summaryrefslogtreecommitdiffstats
path: root/drivers/block/xen-blkback/common.h
blob: c929ae22764c9dd4345195a1542df997c5a8e29b (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
/*
 * 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.
 */

#ifndef __XEN_BLKIF__BACKEND__COMMON_H__
#define __XEN_BLKIF__BACKEND__COMMON_H__

#include <linux/module.h>
#include <linux/interrupt.h>
#include <linux/slab.h>
#include <linux/blkdev.h>
#include <linux/vmalloc.h>
#include <linux/wait.h>
#include <linux/io.h>
#include <linux/rbtree.h>
#include <asm/setup.h>
#include <asm/pgalloc.h>
#include <asm/hypervisor.h>
#include <xen/grant_table.h>
#include <xen/page.h>
#include <xen/xenbus.h>
#include <xen/interface/io/ring.h>
#include <xen/interface/io/blkif.h>
#include <xen/interface/io/protocols.h>

extern unsigned int xen_blkif_max_ring_order;
/*
 * This is the maximum number of segments that would be allowed in indirect
 * requests. This value will also be passed to the frontend.
 */
#define MAX_INDIRECT_SEGMENTS 256

/*
 * Xen use 4K pages. The guest may use different page size (4K or 64K)
 * Number of Xen pages per segment
 */
#define XEN_PAGES_PER_SEGMENT   (PAGE_SIZE / XEN_PAGE_SIZE)

#define XEN_PAGES_PER_INDIRECT_FRAME \
	(XEN_PAGE_SIZE/sizeof(struct blkif_request_segment))
#define SEGS_PER_INDIRECT_FRAME	\
	(XEN_PAGES_PER_INDIRECT_FRAME / XEN_PAGES_PER_SEGMENT)

#define MAX_INDIRECT_PAGES \
	((MAX_INDIRECT_SEGMENTS + SEGS_PER_INDIRECT_FRAME - 1)/SEGS_PER_INDIRECT_FRAME)
#define INDIRECT_PAGES(_segs) DIV_ROUND_UP(_segs, XEN_PAGES_PER_INDIRECT_FRAME)

/* Not a real protocol.  Used to generate ring structs which contain
 * the elements common to all protocols only.  This way we get a
 * compiler-checkable way to use common struct elements, so we can
 * avoid using switch(protocol) in a number of places.  */
struct blkif_common_request {
	char dummy;
};
struct blkif_common_response {
	char dummy;
};

struct blkif_x86_32_request_rw {
	uint8_t        nr_segments;  /* number of segments                   */
	blkif_vdev_t   handle;       /* only for read/write requests         */
	uint64_t       id;           /* private guest value, echoed in resp  */
	blkif_sector_t sector_number;/* start sector idx on disk (r/w only)  */
	struct blkif_request_segment seg[BLKIF_MAX_SEGMENTS_PER_REQUEST];
} __attribute__((__packed__));

struct blkif_x86_32_request_discard {
	uint8_t        flag;         /* BLKIF_DISCARD_SECURE or zero         */
	blkif_vdev_t   _pad1;        /* was "handle" for read/write requests */
	uint64_t       id;           /* private guest value, echoed in resp  */
	blkif_sector_t sector_number;/* start sector idx on disk (r/w only)  */
	uint64_t       nr_sectors;
} __attribute__((__packed__));

struct blkif_x86_32_request_other {
	uint8_t        _pad1;
	blkif_vdev_t   _pad2;
	uint64_t       id;           /* private guest value, echoed in resp  */
} __attribute__((__packed__));

struct blkif_x86_32_request_indirect {
	uint8_t        indirect_op;
	uint16_t       nr_segments;
	uint64_t       id;
	blkif_sector_t sector_number;
	blkif_vdev_t   handle;
	uint16_t       _pad1;
	grant_ref_t    indirect_grefs[BLKIF_MAX_INDIRECT_PAGES_PER_REQUEST];
	/*
	 * The maximum number of indirect segments (and pages) that will
	 * be used is determined by MAX_INDIRECT_SEGMENTS, this value
	 * is also exported to the guest (via xenstore
	 * feature-max-indirect-segments entry), so the frontend knows how
	 * many indirect segments the backend supports.
	 */
	uint64_t       _pad2;        /* make it 64 byte aligned */
} __attribute__((__packed__));

struct blkif_x86_32_request {
	uint8_t        operation;    /* BLKIF_OP_???                         */
	union {
		struct blkif_x86_32_request_rw rw;
		struct blkif_x86_32_request_discard discard;
		struct blkif_x86_32_request_other other;
		struct blkif_x86_32_request_indirect indirect;
	} u;
} __attribute__((__packed__));

