/*
* Locking for serialisation of IO during page faults. This results in a lock
* ordering of:
*
* mmap_sem (MM)
* sb_start_pagefault(vfs, freeze)
* i_mmaplock (XFS - truncate serialisation)
* page_lock (MM)
* i_lock (XFS - extent map serialisation)
*/
static int
__xfs_filemap_fault(
struct vm_fault *vmf,
enum page_entry_size pe_size,
bool write_fault)
{
struct inode *inode = file_inode(vmf->vma->vm_file);
struct xfs_inode *ip = XFS_I(inode);
int ret;
trace_xfs_filemap_fault(ip, pe_size, write_fault);
if (write_fault) {
sb_start_pagefault(inode->i_sb);
file_update_time(vmf->vma->vm_file);
}
xfs_ilock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
if (IS_DAX(inode)) {
ret = dax_iomap_fault(vmf, pe_size, &xfs_iomap_ops);
} else {
if (write_fault)
ret = iomap_page_mkwrite(vmf, &xfs_iomap_ops);
else
ret = filemap_fault(vmf);
}
xfs_iunlock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
if (write_fault)
sb_end_pagefault(inode->i_sb);
return ret;
}
STATIC ssize_t
xfs_file_read_iter(
struct kiocb *iocb,
struct iov_iter *to)
{
struct inode *inode = file_inode(iocb->ki_filp);
struct xfs_mount *mp = XFS_I(inode)->i_mount;
ssize_t ret = 0;
XFS_STATS_INC(mp, xs_read_calls);
if (XFS_FORCED_SHUTDOWN(mp))
return -EIO;
if (IS_DAX(inode))
ret = xfs_file_dax_read(iocb, to);
else if (iocb->ki_flags & IOCB_DIRECT)
ret = xfs_file_dio_aio_read(iocb, to);
else
ret = xfs_file_buffered_aio_read(iocb, to);
if (ret > 0)
XFS_STATS_ADD(mp, xs_read_bytes, ret);
return ret;
}
/*
* pfn_mkwrite was originally inteneded to ensure we capture time stamp
* updates on write faults. In reality, it's need to serialise against
* truncate similar to page_mkwrite. Hence we cycle the XFS_MMAPLOCK_SHARED
* to ensure we serialise the fault barrier in place.
*/
static int
xfs_filemap_pfn_mkwrite(
struct vm_fault *vmf)
{
struct inode *inode = file_inode(vmf->vma->vm_file);
struct xfs_inode *ip = XFS_I(inode);
int ret = VM_FAULT_NOPAGE;
loff_t size;
trace_xfs_filemap_pfn_mkwrite(ip);
sb_start_pagefault(inode->i_sb);
file_update_time(vmf->vma->vm_file);
/* check if the faulting page hasn't raced with truncate */
xfs_ilock(ip, XFS_MMAPLOCK_SHARED);
size = (i_size_read(inode) + PAGE_SIZE - 1) >> PAGE_SHIFT;
if (vmf->pgoff >= size)
ret = VM_FAULT_SIGBUS;
else if (IS_DAX(inode))
ret = dax_iomap_fault(vmf, PE_SIZE_PTE, &xfs_iomap_ops);
xfs_iunlock(ip, XFS_MMAPLOCK_SHARED);
sb_end_pagefault(inode->i_sb);
return ret;
}
/*
* Similar to xfs_filemap_fault(), the DAX fault path can call into here on
* both read and write faults. Hence we need to handle both cases. There is no
* ->huge_mkwrite callout for huge pages, so we have a single function here to
* handle both cases here. @flags carries the information on the type of fault
* occuring.
*/
STATIC int
xfs_filemap_huge_fault(
struct vm_fault *vmf,
enum page_entry_size pe_size)
{
struct inode *inode = file_inode(vmf->vma->vm_file);
struct xfs_inode *ip = XFS_I(inode);
int ret;
if (!IS_DAX(inode))
return VM_FAULT_FALLBACK;
trace_xfs_filemap_huge_fault(ip);
if (vmf->flags & FAULT_FLAG_WRITE) {
sb_start_pagefault(inode->i_sb);
file_update_time(vmf->vma->vm_file);
}
xfs_ilock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
ret = dax_iomap_fault(vmf, pe_size, &xfs_iomap_ops);
xfs_iunlock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
if (vmf->flags & FAULT_FLAG_WRITE)
sb_end_pagefault(inode->i_sb);
return ret;
}
/*
* mmap()d file has taken write protection fault and is being made writable. We
* can set the page state up correctly for a writable page, which means we can
* do correct delalloc accounting (ENOSPC checking!) and unwritten extent
* mapping.
