summaryrefslogtreecommitdiffstats
path: root/drivers/i2c/i2c-dev.c
blob: 6ecfd76270f2769fe5c9b0c21554977eeb563ccb (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
/*
    i2c-dev.c - i2c-bus driver, char device interface

    Copyright (C) 1995-97 Simon G. Vogl
    Copyright (C) 1998-99 Frodo Looijaard <frodol@dds.nl>
    Copyright (C) 2003 Greg Kroah-Hartman <greg@kroah.com>

    This program is free software; you can redistribute it and/or modify
    it under the terms of the GNU General Public License as published by
    the Free Software Foundation; either version 2 of the License, or
    (at your option) any later version.

    This program is distributed in the hope that it will be useful,
    but WITHOUT ANY WARRANTY; without even the implied warranty of
    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
    GNU General Public License for more details.
*/

/* Note that this is a complete rewrite of Simon Vogl's i2c-dev module.
   But I have used so much of his original code and ideas that it seems
   only fair to recognize him as co-author -- Frodo */

/* The I2C_RDWR ioctl code is written by Kolja Waschk <waschk@telos.de> */

#include <linux/cdev.h>
#include <linux/device.h>
#include <linux/fs.h>
#include <linux/i2c-dev.h>
#include <linux/i2c.h>
#include <linux/init.h>
#include <linux/jiffies.h>
#include <linux/kernel.h>
#include <linux/list.h>
#include <linux/module.h>
#include <linux/notifier.h>
#include <linux/slab.h>
#include <linux/uaccess.h>

/*
 * An i2c_dev represents an i2c_adapter ... an I2C or SMBus master, not a
 * slave (i2c_client) with which messages will be exchanged.  It's coupled
 * with a character special file which is accessed by user mode drivers.
 *
 * The list of i2c_dev structures is parallel to the i2c_adapter lists
 * maintained by the driver model, and is updated using bus notifications.
 */
struct i2c_dev {
	struct list_head list;
	struct i2c_adapter *adap;
	struct device *dev;
	struct cdev cdev;
};

#define I2C_MINORS	MINORMASK
static LIST_HEAD(i2c_dev_list);
static DEFINE_SPINLOCK(i2c_dev_list_lock);

static struct i2c_dev *i2c_dev_get_by_minor(unsigned index)
{
	struct i2c_dev *i2c_dev;

	spin_lock(&i2c_dev_list_lock);
	list_for_each_entry(i2c_dev, &i2c_dev_list, list) {
		if (i2c_dev->adap->nr == index)
			goto found;
	}
	i2c_dev = NULL;
found:
	spin_unlock(&i2c_dev_list_lock);
	return i2c_dev;
}

static struct i2c_dev *get_free_i2c_dev(struct i2c_adapter *adap)
{
	struct i2c_dev *i2c_dev;

	if (adap->nr >= I2C_MINORS) {
		printk(KERN_ERR "i2c-dev: Out of device minors (%d)\n",
		       adap->nr);
		return ERR_PTR(-ENODEV);
	}

	i2c_dev = kzalloc(sizeof(*i2c_dev), GFP_KERNEL);
	if (!i2c_dev)
		return ERR_PTR(-ENOMEM);
	i2c_dev->adap = adap;

	spin_lock(&i2c_dev_list_lock);
	list_add_tail(&i2c_dev->list, &i2c_dev_list);
	spin_unlock(&i2c_dev_list_lock);
	return i2c_dev;
}

static void put_i2c_dev(struct i2c_dev *i2c_dev)
{
	spin_lock(&i2c_dev_list_lock);
	list_del(&i2c_dev->list);
	spin_unlock(&i2c_dev_list_lock);
	kfree(i2c_dev);
}

static ssize_t name_show(struct device *dev,
			 struct device_attribute *attr, char *buf)
{
	struct i2c_dev *i2c_dev = i2c_dev_get_by_minor(MINOR(dev->devt));

	if (!i2c_dev)
		return -ENODEV;
	return sprintf(buf, "%s\n", i2c_dev->adap->name);
}
static DEVICE_ATTR_RO(name);

static struct attribute *i2c_attrs[] = {
	&dev_attr_name.attr,
	NULL,
};
ATTRIBUTE_GROUPS(i2c);

/* ------------------------------------------------------------------------- */

/*
 * After opening an instance of this character special file, a file
 * descriptor starts out associated only with an i2c_adapter (and bus).
 *
 * Using the I2C_RDWR ioctl(), you can then *immediately* issue i2c_msg
 * traffic to any devices on the bus used by that adapter.  That's because
 * the i2c_msg vectors embed all the addressing information they need, and
 * are submitted directly to an i2c_adapter.  However, SMBus-only adapters
 * don't support that interface.
 *
 * To use read()/write() system calls on that file descriptor, or to use
 * SMBus interfaces (and work with SMBus-only hosts!), you must first issue
 * an I2C_SLAVE (or I2C_SLAVE_FORCE) ioctl.  That configures an anonymous
 * (never registered) i2c_client so it holds the addressing information
 * needed by those system calls and by this SMBus interface.
 */

static ssize_t i2cdev_read(struct file *file, char __user *buf, size_t count,
		loff_t *offset)
{
	char *tmp;
	int ret;

	struct i2c_client *client = file->private_data;

	if (count > 8192)
		count = 8192;

	tmp = kmalloc(count, GFP_KERNEL);
	if (tmp == NULL)
		return -ENOMEM;

	pr_debug("i2c-dev: i2c-%d reading %zu bytes.\n",
		iminor(file_inode(file)), count);

	ret = i2c_master_recv(client, tmp, count);
	if (ret >= 0)
		ret = copy_to_user(buf, tmp, count) ? -EFAULT : ret;
	kfree(tmp);
	return ret;
}

static ssize_t i2cdev_write(struct file *file, const char __user *buf,
		size_t count, loff_t *offset)
{
	int ret;
	char *tmp;
	struct i2c_client *client = file->private_data;

	if (count > 8192)
		count = 8192;

	tmp = memdup_user(buf, count);
	if (IS_ERR(tmp))
		return PTR_ERR(tmp);

	pr_debug("i2c-dev: i2c-%d writing %zu bytes.\n",
		iminor(file_inode(file)), count);

	ret = i2c_master_send(client, tmp, count);
	kfree(tmp);
	return ret;
}

static int i2cdev_check(struct device *dev, void *addrp)
{
	struct i2c_client *client = i2c_verify_client(dev);

	if (!client || client->addr != *(unsigned int *)addrp)
		return 0;

	return dev->driver ? -EBUSY : 0;
}

/* walk up mux tree */
static int i2cdev_check_mux_parents(struct i2c_adapter *adapter, int addr)
{
	struct i2c_adapter *parent = i2c_parent_is_i2c_adapter(adapter);
	int result;

	result = device_for_each_child(&adapter->dev, &addr, i2cdev_check);
	if (!result && parent)
		result = i2cdev_check_mux_parents(parent, addr);

	return result;
}

/* recurse down mux tree */
static int i2cdev_check_mux_children(struct device *dev, void *addrp)
{
	int result;

	if (dev->type == &i2c_adapter_type)
		result = device_for_each_child(dev, addrp,
						i2cdev_check_mux_children);
	else
		result = i2cdev_check(dev, addrp);

	return result;
}

/* This address checking function differs from the one in i2c-core
   in that it considers an address with a registered device, but no
   driver bound to it, as NOT busy. */
static int i2cdev_check_addr(struct i2c_adapter *adapter, unsigned int addr)
{
	struct i2c_adapter *parent = i2c_parent_is_i2c_adapter(adapter);
	int result = 0;

	if (parent)
		result = i2cdev_check_mux_parents(parent, addr);

	if (!result)
		result = device_for_each_child(&adapter->dev, &addr,
						i2cdev_check_mux_children);

	return result;
}

static noinline int i2cdev_ioctl_rdwr(struct i2c_client *client,
		unsigned long arg)
{
	struct i2c_rdwr_ioctl_data rdwr_arg;
	struct i2c_msg *rdwr_pa;
	u8 __user **data_ptrs;
	int i, res;

	if (copy_from_user(&rdwr_arg,
			   (struct i2c_rdwr_ioctl_data __user *)arg,
			   sizeof(rdwr_arg)))
		return -EFAULT;

	/* Put an arbitrary limit on the number of messages that can
	 * be sent at once */
	if (rdwr_arg.nmsgs > I2C_RDWR_IOCTL_MAX_MSGS)
		return -EINVAL;

	rdwr_pa = memdup_user(rdwr_arg.msgs,
			      rdwr_arg.nmsgs * sizeof(struct i2c_msg));
	if (IS_ERR(rdwr_pa))
		return PTR_ERR(rdwr_pa);

	data_ptrs = kmalloc(rdwr_arg.nmsgs * sizeof(u8 __user *), GFP_KERNEL);
	if (data_ptrs == NULL) {
		kfree(rdwr_pa);
		return -ENOMEM;
	}

	res = 0;
	for (i = 0; i < rdwr_arg.nmsgs; i++) {
		/* Limit the size of the message to a sane amount */
		if (rdwr_pa[i].len > 8192) {
			res = -EINVAL;
			break;
		}

		data_ptrs[i] = (u8 __user *)rdwr_pa[i].buf;
		rdwr_pa[i].buf = memdup_user(data_ptrs[i], rdwr_pa[i].len);
		if (IS_ERR(rdwr_pa[i].buf)) {
			res = PTR_ERR(rdwr_pa[i].buf);
			break;
		}

		/*
		 * If the message length is received from the slave (similar
		 * to SMBus block read), we must ensure that the buffer will
		 * be large enough to cope with a message length of
		 * I2C_SMBUS_BLOCK_MAX as this is the maximum underlying bus
		 * drivers allow. The first byte in the buffer must be
		 * pre-filled with the number of extra bytes, which must be
		 * at least one to hold the message length, but can be
		 * greater (for example to account for a checksum byte at
		 * the end of the message.)
		 */
		if (rdwr_pa[i].flags & I2C_M_RECV_LEN) {
			if (!(rdwr_pa[i].flags & I2C_M_RD) ||
			    rdwr_pa[i].buf[0] < 1 ||
			    rdwr_pa[i].len < rdwr_pa[i].buf[0] +
					     I2C_SMBUS_BLOCK_MAX) {
				res = -EINVAL;
				break;
			}

			rdwr_pa[i].len = rdwr_pa[i].buf[0];
		}
	}
	if (res < 0) {
		int j;
		for (j = 0; j < i; ++j)
			kfree(rdwr_pa[j].buf);
		kfree(data_ptrs);
		kfree(rdwr_pa);
		return res;
	}

	res = i2c_transfer(client->adapter, rdwr_pa, rdwr_arg.nmsgs);
	while (i-- > 0) {
		if (res >= 0 && (rdwr_pa[i].flags & I2C_M_RD)) {
			if (copy_to_user(data_ptrs[i], rdwr_pa[i].buf,
					 rdwr_pa[i].len))
				res = -EFAULT;
		}
		kfree(rdwr_pa[i].buf);
	}
	kfree(data_ptrs);
	kfree(rdwr_pa);
	return res;
}

static noinline int i2cdev_ioctl_smbus(struct i2c_client *client,
		unsigned long arg)
{
	struct i2c_smbus_ioctl_data data_arg;
	union i2c_smbus_data temp;
	int datasize, res;

	if (copy_from_user(&data_arg,
			   (struct i2c_smbus_ioctl_data __user *) arg,
			   sizeof(struct i2c_smbus_ioctl_data)))
		return -EFAULT;
	if ((data_arg.size != I2C_SMBUS_BYTE) &&
	    (data_arg.size != I2C_SMBUS_QUICK) &&
	    (data_arg.size != I2C_SMBUS_BYTE_DATA) &&
	    (data_arg.size != I2C_SMBUS_WORD_DATA) &&
	    (data_arg.size != I2C_SMBUS_PROC_CALL) &&
	    (data_arg.size != I2C_SMBUS_BLOCK_DATA) &&
	    (data_arg.size != I2C_SMBUS_I2C_BLOCK_BROKEN) &&
	    (data_arg.size != I2C_SMBUS_I2C_BLOCK_DATA) &&
	    (data_arg.size != I2C_SMBUS_BLOCK_PROC_CALL)) {
		dev_dbg(&client->adapter->dev,
			"size out of range (%x) in ioctl I2C_SMBUS.\n",
			data_arg.size);
		return -EINVAL;
	}
	/* Note that I2C_SMBUS_READ and I2C_SMBUS_WRITE are 0 and 1,
	   so the check is valid if size==I2C_SMBUS_QUICK too. */
	if ((data_arg.read_write != I2C_SMBUS_READ) &&
	    (data_arg.read_write != I2C_SMBUS_WRITE)) {
		dev_dbg(&client->adapter->dev,
			"read_write out of range (%x) in ioctl I2C_SMBUS.\n",
			data_arg.read_write);
		return -EINVAL;
	}

	/* Note that command values are always valid! */

	if ((data_arg.size == I2C_SMBUS_QUICK) ||
	    ((data_arg.size == I2C_SMBUS_BYTE) &&
	    (data_arg.read_write == I2C_SMBUS_WRITE)))
		/* These are special: we do not use data */
		return i2c_smbus_xfer(client->adapter, client->addr,
				      client->flags, data_arg.read_write,
				      data_arg.command, data_arg.size, NULL);

	if (data_arg.data == NULL) {
		dev_dbg(&client->adapter->dev,
			"data is NULL pointer in ioctl I2C_SMBUS.\n");
		return -EINVAL;
	}

	if ((data_arg.size == I2C_SMBUS_BYTE_DATA) ||
	    (data_arg.size == I2C_SMBUS_BYTE))
		datasize = sizeof(data_arg.data->byte);
	else if ((data_arg.size == I2C_SMBUS_WORD_DATA) ||
		 (data_arg.size == I2C_SMBUS_PROC_CALL))
		datasize = sizeof(data_arg.data->word);
	else /* size == smbus block, i2c block, or block proc. call */
		datasize = sizeof(data_arg.data->block);

	if ((data_arg.size == I2C_SMBUS_PROC_CALL) ||
	    (data_arg.size == I2C_SMBUS_BLOCK_PROC_CALL) ||
	    (data_arg.size == I2C_SMBUS_I2C_BLOCK_DATA) ||
	    (data_arg.read_write == I2C_SMBUS_WRITE)) {
		if (copy_from_user(&temp, data_arg.data, datasize))
			return -EFAULT;
	}
	if (data_arg.size == I2C_SMBUS_I2C_BLOCK_BROKEN) {
		/* Convert old I2C block commands to the new
		   convention. This preserves binary compatibility. */
		data_arg.size = I2C_SMBUS_I2C_BLOCK_DATA;
		if (data_arg.read_write == I2C_SMBUS_READ)
			temp.block[0] = I2C_SMBUS_BLOCK_MAX;
	}
	res = i2c_smbus_xfer(client->adapter, client->addr, client->flags,
	      data_arg.read_write, data_arg.command, data_arg.size, &temp);
	if (!res && ((data_arg.size == I2C_SMBUS_PROC_CALL) ||
		     (data_arg.size == I2C_SMBUS_BLOCK_PROC_CALL) ||
		     (data_arg.read_write == I2C_SMBUS_READ))) {
		if (copy_to_user(data_arg.data, &temp, datasize))
			return -EFAULT;
	}
	return res;
}

static long i2cdev_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
{
	struct i2c_client *client = file->private_data;
	unsigned long funcs;

	dev_dbg(&client->adapter->dev, "ioctl, cmd=0x%02x, arg=0x%02lx\n",
		cmd, arg);

	switch (cmd) {
	case I2C_SLAVE:
	case I2C_SLAVE_FORCE:
		if ((arg > 0x3ff) ||
		    (((client->flags & I2C_M_TEN) == 0) && arg > 0x7f))
			return -EINVAL;
		if (cmd == I2C_SLAVE && i2cdev_check_addr(client->adapter, arg))
			return -EBUSY;
		/* REVISIT: address could become busy later */
		client->addr = arg;
		return 0;
	case I2C_TENBIT:
		if (arg)
			client->flags |= I2C_M_TEN;
		else
			client->flags &= ~I2C_M_TEN;
		return 0;
	case I2C_PEC:
		/*
		 * Setting the PEC flag here won't affect kernel drivers,
		 * which will be using the i2c_client node registered with
		 * the driver model core.  Likewise, when that client has
		 * the PEC flag already set, the i2c-dev driver won't see
		 * (or use) this setting.
		 */
		if (arg)
			client->flags |= I2C_CLIENT_PEC;
		else
			client->flags &= ~I2C_CLIENT_PEC;
		return 0;
	case I2C_FUNCS:
		funcs = i2c_get_functionality(client->adapter);
		return put_user(funcs, (unsigned long __user *)arg);

	case I2C_RDWR:
		return i2cdev_ioctl_rdwr(client, arg);

	case I2C_SMBUS:
		return i2cdev_ioctl_smbus(client, arg);

	case I2C_RETRIES:
		client->adapter->retries = arg;
		break;
	case I2C_TIMEOUT:
		/* For historical reasons, user-space sets the timeout
		 * value in units of 10 ms.
		 */
		client->adapter->timeout = msecs_to_jiffies(arg * 10);
		break;
	default:
		/* NOTE:  returning a fault code here could cause trouble
		 * in buggy userspace code.  Some old kernel bugs returned
		 * zero in this case, and userspace code might accidentally
		 * have depended on that bug.
		 */
		return -ENOTTY;
	}
	return 0;
}

static int i2cdev_open(struct inode *inode, struct file *file)
{
	unsigned int minor = iminor(inode);
	struct i2c_client *client;
	struct i2c_adapter *adap;
	struct i2c_dev *i2c_dev;

	i2c_dev = i2c_dev_get_by_minor(minor);
	if (!i2c_dev)
		return -ENODEV;

	adap = i2c_get_adapter(i2c_dev->adap->nr);
	if (!adap)
		return -ENODEV;

	/* This creates an anonymous i2c_client, which may later be
	 * pointed to some address using I2C_SLAVE or I2C_SLAVE_FORCE.
	 *
	 * This client is ** NEVER REGISTERED ** with the driver model
	 * or I2C core code!!  It just holds private copies of addressing
	 * information and maybe a PEC flag.
	 */
	client = kzalloc(sizeof(*client), GFP_KERNEL);
	if (!client) {
		i2c_put_adapter(adap);
		return -ENOMEM;
	}
	snprintf(client->name, I2C_NAME_SIZE, "i2c-dev %d", adap->nr);

	client->adapter = adap;
	file->private_data = client;

	return 0;
}

static int i2cdev_release(struct inode *inode, struct file *file)
{
	struct i2c_client *client = file->private_data;

	i2c_put_adapter(client->adapter);
	kfree(client);
	file->private_data = NULL;

	return 0;
}

static const struct file_operations i2cdev_fops = {
	.owner		= THIS_MODULE,
	.llseek		= no_llseek,
	.read		= i2cdev_read,
	.write		= i2cdev_write,
	.unlocked_ioctl	= i2cdev_ioctl,
	.open		= i2cdev_open,
	.release	= i2cdev_release,
};

/* ------------------------------------------------------------------------- */

static struct class *i2c_dev_class;

static int i2cdev_attach_adapter(struct device *dev, void *dummy)
{
	struct i2c_adapter *adap;
	struct i2c_dev *i2c_dev;
	int res;

	if (dev->type != &i2c_adapter_type)
		return 0;
	adap = to_i2c_adapter(dev);

	i2c_dev = get_free_i2c_dev(adap);
	if (IS_ERR(i2c_dev))
		return PTR_ERR(i2c_dev);

	cdev_init(&i2c_dev->cdev, &i2cdev_fops);
	i2c_dev->cdev.owner = THIS_MODULE;
	res = cdev_add(&i2c_dev->cdev, MKDEV(I2C_MAJOR, adap->nr), 1);
	if (res)
		goto error_cdev;

	/* register this i2c device with the driver core */
	i2c_dev->dev = device_create(i2c_dev_class, &adap->dev,
				     MKDEV(I2C_MAJOR, adap->nr), NULL,
				     "i2c-%d", adap->nr);
	if (IS_ERR(i2c_dev->dev)) {
		res = PTR_ERR(i2c_dev->dev);
		goto error;
	}

	pr_debug("i2c-dev: adapter [%s] registered as minor %d\n",
		 adap->name, adap->nr);
	return 0;
error:
	cdev_del(&i2c_dev->cdev);
error_cdev:
	put_i2c_dev(i2c_dev);
	return res;
}

static int i2cdev_detach_adapter(struct device *dev, void *dummy)
{
	struct i2c_adapter *adap;
	struct i2c_dev *i2c_dev;

	if (dev->type != &i2c_adapter_type)
		return 0;
	adap = to_i2c_adapter(dev);

	i2c_dev = i2c_dev_get_by_minor(adap->nr);
	if (!i2c_dev) /* attach_adapter must have failed */
		return 0;

	cdev_del(&i2c_dev->cdev);
	put_i2c_dev(i2c_dev);
	device_destroy(i2c_dev_class, MKDEV(I2C_MAJOR, adap->nr));

	pr_debug("i2c-dev: adapter [%s] unregistered\n", adap->name);
	return 0;
}

static int i2cdev_notifier_call(struct notifier_block *nb, unsigned long action,
			 void *data)
{
	struct device *dev = data;

	switch (action) {
	case BUS_NOTIFY_ADD_DEVICE:
		return i2cdev_attach_adapter(dev, NULL);
	case BUS_NOTIFY_DEL_DEVICE:
		return i2cdev_detach_adapter(dev, NULL);
	}

	return 0;
}

static struct notifier_block i2cdev_notifier = {
	.notifier_call = i2cdev_notifier_call,
};

/* ------------------------------------------------------------------------- */

/*
 * module load/unload record keeping
 */

static int __init i2c_dev_init(void)
{
	int res;

	printk(KERN_INFO "i2c /dev entries driver\n");

	res = register_chrdev_region(MKDEV(I2C_MAJOR, 0), I2C_MINORS, "i2c");
	if (res)
		goto out;

	i2c_dev_class = class_create(THIS_MODULE, "i2c-dev");
	if (IS_ERR(i2c_dev_class)) {
		res = PTR_ERR(i2c_dev_class);
		goto out_unreg_chrdev;
	}
	i2c_dev_class->dev_groups = i2c_groups;

	/* Keep track of adapters which will be added or removed later */
	res = bus_register_notifier(&i2c_bus_type, &i2cdev_notifier);
	if (res)
		goto out_unreg_class;

	/* Bind to already existing adapters right away */
	i2c_for_each_dev(NULL, i2cdev_attach_adapter);

	return 0;

out_unreg_class:
	class_destroy(i2c_dev_class);
out_unreg_chrdev:
	unregister_chrdev_region(MKDEV(I2C_MAJOR, 0), I2C_MINORS);
out:
	printk(KERN_ERR "%s: Driver Initialisation failed\n", __FILE__);
	return res;
}

static void __exit i2c_dev_exit(void)
{
	bus_unregister_notifier(&i2c_bus_type, &i2cdev_notifier);
	i2c_for_each_dev(NULL, i2cdev_detach_adapter);
	class_destroy(i2c_dev_class);
	unregister_chrdev_region(MKDEV(I2C_MAJOR, 0), I2C_MINORS);
}

