mirror of
https://github.com/edk2-porting/linux-next.git
synced 2024-12-22 04:03:58 +08:00
a41537e69b
O_DIRECT flags can be toggeled via fcntl(F_SETFL). But this value checked twice inside ext4_file_write_iter() and __generic_file_write() which result in BUG_ON inside ext4_direct_IO. Let's initialize iocb->private unconditionally. TESTCASE: xfstest:generic/036 https://patchwork.ozlabs.org/patch/402445/ #TYPICAL STACK TRACE: kernel BUG at fs/ext4/inode.c:2960! invalid opcode: 0000 [#1] SMP Modules linked in: brd iTCO_wdt lpc_ich mfd_core igb ptp dm_mirror dm_region_hash dm_log dm_mod CPU: 6 PID: 5505 Comm: aio-dio-fcntl-r Not tainted 3.17.0-rc2-00176-gff5c017 #161 Hardware name: Intel Corporation W2600CR/W2600CR, BIOS SE5C600.86B.99.99.x028.061320111235 06/13/2011 task: ffff88080e95a7c0 ti: ffff88080f908000 task.ti: ffff88080f908000 RIP: 0010:[<ffffffff811fabf2>] [<ffffffff811fabf2>] ext4_direct_IO+0x162/0x3d0 RSP: 0018:ffff88080f90bb58 EFLAGS: 00010246 RAX: 0000000000000400 RBX: ffff88080fdb2a28 RCX: 00000000a802c818 RDX: 0000040000080000 RSI: ffff88080d8aeb80 RDI: 0000000000000001 RBP: ffff88080f90bbc8 R08: 0000000000000000 R09: 0000000000001581 R10: 0000000000000000 R11: 0000000000000000 R12: ffff88080d8aeb80 R13: ffff88080f90bbf8 R14: ffff88080fdb28c8 R15: ffff88080fdb2a28 FS: 00007f23b2055700(0000) GS:ffff880818400000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007f23b2045000 CR3: 000000080cedf000 CR4: 00000000000407e0 Stack: ffff88080f90bb98 0000000000000000 7ffffffffffffffe ffff88080fdb2c30 0000000000000200 0000000000000200 0000000000000001 0000000000000200 ffff88080f90bbc8 ffff88080fdb2c30 ffff88080f90be08 0000000000000200 Call Trace: [<ffffffff8112ca9d>] generic_file_direct_write+0xed/0x180 [<ffffffff8112f2b2>] __generic_file_write_iter+0x222/0x370 [<ffffffff811f495b>] ext4_file_write_iter+0x34b/0x400 [<ffffffff811bd709>] ? aio_run_iocb+0x239/0x410 [<ffffffff811bd709>] ? aio_run_iocb+0x239/0x410 [<ffffffff810990e5>] ? local_clock+0x25/0x30 [<ffffffff810abd94>] ? __lock_acquire+0x274/0x700 [<ffffffff811f4610>] ? ext4_unwritten_wait+0xb0/0xb0 [<ffffffff811bd756>] aio_run_iocb+0x286/0x410 [<ffffffff810990e5>] ? local_clock+0x25/0x30 [<ffffffff810ac359>] ? lock_release_holdtime+0x29/0x190 [<ffffffff811bc05b>] ? lookup_ioctx+0x4b/0xf0 [<ffffffff811bde3b>] do_io_submit+0x55b/0x740 [<ffffffff811bdcaa>] ? do_io_submit+0x3ca/0x740 [<ffffffff811be030>] SyS_io_submit+0x10/0x20 [<ffffffff815ce192>] system_call_fastpath+0x16/0x1b Code: 01 48 8b 80 f0 01 00 00 48 8b 18 49 8b 45 10 0f 85 f1 01 00 00 48 03 45 c8 48 3b 43 48 0f 8f e3 01 00 00 49 83 7c 24 18 00 75 04 <0f> 0b eb fe f0 ff 83 ec 01 00 00 49 8b 44 24 18 8b 00 85 c0 89 RIP [<ffffffff811fabf2>] ext4_direct_IO+0x162/0x3d0 RSP <ffff88080f90bb58> Reported-by: Sasha Levin <sasha.levin@oracle.com> Signed-off-by: Theodore Ts'o <tytso@mit.edu> Signed-off-by: Dmitry Monakhov <dmonakhov@openvz.org> Cc: stable@vger.kernel.org
615 lines
15 KiB
C
615 lines
15 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/aio.h>
|
|
#include <linux/quotaops.h>
|
|
#include <linux/pagevec.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_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;
|
|
}
|
|
|
|
static ssize_t
