1// SPDX-License-Identifier: GPL-2.0-only
2/*
3 * intel_pt.c: Intel Processor Trace support
4 * Copyright (c) 2013-2015, Intel Corporation.
5 */
6
7#include <inttypes.h>
8#include <stdio.h>
9#include <stdbool.h>
10#include <errno.h>
11#include <linux/kernel.h>
12#include <linux/string.h>
13#include <linux/types.h>
14#include <linux/zalloc.h>
15
16#include "session.h"
17#include "machine.h"
18#include "memswap.h"
19#include "sort.h"
20#include "tool.h"
21#include "event.h"
22#include "evlist.h"
23#include "evsel.h"
24#include "map.h"
25#include "color.h"
26#include "thread.h"
27#include "thread-stack.h"
28#include "symbol.h"
29#include "callchain.h"
30#include "dso.h"
31#include "debug.h"
32#include "auxtrace.h"
33#include "tsc.h"
34#include "intel-pt.h"
35#include "config.h"
36#include "util/perf_api_probe.h"
37#include "util/synthetic-events.h"
38#include "time-utils.h"
39
40#include "../arch/x86/include/uapi/asm/perf_regs.h"
41
42#include "intel-pt-decoder/intel-pt-log.h"
43#include "intel-pt-decoder/intel-pt-decoder.h"
44#include "intel-pt-decoder/intel-pt-insn-decoder.h"
45#include "intel-pt-decoder/intel-pt-pkt-decoder.h"
46
47#define MAX_TIMESTAMP (~0ULL)
48
49struct range {
50	u64 start;
51	u64 end;
52};
53
54struct intel_pt {
55	struct auxtrace auxtrace;
56	struct auxtrace_queues queues;
57	struct auxtrace_heap heap;
58	u32 auxtrace_type;
59	struct perf_session *session;
60	struct machine *machine;
61	struct evsel *switch_evsel;
62	struct thread *unknown_thread;
63	bool timeless_decoding;
64	bool sampling_mode;
65	bool snapshot_mode;
66	bool per_cpu_mmaps;
67	bool have_tsc;
68	bool data_queued;
69	bool est_tsc;
70	bool sync_switch;
71	bool mispred_all;
72	bool use_thread_stack;
73	bool callstack;
74	unsigned int br_stack_sz;
75	unsigned int br_stack_sz_plus;
76	int have_sched_switch;
77	u32 pmu_type;
78	u64 kernel_start;
79	u64 switch_ip;
80	u64 ptss_ip;
81
82	struct perf_tsc_conversion tc;
83	bool cap_user_time_zero;
84
85	struct itrace_synth_opts synth_opts;
86
87	bool sample_instructions;
88	u64 instructions_sample_type;
89	u64 instructions_id;
90
91	bool sample_branches;
92	u32 branches_filter;
93	u64 branches_sample_type;
94	u64 branches_id;
95
96	bool sample_transactions;
97	u64 transactions_sample_type;
98	u64 transactions_id;
99
100	bool sample_ptwrites;
101	u64 ptwrites_sample_type;
102	u64 ptwrites_id;
103
104	bool sample_pwr_events;
105	u64 pwr_events_sample_type;
106	u64 mwait_id;
107	u64 pwre_id;
108	u64 exstop_id;
109	u64 pwrx_id;
110	u64 cbr_id;
111
112	bool sample_pebs;
113	struct evsel *pebs_evsel;
114
115	u64 tsc_bit;
116	u64 mtc_bit;
117	u64 mtc_freq_bits;
118	u32 tsc_ctc_ratio_n;
119	u32 tsc_ctc_ratio_d;
120	u64 cyc_bit;
121	u64 noretcomp_bit;
122	unsigned max_non_turbo_ratio;
123	unsigned cbr2khz;
124
125	unsigned long num_events;
126
127	char *filter;
128	struct addr_filters filts;
129
130	struct range *time_ranges;
131	unsigned int range_cnt;
132
133	struct ip_callchain *chain;
134	struct branch_stack *br_stack;
135};
136
137enum switch_state {
138	INTEL_PT_SS_NOT_TRACING,
139	INTEL_PT_SS_UNKNOWN,
140	INTEL_PT_SS_TRACING,
141	INTEL_PT_SS_EXPECTING_SWITCH_EVENT,
142	INTEL_PT_SS_EXPECTING_SWITCH_IP,
143};
144
145struct intel_pt_queue {
146	struct intel_pt *pt;
147	unsigned int queue_nr;
148	struct auxtrace_buffer *buffer;
149	struct auxtrace_buffer *old_buffer;
150	void *decoder;
151	const struct intel_pt_state *state;
152	struct ip_callchain *chain;
153	struct branch_stack *last_branch;
154	union perf_event *event_buf;
155	bool on_heap;
156	bool stop;
157	bool step_through_buffers;
158	bool use_buffer_pid_tid;
159	bool sync_switch;
160	pid_t pid, tid;
161	int cpu;
162	int switch_state;
163	pid_t next_tid;
164	struct thread *thread;
165	bool exclude_kernel;
166	bool have_sample;
167	u64 time;
168	u64 timestamp;
169	u64 sel_timestamp;
170	bool sel_start;
171	unsigned int sel_idx;
172	u32 flags;
173	u16 insn_len;
174	u64 last_insn_cnt;
175	u64 ipc_insn_cnt;
176	u64 ipc_cyc_cnt;
177	u64 last_in_insn_cnt;
178	u64 last_in_cyc_cnt;
179	u64 last_br_insn_cnt;
180	u64 last_br_cyc_cnt;
181	unsigned int cbr_seen;
182	char insn[INTEL_PT_INSN_BUF_SZ];
183};
184
185static void intel_pt_dump(struct intel_pt *pt __maybe_unused,
186			  unsigned char *buf, size_t len)
187{
188	struct intel_pt_pkt packet;
189	size_t pos = 0;
190	int ret, pkt_len, i;
191	char desc[INTEL_PT_PKT_DESC_MAX];
192	const char *color = PERF_COLOR_BLUE;
193	enum intel_pt_pkt_ctx ctx = INTEL_PT_NO_CTX;
194
195	color_fprintf(stdout, color,
196		      ". ... Intel Processor Trace data: size %zu bytes\n",
197		      len);
198
199	while (len) {
200		ret = intel_pt_get_packet(buf, len, &packet, &ctx);
201		if (ret > 0)
202			pkt_len = ret;
203		else
204			pkt_len = 1;
205		printf(".");
206		color_fprintf(stdout, color, "  %08x: ", pos);
207		for (i = 0; i < pkt_len; i++)
208			color_fprintf(stdout, color, " %02x", buf[i]);
209		for (; i < 16; i++)
210			color_fprintf(stdout, color, "   ");
211		if (ret > 0) {
212			ret = intel_pt_pkt_desc(&packet, desc,
213						INTEL_PT_PKT_DESC_MAX);
214			if (ret > 0)
215				color_fprintf(stdout, color, " %s\n", desc);
216		} else {
217			color_fprintf(stdout, color, " Bad packet!\n");
218		}
219		pos += pkt_len;
220		buf += pkt_len;
221		len -= pkt_len;
222	}
223}
224
225static void intel_pt_dump_event(struct intel_pt *pt, unsigned char *buf,
226				size_t len)
227{
228	printf(".\n");
229	intel_pt_dump(pt, buf, len);
230}
231
232static void intel_pt_log_event(union perf_event *event)
233{
234	FILE *f = intel_pt_log_fp();
235
236	if (!intel_pt_enable_logging || !f)
237		return;
238
239	perf_event__fprintf(event, NULL, f);
240}
241
242static void intel_pt_dump_sample(struct perf_session *session,
243				 struct perf_sample *sample)
244{
245	struct intel_pt *pt = container_of(session->auxtrace, struct intel_pt,
246					   auxtrace);
247
248	printf("\n");
249	intel_pt_dump(pt, sample->aux_sample.data, sample->aux_sample.size);
250}
251
252static bool intel_pt_log_events(struct intel_pt *pt, u64 tm)
253{
254	struct perf_time_interval *range = pt->synth_opts.ptime_range;
255	int n = pt->synth_opts.range_num;
256
257	if (pt->synth_opts.log_plus_flags & AUXTRACE_LOG_FLG_ALL_PERF_EVTS)
258		return true;
259
260	if (pt->synth_opts.log_minus_flags & AUXTRACE_LOG_FLG_ALL_PERF_EVTS)
261		return false;
262
263	/* perf_time__ranges_skip_sample does not work if time is zero */
264	if (!tm)
265		tm = 1;
266
267	return !n || !perf_time__ranges_skip_sample(range, n, tm);
268}
269
270static int intel_pt_do_fix_overlap(struct intel_pt *pt, struct auxtrace_buffer *a,
271				   struct auxtrace_buffer *b)
272{
273	bool consecutive = false;
274	void *start;
275
276	start = intel_pt_find_overlap(a->data, a->size, b->data, b->size,
277				      pt->have_tsc, &consecutive);
278	if (!start)
279		return -EINVAL;
280	b->use_size = b->data + b->size - start;
281	b->use_data = start;
282	if (b->use_size && consecutive)
283		b->consecutive = true;
284	return 0;
285}
286
287static int intel_pt_get_buffer(struct intel_pt_queue *ptq,
288			       struct auxtrace_buffer *buffer,
289			       struct auxtrace_buffer *old_buffer,
290			       struct intel_pt_buffer *b)
291{
292	bool might_overlap;
293
294	if (!buffer->data) {
295		int fd = perf_data__fd(ptq->pt->session->data);
296
297		buffer->data = auxtrace_buffer__get_data(buffer, fd);
298		if (!buffer->data)
299			return -ENOMEM;
300	}
301
302	might_overlap = ptq->pt->snapshot_mode || ptq->pt->sampling_mode;
303	if (might_overlap && !buffer->consecutive && old_buffer &&
304	    intel_pt_do_fix_overlap(ptq->pt, old_buffer, buffer))
305		return -ENOMEM;
306
307	if (buffer->use_data) {
308		b->len = buffer->use_size;
309		b->buf = buffer->use_data;
310	} else {
311		b->len = buffer->size;
312		b->buf = buffer->data;
313	}
314	b->ref_timestamp = buffer->reference;
315
316	if (!old_buffer || (might_overlap && !buffer->consecutive)) {
317		b->consecutive = false;
318		b->trace_nr = buffer->buffer_nr + 1;
319	} else {
320		b->consecutive = true;
321	}
322
323	return 0;
324}
325
326/* Do not drop buffers with references - refer intel_pt_get_trace() */
327static void intel_pt_lookahead_drop_buffer(struct intel_pt_queue *ptq,
328					   struct auxtrace_buffer *buffer)
329{
330	if (!buffer || buffer == ptq->buffer || buffer == ptq->old_buffer)
331		return;
332
333	auxtrace_buffer__drop_data(buffer);
334}
335
336/* Must be serialized with respect to intel_pt_get_trace() */
337static int intel_pt_lookahead(void *data, intel_pt_lookahead_cb_t cb,
338			      void *cb_data)
339{
340	struct intel_pt_queue *ptq = data;
341	struct auxtrace_buffer *buffer = ptq->buffer;
342	struct auxtrace_buffer *old_buffer = ptq->old_buffer;
343	struct auxtrace_queue *queue;
344	int err = 0;
345
346	queue = &ptq->pt->queues.queue_array[ptq->queue_nr];
347
348	while (1) {
349		struct intel_pt_buffer b = { .len = 0 };
350
351		buffer = auxtrace_buffer__next(queue, buffer);
352		if (!buffer)
353			break;
354
355		err = intel_pt_get_buffer(ptq, buffer, old_buffer, &b);
356		if (err)
357			break;
358
359		if (b.len) {
360			intel_pt_lookahead_drop_buffer(ptq, old_buffer);
361			old_buffer = buffer;
362		} else {
363			intel_pt_lookahead_drop_buffer(ptq, buffer);
364			continue;
365		}
366
367		err = cb(&b, cb_data);
368		if (err)
369			break;
370	}
371
372	if (buffer != old_buffer)
373		intel_pt_lookahead_drop_buffer(ptq, buffer);
374	intel_pt_lookahead_drop_buffer(ptq, old_buffer);
375
376	return err;
377}
378
379/*
380 * This function assumes data is processed sequentially only.
381 * Must be serialized with respect to intel_pt_lookahead()
382 */
383static int intel_pt_get_trace(struct intel_pt_buffer *b, void *data)
384{
385	struct intel_pt_queue *ptq = data;
386	struct auxtrace_buffer *buffer = ptq->buffer;
387	struct auxtrace_buffer *old_buffer = ptq->old_buffer;
388	struct auxtrace_queue *queue;
389	int err;
390
391	if (ptq->stop) {
392		b->len = 0;
393		return 0;
394	}
395
396	queue = &ptq->pt->queues.queue_array[ptq->queue_nr];
397
398	buffer = auxtrace_buffer__next(queue, buffer);
399	if (!buffer) {
400		if (old_buffer)
401			auxtrace_buffer__drop_data(old_buffer);
402		b->len = 0;
403		return 0;
404	}
405
406	ptq->buffer = buffer;
407
408	err = intel_pt_get_buffer(ptq, buffer, old_buffer, b);
409	if (err)
410		return err;
411
412	if (ptq->step_through_buffers)
413		ptq->stop = true;
414
415	if (b->len) {
416		if (old_buffer)
417			auxtrace_buffer__drop_data(old_buffer);
418		ptq->old_buffer = buffer;
419	} else {
420		auxtrace_buffer__drop_data(buffer);
421		return intel_pt_get_trace(b, data);
422	}
423
424	return 0;
425}
426
427struct intel_pt_cache_entry {
428	struct auxtrace_cache_entry	entry;
429	u64				insn_cnt;
430	u64				byte_cnt;
431	enum intel_pt_insn_op		op;
432	enum intel_pt_insn_branch	branch;
433	int				length;
434	int32_t				rel;
435	char				insn[INTEL_PT_INSN_BUF_SZ];
436};
437
438static int intel_pt_config_div(const char *var, const char *value, void *data)
439{
440	int *d = data;
441	long val;
442
443	if (!strcmp(var, "intel-pt.cache-divisor")) {
444		val = strtol(value, NULL, 0);
445		if (val > 0 && val <= INT_MAX)
446			*d = val;
447	}
448
449	return 0;
450}
451
452static int intel_pt_cache_divisor(void)
453{
454	static int d;
455
456	if (d)
457		return d;
458
459	perf_config(intel_pt_config_div, &d);
460
461	if (!d)
462		d = 64;
463
464	return d;
465}
466
467static unsigned int intel_pt_cache_size(struct dso *dso,
468					struct machine *machine)
469{
470	off_t size;
471
472	size = dso__data_size(dso, machine);
473	size /= intel_pt_cache_divisor();
474	if (size < 1000)
475		return 10;
476	if (size > (1 << 21))
477		return 21;
478	return 32 - __builtin_clz(size);
479}
480
481static struct auxtrace_cache *intel_pt_cache(struct dso *dso,
482					     struct machine *machine)
483{
484	struct auxtrace_cache *c;
485	unsigned int bits;
486
487	if (dso->auxtrace_cache)
488		return dso->auxtrace_cache;
489
490	bits = intel_pt_cache_size(dso, machine);
491
492	/* Ignoring cache creation failure */
493	c = auxtrace_cache__new(bits, sizeof(struct intel_pt_cache_entry), 200);
494
495	dso->auxtrace_cache = c;
496
497	return c;
498}
499
500static int intel_pt_cache_add(struct dso *dso, struct machine *machine,
501			      u64 offset, u64 insn_cnt, u64 byte_cnt,
502			      struct intel_pt_insn *intel_pt_insn)
503{
504	struct auxtrace_cache *c = intel_pt_cache(dso, machine);
505	struct intel_pt_cache_entry *e;
506	int err;
507
508	if (!c)
509		return -ENOMEM;
510
511	e = auxtrace_cache__alloc_entry(c);
512	if (!e)
513		return -ENOMEM;
514
515	e->insn_cnt = insn_cnt;
516	e->byte_cnt = byte_cnt;
517	e->op = intel_pt_insn->op;
518	e->branch = intel_pt_insn->branch;
519	e->length = intel_pt_insn->length;
520	e->rel = intel_pt_insn->rel;
521	memcpy(e->insn, intel_pt_insn->buf, INTEL_PT_INSN_BUF_SZ);
522
523	err = auxtrace_cache__add(c, offset, &e->entry);
524	if (err)
525		auxtrace_cache__free_entry(c, e);
526
527	return err;
528}
529
530static struct intel_pt_cache_entry *
531intel_pt_cache_lookup(struct dso *dso, struct machine *machine, u64 offset)
532{
533	struct auxtrace_cache *c = intel_pt_cache(dso, machine);
534
535	if (!c)
536		return NULL;
537
538	return auxtrace_cache__lookup(dso->auxtrace_cache, offset);
539}
540
541static void intel_pt_cache_invalidate(struct dso *dso, struct machine *machine,
542				      u64 offset)
543{
544	struct auxtrace_cache *c = intel_pt_cache(dso, machine);
545
546	if (!c)
547		return;
548
549	auxtrace_cache__remove(dso->auxtrace_cache, offset);
550}
551
552static inline u8 intel_pt_cpumode(struct intel_pt *pt, uint64_t ip)
553{
554	return ip >= pt->kernel_start ?
