* 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
BUFFER_TRACE(bh, "call ext3_journal_revoke");
err = ext3_journal_revoke(handle, blocknr, bh);
if (err)
- ext3_abort(inode->i_sb, __FUNCTION__,
+ ext3_abort(inode->i_sb, __func__,
"error %d when attempting revoke", err);
BUFFER_TRACE(bh, "exit");
return err;
* 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. */
* @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.
* + 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_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;
* 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 {
/*
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 = journal_current_handle();
- int ret = 0;
+ handle_t *handle = ext3_journal_current_handle();
+ 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 (buffer_new(&dummy)) {
J_ASSERT(create != 0);
- J_ASSERT(handle != 0);
+ J_ASSERT(handle != NULL);
/*
* Now that we do not always journal data, we should
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)
return ext3_journal_get_write_access(handle, bh);
}
-static int ext3_prepare_write(struct file *file, struct page *page,
- unsigned from, unsigned to)
+static int ext3_write_begin(struct file *file, struct address_space *mapping,
+ loff_t pos, unsigned len, unsigned flags,
+ struct page **pagep, void **fsdata)
{
- struct inode *inode = page->mapping->host;
+ struct inode *inode = mapping->host;
int ret, needed_blocks = ext3_writepage_trans_blocks(inode);
handle_t *handle;
int retries = 0;
+ struct page *page;
+ pgoff_t index;
+ unsigned from, to;
+
+ index = pos >> PAGE_CACHE_SHIFT;
+ from = pos & (PAGE_CACHE_SIZE - 1);
+ to = from + len;
retry:
+ page = __grab_cache_page(mapping, index);
+ if (!page)
+ return -ENOMEM;
+ *pagep = page;
+
handle = ext3_journal_start(inode, needed_blocks);
if (IS_ERR(handle)) {
+ unlock_page(page);
+ page_cache_release(page);
ret = PTR_ERR(handle);
goto out;
}
- if (test_opt(inode->i_sb, NOBH) && ext3_should_writeback_data(inode))
- ret = nobh_prepare_write(page, from, to, ext3_get_block);
- else
- ret = block_prepare_write(page, from, to, ext3_get_block);
+ ret = block_write_begin(file, mapping, pos, len, flags, pagep, fsdata,
+ ext3_get_block);
if (ret)
- goto prepare_write_failed;
+ goto write_begin_failed;
if (ext3_should_journal_data(inode)) {
ret = walk_page_buffers(handle, page_buffers(page),
from, to, NULL, do_journal_get_write_access);
}
-prepare_write_failed:
- if (ret)
+write_begin_failed:
+ if (ret) {
ext3_journal_stop(handle);
+ unlock_page(page);
+ page_cache_release(page);
+ }
if (ret == -ENOSPC && ext3_should_retry_alloc(inode->i_sb, &retries))
goto retry;
out:
return ret;
}
+
int ext3_journal_dirty_data(handle_t *handle, struct buffer_head *bh)
{
int err = journal_dirty_data(handle, bh);
if (err)
- ext3_journal_abort_handle(__FUNCTION__, __FUNCTION__,
- bh, handle,err);
+ ext3_journal_abort_handle(__func__, __func__,
+ bh, handle, err);
return err;
}
-/* For commit_write() in data=journal mode */
-static int commit_write_fn(handle_t *handle, struct buffer_head *bh)
+/* For write_end() in data=journal mode */
+static int write_end_fn(handle_t *handle, struct buffer_head *bh)
{
if (!buffer_mapped(bh) || buffer_freed(bh))
return 0;
}
/*
+ * Generic write_end handler for ordered and writeback ext3 journal modes.
+ * We can't use generic_write_end, because that unlocks the page and we need to
+ * unlock the page after ext3_journal_stop, but ext3_journal_stop must run
+ * after block_write_end.
+ */
+static int ext3_generic_write_end(struct file *file,
+ struct address_space *mapping,
+ loff_t pos, unsigned len, unsigned copied,
+ struct page *page, void *fsdata)
+{
+ struct inode *inode = file->f_mapping->host;
+
+ copied = block_write_end(file, mapping, pos, len, copied, page, fsdata);
+
+ if (pos+copied > inode->i_size) {
+ i_size_write(inode, pos+copied);
+ mark_inode_dirty(inode);
+ }
+
+ return copied;
+}
+
+/*
* We need to pick up the new inode size which generic_commit_write gave us
* `file' can be NULL - eg, when called from page_symlink().