|
|
ext4_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
|
|
{
|
|
struct file *file = iocb->ki_filp;
|
|
struct inode *inode = file_inode(iocb->ki_filp);
|
|
struct mutex *aio_mutex = NULL;
|
|
struct blk_plug plug;
|
|
int o_direct = file->f_flags & O_DIRECT;
|
|
int overwrite = 0;
|
|
size_t length = iov_iter_count(from);
|
|
ssize_t ret;
|
|
loff_t pos = iocb->ki_pos;
|
|
|
|
/*
|
|
* Unaligned direct AIO must be serialized; see comment above
|
|
* In the case of O_APPEND, assume that we must always serialize
|
|
*/
|
|
if (o_direct &&
|
|
ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS) &&
|
|
!is_sync_kiocb(iocb) &&
|
|
(file->f_flags & O_APPEND ||
|
|
ext4_unaligned_aio(inode, from, pos))) {
|
|
aio_mutex = ext4_aio_mutex(inode);
|
|
mutex_lock(aio_mutex);
|
|
ext4_unwritten_wait(inode);
|
|
}
|
|
|
|
mutex_lock(&inode->i_mutex);
|
|
if (file->f_flags & O_APPEND)
|
|
iocb->ki_pos = pos = i_size_read(inode);
|
|
|
|
/*
|
|
* 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 ((pos > sbi->s_bitmap_maxbytes) ||
|
|
(pos == sbi->s_bitmap_maxbytes && length > 0)) {
|
|
mutex_unlock(&inode->i_mutex);
|
|
ret = -EFBIG;
|
|
goto errout;
|
|
}
|
|
|
|
if (pos + length > sbi->s_bitmap_maxbytes)
|
|
iov_iter_truncate(from, sbi->s_bitmap_maxbytes - pos);
|
|
}
|
|
|
|
iocb->private = &overwrite;
|
|
if (o_direct) {
|
|
blk_start_plug(&plug);
|
|
|
|
|
|
/* check whether we do a DIO overwrite or not */
|
|
if (ext4_should_dioread_nolock(inode) && !aio_mutex &&
|
|
!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
|
|
* unwritten 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_write_iter(iocb, from);
|
|
mutex_unlock(&inode->i_mutex);
|
|
|
|
if (ret > 0) {
|
|
ssize_t err;
|
|
|
|
err = generic_write_sync(file, iocb->ki_pos - ret, ret);
|
|
if (err < 0)
|
|
ret = err;
|
|
}
|
|
if (o_direct)
|
|
blk_finish_plug(&plug);
|
|
|
|
errout:
|
|
if (aio_mutex)
|
|
mutex_unlock(aio_mutex);
|
|
return ret;
|
|
}
|
|
|
|
static const struct vm_operations_struct ext4_file_vm_ops = {
|
|
.fault = filemap_fault,
|
|
.map_pages = filemap_map_pages,
|
|
.page_mkwrite = ext4_page_mkwrite,
|
|
.remap_pages = generic_file_remap_pages,
|
|
};
|
|
|
|
static int ext4_file_mmap(struct file *file, struct vm_area_struct *vma)
|
|
{
|
|
file_accessed(file);
|
|
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;
|
|
|
|
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, 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);
|
|
}
|
|
}
|
|
/*
|
|
* Set up the jbd2_inode if we are opening the inode for
|
|
* writing and the journal is present
|
|
*/
|
|
if (filp->f_mode & FMODE_WRITE) {
|
|
int ret = ext4_inode_attach_jinode(inode);
|
|
if (ret < 0)
|
|
return ret;
|
|
}
|
|
return dquot_file_open(inode, filp);
|
|
}
|
|
|
|
/*
|
|
* Here we use ext4_map_blocks() to get a block mapping for a extent-based
|
|
* file rather than ext4_ext_walk_space() because we can introduce
|
|
* SEEK_DATA/SEEK_HOLE for block-mapped and extent-mapped file at the same
|
|
* function. When extent status tree has been fully implemented, it will
|
|
* track all extent status for a file and we can directly use it to
|
|
* retrieve the offset for SEEK_DATA/SEEK_HOLE.
