1/******************************************************************************
2 *
3 * This file is provided under a dual BSD/GPLv2 license.  When using or
4 * redistributing this file, you may do so under either license.
5 *
6 * GPL LICENSE SUMMARY
7 *
8 * Copyright(c) 2020 Intel Corporation
9 *
10 * This program is free software; you can redistribute it and/or modify
11 * it under the terms of version 2 of the GNU General Public License as
12 * published by the Free Software Foundation.
13 *
14 * This program is distributed in the hope that it will be useful, but
15 * WITHOUT ANY WARRANTY; without even the implied warranty of
16 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
17 * General Public License for more details.
18 *
19 * BSD LICENSE
20 *
21 * Copyright(c) 2020 Intel Corporation
22 * All rights reserved.
23 *
24 * Redistribution and use in source and binary forms, with or without
25 * modification, are permitted provided that the following conditions
26 * are met:
27 *
28 *  * Redistributions of source code must retain the above copyright
29 *    notice, this list of conditions and the following disclaimer.
30 *  * Redistributions in binary form must reproduce the above copyright
31 *    notice, this list of conditions and the following disclaimer in
32 *    the documentation and/or other materials provided with the
33 *    distribution.
34 *  * Neither the name Intel Corporation nor the names of its
35 *    contributors may be used to endorse or promote products derived
36 *    from this software without specific prior written permission.
37 *
38 * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
39 * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
40 * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
41 * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
42 * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
43 * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
44 * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
45 * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
46 * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
47 * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
48 * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
49 *
50 *****************************************************************************/
51#include <net/tso.h>
52#include <linux/tcp.h>
53
54#include "iwl-debug.h"
55#include "iwl-io.h"
56#include "fw/api/tx.h"
57#include "queue/tx.h"
58#include "iwl-fh.h"
59#include "iwl-scd.h"
60#include <linux/dmapool.h>
61
62/*
63 * iwl_txq_gen2_tx_stop - Stop all Tx DMA channels
64 */
65void iwl_txq_gen2_tx_stop(struct iwl_trans *trans)
66{
67	int txq_id;
68
69	/*
70	 * This function can be called before the op_mode disabled the
71	 * queues. This happens when we have an rfkill interrupt.
72	 * Since we stop Tx altogether - mark the queues as stopped.
73	 */
74	memset(trans->txqs.queue_stopped, 0,
75	       sizeof(trans->txqs.queue_stopped));
76	memset(trans->txqs.queue_used, 0, sizeof(trans->txqs.queue_used));
77
78	/* Unmap DMA from host system and free skb's */
79	for (txq_id = 0; txq_id < ARRAY_SIZE(trans->txqs.txq); txq_id++) {
80		if (!trans->txqs.txq[txq_id])
81			continue;
82		iwl_txq_gen2_unmap(trans, txq_id);
83	}
84}
85
86/*
87 * iwl_txq_update_byte_tbl - Set up entry in Tx byte-count array
88 */
89static void iwl_pcie_gen2_update_byte_tbl(struct iwl_trans *trans,
90					  struct iwl_txq *txq, u16 byte_cnt,
91					  int num_tbs)
92{
93	int idx = iwl_txq_get_cmd_index(txq, txq->write_ptr);
94	u8 filled_tfd_size, num_fetch_chunks;
95	u16 len = byte_cnt;
96	__le16 bc_ent;
97
98	if (WARN(idx >= txq->n_window, "%d >= %d\n", idx, txq->n_window))
99		return;
100
101	filled_tfd_size = offsetof(struct iwl_tfh_tfd, tbs) +
102			  num_tbs * sizeof(struct iwl_tfh_tb);
103	/*
104	 * filled_tfd_size contains the number of filled bytes in the TFD.
105	 * Dividing it by 64 will give the number of chunks to fetch
106	 * to SRAM- 0 for one chunk, 1 for 2 and so on.
107	 * If, for example, TFD contains only 3 TBs then 32 bytes
108	 * of the TFD are used, and only one chunk of 64 bytes should
109	 * be fetched
110	 */
111	num_fetch_chunks = DIV_ROUND_UP(filled_tfd_size, 64) - 1;
112
113	if (trans->trans_cfg->device_family >= IWL_DEVICE_FAMILY_AX210) {
114		struct iwl_gen3_bc_tbl *scd_bc_tbl_gen3 = txq->bc_tbl.addr;
115
116		/* Starting from AX210, the HW expects bytes */
117		WARN_ON(trans->txqs.bc_table_dword);
118		WARN_ON(len > 0x3FFF);
119		bc_ent = cpu_to_le16(len | (num_fetch_chunks << 14));
120		scd_bc_tbl_gen3->tfd_offset[idx] = bc_ent;
121	} else {
122		struct iwlagn_scd_bc_tbl *scd_bc_tbl = txq->bc_tbl.addr;
123
124		/* Before AX210, the HW expects DW */
125		WARN_ON(!trans->txqs.bc_table_dword);
126		len = DIV_ROUND_UP(len, 4);
127		WARN_ON(len > 0xFFF);
128		bc_ent = cpu_to_le16(len | (num_fetch_chunks << 12));
129		scd_bc_tbl->tfd_offset[idx] = bc_ent;
130	}
131}
132
133/*
134 * iwl_txq_inc_wr_ptr - Send new write index to hardware
135 */
136void iwl_txq_inc_wr_ptr(struct iwl_trans *trans, struct iwl_txq *txq)
137{
138	lockdep_assert_held(&txq->lock);
139
140	IWL_DEBUG_TX(trans, "Q:%d WR: 0x%x\n", txq->id, txq->write_ptr);
141
142	/*
143	 * if not in power-save mode, uCode will never sleep when we're
144	 * trying to tx (during RFKILL, we're not trying to tx).
145	 */
146	iwl_write32(trans, HBUS_TARG_WRPTR, txq->write_ptr | (txq->id << 16));
147}
148
149static u8 iwl_txq_gen2_get_num_tbs(struct iwl_trans *trans,
150				   struct iwl_tfh_tfd *tfd)
151{
152	return le16_to_cpu(tfd->num_tbs) & 0x1f;
153}
154
155void iwl_txq_gen2_tfd_unmap(struct iwl_trans *trans, struct iwl_cmd_meta *meta,
156			    struct iwl_tfh_tfd *tfd)
157{
158	int i, num_tbs;
159
160	/* Sanity check on number of chunks */
161	num_tbs = iwl_txq_gen2_get_num_tbs(trans, tfd);
162
163	if (num_tbs > trans->txqs.tfd.max_tbs) {
164		IWL_ERR(trans, "Too many chunks: %i\n", num_tbs);
165		return;
166	}
167
168	/* first TB is never freed - it's the bidirectional DMA data */
169	for (i = 1; i < num_tbs; i++) {
170		if (meta->tbs & BIT(i))
171			dma_unmap_page(trans->dev,
172				       le64_to_cpu(tfd->tbs[i].addr),
173				       le16_to_cpu(tfd->tbs[i].tb_len),
174				       DMA_TO_DEVICE);
175		else
176			dma_unmap_single(trans->dev,
177					 le64_to_cpu(tfd->tbs[i].addr),
178					 le16_to_cpu(tfd->tbs[i].tb_len),
179					 DMA_TO_DEVICE);
180	}
181
182	tfd->num_tbs = 0;
183}
184
185void iwl_txq_gen2_free_tfd(struct iwl_trans *trans, struct iwl_txq *txq)
186{
187	/* rd_ptr is bounded by TFD_QUEUE_SIZE_MAX and
188	 * idx is bounded by n_window
189	 */
190	int idx = iwl_txq_get_cmd_index(txq, txq->read_ptr);
191
192	lockdep_assert_held(&txq->lock);
193
194	iwl_txq_gen2_tfd_unmap(trans, &txq->entries[idx].meta,
195			       iwl_txq_get_tfd(trans, txq, idx));
196
197	/* free SKB */
198	if (txq->entries) {
199		struct sk_buff *skb;
200
201		skb = txq->entries[idx].skb;
202
203		/* Can be called from irqs-disabled context
204		 * If skb is not NULL, it means that the whole queue is being
205		 * freed and that the queue is not empty - free the skb
206		 */
207		if (skb) {
208			iwl_op_mode_free_skb(trans->op_mode, skb);
209			txq->entries[idx].skb = NULL;
210		}
211	}
212}
213
214int iwl_txq_gen2_set_tb(struct iwl_trans *trans, struct iwl_tfh_tfd *tfd,
215			dma_addr_t addr, u16 len)
216{
217	int idx = iwl_txq_gen2_get_num_tbs(trans, tfd);
218	struct iwl_tfh_tb *tb;
219
220	/*
221	 * Only WARN here so we know about the issue, but we mess up our
222	 * unmap path because not every place currently checks for errors
223	 * returned from this function - it can only return an error if
224	 * there's no more space, and so when we know there is enough we
225	 * don't always check ...
