Hello,
this is just a trivial export needed for ordered mode rewrite.
Honza
--
Jan Kara <[email protected]>
SUSE Labs, CR
---
From: Jan Kara <[email protected]>
Date: Wed, 21 May 2008 17:05:23 +0200
Subject: [PATCH] vfs: export filemap_fdatawrite_range()
Make filemap_fdatawrite_range() function public, so that it can later
be used in ordered mode rewrite by JBD/JBD2.
Signed-off-by: Jan Kara <[email protected]>
---
include/linux/fs.h | 2 ++
mm/filemap.c | 3 ++-
2 files changed, 4 insertions(+), 1 deletions(-)
Index: linux-2.6-linus/include/linux/fs.h
===================================================================
--- linux-2.6-linus.orig/include/linux/fs.h
+++ linux-2.6-linus/include/linux/fs.h
@@ -1741,6 +1741,8 @@ extern int wait_on_page_writeback_range(
pgoff_t start, pgoff_t end);
extern int __filemap_fdatawrite_range(struct address_space *mapping,
loff_t start, loff_t end, int sync_mode);
+extern int filemap_fdatawrite_range(struct address_space *mapping,
+ loff_t start, loff_t end);
extern long do_fsync(struct file *file, int datasync);
extern void sync_supers(void);
Index: linux-2.6-linus/mm/filemap.c
===================================================================
--- linux-2.6-linus.orig/mm/filemap.c
+++ linux-2.6-linus/mm/filemap.c
@@ -236,11 +236,12 @@ int filemap_fdatawrite(struct address_sp
}
EXPORT_SYMBOL(filemap_fdatawrite);
-static int filemap_fdatawrite_range(struct address_space *mapping, loff_t start,
+int filemap_fdatawrite_range(struct address_space *mapping, loff_t start,
loff_t end)
{
return __filemap_fdatawrite_range(mapping, start, end, WB_SYNC_ALL);
}
+EXPORT_SYMBOL(filemap_fdatawrite_range);
/**
* filemap_flush - mostly a non-blocking flush
From: Jan Kara <[email protected]>
Date: Wed, 21 May 2008 17:01:22 +0200
Subject: [PATCH] ext4: Set journal pointer to NULL when journal is released
Set sbi->s_journal to NULL after we call journal_destroy(). This
will be later needed because after journal_destroy() is called,
ext4_clear_inode() can still be called for some inodes (e.g. root
inode) and we'll need to detect there that journal doesn't exists
anymore.
Signed-off-by: Jan Kara <[email protected]>
---
fs/ext4/super.c | 2 ++
1 files changed, 2 insertions(+), 0 deletions(-)
Index: linux-2.6-linus/fs/ext4/super.c
===================================================================
--- linux-2.6-linus.orig/fs/ext4/super.c
+++ linux-2.6-linus/fs/ext4/super.c
@@ -506,6 +506,7 @@ static void ext4_put_super (struct super
ext4_ext_release(sb);
ext4_xattr_put_super(sb);
jbd2_journal_destroy(sbi->s_journal);
+ sbi->s_journal = NULL;
if (!(sb->s_flags & MS_RDONLY)) {
EXT4_CLEAR_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER);
es->s_state = cpu_to_le16(sbi->s_mount_state);
@@ -2398,6 +2399,7 @@ cantfind_ext4:
failed_mount4:
jbd2_journal_destroy(sbi->s_journal);
+ sbi->s_journal = NULL;
failed_mount3:
percpu_counter_destroy(&sbi->s_freeblocks_counter);
percpu_counter_destroy(&sbi->s_freeinodes_counter);
From: Jan Kara <[email protected]>
Date: Wed, 21 May 2008 17:48:42 +0200
Subject: [PATCH] jbd2: Implement data=ordered mode handling via inodes
This patch adds necessary framework into JBD2 to be able to track inodes
with each transaction and write-out their dirty data during transaction
commit time.
Signed-off-by: Jan Kara <[email protected]>
---
fs/jbd2/commit.c | 90 +++++++++++++++++++++++++++++++++++++++++++++++++
fs/jbd2/journal.c | 52 ++++++++++++++++++++++++++++
fs/jbd2/transaction.c | 86 ++++++++++++++++++++++++++++++++++++++++++++++
include/linux/jbd2.h | 42 +++++++++++++++++++++++
4 files changed, 270 insertions(+), 0 deletions(-)
Index: linux-2.6-linus/fs/jbd2/commit.c
===================================================================
--- linux-2.6-linus.orig/fs/jbd2/commit.c
+++ linux-2.6-linus/fs/jbd2/commit.c
@@ -354,6 +354,81 @@ write_out_data:
journal_do_submit_data(wbuf, bufs);
}
+/*
+ * Submit all the data buffers of inode associated with the transaction to
+ * disk.
+ *
+ * We are in a committing transaction. Therefore no new inode can be added to
+ * our inode list. We use JI_COMMIT_RUNNING flag to protect inode we currently
+ * operate on from being released while we write out pages.
+ */
+static int journal_submit_inode_data_buffers(journal_t *journal,
+ transaction_t *commit_transaction)
+{
+ struct jbd2_inode *jinode;
+ int err, ret = 0;
+ struct address_space *mapping;
+
+ spin_lock(&journal->j_list_lock);
+ list_for_each_entry(jinode, &commit_transaction->t_inode_list, i_list) {
+ mapping = jinode->i_vfs_inode->i_mapping;
+ jinode->i_flags |= JI_COMMIT_RUNNING;
+ spin_unlock(&journal->j_list_lock);
+ err = filemap_fdatawrite_range(mapping, 0,
+ i_size_read(jinode->i_vfs_inode));
+ if (!ret)
+ ret = err;
+ spin_lock(&journal->j_list_lock);
+ J_ASSERT(jinode->i_transaction == commit_transaction);
+ jinode->i_flags &= ~JI_COMMIT_RUNNING;
+ wake_up_bit(&jinode->i_flags, __JI_COMMIT_RUNNING);
+ }
+ spin_unlock(&journal->j_list_lock);
+ return ret;
+}
+
+/*
+ * Wait for data submitted for writeout, refile inodes to proper
+ * transaction if needed.
+ *
+ */
+static int journal_finish_inode_data_buffers(journal_t *journal,
+ transaction_t *commit_transaction)
+{
+ struct jbd2_inode *jinode, *next_i;
+ int err, ret = 0;
+
+ /* For locking, see the comment in journal_submit_inode_data_buffers() */
+ spin_lock(&journal->j_list_lock);
+ list_for_each_entry(jinode, &commit_transaction->t_inode_list, i_list) {
+ jinode->i_flags |= JI_COMMIT_RUNNING;
+ spin_unlock(&journal->j_list_lock);
+ err = filemap_fdatawait(jinode->i_vfs_inode->i_mapping);
+ if (!ret)
+ ret = err;
+ spin_lock(&journal->j_list_lock);
+ jinode->i_flags &= ~JI_COMMIT_RUNNING;
+ wake_up_bit(&jinode->i_flags, __JI_COMMIT_RUNNING);
+ }
+
+ /* Now refile inode to proper lists */
+ list_for_each_entry_safe(jinode, next_i,
+ &commit_transaction->t_inode_list, i_list) {
+ list_del(&jinode->i_list);
+ if (jinode->i_next_transaction) {
+ jinode->i_transaction = jinode->i_next_transaction;
+ jinode->i_next_transaction = NULL;
+ list_add(&jinode->i_list,
+ &jinode->i_transaction->t_inode_list);
+ } else {
+ jinode->i_transaction = NULL;
+ }
+ }
+ spin_unlock(&journal->j_list_lock);
+
+ return ret;
+}
+
static __u32 jbd2_checksum_data(__u32 crc32_sum, struct buffer_head *bh)
{
struct page *page = bh->b_page;
@@ -528,6 +603,9 @@ void jbd2_journal_commit_transaction(jou
*/
err = 0;
journal_submit_data_buffers(journal, commit_transaction);
+ err = journal_submit_inode_data_buffers(journal, commit_transaction);
+ if (err)
+ jbd2_journal_abort(journal, err);
/*
* Wait for all previously submitted IO to complete if commit
@@ -759,6 +837,17 @@ start_journal_io:
__jbd2_journal_abort_hard(journal);
}
+ /*
+ * This is the right place to wait for data buffers both for ASYNC
+ * and !ASYNC commit. If commit is ASYNC, we need to wait only after
+ * the commit block went to disk (which happens above). If commit is
+ * SYNC, we need to wait for data buffers before we start writing
+ * commit block, which happens below in such setting.