|
|
*/
|
|
|
|
/*
|
|
* When we retrieve the offset for SEEK_DATA/SEEK_HOLE, we would need to
|
|
* lookup page cache to check whether or not there has some data between
|
|
* [startoff, endoff] because, if this range contains an unwritten extent,
|
|
* we determine this extent as a data or a hole according to whether the
|
|
* page cache has data or not.
|
|
*/
|
|
static int ext4_find_unwritten_pgoff(struct inode *inode,
|
|
int whence,
|
|
struct ext4_map_blocks *map,
|
|
loff_t *offset)
|
|
{
|
|
struct pagevec pvec;
|
|
unsigned int blkbits;
|
|
pgoff_t index;
|
|
pgoff_t end;
|
|
loff_t endoff;
|
|
loff_t startoff;
|
|
loff_t lastoff;
|
|
int found = 0;
|
|
|
|
blkbits = inode->i_sb->s_blocksize_bits;
|
|
startoff = *offset;
|
|
lastoff = startoff;
|
|
endoff = (loff_t)(map->m_lblk + map->m_len) << blkbits;
|
|
|
|
index = startoff >> PAGE_CACHE_SHIFT;
|
|
end = endoff >> PAGE_CACHE_SHIFT;
|
|
|
|
pagevec_init(&pvec, 0);
|
|
do {
|
|
int i, num;
|
|
unsigned long nr_pages;
|
|
|
|
num = min_t(pgoff_t, end - index, PAGEVEC_SIZE);
|
|
nr_pages = pagevec_lookup(&pvec, inode->i_mapping, index,
|
|
(pgoff_t)num);
|
|
if (nr_pages == 0) {
|
|
if (whence == SEEK_DATA)
|
|
break;
|
|
|
|
BUG_ON(whence != SEEK_HOLE);
|
|
/*
|
|
* If this is the first time to go into the loop and
|
|
* offset is not beyond the end offset, it will be a
|
|
* hole at this offset
|
|
*/
|
|
if (lastoff == startoff || lastoff < endoff)
|
|
found = 1;
|
|
break;
|
|
}
|
|
|
|
/*
|
|
* If this is the first time to go into the loop and
|
|
* offset is smaller than the first page offset, it will be a
|
|
* hole at this offset.
|
|
*/
|
|
if (lastoff == startoff && whence == SEEK_HOLE &&
|
|
lastoff < page_offset(pvec.pages[0])) {
|
|
found = 1;
|
|
break;
|
|
}
|
|
|
|
for (i = 0; i < nr_pages; i++) {
|
|
struct page *page = pvec.pages[i];
|
|
struct buffer_head *bh, *head;
|
|
|
|
/*
|
|
* If the current offset is not beyond the end of given
|
|
* range, it will be a hole.
