[PATCH]JBD2/JBD: race condition while writing updates to journal

[PATCH]JBD2/JBD: race condition while writing updates to journal

[dingdinghua]

resend this patch:

At committing phase, we call jbd2_journal_write_metadata_buffer to
prepare log block's buffer_head, in this function, new_bh->b_data is set
to b_frozen_data or bh_in->b_data. We call "jbd_unlock_bh_state(bh_in)"
too early, since at this point , we haven't file bh_in to BJ_shadow
list, and we may set new_bh->b_data to bh_in->b_data, at this time,
another thread may call get write access of bh_in, modify bh_in->b_data
and dirty it. So , if new_bh->b_data is set to bh_in->b_data, the
committing transaction may flush the newly modified buffer content to
disk, preserve work done in jbd2_journal_get_write_access is useless.
jbd also has this problem.

here is the patch based on kernel version 2.6.30:

Signed-off-by: dingdinghua <dingdinghua@nrchpc.ac.cn>
Acked-by: Jan Kara <jack@suse.cz>

---

diff --git a/fs/jbd/journal.c b/fs/jbd/journal.c
index 737f724..ff5dcb5 100644
--- a/fs/jbd/journal.c
+++ b/fs/jbd/journal.c
@@ -287,6 +287,7 @@ int journal_write_metadata_buffer(transaction_t *transaction,
 	struct page *new_page;
 	unsigned int new_offset;
 	struct buffer_head *bh_in = jh2bh(jh_in);
+	journal_t *journal = transaction->t_journal;
 
 	/*
 	 * The buffer really shouldn't be locked: only the current committing
@@ -300,6 +301,11 @@ int journal_write_metadata_buffer(transaction_t *transaction,
 	J_ASSERT_BH(bh_in, buffer_jbddirty(bh_in));
 
 	new_bh = alloc_buffer_head(GFP_NOFS|__GFP_NOFAIL);
+	/* keep subsequent assertions sane */
+	new_bh->b_state = 0;
+	init_buffer(new_bh, NULL, NULL);
+	atomic_set(&new_bh->b_count, 1);
+	new_jh = journal_add_journal_head(new_bh);	/* This sleeps */
 
 	/*
 	 * If a new transaction has already done a buffer copy-out, then
@@ -361,14 +367,6 @@ repeat:
 		kunmap_atomic(mapped_data, KM_USER0);
 	}
 
-	/* keep subsequent assertions sane */
-	new_bh->b_state = 0;
-	init_buffer(new_bh, NULL, NULL);
-	atomic_set(&new_bh->b_count, 1);
-	jbd_unlock_bh_state(bh_in);
-
-	new_jh = journal_add_journal_head(new_bh);	/* This sleeps */
-
 	set_bh_page(new_bh, new_page, new_offset);
 	new_jh->b_transaction = NULL;
 	new_bh->b_size = jh2bh(jh_in)->b_size;
@@ -385,7 +383,11 @@ repeat:
 	 * copying is moved to the transaction's shadow queue.
 	 */
 	JBUFFER_TRACE(jh_in, "file as BJ_Shadow");
-	journal_file_buffer(jh_in, transaction, BJ_Shadow);
+	spin_lock(&journal->j_list_lock);
+	__journal_file_buffer(jh_in, transaction, BJ_Shadow);
+	spin_unlock(&journal->j_list_lock);
+	jbd_unlock_bh_state(bh_in);
+
 	JBUFFER_TRACE(new_jh, "file as BJ_IO");
 	journal_file_buffer(new_jh, transaction, BJ_IO);
 
diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c
index 18bfd5d..4a0b48f 100644
--- a/fs/jbd2/journal.c
+++ b/fs/jbd2/journal.c
@@ -297,6 +297,8 @@ int jbd2_journal_write_metadata_buffer(transaction_t *transaction,
 	unsigned int new_offset;
 	struct buffer_head *bh_in = jh2bh(jh_in);
 	struct jbd2_buffer_trigger_type *triggers;
+	journal_t *journal = transaction->t_journal;
+
 
