summaryrefslogtreecommitdiff
path: root/net/smc/smc_tx.c
blob: 436ac836f3636081d26350e7aaf227d84d9a39e7 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
// 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"
#include "smc_stats.h"
#include "smc_tracepoint.h"

#define SMC_TX_WORK_DELAY	0

/***************************** 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) {
		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
 */
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;
	}

	if (sk->sk_state == SMC_INIT)
		return -ENOTCONN;

	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;
		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 */
			/* 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;
		/* 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) ||
		       msg->msg_flags & MSG_SENDPAGE_NOTLAST) &&
		      atomic_read(&conn->sndbuf_space)))
			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;
}

int smc_tx_sendpage(struct smc_sock *smc, struct page *page, int offset,
		    size_t size, int flags)
{
	struct msghdr msg = {.msg_flags = flags};
	char *kaddr = kmap(page);
	struct kvec iov;
	int rc;

	iov.iov_base = kaddr + offset;
	iov.iov_len = size;
	iov_iter_kvec(&msg.msg_iter, WRITE, &iov, 1, size);
	rc = smc_tx_sendmsg(smc, &msg, size);
	kunmap(page);
	return rc;
}

/***************************** sndbuf consumer *******************************/

/* 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)
{
	struct smc_ism_position pos;
	int rc;

	memset(&pos, 0, sizeof(pos));
	pos.token = conn->peer_token;
	pos.index = conn->peer_rmbe_idx;
	pos.offset = conn->tx_off + offset;
	pos.signal = signal;
	rc = smc_ism_write(conn->lgr->smcd, &pos, data, len);
	if (rc)
		conn->local_tx_ctrl.conn_state_flags.peer_conn_abort = 1;
	return rc;
}

/* sndbuf consumer: actual data transfer of one target chunk with RDMA write */
static int 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;

	rdma_wr->wr.wr_id = smc_wr_tx_get_next_wr_id(link);
	rdma_wr->wr.num_sge = num_sges;
	rdma_wr->remote_addr =
		lgr->rtokens[conn->rtoken_idx][link->link_idx].dma_addr +
		/* RMBE within RMB */
		conn->tx_off +
		/* offset within RMBE */
		peer_rmbe_offset;
	rdma_wr->rkey = lgr->rtokens[conn->rtoken_idx][link->link_idx].rkey;
	rc = ib_post_send(link->roce_qp, &rdma_wr->wr, NULL);
	if (rc)
		smcr_link_down_cond_sched(link);
	return rc;
}

/* sndbuf consumer */
static inline void smc_tx_advance_cursors(struct smc_connection *conn,
					  union smc_host_cursor *prod,
					  union smc_host_cursor *sent,
					  size_t len)
{
	smc_curs_add(conn->peer_rmbe_size, prod, len);
	/* increased in recv tasklet smc_cdc_msg_rcv() */
	smp_mb__before_atomic();
	/* data in flight reduces usable snd_wnd */
	atomic_sub(len, &conn->peer_rmbe_space);
	/* guarantee 0 <= peer_rmbe_space <= peer_rmbe_size */
	smp_mb__after_atomic();
	smc_curs_add(conn->sndbuf_desc->len, sent, len);
}

/* SMC-R helper for smc_tx_rdma_writes() */
static int smcr_tx_rdma_writes(struct smc_connection *conn, size_t len,
			       size_t src_off, size_t src_len,
			       size_t dst_off, size_t dst_len,
			       struct smc_rdma_wr *wr_rdma_buf)
{
	struct smc_link *link = conn->lnk;

	dma_addr_t dma_addr =
		sg_dma_address(conn->sndbuf_desc->sgt[link->link_idx].sgl);
	int src_len_sum = src_len, dst_len_sum = dst_len;
	int sent_count = src_off;
	int srcchunk, dstchunk;
	int num_sges;
	int rc;

	for (dstchunk = 0; dstchunk < 2; dstchunk++) {
		struct ib_sge *sge =
			wr_rdma_buf->wr_tx_rdma[dstchunk].wr.sg_list;

		num_sges = 0;
		for (srcchunk = 0; srcchunk < 2; srcchunk++) {
			sge[srcchunk].addr = dma_addr + src_off;
			sge[srcchunk].length = src_len;
			num_sges++;

			src_off += src_len;
			if (src_off >= conn->sndbuf_desc->len)
				src_off -= conn->sndbuf_desc->len;
						/* modulo in send ring */
			if (src_len_sum == dst_len)
				break; /* either on 1st or 2nd iteration */
			/* prepare next (== 2nd) iteration */
			src_len = dst_len - src_len; /* remainder */
			src_len_sum += src_len;
		}
		rc = smc_tx_rdma_write(conn, dst_off, num_sges,
				       &wr_rdma_buf->wr_tx_rdma[dstchunk]);
		if (rc)
			return rc;
		if (dst_len_sum == len)
			break; /* either on 1st or 2nd iteration */
		/* prepare next (== 2nd) iteration */
		dst_off = 0; /* modulo offset in RMBE ring buffer */
		dst_len = len - dst_len; /* remainder */
		dst_len_sum += dst_len;
		src_len = min_t(int, dst_len, conn->sndbuf_desc->len -
				sent_count);
		src_len_sum = src_len;
	}
	return 0;
}

