summaryrefslogtreecommitdiff
path: root/drivers/virt/fsl_hypervisor.c
blob: d3eca879a0a85474f858e79b759d8b4920ba9709 (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
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
/*
 * Freescale Hypervisor Management Driver

 * Copyright (C) 2008-2011 Freescale Semiconductor, Inc.
 * Author: Timur Tabi <timur@freescale.com>
 *
 * This file is licensed under the terms of the GNU General Public License
 * version 2.  This program is licensed "as is" without any warranty of any
 * kind, whether express or implied.
 *
 * The Freescale hypervisor management driver provides several services to
 * drivers and applications related to the Freescale hypervisor:
 *
 * 1. An ioctl interface for querying and managing partitions.
 *
 * 2. A file interface to reading incoming doorbells.
 *
 * 3. An interrupt handler for shutting down the partition upon receiving the
 *    shutdown doorbell from a manager partition.
 *
 * 4. A kernel interface for receiving callbacks when a managed partition
 *    shuts down.
 */

#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/init.h>
#include <linux/types.h>
#include <linux/err.h>
#include <linux/fs.h>
#include <linux/miscdevice.h>
#include <linux/mm.h>
#include <linux/pagemap.h>
#include <linux/slab.h>
#include <linux/poll.h>
#include <linux/of.h>
#include <linux/of_irq.h>
#include <linux/reboot.h>
#include <linux/uaccess.h>
#include <linux/notifier.h>
#include <linux/interrupt.h>

#include <linux/io.h>
#include <asm/fsl_hcalls.h>

#include <linux/fsl_hypervisor.h>

static BLOCKING_NOTIFIER_HEAD(failover_subscribers);

/*
 * Ioctl interface for FSL_HV_IOCTL_PARTITION_RESTART
 *
 * Restart a running partition
 */
static long ioctl_restart(struct fsl_hv_ioctl_restart __user *p)
{
	struct fsl_hv_ioctl_restart param;

	/* Get the parameters from the user */
	if (copy_from_user(&param, p, sizeof(struct fsl_hv_ioctl_restart)))
		return -EFAULT;

	param.ret = fh_partition_restart(param.partition);

	if (copy_to_user(&p->ret, &param.ret, sizeof(__u32)))
		return -EFAULT;

	return 0;
}

/*
 * Ioctl interface for FSL_HV_IOCTL_PARTITION_STATUS
 *
 * Query the status of a partition
 */
static long ioctl_status(struct fsl_hv_ioctl_status __user *p)
{
	struct fsl_hv_ioctl_status param;
	u32 status;

	/* Get the parameters from the user */
	if (copy_from_user(&param, p, sizeof(struct fsl_hv_ioctl_status)))
		return -EFAULT;

	param.ret = fh_partition_get_status(param.partition, &status);
	if (!param.ret)
		param.status = status;

	if (copy_to_user(p, &param, sizeof(struct fsl_hv_ioctl_status)))
		return -EFAULT;

	return 0;
}

/*
 * Ioctl interface for FSL_HV_IOCTL_PARTITION_START
 *
 * Start a stopped partition.
 */
static long ioctl_start(struct fsl_hv_ioctl_start __user *p)
{
	struct fsl_hv_ioctl_start param;

	/* Get the parameters from the user */
	if (copy_from_user(&param, p, sizeof(struct fsl_hv_ioctl_start)))
		return -EFAULT;

	param.ret = fh_partition_start(param.partition, param.entry_point,
				       param.load);

	if (copy_to_user(&p->ret, &param.ret, sizeof(__u32)))
		return -EFAULT;

	return 0;
}

/*
 * Ioctl interface for FSL_HV_IOCTL_PARTITION_STOP
 *
 * Stop a running partition
 */
static long ioctl_stop(struct fsl_hv_ioctl_stop __user *p)
{
	struct fsl_hv_ioctl_stop param;

