aboutsummaryrefslogtreecommitdiffstats
path: root/drivers/net/meth.c
blob: c336a1f42510c09d5c9e690cc46c207f9f6880e3 (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
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
/*
 * meth.c -- O2 Builtin 10/100 Ethernet driver
 *
 * Copyright (C) 2001-2003 Ilya Volynets
 *
 *	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.
 */
#include <linux/delay.h>
#include <linux/dma-mapping.h>
#include <linux/init.h>
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/platform_device.h>
#include <linux/slab.h>
#include <linux/errno.h>
#include <linux/types.h>
#include <linux/interrupt.h>

#include <linux/in.h>
#include <linux/in6.h>
#include <linux/device.h> /* struct device, et al */
#include <linux/netdevice.h>   /* struct device, and other headers */
#include <linux/etherdevice.h> /* eth_type_trans */
#include <linux/ip.h>          /* struct iphdr */
#include <linux/tcp.h>         /* struct tcphdr */
#include <linux/skbuff.h>
#include <linux/mii.h>         /* MII definitions */

#include <asm/ip32/mace.h>
#include <asm/ip32/ip32_ints.h>

#include <asm/io.h>

#include "meth.h"

#ifndef MFE_DEBUG
#define MFE_DEBUG 0
#endif

#if MFE_DEBUG>=1
#define DPRINTK(str,args...) printk(KERN_DEBUG "meth: %s: " str, __func__ , ## args)
#define MFE_RX_DEBUG 2
#else
#define DPRINTK(str,args...)
#define MFE_RX_DEBUG 0
#endif


static const char *meth_str="SGI O2 Fast Ethernet";

#define HAVE_TX_TIMEOUT
/* The maximum time waited (in jiffies) before assuming a Tx failed. (400ms) */
#define TX_TIMEOUT (400*HZ/1000)

#ifdef HAVE_TX_TIMEOUT
static int timeout = TX_TIMEOUT;
module_param(timeout, int, 0);
#endif

/*
 * This structure is private to each device. It is used to pass
 * packets in and out, so there is place for a packet
 */
struct meth_private {
	/* in-memory copy of MAC Control register */
	unsigned long mac_ctrl;
	/* in-memory copy of DMA Control register */
	unsigned long dma_ctrl;
	/* address of PHY, used by mdio_* functions, initialized in mdio_probe */
	unsigned long phy_addr;
	tx_packet *tx_ring;
	dma_addr_t tx_ring_dma;
	struct sk_buff *tx_skbs[TX_RING_ENTRIES];
	dma_addr_t tx_skb_dmas[TX_RING_ENTRIES];
	unsigned long tx_read, tx_write, tx_count;

	rx_packet *rx_ring[RX_RING_ENTRIES];
	dma_addr_t rx_ring_dmas[RX_RING_ENTRIES];
	struct sk_buff *rx_skbs[RX_RING_ENTRIES];
	unsigned long rx_write;

	spinlock_t meth_lock;
};

static void meth_tx_timeout(struct net_device *dev);
static irqreturn_t meth_interrupt(int irq, void *dev_id);

/* global, initialized in ip32-setup.c */
char o2meth_eaddr[8]={0,0,0,0,0,0,0,0};

static inline void load_eaddr(struct net_device *dev)
{
	int i;
	u64 macaddr;

	DPRINTK("Loading MAC Address: %pM\n", dev->dev_addr);
	macaddr = 0;
	for (i = 0; i < 6; i++)
		macaddr |= (u64)dev->dev_addr[i] << ((5 - i) * 8);

	mace->eth.mac_addr = macaddr;
}

/*
 * Waits for BUSY status of mdio bus to clear
 */
#define WAIT_FOR_PHY(___rval)					\
	while ((___rval = mace->eth.phy_data) & MDIO_BUSY) {	\
		udelay(25);					\
	}
/*read phy register, return value read */
static unsigned long mdio_read(struct meth_private *priv, unsigned long phyreg)
{
	unsigned long rval;
	WAIT_FOR_PHY(rval);
	mace->eth.phy_regs = (priv->phy_addr << 5) | (phyreg & 0x1f);
	udelay(25);
	mace->eth.phy_trans_go = 1;
	udelay(25);
	WAIT_FOR_PHY(rval);
	return rval & MDIO_DATA_MASK;
}

static int mdio_probe(struct meth_private *priv)
{
	int i;
	unsigned long p2, p3;
	/* check if phy is detected already */
	if(priv->phy_addr>=0&&priv->phy_addr<32)
		return 0;
	spin_lock(&priv->meth_lock);
	for (i=0;i<32;++i){
		priv->phy_addr=i;
		p2=mdio_read(priv,2);
		p3=mdio_read(priv,3);
#if MFE_DEBUG>=2
		switch ((p2<<12)|(p3>>4)){
		case PHY_QS6612X:
			DPRINTK("PHY is QS6612X\n");
			break;
		case PHY_ICS1889:
			DPRINTK("PHY is ICS1889\n");
			break;
		case PHY_ICS1890:
			DPRINTK("PHY is ICS1890\n");
			break;
		case PHY_DP83840:
			DPRINTK("PHY is DP83840\n");
			break;
		}
#endif
		if(p2!=0xffff&&p2!=0x0000){
			DPRINTK("PHY code: %x\n",(p2<<12)|(p3>>4));
			break;
		}
	}
	spin_unlock(&priv->meth_lock);
	if(priv->phy_addr<32) {
		return 0;
	}
	DPRINTK("Oopsie! PHY is not known!\n");
	priv->phy_addr=-1;
	return -ENODEV;
}

static void meth_check_link(struct net_device *dev)
{
	struct meth_private *priv = netdev_priv(dev);
	unsigned long mii_advertising = mdio_read(priv, 4);
	unsigned long mii_partner = mdio_read(priv, 5);
	unsigned long negotiated = mii_advertising & mii_partner;
	unsigned long duplex, speed;

	if (mii_partner == 0xffff)
		return;

	speed = (negotiated & 0x0380) ? METH_100MBIT : 0;
	duplex = ((negotiated & 0x0100) || (negotiated & 0x01C0) == 0x0040) ?
		 METH_PHY_FDX : 0;

	if ((priv->mac_ctrl & METH_PHY_FDX) ^ duplex) {
		DPRINTK("Setting %s-duplex\n", duplex ? "full" : "half");
		if (duplex)
			priv->mac_ctrl |= METH_PHY_FDX;
		else
			priv->mac_ctrl &= ~METH_PHY_FDX;
		mace->eth.mac_ctrl = priv->mac_ctrl;
	}

	if ((priv->mac_ctrl & METH_100MBIT) ^ speed) {
		DPRINTK("Setting %dMbs mode\n", speed ? 100 : 10);
		if (duplex)
			priv->mac_ctrl |= METH_100MBIT;
		else
			priv->mac_ctrl &= ~METH_100MBIT;
		mace->eth.mac_ctrl = priv->mac_ctrl;
	}
}


static int meth_init_tx_ring(struct meth_private *priv)
{
	/* Init TX ring */
	priv->tx_ring = dma_alloc_coherent(NULL, TX_RING_BUFFER_SIZE,
	                                   &priv->tx_ring_dma, GFP_ATOMIC);
	if (!priv->tx_ring)
		return -ENOMEM;
	memset(priv->tx_ring, 0, TX_RING_BUFFER_SIZE);
	priv->tx_count = priv->tx_read = priv->tx_write = 0;
	mace->eth.tx_ring_base = priv->tx_ring_dma;
	/* Now init skb save area */
	memset(priv->tx_skbs, 0, sizeof(priv->tx_skbs));
	memset(priv->tx_skb_dmas, 0, sizeof(priv->tx_skb_dmas));
	return 0;
}

static int meth_init_rx_ring(struct meth_private *priv)
{
	int i;

	for (i = 0; i < RX_RING_ENTRIES; i++) {
		priv->rx_skbs[i] = alloc_skb(METH_RX_BUFF_SIZE, 0);
		/* 8byte status vector + 3quad padding + 2byte padding,
		 * to put data on 64bit aligned boundary */
		skb_reserve(priv->rx_skbs[i],METH_RX_HEAD);
		priv->rx_ring[i]=(rx_packet*)(priv->rx_skbs[i]->head);
		/* I'll need to re-sync it after each RX */
		priv->rx_ring_dmas[i] =
			dma_map_single(NULL, priv->rx_ring[i],
				       METH_RX_BUFF_SIZE, DMA_FROM_DEVICE);
		mace->eth.rx_fifo = priv->rx_ring_dmas[i];
	}
        priv->rx_write = 0;
	return 0;
}
static void meth_free_tx_ring(struct meth_private *priv)
{
	int i;

	/* Remove any pending skb */
	for (i = 0; i < TX_RING_ENTRIES; i++) {
		if (priv->tx_skbs[i])
			dev_kfree_skb(priv->tx_skbs[i]);
		priv->tx_skbs[i] = NULL;
	}
	dma_free_coherent(NULL, TX_RING_BUFFER_SIZE, priv->tx_ring,
	                  priv->tx_ring_dma);
}

/* Presumes RX DMA engine is stopped, and RX fifo ring is reset */
static void meth_free_rx_ring(struct meth_private *priv)
{
	int i;

	for (i = 0; i < RX_RING_ENTRIES; i++) {
		dma_unmap_single(NULL, priv->rx_ring_dmas[i],
				 METH_RX_BUFF_SIZE, DMA_FROM_DEVICE);
		priv->rx_ring[i] = 0;
		priv->rx_ring_dmas[i] = 0;
		kfree_skb(priv->rx_skbs[i]);
	}
}

int meth_reset(struct net_device *dev)
{
	struct meth_private *priv = netdev_priv(dev);

	/* Reset card */
	mace->eth.mac_ctrl = SGI_MAC_RESET;
	udelay(1);
	mace->eth.mac_ctrl = 0;
	udelay(25);

	/* Load ethernet address */
	load_eaddr(dev);
	/* Should load some "errata", but later */

	/* Check for device */
	if (mdio_probe(priv) < 0) {
		DPRINTK("Unable to find PHY\n");
		return -ENODEV;
	}

	/* Initial mode: 10 | Half-duplex | Accept normal packets */
	priv->mac_ctrl = METH_ACCEPT_MCAST | METH_DEFAULT_IPG;
	if (dev->flags & IFF_PROMISC)
		priv->mac_ctrl |= METH_PROMISC;
	mace->eth.mac_ctrl = priv->mac_ctrl;

	/* Autonegotiate speed and duplex mode */
	meth_check_link(dev);

	/* Now set dma control, but don't enable DMA, yet */
	priv->dma_ctrl = (4 << METH_RX_OFFSET_SHIFT) |
			 (RX_RING_ENTRIES << METH_RX_DEPTH_SHIFT);
	mace->eth.dma_ctrl = priv->dma_ctrl;

	return 0;
}

/*============End Helper Routines=====================*/

/*
 * Open and close
 */
static int meth_open(struct net_device *dev)
{
	struct meth_private *priv = netdev_priv(dev);
	int ret;

	priv->phy_addr = -1;    /* No PHY is known yet... */

	/* Initialize the hardware */
	ret = meth_reset(dev);
	if (ret < 0)
		return ret;

	/* Allocate the ring buffers */
	ret = meth_init_tx_ring(priv);
	if (ret < 0)
		return ret;
	ret = meth_init_rx_ring(priv);
	if (ret < 0)
		goto out_free_tx_ring;

	ret = request_irq(dev->irq, meth_interrupt, 0, meth_str, dev);
	if (ret) {
		printk(KERN_ERR "%s: Can't get irq %d\n", dev->name, dev->irq);
		goto out_free_rx_ring;
	}

	/* Start DMA */
	priv->dma_ctrl |= METH_DMA_TX_EN | /*METH_DMA_TX_INT_EN |*/
			  METH_DMA_RX_EN | METH_DMA_RX_INT_EN;
	mace->eth.dma_ctrl = priv->dma_ctrl;

	DPRINTK("About to start queue\n");
	netif_start_queue(dev);

	return 0;

out_free_rx_ring:
	meth_free_rx_ring(priv);
out_free_tx_ring:
	meth_free_tx_ring(priv);

	return ret;
}

static int meth_release(struct net_device *dev)
{
	struct meth_private *priv = netdev_priv(dev);

	DPRINTK("Stopping queue\n");
	netif_stop_queue(dev); /* can't transmit any more */
	/* shut down DMA */
	priv->dma_ctrl &= ~(METH_DMA_TX_EN | METH_DMA_TX_INT_EN |
			    METH_DMA_RX_EN | METH_DMA_RX_INT_EN);
	mace->eth.dma_ctrl = priv->dma_ctrl;
	free_irq(dev->irq, dev);
	meth_free_tx_ring(priv);
	meth_free_rx_ring(priv);

	return 0;
}

/*
 * Receive a packet: retrieve, encapsulate and pass over to upper levels
 */
static void meth_rx(struct net_device* dev, unsigned long int_status)
{
	struct sk_buff *skb;
	unsigned long status;
	struct meth_private *priv = netdev_priv(dev);
	unsigned long fifo_rptr = (int_status & METH_INT_RX_RPTR_MASK) >> 8;

	spin_lock(&priv->meth_lock);
	priv->dma_ctrl &= ~METH_DMA_RX_INT_EN;
	mace->eth.dma_ctrl = priv->dma_ctrl;
	spin_unlock(&priv->meth_lock);

