// 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>
*/
/* callback implementation for sk.sk_write_space() * to wakeup sndbuf producers that blocked with smc_tx_wait(). * called under sk_socket lock.
*/ staticvoid 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) { if (test_bit(SOCK_NOSPACE, &sock->flags))
SMC_STAT_RMB_TX_FULL(smc, !smc->conn.lnk);
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
*/ staticint 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,
READ_ONCE(sk->sk_err) ||
(READ_ONCE(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;
}
/* If we have pending CDC messages, do not send: * Because CQE of this CDC message will happen shortly, it gives * a chance to coalesce future sendmsg() payload in to one RDMA Write, * without need for a timer, and with no latency trade off. * Algorithm here: * 1. First message should never cork * 2. If we have pending Tx CDC messages, wait for the first CDC * message's completion * 3. Don't cork to much data in a single RDMA Write to prevent burst * traffic, total corked message should not exceed sendbuf/2
*/ staticbool smc_should_autocork(struct smc_sock *smc)
{ struct smc_connection *conn = &smc->conn; int corking_size;
/* for a corked socket defer the RDMA writes if * sndbuf_space is still available. The applications * should known how/when to uncork it.
*/ if ((msg->msg_flags & MSG_MORE ||
smc_tx_is_corked(smc)) &&
atomic_read(&conn->sndbuf_space)) returntrue;
returnfalse;
}
/* 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 (len > conn->sndbuf_desc->len)
SMC_STAT_RMB_TX_SIZE_SMALL(smc, !conn->lnk);
if (len > conn->peer_rmbe_size)
SMC_STAT_RMB_TX_PEER_SIZE_SMALL(smc, !conn->lnk);
if (msg->msg_flags & MSG_OOB)
SMC_STAT_INC(smc, urg_data_cnt);
while (msg_data_left(msg)) { 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; 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 */ /* prepare next (== 2nd) iteration */
chunk_len = copylen - chunk_len; /* remainder */
chunk_len_sum += chunk_len;
chunk_off = 0; /* modulo offset in send ring buffer */
}
smc_sndbuf_sync_sg_for_device(conn); /* update cursors */
smc_curs_add(conn->sndbuf_desc->len, &prep, copylen);
smc_curs_copy(&conn->tx_curs_prep, &prep, conn); /* increased in send tasklet smc_cdc_tx_handler() */
smp_mb__before_atomic();
atomic_sub(copylen, &conn->sndbuf_space); /* guarantee 0 <= sndbuf_space <= sndbuf_desc->len */
smp_mb__after_atomic(); /* since we just produced more new data into sndbuf, * trigger sndbuf consumer: RDMA write into peer RMBE and CDC
*/ if ((msg->msg_flags & MSG_OOB) && !send_remaining)
conn->urg_tx_pend = true; /* If we need to cork, do nothing and wait for the next * sendmsg() call or push on tx completion
*/ if (!smc_tx_should_cork(smc, msg))
smc_tx_sndbuf_nonempty(conn);
trace_smc_tx_sendmsg(smc, copylen);
} /* while (msg_data_left(msg)) */
return send_done;
out_err:
rc = sk_stream_error(sk, msg->msg_flags, rc); /* make sure we wake any epoll edge trigger waiter */ if (unlikely(rc == -EAGAIN))
sk->sk_write_space(sk); return rc;
}
/* sndbuf consumer: actual data transfer of one target chunk with ISM write */ int smcd_tx_ism_write(struct smc_connection *conn, void *data, size_t len,
u32 offset, int signal)
{ int rc;
/* sndbuf consumer: actual data transfer of one target chunk with RDMA write */ staticint smc_tx_rdma_write(struct smc_connection *conn, int peer_rmbe_offset, int num_sges, struct ib_rdma_wr *rdma_wr)
{ struct smc_link_group *lgr = conn->lgr; struct smc_link *link = conn->lnk; int rc;