/* i386 protocol version */
#pragma pack(push, 4)
struct blkif_x86_32_response {
	uint64_t        id;              /* copied from request */
	uint8_t         operation;       /* copied from request */
	int16_t         status;          /* BLKIF_RSP_???       */
};
#pragma pack(pop)
/* x86_64 protocol version */

struct blkif_x86_64_request_rw {
	uint8_t        nr_segments;  /* number of segments                   */
	blkif_vdev_t   handle;       /* only for read/write requests         */
	uint32_t       _pad1;        /* offsetof(blkif_reqest..,u.rw.id)==8  */
	uint64_t       id;
	blkif_sector_t sector_number;/* start sector idx on disk (r/w only)  */
	struct blkif_request_segment seg[BLKIF_MAX_SEGMENTS_PER_REQUEST];
} __attribute__((__packed__));

struct blkif_x86_64_request_discard {
	uint8_t        flag;         /* BLKIF_DISCARD_SECURE or zero         */
	blkif_vdev_t   _pad1;        /* was "handle" for read/write requests */
        uint32_t       _pad2;        /* offsetof(blkif_..,u.discard.id)==8   */
	uint64_t       id;
	blkif_sector_t sector_number;/* start sector idx on disk (r/w only)  */
	uint64_t       nr_sectors;
} __attribute__((__packed__));

struct blkif_x86_64_request_other {
	uint8_t        _pad1;
	blkif_vdev_t   _pad2;
	uint32_t       _pad3;        /* offsetof(blkif_..,u.discard.id)==8   */
	uint64_t       id;           /* private guest value, echoed in resp  */
} __attribute__((__packed__));

struct blkif_x86_64_request_indirect {
	uint8_t        indirect_op;
	uint16_t       nr_segments;
	uint32_t       _pad1;        /* offsetof(blkif_..,u.indirect.id)==8   */
	uint64_t       id;
	blkif_sector_t sector_number;
	blkif_vdev_t   handle;
	uint16_t       _pad2;
	grant_ref_t    indirect_grefs[BLKIF_MAX_INDIRECT_PAGES_PER_REQUEST];
	/*
	 * The maximum number of indirect segments (and pages) that will
	 * be used is determined by MAX_INDIRECT_SEGMENTS, this value
	 * is also exported to the guest (via xenstore
	 * feature-max-indirect-segments entry), so the frontend knows how
	 * many indirect segments the backend supports.
	 */
	uint32_t       _pad3;        /* make it 64 byte aligned */
} __attribute__((__packed__));

struct blkif_x86_64_request {
	uint8_t        operation;    /* BLKIF_OP_???                         */
	union {
		struct blkif_x86_64_request_rw rw;
		struct blkif_x86_64_request_discard discard;
		struct blkif_x86_64_request_other other;
		struct blkif_x86_64_request_indirect indirect;
	} u;
} __attribute__((__packed__));

struct blkif_x86_64_response {
	uint64_t       __attribute__((__aligned__(8))) id;
	uint8_t         operation;       /* copied from request */
	int16_t         status;          /* BLKIF_RSP_???       */
};

DEFINE_RING_TYPES(blkif_common, struct blkif_common_request,
		  struct blkif_common_response);
DEFINE_RING_TYPES(blkif_x86_32, struct blkif_x86_32_request,
		  struct blkif_x86_32_response);
DEFINE_RING_TYPES(blkif_x86_64, struct blkif_x86_64_request,
		  struct blkif_x86_64_response);

union blkif_back_rings {
	struct blkif_back_ring        native;
	struct blkif_common_back_ring common;
	struct blkif_x86_32_back_ring x86_32;
	struct blkif_x86_64_back_ring x86_64;
};

enum blkif_protocol {
	BLKIF_PROTOCOL_NATIVE = 1,
	BLKIF_PROTOCOL_X86_32 = 2,
	BLKIF_PROTOCOL_X86_64 = 3,
};

/*
 * Default protocol if the frontend doesn't specify one.
 */
#ifdef CONFIG_X86
#  define BLKIF_PROTOCOL_DEFAULT BLKIF_PROTOCOL_X86_32
#else
#  define BLKIF_PROTOCOL_DEFAULT BLKIF_PROTOCOL_NATIVE
#endif

struct xen_vbd {
	/* What the domain refers to this vbd as. */
	blkif_vdev_t		handle;
	/* Non-zero -> read-only */
	unsigned char		readonly;
	/* VDISK_xxx */
	unsigned char		type;
	/* phys device that this vbd maps to. */
	u32			pdevice;
	struct block_device	*bdev;
	/* Cached size parameter. */
	sector_t		size;
	unsigned int		flush_support:1;
	unsigned int		discard_secure:1;
	unsigned int		feature_gnt_persistent:1;
	unsigned int		overflow_max_grants:1;
};

struct backend_info;

