summaryrefslogtreecommitdiffstats
path: root/net/sunrpc/xprtrdma/svc_rdma_backchannel.c
blob: fc4535ead7c2293490d91815596412b784d1c9e0 (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
/*
 * Copyright (c) 2015 Oracle.  All rights reserved.
 *
 * Support for backward direction RPCs on RPC/RDMA (server-side).
 */

#include <linux/sunrpc/svc_rdma.h>
#include "xprt_rdma.h"

#define RPCDBG_FACILITY	RPCDBG_SVCXPRT

#undef SVCRDMA_BACKCHANNEL_DEBUG

int svc_rdma_handle_bc_reply(struct rpc_xprt *xprt, struct rpcrdma_msg *rmsgp,
			     struct xdr_buf *rcvbuf)
{
	struct rpcrdma_xprt *r_xprt = rpcx_to_rdmax(xprt);
	struct kvec *dst, *src = &rcvbuf->head[0];
	struct rpc_rqst *req;
	unsigned long cwnd;
	u32 credits;
	size_t len;
	__be32 xid;
	__be32 *p;
	int ret;

	p = (__be32 *)src->iov_base;
	len = src->iov_len;
	xid = rmsgp->rm_xid;

#ifdef SVCRDMA_BACKCHANNEL_DEBUG
	pr_info("%s: xid=%08x, length=%zu\n",
		__func__, be32_to_cpu(xid), len);
	pr_info("%s: RPC/RDMA: %*ph\n",
		__func__, (int)RPCRDMA_HDRLEN_MIN, rmsgp);
	pr_info("%s:      RPC: %*ph\n",
		__func__, (int)len, p);
#endif

	ret = -EAGAIN;
	if (src->iov_len < 24)
		goto out_shortreply;

	spin_lock_bh(&xprt->transport_lock);
	req = xprt_lookup_rqst(xprt, xid);
	if (!req)
		goto out_notfound;

	dst = &req->rq_private_buf.head[0];
	memcpy(&req->rq_private_buf, &req->rq_rcv_buf, sizeof(struct xdr_buf));
	if (dst->iov_len < len)
		goto out_unlock;
	memcpy(dst->iov_base, p, len);

	credits = be32_to_cpu(rmsgp->rm_credit);
	if (credits == 0)
		credits = 1;	/* don't deadlock */
	else if (credits > r_xprt->rx_buf.rb_bc_max_requests)
		credits = r_xprt->rx_buf.rb_bc_max_requests;

	cwnd = xprt->cwnd;
	xprt->cwnd = credits << RPC_CWNDSHIFT;
	if (xprt->cwnd > cwnd)
		xprt_release_rqst_cong(req->rq_task);

	ret = 0;
	xprt_complete_rqst(req->rq_task, rcvbuf->len);
	rcvbuf->len = 0;

out_unlock:
	spin_unlock_bh(&xprt->transport_lock);
out:
	return ret;

out_shortreply:
	dprintk("svcrdma: short bc reply: xprt=%p, len=%zu\n",
		xprt, src->iov_len);
	goto out;

out_notfound:
	dprintk("svcrdma: unrecognized bc reply: xprt=%p, xid=%08x\n",
		xprt, be32_to_cpu(xid));

	goto out_unlock;
}

/* Send a backwards direction RPC call.
 *
 * Caller holds the connection's mutex and has already marshaled
 * the RPC/RDMA request.
 *
 * This is similar to svc_rdma_reply, but takes an rpc_rqst
 * instead, does not support chunks, and avoids blocking memory
 * allocation.
 *
 * XXX: There is still an opportunity to block in svc_rdma_send()
 * if there are no SQ entries to post the Send. This may occur if
 * the adapter has a small maximum SQ depth.
 */
static int svc_rdma_bc_sendto(struct svcxprt_rdma *rdma,
			      struct rpc_rqst *rqst)
{
	struct xdr_buf *sndbuf = &rqst->rq_snd_buf;
	struct svc_rdma_op_ctxt *ctxt;
	struct svc_rdma_req_map *vec;
	struct ib_send_wr send_wr;
	int ret;

	vec = svc_rdma_get_req_map(rdma);
	ret = svc_rdma_map_xdr(rdma, sndbuf, vec, false);
	if (ret)
		goto out_err;

	ret = svc_rdma_repost_recv(rdma, GFP_NOIO);
	if (ret)
		goto out_err;

	ctxt = svc_rdma_get_context(rdma);
	ctxt->pages[0] = virt_to_page(rqst->rq_buffer);
	ctxt->count = 1;

