* Copyright (C) 1991, 1992 Linus Torvalds
*
* Goal-directed block allocation by Stephen Tweedie
- * (sct@redhat.com), 1993, 1998
+ * (sct@redhat.com), 1993, 1998
* Big-endian to little-endian byte-swapping/bitmaps by
* David S. Miller (davem@caip.rutgers.edu), 1995
* 64-bit file support on 64-bit platforms by Jakub Jelinek
- * (jj@sunsite.ms.mff.cuni.cz)
+ * (jj@sunsite.ms.mff.cuni.cz)
*
* Assorted race fixes, rewrite of ext3_get_block() by Al Viro, 2000
*/
#include <linux/time.h>
#include <linux/ext3_jbd.h>
#include <linux/jbd.h>
-#include <linux/smp_lock.h>
#include <linux/highuid.h>
#include <linux/pagemap.h>
#include <linux/quotaops.h>
#include <linux/writeback.h>
#include <linux/mpage.h>
#include <linux/uio.h>
+#include <linux/bio.h>
#include "xattr.h"
#include "acl.h"
/*
* The ext3 forget function must perform a revoke if we are freeing data
* which has been journaled. Metadata (eg. indirect blocks) must be
- * revoked in all cases.
+ * revoked in all cases.
*
* "bh" may be NULL: a metadata block may have been freed from memory
* but there may still be a record of it in the journal, and that record
* Work out how many blocks we need to proceed with the next chunk of a
* truncate transaction.
*/
-static unsigned long blocks_for_truncate(struct inode *inode)
+static unsigned long blocks_for_truncate(struct inode *inode)
{
unsigned long needed;
/* But we need to bound the transaction so we don't overflow the
* journal. */
- if (needed > EXT3_MAX_TRANS_DATA)
+ if (needed > EXT3_MAX_TRANS_DATA)
needed = EXT3_MAX_TRANS_DATA;
return EXT3_DATA_TRANS_BLOCKS(inode->i_sb) + needed;
}
-/*
+/*
* Truncate transactions can be complex and absolutely huge. So we need to
* be able to restart the transaction at a conventient checkpoint to make
* sure we don't overflow the journal.
* start_transaction gets us a new handle for a truncate transaction,
* and extend_transaction tries to extend the existing one a bit. If
* extend fails, we need to propagate the failure up and restart the
- * transaction in the top-level truncate loop. --sct
+ * transaction in the top-level truncate loop. --sct
*/
-static handle_t *start_transaction(struct inode *inode)
+static handle_t *start_transaction(struct inode *inode)
{
handle_t *result;
ext3_orphan_del(handle, inode);
EXT3_I(inode)->i_dtime = get_seconds();
- /*
+ /*
* One subtle ordering requirement: if anything has gone wrong
* (transaction abort, IO errors, whatever), then we can still
* do these next steps (the fs will already have been marked as
* having errors), but we can't free the inode if the mark_dirty
- * fails.
+ * fails.
*/
if (ext3_mark_inode_dirty(handle, inode))
/* If that failed, just do the required in-core inode clear. */
* + if there is a block to the left of our position - allocate near it.
* + if pointer will live in indirect block - allocate near that block.
* + if pointer will live in inode - allocate in the same
- * cylinder group.
+ * cylinder group.
*
* In the latter case we colour the starting block by the callers PID to
* prevent it from clashing with concurrent allocations for a different inode
* ext3_blks_to_allocate: Look up the block map and count the number
* of direct blocks need to be allocated for the given branch.
*
- * @branch: chain of indirect blocks
+ * @branch: chain of indirect blocks
* @k: number of blocks need for indirect blocks
* @blks: number of data blocks to be mapped.
* @blocks_to_boundary: the offset in the indirect block
jbd_debug(5, "splicing indirect only\n");
BUFFER_TRACE(where->bh, "call ext3_journal_dirty_metadata");
err = ext3_journal_dirty_metadata(handle, where->bh);
- if (err)
+ if (err)
goto err_out;
} else {
/*
set_buffer_new(bh_result);
got_it:
map_bh(bh_result, inode->i_sb, le32_to_cpu(chain[depth-1].key));
- if (blocks_to_boundary == 0)
+ if (count > blocks_to_boundary)
set_buffer_boundary(bh_result);
err = count;
/* Clean up and exit */
static int ext3_get_block(struct inode *inode, sector_t iblock,
struct buffer_head *bh_result, int create)
{
- handle_t *handle = journal_current_handle();
+ handle_t *handle = ext3_journal_current_handle();
int ret = 0;
unsigned max_blocks = bh_result->b_size >> inode->i_blkbits;
buffer_trace_init(&dummy.b_history);
err = ext3_get_blocks_handle(handle, inode, block, 1,
&dummy, create, 1);
- if (err == 1) {
+ /*
+ * ext3_get_blocks_handle() returns number of blocks
+ * mapped. 0 in case of a HOLE.
+ */
+ if (err > 0) {
+ if (err > 1)
+ WARN_ON(1);
err = 0;
- } else if (err >= 0) {
- WARN_ON(1);
- err = -EIO;
}
*errp = err;
if (!err && buffer_mapped(&dummy)) {
return bh;
if (buffer_uptodate(bh))
return bh;
- ll_rw_block(READ, 1, &bh);
+ ll_rw_block(READ_META, 1, &bh);
wait_on_buffer(bh);
if (buffer_uptodate(bh))
return bh;
for ( bh = head, block_start = 0;
ret == 0 && (bh != head || !block_start);
- block_start = block_end, bh = next)
+ block_start = block_end, bh = next)
{
next = bh->b_this_page;
block_end = block_start + blocksize;
* So what we do is to rely on the fact that journal_stop/journal_start
* will _not_ run commit under these circumstances because handle->h_ref
* is elevated. We'll still have enough credits for the tiny quotafile
- * write.
+ * write.
*/
static int do_journal_get_write_access(handle_t *handle,
struct buffer_head *bh)
if (inode->i_size > EXT3_I(inode)->i_disksize) {
EXT3_I(inode)->i_disksize = inode->i_size;
ret2 = ext3_mark_inode_dirty(handle, inode);
- if (!ret)
+ if (!ret)
ret = ret2;
}
ret2 = ext3_journal_stop(handle);
return ret;
}
-/*
+/*
* bmap() is special. It gets used by applications such as lilo and by
* the swapper to find the on-disk block of a specific piece of data.
*
* filesystem and enables swap, then they may get a nasty shock when the
* data getting swapped to that swapfile suddenly gets overwritten by
* the original zero's written out previously to the journal and
- * awaiting writeback in the kernel's buffer cache.
+ * awaiting writeback in the kernel's buffer cache.
*
* So, if we see any bmap calls here on a modified, data-journaled file,
- * take extra steps to flush any blocks which might be in the cache.
+ * take extra steps to flush any blocks which might be in the cache.
*/
static sector_t ext3_bmap(struct address_space *mapping, sector_t block)
{
int err;
if (EXT3_I(inode)->i_state & EXT3_STATE_JDATA) {
- /*
+ /*
* This is a REALLY heavyweight approach, but the use of
* bmap on dirty files is expected to be extremely rare:
* only if we run lilo or swapon on a freshly made file
- * do we expect this to happen.
+ * do we expect this to happen.
*
* (bmap requires CAP_SYS_RAWIO so this does not
* represent an unprivileged user DOS attack --- we'd be
* in trouble if mortal users could trigger this path at
- * will.)
+ * will.)
*
* NB. EXT3_STATE_JDATA is not set on files other than
* regular files. If somebody wants to bmap a directory
*/
/*
- * And attach them to the current transaction. But only if
+ * And attach them to the current transaction. But only if
* block_write_full_page() succeeded. Otherwise they are unmapped,
* and generally junk.
