/*
* We may have stale swap cache pages in memory: notice
* them here and get rid of the unnecessary final write.
*/
int swap_writepage(struct page *page, struct writeback_control *wbc)
{
struct bio *bio;
int ret = 0, rw = WRITE;
if (try_to_free_swap(page)) {
unlock_page(page);
goto out;
}
#ifdef CONFIG_FRONTSWAP
if (frontswap_store(page) == 0) {
set_page_writeback(page);
unlock_page(page);
end_page_writeback(page);
goto out;
}
#endif
bio = get_swap_bio(GFP_NOIO, page, end_swap_bio_write);
if (bio == NULL) {
set_page_dirty(page);
unlock_page(page);
ret = -ENOMEM;
goto out;
}
if (wbc->sync_mode == WB_SYNC_ALL)
rw |= REQ_SYNC;
count_vm_event(PSWPOUT);
set_page_writeback(page);
unlock_page(page);
submit_bio(rw, bio);
out:
return ret;
}
/*
* We may have stale swap cache pages in memory: notice
* them here and get rid of the unnecessary final write.
*/
int swap_writepage(struct page *page, struct writeback_control *wbc)
{
struct bio *bio;
int ret = 0, rw = WRITE;
if (try_to_free_swap(page)) {
unlock_page(page);
goto out;
}
if (frontswap_put_page(page) == 0) {
set_page_writeback(page);
unlock_page(page);
end_page_writeback(page);
goto out;
}
bio = get_swap_bio(GFP_NOIO, page, end_swap_bio_write);
if (bio == NULL) {
set_page_dirty(page);
unlock_page(page);
ret = -ENOMEM;
goto out;
}
if (wbc->sync_mode == WB_SYNC_ALL)
rw |= (1 << BIO_RW_SYNCIO) | (1 << BIO_RW_UNPLUG);
count_vm_event(PSWPOUT);
set_page_writeback(page);
unlock_page(page);
submit_bio(rw, bio);
out:
return ret;
}
static int rawfs_writepage(struct page *page, struct writeback_control *wbc)
{
struct address_space *mapping = page->mapping;
struct inode *inode;
unsigned long end_index;
char *buffer;
int n_written = 0;
unsigned n_bytes;
loff_t i_size;
if (!mapping)
BUG();
inode = mapping->host;
if (!inode)
BUG();
i_size = i_size_read(inode);
end_index = i_size >> PAGE_CACHE_SHIFT;
if (page->index < end_index)
n_bytes = PAGE_CACHE_SIZE;
else {
n_bytes = i_size & (PAGE_CACHE_SIZE - 1);
if (page->index > end_index || !n_bytes) {
zero_user_segment(page, 0, PAGE_CACHE_SIZE);
set_page_writeback(page);
unlock_page(page);
end_page_writeback(page);
return 0;
}
}
if (n_bytes != PAGE_CACHE_SIZE)
zero_user_segment(page, n_bytes, PAGE_CACHE_SIZE);
get_page(page);
buffer = kmap(page);
/* n_written = yaffs_wr_file(obj, buffer,
page->index << PAGE_CACHE_SHIFT, n_bytes, 0);
*/
n_written = rawfs_write_file(inode, buffer, n_bytes,
page->index << PAGE_CACHE_SHIFT);
kunmap(page);
set_page_writeback(page);
unlock_page(page);
end_page_writeback(page);
put_page(page);
return (n_written == n_bytes) ? 0 : -ENOSPC;
}
/*
* We may have stale swap cache pages in memory: notice
* them here and get rid of the unnecessary final write.
*/
int swap_writepage(struct page *page, struct writeback_control *wbc)
{
struct bio *bio;
int ret = 0, rw = WRITE;
if (try_to_free_swap(page)) {
set_swapped_bit(page_private(page), 0);
unlock_page(page);
goto out;
}
bio = get_swap_bio(GFP_NOIO, page, end_swap_bio_write);
if (bio == NULL) {
set_page_dirty(page);
unlock_page(page);
ret = -ENOMEM;
goto out;
}
if (wbc->sync_mode == WB_SYNC_ALL)
rw |= REQ_SYNC;
bio->bi_io_vec[0].bv_page = priv_encrypt_page(page);
count_vm_event(PSWPOUT);
set_page_writeback(page);
unlock_page(page);
submit_bio(rw, bio);
out:
return ret;
}
static int gfs2_aspace_writepage(struct page *page, struct writeback_control *wbc)
{
int err;
struct buffer_head *bh, *head;
int nr_underway = 0;
int write_op = (1 << BIO_RW_META) | ((wbc->sync_mode == WB_SYNC_ALL ?
WRITE_SYNC_PLUG : WRITE));
BUG_ON(!PageLocked(page));
BUG_ON(!page_has_buffers(page));
head = page_buffers(page);
bh = head;
do {
if (!buffer_mapped(bh))
continue;
/*
* If it's a fully non-blocking write attempt and we cannot
* lock the buffer then redirty the page. Note that this can
* potentially cause a busy-wait loop from pdflush and kswapd
* activity, but those code paths have their own higher-level
* throttling.