|
|
*/
|
|
if (lastoff < endoff && whence == SEEK_HOLE &&
|
|
page->index > end) {
|
|
found = 1;
|
|
*offset = lastoff;
|
|
goto out;
|
|
}
|
|
|
|
lock_page(page);
|
|
|
|
if (unlikely(page->mapping != inode->i_mapping)) {
|
|
unlock_page(page);
|
|
continue;
|
|
}
|
|
|
|
if (!page_has_buffers(page)) {
|
|
unlock_page(page);
|
|
continue;
|
|
}
|
|
|
|
if (page_has_buffers(page)) {
|
|
lastoff = page_offset(page);
|
|
bh = head = page_buffers(page);
|
|
do {
|
|
if (buffer_uptodate(bh) ||
|
|
buffer_unwritten(bh)) {
|
|
if (whence == SEEK_DATA)
|
|
found = 1;
|
|
} else {
|
|
if (whence == SEEK_HOLE)
|
|
found = 1;
|
|
}
|
|
if (found) {
|
|
*offset = max_t(loff_t,
|
|
startoff, lastoff);
|
|
unlock_page(page);
|
|
goto out;
|
|
}
|
|
lastoff += bh->b_size;
|
|
bh = bh->b_this_page;
|
|
} while (bh != head);
|
|
}
|
|
|
|
lastoff = page_offset(page) + PAGE_SIZE;
|
|
unlock_page(page);
|
|
}
|
|
|
|
/*
|
|
* The no. of pages is less than our desired, that would be a
|
|
* hole in there.
|
|
*/
|
|
if (nr_pages < num && whence == SEEK_HOLE) {
|
|
found = 1;
|
|
*offset = lastoff;
|
|
break;
|
|
}
|
|
|
|
index = pvec.pages[i - 1]->index + 1;
|
|
pagevec_release(&pvec);
|
|
} while (index <= end);
|
|
|
|
out:
|
|
pagevec_release(&pvec);
|
|
return found;
|
|
}
|
|
|
|
/*
|
|
* ext4_seek_data() retrieves the offset for SEEK_DATA.
|
|
*/
|
|
static loff_t ext4_seek_data(struct file *file, loff_t offset, loff_t maxsize)
|
|
{
|
|
struct inode *inode = file->f_mapping->host;
|
|
struct ext4_map_blocks map;
|
|
struct extent_status es;
|
|
ext4_lblk_t start, last, end;
|
|
loff_t dataoff, isize;
|
|
int blkbits;
|
|
int ret = 0;
|
|
|
|
mutex_lock(&inode->i_mutex);
|
|
|
|
isize = i_size_read(inode);
|
|
if (offset >= isize) {
|
|
mutex_unlock(&inode->i_mutex);
|
|
return -ENXIO;
|
|
}
|
|
|
|
blkbits = inode->i_sb->s_blocksize_bits;
|
|
start = offset >> blkbits;
|
|
last = start;
|
|
end = isize >> blkbits;
|
|
dataoff = offset;
|
|
|
|
do {
|
|
map.m_lblk = last;
|
|
map.m_len = end - last + 1;
|
|
ret = ext4_map_blocks(NULL, inode, &map, 0);
|
|
if (ret > 0 && !(map.m_flags & EXT4_MAP_UNWRITTEN)) {
|
|
if (last != start)
|
|
dataoff = (loff_t)last << blkbits;
|
|
break;
|
|
}
|
|
|
|
/*
|
|
* If there is a delay extent at this offset,
|
|
* it will be as a data.
|
|
*/
|
|
ext4_es_find_delayed_extent_range(inode, last, last, &es);
|
|
if (es.es_len != 0 && in_range(last, es.es_lblk, es.es_len)) {
|
|
if (last != start)
|
|
dataoff = (loff_t)last << blkbits;
|
|
break;
|
|
}
|
|
|
|
/*
|
|
* If there is a unwritten extent at this offset,
|
|
* it will be as a data or a hole according to page
|
|
* cache that has data or not.
|
|
*/
|
|
if (map.m_flags & EXT4_MAP_UNWRITTEN) {
|
|
int unwritten;
|
|
unwritten = ext4_find_unwritten_pgoff(inode, SEEK_DATA,
|
|
&map, &dataoff);
|
|
if (unwritten)
|
|
break;
|
|
}
|
|
|
|
last++;
|
|
dataoff = (loff_t)last << blkbits;
|
|
} while (last <= end);
|
|
|
|
mutex_unlock(&inode->i_mutex);
|
|
|
|
if (dataoff > isize)
|
|
return -ENXIO;
|
|
|
|
return vfs_setpos(file, dataoff, maxsize);
|
|
}
|
|
|
|
/*
|
|
* ext4_seek_hole() retrieves the offset for SEEK_HOLE.
