RECORD_FINISHED_INIT]		= "FINISHED_INIT",
+	[PERF_RECORD_COMPRESSED2]		= "COMPRESSED2",
+	[PERF_RECORD_BPF_METADATA]		= "BPF_METADATA",
+	[PERF_RECORD_SCHEDSTAT_CPU]		= "SCHEDSTAT_CPU",
+	[PERF_RECORD_SCHEDSTAT_DOMAIN]		= "SCHEDSTAT_DOMAIN",
+};
+
+const char *perf_event__name(unsigned int id)
+{
+	if (id >= ARRAY_SIZE(perf_event__names))
+		return "INVALID";
+	if (!perf_event__names[id])
+		return "UNKNOWN";
+	return perf_event__names[id];
+}
+
+struct process_symbol_args {
+	const char *name;
+	u64	   start;
+};
+
+static int find_func_symbol_cb(void *arg, const char *name, char type,
+			       u64 start)
+{
+	struct process_symbol_args *args = arg;
+
+	/*
+	 * Must be a function or at least an alias, as in PARISC64, where "_text" is
+	 * an 'A' to the same address as "_stext".
+	 */
+	if (!(kallsyms__is_function(type) ||
+	      type == 'A') || strcmp(name, args->name))
+		return 0;
+
+	args->start = start;
+	return 1;
+}
+
+static int find_any_symbol_cb(void *arg, const char *name,
+			      char type __maybe_unused, u64 start)
+{
+	struct process_symbol_args *args = arg;
+
+	if (strcmp(name, args->name))
+		return 0;
+
+	args->start = start;
+	return 1;
+}
+
+int kallsyms__get_function_start(const char *kallsyms_filename,
+				 const char *symbol_name, u64 *addr)
+{
+	struct process_symbol_args args = { .name = symbol_name, };
+
+	if (kallsyms__parse(kallsyms_filename, &args, find_func_symbol_cb) <= 0)
+		return -1;
+
+	*addr = args.start;
+	return 0;
+}
+
+int kallsyms__get_symbol_start(const char *kallsyms_filename,
+			       const char *symbol_name, u64 *addr)
+{
+	struct process_symbol_args args = { .name = symbol_name, };
+
+	if (kallsyms__parse(kallsyms_filename, &args, find_any_symbol_cb) <= 0)
+		return -1;
+
+	*addr = args.start;
+	return 0;
+}
+
+void perf_event__read_stat_config(struct perf_stat_config *config,
+				  struct perf_record_stat_config *event)
+{
+	unsigned i;
+
+	for (i = 0; i < event->nr; i++) {
+
+		switch (event->data[i].tag) {
+#define CASE(__term, __val)					\
+		case PERF_STAT_CONFIG_TERM__##__term:		\
+			config->__val = event->data[i].val;	\
+			break;
+
+		CASE(AGGR_MODE,  aggr_mode)
+		CASE(SCALE,      scale)
+		CASE(INTERVAL,   interval)
+		CASE(AGGR_LEVEL, aggr_level)
+#undef CASE
+		default:
+			pr_warning("unknown stat config term %" PRI_lu64 "\n",
+				   event->data[i].tag);
+		}
+	}
+}
+
+size_t perf_event__fprintf_comm(union perf_event *event, FILE *fp)
+{
+	const char *s;
+
+	if (event->header.misc & PERF_RECORD_MISC_COMM_EXEC)
+		s = " exec";
+	else
+		s = "";
+
+	return fprintf(fp, "%s: %s:%d/%d\n", s, event->comm.comm, event->comm.pid, event->comm.tid);
+}
+
+size_t perf_event__fprintf_namespaces(union perf_event *event, FILE *fp)
+{
+	size_t ret = 0;
+	struct perf_ns_link_info *ns_link_info;
+	u32 nr_namespaces, idx;
+
+	ns_link_info = event->namespaces.link_info;
+	nr_namespaces = event->namespaces.nr_namespaces;
+
+	ret += fprintf(fp, " %d/%d - nr_namespaces: %u\n\t\t[",
+		       event->namespaces.pid,
+		       event->namespaces.tid,
