summaryrefslogtreecommitdiffstats
path: root/drivers/net/usb/asix_common.c
blob: e95dd12edec473198125c18c1cec6bc7d32ec368 (plain) (blame)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
/*
 * ASIX AX8817X based USB 2.0 Ethernet Devices
 * Copyright (C) 2003-2006 David Hollis <dhollis@davehollis.com>
 * Copyright (C) 2005 Phil Chang <pchang23@sbcglobal.net>
 * Copyright (C) 2006 James Painter <jamie.painter@iname.com>
 * Copyright (c) 2002-2003 TiVo Inc.
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License as published by
 * the Free Software Foundation; either version 2 of the License, or
 * (at your option) any later version.
 *
 * This program is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 * GNU General Public License for more details.
 *
 * You should have received a copy of the GNU General Public License
 * along with this program; if not, see <http://www.gnu.org/licenses/>.
 */

#include "asix.h"

int asix_read_cmd(struct usbnet *dev, u8 cmd, u16 value, u16 index,
		  u16 size, void *data, int in_pm)
{
	int ret;
	int (*fn)(struct usbnet *, u8, u8, u16, u16, void *, u16);

	BUG_ON(!dev);

	if (!in_pm)
		fn = usbnet_read_cmd;
	else
		fn = usbnet_read_cmd_nopm;

	ret = fn(dev, cmd, USB_DIR_IN | USB_TYPE_VENDOR | USB_RECIP_DEVICE,
		 value, index, data, size);

	if (unlikely(ret < 0))
		netdev_warn(dev->net, "Failed to read reg index 0x%04x: %d\n",
			    index, ret);

	return ret;
}

int asix_write_cmd(struct usbnet *dev, u8 cmd, u16 value, u16 index,
		   u16 size, void *data, int in_pm)
{
	int ret;
	int (*fn)(struct usbnet *, u8, u8, u16, u16, const void *, u16);

	BUG_ON(!dev);

	if (!in_pm)
		fn = usbnet_write_cmd;
	else
		fn = usbnet_write_cmd_nopm;

	ret = fn(dev, cmd, USB_DIR_OUT | USB_TYPE_VENDOR | USB_RECIP_DEVICE,
		 value, index, data, size);

	if (unlikely(ret < 0))
		netdev_warn(dev->net, "Failed to write reg index 0x%04x: %d\n",
			    index, ret);

	return ret;
}

void asix_write_cmd_async(struct usbnet *dev, u8 cmd, u16 value, u16 index,
			  u16 size, void *data)
{
	usbnet_write_cmd_async(dev, cmd,
			       USB_DIR_OUT | USB_TYPE_VENDOR | USB_RECIP_DEVICE,
			       value, index, data, size);
}

static void reset_asix_rx_fixup_info(struct asix_rx_fixup_info *rx)
{
	/* Reset the variables that have a lifetime outside of
	 * asix_rx_fixup_internal() so that future processing starts from a
	 * known set of initial conditions.
	 */

	if (rx->ax_skb) {
		/* Discard any incomplete Ethernet frame in the netdev buffer */
		kfree_skb(rx->ax_skb);
		rx->ax_skb = NULL;
	}

	/* Assume the Data header 32-bit word is at the start of the current
	 * or next URB socket buffer so reset all the state variables.
	 */
	rx->remaining = 0;
	rx->split_head = false;
	rx->header = 0;
}

int asix_rx_fixup_internal(struct usbnet *dev, struct sk_buff *skb,
			   struct asix_rx_fixup_info *rx)
{
	int offset = 0;
	u16 size;

	/* When an Ethernet frame spans multiple URB socket buffers,
	 * do a sanity test for the Data header synchronisation.
	 * Attempt to detect the situation of the previous socket buffer having
	 * been truncated or a socket buffer was missing. These situations
	 * cause a discontinuity in the data stream and therefore need to avoid
	 * appending bad data to the end of the current netdev socket buffer.
	 * Also avoid unnecessarily discarding a good current netdev socket
	 * buffer.
	 */
	if (rx->remaining && (rx->remaining + sizeof(u32) <= skb->len)) {
		offset = ((rx->remaining + 1) & 0xfffe);
		rx->header = get_unaligned_le32(skb->data + offset);
		offset = 0;

		size = (u16)(rx->header & 0x7ff);
		if (size != ((~rx->header >> 16) & 0x7ff)) {
			netdev_err(dev->net, "asix_rx_fixup() Data Header synchronisation was lost, remaining %d\n",
				   rx->remaining);
			reset_asix_rx_fixup_info(rx);
		}
	}

	while (offset + sizeof(u16) <= skb->len) {
		u16 copy_length;

		if (!rx->remaining) {
			if (skb->len - offset == sizeof(u16)) {
				rx->header = get_unaligned_le16(
						skb->data + offset);
				rx->split_head = true;
				offset += sizeof(u16);
				break;
			}

			if (rx->split_head == true) {
				rx->header |= (get_unaligned_le16(
						skb->data + offset) << 16);
				rx->split_head = false;
				offset += sizeof(u16);
			} else {
				rx->header = get_unaligned_le32(skb->data +
								offset);
				offset += sizeof(u32);
			}

			/* take frame length from Data header 32-bit word */
			size = (u16)(rx->header & 0x7ff);
			if (size != ((~rx->header >> 16) & 0x7ff)) {
				netdev_err(dev->net, "asix_rx_fixup() Bad Header Length 0x%x, offset %d\n",
					   rx->header, offset);
				reset_asix_rx_fixup_info(rx);
				return 0;
			}
			if (size > dev->net->mtu + ETH_HLEN + VLAN_HLEN) {
				netdev_dbg(dev->net, "asix_rx_fixup() Bad RX Length %d\n",
					   size);
				reset_asix_rx_fixup_info(rx);
				return 0;
			}

			/* Sometimes may fail to get a netdev socket buffer but
			 * continue to process the URB socket buffer so that
			 * synchronisation of the Ethernet frame Data header
			 * word is maintained.
			 */
			rx->ax_skb = netdev_alloc_skb_ip_align(dev->net, size);

			rx->remaining = size;
		}

		if (rx->remaining > skb->len - offset) {
			copy_length = skb->len - offset;
			rx->remaining -= copy_length;
		} else {
			copy_length = rx->remaining;
			rx->remaining = 0;
		}

		if (rx->ax_skb) {
			skb_put_data(rx->ax_skb, skb->data + offset,
				     copy_length);
			if (!rx->remaining) {
				usbnet_skb_return(dev, rx->ax_skb);
				rx->ax_skb = NULL;
			}
		}

		offset += (copy_length + 1) & 0xfffe;
	}

	if (skb->len != offset) {
		netdev_err(dev->net, "asix_rx_fixup() Bad SKB Length %d, %d\n",
			   skb->len, offset);
		reset_asix_rx_fixup_info(rx);
		return 0;
	}

	return 1;
}

int asix_rx_fixup_common(struct usbnet *dev, struct sk_buff *skb)
{
	struct asix_common_private *dp = dev->driver_priv;
	struct asix_rx_fixup_info *rx = &dp->rx_fixup_info;

	return asix_rx_fixup_internal(dev, skb, rx);
}

void asix_rx_fixup_common_free(struct asix_common_private *dp)
{
	struct asix_rx_fixup_info *rx;

	if (!dp)
		return;

	rx = &dp->rx_fixup_info;

	if (rx->ax_skb) {
		kfree_skb(rx->ax_skb);
		rx->ax_skb = NULL;
	}
}

struct sk_buff *asix_tx_fixup(struct usbnet *dev, struct sk_buff *skb,
			      gfp_t flags)
{
	int padlen;
	int headroom = skb_headroom(skb);
	int tailroom = skb_tailroom(skb);
	u32 packet_len;
	u32 padbytes = 0xffff0000;

	padlen = ((skb->len + 4) & (dev->maxpacket - 1)) ? 0 : 4;

