static void rgrp_go_inval(struct gfs2_glock *gl, int flags)
{
struct gfs2_sbd *sdp = gl->gl_name.ln_sbd;
struct address_space *mapping = &sdp->sd_aspace;
struct gfs2_rgrpd *rgd = gl->gl_object;
if (rgd)
gfs2_rgrp_brelse(rgd);
WARN_ON_ONCE(!(flags & DIO_METADATA));
gfs2_assert_withdraw(sdp, !atomic_read(&gl->gl_ail_count));
truncate_inode_pages_range(mapping, gl->gl_vm.start, gl->gl_vm.end);
if (rgd)
rgd->rd_flags &= ~GFS2_RDF_UPTODATE;
}
int
xfs_flushinval_pages(
xfs_inode_t *ip,
xfs_off_t first,
xfs_off_t last,
int fiopt)
{
struct address_space *mapping = VFS_I(ip)->i_mapping;
int ret = 0;
trace_xfs_pagecache_inval(ip, first, last);
xfs_iflags_clear(ip, XFS_ITRUNCATED);
ret = filemap_write_and_wait_range(mapping, first,
last == -1 ? LLONG_MAX : last);
if (!ret)
truncate_inode_pages_range(mapping, first, last);
return -ret;
}
/**
* truncate_pagecache_range - unmap and remove pagecache that is hole-punched
* @inode: inode
* @lstart: offset of beginning of hole
* @lend: offset of last byte of hole
*
* This function should typically be called before the filesystem
* releases resources associated with the freed range (eg. deallocates
* blocks). This way, pagecache will always stay logically coherent
* with on-disk format, and the filesystem would not have to deal with
* situations such as writepage being called for a page that has already
* had its underlying blocks deallocated.
*/
void truncate_pagecache_range(struct inode *inode, loff_t lstart, loff_t lend)
{
struct address_space *mapping = inode->i_mapping;
loff_t unmap_start = round_up(lstart, PAGE_SIZE);
loff_t unmap_end = round_down(1 + lend, PAGE_SIZE) - 1;
/*
* This rounding is currently just for example: unmap_mapping_range
* expands its hole outwards, whereas we want it to contract the hole
* inwards. However, existing callers of truncate_pagecache_range are
* doing their own page rounding first. Note that unmap_mapping_range
* allows holelen 0 for all, and we allow lend -1 for end of file.
*/
/*
* Unlike in truncate_pagecache, unmap_mapping_range is called only
* once (before truncating pagecache), and without "even_cows" flag:
* hole-punching should not remove private COWed pages from the hole.
*/
if ((u64)unmap_end > (u64)unmap_start)
unmap_mapping_range(mapping, unmap_start,
1 + unmap_end - unmap_start, 0);
truncate_inode_pages_range(mapping, lstart, lend);
}
static ssize_t gfs2_direct_IO(int rw, struct kiocb *iocb,
const struct iovec *iov, loff_t offset,
unsigned long nr_segs)
{
struct file *file = iocb->ki_filp;
struct inode *inode = file->f_mapping->host;
struct address_space *mapping = inode->i_mapping;
struct gfs2_inode *ip = GFS2_I(inode);
struct gfs2_holder gh;
int rv;
/*
* Deferred lock, even if its a write, since we do no allocation
* on this path. All we need change is atime, and this lock mode
* ensures that other nodes have flushed their buffered read caches
* (i.e. their page cache entries for this inode). We do not,
* unfortunately have the option of only flushing a range like
* the VFS does.
*/
gfs2_holder_init(ip->i_gl, LM_ST_DEFERRED, 0, &gh);
rv = gfs2_glock_nq(&gh);
if (rv)
return rv;
rv = gfs2_ok_for_dio(ip, rw, offset);
if (rv != 1)
goto out; /* dio not valid, fall back to buffered i/o */
/*
* Now since we are holding a deferred (CW) lock at this point, you
* might be wondering why this is ever needed. There is a case however
* where we've granted a deferred local lock against a cached exclusive
* glock. That is ok provided all granted local locks are deferred, but
* it also means that it is possible to encounter pages which are
* cached and possibly also mapped. So here we check for that and sort
* them out ahead of the dio. The glock state machine will take care of
* everything else.
