summaryrefslogtreecommitdiff
path: root/drivers/block/xen-blkback/blkback.c
blob: c73910cc28c919bfdcdc6f1972af1f1f95822138 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
/******************************************************************************
 *
 * Back-end of the driver for virtual block devices. This portion of the
 * driver exports a 'unified' block-device interface that can be accessed
 * by any operating system that implements a compatible front end. A
 * reference front-end implementation can be found in:
 *  drivers/block/xen-blkfront.c
 *
 * Copyright (c) 2003-2004, Keir Fraser & Steve Hand
 * Copyright (c) 2005, Christopher Clark
 *
 * This program is free software; you can redistribute it and/or
 * modify it under the terms of the GNU General Public License version 2
 * as published by the Free Software Foundation; or, when distributed
 * separately from the Linux kernel or incorporated into other
 * software packages, subject to the following license:
 *
 * Permission is hereby granted, free of charge, to any person obtaining a copy
 * of this source file (the "Software"), to deal in the Software without
 * restriction, including without limitation the rights to use, copy, modify,
 * merge, publish, distribute, sublicense, and/or sell copies of the Software,
 * and to permit persons to whom the Software is furnished to do so, subject to
 * the following conditions:
 *
 * The above copyright notice and this permission notice shall be included in
 * all copies or substantial portions of the Software.
 *
 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
 * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
 * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
 * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
 * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
 * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
 * IN THE SOFTWARE.
 */

#include <linux/spinlock.h>
#include <linux/kthread.h>
#include <linux/list.h>
#include <linux/delay.h>
#include <linux/freezer.h>

#include <xen/events.h>
#include <xen/page.h>
#include <asm/xen/hypervisor.h>
#include <asm/xen/hypercall.h>
#include "common.h"

/*
 * These are rather arbitrary. They are fairly large because adjacent requests
 * pulled from a communication ring are quite likely to end up being part of
 * the same scatter/gather request at the disc.
 *
 * ** TRY INCREASING 'xen_blkif_reqs' IF WRITE SPEEDS SEEM TOO LOW **
 *
 * This will increase the chances of being able to write whole tracks.
 * 64 should be enough to keep us competitive with Linux.
 */
static int xen_blkif_reqs = 64;
module_param_named(reqs, xen_blkif_reqs, int, 0);
MODULE_PARM_DESC(reqs, "Number of blkback requests to allocate");

/* Run-time switchable: /sys/module/blkback/parameters/ */
static unsigned int log_stats;
module_param(log_stats, int, 0644);

/*
 * Each outstanding request that we've passed to the lower device layers has a
 * 'pending_req' allocated to it. Each buffer_head that completes decrements
 * the pendcnt towards zero. When it hits zero, the specified domain has a
 * response queued for it, with the saved 'id' passed back.
 */
struct pending_req {
	struct xen_blkif	*blkif;
	u64			id;
	int			nr_pages;
	atomic_t		pendcnt;
	unsigned short		operation;
	int			status;
	struct list_head	free_list;
};

#define BLKBACK_INVALID_HANDLE (~0)

struct xen_blkbk {
	struct pending_req	*pending_reqs;
	/* List of all 'pending_req' available */
	struct list_head	pending_free;
	/* And its spinlock. */
	spinlock_t		pending_free_lock;
	wait_queue_head_t	pending_free_wq;
	/* The list of all pages that are available. */
	struct page		**pending_pages;
	/* And the grant handles that are available. */
	grant_handle_t		*pending_grant_handles;
};

static struct xen_blkbk *blkbk;

/*
 * Little helpful macro to figure out the index and virtual address of the
 * pending_pages[..]. For each 'pending_req' we have have up to
 * BLKIF_MAX_SEGMENTS_PER_REQUEST (11) pages. The seg would be from 0 through
 * 10 and would index in the pending_pages[..].
 */
static inline int vaddr_pagenr(struct pending_req *req, int seg)
{
	return (req - blkbk->pending_reqs) *
		BLKIF_MAX_SEGMENTS_PER_REQUEST + seg;
}

