1// SPDX-License-Identifier: GPL-2.0
2
3/* Copyright (c) 2012-2018, The Linux Foundation. All rights reserved.
4 * Copyright (C) 2019-2020 Linaro Ltd.
5 */
6
7#include <linux/types.h>
8#include <linux/bits.h>
9#include <linux/bitfield.h>
10#include <linux/refcount.h>
11#include <linux/scatterlist.h>
12#include <linux/dma-direction.h>
13
14#include "gsi.h"
15#include "gsi_private.h"
16#include "gsi_trans.h"
17#include "ipa_gsi.h"
18#include "ipa_data.h"
19#include "ipa_cmd.h"
20
21/**
22 * DOC: GSI Transactions
23 *
24 * A GSI transaction abstracts the behavior of a GSI channel by representing
25 * everything about a related group of IPA commands in a single structure.
26 * (A "command" in this sense is either a data transfer or an IPA immediate
27 * command.)  Most details of interaction with the GSI hardware are managed
28 * by the GSI transaction core, allowing users to simply describe commands
29 * to be performed.  When a transaction has completed a callback function
30 * (dependent on the type of endpoint associated with the channel) allows
31 * cleanup of resources associated with the transaction.
32 *
33 * To perform a command (or set of them), a user of the GSI transaction
34 * interface allocates a transaction, indicating the number of TREs required
35 * (one per command).  If sufficient TREs are available, they are reserved
36 * for use in the transaction and the allocation succeeds.  This way
37 * exhaustion of the available TREs in a channel ring is detected
38 * as early as possible.  All resources required to complete a transaction
39 * are allocated at transaction allocation time.
40 *
41 * Commands performed as part of a transaction are represented in an array
42 * of Linux scatterlist structures.  This array is allocated with the
43 * transaction, and its entries are initialized using standard scatterlist
44 * functions (such as sg_set_buf() or skb_to_sgvec()).
45 *
46 * Once a transaction's scatterlist structures have been initialized, the
47 * transaction is committed.  The caller is responsible for mapping buffers
48 * for DMA if necessary, and this should be done *before* allocating
49 * the transaction.  Between a successful allocation and commit of a
50 * transaction no errors should occur.
51 *
52 * Committing transfers ownership of the entire transaction to the GSI
53 * transaction core.  The GSI transaction code formats the content of
54 * the scatterlist array into the channel ring buffer and informs the
55 * hardware that new TREs are available to process.
56 *
57 * The last TRE in each transaction is marked to interrupt the AP when the
58 * GSI hardware has completed it.  Because transfers described by TREs are
59 * performed strictly in order, signaling the completion of just the last
60 * TRE in the transaction is sufficient to indicate the full transaction
61 * is complete.
62 *
63 * When a transaction is complete, ipa_gsi_trans_complete() is called by the
64 * GSI code into the IPA layer, allowing it to perform any final cleanup
65 * required before the transaction is freed.
66 */
67
68/* Hardware values representing a transfer element type */
69enum gsi_tre_type {
70	GSI_RE_XFER	= 0x2,
71	GSI_RE_IMMD_CMD	= 0x3,
72};
73
74/* An entry in a channel ring */
75struct gsi_tre {
76	__le64 addr;		/* DMA address */
77	__le16 len_opcode;	/* length in bytes or enum IPA_CMD_* */
78	__le16 reserved;
79	__le32 flags;		/* TRE_FLAGS_* */
80};
81
82/* gsi_tre->flags mask values (in CPU byte order) */
83#define TRE_FLAGS_CHAIN_FMASK	GENMASK(0, 0)
84#define TRE_FLAGS_IEOT_FMASK	GENMASK(9, 9)
85#define TRE_FLAGS_BEI_FMASK	GENMASK(10, 10)
86#define TRE_FLAGS_TYPE_FMASK	GENMASK(23, 16)
87
88int gsi_trans_pool_init(struct gsi_trans_pool *pool, size_t size, u32 count,
89			u32 max_alloc)
90{
91	void *virt;
92
93#ifdef IPA_VALIDATE
94	if (!size || size % 8)
95		return -EINVAL;
96	if (count < max_alloc)
97		return -EINVAL;
98	if (!max_alloc)
99		return -EINVAL;
100#endif /* IPA_VALIDATE */
101
102	/* By allocating a few extra entries in our pool (one less
103	 * than the maximum number that will be requested in a
104	 * single allocation), we can always satisfy requests without
105	 * ever worrying about straddling the end of the pool array.