 	/*
 	 * The buffer really shouldn't be locked: only the current committing
@@ -310,6 +312,11 @@ int jbd2_journal_write_metadata_buffer(transaction_t *transaction,
 	J_ASSERT_BH(bh_in, buffer_jbddirty(bh_in));
 
 	new_bh = alloc_buffer_head(GFP_NOFS|__GFP_NOFAIL);
+	/* keep subsequent assertions sane */
+	new_bh->b_state = 0;
+	init_buffer(new_bh, NULL, NULL);
+	atomic_set(&new_bh->b_count, 1);
+	new_jh = jbd2_journal_add_journal_head(new_bh);	/* This sleeps */
 
 	/*
 	 * If a new transaction has already done a buffer copy-out, then
@@ -388,14 +395,6 @@ repeat:
 		kunmap_atomic(mapped_data, KM_USER0);
 	}
 
-	/* keep subsequent assertions sane */
-	new_bh->b_state = 0;
-	init_buffer(new_bh, NULL, NULL);
-	atomic_set(&new_bh->b_count, 1);
-	jbd_unlock_bh_state(bh_in);
-
-	new_jh = jbd2_journal_add_journal_head(new_bh);	/* This sleeps */

Re: [PATCH]JBD2/JBD: race condition while writing updates to journal

[Jan Kara]

  Ted, I don't think this got merged...