*/
if (wbc->sync_mode != WB_SYNC_NONE || !wbc->nonblocking) {
lock_buffer(bh);
} else if (!trylock_buffer(bh)) {
redirty_page_for_writepage(wbc, page);
continue;
}
if (test_clear_buffer_dirty(bh)) {
mark_buffer_async_write(bh);
} else {
unlock_buffer(bh);
}
} while ((bh = bh->b_this_page) != head);
/*
* The page and its buffers are protected by PageWriteback(), so we can
* drop the bh refcounts early.
*/
BUG_ON(PageWriteback(page));
set_page_writeback(page);
do {
struct buffer_head *next = bh->b_this_page;
if (buffer_async_write(bh)) {
submit_bh(write_op, bh);
nr_underway++;
}
bh = next;
} while (bh != head);
unlock_page(page);
err = 0;
if (nr_underway == 0)
end_page_writeback(page);
return err;
}
int ext4_bio_write_page(struct ext4_io_submit *io,
struct page *page,
int len,
struct writeback_control *wbc)
{
struct inode *inode = page->mapping->host;
unsigned block_start, block_end, blocksize;
struct ext4_io_page *io_page;
struct buffer_head *bh, *head;
int ret = 0;
blocksize = 1 << inode->i_blkbits;
BUG_ON(PageWriteback(page));
set_page_writeback(page);
ClearPageError(page);
io_page = kmem_cache_alloc(io_page_cachep, GFP_NOFS);
if (!io_page) {
set_page_dirty(page);
unlock_page(page);
return -ENOMEM;
}
io_page->p_page = page;
atomic_set(&io_page->p_count, 1);
get_page(page);
for (bh = head = page_buffers(page), block_start = 0;
bh != head || !block_start;
block_start = block_end, bh = bh->b_this_page) {
block_end = block_start + blocksize;
if (block_start >= len) {
clear_buffer_dirty(bh);
set_buffer_uptodate(bh);
continue;
}
ret = io_submit_add_bh(io, io_page, inode, wbc, bh);
if (ret) {
/*
* We only get here on ENOMEM. Not much else
* we can do but mark the page as dirty, and
* better luck next time.
*/
set_page_dirty(page);
break;
}
}
unlock_page(page);
/*
* If the page was truncated before we could do the writeback,
* or we had a memory allocation error while trying to write
* the first buffer head, we won't have submitted any pages for
* I/O. In that case we need to make sure we've cleared the
* PageWriteback bit from the page to prevent the system from
* wedging later on.
*/
put_io_page(io_page);
return ret;
}
int do_write_data_page(struct f2fs_io_info *fio)
{
struct page *page = fio->page;
struct inode *inode = page->mapping->host;
struct dnode_of_data dn;
int err = 0;
set_new_dnode(&dn, inode, NULL, NULL, 0);
err = get_dnode_of_data(&dn, page->index, LOOKUP_NODE);
if (err)
return err;
fio->blk_addr = dn.data_blkaddr;
/* This page is already truncated */
if (fio->blk_addr == NULL_ADDR) {
ClearPageUptodate(page);
goto out_writepage;
}
if (f2fs_encrypted_inode(inode) && S_ISREG(inode->i_mode)) {
fio->encrypted_page = f2fs_encrypt(inode, fio->page);
if (IS_ERR(fio->encrypted_page)) {
err = PTR_ERR(fio->encrypted_page);
goto out_writepage;
}
}
set_page_writeback(page);
/*
* If current allocation needs SSR,
* it had better in-place writes for updated data.
*/
if (unlikely(fio->blk_addr != NEW_ADDR &&
!is_cold_data(page) &&
need_inplace_update(inode))) {
rewrite_data_page(fio);
set_inode_flag(F2FS_I(inode), FI_UPDATE_WRITE);
trace_f2fs_do_write_data_page(page, IPU);
} else {
write_data_page(&dn, fio);
set_data_blkaddr(&dn);
f2fs_update_extent_cache(&dn);
trace_f2fs_do_write_data_page(page, OPU);
set_inode_flag(F2FS_I(inode), FI_APPEND_WRITE);
if (page->index == 0)
set_inode_flag(F2FS_I(inode), FI_FIRST_BLOCK_WRITTEN);
}
out_writepage:
f2fs_put_dnode(&dn);
return err;
}
int ext4_bio_write_page(struct ext4_io_submit *io,
struct page *page,
int len,
struct writeback_control *wbc)
{
struct inode *inode = page->mapping->host;
unsigned block_start, block_end, blocksize;
struct ext4_io_page *io_page;
struct buffer_head *bh, *head;
int ret = 0;
blocksize = 1 << inode->i_blkbits;
BUG_ON(!PageLocked(page));
BUG_ON(PageWriteback(page));
io_page = kmem_cache_alloc(io_page_cachep, GFP_NOFS);
if (!io_page) {
set_page_dirty(page);
unlock_page(page);
return -ENOMEM;
}
io_page->p_page = page;
atomic_set(&io_page->p_count, 1);
get_page(page);
set_page_writeback(page);
ClearPageError(page);
for (bh = head = page_buffers(page), block_start = 0;
bh != head || !block_start;
block_start = block_end, bh = bh->b_this_page) {
block_end = block_start + blocksize;
if (block_start >= len) {
zero_user_segment(page, block_start, block_end);
clear_buffer_dirty(bh);
set_buffer_uptodate(bh);
continue;
}
clear_buffer_dirty(bh);
ret = io_submit_add_bh(io, io_page, inode, wbc, bh);
if (ret) {
set_page_dirty(page);
break;
}
}
unlock_page(page);
put_io_page(io_page);
return ret;
}
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;
struct request_queue *q = bdev_get_queue(sb->s_bdev);
unsigned int max_pages = queue_max_hw_sectors(q) >> (PAGE_SHIFT - 9);
int i;
if (max_pages > BIO_MAX_PAGES)
max_pages = BIO_MAX_PAGES;
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_idx = 0;
bio->bi_size = i * PAGE_SIZE;
bio->bi_bdev = super->s_bdev;
bio->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);
}
/*
* We may have stale swap cache pages in memory: notice
* them here and get rid of the unnecessary final write.