106	 * If there aren't enough entries starting at the free index,
107	 * we just allocate free entries from the beginning of the pool.
108	 */
109	virt = kcalloc(count + max_alloc - 1, size, GFP_KERNEL);
110	if (!virt)
111		return -ENOMEM;
112
113	pool->base = virt;
114	/* If the allocator gave us any extra memory, use it */
115	pool->count = ksize(pool->base) / size;
116	pool->free = 0;
117	pool->max_alloc = max_alloc;
118	pool->size = size;
119	pool->addr = 0;		/* Only used for DMA pools */
120
121	return 0;
122}
123
124void gsi_trans_pool_exit(struct gsi_trans_pool *pool)
125{
126	kfree(pool->base);
127	memset(pool, 0, sizeof(*pool));
128}
129
130/* Allocate the requested number of (zeroed) entries from the pool */
131/* Home-grown DMA pool.  This way we can preallocate and use the tre_count
132 * to guarantee allocations will succeed.  Even though we specify max_alloc
133 * (and it can be more than one), we only allow allocation of a single
134 * element from a DMA pool.
135 */
136int gsi_trans_pool_init_dma(struct device *dev, struct gsi_trans_pool *pool,
137			    size_t size, u32 count, u32 max_alloc)
138{
139	size_t total_size;
140	dma_addr_t addr;
141	void *virt;
142
143#ifdef IPA_VALIDATE
144	if (!size || size % 8)
145		return -EINVAL;
146	if (count < max_alloc)
147		return -EINVAL;
148	if (!max_alloc)
149		return -EINVAL;
150#endif /* IPA_VALIDATE */
151
152	/* Don't let allocations cross a power-of-two boundary */
153	size = __roundup_pow_of_two(size);
154	total_size = (count + max_alloc - 1) * size;
155
156	/* The allocator will give us a power-of-2 number of pages
157	 * sufficient to satisfy our request.  Round up our requested
158	 * size to avoid any unused space in the allocation.  This way
159	 * gsi_trans_pool_exit_dma() can assume the total allocated
160	 * size is exactly (count * size).
161	 */
162	total_size = PAGE_SIZE << get_order(total_size);
163
164	virt = dma_alloc_coherent(dev, total_size, &addr, GFP_KERNEL);
165	if (!virt)
166		return -ENOMEM;
167
168	pool->base = virt;
169	pool->count = total_size / size;
170	pool->free = 0;
171	pool->size = size;
172	pool->max_alloc = max_alloc;
173	pool->addr = addr;
174
175	return 0;
176}
177
178void gsi_trans_pool_exit_dma(struct device *dev, struct gsi_trans_pool *pool)
179{
180	size_t total_size = pool->count * pool->size;
181
182	dma_free_coherent(dev, total_size, pool->base, pool->addr);
183	memset(pool, 0, sizeof(*pool));
184}
185
186/* Return the byte offset of the next free entry in the pool */
187static u32 gsi_trans_pool_alloc_common(struct gsi_trans_pool *pool, u32 count)
188{
189	u32 offset;
190
191	/* assert(count > 0); */
192	/* assert(count <= pool->max_alloc); */
193
194	/* Allocate from beginning if wrap would occur */
195	if (count > pool->count - pool->free)
196		pool->free = 0;
197
198	offset = pool->free * pool->size;
199	pool->free += count;
200	memset(pool->base + offset, 0, count * pool->size);
201
202	return offset;
203}
204
205/* Allocate a contiguous block of zeroed entries from a pool */
206void *gsi_trans_pool_alloc(struct gsi_trans_pool *pool, u32 count)
207{
208	return pool->base + gsi_trans_pool_alloc_common(pool, count);
209}
210
211/* Allocate a single zeroed entry from a DMA pool */
212void *gsi_trans_pool_alloc_dma(struct gsi_trans_pool *pool, dma_addr_t *addr)
213{
214	u32 offset = gsi_trans_pool_alloc_common(pool, 1);
215
216	*addr = pool->addr + offset;
217
218	return pool->base + offset;
219}
220
221/* Return the pool element that immediately follows the one given.
222 * This only works done if elements are allocated one at a time.