+		       nr_namespaces);
+
+	for (idx = 0; idx < nr_namespaces; idx++) {
+		if (idx && (idx % 4 == 0))
+			ret += fprintf(fp, "\n\t\t ");
+
+		ret  += fprintf(fp, "%u/%s: %" PRIu64 "/%#" PRIx64 "%s", idx,
+				perf_ns__name(idx), (u64)ns_link_info[idx].dev,
+				(u64)ns_link_info[idx].ino,
+				((idx + 1) != nr_namespaces) ? ", " : "]\n");
+	}
+
+	return ret;
+}
+
+size_t perf_event__fprintf_cgroup(union perf_event *event, FILE *fp)
+{
+	return fprintf(fp, " cgroup: %" PRI_lu64 " %s\n",
+		       event->cgroup.id, event->cgroup.path);
+}
+
+int perf_event__process_comm(const struct perf_tool *tool __maybe_unused,
+			     union perf_event *event,
+			     struct perf_sample *sample,
+			     struct machine *machine)
+{
+	return machine__process_comm_event(machine, event, sample);
+}
+
+int perf_event__process_namespaces(const struct perf_tool *tool __maybe_unused,
+				   union perf_event *event,
+				   struct perf_sample *sample,
+				   struct machine *machine)
+{
+	return machine__process_namespaces_event(machine, event, sample);
+}
+
+int perf_event__process_cgroup(const struct perf_tool *tool __maybe_unused,
+			       union perf_event *event,
+			       struct perf_sample *sample,
+			       struct machine *machine)
+{
+	return machine__process_cgroup_event(machine, event, sample);
+}
+
+int perf_event__process_lost(const struct perf_tool *tool __maybe_unused,
+			     union perf_event *event,
+			     struct perf_sample *sample,
+			     struct machine *machine)
+{
+	return machine__process_lost_event(machine, event, sample);
+}
+
+int perf_event__process_aux(const struct perf_tool *tool __maybe_unused,
+			    union perf_event *event,
+			    struct perf_sample *sample __maybe_unused,
+			    struct machine *machine)
+{
+	return machine__process_aux_event(machine, event);
+}
+
+int perf_event__process_itrace_start(const struct perf_tool *tool __maybe_unused,
+				     union perf_event *event,
+				     struct perf_sample *sample __maybe_unused,
+				     struct machine *machine)
+{
+	return machine__process_itrace_start_event(machine, event);
+}
+
+int perf_event__process_aux_output_hw_id(const struct perf_tool *tool __maybe_unused,
+					 union perf_event *event,
+					 struct perf_sample *sample __maybe_unused,
+					 struct machine *machine)
+{
+	return machine__process_aux_output_hw_id_event(machine, event);
+}
+
+int perf_event__process_lost_samples(const struct perf_tool *tool __maybe_unused,
+				     union perf_event *event,
+				     struct perf_sample *sample,
+				     struct machine *machine)
+{
+	return machine__process_lost_samples_event(machine, event, sample);
+}
+
+int perf_event__process_switch(const struct perf_tool *tool __maybe_unused,
+			       union perf_event *event,
+			       struct perf_sample *sample __maybe_unused,
+			       struct machine *machine)
+{
+	return machine__process_switch_event(machine, event);
+}
+
+int perf_event__process_ksymbol(const struct perf_tool *tool __maybe_unused,
+				union perf_event *event,