+ */
+ err = journal_finish_inode_data_buffers(journal, commit_transaction);
+ if (err)
+ jbd2_journal_abort(journal, err);
+
/* Lo and behold: we have just managed to send a transaction to
the log. Before we can commit it, wait for the IO so far to
complete. Control buffers being written are on the
@@ -879,6 +968,7 @@ wait_for_iobuf:
jbd_debug(3, "JBD: commit phase 7\n");
J_ASSERT(commit_transaction->t_sync_datalist == NULL);
+ J_ASSERT(list_empty(&commit_transaction->t_inode_list));
J_ASSERT(commit_transaction->t_buffers == NULL);
J_ASSERT(commit_transaction->t_checkpoint_list == NULL);
J_ASSERT(commit_transaction->t_iobuf_list == NULL);
Index: linux-2.6-linus/fs/jbd2/journal.c
===================================================================
--- linux-2.6-linus.orig/fs/jbd2/journal.c
+++ linux-2.6-linus/fs/jbd2/journal.c
@@ -82,6 +82,10 @@ EXPORT_SYMBOL(jbd2_journal_blocks_per_pa
EXPORT_SYMBOL(jbd2_journal_invalidatepage);
EXPORT_SYMBOL(jbd2_journal_try_to_free_buffers);
EXPORT_SYMBOL(jbd2_journal_force_commit);
+EXPORT_SYMBOL(jbd2_journal_file_inode);
+EXPORT_SYMBOL(jbd2_journal_init_jbd_inode);
+EXPORT_SYMBOL(jbd2_journal_release_jbd_inode);
+EXPORT_SYMBOL(jbd2_journal_begin_ordered_truncate);
static int journal_convert_superblock_v1(journal_t *, journal_superblock_t *);
static void __journal_abort_soft (journal_t *journal, int errno);
@@ -2195,6 +2199,54 @@ void jbd2_journal_put_journal_head(struc
}
/*
+ * Initialize jbd inode head
+ */
+void jbd2_journal_init_jbd_inode(struct jbd2_inode *jinode, struct inode *inode)
+{
+ jinode->i_transaction = NULL;
+ jinode->i_next_transaction = NULL;
+ jinode->i_vfs_inode = inode;
+ jinode->i_flags = 0;
+ INIT_LIST_HEAD(&jinode->i_list);
+}
+
+/*
+ * Function to be called before we start removing inode from memory (i.e.,
+ * clear_inode() is a fine place to be called from). It removes inode from
+ * transaction's lists.
+ */
+void jbd2_journal_release_jbd_inode(journal_t *journal,
+ struct jbd2_inode *jinode)
+{
+ int writeout = 0;
+
+ if (!journal)
+ return;
+restart:
+ spin_lock(&journal->j_list_lock);
+ /* Is commit writing out inode - we have to wait */
+ if (jinode->i_flags & JI_COMMIT_RUNNING) {
+ wait_queue_head_t *wq;
+ DEFINE_WAIT_BIT(wait, &jinode->i_flags, __JI_COMMIT_RUNNING);
+ wq = bit_waitqueue(&jinode->i_flags, __JI_COMMIT_RUNNING);
+ prepare_to_wait(wq, &wait.wait, TASK_UNINTERRUPTIBLE);
+ spin_unlock(&journal->j_list_lock);
+ schedule();
+ finish_wait(wq, &wait.wait);
+ goto restart;
+ }
+
+ /* Do we need to wait for data writeback? */
+ if (journal->j_committing_transaction == jinode->i_transaction)
+ writeout = 1;
+ if (jinode->i_transaction) {
+ list_del(&jinode->i_list);
+ jinode->i_transaction = NULL;
+ }
+ spin_unlock(&journal->j_list_lock);
+}
+
+/*
* debugfs tunables
*/
#ifdef CONFIG_JBD2_DEBUG
Index: linux-2.6-linus/fs/jbd2/transaction.c
===================================================================
--- linux-2.6-linus.orig/fs/jbd2/transaction.c
+++ linux-2.6-linus/fs/jbd2/transaction.c
@@ -51,6 +51,7 @@ jbd2_get_transaction(journal_t *journal,
transaction->t_tid = journal->j_transaction_sequence++;
transaction->t_expires = jiffies + journal->j_commit_interval;
spin_lock_init(&transaction->t_handle_lock);
+ INIT_LIST_HEAD(&transaction->t_inode_list);
/* Set up the commit timer for the new transaction. */
journal->j_commit_timer.expires = round_jiffies(transaction->t_expires);
@@ -2195,3 +2196,88 @@ void jbd2_journal_refile_buffer(journal_
spin_unlock(&journal->j_list_lock);
__brelse(bh);
}
+
+/*
+ * File inode in the inode list of the handle's transaction
+ */
+int jbd2_journal_file_inode(handle_t *handle, struct jbd2_inode *jinode)
+{
+ transaction_t *transaction = handle->h_transaction;
+ journal_t *journal = transaction->t_journal;
+
+ if (is_handle_aborted(handle))
+ return -EIO;
+
+ jbd_debug(4, "Adding inode %lu, tid:%d\n", jinode->i_vfs_inode->i_ino,
+ transaction->t_tid);
+
+ /*
+ * First check whether inode isn't already on the transaction's
+ * lists without taking the lock. Note that this check is safe
+ * without the lock as we cannot race with somebody removing inode
+ * from the transaction. The reason is that we remove inode from the
+ * transaction only in journal_release_jbd_inode() and when we commit
+ * the transaction. We are guarded from the first case by holding
+ * a reference to the inode. We are safe against the second case
+ * because if jinode->i_transaction == transaction, commit code
+ * cannot touch the transaction because we hold reference to it,
+ * and if jinode->i_next_transaction == transaction, commit code
+ * will only file the inode where we want it.
+ */
+ if (jinode->i_transaction == transaction ||
+ jinode->i_next_transaction == transaction)
+ return 0;
+
+ spin_lock(&journal->j_list_lock);
+
+ if (jinode->i_transaction == transaction ||
+ jinode->i_next_transaction == transaction)
+ goto done;
+
+ /* On some different transaction's list - should be
+ * the committing one */
+ if (jinode->i_transaction) {
+ J_ASSERT(jinode->i_next_transaction == NULL);
+ J_ASSERT(jinode->i_transaction ==
+ journal->j_committing_transaction);
+ jinode->i_next_transaction = transaction;
+ goto done;
+ }
+ /* Not on any transaction list... */
+ J_ASSERT(!jinode->i_next_transaction);
+ jinode->i_transaction = transaction;
+ list_add(&jinode->i_list, &transaction->t_inode_list);
+done:
+ spin_unlock(&journal->j_list_lock);
+
+ return 0;
+}
+
+/*
+ * This function must be called when inode is journaled in ordered mode
+ * before truncation happens. It starts writeout of truncated part in
+ * case it is in the committing transaction so that we stand to ordered
+ * mode consistency guarantees.
