static int inode_go_lock(struct gfs2_holder *gh)
{
struct gfs2_glock *gl = gh->gh_gl;
struct gfs2_sbd *sdp = gl->gl_name.ln_sbd;
struct gfs2_inode *ip = gl->gl_object;
int error = 0;
if (!ip || (gh->gh_flags & GL_SKIP))
return 0;
if (test_bit(GIF_INVALID, &ip->i_flags)) {
error = gfs2_inode_refresh(ip);
if (error)
return error;
}
if (gh->gh_state != LM_ST_DEFERRED)
inode_dio_wait(&ip->i_inode);
if ((ip->i_diskflags & GFS2_DIF_TRUNC_IN_PROG) &&
(gl->gl_state == LM_ST_EXCLUSIVE) &&
(gh->gh_state == LM_ST_EXCLUSIVE)) {
spin_lock(&sdp->sd_trunc_lock);
if (list_empty(&ip->i_trunc_list))
list_add(&ip->i_trunc_list, &sdp->sd_trunc_list);
spin_unlock(&sdp->sd_trunc_lock);
wake_up(&sdp->sd_quota_wait);
return 1;
}
return error;
}
static int vvp_io_setattr_trunc(const struct lu_env *env,
const struct cl_io_slice *ios,
struct inode *inode, loff_t size)
{
inode_dio_wait(inode);
return 0;
}
int jfs_setattr(struct dentry *dentry, struct iattr *iattr)
{
struct inode *inode = dentry->d_inode;
int rc;
rc = inode_change_ok(inode, iattr);
if (rc)
return rc;
if (is_quota_modification(inode, iattr))
dquot_initialize(inode);
if ((iattr->ia_valid & ATTR_UID && iattr->ia_uid != inode->i_uid) ||
(iattr->ia_valid & ATTR_GID && iattr->ia_gid != inode->i_gid)) {
rc = dquot_transfer(inode, iattr);
if (rc)
return rc;
}
if ((iattr->ia_valid & ATTR_SIZE) &&
iattr->ia_size != i_size_read(inode)) {
inode_dio_wait(inode);
rc = vmtruncate(inode, iattr->ia_size);
if (rc)
return rc;
}
setattr_copy(inode, iattr);
mark_inode_dirty(inode);
if (iattr->ia_valid & ATTR_MODE)
rc = jfs_acl_chmod(inode);
return rc;
}
/*
* Pre-COW all shared blocks within a given byte range of a file and turn off
* the reflink flag if we unshare all of the file's blocks.
*/
int
xfs_reflink_unshare(
struct xfs_inode *ip,
xfs_off_t offset,
xfs_off_t len)
{
struct xfs_mount *mp = ip->i_mount;
xfs_fileoff_t fbno;
xfs_filblks_t end;
xfs_off_t isize;
int error;
if (!xfs_is_reflink_inode(ip))
return 0;
trace_xfs_reflink_unshare(ip, offset, len);
inode_dio_wait(VFS_I(ip));
/* Try to CoW the selected ranges */
xfs_ilock(ip, XFS_ILOCK_EXCL);
fbno = XFS_B_TO_FSBT(mp, offset);
isize = i_size_read(VFS_I(ip));
end = XFS_B_TO_FSB(mp, offset + len);
error = xfs_reflink_dirty_extents(ip, fbno, end, isize);
if (error)
goto out_unlock;
xfs_iunlock(ip, XFS_ILOCK_EXCL);
/* Wait for the IO to finish */
error = filemap_write_and_wait(VFS_I(ip)->i_mapping);
if (error)
goto out;
/* Turn off the reflink flag if possible. */
error = xfs_reflink_try_clear_inode_flag(ip);
if (error)
goto out;
return 0;
out_unlock:
xfs_iunlock(ip, XFS_ILOCK_EXCL);
out:
trace_xfs_reflink_unshare_error(ip, error, _RET_IP_);
return error;
}
int jfs_setattr(struct dentry *dentry, struct iattr *iattr)
{
struct inode *inode = d_inode(dentry);
int rc;
rc = setattr_prepare(dentry, iattr);
if (rc)
return rc;
if (is_quota_modification(inode, iattr)) {
rc = dquot_initialize(inode);
if (rc)
return rc;
}
if ((iattr->ia_valid & ATTR_UID && !uid_eq(iattr->ia_uid, inode->i_uid)) ||
(iattr->ia_valid & ATTR_GID && !gid_eq(iattr->ia_gid, inode->i_gid))) {
rc = dquot_transfer(inode, iattr);
if (rc)
return rc;
}
if ((iattr->ia_valid & ATTR_SIZE) &&
iattr->ia_size != i_size_read(inode)) {
inode_dio_wait(inode);
rc = inode_newsize_ok(inode, iattr->ia_size);
if (rc)
return rc;
truncate_setsize(inode, iattr->ia_size);
jfs_truncate(inode);
}
setattr_copy(inode, iattr);
mark_inode_dirty(inode);
if (iattr->ia_valid & ATTR_MODE)
rc = posix_acl_chmod(inode, inode->i_mode);
return rc;
}
int nilfs_setattr(struct dentry *dentry, struct iattr *iattr)
{
struct nilfs_transaction_info ti;
struct inode *inode = dentry->d_inode;
struct super_block *sb = inode->i_sb;
int err;
err = inode_change_ok(inode, iattr);
if (err)
return err;
err = nilfs_transaction_begin(sb, &ti, 0);
if (unlikely(err))
return err;
if ((iattr->ia_valid & ATTR_SIZE) &&
iattr->ia_size != i_size_read(inode)) {
inode_dio_wait(inode);
err = vmtruncate(inode, iattr->ia_size);
if (unlikely(err))
goto out_err;
}
setattr_copy(inode, iattr);
mark_inode_dirty(inode);
if (iattr->ia_valid & ATTR_MODE) {
err = nilfs_acl_chmod(inode);
if (unlikely(err))
goto out_err;
}
return nilfs_transaction_commit(sb);
out_err:
nilfs_transaction_abort(sb);
return err;
}
static void inode_go_sync(struct gfs2_glock *gl)
{
struct gfs2_inode *ip = gfs2_glock2inode(gl);
int isreg = ip && S_ISREG(ip->i_inode.i_mode);
struct address_space *metamapping = gfs2_glock2aspace(gl);
int error;
if (isreg) {
if (test_and_clear_bit(GIF_SW_PAGED, &ip->i_flags))
unmap_shared_mapping_range(ip->i_inode.i_mapping, 0, 0);
inode_dio_wait(&ip->i_inode);
}
if (!test_and_clear_bit(GLF_DIRTY, &gl->gl_flags))
goto out;
GLOCK_BUG_ON(gl, gl->gl_state != LM_ST_EXCLUSIVE);
gfs2_log_flush(gl->gl_name.ln_sbd, gl, GFS2_LOG_HEAD_FLUSH_NORMAL |
GFS2_LFC_INODE_GO_SYNC);
filemap_fdatawrite(metamapping);
if (isreg) {
struct address_space *mapping = ip->i_inode.i_mapping;
filemap_fdatawrite(mapping);
error = filemap_fdatawait(mapping);
mapping_set_error(mapping, error);
}
error = filemap_fdatawait(metamapping);
mapping_set_error(metamapping, error);
gfs2_ail_empty_gl(gl);
/*
* Writeback of the data mapping may cause the dirty flag to be set
* so we have to clear it again here.
*/
smp_mb__before_atomic();
clear_bit(GLF_DIRTY, &gl->gl_flags);
out:
gfs2_clear_glop_pending(ip);
}
static void inode_go_sync(struct gfs2_glock *gl)
{
struct gfs2_inode *ip = gl->gl_object;
struct address_space *metamapping = gfs2_glock2aspace(gl);
int error;
if (ip && !S_ISREG(ip->i_inode.i_mode))
ip = NULL;
if (ip) {
if (test_and_clear_bit(GIF_SW_PAGED, &ip->i_flags))
unmap_shared_mapping_range(ip->i_inode.i_mapping, 0, 0);
inode_dio_wait(&ip->i_inode);
}
if (!test_and_clear_bit(GLF_DIRTY, &gl->gl_flags))
return;
GLOCK_BUG_ON(gl, gl->gl_state != LM_ST_EXCLUSIVE);
gfs2_log_flush(gl->gl_sbd, gl, NORMAL_FLUSH);
filemap_fdatawrite(metamapping);
if (ip) {
struct address_space *mapping = ip->i_inode.i_mapping;
filemap_fdatawrite(mapping);
error = filemap_fdatawait(mapping);
mapping_set_error(mapping, error);
}
error = filemap_fdatawait(metamapping);
mapping_set_error(metamapping, error);
gfs2_ail_empty_gl(gl);
/*
* Writeback of the data mapping may cause the dirty flag to be set
* so we have to clear it again here.