	/* Get the parameters from the user */
	if (copy_from_user(&param, p, sizeof(struct fsl_hv_ioctl_stop)))
		return -EFAULT;

	param.ret = fh_partition_stop(param.partition);

	if (copy_to_user(&p->ret, &param.ret, sizeof(__u32)))
		return -EFAULT;

	return 0;
}

/*
 * Ioctl interface for FSL_HV_IOCTL_MEMCPY
 *
 * The FH_MEMCPY hypercall takes an array of address/address/size structures
 * to represent the data being copied.  As a convenience to the user, this
 * ioctl takes a user-create buffer and a pointer to a guest physically
 * contiguous buffer in the remote partition, and creates the
 * address/address/size array for the hypercall.
 */
static long ioctl_memcpy(struct fsl_hv_ioctl_memcpy __user *p)
{
	struct fsl_hv_ioctl_memcpy param;

	struct page **pages = NULL;
	void *sg_list_unaligned = NULL;
	struct fh_sg_list *sg_list = NULL;

	unsigned int num_pages;
	unsigned long lb_offset; /* Offset within a page of the local buffer */

	unsigned int i;
	long ret = 0;
	int num_pinned; /* return value from get_user_pages() */
	phys_addr_t remote_paddr; /* The next address in the remote buffer */
	uint32_t count; /* The number of bytes left to copy */

	/* Get the parameters from the user */
	if (copy_from_user(&param, p, sizeof(struct fsl_hv_ioctl_memcpy)))
		return -EFAULT;

	/*
	 * One partition must be local, the other must be remote.  In other
	 * words, if source and target are both -1, or are both not -1, then
	 * return an error.
	 */
	if ((param.source == -1) == (param.target == -1))
		return -EINVAL;

	/*
	 * The array of pages returned by get_user_pages() covers only
	 * page-aligned memory.  Since the user buffer is probably not
	 * page-aligned, we need to handle the discrepancy.
	 *
	 * We calculate the offset within a page of the S/G list, and make
	 * adjustments accordingly.  This will result in a page list that looks
	 * like this:
	 *
	 *      ----    <-- first page starts before the buffer
	 *     |    |
	 *     |////|-> ----
	 *     |////|  |    |
	 *      ----   |    |
	 *             |    |
	 *      ----   |    |
	 *     |////|  |    |
	 *     |////|  |    |
	 *     |////|  |    |
	 *      ----   |    |
	 *             |    |
	 *      ----   |    |
	 *     |////|  |    |
	 *     |////|  |    |
	 *     |////|  |    |
	 *      ----   |    |
	 *             |    |
	 *      ----   |    |
	 *     |////|  |    |
	 *     |////|-> ----
	 *     |    |   <-- last page ends after the buffer
	 *      ----
	 *
	 * The distance between the start of the first page and the start of the
	 * buffer is lb_offset.  The hashed (///) areas are the parts of the
	 * page list that contain the actual buffer.
	 *
	 * The advantage of this approach is that the number of pages is
	 * equal to the number of entries in the S/G list that we give to the
	 * hypervisor.
	 */
	lb_offset = param.local_vaddr & (PAGE_SIZE - 1);
	num_pages = (param.count + lb_offset + PAGE_SIZE - 1) >> PAGE_SHIFT;

	/* Allocate the buffers we need */

	/*
	 * 'pages' is an array of struct page pointers that's initialized by
	 * get_user_pages().
	 */
	pages = kzalloc(num_pages * sizeof(struct page *), GFP_KERNEL);
	if (!pages) {
		pr_debug("fsl-hv: could not allocate page list\n");
		return -ENOMEM;
	}

	/*
	 * sg_list is the list of fh_sg_list objects that we pass to the
	 * hypervisor.
	 */
	sg_list_unaligned = kmalloc(num_pages * sizeof(struct fh_sg_list) +
		sizeof(struct fh_sg_list) - 1, GFP_KERNEL);
	if (!sg_list_unaligned) {
		pr_debug("fsl-hv: could not allocate S/G list\n");
		ret = -ENOMEM;
		goto exit;
	}
	sg_list = PTR_ALIGN(sg_list_unaligned, sizeof(struct fh_sg_list));

