path: root/net/smc/smc_tx.c

// SPDX-License-Identifier: GPL-2.0
/*
 * Shared Memory Communications over RDMA (SMC-R) and RoCE
 *
 * Manage send buffer.
 * Producer:
 * Copy user space data into send buffer, if send buffer space available.
 * Consumer:
 * Trigger RDMA write into RMBE of peer and send CDC, if RMBE space available.
 *
 * Copyright IBM Corp. 2016
 *
 * Author(s):  Ursula Braun <ubraun@linux.vnet.ibm.com>
 */

#include <linux/net.h>
#include <linux/rcupdate.h>
#include <linux/workqueue.h>
#include <linux/sched/signal.h>

#include <net/sock.h>
#include <net/tcp.h>

#include "smc.h"
#include "smc_wr.h"
#include "smc_cdc.h"
#include "smc_close.h"
#include "smc_ism.h"
#include "smc_tx.h"

#define SMC_TX_WORK_DELAY	0
#define SMC_TX_CORK_DELAY	(HZ >> 2)	/* 250 ms */

/***************************** sndbuf producer *******************************/

/* callback implementation for sk.sk_write_space()
 * to wakeup sndbuf producers that blocked with smc_tx_wait().
 * called under sk_socket lock.
 */
static void smc_tx_write_space(struct sock *sk)
{
	struct socket *sock = sk->sk_socket;
	struct smc_sock *smc = smc_sk(sk);
	struct socket_wq *wq;

	/* similar to sk_stream_write_space */
	if (atomic_read(&smc->conn.sndbuf_space) && sock) {
		clear_bit(SOCK_NOSPACE, &sock->flags);
		rcu_read_lock();
		wq = rcu_dereference(sk->sk_wq);
		if (skwq_has_sleeper(wq))
			wake_up_interruptible_poll(&wq->wait,
						   EPOLLOUT | EPOLLWRNORM |
						   EPOLLWRBAND);
		if (wq && wq->fasync_list && !(sk->sk_shutdown & SEND_SHUTDOWN))
			sock_wake_async(wq, SOCK_WAKE_SPACE, POLL_OUT);
		rcu_read_unlock();
	}
}

/* Wakeup sndbuf producers that blocked with smc_tx_wait().
 * Cf. tcp_data_snd_check()=>tcp_check_space()=>tcp_new_space().
 */
void smc_tx_sndbuf_nonfull(struct smc_sock *smc)
{
	if (smc->sk.sk_socket &&
	    test_bit(SOCK_NOSPACE, &smc->sk.sk_socket->flags))
		smc->sk.sk_write_space(&smc->sk);
}

/* blocks sndbuf producer until at least one byte of free space available
 * or urgent Byte was consumed
 */
static int smc_tx_wait(struct smc_sock *smc, int flags)
{
	DEFINE_WAIT_FUNC(wait, woken_wake_function);
	struct smc_connection *conn = &smc->conn;
	struct sock *sk = &smc->sk;
	long timeo;
	int rc = 0;

	/* similar to sk_stream_wait_memory */
	timeo = sock_sndtimeo(sk, flags & MSG_DONTWAIT);
	add_wait_queue(sk_sleep(sk), &wait);
	while (1) {
		sk_set_bit(SOCKWQ_ASYNC_NOSPACE, sk);
		if (sk->sk_err ||
		    (sk->sk_shutdown & SEND_SHUTDOWN) ||
		    conn->killed ||
		    conn->local_tx_ctrl.conn_state_flags.peer_done_writing) {
			rc = -EPIPE;
			break;
		}
		if (smc_cdc_rxed_any_close(conn)) {
			rc = -ECONNRESET;
			break;
		}
		if (!timeo) {
			/* ensure EPOLLOUT is subsequently generated */
			set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
			rc = -EAGAIN;
			break;
		}
		if (signal_pending(current)) {
			rc = sock_intr_errno(timeo);
			break;
		}
		sk_clear_bit(SOCKWQ_ASYNC_NOSPACE, sk);
		if (atomic_read(&conn->sndbuf_space) && !conn->urg_tx_pend)
			break; /* at least 1 byte of free & no urgent data */
		set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
		sk_wait_event(sk, &timeo,
			      sk->sk_err ||
			      (sk->sk_shutdown & SEND_SHUTDOWN) ||
			      smc_cdc_rxed_any_close(conn) ||
			      (atomic_read(&conn->sndbuf_space) &&
			       !conn->urg_tx_pend),
			      &wait);
	}
	remove_wait_queue(sk_sleep(sk), &wait);
	return rc;
}

