/*
* 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;
}
/*
* 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;
}
/*
* 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;
}
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;
}
/*
* 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;
}
