forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 1
/
blk-settings.c
472 lines (433 loc) · 14.7 KB
/
blk-settings.c
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
/*
* Functions related to setting various queue properties from drivers
*/
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/init.h>
#include <linux/bio.h>
#include <linux/blkdev.h>
#include <linux/bootmem.h> /* for max_pfn/max_low_pfn */
#include "blk.h"
unsigned long blk_max_low_pfn;
EXPORT_SYMBOL(blk_max_low_pfn);
unsigned long blk_max_pfn;
/**
* blk_queue_prep_rq - set a prepare_request function for queue
* @q: queue
* @pfn: prepare_request function
*
* It's possible for a queue to register a prepare_request callback which
* is invoked before the request is handed to the request_fn. The goal of
* the function is to prepare a request for I/O, it can be used to build a
* cdb from the request data for instance.
*
*/
void blk_queue_prep_rq(struct request_queue *q, prep_rq_fn *pfn)
{
q->prep_rq_fn = pfn;
}
EXPORT_SYMBOL(blk_queue_prep_rq);
/**
* blk_queue_set_discard - set a discard_sectors function for queue
* @q: queue
* @dfn: prepare_discard function
*
* It's possible for a queue to register a discard callback which is used
* to transform a discard request into the appropriate type for the
* hardware. If none is registered, then discard requests are failed
* with %EOPNOTSUPP.
*
*/
void blk_queue_set_discard(struct request_queue *q, prepare_discard_fn *dfn)
{
q->prepare_discard_fn = dfn;
}
EXPORT_SYMBOL(blk_queue_set_discard);
/**
* blk_queue_merge_bvec - set a merge_bvec function for queue
* @q: queue
* @mbfn: merge_bvec_fn
*
* Usually queues have static limitations on the max sectors or segments that
* we can put in a request. Stacking drivers may have some settings that
* are dynamic, and thus we have to query the queue whether it is ok to
* add a new bio_vec to a bio at a given offset or not. If the block device
* has such limitations, it needs to register a merge_bvec_fn to control
* the size of bio's sent to it. Note that a block device *must* allow a
* single page to be added to an empty bio. The block device driver may want
* to use the bio_split() function to deal with these bio's. By default
* no merge_bvec_fn is defined for a queue, and only the fixed limits are
* honored.
*/
void blk_queue_merge_bvec(struct request_queue *q, merge_bvec_fn *mbfn)
{
q->merge_bvec_fn = mbfn;
}
EXPORT_SYMBOL(blk_queue_merge_bvec);
void blk_queue_softirq_done(struct request_queue *q, softirq_done_fn *fn)
{
q->softirq_done_fn = fn;
}
EXPORT_SYMBOL(blk_queue_softirq_done);
void blk_queue_rq_timeout(struct request_queue *q, unsigned int timeout)
{
q->rq_timeout = timeout;
}
EXPORT_SYMBOL_GPL(blk_queue_rq_timeout);
void blk_queue_rq_timed_out(struct request_queue *q, rq_timed_out_fn *fn)
{
q->rq_timed_out_fn = fn;
}
EXPORT_SYMBOL_GPL(blk_queue_rq_timed_out);
void blk_queue_lld_busy(struct request_queue *q, lld_busy_fn *fn)
{
q->lld_busy_fn = fn;
}
EXPORT_SYMBOL_GPL(blk_queue_lld_busy);
/**
* blk_queue_make_request - define an alternate make_request function for a device
* @q: the request queue for the device to be affected
* @mfn: the alternate make_request function
*
* Description:
* The normal way for &struct bios to be passed to a device
* driver is for them to be collected into requests on a request
* queue, and then to allow the device driver to select requests
* off that queue when it is ready. This works well for many block
* devices. However some block devices (typically virtual devices
* such as md or lvm) do not benefit from the processing on the
* request queue, and are served best by having the requests passed
* directly to them. This can be achieved by providing a function
* to blk_queue_make_request().
*
* Caveat:
* The driver that does this *must* be able to deal appropriately
* with buffers in "highmemory". This can be accomplished by either calling
* __bio_kmap_atomic() to get a temporary kernel mapping, or by calling
* blk_queue_bounce() to create a buffer in normal memory.
**/
void blk_queue_make_request(struct request_queue *q, make_request_fn *mfn)
{
/*
* set defaults
*/
q->nr_requests = BLKDEV_MAX_RQ;
blk_queue_max_phys_segments(q, MAX_PHYS_SEGMENTS);
blk_queue_max_hw_segments(q, MAX_HW_SEGMENTS);
blk_queue_segment_boundary(q, BLK_SEG_BOUNDARY_MASK);
blk_queue_max_segment_size(q, MAX_SEGMENT_SIZE);
q->make_request_fn = mfn;
q->backing_dev_info.ra_pages =
(VM_MAX_READAHEAD * 1024) / PAGE_CACHE_SIZE;
q->backing_dev_info.state = 0;
q->backing_dev_info.capabilities = BDI_CAP_MAP_COPY;
blk_queue_max_sectors(q, SAFE_MAX_SECTORS);
blk_queue_hardsect_size(q, 512);
blk_queue_dma_alignment(q, 511);
blk_queue_congestion_threshold(q);
q->nr_batching = BLK_BATCH_REQ;
q->unplug_thresh = 4; /* hmm */
q->unplug_delay = (3 * HZ) / 1000; /* 3 milliseconds */
if (q->unplug_delay == 0)
q->unplug_delay = 1;
q->unplug_timer.function = blk_unplug_timeout;
q->unplug_timer.data = (unsigned long)q;
/*
* by default assume old behaviour and bounce for any highmem page
*/
blk_queue_bounce_limit(q, BLK_BOUNCE_HIGH);
}
EXPORT_SYMBOL(blk_queue_make_request);
/**
* blk_queue_bounce_limit - set bounce buffer limit for queue
* @q: the request queue for the device
* @dma_addr: bus address limit
*
* Description:
* Different hardware can have different requirements as to what pages
* it can do I/O directly to. A low level driver can call
* blk_queue_bounce_limit to have lower memory pages allocated as bounce
* buffers for doing I/O to pages residing above @dma_addr.
**/
void blk_queue_bounce_limit(struct request_queue *q, u64 dma_addr)
{
unsigned long b_pfn = dma_addr >> PAGE_SHIFT;
int dma = 0;
q->bounce_gfp = GFP_NOIO;
#if BITS_PER_LONG == 64
/* Assume anything <= 4GB can be handled by IOMMU.
Actually some IOMMUs can handle everything, but I don't
know of a way to test this here. */
if (b_pfn < (min_t(u64, 0x100000000UL, BLK_BOUNCE_HIGH) >> PAGE_SHIFT))
dma = 1;
q->bounce_pfn = max_low_pfn;
#else
if (b_pfn < blk_max_low_pfn)
dma = 1;
q->bounce_pfn = b_pfn;
#endif
if (dma) {
init_emergency_isa_pool();
q->bounce_gfp = GFP_NOIO | GFP_DMA;
q->bounce_pfn = b_pfn;
}
}
EXPORT_SYMBOL(blk_queue_bounce_limit);
/**
* blk_queue_max_sectors - set max sectors for a request for this queue
* @q: the request queue for the device
* @max_sectors: max sectors in the usual 512b unit
*
* Description:
* Enables a low level driver to set an upper limit on the size of
* received requests.
**/
void blk_queue_max_sectors(struct request_queue *q, unsigned int max_sectors)
{
if ((max_sectors << 9) < PAGE_CACHE_SIZE) {
max_sectors = 1 << (PAGE_CACHE_SHIFT - 9);
printk(KERN_INFO "%s: set to minimum %d\n",
__func__, max_sectors);
}
if (BLK_DEF_MAX_SECTORS > max_sectors)
q->max_hw_sectors = q->max_sectors = max_sectors;
else {
q->max_sectors = BLK_DEF_MAX_SECTORS;
q->max_hw_sectors = max_sectors;
}
}
EXPORT_SYMBOL(blk_queue_max_sectors);
/**
* blk_queue_max_phys_segments - set max phys segments for a request for this queue
* @q: the request queue for the device
* @max_segments: max number of segments
*
* Description:
* Enables a low level driver to set an upper limit on the number of
* physical data segments in a request. This would be the largest sized
* scatter list the driver could handle.
