1
0
Fork 0
remarkable-linux/fs/ext4/file.c

795 lines
20 KiB
C
Raw Normal View History

/*
* 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/mount.h>
#include <linux/path.h>
#include <linux/dax.h>
#include <linux/quotaops.h>
#include <linux/pagevec.h>
#include <linux/uio.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;
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 (!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)
ext4: serialize unaligned asynchronous DIO ext4 has a data corruption case when doing non-block-aligned asynchronous direct IO into a sparse file, as demonstrated by xfstest 240. The root cause is that while ext4 preallocates space in the hole, mappings of that space still look "new" and dio_zero_block() will zero out the unwritten portions. When more than one AIO thread is going, they both find this "new" block and race to zero out their portion; this is uncoordinated and causes data corruption. Dave Chinner fixed this for xfs by simply serializing all unaligned asynchronous direct IO. I've done the same here. The difference is that we only wait on conversions, not all IO. This is a very big hammer, and I'm not very pleased with stuffing this into ext4_file_write(). But since ext4 is DIO_LOCKING, we need to serialize it at this high level. I tried to move this into ext4_ext_direct_IO, but by then we have the i_mutex already, and we will wait on the work queue to do conversions - which must also take the i_mutex. So that won't work. This was originally exposed by qemu-kvm installing to a raw disk image with a normal sector-63 alignment. I've tested a backport of this patch with qemu, and it does avoid the corruption. It is also quite a lot slower (14 min for package installs, vs. 8 min for well-aligned) but I'll take slow correctness over fast corruption any day. Mingming suggested that we can track outstanding conversions, and wait on those so that non-sparse files won't be affected, and I've implemented that here; unaligned AIO to nonsparse files won't take a perf hit. [tytso@mit.edu: Keep the mutex as a hashed array instead of bloating the ext4 inode] [tytso@mit.edu: Fix up namespace issues so that global variables are protected with an "ext4_" prefix.] Signed-off-by: Eric Sandeen <sandeen@redhat.com> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
2011-02-12 06:17:34 -07:00
{
wait_queue_head_t *wq = ext4_ioend_wq(inode);
wait_event(*wq, (atomic_read(&EXT4_I(inode)->i_unwritten) == 0));
ext4: serialize unaligned asynchronous DIO ext4 has a data corruption case when doing non-block-aligned asynchronous direct IO into a sparse file, as demonstrated by xfstest 240. The root cause is that while ext4 preallocates space in the hole, mappings of that space still look "new" and dio_zero_block() will zero out the unwritten portions. When more than one AIO thread is going, they both find this "new" block and race to zero out their portion; this is uncoordinated and causes data corruption. Dave Chinner fixed this for xfs by simply serializing all unaligned asynchronous direct IO. I've done the same here. The difference is that we only wait on conversions, not all IO. This is a very big hammer, and I'm not very pleased with stuffing this into ext4_file_write(). But since ext4 is DIO_LOCKING, we need to serialize it at this high level. I tried to move this into ext4_ext_direct_IO, but by then we have the i_mutex already, and we will wait on the work queue to do conversions - which must also take the i_mutex. So that won't work. This was originally exposed by qemu-kvm installing to a raw disk image with a normal sector-63 alignment. I've tested a backport of this patch with qemu, and it does avoid the corruption. It is also quite a lot slower (14 min for package installs, vs. 8 min for well-aligned) but I'll take slow correctness over fast corruption any day. Mingming suggested that we can track outstanding conversions, and wait on those so that non-sparse files won't be affected, and I've implemented that here; unaligned AIO to nonsparse files won't take a perf hit. [tytso@mit.edu: Keep the mutex as a hashed array instead of bloating the ext4 inode] [tytso@mit.edu: Fix up namespace issues so that global variables are protected with an "ext4_" prefix.] Signed-off-by: Eric Sandeen <sandeen@redhat.com> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