								Honza
> resend this patch:
> 
> At committing phase, we call jbd2_journal_write_metadata_buffer to
> prepare log block's buffer_head, in this function, new_bh->b_data is set
> to b_frozen_data or bh_in->b_data. We call "jbd_unlock_bh_state(bh_in)"
> too early, since at this point , we haven't file bh_in to BJ_shadow
> list, and we may set new_bh->b_data to bh_in->b_data, at this time,
> another thread may call get write access of bh_in, modify bh_in->b_data
> and dirty it. So , if new_bh->b_data is set to bh_in->b_data, the
> committing transaction may flush the newly modified buffer content to
> disk, preserve work done in jbd2_journal_get_write_access is useless.
> jbd also has this problem.
> 
> here is the patch based on kernel version 2.6.30:
> 
> Signed-off-by: dingdinghua <dingdinghua@nrchpc.ac.cn>
> Acked-by: Jan Kara <jack@suse.cz>
> 
> ---
> 
> diff --git a/fs/jbd/journal.c b/fs/jbd/journal.c
> index 737f724..ff5dcb5 100644
> --- a/fs/jbd/journal.c
> +++ b/fs/jbd/journal.c
> @@ -287,6 +287,7 @@ int journal_write_metadata_buffer(transaction_t *transaction,
>  	struct page *new_page;
>  	unsigned int new_offset;
>  	struct buffer_head *bh_in = jh2bh(jh_in);
> +	journal_t *journal = transaction->t_journal;
>  
>  	/*
>  	 * The buffer really shouldn't be locked: only the current committing
> @@ -300,6 +301,11 @@ int journal_write_metadata_buffer(transaction_t *transaction,
>  	J_ASSERT_BH(bh_in, buffer_jbddirty(bh_in));
>  
>  	new_bh = alloc_buffer_head(GFP_NOFS|__GFP_NOFAIL);
> +	/* keep subsequent assertions sane */
> +	new_bh->b_state = 0;
> +	init_buffer(new_bh, NULL, NULL);
> +	atomic_set(&new_bh->b_count, 1);
> +	new_jh = journal_add_journal_head(new_bh);	/* This sleeps */
>  
>  	/*
>  	 * If a new transaction has already done a buffer copy-out, then
> @@ -361,14 +367,6 @@ repeat:
>  		kunmap_atomic(mapped_data, KM_USER0);
>  	}
>  
> -	/* keep subsequent assertions sane */
> -	new_bh->b_state = 0;
> -	init_buffer(new_bh, NULL, NULL);
> -	atomic_set(&new_bh->b_count, 1);
> -	jbd_unlock_bh_state(bh_in);
> -
> -	new_jh = journal_add_journal_head(new_bh);	/* This sleeps */
> -
>  	set_bh_page(new_bh, new_page, new_offset);
>  	new_jh->b_transaction = NULL;
>  	new_bh->b_size = jh2bh(jh_in)->b_size;
> @@ -385,7 +383,11 @@ repeat:
>  	 * copying is moved to the transaction's shadow queue.
>  	 */
>  	JBUFFER_TRACE(jh_in, "file as BJ_Shadow");
> -	journal_file_buffer(jh_in, transaction, BJ_Shadow);
> +	spin_lock(&journal->j_list_lock);
> +	__journal_file_buffer(jh_in, transaction, BJ_Shadow);
> +	spin_unlock(&journal->j_list_lock);
> +	jbd_unlock_bh_state(bh_in);
> +
>  	JBUFFER_TRACE(new_jh, "file as BJ_IO");
>  	journal_file_buffer(new_jh, transaction, BJ_IO);
>  
> diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c
> index 18bfd5d..4a0b48f 100644
> --- a/fs/jbd2/journal.c
> +++ b/fs/jbd2/journal.c
> @@ -297,6 +297,8 @@ int jbd2_journal_write_metadata_buffer(transaction_t *transaction,
>  	unsigned int new_offset;
>  	struct buffer_head *bh_in = jh2bh(jh_in);
>  	struct jbd2_buffer_trigger_type *triggers;
> +	journal_t *journal = transaction->t_journal;
> +
>  
>  	/*
>  	 * The buffer really shouldn't be locked: only the current committing
> @@ -310,6 +312,11 @@ int jbd2_journal_write_metadata_buffer(transaction_t *transaction,
>  	J_ASSERT_BH(bh_in, buffer_jbddirty(bh_in));
>  
>  	new_bh = alloc_buffer_head(GFP_NOFS|__GFP_NOFAIL);
> +	/* keep subsequent assertions sane */
> +	new_bh->b_state = 0;
> +	init_buffer(new_bh, NULL, NULL);
> +	atomic_set(&new_bh->b_count, 1);
> +	new_jh = jbd2_journal_add_journal_head(new_bh);	/* This sleeps */
>  
>  	/*
>  	 * If a new transaction has already done a buffer copy-out, then
> @@ -388,14 +395,6 @@ repeat:
>  		kunmap_atomic(mapped_data, KM_USER0);
>  	}
>  
> -	/* keep subsequent assertions sane */
> -	new_bh->b_state = 0;
> -	init_buffer(new_bh, NULL, NULL);
> -	atomic_set(&new_bh->b_count, 1);
> -	jbd_unlock_bh_state(bh_in);
> -
> -	new_jh = jbd2_journal_add_journal_head(new_bh);	/* This sleeps */
> -
>  	set_bh_page(new_bh, new_page, new_offset);
>  	new_jh->b_transaction = NULL;
>  	new_bh->b_size = jh2bh(jh_in)->b_size;
> @@ -412,7 +411,11 @@ repeat:
>  	 * copying is moved to the transaction's shadow queue.
>  	 */
>  	JBUFFER_TRACE(jh_in, "file as BJ_Shadow");
> -	jbd2_journal_file_buffer(jh_in, transaction, BJ_Shadow);
> +	spin_lock(&journal->j_list_lock);
> +	__jbd2_journal_file_buffer(jh_in, transaction, BJ_Shadow);
> +	spin_unlock(&journal->j_list_lock);
> +	jbd_unlock_bh_state(bh_in);
> +
>  	JBUFFER_TRACE(new_jh, "file as BJ_IO");
>  	jbd2_journal_file_buffer(new_jh, transaction, BJ_IO);
> --
> To unsubscribe from this list: send the line "unsubscribe linux-ext4" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at  http://vger.kernel.org/majordomo-info.html
-- 
Jan Kara <jack@suse.cz>
SuSE CR Labs

Re: [PATCH]JBD2/JBD: race condition while writing updates to journal

[Jan Kara]

>   Ted, I don't think this got merged...
  Ah, I see, jbd2 part got merged by you, I'm not sure about the jbd
part since I didn't see Andrew reply. I guess I'll create a tree for
ext3/jbd changes and merge this patch (and other ext3/jbd fixes I have
here) through it.

