static int nilfs_set_page_dirty(struct page *page)
{
struct inode *inode = page->mapping->host;
int ret = __set_page_dirty_nobuffers(page);
if (page_has_buffers(page)) {
unsigned nr_dirty = 0;
struct buffer_head *bh, *head;
/*
* This page is locked by callers, and no other thread
* concurrently marks its buffers dirty since they are
* only dirtied through routines in fs/buffer.c in
* which call sites of mark_buffer_dirty are protected
* by page lock.
*/
bh = head = page_buffers(page);
do {
/* Do not mark hole blocks dirty */
if (buffer_dirty(bh) || !buffer_mapped(bh))
continue;
set_buffer_dirty(bh);
nr_dirty++;
} while (bh = bh->b_this_page, bh != head);
if (nr_dirty)
nilfs_set_file_dirty(inode, nr_dirty);
} else if (ret) {
unsigned nr_dirty = 1 << (PAGE_CACHE_SHIFT - inode->i_blkbits);
nilfs_set_file_dirty(inode, nr_dirty);
}
return ret;
}
void nilfs_truncate(struct inode *inode)
{
unsigned long blkoff;
unsigned int blocksize;
struct nilfs_transaction_info ti;
struct super_block *sb = inode->i_sb;
struct nilfs_inode_info *ii = NILFS_I(inode);
if (!test_bit(NILFS_I_BMAP, &ii->i_state))
return;
if (IS_APPEND(inode) || IS_IMMUTABLE(inode))
return;
blocksize = sb->s_blocksize;
blkoff = (inode->i_size + blocksize - 1) >> sb->s_blocksize_bits;
nilfs_transaction_begin(sb, &ti, 0); /* never fails */
block_truncate_page(inode->i_mapping, inode->i_size, nilfs_get_block);
nilfs_truncate_bmap(ii, blkoff);
inode->i_mtime = inode->i_ctime = CURRENT_TIME;
if (IS_SYNC(inode))
nilfs_set_transaction_flag(NILFS_TI_SYNC);
nilfs_set_file_dirty(NILFS_SB(sb), inode, 0);
nilfs_transaction_commit(sb);
/* May construct a logical segment and may fail in sync mode.
But truncate has no return value. */
}
static int recover_dsync_blocks(struct nilfs_sb_info *sbi,
struct list_head *head,
unsigned long *nr_salvaged_blocks)
{
struct inode *inode;
struct nilfs_recovery_block *rb, *n;
unsigned blocksize = sbi->s_super->s_blocksize;
struct page *page;
loff_t pos;
int err = 0, err2 = 0;
list_for_each_entry_safe(rb, n, head, list) {
inode = nilfs_iget(sbi->s_super, rb->ino);
if (IS_ERR(inode)) {
err = PTR_ERR(inode);
inode = NULL;
goto failed_inode;
}
pos = rb->blkoff << inode->i_blkbits;
page = NULL;
err = block_write_begin(NULL, inode->i_mapping, pos, blocksize,
0, &page, NULL, nilfs_get_block);
if (unlikely(err))
goto failed_inode;
err = nilfs_recovery_copy_block(sbi, rb, page);
if (unlikely(err))
goto failed_page;
err = nilfs_set_file_dirty(sbi, inode, 1);
if (unlikely(err))
goto failed_page;
block_write_end(NULL, inode->i_mapping, pos, blocksize,
blocksize, page, NULL);
unlock_page(page);
page_cache_release(page);
(*nr_salvaged_blocks)++;
goto next;
failed_page:
unlock_page(page);
page_cache_release(page);
failed_inode:
printk(KERN_WARNING
"NILFS warning: error recovering data block "
"(err=%d, ino=%lu, block-offset=%llu)\n",
err, rb->ino, (unsigned long long)rb->blkoff);
if (!err2)
err2 = err;
next:
iput(inode); /* iput(NULL) is just ignored */
list_del_init(&rb->list);
kfree(rb);
}
static int nilfs_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
{
struct page *page = vmf->page;
struct inode *inode = vma->vm_file->f_dentry->d_inode;
struct nilfs_transaction_info ti;
int ret;
if (unlikely(nilfs_near_disk_full(inode->i_sb->s_fs_info)))
return VM_FAULT_SIGBUS;
lock_page(page);
if (page->mapping != inode->i_mapping ||
page_offset(page) >= i_size_read(inode) || !PageUptodate(page)) {
unlock_page(page);
return VM_FAULT_NOPAGE;
}
if (PageMappedToDisk(page))
goto mapped;
if (page_has_buffers(page)) {
struct buffer_head *bh, *head;
int fully_mapped = 1;