226	 */
227	WARN(iwl_txq_crosses_4g_boundary(addr, len),
228	     "possible DMA problem with iova:0x%llx, len:%d\n",
229	     (unsigned long long)addr, len);
230
231	if (WARN_ON(idx >= IWL_TFH_NUM_TBS))
232		return -EINVAL;
233	tb = &tfd->tbs[idx];
234
235	/* Each TFD can point to a maximum max_tbs Tx buffers */
236	if (le16_to_cpu(tfd->num_tbs) >= trans->txqs.tfd.max_tbs) {
237		IWL_ERR(trans, "Error can not send more than %d chunks\n",
238			trans->txqs.tfd.max_tbs);
239		return -EINVAL;
240	}
241
242	put_unaligned_le64(addr, &tb->addr);
243	tb->tb_len = cpu_to_le16(len);
244
245	tfd->num_tbs = cpu_to_le16(idx + 1);
246
247	return idx;
248}
249
250static struct page *get_workaround_page(struct iwl_trans *trans,
251					struct sk_buff *skb)
252{
253	struct page **page_ptr;
254	struct page *ret;
255
256	page_ptr = (void *)((u8 *)skb->cb + trans->txqs.page_offs);
257
258	ret = alloc_page(GFP_ATOMIC);
259	if (!ret)
260		return NULL;
261
262	/* set the chaining pointer to the previous page if there */
263	*(void **)(page_address(ret) + PAGE_SIZE - sizeof(void *)) = *page_ptr;
264	*page_ptr = ret;
265
266	return ret;
267}
268
269/*
270 * Add a TB and if needed apply the FH HW bug workaround;
271 * meta != NULL indicates that it's a page mapping and we
272 * need to dma_unmap_page() and set the meta->tbs bit in
273 * this case.
274 */
275static int iwl_txq_gen2_set_tb_with_wa(struct iwl_trans *trans,
276				       struct sk_buff *skb,
277				       struct iwl_tfh_tfd *tfd,
278				       dma_addr_t phys, void *virt,
279				       u16 len, struct iwl_cmd_meta *meta)
280{
281	dma_addr_t oldphys = phys;
282	struct page *page;
283	int ret;
284
285	if (unlikely(dma_mapping_error(trans->dev, phys)))
286		return -ENOMEM;
287
288	if (likely(!iwl_txq_crosses_4g_boundary(phys, len))) {
289		ret = iwl_txq_gen2_set_tb(trans, tfd, phys, len);
290
291		if (ret < 0)
292			goto unmap;
293
294		if (meta)
295			meta->tbs |= BIT(ret);
296
297		ret = 0;
298		goto trace;
299	}
300
301	/*
302	 * Work around a hardware bug. If (as expressed in the
303	 * condition above) the TB ends on a 32-bit boundary,
304	 * then the next TB may be accessed with the wrong
305	 * address.
306	 * To work around it, copy the data elsewhere and make
307	 * a new mapping for it so the device will not fail.
308	 */
309
310	if (WARN_ON(len > PAGE_SIZE - sizeof(void *))) {
311		ret = -ENOBUFS;
312		goto unmap;
313	}
314
315	page = get_workaround_page(trans, skb);
316	if (!page) {
317		ret = -ENOMEM;
318		goto unmap;
319	}
320
321	memcpy(page_address(page), virt, len);
322
323	phys = dma_map_single(trans->dev, page_address(page), len,
324			      DMA_TO_DEVICE);
325	if (unlikely(dma_mapping_error(trans->dev, phys)))
326		return -ENOMEM;
327	ret = iwl_txq_gen2_set_tb(trans, tfd, phys, len);
328	if (ret < 0) {
329		/* unmap the new allocation as single */
330		oldphys = phys;
331		meta = NULL;
332		goto unmap;
333	}
334	IWL_WARN(trans,
335		 "TB bug workaround: copied %d bytes from 0x%llx to 0x%llx\n",
336		 len, (unsigned long long)oldphys, (unsigned long long)phys);
337
338	ret = 0;
339unmap:
340	if (meta)
341		dma_unmap_page(trans->dev, oldphys, len, DMA_TO_DEVICE);
342	else
343		dma_unmap_single(trans->dev, oldphys, len, DMA_TO_DEVICE);
344trace:
345	trace_iwlwifi_dev_tx_tb(trans->dev, skb, virt, phys, len);
346
347	return ret;
348}
349
350#ifdef CONFIG_INET
351struct iwl_tso_hdr_page *get_page_hdr(struct iwl_trans *trans, size_t len,
352				      struct sk_buff *skb)
353{
354	struct iwl_tso_hdr_page *p = this_cpu_ptr(trans->txqs.tso_hdr_page);
355	struct page **page_ptr;
356
357	page_ptr = (void *)((u8 *)skb->cb + trans->txqs.page_offs);
358
359	if (WARN_ON(*page_ptr))
360		return NULL;
361
362	if (!p->page)
363		goto alloc;
364
365	/*
366	 * Check if there's enough room on this page
367	 *
368	 * Note that we put a page chaining pointer *last* in the
369	 * page - we need it somewhere, and if it's there then we
370	 * avoid DMA mapping the last bits of the page which may
371	 * trigger the 32-bit boundary hardware bug.
