the buffer cache. The default value is 32 blocks.
nouser_xattr Disables Extended User Attributes. See the
- attr(5) manual page and http://acl.bestbits.at/
- for more information about extended attributes.
+ attr(5) manual page for more information about
+ extended attributes.
noacl This option disables POSIX Access Control List
support. If ACL support is enabled in the kernel
configuration (CONFIG_EXT4_FS_POSIX_ACL), ACL is
enabled by default on mount. See the acl(5) manual
- page and http://acl.bestbits.at/ for more information
- about acl.
+ page for more information about acl.
bsddf (*) Make 'df' act like BSD.
minixdf Make 'df' act like Minix.
data_err=abort Abort the journal if an error occurs in a file
data buffer in ordered mode.
- grpid Give objects the same group ID as their creator.
+ grpid New objects have the group ID of their parent.
bsdgroups
nogrpid (*) New objects have the group ID of their creator.
/* The 'colour' (ie low bits) within a PMD of a page offset. */
#define PG_PMD_COLOUR ((PMD_SIZE >> PAGE_SHIFT) - 1)
+#define PG_PMD_NR (PMD_SIZE >> PAGE_SHIFT)
static wait_queue_head_t wait_table[DAX_WAIT_TABLE_ENTRIES];
* unmapped.
*/
if (pmd_downgrade && dax_is_zero_entry(entry))
- unmap_mapping_range(mapping,
- (index << PAGE_SHIFT) & PMD_MASK, PMD_SIZE, 0);
+ unmap_mapping_pages(mapping, index & ~PG_PMD_COLOUR,
+ PG_PMD_NR, false);
err = radix_tree_preload(
mapping_gfp_mask(mapping) & ~__GFP_HIGHMEM);
if (dax_is_zero_entry(entry) && !(flags & RADIX_DAX_ZERO_PAGE)) {
/* we are replacing a zero page with block mapping */
if (dax_is_pmd_entry(entry))
- unmap_mapping_range(mapping,
- (vmf->pgoff << PAGE_SHIFT) & PMD_MASK,
- PMD_SIZE, 0);
+ unmap_mapping_pages(mapping, index & ~PG_PMD_COLOUR,
+ PG_PMD_NR, false);
else /* pte entry */
- unmap_mapping_range(mapping, vmf->pgoff << PAGE_SHIFT,
- PAGE_SIZE, 0);
+ unmap_mapping_pages(mapping, vmf->pgoff, 1, false);
}
spin_lock_irq(&mapping->tree_lock);
pmd = pmd_mkclean(pmd);
set_pmd_at(vma->vm_mm, address, pmdp, pmd);
unlock_pmd:
- spin_unlock(ptl);
#endif
+ spin_unlock(ptl);
} else {
if (pfn != pte_pfn(*ptep))
goto unlock_pte;
}
static int dax_iomap_pte_fault(struct vm_fault *vmf, pfn_t *pfnp,
- const struct iomap_ops *ops)
+ int *iomap_errp, const struct iomap_ops *ops)
{
struct vm_area_struct *vma = vmf->vma;
struct address_space *mapping = vma->vm_file->f_mapping;
* that we never have to deal with more than a single extent here.
*/
error = ops->iomap_begin(inode, pos, PAGE_SIZE, flags, &iomap);
+ if (iomap_errp)
+ *iomap_errp = error;
if (error) {
vmf_ret = dax_fault_return(error);
goto unlock_entry;
}
#ifdef CONFIG_FS_DAX_PMD
-/*
- * The 'colour' (ie low bits) within a PMD of a page offset. This comes up
- * more often than one might expect in the below functions.
- */
-#define PG_PMD_COLOUR ((PMD_SIZE >> PAGE_SHIFT) - 1)
-
static int dax_pmd_load_hole(struct vm_fault *vmf, struct iomap *iomap,
void *entry)
{
* @vmf: The description of the fault
* @pe_size: Size of the page to fault in
* @pfnp: PFN to insert for synchronous faults if fsync is required
+ * @iomap_errp: Storage for detailed error code in case of error
* @ops: Iomap ops passed from the file system
*
* When a page fault occurs, filesystems may call this helper in
* successfully.
*/
int dax_iomap_fault(struct vm_fault *vmf, enum page_entry_size pe_size,
- pfn_t *pfnp, const struct iomap_ops *ops)
+ pfn_t *pfnp, int *iomap_errp, const struct iomap_ops *ops)
{
switch (pe_size) {
case PE_SIZE_PTE:
- return dax_iomap_pte_fault(vmf, pfnp, ops);
+ return dax_iomap_pte_fault(vmf, pfnp, iomap_errp, ops);
case PE_SIZE_PMD:
return dax_iomap_pmd_fault(vmf, pfnp, ops);
default:
+ // SPDX-License-Identifier: LGPL-2.1
/*
* Copyright (c) 2012 Taobao.
* Written by Tao Ma <boyu.mt@taobao.com>
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of version 2.1 of the GNU Lesser General Public License
- * as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
*/
#include <linux/iomap.h>
#include <linux/fiemap.h>
+#include <linux/iversion.h>
#include "ext4_jbd2.h"
#include "ext4.h"
*/
dir->i_mtime = dir->i_ctime = current_time(dir);
ext4_update_dx_flag(dir);
- dir->i_version++;
+ inode_inc_iversion(dir);
return 1;
}
* dirent right now. Scan from the start of the inline
* dir to make sure.
*/
- if (file->f_version != inode->i_version) {
+ if (inode_cmp_iversion(inode, file->f_version)) {
for (i = 0; i < extra_size && i < offset;) {
/*
* "." is with offset 0 and
}
offset = i;
ctx->pos = offset;
- file->f_version = inode->i_version;
+ file->f_version = inode_query_iversion(inode);
}
while (ctx->pos < extra_size) {
#include <linux/slab.h>
#include <linux/bitops.h>
#include <linux/iomap.h>
+#include <linux/iversion.h>
#include "ext4_jbd2.h"
#include "xattr.h"
/* Credits for sb + inode write */
handle = ext4_journal_start(inode, EXT4_HT_INODE, 2);
if (IS_ERR(handle)) {
- /* This is really bad luck. We've written the data
- * but cannot extend i_size. Bail out and pretend
- * the write failed... */
- ret = PTR_ERR(handle);
+ /*
+ * We wrote the data but cannot extend
+ * i_size. Bail out. In async io case, we do
+ * not return error here because we have
+ * already submmitted the corresponding
+ * bio. Returning error here makes the caller
+ * think that this IO is done and failed
+ * resulting in race with bio's completion
+ * handler.
+ */
+ if (!ret)
+ ret = PTR_ERR(handle);
if (inode->i_nlink)
ext4_orphan_del(NULL, inode);
EXT4_EINODE_GET_XTIME(i_crtime, ei, raw_inode);
if (likely(!test_opt2(inode->i_sb, HURD_COMPAT))) {
- inode->i_version = le32_to_cpu(raw_inode->i_disk_version);
+ u64 ivers = le32_to_cpu(raw_inode->i_disk_version);
+
if (EXT4_INODE_SIZE(inode->i_sb) > EXT4_GOOD_OLD_INODE_SIZE) {
if (EXT4_FITS_IN_INODE(raw_inode, ei, i_version_hi))
- inode->i_version |=
+ ivers |=
(__u64)(le32_to_cpu(raw_inode->i_version_hi)) << 32;
}
+ inode_set_iversion_queried(inode, ivers);
}
ret = 0;
}
if (likely(!test_opt2(inode->i_sb, HURD_COMPAT))) {
- raw_inode->i_disk_version = cpu_to_le32(inode->i_version);
+ u64 ivers = inode_peek_iversion(inode);
