aboutsummaryrefslogtreecommitdiffstats
path: root/drivers/rtc/rtc-twl4030.c
blob: 9c8c70c497dcc6a515b44d71035bd313d3955116 (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
/*
 * rtc-twl4030.c -- TWL4030 Real Time Clock interface
 *
 * Copyright (C) 2007 MontaVista Software, Inc
 * Author: Alexandre Rusev <source@mvista.com>
 *
 * Based on original TI driver twl4030-rtc.c
 *   Copyright (C) 2006 Texas Instruments, Inc.
 *
 * Based on rtc-omap.c
 *   Copyright (C) 2003 MontaVista Software, Inc.
 *   Author: George G. Davis <gdavis@mvista.com> or <source@mvista.com>
 *   Copyright (C) 2006 David Brownell
 *
 * This program is free software; you can redistribute it and/or
 * modify it under the terms of the GNU General Public License
 * as published by the Free Software Foundation; either version
 * 2 of the License, or (at your option) any later version.
 */

#include <linux/kernel.h>
#include <linux/errno.h>
#include <linux/init.h>
#include <linux/module.h>
#include <linux/types.h>
#include <linux/rtc.h>
#include <linux/bcd.h>
#include <linux/platform_device.h>
#include <linux/interrupt.h>

#include <linux/i2c/twl4030.h>


/*
 * RTC block register offsets (use TWL_MODULE_RTC)
 */
#define REG_SECONDS_REG                          0x00
#define REG_MINUTES_REG                          0x01
#define REG_HOURS_REG                            0x02
#define REG_DAYS_REG                             0x03
#define REG_MONTHS_REG                           0x04
#define REG_YEARS_REG                            0x05
#define REG_WEEKS_REG                            0x06

#define REG_ALARM_SECONDS_REG                    0x07
#define REG_ALARM_MINUTES_REG                    0x08
#define REG_ALARM_HOURS_REG                      0x09
#define REG_ALARM_DAYS_REG                       0x0A
#define REG_ALARM_MONTHS_REG                     0x0B
#define REG_ALARM_YEARS_REG                      0x0C

#define REG_RTC_CTRL_REG                         0x0D
#define REG_RTC_STATUS_REG                       0x0E
#define REG_RTC_INTERRUPTS_REG                   0x0F

#define REG_RTC_COMP_LSB_REG                     0x10
#define REG_RTC_COMP_MSB_REG                     0x11

/* RTC_CTRL_REG bitfields */
#define BIT_RTC_CTRL_REG_STOP_RTC_M              0x01
#define BIT_RTC_CTRL_REG_ROUND_30S_M             0x02
#define BIT_RTC_CTRL_REG_AUTO_COMP_M             0x04
#define BIT_RTC_CTRL_REG_MODE_12_24_M            0x08
#define BIT_RTC_CTRL_REG_TEST_MODE_M             0x10
#define BIT_RTC_CTRL_REG_SET_32_COUNTER_M        0x20
#define BIT_RTC_CTRL_REG_GET_TIME_M              0x40

/* RTC_STATUS_REG bitfields */
#define BIT_RTC_STATUS_REG_RUN_M                 0x02
#define BIT_RTC_STATUS_REG_1S_EVENT_M            0x04
#define BIT_RTC_STATUS_REG_1M_EVENT_M            0x08
#define BIT_RTC_STATUS_REG_1H_EVENT_M            0x10
#define BIT_RTC_STATUS_REG_1D_EVENT_M            0x20
#define BIT_RTC_STATUS_REG_ALARM_M               0x40
#define BIT_RTC_STATUS_REG_POWER_UP_M            0x80

/* RTC_INTERRUPTS_REG bitfields */
#define BIT_RTC_INTERRUPTS_REG_EVERY_M           0x03
#define BIT_RTC_INTERRUPTS_REG_IT_TIMER_M        0x04
#define BIT_RTC_INTERRUPTS_REG_IT_ALARM_M        0x08


/* REG_SECONDS_REG through REG_YEARS_REG is how many registers? */
#define ALL_TIME_REGS		6

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

/*
 * Supports 1 byte read from TWL4030 RTC register.
 */
static int twl4030_rtc_read_u8(u8 *data, u8 reg)
{
	int ret;

	ret = twl4030_i2c_read_u8(TWL4030_MODULE_RTC, data, reg);
	if (ret < 0)
		pr_err("twl4030_rtc: Could not read TWL4030"
		       "register %X - error %d\n", reg, ret);
	return ret;
}

/*
 * Supports 1 byte write to TWL4030 RTC registers.
 */
static int twl4030_rtc_write_u8(u8 data, u8 reg)
{
	int ret;

	ret = twl4030_i2c_write_u8(TWL4030_MODULE_RTC, data, reg);
	if (ret < 0)
		pr_err("twl4030_rtc: Could not write TWL4030"
		       "register %X - error %d\n", reg, ret);
	return ret;
}

/*
 * Cache the value for timer/alarm interrupts register; this is
 * only changed by callers holding rtc ops lock (or resume).
 */
static unsigned char rtc_irq_bits;

/*
 * Enable 1/second update and/or alarm interrupts.
 */
static int set_rtc_irq_bit(unsigned char bit)
{
	unsigned char val;
	int ret;

	val = rtc_irq_bits | bit;
	val &= ~BIT_RTC_INTERRUPTS_REG_EVERY_M;
	ret = twl4030_rtc_write_u8(val, REG_RTC_INTERRUPTS_REG);
	if (ret == 0)
		rtc_irq_bits = val;

	return ret;
}

/*
 * Disable update and/or alarm interrupts.
 */
static int mask_rtc_irq_bit(unsigned char bit)
{
	unsigned char val;
	int ret;

	val = rtc_irq_bits & ~bit;
	ret = twl4030_rtc_write_u8(val, REG_RTC_INTERRUPTS_REG);
	if (ret == 0)
		rtc_irq_bits = val;

	return ret;
}

static int twl4030_rtc_alarm_irq_enable(struct device *dev, unsigned enabled)
{
	int ret;

	if (enabled)
		ret = set_rtc_irq_bit(BIT_RTC_INTERRUPTS_REG_IT_ALARM_M);
	else
		ret = mask_rtc_irq_bit(BIT_RTC_INTERRUPTS_REG_IT_ALARM_M);

	return ret;
}

static int twl4030_rtc_update_irq_enable(struct device *dev, unsigned enabled)
{
	int ret;

	if (enabled)
		ret = set_rtc_irq_bit(BIT_RTC_INTERRUPTS_REG_IT_TIMER_M);
	else
		ret = mask_rtc_irq_bit(BIT_RTC_INTERRUPTS_REG_IT_TIMER_M);

	return ret;
}

/*
 * Gets current TWL4030 RTC time and date parameters.
 *
 * The RTC's time/alarm representation is not what gmtime(3) requires
 * Linux to use:
 *
 *  - Months are 1..12 vs Linux 0-11
 *  - Years are 0..99 vs Linux 1900..N (we assume 21st century)
 */
static int twl4030_rtc_read_time(struct device *dev, struct rtc_time *tm)
{
	unsigned char rtc_data[ALL_TIME_REGS + 1];
	int ret;
	u8 save_control;

	ret = twl4030_rtc_read_u8(&save_control, REG_RTC_CTRL_REG);
	if (ret < 0)
		return ret;

	save_control |= BIT_RTC_CTRL_REG_GET_TIME_M;

	ret = twl4030_rtc_write_u8(save_control, REG_RTC_CTRL_REG);
	if (ret < 0)
		return ret;

	ret = twl4030_i2c_read(TWL4030_MODULE_RTC, rtc_data,
			       REG_SECONDS_REG, ALL_TIME_REGS);

	if (ret < 0) {
		dev_err(dev, "rtc_read_time error %d\n", ret);
		return ret;
	}

	tm->tm_sec = bcd2bin(rtc_data[0]);
	tm->tm_min = bcd2bin(rtc_data[1]);
	tm->tm_hour = bcd2bin(rtc_data[2]);
	tm->tm_mday = bcd2bin(rtc_data[3]);
	tm->tm_mon = bcd2bin(rtc_data[4]) - 1;
	tm->tm_year = bcd2bin(rtc_data[5]) + 100;

	return ret;
}

static int twl4030_rtc_set_time(struct device *dev, struct rtc_time *tm)
{
	unsigned char save_control;
	unsigned char rtc_data[ALL_TIME_REGS + 1];
	int ret;

	rtc_data[1] = bin2bcd(tm->tm_sec);
	rtc_data[2] = bin2bcd(tm->tm_min);
	rtc_data[3] = bin2bcd(tm->tm_hour);
	rtc_data[4] = bin2bcd(tm->tm_mday);
	rtc_data[5] = bin2bcd(tm->tm_mon + 1);
	rtc_data[6] = bin2bcd(tm->tm_year - 100);