372	 *
373	 * (see also get_workaround_page() in tx-gen2.c)
374	 */
375	if (p->pos + len < (u8 *)page_address(p->page) + PAGE_SIZE -
376			   sizeof(void *))
377		goto out;
378
379	/* We don't have enough room on this page, get a new one. */
380	__free_page(p->page);
381
382alloc:
383	p->page = alloc_page(GFP_ATOMIC);
384	if (!p->page)
385		return NULL;
386	p->pos = page_address(p->page);
387	/* set the chaining pointer to NULL */
388	*(void **)(page_address(p->page) + PAGE_SIZE - sizeof(void *)) = NULL;
389out:
390	*page_ptr = p->page;
391	get_page(p->page);
392	return p;
393}
394#endif
395
396static int iwl_txq_gen2_build_amsdu(struct iwl_trans *trans,
397				    struct sk_buff *skb,
398				    struct iwl_tfh_tfd *tfd, int start_len,
399				    u8 hdr_len,
400				    struct iwl_device_tx_cmd *dev_cmd)
401{
402#ifdef CONFIG_INET
403	struct iwl_tx_cmd_gen2 *tx_cmd = (void *)dev_cmd->payload;
404	struct ieee80211_hdr *hdr = (void *)skb->data;
405	unsigned int snap_ip_tcp_hdrlen, ip_hdrlen, total_len, hdr_room;
406	unsigned int mss = skb_shinfo(skb)->gso_size;
407	u16 length, amsdu_pad;
408	u8 *start_hdr;
409	struct iwl_tso_hdr_page *hdr_page;
410	struct tso_t tso;
411
412	trace_iwlwifi_dev_tx(trans->dev, skb, tfd, sizeof(*tfd),
413			     &dev_cmd->hdr, start_len, 0);
414
415	ip_hdrlen = skb_transport_header(skb) - skb_network_header(skb);
416	snap_ip_tcp_hdrlen = 8 + ip_hdrlen + tcp_hdrlen(skb);
417	total_len = skb->len - snap_ip_tcp_hdrlen - hdr_len;
418	amsdu_pad = 0;
419
420	/* total amount of header we may need for this A-MSDU */
421	hdr_room = DIV_ROUND_UP(total_len, mss) *
422		(3 + snap_ip_tcp_hdrlen + sizeof(struct ethhdr));
423
424	/* Our device supports 9 segments at most, it will fit in 1 page */
425	hdr_page = get_page_hdr(trans, hdr_room, skb);
426	if (!hdr_page)
427		return -ENOMEM;
428
429	start_hdr = hdr_page->pos;
430
431	/*
432	 * Pull the ieee80211 header to be able to use TSO core,
433	 * we will restore it for the tx_status flow.
434	 */
435	skb_pull(skb, hdr_len);
436
437	/*
438	 * Remove the length of all the headers that we don't actually
439	 * have in the MPDU by themselves, but that we duplicate into
440	 * all the different MSDUs inside the A-MSDU.
441	 */
442	le16_add_cpu(&tx_cmd->len, -snap_ip_tcp_hdrlen);
443
444	tso_start(skb, &tso);
445
446	while (total_len) {
447		/* this is the data left for this subframe */
448		unsigned int data_left = min_t(unsigned int, mss, total_len);
449		struct sk_buff *csum_skb = NULL;
450		unsigned int tb_len;
451		dma_addr_t tb_phys;
452		u8 *subf_hdrs_start = hdr_page->pos;
453
454		total_len -= data_left;
455
456		memset(hdr_page->pos, 0, amsdu_pad);
457		hdr_page->pos += amsdu_pad;
458		amsdu_pad = (4 - (sizeof(struct ethhdr) + snap_ip_tcp_hdrlen +
459				  data_left)) & 0x3;
460		ether_addr_copy(hdr_page->pos, ieee80211_get_DA(hdr));
461		hdr_page->pos += ETH_ALEN;
462		ether_addr_copy(hdr_page->pos, ieee80211_get_SA(hdr));
463		hdr_page->pos += ETH_ALEN;
464
465		length = snap_ip_tcp_hdrlen + data_left;
466		*((__be16 *)hdr_page->pos) = cpu_to_be16(length);
467		hdr_page->pos += sizeof(length);
468
469		/*
470		 * This will copy the SNAP as well which will be considered
471		 * as MAC header.
472		 */
473		tso_build_hdr(skb, hdr_page->pos, &tso, data_left, !total_len);
474
475		hdr_page->pos += snap_ip_tcp_hdrlen;
476
477		tb_len = hdr_page->pos - start_hdr;
478		tb_phys = dma_map_single(trans->dev, start_hdr,
479					 tb_len, DMA_TO_DEVICE);
480		if (unlikely(dma_mapping_error(trans->dev, tb_phys))) {
481			dev_kfree_skb(csum_skb);
482			goto out_err;
483		}
484		/*
485		 * No need for _with_wa, this is from the TSO page and
486		 * we leave some space at the end of it so can't hit
487		 * the buggy scenario.
488		 */
489		iwl_txq_gen2_set_tb(trans, tfd, tb_phys, tb_len);
490		trace_iwlwifi_dev_tx_tb(trans->dev, skb, start_hdr,
491					tb_phys, tb_len);
492		/* add this subframe's headers' length to the tx_cmd */
493		le16_add_cpu(&tx_cmd->len, hdr_page->pos - subf_hdrs_start);
494
495		/* prepare the start_hdr for the next subframe */
496		start_hdr = hdr_page->pos;
497
498		/* put the payload */
499		while (data_left) {
500			int ret;
501
502			tb_len = min_t(unsigned int, tso.size, data_left);
503			tb_phys = dma_map_single(trans->dev, tso.data,
504						 tb_len, DMA_TO_DEVICE);
505			ret = iwl_txq_gen2_set_tb_with_wa(trans, skb, tfd,
506							  tb_phys, tso.data,
507							  tb_len, NULL);
508			if (ret) {
509				dev_kfree_skb(csum_skb);
510				goto out_err;
511			}
512
513			data_left -= tb_len;
514			tso_build_data(skb, &tso, tb_len);
515		}
516	}
517
518	/* re -add the WiFi header */
519	skb_push(skb, hdr_len);
520
521	return 0;
522
523out_err:
524#endif
525	return -EINVAL;
526}
527
528static struct
529iwl_tfh_tfd *iwl_txq_gen2_build_tx_amsdu(struct iwl_trans *trans,
530					 struct iwl_txq *txq,
531					 struct iwl_device_tx_cmd *dev_cmd,
532					 struct sk_buff *skb,
533					 struct iwl_cmd_meta *out_meta,
534					 int hdr_len,
535					 int tx_cmd_len)
536{
537	int idx = iwl_txq_get_cmd_index(txq, txq->write_ptr);
538	struct iwl_tfh_tfd *tfd = iwl_txq_get_tfd(trans, txq, idx);
539	dma_addr_t tb_phys;
540	int len;
541	void *tb1_addr;
542
543	tb_phys = iwl_txq_get_first_tb_dma(txq, idx);
544
545	/*
546	 * No need for _with_wa, the first TB allocation is aligned up
547	 * to a 64-byte boundary and thus can't be at the end or cross
548	 * a page boundary (much less a 2^32 boundary).
549	 */
550	iwl_txq_gen2_set_tb(trans, tfd, tb_phys, IWL_FIRST_TB_SIZE);
551
552	/*
553	 * The second TB (tb1) points to the remainder of the TX command
554	 * and the 802.11 header - dword aligned size
555	 * (This calculation modifies the TX command, so do it before the
556	 * setup of the first TB)
557	 */
558	len = tx_cmd_len + sizeof(struct iwl_cmd_header) + hdr_len -
559	      IWL_FIRST_TB_SIZE;
560
561	/* do not align A-MSDU to dword as the subframe header aligns it */
562
563	/* map the data for TB1 */
564	tb1_addr = ((u8 *)&dev_cmd->hdr) + IWL_FIRST_TB_SIZE;
565	tb_phys = dma_map_single(trans->dev, tb1_addr, len, DMA_TO_DEVICE);
566	if (unlikely(dma_mapping_error(trans->dev, tb_phys)))
567		goto out_err;
568	/*
569	 * No need for _with_wa(), we ensure (via alignment) that the data
570	 * here can never cross or end at a page boundary.
