static int gfs2_read_super(struct gfs2_sbd *sdp, sector_t sector, int silent)
{
struct super_block *sb = sdp->sd_vfs;
struct gfs2_sb *p;
struct page *page;
struct bio *bio;
page = alloc_page(GFP_NOFS);
if (unlikely(!page))
return -ENOBUFS;
ClearPageUptodate(page);
ClearPageDirty(page);
lock_page(page);
bio = bio_alloc(GFP_NOFS, 1);
bio->bi_sector = sector * (sb->s_blocksize >> 9);
bio->bi_bdev = sb->s_bdev;
bio_add_page(bio, page, PAGE_SIZE, 0);
bio->bi_end_io = end_bio_io_page;
bio->bi_private = page;
submit_bio(READ_SYNC | REQ_META, bio);
wait_on_page_locked(page);
bio_put(bio);
if (!PageUptodate(page)) {
__free_page(page);
return -EIO;
}
p = kmap(page);
gfs2_sb_in(sdp, p);
kunmap(page);
__free_page(page);
return gfs2_check_sb(sdp, silent);
}
/**
* submit - submit BIO request
* @writing: READ or WRITE.
* @dev: The block device we're using.
* @first_block: The first sector we're using.
* @page: The page being used for I/O.
* @free_group: If writing, the group that was used in allocating the page
* and which will be used in freeing the page from the completion
* routine.
*
* Based on Patrick Mochell's pmdisk code from long ago: "Straight from the
* textbook - allocate and initialize the bio. If we're writing, make sure
* the page is marked as dirty. Then submit it and carry on."
*
* If we're just testing the speed of our own code, we fake having done all
* the hard work and all toi_end_bio immediately.
**/
static int submit(int writing, struct block_device *dev, sector_t first_block,
struct page *page, int free_group)
{
struct bio *bio = NULL;
int cur_outstanding_io, result;
/*
* Shouldn't throttle if reading - can deadlock in the single
* threaded case as pages are only freed when we use the
* readahead.
*/
if (writing) {
result = throttle_if_needed(MEMORY_ONLY | THROTTLE_WAIT);
if (result)
return result;
}
while (!bio) {
bio = bio_alloc(TOI_ATOMIC_GFP, 1);
if (!bio) {
set_free_mem_throttle();
do_bio_wait(1);
}
}
bio->bi_bdev = dev;
bio->bi_sector = first_block;
bio->bi_private = (void *)((unsigned long)free_group);
bio->bi_end_io = toi_end_bio;
bio->bi_flags |= (1 << BIO_TOI);
if (bio_add_page(bio, page, PAGE_SIZE, 0) < PAGE_SIZE) {
printk(KERN_DEBUG "ERROR: adding page to bio at %lld\n",
(unsigned long long)first_block);
bio_put(bio);
return -EFAULT;
}
bio_get(bio);
cur_outstanding_io = atomic_add_return(1, &toi_io_in_progress);
if (writing) {
if (cur_outstanding_io > max_outstanding_writes)
max_outstanding_writes = cur_outstanding_io;
} else {
if (cur_outstanding_io > max_outstanding_reads)
max_outstanding_reads = cur_outstanding_io;
}
/* Still read the header! */
if (unlikely(test_action_state(TOI_TEST_BIO) && writing)) {
/* Fake having done the hard work */
set_bit(BIO_UPTODATE, &bio->bi_flags);
toi_end_bio(bio, 0);
} else
submit_bio(writing | REQ_SYNC, bio);
return 0;
}
static int submit(int rw, pgoff_t page_off, void * page)
{
int error = 0;
struct bio * bio;
bio = bio_alloc(GFP_ATOMIC,1);
if (!bio)
return -ENOMEM;
bio->bi_sector = page_off * (PAGE_SIZE >> 9);
bio_get(bio);
bio->bi_bdev = resume_bdev;
bio->bi_end_io = end_io;
if (bio_add_page(bio, virt_to_page(page), PAGE_SIZE, 0) < PAGE_SIZE) {
printk("pmdisk: ERROR: adding page to bio at %ld\n",page_off);
error = -EFAULT;
goto Done;
}
if (rw == WRITE)
bio_set_pages_dirty(bio);
start_io();
submit_bio(rw | (1 << BIO_RW_SYNC), bio);
wait_io();
Done:
bio_put(bio);
return error;
}
static struct bio *get_failover_bio(struct path *path, unsigned data_size)
{
struct bio *bio;
struct page *page;
bio = bio_alloc(GFP_ATOMIC, 1);
if (!bio) {
DMERR("dm-emc: get_failover_bio: bio_alloc() failed.");
return NULL;
}
bio->bi_rw |= (1 << BIO_RW);
bio->bi_bdev = path->dev->bdev;
bio->bi_sector = 0;
bio->bi_private = path;
bio->bi_end_io = emc_endio;
page = alloc_page(GFP_ATOMIC);
if (!page) {
DMERR("dm-emc: get_failover_bio: alloc_page() failed.");
bio_put(bio);
return NULL;
}
if (bio_add_page(bio, page, data_size, 0) != data_size) {
DMERR("dm-emc: get_failover_bio: alloc_page() failed.");
__free_page(page);
bio_put(bio);
return NULL;
}
return bio;
}
static int test_bio_add_page(void)
{
int res = 0 , i = 0 , offset = 0;
unsigned long addr = 0;
struct page *ppage = NULL;
for (i = 0 ; i < 128 ; i ++) {
addr = get_zeroed_page(GFP_KERNEL);
if(addr == 0) {
printk("tbio: get free page failed %ld\n" , addr);
return -1;
}
ppage = virt_to_page(addr);
if ( ppage == NULL ) {
printk ("tbio: covert virture page to page struct failed\n");
return -1;
}
res = bio_add_page(tbiop , ppage , PAGE_SIZE , offset );
if (res <0 ) {
printk("bio_add_page :res %d\n",res);
return -1;
}
offset += res;
// printk ("tbio: bio_add_page : %d\n", res);
}
return 0;
}
static
int
xixfs_raw_submit(
struct block_device *bdev,
