static ssize_t aufs_aio_write_sp(struct kiocb *kio, const struct iovec *iov,
unsigned long nv, loff_t pos)
{
ssize_t err;
aufs_bindex_t bstart;
unsigned char wbr;
struct super_block *sb;
struct file *file, *h_file;
file = kio->ki_filp;
sb = file->f_dentry->d_sb;
si_read_lock(sb, AuLock_FLUSH);
fi_read_lock(file);
bstart = au_fbstart(file);
h_file = au_hf_top(file);
fi_read_unlock(file);
wbr = !!au_br_writable(au_sbr(sb, bstart)->br_perm);
si_read_unlock(sb);
/* do not change the file in kio */
AuDebugOn(!h_file->f_op || !h_file->f_op->aio_write);
err = h_file->f_op->aio_write(kio, iov, nv, pos);
if (err > 0 && wbr)
file_update_time(h_file);
return err;
}
/*
* 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;
}
static int f2fs_vm_page_mkwrite(struct vm_area_struct *vma,
struct vm_fault *vmf)
{
struct page *page = vmf->page;
struct inode *inode = file_inode(vma->vm_file);
struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
struct dnode_of_data dn;
int err;
f2fs_balance_fs(sbi);
vfs_check_frozen(inode->i_sb, SB_FREEZE_WRITE);
f2fs_bug_on(sbi, f2fs_has_inline_data(inode));
/* block allocation */
f2fs_lock_op(sbi);
set_new_dnode(&dn, inode, NULL, NULL, 0);
err = f2fs_reserve_block(&dn, page->index);
if (err) {
f2fs_unlock_op(sbi);
goto out;
}
f2fs_put_dnode(&dn);
f2fs_unlock_op(sbi);
file_update_time(vma->vm_file);
lock_page(page);
if (unlikely(page->mapping != inode->i_mapping ||
page_offset(page) > i_size_read(inode) ||
!PageUptodate(page))) {
unlock_page(page);
err = -EFAULT;
goto out;
}
/*
* check to see if the page is mapped already (no holes)
*/
if (PageMappedToDisk(page))
goto mapped;
/* page is wholly or partially inside EOF */
if (((page->index + 1) << PAGE_CACHE_SHIFT) > i_size_read(inode)) {
unsigned offset;
offset = i_size_read(inode) & ~PAGE_CACHE_MASK;
zero_user_segment(page, offset, PAGE_CACHE_SIZE);
}
set_page_dirty(page);
SetPageUptodate(page);
trace_f2fs_vm_page_mkwrite(page, DATA);
mapped:
/* fill the page */
f2fs_wait_on_page_writeback(page, DATA);
/* if gced page is attached, don't write to cold segment */
clear_cold_data(page);
out:
return block_page_mkwrite_return(err);
}
static int
v9fs_vm_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
{
struct v9fs_inode *v9inode;
struct page *page = vmf->page;
struct file *filp = vma->vm_file;
struct inode *inode = file_inode(filp);
p9_debug(P9_DEBUG_VFS, "page %p fid %lx\n",
page, (unsigned long)filp->private_data);
/* Update file times before taking page lock */
file_update_time(filp);
v9inode = V9FS_I(inode);
/* make sure the cache has finished storing the page */
v9fs_fscache_wait_on_page_write(inode, page);
BUG_ON(!v9inode->writeback_fid);
lock_page(page);
if (page->mapping != inode->i_mapping)
goto out_unlock;
wait_for_stable_page(page);
return VM_FAULT_LOCKED;
out_unlock:
unlock_page(page);
return VM_FAULT_NOPAGE;
}
/*
* 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 ext2_dax_write_iter(struct kiocb *iocb, struct iov_iter *from)
{
struct file *file = iocb->ki_filp;
struct inode *inode = file->f_mapping->host;
ssize_t ret;
inode_lock(inode);
ret = generic_write_checks(iocb, from);
if (ret <= 0)
goto out_unlock;
ret = file_remove_privs(file);
if (ret)
goto out_unlock;
ret = file_update_time(file);
if (ret)
goto out_unlock;
ret = dax_iomap_rw(iocb, from, &ext2_iomap_ops);
if (ret > 0 && iocb->ki_pos > i_size_read(inode)) {
i_size_write(inode, iocb->ki_pos);
mark_inode_dirty(inode);
}
out_unlock:
inode_unlock(inode);
if (ret > 0)
ret = generic_write_sync(iocb, 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;
}
/*
* 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 file *file,
loff_t *pos,
size_t *count,
int *iolock)
{
struct inode *inode = file->f_mapping->host;
struct xfs_inode *ip = XFS_I(inode);
int error = 0;
restart:
error = generic_write_checks(file, pos, count, S_ISBLK(inode->i_mode));
if (error)
return error;
/*
* 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.
*/
if (*pos > i_size_read(inode)) {
if (*iolock == XFS_IOLOCK_SHARED) {
xfs_rw_iunlock(ip, *iolock);
*iolock = XFS_IOLOCK_EXCL;
xfs_rw_ilock(ip, *iolock);
goto restart;
}
error = -xfs_zero_eof(ip, *pos, i_size_read(inode));
if (error)
return error;
}
/*
* 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.
*/
return file_remove_suid(file);
}
ssize_t hmfs_xip_file_write(struct file * filp, const char __user * buf,
size_t len, loff_t * ppos)
{
struct address_space *mapping = filp->f_mapping;
struct inode *inode = filp->f_inode;
struct hmfs_sb_info *sbi = HMFS_SB(inode->i_sb);
size_t count = 0, ret;
loff_t pos;
int ilock;
mutex_lock(&inode->i_mutex);
if (!access_ok(VERIFY_READ, buf, len)) {
ret = -EFAULT;
goto out_up;
}
pos = *ppos;
count = len;
current->backing_dev_info = mapping->backing_dev_info;
ret = generic_write_checks(filp, &pos, &count, S_ISBLK(inode->i_mode));
if (ret)
goto out_backing;
if (count == 0)
goto out_backing;
ret = file_remove_suid(filp);
if (ret)
goto out_backing;
ret = file_update_time(filp);
if (ret)
goto out_backing;
inode->i_ctime = inode->i_mtime = CURRENT_TIME_SEC;
ilock = mutex_lock_op(sbi);
ret = __hmfs_xip_file_write(filp, buf, count, pos, ppos);
mutex_unlock_op(sbi, ilock);
mark_inode_dirty(inode);
out_backing:
current->backing_dev_info = NULL;
out_up:
mutex_unlock(&inode->i_mutex);
return ret;
}
/*
* 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 file *file,
loff_t *pos,
size_t *count,
int *iolock)
{
struct inode *inode = file->f_mapping->host;
struct xfs_inode *ip = XFS_I(inode);
int error = 0;
xfs_rw_ilock(ip, XFS_ILOCK_EXCL);
restart:
error = generic_write_checks(file, pos, count, S_ISBLK(inode->i_mode));
if (error) {
xfs_rw_iunlock(ip, XFS_ILOCK_EXCL);
return error;
}
if (likely(!(file->f_mode & FMODE_NOCMTIME)))
file_update_time(file);
/*
* 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 involves
* dropping all locks and relocking to maintain correct locking order.
* If we do this, restart the function to ensure all checks and values
* are still valid.
*/
if (*pos > i_size_read(inode)) {
if (*iolock == XFS_IOLOCK_SHARED) {
xfs_rw_iunlock(ip, XFS_ILOCK_EXCL | *iolock);
*iolock = XFS_IOLOCK_EXCL;
xfs_rw_ilock(ip, XFS_ILOCK_EXCL | *iolock);
goto restart;
}
error = -xfs_zero_eof(ip, *pos, i_size_read(inode));
}
xfs_rw_iunlock(ip, XFS_ILOCK_EXCL);
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.
*/
return file_remove_suid(file);
}
static int ll_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
{
int count = 0;
bool printed = false;
bool retry;
int result;
ll_stats_ops_tally(ll_i2sbi(file_inode(vma->vm_file)),
LPROC_LL_MKWRITE, 1);
file_update_time(vma->vm_file);
do {
retry = false;
result = ll_page_mkwrite0(vma, vmf->page, &retry);
if (!printed && ++count > 16) {
const struct dentry *de = file_dentry(vma->vm_file);
CWARN("app(%s): the page %lu of file "DFID" is under"
" heavy contention\n",
current->comm, vmf->pgoff,
PFID(ll_inode2fid(de->d_inode)));
printed = true;
}
} while (retry);
switch(result) {
case 0:
LASSERT(PageLocked(vmf->page));
result = VM_FAULT_LOCKED;
break;
case -ENODATA:
case -EFAULT:
result = VM_FAULT_NOPAGE;
break;
case -ENOMEM:
result = VM_FAULT_OOM;
break;
case -EAGAIN:
result = VM_FAULT_RETRY;
break;
default:
result = VM_FAULT_SIGBUS;
break;
}
return result;
}
/**
* dax_fault - handle a page fault on a DAX file
* @vma: The virtual memory area where the fault occurred
* @vmf: The description of the fault
* @get_block: The filesystem method used to translate file offsets to blocks
*
* When a page fault occurs, filesystems may call this helper in their
* fault handler for DAX files.
*/
int dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
get_block_t get_block, dax_iodone_t complete_unwritten)
{
int result;
struct super_block *sb = file_inode(vma->vm_file)->i_sb;
if (vmf->flags & FAULT_FLAG_WRITE) {
sb_start_pagefault(sb);
file_update_time(vma->vm_file);
}
result = __dax_fault(vma, vmf, get_block, complete_unwritten);
if (vmf->flags & FAULT_FLAG_WRITE)
sb_end_pagefault(sb);
return result;
}
/*
* Common pre-write limit and setup checks.
*
* Returns with iolock held according to @iolock.
*/
STATIC ssize_t
xfs_file_aio_write_checks(
struct file *file,
loff_t *pos,
size_t *count,
int *iolock)
{
struct inode *inode = file->f_mapping->host;
struct xfs_inode *ip = XFS_I(inode);
xfs_fsize_t new_size;
int error = 0;
xfs_rw_ilock(ip, XFS_ILOCK_EXCL);
error = generic_write_checks(file, pos, count, S_ISBLK(inode->i_mode));
if (error) {
xfs_rw_iunlock(ip, XFS_ILOCK_EXCL | *iolock);
*iolock = 0;
return error;
}
new_size = *pos + *count;
if (new_size > ip->i_size)
ip->i_new_size = new_size;
if (likely(!(file->f_mode & FMODE_NOCMTIME)))
file_update_time(file);
/*
* 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 (*pos > ip->i_size)
error = -xfs_zero_eof(ip, *pos, ip->i_size);
xfs_rw_iunlock(ip, XFS_ILOCK_EXCL);
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.
*/
return file_remove_suid(file);
}
/*
* The lock ordering for ext2 DAX fault paths is:
*
* mmap_sem (MM)
* sb_start_pagefault (vfs, freeze)
* ext2_inode_info->dax_sem
* address_space->i_mmap_rwsem or page_lock (mutually exclusive in DAX)
* ext2_inode_info->truncate_mutex
*
* The default page_lock and i_size verification done by non-DAX fault paths
* is sufficient because ext2 doesn't support hole punching.
*/
static vm_fault_t ext2_dax_fault(struct vm_fault *vmf)
{
struct inode *inode = file_inode(vmf->vma->vm_file);
struct ext2_inode_info *ei = EXT2_I(inode);
vm_fault_t ret;
if (vmf->flags & FAULT_FLAG_WRITE) {
sb_start_pagefault(inode->i_sb);
file_update_time(vmf->vma->vm_file);
}
down_read(&ei->dax_sem);
ret = dax_iomap_fault(vmf, PE_SIZE_PTE, NULL, NULL, &ext2_iomap_ops);
up_read(&ei->dax_sem);
if (vmf->flags & FAULT_FLAG_WRITE)
sb_end_pagefault(inode->i_sb);
return ret;
}
/*
* The lock ordering for ext2 DAX fault paths is:
*
* mmap_sem (MM)
* sb_start_pagefault (vfs, freeze)
* ext2_inode_info->dax_sem
* address_space->i_mmap_rwsem or page_lock (mutually exclusive in DAX)
* ext2_inode_info->truncate_mutex
*
* The default page_lock and i_size verification done by non-DAX fault paths
* is sufficient because ext2 doesn't support hole punching.