	ctxt->direction = DMA_TO_DEVICE;
	ctxt->sge[0].lkey = rdma->sc_pd->local_dma_lkey;
	ctxt->sge[0].length = sndbuf->len;
	ctxt->sge[0].addr =
	    ib_dma_map_page(rdma->sc_cm_id->device, ctxt->pages[0], 0,
			    sndbuf->len, DMA_TO_DEVICE);
	if (ib_dma_mapping_error(rdma->sc_cm_id->device, ctxt->sge[0].addr)) {
		ret = -EIO;
		goto out_unmap;
	}
	svc_rdma_count_mappings(rdma, ctxt);

	memset(&send_wr, 0, sizeof(send_wr));
	ctxt->cqe.done = svc_rdma_wc_send;
	send_wr.wr_cqe = &ctxt->cqe;
	send_wr.sg_list = ctxt->sge;
	send_wr.num_sge = 1;
	send_wr.opcode = IB_WR_SEND;
	send_wr.send_flags = IB_SEND_SIGNALED;

	ret = svc_rdma_send(rdma, &send_wr);
	if (ret) {
		ret = -EIO;
		goto out_unmap;
	}

out_err:
	svc_rdma_put_req_map(rdma, vec);
	dprintk("svcrdma: %s returns %d\n", __func__, ret);
	return ret;

out_unmap:
	svc_rdma_unmap_dma(ctxt);
	svc_rdma_put_context(ctxt, 1);
	goto out_err;
}

/* Server-side transport endpoint wants a whole page for its send
 * buffer. The client RPC code constructs the RPC header in this
 * buffer before it invokes ->send_request.
 */
static int
xprt_rdma_bc_allocate(struct rpc_task *task)
{
	struct rpc_rqst *rqst = task->tk_rqstp;
	struct svc_xprt *sxprt = rqst->rq_xprt->bc_xprt;
	size_t size = rqst->rq_callsize;
	struct svcxprt_rdma *rdma;
	struct page *page;

	rdma = container_of(sxprt, struct svcxprt_rdma, sc_xprt);

	if (size > PAGE_SIZE) {
		WARN_ONCE(1, "svcrdma: large bc buffer request (size %zu)\n",
			  size);
		return -EINVAL;
	}

	page = alloc_page(RPCRDMA_DEF_GFP);
	if (!page)
		return -ENOMEM;

	rqst->rq_buffer = page_address(page);
	rqst->rq_rbuffer = (char *)rqst->rq_buffer + rqst->rq_callsize;
	return 0;
}

static void
xprt_rdma_bc_free(struct rpc_task *task)
{
	/* No-op: ctxt and page have already been freed. */
}

static int
rpcrdma_bc_send_request(struct svcxprt_rdma *rdma, struct rpc_rqst *rqst)
{
	struct rpc_xprt *xprt = rqst->rq_xprt;
	struct rpcrdma_xprt *r_xprt = rpcx_to_rdmax(xprt);
	struct rpcrdma_msg *headerp = (struct rpcrdma_msg *)rqst->rq_buffer;
	int rc;

	/* Space in the send buffer for an RPC/RDMA header is reserved
	 * via xprt->tsh_size.
	 */
	headerp->rm_xid = rqst->rq_xid;
	headerp->rm_vers = rpcrdma_version;
	headerp->rm_credit = cpu_to_be32(r_xprt->rx_buf.rb_bc_max_requests);
	headerp->rm_type = rdma_msg;
	headerp->rm_body.rm_chunks[0] = xdr_zero;
	headerp->rm_body.rm_chunks[1] = xdr_zero;
	headerp->rm_body.rm_chunks[2] = xdr_zero;

#ifdef SVCRDMA_BACKCHANNEL_DEBUG
	pr_info("%s: %*ph\n", __func__, 64, rqst->rq_buffer);
#endif

	rc = svc_rdma_bc_sendto(rdma, rqst);
	if (rc)
		goto drop_connection;
	return rc;

drop_connection:
	dprintk("svcrdma: failed to send bc call\n");
	xprt_disconnect_done(xprt);
	return -ENOTCONN;
}

/* Send an RPC call on the passive end of a transport
 * connection.
 */
static int
xprt_rdma_bc_send_request(struct rpc_task *task)
{
	struct rpc_rqst *rqst = task->tk_rqstp;
	struct svc_xprt *sxprt = rqst->rq_xprt->bc_xprt;
	struct svcxprt_rdma *rdma;
	int ret;

	dprintk("svcrdma: sending bc call with xid: %08x\n",
		be32_to_cpu(rqst->rq_xid));

	if (!mutex_trylock(&sxprt->xpt_mutex)) {
		rpc_sleep_on(&sxprt->xpt_bc_pending, task, NULL);
		if (!mutex_trylock(&sxprt->xpt_mutex))
			return -EAGAIN;
		rpc_wake_up_queued_task(&sxprt->xpt_bc_pending, task);
	}

