linux/block/blk-lib.c
Damien Le Moal 615d22a51c block: Fix __blkdev_issue_zeroout loop
The BIO issuing loop in __blkdev_issue_zeroout() is allocating BIOs
with a maximum number of bvec (pages) equal to

min(nr_sects, (sector_t)BIO_MAX_PAGES)

This works since the requested number of bvecs will always be limited
to the absolute maximum number supported (BIO_MAX_PAGES), but this is
ineficient as too many bvec entries may be requested due to the
different units being used in the min() operation (number of sectors vs
number of pages).
To fix this, introduce the helper __blkdev_sectors_to_bio_pages() to
correctly calculate the number of bvecs for zeroout BIOs as the issuing
loop progresses. The calculation is done using consistent units and
makes sure that the number of pages return is at least 1 (for cases
where the number of sectors is less that the number of sectors in
a page).

Also remove a trailing space after the bit shift in the internal loop
min() call.

Signed-off-by: Damien Le Moal <damien.lemoal@wdc.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
2017-07-06 09:43:20 -06:00

378 lines
9.8 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"
static struct bio *next_bio(struct bio *bio, unsigned int nr_pages,
gfp_t gfp)
{
struct bio *new = bio_alloc(gfp, nr_pages);
if (bio) {
bio_chain(bio, new);
submit_bio(bio);
}
return new;
}
int __blkdev_issue_discard(struct block_device *bdev, sector_t sector,
sector_t nr_sects, gfp_t gfp_mask, int flags,
struct bio **biop)
{
struct request_queue *q = bdev_get_queue(bdev);
struct bio *bio = *biop;
unsigned int granularity;
unsigned int op;
int alignment;
sector_t bs_mask;
if (!q)
return -ENXIO;
if (flags & BLKDEV_DISCARD_SECURE) {
if (!blk_queue_secure_erase(q))
return -EOPNOTSUPP;
op = REQ_OP_SECURE_ERASE;
} else {
if (!blk_queue_discard(q))
return -EOPNOTSUPP;
op = REQ_OP_DISCARD;
}
bs_mask = (bdev_logical_block_size(bdev) >> 9) - 1;
if ((sector | nr_sects) & bs_mask)
return -EINVAL;
/* Zero-sector (unknown) and one-sector granularities are the same. */
granularity = max(q->limits.discard_granularity >> 9, 1U);
alignment = (bdev_discard_alignment(bdev) >> 9) % granularity;
while (nr_sects) {
unsigned int req_sects;
sector_t end_sect, tmp;
/* Make sure bi_size doesn't overflow */
req_sects = min_t(sector_t, nr_sects, UINT_MAX >> 9);
/**
* 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;
tmp = end_sect;
if (req_sects < nr_sects &&
sector_div(tmp, granularity) != alignment) {
end_sect = end_sect - alignment;
sector_div(end_sect, granularity);
end_sect = end_sect * granularity + alignment;
req_sects = end_sect - sector;
}
bio = next_bio(bio, 0, gfp_mask);
bio->bi_iter.bi_sector = sector;
bio->bi_bdev = bdev;
bio_set_op_attrs(bio, op, 0);
bio->bi_iter.bi_size = req_sects << 9;
nr_sects -= req_sects;
sector = end_sect;
/*
* We can loop for a long time in here, if someone does
* full device discards (like mkfs). Be nice and allow
* us to schedule out to avoid softlocking if preempt
* is disabled.
*/
cond_resched();
}
*biop = bio;
return 0;
}
EXPORT_SYMBOL(__blkdev_issue_discard);
/**
* 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_DISCARD_* 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)
{
struct bio *bio = NULL;
struct blk_plug plug;
int ret;
blk_start_plug(&plug);
ret = __blkdev_issue_discard(bdev, sector, nr_sects, gfp_mask, flags,
&bio);
if (!ret && bio) {
ret = submit_bio_wait(bio);
if (ret == -EOPNOTSUPP)
ret = 0;
bio_put(bio);
}
blk_finish_plug(&plug);
return ret;
}
EXPORT_SYMBOL(blkdev_issue_discard);
/**
* __blkdev_issue_write_same - generate number of bios with same page
* @bdev: target blockdev
* @sector: start sector
* @nr_sects: number of sectors to write
* @gfp_mask: memory allocation flags (for bio_alloc)
* @page: page containing data to write
* @biop: pointer to anchor bio
*
* Description:
* Generate and issue number of bios(REQ_OP_WRITE_SAME) with same page.
*/
static int __blkdev_issue_write_same(struct block_device *bdev, sector_t sector,
sector_t nr_sects, gfp_t gfp_mask, struct page *page,
struct bio **biop)
{
struct request_queue *q = bdev_get_queue(bdev);
unsigned int max_write_same_sectors;
struct bio *bio = *biop;
sector_t bs_mask;
if (!q)
return -ENXIO;
bs_mask = (bdev_logical_block_size(bdev) >> 9) - 1;
if ((sector | nr_sects) & bs_mask)
return -EINVAL;
if (!bdev_write_same(bdev))
return -EOPNOTSUPP;
/* Ensure that max_write_same_sectors doesn't overflow bi_size */
max_write_same_sectors = UINT_MAX >> 9;
while (nr_sects) {
bio = next_bio(bio, 1, gfp_mask);
bio->bi_iter.bi_sector = sector;
bio->bi_bdev = bdev;
bio->bi_vcnt = 1;
bio->bi_io_vec->bv_page = page;
bio->bi_io_vec->bv_offset = 0;
bio->bi_io_vec->bv_len = bdev_logical_block_size(bdev);
bio_set_op_attrs(bio, REQ_OP_WRITE_SAME, 0);
if (nr_sects > max_write_same_sectors) {
bio->bi_iter.bi_size = max_write_same_sectors << 9;
nr_sects -= max_write_same_sectors;
sector += max_write_same_sectors;
} else {
bio->bi_iter.bi_size = nr_sects << 9;
nr_sects = 0;
}
cond_resched();
}
*biop = bio;
return 0;
}
/**
* blkdev_issue_write_same - queue a write same operation
* @bdev: target blockdev
* @sector: start sector
* @nr_sects: number of sectors to write
* @gfp_mask: memory allocation flags (for bio_alloc)
* @page: page containing data
*
* Description:
* Issue a write same request for the sectors in question.
*/
int blkdev_issue_write_same(struct block_device *bdev, sector_t sector,
sector_t nr_sects, gfp_t gfp_mask,
struct page *page)
{
struct bio *bio = NULL;
struct blk_plug plug;
int ret;
blk_start_plug(&plug);
ret = __blkdev_issue_write_same(bdev, sector, nr_sects, gfp_mask, page,
&bio);
if (ret == 0 && bio) {
ret = submit_bio_wait(bio);
bio_put(bio);
}
blk_finish_plug(&plug);
return ret;
}
EXPORT_SYMBOL(blkdev_issue_write_same);
static int __blkdev_issue_write_zeroes(struct block_device *bdev,
sector_t sector, sector_t nr_sects, gfp_t gfp_mask,
struct bio **biop, unsigned flags)
{
struct bio *bio = *biop;
unsigned int max_write_zeroes_sectors;
struct request_queue *q = bdev_get_queue(bdev);
if (!q)
return -ENXIO;
/* Ensure that max_write_zeroes_sectors doesn't overflow bi_size */
max_write_zeroes_sectors = bdev_write_zeroes_sectors(bdev);
if (max_write_zeroes_sectors == 0)
return -EOPNOTSUPP;
while (nr_sects) {
bio = next_bio(bio, 0, gfp_mask);
bio->bi_iter.bi_sector = sector;
bio->bi_bdev = bdev;
bio->bi_opf = REQ_OP_WRITE_ZEROES;
if (flags & BLKDEV_ZERO_NOUNMAP)
bio->bi_opf |= REQ_NOUNMAP;
if (nr_sects > max_write_zeroes_sectors) {
bio->bi_iter.bi_size = max_write_zeroes_sectors << 9;
nr_sects -= max_write_zeroes_sectors;
sector += max_write_zeroes_sectors;