+				struct perf_sample *sample __maybe_unused,
+				struct machine *machine)
+{
+	return machine__process_ksymbol(machine, event, sample);
+}
+
+int perf_event__process_bpf(const struct perf_tool *tool __maybe_unused,
+			    union perf_event *event,
+			    struct perf_sample *sample,
+			    struct machine *machine)
+{
+	return machine__process_bpf(machine, event, sample);
+}
+
+int perf_event__process_text_poke(const struct perf_tool *tool __maybe_unused,
+				  union perf_event *event,
+				  struct perf_sample *sample,
+				  struct machine *machine)
+{
+	return machine__process_text_poke(machine, event, sample);
+}
+
+size_t perf_event__fprintf_mmap(union perf_event *event, FILE *fp)
+{
+	return fprintf(fp, " %d/%d: [%#" PRI_lx64 "(%#" PRI_lx64 ") @ %#" PRI_lx64 "]: %c %s\n",
+		       event->mmap.pid, event->mmap.tid, event->mmap.start,
+		       event->mmap.len, event->mmap.pgoff,
+		       (event->header.misc & PERF_RECORD_MISC_MMAP_DATA) ? 'r' : 'x',
+		       event->mmap.filename);
+}
+
+size_t perf_event__fprintf_mmap2(union perf_event *event, FILE *fp)
+{
+	if (event->header.misc & PERF_RECORD_MISC_MMAP_BUILD_ID) {
+		char sbuild_id[SBUILD_ID_SIZE];
+		struct build_id bid;
+
+		build_id__init(&bid, event->mmap2.build_id,
+			       event->mmap2.build_id_size);
+		build_id__snprintf(&bid, sbuild_id, sizeof(sbuild_id));
+
+		return fprintf(fp, " %d/%d: [%#" PRI_lx64 "(%#" PRI_lx64 ") @ %#" PRI_lx64
+				   " <%s>]: %c%c%c%c %s\n",
+			       event->mmap2.pid, event->mmap2.tid, event->mmap2.start,
+			       event->mmap2.len, event->mmap2.pgoff, sbuild_id,
+			       (event->mmap2.prot & PROT_READ) ? 'r' : '-',
+			       (event->mmap2.prot & PROT_WRITE) ? 'w' : '-',
+			       (event->mmap2.prot & PROT_EXEC) ? 'x' : '-',
+			       (event->mmap2.flags & MAP_SHARED) ? 's' : 'p',
+			       event->mmap2.filename);
+	} else {
+		return fprintf(fp, " %d/%d: [%#" PRI_lx64 "(%#" PRI_lx64 ") @ %#" PRI_lx64
+				   " %02x:%02x %"PRI_lu64" %"PRI_lu64"]: %c%c%c%c %s\n",
+			       event->mmap2.pid, event->mmap2.tid, event->mmap2.start,
+			       event->mmap2.len, event->mmap2.pgoff, event->mmap2.maj,
+			       event->mmap2.min, event->mmap2.ino,
+			       event->mmap2.ino_generation,
+			       (event->mmap2.prot & PROT_READ) ? 'r' : '-',
+			       (event->mmap2.prot & PROT_WRITE) ? 'w' : '-',
+			       (event->mmap2.prot & PROT_EXEC) ? 'x' : '-',
+			       (event->mmap2.flags & MAP_SHARED) ? 's' : 'p',
+			       event->mmap2.filename);
+	}
+}
+
+size_t perf_event__fprintf_thread_map(union perf_event *event, FILE *fp)
+{
+	struct perf_thread_map *threads = thread_map__new_event(&event->thread_map);
+	size_t ret;
+
+	ret = fprintf(fp, " nr: ");
+
+	if (threads)
+		ret += thread_map__fprintf(threads, fp);
+	else
+		ret += fprintf(fp, "failed to get threads from event\n");
+
+	perf_thread_map__put(threads);
+	return ret;
+}
+
+size_t perf_event__fprintf_cpu_map(union perf_event *event, FILE *fp)
+{
+	struct perf_cpu_map *cpus = cpu_map__new_data(&event->cpu_map.data);
+	size_t ret;
+
+	ret = fprintf(fp, ": ");