*/
STATIC int
xfs_filemap_page_mkwrite(
struct vm_fault *vmf)
{
struct inode *inode = file_inode(vmf->vma->vm_file);
int ret;
trace_xfs_filemap_page_mkwrite(XFS_I(inode));
sb_start_pagefault(inode->i_sb);
file_update_time(vmf->vma->vm_file);
xfs_ilock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
if (IS_DAX(inode)) {
ret = dax_iomap_fault(vmf, PE_SIZE_PTE, &xfs_iomap_ops);
} else {
ret = iomap_page_mkwrite(vmf, &xfs_iomap_ops);
ret = block_page_mkwrite_return(ret);
}
xfs_iunlock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
sb_end_pagefault(inode->i_sb);
return ret;
}
/*
* If we are changing DAX flags, we have to ensure the file is clean and any
* cached objects in the address space are invalidated and removed. This
* requires us to lock out other IO and page faults similar to a truncate
* operation. The locks need to be held until the transaction has been committed
* so that the cache invalidation is atomic with respect to the DAX flag
* manipulation.
*/
static int
xfs_ioctl_setattr_dax_invalidate(
struct xfs_inode *ip,
struct fsxattr *fa,
int *join_flags)
{
struct inode *inode = VFS_I(ip);
int error;
*join_flags = 0;
/*
* It is only valid to set the DAX flag on regular files and
* directories on filesystems where the block size is equal to the page
* size. On directories it serves as an inherit hint.
*/
if (fa->fsx_xflags & FS_XFLAG_DAX) {
if (!(S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode)))
return -EINVAL;
if (ip->i_mount->m_sb.sb_blocksize != PAGE_SIZE)
return -EINVAL;
}
/* If the DAX state is not changing, we have nothing to do here. */
if ((fa->fsx_xflags & FS_XFLAG_DAX) && IS_DAX(inode))
return 0;
if (!(fa->fsx_xflags & FS_XFLAG_DAX) && !IS_DAX(inode))
return 0;
/* lock, flush and invalidate mapping in preparation for flag change */
xfs_ilock(ip, XFS_MMAPLOCK_EXCL | XFS_IOLOCK_EXCL);
error = filemap_write_and_wait(inode->i_mapping);
if (error)
goto out_unlock;
error = invalidate_inode_pages2(inode->i_mapping);
if (error)
goto out_unlock;
*join_flags = XFS_MMAPLOCK_EXCL | XFS_IOLOCK_EXCL;
return 0;
out_unlock:
xfs_iunlock(ip, XFS_MMAPLOCK_EXCL | XFS_IOLOCK_EXCL);
return error;
}
static ssize_t ext2_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
{
#ifdef CONFIG_FS_DAX
if (IS_DAX(iocb->ki_filp->f_mapping->host))
return ext2_dax_write_iter(iocb, from);
#endif
return generic_file_write_iter(iocb, from);
}
static int
xfs_filemap_fault(
struct vm_fault *vmf)
{
/* DAX can shortcut the normal fault path on write faults! */
return __xfs_filemap_fault(vmf, PE_SIZE_PTE,
IS_DAX(file_inode(vmf->vma->vm_file)) &&
(vmf->flags & FAULT_FLAG_WRITE));
}
static int ext2_file_mmap(struct file *file, struct vm_area_struct *vma)
{
if (!IS_DAX(file_inode(file)))
return generic_file_mmap(file, vma);
file_accessed(file);
vma->vm_ops = &ext2_dax_vm_ops;
return 0;
}
STATIC int
xfs_file_mmap(
struct file *filp,
struct vm_area_struct *vma)
{
/*
* We don't support synchronous mappings for non-DAX files. At least
* until someone comes with a sensible use case.
*/
if (!IS_DAX(file_inode(filp)) && (vma->vm_flags & VM_SYNC))
return -EOPNOTSUPP;
file_accessed(filp);
vma->vm_ops = &xfs_file_vm_ops;
if (IS_DAX(file_inode(filp)))
vma->vm_flags |= VM_HUGEPAGE;
return 0;
}
static int ext2_file_mmap(struct file *file, struct vm_area_struct *vma)
{
if (!IS_DAX(file_inode(file)))
return generic_file_mmap(file, vma);
file_accessed(file);
vma->vm_ops = &ext2_dax_vm_ops;
vma->vm_flags |= VM_MIXEDMAP | VM_HUGEPAGE;
return 0;
}
STATIC int
xfs_file_mmap(
struct file *filp,
struct vm_area_struct *vma)
{
file_accessed(filp);
vma->vm_ops = &xfs_file_vm_ops;
if (IS_DAX(file_inode(filp)))
vma->vm_flags |= VM_MIXEDMAP | VM_HUGEPAGE;
return 0;
}
static int
xfs_filemap_huge_fault(
struct vm_fault *vmf,
enum page_entry_size pe_size)
{
if (!IS_DAX(file_inode(vmf->vma->vm_file)))
return VM_FAULT_FALLBACK;
/* DAX can shortcut the normal fault path on write faults! */
return __xfs_filemap_fault(vmf, pe_size,
(vmf->flags & FAULT_FLAG_WRITE));
}
STATIC int
xfs_filemap_fault(
struct vm_fault *vmf)
{
struct inode *inode = file_inode(vmf->vma->vm_file);
int ret;
trace_xfs_filemap_fault(XFS_I(inode));
/* DAX can shortcut the normal fault path on write faults! */
if ((vmf->flags & FAULT_FLAG_WRITE) && IS_DAX(inode))
return xfs_filemap_page_mkwrite(vmf);
xfs_ilock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
if (IS_DAX(inode))
ret = dax_iomap_fault(vmf, PE_SIZE_PTE, &xfs_iomap_ops);
else
ret = filemap_fault(vmf);
xfs_iunlock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
return ret;
}
/*
* xfs_iozero clears the specified range supplied via the page cache (except in
* the DAX case). Writes through the page cache will allocate blocks over holes,
* though the callers usually map the holes first and avoid them. If a block is
* not completely zeroed, then it will be read from disk before being partially
* zeroed.