*
* If in fact the cached glock state (gl->gl_state) is deferred (CW) in
* the first place, mapping->nr_pages will always be zero.
*/
if (mapping->nrpages) {
loff_t lstart = offset & (PAGE_CACHE_SIZE - 1);
loff_t len = iov_length(iov, nr_segs);
loff_t end = PAGE_ALIGN(offset + len) - 1;
rv = 0;
if (len == 0)
goto out;
if (test_and_clear_bit(GIF_SW_PAGED, &ip->i_flags))
unmap_shared_mapping_range(ip->i_inode.i_mapping, offset, len);
rv = filemap_write_and_wait_range(mapping, lstart, end);
if (rv)
goto out;
if (rw == WRITE)
truncate_inode_pages_range(mapping, lstart, end);
}
rv = __blockdev_direct_IO(rw, iocb, inode, inode->i_sb->s_bdev, iov,
offset, nr_segs, gfs2_get_block_direct,
NULL, NULL, 0);
out:
gfs2_glock_dq(&gh);
gfs2_holder_uninit(&gh);
return rv;
}
int f2fs_recover_fsync_data(struct f2fs_sb_info *sbi, bool check_only)
{
struct list_head inode_list, tmp_inode_list;
struct list_head dir_list;
int err;
int ret = 0;
unsigned long s_flags = sbi->sb->s_flags;
bool need_writecp = false;
#ifdef CONFIG_QUOTA
int quota_enabled;
#endif
if (s_flags & SB_RDONLY) {
f2fs_msg(sbi->sb, KERN_INFO,
"recover fsync data on readonly fs");
sbi->sb->s_flags &= ~SB_RDONLY;
}
#ifdef CONFIG_QUOTA
/* Needed for iput() to work correctly and not trash data */
sbi->sb->s_flags |= SB_ACTIVE;
/* Turn on quotas so that they are updated correctly */
quota_enabled = f2fs_enable_quota_files(sbi, s_flags & SB_RDONLY);
#endif
fsync_entry_slab = f2fs_kmem_cache_create("f2fs_fsync_inode_entry",
sizeof(struct fsync_inode_entry));
if (!fsync_entry_slab) {
err = -ENOMEM;
goto out;
}
INIT_LIST_HEAD(&inode_list);
INIT_LIST_HEAD(&tmp_inode_list);
INIT_LIST_HEAD(&dir_list);
/* prevent checkpoint */
mutex_lock(&sbi->cp_mutex);
/* step #1: find fsynced inode numbers */
err = find_fsync_dnodes(sbi, &inode_list, check_only);
if (err || list_empty(&inode_list))
goto skip;
if (check_only) {
ret = 1;
goto skip;
}
need_writecp = true;
/* step #2: recover data */
err = recover_data(sbi, &inode_list, &tmp_inode_list, &dir_list);
if (!err)
f2fs_bug_on(sbi, !list_empty(&inode_list));
else {
/* restore s_flags to let iput() trash data */
sbi->sb->s_flags = s_flags;
}
skip:
destroy_fsync_dnodes(&inode_list, err);
destroy_fsync_dnodes(&tmp_inode_list, err);
/* truncate meta pages to be used by the recovery */
truncate_inode_pages_range(META_MAPPING(sbi),
(loff_t)MAIN_BLKADDR(sbi) << PAGE_SHIFT, -1);
if (err) {
truncate_inode_pages_final(NODE_MAPPING(sbi));
truncate_inode_pages_final(META_MAPPING(sbi));
} else {
clear_sbi_flag(sbi, SBI_POR_DOING);
}
mutex_unlock(&sbi->cp_mutex);
/* let's drop all the directory inodes for clean checkpoint */
destroy_fsync_dnodes(&dir_list, err);
if (need_writecp) {
set_sbi_flag(sbi, SBI_IS_RECOVERED);
if (!err) {
struct cp_control cpc = {
.reason = CP_RECOVERY,
};
err = f2fs_write_checkpoint(sbi, &cpc);
}
}
kmem_cache_destroy(fsync_entry_slab);
out:
#ifdef CONFIG_QUOTA
/* Turn quotas off */
if (quota_enabled)
f2fs_quota_off_umount(sbi->sb);
#endif
sbi->sb->s_flags = s_flags; /* Restore SB_RDONLY status */
return ret ? ret: err;