571	 */
572	iwl_txq_gen2_set_tb(trans, tfd, tb_phys, len);
573
574	if (iwl_txq_gen2_build_amsdu(trans, skb, tfd, len + IWL_FIRST_TB_SIZE,
575				     hdr_len, dev_cmd))
576		goto out_err;
577
578	/* building the A-MSDU might have changed this data, memcpy it now */
579	memcpy(&txq->first_tb_bufs[idx], dev_cmd, IWL_FIRST_TB_SIZE);
580	return tfd;
581
582out_err:
583	iwl_txq_gen2_tfd_unmap(trans, out_meta, tfd);
584	return NULL;
585}
586
587static int iwl_txq_gen2_tx_add_frags(struct iwl_trans *trans,
588				     struct sk_buff *skb,
589				     struct iwl_tfh_tfd *tfd,
590				     struct iwl_cmd_meta *out_meta)
591{
592	int i;
593
594	for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
595		const skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
596		dma_addr_t tb_phys;
597		unsigned int fragsz = skb_frag_size(frag);
598		int ret;
599
600		if (!fragsz)
601			continue;
602
603		tb_phys = skb_frag_dma_map(trans->dev, frag, 0,
604					   fragsz, DMA_TO_DEVICE);
605		ret = iwl_txq_gen2_set_tb_with_wa(trans, skb, tfd, tb_phys,
606						  skb_frag_address(frag),
607						  fragsz, out_meta);
608		if (ret)
609			return ret;
610	}
611
612	return 0;
613}
614
615static struct
616iwl_tfh_tfd *iwl_txq_gen2_build_tx(struct iwl_trans *trans,
617				   struct iwl_txq *txq,
618				   struct iwl_device_tx_cmd *dev_cmd,
619				   struct sk_buff *skb,
620				   struct iwl_cmd_meta *out_meta,
621				   int hdr_len,
622				   int tx_cmd_len,
623				   bool pad)
624{
625	int idx = iwl_txq_get_cmd_index(txq, txq->write_ptr);
626	struct iwl_tfh_tfd *tfd = iwl_txq_get_tfd(trans, txq, idx);
627	dma_addr_t tb_phys;
628	int len, tb1_len, tb2_len;
629	void *tb1_addr;
630	struct sk_buff *frag;
631
632	tb_phys = iwl_txq_get_first_tb_dma(txq, idx);
633
634	/* The first TB points to bi-directional DMA data */
635	memcpy(&txq->first_tb_bufs[idx], dev_cmd, IWL_FIRST_TB_SIZE);
636
637	/*
638	 * No need for _with_wa, the first TB allocation is aligned up
639	 * to a 64-byte boundary and thus can't be at the end or cross
640	 * a page boundary (much less a 2^32 boundary).
641	 */
642	iwl_txq_gen2_set_tb(trans, tfd, tb_phys, IWL_FIRST_TB_SIZE);
643
644	/*
645	 * The second TB (tb1) points to the remainder of the TX command
646	 * and the 802.11 header - dword aligned size
647	 * (This calculation modifies the TX command, so do it before the
648	 * setup of the first TB)
649	 */
650	len = tx_cmd_len + sizeof(struct iwl_cmd_header) + hdr_len -
651	      IWL_FIRST_TB_SIZE;
652
653	if (pad)
654		tb1_len = ALIGN(len, 4);
655	else
656		tb1_len = len;
657
658	/* map the data for TB1 */
659	tb1_addr = ((u8 *)&dev_cmd->hdr) + IWL_FIRST_TB_SIZE;
660	tb_phys = dma_map_single(trans->dev, tb1_addr, tb1_len, DMA_TO_DEVICE);
661	if (unlikely(dma_mapping_error(trans->dev, tb_phys)))
662		goto out_err;
663	/*
664	 * No need for _with_wa(), we ensure (via alignment) that the data
665	 * here can never cross or end at a page boundary.
666	 */
667	iwl_txq_gen2_set_tb(trans, tfd, tb_phys, tb1_len);
668	trace_iwlwifi_dev_tx(trans->dev, skb, tfd, sizeof(*tfd), &dev_cmd->hdr,
669			     IWL_FIRST_TB_SIZE + tb1_len, hdr_len);
670
671	/* set up TFD's third entry to point to remainder of skb's head */
672	tb2_len = skb_headlen(skb) - hdr_len;
673
674	if (tb2_len > 0) {
675		int ret;
676
677		tb_phys = dma_map_single(trans->dev, skb->data + hdr_len,
678					 tb2_len, DMA_TO_DEVICE);
679		ret = iwl_txq_gen2_set_tb_with_wa(trans, skb, tfd, tb_phys,
680						  skb->data + hdr_len, tb2_len,
681						  NULL);
682		if (ret)
683			goto out_err;
684	}
685
686	if (iwl_txq_gen2_tx_add_frags(trans, skb, tfd, out_meta))
687		goto out_err;
688
689	skb_walk_frags(skb, frag) {
690		int ret;
691
692		tb_phys = dma_map_single(trans->dev, frag->data,
693					 skb_headlen(frag), DMA_TO_DEVICE);
694		ret = iwl_txq_gen2_set_tb_with_wa(trans, skb, tfd, tb_phys,
695						  frag->data,
696						  skb_headlen(frag), NULL);
697		if (ret)
698			goto out_err;
699		if (iwl_txq_gen2_tx_add_frags(trans, frag, tfd, out_meta))
700			goto out_err;
701	}
702
703	return tfd;
704
705out_err:
706	iwl_txq_gen2_tfd_unmap(trans, out_meta, tfd);
707	return NULL;
708}
709
710static
711struct iwl_tfh_tfd *iwl_txq_gen2_build_tfd(struct iwl_trans *trans,
712					   struct iwl_txq *txq,
713					   struct iwl_device_tx_cmd *dev_cmd,
714					   struct sk_buff *skb,
715					   struct iwl_cmd_meta *out_meta)
716{
717	struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)skb->data;
718	int idx = iwl_txq_get_cmd_index(txq, txq->write_ptr);
719	struct iwl_tfh_tfd *tfd = iwl_txq_get_tfd(trans, txq, idx);
720	int len, hdr_len;
721	bool amsdu;
722
723	/* There must be data left over for TB1 or this code must be changed */
724	BUILD_BUG_ON(sizeof(struct iwl_tx_cmd_gen2) < IWL_FIRST_TB_SIZE);
725
726	memset(tfd, 0, sizeof(*tfd));
727
728	if (trans->trans_cfg->device_family < IWL_DEVICE_FAMILY_AX210)
729		len = sizeof(struct iwl_tx_cmd_gen2);
730	else
731		len = sizeof(struct iwl_tx_cmd_gen3);
732
733	amsdu = ieee80211_is_data_qos(hdr->frame_control) &&
734			(*ieee80211_get_qos_ctl(hdr) &
735			 IEEE80211_QOS_CTL_A_MSDU_PRESENT);
736
737	hdr_len = ieee80211_hdrlen(hdr->frame_control);
738
739	/*
740	 * Only build A-MSDUs here if doing so by GSO, otherwise it may be
741	 * an A-MSDU for other reasons, e.g. NAN or an A-MSDU having been
742	 * built in the higher layers already.
743	 */
744	if (amsdu && skb_shinfo(skb)->gso_size)
745		return iwl_txq_gen2_build_tx_amsdu(trans, txq, dev_cmd, skb,
746						    out_meta, hdr_len, len);
747	return iwl_txq_gen2_build_tx(trans, txq, dev_cmd, skb, out_meta,
748				      hdr_len, len, !amsdu);
749}
750
751int iwl_txq_space(struct iwl_trans *trans, const struct iwl_txq *q)
752{
753	unsigned int max;
754	unsigned int used;
755
756	/*
757	 * To avoid ambiguity between empty and completely full queues, there
758	 * should always be less than max_tfd_queue_size elements in the queue.
759	 * If q->n_window is smaller than max_tfd_queue_size, there is no need
760	 * to reserve any queue entries for this purpose.
761	 */
762	if (q->n_window < trans->trans_cfg->base_params->max_tfd_queue_size)
763		max = q->n_window;
764	else
765		max = trans->trans_cfg->base_params->max_tfd_queue_size - 1;
766
767	/*
768	 * max_tfd_queue_size is a power of 2, so the following is equivalent to
769	 * modulo by max_tfd_queue_size and is well defined.