*/
int swap_writepage(struct page *page, struct writeback_control *wbc)
{
int ret = 0;
if (try_to_free_swap(page)) {
unlock_page(page);
goto out;
}
if (frontswap_store(page) == 0) {
set_page_writeback(page);
unlock_page(page);
end_page_writeback(page);
goto out;
}
ret = __swap_writepage(page, wbc, end_swap_bio_write);
out:
return ret;
}
int __swap_writepage(struct page *page, struct writeback_control *wbc,
void (*end_write_func)(struct bio *, int))
{
struct bio *bio;
int ret = 0, rw = WRITE;
struct swap_info_struct *sis = page_swap_info(page);
bio = get_swap_bio(GFP_NOIO, page, end_write_func);
if (bio == NULL) {
set_page_dirty(page);
unlock_page(page);
ret = -ENOMEM;
goto out;
}
if (wbc->sync_mode == WB_SYNC_ALL)
rw |= REQ_SYNC;
count_vm_event(PSWPOUT);
set_page_writeback(page);
unlock_page(page);
submit_bio(rw, bio);
out:
return ret;
}
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;
}
/**
* ecryptfs_writepage
* @page: Page that is locked before this call is made
*
* Returns zero on success; non-zero otherwise
*
* This is where we encrypt the data and pass the encrypted data to
* the lower filesystem. In OpenPGP-compatible mode, we operate on
* entire underlying packets.
*/
static int ecryptfs_writepage(struct page *page, struct writeback_control *wbc)
{
#ifndef CONFIG_CRYPTO_DEV_KFIPS
int rc;
#else
struct ecryptfs_page_crypt_req *page_crypt_req;
int rc = 0;
#endif
#ifdef FEATURE_SDCARD_ENCRYPTION
struct inode *ecryptfs_inode;
struct ecryptfs_crypt_stat *crypt_stat =
&ecryptfs_inode_to_private(page->mapping->host)->crypt_stat;
ecryptfs_inode = page->mapping->host;
#endif
#ifdef FEATURE_SDCARD_ENCRYPTION
if (!crypt_stat || !(crypt_stat->flags & ECRYPTFS_ENCRYPTED)) {
ecryptfs_printk(KERN_DEBUG,
"Passing through unencrypted page\n");
rc = ecryptfs_write_lower_page_segment(ecryptfs_inode, page,
0, PAGE_CACHE_SIZE);
if (rc) {
ClearPageUptodate(page);
goto out;
}
SetPageUptodate(page);
} else {
#ifndef CONFIG_CRYPTO_DEV_KFIPS
rc = ecryptfs_encrypt_page(page);
if (rc) {
ecryptfs_printk(KERN_WARNING, "Error encrypting "
"page (upper index [0x%.16lx])\n", page->index);
ClearPageUptodate(page);
#else
// rc = ecryptfs_encrypt_page(page);
// if (rc) {
// ecryptfs_printk(KERN_WARNING, "Error encrypting "
// "page (upper index [0x%.16lx])\n", page->index);
// ClearPageUptodate(page);
page_crypt_req = ecryptfs_alloc_page_crypt_req(
page, ecryptfs_writepage_complete);
if (unlikely(!page_crypt_req)) {
rc = -ENOMEM;
ecryptfs_printk(KERN_ERR,
"Failed to allocate page crypt request "
"for encryption\n");
#endif
goto out;
}
#ifndef CONFIG_CRYPTO_DEV_KFIPS
SetPageUptodate(page);
#else
// SetPageUptodate(page);
set_page_writeback(page);
ecryptfs_encrypt_page_async(page_crypt_req);
#endif
}
#else
rc = ecryptfs_encrypt_page(page);
if (rc) {
ecryptfs_printk(KERN_WARNING, "Error encrypting "
"page (upper index [0x%.16lx])\n", page->index);
ClearPageUptodate(page);
goto out;
}
SetPageUptodate(page);
#endif
out:
unlock_page(page);
return rc;
}
static void strip_xattr_flag(char *page_virt,
struct ecryptfs_crypt_stat *crypt_stat)
{
if (crypt_stat->flags & ECRYPTFS_METADATA_IN_XATTR) {
size_t written;
crypt_stat->flags &= ~ECRYPTFS_METADATA_IN_XATTR;
ecryptfs_write_crypt_stat_flags(page_virt, crypt_stat,
&written);
crypt_stat->flags |= ECRYPTFS_METADATA_IN_XATTR;
}
}
/**
* Header Extent:
* Octets 0-7: Unencrypted file size (big-endian)
* Octets 8-15: eCryptfs special marker
* Octets 16-19: Flags
* Octet 16: File format version number (between 0 and 255)
* Octets 17-18: Reserved
* Octet 19: Bit 1 (lsb): Reserved
* Bit 2: Encrypted?