								Honza

> > resend this patch:
> > 
> > At committing phase, we call jbd2_journal_write_metadata_buffer to
> > prepare log block's buffer_head, in this function, new_bh->b_data is set
> > to b_frozen_data or bh_in->b_data. We call "jbd_unlock_bh_state(bh_in)"
> > too early, since at this point , we haven't file bh_in to BJ_shadow
> > list, and we may set new_bh->b_data to bh_in->b_data, at this time,
> > another thread may call get write access of bh_in, modify bh_in->b_data
> > and dirty it. So , if new_bh->b_data is set to bh_in->b_data, the
> > committing transaction may flush the newly modified buffer content to
> > disk, preserve work done in jbd2_journal_get_write_access is useless.
> > jbd also has this problem.
> > 
> > here is the patch based on kernel version 2.6.30:
> > 
> > Signed-off-by: dingdinghua <dingdinghua@nrchpc.ac.cn>
> > Acked-by: Jan Kara <jack@suse.cz>
> > 
> > ---
> > 
> > diff --git a/fs/jbd/journal.c b/fs/jbd/journal.c
> > index 737f724..ff5dcb5 100644
> > --- a/fs/jbd/journal.c
> > +++ b/fs/jbd/journal.c
> > @@ -287,6 +287,7 @@ int journal_write_metadata_buffer(transaction_t *transaction,
> >  	struct page *new_page;
> >  	unsigned int new_offset;
> >  	struct buffer_head *bh_in = jh2bh(jh_in);
> > +	journal_t *journal = transaction->t_journal;
> >  
> >  	/*
> >  	 * The buffer really shouldn't be locked: only the current committing
> > @@ -300,6 +301,11 @@ int journal_write_metadata_buffer(transaction_t *transaction,
> >  	J_ASSERT_BH(bh_in, buffer_jbddirty(bh_in));
> >  
> >  	new_bh = alloc_buffer_head(GFP_NOFS|__GFP_NOFAIL);
> > +	/* keep subsequent assertions sane */
> > +	new_bh->b_state = 0;
> > +	init_buffer(new_bh, NULL, NULL);
> > +	atomic_set(&new_bh->b_count, 1);
> > +	new_jh = journal_add_journal_head(new_bh);	/* This sleeps */
> >  
> >  	/*
> >  	 * If a new transaction has already done a buffer copy-out, then
> > @@ -361,14 +367,6 @@ repeat:
> >  		kunmap_atomic(mapped_data, KM_USER0);
> >  	}
> >  
> > -	/* keep subsequent assertions sane */
> > -	new_bh->b_state = 0;
> > -	init_buffer(new_bh, NULL, NULL);
> > -	atomic_set(&new_bh->b_count, 1);
> > -	jbd_unlock_bh_state(bh_in);
> > -
> > -	new_jh = journal_add_journal_head(new_bh);	/* This sleeps */
> > -
> >  	set_bh_page(new_bh, new_page, new_offset);
> >  	new_jh->b_transaction = NULL;
> >  	new_bh->b_size = jh2bh(jh_in)->b_size;
> > @@ -385,7 +383,11 @@ repeat:
> >  	 * copying is moved to the transaction's shadow queue.
> >  	 */
> >  	JBUFFER_TRACE(jh_in, "file as BJ_Shadow");
> > -	journal_file_buffer(jh_in, transaction, BJ_Shadow);
> > +	spin_lock(&journal->j_list_lock);
> > +	__journal_file_buffer(jh_in, transaction, BJ_Shadow);