*/
static int ext2_dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
{
struct inode *inode = file_inode(vma->vm_file);
struct ext2_inode_info *ei = EXT2_I(inode);
int ret;
if (vmf->flags & FAULT_FLAG_WRITE) {
sb_start_pagefault(inode->i_sb);
file_update_time(vma->vm_file);
}
down_read(&ei->dax_sem);
ret = __dax_fault(vma, vmf, ext2_get_block, NULL);
up_read(&ei->dax_sem);
if (vmf->flags & FAULT_FLAG_WRITE)
sb_end_pagefault(inode->i_sb);
return ret;
}
static int ext2_dax_pmd_fault(struct vm_area_struct *vma, unsigned long addr,
pmd_t *pmd, unsigned int flags)
{
struct inode *inode = file_inode(vma->vm_file);
struct ext2_inode_info *ei = EXT2_I(inode);
int ret;
if (flags & FAULT_FLAG_WRITE) {
sb_start_pagefault(inode->i_sb);
file_update_time(vma->vm_file);
}
down_read(&ei->dax_sem);
ret = __dax_pmd_fault(vma, addr, pmd, flags, ext2_get_block, NULL);
up_read(&ei->dax_sem);
if (flags & FAULT_FLAG_WRITE)
sb_end_pagefault(inode->i_sb);
return ret;
}
static int sysfs_bin_page_mkwrite(struct vm_area_struct *vma,
struct vm_fault *vmf)
{
struct file *file = vma->vm_file;
struct sysfs_open_file *of = sysfs_of(file);
int ret;
if (!of->vm_ops)
return VM_FAULT_SIGBUS;
if (!sysfs_get_active(of->sd))
return VM_FAULT_SIGBUS;
ret = 0;
if (of->vm_ops->page_mkwrite)
ret = of->vm_ops->page_mkwrite(vma, vmf);
else
file_update_time(file);
sysfs_put_active(of->sd);
return ret;
}
static int bin_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
{
struct file *file = vma->vm_file;
struct bin_buffer *bb = file->private_data;
struct sysfs_dirent *attr_sd = file->f_path.dentry->d_fsdata;
int ret;
if (!bb->vm_ops)
return VM_FAULT_SIGBUS;
if (!sysfs_get_active(attr_sd))
return VM_FAULT_SIGBUS;
ret = 0;
if (bb->vm_ops->page_mkwrite)
ret = bb->vm_ops->page_mkwrite(vma, vmf);
else
file_update_time(file);
sysfs_put_active(attr_sd);
return ret;
}
STATIC ssize_t
xfs_file_aio_write_checks(
struct file *file,
loff_t *pos,
size_t *count,
int *iolock)
{
struct inode *inode = file->f_mapping->host;
struct xfs_inode *ip = XFS_I(inode);
int error = 0;
xfs_rw_ilock(ip, XFS_ILOCK_EXCL);
restart:
error = generic_write_checks(file, pos, count, S_ISBLK(inode->i_mode));
if (error) {
xfs_rw_iunlock(ip, XFS_ILOCK_EXCL);
return error;
}
if (*pos > i_size_read(inode)) {
if (*iolock == XFS_IOLOCK_SHARED) {
xfs_rw_iunlock(ip, XFS_ILOCK_EXCL | *iolock);
*iolock = XFS_IOLOCK_EXCL;
xfs_rw_ilock(ip, XFS_ILOCK_EXCL | *iolock);
goto restart;
}
error = -xfs_zero_eof(ip, *pos, i_size_read(inode));
}
xfs_rw_iunlock(ip, XFS_ILOCK_EXCL);
if (error)
return error;
if (likely(!(file->f_mode & FMODE_NOCMTIME)))
file_update_time(file);
return file_remove_suid(file);
}
static int ext2_dax_pfn_mkwrite(struct vm_area_struct *vma,
struct vm_fault *vmf)
{
struct inode *inode = file_inode(vma->vm_file);
struct ext2_inode_info *ei = EXT2_I(inode);
loff_t size;
int ret;
sb_start_pagefault(inode->i_sb);
file_update_time(vma->vm_file);
down_read(&ei->dax_sem);
/* check that the faulting page hasn't raced with truncate */
size = (i_size_read(inode) + PAGE_SIZE - 1) >> PAGE_SHIFT;
if (vmf->pgoff >= size)
ret = VM_FAULT_SIGBUS;
else
ret = dax_pfn_mkwrite(vma, vmf);
up_read(&ei->dax_sem);
sb_end_pagefault(inode->i_sb);
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;
}
/*
* 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;
}
static int gfs2_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
{
struct page *page = vmf->page;
struct inode *inode = vma->vm_file->f_path.dentry->d_inode;
struct gfs2_inode *ip = GFS2_I(inode);
struct gfs2_sbd *sdp = GFS2_SB(inode);
struct gfs2_alloc_parms ap = { .aflags = 0, };
unsigned long last_index;
u64 pos = page->index << PAGE_CACHE_SHIFT;
unsigned int data_blocks, ind_blocks, rblocks;
int alloc_required = 0;
struct gfs2_holder gh;
loff_t size;
int ret;
sb_start_pagefault(inode->i_sb);
/* Update file times before taking page lock */
file_update_time(vma->vm_file);
ret = get_write_access(inode);
if (ret)
goto out;
ret = gfs2_rs_alloc(ip);
if (ret)
goto out_write_access;
gfs2_holder_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &gh);
ret = gfs2_glock_nq(&gh);
if (ret)
goto out_uninit;
set_bit(GLF_DIRTY, &ip->i_gl->gl_flags);
set_bit(GIF_SW_PAGED, &ip->i_flags);
gfs2_size_hint(inode, pos, PAGE_CACHE_SIZE);
ret = gfs2_write_alloc_required(ip, pos, PAGE_CACHE_SIZE, &alloc_required);
if (ret)
goto out_unlock;
if (!alloc_required) {
lock_page(page);
if (!PageUptodate(page) || page->mapping != inode->i_mapping) {
ret = -EAGAIN;
unlock_page(page);
}
goto out_unlock;
}
ret = gfs2_rindex_update(sdp);
if (ret)
goto out_unlock;
ret = gfs2_quota_lock_check(ip);
if (ret)
goto out_unlock;
gfs2_write_calc_reserv(ip, PAGE_CACHE_SIZE, &data_blocks, &ind_blocks);
ap.target = data_blocks + ind_blocks;
ret = gfs2_inplace_reserve(ip, &ap);
if (ret)
goto out_quota_unlock;
rblocks = RES_DINODE + ind_blocks;
if (gfs2_is_jdata(ip))
rblocks += data_blocks ? data_blocks : 1;
if (ind_blocks || data_blocks) {
rblocks += RES_STATFS + RES_QUOTA;
rblocks += gfs2_rg_blocks(ip, data_blocks + ind_blocks);
}
ret = gfs2_trans_begin(sdp, rblocks, 0);
if (ret)
goto out_trans_fail;
lock_page(page);
ret = -EINVAL;
size = i_size_read(inode);
last_index = (size - 1) >> PAGE_CACHE_SHIFT;
/* Check page index against inode size */
if (size == 0 || (page->index > last_index))
goto out_trans_end;
ret = -EAGAIN;
/* If truncated, we must retry the operation, we may have raced
* with the glock demotion code.
*/
if (!PageUptodate(page) || page->mapping != inode->i_mapping)
goto out_trans_end;
/* Unstuff, if required, and allocate backing blocks for page */
ret = 0;
if (gfs2_is_stuffed(ip))
ret = gfs2_unstuff_dinode(ip, page);
if (ret == 0)
ret = gfs2_allocate_page_backing(page);
out_trans_end:
if (ret)
unlock_page(page);
gfs2_trans_end(sdp);
out_trans_fail:
gfs2_inplace_release(ip);
out_quota_unlock:
gfs2_quota_unlock(ip);
out_unlock:
gfs2_glock_dq(&gh);
out_uninit:
gfs2_holder_uninit(&gh);
if (ret == 0) {
set_page_dirty(page);
wait_for_stable_page(page);
}
out_write_access:
put_write_access(inode);
out:
sb_end_pagefault(inode->i_sb);
return block_page_mkwrite_return(ret);
}
static const struct vm_operations_struct gfs2_vm_ops = {
.fault = filemap_fault,
.page_mkwrite = gfs2_page_mkwrite,
};
/**
* gfs2_mmap -
* @file: The file to map
* @vma: The VMA which described the mapping
*
* There is no need to get a lock here unless we should be updating
* atime. We ignore any locking errors since the only consequence is
* a missed atime update (which will just be deferred until later).