MODULE_AUTHOR("Frodo Looijaard <frodol@dds.nl> and "
		"Simon G. Vogl <simon@tk.uni-linz.ac.at>");
MODULE_DESCRIPTION("I2C /dev entries driver");
MODULE_LICENSE("GPL");

module_init(i2c_dev_init);
module_exit(i2c_dev_exit);
'#n2618'>2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656 4657 4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 4690 4691 4692 4693 4694 4695 4696 4697 4698 4699 4700 4701 4702 4703 4704 4705 4706 4707 4708 4709 4710 4711 4712 4713 4714 4715 4716 4717 4718 4719 4720 4721 4722 4723 4724 4725 4726 4727 4728 4729 4730 4731 4732 4733 4734 4735 4736 4737 4738 4739 4740 4741 4742 4743 4744 4745 4746 4747 4748 4749 4750 4751 4752 4753 4754 4755 4756 4757 4758 4759 4760 4761 4762 4763 4764 4765 4766 4767 4768 4769 4770 4771 4772 4773 4774 4775 4776 4777 4778 4779 4780 4781 4782 4783 4784 4785 4786 4787 4788 4789 4790 4791 4792 4793 4794 4795 4796 4797 4798 4799 4800 4801 4802 4803 4804 4805 4806 4807 4808 4809 4810 4811 4812 4813 4814 4815 4816 4817 4818 4819 4820 4821 4822 4823 4824 4825 4826 4827 4828 4829 4830 4831 4832 4833 4834 4835 4836 4837 4838 4839 4840 4841 4842 4843 4844 4845 4846 4847 4848 4849 4850 4851 4852 4853 4854 4855 4856 4857 4858 4859 4860 4861 4862 4863 4864 4865 4866 4867 4868 4869 4870 4871 4872 4873 4874 4875 4876 4877 4878 4879 4880 4881 4882 4883 4884 4885 4886 4887 4888 4889 4890 4891 4892 4893 4894 4895 4896 4897 4898 4899 4900 4901 4902 4903 4904 4905 4906 4907 4908 4909 4910 4911 4912 4913 4914 4915 4916 4917 4918 4919 4920 4921 4922 4923 4924 4925 4926 4927 4928 4929 4930 4931 4932 4933 4934 4935 4936 4937 4938 4939 4940 4941 4942 4943 4944 4945 4946 4947 4948 4949 4950 4951 4952 4953 4954 4955 4956 4957 4958 4959 4960 4961 4962 4963 4964 4965 4966 4967 4968 4969 4970 4971 4972 4973 4974 4975 4976 4977 4978 4979 4980 4981 4982 4983 4984 4985 4986 4987 4988 4989 4990 4991 4992 4993 4994 4995 4996 4997 4998 4999 5000 5001 5002 5003 5004 5005 5006 5007 5008 5009 5010 5011 5012 5013 5014 5015 5016 5017 5018 5019 5020 5021 5022 5023 5024 5025 5026 5027 5028 5029 5030 5031 5032 5033 5034 5035 5036 5037 5038 5039 5040 5041 5042 5043 5044 5045 5046 5047 5048 5049 5050 5051 5052 5053 5054 5055 5056 5057 5058 5059 5060 5061 5062 5063 5064 5065 5066 5067 5068 5069 5070 5071 5072 5073 5074 5075 5076 5077 5078 5079 5080 5081 5082 5083 5084 5085 5086 5087 5088 5089 5090 5091 5092 5093 5094 5095 5096 5097 5098 5099 5100 5101 5102 5103 5104 5105 5106 5107 5108 5109 5110 5111 5112 5113 5114 5115 5116 5117 5118 5119 5120 5121 5122 5123 5124 5125 5126 5127 5128 5129 5130 5131 5132 5133 5134 5135 5136 5137 5138 5139 5140 5141 5142 5143 5144 5145 5146 5147 5148 5149 5150 5151 5152 5153 5154 5155 5156 5157 5158 5159 5160 5161 5162 5163 5164 5165 5166 5167 5168 5169 5170 5171 5172 5173 5174 5175 5176 5177 5178 5179 5180 5181 5182 5183 5184 5185 5186 5187 5188 5189 5190 5191 5192 5193 5194 5195 5196 5197 5198 5199 5200 5201 5202 5203 5204 5205 5206 5207 5208 5209 5210 5211 5212 5213 5214 5215 5216 5217 5218 5219 5220 5221 5222 5223 5224 5225 5226 5227 5228 5229 5230 5231 5232 5233 5234 5235 5236 5237 5238 5239 5240 5241 5242 5243 5244 5245 5246 5247 5248 5249 5250 5251 5252 5253 5254 5255 5256 5257 5258 5259 5260 5261 5262 5263 5264 5265 5266 5267 5268 5269 5270 5271 5272 5273 5274 5275 5276 5277 5278 5279 5280 5281 5282 5283 5284 5285 5286 5287 5288 5289 5290 5291 5292 5293 5294 5295 5296 5297 5298 5299 5300 5301 5302 5303 5304 5305 5306 5307 5308 5309 5310 5311 5312 5313 5314 5315 5316 5317 5318 5319 5320 5321 5322 5323 5324 5325 5326 5327 5328 5329 5330 5331 5332 5333 5334 5335 5336 5337 5338 5339 5340 5341 5342 5343 5344 5345 5346 5347 5348 5349 5350 5351 5352 5353 5354 5355 5356 5357 5358 5359 5360 5361 5362 5363 5364 5365 5366 5367 5368 5369 5370 5371 5372 5373 5374 5375 5376 5377 5378 5379 5380 5381 5382 5383 5384 5385 5386 5387 5388 5389 5390 5391 5392 5393 5394 5395 5396 5397 5398 5399 5400 5401 5402 5403 5404 5405 5406 5407 5408 5409 5410 5411 5412 5413 5414 5415 5416 5417 5418 5419 5420 5421 5422 5423 5424 5425 5426 5427 5428 5429 5430 5431 5432 5433 5434 5435 5436 5437 5438 5439 5440 5441 5442 5443 5444 5445 5446 5447 5448 5449 5450 5451 5452 5453 5454 5455 5456 5457 5458 5459 5460 5461 5462 5463 5464 5465 5466 5467 5468 5469 5470 5471 5472 5473 5474 5475 5476 5477 5478 5479 5480 5481 5482 5483 5484 5485 5486 5487 5488 5489 5490 5491 5492 5493 5494 5495 5496 5497 5498 5499 5500 5501 5502 5503 5504 5505 5506 5507 5508 5509 5510 5511 5512 5513 5514 5515 5516 5517 5518 5519 5520 5521 5522 5523 5524 5525 5526 5527 5528 5529 5530 5531 5532 5533 5534 5535 5536 5537 5538 5539 5540 5541 5542 5543 5544 5545 5546 5547 5548 5549 5550 5551 5552 5553 5554 5555 5556 5557 5558 5559 5560 5561 5562 5563 5564 5565 5566 5567 5568 5569 5570 5571 5572 5573 5574 5575 5576 5577 5578 5579 5580 5581 5582 5583 5584 5585 5586 5587 5588 5589 5590 5591 5592 5593 5594 5595 5596 5597 5598 5599 5600 5601 5602 5603 5604 5605 5606 5607 5608 5609 5610 5611 5612 5613 5614 5615 5616 5617 5618 5619 5620 5621 5622 5623 5624 5625 5626 5627 5628 5629 5630 5631 5632 5633 5634 5635 5636 5637 5638 5639 5640 5641 5642 5643 5644 5645 5646 5647 5648 5649 5650 5651 5652 5653 5654 5655 5656 5657 5658 5659 5660 5661 5662 5663 5664 5665 5666 5667 5668 5669 5670 5671 5672 5673 5674 5675 5676 5677 5678 5679 5680 5681 5682 5683 5684 5685 5686 5687 5688 5689 5690 5691 5692 5693 5694 5695 5696 5697 5698 5699 5700 5701 5702 5703 5704 5705 5706 5707 5708 5709 5710 5711 5712 5713 5714 5715 5716 5717 5718 5719 5720 5721 5722 5723 5724 5725 5726 5727 5728 5729 5730 5731 5732 5733 5734 5735 5736 5737 5738 5739 5740 5741 5742 5743 5744 5745 5746 5747 5748 5749 5750 5751 5752 5753 5754 5755 5756 5757 5758 5759 5760 5761 5762 5763 5764 5765 5766 5767 5768 5769 5770 5771 5772 5773 5774 5775 5776 5777 5778 5779 5780 5781 5782 5783 5784 5785 5786 5787 5788 5789 5790 5791 5792 5793 5794 5795 5796 5797 5798 5799 5800 5801 5802 5803 5804 5805 5806 5807 5808 5809 5810 5811 5812 5813 5814 5815 5816 5817 5818 5819 5820 5821 5822 5823 5824 5825 5826 5827 5828 5829 5830 5831 5832 5833 5834 5835 5836 5837 5838 5839 5840 5841 5842 5843 5844 5845 5846 5847 5848 5849 5850 5851 5852 5853 5854 5855 5856 5857 5858 5859 5860 5861 5862 5863 5864 5865 5866 5867 5868 5869 5870 5871 5872 5873 5874 5875 5876 5877 5878 5879 5880 5881 5882 5883 5884 5885 5886 5887 5888 5889 5890 5891 5892 5893 5894 5895 5896 5897 5898 5899 5900 5901 5902 5903 5904 5905 5906 5907 5908 5909 5910 5911 5912 5913 5914 5915 5916 5917 5918 5919 5920 5921 5922 5923 5924 5925 5926 5927 5928 5929 5930 5931 5932 5933 5934 5935 5936 5937 5938 5939 5940 5941 5942 5943 5944 5945 5946 5947 5948 5949 5950 5951 5952 5953 5954 5955 5956 5957 5958 5959 5960 5961 5962 5963 5964 5965 5966 5967 5968 5969 5970 5971 5972 5973 5974 5975 5976 5977 5978 5979 5980 5981 5982 5983 5984 5985 5986 5987 5988 5989 5990 5991 5992 5993 5994 5995 5996 5997 5998 5999 6000 6001 6002 6003 6004 6005 6006 6007 6008 6009 6010 6011 6012 6013 6014 6015 6016 6017 6018 6019 6020 6021 6022 6023 6024 6025 6026 6027 6028 6029 6030 6031 6032 6033 6034 6035 6036 6037 6038 6039 6040 6041 6042 6043 6044 6045 6046 6047 6048 6049 6050 6051 6052 6053 6054 6055 6056 6057 6058 6059 6060 6061 6062 6063 6064 6065 6066 6067 6068 6069 6070 6071 6072 6073 6074 6075 6076 6077 6078 6079 6080 6081 6082 6083 6084 6085 6086 6087 6088 6089 6090 6091 6092 6093 6094 6095 6096 6097 6098 6099 6100 6101 6102 6103 6104 6105 6106 6107 6108 6109 6110 6111 6112 6113 6114 6115 6116 6117 6118 6119 6120 6121 6122 6123 6124 6125 6126 6127 6128 6129 6130 6131 6132 6133 6134 6135 6136 6137 6138 6139 6140 6141 6142 6143 6144 6145 6146 6147 6148 6149 6150 6151 6152 6153 6154 6155 6156 6157 6158 6159 6160 6161 6162 6163 6164 6165 6166 6167 6168 6169 6170 6171 6172 6173 6174 6175 6176 6177 6178 6179 6180 6181 6182 6183 6184 6185 6186 6187 6188 6189 6190 6191 6192 6193 6194 6195 6196 6197 6198 6199 6200 6201 6202 6203 6204 6205 6206 6207 6208 6209 6210 6211 6212 6213 6214 6215 6216 6217 6218 6219 6220 6221 6222 6223 6224 6225 6226 6227 6228 6229 6230 6231 6232 6233 6234 6235 6236 6237 6238 6239 6240 6241 6242 6243 6244 6245 6246 6247 6248 6249 6250 6251 6252 6253 6254 6255 6256 6257 6258 6259 6260 6261 6262 6263 6264 6265 6266 6267 6268 6269 6270 6271 6272 6273 6274 6275 6276 6277 6278 6279 6280 6281 6282 6283 6284 6285 6286 6287 6288 6289 6290 6291 6292 6293 6294 6295 6296 6297 6298 6299 6300 6301 6302 6303 6304 6305 6306 6307 6308 6309 6310 6311 6312 6313 6314 6315 6316 6317 6318 6319 6320 6321 6322 6323 6324 6325 6326 6327 6328 6329 6330 6331 6332 6333 6334 6335 6336 6337 6338 6339 6340 6341 6342 6343 6344 6345 6346 6347 6348 6349 6350 6351 6352 6353 6354 6355 6356 6357 6358 6359 6360 6361 6362 6363 6364 6365 6366 6367 6368 6369 6370 6371 6372 6373 6374 6375 6376 6377 6378 6379 6380 6381 6382 6383 6384 6385 6386 6387 6388 6389 6390 6391 6392 6393 6394 6395 6396 6397 6398 6399 6400 6401 6402 6403 6404 6405 6406 6407 6408 6409 6410 6411 6412 6413 6414 6415 6416 6417 6418 6419 6420 6421 6422 6423 6424 6425 6426 6427 6428 6429 6430 6431 6432 6433 6434 6435 6436 6437 6438 6439 6440 6441 6442 6443 6444 6445 6446 6447 6448 6449 6450 6451 6452 6453 6454 6455 6456 6457 6458 6459 6460 6461 6462 6463 6464 6465 6466 6467 6468 6469 6470 6471 6472 6473 6474 6475 6476 6477 6478 6479 6480 6481 6482 6483 6484 6485 6486 6487 6488 6489 6490 6491 6492 6493 6494 6495 6496 6497 6498 6499 6500 6501 6502 6503 6504 6505 6506 6507 6508 6509 6510 6511 6512 6513 6514 6515 6516 6517 6518 6519 6520 6521 6522 6523 6524 6525 6526 6527 6528 6529 6530 6531 6532 6533 6534 6535 6536 6537 6538 6539 6540 6541 6542 6543 6544 6545 6546 6547 6548 6549 6550 6551 6552 6553 6554 6555 6556 6557 6558 6559 6560 6561 6562 6563 6564 6565 6566 6567 6568 6569 6570 6571 6572 6573 6574 6575 6576 6577 6578 6579 6580 6581 6582 6583 6584 6585 6586 6587 6588 6589 6590 6591 6592 6593 6594 6595 6596 6597 6598 6599 6600 6601 6602 6603 6604 6605 6606 6607 6608 6609 6610 6611 6612 6613 6614 6615 6616 6617 6618 6619 6620 6621 6622 6623 6624 6625 6626 6627 6628 6629 6630 6631 6632 6633 6634 6635 6636 6637 6638 6639 6640 6641 6642 6643 6644 6645 6646 6647 6648 6649 6650 6651 6652 6653 6654 6655 6656 6657 6658 6659 6660 6661 6662 6663 6664 6665 6666 6667 6668 6669 6670 6671 6672 6673 6674 6675 6676 6677 6678 6679 6680 6681 6682 6683 6684 6685 6686 6687 6688 6689 6690 6691 6692 6693 6694 6695 6696 6697 6698 6699 6700 6701 6702 6703 6704 6705 6706 6707 6708 6709 6710 6711 6712 6713 6714 6715 6716 6717 6718 6719 6720 6721 6722 6723 6724 6725 6726 6727 6728 6729 6730 6731 6732 6733 6734 6735 6736 6737 6738 6739 6740 6741 6742 6743 6744 6745 6746 6747 6748 6749 6750 6751 6752 6753 6754 6755 6756 6757 6758 6759 6760 6761 6762 6763 6764 6765 6766 6767 6768 6769 6770 6771 6772 6773 6774 6775 6776 6777 6778 6779 6780 6781 6782 6783 6784 6785 6786 6787 6788 6789 6790 6791 6792 6793 6794 6795 6796 6797 6798 6799 6800 6801 6802 6803 6804 6805 6806 6807 6808 6809 6810 6811 6812 6813 6814 6815 6816 6817 6818 6819 6820 6821 6822 6823 6824 6825 6826 6827 6828 6829 6830 6831 6832 6833 6834 6835 6836 6837 6838 6839 6840 6841 6842 6843 6844 6845 6846 6847 6848 6849 6850 6851 6852 6853 6854 6855 6856 6857 6858 6859 6860 6861 6862 6863 6864 6865 6866 6867 6868 6869 6870 6871 6872 6873 6874 6875 6876 6877 6878 6879 6880 6881 6882 6883 6884 6885 6886 6887 6888 6889 6890 6891 6892 6893 6894 6895 6896 6897 6898 6899 6900 6901 6902 6903 6904 6905 6906 6907 6908 6909 6910 6911 6912 6913 6914 6915 6916 6917 6918 6919 6920 6921 6922 6923 6924 6925 6926 6927 6928 6929 6930 6931 6932 6933 6934 6935 6936 6937 6938 6939 6940 6941 6942 6943 6944 6945 6946 6947 6948 6949 6950 6951 6952 6953 6954 6955 6956 6957 6958 6959 6960 6961 6962 6963 6964 6965 6966 6967 6968 6969 6970 6971 6972 6973 6974 6975 6976 6977 6978 6979 6980 6981 6982 6983 6984 6985 6986 6987 6988 6989 6990 6991 6992 6993 6994 6995 6996 6997 6998 6999 7000 7001 7002 7003 7004 7005 7006 7007 7008 7009 7010 7011 7012 7013 7014 7015 7016 7017 7018 7019 7020 7021 7022 7023 7024 7025 7026 7027 7028 7029 7030 7031 7032 7033 7034 7035 7036 7037 7038 7039 7040 7041 7042 7043 7044 7045 7046 7047 7048 7049 7050 7051 7052 7053 7054 7055 7056 7057 7058 7059 7060 7061 7062 7063 7064 7065 7066 7067 7068 7069 7070 7071 7072 7073 7074 7075 7076 7077 7078 7079 7080 7081 7082 7083 7084 7085 7086 7087 7088 7089 7090 7091 7092 7093 7094 7095 7096 7097 7098 7099 7100 7101 7102 7103 7104 7105 7106 7107 7108 7109 7110 7111 7112 7113 7114 7115 7116 7117 7118 7119 7120 7121 7122 7123 7124 7125 7126 7127 7128 7129 7130 7131 7132 7133 7134 7135 7136 7137 7138 7139 7140 7141 7142 7143 7144 7145 7146 7147 7148 7149 7150 7151 7152 7153 7154 7155 7156 7157 7158 7159 7160 7161 7162 7163 7164 7165 7166 7167 7168 7169 7170 7171 7172 7173 7174 7175 7176 7177 7178 7179 7180 7181 7182 7183 7184 7185 7186 7187 7188 7189 7190 7191 7192 7193 7194 7195 7196 7197 7198 7199 7200 7201 7202 7203 7204 7205 7206 7207 7208 7209 7210 7211 7212 7213 7214 7215 7216 7217 7218 7219 7220 7221 7222 7223 7224 7225 7226 7227 7228 7229 7230 7231 7232 7233 7234 7235 7236 7237 7238 7239 7240 7241 7242 7243 7244 7245 7246 7247 7248 7249 7250 7251 7252 7253 7254 7255 7256 7257 7258 7259 7260 7261 7262 7263 7264 7265 7266 7267 7268 7269 7270 7271 7272 7273 7274 7275 7276 7277 7278 7279 7280 7281 7282 7283 7284 7285 7286 7287 7288 7289 7290 7291 7292 7293 7294 7295 7296 7297 7298 7299 7300 7301 7302 7303 7304 7305 7306 7307 7308 7309 7310 7311 7312 7313 7314 7315 7316 7317 7318 7319 7320 7321 7322 7323 7324 7325 7326 7327 7328 7329 7330 7331 7332 7333 7334 7335 7336 7337 7338 7339 7340 7341 7342 7343 7344 7345 7346 7347 7348 7349 7350 7351 7352 7353 7354 7355 7356 7357 7358 7359 7360 7361 7362 7363 7364 7365 7366 7367 7368 7369 7370 7371 7372 7373 7374 7375 7376 7377 7378 7379 7380 7381 7382 7383 7384 7385 7386 7387 7388 7389 7390 7391 7392 7393 7394 7395 7396 7397 7398 7399 7400 7401 7402 7403 7404 7405 7406 7407 7408 7409 7410 7411 7412 7413 7414 7415 7416 7417 7418 7419 7420 7421 7422 7423 7424 7425 7426 7427 7428 7429 7430 7431 7432 7433 7434 7435 7436 7437 7438 7439 7440 7441 7442 7443 7444 7445 7446 7447 7448 7449 7450 7451 7452 7453 7454 7455 7456 7457 7458 7459 7460 7461 7462 7463 7464 7465 7466 7467 7468 7469 7470 7471 7472 7473 7474 7475 7476 7477 7478 7479 7480 7481 7482 7483 7484 7485 7486 7487 7488 7489 7490 7491 7492 7493 7494 7495 7496 7497 7498 7499 7500 7501 7502 7503 7504 7505 7506 7507 7508 7509 7510 7511 7512 7513 7514 7515 7516 7517 7518 7519 7520 7521 7522 7523 7524 7525 7526 7527 7528 7529 7530 7531 7532 7533 7534 7535 7536 7537 7538 7539 7540 7541 7542 7543 7544 7545 7546 7547 7548 7549 7550 7551 7552 7553 7554 7555 7556 7557 7558 7559 7560 7561 7562 7563 7564 7565 7566 7567 7568 7569 7570 7571 7572 7573 7574 7575 7576 7577 7578 7579 7580 7581 7582 7583 7584 7585 7586 7587 7588 7589 7590 7591 7592 7593 7594 7595 7596 7597 7598 7599 7600 7601 7602 7603 7604 7605 7606 7607 7608 7609 7610 7611 7612 7613 7614 7615 7616 7617 7618 7619 7620 7621 7622 7623 7624 7625 7626 7627 7628 7629 7630 7631 7632 7633 7634 7635 7636 7637 7638 7639 7640 7641 7642 7643 7644 7645 7646 7647 7648 7649 7650 7651 7652 7653 7654 7655 7656 7657 7658 7659 7660 7661 7662 7663 7664 7665 7666 7667 7668 7669 7670 7671 7672 7673 7674 7675 7676 7677 7678 7679 7680 7681 7682 7683 7684 7685 7686 7687 7688 7689 7690 7691 7692 7693 7694 7695 7696 7697 7698 7699 7700 7701 7702 7703 7704 7705 7706 7707 7708 7709 7710 7711 7712 7713 7714 7715 7716 7717 7718 7719 7720 7721 7722 7723 7724 7725 7726 7727 7728 7729 7730 7731 7732 7733 7734 7735 7736 7737 7738 7739 7740 7741 7742 7743 7744 7745 7746 7747 7748 7749 7750 7751 7752 7753 7754 7755 7756 7757 7758 7759 7760 7761 7762 7763 7764 7765 7766 7767 7768 7769 7770 7771 7772 7773 7774 7775 7776 7777 7778 7779 7780 7781 7782 7783 7784 7785 7786 7787 7788 7789 7790 7791 7792 7793 7794 7795 7796 7797 7798 7799 7800 7801 7802 7803 7804 7805 7806 7807 7808 7809 7810 7811 7812 7813 7814 7815 7816 7817 7818 7819 7820 7821 7822 7823 7824 7825 7826 7827 7828 7829 7830 7831 7832 7833 7834 7835 7836 7837 7838 7839 7840 7841 7842 7843 7844 7845 7846 7847 7848 7849 7850 7851 7852 7853 7854 7855 7856 7857 7858 7859 7860 7861 7862 7863 7864 7865 7866 7867 7868 7869 7870 7871 7872 7873 7874 7875 7876 7877 7878 7879 7880 7881 7882 7883 7884 7885 7886 7887 7888 7889 7890 7891 7892 7893 7894 7895 7896 7897 7898 7899 7900 7901 7902 7903 7904 7905 7906 7907 7908 7909 7910 7911 7912 7913 7914 7915 7916 7917 7918 7919 7920 7921 7922 7923 7924 7925 7926 7927 7928 7929 7930 7931 7932 7933 7934 7935 7936 7937 7938 7939 7940 7941 7942 7943 7944 7945 7946 7947 7948 7949 7950 7951 7952 7953 7954 7955 7956 7957 7958 7959 7960 7961 7962 7963 7964 7965 7966 7967 7968 7969 7970 7971 7972 7973 7974 7975 7976 7977 7978 7979 7980
/*
 * raid5.c : Multiple Devices driver for Linux
 *	   Copyright (C) 1996, 1997 Ingo Molnar, Miguel de Icaza, Gadi Oxman
 *	   Copyright (C) 1999, 2000 Ingo Molnar
 *	   Copyright (C) 2002, 2003 H. Peter Anvin
 *
 * RAID-4/5/6 management functions.
 * Thanks to Penguin Computing for making the RAID-6 development possible
 * by donating a test server!
 *
 * 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, or (at your option)
 * any later version.
 *
 * You should have received a copy of the GNU General Public License
 * (for example /usr/src/linux/COPYING); if not, write to the Free
 * Software Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
 */

/*
 * BITMAP UNPLUGGING:
 *
 * The sequencing for updating the bitmap reliably is a little
 * subtle (and I got it wrong the first time) so it deserves some
 * explanation.
 *
 * We group bitmap updates into batches.  Each batch has a number.
 * We may write out several batches at once, but that isn't very important.
 * conf->seq_write is the number of the last batch successfully written.
 * conf->seq_flush is the number of the last batch that was closed to
 *    new additions.
 * When we discover that we will need to write to any block in a stripe
 * (in add_stripe_bio) we update the in-memory bitmap and record in sh->bm_seq
 * the number of the batch it will be in. This is seq_flush+1.
 * When we are ready to do a write, if that batch hasn't been written yet,
 *   we plug the array and queue the stripe for later.
 * When an unplug happens, we increment bm_flush, thus closing the current
 *   batch.
 * When we notice that bm_flush > bm_write, we write out all pending updates
 * to the bitmap, and advance bm_write to where bm_flush was.
 * This may occasionally write a bit out twice, but is sure never to
 * miss any bits.
 */

#include <linux/blkdev.h>
#include <linux/kthread.h>
#include <linux/raid/pq.h>
#include <linux/async_tx.h>
#include <linux/module.h>
#include <linux/async.h>
#include <linux/seq_file.h>
#include <linux/cpu.h>
#include <linux/slab.h>
#include <linux/ratelimit.h>
#include <linux/nodemask.h>
#include <linux/flex_array.h>
#include <trace/events/block.h>

#include "md.h"
#include "raid5.h"
#include "raid0.h"
#include "bitmap.h"

#define cpu_to_group(cpu) cpu_to_node(cpu)
#define ANY_GROUP NUMA_NO_NODE

static bool devices_handle_discard_safely = false;
module_param(devices_handle_discard_safely, bool, 0644);
MODULE_PARM_DESC(devices_handle_discard_safely,
		 "Set to Y if all devices in each array reliably return zeroes on reads from discarded regions");
static struct workqueue_struct *raid5_wq;
/*
 * Stripe cache
 */

#define NR_STRIPES		256
#define STRIPE_SIZE		PAGE_SIZE
#define STRIPE_SHIFT		(PAGE_SHIFT - 9)
#define STRIPE_SECTORS		(STRIPE_SIZE>>9)
#define	IO_THRESHOLD		1
#define BYPASS_THRESHOLD	1
#define NR_HASH			(PAGE_SIZE / sizeof(struct hlist_head))
#define HASH_MASK		(NR_HASH - 1)
#define MAX_STRIPE_BATCH	8

static inline struct hlist_head *stripe_hash(struct r5conf *conf, sector_t sect)
{
	int hash = (sect >> STRIPE_SHIFT) & HASH_MASK;
	return &conf->stripe_hashtbl[hash];
}

static inline int stripe_hash_locks_hash(sector_t sect)
{
	return (sect >> STRIPE_SHIFT) & STRIPE_HASH_LOCKS_MASK;
}

static inline void lock_device_hash_lock(struct r5conf *conf, int hash)
{
	spin_lock_irq(conf->hash_locks + hash);
	spin_lock(&conf->device_lock);
}

static inline void unlock_device_hash_lock(struct r5conf *conf, int hash)
{
	spin_unlock(&conf->device_lock);
	spin_unlock_irq(conf->hash_locks + hash);
}

static inline void lock_all_device_hash_locks_irq(struct r5conf *conf)
{
	int i;
	local_irq_disable();
	spin_lock(conf->hash_locks);
	for (i = 1; i < NR_STRIPE_HASH_LOCKS; i++)
		spin_lock_nest_lock(conf->hash_locks + i, conf->hash_locks);
	spin_lock(&conf->device_lock);
}

static inline void unlock_all_device_hash_locks_irq(struct r5conf *conf)
{
	int i;
	spin_unlock(&conf->device_lock);
	for (i = NR_STRIPE_HASH_LOCKS; i; i--)
		spin_unlock(conf->hash_locks + i - 1);
	local_irq_enable();
}

/* bio's attached to a stripe+device for I/O are linked together in bi_sector
 * order without overlap.  There may be several bio's per stripe+device, and
 * a bio could span several devices.
 * When walking this list for a particular stripe+device, we must never proceed
 * beyond a bio that extends past this device, as the next bio might no longer
 * be valid.
 * This function is used to determine the 'next' bio in the list, given the sector
 * of the current stripe+device
 */
static inline struct bio *r5_next_bio(struct bio *bio, sector_t sector)
{
	int sectors = bio_sectors(bio);
	if (bio->bi_iter.bi_sector + sectors < sector + STRIPE_SECTORS)
		return bio->bi_next;
	else
		return NULL;
}