* Bits 3-8: Reserved
* Octets 20-23: Header extent size (big-endian)
* Octets 24-25: Number of header extents at front of file
* (big-endian)
* Octet 26: Begin RFC 2440 authentication token packet set
*/
/**
* ecryptfs_copy_up_encrypted_with_header
* @page: Sort of a ``virtual'' representation of the encrypted lower
* file. The actual lower file does not have the metadata in
* the header. This is locked.
* @crypt_stat: The eCryptfs inode's cryptographic context
*
* The ``view'' is the version of the file that userspace winds up
* seeing, with the header information inserted.
*/
static int
ecryptfs_copy_up_encrypted_with_header(struct page *page,
struct ecryptfs_crypt_stat *crypt_stat)
{
loff_t extent_num_in_page = 0;
loff_t num_extents_per_page = (PAGE_CACHE_SIZE
/ crypt_stat->extent_size);
int rc = 0;
while (extent_num_in_page < num_extents_per_page) {
loff_t view_extent_num = ((((loff_t)page->index)
* num_extents_per_page)
+ extent_num_in_page);
size_t num_header_extents_at_front =
(crypt_stat->metadata_size / crypt_stat->extent_size);
if (view_extent_num < num_header_extents_at_front) {
/* This is a header extent */
char *page_virt;
page_virt = kmap_atomic(page);
memset(page_virt, 0, PAGE_CACHE_SIZE);
/* TODO: Support more than one header extent */
if (view_extent_num == 0) {
size_t written;
rc = ecryptfs_read_xattr_region(
page_virt, page->mapping->host);
strip_xattr_flag(page_virt + 16, crypt_stat);
ecryptfs_write_header_metadata(page_virt + 20,
crypt_stat,
&written);
}
kunmap_atomic(page_virt);
flush_dcache_page(page);
if (rc) {
printk(KERN_ERR "%s: Error reading xattr "
"region; rc = [%d]\n", __func__, rc);
goto out;
}
} else {
/* This is an encrypted data extent */
loff_t lower_offset =
((view_extent_num * crypt_stat->extent_size)
- crypt_stat->metadata_size);
rc = ecryptfs_read_lower_page_segment(
page, (lower_offset >> PAGE_CACHE_SHIFT),
(lower_offset & ~PAGE_CACHE_MASK),
crypt_stat->extent_size, page->mapping->host);
if (rc) {
printk(KERN_ERR "%s: Error attempting to read "
"extent at offset [%lld] in the lower "
"file; rc = [%d]\n", __func__,
lower_offset, rc);
goto out;
}
}
extent_num_in_page++;
}
out:
return rc;
}
int f2fs_convert_inline_page(struct dnode_of_data *dn, struct page *page)
{
void *src_addr, *dst_addr;
struct f2fs_io_info fio = {
.sbi = F2FS_I_SB(dn->inode),
.type = DATA,
.rw = WRITE_SYNC | REQ_PRIO,
.page = page,
.encrypted_page = NULL,
};
int dirty, err;
f2fs_bug_on(F2FS_I_SB(dn->inode), page->index);
if (!f2fs_exist_data(dn->inode))
goto clear_out;
err = f2fs_reserve_block(dn, 0);
if (err)
return err;
f2fs_wait_on_page_writeback(page, DATA);
if (PageUptodate(page))
goto no_update;
zero_user_segment(page, MAX_INLINE_DATA, PAGE_CACHE_SIZE);
/* Copy the whole inline data block */
src_addr = inline_data_addr(dn->inode_page);
dst_addr = kmap_atomic(page);
memcpy(dst_addr, src_addr, MAX_INLINE_DATA);
flush_dcache_page(page);
kunmap_atomic(dst_addr);
SetPageUptodate(page);
no_update:
set_page_dirty(page);
/* clear dirty state */
dirty = clear_page_dirty_for_io(page);
/* write data page to try to make data consistent */
set_page_writeback(page);
fio.blk_addr = dn->data_blkaddr;
write_data_page(dn, &fio);
set_data_blkaddr(dn);
f2fs_update_extent_cache(dn);
f2fs_wait_on_page_writeback(page, DATA);