sector_t startsector,
int32 size,
int32 sectorsize,
PXIX_BUF xbuf,
int32 rw)
{
struct bio * bio;
int ret = 0;
bio = bio_alloc(GFP_NOIO, 1);
bio->bi_sector = startsector;
bio->bi_bdev = bdev;
bio_add_page(bio, xbuf->xix_page, size, xbuf->xixcore_buffer.xcb_offset);
bio->bi_private = (void *)xbuf;
bio->bi_end_io = end_bio_xbuf_io_async;
bio->bi_rw = rw;
bio_get(bio);
submit_bio(rw, bio);
if(bio_flagged(bio, BIO_EOPNOTSUPP))
ret = -EOPNOTSUPP;
bio_put(bio);
return ret;
}
static int test_bio_add_page(void)
{
int ret = 0, i = 0, offset = 0;
unsigned long addr = 0;
struct page *ppage = NULL;
for (i = 0; i < 128; i++) {
addr = get_zeroed_page(GFP_KERNEL);
if (addr == 0) {
prk_err("get free page failed %ld", addr);
ret = -1;
break;
}
ppage = virt_to_page(addr);
if (ppage == NULL) {
prk_err("covert virture page to page struct failed");
ret = -1;
break;
}
ret = bio_add_page(tbiop, ppage, PAGE_SIZE, offset);
if (ret < 0) {
prk_err("bio_add_page failed");
break;
}
offset += ret;
}
return ret;
}
int hfsplus_submit_bio(struct block_device *bdev, sector_t sector,
void *data, int rw)
{
DECLARE_COMPLETION_ONSTACK(wait);
struct bio *bio;
bio = bio_alloc(GFP_NOIO, 1);
bio->bi_sector = sector;
bio->bi_bdev = bdev;
bio->bi_end_io = hfsplus_end_io_sync;
bio->bi_private = &wait;
/*
* We always submit one sector at a time, so bio_add_page must not fail.
*/
if (bio_add_page(bio, virt_to_page(data), HFSPLUS_SECTOR_SIZE,
offset_in_page(data)) != HFSPLUS_SECTOR_SIZE)
BUG();
submit_bio(rw, bio);
wait_for_completion(&wait);
if (!bio_flagged(bio, BIO_UPTODATE))
return -EIO;
return 0;
}
/**
* Allocate a bio with pages.
*
* @size size in bytes.
*
* You must set bi_bdev, bi_opf, bi_iter by yourself.
* bi_iter.bi_size will be set to the specified size if size is not 0.
*/
struct bio* bio_alloc_with_pages(uint size, struct block_device *bdev, gfp_t gfp_mask)
{
struct bio *bio;
uint i, nr_pages, remaining;
nr_pages = (size + PAGE_SIZE - 1) / PAGE_SIZE;
bio = bio_alloc(gfp_mask, nr_pages);
if (!bio)
return NULL;
bio->bi_bdev = bdev; /* required to bio_add_page(). */
remaining = size;
for (i = 0; i < nr_pages; i++) {
uint len0, len1;
struct page *page = alloc_page_inc(gfp_mask);
if (!page)
goto err;
len0 = min_t(uint, PAGE_SIZE, remaining);
len1 = bio_add_page(bio, page, len0, 0);
ASSERT(len0 == len1);
remaining -= len0;
}
ASSERT(remaining == 0);
ASSERT(bio->bi_iter.bi_size == size);
return bio;
err:
bio_put_with_pages(bio);
return NULL;
}
int fscrypt_zeroout_range(const struct inode *inode, pgoff_t lblk,
sector_t pblk, unsigned int len)
{
struct fscrypt_ctx *ctx;
struct page *ciphertext_page = NULL;
struct bio *bio;
int ret, err = 0;
BUG_ON(inode->i_sb->s_blocksize != PAGE_SIZE);
ctx = fscrypt_get_ctx(inode, GFP_NOFS);
if (IS_ERR(ctx))
return PTR_ERR(ctx);
ciphertext_page = fscrypt_alloc_bounce_page(ctx, GFP_NOWAIT);
if (IS_ERR(ciphertext_page)) {
err = PTR_ERR(ciphertext_page);
goto errout;
}
while (len--) {
err = fscrypt_do_page_crypto(inode, FS_ENCRYPT, lblk,
ZERO_PAGE(0), ciphertext_page,
PAGE_SIZE, 0, GFP_NOFS);
if (err)
goto errout;
bio = bio_alloc(GFP_NOWAIT, 1);
if (!bio) {
err = -ENOMEM;
goto errout;
}
bio_set_dev(bio, inode->i_sb->s_bdev);
bio->bi_iter.bi_sector =
pblk << (inode->i_sb->s_blocksize_bits - 9);
bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
ret = bio_add_page(bio, ciphertext_page,
inode->i_sb->s_blocksize, 0);
if (ret != inode->i_sb->s_blocksize) {
/* should never happen! */
WARN_ON(1);
bio_put(bio);
err = -EIO;
goto errout;
}
err = submit_bio_wait(bio);
if (err == 0 && bio->bi_status)
err = -EIO;
bio_put(bio);
if (err)
goto errout;
lblk++;
pblk++;
}
err = 0;
errout:
fscrypt_release_ctx(ctx);
return err;
}
STATIC int _drbd_md_sync_page_io(struct drbd_conf *mdev,
struct drbd_backing_dev *bdev,
struct page *page, sector_t sector,
int rw, int size)
{
struct bio *bio;
struct drbd_md_io md_io;
int ok;
md_io.mdev = mdev;
init_completion(&md_io.event);
md_io.error = 0;
if ((rw & WRITE) && !test_bit(MD_NO_BARRIER, &mdev->flags))
rw |= DRBD_REQ_FUA | DRBD_REQ_FLUSH;
rw |= DRBD_REQ_UNPLUG | DRBD_REQ_SYNC;
#ifndef REQ_FLUSH
/* < 2.6.36, "barrier" semantic may fail with EOPNOTSUPP */
retry:
#endif
bio = bio_alloc(GFP_NOIO, 1);
bio->bi_bdev = bdev->md_bdev;
bio->bi_sector = sector;
ok = (bio_add_page(bio, page, size, 0) == size);
if (!ok)
goto out;
bio->bi_private = &md_io;
bio->bi_end_io = drbd_md_io_complete;
bio->bi_rw = rw;
trace_drbd_bio(mdev, "Md", bio, 0, NULL);
if (drbd_insert_fault(mdev, (rw & WRITE) ? DRBD_FAULT_MD_WR : DRBD_FAULT_MD_RD))
bio_endio(bio, -EIO);
else
submit_bio(rw, bio);
wait_for_completion(&md_io.event);
ok = bio_flagged(bio, BIO_UPTODATE) && md_io.error == 0;
#ifndef REQ_FLUSH
/* check for unsupported barrier op.
