path: root/tools/perf/builtin-record.c

/*
 * builtin-record.c
 *
 * Builtin record command: Record the profile of a workload
 * (or a CPU, or a PID) into the perf.data output file - for
 * later analysis via perf report.
 */
#define _FILE_OFFSET_BITS 64

#include "builtin.h"

#include "perf.h"

#include "util/build-id.h"
#include "util/util.h"
#include "util/parse-options.h"
#include "util/parse-events.h"

#include "util/header.h"
#include "util/event.h"
#include "util/debug.h"
#include "util/session.h"
#include "util/symbol.h"
#include "util/cpumap.h"

#include <unistd.h>
#include <sched.h>
#include <sys/mman.h>

enum write_mode_t {
	WRITE_FORCE,
	WRITE_APPEND
};

static int			*fd[MAX_NR_CPUS][MAX_COUNTERS];

static u64			user_interval			= ULLONG_MAX;
static u64			default_interval		=      0;
static u64			sample_type;

static int			nr_cpus				=      0;
static unsigned int		page_size;
static unsigned int		mmap_pages			=    128;
static unsigned int		user_freq 			= UINT_MAX;
static int			freq				=   1000;
static int			output;
static int			pipe_output			=      0;
static const char		*output_name			= "perf.data";
static int			group				=      0;
static int			realtime_prio			=      0;
static bool			raw_samples			=  false;
static bool			sample_id_all_avail		=   true;
static bool			system_wide			=  false;
static pid_t			target_pid			=     -1;
static pid_t			target_tid			=     -1;
static pid_t			*all_tids			=      NULL;
static int			thread_num			=      0;
static pid_t			child_pid			=     -1;
static bool			no_inherit			=  false;
static enum write_mode_t	write_mode			= WRITE_FORCE;
static bool			call_graph			=  false;
static bool			inherit_stat			=  false;
static bool			no_samples			=  false;
static bool			sample_address			=  false;
static bool			sample_time			=  false;
static bool			no_buildid			=  false;
static bool			no_buildid_cache		=  false;

static long			samples				=      0;
static u64			bytes_written			=      0;

static struct pollfd		*event_array;

static int			nr_poll				=      0;
static int			nr_cpu				=      0;

static int			file_new			=      1;
static off_t			post_processing_offset;

static struct perf_session	*session;
static const char		*cpu_list;

struct mmap_data {
	int			counter;
	void			*base;
	unsigned int		mask;
	unsigned int		prev;
};

static struct mmap_data		mmap_array[MAX_NR_CPUS];

static unsigned long mmap_read_head(struct mmap_data *md)
{
	struct perf_event_mmap_page *pc = md->base;
	long head;

	head = pc->data_head;
	rmb();

	return head;
}

static void mmap_write_tail(struct mmap_data *md, unsigned long tail)
{
	struct perf_event_mmap_page *pc = md->base;

	/*
	 * ensure all reads are done before we write the tail out.
	 */
	/* mb(); */
	pc->data_tail = tail;
}

static void advance_output(size_t size)
{
	bytes_written += size;
}

static void write_output(void *buf, size_t size)
{
	while (size) {
		int ret = write(output, buf, size);

		if (ret < 0)
			die("failed to write");

		size -= ret;
		buf += ret;

		bytes_written += ret;
	}
}

static int process_synthesized_event(event_t *event,
				     struct sample_data *sample __used,
				     struct perf_session *self __used)
{
	write_output(event, event->header.size);
	return 0;
}

static void mmap_read(struct mmap_data *md)
{
	unsigned int head = mmap_read_head(md);
	unsigned int old = md->prev;
	unsigned char *data = md->base + page_size;
	unsigned long size;
	void *buf;
	int diff;

	/*
	 * If we're further behind than half the buffer, there's a chance
	 * the writer will bite our tail and mess up the samples under us.
	 *
	 * If we somehow ended up ahead of the head, we got messed up.
	 *
	 * In either case, truncate and restart at head.
	 */
	diff = head - old;
	if (diff < 0) {
		fprintf(stderr, "WARNING: failed to keep up with mmap data\n");
		/*
		 * head points to a known good entry, start there.
		 */
		old