555	       PERF_RECORD_MISC_KERNEL :
556	       PERF_RECORD_MISC_USER;
557}
558
559static int intel_pt_walk_next_insn(struct intel_pt_insn *intel_pt_insn,
560				   uint64_t *insn_cnt_ptr, uint64_t *ip,
561				   uint64_t to_ip, uint64_t max_insn_cnt,
562				   void *data)
563{
564	struct intel_pt_queue *ptq = data;
565	struct machine *machine = ptq->pt->machine;
566	struct thread *thread;
567	struct addr_location al;
568	unsigned char buf[INTEL_PT_INSN_BUF_SZ];
569	ssize_t len;
570	int x86_64;
571	u8 cpumode;
572	u64 offset, start_offset, start_ip;
573	u64 insn_cnt = 0;
574	bool one_map = true;
575
576	intel_pt_insn->length = 0;
577
578	if (to_ip && *ip == to_ip)
579		goto out_no_cache;
580
581	cpumode = intel_pt_cpumode(ptq->pt, *ip);
582
583	thread = ptq->thread;
584	if (!thread) {
585		if (cpumode != PERF_RECORD_MISC_KERNEL)
586			return -EINVAL;
587		thread = ptq->pt->unknown_thread;
588	}
589
590	while (1) {
591		if (!thread__find_map(thread, cpumode, *ip, &al) || !al.map->dso)
592			return -EINVAL;
593
594		if (al.map->dso->data.status == DSO_DATA_STATUS_ERROR &&
595		    dso__data_status_seen(al.map->dso,
596					  DSO_DATA_STATUS_SEEN_ITRACE))
597			return -ENOENT;
598
599		offset = al.map->map_ip(al.map, *ip);
600
601		if (!to_ip && one_map) {
602			struct intel_pt_cache_entry *e;
603
604			e = intel_pt_cache_lookup(al.map->dso, machine, offset);
605			if (e &&
606			    (!max_insn_cnt || e->insn_cnt <= max_insn_cnt)) {
607				*insn_cnt_ptr = e->insn_cnt;
608				*ip += e->byte_cnt;
609				intel_pt_insn->op = e->op;
610				intel_pt_insn->branch = e->branch;
611				intel_pt_insn->length = e->length;
612				intel_pt_insn->rel = e->rel;
613				memcpy(intel_pt_insn->buf, e->insn,
614				       INTEL_PT_INSN_BUF_SZ);
615				intel_pt_log_insn_no_data(intel_pt_insn, *ip);
616				return 0;
617			}
618		}
619
620		start_offset = offset;
621		start_ip = *ip;
622
623		/* Load maps to ensure dso->is_64_bit has been updated */
624		map__load(al.map);
625
626		x86_64 = al.map->dso->is_64_bit;
627
628		while (1) {
629			len = dso__data_read_offset(al.map->dso, machine,
630						    offset, buf,
631						    INTEL_PT_INSN_BUF_SZ);
632			if (len <= 0)
633				return -EINVAL;
634
635			if (intel_pt_get_insn(buf, len, x86_64, intel_pt_insn))
636				return -EINVAL;
637
638			intel_pt_log_insn(intel_pt_insn, *ip);
639
640			insn_cnt += 1;
641
642			if (intel_pt_insn->branch != INTEL_PT_BR_NO_BRANCH)
643				goto out;
644
645			if (max_insn_cnt && insn_cnt >= max_insn_cnt)
646				goto out_no_cache;
647
648			*ip += intel_pt_insn->length;
649
650			if (to_ip && *ip == to_ip) {
651				intel_pt_insn->length = 0;
652				goto out_no_cache;
653			}
654
655			if (*ip >= al.map->end)
656				break;
657
658			offset += intel_pt_insn->length;
659		}
660		one_map = false;
661	}
662out:
663	*insn_cnt_ptr = insn_cnt;
664
665	if (!one_map)
666		goto out_no_cache;
667
668	/*
669	 * Didn't lookup in the 'to_ip' case, so do it now to prevent duplicate
670	 * entries.
671	 */
672	if (to_ip) {
673		struct intel_pt_cache_entry *e;
674
675		e = intel_pt_cache_lookup(al.map->dso, machine, start_offset);
676		if (e)
677			return 0;
678	}
679
680	/* Ignore cache errors */
681	intel_pt_cache_add(al.map->dso, machine, start_offset, insn_cnt,
682			   *ip - start_ip, intel_pt_insn);
683
684	return 0;
685
686out_no_cache:
687	*insn_cnt_ptr = insn_cnt;
688	return 0;
689}
690
691static bool intel_pt_match_pgd_ip(struct intel_pt *pt, uint64_t ip,
692				  uint64_t offset, const char *filename)
693{
694	struct addr_filter *filt;
695	bool have_filter   = false;
696	bool hit_tracestop = false;
697	bool hit_filter    = false;
698
699	list_for_each_entry(filt, &pt->filts.head, list) {
700		if (filt->start)
701			have_filter = true;
702
703		if ((filename && !filt->filename) ||
704		    (!filename && filt->filename) ||
705		    (filename && strcmp(filename, filt->filename)))
706			continue;
707
708		if (!(offset >= filt->addr && offset < filt->addr + filt->size))
709			continue;
710
711		intel_pt_log("TIP.PGD ip %#"PRIx64" offset %#"PRIx64" in %s hit filter: %s offset %#"PRIx64" size %#"PRIx64"\n",
712			     ip, offset, filename ? filename : "[kernel]",
713			     filt->start ? "filter" : "stop",
714			     filt->addr, filt->size);
715
716		if (filt->start)
717			hit_filter = true;
718		else
719			hit_tracestop = true;
720	}
721
722	if (!hit_tracestop && !hit_filter)
723		intel_pt_log("TIP.PGD ip %#"PRIx64" offset %#"PRIx64" in %s is not in a filter region\n",
724			     ip, offset, filename ? filename : "[kernel]");
725
726	return hit_tracestop || (have_filter && !hit_filter);
727}
728
729static int __intel_pt_pgd_ip(uint64_t ip, void *data)
730{
731	struct intel_pt_queue *ptq = data;
732	struct thread *thread;
733	struct addr_location al;
734	u8 cpumode;
735	u64 offset;
736
737	if (ip >= ptq->pt->kernel_start)
738		return intel_pt_match_pgd_ip(ptq->pt, ip, ip, NULL);
739
740	cpumode = PERF_RECORD_MISC_USER;
741
742	thread = ptq->thread;
743	if (!thread)
744		return -EINVAL;
745
746	if (!thread__find_map(thread, cpumode, ip, &al) || !al.map->dso)
747		return -EINVAL;
748
749	offset = al.map->map_ip(al.map, ip);
750
751	return intel_pt_match_pgd_ip(ptq->pt, ip, offset,
752				     al.map->dso->long_name);
753}
754
755static bool intel_pt_pgd_ip(uint64_t ip, void *data)
756{
757	return __intel_pt_pgd_ip(ip, data) > 0;
758}
759
760static bool intel_pt_get_config(struct intel_pt *pt,
761				struct perf_event_attr *attr, u64 *config)
762{
763	if (attr->type == pt->pmu_type) {
764		if (config)
765			*config = attr->config;
766		return true;
767	}
768
769	return false;
770}
771
772static bool intel_pt_exclude_kernel(struct intel_pt *pt)
773{
774	struct evsel *evsel;
775
776	evlist__for_each_entry(pt->session->evlist, evsel) {
777		if (intel_pt_get_config(pt, &evsel->core.attr, NULL) &&
778		    !evsel->core.attr.exclude_kernel)
779			return false;
780	}
781	return true;
782}
783
784static bool intel_pt_return_compression(struct intel_pt *pt)
785{
786	struct evsel *evsel;
787	u64 config;
788
789	if (!pt->noretcomp_bit)
790		return true;
791
792	evlist__for_each_entry(pt->session->evlist, evsel) {
793		if (intel_pt_get_config(pt, &evsel->core.attr, &config) &&
794		    (config & pt->noretcomp_bit))
795			return false;
796	}
797	return true;
798}
799
800static bool intel_pt_branch_enable(struct intel_pt *pt)
801{
802	struct evsel *evsel;
803	u64 config;
804
805	evlist__for_each_entry(pt->session->evlist, evsel) {
806		if (intel_pt_get_config(pt, &evsel->core.attr, &config) &&
807		    (config & 1) && !(config & 0x2000))
808			return false;
809	}
810	return true;
811}
812
813static unsigned int intel_pt_mtc_period(struct intel_pt *pt)
814{
815	struct evsel *evsel;
816	unsigned int shift;
817	u64 config;
818
819	if (!pt->mtc_freq_bits)
820		return 0;
821
822	for (shift = 0, config = pt->mtc_freq_bits; !(config & 1); shift++)
823		config >>= 1;
824
825	evlist__for_each_entry(pt->session->evlist, evsel) {
826		if (intel_pt_get_config(pt, &evsel->core.attr, &config))
827			return (config & pt->mtc_freq_bits) >> shift;
828	}
829	return 0;
830}
831
832static bool intel_pt_timeless_decoding(struct intel_pt *pt)
833{
834	struct evsel *evsel;
835	bool timeless_decoding = true;
836	u64 config;
837
838	if (!pt->tsc_bit || !pt->cap_user_time_zero)
839		return true;
840
841	evlist__for_each_entry(pt->session->evlist, evsel) {
842		if (!(evsel->core.attr.sample_type & PERF_SAMPLE_TIME))
843			return true;
844		if (intel_pt_get_config(pt, &evsel->core.attr, &config)) {
845			if (config & pt->tsc_bit)
846				timeless_decoding = false;
847			else
848				return true;
849		}
850	}
851	return timeless_decoding;
852}
853
854static bool intel_pt_tracing_kernel(struct intel_pt *pt)
855{
856	struct evsel *evsel;
857
858	evlist__for_each_entry(pt->session->evlist, evsel) {
859		if (intel_pt_get_config(pt, &evsel->core.attr, NULL) &&
860		    !evsel->core.attr.exclude_kernel)
861			return true;
862	}
863	return false;
864}
865
866static bool intel_pt_have_tsc(struct intel_pt *pt)
867{
868	struct evsel *evsel;
869	bool have_tsc = false;
870	u64 config;
871
872	if (!pt->tsc_bit)
873		return false;
874
875	evlist__for_each_entry(pt->session->evlist, evsel) {
876		if (intel_pt_get_config(pt, &evsel->core.attr, &config)) {
877			if (config & pt->tsc_bit)
878				have_tsc = true;
879			else
880				return false;
881		}
882	}
883	return have_tsc;
884}
885
886static bool intel_pt_sampling_mode(struct intel_pt *pt)
887{
888	struct evsel *evsel;
889
890	evlist__for_each_entry(pt->session->evlist, evsel) {
891		if ((evsel->core.attr.sample_type & PERF_SAMPLE_AUX) &&
892		    evsel->core.attr.aux_sample_size)
893			return true;
894	}
895	return false;
896}
897
898static u64 intel_pt_ctl(struct intel_pt *pt)
899{
900	struct evsel *evsel;
901	u64 config;
902
903	evlist__for_each_entry(pt->session->evlist, evsel) {
904		if (intel_pt_get_config(pt, &evsel->core.attr, &config))
905			return config;
906	}
907	return 0;
908}
909
910static u64 intel_pt_ns_to_ticks(const struct intel_pt *pt, u64 ns)
911{
912	u64 quot, rem;
913
914	quot = ns / pt->tc.time_mult;
915	rem  = ns % pt->tc.time_mult;
916	return (quot << pt->tc.time_shift) + (rem << pt->tc.time_shift) /
917		pt->tc.time_mult;
918}
919
920static struct ip_callchain *intel_pt_alloc_chain(struct intel_pt *pt)
921{
922	size_t sz = sizeof(struct ip_callchain);
923
924	/* Add 1 to callchain_sz for callchain context */
925	sz += (pt->synth_opts.callchain_sz + 1) * sizeof(u64);
926	return zalloc(sz);
927}
928
929static int intel_pt_callchain_init(struct intel_pt *pt)
930{
931	struct evsel *evsel;
932
933	evlist__for_each_entry(pt->session->evlist, evsel) {
934		if (!(evsel->core.attr.sample_type & PERF_SAMPLE_CALLCHAIN))
935			evsel->synth_sample_type |= PERF_SAMPLE_CALLCHAIN;
936	}
937
938	pt->chain = intel_pt_alloc_chain(pt);
939	if (!pt->chain)
940		return -ENOMEM;
941
942	return 0;
943}
944
945static void intel_pt_add_callchain(struct intel_pt *pt,
946				   struct perf_sample *sample)
947{
948	struct thread *thread = machine__findnew_thread(pt->machine,
949							sample->pid,
950							sample->tid);
951
952	thread_stack__sample_late(thread, sample->cpu, pt->chain,
953				  pt->synth_opts.callchain_sz + 1, sample->ip,
954				  pt->kernel_start);
955
956	sample->callchain = pt->chain;
957}
958
959static struct branch_stack *intel_pt_alloc_br_stack(unsigned int entry_cnt)
960{
961	size_t sz = sizeof(struct branch_stack);
962
963	sz += entry_cnt * sizeof(struct branch_entry);
964	return zalloc(sz);
965}
966
967static int intel_pt_br_stack_init(struct intel_pt *pt)
968{
969	struct evsel *evsel;
970
971	evlist__for_each_entry(pt->session->evlist, evsel) {
972		if (!(evsel->core.attr.sample_type & PERF_SAMPLE_BRANCH_STACK))
973			evsel->synth_sample_type |= PERF_SAMPLE_BRANCH_STACK;
974	}
975
976	pt->br_stack = intel_pt_alloc_br_stack(pt->br_stack_sz);
977	if (!pt->br_stack)
978		return -ENOMEM;
979
980	return 0;
981}
982
983static void intel_pt_add_br_stack(struct intel_pt *pt,
984				  struct perf_sample *sample)
985{
986	struct thread *thread = machine__findnew_thread(pt->machine,
987							sample->pid,
988							sample->tid);
989
990	thread_stack__br_sample_late(thread, sample->cpu, pt->br_stack,
991				     pt->br_stack_sz, sample->ip,
992				     pt->kernel_start);
993
994	sample->branch_stack = pt->br_stack;
995}
996
997/* INTEL_PT_LBR_0, INTEL_PT_LBR_1 and INTEL_PT_LBR_2 */
998#define LBRS_MAX (INTEL_PT_BLK_ITEM_ID_CNT * 3U)
999
1000static struct intel_pt_queue *intel_pt_alloc_queue(struct intel_pt *pt,
1001						   unsigned int queue_nr)
1002{
1003	struct intel_pt_params params = { .get_trace = 0, };
1004	struct perf_env *env = pt->machine->env;
1005	struct intel_pt_queue *ptq;
1006
1007	ptq = zalloc(sizeof(struct intel_pt_queue));
1008	if (!ptq)
1009		return NULL;
1010
1011	if (pt->synth_opts.callchain) {
1012		ptq->chain = intel_pt_alloc_chain(pt);
1013		if (!ptq->chain)
1014			goto out_free;
1015	}
1016
1017	if (pt->synth_opts.last_branch || pt->synth_opts.other_events) {
1018		unsigned int entry_cnt = max(LBRS_MAX, pt->br_stack_sz);
1019
1020		ptq->last_branch = intel_pt_alloc_br_stack(entry_cnt);
1021		if (!ptq->last_branch)
1022			goto out_free;
1023	}
1024
1025	ptq->event_buf = malloc(PERF_SAMPLE_MAX_SIZE);
1026	if (!ptq->event_buf)
1027		goto out_free;
1028
1029	ptq->pt = pt;
1030	ptq->queue_nr = queue_nr;
1031	ptq->exclude_kernel = intel_pt_exclude_kernel(pt);
1032	ptq->pid = -1;
1033	ptq->tid = -1;
1034	ptq->cpu = -1;
1035	ptq->next_tid = -1;
1036
1037	params.get_trace = intel_pt_get_trace;
1038	params.walk_insn = intel_pt_walk_next_insn;
1039	params.lookahead = intel_pt_lookahead;
1040	params.data = ptq;
1041	params.return_compression = intel_pt_return_compression(pt);
1042	params.branch_enable = intel_pt_branch_enable(pt);
1043	params.ctl = intel_pt_ctl(pt);
1044	params.max_non_turbo_ratio = pt->max_non_turbo_ratio;
1045	params.mtc_period = intel_pt_mtc_period(pt);
1046	params.tsc_ctc_ratio_n = pt->tsc_ctc_ratio_n;
1047	params.tsc_ctc_ratio_d = pt->tsc_ctc_ratio_d;
1048	params.quick = pt->synth_opts.quick;
1049