2011-02-12 06:17:34 -07:00
}
/*
* 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)
ext4: serialize unaligned asynchronous DIO ext4 has a data corruption case when doing non-block-aligned asynchronous direct IO into a sparse file, as demonstrated by xfstest 240. The root cause is that while ext4 preallocates space in the hole, mappings of that space still look "new" and dio_zero_block() will zero out the unwritten portions. When more than one AIO thread is going, they both find this "new" block and race to zero out their portion; this is uncoordinated and causes data corruption. Dave Chinner fixed this for xfs by simply serializing all unaligned asynchronous direct IO. I've done the same here. The difference is that we only wait on conversions, not all IO. This is a very big hammer, and I'm not very pleased with stuffing this into ext4_file_write(). But since ext4 is DIO_LOCKING, we need to serialize it at this high level. I tried to move this into ext4_ext_direct_IO, but by then we have the i_mutex already, and we will wait on the work queue to do conversions - which must also take the i_mutex. So that won't work. This was originally exposed by qemu-kvm installing to a raw disk image with a normal sector-63 alignment. I've tested a backport of this patch with qemu, and it does avoid the corruption. It is also quite a lot slower (14 min for package installs, vs. 8 min for well-aligned) but I'll take slow correctness over fast corruption any day. Mingming suggested that we can track outstanding conversions, and wait on those so that non-sparse files won't be affected, and I've implemented that here; unaligned AIO to nonsparse files won't take a perf hit. [tytso@mit.edu: Keep the mutex as a hashed array instead of bloating the ext4 inode] [tytso@mit.edu: Fix up namespace issues so that global variables are protected with an "ext4_" prefix.] Signed-off-by: Eric Sandeen <sandeen@redhat.com> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
2011-02-12 06:17:34 -07:00
{
struct super_block *sb = inode->i_sb;
int blockmask = sb->s_blocksize - 1;
if (pos >= i_size_read(inode))
ext4: serialize unaligned asynchronous DIO ext4 has a data corruption case when doing non-block-aligned asynchronous direct IO into a sparse file, as demonstrated by xfstest 240. The root cause is that while ext4 preallocates space in the hole, mappings of that space still look "new" and dio_zero_block() will zero out the unwritten portions. When more than one AIO thread is going, they both find this "new" block and race to zero out their portion; this is uncoordinated and causes data corruption. Dave Chinner fixed this for xfs by simply serializing all unaligned asynchronous direct IO. I've done the same here. The difference is that we only wait on conversions, not all IO. This is a very big hammer, and I'm not very pleased with stuffing this into ext4_file_write(). But since ext4 is DIO_LOCKING, we need to serialize it at this high level. I tried to move this into ext4_ext_direct_IO, but by then we have the i_mutex already, and we will wait on the work queue to do conversions - which must also take the i_mutex. So that won't work. This was originally exposed by qemu-kvm installing to a raw disk image with a normal sector-63 alignment. I've tested a backport of this patch with qemu, and it does avoid the corruption. It is also quite a lot slower (14 min for package installs, vs. 8 min for well-aligned) but I'll take slow correctness over fast corruption any day. Mingming suggested that we can track outstanding conversions, and wait on those so that non-sparse files won't be affected, and I've implemented that here; unaligned AIO to nonsparse files won't take a perf hit. [tytso@mit.edu: Keep the mutex as a hashed array instead of bloating the ext4 inode] [tytso@mit.edu: Fix up namespace issues so that global variables are protected with an "ext4_" prefix.] Signed-off-by: Eric Sandeen <sandeen@redhat.com> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
2011-02-12 06:17:34 -07:00
return 0;
if ((pos | iov_iter_alignment(from)) & blockmask)