*
* Returns: 0
*/
static int gfs2_mmap(struct file *file, struct vm_area_struct *vma)
{
struct gfs2_inode *ip = GFS2_I(file->f_mapping->host);
if (!(file->f_flags & O_NOATIME) &&
!IS_NOATIME(&ip->i_inode)) {
struct gfs2_holder i_gh;
int error;
error = gfs2_glock_nq_init(ip->i_gl, LM_ST_SHARED, LM_FLAG_ANY,
&i_gh);
if (error)
return error;
/* grab lock to update inode */
gfs2_glock_dq_uninit(&i_gh);
file_accessed(file);
}
vma->vm_ops = &gfs2_vm_ops;
vma->vm_flags |= VM_CAN_NONLINEAR;
return 0;
}
/**
* gfs2_open - open a file
* @inode: the inode to open
* @file: the struct file for this opening
*
* Returns: errno
*/
static int gfs2_open(struct inode *inode, struct file *file)
{
struct gfs2_inode *ip = GFS2_I(inode);
struct gfs2_holder i_gh;
struct gfs2_file *fp;
int error;
fp = kzalloc(sizeof(struct gfs2_file), GFP_KERNEL);
if (!fp)
return -ENOMEM;
mutex_init(&fp->f_fl_mutex);
gfs2_assert_warn(GFS2_SB(inode), !file->private_data);
file->private_data = fp;
if (S_ISREG(ip->i_inode.i_mode)) {
error = gfs2_glock_nq_init(ip->i_gl, LM_ST_SHARED, LM_FLAG_ANY,
&i_gh);
if (error)
goto fail;
if (!(file->f_flags & O_LARGEFILE) &&
i_size_read(inode) > MAX_NON_LFS) {
error = -EOVERFLOW;
goto fail_gunlock;
}
gfs2_glock_dq_uninit(&i_gh);
}
return 0;
fail_gunlock:
gfs2_glock_dq_uninit(&i_gh);
fail:
file->private_data = NULL;
kfree(fp);
return error;
}
/**
* gfs2_release - called to close a struct file
* @inode: the inode the struct file belongs to
* @file: the struct file being closed
*
* Returns: errno
*/
static int gfs2_release(struct inode *inode, struct file *file)
{
struct gfs2_inode *ip = GFS2_I(inode);
kfree(file->private_data);
file->private_data = NULL;
if (!(file->f_mode & FMODE_WRITE))
return 0;
gfs2_rs_delete(ip);
return 0;
}
/**
* gfs2_fsync - sync the dirty data for a file (across the cluster)
* @file: the file that points to the dentry
* @start: the start position in the file to sync
* @end: the end position in the file to sync
* @datasync: set if we can ignore timestamp changes
*
* The VFS will flush data for us. We only need to worry
* about metadata here.
*
* Returns: errno
*/
static int gfs2_fsync(struct file *file, struct dentry *dentry, int datasync)
{
struct inode *inode = dentry->d_inode;
int sync_state = inode->i_state & I_DIRTY;
struct gfs2_inode *ip = GFS2_I(inode);
int ret;
if (!gfs2_is_jdata(ip))
sync_state &= ~I_DIRTY_PAGES;
if (datasync)
sync_state &= ~I_DIRTY_SYNC;
if (sync_state) {
ret = sync_inode_metadata(inode, 1);
if (ret)
return ret;
if (gfs2_is_jdata(ip))
filemap_write_and_wait(inode->i_mapping);
gfs2_ail_flush(ip->i_gl, 1);
}
return 0;
}
/**
* gfs2_file_aio_write - Perform a write to a file
* @iocb: The io context
* @iov: The data to write
* @nr_segs: Number of @iov segments
* @pos: The file position
*
* We have to do a lock/unlock here to refresh the inode size for
* O_APPEND writes, otherwise we can land up writing at the wrong
* offset. There is still a race, but provided the app is using its
* own file locking, this will make O_APPEND work as expected.
*
*/
static ssize_t gfs2_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
unsigned long nr_segs, loff_t pos)
{
struct file *file = iocb->ki_filp;
size_t writesize = iov_length(iov, nr_segs);
struct dentry *dentry = file->f_dentry;
struct gfs2_inode *ip = GFS2_I(dentry->d_inode);
struct gfs2_sbd *sdp;
int ret;
sdp = GFS2_SB(file->f_mapping->host);
ret = gfs2_rs_alloc(ip);
if (ret)
return ret;
gfs2_size_hint(file->f_dentry->d_inode, pos, writesize);
if (file->f_flags & O_APPEND) {
struct gfs2_holder gh;
ret = gfs2_glock_nq_init(ip->i_gl, LM_ST_SHARED, 0, &gh);
if (ret)
return ret;
gfs2_glock_dq_uninit(&gh);
}
return generic_file_aio_write(iocb, iov, nr_segs, pos);
}
static ssize_t gfs2_file_splice_write(struct pipe_inode_info *pipe,
struct file *out, loff_t *ppos,
size_t len, unsigned int flags)
{
int error;
struct inode *inode = out->f_mapping->host;
struct gfs2_inode *ip = GFS2_I(inode);
error = gfs2_rs_alloc(ip);
if (error)
return (ssize_t)error;
gfs2_size_hint(inode, *ppos, len);
return generic_file_splice_write(pipe, out, ppos, len, flags);
}
/* FIXME: Ugliest function of all in LFS, need I say more? */
static ssize_t lfs_file_write( struct file *file, const char __user *buf,
size_t count, loff_t *ppos)
{
loff_t pos;
struct page *page;
ssize_t res, written, bytes;
struct inode *inode = file->f_dentry->d_inode;
struct super_block *sb = inode->i_sb;
struct segment *segp = LFS_SBI(sb)->s_curr;
//dprintk("lfs_file_write called for %lu at pos %Lu\n", inode->i_ino, *ppos);
if(file->f_flags & O_DIRECT) {
dprintk("The file is requesting direct IO\n");
return -EINVAL;
}
if (unlikely(count < 0 ))
return -EINVAL;
if (unlikely(!access_ok(VERIFY_READ, buf, count)))
return -EFAULT;
//down(&inode->i_sem); /* lock the file */
mutex_lock(&inode->i_mutex); //BrechREiZ: We need this for Kernel 2.6.17
lfs_lock(sb);
pos = *ppos;
res = generic_write_checks(file, &pos, &count, 0);
if (res)
goto out;
if(count == 0)
goto out;
res = remove_suid(file->f_dentry);
if(res)
goto out;
//inode_update_time(inode, 1); /* update mtime and ctime */
file_update_time(inode); //BrechREiZ: We need this for Kernel 2.6.17
written = 0;
do {
long offset;
size_t copied;
int i, siblock, eiblock, boffset;
sector_t block;
offset = (segp->offset % BUF_IN_PAGE) * LFS_BSIZE;
offset += pos & (LFS_BSIZE - 1); /* within block */
bytes = PAGE_CACHE_SIZE - offset; /* number of bytes written
in this iteration */
invalidate_old_page(inode, pos);
if (bytes > count)
bytes = count;
//dprintk("1:segp->start=%Lu,segp->offset=%d,segp->end=%Lu,offset=%lu,bytes=%d\n", segp->start, segp->offset, segp->end,offset,bytes);
siblock = pos >> LFS_BSIZE_BITS;
eiblock = (pos + bytes - 1) >> LFS_BSIZE_BITS;
//dprintk("writing %d bytes at offset %ld (pos = %Lu)\n", bytes, offset, pos);
//dprintk("siblock = %d, eiblock = %d\n", siblock, eiblock);
/*
* Bring in the user page that we will copy from _first_.