}
static long cifs_ioctl_clone(unsigned int xid, struct file *dst_file,
unsigned long srcfd, u64 off, u64 len, u64 destoff)
{
int rc;
struct cifsFileInfo *smb_file_target = dst_file->private_data;
struct inode *target_inode = file_inode(dst_file);
struct cifs_tcon *target_tcon;
struct fd src_file;
struct cifsFileInfo *smb_file_src;
struct inode *src_inode;
struct cifs_tcon *src_tcon;
cifs_dbg(FYI, "ioctl clone range\n");
/* the destination must be opened for writing */
if (!(dst_file->f_mode & FMODE_WRITE)) {
cifs_dbg(FYI, "file target not open for write\n");
return -EINVAL;
}
/* check if target volume is readonly and take reference */
rc = mnt_want_write_file(dst_file);
if (rc) {
cifs_dbg(FYI, "mnt_want_write failed with rc %d\n", rc);
return rc;
}
src_file = fdget(srcfd);
if (!src_file.file) {
rc = -EBADF;
goto out_drop_write;
}
if ((!src_file.file->private_data) || (!dst_file->private_data)) {
rc = -EBADF;
cifs_dbg(VFS, "missing cifsFileInfo on copy range src file\n");
goto out_fput;
}
rc = -EXDEV;
smb_file_target = dst_file->private_data;
smb_file_src = src_file.file->private_data;
src_tcon = tlink_tcon(smb_file_src->tlink);
target_tcon = tlink_tcon(smb_file_target->tlink);
/* check if source and target are on same tree connection */
if (src_tcon != target_tcon) {
cifs_dbg(VFS, "file copy src and target on different volume\n");
goto out_fput;
}
src_inode = src_file.file->f_dentry->d_inode;
/*
* Note: cifs case is easier than btrfs since server responsible for
* checks for proper open modes and file type and if it wants
* server could even support copy of range where source = target
*/
/* so we do not deadlock racing two ioctls on same files */
if (target_inode < src_inode) {
mutex_lock_nested(&target_inode->i_mutex, I_MUTEX_PARENT);
mutex_lock_nested(&src_inode->i_mutex, I_MUTEX_CHILD);
} else {
mutex_lock_nested(&src_inode->i_mutex, I_MUTEX_PARENT);
mutex_lock_nested(&target_inode->i_mutex, I_MUTEX_CHILD);
}
/* determine range to clone */
rc = -EINVAL;
if (off + len > src_inode->i_size || off + len < off)
goto out_unlock;
if (len == 0)
len = src_inode->i_size - off;
cifs_dbg(FYI, "about to flush pages\n");
/* should we flush first and last page first */
truncate_inode_pages_range(&target_inode->i_data, destoff,
PAGE_CACHE_ALIGN(destoff + len)-1);
if (target_tcon->ses->server->ops->clone_range)
rc = target_tcon->ses->server->ops->clone_range(xid,
smb_file_src, smb_file_target, off, len, destoff);
/* force revalidate of size and timestamps of target file now
that target is updated on the server */
CIFS_I(target_inode)->time = 0;
out_unlock:
/* although unlocking in the reverse order from locking is not
strictly necessary here it is a little cleaner to be consistent */
if (target_inode < src_inode) {
mutex_unlock(&src_inode->i_mutex);
mutex_unlock(&target_inode->i_mutex);
} else {
mutex_unlock(&target_inode->i_mutex);
mutex_unlock(&src_inode->i_mutex);
}
out_fput:
fdput(src_file);
out_drop_write:
mnt_drop_write_file(dst_file);
return rc;
}
/*
* Link a range of blocks from one file to another.