#define pending_page(req, seg) pending_pages[vaddr_pagenr(req, seg)]

static inline unsigned long vaddr(struct pending_req *req, int seg)
{
	unsigned long pfn = page_to_pfn(blkbk->pending_page(req, seg));
	return (unsigned long)pfn_to_kaddr(pfn);
}

#define pending_handle(_req, _seg) \
	(blkbk->pending_grant_handles[vaddr_pagenr(_req, _seg)])


static int do_block_io_op(struct xen_blkif *blkif);
static int dispatch_rw_block_io(struct xen_blkif *blkif,
				struct blkif_request *req,
				struct pending_req *pending_req);
static void make_response(struct xen_blkif *blkif, u64 id,
			  unsigned short op, int st);

/*
 * Retrieve from the 'pending_reqs' a free pending_req structure to be used.
 */
static struct pending_req *alloc_req(void)
{
	struct pending_req *req = NULL;
	unsigned long flags;

	spin_lock_irqsave(&blkbk->pending_free_lock, flags);
	if (!list_empty(&blkbk->pending_free)) {
		req = list_entry(blkbk->pending_free.next, struct pending_req,
				 free_list);
		list_del(&req->free_list);
	}
	spin_unlock_irqrestore(&blkbk->pending_free_lock, flags);
	return req;
}

/*
 * Return the 'pending_req' structure back to the freepool. We also
 * wake up the thread if it was waiting for a free page.
 */
static void free_req(struct pending_req *req)
{
	unsigned long flags;
	int was_empty;

	spin_lock_irqsave(&blkbk->pending_free_lock, flags);
	was_empty = list_empty(&blkbk->pending_free);
	list_add(&req->free_list, &blkbk->pending_free);
	spin_unlock_irqrestore(&blkbk->pending_free_lock, flags);
	if (was_empty)
		wake_up(&blkbk->pending_free_wq);
}

/*
 * Routines for managing virtual block devices (vbds).
 */
static int xen_vbd_translate(struct phys_req *req, struct xen_blkif *blkif,
			     int operation)
{
	struct xen_vbd *vbd = &blkif->vbd;
	int rc = -EACCES;

	if ((operation != READ) && vbd->readonly)
		goto out;

	if (likely(req->nr_sects)) {
		blkif_sector_t end = req->sector_number + req->nr_sects;

		if (unlikely(end < req->sector_number))
			goto out;
		if (unlikely(end > vbd_sz(vbd)))
			goto out;
	}

	req->dev  = vbd->pdevice;
	req->bdev = vbd->bdev;
	rc = 0;

 out:
	return rc;
}

static void xen_vbd_resize(struct xen_blkif *blkif)
{
	struct xen_vbd *vbd = &blkif->vbd;
	struct xenbus_transaction xbt;
	int err;
	struct xenbus_device *dev = xen_blkbk_xenbus(blkif->be);
	unsigned long long new_size = vbd_sz(vbd);

	pr_info(DRV_PFX "VBD Resize: Domid: %d, Device: (%d, %d)\n",
		blkif->domid, MAJOR(vbd->pdevice), MINOR(vbd->pdevice));
	pr_info(DRV_PFX "VBD Resize: new size %llu\n", new_size);
	vbd->size = new_size;
again:
	err = xenbus_transaction_start(&xbt);
	if (err) {
		pr_warn(DRV_PFX "Error starting transaction");
		return;
	}
	err = xenbus_printf(xbt, dev->nodename, "sectors", "%llu",
			    (unsigned long long)vbd_sz(vbd));
	if (err) {
		pr_warn(DRV_PFX "Error writing new size");
		goto abort;
	}
	/*
	 * Write the current state; we will use this to synchronize
	 * the front-end. If the current state is "connected" the
	 * front-end will get the new size information online.
	 */
	err = xenbus_printf(xbt, dev->nodename, "state", "%d", dev->state);
	if (err) {
		pr_warn(DRV_PFX "Error writing the state");
		goto abort;
	}

	err = xenbus_transaction_end(xbt, 0);
	if (err == -EAGAIN)
		goto again;
	if (err)
		pr_warn(DRV_PFX "Error ending transaction");
	return;
abort:
	xenbus_transaction_end(xbt, 1);
}