	/* Stop RTC while updating the TC registers */
	ret = twl4030_rtc_read_u8(&save_control, REG_RTC_CTRL_REG);
	if (ret < 0)
		goto out;

	save_control &= ~BIT_RTC_CTRL_REG_STOP_RTC_M;
	twl4030_rtc_write_u8(save_control, REG_RTC_CTRL_REG);
	if (ret < 0)
		goto out;

	/* update all the time registers in one shot */
	ret = twl4030_i2c_write(TWL4030_MODULE_RTC, rtc_data,
			REG_SECONDS_REG, ALL_TIME_REGS);
	if (ret < 0) {
		dev_err(dev, "rtc_set_time error %d\n", ret);
		goto out;
	}

	/* Start back RTC */
	save_control |= BIT_RTC_CTRL_REG_STOP_RTC_M;
	ret = twl4030_rtc_write_u8(save_control, REG_RTC_CTRL_REG);

out:
	return ret;
}

/*
 * Gets current TWL4030 RTC alarm time.
 */
static int twl4030_rtc_read_alarm(struct device *dev, struct rtc_wkalrm *alm)
{
	unsigned char rtc_data[ALL_TIME_REGS + 1];
	int ret;

	ret = twl4030_i2c_read(TWL4030_MODULE_RTC, rtc_data,
			       REG_ALARM_SECONDS_REG, ALL_TIME_REGS);
	if (ret < 0) {
		dev_err(dev, "rtc_read_alarm error %d\n", ret);
		return ret;
	}

	/* some of these fields may be wildcard/"match all" */
	alm->time.tm_sec = bcd2bin(rtc_data[0]);
	alm->time.tm_min = bcd2bin(rtc_data[1]);
	alm->time.tm_hour = bcd2bin(rtc_data[2]);
	alm->time.tm_mday = bcd2bin(rtc_data[3]);
	alm->time.tm_mon = bcd2bin(rtc_data[4]) - 1;
	alm->time.tm_year = bcd2bin(rtc_data[5]) + 100;

	/* report cached alarm enable state */
	if (rtc_irq_bits & BIT_RTC_INTERRUPTS_REG_IT_ALARM_M)
		alm->enabled = 1;

	return ret;
}

static int twl4030_rtc_set_alarm(struct device *dev, struct rtc_wkalrm *alm)
{
	unsigned char alarm_data[ALL_TIME_REGS + 1];
	int ret;

	ret = twl4030_rtc_alarm_irq_enable(dev, 0);
	if (ret)
		goto out;

	alarm_data[1] = bin2bcd(alm->time.tm_sec);
	alarm_data[2] = bin2bcd(alm->time.tm_min);
	alarm_data[3] = bin2bcd(alm->time.tm_hour);
	alarm_data[4] = bin2bcd(alm->time.tm_mday);
	alarm_data[5] = bin2bcd(alm->time.tm_mon + 1);
	alarm_data[6] = bin2bcd(alm->time.tm_year - 100);

	/* update all the alarm registers in one shot */
	ret = twl4030_i2c_write(TWL4030_MODULE_RTC, alarm_data,
			REG_ALARM_SECONDS_REG, ALL_TIME_REGS);
	if (ret) {
		dev_err(dev, "rtc_set_alarm error %d\n", ret);
		goto out;
	}

	if (alm->enabled)
		ret = twl4030_rtc_alarm_irq_enable(dev, 1);
out:
	return ret;
}

static irqreturn_t twl4030_rtc_interrupt(int irq, void *rtc)
{
	unsigned long events = 0;
	int ret = IRQ_NONE;
	int res;
	u8 rd_reg;

#ifdef CONFIG_LOCKDEP
	/* WORKAROUND for lockdep forcing IRQF_DISABLED on us, which
	 * we don't want and can't tolerate.  Although it might be
	 * friendlier not to borrow this thread context...
	 */
	local_irq_enable();
#endif

	res = twl4030_rtc_read_u8(&rd_reg, REG_RTC_STATUS_REG);
	if (res)
		goto out;
	/*
	 * Figure out source of interrupt: ALARM or TIMER in RTC_STATUS_REG.
	 * only one (ALARM or RTC) interrupt source may be enabled
	 * at time, we also could check our results
	 * by reading RTS_INTERRUPTS_REGISTER[IT_TIMER,IT_ALARM]
	 */
	if (rd_reg & BIT_RTC_STATUS_REG_ALARM_M)
		events |= RTC_IRQF | RTC_AF;
	else
		events |= RTC_IRQF | RTC_UF;

	res = twl4030_rtc_write_u8(rd_reg | BIT_RTC_STATUS_REG_ALARM_M,
				   REG_RTC_STATUS_REG);
	if (res)
		goto out;

	/* Clear on Read enabled. RTC_IT bit of TWL4030_INT_PWR_ISR1
	 * needs 2 reads to clear the interrupt. One read is done in
	 * do_twl4030_pwrirq(). Doing the second read, to clear
	 * the bit.
	 *
	 * FIXME the reason PWR_ISR1 needs an extra read is that
	 * RTC_IF retriggered until we cleared REG_ALARM_M above.
	 * But re-reading like this is a bad hack; by doing so we
	 * risk wrongly clearing status for some other IRQ (losing
	 * the interrupt).  Be smarter about handling RTC_UF ...
	 */
	res = twl4030_i2c_read_u8(TWL4030_MODULE_INT,
			&rd_reg, TWL4030_INT_PWR_ISR1);
	if (res)
		goto out;

	/* Notify RTC core on event */
	rtc_update_irq(rtc, 1, events);

	ret = IRQ_HANDLED;
out:
	return ret;
}

static struct rtc_class_ops twl4030_rtc_ops = {
	.read_time	= twl4030_rtc_read_time,
	.set_time	= twl4030_rtc_set_time,
	.read_alarm	= twl4030_rtc_read_alarm,
	.set_alarm	= twl4030_rtc_set_alarm,
	.alarm_irq_enable = twl4030_rtc_alarm_irq_enable,
	.update_irq_enable = twl4030_rtc_update_irq_enable,
};

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

static int __devinit twl4030_rtc_probe(struct platform_device *pdev)
{
	struct rtc_device *rtc;
	int ret = 0;
	int irq = platform_get_irq(pdev, 0);
	u8 rd_reg;

	if (irq <= 0)
		return -EINVAL;

	rtc = rtc_device_register(pdev->name,
				  &pdev->dev, &twl4030_rtc_ops, THIS_MODULE);
	if (IS_ERR(rtc)) {
		ret = PTR_ERR(rtc);
		dev_err(&pdev->dev, "can't register RTC device, err %ld\n",
			PTR_ERR(rtc));
		goto out0;

	}

	platform_set_drvdata(pdev, rtc);

	ret = twl4030_rtc_read_u8(&rd_reg, REG_RTC_STATUS_REG);
	if (ret < 0)
		goto out1;

	if (rd_reg & BIT_RTC_STATUS_REG_POWER_UP_M)
		dev_warn(&pdev->dev, "Power up reset detected.\n");

	if (rd_reg & BIT_RTC_STATUS_REG_ALARM_M)
		dev_warn(&pdev->dev, "Pending Alarm interrupt detected.\n");

	/* Clear RTC Power up reset and pending alarm interrupts */
	ret = twl4030_rtc_write_u8(rd_reg, REG_RTC_STATUS_REG);
	if (ret < 0)
		goto out1;

	ret = request_irq(irq, twl4030_rtc_interrupt,
				IRQF_TRIGGER_RISING,
				dev_name(&rtc->dev), rtc);
	if (ret < 0) {
		dev_err(&pdev->dev, "IRQ is not free.\n");
		goto out1;
	}

	/* Check RTC module status, Enable if it is off */
	ret = twl4030_rtc_read_u8(&rd_reg, REG_RTC_CTRL_REG);
	if (ret < 0)
		goto out2;

	if (!(rd_reg & BIT_RTC_CTRL_REG_STOP_RTC_M)) {
		dev_info(&pdev->dev, "Enabling TWL4030-RTC.\n");
		rd_reg = BIT_RTC_CTRL_REG_STOP_RTC_M;
		ret = twl4030_rtc_write_u8(rd_reg, REG_RTC_CTRL_REG);
		if (ret < 0)
			goto out2;
	}

	/* init cached IRQ enable bits */
	ret = twl4030_rtc_read_u8(&rtc_irq_bits, REG_RTC_INTERRUPTS_REG);
	if (ret < 0)
		goto out2;

	return ret;

out2:
	free_irq(irq, rtc);
out1:
	rtc_device_unregister(rtc);
out0:
	return ret;
}

/*
 * Disable all TWL4030 RTC module interrupts.
 * Sets status flag to free.
 */
static int __devexit twl4030_rtc_remove(struct platform_device *pdev)
{
	/* leave rtc running, but disable irqs */
	struct rtc_device *rtc = platform_get_drvdata(pdev);
	int irq = platform_get_irq(pdev, 0);

	mask_rtc_irq_bit(BIT_RTC_INTERRUPTS_REG_IT_ALARM_M);
	mask_rtc_irq_bit(BIT_RTC_INTERRUPTS_REG_IT_TIMER_M);

	free_irq(irq, rtc);

	rtc_device_unregister(rtc);
	platform_set_drvdata(pdev, NULL);
	return 0;
}

static void twl4030_rtc_shutdown(struct platform_device *pdev)
{
	/* mask timer interrupts, but leave alarm interrupts on to enable
	   power-on when alarm is triggered */
	mask_rtc_irq_bit(BIT_RTC_INTERRUPTS_REG_IT_TIMER_M);
}