* Otherwise there's a nasty deadlock on copying from the
* same page as we're writing to, without it being marked
* up-to-date.
*/
fault_in_pages_readable(buf, bytes);
page = get_seg_page(segp);
if (!page) {
res = -ENOMEM;
break;
}
/* fill the page with current inode blocks if any */
boffset = offset / LFS_BSIZE;;
for(i = siblock; i <= eiblock; ++i, ++boffset) {
struct buffer_head *bh;
//dprintk("Asking for block %d\n", i);
bh = lfs_read_block(inode, i);
if(!bh) /* new block */
break;
//dprintk("boffset = %d\n", boffset);
memcpy(page_address(page) + LFS_BSIZE * boffset, bh->b_data, LFS_BSIZE);
brelse(bh);
}
copied = __copy_from_user(page_address(page) + offset, buf, bytes);
flush_dcache_page(page);
block = segp->start + segp->offset;
for(i = siblock;i <= eiblock; ++i, ++block)
segsum_update_finfo(segp, inode->i_ino, i, block);
block = segp->start + segp->offset;
segp->offset += (bytes - 1)/LFS_BSIZE + 1;
//dprintk("2:segp->start=%Lu,segp->offset=%d,segp->end=%Lu,offset=%lu,bytes=%d\n",
//segp->start, segp->offset, segp->end,offset,bytes);
BUG_ON(segp->start + segp->offset > segp->end);
if(segp->start + segp->offset == segp->end) {
dprintk("allocating new segment\n");
/* This also is going to write the previous segment */
segment_allocate_new(inode->i_sb, segp, segp->start + segp->offset);
segp = LFS_SBI(sb)->s_curr;
}
/* update the inode */
for(i = siblock;i <= eiblock; ++i, ++block)
update_inode(inode, i, block);
//dprintk("start=%Lu,offset=%d,end=%Lu\n", segp->start, segp->offset, segp->end);
segusetbl_add_livebytes(sb, segp->segnum, bytes);
written += bytes;
buf += bytes;
pos += bytes;
count -= bytes;
} while(count);
*ppos = pos;
if(pos > inode->i_size)
i_size_write(inode, pos);
if(written)
mark_inode_dirty(inode);
lfs_unlock(sb);
//up(&inode->i_sem);
mutex_unlock(&inode->i_mutex); //BrechREiZ: and unlocking...
return written ? written : res;
out:
lfs_unlock(sb);
//up(&inode->i_sem);
mutex_unlock(&inode->i_mutex); //BrechREiZ: and unlocking...
return res;
}
int __dax_pmd_fault(struct vm_area_struct *vma, unsigned long address,
pmd_t *pmd, unsigned int flags, get_block_t get_block,
dax_iodone_t complete_unwritten)
{
struct file *file = vma->vm_file;
struct address_space *mapping = file->f_mapping;
struct inode *inode = mapping->host;
struct buffer_head bh;
unsigned blkbits = inode->i_blkbits;
unsigned long pmd_addr = address & PMD_MASK;
bool write = flags & FAULT_FLAG_WRITE;
struct block_device *bdev;
pgoff_t size, pgoff;
sector_t block;
int error, result = 0;
bool alloc = false;
/* dax pmd mappings require pfn_t_devmap() */
if (!IS_ENABLED(CONFIG_FS_DAX_PMD))
return VM_FAULT_FALLBACK;
/* Fall back to PTEs if we're going to COW */
if (write && !(vma->vm_flags & VM_SHARED)) {
split_huge_pmd(vma, pmd, address);
dax_pmd_dbg(NULL, address, "cow write");
return VM_FAULT_FALLBACK;
}
/* If the PMD would extend outside the VMA */
if (pmd_addr < vma->vm_start) {
dax_pmd_dbg(NULL, address, "vma start unaligned");
return VM_FAULT_FALLBACK;
}
if ((pmd_addr + PMD_SIZE) > vma->vm_end) {
dax_pmd_dbg(NULL, address, "vma end unaligned");
return VM_FAULT_FALLBACK;
}
pgoff = linear_page_index(vma, pmd_addr);
size = (i_size_read(inode) + PAGE_SIZE - 1) >> PAGE_SHIFT;
if (pgoff >= size)
return VM_FAULT_SIGBUS;
/* If the PMD would cover blocks out of the file */
if ((pgoff | PG_PMD_COLOUR) >= size) {
dax_pmd_dbg(NULL, address,
"offset + huge page size > file size");
return VM_FAULT_FALLBACK;
}
memset(&bh, 0, sizeof(bh));
bh.b_bdev = inode->i_sb->s_bdev;
block = (sector_t)pgoff << (PAGE_SHIFT - blkbits);
bh.b_size = PMD_SIZE;
if (get_block(inode, block, &bh, 0) != 0)
return VM_FAULT_SIGBUS;
if (!buffer_mapped(&bh) && write) {
if (get_block(inode, block, &bh, 1) != 0)
return VM_FAULT_SIGBUS;
alloc = true;
}
bdev = bh.b_bdev;
/*
* If the filesystem isn't willing to tell us the length of a hole,
* just fall back to PTEs. Calling get_block 512 times in a loop
* would be silly.
*/
if (!buffer_size_valid(&bh) || bh.b_size < PMD_SIZE) {
dax_pmd_dbg(&bh, address, "allocated block too small");
return VM_FAULT_FALLBACK;
}
/*
* If we allocated new storage, make sure no process has any
* zero pages covering this hole
*/
if (alloc) {
loff_t lstart = pgoff << PAGE_SHIFT;
loff_t lend = lstart + PMD_SIZE - 1; /* inclusive */
truncate_pagecache_range(inode, lstart, lend);
}
i_mmap_lock_read(mapping);
/*
* If a truncate happened while we were allocating blocks, we may
* leave blocks allocated to the file that are beyond EOF. We can't
* take i_mutex here, so just leave them hanging; they'll be freed
* when the file is deleted.
