1/*
2 * Copyright(c) 2015 - 2020 Intel Corporation.
3 *
4 * This file is provided under a dual BSD/GPLv2 license.  When using or
5 * redistributing this file, you may do so under either license.
6 *
7 * GPL LICENSE SUMMARY
8 *
9 * This program is free software; you can redistribute it and/or modify
10 * it under the terms of version 2 of the GNU General Public License as
11 * published by the Free Software Foundation.
12 *
13 * This program is distributed in the hope that it will be useful, but
14 * WITHOUT ANY WARRANTY; without even the implied warranty of
15 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
16 * General Public License for more details.
17 *
18 * BSD LICENSE
19 *
20 * Redistribution and use in source and binary forms, with or without
21 * modification, are permitted provided that the following conditions
22 * are met:
23 *
24 *  - Redistributions of source code must retain the above copyright
25 *    notice, this list of conditions and the following disclaimer.
26 *  - Redistributions in binary form must reproduce the above copyright
27 *    notice, this list of conditions and the following disclaimer in
28 *    the documentation and/or other materials provided with the
29 *    distribution.
30 *  - Neither the name of Intel Corporation nor the names of its
31 *    contributors may be used to endorse or promote products derived
32 *    from this software without specific prior written permission.
33 *
34 * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
35 * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
36 * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
37 * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
38 * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
39 * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
40 * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
41 * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
42 * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
43 * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
44 * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
45 *
46 */
47
48#include <rdma/ib_mad.h>
49#include <rdma/ib_user_verbs.h>
50#include <linux/io.h>
51#include <linux/module.h>
52#include <linux/utsname.h>
53#include <linux/rculist.h>
54#include <linux/mm.h>
55#include <linux/vmalloc.h>
56#include <rdma/opa_addr.h>
57#include <linux/nospec.h>
58
59#include "hfi.h"
60#include "common.h"
61#include "device.h"
62#include "trace.h"
63#include "qp.h"
64#include "verbs_txreq.h"
65#include "debugfs.h"
66#include "vnic.h"
67#include "fault.h"
68#include "affinity.h"
69#include "ipoib.h"
70
71static unsigned int hfi1_lkey_table_size = 16;
72module_param_named(lkey_table_size, hfi1_lkey_table_size, uint,
73		   S_IRUGO);
74MODULE_PARM_DESC(lkey_table_size,
75		 "LKEY table size in bits (2^n, 1 <= n <= 23)");
76
77static unsigned int hfi1_max_pds = 0xFFFF;
78module_param_named(max_pds, hfi1_max_pds, uint, S_IRUGO);
79MODULE_PARM_DESC(max_pds,
80		 "Maximum number of protection domains to support");
81
82static unsigned int hfi1_max_ahs = 0xFFFF;
83module_param_named(max_ahs, hfi1_max_ahs, uint, S_IRUGO);
84MODULE_PARM_DESC(max_ahs, "Maximum number of address handles to support");
85
86unsigned int hfi1_max_cqes = 0x2FFFFF;
87module_param_named(max_cqes, hfi1_max_cqes, uint, S_IRUGO);
88MODULE_PARM_DESC(max_cqes,
89		 "Maximum number of completion queue entries to support");
90
91unsigned int hfi1_max_cqs = 0x1FFFF;
92module_param_named(max_cqs, hfi1_max_cqs, uint, S_IRUGO);
93MODULE_PARM_DESC(max_cqs, "Maximum number of completion queues to support");
94
95unsigned int hfi1_max_qp_wrs = 0x3FFF;
96module_param_named(max_qp_wrs, hfi1_max_qp_wrs, uint, S_IRUGO);
97MODULE_PARM_DESC(max_qp_wrs, "Maximum number of QP WRs to support");
98
99unsigned int hfi1_max_qps = 32768;
100module_param_named(max_qps, hfi1_max_qps, uint, S_IRUGO);
101MODULE_PARM_DESC(max_qps, "Maximum number of QPs to support");
102
103unsigned int hfi1_max_sges = 0x60;
104module_param_named(max_sges, hfi1_max_sges, uint, S_IRUGO);
105MODULE_PARM_DESC(max_sges, "Maximum number of SGEs to support");
106
107unsigned int hfi1_max_mcast_grps = 16384;
108module_param_named(max_mcast_grps, hfi1_max_mcast_grps, uint, S_IRUGO);
109MODULE_PARM_DESC(max_mcast_grps,
110		 "Maximum number of multicast groups to support");
111
112unsigned int hfi1_max_mcast_qp_attached = 16;
113module_param_named(max_mcast_qp_attached, hfi1_max_mcast_qp_attached,
114		   uint, S_IRUGO);
115MODULE_PARM_DESC(max_mcast_qp_attached,
116		 "Maximum number of attached QPs to support");
117
118unsigned int hfi1_max_srqs = 1024;
119module_param_named(max_srqs, hfi1_max_srqs, uint, S_IRUGO);
120MODULE_PARM_DESC(max_srqs, "Maximum number of SRQs to support");
121
122unsigned int hfi1_max_srq_sges = 128;
123module_param_named(max_srq_sges, hfi1_max_srq_sges, uint, S_IRUGO);
124MODULE_PARM_DESC(max_srq_sges, "Maximum number of SRQ SGEs to support");
125
126unsigned int hfi1_max_srq_wrs = 0x1FFFF;
127module_param_named(max_srq_wrs, hfi1_max_srq_wrs, uint, S_IRUGO);
128MODULE_PARM_DESC(max_srq_wrs, "Maximum number of SRQ WRs support");
129
130unsigned short piothreshold = 256;
131module_param(piothreshold, ushort, S_IRUGO);
132MODULE_PARM_DESC(piothreshold, "size used to determine sdma vs. pio");
133
134static unsigned int sge_copy_mode;
135module_param(sge_copy_mode, uint, S_IRUGO);
136MODULE_PARM_DESC(sge_copy_mode,
137		 "Verbs copy mode: 0 use memcpy, 1 use cacheless copy, 2 adapt based on WSS");
138
139static void verbs_sdma_complete(
140	struct sdma_txreq *cookie,
141	int status);
142
143static int pio_wait(struct rvt_qp *qp,
144		    struct send_context *sc,
145		    struct hfi1_pkt_state *ps,
146		    u32 flag);
147
148/* Length of buffer to create verbs txreq cache name */
149#define TXREQ_NAME_LEN 24
150
151static uint wss_threshold = 80;
152module_param(wss_threshold, uint, S_IRUGO);
153MODULE_PARM_DESC(wss_threshold, "Percentage (1-100) of LLC to use as a threshold for a cacheless copy");
154static uint wss_clean_period = 256;
155module_param(wss_clean_period, uint, S_IRUGO);
156MODULE_PARM_DESC(wss_clean_period, "Count of verbs copies before an entry in the page copy table is cleaned");
157
158/*
159 * Translate ib_wr_opcode into ib_wc_opcode.
160 */
161const enum ib_wc_opcode ib_hfi1_wc_opcode[] = {
162	[IB_WR_RDMA_WRITE] = IB_WC_RDMA_WRITE,
163	[IB_WR_TID_RDMA_WRITE] = IB_WC_RDMA_WRITE,
164	[IB_WR_RDMA_WRITE_WITH_IMM] = IB_WC_RDMA_WRITE,
165	[IB_WR_SEND] = IB_WC_SEND,
166	[IB_WR_SEND_WITH_IMM] = IB_WC_SEND,
167	[IB_WR_RDMA_READ] = IB_WC_RDMA_READ,
168	[IB_WR_TID_RDMA_READ] = IB_WC_RDMA_READ,
169	[IB_WR_ATOMIC_CMP_AND_SWP] = IB_WC_COMP_SWAP,
170	[IB_WR_ATOMIC_FETCH_AND_ADD] = IB_WC_FETCH_ADD,
171	[IB_WR_SEND_WITH_INV] = IB_WC_SEND,
172	[IB_WR_LOCAL_INV] = IB_WC_LOCAL_INV,
173	[IB_WR_REG_MR] = IB_WC_REG_MR
174};
175
176/*
177 * Length of header by opcode, 0 --> not supported
178 */
179const u8 hdr_len_by_opcode[256] = {
180	/* RC */
181	[IB_OPCODE_RC_SEND_FIRST]                     = 12 + 8,
182	[IB_OPCODE_RC_SEND_MIDDLE]                    = 12 + 8,
183	[IB_OPCODE_RC_SEND_LAST]                      = 12 + 8,
184	[IB_OPCODE_RC_SEND_LAST_WITH_IMMEDIATE]       = 12 + 8 + 4,
185	[IB_OPCODE_RC_SEND_ONLY]                      = 12 + 8,
186	[IB_OPCODE_RC_SEND_ONLY_WITH_IMMEDIATE]       = 12 + 8 + 4,
187	[IB_OPCODE_RC_RDMA_WRITE_FIRST]               = 12 + 8 + 16,
188	[IB_OPCODE_RC_RDMA_WRITE_MIDDLE]              = 12 + 8,
189	[IB_OPCODE_RC_RDMA_WRITE_LAST]                = 12 + 8,
190	[IB_OPCODE_RC_RDMA_WRITE_LAST_WITH_IMMEDIATE] = 12 + 8 + 4,
191	[IB_OPCODE_RC_RDMA_WRITE_ONLY]                = 12 + 8 + 16,
