/**
* mpage_readpages - populate an address space with some pages & start reads against them
* @mapping: the address_space
* @pages: The address of a list_head which contains the target pages. These
* pages have their ->index populated and are otherwise uninitialised.
* The page at @pages->prev has the lowest file offset, and reads should be
* issued in @pages->prev to @pages->next order.
* @nr_pages: The number of pages at *@pages
* @get_block: The filesystem's block mapper function.
*
* This function walks the pages and the blocks within each page, building and
* emitting large BIOs.
*
* If anything unusual happens, such as:
*
* - encountering a page which has buffers
* - encountering a page which has a non-hole after a hole
* - encountering a page with non-contiguous blocks
*
* then this code just gives up and calls the buffer_head-based read function.
* It does handle a page which has holes at the end - that is a common case:
* the end-of-file on blocksize < PAGE_CACHE_SIZE setups.
*
* BH_Boundary explanation:
*
* There is a problem. The mpage read code assembles several pages, gets all
* their disk mappings, and then submits them all. That's fine, but obtaining
* the disk mappings may require I/O. Reads of indirect blocks, for example.
*
* So an mpage read of the first 16 blocks of an ext2 file will cause I/O to be
* submitted in the following order:
* 12 0 1 2 3 4 5 6 7 8 9 10 11 13 14 15 16
*
* because the indirect block has to be read to get the mappings of blocks
* 13,14,15,16. Obviously, this impacts performance.
*
* So what we do it to allow the filesystem's get_block() function to set
* BH_Boundary when it maps block 11. BH_Boundary says: mapping of the block
* after this one will require I/O against a block which is probably close to
* this one. So you should push what I/O you have currently accumulated.
*
* This all causes the disk requests to be issued in the correct order.
*/
int
mpage_readpages(struct address_space *mapping, struct list_head *pages,
unsigned nr_pages, get_block_t get_block)
{
struct bio *bio = NULL;
unsigned page_idx;
sector_t last_block_in_bio = 0;
struct buffer_head map_bh;
unsigned long first_logical_block = 0;
gfp_t gfp = mapping_gfp_constraint(mapping, GFP_KERNEL);
map_bh.b_state = 0;
map_bh.b_size = 0;
for (page_idx = 0; page_idx < nr_pages; page_idx++) {
struct page *page = list_entry(pages->prev, struct page, lru);
prefetchw(&page->flags);
list_del(&page->lru);
if (!add_to_page_cache_lru(page, mapping,
page->index,
gfp)) {
bio = do_mpage_readpage(bio, page,
nr_pages - page_idx,
&last_block_in_bio, &map_bh,
&first_logical_block,
get_block, gfp);
}
page_cache_release(page);
}
BUG_ON(!list_empty(pages));
if (bio)
mpage_bio_submit(READ, bio);
return 0;
}
static int __nilfs_read_inode(struct super_block *sb,
struct nilfs_root *root, unsigned long ino,
struct inode *inode)
{
struct the_nilfs *nilfs = sb->s_fs_info;
struct buffer_head *bh;
struct nilfs_inode *raw_inode;
int err;
down_read(&NILFS_MDT(nilfs->ns_dat)->mi_sem);
err = nilfs_ifile_get_inode_block(root->ifile, ino, &bh);
if (unlikely(err))
goto bad_inode;
raw_inode = nilfs_ifile_map_inode(root->ifile, ino, bh);
err = nilfs_read_inode_common(inode, raw_inode);
if (err)
goto failed_unmap;
if (S_ISREG(inode->i_mode)) {
inode->i_op = &nilfs_file_inode_operations;
inode->i_fop = &nilfs_file_operations;
inode->i_mapping->a_ops = &nilfs_aops;
} else if (S_ISDIR(inode->i_mode)) {
inode->i_op = &nilfs_dir_inode_operations;
inode->i_fop = &nilfs_dir_operations;
inode->i_mapping->a_ops = &nilfs_aops;
} else if (S_ISLNK(inode->i_mode)) {
inode->i_op = &nilfs_symlink_inode_operations;
inode_nohighmem(inode);
inode->i_mapping->a_ops = &nilfs_aops;
} else {
inode->i_op = &nilfs_special_inode_operations;
init_special_inode(
inode, inode->i_mode,
huge_decode_dev(le64_to_cpu(raw_inode->i_device_code)));
}
nilfs_ifile_unmap_inode(root->ifile, ino, bh);
brelse(bh);