/*
 * We maintain a biased count of active stripes in the bottom 16 bits of
 * bi_phys_segments, and a count of processed stripes in the upper 16 bits
 */
static inline int raid5_bi_processed_stripes(struct bio *bio)
{
	atomic_t *segments = (atomic_t *)&bio->bi_phys_segments;
	return (atomic_read(segments) >> 16) & 0xffff;
}

static inline int raid5_dec_bi_active_stripes(struct bio *bio)
{
	atomic_t *segments = (atomic_t *)&bio->bi_phys_segments;
	return atomic_sub_return(1, segments) & 0xffff;
}

static inline void raid5_inc_bi_active_stripes(struct bio *bio)
{
	atomic_t *segments = (atomic_t *)&bio->bi_phys_segments;
	atomic_inc(segments);
}

static inline void raid5_set_bi_processed_stripes(struct bio *bio,
	unsigned int cnt)
{
	atomic_t *segments = (atomic_t *)&bio->bi_phys_segments;
	int old, new;

	do {
		old = atomic_read(segments);
		new = (old & 0xffff) | (cnt << 16);
	} while (atomic_cmpxchg(segments, old, new) != old);
}

static inline void raid5_set_bi_stripes(struct bio *bio, unsigned int cnt)
{
	atomic_t *segments = (atomic_t *)&bio->bi_phys_segments;
	atomic_set(segments, cnt);
}

/* Find first data disk in a raid6 stripe */
static inline int raid6_d0(struct stripe_head *sh)
{
	if (sh->ddf_layout)
		/* ddf always start from first device */
		return 0;
	/* md starts just after Q block */
	if (sh->qd_idx == sh->disks - 1)
		return 0;
	else
		return sh->qd_idx + 1;
}
static inline int raid6_next_disk(int disk, int raid_disks)
{
	disk++;
	return (disk < raid_disks) ? disk : 0;
}

/* When walking through the disks in a raid5, starting at raid6_d0,
 * We need to map each disk to a 'slot', where the data disks are slot
 * 0 .. raid_disks-3, the parity disk is raid_disks-2 and the Q disk
 * is raid_disks-1.  This help does that mapping.
 */
static int raid6_idx_to_slot(int idx, struct stripe_head *sh,
			     int *count, int syndrome_disks)
{
	int slot = *count;

	if (sh->ddf_layout)
		(*count)++;
	if (idx == sh->pd_idx)
		return syndrome_disks;
	if (idx == sh->qd_idx)
		return syndrome_disks + 1;
	if (!sh->ddf_layout)
		(*count)++;
	return slot;
}

static void return_io(struct bio_list *return_bi)
{
	struct bio *bi;
	while ((bi = bio_list_pop(return_bi)) != NULL) {
		bi->bi_iter.bi_size = 0;
		trace_block_bio_complete(bdev_get_queue(bi->bi_bdev),
					 bi, 0);
		bio_endio(bi);
	}
}

static void print_raid5_conf (struct r5conf *conf);

static int stripe_operations_active(struct stripe_head *sh)
{
	return sh->check_state || sh->reconstruct_state ||
	       test_bit(STRIPE_BIOFILL_RUN, &sh->state) ||
	       test_bit(STRIPE_COMPUTE_RUN, &sh->state);
}

static void raid5_wakeup_stripe_thread(struct stripe_head *sh)
{
	struct r5conf *conf = sh->raid_conf;
	struct r5worker_group *group;
	int thread_cnt;
	int i, cpu = sh->cpu;

	if (!cpu_online(cpu)) {
		cpu = cpumask_any(cpu_online_mask);
		sh->cpu = cpu;
	}

	if (list_empty(&sh->lru)) {
		struct r5worker_group *group;
		group = conf->worker_groups + cpu_to_group(cpu);
		list_add_tail(&sh->lru, &group->handle_list);
		group->stripes_cnt++;
		sh->group = group;
	}

	if (conf->worker_cnt_per_group == 0) {
		md_wakeup_thread(conf->mddev->thread);
		return;
	}

	group = conf->worker_groups + cpu_to_group(sh->cpu);

	group->workers[0].working = true;
	/* at least one worker should run to avoid race */
	queue_work_on(sh->cpu, raid5_wq, &group->workers[0].work);

	thread_cnt = group->stripes_cnt / MAX_STRIPE_BATCH - 1;
	/* wakeup more workers */
	for (i = 1; i < conf->worker_cnt_per_group && thread_cnt > 0; i++) {
		if (group->workers[i].working == false) {
			group->workers[i].working = true;
			queue_work_on(sh->cpu, raid5_wq,
				      &group->workers[i].work);
			thread_cnt--;
		}
	}
}

static void do_release_stripe(struct r5conf *conf, struct stripe_head *sh,
			      struct list_head *temp_inactive_list)
{
	BUG_ON(!list_empty(&sh->lru));
	BUG_ON(atomic_read(&conf->active_stripes)==0);
	if (test_bit(STRIPE_HANDLE, &sh->state)) {
		if (test_bit(STRIPE_DELAYED, &sh->state) &&
		    !test_bit(STRIPE_PREREAD_ACTIVE, &sh->state))
			list_add_tail(&sh->lru, &conf->delayed_list);
		else if (test_bit(STRIPE_BIT_DELAY, &sh->state) &&
			   sh->bm_seq - conf->seq_write > 0)
			list_add_tail(&sh->lru, &conf->bitmap_list);
		else {
			clear_bit(STRIPE_DELAYED, &sh->state);
			clear_bit(STRIPE_BIT_DELAY, &sh->state);
			if (conf->worker_cnt_per_group == 0) {
				list_add_tail(&sh->lru, &conf->handle_list);
			} else {
				raid5_wakeup_stripe_thread(sh);
				return;
			}
		}
		md_wakeup_thread(conf->mddev->thread);
	} else {
		BUG_ON(stripe_operations_active(sh));
		if (test_and_clear_bit(STRIPE_PREREAD_ACTIVE, &sh->state))
			if (atomic_dec_return(&conf->preread_active_stripes)
			    < IO_THRESHOLD)
				md_wakeup_thread(conf->mddev->thread);
		atomic_dec(&conf->active_stripes);
		if (!test_bit(STRIPE_EXPANDING, &sh->state))
			list_add_tail(&sh->lru, temp_inactive_list);
	}
}

static void __release_stripe(struct r5conf *conf, struct stripe_head *sh,
			     struct list_head *temp_inactive_list)
{
	if (atomic_dec_and_test(&sh->count))
		do_release_stripe(conf, sh, temp_inactive_list);
}

/*
 * @hash could be NR_STRIPE_HASH_LOCKS, then we have a list of inactive_list
 *
 * Be careful: Only one task can add/delete stripes from temp_inactive_list at
 * given time. Adding stripes only takes device lock, while deleting stripes
 * only takes hash lock.
 */
static void release_inactive_stripe_list(struct r5conf *conf,
					 struct list_head *temp_inactive_list,
					 int hash)
{
	int size;
	bool do_wakeup = false;
	unsigned long flags;

	if (hash == NR_STRIPE_HASH_LOCKS) {
		size = NR_STRIPE_HASH_LOCKS;
		hash = NR_STRIPE_HASH_LOCKS - 1;
	} else
		size = 1;
	while (size) {
		struct list_head *list = &temp_inactive_list[size - 1];

		/*
		 * We don't hold any lock here yet, raid5_get_active_stripe() might
		 * remove stripes from the list
		 */
		if (!list_empty_careful(list)) {
			spin_lock_irqsave(conf->hash_locks + hash, flags);
			if (list_empty(conf->inactive_list + hash) &&
			    !list_empty(list))
				atomic_dec(&conf->empty_inactive_list_nr);
			list_splice_tail_init(list, conf->inactive_list + hash);
			do_wakeup = true;
			spin_unlock_irqrestore(conf->hash_locks + hash, flags);
		}
		size--;
		hash--;
	}

	if (do_wakeup) {
		wake_up(&conf->wait_for_stripe);
		if (atomic_read(&conf->active_stripes) == 0)
			wake_up(&conf->wait_for_quiescent);
		if (conf->retry_read_aligned)
			md_wakeup_thread(conf->mddev->thread);
	}
}

/* should hold conf->device_lock already */
static int release_stripe_list(struct r5conf *conf,
			       struct list_head *temp_inactive_list)
{
	struct stripe_head *sh;
	int count = 0;
	struct llist_node *head;

	head = llist_del_all(&conf->released_stripes);
	head = llist_reverse_order(head);
	while (head) {
		int hash;

		sh = llist_entry(head, struct stripe_head, release_list);
		head = llist_next(head);
		/* sh could be readded after STRIPE_ON_RELEASE_LIST is cleard */
		smp_mb();
		clear_bit(STRIPE_ON_RELEASE_LIST, &sh->state);
		/*
		 * Don't worry the bit is set here, because if the bit is set
		 * again, the count is always > 1. This is true for
		 * STRIPE_ON_UNPLUG_LIST bit too.
		 */
		hash = sh->hash_lock_index;
		__release_stripe(conf, sh, &temp_inactive_list[hash]);
		count++;
	}

	return count;
}

void raid5_release_stripe(struct stripe_head *sh)
{
	struct r5conf *conf = sh->raid_conf;
	unsigned long flags;
	struct list_head list;
	int hash;
	bool wakeup;

	/* Avoid release_list until the last reference.
	 */
	if (atomic_add_unless(&sh->count, -1, 1))
		return;

	if (unlikely(!conf->mddev->thread) ||
		test_and_set_bit(STRIPE_ON_RELEASE_LIST, &sh->state))
		goto slow_path;
	wakeup = llist_add(&sh->release_list, &conf->released_stripes);
	if (wakeup)
		md_wakeup_thread(conf->mddev->thread);
	return;
slow_path:
	local_irq_save(flags);
	/* we are ok here if STRIPE_ON_RELEASE_LIST is set or not */
	if (atomic_dec_and_lock(&sh->count, &conf->device_lock)) {
		INIT_LIST_HEAD(&list);
		hash = sh->hash_lock_index;
		do_release_stripe(conf, sh, &list);
		spin_unlock(&conf->device_lock);
		release_inactive_stripe_list(conf, &list, hash);
	}
	local_irq_restore(flags);
}

static inline void remove_hash(struct stripe_head *sh)
{
	pr_debug("remove_hash(), stripe %llu\n",
		(unsigned long long)sh->sector);

	hlist_del_init(&sh->hash);
}

static inline void insert_hash(struct r5conf *conf, struct stripe_head *sh)
{
	struct hlist_head *hp = stripe_hash(conf, sh->sector);

	pr_debug("insert_hash(), stripe %llu\n",
		(unsigned long long)sh->sector);

	hlist_add_head(&sh->hash, hp);
}

/* find an idle stripe, make sure it is unhashed, and return it. */
static struct stripe_head *get_free_stripe(struct r5conf *conf, int hash)
{
	struct stripe_head *sh = NULL;
	struct list_head *first;

	if (list_empty(conf->inactive_list + hash))
		goto out;
	first = (conf->inactive_list + hash)->next;
	sh = list_entry(first, struct stripe_head, lru);
	list_del_init(first);
	remove_hash(sh);
	atomic_inc(&conf->active_stripes);
	BUG_ON(hash != sh->hash_lock_index);
	if (list_empty(conf->inactive_list + hash))
		atomic_inc(&conf->empty_inactive_list_nr);
out:
	return sh;
}

static void shrink_buffers(struct stripe_head *sh)
{
	struct page *p;
	int i;
	int num = sh->raid_conf->pool_size;

	for (i = 0; i < num ; i++) {
		WARN_ON(sh->dev[i].page != sh->dev[i].orig_page);
		p = sh->dev[i].page;
		if (!p)
			continue;
		sh->dev[i].page = NULL;
		put_page(p);
	}
}

static int grow_buffers(struct stripe_head *sh, gfp_t gfp)
{
	int i;
	int num = sh->raid_conf->pool_size;

	for (i = 0; i < num; i++) {
		struct page *page;

		if (!(page = alloc_page(gfp))) {
			return 1;
		}
		sh->dev[i].page = page;
		sh->dev[i].orig_page = page;
	}
	return 0;
}

static void raid5_build_block(struct stripe_head *sh, int i, int previous);
static void stripe_set_idx(sector_t stripe, struct r5conf *conf, int previous,
			    struct stripe_head *sh);

static void init_stripe(struct stripe_head *sh, sector_t sector, int previous)
{
	struct r5conf *conf = sh->raid_conf;
	int i, seq;

	BUG_ON(atomic_read(&sh->count) != 0);
	BUG_ON(test_bit(STRIPE_HANDLE, &sh->state));
	BUG_ON(stripe_operations_active(sh));
	BUG_ON(sh->batch_head);

	pr_debug("init_stripe called, stripe %llu\n",
		(unsigned long long)sector);
retry:
	seq = read_seqcount_begin(&conf->gen_lock);
	sh->generation = conf->generation - previous;
	sh->disks = previous ? conf->previous_raid_disks : conf->raid_disks;
	sh->sector = sector;
	stripe_set_idx(sector, conf, previous, sh);
	sh->state = 0;

	for (i = sh->disks; i--; ) {
		struct r5dev *dev = &sh->dev[i];

		if (dev->toread || dev->read || dev->towrite || dev->written ||
		    test_bit(R5_LOCKED, &dev->flags)) {
			printk(KERN_ERR "sector=%llx i=%d %p %p %p %p %d\n",
			       (unsigned long long)sh->sector, i, dev->toread,
			       dev->read, dev->towrite, dev->written,
			       test_bit(R5_LOCKED, &dev->flags));
			WARN_ON(1);
		}
		dev->flags = 0;
		raid5_build_block(sh, i, previous);
	}
	if (read_seqcount_retry(&conf->gen_lock, seq))
		goto retry;
	sh->overwrite_disks = 0;
	insert_hash(conf, sh);
	sh->cpu = smp_processor_id();
	set_bit(STRIPE_BATCH_READY, &sh->state);
}

static struct stripe_head *__find_stripe(struct r5conf *conf, sector_t sector,
					 short generation)
{
	struct stripe_head *sh;

	pr_debug("__find_stripe, sector %llu\n", (unsigned long long)sector);
	hlist_for_each_entry(sh, stripe_hash(conf, sector), hash)
		if (sh->sector == sector && sh->generation == generation)
			return sh;
	pr_debug("__stripe %llu not in cache\n", (unsigned long long)sector);
	return NULL;
}

/*
 * Need to check if array has failed when deciding whether to:
 *  - start an array
 *  - remove non-faulty devices
 *  - add a spare
 *  - allow a reshape
 * This determination is simple when no reshape is happening.
 * However if there is a reshape, we need to carefully check
 * both the before and after sections.
 * This is because some failed devices may only affect one
 * of the two sections, and some non-in_sync devices may
 * be insync in the section most affected by failed devices.
 */
static int calc_degraded(struct r5conf *conf)
{
	int degraded, degraded2;
	int i;

	rcu_read_lock();
	degraded = 0;
	for (i = 0; i < conf->previous_raid_disks; i++) {
		struct md_rdev *rdev = rcu_dereference(conf->disks[i].rdev);
		if (rdev && test_bit(Faulty, &rdev->flags))
			rdev = rcu_dereference(conf->disks[i].replacement);
		if (!rdev || test_bit(Faulty, &rdev->flags))
			degraded++;
		else if (test_bit(In_sync, &rdev->flags))
			;
		else
			/* not in-sync or faulty.
			 * If the reshape increases the number of devices,
			 * this is being recovered by the reshape, so
			 * this 'previous' section is not in_sync.
			 * If the number of devices is being reduced however,
			 * the device can only be part of the array if
			 * we are reverting a reshape, so this section will
			 * be in-sync.
			 */
			if (conf->raid_disks >= conf->previous_raid_disks)
				degraded++;
	}
	rcu_read_unlock();
	if (conf->raid_disks == conf->previous_raid_disks)
		return degraded;
	rcu_read_lock();
	degraded2 = 0;
	for (i = 0; i < conf->raid_disks; i++) {
		struct md_rdev *rdev = rcu_dereference(conf->disks[i].rdev);
		if (rdev && test_bit(Faulty, &rdev->flags))
			rdev = rcu_dereference(conf->disks[i].replacement);
		if (!rdev || test_bit(Faulty, &rdev->flags))
			degraded2++;
		else if (test_bit(In_sync, &rdev->flags))
			;
		else
			/* not in-sync or faulty.
			 * If reshape increases the number of devices, this
			 * section has already been recovered, else it
			 * almost certainly hasn't.
			 */
			if (conf->raid_disks <= conf->previous_raid_disks)
				degraded2++;
	}
	rcu_read_unlock();
	if (degraded2 > degraded)
		return degraded2;
	return degraded;
}

static int has_failed(struct r5conf *conf)
{
	int degraded;

	if (conf->mddev->reshape_position == MaxSector)
		return conf->mddev->degraded > conf->max_degraded;

	degraded = calc_degraded(conf);
	if (degraded > conf->max_degraded)
		return 1;
	return 0;
}

struct stripe_head *
raid5_get_active_stripe(struct r5conf *conf, sector_t sector,
			int previous, int noblock, int noquiesce)
{
	struct stripe_head *sh;
	int hash = stripe_hash_locks_hash(sector);

	pr_debug("get_stripe, sector %llu\n", (unsigned long long)sector);

	spin_lock_irq(conf->hash_locks + hash);

	do {
		wait_event_lock_irq(conf->wait_for_quiescent,
				    conf->quiesce == 0 || noquiesce,
				    *(conf->hash_locks + hash));
		sh = __find_stripe(conf, sector, conf->generation - previous);
		if (!sh) {
			if (!test_bit(R5_INACTIVE_BLOCKED, &conf->cache_state)) {
				sh = get_free_stripe(conf, hash);
				if (!sh && !test_bit(R5_DID_ALLOC,
						     &conf->cache_state))
					set_bit(R5_ALLOC_MORE,
						&conf->cache_state);
			}
			if (noblock && sh == NULL)
				break;
			if (!sh) {
				set_bit(R5_INACTIVE_BLOCKED,
					&conf->cache_state);
				wait_event_lock_irq(
					conf->wait_for_stripe,
					!list_empty(conf->inactive_list + hash) &&
					(atomic_read(&conf->active_stripes)
					 < (conf->max_nr_stripes * 3 / 4)
					 || !test_bit(R5_INACTIVE_BLOCKED,
						      &conf->cache_state)),
					*(conf->hash_locks + hash));
				clear_bit(R5_INACTIVE_BLOCKED,
					  &conf->cache_state);
			} else {
				init_stripe(sh, sector, previous);
				atomic_inc(&sh->count);
			}
		} else if (!atomic_inc_not_zero(&sh->count)) {
			spin_lock(&conf->device_lock);
			if (!atomic_read(&sh->count)) {
				if (!test_bit(STRIPE_HANDLE, &sh->state))
					atomic_inc(&conf->active_stripes);
				BUG_ON(list_empty(&sh->lru) &&
				       !test_bit(STRIPE_EXPANDING, &sh->state));
				list_del_init(&sh->lru);
				if (sh->group) {
					sh->group->stripes_cnt--;
					sh->group = NULL;
				}
			}
			atomic_inc(&sh->count);
			spin_unlock(&conf->device_lock);
		}
	} while (sh == NULL);

	spin_unlock_irq(conf->hash_locks + hash);
	return sh;
}

static bool is_full_stripe_write(struct stripe_head *sh)
{
	BUG_ON(sh->overwrite_disks > (sh->disks - sh->raid_conf->max_degraded));
	return sh->overwrite_disks == (sh->disks - sh->raid_conf->max_degraded);
}

static void lock_two_stripes(struct stripe_head *sh1, struct stripe_head *sh2)
{
	local_irq_disable();
	if (sh1 > sh2) {
		spin_lock(&sh2->stripe_lock);
		spin_lock_nested(&sh1->stripe_lock, 1);
	} else {
		spin_lock(&sh1->stripe_lock);
		spin_lock_nested(&sh2->stripe_lock, 1);
	}
}

static void unlock_two_stripes(struct stripe_head *sh1, struct stripe_head *sh2)
{
	spin_unlock(&sh1->stripe_lock);
	spin_unlock(&sh2->stripe_lock);
	local_irq_enable();
}

/* Only freshly new full stripe normal write stripe can be added to a batch list */
static bool stripe_can_batch(struct stripe_head *sh)
{
	struct r5conf *conf = sh->raid_conf;

	if (conf->log)
		return false;
	return test_bit(STRIPE_BATCH_READY, &sh->state) &&
		!test_bit(STRIPE_BITMAP_PENDING, &sh->state) &&
		is_full_stripe_write(sh);
}

/* we only do back search */
static void stripe_add_to_batch_list(struct r5conf *conf, struct stripe_head *sh)
{
	struct stripe_head *head;
	sector_t head_sector, tmp_sec;
	int hash;
	int dd_idx;

	/* Don't cross chunks, so stripe pd_idx/qd_idx is the same */
	tmp_sec = sh->sector;
	if (!sector_div(tmp_sec, conf->chunk_sectors))
		return;
	head_sector = sh->sector - STRIPE_SECTORS;

	hash = stripe_hash_locks_hash(head_sector);
	spin_lock_irq(conf->hash_locks + hash);
	head = __find_stripe(conf, head_sector, conf->generation);
	if (head && !atomic_inc_not_zero(&head->count)) {
		spin_lock(&conf->device_lock);
		if (!atomic_read(&head->count)) {
			if (!test_bit(STRIPE_HANDLE, &head->state))
				atomic_inc(&conf->active_stripes);
			BUG_ON(list_empty(&head->lru) &&
			       !test_bit(STRIPE_EXPANDING, &head->state));
			list_del_init(&head->lru);
			if (head->group) {
				head->group->stripes_cnt--;
				head->group = NULL;
			}
		}
		atomic_inc(&head->count);
		spin_unlock(&conf->device_lock);
	}
	spin_unlock_irq(conf->hash_locks + hash);

	if (!head)
		return;
	if (!stripe_can_batch(head))
		goto out;

	lock_two_stripes(head, sh);
	/* clear_batch_ready clear the flag */
	if (!stripe_can_batch(head) || !stripe_can_batch(sh))
		goto unlock_out;

	if (sh->batch_head)
		goto unlock_out;

	dd_idx = 0;
	while (dd_idx == sh->pd_idx || dd_idx == sh->qd_idx)
		dd_idx++;
	if (head->dev[dd_idx].towrite->bi_rw != sh->dev[dd_idx].towrite->bi_rw)
		goto unlock_out;

	if (head->batch_head) {
		spin_lock(&head->batch_head->batch_lock);
		/* This batch list is already running */
		if (!stripe_can_batch(head)) {
			spin_unlock(&head->batch_head->batch_lock);
			goto unlock_out;
		}

		/*
		 * at this point, head's BATCH_READY could be cleared, but we
		 * can still add the stripe to batch list
		 */
		list_add(&sh->batch_list, &head->batch_list);
		spin_unlock(&head->batch_head->batch_lock);

		sh->batch_head = head->batch_head;
	} else {
		head->batch_head = head;
		sh->batch_head = head->batch_head;
		spin_lock(&head->batch_lock);
		list_add_tail(&sh->batch_list, &head->batch_list);
		spin_unlock(&head->batch_lock);
	}

	if (test_and_clear_bit(STRIPE_PREREAD_ACTIVE, &sh->state))
		if (atomic_dec_return(&conf->preread_active_stripes)
		    < IO_THRESHOLD)
			md_wakeup_thread(conf->mddev->thread);

	if (test_and_clear_bit(STRIPE_BIT_DELAY, &sh->state)) {
		int seq = sh->bm_seq;
		if (test_bit(STRIPE_BIT_DELAY, &sh->batch_head->state) &&
		    sh->batch_head->bm_seq > seq)
			seq = sh->batch_head->bm_seq;
		set_bit(STRIPE_BIT_DELAY, &sh->batch_head->state);
		sh->batch_head->bm_seq = seq;
	}

	atomic_inc(&sh->count);
unlock_out:
	unlock_two_stripes(head, sh);
out:
	raid5_release_stripe(head);
}

/* Determine if 'data_offset' or 'new_data_offset' should be used
 * in this stripe_head.
 */
static int use_new_offset(struct r5conf *conf, struct stripe_head *sh)
{
	sector_t progress = conf->reshape_progress;
	/* Need a memory barrier to make sure we see the value
	 * of conf->generation, or ->data_offset that was set before
	 * reshape_progress was updated.
	 */
	smp_rmb();
	if (progress == MaxSector)
		return 0;
	if (sh->generation == conf->generation - 1)
		return 0;
	/* We are in a reshape, and this is a new-generation stripe,
	 * so use new_data_offset.
	 */
	return 1;
}

static void
raid5_end_read_request(struct bio *bi);
static void
raid5_end_write_request(struct bio *bi);

static void ops_run_io(struct stripe_head *sh, struct stripe_head_state *s)
{
	struct r5conf *conf = sh->raid_conf;
	int i, disks = sh->disks;
	struct stripe_head *head_sh = sh;

	might_sleep();

	if (r5l_write_stripe(conf->log, sh) == 0)
		return;
	for (i = disks; i--; ) {
		int rw;
		int replace_only = 0;
		struct bio *bi, *rbi;
		struct md_rdev *rdev, *rrdev = NULL;

		sh = head_sh;
		if (test_and_clear_bit(R5_Wantwrite, &sh->dev[i].flags)) {
			if (test_and_clear_bit(R5_WantFUA, &sh->dev[i].flags))
				rw = WRITE_FUA;
			else
				rw = WRITE;
			if (test_bit(R5_Discard, &sh->dev[i].flags))
				rw |= REQ_DISCARD;
		} else if (test_and_clear_bit(R5_Wantread, &sh->dev[i].flags))
			rw = READ;
		else if (test_and_clear_bit(R5_WantReplace,
					    &sh->dev[i].flags)) {
			rw = WRITE;
			replace_only = 1;
		} else
			continue;
		if (test_and_clear_bit(R5_SyncIO, &sh->dev[i].flags))
			rw |= REQ_SYNC;

again:
		bi = &sh->dev[i].req;
		rbi = &sh->dev[i].rreq; /* For writing to replacement */

		rcu_read_lock();
		rrdev = rcu_dereference(conf->disks[i].replacement);
		smp_mb(); /* Ensure that if rrdev is NULL, rdev won't be */
		rdev = rcu_dereference(conf->disks[i].rdev);
		if (!rdev) {
			rdev = rrdev;
			rrdev = NULL;
		}
		if (rw & WRITE) {
			if (replace_only)
				rdev = NULL;
			if (rdev == rrdev)
				/* We raced and saw duplicates */
				rrdev = NULL;
		} else {
			if (test_bit(R5_ReadRepl, &head_sh->dev[i].flags) && rrdev)
				rdev = rrdev;
			rrdev = NULL;
		}

		if (rdev && test_bit(Faulty, &rdev->flags))
			rdev = NULL;
		if (rdev)
			atomic_inc(&rdev->nr_pending);
		if (rrdev && test_bit(Faulty, &rrdev->flags))
			rrdev = NULL;
		if (rrdev)
			atomic_inc(&rrdev->nr_pending);
		rcu_read_unlock();