/*
 * Notification from the guest OS.
 */
static void blkif_notify_work(struct xen_blkif *blkif)
{
	blkif->waiting_reqs = 1;
	wake_up(&blkif->wq);
}

irqreturn_t xen_blkif_be_int(int irq, void *dev_id)
{
	blkif_notify_work(dev_id);
	return IRQ_HANDLED;
}

/*
 * SCHEDULER FUNCTIONS
 */

static void print_stats(struct xen_blkif *blkif)
{
	pr_info("xen-blkback (%s): oo %3d  |  rd %4d  |  wr %4d  |  f %4d\n",
		 current->comm, blkif->st_oo_req,
		 blkif->st_rd_req, blkif->st_wr_req, blkif->st_f_req);
	blkif->st_print = jiffies + msecs_to_jiffies(10 * 1000);
	blkif->st_rd_req = 0;
	blkif->st_wr_req = 0;
	blkif->st_oo_req = 0;
}

int xen_blkif_schedule(void *arg)
{
	struct xen_blkif *blkif = arg;
	struct xen_vbd *vbd = &blkif->vbd;

	xen_blkif_get(blkif);

	while (!kthread_should_stop()) {
		if (try_to_freeze())
			continue;
		if (unlikely(vbd->size != vbd_sz(vbd)))
			xen_vbd_resize(blkif);

		wait_event_interruptible(
			blkif->wq,
			blkif->waiting_reqs || kthread_should_stop());
		wait_event_interruptible(
			blkbk->pending_free_wq,
			!list_empty(&blkbk->pending_free) ||
			kthread_should_stop());

		blkif->waiting_reqs = 0;
		smp_mb(); /* clear flag *before* checking for work */

		if (do_block_io_op(blkif))
			blkif->waiting_reqs = 1;

		if (log_stats && time_after(jiffies, blkif->st_print))
			print_stats(blkif);
	}

	if (log_stats)
		print_stats(blkif);

	blkif->xenblkd = NULL;
	xen_blkif_put(blkif);

	return 0;
}

struct seg_buf {
	unsigned long buf;
	unsigned int nsec;
};
/*
 * Unmap the grant references, and also remove the M2P over-rides
 * used in the 'pending_req'.
 */
static void xen_blkbk_unmap(struct pending_req *req)
{
	struct gnttab_unmap_grant_ref unmap[BLKIF_MAX_SEGMENTS_PER_REQUEST];
	unsigned int i, invcount = 0;
	grant_handle_t handle;
	int ret;

	for (i = 0; i < req->nr_pages; i++) {
		handle = pending_handle(req, i);
		if (handle == BLKBACK_INVALID_HANDLE)
			continue;
		gnttab_set_unmap_op(&unmap[invcount], vaddr(req, i),
				    GNTMAP_host_map, handle);
		pending_handle(req, i) = BLKBACK_INVALID_HANDLE;
		invcount++;
	}

	ret = HYPERVISOR_grant_table_op(
		GNTTABOP_unmap_grant_ref, unmap, invcount);
	BUG_ON(ret);
	/*
	 * Note, we use invcount, so nr->pages, so we can't index
	 * using vaddr(req, i).
	 */
	for (i = 0; i < invcount; i++) {
		ret = m2p_remove_override(
			virt_to_page(unmap[i].host_addr), false);
		if (ret) {
			pr_alert(DRV_PFX "Failed to remove M2P override for %lx\n",
				 (unsigned long)unmap[i].host_addr);
			continue;
		}
	}
}

static int xen_blkbk_map(struct blkif_request *req,
			 struct pending_req *pending_req,
			 struct seg_buf seg[])
{
	struct gnttab_map_grant_ref map[BLKIF_MAX_SEGMENTS_PER_REQUEST];
	int i;
	int nseg = req->nr_segments;
	int ret = 0;

	/*
	 * Fill out preq.nr_sects with proper amount of sectors, and setup
	 * assign map[..] with the PFN of the page in our domain with the
	 * corresponding grant reference for each page.
	 */
	for (i = 0; i < nseg; i++) {
		uint32_t flags;

		flags = GNTMAP_host_map;
		if (pending_req->operation != BLKIF_OP_READ)
			flags |= GNTMAP_readonly;
		gnttab_set_map_op(&map[i], vaddr(pending_req, i), flags,
				  req->u.rw.seg[i].gref,
				  pending_req->blkif->domid);
	}

	ret = HYPERVISOR_grant_table_op(GNTTABOP_map_grant_ref, map, nseg);
	BUG_ON(ret);

	/*
	 * Now swizzle the MFN in our domain with the MFN from the other domain
	 * so that when we access vaddr(pending_req,i) it has the contents of
	 * the page from the other domain.
	 */
	for (i = 0; i < nseg; i++) {
		if (unlikely(map[i].status != 0)) {
			pr_debug(DRV_PFX "invalid buffer -- could not remap it\n");
			map[i].handle = BLKBACK_INVALID_HANDLE;
			ret |= 1;
		}

		pending_handle(pending_req, i) = map[i].handle;

		if (ret)
			continue;

		ret = m2p_add_override(PFN_DOWN(map[i].dev_bus_addr),
			blkbk->pending_page(pending_req, i), false);
		if (ret) {
			pr_alert(DRV_PFX "Failed to install M2P override for %lx (ret: %d)\n",
				 (unsigned long)map[i].dev_bus_addr, ret);
			/* We could switch over to GNTTABOP_copy */
			continue;
		}

		seg[i].buf  = map[i].dev_bus_addr |
			(req->u.rw.seg[i].first_sect << 9);
	}
	return ret;
}

/*
 * Completion callback on the bio's. Called as bh->b_end_io()
 */

static void __end_block_io_op(struct pending_req *pending_req, int error)
{
	/* An error fails the entire request. */
	if ((pending_req->operation == BLKIF_OP_FLUSH_DISKCACHE) &&
	    (error == -EOPNOTSUPP)) {
		pr_debug(DRV_PFX "flush diskcache op failed, not supported\n");
		xen_blkbk_flush_diskcache(XBT_NIL, pending_req->blkif->be, 0);
		pending_req->status = BLKIF_RSP_EOPNOTSUPP;
	} else if (error) {
		pr_debug(DRV_PFX "Buffer not up-to-date at end of operation,"
			 " error=%d\n", error);
		pending_req->status = BLKIF_RSP_ERROR;
	}

	/*
	 * If all of the bio's have completed it is time to unmap
	 * the grant references associated with 'request' and provide
	 * the proper response on the ring.
	 */
	if (atomic_dec_and_test(&pending_req->pendcnt)) {
		xen_blkbk_unmap(pending_req);
		make_response(pending_req->blkif, pending_req->id,
			      pending_req->operation, pending_req->status);
		xen_blkif_put(pending_req->blkif);
		free_req(pending_req);
	}
}

/*
 * bio callback.
 */
static void end_block_io_op(struct bio *bio, int error)
{
	__end_block_io_op(bio->bi_private, error);
	bio_put(bio);
}



/*
 * Function to copy the from the ring buffer the 'struct blkif_request'
 * (which has the sectors we want, number of them, grant references, etc),
 * and transmute  it to the block API to hand it over to the proper block disk.
 */
static int do_block_io_op(struct xen_blkif *blkif)
{
	union blkif_back_rings *blk_rings = &blkif->blk_rings;
	struct blkif_request req;
	struct pending_req *pending_req;
	RING_IDX rc, rp;
	int more_to_do = 0;

	rc = blk_rings->common.req_cons;
	rp = blk_rings->common.sring->req_prod;
	rmb(); /* Ensure we see queued requests up to 'rp'. */

	while (rc != rp) {

		if (RING_REQUEST_CONS_OVERFLOW(&blk_rings->common, rc))
			break;

		if (kthread_should_stop()) {
			more_to_do = 1;
			break;
		}

		pending_req = alloc_req();
		if (NULL == pending_req) {
			blkif->st_oo_req++;
			more_to_do = 1;
			break;
		}

		switch (blkif->blk_protocol) {
		case BLKIF_PROTOCOL_NATIVE:
			memcpy(&req, RING_GET_REQUEST(&blk_rings->native, rc), sizeof(req));
			break;
		case BLKIF_PROTOCOL_X86_32:
			blkif_get_x86_32_req(&req, RING_GET_REQUEST(&blk_rings->x86_32, rc));
			break;
		case BLKIF_PROTOCOL_X86_64:
			blkif_get_x86_64_req(&req, RING_GET_REQUEST(&blk_rings->x86_64, rc));
			break;
		default:
			BUG();
		}
		blk_rings->common.req_cons = ++rc; /* before make_response() */

		/* Apply all sanity checks to /private copy/ of request. */
		barrier();

		if (dispatch_rw_block_io(blkif, &req, pending_req))
			break;

		/* Yield point for this unbounded loop. */
		cond_resched();
	}

	return more_to_do;
}

/*
 * Transmutation of the 'struct blkif_request' to a proper 'struct bio'
 * and call the 'submit_bio' to pass it to the underlying storage.
 */
static int dispatch_rw_block_io(struct xen_blkif *blkif,
				struct blkif_request *req,
				struct pending_req *pending_req)
{
	struct phys_req preq;
	struct seg_buf seg[BLKIF_MAX_SEGMENTS_PER_REQUEST];
	unsigned int nseg;
	struct bio *bio = NULL;
	struct bio *biolist[BLKIF_MAX_SEGMENTS_PER_REQUEST];
	int i, nbio = 0;
	int operation;
	struct blk_plug plug;

	switch (req->operation) {
	case BLKIF_OP_READ:
		blkif->st_rd_req++;
		operation = READ;
		break;
	case BLKIF_OP_WRITE:
		blkif->st_wr_req++;
		operation = WRITE_ODIRECT;
		break;
	case BLKIF_OP_FLUSH_DISKCACHE:
		blkif->st_f_req++;
		operation = WRITE_FLUSH;
		break;
	case BLKIF_OP_WRITE_BARRIER:
	default:
		operation = 0; /* make gcc happy */
		goto fail_response;
		break;
	}

	/* Check that the number of segments is sane. */
	nseg = req->nr_segments;
	if (unlikely(nseg == 0 && operation != WRITE_FLUSH) ||
	    unlikely(nseg > BLKIF_MAX_SEGMENTS_PER_REQUEST)) {
		pr_debug(DRV_PFX "Bad number of segments in request (%d)\n",
			 nseg);
		/* Haven't submitted any bio's yet. */
		goto fail_response;
	}

	preq.dev           = req->handle;
	preq.sector_number = req->u.rw.sector_number;
	preq.nr_sects      = 0;

	pending_req->blkif     = blkif;
	pending_req->id        = req->id;
	pending_req->operation = req->operation;
	pending_req->status    = BLKIF_RSP_OKAY;
	pending_req->nr_pages  = nseg;

	for (i = 0; i < nseg; i++) {
		seg[i].nsec = req->u.rw.seg[i].last_sect -
			req->u.rw.seg[i].first_sect + 1;
		if ((req->u.rw.seg[i].last_sect >= (PAGE_SIZE >> 9)) ||
		    (req->u.rw.seg[i].last_sect < req->u.rw.seg[i].first_sect))
			goto fail_response;
		preq.nr_sects += seg[i].nsec;

	}

	if (xen_vbd_translate(&preq, blkif, operation) != 0) {
		pr_debug(DRV_PFX "access denied: %s of [%llu,%llu] on dev=%04x\n",
			 operation == READ ? "read" : "write",
			 preq.sector_number,
			 preq.sector_number + preq.nr_sects, preq.dev);
		goto fail_response;
	}