up_read(&NILFS_MDT(nilfs->ns_dat)->mi_sem);
nilfs_set_inode_flags(inode);
mapping_set_gfp_mask(inode->i_mapping,
mapping_gfp_constraint(inode->i_mapping, ~__GFP_FS));
return 0;
failed_unmap:
nilfs_ifile_unmap_inode(root->ifile, ino, bh);
brelse(bh);
bad_inode:
up_read(&NILFS_MDT(nilfs->ns_dat)->mi_sem);
return err;
}
/*
* This isn't called much at all
*/
int mpage_readpage(struct page *page, get_block_t get_block)
{
struct bio *bio = NULL;
sector_t last_block_in_bio = 0;
struct buffer_head map_bh;
unsigned long first_logical_block = 0;
gfp_t gfp = mapping_gfp_constraint(page->mapping, GFP_KERNEL);
map_bh.b_state = 0;
map_bh.b_size = 0;
bio = do_mpage_readpage(bio, page, 1, &last_block_in_bio,
&map_bh, &first_logical_block, get_block, gfp);
if (bio)
mpage_bio_submit(READ, bio);
return 0;
}
static struct page *get_mapping_page(struct super_block *sb, pgoff_t index,
int use_filler)
{
struct logfs_super *super = logfs_super(sb);
struct address_space *mapping = super->s_mapping_inode->i_mapping;
filler_t *filler = super->s_devops->readpage;
struct page *page;
BUG_ON(mapping_gfp_constraint(mapping, __GFP_FS));
if (use_filler)
page = read_cache_page(mapping, index, filler, sb);
else {
page = find_or_create_page(mapping, index, GFP_NOFS);
if (page)
unlock_page(page);
}
return page;
}
static int nilfs_insert_inode_locked(struct inode *inode,
struct nilfs_root *root,
unsigned long ino)
{
struct nilfs_iget_args args = {
.ino = ino, .root = root, .cno = 0, .for_gc = 0
};
return insert_inode_locked4(inode, ino, nilfs_iget_test, &args);
}
struct inode *nilfs_new_inode(struct inode *dir, umode_t mode)
{
struct super_block *sb = dir->i_sb;
struct the_nilfs *nilfs = sb->s_fs_info;
struct inode *inode;
struct nilfs_inode_info *ii;
struct nilfs_root *root;
int err = -ENOMEM;
ino_t ino;
inode = new_inode(sb);
if (unlikely(!inode))
goto failed;
mapping_set_gfp_mask(inode->i_mapping,
mapping_gfp_constraint(inode->i_mapping, ~__GFP_FS));
root = NILFS_I(dir)->i_root;
ii = NILFS_I(inode);
ii->i_state = BIT(NILFS_I_NEW);
ii->i_root = root;
err = nilfs_ifile_create_inode(root->ifile, &ino, &ii->i_bh);
if (unlikely(err))
goto failed_ifile_create_inode;
/* reference count of i_bh inherits from nilfs_mdt_read_block() */
atomic64_inc(&root->inodes_count);
inode_init_owner(inode, dir, mode);
inode->i_ino = ino;
inode->i_mtime = inode->i_atime = inode->i_ctime = current_time(inode);
if (S_ISREG(mode) || S_ISDIR(mode) || S_ISLNK(mode)) {
err = nilfs_bmap_read(ii->i_bmap, NULL);
if (err < 0)
goto failed_after_creation;
set_bit(NILFS_I_BMAP, &ii->i_state);
/* No lock is needed; iget() ensures it. */
}
ii->i_flags = nilfs_mask_flags(
mode, NILFS_I(dir)->i_flags & NILFS_FL_INHERITED);
/* ii->i_file_acl = 0; */
/* ii->i_dir_acl = 0; */
ii->i_dir_start_lookup = 0;
nilfs_set_inode_flags(inode);
spin_lock(&nilfs->ns_next_gen_lock);
inode->i_generation = nilfs->ns_next_generation++;
spin_unlock(&nilfs->ns_next_gen_lock);
if (nilfs_insert_inode_locked(inode, root, ino) < 0) {
err = -EIO;
goto failed_after_creation;
}
err = nilfs_init_acl(inode, dir);
if (unlikely(err))
/*
* Never occur. When supporting nilfs_init_acl(),
* proper cancellation of above jobs should be considered.
*/
goto failed_after_creation;
return inode;
failed_after_creation:
clear_nlink(inode);
unlock_new_inode(inode);
iput(inode); /*
* raw_inode will be deleted through
* nilfs_evict_inode().
*/
goto failed;
failed_ifile_create_inode:
make_bad_inode(inode);
iput(inode);
failed:
return ERR_PTR(err);
}
void nilfs_set_inode_flags(struct inode *inode)
{
unsigned int flags = NILFS_I(inode)->i_flags;
unsigned int new_fl = 0;
if (flags & FS_SYNC_FL)
new_fl |= S_SYNC;
if (flags & FS_APPEND_FL)
new_fl |= S_APPEND;
if (flags & FS_IMMUTABLE_FL)
new_fl |= S_IMMUTABLE;
if (flags & FS_NOATIME_FL)
new_fl |= S_NOATIME;
if (flags & FS_DIRSYNC_FL)
new_fl |= S_DIRSYNC;
inode_set_flags(inode, new_fl, S_SYNC | S_APPEND | S_IMMUTABLE |
S_NOATIME | S_DIRSYNC);
}