		/* We have already checked bad blocks for reads.  Now
		 * need to check for writes.  We never accept write errors
		 * on the replacement, so we don't to check rrdev.
		 */
		while ((rw & WRITE) && rdev &&
		       test_bit(WriteErrorSeen, &rdev->flags)) {
			sector_t first_bad;
			int bad_sectors;
			int bad = is_badblock(rdev, sh->sector, STRIPE_SECTORS,
					      &first_bad, &bad_sectors);
			if (!bad)
				break;

			if (bad < 0) {
				set_bit(BlockedBadBlocks, &rdev->flags);
				if (!conf->mddev->external &&
				    conf->mddev->flags) {
					/* It is very unlikely, but we might
					 * still need to write out the
					 * bad block log - better give it
					 * a chance*/
					md_check_recovery(conf->mddev);
				}
				/*
				 * Because md_wait_for_blocked_rdev
				 * will dec nr_pending, we must
				 * increment it first.
				 */
				atomic_inc(&rdev->nr_pending);
				md_wait_for_blocked_rdev(rdev, conf->mddev);
			} else {
				/* Acknowledged bad block - skip the write */
				rdev_dec_pending(rdev, conf->mddev);
				rdev = NULL;
			}
		}

		if (rdev) {
			if (s->syncing || s->expanding || s->expanded
			    || s->replacing)
				md_sync_acct(rdev->bdev, STRIPE_SECTORS);

			set_bit(STRIPE_IO_STARTED, &sh->state);

			bio_reset(bi);
			bi->bi_bdev = rdev->bdev;
			bi->bi_rw = rw;
			bi->bi_end_io = (rw & WRITE)
				? raid5_end_write_request
				: raid5_end_read_request;
			bi->bi_private = sh;

			pr_debug("%s: for %llu schedule op %ld on disc %d\n",
				__func__, (unsigned long long)sh->sector,
				bi->bi_rw, i);
			atomic_inc(&sh->count);
			if (sh != head_sh)
				atomic_inc(&head_sh->count);
			if (use_new_offset(conf, sh))
				bi->bi_iter.bi_sector = (sh->sector
						 + rdev->new_data_offset);
			else
				bi->bi_iter.bi_sector = (sh->sector
						 + rdev->data_offset);
			if (test_bit(R5_ReadNoMerge, &head_sh->dev[i].flags))
				bi->bi_rw |= REQ_NOMERGE;

			if (test_bit(R5_SkipCopy, &sh->dev[i].flags))
				WARN_ON(test_bit(R5_UPTODATE, &sh->dev[i].flags));
			sh->dev[i].vec.bv_page = sh->dev[i].page;
			bi->bi_vcnt = 1;
			bi->bi_io_vec[0].bv_len = STRIPE_SIZE;
			bi->bi_io_vec[0].bv_offset = 0;
			bi->bi_iter.bi_size = STRIPE_SIZE;
			/*
			 * If this is discard request, set bi_vcnt 0. We don't
			 * want to confuse SCSI because SCSI will replace payload
			 */
			if (rw & REQ_DISCARD)
				bi->bi_vcnt = 0;
			if (rrdev)
				set_bit(R5_DOUBLE_LOCKED, &sh->dev[i].flags);

			if (conf->mddev->gendisk)
				trace_block_bio_remap(bdev_get_queue(bi->bi_bdev),
						      bi, disk_devt(conf->mddev->gendisk),
						      sh->dev[i].sector);
			generic_make_request(bi);
		}
		if (rrdev) {
			if (s->syncing || s->expanding || s->expanded
			    || s->replacing)
				md_sync_acct(rrdev->bdev, STRIPE_SECTORS);

			set_bit(STRIPE_IO_STARTED, &sh->state);

			bio_reset(rbi);
			rbi->bi_bdev = rrdev->bdev;
			rbi->bi_rw = rw;
			BUG_ON(!(rw & WRITE));
			rbi->bi_end_io = raid5_end_write_request;
			rbi->bi_private = sh;

			pr_debug("%s: for %llu schedule op %ld on "
				 "replacement disc %d\n",
				__func__, (unsigned long long)sh->sector,
				rbi->bi_rw, i);
			atomic_inc(&sh->count);
			if (sh != head_sh)
				atomic_inc(&head_sh->count);
			if (use_new_offset(conf, sh))
				rbi->bi_iter.bi_sector = (sh->sector
						  + rrdev->new_data_offset);
			else
				rbi->bi_iter.bi_sector = (sh->sector
						  + rrdev->data_offset);
			if (test_bit(R5_SkipCopy, &sh->dev[i].flags))
				WARN_ON(test_bit(R5_UPTODATE, &sh->dev[i].flags));
			sh->dev[i].rvec.bv_page = sh->dev[i].page;
			rbi->bi_vcnt = 1;
			rbi->bi_io_vec[0].bv_len = STRIPE_SIZE;
			rbi->bi_io_vec[0].bv_offset = 0;
			rbi->bi_iter.bi_size = STRIPE_SIZE;
			/*
			 * If this is discard request, set bi_vcnt 0. We don't
			 * want to confuse SCSI because SCSI will replace payload
			 */
			if (rw & REQ_DISCARD)
				rbi->bi_vcnt = 0;
			if (conf->mddev->gendisk)
				trace_block_bio_remap(bdev_get_queue(rbi->bi_bdev),
						      rbi, disk_devt(conf->mddev->gendisk),
						      sh->dev[i].sector);
			generic_make_request(rbi);
		}
		if (!rdev && !rrdev) {
			if (rw & WRITE)
				set_bit(STRIPE_DEGRADED, &sh->state);
			pr_debug("skip op %ld on disc %d for sector %llu\n",
				bi->bi_rw, i, (unsigned long long)sh->sector);
			clear_bit(R5_LOCKED, &sh->dev[i].flags);
			set_bit(STRIPE_HANDLE, &sh->state);
		}

		if (!head_sh->batch_head)
			continue;
		sh = list_first_entry(&sh->batch_list, struct stripe_head,
				      batch_list);
		if (sh != head_sh)
			goto again;
	}
}

static struct dma_async_tx_descriptor *
async_copy_data(int frombio, struct bio *bio, struct page **page,
	sector_t sector, struct dma_async_tx_descriptor *tx,
	struct stripe_head *sh)
{
	struct bio_vec bvl;
	struct bvec_iter iter;
	struct page *bio_page;
	int page_offset;
	struct async_submit_ctl submit;
	enum async_tx_flags flags = 0;

	if (bio->bi_iter.bi_sector >= sector)
		page_offset = (signed)(bio->bi_iter.bi_sector - sector) * 512;
	else
		page_offset = (signed)(sector - bio->bi_iter.bi_sector) * -512;

	if (frombio)
		flags |= ASYNC_TX_FENCE;
	init_async_submit(&submit, flags, tx, NULL, NULL, NULL);

	bio_for_each_segment(bvl, bio, iter) {
		int len = bvl.bv_len;
		int clen;
		int b_offset = 0;

		if (page_offset < 0) {
			b_offset = -page_offset;
			page_offset += b_offset;
			len -= b_offset;
		}

		if (len > 0 && page_offset + len > STRIPE_SIZE)
			clen = STRIPE_SIZE - page_offset;
		else
			clen = len;

		if (clen > 0) {
			b_offset += bvl.bv_offset;
			bio_page = bvl.bv_page;
			if (frombio) {
				if (sh->raid_conf->skip_copy &&
				    b_offset == 0 && page_offset == 0 &&
				    clen == STRIPE_SIZE)
					*page = bio_page;
				else
					tx = async_memcpy(*page, bio_page, page_offset,
						  b_offset, clen, &submit);
			} else
				tx = async_memcpy(bio_page, *page, b_offset,
						  page_offset, clen, &submit);
		}
		/* chain the operations */
		submit.depend_tx = tx;

		if (clen < len) /* hit end of page */
			break;
		page_offset +=  len;
	}

	return tx;
}

static void ops_complete_biofill(void *stripe_head_ref)
{
	struct stripe_head *sh = stripe_head_ref;
	struct bio_list return_bi = BIO_EMPTY_LIST;
	int i;

	pr_debug("%s: stripe %llu\n", __func__,
		(unsigned long long)sh->sector);

	/* clear completed biofills */
	for (i = sh->disks; i--; ) {
		struct r5dev *dev = &sh->dev[i];

		/* acknowledge completion of a biofill operation */
		/* and check if we need to reply to a read request,
		 * new R5_Wantfill requests are held off until
		 * !STRIPE_BIOFILL_RUN
		 */
		if (test_and_clear_bit(R5_Wantfill, &dev->flags)) {
			struct bio *rbi, *rbi2;

			BUG_ON(!dev->read);
			rbi = dev->read;
			dev->read = NULL;
			while (rbi && rbi->bi_iter.bi_sector <
				dev->sector + STRIPE_SECTORS) {
				rbi2 = r5_next_bio(rbi, dev->sector);
				if (!raid5_dec_bi_active_stripes(rbi))
					bio_list_add(&return_bi, rbi);
				rbi = rbi2;
			}
		}
	}
	clear_bit(STRIPE_BIOFILL_RUN, &sh->state);

	return_io(&return_bi);

	set_bit(STRIPE_HANDLE, &sh->state);
	raid5_release_stripe(sh);
}

static void ops_run_biofill(struct stripe_head *sh)
{
	struct dma_async_tx_descriptor *tx = NULL;
	struct async_submit_ctl submit;
	int i;

	BUG_ON(sh->batch_head);
	pr_debug("%s: stripe %llu\n", __func__,
		(unsigned long long)sh->sector);

	for (i = sh->disks; i--; ) {
		struct r5dev *dev = &sh->dev[i];
		if (test_bit(R5_Wantfill, &dev->flags)) {
			struct bio *rbi;
			spin_lock_irq(&sh->stripe_lock);
			dev->read = rbi = dev->toread;
			dev->toread = NULL;
			spin_unlock_irq(&sh->stripe_lock);
			while (rbi && rbi->bi_iter.bi_sector <
				dev->sector + STRIPE_SECTORS) {
				tx = async_copy_data(0, rbi, &dev->page,
					dev->sector, tx, sh);
				rbi = r5_next_bio(rbi, dev->sector);
			}
		}
	}

	atomic_inc(&sh->count);
	init_async_submit(&submit, ASYNC_TX_ACK, tx, ops_complete_biofill, sh, NULL);
	async_trigger_callback(&submit);
}

static void mark_target_uptodate(struct stripe_head *sh, int target)
{
	struct r5dev *tgt;

	if (target < 0)
		return;

	tgt = &sh->dev[target];
	set_bit(R5_UPTODATE, &tgt->flags);
	BUG_ON(!test_bit(R5_Wantcompute, &tgt->flags));
	clear_bit(R5_Wantcompute, &tgt->flags);
}

static void ops_complete_compute(void *stripe_head_ref)
{
	struct stripe_head *sh = stripe_head_ref;

	pr_debug("%s: stripe %llu\n", __func__,
		(unsigned long long)sh->sector);

	/* mark the computed target(s) as uptodate */
	mark_target_uptodate(sh, sh->ops.target);
	mark_target_uptodate(sh, sh->ops.target2);

	clear_bit(STRIPE_COMPUTE_RUN, &sh->state);
	if (sh->check_state == check_state_compute_run)
		sh->check_state = check_state_compute_result;
	set_bit(STRIPE_HANDLE, &sh->state);
	raid5_release_stripe(sh);
}

/* return a pointer to the address conversion region of the scribble buffer */
static addr_conv_t *to_addr_conv(struct stripe_head *sh,
				 struct raid5_percpu *percpu, int i)
{
	void *addr;

	addr = flex_array_get(percpu->scribble, i);
	return addr + sizeof(struct page *) * (sh->disks + 2);
}

/* return a pointer to the address conversion region of the scribble buffer */
static struct page **to_addr_page(struct raid5_percpu *percpu, int i)
{
	void *addr;

	addr = flex_array_get(percpu->scribble, i);
	return addr;
}

static struct dma_async_tx_descriptor *
ops_run_compute5(struct stripe_head *sh, struct raid5_percpu *percpu)
{
	int disks = sh->disks;
	struct page **xor_srcs = to_addr_page(percpu, 0);
	int target = sh->ops.target;
	struct r5dev *tgt = &sh->dev[target];
	struct page *xor_dest = tgt->page;
	int count = 0;
	struct dma_async_tx_descriptor *tx;
	struct async_submit_ctl submit;
	int i;

	BUG_ON(sh->batch_head);

	pr_debug("%s: stripe %llu block: %d\n",
		__func__, (unsigned long long)sh->sector, target);
	BUG_ON(!test_bit(R5_Wantcompute, &tgt->flags));

	for (i = disks; i--; )
		if (i != target)
			xor_srcs[count++] = sh->dev[i].page;

	atomic_inc(&sh->count);

	init_async_submit(&submit, ASYNC_TX_FENCE|ASYNC_TX_XOR_ZERO_DST, NULL,
			  ops_complete_compute, sh, to_addr_conv(sh, percpu, 0));
	if (unlikely(count == 1))
		tx = async_memcpy(xor_dest, xor_srcs[0], 0, 0, STRIPE_SIZE, &submit);
	else
		tx = async_xor(xor_dest, xor_srcs, 0, count, STRIPE_SIZE, &submit);

	return tx;
}

/* set_syndrome_sources - populate source buffers for gen_syndrome
 * @srcs - (struct page *) array of size sh->disks
 * @sh - stripe_head to parse
 *
 * Populates srcs in proper layout order for the stripe and returns the
 * 'count' of sources to be used in a call to async_gen_syndrome.  The P
 * destination buffer is recorded in srcs[count] and the Q destination
 * is recorded in srcs[count+1]].
 */
static int set_syndrome_sources(struct page **srcs,
				struct stripe_head *sh,
				int srctype)
{
	int disks = sh->disks;
	int syndrome_disks = sh->ddf_layout ? disks : (disks - 2);
	int d0_idx = raid6_d0(sh);
	int count;
	int i;

	for (i = 0; i < disks; i++)
		srcs[i] = NULL;

	count = 0;
	i = d0_idx;
	do {
		int slot = raid6_idx_to_slot(i, sh, &count, syndrome_disks);
		struct r5dev *dev = &sh->dev[i];

		if (i == sh->qd_idx || i == sh->pd_idx ||
		    (srctype == SYNDROME_SRC_ALL) ||
		    (srctype == SYNDROME_SRC_WANT_DRAIN &&
		     test_bit(R5_Wantdrain, &dev->flags)) ||
		    (srctype == SYNDROME_SRC_WRITTEN &&
		     dev->written))
			srcs[slot] = sh->dev[i].page;
		i = raid6_next_disk(i, disks);
	} while (i != d0_idx);

	return syndrome_disks;
}

static struct dma_async_tx_descriptor *
ops_run_compute6_1(struct stripe_head *sh, struct raid5_percpu *percpu)
{
	int disks = sh->disks;
	struct page **blocks = to_addr_page(percpu, 0);
	int target;
	int qd_idx = sh->qd_idx;
	struct dma_async_tx_descriptor *tx;
	struct async_submit_ctl submit;
	struct r5dev *tgt;
	struct page *dest;
	int i;
	int count;

	BUG_ON(sh->batch_head);
	if (sh->ops.target < 0)
		target = sh->ops.target2;
	else if (sh->ops.target2 < 0)
		target = sh->ops.target;
	else
		/* we should only have one valid target */
		BUG();
	BUG_ON(target < 0);
	pr_debug("%s: stripe %llu block: %d\n",
		__func__, (unsigned long long)sh->sector, target);

	tgt = &sh->dev[target];
	BUG_ON(!test_bit(R5_Wantcompute, &tgt->flags));
	dest = tgt->page;

	atomic_inc(&sh->count);

	if (target == qd_idx) {
		count = set_syndrome_sources(blocks, sh, SYNDROME_SRC_ALL);
		blocks[count] = NULL; /* regenerating p is not necessary */
		BUG_ON(blocks[count+1] != dest); /* q should already be set */
		init_async_submit(&submit, ASYNC_TX_FENCE, NULL,
				  ops_complete_compute, sh,
				  to_addr_conv(sh, percpu, 0));
		tx = async_gen_syndrome(blocks, 0, count+2, STRIPE_SIZE, &submit);
	} else {
		/* Compute any data- or p-drive using XOR */
		count = 0;
		for (i = disks; i-- ; ) {
			if (i == target || i == qd_idx)
				continue;
			blocks[count++] = sh->dev[i].page;
		}

		init_async_submit(&submit, ASYNC_TX_FENCE|ASYNC_TX_XOR_ZERO_DST,
				  NULL, ops_complete_compute, sh,
				  to_addr_conv(sh, percpu, 0));
		tx = async_xor(dest, blocks, 0, count, STRIPE_SIZE, &submit);
	}

	return tx;
}

static struct dma_async_tx_descriptor *
ops_run_compute6_2(struct stripe_head *sh, struct raid5_percpu *percpu)
{
	int i, count, disks = sh->disks;
	int syndrome_disks = sh->ddf_layout ? disks : disks-2;
	int d0_idx = raid6_d0(sh);
	int faila = -1, failb = -1;
	int target = sh->ops.target;
	int target2 = sh->ops.target2;
	struct r5dev *tgt = &sh->dev[target];
	struct r5dev *tgt2 = &sh->dev[target2];
	struct dma_async_tx_descriptor *tx;
	struct page **blocks = to_addr_page(percpu, 0);
	struct async_submit_ctl submit;

	BUG_ON(sh->batch_head);
	pr_debug("%s: stripe %llu block1: %d block2: %d\n",
		 __func__, (unsigned long long)sh->sector, target, target2);
	BUG_ON(target < 0 || target2 < 0);
	BUG_ON(!test_bit(R5_Wantcompute, &tgt->flags));
	BUG_ON(!test_bit(R5_Wantcompute, &tgt2->flags));

	/* we need to open-code set_syndrome_sources to handle the
	 * slot number conversion for 'faila' and 'failb'
	 */
	for (i = 0; i < disks ; i++)
		blocks[i] = NULL;
	count = 0;
	i = d0_idx;
	do {
		int slot = raid6_idx_to_slot(i, sh, &count, syndrome_disks);

		blocks[slot] = sh->dev[i].page;

		if (i == target)
			faila = slot;
		if (i == target2)
			failb = slot;
		i = raid6_next_disk(i, disks);
	} while (i != d0_idx);

	BUG_ON(faila == failb);
	if (failb < faila)
		swap(faila, failb);
	pr_debug("%s: stripe: %llu faila: %d failb: %d\n",
		 __func__, (unsigned long long)sh->sector, faila, failb);

	atomic_inc(&sh->count);

	if (failb == syndrome_disks+1) {
		/* Q disk is one of the missing disks */
		if (faila == syndrome_disks) {
			/* Missing P+Q, just recompute */
			init_async_submit(&submit, ASYNC_TX_FENCE, NULL,
					  ops_complete_compute, sh,
					  to_addr_conv(sh, percpu, 0));
			return async_gen_syndrome(blocks, 0, syndrome_disks+2,
						  STRIPE_SIZE, &submit);
		} else {
			struct page *dest;
			int data_target;
			int qd_idx = sh->qd_idx;

			/* Missing D+Q: recompute D from P, then recompute Q */
			if (target == qd_idx)
				data_target = target2;
			else
				data_target = target;

			count = 0;
			for (i = disks; i-- ; ) {
				if (i == data_target || i == qd_idx)
					continue;
				blocks[count++] = sh->dev[i].page;
			}
			dest = sh->dev[data_target].page;
			init_async_submit(&submit,
					  ASYNC_TX_FENCE|ASYNC_TX_XOR_ZERO_DST,
					  NULL, NULL, NULL,
					  to_addr_conv(sh, percpu, 0));
			tx = async_xor(dest, blocks, 0, count, STRIPE_SIZE,
				       &submit);

			count = set_syndrome_sources(blocks, sh, SYNDROME_SRC_ALL);
			init_async_submit(&submit, ASYNC_TX_FENCE, tx,
					  ops_complete_compute, sh,
					  to_addr_conv(sh, percpu, 0));
			return async_gen_syndrome(blocks, 0, count+2,
						  STRIPE_SIZE, &submit);
		}
	} else {
		init_async_submit(&submit, ASYNC_TX_FENCE, NULL,
				  ops_complete_compute, sh,
				  to_addr_conv(sh, percpu, 0));
		if (failb == syndrome_disks) {
			/* We're missing D+P. */
			return async_raid6_datap_recov(syndrome_disks+2,
						       STRIPE_SIZE, faila,
						       blocks, &submit);
		} else {
			/* We're missing D+D. */
			return async_raid6_2data_recov(syndrome_disks+2,
						       STRIPE_SIZE, faila, failb,
						       blocks, &submit);
		}
	}
}

static void ops_complete_prexor(void *stripe_head_ref)
{
	struct stripe_head *sh = stripe_head_ref;

	pr_debug("%s: stripe %llu\n", __func__,
		(unsigned long long)sh->sector);
}

static struct dma_async_tx_descriptor *
ops_run_prexor5(struct stripe_head *sh, struct raid5_percpu *percpu,
		struct dma_async_tx_descriptor *tx)
{
	int disks = sh->disks;
	struct page **xor_srcs = to_addr_page(percpu, 0);
	int count = 0, pd_idx = sh->pd_idx, i;
	struct async_submit_ctl submit;

	/* existing parity data subtracted */
	struct page *xor_dest = xor_srcs[count++] = sh->dev[pd_idx].page;

	BUG_ON(sh->batch_head);
	pr_debug("%s: stripe %llu\n", __func__,
		(unsigned long long)sh->sector);

	for (i = disks; i--; ) {
		struct r5dev *dev = &sh->dev[i];
		/* Only process blocks that are known to be uptodate */
		if (test_bit(R5_Wantdrain, &dev->flags))
			xor_srcs[count++] = dev->page;
	}

	init_async_submit(&submit, ASYNC_TX_FENCE|ASYNC_TX_XOR_DROP_DST, tx,
			  ops_complete_prexor, sh, to_addr_conv(sh, percpu, 0));
	tx = async_xor(xor_dest, xor_srcs, 0, count, STRIPE_SIZE, &submit);

	return tx;
}

static struct dma_async_tx_descriptor *
ops_run_prexor6(struct stripe_head *sh, struct raid5_percpu *percpu,
		struct dma_async_tx_descriptor *tx)
{
	struct page **blocks = to_addr_page(percpu, 0);
	int count;
	struct async_submit_ctl submit;

	pr_debug("%s: stripe %llu\n", __func__,
		(unsigned long long)sh->sector);

	count = set_syndrome_sources(blocks, sh, SYNDROME_SRC_WANT_DRAIN);

	init_async_submit(&submit, ASYNC_TX_FENCE|ASYNC_TX_PQ_XOR_DST, tx,
			  ops_complete_prexor, sh, to_addr_conv(sh, percpu, 0));
	tx = async_gen_syndrome(blocks, 0, count+2, STRIPE_SIZE,  &submit);

	return tx;
}

static struct dma_async_tx_descriptor *
ops_run_biodrain(struct stripe_head *sh, struct dma_async_tx_descriptor *tx)
{
	int disks = sh->disks;
	int i;
	struct stripe_head *head_sh = sh;

	pr_debug("%s: stripe %llu\n", __func__,
		(unsigned long long)sh->sector);

	for (i = disks; i--; ) {
		struct r5dev *dev;
		struct bio *chosen;

		sh = head_sh;
		if (test_and_clear_bit(R5_Wantdrain, &head_sh->dev[i].flags)) {
			struct bio *wbi;

again:
			dev = &sh->dev[i];
			spin_lock_irq(&sh->stripe_lock);
			chosen = dev->towrite;
			dev->towrite = NULL;
			sh->overwrite_disks = 0;
			BUG_ON(dev->written);
			wbi = dev->written = chosen;
			spin_unlock_irq(&sh->stripe_lock);
			WARN_ON(dev->page != dev->orig_page);

			while (wbi && wbi->bi_iter.bi_sector <
				dev->sector + STRIPE_SECTORS) {
				if (wbi->bi_rw & REQ_FUA)
					set_bit(R5_WantFUA, &dev->flags);
				if (wbi->bi_rw & REQ_SYNC)
					set_bit(R5_SyncIO, &dev->flags);
				if (wbi->bi_rw & REQ_DISCARD)
					set_bit(R5_Discard, &dev->flags);
				else {
					tx = async_copy_data(1, wbi, &dev->page,
						dev->sector, tx, sh);
					if (dev->page != dev->orig_page) {
						set_bit(R5_SkipCopy, &dev->flags);
						clear_bit(R5_UPTODATE, &dev->flags);
						clear_bit(R5_OVERWRITE, &dev->flags);
					}
				}
				wbi = r5_next_bio(wbi, dev->sector);
			}

			if (head_sh->batch_head) {
				sh = list_first_entry(&sh->batch_list,
						      struct stripe_head,
						      batch_list);
				if (sh == head_sh)
					continue;
				goto again;
			}
		}
	}

	return tx;
}

static void ops_complete_reconstruct(void *stripe_head_ref)
{
	struct stripe_head *sh = stripe_head_ref;
	int disks = sh->disks;
	int pd_idx = sh->pd_idx;
	int qd_idx = sh->qd_idx;
	int i;
	bool fua = false, sync = false, discard = false;

	pr_debug("%s: stripe %llu\n", __func__,
		(unsigned long long)sh->sector);

	for (i = disks; i--; ) {
		fua |= test_bit(R5_WantFUA, &sh->dev[i].flags);
		sync |= test_bit(R5_SyncIO, &sh->dev[i].flags);
		discard |= test_bit(R5_Discard, &sh->dev[i].flags);
	}

	for (i = disks; i--; ) {
		struct r5dev *dev = &sh->dev[i];

		if (dev->written || i == pd_idx || i == qd_idx) {
			if (!discard && !test_bit(R5_SkipCopy, &dev->flags))
				set_bit(R5_UPTODATE, &dev->flags);
			if (fua)
				set_bit(R5_WantFUA, &dev->flags);
			if (sync)
				set_bit(R5_SyncIO, &dev->flags);
		}
	}

	if (sh->reconstruct_state == reconstruct_state_drain_run)
		sh->reconstruct_state = reconstruct_state_drain_result;
	else if (sh->reconstruct_state == reconstruct_state_prexor_drain_run)
		sh->reconstruct_state = reconstruct_state_prexor_drain_result;
	else {
		BUG_ON(sh->reconstruct_state != reconstruct_state_run);
		sh->reconstruct_state = reconstruct_state_result;
	}

	set_bit(STRIPE_HANDLE, &sh->state);
	raid5_release_stripe(sh);
}

static void
ops_run_reconstruct5(struct stripe_head *sh, struct raid5_percpu *percpu,
		     struct dma_async_tx_descriptor *tx)
{
	int disks = sh->disks;
	struct page **xor_srcs;
	struct async_submit_ctl submit;
	int count, pd_idx = sh->pd_idx, i;
	struct page *xor_dest;
	int prexor = 0;
	unsigned long flags;
	int j = 0;
	struct stripe_head *head_sh = sh;
	int last_stripe;

	pr_debug("%s: stripe %llu\n", __func__,
		(unsigned long long)sh->sector);

	for (i = 0; i < sh->disks; i++) {
		if (pd_idx == i)
			continue;
		if (!test_bit(R5_Discard, &sh->dev[i].flags))
			break;
	}
	if (i >= sh->disks) {
		atomic_inc(&sh->count);
		set_bit(R5_Discard, &sh->dev[pd_idx].flags);
		ops_complete_reconstruct(sh);
		return;
	}
again:
	count = 0;
	xor_srcs = to_addr_page(percpu, j);
	/* check if prexor is active which means only process blocks
	 * that are part of a read-modify-write (written)
	 */
	if (head_sh->reconstruct_state == reconstruct_state_prexor_drain_run) {
		prexor = 1;
		xor_dest = xor_srcs[count++] = sh->dev[pd_idx].page;
		for (i = disks; i--; ) {
			struct r5dev *dev = &sh->dev[i];
			if (head_sh->dev[i].written)
				xor_srcs[count++] = dev->page;
		}
	} else {
		xor_dest = sh->dev[pd_idx].page;
		for (i = disks; i--; ) {
			struct r5dev *dev = &sh->dev[i];
			if (i != pd_idx)
				xor_srcs[count++] = dev->page;
		}
	}