1050	if (pt->filts.cnt > 0)
1051		params.pgd_ip = intel_pt_pgd_ip;
1052
1053	if (pt->synth_opts.instructions) {
1054		if (pt->synth_opts.period) {
1055			switch (pt->synth_opts.period_type) {
1056			case PERF_ITRACE_PERIOD_INSTRUCTIONS:
1057				params.period_type =
1058						INTEL_PT_PERIOD_INSTRUCTIONS;
1059				params.period = pt->synth_opts.period;
1060				break;
1061			case PERF_ITRACE_PERIOD_TICKS:
1062				params.period_type = INTEL_PT_PERIOD_TICKS;
1063				params.period = pt->synth_opts.period;
1064				break;
1065			case PERF_ITRACE_PERIOD_NANOSECS:
1066				params.period_type = INTEL_PT_PERIOD_TICKS;
1067				params.period = intel_pt_ns_to_ticks(pt,
1068							pt->synth_opts.period);
1069				break;
1070			default:
1071				break;
1072			}
1073		}
1074
1075		if (!params.period) {
1076			params.period_type = INTEL_PT_PERIOD_INSTRUCTIONS;
1077			params.period = 1;
1078		}
1079	}
1080
1081	if (env->cpuid && !strncmp(env->cpuid, "GenuineIntel,6,92,", 18))
1082		params.flags |= INTEL_PT_FUP_WITH_NLIP;
1083
1084	ptq->decoder = intel_pt_decoder_new(&params);
1085	if (!ptq->decoder)
1086		goto out_free;
1087
1088	return ptq;
1089
1090out_free:
1091	zfree(&ptq->event_buf);
1092	zfree(&ptq->last_branch);
1093	zfree(&ptq->chain);
1094	free(ptq);
1095	return NULL;
1096}
1097
1098static void intel_pt_free_queue(void *priv)
1099{
1100	struct intel_pt_queue *ptq = priv;
1101
1102	if (!ptq)
1103		return;
1104	thread__zput(ptq->thread);
1105	intel_pt_decoder_free(ptq->decoder);
1106	zfree(&ptq->event_buf);
1107	zfree(&ptq->last_branch);
1108	zfree(&ptq->chain);
1109	free(ptq);
1110}
1111
1112static void intel_pt_set_pid_tid_cpu(struct intel_pt *pt,
1113				     struct auxtrace_queue *queue)
1114{
1115	struct intel_pt_queue *ptq = queue->priv;
1116
1117	if (queue->tid == -1 || pt->have_sched_switch) {
1118		ptq->tid = machine__get_current_tid(pt->machine, ptq->cpu);
1119		if (ptq->tid == -1)
1120			ptq->pid = -1;
1121		thread__zput(ptq->thread);
1122	}
1123
1124	if (!ptq->thread && ptq->tid != -1)
1125		ptq->thread = machine__find_thread(pt->machine, -1, ptq->tid);
1126
1127	if (ptq->thread) {
1128		ptq->pid = ptq->thread->pid_;
1129		if (queue->cpu == -1)
1130			ptq->cpu = ptq->thread->cpu;
1131	}
1132}
1133
1134static void intel_pt_sample_flags(struct intel_pt_queue *ptq)
1135{
1136	ptq->insn_len = 0;
1137	if (ptq->state->flags & INTEL_PT_ABORT_TX) {
1138		ptq->flags = PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_TX_ABORT;
1139	} else if (ptq->state->flags & INTEL_PT_ASYNC) {
1140		if (ptq->state->to_ip)
1141			ptq->flags = PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_CALL |
1142				     PERF_IP_FLAG_ASYNC |
1143				     PERF_IP_FLAG_INTERRUPT;
1144		else
1145			ptq->flags = PERF_IP_FLAG_BRANCH |
1146				     PERF_IP_FLAG_TRACE_END;
1147		ptq->insn_len = 0;
1148	} else {
1149		if (ptq->state->from_ip)
1150			ptq->flags = intel_pt_insn_type(ptq->state->insn_op);
1151		else
1152			ptq->flags = PERF_IP_FLAG_BRANCH |
1153				     PERF_IP_FLAG_TRACE_BEGIN;
1154		if (ptq->state->flags & INTEL_PT_IN_TX)
1155			ptq->flags |= PERF_IP_FLAG_IN_TX;
1156		ptq->insn_len = ptq->state->insn_len;
1157		memcpy(ptq->insn, ptq->state->insn, INTEL_PT_INSN_BUF_SZ);
1158	}
1159
1160	if (ptq->state->type & INTEL_PT_TRACE_BEGIN)
1161		ptq->flags |= PERF_IP_FLAG_TRACE_BEGIN;
1162	if (ptq->state->type & INTEL_PT_TRACE_END)
1163		ptq->flags |= PERF_IP_FLAG_TRACE_END;
1164}
1165
1166static void intel_pt_setup_time_range(struct intel_pt *pt,
1167				      struct intel_pt_queue *ptq)
1168{
1169	if (!pt->range_cnt)
1170		return;
1171
1172	ptq->sel_timestamp = pt->time_ranges[0].start;
1173	ptq->sel_idx = 0;
1174
1175	if (ptq->sel_timestamp) {
1176		ptq->sel_start = true;
1177	} else {
1178		ptq->sel_timestamp = pt->time_ranges[0].end;
1179		ptq->sel_start = false;
1180	}
1181}
1182
1183static int intel_pt_setup_queue(struct intel_pt *pt,
1184				struct auxtrace_queue *queue,
1185				unsigned int queue_nr)
1186{
1187	struct intel_pt_queue *ptq = queue->priv;
1188
1189	if (list_empty(&queue->head))
1190		return 0;
1191
1192	if (!ptq) {
1193		ptq = intel_pt_alloc_queue(pt, queue_nr);
1194		if (!ptq)
1195			return -ENOMEM;
1196		queue->priv = ptq;
1197
1198		if (queue->cpu != -1)
1199			ptq->cpu = queue->cpu;
1200		ptq->tid = queue->tid;
1201
1202		ptq->cbr_seen = UINT_MAX;
1203
1204		if (pt->sampling_mode && !pt->snapshot_mode &&
1205		    pt->timeless_decoding)
1206			ptq->step_through_buffers = true;
1207
1208		ptq->sync_switch = pt->sync_switch;
1209
1210		intel_pt_setup_time_range(pt, ptq);
1211	}
1212
1213	if (!ptq->on_heap &&
1214	    (!ptq->sync_switch ||
1215	     ptq->switch_state != INTEL_PT_SS_EXPECTING_SWITCH_EVENT)) {
1216		const struct intel_pt_state *state;
1217		int ret;
1218
1219		if (pt->timeless_decoding)
1220			return 0;
1221
1222		intel_pt_log("queue %u getting timestamp\n", queue_nr);
1223		intel_pt_log("queue %u decoding cpu %d pid %d tid %d\n",
1224			     queue_nr, ptq->cpu, ptq->pid, ptq->tid);
1225
1226		if (ptq->sel_start && ptq->sel_timestamp) {
1227			ret = intel_pt_fast_forward(ptq->decoder,
1228						    ptq->sel_timestamp);
1229			if (ret)
1230				return ret;
1231		}
1232
1233		while (1) {
1234			state = intel_pt_decode(ptq->decoder);
1235			if (state->err) {
1236				if (state->err == INTEL_PT_ERR_NODATA) {
1237					intel_pt_log("queue %u has no timestamp\n",
1238						     queue_nr);
1239					return 0;
1240				}
1241				continue;
1242			}
1243			if (state->timestamp)
1244				break;
1245		}
1246
1247		ptq->timestamp = state->timestamp;
1248		intel_pt_log("queue %u timestamp 0x%" PRIx64 "\n",
1249			     queue_nr, ptq->timestamp);
1250		ptq->state = state;
1251		ptq->have_sample = true;
1252		if (ptq->sel_start && ptq->sel_timestamp &&
1253		    ptq->timestamp < ptq->sel_timestamp)
1254			ptq->have_sample = false;
1255		intel_pt_sample_flags(ptq);
1256		ret = auxtrace_heap__add(&pt->heap, queue_nr, ptq->timestamp);
1257		if (ret)
1258			return ret;
1259		ptq->on_heap = true;
1260	}
1261
1262	return 0;
1263}
1264
1265static int intel_pt_setup_queues(struct intel_pt *pt)
1266{
1267	unsigned int i;
1268	int ret;
1269
1270	for (i = 0; i < pt->queues.nr_queues; i++) {
1271		ret = intel_pt_setup_queue(pt, &pt->queues.queue_array[i], i);
1272		if (ret)
1273			return ret;
1274	}
1275	return 0;
1276}
1277
1278static inline bool intel_pt_skip_event(struct intel_pt *pt)
1279{
1280	return pt->synth_opts.initial_skip &&
1281	       pt->num_events++ < pt->synth_opts.initial_skip;
1282}
1283
1284/*
1285 * Cannot count CBR as skipped because it won't go away until cbr == cbr_seen.
1286 * Also ensure CBR is first non-skipped event by allowing for 4 more samples
1287 * from this decoder state.
1288 */
1289static inline bool intel_pt_skip_cbr_event(struct intel_pt *pt)
1290{
1291	return pt->synth_opts.initial_skip &&
1292	       pt->num_events + 4 < pt->synth_opts.initial_skip;
1293}
1294
1295static void intel_pt_prep_a_sample(struct intel_pt_queue *ptq,
1296				   union perf_event *event,
1297				   struct perf_sample *sample)
1298{
1299	event->sample.header.type = PERF_RECORD_SAMPLE;
1300	event->sample.header.size = sizeof(struct perf_event_header);
1301
1302	sample->pid = ptq->pid;
1303	sample->tid = ptq->tid;
1304	sample->cpu = ptq->cpu;
1305	sample->insn_len = ptq->insn_len;
1306	memcpy(sample->insn, ptq->insn, INTEL_PT_INSN_BUF_SZ);
1307}
1308
1309static void intel_pt_prep_b_sample(struct intel_pt *pt,
1310				   struct intel_pt_queue *ptq,
1311				   union perf_event *event,
1312				   struct perf_sample *sample)
1313{
1314	intel_pt_prep_a_sample(ptq, event, sample);
1315
1316	if (!pt->timeless_decoding)
1317		sample->time = tsc_to_perf_time(ptq->timestamp, &pt->tc);
1318
1319	sample->ip = ptq->state->from_ip;
1320	sample->cpumode = intel_pt_cpumode(pt, sample->ip);
1321	sample->addr = ptq->state->to_ip;
1322	sample->period = 1;
1323	sample->flags = ptq->flags;
1324
1325	event->sample.header.misc = sample->cpumode;
1326}
1327
1328static int intel_pt_inject_event(union perf_event *event,
1329				 struct perf_sample *sample, u64 type)
1330{
1331	event->header.size = perf_event__sample_event_size(sample, type, 0);
1332	return perf_event__synthesize_sample(event, type, 0, sample);
1333}
1334
1335static inline int intel_pt_opt_inject(struct intel_pt *pt,
1336				      union perf_event *event,
1337				      struct perf_sample *sample, u64 type)
1338{
1339	if (!pt->synth_opts.inject)
1340		return 0;
1341
1342	return intel_pt_inject_event(event, sample, type);
1343}
1344
1345static int intel_pt_deliver_synth_event(struct intel_pt *pt,
1346					union perf_event *event,
1347					struct perf_sample *sample, u64 type)
1348{
1349	int ret;
1350
1351	ret = intel_pt_opt_inject(pt, event, sample, type);
1352	if (ret)
1353		return ret;
1354
1355	ret = perf_session__deliver_synth_event(pt->session, event, sample);
1356	if (ret)
1357		pr_err("Intel PT: failed to deliver event, error %d\n", ret);
1358
1359	return ret;
1360}
1361
1362static int intel_pt_synth_branch_sample(struct intel_pt_queue *ptq)
1363{
1364	struct intel_pt *pt = ptq->pt;
1365	union perf_event *event = ptq->event_buf;
1366	struct perf_sample sample = { .ip = 0, };
1367	struct dummy_branch_stack {
1368		u64			nr;
1369		u64			hw_idx;
1370		struct branch_entry	entries;
1371	} dummy_bs;
1372
1373	if (pt->branches_filter && !(pt->branches_filter & ptq->flags))
1374		return 0;
1375
1376	if (intel_pt_skip_event(pt))
1377		return 0;
1378
1379	intel_pt_prep_b_sample(pt, ptq, event, &sample);
1380
1381	sample.id = ptq->pt->branches_id;
1382	sample.stream_id = ptq->pt->branches_id;
1383
1384	/*
1385	 * perf report cannot handle events without a branch stack when using
1386	 * SORT_MODE__BRANCH so make a dummy one.
1387	 */
1388	if (pt->synth_opts.last_branch && sort__mode == SORT_MODE__BRANCH) {
1389		dummy_bs = (struct dummy_branch_stack){
1390			.nr = 1,
1391			.hw_idx = -1ULL,
1392			.entries = {
1393				.from = sample.ip,
1394				.to = sample.addr,
1395			},
1396		};
1397		sample.branch_stack = (struct branch_stack *)&dummy_bs;
1398	}
1399
1400	if (ptq->state->flags & INTEL_PT_SAMPLE_IPC)
1401		sample.cyc_cnt = ptq->ipc_cyc_cnt - ptq->last_br_cyc_cnt;
1402	if (sample.cyc_cnt) {
1403		sample.insn_cnt = ptq->ipc_insn_cnt - ptq->last_br_insn_cnt;
1404		ptq->last_br_insn_cnt = ptq->ipc_insn_cnt;
1405		ptq->last_br_cyc_cnt = ptq->ipc_cyc_cnt;
1406	}
1407
1408	return intel_pt_deliver_synth_event(pt, event, &sample,
1409					    pt->branches_sample_type);
1410}
1411
1412static void intel_pt_prep_sample(struct intel_pt *pt,
1413				 struct intel_pt_queue *ptq,
1414				 union perf_event *event,
1415				 struct perf_sample *sample)
1416{
1417	intel_pt_prep_b_sample(pt, ptq, event, sample);
1418
1419	if (pt->synth_opts.callchain) {
1420		thread_stack__sample(ptq->thread, ptq->cpu, ptq->chain,
1421				     pt->synth_opts.callchain_sz + 1,
1422				     sample->ip, pt->kernel_start);
1423		sample->callchain = ptq->chain;
1424	}
1425
1426	if (pt->synth_opts.last_branch) {
1427		thread_stack__br_sample(ptq->thread, ptq->cpu, ptq->last_branch,
1428					pt->br_stack_sz);
1429		sample->branch_stack = ptq->last_branch;
1430	}
1431}
1432
1433static int intel_pt_synth_instruction_sample(struct intel_pt_queue *ptq)
1434{
1435	struct intel_pt *pt = ptq->pt;
1436	union perf_event *event = ptq->event_buf;
1437	struct perf_sample sample = { .ip = 0, };
1438
1439	if (intel_pt_skip_event(pt))
1440		return 0;
1441
1442	intel_pt_prep_sample(pt, ptq, event, &sample);
1443
1444	sample.id = ptq->pt->instructions_id;
1445	sample.stream_id = ptq->pt->instructions_id;
1446	if (pt->synth_opts.quick)
1447		sample.period = 1;
1448	else
1449		sample.period = ptq->state->tot_insn_cnt - ptq->last_insn_cnt;
1450
1451	if (ptq->state->flags & INTEL_PT_SAMPLE_IPC)
1452		sample.cyc_cnt = ptq->ipc_cyc_cnt - ptq->last_in_cyc_cnt;
1453	if (sample.cyc_cnt) {
1454		sample.insn_cnt = ptq->ipc_insn_cnt - ptq->last_in_insn_cnt;
1455		ptq->last_in_insn_cnt = ptq->ipc_insn_cnt;
1456		ptq->last_in_cyc_cnt = ptq->ipc_cyc_cnt;
1457	}
1458
1459	ptq->last_insn_cnt = ptq->state->tot_insn_cnt;
1460
1461	return intel_pt_deliver_synth_event(pt, event, &sample,
1462					    pt->instructions_sample_type);
1463}
1464
1465static int intel_pt_synth_transaction_sample(struct intel_pt_queue *ptq)
1466{
1467	struct intel_pt *pt = ptq->pt;
1468	union perf_event *event = ptq->event_buf;
1469	struct perf_sample sample = { .ip = 0, };
1470
1471	if (intel_pt_skip_event(pt))
1472		return 0;
1473
1474	intel_pt_prep_sample(pt, ptq, event, &sample);
1475
1476	sample.id = ptq->pt->transactions_id;
1477	sample.stream_id = ptq->pt->transactions_id;
1478
1479	return intel_pt_deliver_synth_event(pt, event, &sample,
1480					    pt->transactions_sample_type);
1481}
1482
1483static void intel_pt_prep_p_sample(struct intel_pt *pt,
1484				   struct intel_pt_queue *ptq,
1485				   union perf_event *event,
1486				   struct perf_sample *sample)
1487{
1488	intel_pt_prep_sample(pt, ptq, event, sample);
1489
1490	/*
1491	 * Zero IP is used to mean "trace start" but that is not the case for
1492	 * power or PTWRITE events with no IP, so clear the flags.