	/* Get the physical addresses of the source buffer */
	num_pinned = get_user_pages_unlocked(param.local_vaddr - lb_offset,
		num_pages, pages, (param.source == -1) ? 0 : FOLL_WRITE);

	if (num_pinned != num_pages) {
		/* get_user_pages() failed */
		pr_debug("fsl-hv: could not lock source buffer\n");
		ret = (num_pinned < 0) ? num_pinned : -EFAULT;
		goto exit;
	}

	/*
	 * Build the fh_sg_list[] array.  The first page is special
	 * because it's misaligned.
	 */
	if (param.source == -1) {
		sg_list[0].source = page_to_phys(pages[0]) + lb_offset;
		sg_list[0].target = param.remote_paddr;
	} else {
		sg_list[0].source = param.remote_paddr;
		sg_list[0].target = page_to_phys(pages[0]) + lb_offset;
	}
	sg_list[0].size = min_t(uint64_t, param.count, PAGE_SIZE - lb_offset);

	remote_paddr = param.remote_paddr + sg_list[0].size;
	count = param.count - sg_list[0].size;

	for (i = 1; i < num_pages; i++) {
		if (param.source == -1) {
			/* local to remote */
			sg_list[i].source = page_to_phys(pages[i]);
			sg_list[i].target = remote_paddr;
		} else {
			/* remote to local */
			sg_list[i].source = remote_paddr;
			sg_list[i].target = page_to_phys(pages[i]);
		}
		sg_list[i].size = min_t(uint64_t, count, PAGE_SIZE);

		remote_paddr += sg_list[i].size;
		count -= sg_list[i].size;
	}

	param.ret = fh_partition_memcpy(param.source, param.target,
		virt_to_phys(sg_list), num_pages);

exit:
	if (pages) {
		for (i = 0; i < num_pages; i++)
			if (pages[i])
				put_page(pages[i]);
	}

	kfree(sg_list_unaligned);
	kfree(pages);

	if (!ret)
		if (copy_to_user(&p->ret, &param.ret, sizeof(__u32)))
			return -EFAULT;

	return ret;
}

/*
 * Ioctl interface for FSL_HV_IOCTL_DOORBELL
 *
 * Ring a doorbell
 */
static long ioctl_doorbell(struct fsl_hv_ioctl_doorbell __user *p)
{
	struct fsl_hv_ioctl_doorbell param;

	/* Get the parameters from the user. */
	if (copy_from_user(&param, p, sizeof(struct fsl_hv_ioctl_doorbell)))
		return -EFAULT;

	param.ret = ev_doorbell_send(param.doorbell);

	if (copy_to_user(&p->ret, &param.ret, sizeof(__u32)))
		return -EFAULT;

	return 0;
}

static long ioctl_dtprop(struct fsl_hv_ioctl_prop __user *p, int set)
{
	struct fsl_hv_ioctl_prop param;
	char __user *upath, *upropname;
	void __user *upropval;
	char *path = NULL, *propname = NULL;
	void *propval = NULL;
	int ret = 0;

	/* Get the parameters from the user. */
	if (copy_from_user(&param, p, sizeof(struct fsl_hv_ioctl_prop)))
		return -EFAULT;

	upath = (char __user *)(uintptr_t)param.path;
	upropname = (char __user *)(uintptr_t)param.propname;
	upropval = (void __user *)(uintptr_t)param.propval;

	path = strndup_user(upath, FH_DTPROP_MAX_PATHLEN);
	if (IS_ERR(path)) {
		ret = PTR_ERR(path);
		goto out;
	}

	propname = strndup_user(upropname, FH_DTPROP_MAX_PATHLEN);
	if (IS_ERR(propname)) {
		ret = PTR_ERR(propname);
		goto out;
	}

	if (param.proplen > FH_DTPROP_MAX_PROPLEN) {
		ret = -EINVAL;
		goto out;
	}

	propval = kmalloc(param.proplen, GFP_KERNEL);
	if (!propval) {
		ret = -ENOMEM;
		goto out;
	}

	if (set) {
		if (copy_from_user(propval, upropval, param.proplen)) {
			ret = -EFAULT;
			goto out;
		}