/* Number of available flags */
#define PERSISTENT_GNT_FLAGS_SIZE	2
/* This persistent grant is currently in use */
#define PERSISTENT_GNT_ACTIVE		0
/*
 * This persistent grant has been used, this flag is set when we remove the
 * PERSISTENT_GNT_ACTIVE, to know that this grant has been used recently.
 */
#define PERSISTENT_GNT_WAS_ACTIVE	1

/* Number of requests that we can fit in a ring */
#define XEN_BLKIF_REQS_PER_PAGE		32

struct persistent_gnt {
	struct page *page;
	grant_ref_t gnt;
	grant_handle_t handle;
	DECLARE_BITMAP(flags, PERSISTENT_GNT_FLAGS_SIZE);
	struct rb_node node;
	struct list_head remove_node;
};

struct xen_blkif {
	/* Unique identifier for this interface. */
	domid_t			domid;
	unsigned int		handle;
	/* Physical parameters of the comms window. */
	unsigned int		irq;
	/* Comms information. */
	enum blkif_protocol	blk_protocol;
	union blkif_back_rings	blk_rings;
	void			*blk_ring;
	/* The VBD attached to this interface. */
	struct xen_vbd		vbd;
	/* Back pointer to the backend_info. */
	struct backend_info	*be;
	/* Private fields. */
	spinlock_t		blk_ring_lock;
	atomic_t		refcnt;

	wait_queue_head_t	wq;
	/* for barrier (drain) requests */
	struct completion	drain_complete;
	atomic_t		drain;
	atomic_t		inflight;
	/* One thread per one blkif. */
	struct task_struct	*xenblkd;
	unsigned int		waiting_reqs;

	/* tree to store persistent grants */
	struct rb_root		persistent_gnts;
	unsigned int		persistent_gnt_c;
	atomic_t		persistent_gnt_in_use;
	unsigned long           next_lru;

	/* used by the kworker that offload work from the persistent purge */
	struct list_head	persistent_purge_list;
	struct work_struct	persistent_purge_work;

	/* buffer of free pages to map grant refs */
	spinlock_t		free_pages_lock;
	int			free_pages_num;
	struct list_head	free_pages;

	/* 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;

	/* statistics */
	unsigned long		st_print;
	unsigned long long			st_rd_req;
	unsigned long long			st_wr_req;
	unsigned long long			st_oo_req;
	unsigned long long			st_f_req;
	unsigned long long			st_ds_req;
	unsigned long long			st_rd_sect;
	unsigned long long			st_wr_sect;

	struct work_struct	free_work;
	/* Thread shutdown wait queue. */
	wait_queue_head_t	shutdown_wq;
	unsigned int nr_ring_pages;
};

struct seg_buf {
	unsigned long offset;
	unsigned int nsec;
};

struct grant_page {
	struct page 		*page;
	struct persistent_gnt	*persistent_gnt;
	grant_handle_t		handle;
	grant_ref_t		gref;
};

/*
 * 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_segs;
	atomic_t		pendcnt;
	unsigned short		operation;
	int			status;
	struct list_head	free_list;
	struct grant_page	*segments[MAX_INDIRECT_SEGMENTS];
	/* Indirect descriptors */
	struct grant_page	*indirect_pages[MAX_INDIRECT_PAGES];
	struct seg_buf		seg[MAX_INDIRECT_SEGMENTS];
	struct bio		*biolist[MAX_INDIRECT_SEGMENTS];
	struct gnttab_unmap_grant_ref unmap[MAX_INDIRECT_SEGMENTS];
	struct page                   *unmap_pages[MAX_INDIRECT_SEGMENTS];
	struct gntab_unmap_queue_data gnttab_unmap_data;
};


#define vbd_sz(_v)	((_v)->bdev->bd_part ? \
			 (_v)->bdev->bd_part->nr_sects : \
			  get_capacity((_v)->bdev->bd_disk))

#define xen_blkif_get(_b) (atomic_inc(&(_b)->refcnt))
#define xen_blkif_put(_b)				\
	do {						\
		if (atomic_dec_and_test(&(_b)->refcnt))	\
			schedule_work(&(_b)->free_work);\
	} while (0)

struct phys_req {
	unsigned short		dev;
	blkif_sector_t		nr_sects;
	struct block_device	*bdev;
	blkif_sector_t		sector_number;
};
int xen_blkif_interface_init(void);

int xen_blkif_xenbus_init(void);

irqreturn_t xen_blkif_be_int(int irq, void *dev_id);
int xen_blkif_schedule(void *arg);
int xen_blkif_purge_persistent(void *arg);
void xen_blkbk_free_caches(struct xen_blkif *blkif);

int xen_blkbk_flush_diskcache(struct xenbus_transaction xbt,
			      struct backend_info *be, int state);