+
+	if (cpus)
+		ret += cpu_map__fprintf(cpus, fp);
+	else
+		ret += fprintf(fp, "failed to get cpumap from event\n");
+
+	perf_cpu_map__put(cpus);
+	return ret;
+}
+
+int perf_event__process_mmap(const struct perf_tool *tool __maybe_unused,
+			     union perf_event *event,
+			     struct perf_sample *sample,
+			     struct machine *machine)
+{
+	return machine__process_mmap_event(machine, event, sample);
+}
+
+int perf_event__process_mmap2(const struct perf_tool *tool __maybe_unused,
+			     union perf_event *event,
+			     struct perf_sample *sample,
+			     struct machine *machine)
+{
+	return machine__process_mmap2_event(machine, event, sample);
+}
+
+size_t perf_event__fprintf_task(union perf_event *event, FILE *fp)
+{
+	return fprintf(fp, "(%d:%d):(%d:%d)\n",
+		       event->fork.pid, event->fork.tid,
+		       event->fork.ppid, event->fork.ptid);
+}
+
+int perf_event__process_fork(const struct perf_tool *tool __maybe_unused,
+			     union perf_event *event,
+			     struct perf_sample *sample,
+			     struct machine *machine)
+{
+	return machine__process_fork_event(machine, event, sample);
+}
+
+int perf_event__process_exit(const struct perf_tool *tool __maybe_unused,
+			     union perf_event *event,
+			     struct perf_sample *sample,
+			     struct machine *machine)
+{
+	return machine__process_exit_event(machine, event, sample);
+}
+
+int perf_event__exit_del_thread(const struct perf_tool *tool __maybe_unused,
+				union perf_event *event,
+				struct perf_sample *sample __maybe_unused,
+				struct machine *machine)
+{
+	struct thread *thread = machine__findnew_thread(machine,
+							event->fork.pid,
+							event->fork.tid);
+
+	dump_printf("(%d:%d):(%d:%d)\n", event->fork.pid, event->fork.tid,
+		    event->fork.ppid, event->fork.ptid);
+
+	if (thread) {
+		machine__remove_thread(machine, thread);
+		thread__put(thread);
+	}
+
+	return 0;
+}
+
+size_t perf_event__fprintf_aux(union perf_event *event, FILE *fp)
+{
+	return fprintf(fp, " offset: %#"PRI_lx64" size: %#"PRI_lx64" flags: %#"PRI_lx64" [%s%s%s%s]\n",
+		       event->aux.aux_offset, event->aux.aux_size,
+		       event->aux.flags,
+		       event->aux.flags & PERF_AUX_FLAG_TRUNCATED ? "T" : "",
+		       event->aux.flags & PERF_AUX_FLAG_OVERWRITE ? "O" : "",
+		       event->aux.flags & PERF_AUX_FLAG_PARTIAL   ? "P" : "",
+		       event->aux.flags & PERF_AUX_FLAG_COLLISION ? "C" : "");
+}
+
+size_t perf_event__fprintf_itrace_start(union perf_event *event, FILE *fp)
+{
+	return fprintf(fp, " pid: %u tid: %u\n",
+		       event->itrace_start.pid, event->itrace_start.tid);
+}
+
+size_t perf_event__fprintf_aux_output_hw_id(union perf_event *event, FILE *fp)
+{
+	return fprintf(fp, " hw_id: %#"PRI_lx64"\n",
+		       event->aux_output_hw_id.hw_id);
+}
+
+size_t perf_event__fprintf_switch(union perf_event *event, FILE *fp)
+{
+	bool out = event->header.misc & PERF_RECORD_MISC_SWITCH_OUT;
+	const char *in_out = !out ? "IN         " :
+		!(event->header.misc & PERF_RECORD_MISC_SWITCH_OUT_PREEMPT) ?