	/*
	 * This check _MUST_ be done after xen_vbd_translate as the preq.bdev
	 * is set there.
	 */
	for (i = 0; i < nseg; i++) {
		if (((int)preq.sector_number|(int)seg[i].nsec) &
		    ((bdev_logical_block_size(preq.bdev) >> 9) - 1)) {
			pr_debug(DRV_PFX "Misaligned I/O request from domain %d",
				 blkif->domid);
			goto fail_response;
		}
	}

	/*
	 * If we have failed at this point, we need to undo the M2P override,
	 * set gnttab_set_unmap_op on all of the grant references and perform
	 * the hypercall to unmap the grants - that is all done in
	 * xen_blkbk_unmap.
	 */
	if (xen_blkbk_map(req, pending_req, seg))
		goto fail_flush;

	/* This corresponding xen_blkif_put is done in __end_block_io_op */
	xen_blkif_get(blkif);

	for (i = 0; i < nseg; i++) {
		while ((bio == NULL) ||
		       (bio_add_page(bio,
				     blkbk->pending_page(pending_req, i),
				     seg[i].nsec << 9,
				     seg[i].buf & ~PAGE_MASK) == 0)) {

			bio = bio_alloc(GFP_KERNEL, nseg-i);
			if (unlikely(bio == NULL))
				goto fail_put_bio;

			biolist[nbio++] = bio;
			bio->bi_bdev    = preq.bdev;
			bio->bi_private = pending_req;
			bio->bi_end_io  = end_block_io_op;
			bio->bi_sector  = preq.sector_number;
		}

		preq.sector_number += seg[i].nsec;
	}

	/* This will be hit if the operation was a flush. */
	if (!bio) {
		BUG_ON(operation != WRITE_FLUSH);

		bio = bio_alloc(GFP_KERNEL, 0);
		if (unlikely(bio == NULL))
			goto fail_put_bio;

		biolist[nbio++] = bio;
		bio->bi_bdev    = preq.bdev;
		bio->bi_private = pending_req;
		bio->bi_end_io  = end_block_io_op;
	}

	/*
	 * We set it one so that the last submit_bio does not have to call
	 * atomic_inc.
	 */
	atomic_set(&pending_req->pendcnt, nbio);

	/* Get a reference count for the disk queue and start sending I/O */
	blk_start_plug(&plug);

	for (i = 0; i < nbio; i++)
		submit_bio(operation, biolist[i]);

	/* Let the I/Os go.. */
	blk_finish_plug(&plug);

	if (operation == READ)
		blkif->st_rd_sect += preq.nr_sects;
	else if (operation == WRITE || operation == WRITE_FLUSH)
		blkif->st_wr_sect += preq.nr_sects;

	return 0;

 fail_flush:
	xen_blkbk_unmap(pending_req);
 fail_response:
	/* Haven't submitted any bio's yet. */
	make_response(blkif, req->id, req->operation, BLKIF_RSP_ERROR);
	free_req(pending_req);
	msleep(1); /* back off a bit */
	return -EIO;

 fail_put_bio:
	for (i = 0; i < nbio; i++)
		bio_put(biolist[i]);
	__end_block_io_op(pending_req, -EINVAL);
	msleep(1); /* back off a bit */
	return -EIO;
}



/*
 * Put a response on the ring on how the operation fared.
 */
static void make_response(struct xen_blkif *blkif, u64 id,
			  unsigned short op, int st)
{
	struct blkif_response  resp;
	unsigned long     flags;
	union blkif_back_rings *blk_rings = &blkif->blk_rings;
	int more_to_do = 0;
	int notify;

	resp.id        = id;
	resp.operation = op;
	resp.status    = st;

