* @inode: owner
* @ind: descriptor of indirect block.
*
- * This function returns the prefered place for block allocation.
+ * This function returns the preferred place for block allocation.
* It is used when heuristic for sequential allocation fails.
* Rules are:
* + if there is a block to the left of our position - allocate near it.
}
/**
- * ext3_find_goal - find a prefered place for allocation.
+ * ext3_find_goal - find a preferred place for allocation.
* @inode: owner
* @block: block we want
- * @chain: chain of indirect blocks
* @partial: pointer to the last triple within a chain
- * @goal: place to store the result.
*
- * Normally this function find the prefered place for block allocation,
- * stores it in *@goal and returns zero.
+ * Normally this function find the preferred place for block allocation,
+ * returns it.
*/
static ext3_fsblk_t ext3_find_goal(struct inode *inode, long block,
- Indirect chain[4], Indirect *partial)
+ Indirect *partial)
{
struct ext3_block_alloc_info *block_i;
if (S_ISREG(inode->i_mode) && (!ei->i_block_alloc_info))
ext3_init_block_alloc_info(inode);
- goal = ext3_find_goal(inode, iblock, chain, partial);
+ goal = ext3_find_goal(inode, iblock, partial);
/* the number of blocks need to allocate for [d,t]indirect blocks */
indirect_blks = (chain + depth) - partial - 1;
return err;
}
-#define DIO_CREDITS (EXT3_RESERVE_TRANS_BLOCKS + 32)
+/* Maximum number of blocks we map for direct IO at once. */
+#define DIO_MAX_BLOCKS 4096
+/*
+ * Number of credits we need for writing DIO_MAX_BLOCKS:
+ * We need sb + group descriptor + bitmap + inode -> 4
+ * For B blocks with A block pointers per block we need:
+ * 1 (triple ind.) + (B/A/A + 2) (doubly ind.) + (B/A + 2) (indirect).
+ * If we plug in 4096 for B and 256 for A (for 1KB block size), we get 25.
+ */
+#define DIO_CREDITS 25
static int ext3_get_block(struct inode *inode, sector_t iblock,
struct buffer_head *bh_result, int create)
{
handle_t *handle = ext3_journal_current_handle();
- int ret = 0;
+ int ret = 0, started = 0;
unsigned max_blocks = bh_result->b_size >> inode->i_blkbits;
- if (!create)
- goto get_block; /* A read */
-
- if (max_blocks == 1)
- goto get_block; /* A single block get */
-
- if (handle->h_transaction->t_state == T_LOCKED) {
- /*
- * Huge direct-io writes can hold off commits for long
- * periods of time. Let this commit run.
- */
- ext3_journal_stop(handle);
- handle = ext3_journal_start(inode, DIO_CREDITS);
- if (IS_ERR(handle))
+ if (create && !handle) { /* Direct IO write... */
+ if (max_blocks > DIO_MAX_BLOCKS)
+ max_blocks = DIO_MAX_BLOCKS;
+ handle = ext3_journal_start(inode, DIO_CREDITS +
+ 2 * EXT3_QUOTA_TRANS_BLOCKS(inode->i_sb));
+ if (IS_ERR(handle)) {
ret = PTR_ERR(handle);
- goto get_block;
- }
-
- if (handle->h_buffer_credits <= EXT3_RESERVE_TRANS_BLOCKS) {
- /*
- * Getting low on buffer credits...
- */
- ret = ext3_journal_extend(handle, DIO_CREDITS);
- if (ret > 0) {
- /*
- * Couldn't extend the transaction. Start a new one.
- */
- ret = ext3_journal_restart(handle, DIO_CREDITS);
+ goto out;
}
+ started = 1;
}
-get_block:
- if (ret == 0) {
- ret = ext3_get_blocks_handle(handle, inode, iblock,
+ ret = ext3_get_blocks_handle(handle, inode, iblock,
max_blocks, bh_result, create, 0);
- if (ret > 0) {
- bh_result->b_size = (ret << inode->i_blkbits);
- ret = 0;
- }
+ if (ret > 0) {
+ bh_result->b_size = (ret << inode->i_blkbits);
+ ret = 0;
}
+ if (started)
+ ext3_journal_stop(handle);
+out:
return ret;
}
* if the machine crashes during the write.
*
* If the O_DIRECT write is intantiating holes inside i_size and the machine
- * crashes then stale disk data _may_ be exposed inside the file.