*/
smp_mb__before_atomic();
clear_bit(GLF_DIRTY, &gl->gl_flags);
}
/*
* inode->i_mutex: down
*/
int
reiserfs_xattr_set_handle(struct reiserfs_transaction_handle *th,
struct inode *inode, const char *name,
const void *buffer, size_t buffer_size, int flags)
{
int err = 0;
struct dentry *dentry;
struct page *page;
char *data;
size_t file_pos = 0;
size_t buffer_pos = 0;
size_t new_size;
__u32 xahash = 0;
if (get_inode_sd_version(inode) == STAT_DATA_V1)
return -EOPNOTSUPP;
reiserfs_write_unlock(inode->i_sb);
if (!buffer) {
err = lookup_and_delete_xattr(inode, name);
reiserfs_write_lock(inode->i_sb);
return err;
}
dentry = xattr_lookup(inode, name, flags);
if (IS_ERR(dentry)) {
reiserfs_write_lock(inode->i_sb);
return PTR_ERR(dentry);
}
down_write(&REISERFS_I(inode)->i_xattr_sem);
reiserfs_write_lock(inode->i_sb);
xahash = xattr_hash(buffer, buffer_size);
while (buffer_pos < buffer_size || buffer_pos == 0) {
size_t chunk;
size_t skip = 0;
size_t page_offset = (file_pos & (PAGE_CACHE_SIZE - 1));
if (buffer_size - buffer_pos > PAGE_CACHE_SIZE)
chunk = PAGE_CACHE_SIZE;
else
chunk = buffer_size - buffer_pos;
page = reiserfs_get_page(dentry->d_inode, file_pos);
if (IS_ERR(page)) {
err = PTR_ERR(page);
goto out_unlock;
}
lock_page(page);
data = page_address(page);
if (file_pos == 0) {
struct reiserfs_xattr_header *rxh;
skip = file_pos = sizeof(struct reiserfs_xattr_header);
if (chunk + skip > PAGE_CACHE_SIZE)
chunk = PAGE_CACHE_SIZE - skip;
rxh = (struct reiserfs_xattr_header *)data;
rxh->h_magic = cpu_to_le32(REISERFS_XATTR_MAGIC);
rxh->h_hash = cpu_to_le32(xahash);
}
err = __reiserfs_write_begin(page, page_offset, chunk + skip);
if (!err) {
if (buffer)
memcpy(data + skip, buffer + buffer_pos, chunk);
err = reiserfs_commit_write(NULL, page, page_offset,
page_offset + chunk +
skip);
}
unlock_page(page);
reiserfs_put_page(page);
buffer_pos += chunk;
file_pos += chunk;
skip = 0;
if (err || buffer_size == 0 || !buffer)
break;
}
new_size = buffer_size + sizeof(struct reiserfs_xattr_header);
if (!err && new_size < i_size_read(dentry->d_inode)) {
struct iattr newattrs = {
.ia_ctime = current_fs_time(inode->i_sb),
.ia_size = new_size,
.ia_valid = ATTR_SIZE | ATTR_CTIME,
};
reiserfs_write_unlock(inode->i_sb);
mutex_lock_nested(&dentry->d_inode->i_mutex, I_MUTEX_XATTR);
inode_dio_wait(dentry->d_inode);
reiserfs_write_lock(inode->i_sb);
err = reiserfs_setattr(dentry, &newattrs);
mutex_unlock(&dentry->d_inode->i_mutex);
} else
update_ctime(inode);
out_unlock:
up_write(&REISERFS_I(inode)->i_xattr_sem);
dput(dentry);
return err;
}
int notify_change(struct dentry * dentry, struct iattr * attr)
{
struct inode *inode = dentry->d_inode;
mode_t mode = inode->i_mode;
int error;
struct timespec now;
unsigned int ia_valid = attr->ia_valid;
if (ia_valid & (ATTR_MODE | ATTR_UID | ATTR_GID | ATTR_TIMES_SET)) {
if (IS_IMMUTABLE(inode) || IS_APPEND(inode))
return -EPERM;
}
if ((ia_valid & ATTR_MODE)) {
mode_t amode = attr->ia_mode;
/* Flag setting protected by i_mutex */
if (is_sxid(amode))
inode->i_flags &= ~S_NOSEC;
}
now = current_fs_time(inode->i_sb);
attr->ia_ctime = now;
if (!(ia_valid & ATTR_ATIME_SET))
attr->ia_atime = now;
if (!(ia_valid & ATTR_MTIME_SET))
attr->ia_mtime = now;
if (ia_valid & ATTR_KILL_PRIV) {
attr->ia_valid &= ~ATTR_KILL_PRIV;
ia_valid &= ~ATTR_KILL_PRIV;
error = security_inode_need_killpriv(dentry);
if (error > 0)
error = security_inode_killpriv(dentry);
if (error)
return error;
}
/*
* We now pass ATTR_KILL_S*ID to the lower level setattr function so
* that the function has the ability to reinterpret a mode change
* that's due to these bits. This adds an implicit restriction that
* no function will ever call notify_change with both ATTR_MODE and
* ATTR_KILL_S*ID set.
*/
if ((ia_valid & (ATTR_KILL_SUID|ATTR_KILL_SGID)) &&
(ia_valid & ATTR_MODE))
BUG();
if (ia_valid & ATTR_KILL_SUID) {
if (mode & S_ISUID) {
ia_valid = attr->ia_valid |= ATTR_MODE;
attr->ia_mode = (inode->i_mode & ~S_ISUID);
}
}
if (ia_valid & ATTR_KILL_SGID) {
if ((mode & (S_ISGID | S_IXGRP)) == (S_ISGID | S_IXGRP)) {
if (!(ia_valid & ATTR_MODE)) {
ia_valid = attr->ia_valid |= ATTR_MODE;
attr->ia_mode = inode->i_mode;
}
attr->ia_mode &= ~S_ISGID;
}
}
if (!(attr->ia_valid & ~(ATTR_KILL_SUID | ATTR_KILL_SGID)))
return 0;
error = security_inode_setattr(dentry, attr);
if (error)
return error;
if (ia_valid & ATTR_SIZE)
inode_dio_wait(inode);
if (inode->i_op->setattr)
error = inode->i_op->setattr(dentry, attr);
else
error = simple_setattr(dentry, attr);
if (!error)
fsnotify_change(dentry, ia_valid);
return error;
}
/**
* Swap the information from the given @inode and the inode
* EXT4_BOOT_LOADER_INO. It will basically swap i_data and all other
* important fields of the inodes.
*
* @sb: the super block of the filesystem
* @inode: the inode to swap with EXT4_BOOT_LOADER_INO
*
*/
static long swap_inode_boot_loader(struct super_block *sb,
struct inode *inode)
{
handle_t *handle;
int err;
struct inode *inode_bl;
struct ext4_inode_info *ei_bl;
qsize_t size, size_bl, diff;
blkcnt_t blocks;
unsigned short bytes;
inode_bl = ext4_iget(sb, EXT4_BOOT_LOADER_INO, EXT4_IGET_SPECIAL);
if (IS_ERR(inode_bl))
return PTR_ERR(inode_bl);
ei_bl = EXT4_I(inode_bl);
/* Protect orig inodes against a truncate and make sure,
* that only 1 swap_inode_boot_loader is running. */
lock_two_nondirectories(inode, inode_bl);
if (inode->i_nlink != 1 || !S_ISREG(inode->i_mode) ||
IS_SWAPFILE(inode) || IS_ENCRYPTED(inode) ||
(EXT4_I(inode)->i_flags & EXT4_JOURNAL_DATA_FL) ||
ext4_has_inline_data(inode)) {
err = -EINVAL;
goto journal_err_out;
}
if (IS_RDONLY(inode) || IS_APPEND(inode) || IS_IMMUTABLE(inode) ||
!inode_owner_or_capable(inode) || !capable(CAP_SYS_ADMIN)) {
err = -EPERM;
goto journal_err_out;
}
down_write(&EXT4_I(inode)->i_mmap_sem);
err = filemap_write_and_wait(inode->i_mapping);
if (err)
goto err_out;
err = filemap_write_and_wait(inode_bl->i_mapping);
if (err)
goto err_out;
/* Wait for all existing dio workers */
inode_dio_wait(inode);
inode_dio_wait(inode_bl);
truncate_inode_pages(&inode->i_data, 0);
truncate_inode_pages(&inode_bl->i_data, 0);
handle = ext4_journal_start(inode_bl, EXT4_HT_MOVE_EXTENTS, 2);
if (IS_ERR(handle)) {
err = -EINVAL;
goto err_out;
}
/* Protect extent tree against block allocations via delalloc */
ext4_double_down_write_data_sem(inode, inode_bl);
if (inode_bl->i_nlink == 0) {
/* this inode has never been used as a BOOT_LOADER */
set_nlink(inode_bl, 1);
i_uid_write(inode_bl, 0);
i_gid_write(inode_bl, 0);
inode_bl->i_flags = 0;
ei_bl->i_flags = 0;
inode_set_iversion(inode_bl, 1);
i_size_write(inode_bl, 0);
inode_bl->i_mode = S_IFREG;
if (ext4_has_feature_extents(sb)) {
ext4_set_inode_flag(inode_bl, EXT4_INODE_EXTENTS);
ext4_ext_tree_init(handle, inode_bl);
} else
memset(ei_bl->i_data, 0, sizeof(ei_bl->i_data));
}
err = dquot_initialize(inode);
if (err)
goto err_out1;
size = (qsize_t)(inode->i_blocks) * (1 << 9) + inode->i_bytes;
size_bl = (qsize_t)(inode_bl->i_blocks) * (1 << 9) + inode_bl->i_bytes;
diff = size - size_bl;
swap_inode_data(inode, inode_bl);
inode->i_ctime = inode_bl->i_ctime = current_time(inode);
inode->i_generation = prandom_u32();
inode_bl->i_generation = prandom_u32();
reset_inode_seed(inode);
reset_inode_seed(inode_bl);
ext4_discard_preallocations(inode);
err = ext4_mark_inode_dirty(handle, inode);
if (err < 0) {
/* No need to update quota information. */
ext4_warning(inode->i_sb,
"couldn't mark inode #%lu dirty (err %d)",
inode->i_ino, err);
/* Revert all changes: */
swap_inode_data(inode, inode_bl);
ext4_mark_inode_dirty(handle, inode);
goto err_out1;
}
blocks = inode_bl->i_blocks;
bytes = inode_bl->i_bytes;
inode_bl->i_blocks = inode->i_blocks;
inode_bl->i_bytes = inode->i_bytes;
err = ext4_mark_inode_dirty(handle, inode_bl);
if (err < 0) {
/* No need to update quota information. */
ext4_warning(inode_bl->i_sb,
"couldn't mark inode #%lu dirty (err %d)",
inode_bl->i_ino, err);
goto revert;
}
/* Bootloader inode should not be counted into quota information. */
if (diff > 0)
dquot_free_space(inode, diff);
else
err = dquot_alloc_space(inode, -1 * diff);
if (err < 0) {
revert:
/* Revert all changes: */
inode_bl->i_blocks = blocks;
inode_bl->i_bytes = bytes;
swap_inode_data(inode, inode_bl);
ext4_mark_inode_dirty(handle, inode);
ext4_mark_inode_dirty(handle, inode_bl);
}
err_out1:
ext4_journal_stop(handle);
ext4_double_up_write_data_sem(inode, inode_bl);
err_out:
up_write(&EXT4_I(inode)->i_mmap_sem);
journal_err_out:
unlock_two_nondirectories(inode, inode_bl);
iput(inode_bl);
return err;
}
/*
* Common pre-write limit and setup checks.
*
* Called with the iolocked held either shared and exclusive according to
* @iolock, and returns with it held. Might upgrade the iolock to exclusive
* if called for a direct write beyond i_size.
*/
STATIC ssize_t
xfs_file_aio_write_checks(
struct kiocb *iocb,
struct iov_iter *from,
int *iolock)
{
struct file *file = iocb->ki_filp;
struct inode *inode = file->f_mapping->host;
struct xfs_inode *ip = XFS_I(inode);
ssize_t error = 0;
size_t count = iov_iter_count(from);
bool drained_dio = false;
restart:
error = generic_write_checks(iocb, from);
if (error <= 0)
return error;
error = xfs_break_layouts(inode, iolock);
if (error)
return error;
/*
* For changing security info in file_remove_privs() we need i_rwsem
* exclusively.
