static unsigned long long iblock_emulate_read_cap_with_block_size(
struct se_device *dev,
struct block_device *bd,
struct request_queue *q)
{
unsigned long long blocks_long = (div_u64(i_size_read(bd->bd_inode),
bdev_logical_block_size(bd)) - 1);
u32 block_size = bdev_logical_block_size(bd);
if (block_size == dev->dev_attrib.block_size)
return blocks_long;
switch (block_size) {
case 4096:
switch (dev->dev_attrib.block_size) {
case 2048:
blocks_long <<= 1;
break;
case 1024:
blocks_long <<= 2;
break;
case 512:
blocks_long <<= 3;
default:
break;
}
break;
case 2048:
switch (dev->dev_attrib.block_size) {
case 4096:
blocks_long >>= 1;
break;
case 1024:
blocks_long <<= 1;
break;
case 512:
blocks_long <<= 2;
break;
default:
break;
}
break;
case 1024:
switch (dev->dev_attrib.block_size) {
case 4096:
blocks_long >>= 2;
break;
case 2048:
blocks_long >>= 1;
break;
case 512:
blocks_long <<= 1;
break;
default:
break;
}
break;
case 512:
switch (dev->dev_attrib.block_size) {
case 4096:
blocks_long >>= 3;
break;
case 2048:
blocks_long >>= 2;
break;
case 1024:
blocks_long >>= 1;
break;
default:
break;
}
break;
default:
break;
}
return blocks_long;
}
/**
* nilfs_resize_fs - resize the filesystem
* @sb: super block instance
* @newsize: new size of the filesystem (in bytes)
*/
int nilfs_resize_fs(struct super_block *sb, __u64 newsize)
{
struct the_nilfs *nilfs = sb->s_fs_info;
struct nilfs_super_block **sbp;
__u64 devsize, newnsegs;
loff_t sb2off;
int ret;
ret = -ERANGE;
devsize = i_size_read(sb->s_bdev->bd_inode);
if (newsize > devsize)
goto out;
/*
* Write lock is required to protect some functions depending
* on the number of segments, the number of reserved segments,
* and so forth.
*/
down_write(&nilfs->ns_segctor_sem);
sb2off = NILFS_SB2_OFFSET_BYTES(newsize);
newnsegs = sb2off >> nilfs->ns_blocksize_bits;
do_div(newnsegs, nilfs->ns_blocks_per_segment);
ret = nilfs_sufile_resize(nilfs->ns_sufile, newnsegs);
up_write(&nilfs->ns_segctor_sem);
if (ret < 0)
goto out;
ret = nilfs_construct_segment(sb);
if (ret < 0)
goto out;
down_write(&nilfs->ns_sem);
nilfs_move_2nd_super(sb, sb2off);
ret = -EIO;
sbp = nilfs_prepare_super(sb, 0);
if (likely(sbp)) {
nilfs_set_log_cursor(sbp[0], nilfs);
/*
* Drop NILFS_RESIZE_FS flag for compatibility with
* mount-time resize which may be implemented in a
* future release.
*/
sbp[0]->s_state = cpu_to_le16(le16_to_cpu(sbp[0]->s_state) &
~NILFS_RESIZE_FS);
sbp[0]->s_dev_size = cpu_to_le64(newsize);
sbp[0]->s_nsegments = cpu_to_le64(nilfs->ns_nsegments);
if (sbp[1])
memcpy(sbp[1], sbp[0], nilfs->ns_sbsize);
ret = nilfs_commit_super(sb, NILFS_SB_COMMIT_ALL);
}
up_write(&nilfs->ns_sem);
/*
* Reset the range of allocatable segments last. This order
* is important in the case of expansion because the secondary
* superblock must be protected from log write until migration
* completes.
*/
if (!ret)
nilfs_sufile_set_alloc_range(nilfs->ns_sufile, 0, newnsegs - 1);
out:
return ret;
}
static int ocfs2_get_block(struct inode *inode, sector_t iblock,
struct buffer_head *bh_result, int create)
{
int err = 0;
unsigned int ext_flags;
u64 max_blocks = bh_result->b_size >> inode->i_blkbits;
u64 p_blkno, count, past_eof;
struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
mlog_entry("(0x%p, %llu, 0x%p, %d)\n", inode,
(unsigned long long)iblock, bh_result, create);
if (OCFS2_I(inode)->ip_flags & OCFS2_INODE_SYSTEM_FILE)
mlog(ML_NOTICE, "get_block on system inode 0x%p (%lu)\n",
inode, inode->i_ino);
if (S_ISLNK(inode->i_mode)) {
/* this always does I/O for some reason. */
err = ocfs2_symlink_get_block(inode, iblock, bh_result, create);
goto bail;
}
err = ocfs2_extent_map_get_blocks(inode, iblock, &p_blkno, &count,
&ext_flags);
if (err) {
mlog(ML_ERROR, "Error %d from get_blocks(0x%p, %llu, 1, "
"%llu, NULL)\n", err, inode, (unsigned long long)iblock,
(unsigned long long)p_blkno);
goto bail;
}
if (max_blocks < count)
count = max_blocks;
/*
* ocfs2 never allocates in this function - the only time we
* need to use BH_New is when we're extending i_size on a file
* system which doesn't support holes, in which case BH_New
* allows block_prepare_write() to zero.
*
* If we see this on a sparse file system, then a truncate has
* raced us and removed the cluster. In this case, we clear
* the buffers dirty and uptodate bits and let the buffer code
* ignore it as a hole.
*/
if (create && p_blkno == 0 && ocfs2_sparse_alloc(osb)) {
clear_buffer_dirty(bh_result);
clear_buffer_uptodate(bh_result);
goto bail;
}
/* Treat the unwritten extent as a hole for zeroing purposes. */
if (p_blkno && !(ext_flags & OCFS2_EXT_UNWRITTEN))
map_bh(bh_result, inode->i_sb, p_blkno);
bh_result->b_size = count << inode->i_blkbits;
if (!ocfs2_sparse_alloc(osb)) {
if (p_blkno == 0) {
err = -EIO;
mlog(ML_ERROR,
"iblock = %llu p_blkno = %llu blkno=(%llu)\n",
(unsigned long long)iblock,
(unsigned long long)p_blkno,
(unsigned long long)OCFS2_I(inode)->ip_blkno);
mlog(ML_ERROR, "Size %llu, clusters %u\n", (unsigned long long)i_size_read(inode), OCFS2_I(inode)->ip_clusters);
dump_stack();
}
past_eof = ocfs2_blocks_for_bytes(inode->i_sb, i_size_read(inode));
mlog(0, "Inode %lu, past_eof = %llu\n", inode->i_ino,
(unsigned long long)past_eof);
if (create && (iblock >= past_eof))
set_buffer_new(bh_result);
}
bail:
if (err < 0)
err = -EIO;
mlog_exit(err);
return err;
}
STATIC ssize_t
xfs_file_read_iter(
struct kiocb *iocb,
struct iov_iter *to)
{
struct file *file = iocb->ki_filp;
struct inode *inode = file->f_mapping->host;
struct xfs_inode *ip = XFS_I(inode);
struct xfs_mount *mp = ip->i_mount;
size_t size = iov_iter_count(to);
ssize_t ret = 0;
int ioflags = 0;
xfs_fsize_t n;
loff_t pos = iocb->ki_pos;
XFS_STATS_INC(xs_read_calls);
if (unlikely(file->f_flags & O_DIRECT))
ioflags |= XFS_IO_ISDIRECT;
if (file->f_mode & FMODE_NOCMTIME)
ioflags |= XFS_IO_INVIS;
if (unlikely(ioflags & XFS_IO_ISDIRECT)) {
xfs_buftarg_t *target =
XFS_IS_REALTIME_INODE(ip) ?
mp->m_rtdev_targp : mp->m_ddev_targp;
/* DIO must be aligned to device logical sector size */
if ((pos | size) & target->bt_logical_sectormask) {
if (pos == i_size_read(inode))
return 0;
return -EINVAL;
}
}
n = mp->m_super->s_maxbytes - pos;
if (n <= 0 || size == 0)
return 0;
if (n < size)
size = n;
if (XFS_FORCED_SHUTDOWN(mp))
return -EIO;
/*
* Locking is a bit tricky here. If we take an exclusive lock
* for direct IO, we effectively serialise all new concurrent
* read IO to this file and block it behind IO that is currently in
* progress because IO in progress holds the IO lock shared. We only
* need to hold the lock exclusive to blow away the page cache, so
* only take lock exclusively if the page cache needs invalidation.
* This allows the normal direct IO case of no page cache pages to
* proceeed concurrently without serialisation.
*/
xfs_rw_ilock(ip, XFS_IOLOCK_SHARED);
if ((ioflags & XFS_IO_ISDIRECT) && inode->i_mapping->nrpages) {
xfs_rw_iunlock(ip, XFS_IOLOCK_SHARED);
xfs_rw_ilock(ip, XFS_IOLOCK_EXCL);
if (inode->i_mapping->nrpages) {
ret = filemap_write_and_wait_range(
VFS_I(ip)->i_mapping,
pos, -1);
if (ret) {
xfs_rw_iunlock(ip, XFS_IOLOCK_EXCL);
return ret;
}
truncate_pagecache_range(VFS_I(ip), pos, -1);
}
xfs_rw_ilock_demote(ip, XFS_IOLOCK_EXCL);
}
trace_xfs_file_read(ip, size, pos, ioflags);
ret = generic_file_read_iter(iocb, to);
if (ret > 0)
XFS_STATS_ADD(xs_read_bytes, ret);
xfs_rw_iunlock(ip, XFS_IOLOCK_SHARED);
return ret;
}
/* * bitmap_init_from_disk -- called at bitmap_create time to initialize
* the in-memory bitmap from the on-disk bitmap -- also, sets up the
* memory mapping of the bitmap file
* Special cases:
* if there's no bitmap file, or if the bitmap file had been
* previously kicked from the array, we mark all the bits as
* 1's in order to cause a full resync.
*
* We ignore all bits for sectors that end earlier than 'start'.
* This is used when reading an out-of-date bitmap...
*/
static int bitmap_init_from_disk(struct bitmap *bitmap, sector_t start)
{
unsigned long i, chunks, index, oldindex, bit;
struct page *page = NULL, *oldpage = NULL;
unsigned long num_pages, bit_cnt = 0;
struct file *file;
unsigned long bytes, offset, dummy;
int outofdate;
int ret = -ENOSPC;
void *paddr;
chunks = bitmap->chunks;
file = bitmap->file;
BUG_ON(!file && !bitmap->offset);
#ifdef INJECT_FAULTS_3
outofdate = 1;
#else
outofdate = bitmap->flags & BITMAP_STALE;
#endif
if (outofdate)
printk(KERN_INFO "%s: bitmap file is out of date, doing full "
"recovery\n", bmname(bitmap));
bytes = (chunks + 7) / 8;
num_pages = (bytes + sizeof(bitmap_super_t) + PAGE_SIZE - 1) / PAGE_SIZE;
if (file && i_size_read(file->f_mapping->host) < bytes + sizeof(bitmap_super_t)) {
printk(KERN_INFO "%s: bitmap file too short %lu < %lu\n",
bmname(bitmap),
(unsigned long) i_size_read(file->f_mapping->host),
bytes + sizeof(bitmap_super_t));
goto out;
}
ret = -ENOMEM;
bitmap->filemap = kmalloc(sizeof(struct page *) * num_pages, GFP_KERNEL);
if (!bitmap->filemap)
goto out;
bitmap->filemap_attr = kzalloc(sizeof(long) * num_pages, GFP_KERNEL);
if (!bitmap->filemap_attr)
goto out;
oldindex = ~0L;
for (i = 0; i < chunks; i++) {
int b;
index = file_page_index(i);
bit = file_page_offset(i);
if (index != oldindex) { /* this is a new page, read it in */
/* unmap the old page, we're done with it */
if (index == 0) {
/*
* if we're here then the superblock page
* contains some bits (PAGE_SIZE != sizeof sb)
* we've already read it in, so just use it
*/
page = bitmap->sb_page;
offset = sizeof(bitmap_super_t);
} else if (file) {
page = read_page(file, index, &dummy);
offset = 0;
} else {
page = read_sb_page(bitmap->mddev, bitmap->offset, index);
offset = 0;
}
if (IS_ERR(page)) { /* read error */
ret = PTR_ERR(page);
goto out;
}
oldindex = index;
oldpage = page;
if (outofdate) {
/*
* if bitmap is out of date, dirty the
* whole page and write it out
*/
paddr = kmap_atomic(page, KM_USER0);
memset(paddr + offset, 0xff,
PAGE_SIZE - offset);
kunmap_atomic(paddr, KM_USER0);
ret = write_page(bitmap, page, 1);
if (ret) {
/* release, page not in filemap yet */
put_page(page);
goto out;
}
}
bitmap->filemap[bitmap->file_pages++] = page;
}
paddr = kmap_atomic(page, KM_USER0);
if (bitmap->flags & BITMAP_HOSTENDIAN)
b = test_bit(bit, paddr);
else
b = ext2_test_bit(bit, paddr);
kunmap_atomic(paddr, KM_USER0);
if (b) {
/* if the disk bit is set, set the memory bit */
bitmap_set_memory_bits(bitmap, i << CHUNK_BLOCK_SHIFT(bitmap),
((i+1) << (CHUNK_BLOCK_SHIFT(bitmap)) >= start)
);
bit_cnt++;
set_page_attr(bitmap, page, BITMAP_PAGE_CLEAN);
}
}
/* everything went OK */
ret = 0;
bitmap_mask_state(bitmap, BITMAP_STALE, MASK_UNSET);
if (bit_cnt) { /* Kick recovery if any bits were set */
set_bit(MD_RECOVERY_NEEDED, &bitmap->mddev->recovery);
md_wakeup_thread(bitmap->mddev->thread);
}
out:
printk(KERN_INFO "%s: bitmap initialized from disk: "
"read %lu/%lu pages, set %lu bits, status: %d\n",
bmname(bitmap), bitmap->file_pages, num_pages, bit_cnt, ret);
return ret;
}
int __generic_block_fiemap(struct inode *inode,
struct fiemap_extent_info *fieinfo, u64 start,
u64 len, get_block_t *get_block)
{
struct buffer_head tmp;
unsigned long long start_blk;
long long length = 0, map_len = 0;
u64 logical = 0, phys = 0, size = 0;
u32 flags = FIEMAP_EXTENT_MERGED;
int ret = 0, past_eof = 0, whole_file = 0;
if ((ret = fiemap_check_flags(fieinfo, FIEMAP_FLAG_SYNC)))
return ret;
start_blk = logical_to_blk(inode, start);
length = (long long)min_t(u64, len, i_size_read(inode));
if (length < len)
whole_file = 1;
map_len = length;
do {
/*
* we set b_size to the total size we want so it will map as
* many contiguous blocks as possible at once
*/
memset(&tmp, 0, sizeof(struct buffer_head));
tmp.b_size = map_len;
ret = get_block(inode, start_blk, &tmp, 0);
if (ret)
break;
/* HOLE */
if (!buffer_mapped(&tmp)) {
length -= blk_to_logical(inode, 1);
start_blk++;
/*
* we want to handle the case where there is an
* allocated block at the front of the file, and then
* nothing but holes up to the end of the file properly,
* to make sure that extent at the front gets properly
* marked with FIEMAP_EXTENT_LAST
*/
if (!past_eof &&
blk_to_logical(inode, start_blk) >=
blk_to_logical(inode, 0)+i_size_read(inode))
past_eof = 1;
/*
* first hole after going past the EOF, this is our
* last extent
*/
if (past_eof && size) {
flags = FIEMAP_EXTENT_MERGED|FIEMAP_EXTENT_LAST;
ret = fiemap_fill_next_extent(fieinfo, logical,
phys, size,
flags);
break;
}
/* if we have holes up to/past EOF then we're done */
if (length <= 0 || past_eof)
break;
} else {
/*
* we have gone over the length of what we wanted to
* map, and it wasn't the entire file, so add the extent
* we got last time and exit.
