summaryrefslogtreecommitdiff
path: root/block/bounce.c
blob: 79d81221446dfe6051f31307f2b335b7ab98eeea (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
// SPDX-License-Identifier: GPL-2.0
/* bounce buffer handling for block devices
 *
 * - Split from highmem.c
 */

#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt

#include <linux/mm.h>
#include <linux/export.h>
#include <linux/swap.h>
#include <linux/gfp.h>
#include <linux/bio.h>
#include <linux/pagemap.h>
#include <linux/mempool.h>
#include <linux/blkdev.h>
#include <linux/backing-dev.h>
#include <linux/init.h>
#include <linux/hash.h>
#include <linux/highmem.h>
#include <linux/memblock.h>
#include <linux/printk.h>
#include <asm/tlbflush.h>

#include <trace/events/block.h>
#include "blk.h"

#define POOL_SIZE	64
#define ISA_POOL_SIZE	16

static struct bio_set bounce_bio_set, bounce_bio_split;
static mempool_t page_pool, isa_page_pool;

static void init_bounce_bioset(void)
{
	static bool bounce_bs_setup;
	int ret;

	if (bounce_bs_setup)
		return;

	ret = bioset_init(&bounce_bio_set, BIO_POOL_SIZE, 0, BIOSET_NEED_BVECS);
	BUG_ON(ret);
	if (bioset_integrity_create(&bounce_bio_set, BIO_POOL_SIZE))
		BUG_ON(1);

	ret = bioset_init(&bounce_bio_split, BIO_POOL_SIZE, 0, 0);
	BUG_ON(ret);
	bounce_bs_setup = true;
}

#if defined(CONFIG_HIGHMEM)
static __init int init_emergency_pool(void)
{
	int ret;
#if defined(CONFIG_HIGHMEM) && !defined(CONFIG_MEMORY_HOTPLUG)
	if (max_pfn <= max_low_pfn)
		return 0;
#endif

	ret = mempool_init_page_pool(&page_pool, POOL_SIZE, 0);
	BUG_ON(ret);
	pr_info("pool size: %d pages\n", POOL_SIZE);

	init_bounce_bioset();
	return 0;
}

__initcall(init_emergency_pool);
#endif

#ifdef CONFIG_HIGHMEM
/*
 * highmem version, map in to vec
 */
static void bounce_copy_vec(struct bio_vec *to, unsigned char *vfrom)
{
	unsigned char *vto;

	vto = kmap_atomic(to->bv_page);
	memcpy(vto + to->bv_offset, vfrom, to->bv_len);
	kunmap_atomic(vto);
}

#else /* CONFIG_HIGHMEM */

#define bounce_copy_vec(to, vfrom)	\
	memcpy(page_address((to)->bv_page) + (to)->bv_offset, vfrom, (to)->bv_len)

#endif /* CONFIG_HIGHMEM */

/*
 * allocate pages in the DMA region for the ISA pool
 */
static void *mempool_alloc_pages_isa(gfp_t gfp_mask, void *data)
{
	return mempool_alloc_pages(gfp_mask | GFP_DMA, data);
}

static DEFINE_MUTEX(isa_mutex);

/*
 * gets called "every" time someone init's a queue with BLK_BOUNCE_ISA
 * as the max address, so check if the pool has already been created.
 */
int init_emergency_isa_pool(void)
{
	int ret;

	mutex_lock(&isa_mutex);

	if (mempool_initialized(&isa_page_pool)) {
		mutex_unlock(&isa_mutex);
		return 0;
	}

	ret = mempool_init(&isa_page_pool, ISA_POOL_SIZE, mempool_alloc_pages_isa,
			   mempool_free_pages, (void *) 0);
	BUG_ON(ret);

	pr_info("isa pool size: %d pages\n", ISA_POOL_SIZE);
	init_bounce_bioset();
	mutex_unlock(&isa_mutex);
	return 0;
}