*/
size = (i_size_read(inode) + PAGE_SIZE - 1) >> PAGE_SHIFT;
if (pgoff >= size) {
result = VM_FAULT_SIGBUS;
goto out;
}
if ((pgoff | PG_PMD_COLOUR) >= size) {
dax_pmd_dbg(&bh, address,
"offset + huge page size > file size");
goto fallback;
}
if (!write && !buffer_mapped(&bh) && buffer_uptodate(&bh)) {
spinlock_t *ptl;
pmd_t entry;
struct page *zero_page = get_huge_zero_page();
if (unlikely(!zero_page)) {
dax_pmd_dbg(&bh, address, "no zero page");
goto fallback;
}
ptl = pmd_lock(vma->vm_mm, pmd);
if (!pmd_none(*pmd)) {
spin_unlock(ptl);
dax_pmd_dbg(&bh, address, "pmd already present");
goto fallback;
}
dev_dbg(part_to_dev(bdev->bd_part),
"%s: %s addr: %lx pfn: <zero> sect: %llx\n",
__func__, current->comm, address,
(unsigned long long) to_sector(&bh, inode));
entry = mk_pmd(zero_page, vma->vm_page_prot);
entry = pmd_mkhuge(entry);
set_pmd_at(vma->vm_mm, pmd_addr, pmd, entry);
result = VM_FAULT_NOPAGE;
spin_unlock(ptl);
} else {
struct blk_dax_ctl dax = {
.sector = to_sector(&bh, inode),
.size = PMD_SIZE,
};
long length = dax_map_atomic(bdev, &dax);
if (length < 0) {
result = VM_FAULT_SIGBUS;
goto out;
}
if (length < PMD_SIZE) {
dax_pmd_dbg(&bh, address, "dax-length too small");
dax_unmap_atomic(bdev, &dax);
goto fallback;
}
if (pfn_t_to_pfn(dax.pfn) & PG_PMD_COLOUR) {
dax_pmd_dbg(&bh, address, "pfn unaligned");
dax_unmap_atomic(bdev, &dax);
goto fallback;
}
if (!pfn_t_devmap(dax.pfn)) {
dax_unmap_atomic(bdev, &dax);
dax_pmd_dbg(&bh, address, "pfn not in memmap");
goto fallback;
}
if (buffer_unwritten(&bh) || buffer_new(&bh)) {
clear_pmem(dax.addr, PMD_SIZE);
wmb_pmem();
count_vm_event(PGMAJFAULT);
mem_cgroup_count_vm_event(vma->vm_mm, PGMAJFAULT);
result |= VM_FAULT_MAJOR;
}
dax_unmap_atomic(bdev, &dax);
/*
* For PTE faults we insert a radix tree entry for reads, and
* leave it clean. Then on the first write we dirty the radix
* tree entry via the dax_pfn_mkwrite() path. This sequence
* allows the dax_pfn_mkwrite() call to be simpler and avoid a
* call into get_block() to translate the pgoff to a sector in
* order to be able to create a new radix tree entry.
*
* The PMD path doesn't have an equivalent to
* dax_pfn_mkwrite(), though, so for a read followed by a
* write we traverse all the way through __dax_pmd_fault()
* twice. This means we can just skip inserting a radix tree
* entry completely on the initial read and just wait until
* the write to insert a dirty entry.
*/
if (write) {
error = dax_radix_entry(mapping, pgoff, dax.sector,
true, true);
if (error) {
dax_pmd_dbg(&bh, address,
"PMD radix insertion failed");
goto fallback;
}
}
dev_dbg(part_to_dev(bdev->bd_part),
"%s: %s addr: %lx pfn: %lx sect: %llx\n",
__func__, current->comm, address,
pfn_t_to_pfn(dax.pfn),
(unsigned long long) dax.sector);
result |= vmf_insert_pfn_pmd(vma, address, pmd,
dax.pfn, write);
}
out:
i_mmap_unlock_read(mapping);
if (buffer_unwritten(&bh))
complete_unwritten(&bh, !(result & VM_FAULT_ERROR));
return result;
fallback:
count_vm_event(THP_FAULT_FALLBACK);
result = VM_FAULT_FALLBACK;
goto out;
}
EXPORT_SYMBOL_GPL(__dax_pmd_fault);
/**
* dax_pmd_fault - handle a PMD fault on a DAX file
* @vma: The virtual memory area where the fault occurred
* @vmf: The description of the fault
* @get_block: The filesystem method used to translate file offsets to blocks
*
* When a page fault occurs, filesystems may call this helper in their
* pmd_fault handler for DAX files.
*/
int dax_pmd_fault(struct vm_area_struct *vma, unsigned long address,
pmd_t *pmd, unsigned int flags, get_block_t get_block,
dax_iodone_t complete_unwritten)
{
int result;
struct super_block *sb = file_inode(vma->vm_file)->i_sb;
if (flags & FAULT_FLAG_WRITE) {
sb_start_pagefault(sb);
file_update_time(vma->vm_file);
}
result = __dax_pmd_fault(vma, address, pmd, flags, get_block,
complete_unwritten);
if (flags & FAULT_FLAG_WRITE)
sb_end_pagefault(sb);
return result;
}
STATIC ssize_t
xfs_file_aio_write(
struct kiocb *iocb,
const struct iovec *iovp,
unsigned long nr_segs,
loff_t pos)
{
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, error = 0;
int ioflags = 0;
xfs_fsize_t isize, new_size;
int iolock;
int eventsent = 0;
size_t ocount = 0, count;
int need_i_mutex;
XFS_STATS_INC(xs_write_calls);
BUG_ON(iocb->ki_pos != pos);
if (unlikely(file->f_flags & O_DIRECT))
ioflags |= IO_ISDIRECT;
if (file->f_mode & FMODE_NOCMTIME)
ioflags |= IO_INVIS;
error = generic_segment_checks(iovp, &nr_segs, &ocount, VERIFY_READ);
if (error)
return error;
count = ocount;
if (count == 0)
return 0;
xfs_wait_for_freeze(mp, SB_FREEZE_WRITE);
if (XFS_FORCED_SHUTDOWN(mp))
return -EIO;
relock:
if (ioflags & IO_ISDIRECT) {
iolock = XFS_IOLOCK_SHARED;
need_i_mutex = 0;
} else {
iolock = XFS_IOLOCK_EXCL;
need_i_mutex = 1;
mutex_lock(&inode->i_mutex);
}
xfs_ilock(ip, XFS_ILOCK_EXCL|iolock);
start:
error = -generic_write_checks(file, &pos, &count,
S_ISBLK(inode->i_mode));
if (error) {
xfs_iunlock(ip, XFS_ILOCK_EXCL|iolock);
goto out_unlock_mutex;
}
if ((DM_EVENT_ENABLED(ip, DM_EVENT_WRITE) &&
!(ioflags & IO_INVIS) && !eventsent)) {
int dmflags = FILP_DELAY_FLAG(file);
if (need_i_mutex)
dmflags |= DM_FLAGS_IMUX;
xfs_iunlock(ip, XFS_ILOCK_EXCL);
error = XFS_SEND_DATA(ip->i_mount, DM_EVENT_WRITE, ip,
pos, count, dmflags, &iolock);
if (error) {
goto out_unlock_internal;
}
xfs_ilock(ip, XFS_ILOCK_EXCL);
eventsent = 1;
/*
* The iolock was dropped and reacquired in XFS_SEND_DATA
* so we have to recheck the size when appending.