1493	 */
1494	if (!sample->ip)
1495		sample->flags = 0;
1496}
1497
1498static int intel_pt_synth_ptwrite_sample(struct intel_pt_queue *ptq)
1499{
1500	struct intel_pt *pt = ptq->pt;
1501	union perf_event *event = ptq->event_buf;
1502	struct perf_sample sample = { .ip = 0, };
1503	struct perf_synth_intel_ptwrite raw;
1504
1505	if (intel_pt_skip_event(pt))
1506		return 0;
1507
1508	intel_pt_prep_p_sample(pt, ptq, event, &sample);
1509
1510	sample.id = ptq->pt->ptwrites_id;
1511	sample.stream_id = ptq->pt->ptwrites_id;
1512
1513	raw.flags = 0;
1514	raw.ip = !!(ptq->state->flags & INTEL_PT_FUP_IP);
1515	raw.payload = cpu_to_le64(ptq->state->ptw_payload);
1516
1517	sample.raw_size = perf_synth__raw_size(raw);
1518	sample.raw_data = perf_synth__raw_data(&raw);
1519
1520	return intel_pt_deliver_synth_event(pt, event, &sample,
1521					    pt->ptwrites_sample_type);
1522}
1523
1524static int intel_pt_synth_cbr_sample(struct intel_pt_queue *ptq)
1525{
1526	struct intel_pt *pt = ptq->pt;
1527	union perf_event *event = ptq->event_buf;
1528	struct perf_sample sample = { .ip = 0, };
1529	struct perf_synth_intel_cbr raw;
1530	u32 flags;
1531
1532	if (intel_pt_skip_cbr_event(pt))
1533		return 0;
1534
1535	ptq->cbr_seen = ptq->state->cbr;
1536
1537	intel_pt_prep_p_sample(pt, ptq, event, &sample);
1538
1539	sample.id = ptq->pt->cbr_id;
1540	sample.stream_id = ptq->pt->cbr_id;
1541
1542	flags = (u16)ptq->state->cbr_payload | (pt->max_non_turbo_ratio << 16);
1543	raw.flags = cpu_to_le32(flags);
1544	raw.freq = cpu_to_le32(raw.cbr * pt->cbr2khz);
1545	raw.reserved3 = 0;
1546
1547	sample.raw_size = perf_synth__raw_size(raw);
1548	sample.raw_data = perf_synth__raw_data(&raw);
1549
1550	return intel_pt_deliver_synth_event(pt, event, &sample,
1551					    pt->pwr_events_sample_type);
1552}
1553
1554static int intel_pt_synth_mwait_sample(struct intel_pt_queue *ptq)
1555{
1556	struct intel_pt *pt = ptq->pt;
1557	union perf_event *event = ptq->event_buf;
1558	struct perf_sample sample = { .ip = 0, };
1559	struct perf_synth_intel_mwait raw;
1560
1561	if (intel_pt_skip_event(pt))
1562		return 0;
1563
1564	intel_pt_prep_p_sample(pt, ptq, event, &sample);
1565
1566	sample.id = ptq->pt->mwait_id;
1567	sample.stream_id = ptq->pt->mwait_id;
1568
1569	raw.reserved = 0;
1570	raw.payload = cpu_to_le64(ptq->state->mwait_payload);
1571
1572	sample.raw_size = perf_synth__raw_size(raw);
1573	sample.raw_data = perf_synth__raw_data(&raw);
1574
1575	return intel_pt_deliver_synth_event(pt, event, &sample,
1576					    pt->pwr_events_sample_type);
1577}
1578
1579static int intel_pt_synth_pwre_sample(struct intel_pt_queue *ptq)
1580{
1581	struct intel_pt *pt = ptq->pt;
1582	union perf_event *event = ptq->event_buf;
1583	struct perf_sample sample = { .ip = 0, };
1584	struct perf_synth_intel_pwre raw;
1585
1586	if (intel_pt_skip_event(pt))
1587		return 0;
1588
1589	intel_pt_prep_p_sample(pt, ptq, event, &sample);
1590
1591	sample.id = ptq->pt->pwre_id;
1592	sample.stream_id = ptq->pt->pwre_id;
1593
1594	raw.reserved = 0;
1595	raw.payload = cpu_to_le64(ptq->state->pwre_payload);
1596
1597	sample.raw_size = perf_synth__raw_size(raw);
1598	sample.raw_data = perf_synth__raw_data(&raw);
1599
1600	return intel_pt_deliver_synth_event(pt, event, &sample,
1601					    pt->pwr_events_sample_type);
1602}
1603
1604static int intel_pt_synth_exstop_sample(struct intel_pt_queue *ptq)
1605{
1606	struct intel_pt *pt = ptq->pt;
1607	union perf_event *event = ptq->event_buf;
1608	struct perf_sample sample = { .ip = 0, };
1609	struct perf_synth_intel_exstop raw;
1610
1611	if (intel_pt_skip_event(pt))
1612		return 0;
1613
1614	intel_pt_prep_p_sample(pt, ptq, event, &sample);
1615
1616	sample.id = ptq->pt->exstop_id;
1617	sample.stream_id = ptq->pt->exstop_id;
1618
1619	raw.flags = 0;
1620	raw.ip = !!(ptq->state->flags & INTEL_PT_FUP_IP);
1621
1622	sample.raw_size = perf_synth__raw_size(raw);
1623	sample.raw_data = perf_synth__raw_data(&raw);
1624
1625	return intel_pt_deliver_synth_event(pt, event, &sample,
1626					    pt->pwr_events_sample_type);
1627}
1628
1629static int intel_pt_synth_pwrx_sample(struct intel_pt_queue *ptq)
1630{
1631	struct intel_pt *pt = ptq->pt;
1632	union perf_event *event = ptq->event_buf;
1633	struct perf_sample sample = { .ip = 0, };
1634	struct perf_synth_intel_pwrx raw;
1635
1636	if (intel_pt_skip_event(pt))
1637		return 0;
1638
1639	intel_pt_prep_p_sample(pt, ptq, event, &sample);
1640
1641	sample.id = ptq->pt->pwrx_id;
1642	sample.stream_id = ptq->pt->pwrx_id;
1643
1644	raw.reserved = 0;
1645	raw.payload = cpu_to_le64(ptq->state->pwrx_payload);
1646
1647	sample.raw_size = perf_synth__raw_size(raw);
1648	sample.raw_data = perf_synth__raw_data(&raw);
1649
1650	return intel_pt_deliver_synth_event(pt, event, &sample,
1651					    pt->pwr_events_sample_type);
1652}
1653
1654/*
1655 * PEBS gp_regs array indexes plus 1 so that 0 means not present. Refer
1656 * intel_pt_add_gp_regs().
1657 */
1658static const int pebs_gp_regs[] = {
1659	[PERF_REG_X86_FLAGS]	= 1,
1660	[PERF_REG_X86_IP]	= 2,
1661	[PERF_REG_X86_AX]	= 3,
1662	[PERF_REG_X86_CX]	= 4,
1663	[PERF_REG_X86_DX]	= 5,
1664	[PERF_REG_X86_BX]	= 6,
1665	[PERF_REG_X86_SP]	= 7,
1666	[PERF_REG_X86_BP]	= 8,
1667	[PERF_REG_X86_SI]	= 9,
1668	[PERF_REG_X86_DI]	= 10,
1669	[PERF_REG_X86_R8]	= 11,
1670	[PERF_REG_X86_R9]	= 12,
1671	[PERF_REG_X86_R10]	= 13,
1672	[PERF_REG_X86_R11]	= 14,
1673	[PERF_REG_X86_R12]	= 15,
1674	[PERF_REG_X86_R13]	= 16,
1675	[PERF_REG_X86_R14]	= 17,
1676	[PERF_REG_X86_R15]	= 18,
1677};
1678
1679static u64 *intel_pt_add_gp_regs(struct regs_dump *intr_regs, u64 *pos,
1680				 const struct intel_pt_blk_items *items,
1681				 u64 regs_mask)
1682{
1683	const u64 *gp_regs = items->val[INTEL_PT_GP_REGS_POS];
1684	u32 mask = items->mask[INTEL_PT_GP_REGS_POS];
1685	u32 bit;
1686	int i;
1687
1688	for (i = 0, bit = 1; i < PERF_REG_X86_64_MAX; i++, bit <<= 1) {
1689		/* Get the PEBS gp_regs array index */
1690		int n = pebs_gp_regs[i] - 1;
1691
1692		if (n < 0)
1693			continue;
1694		/*
1695		 * Add only registers that were requested (i.e. 'regs_mask') and
1696		 * that were provided (i.e. 'mask'), and update the resulting
1697		 * mask (i.e. 'intr_regs->mask') accordingly.
1698		 */
1699		if (mask & 1 << n && regs_mask & bit) {
1700			intr_regs->mask |= bit;
1701			*pos++ = gp_regs[n];
1702		}
1703	}
1704
1705	return pos;
1706}
1707
1708#ifndef PERF_REG_X86_XMM0
1709#define PERF_REG_X86_XMM0 32
1710#endif
1711
1712static void intel_pt_add_xmm(struct regs_dump *intr_regs, u64 *pos,
1713			     const struct intel_pt_blk_items *items,
1714			     u64 regs_mask)
1715{
1716	u32 mask = items->has_xmm & (regs_mask >> PERF_REG_X86_XMM0);
1717	const u64 *xmm = items->xmm;
1718
1719	/*
1720	 * If there are any XMM registers, then there should be all of them.
1721	 * Nevertheless, follow the logic to add only registers that were
1722	 * requested (i.e. 'regs_mask') and that were provided (i.e. 'mask'),
1723	 * and update the resulting mask (i.e. 'intr_regs->mask') accordingly.
1724	 */
1725	intr_regs->mask |= (u64)mask << PERF_REG_X86_XMM0;
1726
1727	for (; mask; mask >>= 1, xmm++) {
1728		if (mask & 1)
1729			*pos++ = *xmm;
1730	}
1731}
1732
1733#define LBR_INFO_MISPRED	(1ULL << 63)
1734#define LBR_INFO_IN_TX		(1ULL << 62)
1735#define LBR_INFO_ABORT		(1ULL << 61)
1736#define LBR_INFO_CYCLES		0xffff
1737
1738/* Refer kernel's intel_pmu_store_pebs_lbrs() */
1739static u64 intel_pt_lbr_flags(u64 info)
1740{
1741	union {
1742		struct branch_flags flags;
1743		u64 result;
1744	} u;
1745
1746	u.result	  = 0;
1747	u.flags.mispred	  = !!(info & LBR_INFO_MISPRED);
1748	u.flags.predicted = !(info & LBR_INFO_MISPRED);
1749	u.flags.in_tx	  = !!(info & LBR_INFO_IN_TX);
1750	u.flags.abort	  = !!(info & LBR_INFO_ABORT);
1751	u.flags.cycles	  = info & LBR_INFO_CYCLES;
1752
1753	return u.result;
1754}
1755
1756static void intel_pt_add_lbrs(struct branch_stack *br_stack,
1757			      const struct intel_pt_blk_items *items)
1758{
1759	u64 *to;
1760	int i;
1761
1762	br_stack->nr = 0;
1763
1764	to = &br_stack->entries[0].from;
1765
1766	for (i = INTEL_PT_LBR_0_POS; i <= INTEL_PT_LBR_2_POS; i++) {
1767		u32 mask = items->mask[i];
1768		const u64 *from = items->val[i];
1769
1770		for (; mask; mask >>= 3, from += 3) {
1771			if ((mask & 7) == 7) {
1772				*to++ = from[0];
1773				*to++ = from[1];
1774				*to++ = intel_pt_lbr_flags(from[2]);
1775				br_stack->nr += 1;
1776			}
1777		}
1778	}
1779}
1780
1781static int intel_pt_synth_pebs_sample(struct intel_pt_queue *ptq)
1782{
1783	const struct intel_pt_blk_items *items = &ptq->state->items;
1784	struct perf_sample sample = { .ip = 0, };
1785	union perf_event *event = ptq->event_buf;
1786	struct intel_pt *pt = ptq->pt;
1787	struct evsel *evsel = pt->pebs_evsel;
1788	u64 sample_type = evsel->core.attr.sample_type;
1789	u64 id = evsel->core.id[0];
1790	u8 cpumode;
1791	u64 regs[8 * sizeof(sample.intr_regs.mask)];
1792
1793	if (intel_pt_skip_event(pt))
1794		return 0;
1795
1796	intel_pt_prep_a_sample(ptq, event, &sample);
1797
1798	sample.id = id;
1799	sample.stream_id = id;
1800
1801	if (!evsel->core.attr.freq)
1802		sample.period = evsel->core.attr.sample_period;
1803
1804	/* No support for non-zero CS base */
1805	if (items->has_ip)
1806		sample.ip = items->ip;
1807	else if (items->has_rip)
1808		sample.ip = items->rip;
1809	else
1810		sample.ip = ptq->state->from_ip;
1811
1812	/* No support for guest mode at this time */
1813	cpumode = sample.ip < ptq->pt->kernel_start ?
1814		  PERF_RECORD_MISC_USER :
1815		  PERF_RECORD_MISC_KERNEL;
1816
1817	event->sample.header.misc = cpumode | PERF_RECORD_MISC_EXACT_IP;
1818
1819	sample.cpumode = cpumode;
1820
1821	if (sample_type & PERF_SAMPLE_TIME) {
1822		u64 timestamp = 0;
1823
1824		if (items->has_timestamp)
1825			timestamp = items->timestamp;
1826		else if (!pt->timeless_decoding)
1827			timestamp = ptq->timestamp;
1828		if (timestamp)
1829			sample.time = tsc_to_perf_time(timestamp, &pt->tc);
1830	}
1831
1832	if (sample_type & PERF_SAMPLE_CALLCHAIN &&
1833	    pt->synth_opts.callchain) {
1834		thread_stack__sample(ptq->thread, ptq->cpu, ptq->chain,
1835				     pt->synth_opts.callchain_sz, sample.ip,
1836				     pt->kernel_start);
1837		sample.callchain = ptq->chain;
1838	}
1839
1840	if (sample_type & PERF_SAMPLE_REGS_INTR &&
1841	    (items->mask[INTEL_PT_GP_REGS_POS] ||
1842	     items->mask[INTEL_PT_XMM_POS])) {
1843		u64 regs_mask = evsel->core.attr.sample_regs_intr;
1844		u64 *pos;
1845
1846		sample.intr_regs.abi = items->is_32_bit ?
1847				       PERF_SAMPLE_REGS_ABI_32 :
1848				       PERF_SAMPLE_REGS_ABI_64;
1849		sample.intr_regs.regs = regs;
1850
1851		pos = intel_pt_add_gp_regs(&sample.intr_regs, regs, items, regs_mask);
1852
1853		intel_pt_add_xmm(&sample.intr_regs, pos, items, regs_mask);
1854	}
1855
1856	if (sample_type & PERF_SAMPLE_BRANCH_STACK) {
1857		if (items->mask[INTEL_PT_LBR_0_POS] ||
1858		    items->mask[INTEL_PT_LBR_1_POS] ||
1859		    items->mask[INTEL_PT_LBR_2_POS]) {
1860			intel_pt_add_lbrs(ptq->last_branch, items);
1861		} else if (pt->synth_opts.last_branch) {
1862			thread_stack__br_sample(ptq->thread, ptq->cpu,
1863						ptq->last_branch,
1864						pt->br_stack_sz);
1865		} else {
1866			ptq->last_branch->nr = 0;
1867		}
1868		sample.branch_stack = ptq->last_branch;
1869	}
1870
1871	if (sample_type & PERF_SAMPLE_ADDR && items->has_mem_access_address)
1872		sample.addr = items->mem_access_address;
1873
1874	if (sample_type & PERF_SAMPLE_WEIGHT) {
1875		/*
1876		 * Refer kernel's setup_pebs_adaptive_sample_data() and
1877		 * intel_hsw_weight().
