session.c

#define _FILE_OFFSET_BITS 64

#include <linux/kernel.h>

#include <byteswap.h>
#include <unistd.h>
#include <sys/types.h>
#include <sys/mman.h>

#include "evlist.h"
#include "evsel.h"
#include "session.h"
#include "tool.h"
#include "sort.h"
#include "util.h"
#include "cpumap.h"
#include "event-parse.h"
#include "perf_regs.h"
#include "unwind.h"
#include "vdso.h"

static int perf_session__open(struct perf_session *self, bool force)
{
	struct stat input_stat;

	if (!strcmp(self->filename, "-")) {
		self->fd_pipe = true;
		self->fd = STDIN_FILENO;

		if (perf_session__read_header(self, self->fd) < 0)
			pr_err("incompatible file format (rerun with -v to learn more)");

		return 0;
	}

	self->fd = open(self->filename, O_RDONLY);
	if (self->fd < 0) {
		int err = errno;

		pr_err("failed to open %s: %s", self->filename, strerror(err));
		if (err == ENOENT && !strcmp(self->filename, "perf.data"))
			pr_err("  (try 'perf record' first)");
		pr_err("\n");
		return -errno;
	}

	if (fstat(self->fd, &input_stat) < 0)
		goto out_close;

	if (!force && input_stat.st_uid && (input_stat.st_uid != geteuid())) {
		pr_err("file %s not owned by current user or root\n",
		       self->filename);
		goto out_close;
	}

	if (!input_stat.st_size) {
		pr_info("zero-sized file (%s), nothing to do!\n",
			self->filename);
		goto out_close;
	}

	if (perf_session__read_header(self, self->fd) < 0) {
		pr_err("incompatible file format (rerun with -v to learn more)");
		goto out_close;
	}

	if (!perf_evlist__valid_sample_type(self->evlist)) {
		pr_err("non matching sample_type");
		goto out_close;
	}

	if (!perf_evlist__valid_sample_id_all(self->evlist)) {
		pr_err("non matching sample_id_all");
		goto out_close;
	}

	self->size = input_stat.st_size;
	return 0;

out_close:
	close(self->fd);
	self->fd = -1;
	return -1;
}

void perf_session__set_id_hdr_size(struct perf_session *session)
{
	u16 id_hdr_size = perf_evlist__id_hdr_size(session->evlist);

	session->host_machine.id_hdr_size = id_hdr_size;
	machines__set_id_hdr_size(&session->machines, id_hdr_size);
}

int perf_session__create_kernel_maps(struct perf_session *self)
{
	int ret = machine__create_kernel_maps(&self->host_machine);

	if (ret >= 0)
		ret = machines__create_guest_kernel_maps(&self->machines);
	return ret;
}

static void perf_session__destroy_kernel_maps(struct perf_session *self)
{
	machine__destroy_kernel_maps(&self->host_machine);
	machines__destroy_guest_kernel_maps(&self->machines);
}

struct perf_session *perf_session__new(const char *filename, int mode,
				       bool force, bool repipe,
				       struct perf_tool *tool)
{
	struct perf_session *self;
	struct stat st;
	size_t len;

	if (!filename || !strlen(filename)) {
		if (!fstat(STDIN_FILENO, &st) && S_ISFIFO(st.st_mode))
			filename = "-";
		else
			filename = "perf.data";
	}

	len = strlen(filename);
	self = zalloc(sizeof(*self) + len);

	if (self == NULL)
		goto out;

	memcpy(self->filename, filename, len);
	/*
	 * On 64bit we can mmap the data file in one go. No need for tiny mmap
	 * slices. On 32bit we use 32MB.
	 */
#if BITS_PER_LONG == 64
	self->mmap_window = ULLONG_MAX;
#else
	self->mmap_window = 32 * 1024 * 1024ULL;
#endif
	self->machines = RB_ROOT;
	self->repipe = repipe;
	INIT_LIST_HEAD(&self->ordered_samples.samples);
	INIT_LIST_HEAD(&self->ordered_samples.sample_cache);
	INIT_LIST_HEAD(&self->ordered_samples.to_free);
	machine__init(&self->host_machine, "", HOST_KERNEL_ID);
	hists__init(&self->hists);

	if (mode == O_RDONLY) {
		if (perf_session__open(self, force) < 0)
			goto out_delete;
		perf_session__set_id_hdr_size(self);
	} else if (mode == O_WRONLY) {
		/*
		 * In O_RDONLY mode this will be performed when reading the
		 * kernel MMAP event, in perf_event__process_mmap().
		 */
		if (perf_session__create_kernel_maps(self) < 0)
			goto out_delete;
	}

	if (tool && tool->ordering_requires_timestamps &&
	    tool->ordered_samples && !perf_evlist__sample_id_all(self->evlist)) {
		dump_printf("WARNING: No sample_id_all support, falling back to unordered processing\n");
		tool->ordered_samples = false;
	}

out:
	return self;
out_delete:
	perf_session__delete(self);
	return NULL;
}

static void machine__delete_dead_threads(struct machine *machine)
{
	struct thread *n, *t;

	list_for_each_entry_safe(t, n, &machine->dead_threads, node) {
		list_del(&t->node);
		thread__delete(t);
	}
}

static void perf_session__delete_dead_threads(struct perf_session *session)
{
	machine__delete_dead_threads(&session->host_machine);
}

static void machine__delete_threads(struct machine *self)
{
	struct rb_node *nd = rb_first(&self->threads);

	while (nd) {
		struct thread *t = rb_entry(nd, struct thread, rb_node);

		rb_erase(&t->rb_node, &self->threads);
		nd = rb_next(nd);
		thread__delete(t);
	}
}

static void perf_session__delete_threads(struct perf_session *session)
{
	machine__delete_threads(&session->host_machine);
}

void perf_session__delete(struct perf_session *self)
{
	perf_session__destroy_kernel_maps(self);
	perf_session__delete_dead_threads(self);
	perf_session__delete_threads(self);
	machine__exit(&self->host_machine);
	close(self->fd);
	free(self);
	vdso__exit();
}

void machine__remove_thread(struct machine *self, struct thread *th)
{
	self->last_match = NULL;
	rb_erase(&th->rb_node, &self->threads);
	/*
	 * We may have references to this thread, for instance in some hist_entry
	 * instances, so just move them to a separate list.
	 */
	list_add_tail(&th->node, &self->dead_threads);
}

static bool symbol__match_parent_regex(struct symbol *sym)
{
	if (sym->name && !regexec(&parent_regex, sym->name, 0, NULL, 0))
		return 1;

	return 0;
}

static const u8 cpumodes[] = {
	PERF_RECORD_MISC_USER,
	PERF_RECORD_MISC_KERNEL,
	PERF_RECORD_MISC_GUEST_USER,
	PERF_RECORD_MISC_GUEST_KERNEL
};
#define NCPUMODES (sizeof(cpumodes)/sizeof(u8))

static void ip__resolve_ams(struct machine *self, struct thread *thread,
			    struct addr_map_symbol *ams,
			    u64 ip)
{
	struct addr_location al;
	size_t i;
	u8 m;

	memset(&al, 0, sizeof(al));

	for (i = 0; i < NCPUMODES; i++) {
		m = cpumodes[i];
		/*
		 * We cannot use the header.misc hint to determine whether a
		 * branch stack address is user, kernel, guest, hypervisor.
		 * Branches may straddle the kernel/user/hypervisor boundaries.
		 * Thus, we have to try consecutively until we find a match
		 * or else, the symbol is unknown
		 */
		thread__find_addr_location(thread, self, m, MAP__FUNCTION,
				ip, &al, NULL);
		if (al.sym)
			goto found;
	}
found:
	ams->addr = ip;
	ams->al_addr = al.addr;
	ams->sym = al.sym;
	ams->map = al.map;
}

struct branch_info *machine__resolve_bstack(struct machine *self,
					    struct thread *thr,
					    struct branch_stack *bs)
{
	struct branch_info *bi;
	unsigned int i;

	bi = calloc(bs->nr, sizeof(struct branch_info));
	if (!bi)
		return NULL;

	for (i = 0; i < bs->nr; i++) {
		ip__resolve_ams(self, thr, &bi[i].to, bs->entries[i].to);
		ip__resolve_ams(self, thr, &bi[i].from, bs->entries[i].from);
		bi[i].flags = bs->entries[i].flags;
	}
	return bi;
}

static int machine__resolve_callchain_sample(struct machine *machine,
					     struct thread *thread,
					     struct ip_callchain *chain,
					     struct symbol **parent)

{
	u8 cpumode = PERF_RECORD_MISC_USER;
	unsigned int i;
	int err;

	callchain_cursor_reset(&callchain_cursor);

	if (chain->nr > PERF_MAX_STACK_DEPTH) {
		pr_warning("corrupted callchain. skipping...\n");
		return 0;
	}

	for (i = 0; i < chain->nr; i++) {
		u64 ip;
		struct addr_location al;

		if (callchain_param.order == ORDER_CALLEE)
			ip = chain->ips[i];
		else
			ip = chain->ips[chain->nr - i - 1];

		if (ip >= PERF_CONTEXT_MAX) {
			switch (ip) {
			case PERF_CONTEXT_HV:
				cpumode = PERF_RECORD_MISC_HYPERVISOR;
				break;
			case PERF_CONTEXT_KERNEL:
				cpumode = PERF_RECORD_MISC_KERNEL;
				break;
			case PERF_CONTEXT_USER:
				cpumode = PERF_RECORD_MISC_USER;
				break;
			default:
				pr_debug("invalid callchain context: "
					 "%"PRId64"\n", (s64) ip);
				/*
				 * It seems the callchain is corrupted.
				 * Discard all.
				 */
				callchain_cursor_reset(&callchain_cursor);
				return 0;
			}
			continue;
		}

		al.filtered = false;
		thread__find_addr_location(thread, machine, cpumode,
					   MAP__FUNCTION, ip, &al, NULL);
		if (al.sym != NULL) {
			if (sort__has_parent && !*parent &&
			    symbol__match_parent_regex(al.sym))
				*parent = al.sym;
			if (!symbol_conf.use_callchain)
				break;
		}

		err = callchain_cursor_append(&callchain_cursor,
					      ip, al.map, al.sym);
		if (err)
			return err;
	}

	return 0;
}

static int unwind_entry(struct unwind_entry *entry, void *arg)
{
	struct callchain_cursor *cursor = arg;
	return callchain_cursor_append(cursor, entry->ip,
				       entry->map, entry->sym);
}

int machine__resolve_callchain(struct machine *machine,
			       struct perf_evsel *evsel,
			       struct thread *thread,
			       struct perf_sample *sample,
			       struct symbol **parent)

{
	int ret;

	callchain_cursor_reset(&callchain_cursor);

	ret = machine__resolve_callchain_sample(machine, thread,
						sample->callchain, parent);
	if (ret)
		return ret;

	/* Can we do dwarf post unwind? */
	if (!((evsel->attr.sample_type & PERF_SAMPLE_REGS_USER) &&
	      (evsel->attr.sample_type & PERF_SAMPLE_STACK_USER)))
		return 0;

	/* Bail out if nothing was captured. */
	if ((!sample->user_regs.regs) ||
	    (!sample->user_stack.size))
		return 0;

	return unwind__get_entries(unwind_entry, &callchain_cursor, machine,
				   thread, evsel->attr.sample_regs_user,
				   sample);