*
* This is for the case where say we want to map all the
* way up to the second to the last block in a file, but
* the last block is a hole, making the second to last
* block FIEMAP_EXTENT_LAST. In this case we want to
* see if there is a hole after the second to last block
* so we can mark it properly. If we found data after
* we exceeded the length we were requesting, then we
* are good to go, just add the extent to the fieinfo
* and break
*/
if (length <= 0 && !whole_file) {
ret = fiemap_fill_next_extent(fieinfo, logical,
phys, size,
flags);
break;
}
/*
* if size != 0 then we know we already have an extent
* to add, so add it.
*/
if (size) {
ret = fiemap_fill_next_extent(fieinfo, logical,
phys, size,
flags);
if (ret)
break;
}
logical = blk_to_logical(inode, start_blk);
phys = blk_to_logical(inode, tmp.b_blocknr);
size = tmp.b_size;
flags = FIEMAP_EXTENT_MERGED;
length -= tmp.b_size;
start_blk += logical_to_blk(inode, size);
/*
* If we are past the EOF, then we need to make sure as
* soon as we find a hole that the last extent we found
* is marked with FIEMAP_EXTENT_LAST
*/
if (!past_eof &&
logical+size >=
blk_to_logical(inode, 0)+i_size_read(inode))
past_eof = 1;
}
cond_resched();
} while (1);
/* if ret is 1 then we just hit the end of the extent array */
if (ret == 1)
ret = 0;
return ret;
}
STATIC loff_t
xfs_seek_data(
struct file *file,
loff_t start)
{
struct inode *inode = file->f_mapping->host;
struct xfs_inode *ip = XFS_I(inode);
struct xfs_mount *mp = ip->i_mount;
loff_t uninitialized_var(offset);
xfs_fsize_t isize;
xfs_fileoff_t fsbno;
xfs_filblks_t end;
uint lock;
int error;
lock = xfs_ilock_data_map_shared(ip);
isize = i_size_read(inode);
if (start >= isize) {
error = -ENXIO;
goto out_unlock;
}
/*
* Try to read extents from the first block indicated
* by fsbno to the end block of the file.
*/
fsbno = XFS_B_TO_FSBT(mp, start);
end = XFS_B_TO_FSB(mp, isize);
for (;;) {
struct xfs_bmbt_irec map[2];
int nmap = 2;
unsigned int i;
error = xfs_bmapi_read(ip, fsbno, end - fsbno, map, &nmap,
XFS_BMAPI_ENTIRE);
if (error)
goto out_unlock;
/* No extents at given offset, must be beyond EOF */
if (nmap == 0) {
error = -ENXIO;
goto out_unlock;
}
for (i = 0; i < nmap; i++) {
offset = max_t(loff_t, start,
XFS_FSB_TO_B(mp, map[i].br_startoff));
/* Landed in a data extent */
if (map[i].br_startblock == DELAYSTARTBLOCK ||
(map[i].br_state == XFS_EXT_NORM &&
!isnullstartblock(map[i].br_startblock)))
goto out;
/*
* Landed in an unwritten extent, try to search data
* from page cache.
*/
if (map[i].br_state == XFS_EXT_UNWRITTEN) {
if (xfs_find_get_desired_pgoff(inode, &map[i],
DATA_OFF, &offset))
goto out;
}
}
/*
* map[0] is hole or its an unwritten extent but
* without data in page cache. Probably means that
* we are reading after EOF if nothing in map[1].
*/
if (nmap == 1) {
error = -ENXIO;
goto out_unlock;
}
ASSERT(i > 1);
/*
* Nothing was found, proceed to the next round of search
* if reading offset not beyond or hit EOF.
*/
fsbno = map[i - 1].br_startoff + map[i - 1].br_blockcount;
start = XFS_FSB_TO_B(mp, fsbno);
if (start >= isize) {
error = -ENXIO;
goto out_unlock;
}
}
out:
offset = vfs_setpos(file, offset, inode->i_sb->s_maxbytes);
out_unlock:
xfs_iunlock(ip, lock);
if (error)
return error;
return offset;
}
static int ext4_destroy_inline_data_nolock(handle_t *handle,
struct inode *inode)
{
struct ext4_inode_info *ei = EXT4_I(inode);
struct ext4_xattr_ibody_find is = {
.s = { .not_found = 0, },
};
struct ext4_xattr_info i = {
.name_index = EXT4_XATTR_INDEX_SYSTEM,
.name = EXT4_XATTR_SYSTEM_DATA,
.value = NULL,
.value_len = 0,
};
int error;
if (!ei->i_inline_off)
return 0;
error = ext4_get_inode_loc(inode, &is.iloc);
if (error)
return error;
error = ext4_xattr_ibody_find(inode, &i, &is);
if (error)
goto out;
BUFFER_TRACE(is.iloc.bh, "get_write_access");
error = ext4_journal_get_write_access(handle, is.iloc.bh);
if (error)
goto out;
error = ext4_xattr_ibody_inline_set(handle, inode, &i, &is);
if (error)
goto out;
memset((void *)ext4_raw_inode(&is.iloc)->i_block,
0, EXT4_MIN_INLINE_DATA_SIZE);
if (EXT4_HAS_INCOMPAT_FEATURE(inode->i_sb,
EXT4_FEATURE_INCOMPAT_EXTENTS)) {
if (S_ISDIR(inode->i_mode) ||
S_ISREG(inode->i_mode) || S_ISLNK(inode->i_mode)) {
ext4_set_inode_flag(inode, EXT4_INODE_EXTENTS);
ext4_ext_tree_init(handle, inode);
}
}
ext4_clear_inode_flag(inode, EXT4_INODE_INLINE_DATA);
get_bh(is.iloc.bh);
error = ext4_mark_iloc_dirty(handle, inode, &is.iloc);
EXT4_I(inode)->i_inline_off = 0;
EXT4_I(inode)->i_inline_size = 0;
ext4_clear_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA);
out:
brelse(is.iloc.bh);
if (error == -ENODATA)
error = 0;
return error;
}
static int ext4_read_inline_page(struct inode *inode, struct page *page)
{
void *kaddr;
int ret = 0;
size_t len;
struct ext4_iloc iloc;
BUG_ON(!PageLocked(page));
BUG_ON(!ext4_has_inline_data(inode));
BUG_ON(page->index);
if (!EXT4_I(inode)->i_inline_off) {
ext4_warning(inode->i_sb, "inode %lu doesn't have inline data.",
inode->i_ino);
goto out;
}
ret = ext4_get_inode_loc(inode, &iloc);
if (ret)
goto out;
len = min_t(size_t, ext4_get_inline_size(inode), i_size_read(inode));
kaddr = kmap_atomic(page);
ret = ext4_read_inline_data(inode, kaddr, len, &iloc);
flush_dcache_page(page);
kunmap_atomic(kaddr);
zero_user_segment(page, len, PAGE_CACHE_SIZE);
SetPageUptodate(page);
brelse(iloc.bh);
out:
return ret;
}
int ext4_ext_migrate(struct inode *inode)
{
handle_t *handle;
int retval = 0, i;
__le32 *i_data;
ext4_lblk_t blk_count = 0;
struct ext4_inode_info *ei;
struct inode *tmp_inode = NULL;
struct list_blocks_struct lb;
unsigned long max_entries;
__u32 goal;
/*
* If the filesystem does not support extents, or the inode
* already is extent-based, error out.
*/
if (!EXT4_HAS_INCOMPAT_FEATURE(inode->i_sb,
EXT4_FEATURE_INCOMPAT_EXTENTS) ||
(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)))
return -EINVAL;
if (S_ISLNK(inode->i_mode) && inode->i_blocks == 0)
/*
* don't migrate fast symlink
*/
return retval;
handle = ext4_journal_start(inode,
EXT4_DATA_TRANS_BLOCKS(inode->i_sb) +
EXT4_INDEX_EXTRA_TRANS_BLOCKS + 3 +
EXT4_MAXQUOTAS_INIT_BLOCKS(inode->i_sb)
+ 1);
if (IS_ERR(handle)) {
retval = PTR_ERR(handle);
return retval;
}
goal = (((inode->i_ino - 1) / EXT4_INODES_PER_GROUP(inode->i_sb)) *
EXT4_INODES_PER_GROUP(inode->i_sb)) + 1;
tmp_inode = ext4_new_inode(handle, inode->i_sb->s_root->d_inode,
S_IFREG, NULL, goal);
if (IS_ERR(tmp_inode)) {
retval = -ENOMEM;
ext4_journal_stop(handle);
return retval;
}
i_size_write(tmp_inode, i_size_read(inode));
/*
* Set the i_nlink to zero so it will be deleted later
* when we drop inode reference.
*/
tmp_inode->i_nlink = 0;
ext4_ext_tree_init(handle, tmp_inode);
ext4_orphan_add(handle, tmp_inode);
ext4_journal_stop(handle);
/*
* start with one credit accounted for
* superblock modification.
*
* For the tmp_inode we already have commited the
* trascation that created the inode. Later as and
* when we add extents we extent the journal
*/
/*
* Even though we take i_mutex we can still cause block
* allocation via mmap write to holes. If we have allocated
* new blocks we fail migrate. New block allocation will
* clear EXT4_STATE_EXT_MIGRATE flag. The flag is updated
* with i_data_sem held to prevent racing with block
* allocation.
*/
down_read((&EXT4_I(inode)->i_data_sem));
ext4_set_inode_state(inode, EXT4_STATE_EXT_MIGRATE);
up_read((&EXT4_I(inode)->i_data_sem));
handle = ext4_journal_start(inode, 1);
if (IS_ERR(handle)) {
/*
* It is impossible to update on-disk structures without
* a handle, so just rollback in-core changes and live other
* work to orphan_list_cleanup()
*/
ext4_orphan_del(NULL, tmp_inode);
retval = PTR_ERR(handle);
goto out;
}
ei = EXT4_I(inode);
i_data = ei->i_data;
memset(&lb, 0, sizeof(lb));
/* 32 bit block address 4 bytes */
max_entries = inode->i_sb->s_blocksize >> 2;
for (i = 0; i < EXT4_NDIR_BLOCKS; i++, blk_count++) {
if (i_data[i]) {
retval = update_extent_range(handle, tmp_inode,
le32_to_cpu(i_data[i]),
blk_count, &lb);
if (retval)
goto err_out;
}
}
if (i_data[EXT4_IND_BLOCK]) {
retval = update_ind_extent_range(handle, tmp_inode,
le32_to_cpu(i_data[EXT4_IND_BLOCK]),
&blk_count, &lb);
if (retval)
goto err_out;
} else
blk_count += max_entries;
if (i_data[EXT4_DIND_BLOCK]) {
retval = update_dind_extent_range(handle, tmp_inode,
le32_to_cpu(i_data[EXT4_DIND_BLOCK]),
&blk_count, &lb);
if (retval)
goto err_out;
} else
blk_count += max_entries * max_entries;
if (i_data[EXT4_TIND_BLOCK]) {
retval = update_tind_extent_range(handle, tmp_inode,
le32_to_cpu(i_data[EXT4_TIND_BLOCK]),
&blk_count, &lb);
if (retval)
goto err_out;
}
/*
* Build the last extent
*/
retval = finish_range(handle, tmp_inode, &lb);
err_out:
if (retval)
/*
* Failure case delete the extent information with the
* tmp_inode
*/
free_ext_block(handle, tmp_inode);
else {
retval = ext4_ext_swap_inode_data(handle, inode, tmp_inode);
if (retval)
/*
* if we fail to swap inode data free the extent
* details of the tmp inode
*/
free_ext_block(handle, tmp_inode);
}
/* We mark the tmp_inode dirty via ext4_ext_tree_init. */
if (ext4_journal_extend(handle, 1) != 0)
ext4_journal_restart(handle, 1);
/*
* Mark the tmp_inode as of size zero
*/
i_size_write(tmp_inode, 0);
/*
* set the i_blocks count to zero
* so that the ext4_delete_inode does the
* right job
*
* We don't need to take the i_lock because
* the inode is not visible to user space.