+ * crashes then stale disk data _may_ be exposed inside the file. But current
+ * VFS code falls back into buffered path in that case so we are safe.
*/
static ssize_t ext3_direct_IO(int rw, struct kiocb *iocb,
const struct iovec *iov, loff_t offset,
struct file *file = iocb->ki_filp;
struct inode *inode = file->f_mapping->host;
struct ext3_inode_info *ei = EXT3_I(inode);
- handle_t *handle = NULL;
+ handle_t *handle;
ssize_t ret;
int orphan = 0;
size_t count = iov_length(iov, nr_segs);
if (rw == WRITE) {
loff_t final_size = offset + count;
- handle = ext3_journal_start(inode, DIO_CREDITS);
- if (IS_ERR(handle)) {
- ret = PTR_ERR(handle);
- goto out;
- }
if (final_size > inode->i_size) {
+ /* Credits for sb + inode write */
+ handle = ext3_journal_start(inode, 2);
+ if (IS_ERR(handle)) {
+ ret = PTR_ERR(handle);
+ goto out;
+ }
ret = ext3_orphan_add(handle, inode);
- if (ret)
- goto out_stop;
+ if (ret) {
+ ext3_journal_stop(handle);
+ goto out;
+ }
orphan = 1;
ei->i_disksize = inode->i_size;
+ ext3_journal_stop(handle);
}
}
offset, nr_segs,
ext3_get_block, NULL);
- /*
- * Reacquire the handle: ext3_get_block() can restart the transaction
- */
- handle = ext3_journal_current_handle();
-
-out_stop:
- if (handle) {
+ if (orphan) {
int err;
- if (orphan && inode->i_nlink)
+ /* Credits for sb + inode write */
+ handle = ext3_journal_start(inode, 2);
+ if (IS_ERR(handle)) {
+ /* This is really bad luck. We've written the data
+ * but cannot extend i_size. Bail out and pretend
+ * the write failed... */
+ ret = PTR_ERR(handle);
+ goto out;
+ }
+ if (inode->i_nlink)
ext3_orphan_del(handle, inode);
- if (orphan && ret > 0) {
+ if (ret > 0) {
loff_t end = offset + ret;
if (end > inode->i_size) {
ei->i_disksize = end;
ei->i_flags |= EXT3_DIRSYNC_FL;
}
-void ext3_read_inode(struct inode * inode)
+struct inode *ext3_iget(struct super_block *sb, unsigned long ino)
{
struct ext3_iloc iloc;
struct ext3_inode *raw_inode;
- struct ext3_inode_info *ei = EXT3_I(inode);
+ struct ext3_inode_info *ei;
struct buffer_head *bh;
+ struct inode *inode;
+ long ret;
int block;
+ inode = iget_locked(sb, ino);
+ if (!inode)
+ return ERR_PTR(-ENOMEM);
+ if (!(inode->i_state & I_NEW))
+ return inode;
+
+ ei = EXT3_I(inode);
#ifdef CONFIG_EXT3_FS_POSIX_ACL
ei->i_acl = EXT3_ACL_NOT_CACHED;
ei->i_default_acl = EXT3_ACL_NOT_CACHED;
#endif
ei->i_block_alloc_info = NULL;
- if (__ext3_get_inode_loc(inode, &iloc, 0))
+ ret = __ext3_get_inode_loc(inode, &iloc, 0);
+ if (ret < 0)
goto bad_inode;
bh = iloc.bh;
raw_inode = ext3_raw_inode(&iloc);
!(EXT3_SB(inode->i_sb)->s_mount_state & EXT3_ORPHAN_FS)) {
/* this inode is deleted */
brelse (bh);
+ ret = -ESTALE;
goto bad_inode;
}
/* The only unlinked inodes we let through here have
if (EXT3_GOOD_OLD_INODE_SIZE + ei->i_extra_isize >
EXT3_INODE_SIZE(inode->i_sb)) {
brelse (bh);
+ ret = -EIO;
goto bad_inode;
}
if (ei->i_extra_isize == 0) {
}
brelse (iloc.bh);
ext3_set_inode_flags(inode);
- return;
+ unlock_new_inode(inode);
+ return inode;
bad_inode:
- make_bad_inode(inode);
- return;
+ iget_failed(inode);
+ return ERR_PTR(ret);
}
/*
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff