![Linus Torvalds](/assets/img/avatar_default.png)
greatest note is a speed up for parallel, non-allocating DIO writes, since we no longer take the i_mutex lock in that case. For bug fixes, we fix an incorrect overhead calculation which caused slightly incorrect results for df(1) and statfs(2). We also fixed bugs in the metadata checksum feature. -----BEGIN PGP SIGNATURE----- Version: GnuPG v1.4.12 (GNU/Linux) iQIcBAABCAAGBQJQE1SzAAoJENNvdpvBGATwzOMQAKxVkaTqkMc+cUahLLUkFdGQ xnmigHufVuOvv+B8l1p6vbYx+qOftztqXF1WC41j8mTfEDs19jKXv3LI57TJ+bIW a/Kp1CjMicRs/HGhFPNWp1D+N8J95MTFP6Y9biXSmBBvefg2NSwxpg48yZtjUy1/ Zl0414AqMvTJyqKKOUa++oyl3XlawnzDZ+6a7QPKsrAaDOU5977W4y2tZkNFk84d qRjTfaiX13aVe7XupgQHe/jtk40Sj38pyGVGiAGlHOZhZtYKE6MzB8OreGiMTy8z rmJz/CQUsQ8+sbKYhAcDru+bMrKghbO0u78XRz9CY+YpVFF/Xs2QiXoV0ZOGkIm6 eokq7jEV0K+LtDEmM3PkmUPgXfYw5damTv8qWuBUFd4wtVE5x/DmK8AJVMidCAUN GkVR+rEbbEi7RCwsuac/aKB8baVQCTiJ5tfNTgWh9zll+9GZSk+U71Pp0KdcJGiS nxitAZ+20hZN2CQctlmaGbCPTPYCWU4hQ3IuMdTlQTQAs8S0y1FtylTRsXcC1eVR i1hBS/dVw5PVCaqoX79zYrByUymgX0ZaYY6seRT6+U9xPGDCSNJ9mjXZL3fttnOC d5gsx/pbMIAv52G5Hj6DfsXR2JFmmxsaIzsLtRvKi9q89d84XaZfbUsHYjn4Neym 5lTKaSQHU71cKCxrStHC =VAVB -----END PGP SIGNATURE----- Merge tag 'ext4_for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4 Pull ext4 updates from Ted Ts'o: "The usual collection of bug fixes and optimizations. Perhaps of greatest note is a speed up for parallel, non-allocating DIO writes, since we no longer take the i_mutex lock in that case. For bug fixes, we fix an incorrect overhead calculation which caused slightly incorrect results for df(1) and statfs(2). We also fixed bugs in the metadata checksum feature." * tag 'ext4_for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4: (23 commits) ext4: undo ext4_calc_metadata_amount if we fail to claim space ext4: don't let i_reserved_meta_blocks go negative ext4: fix hole punch failure when depth is greater than 0 ext4: remove unnecessary argument from __ext4_handle_dirty_metadata() ext4: weed out ext4_write_super ext4: remove unnecessary superblock dirtying ext4: convert last user of ext4_mark_super_dirty() to ext4_handle_dirty_super() ext4: remove useless marking of superblock dirty ext4: fix ext4 mismerge back in January ext4: remove dynamic array size in ext4_chksum() ext4: remove unused variable in ext4_update_super() ext4: make quota as first class supported feature ext4: don't take the i_mutex lock when doing DIO overwrites ext4: add a new nolock flag in ext4_map_blocks ext4: split ext4_file_write into buffered IO and direct IO ext4: remove an unused statement in ext4_mb_get_buddy_page_lock() ext4: fix out-of-date comments in extents.c ext4: use s_csum_seed instead of i_csum_seed for xattr block ext4: use proper csum calculation in ext4_rename ext4: fix overhead calculation used by ext4_statfs() ...
339 lines
9.3 KiB
C
339 lines
9.3 KiB
C
/*
|
|
* 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/jbd2.h>
|
|
#include <linux/mount.h>
|
|
#include <linux/path.h>
|
|
#include <linux/quotaops.h>
|
|
#include "ext4.h"
|
|
#include "ext4_jbd2.h"
|
|
#include "xattr.h"
|
|
#include "acl.h"
|
|
|
|
/*
|
|
* 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_aiodio_wait(struct inode *inode)
|
|
{
|
|
wait_queue_head_t *wq = ext4_ioend_wq(inode);
|
|
|
|
wait_event(*wq, (atomic_read(&EXT4_I(inode)->i_aiodio_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, const struct iovec *iov,
|
|
unsigned long nr_segs, loff_t pos)
|
|
{
|
|
struct super_block *sb = inode->i_sb;
|
|
int blockmask = sb->s_blocksize - 1;
|
|
size_t count = iov_length(iov, nr_segs);
|
|
loff_t final_size = pos + count;
|
|
|
|
if (pos >= inode->i_size)
|
|
return 0;
|
|
|
|
if ((pos & blockmask) || (final_size & blockmask))
|
|
return 1;
|
|
|
|
return 0;
|
|
}
|
|
|
|
static ssize_t
|
|
ext4_file_dio_write(struct kiocb *iocb, const struct iovec *iov,
|
|
unsigned long nr_segs, loff_t pos)
|
|
{
|
|
struct file *file = iocb->ki_filp;
|
|
struct inode *inode = file->f_mapping->host;
|
|
struct blk_plug plug;
|
|
int unaligned_aio = 0;
|
|
ssize_t ret;
|
|
int overwrite = 0;
|
|
size_t length = iov_length(iov, nr_segs);
|
|
|
|
if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS) &&
|
|
!is_sync_kiocb(iocb))
|
|
unaligned_aio = ext4_unaligned_aio(inode, iov, nr_segs, pos);
|
|
|
|
/* Unaligned direct AIO must be serialized; see comment above */
|
|
if (unaligned_aio) {
|
|
static unsigned long unaligned_warn_time;
|
|
|
|
/* Warn about this once per day */
|
|
if (printk_timed_ratelimit(&unaligned_warn_time, 60*60*24*HZ))
|
|
ext4_msg(inode->i_sb, KERN_WARNING,
|
|
"Unaligned AIO/DIO on inode %ld by %s; "
|
|
"performance will be poor.",
|
|
inode->i_ino, current->comm);
|
|
mutex_lock(ext4_aio_mutex(inode));
|
|
ext4_aiodio_wait(inode);
|
|
}
|
|
|
|
BUG_ON(iocb->ki_pos != pos);
|
|
|
|
mutex_lock(&inode->i_mutex);
|
|
blk_start_plug(&plug);
|
|
|
|
iocb->private = &overwrite;
|
|
|
|
/* check whether we do a DIO overwrite or not */
|
|
if (ext4_should_dioread_nolock(inode) && !unaligned_aio &&
|
|
!file->f_mapping->nrpages && pos + length <= i_size_read(inode)) {
|
|
struct ext4_map_blocks map;
|
|
unsigned int blkbits = inode->i_blkbits;
|
|
int err, len;
|
|
|
|
map.m_lblk = pos >> blkbits;
|
|
map.m_len = (EXT4_BLOCK_ALIGN(pos + length, blkbits) >> blkbits)
|
|
- map.m_lblk;
|
|
len = map.m_len;
|
|
|
|
err = ext4_map_blocks(NULL, inode, &map, 0);
|
|
/*
|
|
* 'err==len' means that all of blocks has been preallocated no
|
|
* matter they are initialized or not. For excluding
|
|
* uninitialized extents, we need to check m_flags. There are
|
|
* two conditions that indicate for initialized extents.
|
|
* 1) If we hit extent cache, EXT4_MAP_MAPPED flag is returned;
|
|
* 2) If we do a real lookup, non-flags are returned.
|
|
* So we should check these two conditions.