	/* 1/ if we prexor'd then the dest is reused as a source
	 * 2/ if we did not prexor then we are redoing the parity
	 * set ASYNC_TX_XOR_DROP_DST and ASYNC_TX_XOR_ZERO_DST
	 * for the synchronous xor case
	 */
	last_stripe = !head_sh->batch_head ||
		list_first_entry(&sh->batch_list,
				 struct stripe_head, batch_list) == head_sh;
	if (last_stripe) {
		flags = ASYNC_TX_ACK |
			(prexor ? ASYNC_TX_XOR_DROP_DST : ASYNC_TX_XOR_ZERO_DST);

		atomic_inc(&head_sh->count);
		init_async_submit(&submit, flags, tx, ops_complete_reconstruct, head_sh,
				  to_addr_conv(sh, percpu, j));
	} else {
		flags = prexor ? ASYNC_TX_XOR_DROP_DST : ASYNC_TX_XOR_ZERO_DST;
		init_async_submit(&submit, flags, tx, NULL, NULL,
				  to_addr_conv(sh, percpu, j));
	}

	if (unlikely(count == 1))
		tx = async_memcpy(xor_dest, xor_srcs[0], 0, 0, STRIPE_SIZE, &submit);
	else
		tx = async_xor(xor_dest, xor_srcs, 0, count, STRIPE_SIZE, &submit);
	if (!last_stripe) {
		j++;
		sh = list_first_entry(&sh->batch_list, struct stripe_head,
				      batch_list);
		goto again;
	}
}

static void
ops_run_reconstruct6(struct stripe_head *sh, struct raid5_percpu *percpu,
		     struct dma_async_tx_descriptor *tx)
{
	struct async_submit_ctl submit;
	struct page **blocks;
	int count, i, j = 0;
	struct stripe_head *head_sh = sh;
	int last_stripe;
	int synflags;
	unsigned long txflags;

	pr_debug("%s: stripe %llu\n", __func__, (unsigned long long)sh->sector);

	for (i = 0; i < sh->disks; i++) {
		if (sh->pd_idx == i || sh->qd_idx == i)
			continue;
		if (!test_bit(R5_Discard, &sh->dev[i].flags))
			break;
	}
	if (i >= sh->disks) {
		atomic_inc(&sh->count);
		set_bit(R5_Discard, &sh->dev[sh->pd_idx].flags);
		set_bit(R5_Discard, &sh->dev[sh->qd_idx].flags);
		ops_complete_reconstruct(sh);
		return;
	}

again:
	blocks = to_addr_page(percpu, j);

	if (sh->reconstruct_state == reconstruct_state_prexor_drain_run) {
		synflags = SYNDROME_SRC_WRITTEN;
		txflags = ASYNC_TX_ACK | ASYNC_TX_PQ_XOR_DST;
	} else {
		synflags = SYNDROME_SRC_ALL;
		txflags = ASYNC_TX_ACK;
	}

	count = set_syndrome_sources(blocks, sh, synflags);
	last_stripe = !head_sh->batch_head ||
		list_first_entry(&sh->batch_list,
				 struct stripe_head, batch_list) == head_sh;

	if (last_stripe) {
		atomic_inc(&head_sh->count);
		init_async_submit(&submit, txflags, tx, ops_complete_reconstruct,
				  head_sh, to_addr_conv(sh, percpu, j));
	} else
		init_async_submit(&submit, 0, tx, NULL, NULL,
				  to_addr_conv(sh, percpu, j));
	tx = async_gen_syndrome(blocks, 0, count+2, STRIPE_SIZE,  &submit);
	if (!last_stripe) {
		j++;
		sh = list_first_entry(&sh->batch_list, struct stripe_head,
				      batch_list);
		goto again;
	}
}

static void ops_complete_check(void *stripe_head_ref)
{
	struct stripe_head *sh = stripe_head_ref;

	pr_debug("%s: stripe %llu\n", __func__,
		(unsigned long long)sh->sector);

	sh->check_state = check_state_check_result;
	set_bit(STRIPE_HANDLE, &sh->state);
	raid5_release_stripe(sh);
}

static void ops_run_check_p(struct stripe_head *sh, struct raid5_percpu *percpu)
{
	int disks = sh->disks;
	int pd_idx = sh->pd_idx;
	int qd_idx = sh->qd_idx;
	struct page *xor_dest;
	struct page **xor_srcs = to_addr_page(percpu, 0);
	struct dma_async_tx_descriptor *tx;
	struct async_submit_ctl submit;
	int count;
	int i;

	pr_debug("%s: stripe %llu\n", __func__,
		(unsigned long long)sh->sector);

	BUG_ON(sh->batch_head);
	count = 0;
	xor_dest = sh->dev[pd_idx].page;
	xor_srcs[count++] = xor_dest;
	for (i = disks; i--; ) {
		if (i == pd_idx || i == qd_idx)
			continue;
		xor_srcs[count++] = sh->dev[i].page;
	}

	init_async_submit(&submit, 0, NULL, NULL, NULL,
			  to_addr_conv(sh, percpu, 0));
	tx = async_xor_val(xor_dest, xor_srcs, 0, count, STRIPE_SIZE,
			   &sh->ops.zero_sum_result, &submit);

	atomic_inc(&sh->count);
	init_async_submit(&submit, ASYNC_TX_ACK, tx, ops_complete_check, sh, NULL);
	tx = async_trigger_callback(&submit);
}

static void ops_run_check_pq(struct stripe_head *sh, struct raid5_percpu *percpu, int checkp)
{
	struct page **srcs = to_addr_page(percpu, 0);
	struct async_submit_ctl submit;
	int count;

	pr_debug("%s: stripe %llu checkp: %d\n", __func__,
		(unsigned long long)sh->sector, checkp);

	BUG_ON(sh->batch_head);
	count = set_syndrome_sources(srcs, sh, SYNDROME_SRC_ALL);
	if (!checkp)
		srcs[count] = NULL;

	atomic_inc(&sh->count);
	init_async_submit(&submit, ASYNC_TX_ACK, NULL, ops_complete_check,
			  sh, to_addr_conv(sh, percpu, 0));
	async_syndrome_val(srcs, 0, count+2, STRIPE_SIZE,
			   &sh->ops.zero_sum_result, percpu->spare_page, &submit);
}

static void raid_run_ops(struct stripe_head *sh, unsigned long ops_request)
{
	int overlap_clear = 0, i, disks = sh->disks;
	struct dma_async_tx_descriptor *tx = NULL;
	struct r5conf *conf = sh->raid_conf;
	int level = conf->level;
	struct raid5_percpu *percpu;
	unsigned long cpu;

	cpu = get_cpu();
	percpu = per_cpu_ptr(conf->percpu, cpu);
	if (test_bit(STRIPE_OP_BIOFILL, &ops_request)) {
		ops_run_biofill(sh);
		overlap_clear++;
	}

	if (test_bit(STRIPE_OP_COMPUTE_BLK, &ops_request)) {
		if (level < 6)
			tx = ops_run_compute5(sh, percpu);
		else {
			if (sh->ops.target2 < 0 || sh->ops.target < 0)
				tx = ops_run_compute6_1(sh, percpu);
			else
				tx = ops_run_compute6_2(sh, percpu);
		}
		/* terminate the chain if reconstruct is not set to be run */
		if (tx && !test_bit(STRIPE_OP_RECONSTRUCT, &ops_request))
			async_tx_ack(tx);
	}

	if (test_bit(STRIPE_OP_PREXOR, &ops_request)) {
		if (level < 6)
			tx = ops_run_prexor5(sh, percpu, tx);
		else
			tx = ops_run_prexor6(sh, percpu, tx);
	}

	if (test_bit(STRIPE_OP_BIODRAIN, &ops_request)) {
		tx = ops_run_biodrain(sh, tx);
		overlap_clear++;
	}

	if (test_bit(STRIPE_OP_RECONSTRUCT, &ops_request)) {
		if (level < 6)
			ops_run_reconstruct5(sh, percpu, tx);
		else
			ops_run_reconstruct6(sh, percpu, tx);
	}

	if (test_bit(STRIPE_OP_CHECK, &ops_request)) {
		if (sh->check_state == check_state_run)
			ops_run_check_p(sh, percpu);
		else if (sh->check_state == check_state_run_q)
			ops_run_check_pq(sh, percpu, 0);
		else if (sh->check_state == check_state_run_pq)
			ops_run_check_pq(sh, percpu, 1);
		else
			BUG();
	}

	if (overlap_clear && !sh->batch_head)
		for (i = disks; i--; ) {
			struct r5dev *dev = &sh->dev[i];
			if (test_and_clear_bit(R5_Overlap, &dev->flags))
				wake_up(&sh->raid_conf->wait_for_overlap);
		}
	put_cpu();
}

static struct stripe_head *alloc_stripe(struct kmem_cache *sc, gfp_t gfp)
{
	struct stripe_head *sh;

	sh = kmem_cache_zalloc(sc, gfp);
	if (sh) {
		spin_lock_init(&sh->stripe_lock);
		spin_lock_init(&sh->batch_lock);
		INIT_LIST_HEAD(&sh->batch_list);
		INIT_LIST_HEAD(&sh->lru);
		atomic_set(&sh->count, 1);
	}
	return sh;
}
static int grow_one_stripe(struct r5conf *conf, gfp_t gfp)
{
	struct stripe_head *sh;

	sh = alloc_stripe(conf->slab_cache, gfp);
	if (!sh)
		return 0;

	sh->raid_conf = conf;

	if (grow_buffers(sh, gfp)) {
		shrink_buffers(sh);
		kmem_cache_free(conf->slab_cache, sh);
		return 0;
	}
	sh->hash_lock_index =
		conf->max_nr_stripes % NR_STRIPE_HASH_LOCKS;
	/* we just created an active stripe so... */
	atomic_inc(&conf->active_stripes);

	raid5_release_stripe(sh);
	conf->max_nr_stripes++;
	return 1;
}

static int grow_stripes(struct r5conf *conf, int num)
{
	struct kmem_cache *sc;
	int devs = max(conf->raid_disks, conf->previous_raid_disks);

	if (conf->mddev->gendisk)
		sprintf(conf->cache_name[0],
			"raid%d-%s", conf->level, mdname(conf->mddev));
	else
		sprintf(conf->cache_name[0],
			"raid%d-%p", conf->level, conf->mddev);
	sprintf(conf->cache_name[1], "%s-alt", conf->cache_name[0]);

	conf->active_name = 0;
	sc = kmem_cache_create(conf->cache_name[conf->active_name],
			       sizeof(struct stripe_head)+(devs-1)*sizeof(struct r5dev),
			       0, 0, NULL);
	if (!sc)
		return 1;
	conf->slab_cache = sc;
	conf->pool_size = devs;
	while (num--)
		if (!grow_one_stripe(conf, GFP_KERNEL))
			return 1;

	return 0;
}

/**
 * scribble_len - return the required size of the scribble region
 * @num - total number of disks in the array
 *
 * The size must be enough to contain:
 * 1/ a struct page pointer for each device in the array +2
 * 2/ room to convert each entry in (1) to its corresponding dma
 *    (dma_map_page()) or page (page_address()) address.
 *
 * Note: the +2 is for the destination buffers of the ddf/raid6 case where we
 * calculate over all devices (not just the data blocks), using zeros in place
 * of the P and Q blocks.
 */
static struct flex_array *scribble_alloc(int num, int cnt, gfp_t flags)
{
	struct flex_array *ret;
	size_t len;

	len = sizeof(struct page *) * (num+2) + sizeof(addr_conv_t) * (num+2);
	ret = flex_array_alloc(len, cnt, flags);
	if (!ret)
		return NULL;
	/* always prealloc all elements, so no locking is required */
	if (flex_array_prealloc(ret, 0, cnt, flags)) {
		flex_array_free(ret);
		return NULL;
	}
	return ret;
}

static int resize_chunks(struct r5conf *conf, int new_disks, int new_sectors)
{
	unsigned long cpu;
	int err = 0;

	/*
	 * Never shrink. And mddev_suspend() could deadlock if this is called
	 * from raid5d. In that case, scribble_disks and scribble_sectors
	 * should equal to new_disks and new_sectors
	 */
	if (conf->scribble_disks >= new_disks &&
	    conf->scribble_sectors >= new_sectors)
		return 0;
	mddev_suspend(conf->mddev);
	get_online_cpus();
	for_each_present_cpu(cpu) {
		struct raid5_percpu *percpu;
		struct flex_array *scribble;

		percpu = per_cpu_ptr(conf->percpu, cpu);
		scribble = scribble_alloc(new_disks,
					  new_sectors / STRIPE_SECTORS,
					  GFP_NOIO);

		if (scribble) {
			flex_array_free(percpu->scribble);
			percpu->scribble = scribble;
		} else {
			err = -ENOMEM;
			break;
		}
	}
	put_online_cpus();
	mddev_resume(conf->mddev);
	if (!err) {
		conf->scribble_disks = new_disks;
		conf->scribble_sectors = new_sectors;
	}
	return err;
}

static int resize_stripes(struct r5conf *conf, int newsize)
{
	/* Make all the stripes able to hold 'newsize' devices.
	 * New slots in each stripe get 'page' set to a new page.
	 *
	 * This happens in stages:
	 * 1/ create a new kmem_cache and allocate the required number of
	 *    stripe_heads.
	 * 2/ gather all the old stripe_heads and transfer the pages across
	 *    to the new stripe_heads.  This will have the side effect of
	 *    freezing the array as once all stripe_heads have been collected,
	 *    no IO will be possible.  Old stripe heads are freed once their
	 *    pages have been transferred over, and the old kmem_cache is
	 *    freed when all stripes are done.
	 * 3/ reallocate conf->disks to be suitable bigger.  If this fails,
	 *    we simple return a failre status - no need to clean anything up.
	 * 4/ allocate new pages for the new slots in the new stripe_heads.
	 *    If this fails, we don't bother trying the shrink the
	 *    stripe_heads down again, we just leave them as they are.
	 *    As each stripe_head is processed the new one is released into
	 *    active service.
	 *
	 * Once step2 is started, we cannot afford to wait for a write,
	 * so we use GFP_NOIO allocations.
	 */
	struct stripe_head *osh, *nsh;
	LIST_HEAD(newstripes);
	struct disk_info *ndisks;
	int err;
	struct kmem_cache *sc;
	int i;
	int hash, cnt;

	if (newsize <= conf->pool_size)
		return 0; /* never bother to shrink */

	err = md_allow_write(conf->mddev);
	if (err)
		return err;

	/* Step 1 */
	sc = kmem_cache_create(conf->cache_name[1-conf->active_name],
			       sizeof(struct stripe_head)+(newsize-1)*sizeof(struct r5dev),
			       0, 0, NULL);
	if (!sc)
		return -ENOMEM;

	/* Need to ensure auto-resizing doesn't interfere */
	mutex_lock(&conf->cache_size_mutex);

	for (i = conf->max_nr_stripes; i; i--) {
		nsh = alloc_stripe(sc, GFP_KERNEL);
		if (!nsh)
			break;

		nsh->raid_conf = conf;
		list_add(&nsh->lru, &newstripes);
	}
	if (i) {
		/* didn't get enough, give up */
		while (!list_empty(&newstripes)) {
			nsh = list_entry(newstripes.next, struct stripe_head, lru);
			list_del(&nsh->lru);
			kmem_cache_free(sc, nsh);
		}
		kmem_cache_destroy(sc);
		mutex_unlock(&conf->cache_size_mutex);
		return -ENOMEM;
	}
	/* Step 2 - Must use GFP_NOIO now.
	 * OK, we have enough stripes, start collecting inactive
	 * stripes and copying them over
	 */
	hash = 0;
	cnt = 0;
	list_for_each_entry(nsh, &newstripes, lru) {
		lock_device_hash_lock(conf, hash);
		wait_event_cmd(conf->wait_for_stripe,
				    !list_empty(conf->inactive_list + hash),
				    unlock_device_hash_lock(conf, hash),
				    lock_device_hash_lock(conf, hash));
		osh = get_free_stripe(conf, hash);
		unlock_device_hash_lock(conf, hash);

		for(i=0; i<conf->pool_size; i++) {
			nsh->dev[i].page = osh->dev[i].page;
			nsh->dev[i].orig_page = osh->dev[i].page;
		}
		nsh->hash_lock_index = hash;
		kmem_cache_free(conf->slab_cache, osh);
		cnt++;
		if (cnt >= conf->max_nr_stripes / NR_STRIPE_HASH_LOCKS +
		    !!((conf->max_nr_stripes % NR_STRIPE_HASH_LOCKS) > hash)) {
			hash++;
			cnt = 0;
		}
	}
	kmem_cache_destroy(conf->slab_cache);

	/* Step 3.
	 * At this point, we are holding all the stripes so the array
	 * is completely stalled, so now is a good time to resize
	 * conf->disks and the scribble region
	 */
	ndisks = kzalloc(newsize * sizeof(struct disk_info), GFP_NOIO);
	if (ndisks) {
		for (i=0; i<conf->raid_disks; i++)
			ndisks[i] = conf->disks[i];
		kfree(conf->disks);
		conf->disks = ndisks;
	} else
		err = -ENOMEM;

	mutex_unlock(&conf->cache_size_mutex);
	/* Step 4, return new stripes to service */
	while(!list_empty(&newstripes)) {
		nsh = list_entry(newstripes.next, struct stripe_head, lru);
		list_del_init(&nsh->lru);

		for (i=conf->raid_disks; i < newsize; i++)
			if (nsh->dev[i].page == NULL) {
				struct page *p = alloc_page(GFP_NOIO);
				nsh->dev[i].page = p;
				nsh->dev[i].orig_page = p;
				if (!p)
					err = -ENOMEM;
			}
		raid5_release_stripe(nsh);
	}
	/* critical section pass, GFP_NOIO no longer needed */

	conf->slab_cache = sc;
	conf->active_name = 1-conf->active_name;
	if (!err)
		conf->pool_size = newsize;
	return err;
}

static int drop_one_stripe(struct r5conf *conf)
{
	struct stripe_head *sh;
	int hash = (conf->max_nr_stripes - 1) & STRIPE_HASH_LOCKS_MASK;

	spin_lock_irq(conf->hash_locks + hash);
	sh = get_free_stripe(conf, hash);
	spin_unlock_irq(conf->hash_locks + hash);
	if (!sh)
		return 0;
	BUG_ON(atomic_read(&sh->count));
	shrink_buffers(sh);
	kmem_cache_free(conf->slab_cache, sh);
	atomic_dec(&conf->active_stripes);
	conf->max_nr_stripes--;
	return 1;
}

static void shrink_stripes(struct r5conf *conf)
{
	while (conf->max_nr_stripes &&
	       drop_one_stripe(conf))
		;

	kmem_cache_destroy(conf->slab_cache);
	conf->slab_cache = NULL;
}

static void raid5_end_read_request(struct bio * bi)
{
	struct stripe_head *sh = bi->bi_private;
	struct r5conf *conf = sh->raid_conf;
	int disks = sh->disks, i;
	char b[BDEVNAME_SIZE];
	struct md_rdev *rdev = NULL;
	sector_t s;

	for (i=0 ; i<disks; i++)
		if (bi == &sh->dev[i].req)
			break;

	pr_debug("end_read_request %llu/%d, count: %d, error %d.\n",
		(unsigned long long)sh->sector, i, atomic_read(&sh->count),
		bi->bi_error);
	if (i == disks) {
		BUG();
		return;
	}
	if (test_bit(R5_ReadRepl, &sh->dev[i].flags))
		/* If replacement finished while this request was outstanding,
		 * 'replacement' might be NULL already.
		 * In that case it moved down to 'rdev'.
		 * rdev is not removed until all requests are finished.
		 */
		rdev = conf->disks[i].replacement;
	if (!rdev)
		rdev = conf->disks[i].rdev;

	if (use_new_offset(conf, sh))
		s = sh->sector + rdev->new_data_offset;
	else
		s = sh->sector + rdev->data_offset;
	if (!bi->bi_error) {
		set_bit(R5_UPTODATE, &sh->dev[i].flags);
		if (test_bit(R5_ReadError, &sh->dev[i].flags)) {
			/* Note that this cannot happen on a
			 * replacement device.  We just fail those on
			 * any error
			 */
			printk_ratelimited(
				KERN_INFO
				"md/raid:%s: read error corrected"
				" (%lu sectors at %llu on %s)\n",
				mdname(conf->mddev), STRIPE_SECTORS,
				(unsigned long long)s,
				bdevname(rdev->bdev, b));
			atomic_add(STRIPE_SECTORS, &rdev->corrected_errors);
			clear_bit(R5_ReadError, &sh->dev[i].flags);
			clear_bit(R5_ReWrite, &sh->dev[i].flags);
		} else if (test_bit(R5_ReadNoMerge, &sh->dev[i].flags))
			clear_bit(R5_ReadNoMerge, &sh->dev[i].flags);

		if (atomic_read(&rdev->read_errors))
			atomic_set(&rdev->read_errors, 0);
	} else {
		const char *bdn = bdevname(rdev->bdev, b);
		int retry = 0;
		int set_bad = 0;

		clear_bit(R5_UPTODATE, &sh->dev[i].flags);
		atomic_inc(&rdev->read_errors);
		if (test_bit(R5_ReadRepl, &sh->dev[i].flags))
			printk_ratelimited(
				KERN_WARNING
				"md/raid:%s: read error on replacement device "
				"(sector %llu on %s).\n",
				mdname(conf->mddev),
				(unsigned long long)s,
				bdn);
		else if (conf->mddev->degraded >= conf->max_degraded) {
			set_bad = 1;
			printk_ratelimited(
				KERN_WARNING
				"md/raid:%s: read error not correctable "
				"(sector %llu on %s).\n",
				mdname(conf->mddev),
				(unsigned long long)s,
				bdn);
		} else if (test_bit(R5_ReWrite, &sh->dev[i].flags)) {
			/* Oh, no!!! */
			set_bad = 1;
			printk_ratelimited(
				KERN_WARNING
				"md/raid:%s: read error NOT corrected!! "
				"(sector %llu on %s).\n",
				mdname(conf->mddev),
				(unsigned long long)s,
				bdn);
		} else if (atomic_read(&rdev->read_errors)
			 > conf->max_nr_stripes)
			printk(KERN_WARNING
			       "md/raid:%s: Too many read errors, failing device %s.\n",
			       mdname(conf->mddev), bdn);
		else
			retry = 1;
		if (set_bad && test_bit(In_sync, &rdev->flags)
		    && !test_bit(R5_ReadNoMerge, &sh->dev[i].flags))
			retry = 1;
		if (retry)
			if (test_bit(R5_ReadNoMerge, &sh->dev[i].flags)) {
				set_bit(R5_ReadError, &sh->dev[i].flags);
				clear_bit(R5_ReadNoMerge, &sh->dev[i].flags);
			} else
				set_bit(R5_ReadNoMerge, &sh->dev[i].flags);
		else {
			clear_bit(R5_ReadError, &sh->dev[i].flags);
			clear_bit(R5_ReWrite, &sh->dev[i].flags);
			if (!(set_bad
			      && test_bit(In_sync, &rdev->flags)
			      && rdev_set_badblocks(
				      rdev, sh->sector, STRIPE_SECTORS, 0)))
				md_error(conf->mddev, rdev);
		}
	}
	rdev_dec_pending(rdev, conf->mddev);
	clear_bit(R5_LOCKED, &sh->dev[i].flags);
	set_bit(STRIPE_HANDLE, &sh->state);
	raid5_release_stripe(sh);
}

static void raid5_end_write_request(struct bio *bi)
{
	struct stripe_head *sh = bi->bi_private;
	struct r5conf *conf = sh->raid_conf;
	int disks = sh->disks, i;
	struct md_rdev *uninitialized_var(rdev);
	sector_t first_bad;
	int bad_sectors;
	int replacement = 0;