/*
 * Simple bounce buffer support for highmem pages. Depending on the
 * queue gfp mask set, *to may or may not be a highmem page. kmap it
 * always, it will do the Right Thing
 */
static void copy_to_high_bio_irq(struct bio *to, struct bio *from)
{
	unsigned char *vfrom;
	struct bio_vec tovec, fromvec;
	struct bvec_iter iter;
	/*
	 * The bio of @from is created by bounce, so we can iterate
	 * its bvec from start to end, but the @from->bi_iter can't be
	 * trusted because it might be changed by splitting.
	 */
	struct bvec_iter from_iter = BVEC_ITER_ALL_INIT;

	bio_for_each_segment(tovec, to, iter) {
		fromvec = bio_iter_iovec(from, from_iter);
		if (tovec.bv_page != fromvec.bv_page) {
			/*
			 * fromvec->bv_offset and fromvec->bv_len might have
			 * been modified by the block layer, so use the original
			 * copy, bounce_copy_vec already uses tovec->bv_len
			 */
			vfrom = page_address(fromvec.bv_page) +
				tovec.bv_offset;

			bounce_copy_vec(&tovec, vfrom);
			flush_dcache_page(tovec.bv_page);
		}
		bio_advance_iter(from, &from_iter, tovec.bv_len);
	}
}

static void bounce_end_io(struct bio *bio, mempool_t *pool)
{
	struct bio *bio_orig = bio->bi_private;
	struct bio_vec *bvec, orig_vec;
	struct bvec_iter orig_iter = bio_orig->bi_iter;
	struct bvec_iter_all iter_all;

	/*
	 * free up bounce indirect pages used
	 */
	bio_for_each_segment_all(bvec, bio, iter_all) {
		orig_vec = bio_iter_iovec(bio_orig, orig_iter);
		if (bvec->bv_page != orig_vec.bv_page) {
			dec_zone_page_state(bvec->bv_page, NR_BOUNCE);
			mempool_free(bvec->bv_page, pool);
		}
		bio_advance_iter(bio_orig, &orig_iter, orig_vec.bv_len);
	}

	bio_orig->bi_status = bio->bi_status;
	bio_endio(bio_orig);
	bio_put(bio);
}

static void bounce_end_io_write(struct bio *bio)
{
	bounce_end_io(bio, &page_pool);
}

static void bounce_end_io_write_isa(struct bio *bio)
{

	bounce_end_io(bio, &isa_page_pool);
}

static void __bounce_end_io_read(struct bio *bio, mempool_t *pool)
{
	struct bio *bio_orig = bio->bi_private;

	if (!bio->bi_status)
		copy_to_high_bio_irq(bio_orig, bio);

	bounce_end_io(bio, pool);
}

static void bounce_end_io_read(struct bio *bio)
{
	__bounce_end_io_read(bio, &page_pool);
}

static void bounce_end_io_read_isa(struct bio *bio)
{
	__bounce_end_io_read(bio, &isa_page_pool);
}

static struct bio *bounce_clone_bio(struct bio *bio_src, gfp_t gfp_mask)
{
	struct bvec_iter iter;
	struct bio_vec bv;
	struct bio *bio;

	/*
	 * Pre immutable biovecs, __bio_clone() used to just do a memcpy from
	 * bio_src->bi_io_vec to bio->bi_io_vec.
	 *
	 * We can't do that anymore, because:
	 *
	 *  - The point of cloning the biovec is to produce a bio with a biovec
	 *    the caller can modify: bi_idx and bi_bvec_done should be 0.
	 *
	 *  - The original bio could've had more than BIO_MAX_PAGES biovecs; if
	 *    we tried to clone the whole thing bio_alloc_bioset() would fail.
	 *    But the clone should succeed as long as the number of biovecs we
	 *    actually need to allocate is fewer than BIO_MAX_PAGES.
	 *
	 *  - Lastly, bi_vcnt should not be looked at or relied upon by code
	 *    that does not own the bio - reason being drivers don't use it for
	 *    iterating over the biovec anymore, so expecting it to be kept up
	 *    to date (i.e. for clones that share the parent biovec) is just
	 *    asking for trouble and would force extra work on
	 *    __bio_clone_fast() anyways.
	 */
	if (bio_is_passthrough(bio_src))
		bio = bio_kmalloc(gfp_mask, bio_segments(bio_src));
	else
		bio = bio_alloc_bioset(gfp_mask, bio_segments(bio_src),
				       &bounce_bio_set);
	if (!bio)
		return NULL;
	bio->bi_bdev		= bio_src->bi_bdev;
	if (bio_flagged(bio_src, BIO_REMAPPED))
		bio_set_flag(bio, BIO_REMAPPED);
	bio->bi_opf		= bio_src->bi_opf;
	bio->bi_ioprio		= bio_src->bi_ioprio;
	bio->bi_write_hint	= bio_src->bi_write_hint;
	bio->bi_iter.bi_sector	= bio_src->bi_iter.bi_sector;
	bio->bi_iter.bi_size	= bio_src->bi_iter.bi_size;