770	 */
771	used = (q->write_ptr - q->read_ptr) &
772		(trans->trans_cfg->base_params->max_tfd_queue_size - 1);
773
774	if (WARN_ON(used > max))
775		return 0;
776
777	return max - used;
778}
779
780int iwl_txq_gen2_tx(struct iwl_trans *trans, struct sk_buff *skb,
781		    struct iwl_device_tx_cmd *dev_cmd, int txq_id)
782{
783	struct iwl_cmd_meta *out_meta;
784	struct iwl_txq *txq = trans->txqs.txq[txq_id];
785	u16 cmd_len;
786	int idx;
787	void *tfd;
788
789	if (WARN_ONCE(txq_id >= IWL_MAX_TVQM_QUEUES,
790		      "queue %d out of range", txq_id))
791		return -EINVAL;
792
793	if (WARN_ONCE(!test_bit(txq_id, trans->txqs.queue_used),
794		      "TX on unused queue %d\n", txq_id))
795		return -EINVAL;
796
797	if (skb_is_nonlinear(skb) &&
798	    skb_shinfo(skb)->nr_frags > IWL_TRANS_MAX_FRAGS(trans) &&
799	    __skb_linearize(skb))
800		return -ENOMEM;
801
802	spin_lock(&txq->lock);
803
804	if (iwl_txq_space(trans, txq) < txq->high_mark) {
805		iwl_txq_stop(trans, txq);
806
807		/* don't put the packet on the ring, if there is no room */
808		if (unlikely(iwl_txq_space(trans, txq) < 3)) {
809			struct iwl_device_tx_cmd **dev_cmd_ptr;
810
811			dev_cmd_ptr = (void *)((u8 *)skb->cb +
812					       trans->txqs.dev_cmd_offs);
813
814			*dev_cmd_ptr = dev_cmd;
815			__skb_queue_tail(&txq->overflow_q, skb);
816			spin_unlock(&txq->lock);
817			return 0;
818		}
819	}
820
821	idx = iwl_txq_get_cmd_index(txq, txq->write_ptr);
822
823	/* Set up driver data for this TFD */
824	txq->entries[idx].skb = skb;
825	txq->entries[idx].cmd = dev_cmd;
826
827	dev_cmd->hdr.sequence =
828		cpu_to_le16((u16)(QUEUE_TO_SEQ(txq_id) |
829			    INDEX_TO_SEQ(idx)));
830
831	/* Set up first empty entry in queue's array of Tx/cmd buffers */
832	out_meta = &txq->entries[idx].meta;
833	out_meta->flags = 0;
834
835	tfd = iwl_txq_gen2_build_tfd(trans, txq, dev_cmd, skb, out_meta);
836	if (!tfd) {
837		spin_unlock(&txq->lock);
838		return -1;
839	}
840
841	if (trans->trans_cfg->device_family >= IWL_DEVICE_FAMILY_AX210) {
842		struct iwl_tx_cmd_gen3 *tx_cmd_gen3 =
843			(void *)dev_cmd->payload;
844
845		cmd_len = le16_to_cpu(tx_cmd_gen3->len);
846	} else {
847		struct iwl_tx_cmd_gen2 *tx_cmd_gen2 =
848			(void *)dev_cmd->payload;
849
850		cmd_len = le16_to_cpu(tx_cmd_gen2->len);
851	}
852
853	/* Set up entry for this TFD in Tx byte-count array */
854	iwl_pcie_gen2_update_byte_tbl(trans, txq, cmd_len,
855				      iwl_txq_gen2_get_num_tbs(trans, tfd));
856
857	/* start timer if queue currently empty */
858	if (txq->read_ptr == txq->write_ptr && txq->wd_timeout)
859		mod_timer(&txq->stuck_timer, jiffies + txq->wd_timeout);
860
861	/* Tell device the write index *just past* this latest filled TFD */
862	txq->write_ptr = iwl_txq_inc_wrap(trans, txq->write_ptr);
863	iwl_txq_inc_wr_ptr(trans, txq);
864	/*
865	 * At this point the frame is "transmitted" successfully
866	 * and we will get a TX status notification eventually.
867	 */
868	spin_unlock(&txq->lock);
869	return 0;
870}
871
872/*************** HOST COMMAND QUEUE FUNCTIONS   *****/
873
874/*
875 * iwl_txq_gen2_unmap -  Unmap any remaining DMA mappings and free skb's
876 */
877void iwl_txq_gen2_unmap(struct iwl_trans *trans, int txq_id)
878{
879	struct iwl_txq *txq = trans->txqs.txq[txq_id];
880
881	spin_lock_bh(&txq->lock);
882	while (txq->write_ptr != txq->read_ptr) {
883		IWL_DEBUG_TX_REPLY(trans, "Q %d Free %d\n",
884				   txq_id, txq->read_ptr);
885
886		if (txq_id != trans->txqs.cmd.q_id) {
887			int idx = iwl_txq_get_cmd_index(txq, txq->read_ptr);
888			struct sk_buff *skb = txq->entries[idx].skb;
889
890			if (!WARN_ON_ONCE(!skb))
891				iwl_txq_free_tso_page(trans, skb);
892		}
893		iwl_txq_gen2_free_tfd(trans, txq);
894		txq->read_ptr = iwl_txq_inc_wrap(trans, txq->read_ptr);
895	}
896
897	while (!skb_queue_empty(&txq->overflow_q)) {
898		struct sk_buff *skb = __skb_dequeue(&txq->overflow_q);
899
900		iwl_op_mode_free_skb(trans->op_mode, skb);
901	}
902
903	spin_unlock_bh(&txq->lock);
904
905	/* just in case - this queue may have been stopped */
906	iwl_wake_queue(trans, txq);
907}
908
909static void iwl_txq_gen2_free_memory(struct iwl_trans *trans,
910				     struct iwl_txq *txq)
911{
912	struct device *dev = trans->dev;
913
914	/* De-alloc circular buffer of TFDs */
915	if (txq->tfds) {
916		dma_free_coherent(dev,
917				  trans->txqs.tfd.size * txq->n_window,
918				  txq->tfds, txq->dma_addr);
919		dma_free_coherent(dev,
920				  sizeof(*txq->first_tb_bufs) * txq->n_window,
921				  txq->first_tb_bufs, txq->first_tb_dma);
922	}
923
924	kfree(txq->entries);
925	if (txq->bc_tbl.addr)
926		dma_pool_free(trans->txqs.bc_pool,
927			      txq->bc_tbl.addr, txq->bc_tbl.dma);
928	kfree(txq);
929}
930
931/*
932 * iwl_pcie_txq_free - Deallocate DMA queue.
933 * @txq: Transmit queue to deallocate.
934 *
935 * Empty queue by removing and destroying all BD's.
936 * Free all buffers.
937 * 0-fill, but do not free "txq" descriptor structure.