|
|
*/
|
|
static loff_t ext4_seek_hole(struct file *file, loff_t offset, loff_t maxsize)
|
|
{
|
|
struct inode *inode = file->f_mapping->host;
|
|
struct ext4_map_blocks map;
|
|
struct extent_status es;
|
|
ext4_lblk_t start, last, end;
|
|
loff_t holeoff, isize;
|
|
int blkbits;
|
|
int ret = 0;
|
|
|
|
mutex_lock(&inode->i_mutex);
|
|
|
|
isize = i_size_read(inode);
|
|
if (offset >= isize) {
|
|
mutex_unlock(&inode->i_mutex);
|
|
return -ENXIO;
|
|
}
|
|
|
|
blkbits = inode->i_sb->s_blocksize_bits;
|
|
start = offset >> blkbits;
|
|
last = start;
|
|
end = isize >> blkbits;
|
|
holeoff = offset;
|
|
|
|
do {
|
|
map.m_lblk = last;
|
|
map.m_len = end - last + 1;
|
|
ret = ext4_map_blocks(NULL, inode, &map, 0);
|
|
if (ret > 0 && !(map.m_flags & EXT4_MAP_UNWRITTEN)) {
|
|
last += ret;
|
|
holeoff = (loff_t)last << blkbits;
|
|
continue;
|
|
}
|
|
|
|
/*
|
|
* If there is a delay extent at this offset,
|
|
* we will skip this extent.
|
|
*/
|
|
ext4_es_find_delayed_extent_range(inode, last, last, &es);
|
|
if (es.es_len != 0 && in_range(last, es.es_lblk, es.es_len)) {
|
|
last = es.es_lblk + es.es_len;
|
|
holeoff = (loff_t)last << blkbits;
|
|
continue;
|
|
}
|
|
|
|
/*
|
|
* If there is a unwritten extent at this offset,
|
|
* it will be as a data or a hole according to page
|
|
* cache that has data or not.
|
|
*/
|
|
if (map.m_flags & EXT4_MAP_UNWRITTEN) {
|
|
int unwritten;
|
|
unwritten = ext4_find_unwritten_pgoff(inode, SEEK_HOLE,
|
|
&map, &holeoff);
|
|
if (!unwritten) {
|
|
last += ret;
|
|
holeoff = (loff_t)last << blkbits;
|
|
continue;
|
|
}
|
|
}
|
|
|
|
/* find a hole */
|
|
break;
|
|
} while (last <= end);
|
|
|
|
mutex_unlock(&inode->i_mutex);
|
|
|
|
if (holeoff > isize)
|
|
holeoff = isize;
|
|
|
|
return vfs_setpos(file, holeoff, maxsize);
|
|
}
|
|
|
|
/*
|
|
* 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) {
|
|
case SEEK_SET:
|
|
case SEEK_CUR:
|
|
case SEEK_END:
|
|
return generic_file_llseek_size(file, offset, whence,
|
|
maxbytes, i_size_read(inode));
|
|
case SEEK_DATA:
|
|
return ext4_seek_data(file, offset, maxbytes);
|
|
case SEEK_HOLE:
|
|
return ext4_seek_hole(file, offset, maxbytes);
|
|
}
|
|
|
|
return -EINVAL;
|
|
}
|
|
|
|
const struct file_operations ext4_file_operations = {
|
|
.llseek = ext4_llseek,
|
|
.read = new_sync_read,
|
|
.write = new_sync_write,
|
|
.read_iter = generic_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,
|
|
.open = ext4_file_open,
|
|
.release = ext4_release_file,
|
|
.fsync = ext4_sync_file,
|
|
.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_getattr,
|
|
.setxattr = generic_setxattr,
|
|
.getxattr = generic_getxattr,
|
|
.listxattr = ext4_listxattr,
|
|
.removexattr = generic_removexattr,
|
|
.get_acl = ext4_get_acl,
|
|
.set_acl = ext4_set_acl,
|
|
.fiemap = ext4_fiemap,
|
|
};
|
|
|