int xen_blkbk_barrier(struct xenbus_transaction xbt,
		      struct backend_info *be, int state);
struct xenbus_device *xen_blkbk_xenbus(struct backend_info *be);
void xen_blkbk_unmap_purged_grants(struct work_struct *work);

static inline void blkif_get_x86_32_req(struct blkif_request *dst,
					struct blkif_x86_32_request *src)
{
	int i, n = BLKIF_MAX_SEGMENTS_PER_REQUEST, j;
	dst->operation = READ_ONCE(src->operation);
	switch (dst->operation) {
	case BLKIF_OP_READ:
	case BLKIF_OP_WRITE:
	case BLKIF_OP_WRITE_BARRIER:
	case BLKIF_OP_FLUSH_DISKCACHE:
		dst->u.rw.nr_segments = src->u.rw.nr_segments;
		dst->u.rw.handle = src->u.rw.handle;
		dst->u.rw.id = src->u.rw.id;
		dst->u.rw.sector_number = src->u.rw.sector_number;
		barrier();
		if (n > dst->u.rw.nr_segments)
			n = dst->u.rw.nr_segments;
		for (i = 0; i < n; i++)
			dst->u.rw.seg[i] = src->u.rw.seg[i];
		break;
	case BLKIF_OP_DISCARD:
		dst->u.discard.flag = src->u.discard.flag;
		dst->u.discard.id = src->u.discard.id;
		dst->u.discard.sector_number = src->u.discard.sector_number;
		dst->u.discard.nr_sectors = src->u.discard.nr_sectors;
		break;
	case BLKIF_OP_INDIRECT:
		dst->u.indirect.indirect_op = src->u.indirect.indirect_op;
		dst->u.indirect.nr_segments = src->u.indirect.nr_segments;
		dst->u.indirect.handle = src->u.indirect.handle;
		dst->u.indirect.id = src->u.indirect.id;
		dst->u.indirect.sector_number = src->u.indirect.sector_number;
		barrier();
		j = min(MAX_INDIRECT_PAGES, INDIRECT_PAGES(dst->u.indirect.nr_segments));
		for (i = 0; i < j; i++)
			dst->u.indirect.indirect_grefs[i] =
				src->u.indirect.indirect_grefs[i];
		break;
	default:
		/*
		 * Don't know how to translate this op. Only get the
		 * ID so failure can be reported to the frontend.
		 */
		dst->u.other.id = src->u.other.id;
		break;
	}
}

static inline void blkif_get_x86_64_req(struct blkif_request *dst,
					struct blkif_x86_64_request *src)
{
	int i, n = BLKIF_MAX_SEGMENTS_PER_REQUEST, j;
	dst->operation = READ_ONCE(src->operation);
	switch (dst->operation) {
	case BLKIF_OP_READ:
	case BLKIF_OP_WRITE:
	case BLKIF_OP_WRITE_BARRIER:
	case BLKIF_OP_FLUSH_DISKCACHE:
		dst->u.rw.nr_segments = src->u.rw.nr_segments;
		dst->u.rw.handle = src->u.rw.handle;
		dst->u.rw.id = src->u.rw.id;
		dst->u.rw.sector_number = src->u.rw.sector_number;
		barrier();
		if (n > dst->u.rw.nr_segments)
			n = dst->u.rw.nr_segments;
		for (i = 0; i < n; i++)
			dst->u.rw.seg[i] = src->u.rw.seg[i];
		break;
	case BLKIF_OP_DISCARD:
		dst->u.discard.flag = src->u.discard.flag;
		dst->u.discard.id = src->u.discard.id;
		dst->u.discard.sector_number = src->u.discard.sector_number;
		dst->u.discard.nr_sectors = src->u.discard.nr_sectors;
		break;
	case BLKIF_OP_INDIRECT:
		dst->u.indirect.indirect_op = src->u.indirect.indirect_op;
		dst->u.indirect.nr_segments = src->u.indirect.nr_segments;
		dst->u.indirect.handle = src->u.indirect.handle;
		dst->u.indirect.id = src->u.indirect.id;
		dst->u.indirect.sector_number = src->u.indirect.sector_number;
		barrier();
		j = min(MAX_INDIRECT_PAGES, INDIRECT_PAGES(dst->u.indirect.nr_segments));
		for (i = 0; i < j; i++)
			dst->u.indirect.indirect_grefs[i] =
				src->u.indirect.indirect_grefs[i];
		break;
	default:
		/*
		 * Don't know how to translate this op. Only get the
		 * ID so failure can be reported to the frontend.
		 */
		dst->u.other.id = src->u.other.id;
		break;
	}
}

#endif /* __XEN_BLKIF__BACKEND__COMMON_H__ */