+				    "OUT        " : "OUT preempt";
+
+	if (event->header.type == PERF_RECORD_SWITCH)
+		return fprintf(fp, " %s\n", in_out);
+
+	return fprintf(fp, " %s  %s pid/tid: %5d/%-5d\n",
+		       in_out, out ? "next" : "prev",
+		       event->context_switch.next_prev_pid,
+		       event->context_switch.next_prev_tid);
+}
+
+static size_t perf_event__fprintf_lost(union perf_event *event, FILE *fp)
+{
+	return fprintf(fp, " lost %" PRI_lu64 "\n", event->lost.lost);
+}
+
+size_t perf_event__fprintf_ksymbol(union perf_event *event, FILE *fp)
+{
+	return fprintf(fp, " addr %" PRI_lx64 " len %u type %u flags 0x%x name %s\n",
+		       event->ksymbol.addr, event->ksymbol.len,
+		       event->ksymbol.ksym_type,
+		       event->ksymbol.flags, event->ksymbol.name);
+}
+
+size_t perf_event__fprintf_bpf(union perf_event *event, FILE *fp)
+{
+	return fprintf(fp, " type %u, flags %u, id %u\n",
+		       event->bpf.type, event->bpf.flags, event->bpf.id);
+}
+
+size_t perf_event__fprintf_bpf_metadata(union perf_event *event, FILE *fp)
+{
+	struct perf_record_bpf_metadata *metadata = &event->bpf_metadata;
+	size_t ret;
+
+	ret = fprintf(fp, " prog %s\n", metadata->prog_name);
+	for (__u32 i = 0; i < metadata->nr_entries; i++) {
+		ret += fprintf(fp, "  entry %d: %20s = %s\n", i,
+			       metadata->entries[i].key,
+			       metadata->entries[i].value);
+	}
+	return ret;
+}
+
+static int text_poke_printer(enum binary_printer_ops op, unsigned int val,
+			     void *extra, FILE *fp)
+{
+	bool old = *(bool *)extra;
+
+	switch ((int)op) {
+	case BINARY_PRINT_LINE_BEGIN:
+		return fprintf(fp, "            %s bytes:", old ? "Old" : "New");
+	case BINARY_PRINT_NUM_DATA:
+		return fprintf(fp, " %02x", val);
+	case BINARY_PRINT_LINE_END:
+		return fprintf(fp, "\n");
+	default:
+		return 0;
+	}
+}
+
+size_t perf_event__fprintf_text_poke(union perf_event *event, struct machine *machine, FILE *fp)
+{
+	struct perf_record_text_poke_event *tp = &event->text_poke;
+	size_t ret;
+	bool old;
+
+	ret = fprintf(fp, " %" PRI_lx64 " ", tp->addr);
+	if (machine) {
+		struct addr_location al;
+
+		addr_location__init(&al);
+		al.map = maps__find(machine__kernel_maps(machine), tp->addr);
+		if (al.map && map__load(al.map) >= 0) {
+			al.addr = map__map_ip(al.map, tp->addr);
+			al.sym = map__find_symbol(al.map, al.addr);
+			if (al.sym)
+				ret += symbol__fprintf_symname_offs(al.sym, &al, fp);
+		}
+		addr_location__exit(&al);
+	}
+	ret += fprintf(fp, " old len %u new len %u\n", tp->old_len, tp->new_len);
+	old = true;
+	ret += binary__fprintf(tp->bytes, tp->old_len, 16, text_poke_printer,
+			       &old, fp);
+	old = false;
+	ret += binary__fprintf(tp->bytes + tp->old_len, tp->new_len, 16,
+			       text_poke_printer, &old, fp);
+	return ret;
+}
+
+size_t perf_event__fprintf_schedstat_cpu(union perf_event *event, FILE *fp)
+{
+	struct perf_record_schedstat_cpu *cs = &event->schedstat_cpu;
+	size_t size = fprintf(fp, "\ncpu%u ", cs->cpu);
+	__u16 version = cs->version;
+
+#define CPU_FIELD(_type, _name, _desc, _format, _is_pct, _pct_of, _ver)		\
+	size += fprintf(fp, "%" PRIu64 " ", (uint64_t)cs->_ver._name)
+
+	if (version == 15) {
+#include <perf/schedstat-v15.h>
+		return size;
+	} else if (version == 16) {
+#include <perf/schedstat-v16.h>
+		return size;
+	} else if (version == 17) {
+#include <perf/schedstat-v17.h>
+		return size;
+	}
+#undef CPU_FIELD
+
+	return fprintf(fp, "Unsupported /proc/schedstat version %d.\n",
+		       event->schedstat_cpu.version);
+}
+
+size_t perf_event__fprintf_schedstat_domain(union perf_event *event, FILE *fp)
+{
+	struct perf_record_schedstat_domain *ds = &event->schedstat_domain;
+	__u16 version = ds->version;
+	size_t size = fprintf(fp, "\ndomain%u ", ds->domain);
+
+#define DOMAIN_FIELD(_type, _name, _desc, _format, _is_jiffies, _ver)		\