*
* In the DAX case, we can just directly write to the underlying pages. This
* will not allocate blocks, but will avoid holes and unwritten extents and so
* not do unnecessary work.
*/
int
xfs_iozero(
struct xfs_inode *ip, /* inode */
loff_t pos, /* offset in file */
size_t count) /* size of data to zero */
{
struct page *page;
struct address_space *mapping;
int status = 0;
mapping = VFS_I(ip)->i_mapping;
do {
unsigned offset, bytes;
void *fsdata;
offset = (pos & (PAGE_CACHE_SIZE -1)); /* Within page */
bytes = PAGE_CACHE_SIZE - offset;
if (bytes > count)
bytes = count;
if (IS_DAX(VFS_I(ip))) {
status = dax_zero_page_range(VFS_I(ip), pos, bytes,
xfs_get_blocks_direct);
if (status)
break;
} else {
status = pagecache_write_begin(NULL, mapping, pos, bytes,
AOP_FLAG_UNINTERRUPTIBLE,
&page, &fsdata);
if (status)
break;
zero_user(page, offset, bytes);
status = pagecache_write_end(NULL, mapping, pos, bytes,
bytes, page, fsdata);
WARN_ON(status <= 0); /* can't return less than zero! */
status = 0;
}
pos += bytes;
count -= bytes;
} while (count);
return status;
}
STATIC ssize_t
xfs_file_write_iter(
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);
ssize_t ret;
size_t ocount = iov_iter_count(from);
XFS_STATS_INC(ip->i_mount, xs_write_calls);
if (ocount == 0)
return 0;
if (XFS_FORCED_SHUTDOWN(ip->i_mount))
return -EIO;
if (IS_DAX(inode))
ret = xfs_file_dax_write(iocb, from);
else if (iocb->ki_flags & IOCB_DIRECT) {
/*
* Allow a directio write to fall back to a buffered
* write *only* in the case that we're doing a reflink
* CoW. In all other directio scenarios we do not
* allow an operation to fall back to buffered mode.
*/
ret = xfs_file_dio_aio_write(iocb, from);
if (ret == -EREMCHG)
goto buffered;
} else {
buffered:
ret = xfs_file_buffered_aio_write(iocb, from);
}
if (ret > 0) {
XFS_STATS_ADD(ip->i_mount, xs_write_bytes, ret);
/* Handle various SYNC-type writes */
ret = generic_write_sync(iocb, ret);
}
return ret;
}
STATIC ssize_t
xfs_file_splice_read(
struct file *infilp,
loff_t *ppos,
struct pipe_inode_info *pipe,
size_t count,
unsigned int flags)
{
struct xfs_inode *ip = XFS_I(infilp->f_mapping->host);
int ioflags = 0;
ssize_t ret;
XFS_STATS_INC(ip->i_mount, xs_read_calls);
if (infilp->f_mode & FMODE_NOCMTIME)
ioflags |= XFS_IO_INVIS;
if (XFS_FORCED_SHUTDOWN(ip->i_mount))
return -EIO;
trace_xfs_file_splice_read(ip, count, *ppos, ioflags);
/*
* DAX inodes cannot ues the page cache for splice, so we have to push
* them through the VFS IO path. This means it goes through
* ->read_iter, which for us takes the XFS_IOLOCK_SHARED. Hence we
* cannot lock the splice operation at this level for DAX inodes.