	if (int_status & METH_INT_RX_UNDERFLOW) {
		fifo_rptr = (fifo_rptr - 1) & 0x0f;
	}
	while (priv->rx_write != fifo_rptr) {
		dma_unmap_single(NULL, priv->rx_ring_dmas[priv->rx_write],
				 METH_RX_BUFF_SIZE, DMA_FROM_DEVICE);
		status = priv->rx_ring[priv->rx_write]->status.raw;
#if MFE_DEBUG
		if (!(status & METH_RX_ST_VALID)) {
			DPRINTK("Not received? status=%016lx\n",status);
		}
#endif
		if ((!(status & METH_RX_STATUS_ERRORS)) && (status & METH_RX_ST_VALID)) {
			int len = (status & 0xffff) - 4; /* omit CRC */
			/* length sanity check */
			if (len < 60 || len > 1518) {
				printk(KERN_DEBUG "%s: bogus packet size: %ld, status=%#2lx.\n",
				       dev->name, priv->rx_write,
				       priv->rx_ring[priv->rx_write]->status.raw);
				dev->stats.rx_errors++;
				dev->stats.rx_length_errors++;
				skb = priv->rx_skbs[priv->rx_write];
			} else {
				skb = alloc_skb(METH_RX_BUFF_SIZE, GFP_ATOMIC);
				if (!skb) {
					/* Ouch! No memory! Drop packet on the floor */
					DPRINTK("No mem: dropping packet\n");
					dev->stats.rx_dropped++;
					skb = priv->rx_skbs[priv->rx_write];
				} else {
					struct sk_buff *skb_c = priv->rx_skbs[priv->rx_write];
					/* 8byte status vector + 3quad padding + 2byte padding,
					 * to put data on 64bit aligned boundary */
					skb_reserve(skb, METH_RX_HEAD);
					/* Write metadata, and then pass to the receive level */
					skb_put(skb_c, len);
					priv->rx_skbs[priv->rx_write] = skb;
					skb_c->protocol = eth_type_trans(skb_c, dev);
					dev->stats.rx_packets++;
					dev->stats.rx_bytes += len;
					netif_rx(skb_c);
				}
			}
		} else {
			dev->stats.rx_errors++;
			skb=priv->rx_skbs[priv->rx_write];
#if MFE_DEBUG>0
			printk(KERN_WARNING "meth: RX error: status=0x%016lx\n",status);
			if(status&METH_RX_ST_RCV_CODE_VIOLATION)
				printk(KERN_WARNING "Receive Code Violation\n");
			if(status&METH_RX_ST_CRC_ERR)
				printk(KERN_WARNING "CRC error\n");
			if(status&METH_RX_ST_INV_PREAMBLE_CTX)
				printk(KERN_WARNING "Invalid Preamble Context\n");
			if(status&METH_RX_ST_LONG_EVT_SEEN)
				printk(KERN_WARNING "Long Event Seen...\n");
			if(status&METH_RX_ST_BAD_PACKET)
				printk(KERN_WARNING "Bad Packet\n");
			if(status&METH_RX_ST_CARRIER_EVT_SEEN)
				printk(KERN_WARNING "Carrier Event Seen\n");
#endif
		}
		priv->rx_ring[priv->rx_write] = (rx_packet*)skb->head;
		priv->rx_ring[priv->rx_write]->status.raw = 0;
		priv->rx_ring_dmas[priv->rx_write] =
			dma_map_single(NULL, priv->rx_ring[priv->rx_write],
				       METH_RX_BUFF_SIZE, DMA_FROM_DEVICE);
		mace->eth.rx_fifo = priv->rx_ring_dmas[priv->rx_write];
		ADVANCE_RX_PTR(priv->rx_write);
	}
	spin_lock(&priv->meth_lock);
	/* In case there was underflow, and Rx DMA was disabled */
	priv->dma_ctrl |= METH_DMA_RX_INT_EN | METH_DMA_RX_EN;
	mace->eth.dma_ctrl = priv->dma_ctrl;
	mace->eth.int_stat = METH_INT_RX_THRESHOLD;
	spin_unlock(&priv->meth_lock);
}

static int meth_tx_full(struct net_device *dev)
{
	struct meth_private *priv = netdev_priv(dev);

	return (priv->tx_count >= TX_RING_ENTRIES - 1);
}

static void meth_tx_cleanup(struct net_device* dev, unsigned long int_status)
{
	struct meth_private *priv = netdev_priv(dev);
	unsigned long status;
	struct sk_buff *skb;
	unsigned long rptr = (int_status&TX_INFO_RPTR) >> 16;

	spin_lock(&priv->meth_lock);

	/* Stop DMA notification */
	priv->dma_ctrl &= ~(METH_DMA_TX_INT_EN);
	mace->eth.dma_ctrl = priv->dma_ctrl;

	while (priv->tx_read != rptr) {
		skb = priv->tx_skbs[priv->tx_read];
		status = priv->tx_ring[priv->tx_read].header.raw;
#if MFE_DEBUG>=1
		if (priv->tx_read == priv->tx_write)
			DPRINTK("Auchi! tx_read=%d,tx_write=%d,rptr=%d?\n", priv->tx_read, priv->tx_write,rptr);
#endif
		if (status & METH_TX_ST_DONE) {
			if (status & METH_TX_ST_SUCCESS){
				dev->stats.tx_packets++;
				dev->stats.tx_bytes += skb->len;
			} else {
				dev->stats.tx_errors++;
#if MFE_DEBUG>=1
				DPRINTK("TX error: status=%016lx <",status);
				if(status & METH_TX_ST_SUCCESS)
					printk(" SUCCESS");
				if(status & METH_TX_ST_TOOLONG)
					printk(" TOOLONG");
				if(status & METH_TX_ST_UNDERRUN)
					printk(" UNDERRUN");
				if(status & METH_TX_ST_EXCCOLL)
					printk(" EXCCOLL");
				if(status & METH_TX_ST_DEFER)
					printk(" DEFER");
				if(status & METH_TX_ST_LATECOLL)
					printk(" LATECOLL");
				printk(" >\n");
#endif
			}
		} else {
			DPRINTK("RPTR points us here, but packet not done?\n");
			break;
		}
		dev_kfree_skb_irq(skb);
		priv->tx_skbs[priv->tx_read] = NULL;
		priv->tx_ring[priv->tx_read].header.raw = 0;
		priv->tx_read = (priv->tx_read+1)&(TX_RING_ENTRIES-1);
		priv->tx_count--;
	}

	/* wake up queue if it was stopped */
	if (netif_queue_stopped(dev) && !meth_tx_full(dev)) {
		netif_wake_queue(dev);
	}

	mace->eth.int_stat = METH_INT_TX_EMPTY | METH_INT_TX_PKT;
	spin_unlock(&priv->meth_lock);
}

static void meth_error(struct net_device* dev, unsigned status)
{
	struct meth_private *priv = netdev_priv(dev);

	printk(KERN_WARNING "meth: error status: 0x%08x\n",status);
	/* check for errors too... */
	if (status & (METH_INT_TX_LINK_FAIL))
		printk(KERN_WARNING "meth: link failure\n");
	/* Should I do full reset in this case? */
	if (status & (METH_INT_MEM_ERROR))
		printk(KERN_WARNING "meth: memory error\n");
	if (status & (METH_INT_TX_ABORT))
		printk(KERN_WARNING "meth: aborted\n");
	if (status & (METH_INT_RX_OVERFLOW))
		printk(KERN_WARNING "meth: Rx overflow\n");
	if (status & (METH_INT_RX_UNDERFLOW)) {
		printk(KERN_WARNING "meth: Rx underflow\n");
		spin_lock(&priv->meth_lock);
		mace->eth.int_stat = METH_INT_RX_UNDERFLOW;
		/* more underflow interrupts will be delivered,
		 * effectively throwing us into an infinite loop.
		 *  Thus I stop processing Rx in this case. */
		priv->dma_ctrl &= ~METH_DMA_RX_EN;
		mace->eth.dma_ctrl = priv->dma_ctrl;
		DPRINTK("Disabled meth Rx DMA temporarily\n");
		spin_unlock(&priv->meth_lock);
	}
	mace->eth.int_stat = METH_INT_ERROR;
}

/*
 * The typical interrupt entry point
 */
static irqreturn_t meth_interrupt(int irq, void *dev_id)
{
	struct net_device *dev = (struct net_device *)dev_id;
	struct meth_private *priv = netdev_priv(dev);
	unsigned long status;

	status = mace->eth.int_stat;
	while (status & 0xff) {
		/* First handle errors - if we get Rx underflow,
		 * Rx DMA will be disabled, and Rx handler will reenable
		 * it. I don't think it's possible to get Rx underflow,
		 * without getting Rx interrupt */
		if (status & METH_INT_ERROR) {
			meth_error(dev, status);
		}
		if (status & (METH_INT_TX_EMPTY | METH_INT_TX_PKT)) {
			/* a transmission is over: free the skb */
			meth_tx_cleanup(dev, status);
		}
		if (status & METH_INT_RX_THRESHOLD) {
			if (!(priv->dma_ctrl & METH_DMA_RX_INT_EN))
				break;
			/* send it to meth_rx for handling */
			meth_rx(dev, status);
		}
		status = mace->eth.int_stat;
	}

	return IRQ_HANDLED;
}

/*
 * Transmits packets that fit into TX descriptor (are <=120B)
 */
static void meth_tx_short_prepare(struct meth_private *priv,
				  struct sk_buff *skb)
{
	tx_packet *desc = &priv->tx_ring[priv->tx_write];
	int len = (skb->len < ETH_ZLEN) ? ETH_ZLEN : skb->len;

	desc->header.raw = METH_TX_CMD_INT_EN | (len-1) | ((128-len) << 16);
	/* maybe I should set whole thing to 0 first... */
	skb_copy_from_linear_data(skb, desc->data.dt + (120 - len), skb->len);
	if (skb->len < len)
		memset(desc->data.dt + 120 - len + skb->len, 0, len-skb->len);
}
#define TX_CATBUF1 BIT(25)
static void meth_tx_1page_prepare(struct meth_private *priv,
				  struct sk_buff *skb)
{
	tx_packet *desc = &priv->tx_ring[priv->tx_write];
	void *buffer_data = (void *)(((unsigned long)skb->data + 7) & ~7);
	int unaligned_len = (int)((unsigned long)buffer_data - (unsigned long)skb->data);
	int buffer_len = skb->len - unaligned_len;
	dma_addr_t catbuf;

	desc->header.raw = METH_TX_CMD_INT_EN | TX_CATBUF1 | (skb->len - 1);

	/* unaligned part */
	if (unaligned_len) {
		skb_copy_from_linear_data(skb, desc->data.dt + (120 - unaligned_len),
			      unaligned_len);
		desc->header.raw |= (128 - unaligned_len) << 16;
	}

	/* first page */
	catbuf = dma_map_single(NULL, buffer_data, buffer_len,
				DMA_TO_DEVICE);
	desc->data.cat_buf[0].form.start_addr = catbuf >> 3;
	desc->data.cat_buf[0].form.len = buffer_len - 1;
}
#define TX_CATBUF2 BIT(26)
static void meth_tx_2page_prepare(struct meth_private *priv,
				  struct sk_buff *skb)
{
	tx_packet *desc = &priv->tx_ring[priv->tx_write];
	void *buffer1_data = (void *)(((unsigned long)skb->data + 7) & ~7);
	void *buffer2_data = (void *)PAGE_ALIGN((unsigned long)skb->data);
	int unaligned_len = (int)((unsigned long)buffer1_data - (unsigned long)skb->data);
	int buffer1_len = (int)((unsigned long)buffer2_data - (unsigned long)buffer1_data);
	int buffer2_len = skb->len - buffer1_len - unaligned_len;
	dma_addr_t catbuf1, catbuf2;

	desc->header.raw = METH_TX_CMD_INT_EN | TX_CATBUF1 | TX_CATBUF2| (skb->len - 1);
	/* unaligned part */
	if (unaligned_len){
		skb_copy_from_linear_data(skb, desc->data.dt + (120 - unaligned_len),
			      unaligned_len);
		desc->header.raw |= (128 - unaligned_len) << 16;
	}

	/* first page */
	catbuf1 = dma_map_single(NULL, buffer1_data, buffer1_len,
				 DMA_TO_DEVICE);
	desc->data.cat_buf[0].form.start_addr = catbuf1 >> 3;
	desc->data.cat_buf[0].form.len = buffer1_len - 1;
	/* second page */
	catbuf2 = dma_map_single(NULL, buffer2_data, buffer2_len,
				 DMA_TO_DEVICE);
	desc->data.cat_buf[1].form.start_addr = catbuf2 >> 3;
	desc->data.cat_buf[1].form.len = buffer2_len - 1;
}

static void meth_add_to_tx_ring(struct meth_private *priv, struct sk_buff *skb)
{
	/* Remember the skb, so we can free it at interrupt time */
	priv->tx_skbs[priv->tx_write] = skb;
	if (skb->len <= 120) {
		/* Whole packet fits into descriptor */
		meth_tx_short_prepare(priv, skb);
	} else if (PAGE_ALIGN((unsigned long)skb->data) !=
		   PAGE_ALIGN((unsigned long)skb->data + skb->len - 1)) {
		/* Packet crosses page boundary */
		meth_tx_2page_prepare(priv, skb);
	} else {
		/* Packet is in one page */
		meth_tx_1page_prepare(priv, skb);
	}
	priv->tx_write = (priv->tx_write + 1) & (TX_RING_ENTRIES - 1);
	mace->eth.tx_info = priv->tx_write;
	priv->tx_count++;
}

/*
 * Transmit a packet (called by the kernel)
 */
static int meth_tx(struct sk_buff *skb, struct net_device *dev)
{
	struct meth_private *priv = netdev_priv(dev);
	unsigned long flags;

	spin_lock_irqsave(&priv->meth_lock, flags);
	/* Stop DMA notification */
	priv->dma_ctrl &= ~(METH_DMA_TX_INT_EN);
	mace->eth.dma_ctrl = priv->dma_ctrl;

	meth_add_to_tx_ring(priv, skb);
	dev->trans_start = jiffies; /* save the timestamp */

	/* If TX ring is full, tell the upper layer to stop sending packets */
	if (meth_tx_full(dev)) {
	        printk(KERN_DEBUG "TX full: stopping\n");
		netif_stop_queue(dev);
	}

	/* Restart DMA notification */
	priv->dma_ctrl |= METH_DMA_TX_INT_EN;
	mace->eth.dma_ctrl = priv->dma_ctrl;

	spin_unlock_irqrestore(&priv->meth_lock, flags);

	return 0;
}

/*
 * Deal with a transmit timeout.
 */
static void meth_tx_timeout(struct net_device *dev)
{
	struct meth_private *priv = netdev_priv(dev);
	unsigned long flags;

	printk(KERN_WARNING "%s: transmit timed out\n", dev->name);

	/* Protect against concurrent rx interrupts */
	spin_lock_irqsave(&priv->meth_lock,flags);

	/* Try to reset the interface. */
	meth_reset(dev);

	dev->stats.tx_errors++;

	/* Clear all rings */
	meth_free_tx_ring(priv);
	meth_free_rx_ring(priv);
	meth_init_tx_ring(priv);
	meth_init_rx_ring(priv);

	/* Restart dma */
	priv->dma_ctrl |= METH_DMA_TX_EN | METH_DMA_RX_EN | METH_DMA_RX_INT_EN;
	mace->eth.dma_ctrl = priv->dma_ctrl;

