linux-stable/fs/logfs/dev_bdev.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

321 lines
7.8 KiB
C

/*
* fs/logfs/dev_bdev.c - Device access methods for block devices
*
* As should be obvious for Linux kernel code, license is GPLv2
*
* Copyright (c) 2005-2008 Joern Engel <joern@logfs.org>
*/
#include "logfs.h"
#include <linux/bio.h>
#include <linux/blkdev.h>
#include <linux/buffer_head.h>
#include <linux/gfp.h>
#include <linux/prefetch.h>
#define PAGE_OFS(ofs) ((ofs) & (PAGE_SIZE-1))
static int sync_request(struct page *page, struct block_device *bdev, int rw)
{
struct bio bio;
struct bio_vec bio_vec;
bio_init(&bio);
bio.bi_max_vecs = 1;
bio.bi_io_vec = &bio_vec;
bio_vec.bv_page = page;
bio_vec.bv_len = PAGE_SIZE;
bio_vec.bv_offset = 0;
bio.bi_vcnt = 1;
bio.bi_bdev = bdev;
bio.bi_iter.bi_sector = page->index * (PAGE_SIZE >> 9);
bio.bi_iter.bi_size = PAGE_SIZE;
return submit_bio_wait(rw, &bio);
}
static int bdev_readpage(void *_sb, struct page *page)
{
struct super_block *sb = _sb;
struct block_device *bdev = logfs_super(sb)->s_bdev;
int err;
err = sync_request(page, bdev, READ);
if (err) {
ClearPageUptodate(page);
SetPageError(page);
} else {
SetPageUptodate(page);
ClearPageError(page);
}
unlock_page(page);
return err;
}
static DECLARE_WAIT_QUEUE_HEAD(wq);
static void writeseg_end_io(struct bio *bio, int err)
{
const int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
struct bio_vec *bvec;
int i;
struct super_block *sb = bio->bi_private;
struct logfs_super *super = logfs_super(sb);
BUG_ON(!uptodate); /* FIXME: Retry io or write elsewhere */
BUG_ON(err);
bio_for_each_segment_all(bvec, bio, i) {
end_page_writeback(bvec->bv_page);
page_cache_release(bvec->bv_page);
}
bio_put(bio);
if (atomic_dec_and_test(&super->s_pending_writes))
wake_up(&wq);
}
static int __bdev_writeseg(struct super_block *sb, u64 ofs, pgoff_t index,
size_t nr_pages)
{
struct logfs_super *super = logfs_super(sb);
struct address_space *mapping = super->s_mapping_inode->i_mapping;
struct bio *bio;
struct page *page;
unsigned int max_pages;
int i;
max_pages = min(nr_pages, (size_t) bio_get_nr_vecs(super->s_bdev));
bio = bio_alloc(GFP_NOFS, max_pages);
BUG_ON(!bio);
for (i = 0; i < nr_pages; i++) {
if (i >= max_pages) {
/* Block layer cannot split bios :( */
bio->bi_vcnt = i;
bio->bi_iter.bi_size = i * PAGE_SIZE;
bio->bi_bdev = super->s_bdev;
bio->bi_iter.bi_sector = ofs >> 9;
bio->bi_private = sb;
bio->bi_end_io = writeseg_end_io;
atomic_inc(&super->s_pending_writes);
submit_bio(WRITE, bio);
ofs += i * PAGE_SIZE;
index += i;
nr_pages -= i;
i = 0;
bio = bio_alloc(GFP_NOFS, max_pages);
BUG_ON(!bio);
}
page = find_lock_page(mapping, index + i);
BUG_ON(!page);
bio->bi_io_vec[i].bv_page = page;
bio->bi_io_vec[i].bv_len = PAGE_SIZE;
bio->bi_io_vec[i].bv_offset = 0;
BUG_ON(PageWriteback(page));
set_page_writeback(page);
unlock_page(page);
}
bio->bi_vcnt = nr_pages;
bio->bi_iter.bi_size = nr_pages * PAGE_SIZE;
bio->bi_bdev = super->s_bdev;
bio->bi_iter.bi_sector = ofs >> 9;
bio->bi_private = sb;
bio->bi_end_io = writeseg_end_io;
atomic_inc(&super->s_pending_writes);
submit_bio(WRITE, bio);
return 0;
}
static void bdev_writeseg(struct super_block *sb, u64 ofs, size_t len)
{
struct logfs_super *super = logfs_super(sb);
int head;
BUG_ON(super->s_flags & LOGFS_SB_FLAG_RO);
if (len == 0) {
/* This can happen when the object fit perfectly into a
* segment, the segment gets written per sync and subsequently
* closed.