	/* We need to push 4 bytes in front of frame (packet_len)
	 * and maybe add 4 bytes after the end (if padlen is 4)
	 *
	 * Avoid skb_copy_expand() expensive call, using following rules :
	 * - We are allowed to push 4 bytes in headroom if skb_header_cloned()
	 *   is false (and if we have 4 bytes of headroom)
	 * - We are allowed to put 4 bytes at tail if skb_cloned()
	 *   is false (and if we have 4 bytes of tailroom)
	 *
	 * TCP packets for example are cloned, but __skb_header_release()
	 * was called in tcp stack, allowing us to use headroom for our needs.
	 */
	if (!skb_header_cloned(skb) &&
	    !(padlen && skb_cloned(skb)) &&
	    headroom + tailroom >= 4 + padlen) {
		/* following should not happen, but better be safe */
		if (headroom < 4 ||
		    tailroom < padlen) {
			skb->data = memmove(skb->head + 4, skb->data, skb->len);
			skb_set_tail_pointer(skb, skb->len);
		}
	} else {
		struct sk_buff *skb2;

		skb2 = skb_copy_expand(skb, 4, padlen, flags);
		dev_kfree_skb_any(skb);
		skb = skb2;
		if (!skb)
			return NULL;
	}

	packet_len = ((skb->len ^ 0x0000ffff) << 16) + skb->len;
	skb_push(skb, 4);
	cpu_to_le32s(&packet_len);
	skb_copy_to_linear_data(skb, &packet_len, sizeof(packet_len));

	if (padlen) {
		cpu_to_le32s(&padbytes);
		memcpy(skb_tail_pointer(skb), &padbytes, sizeof(padbytes));
		skb_put(skb, sizeof(padbytes));
	}

	usbnet_set_skb_tx_stats(skb, 1, 0);
	return skb;
}

int asix_set_sw_mii(struct usbnet *dev, int in_pm)
{
	int ret;
	ret = asix_write_cmd(dev, AX_CMD_SET_SW_MII, 0x0000, 0, 0, NULL, in_pm);

	if (ret < 0)
		netdev_err(dev->net, "Failed to enable software MII access\n");
	return ret;
}

int asix_set_hw_mii(struct usbnet *dev, int in_pm)
{
	int ret;
	ret = asix_write_cmd(dev, AX_CMD_SET_HW_MII, 0x0000, 0, 0, NULL, in_pm);
	if (ret < 0)
		netdev_err(dev->net, "Failed to enable hardware MII access\n");
	return ret;
}

int asix_read_phy_addr(struct usbnet *dev, int internal)
{
	int offset = (internal ? 1 : 0);
	u8 buf[2];
	int ret = asix_read_cmd(dev, AX_CMD_READ_PHY_ID, 0, 0, 2, buf, 0);

	netdev_dbg(dev->net, "asix_get_phy_addr()\n");

	if (ret < 0) {
		netdev_err(dev->net, "Error reading PHYID register: %02x\n", ret);
		goto out;
	}
	netdev_dbg(dev->net, "asix_get_phy_addr() returning 0x%04x\n",
		   *((__le16 *)buf));
	ret = buf[offset];

out:
	return ret;
}

int asix_get_phy_addr(struct usbnet *dev)
{
	/* return the address of the internal phy */
	return asix_read_phy_addr(dev, 1);
}


int asix_sw_reset(struct usbnet *dev, u8 flags, int in_pm)
{
	int ret;

	ret = asix_write_cmd(dev, AX_CMD_SW_RESET, flags, 0, 0, NULL, in_pm);
	if (ret < 0)
		netdev_err(dev->net, "Failed to send software reset: %02x\n", ret);

	return ret;
}

u16 asix_read_rx_ctl(struct usbnet *dev, int in_pm)
{
	__le16 v;
	int ret = asix_read_cmd(dev, AX_CMD_READ_RX_CTL, 0, 0, 2, &v, in_pm);

	if (ret < 0) {
		netdev_err(dev->net, "Error reading RX_CTL register: %02x\n", ret);
		goto out;
	}
	ret = le16_to_cpu(v);
out:
	return ret;
}

int asix_write_rx_ctl(struct usbnet *dev, u16 mode, int in_pm)
{
	int ret;

	netdev_dbg(dev->net, "asix_write_rx_ctl() - mode = 0x%04x\n", mode);
	ret = asix_write_cmd(dev, AX_CMD_WRITE_RX_CTL, mode, 0, 0, NULL, in_pm);
	if (ret < 0)
		netdev_err(dev->net, "Failed to write RX_CTL mode to 0x%04x: %02x\n",
			   mode, ret);

	return ret;
}

u16 asix_read_medium_status(struct usbnet *dev, int in_pm)
{
	__le16 v;
	int ret = asix_read_cmd(dev, AX_CMD_READ_MEDIUM_STATUS,
				0, 0, 2, &v, in_pm);

	if (ret < 0) {
		netdev_err(dev->net, "Error reading Medium Status register: %02x\n",
			   ret);
		return ret;	/* TODO: callers not checking for error ret */
	}

	return le16_to_cpu(v);

}

int asix_write_medium_mode(struct usbnet *dev, u16 mode, int in_pm)
{
	int ret;

	netdev_dbg(dev->net, "asix_write_medium_mode() - mode = 0x%04x\n", mode);
	ret = asix_write_cmd(dev, AX_CMD_WRITE_MEDIUM_MODE,
			     mode, 0, 0, NULL, in_pm);
	if (ret < 0)
		netdev_err(dev->net, "Failed to write Medium Mode mode to 0x%04x: %02x\n",
			   mode, ret);

	return ret;
}

int asix_write_gpio(struct usbnet *dev, u16 value, int sleep, int in_pm)
{
	int ret;

	netdev_dbg(dev->net, "asix_write_gpio() - value = 0x%04x\n", value);
	ret = asix_write_cmd(dev, AX_CMD_WRITE_GPIOS, value, 0, 0, NULL, in_pm);
	if (ret < 0)
		netdev_err(dev->net, "Failed to write GPIO value 0x%04x: %02x\n",
			   value, ret);

	if (sleep)
		msleep(sleep);

	return ret;
}

/*
 * AX88772 & AX88178 have a 16-bit RX_CTL value
 */
void asix_set_multicast(struct net_device *net)
{
	struct usbnet *dev = netdev_priv(net);
	struct asix_data *data = (struct asix_data *)&dev->data;
	u16 rx_ctl = AX_DEFAULT_RX_CTL;

	if (net->flags & IFF_PROMISC) {
		rx_ctl |= AX_RX_CTL_PRO;
	} else if (net->flags & IFF_ALLMULTI ||
		   netdev_mc_count(net) > AX_MAX_MCAST) {
		rx_ctl |= AX_RX_CTL_AMALL;
	} else if (netdev_mc_empty(net)) {
		/* just broadcast and directed */
	} else {
		/* We use the 20 byte dev->data
		 * for our 8 byte filter buffer
		 * to avoid allocating memory that
		 * is tricky to free later */
		struct netdev_hw_addr *ha;
		u32 crc_bits;

		memset(data->multi_filter, 0, AX_MCAST_FILTER_SIZE);

		/* Build the multicast hash filter. */
		netdev_for_each_mc_addr(ha, net) {
			crc_bits = ether_crc(ETH_ALEN, ha->addr) >> 26;
			data->multi_filter[crc_bits >> 3] |=
			    1 << (crc_bits & 7);
		}

		asix_write_cmd_async(dev, AX_CMD_WRITE_MULTI_FILTER, 0, 0,
				   AX_MCAST_FILTER_SIZE, data->multi_filter);

		rx_ctl |= AX_RX_CTL_AM;
	}

	asix_write_cmd_async(dev, AX_CMD_WRITE_RX_CTL, rx_ctl, 0, 0, NULL);
}

int asix_mdio_read(struct net_device *netdev, int phy_id, int loc)
{
	struct usbnet *dev = netdev_priv(netdev);
	__le16 res;
	u8 smsr;
	int i = 0;
	int ret;

	mutex_lock(&dev->phy_mutex);
	do {
		ret = asix_set_sw_mii(dev, 0);
		if (ret == -ENODEV || ret == -ETIMEDOUT)
			break;
		usleep_range(1000, 1100);
		ret = asix_read_cmd(dev, AX_CMD_STATMNGSTS_REG,
				    0, 0, 1, &smsr, 0);
	} while (!(smsr & AX_HOST_EN) && (i++ < 30) && (ret != -ENODEV));
	if (ret == -ENODEV || ret == -ETIMEDOUT) {
		mutex_unlock(&dev->phy_mutex);
		return ret;
	}

	asix_read_cmd(dev, AX_CMD_READ_MII_REG, phy_id,
				(__u16)loc, 2, &res, 0);
	asix_set_hw_mii(dev, 0);
	mutex_unlock(&dev->phy_mutex);

	netdev_dbg(dev->net, "asix_mdio_read() phy_id=0x%02x, loc=0x%02x, returns=0x%04x\n",
			phy_id, loc, le16_to_cpu(res));

	return le16_to_cpu(res);
}

void asix_mdio_write(struct net_device *netdev, int phy_id, int loc, int val)
{
	struct usbnet *dev = netdev_priv(netdev);
	__le16 res = cpu_to_le16(val);
	u8 smsr;
	int i = 0;
	int ret;

	netdev_dbg(dev->net, "asix_mdio_write() phy_id=0x%02x, loc=0x%02x, val=0x%04x\n",
			phy_id, loc, val);