*/
if (IS_DAX(VFS_I(ip))) {
ret = default_file_splice_read(infilp, ppos, pipe, count,
flags);
goto out;
}
xfs_rw_ilock(ip, XFS_IOLOCK_SHARED);
ret = generic_file_splice_read(infilp, ppos, pipe, count, flags);
xfs_rw_iunlock(ip, XFS_IOLOCK_SHARED);
out:
if (ret > 0)
XFS_STATS_ADD(ip->i_mount, xs_read_bytes, ret);
return ret;
}
/*
* Locking for serialisation of IO during page faults. This results in a lock
* ordering of:
*
* mmap_sem (MM)
* sb_start_pagefault(vfs, freeze)
* i_mmaplock (XFS - truncate serialisation)
* page_lock (MM)
* i_lock (XFS - extent map serialisation)
*/
static vm_fault_t
__xfs_filemap_fault(
struct vm_fault *vmf,
enum page_entry_size pe_size,
bool write_fault)
{
struct inode *inode = file_inode(vmf->vma->vm_file);
struct xfs_inode *ip = XFS_I(inode);
vm_fault_t ret;
trace_xfs_filemap_fault(ip, pe_size, write_fault);
if (write_fault) {
sb_start_pagefault(inode->i_sb);
file_update_time(vmf->vma->vm_file);
}
xfs_ilock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
if (IS_DAX(inode)) {
pfn_t pfn;
ret = dax_iomap_fault(vmf, pe_size, &pfn, NULL, &xfs_iomap_ops);
if (ret & VM_FAULT_NEEDDSYNC)
ret = dax_finish_sync_fault(vmf, pe_size, pfn);
} else {
if (write_fault)
ret = iomap_page_mkwrite(vmf, &xfs_iomap_ops);
else
ret = filemap_fault(vmf);
}
xfs_iunlock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
if (write_fault)
sb_end_pagefault(inode->i_sb);
return ret;
}
long ext4_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
{
struct inode *inode = file_inode(filp);
struct super_block *sb = inode->i_sb;
struct ext4_inode_info *ei = EXT4_I(inode);
unsigned int flags;
ext4_debug("cmd = %u, arg = %lu\n", cmd, arg);
switch (cmd) {
case FS_IOC_GETFSMAP:
return ext4_ioc_getfsmap(sb, (void __user *)arg);
case EXT4_IOC_GETFLAGS:
flags = ei->i_flags & EXT4_FL_USER_VISIBLE;
return put_user(flags, (int __user *) arg);
case EXT4_IOC_SETFLAGS: {
int err;
if (!inode_owner_or_capable(inode))
return -EACCES;
if (get_user(flags, (int __user *) arg))
return -EFAULT;
if (flags & ~EXT4_FL_USER_VISIBLE)
return -EOPNOTSUPP;
/*
* chattr(1) grabs flags via GETFLAGS, modifies the result and
* passes that to SETFLAGS. So we cannot easily make SETFLAGS
* more restrictive than just silently masking off visible but
* not settable flags as we always did.
*/
flags &= EXT4_FL_USER_MODIFIABLE;
if (ext4_mask_flags(inode->i_mode, flags) != flags)
return -EOPNOTSUPP;
err = mnt_want_write_file(filp);
if (err)
return err;
inode_lock(inode);
err = ext4_ioctl_setflags(inode, flags);
inode_unlock(inode);
mnt_drop_write_file(filp);
return err;
}
case EXT4_IOC_GETVERSION:
case EXT4_IOC_GETVERSION_OLD:
return put_user(inode->i_generation, (int __user *) arg);
case EXT4_IOC_SETVERSION:
case EXT4_IOC_SETVERSION_OLD: {
handle_t *handle;
struct ext4_iloc iloc;
__u32 generation;
int err;
if (!inode_owner_or_capable(inode))
return -EPERM;
if (ext4_has_metadata_csum(inode->i_sb)) {
ext4_warning(sb, "Setting inode version is not "
"supported with metadata_csum enabled.");
return -ENOTTY;
}
err = mnt_want_write_file(filp);
if (err)
return err;
if (get_user(generation, (int __user *) arg)) {
err = -EFAULT;
goto setversion_out;
}
inode_lock(inode);
handle = ext4_journal_start(inode, EXT4_HT_INODE, 1);
if (IS_ERR(handle)) {
err = PTR_ERR(handle);
goto unlock_out;
}
err = ext4_reserve_inode_write(handle, inode, &iloc);
if (err == 0) {
inode->i_ctime = current_time(inode);
inode->i_generation = generation;
err = ext4_mark_iloc_dirty(handle, inode, &iloc);
}
ext4_journal_stop(handle);
unlock_out:
inode_unlock(inode);
setversion_out:
mnt_drop_write_file(filp);
return err;
}
case EXT4_IOC_GROUP_EXTEND: {
ext4_fsblk_t n_blocks_count;
int err, err2=0;
err = ext4_resize_begin(sb);
if (err)
return err;
if (get_user(n_blocks_count, (__u32 __user *)arg)) {
err = -EFAULT;
goto group_extend_out;
}
if (ext4_has_feature_bigalloc(sb)) {
ext4_msg(sb, KERN_ERR,