*/
if (*iolock == XFS_IOLOCK_SHARED && !IS_NOSEC(inode)) {
xfs_iunlock(ip, *iolock);
*iolock = XFS_IOLOCK_EXCL;
xfs_ilock(ip, *iolock);
goto restart;
}
/*
* If the offset is beyond the size of the file, we need to zero any
* blocks that fall between the existing EOF and the start of this
* write. If zeroing is needed and we are currently holding the
* iolock shared, we need to update it to exclusive which implies
* having to redo all checks before.
*
* We need to serialise against EOF updates that occur in IO
* completions here. We want to make sure that nobody is changing the
* size while we do this check until we have placed an IO barrier (i.e.
* hold the XFS_IOLOCK_EXCL) that prevents new IO from being dispatched.
* The spinlock effectively forms a memory barrier once we have the
* XFS_IOLOCK_EXCL so we are guaranteed to see the latest EOF value
* and hence be able to correctly determine if we need to run zeroing.
*/
spin_lock(&ip->i_flags_lock);
if (iocb->ki_pos > i_size_read(inode)) {
spin_unlock(&ip->i_flags_lock);
if (!drained_dio) {
if (*iolock == XFS_IOLOCK_SHARED) {
xfs_iunlock(ip, *iolock);
*iolock = XFS_IOLOCK_EXCL;
xfs_ilock(ip, *iolock);
iov_iter_reexpand(from, count);
}
/*
* We now have an IO submission barrier in place, but
* AIO can do EOF updates during IO completion and hence
* we now need to wait for all of them to drain. Non-AIO
* DIO will have drained before we are given the
* XFS_IOLOCK_EXCL, and so for most cases this wait is a
* no-op.
*/
inode_dio_wait(inode);
drained_dio = true;
goto restart;
}
error = xfs_zero_eof(ip, iocb->ki_pos, i_size_read(inode), NULL);
if (error)
return error;
} else
spin_unlock(&ip->i_flags_lock);
/*
* Updating the timestamps will grab the ilock again from
* xfs_fs_dirty_inode, so we have to call it after dropping the
* lock above. Eventually we should look into a way to avoid
* the pointless lock roundtrip.
*/
if (likely(!(file->f_mode & FMODE_NOCMTIME))) {
error = file_update_time(file);
if (error)
return error;
}
/*
* If we're writing the file then make sure to clear the setuid and
* setgid bits if the process is not being run by root. This keeps
* people from modifying setuid and setgid binaries.
*/
if (!IS_NOSEC(inode))
return file_remove_privs(file);
return 0;
}
int
xfs_free_file_space(
struct xfs_inode *ip,
xfs_off_t offset,
xfs_off_t len)
{
int committed;
int done;
xfs_fileoff_t endoffset_fsb;
int error;
xfs_fsblock_t firstfsb;
xfs_bmap_free_t free_list;
xfs_bmbt_irec_t imap;
xfs_off_t ioffset;
xfs_extlen_t mod=0;
xfs_mount_t *mp;
int nimap;
uint resblks;
xfs_off_t rounding;
int rt;
xfs_fileoff_t startoffset_fsb;
xfs_trans_t *tp;
mp = ip->i_mount;
trace_xfs_free_file_space(ip);
error = xfs_qm_dqattach(ip, 0);
if (error)
return error;
error = 0;
if (len <= 0) /* if nothing being freed */
return error;
rt = XFS_IS_REALTIME_INODE(ip);
startoffset_fsb = XFS_B_TO_FSB(mp, offset);
endoffset_fsb = XFS_B_TO_FSBT(mp, offset + len);
/* wait for the completion of any pending DIOs */
inode_dio_wait(VFS_I(ip));
rounding = max_t(xfs_off_t, 1 << mp->m_sb.sb_blocklog, PAGE_CACHE_SIZE);
ioffset = offset & ~(rounding - 1);
error = -filemap_write_and_wait_range(VFS_I(ip)->i_mapping,
ioffset, -1);
if (error)
goto out;
truncate_pagecache_range(VFS_I(ip), ioffset, -1);
/*
* Need to zero the stuff we're not freeing, on disk.
* If it's a realtime file & can't use unwritten extents then we
* actually need to zero the extent edges. Otherwise xfs_bunmapi
* will take care of it for us.
*/
if (rt && !xfs_sb_version_hasextflgbit(&mp->m_sb)) {
nimap = 1;
error = xfs_bmapi_read(ip, startoffset_fsb, 1,
&imap, &nimap, 0);
if (error)
goto out;
ASSERT(nimap == 0 || nimap == 1);
if (nimap && imap.br_startblock != HOLESTARTBLOCK) {
xfs_daddr_t block;
ASSERT(imap.br_startblock != DELAYSTARTBLOCK);
block = imap.br_startblock;
mod = do_div(block, mp->m_sb.sb_rextsize);
if (mod)
startoffset_fsb += mp->m_sb.sb_rextsize - mod;
}
nimap = 1;
error = xfs_bmapi_read(ip, endoffset_fsb - 1, 1,
&imap, &nimap, 0);
if (error)
goto out;
ASSERT(nimap == 0 || nimap == 1);
if (nimap && imap.br_startblock != HOLESTARTBLOCK) {
ASSERT(imap.br_startblock != DELAYSTARTBLOCK);
mod++;
if (mod && (mod != mp->m_sb.sb_rextsize))
endoffset_fsb -= mod;
}
}
if ((done = (endoffset_fsb <= startoffset_fsb)))
/*
* One contiguous piece to clear
*/
error = xfs_zero_remaining_bytes(ip, offset, offset + len - 1);
else {
/*
* Some full blocks, possibly two pieces to clear
*/
if (offset < XFS_FSB_TO_B(mp, startoffset_fsb))
error = xfs_zero_remaining_bytes(ip, offset,
XFS_FSB_TO_B(mp, startoffset_fsb) - 1);
if (!error &&
XFS_FSB_TO_B(mp, endoffset_fsb) < offset + len)
error = xfs_zero_remaining_bytes(ip,
XFS_FSB_TO_B(mp, endoffset_fsb),
offset + len - 1);
}
/*
* free file space until done or until there is an error
*/
resblks = XFS_DIOSTRAT_SPACE_RES(mp, 0);
while (!error && !done) {
/*
* allocate and setup the transaction. Allow this
* transaction to dip into the reserve blocks to ensure
* the freeing of the space succeeds at ENOSPC.
*/
tp = xfs_trans_alloc(mp, XFS_TRANS_DIOSTRAT);
tp->t_flags |= XFS_TRANS_RESERVE;
error = xfs_trans_reserve(tp, &M_RES(mp)->tr_write, resblks, 0);
/*
* check for running out of space
*/
if (error) {
/*
* Free the transaction structure.
*/
ASSERT(error == ENOSPC || XFS_FORCED_SHUTDOWN(mp));
xfs_trans_cancel(tp, 0);
break;
}
xfs_ilock(ip, XFS_ILOCK_EXCL);
error = xfs_trans_reserve_quota(tp, mp,
ip->i_udquot, ip->i_gdquot, ip->i_pdquot,
resblks, 0, XFS_QMOPT_RES_REGBLKS);
if (error)
goto error1;
xfs_trans_ijoin(tp, ip, 0);
/*
* issue the bunmapi() call to free the blocks
*/
xfs_bmap_init(&free_list, &firstfsb);
error = xfs_bunmapi(tp, ip, startoffset_fsb,
endoffset_fsb - startoffset_fsb,
0, 2, &firstfsb, &free_list, &done);
if (error) {
goto error0;
}
/*
* complete the transaction
*/
error = xfs_bmap_finish(&tp, &free_list, &committed);
if (error) {
goto error0;
}
error = xfs_trans_commit(tp, XFS_TRANS_RELEASE_LOG_RES);
xfs_iunlock(ip, XFS_ILOCK_EXCL);
}
out:
return error;
error0:
xfs_bmap_cancel(&free_list);
error1:
xfs_trans_cancel(tp, XFS_TRANS_RELEASE_LOG_RES | XFS_TRANS_ABORT);
xfs_iunlock(ip, XFS_ILOCK_EXCL);
goto out;
}
/*
* Truncate file. Must have write permission and not be a directory.
*/
int
xfs_setattr_size(
struct xfs_inode *ip,
struct iattr *iattr)
{
struct xfs_mount *mp = ip->i_mount;
struct inode *inode = VFS_I(ip);
xfs_off_t oldsize, newsize;
struct xfs_trans *tp;
int error;
uint lock_flags = 0;
bool did_zeroing = false;
trace_xfs_setattr(ip);
if (mp->m_flags & XFS_MOUNT_RDONLY)
return -EROFS;
if (XFS_FORCED_SHUTDOWN(mp))
return -EIO;
error = inode_change_ok(inode, iattr);
if (error)
return error;
ASSERT(xfs_isilocked(ip, XFS_IOLOCK_EXCL));
ASSERT(xfs_isilocked(ip, XFS_MMAPLOCK_EXCL));
ASSERT(S_ISREG(inode->i_mode));
ASSERT((iattr->ia_valid & (ATTR_UID|ATTR_GID|ATTR_ATIME|ATTR_ATIME_SET|
ATTR_MTIME_SET|ATTR_KILL_PRIV|ATTR_TIMES_SET)) == 0);
oldsize = inode->i_size;
newsize = iattr->ia_size;
/*
* Short circuit the truncate case for zero length files.
*/
if (newsize == 0 && oldsize == 0 && ip->i_d.di_nextents == 0) {
if (!(iattr->ia_valid & (ATTR_CTIME|ATTR_MTIME)))
return 0;
/*
* Use the regular setattr path to update the timestamps.
*/
iattr->ia_valid &= ~ATTR_SIZE;
return xfs_setattr_nonsize(ip, iattr, 0);
}
/*
* Make sure that the dquots are attached to the inode.
*/
error = xfs_qm_dqattach(ip, 0);
if (error)
return error;
/*
* Wait for all direct I/O to complete.
*/
inode_dio_wait(inode);
/*
* File data changes must be complete before we start the transaction to
* modify the inode. This needs to be done before joining the inode to
* the transaction because the inode cannot be unlocked once it is a
* part of the transaction.
*
* Start with zeroing any data beyond EOF that we may expose on file
* extension, or zeroing out the rest of the block on a downward
* truncate.
*/
if (newsize > oldsize) {
error = xfs_zero_eof(ip, newsize, oldsize, &did_zeroing);
} else {
error = iomap_truncate_page(inode, newsize, &did_zeroing,
&xfs_iomap_ops);
}
if (error)
return error;
/*
* We are going to log the inode size change in this transaction so
* any previous writes that are beyond the on disk EOF and the new
* EOF that have not been written out need to be written here. If we
* do not write the data out, we expose ourselves to the null files
* problem. Note that this includes any block zeroing we did above;
* otherwise those blocks may not be zeroed after a crash.