223 */
224void *gsi_trans_pool_next(struct gsi_trans_pool *pool, void *element)
225{
226	void *end = pool->base + pool->count * pool->size;
227
228	/* assert(element >= pool->base); */
229	/* assert(element < end); */
230	/* assert(pool->max_alloc == 1); */
231	element += pool->size;
232
233	return element < end ? element : pool->base;
234}
235
236/* Map a given ring entry index to the transaction associated with it */
237static void gsi_channel_trans_map(struct gsi_channel *channel, u32 index,
238				  struct gsi_trans *trans)
239{
240	/* Note: index *must* be used modulo the ring count here */
241	channel->trans_info.map[index % channel->tre_ring.count] = trans;
242}
243
244/* Return the transaction mapped to a given ring entry */
245struct gsi_trans *
246gsi_channel_trans_mapped(struct gsi_channel *channel, u32 index)
247{
248	/* Note: index *must* be used modulo the ring count here */
249	return channel->trans_info.map[index % channel->tre_ring.count];
250}
251
252/* Return the oldest completed transaction for a channel (or null) */
253struct gsi_trans *gsi_channel_trans_complete(struct gsi_channel *channel)
254{
255	return list_first_entry_or_null(&channel->trans_info.complete,
256					struct gsi_trans, links);
257}
258
259/* Move a transaction from the allocated list to the pending list */
260static void gsi_trans_move_pending(struct gsi_trans *trans)
261{
262	struct gsi_channel *channel = &trans->gsi->channel[trans->channel_id];
263	struct gsi_trans_info *trans_info = &channel->trans_info;
264
265	spin_lock_bh(&trans_info->spinlock);
266
267	list_move_tail(&trans->links, &trans_info->pending);
268
269	spin_unlock_bh(&trans_info->spinlock);
270}
271
272/* Move a transaction and all of its predecessors from the pending list
273 * to the completed list.
274 */
275void gsi_trans_move_complete(struct gsi_trans *trans)
276{
277	struct gsi_channel *channel = &trans->gsi->channel[trans->channel_id];
278	struct gsi_trans_info *trans_info = &channel->trans_info;
279	struct list_head list;
280
281	spin_lock_bh(&trans_info->spinlock);
282
283	/* Move this transaction and all predecessors to completed list */
284	list_cut_position(&list, &trans_info->pending, &trans->links);
285	list_splice_tail(&list, &trans_info->complete);
286
287	spin_unlock_bh(&trans_info->spinlock);
288}
289
290/* Move a transaction from the completed list to the polled list */
291void gsi_trans_move_polled(struct gsi_trans *trans)
292{
293	struct gsi_channel *channel = &trans->gsi->channel[trans->channel_id];
294	struct gsi_trans_info *trans_info = &channel->trans_info;
295
296	spin_lock_bh(&trans_info->spinlock);
297
298	list_move_tail(&trans->links, &trans_info->polled);
299
300	spin_unlock_bh(&trans_info->spinlock);
301}
302
303/* Reserve some number of TREs on a channel.  Returns true if successful */
304static bool
305gsi_trans_tre_reserve(struct gsi_trans_info *trans_info, u32 tre_count)
306{
307	int avail = atomic_read(&trans_info->tre_avail);
308	int new;
309
310	do {
311		new = avail - (int)tre_count;
312		if (unlikely(new < 0))
313			return false;
314	} while (!atomic_try_cmpxchg(&trans_info->tre_avail, &avail, new));
315
316	return true;
317}
318
319/* Release previously-reserved TRE entries to a channel */
320static void
321gsi_trans_tre_release(struct gsi_trans_info *trans_info, u32 tre_count)
322{
323	atomic_add(tre_count, &trans_info->tre_avail);
324}
325
326/* Allocate a GSI transaction on a channel */
327struct gsi_trans *gsi_channel_trans_alloc(struct gsi *gsi, u32 channel_id,
328					  u32 tre_count,
329					  enum dma_data_direction direction)
330{
331	struct gsi_channel *channel = &gsi->channel[channel_id];
332	struct gsi_trans_info *trans_info;
333	struct gsi_trans *trans;
334
335	/* assert(tre_count <= gsi_channel_trans_tre_max(gsi, channel_id)); */
336
337	trans_info = &channel->trans_info;
338
339	/* We reserve the TREs now, but consume them at commit time.
340	 * If there aren't enough available, we're done.