/* SMC-D helper for smc_tx_rdma_writes() */
static int smcd_tx_rdma_writes(struct smc_connection *conn, size_t len,
			       size_t src_off, size_t src_len,
			       size_t dst_off, size_t dst_len)
{
	int src_len_sum = src_len, dst_len_sum = dst_len;
	int srcchunk, dstchunk;
	int rc;

	for (dstchunk = 0; dstchunk < 2; dstchunk++) {
		for (srcchunk = 0; srcchunk < 2; srcchunk++) {
			void *data = conn->sndbuf_desc->cpu_addr + src_off;

			rc = smcd_tx_ism_write(conn, data, src_len, dst_off +
					       sizeof(struct smcd_cdc_msg), 0);
			if (rc)
				return rc;
			dst_off += src_len;
			src_off += src_len;
			if (src_off >= conn->sndbuf_desc->len)
				src_off -= conn->sndbuf_desc->len;
						/* modulo in send ring */
			if (src_len_sum == dst_len)
				break; /* either on 1st or 2nd iteration */
			/* prepare next (== 2nd) iteration */
			src_len = dst_len - src_len; /* remainder */
			src_len_sum += src_len;
		}
		if (dst_len_sum == len)
			break; /* either on 1st or 2nd iteration */
		/* prepare next (== 2nd) iteration */
		dst_off = 0; /* modulo offset in RMBE ring buffer */
		dst_len = len - dst_len; /* remainder */
		dst_len_sum += dst_len;
		src_len = min_t(int, dst_len, conn->sndbuf_desc->len - src_off);
		src_len_sum = src_len;
	}
	return 0;
}

/* sndbuf consumer: prepare all necessary (src&dst) chunks of data transmit;
 * usable snd_wnd as max transmit
 */
static int smc_tx_rdma_writes(struct smc_connection *conn,
			      struct smc_rdma_wr *wr_rdma_buf)
{
	size_t len, src_len, dst_off, dst_len; /* current chunk values */
	union smc_host_cursor sent, prep, prod, cons;
	struct smc_cdc_producer_flags *pflags;
	int to_send, rmbespace;
	int rc;

	/* source: sndbuf */
	smc_curs_copy(&sent, &conn->tx_curs_sent, conn);
	smc_curs_copy(&prep, &conn->tx_curs_prep, conn);
	/* cf. wmem_alloc - (snd_max - snd_una) */
	to_send = smc_curs_diff(conn->sndbuf_desc->len, &sent, &prep);
	if (to_send <= 0)
		return 0;

	/* destination: RMBE */
	/* cf. snd_wnd */
	rmbespace = atomic_read(&conn->peer_rmbe_space);
	if (rmbespace <= 0) {
		struct smc_sock *smc = container_of(conn, struct smc_sock,
						    conn);
		SMC_STAT_RMB_TX_PEER_FULL(smc, !conn->lnk);
		return 0;
	}
	smc_curs_copy(&prod, &conn->local_tx_ctrl.prod, conn);
	smc_curs_copy(&cons, &conn->local_rx_ctrl.cons, conn);

	/* 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->lgr->is_smcd)
		rc = smcd_tx_rdma_writes(conn, len, sent.count, src_len,
					 dst_off, dst_len);
	else
		rc = smcr_tx_rdma_writes(conn, len, sent.count, src_len,
					 dst_off, dst_len, wr_rdma_buf);
	if (rc)
		return rc;