192	[IB_OPCODE_RC_RDMA_WRITE_ONLY_WITH_IMMEDIATE] = 12 + 8 + 20,
193	[IB_OPCODE_RC_RDMA_READ_REQUEST]              = 12 + 8 + 16,
194	[IB_OPCODE_RC_RDMA_READ_RESPONSE_FIRST]       = 12 + 8 + 4,
195	[IB_OPCODE_RC_RDMA_READ_RESPONSE_MIDDLE]      = 12 + 8,
196	[IB_OPCODE_RC_RDMA_READ_RESPONSE_LAST]        = 12 + 8 + 4,
197	[IB_OPCODE_RC_RDMA_READ_RESPONSE_ONLY]        = 12 + 8 + 4,
198	[IB_OPCODE_RC_ACKNOWLEDGE]                    = 12 + 8 + 4,
199	[IB_OPCODE_RC_ATOMIC_ACKNOWLEDGE]             = 12 + 8 + 4 + 8,
200	[IB_OPCODE_RC_COMPARE_SWAP]                   = 12 + 8 + 28,
201	[IB_OPCODE_RC_FETCH_ADD]                      = 12 + 8 + 28,
202	[IB_OPCODE_RC_SEND_LAST_WITH_INVALIDATE]      = 12 + 8 + 4,
203	[IB_OPCODE_RC_SEND_ONLY_WITH_INVALIDATE]      = 12 + 8 + 4,
204	[IB_OPCODE_TID_RDMA_READ_REQ]                 = 12 + 8 + 36,
205	[IB_OPCODE_TID_RDMA_READ_RESP]                = 12 + 8 + 36,
206	[IB_OPCODE_TID_RDMA_WRITE_REQ]                = 12 + 8 + 36,
207	[IB_OPCODE_TID_RDMA_WRITE_RESP]               = 12 + 8 + 36,
208	[IB_OPCODE_TID_RDMA_WRITE_DATA]               = 12 + 8 + 36,
209	[IB_OPCODE_TID_RDMA_WRITE_DATA_LAST]          = 12 + 8 + 36,
210	[IB_OPCODE_TID_RDMA_ACK]                      = 12 + 8 + 36,
211	[IB_OPCODE_TID_RDMA_RESYNC]                   = 12 + 8 + 36,
212	/* UC */
213	[IB_OPCODE_UC_SEND_FIRST]                     = 12 + 8,
214	[IB_OPCODE_UC_SEND_MIDDLE]                    = 12 + 8,
215	[IB_OPCODE_UC_SEND_LAST]                      = 12 + 8,
216	[IB_OPCODE_UC_SEND_LAST_WITH_IMMEDIATE]       = 12 + 8 + 4,
217	[IB_OPCODE_UC_SEND_ONLY]                      = 12 + 8,
218	[IB_OPCODE_UC_SEND_ONLY_WITH_IMMEDIATE]       = 12 + 8 + 4,
219	[IB_OPCODE_UC_RDMA_WRITE_FIRST]               = 12 + 8 + 16,
220	[IB_OPCODE_UC_RDMA_WRITE_MIDDLE]              = 12 + 8,
221	[IB_OPCODE_UC_RDMA_WRITE_LAST]                = 12 + 8,
222	[IB_OPCODE_UC_RDMA_WRITE_LAST_WITH_IMMEDIATE] = 12 + 8 + 4,
223	[IB_OPCODE_UC_RDMA_WRITE_ONLY]                = 12 + 8 + 16,
224	[IB_OPCODE_UC_RDMA_WRITE_ONLY_WITH_IMMEDIATE] = 12 + 8 + 20,
225	/* UD */
226	[IB_OPCODE_UD_SEND_ONLY]                      = 12 + 8 + 8,
227	[IB_OPCODE_UD_SEND_ONLY_WITH_IMMEDIATE]       = 12 + 8 + 12
228};
229
230static const opcode_handler opcode_handler_tbl[256] = {
231	/* RC */
232	[IB_OPCODE_RC_SEND_FIRST]                     = &hfi1_rc_rcv,
233	[IB_OPCODE_RC_SEND_MIDDLE]                    = &hfi1_rc_rcv,
234	[IB_OPCODE_RC_SEND_LAST]                      = &hfi1_rc_rcv,
235	[IB_OPCODE_RC_SEND_LAST_WITH_IMMEDIATE]       = &hfi1_rc_rcv,
236	[IB_OPCODE_RC_SEND_ONLY]                      = &hfi1_rc_rcv,
237	[IB_OPCODE_RC_SEND_ONLY_WITH_IMMEDIATE]       = &hfi1_rc_rcv,
238	[IB_OPCODE_RC_RDMA_WRITE_FIRST]               = &hfi1_rc_rcv,
239	[IB_OPCODE_RC_RDMA_WRITE_MIDDLE]              = &hfi1_rc_rcv,
240	[IB_OPCODE_RC_RDMA_WRITE_LAST]                = &hfi1_rc_rcv,
241	[IB_OPCODE_RC_RDMA_WRITE_LAST_WITH_IMMEDIATE] = &hfi1_rc_rcv,
242	[IB_OPCODE_RC_RDMA_WRITE_ONLY]                = &hfi1_rc_rcv,
243	[IB_OPCODE_RC_RDMA_WRITE_ONLY_WITH_IMMEDIATE] = &hfi1_rc_rcv,
244	[IB_OPCODE_RC_RDMA_READ_REQUEST]              = &hfi1_rc_rcv,
245	[IB_OPCODE_RC_RDMA_READ_RESPONSE_FIRST]       = &hfi1_rc_rcv,
246	[IB_OPCODE_RC_RDMA_READ_RESPONSE_MIDDLE]      = &hfi1_rc_rcv,
247	[IB_OPCODE_RC_RDMA_READ_RESPONSE_LAST]        = &hfi1_rc_rcv,
248	[IB_OPCODE_RC_RDMA_READ_RESPONSE_ONLY]        = &hfi1_rc_rcv,
249	[IB_OPCODE_RC_ACKNOWLEDGE]                    = &hfi1_rc_rcv,
250	[IB_OPCODE_RC_ATOMIC_ACKNOWLEDGE]             = &hfi1_rc_rcv,
251	[IB_OPCODE_RC_COMPARE_SWAP]                   = &hfi1_rc_rcv,
252	[IB_OPCODE_RC_FETCH_ADD]                      = &hfi1_rc_rcv,
253	[IB_OPCODE_RC_SEND_LAST_WITH_INVALIDATE]      = &hfi1_rc_rcv,
254	[IB_OPCODE_RC_SEND_ONLY_WITH_INVALIDATE]      = &hfi1_rc_rcv,
255
256	/* TID RDMA has separate handlers for different opcodes.*/
257	[IB_OPCODE_TID_RDMA_WRITE_REQ]       = &hfi1_rc_rcv_tid_rdma_write_req,
258	[IB_OPCODE_TID_RDMA_WRITE_RESP]      = &hfi1_rc_rcv_tid_rdma_write_resp,
259	[IB_OPCODE_TID_RDMA_WRITE_DATA]      = &hfi1_rc_rcv_tid_rdma_write_data,
260	[IB_OPCODE_TID_RDMA_WRITE_DATA_LAST] = &hfi1_rc_rcv_tid_rdma_write_data,
261	[IB_OPCODE_TID_RDMA_READ_REQ]        = &hfi1_rc_rcv_tid_rdma_read_req,
262	[IB_OPCODE_TID_RDMA_READ_RESP]       = &hfi1_rc_rcv_tid_rdma_read_resp,
263	[IB_OPCODE_TID_RDMA_RESYNC]          = &hfi1_rc_rcv_tid_rdma_resync,
264	[IB_OPCODE_TID_RDMA_ACK]             = &hfi1_rc_rcv_tid_rdma_ack,
265
266	/* UC */
267	[IB_OPCODE_UC_SEND_FIRST]                     = &hfi1_uc_rcv,
268	[IB_OPCODE_UC_SEND_MIDDLE]                    = &hfi1_uc_rcv,
269	[IB_OPCODE_UC_SEND_LAST]                      = &hfi1_uc_rcv,
270	[IB_OPCODE_UC_SEND_LAST_WITH_IMMEDIATE]       = &hfi1_uc_rcv,
271	[IB_OPCODE_UC_SEND_ONLY]                      = &hfi1_uc_rcv,
272	[IB_OPCODE_UC_SEND_ONLY_WITH_IMMEDIATE]       = &hfi1_uc_rcv,
273	[IB_OPCODE_UC_RDMA_WRITE_FIRST]               = &hfi1_uc_rcv,
274	[IB_OPCODE_UC_RDMA_WRITE_MIDDLE]              = &hfi1_uc_rcv,
275	[IB_OPCODE_UC_RDMA_WRITE_LAST]                = &hfi1_uc_rcv,
276	[IB_OPCODE_UC_RDMA_WRITE_LAST_WITH_IMMEDIATE] = &hfi1_uc_rcv,
277	[IB_OPCODE_UC_RDMA_WRITE_ONLY]                = &hfi1_uc_rcv,
278	[IB_OPCODE_UC_RDMA_WRITE_ONLY_WITH_IMMEDIATE] = &hfi1_uc_rcv,
279	/* UD */
280	[IB_OPCODE_UD_SEND_ONLY]                      = &hfi1_ud_rcv,
281	[IB_OPCODE_UD_SEND_ONLY_WITH_IMMEDIATE]       = &hfi1_ud_rcv,
282	/* CNP */
283	[IB_OPCODE_CNP]				      = &hfi1_cnp_rcv
284};
285
286#define OPMASK 0x1f
287
288static const u32 pio_opmask[BIT(3)] = {
289	/* RC */
290	[IB_OPCODE_RC >> 5] =
291		BIT(RC_OP(SEND_ONLY) & OPMASK) |
292		BIT(RC_OP(SEND_ONLY_WITH_IMMEDIATE) & OPMASK) |
293		BIT(RC_OP(RDMA_WRITE_ONLY) & OPMASK) |
294		BIT(RC_OP(RDMA_WRITE_ONLY_WITH_IMMEDIATE) & OPMASK) |
295		BIT(RC_OP(RDMA_READ_REQUEST) & OPMASK) |
296		BIT(RC_OP(ACKNOWLEDGE) & OPMASK) |
297		BIT(RC_OP(ATOMIC_ACKNOWLEDGE) & OPMASK) |
298		BIT(RC_OP(COMPARE_SWAP) & OPMASK) |
299		BIT(RC_OP(FETCH_ADD) & OPMASK),
300	/* UC */
301	[IB_OPCODE_UC >> 5] =
302		BIT(UC_OP(SEND_ONLY) & OPMASK) |
303		BIT(UC_OP(SEND_ONLY_WITH_IMMEDIATE) & OPMASK) |
304		BIT(UC_OP(RDMA_WRITE_ONLY) & OPMASK) |
305		BIT(UC_OP(RDMA_WRITE_ONLY_WITH_IMMEDIATE) & OPMASK),
306};
307
308/*
309 * System image GUID.
310 */
311__be64 ib_hfi1_sys_image_guid;
312
313/*
314 * Make sure the QP is ready and able to accept the given opcode.
315 */
316static inline opcode_handler qp_ok(struct hfi1_packet *packet)
317{
318	if (!(ib_rvt_state_ops[packet->qp->state] & RVT_PROCESS_RECV_OK))
319		return NULL;
320	if (((packet->opcode & RVT_OPCODE_QP_MASK) ==
321	     packet->qp->allowed_ops) ||
322	    (packet->opcode == IB_OPCODE_CNP))
323		return opcode_handler_tbl[packet->opcode];
324
325	return NULL;
326}
327
328static u64 hfi1_fault_tx(struct rvt_qp *qp, u8 opcode, u64 pbc)
329{
330#ifdef CONFIG_FAULT_INJECTION
331	if ((opcode & IB_OPCODE_MSP) == IB_OPCODE_MSP) {
332		/*
333		 * In order to drop non-IB traffic we
334		 * set PbcInsertHrc to NONE (0x2).
335		 * The packet will still be delivered
336		 * to the receiving node but a
337		 * KHdrHCRCErr (KDETH packet with a bad
338		 * HCRC) will be triggered and the
339		 * packet will not be delivered to the
340		 * correct context.
341		 */
342		pbc &= ~PBC_INSERT_HCRC_SMASK;
343		pbc |= (u64)PBC_IHCRC_NONE << PBC_INSERT_HCRC_SHIFT;
344	} else {
345		/*
346		 * In order to drop regular verbs
347		 * traffic we set the PbcTestEbp
348		 * flag. The packet will still be
349		 * delivered to the receiving node but
350		 * a 'late ebp error' will be
351		 * triggered and will be dropped.