*/
tmp_inode->i_blocks = 0;
/* Reset the extent details */
ext4_ext_tree_init(handle, tmp_inode);
ext4_journal_stop(handle);
out:
unlock_new_inode(tmp_inode);
iput(tmp_inode);
return retval;
}
/**
* ecryptfs_open
* @inode: inode speciying file to open
* @file: Structure to return filled in
*
* Opens the file specified by inode.
*
* Returns zero on success; non-zero otherwise
*/
static int ecryptfs_open(struct inode *inode, struct file *file)
{
int rc = 0;
struct ecryptfs_crypt_stat *crypt_stat = NULL;
struct ecryptfs_mount_crypt_stat *mount_crypt_stat;
struct dentry *ecryptfs_dentry = file->f_path.dentry;
/* Private value of ecryptfs_dentry allocated in
* ecryptfs_lookup() */
struct dentry *lower_dentry;
struct ecryptfs_file_info *file_info;
mount_crypt_stat = &ecryptfs_superblock_to_private(
ecryptfs_dentry->d_sb)->mount_crypt_stat;
if ((mount_crypt_stat->flags & ECRYPTFS_ENCRYPTED_VIEW_ENABLED)
&& ((file->f_flags & O_WRONLY) || (file->f_flags & O_RDWR)
|| (file->f_flags & O_CREAT) || (file->f_flags & O_TRUNC)
|| (file->f_flags & O_APPEND))) {
printk(KERN_WARNING "Mount has encrypted view enabled; "
"files may only be read\n");
rc = -EPERM;
goto out;
}
/* Released in ecryptfs_release or end of function if failure */
file_info = kmem_cache_zalloc(ecryptfs_file_info_cache, GFP_KERNEL);
ecryptfs_set_file_private(file, file_info);
if (!file_info) {
ecryptfs_printk(KERN_ERR,
"Error attempting to allocate memory\n");
rc = -ENOMEM;
goto out;
}
lower_dentry = ecryptfs_dentry_to_lower(ecryptfs_dentry);
crypt_stat = &ecryptfs_inode_to_private(inode)->crypt_stat;
mutex_lock(&crypt_stat->cs_mutex);
if (!(crypt_stat->flags & ECRYPTFS_POLICY_APPLIED)) {
ecryptfs_printk(KERN_DEBUG, "Setting flags for stat...\n");
/* Policy code enabled in future release */
crypt_stat->flags |= (ECRYPTFS_POLICY_APPLIED
| ECRYPTFS_ENCRYPTED);
}
mutex_unlock(&crypt_stat->cs_mutex);
rc = ecryptfs_get_lower_file(ecryptfs_dentry, inode);
if (rc) {
printk(KERN_ERR "%s: Error attempting to initialize "
"the lower file for the dentry with name "
"[%s]; rc = [%d]\n", __func__,
ecryptfs_dentry->d_name.name, rc);
goto out_free;
}
if ((ecryptfs_inode_to_private(inode)->lower_file->f_flags & O_ACCMODE)
== O_RDONLY && (file->f_flags & O_ACCMODE) != O_RDONLY) {
rc = -EPERM;
printk(KERN_WARNING "%s: Lower file is RO; eCryptfs "
"file must hence be opened RO\n", __func__);
goto out_put;
}
ecryptfs_set_file_lower(
file, ecryptfs_inode_to_private(inode)->lower_file);
if (S_ISDIR(ecryptfs_dentry->d_inode->i_mode)) {
ecryptfs_printk(KERN_DEBUG, "This is a directory\n");
mutex_lock(&crypt_stat->cs_mutex);
crypt_stat->flags &= ~(ECRYPTFS_ENCRYPTED);
mutex_unlock(&crypt_stat->cs_mutex);
rc = 0;
goto out;
}
rc = read_or_initialize_metadata(ecryptfs_dentry);
if (rc)
goto out_put;
ecryptfs_printk(KERN_DEBUG, "inode w/ addr = [0x%p], i_ino = "
"[0x%.16lx] size: [0x%.16llx]\n", inode, inode->i_ino,
(unsigned long long)i_size_read(inode));
goto out;
out_put:
ecryptfs_put_lower_file(inode);
out_free:
kmem_cache_free(ecryptfs_file_info_cache,
ecryptfs_file_to_private(file));
out:
return rc;
}
int __generic_block_fiemap(struct inode *inode,
struct fiemap_extent_info *fieinfo, loff_t start,
loff_t len, get_block_t *get_block)
{
struct buffer_head map_bh;
sector_t start_blk, last_blk;
loff_t isize = i_size_read(inode);
u64 logical = 0, phys = 0, size = 0;
u32 flags = FIEMAP_EXTENT_MERGED;
bool past_eof = false, whole_file = false;
int ret = 0;
ret = fiemap_check_flags(fieinfo, FIEMAP_FLAG_SYNC);
if (ret)
return ret;
/*
* Either the i_mutex or other appropriate locking needs to be held
* since we expect isize to not change at all through the duration of
* this call.
*/
if (len >= isize) {
whole_file = true;
len = isize;
}
/*
* Some filesystems can't deal with being asked to map less than
* blocksize, so make sure our len is at least block length.
*/
if (logical_to_blk(inode, len) == 0)
len = blk_to_logical(inode, 1);
start_blk = logical_to_blk(inode, start);
last_blk = logical_to_blk(inode, start + len - 1);
do {
/*
* we set b_size to the total size we want so it will map as
* many contiguous blocks as possible at once
*/
memset(&map_bh, 0, sizeof(struct buffer_head));
map_bh.b_size = len;
ret = get_block(inode, start_blk, &map_bh, 0);
if (ret)
break;
/* HOLE */
if (!buffer_mapped(&map_bh)) {
start_blk++;
/*
* We want to handle the case where there is an
* allocated block at the front of the file, and then
* nothing but holes up to the end of the file properly,
* to make sure that extent at the front gets properly
* marked with FIEMAP_EXTENT_LAST
*/
if (!past_eof &&
blk_to_logical(inode, start_blk) >= isize)
past_eof = 1;
/*
* First hole after going past the EOF, this is our
* last extent
*/
if (past_eof && size) {
flags = FIEMAP_EXTENT_MERGED|FIEMAP_EXTENT_LAST;
ret = fiemap_fill_next_extent(fieinfo, logical,
phys, size,
flags);
} else if (size) {
ret = fiemap_fill_next_extent(fieinfo, logical,
phys, size, flags);
size = 0;
}
/* if we have holes up to/past EOF then we're done */
if (start_blk > last_blk || past_eof || ret)
break;
} else {
/*
* We have gone over the length of what we wanted to
* map, and it wasn't the entire file, so add the extent
* we got last time and exit.
*
* This is for the case where say we want to map all the
* way up to the second to the last block in a file, but
* the last block is a hole, making the second to last
* block FIEMAP_EXTENT_LAST. In this case we want to
* see if there is a hole after the second to last block
* so we can mark it properly. If we found data after
* we exceeded the length we were requesting, then we
* are good to go, just add the extent to the fieinfo
* and break
*/
if (start_blk > last_blk && !whole_file) {
ret = fiemap_fill_next_extent(fieinfo, logical,
phys, size,
flags);
break;
}
/*
* if size != 0 then we know we already have an extent
* to add, so add it.
*/
if (size) {
ret = fiemap_fill_next_extent(fieinfo, logical,
phys, size,
flags);
if (ret)
break;
}
logical = blk_to_logical(inode, start_blk);
phys = blk_to_logical(inode, map_bh.b_blocknr);
size = map_bh.b_size;
flags = FIEMAP_EXTENT_MERGED;
start_blk += logical_to_blk(inode, size);
/*
* If we are past the EOF, then we need to make sure as
* soon as we find a hole that the last extent we found
* is marked with FIEMAP_EXTENT_LAST
*/
if (!past_eof && logical + size >= isize)
past_eof = true;
}
cond_resched();
} while (1);
/* If ret is 1 then we just hit the end of the extent array */
if (ret == 1)
ret = 0;
return ret;
}
/*search pattern*/
int search_pat(void *arg){
int rc = 0;
struct strops_args *kptr = (struct strops_args *)arg;
struct file *readFilePtr = NULL;/*for input file pointer.*/
size_t inputInodeSize = 0;/* for get size of input file*/
mm_segment_t oldfs;
char *bytes;/* bytes from input file*/
char *temp;
char *res;
int page_count = 0;
readFilePtr = filp_open(kptr->in_file, O_EXCL, 0);
if(!readFilePtr || IS_ERR(readFilePtr)){
printk("Open input file error: %d\n", (int)PTR_ERR(readFilePtr));
rc = -ENOENT;
readFilePtr = NULL;
goto out;
}
rc = isInFileValid(readFilePtr);
if(rc < 0)
goto close_input_file;
inputInodeSize = i_size_read(readFilePtr->f_path.dentry->d_inode);
bytes = (char *)kmalloc(PAGE * sizeof(char) + 1, GFP_KERNEL);
if(IS_ERR(bytes)){
rc = -ENOMEM;
goto close_input_file;
}
oldfs = get_fs();
set_fs(get_ds());
while((inputInodeSize - readFilePtr->f_pos) > 0){
if(kptr->res_len == MAX_OCC){
printk("find more than maximum(100) number of results! Truncate.\n");
break;
}
if(inputInodeSize - readFilePtr->f_pos >= PAGE){
rc = readFilePtr->f_op->read(readFilePtr, bytes, PAGE, &readFilePtr->f_pos);
if(rc < 0){
rc = -EPERM;
printk("Read Blocks failed!\n");
goto set_oldfs;
}
bytes[PAGE] = '\0';
temp = bytes;
while((res = strstr(temp, kptr->old_str)) != NULL){
int dis = res - bytes;
if(kptr->res_len == MAX_OCC){
printk("find more than maximum(100) number of results! Truncate.\n");
goto set_oldfs;
}
if(page_count == 0){
kptr->res[(kptr->res_len)++] = dis;
}
else{
kptr->res[(kptr->res_len)++] = dis - kptr->old_len * page_count + (PAGE) * page_count;
}
temp = kptr->old_len + res;
}
page_count++;
readFilePtr->f_pos -= kptr->old_len;
}else{
int rest = inputInodeSize - readFilePtr->f_pos;
rc = readFilePtr->f_op->read(readFilePtr, bytes, rest, &readFilePtr->f_pos);
if(rc < 0){
rc = -EPERM;
printk("Read Blocks failed!\n");
goto set_oldfs;
}
bytes[rest] = '\0';
temp = bytes;
while((res = strstr(temp, kptr->old_str)) != NULL){
int dis = res - bytes;
if(kptr->res_len == MAX_OCC){
printk("find more than maximum(100) number of results! Truncate.\n");
goto set_oldfs;
}
if(page_count != 0)
kptr->res[(kptr->res_len)++] = dis - kptr->old_len * page_count + (PAGE) * page_count;
else
kptr->res[(kptr->res_len)++] = dis;
temp = kptr->old_len + res;
}
}
}
set_oldfs:
set_fs(oldfs);
kfree(bytes);
close_input_file:
filp_close(readFilePtr, NULL);
out:
return rc;
}
/*write pattern*/
int write_pat(void *arg, int mode){
int i;
int rc = 0;
struct strops_args *kptr = (struct strops_args *)arg;
struct file *readFilePtr = NULL;/*for input file pointer.*/
size_t inputInodeSize = 0;/* for get size of input file*/
struct file *writeFilePtr = NULL;/*for output file pointer.*/
char *out_dir = "temp.txt";
mm_segment_t oldfs;
char *bytes;/* bytes from input file*/
char *temp;
if(mode == 0){ /* write to temp file*/
readFilePtr = filp_open(kptr->in_file, O_EXCL, 0);
}
else{
readFilePtr = filp_open(out_dir, O_EXCL, 0);
}
if(!readFilePtr || IS_ERR(readFilePtr)){
printk("Open input file error: %d\n", (int)PTR_ERR(readFilePtr));
rc = -ENOENT;
readFilePtr = NULL;
goto out;
}
rc = isInFileValid(readFilePtr);
if(rc < 0)
goto close_input_file;
inputInodeSize = i_size_read(readFilePtr->f_path.dentry->d_inode);
/*check whether can open:*/
if(mode == 0){
writeFilePtr = filp_open(out_dir, O_WRONLY|O_CREAT|O_TRUNC, 0644);
}else{
writeFilePtr = filp_open(kptr->in_file, O_WRONLY|O_CREAT|O_TRUNC, 0644);
}
if(!writeFilePtr || IS_ERR(writeFilePtr)){
printk("Open output file error: %d\n", (int)PTR_ERR(writeFilePtr));
rc = -ENOENT;
writeFilePtr = NULL;
goto close_input_file;
}
rc = isOutFileValid(writeFilePtr);
if(rc < 0)
goto close_output_file;
bytes = (char *)kmalloc(PAGE * sizeof(char) + 1, GFP_KERNEL);