"Online resizing not supported with bigalloc");
err = -EOPNOTSUPP;
goto group_extend_out;
}
err = mnt_want_write_file(filp);
if (err)
goto group_extend_out;
err = ext4_group_extend(sb, EXT4_SB(sb)->s_es, n_blocks_count);
if (EXT4_SB(sb)->s_journal) {
jbd2_journal_lock_updates(EXT4_SB(sb)->s_journal);
err2 = jbd2_journal_flush(EXT4_SB(sb)->s_journal);
jbd2_journal_unlock_updates(EXT4_SB(sb)->s_journal);
}
if (err == 0)
err = err2;
mnt_drop_write_file(filp);
group_extend_out:
ext4_resize_end(sb);
return err;
}
case EXT4_IOC_MOVE_EXT: {
struct move_extent me;
struct fd donor;
int err;
if (!(filp->f_mode & FMODE_READ) ||
!(filp->f_mode & FMODE_WRITE))
return -EBADF;
if (copy_from_user(&me,
(struct move_extent __user *)arg, sizeof(me)))
return -EFAULT;
me.moved_len = 0;
donor = fdget(me.donor_fd);
if (!donor.file)
return -EBADF;
if (!(donor.file->f_mode & FMODE_WRITE)) {
err = -EBADF;
goto mext_out;
}
if (ext4_has_feature_bigalloc(sb)) {
ext4_msg(sb, KERN_ERR,
"Online defrag not supported with bigalloc");
err = -EOPNOTSUPP;
goto mext_out;
} else if (IS_DAX(inode)) {
ext4_msg(sb, KERN_ERR,
"Online defrag not supported with DAX");
err = -EOPNOTSUPP;
goto mext_out;
}
err = mnt_want_write_file(filp);
if (err)
goto mext_out;
err = ext4_move_extents(filp, donor.file, me.orig_start,
me.donor_start, me.len, &me.moved_len);
mnt_drop_write_file(filp);
if (copy_to_user((struct move_extent __user *)arg,
&me, sizeof(me)))
err = -EFAULT;
mext_out:
fdput(donor);
return err;
}
case EXT4_IOC_GROUP_ADD: {
struct ext4_new_group_data input;
if (copy_from_user(&input, (struct ext4_new_group_input __user *)arg,
sizeof(input)))
return -EFAULT;
return ext4_ioctl_group_add(filp, &input);
}
case EXT4_IOC_MIGRATE:
{
int err;
if (!inode_owner_or_capable(inode))
return -EACCES;
err = mnt_want_write_file(filp);
if (err)
return err;
/*
* inode_mutex prevent write and truncate on the file.
* Read still goes through. We take i_data_sem in
* ext4_ext_swap_inode_data before we switch the
* inode format to prevent read.
*/
inode_lock((inode));
err = ext4_ext_migrate(inode);
inode_unlock((inode));
mnt_drop_write_file(filp);
return err;
}
case EXT4_IOC_ALLOC_DA_BLKS:
{
int err;
if (!inode_owner_or_capable(inode))
return -EACCES;
err = mnt_want_write_file(filp);
if (err)
return err;
err = ext4_alloc_da_blocks(inode);
mnt_drop_write_file(filp);
return err;
}
case EXT4_IOC_SWAP_BOOT:
{
int err;
if (!(filp->f_mode & FMODE_WRITE))
return -EBADF;
err = mnt_want_write_file(filp);
if (err)
return err;
err = swap_inode_boot_loader(sb, inode);
mnt_drop_write_file(filp);
return err;
}
case EXT4_IOC_RESIZE_FS: {
ext4_fsblk_t n_blocks_count;
int err = 0, err2 = 0;
ext4_group_t o_group = EXT4_SB(sb)->s_groups_count;
if (copy_from_user(&n_blocks_count, (__u64 __user *)arg,
sizeof(__u64))) {
return -EFAULT;
}
err = ext4_resize_begin(sb);
if (err)
return err;
err = mnt_want_write_file(filp);
if (err)
goto resizefs_out;
err = ext4_resize_fs(sb, n_blocks_count);
if (EXT4_SB(sb)->s_journal) {
jbd2_journal_lock_updates(EXT4_SB(sb)->s_journal);
err2 = jbd2_journal_flush(EXT4_SB(sb)->s_journal);
jbd2_journal_unlock_updates(EXT4_SB(sb)->s_journal);
}
if (err == 0)
err = err2;
mnt_drop_write_file(filp);
if (!err && (o_group > EXT4_SB(sb)->s_groups_count) &&
ext4_has_group_desc_csum(sb) &&
test_opt(sb, INIT_INODE_TABLE))
err = ext4_register_li_request(sb, o_group);
resizefs_out:
ext4_resize_end(sb);
return err;
}
case FITRIM:
{
struct request_queue *q = bdev_get_queue(sb->s_bdev);
struct fstrim_range range;
int ret = 0;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
if (!blk_queue_discard(q))
return -EOPNOTSUPP;
if (copy_from_user(&range, (struct fstrim_range __user *)arg,
sizeof(range)))
return -EFAULT;
range.minlen = max((unsigned int)range.minlen,
q->limits.discard_granularity);
ret = ext4_trim_fs(sb, &range);
if (ret < 0)
return ret;
if (copy_to_user((struct fstrim_range __user *)arg, &range,
