linux/fs/ext4/file.c
Linus Torvalds a3841f94c7 libnvdimm for 4.15
* Introduce MAP_SYNC and MAP_SHARED_VALIDATE, a mechanism to enable
  'userspace flush' of persistent memory updates via filesystem-dax
   mappings. It arranges for any filesystem metadata updates that may be
   required to satisfy a write fault to also be flushed ("on disk") before
   the kernel returns to userspace from the fault handler. Effectively
   every write-fault that dirties metadata completes an fsync() before
   returning from the fault handler. The new MAP_SHARED_VALIDATE mapping
   type guarantees that the MAP_SYNC flag is validated as supported by the
   filesystem's ->mmap() file operation.
 
 * Add support for the standard ACPI 6.2 label access methods that
   replace the NVDIMM_FAMILY_INTEL (vendor specific) label methods. This
   enables interoperability with environments that only implement the
   standardized methods.
 
 * Add support for the ACPI 6.2 NVDIMM media error injection methods.
 
 * Add support for the NVDIMM_FAMILY_INTEL v1.6 DIMM commands for latch
   last shutdown status, firmware update, SMART error injection, and
   SMART alarm threshold control.
 
 * Cleanup physical address information disclosures to be root-only.
 
 * Fix revalidation of the DIMM "locked label area" status to support
   dynamic unlock of the label area.
 
 * Expand unit test infrastructure to mock the ACPI 6.2 Translate SPA
   (system-physical-address) command and error injection commands.
 
 Acknowledgements that came after the commits were pushed to -next:
 
 957ac8c421 dax: fix PMD faults on zero-length files
 Reviewed-by: Ross Zwisler <ross.zwisler@linux.intel.com>
 
 a39e596baa xfs: support for synchronous DAX faults
 Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
 
 7b565c9f96 xfs: Implement xfs_filemap_pfn_mkwrite() using __xfs_filemap_fault()
 Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
 -----BEGIN PGP SIGNATURE-----
 
 iQIcBAABAgAGBQJaDfvcAAoJEB7SkWpmfYgCk7sP/2qJhBH+VTTdg2osDnhAdAhI
 co/AGEmsHFlUCMBb/Ek7UnMAmhBYiJU2q4ywPsNFBpusXpMlqNy5Iwo7k4/wQHE/
 SJcIM0g4zg0ViFuUhwV+C2T0R5UzFR8JLd9EYWj/YS6aJpurtotm5l4UStaM0Hzo
 AhxSXJLrBDuqCpbOxbctfiGEmdRL7aRfBEAARTNRKBn/iXxJUcYHlp62rtXQS+t4
 I6LC/URCWTNTTMGmzW6TRsgSD9WMfd19xKcGzN3qL6ee0KFccxN4ctFqHA/sFGOh
 iYLeR0XJUjJxyp+PkWGteXPVZL0Kj3bD/lSTG+Co5bm/ra8a/sh3TSFfgFyoBZD1
 EqMN8Ryf80hGp3FabeH2Iw2SviYPZpHSWgjddjxLD0RA6OmpzINc+Wm8eqApjMME
 sbZDTOijiab4QMQ0XamF4GuDHyQtawv5Y/w2Ehhl1tmiqW+5tKhsKqxkQt+/V3Yt
 RTVSRe2Pkway66b+cD64IdQ6L2tyonPnmi5IzgkKOhlOEGomy+4/U2Jt2bMbhzq6
 ymszKmXp2XI8P06wU8sHrIUeXO5I9qoKn/fZA73Eb8aIzgJe3tBE/5+Ab7RG6HB9
 1OVfcMWoXU1gNgNktTs63X1Lsg4aW9kt/K4fPHHcqUcaliEJpJTlAbg9GLF2buoW
 nQ+0fTRgMRihE3ZA0Fs3
 =h2vZ
 -----END PGP SIGNATURE-----

Merge tag 'libnvdimm-for-4.15' of git://git.kernel.org/pub/scm/linux/kernel/git/nvdimm/nvdimm

Pull libnvdimm and dax updates from Dan Williams:
 "Save for a few late fixes, all of these commits have shipped in -next
  releases since before the merge window opened, and 0day has given a
  build success notification.

  The ext4 touches came from Jan, and the xfs touches have Darrick's
  reviewed-by. An xfstest for the MAP_SYNC feature has been through
  a few round of reviews and is on track to be merged.