		param.ret = fh_partition_set_dtprop(param.handle,
						    virt_to_phys(path),
						    virt_to_phys(propname),
						    virt_to_phys(propval),
						    param.proplen);
	} else {
		param.ret = fh_partition_get_dtprop(param.handle,
						    virt_to_phys(path),
						    virt_to_phys(propname),
						    virt_to_phys(propval),
						    &param.proplen);

		if (param.ret == 0) {
			if (copy_to_user(upropval, propval, param.proplen) ||
			    put_user(param.proplen, &p->proplen)) {
				ret = -EFAULT;
				goto out;
			}
		}
	}

	if (put_user(param.ret, &p->ret))
		ret = -EFAULT;

out:
	kfree(path);
	kfree(propval);
	kfree(propname);

	return ret;
}

/*
 * Ioctl main entry point
 */
static long fsl_hv_ioctl(struct file *file, unsigned int cmd,
			 unsigned long argaddr)
{
	void __user *arg = (void __user *)argaddr;
	long ret;

	switch (cmd) {
	case FSL_HV_IOCTL_PARTITION_RESTART:
		ret = ioctl_restart(arg);
		break;
	case FSL_HV_IOCTL_PARTITION_GET_STATUS:
		ret = ioctl_status(arg);
		break;
	case FSL_HV_IOCTL_PARTITION_START:
		ret = ioctl_start(arg);
		break;
	case FSL_HV_IOCTL_PARTITION_STOP:
		ret = ioctl_stop(arg);
		break;
	case FSL_HV_IOCTL_MEMCPY:
		ret = ioctl_memcpy(arg);
		break;
	case FSL_HV_IOCTL_DOORBELL:
		ret = ioctl_doorbell(arg);
		break;
	case FSL_HV_IOCTL_GETPROP:
		ret = ioctl_dtprop(arg, 0);
		break;
	case FSL_HV_IOCTL_SETPROP:
		ret = ioctl_dtprop(arg, 1);
		break;
	default:
		pr_debug("fsl-hv: bad ioctl dir=%u type=%u cmd=%u size=%u\n",
			 _IOC_DIR(cmd), _IOC_TYPE(cmd), _IOC_NR(cmd),
			 _IOC_SIZE(cmd));
		return -ENOTTY;
	}

	return ret;
}

/* Linked list of processes that have us open */
static struct list_head db_list;

/* spinlock for db_list */
static DEFINE_SPINLOCK(db_list_lock);

/* The size of the doorbell event queue.  This must be a power of two. */
#define QSIZE	16

/* Returns the next head/tail pointer, wrapping around the queue if necessary */
#define nextp(x) (((x) + 1) & (QSIZE - 1))

/* Per-open data structure */
struct doorbell_queue {
	struct list_head list;
	spinlock_t lock;
	wait_queue_head_t wait;
	unsigned int head;
	unsigned int tail;
	uint32_t q[QSIZE];
};

/* Linked list of ISRs that we registered */
struct list_head isr_list;

/* Per-ISR data structure */
struct doorbell_isr {
	struct list_head list;
	unsigned int irq;
	uint32_t doorbell;	/* The doorbell handle */
	uint32_t partition;	/* The partition handle, if used */
};

/*
 * Add a doorbell to all of the doorbell queues
 */
static void fsl_hv_queue_doorbell(uint32_t doorbell)
{
	struct doorbell_queue *dbq;
	unsigned long flags;

	/* Prevent another core from modifying db_list */
	spin_lock_irqsave(&db_list_lock, flags);

	list_for_each_entry(dbq, &db_list, list) {
		if (dbq->head != nextp(dbq->tail)) {
			dbq->q[dbq->tail] = doorbell;
			/*
			 * This memory barrier eliminates the need to grab
			 * the spinlock for dbq.
			 */
			smp_wmb();
			dbq->tail = nextp(dbq->tail);
			wake_up_interruptible(&dbq->wait);
		}
	}

	spin_unlock_irqrestore(&db_list_lock, flags);
}

/*
 * Interrupt handler for all doorbells
 *
 * We use the same interrupt handler for all doorbells.  Whenever a doorbell
 * is rung, and we receive an interrupt, we just put the handle for that
 * doorbell (passed to us as *data) into all of the queues.
 */
static irqreturn_t fsl_hv_isr(int irq, void *data)
{
	fsl_hv_queue_doorbell((uintptr_t) data);