*/
if (did_zeroing ||
(newsize > ip->i_d.di_size && oldsize != ip->i_d.di_size)) {
error = filemap_write_and_wait_range(VFS_I(ip)->i_mapping,
ip->i_d.di_size, newsize);
if (error)
return error;
}
/*
* We've already locked out new page faults, so now we can safely remove
* pages from the page cache knowing they won't get refaulted until we
* drop the XFS_MMAP_EXCL lock after the extent manipulations are
* complete. The truncate_setsize() call also cleans partial EOF page
* PTEs on extending truncates and hence ensures sub-page block size
* filesystems are correctly handled, too.
*
* We have to do all the page cache truncate work outside the
* transaction context as the "lock" order is page lock->log space
* reservation as defined by extent allocation in the writeback path.
* Hence a truncate can fail with ENOMEM from xfs_trans_alloc(), but
* having already truncated the in-memory version of the file (i.e. made
* user visible changes). There's not much we can do about this, except
* to hope that the caller sees ENOMEM and retries the truncate
* operation.
*/
truncate_setsize(inode, newsize);
error = xfs_trans_alloc(mp, &M_RES(mp)->tr_itruncate, 0, 0, 0, &tp);
if (error)
return error;
lock_flags |= XFS_ILOCK_EXCL;
xfs_ilock(ip, XFS_ILOCK_EXCL);
xfs_trans_ijoin(tp, ip, 0);
/*
* Only change the c/mtime if we are changing the size or we are
* explicitly asked to change it. This handles the semantic difference
* between truncate() and ftruncate() as implemented in the VFS.
*
* The regular truncate() case without ATTR_CTIME and ATTR_MTIME is a
* special case where we need to update the times despite not having
* these flags set. For all other operations the VFS set these flags
* explicitly if it wants a timestamp update.
*/
if (newsize != oldsize &&
!(iattr->ia_valid & (ATTR_CTIME | ATTR_MTIME))) {
iattr->ia_ctime = iattr->ia_mtime =
current_fs_time(inode->i_sb);
iattr->ia_valid |= ATTR_CTIME | ATTR_MTIME;
}
/*
* The first thing we do is set the size to new_size permanently on
* disk. This way we don't have to worry about anyone ever being able
* to look at the data being freed even in the face of a crash.
* What we're getting around here is the case where we free a block, it
* is allocated to another file, it is written to, and then we crash.
* If the new data gets written to the file but the log buffers
* containing the free and reallocation don't, then we'd end up with
* garbage in the blocks being freed. As long as we make the new size
* permanent before actually freeing any blocks it doesn't matter if
* they get written to.
*/
ip->i_d.di_size = newsize;
xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
if (newsize <= oldsize) {
error = xfs_itruncate_extents(&tp, ip, XFS_DATA_FORK, newsize);
if (error)
goto out_trans_cancel;
/*
* Truncated "down", so we're removing references to old data
* here - if we delay flushing for a long time, we expose
* ourselves unduly to the notorious NULL files problem. So,
* we mark this inode and flush it when the file is closed,
* and do not wait the usual (long) time for writeout.
*/
xfs_iflags_set(ip, XFS_ITRUNCATED);
/* A truncate down always removes post-EOF blocks. */
xfs_inode_clear_eofblocks_tag(ip);
}
if (iattr->ia_valid & ATTR_MODE)
xfs_setattr_mode(ip, iattr);
if (iattr->ia_valid & (ATTR_ATIME|ATTR_CTIME|ATTR_MTIME))
xfs_setattr_time(ip, iattr);
xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
XFS_STATS_INC(mp, xs_ig_attrchg);
if (mp->m_flags & XFS_MOUNT_WSYNC)
xfs_trans_set_sync(tp);
error = xfs_trans_commit(tp);
out_unlock:
if (lock_flags)
xfs_iunlock(ip, lock_flags);
return error;
out_trans_cancel:
xfs_trans_cancel(tp);
goto out_unlock;
}
/*
* xfs_file_dio_aio_write - handle direct IO writes
*
* Lock the inode appropriately to prepare for and issue a direct IO write.
* By separating it from the buffered write path we remove all the tricky to
* follow locking changes and looping.
*
* If there are cached pages or we're extending the file, we need IOLOCK_EXCL
* until we're sure the bytes at the new EOF have been zeroed and/or the cached
* pages are flushed out.
*
* In most cases the direct IO writes will be done holding IOLOCK_SHARED
* allowing them to be done in parallel with reads and other direct IO writes.
* However, if the IO is not aligned to filesystem blocks, the direct IO layer
* needs to do sub-block zeroing and that requires serialisation against other
* direct IOs to the same block. In this case we need to serialise the
* submission of the unaligned IOs so that we don't get racing block zeroing in
* the dio layer. To avoid the problem with aio, we also need to wait for
* outstanding IOs to complete so that unwritten extent conversion is completed
* before we try to map the overlapping block. This is currently implemented by
* hitting it with a big hammer (i.e. inode_dio_wait()).
*
* Returns with locks held indicated by @iolock and errors indicated by
* negative return values.
*/
STATIC ssize_t
xfs_file_dio_aio_write(
struct kiocb *iocb,
struct iov_iter *from)
{
struct file *file = iocb->ki_filp;
struct address_space *mapping = file->f_mapping;
struct inode *inode = mapping->host;
struct xfs_inode *ip = XFS_I(inode);
struct xfs_mount *mp = ip->i_mount;
ssize_t ret = 0;
int unaligned_io = 0;
int iolock;
size_t count = iov_iter_count(from);
loff_t pos = iocb->ki_pos;
struct xfs_buftarg *target = XFS_IS_REALTIME_INODE(ip) ?
mp->m_rtdev_targp : mp->m_ddev_targp;
/* DIO must be aligned to device logical sector size */
if ((pos | count) & target->bt_logical_sectormask)
return -EINVAL;
/* "unaligned" here means not aligned to a filesystem block */
if ((pos & mp->m_blockmask) || ((pos + count) & mp->m_blockmask))
unaligned_io = 1;
/*
* We don't need to take an exclusive lock unless there page cache needs
* to be invalidated or unaligned IO is being executed. We don't need to
* consider the EOF extension case here because
* xfs_file_aio_write_checks() will relock the inode as necessary for
* EOF zeroing cases and fill out the new inode size as appropriate.
*/
if (unaligned_io || mapping->nrpages)
iolock = XFS_IOLOCK_EXCL;
else
iolock = XFS_IOLOCK_SHARED;
xfs_rw_ilock(ip, iolock);
/*
* Recheck if there are cached pages that need invalidate after we got
* the iolock to protect against other threads adding new pages while
* we were waiting for the iolock.
*/
if (mapping->nrpages && iolock == XFS_IOLOCK_SHARED) {
xfs_rw_iunlock(ip, iolock);
iolock = XFS_IOLOCK_EXCL;
xfs_rw_ilock(ip, iolock);
}
ret = xfs_file_aio_write_checks(file, &pos, &count, &iolock);
if (ret)
goto out;
iov_iter_truncate(from, count);
if (mapping->nrpages) {
ret = filemap_write_and_wait_range(VFS_I(ip)->i_mapping,
pos, -1);
if (ret)
goto out;
truncate_pagecache_range(VFS_I(ip), pos, -1);
}
/*
* If we are doing unaligned IO, wait for all other IO to drain,
* otherwise demote the lock if we had to flush cached pages
*/
if (unaligned_io)
inode_dio_wait(inode);
else if (iolock == XFS_IOLOCK_EXCL) {
xfs_rw_ilock_demote(ip, XFS_IOLOCK_EXCL);
iolock = XFS_IOLOCK_SHARED;
}
trace_xfs_file_direct_write(ip, count, iocb->ki_pos, 0);
ret = generic_file_direct_write(iocb, from, pos);
out:
xfs_rw_iunlock(ip, iolock);
/* No fallback to buffered IO on errors for XFS. */
ASSERT(ret < 0 || ret == count);
return ret;
}
/*
* Truncate file. Must have write permission and not be a directory.
*/
int
xfs_setattr_size(
struct xfs_inode *ip,
struct iattr *iattr,
int flags)
{
struct xfs_mount *mp = ip->i_mount;
struct inode *inode = VFS_I(ip);
int mask = iattr->ia_valid;
struct xfs_trans *tp;
int error;
uint lock_flags;
uint commit_flags = 0;
trace_xfs_setattr(ip);
if (mp->m_flags & XFS_MOUNT_RDONLY)
return XFS_ERROR(EROFS);
if (XFS_FORCED_SHUTDOWN(mp))
return XFS_ERROR(EIO);
error = -inode_change_ok(inode, iattr);
if (error)
return XFS_ERROR(error);
ASSERT(S_ISREG(ip->i_d.di_mode));
ASSERT((mask & (ATTR_MODE|ATTR_UID|ATTR_GID|ATTR_ATIME|ATTR_ATIME_SET|
ATTR_MTIME_SET|ATTR_KILL_SUID|ATTR_KILL_SGID|
ATTR_KILL_PRIV|ATTR_TIMES_SET)) == 0);
lock_flags = XFS_ILOCK_EXCL;
if (!(flags & XFS_ATTR_NOLOCK))
lock_flags |= XFS_IOLOCK_EXCL;
xfs_ilock(ip, lock_flags);
/*
* Short circuit the truncate case for zero length files.
*/
if (iattr->ia_size == 0 &&
ip->i_size == 0 && ip->i_d.di_nextents == 0) {
if (!(mask & (ATTR_CTIME|ATTR_MTIME)))
goto out_unlock;
/*
* Use the regular setattr path to update the timestamps.
*/
xfs_iunlock(ip, lock_flags);
iattr->ia_valid &= ~ATTR_SIZE;
return xfs_setattr_nonsize(ip, iattr, 0);
}
/*
* Make sure that the dquots are attached to the inode.
*/
error = xfs_qm_dqattach_locked(ip, 0);
if (error)
goto out_unlock;
/*
* Now we can make the changes. Before we join the inode to the
* transaction, take care of the part of the truncation that must be
* done without the inode lock. This needs to be done before joining
* the inode to the transaction, because the inode cannot be unlocked
* once it is a part of the transaction.
*/
if (iattr->ia_size > ip->i_size) {
/*
* Do the first part of growing a file: zero any data in the
* last block that is beyond the old EOF. We need to do this
* before the inode is joined to the transaction to modify
* i_size.