*/
return;
}
head = ofs & (PAGE_SIZE - 1);
if (head) {
ofs -= head;
len += head;
}
len = PAGE_ALIGN(len);
__bdev_writeseg(sb, ofs, ofs >> PAGE_SHIFT, len >> PAGE_SHIFT);
}
static void erase_end_io(struct bio *bio, int err)
{
const int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
struct super_block *sb = bio->bi_private;
struct logfs_super *super = logfs_super(sb);
BUG_ON(!uptodate); /* FIXME: Retry io or write elsewhere */
BUG_ON(err);
BUG_ON(bio->bi_vcnt == 0);
bio_put(bio);
if (atomic_dec_and_test(&super->s_pending_writes))
wake_up(&wq);
}
static int do_erase(struct super_block *sb, u64 ofs, pgoff_t index,
size_t nr_pages)
{
struct logfs_super *super = logfs_super(sb);
struct bio *bio;
unsigned int max_pages;
int i;
max_pages = min(nr_pages, (size_t) bio_get_nr_vecs(super->s_bdev));
bio = bio_alloc(GFP_NOFS, max_pages);
BUG_ON(!bio);
for (i = 0; i < nr_pages; i++) {
if (i >= max_pages) {
/* Block layer cannot split bios :( */
bio->bi_vcnt = i;
bio->bi_iter.bi_size = i * PAGE_SIZE;
bio->bi_bdev = super->s_bdev;
bio->bi_iter.bi_sector = ofs >> 9;
bio->bi_private = sb;
bio->bi_end_io = erase_end_io;
atomic_inc(&super->s_pending_writes);
submit_bio(WRITE, bio);
ofs += i * PAGE_SIZE;
index += i;
nr_pages -= i;
i = 0;
bio = bio_alloc(GFP_NOFS, max_pages);
BUG_ON(!bio);
}
bio->bi_io_vec[i].bv_page = super->s_erase_page;
bio->bi_io_vec[i].bv_len = PAGE_SIZE;
bio->bi_io_vec[i].bv_offset = 0;
}
bio->bi_vcnt = nr_pages;
bio->bi_iter.bi_size = nr_pages * PAGE_SIZE;
bio->bi_bdev = super->s_bdev;
bio->bi_iter.bi_sector = ofs >> 9;
bio->bi_private = sb;
bio->bi_end_io = erase_end_io;
atomic_inc(&super->s_pending_writes);
submit_bio(WRITE, bio);
return 0;
}
static int bdev_erase(struct super_block *sb, loff_t to, size_t len,
int ensure_write)
{
struct logfs_super *super = logfs_super(sb);
BUG_ON(to & (PAGE_SIZE - 1));
BUG_ON(len & (PAGE_SIZE - 1));
if (super->s_flags & LOGFS_SB_FLAG_RO)
return -EROFS;
if (ensure_write) {
/*
* Object store doesn't care whether erases happen or not.
* But for the journal they are required. Otherwise a scan
* can find an old commit entry and assume it is the current
* one, travelling back in time.
*/
do_erase(sb, to, to >> PAGE_SHIFT, len >> PAGE_SHIFT);
}
return 0;
}
static void bdev_sync(struct super_block *sb)
{
struct logfs_super *super = logfs_super(sb);
wait_event(wq, atomic_read(&super->s_pending_writes) == 0);
}
static struct page *bdev_find_first_sb(struct super_block *sb, u64 *ofs)
{
struct logfs_super *super = logfs_super(sb);
struct address_space *mapping = super->s_mapping_inode->i_mapping;
filler_t *filler = bdev_readpage;
*ofs = 0;
return read_cache_page(mapping, 0, filler, sb);
}
static struct page *bdev_find_last_sb(struct super_block *sb, u64 *ofs)
{
struct logfs_super *super = logfs_super(sb);
struct address_space *mapping = super->s_mapping_inode->i_mapping;
filler_t *filler = bdev_readpage;
u64 pos = (super->s_bdev->bd_inode->i_size & ~0xfffULL) - 0x1000;
pgoff_t index = pos >> PAGE_SHIFT;
*ofs = pos;
return read_cache_page(mapping, index, filler, sb);
}
static int bdev_write_sb(struct super_block *sb, struct page *page)
{
struct block_device *bdev = logfs_super(sb)->s_bdev;
/* Nothing special to do for block devices. */
return sync_request(page, bdev, WRITE);
}
static void bdev_put_device(struct logfs_super *s)
{
blkdev_put(s->s_bdev, FMODE_READ|FMODE_WRITE|FMODE_EXCL);
}
static int bdev_can_write_buf(struct super_block *sb, u64 ofs)
{
return 0;
}
static const struct logfs_device_ops bd_devops = {
.find_first_sb = bdev_find_first_sb,
.find_last_sb = bdev_find_last_sb,
.write_sb = bdev_write_sb,
.readpage = bdev_readpage,
.writeseg = bdev_writeseg,
.erase = bdev_erase,
.can_write_buf = bdev_can_write_buf,
.sync = bdev_sync,
.put_device = bdev_put_device,
};
int logfs_get_sb_bdev(struct logfs_super *p, struct file_system_type *type,
const char *devname)
{
struct block_device *bdev;
bdev = blkdev_get_by_path(devname, FMODE_READ|FMODE_WRITE|FMODE_EXCL,
type);
if (IS_ERR(bdev))
return PTR_ERR(bdev);
if (MAJOR(bdev->bd_dev) == MTD_BLOCK_MAJOR) {
int mtdnr = MINOR(bdev->bd_dev);
blkdev_put(bdev, FMODE_READ|FMODE_WRITE|FMODE_EXCL);
return logfs_get_sb_mtd(p, mtdnr);
}
p->s_bdev = bdev;
p->s_mtd = NULL;
p->s_devops = &bd_devops;
return 0;
}