	/* Enable interrupt */
	spin_unlock_irqrestore(&priv->meth_lock, flags);

	dev->trans_start = jiffies;
	netif_wake_queue(dev);

	return;
}

/*
 * Ioctl commands
 */
static int meth_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
{
	/* XXX Not yet implemented */
	switch(cmd) {
	case SIOCGMIIPHY:
	case SIOCGMIIREG:
	case SIOCSMIIREG:
	default:
		return -EOPNOTSUPP;
	}
}

/*
 * Return statistics to the caller
 */
/*
 * The init function.
 */
static int __init meth_probe(struct platform_device *pdev)
{
	struct net_device *dev;
	struct meth_private *priv;
	int err;

	dev = alloc_etherdev(sizeof(struct meth_private));
	if (!dev)
		return -ENOMEM;

	dev->open            = meth_open;
	dev->stop            = meth_release;
	dev->hard_start_xmit = meth_tx;
	dev->do_ioctl        = meth_ioctl;
#ifdef HAVE_TX_TIMEOUT
	dev->tx_timeout      = meth_tx_timeout;
	dev->watchdog_timeo  = timeout;
#endif
	dev->irq	     = MACE_ETHERNET_IRQ;
	dev->base_addr	     = (unsigned long)&mace->eth;
	memcpy(dev->dev_addr, o2meth_eaddr, 6);

	priv = netdev_priv(dev);
	spin_lock_init(&priv->meth_lock);
	SET_NETDEV_DEV(dev, &pdev->dev);

	err = register_netdev(dev);
	if (err) {
		free_netdev(dev);
		return err;
	}

	printk(KERN_INFO "%s: SGI MACE Ethernet rev. %d\n",
	       dev->name, (unsigned int)(mace->eth.mac_ctrl >> 29));
	return 0;
}

static int __exit meth_remove(struct platform_device *pdev)
{
	struct net_device *dev = platform_get_drvdata(pdev);

	unregister_netdev(dev);
	free_netdev(dev);
	platform_set_drvdata(pdev, NULL);

	return 0;
}

static struct platform_driver meth_driver = {
	.probe	= meth_probe,
	.remove	= __devexit_p(meth_remove),
	.driver = {
		.name	= "meth",
		.owner	= THIS_MODULE,
	}
};

static int __init meth_init_module(void)
{
	int err;

	err = platform_driver_register(&meth_driver);
	if (err)
		printk(KERN_ERR "Driver registration failed\n");

	return err;
}

static void __exit meth_exit_module(void)
{
	platform_driver_unregister(&meth_driver);
}

module_init(meth_init_module);
module_exit(meth_exit_module);

MODULE_AUTHOR("Ilya Volynets <ilya@theIlya.com>");
MODULE_DESCRIPTION("SGI O2 Builtin Fast Ethernet driver");
MODULE_LICENSE("GPL");
MODULE_ALIAS("platform:meth");
a> 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
/*
 *  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/blkdev.h>
#include <linux/elevator.h>
#include <linux/jiffies.h>
#include <linux/rbtree.h>
#include <linux/ioprio.h>
#include <linux/blktrace_api.h>
#include "blk-cgroup.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 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_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)
#define RQ_CFQQ(rq)		(struct cfq_queue *) ((rq)->elevator_private2)

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);

#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 rb_node *active;
};
#define CFQ_RB_ROOT	(struct cfq_rb_root) { .rb = RB_ROOT, .left = NULL, \
			.count = 0, .min_vdisktime = 0, }

/*
 * Per process-grouping structure
 */
struct cfq_queue {
	/* reference count */
	atomic_t 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 metadata requests */
	int meta_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, org_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;
	struct cfq_group *orig_cfqg;
	/* Sectors dispatched in current 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,
};

/*
 * 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;
	bool on_st;

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

	/* Per group busy queus average. Useful for workload slice calc. */
	unsigned int busy_queues_avg[2];
	/*
	 * rr lists of queues with requests, onle rr for each priority class.
	 * 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;
	atomic_t ref;
#endif
};

/*
 * 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;
	bool noidle_tree_requires_idle;

	/*
	 * 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;

	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_latency;
	unsigned int cfq_group_isolation;

	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;
	struct rcu_head rcu;
};

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_DEBUG_CFQ_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 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;
}

/*
 * 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_rw_flagged(bio, BIO_RW_SYNCIO);
}

/*
 * 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);
	}
}

static int cfq_queue_empty(struct request_queue *q)
{
	struct cfq_data *cfqd = q->elevator->elevator_data;

	return !cfqd->rq_queued;
}

/*
 * 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)
{
	u64 vdisktime = st->min_vdisktime;
	struct cfq_group *cfqg;

	if (st->active) {
		cfqg = rb_entry_cfqg(st->active);
		vdisktime = cfqg->vdisktime;
	}

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

	st->min_vdisktime = max_vdisktime(st->min_vdisktime, 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 void
cfq_set_prio_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);
		}
	}
	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 0;
	if (time_before(jiffies, cfqq->slice_end))
		return 0;

	return 1;
}

/*
 * 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 rq1;
	else if (rq_is_sync(rq2) && !rq_is_sync(rq1))
		return rq2;
	if (rq_is_meta(rq1) && !rq_is_meta(rq2))
		return rq1;
	else if (rq_is_meta(rq2) && !rq_is_meta(rq1))
		return 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_group_service_tree_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 (cfqg->on_st)
		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 continously 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);
	cfqg->on_st = true;
	st->total_weight += cfqg->weight;
}

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

	if (st->active == &cfqg->rb_node)
		st->active = NULL;

	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");
	cfqg->on_st = false;
	st->total_weight -= cfqg->weight;
	if (!RB_EMPTY_NODE(&cfqg->rb_node))
		cfq_rb_erase(&cfqg->rb_node, st);
	cfqg->saved_workload_slice = 0;
	blkiocg_update_blkio_group_dequeue_stats(&cfqg->blkg, 1);
}

static inline unsigned int cfq_cfqq_slice_usage(struct cfq_queue *cfqq)
{
	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)
			slice_used = cfqq->allocated_slice;
	}

	cfq_log_cfqq(cfqq->cfqd, cfqq, "sl_used=%u sect=%lu", slice_used,
				cfqq->nr_sectors);
	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_sl;
	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_sl = cfq_cfqq_slice_usage(cfqq);

	if (!cfq_cfqq_sync(cfqq) && !nr_sync)
		charge_sl = cfqq->allocated_slice;

	/* Can't update vdisktime while group is on service tree */
	cfq_rb_erase(&cfqg->rb_node, st);
	cfqg->vdisktime += cfq_scale_slice(charge_sl, cfqg);
	__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);
	blkiocg_update_blkio_group_stats(&cfqg->blkg, used_sl,
						cfqq->nr_sectors);
}

#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;
}

void
cfq_update_blkio_group_weight(struct blkio_group *blkg, unsigned int weight)
{
	cfqg_of_blkg(blkg)->weight = weight;
}

static struct cfq_group *
cfq_find_alloc_cfqg(struct cfq_data *cfqd, struct cgroup *cgroup, int create)
{
	struct blkio_cgroup *blkcg = cgroup_to_blkio_cgroup(cgroup);
	struct cfq_group *cfqg = NULL;
	void *key = cfqd;
	int i, j;
	struct cfq_rb_root *st;
	struct backing_dev_info *bdi = &cfqd->queue->backing_dev_info;
	unsigned int major, minor;

	cfqg = cfqg_of_blkg(blkiocg_lookup_group(blkcg, key));
	if (cfqg || !create)
		goto done;

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

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

	/*
	 * 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.
	 */
	atomic_set(&cfqg->ref, 1);

	/* Add group onto cgroup list */
	sscanf(dev_name(bdi->dev), "%u:%u", &major, &minor);
	blkiocg_add_blkio_group(blkcg, &cfqg->blkg, (void *)cfqd,
					MKDEV(major, minor));

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

done:
	return cfqg;
}

/*
 * Search for the cfq group current task belongs to. If create = 1, then also
 * create the cfq group if it does not exist. request_queue lock must be held.
 */
static struct cfq_group *cfq_get_cfqg(struct cfq_data *cfqd, int create)
{
	struct cgroup *cgroup;
	struct cfq_group *cfqg = NULL;

	rcu_read_lock();
	cgroup = task_cgroup(current, blkio_subsys_id);
	cfqg = cfq_find_alloc_cfqg(cfqd, cgroup, create);
	if (!cfqg && create)
		cfqg = &cfqd->root_group;
	rcu_read_unlock();
	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 */
	atomic_inc(&cfqq->cfqg->ref);
}

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

	BUG_ON(atomic_read(&cfqg->ref) <= 0);
	if (!atomic_dec_and_test(&cfqg->ref))
		return;
	for_each_cfqg_st(cfqg, i, j, st)
		BUG_ON(!RB_EMPTY_ROOT(&st->rb) || st->active != NULL);
	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);

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

static void cfq_release_cfq_groups(struct cfq_data *cfqd)
{
	struct hlist_node *pos, *n;
	struct cfq_group *cfqg;

	hlist_for_each_entry_safe(cfqg, pos, n, &cfqd->cfqg_list, cfqd_node) {
		/*
		 * If cgroup removal path got to blk_group first and removed
		 * it from cgroup list, then it will take care of destroying
		 * cfqg also.
		 */
		if (!blkiocg_del_blkio_group(&cfqg->blkg))
			cfq_destroy_cfqg(cfqd, cfqg);
	}
}

/*
 * Blk cgroup controller notification saying that blkio_group object is being
 * delinked as associated cgroup object is going away. That also means that
 * no new IO will come in this group. So get rid of this group as soon as
 * any pending IO in the group is finished.
 *
 * This function is called under rcu_read_lock(). key is the rcu protected
 * pointer. That means "key" is a valid cfq_data pointer as long as we are rcu
 * read lock.
 *
 * "key" was fetched from blkio_group under blkio_cgroup->lock. That means
 * it should not be NULL as even if elevator was exiting, cgroup deltion
 * path got to it first.
 */
void cfq_unlink_blkio_group(void *key, struct blkio_group *blkg)
{
	unsigned long  flags;
	struct cfq_data *cfqd = key;

	spin_lock_irqsave(cfqd->queue->queue_lock, flags);
	cfq_destroy_cfqg(cfqd, cfqg_of_blkg(blkg));
	spin_unlock_irqrestore(cfqd->queue->queue_lock, flags);
}

#else /* GROUP_IOSCHED */
static struct cfq_group *cfq_get_cfqg(struct cfq_data *cfqd, int create)
{
	return &cfqd->root_group;
}
static inline void
cfq_link_cfqq_cfqg(struct cfq_queue *cfqq, struct cfq_group *cfqg) {
	cfqq->cfqg = cfqg;
}

static void cfq_release_cfq_groups(struct cfq_data *cfqd) {}
static inline void cfq_put_cfqg(struct cfq_group *cfqg) {}

#endif /* GROUP_IOSCHED */

/*
 * The cfqd->service_trees holds all pending cfq_queue's that have
 * requests waiting to be processed. It is sorted in the order that
 * we will service the queues.
 */
static void cfq_service_tree_add(struct cfq_data *cfqd, struct cfq_queue *cfqq,
				 bool add_front)
{
	struct rb_node **p, *parent;
	struct cfq_queue *__cfqq;
	unsigned long rb_key;
	struct cfq_rb_root *service_tree;
	int left;
	int new_cfqq = 1;
	int group_changed = 0;

#ifdef CONFIG_CFQ_GROUP_IOSCHED
	if (!cfqd->cfq_group_isolation
	    && cfqq_type(cfqq) == SYNC_NOIDLE_WORKLOAD
	    && cfqq->cfqg && cfqq->cfqg != &cfqd->root_group) {
		/* Move this cfq to root group */
		cfq_log_cfqq(cfqd, cfqq, "moving to root group");
		if (!RB_EMPTY_NODE(&cfqq->rb_node))
			cfq_group_service_tree_del(cfqd, cfqq->cfqg);
		cfqq->orig_cfqg = cfqq->cfqg;
		cfqq->cfqg = &cfqd->root_group;
		atomic_inc(&cfqd->root_group.ref);
		group_changed = 1;
	} else if (!cfqd->cfq_group_isolation
		   && cfqq_type(cfqq) == SYNC_WORKLOAD && cfqq->orig_cfqg) {
		/* cfqq is sequential now needs to go to its original group */
		BUG_ON(cfqq->cfqg != &cfqd->root_group);
		if (!RB_EMPTY_NODE(&cfqq->rb_node))
			cfq_group_service_tree_del(cfqd, cfqq->cfqg);
		cfq_put_cfqg(cfqq->cfqg);
		cfqq->cfqg = cfqq->orig_cfqg;
		cfqq->orig_cfqg = NULL;
		group_changed = 1;
		cfq_log_cfqq(cfqd, cfqq, "moved to origin group");
	}
#endif

	service_tree = service_tree_for(cfqq->cfqg, cfqq_prio(cfqq),
						cfqq_type(cfqq));
	if (cfq_class_idle(cfqq)) {
		rb_key = CFQ_IDLE_DELAY;
		parent = rb_last(&service_tree->rb);
		if (parent && parent != &cfqq->rb_node) {
			__cfqq = rb_entry(parent, struct cfq_queue, rb_node);
			rb_key += __cfqq->rb_key;
		} else
			rb_key += jiffies;
	} else if (!add_front) {
		/*
		 * Get our rb key offset. Subtract any residual slice
		 * value carried from last service. A negative resid
		 * count indicates slice overrun, and this should position
		 * the next service time further away in the tree.
		 */
		rb_key = cfq_slice_offset(cfqd, cfqq) + jiffies;
		rb_key -= cfqq->slice_resid;
		cfqq->slice_resid = 0;
	} else {
		rb_key = -HZ;
		__cfqq = cfq_rb_first(service_tree);
		rb_key += __cfqq ? __cfqq->rb_key : jiffies;
	}

	if (!RB_EMPTY_NODE(&cfqq->rb_node)) {
		new_cfqq = 0;
		/*
		 * same position, nothing more to do
		 */
		if (rb_key == cfqq->rb_key &&
		    cfqq->service_tree == service_tree)
			return;

		cfq_rb_erase(&cfqq->rb_node, cfqq->service_tree);
		cfqq->service_tree = NULL;
	}

	left = 1;
	parent = NULL;
	cfqq->service_tree = service_tree;
	p = &service_tree->rb.rb_node;
	while (*p) {
		struct rb_node **n;

		parent = *p;
		__cfqq = rb_entry(parent, struct cfq_queue, rb_node);

