1/*
2 * Copyright(c) 2015-2018 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 <linux/delay.h>
49#include "hfi.h"
50#include "qp.h"
51#include "trace.h"
52
53#define SC(name) SEND_CTXT_##name
54/*
55 * Send Context functions
56 */
57static void sc_wait_for_packet_egress(struct send_context *sc, int pause);
58
59/*
60 * Set the CM reset bit and wait for it to clear.  Use the provided
61 * sendctrl register.  This routine has no locking.
62 */
63void __cm_reset(struct hfi1_devdata *dd, u64 sendctrl)
64{
65	write_csr(dd, SEND_CTRL, sendctrl | SEND_CTRL_CM_RESET_SMASK);
66	while (1) {
67		udelay(1);
68		sendctrl = read_csr(dd, SEND_CTRL);
69		if ((sendctrl & SEND_CTRL_CM_RESET_SMASK) == 0)
70			break;
71	}
72}
73
74/* global control of PIO send */
75void pio_send_control(struct hfi1_devdata *dd, int op)
76{
77	u64 reg, mask;
78	unsigned long flags;
79	int write = 1;	/* write sendctrl back */
80	int flush = 0;	/* re-read sendctrl to make sure it is flushed */
81	int i;
82
83	spin_lock_irqsave(&dd->sendctrl_lock, flags);
84
85	reg = read_csr(dd, SEND_CTRL);
86	switch (op) {
87	case PSC_GLOBAL_ENABLE:
88		reg |= SEND_CTRL_SEND_ENABLE_SMASK;
89		fallthrough;
90	case PSC_DATA_VL_ENABLE:
91		mask = 0;
92		for (i = 0; i < ARRAY_SIZE(dd->vld); i++)
93			if (!dd->vld[i].mtu)
94				mask |= BIT_ULL(i);
95		/* Disallow sending on VLs not enabled */
96		mask = (mask & SEND_CTRL_UNSUPPORTED_VL_MASK) <<
97			SEND_CTRL_UNSUPPORTED_VL_SHIFT;
98		reg = (reg & ~SEND_CTRL_UNSUPPORTED_VL_SMASK) | mask;
99		break;
100	case PSC_GLOBAL_DISABLE:
101		reg &= ~SEND_CTRL_SEND_ENABLE_SMASK;
102		break;
103	case PSC_GLOBAL_VLARB_ENABLE:
104		reg |= SEND_CTRL_VL_ARBITER_ENABLE_SMASK;
105		break;
106	case PSC_GLOBAL_VLARB_DISABLE:
107		reg &= ~SEND_CTRL_VL_ARBITER_ENABLE_SMASK;
108		break;
109	case PSC_CM_RESET:
110		__cm_reset(dd, reg);
111		write = 0; /* CSR already written (and flushed) */
112		break;
113	case PSC_DATA_VL_DISABLE:
114		reg |= SEND_CTRL_UNSUPPORTED_VL_SMASK;
115		flush = 1;
116		break;
117	default:
118		dd_dev_err(dd, "%s: invalid control %d\n", __func__, op);
119		break;
120	}
121
122	if (write) {
123		write_csr(dd, SEND_CTRL, reg);
124		if (flush)
125			(void)read_csr(dd, SEND_CTRL); /* flush write */
126	}
127
128	spin_unlock_irqrestore(&dd->sendctrl_lock, flags);
129}
130
131/* number of send context memory pools */
132#define NUM_SC_POOLS 2
133
134/* Send Context Size (SCS) wildcards */
135#define SCS_POOL_0 -1
136#define SCS_POOL_1 -2
137
138/* Send Context Count (SCC) wildcards */
139#define SCC_PER_VL -1
140#define SCC_PER_CPU  -2
141#define SCC_PER_KRCVQ  -3
142
143/* Send Context Size (SCS) constants */
144#define SCS_ACK_CREDITS  32
145#define SCS_VL15_CREDITS 102	/* 3 pkts of 2048B data + 128B header */
146
147#define PIO_THRESHOLD_CEILING 4096
148
149#define PIO_WAIT_BATCH_SIZE 5
150
151/* default send context sizes */
152static struct sc_config_sizes sc_config_sizes[SC_MAX] = {
153	[SC_KERNEL] = { .size  = SCS_POOL_0,	/* even divide, pool 0 */
154			.count = SCC_PER_VL },	/* one per NUMA */
155	[SC_ACK]    = { .size  = SCS_ACK_CREDITS,
156			.count = SCC_PER_KRCVQ },
157	[SC_USER]   = { .size  = SCS_POOL_0,	/* even divide, pool 0 */
158			.count = SCC_PER_CPU },	/* one per CPU */
159	[SC_VL15]   = { .size  = SCS_VL15_CREDITS,
160			.count = 1 },
161
162};
163
164/* send context memory pool configuration */
165struct mem_pool_config {
166	int centipercent;	/* % of memory, in 100ths of 1% */
167	int absolute_blocks;	/* absolute block count */
168};
169
170/* default memory pool configuration: 100% in pool 0 */
171static struct mem_pool_config sc_mem_pool_config[NUM_SC_POOLS] = {
172	/* centi%, abs blocks */
173	{  10000,     -1 },		/* pool 0 */
174	{      0,     -1 },		/* pool 1 */
175};
176
177/* memory pool information, used when calculating final sizes */
178struct mem_pool_info {
179	int centipercent;	/*
180				 * 100th of 1% of memory to use, -1 if blocks
181				 * already set
182				 */
183	int count;		/* count of contexts in the pool */
184	int blocks;		/* block size of the pool */
185	int size;		/* context size, in blocks */
186};
187
188/*
189 * Convert a pool wildcard to a valid pool index.  The wildcards
190 * start at -1 and increase negatively.  Map them as:
191 *	-1 => 0
192 *	-2 => 1
193 *	etc.
194 *
195 * Return -1 on non-wildcard input, otherwise convert to a pool number.
196 */
197static int wildcard_to_pool(int wc)
198{
199	if (wc >= 0)
200		return -1;	/* non-wildcard */
201	return -wc - 1;
202}
203
204static const char *sc_type_names[SC_MAX] = {
205	"kernel",
206	"ack",
207	"user",
208	"vl15"
209};
210
211static const char *sc_type_name(int index)
212{
213	if (index < 0 || index >= SC_MAX)
214		return "unknown";
215	return sc_type_names[index];
216}
217
218/*
219 * Read the send context memory pool configuration and send context
220 * size configuration.  Replace any wildcards and come up with final
221 * counts and sizes for the send context types.
222 */
223int init_sc_pools_and_sizes(struct hfi1_devdata *dd)
224{
225	struct mem_pool_info mem_pool_info[NUM_SC_POOLS] = { { 0 } };
226	int total_blocks = (chip_pio_mem_size(dd) / PIO_BLOCK_SIZE) - 1;
227	int total_contexts = 0;
228	int fixed_blocks;
229	int pool_blocks;
230	int used_blocks;
231	int cp_total;		/* centipercent total */
232	int ab_total;		/* absolute block total */
233	int extra;
234	int i;
235
236	/*
237	 * When SDMA is enabled, kernel context pio packet size is capped by
238	 * "piothreshold". Reduce pio buffer allocation for kernel context by
239	 * setting it to a fixed size. The allocation allows 3-deep buffering
240	 * of the largest pio packets plus up to 128 bytes header, sufficient
241	 * to maintain verbs performance.
242	 *
243	 * When SDMA is disabled, keep the default pooling allocation.
244	 */
245	if (HFI1_CAP_IS_KSET(SDMA)) {
246		u16 max_pkt_size = (piothreshold < PIO_THRESHOLD_CEILING) ?
247					 piothreshold : PIO_THRESHOLD_CEILING;
248		sc_config_sizes[SC_KERNEL].size =
249			3 * (max_pkt_size + 128) / PIO_BLOCK_SIZE;
250	}
251
252	/*
253	 * Step 0:
254	 *	- copy the centipercents/absolute sizes from the pool config
255	 *	- sanity check these values
256	 *	- add up centipercents, then later check for full value
257	 *	- add up absolute blocks, then later check for over-commit
258	 */
259	cp_total = 0;
260	ab_total = 0;
261	for (i = 0; i < NUM_SC_POOLS; i++) {
262		int cp = sc_mem_pool_config[i].centipercent;
263		int ab = sc_mem_pool_config[i].absolute_blocks;
264
265		/*
266		 * A negative value is "unused" or "invalid".  Both *can*
267		 * be valid, but centipercent wins, so check that first
268		 */
269		if (cp >= 0) {			/* centipercent valid */
270			cp_total += cp;
271		} else if (ab >= 0) {		/* absolute blocks valid */
272			ab_total += ab;
273		} else {			/* neither valid */
274			dd_dev_err(
275				dd,
276				"Send context memory pool %d: both the block count and centipercent are invalid\n",
277				i);
278			return -EINVAL;
279		}
280
281		mem_pool_info[i].centipercent = cp;
282		mem_pool_info[i].blocks = ab;
283	}
284
285	/* do not use both % and absolute blocks for different pools */
286	if (cp_total != 0 && ab_total != 0) {
287		dd_dev_err(
288			dd,
289			"All send context memory pools must be described as either centipercent or blocks, no mixing between pools\n");
290		return -EINVAL;
291	}
292
293	/* if any percentages are present, they must add up to 100% x 100 */
294	if (cp_total != 0 && cp_total != 10000) {
295		dd_dev_err(
296			dd,
297			"Send context memory pool centipercent is %d, expecting 10000\n",
298			cp_total);
299		return -EINVAL;
300	}
301
302	/* the absolute pool total cannot be more than the mem total */
303	if (ab_total > total_blocks) {
304		dd_dev_err(
305			dd,
306			"Send context memory pool absolute block count %d is larger than the memory size %d\n",
307			ab_total, total_blocks);
308		return -EINVAL;
309	}
310
311	/*
312	 * Step 2:
313	 *	- copy from the context size config
314	 *	- replace context type wildcard counts with real values
315	 *	- add up non-memory pool block sizes
316	 *	- add up memory pool user counts
317	 */
318	fixed_blocks = 0;
319	for (i = 0; i < SC_MAX; i++) {
320		int count = sc_config_sizes[i].count;
321		int size = sc_config_sizes[i].size;
322		int pool;
323
324		/*
325		 * Sanity check count: Either a positive value or
326		 * one of the expected wildcards is valid.  The positive
327		 * value is checked later when we compare against total
328		 * memory available.