}

static int process_event_synth_tracing_data_stub(union perf_event *event
						 __maybe_unused,
						 struct perf_session *session
						__maybe_unused)
{
	dump_printf(": unhandled!\n");
	return 0;
}

static int process_event_synth_attr_stub(union perf_event *event __maybe_unused,
					 struct perf_evlist **pevlist
					 __maybe_unused)
{
	dump_printf(": unhandled!\n");
	return 0;
}

static int process_event_sample_stub(struct perf_tool *tool __maybe_unused,
				     union perf_event *event __maybe_unused,
				     struct perf_sample *sample __maybe_unused,
				     struct perf_evsel *evsel __maybe_unused,
				     struct machine *machine __maybe_unused)
{
	dump_printf(": unhandled!\n");
	return 0;
}

static int process_event_stub(struct perf_tool *tool __maybe_unused,
			      union perf_event *event __maybe_unused,
			      struct perf_sample *sample __maybe_unused,
			      struct machine *machine __maybe_unused)
{
	dump_printf(": unhandled!\n");
	return 0;
}

static int process_finished_round_stub(struct perf_tool *tool __maybe_unused,
				       union perf_event *event __maybe_unused,
				       struct perf_session *perf_session
				       __maybe_unused)
{
	dump_printf(": unhandled!\n");
	return 0;
}

static int process_event_type_stub(struct perf_tool *tool __maybe_unused,
				   union perf_event *event __maybe_unused)
{
	dump_printf(": unhandled!\n");
	return 0;
}

static int process_finished_round(struct perf_tool *tool,
				  union perf_event *event,
				  struct perf_session *session);

static void perf_tool__fill_defaults(struct perf_tool *tool)
{
	if (tool->sample == NULL)
		tool->sample = process_event_sample_stub;
	if (tool->mmap == NULL)
		tool->mmap = process_event_stub;
	if (tool->comm == NULL)
		tool->comm = process_event_stub;
	if (tool->fork == NULL)
		tool->fork = process_event_stub;
	if (tool->exit == NULL)
		tool->exit = process_event_stub;
	if (tool->lost == NULL)
		tool->lost = perf_event__process_lost;
	if (tool->read == NULL)
		tool->read = process_event_sample_stub;
	if (tool->throttle == NULL)
		tool->throttle = process_event_stub;
	if (tool->unthrottle == NULL)
		tool->unthrottle = process_event_stub;
	if (tool->attr == NULL)
		tool->attr = process_event_synth_attr_stub;
	if (tool->event_type == NULL)
		tool->event_type = process_event_type_stub;
	if (tool->tracing_data == NULL)
		tool->tracing_data = process_event_synth_tracing_data_stub;
	if (tool->build_id == NULL)
		tool->build_id = process_finished_round_stub;
	if (tool->finished_round == NULL) {
		if (tool->ordered_samples)
			tool->finished_round = process_finished_round;
		else
			tool->finished_round = process_finished_round_stub;
	}
}
 
void mem_bswap_32(void *src, int byte_size)
{
	u32 *m = src;
	while (byte_size > 0) {
		*m = bswap_32(*m);
		byte_size -= sizeof(u32);
		++m;
	}
}

void mem_bswap_64(void *src, int byte_size)
{
	u64 *m = src;

	while (byte_size > 0) {
		*m = bswap_64(*m);
		byte_size -= sizeof(u64);
		++m;
	}
}

static void swap_sample_id_all(union perf_event *event, void *data)
{
	void *end = (void *) event + event->header.size;
	int size = end - data;