938 */
939static void iwl_txq_gen2_free(struct iwl_trans *trans, int txq_id)
940{
941	struct iwl_txq *txq;
942	int i;
943
944	if (WARN_ONCE(txq_id >= IWL_MAX_TVQM_QUEUES,
945		      "queue %d out of range", txq_id))
946		return;
947
948	txq = trans->txqs.txq[txq_id];
949
950	if (WARN_ON(!txq))
951		return;
952
953	iwl_txq_gen2_unmap(trans, txq_id);
954
955	/* De-alloc array of command/tx buffers */
956	if (txq_id == trans->txqs.cmd.q_id)
957		for (i = 0; i < txq->n_window; i++) {
958			kfree_sensitive(txq->entries[i].cmd);
959			kfree_sensitive(txq->entries[i].free_buf);
960		}
961	del_timer_sync(&txq->stuck_timer);
962
963	iwl_txq_gen2_free_memory(trans, txq);
964
965	trans->txqs.txq[txq_id] = NULL;
966
967	clear_bit(txq_id, trans->txqs.queue_used);
968}
969
970/*
971 * iwl_queue_init - Initialize queue's high/low-water and read/write indexes
972 */
973static int iwl_queue_init(struct iwl_txq *q, int slots_num)
974{
975	q->n_window = slots_num;
976
977	/* slots_num must be power-of-two size, otherwise
978	 * iwl_txq_get_cmd_index is broken. */
979	if (WARN_ON(!is_power_of_2(slots_num)))
980		return -EINVAL;
981
982	q->low_mark = q->n_window / 4;
983	if (q->low_mark < 4)
984		q->low_mark = 4;
985
986	q->high_mark = q->n_window / 8;
987	if (q->high_mark < 2)
988		q->high_mark = 2;
989
990	q->write_ptr = 0;
991	q->read_ptr = 0;
992
993	return 0;
994}
995
996int iwl_txq_init(struct iwl_trans *trans, struct iwl_txq *txq, int slots_num,
997		 bool cmd_queue)
998{
999	int ret;
1000	u32 tfd_queue_max_size =
1001		trans->trans_cfg->base_params->max_tfd_queue_size;
1002
1003	txq->need_update = false;
1004
1005	/* max_tfd_queue_size must be power-of-two size, otherwise
1006	 * iwl_txq_inc_wrap and iwl_txq_dec_wrap are broken. */
1007	if (WARN_ONCE(tfd_queue_max_size & (tfd_queue_max_size - 1),
1008		      "Max tfd queue size must be a power of two, but is %d",
1009		      tfd_queue_max_size))
1010		return -EINVAL;
1011
1012	/* Initialize queue's high/low-water marks, and head/tail indexes */
1013	ret = iwl_queue_init(txq, slots_num);
1014	if (ret)
1015		return ret;
1016
1017	spin_lock_init(&txq->lock);
1018
1019	if (cmd_queue) {
1020		static struct lock_class_key iwl_txq_cmd_queue_lock_class;
1021
1022		lockdep_set_class(&txq->lock, &iwl_txq_cmd_queue_lock_class);
1023	}
1024
1025	__skb_queue_head_init(&txq->overflow_q);
1026
1027	return 0;
1028}
1029
1030void iwl_txq_free_tso_page(struct iwl_trans *trans, struct sk_buff *skb)
1031{
1032	struct page **page_ptr;
1033	struct page *next;
1034
1035	page_ptr = (void *)((u8 *)skb->cb + trans->txqs.page_offs);
1036	next = *page_ptr;
1037	*page_ptr = NULL;
1038
1039	while (next) {
1040		struct page *tmp = next;
1041
1042		next = *(void **)(page_address(next) + PAGE_SIZE -
1043				  sizeof(void *));
1044		__free_page(tmp);
1045	}
1046}
1047
1048void iwl_txq_log_scd_error(struct iwl_trans *trans, struct iwl_txq *txq)
1049{
1050	u32 txq_id = txq->id;
1051	u32 status;
1052	bool active;
1053	u8 fifo;
1054
1055	if (trans->trans_cfg->use_tfh) {
1056		IWL_ERR(trans, "Queue %d is stuck %d %d\n", txq_id,
1057			txq->read_ptr, txq->write_ptr);
1058		/* TODO: access new SCD registers and dump them */
1059		return;
1060	}
1061
1062	status = iwl_read_prph(trans, SCD_QUEUE_STATUS_BITS(txq_id));
1063	fifo = (status >> SCD_QUEUE_STTS_REG_POS_TXF) & 0x7;
1064	active = !!(status & BIT(SCD_QUEUE_STTS_REG_POS_ACTIVE));
1065
1066	IWL_ERR(trans,
1067		"Queue %d is %sactive on fifo %d and stuck for %u ms. SW [%d, %d] HW [%d, %d] FH TRB=0x0%x\n",
1068		txq_id, active ? "" : "in", fifo,
1069		jiffies_to_msecs(txq->wd_timeout),
1070		txq->read_ptr, txq->write_ptr,
1071		iwl_read_prph(trans, SCD_QUEUE_RDPTR(txq_id)) &
1072			(trans->trans_cfg->base_params->max_tfd_queue_size - 1),
1073			iwl_read_prph(trans, SCD_QUEUE_WRPTR(txq_id)) &
1074			(trans->trans_cfg->base_params->max_tfd_queue_size - 1),
1075			iwl_read_direct32(trans, FH_TX_TRB_REG(fifo)));
1076}
1077
1078static void iwl_txq_stuck_timer(struct timer_list *t)
1079{
1080	struct iwl_txq *txq = from_timer(txq, t, stuck_timer);
1081	struct iwl_trans *trans = txq->trans;
1082
1083	spin_lock(&txq->lock);
1084	/* check if triggered erroneously */
1085	if (txq->read_ptr == txq->write_ptr) {
1086		spin_unlock(&txq->lock);
1087		return;
1088	}
1089	spin_unlock(&txq->lock);
1090
1091	iwl_txq_log_scd_error(trans, txq);
1092
1093	iwl_force_nmi(trans);
1094}
1095
1096int iwl_txq_alloc(struct iwl_trans *trans, struct iwl_txq *txq, int slots_num,
1097		  bool cmd_queue)
1098{
1099	size_t tfd_sz = trans->txqs.tfd.size *
1100		trans->trans_cfg->base_params->max_tfd_queue_size;
1101	size_t tb0_buf_sz;
1102	int i;
1103
1104	if (WARN_ON(txq->entries || txq->tfds))
1105		return -EINVAL;
1106
1107	if (trans->trans_cfg->use_tfh)
1108		tfd_sz = trans->txqs.tfd.size * slots_num;
1109
1110	timer_setup(&txq->stuck_timer, iwl_txq_stuck_timer, 0);
1111	txq->trans = trans;
1112
1113	txq->n_window = slots_num;
1114
1115	txq->entries = kcalloc(slots_num,
1116			       sizeof(struct iwl_pcie_txq_entry),
1117			       GFP_KERNEL);
1118
1119	if (!txq->entries)