352		 */
353		pbc |= PBC_TEST_EBP;
354	}
355#endif
356	return pbc;
357}
358
359static opcode_handler tid_qp_ok(int opcode, struct hfi1_packet *packet)
360{
361	if (packet->qp->ibqp.qp_type != IB_QPT_RC ||
362	    !(ib_rvt_state_ops[packet->qp->state] & RVT_PROCESS_RECV_OK))
363		return NULL;
364	if ((opcode & RVT_OPCODE_QP_MASK) == IB_OPCODE_TID_RDMA)
365		return opcode_handler_tbl[opcode];
366	return NULL;
367}
368
369void hfi1_kdeth_eager_rcv(struct hfi1_packet *packet)
370{
371	struct hfi1_ctxtdata *rcd = packet->rcd;
372	struct ib_header *hdr = packet->hdr;
373	u32 tlen = packet->tlen;
374	struct hfi1_pportdata *ppd = rcd->ppd;
375	struct hfi1_ibport *ibp = &ppd->ibport_data;
376	struct rvt_dev_info *rdi = &ppd->dd->verbs_dev.rdi;
377	opcode_handler opcode_handler;
378	unsigned long flags;
379	u32 qp_num;
380	int lnh;
381	u8 opcode;
382
383	/* DW == LRH (2) + BTH (3) + KDETH (9) + CRC (1) */
384	if (unlikely(tlen < 15 * sizeof(u32)))
385		goto drop;
386
387	lnh = be16_to_cpu(hdr->lrh[0]) & 3;
388	if (lnh != HFI1_LRH_BTH)
389		goto drop;
390
391	packet->ohdr = &hdr->u.oth;
392	trace_input_ibhdr(rcd->dd, packet, !!(rhf_dc_info(packet->rhf)));
393
394	opcode = (be32_to_cpu(packet->ohdr->bth[0]) >> 24);
395	inc_opstats(tlen, &rcd->opstats->stats[opcode]);
396
397	/* verbs_qp can be picked up from any tid_rdma header struct */
398	qp_num = be32_to_cpu(packet->ohdr->u.tid_rdma.r_req.verbs_qp) &
399		RVT_QPN_MASK;
400
401	rcu_read_lock();
402	packet->qp = rvt_lookup_qpn(rdi, &ibp->rvp, qp_num);
403	if (!packet->qp)
404		goto drop_rcu;
405	spin_lock_irqsave(&packet->qp->r_lock, flags);
406	opcode_handler = tid_qp_ok(opcode, packet);
407	if (likely(opcode_handler))
408		opcode_handler(packet);
409	else
410		goto drop_unlock;
411	spin_unlock_irqrestore(&packet->qp->r_lock, flags);
412	rcu_read_unlock();
413
414	return;
415drop_unlock:
416	spin_unlock_irqrestore(&packet->qp->r_lock, flags);
417drop_rcu:
418	rcu_read_unlock();
419drop:
420	ibp->rvp.n_pkt_drops++;
421}
422
423void hfi1_kdeth_expected_rcv(struct hfi1_packet *packet)
424{
425	struct hfi1_ctxtdata *rcd = packet->rcd;
426	struct ib_header *hdr = packet->hdr;
427	u32 tlen = packet->tlen;
428	struct hfi1_pportdata *ppd = rcd->ppd;
429	struct hfi1_ibport *ibp = &ppd->ibport_data;
430	struct rvt_dev_info *rdi = &ppd->dd->verbs_dev.rdi;
431	opcode_handler opcode_handler;
432	unsigned long flags;
433	u32 qp_num;
434	int lnh;
435	u8 opcode;
436
437	/* DW == LRH (2) + BTH (3) + KDETH (9) + CRC (1) */
438	if (unlikely(tlen < 15 * sizeof(u32)))
439		goto drop;
440
441	lnh = be16_to_cpu(hdr->lrh[0]) & 3;
442	if (lnh != HFI1_LRH_BTH)
443		goto drop;
444
445	packet->ohdr = &hdr->u.oth;
446	trace_input_ibhdr(rcd->dd, packet, !!(rhf_dc_info(packet->rhf)));
447
448	opcode = (be32_to_cpu(packet->ohdr->bth[0]) >> 24);
449	inc_opstats(tlen, &rcd->opstats->stats[opcode]);
450
451	/* verbs_qp can be picked up from any tid_rdma header struct */
452	qp_num = be32_to_cpu(packet->ohdr->u.tid_rdma.r_rsp.verbs_qp) &
453		RVT_QPN_MASK;
454
455	rcu_read_lock();
456	packet->qp = rvt_lookup_qpn(rdi, &ibp->rvp, qp_num);
457	if (!packet->qp)
458		goto drop_rcu;
459	spin_lock_irqsave(&packet->qp->r_lock, flags);
460	opcode_handler = tid_qp_ok(opcode, packet);
461	if (likely(opcode_handler))
462		opcode_handler(packet);
463	else
464		goto drop_unlock;
465	spin_unlock_irqrestore(&packet->qp->r_lock, flags);
466	rcu_read_unlock();
467
468	return;
469drop_unlock:
470	spin_unlock_irqrestore(&packet->qp->r_lock, flags);
471drop_rcu:
472	rcu_read_unlock();
473drop:
474	ibp->rvp.n_pkt_drops++;
475}
476
477static int hfi1_do_pkey_check(struct hfi1_packet *packet)
478{
479	struct hfi1_ctxtdata *rcd = packet->rcd;
480	struct hfi1_pportdata *ppd = rcd->ppd;
481	struct hfi1_16b_header *hdr = packet->hdr;
482	u16 pkey;
483
484	/* Pkey check needed only for bypass packets */
485	if (packet->etype != RHF_RCV_TYPE_BYPASS)
486		return 0;
487
488	/* Perform pkey check */
489	pkey = hfi1_16B_get_pkey(hdr);
490	return ingress_pkey_check(ppd, pkey, packet->sc,
491				  packet->qp->s_pkey_index,
492				  packet->slid, true);
493}
494
495static inline void hfi1_handle_packet(struct hfi1_packet *packet,
496				      bool is_mcast)
497{
498	u32 qp_num;
499	struct hfi1_ctxtdata *rcd = packet->rcd;
500	struct hfi1_pportdata *ppd = rcd->ppd;
501	struct hfi1_ibport *ibp = rcd_to_iport(rcd);
502	struct rvt_dev_info *rdi = &ppd->dd->verbs_dev.rdi;
503	opcode_handler packet_handler;
504	unsigned long flags;
505
506	inc_opstats(packet->tlen, &rcd->opstats->stats[packet->opcode]);
507
508	if (unlikely(is_mcast)) {
509		struct rvt_mcast *mcast;
510		struct rvt_mcast_qp *p;
511
512		if (!packet->grh)
513			goto drop;
514		mcast = rvt_mcast_find(&ibp->rvp,
515				       &packet->grh->dgid,
516				       opa_get_lid(packet->dlid, 9B));
517		if (!mcast)
518			goto drop;
519		rcu_read_lock();
520		list_for_each_entry_rcu(p, &mcast->qp_list, list) {
521			packet->qp = p->qp;
522			if (hfi1_do_pkey_check(packet))
523				goto unlock_drop;
524			spin_lock_irqsave(&packet->qp->r_lock, flags);
525			packet_handler = qp_ok(packet);
526			if (likely(packet_handler))
527				packet_handler(packet);
528			else
529				ibp->rvp.n_pkt_drops++;
530			spin_unlock_irqrestore(&packet->qp->r_lock, flags);
531		}
532		rcu_read_unlock();
533		/*
534		 * Notify rvt_multicast_detach() if it is waiting for us
535		 * to finish.
536		 */
537		if (atomic_dec_return(&mcast->refcount) <= 1)
538			wake_up(&mcast->wait);
539	} else {
540		/* Get the destination QP number. */
541		if (packet->etype == RHF_RCV_TYPE_BYPASS &&
542		    hfi1_16B_get_l4(packet->hdr) == OPA_16B_L4_FM)
543			qp_num = hfi1_16B_get_dest_qpn(packet->mgmt);
544		else
545			qp_num = ib_bth_get_qpn(packet->ohdr);
546
547		rcu_read_lock();
548		packet->qp = rvt_lookup_qpn(rdi, &ibp->rvp, qp_num);
549		if (!packet->qp)
550			goto unlock_drop;
551
552		if (hfi1_do_pkey_check(packet))
553			goto unlock_drop;
554
555		spin_lock_irqsave(&packet->qp->r_lock, flags);
556		packet_handler = qp_ok(packet);
557		if (likely(packet_handler))
558			packet_handler(packet);
559		else
560			ibp->rvp.n_pkt_drops++;
561		spin_unlock_irqrestore(&packet->qp->r_lock, flags);
562		rcu_read_unlock();
563	}
564	return;
565unlock_drop:
566	rcu_read_unlock();
567drop:
568	ibp->rvp.n_pkt_drops++;
569}
570
571/**
572 * hfi1_ib_rcv - process an incoming packet
573 * @packet: data packet information
574 *
575 * This is called to process an incoming packet at interrupt level.
576 */
577void hfi1_ib_rcv(struct hfi1_packet *packet)
578{
579	struct hfi1_ctxtdata *rcd = packet->rcd;
580
581	trace_input_ibhdr(rcd->dd, packet, !!(rhf_dc_info(packet->rhf)));
582	hfi1_handle_packet(packet, hfi1_check_mcast(packet->dlid));
583}
584
585void hfi1_16B_rcv(struct hfi1_packet *packet)
586{
587	struct hfi1_ctxtdata *rcd = packet->rcd;
588
589	trace_input_ibhdr(rcd->dd, packet, false);
590	hfi1_handle_packet(packet, hfi1_check_mcast(packet->dlid));
591}
592
593/*
594 * This is called from a timer to check for QPs
595 * which need kernel memory in order to send a packet.
596 */
597static void mem_timer(struct timer_list *t)
598{
599	struct hfi1_ibdev *dev = from_timer(dev, t, mem_timer);
600	struct list_head *list = &dev->memwait;
601	struct rvt_qp *qp = NULL;
602	struct iowait *wait;
603	unsigned long flags;
604	struct hfi1_qp_priv *priv;
605
606	write_seqlock_irqsave(&dev->iowait_lock, flags);
607	if (!list_empty(list)) {
608		wait = list_first_entry(list, struct iowait, list);
609		qp = iowait_to_qp(wait);
610		priv = qp->priv;
611		list_del_init(&priv->s_iowait.list);
612		priv->s_iowait.lock = NULL;
613		/* refcount held until actual wake up */
614		if (!list_empty(list))
615			mod_timer(&dev->mem_timer, jiffies + 1);
616	}
617	write_sequnlock_irqrestore(&dev->iowait_lock, flags);
618
619	if (qp)
620		hfi1_qp_wakeup(qp, RVT_S_WAIT_KMEM);
621}
622
623/*
624 * This is called with progress side lock held.
625 */
626/* New API */
627static void verbs_sdma_complete(
628	struct sdma_txreq *cookie,
629	int status)
630{
631	struct verbs_txreq *tx =
632		container_of(cookie, struct verbs_txreq, txreq);
633	struct rvt_qp *qp = tx->qp;
634
635	spin_lock(&qp->s_lock);
636	if (tx->wqe) {
637		rvt_send_complete(qp, tx->wqe, IB_WC_SUCCESS);
638	} else if (qp->ibqp.qp_type == IB_QPT_RC) {
639		struct hfi1_opa_header *hdr;
640
641		hdr = &tx->phdr.hdr;
642		if (unlikely(status == SDMA_TXREQ_S_ABORTED))
643			hfi1_rc_verbs_aborted(qp, hdr);
644		hfi1_rc_send_complete(qp, hdr);
645	}
646	spin_unlock(&qp->s_lock);
647
648	hfi1_put_txreq(tx);
649}
650
651void hfi1_wait_kmem(struct rvt_qp *qp)
652{
653	struct hfi1_qp_priv *priv = qp->priv;
654	struct ib_qp *ibqp = &qp->ibqp;
655	struct ib_device *ibdev = ibqp->device;
656	struct hfi1_ibdev *dev = to_idev(ibdev);
657
658	if (list_empty(&priv->s_iowait.list)) {
659		if (list_empty(&dev->memwait))
660			mod_timer(&dev->mem_timer, jiffies + 1);
661		qp->s_flags |= RVT_S_WAIT_KMEM;
662		list_add_tail(&priv->s_iowait.list, &dev->memwait);
663		priv->s_iowait.lock = &dev->iowait_lock;
664		trace_hfi1_qpsleep(qp, RVT_S_WAIT_KMEM);
665		rvt_get_qp(qp);
666	}
667}
668
669static int wait_kmem(struct hfi1_ibdev *dev,
670		     struct rvt_qp *qp,
671		     struct hfi1_pkt_state *ps)
672{
673	unsigned long flags;
674	int ret = 0;
675
676	spin_lock_irqsave(&qp->s_lock, flags);
677	if (ib_rvt_state_ops[qp->state] & RVT_PROCESS_RECV_OK) {
678		write_seqlock(&dev->iowait_lock);
679		list_add_tail(&ps->s_txreq->txreq.list,
680			      &ps->wait->tx_head);
681		hfi1_wait_kmem(qp);
682		write_sequnlock(&dev->iowait_lock);
683		hfi1_qp_unbusy(qp, ps->wait);
684		ret = -EBUSY;
685	}
686	spin_unlock_irqrestore(&qp->s_lock, flags);
687
688	return ret;
689}
690
691/*
692 * This routine calls txadds for each sg entry.