1878		 */
1879		if (items->has_mem_access_latency)
1880			sample.weight = items->mem_access_latency;
1881		if (!sample.weight && items->has_tsx_aux_info) {
1882			/* Cycles last block */
1883			sample.weight = (u32)items->tsx_aux_info;
1884		}
1885	}
1886
1887	if (sample_type & PERF_SAMPLE_TRANSACTION && items->has_tsx_aux_info) {
1888		u64 ax = items->has_rax ? items->rax : 0;
1889		/* Refer kernel's intel_hsw_transaction() */
1890		u64 txn = (u8)(items->tsx_aux_info >> 32);
1891
1892		/* For RTM XABORTs also log the abort code from AX */
1893		if (txn & PERF_TXN_TRANSACTION && ax & 1)
1894			txn |= ((ax >> 24) & 0xff) << PERF_TXN_ABORT_SHIFT;
1895		sample.transaction = txn;
1896	}
1897
1898	return intel_pt_deliver_synth_event(pt, event, &sample, sample_type);
1899}
1900
1901static int intel_pt_synth_error(struct intel_pt *pt, int code, int cpu,
1902				pid_t pid, pid_t tid, u64 ip, u64 timestamp)
1903{
1904	union perf_event event;
1905	char msg[MAX_AUXTRACE_ERROR_MSG];
1906	int err;
1907
1908	if (pt->synth_opts.error_minus_flags) {
1909		if (code == INTEL_PT_ERR_OVR &&
1910		    pt->synth_opts.error_minus_flags & AUXTRACE_ERR_FLG_OVERFLOW)
1911			return 0;
1912		if (code == INTEL_PT_ERR_LOST &&
1913		    pt->synth_opts.error_minus_flags & AUXTRACE_ERR_FLG_DATA_LOST)
1914			return 0;
1915	}
1916
1917	intel_pt__strerror(code, msg, MAX_AUXTRACE_ERROR_MSG);
1918
1919	auxtrace_synth_error(&event.auxtrace_error, PERF_AUXTRACE_ERROR_ITRACE,
1920			     code, cpu, pid, tid, ip, msg, timestamp);
1921
1922	err = perf_session__deliver_synth_event(pt->session, &event, NULL);
1923	if (err)
1924		pr_err("Intel Processor Trace: failed to deliver error event, error %d\n",
1925		       err);
1926
1927	return err;
1928}
1929
1930static int intel_ptq_synth_error(struct intel_pt_queue *ptq,
1931				 const struct intel_pt_state *state)
1932{
1933	struct intel_pt *pt = ptq->pt;
1934	u64 tm = ptq->timestamp;
1935
1936	tm = pt->timeless_decoding ? 0 : tsc_to_perf_time(tm, &pt->tc);
1937
1938	return intel_pt_synth_error(pt, state->err, ptq->cpu, ptq->pid,
1939				    ptq->tid, state->from_ip, tm);
1940}
1941
1942static int intel_pt_next_tid(struct intel_pt *pt, struct intel_pt_queue *ptq)
1943{
1944	struct auxtrace_queue *queue;
1945	pid_t tid = ptq->next_tid;
1946	int err;
1947
1948	if (tid == -1)
1949		return 0;
1950
1951	intel_pt_log("switch: cpu %d tid %d\n", ptq->cpu, tid);
1952
1953	err = machine__set_current_tid(pt->machine, ptq->cpu, -1, tid);
1954
1955	queue = &pt->queues.queue_array[ptq->queue_nr];
1956	intel_pt_set_pid_tid_cpu(pt, queue);
1957
1958	ptq->next_tid = -1;
1959
1960	return err;
1961}
1962
1963static inline bool intel_pt_is_switch_ip(struct intel_pt_queue *ptq, u64 ip)
1964{
1965	struct intel_pt *pt = ptq->pt;
1966
1967	return ip == pt->switch_ip &&
1968	       (ptq->flags & PERF_IP_FLAG_BRANCH) &&
1969	       !(ptq->flags & (PERF_IP_FLAG_CONDITIONAL | PERF_IP_FLAG_ASYNC |
1970			       PERF_IP_FLAG_INTERRUPT | PERF_IP_FLAG_TX_ABORT));
1971}
1972
1973#define INTEL_PT_PWR_EVT (INTEL_PT_MWAIT_OP | INTEL_PT_PWR_ENTRY | \
1974			  INTEL_PT_EX_STOP | INTEL_PT_PWR_EXIT)
1975
1976static int intel_pt_sample(struct intel_pt_queue *ptq)
1977{
1978	const struct intel_pt_state *state = ptq->state;
1979	struct intel_pt *pt = ptq->pt;
1980	int err;
1981
1982	if (!ptq->have_sample)
1983		return 0;
1984
1985	ptq->have_sample = false;
1986
1987	ptq->ipc_insn_cnt = ptq->state->tot_insn_cnt;
1988	ptq->ipc_cyc_cnt = ptq->state->tot_cyc_cnt;
1989
1990	/*
1991	 * Do PEBS first to allow for the possibility that the PEBS timestamp
1992	 * precedes the current timestamp.
1993	 */
1994	if (pt->sample_pebs && state->type & INTEL_PT_BLK_ITEMS) {
1995		err = intel_pt_synth_pebs_sample(ptq);
1996		if (err)
1997			return err;
1998	}
1999
2000	if (pt->sample_pwr_events) {
2001		if (ptq->state->cbr != ptq->cbr_seen) {
2002			err = intel_pt_synth_cbr_sample(ptq);
2003			if (err)
2004				return err;
2005		}
2006		if (state->type & INTEL_PT_PWR_EVT) {
2007			if (state->type & INTEL_PT_MWAIT_OP) {
2008				err = intel_pt_synth_mwait_sample(ptq);
2009				if (err)
2010					return err;
2011			}
2012			if (state->type & INTEL_PT_PWR_ENTRY) {
2013				err = intel_pt_synth_pwre_sample(ptq);
2014				if (err)
2015					return err;
2016			}
2017			if (state->type & INTEL_PT_EX_STOP) {
2018				err = intel_pt_synth_exstop_sample(ptq);
2019				if (err)
2020					return err;
2021			}
2022			if (state->type & INTEL_PT_PWR_EXIT) {
2023				err = intel_pt_synth_pwrx_sample(ptq);
2024				if (err)
2025					return err;
2026			}
2027		}
2028	}
2029
2030	if (pt->sample_instructions && (state->type & INTEL_PT_INSTRUCTION)) {
2031		err = intel_pt_synth_instruction_sample(ptq);
2032		if (err)
2033			return err;
2034	}
2035
2036	if (pt->sample_transactions && (state->type & INTEL_PT_TRANSACTION)) {
2037		err = intel_pt_synth_transaction_sample(ptq);
2038		if (err)
2039			return err;
2040	}
2041
2042	if (pt->sample_ptwrites && (state->type & INTEL_PT_PTW)) {
2043		err = intel_pt_synth_ptwrite_sample(ptq);
2044		if (err)
2045			return err;
2046	}
2047
2048	if (!(state->type & INTEL_PT_BRANCH))
2049		return 0;
2050
2051	if (pt->use_thread_stack) {
2052		thread_stack__event(ptq->thread, ptq->cpu, ptq->flags,
2053				    state->from_ip, state->to_ip, ptq->insn_len,
2054				    state->trace_nr, pt->callstack,
2055				    pt->br_stack_sz_plus,
2056				    pt->mispred_all);
2057	} else {
2058		thread_stack__set_trace_nr(ptq->thread, ptq->cpu, state->trace_nr);
2059	}
2060
2061	if (pt->sample_branches) {
2062		err = intel_pt_synth_branch_sample(ptq);
2063		if (err)
2064			return err;
2065	}
2066
2067	if (!ptq->sync_switch)
2068		return 0;
2069
2070	if (intel_pt_is_switch_ip(ptq, state->to_ip)) {
2071		switch (ptq->switch_state) {
2072		case INTEL_PT_SS_NOT_TRACING:
2073		case INTEL_PT_SS_UNKNOWN:
2074		case INTEL_PT_SS_EXPECTING_SWITCH_IP:
2075			err = intel_pt_next_tid(pt, ptq);
2076			if (err)
2077				return err;
2078			ptq->switch_state = INTEL_PT_SS_TRACING;
2079			break;
2080		default:
2081			ptq->switch_state = INTEL_PT_SS_EXPECTING_SWITCH_EVENT;
2082			return 1;
2083		}
2084	} else if (!state->to_ip) {
2085		ptq->switch_state = INTEL_PT_SS_NOT_TRACING;
2086	} else if (ptq->switch_state == INTEL_PT_SS_NOT_TRACING) {
2087		ptq->switch_state = INTEL_PT_SS_UNKNOWN;
2088	} else if (ptq->switch_state == INTEL_PT_SS_UNKNOWN &&
2089		   state->to_ip == pt->ptss_ip &&
2090		   (ptq->flags & PERF_IP_FLAG_CALL)) {
2091		ptq->switch_state = INTEL_PT_SS_TRACING;
2092	}
2093
2094	return 0;
2095}
2096
2097static u64 intel_pt_switch_ip(struct intel_pt *pt, u64 *ptss_ip)
2098{
2099	struct machine *machine = pt->machine;
2100	struct map *map;
2101	struct symbol *sym, *start;
2102	u64 ip, switch_ip = 0;
2103	const char *ptss;
2104
2105	if (ptss_ip)
2106		*ptss_ip = 0;
2107
2108	map = machine__kernel_map(machine);
2109	if (!map)
2110		return 0;
2111
2112	if (map__load(map))
2113		return 0;
2114
2115	start = dso__first_symbol(map->dso);
2116
2117	for (sym = start; sym; sym = dso__next_symbol(sym)) {
2118		if (sym->binding == STB_GLOBAL &&
2119		    !strcmp(sym->name, "__switch_to")) {
2120			ip = map->unmap_ip(map, sym->start);
2121			if (ip >= map->start && ip < map->end) {
2122				switch_ip = ip;
2123				break;
2124			}
2125		}
2126	}
2127
2128	if (!switch_ip || !ptss_ip)
2129		return 0;
2130
2131	if (pt->have_sched_switch == 1)
2132		ptss = "perf_trace_sched_switch";
2133	else
2134		ptss = "__perf_event_task_sched_out";
2135
2136	for (sym = start; sym; sym = dso__next_symbol(sym)) {
2137		if (!strcmp(sym->name, ptss)) {
2138			ip = map->unmap_ip(map, sym->start);
2139			if (ip >= map->start && ip < map->end) {
2140				*ptss_ip = ip;
2141				break;
2142			}
2143		}
2144	}
2145
2146	return switch_ip;
2147}
2148
2149static void intel_pt_enable_sync_switch(struct intel_pt *pt)
2150{
2151	unsigned int i;
2152
2153	pt->sync_switch = true;
2154
2155	for (i = 0; i < pt->queues.nr_queues; i++) {
2156		struct auxtrace_queue *queue = &pt->queues.queue_array[i];
2157		struct intel_pt_queue *ptq = queue->priv;
2158
2159		if (ptq)
2160			ptq->sync_switch = true;
2161	}
2162}
2163
2164/*
2165 * To filter against time ranges, it is only necessary to look at the next start
2166 * or end time.
2167 */
2168static bool intel_pt_next_time(struct intel_pt_queue *ptq)
2169{
2170	struct intel_pt *pt = ptq->pt;
2171
2172	if (ptq->sel_start) {
2173		/* Next time is an end time */
2174		ptq->sel_start = false;
2175		ptq->sel_timestamp = pt->time_ranges[ptq->sel_idx].end;
2176		return true;
2177	} else if (ptq->sel_idx + 1 < pt->range_cnt) {
2178		/* Next time is a start time */
2179		ptq->sel_start = true;
2180		ptq->sel_idx += 1;
2181		ptq->sel_timestamp = pt->time_ranges[ptq->sel_idx].start;
2182		return true;
2183	}
2184
2185	/* No next time */
2186	return false;
2187}
2188
2189static int intel_pt_time_filter(struct intel_pt_queue *ptq, u64 *ff_timestamp)
2190{
2191	int err;
2192
2193	while (1) {
2194		if (ptq->sel_start) {
2195			if (ptq->timestamp >= ptq->sel_timestamp) {
2196				/* After start time, so consider next time */
2197				intel_pt_next_time(ptq);
2198				if (!ptq->sel_timestamp) {
2199					/* No end time */
2200					return 0;
2201				}
2202				/* Check against end time */
2203				continue;
2204			}
2205			/* Before start time, so fast forward */
2206			ptq->have_sample = false;
2207			if (ptq->sel_timestamp > *ff_timestamp) {
2208				if (ptq->sync_switch) {
2209					intel_pt_next_tid(ptq->pt, ptq);
2210					ptq->switch_state = INTEL_PT_SS_UNKNOWN;
2211				}
2212				*ff_timestamp = ptq->sel_timestamp;
2213				err = intel_pt_fast_forward(ptq->decoder,
2214							    ptq->sel_timestamp);
2215				if (err)
2216					return err;
2217			}
2218			return 0;
2219		} else if (ptq->timestamp > ptq->sel_timestamp) {
2220			/* After end time, so consider next time */
2221			if (!intel_pt_next_time(ptq)) {
2222				/* No next time range, so stop decoding */
2223				ptq->have_sample = false;
2224				ptq->switch_state = INTEL_PT_SS_NOT_TRACING;
2225				return 1;
2226			}
2227			/* Check against next start time */
2228			continue;
2229		} else {
2230			/* Before end time */
2231			return 0;
2232		}
2233	}
2234}
2235
2236static int intel_pt_run_decoder(struct intel_pt_queue *ptq, u64 *timestamp)
2237{
2238	const struct intel_pt_state *state = ptq->state;
2239	struct intel_pt *pt = ptq->pt;
2240	u64 ff_timestamp = 0;
2241	int err;
2242
2243	if (!pt->kernel_start) {
2244		pt->kernel_start = machine__kernel_start(pt->machine);
2245		if (pt->per_cpu_mmaps &&
2246		    (pt->have_sched_switch == 1 || pt->have_sched_switch == 3) &&
2247		    !pt->timeless_decoding && intel_pt_tracing_kernel(pt) &&
2248		    !pt->sampling_mode) {
2249			pt->switch_ip = intel_pt_switch_ip(pt, &pt->ptss_ip);
2250			if (pt->switch_ip) {
2251				intel_pt_log("switch_ip: %"PRIx64" ptss_ip: %"PRIx64"\n",
2252					     pt->switch_ip, pt->ptss_ip);
2253				intel_pt_enable_sync_switch(pt);
2254			}
2255		}
2256	}
2257
2258	intel_pt_log("queue %u decoding cpu %d pid %d tid %d\n",
2259		     ptq->queue_nr, ptq->cpu, ptq->pid, ptq->tid);
2260	while (1) {
2261		err = intel_pt_sample(ptq);
2262		if (err)
2263			return err;
2264
2265		state = intel_pt_decode(ptq->decoder);
2266		if (state->err) {
2267			if (state->err == INTEL_PT_ERR_NODATA)
2268				return 1;
2269			if (ptq->sync_switch &&
2270			    state->from_ip >= pt->kernel_start) {
2271				ptq->sync_switch = false;
2272				intel_pt_next_tid(pt, ptq);
2273			}
2274			ptq->timestamp = state->est_timestamp;
2275			if (pt->synth_opts.errors) {
2276				err = intel_ptq_synth_error(ptq, state);
2277				if (err)
2278					return err;
2279			}
2280			continue;
2281		}
2282