	mutex_lock(&dev->phy_mutex);
	do {
		ret = asix_set_sw_mii(dev, 0);
		if (ret == -ENODEV)
			break;
		usleep_range(1000, 1100);
		ret = asix_read_cmd(dev, AX_CMD_STATMNGSTS_REG,
				    0, 0, 1, &smsr, 0);
	} while (!(smsr & AX_HOST_EN) && (i++ < 30) && (ret != -ENODEV));
	if (ret == -ENODEV) {
		mutex_unlock(&dev->phy_mutex);
		return;
	}

	asix_write_cmd(dev, AX_CMD_WRITE_MII_REG, phy_id,
		       (__u16)loc, 2, &res, 0);
	asix_set_hw_mii(dev, 0);
	mutex_unlock(&dev->phy_mutex);
}

int asix_mdio_read_nopm(struct net_device *netdev, int phy_id, int loc)
{
	struct usbnet *dev = netdev_priv(netdev);
	__le16 res;
	u8 smsr;
	int i = 0;
	int ret;

	mutex_lock(&dev->phy_mutex);
	do {
		ret = asix_set_sw_mii(dev, 1);
		if (ret == -ENODEV || ret == -ETIMEDOUT)
			break;
		usleep_range(1000, 1100);
		ret = asix_read_cmd(dev, AX_CMD_STATMNGSTS_REG,
				    0, 0, 1, &smsr, 1);
	} while (!(smsr & AX_HOST_EN) && (i++ < 30) && (ret != -ENODEV));
	if (ret == -ENODEV || ret == -ETIMEDOUT) {
		mutex_unlock(&dev->phy_mutex);
		return ret;
	}

	asix_read_cmd(dev, AX_CMD_READ_MII_REG, phy_id,
		      (__u16)loc, 2, &res, 1);
	asix_set_hw_mii(dev, 1);
	mutex_unlock(&dev->phy_mutex);

	netdev_dbg(dev->net, "asix_mdio_read_nopm() phy_id=0x%02x, loc=0x%02x, returns=0x%04x\n",
			phy_id, loc, le16_to_cpu(res));

	return le16_to_cpu(res);
}

void
asix_mdio_write_nopm(struct net_device *netdev, int phy_id, int loc, int val)
{
	struct usbnet *dev = netdev_priv(netdev);
	__le16 res = cpu_to_le16(val);
	u8 smsr;
	int i = 0;
	int ret;

	netdev_dbg(dev->net, "asix_mdio_write() phy_id=0x%02x, loc=0x%02x, val=0x%04x\n",
			phy_id, loc, val);

	mutex_lock(&dev->phy_mutex);
	do {
		ret = asix_set_sw_mii(dev, 1);
		if (ret == -ENODEV)
			break;
		usleep_range(1000, 1100);
		ret = asix_read_cmd(dev, AX_CMD_STATMNGSTS_REG,
				    0, 0, 1, &smsr, 1);
	} while (!(smsr & AX_HOST_EN) && (i++ < 30) && (ret != -ENODEV));
	if (ret == -ENODEV) {
		mutex_unlock(&dev->phy_mutex);
		return;
	}

	asix_write_cmd(dev, AX_CMD_WRITE_MII_REG, phy_id,
		       (__u16)loc, 2, &res, 1);
	asix_set_hw_mii(dev, 1);
	mutex_unlock(&dev->phy_mutex);
}

void asix_get_wol(struct net_device *net, struct ethtool_wolinfo *wolinfo)
{
	struct usbnet *dev = netdev_priv(net);
	u8 opt;

	if (asix_read_cmd(dev, AX_CMD_READ_MONITOR_MODE,
			  0, 0, 1, &opt, 0) < 0) {
		wolinfo->supported = 0;
		wolinfo->wolopts = 0;
		return;
	}
	wolinfo->supported = WAKE_PHY | WAKE_MAGIC;
	wolinfo->wolopts = 0;
	if (opt & AX_MONITOR_LINK)
		wolinfo->wolopts |= WAKE_PHY;
	if (opt & AX_MONITOR_MAGIC)
		wolinfo->wolopts |= WAKE_MAGIC;
}

int asix_set_wol(struct net_device *net, struct ethtool_wolinfo *wolinfo)
{
	struct usbnet *dev = netdev_priv(net);
	u8 opt = 0;

	if (wolinfo->wolopts & WAKE_PHY)
		opt |= AX_MONITOR_LINK;
	if (wolinfo->wolopts & WAKE_MAGIC)
		opt |= AX_MONITOR_MAGIC;

	if (asix_write_cmd(dev, AX_CMD_WRITE_MONITOR_MODE,
			      opt, 0, 0, NULL, 0) < 0)
		return -EINVAL;

	return 0;
}

int asix_get_eeprom_len(struct net_device *net)
{
	return AX_EEPROM_LEN;
}

int asix_get_eeprom(struct net_device *net, struct ethtool_eeprom *eeprom,
		    u8 *data)
{
	struct usbnet *dev = netdev_priv(net);
	u16 *eeprom_buff;
	int first_word, last_word;
	int i;

	if (eeprom->len == 0)
		return -EINVAL;

	eeprom->magic = AX_EEPROM_MAGIC;

	first_word = eeprom->offset >> 1;
	last_word = (eeprom->offset + eeprom->len - 1) >> 1;

	eeprom_buff = kmalloc_array(last_word - first_word + 1, sizeof(u16),
				    GFP_KERNEL);
	if (!eeprom_buff)
		return -ENOMEM;

	/* ax8817x returns 2 bytes from eeprom on read */
	for (i = first_word; i <= last_word; i++) {
		if (asix_read_cmd(dev, AX_CMD_READ_EEPROM, i, 0, 2,
				  &eeprom_buff[i - first_word], 0) < 0) {
			kfree(eeprom_buff);
			return -EIO;
		}
	}

	memcpy(data, (u8 *)eeprom_buff + (eeprom->offset & 1), eeprom->len);
	kfree(eeprom_buff);
	return 0;
}

int asix_set_eeprom(struct net_device *net, struct ethtool_eeprom *eeprom,
		    u8 *data)
{
	struct usbnet *dev = netdev_priv(net);
	u16 *eeprom_buff;
	int first_word, last_word;
	int i;
	int ret;

	netdev_dbg(net, "write EEPROM len %d, offset %d, magic 0x%x\n",
		   eeprom->len, eeprom->offset, eeprom->magic);

	if (eeprom->len == 0)
		return -EINVAL;

	if (eeprom->magic != AX_EEPROM_MAGIC)
		return -EINVAL;

	first_word = eeprom->offset >> 1;
	last_word = (eeprom->offset + eeprom->len - 1) >> 1;

	eeprom_buff = kmalloc_array(last_word - first_word + 1, sizeof(u16),
				    GFP_KERNEL);
	if (!eeprom_buff)
		return -ENOMEM;

	/* align data to 16 bit boundaries, read the missing data from
	   the EEPROM */
	if (eeprom->offset & 1) {
		ret = asix_read_cmd(dev, AX_CMD_READ_EEPROM, first_word, 0, 2,
				    &eeprom_buff[0], 0);
		if (ret < 0) {
			netdev_err(net, "Failed to read EEPROM at offset 0x%02x.\n", first_word);
			goto free;
		}
	}

	if ((eeprom->offset + eeprom->len) & 1) {
		ret = asix_read_cmd(dev, AX_CMD_READ_EEPROM, last_word, 0, 2,
				    &eeprom_buff[last_word - first_word], 0);
		if (ret < 0) {
			netdev_err(net, "Failed to read EEPROM at offset 0x%02x.\n", last_word);
			goto free;
		}
	}

	memcpy((u8 *)eeprom_buff + (eeprom->offset & 1), data, eeprom->len);

	/* write data to EEPROM */
	ret = asix_write_cmd(dev, AX_CMD_WRITE_ENABLE, 0x0000, 0, 0, NULL, 0);
	if (ret < 0) {
		netdev_err(net, "Failed to enable EEPROM write\n");
		goto free;
	}
	msleep(20);

	for (i = first_word; i <= last_word; i++) {
		netdev_dbg(net, "write to EEPROM at offset 0x%02x, data 0x%04x\n",
			   i, eeprom_buff[i - first_word]);
		ret = asix_write_cmd(dev, AX_CMD_WRITE_EEPROM, i,
				     eeprom_buff[i - first_word], 0, NULL, 0);
		if (ret < 0) {
			netdev_err(net, "Failed to write EEPROM at offset 0x%02x.\n",
				   i);
			goto free;
		}
		msleep(20);
	}

	ret = asix_write_cmd(dev, AX_CMD_WRITE_DISABLE, 0x0000, 0, 0, NULL, 0);
	if (ret < 0) {
		netdev_err(net, "Failed to disable EEPROM write\n");
		goto free;
	}

	ret = 0;
free:
	kfree(eeprom_buff);
	return ret;
}

void asix_get_drvinfo(struct net_device *net, struct ethtool_drvinfo *info)
{
	/* Inherit standard device info */
	usbnet_get_drvinfo(net, info);
	strlcpy(info->driver, DRIVER_NAME, sizeof(info->driver));
	strlcpy(info->version, DRIVER_VERSION, sizeof(info->version));
}

int asix_set_mac_address(struct net_device *net, void *p)
{
	struct usbnet *dev = netdev_priv(net);
	struct asix_data *data = (struct asix_data *)&dev->data;
	struct sockaddr *addr = p;

	if (netif_running(net))
		return -EBUSY;
	if (!is_valid_ether_addr(addr->sa_data))
		return -EADDRNOTAVAIL;

	memcpy(net->dev_addr, addr->sa_data, ETH_ALEN);