bh = head = page_buffers(page);
do {
if (!buffer_mapped(bh)) {
fully_mapped = 0;
break;
}
} while (bh = bh->b_this_page, bh != head);
if (fully_mapped) {
SetPageMappedToDisk(page);
goto mapped;
}
}
unlock_page(page);
ret = nilfs_transaction_begin(inode->i_sb, &ti, 1);
if (unlikely(ret))
return VM_FAULT_SIGBUS;
ret = block_page_mkwrite(vma, vmf, nilfs_get_block);
if (ret != VM_FAULT_LOCKED) {
nilfs_transaction_abort(inode->i_sb);
return ret;
}
nilfs_set_file_dirty(inode, 1 << (PAGE_SHIFT - inode->i_blkbits));
nilfs_transaction_commit(inode->i_sb);
mapped:
wait_on_page_writeback(page);
return VM_FAULT_LOCKED;
}
static int nilfs_set_page_dirty(struct page *page)
{
int ret = __set_page_dirty_buffers(page);
if (ret) {
struct inode *inode = page->mapping->host;
unsigned nr_dirty = 1 << (PAGE_SHIFT - inode->i_blkbits);
nilfs_set_file_dirty(inode, nr_dirty);
}
return ret;
}
static int nilfs_commit_write(struct file *file, struct page *page,
unsigned from, unsigned to)
{
struct inode *inode = page->mapping->host;
unsigned nr_dirty = nilfs_page_count_clean_buffers(page, from, to);
int err;
generic_commit_write(file, page, from, to);
nilfs_set_file_dirty(NILFS_SB(inode->i_sb), inode, nr_dirty);
err = nilfs_transaction_commit(inode->i_sb);
return err;
}
static int nilfs_set_page_dirty(struct page *page)
{
int ret = __set_page_dirty_buffers(page);
page_debug(3, "called (page=%p)\n", page);
if (ret) {
struct inode *inode = page->mapping->host;
struct nilfs_sb_info *sbi = NILFS_SB(inode->i_sb);
unsigned nr_dirty = 1 << (PAGE_SHIFT - inode->i_blkbits);
nilfs_set_file_dirty(sbi, inode, nr_dirty);
}
page_debug(3, "done (ret=%d, page=%p)\n", ret, page);
return ret;
}
static int nilfs_write_end(struct file *file, struct address_space *mapping,
loff_t pos, unsigned len, unsigned copied,
struct page *page, void *fsdata)
{
struct inode *inode = mapping->host;
unsigned start = pos & (PAGE_CACHE_SIZE - 1);
unsigned nr_dirty;
int err;
nr_dirty = nilfs_page_count_clean_buffers(page, start,
start + copied);
copied = generic_write_end(file, mapping, pos, len, copied, page,
fsdata);
nilfs_set_file_dirty(inode, nr_dirty);
err = nilfs_transaction_commit(inode->i_sb);
return err ? : copied;
}
struct inode *nilfs_ilookup(struct super_block *sb, struct nilfs_root *root,
unsigned long ino)
{
struct nilfs_iget_args args = {
.ino = ino, .root = root, .cno = 0, .for_gc = 0
};
return ilookup5(sb, ino, nilfs_iget_test, &args);
}
struct inode *nilfs_iget_locked(struct super_block *sb, struct nilfs_root *root,
unsigned long ino)
{
struct nilfs_iget_args args = {
.ino = ino, .root = root, .cno = 0, .for_gc = 0
};
return iget5_locked(sb, ino, nilfs_iget_test, nilfs_iget_set, &args);
}
struct inode *nilfs_iget(struct super_block *sb, struct nilfs_root *root,
unsigned long ino)
{
struct inode *inode;
int err;
inode = nilfs_iget_locked(sb, root, ino);
if (unlikely(!inode))
return ERR_PTR(-ENOMEM);
if (!(inode->i_state & I_NEW))
return inode;
err = __nilfs_read_inode(sb, root, ino, inode);
if (unlikely(err)) {
iget_failed(inode);
return ERR_PTR(err);
}
unlock_new_inode(inode);
return inode;
}
struct inode *nilfs_iget_for_gc(struct super_block *sb, unsigned long ino,
__u64 cno)
{
struct nilfs_iget_args args = {
.ino = ino, .root = NULL, .cno = cno, .for_gc = 1
};
struct inode *inode;
int err;
inode = iget5_locked(sb, ino, nilfs_iget_test, nilfs_iget_set, &args);
if (unlikely(!inode))
return ERR_PTR(-ENOMEM);
if (!(inode->i_state & I_NEW))
return inode;
err = nilfs_init_gcinode(inode);
if (unlikely(err)) {
iget_failed(inode);
return ERR_PTR(err);
}
unlock_new_inode(inode);