*/
error = xfs_zero_eof(ip, iattr->ia_size, ip->i_size);
if (error)
goto out_unlock;
}
xfs_iunlock(ip, XFS_ILOCK_EXCL);
lock_flags &= ~XFS_ILOCK_EXCL;
/*
* We are going to log the inode size change in this transaction so
* any previous writes that are beyond the on disk EOF and the new
* EOF that have not been written out need to be written here. If we
* do not write the data out, we expose ourselves to the null files
* problem.
*
* Only flush from the on disk size to the smaller of the in memory
* file size or the new size as that's the range we really care about
* here and prevents waiting for other data not within the range we
* care about here.
*/
if (ip->i_size != ip->i_d.di_size && iattr->ia_size > ip->i_d.di_size) {
error = xfs_flush_pages(ip, ip->i_d.di_size, iattr->ia_size, 0,
FI_NONE);
if (error)
goto out_unlock;
}
/*
* Wait for all direct I/O to complete.
*/
inode_dio_wait(inode);
error = -block_truncate_page(inode->i_mapping, iattr->ia_size,
xfs_get_blocks);
if (error)
goto out_unlock;
tp = xfs_trans_alloc(mp, XFS_TRANS_SETATTR_SIZE);
error = xfs_trans_reserve(tp, 0, XFS_ITRUNCATE_LOG_RES(mp), 0,
XFS_TRANS_PERM_LOG_RES,
XFS_ITRUNCATE_LOG_COUNT);
if (error)
goto out_trans_cancel;
truncate_setsize(inode, iattr->ia_size);
commit_flags = XFS_TRANS_RELEASE_LOG_RES;
lock_flags |= XFS_ILOCK_EXCL;
xfs_ilock(ip, XFS_ILOCK_EXCL);
xfs_trans_ijoin(tp, ip, 0);
/*
* Only change the c/mtime if we are changing the size or we are
* explicitly asked to change it. This handles the semantic difference
* between truncate() and ftruncate() as implemented in the VFS.
*
* The regular truncate() case without ATTR_CTIME and ATTR_MTIME is a
* special case where we need to update the times despite not having
* these flags set. For all other operations the VFS set these flags
* explicitly if it wants a timestamp update.
*/
if (iattr->ia_size != ip->i_size &&
(!(mask & (ATTR_CTIME | ATTR_MTIME)))) {
iattr->ia_ctime = iattr->ia_mtime =
current_fs_time(inode->i_sb);
mask |= ATTR_CTIME | ATTR_MTIME;
}
if (iattr->ia_size > ip->i_size) {
ip->i_d.di_size = iattr->ia_size;
ip->i_size = iattr->ia_size;
} else if (iattr->ia_size <= ip->i_size ||
(iattr->ia_size == 0 && ip->i_d.di_nextents)) {
error = xfs_itruncate_data(&tp, ip, iattr->ia_size);
if (error)
goto out_trans_abort;
/*
* Truncated "down", so we're removing references to old data
* here - if we delay flushing for a long time, we expose
* ourselves unduly to the notorious NULL files problem. So,
* we mark this inode and flush it when the file is closed,
* and do not wait the usual (long) time for writeout.
*/
xfs_iflags_set(ip, XFS_ITRUNCATED);
}
if (mask & ATTR_CTIME) {
inode->i_ctime = iattr->ia_ctime;
ip->i_d.di_ctime.t_sec = iattr->ia_ctime.tv_sec;
ip->i_d.di_ctime.t_nsec = iattr->ia_ctime.tv_nsec;
ip->i_update_core = 1;
}
if (mask & ATTR_MTIME) {
inode->i_mtime = iattr->ia_mtime;
ip->i_d.di_mtime.t_sec = iattr->ia_mtime.tv_sec;
ip->i_d.di_mtime.t_nsec = iattr->ia_mtime.tv_nsec;
ip->i_update_core = 1;
}
xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
XFS_STATS_INC(xs_ig_attrchg);
if (mp->m_flags & XFS_MOUNT_WSYNC)
xfs_trans_set_sync(tp);
error = xfs_trans_commit(tp, XFS_TRANS_RELEASE_LOG_RES);
out_unlock:
if (lock_flags)
xfs_iunlock(ip, lock_flags);
return error;
out_trans_abort:
commit_flags |= XFS_TRANS_ABORT;
out_trans_cancel:
xfs_trans_cancel(tp, commit_flags);
goto out_unlock;
}
/*
* xfs_file_dio_aio_write - handle direct IO writes
*
* Lock the inode appropriately to prepare for and issue a direct IO write.
* By separating it from the buffered write path we remove all the tricky to
* follow locking changes and looping.
*
* If there are cached pages or we're extending the file, we need IOLOCK_EXCL
* until we're sure the bytes at the new EOF have been zeroed and/or the cached
* pages are flushed out.
*
* In most cases the direct IO writes will be done holding IOLOCK_SHARED
* allowing them to be done in parallel with reads and other direct IO writes.
* However, if the IO is not aligned to filesystem blocks, the direct IO layer
* needs to do sub-block zeroing and that requires serialisation against other
* direct IOs to the same block. In this case we need to serialise the
* submission of the unaligned IOs so that we don't get racing block zeroing in
* the dio layer. To avoid the problem with aio, we also need to wait for
* outstanding IOs to complete so that unwritten extent conversion is completed
* before we try to map the overlapping block. This is currently implemented by
* hitting it with a big hammer (i.e. inode_dio_wait()).
*
* Returns with locks held indicated by @iolock and errors indicated by
* negative return values.
*/
STATIC ssize_t
xfs_file_dio_aio_write(
struct kiocb *iocb,
struct iov_iter *from)
{
struct file *file = iocb->ki_filp;
struct address_space *mapping = file->f_mapping;
struct inode *inode = mapping->host;
struct xfs_inode *ip = XFS_I(inode);
struct xfs_mount *mp = ip->i_mount;
ssize_t ret = 0;
int unaligned_io = 0;
int iolock;
size_t count = iov_iter_count(from);
loff_t end;
struct iov_iter data;
struct xfs_buftarg *target = XFS_IS_REALTIME_INODE(ip) ?
mp->m_rtdev_targp : mp->m_ddev_targp;
/* DIO must be aligned to device logical sector size */
if (!IS_DAX(inode) &&
((iocb->ki_pos | count) & target->bt_logical_sectormask))
return -EINVAL;
/* "unaligned" here means not aligned to a filesystem block */
if ((iocb->ki_pos & mp->m_blockmask) ||
((iocb->ki_pos + count) & mp->m_blockmask))
unaligned_io = 1;
/*
* We don't need to take an exclusive lock unless there page cache needs
* to be invalidated or unaligned IO is being executed. We don't need to
* consider the EOF extension case here because
* xfs_file_aio_write_checks() will relock the inode as necessary for
* EOF zeroing cases and fill out the new inode size as appropriate.
*/
if (unaligned_io || mapping->nrpages)
iolock = XFS_IOLOCK_EXCL;
else
iolock = XFS_IOLOCK_SHARED;
xfs_rw_ilock(ip, iolock);
/*
* Recheck if there are cached pages that need invalidate after we got
* the iolock to protect against other threads adding new pages while
* we were waiting for the iolock.
*/
if (mapping->nrpages && iolock == XFS_IOLOCK_SHARED) {
xfs_rw_iunlock(ip, iolock);
iolock = XFS_IOLOCK_EXCL;
xfs_rw_ilock(ip, iolock);
}
ret = xfs_file_aio_write_checks(iocb, from, &iolock);
if (ret)
goto out;
count = iov_iter_count(from);
end = iocb->ki_pos + count - 1;
/*
* See xfs_file_read_iter() for why we do a full-file flush here.
*/
if (mapping->nrpages) {
ret = filemap_write_and_wait(VFS_I(ip)->i_mapping);
if (ret)
goto out;
/*
* Invalidate whole pages. This can return an error if we fail
* to invalidate a page, but this should never happen on XFS.
* Warn if it does fail.
*/
ret = invalidate_inode_pages2(VFS_I(ip)->i_mapping);
WARN_ON_ONCE(ret);
ret = 0;
}
/*
* If we are doing unaligned IO, wait for all other IO to drain,
* otherwise demote the lock if we had to flush cached pages
*/
if (unaligned_io)
inode_dio_wait(inode);
else if (iolock == XFS_IOLOCK_EXCL) {
xfs_rw_ilock_demote(ip, XFS_IOLOCK_EXCL);
iolock = XFS_IOLOCK_SHARED;
}
trace_xfs_file_direct_write(ip, count, iocb->ki_pos, 0);
data = *from;
ret = mapping->a_ops->direct_IO(iocb, &data);
/* see generic_file_direct_write() for why this is necessary */
if (mapping->nrpages) {
invalidate_inode_pages2_range(mapping,
iocb->ki_pos >> PAGE_SHIFT,
end >> PAGE_SHIFT);
}
/*
* xfs_file_dio_aio_write - handle direct IO writes
*
* Lock the inode appropriately to prepare for and issue a direct IO write.
* By separating it from the buffered write path we remove all the tricky to
* follow locking changes and looping.
*
* If there are cached pages or we're extending the file, we need IOLOCK_EXCL
* until we're sure the bytes at the new EOF have been zeroed and/or the cached
* pages are flushed out.
*
* In most cases the direct IO writes will be done holding IOLOCK_SHARED
* allowing them to be done in parallel with reads and other direct IO writes.
* However, if the IO is not aligned to filesystem blocks, the direct IO layer
* needs to do sub-block zeroing and that requires serialisation against other
* direct IOs to the same block. In this case we need to serialise the
* submission of the unaligned IOs so that we don't get racing block zeroing in
* the dio layer. To avoid the problem with aio, we also need to wait for
* outstanding IOs to complete so that unwritten extent conversion is completed
* before we try to map the overlapping block. This is currently implemented by
* hitting it with a big hammer (i.e. inode_dio_wait()).
*
* Returns with locks held indicated by @iolock and errors indicated by
* negative return values.
*/
STATIC ssize_t
xfs_file_dio_aio_write(
struct kiocb *iocb,
const struct iovec *iovp,
unsigned long nr_segs,
loff_t pos,
size_t ocount)
{
struct file *file = iocb->ki_filp;
struct address_space *mapping = file->f_mapping;
struct inode *inode = mapping->host;
struct xfs_inode *ip = XFS_I(inode);
struct xfs_mount *mp = ip->i_mount;
ssize_t ret = 0;
size_t count = ocount;
int unaligned_io = 0;
int iolock;
struct xfs_buftarg *target = XFS_IS_REALTIME_INODE(ip) ?
mp->m_rtdev_targp : mp->m_ddev_targp;
if ((pos & target->bt_smask) || (count & target->bt_smask))
return -XFS_ERROR(EINVAL);
if ((pos & mp->m_blockmask) || ((pos + count) & mp->m_blockmask))
unaligned_io = 1;
/*
* We don't need to take an exclusive lock unless there page cache needs
* to be invalidated or unaligned IO is being executed. We don't need to
* consider the EOF extension case here because
* xfs_file_aio_write_checks() will relock the inode as necessary for
* EOF zeroing cases and fill out the new inode size as appropriate.