+	size += fprintf(fp, "%" PRIu64 " ", (uint64_t)ds->_ver._name)
+
+	if (version == 15) {
+#include <perf/schedstat-v15.h>
+		return size;
+	} else if (version == 16) {
+#include <perf/schedstat-v16.h>
+		return size;
+	} else if (version == 17) {
+#include <perf/schedstat-v17.h>
+		return size;
+	}
+#undef DOMAIN_FIELD
+
+	return fprintf(fp, "Unsupported /proc/schedstat version %d.\n",
+		       event->schedstat_domain.version);
+}
+
+size_t perf_event__fprintf(union perf_event *event, struct machine *machine, FILE *fp)
+{
+	size_t ret = fprintf(fp, "PERF_RECORD_%s",
+			     perf_event__name(event->header.type));
+
+	switch (event->header.type) {
+	case PERF_RECORD_COMM:
+		ret += perf_event__fprintf_comm(event, fp);
+		break;
+	case PERF_RECORD_FORK:
+	case PERF_RECORD_EXIT:
+		ret += perf_event__fprintf_task(event, fp);
+		break;
+	case PERF_RECORD_MMAP:
+		ret += perf_event__fprintf_mmap(event, fp);
+		break;
+	case PERF_RECORD_NAMESPACES:
+		ret += perf_event__fprintf_namespaces(event, fp);
+		break;
+	case PERF_RECORD_CGROUP:
+		ret += perf_event__fprintf_cgroup(event, fp);
+		break;
+	case PERF_RECORD_MMAP2:
+		ret += perf_event__fprintf_mmap2(event, fp);
+		break;
+	case PERF_RECORD_AUX:
+		ret += perf_event__fprintf_aux(event, fp);
+		break;
+	case PERF_RECORD_ITRACE_START:
+		ret += perf_event__fprintf_itrace_start(event, fp);
+		break;
+	case PERF_RECORD_SWITCH:
+	case PERF_RECORD_SWITCH_CPU_WIDE:
+		ret += perf_event__fprintf_switch(event, fp);
+		break;
+	case PERF_RECORD_LOST:
+		ret += perf_event__fprintf_lost(event, fp);
+		break;
+	case PERF_RECORD_KSYMBOL:
+		ret += perf_event__fprintf_ksymbol(event, fp);
+		break;
+	case PERF_RECORD_BPF_EVENT:
+		ret += perf_event__fprintf_bpf(event, fp);
+		break;
+	case PERF_RECORD_TEXT_POKE:
+		ret += perf_event__fprintf_text_poke(event, machine, fp);
+		break;
+	case PERF_RECORD_AUX_OUTPUT_HW_ID:
+		ret += perf_event__fprintf_aux_output_hw_id(event, fp);
+		break;
+	case PERF_RECORD_BPF_METADATA:
+		ret += perf_event__fprintf_bpf_metadata(event, fp);
+		break;
+	default:
+		ret += fprintf(fp, "\n");
+	}
+
+	return ret;
+}
+
+int perf_event__process(const struct perf_tool *tool __maybe_unused,
+			union perf_event *event,
+			struct perf_sample *sample,
+			struct machine *machine)
+{
+	return machine__process_event(machine, event, sample);
+}
+
+struct map *thread__find_map(struct thread *thread, u8 cpumode, u64 addr,
+			     struct addr_location *al)
+{
+	struct maps *maps = thread__maps(thread);
+	struct machine *machine = maps__machine(maps);
+	bool load_map = false;
+
+	map__zput(al->map);
+	thread__zput(al->thread);
+	al->thread = thread__get(thread);
+
+	al->addr = addr;
+	al->cpumode = cpumode;
+	al->filtered = 0;
+
+	if (machine == NULL)
+		return NULL;
+
+	if (cpumode == PERF_RECORD_MISC_KERNEL && perf_host) {
+		al->level = 'k';
+		maps = machine__kernel_maps(machine);
+		load_map = !symbol_conf.lazy_load_kernel_maps;
+	} else if (cpumode == PERF_RECORD_MISC_USER && perf_host) {
+		al->level = '.';
+	} else if (cpumode == PERF_RECORD_MISC_GUEST_KERNEL && perf_guest) {
+		al->level = 'g';
+		maps = machine__kernel_maps(machine);
+		load_map = !symbol_conf.lazy_load_kernel_maps;
+	} else if (cpumode == PERF_RECORD_MISC_GUEST_USER && perf_guest) {
+		al->level = 'u';
+	} else {
+		al->level = 'H';
+
+		if ((cpumode == PERF_RECORD_MISC_GUEST_USER ||
+			cpumode == PERF_RECORD_MISC_GUEST_KERNEL) &&
+			!perf_guest)
+			al->filtered |= (1 << HIST_FILTER__GUEST);
+		if ((cpumode == PERF_RECORD_MISC_USER ||
+			cpumode == PERF_RECORD_MISC_KERNEL) &&
+			!perf_host)
+			al->filtered |= (1 << HIST_FILTER__HOST);
+
+		return NULL;
+	}
+	al->map = maps__find(maps, al->addr);
+	if (al->map != NULL) {
+		/*
+		 * Kernel maps might be changed when loading symbols so loading
+		 * must be done prior to using kernel maps.