*
* ext3 never places buffers on inode->i_mapping->private_list. metadata
* buffers are managed internally.
*/
-static int ext3_ordered_commit_write(struct file *file, struct page *page,
- unsigned from, unsigned to)
+static int ext3_ordered_write_end(struct file *file,
+ struct address_space *mapping,
+ loff_t pos, unsigned len, unsigned copied,
+ struct page *page, void *fsdata)
{
handle_t *handle = ext3_journal_current_handle();
- struct inode *inode = page->mapping->host;
+ struct inode *inode = file->f_mapping->host;
+ unsigned from, to;
int ret = 0, ret2;
+ from = pos & (PAGE_CACHE_SIZE - 1);
+ to = from + len;
+
ret = walk_page_buffers(handle, page_buffers(page),
from, to, NULL, ext3_journal_dirty_data);
if (ret == 0) {
/*
- * generic_commit_write() will run mark_inode_dirty() if i_size
+ * generic_write_end() will run mark_inode_dirty() if i_size
* changes. So let's piggyback the i_disksize mark_inode_dirty
* into that.
*/
loff_t new_i_size;
- new_i_size = ((loff_t)page->index << PAGE_CACHE_SHIFT) + to;
+ new_i_size = pos + copied;
if (new_i_size > EXT3_I(inode)->i_disksize)
EXT3_I(inode)->i_disksize = new_i_size;
- ret = generic_commit_write(file, page, from, to);
+ ret2 = ext3_generic_write_end(file, mapping, pos, len, copied,
+ page, fsdata);
+ copied = ret2;
+ if (ret2 < 0)
+ ret = ret2;
}
ret2 = ext3_journal_stop(handle);
if (!ret)
ret = ret2;
- return ret;
+ unlock_page(page);
+ page_cache_release(page);
+
+ return ret ? ret : copied;
}
-static int ext3_writeback_commit_write(struct file *file, struct page *page,
- unsigned from, unsigned to)
+static int ext3_writeback_write_end(struct file *file,
+ struct address_space *mapping,
+ loff_t pos, unsigned len, unsigned copied,
+ struct page *page, void *fsdata)
{
handle_t *handle = ext3_journal_current_handle();
- struct inode *inode = page->mapping->host;
+ struct inode *inode = file->f_mapping->host;
int ret = 0, ret2;
loff_t new_i_size;
- new_i_size = ((loff_t)page->index << PAGE_CACHE_SHIFT) + to;
+ new_i_size = pos + copied;
if (new_i_size > EXT3_I(inode)->i_disksize)
EXT3_I(inode)->i_disksize = new_i_size;
- if (test_opt(inode->i_sb, NOBH) && ext3_should_writeback_data(inode))
- ret = nobh_commit_write(file, page, from, to);
- else
- ret = generic_commit_write(file, page, from, to);
+ ret2 = ext3_generic_write_end(file, mapping, pos, len, copied,
+ page, fsdata);
+ copied = ret2;
+ if (ret2 < 0)
+ ret = ret2;
ret2 = ext3_journal_stop(handle);
if (!ret)
ret = ret2;
- return ret;
+ unlock_page(page);
+ page_cache_release(page);
+
+ return ret ? ret : copied;
}
-static int ext3_journalled_commit_write(struct file *file,
- struct page *page, unsigned from, unsigned to)
+static int ext3_journalled_write_end(struct file *file,
+ struct address_space *mapping,
+ loff_t pos, unsigned len, unsigned copied,
+ struct page *page, void *fsdata)
{
handle_t *handle = ext3_journal_current_handle();
- struct inode *inode = page->mapping->host;
+ struct inode *inode = mapping->host;
int ret = 0, ret2;
int partial = 0;
- loff_t pos;
+ unsigned from, to;
- /*
- * Here we duplicate the generic_commit_write() functionality
- */
- pos = ((loff_t)page->index << PAGE_CACHE_SHIFT) + to;
+ from = pos & (PAGE_CACHE_SIZE - 1);
+ to = from + len;
+
+ if (copied < len) {
+ if (!PageUptodate(page))
+ copied = 0;
+ page_zero_new_buffers(page, from+copied, to);
+ }
ret = walk_page_buffers(handle, page_buffers(page), from,
- to, &partial, commit_write_fn);
+ to, &partial, write_end_fn);
if (!partial)
SetPageUptodate(page);
- if (pos > inode->i_size)
- i_size_write(inode, pos);
+ if (pos+copied > inode->i_size)
+ i_size_write(inode, pos+copied);
EXT3_I(inode)->i_state |= EXT3_STATE_JDATA;
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);
if (!ret)
ret = ret2;
- return ret;
+ unlock_page(page);
+ page_cache_release(page);
+
+ return ret ? ret : copied;
}
-/*
+/*
* 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.
*/
PAGE_CACHE_SIZE, NULL, do_journal_get_write_access);
err = walk_page_buffers(handle, page_buffers(page), 0,
- PAGE_CACHE_SIZE, NULL, commit_write_fn);
+ PAGE_CACHE_SIZE, NULL, write_end_fn);
if (ret == 0)
ret = err;
EXT3_I(inode)->i_state |= EXT3_STATE_JDATA;
* 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);
}
}
- 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();
-
-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;
}
static const struct address_space_operations ext3_ordered_aops = {
- .readpage = ext3_readpage,
- .readpages = ext3_readpages,
- .writepage = ext3_ordered_writepage,
- .sync_page = block_sync_page,
- .prepare_write = ext3_prepare_write,
- .commit_write = ext3_ordered_commit_write,
- .bmap = ext3_bmap,
- .invalidatepage = ext3_invalidatepage,
- .releasepage = ext3_releasepage,
- .direct_IO = ext3_direct_IO,
- .migratepage = buffer_migrate_page,
+ .readpage = ext3_readpage,
+ .readpages = ext3_readpages,
+ .writepage = ext3_ordered_writepage,
+ .sync_page = block_sync_page,
+ .write_begin = ext3_write_begin,
+ .write_end = ext3_ordered_write_end,
+ .bmap = ext3_bmap,
+ .invalidatepage = ext3_invalidatepage,
+ .releasepage = ext3_releasepage,
+ .direct_IO = ext3_direct_IO,
+ .migratepage = buffer_migrate_page,
+ .is_partially_uptodate = block_is_partially_uptodate,
};
static const struct address_space_operations ext3_writeback_aops = {
- .readpage = ext3_readpage,
- .readpages = ext3_readpages,
- .writepage = ext3_writeback_writepage,
- .sync_page = block_sync_page,
- .prepare_write = ext3_prepare_write,
- .commit_write = ext3_writeback_commit_write,
- .bmap = ext3_bmap,
- .invalidatepage = ext3_invalidatepage,
- .releasepage = ext3_releasepage,
- .direct_IO = ext3_direct_IO,
- .migratepage = buffer_migrate_page,
+ .readpage = ext3_readpage,
+ .readpages = ext3_readpages,
+ .writepage = ext3_writeback_writepage,
+ .sync_page = block_sync_page,
+ .write_begin = ext3_write_begin,
+ .write_end = ext3_writeback_write_end,
+ .bmap = ext3_bmap,
+ .invalidatepage = ext3_invalidatepage,
+ .releasepage = ext3_releasepage,
+ .direct_IO = ext3_direct_IO,
+ .migratepage = buffer_migrate_page,
+ .is_partially_uptodate = block_is_partially_uptodate,
};
static const struct address_space_operations ext3_journalled_aops = {
- .readpage = ext3_readpage,
- .readpages = ext3_readpages,
- .writepage = ext3_journalled_writepage,
- .sync_page = block_sync_page,
- .prepare_write = ext3_prepare_write,
- .commit_write = ext3_journalled_commit_write,
- .set_page_dirty = ext3_journalled_set_page_dirty,
- .bmap = ext3_bmap,
- .invalidatepage = ext3_invalidatepage,
- .releasepage = ext3_releasepage,
+ .readpage = ext3_readpage,
+ .readpages = ext3_readpages,
+ .writepage = ext3_journalled_writepage,
+ .sync_page = block_sync_page,
+ .write_begin = ext3_write_begin,
+ .write_end = ext3_journalled_write_end,
+ .set_page_dirty = ext3_journalled_set_page_dirty,
+ .bmap = ext3_bmap,
+ .invalidatepage = ext3_invalidatepage,
+ .releasepage = ext3_releasepage,
+ .is_partially_uptodate = block_is_partially_uptodate,
};
void ext3_set_aops(struct inode *inode)
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, offset, length);
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, offset, length);
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 (this_bh) {
BUFFER_TRACE(this_bh, "call ext3_journal_dirty_metadata");
- ext3_journal_dirty_metadata(handle, this_bh);
+
+ /*
+ * The buffer head should have an attached journal head at this
+ * point. However, if the data is corrupted and an indirect
+ * block pointed to itself, it would have been detached when
+ * the block was cleared. Check for this instead of OOPSing.
