tools/perf/util/cs-etm.c

/*
 * SPDX-License-Identifier: GPL-2.0
 *
 * Copyright(C) 2015-2018 Linaro Limited.
 *
 * Author: Tor Jeremiassen <tor@ti.com>
 * Author: Mathieu Poirier <mathieu.poirier@linaro.org>
 */

#include <linux/bitops.h>
#include <linux/err.h>
#include <linux/kernel.h>
#include <linux/log2.h>
#include <linux/types.h>

#include <stdlib.h>

#include "auxtrace.h"
#include "color.h"
#include "cs-etm.h"
#include "debug.h"
#include "evlist.h"
#include "intlist.h"
#include "machine.h"
#include "map.h"
#include "perf.h"
#include "thread.h"
#include "thread_map.h"
#include "thread-stack.h"
#include "util.h"

#define MAX_TIMESTAMP (~0ULL)

struct cs_etm_auxtrace {
	struct auxtrace auxtrace;
	struct auxtrace_queues queues;
	struct auxtrace_heap heap;
	struct itrace_synth_opts synth_opts;
	struct perf_session *session;
	struct machine *machine;
	struct thread *unknown_thread;

	u8 timeless_decoding;
	u8 snapshot_mode;
	u8 data_queued;
	u8 sample_branches;

	int num_cpu;
	u32 auxtrace_type;
	u64 branches_sample_type;
	u64 branches_id;
	u64 **metadata;
	u64 kernel_start;
	unsigned int pmu_type;
};

struct cs_etm_queue {
	struct cs_etm_auxtrace *etm;
	struct thread *thread;
	struct cs_etm_decoder *decoder;
	struct auxtrace_buffer *buffer;
	const struct cs_etm_state *state;
	union perf_event *event_buf;
	unsigned int queue_nr;
	pid_t pid, tid;
	int cpu;
	u64 time;
	u64 timestamp;
	u64 offset;
};

static int cs_etm__flush_events(struct perf_session *session,
				struct perf_tool *tool)
{
	(void) session;
	(void) tool;
	return 0;
}

static void cs_etm__free_queue(void *priv)
{
	struct cs_etm_queue *etmq = priv;

	free(etmq);
}

static void cs_etm__free_events(struct perf_session *session)
{
	unsigned int i;
	struct cs_etm_auxtrace *aux = container_of(session->auxtrace,
						   struct cs_etm_auxtrace,
						   auxtrace);
	struct auxtrace_queues *queues = &aux->queues;

	for (i = 0; i < queues->nr_queues; i++) {
		cs_etm__free_queue(queues->queue_array[i].priv);
		queues->queue_array[i].priv = NULL;
	}

	auxtrace_queues__free(queues);
}

static void cs_etm__free(struct perf_session *session)
{
	int i;
	struct int_node *inode, *tmp;
	struct cs_etm_auxtrace *aux = container_of(session->auxtrace,
						   struct cs_etm_auxtrace,
						   auxtrace);
	cs_etm__free_events(session);
	session->auxtrace = NULL;

	/* First remove all traceID/CPU# nodes for the RB tree */
	intlist__for_each_entry_safe(inode, tmp, traceid_list)
		intlist__remove(traceid_list, inode);
	/* Then the RB tree itself */
	intlist__delete(traceid_list);

	for (i = 0; i < aux->num_cpu; i++)
		zfree(&aux->metadata[i]);

	zfree(&aux->metadata);
	zfree(&aux);
}

static int cs_etm__process_event(struct perf_session *session,
				 union perf_event *event,
				 struct perf_sample *sample,
				 struct perf_tool *tool)
{
	(void) session;
	(void) event;
	(void) sample;
	(void) tool;
	return 0;
}

static int cs_etm__process_auxtrace_event(struct perf_session *session,
					  union perf_event *event,
					  struct perf_tool *tool)
{
	(void) session;
	(void) event;
	(void) tool;
	return 0;
}

static bool cs_etm__is_timeless_decoding(struct cs_etm_auxtrace *etm)
{
	struct perf_evsel *evsel;
	struct perf_evlist *evlist = etm->session->evlist;
	bool timeless_decoding = true;