if (dirty)
inode_dec_dirty_pages(dn->inode);
/* this converted inline_data should be recovered. */
set_inode_flag(F2FS_I(dn->inode), FI_APPEND_WRITE);
/* clear inline data and flag after data writeback */
truncate_inline_inode(dn->inode_page, 0);
clear_out:
stat_dec_inline_inode(dn->inode);
f2fs_clear_inline_inode(dn->inode);
sync_inode_page(dn);
f2fs_put_dnode(dn);
return 0;
}
int f2fs_convert_inline_inode(struct inode *inode)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct dnode_of_data dn;
struct page *ipage, *page;
int err = 0;
page = grab_cache_page(inode->i_mapping, 0);
if (!page)
return -ENOMEM;
f2fs_lock_op(sbi);
ipage = get_node_page(sbi, inode->i_ino);
if (IS_ERR(ipage)) {
err = PTR_ERR(ipage);
goto out;
}
set_new_dnode(&dn, inode, ipage, ipage, 0);
if (f2fs_has_inline_data(inode))
err = f2fs_convert_inline_page(&dn, page);
f2fs_put_dnode(&dn);
out:
f2fs_unlock_op(sbi);
f2fs_put_page(page, 1);
return err;
}
int f2fs_write_inline_data(struct inode *inode, struct page *page)
{
void *src_addr, *dst_addr;
struct dnode_of_data dn;
int err;
set_new_dnode(&dn, inode, NULL, NULL, 0);
err = get_dnode_of_data(&dn, 0, LOOKUP_NODE);
if (err)
return err;
if (!f2fs_has_inline_data(inode)) {
f2fs_put_dnode(&dn);
return -EAGAIN;
}
f2fs_bug_on(F2FS_I_SB(inode), page->index);
f2fs_wait_on_page_writeback(dn.inode_page, NODE);
src_addr = kmap_atomic(page);
dst_addr = inline_data_addr(dn.inode_page);
memcpy(dst_addr, src_addr, MAX_INLINE_DATA);
kunmap_atomic(src_addr);
set_inode_flag(F2FS_I(inode), FI_APPEND_WRITE);
set_inode_flag(F2FS_I(inode), FI_DATA_EXIST);
sync_inode_page(&dn);
f2fs_put_dnode(&dn);
return 0;
}
int ext4_bio_write_page(struct ext4_io_submit *io,
struct page *page,
int len,
struct writeback_control *wbc)
{
struct inode *inode = page->mapping->host;
unsigned block_start, block_end, blocksize;
struct ext4_io_page *io_page;
struct buffer_head *bh, *head;
int ret = 0;
blocksize = 1 << inode->i_blkbits;
BUG_ON(!PageLocked(page));
BUG_ON(PageWriteback(page));
io_page = kmem_cache_alloc(io_page_cachep, GFP_NOFS);
if (!io_page) {
set_page_dirty(page);
unlock_page(page);
return -ENOMEM;
}
io_page->p_page = page;
atomic_set(&io_page->p_count, 1);
get_page(page);
set_page_writeback(page);
ClearPageError(page);
/*
* Comments copied from block_write_full_page_endio:
*
* 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."
*/
if (len < PAGE_CACHE_SIZE)
zero_user_segment(page, len, PAGE_CACHE_SIZE);
for (bh = head = page_buffers(page), block_start = 0;
bh != head || !block_start;
block_start = block_end, bh = bh->b_this_page) {
block_end = block_start + blocksize;
if (block_start >= len) {
clear_buffer_dirty(bh);
set_buffer_uptodate(bh);
continue;
}
clear_buffer_dirty(bh);
ret = io_submit_add_bh(io, io_page, inode, wbc, bh);
if (ret) {
/*
* We only get here on ENOMEM. Not much else
* we can do but mark the page as dirty, and
* better luck next time.
*/
set_page_dirty(page);
break;
}
}
unlock_page(page);
/*
* If the page was truncated before we could do the writeback,
* or we had a memory allocation error while trying to write
* the first buffer head, we won't have submitted any pages for
* I/O. In that case we need to make sure we've cleared the
* PageWriteback bit from the page to prevent the system from
* wedging later on.