+ */
+int jbd2_journal_begin_ordered_truncate(struct jbd2_inode *inode,
+ loff_t new_size)
+{
+ journal_t *journal;
+ transaction_t *commit_trans;
+ int ret = 0;
+
+ if (!inode->i_transaction && !inode->i_next_transaction)
+ goto out;
+ journal = inode->i_transaction->t_journal;
+ spin_lock(&journal->j_state_lock);
+ commit_trans = journal->j_committing_transaction;
+ spin_unlock(&journal->j_state_lock);
+ if (inode->i_transaction == commit_trans) {
+ ret = filemap_fdatawrite_range(inode->i_vfs_inode->i_mapping,
+ new_size, LLONG_MAX);
+ if (ret)
+ jbd2_journal_abort(journal, ret);
+ }
+out:
+ return ret;
+}
Index: linux-2.6-linus/include/linux/jbd2.h
===================================================================
--- linux-2.6-linus.orig/include/linux/jbd2.h
+++ linux-2.6-linus/include/linux/jbd2.h
@@ -381,6 +381,38 @@ static inline void jbd_unlock_bh_journal
bit_spin_unlock(BH_JournalHead, &bh->b_state);
}
+/* Flags in jbd_inode->i_flags */
+#define __JI_COMMIT_RUNNING 0
+/* Commit of the inode data in progress. We use this flag to protect us from
+ * concurrent deletion of inode. We cannot use reference to inode for this
+ * since we cannot afford doing last iput() on behalf of kjournald
+ */
+#define JI_COMMIT_RUNNING (1 << __JI_COMMIT_RUNNING)
+
+/**
+ * struct jbd_inode is the structure linking inodes in ordered mode
+ * present in a transaction so that we can sync them during commit.
+ */
+struct jbd2_inode {
+ /* Which transaction does this inode belong to? Either the running
+ * transaction or the committing one. [j_list_lock] */
+ transaction_t *i_transaction;
+
+ /* Pointer to the running transaction modifying inode's data in case
+ * there is already a committing transaction touching it. [j_list_lock] */
+ transaction_t *i_next_transaction;
+
+ /* List of inodes in the i_transaction [j_list_lock] */
+ struct list_head i_list;
+
+ /* VFS inode this inode belongs to [constant during the lifetime
+ * of the structure] */
+ struct inode *i_vfs_inode;
+
+ /* Flags of inode [j_list_lock] */
+ unsigned int i_flags;
+};
+
struct jbd2_revoke_table_s;
/**
@@ -567,6 +599,12 @@ struct transaction_s
struct journal_head *t_log_list;
/*
+ * List of inodes whose data we've modified in data=ordered mode.
+ * [j_list_lock]
+ */
+ struct list_head t_inode_list;
+
+ /*
* Protects info related to handles
*/
spinlock_t t_handle_lock;
@@ -1043,6 +1081,10 @@ extern void jbd2_journal_ack_err (
extern int jbd2_journal_clear_err (journal_t *);
extern int jbd2_journal_bmap(journal_t *, unsigned long, unsigned long long *);
extern int jbd2_journal_force_commit(journal_t *);
+extern int jbd2_journal_file_inode(handle_t *handle, struct jbd2_inode *inode);
+extern int jbd2_journal_begin_ordered_truncate(struct jbd2_inode *inode, loff_t new_size);
+extern void jbd2_journal_init_jbd_inode(struct jbd2_inode *jinode, struct inode *inode);
+extern void jbd2_journal_release_jbd_inode(journal_t *journal, struct jbd2_inode *jinode);
/*
* journal_head management
From: Jan Kara <[email protected]>
Date: Thu, 22 May 2008 00:51:17 +0200
Subject: [PATCH] ext4: Use new framework for data=ordered mode in JBD2
Signed-off-by: Jan Kara <[email protected]>
---
fs/ext4/ext4_i.h | 1 +
fs/ext4/ext4_jbd2.h | 7 ++-
fs/ext4/ialloc.c | 1 +
fs/ext4/inode.c | 160 ++++++++++++++++++---------------------------------
fs/ext4/super.c | 4 +-
5 files changed, 67 insertions(+), 106 deletions(-)
Index: linux-2.6-linus/fs/ext4/ext4_i.h
===================================================================
--- linux-2.6-linus.orig/fs/ext4/ext4_i.h
+++ linux-2.6-linus/fs/ext4/ext4_i.h
@@ -150,6 +150,7 @@ struct ext4_inode_info {
*/
struct rw_semaphore i_data_sem;
struct inode vfs_inode;
+ struct jbd2_inode jinode;
unsigned long i_ext_generation;
struct ext4_ext_cache i_cached_extent;
Index: linux-2.6-linus/fs/ext4/ext4_jbd2.h
===================================================================
--- linux-2.6-linus.orig/fs/ext4/ext4_jbd2.h
+++ linux-2.6-linus/fs/ext4/ext4_jbd2.h
@@ -154,8 +154,6 @@ int __ext4_journal_dirty_metadata(const
#define ext4_journal_forget(handle, bh) \
__ext4_journal_forget(__FUNCTION__, (handle), (bh))
-int ext4_journal_dirty_data(handle_t *handle, struct buffer_head *bh);
-
handle_t *ext4_journal_start_sb(struct super_block *sb, int nblocks);
int __ext4_journal_stop(const char *where, handle_t *handle);
@@ -192,6 +190,11 @@ static inline int ext4_journal_force_com
return jbd2_journal_force_commit(journal);
}
+static inline int ext4_jbd2_file_inode(handle_t *handle, struct inode *inode)
+{
+ return jbd2_journal_file_inode(handle, &EXT4_I(inode)->jinode);
+}
+
/* super.c */
int ext4_force_commit(struct super_block *sb);
Index: linux-2.6-linus/fs/ext4/ialloc.c
===================================================================
--- linux-2.6-linus.orig/fs/ext4/ialloc.c
+++ linux-2.6-linus/fs/ext4/ialloc.c
@@ -820,6 +820,7 @@ got:
ei->i_state = EXT4_STATE_NEW;
ei->i_extra_isize = EXT4_SB(sb)->s_want_extra_isize;
+ jbd2_journal_init_jbd_inode(&ei->jinode, inode);
ret = inode;
if(DQUOT_ALLOC_INODE(inode)) {
Index: linux-2.6-linus/fs/ext4/inode.c
===================================================================
--- linux-2.6-linus.orig/fs/ext4/inode.c
+++ linux-2.6-linus/fs/ext4/inode.c
@@ -39,6 +39,13 @@
#include "xattr.h"
#include "acl.h"
+static inline int ext4_begin_ordered_truncate(struct inode *inode,
+ loff_t new_size)
+{
+ return jbd2_journal_begin_ordered_truncate(&EXT4_I(inode)->jinode,
+ new_size);
+}
+
/*
* Test whether an inode is a fast symlink.