341	 */
342	if (!gsi_trans_tre_reserve(trans_info, tre_count))
343		return NULL;
344
345	/* Allocate and initialize non-zero fields in the the transaction */
346	trans = gsi_trans_pool_alloc(&trans_info->pool, 1);
347	trans->gsi = gsi;
348	trans->channel_id = channel_id;
349	trans->tre_count = tre_count;
350	init_completion(&trans->completion);
351
352	/* Allocate the scatterlist and (if requested) info entries. */
353	trans->sgl = gsi_trans_pool_alloc(&trans_info->sg_pool, tre_count);
354	sg_init_marker(trans->sgl, tre_count);
355
356	trans->direction = direction;
357
358	spin_lock_bh(&trans_info->spinlock);
359
360	list_add_tail(&trans->links, &trans_info->alloc);
361
362	spin_unlock_bh(&trans_info->spinlock);
363
364	refcount_set(&trans->refcount, 1);
365
366	return trans;
367}
368
369/* Free a previously-allocated transaction */
370void gsi_trans_free(struct gsi_trans *trans)
371{
372	refcount_t *refcount = &trans->refcount;
373	struct gsi_trans_info *trans_info;
374	bool last;
375
376	/* We must hold the lock to release the last reference */
377	if (refcount_dec_not_one(refcount))
378		return;
379
380	trans_info = &trans->gsi->channel[trans->channel_id].trans_info;
381
382	spin_lock_bh(&trans_info->spinlock);
383
384	/* Reference might have been added before we got the lock */
385	last = refcount_dec_and_test(refcount);
386	if (last)
387		list_del(&trans->links);
388
389	spin_unlock_bh(&trans_info->spinlock);
390
391	if (!last)
392		return;
393
394	ipa_gsi_trans_release(trans);
395
396	/* Releasing the reserved TREs implicitly frees the sgl[] and
397	 * (if present) info[] arrays, plus the transaction itself.
398	 */
399	gsi_trans_tre_release(trans_info, trans->tre_count);
400}
401
402/* Add an immediate command to a transaction */
403void gsi_trans_cmd_add(struct gsi_trans *trans, void *buf, u32 size,
404		       dma_addr_t addr, enum dma_data_direction direction,
405		       enum ipa_cmd_opcode opcode)
406{
407	struct ipa_cmd_info *info;
408	u32 which = trans->used++;
409	struct scatterlist *sg;
410
411	/* assert(which < trans->tre_count); */
412
413	/* Commands are quite different from data transfer requests.
414	 * Their payloads come from a pool whose memory is allocated
415	 * using dma_alloc_coherent().  We therefore do *not* map them
416	 * for DMA (unlike what we do for pages and skbs).
417	 *
418	 * When a transaction completes, the SGL is normally unmapped.
419	 * A command transaction has direction DMA_NONE, which tells
420	 * gsi_trans_complete() to skip the unmapping step.
421	 *
422	 * The only things we use directly in a command scatter/gather
423	 * entry are the DMA address and length.  We still need the SG
424	 * table flags to be maintained though, so assign a NULL page
425	 * pointer for that purpose.
426	 */
427	sg = &trans->sgl[which];
428	sg_assign_page(sg, NULL);
429	sg_dma_address(sg) = addr;
430	sg_dma_len(sg) = size;
431
432	info = &trans->info[which];
433	info->opcode = opcode;
434	info->direction = direction;
435}
436
437/* Add a page transfer to a transaction.  It will fill the only TRE. */
438int gsi_trans_page_add(struct gsi_trans *trans, struct page *page, u32 size,
439		       u32 offset)
440{
441	struct scatterlist *sg = &trans->sgl[0];
442	int ret;
443
444	/* assert(trans->tre_count == 1); */
445	/* assert(!trans->used); */
446
447	sg_set_page(sg, page, size, offset);
448	ret = dma_map_sg(trans->gsi->dev, sg, 1, trans->direction);
449	if (!ret)
450		return -ENOMEM;
451
452	trans->used++;	/* Transaction now owns the (DMA mapped) page */