* would rather check on EOPNOTSUPP, but that is not reliable.
* don't try again for ANY return value != 0 */
if (unlikely((bio->bi_rw & DRBD_REQ_HARDBARRIER) && !ok)) {
/* Try again with no barrier */
dev_warn(DEV, "Barriers not supported on meta data device - disabling\n");
set_bit(MD_NO_BARRIER, &mdev->flags);
rw &= ~DRBD_REQ_HARDBARRIER;
bio_put(bio);
goto retry;
}
#endif
out:
bio_put(bio);
return ok;
}
/*
* hfsplus_submit_bio - Perfrom block I/O
* @sb: super block of volume for I/O
* @sector: block to read or write, for blocks of HFSPLUS_SECTOR_SIZE bytes
* @buf: buffer for I/O
* @data: output pointer for location of requested data
* @rw: direction of I/O
*
* The unit of I/O is hfsplus_min_io_size(sb), which may be bigger than
* HFSPLUS_SECTOR_SIZE, and @buf must be sized accordingly. On reads
* @data will return a pointer to the start of the requested sector,
* which may not be the same location as @buf.
*
* If @sector is not aligned to the bdev logical block size it will
* be rounded down. For writes this means that @buf should contain data
* that starts at the rounded-down address. As long as the data was
* read using hfsplus_submit_bio() and the same buffer is used things
* will work correctly.
*/
int hfsplus_submit_bio(struct super_block *sb, sector_t sector,
void *buf, void **data, int rw)
{
DECLARE_COMPLETION_ONSTACK(wait);
struct bio *bio;
int ret = 0;
u64 io_size;
loff_t start;
int offset;
/*
* Align sector to hardware sector size and find offset. We
* assume that io_size is a power of two, which _should_
* be true.
*/
io_size = hfsplus_min_io_size(sb);
start = (loff_t)sector << HFSPLUS_SECTOR_SHIFT;
offset = start & (io_size - 1);
sector &= ~((io_size >> HFSPLUS_SECTOR_SHIFT) - 1);
bio = bio_alloc(GFP_NOIO, 1);
bio->bi_sector = sector;
bio->bi_bdev = sb->s_bdev;
bio->bi_end_io = hfsplus_end_io_sync;
bio->bi_private = &wait;
if (!(rw & WRITE) && data)
*data = (u8 *)buf + offset;
while (io_size > 0) {
unsigned int page_offset = offset_in_page(buf);
unsigned int len = min_t(unsigned int, PAGE_SIZE - page_offset,
io_size);
ret = bio_add_page(bio, virt_to_page(buf), len, page_offset);
if (ret != len) {
ret = -EIO;
goto out;
}
io_size -= len;
buf = (u8 *)buf + len;
}
submit_bio(rw, bio);
wait_for_completion(&wait);
if (!bio_flagged(bio, BIO_UPTODATE))
ret = -EIO;
out:
bio_put(bio);
return ret < 0 ? ret : 0;
}
int ext4_encrypted_zeroout(struct inode *inode, struct ext4_extent *ex)
{
struct ext4_crypto_ctx *ctx;
struct page *ciphertext_page = NULL;
struct bio *bio;
ext4_lblk_t lblk = ex->ee_block;
ext4_fsblk_t pblk = ext4_ext_pblock(ex);
unsigned int len = ext4_ext_get_actual_len(ex);
int err = 0;
BUG_ON(inode->i_sb->s_blocksize != PAGE_CACHE_SIZE);
ctx = ext4_get_crypto_ctx(inode);
if (IS_ERR(ctx))
return PTR_ERR(ctx);
ciphertext_page = alloc_bounce_page(ctx);
if (IS_ERR(ciphertext_page)) {
err = PTR_ERR(ciphertext_page);
goto errout;
}
while (len--) {
err = ext4_page_crypto(ctx, inode, EXT4_ENCRYPT, lblk,
ZERO_PAGE(0), ciphertext_page);
if (err)
goto errout;
bio = bio_alloc(GFP_KERNEL, 1);
if (!bio) {
err = -ENOMEM;
goto errout;
}
bio->bi_bdev = inode->i_sb->s_bdev;
bio->bi_sector = pblk;
err = bio_add_page(bio, ciphertext_page,
inode->i_sb->s_blocksize, 0);
if (err) {
bio_put(bio);
goto errout;
}
err = submit_bio_wait(WRITE, bio);
bio_put(bio);
if (err)
goto errout;
}
err = 0;
errout:
ext4_release_crypto_ctx(ctx);
return err;
}
static int io_submit_add_bh(struct ext4_io_submit *io,
struct ext4_io_page *io_page,
struct inode *inode,
struct writeback_control *wbc,
struct buffer_head *bh)
{
ext4_io_end_t *io_end;
int ret;
if (buffer_new(bh)) {
clear_buffer_new(bh);
unmap_underlying_metadata(bh->b_bdev, bh->b_blocknr);
}
if (!buffer_mapped(bh) || buffer_delay(bh)) {
if (!buffer_mapped(bh))
clear_buffer_dirty(bh);
if (io->io_bio)
ext4_io_submit(io);
return 0;
}
if (io->io_bio && bh->b_blocknr != io->io_next_block) {