*/
@@ -181,6 +188,8 @@ void ext4_delete_inode (struct inode * i
{
handle_t *handle;
+ if (ext4_should_order_data(inode))
+ ext4_begin_ordered_truncate(inode, 0);
truncate_inode_pages(&inode->i_data, 0);
if (is_bad_inode(inode))
@@ -1273,15 +1282,6 @@ out:
return ret;
}
-int ext4_journal_dirty_data(handle_t *handle, struct buffer_head *bh)
-{
- int err = jbd2_journal_dirty_data(handle, bh);
- if (err)
- ext4_journal_abort_handle(__func__, __func__,
- bh, handle, err);
- return err;
-}
-
/* For write_end() in data=journal mode */
static int write_end_fn(handle_t *handle, struct buffer_head *bh)
{
@@ -1311,8 +1311,7 @@ static int ext4_ordered_write_end(struct
from = pos & (PAGE_CACHE_SIZE - 1);
to = from + len;
- ret = walk_page_buffers(handle, page_buffers(page),
- from, to, NULL, ext4_journal_dirty_data);
+ ret = ext4_jbd2_file_inode(handle, inode);
if (ret == 0) {
/*
@@ -1472,25 +1471,22 @@ static int bput_one(handle_t *handle, st
return 0;
}
-static int jbd2_journal_dirty_data_fn(handle_t *handle, struct buffer_head *bh)
-{
- if (buffer_mapped(bh))
- return ext4_journal_dirty_data(handle, bh);
- return 0;
-}
-
static int ext4_bh_unmapped_or_delay(handle_t *handle, struct buffer_head *bh)
{
return !buffer_mapped(bh) || buffer_delay(bh);
}
/*
- * Note that we don't need to start a transaction unless we're journaling
- * data because we should have holes filled from ext4_page_mkwrite(). If
- * we are journaling data, we cannot start transaction directly because
- * transaction start ranks above page lock so we have to do some magic...
+ * Note that we don't need to start a transaction unless we're journaling data
+ * because we should have holes filled from ext4_page_mkwrite(). We even don't
+ * need to file the inode to the transaction's list in ordered mode because if
+ * we are writing back data added by write(), the inode is already there and if
+ * we are writing back data modified via mmap(), noone guarantees in which
+ * transaction the data will hit the disk. In case we are journaling data, we
+ * cannot start transaction directly because transaction start ranks above page
+ * lock so we have to do some magic.
*
- * In all journalling modes block_write_full_page() will start the I/O.
+ * In all journaling modes block_write_full_page() will start the I/O.
*
* Problem:
*
@@ -1533,86 +1529,7 @@ static int ext4_bh_unmapped_or_delay(han
* us.
*
*/
-static int __ext4_ordered_writepage(struct page *page,
- struct writeback_control *wbc)
-{
- struct inode *inode = page->mapping->host;
- struct buffer_head *page_bufs;
- handle_t *handle = NULL;
- int ret = 0;
- int err;
-
- if (!page_has_buffers(page)) {
- create_empty_buffers(page, inode->i_sb->s_blocksize,
- (1 << BH_Dirty)|(1 << BH_Uptodate));
- }
- page_bufs = page_buffers(page);
- walk_page_buffers(handle, page_bufs, 0,
- PAGE_CACHE_SIZE, NULL, bget_one);
-
- ret = block_write_full_page(page, ext4_get_block, wbc);
-
- /*
- * The page can become unlocked at any point now, and
- * truncate can then come in and change things. So we
- * can't touch *page from now on. But *page_bufs is
- * safe due to elevated refcount.
- */
-
- /*
- * And attach them to the current transaction. But only if
- * block_write_full_page() succeeded. Otherwise they are unmapped,
- * and generally junk.
- */
- if (ret == 0) {
- handle = ext4_journal_start(inode,
- ext4_writepage_trans_blocks(inode));
- if (IS_ERR(handle)) {
- ret = PTR_ERR(handle);
- goto out_put;
- }
-
- ret = walk_page_buffers(handle, page_bufs, 0, PAGE_CACHE_SIZE,
- NULL, jbd2_journal_dirty_data_fn);
- err = ext4_journal_stop(handle);
- if (!ret)
- ret = err;
- }
-out_put:
- walk_page_buffers(handle, page_bufs, 0, PAGE_CACHE_SIZE, NULL,
- bput_one);
- return ret;
-}
-
-static int ext4_ordered_writepage(struct page *page,
- struct writeback_control *wbc)
-{
- struct inode *inode = page->mapping->host;
- loff_t size = i_size_read(inode);
- loff_t len;
-
- J_ASSERT(PageLocked(page));
- J_ASSERT(page_has_buffers(page));
- if (page->index == size >> PAGE_CACHE_SHIFT)
- len = size & ~PAGE_CACHE_MASK;
- else
- len = PAGE_CACHE_SIZE;
- BUG_ON(walk_page_buffers(NULL, page_buffers(page), 0, len, NULL,
- ext4_bh_unmapped_or_delay));
-
- /*
- * We give up here if we're reentered, because it might be for a
- * different filesystem.
- */
- if (!ext4_journal_current_handle())
- return __ext4_ordered_writepage(page, wbc);
-
- redirty_page_for_writepage(wbc, page);
- unlock_page(page);
- return 0;
-}
-
-static int __ext4_writeback_writepage(struct page *page,
+static int __ext4_normal_writepage(struct page *page,
struct writeback_control *wbc)
{
struct inode *inode = page->mapping->host;
@@ -1624,7 +1541,7 @@ static int __ext4_writeback_writepage(st
}
-static int ext4_writeback_writepage(struct page *page,
+static int ext4_normal_writepage(struct page *page,
struct writeback_control *wbc)
{
struct inode *inode = page->mapping->host;
@@ -1641,7 +1558,7 @@ static int ext4_writeback_writepage(stru
ext4_bh_unmapped_or_delay));
if (!ext4_journal_current_handle())
- return __ext4_writeback_writepage(page, wbc);
+ return __ext4_normal_writepage(page, wbc);
redirty_page_for_writepage(wbc, page);
unlock_page(page);
@@ -1877,7 +1794,7 @@ static int ext4_journalled_set_page_dirt
static const struct address_space_operations ext4_ordered_aops = {
.readpage = ext4_readpage,
.readpages = ext4_readpages,
- .writepage = ext4_ordered_writepage,
+ .writepage = ext4_normal_writepage,
.sync_page = block_sync_page,
.write_begin = ext4_write_begin,
.write_end = ext4_ordered_write_end,
@@ -1891,7 +1808,7 @@ static const struct address_space_operat
static const struct address_space_operations ext4_writeback_aops = {
.readpage = ext4_readpage,
.readpages = ext4_readpages,
- .writepage = ext4_writeback_writepage,
+ .writepage = ext4_normal_writepage,
.sync_page = block_sync_page,
.write_begin = ext4_write_begin,
.write_end = ext4_writeback_write_end,
@@ -2019,7 +1936,7 @@ int ext4_block_truncate_page(handle_t *h
err = ext4_journal_dirty_metadata(handle, bh);
} else {
if (ext4_should_order_data(inode))
- err = ext4_journal_dirty_data(handle, bh);
+ err = ext4_jbd2_file_inode(handle, inode);
mark_buffer_dirty(bh);
}
@@ -2787,6 +2704,7 @@ struct inode *ext4_iget(struct super_blo
ei->i_default_acl = EXT4_ACL_NOT_CACHED;
#endif
ei->i_block_alloc_info = NULL;
+ jbd2_journal_init_jbd_inode(&ei->jinode, inode);
ret = __ext4_get_inode_loc(inode, &iloc, 0);
if (ret < 0)
@@ -3149,7 +3067,14 @@ int ext4_write_inode(struct inode *inode
* be freed, so we have a strong guarantee that no future commit will
* leave these blocks visible to the user.)
*
- * Called with inode->sem down.
+ * Another thing we have to assure is that if we are in ordered mode
+ * and inode is still attached to the committing transaction, we must
+ * we start writeout of all the dirty pages which are being truncated.