> > +	spin_unlock(&journal->j_list_lock);
> > +	jbd_unlock_bh_state(bh_in);
> > +
> >  	JBUFFER_TRACE(new_jh, "file as BJ_IO");
> >  	journal_file_buffer(new_jh, transaction, BJ_IO);
> >  
> > diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c
> > index 18bfd5d..4a0b48f 100644
> > --- a/fs/jbd2/journal.c
> > +++ b/fs/jbd2/journal.c
> > @@ -297,6 +297,8 @@ int jbd2_journal_write_metadata_buffer(transaction_t *transaction,
> >  	unsigned int new_offset;
> >  	struct buffer_head *bh_in = jh2bh(jh_in);
> >  	struct jbd2_buffer_trigger_type *triggers;
> > +	journal_t *journal = transaction->t_journal;
> > +
> >  
> >  	/*
> >  	 * The buffer really shouldn't be locked: only the current committing
> > @@ -310,6 +312,11 @@ int jbd2_journal_write_metadata_buffer(transaction_t *transaction,
> >  	J_ASSERT_BH(bh_in, buffer_jbddirty(bh_in));
> >  
> >  	new_bh = alloc_buffer_head(GFP_NOFS|__GFP_NOFAIL);
> > +	/* keep subsequent assertions sane */
> > +	new_bh->b_state = 0;
> > +	init_buffer(new_bh, NULL, NULL);
> > +	atomic_set(&new_bh->b_count, 1);
> > +	new_jh = jbd2_journal_add_journal_head(new_bh);	/* This sleeps */
> >  
> >  	/*
> >  	 * If a new transaction has already done a buffer copy-out, then
> > @@ -388,14 +395,6 @@ repeat:
> >  		kunmap_atomic(mapped_data, KM_USER0);
> >  	}
> >  
> > -	/* keep subsequent assertions sane */
> > -	new_bh->b_state = 0;
> > -	init_buffer(new_bh, NULL, NULL);
> > -	atomic_set(&new_bh->b_count, 1);
> > -	jbd_unlock_bh_state(bh_in);
> > -
> > -	new_jh = jbd2_journal_add_journal_head(new_bh);	/* This sleeps */
> > -
> >  	set_bh_page(new_bh, new_page, new_offset);
> >  	new_jh->b_transaction = NULL;
> >  	new_bh->b_size = jh2bh(jh_in)->b_size;
> > @@ -412,7 +411,11 @@ repeat:
> >  	 * copying is moved to the transaction's shadow queue.
> >  	 */
> >  	JBUFFER_TRACE(jh_in, "file as BJ_Shadow");
> > -	jbd2_journal_file_buffer(jh_in, transaction, BJ_Shadow);
> > +	spin_lock(&journal->j_list_lock);
> > +	__jbd2_journal_file_buffer(jh_in, transaction, BJ_Shadow);
> > +	spin_unlock(&journal->j_list_lock);
> > +	jbd_unlock_bh_state(bh_in);
> > +
> >  	JBUFFER_TRACE(new_jh, "file as BJ_IO");
> >  	jbd2_journal_file_buffer(new_jh, transaction, BJ_IO);
> > --
> > To unsubscribe from this list: send the line "unsubscribe linux-ext4" in
> > the body of a message to majordomo@vger.kernel.org
> > More majordomo info at  http://vger.kernel.org/majordomo-info.html
> -- 
> Jan Kara <jack@suse.cz>
> SuSE CR Labs
> --
> To unsubscribe from this list: send the line "unsubscribe linux-ext4" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at  http://vger.kernel.org/majordomo-info.html
-- 
Jan Kara <jack@suse.cz>
SuSE CR Labs