submit_and_retry:
ext4_io_submit(io);
}
if (io->io_bio == NULL) {
ret = io_submit_init(io, inode, wbc, bh);
if (ret)
return ret;
}
io_end = io->io_end;
if ((io_end->num_io_pages >= MAX_IO_PAGES) &&
(io_end->pages[io_end->num_io_pages-1] != io_page))
goto submit_and_retry;
if (buffer_uninit(bh) && !(io_end->flag & EXT4_IO_END_UNWRITTEN)) {
io_end->flag |= EXT4_IO_END_UNWRITTEN;
atomic_inc(&EXT4_I(inode)->i_aiodio_unwritten);
}
io->io_end->size += bh->b_size;
io->io_next_block++;
ret = bio_add_page(io->io_bio, bh->b_page, bh->b_size, bh_offset(bh));
if (ret != bh->b_size)
goto submit_and_retry;
if ((io_end->num_io_pages == 0) ||
(io_end->pages[io_end->num_io_pages-1] != io_page)) {
io_end->pages[io_end->num_io_pages++] = io_page;
atomic_inc(&io_page->p_count);
}
return 0;
}
/*-----------------------------------------------------------------
* IO routines that accept a list of pages.
*---------------------------------------------------------------*/
static void do_region(int rw, unsigned region, struct dm_io_region *where,
struct dpages *dp, struct io *io)
{
struct bio *bio;
struct page *page;
unsigned long len;
unsigned offset;
unsigned num_bvecs;
sector_t remaining = where->count;
/*
* where->count may be zero if rw holds a flush and we need to
* send a zero-sized flush.
*/
do {
/*
* Allocate a suitably sized-bio.
*/
num_bvecs = dm_sector_div_up(remaining,
(PAGE_SIZE >> SECTOR_SHIFT));
num_bvecs = min_t(int, bio_get_nr_vecs(where->bdev), num_bvecs);
bio = bio_alloc_bioset(GFP_NOIO, num_bvecs, io->client->bios);
if (!bio) {
printk(KERN_WARNING "%s : %s() failed\n", __FILE__, __func__);
BUG_ON(1);
}
bio->bi_sector = where->sector + (where->count - remaining);
bio->bi_bdev = where->bdev;
bio->bi_end_io = endio;
bio->bi_destructor = dm_bio_destructor;
store_io_and_region_in_bio(bio, io, region);
/*
* Try and add as many pages as possible.
*/
while (remaining) {
dp->get_page(dp, &page, &len, &offset);
len = min(len, to_bytes(remaining));
if (!bio_add_page(bio, page, len, offset))
break;
offset = 0;
remaining -= to_sector(len);
dp->next_page(dp);
}
atomic_inc(&io->count);
submit_bio(rw, bio);
} while (remaining);
}
struct bio * _do_readpage_aio(struct page *page)
{
DD("_do_readpage_aio.");
if(page == NULL)
{
return NULL;
}
struct bio *bio = make_bio();
bio_add_page(bio, page, BIO_READ);
return bio;
}
static int write_metadata(struct log_writes_c *lc, void *entry,
size_t entrylen, void *data, size_t datalen,
sector_t sector)
{
struct bio *bio;
struct page *page;
void *ptr;
size_t ret;
bio = bio_alloc(GFP_KERNEL, 1);
if (!bio) {
DMERR("Couldn't alloc log bio");
goto error;
}
bio->bi_iter.bi_size = 0;
bio->bi_iter.bi_sector = sector;
bio->bi_bdev = lc->logdev->bdev;
bio->bi_end_io = log_end_io;
bio->bi_private = lc;
bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
page = alloc_page(GFP_KERNEL);
if (!page) {
DMERR("Couldn't alloc log page");
bio_put(bio);
goto error;
}
ptr = kmap_atomic(page);
memcpy(ptr, entry, entrylen);
if (datalen)
memcpy(ptr + entrylen, data, datalen);
memset(ptr + entrylen + datalen, 0,
lc->sectorsize - entrylen - datalen);
kunmap_atomic(ptr);
ret = bio_add_page(bio, page, lc->sectorsize, 0);
if (ret != lc->sectorsize) {
DMERR("Couldn't add page to the log block");
goto error_bio;
}
submit_bio(bio);
return 0;
error_bio:
bio_put(bio);
__free_page(page);
error:
put_io_block(lc);
return -1;
}
static struct bio* kr_create_bio(KrDevice* dev, struct page* page, int sector)
{
struct bio* bio = bio_alloc(GFP_NOIO, 1);
if (!bio)
return NULL;
/* setup bio. */
bio->bi_bdev = dev->bdev;
bio->bi_sector = sector;
bio_add_page(bio, page, KR_BLOCK_SIZE, 0);
return bio;
}
/*
* Generate a new unfragmented bio with the given size
* This should never violate the device limitations
* May return a smaller bio when running out of pages, indicated by
* *out_of_pages set to 1.