	/* We use the 20 byte dev->data
	 * for our 6 byte mac buffer
	 * to avoid allocating memory that
	 * is tricky to free later */
	memcpy(data->mac_addr, addr->sa_data, ETH_ALEN);
	asix_write_cmd_async(dev, AX_CMD_WRITE_NODE_ID, 0, 0, ETH_ALEN,
							data->mac_addr);

	return 0;
}
18'>3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318
/*
 *  CFQ, or complete fairness queueing, disk scheduler.
 *
 *  Based on ideas from a previously unfinished io
 *  scheduler (round robin per-process disk scheduling) and Andrea Arcangeli.
 *
 *  Copyright (C) 2003 Jens Axboe <axboe@kernel.dk>
 */
#include <linux/module.h>
#include <linux/slab.h>
#include <linux/blkdev.h>
#include <linux/elevator.h>
#include <linux/jiffies.h>
#include <linux/rbtree.h>
#include <linux/ioprio.h>
#include <linux/blktrace_api.h>
#include "cfq.h"

/*
 * tunables
 */
/* max queue in one round of service */
static const int cfq_quantum = 8;
static const int cfq_fifo_expire[2] = { HZ / 4, HZ / 8 };
/* maximum backwards seek, in KiB */
static const int cfq_back_max = 16 * 1024;
/* penalty of a backwards seek */
static const int cfq_back_penalty = 2;
static const int cfq_slice_sync = HZ / 10;
static int cfq_slice_async = HZ / 25;
static const int cfq_slice_async_rq = 2;
static int cfq_slice_idle = HZ / 125;
static int cfq_group_idle = HZ / 125;
static const int cfq_target_latency = HZ * 3/10; /* 300 ms */
static const int cfq_hist_divisor = 4;

/*
 * offset from end of service tree
 */
#define CFQ_IDLE_DELAY		(HZ / 5)

/*
 * below this threshold, we consider thinktime immediate
 */
#define CFQ_MIN_TT		(2)

#define CFQ_SLICE_SCALE		(5)
#define CFQ_HW_QUEUE_MIN	(5)
#define CFQ_SERVICE_SHIFT       12

#define CFQQ_SEEK_THR		(sector_t)(8 * 100)
#define CFQQ_CLOSE_THR		(sector_t)(8 * 1024)
#define CFQQ_SECT_THR_NONROT	(sector_t)(2 * 32)
#define CFQQ_SEEKY(cfqq)	(hweight32(cfqq->seek_history) > 32/8)

#define RQ_CIC(rq)		\
	((struct cfq_io_context *) (rq)->elevator_private[0])
#define RQ_CFQQ(rq)		(struct cfq_queue *) ((rq)->elevator_private[1])
#define RQ_CFQG(rq)		(struct cfq_group *) ((rq)->elevator_private[2])

static struct kmem_cache *cfq_pool;
static struct kmem_cache *cfq_ioc_pool;

static DEFINE_PER_CPU(unsigned long, cfq_ioc_count);
static struct completion *ioc_gone;
static DEFINE_SPINLOCK(ioc_gone_lock);

static DEFINE_SPINLOCK(cic_index_lock);
static DEFINE_IDA(cic_index_ida);

#define CFQ_PRIO_LISTS		IOPRIO_BE_NR
#define cfq_class_idle(cfqq)	((cfqq)->ioprio_class == IOPRIO_CLASS_IDLE)
#define cfq_class_rt(cfqq)	((cfqq)->ioprio_class == IOPRIO_CLASS_RT)

#define sample_valid(samples)	((samples) > 80)
#define rb_entry_cfqg(node)	rb_entry((node), struct cfq_group, rb_node)

/*
 * Most of our rbtree usage is for sorting with min extraction, so
 * if we cache the leftmost node we don't have to walk down the tree
 * to find it. Idea borrowed from Ingo Molnars CFS scheduler. We should
 * move this into the elevator for the rq sorting as well.
 */
struct cfq_rb_root {
	struct rb_root rb;
	struct rb_node *left;
	unsigned count;
	unsigned total_weight;
	u64 min_vdisktime;
	struct cfq_ttime ttime;
};
#define CFQ_RB_ROOT	(struct cfq_rb_root) { .rb = RB_ROOT, \
			.ttime = {.last_end_request = jiffies,},}

/*
 * Per process-grouping structure
 */
struct cfq_queue {
	/* reference count */
	int ref;
	/* various state flags, see below */
	unsigned int flags;
	/* parent cfq_data */
	struct cfq_data *cfqd;
	/* service_tree member */
	struct rb_node rb_node;
	/* service_tree key */
	unsigned long rb_key;
	/* prio tree member */
	struct rb_node p_node;
	/* prio tree root we belong to, if any */
	struct rb_root *p_root;
	/* sorted list of pending requests */
	struct rb_root sort_list;
	/* if fifo isn't expired, next request to serve */
	struct request *next_rq;
	/* requests queued in sort_list */
	int queued[2];
	/* currently allocated requests */
	int allocated[2];
	/* fifo list of requests in sort_list */
	struct list_head fifo;

	/* time when queue got scheduled in to dispatch first request. */
	unsigned long dispatch_start;
	unsigned int allocated_slice;
	unsigned int slice_dispatch;
	/* time when first request from queue completed and slice started. */
	unsigned long slice_start;
	unsigned long slice_end;
	long slice_resid;

	/* pending priority requests */
	int prio_pending;
	/* number of requests that are on the dispatch list or inside driver */
	int dispatched;

	/* io prio of this group */
	unsigned short ioprio, org_ioprio;
	unsigned short ioprio_class;

	pid_t pid;

	u32 seek_history;
	sector_t last_request_pos;

	struct cfq_rb_root *service_tree;
	struct cfq_queue *new_cfqq;
	struct cfq_group *cfqg;
	/* Number of sectors dispatched from queue in single dispatch round */
	unsigned long nr_sectors;
};

/*
 * First index in the service_trees.
 * IDLE is handled separately, so it has negative index
 */
enum wl_prio_t {
	BE_WORKLOAD = 0,
	RT_WORKLOAD = 1,
	IDLE_WORKLOAD = 2,
	CFQ_PRIO_NR,
};

/*
 * Second index in the service_trees.
 */
enum wl_type_t {
	ASYNC_WORKLOAD = 0,
	SYNC_NOIDLE_WORKLOAD = 1,
	SYNC_WORKLOAD = 2
};

/* This is per cgroup per device grouping structure */
struct cfq_group {
	/* group service_tree member */
	struct rb_node rb_node;

	/* group service_tree key */
	u64 vdisktime;
	unsigned int weight;
	unsigned int new_weight;
	bool needs_update;

	/* number of cfqq currently on this group */
	int nr_cfqq;

	/*
	 * Per group busy queues average. Useful for workload slice calc. We
	 * create the array for each prio class but at run time it is used
	 * only for RT and BE class and slot for IDLE class remains unused.
	 * This is primarily done to avoid confusion and a gcc warning.
	 */
	unsigned int busy_queues_avg[CFQ_PRIO_NR];
	/*
	 * rr lists of queues with requests. We maintain service trees for
	 * RT and BE classes. These trees are subdivided in subclasses
	 * of SYNC, SYNC_NOIDLE and ASYNC based on workload type. For IDLE
	 * class there is no subclassification and all the cfq queues go on
	 * a single tree service_tree_idle.
	 * Counts are embedded in the cfq_rb_root
	 */
	struct cfq_rb_root service_trees[2][3];
	struct cfq_rb_root service_tree_idle;

	unsigned long saved_workload_slice;
	enum wl_type_t saved_workload;
	enum wl_prio_t saved_serving_prio;
	struct blkio_group blkg;
#ifdef CONFIG_CFQ_GROUP_IOSCHED
	struct hlist_node cfqd_node;
	int ref;
#endif
	/* number of requests that are on the dispatch list or inside driver */
	int dispatched;
	struct cfq_ttime ttime;
};

/*
 * Per block device queue structure
 */
struct cfq_data {
	struct request_queue *queue;
	/* Root service tree for cfq_groups */
	struct cfq_rb_root grp_service_tree;
	struct cfq_group root_group;

