path: root/tools/perf/util/s390-cpumsf.c

// SPDX-License-Identifier: GPL-2.0
/*
 * Copyright IBM Corp. 2018
 * Auxtrace support for s390 CPU-Measurement Sampling Facility
 *
 * Author(s):  Thomas Richter <tmricht@linux.ibm.com>
 *
 * Auxiliary traces are collected during 'perf record' using rbd000 event.
 * Several PERF_RECORD_XXX are generated during recording:
 *
 * PERF_RECORD_AUX:
 *	Records that new data landed in the AUX buffer part.
 * PERF_RECORD_AUXTRACE:
 *	Defines auxtrace data. Followed by the actual data. The contents of
 *	the auxtrace data is dependent on the event and the CPU.
 *	This record is generated by perf record command. For details
 *	see Documentation/perf.data-file-format.txt.
 * PERF_RECORD_AUXTRACE_INFO:
 *	Defines a table of contains for PERF_RECORD_AUXTRACE records. This
 *	record is generated during 'perf record' command. Each record contains
 *	up to 256 entries describing offset and size of the AUXTRACE data in the
 *	perf.data file.
 * PERF_RECORD_AUXTRACE_ERROR:
 *	Indicates an error during AUXTRACE collection such as buffer overflow.
 * PERF_RECORD_FINISHED_ROUND:
 *	Perf events are not necessarily in time stamp order, as they can be
 *	collected in parallel on different CPUs. If the events should be
 *	processed in time order they need to be sorted first.
 *	Perf report guarantees that there is no reordering over a
 *	PERF_RECORD_FINISHED_ROUND boundary event. All perf records with a
 *	time stamp lower than this record are processed (and displayed) before
 *	the succeeding perf record are processed.
 *
 * These records are evaluated during perf report command.
 *
 * 1. PERF_RECORD_AUXTRACE_INFO is used to set up the infrastructure for
 * auxiliary trace data processing. See s390_cpumsf_process_auxtrace_info()
 * below.
 * Auxiliary trace data is collected per CPU. To merge the data into the report
 * an auxtrace_queue is created for each CPU. It is assumed that the auxtrace
 * data is in ascending order.
 *
 * Each queue has a double linked list of auxtrace_buffers. This list contains
 * the offset and size of a CPU's auxtrace data. During auxtrace processing
 * the data portion is mmap()'ed.
 *
 * To sort the queues in chronological order, all queue access is controlled
 * by the auxtrace_heap. This is basicly a stack, each stack element has two
 * entries, the queue number and a time stamp. However the stack is sorted by
 * the time stamps. The highest time stamp is at the bottom the lowest
 * (nearest) time stamp is at the top. That sort order is maintained at all
 * times!
 *
 * After the auxtrace infrastructure has been setup, the auxtrace queues are
 * filled with data (offset/size pairs) and the auxtrace_heap is populated.
 *
 * 2. PERF_RECORD_XXX processing triggers access to the auxtrace_queues.
 * Each record is handled by s390_cpumsf_process_event(). The time stamp of
 * the perf record is compared with the time stamp located on the auxtrace_heap
 * top element. If that time stamp is lower than the time stamp from the
 * record sample, the auxtrace queues will be processed. As auxtrace queues
 * control many auxtrace_buffers and each buffer can be quite large, the
 * auxtrace buffer might be processed only partially. In this case the
 * position in the auxtrace_buffer of that queue is remembered and the time
 * stamp of the last processed entry of the auxtrace_buffer replaces the
 * current auxtrace_heap top.
 *
 * 3. Auxtrace_queues might run of out data and are feeded by the
 * PERF_RECORD_AUXTRACE handling, see s390_cpumsf_process_auxtrace_event().
 *
 * Event Generation
 * Each sampling-data entry in the auxilary trace data generates a perf sample.
 * This sample is filled
 * with data from the auxtrace such as PID/TID, instruction address, CPU state,
 * etc. This sample is processed with perf_session__deliver_synth_event() to
 * be included into the GUI.
 *
 * 4. PERF_RECORD_FINISHED_ROUND event is used to process all the remaining
 * auxiliary traces entries until the time stamp of this record is reached
 * auxtrace_heap top. This is triggered by ordered_event->deliver().
 *
 *
 * Perf event processing.
 * Event processing of PERF_RECORD_XXX entries relies on time stamp entries.
 * This is the function call sequence:
 *
 * __cmd_report()
 * |
 * perf_session__process_events()
 * |
 * __perf_session__process_events()
 * |
 * perf_session__process_event()
 * |  This functions splits the PERF_RECORD_XXX records.
 * |  - Those generated by perf record command (type number equal or higher
 * |    than PERF_RECORD_USER_TYPE_START) are handled by
 * |    perf_session__process_user_event(see below)
 * |  - Those generated by the kernel are handled by
 * |    perf_evlist__parse_sample_timestamp()
 * |
 * perf_evlist__parse_sample_timestamp()
 * |  Extract time stamp from sample data.
 * |
 * perf_session__queue_event()
 * |  If timestamp is positive the sample is entered into an ordered_event
 * |  list, sort order is the timestamp. The event processing is deferred until
 * |  later (see perf_session__process_user_event()).
 * |  Other timestamps (0 or -1) are handled immediately by
 * |  perf_session__deliver_event(). These are events generated at start up
 * |  of command perf record. They create PERF_RECORD_COMM and PERF_RECORD_MMAP*
 * |  records. They are needed to create a list of running processes and its
 * |  memory mappings and layout. They are needed at the beginning to enable
 * |  command perf report to create process trees and memory mappings.
 * |
 * perf_session__deliver_event()
 * |  Delivers a PERF_RECORD_XXX entry for handling.
 * |
 * auxtrace__process_event()
 * |  The timestamp of the PERF_RECORD_XXX entry is taken to correlate with
 * |  time stamps from the auxiliary trace buffers. This enables
 * |  synchronization between auxiliary trace data and the events on the
 * |  perf.data file.
 * |
 * machine__deliver_event()
 * |  Handles the PERF_RECORD_XXX event. This depends on the record type.
 *    It might update the process tree, update a process memory map or enter
 *    a sample with IP and call back chain data into GUI data pool.
 *
 *
 * Deferred processing determined by perf_session__process_user_event() is
 * finally processed when a PERF_RECORD_FINISHED_ROUND is encountered. These
 * are generated during command perf record.
 * The timestamp of PERF_RECORD_FINISHED_ROUND event is taken to process all
 * PERF_RECORD_XXX entries stored in the ordered_event list. This list was
 * built up while reading the perf.data file.
 * Each event is now processed by calling perf_session__deliver_event().
 * This enables time synchronization between the data in the perf.data file and
 * the data in the auxiliary trace buffers.
 */

