2005-04-17 02:20:36 +04:00
|
|
|
/*
|
|
|
|
* linux/fs/ext2/file.c
|
|
|
|
*
|
|
|
|
* Copyright (C) 1992, 1993, 1994, 1995
|
|
|
|
* Remy Card (card@masi.ibp.fr)
|
|
|
|
* Laboratoire MASI - Institut Blaise Pascal
|
|
|
|
* Universite Pierre et Marie Curie (Paris VI)
|
|
|
|
*
|
|
|
|
* from
|
|
|
|
*
|
|
|
|
* linux/fs/minix/file.c
|
|
|
|
*
|
|
|
|
* Copyright (C) 1991, 1992 Linus Torvalds
|
|
|
|
*
|
|
|
|
* ext2 fs regular file handling primitives
|
|
|
|
*
|
|
|
|
* 64-bit file support on 64-bit platforms by Jakub Jelinek
|
|
|
|
* (jj@sunsite.ms.mff.cuni.cz)
|
|
|
|
*/
|
|
|
|
|
|
|
|
#include <linux/time.h>
|
2009-12-16 03:46:49 +03:00
|
|
|
#include <linux/pagemap.h>
|
2015-09-09 00:58:40 +03:00
|
|
|
#include <linux/dax.h>
|
2010-03-03 17:05:07 +03:00
|
|
|
#include <linux/quotaops.h>
|
2016-09-19 04:30:29 +03:00
|
|
|
#include <linux/iomap.h>
|
|
|
|
#include <linux/uio.h>
|
2005-04-17 02:20:36 +04:00
|
|
|
#include "ext2.h"
|
|
|
|
#include "xattr.h"
|
|
|
|
#include "acl.h"
|
|
|
|
|
2015-02-17 02:59:25 +03:00
|
|
|
#ifdef CONFIG_FS_DAX
|
2016-09-19 04:30:29 +03:00
|
|
|
static ssize_t ext2_dax_read_iter(struct kiocb *iocb, struct iov_iter *to)
|
|
|
|
{
|
|
|
|
struct inode *inode = iocb->ki_filp->f_mapping->host;
|
|
|
|
ssize_t ret;
|
|
|
|
|
|
|
|
if (!iov_iter_count(to))
|
|
|
|
return 0; /* skip atime */
|
|
|
|
|
|
|
|
inode_lock_shared(inode);
|
2016-11-08 03:32:46 +03:00
|
|
|
ret = dax_iomap_rw(iocb, to, &ext2_iomap_ops);
|
2016-09-19 04:30:29 +03:00
|
|
|
inode_unlock_shared(inode);
|
|
|
|
|
|
|
|
file_accessed(iocb->ki_filp);
|
|
|
|
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;
|
|
|
|
|
2016-11-08 03:32:46 +03:00
|
|
|
ret = dax_iomap_rw(iocb, from, &ext2_iomap_ops);
|
2016-09-19 04:30:29 +03:00
|
|
|
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;
|
|
|
|
}
|
|
|
|
|
2015-10-14 01:25:37 +03:00
|
|
|
/*
|
|
|
|
* 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.
|
|
|
|
*/
|
2017-02-25 01:56:41 +03:00
|
|
|
static int ext2_dax_fault(struct vm_fault *vmf)
|
2015-02-17 02:59:02 +03:00
|
|
|
{
|
2017-02-25 01:56:41 +03:00
|
|
|
struct inode *inode = file_inode(vmf->vma->vm_file);
|
2015-10-14 01:25:37 +03:00
|
|
|
struct ext2_inode_info *ei = EXT2_I(inode);
|
|
|
|
int ret;
|
|
|
|
|
|
|
|
if (vmf->flags & FAULT_FLAG_WRITE) {
|
|
|
|
sb_start_pagefault(inode->i_sb);
|
2017-02-25 01:56:41 +03:00
|
|
|
file_update_time(vmf->vma->vm_file);
|
2015-10-14 01:25:37 +03:00
|
|
|
}
|
|
|
|
down_read(&ei->dax_sem);
|
|
|
|
|
2017-02-25 01:57:08 +03:00
|
|
|
ret = dax_iomap_fault(vmf, PE_SIZE_PTE, &ext2_iomap_ops);
|
2015-10-14 01:25:37 +03:00
|
|
|
|
|
|
|
up_read(&ei->dax_sem);
|
|
|
|
if (vmf->flags & FAULT_FLAG_WRITE)
|
|
|
|
sb_end_pagefault(inode->i_sb);
|
|
|
|
return ret;
|
2015-02-17 02:59:02 +03:00
|
|
|
}
|
|
|
|
|
2017-02-25 01:56:41 +03:00
|
|
|
static int ext2_dax_pfn_mkwrite(struct vm_fault *vmf)
|
2015-10-14 01:25:37 +03:00
|
|
|
{
|
2017-02-25 01:56:41 +03:00
|
|
|
struct inode *inode = file_inode(vmf->vma->vm_file);
|
2015-10-14 01:25:37 +03:00
|
|
|
struct ext2_inode_info *ei = EXT2_I(inode);
|
|
|
|
loff_t size;
|
2016-01-23 02:10:50 +03:00
|
|
|
int ret;
|
2015-10-14 01:25:37 +03:00
|
|
|
|
|
|
|
sb_start_pagefault(inode->i_sb);
|
2017-02-25 01:56:41 +03:00
|
|
|
file_update_time(vmf->vma->vm_file);
|
2015-10-14 01:25:37 +03:00
|
|
|
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;
|
2016-01-23 02:10:50 +03:00
|
|
|
else
|
2017-02-25 01:56:41 +03:00
|
|
|
ret = dax_pfn_mkwrite(vmf);
|
2015-10-14 01:25:37 +03:00
|
|
|
|
|
|
|
up_read(&ei->dax_sem);
|
|
|
|
sb_end_pagefault(inode->i_sb);
|
|
|
|
return ret;
|
2015-02-17 02:59:02 +03:00
|
|
|
}
|
|
|
|
|
|
|
|
static const struct vm_operations_struct ext2_dax_vm_ops = {
|
|
|
|
.fault = ext2_dax_fault,
|
2016-11-08 03:31:33 +03:00
|
|
|
/*
|
mm,fs,dax: change ->pmd_fault to ->huge_fault
Patch series "1G transparent hugepage support for device dax", v2.