   - Introduce MAP_SYNC and MAP_SHARED_VALIDATE, a mechanism to enable
     'userspace flush' of persistent memory updates via filesystem-dax
     mappings. It arranges for any filesystem metadata updates that may
     be required to satisfy a write fault to also be flushed ("on disk")
     before the kernel returns to userspace from the fault handler.
     Effectively every write-fault that dirties metadata completes an
     fsync() before returning from the fault handler. The new
     MAP_SHARED_VALIDATE mapping type guarantees that the MAP_SYNC flag
     is validated as supported by the filesystem's ->mmap() file
     operation.

   - Add support for the standard ACPI 6.2 label access methods that
     replace the NVDIMM_FAMILY_INTEL (vendor specific) label methods.
     This enables interoperability with environments that only implement
     the standardized methods.

   - Add support for the ACPI 6.2 NVDIMM media error injection methods.

   - Add support for the NVDIMM_FAMILY_INTEL v1.6 DIMM commands for
     latch last shutdown status, firmware update, SMART error injection,
     and SMART alarm threshold control.

   - Cleanup physical address information disclosures to be root-only.

   - Fix revalidation of the DIMM "locked label area" status to support
     dynamic unlock of the label area.

   - Expand unit test infrastructure to mock the ACPI 6.2 Translate SPA
     (system-physical-address) command and error injection commands.

  Acknowledgements that came after the commits were pushed to -next:

   - 957ac8c421 ("dax: fix PMD faults on zero-length files"):
       Reviewed-by: Ross Zwisler <ross.zwisler@linux.intel.com>

   - a39e596baa ("xfs: support for synchronous DAX faults") and
     7b565c9f96 ("xfs: Implement xfs_filemap_pfn_mkwrite() using __xfs_filemap_fault()")
        Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>"

* tag 'libnvdimm-for-4.15' of git://git.kernel.org/pub/scm/linux/kernel/git/nvdimm/nvdimm: (49 commits)
  acpi, nfit: add 'Enable Latch System Shutdown Status' command support
  dax: fix general protection fault in dax_alloc_inode
  dax: fix PMD faults on zero-length files
  dax: stop requiring a live device for dax_flush()
  brd: remove dax support
  dax: quiet bdev_dax_supported()
  fs, dax: unify IOMAP_F_DIRTY read vs write handling policy in the dax core
  tools/testing/nvdimm: unit test clear-error commands
  acpi, nfit: validate commands against the device type
  tools/testing/nvdimm: stricter bounds checking for error injection commands
  xfs: support for synchronous DAX faults
  xfs: Implement xfs_filemap_pfn_mkwrite() using __xfs_filemap_fault()
  ext4: Support for synchronous DAX faults
  ext4: Simplify error handling in ext4_dax_huge_fault()
  dax: Implement dax_finish_sync_fault()
  dax, iomap: Add support for synchronous faults
  mm: Define MAP_SYNC and VM_SYNC flags
  dax: Allow tuning whether dax_insert_mapping_entry() dirties entry
  dax: Allow dax_iomap_fault() to return pfn
  dax: Fix comment describing dax_iomap_fault()
  ...
2017-11-17 09:51:57 -08:00