**/
void blk_queue_max_phys_segments(struct request_queue *q,
unsigned short max_segments)
{
if (!max_segments) {
max_segments = 1;
printk(KERN_INFO "%s: set to minimum %d\n",
__func__, max_segments);
}
q->max_phys_segments = max_segments;
}
EXPORT_SYMBOL(blk_queue_max_phys_segments);
/**
* blk_queue_max_hw_segments - set max hw segments for a request for this queue
* @q: the request queue for the device
* @max_segments: max number of segments
*
* Description:
* Enables a low level driver to set an upper limit on the number of
* hw data segments in a request. This would be the largest number of
* address/length pairs the host adapter can actually give at once
* to the device.
**/
void blk_queue_max_hw_segments(struct request_queue *q,
unsigned short max_segments)
{
if (!max_segments) {
max_segments = 1;
printk(KERN_INFO "%s: set to minimum %d\n",
__func__, max_segments);
}
q->max_hw_segments = max_segments;
}
EXPORT_SYMBOL(blk_queue_max_hw_segments);
/**
* blk_queue_max_segment_size - set max segment size for blk_rq_map_sg
* @q: the request queue for the device
* @max_size: max size of segment in bytes
*
* Description:
* Enables a low level driver to set an upper limit on the size of a
* coalesced segment
**/
void blk_queue_max_segment_size(struct request_queue *q, unsigned int max_size)
{
if (max_size < PAGE_CACHE_SIZE) {
max_size = PAGE_CACHE_SIZE;
printk(KERN_INFO "%s: set to minimum %d\n",
__func__, max_size);
}
q->max_segment_size = max_size;
}
EXPORT_SYMBOL(blk_queue_max_segment_size);
/**
* blk_queue_hardsect_size - set hardware sector size for the queue
* @q: the request queue for the device
* @size: the hardware sector size, in bytes
*
* Description:
* This should typically be set to the lowest possible sector size
* that the hardware can operate on (possible without reverting to
* even internal read-modify-write operations). Usually the default
* of 512 covers most hardware.
**/
void blk_queue_hardsect_size(struct request_queue *q, unsigned short size)
{
q->hardsect_size = size;
}
EXPORT_SYMBOL(blk_queue_hardsect_size);
/*
* Returns the minimum that is _not_ zero, unless both are zero.
*/
#define min_not_zero(l, r) (l == 0) ? r : ((r == 0) ? l : min(l, r))
/**
* blk_queue_stack_limits - inherit underlying queue limits for stacked drivers
* @t: the stacking driver (top)
* @b: the underlying device (bottom)
**/
void blk_queue_stack_limits(struct request_queue *t, struct request_queue *b)
{
/* zero is "infinity" */
t->max_sectors = min_not_zero(t->max_sectors, b->max_sectors);
t->max_hw_sectors = min_not_zero(t->max_hw_sectors, b->max_hw_sectors);
t->seg_boundary_mask = min_not_zero(t->seg_boundary_mask, b->seg_boundary_mask);
t->max_phys_segments = min_not_zero(t->max_phys_segments, b->max_phys_segments);
t->max_hw_segments = min_not_zero(t->max_hw_segments, b->max_hw_segments);
t->max_segment_size = min_not_zero(t->max_segment_size, b->max_segment_size);
t->hardsect_size = max(t->hardsect_size, b->hardsect_size);
if (!t->queue_lock)
WARN_ON_ONCE(1);
else if (!test_bit(QUEUE_FLAG_CLUSTER, &b->queue_flags)) {
unsigned long flags;
spin_lock_irqsave(t->queue_lock, flags);
queue_flag_clear(QUEUE_FLAG_CLUSTER, t);
spin_unlock_irqrestore(t->queue_lock, flags);
}
}
EXPORT_SYMBOL(blk_queue_stack_limits);
/**
* blk_queue_dma_pad - set pad mask
* @q: the request queue for the device
* @mask: pad mask
*
* Set dma pad mask.
*
* Appending pad buffer to a request modifies the last entry of a
* scatter list such that it includes the pad buffer.