+
+ raw_inode->i_disk_version = cpu_to_le32(ivers);
if (ei->i_extra_isize) {
if (EXT4_FITS_IN_INODE(raw_inode, ei, i_version_hi))
raw_inode->i_version_hi =
- cpu_to_le32(inode->i_version >> 32);
+ cpu_to_le32(ivers >> 32);
raw_inode->i_extra_isize =
cpu_to_le16(ei->i_extra_isize);
}
#include <linux/quotaops.h>
#include <linux/buffer_head.h>
#include <linux/bio.h>
+#include <linux/iversion.h>
#include "ext4.h"
#include "ext4_jbd2.h"
"empty directory '%.*s' has too many links (%u)",
dentry->d_name.len, dentry->d_name.name,
inode->i_nlink);
- inode->i_version++;
+ inode_inc_iversion(inode);
clear_nlink(inode);
/* There's no need to set i_disksize: the fact that i_nlink is
* zero will ensure that the right thing happens during any
if (err)
return err;
- if ((ext4_test_inode_flag(dir, EXT4_INODE_PROJINHERIT)) &&
- (!projid_eq(EXT4_I(dir)->i_projid,
- EXT4_I(old_dentry->d_inode)->i_projid)))
+ if ((ext4_test_inode_flag(dir, EXT4_INODE_PROJINHERIT)) &&
+ (!projid_eq(EXT4_I(dir)->i_projid,
+ EXT4_I(old_dentry->d_inode)->i_projid)))
return -EXDEV;
err = dquot_initialize(dir);
ent->de->inode = cpu_to_le32(ino);
if (ext4_has_feature_filetype(ent->dir->i_sb))
ent->de->file_type = file_type;
- ent->dir->i_version++;
+ inode_inc_iversion(ent->dir);
ent->dir->i_ctime = ent->dir->i_mtime =
current_time(ent->dir);
ext4_mark_inode_dirty(handle, ent->dir);
+ // SPDX-License-Identifier: GPL-2.0
/*
* linux/fs/ext4/super.c
*
#include <linux/dax.h>
#include <linux/cleancache.h>
#include <linux/uaccess.h>
+#include <linux/iversion.h>
#include <linux/kthread.h>
#include <linux/freezer.h>
}
ext4_unlock_group(sb, grp);
+ ext4_commit_super(sb, 1);
ext4_handle_error(sb);
/*
* We only get here in the ERRORS_RO case; relocking the group
ext4_unregister_li_request(sb);
ext4_quota_off_umount(sb);
- flush_workqueue(sbi->rsv_conversion_wq);
destroy_workqueue(sbi->rsv_conversion_wq);
if (sbi->s_journal) {
if (!ei)
return NULL;
- ei->vfs_inode.i_version = 1;
+ inode_set_iversion(&ei->vfs_inode, 1);
spin_lock_init(&ei->i_raw_lock);
INIT_LIST_HEAD(&ei->i_prealloc_list);
spin_lock_init(&ei->i_prealloc_lock);
* compensate.
*/
if (sb->s_blocksize == 1024 && nr == 0 &&
- le32_to_cpu(EXT4_SB(sb)->s_es->s_first_data_block) == 0)
+ le32_to_cpu(sbi->s_es->s_first_data_block) == 0)
has_super++;
return (has_super + ext4_group_first_block_no(sb, bg));
{
struct ext4_sb_info *sbi = EXT4_SB(sb);
struct ext4_li_request *elr = NULL;
- ext4_group_t ngroups = EXT4_SB(sb)->s_groups_count;
+ ext4_group_t ngroups = sbi->s_groups_count;
int ret = 0;
mutex_lock(&ext4_li_mtx);
bool needs_barrier = false;
struct ext4_sb_info *sbi = EXT4_SB(sb);
- if (unlikely(ext4_forced_shutdown(EXT4_SB(sb))))
+ if (unlikely(ext4_forced_shutdown(sbi)))
return 0;
trace_ext4_sync_fs(sb, wait);