	BUG_ON(size % sizeof(u64));
	mem_bswap_64(data, size);
}

static void perf_event__all64_swap(union perf_event *event,
				   bool sample_id_all __maybe_unused)
{
	struct perf_event_header *hdr = &event->header;
	mem_bswap_64(hdr + 1, event->header.size - sizeof(*hdr));
}

static void perf_event__comm_swap(union perf_event *event, bool sample_id_all)
{
	event->comm.pid = bswap_32(event->comm.pid);
	event->comm.tid = bswap_32(event->comm.tid);

	if (sample_id_all) {
		void *data = &event->comm.comm;

		data += PERF_ALIGN(strlen(data) + 1, sizeof(u64));
		swap_sample_id_all(event, data);
	}
}

static void perf_event__mmap_swap(union perf_event *event,
				  bool sample_id_all)
{
	event->mmap.pid	  = bswap_32(event->mmap.pid);
	event->mmap.tid	  = bswap_32(event->mmap.tid);
	event->mmap.start = bswap_64(event->mmap.start);
	event->mmap.len	  = bswap_64(event->mmap.len);
	event->mmap.pgoff = bswap_64(event->mmap.pgoff);

	if (sample_id_all) {
		void *data = &event->mmap.filename;

		data += PERF_ALIGN(strlen(data) + 1, sizeof(u64));
		swap_sample_id_all(event, data);
	}
}

static void perf_event__task_swap(union perf_event *event, bool sample_id_all)
{
	event->fork.pid	 = bswap_32(event->fork.pid);
	event->fork.tid	 = bswap_32(event->fork.tid);
	event->fork.ppid = bswap_32(event->fork.ppid);
	event->fork.ptid = bswap_32(event->fork.ptid);
	event->fork.time = bswap_64(event->fork.time);

	if (sample_id_all)
		swap_sample_id_all(event, &event->fork + 1);
}

static void perf_event__read_swap(union perf_event *event, bool sample_id_all)
{
	event->read.pid		 = bswap_32(event->read.pid);
	event->read.tid		 = bswap_32(event->read.tid);
	event->read.value	 = bswap_64(event->read.value);
	event->read.time_enabled = bswap_64(event->read.time_enabled);
	event->read.time_running = bswap_64(event->read.time_running);
	event->read.id		 = bswap_64(event->read.id);

	if (sample_id_all)
		swap_sample_id_all(event, &event->read + 1);
}

static u8 revbyte(u8 b)
{
	int rev = (b >> 4) | ((b & 0xf) << 4);
	rev = ((rev & 0xcc) >> 2) | ((rev & 0x33) << 2);
	rev = ((rev & 0xaa) >> 1) | ((rev & 0x55) << 1);
	return (u8) rev;
}

/*
 * XXX this is hack in attempt to carry flags bitfield
 * throught endian village. ABI says:
 *
 * Bit-fields are allocated from right to left (least to most significant)
 * on little-endian implementations and from left to right (most to least
 * significant) on big-endian implementations.
 *
 * The above seems to be byte specific, so we need to reverse each
 * byte of the bitfield. 'Internet' also says this might be implementation
 * specific and we probably need proper fix and carry perf_event_attr
 * bitfield flags in separate data file FEAT_ section. Thought this seems
 * to work for now.
 */
static void swap_bitfield(u8 *p, unsigned len)
{
	unsigned i;

	for (i = 0; i < len; i++) {
		*p = revbyte(*p);
		p++;
	}
}

/* exported for swapping attributes in file header */
void perf_event__attr_swap(struct perf_event_attr *attr)
{
	attr->type		= bswap_32(attr->type);
	attr->size		= bswap_32(attr->size);
	attr->config		= bswap_64(attr->config);
	attr->sample_period	= bswap_64(attr->sample_period);
	attr->sample_type	= bswap_64(attr->sample_type);
	attr->read_format	= bswap_64(attr->read_format);
	attr->wakeup_events	= bswap_32(attr->wakeup_events);
	attr->bp_type		= bswap_32(attr->bp_type);
	attr->bp_addr		= bswap_64(attr->bp_addr);
	attr->bp_len		= bswap_64(attr->bp_len);

	swap_bitfield((u8 *) (&attr->read_format + 1), sizeof(u64));
}

static void perf_event__hdr_attr_swap(union perf_event *event,
				      bool sample_id_all __maybe_unused)
{
	size_t size;