ext4: serialize unaligned asynchronous DIO ext4 has a data corruption case when doing non-block-aligned asynchronous direct IO into a sparse file, as demonstrated by xfstest 240. The root cause is that while ext4 preallocates space in the hole, mappings of that space still look "new" and dio_zero_block() will zero out the unwritten portions. When more than one AIO thread is going, they both find this "new" block and race to zero out their portion; this is uncoordinated and causes data corruption. Dave Chinner fixed this for xfs by simply serializing all unaligned asynchronous direct IO. I've done the same here. The difference is that we only wait on conversions, not all IO. This is a very big hammer, and I'm not very pleased with stuffing this into ext4_file_write(). But since ext4 is DIO_LOCKING, we need to serialize it at this high level. I tried to move this into ext4_ext_direct_IO, but by then we have the i_mutex already, and we will wait on the work queue to do conversions - which must also take the i_mutex. So that won't work. This was originally exposed by qemu-kvm installing to a raw disk image with a normal sector-63 alignment. I've tested a backport of this patch with qemu, and it does avoid the corruption. It is also quite a lot slower (14 min for package installs, vs. 8 min for well-aligned) but I'll take slow correctness over fast corruption any day. Mingming suggested that we can track outstanding conversions, and wait on those so that non-sparse files won't be affected, and I've implemented that here; unaligned AIO to nonsparse files won't take a perf hit. [tytso@mit.edu: Keep the mutex as a hashed array instead of bloating the ext4 inode] [tytso@mit.edu: Fix up namespace issues so that global variables are protected with an "ext4_" prefix.] Signed-off-by: Eric Sandeen <sandeen@redhat.com> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
2011-02-12 06:17:34 -07:00
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;
bool overwrite = false;
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;
if (ext4_overwrite_io(inode, iocb->ki_pos, iov_iter_count(from))) {
overwrite = true;
downgrade_write(&inode->i_rwsem);
}
ret = dax_iomap_rw(iocb, from, &ext4_iomap_ops);
out:
if (!overwrite)
inode_unlock(inode);
else
inode_unlock_shared(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;
#ifdef CONFIG_FS_DAX
if (IS_DAX(inode))
return ext4_dax_write_iter(iocb, from);
#endif
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);
}
ext4: prevent bugon on race between write/fcntl 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
2014-10-30 08:53:16 -06:00
iocb->private = &overwrite;
/* Check whether we do a DIO overwrite or not */
if (o_direct && ext4_should_dioread_nolock(inode) && !unaligned_aio &&
ext4_overwrite_io(inode, iocb->ki_pos, iov_iter_count(from)))
overwrite = 1;
ret = __generic_file_write_iter(iocb, from);
inode_unlock(inode);
if (ret > 0)
ret = generic_write_sync(iocb, ret);
ext4: serialize unaligned asynchronous DIO ext4 has a data corruption case when doing non-block-aligned asynchronous direct IO into a sparse file, as demonstrated by xfstest 240. The root cause is that while ext4 preallocates space in the hole, mappings of that space still look "new" and dio_zero_block() will zero out the unwritten portions. When more than one AIO thread is going, they both find this "new" block and race to zero out their portion; this is uncoordinated and causes data corruption. Dave Chinner fixed this for xfs by simply serializing all unaligned asynchronous direct IO. I've done the same here. The difference is that we only wait on conversions, not all IO. This is a very big hammer, and I'm not very pleased with stuffing this into ext4_file_write(). But since ext4 is DIO_LOCKING, we need to serialize it at this high level. I tried to move this into ext4_ext_direct_IO, but by then we have the i_mutex already, and we will wait on the work queue to do conversions - which must also take the i_mutex. So that won't work. This was originally exposed by qemu-kvm installing to a raw disk image with a normal sector-63 alignment. I've tested a backport of this patch with qemu, and it does avoid the corruption. It is also quite a lot slower (14 min for package installs, vs. 8 min for well-aligned) but I'll take slow correctness over fast corruption any day. Mingming suggested that we can track outstanding conversions, and wait on those so that non-sparse files won't be affected, and I've implemented that here; unaligned AIO to nonsparse files won't take a perf hit. [tytso@mit.edu: Keep the mutex as a hashed array instead of bloating the ext4 inode] [tytso@mit.edu: Fix up namespace issues so that global variables are protected with an "ext4_" prefix.] Signed-off-by: Eric Sandeen <sandeen@redhat.com> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
