alistair23-linux/block/blk-lib.c
Paolo Bonzini c6e666345e block: split discard into aligned requests
When a disk has large discard_granularity and small max_discard_sectors,
discards are not split with optimal alignment.  In the limit case of
discard_granularity == max_discard_sectors, no request could be aligned
correctly, so in fact you might end up with no discarded logical blocks
at all.

Another example that helps showing the condition in the patch is with
discard_granularity == 64, max_discard_sectors == 128.  A request that is
submitted for 256 sectors 2..257 will be split in two: 2..129, 130..257.
However, only 2 aligned blocks out of 3 are included in the request;
128..191 may be left intact and not discarded.  With this patch, the
first request will be truncated to ensure good alignment of what's left,
and the split will be 2..127, 128..255, 256..257.  The patch will also
take into account the discard_alignment.

At most one extra request will be introduced, because the first request
will be reduced by at most granularity-1 sectors, and granularity
must be less than max_discard_sectors.  Subsequent requests will run
on round_down(max_discard_sectors, granularity) sectors, as in the
current code.

Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Acked-by: Vivek Goyal <vgoyal@redhat.com>
Tested-by: Mike Snitzer <snitzer@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
2012-08-02 09:48:50 +02:00

194 lines
4.5 KiB
C

/*
* Functions related to generic helpers functions
*/
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/bio.h>
#include <linux/blkdev.h>
#include <linux/scatterlist.h>
#include "blk.h"
struct bio_batch {
atomic_t done;
unsigned long flags;
struct completion *wait;
};
static void bio_batch_end_io(struct bio *bio, int err)
{
struct bio_batch *bb = bio->bi_private;
if (err && (err != -EOPNOTSUPP))
clear_bit(BIO_UPTODATE, &bb->flags);
if (atomic_dec_and_test(&bb->done))
complete(bb->wait);
bio_put(bio);
}
/**
* blkdev_issue_discard - queue a discard
* @bdev: blockdev to issue discard for
* @sector: start sector
* @nr_sects: number of sectors to discard
* @gfp_mask: memory allocation flags (for bio_alloc)
* @flags: BLKDEV_IFL_* flags to control behaviour
*
* Description:
* Issue a discard request for the sectors in question.
*/
int blkdev_issue_discard(struct block_device *bdev, sector_t sector,
sector_t nr_sects, gfp_t gfp_mask, unsigned long flags)
{
DECLARE_COMPLETION_ONSTACK(wait);
struct request_queue *q = bdev_get_queue(bdev);
int type = REQ_WRITE | REQ_DISCARD;
unsigned int max_discard_sectors;
unsigned int granularity, alignment, mask;
struct bio_batch bb;
struct bio *bio;
int ret = 0;
if (!q)
return -ENXIO;
if (!blk_queue_discard(q))
return -EOPNOTSUPP;
/* Zero-sector (unknown) and one-sector granularities are the same. */
granularity = max(q->limits.discard_granularity >> 9, 1U);
mask = granularity - 1;
alignment = (bdev_discard_alignment(bdev) >> 9) & mask;
/*
* Ensure that max_discard_sectors is of the proper
* granularity, so that requests stay aligned after a split.
*/
max_discard_sectors = min(q->limits.max_discard_sectors, UINT_MAX >> 9);
max_discard_sectors = round_down(max_discard_sectors, granularity);
if (unlikely(!max_discard_sectors)) {
/* Avoid infinite loop below. Being cautious never hurts. */
return -EOPNOTSUPP;
}
if (flags & BLKDEV_DISCARD_SECURE) {
if (!blk_queue_secdiscard(q))
return -EOPNOTSUPP;
type |= REQ_SECURE;
}
atomic_set(&bb.done, 1);
bb.flags = 1 << BIO_UPTODATE;
bb.wait = &wait;
while (nr_sects) {
unsigned int req_sects;
sector_t end_sect;
bio = bio_alloc(gfp_mask, 1);
if (!bio) {
ret = -ENOMEM;
break;
}
req_sects = min_t(sector_t, nr_sects, max_discard_sectors);
/*
* If splitting a request, and the next starting sector would be
* misaligned, stop the discard at the previous aligned sector.
*/
end_sect = sector + req_sects;
if (req_sects < nr_sects && (end_sect & mask) != alignment) {
end_sect =
round_down(end_sect - alignment, granularity)
+ alignment;
req_sects = end_sect - sector;
}
bio->bi_sector = sector;
bio->bi_end_io = bio_batch_end_io;
bio->bi_bdev = bdev;
bio->bi_private = &bb;
bio->bi_size = req_sects << 9;
nr_sects -= req_sects;
sector = end_sect;
atomic_inc(&bb.done);
submit_bio(type, bio);
}
/* Wait for bios in-flight */
if (!atomic_dec_and_test(&bb.done))
wait_for_completion(&wait);
if (!test_bit(BIO_UPTODATE, &bb.flags))
ret = -EIO;
return ret;
}
EXPORT_SYMBOL(blkdev_issue_discard);
/**
* blkdev_issue_zeroout - generate number of zero filed write bios
* @bdev: blockdev to issue
* @sector: start sector
* @nr_sects: number of sectors to write
* @gfp_mask: memory allocation flags (for bio_alloc)
*
* Description:
* Generate and issue number of bios with zerofiled pages.
*/
int blkdev_issue_zeroout(struct block_device *bdev, sector_t sector,
sector_t nr_sects, gfp_t gfp_mask)
{
int ret;
struct bio *bio;
struct bio_batch bb;
unsigned int sz;
DECLARE_COMPLETION_ONSTACK(wait);
atomic_set(&bb.done, 1);
bb.flags = 1 << BIO_UPTODATE;
bb.wait = &wait;
ret = 0;
while (nr_sects != 0) {
bio = bio_alloc(gfp_mask,
min(nr_sects, (sector_t)BIO_MAX_PAGES));
if (!bio) {
ret = -ENOMEM;
break;
}
bio->bi_sector = sector;
bio->bi_bdev = bdev;
bio->bi_end_io = bio_batch_end_io;
bio->bi_private = &bb;
while (nr_sects != 0) {
sz = min((sector_t) PAGE_SIZE >> 9 , nr_sects);
ret = bio_add_page(bio, ZERO_PAGE(0), sz << 9, 0);
nr_sects -= ret >> 9;
sector += ret >> 9;
if (ret < (sz << 9))
break;
}
ret = 0;
atomic_inc(&bb.done);
submit_bio(WRITE, bio);
}
/* Wait for bios in-flight */
if (!atomic_dec_and_test(&bb.done))
wait_for_completion(&wait);
if (!test_bit(BIO_UPTODATE, &bb.flags))
/* One of bios in the batch was completed with error.*/
ret = -EIO;
return ret;
}
EXPORT_SYMBOL(blkdev_issue_zeroout);