*/
int
xfs_reflink_remap_range(
struct file *file_in,
loff_t pos_in,
struct file *file_out,
loff_t pos_out,
u64 len,
bool is_dedupe)
{
struct inode *inode_in = file_inode(file_in);
struct xfs_inode *src = XFS_I(inode_in);
struct inode *inode_out = file_inode(file_out);
struct xfs_inode *dest = XFS_I(inode_out);
struct xfs_mount *mp = src->i_mount;
bool same_inode = (inode_in == inode_out);
xfs_fileoff_t sfsbno, dfsbno;
xfs_filblks_t fsblen;
xfs_extlen_t cowextsize;
ssize_t ret;
if (!xfs_sb_version_hasreflink(&mp->m_sb))
return -EOPNOTSUPP;
if (XFS_FORCED_SHUTDOWN(mp))
return -EIO;
/* Lock both files against IO */
lock_two_nondirectories(inode_in, inode_out);
if (same_inode)
xfs_ilock(src, XFS_MMAPLOCK_EXCL);
else
xfs_lock_two_inodes(src, dest, XFS_MMAPLOCK_EXCL);
/* Check file eligibility and prepare for block sharing. */
ret = -EINVAL;
/* Don't reflink realtime inodes */
if (XFS_IS_REALTIME_INODE(src) || XFS_IS_REALTIME_INODE(dest))
goto out_unlock;
/* Don't share DAX file data for now. */
if (IS_DAX(inode_in) || IS_DAX(inode_out))
goto out_unlock;
ret = vfs_clone_file_prep_inodes(inode_in, pos_in, inode_out, pos_out,
&len, is_dedupe);
if (ret <= 0)
goto out_unlock;
trace_xfs_reflink_remap_range(src, pos_in, len, dest, pos_out);
/* Set flags and remap blocks. */
ret = xfs_reflink_set_inode_flag(src, dest);
if (ret)
goto out_unlock;
dfsbno = XFS_B_TO_FSBT(mp, pos_out);
sfsbno = XFS_B_TO_FSBT(mp, pos_in);
fsblen = XFS_B_TO_FSB(mp, len);
ret = xfs_reflink_remap_blocks(src, sfsbno, dest, dfsbno, fsblen,
pos_out + len);
if (ret)
goto out_unlock;
/* Zap any page cache for the destination file's range. */
truncate_inode_pages_range(&inode_out->i_data, pos_out,
PAGE_ALIGN(pos_out + len) - 1);
/*
* Carry the cowextsize hint from src to dest if we're sharing the
* entire source file to the entire destination file, the source file
* has a cowextsize hint, and the destination file does not.
*/
cowextsize = 0;
if (pos_in == 0 && len == i_size_read(inode_in) &&
(src->i_d.di_flags2 & XFS_DIFLAG2_COWEXTSIZE) &&
pos_out == 0 && len >= i_size_read(inode_out) &&
!(dest->i_d.di_flags2 & XFS_DIFLAG2_COWEXTSIZE))
cowextsize = src->i_d.di_cowextsize;
ret = xfs_reflink_update_dest(dest, pos_out + len, cowextsize,
is_dedupe);
out_unlock:
xfs_iunlock(src, XFS_MMAPLOCK_EXCL);
if (!same_inode)
xfs_iunlock(dest, XFS_MMAPLOCK_EXCL);
unlock_two_nondirectories(inode_in, inode_out);
if (ret)
trace_xfs_reflink_remap_range_error(dest, ret, _RET_IP_);
return ret;
}
/**
* truncate_inode_pages - truncate *all* the pages from an offset
* @mapping: mapping to truncate
* @lstart: offset from which to truncate
*
* Called under (and serialised by) inode->i_mutex.
*
* Note: When this function returns, there can be a page in the process of
* deletion (inside __delete_from_page_cache()) in the specified range. Thus
* mapping->nrpages can be non-zero when this function returns even after
* truncation of the whole mapping.