693 *
694 * Add failures will revert the sge cursor
695 */
696static noinline int build_verbs_ulp_payload(
697	struct sdma_engine *sde,
698	u32 length,
699	struct verbs_txreq *tx)
700{
701	struct rvt_sge_state *ss = tx->ss;
702	struct rvt_sge *sg_list = ss->sg_list;
703	struct rvt_sge sge = ss->sge;
704	u8 num_sge = ss->num_sge;
705	u32 len;
706	int ret = 0;
707
708	while (length) {
709		len = rvt_get_sge_length(&ss->sge, length);
710		WARN_ON_ONCE(len == 0);
711		ret = sdma_txadd_kvaddr(
712			sde->dd,
713			&tx->txreq,
714			ss->sge.vaddr,
715			len);
716		if (ret)
717			goto bail_txadd;
718		rvt_update_sge(ss, len, false);
719		length -= len;
720	}
721	return ret;
722bail_txadd:
723	/* unwind cursor */
724	ss->sge = sge;
725	ss->num_sge = num_sge;
726	ss->sg_list = sg_list;
727	return ret;
728}
729
730/**
731 * update_tx_opstats - record stats by opcode
732 * @qp; the qp
733 * @ps: transmit packet state
734 * @plen: the plen in dwords
735 *
736 * This is a routine to record the tx opstats after a
737 * packet has been presented to the egress mechanism.
738 */
739static void update_tx_opstats(struct rvt_qp *qp, struct hfi1_pkt_state *ps,
740			      u32 plen)
741{
742#ifdef CONFIG_DEBUG_FS
743	struct hfi1_devdata *dd = dd_from_ibdev(qp->ibqp.device);
744	struct hfi1_opcode_stats_perctx *s = get_cpu_ptr(dd->tx_opstats);
745
746	inc_opstats(plen * 4, &s->stats[ps->opcode]);
747	put_cpu_ptr(s);
748#endif
749}
750
751/*
752 * Build the number of DMA descriptors needed to send length bytes of data.
753 *
754 * NOTE: DMA mapping is held in the tx until completed in the ring or
755 *       the tx desc is freed without having been submitted to the ring
756 *
757 * This routine ensures all the helper routine calls succeed.
758 */
759/* New API */
760static int build_verbs_tx_desc(
761	struct sdma_engine *sde,
762	u32 length,
763	struct verbs_txreq *tx,
764	struct hfi1_ahg_info *ahg_info,
765	u64 pbc)
766{
767	int ret = 0;
768	struct hfi1_sdma_header *phdr = &tx->phdr;
769	u16 hdrbytes = (tx->hdr_dwords + sizeof(pbc) / 4) << 2;
770	u8 extra_bytes = 0;
771
772	if (tx->phdr.hdr.hdr_type) {
773		/*
774		 * hdrbytes accounts for PBC. Need to subtract 8 bytes
775		 * before calculating padding.
776		 */
777		extra_bytes = hfi1_get_16b_padding(hdrbytes - 8, length) +
778			      (SIZE_OF_CRC << 2) + SIZE_OF_LT;
779	}
780	if (!ahg_info->ahgcount) {
781		ret = sdma_txinit_ahg(
782			&tx->txreq,
783			ahg_info->tx_flags,
784			hdrbytes + length +
785			extra_bytes,
786			ahg_info->ahgidx,
787			0,
788			NULL,
789			0,
790			verbs_sdma_complete);
791		if (ret)
792			goto bail_txadd;
793		phdr->pbc = cpu_to_le64(pbc);
794		ret = sdma_txadd_kvaddr(
795			sde->dd,
796			&tx->txreq,
797			phdr,
798			hdrbytes);
799		if (ret)
800			goto bail_txadd;
801	} else {
802		ret = sdma_txinit_ahg(
803			&tx->txreq,
804			ahg_info->tx_flags,
805			length,
806			ahg_info->ahgidx,
807			ahg_info->ahgcount,
808			ahg_info->ahgdesc,
809			hdrbytes,
810			verbs_sdma_complete);
811		if (ret)
812			goto bail_txadd;
813	}
814	/* add the ulp payload - if any. tx->ss can be NULL for acks */
815	if (tx->ss) {
816		ret = build_verbs_ulp_payload(sde, length, tx);
817		if (ret)
818			goto bail_txadd;
819	}
820
821	/* add icrc, lt byte, and padding to flit */
822	if (extra_bytes)
823		ret = sdma_txadd_daddr(sde->dd, &tx->txreq, sde->dd->sdma_pad_phys,
824				       extra_bytes);
825
826bail_txadd:
827	return ret;
828}
829
830static u64 update_hcrc(u8 opcode, u64 pbc)
831{
832	if ((opcode & IB_OPCODE_TID_RDMA) == IB_OPCODE_TID_RDMA) {
833		pbc &= ~PBC_INSERT_HCRC_SMASK;
834		pbc |= (u64)PBC_IHCRC_LKDETH << PBC_INSERT_HCRC_SHIFT;
835	}
836	return pbc;
837}
838
839int hfi1_verbs_send_dma(struct rvt_qp *qp, struct hfi1_pkt_state *ps,
840			u64 pbc)
841{
842	struct hfi1_qp_priv *priv = qp->priv;
843	struct hfi1_ahg_info *ahg_info = priv->s_ahg;
844	u32 hdrwords = ps->s_txreq->hdr_dwords;
845	u32 len = ps->s_txreq->s_cur_size;
846	u32 plen;
847	struct hfi1_ibdev *dev = ps->dev;
848	struct hfi1_pportdata *ppd = ps->ppd;
849	struct verbs_txreq *tx;
850	u8 sc5 = priv->s_sc;
851	int ret;
852	u32 dwords;
853
854	if (ps->s_txreq->phdr.hdr.hdr_type) {
855		u8 extra_bytes = hfi1_get_16b_padding((hdrwords << 2), len);
856
857		dwords = (len + extra_bytes + (SIZE_OF_CRC << 2) +
858			  SIZE_OF_LT) >> 2;
859	} else {
860		dwords = (len + 3) >> 2;
861	}
862	plen = hdrwords + dwords + sizeof(pbc) / 4;
863
864	tx = ps->s_txreq;
865	if (!sdma_txreq_built(&tx->txreq)) {
866		if (likely(pbc == 0)) {
867			u32 vl = sc_to_vlt(dd_from_ibdev(qp->ibqp.device), sc5);
868
869			/* No vl15 here */
870			/* set PBC_DC_INFO bit (aka SC[4]) in pbc */
871			if (ps->s_txreq->phdr.hdr.hdr_type)
872				pbc |= PBC_PACKET_BYPASS |
873				       PBC_INSERT_BYPASS_ICRC;
874			else
875				pbc |= (ib_is_sc5(sc5) << PBC_DC_INFO_SHIFT);
876
877			pbc = create_pbc(ppd,
878					 pbc,
879					 qp->srate_mbps,
880					 vl,
881					 plen);
882
883			if (unlikely(hfi1_dbg_should_fault_tx(qp, ps->opcode)))
884				pbc = hfi1_fault_tx(qp, ps->opcode, pbc);
885			else
886				/* Update HCRC based on packet opcode */
887				pbc = update_hcrc(ps->opcode, pbc);
888		}
889		tx->wqe = qp->s_wqe;
890		ret = build_verbs_tx_desc(tx->sde, len, tx, ahg_info, pbc);
891		if (unlikely(ret))
892			goto bail_build;
893	}
894	ret =  sdma_send_txreq(tx->sde, ps->wait, &tx->txreq, ps->pkts_sent);
895	if (unlikely(ret < 0)) {
896		if (ret == -ECOMM)
897			goto bail_ecomm;
898		return ret;
899	}
900
901	update_tx_opstats(qp, ps, plen);
902	trace_sdma_output_ibhdr(dd_from_ibdev(qp->ibqp.device),
903				&ps->s_txreq->phdr.hdr, ib_is_sc5(sc5));
904	return ret;
905
906bail_ecomm:
907	/* The current one got "sent" */
908	return 0;
909bail_build:
910	ret = wait_kmem(dev, qp, ps);
911	if (!ret) {
912		/* free txreq - bad state */
913		hfi1_put_txreq(ps->s_txreq);
914		ps->s_txreq = NULL;
915	}
916	return ret;
917}
918
919/*
920 * If we are now in the error state, return zero to flush the
921 * send work request.
922 */
923static int pio_wait(struct rvt_qp *qp,
924		    struct send_context *sc,
925		    struct hfi1_pkt_state *ps,
926		    u32 flag)
927{
928	struct hfi1_qp_priv *priv = qp->priv;
929	struct hfi1_devdata *dd = sc->dd;
930	unsigned long flags;
931	int ret = 0;
932
933	/*
934	 * Note that as soon as want_buffer() is called and
935	 * possibly before it returns, sc_piobufavail()
936	 * could be called. Therefore, put QP on the I/O wait list before
937	 * enabling the PIO avail interrupt.
938	 */
939	spin_lock_irqsave(&qp->s_lock, flags);
940	if (ib_rvt_state_ops[qp->state] & RVT_PROCESS_RECV_OK) {
941		write_seqlock(&sc->waitlock);
942		list_add_tail(&ps->s_txreq->txreq.list,
943			      &ps->wait->tx_head);
944		if (list_empty(&priv->s_iowait.list)) {
945			struct hfi1_ibdev *dev = &dd->verbs_dev;
946			int was_empty;
947
948			dev->n_piowait += !!(flag & RVT_S_WAIT_PIO);
949			dev->n_piodrain += !!(flag & HFI1_S_WAIT_PIO_DRAIN);
950			qp->s_flags |= flag;
951			was_empty = list_empty(&sc->piowait);
952			iowait_get_priority(&priv->s_iowait);
953			iowait_queue(ps->pkts_sent, &priv->s_iowait,
954				     &sc->piowait);
955			priv->s_iowait.lock = &sc->waitlock;
956			trace_hfi1_qpsleep(qp, RVT_S_WAIT_PIO);
957			rvt_get_qp(qp);
958			/* counting: only call wantpiobuf_intr if first user */
959			if (was_empty)
960				hfi1_sc_wantpiobuf_intr(sc, 1);
961		}
962		write_sequnlock(&sc->waitlock);
963		hfi1_qp_unbusy(qp, ps->wait);
964		ret = -EBUSY;
965	}
966	spin_unlock_irqrestore(&qp->s_lock, flags);
967	return ret;
968}
969
970static void verbs_pio_complete(void *arg, int code)
971{
972	struct rvt_qp *qp = (struct rvt_qp *)arg;
973	struct hfi1_qp_priv *priv = qp->priv;
974
975	if (iowait_pio_dec(&priv->s_iowait))
976		iowait_drain_wakeup(&priv->s_iowait);
977}
978
979int hfi1_verbs_send_pio(struct rvt_qp *qp, struct hfi1_pkt_state *ps,
980			u64 pbc)
981{
982	struct hfi1_qp_priv *priv = qp->priv;
983	u32 hdrwords = ps->s_txreq->hdr_dwords;
984	struct rvt_sge_state *ss = ps->s_txreq->ss;
985	u32 len = ps->s_txreq->s_cur_size;
986	u32 dwords;
987	u32 plen;
988	struct hfi1_pportdata *ppd = ps->ppd;
989	u32 *hdr;
990	u8 sc5;
991	unsigned long flags = 0;
992	struct send_context *sc;
993	struct pio_buf *pbuf;
994	int wc_status = IB_WC_SUCCESS;
995	int ret = 0;
996	pio_release_cb cb = NULL;
997	u8 extra_bytes = 0;
998
999	if (ps->s_txreq->phdr.hdr.hdr_type) {
1000		u8 pad_size = hfi1_get_16b_padding((hdrwords << 2), len);
1001
1002		extra_bytes = pad_size + (SIZE_OF_CRC << 2) + SIZE_OF_LT;
1003		dwords = (len + extra_bytes) >> 2;
1004		hdr = (u32 *)&ps->s_txreq->phdr.hdr.opah;
1005	} else {
1006		dwords = (len + 3) >> 2;
1007		hdr = (u32 *)&ps->s_txreq->phdr.hdr.ibh;
1008	}
1009	plen = hdrwords + dwords + sizeof(pbc) / 4;
1010
1011	/* only RC/UC use complete */
1012	switch (qp->ibqp.qp_type) {
1013	case IB_QPT_RC:
1014	case IB_QPT_UC:
1015		cb = verbs_pio_complete;
1016		break;
1017	default:
1018		break;
1019	}
1020
1021	/* vl15 special case taken care of in ud.c */
1022	sc5 = priv->s_sc;
1023	sc = ps->s_txreq->psc;
1024
1025	if (likely(pbc == 0)) {
1026		u8 vl = sc_to_vlt(dd_from_ibdev(qp->ibqp.device), sc5);
1027
1028		/* set PBC_DC_INFO bit (aka SC[4]) in pbc */
1029		if (ps->s_txreq->phdr.hdr.hdr_type)
1030			pbc |= PBC_PACKET_BYPASS | PBC_INSERT_BYPASS_ICRC;
1031		else
1032			pbc |= (ib_is_sc5(sc5) << PBC_DC_INFO_SHIFT);
1033
1034		pbc = create_pbc(ppd, pbc, qp->srate_mbps, vl, plen);
1035		if (unlikely(hfi1_dbg_should_fault_tx(qp, ps->opcode)))
1036			pbc = hfi1_fault_tx(qp, ps->opcode, pbc);
1037		else
1038			/* Update HCRC based on packet opcode */
1039			pbc = update_hcrc(ps->opcode, pbc);
1040	}
1041	if (cb)
1042		iowait_pio_inc(&priv->s_iowait);
1043	pbuf = sc_buffer_alloc(sc, plen, cb, qp);
1044	if (IS_ERR_OR_NULL(pbuf)) {
1045		if (cb)
1046			verbs_pio_complete(qp, 0);
1047		if (IS_ERR(pbuf)) {
1048			/*
1049			 * If we have filled the PIO buffers to capacity and are
1050			 * not in an active state this request is not going to
1051			 * go out to so just complete it with an error or else a
1052			 * ULP or the core may be stuck waiting.