+ * This way we are sure that all the data written in the previous
+ * transaction are already on disk (truncate waits for pages under
+ * writeback).
+ *
+ * Called with inode->i_mutex down.
*/
int ext4_setattr(struct dentry *dentry, struct iattr *attr)
{
@@ -3215,6 +3140,22 @@ int ext4_setattr(struct dentry *dentry,
if (!error)
error = rc;
ext4_journal_stop(handle);
+
+ if (ext4_should_order_data(inode)) {
+ error = ext4_begin_ordered_truncate(inode,
+ attr->ia_size);
+ if (error) {
+ /* Do as much error cleanup as possible */
+ handle = ext4_journal_start(inode, 3);
+ if (IS_ERR(handle)) {
+ ext4_orphan_del(NULL, inode);
+ goto err_out;
+ }
+ ext4_orphan_del(handle, inode);
+ ext4_journal_stop(handle);
+ goto err_out;
+ }
+ }
}
rc = inode_setattr(inode, attr);
@@ -3624,12 +3565,13 @@ int ext4_page_mkwrite(struct vm_area_str
lock_page(page);
wbc.range_start = page_offset(page);
wbc.range_end = page_offset(page) + len;
- if (ext4_should_writeback_data(inode))
- ret = __ext4_writeback_writepage(page, &wbc);
- else if (ext4_should_order_data(inode))
- ret = __ext4_ordered_writepage(page, &wbc);
- else
+ if (!ext4_should_journal_data(inode)) {
+ ret = __ext4_normal_writepage(page, &wbc);
+ if (!ret && ext4_should_order_data(inode))
+ ret = ext4_jbd2_file_inode(handle, inode);
+ } else {
ret = __ext4_journalled_writepage(page, &wbc);
+ }
/* Page got unlocked in writepage */
err = ext4_journal_stop(handle);
if (!ret)
Index: linux-2.6-linus/fs/ext4/super.c
===================================================================
--- linux-2.6-linus.orig/fs/ext4/super.c
+++ linux-2.6-linus/fs/ext4/super.c
@@ -637,6 +637,8 @@ static void ext4_clear_inode(struct inod
EXT4_I(inode)->i_block_alloc_info = NULL;
if (unlikely(rsv))
kfree(rsv);
+ jbd2_journal_release_jbd_inode(EXT4_SB(inode->i_sb)->s_journal,
+ &EXT4_I(inode)->jinode);
}
static inline void ext4_show_quota_options(struct seq_file *seq, struct super_block *sb)
@@ -3353,7 +3355,7 @@ static ssize_t ext4_quota_write(struct s
err = ext4_journal_dirty_metadata(handle, bh);
else {
/* Always do at least ordered writes for quotas */
- err = ext4_journal_dirty_data(handle, bh);
+ err = ext4_jbd2_file_inode(handle, inode);
mark_buffer_dirty(bh);
}
brelse(bh);
Index: linux-2.6-linus/fs/ext4/mballoc.c
===================================================================
--- linux-2.6-linus.orig/fs/ext4/mballoc.c
+++ linux-2.6-linus/fs/ext4/mballoc.c
@@ -2255,6 +2255,8 @@ static int ext4_mb_init_backend(struct s
printk(KERN_ERR "EXT4-fs: can't get new inode\n");
goto err_freesgi;
}
+ jbd2_journal_init_jbd_inode(&EXT4_I(sbi->s_buddy_cache)->jinode,
+ sbi->s_buddy_cache);
EXT4_I(sbi->s_buddy_cache)->i_disksize = 0;
metalen = sizeof(*meta_group_info) << EXT4_DESC_PER_BLOCK_BITS(sb);
From: Jan Kara <[email protected]>
Date: Thu, 22 May 2008 01:28:16 +0200
Subject: [PATCH] jbd2: Remove data=ordered mode support using jbd buffer heads
Signed-off-by: Jan Kara <[email protected]>
---
fs/jbd2/checkpoint.c | 1 -
fs/jbd2/commit.c | 230 ++-----------------------------------------------
fs/jbd2/journal.c | 1 -
fs/jbd2/transaction.c | 217 ++---------------------------------------------
include/linux/jbd2.h | 29 ++-----
5 files changed, 21 insertions(+), 457 deletions(-)
Index: linux-2.6-linus/fs/jbd2/checkpoint.c
===================================================================
--- linux-2.6-linus.orig/fs/jbd2/checkpoint.c
+++ linux-2.6-linus/fs/jbd2/checkpoint.c
@@ -688,7 +688,6 @@ void __jbd2_journal_drop_transaction(jou
J_ASSERT(transaction->t_state == T_FINISHED);
J_ASSERT(transaction->t_buffers == NULL);
- J_ASSERT(transaction->t_sync_datalist == NULL);
J_ASSERT(transaction->t_forget == NULL);
J_ASSERT(transaction->t_iobuf_list == NULL);
J_ASSERT(transaction->t_shadow_list == NULL);
Index: linux-2.6-linus/fs/jbd2/commit.c
===================================================================
--- linux-2.6-linus.orig/fs/jbd2/commit.c
+++ linux-2.6-linus/fs/jbd2/commit.c
@@ -37,8 +37,8 @@ static void journal_end_buffer_io_sync(s
}
/*
- * When an ext3-ordered file is truncated, it is possible that many pages are
- * not sucessfully freed, because they are attached to a committing transaction.
+ * When an ext4 file is truncated, it is possible that some pages are not
+ * successfully freed, because they are attached to a committing transaction.
* After the transaction commits, these pages are left on the LRU, with no
* ->mapping, and with attached buffers. These pages are trivially reclaimable
* by the VM, but their apparent absence upsets the VM accounting, and it makes
@@ -80,21 +80,6 @@ nope:
}
/*
- * Try to acquire jbd_lock_bh_state() against the buffer, when j_list_lock is
- * held. For ranking reasons we must trylock. If we lose, schedule away and
- * return 0. j_list_lock is dropped in this case.
- */
-static int inverted_lock(journal_t *journal, struct buffer_head *bh)
-{
- if (!jbd_trylock_bh_state(bh)) {
- spin_unlock(&journal->j_list_lock);
- schedule();
- return 0;
- }
- return 1;
-}
-
-/*
* Done it all: now submit the commit record. We should have
* cleaned up our previous buffers by now, so if we are in abort
* mode we can now just skip the rest of the journal write
@@ -199,162 +184,6 @@ static int journal_wait_on_commit_record
}
/*
- * Wait for all submitted IO to complete.
- */
-static int journal_wait_on_locked_list(journal_t *journal,
- transaction_t *commit_transaction)
-{
- int ret = 0;
- struct journal_head *jh;
-
- while (commit_transaction->t_locked_list) {
- struct buffer_head *bh;
-
- jh = commit_transaction->t_locked_list->b_tprev;
- bh = jh2bh(jh);
- get_bh(bh);
- if (buffer_locked(bh)) {
- spin_unlock(&journal->j_list_lock);
- wait_on_buffer(bh);
- if (unlikely(!buffer_uptodate(bh)))
- ret = -EIO;
- spin_lock(&journal->j_list_lock);
- }
- if (!inverted_lock(journal, bh)) {
- put_bh(bh);
- spin_lock(&journal->j_list_lock);
- continue;
- }
- if (buffer_jbd(bh) && jh->b_jlist == BJ_Locked) {
- __jbd2_journal_unfile_buffer(jh);
- jbd_unlock_bh_state(bh);
- jbd2_journal_remove_journal_head(bh);
- put_bh(bh);
- } else {
- jbd_unlock_bh_state(bh);
- }
- put_bh(bh);
- cond_resched_lock(&journal->j_list_lock);
- }
- return ret;
- }
-
-static void journal_do_submit_data(struct buffer_head **wbuf, int bufs)
-{
- int i;
-
- for (i = 0; i < bufs; i++) {
- wbuf[i]->b_end_io = end_buffer_write_sync;
- /* We use-up our safety reference in submit_bh() */
- submit_bh(WRITE, wbuf[i]);
- }
-}
-
-/*
- * Submit all the data buffers to disk
- */
-static void journal_submit_data_buffers(journal_t *journal,
- transaction_t *commit_transaction)
-{
- struct journal_head *jh;
- struct buffer_head *bh;
- int locked;
- int bufs = 0;
- struct buffer_head **wbuf = journal->j_wbuf;
-
- /*
- * Whenever we unlock the journal and sleep, things can get added
- * onto ->t_sync_datalist, so we have to keep looping back to
- * write_out_data until we *know* that the list is empty.