*/
void truncate_inode_pages(struct address_space *mapping, loff_t lstart)
{
truncate_inode_pages_range(mapping, lstart, (loff_t)-1);
}
///////////////////////////////////////////////////////////
// ufsd_log
//
//
///////////////////////////////////////////////////////////
static void
ufsd_log(
IN const char * fmt,
IN int len
)
{
if ( len <= 0 || 0 == fmt[0] )
return;
if ( !log_file_opened && 0 != ufsd_trace_file[0] ) {
log_file_opened = 1;
log_file = filp_open( ufsd_trace_file, O_WRONLY | O_CREAT | O_TRUNC, S_IRUGO | S_IWUGO );
if ( IS_ERR(log_file) ) {
long error = PTR_ERR(log_file);
log_file = NULL;
printk(KERN_NOTICE QUOTED_UFSD_DEVICE": failed to start log to '%s' (errno=%ld), using system log\n", ufsd_trace_file, -error);
}
else {
assert(NULL != log_file);
}
}
if ( NULL != log_file && NULL != log_file->f_op && NULL != log_file->f_op->write && !log_file_error ) {
mm_segment_t old_limit = get_fs();
long error = 0;
set_fs( KERNEL_DS );
if ( 0 != UFSD_CycleMB ) {
size_t bytes = UFSD_CycleMB << 20;
int to_write = log_file->f_pos + len > bytes? (bytes - log_file->f_pos) : len;
assert( to_write >= 0 );
if ( to_write <= 0 )
to_write = 0;
else {
error = log_file->f_op->write(log_file, fmt, to_write, &log_file->f_pos);
if ( error < 0 )
log_file_error = error;
fmt += to_write;
len -= to_write;
}
if ( 0 != len )
log_file->f_pos = 0;
}
if ( 0 != len ) {
error = log_file->f_op->write(log_file, fmt, len, &log_file->f_pos );
if ( error < 0 )
log_file_error = error;
}
#if 0 // LINUX_VERSION_CODE >= KERNEL_VERSION(2,6,26)
if ( 0 == log_file_error ) {
struct address_space* m = log_file->f_dentry->d_inode->i_mapping;
long hint = log_file->f_pos - 4*PAGE_SIZE;
if ( m->nrpages > 32 && hint > 0 ) {
unsigned end = hint & ~(PAGE_SIZE - 1);
// unsigned long nrpages = m->nrpages;
int err = filemap_fdatawrite_range( m, 0, end - 1 );
if ( 0 == err )
truncate_inode_pages_range( m, 0, end - 1 );
// printk("truncate_inode_pages_range %x, %lu -> %lu, %d\n", end, nrpages, m->nrpages, err );
}
}
#endif
set_fs(old_limit);
if ( error < 0 )
printk("log write failed: %ld\n", -error);
}
// Comment out this 'else' to duplicate the output to klog.
else {
printk( KERN_NOTICE QUOTED_UFSD_DEVICE":%s", fmt );
}
}
static int nfs42_clone_file_range(struct file *src_file, loff_t src_off,
struct file *dst_file, loff_t dst_off, u64 count)
{
struct inode *dst_inode = file_inode(dst_file);
struct nfs_server *server = NFS_SERVER(dst_inode);
struct inode *src_inode = file_inode(src_file);
unsigned int bs = server->clone_blksize;
bool same_inode = false;
int ret;
/* check alignment w.r.t. clone_blksize */
ret = -EINVAL;
if (bs) {
if (!IS_ALIGNED(src_off, bs) || !IS_ALIGNED(dst_off, bs))
goto out;
if (!IS_ALIGNED(count, bs) && i_size_read(src_inode) != (src_off + count))
goto out;
}
if (src_inode == dst_inode)
same_inode = true;
/* XXX: do we lock at all? what if server needs CB_RECALL_LAYOUT? */
if (same_inode) {
inode_lock(src_inode);
} else if (dst_inode < src_inode) {
inode_lock_nested(dst_inode, I_MUTEX_PARENT);
inode_lock_nested(src_inode, I_MUTEX_CHILD);
} else {
inode_lock_nested(src_inode, I_MUTEX_PARENT);
inode_lock_nested(dst_inode, I_MUTEX_CHILD);
}
/* flush all pending writes on both src and dst so that server
* has the latest data */
ret = nfs_sync_inode(src_inode);
if (ret)
goto out_unlock;
ret = nfs_sync_inode(dst_inode);
if (ret)
goto out_unlock;
ret = nfs42_proc_clone(src_file, dst_file, src_off, dst_off, count);
/* truncate inode page cache of the dst range so that future reads can fetch
* new data from server */
if (!ret)
truncate_inode_pages_range(&dst_inode->i_data, dst_off, dst_off + count - 1);
out_unlock:
if (same_inode) {
inode_unlock(src_inode);
} else if (dst_inode < src_inode) {
inode_unlock(src_inode);
inode_unlock(dst_inode);
} else {
inode_unlock(dst_inode);
inode_unlock(src_inode);
}
out:
return ret;
}