*/
put_io_page(io_page);
return ret;
}
static int __f2fs_convert_inline_data(struct inode *inode, struct page *page)
{
int err;
struct page *ipage;
struct dnode_of_data dn;
void *src_addr, *dst_addr;
block_t new_blk_addr;
struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
struct f2fs_io_info fio = {
.type = DATA,
.rw = WRITE_SYNC | REQ_PRIO,
};
f2fs_lock_op(sbi);
ipage = get_node_page(sbi, inode->i_ino);
if (IS_ERR(ipage))
return PTR_ERR(ipage);
/*
* i_addr[0] is not used for inline data,
* so reserving new block will not destroy inline data
*/
set_new_dnode(&dn, inode, ipage, NULL, 0);
err = f2fs_reserve_block(&dn, 0);
if (err) {
f2fs_unlock_op(sbi);
return err;
}
zero_user_segment(page, MAX_INLINE_DATA, PAGE_CACHE_SIZE);
/* Copy the whole inline data block */
src_addr = inline_data_addr(ipage);
dst_addr = kmap(page);
memcpy(dst_addr, src_addr, MAX_INLINE_DATA);
kunmap(page);
SetPageUptodate(page);
/* write data page to try to make data consistent */
set_page_writeback(page);
write_data_page(page, &dn, &new_blk_addr, &fio);
update_extent_cache(new_blk_addr, &dn);
f2fs_wait_on_page_writeback(page, DATA);
/* clear inline data and flag after data writeback */
zero_user_segment(ipage, INLINE_DATA_OFFSET,
INLINE_DATA_OFFSET + MAX_INLINE_DATA);
clear_inode_flag(F2FS_I(inode), FI_INLINE_DATA);
stat_dec_inline_inode(inode);
sync_inode_page(&dn);
f2fs_put_dnode(&dn);
f2fs_unlock_op(sbi);
return err;
}
int f2fs_convert_inline_data(struct inode *inode, pgoff_t to_size)
{
struct page *page;
int err;
if (!f2fs_has_inline_data(inode))
return 0;
else if (to_size <= MAX_INLINE_DATA)
return 0;
page = grab_cache_page_write_begin(inode->i_mapping, 0, AOP_FLAG_NOFS);
if (!page)
return -ENOMEM;
err = __f2fs_convert_inline_data(inode, page);
f2fs_put_page(page, 1);
return err;
}
int f2fs_write_inline_data(struct inode *inode,
struct page *page, unsigned size)
{
void *src_addr, *dst_addr;
struct page *ipage;
struct dnode_of_data dn;
int err;
set_new_dnode(&dn, inode, NULL, NULL, 0);
err = get_dnode_of_data(&dn, 0, LOOKUP_NODE);
if (err)
return err;
ipage = dn.inode_page;
zero_user_segment(ipage, INLINE_DATA_OFFSET,
INLINE_DATA_OFFSET + MAX_INLINE_DATA);
src_addr = kmap(page);
dst_addr = inline_data_addr(ipage);
memcpy(dst_addr, src_addr, size);
kunmap(page);
/* Release the first data block if it is allocated */
if (!f2fs_has_inline_data(inode)) {
truncate_data_blocks_range(&dn, 1);
set_inode_flag(F2FS_I(inode), FI_INLINE_DATA);
stat_inc_inline_inode(inode);
}
sync_inode_page(&dn);
f2fs_put_dnode(&dn);
return 0;
}
int ext4_bio_write_page(struct ext4_io_submit *io,
struct page *page,
int len,
struct writeback_control *wbc)
{
struct inode *inode = page->mapping->host;
unsigned block_start, block_end, blocksize;
struct ext4_io_page *io_page;
struct buffer_head *bh, *head;
int ret = 0;
blocksize = 1 << inode->i_blkbits;
BUG_ON(!PageLocked(page));
BUG_ON(PageWriteback(page));
io_page = kmem_cache_alloc(io_page_cachep, GFP_NOFS);
if (!io_page) {
set_page_dirty(page);
unlock_page(page);
return -ENOMEM;
}
io_page->p_page = page;
atomic_set(&io_page->p_count, 1);
get_page(page);
set_page_writeback(page);
ClearPageError(page);
for (bh = head = page_buffers(page), block_start = 0;
bh != head || !block_start;
block_start = block_end, bh = bh->b_this_page) {
block_end = block_start + blocksize;
if (block_start >= len) {
/*
* Comments copied from block_write_full_page_endio:
*
* 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."