		/*
		 * sort by key, that represents service time.
		 */
		if (time_before(rb_key, __cfqq->rb_key))
			n = &(*p)->rb_left;
		else {
			n = &(*p)->rb_right;
			left = 0;
		}

		p = n;
	}

	if (left)
		service_tree->left = &cfqq->rb_node;

	cfqq->rb_key = rb_key;
	rb_link_node(&cfqq->rb_node, parent, p);
	rb_insert_color(&cfqq->rb_node, &service_tree->rb);
	service_tree->count++;
	if ((add_front || !new_cfqq) && !group_changed)
		return;
	cfq_group_service_tree_add(cfqd, cfqq->cfqg);
}

static struct cfq_queue *
cfq_prio_tree_lookup(struct cfq_data *cfqd, struct rb_root *root,
		     sector_t sector, struct rb_node **ret_parent,
		     struct rb_node ***rb_link)
{
	struct rb_node **p, *parent;
	struct cfq_queue *cfqq = NULL;

	parent = NULL;
	p = &root->rb_node;
	while (*p) {
		struct rb_node **n;

		parent = *p;
		cfqq = rb_entry(parent, struct cfq_queue, p_node);

		/*
		 * Sort strictly based on sector.  Smallest to the left,
		 * largest to the right.
		 */
		if (sector > blk_rq_pos(cfqq->next_rq))
			n = &(*p)->rb_right;
		else if (sector < blk_rq_pos(cfqq->next_rq))
			n = &(*p)->rb_left;
		else
			break;
		p = n;
		cfqq = NULL;
	}

	*ret_parent = parent;
	if (rb_link)
		*rb_link = p;
	return cfqq;
}

static void cfq_prio_tree_add(struct cfq_data *cfqd, struct cfq_queue *cfqq)
{
	struct rb_node **p, *parent;
	struct cfq_queue *__cfqq;

	if (cfqq->p_root) {
		rb_erase(&cfqq->p_node, cfqq->p_root);
		cfqq->p_root = NULL;
	}

	if (cfq_class_idle(cfqq))
		return;
	if (!cfqq->next_rq)
		return;

	cfqq->p_root = &cfqd->prio_trees[cfqq->org_ioprio];
	__cfqq = cfq_prio_tree_lookup(cfqd, cfqq->p_root,
				      blk_rq_pos(cfqq->next_rq), &parent, &p);
	if (!__cfqq) {
		rb_link_node(&cfqq->p_node, parent, p);
		rb_insert_color(&cfqq->p_node, cfqq->p_root);
	} else
		cfqq->p_root = NULL;
}

/*
 * Update cfqq's position in the service tree.
 */
static void cfq_resort_rr_list(struct cfq_data *cfqd, struct cfq_queue *cfqq)
{
	/*
	 * Resorting requires the cfqq to be on the RR list already.
	 */
	if (cfq_cfqq_on_rr(cfqq)) {
		cfq_service_tree_add(cfqd, cfqq, 0);
		cfq_prio_tree_add(cfqd, cfqq);
	}
}

/*
 * add to busy list of queues for service, trying to be fair in ordering
 * the pending list according to last request service
 */
static void cfq_add_cfqq_rr(struct cfq_data *cfqd, struct cfq_queue *cfqq)
{
	cfq_log_cfqq(cfqd, cfqq, "add_to_rr");
	BUG_ON(cfq_cfqq_on_rr(cfqq));
	cfq_mark_cfqq_on_rr(cfqq);
	cfqd->busy_queues++;

	cfq_resort_rr_list(cfqd, cfqq);
}

/*
 * Called when the cfqq no longer has requests pending, remove it from
 * the service tree.
 */
static void cfq_del_cfqq_rr(struct cfq_data *cfqd, struct cfq_queue *cfqq)
{
	cfq_log_cfqq(cfqd, cfqq, "del_from_rr");
	BUG_ON(!cfq_cfqq_on_rr(cfqq));
	cfq_clear_cfqq_on_rr(cfqq);

	if (!RB_EMPTY_NODE(&cfqq->rb_node)) {
		cfq_rb_erase(&cfqq->rb_node, cfqq->service_tree);
		cfqq->service_tree = NULL;
	}
	if (cfqq->p_root) {
		rb_erase(&cfqq->p_node, cfqq->p_root);
		cfqq->p_root = NULL;
	}

	cfq_group_service_tree_del(cfqd, cfqq->cfqg);
	BUG_ON(!cfqd->busy_queues);
	cfqd->busy_queues--;
}

/*
 * rb tree support functions
 */
static void cfq_del_rq_rb(struct request *rq)
{
	struct cfq_queue *cfqq = RQ_CFQQ(rq);
	const int sync = rq_is_sync(rq);

	BUG_ON(!cfqq->queued[sync]);
	cfqq->queued[sync]--;

	elv_rb_del(&cfqq->sort_list, rq);

	if (cfq_cfqq_on_rr(cfqq) && RB_EMPTY_ROOT(&cfqq->sort_list)) {
		/*
		 * Queue will be deleted from service tree when we actually
		 * expire it later. Right now just remove it from prio tree
		 * as it is empty.
		 */
		if (cfqq->p_root) {
			rb_erase(&cfqq->p_node, cfqq->p_root);
			cfqq->p_root = NULL;
		}
	}
}

static void cfq_add_rq_rb(struct request *rq)
{
	struct cfq_queue *cfqq = RQ_CFQQ(rq);
	struct cfq_data *cfqd = cfqq->cfqd;
	struct request *__alias, *prev;

	cfqq->queued[rq_is_sync(rq)]++;

	/*
	 * looks a little odd, but the first insert might return an alias.
	 * if that happens, put the alias on the dispatch list
	 */
	while ((__alias = elv_rb_add(&cfqq->sort_list, rq)) != NULL)
		cfq_dispatch_insert(cfqd->queue, __alias);

	if (!cfq_cfqq_on_rr(cfqq))
		cfq_add_cfqq_rr(cfqd, cfqq);

	/*
	 * check if this request is a better next-serve candidate
	 */
	prev = cfqq->next_rq;
	cfqq->next_rq = cfq_choose_req(cfqd, cfqq->next_rq, rq, cfqd->last_position);

	/*
	 * adjust priority tree position, if ->next_rq changes
	 */
	if (prev != cfqq->next_rq)
		cfq_prio_tree_add(cfqd, cfqq);

	BUG_ON(!cfqq->next_rq);
}

static void cfq_reposition_rq_rb(struct cfq_queue *cfqq, struct request *rq)
{
	elv_rb_del(&cfqq->sort_list, rq);
	cfqq->queued[rq_is_sync(rq)]--;
	cfq_add_rq_rb(rq);
}

static struct request *
cfq_find_rq_fmerge(struct cfq_data *cfqd, struct bio *bio)
{
	struct task_struct *tsk = current;
	struct cfq_io_context *cic;
	struct cfq_queue *cfqq;

	cic = cfq_cic_lookup(cfqd, tsk->io_context);
	if (!cic)
		return NULL;

	cfqq = cic_to_cfqq(cic, cfq_bio_sync(bio));
	if (cfqq) {
		sector_t sector = bio->bi_sector + bio_sectors(bio);

		return elv_rb_find(&cfqq->sort_list, sector);
	}

	return NULL;
}

static void cfq_activate_request(struct request_queue *q, struct request *rq)
{
	struct cfq_data *cfqd = q->elevator->elevator_data;

	cfqd->rq_in_driver++;
	cfq_log_cfqq(cfqd, RQ_CFQQ(rq), "activate rq, drv=%d",
						cfqd->rq_in_driver);

	cfqd->last_position = blk_rq_pos(rq) + blk_rq_sectors(rq);
}

static void cfq_deactivate_request(struct request_queue *q, struct request *rq)
{
	struct cfq_data *cfqd = q->elevator->elevator_data;

	WARN_ON(!cfqd->rq_in_driver);
	cfqd->rq_in_driver--;
	cfq_log_cfqq(cfqd, RQ_CFQQ(rq), "deactivate rq, drv=%d",
						cfqd->rq_in_driver);
}

static void cfq_remove_request(struct request *rq)
{
	struct cfq_queue *cfqq = RQ_CFQQ(rq);

	if (cfqq->next_rq == rq)
		cfqq->next_rq = cfq_find_next_rq(cfqq->cfqd, cfqq, rq);

	list_del_init(&rq->queuelist);
	cfq_del_rq_rb(rq);

	cfqq->cfqd->rq_queued--;
	if (rq_is_meta(rq)) {
		WARN_ON(!cfqq->meta_pending);
		cfqq->meta_pending--;
	}
}

static int cfq_merge(struct request_queue *q, struct request **req,
		     struct bio *bio)
{
	struct cfq_data *cfqd = q->elevator->elevator_data;
	struct request *__rq;

	__rq = cfq_find_rq_fmerge(cfqd, bio);
	if (__rq && elv_rq_merge_ok(__rq, bio)) {
		*req = __rq;
		return ELEVATOR_FRONT_MERGE;
	}

	return ELEVATOR_NO_MERGE;
}

static void cfq_merged_request(struct request_queue *q, struct request *req,
			       int type)
{
	if (type == ELEVATOR_FRONT_MERGE) {
		struct cfq_queue *cfqq = RQ_CFQQ(req);

		cfq_reposition_rq_rb(cfqq, req);
	}
}

static void
cfq_merged_requests(struct request_queue *q, struct request *rq,
		    struct request *next)
{
	struct cfq_queue *cfqq = RQ_CFQQ(rq);
	/*
	 * reposition in fifo if next is older than rq
	 */
	if (!list_empty(&rq->queuelist) && !list_empty(&next->queuelist) &&
	    time_before(rq_fifo_time(next), rq_fifo_time(rq))) {
		list_move(&rq->queuelist, &next->queuelist);
		rq_set_fifo_time(rq, rq_fifo_time(next));
	}

	if (cfqq->next_rq == next)
		cfqq->next_rq = rq;
	cfq_remove_request(next);
}

static int cfq_allow_merge(struct request_queue *q, struct request *rq,
			   struct bio *bio)
{
	struct cfq_data *cfqd = q->elevator->elevator_data;
	struct cfq_io_context *cic;
	struct cfq_queue *cfqq;

	/*
	 * Disallow merge of a sync bio into an async request.
	 */
	if (cfq_bio_sync(bio) && !rq_is_sync(rq))
		return false;

	/*
	 * Lookup the cfqq that this bio will be queued with. Allow
	 * merge only if rq is queued there.
	 */
	cic = cfq_cic_lookup(cfqd, current->io_context);
	if (!cic)
		return false;

	cfqq = cic_to_cfqq(cic, cfq_bio_sync(bio));
	return cfqq == RQ_CFQQ(rq);
}

static void __cfq_set_active_queue(struct cfq_data *cfqd,
				   struct cfq_queue *cfqq)
{
	if (cfqq) {
		cfq_log_cfqq(cfqd, cfqq, "set_active");
		cfqq->slice_start = 0;
		cfqq->dispatch_start = jiffies;
		cfqq->allocated_slice = 0;
		cfqq->slice_end = 0;
		cfqq->slice_dispatch = 0;
		cfqq->nr_sectors = 0;

		cfq_clear_cfqq_wait_request(cfqq);
		cfq_clear_cfqq_must_dispatch(cfqq);
		cfq_clear_cfqq_must_alloc_slice(cfqq);
		cfq_clear_cfqq_fifo_expire(cfqq);
		cfq_mark_cfqq_slice_new(cfqq);

		del_timer(&cfqd->idle_slice_timer);
	}

	cfqd->active_queue = cfqq;
}

/*
 * current cfqq expired its slice (or was too idle), select new one
 */
static void
__cfq_slice_expired(struct cfq_data *cfqd, struct cfq_queue *cfqq,
		    bool timed_out)
{
	cfq_log_cfqq(cfqd, cfqq, "slice expired t=%d", timed_out);

	if (cfq_cfqq_wait_request(cfqq))
		del_timer(&cfqd->idle_slice_timer);

	cfq_clear_cfqq_wait_request(cfqq);
	cfq_clear_cfqq_wait_busy(cfqq);

	/*
	 * If this cfqq is shared between multiple processes, check to
	 * make sure that those processes are still issuing I/Os within
	 * the mean seek distance.  If not, it may be time to break the
	 * queues apart again.
	 */
	if (cfq_cfqq_coop(cfqq) && CFQQ_SEEKY(cfqq))
		cfq_mark_cfqq_split_coop(cfqq);

	/*
	 * store what was left of this slice, if the queue idled/timed out
	 */
	if (timed_out && !cfq_cfqq_slice_new(cfqq)) {
		cfqq->slice_resid = cfqq->slice_end - jiffies;
		cfq_log_cfqq(cfqd, cfqq, "resid=%ld", cfqq->slice_resid);
	}

	cfq_group_served(cfqd, cfqq->cfqg, cfqq);

	if (cfq_cfqq_on_rr(cfqq) && RB_EMPTY_ROOT(&cfqq->sort_list))
		cfq_del_cfqq_rr(cfqd, cfqq);

	cfq_resort_rr_list(cfqd, cfqq);

	if (cfqq == cfqd->active_queue)
		cfqd->active_queue = NULL;

	if (&cfqq->cfqg->rb_node == cfqd->grp_service_tree.active)
		cfqd->grp_service_tree.active = NULL;

	if (cfqd->active_cic) {
		put_io_context(cfqd->active_cic->ioc);
		cfqd->active_cic = NULL;
	}
}

static inline void cfq_slice_expired(struct cfq_data *cfqd, bool timed_out)
{
	struct cfq_queue *cfqq = cfqd->active_queue;

	if (cfqq)
		__cfq_slice_expired(cfqd, cfqq, timed_out);
}

/*
 * Get next queue for service. Unless we have a queue preemption,
 * we'll simply select the first cfqq in the service tree.
 */
static struct cfq_queue *cfq_get_next_queue(struct cfq_data *cfqd)
{
	struct cfq_rb_root *service_tree =
		service_tree_for(cfqd->serving_group, cfqd->serving_prio,
					cfqd->serving_type);

	if (!cfqd->rq_queued)
		return NULL;