	for (i = 0 ; i < disks; i++) {
		if (bi == &sh->dev[i].req) {
			rdev = conf->disks[i].rdev;
			break;
		}
		if (bi == &sh->dev[i].rreq) {
			rdev = conf->disks[i].replacement;
			if (rdev)
				replacement = 1;
			else
				/* rdev was removed and 'replacement'
				 * replaced it.  rdev is not removed
				 * until all requests are finished.
				 */
				rdev = conf->disks[i].rdev;
			break;
		}
	}
	pr_debug("end_write_request %llu/%d, count %d, error: %d.\n",
		(unsigned long long)sh->sector, i, atomic_read(&sh->count),
		bi->bi_error);
	if (i == disks) {
		BUG();
		return;
	}

	if (replacement) {
		if (bi->bi_error)
			md_error(conf->mddev, rdev);
		else if (is_badblock(rdev, sh->sector,
				     STRIPE_SECTORS,
				     &first_bad, &bad_sectors))
			set_bit(R5_MadeGoodRepl, &sh->dev[i].flags);
	} else {
		if (bi->bi_error) {
			set_bit(STRIPE_DEGRADED, &sh->state);
			set_bit(WriteErrorSeen, &rdev->flags);
			set_bit(R5_WriteError, &sh->dev[i].flags);
			if (!test_and_set_bit(WantReplacement, &rdev->flags))
				set_bit(MD_RECOVERY_NEEDED,
					&rdev->mddev->recovery);
		} else if (is_badblock(rdev, sh->sector,
				       STRIPE_SECTORS,
				       &first_bad, &bad_sectors)) {
			set_bit(R5_MadeGood, &sh->dev[i].flags);
			if (test_bit(R5_ReadError, &sh->dev[i].flags))
				/* That was a successful write so make
				 * sure it looks like we already did
				 * a re-write.
				 */
				set_bit(R5_ReWrite, &sh->dev[i].flags);
		}
	}
	rdev_dec_pending(rdev, conf->mddev);

	if (sh->batch_head && bi->bi_error && !replacement)
		set_bit(STRIPE_BATCH_ERR, &sh->batch_head->state);

	if (!test_and_clear_bit(R5_DOUBLE_LOCKED, &sh->dev[i].flags))
		clear_bit(R5_LOCKED, &sh->dev[i].flags);
	set_bit(STRIPE_HANDLE, &sh->state);
	raid5_release_stripe(sh);

	if (sh->batch_head && sh != sh->batch_head)
		raid5_release_stripe(sh->batch_head);
}

static void raid5_build_block(struct stripe_head *sh, int i, int previous)
{
	struct r5dev *dev = &sh->dev[i];

	bio_init(&dev->req);
	dev->req.bi_io_vec = &dev->vec;
	dev->req.bi_max_vecs = 1;
	dev->req.bi_private = sh;

	bio_init(&dev->rreq);
	dev->rreq.bi_io_vec = &dev->rvec;
	dev->rreq.bi_max_vecs = 1;
	dev->rreq.bi_private = sh;

	dev->flags = 0;
	dev->sector = raid5_compute_blocknr(sh, i, previous);
}

static void raid5_error(struct mddev *mddev, struct md_rdev *rdev)
{
	char b[BDEVNAME_SIZE];
	struct r5conf *conf = mddev->private;
	unsigned long flags;
	pr_debug("raid456: error called\n");

	spin_lock_irqsave(&conf->device_lock, flags);
	clear_bit(In_sync, &rdev->flags);
	mddev->degraded = calc_degraded(conf);
	spin_unlock_irqrestore(&conf->device_lock, flags);
	set_bit(MD_RECOVERY_INTR, &mddev->recovery);

	set_bit(Blocked, &rdev->flags);
	set_bit(Faulty, &rdev->flags);
	set_mask_bits(&mddev->flags, 0,
		      BIT(MD_CHANGE_DEVS) | BIT(MD_CHANGE_PENDING));
	printk(KERN_ALERT
	       "md/raid:%s: Disk failure on %s, disabling device.\n"
	       "md/raid:%s: Operation continuing on %d devices.\n",
	       mdname(mddev),
	       bdevname(rdev->bdev, b),
	       mdname(mddev),
	       conf->raid_disks - mddev->degraded);
}

/*
 * Input: a 'big' sector number,
 * Output: index of the data and parity disk, and the sector # in them.
 */
sector_t raid5_compute_sector(struct r5conf *conf, sector_t r_sector,
			      int previous, int *dd_idx,
			      struct stripe_head *sh)
{
	sector_t stripe, stripe2;
	sector_t chunk_number;
	unsigned int chunk_offset;
	int pd_idx, qd_idx;
	int ddf_layout = 0;
	sector_t new_sector;
	int algorithm = previous ? conf->prev_algo
				 : conf->algorithm;
	int sectors_per_chunk = previous ? conf->prev_chunk_sectors
					 : conf->chunk_sectors;
	int raid_disks = previous ? conf->previous_raid_disks
				  : conf->raid_disks;
	int data_disks = raid_disks - conf->max_degraded;

	/* First compute the information on this sector */

	/*
	 * Compute the chunk number and the sector offset inside the chunk
	 */
	chunk_offset = sector_div(r_sector, sectors_per_chunk);
	chunk_number = r_sector;

	/*
	 * Compute the stripe number
	 */
	stripe = chunk_number;
	*dd_idx = sector_div(stripe, data_disks);
	stripe2 = stripe;
	/*
	 * Select the parity disk based on the user selected algorithm.
	 */
	pd_idx = qd_idx = -1;
	switch(conf->level) {
	case 4:
		pd_idx = data_disks;
		break;
	case 5:
		switch (algorithm) {
		case ALGORITHM_LEFT_ASYMMETRIC:
			pd_idx = data_disks - sector_div(stripe2, raid_disks);
			if (*dd_idx >= pd_idx)
				(*dd_idx)++;
			break;
		case ALGORITHM_RIGHT_ASYMMETRIC:
			pd_idx = sector_div(stripe2, raid_disks);
			if (*dd_idx >= pd_idx)
				(*dd_idx)++;
			break;
		case ALGORITHM_LEFT_SYMMETRIC:
			pd_idx = data_disks - sector_div(stripe2, raid_disks);
			*dd_idx = (pd_idx + 1 + *dd_idx) % raid_disks;
			break;
		case ALGORITHM_RIGHT_SYMMETRIC:
			pd_idx = sector_div(stripe2, raid_disks);
			*dd_idx = (pd_idx + 1 + *dd_idx) % raid_disks;
			break;
		case ALGORITHM_PARITY_0:
			pd_idx = 0;
			(*dd_idx)++;
			break;
		case ALGORITHM_PARITY_N:
			pd_idx = data_disks;
			break;
		default:
			BUG();
		}
		break;
	case 6:

		switch (algorithm) {
		case ALGORITHM_LEFT_ASYMMETRIC:
			pd_idx = raid_disks - 1 - sector_div(stripe2, raid_disks);
			qd_idx = pd_idx + 1;
			if (pd_idx == raid_disks-1) {
				(*dd_idx)++;	/* Q D D D P */
				qd_idx = 0;
			} else if (*dd_idx >= pd_idx)
				(*dd_idx) += 2; /* D D P Q D */
			break;
		case ALGORITHM_RIGHT_ASYMMETRIC:
			pd_idx = sector_div(stripe2, raid_disks);
			qd_idx = pd_idx + 1;
			if (pd_idx == raid_disks-1) {
				(*dd_idx)++;	/* Q D D D P */
				qd_idx = 0;
			} else if (*dd_idx >= pd_idx)
				(*dd_idx) += 2; /* D D P Q D */
			break;
		case ALGORITHM_LEFT_SYMMETRIC:
			pd_idx = raid_disks - 1 - sector_div(stripe2, raid_disks);
			qd_idx = (pd_idx + 1) % raid_disks;
			*dd_idx = (pd_idx + 2 + *dd_idx) % raid_disks;
			break;
		case ALGORITHM_RIGHT_SYMMETRIC:
			pd_idx = sector_div(stripe2, raid_disks);
			qd_idx = (pd_idx + 1) % raid_disks;
			*dd_idx = (pd_idx + 2 + *dd_idx) % raid_disks;
			break;

		case ALGORITHM_PARITY_0:
			pd_idx = 0;
			qd_idx = 1;
			(*dd_idx) += 2;
			break;
		case ALGORITHM_PARITY_N:
			pd_idx = data_disks;
			qd_idx = data_disks + 1;
			break;

		case ALGORITHM_ROTATING_ZERO_RESTART:
			/* Exactly the same as RIGHT_ASYMMETRIC, but or
			 * of blocks for computing Q is different.
			 */
			pd_idx = sector_div(stripe2, raid_disks);
			qd_idx = pd_idx + 1;
			if (pd_idx == raid_disks-1) {
				(*dd_idx)++;	/* Q D D D P */
				qd_idx = 0;
			} else if (*dd_idx >= pd_idx)
				(*dd_idx) += 2; /* D D P Q D */
			ddf_layout = 1;
			break;

		case ALGORITHM_ROTATING_N_RESTART:
			/* Same a left_asymmetric, by first stripe is
			 * D D D P Q  rather than
			 * Q D D D P
			 */
			stripe2 += 1;
			pd_idx = raid_disks - 1 - sector_div(stripe2, raid_disks);
			qd_idx = pd_idx + 1;
			if (pd_idx == raid_disks-1) {
				(*dd_idx)++;	/* Q D D D P */
				qd_idx = 0;
			} else if (*dd_idx >= pd_idx)
				(*dd_idx) += 2; /* D D P Q D */
			ddf_layout = 1;
			break;

		case ALGORITHM_ROTATING_N_CONTINUE:
			/* Same as left_symmetric but Q is before P */
			pd_idx = raid_disks - 1 - sector_div(stripe2, raid_disks);
			qd_idx = (pd_idx + raid_disks - 1) % raid_disks;
			*dd_idx = (pd_idx + 1 + *dd_idx) % raid_disks;
			ddf_layout = 1;
			break;

		case ALGORITHM_LEFT_ASYMMETRIC_6:
			/* RAID5 left_asymmetric, with Q on last device */
			pd_idx = data_disks - sector_div(stripe2, raid_disks-1);
			if (*dd_idx >= pd_idx)
				(*dd_idx)++;
			qd_idx = raid_disks - 1;
			break;

		case ALGORITHM_RIGHT_ASYMMETRIC_6:
			pd_idx = sector_div(stripe2, raid_disks-1);
			if (*dd_idx >= pd_idx)
				(*dd_idx)++;
			qd_idx = raid_disks - 1;
			break;

		case ALGORITHM_LEFT_SYMMETRIC_6:
			pd_idx = data_disks - sector_div(stripe2, raid_disks-1);
			*dd_idx = (pd_idx + 1 + *dd_idx) % (raid_disks-1);
			qd_idx = raid_disks - 1;
			break;

		case ALGORITHM_RIGHT_SYMMETRIC_6:
			pd_idx = sector_div(stripe2, raid_disks-1);
			*dd_idx = (pd_idx + 1 + *dd_idx) % (raid_disks-1);
			qd_idx = raid_disks - 1;
			break;

		case ALGORITHM_PARITY_0_6:
			pd_idx = 0;
			(*dd_idx)++;
			qd_idx = raid_disks - 1;
			break;

		default:
			BUG();
		}
		break;
	}

	if (sh) {
		sh->pd_idx = pd_idx;
		sh->qd_idx = qd_idx;
		sh->ddf_layout = ddf_layout;
	}
	/*
	 * Finally, compute the new sector number
	 */
	new_sector = (sector_t)stripe * sectors_per_chunk + chunk_offset;
	return new_sector;
}

sector_t raid5_compute_blocknr(struct stripe_head *sh, int i, int previous)
{
	struct r5conf *conf = sh->raid_conf;
	int raid_disks = sh->disks;
	int data_disks = raid_disks - conf->max_degraded;
	sector_t new_sector = sh->sector, check;
	int sectors_per_chunk = previous ? conf->prev_chunk_sectors
					 : conf->chunk_sectors;
	int algorithm = previous ? conf->prev_algo
				 : conf->algorithm;
	sector_t stripe;
	int chunk_offset;
	sector_t chunk_number;
	int dummy1, dd_idx = i;
	sector_t r_sector;
	struct stripe_head sh2;

	chunk_offset = sector_div(new_sector, sectors_per_chunk);
	stripe = new_sector;

	if (i == sh->pd_idx)
		return 0;
	switch(conf->level) {
	case 4: break;
	case 5:
		switch (algorithm) {
		case ALGORITHM_LEFT_ASYMMETRIC:
		case ALGORITHM_RIGHT_ASYMMETRIC:
			if (i > sh->pd_idx)
				i--;
			break;
		case ALGORITHM_LEFT_SYMMETRIC:
		case ALGORITHM_RIGHT_SYMMETRIC:
			if (i < sh->pd_idx)
				i += raid_disks;
			i -= (sh->pd_idx + 1);
			break;
		case ALGORITHM_PARITY_0:
			i -= 1;
			break;
		case ALGORITHM_PARITY_N:
			break;
		default:
			BUG();
		}
		break;
	case 6:
		if (i == sh->qd_idx)
			return 0; /* It is the Q disk */
		switch (algorithm) {
		case ALGORITHM_LEFT_ASYMMETRIC:
		case ALGORITHM_RIGHT_ASYMMETRIC:
		case ALGORITHM_ROTATING_ZERO_RESTART:
		case ALGORITHM_ROTATING_N_RESTART:
			if (sh->pd_idx == raid_disks-1)
				i--;	/* Q D D D P */
			else if (i > sh->pd_idx)
				i -= 2; /* D D P Q D */
			break;
		case ALGORITHM_LEFT_SYMMETRIC:
		case ALGORITHM_RIGHT_SYMMETRIC:
			if (sh->pd_idx == raid_disks-1)
				i--; /* Q D D D P */
			else {
				/* D D P Q D */
				if (i < sh->pd_idx)
					i += raid_disks;
				i -= (sh->pd_idx + 2);
			}
			break;
		case ALGORITHM_PARITY_0:
			i -= 2;
			break;
		case ALGORITHM_PARITY_N:
			break;
		case ALGORITHM_ROTATING_N_CONTINUE:
			/* Like left_symmetric, but P is before Q */
			if (sh->pd_idx == 0)
				i--;	/* P D D D Q */
			else {
				/* D D Q P D */
				if (i < sh->pd_idx)
					i += raid_disks;
				i -= (sh->pd_idx + 1);
			}
			break;
		case ALGORITHM_LEFT_ASYMMETRIC_6:
		case ALGORITHM_RIGHT_ASYMMETRIC_6:
			if (i > sh->pd_idx)
				i--;
			break;
		case ALGORITHM_LEFT_SYMMETRIC_6:
		case ALGORITHM_RIGHT_SYMMETRIC_6:
			if (i < sh->pd_idx)
				i += data_disks + 1;
			i -= (sh->pd_idx + 1);
			break;
		case ALGORITHM_PARITY_0_6:
			i -= 1;
			break;
		default:
			BUG();
		}
		break;
	}

	chunk_number = stripe * data_disks + i;
	r_sector = chunk_number * sectors_per_chunk + chunk_offset;

	check = raid5_compute_sector(conf, r_sector,
				     previous, &dummy1, &sh2);
	if (check != sh->sector || dummy1 != dd_idx || sh2.pd_idx != sh->pd_idx
		|| sh2.qd_idx != sh->qd_idx) {
		printk(KERN_ERR "md/raid:%s: compute_blocknr: map not correct\n",
		       mdname(conf->mddev));
		return 0;
	}
	return r_sector;
}

static void
schedule_reconstruction(struct stripe_head *sh, struct stripe_head_state *s,
			 int rcw, int expand)
{
	int i, pd_idx = sh->pd_idx, qd_idx = sh->qd_idx, disks = sh->disks;
	struct r5conf *conf = sh->raid_conf;
	int level = conf->level;

	if (rcw) {

		for (i = disks; i--; ) {
			struct r5dev *dev = &sh->dev[i];

			if (dev->towrite) {
				set_bit(R5_LOCKED, &dev->flags);
				set_bit(R5_Wantdrain, &dev->flags);
				if (!expand)
					clear_bit(R5_UPTODATE, &dev->flags);
				s->locked++;
			}
		}
		/* if we are not expanding this is a proper write request, and
		 * there will be bios with new data to be drained into the
		 * stripe cache
		 */
		if (!expand) {
			if (!s->locked)
				/* False alarm, nothing to do */
				return;
			sh->reconstruct_state = reconstruct_state_drain_run;
			set_bit(STRIPE_OP_BIODRAIN, &s->ops_request);
		} else
			sh->reconstruct_state = reconstruct_state_run;

		set_bit(STRIPE_OP_RECONSTRUCT, &s->ops_request);

		if (s->locked + conf->max_degraded == disks)
			if (!test_and_set_bit(STRIPE_FULL_WRITE, &sh->state))
				atomic_inc(&conf->pending_full_writes);
	} else {
		BUG_ON(!(test_bit(R5_UPTODATE, &sh->dev[pd_idx].flags) ||
			test_bit(R5_Wantcompute, &sh->dev[pd_idx].flags)));
		BUG_ON(level == 6 &&
			(!(test_bit(R5_UPTODATE, &sh->dev[qd_idx].flags) ||
			   test_bit(R5_Wantcompute, &sh->dev[qd_idx].flags))));

		for (i = disks; i--; ) {
			struct r5dev *dev = &sh->dev[i];
			if (i == pd_idx || i == qd_idx)
				continue;

			if (dev->towrite &&
			    (test_bit(R5_UPTODATE, &dev->flags) ||
			     test_bit(R5_Wantcompute, &dev->flags))) {
				set_bit(R5_Wantdrain, &dev->flags);
				set_bit(R5_LOCKED, &dev->flags);
				clear_bit(R5_UPTODATE, &dev->flags);
				s->locked++;
			}
		}
		if (!s->locked)
			/* False alarm - nothing to do */
			return;
		sh->reconstruct_state = reconstruct_state_prexor_drain_run;
		set_bit(STRIPE_OP_PREXOR, &s->ops_request);
		set_bit(STRIPE_OP_BIODRAIN, &s->ops_request);
		set_bit(STRIPE_OP_RECONSTRUCT, &s->ops_request);
	}

	/* keep the parity disk(s) locked while asynchronous operations
	 * are in flight
	 */
	set_bit(R5_LOCKED, &sh->dev[pd_idx].flags);
	clear_bit(R5_UPTODATE, &sh->dev[pd_idx].flags);
	s->locked++;

	if (level == 6) {
		int qd_idx = sh->qd_idx;
		struct r5dev *dev = &sh->dev[qd_idx];

		set_bit(R5_LOCKED, &dev->flags);
		clear_bit(R5_UPTODATE, &dev->flags);
		s->locked++;
	}

	pr_debug("%s: stripe %llu locked: %d ops_request: %lx\n",
		__func__, (unsigned long long)sh->sector,
		s->locked, s->ops_request);
}

/*
 * Each stripe/dev can have one or more bion attached.
 * toread/towrite point to the first in a chain.
 * The bi_next chain must be in order.
 */
static int add_stripe_bio(struct stripe_head *sh, struct bio *bi, int dd_idx,
			  int forwrite, int previous)
{
	struct bio **bip;
	struct r5conf *conf = sh->raid_conf;
	int firstwrite=0;

	pr_debug("adding bi b#%llu to stripe s#%llu\n",
		(unsigned long long)bi->bi_iter.bi_sector,
		(unsigned long long)sh->sector);

	/*
	 * If several bio share a stripe. The bio bi_phys_segments acts as a
	 * reference count to avoid race. The reference count should already be
	 * increased before this function is called (for example, in
	 * raid5_make_request()), so other bio sharing this stripe will not free the
	 * stripe. If a stripe is owned by one stripe, the stripe lock will
	 * protect it.
	 */
	spin_lock_irq(&sh->stripe_lock);
	/* Don't allow new IO added to stripes in batch list */
	if (sh->batch_head)
		goto overlap;
	if (forwrite) {
		bip = &sh->dev[dd_idx].towrite;
		if (*bip == NULL)
			firstwrite = 1;
	} else
		bip = &sh->dev[dd_idx].toread;
	while (*bip && (*bip)->bi_iter.bi_sector < bi->bi_iter.bi_sector) {
		if (bio_end_sector(*bip) > bi->bi_iter.bi_sector)
			goto overlap;
		bip = & (*bip)->bi_next;
	}
	if (*bip && (*bip)->bi_iter.bi_sector < bio_end_sector(bi))
		goto overlap;

	if (!forwrite || previous)
		clear_bit(STRIPE_BATCH_READY, &sh->state);

	BUG_ON(*bip && bi->bi_next && (*bip) != bi->bi_next);
	if (*bip)
		bi->bi_next = *bip;
	*bip = bi;
	raid5_inc_bi_active_stripes(bi);

	if (forwrite) {
		/* check if page is covered */
		sector_t sector = sh->dev[dd_idx].sector;
		for (bi=sh->dev[dd_idx].towrite;
		     sector < sh->dev[dd_idx].sector + STRIPE_SECTORS &&
			     bi && bi->bi_iter.bi_sector <= sector;
		     bi = r5_next_bio(bi, sh->dev[dd_idx].sector)) {
			if (bio_end_sector(bi) >= sector)
				sector = bio_end_sector(bi);
		}
		if (sector >= sh->dev[dd_idx].sector + STRIPE_SECTORS)
			if (!test_and_set_bit(R5_OVERWRITE, &sh->dev[dd_idx].flags))
				sh->overwrite_disks++;
	}

	pr_debug("added bi b#%llu to stripe s#%llu, disk %d.\n",
		(unsigned long long)(*bip)->bi_iter.bi_sector,
		(unsigned long long)sh->sector, dd_idx);

	if (conf->mddev->bitmap && firstwrite) {
		/* Cannot hold spinlock over bitmap_startwrite,
		 * but must ensure this isn't added to a batch until
		 * we have added to the bitmap and set bm_seq.
		 * So set STRIPE_BITMAP_PENDING to prevent
		 * batching.
		 * If multiple add_stripe_bio() calls race here they
		 * much all set STRIPE_BITMAP_PENDING.  So only the first one
		 * to complete "bitmap_startwrite" gets to set
		 * STRIPE_BIT_DELAY.  This is important as once a stripe
		 * is added to a batch, STRIPE_BIT_DELAY cannot be changed
		 * any more.
		 */
		set_bit(STRIPE_BITMAP_PENDING, &sh->state);
		spin_unlock_irq(&sh->stripe_lock);
		bitmap_startwrite(conf->mddev->bitmap, sh->sector,
				  STRIPE_SECTORS, 0);
		spin_lock_irq(&sh->stripe_lock);
		clear_bit(STRIPE_BITMAP_PENDING, &sh->state);
		if (!sh->batch_head) {
			sh->bm_seq = conf->seq_flush+1;
			set_bit(STRIPE_BIT_DELAY, &sh->state);
		}
	}
	spin_unlock_irq(&sh->stripe_lock);

	if (stripe_can_batch(sh))
		stripe_add_to_batch_list(conf, sh);
	return 1;

 overlap:
	set_bit(R5_Overlap, &sh->dev[dd_idx].flags);
	spin_unlock_irq(&sh->stripe_lock);
	return 0;
}

static void end_reshape(struct r5conf *conf);

static void stripe_set_idx(sector_t stripe, struct r5conf *conf, int previous,
			    struct stripe_head *sh)
{
	int sectors_per_chunk =
		previous ? conf->prev_chunk_sectors : conf->chunk_sectors;
	int dd_idx;
	int chunk_offset = sector_div(stripe, sectors_per_chunk);
	int disks = previous ? conf->previous_raid_disks : conf->raid_disks;

	raid5_compute_sector(conf,
			     stripe * (disks - conf->max_degraded)
			     *sectors_per_chunk + chunk_offset,
			     previous,
			     &dd_idx, sh);
}

static void
handle_failed_stripe(struct r5conf *conf, struct stripe_head *sh,
				struct stripe_head_state *s, int disks,
				struct bio_list *return_bi)
{
	int i;
	BUG_ON(sh->batch_head);
	for (i = disks; i--; ) {
		struct bio *bi;
		int bitmap_end = 0;

		if (test_bit(R5_ReadError, &sh->dev[i].flags)) {
			struct md_rdev *rdev;
			rcu_read_lock();
			rdev = rcu_dereference(conf->disks[i].rdev);
			if (rdev && test_bit(In_sync, &rdev->flags))
				atomic_inc(&rdev->nr_pending);
			else
				rdev = NULL;
			rcu_read_unlock();
			if (rdev) {
				if (!rdev_set_badblocks(
					    rdev,
					    sh->sector,
					    STRIPE_SECTORS, 0))
					md_error(conf->mddev, rdev);
				rdev_dec_pending(rdev, conf->mddev);
			}
		}
		spin_lock_irq(&sh->stripe_lock);
		/* fail all writes first */
		bi = sh->dev[i].towrite;
		sh->dev[i].towrite = NULL;
		sh->overwrite_disks = 0;
		spin_unlock_irq(&sh->stripe_lock);
		if (bi)
			bitmap_end = 1;

		r5l_stripe_write_finished(sh);

		if (test_and_clear_bit(R5_Overlap, &sh->dev[i].flags))
			wake_up(&conf->wait_for_overlap);

		while (bi && bi->bi_iter.bi_sector <
			sh->dev[i].sector + STRIPE_SECTORS) {
			struct bio *nextbi = r5_next_bio(bi, sh->dev[i].sector);

			bi->bi_error = -EIO;
			if (!raid5_dec_bi_active_stripes(bi)) {
				md_write_end(conf->mddev);
				bio_list_add(return_bi, bi);
			}
			bi = nextbi;
		}
		if (bitmap_end)
			bitmap_endwrite(conf->mddev->bitmap, sh->sector,
				STRIPE_SECTORS, 0, 0);
		bitmap_end = 0;
		/* and fail all 'written' */
		bi = sh->dev[i].written;
		sh->dev[i].written = NULL;
		if (test_and_clear_bit(R5_SkipCopy, &sh->dev[i].flags)) {
			WARN_ON(test_bit(R5_UPTODATE, &sh->dev[i].flags));
			sh->dev[i].page = sh->dev[i].orig_page;
		}

		if (bi) bitmap_end = 1;
		while (bi && bi->bi_iter.bi_sector <
		       sh->dev[i].sector + STRIPE_SECTORS) {
			struct bio *bi2 = r5_next_bio(bi, sh->dev[i].sector);

			bi->bi_error = -EIO;
			if (!raid5_dec_bi_active_stripes(bi)) {
				md_write_end(conf->mddev);
				bio_list_add(return_bi, bi);
			}
			bi = bi2;
		}