2011-02-12 06:17:34 -07:00
return ret;
out:
inode_unlock(inode);
ext4: serialize unaligned asynchronous DIO ext4 has a data corruption case when doing non-block-aligned asynchronous direct IO into a sparse file, as demonstrated by xfstest 240. The root cause is that while ext4 preallocates space in the hole, mappings of that space still look "new" and dio_zero_block() will zero out the unwritten portions. When more than one AIO thread is going, they both find this "new" block and race to zero out their portion; this is uncoordinated and causes data corruption. Dave Chinner fixed this for xfs by simply serializing all unaligned asynchronous direct IO. I've done the same here. The difference is that we only wait on conversions, not all IO. This is a very big hammer, and I'm not very pleased with stuffing this into ext4_file_write(). But since ext4 is DIO_LOCKING, we need to serialize it at this high level. I tried to move this into ext4_ext_direct_IO, but by then we have the i_mutex already, and we will wait on the work queue to do conversions - which must also take the i_mutex. So that won't work. This was originally exposed by qemu-kvm installing to a raw disk image with a normal sector-63 alignment. I've tested a backport of this patch with qemu, and it does avoid the corruption. It is also quite a lot slower (14 min for package installs, vs. 8 min for well-aligned) but I'll take slow correctness over fast corruption any day. Mingming suggested that we can track outstanding conversions, and wait on those so that non-sparse files won't be affected, and I've implemented that here; unaligned AIO to nonsparse files won't take a perf hit. [tytso@mit.edu: Keep the mutex as a hashed array instead of bloating the ext4 inode] [tytso@mit.edu: Fix up namespace issues so that global variables are protected with an "ext4_" prefix.] Signed-off-by: Eric Sandeen <sandeen@redhat.com> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
2011-02-12 06:17:34 -07:00
return ret;
}
#ifdef CONFIG_FS_DAX
static int ext4_dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
{
int result;
handle_t *handle = NULL;
struct inode *inode = file_inode(vma->vm_file);
struct super_block *sb = inode->i_sb;
bool write = vmf->flags & FAULT_FLAG_WRITE;
if (write) {
sb_start_pagefault(sb);
file_update_time(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));
} else
down_read(&EXT4_I(inode)->i_mmap_sem);
if (IS_ERR(handle))
result = VM_FAULT_SIGBUS;
else
result = dax_iomap_fault(vma, vmf, &ext4_iomap_ops);
if (write) {
if (!IS_ERR(handle))
ext4_journal_stop(handle);
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_pmd_fault(struct vm_area_struct *vma, unsigned long addr,
pmd_t *pmd, unsigned int flags)
{
int result;
handle_t *handle = NULL;
struct inode *inode = file_inode(vma->vm_file);
struct super_block *sb = inode->i_sb;
bool write = flags & FAULT_FLAG_WRITE;
if (write) {
sb_start_pagefault(sb);
file_update_time(vma->vm_file);
down_read(&EXT4_I(inode)->i_mmap_sem);
handle = ext4_journal_start_sb(sb, EXT4_HT_WRITE_PAGE,
ext4_chunk_trans_blocks(inode,
PMD_SIZE / PAGE_SIZE));
} else
down_read(&EXT4_I(inode)->i_mmap_sem);
if (IS_ERR(handle))
result = VM_FAULT_SIGBUS;
else {
result = dax_iomap_pmd_fault(vma, addr, pmd, flags,
&ext4_iomap_ops);
}
if (write) {
if (!IS_ERR(handle))
ext4_journal_stop(handle);
up_read(&EXT4_I(inode)->i_mmap_sem);
sb_end_pagefault(sb);
} else
up_read(&EXT4_I(inode)->i_mmap_sem);
return result;
}
/*
* Handle write fault for VM_MIXEDMAP mappings. Similarly to ext4_dax_fault()
* handler we check for races agaist truncate. Note that since we cycle through
* i_mmap_sem, we are sure that also any hole punching that began before we
* were called is finished by now and so if it included part of the file we
* are working on, our pte will get unmapped and the check for pte_same() in
* wp_pfn_shared() fails. Thus fault gets retried and things work out as
* desired.