*/
zero_user_segment(page, block_start, block_end);
clear_buffer_dirty(bh);
set_buffer_uptodate(bh);
continue;
}
clear_buffer_dirty(bh);
ret = io_submit_add_bh(io, io_page, inode, wbc, bh);
if (ret) {
set_page_dirty(page);
break;
}
}
unlock_page(page);
put_io_page(io_page);
return ret;
}
int f2fs_convert_inline_page(struct dnode_of_data *dn, struct page *page)
{
struct f2fs_io_info fio = {
.sbi = F2FS_I_SB(dn->inode),
.type = DATA,
.op = REQ_OP_WRITE,
.op_flags = REQ_SYNC | REQ_PRIO,
.page = page,
.encrypted_page = NULL,
};
int dirty, err;
if (!f2fs_exist_data(dn->inode))
goto clear_out;
err = f2fs_reserve_block(dn, 0);
if (err)
return err;
f2fs_bug_on(F2FS_P_SB(page), PageWriteback(page));
read_inline_data(page, dn->inode_page);
set_page_dirty(page);
/* clear dirty state */
dirty = clear_page_dirty_for_io(page);
/* write data page to try to make data consistent */
set_page_writeback(page);
fio.old_blkaddr = dn->data_blkaddr;
set_inode_flag(dn->inode, FI_HOT_DATA);
write_data_page(dn, &fio);
f2fs_wait_on_page_writeback(page, DATA, true);
if (dirty) {
inode_dec_dirty_pages(dn->inode);
remove_dirty_inode(dn->inode);
}
/* this converted inline_data should be recovered. */
set_inode_flag(dn->inode, FI_APPEND_WRITE);
/* clear inline data and flag after data writeback */
truncate_inline_inode(dn->inode, dn->inode_page, 0);
clear_inline_node(dn->inode_page);
clear_out:
stat_dec_inline_inode(dn->inode);
clear_inode_flag(dn->inode, FI_INLINE_DATA);
f2fs_put_dnode(dn);
return 0;
}
int f2fs_convert_inline_inode(struct inode *inode)
{
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct dnode_of_data dn;
struct page *ipage, *page;
int err = 0;
if (!f2fs_has_inline_data(inode))
return 0;
page = f2fs_grab_cache_page(inode->i_mapping, 0, false);
if (!page)
return -ENOMEM;
f2fs_lock_op(sbi);
ipage = get_node_page(sbi, inode->i_ino);
if (IS_ERR(ipage)) {
err = PTR_ERR(ipage);
goto out;
}
set_new_dnode(&dn, inode, ipage, ipage, 0);
if (f2fs_has_inline_data(inode))
err = f2fs_convert_inline_page(&dn, page);
f2fs_put_dnode(&dn);
out:
f2fs_unlock_op(sbi);
f2fs_put_page(page, 1);
f2fs_balance_fs(sbi, dn.node_changed);
return err;
}
int f2fs_write_inline_data(struct inode *inode, struct page *page)
{
void *src_addr, *dst_addr;
struct dnode_of_data dn;
int err;
set_new_dnode(&dn, inode, NULL, NULL, 0);
err = get_dnode_of_data(&dn, 0, LOOKUP_NODE);
if (err)
return err;
if (!f2fs_has_inline_data(inode)) {
f2fs_put_dnode(&dn);
return -EAGAIN;
}
f2fs_bug_on(F2FS_I_SB(inode), page->index);
f2fs_wait_on_page_writeback(dn.inode_page, NODE, true);
src_addr = kmap_atomic(page);
dst_addr = inline_data_addr(dn.inode_page);
memcpy(dst_addr, src_addr, MAX_INLINE_DATA);
kunmap_atomic(src_addr);
set_page_dirty(dn.inode_page);
set_inode_flag(inode, FI_APPEND_WRITE);
set_inode_flag(inode, FI_DATA_EXIST);
clear_inline_node(dn.inode_page);
f2fs_put_dnode(&dn);
return 0;
}
/**
* ntfs_mft_writepage - check if a metadata page contains dirty mft records
* @page: metadata page possibly containing dirty mft records
* @wbc: writeback control structure
*
* This is called from the VM when it wants to have a dirty $MFT/$DATA metadata
* page cache page cleaned. The VM has already locked the page and marked it
* clean. Instead of writing the page as a conventional ->writepage function
* would do, we check if the page still contains any dirty mft records (it must
* have done at some point in the past since the page was marked dirty) and if
* none are found, i.e. all mft records are clean, we unlock the page and
* return. The VM is then free to do with the page as it pleases. If on the
* other hand we do find any dirty mft records in the page, we redirty the page
* before unlocking it and returning so the VM knows that the page is still
* busy and cannot be thrown out.
*
* Note, we do not actually write any dirty mft records here because they are
* dirty inodes and hence will be written by the VFS inode dirty code paths.
* There is no need to write them from the VM page dirty code paths, too and in
* fact once we implement journalling it would be a complete nightmare having
* two code paths leading to mft record writeout.
*/
static int ntfs_mft_writepage(struct page *page, struct writeback_control *wbc)
{
struct inode *mft_vi = page->mapping->host;
struct super_block *sb = mft_vi->i_sb;
ntfs_volume *vol = NTFS_SB(sb);
u8 *maddr;
MFT_RECORD *m;
ntfs_inode **extent_nis;
unsigned long mft_no;
int nr, i, j;
BOOL is_dirty = FALSE;
BUG_ON(!PageLocked(page));
BUG_ON(PageWriteback(page));
BUG_ON(mft_vi != vol->mft_ino);
/* The first mft record number in the page. */
mft_no = page->index << (PAGE_CACHE_SHIFT - vol->mft_record_size_bits);
/* Number of mft records in the page. */
nr = PAGE_CACHE_SIZE >> vol->mft_record_size_bits;
BUG_ON(!nr);
ntfs_debug("Entering for %i inodes starting at 0x%lx.", nr, mft_no);
/* Iterate over the mft records in the page looking for a dirty one. */
maddr = (u8*)kmap(page);
for (i = 0; i < nr; ++i, ++mft_no, maddr += vol->mft_record_size) {
struct inode *vi;
ntfs_inode *ni, *eni;
ntfs_attr na;
na.mft_no = mft_no;
na.name = NULL;
na.name_len = 0;
na.type = AT_UNUSED;
/*
* Check if the inode corresponding to this mft record is in
* the VFS inode cache and obtain a reference to it if it is.