329		 */
330		if (i == SC_ACK) {
331			count = dd->n_krcv_queues;
332		} else if (i == SC_KERNEL) {
333			count = INIT_SC_PER_VL * num_vls;
334		} else if (count == SCC_PER_CPU) {
335			count = dd->num_rcv_contexts - dd->n_krcv_queues;
336		} else if (count < 0) {
337			dd_dev_err(
338				dd,
339				"%s send context invalid count wildcard %d\n",
340				sc_type_name(i), count);
341			return -EINVAL;
342		}
343		if (total_contexts + count > chip_send_contexts(dd))
344			count = chip_send_contexts(dd) - total_contexts;
345
346		total_contexts += count;
347
348		/*
349		 * Sanity check pool: The conversion will return a pool
350		 * number or -1 if a fixed (non-negative) value.  The fixed
351		 * value is checked later when we compare against
352		 * total memory available.
353		 */
354		pool = wildcard_to_pool(size);
355		if (pool == -1) {			/* non-wildcard */
356			fixed_blocks += size * count;
357		} else if (pool < NUM_SC_POOLS) {	/* valid wildcard */
358			mem_pool_info[pool].count += count;
359		} else {				/* invalid wildcard */
360			dd_dev_err(
361				dd,
362				"%s send context invalid pool wildcard %d\n",
363				sc_type_name(i), size);
364			return -EINVAL;
365		}
366
367		dd->sc_sizes[i].count = count;
368		dd->sc_sizes[i].size = size;
369	}
370	if (fixed_blocks > total_blocks) {
371		dd_dev_err(
372			dd,
373			"Send context fixed block count, %u, larger than total block count %u\n",
374			fixed_blocks, total_blocks);
375		return -EINVAL;
376	}
377
378	/* step 3: calculate the blocks in the pools, and pool context sizes */
379	pool_blocks = total_blocks - fixed_blocks;
380	if (ab_total > pool_blocks) {
381		dd_dev_err(
382			dd,
383			"Send context fixed pool sizes, %u, larger than pool block count %u\n",
384			ab_total, pool_blocks);
385		return -EINVAL;
386	}
387	/* subtract off the fixed pool blocks */
388	pool_blocks -= ab_total;
389
390	for (i = 0; i < NUM_SC_POOLS; i++) {
391		struct mem_pool_info *pi = &mem_pool_info[i];
392
393		/* % beats absolute blocks */
394		if (pi->centipercent >= 0)
395			pi->blocks = (pool_blocks * pi->centipercent) / 10000;
396
397		if (pi->blocks == 0 && pi->count != 0) {
398			dd_dev_err(
399				dd,
400				"Send context memory pool %d has %u contexts, but no blocks\n",
401				i, pi->count);
402			return -EINVAL;
403		}
404		if (pi->count == 0) {
405			/* warn about wasted blocks */
406			if (pi->blocks != 0)
407				dd_dev_err(
408					dd,
409					"Send context memory pool %d has %u blocks, but zero contexts\n",
410					i, pi->blocks);
411			pi->size = 0;
412		} else {
413			pi->size = pi->blocks / pi->count;
414		}
415	}
416
417	/* step 4: fill in the context type sizes from the pool sizes */
418	used_blocks = 0;
419	for (i = 0; i < SC_MAX; i++) {
420		if (dd->sc_sizes[i].size < 0) {
421			unsigned pool = wildcard_to_pool(dd->sc_sizes[i].size);
422
423			WARN_ON_ONCE(pool >= NUM_SC_POOLS);
424			dd->sc_sizes[i].size = mem_pool_info[pool].size;
425		}
426		/* make sure we are not larger than what is allowed by the HW */
427#define PIO_MAX_BLOCKS 1024
428		if (dd->sc_sizes[i].size > PIO_MAX_BLOCKS)
429			dd->sc_sizes[i].size = PIO_MAX_BLOCKS;
430
431		/* calculate our total usage */
432		used_blocks += dd->sc_sizes[i].size * dd->sc_sizes[i].count;
433	}
434	extra = total_blocks - used_blocks;
435	if (extra != 0)
436		dd_dev_info(dd, "unused send context blocks: %d\n", extra);
437
438	return total_contexts;
439}
440
441int init_send_contexts(struct hfi1_devdata *dd)
442{
443	u16 base;
444	int ret, i, j, context;
445
446	ret = init_credit_return(dd);
447	if (ret)
448		return ret;
449
450	dd->hw_to_sw = kmalloc_array(TXE_NUM_CONTEXTS, sizeof(u8),
451					GFP_KERNEL);
452	dd->send_contexts = kcalloc(dd->num_send_contexts,
453				    sizeof(struct send_context_info),
454				    GFP_KERNEL);
455	if (!dd->send_contexts || !dd->hw_to_sw) {
456		kfree(dd->hw_to_sw);
457		kfree(dd->send_contexts);
458		free_credit_return(dd);
459		return -ENOMEM;
460	}
461
462	/* hardware context map starts with invalid send context indices */
463	for (i = 0; i < TXE_NUM_CONTEXTS; i++)
464		dd->hw_to_sw[i] = INVALID_SCI;
465
466	/*
467	 * All send contexts have their credit sizes.  Allocate credits
468	 * for each context one after another from the global space.
469	 */
470	context = 0;
471	base = 1;
472	for (i = 0; i < SC_MAX; i++) {
473		struct sc_config_sizes *scs = &dd->sc_sizes[i];
474
475		for (j = 0; j < scs->count; j++) {
476			struct send_context_info *sci =
477						&dd->send_contexts[context];
478			sci->type = i;
479			sci->base = base;
480			sci->credits = scs->size;
481
482			context++;
483			base += scs->size;
484		}
485	}
486
487	return 0;
488}
489
490/*
491 * Allocate a software index and hardware context of the given type.
492 *
493 * Must be called with dd->sc_lock held.
494 */
495static int sc_hw_alloc(struct hfi1_devdata *dd, int type, u32 *sw_index,
496		       u32 *hw_context)
497{
498	struct send_context_info *sci;
499	u32 index;
500	u32 context;
501
502	for (index = 0, sci = &dd->send_contexts[0];
503			index < dd->num_send_contexts; index++, sci++) {
504		if (sci->type == type && sci->allocated == 0) {
505			sci->allocated = 1;
506			/* use a 1:1 mapping, but make them non-equal */
507			context = chip_send_contexts(dd) - index - 1;
508			dd->hw_to_sw[context] = index;
509			*sw_index = index;
510			*hw_context = context;
511			return 0; /* success */
512		}
513	}
514	dd_dev_err(dd, "Unable to locate a free type %d send context\n", type);
515	return -ENOSPC;
516}
517
518/*
519 * Free the send context given by its software index.
520 *
521 * Must be called with dd->sc_lock held.
522 */
523static void sc_hw_free(struct hfi1_devdata *dd, u32 sw_index, u32 hw_context)
524{
525	struct send_context_info *sci;
526
527	sci = &dd->send_contexts[sw_index];
528	if (!sci->allocated) {
529		dd_dev_err(dd, "%s: sw_index %u not allocated? hw_context %u\n",
530			   __func__, sw_index, hw_context);
531	}
532	sci->allocated = 0;
533	dd->hw_to_sw[hw_context] = INVALID_SCI;
534}
535
536/* return the base context of a context in a group */
537static inline u32 group_context(u32 context, u32 group)
538{
539	return (context >> group) << group;
540}
541
542/* return the size of a group */
543static inline u32 group_size(u32 group)
544{
545	return 1 << group;
546}
547
548/*
549 * Obtain the credit return addresses, kernel virtual and bus, for the
550 * given sc.
551 *
552 * To understand this routine:
553 * o va and dma are arrays of struct credit_return.  One for each physical
554 *   send context, per NUMA.
555 * o Each send context always looks in its relative location in a struct
556 *   credit_return for its credit return.
557 * o Each send context in a group must have its return address CSR programmed
558 *   with the same value.  Use the address of the first send context in the
559 *   group.
560 */
561static void cr_group_addresses(struct send_context *sc, dma_addr_t *dma)
562{
563	u32 gc = group_context(sc->hw_context, sc->group);
564	u32 index = sc->hw_context & 0x7;
565
566	sc->hw_free = &sc->dd->cr_base[sc->node].va[gc].cr[index];
567	*dma = (unsigned long)
568	       &((struct credit_return *)sc->dd->cr_base[sc->node].dma)[gc];
569}
570
571/*
572 * Work queue function triggered in error interrupt routine for
573 * kernel contexts.
574 */
575static void sc_halted(struct work_struct *work)
576{
577	struct send_context *sc;
578
579	sc = container_of(work, struct send_context, halt_work);
580	sc_restart(sc);
581}
582
583/*
584 * Calculate PIO block threshold for this send context using the given MTU.
585 * Trigger a return when one MTU plus optional header of credits remain.
586 *
587 * Parameter mtu is in bytes.
588 * Parameter hdrqentsize is in DWORDs.
589 *
590 * Return value is what to write into the CSR: trigger return when
591 * unreturned credits pass this count.
592 */
593u32 sc_mtu_to_threshold(struct send_context *sc, u32 mtu, u32 hdrqentsize)
594{
595	u32 release_credits;
596	u32 threshold;
597
598	/* add in the header size, then divide by the PIO block size */
599	mtu += hdrqentsize << 2;
600	release_credits = DIV_ROUND_UP(mtu, PIO_BLOCK_SIZE);
601
602	/* check against this context's credits */
603	if (sc->credits <= release_credits)
604		threshold = 1;
605	else
606		threshold = sc->credits - release_credits;
607
608	return threshold;
609}
610
611/*
612 * Calculate credit threshold in terms of percent of the allocated credits.
613 * Trigger when unreturned credits equal or exceed the percentage of the whole.
614 *
615 * Return value is what to write into the CSR: trigger return when
616 * unreturned credits pass this count.
617 */
618u32 sc_percent_to_threshold(struct send_context *sc, u32 percent)
619{
620	return (sc->credits * percent) / 100;
621}
622
623/*
624 * Set the credit return threshold.