*/
static int ext4_dax_pfn_mkwrite(struct vm_area_struct *vma,
struct vm_fault *vmf)
{
struct inode *inode = file_inode(vma->vm_file);
struct super_block *sb = inode->i_sb;
loff_t size;
int ret;
sb_start_pagefault(sb);
file_update_time(vma->vm_file);
down_read(&EXT4_I(inode)->i_mmap_sem);
size = (i_size_read(inode) + PAGE_SIZE - 1) >> PAGE_SHIFT;
if (vmf->pgoff >= size)
ret = VM_FAULT_SIGBUS;
else
ret = dax_pfn_mkwrite(vma, vmf);
up_read(&EXT4_I(inode)->i_mmap_sem);
sb_end_pagefault(sb);
return ret;
}
static const struct vm_operations_struct ext4_dax_vm_ops = {
.fault = ext4_dax_fault,
.pmd_fault = ext4_dax_pmd_fault,
.page_mkwrite = ext4_dax_fault,
.pfn_mkwrite = ext4_dax_pfn_mkwrite,
};
#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 (ext4_encrypted_inode(inode)) {
int err = fscrypt_get_encryption_info(inode);
if (err)
return 0;
if (!fscrypt_has_encryption_key(inode))
return -ENOKEY;
}
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 dentry *dir;
struct path path;
char buf[64], *cp;
int ret;
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);
}
}
if (ext4_encrypted_inode(inode)) {
ret = fscrypt_get_encryption_info(inode);
if (ret)
return -EACCES;
if (!fscrypt_has_encryption_key(inode))
return -ENOKEY;
}
dir = dget_parent(file_dentry(filp));
if (ext4_encrypted_inode(d_inode(dir)) &&
!fscrypt_has_permitted_context(d_inode(dir), inode)) {
ext4_warning(inode->i_sb,
"Inconsistent encryption contexts: %lu/%lu",
(unsigned long) d_inode(dir)->i_ino,
(unsigned long) inode->i_ino);
dput(dir);
return -EPERM;
}
dput(dir);
/*
* 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;
}
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,
ext4_lblk_t end_blk,
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)end_blk << blkbits;
mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} macros were introduced *long* time ago with promise that one day it will be possible to implement page cache with bigger chunks than PAGE_SIZE. This promise never materialized. And unlikely will. We have many places where PAGE_CACHE_SIZE assumed to be equal to PAGE_SIZE. And it's constant source of confusion on whether PAGE_CACHE_* or PAGE_* constant should be used in a particular case, especially on the border between fs and mm. Global switching to PAGE_CACHE_SIZE != PAGE_SIZE would cause to much breakage to be doable. Let's stop pretending that pages in page cache are special. They are not. The changes are pretty straight-forward: - <foo> << (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - <foo> >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>; - PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} -> PAGE_{SIZE,SHIFT,MASK,ALIGN}; - page_cache_get() -> get_page(); - page_cache_release() -> put_page(); This patch contains automated changes generated with coccinelle using script below. For some reason, coccinelle doesn't patch header files. I've called spatch for them manually. The only adjustment after coccinelle is revert of changes to PAGE_CAHCE_ALIGN definition: we are going to drop it later. There are few places in the code where coccinelle didn't reach. I'll fix them manually in a separate patch. Comments and documentation also will be addressed with the separate patch. virtual patch @@ expression E; @@ - E << (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ expression E; @@ - E >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ @@ - PAGE_CACHE_SHIFT + PAGE_SHIFT @@ @@ - PAGE_CACHE_SIZE + PAGE_SIZE @@ @@ - PAGE_CACHE_MASK + PAGE_MASK @@ expression E; @@ - PAGE_CACHE_ALIGN(E) + PAGE_ALIGN(E) @@ expression E; @@ - page_cache_get(E) + get_page(E) @@ expression E; @@ - page_cache_release(E) + put_page(E) Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Acked-by: Michal Hocko <mhocko@suse.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-04-01 06:29:47 -06:00
index = startoff >> PAGE_SHIFT;
end = endoff >> PAGE_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 extent_status es;
ext4_lblk_t start, last, end;
loff_t dataoff, isize;
int blkbits;
int ret;
inode_lock(inode);
isize = i_size_read(inode);