	/* There is nothing to dispatch */
	if (!service_tree)
		return NULL;
	if (RB_EMPTY_ROOT(&service_tree->rb))
		return NULL;
	return cfq_rb_first(service_tree);
}

static struct cfq_queue *cfq_get_next_queue_forced(struct cfq_data *cfqd)
{
	struct cfq_group *cfqg;
	struct cfq_queue *cfqq;
	int i, j;
	struct cfq_rb_root *st;

	if (!cfqd->rq_queued)
		return NULL;

	cfqg = cfq_get_next_cfqg(cfqd);
	if (!cfqg)
		return NULL;

	for_each_cfqg_st(cfqg, i, j, st)
		if ((cfqq = cfq_rb_first(st)) != NULL)
			return cfqq;
	return NULL;
}

/*
 * Get and set a new active queue for service.
 */
static struct cfq_queue *cfq_set_active_queue(struct cfq_data *cfqd,
					      struct cfq_queue *cfqq)
{
	if (!cfqq)
		cfqq = cfq_get_next_queue(cfqd);

	__cfq_set_active_queue(cfqd, cfqq);
	return cfqq;
}

static inline sector_t cfq_dist_from_last(struct cfq_data *cfqd,
					  struct request *rq)
{
	if (blk_rq_pos(rq) >= cfqd->last_position)
		return blk_rq_pos(rq) - cfqd->last_position;
	else
		return cfqd->last_position - blk_rq_pos(rq);
}

static inline int cfq_rq_close(struct cfq_data *cfqd, struct cfq_queue *cfqq,
			       struct request *rq, bool for_preempt)
{
	return cfq_dist_from_last(cfqd, rq) <= CFQQ_SEEK_THR;
}

static struct cfq_queue *cfqq_close(struct cfq_data *cfqd,
				    struct cfq_queue *cur_cfqq)
{
	struct rb_root *root = &cfqd->prio_trees[cur_cfqq->org_ioprio];
	struct rb_node *parent, *node;
	struct cfq_queue *__cfqq;
	sector_t sector = cfqd->last_position;

	if (RB_EMPTY_ROOT(root))
		return NULL;

	/*
	 * First, if we find a request starting at the end of the last
	 * request, choose it.
	 */
	__cfqq = cfq_prio_tree_lookup(cfqd, root, sector, &parent, NULL);
	if (__cfqq)
		return __cfqq;

	/*
	 * If the exact sector wasn't found, the parent of the NULL leaf
	 * will contain the closest sector.
	 */
	__cfqq = rb_entry(parent, struct cfq_queue, p_node);
	if (cfq_rq_close(cfqd, cur_cfqq, __cfqq->next_rq, false))
		return __cfqq;

	if (blk_rq_pos(__cfqq->next_rq) < sector)
		node = rb_next(&__cfqq->p_node);
	else
		node = rb_prev(&__cfqq->p_node);
	if (!node)
		return NULL;

	__cfqq = rb_entry(node, struct cfq_queue, p_node);
	if (cfq_rq_close(cfqd, cur_cfqq, __cfqq->next_rq, false))
		return __cfqq;

	return NULL;
}

/*
 * cfqd - obvious
 * cur_cfqq - passed in so that we don't decide that the current queue is
 * 	      closely cooperating with itself.
 *
 * So, basically we're assuming that that cur_cfqq has dispatched at least
 * one request, and that cfqd->last_position reflects a position on the disk
 * associated with the I/O issued by cur_cfqq.  I'm not sure this is a valid
 * assumption.
 */
static struct cfq_queue *cfq_close_cooperator(struct cfq_data *cfqd,
					      struct cfq_queue *cur_cfqq)
{
	struct cfq_queue *cfqq;

	if (!cfq_cfqq_sync(cur_cfqq))
		return NULL;
	if (CFQQ_SEEKY(cur_cfqq))
		return NULL;

	/*
	 * Don't search priority tree if it's the only queue in the group.
	 */
	if (cur_cfqq->cfqg->nr_cfqq == 1)
		return NULL;

	/*
	 * We should notice if some of the queues are cooperating, eg
	 * working closely on the same area of the disk. In that case,
	 * we can group them together and don't waste time idling.
	 */
	cfqq = cfqq_close(cfqd, cur_cfqq);
	if (!cfqq)
		return NULL;

	/* If new queue belongs to different cfq_group, don't choose it */
	if (cur_cfqq->cfqg != cfqq->cfqg)
		return NULL;

	/*
	 * It only makes sense to merge sync queues.
	 */
	if (!cfq_cfqq_sync(cfqq))
		return NULL;
	if (CFQQ_SEEKY(cfqq))
		return NULL;

	/*
	 * Do not merge queues of different priority classes
	 */
	if (cfq_class_rt(cfqq) != cfq_class_rt(cur_cfqq))
		return NULL;

	return cfqq;
}

/*
 * Determine whether we should enforce idle window for this queue.
 */

static bool cfq_should_idle(struct cfq_data *cfqd, struct cfq_queue *cfqq)
{
	enum wl_prio_t prio = cfqq_prio(cfqq);
	struct cfq_rb_root *service_tree = cfqq->service_tree;

	BUG_ON(!service_tree);
	BUG_ON(!service_tree->count);

	/* We never do for idle class queues. */
	if (prio == IDLE_WORKLOAD)
		return false;

	/* We do for queues that were marked with idle window flag. */
	if (cfq_cfqq_idle_window(cfqq) &&
	   !(blk_queue_nonrot(cfqd->queue) && cfqd->hw_tag))
		return true;

	/*
	 * Otherwise, we do only if they are the last ones
	 * in their service tree.
	 */
	return service_tree->count == 1 && cfq_cfqq_sync(cfqq);
}

static void cfq_arm_slice_timer(struct cfq_data *cfqd)
{
	struct cfq_queue *cfqq = cfqd->active_queue;
	struct cfq_io_context *cic;
	unsigned long sl;

	/*
	 * SSD device without seek penalty, disable idling. But only do so
	 * for devices that support queuing, otherwise we still have a problem
	 * with sync vs async workloads.
	 */
	if (blk_queue_nonrot(cfqd->queue) && cfqd->hw_tag)
		return;

	WARN_ON(!RB_EMPTY_ROOT(&cfqq->sort_list));
	WARN_ON(cfq_cfqq_slice_new(cfqq));

	/*
	 * idle is disabled, either manually or by past process history
	 */
	if (!cfqd->cfq_slice_idle || !cfq_should_idle(cfqd, cfqq))
		return;

	/*
	 * still active requests from this queue, don't idle
	 */
	if (cfqq->dispatched)
		return;

	/*
	 * task has exited, don't wait
	 */
	cic = cfqd->active_cic;
	if (!cic || !atomic_read(&cic->ioc->nr_tasks))
		return;

	/*
	 * If our average think time is larger than the remaining time
	 * slice, then don't idle. This avoids overrunning the allotted
	 * time slice.
	 */
	if (sample_valid(cic->ttime_samples) &&
	    (cfqq->slice_end - jiffies < cic->ttime_mean))
		return;

	cfq_mark_cfqq_wait_request(cfqq);

	sl = cfqd->cfq_slice_idle;

	mod_timer(&cfqd->idle_slice_timer, jiffies + sl);
	cfq_log_cfqq(cfqd, cfqq, "arm_idle: %lu", sl);
}

/*
 * Move request from internal lists to the request queue dispatch list.
 */
static void cfq_dispatch_insert(struct request_queue *q, struct request *rq)
{
	struct cfq_data *cfqd = q->elevator->elevator_data;
	struct cfq_queue *cfqq = RQ_CFQQ(rq);

	cfq_log_cfqq(cfqd, cfqq, "dispatch_insert");

	cfqq->next_rq = cfq_find_next_rq(cfqd, cfqq, rq);
	cfq_remove_request(rq);
	cfqq->dispatched++;
	elv_dispatch_sort(q, rq);

	cfqd->rq_in_flight[cfq_cfqq_sync(cfqq)]++;
	cfqq->nr_sectors += blk_rq_sectors(rq);
}

/*
 * return expired entry, or NULL to just start from scratch in rbtree
 */
static struct request *cfq_check_fifo(struct cfq_queue *cfqq)
{
	struct request *rq = NULL;

	if (cfq_cfqq_fifo_expire(cfqq))
		return NULL;

	cfq_mark_cfqq_fifo_expire(cfqq);

	if (list_empty(&cfqq->fifo))
		return NULL;

	rq = rq_entry_fifo(cfqq->fifo.next);
	if (time_before(jiffies, rq_fifo_time(rq)))
		rq = NULL;

	cfq_log_cfqq(cfqq->cfqd, cfqq, "fifo=%p", rq);
	return rq;
}

static inline int
cfq_prio_to_maxrq(struct cfq_data *cfqd, struct cfq_queue *cfqq)
{
	const int base_rq = cfqd->cfq_slice_async_rq;

	WARN_ON(cfqq->ioprio >= IOPRIO_BE_NR);

	return 2 * (base_rq + base_rq * (CFQ_PRIO_LISTS - 1 - cfqq->ioprio));
}

/*
 * Must be called with the queue_lock held.
 */
static int cfqq_process_refs(struct cfq_queue *cfqq)
{
	int process_refs, io_refs;

	io_refs = cfqq->allocated[READ] + cfqq->allocated[WRITE];
	process_refs = atomic_read(&cfqq->ref) - io_refs;
	BUG_ON(process_refs < 0);
	return process_refs;
}

static void cfq_setup_merge(struct cfq_queue *cfqq, struct cfq_queue *new_cfqq)
{
	int process_refs, new_process_refs;
	struct cfq_queue *__cfqq;

	/* Avoid a circular list and skip interim queue merges */
	while ((__cfqq = new_cfqq->new_cfqq)) {
		if (__cfqq == cfqq)
			return;
		new_cfqq = __cfqq;
	}

	process_refs = cfqq_process_refs(cfqq);
	/*
	 * If the process for the cfqq has gone away, there is no
	 * sense in merging the queues.
	 */
	if (process_refs == 0)
		return;

	/*
	 * Merge in the direction of the lesser amount of work.
	 */
	new_process_refs = cfqq_process_refs(new_cfqq);
	if (new_process_refs >= process_refs) {
		cfqq->new_cfqq = new_cfqq;
		atomic_add(process_refs, &new_cfqq->ref);
	} else {
		new_cfqq->new_cfqq = cfqq;
		atomic_add(new_process_refs, &cfqq->ref);
	}
}

static enum wl_type_t cfq_choose_wl(struct cfq_data *cfqd,
				struct cfq_group *cfqg, enum wl_prio_t prio)
{
	struct cfq_queue *queue;
	int i;
	bool key_valid = false;
	unsigned long lowest_key = 0;
	enum wl_type_t cur_best = SYNC_NOIDLE_WORKLOAD;

	for (i = 0; i <= SYNC_WORKLOAD; ++i) {
		/* select the one with lowest rb_key */
		queue = cfq_rb_first(service_tree_for(cfqg, prio, i));
		if (queue &&
		    (!key_valid || time_before(queue->rb_key, lowest_key))) {
			lowest_key = queue->rb_key;
			cur_best = i;
			key_valid = true;
		}
	}

	return cur_best;
}

static void choose_service_tree(struct cfq_data *cfqd, struct cfq_group *cfqg)
{
	unsigned slice;
	unsigned count;
	struct cfq_rb_root *st;
	unsigned group_slice;

	if (!cfqg) {
		cfqd->serving_prio = IDLE_WORKLOAD;
		cfqd->workload_expires = jiffies + 1;
		return;
	}

	/* Choose next priority. RT > BE > IDLE */
	if (cfq_group_busy_queues_wl(RT_WORKLOAD, cfqd, cfqg))
		cfqd->serving_prio = RT_WORKLOAD;
	else if (cfq_group_busy_queues_wl(BE_WORKLOAD, cfqd, cfqg))
		cfqd->serving_prio = BE_WORKLOAD;
	else {
		cfqd->serving_prio = IDLE_WORKLOAD;
		cfqd->workload_expires = jiffies + 1;
		return;
	}

	/*
	 * For RT and BE, we have to choose also the type
	 * (SYNC, SYNC_NOIDLE, ASYNC), and to compute a workload
	 * expiration time
	 */
	st = service_tree_for(cfqg, cfqd->serving_prio, cfqd->serving_type);
	count = st->count;

	/*
	 * check workload expiration, and that we still have other queues ready
	 */
	if (count && !time_after(jiffies, cfqd->workload_expires))
		return;

	/* otherwise select new workload type */
	cfqd->serving_type =
		cfq_choose_wl(cfqd, cfqg, cfqd->serving_prio);
	st = service_tree_for(cfqg, cfqd->serving_prio, cfqd->serving_type);
	count = st->count;

	/*
	 * the workload slice is computed as a fraction of target latency
	 * proportional to the number of queues in that workload, over
	 * all the queues in the same priority class
	 */
	group_slice = cfq_group_slice(cfqd, cfqg);

	slice = group_slice * count /
		max_t(unsigned, cfqg->busy_queues_avg[cfqd->serving_prio],
		      cfq_group_busy_queues_wl(cfqd->serving_prio, cfqd, cfqg));

	if (cfqd->serving_type == ASYNC_WORKLOAD) {
		unsigned int tmp;

		/*
		 * Async queues are currently system wide. Just taking
		 * proportion of queues with-in same group will lead to higher
		 * async ratio system wide as generally root group is going
		 * to have higher weight. A more accurate thing would be to
		 * calculate system wide asnc/sync ratio.
		 */
		tmp = cfq_target_latency * cfqg_busy_async_queues(cfqd, cfqg);
		tmp = tmp/cfqd->busy_queues;
		slice = min_t(unsigned, slice, tmp);

		/* async workload slice is scaled down according to
		 * the sync/async slice ratio. */
		slice = slice * cfqd->cfq_slice[0] / cfqd->cfq_slice[1];
	} else
		/* sync workload slice is at least 2 * cfq_slice_idle */
		slice = max(slice, 2 * cfqd->cfq_slice_idle);

	slice = max_t(unsigned, slice, CFQ_MIN_TT);
	cfqd->workload_expires = jiffies + slice;
	cfqd->noidle_tree_requires_idle = false;
}

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

	if (RB_EMPTY_ROOT(&st->rb))
		return NULL;
	cfqg = cfq_rb_first_group(st);
	st->active = &cfqg->rb_node;
	update_min_vdisktime(st);
	return cfqg;
}

static void cfq_choose_cfqg(struct cfq_data *cfqd)
{
	struct cfq_group *cfqg = cfq_get_next_cfqg(cfqd);

	cfqd->serving_group = cfqg;