sizeof(range)))
return -EFAULT;
return 0;
}
case EXT4_IOC_PRECACHE_EXTENTS:
return ext4_ext_precache(inode);
case EXT4_IOC_SET_ENCRYPTION_POLICY:
if (!ext4_has_feature_encrypt(sb))
return -EOPNOTSUPP;
return fscrypt_ioctl_set_policy(filp, (const void __user *)arg);
case EXT4_IOC_GET_ENCRYPTION_PWSALT: {
#ifdef CONFIG_EXT4_FS_ENCRYPTION
int err, err2;
struct ext4_sb_info *sbi = EXT4_SB(sb);
handle_t *handle;
if (!ext4_has_feature_encrypt(sb))
return -EOPNOTSUPP;
if (uuid_is_zero(sbi->s_es->s_encrypt_pw_salt)) {
err = mnt_want_write_file(filp);
if (err)
return err;
handle = ext4_journal_start_sb(sb, EXT4_HT_MISC, 1);
if (IS_ERR(handle)) {
err = PTR_ERR(handle);
goto pwsalt_err_exit;
}
err = ext4_journal_get_write_access(handle, sbi->s_sbh);
if (err)
goto pwsalt_err_journal;
generate_random_uuid(sbi->s_es->s_encrypt_pw_salt);
err = ext4_handle_dirty_metadata(handle, NULL,
sbi->s_sbh);
pwsalt_err_journal:
err2 = ext4_journal_stop(handle);
if (err2 && !err)
err = err2;
pwsalt_err_exit:
mnt_drop_write_file(filp);
if (err)
return err;
}
if (copy_to_user((void __user *) arg,
sbi->s_es->s_encrypt_pw_salt, 16))
return -EFAULT;
return 0;
#else
return -EOPNOTSUPP;
#endif
}
case EXT4_IOC_GET_ENCRYPTION_POLICY:
return fscrypt_ioctl_get_policy(filp, (void __user *)arg);
case EXT4_IOC_FSGETXATTR:
{
struct fsxattr fa;
memset(&fa, 0, sizeof(struct fsxattr));
fa.fsx_xflags = ext4_iflags_to_xflags(ei->i_flags & EXT4_FL_USER_VISIBLE);
if (ext4_has_feature_project(inode->i_sb)) {
fa.fsx_projid = (__u32)from_kprojid(&init_user_ns,
EXT4_I(inode)->i_projid);
}
if (copy_to_user((struct fsxattr __user *)arg,
&fa, sizeof(fa)))
return -EFAULT;
return 0;
}
case EXT4_IOC_FSSETXATTR:
{
struct fsxattr fa;
int err;
if (copy_from_user(&fa, (struct fsxattr __user *)arg,
sizeof(fa)))
return -EFAULT;
/* Make sure caller has proper permission */
if (!inode_owner_or_capable(inode))
return -EACCES;
if (fa.fsx_xflags & ~EXT4_SUPPORTED_FS_XFLAGS)
return -EOPNOTSUPP;
flags = ext4_xflags_to_iflags(fa.fsx_xflags);
if (ext4_mask_flags(inode->i_mode, flags) != flags)
return -EOPNOTSUPP;
err = mnt_want_write_file(filp);
if (err)
return err;
inode_lock(inode);
flags = (ei->i_flags & ~EXT4_FL_XFLAG_VISIBLE) |
(flags & EXT4_FL_XFLAG_VISIBLE);
err = ext4_ioctl_setflags(inode, flags);
inode_unlock(inode);
mnt_drop_write_file(filp);
if (err)
return err;
err = ext4_ioctl_setproject(filp, fa.fsx_projid);
if (err)
return err;
return 0;
}
case EXT4_IOC_SHUTDOWN:
return ext4_shutdown(sb, arg);
default:
return -ENOTTY;
}
}
STATIC ssize_t
xfs_file_read_iter(
struct kiocb *iocb,
struct iov_iter *to)
{
struct file *file = iocb->ki_filp;
struct inode *inode = file->f_mapping->host;
struct xfs_inode *ip = XFS_I(inode);
struct xfs_mount *mp = ip->i_mount;
size_t size = iov_iter_count(to);
ssize_t ret = 0;
int ioflags = 0;
xfs_fsize_t n;
loff_t pos = iocb->ki_pos;
XFS_STATS_INC(mp, xs_read_calls);
if (unlikely(iocb->ki_flags & IOCB_DIRECT))
ioflags |= XFS_IO_ISDIRECT;
if (file->f_mode & FMODE_NOCMTIME)
ioflags |= XFS_IO_INVIS;
if ((ioflags & XFS_IO_ISDIRECT) && !IS_DAX(inode)) {
xfs_buftarg_t *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 | size) & target->bt_logical_sectormask) {
if (pos == i_size_read(inode))
return 0;
return -EINVAL;
}
}
n = mp->m_super->s_maxbytes - pos;
if (n <= 0 || size == 0)
return 0;
if (n < size)
size = n;
if (XFS_FORCED_SHUTDOWN(mp))
return -EIO;
/*
* Locking is a bit tricky here. If we take an exclusive lock for direct
* IO, we effectively serialise all new concurrent read IO to this file
* and block it behind IO that is currently in progress because IO in
* progress holds the IO lock shared. We only need to hold the lock
* exclusive to blow away the page cache, so only take lock exclusively
* if the page cache needs invalidation. This allows the normal direct
* IO case of no page cache pages to proceeed concurrently without
* serialisation.