625 */
626void sc_set_cr_threshold(struct send_context *sc, u32 new_threshold)
627{
628	unsigned long flags;
629	u32 old_threshold;
630	int force_return = 0;
631
632	spin_lock_irqsave(&sc->credit_ctrl_lock, flags);
633
634	old_threshold = (sc->credit_ctrl >>
635				SC(CREDIT_CTRL_THRESHOLD_SHIFT))
636			 & SC(CREDIT_CTRL_THRESHOLD_MASK);
637
638	if (new_threshold != old_threshold) {
639		sc->credit_ctrl =
640			(sc->credit_ctrl
641				& ~SC(CREDIT_CTRL_THRESHOLD_SMASK))
642			| ((new_threshold
643				& SC(CREDIT_CTRL_THRESHOLD_MASK))
644			   << SC(CREDIT_CTRL_THRESHOLD_SHIFT));
645		write_kctxt_csr(sc->dd, sc->hw_context,
646				SC(CREDIT_CTRL), sc->credit_ctrl);
647
648		/* force a credit return on change to avoid a possible stall */
649		force_return = 1;
650	}
651
652	spin_unlock_irqrestore(&sc->credit_ctrl_lock, flags);
653
654	if (force_return)
655		sc_return_credits(sc);
656}
657
658/*
659 * set_pio_integrity
660 *
661 * Set the CHECK_ENABLE register for the send context 'sc'.
662 */
663void set_pio_integrity(struct send_context *sc)
664{
665	struct hfi1_devdata *dd = sc->dd;
666	u32 hw_context = sc->hw_context;
667	int type = sc->type;
668
669	write_kctxt_csr(dd, hw_context,
670			SC(CHECK_ENABLE),
671			hfi1_pkt_default_send_ctxt_mask(dd, type));
672}
673
674static u32 get_buffers_allocated(struct send_context *sc)
675{
676	int cpu;
677	u32 ret = 0;
678
679	for_each_possible_cpu(cpu)
680		ret += *per_cpu_ptr(sc->buffers_allocated, cpu);
681	return ret;
682}
683
684static void reset_buffers_allocated(struct send_context *sc)
685{
686	int cpu;
687
688	for_each_possible_cpu(cpu)
689		(*per_cpu_ptr(sc->buffers_allocated, cpu)) = 0;
690}
691
692/*
693 * Allocate a NUMA relative send context structure of the given type along
694 * with a HW context.
695 */
696struct send_context *sc_alloc(struct hfi1_devdata *dd, int type,
697			      uint hdrqentsize, int numa)
698{
699	struct send_context_info *sci;
700	struct send_context *sc = NULL;
701	dma_addr_t dma;
702	unsigned long flags;
703	u64 reg;
704	u32 thresh;
705	u32 sw_index;
706	u32 hw_context;
707	int ret;
708	u8 opval, opmask;
709
710	/* do not allocate while frozen */
711	if (dd->flags & HFI1_FROZEN)
712		return NULL;
713
714	sc = kzalloc_node(sizeof(*sc), GFP_KERNEL, numa);
715	if (!sc)
716		return NULL;
717
718	sc->buffers_allocated = alloc_percpu(u32);
719	if (!sc->buffers_allocated) {
720		kfree(sc);
721		dd_dev_err(dd,
722			   "Cannot allocate buffers_allocated per cpu counters\n"
723			  );
724		return NULL;
725	}
726
727	spin_lock_irqsave(&dd->sc_lock, flags);
728	ret = sc_hw_alloc(dd, type, &sw_index, &hw_context);
729	if (ret) {
730		spin_unlock_irqrestore(&dd->sc_lock, flags);
731		free_percpu(sc->buffers_allocated);
732		kfree(sc);
733		return NULL;
734	}
735
736	sci = &dd->send_contexts[sw_index];
737	sci->sc = sc;
738
739	sc->dd = dd;
740	sc->node = numa;
741	sc->type = type;
742	spin_lock_init(&sc->alloc_lock);
743	spin_lock_init(&sc->release_lock);
744	spin_lock_init(&sc->credit_ctrl_lock);
745	seqlock_init(&sc->waitlock);
746	INIT_LIST_HEAD(&sc->piowait);
747	INIT_WORK(&sc->halt_work, sc_halted);
748	init_waitqueue_head(&sc->halt_wait);
749
750	/* grouping is always single context for now */
751	sc->group = 0;
752
753	sc->sw_index = sw_index;
754	sc->hw_context = hw_context;
755	cr_group_addresses(sc, &dma);
756	sc->credits = sci->credits;
757	sc->size = sc->credits * PIO_BLOCK_SIZE;
758
759/* PIO Send Memory Address details */
760#define PIO_ADDR_CONTEXT_MASK 0xfful
761#define PIO_ADDR_CONTEXT_SHIFT 16
762	sc->base_addr = dd->piobase + ((hw_context & PIO_ADDR_CONTEXT_MASK)
763					<< PIO_ADDR_CONTEXT_SHIFT);
764
765	/* set base and credits */
766	reg = ((sci->credits & SC(CTRL_CTXT_DEPTH_MASK))
767					<< SC(CTRL_CTXT_DEPTH_SHIFT))
768		| ((sci->base & SC(CTRL_CTXT_BASE_MASK))
769					<< SC(CTRL_CTXT_BASE_SHIFT));
770	write_kctxt_csr(dd, hw_context, SC(CTRL), reg);
771
772	set_pio_integrity(sc);
773
774	/* unmask all errors */
775	write_kctxt_csr(dd, hw_context, SC(ERR_MASK), (u64)-1);
776
777	/* set the default partition key */
778	write_kctxt_csr(dd, hw_context, SC(CHECK_PARTITION_KEY),
779			(SC(CHECK_PARTITION_KEY_VALUE_MASK) &
780			 DEFAULT_PKEY) <<
781			SC(CHECK_PARTITION_KEY_VALUE_SHIFT));
782
783	/* per context type checks */
784	if (type == SC_USER) {
785		opval = USER_OPCODE_CHECK_VAL;
786		opmask = USER_OPCODE_CHECK_MASK;
787	} else {
788		opval = OPCODE_CHECK_VAL_DISABLED;
789		opmask = OPCODE_CHECK_MASK_DISABLED;
790	}
791
792	/* set the send context check opcode mask and value */
793	write_kctxt_csr(dd, hw_context, SC(CHECK_OPCODE),
794			((u64)opmask << SC(CHECK_OPCODE_MASK_SHIFT)) |
795			((u64)opval << SC(CHECK_OPCODE_VALUE_SHIFT)));
796
797	/* set up credit return */
798	reg = dma & SC(CREDIT_RETURN_ADDR_ADDRESS_SMASK);
799	write_kctxt_csr(dd, hw_context, SC(CREDIT_RETURN_ADDR), reg);
800
801	/*
802	 * Calculate the initial credit return threshold.
803	 *
804	 * For Ack contexts, set a threshold for half the credits.
805	 * For User contexts use the given percentage.  This has been
806	 * sanitized on driver start-up.
807	 * For Kernel contexts, use the default MTU plus a header
808	 * or half the credits, whichever is smaller. This should
809	 * work for both the 3-deep buffering allocation and the
810	 * pooling allocation.
811	 */
812	if (type == SC_ACK) {
813		thresh = sc_percent_to_threshold(sc, 50);
814	} else if (type == SC_USER) {
815		thresh = sc_percent_to_threshold(sc,
816						 user_credit_return_threshold);
817	} else { /* kernel */
818		thresh = min(sc_percent_to_threshold(sc, 50),
819			     sc_mtu_to_threshold(sc, hfi1_max_mtu,
820						 hdrqentsize));
821	}
822	reg = thresh << SC(CREDIT_CTRL_THRESHOLD_SHIFT);
823	/* add in early return */
824	if (type == SC_USER && HFI1_CAP_IS_USET(EARLY_CREDIT_RETURN))
825		reg |= SC(CREDIT_CTRL_EARLY_RETURN_SMASK);
826	else if (HFI1_CAP_IS_KSET(EARLY_CREDIT_RETURN)) /* kernel, ack */
827		reg |= SC(CREDIT_CTRL_EARLY_RETURN_SMASK);
828
829	/* set up write-through credit_ctrl */
830	sc->credit_ctrl = reg;
831	write_kctxt_csr(dd, hw_context, SC(CREDIT_CTRL), reg);
832
833	/* User send contexts should not allow sending on VL15 */
834	if (type == SC_USER) {
835		reg = 1ULL << 15;
836		write_kctxt_csr(dd, hw_context, SC(CHECK_VL), reg);
837	}
838
839	spin_unlock_irqrestore(&dd->sc_lock, flags);
840
841	/*
842	 * Allocate shadow ring to track outstanding PIO buffers _after_
843	 * unlocking.  We don't know the size until the lock is held and
844	 * we can't allocate while the lock is held.  No one is using
845	 * the context yet, so allocate it now.
846	 *
847	 * User contexts do not get a shadow ring.
848	 */
849	if (type != SC_USER) {
850		/*
851		 * Size the shadow ring 1 larger than the number of credits
852		 * so head == tail can mean empty.