		/* fail any reads if this device is non-operational and
		 * the data has not reached the cache yet.
		 */
		if (!test_bit(R5_Wantfill, &sh->dev[i].flags) &&
		    s->failed > conf->max_degraded &&
		    (!test_bit(R5_Insync, &sh->dev[i].flags) ||
		      test_bit(R5_ReadError, &sh->dev[i].flags))) {
			spin_lock_irq(&sh->stripe_lock);
			bi = sh->dev[i].toread;
			sh->dev[i].toread = NULL;
			spin_unlock_irq(&sh->stripe_lock);
			if (test_and_clear_bit(R5_Overlap, &sh->dev[i].flags))
				wake_up(&conf->wait_for_overlap);
			if (bi)
				s->to_read--;
			while (bi && bi->bi_iter.bi_sector <
			       sh->dev[i].sector + STRIPE_SECTORS) {
				struct bio *nextbi =
					r5_next_bio(bi, sh->dev[i].sector);

				bi->bi_error = -EIO;
				if (!raid5_dec_bi_active_stripes(bi))
					bio_list_add(return_bi, bi);
				bi = nextbi;
			}
		}
		if (bitmap_end)
			bitmap_endwrite(conf->mddev->bitmap, sh->sector,
					STRIPE_SECTORS, 0, 0);
		/* If we were in the middle of a write the parity block might
		 * still be locked - so just clear all R5_LOCKED flags
		 */
		clear_bit(R5_LOCKED, &sh->dev[i].flags);
	}
	s->to_write = 0;
	s->written = 0;

	if (test_and_clear_bit(STRIPE_FULL_WRITE, &sh->state))
		if (atomic_dec_and_test(&conf->pending_full_writes))
			md_wakeup_thread(conf->mddev->thread);
}

static void
handle_failed_sync(struct r5conf *conf, struct stripe_head *sh,
		   struct stripe_head_state *s)
{
	int abort = 0;
	int i;

	BUG_ON(sh->batch_head);
	clear_bit(STRIPE_SYNCING, &sh->state);
	if (test_and_clear_bit(R5_Overlap, &sh->dev[sh->pd_idx].flags))
		wake_up(&conf->wait_for_overlap);
	s->syncing = 0;
	s->replacing = 0;
	/* There is nothing more to do for sync/check/repair.
	 * Don't even need to abort as that is handled elsewhere
	 * if needed, and not always wanted e.g. if there is a known
	 * bad block here.
	 * For recover/replace we need to record a bad block on all
	 * non-sync devices, or abort the recovery
	 */
	if (test_bit(MD_RECOVERY_RECOVER, &conf->mddev->recovery)) {
		/* During recovery devices cannot be removed, so
		 * locking and refcounting of rdevs is not needed
		 */
		for (i = 0; i < conf->raid_disks; i++) {
			struct md_rdev *rdev = conf->disks[i].rdev;
			if (rdev
			    && !test_bit(Faulty, &rdev->flags)
			    && !test_bit(In_sync, &rdev->flags)
			    && !rdev_set_badblocks(rdev, sh->sector,
						   STRIPE_SECTORS, 0))
				abort = 1;
			rdev = conf->disks[i].replacement;
			if (rdev
			    && !test_bit(Faulty, &rdev->flags)
			    && !test_bit(In_sync, &rdev->flags)
			    && !rdev_set_badblocks(rdev, sh->sector,
						   STRIPE_SECTORS, 0))
				abort = 1;
		}
		if (abort)
			conf->recovery_disabled =
				conf->mddev->recovery_disabled;
	}
	md_done_sync(conf->mddev, STRIPE_SECTORS, !abort);
}

static int want_replace(struct stripe_head *sh, int disk_idx)
{
	struct md_rdev *rdev;
	int rv = 0;
	/* Doing recovery so rcu locking not required */
	rdev = sh->raid_conf->disks[disk_idx].replacement;
	if (rdev
	    && !test_bit(Faulty, &rdev->flags)
	    && !test_bit(In_sync, &rdev->flags)
	    && (rdev->recovery_offset <= sh->sector
		|| rdev->mddev->recovery_cp <= sh->sector))
		rv = 1;

	return rv;
}

/* fetch_block - checks the given member device to see if its data needs
 * to be read or computed to satisfy a request.
 *
 * Returns 1 when no more member devices need to be checked, otherwise returns
 * 0 to tell the loop in handle_stripe_fill to continue
 */

static int need_this_block(struct stripe_head *sh, struct stripe_head_state *s,
			   int disk_idx, int disks)
{
	struct r5dev *dev = &sh->dev[disk_idx];
	struct r5dev *fdev[2] = { &sh->dev[s->failed_num[0]],
				  &sh->dev[s->failed_num[1]] };
	int i;


	if (test_bit(R5_LOCKED, &dev->flags) ||
	    test_bit(R5_UPTODATE, &dev->flags))
		/* No point reading this as we already have it or have
		 * decided to get it.
		 */
		return 0;

	if (dev->toread ||
	    (dev->towrite && !test_bit(R5_OVERWRITE, &dev->flags)))
		/* We need this block to directly satisfy a request */
		return 1;

	if (s->syncing || s->expanding ||
	    (s->replacing && want_replace(sh, disk_idx)))
		/* When syncing, or expanding we read everything.
		 * When replacing, we need the replaced block.
		 */
		return 1;

	if ((s->failed >= 1 && fdev[0]->toread) ||
	    (s->failed >= 2 && fdev[1]->toread))
		/* If we want to read from a failed device, then
		 * we need to actually read every other device.
		 */
		return 1;

	/* Sometimes neither read-modify-write nor reconstruct-write
	 * cycles can work.  In those cases we read every block we
	 * can.  Then the parity-update is certain to have enough to
	 * work with.
	 * This can only be a problem when we need to write something,
	 * and some device has failed.  If either of those tests
	 * fail we need look no further.
	 */
	if (!s->failed || !s->to_write)
		return 0;

	if (test_bit(R5_Insync, &dev->flags) &&
	    !test_bit(STRIPE_PREREAD_ACTIVE, &sh->state))
		/* Pre-reads at not permitted until after short delay
		 * to gather multiple requests.  However if this
		 * device is no Insync, the block could only be be computed
		 * and there is no need to delay that.
		 */
		return 0;

	for (i = 0; i < s->failed && i < 2; i++) {
		if (fdev[i]->towrite &&
		    !test_bit(R5_UPTODATE, &fdev[i]->flags) &&
		    !test_bit(R5_OVERWRITE, &fdev[i]->flags))
			/* If we have a partial write to a failed
			 * device, then we will need to reconstruct
			 * the content of that device, so all other
			 * devices must be read.
			 */
			return 1;
	}

	/* If we are forced to do a reconstruct-write, either because
	 * the current RAID6 implementation only supports that, or
	 * or because parity cannot be trusted and we are currently
	 * recovering it, there is extra need to be careful.
	 * If one of the devices that we would need to read, because
	 * it is not being overwritten (and maybe not written at all)
	 * is missing/faulty, then we need to read everything we can.
	 */
	if (sh->raid_conf->level != 6 &&
	    sh->sector < sh->raid_conf->mddev->recovery_cp)
		/* reconstruct-write isn't being forced */
		return 0;
	for (i = 0; i < s->failed && i < 2; i++) {
		if (s->failed_num[i] != sh->pd_idx &&
		    s->failed_num[i] != sh->qd_idx &&
		    !test_bit(R5_UPTODATE, &fdev[i]->flags) &&
		    !test_bit(R5_OVERWRITE, &fdev[i]->flags))
			return 1;
	}

	return 0;
}

static int fetch_block(struct stripe_head *sh, struct stripe_head_state *s,
		       int disk_idx, int disks)
{
	struct r5dev *dev = &sh->dev[disk_idx];

	/* is the data in this block needed, and can we get it? */
	if (need_this_block(sh, s, disk_idx, disks)) {
		/* we would like to get this block, possibly by computing it,
		 * otherwise read it if the backing disk is insync
		 */
		BUG_ON(test_bit(R5_Wantcompute, &dev->flags));
		BUG_ON(test_bit(R5_Wantread, &dev->flags));
		BUG_ON(sh->batch_head);
		if ((s->uptodate == disks - 1) &&
		    (s->failed && (disk_idx == s->failed_num[0] ||
				   disk_idx == s->failed_num[1]))) {
			/* have disk failed, and we're requested to fetch it;
			 * do compute it
			 */
			pr_debug("Computing stripe %llu block %d\n",
			       (unsigned long long)sh->sector, disk_idx);
			set_bit(STRIPE_COMPUTE_RUN, &sh->state);
			set_bit(STRIPE_OP_COMPUTE_BLK, &s->ops_request);
			set_bit(R5_Wantcompute, &dev->flags);
			sh->ops.target = disk_idx;
			sh->ops.target2 = -1; /* no 2nd target */
			s->req_compute = 1;
			/* Careful: from this point on 'uptodate' is in the eye
			 * of raid_run_ops which services 'compute' operations
			 * before writes. R5_Wantcompute flags a block that will
			 * be R5_UPTODATE by the time it is needed for a
			 * subsequent operation.
			 */
			s->uptodate++;
			return 1;
		} else if (s->uptodate == disks-2 && s->failed >= 2) {
			/* Computing 2-failure is *very* expensive; only
			 * do it if failed >= 2
			 */
			int other;
			for (other = disks; other--; ) {
				if (other == disk_idx)
					continue;
				if (!test_bit(R5_UPTODATE,
				      &sh->dev[other].flags))
					break;
			}
			BUG_ON(other < 0);
			pr_debug("Computing stripe %llu blocks %d,%d\n",
			       (unsigned long long)sh->sector,
			       disk_idx, other);
			set_bit(STRIPE_COMPUTE_RUN, &sh->state);
			set_bit(STRIPE_OP_COMPUTE_BLK, &s->ops_request);
			set_bit(R5_Wantcompute, &sh->dev[disk_idx].flags);
			set_bit(R5_Wantcompute, &sh->dev[other].flags);
			sh->ops.target = disk_idx;
			sh->ops.target2 = other;
			s->uptodate += 2;
			s->req_compute = 1;
			return 1;
		} else if (test_bit(R5_Insync, &dev->flags)) {
			set_bit(R5_LOCKED, &dev->flags);
			set_bit(R5_Wantread, &dev->flags);
			s->locked++;
			pr_debug("Reading block %d (sync=%d)\n",
				disk_idx, s->syncing);
		}
	}

	return 0;
}

/**
 * handle_stripe_fill - read or compute data to satisfy pending requests.
 */
static void handle_stripe_fill(struct stripe_head *sh,
			       struct stripe_head_state *s,
			       int disks)
{
	int i;

	/* look for blocks to read/compute, skip this if a compute
	 * is already in flight, or if the stripe contents are in the
	 * midst of changing due to a write
	 */
	if (!test_bit(STRIPE_COMPUTE_RUN, &sh->state) && !sh->check_state &&
	    !sh->reconstruct_state)
		for (i = disks; i--; )
			if (fetch_block(sh, s, i, disks))
				break;
	set_bit(STRIPE_HANDLE, &sh->state);
}

static void break_stripe_batch_list(struct stripe_head *head_sh,
				    unsigned long handle_flags);
/* handle_stripe_clean_event
 * any written block on an uptodate or failed drive can be returned.
 * Note that if we 'wrote' to a failed drive, it will be UPTODATE, but
 * never LOCKED, so we don't need to test 'failed' directly.
 */
static void handle_stripe_clean_event(struct r5conf *conf,
	struct stripe_head *sh, int disks, struct bio_list *return_bi)
{
	int i;
	struct r5dev *dev;
	int discard_pending = 0;
	struct stripe_head *head_sh = sh;
	bool do_endio = false;

	for (i = disks; i--; )
		if (sh->dev[i].written) {
			dev = &sh->dev[i];
			if (!test_bit(R5_LOCKED, &dev->flags) &&
			    (test_bit(R5_UPTODATE, &dev->flags) ||
			     test_bit(R5_Discard, &dev->flags) ||
			     test_bit(R5_SkipCopy, &dev->flags))) {
				/* We can return any write requests */
				struct bio *wbi, *wbi2;
				pr_debug("Return write for disc %d\n", i);
				if (test_and_clear_bit(R5_Discard, &dev->flags))
					clear_bit(R5_UPTODATE, &dev->flags);
				if (test_and_clear_bit(R5_SkipCopy, &dev->flags)) {
					WARN_ON(test_bit(R5_UPTODATE, &dev->flags));
				}
				do_endio = true;

returnbi:
				dev->page = dev->orig_page;
				wbi = dev->written;
				dev->written = NULL;
				while (wbi && wbi->bi_iter.bi_sector <
					dev->sector + STRIPE_SECTORS) {
					wbi2 = r5_next_bio(wbi, dev->sector);
					if (!raid5_dec_bi_active_stripes(wbi)) {
						md_write_end(conf->mddev);
						bio_list_add(return_bi, wbi);
					}
					wbi = wbi2;
				}
				bitmap_endwrite(conf->mddev->bitmap, sh->sector,
						STRIPE_SECTORS,
					 !test_bit(STRIPE_DEGRADED, &sh->state),
						0);
				if (head_sh->batch_head) {
					sh = list_first_entry(&sh->batch_list,
							      struct stripe_head,
							      batch_list);
					if (sh != head_sh) {
						dev = &sh->dev[i];
						goto returnbi;
					}
				}
				sh = head_sh;
				dev = &sh->dev[i];
			} else if (test_bit(R5_Discard, &dev->flags))
				discard_pending = 1;
		}

	r5l_stripe_write_finished(sh);

	if (!discard_pending &&
	    test_bit(R5_Discard, &sh->dev[sh->pd_idx].flags)) {
		int hash;
		clear_bit(R5_Discard, &sh->dev[sh->pd_idx].flags);
		clear_bit(R5_UPTODATE, &sh->dev[sh->pd_idx].flags);
		if (sh->qd_idx >= 0) {
			clear_bit(R5_Discard, &sh->dev[sh->qd_idx].flags);
			clear_bit(R5_UPTODATE, &sh->dev[sh->qd_idx].flags);
		}
		/* now that discard is done we can proceed with any sync */
		clear_bit(STRIPE_DISCARD, &sh->state);
		/*
		 * SCSI discard will change some bio fields and the stripe has
		 * no updated data, so remove it from hash list and the stripe
		 * will be reinitialized
		 */
unhash:
		hash = sh->hash_lock_index;
		spin_lock_irq(conf->hash_locks + hash);
		remove_hash(sh);
		spin_unlock_irq(conf->hash_locks + hash);
		if (head_sh->batch_head) {
			sh = list_first_entry(&sh->batch_list,
					      struct stripe_head, batch_list);
			if (sh != head_sh)
					goto unhash;
		}
		sh = head_sh;

		if (test_bit(STRIPE_SYNC_REQUESTED, &sh->state))
			set_bit(STRIPE_HANDLE, &sh->state);

	}

	if (test_and_clear_bit(STRIPE_FULL_WRITE, &sh->state))
		if (atomic_dec_and_test(&conf->pending_full_writes))
			md_wakeup_thread(conf->mddev->thread);

	if (head_sh->batch_head && do_endio)
		break_stripe_batch_list(head_sh, STRIPE_EXPAND_SYNC_FLAGS);
}

static void handle_stripe_dirtying(struct r5conf *conf,
				   struct stripe_head *sh,
				   struct stripe_head_state *s,
				   int disks)
{
	int rmw = 0, rcw = 0, i;
	sector_t recovery_cp = conf->mddev->recovery_cp;

	/* Check whether resync is now happening or should start.
	 * If yes, then the array is dirty (after unclean shutdown or
	 * initial creation), so parity in some stripes might be inconsistent.
	 * In this case, we need to always do reconstruct-write, to ensure
	 * that in case of drive failure or read-error correction, we
	 * generate correct data from the parity.
	 */
	if (conf->rmw_level == PARITY_DISABLE_RMW ||
	    (recovery_cp < MaxSector && sh->sector >= recovery_cp &&
	     s->failed == 0)) {
		/* Calculate the real rcw later - for now make it
		 * look like rcw is cheaper
		 */
		rcw = 1; rmw = 2;
		pr_debug("force RCW rmw_level=%u, recovery_cp=%llu sh->sector=%llu\n",
			 conf->rmw_level, (unsigned long long)recovery_cp,
			 (unsigned long long)sh->sector);
	} else for (i = disks; i--; ) {
		/* would I have to read this buffer for read_modify_write */
		struct r5dev *dev = &sh->dev[i];
		if ((dev->towrite || i == sh->pd_idx || i == sh->qd_idx) &&
		    !test_bit(R5_LOCKED, &dev->flags) &&
		    !(test_bit(R5_UPTODATE, &dev->flags) ||
		      test_bit(R5_Wantcompute, &dev->flags))) {
			if (test_bit(R5_Insync, &dev->flags))
				rmw++;
			else
				rmw += 2*disks;  /* cannot read it */
		}
		/* Would I have to read this buffer for reconstruct_write */
		if (!test_bit(R5_OVERWRITE, &dev->flags) &&
		    i != sh->pd_idx && i != sh->qd_idx &&
		    !test_bit(R5_LOCKED, &dev->flags) &&
		    !(test_bit(R5_UPTODATE, &dev->flags) ||
		    test_bit(R5_Wantcompute, &dev->flags))) {
			if (test_bit(R5_Insync, &dev->flags))
				rcw++;
			else
				rcw += 2*disks;
		}
	}
	pr_debug("for sector %llu, rmw=%d rcw=%d\n",
		(unsigned long long)sh->sector, rmw, rcw);
	set_bit(STRIPE_HANDLE, &sh->state);
	if ((rmw < rcw || (rmw == rcw && conf->rmw_level == PARITY_ENABLE_RMW)) && rmw > 0) {
		/* prefer read-modify-write, but need to get some data */
		if (conf->mddev->queue)
			blk_add_trace_msg(conf->mddev->queue,
					  "raid5 rmw %llu %d",
					  (unsigned long long)sh->sector, rmw);
		for (i = disks; i--; ) {
			struct r5dev *dev = &sh->dev[i];
			if ((dev->towrite || i == sh->pd_idx || i == sh->qd_idx) &&
			    !test_bit(R5_LOCKED, &dev->flags) &&
			    !(test_bit(R5_UPTODATE, &dev->flags) ||
			    test_bit(R5_Wantcompute, &dev->flags)) &&
			    test_bit(R5_Insync, &dev->flags)) {
				if (test_bit(STRIPE_PREREAD_ACTIVE,
					     &sh->state)) {
					pr_debug("Read_old block %d for r-m-w\n",
						 i);
					set_bit(R5_LOCKED, &dev->flags);
					set_bit(R5_Wantread, &dev->flags);
					s->locked++;
				} else {
					set_bit(STRIPE_DELAYED, &sh->state);
					set_bit(STRIPE_HANDLE, &sh->state);
				}
			}
		}
	}
	if ((rcw < rmw || (rcw == rmw && conf->rmw_level != PARITY_ENABLE_RMW)) && rcw > 0) {
		/* want reconstruct write, but need to get some data */
		int qread =0;
		rcw = 0;
		for (i = disks; i--; ) {
			struct r5dev *dev = &sh->dev[i];
			if (!test_bit(R5_OVERWRITE, &dev->flags) &&
			    i != sh->pd_idx && i != sh->qd_idx &&
			    !test_bit(R5_LOCKED, &dev->flags) &&
			    !(test_bit(R5_UPTODATE, &dev->flags) ||
			      test_bit(R5_Wantcompute, &dev->flags))) {
				rcw++;
				if (test_bit(R5_Insync, &dev->flags) &&
				    test_bit(STRIPE_PREREAD_ACTIVE,
					     &sh->state)) {
					pr_debug("Read_old block "
						"%d for Reconstruct\n", i);
					set_bit(R5_LOCKED, &dev->flags);
					set_bit(R5_Wantread, &dev->flags);
					s->locked++;
					qread++;
				} else {
					set_bit(STRIPE_DELAYED, &sh->state);
					set_bit(STRIPE_HANDLE, &sh->state);
				}
			}
		}
		if (rcw && conf->mddev->queue)
			blk_add_trace_msg(conf->mddev->queue, "raid5 rcw %llu %d %d %d",
					  (unsigned long long)sh->sector,
					  rcw, qread, test_bit(STRIPE_DELAYED, &sh->state));
	}

	if (rcw > disks && rmw > disks &&
	    !test_bit(STRIPE_PREREAD_ACTIVE, &sh->state))
		set_bit(STRIPE_DELAYED, &sh->state);

	/* now if nothing is locked, and if we have enough data,
	 * we can start a write request
	 */
	/* since handle_stripe can be called at any time we need to handle the
	 * case where a compute block operation has been submitted and then a
	 * subsequent call wants to start a write request.  raid_run_ops only
	 * handles the case where compute block and reconstruct are requested
	 * simultaneously.  If this is not the case then new writes need to be
	 * held off until the compute completes.
	 */
	if ((s->req_compute || !test_bit(STRIPE_COMPUTE_RUN, &sh->state)) &&
	    (s->locked == 0 && (rcw == 0 || rmw == 0) &&
	    !test_bit(STRIPE_BIT_DELAY, &sh->state)))
		schedule_reconstruction(sh, s, rcw == 0, 0);
}

static void handle_parity_checks5(struct r5conf *conf, struct stripe_head *sh,
				struct stripe_head_state *s, int disks)
{
	struct r5dev *dev = NULL;

	BUG_ON(sh->batch_head);
	set_bit(STRIPE_HANDLE, &sh->state);

	switch (sh->check_state) {
	case check_state_idle:
		/* start a new check operation if there are no failures */
		if (s->failed == 0) {
			BUG_ON(s->uptodate != disks);
			sh->check_state = check_state_run;
			set_bit(STRIPE_OP_CHECK, &s->ops_request);
			clear_bit(R5_UPTODATE, &sh->dev[sh->pd_idx].flags);
			s->uptodate--;
			break;
		}
		dev = &sh->dev[s->failed_num[0]];
		/* fall through */
	case check_state_compute_result:
		sh->check_state = check_state_idle;
		if (!dev)
			dev = &sh->dev[sh->pd_idx];

		/* check that a write has not made the stripe insync */
		if (test_bit(STRIPE_INSYNC, &sh->state))
			break;

		/* either failed parity check, or recovery is happening */
		BUG_ON(!test_bit(R5_UPTODATE, &dev->flags));
		BUG_ON(s->uptodate != disks);

		set_bit(R5_LOCKED, &dev->flags);
		s->locked++;
		set_bit(R5_Wantwrite, &dev->flags);

		clear_bit(STRIPE_DEGRADED, &sh->state);
		set_bit(STRIPE_INSYNC, &sh->state);
		break;
	case check_state_run:
		break; /* we will be called again upon completion */
	case check_state_check_result:
		sh->check_state = check_state_idle;

		/* if a failure occurred during the check operation, leave
		 * STRIPE_INSYNC not set and let the stripe be handled again
		 */
		if (s->failed)
			break;

		/* handle a successful check operation, if parity is correct
		 * we are done.  Otherwise update the mismatch count and repair
		 * parity if !MD_RECOVERY_CHECK
		 */
		if ((sh->ops.zero_sum_result & SUM_CHECK_P_RESULT) == 0)
			/* parity is correct (on disc,
			 * not in buffer any more)
			 */
			set_bit(STRIPE_INSYNC, &sh->state);
		else {
			atomic64_add(STRIPE_SECTORS, &conf->mddev->resync_mismatches);
			if (test_bit(MD_RECOVERY_CHECK, &conf->mddev->recovery))
				/* don't try to repair!! */
				set_bit(STRIPE_INSYNC, &sh->state);
			else {
				sh->check_state = check_state_compute_run;
				set_bit(STRIPE_COMPUTE_RUN, &sh->state);
				set_bit(STRIPE_OP_COMPUTE_BLK, &s->ops_request);
				set_bit(R5_Wantcompute,
					&sh->dev[sh->pd_idx].flags);
				sh->ops.target = sh->pd_idx;
				sh->ops.target2 = -1;
				s->uptodate++;
			}
		}
		break;
	case check_state_compute_run:
		break;
	default:
		printk(KERN_ERR "%s: unknown check_state: %d sector: %llu\n",
		       __func__, sh->check_state,
		       (unsigned long long) sh->sector);
		BUG();
	}
}

static void handle_parity_checks6(struct r5conf *conf, struct stripe_head *sh,
				  struct stripe_head_state *s,
				  int disks)
{
	int pd_idx = sh->pd_idx;
	int qd_idx = sh->qd_idx;
	struct r5dev *dev;

	BUG_ON(sh->batch_head);
	set_bit(STRIPE_HANDLE, &sh->state);

	BUG_ON(s->failed > 2);

	/* Want to check and possibly repair P and Q.
	 * However there could be one 'failed' device, in which
	 * case we can only check one of them, possibly using the
	 * other to generate missing data
	 */

	switch (sh->check_state) {
	case check_state_idle:
		/* start a new check operation if there are < 2 failures */
		if (s->failed == s->q_failed) {
			/* The only possible failed device holds Q, so it
			 * makes sense to check P (If anything else were failed,
			 * we would have used P to recreate it).
			 */
			sh->check_state = check_state_run;
		}
		if (!s->q_failed && s->failed < 2) {
			/* Q is not failed, and we didn't use it to generate
			 * anything, so it makes sense to check it
			 */
			if (sh->check_state == check_state_run)
				sh->check_state = check_state_run_pq;
			else
				sh->check_state = check_state_run_q;
		}

		/* discard potentially stale zero_sum_result */
		sh->ops.zero_sum_result = 0;

		if (sh->check_state == check_state_run) {
			/* async_xor_zero_sum destroys the contents of P */
			clear_bit(R5_UPTODATE, &sh->dev[pd_idx].flags);
			s->uptodate--;
		}
		if (sh->check_state >= check_state_run &&
		    sh->check_state <= check_state_run_pq) {
			/* async_syndrome_zero_sum preserves P and Q, so
			 * no need to mark them !uptodate here
			 */
			set_bit(STRIPE_OP_CHECK, &s->ops_request);
			break;
		}

		/* we have 2-disk failure */
		BUG_ON(s->failed != 2);
		/* fall through */
	case check_state_compute_result:
		sh->check_state = check_state_idle;