- *
- * Cleanup any flushed data buffers from the data list. Even in
- * abort mode, we want to flush this out as soon as possible.
- */
-write_out_data:
- cond_resched();
- spin_lock(&journal->j_list_lock);
-
- while (commit_transaction->t_sync_datalist) {
- jh = commit_transaction->t_sync_datalist;
- bh = jh2bh(jh);
- locked = 0;
-
- /* Get reference just to make sure buffer does not disappear
- * when we are forced to drop various locks */
- get_bh(bh);
- /* If the buffer is dirty, we need to submit IO and hence
- * we need the buffer lock. We try to lock the buffer without
- * blocking. If we fail, we need to drop j_list_lock and do
- * blocking lock_buffer().
- */
- if (buffer_dirty(bh)) {
- if (test_set_buffer_locked(bh)) {
- BUFFER_TRACE(bh, "needs blocking lock");
- spin_unlock(&journal->j_list_lock);
- /* Write out all data to prevent deadlocks */
- journal_do_submit_data(wbuf, bufs);
- bufs = 0;
- lock_buffer(bh);
- spin_lock(&journal->j_list_lock);
- }
- locked = 1;
- }
- /* We have to get bh_state lock. Again out of order, sigh. */
- if (!inverted_lock(journal, bh)) {
- jbd_lock_bh_state(bh);
- spin_lock(&journal->j_list_lock);
- }
- /* Someone already cleaned up the buffer? */
- if (!buffer_jbd(bh)
- || jh->b_transaction != commit_transaction
- || jh->b_jlist != BJ_SyncData) {
- jbd_unlock_bh_state(bh);
- if (locked)
- unlock_buffer(bh);
- BUFFER_TRACE(bh, "already cleaned up");
- put_bh(bh);
- continue;
- }
- if (locked && test_clear_buffer_dirty(bh)) {
- BUFFER_TRACE(bh, "needs writeout, adding to array");
- wbuf[bufs++] = bh;
- __jbd2_journal_file_buffer(jh, commit_transaction,
- BJ_Locked);
- jbd_unlock_bh_state(bh);
- if (bufs == journal->j_wbufsize) {
- spin_unlock(&journal->j_list_lock);
- journal_do_submit_data(wbuf, bufs);
- bufs = 0;
- goto write_out_data;
- }
- } else if (!locked && buffer_locked(bh)) {
- __jbd2_journal_file_buffer(jh, commit_transaction,
- BJ_Locked);
- jbd_unlock_bh_state(bh);
- put_bh(bh);
- } else {
- BUFFER_TRACE(bh, "writeout complete: unfile");
- __jbd2_journal_unfile_buffer(jh);
- jbd_unlock_bh_state(bh);
- if (locked)
- unlock_buffer(bh);
- jbd2_journal_remove_journal_head(bh);
- /* Once for our safety reference, once for
- * jbd2_journal_remove_journal_head() */
- put_bh(bh);
- put_bh(bh);
- }
-
- if (need_resched() || spin_needbreak(&journal->j_list_lock)) {
- spin_unlock(&journal->j_list_lock);
- goto write_out_data;
- }
- }
- spin_unlock(&journal->j_list_lock);
- journal_do_submit_data(wbuf, bufs);
-}
-
-/*
* Submit all the data buffers of inode associated with the transaction to
* disk.
*
@@ -601,42 +430,15 @@ void jbd2_journal_commit_transaction(jou
* Now start flushing things to disk, in the order they appear
* on the transaction lists. Data blocks go first.
*/
- err = 0;
- journal_submit_data_buffers(journal, commit_transaction);
err = journal_submit_inode_data_buffers(journal, commit_transaction);
if (err)
jbd2_journal_abort(journal, err);
- /*
- * Wait for all previously submitted IO to complete if commit
- * record is to be written synchronously.
- */
- spin_lock(&journal->j_list_lock);
- if (!JBD2_HAS_INCOMPAT_FEATURE(journal,
- JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT))
- err = journal_wait_on_locked_list(journal,
- commit_transaction);
-
- spin_unlock(&journal->j_list_lock);
-
- if (err)
- jbd2_journal_abort(journal, err);
-
jbd2_journal_write_revoke_records(journal, commit_transaction);
jbd_debug(3, "JBD: commit phase 2\n");
/*
- * If we found any dirty or locked buffers, then we should have
- * looped back up to the write_out_data label. If there weren't
- * any then journal_clean_data_list should have wiped the list
- * clean by now, so check that it is in fact empty.
- */
- J_ASSERT (commit_transaction->t_sync_datalist == NULL);
-
- jbd_debug (3, "JBD: commit phase 3\n");
-
- /*
* Way to go: we have now written out all of the data for a
* transaction! Now comes the tricky part: we need to write out
* metadata. Loop over the transaction's entire buffer list:
@@ -654,6 +456,7 @@ void jbd2_journal_commit_transaction(jou
J_ASSERT(commit_transaction->t_nr_buffers <=
commit_transaction->t_outstanding_credits);
+ err = 0;
descriptor = NULL;
bufs = 0;
while (commit_transaction->t_buffers) {
@@ -828,13 +631,6 @@ start_journal_io:
&cbh, crc32_sum);
if (err)
__jbd2_journal_abort_hard(journal);
-
- spin_lock(&journal->j_list_lock);
- err = journal_wait_on_locked_list(journal,
- commit_transaction);
- spin_unlock(&journal->j_list_lock);
- if (err)
- __jbd2_journal_abort_hard(journal);
}
/*
@@ -859,7 +655,7 @@ start_journal_io:
so we incur less scheduling load.
*/
- jbd_debug(3, "JBD: commit phase 4\n");
+ jbd_debug(3, "JBD: commit phase 3\n");
/*
* akpm: these are BJ_IO, and j_list_lock is not needed.