853		 */
854		sc->sr_size = sci->credits + 1;
855		sc->sr = kcalloc_node(sc->sr_size,
856				      sizeof(union pio_shadow_ring),
857				      GFP_KERNEL, numa);
858		if (!sc->sr) {
859			sc_free(sc);
860			return NULL;
861		}
862	}
863
864	hfi1_cdbg(PIO,
865		  "Send context %u(%u) %s group %u credits %u credit_ctrl 0x%llx threshold %u\n",
866		  sw_index,
867		  hw_context,
868		  sc_type_name(type),
869		  sc->group,
870		  sc->credits,
871		  sc->credit_ctrl,
872		  thresh);
873
874	return sc;
875}
876
877/* free a per-NUMA send context structure */
878void sc_free(struct send_context *sc)
879{
880	struct hfi1_devdata *dd;
881	unsigned long flags;
882	u32 sw_index;
883	u32 hw_context;
884
885	if (!sc)
886		return;
887
888	sc->flags |= SCF_IN_FREE;	/* ensure no restarts */
889	dd = sc->dd;
890	if (!list_empty(&sc->piowait))
891		dd_dev_err(dd, "piowait list not empty!\n");
892	sw_index = sc->sw_index;
893	hw_context = sc->hw_context;
894	sc_disable(sc);	/* make sure the HW is disabled */
895	flush_work(&sc->halt_work);
896
897	spin_lock_irqsave(&dd->sc_lock, flags);
898	dd->send_contexts[sw_index].sc = NULL;
899
900	/* clear/disable all registers set in sc_alloc */
901	write_kctxt_csr(dd, hw_context, SC(CTRL), 0);
902	write_kctxt_csr(dd, hw_context, SC(CHECK_ENABLE), 0);
903	write_kctxt_csr(dd, hw_context, SC(ERR_MASK), 0);
904	write_kctxt_csr(dd, hw_context, SC(CHECK_PARTITION_KEY), 0);
905	write_kctxt_csr(dd, hw_context, SC(CHECK_OPCODE), 0);
906	write_kctxt_csr(dd, hw_context, SC(CREDIT_RETURN_ADDR), 0);
907	write_kctxt_csr(dd, hw_context, SC(CREDIT_CTRL), 0);
908
909	/* release the index and context for re-use */
910	sc_hw_free(dd, sw_index, hw_context);
911	spin_unlock_irqrestore(&dd->sc_lock, flags);
912
913	kfree(sc->sr);
914	free_percpu(sc->buffers_allocated);
915	kfree(sc);
916}
917
918/* disable the context */
919void sc_disable(struct send_context *sc)
920{
921	u64 reg;
922	struct pio_buf *pbuf;
923	LIST_HEAD(wake_list);
924
925	if (!sc)
926		return;
927
928	/* do all steps, even if already disabled */
929	spin_lock_irq(&sc->alloc_lock);
930	reg = read_kctxt_csr(sc->dd, sc->hw_context, SC(CTRL));
931	reg &= ~SC(CTRL_CTXT_ENABLE_SMASK);
932	sc->flags &= ~SCF_ENABLED;
933	sc_wait_for_packet_egress(sc, 1);
934	write_kctxt_csr(sc->dd, sc->hw_context, SC(CTRL), reg);
935
936	/*
937	 * Flush any waiters.  Once the context is disabled,
938	 * credit return interrupts are stopped (although there
939	 * could be one in-process when the context is disabled).
940	 * Wait one microsecond for any lingering interrupts, then
941	 * proceed with the flush.
942	 */
943	udelay(1);
944	spin_lock(&sc->release_lock);
945	if (sc->sr) {	/* this context has a shadow ring */
946		while (sc->sr_tail != sc->sr_head) {
947			pbuf = &sc->sr[sc->sr_tail].pbuf;
948			if (pbuf->cb)
949				(*pbuf->cb)(pbuf->arg, PRC_SC_DISABLE);
950			sc->sr_tail++;
951			if (sc->sr_tail >= sc->sr_size)
952				sc->sr_tail = 0;
953		}
954	}
955	spin_unlock(&sc->release_lock);
956
957	write_seqlock(&sc->waitlock);
958	list_splice_init(&sc->piowait, &wake_list);
959	write_sequnlock(&sc->waitlock);
960	while (!list_empty(&wake_list)) {
961		struct iowait *wait;
962		struct rvt_qp *qp;
963		struct hfi1_qp_priv *priv;
964
965		wait = list_first_entry(&wake_list, struct iowait, list);
966		qp = iowait_to_qp(wait);
967		priv = qp->priv;
968		list_del_init(&priv->s_iowait.list);
969		priv->s_iowait.lock = NULL;
970		hfi1_qp_wakeup(qp, RVT_S_WAIT_PIO | HFI1_S_WAIT_PIO_DRAIN);
971	}
972
973	spin_unlock_irq(&sc->alloc_lock);
974}
975
976/* return SendEgressCtxtStatus.PacketOccupancy */
977static u64 packet_occupancy(u64 reg)
978{
979	return (reg &
980		SEND_EGRESS_CTXT_STATUS_CTXT_EGRESS_PACKET_OCCUPANCY_SMASK)
981		>> SEND_EGRESS_CTXT_STATUS_CTXT_EGRESS_PACKET_OCCUPANCY_SHIFT;
982}
983
984/* is egress halted on the context? */
985static bool egress_halted(u64 reg)
986{
987	return !!(reg & SEND_EGRESS_CTXT_STATUS_CTXT_EGRESS_HALT_STATUS_SMASK);
988}
989
990/* is the send context halted? */
991static bool is_sc_halted(struct hfi1_devdata *dd, u32 hw_context)
992{
993	return !!(read_kctxt_csr(dd, hw_context, SC(STATUS)) &
994		  SC(STATUS_CTXT_HALTED_SMASK));
995}
996
997/**
998 * sc_wait_for_packet_egress
999 * @sc: valid send context
1000 * @pause: wait for credit return
1001 *
1002 * Wait for packet egress, optionally pause for credit return
1003 *
1004 * Egress halt and Context halt are not necessarily the same thing, so
1005 * check for both.
1006 *
1007 * NOTE: The context halt bit may not be set immediately.  Because of this,
1008 * it is necessary to check the SW SFC_HALTED bit (set in the IRQ) and the HW
1009 * context bit to determine if the context is halted.
1010 */
1011static void sc_wait_for_packet_egress(struct send_context *sc, int pause)
1012{
1013	struct hfi1_devdata *dd = sc->dd;
1014	u64 reg = 0;
1015	u64 reg_prev;
1016	u32 loop = 0;
1017
1018	while (1) {
1019		reg_prev = reg;
1020		reg = read_csr(dd, sc->hw_context * 8 +
1021			       SEND_EGRESS_CTXT_STATUS);
1022		/* done if any halt bits, SW or HW are set */
1023		if (sc->flags & SCF_HALTED ||
1024		    is_sc_halted(dd, sc->hw_context) || egress_halted(reg))
1025			break;
1026		reg = packet_occupancy(reg);
1027		if (reg == 0)
1028			break;
1029		/* counter is reset if occupancy count changes */
1030		if (reg != reg_prev)
1031			loop = 0;
1032		if (loop > 50000) {
1033			/* timed out - bounce the link */
1034			dd_dev_err(dd,
1035				   "%s: context %u(%u) timeout waiting for packets to egress, remaining count %u, bouncing link\n",
1036				   __func__, sc->sw_index,
1037				   sc->hw_context, (u32)reg);
1038			queue_work(dd->pport->link_wq,
1039				   &dd->pport->link_bounce_work);
1040			break;
1041		}
1042		loop++;
1043		udelay(1);
1044	}
1045
1046	if (pause)
1047		/* Add additional delay to ensure chip returns all credits */
1048		pause_for_credit_return(dd);
1049}
1050
1051void sc_wait(struct hfi1_devdata *dd)
1052{
1053	int i;
1054
1055	for (i = 0; i < dd->num_send_contexts; i++) {
1056		struct send_context *sc = dd->send_contexts[i].sc;
1057
1058		if (!sc)
1059			continue;
1060		sc_wait_for_packet_egress(sc, 0);
1061	}
1062}
1063
1064/*
1065 * Restart a context after it has been halted due to error.
1066 *
1067 * If the first step fails - wait for the halt to be asserted, return early.
1068 * Otherwise complain about timeouts but keep going.
1069 *
1070 * It is expected that allocations (enabled flag bit) have been shut off
1071 * already (only applies to kernel contexts).
1072 */
1073int sc_restart(struct send_context *sc)
1074{
1075	struct hfi1_devdata *dd = sc->dd;
1076	u64 reg;
1077	u32 loop;
1078	int count;
1079
1080	/* bounce off if not halted, or being free'd */
1081	if (!(sc->flags & SCF_HALTED) || (sc->flags & SCF_IN_FREE))
1082		return -EINVAL;
1083
1084	dd_dev_info(dd, "restarting send context %u(%u)\n", sc->sw_index,
1085		    sc->hw_context);
1086
1087	/*
1088	 * Step 1: Wait for the context to actually halt.
1089	 *
1090	 * The error interrupt is asynchronous to actually setting halt
1091	 * on the context.
1092	 */
1093	loop = 0;
1094	while (1) {
1095		reg = read_kctxt_csr(dd, sc->hw_context, SC(STATUS));
1096		if (reg & SC(STATUS_CTXT_HALTED_SMASK))
1097			break;
1098		if (loop > 100) {
1099			dd_dev_err(dd, "%s: context %u(%u) not halting, skipping\n",
1100				   __func__, sc->sw_index, sc->hw_context);
1101			return -ETIME;
1102		}
1103		loop++;
1104		udelay(1);
1105	}
1106
1107	/*
1108	 * Step 2: Ensure no users are still trying to write to PIO.
1109	 *
1110	 * For kernel contexts, we have already turned off buffer allocation.
1111	 * Now wait for the buffer count to go to zero.
1112	 *
1113	 * For user contexts, the user handling code has cut off write access
1114	 * to the context's PIO pages before calling this routine and will
1115	 * restore write access after this routine returns.
1116	 */
1117	if (sc->type != SC_USER) {
1118		/* kernel context */
1119		loop = 0;
1120		while (1) {
1121			count = get_buffers_allocated(sc);
1122			if (count == 0)
1123				break;
1124			if (loop > 100) {
1125				dd_dev_err(dd,
1126					   "%s: context %u(%u) timeout waiting for PIO buffers to zero, remaining %d\n",
1127					   __func__, sc->sw_index,
1128					   sc->hw_context, count);
1129			}
1130			loop++;
1131			udelay(1);
1132		}
1133	}
1134
1135	/*
1136	 * Step 3: Wait for all packets to egress.
1137	 * This is done while disabling the send context
1138	 *
1139	 * Step 4: Disable the context
1140	 *
1141	 * This is a superset of the halt.  After the disable, the
1142	 * errors can be cleared.
1143	 */
1144	sc_disable(sc);
1145
1146	/*
1147	 * Step 5: Enable the context
1148	 *
1149	 * This enable will clear the halted flag and per-send context
1150	 * error flags.
1151	 */
1152	return sc_enable(sc);
1153}
1154
1155/*
1156 * PIO freeze processing.  To be called after the TXE block is fully frozen.
1157 * Go through all frozen send contexts and disable them.  The contexts are
1158 * already stopped by the freeze.
1159 */
1160void pio_freeze(struct hfi1_devdata *dd)
1161{
1162	struct send_context *sc;
1163	int i;
1164
1165	for (i = 0; i < dd->num_send_contexts; i++) {
1166		sc = dd->send_contexts[i].sc;
1167		/*
1168		 * Don't disable unallocated, unfrozen, or user send contexts.