+		 */
+		if (load_map)
+			map__load(al->map);
+		al->addr = map__map_ip(al->map, al->addr);
+	}
+
+	return al->map;
+}
+
+/*
+ * For branch stacks or branch samples, the sample cpumode might not be correct
+ * because it applies only to the sample 'ip' and not necessary to 'addr' or
+ * branch stack addresses. If possible, use a fallback to deal with those cases.
+ */
+struct map *thread__find_map_fb(struct thread *thread, u8 cpumode, u64 addr,
+				struct addr_location *al)
+{
+	struct map *map = thread__find_map(thread, cpumode, addr, al);
+	struct machine *machine = maps__machine(thread__maps(thread));
+	u8 addr_cpumode = machine__addr_cpumode(machine, cpumode, addr);
+
+	if (map || addr_cpumode == cpumode)
+		return map;
+
+	return thread__find_map(thread, addr_cpumode, addr, al);
+}
+
+struct symbol *thread__find_symbol(struct thread *thread, u8 cpumode,
+				   u64 addr, struct addr_location *al)
+{
+	al->sym = NULL;
+	if (thread__find_map(thread, cpumode, addr, al))
+		al->sym = map__find_symbol(al->map, al->addr);
+	return al->sym;
+}
+
+struct symbol *thread__find_symbol_fb(struct thread *thread, u8 cpumode,
+				      u64 addr, struct addr_location *al)
+{
+	al->sym = NULL;
+	if (thread__find_map_fb(thread, cpumode, addr, al))
+		al->sym = map__find_symbol(al->map, al->addr);
+	return al->sym;
+}
+
+static bool check_address_range(struct intlist *addr_list, int addr_range,
+				unsigned long addr)
+{
+	struct int_node *pos;
+
+	intlist__for_each_entry(pos, addr_list) {
+		if (addr >= pos->i && addr < pos->i + addr_range)
+			return true;
+	}
+
+	return false;
+}
+
+/*
+ * Callers need to drop the reference to al->thread, obtained in
+ * machine__findnew_thread()
+ */
+int machine__resolve(struct machine *machine, struct addr_location *al,
+		     struct perf_sample *sample)
+{
+	struct thread *thread;
+	struct dso *dso;
+
+	if (symbol_conf.guest_code && !machine__is_host(machine))
+		thread = machine__findnew_guest_code(machine, sample->pid);
+	else
+		thread = machine__findnew_thread(machine, sample->pid, sample->tid);
+	if (thread == NULL)
+		return -1;
+
+	dump_printf(" ... thread: %s:%d\n", thread__comm_str(thread), thread__tid(thread));
+	thread__find_map(thread, sample->cpumode, sample->ip, al);
+	dso = al->map ? map__dso(al->map) : NULL;
+	dump_printf(" ...... dso: %s\n",
+		dso
+		? dso__long_name(dso)
+		: (al->level == 'H' ? "[hypervisor]" : "<not found>"));
+
+	if (thread__is_filtered(thread))
+		al->filtered |= (1 << HIST_FILTER__THREAD);
+
+	thread__put(thread);
+	thread = NULL;
+
+	al->sym = NULL;
+	al->cpu = sample->cpu;
+	al->socket = -1;
+	al->srcline = NULL;
+
+	if (al->cpu >= 0) {
+		struct perf_env *env = machine->env;
+
+		/*
+		 * Bounds-check al->cpu (s32) before casting to struct perf_cpu
+		 * (int16_t): without this, e.g. 65536 truncates to 0 and silently
+		 * returns CPU 0's topology.  Can go once perf_cpu.cpu is widened.