	perf_event__attr_swap(&event->attr.attr);

	size = event->header.size;
	size -= (void *)&event->attr.id - (void *)event;
	mem_bswap_64(event->attr.id, size);
}

static void perf_event__event_type_swap(union perf_event *event,
					bool sample_id_all __maybe_unused)
{
	event->event_type.event_type.event_id =
		bswap_64(event->event_type.event_type.event_id);
}

static void perf_event__tracing_data_swap(union perf_event *event,
					  bool sample_id_all __maybe_unused)
{
	event->tracing_data.size = bswap_32(event->tracing_data.size);
}

typedef void (*perf_event__swap_op)(union perf_event *event,
				    bool sample_id_all);

static perf_event__swap_op perf_event__swap_ops[] = {
	[PERF_RECORD_MMAP]		  = perf_event__mmap_swap,
	[PERF_RECORD_COMM]		  = perf_event__comm_swap,
	[PERF_RECORD_FORK]		  = perf_event__task_swap,
	[PERF_RECORD_EXIT]		  = perf_event__task_swap,
	[PERF_RECORD_LOST]		  = perf_event__all64_swap,
	[PERF_RECORD_READ]		  = perf_event__read_swap,
	[PERF_RECORD_SAMPLE]		  = perf_event__all64_swap,
	[PERF_RECORD_HEADER_ATTR]	  = perf_event__hdr_attr_swap,
	[PERF_RECORD_HEADER_EVENT_TYPE]	  = perf_event__event_type_swap,
	[PERF_RECORD_HEADER_TRACING_DATA] = perf_event__tracing_data_swap,
	[PERF_RECORD_HEADER_BUILD_ID]	  = NULL,
	[PERF_RECORD_HEADER_MAX]	  = NULL,
};

struct sample_queue {
	u64			timestamp;
	u64			file_offset;
	union perf_event	*event;
	struct list_head	list;
};

static void perf_session_free_sample_buffers(struct perf_session *session)
{
	struct ordered_samples *os = &session->ordered_samples;

	while (!list_empty(&os->to_free)) {
		struct sample_queue *sq;

		sq = list_entry(os->to_free.next, struct sample_queue, list);
		list_del(&sq->list);
		free(sq);
	}
}

static int perf_session_deliver_event(struct perf_session *session,
				      union perf_event *event,
				      struct perf_sample *sample,
				      struct perf_tool *tool,
				      u64 file_offset);

static int flush_sample_queue(struct perf_session *s,
			       struct perf_tool *tool)
{
	struct ordered_samples *os = &s->ordered_samples;
	struct list_head *head = &os->samples;
	struct sample_queue *tmp, *iter;
	struct perf_sample sample;
	u64 limit = os->next_flush;
	u64 last_ts = os->last_sample ? os->last_sample->timestamp : 0ULL;
	unsigned idx = 0, progress_next = os->nr_samples / 16;
	int ret;

	if (!tool->ordered_samples || !limit)
		return 0;

	list_for_each_entry_safe(iter, tmp, head, list) {
		if (iter->timestamp > limit)
			break;

		ret = perf_evlist__parse_sample(s->evlist, iter->event, &sample,
						s->header.needs_swap);
		if (ret)
			pr_err("Can't parse sample, err = %d\n", ret);
		else {
			ret = perf_session_deliver_event(s, iter->event, &sample, tool,
							 iter->file_offset);
			if (ret)
				return ret;
		}

		os->last_flush = iter->timestamp;
		list_del(&iter->list);
		list_add(&iter->list, &os->sample_cache);
		if (++idx >= progress_next) {
			progress_next += os->nr_samples / 16;
			ui_progress__update(idx, os->nr_samples,
					    "Processing time ordered events...");
		}
	}

	if (list_empty(head)) {
		os->last_sample = NULL;
	} else if (last_ts <= limit) {
		os->last_sample =
			list_entry(head->prev, struct sample_queue, list);
	}