1169		 * User send contexts will be disabled when the process
1170		 * calls into the driver to reset its context.
1171		 */
1172		if (!sc || !(sc->flags & SCF_FROZEN) || sc->type == SC_USER)
1173			continue;
1174
1175		/* only need to disable, the context is already stopped */
1176		sc_disable(sc);
1177	}
1178}
1179
1180/*
1181 * Unfreeze PIO for kernel send contexts.  The precondition for calling this
1182 * is that all PIO send contexts have been disabled and the SPC freeze has
1183 * been cleared.  Now perform the last step and re-enable each kernel context.
1184 * User (PSM) processing will occur when PSM calls into the kernel to
1185 * acknowledge the freeze.
1186 */
1187void pio_kernel_unfreeze(struct hfi1_devdata *dd)
1188{
1189	struct send_context *sc;
1190	int i;
1191
1192	for (i = 0; i < dd->num_send_contexts; i++) {
1193		sc = dd->send_contexts[i].sc;
1194		if (!sc || !(sc->flags & SCF_FROZEN) || sc->type == SC_USER)
1195			continue;
1196		if (sc->flags & SCF_LINK_DOWN)
1197			continue;
1198
1199		sc_enable(sc);	/* will clear the sc frozen flag */
1200	}
1201}
1202
1203/**
1204 * pio_kernel_linkup() - Re-enable send contexts after linkup event
1205 * @dd: valid devive data
1206 *
1207 * When the link goes down, the freeze path is taken.  However, a link down
1208 * event is different from a freeze because if the send context is re-enabled
1209 * whowever is sending data will start sending data again, which will hang
1210 * any QP that is sending data.
1211 *
1212 * The freeze path now looks at the type of event that occurs and takes this
1213 * path for link down event.
1214 */
1215void pio_kernel_linkup(struct hfi1_devdata *dd)
1216{
1217	struct send_context *sc;
1218	int i;
1219
1220	for (i = 0; i < dd->num_send_contexts; i++) {
1221		sc = dd->send_contexts[i].sc;
1222		if (!sc || !(sc->flags & SCF_LINK_DOWN) || sc->type == SC_USER)
1223			continue;
1224
1225		sc_enable(sc);	/* will clear the sc link down flag */
1226	}
1227}
1228
1229/*
1230 * Wait for the SendPioInitCtxt.PioInitInProgress bit to clear.
1231 * Returns:
1232 *	-ETIMEDOUT - if we wait too long
1233 *	-EIO	   - if there was an error
1234 */
1235static int pio_init_wait_progress(struct hfi1_devdata *dd)
1236{
1237	u64 reg;
1238	int max, count = 0;
1239
1240	/* max is the longest possible HW init time / delay */
1241	max = (dd->icode == ICODE_FPGA_EMULATION) ? 120 : 5;
1242	while (1) {
1243		reg = read_csr(dd, SEND_PIO_INIT_CTXT);
1244		if (!(reg & SEND_PIO_INIT_CTXT_PIO_INIT_IN_PROGRESS_SMASK))
1245			break;
1246		if (count >= max)
1247			return -ETIMEDOUT;
1248		udelay(5);
1249		count++;
1250	}
1251
1252	return reg & SEND_PIO_INIT_CTXT_PIO_INIT_ERR_SMASK ? -EIO : 0;
1253}
1254
1255/*
1256 * Reset all of the send contexts to their power-on state.  Used
1257 * only during manual init - no lock against sc_enable needed.
1258 */
1259void pio_reset_all(struct hfi1_devdata *dd)
1260{
1261	int ret;
1262
1263	/* make sure the init engine is not busy */
1264	ret = pio_init_wait_progress(dd);
1265	/* ignore any timeout */
1266	if (ret == -EIO) {
1267		/* clear the error */
1268		write_csr(dd, SEND_PIO_ERR_CLEAR,
1269			  SEND_PIO_ERR_CLEAR_PIO_INIT_SM_IN_ERR_SMASK);
1270	}
1271
1272	/* reset init all */
1273	write_csr(dd, SEND_PIO_INIT_CTXT,
1274		  SEND_PIO_INIT_CTXT_PIO_ALL_CTXT_INIT_SMASK);
1275	udelay(2);
1276	ret = pio_init_wait_progress(dd);
1277	if (ret < 0) {
1278		dd_dev_err(dd,
1279			   "PIO send context init %s while initializing all PIO blocks\n",
1280			   ret == -ETIMEDOUT ? "is stuck" : "had an error");
1281	}
1282}
1283
1284/* enable the context */
1285int sc_enable(struct send_context *sc)
1286{
1287	u64 sc_ctrl, reg, pio;
1288	struct hfi1_devdata *dd;
1289	unsigned long flags;
1290	int ret = 0;
1291
1292	if (!sc)
1293		return -EINVAL;
1294	dd = sc->dd;
1295
1296	/*
1297	 * Obtain the allocator lock to guard against any allocation
1298	 * attempts (which should not happen prior to context being
1299	 * enabled). On the release/disable side we don't need to
1300	 * worry about locking since the releaser will not do anything
1301	 * if the context accounting values have not changed.
1302	 */
1303	spin_lock_irqsave(&sc->alloc_lock, flags);
1304	sc_ctrl = read_kctxt_csr(dd, sc->hw_context, SC(CTRL));
1305	if ((sc_ctrl & SC(CTRL_CTXT_ENABLE_SMASK)))
1306		goto unlock; /* already enabled */
1307
1308	/* IMPORTANT: only clear free and fill if transitioning 0 -> 1 */
1309
1310	*sc->hw_free = 0;
1311	sc->free = 0;
1312	sc->alloc_free = 0;
1313	sc->fill = 0;
1314	sc->fill_wrap = 0;
1315	sc->sr_head = 0;
1316	sc->sr_tail = 0;
1317	sc->flags = 0;
1318	/* the alloc lock insures no fast path allocation */
1319	reset_buffers_allocated(sc);
1320
1321	/*
1322	 * Clear all per-context errors.  Some of these will be set when
1323	 * we are re-enabling after a context halt.  Now that the context
1324	 * is disabled, the halt will not clear until after the PIO init
1325	 * engine runs below.
1326	 */
1327	reg = read_kctxt_csr(dd, sc->hw_context, SC(ERR_STATUS));
1328	if (reg)
1329		write_kctxt_csr(dd, sc->hw_context, SC(ERR_CLEAR), reg);
1330
1331	/*
1332	 * The HW PIO initialization engine can handle only one init
1333	 * request at a time. Serialize access to each device's engine.
1334	 */
1335	spin_lock(&dd->sc_init_lock);
1336	/*
1337	 * Since access to this code block is serialized and
1338	 * each access waits for the initialization to complete
1339	 * before releasing the lock, the PIO initialization engine
1340	 * should not be in use, so we don't have to wait for the
1341	 * InProgress bit to go down.
1342	 */
1343	pio = ((sc->hw_context & SEND_PIO_INIT_CTXT_PIO_CTXT_NUM_MASK) <<
1344	       SEND_PIO_INIT_CTXT_PIO_CTXT_NUM_SHIFT) |
1345		SEND_PIO_INIT_CTXT_PIO_SINGLE_CTXT_INIT_SMASK;
1346	write_csr(dd, SEND_PIO_INIT_CTXT, pio);
1347	/*
1348	 * Wait until the engine is done.  Give the chip the required time
1349	 * so, hopefully, we read the register just once.
1350	 */
1351	udelay(2);
1352	ret = pio_init_wait_progress(dd);
1353	spin_unlock(&dd->sc_init_lock);
1354	if (ret) {
1355		dd_dev_err(dd,
1356			   "sctxt%u(%u): Context not enabled due to init failure %d\n",
1357			   sc->sw_index, sc->hw_context, ret);
1358		goto unlock;
1359	}
1360
1361	/*
1362	 * All is well. Enable the context.
1363	 */
1364	sc_ctrl |= SC(CTRL_CTXT_ENABLE_SMASK);
1365	write_kctxt_csr(dd, sc->hw_context, SC(CTRL), sc_ctrl);
1366	/*
1367	 * Read SendCtxtCtrl to force the write out and prevent a timing
1368	 * hazard where a PIO write may reach the context before the enable.
1369	 */
1370	read_kctxt_csr(dd, sc->hw_context, SC(CTRL));
1371	sc->flags |= SCF_ENABLED;
1372
1373unlock:
1374	spin_unlock_irqrestore(&sc->alloc_lock, flags);
1375
1376	return ret;
1377}
1378
1379/* force a credit return on the context */
1380void sc_return_credits(struct send_context *sc)
1381{
1382	if (!sc)
1383		return;
1384
1385	/* a 0->1 transition schedules a credit return */
1386	write_kctxt_csr(sc->dd, sc->hw_context, SC(CREDIT_FORCE),
1387			SC(CREDIT_FORCE_FORCE_RETURN_SMASK));
1388	/*
1389	 * Ensure that the write is flushed and the credit return is
1390	 * scheduled. We care more about the 0 -> 1 transition.
1391	 */
1392	read_kctxt_csr(sc->dd, sc->hw_context, SC(CREDIT_FORCE));
1393	/* set back to 0 for next time */
1394	write_kctxt_csr(sc->dd, sc->hw_context, SC(CREDIT_FORCE), 0);
1395}
1396
1397/* allow all in-flight packets to drain on the context */
1398void sc_flush(struct send_context *sc)
1399{
1400	if (!sc)
1401		return;
1402
1403	sc_wait_for_packet_egress(sc, 1);
1404}
1405
1406/* drop all packets on the context, no waiting until they are sent */
1407void sc_drop(struct send_context *sc)
1408{
1409	if (!sc)
1410		return;
1411
1412	dd_dev_info(sc->dd, "%s: context %u(%u) - not implemented\n",
1413		    __func__, sc->sw_index, sc->hw_context);
1414}
1415
1416/*
1417 * Start the software reaction to a context halt or SPC freeze:
1418 *	- mark the context as halted or frozen
1419 *	- stop buffer allocations
1420 *
1421 * Called from the error interrupt.  Other work is deferred until
1422 * out of the interrupt.