	/*
	 * The priority currently being served
	 */
	enum wl_prio_t serving_prio;
	enum wl_type_t serving_type;
	unsigned long workload_expires;
	struct cfq_group *serving_group;

	/*
	 * Each priority tree is sorted by next_request position.  These
	 * trees are used when determining if two or more queues are
	 * interleaving requests (see cfq_close_cooperator).
	 */
	struct rb_root prio_trees[CFQ_PRIO_LISTS];

	unsigned int busy_queues;
	unsigned int busy_sync_queues;

	int rq_in_driver;
	int rq_in_flight[2];

	/*
	 * queue-depth detection
	 */
	int rq_queued;
	int hw_tag;
	/*
	 * hw_tag can be
	 * -1 => indeterminate, (cfq will behave as if NCQ is present, to allow better detection)
	 *  1 => NCQ is present (hw_tag_est_depth is the estimated max depth)
	 *  0 => no NCQ
	 */
	int hw_tag_est_depth;
	unsigned int hw_tag_samples;

	/*
	 * idle window management
	 */
	struct timer_list idle_slice_timer;
	struct work_struct unplug_work;

	struct cfq_queue *active_queue;
	struct cfq_io_context *active_cic;

	/*
	 * async queue for each priority case
	 */
	struct cfq_queue *async_cfqq[2][IOPRIO_BE_NR];
	struct cfq_queue *async_idle_cfqq;

	sector_t last_position;

	/*
	 * tunables, see top of file
	 */
	unsigned int cfq_quantum;
	unsigned int cfq_fifo_expire[2];
	unsigned int cfq_back_penalty;
	unsigned int cfq_back_max;
	unsigned int cfq_slice[2];
	unsigned int cfq_slice_async_rq;
	unsigned int cfq_slice_idle;
	unsigned int cfq_group_idle;
	unsigned int cfq_latency;

	unsigned int cic_index;
	struct list_head cic_list;

	/*
	 * Fallback dummy cfqq for extreme OOM conditions
	 */
	struct cfq_queue oom_cfqq;

	unsigned long last_delayed_sync;

	/* List of cfq groups being managed on this device*/
	struct hlist_head cfqg_list;

	/* Number of groups which are on blkcg->blkg_list */
	unsigned int nr_blkcg_linked_grps;
};

static struct cfq_group *cfq_get_next_cfqg(struct cfq_data *cfqd);

static struct cfq_rb_root *service_tree_for(struct cfq_group *cfqg,
					    enum wl_prio_t prio,
					    enum wl_type_t type)
{
	if (!cfqg)
		return NULL;

	if (prio == IDLE_WORKLOAD)
		return &cfqg->service_tree_idle;

	return &cfqg->service_trees[prio][type];
}

enum cfqq_state_flags {
	CFQ_CFQQ_FLAG_on_rr = 0,	/* on round-robin busy list */
	CFQ_CFQQ_FLAG_wait_request,	/* waiting for a request */
	CFQ_CFQQ_FLAG_must_dispatch,	/* must be allowed a dispatch */
	CFQ_CFQQ_FLAG_must_alloc_slice,	/* per-slice must_alloc flag */
	CFQ_CFQQ_FLAG_fifo_expire,	/* FIFO checked in this slice */
	CFQ_CFQQ_FLAG_idle_window,	/* slice idling enabled */
	CFQ_CFQQ_FLAG_prio_changed,	/* task priority has changed */
	CFQ_CFQQ_FLAG_slice_new,	/* no requests dispatched in slice */
	CFQ_CFQQ_FLAG_sync,		/* synchronous queue */
	CFQ_CFQQ_FLAG_coop,		/* cfqq is shared */
	CFQ_CFQQ_FLAG_split_coop,	/* shared cfqq will be splitted */
	CFQ_CFQQ_FLAG_deep,		/* sync cfqq experienced large depth */
	CFQ_CFQQ_FLAG_wait_busy,	/* Waiting for next request */
};

#define CFQ_CFQQ_FNS(name)						\
static inline void cfq_mark_cfqq_##name(struct cfq_queue *cfqq)		\
{									\
	(cfqq)->flags |= (1 << CFQ_CFQQ_FLAG_##name);			\
}									\
static inline void cfq_clear_cfqq_##name(struct cfq_queue *cfqq)	\
{									\
	(cfqq)->flags &= ~(1 << CFQ_CFQQ_FLAG_##name);			\
}									\
static inline int cfq_cfqq_##name(const struct cfq_queue *cfqq)		\
{									\
	return ((cfqq)->flags & (1 << CFQ_CFQQ_FLAG_##name)) != 0;	\
}

CFQ_CFQQ_FNS(on_rr);
CFQ_CFQQ_FNS(wait_request);
CFQ_CFQQ_FNS(must_dispatch);
CFQ_CFQQ_FNS(must_alloc_slice);
CFQ_CFQQ_FNS(fifo_expire);
CFQ_CFQQ_FNS(idle_window);
CFQ_CFQQ_FNS(prio_changed);
CFQ_CFQQ_FNS(slice_new);
CFQ_CFQQ_FNS(sync);
CFQ_CFQQ_FNS(coop);
CFQ_CFQQ_FNS(split_coop);
CFQ_CFQQ_FNS(deep);
CFQ_CFQQ_FNS(wait_busy);
#undef CFQ_CFQQ_FNS

#ifdef CONFIG_CFQ_GROUP_IOSCHED
#define cfq_log_cfqq(cfqd, cfqq, fmt, args...)	\
	blk_add_trace_msg((cfqd)->queue, "cfq%d%c %s " fmt, (cfqq)->pid, \
			cfq_cfqq_sync((cfqq)) ? 'S' : 'A', \
			blkg_path(&(cfqq)->cfqg->blkg), ##args)

#define cfq_log_cfqg(cfqd, cfqg, fmt, args...)				\
	blk_add_trace_msg((cfqd)->queue, "%s " fmt,			\
				blkg_path(&(cfqg)->blkg), ##args)       \

#else
#define cfq_log_cfqq(cfqd, cfqq, fmt, args...)	\
	blk_add_trace_msg((cfqd)->queue, "cfq%d " fmt, (cfqq)->pid, ##args)
#define cfq_log_cfqg(cfqd, cfqg, fmt, args...)		do {} while (0)
#endif
#define cfq_log(cfqd, fmt, args...)	\
	blk_add_trace_msg((cfqd)->queue, "cfq " fmt, ##args)

/* Traverses through cfq group service trees */
#define for_each_cfqg_st(cfqg, i, j, st) \
	for (i = 0; i <= IDLE_WORKLOAD; i++) \
		for (j = 0, st = i < IDLE_WORKLOAD ? &cfqg->service_trees[i][j]\
			: &cfqg->service_tree_idle; \
			(i < IDLE_WORKLOAD && j <= SYNC_WORKLOAD) || \
			(i == IDLE_WORKLOAD && j == 0); \
			j++, st = i < IDLE_WORKLOAD ? \
			&cfqg->service_trees[i][j]: NULL) \

static inline bool cfq_io_thinktime_big(struct cfq_data *cfqd,
	struct cfq_ttime *ttime, bool group_idle)
{
	unsigned long slice;
	if (!sample_valid(ttime->ttime_samples))
		return false;
	if (group_idle)
		slice = cfqd->cfq_group_idle;
	else
		slice = cfqd->cfq_slice_idle;
	return ttime->ttime_mean > slice;
}

static inline bool iops_mode(struct cfq_data *cfqd)
{
	/*
	 * If we are not idling on queues and it is a NCQ drive, parallel
	 * execution of requests is on and measuring time is not possible
	 * in most of the cases until and unless we drive shallower queue
	 * depths and that becomes a performance bottleneck. In such cases
	 * switch to start providing fairness in terms of number of IOs.
	 */
	if (!cfqd->cfq_slice_idle && cfqd->hw_tag)
		return true;
	else
		return false;
}

static inline enum wl_prio_t cfqq_prio(struct cfq_queue *cfqq)
{
	if (cfq_class_idle(cfqq))
		return IDLE_WORKLOAD;
	if (cfq_class_rt(cfqq))
		return RT_WORKLOAD;
	return BE_WORKLOAD;
}


static enum wl_type_t cfqq_type(struct cfq_queue *cfqq)
{
	if (!cfq_cfqq_sync(cfqq))
		return ASYNC_WORKLOAD;
	if (!cfq_cfqq_idle_window(cfqq))
		return SYNC_NOIDLE_WORKLOAD;
	return SYNC_WORKLOAD;
}

static inline int cfq_group_busy_queues_wl(enum wl_prio_t wl,
					struct cfq_data *cfqd,
					struct cfq_group *cfqg)
{
	if (wl == IDLE_WORKLOAD)
		return cfqg->service_tree_idle.count;

	return cfqg->service_trees[wl][ASYNC_WORKLOAD].count
		+ cfqg->service_trees[wl][SYNC_NOIDLE_WORKLOAD].count
		+ cfqg->service_trees[wl][SYNC_WORKLOAD].count;
}

static inline int cfqg_busy_async_queues(struct cfq_data *cfqd,
					struct cfq_group *cfqg)
{
	return cfqg->service_trees[RT_WORKLOAD][ASYNC_WORKLOAD].count
		+ cfqg->service_trees[BE_WORKLOAD][ASYNC_WORKLOAD].count;
}

static void cfq_dispatch_insert(struct request_queue *, struct request *);
static struct cfq_queue *cfq_get_queue(struct cfq_data *, bool,
				       struct io_context *, gfp_t);
static struct cfq_io_context *cfq_cic_lookup(struct cfq_data *,
						struct io_context *);

static inline struct cfq_queue *cic_to_cfqq(struct cfq_io_context *cic,
					    bool is_sync)
{
	return cic->cfqq[is_sync];
}

static inline void cic_set_cfqq(struct cfq_io_context *cic,
				struct cfq_queue *cfqq, bool is_sync)
{
	cic->cfqq[is_sync] = cfqq;
}