*/
if (unaligned_io || mapping->nrpages)
iolock = XFS_IOLOCK_EXCL;
else
iolock = XFS_IOLOCK_SHARED;
xfs_rw_ilock(ip, iolock);
/*
* Recheck if there are cached pages that need invalidate after we got
* the iolock to protect against other threads adding new pages while
* we were waiting for the iolock.
*/
if (mapping->nrpages && iolock == XFS_IOLOCK_SHARED) {
xfs_rw_iunlock(ip, iolock);
iolock = XFS_IOLOCK_EXCL;
xfs_rw_ilock(ip, iolock);
}
ret = xfs_file_aio_write_checks(file, &pos, &count, &iolock);
if (ret)
goto out;
if (mapping->nrpages) {
ret = -xfs_flushinval_pages(ip, (pos & PAGE_CACHE_MASK), -1,
FI_REMAPF_LOCKED);
if (ret)
goto out;
}
/*
* If we are doing unaligned IO, wait for all other IO to drain,
* otherwise demote the lock if we had to flush cached pages
*/
if (unaligned_io)
inode_dio_wait(inode);
else if (iolock == XFS_IOLOCK_EXCL) {
xfs_rw_ilock_demote(ip, XFS_IOLOCK_EXCL);
iolock = XFS_IOLOCK_SHARED;
}
trace_xfs_file_direct_write(ip, count, iocb->ki_pos, 0);
ret = generic_file_direct_write(iocb, iovp,
&nr_segs, pos, &iocb->ki_pos, count, ocount);
out:
xfs_rw_iunlock(ip, iolock);
/* No fallback to buffered IO on errors for XFS. */
ASSERT(ret < 0 || ret == count);
return ret;
}
int
xfs_setattr_size(
struct xfs_inode *ip,
struct iattr *iattr,
int flags)
{
struct xfs_mount *mp = ip->i_mount;
struct inode *inode = VFS_I(ip);
int mask = iattr->ia_valid;
xfs_off_t oldsize, newsize;
struct xfs_trans *tp;
int error;
uint lock_flags;
uint commit_flags = 0;
trace_xfs_setattr(ip);
if (mp->m_flags & XFS_MOUNT_RDONLY)
return XFS_ERROR(EROFS);
if (XFS_FORCED_SHUTDOWN(mp))
return XFS_ERROR(EIO);
error = -inode_change_ok(inode, iattr);
if (error)
return XFS_ERROR(error);
ASSERT(S_ISREG(ip->i_d.di_mode));
ASSERT((mask & (ATTR_MODE|ATTR_UID|ATTR_GID|ATTR_ATIME|ATTR_ATIME_SET|
ATTR_MTIME_SET|ATTR_KILL_SUID|ATTR_KILL_SGID|
ATTR_KILL_PRIV|ATTR_TIMES_SET)) == 0);
lock_flags = XFS_ILOCK_EXCL;
if (!(flags & XFS_ATTR_NOLOCK))
lock_flags |= XFS_IOLOCK_EXCL;
xfs_ilock(ip, lock_flags);
oldsize = inode->i_size;
newsize = iattr->ia_size;
if (newsize == 0 && oldsize == 0 && ip->i_d.di_nextents == 0) {
if (!(mask & (ATTR_CTIME|ATTR_MTIME)))
goto out_unlock;
xfs_iunlock(ip, lock_flags);
iattr->ia_valid &= ~ATTR_SIZE;
return xfs_setattr_nonsize(ip, iattr, 0);
}
error = xfs_qm_dqattach_locked(ip, 0);
if (error)
goto out_unlock;
if (newsize > oldsize) {
error = xfs_zero_eof(ip, newsize, oldsize);
if (error)
goto out_unlock;
}
xfs_iunlock(ip, XFS_ILOCK_EXCL);
lock_flags &= ~XFS_ILOCK_EXCL;
/*
* We are going to log the inode size change in this transaction so
* any previous writes that are beyond the on disk EOF and the new
* EOF that have not been written out need to be written here. If we
* do not write the data out, we expose ourselves to the null files
* problem.
*
* Only flush from the on disk size to the smaller of the in memory
* file size or the new size as that's the range we really care about
* here and prevents waiting for other data not within the range we
* care about here.
*/
if (oldsize != ip->i_d.di_size && newsize > ip->i_d.di_size) {
error = xfs_flush_pages(ip, ip->i_d.di_size, newsize, 0,
FI_NONE);
if (error)
goto out_unlock;
}
inode_dio_wait(inode);
error = -block_truncate_page(inode->i_mapping, newsize, xfs_get_blocks);
if (error)
goto out_unlock;
tp = xfs_trans_alloc(mp, XFS_TRANS_SETATTR_SIZE);
error = xfs_trans_reserve(tp, 0, XFS_ITRUNCATE_LOG_RES(mp), 0,
XFS_TRANS_PERM_LOG_RES,
XFS_ITRUNCATE_LOG_COUNT);
if (error)
goto out_trans_cancel;
truncate_setsize(inode, newsize);
commit_flags = XFS_TRANS_RELEASE_LOG_RES;
lock_flags |= XFS_ILOCK_EXCL;
xfs_ilock(ip, XFS_ILOCK_EXCL);
xfs_trans_ijoin(tp, ip, 0);
if (newsize != oldsize && (!(mask & (ATTR_CTIME | ATTR_MTIME)))) {
iattr->ia_ctime = iattr->ia_mtime =
current_fs_time(inode->i_sb);
mask |= ATTR_CTIME | ATTR_MTIME;
}
/*
* The first thing we do is set the size to new_size permanently on
* disk. This way we don't have to worry about anyone ever being able
* to look at the data being freed even in the face of a crash.
* What we're getting around here is the case where we free a block, it
* is allocated to another file, it is written to, and then we crash.
* If the new data gets written to the file but the log buffers
* containing the free and reallocation don't, then we'd end up with
* garbage in the blocks being freed. As long as we make the new size
* permanent before actually freeing any blocks it doesn't matter if
* they get written to.
*/
ip->i_d.di_size = newsize;
xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
if (newsize <= oldsize) {
error = xfs_itruncate_extents(&tp, ip, XFS_DATA_FORK, newsize);
if (error)
goto out_trans_abort;
xfs_iflags_set(ip, XFS_ITRUNCATED);
}
if (mask & ATTR_CTIME) {
inode->i_ctime = iattr->ia_ctime;
ip->i_d.di_ctime.t_sec = iattr->ia_ctime.tv_sec;
ip->i_d.di_ctime.t_nsec = iattr->ia_ctime.tv_nsec;
}
if (mask & ATTR_MTIME) {
inode->i_mtime = iattr->ia_mtime;
ip->i_d.di_mtime.t_sec = iattr->ia_mtime.tv_sec;
ip->i_d.di_mtime.t_nsec = iattr->ia_mtime.tv_nsec;
}
xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
XFS_STATS_INC(xs_ig_attrchg);
if (mp->m_flags & XFS_MOUNT_WSYNC)
xfs_trans_set_sync(tp);
error = xfs_trans_commit(tp, XFS_TRANS_RELEASE_LOG_RES);
out_unlock:
if (lock_flags)
xfs_iunlock(ip, lock_flags);
return error;
out_trans_abort:
commit_flags |= XFS_TRANS_ABORT;
out_trans_cancel:
xfs_trans_cancel(tp, commit_flags);
goto out_unlock;
}
/*
* Truncate file. Must have write permission and not be a directory.
*/
int
xfs_setattr_size(
struct xfs_inode *ip,
struct iattr *iattr)
{
struct xfs_mount *mp = ip->i_mount;
struct inode *inode = VFS_I(ip);
xfs_off_t oldsize, newsize;
struct xfs_trans *tp;
int error;
uint lock_flags = 0;
uint commit_flags = 0;
trace_xfs_setattr(ip);
if (mp->m_flags & XFS_MOUNT_RDONLY)
return XFS_ERROR(EROFS);
if (XFS_FORCED_SHUTDOWN(mp))
return XFS_ERROR(EIO);
error = -inode_change_ok(inode, iattr);
if (error)
return XFS_ERROR(error);
ASSERT(xfs_isilocked(ip, XFS_IOLOCK_EXCL));
ASSERT(S_ISREG(ip->i_d.di_mode));
ASSERT((iattr->ia_valid & (ATTR_UID|ATTR_GID|ATTR_ATIME|ATTR_ATIME_SET|
ATTR_MTIME_SET|ATTR_KILL_PRIV|ATTR_TIMES_SET)) == 0);
oldsize = inode->i_size;
newsize = iattr->ia_size;
/*
* Short circuit the truncate case for zero length files.
*/
if (newsize == 0 && oldsize == 0 && ip->i_d.di_nextents == 0) {
if (!(iattr->ia_valid & (ATTR_CTIME|ATTR_MTIME)))
return 0;
/*
* Use the regular setattr path to update the timestamps.
*/
iattr->ia_valid &= ~ATTR_SIZE;
return xfs_setattr_nonsize(ip, iattr, 0);
}
/*
* Make sure that the dquots are attached to the inode.
*/
error = xfs_qm_dqattach(ip, 0);
if (error)
return error;
/*
* Now we can make the changes. Before we join the inode to the
* transaction, take care of the part of the truncation that must be
* done without the inode lock. This needs to be done before joining
* the inode to the transaction, because the inode cannot be unlocked
* once it is a part of the transaction.
*/
if (newsize > oldsize) {
/*
* Do the first part of growing a file: zero any data in the
* last block that is beyond the old EOF. We need to do this
* before the inode is joined to the transaction to modify
* i_size.
*/
error = xfs_zero_eof(ip, newsize, oldsize);
if (error)
return error;
}
/*
* We are going to log the inode size change in this transaction so
* any previous writes that are beyond the on disk EOF and the new
* EOF that have not been written out need to be written here. If we
* do not write the data out, we expose ourselves to the null files
* problem.
*
* Only flush from the on disk size to the smaller of the in memory
* file size or the new size as that's the range we really care about
* here and prevents waiting for other data not within the range we
* care about here.
*/
if (oldsize != ip->i_d.di_size && newsize > ip->i_d.di_size) {
error = -filemap_write_and_wait_range(VFS_I(ip)->i_mapping,
ip->i_d.di_size, newsize);
if (error)
return error;
}
/*
* Wait for all direct I/O to complete.