453
454	return 0;
455}
456
457/* Add an SKB transfer to a transaction.  No other TREs will be used. */
458int gsi_trans_skb_add(struct gsi_trans *trans, struct sk_buff *skb)
459{
460	struct scatterlist *sg = &trans->sgl[0];
461	u32 used;
462	int ret;
463
464	/* assert(trans->tre_count == 1); */
465	/* assert(!trans->used); */
466
467	/* skb->len will not be 0 (checked early) */
468	ret = skb_to_sgvec(skb, sg, 0, skb->len);
469	if (ret < 0)
470		return ret;
471	used = ret;
472
473	ret = dma_map_sg(trans->gsi->dev, sg, used, trans->direction);
474	if (!ret)
475		return -ENOMEM;
476
477	trans->used += used;	/* Transaction now owns the (DMA mapped) skb */
478
479	return 0;
480}
481
482/* Compute the length/opcode value to use for a TRE */
483static __le16 gsi_tre_len_opcode(enum ipa_cmd_opcode opcode, u32 len)
484{
485	return opcode == IPA_CMD_NONE ? cpu_to_le16((u16)len)
486				      : cpu_to_le16((u16)opcode);
487}
488
489/* Compute the flags value to use for a given TRE */
490static __le32 gsi_tre_flags(bool last_tre, bool bei, enum ipa_cmd_opcode opcode)
491{
492	enum gsi_tre_type tre_type;
493	u32 tre_flags;
494
495	tre_type = opcode == IPA_CMD_NONE ? GSI_RE_XFER : GSI_RE_IMMD_CMD;
496	tre_flags = u32_encode_bits(tre_type, TRE_FLAGS_TYPE_FMASK);
497
498	/* Last TRE contains interrupt flags */
499	if (last_tre) {
500		/* All transactions end in a transfer completion interrupt */
501		tre_flags |= TRE_FLAGS_IEOT_FMASK;
502		/* Don't interrupt when outbound commands are acknowledged */
503		if (bei)
504			tre_flags |= TRE_FLAGS_BEI_FMASK;
505	} else {	/* All others indicate there's more to come */
506		tre_flags |= TRE_FLAGS_CHAIN_FMASK;
507	}
508
509	return cpu_to_le32(tre_flags);
510}
511
512static void gsi_trans_tre_fill(struct gsi_tre *dest_tre, dma_addr_t addr,
513			       u32 len, bool last_tre, bool bei,
514			       enum ipa_cmd_opcode opcode)
515{
516	struct gsi_tre tre;
517
518	tre.addr = cpu_to_le64(addr);
519	tre.len_opcode = gsi_tre_len_opcode(opcode, len);
520	tre.reserved = 0;
521	tre.flags = gsi_tre_flags(last_tre, bei, opcode);
522
523	/* ARM64 can write 16 bytes as a unit with a single instruction.
524	 * Doing the assignment this way is an attempt to make that happen.
525	 */
526	*dest_tre = tre;
527}
528
529/**
530 * __gsi_trans_commit() - Common GSI transaction commit code
531 * @trans:	Transaction to commit
532 * @ring_db:	Whether to tell the hardware about these queued transfers
533 *
534 * Formats channel ring TRE entries based on the content of the scatterlist.
535 * Maps a transaction pointer to the last ring entry used for the transaction,
536 * so it can be recovered when it completes.  Moves the transaction to the
537 * pending list.  Finally, updates the channel ring pointer and optionally
538 * rings the doorbell.
539 */
540static void __gsi_trans_commit(struct gsi_trans *trans, bool ring_db)
541{
542	struct gsi_channel *channel = &trans->gsi->channel[trans->channel_id];
543	struct gsi_ring *ring = &channel->tre_ring;
544	enum ipa_cmd_opcode opcode = IPA_CMD_NONE;
545	bool bei = channel->toward_ipa;
546	struct ipa_cmd_info *info;
547	struct gsi_tre *dest_tre;
548	struct scatterlist *sg;
549	u32 byte_count = 0;
550	u32 avail;
551	u32 i;
552
553	/* assert(trans->used > 0); */
554
555	/* Consume the entries.  If we cross the end of the ring while
556	 * filling them we'll switch to the beginning to finish.
557	 * If there is no info array we're doing a simple data
558	 * transfer request, whose opcode is IPA_CMD_NONE.