1120		goto error;
1121
1122	if (cmd_queue)
1123		for (i = 0; i < slots_num; i++) {
1124			txq->entries[i].cmd =
1125				kmalloc(sizeof(struct iwl_device_cmd),
1126					GFP_KERNEL);
1127			if (!txq->entries[i].cmd)
1128				goto error;
1129		}
1130
1131	/* Circular buffer of transmit frame descriptors (TFDs),
1132	 * shared with device */
1133	txq->tfds = dma_alloc_coherent(trans->dev, tfd_sz,
1134				       &txq->dma_addr, GFP_KERNEL);
1135	if (!txq->tfds)
1136		goto error;
1137
1138	BUILD_BUG_ON(sizeof(*txq->first_tb_bufs) != IWL_FIRST_TB_SIZE_ALIGN);
1139
1140	tb0_buf_sz = sizeof(*txq->first_tb_bufs) * slots_num;
1141
1142	txq->first_tb_bufs = dma_alloc_coherent(trans->dev, tb0_buf_sz,
1143						&txq->first_tb_dma,
1144						GFP_KERNEL);
1145	if (!txq->first_tb_bufs)
1146		goto err_free_tfds;
1147
1148	return 0;
1149err_free_tfds:
1150	dma_free_coherent(trans->dev, tfd_sz, txq->tfds, txq->dma_addr);
1151	txq->tfds = NULL;
1152error:
1153	if (txq->entries && cmd_queue)
1154		for (i = 0; i < slots_num; i++)
1155			kfree(txq->entries[i].cmd);
1156	kfree(txq->entries);
1157	txq->entries = NULL;
1158
1159	return -ENOMEM;
1160}
1161
1162static int iwl_txq_dyn_alloc_dma(struct iwl_trans *trans,
1163				 struct iwl_txq **intxq, int size,
1164				 unsigned int timeout)
1165{
1166	size_t bc_tbl_size, bc_tbl_entries;
1167	struct iwl_txq *txq;
1168	int ret;
1169
1170	WARN_ON(!trans->txqs.bc_tbl_size);
1171
1172	bc_tbl_size = trans->txqs.bc_tbl_size;
1173	bc_tbl_entries = bc_tbl_size / sizeof(u16);
1174
1175	if (WARN_ON(size > bc_tbl_entries))
1176		return -EINVAL;
1177
1178	txq = kzalloc(sizeof(*txq), GFP_KERNEL);
1179	if (!txq)
1180		return -ENOMEM;
1181
1182	txq->bc_tbl.addr = dma_pool_alloc(trans->txqs.bc_pool, GFP_KERNEL,
1183					  &txq->bc_tbl.dma);
1184	if (!txq->bc_tbl.addr) {
1185		IWL_ERR(trans, "Scheduler BC Table allocation failed\n");
1186		kfree(txq);
1187		return -ENOMEM;
1188	}
1189
1190	ret = iwl_txq_alloc(trans, txq, size, false);
1191	if (ret) {
1192		IWL_ERR(trans, "Tx queue alloc failed\n");
1193		goto error;
1194	}
1195	ret = iwl_txq_init(trans, txq, size, false);
1196	if (ret) {
1197		IWL_ERR(trans, "Tx queue init failed\n");
1198		goto error;
1199	}
1200
1201	txq->wd_timeout = msecs_to_jiffies(timeout);
1202
1203	*intxq = txq;
1204	return 0;
1205
1206error:
1207	iwl_txq_gen2_free_memory(trans, txq);
1208	return ret;
1209}
1210
1211static int iwl_txq_alloc_response(struct iwl_trans *trans, struct iwl_txq *txq,
1212				  struct iwl_host_cmd *hcmd)
1213{
1214	struct iwl_tx_queue_cfg_rsp *rsp;
1215	int ret, qid;
1216	u32 wr_ptr;
1217
1218	if (WARN_ON(iwl_rx_packet_payload_len(hcmd->resp_pkt) !=
1219		    sizeof(*rsp))) {
1220		ret = -EINVAL;
1221		goto error_free_resp;
1222	}
1223
1224	rsp = (void *)hcmd->resp_pkt->data;
1225	qid = le16_to_cpu(rsp->queue_number);
1226	wr_ptr = le16_to_cpu(rsp->write_pointer);
1227
1228	if (qid >= ARRAY_SIZE(trans->txqs.txq)) {
1229		WARN_ONCE(1, "queue index %d unsupported", qid);
1230		ret = -EIO;
1231		goto error_free_resp;
1232	}
1233
1234	if (test_and_set_bit(qid, trans->txqs.queue_used)) {
1235		WARN_ONCE(1, "queue %d already used", qid);
1236		ret = -EIO;
1237		goto error_free_resp;
1238	}
1239
1240	txq->id = qid;
1241	trans->txqs.txq[qid] = txq;
1242	wr_ptr &= (trans->trans_cfg->base_params->max_tfd_queue_size - 1);
1243
1244	/* Place first TFD at index corresponding to start sequence number */
1245	txq->read_ptr = wr_ptr;
1246	txq->write_ptr = wr_ptr;
1247
1248	IWL_DEBUG_TX_QUEUES(trans, "Activate queue %d\n", qid);
1249
1250	iwl_free_resp(hcmd);
1251	return qid;
1252
1253error_free_resp:
1254	iwl_free_resp(hcmd);
1255	iwl_txq_gen2_free_memory(trans, txq);
1256	return ret;
1257}
1258
1259int iwl_txq_dyn_alloc(struct iwl_trans *trans, __le16 flags, u8 sta_id, u8 tid,
1260		      int cmd_id, int size, unsigned int timeout)
1261{
1262	struct iwl_txq *txq = NULL;
1263	struct iwl_tx_queue_cfg_cmd cmd = {
1264		.flags = flags,
1265		.sta_id = sta_id,
1266		.tid = tid,
1267	};
1268	struct iwl_host_cmd hcmd = {
1269		.id = cmd_id,
1270		.len = { sizeof(cmd) },
1271		.data = { &cmd, },
1272		.flags = CMD_WANT_SKB,
1273	};
1274	int ret;
1275
1276	ret = iwl_txq_dyn_alloc_dma(trans, &txq, size, timeout);
1277	if (ret)
1278		return ret;
1279
1280	cmd.tfdq_addr = cpu_to_le64(txq->dma_addr);
1281	cmd.byte_cnt_addr = cpu_to_le64(txq->bc_tbl.dma);
1282	cmd.cb_size = cpu_to_le32(TFD_QUEUE_CB_SIZE(size));
1283
1284	ret = iwl_trans_send_cmd(trans, &hcmd);
1285	if (ret)
1286		goto error;
1287
1288	return iwl_txq_alloc_response(trans, txq, &hcmd);
1289
1290error:
1291	iwl_txq_gen2_free_memory(trans, txq);
1292	return ret;
1293}
1294
1295void iwl_txq_dyn_free(struct iwl_trans *trans, int queue)
1296{
1297	if (WARN(queue >= IWL_MAX_TVQM_QUEUES,
1298		 "queue %d out of range", queue))
1299		return;
1300
1301	/*
1302	 * Upon HW Rfkill - we stop the device, and then stop the queues
1303	 * in the op_mode. Just for the sake of the simplicity of the op_mode,
1304	 * allow the op_mode to call txq_disable after it already called
1305	 * stop_device.