@@ -918,7 +714,7 @@ wait_for_iobuf:
J_ASSERT (commit_transaction->t_shadow_list == NULL);
- jbd_debug(3, "JBD: commit phase 5\n");
+ jbd_debug(3, "JBD: commit phase 4\n");
/* Here we wait for the revoke record and descriptor record buffers */
wait_for_ctlbuf:
@@ -945,7 +741,7 @@ wait_for_iobuf:
/* AKPM: bforget here */
}
- jbd_debug(3, "JBD: commit phase 6\n");
+ jbd_debug(3, "JBD: commit phase 5\n");
if (!JBD2_HAS_INCOMPAT_FEATURE(journal,
JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT)) {
@@ -965,9 +761,8 @@ wait_for_iobuf:
transaction can be removed from any checkpoint list it was on
before. */
- jbd_debug(3, "JBD: commit phase 7\n");
+ jbd_debug(3, "JBD: commit phase 6\n");
- J_ASSERT(commit_transaction->t_sync_datalist == NULL);
J_ASSERT(list_empty(&commit_transaction->t_inode_list));
J_ASSERT(commit_transaction->t_buffers == NULL);
J_ASSERT(commit_transaction->t_checkpoint_list == NULL);
@@ -1089,7 +884,7 @@ restart_loop:
/* Done with this transaction! */
- jbd_debug(3, "JBD: commit phase 8\n");
+ jbd_debug(3, "JBD: commit phase 7\n");
J_ASSERT(commit_transaction->t_state == T_COMMIT);
Index: linux-2.6-linus/fs/jbd2/journal.c
===================================================================
--- linux-2.6-linus.orig/fs/jbd2/journal.c
+++ linux-2.6-linus/fs/jbd2/journal.c
@@ -50,7 +50,6 @@ EXPORT_SYMBOL(jbd2_journal_unlock_update
EXPORT_SYMBOL(jbd2_journal_get_write_access);
EXPORT_SYMBOL(jbd2_journal_get_create_access);
EXPORT_SYMBOL(jbd2_journal_get_undo_access);
-EXPORT_SYMBOL(jbd2_journal_dirty_data);
EXPORT_SYMBOL(jbd2_journal_dirty_metadata);
EXPORT_SYMBOL(jbd2_journal_release_buffer);
EXPORT_SYMBOL(jbd2_journal_forget);
Index: linux-2.6-linus/fs/jbd2/transaction.c
===================================================================
--- linux-2.6-linus.orig/fs/jbd2/transaction.c
+++ linux-2.6-linus/fs/jbd2/transaction.c
@@ -943,183 +943,6 @@ out:
}
/**
- * int jbd2_journal_dirty_data() - mark a buffer as containing dirty data which
- * needs to be flushed before we can commit the
- * current transaction.
- * @handle: transaction
- * @bh: bufferhead to mark
- *
- * The buffer is placed on the transaction's data list and is marked as
- * belonging to the transaction.
- *
- * Returns error number or 0 on success.
- *
- * jbd2_journal_dirty_data() can be called via page_launder->ext3_writepage
- * by kswapd.
- */
-int jbd2_journal_dirty_data(handle_t *handle, struct buffer_head *bh)
-{
- journal_t *journal = handle->h_transaction->t_journal;
- int need_brelse = 0;
- struct journal_head *jh;
-
- if (is_handle_aborted(handle))
- return 0;
-
- jh = jbd2_journal_add_journal_head(bh);
- JBUFFER_TRACE(jh, "entry");
-
- /*
- * The buffer could *already* be dirty. Writeout can start
- * at any time.
- */
- jbd_debug(4, "jh: %p, tid:%d\n", jh, handle->h_transaction->t_tid);
-
- /*
- * What if the buffer is already part of a running transaction?
- *
- * There are two cases:
- * 1) It is part of the current running transaction. Refile it,
- * just in case we have allocated it as metadata, deallocated
- * it, then reallocated it as data.
- * 2) It is part of the previous, still-committing transaction.
- * If all we want to do is to guarantee that the buffer will be
- * written to disk before this new transaction commits, then
- * being sure that the *previous* transaction has this same
- * property is sufficient for us! Just leave it on its old
- * transaction.
- *
- * In case (2), the buffer must not already exist as metadata
- * --- that would violate write ordering (a transaction is free
- * to write its data at any point, even before the previous
- * committing transaction has committed). The caller must
- * never, ever allow this to happen: there's nothing we can do
- * about it in this layer.
- */
- jbd_lock_bh_state(bh);
- spin_lock(&journal->j_list_lock);
-
- /* Now that we have bh_state locked, are we really still mapped? */
- if (!buffer_mapped(bh)) {
- JBUFFER_TRACE(jh, "unmapped buffer, bailing out");
- goto no_journal;
- }
-
- if (jh->b_transaction) {
- JBUFFER_TRACE(jh, "has transaction");
- if (jh->b_transaction != handle->h_transaction) {
- JBUFFER_TRACE(jh, "belongs to older transaction");
- J_ASSERT_JH(jh, jh->b_transaction ==
- journal->j_committing_transaction);
-
- /* @@@ IS THIS TRUE ? */
- /*
- * Not any more. Scenario: someone does a write()
- * in data=journal mode. The buffer's transaction has
- * moved into commit. Then someone does another
- * write() to the file. We do the frozen data copyout
- * and set b_next_transaction to point to j_running_t.
- * And while we're in that state, someone does a
- * writepage() in an attempt to pageout the same area
- * of the file via a shared mapping. At present that
- * calls jbd2_journal_dirty_data(), and we get right here.
- * It may be too late to journal the data. Simply
- * falling through to the next test will suffice: the
- * data will be dirty and wil be checkpointed. The
- * ordering comments in the next comment block still
- * apply.
- */
- //J_ASSERT_JH(jh, jh->b_next_transaction == NULL);
-
- /*
- * If we're journalling data, and this buffer was
- * subject to a write(), it could be metadata, forget
- * or shadow against the committing transaction. Now,
- * someone has dirtied the same darn page via a mapping
- * and it is being writepage()'d.
- * We *could* just steal the page from commit, with some
- * fancy locking there. Instead, we just skip it -
- * don't tie the page's buffers to the new transaction
- * at all.
- * Implication: if we crash before the writepage() data
- * is written into the filesystem, recovery will replay
- * the write() data.
- */
- if (jh->b_jlist != BJ_None &&
- jh->b_jlist != BJ_SyncData &&
- jh->b_jlist != BJ_Locked) {
- JBUFFER_TRACE(jh, "Not stealing");
- goto no_journal;
- }
-
- /*
- * This buffer may be undergoing writeout in commit. We
- * can't return from here and let the caller dirty it
- * again because that can cause the write-out loop in
- * commit to never terminate.
- */
- if (buffer_dirty(bh)) {
- get_bh(bh);
- spin_unlock(&journal->j_list_lock);
- jbd_unlock_bh_state(bh);
- need_brelse = 1;
- sync_dirty_buffer(bh);
- jbd_lock_bh_state(bh);
- spin_lock(&journal->j_list_lock);
- /* Since we dropped the lock... */
- if (!buffer_mapped(bh)) {
- JBUFFER_TRACE(jh, "buffer got unmapped");
- goto no_journal;
- }
- /* The buffer may become locked again at any
- time if it is redirtied */
- }
-
- /* journal_clean_data_list() may have got there first */
- if (jh->b_transaction != NULL) {
- JBUFFER_TRACE(jh, "unfile from commit");
- __jbd2_journal_temp_unlink_buffer(jh);
- /* It still points to the committing
- * transaction; move it to this one so
- * that the refile assert checks are
- * happy. */
- jh->b_transaction = handle->h_transaction;
- }
- /* The buffer will be refiled below */
-
- }
- /*
- * Special case --- the buffer might actually have been
- * allocated and then immediately deallocated in the previous,
- * committing transaction, so might still be left on that
- * transaction's metadata lists.