#include <endian.h>
#include <errno.h>
#include <byteswap.h>
#include <inttypes.h>
#include <linux/kernel.h>
#include <linux/types.h>
#include <linux/bitops.h>
#include <linux/log2.h>
#include <linux/zalloc.h>

#include <sys/stat.h>
#include <sys/types.h>

#include "cpumap.h"
#include "color.h"
#include "evsel.h"
#include "evlist.h"
#include "machine.h"
#include "session.h"
#include "thread.h"
#include "debug.h"
#include "auxtrace.h"
#include "s390-cpumsf.h"
#include "s390-cpumsf-kernel.h"
#include "s390-cpumcf-kernel.h"
#include "config.h"

struct s390_cpumsf {
	struct auxtrace		auxtrace;
	struct auxtrace_queues	queues;
	struct auxtrace_heap	heap;
	struct perf_session	*session;
	struct machine		*machine;
	u32			auxtrace_type;
	u32			pmu_type;
	u16			machine_type;
	bool			data_queued;
	bool			use_logfile;
	char			*logdir;
};

struct s390_cpumsf_queue {
	struct s390_cpumsf	*sf;
	unsigned int		queue_nr;
	struct auxtrace_buffer	*buffer;
	int			cpu;
	FILE			*logfile;
	FILE			*logfile_ctr;
};

/* Check if the raw data should be dumped to file. If this is the case and
 * the file to dump to has not been opened for writing, do so.
 *
 * Return 0 on success and greater zero on error so processing continues.
 */
static int s390_cpumcf_dumpctr(struct s390_cpumsf *sf,
			       struct perf_sample *sample)
{