if(IS_ERR(bytes)){
rc = -ENOMEM;
goto close_output_file;
}
temp = (char *)kmalloc(PAGE * sizeof(char) + 1, GFP_KERNEL);
if(IS_ERR(temp)){
rc = -ENOMEM;
goto free_bytes;
}
oldfs = get_fs();
set_fs(get_ds());
if(mode == 0){/*write new file to temp*/
if(kptr->flag == 1){/* delete pattern*/
char *index;
int page_count = 1;
int dist = 0;
while((inputInodeSize - readFilePtr->f_pos) > 0){
if(inputInodeSize - readFilePtr->f_pos >= PAGE){
int pos = readFilePtr->f_pos;
dist = 0;
rc = readFilePtr->f_op->read(readFilePtr, bytes, PAGE, &readFilePtr->f_pos);
if(rc < 0){
rc = -EPERM;
printk("Read Blocks failed!\n");
goto set_oldfs;
}
bytes[PAGE] = '\0';
index = bytes;
for(i = 0; i < kptr->res_len; i++){
if(kptr->res[i] < pos) continue;
if(kptr->res[i] > page_count * PAGE) continue;
dist = kptr->res[i] % PAGE - (index - bytes);
strncpy(temp, index, dist);
temp[dist] = '\0';
index += dist + kptr->old_len;
rc = writeFilePtr->f_op->write(writeFilePtr, temp ,strlen(temp), &writeFilePtr->f_pos);
if(rc < 0){
rc = -EPERM;
printk("Write the hash key to header of output file reading failed!\n");
goto set_oldfs;
}
}
strncpy(temp, index, PAGE - (index - bytes));
temp[PAGE - (index - bytes)] = '\0';
rc = writeFilePtr->f_op->write(writeFilePtr, temp ,strlen(temp), &writeFilePtr->f_pos);
if(rc < 0){
rc = -EPERM;
printk("Write the hash key to header of output file reading failed!\n");
goto set_oldfs;
}
page_count++;
}else{
int rest = inputInodeSize - readFilePtr->f_pos;
int pos = readFilePtr->f_pos;
dist = 0;
rc = readFilePtr->f_op->read(readFilePtr, bytes, rest, &readFilePtr->f_pos);
if(rc < 0){
rc = -EPERM;
printk("Read Blocks failed!\n");
goto set_oldfs;
}
bytes[rest] = '\0';
index = bytes;
for(i = 0; i < kptr->res_len; i++){
if(kptr->res[i] < pos) continue;
dist = kptr->res[i] % PAGE - (index - bytes);
strncpy(temp, index, dist);
temp[dist] = '\0';
index += dist + kptr->old_len;
rc = writeFilePtr->f_op->write(writeFilePtr, temp ,strlen(temp), &writeFilePtr->f_pos);
if(rc < 0){
rc = -EPERM;
printk("Write the hash key to header of output file reading failed!\n");
goto set_oldfs;
}
}
strncpy(temp, index, rest - (index - bytes));
temp[rest - (index - bytes)] = '\0';
rc = writeFilePtr->f_op->write(writeFilePtr, temp ,strlen(temp), &writeFilePtr->f_pos);
if(rc < 0){
rc = -EPERM;
printk("Write the hash key to header of output file reading failed!\n");
goto set_oldfs;
}
}
}
}
if(kptr->flag == 2){/* replace pattern */
char *index;
int page_count = 1;
int dist = 0;
while((inputInodeSize - readFilePtr->f_pos) > 0){
if(inputInodeSize - readFilePtr->f_pos >= PAGE){
int pos = readFilePtr->f_pos;
dist = 0;
rc = readFilePtr->f_op->read(readFilePtr, bytes, PAGE, &readFilePtr->f_pos);
if(rc < 0){
rc = -EPERM;
printk("Read Blocks failed!\n");
goto set_oldfs;
}
bytes[PAGE] = '\0';
index = bytes;
for(i = 0; i < kptr->res_len; i++){
if(kptr->res[i] < pos) continue;
if(kptr->res[i] > page_count * PAGE) continue;
dist = kptr->res[i] % PAGE - (index - bytes);
strncpy(temp, index, dist);
temp[dist] = '\0';
index += dist + kptr->old_len;
rc = writeFilePtr->f_op->write(writeFilePtr, temp ,strlen(temp), &writeFilePtr->f_pos);
if(rc < 0){
rc = -EPERM;
printk("Write the hash key to header of output file reading failed!\n");
goto set_oldfs;
}
strncpy(temp, kptr->new_str, kptr->new_len);
temp[kptr->new_len] = '\0';
rc = writeFilePtr->f_op->write(writeFilePtr, temp ,strlen(temp), &writeFilePtr->f_pos);
if(rc < 0){
rc = -EPERM;
printk("Write the hash key to header of output file reading failed!\n");
goto set_oldfs;
}
}
strncpy(temp, index, PAGE - (index - bytes));
temp[PAGE - (index - bytes)] = '\0';
rc = writeFilePtr->f_op->write(writeFilePtr, temp ,strlen(temp), &writeFilePtr->f_pos);
if(rc < 0){
rc = -EPERM;
printk("Write the hash key to header of output file reading failed!\n");
goto set_oldfs;
}
page_count++;
}else{
int rest = inputInodeSize - readFilePtr->f_pos;
int pos = readFilePtr->f_pos;
dist = 0;
rc = readFilePtr->f_op->read(readFilePtr, bytes, rest, &readFilePtr->f_pos);
if(rc < 0){
rc = -EPERM;
printk("Read Blocks failed!\n");
goto set_oldfs;
}
bytes[rest] = '\0';
index = bytes;
for(i = 0; i < kptr->res_len; i++){
if(kptr->res[i] < pos) continue;
dist = kptr->res[i] % PAGE - (index - bytes);
strncpy(temp, index, dist);
temp[dist] = '\0';
index += dist + kptr->old_len;
rc = writeFilePtr->f_op->write(writeFilePtr, temp ,strlen(temp), &writeFilePtr->f_pos);
if(rc < 0){
rc = -EPERM;
printk("Write the hash key to header of output file reading failed!\n");
goto set_oldfs;
}
strncpy(temp, kptr->new_str, kptr->new_len);
temp[kptr->new_len] = '\0';
rc = writeFilePtr->f_op->write(writeFilePtr, temp ,strlen(temp), &writeFilePtr->f_pos);
if(rc < 0){
rc = -EPERM;
printk("Write the hash key to header of output file reading failed!\n");
goto set_oldfs;
}
}
strncpy(temp, index, rest - (index - bytes));
temp[rest - (index - bytes)] = '\0';
rc = writeFilePtr->f_op->write(writeFilePtr, temp ,strlen(temp), &writeFilePtr->f_pos);
if(rc < 0){
rc = -EPERM;
printk("Write the hash key to header of output file reading failed!\n");
goto set_oldfs;
}
}
}
}
/*goto mode 1 to write back*/
rc = write_pat(kptr, 1);
}
if(mode == 1){/*write temp to new file*/
while((inputInodeSize - readFilePtr->f_pos) > 0){
if(inputInodeSize - readFilePtr->f_pos >= PAGE){
rc = readFilePtr->f_op->read(readFilePtr, bytes, PAGE, &readFilePtr->f_pos);
if(rc < 0){
rc = -EPERM;
printk("Read Blocks failed!\n");
goto set_oldfs;
}
bytes[PAGE] = '\0';
rc = writeFilePtr->f_op->write(writeFilePtr, bytes ,PAGE, &writeFilePtr->f_pos);
if(rc < 0){
rc = -EPERM;
printk("Write the hash key to header of output file reading failed!\n");
goto set_oldfs;
}
}else{
int rest = inputInodeSize - readFilePtr->f_pos;
rc = readFilePtr->f_op->read(readFilePtr, bytes, rest, &readFilePtr->f_pos);
if(rc < 0){
rc = -EPERM;
printk("Read Blocks failed!\n");
goto set_oldfs;
}
bytes[rest] = '\0';
rc = writeFilePtr->f_op->write(writeFilePtr, bytes ,rest, &writeFilePtr->f_pos);
if(rc < 0){
rc = -EPERM;
printk("Write the hash key to header of output file reading failed!\n");
goto set_oldfs;
}
}
}
if(kptr->flag == 1){printk("Deletion Succeed!\n"); kptr->flag = -1;}
if(kptr->flag == 2){printk("Replacement Succeed!\n");kptr->flag = -2;}
if ((rc = vfs_unlink(readFilePtr->f_path.dentry->d_parent->d_inode, readFilePtr->f_path.dentry, NULL)) < 0)
printk("vfs_unlink failed\n");
}
set_oldfs:
set_fs(oldfs);
kfree(temp);
free_bytes:
kfree(bytes);
close_output_file:
filp_close(writeFilePtr, NULL);
close_input_file:
filp_close(readFilePtr, NULL);
out:
return rc;
}
static int fd_configure_device(struct se_device *dev)
{
struct fd_dev *fd_dev = FD_DEV(dev);
struct fd_host *fd_host = dev->se_hba->hba_ptr;
struct file *file;
struct inode *inode = NULL;
int flags, ret = -EINVAL;
if (!(fd_dev->fbd_flags & FBDF_HAS_PATH)) {
pr_err("Missing fd_dev_name=\n");
return -EINVAL;
}
/*
* Use O_DSYNC by default instead of O_SYNC to forgo syncing
* of pure timestamp updates.
*/
flags = O_RDWR | O_CREAT | O_LARGEFILE | O_DSYNC;
/*
* Optionally allow fd_buffered_io=1 to be enabled for people
* who want use the fs buffer cache as an WriteCache mechanism.
*
* This means that in event of a hard failure, there is a risk
* of silent data-loss if the SCSI client has *not* performed a
* forced unit access (FUA) write, or issued SYNCHRONIZE_CACHE
* to write-out the entire device cache.
*/
if (fd_dev->fbd_flags & FDBD_HAS_BUFFERED_IO_WCE) {
pr_debug("FILEIO: Disabling O_DSYNC, using buffered FILEIO\n");
flags &= ~O_DSYNC;
}
file = filp_open(fd_dev->fd_dev_name, flags, 0600);
if (IS_ERR(file)) {
pr_err("filp_open(%s) failed\n", fd_dev->fd_dev_name);
ret = PTR_ERR(file);
goto fail;
}
fd_dev->fd_file = file;
/*
* If using a block backend with this struct file, we extract
* fd_dev->fd_[block,dev]_size from struct block_device.
*
* Otherwise, we use the passed fd_size= from configfs
*/
inode = file->f_mapping->host;
if (S_ISBLK(inode->i_mode)) {
struct request_queue *q = bdev_get_queue(inode->i_bdev);
unsigned long long dev_size;
fd_dev->fd_block_size = bdev_logical_block_size(inode->i_bdev);
/*
* Determine the number of bytes from i_size_read() minus
* one (1) logical sector from underlying struct block_device
*/
dev_size = (i_size_read(file->f_mapping->host) -
fd_dev->fd_block_size);
pr_debug("FILEIO: Using size: %llu bytes from struct"
" block_device blocks: %llu logical_block_size: %d\n",
dev_size, div_u64(dev_size, fd_dev->fd_block_size),
fd_dev->fd_block_size);
/*
* Check if the underlying struct block_device request_queue supports
* the QUEUE_FLAG_DISCARD bit for UNMAP/WRITE_SAME in SCSI + TRIM
* in ATA and we need to set TPE=1
*/
if (blk_queue_discard(q)) {
dev->dev_attrib.max_unmap_lba_count =
q->limits.max_discard_sectors;
/*
* Currently hardcoded to 1 in Linux/SCSI code..
*/
dev->dev_attrib.max_unmap_block_desc_count = 1;
dev->dev_attrib.unmap_granularity =
q->limits.discard_granularity >> 9;
dev->dev_attrib.unmap_granularity_alignment =
q->limits.discard_alignment;
pr_debug("IFILE: BLOCK Discard support available,"
" disabled by default\n");
}
/*
* Enable write same emulation for IBLOCK and use 0xFFFF as
* the smaller WRITE_SAME(10) only has a two-byte block count.
*/
dev->dev_attrib.max_write_same_len = 0xFFFF;
if (blk_queue_nonrot(q))
dev->dev_attrib.is_nonrot = 1;
} else {
if (!(fd_dev->fbd_flags & FBDF_HAS_SIZE)) {
ssize_t /* bytes written, or (-) error */
xfs_write(
bhv_desc_t *bdp,
struct kiocb *iocb,
const struct iovec *iovp,
unsigned int nsegs,
loff_t *offset,
int ioflags,
cred_t *credp)
{
struct file *file = iocb->ki_filp;
struct address_space *mapping = file->f_mapping;
struct inode *inode = mapping->host;
unsigned long segs = nsegs;
xfs_inode_t *xip;
xfs_mount_t *mp;
ssize_t ret = 0, error = 0;
xfs_fsize_t isize, new_size;
xfs_iocore_t *io;
vnode_t *vp;
unsigned long seg;
int iolock;
int eventsent = 0;
vrwlock_t locktype;
size_t ocount = 0, count;
loff_t pos;
int need_isem = 1, need_flush = 0;
XFS_STATS_INC(xs_write_calls);
vp = BHV_TO_VNODE(bdp);
xip = XFS_BHVTOI(bdp);
for (seg = 0; seg < segs; seg++) {
const struct iovec *iv = &iovp[seg];
/*
* If any segment has a negative length, or the cumulative
* length ever wraps negative then return -EINVAL.