*/
xfs_rw_ilock(ip, XFS_IOLOCK_SHARED);
if ((ioflags & XFS_IO_ISDIRECT) && inode->i_mapping->nrpages) {
xfs_rw_iunlock(ip, XFS_IOLOCK_SHARED);
xfs_rw_ilock(ip, XFS_IOLOCK_EXCL);
/*
* The generic dio code only flushes the range of the particular
* I/O. Because we take an exclusive lock here, this whole
* sequence is considerably more expensive for us. This has a
* noticeable performance impact for any file with cached pages,
* even when outside of the range of the particular I/O.
*
* Hence, amortize the cost of the lock against a full file
* flush and reduce the chances of repeated iolock cycles going
* forward.
*/
if (inode->i_mapping->nrpages) {
ret = filemap_write_and_wait(VFS_I(ip)->i_mapping);
if (ret) {
xfs_rw_iunlock(ip, XFS_IOLOCK_EXCL);
return ret;
}
/*
* 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;
}
xfs_rw_ilock_demote(ip, XFS_IOLOCK_EXCL);
}
trace_xfs_file_read(ip, size, pos, ioflags);
ret = generic_file_read_iter(iocb, to);
if (ret > 0)
XFS_STATS_ADD(mp, xs_read_bytes, ret);
xfs_rw_iunlock(ip, XFS_IOLOCK_SHARED);
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);
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);
}
/*
* 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(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;
/*
* 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 block beyond EOF that we may expose on
* file extension.
*/
if (newsize > oldsize) {
error = xfs_zero_eof(ip, newsize, oldsize, &did_zeroing);
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 (newsize > ip->i_d.di_size &&
(oldsize != ip->i_d.di_size || did_zeroing)) {
error = filemap_write_and_wait_range(VFS_I(ip)->i_mapping,
ip->i_d.di_size, newsize);
if (error)
return error;
}
/* Now wait for all direct I/O to complete. */
inode_dio_wait(inode);
/*
* 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_reserve(), 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.
*/
if (IS_DAX(inode))
error = dax_truncate_page(inode, newsize, xfs_get_blocks_direct);
else
error = block_truncate_page(inode->i_mapping, newsize,
xfs_get_blocks);
if (error)
return error;
truncate_setsize(inode, newsize);
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;
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;
}
/*
* Prepare two files for range cloning. Upon a successful return both inodes
* will have the iolock and mmaplock held, the page cache of the out file will
* be truncated, and any leases on the out file will have been broken. This
* function borrows heavily from xfs_file_aio_write_checks.
*
* The VFS allows partial EOF blocks to "match" for dedupe even though it hasn't
* checked that the bytes beyond EOF physically match. Hence we cannot use the
* EOF block in the source dedupe range because it's not a complete block match,
* hence can introduce a corruption into the file that has it's block replaced.
*
* In similar fashion, the VFS file cloning also allows partial EOF blocks to be
* "block aligned" for the purposes of cloning entire files. However, if the
* source file range includes the EOF block and it lands within the existing EOF
* of the destination file, then we can expose stale data from beyond the source
* file EOF in the destination file.
*
* XFS doesn't support partial block sharing, so in both cases we have check
* these cases ourselves. For dedupe, we can simply round the length to dedupe
* down to the previous whole block and ignore the partial EOF block. While this
* means we can't dedupe the last block of a file, this is an acceptible
* tradeoff for simplicity on implementation.