	/*
	 * Circle through the list of event and complain if we find one
	 * with the time bit set.
	 */
	evlist__for_each_entry(evlist, evsel) {
		if ((evsel->attr.sample_type & PERF_SAMPLE_TIME))
			timeless_decoding = false;
	}

	return timeless_decoding;
}

static const char * const cs_etm_global_header_fmts[] = {
	[CS_HEADER_VERSION_0]	= "	Header version		       %llx\n",
	[CS_PMU_TYPE_CPUS]	= "	PMU type/num cpus	       %llx\n",
	[CS_ETM_SNAPSHOT]	= "	Snapshot		       %llx\n",
};

static const char * const cs_etm_priv_fmts[] = {
	[CS_ETM_MAGIC]		= "	Magic number		       %llx\n",
	[CS_ETM_CPU]		= "	CPU			       %lld\n",
	[CS_ETM_ETMCR]		= "	ETMCR			       %llx\n",
	[CS_ETM_ETMTRACEIDR]	= "	ETMTRACEIDR		       %llx\n",
	[CS_ETM_ETMCCER]	= "	ETMCCER			       %llx\n",
	[CS_ETM_ETMIDR]		= "	ETMIDR			       %llx\n",
};

static const char * const cs_etmv4_priv_fmts[] = {
	[CS_ETM_MAGIC]		= "	Magic number		       %llx\n",
	[CS_ETM_CPU]		= "	CPU			       %lld\n",
	[CS_ETMV4_TRCCONFIGR]	= "	TRCCONFIGR		       %llx\n",
	[CS_ETMV4_TRCTRACEIDR]	= "	TRCTRACEIDR		       %llx\n",
	[CS_ETMV4_TRCIDR0]	= "	TRCIDR0			       %llx\n",
	[CS_ETMV4_TRCIDR1]	= "	TRCIDR1			       %llx\n",
	[CS_ETMV4_TRCIDR2]	= "	TRCIDR2			       %llx\n",
	[CS_ETMV4_TRCIDR8]	= "	TRCIDR8			       %llx\n",
	[CS_ETMV4_TRCAUTHSTATUS] = "	TRCAUTHSTATUS		       %llx\n",
};

static void cs_etm__print_auxtrace_info(u64 *val, int num)
{
	int i, j, cpu = 0;

	for (i = 0; i < CS_HEADER_VERSION_0_MAX; i++)
		fprintf(stdout, cs_etm_global_header_fmts[i], val[i]);

	for (i = CS_HEADER_VERSION_0_MAX; cpu < num; cpu++) {
		if (val[i] == __perf_cs_etmv3_magic)
			for (j = 0; j < CS_ETM_PRIV_MAX; j++, i++)
				fprintf(stdout, cs_etm_priv_fmts[j], val[i]);
		else if (val[i] == __perf_cs_etmv4_magic)
			for (j = 0; j < CS_ETMV4_PRIV_MAX; j++, i++)
				fprintf(stdout, cs_etmv4_priv_fmts[j], val[i]);
		else
			/* failure.. return */
			return;
	}
}

int cs_etm__process_auxtrace_info(union perf_event *event,
				  struct perf_session *session)
{
	struct auxtrace_info_event *auxtrace_info = &event->auxtrace_info;
	struct cs_etm_auxtrace *etm = NULL;
	struct int_node *inode;
	unsigned int pmu_type;
	int event_header_size = sizeof(struct perf_event_header);
	int info_header_size;
	int total_size = auxtrace_info->header.size;
	int priv_size = 0;
	int num_cpu;
	int err = 0, idx = -1;
	int i, j, k;
	u64 *ptr, *hdr = NULL;
	u64 **metadata = NULL;

	/*
	 * sizeof(auxtrace_info_event::type) +
	 * sizeof(auxtrace_info_event::reserved) == 8
	 */
	info_header_size = 8;

	if (total_size < (event_header_size + info_header_size))
		return -EINVAL;

	priv_size = total_size - event_header_size - info_header_size;

	/* First the global part */
	ptr = (u64 *) auxtrace_info->priv;

	/* Look for version '0' of the header */
	if (ptr[0] != 0)
		return -EINVAL;

	hdr = zalloc(sizeof(*hdr) * CS_HEADER_VERSION_0_MAX);
	if (!hdr)
		return -ENOMEM;

	/* Extract header information - see cs-etm.h for format */
	for (i = 0; i < CS_HEADER_VERSION_0_MAX; i++)
		hdr[i] = ptr[i];
	num_cpu = hdr[CS_PMU_TYPE_CPUS] & 0xffffffff;
	pmu_type = (unsigned int) ((hdr[CS_PMU_TYPE_CPUS] >> 32) &
				    0xffffffff);