504 lines
13 KiB
C

// SPDX-License-Identifier: GPL-2.0
/*
* linux/fs/ext4/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
*
* ext4 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>
#include <linux/fs.h>
#include <linux/iomap.h>
#include <linux/mount.h>
#include <linux/path.h>
#include <linux/dax.h>
#include <linux/quotaops.h>
#include <linux/pagevec.h>
#include <linux/uio.h>
#include <linux/mman.h>
#include "ext4.h"
#include "ext4_jbd2.h"
#include "xattr.h"
#include "acl.h"
#ifdef CONFIG_FS_DAX
static ssize_t ext4_dax_read_iter(struct kiocb *iocb, struct iov_iter *to)
{
struct inode *inode = file_inode(iocb->ki_filp);
ssize_t ret;
if (!inode_trylock_shared(inode)) {
if (iocb->ki_flags & IOCB_NOWAIT)
return -EAGAIN;
inode_lock_shared(inode);
}
/*
* Recheck under inode lock - at this point we are sure it cannot
* change anymore
*/
if (!IS_DAX(inode)) {
inode_unlock_shared(inode);
/* Fallback to buffered IO in case we cannot support DAX */
return generic_file_read_iter(iocb, to);
}
ret = dax_iomap_rw(iocb, to, &ext4_iomap_ops);
inode_unlock_shared(inode);
file_accessed(iocb->ki_filp);
return ret;
}
#endif
static ssize_t ext4_file_read_iter(struct kiocb *iocb, struct iov_iter *to)
{
if (unlikely(ext4_forced_shutdown(EXT4_SB(file_inode(iocb->ki_filp)->i_sb))))
return -EIO;
if (!iov_iter_count(to))
return 0; /* skip atime */
#ifdef CONFIG_FS_DAX
if (IS_DAX(file_inode(iocb->ki_filp)))
return ext4_dax_read_iter(iocb, to);
#endif
return generic_file_read_iter(iocb, to);
}
/*
* Called when an inode is released. Note that this is different
* from ext4_file_open: open gets called at every open, but release
* gets called only when /all/ the files are closed.
*/
static int ext4_release_file(struct inode *inode, struct file *filp)
{
if (ext4_test_inode_state(inode, EXT4_STATE_DA_ALLOC_CLOSE)) {
ext4_alloc_da_blocks(inode);
ext4_clear_inode_state(inode, EXT4_STATE_DA_ALLOC_CLOSE);
}
/* if we are the last writer on the inode, drop the block reservation */
if ((filp->f_mode & FMODE_WRITE) &&
(atomic_read(&inode->i_writecount) == 1) &&
!EXT4_I(inode)->i_reserved_data_blocks)
{
down_write(&EXT4_I(inode)->i_data_sem);
ext4_discard_preallocations(inode);
up_write(&EXT4_I(inode)->i_data_sem);
}
if (is_dx(inode) && filp->private_data)
ext4_htree_free_dir_info(filp->private_data);
return 0;
}
static void ext4_unwritten_wait(struct inode *inode)
{
wait_queue_head_t *wq = ext4_ioend_wq(inode);
wait_event(*wq, (atomic_read(&EXT4_I(inode)->i_unwritten) == 0));
}
/*
* This tests whether the IO in question is block-aligned or not.
* Ext4 utilizes unwritten extents when hole-filling during direct IO, and they
* are converted to written only after the IO is complete. Until they are
* mapped, these blocks appear as holes, so dio_zero_block() will assume that
* it needs to zero out portions of the start and/or end block. If 2 AIO
* threads are at work on the same unwritten block, they must be synchronized
* or one thread will zero the other's data, causing corruption.
*/
static int
ext4_unaligned_aio(struct inode *inode, struct iov_iter *from, loff_t pos)
{
struct super_block *sb = inode->i_sb;
int blockmask = sb->s_blocksize - 1;
if (pos >= i_size_read(inode))
return 0;
if ((pos | iov_iter_alignment(from)) & blockmask)
return 1;
return 0;
}
/* Is IO overwriting allocated and initialized blocks? */
static bool ext4_overwrite_io(struct inode *inode, loff_t pos, loff_t len)
{
struct ext4_map_blocks map;
unsigned int blkbits = inode->i_blkbits;
int err, blklen;
if (pos + len > i_size_read(inode))
return false;
map.m_lblk = pos >> blkbits;
map.m_len = EXT4_MAX_BLOCKS(len, pos, blkbits);
blklen = map.m_len;
err = ext4_map_blocks(NULL, inode, &map, 0);
/*
* 'err==len' means that all of the blocks have been preallocated,
* regardless of whether they have been initialized or not. To exclude
* unwritten extents, we need to check m_flags.
*/
return err == blklen && (map.m_flags & EXT4_MAP_MAPPED);
}
static ssize_t ext4_write_checks(struct kiocb *iocb, struct iov_iter *from)
{
struct inode *inode = file_inode(iocb->ki_filp);
ssize_t ret;