1423 */
1424void sc_stop(struct send_context *sc, int flag)
1425{
1426	unsigned long flags;
1427
1428	/* stop buffer allocations */
1429	spin_lock_irqsave(&sc->alloc_lock, flags);
1430	/* mark the context */
1431	sc->flags |= flag;
1432	sc->flags &= ~SCF_ENABLED;
1433	spin_unlock_irqrestore(&sc->alloc_lock, flags);
1434	wake_up(&sc->halt_wait);
1435}
1436
1437#define BLOCK_DWORDS (PIO_BLOCK_SIZE / sizeof(u32))
1438#define dwords_to_blocks(x) DIV_ROUND_UP(x, BLOCK_DWORDS)
1439
1440/*
1441 * The send context buffer "allocator".
1442 *
1443 * @sc: the PIO send context we are allocating from
1444 * @len: length of whole packet - including PBC - in dwords
1445 * @cb: optional callback to call when the buffer is finished sending
1446 * @arg: argument for cb
1447 *
1448 * Return a pointer to a PIO buffer, NULL if not enough room, -ECOMM
1449 * when link is down.
1450 */
1451struct pio_buf *sc_buffer_alloc(struct send_context *sc, u32 dw_len,
1452				pio_release_cb cb, void *arg)
1453{
1454	struct pio_buf *pbuf = NULL;
1455	unsigned long flags;
1456	unsigned long avail;
1457	unsigned long blocks = dwords_to_blocks(dw_len);
1458	u32 fill_wrap;
1459	int trycount = 0;
1460	u32 head, next;
1461
1462	spin_lock_irqsave(&sc->alloc_lock, flags);
1463	if (!(sc->flags & SCF_ENABLED)) {
1464		spin_unlock_irqrestore(&sc->alloc_lock, flags);
1465		return ERR_PTR(-ECOMM);
1466	}
1467
1468retry:
1469	avail = (unsigned long)sc->credits - (sc->fill - sc->alloc_free);
1470	if (blocks > avail) {
1471		/* not enough room */
1472		if (unlikely(trycount))	{ /* already tried to get more room */
1473			spin_unlock_irqrestore(&sc->alloc_lock, flags);
1474			goto done;
1475		}
1476		/* copy from receiver cache line and recalculate */
1477		sc->alloc_free = READ_ONCE(sc->free);
1478		avail =
1479			(unsigned long)sc->credits -
1480			(sc->fill - sc->alloc_free);
1481		if (blocks > avail) {
1482			/* still no room, actively update */
1483			sc_release_update(sc);
1484			sc->alloc_free = READ_ONCE(sc->free);
1485			trycount++;
1486			goto retry;
1487		}
1488	}
1489
1490	/* there is enough room */
1491
1492	preempt_disable();
1493	this_cpu_inc(*sc->buffers_allocated);
1494
1495	/* read this once */
1496	head = sc->sr_head;
1497
1498	/* "allocate" the buffer */
1499	sc->fill += blocks;
1500	fill_wrap = sc->fill_wrap;
1501	sc->fill_wrap += blocks;
1502	if (sc->fill_wrap >= sc->credits)
1503		sc->fill_wrap = sc->fill_wrap - sc->credits;
1504
1505	/*
1506	 * Fill the parts that the releaser looks at before moving the head.
1507	 * The only necessary piece is the sent_at field.  The credits
1508	 * we have just allocated cannot have been returned yet, so the
1509	 * cb and arg will not be looked at for a "while".  Put them
1510	 * on this side of the memory barrier anyway.
1511	 */
1512	pbuf = &sc->sr[head].pbuf;
1513	pbuf->sent_at = sc->fill;
1514	pbuf->cb = cb;
1515	pbuf->arg = arg;
1516	pbuf->sc = sc;	/* could be filled in at sc->sr init time */
1517	/* make sure this is in memory before updating the head */
1518
1519	/* calculate next head index, do not store */
1520	next = head + 1;
1521	if (next >= sc->sr_size)
1522		next = 0;
1523	/*
1524	 * update the head - must be last! - the releaser can look at fields
1525	 * in pbuf once we move the head
1526	 */
1527	smp_wmb();
1528	sc->sr_head = next;
1529	spin_unlock_irqrestore(&sc->alloc_lock, flags);
1530
1531	/* finish filling in the buffer outside the lock */
1532	pbuf->start = sc->base_addr + fill_wrap * PIO_BLOCK_SIZE;
1533	pbuf->end = sc->base_addr + sc->size;
1534	pbuf->qw_written = 0;
1535	pbuf->carry_bytes = 0;
1536	pbuf->carry.val64 = 0;
1537done:
1538	return pbuf;
1539}
1540
1541/*
1542 * There are at least two entities that can turn on credit return
1543 * interrupts and they can overlap.  Avoid problems by implementing
1544 * a count scheme that is enforced by a lock.  The lock is needed because
1545 * the count and CSR write must be paired.
1546 */
1547
1548/*
1549 * Start credit return interrupts.  This is managed by a count.  If already
1550 * on, just increment the count.
1551 */
1552void sc_add_credit_return_intr(struct send_context *sc)
1553{
1554	unsigned long flags;
1555
1556	/* lock must surround both the count change and the CSR update */
1557	spin_lock_irqsave(&sc->credit_ctrl_lock, flags);
1558	if (sc->credit_intr_count == 0) {
1559		sc->credit_ctrl |= SC(CREDIT_CTRL_CREDIT_INTR_SMASK);
1560		write_kctxt_csr(sc->dd, sc->hw_context,
1561				SC(CREDIT_CTRL), sc->credit_ctrl);
1562	}
1563	sc->credit_intr_count++;
1564	spin_unlock_irqrestore(&sc->credit_ctrl_lock, flags);
1565}
1566
1567/*
1568 * Stop credit return interrupts.  This is managed by a count.  Decrement the
1569 * count, if the last user, then turn the credit interrupts off.
1570 */
1571void sc_del_credit_return_intr(struct send_context *sc)
1572{
1573	unsigned long flags;
1574
1575	WARN_ON(sc->credit_intr_count == 0);
1576
1577	/* lock must surround both the count change and the CSR update */
1578	spin_lock_irqsave(&sc->credit_ctrl_lock, flags);
1579	sc->credit_intr_count--;
1580	if (sc->credit_intr_count == 0) {
1581		sc->credit_ctrl &= ~SC(CREDIT_CTRL_CREDIT_INTR_SMASK);
1582		write_kctxt_csr(sc->dd, sc->hw_context,
1583				SC(CREDIT_CTRL), sc->credit_ctrl);
1584	}
1585	spin_unlock_irqrestore(&sc->credit_ctrl_lock, flags);
1586}
1587
1588/*
1589 * The caller must be careful when calling this.  All needint calls
1590 * must be paired with !needint.
1591 */
1592void hfi1_sc_wantpiobuf_intr(struct send_context *sc, u32 needint)
1593{
1594	if (needint)
1595		sc_add_credit_return_intr(sc);
1596	else
1597		sc_del_credit_return_intr(sc);
1598	trace_hfi1_wantpiointr(sc, needint, sc->credit_ctrl);
1599	if (needint)
1600		sc_return_credits(sc);
1601}
1602
1603/**
1604 * sc_piobufavail - callback when a PIO buffer is available
1605 * @sc: the send context
1606 *
1607 * This is called from the interrupt handler when a PIO buffer is
1608 * available after hfi1_verbs_send() returned an error that no buffers were
1609 * available. Disable the interrupt if there are no more QPs waiting.
1610 */
1611static void sc_piobufavail(struct send_context *sc)
1612{
1613	struct hfi1_devdata *dd = sc->dd;
1614	struct list_head *list;
1615	struct rvt_qp *qps[PIO_WAIT_BATCH_SIZE];
1616	struct rvt_qp *qp;
1617	struct hfi1_qp_priv *priv;
1618	unsigned long flags;
1619	uint i, n = 0, top_idx = 0;
1620
1621	if (dd->send_contexts[sc->sw_index].type != SC_KERNEL &&
1622	    dd->send_contexts[sc->sw_index].type != SC_VL15)
1623		return;
1624	list = &sc->piowait;
1625	/*
1626	 * Note: checking that the piowait list is empty and clearing
1627	 * the buffer available interrupt needs to be atomic or we
1628	 * could end up with QPs on the wait list with the interrupt
1629	 * disabled.
1630	 */
1631	write_seqlock_irqsave(&sc->waitlock, flags);
1632	while (!list_empty(list)) {
1633		struct iowait *wait;
1634
1635		if (n == ARRAY_SIZE(qps))
1636			break;
1637		wait = list_first_entry(list, struct iowait, list);
1638		iowait_get_priority(wait);
1639		qp = iowait_to_qp(wait);
1640		priv = qp->priv;
1641		list_del_init(&priv->s_iowait.list);
1642		priv->s_iowait.lock = NULL;
1643		if (n) {
1644			priv = qps[top_idx]->priv;
1645			top_idx = iowait_priority_update_top(wait,
1646							     &priv->s_iowait,
1647							     n, top_idx);
1648		}
1649
1650		/* refcount held until actual wake up */
1651		qps[n++] = qp;
1652	}
1653	/*
1654	 * If there had been waiters and there are more
1655	 * insure that we redo the force to avoid a potential hang.
1656	 */
1657	if (n) {
1658		hfi1_sc_wantpiobuf_intr(sc, 0);
1659		if (!list_empty(list))
1660			hfi1_sc_wantpiobuf_intr(sc, 1);
1661	}
1662	write_sequnlock_irqrestore(&sc->waitlock, flags);
1663
1664	/* Wake up the top-priority one first */
1665	if (n)
1666		hfi1_qp_wakeup(qps[top_idx],
1667			       RVT_S_WAIT_PIO | HFI1_S_WAIT_PIO_DRAIN);
1668	for (i = 0; i < n; i++)
1669		if (i != top_idx)
1670			hfi1_qp_wakeup(qps[i],
1671				       RVT_S_WAIT_PIO | HFI1_S_WAIT_PIO_DRAIN);
1672}
1673
1674/* translate a send credit update to a bit code of reasons */
1675static inline int fill_code(u64 hw_free)
1676{
1677	int code = 0;
1678
1679	if (hw_free & CR_STATUS_SMASK)
1680		code |= PRC_STATUS_ERR;
1681	if (hw_free & CR_CREDIT_RETURN_DUE_TO_PBC_SMASK)
1682		code |= PRC_PBC;
1683	if (hw_free & CR_CREDIT_RETURN_DUE_TO_THRESHOLD_SMASK)
1684		code |= PRC_THRESHOLD;
1685	if (hw_free & CR_CREDIT_RETURN_DUE_TO_ERR_SMASK)
1686		code |= PRC_FILL_ERR;
1687	if (hw_free & CR_CREDIT_RETURN_DUE_TO_FORCE_SMASK)
1688		code |= PRC_SC_DISABLE;
1689	return code;
1690}
1691
1692/* use the jiffies compare to get the wrap right */
1693#define sent_before(a, b) time_before(a, b)	/* a < b */
1694
1695/*
1696 * The send context buffer "releaser".