*/
static struct bio *crypt_alloc_buffer(struct dm_crypt_io *io, unsigned size,
unsigned *out_of_pages)
{
struct crypt_config *cc = io->cc;
struct bio *clone;
unsigned int nr_iovecs = (size + PAGE_SIZE - 1) >> PAGE_SHIFT;
gfp_t gfp_mask = GFP_NOIO | __GFP_HIGHMEM;
unsigned i, len;
struct page *page;
clone = bio_alloc_bioset(GFP_NOIO, nr_iovecs, cc->bs);
if (!clone)
return NULL;
clone_init(io, clone);
*out_of_pages = 0;
for (i = 0; i < nr_iovecs; i++) {
page = mempool_alloc(cc->page_pool, gfp_mask);
if (!page) {
*out_of_pages = 1;
break;
}
/*
* If additional pages cannot be allocated without waiting,
* return a partially-allocated bio. The caller will then try
* to allocate more bios while submitting this partial bio.
*/
gfp_mask = (gfp_mask | __GFP_NOWARN) & ~__GFP_WAIT;
len = (size > PAGE_SIZE) ? PAGE_SIZE : size;
if (!bio_add_page(clone, page, len, 0)) {
mempool_free(page, cc->page_pool);
break;
}
size -= len;
}
if (!clone->bi_size) {
bio_put(clone);
return NULL;
}
return clone;
}
static 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.error = 0;
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 (bb.error)
return bb.error;
return ret;
}
static struct bio *get_swap_bio(gfp_t gfp_flags,
struct page *page, bio_end_io_t end_io)
{
struct bio *bio;
bio = bio_alloc(gfp_flags, 1);
if (bio) {
bio->bi_iter.bi_sector = map_swap_page(page, &bio->bi_bdev);
bio->bi_iter.bi_sector <<= PAGE_SHIFT - 9;
bio->bi_end_io = end_io;
bio_add_page(bio, page, PAGE_SIZE, 0);
BUG_ON(bio->bi_iter.bi_size != PAGE_SIZE);
}
return bio;
}
static void do_region(int rw, unsigned region, struct dm_io_region *where,
struct dpages *dp, struct io *io)
{
struct bio *bio;
struct page *page;
unsigned long len;
unsigned offset;
unsigned num_bvecs;
sector_t remaining = where->count;
struct request_queue *q = bdev_get_queue(where->bdev);
sector_t discard_sectors;
do {
if (rw & REQ_DISCARD)
num_bvecs = 1;
else
num_bvecs = min_t(int, bio_get_nr_vecs(where->bdev),
dm_sector_div_up(remaining, (PAGE_SIZE >> SECTOR_SHIFT)));
bio = bio_alloc_bioset(GFP_NOIO, num_bvecs, io->client->bios);
bio->bi_sector = where->sector + (where->count - remaining);
bio->bi_bdev = where->bdev;
bio->bi_end_io = endio;
bio->bi_destructor = dm_bio_destructor;
store_io_and_region_in_bio(bio, io, region);
if (rw & REQ_DISCARD) {
discard_sectors = min_t(sector_t, q->limits.max_discard_sectors, remaining);
bio->bi_size = discard_sectors << SECTOR_SHIFT;
remaining -= discard_sectors;
} else while (remaining) {
dp->get_page(dp, &page, &len, &offset);
len = min(len, to_bytes(remaining));
if (!bio_add_page(bio, page, len, offset))
break;
offset = 0;
remaining -= to_sector(len);
dp->next_page(dp);
}
atomic_inc(&io->count);
submit_bio(rw, bio);
} while (remaining);
}
/*
* Fill the locked page with data located in the block address.
* Return unlocked page.
*/
int f2fs_submit_page_bio(struct f2fs_io_info *fio)
{
struct bio *bio;
struct page *page = fio->encrypted_page ? fio->encrypted_page : fio->page;
trace_f2fs_submit_page_bio(page, fio);
f2fs_trace_ios(fio, 0);
/* Allocate a new bio */
bio = __bio_alloc(fio->sbi, fio->blk_addr, 1, is_read_io(fio->rw));
if (bio_add_page(bio, page, PAGE_CACHE_SIZE, 0) < PAGE_CACHE_SIZE) {
bio_put(bio);
return -EFAULT;
}
submit_bio(fio->rw, bio);
return 0;
}
void f2fs_submit_page_mbio(struct f2fs_io_info *fio)
{
struct f2fs_sb_info *sbi = fio->sbi;
enum page_type btype = PAGE_TYPE_OF_BIO(fio->type);
struct f2fs_bio_info *io;
bool is_read = is_read_io(fio->rw);
struct page *bio_page;
io = is_read ? &sbi->read_io : &sbi->write_io[btype];
verify_block_addr(sbi, fio->blk_addr);
down_write(&io->io_rwsem);
if (!is_read)
inc_page_count(sbi, F2FS_WRITEBACK);
if (io->bio && (io->last_block_in_bio != fio->blk_addr - 1 ||
io->fio.rw != fio->rw))
__submit_merged_bio(io);
alloc_new:
if (io->bio == NULL) {
int bio_blocks = MAX_BIO_BLOCKS(sbi);
io->bio = __bio_alloc(sbi, fio->blk_addr, bio_blocks, is_read);
io->fio = *fio;
}
bio_page = fio->encrypted_page ? fio->encrypted_page : fio->page;
if (bio_add_page(io->bio, bio_page, PAGE_CACHE_SIZE, 0) <
PAGE_CACHE_SIZE) {
__submit_merged_bio(io);
goto alloc_new;
}
io->last_block_in_bio = fio->blk_addr;
f2fs_trace_ios(fio, 0);
up_write(&io->io_rwsem);
trace_f2fs_submit_page_mbio(fio->page, fio);
}
/**
* blkmtd_add_page - add a page to the current BIO
* @bio: bio to add to (NULL to alloc initial bio)
* @blkdev: block device
* @page: page to add
* @pagecnt: pages left to add
*
* Adds a page to the current bio, allocating it if necessary. If it cannot be
* added, the current bio is written out and a new one is allocated. Returns