	os->nr_samples = 0;

	return 0;
}

/*
 * When perf record finishes a pass on every buffers, it records this pseudo
 * event.
 * We record the max timestamp t found in the pass n.
 * Assuming these timestamps are monotonic across cpus, we know that if
 * a buffer still has events with timestamps below t, they will be all
 * available and then read in the pass n + 1.
 * Hence when we start to read the pass n + 2, we can safely flush every
 * events with timestamps below t.
 *
 *    ============ PASS n =================
 *       CPU 0         |   CPU 1
 *                     |
 *    cnt1 timestamps  |   cnt2 timestamps
 *          1          |         2
 *          2          |         3
 *          -          |         4  <--- max recorded
 *
 *    ============ PASS n + 1 ==============
 *       CPU 0         |   CPU 1
 *                     |
 *    cnt1 timestamps  |   cnt2 timestamps
 *          3          |         5
 *          4          |         6
 *          5          |         7 <---- max recorded
 *
 *      Flush every events below timestamp 4
 *
 *    ============ PASS n + 2 ==============
 *       CPU 0         |   CPU 1
 *                     |
 *    cnt1 timestamps  |   cnt2 timestamps
 *          6          |         8
 *          7          |         9
 *          -          |         10
 *
 *      Flush every events below timestamp 7
 *      etc...
 */
static int process_finished_round(struct perf_tool *tool,
				  union perf_event *event __maybe_unused,
				  struct perf_session *session)
{
	int ret = flush_sample_queue(session, tool);
	if (!ret)
		session->ordered_samples.next_flush = session->ordered_samples.max_timestamp;

	return ret;
}

/* The queue is ordered by time */
static void __queue_event(struct sample_queue *new, struct perf_session *s)
{
	struct ordered_samples *os = &s->ordered_samples;
	struct sample_queue *sample = os->last_sample;
	u64 timestamp = new->timestamp;
	struct list_head *p;

	++os->nr_samples;
	os->last_sample = new;

	if (!sample) {
		list_add(&new->list, &os->samples);
		os->max_timestamp = timestamp;
		return;
	}

	/*
	 * last_sample might point to some random place in the list as it's
	 * the last queued event. We expect that the new event is close to
	 * this.
	 */
	if (sample->timestamp <= timestamp) {
		while (sample->timestamp <= timestamp) {
			p = sample->list.next;
			if (p == &os->samples) {
				list_add_tail(&new->list, &os->samples);
				os->max_timestamp = timestamp;
				return;
			}
			sample = list_entry(p, struct sample_queue, list);
		}
		list_add_tail(&new->list, &sample->list);
	} else {
		while (sample->timestamp > timestamp) {
			p = sample->list.prev;
			if (p == &os->samples) {
				list_add(&new->list, &os->samples);
				return;
			}
			sample = list_entry(p, struct sample_queue, list);
		}
		list_add(&new->list, &sample->list);
	}
}

#define MAX_SAMPLE_BUFFER	(64 * 1024 / sizeof(struct sample_queue))

static int perf_session_queue_event(struct perf_session *s, union perf_event *event,
				    struct perf_sample *sample, u64 file_offset)
{
	struct ordered_samples *os = &s->ordered_samples;
	struct list_head *sc = &os->sample_cache;
	u64 timestamp = sample->time;
	struct sample_queue *new;

	if (!timestamp || timestamp == ~0ULL)
		return -ETIME;

	if (timestamp < s->ordered_samples.last_flush) {
		printf("Warning: Timestamp below last timeslice flush\n");
		return -EINVAL;
	}

	if (!list_empty(sc)) {
		new = list_entry(sc->next, struct sample_queue, list);
		list_del(&new->list);
	} else if (os->sample_buffer) {
		new = os->sample_buffer + os->sample_buffer_idx;
		if (++os->sample_buffer_idx == MAX_SAMPLE_BUFFER)
			os->sample_buffer = NULL;
	} else {
		os->sample_buffer = malloc(MAX_SAMPLE_BUFFER * sizeof(*new));
		if (!os->sample_buffer)
			return -ENOMEM;
		list_add(&os->sample_buffer->list, &os->to_free);
		os->sample_buffer_idx = 2;
		new = os->sample_buffer + 1;
	}

	new->timestamp = timestamp;
	new->file_offset = file_offset;
	new->event = event;