if (offset >= isize) {
inode_unlock(inode);
return -ENXIO;
}
blkbits = inode->i_sb->s_blocksize_bits;
start = offset >> blkbits;
last = start;
end = isize >> blkbits;
dataoff = offset;
do {
ret = ext4_get_next_extent(inode, last, end - last + 1, &es);
if (ret <= 0) {
/* No extent found -> no data */
if (ret == 0)
ret = -ENXIO;
inode_unlock(inode);
return ret;
}
last = es.es_lblk;
if (last != start)
dataoff = (loff_t)last << blkbits;
if (!ext4_es_is_unwritten(&es))
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 (ext4_find_unwritten_pgoff(inode, SEEK_DATA,
es.es_lblk + es.es_len, &dataoff))
break;
last += es.es_len;
dataoff = (loff_t)last << blkbits;
cond_resched();
} while (last <= end);
inode_unlock(inode);
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 extent_status es;
ext4_lblk_t start, last, end;
loff_t holeoff, isize;
int blkbits;
int ret;
inode_lock(inode);
isize = i_size_read(inode);
if (offset >= isize) {
inode_unlock(inode);
return -ENXIO;
}
blkbits = inode->i_sb->s_blocksize_bits;
start = offset >> blkbits;
last = start;
end = isize >> blkbits;
holeoff = offset;
do {
ret = ext4_get_next_extent(inode, last, end - last + 1, &es);
if (ret < 0) {
inode_unlock(inode);
return ret;
}
/* Found a hole? */
if (ret == 0 || es.es_lblk > last) {
if (last != start)
holeoff = (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 (ext4_es_is_unwritten(&es) &&
ext4_find_unwritten_pgoff(inode, SEEK_HOLE,
last + es.es_len, &holeoff))
break;
last += es.es_len;
holeoff = (loff_t)last << blkbits;
cond_resched();
} while (last <= end);
inode_unlock(inode);
if (holeoff > isize)
holeoff = isize;
return vfs_setpos(file, holeoff, maxsize);
}
ext4: improve llseek error handling for overly large seek offsets The llseek system call should return EINVAL if passed a seek offset which results in a write error. What this maximum offset should be depends on whether or not the huge_file file system feature is set, and whether or not the file is extent based or not. If the file has no "EXT4_EXTENTS_FL" flag, the maximum size which can be written (write systemcall) is different from the maximum size which can be sought (lseek systemcall). For example, the following 2 cases demonstrates the differences between the maximum size which can be written, versus the seek offset allowed by the llseek system call: #1: mkfs.ext3 <dev>; mount -t ext4 <dev> #2: mkfs.ext3 <dev>; tune2fs -Oextent,huge_file <dev>; mount -t ext4 <dev> Table. the max file size which we can write or seek at each filesystem feature tuning and file flag setting +============+===============================+===============================+ | \ File flag| | | | \ | !EXT4_EXTENTS_FL | EXT4_EXTETNS_FL | |case \| | | +------------+-------------------------------+-------------------------------+ | #1 | write: 2194719883264 | write: -------------- | | | seek: 2199023251456 | seek: -------------- | +------------+-------------------------------+-------------------------------+ | #2 | write: 4402345721856 | write: 17592186044415 | | | seek: 17592186044415 | seek: 17592186044415 | +------------+-------------------------------+-------------------------------+ The differences exist because ext4 has 2 maxbytes which are sb->s_maxbytes (= extent-mapped maxbytes) and EXT4_SB(sb)->s_bitmap_maxbytes (= block-mapped maxbytes). Although generic_file_llseek uses only extent-mapped maxbytes. (llseek of ext4_file_operations is generic_file_llseek which uses sb->s_maxbytes.) Therefore we create ext4 llseek function which uses 2 maxbytes. The new own function originates from generic_file_llseek(). If the file flag, "EXT4_EXTENTS_FL" is not set, the function alters inode->i_sb->s_maxbytes into EXT4_SB(inode->i_sb)->s_bitmap_maxbytes. Signed-off-by: Toshiyuki Okajima <toshi.okajima@jp.fujitsu.com> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu> Cc: Andreas Dilger <adilger.kernel@dilger.ca>
2010-10-27 19:30:06 -06:00
/*
* ext4_llseek() handles both block-mapped and extent-mapped maxbytes values
* by calling generic_file_llseek_size() with the appropriate maxbytes
* value for each.