*/
inode_dio_wait(inode);
error = -block_truncate_page(inode->i_mapping, newsize, xfs_get_blocks);
if (error)
return error;
tp = xfs_trans_alloc(mp, XFS_TRANS_SETATTR_SIZE);
error = xfs_trans_reserve(tp, &M_RES(mp)->tr_itruncate, 0, 0);
if (error)
goto out_trans_cancel;
truncate_setsize(inode, newsize);
commit_flags = XFS_TRANS_RELEASE_LOG_RES;
lock_flags |= XFS_ILOCK_EXCL;
xfs_ilock(ip, XFS_ILOCK_EXCL);
xfs_trans_ijoin(tp, ip, 0);
/*
* Only change the c/mtime if we are changing the size or we are
* explicitly asked to change it. This handles the semantic difference
* between truncate() and ftruncate() as implemented in the VFS.
*
* The regular truncate() case without ATTR_CTIME and ATTR_MTIME is a
* special case where we need to update the times despite not having
* these flags set. For all other operations the VFS set these flags
* explicitly if it wants a timestamp update.
*/
if (newsize != oldsize &&
!(iattr->ia_valid & (ATTR_CTIME | ATTR_MTIME))) {
iattr->ia_ctime = iattr->ia_mtime =
current_fs_time(inode->i_sb);
iattr->ia_valid |= ATTR_CTIME | ATTR_MTIME;
}
/*
* The first thing we do is set the size to new_size permanently on
* disk. This way we don't have to worry about anyone ever being able
* to look at the data being freed even in the face of a crash.
* What we're getting around here is the case where we free a block, it
* is allocated to another file, it is written to, and then we crash.
* If the new data gets written to the file but the log buffers
* containing the free and reallocation don't, then we'd end up with
* garbage in the blocks being freed. As long as we make the new size
* permanent before actually freeing any blocks it doesn't matter if
* they get written to.
*/
ip->i_d.di_size = newsize;
xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
if (newsize <= oldsize) {
error = xfs_itruncate_extents(&tp, ip, XFS_DATA_FORK, newsize);
if (error)
goto out_trans_abort;
/*
* Truncated "down", so we're removing references to old data
* here - if we delay flushing for a long time, we expose
* ourselves unduly to the notorious NULL files problem. So,
* we mark this inode and flush it when the file is closed,
* and do not wait the usual (long) time for writeout.
*/
xfs_iflags_set(ip, XFS_ITRUNCATED);
/* A truncate down always removes post-EOF blocks. */
xfs_inode_clear_eofblocks_tag(ip);
}
if (iattr->ia_valid & ATTR_MODE)
xfs_setattr_mode(ip, iattr);
if (iattr->ia_valid & (ATTR_ATIME|ATTR_CTIME|ATTR_MTIME))
xfs_setattr_time(ip, iattr);
xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
XFS_STATS_INC(xs_ig_attrchg);
if (mp->m_flags & XFS_MOUNT_WSYNC)
xfs_trans_set_sync(tp);
error = xfs_trans_commit(tp, XFS_TRANS_RELEASE_LOG_RES);
out_unlock:
if (lock_flags)
xfs_iunlock(ip, lock_flags);
return error;
out_trans_abort:
commit_flags |= XFS_TRANS_ABORT;
out_trans_cancel:
xfs_trans_cancel(tp, commit_flags);
goto out_unlock;
}
/*
* xfs_file_dio_aio_write - handle direct IO writes
*
* Lock the inode appropriately to prepare for and issue a direct IO write.
* By separating it from the buffered write path we remove all the tricky to
* follow locking changes and looping.
*
* If there are cached pages or we're extending the file, we need IOLOCK_EXCL
* until we're sure the bytes at the new EOF have been zeroed and/or the cached
* pages are flushed out.
*
* In most cases the direct IO writes will be done holding IOLOCK_SHARED
* allowing them to be done in parallel with reads and other direct IO writes.
* However, if the IO is not aligned to filesystem blocks, the direct IO layer
* needs to do sub-block zeroing and that requires serialisation against other
* direct IOs to the same block. In this case we need to serialise the
* submission of the unaligned IOs so that we don't get racing block zeroing in
* the dio layer. To avoid the problem with aio, we also need to wait for
* outstanding IOs to complete so that unwritten extent conversion is completed
* before we try to map the overlapping block. This is currently implemented by
* hitting it with a big hammer (i.e. inode_dio_wait()).
*
* Returns with locks held indicated by @iolock and errors indicated by
* negative return values.
*/
STATIC ssize_t
xfs_file_dio_aio_write(
struct kiocb *iocb,
const struct iovec *iovp,
unsigned long nr_segs,
loff_t pos,
size_t ocount)
{
struct file *file = iocb->ki_filp;
struct address_space *mapping = file->f_mapping;
struct inode *inode = mapping->host;
struct xfs_inode *ip = XFS_I(inode);
struct xfs_mount *mp = ip->i_mount;
ssize_t ret = 0;
size_t count = ocount;
int unaligned_io = 0;
int iolock;
struct xfs_buftarg *target = XFS_IS_REALTIME_INODE(ip) ?
mp->m_rtdev_targp : mp->m_ddev_targp;
if ((pos & target->bt_smask) || (count & target->bt_smask))
return -XFS_ERROR(EINVAL);
if ((pos & mp->m_blockmask) || ((pos + count) & mp->m_blockmask))
unaligned_io = 1;
if (unaligned_io || mapping->nrpages)
iolock = XFS_IOLOCK_EXCL;
else
iolock = XFS_IOLOCK_SHARED;
xfs_rw_ilock(ip, iolock);
if (mapping->nrpages && iolock == XFS_IOLOCK_SHARED) {
xfs_rw_iunlock(ip, iolock);
iolock = XFS_IOLOCK_EXCL;
xfs_rw_ilock(ip, iolock);
}
ret = xfs_file_aio_write_checks(file, &pos, &count, &iolock);
if (ret)
goto out;
if (mapping->nrpages) {
ret = -xfs_flushinval_pages(ip, (pos & PAGE_CACHE_MASK), -1,
FI_REMAPF_LOCKED);
if (ret)
goto out;
}
if (unaligned_io)
inode_dio_wait(inode);
else if (iolock == XFS_IOLOCK_EXCL) {
xfs_rw_ilock_demote(ip, XFS_IOLOCK_EXCL);
iolock = XFS_IOLOCK_SHARED;
}
trace_xfs_file_direct_write(ip, count, iocb->ki_pos, 0);
ret = generic_file_direct_write(iocb, iovp,
&nr_segs, pos, &iocb->ki_pos, count, ocount);
out:
xfs_rw_iunlock(ip, iolock);
ASSERT(ret < 0 || ret == count);
return ret;
}
/*
* xfs_file_dio_aio_write - handle direct IO writes
*
* Lock the inode appropriately to prepare for and issue a direct IO write.
* By separating it from the buffered write path we remove all the tricky to
* follow locking changes and looping.
*
* If there are cached pages or we're extending the file, we need IOLOCK_EXCL
* until we're sure the bytes at the new EOF have been zeroed and/or the cached
* pages are flushed out.
*
* In most cases the direct IO writes will be done holding IOLOCK_SHARED
* allowing them to be done in parallel with reads and other direct IO writes.
* However, if the IO is not aligned to filesystem blocks, the direct IO layer
* needs to do sub-block zeroing and that requires serialisation against other
* direct IOs to the same block. In this case we need to serialise the
* submission of the unaligned IOs so that we don't get racing block zeroing in
* the dio layer. To avoid the problem with aio, we also need to wait for
* outstanding IOs to complete so that unwritten extent conversion is completed
* before we try to map the overlapping block. This is currently implemented by
* hitting it with a big hammer (i.e. inode_dio_wait()).
*
* Returns with locks held indicated by @iolock and errors indicated by
* negative return values.
*/
STATIC ssize_t
xfs_file_dio_aio_write(
struct kiocb *iocb,
struct iov_iter *from)
{
struct file *file = iocb->ki_filp;
struct address_space *mapping = file->f_mapping;
struct inode *inode = mapping->host;
struct xfs_inode *ip = XFS_I(inode);
struct xfs_mount *mp = ip->i_mount;
ssize_t ret = 0;
int unaligned_io = 0;
int iolock;
size_t count = iov_iter_count(from);
struct xfs_buftarg *target = XFS_IS_REALTIME_INODE(ip) ?
mp->m_rtdev_targp : mp->m_ddev_targp;
/* DIO must be aligned to device logical sector size */
if ((iocb->ki_pos | count) & target->bt_logical_sectormask)
return -EINVAL;
/*
* Don't take the exclusive iolock here unless the I/O is unaligned to
* the file system block size. We don't need to consider the EOF
* extension case here because xfs_file_aio_write_checks() will relock
* the inode as necessary for EOF zeroing cases and fill out the new
* inode size as appropriate.
*/
if ((iocb->ki_pos & mp->m_blockmask) ||
((iocb->ki_pos + count) & mp->m_blockmask)) {
unaligned_io = 1;
/*
* We can't properly handle unaligned direct I/O to reflink
* files yet, as we can't unshare a partial block.
*/
if (xfs_is_reflink_inode(ip)) {
trace_xfs_reflink_bounce_dio_write(ip, iocb->ki_pos, count);
return -EREMCHG;
}
iolock = XFS_IOLOCK_EXCL;
} else {
iolock = XFS_IOLOCK_SHARED;
}
if (iocb->ki_flags & IOCB_NOWAIT) {
if (!xfs_ilock_nowait(ip, iolock))
return -EAGAIN;
} else {
xfs_ilock(ip, iolock);
}
ret = xfs_file_aio_write_checks(iocb, from, &iolock);
if (ret)
goto out;
count = iov_iter_count(from);
/*
* If we are doing unaligned IO, wait for all other IO to drain,
* otherwise demote the lock if we had to take the exclusive lock
* for other reasons in xfs_file_aio_write_checks.
*/
if (unaligned_io) {
/* If we are going to wait for other DIO to finish, bail */
if (iocb->ki_flags & IOCB_NOWAIT) {
if (atomic_read(&inode->i_dio_count))
return -EAGAIN;
} else {
inode_dio_wait(inode);
}
} else if (iolock == XFS_IOLOCK_EXCL) {
xfs_ilock_demote(ip, XFS_IOLOCK_EXCL);
iolock = XFS_IOLOCK_SHARED;
}
trace_xfs_file_direct_write(ip, count, iocb->ki_pos);
ret = iomap_dio_rw(iocb, from, &xfs_iomap_ops, xfs_dio_write_end_io);
out:
xfs_iunlock(ip, iolock);
/*
* No fallback to buffered IO on errors for XFS, direct IO will either
* complete fully or fail.