	/*
	 * Create an RB tree for traceID-CPU# tuple. Since the conversion has
	 * to be made for each packet that gets decoded, optimizing access in
	 * anything other than a sequential array is worth doing.
	 */
	traceid_list = intlist__new(NULL);
	if (!traceid_list) {
		err = -ENOMEM;
		goto err_free_hdr;
	}

	metadata = zalloc(sizeof(*metadata) * num_cpu);
	if (!metadata) {
		err = -ENOMEM;
		goto err_free_traceid_list;
	}

	/*
	 * The metadata is stored in the auxtrace_info section and encodes
	 * the configuration of the ARM embedded trace macrocell which is
	 * required by the trace decoder to properly decode the trace due
	 * to its highly compressed nature.
	 */
	for (j = 0; j < num_cpu; j++) {
		if (ptr[i] == __perf_cs_etmv3_magic) {
			metadata[j] = zalloc(sizeof(*metadata[j]) *
					     CS_ETM_PRIV_MAX);
			if (!metadata[j]) {
				err = -ENOMEM;
				goto err_free_metadata;
			}
			for (k = 0; k < CS_ETM_PRIV_MAX; k++)
				metadata[j][k] = ptr[i + k];

			/* The traceID is our handle */
			idx = metadata[j][CS_ETM_ETMTRACEIDR];
			i += CS_ETM_PRIV_MAX;
		} else if (ptr[i] == __perf_cs_etmv4_magic) {
			metadata[j] = zalloc(sizeof(*metadata[j]) *
					     CS_ETMV4_PRIV_MAX);
			if (!metadata[j]) {
				err = -ENOMEM;
				goto err_free_metadata;
			}
			for (k = 0; k < CS_ETMV4_PRIV_MAX; k++)
				metadata[j][k] = ptr[i + k];

			/* The traceID is our handle */
			idx = metadata[j][CS_ETMV4_TRCTRACEIDR];
			i += CS_ETMV4_PRIV_MAX;
		}

		/* Get an RB node for this CPU */
		inode = intlist__findnew(traceid_list, idx);

		/* Something went wrong, no need to continue */
		if (!inode) {
			err = PTR_ERR(inode);
			goto err_free_metadata;
		}

		/*
		 * The node for that CPU should not be taken.
		 * Back out if that's the case.
		 */
		if (inode->priv) {
			err = -EINVAL;
			goto err_free_metadata;
		}
		/* All good, associate the traceID with the CPU# */
		inode->priv = &metadata[j][CS_ETM_CPU];
	}

	/*
	 * Each of CS_HEADER_VERSION_0_MAX, CS_ETM_PRIV_MAX and
	 * CS_ETMV4_PRIV_MAX mark how many double words are in the
	 * global metadata, and each cpu's metadata respectively.
	 * The following tests if the correct number of double words was
	 * present in the auxtrace info section.
	 */
	if (i * 8 != priv_size) {
		err = -EINVAL;
		goto err_free_metadata;
	}

	etm = zalloc(sizeof(*etm));

	if (!etm) {
		err = -ENOMEM;
		goto err_free_metadata;
	}

	err = auxtrace_queues__init(&etm->queues);
	if (err)
		goto err_free_etm;

	etm->session = session;
	etm->machine = &session->machines.host;

	etm->num_cpu = num_cpu;
	etm->pmu_type = pmu_type;
	etm->snapshot_mode = (hdr[CS_ETM_SNAPSHOT] != 0);
	etm->metadata = metadata;
	etm->auxtrace_type = auxtrace_info->type;
	etm->timeless_decoding = cs_etm__is_timeless_decoding(etm);

	etm->auxtrace.process_event = cs_etm__process_event;
	etm->auxtrace.process_auxtrace_event = cs_etm__process_auxtrace_event;
	etm->auxtrace.flush_events = cs_etm__flush_events;
	etm->auxtrace.free_events = cs_etm__free_events;
	etm->auxtrace.free = cs_etm__free;
	session->auxtrace = &etm->auxtrace;

	if (dump_trace) {
		cs_etm__print_auxtrace_info(auxtrace_info->priv, num_cpu);
		return 0;
	}

	err = auxtrace_queues__process_index(&etm->queues, session);
	if (err)
		goto err_free_queues;

	etm->data_queued = etm->queues.populated;

	return 0;

err_free_queues:
	auxtrace_queues__free(&etm->queues);
	session->auxtrace = NULL;
err_free_etm:
	zfree(&etm);
err_free_metadata:
	/* No need to check @metadata[j], free(NULL) is supported */
	for (j = 0; j < num_cpu; j++)
		free(metadata[j]);
	zfree(&metadata);
err_free_traceid_list:
	intlist__delete(traceid_list);
err_free_hdr:
	zfree(&hdr);

	return -EINVAL;
}