* the new bio to add or NULL on error
*/
static struct bio *blkmtd_add_page(struct bio *bio, struct block_device *blkdev,
struct page *page, int pagecnt)
{
retry:
if(!bio) {
bio = bio_alloc(GFP_KERNEL, pagecnt);
if(!bio)
return NULL;
bio->bi_sector = page->index << (PAGE_SHIFT-9);
bio->bi_bdev = blkdev;
}
if(bio_add_page(bio, page, PAGE_SIZE, 0) != PAGE_SIZE) {
blkmtd_write_out(bio);
bio = NULL;
goto retry;
}
return bio;
}
static int _drbd_md_sync_page_io(struct drbd_conf *mdev,
struct drbd_backing_dev *bdev,
struct page *page, sector_t sector,
int rw, int size)
{
struct bio *bio;
struct drbd_md_io md_io;
int ok;
md_io.mdev = mdev;
init_completion(&md_io.event);
md_io.error = 0;
if ((rw & WRITE) && !test_bit(MD_NO_FUA, &mdev->flags))
rw |= REQ_FUA;
rw |= REQ_UNPLUG | REQ_SYNC;
bio = bio_alloc(GFP_NOIO, 1);
bio->bi_bdev = bdev->md_bdev;
bio->bi_sector = sector;
ok = (bio_add_page(bio, page, size, 0) == size);
if (!ok)
goto out;
bio->bi_private = &md_io;
bio->bi_end_io = drbd_md_io_complete;
bio->bi_rw = rw;
if (FAULT_ACTIVE(mdev, (rw & WRITE) ? DRBD_FAULT_MD_WR : DRBD_FAULT_MD_RD))
bio_endio(bio, -EIO);
else
submit_bio(rw, bio);
wait_for_completion(&md_io.event);
ok = bio_flagged(bio, BIO_UPTODATE) && md_io.error == 0;
out:
bio_put(bio);
return ok;
}
/* read one page from the block device */
static int blkmtd_readpage(struct blkmtd_dev *dev, struct page *page)
{
struct bio *bio;
struct completion event;
int err = -ENOMEM;
if(PageUptodate(page)) {
DEBUG(2, "blkmtd: readpage page %ld is already upto date\n", page->index);
unlock_page(page);
return 0;
}
ClearPageUptodate(page);
ClearPageError(page);
bio = bio_alloc(GFP_KERNEL, 1);
if(bio) {
init_completion(&event);
bio->bi_bdev = dev->blkdev;
bio->bi_sector = page->index << (PAGE_SHIFT-9);
bio->bi_private = &event;
bio->bi_end_io = bi_read_complete;
if(bio_add_page(bio, page, PAGE_SIZE, 0) == PAGE_SIZE) {
submit_bio(READ_SYNC, bio);
wait_for_completion(&event);
err = test_bit(BIO_UPTODATE, &bio->bi_flags) ? 0 : -EIO;
bio_put(bio);
}
}
if(err)
SetPageError(page);
else
SetPageUptodate(page);
flush_dcache_page(page);
unlock_page(page);
return err;
}
/**
* submit - submit BIO request.
* @rw: READ or WRITE.
* @off physical offset of page.
* @page: page we're reading or writing.
* @bio_chain: list of pending biod (for async reading)
*
* Straight from the textbook - allocate and initialize the bio.
* If we're reading, make sure the page is marked as dirty.
* Then submit it and, if @bio_chain == NULL, wait.
*/
static int submit(int rw, struct block_device *bdev, sector_t sector,
struct page *page, struct bio **bio_chain)
{
const int bio_rw = rw | REQ_SYNC;
struct bio *bio;
bio = bio_alloc(__GFP_WAIT | __GFP_HIGH, 1);
bio->bi_sector = sector;
bio->bi_bdev = bdev;
bio->bi_end_io = end_swap_bio_read;
if (bio_add_page(bio, page, PAGE_SIZE, 0) < PAGE_SIZE) {
printk(KERN_ERR "PM: Adding page to bio failed at %llu\n",
(unsigned long long)sector);
bio_put(bio);
return -EFAULT;
}
lock_page(page);
bio_get(bio);
if (bio_chain == NULL) {
submit_bio(bio_rw, bio);
wait_on_page_locked(page);
if (rw == READ)
bio_set_pages_dirty(bio);
bio_put(bio);
} else {
if (rw == READ)
get_page(page); /* These pages are freed later */
bio->bi_private = *bio_chain;
*bio_chain = bio;
submit_bio(bio_rw, bio);
}
return 0;
}
int ext4_mpage_readpages(struct address_space *mapping,
struct list_head *pages, struct page *page,
unsigned nr_pages, bool is_readahead)
{
struct bio *bio = NULL;
sector_t last_block_in_bio = 0;
struct inode *inode = mapping->host;
const unsigned blkbits = inode->i_blkbits;
const unsigned blocks_per_page = PAGE_SIZE >> blkbits;
const unsigned blocksize = 1 << blkbits;
sector_t block_in_file;
sector_t last_block;
sector_t last_block_in_file;
sector_t blocks[MAX_BUF_PER_PAGE];
unsigned page_block;
struct block_device *bdev = inode->i_sb->s_bdev;
int length;
unsigned relative_block = 0;
struct ext4_map_blocks map;
map.m_pblk = 0;
map.m_lblk = 0;
map.m_len = 0;
map.m_flags = 0;
for (; nr_pages; nr_pages--) {
int fully_mapped = 1;
unsigned first_hole = blocks_per_page;
prefetchw(&page->flags);
if (pages) {
page = lru_to_page(pages);
list_del(&page->lru);
if (add_to_page_cache_lru(page, mapping, page->index,
readahead_gfp_mask(mapping)))
goto next_page;
}
if (page_has_buffers(page))
goto confused;
block_in_file = (sector_t)page->index << (PAGE_SHIFT - blkbits);
last_block = block_in_file + nr_pages * blocks_per_page;
last_block_in_file = (i_size_read(inode) + blocksize - 1) >> blkbits;
if (last_block > last_block_in_file)
last_block = last_block_in_file;
page_block = 0;
/*
* Map blocks using the previous result first.