#define CIC_DEAD_KEY	1ul
#define CIC_DEAD_INDEX_SHIFT	1

static inline void *cfqd_dead_key(struct cfq_data *cfqd)
{
	return (void *)(cfqd->cic_index << CIC_DEAD_INDEX_SHIFT | CIC_DEAD_KEY);
}

static inline struct cfq_data *cic_to_cfqd(struct cfq_io_context *cic)
{
	struct cfq_data *cfqd = cic->key;

	if (unlikely((unsigned long) cfqd & CIC_DEAD_KEY))
		return NULL;

	return cfqd;
}

/*
 * We regard a request as SYNC, if it's either a read or has the SYNC bit
 * set (in which case it could also be direct WRITE).
 */
static inline bool cfq_bio_sync(struct bio *bio)
{
	return bio_data_dir(bio) == READ || (bio->bi_rw & REQ_SYNC);
}

/*
 * scheduler run of queue, if there are requests pending and no one in the
 * driver that will restart queueing
 */
static inline void cfq_schedule_dispatch(struct cfq_data *cfqd)
{
	if (cfqd->busy_queues) {
		cfq_log(cfqd, "schedule dispatch");
		kblockd_schedule_work(cfqd->queue, &cfqd->unplug_work);
	}
}

/*
 * Scale schedule slice based on io priority. Use the sync time slice only
 * if a queue is marked sync and has sync io queued. A sync queue with async
 * io only, should not get full sync slice length.
 */
static inline int cfq_prio_slice(struct cfq_data *cfqd, bool sync,
				 unsigned short prio)
{
	const int base_slice = cfqd->cfq_slice[sync];

	WARN_ON(prio >= IOPRIO_BE_NR);

	return base_slice + (base_slice/CFQ_SLICE_SCALE * (4 - prio));
}

static inline int
cfq_prio_to_slice(struct cfq_data *cfqd, struct cfq_queue *cfqq)
{
	return cfq_prio_slice(cfqd, cfq_cfqq_sync(cfqq), cfqq->ioprio);
}

static inline u64 cfq_scale_slice(unsigned long delta, struct cfq_group *cfqg)
{
	u64 d = delta << CFQ_SERVICE_SHIFT;

	d = d * BLKIO_WEIGHT_DEFAULT;
	do_div(d, cfqg->weight);
	return d;
}

static inline u64 max_vdisktime(u64 min_vdisktime, u64 vdisktime)
{
	s64 delta = (s64)(vdisktime - min_vdisktime);
	if (delta > 0)
		min_vdisktime = vdisktime;

	return min_vdisktime;
}

static inline u64 min_vdisktime(u64 min_vdisktime, u64 vdisktime)
{
	s64 delta = (s64)(vdisktime - min_vdisktime);
	if (delta < 0)
		min_vdisktime = vdisktime;

	return min_vdisktime;
}

static void update_min_vdisktime(struct cfq_rb_root *st)
{
	struct cfq_group *cfqg;

	if (st->left) {
		cfqg = rb_entry_cfqg(st->left);
		st->min_vdisktime = max_vdisktime(st->min_vdisktime,
						  cfqg->vdisktime);
	}
}

/*
 * get averaged number of queues of RT/BE priority.
 * average is updated, with a formula that gives more weight to higher numbers,
 * to quickly follows sudden increases and decrease slowly
 */

static inline unsigned cfq_group_get_avg_queues(struct cfq_data *cfqd,
					struct cfq_group *cfqg, bool rt)
{
	unsigned min_q, max_q;
	unsigned mult  = cfq_hist_divisor - 1;
	unsigned round = cfq_hist_divisor / 2;
	unsigned busy = cfq_group_busy_queues_wl(rt, cfqd, cfqg);

	min_q = min(cfqg->busy_queues_avg[rt], busy);
	max_q = max(cfqg->busy_queues_avg[rt], busy);
	cfqg->busy_queues_avg[rt] = (mult * max_q + min_q + round) /
		cfq_hist_divisor;
	return cfqg->busy_queues_avg[rt];
}

static inline unsigned
cfq_group_slice(struct cfq_data *cfqd, struct cfq_group *cfqg)
{
	struct cfq_rb_root *st = &cfqd->grp_service_tree;

	return cfq_target_latency * cfqg->weight / st->total_weight;
}

static inline unsigned
cfq_scaled_cfqq_slice(struct cfq_data *cfqd, struct cfq_queue *cfqq)
{
	unsigned slice = cfq_prio_to_slice(cfqd, cfqq);
	if (cfqd->cfq_latency) {
		/*
		 * interested queues (we consider only the ones with the same
		 * priority class in the cfq group)
		 */
		unsigned iq = cfq_group_get_avg_queues(cfqd, cfqq->cfqg,
						cfq_class_rt(cfqq));
		unsigned sync_slice = cfqd->cfq_slice[1];
		unsigned expect_latency = sync_slice * iq;
		unsigned group_slice = cfq_group_slice(cfqd, cfqq->cfqg);

		if (expect_latency > group_slice) {
			unsigned base_low_slice = 2 * cfqd->cfq_slice_idle;
			/* scale low_slice according to IO priority
			 * and sync vs async */
			unsigned low_slice =
				min(slice, base_low_slice * slice / sync_slice);
			/* the adapted slice value is scaled to fit all iqs
			 * into the target latency */
			slice = max(slice * group_slice / expect_latency,
				    low_slice);
		}
	}
	return slice;
}

static inline void
cfq_set_prio_slice(struct cfq_data *cfqd, struct cfq_queue *cfqq)
{
	unsigned slice = cfq_scaled_cfqq_slice(cfqd, cfqq);

	cfqq->slice_start = jiffies;
	cfqq->slice_end = jiffies + slice;
	cfqq->allocated_slice = slice;
	cfq_log_cfqq(cfqd, cfqq, "set_slice=%lu", cfqq->slice_end - jiffies);
}

/*
 * We need to wrap this check in cfq_cfqq_slice_new(), since ->slice_end
 * isn't valid until the first request from the dispatch is activated
 * and the slice time set.
 */
static inline bool cfq_slice_used(struct cfq_queue *cfqq)
{
	if (cfq_cfqq_slice_new(cfqq))
		return false;
	if (time_before(jiffies, cfqq->slice_end))
		return false;

	return true;
}

/*
 * Lifted from AS - choose which of rq1 and rq2 that is best served now.
 * We choose the request that is closest to the head right now. Distance
 * behind the head is penalized and only allowed to a certain extent.
 */
static struct request *
cfq_choose_req(struct cfq_data *cfqd, struct request *rq1, struct request *rq2, sector_t last)
{
	sector_t s1, s2, d1 = 0, d2 = 0;
	unsigned long back_max;
#define CFQ_RQ1_WRAP	0x01 /* request 1 wraps */
#define CFQ_RQ2_WRAP	0x02 /* request 2 wraps */
	unsigned wrap = 0; /* bit mask: requests behind the disk head? */

	if (rq1 == NULL || rq1 == rq2)
		return rq2;
	if (rq2 == NULL)
		return rq1;

	if (rq_is_sync(rq1) != rq_is_sync(rq2))
		return rq_is_sync(rq1) ? rq1 : rq2;

	if ((rq1->cmd_flags ^ rq2->cmd_flags) & REQ_PRIO)
		return rq1->cmd_flags & REQ_PRIO ? rq1 : rq2;

	s1 = blk_rq_pos(rq1);
	s2 = blk_rq_pos(rq2);

	/*
	 * by definition, 1KiB is 2 sectors
	 */
	back_max = cfqd->cfq_back_max * 2;

