kernel_optimize_test/block/blk-lib.c
Kent Overstreet 4f024f3797 block: Abstract out bvec iterator
Immutable biovecs are going to require an explicit iterator. To
implement immutable bvecs, a later patch is going to add a bi_bvec_done
member to this struct; for now, this patch effectively just renames
things.

Signed-off-by: Kent Overstreet <kmo@daterainc.com>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Geert Uytterhoeven <geert@linux-m68k.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: "Ed L. Cashin" <ecashin@coraid.com>
Cc: Nick Piggin <npiggin@kernel.dk>
Cc: Lars Ellenberg <drbd-dev@lists.linbit.com>
Cc: Jiri Kosina <jkosina@suse.cz>
Cc: Matthew Wilcox <willy@linux.intel.com>
Cc: Geoff Levand <geoff@infradead.org>
Cc: Yehuda Sadeh <yehuda@inktank.com>
Cc: Sage Weil <sage@inktank.com>
Cc: Alex Elder <elder@inktank.com>
Cc: ceph-devel@vger.kernel.org
Cc: Joshua Morris <josh.h.morris@us.ibm.com>
Cc: Philip Kelleher <pjk1939@linux.vnet.ibm.com>
Cc: Rusty Russell <rusty@rustcorp.com.au>
Cc: "Michael S. Tsirkin" <mst@redhat.com>
Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Cc: Jeremy Fitzhardinge <jeremy@goop.org>
Cc: Neil Brown <neilb@suse.de>
Cc: Alasdair Kergon <agk@redhat.com>
Cc: Mike Snitzer <snitzer@redhat.com>
Cc: dm-devel@redhat.com
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: linux390@de.ibm.com
Cc: Boaz Harrosh <bharrosh@panasas.com>
Cc: Benny Halevy <bhalevy@tonian.com>
Cc: "James E.J. Bottomley" <JBottomley@parallels.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: "Nicholas A. Bellinger" <nab@linux-iscsi.org>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Chris Mason <chris.mason@fusionio.com>
Cc: "Theodore Ts'o" <tytso@mit.edu>
Cc: Andreas Dilger <adilger.kernel@dilger.ca>
Cc: Jaegeuk Kim <jaegeuk.kim@samsung.com>
Cc: Steven Whitehouse <swhiteho@redhat.com>
Cc: Dave Kleikamp <shaggy@kernel.org>
Cc: Joern Engel <joern@logfs.org>
Cc: Prasad Joshi <prasadjoshi.linux@gmail.com>
Cc: Trond Myklebust <Trond.Myklebust@netapp.com>
Cc: KONISHI Ryusuke <konishi.ryusuke@lab.ntt.co.jp>
Cc: Mark Fasheh <mfasheh@suse.com>
Cc: Joel Becker <jlbec@evilplan.org>
Cc: Ben Myers <bpm@sgi.com>
Cc: xfs@oss.sgi.com
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Len Brown <len.brown@intel.com>
Cc: Pavel Machek <pavel@ucw.cz>
Cc: "Rafael J. Wysocki" <rjw@sisk.pl>
Cc: Herton Ronaldo Krzesinski <herton.krzesinski@canonical.com>
Cc: Ben Hutchings <ben@decadent.org.uk>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Guo Chao <yan@linux.vnet.ibm.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: Asai Thambi S P <asamymuthupa@micron.com>
Cc: Selvan Mani <smani@micron.com>
Cc: Sam Bradshaw <sbradshaw@micron.com>
Cc: Wei Yongjun <yongjun_wei@trendmicro.com.cn>
Cc: "Roger Pau Monné" <roger.pau@citrix.com>
Cc: Jan Beulich <jbeulich@suse.com>
Cc: Stefano Stabellini <stefano.stabellini@eu.citrix.com>
Cc: Ian Campbell <Ian.Campbell@citrix.com>
Cc: Sebastian Ott <sebott@linux.vnet.ibm.com>
Cc: Christian Borntraeger <borntraeger@de.ibm.com>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Jiang Liu <jiang.liu@huawei.com>
Cc: Nitin Gupta <ngupta@vflare.org>
Cc: Jerome Marchand <jmarchand@redhat.com>
Cc: Joe Perches <joe@perches.com>
Cc: Peng Tao <tao.peng@emc.com>