+ */
+ if (bh2jh(this_bh))
+ ext3_journal_dirty_metadata(handle, this_bh);
+ else
+ ext3_error(inode->i_sb, "ext3_free_data",
+ "circular indirect block detected, "
+ "inode=%lu, block=%llu",
+ inode->i_ino,
+ (unsigned long long)this_bh->b_blocknr);
}
}
*/
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);
}
}
}
}
+int ext3_can_truncate(struct inode *inode)
+{
+ if (IS_APPEND(inode) || IS_IMMUTABLE(inode))
+ return 0;
+ if (S_ISREG(inode->i_mode))
+ return 1;
+ if (S_ISDIR(inode->i_mode))
+ return 1;
+ if (S_ISLNK(inode->i_mode))
+ return !ext3_inode_is_fast_symlink(inode);
+ return 0;
+}
+
/*
* ext3_truncate()
*
unsigned blocksize = inode->i_sb->s_blocksize;
struct page *page;
- if (!(S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) ||
- S_ISLNK(inode->i_mode)))
- return;
- if (ext3_inode_is_fast_symlink(inode))
- return;
- if (IS_APPEND(inode) || IS_IMMUTABLE(inode))
+ if (!ext3_can_truncate(inode))
return;
/*
static ext3_fsblk_t ext3_get_inode_block(struct super_block *sb,
unsigned long ino, struct ext3_iloc *iloc)
{
- unsigned long desc, group_desc, block_group;
+ unsigned long block_group;
unsigned long offset;
ext3_fsblk_t block;
- struct buffer_head *bh;
- struct ext3_group_desc * gdp;
+ struct ext3_group_desc *gdp;
if (!ext3_valid_inum(sb, ino)) {
/*
}
block_group = (ino - 1) / EXT3_INODES_PER_GROUP(sb);
- if (block_group >= EXT3_SB(sb)->s_groups_count) {
- ext3_error(sb,"ext3_get_inode_block","group >= groups count");
- return 0;
- }
- smp_rmb();
- group_desc = block_group >> EXT3_DESC_PER_BLOCK_BITS(sb);
- desc = block_group & (EXT3_DESC_PER_BLOCK(sb) - 1);
- bh = EXT3_SB(sb)->s_group_desc[group_desc];
- if (!bh) {
- ext3_error (sb, "ext3_get_inode_block",
- "Descriptor not loaded");
+ gdp = ext3_get_group_desc(sb, block_group, NULL);
+ if (!gdp)
return 0;
- }
-
- gdp = (struct ext3_group_desc *)bh->b_data;
/*
* Figure out the offset within the block group inode table
*/
offset = ((ino - 1) % EXT3_INODES_PER_GROUP(sb)) *
EXT3_INODE_SIZE(sb);
- block = le32_to_cpu(gdp[desc].bg_inode_table) +
+ block = le32_to_cpu(gdp->bg_inode_table) +
(offset >> EXT3_BLOCK_SIZE_BITS(sb));
iloc->block_group = block_group;
}
if (!buffer_uptodate(bh)) {
lock_buffer(bh);
+
+ /*
+ * If the buffer has the write error flag, we have failed
+ * to write out another inode in the same block. In this
+ * case, we don't have to read the block because we may
+ * read the old inode data successfully.
+ */
+ if (buffer_write_io_error(bh) && !buffer_uptodate(bh))
+ set_buffer_uptodate(bh);
+
if (buffer_uptodate(bh)) {
/* someone brought it uptodate while we waited */
unlock_buffer(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;
}
-void ext3_read_inode(struct inode * inode)
+/* 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;
+}
+
+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);
}
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;
!(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
* 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);
+ ret = -EIO;
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])));
}
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);
}
/*
*
* 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));
return 0;
if (ext3_journal_current_handle()) {
- jbd_debug(0, "called recursively, non-PF_MEMALLOC!\n");
+ jbd_debug(1, "called recursively, non-PF_MEMALLOC!\n");
dump_stack();
return -EIO;
}
* 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;
current_handle->h_transaction != handle->h_transaction) {
/* This task has a transaction open against a different fs */
printk(KERN_EMERG "%s: transactions do not match!\n",
- __FUNCTION__);
+ __func__);
} else {
jbd_debug(5, "marking dirty. outer handle=%p\n",
current_handle);
}
#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);