ret = generic_write_checks(iocb, from);
if (ret <= 0)
return ret;
/*
* If we have encountered a bitmap-format file, the size limit
* is smaller than s_maxbytes, which is for extent-mapped files.
*/
if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))) {
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
if (iocb->ki_pos >= sbi->s_bitmap_maxbytes)
return -EFBIG;
iov_iter_truncate(from, sbi->s_bitmap_maxbytes - iocb->ki_pos);
}
return iov_iter_count(from);
}
#ifdef CONFIG_FS_DAX
static ssize_t
ext4_dax_write_iter(struct kiocb *iocb, struct iov_iter *from)
{
struct inode *inode = file_inode(iocb->ki_filp);
ssize_t ret;
if (!inode_trylock(inode)) {
if (iocb->ki_flags & IOCB_NOWAIT)
return -EAGAIN;
inode_lock(inode);
}
ret = ext4_write_checks(iocb, from);
if (ret <= 0)
goto out;
ret = file_remove_privs(iocb->ki_filp);
if (ret)
goto out;
ret = file_update_time(iocb->ki_filp);
if (ret)
goto out;
ret = dax_iomap_rw(iocb, from, &ext4_iomap_ops);
out:
inode_unlock(inode);
if (ret > 0)
ret = generic_write_sync(iocb, ret);
return ret;
}
#endif
static ssize_t
ext4_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
{
struct inode *inode = file_inode(iocb->ki_filp);
int o_direct = iocb->ki_flags & IOCB_DIRECT;
int unaligned_aio = 0;
int overwrite = 0;
ssize_t ret;
if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb))))
return -EIO;
#ifdef CONFIG_FS_DAX
if (IS_DAX(inode))
return ext4_dax_write_iter(iocb, from);
#endif
if (!o_direct && (iocb->ki_flags & IOCB_NOWAIT))
return -EOPNOTSUPP;
if (!inode_trylock(inode)) {
if (iocb->ki_flags & IOCB_NOWAIT)
return -EAGAIN;
inode_lock(inode);
}
ret = ext4_write_checks(iocb, from);
if (ret <= 0)
goto out;
/*
* Unaligned direct AIO must be serialized among each other as zeroing
* of partial blocks of two competing unaligned AIOs can result in data
* corruption.
*/
if (o_direct && ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS) &&
!is_sync_kiocb(iocb) &&
ext4_unaligned_aio(inode, from, iocb->ki_pos)) {
unaligned_aio = 1;
ext4_unwritten_wait(inode);
}
iocb->private = &overwrite;
/* Check whether we do a DIO overwrite or not */
if (o_direct && !unaligned_aio) {
if (ext4_overwrite_io(inode, iocb->ki_pos, iov_iter_count(from))) {
if (ext4_should_dioread_nolock(inode))
overwrite = 1;
} else if (iocb->ki_flags & IOCB_NOWAIT) {
ret = -EAGAIN;
goto out;
}
}
ret = __generic_file_write_iter(iocb, from);
inode_unlock(inode);
if (ret > 0)
ret = generic_write_sync(iocb, ret);
return ret;
out:
inode_unlock(inode);
return ret;
}
#ifdef CONFIG_FS_DAX
static int ext4_dax_huge_fault(struct vm_fault *vmf,
enum page_entry_size pe_size)
{
int result;
handle_t *handle = NULL;
struct inode *inode = file_inode(vmf->vma->vm_file);
struct super_block *sb = inode->i_sb;
/*
* We have to distinguish real writes from writes which will result in a
* COW page; COW writes should *not* poke the journal (the file will not
* be changed). Doing so would cause unintended failures when mounted
* read-only.
*
* We check for VM_SHARED rather than vmf->cow_page since the latter is
* unset for pe_size != PE_SIZE_PTE (i.e. only in do_cow_fault); for
* other sizes, dax_iomap_fault will handle splitting / fallback so that
* we eventually come back with a COW page.
*/
bool write = (vmf->flags & FAULT_FLAG_WRITE) &&
(vmf->vma->vm_flags & VM_SHARED);
pfn_t pfn;
if (write) {
sb_start_pagefault(sb);
file_update_time(vmf->vma->vm_file);
down_read(&EXT4_I(inode)->i_mmap_sem);
handle = ext4_journal_start_sb(sb, EXT4_HT_WRITE_PAGE,
EXT4_DATA_TRANS_BLOCKS(sb));
if (IS_ERR(handle)) {
up_read(&EXT4_I(inode)->i_mmap_sem);
sb_end_pagefault(sb);
return VM_FAULT_SIGBUS;
}
} else {
down_read(&EXT4_I(inode)->i_mmap_sem);
}
result = dax_iomap_fault(vmf, pe_size, &pfn, &ext4_iomap_ops);
if (write) {
ext4_journal_stop(handle);
/* Handling synchronous page fault? */
if (result & VM_FAULT_NEEDDSYNC)
result = dax_finish_sync_fault(vmf, pe_size, pfn);
up_read(&EXT4_I(inode)->i_mmap_sem);
sb_end_pagefault(sb);
} else {
up_read(&EXT4_I(inode)->i_mmap_sem);
}
return result;
}
static int ext4_dax_fault(struct vm_fault *vmf)
{
return ext4_dax_huge_fault(vmf, PE_SIZE_PTE);