return inode;
}
void nilfs_write_inode_common(struct inode *inode,
struct nilfs_inode *raw_inode, int has_bmap)
{
struct nilfs_inode_info *ii = NILFS_I(inode);
raw_inode->i_mode = cpu_to_le16(inode->i_mode);
raw_inode->i_uid = cpu_to_le32(inode->i_uid);
raw_inode->i_gid = cpu_to_le32(inode->i_gid);
raw_inode->i_links_count = cpu_to_le16(inode->i_nlink);
raw_inode->i_size = cpu_to_le64(inode->i_size);
raw_inode->i_ctime = cpu_to_le64(inode->i_ctime.tv_sec);
raw_inode->i_mtime = cpu_to_le64(inode->i_mtime.tv_sec);
raw_inode->i_ctime_nsec = cpu_to_le32(inode->i_ctime.tv_nsec);
raw_inode->i_mtime_nsec = cpu_to_le32(inode->i_mtime.tv_nsec);
raw_inode->i_blocks = cpu_to_le64(inode->i_blocks);
raw_inode->i_flags = cpu_to_le32(ii->i_flags);
raw_inode->i_generation = cpu_to_le32(inode->i_generation);
if (NILFS_ROOT_METADATA_FILE(inode->i_ino)) {
struct the_nilfs *nilfs = inode->i_sb->s_fs_info;
/* zero-fill unused portion in the case of super root block */
raw_inode->i_xattr = 0;
raw_inode->i_pad = 0;
memset((void *)raw_inode + sizeof(*raw_inode), 0,
nilfs->ns_inode_size - sizeof(*raw_inode));
}
if (has_bmap)
nilfs_bmap_write(ii->i_bmap, raw_inode);
else if (S_ISCHR(inode->i_mode) || S_ISBLK(inode->i_mode))
raw_inode->i_device_code =
cpu_to_le64(huge_encode_dev(inode->i_rdev));
/* When extending inode, nilfs->ns_inode_size should be checked
for substitutions of appended fields */
}
void nilfs_update_inode(struct inode *inode, struct buffer_head *ibh)
{
ino_t ino = inode->i_ino;
struct nilfs_inode_info *ii = NILFS_I(inode);
struct inode *ifile = ii->i_root->ifile;
struct nilfs_inode *raw_inode;
raw_inode = nilfs_ifile_map_inode(ifile, ino, ibh);
if (test_and_clear_bit(NILFS_I_NEW, &ii->i_state))
memset(raw_inode, 0, NILFS_MDT(ifile)->mi_entry_size);
set_bit(NILFS_I_INODE_DIRTY, &ii->i_state);
nilfs_write_inode_common(inode, raw_inode, 0);
/* XXX: call with has_bmap = 0 is a workaround to avoid
deadlock of bmap. This delays update of i_bmap to just
before writing */
nilfs_ifile_unmap_inode(ifile, ino, ibh);
}
#define NILFS_MAX_TRUNCATE_BLOCKS 16384 /* 64MB for 4KB block */
static void nilfs_truncate_bmap(struct nilfs_inode_info *ii,
unsigned long from)
{
unsigned long b;
int ret;
if (!test_bit(NILFS_I_BMAP, &ii->i_state))
return;
repeat:
ret = nilfs_bmap_last_key(ii->i_bmap, &b);
if (ret == -ENOENT)
return;
else if (ret < 0)
goto failed;
if (b < from)
return;
b -= min_t(unsigned long, NILFS_MAX_TRUNCATE_BLOCKS, b - from);
ret = nilfs_bmap_truncate(ii->i_bmap, b);
nilfs_relax_pressure_in_lock(ii->vfs_inode.i_sb);
if (!ret || (ret == -ENOMEM &&
nilfs_bmap_truncate(ii->i_bmap, b) == 0))
goto repeat;
failed:
nilfs_warning(ii->vfs_inode.i_sb, __func__,
"failed to truncate bmap (ino=%lu, err=%d)",
ii->vfs_inode.i_ino, ret);
}
void nilfs_truncate(struct inode *inode)
{
unsigned long blkoff;
unsigned int blocksize;
struct nilfs_transaction_info ti;
struct super_block *sb = inode->i_sb;
struct nilfs_inode_info *ii = NILFS_I(inode);
if (!test_bit(NILFS_I_BMAP, &ii->i_state))
return;
if (IS_APPEND(inode) || IS_IMMUTABLE(inode))
return;
blocksize = sb->s_blocksize;
blkoff = (inode->i_size + blocksize - 1) >> sb->s_blocksize_bits;
nilfs_transaction_begin(sb, &ti, 0); /* never fails */
block_truncate_page(inode->i_mapping, inode->i_size, nilfs_get_block);
nilfs_truncate_bmap(ii, blkoff);
inode->i_mtime = inode->i_ctime = CURRENT_TIME;
if (IS_SYNC(inode))
nilfs_set_transaction_flag(NILFS_TI_SYNC);
nilfs_mark_inode_dirty(inode);
nilfs_set_file_dirty(inode, 0);
nilfs_transaction_commit(sb);
/* May construct a logical segment and may fail in sync mode.