} else {
bio->bi_iter.bi_size = nr_sects << 9;
nr_sects = 0;
}
cond_resched();
}
*biop = bio;
return 0;
}
/*
* Convert a number of 512B sectors to a number of pages.
* The result is limited to a number of pages that can fit into a BIO.
* Also make sure that the result is always at least 1 (page) for the cases
* where nr_sects is lower than the number of sectors in a page.
*/
static unsigned int __blkdev_sectors_to_bio_pages(sector_t nr_sects)
{
sector_t bytes = (nr_sects << 9) + PAGE_SIZE - 1;
return min(bytes >> PAGE_SHIFT, (sector_t)BIO_MAX_PAGES);
}
/**
* __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)
* @biop: pointer to anchor bio
* @flags: controls detailed behavior
*
* Description:
* Zero-fill a block range, either using hardware offload or by explicitly
* writing zeroes to the device.
*
* Note that this function may fail with -EOPNOTSUPP if the driver signals
* zeroing offload support, but the device fails to process the command (for
* some devices there is no non-destructive way to verify whether this
* operation is actually supported). In this case the caller should call
* retry the call to blkdev_issue_zeroout() and the fallback path will be used.
*
* If a device is using logical block provisioning, the underlying space will
* not be released if %flags contains BLKDEV_ZERO_NOUNMAP.
*
* If %flags contains BLKDEV_ZERO_NOFALLBACK, the function will return
* -EOPNOTSUPP if no explicit hardware offload for zeroing is provided.
*/
int __blkdev_issue_zeroout(struct block_device *bdev, sector_t sector,
sector_t nr_sects, gfp_t gfp_mask, struct bio **biop,
unsigned flags)
{
int ret;
int bi_size = 0;
struct bio *bio = *biop;
unsigned int sz;
sector_t bs_mask;
bs_mask = (bdev_logical_block_size(bdev) >> 9) - 1;
if ((sector | nr_sects) & bs_mask)
return -EINVAL;
ret = __blkdev_issue_write_zeroes(bdev, sector, nr_sects, gfp_mask,
biop, flags);
if (ret != -EOPNOTSUPP || (flags & BLKDEV_ZERO_NOFALLBACK))
goto out;
ret = 0;
while (nr_sects != 0) {
bio = next_bio(bio, __blkdev_sectors_to_bio_pages(nr_sects),
gfp_mask);
bio->bi_iter.bi_sector = sector;
bio->bi_bdev = bdev;
bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
while (nr_sects != 0) {
sz = min((sector_t) PAGE_SIZE, nr_sects << 9);
bi_size = bio_add_page(bio, ZERO_PAGE(0), sz, 0);
nr_sects -= bi_size >> 9;
sector += bi_size >> 9;
if (bi_size < sz)
break;
}
cond_resched();
}
*biop = bio;
out:
return ret;
}
EXPORT_SYMBOL(__blkdev_issue_zeroout);
/**
* blkdev_issue_zeroout - zero-fill a block range
* @bdev: blockdev to write
* @sector: start sector
* @nr_sects: number of sectors to write
* @gfp_mask: memory allocation flags (for bio_alloc)
* @flags: controls detailed behavior
*
* Description:
* Zero-fill a block range, either using hardware offload or by explicitly
* writing zeroes to the device. See __blkdev_issue_zeroout() for the
* valid values for %flags.
*/
int blkdev_issue_zeroout(struct block_device *bdev, sector_t sector,
sector_t nr_sects, gfp_t gfp_mask, unsigned flags)
{
int ret;
struct bio *bio = NULL;
struct blk_plug plug;
blk_start_plug(&plug);
ret = __blkdev_issue_zeroout(bdev, sector, nr_sects, gfp_mask,
&bio, flags);
if (ret == 0 && bio) {
ret = submit_bio_wait(bio);
bio_put(bio);
}
blk_finish_plug(&plug);
return ret;
}
EXPORT_SYMBOL(blkdev_issue_zeroout);