	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
 */
static int 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;

	if (!link || !smc_wr_tx_link_hold(link))
		return -ENOLINK;
	rc = smc_cdc_get_free_slot(conn, link, &wr_buf, &wr_rdma_buf, &pend);
	if (rc < 0) {
		smc_wr_tx_link_put(link);
		if (rc == -EBUSY) {
			struct smc_sock *smc =
				container_of(conn, struct smc_sock, conn);

			if (smc->sk.sk_err == ECONNABORTED)
				return sock_error(&smc->sk);
			if (conn->killed)
				return -EPIPE;
			rc = 0;
			mod_delayed_work(conn->lgr->tx_wq, &conn->tx_work,
					 SMC_TX_WORK_DELAY);
		}
		return rc;
	}

	spin_lock_bh(&conn->send_lock);
	if (link != conn->lnk) {
		/* link of connection changed, tx_work will restart */
		smc_wr_tx_put_slot(link,
				   (struct smc_wr_tx_pend_priv *)pend);
		rc = -ENOLINK;
		goto out_unlock;
	}
	if (!pflags->urg_data_present) {
		rc = smc_tx_rdma_writes(conn, wr_rdma_buf);
		if (rc) {
			smc_wr_tx_put_slot(link,
					   (struct smc_wr_tx_pend_priv *)pend);
			goto out_unlock;
		}
	}

	rc = smc_cdc_msg_send(conn, wr_buf, pend);
	if (!rc && pflags->urg_data_present) {
		pflags->urg_data_pending = 0;
		pflags->urg_data_present = 0;
	}

out_unlock:
	spin_unlock_bh(&conn->send_lock);
	smc_wr_tx_link_put(link);
	return rc;
}

static int smcd_tx_sndbuf_nonempty(struct smc_connection *conn)
{
	struct smc_cdc_producer_flags *pflags = &conn->local_tx_ctrl.prod_flags;
	int rc = 0;

	spin_lock_bh(&conn->send_lock);
	if (!pflags->urg_data_present)
		rc = smc_tx_rdma_writes(conn, NULL);
	if (!rc)
		rc = smcd_cdc_msg_send(conn);

	if (!rc && pflags->urg_data_present) {
		pflags->urg_data_pending = 0;
		pflags->urg_data_present = 0;
	}
	spin_unlock_bh(&conn->send_lock);
	return rc;
}

int smc_tx_sndbuf_nonempty(struct smc_connection *conn)
{
	int rc;

	if (conn->killed ||
	    conn->local_rx_ctrl.conn_state_flags.peer_conn_abort)
		return -EPIPE;	/* connection being aborted */
	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 */
		struct smc_sock *smc = container_of(conn, struct smc_sock,
						    conn);
		smc_close_wake_tx_prepared(smc);
	}
	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;

	if (smc->sk.sk_err)
		return;

	rc = smc_tx_sndbuf_nonempty(conn);
	if (!rc && conn->local_rx_ctrl.prod_flags.write_blocked &&
	    !atomic_read(&conn->bytes_to_rcv))
		conn->local_rx_ctrl.prod_flags.write_blocked = 0;
}

/* 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);

	lock_sock(&smc->sk);
	smc_tx_pending(conn);
	release_sock(&smc->sk);
}

void smc_tx_consumer_update(struct smc_connection *conn, bool force)
{
	union smc_host_cursor cfed, cons, prod;
	int sender_free = conn->rmb_desc->len;
	int to_confirm;

	smc_curs_copy(&cons, &conn->local_tx_ctrl.cons, conn);
	smc_curs_copy(&cfed, &conn->rx_curs_confirmed, conn);
	to_confirm = smc_curs_diff(conn->rmb_desc->len, &cfed, &cons);
	if (to_confirm > conn->rmbe_update_limit) {
		smc_curs_copy(&prod, &conn->local_rx_ctrl.prod, conn);
		sender_free = conn->rmb_desc->len -
			      smc_curs_diff_large(conn->rmb_desc->len,
						  &cfed, &prod);
	}

	if (conn->local_rx_ctrl.prod_flags.cons_curs_upd_req ||
	    force ||
	    ((to_confirm > conn->rmbe_update_limit) &&
	     ((sender_free <= (conn->rmb_desc->len / 2)) ||
	      conn->local_rx_ctrl.prod_flags.write_blocked))) {
		if (conn->killed ||
		    conn->local_rx_ctrl.conn_state_flags.peer_conn_abort)
			return;
		if ((smc_cdc_get_slot_and_msg_send(conn) < 0) &&
		    !conn->killed) {
			queue_delayed_work(conn->lgr->tx_wq, &conn->tx_work,
					   SMC_TX_WORK_DELAY);
			return;
		}
	}
	if (conn->local_rx_ctrl.prod_flags.write_blocked &&
	    !atomic_read(&conn->bytes_to_rcv))
		conn->local_rx_ctrl.prod_flags.write_blocked = 0;
}

/***************************** send initialize *******************************/

/* Initialize send properties on connection establishment. NB: not __init! */
void smc_tx_init(struct smc_sock *smc)
{
	smc->sk.sk_write_space = smc_tx_write_space;
}