	__queue_event(new, s);

	return 0;
}

static void callchain__printf(struct perf_sample *sample)
{
	unsigned int i;

	printf("... chain: nr:%" PRIu64 "\n", sample->callchain->nr);

	for (i = 0; i < sample->callchain->nr; i++)
		printf("..... %2d: %016" PRIx64 "\n",
		       i, sample->callchain->ips[i]);
}

static void branch_stack__printf(struct perf_sample *sample)
{
	uint64_t i;

	printf("... branch stack: nr:%" PRIu64 "\n", sample->branch_stack->nr);

	for (i = 0; i < sample->branch_stack->nr; i++)
		printf("..... %2"PRIu64": %016" PRIx64 " -> %016" PRIx64 "\n",
			i, sample->branch_stack->entries[i].from,
			sample->branch_stack->entries[i].to);
}

static void regs_dump__printf(u64 mask, u64 *regs)
{
	unsigned rid, i = 0;

	for_each_set_bit(rid, (unsigned long *) &mask, sizeof(mask) * 8) {
		u64 val = regs[i++];

		printf(".... %-5s 0x%" PRIx64 "\n",
		       perf_reg_name(rid), val);
	}
}

static void regs_user__printf(struct perf_sample *sample, u64 mask)
{
	struct regs_dump *user_regs = &sample->user_regs;

	if (user_regs->regs) {
		printf("... user regs: mask 0x%" PRIx64 "\n", mask);
		regs_dump__printf(mask, user_regs->regs);
	}
}

static void stack_user__printf(struct stack_dump *dump)
{
	printf("... ustack: size %" PRIu64 ", offset 0x%x\n",
	       dump->size, dump->offset);
}

static void perf_session__print_tstamp(struct perf_session *session,
				       union perf_event *event,
				       struct perf_sample *sample)
{
	u64 sample_type = perf_evlist__sample_type(session->evlist);

	if (event->header.type != PERF_RECORD_SAMPLE &&
	    !perf_evlist__sample_id_all(session->evlist)) {
		fputs("-1 -1 ", stdout);
		return;
	}

	if ((sample_type & PERF_SAMPLE_CPU))
		printf("%u ", sample->cpu);

	if (sample_type & PERF_SAMPLE_TIME)
		printf("%" PRIu64 " ", sample->time);
}

static void dump_event(struct perf_session *session, union perf_event *event,
		       u64 file_offset, struct perf_sample *sample)
{
	if (!dump_trace)
		return;

	printf("\n%#" PRIx64 " [%#x]: event: %d\n",
	       file_offset, event->header.size, event->header.type);

	trace_event(event);

	if (sample)
		perf_session__print_tstamp(session, event, sample);

	printf("%#" PRIx64 " [%#x]: PERF_RECORD_%s", file_offset,
	       event->header.size, perf_event__name(event->header.type));
}

static void dump_sample(struct perf_evsel *evsel, union perf_event *event,
			struct perf_sample *sample)
{
	u64 sample_type;

	if (!dump_trace)
		return;

	printf("(IP, %d): %d/%d: %#" PRIx64 " period: %" PRIu64 " addr: %#" PRIx64 "\n",
	       event->header.misc, sample->pid, sample->tid, sample->ip,
	       sample->period, sample->addr);

	sample_type = evsel->attr.sample_type;

	if (sample_type & PERF_SAMPLE_CALLCHAIN)
		callchain__printf(sample);