*/
ntfs_debug("Looking for inode 0x%lx in icache.", mft_no);
/*
* For inode 0, i.e. $MFT itself, we cannot use ilookup5() from
* here or we deadlock because the inode is already locked by
* the kernel (fs/fs-writeback.c::__sync_single_inode()) and
* ilookup5() waits until the inode is unlocked before
* returning it and it never gets unlocked because
* ntfs_mft_writepage() never returns. )-: Fortunately, we
* have inode 0 pinned in icache for the duration of the mount
* so we can access it directly.
*/
if (!mft_no) {
/* Balance the below iput(). */
vi = igrab(mft_vi);
BUG_ON(vi != mft_vi);
} else
vi = ilookup5(sb, mft_no, (test_t)ntfs_test_inode, &na);
if (vi) {
ntfs_debug("Inode 0x%lx is in icache.", mft_no);
/* The inode is in icache. Check if it is dirty. */
ni = NTFS_I(vi);
if (!NInoDirty(ni)) {
/* The inode is not dirty, skip this record. */
ntfs_debug("Inode 0x%lx is not dirty, "
"continuing search.", mft_no);
iput(vi);
continue;
}
ntfs_debug("Inode 0x%lx is dirty, aborting search.",
mft_no);
/* The inode is dirty, no need to search further. */
iput(vi);
is_dirty = TRUE;
break;
}
ntfs_debug("Inode 0x%lx is not in icache.", mft_no);
/* The inode is not in icache. */
/* Skip the record if it is not a mft record (type "FILE"). */
if (!ntfs_is_mft_recordp(maddr)) {
ntfs_debug("Mft record 0x%lx is not a FILE record, "
"continuing search.", mft_no);
continue;
}
m = (MFT_RECORD*)maddr;
/*
* Skip the mft record if it is not in use. FIXME: What about
* deleted/deallocated (extent) inodes? (AIA)
*/
if (!(m->flags & MFT_RECORD_IN_USE)) {
ntfs_debug("Mft record 0x%lx is not in use, "
"continuing search.", mft_no);
continue;
}
/* Skip the mft record if it is a base inode. */
if (!m->base_mft_record) {
ntfs_debug("Mft record 0x%lx is a base record, "
"continuing search.", mft_no);
continue;
}
/*
* This is an extent mft record. Check if the inode
* corresponding to its base mft record is in icache.
*/
na.mft_no = MREF_LE(m->base_mft_record);
ntfs_debug("Mft record 0x%lx is an extent record. Looking "
"for base inode 0x%lx in icache.", mft_no,
na.mft_no);
vi = ilookup5(sb, na.mft_no, (test_t)ntfs_test_inode,
&na);
if (!vi) {
/*
* The base inode is not in icache. Skip this extent
* mft record.
*/
ntfs_debug("Base inode 0x%lx is not in icache, "
"continuing search.", na.mft_no);
continue;
}
ntfs_debug("Base inode 0x%lx is in icache.", na.mft_no);
/*
* The base inode is in icache. Check if it has the extent
* inode corresponding to this extent mft record attached.
*/
ni = NTFS_I(vi);
down(&ni->extent_lock);
if (ni->nr_extents <= 0) {
/*
* The base inode has no attached extent inodes. Skip
* this extent mft record.
*/
up(&ni->extent_lock);
iput(vi);
continue;
}
/* Iterate over the attached extent inodes. */
extent_nis = ni->ext.extent_ntfs_inos;
for (eni = NULL, j = 0; j < ni->nr_extents; ++j) {
if (mft_no == extent_nis[j]->mft_no) {
/*
* Found the extent inode corresponding to this
* extent mft record.
*/
eni = extent_nis[j];
break;
}
}
/*
* If the extent inode was not attached to the base inode, skip
* this extent mft record.
*/
if (!eni) {
up(&ni->extent_lock);
iput(vi);
continue;
}
/*
* Found the extent inode corrsponding to this extent mft
* record. If it is dirty, no need to search further.
*/
if (NInoDirty(eni)) {
up(&ni->extent_lock);
iput(vi);
is_dirty = TRUE;
break;
}
/* The extent inode is not dirty, so do the next record. */
up(&ni->extent_lock);
iput(vi);
}
kunmap(page);
/* If a dirty mft record was found, redirty the page. */
if (is_dirty) {
ntfs_debug("Inode 0x%lx is dirty. Redirtying the page "
"starting at inode 0x%lx.", mft_no,
page->index << (PAGE_CACHE_SHIFT -
vol->mft_record_size_bits));
redirty_page_for_writepage(wbc, page);
unlock_page(page);
} else {
/*
* Keep the VM happy. This must be done otherwise the
* radix-tree tag PAGECACHE_TAG_DIRTY remains set even though
* the page is clean.
*/
BUG_ON(PageWriteback(page));
set_page_writeback(page);
unlock_page(page);
end_page_writeback(page);
}
ntfs_debug("Done.");
return 0;
}