559	 */
560	info = trans->info ? &trans->info[0] : NULL;
561	avail = ring->count - ring->index % ring->count;
562	dest_tre = gsi_ring_virt(ring, ring->index);
563	for_each_sg(trans->sgl, sg, trans->used, i) {
564		bool last_tre = i == trans->used - 1;
565		dma_addr_t addr = sg_dma_address(sg);
566		u32 len = sg_dma_len(sg);
567
568		byte_count += len;
569		if (!avail--)
570			dest_tre = gsi_ring_virt(ring, 0);
571		if (info)
572			opcode = info++->opcode;
573
574		gsi_trans_tre_fill(dest_tre, addr, len, last_tre, bei, opcode);
575		dest_tre++;
576	}
577	ring->index += trans->used;
578
579	if (channel->toward_ipa) {
580		/* We record TX bytes when they are sent */
581		trans->len = byte_count;
582		trans->trans_count = channel->trans_count;
583		trans->byte_count = channel->byte_count;
584		channel->trans_count++;
585		channel->byte_count += byte_count;
586	}
587
588	/* Associate the last TRE with the transaction */
589	gsi_channel_trans_map(channel, ring->index - 1, trans);
590
591	gsi_trans_move_pending(trans);
592
593	/* Ring doorbell if requested, or if all TREs are allocated */
594	if (ring_db || !atomic_read(&channel->trans_info.tre_avail)) {
595		/* Report what we're handing off to hardware for TX channels */
596		if (channel->toward_ipa)
597			gsi_channel_tx_queued(channel);
598		gsi_channel_doorbell(channel);
599	}
600}
601
602/* Commit a GSI transaction */
603void gsi_trans_commit(struct gsi_trans *trans, bool ring_db)
604{
605	if (trans->used)
606		__gsi_trans_commit(trans, ring_db);
607	else
608		gsi_trans_free(trans);
609}
610
611/* Commit a GSI transaction and wait for it to complete */
612void gsi_trans_commit_wait(struct gsi_trans *trans)
613{
614	if (!trans->used)
615		goto out_trans_free;
616
617	refcount_inc(&trans->refcount);
618
619	__gsi_trans_commit(trans, true);
620
621	wait_for_completion(&trans->completion);
622
623out_trans_free:
624	gsi_trans_free(trans);
625}
626
627/* Commit a GSI transaction and wait for it to complete, with timeout */
628int gsi_trans_commit_wait_timeout(struct gsi_trans *trans,
629				  unsigned long timeout)
630{
631	unsigned long timeout_jiffies = msecs_to_jiffies(timeout);
632	unsigned long remaining = 1;	/* In case of empty transaction */
633
634	if (!trans->used)
635		goto out_trans_free;
636
637	refcount_inc(&trans->refcount);
638
639	__gsi_trans_commit(trans, true);
640
641	remaining = wait_for_completion_timeout(&trans->completion,
642						timeout_jiffies);
643out_trans_free:
644	gsi_trans_free(trans);
645
646	return remaining ? 0 : -ETIMEDOUT;
647}
648
649/* Process the completion of a transaction; called while polling */
650void gsi_trans_complete(struct gsi_trans *trans)
651{
652	/* If the entire SGL was mapped when added, unmap it now */
653	if (trans->direction != DMA_NONE)
654		dma_unmap_sg(trans->gsi->dev, trans->sgl, trans->used,
655			     trans->direction);
656
657	ipa_gsi_trans_complete(trans);
658
659	complete(&trans->completion);
660
661	gsi_trans_free(trans);
662}
663
664/* Cancel a channel's pending transactions */
665void gsi_channel_trans_cancel_pending(struct gsi_channel *channel)
666{
667	struct gsi_trans_info *trans_info = &channel->trans_info;
668	struct gsi_trans *trans;
669	bool cancelled;
670
671	/* channel->gsi->mutex is held by caller */
672	spin_lock_bh(&trans_info->spinlock);
673
674	cancelled = !list_empty(&trans_info->pending);
675	list_for_each_entry(trans, &trans_info->pending, links)
676		trans->cancelled = true;
677
678	list_splice_tail_init(&trans_info->pending, &trans_info->complete);
679
680	spin_unlock_bh(&trans_info->spinlock);
681
682	/* Schedule NAPI polling to complete the cancelled transactions */
683	if (cancelled)
684		napi_schedule(&channel->napi);
685}
686
687/* Issue a command to read a single byte from a channel */
688int gsi_trans_read_byte(struct gsi *gsi, u32 channel_id, dma_addr_t addr)
689{
690	struct gsi_channel *channel = &gsi->channel[channel_id];
691	struct gsi_ring *ring = &channel->tre_ring;
692	struct gsi_trans_info *trans_info;