	return IRQ_HANDLED;
}

/*
 * State change thread function
 *
 * The state change notification arrives in an interrupt, but we can't call
 * blocking_notifier_call_chain() in an interrupt handler.  We could call
 * atomic_notifier_call_chain(), but that would require the clients' call-back
 * function to run in interrupt context.  Since we don't want to impose that
 * restriction on the clients, we use a threaded IRQ to process the
 * notification in kernel context.
 */
static irqreturn_t fsl_hv_state_change_thread(int irq, void *data)
{
	struct doorbell_isr *dbisr = data;

	blocking_notifier_call_chain(&failover_subscribers, dbisr->partition,
				     NULL);

	return IRQ_HANDLED;
}

/*
 * Interrupt handler for state-change doorbells
 */
static irqreturn_t fsl_hv_state_change_isr(int irq, void *data)
{
	unsigned int status;
	struct doorbell_isr *dbisr = data;
	int ret;

	/* It's still a doorbell, so add it to all the queues. */
	fsl_hv_queue_doorbell(dbisr->doorbell);

	/* Determine the new state, and if it's stopped, notify the clients. */
	ret = fh_partition_get_status(dbisr->partition, &status);
	if (!ret && (status == FH_PARTITION_STOPPED))
		return IRQ_WAKE_THREAD;

	return IRQ_HANDLED;
}

/*
 * Returns a bitmask indicating whether a read will block
 */
static unsigned int fsl_hv_poll(struct file *filp, struct poll_table_struct *p)
{
	struct doorbell_queue *dbq = filp->private_data;
	unsigned long flags;
	unsigned int mask;

	spin_lock_irqsave(&dbq->lock, flags);

	poll_wait(filp, &dbq->wait, p);
	mask = (dbq->head == dbq->tail) ? 0 : (POLLIN | POLLRDNORM);

	spin_unlock_irqrestore(&dbq->lock, flags);

	return mask;
}

/*
 * Return the handles for any incoming doorbells
 *
 * If there are doorbell handles in the queue for this open instance, then
 * return them to the caller as an array of 32-bit integers.  Otherwise,
 * block until there is at least one handle to return.
 */
static ssize_t fsl_hv_read(struct file *filp, char __user *buf, size_t len,
			   loff_t *off)
{
	struct doorbell_queue *dbq = filp->private_data;
	uint32_t __user *p = (uint32_t __user *) buf; /* for put_user() */
	unsigned long flags;
	ssize_t count = 0;

	/* Make sure we stop when the user buffer is full. */
	while (len >= sizeof(uint32_t)) {
		uint32_t dbell;	/* Local copy of doorbell queue data */

		spin_lock_irqsave(&dbq->lock, flags);

		/*
		 * If the queue is empty, then either we're done or we need
		 * to block.  If the application specified O_NONBLOCK, then
		 * we return the appropriate error code.
		 */
		if (dbq->head == dbq->tail) {
			spin_unlock_irqrestore(&dbq->lock, flags);
			if (count)
				break;
			if (filp->f_flags & O_NONBLOCK)
				return -EAGAIN;
			if (wait_event_interruptible(dbq->wait,
						     dbq->head != dbq->tail))
				return -ERESTARTSYS;
			continue;
		}

		/*
		 * Even though we have an smp_wmb() in the ISR, the core
		 * might speculatively execute the "dbell = ..." below while
		 * it's evaluating the if-statement above.  In that case, the
		 * value put into dbell could be stale if the core accepts the
		 * speculation. To prevent that, we need a read memory barrier
		 * here as well.
		 */
		smp_rmb();