#ifdef CONFIG_PM

static unsigned char irqstat;

static int twl4030_rtc_suspend(struct platform_device *pdev, pm_message_t state)
{
	irqstat = rtc_irq_bits;

	mask_rtc_irq_bit(BIT_RTC_INTERRUPTS_REG_IT_TIMER_M);
	return 0;
}

static int twl4030_rtc_resume(struct platform_device *pdev)
{
	set_rtc_irq_bit(irqstat);
	return 0;
}

#else
#define twl4030_rtc_suspend NULL
#define twl4030_rtc_resume  NULL
#endif

MODULE_ALIAS("platform:twl4030_rtc");

static struct platform_driver twl4030rtc_driver = {
	.probe		= twl4030_rtc_probe,
	.remove		= __devexit_p(twl4030_rtc_remove),
	.shutdown	= twl4030_rtc_shutdown,
	.suspend	= twl4030_rtc_suspend,
	.resume		= twl4030_rtc_resume,
	.driver		= {
		.owner	= THIS_MODULE,
		.name	= "twl4030_rtc",
	},
};

static int __init twl4030_rtc_init(void)
{
	return platform_driver_register(&twl4030rtc_driver);
}
module_init(twl4030_rtc_init);

static void __exit twl4030_rtc_exit(void)
{
	platform_driver_unregister(&twl4030rtc_driver);
}
module_exit(twl4030_rtc_exit);