*/
}
}
- ret = blockdev_direct_IO(rw, iocb, inode, inode->i_sb->s_bdev, iov,
+ ret = blockdev_direct_IO(rw, iocb, inode, inode->i_sb->s_bdev, iov,
offset, nr_segs,
ext3_get_block, NULL);
/*
* Reacquire the handle: ext3_get_block() can restart the transaction
*/
- handle = journal_current_handle();
+ handle = ext3_journal_current_handle();
out_stop:
if (handle) {
struct inode *inode = mapping->host;
struct buffer_head *bh;
int err = 0;
- void *kaddr;
blocksize = inode->i_sb->s_blocksize;
length = blocksize - (offset & (blocksize - 1));
*/
if (!page_has_buffers(page) && test_opt(inode->i_sb, NOBH) &&
ext3_should_writeback_data(inode) && PageUptodate(page)) {
- kaddr = kmap_atomic(page, KM_USER0);
- memset(kaddr + offset, 0, length);
- flush_dcache_page(page);
- kunmap_atomic(kaddr, KM_USER0);
+ zero_user_page(page, offset, length, KM_USER0);
set_page_dirty(page);
goto unlock;
}
goto unlock;
}
- kaddr = kmap_atomic(page, KM_USER0);
- memset(kaddr + offset, 0, length);
- flush_dcache_page(page);
- kunmap_atomic(kaddr, KM_USER0);
-
+ zero_user_page(page, offset, length, KM_USER0);
BUFFER_TRACE(bh, "zeroed end of block");
err = 0;
__le32 *first, __le32 *last)
{
ext3_fsblk_t block_to_free = 0; /* Starting block # of a run */
- unsigned long count = 0; /* Number of blocks in the run */
+ unsigned long count = 0; /* Number of blocks in the run */
__le32 *block_to_free_p = NULL; /* Pointer into inode/ind
corresponding to
block_to_free */
} else if (nr == block_to_free + count) {
count++;
} else {
- ext3_clear_blocks(handle, inode, this_bh,
+ ext3_clear_blocks(handle, inode, this_bh,
block_to_free,
count, block_to_free_p, p);
block_to_free = nr;
*/
if (!bh) {
ext3_error(inode->i_sb, "ext3_free_branches",
- "Read failure, inode=%ld, block="E3FSBLK,
+ "Read failure, inode=%lu, block="E3FSBLK,
inode->i_ino, nr);
continue;
}
*p = 0;
BUFFER_TRACE(parent_bh,
"call ext3_journal_dirty_metadata");
- ext3_journal_dirty_metadata(handle,
+ ext3_journal_dirty_metadata(handle,
parent_bh);
}
}
*/
get_bh(bh);
bh->b_end_io = end_buffer_read_sync;
- submit_bh(READ, bh);
+ submit_bh(READ_META, bh);
wait_on_buffer(bh);
if (!buffer_uptodate(bh)) {
ext3_error(inode->i_sb, "ext3_get_inode_loc",
inode->i_flags |= S_DIRSYNC;
}
+/* Propagate flags from i_flags to EXT3_I(inode)->i_flags */
+void ext3_get_inode_flags(struct ext3_inode_info *ei)
+{
+ unsigned int flags = ei->vfs_inode.i_flags;
+
+ ei->i_flags &= ~(EXT3_SYNC_FL|EXT3_APPEND_FL|
+ EXT3_IMMUTABLE_FL|EXT3_NOATIME_FL|EXT3_DIRSYNC_FL);
+ if (flags & S_SYNC)
+ ei->i_flags |= EXT3_SYNC_FL;
+ if (flags & S_APPEND)
+ ei->i_flags |= EXT3_APPEND_FL;
+ if (flags & S_IMMUTABLE)
+ ei->i_flags |= EXT3_IMMUTABLE_FL;
+ if (flags & S_NOATIME)
+ ei->i_flags |= EXT3_NOATIME_FL;
+ if (flags & S_DIRSYNC)
+ ei->i_flags |= EXT3_DIRSYNC_FL;
+}
+
void ext3_read_inode(struct inode * inode)
{
struct ext3_iloc iloc;
}
inode->i_nlink = le16_to_cpu(raw_inode->i_links_count);
inode->i_size = le32_to_cpu(raw_inode->i_size);
- inode->i_atime.tv_sec = le32_to_cpu(raw_inode->i_atime);
- inode->i_ctime.tv_sec = le32_to_cpu(raw_inode->i_ctime);