*/
if ((map.m_flags & EXT4_MAP_MAPPED) &&
block_in_file > map.m_lblk &&
block_in_file < (map.m_lblk + map.m_len)) {
unsigned map_offset = block_in_file - map.m_lblk;
unsigned last = map.m_len - map_offset;
for (relative_block = 0; ; relative_block++) {
if (relative_block == last) {
/* needed? */
map.m_flags &= ~EXT4_MAP_MAPPED;
break;
}
if (page_block == blocks_per_page)
break;
blocks[page_block] = map.m_pblk + map_offset +
relative_block;
page_block++;
block_in_file++;
}
}
/*
* Then do more ext4_map_blocks() calls until we are
* done with this page.
*/
while (page_block < blocks_per_page) {
if (block_in_file < last_block) {
map.m_lblk = block_in_file;
map.m_len = last_block - block_in_file;
if (ext4_map_blocks(NULL, inode, &map, 0) < 0) {
set_error_page:
SetPageError(page);
zero_user_segment(page, 0,
PAGE_SIZE);
unlock_page(page);
goto next_page;
}
}
if ((map.m_flags & EXT4_MAP_MAPPED) == 0) {
fully_mapped = 0;
if (first_hole == blocks_per_page)
first_hole = page_block;
page_block++;
block_in_file++;
continue;
}
if (first_hole != blocks_per_page)
goto confused; /* hole -> non-hole */
/* Contiguous blocks? */
if (page_block && blocks[page_block-1] != map.m_pblk-1)
goto confused;
for (relative_block = 0; ; relative_block++) {
if (relative_block == map.m_len) {
/* needed? */
map.m_flags &= ~EXT4_MAP_MAPPED;
break;
} else if (page_block == blocks_per_page)
break;
blocks[page_block] = map.m_pblk+relative_block;
page_block++;
block_in_file++;
}
}
if (first_hole != blocks_per_page) {
zero_user_segment(page, first_hole << blkbits,
PAGE_SIZE);
if (first_hole == 0) {
SetPageUptodate(page);
unlock_page(page);
goto next_page;
}
} else if (fully_mapped) {
SetPageMappedToDisk(page);
}
if (fully_mapped && blocks_per_page == 1 &&
!PageUptodate(page) && cleancache_get_page(page) == 0) {
SetPageUptodate(page);
goto confused;
}
/*
* This page will go to BIO. Do we need to send this
* BIO off first?
*/
if (bio && (last_block_in_bio != blocks[0] - 1)) {
submit_and_realloc:
submit_bio(bio);
bio = NULL;
}
if (bio == NULL) {
struct fscrypt_ctx *ctx = NULL;
if (IS_ENCRYPTED(inode) && S_ISREG(inode->i_mode)) {
ctx = fscrypt_get_ctx(inode, GFP_NOFS);
if (IS_ERR(ctx))
goto set_error_page;
}
bio = bio_alloc(GFP_KERNEL,
min_t(int, nr_pages, BIO_MAX_PAGES));
if (!bio) {
if (ctx)
fscrypt_release_ctx(ctx);
goto set_error_page;
}
bio_set_dev(bio, bdev);
bio->bi_iter.bi_sector = blocks[0] << (blkbits - 9);
bio->bi_end_io = mpage_end_io;
bio->bi_private = ctx;
bio_set_op_attrs(bio, REQ_OP_READ,
is_readahead ? REQ_RAHEAD : 0);
}
length = first_hole << blkbits;
if (bio_add_page(bio, page, length, 0) < length)
goto submit_and_realloc;
if (((map.m_flags & EXT4_MAP_BOUNDARY) &&
(relative_block == map.m_len)) ||
(first_hole != blocks_per_page)) {
submit_bio(bio);
bio = NULL;
} else
last_block_in_bio = blocks[blocks_per_page - 1];
goto next_page;
confused:
if (bio) {
submit_bio(bio);
bio = NULL;
}
if (!PageUptodate(page))
block_read_full_page(page, ext4_get_block);
else
unlock_page(page);
next_page:
if (pages)
put_page(page);
}
BUG_ON(pages && !list_empty(pages));
if (bio)
submit_bio(bio);
return 0;
}
static int __mpage_writepage(struct page *page, struct writeback_control *wbc,
void *data)
{
struct mpage_data *mpd = data;
struct bio *bio = mpd->bio;
struct address_space *mapping = page->mapping;
struct inode *inode = page->mapping->host;
const unsigned blkbits = inode->i_blkbits;
unsigned long end_index;
const unsigned blocks_per_page = PAGE_CACHE_SIZE >> blkbits;
sector_t last_block;
sector_t block_in_file;
sector_t blocks[MAX_BUF_PER_PAGE];
unsigned page_block;
unsigned first_unmapped = blocks_per_page;
struct block_device *bdev = NULL;
int boundary = 0;
sector_t boundary_block = 0;
struct block_device *boundary_bdev = NULL;
int length;
struct buffer_head map_bh;
loff_t i_size = i_size_read(inode);
int ret = 0;
int wr = (wbc->sync_mode == WB_SYNC_ALL ? WRITE_SYNC : WRITE);
if (page_has_buffers(page)) {
struct buffer_head *head = page_buffers(page);
struct buffer_head *bh = head;