	spin_lock_irqsave(&blkif->blk_ring_lock, flags);
	/* Place on the response ring for the relevant domain. */
	switch (blkif->blk_protocol) {
	case BLKIF_PROTOCOL_NATIVE:
		memcpy(RING_GET_RESPONSE(&blk_rings->native, blk_rings->native.rsp_prod_pvt),
		       &resp, sizeof(resp));
		break;
	case BLKIF_PROTOCOL_X86_32:
		memcpy(RING_GET_RESPONSE(&blk_rings->x86_32, blk_rings->x86_32.rsp_prod_pvt),
		       &resp, sizeof(resp));
		break;
	case BLKIF_PROTOCOL_X86_64:
		memcpy(RING_GET_RESPONSE(&blk_rings->x86_64, blk_rings->x86_64.rsp_prod_pvt),
		       &resp, sizeof(resp));
		break;
	default:
		BUG();
	}
	blk_rings->common.rsp_prod_pvt++;
	RING_PUSH_RESPONSES_AND_CHECK_NOTIFY(&blk_rings->common, notify);
	if (blk_rings->common.rsp_prod_pvt == blk_rings->common.req_cons) {
		/*
		 * Tail check for pending requests. Allows frontend to avoid
		 * notifications if requests are already in flight (lower
		 * overheads and promotes batching).
		 */
		RING_FINAL_CHECK_FOR_REQUESTS(&blk_rings->common, more_to_do);

	} else if (RING_HAS_UNCONSUMED_REQUESTS(&blk_rings->common)) {
		more_to_do = 1;
	}

	spin_unlock_irqrestore(&blkif->blk_ring_lock, flags);

	if (more_to_do)
		blkif_notify_work(blkif);
	if (notify)
		notify_remote_via_irq(blkif->irq);
}

static int __init xen_blkif_init(void)
{
	int i, mmap_pages;
	int rc = 0;

	if (!xen_pv_domain())
		return -ENODEV;

	blkbk = kzalloc(sizeof(struct xen_blkbk), GFP_KERNEL);
	if (!blkbk) {
		pr_alert(DRV_PFX "%s: out of memory!\n", __func__);
		return -ENOMEM;
	}

	mmap_pages = xen_blkif_reqs * BLKIF_MAX_SEGMENTS_PER_REQUEST;

	blkbk->pending_reqs          = kmalloc(sizeof(blkbk->pending_reqs[0]) *
					xen_blkif_reqs, GFP_KERNEL);
	blkbk->pending_grant_handles = kzalloc(sizeof(blkbk->pending_grant_handles[0]) *
					mmap_pages, GFP_KERNEL);
	blkbk->pending_pages         = kzalloc(sizeof(blkbk->pending_pages[0]) *
					mmap_pages, GFP_KERNEL);

	if (!blkbk->pending_reqs || !blkbk->pending_grant_handles ||
	    !blkbk->pending_pages) {
		rc = -ENOMEM;
		goto out_of_memory;
	}

	for (i = 0; i < mmap_pages; i++) {
		blkbk->pending_grant_handles[i] = BLKBACK_INVALID_HANDLE;
		blkbk->pending_pages[i] = alloc_page(GFP_KERNEL);
		if (blkbk->pending_pages[i] == NULL) {
			rc = -ENOMEM;
			goto out_of_memory;
		}
	}
	rc = xen_blkif_interface_init();
	if (rc)
		goto failed_init;

	memset(blkbk->pending_reqs, 0, sizeof(blkbk->pending_reqs));

	INIT_LIST_HEAD(&blkbk->pending_free);
	spin_lock_init(&blkbk->pending_free_lock);
	init_waitqueue_head(&blkbk->pending_free_wq);

	for (i = 0; i < xen_blkif_reqs; i++)
		list_add_tail(&blkbk->pending_reqs[i].free_list,
			      &blkbk->pending_free);

	rc = xen_blkif_xenbus_init();
	if (rc)
		goto failed_init;

	return 0;

 out_of_memory:
	pr_alert(DRV_PFX "%s: out of memory\n", __func__);
 failed_init:
	kfree(blkbk->pending_reqs);
	kfree(blkbk->pending_grant_handles);
	for (i = 0; i < mmap_pages; i++) {
		if (blkbk->pending_pages[i])
			__free_page(blkbk->pending_pages[i]);
	}
	kfree(blkbk->pending_pages);
	kfree(blkbk);
	blkbk = NULL;
	return rc;
}

module_init(xen_blkif_init);

MODULE_LICENSE("Dual BSD/GPL");