ext4: improve llseek error handling for overly large seek offsets The llseek system call should return EINVAL if passed a seek offset which results in a write error. What this maximum offset should be depends on whether or not the huge_file file system feature is set, and whether or not the file is extent based or not. If the file has no "EXT4_EXTENTS_FL" flag, the maximum size which can be written (write systemcall) is different from the maximum size which can be sought (lseek systemcall). For example, the following 2 cases demonstrates the differences between the maximum size which can be written, versus the seek offset allowed by the llseek system call: #1: mkfs.ext3 <dev>; mount -t ext4 <dev> #2: mkfs.ext3 <dev>; tune2fs -Oextent,huge_file <dev>; mount -t ext4 <dev> Table. the max file size which we can write or seek at each filesystem feature tuning and file flag setting +============+===============================+===============================+ | \ File flag| | | | \ | !EXT4_EXTENTS_FL | EXT4_EXTETNS_FL | |case \| | | +------------+-------------------------------+-------------------------------+ | #1 | write: 2194719883264 | write: -------------- | | | seek: 2199023251456 | seek: -------------- | +------------+-------------------------------+-------------------------------+ | #2 | write: 4402345721856 | write: 17592186044415 | | | seek: 17592186044415 | seek: 17592186044415 | +------------+-------------------------------+-------------------------------+ The differences exist because ext4 has 2 maxbytes which are sb->s_maxbytes (= extent-mapped maxbytes) and EXT4_SB(sb)->s_bitmap_maxbytes (= block-mapped maxbytes). Although generic_file_llseek uses only extent-mapped maxbytes. (llseek of ext4_file_operations is generic_file_llseek which uses sb->s_maxbytes.) Therefore we create ext4 llseek function which uses 2 maxbytes. The new own function originates from generic_file_llseek(). If the file flag, "EXT4_EXTENTS_FL" is not set, the function alters inode->i_sb->s_maxbytes into EXT4_SB(inode->i_sb)->s_bitmap_maxbytes. Signed-off-by: Toshiyuki Okajima <toshi.okajima@jp.fujitsu.com> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu> Cc: Andreas Dilger <adilger.kernel@dilger.ca>
2010-10-27 19:30:06 -06:00
*/
loff_t ext4_llseek(struct file *file, loff_t offset, int whence)
ext4: improve llseek error handling for overly large seek offsets The llseek system call should return EINVAL if passed a seek offset which results in a write error. What this maximum offset should be depends on whether or not the huge_file file system feature is set, and whether or not the file is extent based or not. If the file has no "EXT4_EXTENTS_FL" flag, the maximum size which can be written (write systemcall) is different from the maximum size which can be sought (lseek systemcall). For example, the following 2 cases demonstrates the differences between the maximum size which can be written, versus the seek offset allowed by the llseek system call: #1: mkfs.ext3 <dev>; mount -t ext4 <dev> #2: mkfs.ext3 <dev>; tune2fs -Oextent,huge_file <dev>; mount -t ext4 <dev> Table. the max file size which we can write or seek at each filesystem feature tuning and file flag setting +============+===============================+===============================+ | \ File flag| | | | \ | !EXT4_EXTENTS_FL | EXT4_EXTETNS_FL | |case \| | | +------------+-------------------------------+-------------------------------+ | #1 | write: 2194719883264 | write: -------------- | | | seek: 2199023251456 | seek: -------------- | +------------+-------------------------------+-------------------------------+ | #2 | write: 4402345721856 | write: 17592186044415 | | | seek: 17592186044415 | seek: 17592186044415 | +------------+-------------------------------+-------------------------------+ The differences exist because ext4 has 2 maxbytes which are sb->s_maxbytes (= extent-mapped maxbytes) and EXT4_SB(sb)->s_bitmap_maxbytes (= block-mapped maxbytes). Although generic_file_llseek uses only extent-mapped maxbytes. (llseek of ext4_file_operations is generic_file_llseek which uses sb->s_maxbytes.) Therefore we create ext4 llseek function which uses 2 maxbytes. The new own function originates from generic_file_llseek(). If the file flag, "EXT4_EXTENTS_FL" is not set, the function alters inode->i_sb->s_maxbytes into EXT4_SB(inode->i_sb)->s_bitmap_maxbytes. Signed-off-by: Toshiyuki Okajima <toshi.okajima@jp.fujitsu.com> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu> Cc: Andreas Dilger <adilger.kernel@dilger.ca>
2010-10-27 19:30:06 -06:00
{
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;