*/
ocount += iv->iov_len;
if (unlikely((ssize_t)(ocount|iv->iov_len) < 0))
return -EINVAL;
if (access_ok(VERIFY_READ, iv->iov_base, iv->iov_len))
continue;
if (seg == 0)
return -EFAULT;
segs = seg;
ocount -= iv->iov_len; /* This segment is no good */
break;
}
count = ocount;
pos = *offset;
if (count == 0)
return 0;
io = &xip->i_iocore;
mp = io->io_mount;
if (XFS_FORCED_SHUTDOWN(mp))
return -EIO;
fs_check_frozen(vp->v_vfsp, SB_FREEZE_WRITE);
if (ioflags & IO_ISDIRECT) {
xfs_buftarg_t *target =
(xip->i_d.di_flags & XFS_DIFLAG_REALTIME) ?
mp->m_rtdev_targp : mp->m_ddev_targp;
if ((pos & target->pbr_smask) || (count & target->pbr_smask))
return XFS_ERROR(-EINVAL);
if (!VN_CACHED(vp) && pos < i_size_read(inode))
need_isem = 0;
if (VN_CACHED(vp))
need_flush = 1;
}
relock:
if (need_isem) {
iolock = XFS_IOLOCK_EXCL;
locktype = VRWLOCK_WRITE;
down(&inode->i_sem);
} else {
iolock = XFS_IOLOCK_SHARED;
locktype = VRWLOCK_WRITE_DIRECT;
}
xfs_ilock(xip, XFS_ILOCK_EXCL|iolock);
isize = i_size_read(inode);
if (file->f_flags & O_APPEND)
*offset = isize;
start:
error = -generic_write_checks(file, &pos, &count,
S_ISBLK(inode->i_mode));
if (error) {
xfs_iunlock(xip, XFS_ILOCK_EXCL|iolock);
goto out_unlock_isem;
}
new_size = pos + count;
if (new_size > isize)
io->io_new_size = new_size;
if ((DM_EVENT_ENABLED(vp->v_vfsp, xip, DM_EVENT_WRITE) &&
!(ioflags & IO_INVIS) && !eventsent)) {
loff_t savedsize = pos;
int dmflags = FILP_DELAY_FLAG(file);
if (need_isem)
dmflags |= DM_FLAGS_ISEM;
xfs_iunlock(xip, XFS_ILOCK_EXCL);
error = XFS_SEND_DATA(xip->i_mount, DM_EVENT_WRITE, vp,
pos, count,
dmflags, &locktype);
if (error) {
xfs_iunlock(xip, iolock);
goto out_unlock_isem;
}
xfs_ilock(xip, XFS_ILOCK_EXCL);
eventsent = 1;
/*
* The iolock was dropped and reaquired in XFS_SEND_DATA
* so we have to recheck the size when appending.
* We will only "goto start;" once, since having sent the
* event prevents another call to XFS_SEND_DATA, which is
* what allows the size to change in the first place.
*/
if ((file->f_flags & O_APPEND) && savedsize != isize) {
pos = isize = xip->i_d.di_size;
goto start;
}
}
/*
* On Linux, generic_file_write updates the times even if
* no data is copied in so long as the write had a size.
*
* We must update xfs' times since revalidate will overcopy xfs.
*/
if (!(ioflags & IO_INVIS)) {
xfs_ichgtime(xip, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
inode_update_time(inode, 1);
}
/*
* If the offset is beyond the size of the file, we have a couple
* of things to do. First, if there is already space allocated
* we need to either create holes or zero the disk or ...
*
* If there is a page where the previous size lands, we need
* to zero it out up to the new size.
*/
if (pos > isize) {
error = xfs_zero_eof(BHV_TO_VNODE(bdp), io, pos,
isize, pos + count);
if (error) {
xfs_iunlock(xip, XFS_ILOCK_EXCL|iolock);
goto out_unlock_isem;
}
}
xfs_iunlock(xip, XFS_ILOCK_EXCL);
/*
* If we're writing the file then make sure to clear the
* setuid and setgid bits if the process is not being run
* by root. This keeps people from modifying setuid and
* setgid binaries.
*/
if (((xip->i_d.di_mode & S_ISUID) ||
((xip->i_d.di_mode & (S_ISGID | S_IXGRP)) ==
(S_ISGID | S_IXGRP))) &&
!capable(CAP_FSETID)) {
error = xfs_write_clear_setuid(xip);
if (likely(!error))
error = -remove_suid(file->f_dentry);
if (unlikely(error)) {
xfs_iunlock(xip, iolock);
goto out_unlock_isem;
}
}
retry:
/* We can write back this queue in page reclaim */
current->backing_dev_info = mapping->backing_dev_info;
if ((ioflags & IO_ISDIRECT)) {
if (need_flush) {
xfs_inval_cached_trace(io, pos, -1,
ctooff(offtoct(pos)), -1);
VOP_FLUSHINVAL_PAGES(vp, ctooff(offtoct(pos)),
-1, FI_REMAPF_LOCKED);
}
if (need_isem) {
/* demote the lock now the cached pages are gone */
XFS_ILOCK_DEMOTE(mp, io, XFS_IOLOCK_EXCL);
up(&inode->i_sem);
iolock = XFS_IOLOCK_SHARED;
locktype = VRWLOCK_WRITE_DIRECT;
need_isem = 0;
}
xfs_rw_enter_trace(XFS_DIOWR_ENTER, io, (void *)iovp, segs,
*offset, ioflags);
ret = generic_file_direct_write(iocb, iovp,
&segs, pos, offset, count, ocount);
/*
* direct-io write to a hole: fall through to buffered I/O
* for completing the rest of the request.
*/
if (ret >= 0 && ret != count) {
XFS_STATS_ADD(xs_write_bytes, ret);
pos += ret;
count -= ret;
need_isem = 1;
ioflags &= ~IO_ISDIRECT;
xfs_iunlock(xip, iolock);
goto relock;
}
} else {
xfs_rw_enter_trace(XFS_WRITE_ENTER, io, (void *)iovp, segs,
*offset, ioflags);
ret = generic_file_buffered_write(iocb, iovp, segs,
pos, offset, count, ret);
}
current->backing_dev_info = NULL;
if (ret == -EIOCBQUEUED && !(ioflags & IO_ISAIO))
ret = wait_on_sync_kiocb(iocb);
if ((ret == -ENOSPC) &&
DM_EVENT_ENABLED(vp->v_vfsp, xip, DM_EVENT_NOSPACE) &&
!(ioflags & IO_INVIS)) {
xfs_rwunlock(bdp, locktype);
error = XFS_SEND_NAMESP(xip->i_mount, DM_EVENT_NOSPACE, vp,
DM_RIGHT_NULL, vp, DM_RIGHT_NULL, NULL, NULL,
0, 0, 0); /* Delay flag intentionally unused */
if (error)
goto out_unlock_isem;
xfs_rwlock(bdp, locktype);
pos = xip->i_d.di_size;
ret = 0;
goto retry;
}
if (*offset > xip->i_d.di_size) {
xfs_ilock(xip, XFS_ILOCK_EXCL);
if (*offset > xip->i_d.di_size) {
xip->i_d.di_size = *offset;
i_size_write(inode, *offset);
xip->i_update_core = 1;
xip->i_update_size = 1;
}
xfs_iunlock(xip, XFS_ILOCK_EXCL);
}
error = -ret;
if (ret <= 0)
goto out_unlock_internal;
XFS_STATS_ADD(xs_write_bytes, ret);
/* Handle various SYNC-type writes */
if ((file->f_flags & O_SYNC) || IS_SYNC(inode)) {
/*
* If we're treating this as O_DSYNC and we have not updated the
* size, force the log.
*/
if (!(mp->m_flags & XFS_MOUNT_OSYNCISOSYNC) &&
!(xip->i_update_size)) {
xfs_inode_log_item_t *iip = xip->i_itemp;
/*
* If an allocation transaction occurred
* without extending the size, then we have to force
* the log up the proper point to ensure that the
* allocation is permanent. We can't count on
* the fact that buffered writes lock out direct I/O
* writes - the direct I/O write could have extended
* the size nontransactionally, then finished before
* we started. xfs_write_file will think that the file
* didn't grow but the update isn't safe unless the
* size change is logged.
*
* Force the log if we've committed a transaction
* against the inode or if someone else has and
* the commit record hasn't gone to disk (e.g.
* the inode is pinned). This guarantees that
* all changes affecting the inode are permanent
* when we return.
*/
if (iip && iip->ili_last_lsn) {
xfs_log_force(mp, iip->ili_last_lsn,
XFS_LOG_FORCE | XFS_LOG_SYNC);
} else if (xfs_ipincount(xip) > 0) {
xfs_log_force(mp, (xfs_lsn_t)0,
XFS_LOG_FORCE | XFS_LOG_SYNC);
}
} else {
xfs_trans_t *tp;
/*
* O_SYNC or O_DSYNC _with_ a size update are handled
* the same way.
*
* If the write was synchronous then we need to make
* sure that the inode modification time is permanent.
* We'll have updated the timestamp above, so here
* we use a synchronous transaction to log the inode.
* It's not fast, but it's necessary.
*
* If this a dsync write and the size got changed
* non-transactionally, then we need to ensure that
* the size change gets logged in a synchronous
* transaction.
*/
tp = xfs_trans_alloc(mp, XFS_TRANS_WRITE_SYNC);
if ((error = xfs_trans_reserve(tp, 0,
XFS_SWRITE_LOG_RES(mp),
0, 0, 0))) {
/* Transaction reserve failed */
xfs_trans_cancel(tp, 0);
} else {
/* Transaction reserve successful */
xfs_ilock(xip, XFS_ILOCK_EXCL);
xfs_trans_ijoin(tp, xip, XFS_ILOCK_EXCL);
xfs_trans_ihold(tp, xip);
xfs_trans_log_inode(tp, xip, XFS_ILOG_CORE);
xfs_trans_set_sync(tp);
error = xfs_trans_commit(tp, 0, NULL);
xfs_iunlock(xip, XFS_ILOCK_EXCL);
}
if (error)
goto out_unlock_internal;
}
xfs_rwunlock(bdp, locktype);
if (need_isem)
up(&inode->i_sem);
error = sync_page_range(inode, mapping, pos, ret);
if (!error)
error = ret;
return error;
}
out_unlock_internal:
xfs_rwunlock(bdp, locktype);
out_unlock_isem:
if (need_isem)
up(&inode->i_sem);
return -error;
}
/**
* ecryptfs_lookup_and_interpose_lower - Perform a lookup
*/
int ecryptfs_lookup_and_interpose_lower(struct dentry *ecryptfs_dentry,
struct dentry *lower_dentry,
struct inode *ecryptfs_dir_inode,
struct nameidata *ecryptfs_nd)
{
struct dentry *lower_dir_dentry;
struct vfsmount *lower_mnt;
struct inode *lower_inode;
struct ecryptfs_mount_crypt_stat *mount_crypt_stat;
struct ecryptfs_crypt_stat *crypt_stat;
char *page_virt = NULL;
u64 file_size;
int rc = 0;
lower_dir_dentry = lower_dentry->d_parent;
lower_mnt = mntget(ecryptfs_dentry_to_lower_mnt(
ecryptfs_dentry->d_parent));
lower_inode = lower_dentry->d_inode;
fsstack_copy_attr_atime(ecryptfs_dir_inode, lower_dir_dentry->d_inode);
BUG_ON(!atomic_read(&lower_dentry->d_count));
ecryptfs_set_dentry_private(ecryptfs_dentry,
kmem_cache_alloc(ecryptfs_dentry_info_cache,
GFP_KERNEL));
if (!ecryptfs_dentry_to_private(ecryptfs_dentry)) {
rc = -ENOMEM;
printk(KERN_ERR "%s: Out of memory whilst attempting "
"to allocate ecryptfs_dentry_info struct\n",
__func__);
goto out_put;
}
ecryptfs_set_dentry_lower(ecryptfs_dentry, lower_dentry);
ecryptfs_set_dentry_lower_mnt(ecryptfs_dentry, lower_mnt);
if (!lower_dentry->d_inode) {
/* We want to add because we couldn't find in lower */
d_add(ecryptfs_dentry, NULL);
goto out;
}
rc = ecryptfs_interpose(lower_dentry, ecryptfs_dentry,
ecryptfs_dir_inode->i_sb,
ECRYPTFS_INTERPOSE_FLAG_D_ADD);
if (rc) {
printk(KERN_ERR "%s: Error interposing; rc = [%d]\n",
__func__, rc);
goto out;
}
if (S_ISDIR(lower_inode->i_mode))
goto out;
if (S_ISLNK(lower_inode->i_mode))
goto out;
if (special_file(lower_inode->i_mode))
goto out;
if (!ecryptfs_nd)
goto out;
/* Released in this function */
page_virt = kmem_cache_zalloc(ecryptfs_header_cache_2, GFP_USER);
if (!page_virt) {
printk(KERN_ERR "%s: Cannot kmem_cache_zalloc() a page\n",
__func__);
rc = -ENOMEM;
goto out;
}
if (!ecryptfs_inode_to_private(ecryptfs_dentry->d_inode)->lower_file) {
rc = ecryptfs_init_persistent_file(ecryptfs_dentry);
if (rc) {
printk(KERN_ERR "%s: Error attempting to initialize "
"the persistent file for the dentry with name "
"[%s]; rc = [%d]\n", __func__,
ecryptfs_dentry->d_name.name, rc);
goto out_free_kmem;
}
}
crypt_stat = &ecryptfs_inode_to_private(
ecryptfs_dentry->d_inode)->crypt_stat;
/* TODO: lock for crypt_stat comparison */
if (!(crypt_stat->flags & ECRYPTFS_POLICY_APPLIED))
ecryptfs_set_default_sizes(crypt_stat);
rc = ecryptfs_read_and_validate_header_region(page_virt,
ecryptfs_dentry->d_inode);
if (rc) {
memset(page_virt, 0, PAGE_CACHE_SIZE);
rc = ecryptfs_read_and_validate_xattr_region(page_virt,
ecryptfs_dentry);
if (rc) {
rc = 0;
goto out_free_kmem;
}
crypt_stat->flags |= ECRYPTFS_METADATA_IN_XATTR;
}
mount_crypt_stat = &ecryptfs_superblock_to_private(
ecryptfs_dentry->d_sb)->mount_crypt_stat;
if (mount_crypt_stat->flags & ECRYPTFS_ENCRYPTED_VIEW_ENABLED) {
if (crypt_stat->flags & ECRYPTFS_METADATA_IN_XATTR)
file_size = (crypt_stat->metadata_size
+ i_size_read(lower_dentry->d_inode));
else
file_size = i_size_read(lower_dentry->d_inode);
} else {
file_size = get_unaligned_be64(page_virt);
}
i_size_write(ecryptfs_dentry->d_inode, (loff_t)file_size);
out_free_kmem:
kmem_cache_free(ecryptfs_header_cache_2, page_virt);
goto out;
out_put:
dput(lower_dentry);
mntput(lower_mnt);
d_drop(ecryptfs_dentry);
out:
return rc;
}
static struct dentry *squashfs_lookup(struct inode *dir, struct dentry *dentry,
struct nameidata *nd)
{
const unsigned char *name = dentry->d_name.name;
int len = dentry->d_name.len;
struct inode *inode = NULL;
struct squashfs_sb_info *msblk = dir->i_sb->s_fs_info;
struct squashfs_dir_header dirh;
struct squashfs_dir_entry *dire;
u64 block = squashfs_i(dir)->start + msblk->directory_table;
int offset = squashfs_i(dir)->offset;
int err, length = 0, dir_count, size;
TRACE("Entered squashfs_lookup [%llx:%x]\n", block, offset);
dire = kmalloc(sizeof(*dire) + SQUASHFS_NAME_LEN + 1, GFP_KERNEL);
if (dire == NULL) {
ERROR("Failed to allocate squashfs_dir_entry\n");
return ERR_PTR(-ENOMEM);
}
if (len > SQUASHFS_NAME_LEN) {
err = -ENAMETOOLONG;
goto failed;
}
length = get_dir_index_using_name(dir->i_sb, &block, &offset,
squashfs_i(dir)->dir_idx_start,
squashfs_i(dir)->dir_idx_offset,
squashfs_i(dir)->dir_idx_cnt, name, len);
while (length < i_size_read(dir)) {
/*
* Read directory header.