MODULE_AUTHOR("Texas Instruments, MontaVista Software");
MODULE_LICENSE("GPL");
s="hl num">7, VSTOR_OPERATION_END_INITIALIZATION = 8, VSTOR_OPERATION_QUERY_PROTOCOL_VERSION = 9, VSTOR_OPERATION_QUERY_PROPERTIES = 10, VSTOR_OPERATION_ENUMERATE_BUS = 11, VSTOR_OPERATION_FCHBA_DATA = 12, VSTOR_OPERATION_CREATE_SUB_CHANNELS = 13, VSTOR_OPERATION_MAXIMUM = 13 }; /* * WWN packet for Fibre Channel HBA */ struct hv_fc_wwn_packet { bool primary_active; u8 reserved1; u8 reserved2; u8 primary_port_wwn[8]; u8 primary_node_wwn[8]; u8 secondary_port_wwn[8]; u8 secondary_node_wwn[8]; }; /* * SRB Flag Bits */ #define SRB_FLAGS_QUEUE_ACTION_ENABLE 0x00000002 #define SRB_FLAGS_DISABLE_DISCONNECT 0x00000004 #define SRB_FLAGS_DISABLE_SYNCH_TRANSFER 0x00000008 #define SRB_FLAGS_BYPASS_FROZEN_QUEUE 0x00000010 #define SRB_FLAGS_DISABLE_AUTOSENSE 0x00000020 #define SRB_FLAGS_DATA_IN 0x00000040 #define SRB_FLAGS_DATA_OUT 0x00000080 #define SRB_FLAGS_NO_DATA_TRANSFER 0x00000000 #define SRB_FLAGS_UNSPECIFIED_DIRECTION (SRB_FLAGS_DATA_IN | SRB_FLAGS_DATA_OUT) #define SRB_FLAGS_NO_QUEUE_FREEZE 0x00000100 #define SRB_FLAGS_ADAPTER_CACHE_ENABLE 0x00000200 #define SRB_FLAGS_FREE_SENSE_BUFFER 0x00000400 /* * This flag indicates the request is part of the workflow for processing a D3. */ #define SRB_FLAGS_D3_PROCESSING 0x00000800 #define SRB_FLAGS_IS_ACTIVE 0x00010000 #define SRB_FLAGS_ALLOCATED_FROM_ZONE 0x00020000 #define SRB_FLAGS_SGLIST_FROM_POOL 0x00040000 #define SRB_FLAGS_BYPASS_LOCKED_QUEUE 0x00080000 #define SRB_FLAGS_NO_KEEP_AWAKE 0x00100000 #define SRB_FLAGS_PORT_DRIVER_ALLOCSENSE 0x00200000 #define SRB_FLAGS_PORT_DRIVER_SENSEHASPORT 0x00400000 #define SRB_FLAGS_DONT_START_NEXT_PACKET 0x00800000 #define SRB_FLAGS_PORT_DRIVER_RESERVED 0x0F000000 #define SRB_FLAGS_CLASS_DRIVER_RESERVED 0xF0000000 /* * Platform neutral description of a scsi request - * this remains the same across the write regardless of 32/64 bit * note: it's patterned off the SCSI_PASS_THROUGH structure */ #define STORVSC_MAX_CMD_LEN 0x10 #define POST_WIN7_STORVSC_SENSE_BUFFER_SIZE 0x14 #define PRE_WIN8_STORVSC_SENSE_BUFFER_SIZE 0x12 #define STORVSC_SENSE_BUFFER_SIZE 0x14 #define STORVSC_MAX_BUF_LEN_WITH_PADDING 0x14 /* * Sense buffer size changed in win8; have a run-time * variable to track the size we should use. */ static int sense_buffer_size; /* * The size of the vmscsi_request has changed in win8. The * additional size is because of new elements added to the * structure. These elements are valid only when we are talking * to a win8 host. * Track the correction to size we need to apply. */ static int vmscsi_size_delta; static int vmstor_current_major; static int vmstor_current_minor; struct vmscsi_win8_extension { /* * The following were added in Windows 8 */ u16 reserve; u8 queue_tag; u8 queue_action; u32 srb_flags; u32 time_out_value; u32 queue_sort_ey; } __packed; struct vmscsi_request { u16 length; u8 srb_status; u8 scsi_status; u8 port_number; u8 path_id; u8 target_id; u8 lun; u8 cdb_length; u8 sense_info_length; u8 data_in; u8 reserved; u32 data_transfer_length; union { u8 cdb[STORVSC_MAX_CMD_LEN]; u8 sense_data[STORVSC_SENSE_BUFFER_SIZE]; u8 reserved_array[STORVSC_MAX_BUF_LEN_WITH_PADDING]; }; /* * The following was added in win8. */ struct vmscsi_win8_extension win8_extension; } __attribute((packed)); /* * This structure is sent during the intialization phase to get the different * properties of the channel. */ #define STORAGE_CHANNEL_SUPPORTS_MULTI_CHANNEL 0x1 struct vmstorage_channel_properties { u32 reserved; u16 max_channel_cnt; u16 reserved1; u32 flags; u32 max_transfer_bytes; u64 reserved2; } __packed; /* This structure is sent during the storage protocol negotiations. */ struct vmstorage_protocol_version { /* Major (MSW) and minor (LSW) version numbers. */ u16 major_minor; /* * Revision number is auto-incremented whenever this file is changed * (See FILL_VMSTOR_REVISION macro above). Mismatch does not * definitely indicate incompatibility--but it does indicate mismatched * builds. * This is only used on the windows side. Just set it to 0. */ u16 revision; } __packed; /* Channel Property Flags */ #define STORAGE_CHANNEL_REMOVABLE_FLAG 0x1 #define STORAGE_CHANNEL_EMULATED_IDE_FLAG 0x2 struct vstor_packet { /* Requested operation type */ enum vstor_packet_operation operation; /* Flags - see below for values */ u32 flags; /* Status of the request returned from the server side. */ u32 status; /* Data payload area */ union { /* * Structure used to forward SCSI commands from the * client to the server. */ struct vmscsi_request vm_srb; /* Structure used to query channel properties. */ struct vmstorage_channel_properties storage_channel_properties; /* Used during version negotiations. */ struct vmstorage_protocol_version version; /* Fibre channel address packet */ struct hv_fc_wwn_packet wwn_packet; /* Number of sub-channels to create */ u16 sub_channel_count; /* This will be the maximum of the union members */ u8 buffer[0x34]; }; } __packed; /* * Packet Flags: * * This flag indicates that the server should send back a completion for this * packet. */ #define REQUEST_COMPLETION_FLAG 0x1 /* Matches Windows-end */ enum storvsc_request_type { WRITE_TYPE = 0, READ_TYPE, UNKNOWN_TYPE, }; /* * SRB status codes and masks; a subset of the codes used here. */ #define SRB_STATUS_AUTOSENSE_VALID 0x80 #define SRB_STATUS_INVALID_LUN 0x20 #define SRB_STATUS_SUCCESS 0x01 #define SRB_STATUS_ABORTED 0x02 #define SRB_STATUS_ERROR 0x04 /* * This is the end of Protocol specific defines. */ /* * We setup a mempool to allocate request structures for this driver * on a per-lun basis. The following define specifies the number of * elements in the pool. */ #define STORVSC_MIN_BUF_NR 64 static int storvsc_ringbuffer_size = (20 * PAGE_SIZE); module_param(storvsc_ringbuffer_size, int, S_IRUGO); MODULE_PARM_DESC(storvsc_ringbuffer_size, "Ring buffer size (bytes)"); /* * Timeout in seconds for all devices managed by this driver. */ static int storvsc_timeout = 180; static int msft_blist_flags = BLIST_TRY_VPD_PAGES; #define STORVSC_MAX_IO_REQUESTS 200 static void storvsc_on_channel_callback(void *context); #define STORVSC_MAX_LUNS_PER_TARGET 255 #define STORVSC_MAX_TARGETS 2 #define STORVSC_MAX_CHANNELS 8 #define STORVSC_FC_MAX_LUNS_PER_TARGET 255 #define STORVSC_FC_MAX_TARGETS 128 #define STORVSC_FC_MAX_CHANNELS 8 #define STORVSC_IDE_MAX_LUNS_PER_TARGET 64 #define STORVSC_IDE_MAX_TARGETS 1 #define STORVSC_IDE_MAX_CHANNELS 1 struct storvsc_cmd_request { struct list_head entry; struct scsi_cmnd *cmd; unsigned int bounce_sgl_count; struct scatterlist *bounce_sgl; struct hv_device *device; /* Synchronize the request/response if needed */ struct completion wait_event; unsigned char *sense_buffer; struct hv_multipage_buffer data_buffer; struct vstor_packet vstor_packet; }; /* A storvsc device is a device object that contains a vmbus channel */ struct storvsc_device { struct hv_device *device; bool destroy; bool drain_notify; bool open_sub_channel; atomic_t num_outstanding_req; struct Scsi_Host *host; wait_queue_head_t waiting_to_drain; /* * Each unique Port/Path/Target represents 1 channel ie scsi * controller. In reality, the pathid, targetid is always 0 * and the port is set by us */ unsigned int port_number; unsigned char path_id; unsigned char target_id; /* Used for vsc/vsp channel reset process */ struct storvsc_cmd_request init_request; struct storvsc_cmd_request reset_request; }; struct stor_mem_pools { struct kmem_cache *request_pool; mempool_t *request_mempool; }; struct hv_host_device { struct hv_device *dev; unsigned int port; unsigned char path; unsigned char target; }; struct storvsc_scan_work { struct work_struct work; struct Scsi_Host *host; uint lun; }; static void storvsc_device_scan(struct work_struct *work) { struct storvsc_scan_work *wrk; uint lun; struct scsi_device *sdev; wrk = container_of(work, struct storvsc_scan_work, work); lun = wrk->lun; sdev = scsi_device_lookup(wrk->host, 0, 0, lun); if (!sdev) goto done; scsi_rescan_device(&sdev->sdev_gendev); scsi_device_put(sdev); done: kfree(wrk); } static void storvsc_bus_scan(struct work_struct *work) { struct storvsc_scan_work *wrk; int id, order_id; wrk = container_of(work, struct storvsc_scan_work, work); for (id = 0; id < wrk->host->max_id; ++id) { if (wrk->host->reverse_ordering) order_id = wrk->host->max_id - id - 1; else order_id = id; scsi_scan_target(&wrk->host->shost_gendev, 0, order_id, SCAN_WILD_CARD, 1); } kfree(wrk); } static void storvsc_remove_lun(struct work_struct *work) { struct storvsc_scan_work *wrk; struct scsi_device *sdev; wrk = container_of(work, struct storvsc_scan_work, work); if (!scsi_host_get(wrk->host)) goto done; sdev = scsi_device_lookup(wrk->host, 0, 0, wrk->lun); if (sdev) { scsi_remove_device(sdev); scsi_device_put(sdev); } scsi_host_put(wrk->host); done: kfree(wrk); } /* * Major/minor macros. Minor version is in LSB, meaning that earlier flat * version numbers will be interpreted as "0.x" (i.e., 1 becomes 0.1). */ static inline u16 storvsc_get_version(u8 major, u8 minor) { u16 version; version = ((major << 8) | minor); return version; } /* * We can get incoming messages from the host that are not in response to * messages that we have sent out. An example of this would be messages * received by the guest to notify dynamic addition/removal of LUNs. To * deal with potential race conditions where the driver may be in the * midst of being unloaded when we might receive an unsolicited message * from the host, we have implemented a mechanism to gurantee sequential * consistency: * * 1) Once the device is marked as being destroyed, we will fail all * outgoing messages. * 2) We permit incoming messages when the device is being destroyed, * only to properly account for messages already sent out. */ static inline struct storvsc_device *get_out_stor_device( struct hv_device *device) { struct storvsc_device *stor_device; stor_device = hv_get_drvdata(device); if (stor_device && stor_device->destroy) stor_device = NULL; return stor_device; } static inline void storvsc_wait_to_drain(struct storvsc_device *dev) { dev->drain_notify = true; wait_event(dev->waiting_to_drain, atomic_read(&dev->num_outstanding_req) == 0); dev->drain_notify = false; } static inline struct storvsc_device *get_in_stor_device( struct hv_device *device) { struct storvsc_device *stor_device; stor_device = hv_get_drvdata(device); if (!stor_device) goto get_in_err; /* * If the device is being destroyed; allow incoming * traffic only to cleanup outstanding requests. */ if (stor_device->destroy && (atomic_read(&stor_device->num_outstanding_req) == 0)) stor_device = NULL; get_in_err: return stor_device; } static void destroy_bounce_buffer(struct scatterlist *sgl, unsigned int sg_count) { int i; struct page *page_buf; for (i = 0; i < sg_count; i++) { page_buf = sg_page((&sgl[i])); if (page_buf != NULL) __free_page(page_buf); } kfree(sgl); } static int do_bounce_buffer(struct scatterlist *sgl, unsigned int sg_count) { int i; /* No need to check */ if (sg_count < 2) return -1; /* We have at least 2 sg entries */ for (i = 0; i < sg_count; i++) { if (i == 0) { /* make sure 1st one does not have hole */ if (sgl[i].offset + sgl[i].length != PAGE_SIZE) return i; } else if (i == sg_count - 1) { /* make sure last one does not have hole */ if (sgl[i].offset != 0) return i; } else { /* make sure no hole in the middle */ if (sgl[i].length != PAGE_SIZE || sgl[i].offset != 0) return i; } } return -1; } static struct scatterlist *create_bounce_buffer(struct scatterlist *sgl, unsigned int sg_count, unsigned int len, int write) { int i; int num_pages; struct scatterlist *bounce_sgl; struct page *page_buf; unsigned int buf_len = ((write == WRITE_TYPE) ? 0 : PAGE_SIZE); num_pages = ALIGN(len, PAGE_SIZE) >> PAGE_SHIFT; bounce_sgl = kcalloc(num_pages, sizeof(struct scatterlist), GFP_ATOMIC); if (!bounce_sgl) return NULL; sg_init_table(bounce_sgl, num_pages); for (i = 0; i < num_pages; i++) { page_buf = alloc_page(GFP_ATOMIC); if (!page_buf) goto cleanup; sg_set_page(&bounce_sgl[i], page_buf, buf_len, 0); } return bounce_sgl; cleanup: destroy_bounce_buffer(bounce_sgl, num_pages); return NULL; } /* Disgusting wrapper functions */ static inline unsigned long sg_kmap_atomic(struct scatterlist *sgl, int idx) { void *addr = kmap_atomic(sg_page(sgl + idx)); return (unsigned long)addr; } static inline void sg_kunmap_atomic(unsigned long addr) { kunmap_atomic((void *)addr); } /* Assume the original sgl has enough room */ static unsigned int copy_from_bounce_buffer(struct scatterlist *orig_sgl, struct scatterlist *bounce_sgl, unsigned int orig_sgl_count, unsigned int bounce_sgl_count) { int i; int j = 0; unsigned long src, dest; unsigned int srclen, destlen, copylen; unsigned int total_copied = 0; unsigned long bounce_addr = 0; unsigned long dest_addr = 0; unsigned long flags; local_irq_save(flags); for (i = 0; i < orig_sgl_count; i++) { dest_addr = sg_kmap_atomic(orig_sgl,i) + orig_sgl[i].offset; dest = dest_addr; destlen = orig_sgl[i].length; if (bounce_addr == 0) bounce_addr = sg_kmap_atomic(bounce_sgl,j); while (destlen) { src = bounce_addr + bounce_sgl[j].offset; srclen = bounce_sgl[j].length - bounce_sgl[j].offset; copylen = min(srclen, destlen); memcpy((void *)dest, (void *)src, copylen); total_copied += copylen; bounce_sgl[j].offset += copylen; destlen -= copylen; dest += copylen; if (bounce_sgl[j].offset == bounce_sgl[j].length) { /* full */ sg_kunmap_atomic(bounce_addr); j++; /* * It is possible that the number of elements * in the bounce buffer may not be equal to * the number of elements in the original * scatter list. Handle this correctly. */ if (j == bounce_sgl_count) { /* * We are done; cleanup and return. */ sg_kunmap_atomic(dest_addr - orig_sgl[i].offset); local_irq_restore(flags); return total_copied; } /* if we need to use another bounce buffer */ if (destlen || i != orig_sgl_count - 1) bounce_addr = sg_kmap_atomic(bounce_sgl,j); } else if (destlen == 0 && i == orig_sgl_count - 1) { /* unmap the last bounce that is < PAGE_SIZE */ sg_kunmap_atomic(bounce_addr); } } sg_kunmap_atomic(dest_addr - orig_sgl[i].offset); } local_irq_restore(flags); return total_copied; } /* Assume the bounce_sgl has enough room ie using the create_bounce_buffer() */ static unsigned int copy_to_bounce_buffer(struct scatterlist *orig_sgl, struct scatterlist *bounce_sgl, unsigned int orig_sgl_count) { int i; int j = 0; unsigned long src, dest; unsigned int srclen, destlen, copylen; unsigned int total_copied = 0; unsigned long bounce_addr = 0; unsigned long src_addr = 0; unsigned long flags; local_irq_save(flags); for (i = 0; i < orig_sgl_count; i++) { src_addr = sg_kmap_atomic(orig_sgl,i) + orig_sgl[i].offset; src = src_addr; srclen = orig_sgl[i].length; if (bounce_addr == 0) bounce_addr = sg_kmap_atomic(bounce_sgl,j); while (srclen) { /* assume bounce offset always == 0 */ dest = bounce_addr + bounce_sgl[j].length; destlen = PAGE_SIZE - bounce_sgl[j].length; copylen = min(srclen, destlen); memcpy((void *)dest, (void *)src, copylen); total_copied += copylen; bounce_sgl[j].length += copylen; srclen -= copylen; src += copylen; if (bounce_sgl[j].length == PAGE_SIZE) { /* full..move to next entry */ sg_kunmap_atomic(bounce_addr); j++; /* if we need to use another bounce buffer */ if (srclen || i != orig_sgl_count - 1) bounce_addr = sg_kmap_atomic(bounce_sgl,j); } else if (srclen == 0 && i == orig_sgl_count - 1) { /* unmap the last bounce that is < PAGE_SIZE */ sg_kunmap_atomic(bounce_addr); } } sg_kunmap_atomic(src_addr - orig_sgl[i].offset); } local_irq_restore(flags); return total_copied; } static void handle_sc_creation(struct vmbus_channel *new_sc) { struct hv_device *device = new_sc->primary_channel->device_obj; struct storvsc_device *stor_device; struct vmstorage_channel_properties props; stor_device = get_out_stor_device(device); if (!stor_device) return; if (stor_device->open_sub_channel == false) return; memset(&props, 0, sizeof(struct vmstorage_channel_properties)); vmbus_open(new_sc, storvsc_ringbuffer_size, storvsc_ringbuffer_size, (void *)&props, sizeof(struct vmstorage_channel_properties), storvsc_on_channel_callback, new_sc); } static void handle_multichannel_storage(struct hv_device *device, int max_chns) { struct storvsc_device *stor_device; int num_cpus = num_online_cpus(); int num_sc; struct storvsc_cmd_request *request; struct vstor_packet *vstor_packet; int ret, t; num_sc = ((max_chns > num_cpus) ? num_cpus : max_chns); stor_device = get_out_stor_device(device); if (!stor_device) return; request = &stor_device->init_request; vstor_packet = &request->vstor_packet; stor_device->open_sub_channel = true; /* * Establish a handler for dealing with subchannels. */ vmbus_set_sc_create_callback(device->channel, handle_sc_creation); /* * Check to see if sub-channels have already been created. This * can happen when this driver is re-loaded after unloading. */ if (vmbus_are_subchannels_present(device->channel)) return; stor_device->open_sub_channel = false; /* * Request the host to create sub-channels. */ memset(request, 0, sizeof(struct storvsc_cmd_request)); init_completion(&request->wait_event); vstor_packet->operation = VSTOR_OPERATION_CREATE_SUB_CHANNELS; vstor_packet->flags = REQUEST_COMPLETION_FLAG; vstor_packet->sub_channel_count = num_sc; ret = vmbus_sendpacket(device->channel, vstor_packet, (sizeof(struct vstor_packet) - vmscsi_size_delta), (unsigned long)request, VM_PKT_DATA_INBAND, VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED); if (ret != 0) return; t = wait_for_completion_timeout(&request->wait_event, 10*HZ); if (t == 0) return; if (vstor_packet->operation != VSTOR_OPERATION_COMPLETE_IO || vstor_packet->status != 0) return; /* * Now that we created the sub-channels, invoke the check; this * may trigger the callback. */ stor_device->open_sub_channel = true; vmbus_are_subchannels_present(device->channel); } static int storvsc_channel_init(struct hv_device *device) { struct storvsc_device *stor_device; struct storvsc_cmd_request *request; struct vstor_packet *vstor_packet; int ret, t; int max_chns; bool process_sub_channels = false; stor_device = get_out_stor_device(device); if (!stor_device) return -ENODEV; request = &stor_device->init_request; vstor_packet = &request->vstor_packet; /* * Now, initiate the vsc/vsp initialization protocol on the open * channel */ memset(request, 0, sizeof(struct storvsc_cmd_request)); init_completion(&request->wait_event); vstor_packet->operation = VSTOR_OPERATION_BEGIN_INITIALIZATION; vstor_packet->flags = REQUEST_COMPLETION_FLAG; ret = vmbus_sendpacket(device->channel, vstor_packet, (sizeof(struct vstor_packet) - vmscsi_size_delta), (unsigned long)request, VM_PKT_DATA_INBAND, VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED); if (ret != 0) goto cleanup; t = wait_for_completion_timeout(&request->wait_event, 5*HZ); if (t == 0) { ret = -ETIMEDOUT; goto cleanup; } if (vstor_packet->operation != VSTOR_OPERATION_COMPLETE_IO || vstor_packet->status != 0) goto cleanup; /* reuse the packet for version range supported */ memset(vstor_packet, 0, sizeof(struct vstor_packet)); vstor_packet->operation = VSTOR_OPERATION_QUERY_PROTOCOL_VERSION; vstor_packet->flags = REQUEST_COMPLETION_FLAG; vstor_packet->version.major_minor = storvsc_get_version(vmstor_current_major, vmstor_current_minor); /* * The revision number is only used in Windows; set it to 0. */ vstor_packet->version.revision = 0; ret = vmbus_sendpacket(device->channel, vstor_packet, (sizeof(struct vstor_packet) - vmscsi_size_delta), (unsigned long)request, VM_PKT_DATA_INBAND, VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED); if (ret != 0) goto cleanup; t = wait_for_completion_timeout(&request->wait_event, 5*HZ); if (t == 0) { ret = -ETIMEDOUT; goto cleanup; } if (vstor_packet->operation != VSTOR_OPERATION_COMPLETE_IO || vstor_packet->status != 0) goto cleanup; memset(vstor_packet, 0, sizeof(struct vstor_packet)); vstor_packet->operation = VSTOR_OPERATION_QUERY_PROPERTIES; vstor_packet->flags = REQUEST_COMPLETION_FLAG; ret = vmbus_sendpacket(device->channel, vstor_packet, (sizeof(struct vstor_packet) - vmscsi_size_delta), (unsigned long)request, VM_PKT_DATA_INBAND, VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED); if (ret != 0) goto cleanup; t = wait_for_completion_timeout(&request->wait_event, 5*HZ); if (t == 0) { ret = -ETIMEDOUT; goto cleanup; } if (vstor_packet->operation != VSTOR_OPERATION_COMPLETE_IO || vstor_packet->status != 0) goto cleanup; /* * Check to see if multi-channel support is there. * Hosts that implement protocol version of 5.1 and above * support multi-channel. */ max_chns = vstor_packet->storage_channel_properties.max_channel_cnt; if ((vmbus_proto_version != VERSION_WIN7) && (vmbus_proto_version != VERSION_WS2008)) { if (vstor_packet->storage_channel_properties.flags & STORAGE_CHANNEL_SUPPORTS_MULTI_CHANNEL) process_sub_channels = true; } memset(vstor_packet, 0, sizeof(struct vstor_packet)); vstor_packet->operation = VSTOR_OPERATION_END_INITIALIZATION; vstor_packet->flags = REQUEST_COMPLETION_FLAG; ret = vmbus_sendpacket(device->channel, vstor_packet, (sizeof(struct vstor_packet) - vmscsi_size_delta), (unsigned long)request, VM_PKT_DATA_INBAND, VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED); if (ret != 0) goto cleanup; t = wait_for_completion_timeout(&request->wait_event, 5*HZ); if (t == 0) { ret = -ETIMEDOUT; goto cleanup; } if (vstor_packet->operation != VSTOR_OPERATION_COMPLETE_IO || vstor_packet->status != 0) goto cleanup; if (process_sub_channels) handle_multichannel_storage(device, max_chns); cleanup: return ret; } static void storvsc_handle_error(struct vmscsi_request *vm_srb, struct scsi_cmnd *scmnd, struct Scsi_Host *host, u8 asc, u8 ascq) { struct storvsc_scan_work *wrk; void (*process_err_fn)(struct work_struct *work); bool do_work = false; switch (vm_srb->srb_status) { case SRB_STATUS_ERROR: /* * If there is an error; offline the device since all * error recovery strategies would have already been * deployed on the host side. However, if the command * were a pass-through command deal with it appropriately. */ switch (scmnd->cmnd[0]) { case ATA_16: case ATA_12: set_host_byte(scmnd, DID_PASSTHROUGH); break; /* * On Some Windows hosts TEST_UNIT_READY command can return * SRB_STATUS_ERROR, let the upper level code deal with it * based on the sense information. */ case TEST_UNIT_READY: break; default: set_host_byte(scmnd, DID_TARGET_FAILURE); } break; case SRB_STATUS_INVALID_LUN: do_work = true; process_err_fn = storvsc_remove_lun; break; case (SRB_STATUS_ABORTED | SRB_STATUS_AUTOSENSE_VALID): if ((asc == 0x2a) && (ascq == 0x9)) { do_work = true; process_err_fn = storvsc_device_scan; /* * Retry the I/O that trigerred this. */ set_host_byte(scmnd, DID_REQUEUE); } break; } if (!do_work) return; /* * We need to schedule work to process this error; schedule it. */ wrk = kmalloc(sizeof(struct storvsc_scan_work), GFP_ATOMIC); if (!wrk) { set_host_byte(scmnd, DID_TARGET_FAILURE); return; } wrk->host = host; wrk->lun = vm_srb->lun; INIT_WORK(&wrk->work, process_err_fn); schedule_work(&wrk->work); } static void storvsc_command_completion(struct storvsc_cmd_request *cmd_request) { struct scsi_cmnd *scmnd = cmd_request->cmd; struct hv_host_device *host_dev = shost_priv(scmnd->device->host); void (*scsi_done_fn)(struct scsi_cmnd *); struct scsi_sense_hdr sense_hdr; struct vmscsi_request *vm_srb; struct stor_mem_pools *memp = scmnd->device->hostdata; struct Scsi_Host *host; struct storvsc_device *stor_dev; struct hv_device *dev = host_dev->dev; stor_dev = get_in_stor_device(dev); host = stor_dev->host; vm_srb = &cmd_request->vstor_packet.vm_srb; if (cmd_request->bounce_sgl_count) { if (vm_srb->data_in == READ_TYPE) copy_from_bounce_buffer(scsi_sglist(scmnd), cmd_request->bounce_sgl, scsi_sg_count(scmnd), cmd_request->bounce_sgl_count); destroy_bounce_buffer(cmd_request->bounce_sgl, cmd_request->bounce_sgl_count); } scmnd->result = vm_srb->scsi_status; if (scmnd->result) { if (scsi_normalize_sense(scmnd->sense_buffer, SCSI_SENSE_BUFFERSIZE, &sense_hdr)) scsi_print_sense_hdr("storvsc", &sense_hdr); } if (vm_srb->srb_status != SRB_STATUS_SUCCESS) storvsc_handle_error(vm_srb, scmnd, host, sense_hdr.asc, sense_hdr.ascq); scsi_set_resid(scmnd, cmd_request->data_buffer.len - vm_srb->data_transfer_length); scsi_done_fn = scmnd->scsi_done; scmnd->host_scribble = NULL; scmnd->scsi_done = NULL; scsi_done_fn(scmnd); mempool_free(cmd_request, memp->request_mempool); } static void storvsc_on_io_completion(struct hv_device *device, struct vstor_packet *vstor_packet, struct storvsc_cmd_request *request) { struct storvsc_device *stor_device; struct vstor_packet *stor_pkt; stor_device = hv_get_drvdata(device); stor_pkt = &request->vstor_packet; /* * The current SCSI handling on the host side does * not correctly handle: * INQUIRY command with page code parameter set to 0x80 * MODE_SENSE command with cmd[2] == 0x1c * * Setup srb and scsi status so this won't be fatal. * We do this so we can distinguish truly fatal failues * (srb status == 0x4) and off-line the device in that case. */ if ((stor_pkt->vm_srb.cdb[0] == INQUIRY) || (stor_pkt->vm_srb.cdb[0] == MODE_SENSE)) { vstor_packet->vm_srb.scsi_status = 0; vstor_packet->vm_srb.srb_status = SRB_STATUS_SUCCESS; } /* Copy over the status...etc */ stor_pkt->vm_srb.scsi_status = vstor_packet->vm_srb.scsi_status; stor_pkt->vm_srb.srb_status = vstor_packet->vm_srb.srb_status; stor_pkt->vm_srb.sense_info_length = vstor_packet->vm_srb.sense_info_length; if (vstor_packet->vm_srb.scsi_status != 0 || vstor_packet->vm_srb.srb_status != SRB_STATUS_SUCCESS){ dev_warn(&device->device, "cmd 0x%x scsi status 0x%x srb status 0x%x\n", stor_pkt->vm_srb.cdb[0], vstor_packet->vm_srb.scsi_status, vstor_packet->vm_srb.srb_status); } if ((vstor_packet->vm_srb.scsi_status & 0xFF) == 0x02) { /* CHECK_CONDITION */ if (vstor_packet->vm_srb.srb_status & SRB_STATUS_AUTOSENSE_VALID) { /* autosense data available */ dev_warn(&device->device, "stor pkt %p autosense data valid - len %d\n", request, vstor_packet->vm_srb.sense_info_length); memcpy(request->sense_buffer, vstor_packet->vm_srb.sense_data, vstor_packet->vm_srb.sense_info_length); } } stor_pkt->vm_srb.data_transfer_length = vstor_packet->vm_srb.data_transfer_length; storvsc_command_completion(request); if (atomic_dec_and_test(&stor_device->num_outstanding_req) && stor_device->drain_notify) wake_up(&stor_device->waiting_to_drain); } static void storvsc_on_receive(struct hv_device *device, struct vstor_packet *vstor_packet, struct storvsc_cmd_request *request) { struct storvsc_scan_work *work; struct storvsc_device *stor_device; switch (vstor_packet->operation) { case VSTOR_OPERATION_COMPLETE_IO: storvsc_on_io_completion(device, vstor_packet, request); break; case VSTOR_OPERATION_REMOVE_DEVICE: case VSTOR_OPERATION_ENUMERATE_BUS: stor_device = get_in_stor_device(device); work = kmalloc(sizeof(struct storvsc_scan_work), GFP_ATOMIC); if (!work) return; INIT_WORK(&work->work, storvsc_bus_scan); work->host = stor_device->host; schedule_work(&work->work); break; default: break; } } static void storvsc_on_channel_callback(void *context) { struct vmbus_channel *channel = (struct vmbus_channel *)context; struct hv_device *device; struct storvsc_device *stor_device; u32 bytes_recvd; u64 request_id; unsigned char packet[ALIGN(sizeof(struct vstor_packet), 8)]; struct storvsc_cmd_request *request; int ret; if (channel->primary_channel != NULL) device = channel->primary_channel->device_obj; else device = channel->device_obj; stor_device = get_in_stor_device(device); if (!stor_device) return; do { ret = vmbus_recvpacket(channel, packet, ALIGN((sizeof(struct vstor_packet) - vmscsi_size_delta), 8), &bytes_recvd, &request_id); if (ret == 0 && bytes_recvd > 0) { request = (struct storvsc_cmd_request *) (unsigned long)request_id; if ((request == &stor_device->init_request) || (request == &stor_device->reset_request)) { memcpy(&request->vstor_packet, packet, (sizeof(struct vstor_packet) - vmscsi_size_delta)); complete(&request->wait_event); } else { storvsc_on_receive(device, (struct vstor_packet *)packet, request); } } else { break; } } while (1); return; } static int storvsc_connect_to_vsp(struct hv_device *device, u32 ring_size) { struct vmstorage_channel_properties props; int ret; memset(&props, 0, sizeof(struct vmstorage_channel_properties)); ret = vmbus_open(device->channel, ring_size, ring_size, (void *)&props, sizeof(struct vmstorage_channel_properties), storvsc_on_channel_callback, device->channel); if (ret != 0) return ret; ret = storvsc_channel_init(device); return ret; } static int storvsc_dev_remove(struct hv_device *device) { struct storvsc_device *stor_device; unsigned long flags; stor_device = hv_get_drvdata(device); spin_lock_irqsave(&device->channel->inbound_lock, flags); stor_device->destroy = true; spin_unlock_irqrestore(&device->channel->inbound_lock, flags); /* * At this point, all outbound traffic should be disable. We * only allow inbound traffic (responses) to proceed so that * outstanding requests can be completed. */ storvsc_wait_to_drain(stor_device); /* * Since we have already drained, we don't need to busy wait * as was done in final_release_stor_device() * Note that we cannot set the ext pointer to NULL until * we have drained - to drain the outgoing packets, we need to * allow incoming packets. */ spin_lock_irqsave(&device->channel->inbound_lock, flags); hv_set_drvdata(device, NULL); spin_unlock_irqrestore(&device->channel->inbound_lock, flags); /* Close the channel */ vmbus_close(device->channel); kfree(stor_device); return 0; } static int storvsc_do_io(struct hv_device *device, struct storvsc_cmd_request *request) { struct storvsc_device *stor_device; struct vstor_packet *vstor_packet; struct vmbus_channel *outgoing_channel; int ret = 0; vstor_packet = &request->vstor_packet; stor_device = get_out_stor_device(device); if (!stor_device) return -ENODEV; request->device = device; /* * Select an an appropriate channel to send the request out. */ outgoing_channel = vmbus_get_outgoing_channel(device->channel); vstor_packet->flags |= REQUEST_COMPLETION_FLAG; vstor_packet->vm_srb.length = (sizeof(struct vmscsi_request) - vmscsi_size_delta); vstor_packet->vm_srb.sense_info_length = sense_buffer_size; vstor_packet->vm_srb.data_transfer_length = request->data_buffer.len; vstor_packet->operation = VSTOR_OPERATION_EXECUTE_SRB; if (request->data_buffer.len) { ret = vmbus_sendpacket_multipagebuffer(outgoing_channel, &request->data_buffer, vstor_packet, (sizeof(struct vstor_packet) - vmscsi_size_delta), (unsigned long)request); } else { ret = vmbus_sendpacket(device->channel, vstor_packet, (sizeof(struct vstor_packet) - vmscsi_size_delta), (unsigned long)request, VM_PKT_DATA_INBAND, VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED); } if (ret != 0) return ret; atomic_inc(&stor_device->num_outstanding_req); return ret; } static int storvsc_device_alloc(struct scsi_device *sdevice) { struct stor_mem_pools *memp; int number = STORVSC_MIN_BUF_NR; memp = kzalloc(sizeof(struct stor_mem_pools), GFP_KERNEL); if (!memp) return -ENOMEM; memp->request_pool = kmem_cache_create(dev_name(&sdevice->sdev_dev), sizeof(struct storvsc_cmd_request), 0, SLAB_HWCACHE_ALIGN, NULL); if (!memp->request_pool) goto err0; memp->request_mempool = mempool_create(number, mempool_alloc_slab, mempool_free_slab, memp->request_pool); if (!memp->request_mempool) goto err1; sdevice->hostdata = memp; return 0; err1: kmem_cache_destroy(memp->request_pool); err0: kfree(memp); return -ENOMEM; } static void storvsc_device_destroy(struct scsi_device *sdevice) { struct stor_mem_pools *memp = sdevice->hostdata; if (!memp) return; mempool_destroy(memp->request_mempool); kmem_cache_destroy(memp->request_pool); kfree(memp); sdevice->hostdata = NULL; } static int storvsc_device_configure(struct scsi_device *sdevice) { scsi_adjust_queue_depth(sdevice, MSG_SIMPLE_TAG, STORVSC_MAX_IO_REQUESTS); blk_queue_max_segment_size(sdevice->request_queue, PAGE_SIZE); blk_queue_bounce_limit(sdevice->request_queue, BLK_BOUNCE_ANY); blk_queue_rq_timeout(sdevice->request_queue, (storvsc_timeout * HZ)); sdevice->no_write_same = 1; /* * Add blist flags to permit the reading of the VPD pages even when * the target may claim SPC-2 compliance. MSFT targets currently * claim SPC-2 compliance while they implement post SPC-2 features. * With this patch we can correctly handle WRITE_SAME_16 issues. */ sdevice->sdev_bflags |= msft_blist_flags; return 0; } static int storvsc_get_chs(struct scsi_device *sdev, struct block_device * bdev, sector_t capacity, int *info) { sector_t nsect = capacity; sector_t cylinders = nsect; int heads, sectors_pt; /* * We are making up these values; let us keep it simple. */ heads = 0xff; sectors_pt = 0x3f; /* Sectors per track */ sector_div(cylinders, heads * sectors_pt); if ((sector_t)(cylinders + 1) * heads * sectors_pt < nsect) cylinders = 0xffff; info[0] = heads; info[1] = sectors_pt; info[2] = (int)cylinders; return 0; } static int storvsc_host_reset_handler(struct scsi_cmnd *scmnd) { struct hv_host_device *host_dev = shost_priv(scmnd->device->host); struct hv_device *device = host_dev->dev; struct storvsc_device *stor_device; struct storvsc_cmd_request *request; struct vstor_packet *vstor_packet; int ret, t; stor_device = get_out_stor_device(device); if (!stor_device) return FAILED; request = &stor_device->reset_request; vstor_packet = &request->vstor_packet; init_completion(&request->wait_event); vstor_packet->operation = VSTOR_OPERATION_RESET_BUS; vstor_packet->flags = REQUEST_COMPLETION_FLAG; vstor_packet->vm_srb.path_id = stor_device->path_id; ret = vmbus_sendpacket(device->channel, vstor_packet, (sizeof(struct vstor_packet) - vmscsi_size_delta), (unsigned long)&stor_device->reset_request, VM_PKT_DATA_INBAND, VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED); if (ret != 0) return FAILED; t = wait_for_completion_timeout(&request->wait_event, 5*HZ); if (t == 0) return TIMEOUT_ERROR; /* * At this point, all outstanding requests in the adapter * should have been flushed out and return to us * There is a potential race here where the host may be in * the process of responding when we return from here. * Just wait for all in-transit packets to be accounted for * before we return from here. */ storvsc_wait_to_drain(stor_device); return SUCCESS; } /* * The host guarantees to respond to each command, although I/O latencies might * be unbounded on Azure. Reset the timer unconditionally to give the host a * chance to perform EH. */ static enum blk_eh_timer_return storvsc_eh_timed_out(struct scsi_cmnd *scmnd) { return BLK_EH_RESET_TIMER; } static bool storvsc_scsi_cmd_ok(struct scsi_cmnd *scmnd) { bool allowed = true; u8 scsi_op = scmnd->cmnd[0]; switch (scsi_op) { /* the host does not handle WRITE_SAME, log accident usage */ case WRITE_SAME: /* * smartd sends this command and the host does not handle * this. So, don't send it. */ case SET_WINDOW: scmnd->result = ILLEGAL_REQUEST << 16; allowed = false; break; default: break; } return allowed; } static int storvsc_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *scmnd) { int ret; struct