/* If they're all mapped and dirty, do it */
page_block = 0;
do {
BUG_ON(buffer_locked(bh));
if (!buffer_mapped(bh)) {
/*
* unmapped dirty buffers are created by
* __set_page_dirty_buffers -> mmapped data
*/
if (buffer_dirty(bh))
goto confused;
if (first_unmapped == blocks_per_page)
first_unmapped = page_block;
continue;
}
if (first_unmapped != blocks_per_page)
goto confused; /* hole -> non-hole */
if (!buffer_dirty(bh) || !buffer_uptodate(bh))
goto confused;
if (page_block) {
if (bh->b_blocknr != blocks[page_block-1] + 1)
goto confused;
}
blocks[page_block++] = bh->b_blocknr;
boundary = buffer_boundary(bh);
if (boundary) {
boundary_block = bh->b_blocknr;
boundary_bdev = bh->b_bdev;
}
bdev = bh->b_bdev;
} while ((bh = bh->b_this_page) != head);
if (first_unmapped)
goto page_is_mapped;
/*
* Page has buffers, but they are all unmapped. The page was
* created by pagein or read over a hole which was handled by
* block_read_full_page(). If this address_space is also
* using mpage_readpages then this can rarely happen.
*/
goto confused;
}
/*
* The page has no buffers: map it to disk
*/
BUG_ON(!PageUptodate(page));
block_in_file = (sector_t)page->index << (PAGE_CACHE_SHIFT - blkbits);
last_block = (i_size - 1) >> blkbits;
map_bh.b_page = page;
for (page_block = 0; page_block < blocks_per_page; ) {
map_bh.b_state = 0;
map_bh.b_size = 1 << blkbits;
if (mpd->get_block(inode, block_in_file, &map_bh, 1))
goto confused;
if (buffer_new(&map_bh))
unmap_underlying_metadata(map_bh.b_bdev,
map_bh.b_blocknr);
if (buffer_boundary(&map_bh)) {
boundary_block = map_bh.b_blocknr;
boundary_bdev = map_bh.b_bdev;
}
if (page_block) {
if (map_bh.b_blocknr != blocks[page_block-1] + 1)
goto confused;
}
blocks[page_block++] = map_bh.b_blocknr;
boundary = buffer_boundary(&map_bh);
bdev = map_bh.b_bdev;
if (block_in_file == last_block)
break;
block_in_file++;
}
BUG_ON(page_block == 0);
first_unmapped = page_block;
page_is_mapped:
end_index = i_size >> PAGE_CACHE_SHIFT;
if (page->index >= end_index) {
/*
* The page straddles i_size. It must be zeroed out on each
* and every writepage invocation because it may be mmapped.
* "A file is mapped in multiples of the page size. For a file
* that is not a multiple of the page size, the remaining memory
* is zeroed when mapped, and writes to that region are not
* written out to the file."
*/
unsigned offset = i_size & (PAGE_CACHE_SIZE - 1);
if (page->index > end_index || !offset)
goto confused;
zero_user_segment(page, offset, PAGE_CACHE_SIZE);
}
/*
* This page will go to BIO. Do we need to send this BIO off first?
*/
if (bio && mpd->last_block_in_bio != blocks[0] - 1)
bio = mpage_bio_submit(wr, bio);
alloc_new:
if (bio == NULL) {
if (first_unmapped == blocks_per_page) {
if (!bdev_write_page(bdev, blocks[0] << (blkbits - 9),
page, wbc)) {
clean_buffers(page, first_unmapped);
goto out;
}
}
bio = mpage_alloc(bdev, blocks[0] << (blkbits - 9),
BIO_MAX_PAGES, GFP_NOFS|__GFP_HIGH);
if (bio == NULL)
goto confused;
wbc_init_bio(wbc, bio);
}
/*
* Must try to add the page before marking the buffer clean or
* the confused fail path above (OOM) will be very confused when
* it finds all bh marked clean (i.e. it will not write anything)
*/
wbc_account_io(wbc, page, PAGE_SIZE);
length = first_unmapped << blkbits;
if (bio_add_page(bio, page, length, 0) < length) {
bio = mpage_bio_submit(wr, bio);
goto alloc_new;
}
clean_buffers(page, first_unmapped);
BUG_ON(PageWriteback(page));
set_page_writeback(page);
unlock_page(page);
if (boundary || (first_unmapped != blocks_per_page)) {
bio = mpage_bio_submit(wr, bio);
if (boundary_block) {
write_boundary_block(boundary_bdev,
boundary_block, 1 << blkbits);
}
} else {
mpd->last_block_in_bio = blocks[blocks_per_page - 1];
}
goto out;
confused:
if (bio)
bio = mpage_bio_submit(wr, bio);
if (mpd->use_writepage) {
ret = mapping->a_ops->writepage(page, wbc);
} else {
ret = -EAGAIN;
goto out;
}
/*
* The caller has a ref on the inode, so *mapping is stable
*/
mapping_set_error(mapping, ret);
out:
mpd->bio = bio;
return ret;
}