*/
err = squashfs_read_metadata(dir->i_sb, &dirh, &block,
&offset, sizeof(dirh));
if (err < 0)
goto read_failure;
length += sizeof(dirh);
dir_count = le32_to_cpu(dirh.count) + 1;
while (dir_count--) {
/*
* Read directory entry.
*/
err = squashfs_read_metadata(dir->i_sb, dire, &block,
&offset, sizeof(*dire));
if (err < 0)
goto read_failure;
size = le16_to_cpu(dire->size) + 1;
err = squashfs_read_metadata(dir->i_sb, dire->name,
&block, &offset, size);
if (err < 0)
goto read_failure;
length += sizeof(*dire) + size;
if (name[0] < dire->name[0])
goto exit_lookup;
if (len == size && !strncmp(name, dire->name, len)) {
unsigned int blk, off, ino_num;
long long ino;
blk = le32_to_cpu(dirh.start_block);
off = le16_to_cpu(dire->offset);
ino_num = le32_to_cpu(dirh.inode_number) +
(short) le16_to_cpu(dire->inode_number);
ino = SQUASHFS_MKINODE(blk, off);
TRACE("calling squashfs_iget for directory "
"entry %s, inode %x:%x, %d\n", name,
blk, off, ino_num);
inode = squashfs_iget(dir->i_sb, ino, ino_num);
if (IS_ERR(inode)) {
err = PTR_ERR(inode);
goto failed;
}
goto exit_lookup;
}
}
}
exit_lookup:
kfree(dire);
if (inode)
return d_splice_alias(inode, dentry);
d_add(dentry, inode);
return ERR_PTR(0);
read_failure:
ERROR("Unable to read directory block [%llx:%x]\n",
squashfs_i(dir)->start + msblk->directory_table,
squashfs_i(dir)->offset);
failed:
kfree(dire);
return ERR_PTR(err);
}
static long
kdbus_memfd_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
{
void __user *argp = (void __user *)arg;
struct kdbus_memfile *mf = file->private_data;
long ret = 0;
mutex_lock(&mf->lock);
switch (cmd) {
case KDBUS_CMD_MEMFD_SIZE_GET: {
u64 size = i_size_read(file_inode(mf->fp));
if (!KDBUS_IS_ALIGNED8(arg)) {
ret = -EFAULT;
goto exit;
}
if (copy_to_user(argp, &size, sizeof(__u64))) {
ret = -EFAULT;
goto exit;
}
break;
}
case KDBUS_CMD_MEMFD_SIZE_SET: {
u64 size;
if (!KDBUS_IS_ALIGNED8(arg)) {
ret = -EFAULT;
goto exit;
}
if (copy_from_user(&size, argp, sizeof(__u64))) {
ret = -EFAULT;
goto exit;
}
/* deny a writable access to a sealed file */
if (mf->sealed) {
if (size == i_size_read(file_inode(mf->fp)))
ret = -EALREADY;
else
ret = -EPERM;
goto exit;
}
if (size != i_size_read(file_inode(mf->fp)))
ret = vfs_truncate(&mf->fp->f_path, size);
break;
}
case KDBUS_CMD_MEMFD_SEAL_GET: {
int __user *addr = argp;
if (put_user(mf->sealed, addr)) {
ret = -EFAULT;
goto exit;
}
break;
}
case KDBUS_CMD_MEMFD_SEAL_SET: {
struct mm_struct *mm = current->mm;
/*
* Make sure we have only one single user of the file
* before we seal, we rely on the fact there is no
* any other possibly writable references to the file.
*
* Protect mmap() racing against us, take mm->mmap_sem
* when accessing mf->sealed.
*/
down_read(&mm->mmap_sem);
if (file_count(mf->fp) != 1) {
if (mf->sealed == !!argp)
ret = -EALREADY;
else
ret = -ETXTBSY;
}
if (ret == 0)
mf->sealed = !!argp;
up_read(&mm->mmap_sem);
break;
}
default:
ret = -ENOTTY;
break;
}
exit:
mutex_unlock(&mf->lock);
return ret;
}
/*
* Called when an inode is about to be open.
* We use this to disallow opening large files on 32bit systems if
* the caller didn't specify O_LARGEFILE. On 64bit systems we force
* on this flag in sys_open.
*/
int generic_file_open(struct inode * inode, struct file * filp)
{
if (!(filp->f_flags & O_LARGEFILE) && i_size_read(inode) > MAX_NON_LFS)
return -EOVERFLOW;
return 0;
}
static int __ocfs2_page_mkwrite(struct inode *inode, struct buffer_head *di_bh,
struct page *page)
{
int ret;
struct address_space *mapping = inode->i_mapping;
loff_t pos = page_offset(page);
unsigned int len = PAGE_CACHE_SIZE;
pgoff_t last_index;
struct page *locked_page = NULL;
void *fsdata;
loff_t size = i_size_read(inode);
/*
* Another node might have truncated while we were waiting on
* cluster locks.
*/
last_index = size >> PAGE_CACHE_SHIFT;
if (page->index > last_index) {
ret = -EINVAL;
goto out;
}
/*
* The i_size check above doesn't catch the case where nodes
* truncated and then re-extended the file. We'll re-check the
* page mapping after taking the page lock inside of
* ocfs2_write_begin_nolock().
*/
if (!PageUptodate(page) || page->mapping != inode->i_mapping) {
/*
* the page has been umapped in ocfs2_data_downconvert_worker.
* So return 0 here and let VFS retry.
*/
ret = 0;
goto out;
}
/*
* Call ocfs2_write_begin() and ocfs2_write_end() to take
* advantage of the allocation code there. We pass a write
* length of the whole page (chopped to i_size) to make sure
* the whole thing is allocated.
*
* Since we know the page is up to date, we don't have to
* worry about ocfs2_write_begin() skipping some buffer reads
* because the "write" would invalidate their data.
*/
if (page->index == last_index)
len = size & ~PAGE_CACHE_MASK;
ret = ocfs2_write_begin_nolock(mapping, pos, len, 0, &locked_page,
&fsdata, di_bh, page);
if (ret) {
if (ret != -ENOSPC)
mlog_errno(ret);
goto out;
}
ret = ocfs2_write_end_nolock(mapping, pos, len, len, locked_page,
fsdata);
if (ret < 0) {
mlog_errno(ret);
goto out;
}
BUG_ON(ret != len);
ret = 0;
out:
return ret;
}
STATIC loff_t
xfs_seek_hole(
struct file *file,
loff_t start)
{
struct inode *inode = file->f_mapping->host;
struct xfs_inode *ip = XFS_I(inode);
struct xfs_mount *mp = ip->i_mount;
loff_t uninitialized_var(offset);
xfs_fsize_t isize;
xfs_fileoff_t fsbno;
xfs_filblks_t end;
uint lock;
int error;
if (XFS_FORCED_SHUTDOWN(mp))
return -EIO;
lock = xfs_ilock_data_map_shared(ip);
isize = i_size_read(inode);
if (start >= isize) {
error = -ENXIO;
goto out_unlock;
}
fsbno = XFS_B_TO_FSBT(mp, start);
end = XFS_B_TO_FSB(mp, isize);
for (;;) {
struct xfs_bmbt_irec map[2];
int nmap = 2;
unsigned int i;
error = xfs_bmapi_read(ip, fsbno, end - fsbno, map, &nmap,
XFS_BMAPI_ENTIRE);
if (error)
goto out_unlock;
/* No extents at given offset, must be beyond EOF */
if (nmap == 0) {
error = -ENXIO;
goto out_unlock;
}
for (i = 0; i < nmap; i++) {
offset = max_t(loff_t, start,
XFS_FSB_TO_B(mp, map[i].br_startoff));
/* Landed in a hole */
if (map[i].br_startblock == HOLESTARTBLOCK)
goto out;
/*
* Landed in an unwritten extent, try to search hole
* from page cache.
*/
if (map[i].br_state == XFS_EXT_UNWRITTEN) {
if (xfs_find_get_desired_pgoff(inode, &map[i],
HOLE_OFF, &offset))
goto out;
}
}
/*
* map[0] contains data or its unwritten but contains
* data in page cache, probably means that we are
* reading after EOF. We should fix offset to point
* to the end of the file(i.e., there is an implicit
* hole at the end of any file).
*/
if (nmap == 1) {
offset = isize;
break;
}
ASSERT(i > 1);
/*
* Both mappings contains data, proceed to the next round of
* search if the current reading offset not beyond or hit EOF.
*/
fsbno = map[i - 1].br_startoff + map[i - 1].br_blockcount;
start = XFS_FSB_TO_B(mp, fsbno);
if (start >= isize) {
offset = isize;
break;
}
}
out:
/*
* At this point, we must have found a hole. However, the returned
* offset may be bigger than the file size as it may be aligned to
* page boundary for unwritten extents, we need to deal with this
* situation in particular.