693	struct gsi_tre *dest_tre;
694
695	trans_info = &channel->trans_info;
696
697	/* First reserve the TRE, if possible */
698	if (!gsi_trans_tre_reserve(trans_info, 1))
699		return -EBUSY;
700
701	/* Now fill the the reserved TRE and tell the hardware */
702
703	dest_tre = gsi_ring_virt(ring, ring->index);
704	gsi_trans_tre_fill(dest_tre, addr, 1, true, false, IPA_CMD_NONE);
705
706	ring->index++;
707	gsi_channel_doorbell(channel);
708
709	return 0;
710}
711
712/* Mark a gsi_trans_read_byte() request done */
713void gsi_trans_read_byte_done(struct gsi *gsi, u32 channel_id)
714{
715	struct gsi_channel *channel = &gsi->channel[channel_id];
716
717	gsi_trans_tre_release(&channel->trans_info, 1);
718}
719
720/* Initialize a channel's GSI transaction info */
721int gsi_channel_trans_init(struct gsi *gsi, u32 channel_id)
722{
723	struct gsi_channel *channel = &gsi->channel[channel_id];
724	struct gsi_trans_info *trans_info;
725	u32 tre_max;
726	int ret;
727
728	/* Ensure the size of a channel element is what's expected */
729	BUILD_BUG_ON(sizeof(struct gsi_tre) != GSI_RING_ELEMENT_SIZE);
730
731	/* The map array is used to determine what transaction is associated
732	 * with a TRE that the hardware reports has completed.  We need one
733	 * map entry per TRE.
734	 */
735	trans_info = &channel->trans_info;
736	trans_info->map = kcalloc(channel->tre_count, sizeof(*trans_info->map),
737				  GFP_KERNEL);
738	if (!trans_info->map)
739		return -ENOMEM;
740
741	/* We can't use more TREs than there are available in the ring.
742	 * This limits the number of transactions that can be oustanding.
743	 * Worst case is one TRE per transaction (but we actually limit
744	 * it to something a little less than that).  We allocate resources
745	 * for transactions (including transaction structures) based on
746	 * this maximum number.
747	 */
748	tre_max = gsi_channel_tre_max(channel->gsi, channel_id);
749
750	/* Transactions are allocated one at a time. */
751	ret = gsi_trans_pool_init(&trans_info->pool, sizeof(struct gsi_trans),
752				  tre_max, 1);
753	if (ret)
754		goto err_kfree;
755
756	/* A transaction uses a scatterlist array to represent the data
757	 * transfers implemented by the transaction.  Each scatterlist
758	 * element is used to fill a single TRE when the transaction is
759	 * committed.  So we need as many scatterlist elements as the
760	 * maximum number of TREs that can be outstanding.
761	 *
762	 * All TREs in a transaction must fit within the channel's TLV FIFO.
763	 * A transaction on a channel can allocate as many TREs as that but
764	 * no more.
765	 */
766	ret = gsi_trans_pool_init(&trans_info->sg_pool,
767				  sizeof(struct scatterlist),
768				  tre_max, channel->tlv_count);
769	if (ret)
770		goto err_trans_pool_exit;
771
772	/* Finally, the tre_avail field is what ultimately limits the number
773	 * of outstanding transactions and their resources.  A transaction
774	 * allocation succeeds only if the TREs available are sufficient for
775	 * what the transaction might need.  Transaction resource pools are
776	 * sized based on the maximum number of outstanding TREs, so there
777	 * will always be resources available if there are TREs available.
778	 */
779	atomic_set(&trans_info->tre_avail, tre_max);
780
781	spin_lock_init(&trans_info->spinlock);
782	INIT_LIST_HEAD(&trans_info->alloc);
783	INIT_LIST_HEAD(&trans_info->pending);
784	INIT_LIST_HEAD(&trans_info->complete);
785	INIT_LIST_HEAD(&trans_info->polled);
786
787	return 0;
788
789err_trans_pool_exit:
790	gsi_trans_pool_exit(&trans_info->pool);
791err_kfree:
792	kfree(trans_info->map);
793
794	dev_err(gsi->dev, "error %d initializing channel %u transactions\n",
795		ret, channel_id);
796
797	return ret;
798}
799
800/* Inverse of gsi_channel_trans_init() */
801void gsi_channel_trans_exit(struct gsi_channel *channel)
802{
803	struct gsi_trans_info *trans_info = &channel->trans_info;
804
805	gsi_trans_pool_exit(&trans_info->sg_pool);
806	gsi_trans_pool_exit(&trans_info->pool);
807	kfree(trans_info->map);
808}
809