	/* Restore the workload type data */
	if (cfqg->saved_workload_slice) {
		cfqd->workload_expires = jiffies + cfqg->saved_workload_slice;
		cfqd->serving_type = cfqg->saved_workload;
		cfqd->serving_prio = cfqg->saved_serving_prio;
	} else
		cfqd->workload_expires = jiffies - 1;

	choose_service_tree(cfqd, cfqg);
}

/*
 * Select a queue for service. If we have a current active queue,
 * check whether to continue servicing it, or retrieve and set a new one.
 */
static struct cfq_queue *cfq_select_queue(struct cfq_data *cfqd)
{
	struct cfq_queue *cfqq, *new_cfqq = NULL;

	cfqq = cfqd->active_queue;
	if (!cfqq)
		goto new_queue;

	if (!cfqd->rq_queued)
		return NULL;

	/*
	 * We were waiting for group to get backlogged. Expire the queue
	 */
	if (cfq_cfqq_wait_busy(cfqq) && !RB_EMPTY_ROOT(&cfqq->sort_list))
		goto expire;

	/*
	 * The active queue has run out of time, expire it and select new.
	 */
	if (cfq_slice_used(cfqq) && !cfq_cfqq_must_dispatch(cfqq)) {
		/*
		 * If slice had not expired at the completion of last request
		 * we might not have turned on wait_busy flag. Don't expire
		 * the queue yet. Allow the group to get backlogged.
		 *
		 * The very fact that we have used the slice, that means we
		 * have been idling all along on this queue and it should be
		 * ok to wait for this request to complete.
		 */
		if (cfqq->cfqg->nr_cfqq == 1 && RB_EMPTY_ROOT(&cfqq->sort_list)
		    && cfqq->dispatched && cfq_should_idle(cfqd, cfqq)) {
			cfqq = NULL;
			goto keep_queue;
		} else
			goto expire;
	}

	/*
	 * The active queue has requests and isn't expired, allow it to
	 * dispatch.
	 */
	if (!RB_EMPTY_ROOT(&cfqq->sort_list))
		goto keep_queue;

	/*
	 * If another queue has a request waiting within our mean seek
	 * distance, let it run.  The expire code will check for close
	 * cooperators and put the close queue at the front of the service
	 * tree.  If possible, merge the expiring queue with the new cfqq.
	 */
	new_cfqq = cfq_close_cooperator(cfqd, cfqq);
	if (new_cfqq) {
		if (!cfqq->new_cfqq)
			cfq_setup_merge(cfqq, new_cfqq);
		goto expire;
	}

	/*
	 * No requests pending. If the active queue still has requests in
	 * flight or is idling for a new request, allow either of these
	 * conditions to happen (or time out) before selecting a new queue.
	 */
	if (timer_pending(&cfqd->idle_slice_timer) ||
	    (cfqq->dispatched && cfq_should_idle(cfqd, cfqq))) {
		cfqq = NULL;
		goto keep_queue;
	}

expire:
	cfq_slice_expired(cfqd, 0);
new_queue:
	/*
	 * Current queue expired. Check if we have to switch to a new
	 * service tree
	 */
	if (!new_cfqq)
		cfq_choose_cfqg(cfqd);

	cfqq = cfq_set_active_queue(cfqd, new_cfqq);
keep_queue:
	return cfqq;
}

static int __cfq_forced_dispatch_cfqq(struct cfq_queue *cfqq)
{
	int dispatched = 0;

	while (cfqq->next_rq) {
		cfq_dispatch_insert(cfqq->cfqd->queue, cfqq->next_rq);
		dispatched++;
	}

	BUG_ON(!list_empty(&cfqq->fifo));

	/* By default cfqq is not expired if it is empty. Do it explicitly */
	__cfq_slice_expired(cfqq->cfqd, cfqq, 0);
	return dispatched;
}

/*
 * Drain our current requests. Used for barriers and when switching
 * io schedulers on-the-fly.
 */
static int cfq_forced_dispatch(struct cfq_data *cfqd)
{
	struct cfq_queue *cfqq;
	int dispatched = 0;

	while ((cfqq = cfq_get_next_queue_forced(cfqd)) != NULL)
		dispatched += __cfq_forced_dispatch_cfqq(cfqq);

	cfq_slice_expired(cfqd, 0);
	BUG_ON(cfqd->busy_queues);

	cfq_log(cfqd, "forced_dispatch=%d", dispatched);
	return dispatched;
}

static inline bool cfq_slice_used_soon(struct cfq_data *cfqd,
	struct cfq_queue *cfqq)
{
	/* the queue hasn't finished any request, can't estimate */
	if (cfq_cfqq_slice_new(cfqq))
		return 1;
	if (time_after(jiffies + cfqd->cfq_slice_idle * cfqq->dispatched,
		cfqq->slice_end))
		return 1;

	return 0;
}

static bool cfq_may_dispatch(struct cfq_data *cfqd, struct cfq_queue *cfqq)
{
	unsigned int max_dispatch;

	/*
	 * Drain async requests before we start sync IO
	 */
	if (cfq_should_idle(cfqd, cfqq) && cfqd->rq_in_flight[BLK_RW_ASYNC])
		return false;

	/*
	 * If this is an async queue and we have sync IO in flight, let it wait
	 */
	if (cfqd->rq_in_flight[BLK_RW_SYNC] && !cfq_cfqq_sync(cfqq))
		return false;

	max_dispatch = max_t(unsigned int, cfqd->cfq_quantum / 2, 1);
	if (cfq_class_idle(cfqq))
		max_dispatch = 1;

	/*
	 * Does this cfqq already have too much IO in flight?
	 */
	if (cfqq->dispatched >= max_dispatch) {
		/*
		 * idle queue must always only have a single IO in flight
		 */
		if (cfq_class_idle(cfqq))
			return false;

		/*
		 * We have other queues, don't allow more IO from this one
		 */
		if (cfqd->busy_queues > 1 && cfq_slice_used_soon(cfqd, cfqq))
			return false;

		/*
		 * Sole queue user, no limit
		 */
		if (cfqd->busy_queues == 1)
			max_dispatch = -1;
		else
			/*
			 * Normally we start throttling cfqq when cfq_quantum/2
			 * requests have been dispatched. But we can drive
			 * deeper queue depths at the beginning of slice
			 * subjected to upper limit of cfq_quantum.
			 * */
			max_dispatch = cfqd->cfq_quantum;
	}

	/*
	 * Async queues must wait a bit before being allowed dispatch.
	 * We also ramp up the dispatch depth gradually for async IO,
	 * based on the last sync IO we serviced
	 */
	if (!cfq_cfqq_sync(cfqq) && cfqd->cfq_latency) {
		unsigned long last_sync = jiffies - cfqd->last_delayed_sync;
		unsigned int depth;

		depth = last_sync / cfqd->cfq_slice[1];
		if (!depth && !cfqq->dispatched)
			depth = 1;
		if (depth < max_dispatch)
			max_dispatch = depth;
	}

	/*
	 * If we're below the current max, allow a dispatch
	 */
	return cfqq->dispatched < max_dispatch;
}

/*
 * Dispatch a request from cfqq, moving them to the request queue
 * dispatch list.
 */
static bool cfq_dispatch_request(struct cfq_data *cfqd, struct cfq_queue *cfqq)
{
	struct request *rq;

	BUG_ON(RB_EMPTY_ROOT(&cfqq->sort_list));

	if (!cfq_may_dispatch(cfqd, cfqq))
		return false;

	/*
	 * follow expired path, else get first next available
	 */
	rq = cfq_check_fifo(cfqq);
	if (!rq)
		rq = cfqq->next_rq;

	/*
	 * insert request into driver dispatch list
	 */
	cfq_dispatch_insert(cfqd->queue, rq);

	if (!cfqd->active_cic) {
		struct cfq_io_context *cic = RQ_CIC(rq);

		atomic_long_inc(&cic->ioc->refcount);
		cfqd->active_cic = cic;
	}

	return true;
}

/*
 * Find the cfqq that we need to service and move a request from that to the
 * dispatch list
 */
static int cfq_dispatch_requests(struct request_queue *q, int force)
{
	struct cfq_data *cfqd = q->elevator->elevator_data;
	struct cfq_queue *cfqq;

	if (!cfqd->busy_queues)
		return 0;

	if (unlikely(force))
		return cfq_forced_dispatch(cfqd);

	cfqq = cfq_select_queue(cfqd);
	if (!cfqq)
		return 0;

	/*
	 * Dispatch a request from this cfqq, if it is allowed
	 */
	if (!cfq_dispatch_request(cfqd, cfqq))
		return 0;

	cfqq->slice_dispatch++;
	cfq_clear_cfqq_must_dispatch(cfqq);

	/*
	 * expire an async queue immediately if it has used up its slice. idle
	 * queue always expire after 1 dispatch round.
	 */
	if (cfqd->busy_queues > 1 && ((!cfq_cfqq_sync(cfqq) &&
	    cfqq->slice_dispatch >= cfq_prio_to_maxrq(cfqd, cfqq)) ||
	    cfq_class_idle(cfqq))) {
		cfqq->slice_end = jiffies + 1;
		cfq_slice_expired(cfqd, 0);
	}

	cfq_log_cfqq(cfqd, cfqq, "dispatched a request");
	return 1;
}

/*
 * task holds one reference to the queue, dropped when task exits. each rq
 * in-flight on this queue also holds a reference, dropped when rq is freed.
 *
 * Each cfq queue took a reference on the parent group. Drop it now.
 * queue lock must be held here.
 */
static void cfq_put_queue(struct cfq_queue *cfqq)
{
	struct cfq_data *cfqd = cfqq->cfqd;
	struct cfq_group *cfqg, *orig_cfqg;

	BUG_ON(atomic_read(&cfqq->ref) <= 0);

	if (!atomic_dec_and_test(&cfqq->ref))
		return;

	cfq_log_cfqq(cfqd, cfqq, "put_queue");
	BUG_ON(rb_first(&cfqq->sort_list));
	BUG_ON(cfqq->allocated[READ] + cfqq->allocated[WRITE]);
	cfqg = cfqq->cfqg;
	orig_cfqg = cfqq->orig_cfqg;

	if (unlikely(cfqd->active_queue == cfqq)) {
		__cfq_slice_expired(cfqd, cfqq, 0);
		cfq_schedule_dispatch(cfqd);
	}

	BUG_ON(cfq_cfqq_on_rr(cfqq));
	kmem_cache_free(cfq_pool, cfqq);
	cfq_put_cfqg(cfqg);
	if (orig_cfqg)
		cfq_put_cfqg(orig_cfqg);
}

/*
 * Must always be called with the rcu_read_lock() held
 */
static void
__call_for_each_cic(struct io_context *ioc,
		    void (*func)(struct io_context *, struct cfq_io_context *))
{
	struct cfq_io_context *cic;
	struct hlist_node *n;

	hlist_for_each_entry_rcu(cic, n, &ioc->cic_list, cic_list)
		func(ioc, cic);
}

/*
 * Call func for each cic attached to this ioc.
 */
static void
call_for_each_cic(struct io_context *ioc,
		  void (*func)(struct io_context *, struct cfq_io_context *))
{
	rcu_read_lock();
	__call_for_each_cic(ioc, func);
	rcu_read_unlock();
}

static void cfq_cic_free_rcu(struct rcu_head *head)
{
	struct cfq_io_context *cic;

	cic = container_of(head, struct cfq_io_context, rcu_head);

	kmem_cache_free(cfq_ioc_pool, cic);
	elv_ioc_count_dec(cfq_ioc_count);

	if (ioc_gone) {
		/*
		 * CFQ scheduler is exiting, grab exit lock and check
		 * the pending io context count. If it hits zero,
		 * complete ioc_gone and set it back to NULL
		 */
		spin_lock(&ioc_gone_lock);
		if (ioc_gone && !elv_ioc_count_read(cfq_ioc_count)) {
			complete(ioc_gone);
			ioc_gone = NULL;
		}
		spin_unlock(&ioc_gone_lock);
	}
}

static void cfq_cic_free(struct cfq_io_context *cic)
{
	call_rcu(&cic->rcu_head, cfq_cic_free_rcu);
}

static void cic_free_func(struct io_context *ioc, struct cfq_io_context *cic)
{
	unsigned long flags;

	BUG_ON(!cic->dead_key);

	spin_lock_irqsave(&ioc->lock, flags);
	radix_tree_delete(&ioc->radix_root, cic->dead_key);
	hlist_del_rcu(&cic->cic_list);
	spin_unlock_irqrestore(&ioc->lock, flags);

	cfq_cic_free(cic);
}

/*
 * Must be called with rcu_read_lock() held or preemption otherwise disabled.
 * Only two callers of this - ->dtor() which is called with the rcu_read_lock(),
 * and ->trim() which is called with the task lock held
 */
static void cfq_free_io_context(struct io_context *ioc)
{
	/*
	 * ioc->refcount is zero here, or we are called from elv_unregister(),
	 * so no more cic's are allowed to be linked into this ioc.  So it
	 * should be ok to iterate over the known list, we will see all cic's
	 * since no new ones are added.
	 */
	__call_for_each_cic(ioc, cic_free_func);
}

static void cfq_exit_cfqq(struct cfq_data *cfqd, struct cfq_queue *cfqq)
{
	struct cfq_queue *__cfqq, *next;

	if (unlikely(cfqq == cfqd->active_queue)) {
		__cfq_slice_expired(cfqd, cfqq, 0);
		cfq_schedule_dispatch(cfqd);
	}

	/*
	 * If this queue was scheduled to merge with another queue, be
	 * sure to drop the reference taken on that queue (and others in
	 * the merge chain).  See cfq_setup_merge and cfq_merge_cfqqs.
	 */
	__cfqq = cfqq->new_cfqq;
	while (__cfqq) {
		if (__cfqq == cfqq) {
			WARN(1, "cfqq->new_cfqq loop detected\n");
			break;
		}
		next = __cfqq->new_cfqq;
		cfq_put_queue(__cfqq);
		__cfqq = next;
	}

	cfq_put_queue(cfqq);
}

static void __cfq_exit_single_io_context(struct cfq_data *cfqd,
					 struct cfq_io_context *cic)
{
	struct io_context *ioc = cic->ioc;

	list_del_init(&cic->queue_list);

	/*
	 * Make sure key == NULL is seen for dead queues
	 */
	smp_wmb();
	cic->dead_key = (unsigned long) cic->key;
	cic->key = NULL;

	if (ioc->ioc_data == cic)
		rcu_assign_pointer(ioc->ioc_data, NULL);

	if (cic->cfqq[BLK_RW_ASYNC]) {
		cfq_exit_cfqq(cfqd, cic->cfqq[BLK_RW_ASYNC]);
		cic->cfqq[BLK_RW_ASYNC] = NULL;
	}

	if (cic->cfqq[BLK_RW_SYNC]) {
		cfq_exit_cfqq(cfqd, cic->cfqq[BLK_RW_SYNC]);
		cic->cfqq[BLK_RW_SYNC] = NULL;
	}
}

static void cfq_exit_single_io_context(struct io_context *ioc,
				       struct cfq_io_context *cic)
{
	struct cfq_data *cfqd = cic->key;

	if (cfqd) {
		struct request_queue *q = cfqd->queue;
		unsigned long flags;

		spin_lock_irqsave(q->queue_lock, flags);

		/*
		 * Ensure we get a fresh copy of the ->key to prevent
		 * race between exiting task and queue
		 */
		smp_read_barrier_depends();
		if (cic->key)
			__cfq_exit_single_io_context(cfqd, cic);

		spin_unlock_irqrestore(q->queue_lock, flags);
	}
}

/*
 * The process that ioc belongs to has exited, we need to clean up
 * and put the internal structures we have that belongs to that process.
 */
static void cfq_exit_io_context(struct io_context *ioc)
{
	call_for_each_cic(ioc, cfq_exit_single_io_context);
}

static struct cfq_io_context *
cfq_alloc_io_context(struct cfq_data *cfqd, gfp_t gfp_mask)
{
	struct cfq_io_context *cic;

	cic = kmem_cache_alloc_node(cfq_ioc_pool, gfp_mask | __GFP_ZERO,
							cfqd->queue->node);
	if (cic) {
		cic->last_end_request = jiffies;
		INIT_LIST_HEAD(&cic->queue_list);
		INIT_HLIST_NODE(&cic->cic_list);
		cic->dtor = cfq_free_io_context;
		cic->exit = cfq_exit_io_context;
		elv_ioc_count_inc(cfq_ioc_count);
	}

	return cic;
}

static void cfq_init_prio_data(struct cfq_queue *cfqq, struct io_context *ioc)
{
	struct task_struct *tsk = current;
	int ioprio_class;

	if (!cfq_cfqq_prio_changed(cfqq))
		return;

	ioprio_class = IOPRIO_PRIO_CLASS(ioc->ioprio);
	switch (ioprio_class) {
	default:
		printk(KERN_ERR "cfq: bad prio %x\n", ioprio_class);
	case IOPRIO_CLASS_NONE:
		/*
		 * no prio set, inherit CPU scheduling settings
		 */
		cfqq->ioprio = task_nice_ioprio(tsk);
		cfqq->ioprio_class = task_nice_ioclass(tsk);
		break;
	case IOPRIO_CLASS_RT:
		cfqq->ioprio = task_ioprio(ioc);
		cfqq->ioprio_class = IOPRIO_CLASS_RT;
		break;
	case IOPRIO_CLASS_BE:
		cfqq->ioprio = task_ioprio(ioc);
		cfqq->ioprio_class = IOPRIO_CLASS_BE;
		break;
	case IOPRIO_CLASS_IDLE:
		cfqq->ioprio_class = IOPRIO_CLASS_IDLE;
		cfqq->ioprio = 7;
		cfq_clear_cfqq_idle_window(cfqq);
		break;
	}

	/*
	 * keep track of original prio settings in case we have to temporarily
	 * elevate the priority of this queue
	 */
	cfqq->org_ioprio = cfqq->ioprio;
	cfqq->org_ioprio_class = cfqq->ioprio_class;
	cfq_clear_cfqq_prio_changed(cfqq);
}

static void changed_ioprio(struct io_context *ioc, struct cfq_io_context *cic)
{
	struct cfq_data *cfqd = cic->key;
	struct cfq_queue *cfqq;
	unsigned long flags;

	if (unlikely(!cfqd))
		return;

	spin_lock_irqsave(cfqd->queue->queue_lock, flags);

	cfqq = cic->cfqq[BLK_RW_ASYNC];
	if (cfqq) {
		struct cfq_queue *new_cfqq;
		new_cfqq = cfq_get_queue(cfqd, BLK_RW_ASYNC, cic->ioc,
						GFP_ATOMIC);
		if (new_cfqq) {
			cic->cfqq[BLK_RW_ASYNC] = new_cfqq;
			cfq_put_queue(cfqq);
		}
	}

	cfqq = cic->cfqq[BLK_RW_SYNC];
	if (cfqq)
		cfq_mark_cfqq_prio_changed(cfqq);

	spin_unlock_irqrestore(cfqd->queue->queue_lock, flags);
}

static void cfq_ioc_set_ioprio(struct io_context *ioc)
{
	call_for_each_cic(ioc, changed_ioprio);
	ioc->ioprio_changed = 0;
}

static void cfq_init_cfqq(struct cfq_data *cfqd, struct cfq_queue *cfqq,
			  pid_t pid, bool is_sync)
{
	RB_CLEAR_NODE(&cfqq->rb_node);
	RB_CLEAR_NODE(&cfqq->p_node);
	INIT_LIST_HEAD(&cfqq->fifo);

	atomic_set(&cfqq->ref, 0);
	cfqq->cfqd = cfqd;

	cfq_mark_cfqq_prio_changed(cfqq);

	if (is_sync) {
		if (!cfq_class_idle(cfqq))
			cfq_mark_cfqq_idle_window(cfqq);
		cfq_mark_cfqq_sync(cfqq);
	}
	cfqq->pid = pid;
}

#ifdef CONFIG_CFQ_GROUP_IOSCHED
static void changed_cgroup(struct io_context *ioc, struct cfq_io_context *cic)
{
	struct cfq_queue *sync_cfqq = cic_to_cfqq(cic, 1);
	struct cfq_data *cfqd = cic->key;
	unsigned long flags;
	struct request_queue *q;

	if (unlikely(!cfqd))
		return;

	q = cfqd->queue;

	spin_lock_irqsave(q->queue_lock, flags);

	if (sync_cfqq) {
		/*
		 * Drop reference to sync queue. A new sync queue will be
		 * assigned in new group upon arrival of a fresh request.
		 */
		cfq_log_cfqq(cfqd, sync_cfqq, "changed cgroup");
		cic_set_cfqq(cic, NULL, 1);
		cfq_put_queue(sync_cfqq);
	}

	spin_unlock_irqrestore(q->queue_lock, flags);
}

static void cfq_ioc_set_cgroup(struct io_context *ioc)
{
	call_for_each_cic(ioc, changed_cgroup);
	ioc->cgroup_changed = 0;
}
#endif  /* CONFIG_CFQ_GROUP_IOSCHED */

static struct cfq_queue *
cfq_find_alloc_queue(struct cfq_data *cfqd, bool is_sync,
		     struct io_context *ioc, gfp_t gfp_mask)
{
	struct cfq_queue *cfqq, *new_cfqq = NULL;
	struct cfq_io_context *cic;
	struct cfq_group *cfqg;

retry:
	cfqg = cfq_get_cfqg(cfqd, 1);
	cic = cfq_cic_lookup(cfqd, ioc);
	/* cic always exists here */
	cfqq = cic_to_cfqq(cic, is_sync);

	/*
	 * Always try a new alloc if we fell back to the OOM cfqq
	 * originally, since it should just be a temporary situation.
	 */
	if (!cfqq || cfqq == &cfqd->oom_cfqq) {
		cfqq = NULL;
		if (new_cfqq) {
			cfqq = new_cfqq;
			new_cfqq = NULL;
		} else if (gfp_mask & __GFP_WAIT) {
			spin_unlock_irq(cfqd->queue->queue_lock);
			new_cfqq = kmem_cache_alloc_node(cfq_pool,
					gfp_mask | __GFP_ZERO,
					cfqd->queue->node);
			spin_lock_irq(cfqd->queue->queue_lock);
			if (new_cfqq)
				goto retry;
		} else {
			cfqq = kmem_cache_alloc_node(cfq_pool,
					gfp_mask | __GFP_ZERO,
					cfqd->queue->node);
		}

		if (cfqq) {
			cfq_init_cfqq(cfqd, cfqq, current->pid, is_sync);
			cfq_init_prio_data(cfqq, ioc);
			cfq_link_cfqq_cfqg(cfqq, cfqg);
			cfq_log_cfqq(cfqd, cfqq, "alloced");
		} else
			cfqq = &cfqd->oom_cfqq;
	}

	if (new_cfqq)
		kmem_cache_free(cfq_pool, new_cfqq);

	return cfqq;
}

static struct cfq_queue **
cfq_async_queue_prio(struct cfq_data *cfqd, int ioprio_class, int ioprio)
{
	switch (ioprio_class) {
	case IOPRIO_CLASS_RT:
		return &cfqd->async_cfqq[0][ioprio];
	case IOPRIO_CLASS_BE:
		return &cfqd->async_cfqq[1][ioprio];
	case IOPRIO_CLASS_IDLE:
		return &cfqd->async_idle_cfqq;
	default:
		BUG();
	}
}

static struct cfq_queue *
cfq_get_queue(struct cfq_data *cfqd, bool is_sync, struct io_context *ioc,
	      gfp_t gfp_mask)
{
	const int ioprio = task_ioprio(ioc);
	const int ioprio_class = task_ioprio_class(ioc);
	struct cfq_queue **async_cfqq = NULL;
	struct cfq_queue *cfqq = NULL;

	if (!is_sync) {
		async_cfqq = cfq_async_queue_prio(cfqd, ioprio_class, ioprio);
		cfqq = *async_cfqq;
	}

	if (!cfqq)
		cfqq = cfq_find_alloc_queue(cfqd, is_sync, ioc, gfp_mask);

	/*
	 * pin the queue now that it's allocated, scheduler exit will prune it
	 */
	if (!is_sync && !(*async_cfqq)) {
		atomic_inc(&cfqq->ref);
		*async_cfqq = cfqq;
	}

	atomic_inc(&cfqq->ref);
	return cfqq;
}

/*
 * We drop cfq io contexts lazily, so we may find a dead one.
 */
static void
cfq_drop_dead_cic(struct cfq_data *cfqd, struct io_context *ioc,
		  struct cfq_io_context *cic)
{
	unsigned long flags;

	WARN_ON(!list_empty(&cic->queue_list));

	spin_lock_irqsave(&ioc->lock, flags);

	BUG_ON(ioc->ioc_data == cic);

	radix_tree_delete(&ioc->radix_root, (unsigned long) cfqd);
	hlist_del_rcu(&cic->cic_list);
	spin_unlock_irqrestore(&ioc->lock, flags);

	cfq_cic_free(cic);
}

static struct cfq_io_context *
cfq_cic_lookup(struct cfq_data *cfqd, struct io_context *ioc)
{
	struct cfq_io_context *cic;
	unsigned long flags;
	void *k;

	if (unlikely(!ioc))
		return NULL;

	rcu_read_lock();

	/*
	 * we maintain a last-hit cache, to avoid browsing over the tree
	 */
	cic = rcu_dereference(ioc->ioc_data);
	if (cic && cic->key == cfqd) {
		rcu_read_unlock();
		return cic;
	}

	do {
		cic = radix_tree_lookup(&ioc->radix_root, (unsigned long) cfqd);
		rcu_read_unlock();
		if (!cic)
			break;
		/* ->key must be copied to avoid race with cfq_exit_queue() */
		k = cic->key;
		if (unlikely(!k)) {
			cfq_drop_dead_cic(cfqd, ioc, cic);
			rcu_read_lock();
			continue;
		}

		spin_lock_irqsave(&ioc->lock, flags);
		rcu_assign_pointer(ioc->ioc_data, cic);
		spin_unlock_irqrestore(&ioc->lock, flags);
		break;
	} while (1);

	return cic;
}

/*
 * Add cic into ioc, using cfqd as the search key. This enables us to lookup
 * the process specific cfq io context when entered from the block layer.
 * Also adds the cic to a per-cfqd list, used when this queue is removed.
 */
static int cfq_cic_link(struct cfq_data *cfqd, struct io_context *ioc,
			struct cfq_io_context *cic, gfp_t gfp_mask)
{
	unsigned long flags;
	int ret;

	ret = radix_tree_preload(gfp_mask);
	if (!ret) {
		cic->ioc = ioc;
		cic->key = cfqd;

		spin_lock_irqsave(&ioc->lock, flags);
		ret = radix_tree_insert(&ioc->radix_root,
						(unsigned long) cfqd, cic);
		if (!ret)
			hlist_add_head_rcu(&cic->cic_list, &ioc->cic_list);
		spin_unlock_irqrestore(&ioc->lock, flags);

		radix_tree_preload_end();

		if (!ret) {
			spin_lock_irqsave(cfqd->queue->queue_lock, flags);
			list_add(&cic->queue_list, &cfqd->cic_list);
			spin_unlock_irqrestore(cfqd->queue->queue_lock, flags);
		}
	}

	if (ret)
		printk(KERN_ERR "cfq: cic link failed!\n");

	return ret;
}

/*
 * Setup general io context and cfq io context. There can be several cfq
 * io contexts per general io context, if this process is doing io to more
 * than one device managed by cfq.
 */
static struct cfq_io_context *
cfq_get_io_context(struct cfq_data *cfqd, gfp_t gfp_mask)
{
	struct io_context *ioc = NULL;
	struct cfq_io_context *cic;

	might_sleep_if(gfp_mask & __GFP_WAIT);

	ioc = get_io_context(gfp_mask, cfqd->queue->node);
	if (!ioc)
		return NULL;

	cic = cfq_cic_lookup(cfqd, ioc);
	if (cic)
		goto out;

	cic = cfq_alloc_io_context(cfqd, gfp_mask);
	if (cic == NULL)
		goto err;

	if (cfq_cic_link(cfqd, ioc, cic, gfp_mask))
		goto err_free;

out:
	smp_read_barrier_depends();
	if (unlikely(ioc->ioprio_changed))
		cfq_ioc_set_ioprio(ioc);