1053			 */
1054			hfi1_cdbg(
1055				PIO,
1056				"alloc failed. state not active, completing");
1057			wc_status = IB_WC_GENERAL_ERR;
1058			goto pio_bail;
1059		} else {
1060			/*
1061			 * This is a normal occurrence. The PIO buffs are full
1062			 * up but we are still happily sending, well we could be
1063			 * so lets continue to queue the request.
1064			 */
1065			hfi1_cdbg(PIO, "alloc failed. state active, queuing");
1066			ret = pio_wait(qp, sc, ps, RVT_S_WAIT_PIO);
1067			if (!ret)
1068				/* txreq not queued - free */
1069				goto bail;
1070			/* tx consumed in wait */
1071			return ret;
1072		}
1073	}
1074
1075	if (dwords == 0) {
1076		pio_copy(ppd->dd, pbuf, pbc, hdr, hdrwords);
1077	} else {
1078		seg_pio_copy_start(pbuf, pbc,
1079				   hdr, hdrwords * 4);
1080		if (ss) {
1081			while (len) {
1082				void *addr = ss->sge.vaddr;
1083				u32 slen = rvt_get_sge_length(&ss->sge, len);
1084
1085				rvt_update_sge(ss, slen, false);
1086				seg_pio_copy_mid(pbuf, addr, slen);
1087				len -= slen;
1088			}
1089		}
1090		/* add icrc, lt byte, and padding to flit */
1091		if (extra_bytes)
1092			seg_pio_copy_mid(pbuf, ppd->dd->sdma_pad_dma,
1093					 extra_bytes);
1094
1095		seg_pio_copy_end(pbuf);
1096	}
1097
1098	update_tx_opstats(qp, ps, plen);
1099	trace_pio_output_ibhdr(dd_from_ibdev(qp->ibqp.device),
1100			       &ps->s_txreq->phdr.hdr, ib_is_sc5(sc5));
1101
1102pio_bail:
1103	spin_lock_irqsave(&qp->s_lock, flags);
1104	if (qp->s_wqe) {
1105		rvt_send_complete(qp, qp->s_wqe, wc_status);
1106	} else if (qp->ibqp.qp_type == IB_QPT_RC) {
1107		if (unlikely(wc_status == IB_WC_GENERAL_ERR))
1108			hfi1_rc_verbs_aborted(qp, &ps->s_txreq->phdr.hdr);
1109		hfi1_rc_send_complete(qp, &ps->s_txreq->phdr.hdr);
1110	}
1111	spin_unlock_irqrestore(&qp->s_lock, flags);
1112
1113	ret = 0;
1114
1115bail:
1116	hfi1_put_txreq(ps->s_txreq);
1117	return ret;
1118}
1119
1120/*
1121 * egress_pkey_matches_entry - return 1 if the pkey matches ent (ent
1122 * being an entry from the partition key table), return 0
1123 * otherwise. Use the matching criteria for egress partition keys
1124 * specified in the OPAv1 spec., section 9.1l.7.
1125 */
1126static inline int egress_pkey_matches_entry(u16 pkey, u16 ent)
1127{
1128	u16 mkey = pkey & PKEY_LOW_15_MASK;
1129	u16 mentry = ent & PKEY_LOW_15_MASK;
1130
1131	if (mkey == mentry) {
1132		/*
1133		 * If pkey[15] is set (full partition member),
1134		 * is bit 15 in the corresponding table element
1135		 * clear (limited member)?
1136		 */
1137		if (pkey & PKEY_MEMBER_MASK)
1138			return !!(ent & PKEY_MEMBER_MASK);
1139		return 1;
1140	}
1141	return 0;
1142}
1143
1144/**
1145 * egress_pkey_check - check P_KEY of a packet
1146 * @ppd:  Physical IB port data
1147 * @slid: SLID for packet
1148 * @bkey: PKEY for header
1149 * @sc5:  SC for packet
1150 * @s_pkey_index: It will be used for look up optimization for kernel contexts
1151 * only. If it is negative value, then it means user contexts is calling this
1152 * function.
1153 *
1154 * It checks if hdr's pkey is valid.
1155 *
1156 * Return: 0 on success, otherwise, 1
1157 */
1158int egress_pkey_check(struct hfi1_pportdata *ppd, u32 slid, u16 pkey,
1159		      u8 sc5, int8_t s_pkey_index)
1160{
1161	struct hfi1_devdata *dd;
1162	int i;
1163	int is_user_ctxt_mechanism = (s_pkey_index < 0);
1164
1165	if (!(ppd->part_enforce & HFI1_PART_ENFORCE_OUT))
1166		return 0;
1167
1168	/* If SC15, pkey[0:14] must be 0x7fff */
1169	if ((sc5 == 0xf) && ((pkey & PKEY_LOW_15_MASK) != PKEY_LOW_15_MASK))
1170		goto bad;
1171
1172	/* Is the pkey = 0x0, or 0x8000? */
1173	if ((pkey & PKEY_LOW_15_MASK) == 0)
1174		goto bad;
1175
1176	/*
1177	 * For the kernel contexts only, if a qp is passed into the function,
1178	 * the most likely matching pkey has index qp->s_pkey_index
1179	 */
1180	if (!is_user_ctxt_mechanism &&
1181	    egress_pkey_matches_entry(pkey, ppd->pkeys[s_pkey_index])) {
1182		return 0;
1183	}
1184
1185	for (i = 0; i < MAX_PKEY_VALUES; i++) {
1186		if (egress_pkey_matches_entry(pkey, ppd->pkeys[i]))
1187			return 0;
1188	}
1189bad:
1190	/*
1191	 * For the user-context mechanism, the P_KEY check would only happen
1192	 * once per SDMA request, not once per packet.  Therefore, there's no
1193	 * need to increment the counter for the user-context mechanism.
1194	 */
1195	if (!is_user_ctxt_mechanism) {
1196		incr_cntr64(&ppd->port_xmit_constraint_errors);
1197		dd = ppd->dd;
1198		if (!(dd->err_info_xmit_constraint.status &
1199		      OPA_EI_STATUS_SMASK)) {
1200			dd->err_info_xmit_constraint.status |=
1201				OPA_EI_STATUS_SMASK;
1202			dd->err_info_xmit_constraint.slid = slid;
1203			dd->err_info_xmit_constraint.pkey = pkey;
1204		}
1205	}
1206	return 1;
1207}
1208
1209/**
1210 * get_send_routine - choose an egress routine
1211 *
1212 * Choose an egress routine based on QP type
1213 * and size
1214 */
1215static inline send_routine get_send_routine(struct rvt_qp *qp,
1216					    struct hfi1_pkt_state *ps)
1217{
1218	struct hfi1_devdata *dd = dd_from_ibdev(qp->ibqp.device);
1219	struct hfi1_qp_priv *priv = qp->priv;
1220	struct verbs_txreq *tx = ps->s_txreq;
1221
1222	if (unlikely(!(dd->flags & HFI1_HAS_SEND_DMA)))
1223		return dd->process_pio_send;
1224	switch (qp->ibqp.qp_type) {
1225	case IB_QPT_SMI:
1226		return dd->process_pio_send;
1227	case IB_QPT_GSI:
1228	case IB_QPT_UD:
1229		break;
1230	case IB_QPT_UC:
1231	case IB_QPT_RC:
1232		priv->s_running_pkt_size =
1233			(tx->s_cur_size + priv->s_running_pkt_size) / 2;
1234		if (piothreshold &&
1235		    priv->s_running_pkt_size <= min(piothreshold, qp->pmtu) &&
1236		    (BIT(ps->opcode & OPMASK) & pio_opmask[ps->opcode >> 5]) &&
1237		    iowait_sdma_pending(&priv->s_iowait) == 0 &&
1238		    !sdma_txreq_built(&tx->txreq))
1239			return dd->process_pio_send;
1240		break;
1241	default:
1242		break;
1243	}
1244	return dd->process_dma_send;
1245}
1246
1247/**
1248 * hfi1_verbs_send - send a packet
1249 * @qp: the QP to send on
1250 * @ps: the state of the packet to send
1251 *
1252 * Return zero if packet is sent or queued OK.
1253 * Return non-zero and clear qp->s_flags RVT_S_BUSY otherwise.