+		 */
+		if (env && al->cpu < env->nr_cpus_avail) {
+			struct cpu_topology_map *topo;
+
+			topo = perf_env__get_cpu_topology(env, (struct perf_cpu){ al->cpu });
+			if (topo)
+				al->socket = topo->socket_id;
+		}
+	}
+
+	/* Account for possible out-of-order switch events. */
+	al->parallelism = max(1, min(machine->parallelism, machine__nr_cpus_avail(machine)));
+	if (test_bit(al->parallelism, symbol_conf.parallelism_filter))
+		al->filtered |= (1 << HIST_FILTER__PARALLELISM);
+	/*
+	 * Multiply it by some const to avoid precision loss or dealing
+	 * with floats. The multiplier does not matter otherwise since
+	 * we only print it as percents.
+	 */
+	al->latency = sample->period * 1000 / al->parallelism;
+
+	if (al->map) {
+		if (symbol_conf.dso_list &&
+		    (!dso || !(strlist__has_entry(symbol_conf.dso_list,
+						  dso__short_name(dso)) ||
+			       (dso__short_name(dso) != dso__long_name(dso) &&
+				strlist__has_entry(symbol_conf.dso_list,
+						   dso__long_name(dso)))))) {
+			al->filtered |= (1 << HIST_FILTER__DSO);
+		}
+
+		al->sym = map__find_symbol(al->map, al->addr);
+	} else if (symbol_conf.dso_list) {
+		al->filtered |= (1 << HIST_FILTER__DSO);
+	}
+
+	if (symbol_conf.sym_list) {
+		int ret = 0;
+		char al_addr_str[32];
+		size_t sz = sizeof(al_addr_str);
+
+		if (al->sym) {
+			ret = strlist__has_entry(symbol_conf.sym_list,
+						al->sym->name);
+		}
+		if (!ret && al->sym) {
+			snprintf(al_addr_str, sz, "0x%"PRIx64,
+				 map__unmap_ip(al->map, al->sym->start));
+			ret = strlist__has_entry(symbol_conf.sym_list,
+						al_addr_str);
+		}
+		if (!ret && symbol_conf.addr_list && al->map) {
+			unsigned long addr = map__unmap_ip(al->map, al->addr);
+
+			ret = intlist__has_entry(symbol_conf.addr_list, addr);
+			if (!ret && symbol_conf.addr_range) {
+				ret = check_address_range(symbol_conf.addr_list,
+							  symbol_conf.addr_range,
+							  addr);
+			}
+		}
+
+		if (!ret)
+			al->filtered |= (1 << HIST_FILTER__SYMBOL);
+	}
+
+	return 0;
+}
+
+bool is_bts_event(struct perf_event_attr *attr)
+{
+	return attr->type == PERF_TYPE_HARDWARE &&
+	       (attr->config & PERF_COUNT_HW_BRANCH_INSTRUCTIONS) &&
+	       attr->sample_period == 1;
+}
+
+bool sample_addr_correlates_sym(struct perf_event_attr *attr)
+{
+	if (attr->type == PERF_TYPE_SOFTWARE &&
+	    (attr->config == PERF_COUNT_SW_PAGE_FAULTS ||
+	     attr->config == PERF_COUNT_SW_PAGE_FAULTS_MIN ||
+	     attr->config == PERF_COUNT_SW_PAGE_FAULTS_MAJ))
+		return true;
+
+	if (is_bts_event(attr))
+		return true;
+
+	return false;
+}
+
+void thread__resolve(struct thread *thread, struct addr_location *al,
+		     struct perf_sample *sample)
+{
+	thread__find_map_fb(thread, sample->cpumode, sample->addr, al);
+
+	al->cpu = sample->cpu;
+	al->sym = NULL;
+
+	if (al->map)
+		al->sym = map__find_symbol(al->map, al->addr);
+}