*/
offset = min_t(loff_t, offset, isize);
offset = vfs_setpos(file, offset, inode->i_sb->s_maxbytes);
out_unlock:
xfs_iunlock(ip, lock);
if (error)
return error;
return offset;
}
/*
* inode->i_mutex: down
*/
int
reiserfs_xattr_set_handle(struct reiserfs_transaction_handle *th,
struct inode *inode, const char *name,
const void *buffer, size_t buffer_size, int flags)
{
int err = 0;
struct dentry *dentry;
struct page *page;
char *data;
size_t file_pos = 0;
size_t buffer_pos = 0;
size_t new_size;
__u32 xahash = 0;
if (get_inode_sd_version(inode) == STAT_DATA_V1)
return -EOPNOTSUPP;
if (!buffer) {
err = lookup_and_delete_xattr(inode, name);
return err;
}
dentry = xattr_lookup(inode, name, flags);
if (IS_ERR(dentry))
return PTR_ERR(dentry);
down_write(&REISERFS_I(inode)->i_xattr_sem);
xahash = xattr_hash(buffer, buffer_size);
while (buffer_pos < buffer_size || buffer_pos == 0) {
size_t chunk;
size_t skip = 0;
size_t page_offset = (file_pos & (PAGE_CACHE_SIZE - 1));
if (buffer_size - buffer_pos > PAGE_CACHE_SIZE)
chunk = PAGE_CACHE_SIZE;
else
chunk = buffer_size - buffer_pos;
page = reiserfs_get_page(dentry->d_inode, file_pos);
if (IS_ERR(page)) {
err = PTR_ERR(page);
goto out_unlock;
}
lock_page(page);
data = page_address(page);
if (file_pos == 0) {
struct reiserfs_xattr_header *rxh;
skip = file_pos = sizeof(struct reiserfs_xattr_header);
if (chunk + skip > PAGE_CACHE_SIZE)
chunk = PAGE_CACHE_SIZE - skip;
rxh = (struct reiserfs_xattr_header *)data;
rxh->h_magic = cpu_to_le32(REISERFS_XATTR_MAGIC);
rxh->h_hash = cpu_to_le32(xahash);
}
reiserfs_write_lock(inode->i_sb);
err = __reiserfs_write_begin(page, page_offset, chunk + skip);
if (!err) {
if (buffer)
memcpy(data + skip, buffer + buffer_pos, chunk);
err = reiserfs_commit_write(NULL, page, page_offset,
page_offset + chunk +
skip);
}
reiserfs_write_unlock(inode->i_sb);
unlock_page(page);
reiserfs_put_page(page);
buffer_pos += chunk;
file_pos += chunk;
skip = 0;
if (err || buffer_size == 0 || !buffer)
break;
}
new_size = buffer_size + sizeof(struct reiserfs_xattr_header);
if (!err && new_size < i_size_read(dentry->d_inode)) {
struct iattr newattrs = {
.ia_ctime = current_fs_time(inode->i_sb),
.ia_size = new_size,
.ia_valid = ATTR_SIZE | ATTR_CTIME,
};
mutex_lock_nested(&dentry->d_inode->i_mutex, I_MUTEX_XATTR);
inode_dio_wait(dentry->d_inode);
err = reiserfs_setattr(dentry, &newattrs);
mutex_unlock(&dentry->d_inode->i_mutex);
} else
update_ctime(inode);
out_unlock:
up_write(&REISERFS_I(inode)->i_xattr_sem);
dput(dentry);
return err;
}
STATIC long
xfs_file_fallocate(
struct file *file,
int mode,
loff_t offset,
loff_t len)
{
struct inode *inode = file_inode(file);
struct xfs_inode *ip = XFS_I(inode);
struct xfs_trans *tp;
long error;
loff_t new_size = 0;
if (!S_ISREG(inode->i_mode))
return -EINVAL;
if (mode & ~(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE |
FALLOC_FL_COLLAPSE_RANGE | FALLOC_FL_ZERO_RANGE))
return -EOPNOTSUPP;
xfs_ilock(ip, XFS_IOLOCK_EXCL);
if (mode & FALLOC_FL_PUNCH_HOLE) {
error = xfs_free_file_space(ip, offset, len);
if (error)
goto out_unlock;
} else if (mode & FALLOC_FL_COLLAPSE_RANGE) {
unsigned blksize_mask = (1 << inode->i_blkbits) - 1;
if (offset & blksize_mask || len & blksize_mask) {
error = -EINVAL;
goto out_unlock;
}
/*
* There is no need to overlap collapse range with EOF,
* in which case it is effectively a truncate operation
*/
if (offset + len >= i_size_read(inode)) {
error = -EINVAL;
goto out_unlock;
}
new_size = i_size_read(inode) - len;
error = xfs_collapse_file_space(ip, offset, len);
if (error)
goto out_unlock;
} else {
if (!(mode & FALLOC_FL_KEEP_SIZE) &&
offset + len > i_size_read(inode)) {
new_size = offset + len;
error = inode_newsize_ok(inode, new_size);
if (error)
goto out_unlock;
}
if (mode & FALLOC_FL_ZERO_RANGE)
error = xfs_zero_file_space(ip, offset, len);
else
error = xfs_alloc_file_space(ip, offset, len,
XFS_BMAPI_PREALLOC);
if (error)
goto out_unlock;
}
tp = xfs_trans_alloc(ip->i_mount, XFS_TRANS_WRITEID);
error = xfs_trans_reserve(tp, &M_RES(ip->i_mount)->tr_writeid, 0, 0);
if (error) {
xfs_trans_cancel(tp, 0);
goto out_unlock;
}
xfs_ilock(ip, XFS_ILOCK_EXCL);
xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL);
ip->i_d.di_mode &= ~S_ISUID;
if (ip->i_d.di_mode & S_IXGRP)
ip->i_d.di_mode &= ~S_ISGID;
if (!(mode & (FALLOC_FL_PUNCH_HOLE | FALLOC_FL_COLLAPSE_RANGE)))
ip->i_d.di_flags |= XFS_DIFLAG_PREALLOC;
xfs_trans_ichgtime(tp, ip, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
if (file->f_flags & O_DSYNC)
xfs_trans_set_sync(tp);
error = xfs_trans_commit(tp, 0);
if (error)
goto out_unlock;
/* Change file size if needed */
if (new_size) {
struct iattr iattr;
iattr.ia_valid = ATTR_SIZE;
iattr.ia_size = new_size;
error = xfs_setattr_size(ip, &iattr);
}
out_unlock:
xfs_iunlock(ip, XFS_IOLOCK_EXCL);
return error;
}
/*
* inode->i_mutex: down
*/
int
reiserfs_xattr_get(struct inode *inode, const char *name, void *buffer,
size_t buffer_size)
{
ssize_t err = 0;
struct dentry *dentry;
size_t isize;
size_t file_pos = 0;
size_t buffer_pos = 0;
struct page *page;
__u32 hash = 0;
if (name == NULL)
return -EINVAL;
/* We can't have xattrs attached to v1 items since they don't have
* generation numbers */
if (get_inode_sd_version(inode) == STAT_DATA_V1)
return -EOPNOTSUPP;
dentry = xattr_lookup(inode, name, XATTR_REPLACE);
if (IS_ERR(dentry)) {
err = PTR_ERR(dentry);
goto out;
}
down_read(&REISERFS_I(inode)->i_xattr_sem);
isize = i_size_read(dentry->d_inode);
/* Just return the size needed */
if (buffer == NULL) {
err = isize - sizeof(struct reiserfs_xattr_header);
goto out_unlock;
}
if (buffer_size < isize - sizeof(struct reiserfs_xattr_header)) {
err = -ERANGE;
goto out_unlock;
}
while (file_pos < isize) {
size_t chunk;
char *data;
size_t skip = 0;
if (isize - file_pos > PAGE_CACHE_SIZE)
chunk = PAGE_CACHE_SIZE;
else
chunk = isize - file_pos;
page = reiserfs_get_page(dentry->d_inode, file_pos);
if (IS_ERR(page)) {
err = PTR_ERR(page);
goto out_unlock;
}
lock_page(page);
data = page_address(page);
if (file_pos == 0) {
struct reiserfs_xattr_header *rxh =
(struct reiserfs_xattr_header *)data;
skip = file_pos = sizeof(struct reiserfs_xattr_header);
chunk -= skip;
/* Magic doesn't match up.. */
if (rxh->h_magic != cpu_to_le32(REISERFS_XATTR_MAGIC)) {
unlock_page(page);
reiserfs_put_page(page);
reiserfs_warning(inode->i_sb, "jdm-20001",
"Invalid magic for xattr (%s) "
"associated with %k", name,
INODE_PKEY(inode));
err = -EIO;
goto out_unlock;
}
hash = le32_to_cpu(rxh->h_hash);
}
memcpy(buffer + buffer_pos, data + skip, chunk);
unlock_page(page);
reiserfs_put_page(page);
file_pos += chunk;
buffer_pos += chunk;
skip = 0;
}
err = isize - sizeof(struct reiserfs_xattr_header);
if (xattr_hash(buffer, isize - sizeof(struct reiserfs_xattr_header)) !=
hash) {
reiserfs_warning(inode->i_sb, "jdm-20002",
"Invalid hash for xattr (%s) associated "
"with %k", name, INODE_PKEY(inode));
err = -EIO;
}
out_unlock:
up_read(&REISERFS_I(inode)->i_xattr_sem);
dput(dentry);
out:
return err;
}
static unsigned long dir_blocks(struct inode *inode)
{
return ((unsigned long long) (i_size_read(inode) + PAGE_CACHE_SIZE - 1))
>> PAGE_CACHE_SHIFT;
}
static int squashfs_fill_super(struct super_block *sb, void *data, int silent)
{
struct squashfs_sb_info *msblk;
struct squashfs_super_block *sblk = NULL;
char b[BDEVNAME_SIZE];
struct inode *root;
long long root_inode;
unsigned short flags;
unsigned int fragments;
u64 lookup_table_start, xattr_id_table_start, next_table;
int err;
TRACE("Entered squashfs_fill_superblock\n");
sb->s_fs_info = kzalloc(sizeof(*msblk), GFP_KERNEL);
if (sb->s_fs_info == NULL) {
ERROR("Failed to allocate squashfs_sb_info\n");
return -ENOMEM;
}
msblk = sb->s_fs_info;
msblk->devblksize = sb_min_blocksize(sb, SQUASHFS_DEVBLK_SIZE);
msblk->devblksize_log2 = ffz(~msblk->devblksize);
mutex_init(&msblk->read_data_mutex);
mutex_init(&msblk->meta_index_mutex);
/*
* msblk->bytes_used is checked in squashfs_read_table to ensure reads
* are not beyond filesystem end. But as we're using
* squashfs_read_table here to read the superblock (including the value
* of bytes_used) we need to set it to an initial sensible dummy value
*/
msblk->bytes_used = sizeof(*sblk);
sblk = squashfs_read_table(sb, SQUASHFS_START, sizeof(*sblk));
if (IS_ERR(sblk)) {
ERROR("unable to read squashfs_super_block\n");
err = PTR_ERR(sblk);
sblk = NULL;
goto failed_mount;
}
err = -EINVAL;
/* Check it is a SQUASHFS superblock */
sb->s_magic = le32_to_cpu(sblk->s_magic);
if (sb->s_magic != SQUASHFS_MAGIC) {
if (!silent)
ERROR("Can't find a SQUASHFS superblock on %s\n",
bdevname(sb->s_bdev, b));
goto failed_mount;
}
/* Check the MAJOR & MINOR versions and lookup compression type */
msblk->decompressor = supported_squashfs_filesystem(
le16_to_cpu(sblk->s_major),
le16_to_cpu(sblk->s_minor),
le16_to_cpu(sblk->compression));
if (msblk->decompressor == NULL)
goto failed_mount;
/* Check the filesystem does not extend beyond the end of the
block device */
msblk->bytes_used = le64_to_cpu(sblk->bytes_used);
if (msblk->bytes_used < 0 || msblk->bytes_used >
i_size_read(sb->s_bdev->bd_inode))
goto failed_mount;
/* Check block size for sanity */
msblk->block_size = le32_to_cpu(sblk->block_size);
if (msblk->block_size > SQUASHFS_FILE_MAX_SIZE)
goto failed_mount;
/*
* Check the system page size is not larger than the filesystem
* block size (by default 128K). This is currently not supported.
*/
if (PAGE_CACHE_SIZE > msblk->block_size) {
ERROR("Page size > filesystem block size (%d). This is "
"currently not supported!\n", msblk->block_size);
goto failed_mount;
}
msblk->block_log = le16_to_cpu(sblk->block_log);
if (msblk->block_log > SQUASHFS_FILE_MAX_LOG)
goto failed_mount;
/* Check the root inode for sanity */
root_inode = le64_to_cpu(sblk->root_inode);
if (SQUASHFS_INODE_OFFSET(root_inode) > SQUASHFS_METADATA_SIZE)
goto failed_mount;
msblk->inode_table = le64_to_cpu(sblk->inode_table_start);
msblk->directory_table = le64_to_cpu(sblk->directory_table_start);
msblk->inodes = le32_to_cpu(sblk->inodes);
flags = le16_to_cpu(sblk->flags);
TRACE("Found valid superblock on %s\n", bdevname(sb->s_bdev, b));
TRACE("Inodes are %scompressed\n", SQUASHFS_UNCOMPRESSED_INODES(flags)
? "un" : "");
TRACE("Data is %scompressed\n", SQUASHFS_UNCOMPRESSED_DATA(flags)
? "un" : "");
TRACE("Filesystem size %lld bytes\n", msblk->bytes_used);
TRACE("Block size %d\n", msblk->block_size);
TRACE("Number of inodes %d\n", msblk->inodes);
TRACE("Number of fragments %d\n", le32_to_cpu(sblk->fragments));
TRACE("Number of ids %d\n", le16_to_cpu(sblk->no_ids));
TRACE("sblk->inode_table_start %llx\n", msblk->inode_table);
TRACE("sblk->directory_table_start %llx\n", msblk->directory_table);
TRACE("sblk->fragment_table_start %llx\n",
(u64) le64_to_cpu(sblk->fragment_table_start));
TRACE("sblk->id_table_start %llx\n",
(u64) le64_to_cpu(sblk->id_table_start));
sb->s_maxbytes = MAX_LFS_FILESIZE;
sb->s_flags |= MS_RDONLY;
sb->s_op = &squashfs_super_ops;
err = -ENOMEM;
msblk->block_cache = squashfs_cache_init("metadata",
SQUASHFS_CACHED_BLKS, SQUASHFS_METADATA_SIZE);
if (msblk->block_cache == NULL)
goto failed_mount;
/* Allocate read_page block */
msblk->read_page = squashfs_cache_init("data", 1, msblk->block_size);
if (msblk->read_page == NULL) {
ERROR("Failed to allocate read_page block\n");
goto failed_mount;
}
msblk->stream = squashfs_decompressor_init(sb, flags);
if (IS_ERR(msblk->stream)) {
err = PTR_ERR(msblk->stream);
msblk->stream = NULL;
goto failed_mount;
}
/* Handle xattrs */
sb->s_xattr = squashfs_xattr_handlers;
xattr_id_table_start = le64_to_cpu(sblk->xattr_id_table_start);
if (xattr_id_table_start == SQUASHFS_INVALID_BLK) {
next_table = msblk->bytes_used;
goto allocate_id_index_table;
}
/* Allocate and read xattr id lookup table */
msblk->xattr_id_table = squashfs_read_xattr_id_table(sb,
xattr_id_table_start, &msblk->xattr_table, &msblk->xattr_ids);
if (IS_ERR(msblk->xattr_id_table)) {
ERROR("unable to read xattr id index table\n");
err = PTR_ERR(msblk->xattr_id_table);
msblk->xattr_id_table = NULL;
if (err != -ENOTSUPP)
goto failed_mount;
}
next_table = msblk->xattr_table;
allocate_id_index_table:
/* Allocate and read id index table */
msblk->id_table = squashfs_read_id_index_table(sb,