	/*
	 * Strict one way elevator _except_ in the case where we allow
	 * short backward seeks which are biased as twice the cost of a
	 * similar forward seek.
	 */
	if (s1 >= last)
		d1 = s1 - last;
	else if (s1 + back_max >= last)
		d1 = (last - s1) * cfqd->cfq_back_penalty;
	else
		wrap |= CFQ_RQ1_WRAP;

	if (s2 >= last)
		d2 = s2 - last;
	else if (s2 + back_max >= last)
		d2 = (last - s2) * cfqd->cfq_back_penalty;
	else
		wrap |= CFQ_RQ2_WRAP;

	/* Found required data */

	/*
	 * By doing switch() on the bit mask "wrap" we avoid having to
	 * check two variables for all permutations: --> faster!
	 */
	switch (wrap) {
	case 0: /* common case for CFQ: rq1 and rq2 not wrapped */
		if (d1 < d2)
			return rq1;
		else if (d2 < d1)
			return rq2;
		else {
			if (s1 >= s2)
				return rq1;
			else
				return rq2;
		}

	case CFQ_RQ2_WRAP:
		return rq1;
	case CFQ_RQ1_WRAP:
		return rq2;
	case (CFQ_RQ1_WRAP|CFQ_RQ2_WRAP): /* both rqs wrapped */
	default:
		/*
		 * Since both rqs are wrapped,
		 * start with the one that's further behind head
		 * (--> only *one* back seek required),
		 * since back seek takes more time than forward.
		 */
		if (s1 <= s2)
			return rq1;
		else
			return rq2;
	}
}

/*
 * The below is leftmost cache rbtree addon
 */
static struct cfq_queue *cfq_rb_first(struct cfq_rb_root *root)
{
	/* Service tree is empty */
	if (!root->count)
		return NULL;

	if (!root->left)
		root->left = rb_first(&root->rb);

	if (root->left)
		return rb_entry(root->left, struct cfq_queue, rb_node);

	return NULL;
}

static struct cfq_group *cfq_rb_first_group(struct cfq_rb_root *root)
{
	if (!root->left)
		root->left = rb_first(&root->rb);

	if (root->left)
		return rb_entry_cfqg(root->left);

	return NULL;
}

static void rb_erase_init(struct rb_node *n, struct rb_root *root)
{
	rb_erase(n, root);
	RB_CLEAR_NODE(n);
}

static void cfq_rb_erase(struct rb_node *n, struct cfq_rb_root *root)
{
	if (root->left == n)
		root->left = NULL;
	rb_erase_init(n, &root->rb);
	--root->count;
}

/*
 * would be nice to take fifo expire time into account as well
 */
static struct request *
cfq_find_next_rq(struct cfq_data *cfqd, struct cfq_queue *cfqq,
		  struct request *last)
{
	struct rb_node *rbnext = rb_next(&last->rb_node);
	struct rb_node *rbprev = rb_prev(&last->rb_node);
	struct request *next = NULL, *prev = NULL;

	BUG_ON(RB_EMPTY_NODE(&last->rb_node));

	if (rbprev)
		prev = rb_entry_rq(rbprev);

	if (rbnext)
		next = rb_entry_rq(rbnext);
	else {
		rbnext = rb_first(&cfqq->sort_list);
		if (rbnext && rbnext != &last->rb_node)
			next = rb_entry_rq(rbnext);
	}

	return cfq_choose_req(cfqd, next, prev, blk_rq_pos(last));
}

static unsigned long cfq_slice_offset(struct cfq_data *cfqd,
				      struct cfq_queue *cfqq)
{
	/*
	 * just an approximation, should be ok.
	 */
	return (cfqq->cfqg->nr_cfqq - 1) * (cfq_prio_slice(cfqd, 1, 0) -
		       cfq_prio_slice(cfqd, cfq_cfqq_sync(cfqq), cfqq->ioprio));
}

static inline s64
cfqg_key(struct cfq_rb_root *st, struct cfq_group *cfqg)
{
	return cfqg->vdisktime - st->min_vdisktime;
}

static void
__cfq_group_service_tree_add(struct cfq_rb_root *st, struct cfq_group *cfqg)
{
	struct rb_node **node = &st->rb.rb_node;
	struct rb_node *parent = NULL;
	struct cfq_group *__cfqg;
	s64 key = cfqg_key(st, cfqg);
	int left = 1;

	while (*node != NULL) {
		parent = *node;
		__cfqg = rb_entry_cfqg(parent);

		if (key < cfqg_key(st, __cfqg))
			node = &parent->rb_left;
		else {
			node = &parent->rb_right;
			left = 0;
		}
	}

	if (left)
		st->left = &cfqg->rb_node;

	rb_link_node(&cfqg->rb_node, parent, node);
	rb_insert_color(&cfqg->rb_node, &st->rb);
}

static void
cfq_update_group_weight(struct cfq_group *cfqg)
{
	BUG_ON(!RB_EMPTY_NODE(&cfqg->rb_node));
	if (cfqg->needs_update) {
		cfqg->weight = cfqg->new_weight;
		cfqg->needs_update = false;
	}
}

static void
cfq_group_service_tree_add(struct cfq_rb_root *st, struct cfq_group *cfqg)
{
	BUG_ON(!RB_EMPTY_NODE(&cfqg->rb_node));

	cfq_update_group_weight(cfqg);
	__cfq_group_service_tree_add(st, cfqg);
	st->total_weight += cfqg->weight;
}

static void
cfq_group_notify_queue_add(struct cfq_data *cfqd, struct cfq_group *cfqg)
{
	struct cfq_rb_root *st = &cfqd->grp_service_tree;
	struct cfq_group *__cfqg;
	struct rb_node *n;

	cfqg->nr_cfqq++;
	if (!RB_EMPTY_NODE(&cfqg->rb_node))
		return;

	/*
	 * Currently put the group at the end. Later implement something
	 * so that groups get lesser vtime based on their weights, so that
	 * if group does not loose all if it was not continuously backlogged.
	 */
	n = rb_last(&st->rb);
	if (n) {
		__cfqg = rb_entry_cfqg(n);
		cfqg->vdisktime = __cfqg->vdisktime + CFQ_IDLE_DELAY;
	} else
		cfqg->vdisktime = st->min_vdisktime;
	cfq_group_service_tree_add(st, cfqg);
}

static void
cfq_group_service_tree_del(struct cfq_rb_root *st, struct cfq_group *cfqg)
{
	st->total_weight -= cfqg->weight;
	if (!RB_EMPTY_NODE(&cfqg->rb_node))
		cfq_rb_erase(&cfqg->rb_node, st);
}

static void
cfq_group_notify_queue_del(struct cfq_data *cfqd, struct cfq_group *cfqg)
{
	struct cfq_rb_root *st = &cfqd->grp_service_tree;

	BUG_ON(cfqg->nr_cfqq < 1);
	cfqg->nr_cfqq--;

	/* If there are other cfq queues under this group, don't delete it */
	if (cfqg->nr_cfqq)
		return;

	cfq_log_cfqg(cfqd, cfqg, "del_from_rr group");
	cfq_group_service_tree_del(st, cfqg);
	cfqg->saved_workload_slice = 0;
	cfq_blkiocg_update_dequeue_stats(&cfqg->blkg, 1);
}

static inline unsigned int cfq_cfqq_slice_usage(struct cfq_queue *cfqq,
						unsigned int *unaccounted_time)
{
	unsigned int slice_used;

	/*
	 * Queue got expired before even a single request completed or
	 * got expired immediately after first request completion.
	 */
	if (!cfqq->slice_start || cfqq->slice_start == jiffies) {
		/*
		 * Also charge the seek time incurred to the group, otherwise
		 * if there are mutiple queues in the group, each can dispatch
		 * a single request on seeky media and cause lots of seek time
		 * and group will never know it.
		 */
		slice_used = max_t(unsigned, (jiffies - cfqq->dispatch_start),
					1);
	} else {
		slice_used = jiffies - cfqq->slice_start;
		if (slice_used > cfqq->allocated_slice) {
			*unaccounted_time = slice_used - cfqq->allocated_slice;
			slice_used = cfqq->allocated_slice;
		}
		if (time_after(cfqq->slice_start, cfqq->dispatch_start))
			*unaccounted_time += cfqq->slice_start -
					cfqq->dispatch_start;
	}

	return slice_used;
}

static void cfq_group_served(struct cfq_data *cfqd, struct cfq_group *cfqg,
				struct cfq_queue *cfqq)
{
	struct cfq_rb_root *st = &cfqd->grp_service_tree;
	unsigned int used_sl, charge, unaccounted_sl = 0;
	int nr_sync = cfqg->nr_cfqq - cfqg_busy_async_queues(cfqd, cfqg)
			- cfqg->service_tree_idle.count;