/* if usable snd_wnd closes ask peer to advertise once it opens again */
pflags = &conn->local_tx_ctrl.prod_flags;
pflags->write_blocked = (to_send >= rmbespace); /* cf. usable snd_wnd */
len = min(to_send, rmbespace);
/* initialize variables for first iteration of subsequent nested loop */
dst_off = prod.count; if (prod.wrap == cons.wrap) { /* the filled destination area is unwrapped, * hence the available free destination space is wrapped * and we need 2 destination chunks of sum len; start with 1st * which is limited by what's available in sndbuf
*/
dst_len = min_t(size_t,
conn->peer_rmbe_size - prod.count, len);
} else { /* the filled destination area is wrapped, * hence the available free destination space is unwrapped * and we need a single destination chunk of entire len
*/
dst_len = len;
} /* dst_len determines the maximum src_len */ if (sent.count + dst_len <= conn->sndbuf_desc->len) { /* unwrapped src case: single chunk of entire dst_len */
src_len = dst_len;
} else { /* wrapped src case: 2 chunks of sum dst_len; start with 1st: */
src_len = conn->sndbuf_desc->len - sent.count;
}
if (conn->urg_tx_pend && len == to_send)
pflags->urg_data_present = 1;
smc_tx_advance_cursors(conn, &prod, &sent, len); /* update connection's cursors with advanced local cursors */
smc_curs_copy(&conn->local_tx_ctrl.prod, &prod, conn); /* dst: peer RMBE */
smc_curs_copy(&conn->tx_curs_sent, &sent, conn);/* src: local sndbuf */
return 0;
}
/* Wakeup sndbuf consumers from any context (IRQ or process) * since there is more data to transmit; usable snd_wnd as max transmit
*/ staticint smcr_tx_sndbuf_nonempty(struct smc_connection *conn)
{ struct smc_cdc_producer_flags *pflags = &conn->local_tx_ctrl.prod_flags; struct smc_link *link = conn->lnk; struct smc_rdma_wr *wr_rdma_buf; struct smc_cdc_tx_pend *pend; struct smc_wr_buf *wr_buf; int rc;
int smc_tx_sndbuf_nonempty(struct smc_connection *conn)
{ struct smc_sock *smc = container_of(conn, struct smc_sock, conn); int rc = 0;
/* No data in the send queue */ if (unlikely(smc_tx_prepared_sends(conn) <= 0)) goto out;
/* Peer don't have RMBE space */ if (unlikely(atomic_read(&conn->peer_rmbe_space) <= 0)) {
SMC_STAT_RMB_TX_PEER_FULL(smc, !conn->lnk); goto out;
}
if (conn->killed ||
conn->local_rx_ctrl.conn_state_flags.peer_conn_abort) {
rc = -EPIPE; /* connection being aborted */ goto out;
} if (conn->lgr->is_smcd)
rc = smcd_tx_sndbuf_nonempty(conn); else
rc = smcr_tx_sndbuf_nonempty(conn);
if (!rc) { /* trigger socket release if connection is closing */
smc_close_wake_tx_prepared(smc);
}
out: return rc;
}
/* Wakeup sndbuf consumers from process context * since there is more data to transmit. The caller * must hold sock lock.
*/ void smc_tx_pending(struct smc_connection *conn)
{ struct smc_sock *smc = container_of(conn, struct smc_sock, conn); int rc;
/* Wakeup sndbuf consumers from process context * since there is more data to transmit in locked * sock.
*/ void smc_tx_work(struct work_struct *work)
{ struct smc_connection *conn = container_of(to_delayed_work(work), struct smc_connection,
tx_work); struct smc_sock *smc = container_of(conn, struct smc_sock, conn);
Die Informationen auf dieser Webseite wurden
nach bestem Wissen sorgfältig zusammengestellt. Es wird jedoch weder Vollständigkeit, noch Richtigkeit,
noch Qualität der bereit gestellten Informationen zugesichert.
Bemerkung:
Die farbliche Syntaxdarstellung und die Messung sind noch experimentell.