hv_host_device *host_dev = shost_priv(host); struct hv_device *dev = host_dev->dev; struct storvsc_cmd_request *cmd_request; unsigned int request_size = 0; int i; struct scatterlist *sgl; unsigned int sg_count = 0; struct vmscsi_request *vm_srb; struct stor_mem_pools *memp = scmnd->device->hostdata; if (vmstor_current_major <= VMSTOR_WIN8_MAJOR) { /* * On legacy hosts filter unimplemented commands. * Future hosts are expected to correctly handle * unsupported commands. Furthermore, it is * possible that some of the currently * unsupported commands maybe supported in * future versions of the host. */ if (!storvsc_scsi_cmd_ok(scmnd)) { scmnd->scsi_done(scmnd); return 0; } } request_size = sizeof(struct storvsc_cmd_request); cmd_request = mempool_alloc(memp->request_mempool, GFP_ATOMIC); /* * We might be invoked in an interrupt context; hence * mempool_alloc() can fail. */ if (!cmd_request) return SCSI_MLQUEUE_DEVICE_BUSY; memset(cmd_request, 0, sizeof(struct storvsc_cmd_request)); /* Setup the cmd request */ cmd_request->cmd = scmnd; scmnd->host_scribble = (unsigned char *)cmd_request; vm_srb = &cmd_request->vstor_packet.vm_srb; vm_srb->win8_extension.time_out_value = 60; vm_srb->win8_extension.srb_flags |= (SRB_FLAGS_QUEUE_ACTION_ENABLE | SRB_FLAGS_DISABLE_SYNCH_TRANSFER); /* Build the SRB */ switch (scmnd->sc_data_direction) { case DMA_TO_DEVICE: vm_srb->data_in = WRITE_TYPE; vm_srb->win8_extension.srb_flags |= SRB_FLAGS_DATA_OUT; break; case DMA_FROM_DEVICE: vm_srb->data_in = READ_TYPE; vm_srb->win8_extension.srb_flags |= SRB_FLAGS_DATA_IN; break; default: vm_srb->data_in = UNKNOWN_TYPE; vm_srb->win8_extension.srb_flags |= (SRB_FLAGS_DATA_IN | SRB_FLAGS_DATA_OUT); break; } vm_srb->port_number = host_dev->port; vm_srb->path_id = scmnd->device->channel; vm_srb->target_id = scmnd->device->id; vm_srb->lun = scmnd->device->lun; vm_srb->cdb_length = scmnd->cmd_len; memcpy(vm_srb->cdb, scmnd->cmnd, vm_srb->cdb_length); cmd_request->sense_buffer = scmnd->sense_buffer; cmd_request->data_buffer.len = scsi_bufflen(scmnd); if (scsi_sg_count(scmnd)) { sgl = (struct scatterlist *)scsi_sglist(scmnd); sg_count = scsi_sg_count(scmnd); /* check if we need to bounce the sgl */ if (do_bounce_buffer(sgl, scsi_sg_count(scmnd)) != -1) { cmd_request->bounce_sgl = create_bounce_buffer(sgl, scsi_sg_count(scmnd), scsi_bufflen(scmnd), vm_srb->data_in); if (!cmd_request->bounce_sgl) { ret = SCSI_MLQUEUE_HOST_BUSY; goto queue_error; } cmd_request->bounce_sgl_count = ALIGN(scsi_bufflen(scmnd), PAGE_SIZE) >> PAGE_SHIFT; if (vm_srb->data_in == WRITE_TYPE) copy_to_bounce_buffer(sgl, cmd_request->bounce_sgl, scsi_sg_count(scmnd)); sgl = cmd_request->bounce_sgl; sg_count = cmd_request->bounce_sgl_count; } cmd_request->data_buffer.offset = sgl[0].offset; for (i = 0; i < sg_count; i++) cmd_request->data_buffer.pfn_array[i] = page_to_pfn(sg_page((&sgl[i]))); } else if (scsi_sglist(scmnd)) { cmd_request->data_buffer.offset = virt_to_phys(scsi_sglist(scmnd)) & (PAGE_SIZE-1); cmd_request->data_buffer.pfn_array[0] = virt_to_phys(scsi_sglist(scmnd)) >> PAGE_SHIFT; } /* Invokes the vsc to start an IO */ ret = storvsc_do_io(dev, cmd_request); if (ret == -EAGAIN) { /* no more space */ if (cmd_request->bounce_sgl_count) { destroy_bounce_buffer(cmd_request->bounce_sgl, cmd_request->bounce_sgl_count); ret = SCSI_MLQUEUE_DEVICE_BUSY; goto queue_error; } } return 0; queue_error: mempool_free(cmd_request, memp->request_mempool); scmnd->host_scribble = NULL; return ret; } static struct scsi_host_template scsi_driver = { .module = THIS_MODULE, .name = "storvsc_host_t", .bios_param = storvsc_get_chs, .queuecommand = storvsc_queuecommand, .eh_host_reset_handler = storvsc_host_reset_handler, .eh_timed_out = storvsc_eh_timed_out, .slave_alloc = storvsc_device_alloc, .slave_destroy = storvsc_device_destroy, .slave_configure = storvsc_device_configure, .cmd_per_lun = 255, .can_queue = STORVSC_MAX_IO_REQUESTS*STORVSC_MAX_TARGETS, .this_id = -1, /* no use setting to 0 since ll_blk_rw reset it to 1 */ /* currently 32 */ .sg_tablesize = MAX_MULTIPAGE_BUFFER_COUNT, .use_clustering = DISABLE_CLUSTERING, /* Make sure we dont get a sg segment crosses a page boundary */ .dma_boundary = PAGE_SIZE-1, .no_write_same = 1, }; enum { SCSI_GUID, IDE_GUID, SFC_GUID, }; static const struct hv_vmbus_device_id id_table[] = { /* SCSI guid */ { HV_SCSI_GUID, .driver_data = SCSI_GUID }, /* IDE guid */ { HV_IDE_GUID, .driver_data = IDE_GUID }, /* Fibre Channel GUID */ { HV_SYNTHFC_GUID, .driver_data = SFC_GUID }, { }, }; MODULE_DEVICE_TABLE(vmbus, id_table); static int storvsc_probe(struct hv_device *device, const struct hv_vmbus_device_id *dev_id) { int ret; struct Scsi_Host *host; struct hv_host_device *host_dev; bool dev_is_ide = ((dev_id->driver_data == IDE_GUID) ? true : false); int target = 0; struct storvsc_device *stor_device; /* * Based on the windows host we are running on, * set state to properly communicate with the host. */ switch (vmbus_proto_version) { case VERSION_WS2008: case VERSION_WIN7: sense_buffer_size = PRE_WIN8_STORVSC_SENSE_BUFFER_SIZE; vmscsi_size_delta = sizeof(struct vmscsi_win8_extension); vmstor_current_major = VMSTOR_WIN7_MAJOR; vmstor_current_minor = VMSTOR_WIN7_MINOR; break; default: sense_buffer_size = POST_WIN7_STORVSC_SENSE_BUFFER_SIZE; vmscsi_size_delta = 0; vmstor_current_major = VMSTOR_WIN8_MAJOR; vmstor_current_minor = VMSTOR_WIN8_MINOR; break; } if (dev_id->driver_data == SFC_GUID) scsi_driver.can_queue = (STORVSC_MAX_IO_REQUESTS * STORVSC_FC_MAX_TARGETS); host = scsi_host_alloc(&scsi_driver, sizeof(struct hv_host_device)); if (!host) return -ENOMEM; host_dev = shost_priv(host); memset(host_dev, 0, sizeof(struct hv_host_device)); host_dev->port = host->host_no; host_dev->dev = device; stor_device = kzalloc(sizeof(struct storvsc_device), GFP_KERNEL); if (!stor_device) { ret = -ENOMEM; goto err_out0; } stor_device->destroy = false; stor_device->open_sub_channel = false; init_waitqueue_head(&stor_device->waiting_to_drain); stor_device->device = device; stor_device->host = host; hv_set_drvdata(device, stor_device); stor_device->port_number = host->host_no; ret = storvsc_connect_to_vsp(device, storvsc_ringbuffer_size); if (ret) goto err_out1; host_dev->path = stor_device->path_id; host_dev->target = stor_device->target_id; switch (dev_id->driver_data) { case SFC_GUID: host->max_lun = STORVSC_FC_MAX_LUNS_PER_TARGET; host->max_id = STORVSC_FC_MAX_TARGETS; host->max_channel = STORVSC_FC_MAX_CHANNELS - 1; break; case SCSI_GUID: host->max_lun = STORVSC_MAX_LUNS_PER_TARGET; host->max_id = STORVSC_MAX_TARGETS; host->max_channel = STORVSC_MAX_CHANNELS - 1; break; default: host->max_lun = STORVSC_IDE_MAX_LUNS_PER_TARGET; host->max_id = STORVSC_IDE_MAX_TARGETS; host->max_channel = STORVSC_IDE_MAX_CHANNELS - 1; break; } /* max cmd length */ host->max_cmd_len = STORVSC_MAX_CMD_LEN; /* Register the HBA and start the scsi bus scan */ ret = scsi_add_host(host, &device->device); if (ret != 0) goto err_out2; if (!dev_is_ide) { scsi_scan_host(host); } else { target = (device->dev_instance.b[5] << 8 | device->dev_instance.b[4]); ret = scsi_add_device(host, 0, target, 0); if (ret) { scsi_remove_host(host); goto err_out2; } } return 0; err_out2: /* * Once we have connected with the host, we would need to * to invoke storvsc_dev_remove() to rollback this state and * this call also frees up the stor_device; hence the jump around * err_out1 label. */ storvsc_dev_remove(device); goto err_out0; err_out1: kfree(stor_device); err_out0: scsi_host_put(host); return ret; } static int storvsc_remove(struct hv_device *dev) { struct storvsc_device *stor_device = hv_get_drvdata(dev); struct Scsi_Host *host = stor_device->host; scsi_remove_host(host); storvsc_dev_remove(dev); scsi_host_put(host); return 0; } static struct hv_driver storvsc_drv = { .name = KBUILD_MODNAME, .id_table = id_table, .probe = storvsc_probe, .remove = storvsc_remove, }; static int __init storvsc_drv_init(void) { u32 max_outstanding_req_per_channel; /* * Divide the ring buffer data size (which is 1 page less * than the ring buffer size since that page is reserved for * the ring buffer indices) by the max request size (which is * vmbus_channel_packet_multipage_buffer + struct vstor_packet + u64) */ max_outstanding_req_per_channel = ((storvsc_ringbuffer_size - PAGE_SIZE) / ALIGN(MAX_MULTIPAGE_BUFFER_PACKET + sizeof(struct vstor_packet) + sizeof(u64) - vmscsi_size_delta, sizeof(u64))); if (max_outstanding_req_per_channel < STORVSC_MAX_IO_REQUESTS) return -EINVAL; return vmbus_driver_register(&storvsc_drv); } static void __exit storvsc_drv_exit(void) { vmbus_driver_unregister(&storvsc_drv); } MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("Microsoft Hyper-V virtual storage driver"); module_init(storvsc_drv_init); module_exit(storvsc_drv_exit);