2283		ptq->state = state;
2284		ptq->have_sample = true;
2285		intel_pt_sample_flags(ptq);
2286
2287		/* Use estimated TSC upon return to user space */
2288		if (pt->est_tsc &&
2289		    (state->from_ip >= pt->kernel_start || !state->from_ip) &&
2290		    state->to_ip && state->to_ip < pt->kernel_start) {
2291			intel_pt_log("TSC %"PRIx64" est. TSC %"PRIx64"\n",
2292				     state->timestamp, state->est_timestamp);
2293			ptq->timestamp = state->est_timestamp;
2294		/* Use estimated TSC in unknown switch state */
2295		} else if (ptq->sync_switch &&
2296			   ptq->switch_state == INTEL_PT_SS_UNKNOWN &&
2297			   intel_pt_is_switch_ip(ptq, state->to_ip) &&
2298			   ptq->next_tid == -1) {
2299			intel_pt_log("TSC %"PRIx64" est. TSC %"PRIx64"\n",
2300				     state->timestamp, state->est_timestamp);
2301			ptq->timestamp = state->est_timestamp;
2302		} else if (state->timestamp > ptq->timestamp) {
2303			ptq->timestamp = state->timestamp;
2304		}
2305
2306		if (ptq->sel_timestamp) {
2307			err = intel_pt_time_filter(ptq, &ff_timestamp);
2308			if (err)
2309				return err;
2310		}
2311
2312		if (!pt->timeless_decoding && ptq->timestamp >= *timestamp) {
2313			*timestamp = ptq->timestamp;
2314			return 0;
2315		}
2316	}
2317	return 0;
2318}
2319
2320static inline int intel_pt_update_queues(struct intel_pt *pt)
2321{
2322	if (pt->queues.new_data) {
2323		pt->queues.new_data = false;
2324		return intel_pt_setup_queues(pt);
2325	}
2326	return 0;
2327}
2328
2329static int intel_pt_process_queues(struct intel_pt *pt, u64 timestamp)
2330{
2331	unsigned int queue_nr;
2332	u64 ts;
2333	int ret;
2334
2335	while (1) {
2336		struct auxtrace_queue *queue;
2337		struct intel_pt_queue *ptq;
2338
2339		if (!pt->heap.heap_cnt)
2340			return 0;
2341
2342		if (pt->heap.heap_array[0].ordinal >= timestamp)
2343			return 0;
2344
2345		queue_nr = pt->heap.heap_array[0].queue_nr;
2346		queue = &pt->queues.queue_array[queue_nr];
2347		ptq = queue->priv;
2348
2349		intel_pt_log("queue %u processing 0x%" PRIx64 " to 0x%" PRIx64 "\n",
2350			     queue_nr, pt->heap.heap_array[0].ordinal,
2351			     timestamp);
2352
2353		auxtrace_heap__pop(&pt->heap);
2354
2355		if (pt->heap.heap_cnt) {
2356			ts = pt->heap.heap_array[0].ordinal + 1;
2357			if (ts > timestamp)
2358				ts = timestamp;
2359		} else {
2360			ts = timestamp;
2361		}
2362
2363		intel_pt_set_pid_tid_cpu(pt, queue);
2364
2365		ret = intel_pt_run_decoder(ptq, &ts);
2366
2367		if (ret < 0) {
2368			auxtrace_heap__add(&pt->heap, queue_nr, ts);
2369			return ret;
2370		}
2371
2372		if (!ret) {
2373			ret = auxtrace_heap__add(&pt->heap, queue_nr, ts);
2374			if (ret < 0)
2375				return ret;
2376		} else {
2377			ptq->on_heap = false;
2378		}
2379	}
2380
2381	return 0;
2382}
2383
2384static int intel_pt_process_timeless_queues(struct intel_pt *pt, pid_t tid,
2385					    u64 time_)
2386{
2387	struct auxtrace_queues *queues = &pt->queues;
2388	unsigned int i;
2389	u64 ts = 0;
2390
2391	for (i = 0; i < queues->nr_queues; i++) {
2392		struct auxtrace_queue *queue = &pt->queues.queue_array[i];
2393		struct intel_pt_queue *ptq = queue->priv;
2394
2395		if (ptq && (tid == -1 || ptq->tid == tid)) {
2396			ptq->time = time_;
2397			intel_pt_set_pid_tid_cpu(pt, queue);
2398			intel_pt_run_decoder(ptq, &ts);
2399		}
2400	}
2401	return 0;
2402}
2403
2404static void intel_pt_sample_set_pid_tid_cpu(struct intel_pt_queue *ptq,
2405					    struct auxtrace_queue *queue,
2406					    struct perf_sample *sample)
2407{
2408	struct machine *m = ptq->pt->machine;
2409
2410	ptq->pid = sample->pid;
2411	ptq->tid = sample->tid;
2412	ptq->cpu = queue->cpu;
2413
2414	intel_pt_log("queue %u cpu %d pid %d tid %d\n",
2415		     ptq->queue_nr, ptq->cpu, ptq->pid, ptq->tid);
2416
2417	thread__zput(ptq->thread);
2418
2419	if (ptq->tid == -1)
2420		return;
2421
2422	if (ptq->pid == -1) {
2423		ptq->thread = machine__find_thread(m, -1, ptq->tid);
2424		if (ptq->thread)
2425			ptq->pid = ptq->thread->pid_;
2426		return;
2427	}
2428
2429	ptq->thread = machine__findnew_thread(m, ptq->pid, ptq->tid);
2430}
2431
2432static int intel_pt_process_timeless_sample(struct intel_pt *pt,
2433					    struct perf_sample *sample)
2434{
2435	struct auxtrace_queue *queue;
2436	struct intel_pt_queue *ptq;
2437	u64 ts = 0;
2438
2439	queue = auxtrace_queues__sample_queue(&pt->queues, sample, pt->session);
2440	if (!queue)
2441		return -EINVAL;
2442
2443	ptq = queue->priv;
2444	if (!ptq)
2445		return 0;
2446
2447	ptq->stop = false;
2448	ptq->time = sample->time;
2449	intel_pt_sample_set_pid_tid_cpu(ptq, queue, sample);
2450	intel_pt_run_decoder(ptq, &ts);
2451	return 0;
2452}
2453
2454static int intel_pt_lost(struct intel_pt *pt, struct perf_sample *sample)
2455{
2456	return intel_pt_synth_error(pt, INTEL_PT_ERR_LOST, sample->cpu,
2457				    sample->pid, sample->tid, 0, sample->time);
2458}
2459
2460static struct intel_pt_queue *intel_pt_cpu_to_ptq(struct intel_pt *pt, int cpu)
2461{
2462	unsigned i, j;
2463
2464	if (cpu < 0 || !pt->queues.nr_queues)
2465		return NULL;
2466
2467	if ((unsigned)cpu >= pt->queues.nr_queues)
2468		i = pt->queues.nr_queues - 1;
2469	else
2470		i = cpu;
2471
2472	if (pt->queues.queue_array[i].cpu == cpu)
2473		return pt->queues.queue_array[i].priv;
2474
2475	for (j = 0; i > 0; j++) {
2476		if (pt->queues.queue_array[--i].cpu == cpu)
2477			return pt->queues.queue_array[i].priv;
2478	}
2479
2480	for (; j < pt->queues.nr_queues; j++) {
2481		if (pt->queues.queue_array[j].cpu == cpu)
2482			return pt->queues.queue_array[j].priv;
2483	}
2484
2485	return NULL;
2486}
2487
2488static int intel_pt_sync_switch(struct intel_pt *pt, int cpu, pid_t tid,
2489				u64 timestamp)
2490{
2491	struct intel_pt_queue *ptq;
2492	int err;
2493
2494	if (!pt->sync_switch)
2495		return 1;
2496
2497	ptq = intel_pt_cpu_to_ptq(pt, cpu);
2498	if (!ptq || !ptq->sync_switch)
2499		return 1;
2500
2501	switch (ptq->switch_state) {
2502	case INTEL_PT_SS_NOT_TRACING:
2503		break;
2504	case INTEL_PT_SS_UNKNOWN:
2505	case INTEL_PT_SS_TRACING:
2506		ptq->next_tid = tid;
2507		ptq->switch_state = INTEL_PT_SS_EXPECTING_SWITCH_IP;
2508		return 0;
2509	case INTEL_PT_SS_EXPECTING_SWITCH_EVENT:
2510		if (!ptq->on_heap) {
2511			ptq->timestamp = perf_time_to_tsc(timestamp,
2512							  &pt->tc);
2513			err = auxtrace_heap__add(&pt->heap, ptq->queue_nr,
2514						 ptq->timestamp);
2515			if (err)
2516				return err;
2517			ptq->on_heap = true;
2518		}
2519		ptq->switch_state = INTEL_PT_SS_TRACING;
2520		break;
2521	case INTEL_PT_SS_EXPECTING_SWITCH_IP:
2522		intel_pt_log("ERROR: cpu %d expecting switch ip\n", cpu);
2523		break;
2524	default:
2525		break;
2526	}
2527
2528	ptq->next_tid = -1;
2529
2530	return 1;
2531}
2532
2533static int intel_pt_process_switch(struct intel_pt *pt,
2534				   struct perf_sample *sample)
2535{
2536	struct evsel *evsel;
2537	pid_t tid;
2538	int cpu, ret;
2539
2540	evsel = perf_evlist__id2evsel(pt->session->evlist, sample->id);
2541	if (evsel != pt->switch_evsel)
2542		return 0;
2543
2544	tid = evsel__intval(evsel, sample, "next_pid");
2545	cpu = sample->cpu;
2546
2547	intel_pt_log("sched_switch: cpu %d tid %d time %"PRIu64" tsc %#"PRIx64"\n",
2548		     cpu, tid, sample->time, perf_time_to_tsc(sample->time,
2549		     &pt->tc));
2550
2551	ret = intel_pt_sync_switch(pt, cpu, tid, sample->time);
2552	if (ret <= 0)
2553		return ret;
2554
2555	return machine__set_current_tid(pt->machine, cpu, -1, tid);
2556}
2557
2558static int intel_pt_context_switch_in(struct intel_pt *pt,
2559				      struct perf_sample *sample)
2560{
2561	pid_t pid = sample->pid;
2562	pid_t tid = sample->tid;
2563	int cpu = sample->cpu;
2564
2565	if (pt->sync_switch) {
2566		struct intel_pt_queue *ptq;
2567
2568		ptq = intel_pt_cpu_to_ptq(pt, cpu);
2569		if (ptq && ptq->sync_switch) {
2570			ptq->next_tid = -1;
2571			switch (ptq->switch_state) {
2572			case INTEL_PT_SS_NOT_TRACING:
2573			case INTEL_PT_SS_UNKNOWN:
2574			case INTEL_PT_SS_TRACING:
2575				break;
2576			case INTEL_PT_SS_EXPECTING_SWITCH_EVENT:
2577			case INTEL_PT_SS_EXPECTING_SWITCH_IP:
2578				ptq->switch_state = INTEL_PT_SS_TRACING;
2579				break;
2580			default:
2581				break;
2582			}
2583		}
2584	}
2585
2586	/*
2587	 * If the current tid has not been updated yet, ensure it is now that
2588	 * a "switch in" event has occurred.
2589	 */
2590	if (machine__get_current_tid(pt->machine, cpu) == tid)
2591		return 0;
2592
2593	return machine__set_current_tid(pt->machine, cpu, pid, tid);
2594}
2595
2596static int intel_pt_context_switch(struct intel_pt *pt, union perf_event *event,
2597				   struct perf_sample *sample)
2598{
2599	bool out = event->header.misc & PERF_RECORD_MISC_SWITCH_OUT;
2600	pid_t pid, tid;
2601	int cpu, ret;
2602
2603	cpu = sample->cpu;
2604
2605	if (pt->have_sched_switch == 3) {
2606		if (!out)
2607			return intel_pt_context_switch_in(pt, sample);
2608		if (event->header.type != PERF_RECORD_SWITCH_CPU_WIDE) {
2609			pr_err("Expecting CPU-wide context switch event\n");
2610			return -EINVAL;
2611		}
2612		pid = event->context_switch.next_prev_pid;
2613		tid = event->context_switch.next_prev_tid;
2614	} else {
2615		if (out)
2616			return 0;
2617		pid = sample->pid;
2618		tid = sample->tid;
2619	}
2620
2621	if (tid == -1)
2622		intel_pt_log("context_switch event has no tid\n");
2623
2624	ret = intel_pt_sync_switch(pt, cpu, tid, sample->time);
2625	if (ret <= 0)
2626		return ret;
2627
2628	return machine__set_current_tid(pt->machine, cpu, pid, tid);
2629}
2630
2631static int intel_pt_process_itrace_start(struct intel_pt *pt,
2632					 union perf_event *event,
2633					 struct perf_sample *sample)
2634{
2635	if (!pt->per_cpu_mmaps)
2636		return 0;
2637
2638	intel_pt_log("itrace_start: cpu %d pid %d tid %d time %"PRIu64" tsc %#"PRIx64"\n",
2639		     sample->cpu, event->itrace_start.pid,
2640		     event->itrace_start.tid, sample->time,
2641		     perf_time_to_tsc(sample->time, &pt->tc));
2642
2643	return machine__set_current_tid(pt->machine, sample->cpu,
2644					event->itrace_start.pid,
2645					event->itrace_start.tid);
2646}
2647
2648static int intel_pt_find_map(struct thread *thread, u8 cpumode, u64 addr,
2649			     struct addr_location *al)
2650{
2651	if (!al->map || addr < al->map->start || addr >= al->map->end) {
2652		if (!thread__find_map(thread, cpumode, addr, al))
2653			return -1;
2654	}
2655
2656	return 0;
2657}
2658
2659/* Invalidate all instruction cache entries that overlap the text poke */
2660static int intel_pt_text_poke(struct intel_pt *pt, union perf_event *event)
2661{
2662	u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
2663	u64 addr = event->text_poke.addr + event->text_poke.new_len - 1;
2664	/* Assume text poke begins in a basic block no more than 4096 bytes */
2665	int cnt = 4096 + event->text_poke.new_len;
2666	struct thread *thread = pt->unknown_thread;
2667	struct addr_location al = { .map = NULL };
2668	struct machine *machine = pt->machine;
2669	struct intel_pt_cache_entry *e;
2670	u64 offset;
2671
2672	if (!event->text_poke.new_len)
2673		return 0;
2674
2675	for (; cnt; cnt--, addr--) {
2676		if (intel_pt_find_map(thread, cpumode, addr, &al)) {
2677			if (addr < event->text_poke.addr)
2678				return 0;
2679			continue;
2680		}
2681
2682		if (!al.map->dso || !al.map->dso->auxtrace_cache)
2683			continue;
2684
2685		offset = al.map->map_ip(al.map, addr);
2686
2687		e = intel_pt_cache_lookup(al.map->dso, machine, offset);
2688		if (!e)
2689			continue;
2690
2691		if (addr + e->byte_cnt + e->length <= event->text_poke.addr) {
2692			/*
2693			 * No overlap. Working backwards there cannot be another
2694			 * basic block that overlaps the text poke if there is a
2695			 * branch instruction before the text poke address.
