DPDK总结（eal_thread_loop）

DPDK学习（rte_eal_init）
DPDK学习（eal_thread_loop）

rte_eal_remote_launch()

MASTER lcore调用rte_eal_remote_launch()将回调函数和参数注册到lcore_config[].f和lcore_config[].arg中，并通知SLAVE lcore执行该回调函数

/*
 * Send a message to a slave lcore identified by slave_id to call a
 * function f with argument arg. Once the execution is done, the
 * remote lcore switch in FINISHED state.
 */
int
rte_eal_remote_launch(int (*f)(void *), void *arg, unsigned slave_id)
{
	int n;
	char c = 0;
	int m2s = lcore_config[slave_id].pipe_master2slave[1];
	int s2m = lcore_config[slave_id].pipe_slave2master[0];

	if (lcore_config[slave_id].state != WAIT)
		return -EBUSY;

	/* 注册回调函数和参数 */
	lcore_config[slave_id].f = f;
	lcore_config[slave_id].arg = arg;

	/* send message */
	/* 发送消息给SLAVE lcore */
	n = 0;
	while (n == 0 || (n < 0 && errno == EINTR))
		n = write(m2s, &c, 1);
	if (n < 0)
		rte_panic("cannot write on configuration pipe\n");

	/* wait ack */
	/* 等待SLAVE lcore的确认 */
	do {
		n = read(s2m, &c, 1);
	} while (n < 0 && errno == EINTR);

	if (n <= 0)
		rte_panic("cannot read on configuration pipe\n");

	return 0;
}

rte_eal_mp_remote_launch()

/*
 * Check that every SLAVE lcores are in WAIT state, then call
 * rte_eal_remote_launch() for all of them. If call_master is true
 * (set to CALL_MASTER), also call the function on the master lcore.
 */
int
rte_eal_mp_remote_launch(int (*f)(void *), void *arg,
			 enum rte_rmt_call_master_t call_master)
{
	int lcore_id;
	int master = rte_get_master_lcore();

	/* check state of lcores */
	/* 检查每个SLAVE lcore的状态是否为WAIT */
	RTE_LCORE_FOREACH_SLAVE(lcore_id) {
		if (lcore_config[lcore_id].state != WAIT)
			return -EBUSY;
	}

	/* send messages to cores */
	/* 发送消息给每个SLAVE lcore执行回调函数 */
	RTE_LCORE_FOREACH_SLAVE(lcore_id) {
		rte_eal_remote_launch(f, arg, lcore_id);
	}

	/* 若需要，在MASTER lcore上也执行回调函数 */
	if (call_master == CALL_MASTER) {
		lcore_config[master].ret = f(arg);
		lcore_config[master].state = FINISHED;
	}

	return 0;
}

rte_eal_wait_lcore()

/*
 * Wait until a lcore finished its job.
 */
int
rte_eal_wait_lcore(unsigned slave_id)
{
	if (lcore_config[slave_id].state == WAIT)
		return 0;

	/* 等待SLAVE lcore执行完回调函数
	 * 注意：大部分DPDK应用的回调函数都是一个死循环，MASTER lcore会阻塞在这里 */
	while (lcore_config[slave_id].state != WAIT &&
	       lcore_config[slave_id].state != FINISHED)
		rte_pause();

	rte_rmb();

	/* we are in finished state, go to wait state */
	lcore_config[slave_id].state = WAIT; /* 设置SLAVE lcore的状态为WAIT */
	return lcore_config[slave_id].ret;
}

rte_eal_mp_wait_lcore()

/*
 * Do a rte_eal_wait_lcore() for every lcore. The return values are
 * ignored.
 */
void
rte_eal_mp_wait_lcore(void)
{
	unsigned lcore_id;

	/* 等待每个SLAVE lcore执行完回调函数 */
	RTE_LCORE_FOREACH_SLAVE(lcore_id) {
		rte_eal_wait_lcore(lcore_id);
	}
}

eal_thread_loop()

SLAVE lcore的主循环函数

/* main loop of threads */
__attribute__((noreturn)) void *
eal_thread_loop(__attribute__((unused)) void *arg)
{
	char c;
	int n, ret;
	unsigned lcore_id;
	pthread_t thread_id;
	int m2s, s2m;
	char cpuset[RTE_CPU_AFFINITY_STR_LEN];

	thread_id = pthread_self();

	/* retrieve our lcore_id from the configuration structure */
	/* 根据tid找到对应的lcore_id */
	RTE_LCORE_FOREACH_SLAVE(lcore_id) {
		if (thread_id == lcore_config[lcore_id].thread_id)
			break;
	}
	if (lcore_id == RTE_MAX_LCORE)
		rte_panic("cannot retrieve lcore id\n");

	m2s = lcore_config[lcore_id].pipe_master2slave[0];
	s2m = lcore_config[lcore_id].pipe_slave2master[1];

	/* set the lcore ID in per-lcore memory area */
	RTE_PER_LCORE(_lcore_id) = lcore_id;

	/* set CPU affinity */
	/* 绑定SLAVE lcore到logical CPU */
	if (eal_thread_set_affinity() < 0)
		rte_panic("cannot set affinity\n");

	ret = eal_thread_dump_affinity(cpuset, RTE_CPU_AFFINITY_STR_LEN);

	RTE_LOG(DEBUG, EAL, "lcore %u is ready (tid=%x;cpuset=[%s%s])\n",
		lcore_id, (int)thread_id, cpuset, ret == 0 ? "" : "...");

	/* read on our pipe to get commands */
	while (1) {
		void *fct_arg;

		/* wait command */
		/* 等待MASTER lcore的消息 */
		do {
			n = read(m2s, &c, 1);
		} while (n < 0 && errno == EINTR);

		if (n <= 0)
			rte_panic("cannot read on configuration pipe\n");

		lcore_config[lcore_id].state = RUNNING; /* 设置SLAVE lcore的状态为RUNNING */

		/* send ack */
		/* 发送确认给MASTER lcore */
		n = 0;
		while (n == 0 || (n < 0 && errno == EINTR))
			n = write(s2m, &c, 1);
		if (n < 0)
			rte_panic("cannot write on configuration pipe\n");

		if (lcore_config[lcore_id].f == NULL)
			rte_panic("NULL function pointer\n");

		/* call the function and store the return value */
		fct_arg = lcore_config[lcore_id].arg;
		/* 执行MASTER lcore通过rte_eal_remote_launch()注册的回调函数
		 * 注意：大部分DPDK应用的回调函数都是一个死循环，SLAVE lcore会阻塞在这里 */
		ret = lcore_config[lcore_id].f(fct_arg);
		lcore_config[lcore_id].ret = ret;
		rte_wmb();

		/* when a service core returns, it should go directly to WAIT
		 * state, because the application will not lcore_wait() for it.
		 */
		if (lcore_config[lcore_id].core_role == ROLE_SERVICE)
			lcore_config[lcore_id].state = WAIT;
		else
			lcore_config[lcore_id].state = FINISHED; /* 设置SLAVE lcore的状态为FINISHED */
	}

	/* never reached */
	/* pthread_exit(NULL); */
	/* return NULL; */
}