		/* Copy the data to a temporary local buffer, because
		 * we can't call copy_to_user() from inside a spinlock
		 */
		dbell = dbq->q[dbq->head];
		dbq->head = nextp(dbq->head);

		spin_unlock_irqrestore(&dbq->lock, flags);

		if (put_user(dbell, p))
			return -EFAULT;
		p++;
		count += sizeof(uint32_t);
		len -= sizeof(uint32_t);
	}

	return count;
}

/*
 * Open the driver and prepare for reading doorbells.
 *
 * Every time an application opens the driver, we create a doorbell queue
 * for that file handle.  This queue is used for any incoming doorbells.
 */
static int fsl_hv_open(struct inode *inode, struct file *filp)
{
	struct doorbell_queue *dbq;
	unsigned long flags;
	int ret = 0;

	dbq = kzalloc(sizeof(struct doorbell_queue), GFP_KERNEL);
	if (!dbq) {
		pr_err("fsl-hv: out of memory\n");
		return -ENOMEM;
	}

	spin_lock_init(&dbq->lock);
	init_waitqueue_head(&dbq->wait);

	spin_lock_irqsave(&db_list_lock, flags);
	list_add(&dbq->list, &db_list);
	spin_unlock_irqrestore(&db_list_lock, flags);

	filp->private_data = dbq;

	return ret;
}

/*
 * Close the driver
 */
static int fsl_hv_close(struct inode *inode, struct file *filp)
{
	struct doorbell_queue *dbq = filp->private_data;
	unsigned long flags;

	int ret = 0;

	spin_lock_irqsave(&db_list_lock, flags);
	list_del(&dbq->list);
	spin_unlock_irqrestore(&db_list_lock, flags);

	kfree(dbq);

	return ret;
}

static const struct file_operations fsl_hv_fops = {
	.owner = THIS_MODULE,
	.open = fsl_hv_open,
	.release = fsl_hv_close,
	.poll = fsl_hv_poll,
	.read = fsl_hv_read,
	.unlocked_ioctl = fsl_hv_ioctl,
	.compat_ioctl = fsl_hv_ioctl,
};

static struct miscdevice fsl_hv_misc_dev = {
	MISC_DYNAMIC_MINOR,
	"fsl-hv",
	&fsl_hv_fops
};

static irqreturn_t fsl_hv_shutdown_isr(int irq, void *data)
{
	orderly_poweroff(false);

	return IRQ_HANDLED;
}

/*
 * Returns the handle of the parent of the given node
 *
 * The handle is the value of the 'hv-handle' property
 */
static int get_parent_handle(struct device_node *np)
{
	struct device_node *parent;
	const uint32_t *prop;
	uint32_t handle;
	int len;

	parent = of_get_parent(np);
	if (!parent)
		/* It's not really possible for this to fail */
		return -ENODEV;

	/*
	 * The proper name for the handle property is "hv-handle", but some
	 * older versions of the hypervisor used "reg".
	 */
	prop = of_get_property(parent, "hv-handle", &len);
	if (!prop)
		prop = of_get_property(parent, "reg", &len);

	if (!prop || (len != sizeof(uint32_t))) {
		/* This can happen only if the node is malformed */
		of_node_put(parent);
		return -ENODEV;
	}

	handle = be32_to_cpup(prop);
	of_node_put(parent);

	return handle;
}

/*
 * Register a callback for failover events
 *
 * This function is called by device drivers to register their callback
 * functions for fail-over events.
 */
int fsl_hv_failover_register(struct notifier_block *nb)
{
	return blocking_notifier_chain_register(&failover_subscribers, nb);
}
EXPORT_SYMBOL(fsl_hv_failover_register);

/*
 * Unregister a callback for failover events
 */
int fsl_hv_failover_unregister(struct notifier_block *nb)
{
	return blocking_notifier_chain_unregister(&failover_subscribers, nb);
}
EXPORT_SYMBOL(fsl_hv_failover_unregister);

/*
 * Return TRUE if we're running under FSL hypervisor
 *
 * This function checks to see if we're running under the Freescale
 * hypervisor, and returns zero if we're not, or non-zero if we are.
 *
 * First, it checks if MSR[GS]==1, which means we're running under some
 * hypervisor.  Then it checks if there is a hypervisor node in the device
 * tree.  Currently, that means there needs to be a node in the root called
 * "hypervisor" and which has a property named "fsl,hv-version".
 */
static int has_fsl_hypervisor(void)
{
	struct device_node *node;
	int ret;

	node = of_find_node_by_path("/hypervisor");
	if (!node)
		return 0;