ext4: improve llseek error handling for overly large seek offsets The llseek system call should return EINVAL if passed a seek offset which results in a write error. What this maximum offset should be depends on whether or not the huge_file file system feature is set, and whether or not the file is extent based or not. If the file has no "EXT4_EXTENTS_FL" flag, the maximum size which can be written (write systemcall) is different from the maximum size which can be sought (lseek systemcall). For example, the following 2 cases demonstrates the differences between the maximum size which can be written, versus the seek offset allowed by the llseek system call: #1: mkfs.ext3 <dev>; mount -t ext4 <dev> #2: mkfs.ext3 <dev>; tune2fs -Oextent,huge_file <dev>; mount -t ext4 <dev> Table. the max file size which we can write or seek at each filesystem feature tuning and file flag setting +============+===============================+===============================+ | \ File flag| | | | \ | !EXT4_EXTENTS_FL | EXT4_EXTETNS_FL | |case \| | | +------------+-------------------------------+-------------------------------+ | #1 | write: 2194719883264 | write: -------------- | | | seek: 2199023251456 | seek: -------------- | +------------+-------------------------------+-------------------------------+ | #2 | write: 4402345721856 | write: 17592186044415 | | | seek: 17592186044415 | seek: 17592186044415 | +------------+-------------------------------+-------------------------------+ The differences exist because ext4 has 2 maxbytes which are sb->s_maxbytes (= extent-mapped maxbytes) and EXT4_SB(sb)->s_bitmap_maxbytes (= block-mapped maxbytes). Although generic_file_llseek uses only extent-mapped maxbytes. (llseek of ext4_file_operations is generic_file_llseek which uses sb->s_maxbytes.) Therefore we create ext4 llseek function which uses 2 maxbytes. The new own function originates from generic_file_llseek(). If the file flag, "EXT4_EXTENTS_FL" is not set, the function alters inode->i_sb->s_maxbytes into EXT4_SB(inode->i_sb)->s_bitmap_maxbytes. Signed-off-by: Toshiyuki Okajima <toshi.okajima@jp.fujitsu.com> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu> Cc: Andreas Dilger <adilger.kernel@dilger.ca>
2010-10-27 19:30:06 -06:00
}
const struct file_operations ext4_file_operations = {
ext4: improve llseek error handling for overly large seek offsets The llseek system call should return EINVAL if passed a seek offset which results in a write error. What this maximum offset should be depends on whether or not the huge_file file system feature is set, and whether or not the file is extent based or not. If the file has no "EXT4_EXTENTS_FL" flag, the maximum size which can be written (write systemcall) is different from the maximum size which can be sought (lseek systemcall). For example, the following 2 cases demonstrates the differences between the maximum size which can be written, versus the seek offset allowed by the llseek system call: #1: mkfs.ext3 <dev>; mount -t ext4 <dev> #2: mkfs.ext3 <dev>; tune2fs -Oextent,huge_file <dev>; mount -t ext4 <dev> Table. the max file size which we can write or seek at each filesystem feature tuning and file flag setting +============+===============================+===============================+ | \ File flag| | | | \ | !EXT4_EXTENTS_FL | EXT4_EXTETNS_FL | |case \| | | +------------+-------------------------------+-------------------------------+ | #1 | write: 2194719883264 | write: -------------- | | | seek: 2199023251456 | seek: -------------- | +------------+-------------------------------+-------------------------------+ | #2 | write: 4402345721856 | write: 17592186044415 | | | seek: 17592186044415 | seek: 17592186044415 | +------------+-------------------------------+-------------------------------+ The differences exist because ext4 has 2 maxbytes which are sb->s_maxbytes (= extent-mapped maxbytes) and EXT4_SB(sb)->s_bitmap_maxbytes (= block-mapped maxbytes). Although generic_file_llseek uses only extent-mapped maxbytes. (llseek of ext4_file_operations is generic_file_llseek which uses sb->s_maxbytes.) Therefore we create ext4 llseek function which uses 2 maxbytes. The new own function originates from generic_file_llseek(). If the file flag, "EXT4_EXTENTS_FL" is not set, the function alters inode->i_sb->s_maxbytes into EXT4_SB(inode->i_sb)->s_bitmap_maxbytes. Signed-off-by: Toshiyuki Okajima <toshi.okajima@jp.fujitsu.com> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu> Cc: Andreas Dilger <adilger.kernel@dilger.ca>
2010-10-27 19:30:06 -06:00
.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,
.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_getattr,
.listxattr = ext4_listxattr,
.get_acl = ext4_get_acl,
.set_acl = ext4_set_acl,
.fiemap = ext4_fiemap,
};