- */
- if (jh->b_jlist != BJ_SyncData && jh->b_jlist != BJ_Locked) {
- JBUFFER_TRACE(jh, "not on correct data list: unfile");
- J_ASSERT_JH(jh, jh->b_jlist != BJ_Shadow);
- __jbd2_journal_temp_unlink_buffer(jh);
- jh->b_transaction = handle->h_transaction;
- JBUFFER_TRACE(jh, "file as data");
- __jbd2_journal_file_buffer(jh, handle->h_transaction,
- BJ_SyncData);
- }
- } else {
- JBUFFER_TRACE(jh, "not on a transaction");
- __jbd2_journal_file_buffer(jh, handle->h_transaction, BJ_SyncData);
- }
-no_journal:
- spin_unlock(&journal->j_list_lock);
- jbd_unlock_bh_state(bh);
- if (need_brelse) {
- BUFFER_TRACE(bh, "brelse");
- __brelse(bh);
- }
- JBUFFER_TRACE(jh, "exit");
- jbd2_journal_put_journal_head(jh);
- return 0;
-}
-
-/**
* int jbd2_journal_dirty_metadata() - mark a buffer as containing dirty metadata
* @handle: transaction to add buffer to.
* @bh: buffer to mark
@@ -1541,10 +1364,10 @@ __blist_del_buffer(struct journal_head *
* Remove a buffer from the appropriate transaction list.
*
* Note that this function can *change* the value of
- * bh->b_transaction->t_sync_datalist, t_buffers, t_forget,
- * t_iobuf_list, t_shadow_list, t_log_list or t_reserved_list. If the caller
- * is holding onto a copy of one of thee pointers, it could go bad.
- * Generally the caller needs to re-read the pointer from the transaction_t.
+ * bh->b_transaction->t_buffers, t_forget, t_iobuf_list, t_shadow_list,
+ * t_log_list or t_reserved_list. If the caller is holding onto a copy of one
+ * of these pointers, it could go bad. Generally the caller needs to re-read
+ * the pointer from the transaction_t.
*
* Called under j_list_lock. The journal may not be locked.
*/
@@ -1566,9 +1389,6 @@ void __jbd2_journal_temp_unlink_buffer(s
switch (jh->b_jlist) {
case BJ_None:
return;
- case BJ_SyncData:
- list = &transaction->t_sync_datalist;
- break;
case BJ_Metadata:
transaction->t_nr_buffers--;
J_ASSERT_JH(jh, transaction->t_nr_buffers >= 0);
@@ -1589,9 +1409,6 @@ void __jbd2_journal_temp_unlink_buffer(s
case BJ_Reserved:
list = &transaction->t_reserved_list;
break;
- case BJ_Locked:
- list = &transaction->t_locked_list;
- break;
}
__blist_del_buffer(list, jh);
@@ -1634,15 +1451,7 @@ __journal_try_to_free_buffer(journal_t *
goto out;
spin_lock(&journal->j_list_lock);
- if (jh->b_transaction != NULL && jh->b_cp_transaction == NULL) {
- if (jh->b_jlist == BJ_SyncData || jh->b_jlist == BJ_Locked) {
- /* A written-back ordered data buffer */
- JBUFFER_TRACE(jh, "release data");
- __jbd2_journal_unfile_buffer(jh);
- jbd2_journal_remove_journal_head(bh);
- __brelse(bh);
- }
- } else if (jh->b_cp_transaction != NULL && jh->b_transaction == NULL) {
+ if (jh->b_cp_transaction != NULL && jh->b_transaction == NULL) {
/* written-back checkpointed metadata buffer */
if (jh->b_jlist == BJ_None) {
JBUFFER_TRACE(jh, "remove from checkpoint list");
@@ -1878,6 +1687,7 @@ static int journal_unmap_buffer(journal_
if (!buffer_jbd(bh))
goto zap_buffer_unlocked;
+ /* OK, we have data buffer in journaled mode */
spin_lock(&journal->j_state_lock);
jbd_lock_bh_state(bh);
spin_lock(&journal->j_list_lock);
@@ -1941,15 +1751,6 @@ static int journal_unmap_buffer(journal_
}
} else if (transaction == journal->j_committing_transaction) {
JBUFFER_TRACE(jh, "on committing transaction");
- if (jh->b_jlist == BJ_Locked) {
- /*
- * The buffer is on the committing transaction's locked
- * list. We have the buffer locked, so I/O has
- * completed. So we can nail the buffer now.
- */
- may_free = __dispose_buffer(jh, transaction);
- goto zap_buffer;
- }
/*
* If it is committing, we simply cannot touch it. We
* can remove it's next_transaction pointer from the
@@ -2082,9 +1883,6 @@ void __jbd2_journal_file_buffer(struct j
J_ASSERT_JH(jh, !jh->b_committed_data);
J_ASSERT_JH(jh, !jh->b_frozen_data);
return;
- case BJ_SyncData:
- list = &transaction->t_sync_datalist;
- break;
case BJ_Metadata:
transaction->t_nr_buffers++;
list = &transaction->t_buffers;
@@ -2104,9 +1902,6 @@ void __jbd2_journal_file_buffer(struct j
case BJ_Reserved:
list = &transaction->t_reserved_list;
break;
- case BJ_Locked:
- list = &transaction->t_locked_list;
- break;
}
__blist_add_buffer(list, jh);
Index: linux-2.6-linus/include/linux/jbd2.h
===================================================================
--- linux-2.6-linus.orig/include/linux/jbd2.h
+++ linux-2.6-linus/include/linux/jbd2.h
@@ -543,24 +543,12 @@ struct transaction_s
struct journal_head *t_reserved_list;
/*
- * Doubly-linked circular list of all buffers under writeout during
- * commit [j_list_lock]
- */
- struct journal_head *t_locked_list;
-
- /*
* Doubly-linked circular list of all metadata buffers owned by this
* transaction [j_list_lock]
*/
struct journal_head *t_buffers;
/*
- * Doubly-linked circular list of all data buffers still to be
- * flushed before this transaction can be committed [j_list_lock]
- */
- struct journal_head *t_sync_datalist;
-
- /*
* Doubly-linked circular list of all forget buffers (superseded
* buffers which we can un-checkpoint once this transaction commits)
* [j_list_lock]
@@ -1041,7 +1029,6 @@ extern int jbd2_journal_extend (handle_
extern int jbd2_journal_get_write_access(handle_t *, struct buffer_head *);
extern int jbd2_journal_get_create_access (handle_t *, struct buffer_head *);
extern int jbd2_journal_get_undo_access(handle_t *, struct buffer_head *);
-extern int jbd2_journal_dirty_data (handle_t *, struct buffer_head *);
extern int jbd2_journal_dirty_metadata (handle_t *, struct buffer_head *);
extern void jbd2_journal_release_buffer (handle_t *, struct buffer_head *);
extern int jbd2_journal_forget (handle_t *, struct buffer_head *);
@@ -1220,15 +1207,13 @@ static inline int jbd_space_needed(journ
/* journaling buffer types */
#define BJ_None 0 /* Not journaled */
-#define BJ_SyncData 1 /* Normal data: flush before commit */
-#define BJ_Metadata 2 /* Normal journaled metadata */
-#define BJ_Forget 3 /* Buffer superseded by this transaction */
-#define BJ_IO 4 /* Buffer is for temporary IO use */
-#define BJ_Shadow 5 /* Buffer contents being shadowed to the log */
-#define BJ_LogCtl 6 /* Buffer contains log descriptors */
-#define BJ_Reserved 7 /* Buffer is reserved for access by journal */
-#define BJ_Locked 8 /* Locked for I/O during commit */
-#define BJ_Types 9
+#define BJ_Metadata 1 /* Normal journaled metadata */
+#define BJ_Forget 2 /* Buffer superseded by this transaction */
+#define BJ_IO 3 /* Buffer is for temporary IO use */
+#define BJ_Shadow 4 /* Buffer contents being shadowed to the log */
+#define BJ_LogCtl 5 /* Buffer contains log descriptors */
+#define BJ_Reserved 6 /* Buffer is reserved for access by journal */
+#define BJ_Types 7
extern int jbd_blocks_per_page(struct inode *inode);