1306	 */
1307	if (!test_and_clear_bit(queue, trans->txqs.queue_used)) {
1308		WARN_ONCE(test_bit(STATUS_DEVICE_ENABLED, &trans->status),
1309			  "queue %d not used", queue);
1310		return;
1311	}
1312
1313	iwl_txq_gen2_unmap(trans, queue);
1314
1315	iwl_txq_gen2_free_memory(trans, trans->txqs.txq[queue]);
1316
1317	trans->txqs.txq[queue] = NULL;
1318
1319	IWL_DEBUG_TX_QUEUES(trans, "Deactivate queue %d\n", queue);
1320}
1321
1322void iwl_txq_gen2_tx_free(struct iwl_trans *trans)
1323{
1324	int i;
1325
1326	memset(trans->txqs.queue_used, 0, sizeof(trans->txqs.queue_used));
1327
1328	/* Free all TX queues */
1329	for (i = 0; i < ARRAY_SIZE(trans->txqs.txq); i++) {
1330		if (!trans->txqs.txq[i])
1331			continue;
1332
1333		iwl_txq_gen2_free(trans, i);
1334	}
1335}
1336
1337int iwl_txq_gen2_init(struct iwl_trans *trans, int txq_id, int queue_size)
1338{
1339	struct iwl_txq *queue;
1340	int ret;
1341
1342	/* alloc and init the tx queue */
1343	if (!trans->txqs.txq[txq_id]) {
1344		queue = kzalloc(sizeof(*queue), GFP_KERNEL);
1345		if (!queue) {
1346			IWL_ERR(trans, "Not enough memory for tx queue\n");
1347			return -ENOMEM;
1348		}
1349		trans->txqs.txq[txq_id] = queue;
1350		ret = iwl_txq_alloc(trans, queue, queue_size, true);
1351		if (ret) {
1352			IWL_ERR(trans, "Tx %d queue init failed\n", txq_id);
1353			goto error;
1354		}
1355	} else {
1356		queue = trans->txqs.txq[txq_id];
1357	}
1358
1359	ret = iwl_txq_init(trans, queue, queue_size,
1360			   (txq_id == trans->txqs.cmd.q_id));
1361	if (ret) {
1362		IWL_ERR(trans, "Tx %d queue alloc failed\n", txq_id);
1363		goto error;
1364	}
1365	trans->txqs.txq[txq_id]->id = txq_id;
1366	set_bit(txq_id, trans->txqs.queue_used);
1367
1368	return 0;
1369
1370error:
1371	iwl_txq_gen2_tx_free(trans);
1372	return ret;
1373}
1374
1375static inline dma_addr_t iwl_txq_gen1_tfd_tb_get_addr(struct iwl_trans *trans,
1376						      void *_tfd, u8 idx)
1377{
1378	struct iwl_tfd *tfd;
1379	struct iwl_tfd_tb *tb;
1380	dma_addr_t addr;
1381	dma_addr_t hi_len;
1382
1383	if (trans->trans_cfg->use_tfh) {
1384		struct iwl_tfh_tfd *tfd = _tfd;
1385		struct iwl_tfh_tb *tb = &tfd->tbs[idx];
1386
1387		return (dma_addr_t)(le64_to_cpu(tb->addr));
1388	}
1389
1390	tfd = _tfd;
1391	tb = &tfd->tbs[idx];
1392	addr = get_unaligned_le32(&tb->lo);
1393
1394	if (sizeof(dma_addr_t) <= sizeof(u32))
1395		return addr;
1396
1397	hi_len = le16_to_cpu(tb->hi_n_len) & 0xF;
1398
1399	/*
1400	 * shift by 16 twice to avoid warnings on 32-bit
1401	 * (where this code never runs anyway due to the
1402	 * if statement above)
1403	 */
1404	return addr | ((hi_len << 16) << 16);
1405}
1406
1407void iwl_txq_gen1_tfd_unmap(struct iwl_trans *trans,
1408			    struct iwl_cmd_meta *meta,
1409			    struct iwl_txq *txq, int index)
1410{
1411	int i, num_tbs;
1412	void *tfd = iwl_txq_get_tfd(trans, txq, index);
1413
1414	/* Sanity check on number of chunks */
1415	num_tbs = iwl_txq_gen1_tfd_get_num_tbs(trans, tfd);
1416
1417	if (num_tbs > trans->txqs.tfd.max_tbs) {
1418		IWL_ERR(trans, "Too many chunks: %i\n", num_tbs);
1419		/* @todo issue fatal error, it is quite serious situation */
1420		return;
1421	}
1422
1423	/* first TB is never freed - it's the bidirectional DMA data */
1424
1425	for (i = 1; i < num_tbs; i++) {
1426		if (meta->tbs & BIT(i))
1427			dma_unmap_page(trans->dev,
1428				       iwl_txq_gen1_tfd_tb_get_addr(trans,
1429								    tfd, i),
1430				       iwl_txq_gen1_tfd_tb_get_len(trans,
1431								   tfd, i),
1432				       DMA_TO_DEVICE);
1433		else
1434			dma_unmap_single(trans->dev,
1435					 iwl_txq_gen1_tfd_tb_get_addr(trans,
1436								      tfd, i),
1437					 iwl_txq_gen1_tfd_tb_get_len(trans,
1438								     tfd, i),
1439					 DMA_TO_DEVICE);
1440	}
1441
1442	meta->tbs = 0;
1443
1444	if (trans->trans_cfg->use_tfh) {
1445		struct iwl_tfh_tfd *tfd_fh = (void *)tfd;
1446
1447		tfd_fh->num_tbs = 0;
1448	} else {
1449		struct iwl_tfd *tfd_fh = (void *)tfd;
1450
1451		tfd_fh->num_tbs = 0;
1452	}
1453}
1454
1455#define IWL_TX_CRC_SIZE 4
1456#define IWL_TX_DELIMITER_SIZE 4
1457
1458/*
1459 * iwl_txq_gen1_update_byte_cnt_tbl - Set up entry in Tx byte-count array
1460 */
1461void iwl_txq_gen1_update_byte_cnt_tbl(struct iwl_trans *trans,
1462				      struct iwl_txq *txq, u16 byte_cnt,
1463				      int num_tbs)
1464{
1465	struct iwlagn_scd_bc_tbl *scd_bc_tbl;
1466	int write_ptr = txq->write_ptr;
1467	int txq_id = txq->id;
1468	u8 sec_ctl = 0;
1469	u16 len = byte_cnt + IWL_TX_CRC_SIZE + IWL_TX_DELIMITER_SIZE;
1470	__le16 bc_ent;
1471	struct iwl_device_tx_cmd *dev_cmd = txq->entries[txq->write_ptr].cmd;
1472	struct iwl_tx_cmd *tx_cmd = (void *)dev_cmd->payload;
1473	u8 sta_id = tx_cmd->sta_id;
1474
1475	scd_bc_tbl = trans->txqs.scd_bc_tbls.addr;
1476
1477	sec_ctl = tx_cmd->sec_ctl;
1478
1479	switch (sec_ctl & TX_CMD_SEC_MSK) {
1480	case TX_CMD_SEC_CCM:
1481		len += IEEE80211_CCMP_MIC_LEN;
1482		break;
1483	case TX_CMD_SEC_TKIP:
1484		len += IEEE80211_TKIP_ICV_LEN;
1485		break;
1486	case TX_CMD_SEC_WEP:
1487		len += IEEE80211_WEP_IV_LEN + IEEE80211_WEP_ICV_LEN;
1488		break;
1489	}
1490	if (trans->txqs.bc_table_dword)
1491		len = DIV_ROUND_UP(len, 4);
1492
1493	if (WARN_ON(len > 0xFFF || write_ptr >= TFD_QUEUE_SIZE_MAX))
1494		return;
1495
1496	bc_ent = cpu_to_le16(len | (sta_id << 12));
1497
1498	scd_bc_tbl[txq_id].tfd_offset[write_ptr] = bc_ent;
1499
1500	if (write_ptr < TFD_QUEUE_SIZE_BC_DUP)
1501		scd_bc_tbl[txq_id].tfd_offset[TFD_QUEUE_SIZE_MAX + write_ptr] =
1502			bc_ent;
1503}
1504
1505void iwl_txq_gen1_inval_byte_cnt_tbl(struct iwl_trans *trans,
1506				     struct iwl_txq *txq)
1507{
1508	struct iwlagn_scd_bc_tbl *scd_bc_tbl = trans->txqs.scd_bc_tbls.addr;
1509	int txq_id = txq->id;
1510	int read_ptr = txq->read_ptr;
1511	u8 sta_id = 0;
1512	__le16 bc_ent;
1513	struct iwl_device_tx_cmd *dev_cmd = txq->entries[read_ptr].cmd;
1514	struct iwl_tx_cmd *tx_cmd = (void *)dev_cmd->payload;
1515
1516	WARN_ON(read_ptr >= TFD_QUEUE_SIZE_MAX);
1517
1518	if (txq_id != trans->txqs.cmd.q_id)
1519		sta_id = tx_cmd->sta_id;
1520
1521	bc_ent = cpu_to_le16(1 | (sta_id << 12));
1522
1523	scd_bc_tbl[txq_id].tfd_offset[read_ptr] = bc_ent;
1524
1525	if (read_ptr < TFD_QUEUE_SIZE_BC_DUP)
1526		scd_bc_tbl[txq_id].tfd_offset[TFD_QUEUE_SIZE_MAX + read_ptr] =
1527			bc_ent;
1528}
1529