2696			 */
2697			if (e->branch != INTEL_PT_BR_NO_BRANCH)
2698				return 0;
2699		} else {
2700			intel_pt_cache_invalidate(al.map->dso, machine, offset);
2701			intel_pt_log("Invalidated instruction cache for %s at %#"PRIx64"\n",
2702				     al.map->dso->long_name, addr);
2703		}
2704	}
2705
2706	return 0;
2707}
2708
2709static int intel_pt_process_event(struct perf_session *session,
2710				  union perf_event *event,
2711				  struct perf_sample *sample,
2712				  struct perf_tool *tool)
2713{
2714	struct intel_pt *pt = container_of(session->auxtrace, struct intel_pt,
2715					   auxtrace);
2716	u64 timestamp;
2717	int err = 0;
2718
2719	if (dump_trace)
2720		return 0;
2721
2722	if (!tool->ordered_events) {
2723		pr_err("Intel Processor Trace requires ordered events\n");
2724		return -EINVAL;
2725	}
2726
2727	if (sample->time && sample->time != (u64)-1)
2728		timestamp = perf_time_to_tsc(sample->time, &pt->tc);
2729	else
2730		timestamp = 0;
2731
2732	if (timestamp || pt->timeless_decoding) {
2733		err = intel_pt_update_queues(pt);
2734		if (err)
2735			return err;
2736	}
2737
2738	if (pt->timeless_decoding) {
2739		if (pt->sampling_mode) {
2740			if (sample->aux_sample.size)
2741				err = intel_pt_process_timeless_sample(pt,
2742								       sample);
2743		} else if (event->header.type == PERF_RECORD_EXIT) {
2744			err = intel_pt_process_timeless_queues(pt,
2745							       event->fork.tid,
2746							       sample->time);
2747		}
2748	} else if (timestamp) {
2749		err = intel_pt_process_queues(pt, timestamp);
2750	}
2751	if (err)
2752		return err;
2753
2754	if (event->header.type == PERF_RECORD_SAMPLE) {
2755		if (pt->synth_opts.add_callchain && !sample->callchain)
2756			intel_pt_add_callchain(pt, sample);
2757		if (pt->synth_opts.add_last_branch && !sample->branch_stack)
2758			intel_pt_add_br_stack(pt, sample);
2759	}
2760
2761	if (event->header.type == PERF_RECORD_AUX &&
2762	    (event->aux.flags & PERF_AUX_FLAG_TRUNCATED) &&
2763	    pt->synth_opts.errors) {
2764		err = intel_pt_lost(pt, sample);
2765		if (err)
2766			return err;
2767	}
2768
2769	if (pt->switch_evsel && event->header.type == PERF_RECORD_SAMPLE)
2770		err = intel_pt_process_switch(pt, sample);
2771	else if (event->header.type == PERF_RECORD_ITRACE_START)
2772		err = intel_pt_process_itrace_start(pt, event, sample);
2773	else if (event->header.type == PERF_RECORD_SWITCH ||
2774		 event->header.type == PERF_RECORD_SWITCH_CPU_WIDE)
2775		err = intel_pt_context_switch(pt, event, sample);
2776
2777	if (!err && event->header.type == PERF_RECORD_TEXT_POKE)
2778		err = intel_pt_text_poke(pt, event);
2779
2780	if (intel_pt_enable_logging && intel_pt_log_events(pt, sample->time)) {
2781		intel_pt_log("event %u: cpu %d time %"PRIu64" tsc %#"PRIx64" ",
2782			     event->header.type, sample->cpu, sample->time, timestamp);
2783		intel_pt_log_event(event);
2784	}
2785
2786	return err;
2787}
2788
2789static int intel_pt_flush(struct perf_session *session, struct perf_tool *tool)
2790{
2791	struct intel_pt *pt = container_of(session->auxtrace, struct intel_pt,
2792					   auxtrace);
2793	int ret;
2794
2795	if (dump_trace)
2796		return 0;
2797
2798	if (!tool->ordered_events)
2799		return -EINVAL;
2800
2801	ret = intel_pt_update_queues(pt);
2802	if (ret < 0)
2803		return ret;
2804
2805	if (pt->timeless_decoding)
2806		return intel_pt_process_timeless_queues(pt, -1,
2807							MAX_TIMESTAMP - 1);
2808
2809	return intel_pt_process_queues(pt, MAX_TIMESTAMP);
2810}
2811
2812static void intel_pt_free_events(struct perf_session *session)
2813{
2814	struct intel_pt *pt = container_of(session->auxtrace, struct intel_pt,
2815					   auxtrace);
2816	struct auxtrace_queues *queues = &pt->queues;
2817	unsigned int i;
2818
2819	for (i = 0; i < queues->nr_queues; i++) {
2820		intel_pt_free_queue(queues->queue_array[i].priv);
2821		queues->queue_array[i].priv = NULL;
2822	}
2823	intel_pt_log_disable();
2824	auxtrace_queues__free(queues);
2825}
2826
2827static void intel_pt_free(struct perf_session *session)
2828{
2829	struct intel_pt *pt = container_of(session->auxtrace, struct intel_pt,
2830					   auxtrace);
2831
2832	auxtrace_heap__free(&pt->heap);
2833	intel_pt_free_events(session);
2834	session->auxtrace = NULL;
2835	thread__put(pt->unknown_thread);
2836	addr_filters__exit(&pt->filts);
2837	zfree(&pt->chain);
2838	zfree(&pt->filter);
2839	zfree(&pt->time_ranges);
2840	free(pt);
2841}
2842
2843static bool intel_pt_evsel_is_auxtrace(struct perf_session *session,
2844				       struct evsel *evsel)
2845{
2846	struct intel_pt *pt = container_of(session->auxtrace, struct intel_pt,
2847					   auxtrace);
2848
2849	return evsel->core.attr.type == pt->pmu_type;
2850}
2851
2852static int intel_pt_process_auxtrace_event(struct perf_session *session,
2853					   union perf_event *event,
2854					   struct perf_tool *tool __maybe_unused)
2855{
2856	struct intel_pt *pt = container_of(session->auxtrace, struct intel_pt,
2857					   auxtrace);
2858
2859	if (!pt->data_queued) {
2860		struct auxtrace_buffer *buffer;
2861		off_t data_offset;
2862		int fd = perf_data__fd(session->data);
2863		int err;
2864
2865		if (perf_data__is_pipe(session->data)) {
2866			data_offset = 0;
2867		} else {
2868			data_offset = lseek(fd, 0, SEEK_CUR);
2869			if (data_offset == -1)
2870				return -errno;
2871		}
2872
2873		err = auxtrace_queues__add_event(&pt->queues, session, event,
2874						 data_offset, &buffer);
2875		if (err)
2876			return err;
2877
2878		/* Dump here now we have copied a piped trace out of the pipe */
2879		if (dump_trace) {
2880			if (auxtrace_buffer__get_data(buffer, fd)) {
2881				intel_pt_dump_event(pt, buffer->data,
2882						    buffer->size);
2883				auxtrace_buffer__put_data(buffer);
2884			}
2885		}
2886	}
2887
2888	return 0;
2889}
2890
2891static int intel_pt_queue_data(struct perf_session *session,
2892			       struct perf_sample *sample,
2893			       union perf_event *event, u64 data_offset)
2894{
2895	struct intel_pt *pt = container_of(session->auxtrace, struct intel_pt,
2896					   auxtrace);
2897	u64 timestamp;
2898
2899	if (event) {
2900		return auxtrace_queues__add_event(&pt->queues, session, event,
2901						  data_offset, NULL);
2902	}
2903
2904	if (sample->time && sample->time != (u64)-1)
2905		timestamp = perf_time_to_tsc(sample->time, &pt->tc);
2906	else
2907		timestamp = 0;
2908
2909	return auxtrace_queues__add_sample(&pt->queues, session, sample,
2910					   data_offset, timestamp);
2911}
2912
2913struct intel_pt_synth {
2914	struct perf_tool dummy_tool;
2915	struct perf_session *session;
2916};
2917
2918static int intel_pt_event_synth(struct perf_tool *tool,
2919				union perf_event *event,
2920				struct perf_sample *sample __maybe_unused,
2921				struct machine *machine __maybe_unused)
2922{
2923	struct intel_pt_synth *intel_pt_synth =
2924			container_of(tool, struct intel_pt_synth, dummy_tool);
2925
2926	return perf_session__deliver_synth_event(intel_pt_synth->session, event,
2927						 NULL);
2928}
2929
2930static int intel_pt_synth_event(struct perf_session *session, const char *name,
2931				struct perf_event_attr *attr, u64 id)
2932{
2933	struct intel_pt_synth intel_pt_synth;
2934	int err;
2935
2936	pr_debug("Synthesizing '%s' event with id %" PRIu64 " sample type %#" PRIx64 "\n",
2937		 name, id, (u64)attr->sample_type);
2938
2939	memset(&intel_pt_synth, 0, sizeof(struct intel_pt_synth));
2940	intel_pt_synth.session = session;
2941
2942	err = perf_event__synthesize_attr(&intel_pt_synth.dummy_tool, attr, 1,
2943					  &id, intel_pt_event_synth);
2944	if (err)
2945		pr_err("%s: failed to synthesize '%s' event type\n",
2946		       __func__, name);
2947
2948	return err;
2949}
2950
2951static void intel_pt_set_event_name(struct evlist *evlist, u64 id,
2952				    const char *name)
2953{
2954	struct evsel *evsel;
2955
2956	evlist__for_each_entry(evlist, evsel) {
2957		if (evsel->core.id && evsel->core.id[0] == id) {
2958			if (evsel->name)
2959				zfree(&evsel->name);
2960			evsel->name = strdup(name);
2961			break;
2962		}
2963	}
2964}
2965
2966static struct evsel *intel_pt_evsel(struct intel_pt *pt,
2967					 struct evlist *evlist)
2968{
2969	struct evsel *evsel;
2970
2971	evlist__for_each_entry(evlist, evsel) {
2972		if (evsel->core.attr.type == pt->pmu_type && evsel->core.ids)
2973			return evsel;
2974	}
2975
2976	return NULL;
2977}
2978
2979static int intel_pt_synth_events(struct intel_pt *pt,
2980				 struct perf_session *session)
2981{
2982	struct evlist *evlist = session->evlist;
2983	struct evsel *evsel = intel_pt_evsel(pt, evlist);
2984	struct perf_event_attr attr;
2985	u64 id;
2986	int err;
2987
2988	if (!evsel) {
2989		pr_debug("There are no selected events with Intel Processor Trace data\n");
2990		return 0;
2991	}
2992
2993	memset(&attr, 0, sizeof(struct perf_event_attr));
2994	attr.size = sizeof(struct perf_event_attr);
2995	attr.type = PERF_TYPE_HARDWARE;
2996	attr.sample_type = evsel->core.attr.sample_type & PERF_SAMPLE_MASK;
2997	attr.sample_type |= PERF_SAMPLE_IP | PERF_SAMPLE_TID |
2998			    PERF_SAMPLE_PERIOD;
2999	if (pt->timeless_decoding)
3000		attr.sample_type &= ~(u64)PERF_SAMPLE_TIME;
3001	else
3002		attr.sample_type |= PERF_SAMPLE_TIME;
3003	if (!pt->per_cpu_mmaps)
3004		attr.sample_type &= ~(u64)PERF_SAMPLE_CPU;
3005	attr.exclude_user = evsel->core.attr.exclude_user;
3006	attr.exclude_kernel = evsel->core.attr.exclude_kernel;
3007	attr.exclude_hv = evsel->core.attr.exclude_hv;
3008	attr.exclude_host = evsel->core.attr.exclude_host;
3009	attr.exclude_guest = evsel->core.attr.exclude_guest;
3010	attr.sample_id_all = evsel->core.attr.sample_id_all;
3011	attr.read_format = evsel->core.attr.read_format;
3012
3013	id = evsel->core.id[0] + 1000000000;
3014	if (!id)
3015		id = 1;
3016
3017	if (pt->synth_opts.branches) {
3018		attr.config = PERF_COUNT_HW_BRANCH_INSTRUCTIONS;
3019		attr.sample_period = 1;
3020		attr.sample_type |= PERF_SAMPLE_ADDR;
3021		err = intel_pt_synth_event(session, "branches", &attr, id);
3022		if (err)
3023			return err;
3024		pt->sample_branches = true;
3025		pt->branches_sample_type = attr.sample_type;
3026		pt->branches_id = id;
3027		id += 1;
3028		attr.sample_type &= ~(u64)PERF_SAMPLE_ADDR;
3029	}
3030
3031	if (pt->synth_opts.callchain)
3032		attr.sample_type |= PERF_SAMPLE_CALLCHAIN;
3033	if (pt->synth_opts.last_branch) {
3034		attr.sample_type |= PERF_SAMPLE_BRANCH_STACK;
3035		/*
3036		 * We don't use the hardware index, but the sample generation
3037		 * code uses the new format branch_stack with this field,
3038		 * so the event attributes must indicate that it's present.
3039		 */
3040		attr.branch_sample_type |= PERF_SAMPLE_BRANCH_HW_INDEX;
3041	}
3042
3043	if (pt->synth_opts.instructions) {
3044		attr.config = PERF_COUNT_HW_INSTRUCTIONS;
3045		if (pt->synth_opts.period_type == PERF_ITRACE_PERIOD_NANOSECS)
3046			attr.sample_period =
3047				intel_pt_ns_to_ticks(pt, pt->synth_opts.period);
3048		else
3049			attr.sample_period = pt->synth_opts.period;
3050		err = intel_pt_synth_event(session, "instructions", &attr, id);
3051		if (err)
3052			return err;
3053		pt->sample_instructions = true;
3054		pt->instructions_sample_type = attr.sample_type;
3055		pt->instructions_id = id;
3056		id += 1;
3057	}
3058
3059	attr.sample_type &= ~(u64)PERF_SAMPLE_PERIOD;
3060	attr.sample_period = 1;
3061
3062	if (pt->synth_opts.transactions) {
3063		attr.config = PERF_COUNT_HW_INSTRUCTIONS;
3064		err = intel_pt_synth_event(session, "transactions", &attr, id);
3065		if (err)
3066			return err;
3067		pt->sample_transactions = true;
3068		pt->transactions_sample_type = attr.sample_type;
3069		pt->transactions_id = id;
3070		intel_pt_set_event_name(evlist, id, "transactions");
3071		id += 1;
3072	}
3073
3074	attr.type = PERF_TYPE_SYNTH;
3075	attr.sample_type |= PERF_SAMPLE_RAW;
3076
3077	if (pt->synth_opts.ptwrites) {
3078		attr.config = PERF_SYNTH_INTEL_PTWRITE;
3079		err = intel_pt_synth_event(session, "ptwrite", &attr, id);
3080		if (err)
3081			return err;
3082		pt->sample_ptwrites = true;
3083		pt->ptwrites_sample_type = attr.sample_type;
3084		pt->ptwrites_id = id;
3085		intel_pt_set_event_name(evlist, id, "ptwrite");
3086		id += 1;
3087	}
3088
3089	if (pt->synth_opts.pwr_events) {
3090		pt->sample_pwr_events = true;
3091		pt->pwr_events_sample_type = attr.sample_type;
3092
3093		attr.config = PERF_SYNTH_INTEL_CBR;
3094		err = intel_pt_synth_event(session, "cbr", &attr, id);
3095		if (err)
3096			return err;
3097		pt->cbr_id = id;
3098		intel_pt_set_event_name(evlist, id, "cbr");
3099		id += 1;
3100	}
3101
3102	if (pt->synth_opts.pwr_events && (evsel->core.attr.config & 0x10)) {
3103		attr.config = PERF_SYNTH_INTEL_MWAIT;
3104		err = intel_pt_synth_event(session, "mwait", &attr, id);
3105		if (err)
3106			return err;
3107		pt->mwait_id = id;
3108		intel_pt_set_event_name(evlist, id, "mwait");
3109		id += 1;
3110
3111		attr.config = PERF_SYNTH_INTEL_PWRE;
3112		err = intel_pt_synth_event(session, "pwre", &attr, id);
3113		if (err)
3114			return err;
3115		pt->pwre_id = id;
3116		intel_pt_set_event_name(evlist, id, "pwre");
3117		id += 1;
3118
3119		attr.config = PERF_SYNTH_INTEL_EXSTOP;
3120		err = intel_pt_synth_event(session, "exstop", &attr, id);
3121		if (err)
3122			return err;
3123		pt->exstop_id = id;
3124		intel_pt_set_event_name(evlist, id, "exstop");
3125		id += 1;
3126
3127		attr.config = PERF_SYNTH_INTEL_PWRX;
3128		err = intel_pt_synth_event(session, "pwrx", &attr, id);
3129		if (err)
3130			return err;
3131		pt->pwrx_id = id;
3132		intel_pt_set_event_name(evlist, id, "pwrx");
3133		id += 1;
3134	}
3135
3136	return 0;
3137}
3138
3139static void intel_pt_setup_pebs_events(struct intel_pt *pt)
3140{
3141	struct evsel *evsel;
3142
3143	if (!pt->synth_opts.other_events)
3144		return;
3145
3146	evlist__for_each_entry(pt->session->evlist, evsel) {
3147		if (evsel->core.attr.aux_output && evsel->core.id) {
3148			pt->sample_pebs = true;
3149			pt->pebs_evsel = evsel;
3150			return;
3151		}
3152	}
3153}
3154
3155static struct evsel *intel_pt_find_sched_switch(struct evlist *evlist)
3156{
3157	struct evsel *evsel;
3158
3159	evlist__for_each_entry_reverse(evlist, evsel) {
3160		const char *name = evsel__name(evsel);
3161
3162		if (!strcmp(name, "sched:sched_switch"))
3163			return evsel;
3164	}
3165
3166	return NULL;
3167}
3168
3169static bool intel_pt_find_switch(struct evlist *evlist)
3170{
3171	struct evsel *evsel;
3172
3173	evlist__for_each_entry(evlist, evsel) {
3174		if (evsel->core.attr.context_switch)
3175			return true;
3176	}
3177
3178	return false;
3179}
3180
3181static int intel_pt_perf_config(const char *var, const char *value, void *data)
3182{
3183	struct intel_pt *pt = data;
3184
3185	if (!strcmp(var, "intel-pt.mispred-all"))
3186		pt->mispred_all = perf_config_bool(var, value);
3187
3188	return 0;
3189}
3190
3191/* Find least TSC which converts to ns or later */
3192static u64 intel_pt_tsc_start(u64 ns, struct intel_pt *pt)
3193{
3194	u64 tsc, tm;
3195
3196	tsc = perf_time_to_tsc(ns, &pt->tc);
3197
3198	while (1) {
3199		tm = tsc_to_perf_time(tsc, &pt->tc);
3200		if (tm < ns)
3201			break;
3202		tsc -= 1;
3203	}
3204
3205	while (tm < ns)
3206		tm = tsc_to_perf_time(++tsc, &pt->tc);
3207
3208	return tsc;
3209}
3210
3211/* Find greatest TSC which converts to ns or earlier */
3212static u64 intel_pt_tsc_end(u64 ns, struct intel_pt *pt)
3213{
3214	u64 tsc, tm;
3215
3216	tsc = perf_time_to_tsc(ns, &pt->tc);
3217
3218	while (1) {
3219		tm = tsc_to_perf_time(tsc, &pt->tc);
3220		if (tm > ns)
3221			break;
3222		tsc += 1;
3223	}
3224
3225	while (tm > ns)
3226		tm = tsc_to_perf_time(--tsc, &pt->tc);
3227
3228	return tsc;
3229}
3230
3231static int intel_pt_setup_time_ranges(struct intel_pt *pt,
3232				      struct itrace_synth_opts *opts)
3233{
3234	struct perf_time_interval *p = opts->ptime_range;
3235	int n = opts->range_num;
3236	int i;
3237
3238	if (!n || !p || pt->timeless_decoding)
3239		return 0;
3240
3241	pt->time_ranges = calloc(n, sizeof(struct range));
3242	if (!pt->time_ranges)
3243		return -ENOMEM;
3244
3245	pt->range_cnt = n;
3246
3247	intel_pt_log("%s: %u range(s)\n", __func__, n);
3248
3249	for (i = 0; i < n; i++) {
3250		struct range *r = &pt->time_ranges[i];
3251		u64 ts = p[i].start;
3252		u64 te = p[i].end;
3253
3254		/*
3255		 * Take care to ensure the TSC range matches the perf-time range
3256		 * when converted back to perf-time.