	BUG_ON(nr_sync < 0);
	used_sl = charge = cfq_cfqq_slice_usage(cfqq, &unaccounted_sl);

	if (iops_mode(cfqd))
		charge = cfqq->slice_dispatch;
	else if (!cfq_cfqq_sync(cfqq) && !nr_sync)
		charge = cfqq->allocated_slice;

	/* Can't update vdisktime while group is on service tree */
	cfq_group_service_tree_del(st, cfqg);
	cfqg->vdisktime += cfq_scale_slice(charge, cfqg);
	/* If a new weight was requested, update now, off tree */
	cfq_group_service_tree_add(st, cfqg);

	/* This group is being expired. Save the context */
	if (time_after(cfqd->workload_expires, jiffies)) {
		cfqg->saved_workload_slice = cfqd->workload_expires
						- jiffies;
		cfqg->saved_workload = cfqd->serving_type;
		cfqg->saved_serving_prio = cfqd->serving_prio;
	} else
		cfqg->saved_workload_slice = 0;

	cfq_log_cfqg(cfqd, cfqg, "served: vt=%llu min_vt=%llu", cfqg->vdisktime,
					st->min_vdisktime);
	cfq_log_cfqq(cfqq->cfqd, cfqq,
		     "sl_used=%u disp=%u charge=%u iops=%u sect=%lu",
		     used_sl, cfqq->slice_dispatch, charge,
		     iops_mode(cfqd), cfqq->nr_sectors);
	cfq_blkiocg_update_timeslice_used(&cfqg->blkg, used_sl,
					  unaccounted_sl);
	cfq_blkiocg_set_start_empty_time(&cfqg->blkg);
}

#ifdef CONFIG_CFQ_GROUP_IOSCHED
static inline struct cfq_group *cfqg_of_blkg(struct blkio_group *blkg)
{
	if (blkg)
		return container_of(blkg, struct cfq_group, blkg);
	return NULL;
}

static void cfq_update_blkio_group_weight(void *key, struct blkio_group *blkg,
					  unsigned int weight)
{
	struct cfq_group *cfqg = cfqg_of_blkg(blkg);
	cfqg->new_weight = weight;
	cfqg->needs_update = true;
}

static void cfq_init_add_cfqg_lists(struct cfq_data *cfqd,
			struct cfq_group *cfqg, struct blkio_cgroup *blkcg)
{
	struct backing_dev_info *bdi = &cfqd->queue->backing_dev_info;
	unsigned int major, minor;

	/*
	 * Add group onto cgroup list. It might happen that bdi->dev is
	 * not initialized yet. Initialize this new group without major
	 * and minor info and this info will be filled in once a new thread
	 * comes for IO.
	 */
	if (bdi->dev) {
		sscanf(dev_name(bdi->dev), "%u:%u", &major, &minor);
		cfq_blkiocg_add_blkio_group(blkcg, &cfqg->blkg,
					(void *)cfqd, MKDEV(major, minor));
	} else
		cfq_blkiocg_add_blkio_group(blkcg, &cfqg->blkg,
					(void *)cfqd, 0);

	cfqd->nr_blkcg_linked_grps++;
	cfqg->weight = blkcg_get_weight(blkcg, cfqg->blkg.dev);

	/* Add group on cfqd list */
	hlist_add_head(&cfqg->cfqd_node, &cfqd->cfqg_list);
}

/*
 * Should be called from sleepable context. No request queue lock as per
 * cpu stats are allocated dynamically and alloc_percpu needs to be called
 * from sleepable context.
 */
static struct cfq_group * cfq_alloc_cfqg(struct cfq_data *cfqd)
{
	struct cfq_group *cfqg = NULL;
	int i, j, ret;
	struct cfq_rb_root *st;

	cfqg = kzalloc_node(sizeof(*cfqg), GFP_ATOMIC, cfqd->queue->node);
	if (!cfqg)
		return NULL;

	for_each_cfqg_st(cfqg, i, j, st)
		*st = CFQ_RB_ROOT;
	RB_CLEAR_NODE(&cfqg->rb_node);

	cfqg->ttime.last_end_request = jiffies;

	/*
	 * Take the initial reference that will be released on destroy
	 * This can be thought of a joint reference by cgroup and
	 * elevator which will be dropped by either elevator exit
	 * or cgroup deletion path depending on who is exiting first.
	 */
	cfqg->ref = 1;

	ret = blkio_alloc_blkg_stats(&cfqg->blkg);
	if (ret) {
		kfree(cfqg);
		return NULL;
	}

	return cfqg;
}

static struct cfq_group *
cfq_find_cfqg(struct cfq_data *cfqd, struct blkio_cgroup *blkcg)
{
	struct cfq_group *cfqg = NULL;
	void *key = cfqd;
	struct backing_dev_info *bdi = &cfqd->queue->backing_dev_info;
	unsigned int major, minor;

	/*
	 * This is the common case when there are no blkio cgroups.
	 * Avoid lookup in this case
	 */
	if (blkcg == &blkio_root_cgroup)
		cfqg = &cfqd->root_group;
	else
		cfqg = cfqg_of_blkg(blkiocg_lookup_group(blkcg, key));

	if (cfqg && !cfqg->blkg.dev && bdi->dev && dev_name(bdi->dev)) {
		sscanf(dev_name(bdi->dev), "%u:%u", &major, &minor);
		cfqg->blkg.dev = MKDEV(major, minor);
	}

	return cfqg;
}

/*
 * Search for the cfq group current task belongs to. request_queue lock must
 * be held.
 */
static struct cfq_group *cfq_get_cfqg(struct cfq_data *cfqd)
{
	struct blkio_cgroup *blkcg;
	struct cfq_group *cfqg = NULL, *__cfqg = NULL;
	struct request_queue *q = cfqd->queue;

	rcu_read_lock();
	blkcg = task_blkio_cgroup(current);
	cfqg = cfq_find_cfqg(cfqd, blkcg);
	if (cfqg) {
		rcu_read_unlock();
		return cfqg;
	}

	/*
	 * Need to allocate a group. Allocation of group also needs allocation
	 * of per cpu stats which in-turn takes a mutex() and can block. Hence
	 * we need to drop rcu lock and queue_lock before we call alloc.
	 *
	 * Not taking any queue reference here and assuming that queue is
	 * around by the time we return. CFQ queue allocation code does
	 * the same. It might be racy though.
	 */

	rcu_read_unlock();
	spin_unlock_irq(q->queue_lock);

	cfqg = cfq_alloc_cfqg(cfqd);

	spin_lock_irq(q->queue_lock);

	rcu_read_lock();
	blkcg = task_blkio_cgroup(current);

	/*
	 * If some other thread already allocated the group while we were
	 * not holding queue lock, free up the group
	 */
	__cfqg = cfq_find_cfqg(cfqd, blkcg);

	if (__cfqg) {
		kfree(cfqg);
		rcu_read_unlock();
		return __cfqg;
	}

	if (!cfqg)
		cfqg = &cfqd->root_group;

	cfq_init_add_cfqg_lists(cfqd, cfqg, blkcg);
	rcu_read_unlock();
	return cfqg;
}

static inline struct cfq_group *cfq_ref_get_cfqg(struct cfq_group *cfqg)
{
	cfqg->ref++;
	return cfqg;
}

static void cfq_link_cfqq_cfqg(struct cfq_queue *cfqq, struct cfq_group *cfqg)
{
	/* Currently, all async queues are mapped to root group */
	if (!cfq_cfqq_sync(cfqq))
		cfqg = &cfqq->cfqd->root_group;

	cfqq->cfqg = cfqg;
	/* cfqq reference on cfqg */
	cfqq->cfqg->ref++;
}

static void cfq_put_cfqg(struct cfq_group *cfqg)
{
	struct cfq_rb_root *st;
	int i, j;

	BUG_ON(cfqg->ref <= 0);
	cfqg->ref--;
	if (cfqg->ref)
		return;
	for_each_cfqg_st(cfqg, i, j, st)
		BUG_ON(!RB_EMPTY_ROOT(&st->rb));
	free_percpu(cfqg->blkg.stats_cpu);
	kfree(cfqg);
}

static void cfq_destroy_cfqg(struct cfq_data *cfqd, struct cfq_group *cfqg)
{
	/* Something wrong if we are trying to remove same group twice */
	BUG_ON(hlist_unhashed(&cfqg->cfqd_node));

	hlist_del_init(&cfqg->cfqd_node);

	BUG_ON(cfqd->nr_blkcg_linked_grps <= 0);
	cfqd->nr_blkcg_linked_grps--;

	/*
	 * Put the reference taken at the time of creation so that when all
	 * queues are gone, group can be destroyed.
	 */
	cfq_put_cfqg(cfqg);
}