static bool smc_tx_is_corked(struct smc_sock *smc)
{
	struct tcp_sock *tp = tcp_sk(smc->clcsock->sk);

	return (tp->nonagle & TCP_NAGLE_CORK) ? true : false;
}

/* sndbuf producer: main API called by socket layer.
 * called under sock lock.
 */
int smc_tx_sendmsg(struct smc_sock *smc, struct msghdr *msg, size_t len)
{
	size_t copylen, send_done = 0, send_remaining = len;
	size_t chunk_len, chunk_off, chunk_len_sum;
	struct smc_connection *conn = &smc->conn;
	union smc_host_cursor prep;
	struct sock *sk = &smc->sk;
	char *sndbuf_base;
	int tx_cnt_prep;
	int writespace;
	int rc, chunk;

	/* This should be in poll */
	sk_clear_bit(SOCKWQ_ASYNC_NOSPACE, sk);

	if (sk->sk_err || (sk->sk_shutdown & SEND_SHUTDOWN)) {
		rc = -EPIPE;
		goto out_err;
	}

	while (msg_data_left(msg)) {
		if (sk->sk_state == SMC_INIT)
			return -ENOTCONN;
		if (smc->sk.sk_shutdown & SEND_SHUTDOWN ||
		    (smc->sk.sk_err == ECONNABORTED) ||
		    conn->killed)
			return -EPIPE;
		if (smc_cdc_rxed_any_close(conn))
			return send_done ?: -ECONNRESET;

		if (msg->msg_flags & MSG_OOB)
			conn->local_tx_ctrl.prod_flags.urg_data_pending = 1;

		if (!atomic_read(&conn->sndbuf_space) || conn->urg_tx_pend) {
			if (send_done)
				return send_done;
			rc = smc_tx_wait(smc, msg->msg_flags);
			if (rc)
				goto out_err;
			continue;
		}

		/* initialize variables for 1st iteration of subsequent loop */
		/* could be just 1 byte, even after smc_tx_wait above */
		writespace = atomic_read(&conn->sndbuf_space);
		/* not more than what user space asked for */
		copylen = min_t(size_t, send_remaining, writespace);
		/* determine start of sndbuf */
		sndbuf_base = conn->sndbuf_desc->cpu_addr;
		smc_curs_copy(&prep, &conn->tx_curs_prep, conn);
		tx_cnt_prep = prep.count;
		/* determine chunks where to write into sndbuf */
		/* either unwrapped case, or 1st chunk of wrapped case */
		chunk_len = min_t(size_t, copylen, conn->sndbuf_desc->len -
				  tx_cnt_prep);
		chunk_len_sum = chunk_len;
		chunk_off = tx_cnt_prep;
		smc_sndbuf_sync_sg_for_cpu(conn);
		for (chunk = 0; chunk < 2; chunk++) {
			rc = memcpy_from_msg(sndbuf_base + chunk_off,
					     msg, chunk_len);
			if (rc) {
				smc_sndbuf_sync_sg_for_device(conn);
				if (send_done)
					return send_done;
				goto out_err;
			}
			send_done += chunk_len;
			send_remaining -= chunk_len;

			if (chunk_len_sum == copylen)
				break; /* either on 1st or 2nd iteration */