- inode->i_mtime.tv_sec = le32_to_cpu(raw_inode->i_mtime);
+ inode->i_atime.tv_sec = (signed)le32_to_cpu(raw_inode->i_atime);
+ inode->i_ctime.tv_sec = (signed)le32_to_cpu(raw_inode->i_ctime);
+ inode->i_mtime.tv_sec = (signed)le32_to_cpu(raw_inode->i_mtime);
inode->i_atime.tv_nsec = inode->i_ctime.tv_nsec = inode->i_mtime.tv_nsec = 0;
ei->i_state = 0;
* recovery code: that's fine, we're about to complete
* the process of deleting those. */
}
- inode->i_blksize = PAGE_SIZE; /* This is the optimal IO size
- * (for stat), not the fs block
- * size */
inode->i_blocks = le32_to_cpu(raw_inode->i_blocks);
ei->i_flags = le32_to_cpu(raw_inode->i_flags);
#ifdef EXT3_FRAGMENTS
*/
ei->i_extra_isize = le16_to_cpu(raw_inode->i_extra_isize);
if (EXT3_GOOD_OLD_INODE_SIZE + ei->i_extra_isize >
- EXT3_INODE_SIZE(inode->i_sb))
+ EXT3_INODE_SIZE(inode->i_sb)) {
+ brelse (bh);
goto bad_inode;
+ }
if (ei->i_extra_isize == 0) {
/* The extra space is currently unused. Use it. */
ei->i_extra_isize = sizeof(struct ext3_inode) -
if (raw_inode->i_block[0])
init_special_inode(inode, inode->i_mode,
old_decode_dev(le32_to_cpu(raw_inode->i_block[0])));
- else
+ else
init_special_inode(inode, inode->i_mode,
new_decode_dev(le32_to_cpu(raw_inode->i_block[1])));
}
*
* The caller must have write access to iloc->bh.
*/
-static int ext3_do_update_inode(handle_t *handle,
- struct inode *inode,
+static int ext3_do_update_inode(handle_t *handle,
+ struct inode *inode,
struct ext3_iloc *iloc)
{
struct ext3_inode *raw_inode = ext3_raw_inode(iloc);
if (ei->i_state & EXT3_STATE_NEW)
memset(raw_inode, 0, EXT3_SB(inode->i_sb)->s_inode_size);
+ ext3_get_inode_flags(ei);
raw_inode->i_mode = cpu_to_le16(inode->i_mode);
if(!(test_opt(inode->i_sb, NO_UID32))) {
raw_inode->i_uid_low = cpu_to_le16(low_16_bits(inode->i_uid));
* commit will leave the blocks being flushed in an unused state on
* disk. (On recovery, the inode will get truncated and the blocks will
* be freed, so we have a strong guarantee that no future commit will
- * leave these blocks visible to the user.)
+ * leave these blocks visible to the user.)
*
* Called with inode->sem down.
*/
return err;
}
-/*
+/*
* On success, We end up with an outstanding reference count against
- * iloc->bh. This _must_ be cleaned up later.
+ * iloc->bh. This _must_ be cleaned up later.
*/
int
-ext3_reserve_inode_write(handle_t *handle, struct inode *inode,
+ext3_reserve_inode_write(handle_t *handle, struct inode *inode,
struct ext3_iloc *iloc)
{
int err = 0;
}
#if 0
-/*
+/*
* Bind an inode's backing buffer_head into this transaction, to prevent
* it from being flushed to disk early. Unlike
* ext3_reserve_inode_write, this leaves behind no bh reference and
BUFFER_TRACE(iloc.bh, "get_write_access");
err = journal_get_write_access(handle, iloc.bh);
if (!err)
- err = ext3_journal_dirty_metadata(handle,
+ err = ext3_journal_dirty_metadata(handle,
iloc.bh);
brelse(iloc.bh);
}
*/
journal = EXT3_JOURNAL(inode);
- if (is_journal_aborted(journal) || IS_RDONLY(inode))
+ if (is_journal_aborted(journal))
return -EROFS;
journal_lock_updates(journal);