#ifdef CONFIG_CFQ_GROUP_IOSCHED
	if (unlikely(ioc->cgroup_changed))
		cfq_ioc_set_cgroup(ioc);
#endif
	return cic;
err_free:
	cfq_cic_free(cic);
err:
	put_io_context(ioc);
	return NULL;
}

static void
cfq_update_io_thinktime(struct cfq_data *cfqd, struct cfq_io_context *cic)
{
	unsigned long elapsed = jiffies - cic->last_end_request;
	unsigned long ttime = min(elapsed, 2UL * cfqd->cfq_slice_idle);

	cic->ttime_samples = (7*cic->ttime_samples + 256) / 8;
	cic->ttime_total = (7*cic->ttime_total + 256*ttime) / 8;
	cic->ttime_mean = (cic->ttime_total + 128) / cic->ttime_samples;
}

static void
cfq_update_io_seektime(struct cfq_data *cfqd, struct cfq_queue *cfqq,
		       struct request *rq)
{
	sector_t sdist = 0;
	sector_t n_sec = blk_rq_sectors(rq);
	if (cfqq->last_request_pos) {
		if (cfqq->last_request_pos < blk_rq_pos(rq))
			sdist = blk_rq_pos(rq) - cfqq->last_request_pos;
		else
			sdist = cfqq->last_request_pos - blk_rq_pos(rq);
	}

	cfqq->seek_history <<= 1;
	if (blk_queue_nonrot(cfqd->queue))
		cfqq->seek_history |= (n_sec < CFQQ_SECT_THR_NONROT);
	else
		cfqq->seek_history |= (sdist > CFQQ_SEEK_THR);
}

/*
 * Disable idle window if the process thinks too long or seeks so much that
 * it doesn't matter
 */
static void
cfq_update_idle_window(struct cfq_data *cfqd, struct cfq_queue *cfqq,
		       struct cfq_io_context *cic)
{
	int old_idle, enable_idle;

	/*
	 * Don't idle for async or idle io prio class
	 */
	if (!cfq_cfqq_sync(cfqq) || cfq_class_idle(cfqq))
		return;

	enable_idle = old_idle = cfq_cfqq_idle_window(cfqq);

	if (cfqq->queued[0] + cfqq->queued[1] >= 4)
		cfq_mark_cfqq_deep(cfqq);

	if (!atomic_read(&cic->ioc->nr_tasks) || !cfqd->cfq_slice_idle ||
	    (!cfq_cfqq_deep(cfqq) && CFQQ_SEEKY(cfqq)))
		enable_idle = 0;
	else if (sample_valid(cic->ttime_samples)) {
		if (cic->ttime_mean > cfqd->cfq_slice_idle)
			enable_idle = 0;
		else
			enable_idle = 1;
	}

	if (old_idle != enable_idle) {
		cfq_log_cfqq(cfqd, cfqq, "idle=%d", enable_idle);
		if (enable_idle)
			cfq_mark_cfqq_idle_window(cfqq);
		else
			cfq_clear_cfqq_idle_window(cfqq);
	}
}

/*
 * Check if new_cfqq should preempt the currently active queue. Return 0 for
 * no or if we aren't sure, a 1 will cause a preempt.
 */
static bool
cfq_should_preempt(struct cfq_data *cfqd, struct cfq_queue *new_cfqq,
		   struct request *rq)
{
	struct cfq_queue *cfqq;

	cfqq = cfqd->active_queue;
	if (!cfqq)
		return false;

	if (cfq_class_idle(new_cfqq))
		return false;

	if (cfq_class_idle(cfqq))
		return true;

	/*
	 * Don't allow a non-RT request to preempt an ongoing RT cfqq timeslice.
	 */
	if (cfq_class_rt(cfqq) && !cfq_class_rt(new_cfqq))
		return false;

	/*
	 * if the new request is sync, but the currently running queue is
	 * not, let the sync request have priority.
	 */
	if (rq_is_sync(rq) && !cfq_cfqq_sync(cfqq))
		return true;

	if (new_cfqq->cfqg != cfqq->cfqg)
		return false;

	if (cfq_slice_used(cfqq))
		return true;

	/* Allow preemption only if we are idling on sync-noidle tree */
	if (cfqd->serving_type == SYNC_NOIDLE_WORKLOAD &&
	    cfqq_type(new_cfqq) == SYNC_NOIDLE_WORKLOAD &&
	    new_cfqq->service_tree->count == 2 &&
	    RB_EMPTY_ROOT(&cfqq->sort_list))
		return true;

	/*
	 * So both queues are sync. Let the new request get disk time if
	 * it's a metadata request and the current queue is doing regular IO.
	 */
	if (rq_is_meta(rq) && !cfqq->meta_pending)
		return true;

	/*
	 * Allow an RT request to pre-empt an ongoing non-RT cfqq timeslice.
	 */
	if (cfq_class_rt(new_cfqq) && !cfq_class_rt(cfqq))
		return true;

	if (!cfqd->active_cic || !cfq_cfqq_wait_request(cfqq))
		return false;

	/*
	 * if this request is as-good as one we would expect from the
	 * current cfqq, let it preempt
	 */
	if (cfq_rq_close(cfqd, cfqq, rq, true))
		return true;

	return false;
}

/*
 * cfqq preempts the active queue. if we allowed preempt with no slice left,
 * let it have half of its nominal slice.
 */
static void cfq_preempt_queue(struct cfq_data *cfqd, struct cfq_queue *cfqq)
{
	cfq_log_cfqq(cfqd, cfqq, "preempt");
	cfq_slice_expired(cfqd, 1);

	/*
	 * Put the new queue at the front of the of the current list,
	 * so we know that it will be selected next.
	 */
	BUG_ON(!cfq_cfqq_on_rr(cfqq));

	cfq_service_tree_add(cfqd, cfqq, 1);

	cfqq->slice_end = 0;
	cfq_mark_cfqq_slice_new(cfqq);
}

/*
 * Called when a new fs request (rq) is added (to cfqq). Check if there's
 * something we should do about it
 */
static void
cfq_rq_enqueued(struct cfq_data *cfqd, struct cfq_queue *cfqq,
		struct request *rq)
{
	struct cfq_io_context *cic = RQ_CIC(rq);

	cfqd->rq_queued++;
	if (rq_is_meta(rq))
		cfqq->meta_pending++;

	cfq_update_io_thinktime(cfqd, cic);
	cfq_update_io_seektime(cfqd, cfqq, rq);
	cfq_update_idle_window(cfqd, cfqq, cic);

	cfqq->last_request_pos = blk_rq_pos(rq) + blk_rq_sectors(rq);

	if (cfqq == cfqd->active_queue) {
		/*
		 * Remember that we saw a request from this process, but
		 * don't start queuing just yet. Otherwise we risk seeing lots
		 * of tiny requests, because we disrupt the normal plugging
		 * and merging. If the request is already larger than a single
		 * page, let it rip immediately. For that case we assume that
		 * merging is already done. Ditto for a busy system that
		 * has other work pending, don't risk delaying until the
		 * idle timer unplug to continue working.
		 */
		if (cfq_cfqq_wait_request(cfqq)) {
			if (blk_rq_bytes(rq) > PAGE_CACHE_SIZE ||
			    cfqd->busy_queues > 1) {
				del_timer(&cfqd->idle_slice_timer);
				cfq_clear_cfqq_wait_request(cfqq);
				__blk_run_queue(cfqd->queue);
			} else
				cfq_mark_cfqq_must_dispatch(cfqq);
		}
	} else if (cfq_should_preempt(cfqd, cfqq, rq)) {
		/*
		 * not the active queue - expire current slice if it is
		 * idle and has expired it's mean thinktime or this new queue
		 * has some old slice time left and is of higher priority or
		 * this new queue is RT and the current one is BE
		 */
		cfq_preempt_queue(cfqd, cfqq);
		__blk_run_queue(cfqd->queue);
	}
}

static void cfq_insert_request(struct request_queue *q, struct request *rq)
{
	struct cfq_data *cfqd = q->elevator->elevator_data;
	struct cfq_queue *cfqq = RQ_CFQQ(rq);

	cfq_log_cfqq(cfqd, cfqq, "insert_request");
	cfq_init_prio_data(cfqq, RQ_CIC(rq)->ioc);

	rq_set_fifo_time(rq, jiffies + cfqd->cfq_fifo_expire[rq_is_sync(rq)]);
	list_add_tail(&rq->queuelist, &cfqq->fifo);
	cfq_add_rq_rb(rq);

	cfq_rq_enqueued(cfqd, cfqq, rq);
}

/*
 * Update hw_tag based on peak queue depth over 50 samples under
 * sufficient load.
 */
static void cfq_update_hw_tag(struct cfq_data *cfqd)
{
	struct cfq_queue *cfqq = cfqd->active_queue;

	if (cfqd->rq_in_driver > cfqd->hw_tag_est_depth)
		cfqd->hw_tag_est_depth = cfqd->rq_in_driver;

	if (cfqd->hw_tag == 1)
		return;

	if (cfqd->rq_queued <= CFQ_HW_QUEUE_MIN &&
	    cfqd->rq_in_driver <= CFQ_HW_QUEUE_MIN)
		return;

	/*
	 * If active queue hasn't enough requests and can idle, cfq might not
	 * dispatch sufficient requests to hardware. Don't zero hw_tag in this
	 * case
	 */
	if (cfqq && cfq_cfqq_idle_window(cfqq) &&
	    cfqq->dispatched + cfqq->queued[0] + cfqq->queued[1] <
	    CFQ_HW_QUEUE_MIN && cfqd->rq_in_driver < CFQ_HW_QUEUE_MIN)
		return;

	if (cfqd->hw_tag_samples++ < 50)
		return;

	if (cfqd->hw_tag_est_depth >= CFQ_HW_QUEUE_MIN)
		cfqd->hw_tag = 1;
	else
		cfqd->hw_tag = 0;
}

static bool cfq_should_wait_busy(struct cfq_data *cfqd, struct cfq_queue *cfqq)
{
	struct cfq_io_context *cic = cfqd->active_cic;

	/* If there are other queues in the group, don't wait */
	if (cfqq->cfqg->nr_cfqq > 1)
		return false;

	if (cfq_slice_used(cfqq))
		return true;

	/* if slice left is less than think time, wait busy */
	if (cic && sample_valid(cic->ttime_samples)
	    && (cfqq->slice_end - jiffies < cic->ttime_mean))
		return true;

	/*
	 * If think times is less than a jiffy than ttime_mean=0 and above
	 * will not be true. It might happen that slice has not expired yet
	 * but will expire soon (4-5 ns) during select_queue(). To cover the
	 * case where think time is less than a jiffy, mark the queue wait
	 * busy if only 1 jiffy is left in the slice.
	 */
	if (cfqq->slice_end - jiffies == 1)
		return true;

	return false;
}

static void cfq_completed_request(struct request_queue *q, struct request *rq)
{
	struct cfq_queue *cfqq = RQ_CFQQ(rq);
	struct cfq_data *cfqd = cfqq->cfqd;
	const int sync = rq_is_sync(rq);
	unsigned long now;

	now = jiffies;
	cfq_log_cfqq(cfqd, cfqq, "complete rqnoidle %d", !!rq_noidle(rq));

	cfq_update_hw_tag(cfqd);

	WARN_ON(!cfqd->rq_in_driver);
	WARN_ON(!cfqq->dispatched);
	cfqd->rq_in_driver--;
	cfqq->dispatched--;

	cfqd->rq_in_flight[cfq_cfqq_sync(cfqq)]--;

	if (sync) {
		RQ_CIC(rq)->last_end_request = now;
		if (!time_after(rq->start_time + cfqd->cfq_fifo_expire[1], now))
			cfqd->last_delayed_sync = now;
	}

	/*
	 * If this is the active queue, check if it needs to be expired,
	 * or if we want to idle in case it has no pending requests.
	 */
	if (cfqd->active_queue == cfqq) {
		const bool cfqq_empty = RB_EMPTY_ROOT(&cfqq->sort_list);

		if (cfq_cfqq_slice_new(cfqq)) {
			cfq_set_prio_slice(cfqd, cfqq);
			cfq_clear_cfqq_slice_new(cfqq);
		}

		/*
		 * Should we wait for next request to come in before we expire
		 * the queue.
		 */
		if (cfq_should_wait_busy(cfqd, cfqq)) {
			cfqq->slice_end = jiffies + cfqd->cfq_slice_idle;
			cfq_mark_cfqq_wait_busy(cfqq);
		}

		/*
		 * Idling is not enabled on:
		 * - expired queues
		 * - idle-priority queues
		 * - async queues
		 * - queues with still some requests queued
		 * - when there is a close cooperator
		 */
		if (cfq_slice_used(cfqq) || cfq_class_idle(cfqq))
			cfq_slice_expired(cfqd, 1);
		else if (sync && cfqq_empty &&
			 !cfq_close_cooperator(cfqd, cfqq)) {
			cfqd->noidle_tree_requires_idle |= !rq_noidle(rq);
			/*
			 * Idling is enabled for SYNC_WORKLOAD.
			 * SYNC_NOIDLE_WORKLOAD idles at the end of the tree
			 * only if we processed at least one !rq_noidle request
			 */
			if (cfqd->serving_type == SYNC_WORKLOAD
			    || cfqd->noidle_tree_requires_idle
			    || cfqq->cfqg->nr_cfqq == 1)
				cfq_arm_slice_timer(cfqd);
		}
	}

	if (!cfqd->rq_in_driver)
		cfq_schedule_dispatch(cfqd);
}

/*
 * we temporarily boost lower priority queues if they are holding fs exclusive
 * resources. they are boosted to normal prio (CLASS_BE/4)
 */
static void cfq_prio_boost(struct cfq_queue *cfqq)
{
	if (has_fs_excl()) {
		/*
		 * boost idle prio on transactions that would lock out other
		 * users of the filesystem
		 */
		if (cfq_class_idle(cfqq))
			cfqq->ioprio_class = IOPRIO_CLASS_BE;
		if (cfqq->ioprio > IOPRIO_NORM)
			cfqq->ioprio = IOPRIO_NORM;
	} else {
		/*
		 * unboost the queue (if needed)
		 */
		cfqq->ioprio_class = cfqq->org_ioprio_class;
		cfqq->ioprio = cfqq->org_ioprio;
	}
}

static inline int __cfq_may_queue(struct cfq_queue *cfqq)
{
	if (cfq_cfqq_wait_request(cfqq) && !cfq_cfqq_must_alloc_slice(cfqq)) {
		cfq_mark_cfqq_must_alloc_slice(cfqq);
		return ELV_MQUEUE_MUST;
	}

	return ELV_MQUEUE_MAY;
}

static int cfq_may_queue(struct request_queue *q, int rw)
{
	struct cfq_data *cfqd = q->elevator->elevator_data;
	struct task_struct *tsk = current;
	struct cfq_io_context *cic;
	struct cfq_queue *cfqq;