	ret = -ENOTCONN;
	rdma = container_of(sxprt, struct svcxprt_rdma, sc_xprt);
	if (!test_bit(XPT_DEAD, &sxprt->xpt_flags))
		ret = rpcrdma_bc_send_request(rdma, rqst);

	mutex_unlock(&sxprt->xpt_mutex);

	if (ret < 0)
		return ret;
	return 0;
}

static void
xprt_rdma_bc_close(struct rpc_xprt *xprt)
{
	dprintk("svcrdma: %s: xprt %p\n", __func__, xprt);
}

static void
xprt_rdma_bc_put(struct rpc_xprt *xprt)
{
	dprintk("svcrdma: %s: xprt %p\n", __func__, xprt);

	xprt_free(xprt);
	module_put(THIS_MODULE);
}

static struct rpc_xprt_ops xprt_rdma_bc_procs = {
	.reserve_xprt		= xprt_reserve_xprt_cong,
	.release_xprt		= xprt_release_xprt_cong,
	.alloc_slot		= xprt_alloc_slot,
	.release_request	= xprt_release_rqst_cong,
	.buf_alloc		= xprt_rdma_bc_allocate,
	.buf_free		= xprt_rdma_bc_free,
	.send_request		= xprt_rdma_bc_send_request,
	.set_retrans_timeout	= xprt_set_retrans_timeout_def,
	.close			= xprt_rdma_bc_close,
	.destroy		= xprt_rdma_bc_put,
	.print_stats		= xprt_rdma_print_stats
};

static const struct rpc_timeout xprt_rdma_bc_timeout = {
	.to_initval = 60 * HZ,
	.to_maxval = 60 * HZ,
};

/* It shouldn't matter if the number of backchannel session slots
 * doesn't match the number of RPC/RDMA credits. That just means
 * one or the other will have extra slots that aren't used.
 */
static struct rpc_xprt *
xprt_setup_rdma_bc(struct xprt_create *args)
{
	struct rpc_xprt *xprt;
	struct rpcrdma_xprt *new_xprt;

	if (args->addrlen > sizeof(xprt->addr)) {
		dprintk("RPC:       %s: address too large\n", __func__);
		return ERR_PTR(-EBADF);
	}

	xprt = xprt_alloc(args->net, sizeof(*new_xprt),
			  RPCRDMA_MAX_BC_REQUESTS,
			  RPCRDMA_MAX_BC_REQUESTS);
	if (!xprt) {
		dprintk("RPC:       %s: couldn't allocate rpc_xprt\n",
			__func__);
		return ERR_PTR(-ENOMEM);
	}

	xprt->timeout = &xprt_rdma_bc_timeout;
	xprt_set_bound(xprt);
	xprt_set_connected(xprt);
	xprt->bind_timeout = RPCRDMA_BIND_TO;
	xprt->reestablish_timeout = RPCRDMA_INIT_REEST_TO;
	xprt->idle_timeout = RPCRDMA_IDLE_DISC_TO;

	xprt->prot = XPRT_TRANSPORT_BC_RDMA;
	xprt->tsh_size = RPCRDMA_HDRLEN_MIN / sizeof(__be32);
	xprt->ops = &xprt_rdma_bc_procs;

	memcpy(&xprt->addr, args->dstaddr, args->addrlen);
	xprt->addrlen = args->addrlen;
	xprt_rdma_format_addresses(xprt, (struct sockaddr *)&xprt->addr);
	xprt->resvport = 0;

	xprt->max_payload = xprt_rdma_max_inline_read;

	new_xprt = rpcx_to_rdmax(xprt);
	new_xprt->rx_buf.rb_bc_max_requests = xprt->max_reqs;

	xprt_get(xprt);
	args->bc_xprt->xpt_bc_xprt = xprt;
	xprt->bc_xprt = args->bc_xprt;

	if (!try_module_get(THIS_MODULE))
		goto out_fail;

	/* Final put for backchannel xprt is in __svc_rdma_free */
	xprt_get(xprt);
	return xprt;

out_fail:
	xprt_rdma_free_addresses(xprt);
	args->bc_xprt->xpt_bc_xprt = NULL;
	xprt_put(xprt);
	xprt_free(xprt);
	return ERR_PTR(-EINVAL);
}

struct xprt_class xprt_rdma_bc = {
	.list			= LIST_HEAD_INIT(xprt_rdma_bc.list),
	.name			= "rdma backchannel",
	.owner			= THIS_MODULE,
	.ident			= XPRT_TRANSPORT_BC_RDMA,
	.setup			= xprt_setup_rdma_bc,
};