	switch (bio_op(bio)) {
	case REQ_OP_DISCARD:
	case REQ_OP_SECURE_ERASE:
	case REQ_OP_WRITE_ZEROES:
		break;
	case REQ_OP_WRITE_SAME:
		bio->bi_io_vec[bio->bi_vcnt++] = bio_src->bi_io_vec[0];
		break;
	default:
		bio_for_each_segment(bv, bio_src, iter)
			bio->bi_io_vec[bio->bi_vcnt++] = bv;
		break;
	}

	if (bio_crypt_clone(bio, bio_src, gfp_mask) < 0)
		goto err_put;

	if (bio_integrity(bio_src) &&
	    bio_integrity_clone(bio, bio_src, gfp_mask) < 0)
		goto err_put;

	bio_clone_blkg_association(bio, bio_src);
	blkcg_bio_issue_init(bio);

	return bio;

err_put:
	bio_put(bio);
	return NULL;
}

static void __blk_queue_bounce(struct request_queue *q, struct bio **bio_orig,
			       mempool_t *pool)
{
	struct bio *bio;
	int rw = bio_data_dir(*bio_orig);
	struct bio_vec *to, from;
	struct bvec_iter iter;
	unsigned i = 0;
	bool bounce = false;
	int sectors = 0;

	bio_for_each_segment(from, *bio_orig, iter) {
		if (i++ < BIO_MAX_PAGES)
			sectors += from.bv_len >> 9;
		if (page_to_pfn(from.bv_page) > q->limits.bounce_pfn)
			bounce = true;
	}
	if (!bounce)
		return;

	if (!bio_is_passthrough(*bio_orig) &&
	    sectors < bio_sectors(*bio_orig)) {
		bio = bio_split(*bio_orig, sectors, GFP_NOIO, &bounce_bio_split);
		bio_chain(bio, *bio_orig);
		submit_bio_noacct(*bio_orig);
		*bio_orig = bio;
	}
	bio = bounce_clone_bio(*bio_orig, GFP_NOIO);

	/*
	 * Bvec table can't be updated by bio_for_each_segment_all(),
	 * so retrieve bvec from the table directly. This way is safe
	 * because the 'bio' is single-page bvec.
	 */
	for (i = 0, to = bio->bi_io_vec; i < bio->bi_vcnt; to++, i++) {
		struct page *page = to->bv_page;

		if (page_to_pfn(page) <= q->limits.bounce_pfn)
			continue;

		to->bv_page = mempool_alloc(pool, q->bounce_gfp);
		inc_zone_page_state(to->bv_page, NR_BOUNCE);

		if (rw == WRITE) {
			char *vto, *vfrom;

			flush_dcache_page(page);

			vto = page_address(to->bv_page) + to->bv_offset;
			vfrom = kmap_atomic(page) + to->bv_offset;
			memcpy(vto, vfrom, to->bv_len);
			kunmap_atomic(vfrom);
		}
	}

	trace_block_bio_bounce(*bio_orig);

	bio->bi_flags |= (1 << BIO_BOUNCED);

	if (pool == &page_pool) {
		bio->bi_end_io = bounce_end_io_write;
		if (rw == READ)
			bio->bi_end_io = bounce_end_io_read;
	} else {
		bio->bi_end_io = bounce_end_io_write_isa;
		if (rw == READ)
			bio->bi_end_io = bounce_end_io_read_isa;
	}

	bio->bi_private = *bio_orig;
	*bio_orig = bio;
}

void blk_queue_bounce(struct request_queue *q, struct bio **bio_orig)
{
	mempool_t *pool;

	/*
	 * Data-less bio, nothing to bounce
	 */
	if (!bio_has_data(*bio_orig))
		return;

	/*
	 * for non-isa bounce case, just check if the bounce pfn is equal
	 * to or bigger than the highest pfn in the system -- in that case,
	 * don't waste time iterating over bio segments
	 */
	if (!(q->bounce_gfp & GFP_DMA)) {
		if (q->limits.bounce_pfn >= blk_max_pfn)
			return;
		pool = &page_pool;
	} else {
		BUG_ON(!mempool_initialized(&isa_page_pool));
		pool = &isa_page_pool;
	}

	/*
	 * slow path
	 */
	__blk_queue_bounce(q, bio_orig, pool);
}