**/
void blk_queue_dma_pad(struct request_queue *q, unsigned int mask)
{
q->dma_pad_mask = mask;
}
EXPORT_SYMBOL(blk_queue_dma_pad);
/**
* blk_queue_update_dma_pad - update pad mask
* @q: the request queue for the device
* @mask: pad mask
*
* Update dma pad mask.
*
* Appending pad buffer to a request modifies the last entry of a
* scatter list such that it includes the pad buffer.
**/
void blk_queue_update_dma_pad(struct request_queue *q, unsigned int mask)
{
if (mask > q->dma_pad_mask)
q->dma_pad_mask = mask;
}
EXPORT_SYMBOL(blk_queue_update_dma_pad);
/**
* blk_queue_dma_drain - Set up a drain buffer for excess dma.
* @q: the request queue for the device
* @dma_drain_needed: fn which returns non-zero if drain is necessary
* @buf: physically contiguous buffer
* @size: size of the buffer in bytes
*
* Some devices have excess DMA problems and can't simply discard (or
* zero fill) the unwanted piece of the transfer. They have to have a
* real area of memory to transfer it into. The use case for this is
* ATAPI devices in DMA mode. If the packet command causes a transfer
* bigger than the transfer size some HBAs will lock up if there
* aren't DMA elements to contain the excess transfer. What this API
* does is adjust the queue so that the buf is always appended
* silently to the scatterlist.
*
* Note: This routine adjusts max_hw_segments to make room for
* appending the drain buffer. If you call
* blk_queue_max_hw_segments() or blk_queue_max_phys_segments() after
* calling this routine, you must set the limit to one fewer than your
* device can support otherwise there won't be room for the drain
* buffer.
*/
int blk_queue_dma_drain(struct request_queue *q,
dma_drain_needed_fn *dma_drain_needed,
void *buf, unsigned int size)
{
if (q->max_hw_segments < 2 || q->max_phys_segments < 2)
return -EINVAL;
/* make room for appending the drain */
--q->max_hw_segments;
--q->max_phys_segments;
q->dma_drain_needed = dma_drain_needed;
q->dma_drain_buffer = buf;
q->dma_drain_size = size;
return 0;
}
EXPORT_SYMBOL_GPL(blk_queue_dma_drain);
/**
* blk_queue_segment_boundary - set boundary rules for segment merging
* @q: the request queue for the device
* @mask: the memory boundary mask
**/
void blk_queue_segment_boundary(struct request_queue *q, unsigned long mask)
{
if (mask < PAGE_CACHE_SIZE - 1) {
mask = PAGE_CACHE_SIZE - 1;
printk(KERN_INFO "%s: set to minimum %lx\n",
__func__, mask);
}
q->seg_boundary_mask = mask;
}
EXPORT_SYMBOL(blk_queue_segment_boundary);
/**
* blk_queue_dma_alignment - set dma length and memory alignment
* @q: the request queue for the device
* @mask: alignment mask
*
* description:
* set required memory and length alignment for direct dma transactions.
* this is used when buiding direct io requests for the queue.
*
**/
void blk_queue_dma_alignment(struct request_queue *q, int mask)
{
q->dma_alignment = mask;
}
EXPORT_SYMBOL(blk_queue_dma_alignment);
/**
* blk_queue_update_dma_alignment - update dma length and memory alignment
* @q: the request queue for the device
* @mask: alignment mask
*
* description:
* update required memory and length alignment for direct dma transactions.
* If the requested alignment is larger than the current alignment, then
* the current queue alignment is updated to the new value, otherwise it
* is left alone. The design of this is to allow multiple objects
* (driver, device, transport etc) to set their respective
* alignments without having them interfere.
*
**/
void blk_queue_update_dma_alignment(struct request_queue *q, int mask)
{
BUG_ON(mask > PAGE_SIZE);
if (mask > q->dma_alignment)
q->dma_alignment = mask;
}
EXPORT_SYMBOL(blk_queue_update_dma_alignment);
static int __init blk_settings_init(void)
{
blk_max_low_pfn = max_low_pfn - 1;
blk_max_pfn = max_pfn - 1;
return 0;
}
subsys_initcall(blk_settings_init);