|
|
*/
|
|
if (err == len && (map.m_flags & EXT4_MAP_MAPPED))
|
|
overwrite = 1;
|
|
}
|
|
|
|
ret = __generic_file_aio_write(iocb, iov, nr_segs, &iocb->ki_pos);
|
|
mutex_unlock(&inode->i_mutex);
|
|
|
|
if (ret > 0 || ret == -EIOCBQUEUED) {
|
|
ssize_t err;
|
|
|
|
err = generic_write_sync(file, pos, ret);
|
|
if (err < 0 && ret > 0)
|
|
ret = err;
|
|
}
|
|
blk_finish_plug(&plug);
|
|
|
|
if (unaligned_aio)
|
|
mutex_unlock(ext4_aio_mutex(inode));
|
|
|
|
return ret;
|
|
}
|
|
|
|
static ssize_t
|
|
ext4_file_write(struct kiocb *iocb, const struct iovec *iov,
|
|
unsigned long nr_segs, loff_t pos)
|
|
{
|
|
struct inode *inode = iocb->ki_filp->f_path.dentry->d_inode;
|
|
ssize_t 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);
|
|
size_t length = iov_length(iov, nr_segs);
|
|
|
|
if ((pos > sbi->s_bitmap_maxbytes ||
|
|
(pos == sbi->s_bitmap_maxbytes && length > 0)))
|
|
return -EFBIG;
|
|
|
|
if (pos + length > sbi->s_bitmap_maxbytes) {
|
|
nr_segs = iov_shorten((struct iovec *)iov, nr_segs,
|
|
sbi->s_bitmap_maxbytes - pos);
|
|
}
|
|
}
|
|
|
|
if (unlikely(iocb->ki_filp->f_flags & O_DIRECT))
|
|
ret = ext4_file_dio_write(iocb, iov, nr_segs, pos);
|
|
else
|
|
ret = generic_file_aio_write(iocb, iov, nr_segs, pos);
|
|
|
|
return ret;
|
|
}
|
|
|
|
static const struct vm_operations_struct ext4_file_vm_ops = {
|
|
.fault = filemap_fault,
|
|
.page_mkwrite = ext4_page_mkwrite,
|
|
};
|
|
|
|
static int ext4_file_mmap(struct file *file, struct vm_area_struct *vma)
|
|
{
|
|
struct address_space *mapping = file->f_mapping;
|
|
|
|
if (!mapping->a_ops->readpage)
|
|
return -ENOEXEC;
|
|
file_accessed(file);
|
|
vma->vm_ops = &ext4_file_vm_ops;
|
|
vma->vm_flags |= VM_CAN_NONLINEAR;
|
|
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 ext4_inode_info *ei = EXT4_I(inode);
|
|
struct vfsmount *mnt = filp->f_path.mnt;
|
|
struct path path;
|
|
char buf[64], *cp;
|
|
|
|
if (unlikely(!(sbi->s_mount_flags & EXT4_MF_MNTDIR_SAMPLED) &&
|
|
!(sb->s_flags & MS_RDONLY))) {
|
|
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, 1);
|
|
if (IS_ERR(handle))
|
|
return PTR_ERR(handle);
|
|
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);
|
|
}
|
|
}
|
|
/*
|
|
* Set up the jbd2_inode if we are opening the inode for
|
|
* writing and the journal is present
|
|
*/
|
|
if (sbi->s_journal && !ei->jinode && (filp->f_mode & FMODE_WRITE)) {
|
|
struct jbd2_inode *jinode = jbd2_alloc_inode(GFP_KERNEL);
|
|
|
|
spin_lock(&inode->i_lock);
|
|
if (!ei->jinode) {
|
|
if (!jinode) {
|
|
spin_unlock(&inode->i_lock);
|
|
return -ENOMEM;
|
|
}
|
|
ei->jinode = jinode;
|
|
jbd2_journal_init_jbd_inode(ei->jinode, inode);
|
|
jinode = NULL;
|
|
}
|
|
spin_unlock(&inode->i_lock);
|
|
if (unlikely(jinode != NULL))
|
|
jbd2_free_inode(jinode);
|
|
}
|
|
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 origin)
|
|
{
|
|
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;
|
|
|
|
return generic_file_llseek_size(file, offset, origin,
|
|
maxbytes, i_size_read(inode));
|
|
}
|
|
|
|
const struct file_operations ext4_file_operations = {
|
|
.llseek = ext4_llseek,
|
|
.read = do_sync_read,
|
|
.write = do_sync_write,
|
|
.aio_read = generic_file_aio_read,
|
|
.aio_write = ext4_file_write,
|
|
.unlocked_ioctl = ext4_ioctl,
|
|
#ifdef CONFIG_COMPAT
|
|
.compat_ioctl = ext4_compat_ioctl,
|
|
#endif
|
|
.mmap = ext4_file_mmap,
|
|
.open = ext4_file_open,
|
|
.release = ext4_release_file,
|
|
.fsync = ext4_sync_file,
|
|
.splice_read = generic_file_splice_read,
|
|
.splice_write = generic_file_splice_write,
|
|
.fallocate = ext4_fallocate,
|
|
};
|
|
|
|
const struct inode_operations ext4_file_inode_operations = {
|
|
.setattr = ext4_setattr,
|
|
.getattr = ext4_getattr,
|
|
#ifdef CONFIG_EXT4_FS_XATTR
|
|
.setxattr = generic_setxattr,
|
|
.getxattr = generic_getxattr,
|
|
.listxattr = ext4_listxattr,
|
|
.removexattr = generic_removexattr,
|
|
#endif
|
|
.get_acl = ext4_get_acl,
|
|
.fiemap = ext4_fiemap,
|
|
};
|
|
|