The following series implements support for 1G trasparent hugepage on
x86 for device dax. The bulk of the code was written by Mathew Wilcox a
while back supporting transparent 1G hugepage for fs DAX. I have
forward ported the relevant bits to 4.10-rc. The current submission has
only the necessary code to support device DAX.
Comments from Dan Williams: So the motivation and intended user of this
functionality mirrors the motivation and users of 1GB page support in
hugetlbfs. Given expected capacities of persistent memory devices an
in-memory database may want to reduce tlb pressure beyond what they can
already achieve with 2MB mappings of a device-dax file. We have
customer feedback to that effect as Willy mentioned in his previous
version of these patches [1].
[1]: https://lkml.org/lkml/2016/1/31/52
Comments from Nilesh @ Oracle:
There are applications which have a process model; and if you assume
10,000 processes attempting to mmap all the 6TB memory available on a
server; we are looking at the following:
processes : 10,000
memory : 6TB
pte @ 4k page size: 8 bytes / 4K of memory * #processes = 6TB / 4k * 8 * 10000 = 1.5GB * 80000 = 120,000GB
pmd @ 2M page size: 120,000 / 512 = ~240GB
pud @ 1G page size: 240GB / 512 = ~480MB
As you can see with 2M pages, this system will use up an exorbitant
amount of DRAM to hold the page tables; but the 1G pages finally brings
it down to a reasonable level. Memory sizes will keep increasing; so
this number will keep increasing.
An argument can be made to convert the applications from process model
to thread model, but in the real world that may not be always practical.
Hopefully this helps explain the use case where this is valuable.
This patch (of 3):
In preparation for adding the ability to handle PUD pages, convert
vm_operations_struct.pmd_fault to vm_operations_struct.huge_fault. The
vm_fault structure is extended to include a union of the different page
table pointers that may be needed, and three flag bits are reserved to
indicate which type of pointer is in the union.
[ross.zwisler@linux.intel.com: remove unused function ext4_dax_huge_fault()]
Link: http://lkml.kernel.org/r/1485813172-7284-1-git-send-email-ross.zwisler@linux.intel.com
[dave.jiang@intel.com: clear PMD or PUD size flags when in fall through path]
Link: http://lkml.kernel.org/r/148589842696.5820.16078080610311444794.stgit@djiang5-desk3.ch.intel.com
Link: http://lkml.kernel.org/r/148545058784.17912.6353162518188733642.stgit@djiang5-desk3.ch.intel.com
Signed-off-by: Matthew Wilcox <mawilcox@microsoft.com>
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
Signed-off-by: Ross Zwisler <ross.zwisler@linux.intel.com>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Jan Kara <jack@suse.com>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Nilesh Choudhury <nilesh.choudhury@oracle.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Dave Jiang <dave.jiang@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-02-25 01:56:59 +03:00
|
|
|
* .huge_fault is not supported for DAX because allocation in ext2
|
2016-11-08 03:31:33 +03:00
|
|
|
* cannot be reliably aligned to huge page sizes and so pmd faults
|
|
|
|
* will always fail and fail back to regular faults.