1697 */
1698void sc_release_update(struct send_context *sc)
1699{
1700	struct pio_buf *pbuf;
1701	u64 hw_free;
1702	u32 head, tail;
1703	unsigned long old_free;
1704	unsigned long free;
1705	unsigned long extra;
1706	unsigned long flags;
1707	int code;
1708
1709	if (!sc)
1710		return;
1711
1712	spin_lock_irqsave(&sc->release_lock, flags);
1713	/* update free */
1714	hw_free = le64_to_cpu(*sc->hw_free);		/* volatile read */
1715	old_free = sc->free;
1716	extra = (((hw_free & CR_COUNTER_SMASK) >> CR_COUNTER_SHIFT)
1717			- (old_free & CR_COUNTER_MASK))
1718				& CR_COUNTER_MASK;
1719	free = old_free + extra;
1720	trace_hfi1_piofree(sc, extra);
1721
1722	/* call sent buffer callbacks */
1723	code = -1;				/* code not yet set */
1724	head = READ_ONCE(sc->sr_head);	/* snapshot the head */
1725	tail = sc->sr_tail;
1726	while (head != tail) {
1727		pbuf = &sc->sr[tail].pbuf;
1728
1729		if (sent_before(free, pbuf->sent_at)) {
1730			/* not sent yet */
1731			break;
1732		}
1733		if (pbuf->cb) {
1734			if (code < 0) /* fill in code on first user */
1735				code = fill_code(hw_free);
1736			(*pbuf->cb)(pbuf->arg, code);
1737		}
1738
1739		tail++;
1740		if (tail >= sc->sr_size)
1741			tail = 0;
1742	}
1743	sc->sr_tail = tail;
1744	/* make sure tail is updated before free */
1745	smp_wmb();
1746	sc->free = free;
1747	spin_unlock_irqrestore(&sc->release_lock, flags);
1748	sc_piobufavail(sc);
1749}
1750
1751/*
1752 * Send context group releaser.  Argument is the send context that caused
1753 * the interrupt.  Called from the send context interrupt handler.
1754 *
1755 * Call release on all contexts in the group.
1756 *
1757 * This routine takes the sc_lock without an irqsave because it is only
1758 * called from an interrupt handler.  Adjust if that changes.
1759 */
1760void sc_group_release_update(struct hfi1_devdata *dd, u32 hw_context)
1761{
1762	struct send_context *sc;
1763	u32 sw_index;
1764	u32 gc, gc_end;
1765
1766	spin_lock(&dd->sc_lock);
1767	sw_index = dd->hw_to_sw[hw_context];
1768	if (unlikely(sw_index >= dd->num_send_contexts)) {
1769		dd_dev_err(dd, "%s: invalid hw (%u) to sw (%u) mapping\n",
1770			   __func__, hw_context, sw_index);
1771		goto done;
1772	}
1773	sc = dd->send_contexts[sw_index].sc;
1774	if (unlikely(!sc))
1775		goto done;
1776
1777	gc = group_context(hw_context, sc->group);
1778	gc_end = gc + group_size(sc->group);
1779	for (; gc < gc_end; gc++) {
1780		sw_index = dd->hw_to_sw[gc];
1781		if (unlikely(sw_index >= dd->num_send_contexts)) {
1782			dd_dev_err(dd,
1783				   "%s: invalid hw (%u) to sw (%u) mapping\n",
1784				   __func__, hw_context, sw_index);
1785			continue;
1786		}
1787		sc_release_update(dd->send_contexts[sw_index].sc);
1788	}
1789done:
1790	spin_unlock(&dd->sc_lock);
1791}
1792
1793/*
1794 * pio_select_send_context_vl() - select send context
1795 * @dd: devdata
1796 * @selector: a spreading factor
1797 * @vl: this vl
1798 *
1799 * This function returns a send context based on the selector and a vl.
1800 * The mapping fields are protected by RCU
1801 */
1802struct send_context *pio_select_send_context_vl(struct hfi1_devdata *dd,
1803						u32 selector, u8 vl)
1804{
1805	struct pio_vl_map *m;
1806	struct pio_map_elem *e;
1807	struct send_context *rval;
1808
1809	/*
1810	 * NOTE This should only happen if SC->VL changed after the initial
1811	 * checks on the QP/AH
1812	 * Default will return VL0's send context below
1813	 */
1814	if (unlikely(vl >= num_vls)) {
1815		rval = NULL;
1816		goto done;
1817	}
1818
1819	rcu_read_lock();
1820	m = rcu_dereference(dd->pio_map);
1821	if (unlikely(!m)) {
1822		rcu_read_unlock();
1823		return dd->vld[0].sc;
1824	}
1825	e = m->map[vl & m->mask];
1826	rval = e->ksc[selector & e->mask];
1827	rcu_read_unlock();
1828
1829done:
1830	rval = !rval ? dd->vld[0].sc : rval;
1831	return rval;
1832}
1833
1834/*
1835 * pio_select_send_context_sc() - select send context
1836 * @dd: devdata
1837 * @selector: a spreading factor
1838 * @sc5: the 5 bit sc
1839 *
1840 * This function returns an send context based on the selector and an sc
1841 */
1842struct send_context *pio_select_send_context_sc(struct hfi1_devdata *dd,
1843						u32 selector, u8 sc5)
1844{
1845	u8 vl = sc_to_vlt(dd, sc5);
1846
1847	return pio_select_send_context_vl(dd, selector, vl);
1848}
1849
1850/*
1851 * Free the indicated map struct
1852 */
1853static void pio_map_free(struct pio_vl_map *m)
1854{
1855	int i;
1856
1857	for (i = 0; m && i < m->actual_vls; i++)
1858		kfree(m->map[i]);
1859	kfree(m);
1860}
1861
1862/*
1863 * Handle RCU callback
1864 */
1865static void pio_map_rcu_callback(struct rcu_head *list)
1866{
1867	struct pio_vl_map *m = container_of(list, struct pio_vl_map, list);
1868
1869	pio_map_free(m);
1870}
1871
1872/*
1873 * Set credit return threshold for the kernel send context
1874 */
1875static void set_threshold(struct hfi1_devdata *dd, int scontext, int i)
1876{
1877	u32 thres;
1878
1879	thres = min(sc_percent_to_threshold(dd->kernel_send_context[scontext],
1880					    50),
1881		    sc_mtu_to_threshold(dd->kernel_send_context[scontext],
1882					dd->vld[i].mtu,
1883					dd->rcd[0]->rcvhdrqentsize));
1884	sc_set_cr_threshold(dd->kernel_send_context[scontext], thres);
1885}
1886
1887/*
1888 * pio_map_init - called when #vls change
1889 * @dd: hfi1_devdata
1890 * @port: port number
1891 * @num_vls: number of vls
1892 * @vl_scontexts: per vl send context mapping (optional)
1893 *
1894 * This routine changes the mapping based on the number of vls.
1895 *
1896 * vl_scontexts is used to specify a non-uniform vl/send context
1897 * loading. NULL implies auto computing the loading and giving each
1898 * VL an uniform distribution of send contexts per VL.
1899 *
1900 * The auto algorithm computers the sc_per_vl and the number of extra
1901 * send contexts. Any extra send contexts are added from the last VL
1902 * on down
1903 *
1904 * rcu locking is used here to control access to the mapping fields.
1905 *
1906 * If either the num_vls or num_send_contexts are non-power of 2, the
1907 * array sizes in the struct pio_vl_map and the struct pio_map_elem are
1908 * rounded up to the next highest power of 2 and the first entry is
1909 * reused in a round robin fashion.
1910 *
1911 * If an error occurs the map change is not done and the mapping is not
1912 * chaged.