Cc: Andy Adamson <andros@netapp.com>
Cc: fanchaoting <fanchaoting@cn.fujitsu.com>
Cc: Jie Liu <jeff.liu@oracle.com>
Cc: Sunil Mushran <sunil.mushran@gmail.com>
Cc: "Martin K. Petersen" <martin.petersen@oracle.com>
Cc: Namjae Jeon <namjae.jeon@samsung.com>
Cc: Pankaj Kumar <pankaj.km@samsung.com>
Cc: Dan Magenheimer <dan.magenheimer@oracle.com>
Cc: Mel Gorman <mgorman@suse.de>6
2013-11-23 22:33:47 -08:00

300 lines
7.1 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, granularity;
int alignment;
struct bio_batch bb;
struct bio *bio;
int ret = 0;
struct blk_plug plug;
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);
alignment = (bdev_discard_alignment(bdev) >> 9) % granularity;
/*
* 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 -= 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;
blk_start_plug(&plug);
while (nr_sects) {
unsigned int req_sects;
sector_t end_sect, tmp;
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;
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->bi_iter.bi_sector = sector;
bio->bi_end_io = bio_batch_end_io;
bio->bi_bdev = bdev;
bio->bi_private = &bb;
bio->bi_iter.bi_size = req_sects << 9;
nr_sects -= req_sects;
sector = end_sect;
atomic_inc(&bb.done);
submit_bio(type, bio);
}
blk_finish_plug(&plug);
/* Wait for bios in-flight */
if (!atomic_dec_and_test(&bb.done))
wait_for_completion_io(&wait);
if (!test_bit(BIO_UPTODATE, &bb.flags))
ret = -EIO;
return ret;
}
EXPORT_SYMBOL(blkdev_issue_discard);
/**
* 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 to write
*
* 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)
{
DECLARE_COMPLETION_ONSTACK(wait);
struct request_queue *q = bdev_get_queue(bdev);
unsigned int max_write_same_sectors;
struct bio_batch bb;
struct bio *bio;
int ret = 0;
if (!q)
return -ENXIO;
max_write_same_sectors = q->limits.max_write_same_sectors;
if (max_write_same_sectors == 0)
return -EOPNOTSUPP;
atomic_set(&bb.done, 1);
bb.flags = 1 << BIO_UPTODATE;
bb.wait = &wait;
while (nr_sects) {
bio = bio_alloc(gfp_mask, 1);
if (!bio) {
ret = -ENOMEM;
break;
}
bio->bi_iter.bi_sector = sector;
bio->bi_end_io = bio_batch_end_io;
bio->bi_bdev = bdev;
bio->bi_private = &bb;
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);
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;
}
atomic_inc(&bb.done);
submit_bio(REQ_WRITE | REQ_WRITE_SAME, bio);
}
/* Wait for bios in-flight */
if (!atomic_dec_and_test(&bb.done))
wait_for_completion_io(&wait);
if (!test_bit(BIO_UPTODATE, &bb.flags))
ret = -ENOTSUPP;
return ret;
}
EXPORT_SYMBOL(blkdev_issue_write_same);
/**
* 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_iter.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_io(&wait);
if (!test_bit(BIO_UPTODATE, &bb.flags))
/* One of bios in the batch was completed with error.*/
ret = -EIO;
return ret;
}
/**
* 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)
*
* 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)
{
if (bdev_write_same(bdev)) {
unsigned char bdn[BDEVNAME_SIZE];
if (!blkdev_issue_write_same(bdev, sector, nr_sects, gfp_mask,
ZERO_PAGE(0)))
return 0;
bdevname(bdev, bdn);
pr_err("%s: WRITE SAME failed. Manually zeroing.\n", bdn);
}
return __blkdev_issue_zeroout(bdev, sector, nr_sects, gfp_mask);
}
EXPORT_SYMBOL(blkdev_issue_zeroout);