|
|
|
|
*/
|
2016-02-27 22:01:13 +03:00
|
|
|
.page_mkwrite = ext2_dax_fault,
|
2015-10-14 01:25:37 +03:00
|
|
|
.pfn_mkwrite = ext2_dax_pfn_mkwrite,
|
2015-02-17 02:59:02 +03:00
|
|
|
};
|
|
|
|
|
|
|
|
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;
|
2016-11-08 03:31:33 +03:00
|
|
|
vma->vm_flags |= VM_MIXEDMAP;
|
2015-02-17 02:59:02 +03:00
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
#else
|
|
|
|
#define ext2_file_mmap generic_file_mmap
|
|
|
|
#endif
|
|
|
|
|
2005-04-17 02:20:36 +04:00
|
|
|
/*
|
2007-07-16 10:40:22 +04:00
|
|
|
* Called when filp is released. This happens when all file descriptors
|
|
|
|
* for a single struct file are closed. Note that different open() calls
|
|
|
|
* for the same file yield different struct file structures.
|
2005-04-17 02:20:36 +04:00
|
|
|
*/
|
|
|
|
static int ext2_release_file (struct inode * inode, struct file * filp)
|
|
|
|
{
|
2007-10-17 10:30:46 +04:00
|
|
|
if (filp->f_mode & FMODE_WRITE) {
|
|
|
|
mutex_lock(&EXT2_I(inode)->truncate_mutex);
|
|
|
|
ext2_discard_reservation(inode);
|
|
|
|
mutex_unlock(&EXT2_I(inode)->truncate_mutex);
|
|
|
|
}
|
2005-04-17 02:20:36 +04:00
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2011-07-17 04:44:56 +04:00
|
|
|
int ext2_fsync(struct file *file, loff_t start, loff_t end, int datasync)
|
2009-12-16 03:46:49 +03:00
|
|
|
{
|
|
|
|
int ret;
|
2010-05-26 19:53:25 +04:00
|
|
|
struct super_block *sb = file->f_mapping->host->i_sb;
|
2009-12-16 03:46:49 +03:00
|
|
|
|
2011-07-17 04:44:56 +04:00
|
|
|
ret = generic_file_fsync(file, start, end, datasync);
|
2017-07-06 14:02:21 +03:00
|
|
|
if (ret == -EIO)
|
2009-12-16 03:46:49 +03:00
|
|
|
/* We don't really know where the IO error happened... */
|
|
|
|
ext2_error(sb, __func__,
|
|
|
|
"detected IO error when writing metadata buffers");
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
2016-09-19 04:30:29 +03:00
|
|
|
static ssize_t ext2_file_read_iter(struct kiocb *iocb, struct iov_iter *to)
|
|
|
|
{
|
|
|
|
#ifdef CONFIG_FS_DAX
|
|
|
|
if (IS_DAX(iocb->ki_filp->f_mapping->host))
|
|
|
|
return ext2_dax_read_iter(iocb, to);
|
|
|
|
#endif
|
|
|
|
return generic_file_read_iter(iocb, to);
|
|
|
|
}
|
|
|
|
|
|
|
|
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);
|
|
|
|
}
|
|
|
|
|
2006-03-28 13:56:42 +04:00
|
|
|
const struct file_operations ext2_file_operations = {
|
2005-04-17 02:20:36 +04:00
|
|
|
.llseek = generic_file_llseek,
|
2016-09-19 04:30:29 +03:00
|
|
|
.read_iter = ext2_file_read_iter,
|
|
|
|
.write_iter = ext2_file_write_iter,
|
2008-02-06 12:40:10 +03:00
|
|
|
.unlocked_ioctl = ext2_ioctl,
|
2006-08-29 22:06:20 +04:00
|
|
|
#ifdef CONFIG_COMPAT
|
|
|
|
.compat_ioctl = ext2_compat_ioctl,
|
|
|
|
#endif
|
2015-02-17 02:59:02 +03:00
|
|
|
.mmap = ext2_file_mmap,
|
2010-03-03 17:05:06 +03:00
|
|
|
.open = dquot_file_open,
|
2005-04-17 02:20:36 +04:00
|
|
|
.release = ext2_release_file,
|
2009-12-16 03:46:49 +03:00
|
|
|
.fsync = ext2_fsync,
|
2016-10-08 02:59:59 +03:00
|
|
|
.get_unmapped_area = thp_get_unmapped_area,
|
2006-03-30 17:15:30 +04:00
|
|
|
.splice_read = generic_file_splice_read,
|
2014-04-05 12:27:08 +04:00
|
|
|
.splice_write = iter_file_splice_write,
|
2005-04-17 02:20:36 +04:00
|
|
|
};
|
|
|
|
|
2007-02-12 11:55:38 +03:00
|
|
|
const struct inode_operations ext2_file_inode_operations = {
|
2005-04-17 02:20:36 +04:00
|
|
|
#ifdef CONFIG_EXT2_FS_XATTR
|
|
|
|
.listxattr = ext2_listxattr,
|
|
|
|
#endif
|
|
|
|
.setattr = ext2_setattr,
|
2011-07-23 19:37:31 +04:00
|
|
|
.get_acl = ext2_get_acl,
|
2013-12-20 17:16:44 +04:00
|
|
|
.set_acl = ext2_set_acl,
|
2008-10-04 01:32:43 +04:00
|
|
|
.fiemap = ext2_fiemap,
|
2005-04-17 02:20:36 +04:00
|
|
|
};
|