1913 *
1914 */
1915int pio_map_init(struct hfi1_devdata *dd, u8 port, u8 num_vls, u8 *vl_scontexts)
1916{
1917	int i, j;
1918	int extra, sc_per_vl;
1919	int scontext = 1;
1920	int num_kernel_send_contexts = 0;
1921	u8 lvl_scontexts[OPA_MAX_VLS];
1922	struct pio_vl_map *oldmap, *newmap;
1923
1924	if (!vl_scontexts) {
1925		for (i = 0; i < dd->num_send_contexts; i++)
1926			if (dd->send_contexts[i].type == SC_KERNEL)
1927				num_kernel_send_contexts++;
1928		/* truncate divide */
1929		sc_per_vl = num_kernel_send_contexts / num_vls;
1930		/* extras */
1931		extra = num_kernel_send_contexts % num_vls;
1932		vl_scontexts = lvl_scontexts;
1933		/* add extras from last vl down */
1934		for (i = num_vls - 1; i >= 0; i--, extra--)
1935			vl_scontexts[i] = sc_per_vl + (extra > 0 ? 1 : 0);
1936	}
1937	/* build new map */
1938	newmap = kzalloc(sizeof(*newmap) +
1939			 roundup_pow_of_two(num_vls) *
1940			 sizeof(struct pio_map_elem *),
1941			 GFP_KERNEL);
1942	if (!newmap)
1943		goto bail;
1944	newmap->actual_vls = num_vls;
1945	newmap->vls = roundup_pow_of_two(num_vls);
1946	newmap->mask = (1 << ilog2(newmap->vls)) - 1;
1947	for (i = 0; i < newmap->vls; i++) {
1948		/* save for wrap around */
1949		int first_scontext = scontext;
1950
1951		if (i < newmap->actual_vls) {
1952			int sz = roundup_pow_of_two(vl_scontexts[i]);
1953
1954			/* only allocate once */
1955			newmap->map[i] = kzalloc(sizeof(*newmap->map[i]) +
1956						 sz * sizeof(struct
1957							     send_context *),
1958						 GFP_KERNEL);
1959			if (!newmap->map[i])
1960				goto bail;
1961			newmap->map[i]->mask = (1 << ilog2(sz)) - 1;
1962			/*
1963			 * assign send contexts and
1964			 * adjust credit return threshold
1965			 */
1966			for (j = 0; j < sz; j++) {
1967				if (dd->kernel_send_context[scontext]) {
1968					newmap->map[i]->ksc[j] =
1969					dd->kernel_send_context[scontext];
1970					set_threshold(dd, scontext, i);
1971				}
1972				if (++scontext >= first_scontext +
1973						  vl_scontexts[i])
1974					/* wrap back to first send context */
1975					scontext = first_scontext;
1976			}
1977		} else {
1978			/* just re-use entry without allocating */
1979			newmap->map[i] = newmap->map[i % num_vls];
1980		}
1981		scontext = first_scontext + vl_scontexts[i];
1982	}
1983	/* newmap in hand, save old map */
1984	spin_lock_irq(&dd->pio_map_lock);
1985	oldmap = rcu_dereference_protected(dd->pio_map,
1986					   lockdep_is_held(&dd->pio_map_lock));
1987
1988	/* publish newmap */
1989	rcu_assign_pointer(dd->pio_map, newmap);
1990
1991	spin_unlock_irq(&dd->pio_map_lock);
1992	/* success, free any old map after grace period */
1993	if (oldmap)
1994		call_rcu(&oldmap->list, pio_map_rcu_callback);
1995	return 0;
1996bail:
1997	/* free any partial allocation */
1998	pio_map_free(newmap);
1999	return -ENOMEM;
2000}
2001
2002void free_pio_map(struct hfi1_devdata *dd)
2003{
2004	/* Free PIO map if allocated */
2005	if (rcu_access_pointer(dd->pio_map)) {
2006		spin_lock_irq(&dd->pio_map_lock);
2007		pio_map_free(rcu_access_pointer(dd->pio_map));
2008		RCU_INIT_POINTER(dd->pio_map, NULL);
2009		spin_unlock_irq(&dd->pio_map_lock);
2010		synchronize_rcu();
2011	}
2012	kfree(dd->kernel_send_context);
2013	dd->kernel_send_context = NULL;
2014}
2015
2016int init_pervl_scs(struct hfi1_devdata *dd)
2017{
2018	int i;
2019	u64 mask, all_vl_mask = (u64)0x80ff; /* VLs 0-7, 15 */
2020	u64 data_vls_mask = (u64)0x00ff; /* VLs 0-7 */
2021	u32 ctxt;
2022	struct hfi1_pportdata *ppd = dd->pport;
2023
2024	dd->vld[15].sc = sc_alloc(dd, SC_VL15,
2025				  dd->rcd[0]->rcvhdrqentsize, dd->node);
2026	if (!dd->vld[15].sc)
2027		return -ENOMEM;
2028
2029	hfi1_init_ctxt(dd->vld[15].sc);
2030	dd->vld[15].mtu = enum_to_mtu(OPA_MTU_2048);
2031
2032	dd->kernel_send_context = kcalloc_node(dd->num_send_contexts,
2033					       sizeof(struct send_context *),
2034					       GFP_KERNEL, dd->node);
2035	if (!dd->kernel_send_context)
2036		goto freesc15;
2037
2038	dd->kernel_send_context[0] = dd->vld[15].sc;
2039
2040	for (i = 0; i < num_vls; i++) {
2041		/*
2042		 * Since this function does not deal with a specific
2043		 * receive context but we need the RcvHdrQ entry size,
2044		 * use the size from rcd[0]. It is guaranteed to be
2045		 * valid at this point and will remain the same for all
2046		 * receive contexts.
2047		 */
2048		dd->vld[i].sc = sc_alloc(dd, SC_KERNEL,
2049					 dd->rcd[0]->rcvhdrqentsize, dd->node);
2050		if (!dd->vld[i].sc)
2051			goto nomem;
2052		dd->kernel_send_context[i + 1] = dd->vld[i].sc;
2053		hfi1_init_ctxt(dd->vld[i].sc);
2054		/* non VL15 start with the max MTU */
2055		dd->vld[i].mtu = hfi1_max_mtu;
2056	}
2057	for (i = num_vls; i < INIT_SC_PER_VL * num_vls; i++) {
2058		dd->kernel_send_context[i + 1] =
2059		sc_alloc(dd, SC_KERNEL, dd->rcd[0]->rcvhdrqentsize, dd->node);
2060		if (!dd->kernel_send_context[i + 1])
2061			goto nomem;
2062		hfi1_init_ctxt(dd->kernel_send_context[i + 1]);
2063	}
2064
2065	sc_enable(dd->vld[15].sc);
2066	ctxt = dd->vld[15].sc->hw_context;
2067	mask = all_vl_mask & ~(1LL << 15);
2068	write_kctxt_csr(dd, ctxt, SC(CHECK_VL), mask);
2069	dd_dev_info(dd,
2070		    "Using send context %u(%u) for VL15\n",
2071		    dd->vld[15].sc->sw_index, ctxt);
2072
2073	for (i = 0; i < num_vls; i++) {
2074		sc_enable(dd->vld[i].sc);
2075		ctxt = dd->vld[i].sc->hw_context;
2076		mask = all_vl_mask & ~(data_vls_mask);
2077		write_kctxt_csr(dd, ctxt, SC(CHECK_VL), mask);
2078	}
2079	for (i = num_vls; i < INIT_SC_PER_VL * num_vls; i++) {
2080		sc_enable(dd->kernel_send_context[i + 1]);
2081		ctxt = dd->kernel_send_context[i + 1]->hw_context;
2082		mask = all_vl_mask & ~(data_vls_mask);
2083		write_kctxt_csr(dd, ctxt, SC(CHECK_VL), mask);
2084	}
2085
2086	if (pio_map_init(dd, ppd->port - 1, num_vls, NULL))
2087		goto nomem;
2088	return 0;
2089
2090nomem:
2091	for (i = 0; i < num_vls; i++) {
2092		sc_free(dd->vld[i].sc);
2093		dd->vld[i].sc = NULL;
2094	}
2095
2096	for (i = num_vls; i < INIT_SC_PER_VL * num_vls; i++)
2097		sc_free(dd->kernel_send_context[i + 1]);
2098
2099	kfree(dd->kernel_send_context);
2100	dd->kernel_send_context = NULL;
2101
2102freesc15:
2103	sc_free(dd->vld[15].sc);
2104	return -ENOMEM;
2105}
2106
2107int init_credit_return(struct hfi1_devdata *dd)
2108{
2109	int ret;
2110	int i;
2111
2112	dd->cr_base = kcalloc(
2113		node_affinity.num_possible_nodes,
2114		sizeof(struct credit_return_base),
2115		GFP_KERNEL);
2116	if (!dd->cr_base) {
2117		ret = -ENOMEM;
2118		goto done;
2119	}
2120	for_each_node_with_cpus(i) {
2121		int bytes = TXE_NUM_CONTEXTS * sizeof(struct credit_return);
2122
2123		set_dev_node(&dd->pcidev->dev, i);
2124		dd->cr_base[i].va = dma_alloc_coherent(&dd->pcidev->dev,
2125						       bytes,
2126						       &dd->cr_base[i].dma,
2127						       GFP_KERNEL);
2128		if (!dd->cr_base[i].va) {
2129			set_dev_node(&dd->pcidev->dev, dd->node);
2130			dd_dev_err(dd,
2131				   "Unable to allocate credit return DMA range for NUMA %d\n",
2132				   i);
2133			ret = -ENOMEM;
2134			goto done;
2135		}
2136	}
2137	set_dev_node(&dd->pcidev->dev, dd->node);
2138
2139	ret = 0;
2140done:
2141	return ret;
2142}
2143
2144void free_credit_return(struct hfi1_devdata *dd)
2145{
2146	int i;
2147
2148	if (!dd->cr_base)
2149		return;
2150	for (i = 0; i < node_affinity.num_possible_nodes; i++) {
2151		if (dd->cr_base[i].va) {
2152			dma_free_coherent(&dd->pcidev->dev,
2153					  TXE_NUM_CONTEXTS *
2154					  sizeof(struct credit_return),
2155					  dd->cr_base[i].va,
2156					  dd->cr_base[i].dma);
2157		}
2158	}
2159	kfree(dd->cr_base);
2160	dd->cr_base = NULL;
2161}
2162
2163void seqfile_dump_sci(struct seq_file *s, u32 i,
2164		      struct send_context_info *sci)
2165{
2166	struct send_context *sc = sci->sc;
2167	u64 reg;
2168
2169	seq_printf(s, "SCI %u: type %u base %u credits %u\n",
2170		   i, sci->type, sci->base, sci->credits);
2171	seq_printf(s, "  flags 0x%x sw_inx %u hw_ctxt %u grp %u\n",
2172		   sc->flags,  sc->sw_index, sc->hw_context, sc->group);
2173	seq_printf(s, "  sr_size %u credits %u sr_head %u sr_tail %u\n",
2174		   sc->sr_size, sc->credits, sc->sr_head, sc->sr_tail);
2175	seq_printf(s, "  fill %lu free %lu fill_wrap %u alloc_free %lu\n",
2176		   sc->fill, sc->free, sc->fill_wrap, sc->alloc_free);
2177	seq_printf(s, "  credit_intr_count %u credit_ctrl 0x%llx\n",
2178		   sc->credit_intr_count, sc->credit_ctrl);
2179	reg = read_kctxt_csr(sc->dd, sc->hw_context, SC(CREDIT_STATUS));
2180	seq_printf(s, "  *hw_free %llu CurrentFree %llu LastReturned %llu\n",
2181		   (le64_to_cpu(*sc->hw_free) & CR_COUNTER_SMASK) >>
2182		    CR_COUNTER_SHIFT,
2183		   (reg >> SC(CREDIT_STATUS_CURRENT_FREE_COUNTER_SHIFT)) &
2184		    SC(CREDIT_STATUS_CURRENT_FREE_COUNTER_MASK),
2185		   reg & SC(CREDIT_STATUS_LAST_RETURNED_COUNTER_SMASK));
2186}
2187