3257		 */
3258		r->start = ts ? intel_pt_tsc_start(ts, pt) : 0;
3259		r->end   = te ? intel_pt_tsc_end(te, pt) : 0;
3260
3261		intel_pt_log("range %d: perf time interval: %"PRIu64" to %"PRIu64"\n",
3262			     i, ts, te);
3263		intel_pt_log("range %d: TSC time interval: %#"PRIx64" to %#"PRIx64"\n",
3264			     i, r->start, r->end);
3265	}
3266
3267	return 0;
3268}
3269
3270static const char * const intel_pt_info_fmts[] = {
3271	[INTEL_PT_PMU_TYPE]		= "  PMU Type            %"PRId64"\n",
3272	[INTEL_PT_TIME_SHIFT]		= "  Time Shift          %"PRIu64"\n",
3273	[INTEL_PT_TIME_MULT]		= "  Time Muliplier      %"PRIu64"\n",
3274	[INTEL_PT_TIME_ZERO]		= "  Time Zero           %"PRIu64"\n",
3275	[INTEL_PT_CAP_USER_TIME_ZERO]	= "  Cap Time Zero       %"PRId64"\n",
3276	[INTEL_PT_TSC_BIT]		= "  TSC bit             %#"PRIx64"\n",
3277	[INTEL_PT_NORETCOMP_BIT]	= "  NoRETComp bit       %#"PRIx64"\n",
3278	[INTEL_PT_HAVE_SCHED_SWITCH]	= "  Have sched_switch   %"PRId64"\n",
3279	[INTEL_PT_SNAPSHOT_MODE]	= "  Snapshot mode       %"PRId64"\n",
3280	[INTEL_PT_PER_CPU_MMAPS]	= "  Per-cpu maps        %"PRId64"\n",
3281	[INTEL_PT_MTC_BIT]		= "  MTC bit             %#"PRIx64"\n",
3282	[INTEL_PT_MTC_FREQ_BITS]	= "  MTC freq bits       %#"PRIx64"\n",
3283	[INTEL_PT_TSC_CTC_N]		= "  TSC:CTC numerator   %"PRIu64"\n",
3284	[INTEL_PT_TSC_CTC_D]		= "  TSC:CTC denominator %"PRIu64"\n",
3285	[INTEL_PT_CYC_BIT]		= "  CYC bit             %#"PRIx64"\n",
3286	[INTEL_PT_MAX_NONTURBO_RATIO]	= "  Max non-turbo ratio %"PRIu64"\n",
3287	[INTEL_PT_FILTER_STR_LEN]	= "  Filter string len.  %"PRIu64"\n",
3288};
3289
3290static void intel_pt_print_info(__u64 *arr, int start, int finish)
3291{
3292	int i;
3293
3294	if (!dump_trace)
3295		return;
3296
3297	for (i = start; i <= finish; i++) {
3298		const char *fmt = intel_pt_info_fmts[i];
3299
3300		if (fmt)
3301			fprintf(stdout, fmt, arr[i]);
3302	}
3303}
3304
3305static void intel_pt_print_info_str(const char *name, const char *str)
3306{
3307	if (!dump_trace)
3308		return;
3309
3310	fprintf(stdout, "  %-20s%s\n", name, str ? str : "");
3311}
3312
3313static bool intel_pt_has(struct perf_record_auxtrace_info *auxtrace_info, int pos)
3314{
3315	return auxtrace_info->header.size >=
3316		sizeof(struct perf_record_auxtrace_info) + (sizeof(u64) * (pos + 1));
3317}
3318
3319int intel_pt_process_auxtrace_info(union perf_event *event,
3320				   struct perf_session *session)
3321{
3322	struct perf_record_auxtrace_info *auxtrace_info = &event->auxtrace_info;
3323	size_t min_sz = sizeof(u64) * INTEL_PT_PER_CPU_MMAPS;
3324	struct intel_pt *pt;
3325	void *info_end;
3326	__u64 *info;
3327	int err;
3328
3329	if (auxtrace_info->header.size < sizeof(struct perf_record_auxtrace_info) +
3330					min_sz)
3331		return -EINVAL;
3332
3333	pt = zalloc(sizeof(struct intel_pt));
3334	if (!pt)
3335		return -ENOMEM;
3336
3337	addr_filters__init(&pt->filts);
3338
3339	err = perf_config(intel_pt_perf_config, pt);
3340	if (err)
3341		goto err_free;
3342
3343	err = auxtrace_queues__init(&pt->queues);
3344	if (err)
3345		goto err_free;
3346
3347	intel_pt_log_set_name(INTEL_PT_PMU_NAME);
3348
3349	pt->session = session;
3350	pt->machine = &session->machines.host; /* No kvm support */
3351	pt->auxtrace_type = auxtrace_info->type;
3352	pt->pmu_type = auxtrace_info->priv[INTEL_PT_PMU_TYPE];
3353	pt->tc.time_shift = auxtrace_info->priv[INTEL_PT_TIME_SHIFT];
3354	pt->tc.time_mult = auxtrace_info->priv[INTEL_PT_TIME_MULT];
3355	pt->tc.time_zero = auxtrace_info->priv[INTEL_PT_TIME_ZERO];
3356	pt->cap_user_time_zero = auxtrace_info->priv[INTEL_PT_CAP_USER_TIME_ZERO];
3357	pt->tsc_bit = auxtrace_info->priv[INTEL_PT_TSC_BIT];
3358	pt->noretcomp_bit = auxtrace_info->priv[INTEL_PT_NORETCOMP_BIT];
3359	pt->have_sched_switch = auxtrace_info->priv[INTEL_PT_HAVE_SCHED_SWITCH];
3360	pt->snapshot_mode = auxtrace_info->priv[INTEL_PT_SNAPSHOT_MODE];
3361	pt->per_cpu_mmaps = auxtrace_info->priv[INTEL_PT_PER_CPU_MMAPS];
3362	intel_pt_print_info(&auxtrace_info->priv[0], INTEL_PT_PMU_TYPE,
3363			    INTEL_PT_PER_CPU_MMAPS);
3364
3365	if (intel_pt_has(auxtrace_info, INTEL_PT_CYC_BIT)) {
3366		pt->mtc_bit = auxtrace_info->priv[INTEL_PT_MTC_BIT];
3367		pt->mtc_freq_bits = auxtrace_info->priv[INTEL_PT_MTC_FREQ_BITS];
3368		pt->tsc_ctc_ratio_n = auxtrace_info->priv[INTEL_PT_TSC_CTC_N];
3369		pt->tsc_ctc_ratio_d = auxtrace_info->priv[INTEL_PT_TSC_CTC_D];
3370		pt->cyc_bit = auxtrace_info->priv[INTEL_PT_CYC_BIT];
3371		intel_pt_print_info(&auxtrace_info->priv[0], INTEL_PT_MTC_BIT,
3372				    INTEL_PT_CYC_BIT);
3373	}
3374
3375	if (intel_pt_has(auxtrace_info, INTEL_PT_MAX_NONTURBO_RATIO)) {
3376		pt->max_non_turbo_ratio =
3377			auxtrace_info->priv[INTEL_PT_MAX_NONTURBO_RATIO];
3378		intel_pt_print_info(&auxtrace_info->priv[0],
3379				    INTEL_PT_MAX_NONTURBO_RATIO,
3380				    INTEL_PT_MAX_NONTURBO_RATIO);
3381	}
3382
3383	info = &auxtrace_info->priv[INTEL_PT_FILTER_STR_LEN] + 1;
3384	info_end = (void *)info + auxtrace_info->header.size;
3385
3386	if (intel_pt_has(auxtrace_info, INTEL_PT_FILTER_STR_LEN)) {
3387		size_t len;
3388
3389		len = auxtrace_info->priv[INTEL_PT_FILTER_STR_LEN];
3390		intel_pt_print_info(&auxtrace_info->priv[0],
3391				    INTEL_PT_FILTER_STR_LEN,
3392				    INTEL_PT_FILTER_STR_LEN);
3393		if (len) {
3394			const char *filter = (const char *)info;
3395
3396			len = roundup(len + 1, 8);
3397			info += len >> 3;
3398			if ((void *)info > info_end) {
3399				pr_err("%s: bad filter string length\n", __func__);
3400				err = -EINVAL;
3401				goto err_free_queues;
3402			}
3403			pt->filter = memdup(filter, len);
3404			if (!pt->filter) {
3405				err = -ENOMEM;
3406				goto err_free_queues;
3407			}
3408			if (session->header.needs_swap)
3409				mem_bswap_64(pt->filter, len);
3410			if (pt->filter[len - 1]) {
3411				pr_err("%s: filter string not null terminated\n", __func__);
3412				err = -EINVAL;
3413				goto err_free_queues;
3414			}
3415			err = addr_filters__parse_bare_filter(&pt->filts,
3416							      filter);
3417			if (err)
3418				goto err_free_queues;
3419		}
3420		intel_pt_print_info_str("Filter string", pt->filter);
3421	}
3422
3423	pt->timeless_decoding = intel_pt_timeless_decoding(pt);
3424	if (pt->timeless_decoding && !pt->tc.time_mult)
3425		pt->tc.time_mult = 1;
3426	pt->have_tsc = intel_pt_have_tsc(pt);
3427	pt->sampling_mode = intel_pt_sampling_mode(pt);
3428	pt->est_tsc = !pt->timeless_decoding;
3429
3430	pt->unknown_thread = thread__new(999999999, 999999999);
3431	if (!pt->unknown_thread) {
3432		err = -ENOMEM;
3433		goto err_free_queues;
3434	}
3435
3436	/*
3437	 * Since this thread will not be kept in any rbtree not in a
3438	 * list, initialize its list node so that at thread__put() the
3439	 * current thread lifetime assuption is kept and we don't segfault
3440	 * at list_del_init().
3441	 */
3442	INIT_LIST_HEAD(&pt->unknown_thread->node);
3443
3444	err = thread__set_comm(pt->unknown_thread, "unknown", 0);
3445	if (err)
3446		goto err_delete_thread;
3447	if (thread__init_maps(pt->unknown_thread, pt->machine)) {
3448		err = -ENOMEM;
3449		goto err_delete_thread;
3450	}
3451
3452	pt->auxtrace.process_event = intel_pt_process_event;
3453	pt->auxtrace.process_auxtrace_event = intel_pt_process_auxtrace_event;
3454	pt->auxtrace.queue_data = intel_pt_queue_data;
3455	pt->auxtrace.dump_auxtrace_sample = intel_pt_dump_sample;
3456	pt->auxtrace.flush_events = intel_pt_flush;
3457	pt->auxtrace.free_events = intel_pt_free_events;
3458	pt->auxtrace.free = intel_pt_free;
3459	pt->auxtrace.evsel_is_auxtrace = intel_pt_evsel_is_auxtrace;
3460	session->auxtrace = &pt->auxtrace;
3461
3462	if (dump_trace)
3463		return 0;
3464
3465	if (pt->have_sched_switch == 1) {
3466		pt->switch_evsel = intel_pt_find_sched_switch(session->evlist);
3467		if (!pt->switch_evsel) {
3468			pr_err("%s: missing sched_switch event\n", __func__);
3469			err = -EINVAL;
3470			goto err_delete_thread;
3471		}
3472	} else if (pt->have_sched_switch == 2 &&
3473		   !intel_pt_find_switch(session->evlist)) {
3474		pr_err("%s: missing context_switch attribute flag\n", __func__);
3475		err = -EINVAL;
3476		goto err_delete_thread;
3477	}
3478
3479	if (session->itrace_synth_opts->set) {
3480		pt->synth_opts = *session->itrace_synth_opts;
3481	} else {
3482		itrace_synth_opts__set_default(&pt->synth_opts,
3483				session->itrace_synth_opts->default_no_sample);
3484		if (!session->itrace_synth_opts->default_no_sample &&
3485		    !session->itrace_synth_opts->inject) {
3486			pt->synth_opts.branches = false;
3487			pt->synth_opts.callchain = true;
3488			pt->synth_opts.add_callchain = true;
3489		}
3490		pt->synth_opts.thread_stack =
3491				session->itrace_synth_opts->thread_stack;
3492	}
3493
3494	if (pt->synth_opts.log)
3495		intel_pt_log_enable();
3496
3497	/* Maximum non-turbo ratio is TSC freq / 100 MHz */
3498	if (pt->tc.time_mult) {
3499		u64 tsc_freq = intel_pt_ns_to_ticks(pt, 1000000000);
3500
3501		if (!pt->max_non_turbo_ratio)
3502			pt->max_non_turbo_ratio =
3503					(tsc_freq + 50000000) / 100000000;
3504		intel_pt_log("TSC frequency %"PRIu64"\n", tsc_freq);
3505		intel_pt_log("Maximum non-turbo ratio %u\n",
3506			     pt->max_non_turbo_ratio);
3507		pt->cbr2khz = tsc_freq / pt->max_non_turbo_ratio / 1000;
3508	}
3509
3510	err = intel_pt_setup_time_ranges(pt, session->itrace_synth_opts);
3511	if (err)
3512		goto err_delete_thread;
3513
3514	if (pt->synth_opts.calls)
3515		pt->branches_filter |= PERF_IP_FLAG_CALL | PERF_IP_FLAG_ASYNC |
3516				       PERF_IP_FLAG_TRACE_END;
3517	if (pt->synth_opts.returns)
3518		pt->branches_filter |= PERF_IP_FLAG_RETURN |
3519				       PERF_IP_FLAG_TRACE_BEGIN;
3520
3521	if ((pt->synth_opts.callchain || pt->synth_opts.add_callchain) &&
3522	    !symbol_conf.use_callchain) {
3523		symbol_conf.use_callchain = true;
3524		if (callchain_register_param(&callchain_param) < 0) {
3525			symbol_conf.use_callchain = false;
3526			pt->synth_opts.callchain = false;
3527			pt->synth_opts.add_callchain = false;
3528		}
3529	}
3530
3531	if (pt->synth_opts.add_callchain) {
3532		err = intel_pt_callchain_init(pt);
3533		if (err)
3534			goto err_delete_thread;
3535	}
3536
3537	if (pt->synth_opts.last_branch || pt->synth_opts.add_last_branch) {
3538		pt->br_stack_sz = pt->synth_opts.last_branch_sz;
3539		pt->br_stack_sz_plus = pt->br_stack_sz;
3540	}
3541
3542	if (pt->synth_opts.add_last_branch) {
3543		err = intel_pt_br_stack_init(pt);
3544		if (err)
3545			goto err_delete_thread;
3546		/*
3547		 * Additional branch stack size to cater for tracing from the
3548		 * actual sample ip to where the sample time is recorded.
3549		 * Measured at about 200 branches, but generously set to 1024.
3550		 * If kernel space is not being traced, then add just 1 for the
3551		 * branch to kernel space.
3552		 */
3553		if (intel_pt_tracing_kernel(pt))
3554			pt->br_stack_sz_plus += 1024;
3555		else
3556			pt->br_stack_sz_plus += 1;
3557	}
3558
3559	pt->use_thread_stack = pt->synth_opts.callchain ||
3560			       pt->synth_opts.add_callchain ||
3561			       pt->synth_opts.thread_stack ||
3562			       pt->synth_opts.last_branch ||
3563			       pt->synth_opts.add_last_branch;
3564
3565	pt->callstack = pt->synth_opts.callchain ||
3566			pt->synth_opts.add_callchain ||
3567			pt->synth_opts.thread_stack;
3568
3569	err = intel_pt_synth_events(pt, session);
3570	if (err)
3571		goto err_delete_thread;
3572
3573	intel_pt_setup_pebs_events(pt);
3574
3575	if (pt->sampling_mode || list_empty(&session->auxtrace_index))
3576		err = auxtrace_queue_data(session, true, true);
3577	else
3578		err = auxtrace_queues__process_index(&pt->queues, session);
3579	if (err)
3580		goto err_delete_thread;
3581
3582	if (pt->queues.populated)
3583		pt->data_queued = true;
3584
3585	if (pt->timeless_decoding)
3586		pr_debug2("Intel PT decoding without timestamps\n");
3587
3588	return 0;
3589
3590err_delete_thread:
3591	zfree(&pt->chain);
3592	thread__zput(pt->unknown_thread);
3593err_free_queues:
3594	intel_pt_log_disable();
3595	auxtrace_queues__free(&pt->queues);
3596	session->auxtrace = NULL;
3597err_free:
3598	addr_filters__exit(&pt->filts);
3599	zfree(&pt->filter);
3600	zfree(&pt->time_ranges);
3601	free(pt);
3602	return err;
3603}
3604