But truncate has no return value. */
}
static int nilfs_recover_dsync_blocks(struct the_nilfs *nilfs,
struct super_block *sb,
struct nilfs_root *root,
struct list_head *head,
unsigned long *nr_salvaged_blocks)
{
struct inode *inode;
struct nilfs_recovery_block *rb, *n;
unsigned int blocksize = nilfs->ns_blocksize;
struct page *page;
loff_t pos;
int err = 0, err2 = 0;
list_for_each_entry_safe(rb, n, head, list) {
inode = nilfs_iget(sb, root, rb->ino);
if (IS_ERR(inode)) {
err = PTR_ERR(inode);
inode = NULL;
goto failed_inode;
}
pos = rb->blkoff << inode->i_blkbits;
err = block_write_begin(inode->i_mapping, pos, blocksize,
0, &page, nilfs_get_block);
if (unlikely(err)) {
loff_t isize = inode->i_size;
if (pos + blocksize > isize)
nilfs_write_failed(inode->i_mapping,
pos + blocksize);
goto failed_inode;
}
err = nilfs_recovery_copy_block(nilfs, rb, page);
if (unlikely(err))
goto failed_page;
err = nilfs_set_file_dirty(inode, 1);
if (unlikely(err))
goto failed_page;
block_write_end(NULL, inode->i_mapping, pos, blocksize,
blocksize, page, NULL);
unlock_page(page);
put_page(page);
(*nr_salvaged_blocks)++;
goto next;
failed_page:
unlock_page(page);
put_page(page);
failed_inode:
nilfs_msg(sb, KERN_WARNING,
"error %d recovering data block (ino=%lu, block-offset=%llu)",
err, (unsigned long)rb->ino,
(unsigned long long)rb->blkoff);
if (!err2)
err2 = err;
next:
iput(inode); /* iput(NULL) is just ignored */
list_del_init(&rb->list);
kfree(rb);
}
static int nilfs_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
{
struct page *page = vmf->page;
struct inode *inode = file_inode(vma->vm_file);
struct nilfs_transaction_info ti;
int ret = 0;
if (unlikely(nilfs_near_disk_full(inode->i_sb->s_fs_info)))
return VM_FAULT_SIGBUS; /* -ENOSPC */
sb_start_pagefault(inode->i_sb);
lock_page(page);
if (page->mapping != inode->i_mapping ||
page_offset(page) >= i_size_read(inode) || !PageUptodate(page)) {
unlock_page(page);
ret = -EFAULT; /* make the VM retry the fault */
goto out;
}
/*
* check to see if the page is mapped already (no holes)
*/
if (PageMappedToDisk(page))
goto mapped;
if (page_has_buffers(page)) {
struct buffer_head *bh, *head;
int fully_mapped = 1;
bh = head = page_buffers(page);
do {
if (!buffer_mapped(bh)) {
fully_mapped = 0;
break;
}
} while (bh = bh->b_this_page, bh != head);
if (fully_mapped) {
SetPageMappedToDisk(page);
goto mapped;
}
}
unlock_page(page);
/*
* fill hole blocks
*/
ret = nilfs_transaction_begin(inode->i_sb, &ti, 1);
/* never returns -ENOMEM, but may return -ENOSPC */
if (unlikely(ret))
goto out;
file_update_time(vma->vm_file);
ret = __block_page_mkwrite(vma, vmf, nilfs_get_block);
if (ret) {
nilfs_transaction_abort(inode->i_sb);
goto out;
}
nilfs_set_file_dirty(inode, 1 << (PAGE_SHIFT - inode->i_blkbits));
nilfs_transaction_commit(inode->i_sb);
mapped:
wait_for_stable_page(page);
out:
sb_end_pagefault(inode->i_sb);
return block_page_mkwrite_return(ret);
}