* We will only "goto start;" once, since having sent the
* event prevents another call to XFS_SEND_DATA, which is
* what allows the size to change in the first place.
*/
if ((file->f_flags & O_APPEND) && pos != ip->i_size)
goto start;
}
if (ioflags & IO_ISDIRECT) {
xfs_buftarg_t *target =
XFS_IS_REALTIME_INODE(ip) ?
mp->m_rtdev_targp : mp->m_ddev_targp;
if ((pos & target->bt_smask) || (count & target->bt_smask)) {
xfs_iunlock(ip, XFS_ILOCK_EXCL|iolock);
return XFS_ERROR(-EINVAL);
}
if (!need_i_mutex && (mapping->nrpages || pos > ip->i_size)) {
xfs_iunlock(ip, XFS_ILOCK_EXCL|iolock);
iolock = XFS_IOLOCK_EXCL;
need_i_mutex = 1;
mutex_lock(&inode->i_mutex);
xfs_ilock(ip, XFS_ILOCK_EXCL|iolock);
goto start;
}
}
new_size = pos + count;
if (new_size > ip->i_size)
ip->i_new_size = new_size;
if (likely(!(ioflags & IO_INVIS)))
file_update_time(file);
/*
* If the offset is beyond the size of the file, we have a couple
* of things to do. First, if there is already space allocated
* we need to either create holes or zero the disk or ...
*
* If there is a page where the previous size lands, we need
* to zero it out up to the new size.
*/
if (pos > ip->i_size) {
error = xfs_zero_eof(ip, pos, ip->i_size);
if (error) {
xfs_iunlock(ip, XFS_ILOCK_EXCL);
goto out_unlock_internal;
}
}
xfs_iunlock(ip, XFS_ILOCK_EXCL);
/*
* 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.
*/
error = -file_remove_suid(file);
if (unlikely(error))
goto out_unlock_internal;
/* We can write back this queue in page reclaim */
current->backing_dev_info = mapping->backing_dev_info;
if ((ioflags & IO_ISDIRECT)) {
if (mapping->nrpages) {
WARN_ON(need_i_mutex == 0);
error = xfs_flushinval_pages(ip,
(pos & PAGE_CACHE_MASK),
-1, FI_REMAPF_LOCKED);
if (error)
goto out_unlock_internal;
}
if (need_i_mutex) {
/* demote the lock now the cached pages are gone */
xfs_ilock_demote(ip, XFS_IOLOCK_EXCL);
mutex_unlock(&inode->i_mutex);
iolock = XFS_IOLOCK_SHARED;
need_i_mutex = 0;
}
trace_xfs_file_direct_write(ip, count, iocb->ki_pos, ioflags);
ret = generic_file_direct_write(iocb, iovp,
&nr_segs, pos, &iocb->ki_pos, count, ocount);
/*
* direct-io write to a hole: fall through to buffered I/O
* for completing the rest of the request.
*/
if (ret >= 0 && ret != count) {
XFS_STATS_ADD(xs_write_bytes, ret);
pos += ret;
count -= ret;
ioflags &= ~IO_ISDIRECT;
xfs_iunlock(ip, iolock);
goto relock;
}
} else {
int enospc = 0;
ssize_t ret2 = 0;
write_retry:
trace_xfs_file_buffered_write(ip, count, iocb->ki_pos, ioflags);
ret2 = generic_file_buffered_write(iocb, iovp, nr_segs,
pos, &iocb->ki_pos, count, ret);
/*
* if we just got an ENOSPC, flush the inode now we
* aren't holding any page locks and retry *once*
*/
if (ret2 == -ENOSPC && !enospc) {
error = xfs_flush_pages(ip, 0, -1, 0, FI_NONE);
if (error)
goto out_unlock_internal;
enospc = 1;
goto write_retry;
}
ret = ret2;
}
current->backing_dev_info = NULL;
isize = i_size_read(inode);
if (unlikely(ret < 0 && ret != -EFAULT && iocb->ki_pos > isize))
iocb->ki_pos = isize;
if (iocb->ki_pos > ip->i_size) {
xfs_ilock(ip, XFS_ILOCK_EXCL);
if (iocb->ki_pos > ip->i_size)
ip->i_size = iocb->ki_pos;
xfs_iunlock(ip, XFS_ILOCK_EXCL);
}
if (ret == -ENOSPC &&
DM_EVENT_ENABLED(ip, DM_EVENT_NOSPACE) && !(ioflags & IO_INVIS)) {
xfs_iunlock(ip, iolock);
if (need_i_mutex)
mutex_unlock(&inode->i_mutex);
error = XFS_SEND_NAMESP(ip->i_mount, DM_EVENT_NOSPACE, ip,
DM_RIGHT_NULL, ip, DM_RIGHT_NULL, NULL, NULL,
0, 0, 0); /* Delay flag intentionally unused */
if (need_i_mutex)
mutex_lock(&inode->i_mutex);
xfs_ilock(ip, iolock);
if (error)
goto out_unlock_internal;
goto start;
}
error = -ret;
if (ret <= 0)
goto out_unlock_internal;
XFS_STATS_ADD(xs_write_bytes, ret);
/* Handle various SYNC-type writes */
if ((file->f_flags & O_DSYNC) || IS_SYNC(inode)) {
loff_t end = pos + ret - 1;
int error2;
xfs_iunlock(ip, iolock);
if (need_i_mutex)
mutex_unlock(&inode->i_mutex);
error2 = filemap_write_and_wait_range(mapping, pos, end);
if (!error)
error = error2;
if (need_i_mutex)
mutex_lock(&inode->i_mutex);
xfs_ilock(ip, iolock);
error2 = -xfs_file_fsync(file, file->f_path.dentry,
(file->f_flags & __O_SYNC) ? 0 : 1);
if (!error)
error = error2;
}
out_unlock_internal:
if (ip->i_new_size) {
xfs_ilock(ip, XFS_ILOCK_EXCL);
ip->i_new_size = 0;
/*
* If this was a direct or synchronous I/O that failed (such
* as ENOSPC) then part of the I/O may have been written to
* disk before the error occured. In this case the on-disk
* file size may have been adjusted beyond the in-memory file
* size and now needs to be truncated back.