	ret = of_find_property(node, "fsl,hv-version", NULL) != NULL;

	of_node_put(node);

	return ret;
}

/*
 * Freescale hypervisor management driver init
 *
 * This function is called when this module is loaded.
 *
 * Register ourselves as a miscellaneous driver.  This will register the
 * fops structure and create the right sysfs entries for udev.
 */
static int __init fsl_hypervisor_init(void)
{
	struct device_node *np;
	struct doorbell_isr *dbisr, *n;
	int ret;

	pr_info("Freescale hypervisor management driver\n");

	if (!has_fsl_hypervisor()) {
		pr_info("fsl-hv: no hypervisor found\n");
		return -ENODEV;
	}

	ret = misc_register(&fsl_hv_misc_dev);
	if (ret) {
		pr_err("fsl-hv: cannot register device\n");
		return ret;
	}

	INIT_LIST_HEAD(&db_list);
	INIT_LIST_HEAD(&isr_list);

	for_each_compatible_node(np, NULL, "epapr,hv-receive-doorbell") {
		unsigned int irq;
		const uint32_t *handle;

		handle = of_get_property(np, "interrupts", NULL);
		irq = irq_of_parse_and_map(np, 0);
		if (!handle || (irq == NO_IRQ)) {
			pr_err("fsl-hv: no 'interrupts' property in %s node\n",
				np->full_name);
			continue;
		}

		dbisr = kzalloc(sizeof(*dbisr), GFP_KERNEL);
		if (!dbisr)
			goto out_of_memory;

		dbisr->irq = irq;
		dbisr->doorbell = be32_to_cpup(handle);

		if (of_device_is_compatible(np, "fsl,hv-shutdown-doorbell")) {
			/* The shutdown doorbell gets its own ISR */
			ret = request_irq(irq, fsl_hv_shutdown_isr, 0,
					  np->name, NULL);
		} else if (of_device_is_compatible(np,
			"fsl,hv-state-change-doorbell")) {
			/*
			 * The state change doorbell triggers a notification if
			 * the state of the managed partition changes to
			 * "stopped". We need a separate interrupt handler for
			 * that, and we also need to know the handle of the
			 * target partition, not just the handle of the
			 * doorbell.
			 */
			dbisr->partition = ret = get_parent_handle(np);
			if (ret < 0) {
				pr_err("fsl-hv: node %s has missing or "
				       "malformed parent\n", np->full_name);
				kfree(dbisr);
				continue;
			}
			ret = request_threaded_irq(irq, fsl_hv_state_change_isr,
						   fsl_hv_state_change_thread,
						   0, np->name, dbisr);
		} else
			ret = request_irq(irq, fsl_hv_isr, 0, np->name, dbisr);

		if (ret < 0) {
			pr_err("fsl-hv: could not request irq %u for node %s\n",
			       irq, np->full_name);
			kfree(dbisr);
			continue;
		}

		list_add(&dbisr->list, &isr_list);

		pr_info("fsl-hv: registered handler for doorbell %u\n",
			dbisr->doorbell);
	}

	return 0;

out_of_memory:
	list_for_each_entry_safe(dbisr, n, &isr_list, list) {
		free_irq(dbisr->irq, dbisr);
		list_del(&dbisr->list);
		kfree(dbisr);
	}

	misc_deregister(&fsl_hv_misc_dev);

	return -ENOMEM;
}

/*
 * Freescale hypervisor management driver termination
 *
 * This function is called when this driver is unloaded.
 */
static void __exit fsl_hypervisor_exit(void)
{
	struct doorbell_isr *dbisr, *n;

	list_for_each_entry_safe(dbisr, n, &isr_list, list) {
		free_irq(dbisr->irq, dbisr);
		list_del(&dbisr->list);
		kfree(dbisr);
	}

	misc_deregister(&fsl_hv_misc_dev);
}

module_init(fsl_hypervisor_init);
module_exit(fsl_hypervisor_exit);

MODULE_AUTHOR("Timur Tabi <timur@freescale.com>");
MODULE_DESCRIPTION("Freescale hypervisor management driver");
MODULE_LICENSE("GPL v2");