1254 */
1255int hfi1_verbs_send(struct rvt_qp *qp, struct hfi1_pkt_state *ps)
1256{
1257	struct hfi1_devdata *dd = dd_from_ibdev(qp->ibqp.device);
1258	struct hfi1_qp_priv *priv = qp->priv;
1259	struct ib_other_headers *ohdr = NULL;
1260	send_routine sr;
1261	int ret;
1262	u16 pkey;
1263	u32 slid;
1264	u8 l4 = 0;
1265
1266	/* locate the pkey within the headers */
1267	if (ps->s_txreq->phdr.hdr.hdr_type) {
1268		struct hfi1_16b_header *hdr = &ps->s_txreq->phdr.hdr.opah;
1269
1270		l4 = hfi1_16B_get_l4(hdr);
1271		if (l4 == OPA_16B_L4_IB_LOCAL)
1272			ohdr = &hdr->u.oth;
1273		else if (l4 == OPA_16B_L4_IB_GLOBAL)
1274			ohdr = &hdr->u.l.oth;
1275
1276		slid = hfi1_16B_get_slid(hdr);
1277		pkey = hfi1_16B_get_pkey(hdr);
1278	} else {
1279		struct ib_header *hdr = &ps->s_txreq->phdr.hdr.ibh;
1280		u8 lnh = ib_get_lnh(hdr);
1281
1282		if (lnh == HFI1_LRH_GRH)
1283			ohdr = &hdr->u.l.oth;
1284		else
1285			ohdr = &hdr->u.oth;
1286		slid = ib_get_slid(hdr);
1287		pkey = ib_bth_get_pkey(ohdr);
1288	}
1289
1290	if (likely(l4 != OPA_16B_L4_FM))
1291		ps->opcode = ib_bth_get_opcode(ohdr);
1292	else
1293		ps->opcode = IB_OPCODE_UD_SEND_ONLY;
1294
1295	sr = get_send_routine(qp, ps);
1296	ret = egress_pkey_check(dd->pport, slid, pkey,
1297				priv->s_sc, qp->s_pkey_index);
1298	if (unlikely(ret)) {
1299		/*
1300		 * The value we are returning here does not get propagated to
1301		 * the verbs caller. Thus we need to complete the request with
1302		 * error otherwise the caller could be sitting waiting on the
1303		 * completion event. Only do this for PIO. SDMA has its own
1304		 * mechanism for handling the errors. So for SDMA we can just
1305		 * return.
1306		 */
1307		if (sr == dd->process_pio_send) {
1308			unsigned long flags;
1309
1310			hfi1_cdbg(PIO, "%s() Failed. Completing with err",
1311				  __func__);
1312			spin_lock_irqsave(&qp->s_lock, flags);
1313			rvt_send_complete(qp, qp->s_wqe, IB_WC_GENERAL_ERR);
1314			spin_unlock_irqrestore(&qp->s_lock, flags);
1315		}
1316		return -EINVAL;
1317	}
1318	if (sr == dd->process_dma_send && iowait_pio_pending(&priv->s_iowait))
1319		return pio_wait(qp,
1320				ps->s_txreq->psc,
1321				ps,
1322				HFI1_S_WAIT_PIO_DRAIN);
1323	return sr(qp, ps, 0);
1324}
1325
1326/**
1327 * hfi1_fill_device_attr - Fill in rvt dev info device attributes.
1328 * @dd: the device data structure
1329 */
1330static void hfi1_fill_device_attr(struct hfi1_devdata *dd)
1331{
1332	struct rvt_dev_info *rdi = &dd->verbs_dev.rdi;
1333	u32 ver = dd->dc8051_ver;
1334
1335	memset(&rdi->dparms.props, 0, sizeof(rdi->dparms.props));
1336
1337	rdi->dparms.props.fw_ver = ((u64)(dc8051_ver_maj(ver)) << 32) |
1338		((u64)(dc8051_ver_min(ver)) << 16) |
1339		(u64)dc8051_ver_patch(ver);
1340
1341	rdi->dparms.props.device_cap_flags = IB_DEVICE_BAD_PKEY_CNTR |
1342			IB_DEVICE_BAD_QKEY_CNTR | IB_DEVICE_SHUTDOWN_PORT |
1343			IB_DEVICE_SYS_IMAGE_GUID | IB_DEVICE_RC_RNR_NAK_GEN |
1344			IB_DEVICE_PORT_ACTIVE_EVENT | IB_DEVICE_SRQ_RESIZE |
1345			IB_DEVICE_MEM_MGT_EXTENSIONS |
1346			IB_DEVICE_RDMA_NETDEV_OPA;
1347	rdi->dparms.props.page_size_cap = PAGE_SIZE;
1348	rdi->dparms.props.vendor_id = dd->oui1 << 16 | dd->oui2 << 8 | dd->oui3;
1349	rdi->dparms.props.vendor_part_id = dd->pcidev->device;
1350	rdi->dparms.props.hw_ver = dd->minrev;
1351	rdi->dparms.props.sys_image_guid = ib_hfi1_sys_image_guid;
1352	rdi->dparms.props.max_mr_size = U64_MAX;
1353	rdi->dparms.props.max_fast_reg_page_list_len = UINT_MAX;
1354	rdi->dparms.props.max_qp = hfi1_max_qps;
1355	rdi->dparms.props.max_qp_wr =
1356		(hfi1_max_qp_wrs >= HFI1_QP_WQE_INVALID ?
1357		 HFI1_QP_WQE_INVALID - 1 : hfi1_max_qp_wrs);
1358	rdi->dparms.props.max_send_sge = hfi1_max_sges;
1359	rdi->dparms.props.max_recv_sge = hfi1_max_sges;
1360	rdi->dparms.props.max_sge_rd = hfi1_max_sges;
1361	rdi->dparms.props.max_cq = hfi1_max_cqs;
1362	rdi->dparms.props.max_ah = hfi1_max_ahs;
1363	rdi->dparms.props.max_cqe = hfi1_max_cqes;
1364	rdi->dparms.props.max_pd = hfi1_max_pds;
1365	rdi->dparms.props.max_qp_rd_atom = HFI1_MAX_RDMA_ATOMIC;
1366	rdi->dparms.props.max_qp_init_rd_atom = 255;
1367	rdi->dparms.props.max_srq = hfi1_max_srqs;
1368	rdi->dparms.props.max_srq_wr = hfi1_max_srq_wrs;
1369	rdi->dparms.props.max_srq_sge = hfi1_max_srq_sges;
1370	rdi->dparms.props.atomic_cap = IB_ATOMIC_GLOB;
1371	rdi->dparms.props.max_pkeys = hfi1_get_npkeys(dd);
1372	rdi->dparms.props.max_mcast_grp = hfi1_max_mcast_grps;
1373	rdi->dparms.props.max_mcast_qp_attach = hfi1_max_mcast_qp_attached;
1374	rdi->dparms.props.max_total_mcast_qp_attach =
1375					rdi->dparms.props.max_mcast_qp_attach *
1376					rdi->dparms.props.max_mcast_grp;
1377}
1378
1379static inline u16 opa_speed_to_ib(u16 in)
1380{
1381	u16 out = 0;
1382
1383	if (in & OPA_LINK_SPEED_25G)
1384		out |= IB_SPEED_EDR;
1385	if (in & OPA_LINK_SPEED_12_5G)
1386		out |= IB_SPEED_FDR;
1387
1388	return out;
1389}
1390
1391/*
1392 * Convert a single OPA link width (no multiple flags) to an IB value.
1393 * A zero OPA link width means link down, which means the IB width value
1394 * is a don't care.
1395 */
1396static inline u16 opa_width_to_ib(u16 in)
1397{
1398	switch (in) {
1399	case OPA_LINK_WIDTH_1X:
1400	/* map 2x and 3x to 1x as they don't exist in IB */
1401	case OPA_LINK_WIDTH_2X:
1402	case OPA_LINK_WIDTH_3X:
1403		return IB_WIDTH_1X;
1404	default: /* link down or unknown, return our largest width */
1405	case OPA_LINK_WIDTH_4X:
1406		return IB_WIDTH_4X;
1407	}
1408}
1409
1410static int query_port(struct rvt_dev_info *rdi, u8 port_num,
1411		      struct ib_port_attr *props)
1412{
1413	struct hfi1_ibdev *verbs_dev = dev_from_rdi(rdi);
1414	struct hfi1_devdata *dd = dd_from_dev(verbs_dev);
1415	struct hfi1_pportdata *ppd = &dd->pport[port_num - 1];
1416	u32 lid = ppd->lid;
1417
1418	/* props being zeroed by the caller, avoid zeroing it here */
1419	props->lid = lid ? lid : 0;
1420	props->lmc = ppd->lmc;
1421	/* OPA logical states match IB logical states */
1422	props->state = driver_lstate(ppd);
1423	props->phys_state = driver_pstate(ppd);
1424	props->gid_tbl_len = HFI1_GUIDS_PER_PORT;
1425	props->active_width = (u8)opa_width_to_ib(ppd->link_width_active);
1426	/* see rate_show() in ib core/sysfs.c */
1427	props->active_speed = opa_speed_to_ib(ppd->link_speed_active);
1428	props->max_vl_num = ppd->vls_supported;
1429
1430	/* Once we are a "first class" citizen and have added the OPA MTUs to
1431	 * the core we can advertise the larger MTU enum to the ULPs, for now
1432	 * advertise only 4K.
1433	 *
1434	 * Those applications which are either OPA aware or pass the MTU enum
1435	 * from the Path Records to us will get the new 8k MTU.  Those that
1436	 * attempt to process the MTU enum may fail in various ways.
1437	 */
1438	props->max_mtu = mtu_to_enum((!valid_ib_mtu(hfi1_max_mtu) ?
1439				      4096 : hfi1_max_mtu), IB_MTU_4096);
1440	props->active_mtu = !valid_ib_mtu(ppd->ibmtu) ? props->max_mtu :
1441		mtu_to_enum(ppd->ibmtu, IB_MTU_4096);
1442	props->phys_mtu = hfi1_max_mtu;
1443
1444	return 0;
1445}
1446
1447static int modify_device(struct ib_device *device,
1448			 int device_modify_mask,
1449			 struct ib_device_modify *device_modify)
1450{
1451	struct hfi1_devdata *dd = dd_from_ibdev(device);
1452	unsigned i;
1453	int ret;
1454
1455	if (device_modify_mask & ~(IB_DEVICE_MODIFY_SYS_IMAGE_GUID |
1456				   IB_DEVICE_MODIFY_NODE_DESC)) {
1457		ret = -EOPNOTSUPP;
1458		goto bail;
1459	}
1460
1461	if (device_modify_mask & IB_DEVICE_MODIFY_NODE_DESC) {
1462		memcpy(device->node_desc, device_modify->node_desc,
1463		       IB_DEVICE_NODE_DESC_MAX);
1464		for (i = 0; i < dd->num_pports; i++) {
1465			struct hfi1_ibport *ibp = &dd->pport[i].ibport_data;
1466
1467			hfi1_node_desc_chg(ibp);
1468		}
1469	}
1470
1471	if (device_modify_mask & IB_DEVICE_MODIFY_SYS_IMAGE_GUID) {
1472		ib_hfi1_sys_image_guid =
1473			cpu_to_be64(device_modify->sys_image_guid);
1474		for (i = 0; i < dd->num_pports; i++) {
1475			struct hfi1_ibport *ibp = &dd->pport[i].ibport_data;
1476
1477			hfi1_sys_guid_chg(ibp);
1478		}
1479	}
1480
1481	ret = 0;
1482
1483bail:
1484	return ret;
1485}
1486
1487static int shut_down_port(struct rvt_dev_info *rdi, u8 port_num)
1488{
1489	struct hfi1_ibdev *verbs_dev = dev_from_rdi(rdi);
1490	struct hfi1_devdata *dd = dd_from_dev(verbs_dev);
1491	struct hfi1_pportdata *ppd = &dd->pport[port_num - 1];
1492	int ret;
1493
1494	set_link_down_reason(ppd, OPA_LINKDOWN_REASON_UNKNOWN, 0,
1495			     OPA_LINKDOWN_REASON_UNKNOWN);
1496	ret = set_link_state(ppd, HLS_DN_DOWNDEF);
1497	return ret;
1498}
1499
1500static int hfi1_get_guid_be(struct rvt_dev_info *rdi, struct rvt_ibport *rvp,
1501			    int guid_index, __be64 *guid)
1502{
1503	struct hfi1_ibport *ibp = container_of(rvp, struct hfi1_ibport, rvp);
1504
1505	if (guid_index >= HFI1_GUIDS_PER_PORT)
1506		return -EINVAL;
1507
1508	*guid = get_sguid(ibp, guid_index);
1509	return 0;
1510}
1511
1512/*
1513 * convert ah port,sl to sc
1514 */
1515u8 ah_to_sc(struct ib_device *ibdev, struct rdma_ah_attr *ah)
1516{
1517	struct hfi1_ibport *ibp = to_iport(ibdev, rdma_ah_get_port_num(ah));
1518
1519	return ibp->sl_to_sc[rdma_ah_get_sl(ah)];
1520}
1521
1522static int hfi1_check_ah(struct ib_device *ibdev, struct rdma_ah_attr *ah_attr)
1523{
1524	struct hfi1_ibport *ibp;
1525	struct hfi1_pportdata *ppd;
1526	struct hfi1_devdata *dd;
1527	u8 sc5;
1528	u8 sl;
1529
1530	if (hfi1_check_mcast(rdma_ah_get_dlid(ah_attr)) &&
1531	    !(rdma_ah_get_ah_flags(ah_attr) & IB_AH_GRH))
1532		return -EINVAL;
1533
1534	/* test the mapping for validity */
1535	ibp = to_iport(ibdev, rdma_ah_get_port_num(ah_attr));
1536	ppd = ppd_from_ibp(ibp);
1537	dd = dd_from_ppd(ppd);
1538
1539	sl = rdma_ah_get_sl(ah_attr);
1540	if (sl >= ARRAY_SIZE(ibp->sl_to_sc))
1541		return -EINVAL;
1542	sl = array_index_nospec(sl, ARRAY_SIZE(ibp->sl_to_sc));
1543
1544	sc5 = ibp->sl_to_sc[sl];
1545	if (sc_to_vlt(dd, sc5) > num_vls && sc_to_vlt(dd, sc5) != 0xf)
1546		return -EINVAL;
1547	return 0;
1548}
1549
1550static void hfi1_notify_new_ah(struct ib_device *ibdev,
1551			       struct rdma_ah_attr *ah_attr,
1552			       struct rvt_ah *ah)
1553{
1554	struct hfi1_ibport *ibp;
1555	struct hfi1_pportdata *ppd;
1556	struct hfi1_devdata *dd;
1557	u8 sc5;
1558	struct rdma_ah_attr *attr = &ah->attr;
1559
1560	/*
1561	 * Do not trust reading anything from rvt_ah at this point as it is not
1562	 * done being setup. We can however modify things which we need to set.
1563	 */
1564
1565	ibp = to_iport(ibdev, rdma_ah_get_port_num(ah_attr));
1566	ppd = ppd_from_ibp(ibp);
1567	sc5 = ibp->sl_to_sc[rdma_ah_get_sl(&ah->attr)];
1568	hfi1_update_ah_attr(ibdev, attr);
1569	hfi1_make_opa_lid(attr);
1570	dd = dd_from_ppd(ppd);
1571	ah->vl = sc_to_vlt(dd, sc5);
1572	if (ah->vl < num_vls || ah->vl == 15)
1573		ah->log_pmtu = ilog2(dd->vld[ah->vl].mtu);
1574}
1575
1576/**
1577 * hfi1_get_npkeys - return the size of the PKEY table for context 0
1578 * @dd: the hfi1_ib device
1579 */
1580unsigned hfi1_get_npkeys(struct hfi1_devdata *dd)
1581{
1582	return ARRAY_SIZE(dd->pport[0].pkeys);
1583}
1584
1585static void init_ibport(struct hfi1_pportdata *ppd)
1586{
1587	struct hfi1_ibport *ibp = &ppd->ibport_data;
1588	size_t sz = ARRAY_SIZE(ibp->sl_to_sc);
1589	int i;
1590
1591	for (i = 0; i < sz; i++) {
1592		ibp->sl_to_sc[i] = i;
1593		ibp->sc_to_sl[i] = i;
1594	}
1595
1596	for (i = 0; i < RVT_MAX_TRAP_LISTS ; i++)
1597		INIT_LIST_HEAD(&ibp->rvp.trap_lists[i].list);
1598	timer_setup(&ibp->rvp.trap_timer, hfi1_handle_trap_timer, 0);
1599
1600	spin_lock_init(&ibp->rvp.lock);
1601	/* Set the prefix to the default value (see ch. 4.1.1) */
1602	ibp->rvp.gid_prefix = IB_DEFAULT_GID_PREFIX;
1603	ibp->rvp.sm_lid = 0;
1604	/*
1605	 * Below should only set bits defined in OPA PortInfo.CapabilityMask
1606	 * and PortInfo.CapabilityMask3
1607	 */
1608	ibp->rvp.port_cap_flags = IB_PORT_AUTO_MIGR_SUP |
1609		IB_PORT_CAP_MASK_NOTICE_SUP;
1610	ibp->rvp.port_cap3_flags = OPA_CAP_MASK3_IsSharedSpaceSupported;
1611	ibp->rvp.pma_counter_select[0] = IB_PMA_PORT_XMIT_DATA;
1612	ibp->rvp.pma_counter_select[1] = IB_PMA_PORT_RCV_DATA;
1613	ibp->rvp.pma_counter_select[2] = IB_PMA_PORT_XMIT_PKTS;
1614	ibp->rvp.pma_counter_select[3] = IB_PMA_PORT_RCV_PKTS;
1615	ibp->rvp.pma_counter_select[4] = IB_PMA_PORT_XMIT_WAIT;
1616
1617	RCU_INIT_POINTER(ibp->rvp.qp[0], NULL);
1618	RCU_INIT_POINTER(ibp->rvp.qp[1], NULL);
1619}
1620
1621static void hfi1_get_dev_fw_str(struct ib_device *ibdev, char *str)
1622{
1623	struct rvt_dev_info *rdi = ib_to_rvt(ibdev);
1624	struct hfi1_ibdev *dev = dev_from_rdi(rdi);
1625	u32 ver = dd_from_dev(dev)->dc8051_ver;
1626
1627	snprintf(str, IB_FW_VERSION_NAME_MAX, "%u.%u.%u", dc8051_ver_maj(ver),
1628		 dc8051_ver_min(ver), dc8051_ver_patch(ver));
1629}
1630
1631static const char * const driver_cntr_names[] = {
1632	/* must be element 0*/
1633	"DRIVER_KernIntr",
1634	"DRIVER_ErrorIntr",
1635	"DRIVER_Tx_Errs",
1636	"DRIVER_Rcv_Errs",
1637	"DRIVER_HW_Errs",
1638	"DRIVER_NoPIOBufs",
1639	"DRIVER_CtxtsOpen",
1640	"DRIVER_RcvLen_Errs",
1641	"DRIVER_EgrBufFull",
1642	"DRIVER_EgrHdrFull"
1643};
1644
1645static DEFINE_MUTEX(cntr_names_lock); /* protects the *_cntr_names bufers */
1646static const char **dev_cntr_names;
1647static const char **port_cntr_names;
1648int num_driver_cntrs = ARRAY_SIZE(driver_cntr_names);
1649static int num_dev_cntrs;
1650static int num_port_cntrs;
1651static int cntr_names_initialized;
1652
1653/*
1654 * Convert a list of names separated by '\n' into an array of NULL terminated
1655 * strings. Optionally some entries can be reserved in the array to hold extra
1656 * external strings.
1657 */
1658static int init_cntr_names(const char *names_in,
1659			   const size_t names_len,
1660			   int num_extra_names,
1661			   int *num_cntrs,
1662			   const char ***cntr_names)
1663{
1664	char *names_out, *p, **q;
1665	int i, n;
1666
1667	n = 0;
1668	for (i = 0; i < names_len; i++)
1669		if (names_in[i] == '\n')
1670			n++;
1671
1672	names_out = kmalloc((n + num_extra_names) * sizeof(char *) + names_len,
1673			    GFP_KERNEL);
1674	if (!names_out) {
1675		*num_cntrs = 0;
1676		*cntr_names = NULL;
1677		return -ENOMEM;
1678	}
1679
1680	p = names_out + (n + num_extra_names) * sizeof(char *);
1681	memcpy(p, names_in, names_len);
1682
1683	q = (char **)names_out;
1684	for (i = 0; i < n; i++) {
1685		q[i] = p;
1686		p = strchr(p, '\n');
1687		*p++ = '\0';
1688	}
1689
1690	*num_cntrs = n;
1691	*cntr_names = (const char **)names_out;
1692	return 0;
1693}
1694
1695static struct rdma_hw_stats *alloc_hw_stats(struct ib_device *ibdev,
1696					    u8 port_num)
1697{
1698	int i, err;
1699
1700	mutex_lock(&cntr_names_lock);
1701	if (!cntr_names_initialized) {
1702		struct hfi1_devdata *dd = dd_from_ibdev(ibdev);
1703
1704		err = init_cntr_names(dd->cntrnames,
1705				      dd->cntrnameslen,
1706				      num_driver_cntrs,
1707				      &num_dev_cntrs,
1708				      &dev_cntr_names);
1709		if (err) {
1710			mutex_unlock(&cntr_names_lock);
1711			return NULL;
1712		}
1713
1714		for (i = 0; i < num_driver_cntrs; i++)
1715			dev_cntr_names[num_dev_cntrs + i] =
1716				driver_cntr_names[i];
1717
1718		err = init_cntr_names(dd->portcntrnames,
1719				      dd->portcntrnameslen,
1720				      0,
1721				      &num_port_cntrs,
1722				      &port_cntr_names);
1723		if (err) {
1724			kfree(dev_cntr_names);
1725			dev_cntr_names = NULL;
1726			mutex_unlock(&cntr_names_lock);
1727			return NULL;
1728		}
1729		cntr_names_initialized = 1;
1730	}
1731	mutex_unlock(&cntr_names_lock);
1732
1733	if (!port_num)
1734		return rdma_alloc_hw_stats_struct(
1735				dev_cntr_names,
1736				num_dev_cntrs + num_driver_cntrs,
1737				RDMA_HW_STATS_DEFAULT_LIFESPAN);
1738	else
1739		return rdma_alloc_hw_stats_struct(
1740				port_cntr_names,
1741				num_port_cntrs,
1742				RDMA_HW_STATS_DEFAULT_LIFESPAN);
1743}
1744
1745static u64 hfi1_sps_ints(void)
1746{
1747	unsigned long index, flags;
1748	struct hfi1_devdata *dd;
1749	u64 sps_ints = 0;
1750
1751	xa_lock_irqsave(&hfi1_dev_table, flags);
1752	xa_for_each(&hfi1_dev_table, index, dd) {
1753		sps_ints += get_all_cpu_total(dd->int_counter);
1754	}
1755	xa_unlock_irqrestore(&hfi1_dev_table, flags);
1756	return sps_ints;
1757}
1758
1759static int get_hw_stats(struct ib_device *ibdev, struct rdma_hw_stats *stats,
1760			u8 port, int index)
1761{
1762	u64 *values;
1763	int count;
1764
1765	if (!port) {
1766		u64 *stats = (u64 *)&hfi1_stats;
1767		int i;
1768
1769		hfi1_read_cntrs(dd_from_ibdev(ibdev), NULL, &values);
1770		values[num_dev_cntrs] = hfi1_sps_ints();
1771		for (i = 1; i < num_driver_cntrs; i++)
1772			values[num_dev_cntrs + i] = stats[i];
1773		count = num_dev_cntrs + num_driver_cntrs;
1774	} else {
1775		struct hfi1_ibport *ibp = to_iport(ibdev, port);
1776
1777		hfi1_read_portcntrs(ppd_from_ibp(ibp), NULL, &values);
1778		count = num_port_cntrs;
1779	}
1780
1781	memcpy(stats->value, values, count * sizeof(u64));
1782	return count;
1783}
1784
1785static const struct ib_device_ops hfi1_dev_ops = {
1786	.owner = THIS_MODULE,
1787	.driver_id = RDMA_DRIVER_HFI1,
1788
1789	.alloc_hw_stats = alloc_hw_stats,
1790	.alloc_rdma_netdev = hfi1_vnic_alloc_rn,
1791	.get_dev_fw_str = hfi1_get_dev_fw_str,
1792	.get_hw_stats = get_hw_stats,
1793	.init_port = hfi1_create_port_files,
1794	.modify_device = modify_device,
1795	/* keep process mad in the driver */
1796	.process_mad = hfi1_process_mad,
1797	.rdma_netdev_get_params = hfi1_ipoib_rn_get_params,
1798};
1799
1800/**
1801 * hfi1_register_ib_device - register our device with the infiniband core
1802 * @dd: the device data structure
1803 * Return 0 if successful, errno if unsuccessful.
1804 */
1805int hfi1_register_ib_device(struct hfi1_devdata *dd)
1806{
1807	struct hfi1_ibdev *dev = &dd->verbs_dev;
1808	struct ib_device *ibdev = &dev->rdi.ibdev;
1809	struct hfi1_pportdata *ppd = dd->pport;
1810	struct hfi1_ibport *ibp = &ppd->ibport_data;
1811	unsigned i;
1812	int ret;
1813
1814	for (i = 0; i < dd->num_pports; i++)
1815		init_ibport(ppd + i);
1816
1817	/* Only need to initialize non-zero fields. */
1818
1819	timer_setup(&dev->mem_timer, mem_timer, 0);
1820
1821	seqlock_init(&dev->iowait_lock);
1822	seqlock_init(&dev->txwait_lock);
1823	INIT_LIST_HEAD(&dev->txwait);
1824	INIT_LIST_HEAD(&dev->memwait);
1825
1826	ret = verbs_txreq_init(dev);
1827	if (ret)
1828		goto err_verbs_txreq;
1829
1830	/* Use first-port GUID as node guid */
1831	ibdev->node_guid = get_sguid(ibp, HFI1_PORT_GUID_INDEX);
1832
1833	/*
1834	 * The system image GUID is supposed to be the same for all
1835	 * HFIs in a single system but since there can be other
1836	 * device types in the system, we can't be sure this is unique.
1837	 */
1838	if (!ib_hfi1_sys_image_guid)
1839		ib_hfi1_sys_image_guid = ibdev->node_guid;
1840	ibdev->phys_port_cnt = dd->num_pports;
1841	ibdev->dev.parent = &dd->pcidev->dev;
1842
1843	ib_set_device_ops(ibdev, &hfi1_dev_ops);
1844
1845	strlcpy(ibdev->node_desc, init_utsname()->nodename,
1846		sizeof(ibdev->node_desc));
1847
1848	/*
1849	 * Fill in rvt info object.
1850	 */
1851	dd->verbs_dev.rdi.driver_f.get_pci_dev = get_pci_dev;
1852	dd->verbs_dev.rdi.driver_f.check_ah = hfi1_check_ah;
1853	dd->verbs_dev.rdi.driver_f.notify_new_ah = hfi1_notify_new_ah;
1854	dd->verbs_dev.rdi.driver_f.get_guid_be = hfi1_get_guid_be;
1855	dd->verbs_dev.rdi.driver_f.query_port_state = query_port;
1856	dd->verbs_dev.rdi.driver_f.shut_down_port = shut_down_port;
1857	dd->verbs_dev.rdi.driver_f.cap_mask_chg = hfi1_cap_mask_chg;
1858	/*
1859	 * Fill in rvt info device attributes.
1860	 */
1861	hfi1_fill_device_attr(dd);
1862
1863	/* queue pair */
1864	dd->verbs_dev.rdi.dparms.qp_table_size = hfi1_qp_table_size;
1865	dd->verbs_dev.rdi.dparms.qpn_start = 0;
1866	dd->verbs_dev.rdi.dparms.qpn_inc = 1;
1867	dd->verbs_dev.rdi.dparms.qos_shift = dd->qos_shift;
1868	dd->verbs_dev.rdi.dparms.qpn_res_start = RVT_KDETH_QP_BASE;
1869	dd->verbs_dev.rdi.dparms.qpn_res_end = RVT_AIP_QP_MAX;
1870	dd->verbs_dev.rdi.dparms.max_rdma_atomic = HFI1_MAX_RDMA_ATOMIC;
1871	dd->verbs_dev.rdi.dparms.psn_mask = PSN_MASK;
1872	dd->verbs_dev.rdi.dparms.psn_shift = PSN_SHIFT;
1873	dd->verbs_dev.rdi.dparms.psn_modify_mask = PSN_MODIFY_MASK;
1874	dd->verbs_dev.rdi.dparms.core_cap_flags = RDMA_CORE_PORT_INTEL_OPA |
1875						RDMA_CORE_CAP_OPA_AH;
1876	dd->verbs_dev.rdi.dparms.max_mad_size = OPA_MGMT_MAD_SIZE;
1877
1878	dd->verbs_dev.rdi.driver_f.qp_priv_alloc = qp_priv_alloc;
1879	dd->verbs_dev.rdi.driver_f.qp_priv_init = hfi1_qp_priv_init;
1880	dd->verbs_dev.rdi.driver_f.qp_priv_free = qp_priv_free;
1881	dd->verbs_dev.rdi.driver_f.free_all_qps = free_all_qps;
1882	dd->verbs_dev.rdi.driver_f.notify_qp_reset = notify_qp_reset;
1883	dd->verbs_dev.rdi.driver_f.do_send = hfi1_do_send_from_rvt;
1884	dd->verbs_dev.rdi.driver_f.schedule_send = hfi1_schedule_send;
1885	dd->verbs_dev.rdi.driver_f.schedule_send_no_lock = _hfi1_schedule_send;
1886	dd->verbs_dev.rdi.driver_f.get_pmtu_from_attr = get_pmtu_from_attr;
1887	dd->verbs_dev.rdi.driver_f.notify_error_qp = notify_error_qp;
1888	dd->verbs_dev.rdi.driver_f.flush_qp_waiters = flush_qp_waiters;
1889	dd->verbs_dev.rdi.driver_f.stop_send_queue = stop_send_queue;
1890	dd->verbs_dev.rdi.driver_f.quiesce_qp = quiesce_qp;
1891	dd->verbs_dev.rdi.driver_f.notify_error_qp = notify_error_qp;
1892	dd->verbs_dev.rdi.driver_f.mtu_from_qp = mtu_from_qp;
1893	dd->verbs_dev.rdi.driver_f.mtu_to_path_mtu = mtu_to_path_mtu;
1894	dd->verbs_dev.rdi.driver_f.check_modify_qp = hfi1_check_modify_qp;
1895	dd->verbs_dev.rdi.driver_f.modify_qp = hfi1_modify_qp;
1896	dd->verbs_dev.rdi.driver_f.notify_restart_rc = hfi1_restart_rc;
1897	dd->verbs_dev.rdi.driver_f.setup_wqe = hfi1_setup_wqe;
1898	dd->verbs_dev.rdi.driver_f.comp_vect_cpu_lookup =
1899						hfi1_comp_vect_mappings_lookup;
1900
1901	/* completeion queue */
1902	dd->verbs_dev.rdi.ibdev.num_comp_vectors = dd->comp_vect_possible_cpus;
1903	dd->verbs_dev.rdi.dparms.node = dd->node;
1904
1905	/* misc settings */
1906	dd->verbs_dev.rdi.flags = 0; /* Let rdmavt handle it all */
1907	dd->verbs_dev.rdi.dparms.lkey_table_size = hfi1_lkey_table_size;
1908	dd->verbs_dev.rdi.dparms.nports = dd->num_pports;
1909	dd->verbs_dev.rdi.dparms.npkeys = hfi1_get_npkeys(dd);
1910	dd->verbs_dev.rdi.dparms.sge_copy_mode = sge_copy_mode;
1911	dd->verbs_dev.rdi.dparms.wss_threshold = wss_threshold;
1912	dd->verbs_dev.rdi.dparms.wss_clean_period = wss_clean_period;
1913	dd->verbs_dev.rdi.dparms.reserved_operations = 1;
1914	dd->verbs_dev.rdi.dparms.extra_rdma_atomic = HFI1_TID_RDMA_WRITE_CNT;
1915
1916	/* post send table */
1917	dd->verbs_dev.rdi.post_parms = hfi1_post_parms;
1918
1919	/* opcode translation table */
1920	dd->verbs_dev.rdi.wc_opcode = ib_hfi1_wc_opcode;
1921
1922	ppd = dd->pport;
1923	for (i = 0; i < dd->num_pports; i++, ppd++)
1924		rvt_init_port(&dd->verbs_dev.rdi,
1925			      &ppd->ibport_data.rvp,
1926			      i,
1927			      ppd->pkeys);
1928
1929	rdma_set_device_sysfs_group(&dd->verbs_dev.rdi.ibdev,
1930				    &ib_hfi1_attr_group);
1931
1932	ret = rvt_register_device(&dd->verbs_dev.rdi);
1933	if (ret)
1934		goto err_verbs_txreq;
1935
1936	ret = hfi1_verbs_register_sysfs(dd);
1937	if (ret)
1938		goto err_class;
1939
1940	return ret;
1941
1942err_class:
1943	rvt_unregister_device(&dd->verbs_dev.rdi);
1944err_verbs_txreq:
1945	verbs_txreq_exit(dev);
1946	dd_dev_err(dd, "cannot register verbs: %d!\n", -ret);
1947	return ret;
1948}
1949
1950void hfi1_unregister_ib_device(struct hfi1_devdata *dd)
1951{
1952	struct hfi1_ibdev *dev = &dd->verbs_dev;
1953
1954	hfi1_verbs_unregister_sysfs(dd);
1955
1956	rvt_unregister_device(&dd->verbs_dev.rdi);
1957
1958	if (!list_empty(&dev->txwait))
1959		dd_dev_err(dd, "txwait list not empty!\n");
1960	if (!list_empty(&dev->memwait))
1961		dd_dev_err(dd, "memwait list not empty!\n");
1962
1963	del_timer_sync(&dev->mem_timer);
1964	verbs_txreq_exit(dev);
1965
1966	mutex_lock(&cntr_names_lock);
1967	kfree(dev_cntr_names);
1968	kfree(port_cntr_names);
1969	dev_cntr_names = NULL;
1970	port_cntr_names = NULL;
1971	cntr_names_initialized = 0;
1972	mutex_unlock(&cntr_names_lock);
1973}
1974
1975void hfi1_cnp_rcv(struct hfi1_packet *packet)
1976{
1977	struct hfi1_ibport *ibp = rcd_to_iport(packet->rcd);
1978	struct hfi1_pportdata *ppd = ppd_from_ibp(ibp);
1979	struct ib_header *hdr = packet->hdr;
1980	struct rvt_qp *qp = packet->qp;
1981	u32 lqpn, rqpn = 0;
1982	u16 rlid = 0;
1983	u8 sl, sc5, svc_type;
1984
1985	switch (packet->qp->ibqp.qp_type) {
1986	case IB_QPT_UC:
1987		rlid = rdma_ah_get_dlid(&qp->remote_ah_attr);
1988		rqpn = qp->remote_qpn;
1989		svc_type = IB_CC_SVCTYPE_UC;
1990		break;
1991	case IB_QPT_RC:
1992		rlid = rdma_ah_get_dlid(&qp->remote_ah_attr);
1993		rqpn = qp->remote_qpn;
1994		svc_type = IB_CC_SVCTYPE_RC;
1995		break;
1996	case IB_QPT_SMI:
1997	case IB_QPT_GSI:
1998	case IB_QPT_UD:
1999		svc_type = IB_CC_SVCTYPE_UD;
2000		break;
2001	default:
2002		ibp->rvp.n_pkt_drops++;
2003		return;
2004	}
2005
2006	sc5 = hfi1_9B_get_sc5(hdr, packet->rhf);
2007	sl = ibp->sc_to_sl[sc5];
2008	lqpn = qp->ibqp.qp_num;
2009
2010	process_becn(ppd, sl, rlid, lqpn, rqpn, svc_type);
2011}
2012