*/
if (ip->i_d.di_size > ip->i_size)
ip->i_d.di_size = ip->i_size;
xfs_iunlock(ip, XFS_ILOCK_EXCL);
}
xfs_iunlock(ip, iolock);
out_unlock_mutex:
if (need_i_mutex)
mutex_unlock(&inode->i_mutex);
return -error;
}
static ssize_t
svfs_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
unsigned long nr_segs, loff_t pos)
{
struct file *filp = iocb->ki_filp;
struct file *llfs_filp;
struct inode *inode = filp->f_dentry->d_inode;
struct svfs_inode *si = SVFS_I(inode);
const char __user *buf;
size_t count;
ssize_t ret = 0, bw;
int seg;
svfs_entry(mdc, "f_mode 0x%x, pos %lu, check 0x%x\n",
filp->f_mode,
(unsigned long)pos,
(si->state & SVFS_STATE_CONN));
if (si->state & SVFS_STATE_DA) {
/* create it now */
ASSERT(!(si->state & SVFS_STATE_CONN));
ret = llfs_create(filp->f_dentry);
if (ret)
goto out;
}
if (!(si->state & SVFS_STATE_CONN)) {
/* open it? */
ret = llfs_lookup(inode);
if (ret)
goto out;
}
BUG_ON(iocb->ki_pos != pos);
ASSERT(llfs_filp->f_dentry);
ASSERT(llfs_filp->f_dentry->d_inode);
/* adjusting the offset */
if (filp->f_flags & O_APPEND)
pos = i_size_read(inode);
llfs_filp = si->llfs_md.llfs_filp;
llfs_filp->f_pos = pos;
if (!(llfs_filp->f_mode & FMODE_WRITE))
return -EBADF;
if (!llfs_filp->f_op ||
(!llfs_filp->f_op->write && !llfs_filp->f_op->aio_write))
return -EINVAL;
for (seg = 0; seg < nr_segs; seg++) {
buf = iov[seg].iov_base;
count = iov[seg].iov_len;
svfs_debug(mdc, "buf %p, len %ld: \n", buf, count);
if (llfs_filp->f_op->write)
bw = llfs_filp->f_op->write(llfs_filp, buf, count,
&llfs_filp->f_pos);
else
bw = do_sync_write(llfs_filp, buf, count, &llfs_filp->f_pos);
if (bw < 0) {
ret = bw;
goto out;
}
ret += bw;
}
if (ret > 0)
fsnotify_modify(llfs_filp->f_dentry);
if (ret > 0 && ((filp->f_flags & O_SYNC) || IS_SYNC(inode))) {
ssize_t err;
err = sync_page_range(llfs_filp->f_dentry->d_inode,
llfs_filp->f_mapping,
pos, ret);
if (err < 0)
ret = err;
}
iocb->ki_pos += ret;
ASSERT(llfs_filp->f_pos == iocb->ki_ops);
/* should update the file info */
file_update_time(filp);
if (pos + ret > inode->i_size) {
svfs_debug(mdc, "update with pos %lu count %ld, "
"original i_size %lu\n",
(unsigned long)pos, ret,
(unsigned long)inode->i_size);
i_size_write(inode, pos + ret);
mark_inode_dirty(inode);
}
out:
return ret;
}
static ssize_t
ncp_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
{
struct file *file = iocb->ki_filp;
struct inode *inode = file_inode(file);
size_t already_written = 0;
size_t bufsize;
int errno;
void *bouncebuffer;
off_t pos;
ncp_dbg(1, "enter %pD2\n", file);
errno = generic_write_checks(iocb, from);
if (errno <= 0)
return errno;
errno = ncp_make_open(inode, O_WRONLY);
if (errno) {
ncp_dbg(1, "open failed, error=%d\n", errno);
return errno;
}
bufsize = NCP_SERVER(inode)->buffer_size;
errno = file_update_time(file);
if (errno)
goto outrel;
bouncebuffer = vmalloc(bufsize);
if (!bouncebuffer) {
errno = -EIO; /* -ENOMEM */
goto outrel;
}
pos = iocb->ki_pos;
while (iov_iter_count(from)) {
int written_this_time;
size_t to_write = min_t(size_t,
bufsize - (pos % bufsize),
iov_iter_count(from));
if (copy_from_iter(bouncebuffer, to_write, from) != to_write) {
errno = -EFAULT;
break;
}
if (ncp_write_kernel(NCP_SERVER(inode),
NCP_FINFO(inode)->file_handle,
pos, to_write, bouncebuffer, &written_this_time) != 0) {
errno = -EIO;
break;
}
pos += written_this_time;
already_written += written_this_time;
if (written_this_time != to_write)
break;
}
vfree(bouncebuffer);
iocb->ki_pos = pos;
if (pos > i_size_read(inode)) {
mutex_lock(&inode->i_mutex);
if (pos > i_size_read(inode))
i_size_write(inode, pos);
mutex_unlock(&inode->i_mutex);
}
ncp_dbg(1, "exit %pD2\n", file);
outrel:
ncp_inode_close(inode);
return already_written ? already_written : errno;
}
static int nilfs_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
{
struct page *page = vmf->page;
struct inode *inode = file_inode(vma->vm_file);
struct nilfs_transaction_info ti;
int ret = 0;
if (unlikely(nilfs_near_disk_full(inode->i_sb->s_fs_info)))
return VM_FAULT_SIGBUS; /* -ENOSPC */
sb_start_pagefault(inode->i_sb);
lock_page(page);
if (page->mapping != inode->i_mapping ||
page_offset(page) >= i_size_read(inode) || !PageUptodate(page)) {
unlock_page(page);
ret = -EFAULT; /* make the VM retry the fault */
goto out;
}
/*
* check to see if the page is mapped already (no holes)
*/
if (PageMappedToDisk(page))
goto mapped;
if (page_has_buffers(page)) {
struct buffer_head *bh, *head;
int fully_mapped = 1;
bh = head = page_buffers(page);
do {
if (!buffer_mapped(bh)) {
fully_mapped = 0;
break;
}
} while (bh = bh->b_this_page, bh != head);
if (fully_mapped) {
SetPageMappedToDisk(page);
goto mapped;
}
}
unlock_page(page);
/*
* fill hole blocks
*/
ret = nilfs_transaction_begin(inode->i_sb, &ti, 1);
/* never returns -ENOMEM, but may return -ENOSPC */
if (unlikely(ret))
goto out;
file_update_time(vma->vm_file);
ret = __block_page_mkwrite(vma, vmf, nilfs_get_block);
if (ret) {
nilfs_transaction_abort(inode->i_sb);
goto out;
}
nilfs_set_file_dirty(inode, 1 << (PAGE_SHIFT - inode->i_blkbits));
nilfs_transaction_commit(inode->i_sb);
mapped:
wait_for_stable_page(page);
out:
sb_end_pagefault(inode->i_sb);
return block_page_mkwrite_return(ret);
}