*/
ASSERT(ret < 0 || ret == count);
return ret;
}
/*
* Check that the two inodes are eligible for cloning, the ranges make
* sense, and then flush all dirty data. Caller must ensure that the
* inodes have been locked against any other modifications.
*
* If there's an error, then the usual negative error code is returned.
* Otherwise returns 0 with *len set to the request length.
*/
int generic_remap_file_range_prep(struct file *file_in, loff_t pos_in,
struct file *file_out, loff_t pos_out,
loff_t *len, unsigned int remap_flags)
{
struct inode *inode_in = file_inode(file_in);
struct inode *inode_out = file_inode(file_out);
bool same_inode = (inode_in == inode_out);
int ret;
/* Don't touch certain kinds of inodes */
if (IS_IMMUTABLE(inode_out))
return -EPERM;
if (IS_SWAPFILE(inode_in) || IS_SWAPFILE(inode_out))
return -ETXTBSY;
/* Don't reflink dirs, pipes, sockets... */
if (S_ISDIR(inode_in->i_mode) || S_ISDIR(inode_out->i_mode))
return -EISDIR;
if (!S_ISREG(inode_in->i_mode) || !S_ISREG(inode_out->i_mode))
return -EINVAL;
/* Zero length dedupe exits immediately; reflink goes to EOF. */
if (*len == 0) {
loff_t isize = i_size_read(inode_in);
if ((remap_flags & REMAP_FILE_DEDUP) || pos_in == isize)
return 0;
if (pos_in > isize)
return -EINVAL;
*len = isize - pos_in;
if (*len == 0)
return 0;
}
/* Check that we don't violate system file offset limits. */
ret = generic_remap_checks(file_in, pos_in, file_out, pos_out, len,
remap_flags);
if (ret)
return ret;
/* Wait for the completion of any pending IOs on both files */
inode_dio_wait(inode_in);
if (!same_inode)
inode_dio_wait(inode_out);
ret = filemap_write_and_wait_range(inode_in->i_mapping,
pos_in, pos_in + *len - 1);
if (ret)
return ret;
ret = filemap_write_and_wait_range(inode_out->i_mapping,
pos_out, pos_out + *len - 1);
if (ret)
return ret;
/*
* Check that the extents are the same.
*/
if (remap_flags & REMAP_FILE_DEDUP) {
bool is_same = false;
ret = vfs_dedupe_file_range_compare(inode_in, pos_in,
inode_out, pos_out, *len, &is_same);
if (ret)
return ret;
if (!is_same)
return -EBADE;
}
ret = generic_remap_check_len(inode_in, inode_out, pos_out, len,
remap_flags);
if (ret)
return ret;
/* If can't alter the file contents, we're done. */
if (!(remap_flags & REMAP_FILE_DEDUP)) {
/* Update the timestamps, since we can alter file contents. */
if (!(file_out->f_mode & FMODE_NOCMTIME)) {
ret = file_update_time(file_out);
if (ret)
return ret;
}
/*
* Clear the security bits if the process is not being run by
* root. This keeps people from modifying setuid and setgid
* binaries.
*/
ret = file_remove_privs(file_out);
if (ret)
return ret;
}
return 0;
}
/**
* Swap the information from the given @inode and the inode
* EXT4_BOOT_LOADER_INO. It will basically swap i_data and all other
* important fields of the inodes.
*
* @sb: the super block of the filesystem
* @inode: the inode to swap with EXT4_BOOT_LOADER_INO
*
*/
static long swap_inode_boot_loader(struct super_block *sb,
struct inode *inode)
{
handle_t *handle;
int err;
struct inode *inode_bl;
struct ext4_inode_info *ei_bl;
struct ext4_sb_info *sbi = EXT4_SB(sb);
if (inode->i_nlink != 1 || !S_ISREG(inode->i_mode)) {
err = -EINVAL;
goto swap_boot_out;
}
if (!inode_owner_or_capable(inode) || !capable(CAP_SYS_ADMIN)) {
err = -EPERM;
goto swap_boot_out;
}
inode_bl = ext4_iget(sb, EXT4_BOOT_LOADER_INO);
if (IS_ERR(inode_bl)) {
err = PTR_ERR(inode_bl);
goto swap_boot_out;
}
ei_bl = EXT4_I(inode_bl);
filemap_flush(inode->i_mapping);
filemap_flush(inode_bl->i_mapping);
/* Protect orig inodes against a truncate and make sure,
* that only 1 swap_inode_boot_loader is running. */
lock_two_nondirectories(inode, inode_bl);
truncate_inode_pages(&inode->i_data, 0);
truncate_inode_pages(&inode_bl->i_data, 0);
/* Wait for all existing dio workers */
ext4_inode_block_unlocked_dio(inode);
ext4_inode_block_unlocked_dio(inode_bl);
inode_dio_wait(inode);
inode_dio_wait(inode_bl);
handle = ext4_journal_start(inode_bl, EXT4_HT_MOVE_EXTENTS, 2);
if (IS_ERR(handle)) {
err = -EINVAL;
goto journal_err_out;
}
/* Protect extent tree against block allocations via delalloc */
ext4_double_down_write_data_sem(inode, inode_bl);
if (inode_bl->i_nlink == 0) {
/* this inode has never been used as a BOOT_LOADER */
set_nlink(inode_bl, 1);
i_uid_write(inode_bl, 0);
i_gid_write(inode_bl, 0);
inode_bl->i_flags = 0;
ei_bl->i_flags = 0;
inode_bl->i_version = 1;
i_size_write(inode_bl, 0);
inode_bl->i_mode = S_IFREG;
if (EXT4_HAS_INCOMPAT_FEATURE(sb,
EXT4_FEATURE_INCOMPAT_EXTENTS)) {
ext4_set_inode_flag(inode_bl, EXT4_INODE_EXTENTS);
ext4_ext_tree_init(handle, inode_bl);
} else
memset(ei_bl->i_data, 0, sizeof(ei_bl->i_data));
}
swap_inode_data(inode, inode_bl);
inode->i_ctime = inode_bl->i_ctime = ext4_current_time(inode);
spin_lock(&sbi->s_next_gen_lock);
inode->i_generation = sbi->s_next_generation++;
inode_bl->i_generation = sbi->s_next_generation++;
spin_unlock(&sbi->s_next_gen_lock);
ext4_discard_preallocations(inode);
err = ext4_mark_inode_dirty(handle, inode);
if (err < 0) {
ext4_warning(inode->i_sb,
"couldn't mark inode #%lu dirty (err %d)",
inode->i_ino, err);
/* Revert all changes: */
swap_inode_data(inode, inode_bl);
} else {
err = ext4_mark_inode_dirty(handle, inode_bl);
if (err < 0) {
ext4_warning(inode_bl->i_sb,
"couldn't mark inode #%lu dirty (err %d)",
inode_bl->i_ino, err);
/* Revert all changes: */
swap_inode_data(inode, inode_bl);
ext4_mark_inode_dirty(handle, inode);
}
}
ext4_journal_stop(handle);
ext4_double_up_write_data_sem(inode, inode_bl);
journal_err_out:
ext4_inode_resume_unlocked_dio(inode);
ext4_inode_resume_unlocked_dio(inode_bl);
unlock_two_nondirectories(inode, inode_bl);
iput(inode_bl);
swap_boot_out:
return err;
}
/*
* Check that the two inodes are eligible for cloning, the ranges make
* sense, and then flush all dirty data. Caller must ensure that the
* inodes have been locked against any other modifications.
*
* Returns: 0 for "nothing to clone", 1 for "something to clone", or
* the usual negative error code.
*/
int vfs_clone_file_prep_inodes(struct inode *inode_in, loff_t pos_in,
struct inode *inode_out, loff_t pos_out,
u64 *len, bool is_dedupe)
{
loff_t bs = inode_out->i_sb->s_blocksize;
loff_t blen;
loff_t isize;
bool same_inode = (inode_in == inode_out);
int ret;
/* Don't touch certain kinds of inodes */
if (IS_IMMUTABLE(inode_out))
return -EPERM;
if (IS_SWAPFILE(inode_in) || IS_SWAPFILE(inode_out))
return -ETXTBSY;
/* Don't reflink dirs, pipes, sockets... */
if (S_ISDIR(inode_in->i_mode) || S_ISDIR(inode_out->i_mode))
return -EISDIR;
if (!S_ISREG(inode_in->i_mode) || !S_ISREG(inode_out->i_mode))
return -EINVAL;
/* Are we going all the way to the end? */
isize = i_size_read(inode_in);
if (isize == 0)
return 0;
/* Zero length dedupe exits immediately; reflink goes to EOF. */
if (*len == 0) {
if (is_dedupe || pos_in == isize)
return 0;
if (pos_in > isize)
return -EINVAL;
*len = isize - pos_in;
}
/* Ensure offsets don't wrap and the input is inside i_size */
if (pos_in + *len < pos_in || pos_out + *len < pos_out ||
pos_in + *len > isize)
return -EINVAL;
/* Don't allow dedupe past EOF in the dest file */
if (is_dedupe) {
loff_t disize;
disize = i_size_read(inode_out);
if (pos_out >= disize || pos_out + *len > disize)
return -EINVAL;
}
/* If we're linking to EOF, continue to the block boundary. */
if (pos_in + *len == isize)
blen = ALIGN(isize, bs) - pos_in;
else
blen = *len;
/* Only reflink if we're aligned to block boundaries */
if (!IS_ALIGNED(pos_in, bs) || !IS_ALIGNED(pos_in + blen, bs) ||
!IS_ALIGNED(pos_out, bs) || !IS_ALIGNED(pos_out + blen, bs))
return -EINVAL;
/* Don't allow overlapped reflink within the same file */
if (same_inode) {
if (pos_out + blen > pos_in && pos_out < pos_in + blen)
return -EINVAL;
}
/* Wait for the completion of any pending IOs on both files */
inode_dio_wait(inode_in);
if (!same_inode)
inode_dio_wait(inode_out);
ret = filemap_write_and_wait_range(inode_in->i_mapping,
pos_in, pos_in + *len - 1);
if (ret)
return ret;
ret = filemap_write_and_wait_range(inode_out->i_mapping,
pos_out, pos_out + *len - 1);
if (ret)
return ret;
/*
* Check that the extents are the same.
*/
if (is_dedupe) {
bool is_same = false;
ret = vfs_dedupe_file_range_compare(inode_in, pos_in,
inode_out, pos_out, *len, &is_same);
if (ret)
return ret;
if (!is_same)
return -EBADE;
}
return 1;
}