*
* For cloning, we want to share the partial EOF block if it is also the new EOF
* block of the destination file. If the partial EOF block lies inside the
* existing destination EOF, then we have to abort the clone to avoid exposing
* stale data in the destination file. Hence we reject these clone attempts with
* -EINVAL in this case.
*/
int
xfs_reflink_remap_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 xfs_inode *src = XFS_I(inode_in);
struct inode *inode_out = file_inode(file_out);
struct xfs_inode *dest = XFS_I(inode_out);
bool same_inode = (inode_in == inode_out);
ssize_t ret;
/* Lock both files against IO */
ret = xfs_iolock_two_inodes_and_break_layout(inode_in, inode_out);
if (ret)
return ret;
if (same_inode)
xfs_ilock(src, XFS_MMAPLOCK_EXCL);
else
xfs_lock_two_inodes(src, XFS_MMAPLOCK_SHARED, 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 = generic_remap_file_range_prep(file_in, pos_in, file_out, pos_out,
len, remap_flags);
if (ret < 0 || *len == 0)
goto out_unlock;
/* Attach dquots to dest inode before changing block map */
ret = xfs_qm_dqattach(dest);
if (ret)
goto out_unlock;
/*
* Zero existing post-eof speculative preallocations in the destination
* file.
*/
ret = xfs_reflink_zero_posteof(dest, pos_out);
if (ret)
goto out_unlock;
/* Set flags and remap blocks. */
ret = xfs_reflink_set_inode_flag(src, dest);
if (ret)
goto out_unlock;
/*
* If pos_out > EOF, we may have dirtied blocks between EOF and
* pos_out. In that case, we need to extend the flush and unmap to cover
* from EOF to the end of the copy length.
*/
if (pos_out > XFS_ISIZE(dest)) {
loff_t flen = *len + (pos_out - XFS_ISIZE(dest));
ret = xfs_flush_unmap_range(dest, XFS_ISIZE(dest), flen);
} else {
ret = xfs_flush_unmap_range(dest, pos_out, *len);
}
if (ret)
goto out_unlock;
return 1;
out_unlock:
xfs_reflink_remap_unlock(file_in, file_out);
return ret;
}
/*
* 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;
}
STATIC ssize_t
xfs_file_read_iter(
struct kiocb *iocb,
struct iov_iter *to)
{
struct file *file = iocb->ki_filp;
struct inode *inode = file->f_mapping->host;
struct xfs_inode *ip = XFS_I(inode);
struct xfs_mount *mp = ip->i_mount;
size_t size = iov_iter_count(to);
ssize_t ret = 0;
int ioflags = 0;
xfs_fsize_t n;
loff_t pos = iocb->ki_pos;
XFS_STATS_INC(xs_read_calls);
if (unlikely(iocb->ki_flags & IOCB_DIRECT))
ioflags |= XFS_IO_ISDIRECT;
if (file->f_mode & FMODE_NOCMTIME)
ioflags |= XFS_IO_INVIS;
if ((ioflags & XFS_IO_ISDIRECT) && !IS_DAX(inode)) {
xfs_buftarg_t *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 | size) & target->bt_logical_sectormask) {
if (pos == i_size_read(inode))
return 0;
return -EINVAL;
}
}
n = mp->m_super->s_maxbytes - pos;
if (n <= 0 || size == 0)
return 0;
if (n < size)
size = n;
if (XFS_FORCED_SHUTDOWN(mp))
return -EIO;
/*
* Locking is a bit tricky here. If we take an exclusive lock
* for direct IO, we effectively serialise all new concurrent
* read IO to this file and block it behind IO that is currently in
* progress because IO in progress holds the IO lock shared. We only
* need to hold the lock exclusive to blow away the page cache, so
* only take lock exclusively if the page cache needs invalidation.
* This allows the normal direct IO case of no page cache pages to
* proceeed concurrently without serialisation.
*/
xfs_rw_ilock(ip, XFS_IOLOCK_SHARED);
if ((ioflags & XFS_IO_ISDIRECT) && inode->i_mapping->nrpages) {
xfs_rw_iunlock(ip, XFS_IOLOCK_SHARED);
xfs_rw_ilock(ip, XFS_IOLOCK_EXCL);
if (inode->i_mapping->nrpages) {
ret = filemap_write_and_wait_range(
VFS_I(ip)->i_mapping,
pos, pos + size - 1);
if (ret) {
xfs_rw_iunlock(ip, XFS_IOLOCK_EXCL);
return ret;
}
/*
* 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_range(VFS_I(ip)->i_mapping,
pos >> PAGE_CACHE_SHIFT,
(pos + size - 1) >> PAGE_CACHE_SHIFT);
WARN_ON_ONCE(ret);
ret = 0;
}