		/* check that a write has not made the stripe insync */
		if (test_bit(STRIPE_INSYNC, &sh->state))
			break;

		/* now write out any block on a failed drive,
		 * or P or Q if they were recomputed
		 */
		BUG_ON(s->uptodate < disks - 1); /* We don't need Q to recover */
		if (s->failed == 2) {
			dev = &sh->dev[s->failed_num[1]];
			s->locked++;
			set_bit(R5_LOCKED, &dev->flags);
			set_bit(R5_Wantwrite, &dev->flags);
		}
		if (s->failed >= 1) {
			dev = &sh->dev[s->failed_num[0]];
			s->locked++;
			set_bit(R5_LOCKED, &dev->flags);
			set_bit(R5_Wantwrite, &dev->flags);
		}
		if (sh->ops.zero_sum_result & SUM_CHECK_P_RESULT) {
			dev = &sh->dev[pd_idx];
			s->locked++;
			set_bit(R5_LOCKED, &dev->flags);
			set_bit(R5_Wantwrite, &dev->flags);
		}
		if (sh->ops.zero_sum_result & SUM_CHECK_Q_RESULT) {
			dev = &sh->dev[qd_idx];
			s->locked++;
			set_bit(R5_LOCKED, &dev->flags);
			set_bit(R5_Wantwrite, &dev->flags);
		}
		clear_bit(STRIPE_DEGRADED, &sh->state);

		set_bit(STRIPE_INSYNC, &sh->state);
		break;
	case check_state_run:
	case check_state_run_q:
	case check_state_run_pq:
		break; /* we will be called again upon completion */
	case check_state_check_result:
		sh->check_state = check_state_idle;

		/* handle a successful check operation, if parity is correct
		 * we are done.  Otherwise update the mismatch count and repair
		 * parity if !MD_RECOVERY_CHECK
		 */
		if (sh->ops.zero_sum_result == 0) {
			/* both parities are correct */
			if (!s->failed)
				set_bit(STRIPE_INSYNC, &sh->state);
			else {
				/* in contrast to the raid5 case we can validate
				 * parity, but still have a failure to write
				 * back
				 */
				sh->check_state = check_state_compute_result;
				/* Returning at this point means that we may go
				 * off and bring p and/or q uptodate again so
				 * we make sure to check zero_sum_result again
				 * to verify if p or q need writeback
				 */
			}
		} else {
			atomic64_add(STRIPE_SECTORS, &conf->mddev->resync_mismatches);
			if (test_bit(MD_RECOVERY_CHECK, &conf->mddev->recovery))
				/* don't try to repair!! */
				set_bit(STRIPE_INSYNC, &sh->state);
			else {
				int *target = &sh->ops.target;

				sh->ops.target = -1;
				sh->ops.target2 = -1;
				sh->check_state = check_state_compute_run;
				set_bit(STRIPE_COMPUTE_RUN, &sh->state);
				set_bit(STRIPE_OP_COMPUTE_BLK, &s->ops_request);
				if (sh->ops.zero_sum_result & SUM_CHECK_P_RESULT) {
					set_bit(R5_Wantcompute,
						&sh->dev[pd_idx].flags);
					*target = pd_idx;
					target = &sh->ops.target2;
					s->uptodate++;
				}
				if (sh->ops.zero_sum_result & SUM_CHECK_Q_RESULT) {
					set_bit(R5_Wantcompute,
						&sh->dev[qd_idx].flags);
					*target = qd_idx;
					s->uptodate++;
				}
			}
		}
		break;
	case check_state_compute_run:
		break;
	default:
		printk(KERN_ERR "%s: unknown check_state: %d sector: %llu\n",
		       __func__, sh->check_state,
		       (unsigned long long) sh->sector);
		BUG();
	}
}

static void handle_stripe_expansion(struct r5conf *conf, struct stripe_head *sh)
{
	int i;

	/* We have read all the blocks in this stripe and now we need to
	 * copy some of them into a target stripe for expand.
	 */
	struct dma_async_tx_descriptor *tx = NULL;
	BUG_ON(sh->batch_head);
	clear_bit(STRIPE_EXPAND_SOURCE, &sh->state);
	for (i = 0; i < sh->disks; i++)
		if (i != sh->pd_idx && i != sh->qd_idx) {
			int dd_idx, j;
			struct stripe_head *sh2;
			struct async_submit_ctl submit;

			sector_t bn = raid5_compute_blocknr(sh, i, 1);
			sector_t s = raid5_compute_sector(conf, bn, 0,
							  &dd_idx, NULL);
			sh2 = raid5_get_active_stripe(conf, s, 0, 1, 1);
			if (sh2 == NULL)
				/* so far only the early blocks of this stripe
				 * have been requested.  When later blocks
				 * get requested, we will try again
				 */
				continue;
			if (!test_bit(STRIPE_EXPANDING, &sh2->state) ||
			   test_bit(R5_Expanded, &sh2->dev[dd_idx].flags)) {
				/* must have already done this block */
				raid5_release_stripe(sh2);
				continue;
			}

			/* place all the copies on one channel */
			init_async_submit(&submit, 0, tx, NULL, NULL, NULL);
			tx = async_memcpy(sh2->dev[dd_idx].page,
					  sh->dev[i].page, 0, 0, STRIPE_SIZE,
					  &submit);

			set_bit(R5_Expanded, &sh2->dev[dd_idx].flags);
			set_bit(R5_UPTODATE, &sh2->dev[dd_idx].flags);
			for (j = 0; j < conf->raid_disks; j++)
				if (j != sh2->pd_idx &&
				    j != sh2->qd_idx &&
				    !test_bit(R5_Expanded, &sh2->dev[j].flags))
					break;
			if (j == conf->raid_disks) {
				set_bit(STRIPE_EXPAND_READY, &sh2->state);
				set_bit(STRIPE_HANDLE, &sh2->state);
			}
			raid5_release_stripe(sh2);

		}
	/* done submitting copies, wait for them to complete */
	async_tx_quiesce(&tx);
}

/*
 * handle_stripe - do things to a stripe.
 *
 * We lock the stripe by setting STRIPE_ACTIVE and then examine the
 * state of various bits to see what needs to be done.
 * Possible results:
 *    return some read requests which now have data
 *    return some write requests which are safely on storage
 *    schedule a read on some buffers
 *    schedule a write of some buffers
 *    return confirmation of parity correctness
 *
 */

static void analyse_stripe(struct stripe_head *sh, struct stripe_head_state *s)
{
	struct r5conf *conf = sh->raid_conf;
	int disks = sh->disks;
	struct r5dev *dev;
	int i;
	int do_recovery = 0;

	memset(s, 0, sizeof(*s));

	s->expanding = test_bit(STRIPE_EXPAND_SOURCE, &sh->state) && !sh->batch_head;
	s->expanded = test_bit(STRIPE_EXPAND_READY, &sh->state) && !sh->batch_head;
	s->failed_num[0] = -1;
	s->failed_num[1] = -1;
	s->log_failed = r5l_log_disk_error(conf);

	/* Now to look around and see what can be done */
	rcu_read_lock();
	for (i=disks; i--; ) {
		struct md_rdev *rdev;
		sector_t first_bad;
		int bad_sectors;
		int is_bad = 0;

		dev = &sh->dev[i];

		pr_debug("check %d: state 0x%lx read %p write %p written %p\n",
			 i, dev->flags,
			 dev->toread, dev->towrite, dev->written);
		/* maybe we can reply to a read
		 *
		 * new wantfill requests are only permitted while
		 * ops_complete_biofill is guaranteed to be inactive
		 */
		if (test_bit(R5_UPTODATE, &dev->flags) && dev->toread &&
		    !test_bit(STRIPE_BIOFILL_RUN, &sh->state))
			set_bit(R5_Wantfill, &dev->flags);

		/* now count some things */
		if (test_bit(R5_LOCKED, &dev->flags))
			s->locked++;
		if (test_bit(R5_UPTODATE, &dev->flags))
			s->uptodate++;
		if (test_bit(R5_Wantcompute, &dev->flags)) {
			s->compute++;
			BUG_ON(s->compute > 2);
		}

		if (test_bit(R5_Wantfill, &dev->flags))
			s->to_fill++;
		else if (dev->toread)
			s->to_read++;
		if (dev->towrite) {
			s->to_write++;
			if (!test_bit(R5_OVERWRITE, &dev->flags))
				s->non_overwrite++;
		}
		if (dev->written)
			s->written++;
		/* Prefer to use the replacement for reads, but only
		 * if it is recovered enough and has no bad blocks.
		 */
		rdev = rcu_dereference(conf->disks[i].replacement);
		if (rdev && !test_bit(Faulty, &rdev->flags) &&
		    rdev->recovery_offset >= sh->sector + STRIPE_SECTORS &&
		    !is_badblock(rdev, sh->sector, STRIPE_SECTORS,
				 &first_bad, &bad_sectors))
			set_bit(R5_ReadRepl, &dev->flags);
		else {
			if (rdev && !test_bit(Faulty, &rdev->flags))
				set_bit(R5_NeedReplace, &dev->flags);
			else
				clear_bit(R5_NeedReplace, &dev->flags);
			rdev = rcu_dereference(conf->disks[i].rdev);
			clear_bit(R5_ReadRepl, &dev->flags);
		}
		if (rdev && test_bit(Faulty, &rdev->flags))
			rdev = NULL;
		if (rdev) {
			is_bad = is_badblock(rdev, sh->sector, STRIPE_SECTORS,
					     &first_bad, &bad_sectors);
			if (s->blocked_rdev == NULL
			    && (test_bit(Blocked, &rdev->flags)
				|| is_bad < 0)) {
				if (is_bad < 0)
					set_bit(BlockedBadBlocks,
						&rdev->flags);
				s->blocked_rdev = rdev;
				atomic_inc(&rdev->nr_pending);
			}
		}
		clear_bit(R5_Insync, &dev->flags);
		if (!rdev)
			/* Not in-sync */;
		else if (is_bad) {
			/* also not in-sync */
			if (!test_bit(WriteErrorSeen, &rdev->flags) &&
			    test_bit(R5_UPTODATE, &dev->flags)) {
				/* treat as in-sync, but with a read error
				 * which we can now try to correct
				 */
				set_bit(R5_Insync, &dev->flags);
				set_bit(R5_ReadError, &dev->flags);
			}
		} else if (test_bit(In_sync, &rdev->flags))
			set_bit(R5_Insync, &dev->flags);
		else if (sh->sector + STRIPE_SECTORS <= rdev->recovery_offset)
			/* in sync if before recovery_offset */
			set_bit(R5_Insync, &dev->flags);
		else if (test_bit(R5_UPTODATE, &dev->flags) &&
			 test_bit(R5_Expanded, &dev->flags))
			/* If we've reshaped into here, we assume it is Insync.
			 * We will shortly update recovery_offset to make
			 * it official.
			 */
			set_bit(R5_Insync, &dev->flags);

		if (test_bit(R5_WriteError, &dev->flags)) {
			/* This flag does not apply to '.replacement'
			 * only to .rdev, so make sure to check that*/
			struct md_rdev *rdev2 = rcu_dereference(
				conf->disks[i].rdev);
			if (rdev2 == rdev)
				clear_bit(R5_Insync, &dev->flags);
			if (rdev2 && !test_bit(Faulty, &rdev2->flags)) {
				s->handle_bad_blocks = 1;
				atomic_inc(&rdev2->nr_pending);
			} else
				clear_bit(R5_WriteError, &dev->flags);
		}
		if (test_bit(R5_MadeGood, &dev->flags)) {
			/* This flag does not apply to '.replacement'
			 * only to .rdev, so make sure to check that*/
			struct md_rdev *rdev2 = rcu_dereference(
				conf->disks[i].rdev);
			if (rdev2 && !test_bit(Faulty, &rdev2->flags)) {
				s->handle_bad_blocks = 1;
				atomic_inc(&rdev2->nr_pending);
			} else
				clear_bit(R5_MadeGood, &dev->flags);
		}
		if (test_bit(R5_MadeGoodRepl, &dev->flags)) {
			struct md_rdev *rdev2 = rcu_dereference(
				conf->disks[i].replacement);
			if (rdev2 && !test_bit(Faulty, &rdev2->flags)) {
				s->handle_bad_blocks = 1;
				atomic_inc(&rdev2->nr_pending);
			} else
				clear_bit(R5_MadeGoodRepl, &dev->flags);
		}
		if (!test_bit(R5_Insync, &dev->flags)) {
			/* The ReadError flag will just be confusing now */
			clear_bit(R5_ReadError, &dev->flags);
			clear_bit(R5_ReWrite, &dev->flags);
		}
		if (test_bit(R5_ReadError, &dev->flags))
			clear_bit(R5_Insync, &dev->flags);
		if (!test_bit(R5_Insync, &dev->flags)) {
			if (s->failed < 2)
				s->failed_num[s->failed] = i;
			s->failed++;
			if (rdev && !test_bit(Faulty, &rdev->flags))
				do_recovery = 1;
		}
	}
	if (test_bit(STRIPE_SYNCING, &sh->state)) {
		/* If there is a failed device being replaced,
		 *     we must be recovering.
		 * else if we are after recovery_cp, we must be syncing
		 * else if MD_RECOVERY_REQUESTED is set, we also are syncing.
		 * else we can only be replacing
		 * sync and recovery both need to read all devices, and so
		 * use the same flag.
		 */
		if (do_recovery ||
		    sh->sector >= conf->mddev->recovery_cp ||
		    test_bit(MD_RECOVERY_REQUESTED, &(conf->mddev->recovery)))
			s->syncing = 1;
		else
			s->replacing = 1;
	}
	rcu_read_unlock();
}

static int clear_batch_ready(struct stripe_head *sh)
{
	/* Return '1' if this is a member of batch, or
	 * '0' if it is a lone stripe or a head which can now be
	 * handled.
	 */
	struct stripe_head *tmp;
	if (!test_and_clear_bit(STRIPE_BATCH_READY, &sh->state))
		return (sh->batch_head && sh->batch_head != sh);
	spin_lock(&sh->stripe_lock);
	if (!sh->batch_head) {
		spin_unlock(&sh->stripe_lock);
		return 0;
	}

	/*
	 * this stripe could be added to a batch list before we check
	 * BATCH_READY, skips it
	 */
	if (sh->batch_head != sh) {
		spin_unlock(&sh->stripe_lock);
		return 1;
	}
	spin_lock(&sh->batch_lock);
	list_for_each_entry(tmp, &sh->batch_list, batch_list)
		clear_bit(STRIPE_BATCH_READY, &tmp->state);
	spin_unlock(&sh->batch_lock);
	spin_unlock(&sh->stripe_lock);

	/*
	 * BATCH_READY is cleared, no new stripes can be added.
	 * batch_list can be accessed without lock
	 */
	return 0;
}

static void break_stripe_batch_list(struct stripe_head *head_sh,
				    unsigned long handle_flags)
{
	struct stripe_head *sh, *next;
	int i;
	int do_wakeup = 0;

	list_for_each_entry_safe(sh, next, &head_sh->batch_list, batch_list) {

		list_del_init(&sh->batch_list);

		WARN_ONCE(sh->state & ((1 << STRIPE_ACTIVE) |
					  (1 << STRIPE_SYNCING) |
					  (1 << STRIPE_REPLACED) |
					  (1 << STRIPE_DELAYED) |
					  (1 << STRIPE_BIT_DELAY) |
					  (1 << STRIPE_FULL_WRITE) |
					  (1 << STRIPE_BIOFILL_RUN) |
					  (1 << STRIPE_COMPUTE_RUN)  |
					  (1 << STRIPE_OPS_REQ_PENDING) |
					  (1 << STRIPE_DISCARD) |
					  (1 << STRIPE_BATCH_READY) |
					  (1 << STRIPE_BATCH_ERR) |
					  (1 << STRIPE_BITMAP_PENDING)),
			"stripe state: %lx\n", sh->state);
		WARN_ONCE(head_sh->state & ((1 << STRIPE_DISCARD) |
					      (1 << STRIPE_REPLACED)),
			"head stripe state: %lx\n", head_sh->state);

		set_mask_bits(&sh->state, ~(STRIPE_EXPAND_SYNC_FLAGS |
					    (1 << STRIPE_PREREAD_ACTIVE) |
					    (1 << STRIPE_DEGRADED)),
			      head_sh->state & (1 << STRIPE_INSYNC));

		sh->check_state = head_sh->check_state;
		sh->reconstruct_state = head_sh->reconstruct_state;
		for (i = 0; i < sh->disks; i++) {
			if (test_and_clear_bit(R5_Overlap, &sh->dev[i].flags))
				do_wakeup = 1;
			sh->dev[i].flags = head_sh->dev[i].flags &
				(~((1 << R5_WriteError) | (1 << R5_Overlap)));
		}
		spin_lock_irq(&sh->stripe_lock);
		sh->batch_head = NULL;
		spin_unlock_irq(&sh->stripe_lock);
		if (handle_flags == 0 ||
		    sh->state & handle_flags)
			set_bit(STRIPE_HANDLE, &sh->state);
		raid5_release_stripe(sh);
	}
	spin_lock_irq(&head_sh->stripe_lock);
	head_sh->batch_head = NULL;
	spin_unlock_irq(&head_sh->stripe_lock);
	for (i = 0; i < head_sh->disks; i++)
		if (test_and_clear_bit(R5_Overlap, &head_sh->dev[i].flags))
			do_wakeup = 1;
	if (head_sh->state & handle_flags)
		set_bit(STRIPE_HANDLE, &head_sh->state);

	if (do_wakeup)
		wake_up(&head_sh->raid_conf->wait_for_overlap);
}

static void handle_stripe(struct stripe_head *sh)
{
	struct stripe_head_state s;
	struct r5conf *conf = sh->raid_conf;
	int i;
	int prexor;
	int disks = sh->disks;
	struct r5dev *pdev, *qdev;

	clear_bit(STRIPE_HANDLE, &sh->state);
	if (test_and_set_bit_lock(STRIPE_ACTIVE, &sh->state)) {
		/* already being handled, ensure it gets handled
		 * again when current action finishes */
		set_bit(STRIPE_HANDLE, &sh->state);
		return;
	}

	if (clear_batch_ready(sh) ) {
		clear_bit_unlock(STRIPE_ACTIVE, &sh->state);
		return;
	}

	if (test_and_clear_bit(STRIPE_BATCH_ERR, &sh->state))
		break_stripe_batch_list(sh, 0);

	if (test_bit(STRIPE_SYNC_REQUESTED, &sh->state) && !sh->batch_head) {
		spin_lock(&sh->stripe_lock);
		/* Cannot process 'sync' concurrently with 'discard' */
		if (!test_bit(STRIPE_DISCARD, &sh->state) &&
		    test_and_clear_bit(STRIPE_SYNC_REQUESTED, &sh->state)) {
			set_bit(STRIPE_SYNCING, &sh->state);
			clear_bit(STRIPE_INSYNC, &sh->state);
			clear_bit(STRIPE_REPLACED, &sh->state);
		}
		spin_unlock(&sh->stripe_lock);
	}
	clear_bit(STRIPE_DELAYED, &sh->state);

	pr_debug("handling stripe %llu, state=%#lx cnt=%d, "
		"pd_idx=%d, qd_idx=%d\n, check:%d, reconstruct:%d\n",
	       (unsigned long long)sh->sector, sh->state,
	       atomic_read(&sh->count), sh->pd_idx, sh->qd_idx,
	       sh->check_state, sh->reconstruct_state);

	analyse_stripe(sh, &s);

	if (test_bit(STRIPE_LOG_TRAPPED, &sh->state))
		goto finish;

	if (s.handle_bad_blocks) {
		set_bit(STRIPE_HANDLE, &sh->state);
		goto finish;
	}

	if (unlikely(s.blocked_rdev)) {
		if (s.syncing || s.expanding || s.expanded ||
		    s.replacing || s.to_write || s.written) {
			set_bit(STRIPE_HANDLE, &sh->state);
			goto finish;
		}
		/* There is nothing for the blocked_rdev to block */
		rdev_dec_pending(s.blocked_rdev, conf->mddev);
		s.blocked_rdev = NULL;
	}

	if (s.to_fill && !test_bit(STRIPE_BIOFILL_RUN, &sh->state)) {
		set_bit(STRIPE_OP_BIOFILL, &s.ops_request);
		set_bit(STRIPE_BIOFILL_RUN, &sh->state);
	}

	pr_debug("locked=%d uptodate=%d to_read=%d"
	       " to_write=%d failed=%d failed_num=%d,%d\n",
	       s.locked, s.uptodate, s.to_read, s.to_write, s.failed,
	       s.failed_num[0], s.failed_num[1]);
	/* check if the array has lost more than max_degraded devices and,
	 * if so, some requests might need to be failed.
	 */
	if (s.failed > conf->max_degraded || s.log_failed) {
		sh->check_state = 0;
		sh->reconstruct_state = 0;
		break_stripe_batch_list(sh, 0);
		if (s.to_read+s.to_write+s.written)
			handle_failed_stripe(conf, sh, &s, disks, &s.return_bi);
		if (s.syncing + s.replacing)
			handle_failed_sync(conf, sh, &s);
	}

	/* Now we check to see if any write operations have recently
	 * completed
	 */
	prexor = 0;
	if (sh->reconstruct_state == reconstruct_state_prexor_drain_result)
		prexor = 1;
	if (sh->reconstruct_state == reconstruct_state_drain_result ||
	    sh->reconstruct_state == reconstruct_state_prexor_drain_result) {
		sh->reconstruct_state = reconstruct_state_idle;

		/* All the 'written' buffers and the parity block are ready to
		 * be written back to disk
		 */
		BUG_ON(!test_bit(R5_UPTODATE, &sh->dev[sh->pd_idx].flags) &&
		       !test_bit(R5_Discard, &sh->dev[sh->pd_idx].flags));
		BUG_ON(sh->qd_idx >= 0 &&
		       !test_bit(R5_UPTODATE, &sh->dev[sh->qd_idx].flags) &&
		       !test_bit(R5_Discard, &sh->dev[sh->qd_idx].flags));
		for (i = disks; i--; ) {
			struct r5dev *dev = &sh->dev[i];
			if (test_bit(R5_LOCKED, &dev->flags) &&
				(i == sh->pd_idx || i == sh->qd_idx ||
				 dev->written)) {
				pr_debug("Writing block %d\n", i);
				set_bit(R5_Wantwrite, &dev->flags);
				if (prexor)
					continue;
				if (s.failed > 1)
					continue;
				if (!test_bit(R5_Insync, &dev->flags) ||
				    ((i == sh->pd_idx || i == sh->qd_idx)  &&
				     s.failed == 0))
					set_bit(STRIPE_INSYNC, &sh->state);
			}
		}
		if (test_and_clear_bit(STRIPE_PREREAD_ACTIVE, &sh->state))
			s.dec_preread_active = 1;
	}

	/*
	 * might be able to return some write requests if the parity blocks
	 * are safe, or on a failed drive
	 */
	pdev = &sh->dev[sh->pd_idx];
	s.p_failed = (s.failed >= 1 && s.failed_num[0] == sh->pd_idx)
		|| (s.failed >= 2 && s.failed_num[1] == sh->pd_idx);
	qdev = &sh->dev[sh->qd_idx];
	s.q_failed = (s.failed >= 1 && s.failed_num[0] == sh->qd_idx)
		|| (s.failed >= 2 && s.failed_num[1] == sh->qd_idx)
		|| conf->level < 6;

	if (s.written &&
	    (s.p_failed || ((test_bit(R5_Insync, &pdev->flags)
			     && !test_bit(R5_LOCKED, &pdev->flags)
			     && (test_bit(R5_UPTODATE, &pdev->flags) ||
				 test_bit(R5_Discard, &pdev->flags))))) &&
	    (s.q_failed || ((test_bit(R5_Insync, &qdev->flags)
			     && !test_bit(R5_LOCKED, &qdev->flags)
			     && (test_bit(R5_UPTODATE, &qdev->flags) ||
				 test_bit(R5_Discard, &qdev->flags))))))
		handle_stripe_clean_event(conf, sh, disks, &s.return_bi);

	/* Now we might consider reading some blocks, either to check/generate
	 * parity, or to satisfy requests
	 * or to load a block that is being partially written.
	 */
	if (s.to_read || s.non_overwrite
	    || (conf->level == 6 && s.to_write && s.failed)
	    || (s.syncing && (s.uptodate + s.compute < disks))
	    || s.replacing
	    || s.expanding)
		handle_stripe_fill(sh, &s, disks);

	/* Now to consider new write requests and what else, if anything
	 * should be read.  We do not handle new writes when:
	 * 1/ A 'write' operation (copy+xor) is already in flight.
	 * 2/ A 'check' operation is in flight, as it may clobber the parity
	 *    block.
	 */
	if (s.to_write && !sh->reconstruct_state && !sh->check_state)
		handle_stripe_dirtying(conf, sh, &s, disks);

	/* maybe we need to check and possibly fix the parity for this stripe
	 * Any reads will already have been scheduled, so we just see if enough
	 * data is available.  The parity check is held off while parity
	 * dependent operations are in flight.
	 */
	if (sh->check_state ||
	    (s.syncing && s.locked == 0 &&
	     !test_bit(STRIPE_COMPUTE_RUN, &sh->state) &&
	     !test_bit(STRIPE_INSYNC, &sh->state))) {
		if (conf->level == 6)
			handle_parity_checks6(conf, sh, &s, disks);
		else
			handle_parity_checks5(conf, sh, &s, disks);
	}

	if ((s.replacing || s.syncing) && s.locked == 0
	    && !test_bit(STRIPE_COMPUTE_RUN, &sh->state)
	    && !test_bit(STRIPE_REPLACED, &sh->state)) {
		/* Write out to replacement devices where possible */
		for (i = 0; i < conf->raid_disks; i++)
			if (test_bit(R5_NeedReplace, &sh->dev[i].flags)) {
				WARN_ON(!test_bit(R5_UPTODATE, &sh->dev[i].flags));
				set_bit(R5_WantReplace, &sh->dev[i].flags);
				set_bit(R5_LOCKED, &sh->dev[i].flags);
				s.locked++;
			}
		if (s.replacing)
			set_bit(STRIPE_INSYNC, &sh->state);
		set_bit(STRIPE_REPLACED, &sh->state);
	}
	if ((s.syncing || s.replacing) && s.locked == 0 &&
	    !test_bit(STRIPE_COMPUTE_RUN, &sh->state) &&
	    test_bit(STRIPE_INSYNC, &sh->state)) {