le64_to_cpu(sblk->id_table_start), next_table,
le16_to_cpu(sblk->no_ids));
if (IS_ERR(msblk->id_table)) {
ERROR("unable to read id index table\n");
err = PTR_ERR(msblk->id_table);
msblk->id_table = NULL;
goto failed_mount;
}
next_table = le64_to_cpu(msblk->id_table[0]);
/* Handle inode lookup table */
lookup_table_start = le64_to_cpu(sblk->lookup_table_start);
if (lookup_table_start == SQUASHFS_INVALID_BLK)
goto handle_fragments;
/* Allocate and read inode lookup table */
msblk->inode_lookup_table = squashfs_read_inode_lookup_table(sb,
lookup_table_start, next_table, msblk->inodes);
if (IS_ERR(msblk->inode_lookup_table)) {
ERROR("unable to read inode lookup table\n");
err = PTR_ERR(msblk->inode_lookup_table);
msblk->inode_lookup_table = NULL;
goto failed_mount;
}
next_table = le64_to_cpu(msblk->inode_lookup_table[0]);
sb->s_export_op = &squashfs_export_ops;
handle_fragments:
fragments = le32_to_cpu(sblk->fragments);
if (fragments == 0)
goto check_directory_table;
msblk->fragment_cache = squashfs_cache_init("fragment",
SQUASHFS_CACHED_FRAGMENTS, msblk->block_size);
if (msblk->fragment_cache == NULL) {
err = -ENOMEM;
goto failed_mount;
}
/* Allocate and read fragment index table */
msblk->fragment_index = squashfs_read_fragment_index_table(sb,
le64_to_cpu(sblk->fragment_table_start), next_table, fragments);
if (IS_ERR(msblk->fragment_index)) {
ERROR("unable to read fragment index table\n");
err = PTR_ERR(msblk->fragment_index);
msblk->fragment_index = NULL;
goto failed_mount;
}
next_table = le64_to_cpu(msblk->fragment_index[0]);
check_directory_table:
/* Sanity check directory_table */
if (msblk->directory_table >= next_table) {
err = -EINVAL;
goto failed_mount;
}
/* Sanity check inode_table */
if (msblk->inode_table >= msblk->directory_table) {
err = -EINVAL;
goto failed_mount;
}
/* allocate root */
root = new_inode(sb);
if (!root) {
err = -ENOMEM;
goto failed_mount;
}
err = squashfs_read_inode(root, root_inode);
if (err) {
make_bad_inode(root);
iput(root);
goto failed_mount;
}
insert_inode_hash(root);
sb->s_root = d_alloc_root(root);
if (sb->s_root == NULL) {
ERROR("Root inode create failed\n");
err = -ENOMEM;
iput(root);
goto failed_mount;
}
TRACE("Leaving squashfs_fill_super\n");
kfree(sblk);
return 0;
failed_mount:
squashfs_cache_delete(msblk->block_cache);
squashfs_cache_delete(msblk->fragment_cache);
squashfs_cache_delete(msblk->read_page);
squashfs_decompressor_free(msblk, msblk->stream);
kfree(msblk->inode_lookup_table);
kfree(msblk->fragment_index);
kfree(msblk->id_table);
kfree(msblk->xattr_id_table);
kfree(sb->s_fs_info);
sb->s_fs_info = NULL;
kfree(sblk);
return err;
}
static int ufs_alloc_lastblock(struct inode *inode)
{
int err = 0;
struct super_block *sb = inode->i_sb;
struct address_space *mapping = inode->i_mapping;
struct ufs_sb_private_info *uspi = UFS_SB(sb)->s_uspi;
unsigned i, end;
sector_t lastfrag;
struct page *lastpage;
struct buffer_head *bh;
u64 phys64;
lastfrag = (i_size_read(inode) + uspi->s_fsize - 1) >> uspi->s_fshift;
if (!lastfrag)
goto out;
lastfrag--;
lastpage = ufs_get_locked_page(mapping, lastfrag >>
(PAGE_CACHE_SHIFT - inode->i_blkbits));
if (IS_ERR(lastpage)) {
err = -EIO;
goto out;
}
end = lastfrag & ((1 << (PAGE_CACHE_SHIFT - inode->i_blkbits)) - 1);
bh = page_buffers(lastpage);
for (i = 0; i < end; ++i)
bh = bh->b_this_page;
err = ufs_getfrag_block(inode, lastfrag, bh, 1);
if (unlikely(err))
goto out_unlock;
if (buffer_new(bh)) {
clear_buffer_new(bh);
unmap_underlying_metadata(bh->b_bdev,
bh->b_blocknr);
/*
* we do not zeroize fragment, because of
* if it maped to hole, it already contains zeroes
*/
set_buffer_uptodate(bh);
mark_buffer_dirty(bh);
set_page_dirty(lastpage);
}
if (lastfrag >= UFS_IND_FRAGMENT) {
end = uspi->s_fpb - ufs_fragnum(lastfrag) - 1;
phys64 = bh->b_blocknr + 1;
for (i = 0; i < end; ++i) {
bh = sb_getblk(sb, i + phys64);
lock_buffer(bh);
memset(bh->b_data, 0, sb->s_blocksize);
set_buffer_uptodate(bh);
mark_buffer_dirty(bh);
unlock_buffer(bh);
sync_dirty_buffer(bh);
brelse(bh);
}
}
out_unlock:
ufs_put_locked_page(lastpage);
out:
return err;
}
/*
* This is the worker routine which does all the work of mapping the disk
* blocks and constructs largest possible bios, submits them for IO if the
* blocks are not contiguous on the disk.
*
* We pass a buffer_head back and forth and use its buffer_mapped() flag to
* represent the validity of its disk mapping and to decide when to do the next
* get_block() call.
*/
static struct bio *
do_mpage_readpage(struct bio *bio, struct page *page, unsigned nr_pages,
sector_t *last_block_in_bio, struct buffer_head *map_bh,
unsigned long *first_logical_block, get_block_t get_block)
{
struct inode *inode = page->mapping->host;
const unsigned blkbits = inode->i_blkbits;
const unsigned blocks_per_page = PAGE_CACHE_SIZE >> blkbits;
const unsigned blocksize = 1 << blkbits;
sector_t block_in_file;
sector_t last_block;
sector_t last_block_in_file;
sector_t blocks[MAX_BUF_PER_PAGE];
unsigned page_block;
unsigned first_hole = blocks_per_page;
struct block_device *bdev = NULL;
int length, bio_length;
int fully_mapped = 1;
unsigned nblocks;
unsigned relative_block;
if (page_has_buffers(page))
goto confused;
block_in_file = (sector_t)page->index << (PAGE_CACHE_SHIFT - blkbits);
last_block = block_in_file + nr_pages * blocks_per_page;
last_block_in_file = (i_size_read(inode) + blocksize - 1) >> blkbits;
if (last_block > last_block_in_file)
last_block = last_block_in_file;
page_block = 0;
/*
* Map blocks using the result from the previous get_blocks call first.
*/
nblocks = map_bh->b_size >> blkbits;
if (buffer_mapped(map_bh) && block_in_file > *first_logical_block &&
block_in_file < (*first_logical_block + nblocks)) {
unsigned map_offset = block_in_file - *first_logical_block;
unsigned last = nblocks - map_offset;
for (relative_block = 0; ; relative_block++) {
if (relative_block == last) {
clear_buffer_mapped(map_bh);
break;
}
if (page_block == blocks_per_page)
break;
blocks[page_block] = map_bh->b_blocknr + map_offset +
relative_block;
page_block++;
block_in_file++;
}
bdev = map_bh->b_bdev;
}
/*
* Then do more get_blocks calls until we are done with this page.
*/
map_bh->b_page = page;
while (page_block < blocks_per_page) {
map_bh->b_state = 0;
map_bh->b_size = 0;
if (block_in_file < last_block) {
map_bh->b_size = (last_block-block_in_file) << blkbits;
if (get_block(inode, block_in_file, map_bh, 0))
goto confused;
*first_logical_block = block_in_file;
}
if (!buffer_mapped(map_bh)) {
fully_mapped = 0;
if (first_hole == blocks_per_page)
first_hole = page_block;
page_block++;
block_in_file++;
continue;
}
/* some filesystems will copy data into the page during
* the get_block call, in which case we don't want to
* read it again. map_buffer_to_page copies the data
* we just collected from get_block into the page's buffers
* so readpage doesn't have to repeat the get_block call
*/
if (buffer_uptodate(map_bh)) {
map_buffer_to_page(page, map_bh, page_block);
goto confused;
}
if (first_hole != blocks_per_page)
goto confused; /* hole -> non-hole */
/* Contiguous blocks? */
if (page_block && blocks[page_block-1] != map_bh->b_blocknr-1)
goto confused;
nblocks = map_bh->b_size >> blkbits;
for (relative_block = 0; ; relative_block++) {
if (relative_block == nblocks) {
clear_buffer_mapped(map_bh);
break;
} else if (page_block == blocks_per_page)
break;
blocks[page_block] = map_bh->b_blocknr+relative_block;
page_block++;
block_in_file++;
}
bdev = map_bh->b_bdev;
}
if (first_hole != blocks_per_page) {
zero_user_segment(page, first_hole << blkbits, PAGE_CACHE_SIZE);
if (first_hole == 0) {
SetPageUptodate(page);
if (PageBaio(page))
baiocb_put(current->current_baiocb);
unlock_page(page);
goto out;
}
} else if (fully_mapped) {
SetPageMappedToDisk(page);
}
/*
* This page will go to BIO. Do we need to send this BIO off first?
*/
if (bio && (*last_block_in_bio != blocks[0] - 1))
bio = mpage_bio_submit(READ, bio);
alloc_new:
if (bio == NULL) {
bio = mpage_alloc(bdev, blocks[0] << (blkbits - 9),
min_t(int, nr_pages, bio_get_nr_vecs(bdev)),
GFP_KERNEL);
if (bio == NULL)
goto confused;
}
/*
* TODO: Make this into a generic get_blocks function.
*
* From do_direct_io in direct-io.c:
* "So what we do is to permit the ->get_blocks function to populate
* bh.b_size with the size of IO which is permitted at this offset and
* this i_blkbits."
*
* This function is called directly from get_more_blocks in direct-io.c.
*
* called like this: dio->get_blocks(dio->inode, fs_startblk,
* fs_count, map_bh, dio->rw == WRITE);
*/
static int ocfs2_direct_IO_get_blocks(struct inode *inode, sector_t iblock,
struct buffer_head *bh_result, int create)
{
int ret;
u64 p_blkno, inode_blocks, contig_blocks;
unsigned int ext_flags;
unsigned char blocksize_bits = inode->i_sb->s_blocksize_bits;
unsigned long max_blocks = bh_result->b_size >> inode->i_blkbits;
/* This function won't even be called if the request isn't all
* nicely aligned and of the right size, so there's no need
* for us to check any of that. */
inode_blocks = ocfs2_blocks_for_bytes(inode->i_sb, i_size_read(inode));
/*
* Any write past EOF is not allowed because we'd be extending.
*/
if (create && (iblock + max_blocks) > inode_blocks) {
ret = -EIO;
goto bail;
}
/* This figures out the size of the next contiguous block, and
* our logical offset */
ret = ocfs2_extent_map_get_blocks(inode, iblock, &p_blkno,
&contig_blocks, &ext_flags);
if (ret) {
mlog(ML_ERROR, "get_blocks() failed iblock=%llu\n",
(unsigned long long)iblock);
ret = -EIO;
goto bail;
}
if (!ocfs2_sparse_alloc(OCFS2_SB(inode->i_sb)) && !p_blkno && create) {
ocfs2_error(inode->i_sb,
"Inode %llu has a hole at block %llu\n",
(unsigned long long)OCFS2_I(inode)->ip_blkno,
(unsigned long long)iblock);
ret = -EROFS;
goto bail;
}
/*
* get_more_blocks() expects us to describe a hole by clearing
* the mapped bit on bh_result().
*
* Consider an unwritten extent as a hole.
*/
if (p_blkno && !(ext_flags & OCFS2_EXT_UNWRITTEN))
map_bh(bh_result, inode->i_sb, p_blkno);
else {
/*
* ocfs2_prepare_inode_for_write() should have caught
* the case where we'd be filling a hole and triggered
* a buffered write instead.
*/
if (create) {
ret = -EIO;
mlog_errno(ret);
goto bail;
}
clear_buffer_mapped(bh_result);
}
/* make sure we don't map more than max_blocks blocks here as
that's all the kernel will handle at this point. */
if (max_blocks < contig_blocks)
contig_blocks = max_blocks;
bh_result->b_size = contig_blocks << blocksize_bits;
bail:
return ret;
}
/*
* AFS read page from file, directory or symlink
*/
static int afs_readpage(struct file *file, struct page *page)
{
struct afs_vnode *vnode;
struct inode *inode;
struct key *key;
size_t len;
off_t offset;
int ret;
inode = page->mapping->host;
ASSERT(file != NULL);
key = file->private_data;
ASSERT(key != NULL);
_enter("{%x},{%lu},{%lu}", key_serial(key), inode->i_ino, page->index);
vnode = AFS_FS_I(inode);
BUG_ON(!PageLocked(page));
ret = -ESTALE;
if (test_bit(AFS_VNODE_DELETED, &vnode->flags))
goto error;
#ifdef AFS_CACHING_SUPPORT
/* is it cached? */
ret = cachefs_read_or_alloc_page(vnode->cache,
page,
afs_file_readpage_read_complete,
NULL,
GFP_KERNEL);
#else
ret = -ENOBUFS;
#endif
switch (ret) {
/* read BIO submitted and wb-journal entry found */
case 1:
BUG(); // TODO - handle wb-journal match
/* read BIO submitted (page in cache) */
case 0:
break;
/* no page available in cache */
case -ENOBUFS:
case -ENODATA:
default:
offset = page->index << PAGE_CACHE_SHIFT;
len = min_t(size_t, i_size_read(inode) - offset, PAGE_SIZE);
/* read the contents of the file from the server into the
* page */
ret = afs_vnode_fetch_data(vnode, key, offset, len, page);
if (ret < 0) {
if (ret == -ENOENT) {
_debug("got NOENT from server"
" - marking file deleted and stale");
set_bit(AFS_VNODE_DELETED, &vnode->flags);
ret = -ESTALE;
}
#ifdef AFS_CACHING_SUPPORT
cachefs_uncache_page(vnode->cache, page);
#endif
goto error;
}
SetPageUptodate(page);
#ifdef AFS_CACHING_SUPPORT
if (cachefs_write_page(vnode->cache,
page,
afs_file_readpage_write_complete,
NULL,
GFP_KERNEL) != 0
) {
cachefs_uncache_page(vnode->cache, page);
unlock_page(page);
}
#else
unlock_page(page);
#endif
}
_leave(" = 0");
return 0;
error:
SetPageError(page);
unlock_page(page);
_leave(" = %d", ret);
return ret;
}