}
static const struct vm_operations_struct ext4_dax_vm_ops = {
.fault = ext4_dax_fault,
.huge_fault = ext4_dax_huge_fault,
.page_mkwrite = ext4_dax_fault,
.pfn_mkwrite = ext4_dax_fault,
};
#else
#define ext4_dax_vm_ops ext4_file_vm_ops
#endif
static const struct vm_operations_struct ext4_file_vm_ops = {
.fault = ext4_filemap_fault,
.map_pages = filemap_map_pages,
.page_mkwrite = ext4_page_mkwrite,
};
static int ext4_file_mmap(struct file *file, struct vm_area_struct *vma)
{
struct inode *inode = file->f_mapping->host;
if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb))))
return -EIO;
/*
* 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(file)) && (vma->vm_flags & VM_SYNC))
return -EOPNOTSUPP;
file_accessed(file);
if (IS_DAX(file_inode(file))) {
vma->vm_ops = &ext4_dax_vm_ops;
vma->vm_flags |= VM_MIXEDMAP | VM_HUGEPAGE;
} else {
vma->vm_ops = &ext4_file_vm_ops;
}
return 0;
}
static int ext4_file_open(struct inode * inode, struct file * filp)
{
struct super_block *sb = inode->i_sb;
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
struct vfsmount *mnt = filp->f_path.mnt;
struct path path;
char buf[64], *cp;
int ret;
if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb))))
return -EIO;
if (unlikely(!(sbi->s_mount_flags & EXT4_MF_MNTDIR_SAMPLED) &&
!sb_rdonly(sb))) {
sbi->s_mount_flags |= EXT4_MF_MNTDIR_SAMPLED;
/*
* Sample where the filesystem has been mounted and
* store it in the superblock for sysadmin convenience
* when trying to sort through large numbers of block
* devices or filesystem images.
*/
memset(buf, 0, sizeof(buf));
path.mnt = mnt;
path.dentry = mnt->mnt_root;
cp = d_path(&path, buf, sizeof(buf));
if (!IS_ERR(cp)) {
handle_t *handle;
int err;
handle = ext4_journal_start_sb(sb, EXT4_HT_MISC, 1);
if (IS_ERR(handle))
return PTR_ERR(handle);
BUFFER_TRACE(sbi->s_sbh, "get_write_access");
err = ext4_journal_get_write_access(handle, sbi->s_sbh);
if (err) {
ext4_journal_stop(handle);
return err;
}
strlcpy(sbi->s_es->s_last_mounted, cp,
sizeof(sbi->s_es->s_last_mounted));
ext4_handle_dirty_super(handle, sb);
ext4_journal_stop(handle);
}
}
ret = fscrypt_file_open(inode, filp);
if (ret)
return ret;
/*
* Set up the jbd2_inode if we are opening the inode for
* writing and the journal is present
*/
if (filp->f_mode & FMODE_WRITE) {
ret = ext4_inode_attach_jinode(inode);
if (ret < 0)
return ret;
}
filp->f_mode |= FMODE_NOWAIT;
return dquot_file_open(inode, filp);
}
/*
* ext4_llseek() handles both block-mapped and extent-mapped maxbytes values
* by calling generic_file_llseek_size() with the appropriate maxbytes
* value for each.
*/
loff_t ext4_llseek(struct file *file, loff_t offset, int whence)
{
struct inode *inode = file->f_mapping->host;
loff_t maxbytes;
if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)))
maxbytes = EXT4_SB(inode->i_sb)->s_bitmap_maxbytes;
else
maxbytes = inode->i_sb->s_maxbytes;
switch (whence) {
default:
return generic_file_llseek_size(file, offset, whence,
maxbytes, i_size_read(inode));
case SEEK_HOLE:
inode_lock_shared(inode);
offset = iomap_seek_hole(inode, offset, &ext4_iomap_ops);
inode_unlock_shared(inode);
break;
case SEEK_DATA:
inode_lock_shared(inode);
offset = iomap_seek_data(inode, offset, &ext4_iomap_ops);
inode_unlock_shared(inode);
break;
}
if (offset < 0)
return offset;
return vfs_setpos(file, offset, maxbytes);
}
const struct file_operations ext4_file_operations = {
.llseek = ext4_llseek,
.read_iter = ext4_file_read_iter,
.write_iter = ext4_file_write_iter,
.unlocked_ioctl = ext4_ioctl,
#ifdef CONFIG_COMPAT
.compat_ioctl = ext4_compat_ioctl,
#endif
.mmap = ext4_file_mmap,
.mmap_supported_flags = MAP_SYNC,
.open = ext4_file_open,
.release = ext4_release_file,
.fsync = ext4_sync_file,
.get_unmapped_area = thp_get_unmapped_area,
.splice_read = generic_file_splice_read,
.splice_write = iter_file_splice_write,
.fallocate = ext4_fallocate,
};
const struct inode_operations ext4_file_inode_operations = {
.setattr = ext4_setattr,
.getattr = ext4_file_getattr,
.listxattr = ext4_listxattr,
.get_acl = ext4_get_acl,
.set_acl = ext4_set_acl,
.fiemap = ext4_fiemap,
};