Re: [PATCH]JBD2/JBD: race condition while writing updates to journal

[Theodore Tso]

On Wed, Jul 15, 2009 at 08:13:43PM +0200, Jan Kara wrote:
> >   Ted, I don't think this got merged...
>   Ah, I see, jbd2 part got merged by you, I'm not sure about the jbd
> part since I didn't see Andrew reply. I guess I'll create a tree for
> ext3/jbd changes and merge this patch (and other ext3/jbd fixes I have
> here) through it.

I did get a note from Andrew saying he had grabbed the patch.  It
probably hasn't been published in his mmotm tree yet.

	 	     	       	      	    - Ted

Re: [PATCH]JBD2/JBD: race condition while writing updates to journal

[Jan Kara]

On Thu 16-07-09 21:36:12, Theodore Tso wrote:
> On Wed, Jul 15, 2009 at 08:13:43PM +0200, Jan Kara wrote:
> > >   Ted, I don't think this got merged...
> >   Ah, I see, jbd2 part got merged by you, I'm not sure about the jbd
> > part since I didn't see Andrew reply. I guess I'll create a tree for
> > ext3/jbd changes and merge this patch (and other ext3/jbd fixes I have
> > here) through it.
> 
> I did get a note from Andrew saying he had grabbed the patch.  It
> probably hasn't been published in his mmotm tree yet.
  Thanks for info. Yes, I can see the patch in mmotm now.

								Honza
-- 
Jan Kara <jack@suse.cz>
SUSE Labs, CR

Re: [PATCH]JBD2/JBD: race condition while writing updates to journal

[Theodore Tso]

On Mon, Jun 22, 2009 at 12:22:03AM +0800, dingdinghua wrote:
> 
> At committing phase, we call jbd2_journal_write_metadata_buffer to
> prepare log block's buffer_head, in this function, new_bh->b_data is set
> to b_frozen_data or bh_in->b_data. We call "jbd_unlock_bh_state(bh_in)"
> too early, since at this point , we haven't file bh_in to BJ_shadow list,
> and we may set new_bh->b_data to bh_in->b_data, at this time, another
> thread may call get write access of bh_in, modify bh_in->b_data and
> dirty it. So , if new_bh->b_data is set to bh_in->b_data, the committing
> transaction may flush the newly modified buffer content to disk,
> preserve work done in jbd2_journal_get_write_access is useless. jbd also
> has this problem.
> 
> here is the patch based on kernel version 2.6.30:

This patch is completely whitespace damaged.  Could you resend it
using a mail user agent that doesn't damage patches, please?    Thanks!!

      	     	  	     	     	    - Ted

[PATCH]JBD2/JBD: race condition while writing updates to journal

[dingdinghua]

At committing phase, we call jbd2_journal_write_metadata_buffer to
prepare log block's buffer_head, in this function, new_bh->b_data is set
to b_frozen_data or bh_in->b_data. We call "jbd_unlock_bh_state(bh_in)"
too early, since at this point , we haven't file bh_in to BJ_shadow list,
and we may set new_bh->b_data to bh_in->b_data, at this time, another
thread may call get write access of bh_in, modify bh_in->b_data and
dirty it. So , if new_bh->b_data is set to bh_in->b_data, the committing
transaction may flush the newly modified buffer content to disk,
preserve work done in jbd2_journal_get_write_access is useless. jbd also
has this problem.

here is the patch based on kernel version 2.6.30:

Signed-off-by: dingdinghua <dingdinghua85@gmail.com>
Acked-by: Jan Kara <jack@suse.cz>

---

--- fs/jbd2/journal.c.old 2009-06-21 16:18:18.000000000 +0800
+++ fs/jbd2/journal.c 2009-06-21 16:38:53.000000000 +0800
@@ -297,6 +297,8 @@ int jbd2_journal_write_metadata_buffer(t
unsigned int new_offset;
struct buffer_head *bh_in = jh2bh(jh_in);
struct jbd2_buffer_trigger_type *triggers;
+ journal_t *journal = transaction->t_journal;
+

/*
* The buffer really shouldn't be locked: only the current committing
@@ -310,6 +312,11 @@ int jbd2_journal_write_metadata_buffer(t
J_ASSERT_BH(bh_in, buffer_jbddirty(bh_in));

new_bh = alloc_buffer_head(GFP_NOFS|__GFP_NOFAIL);
+ /* keep subsequent assertions sane */
+ new_bh->b_state = 0;
+ init_buffer(new_bh, NULL, NULL);
+ atomic_set(&new_bh->b_count, 1);
+ new_jh = jbd2_journal_add_journal_head(new_bh); /* This sleeps */

/*
* If a new transaction has already done a buffer copy-out, then
@@ -388,14 +395,6 @@ repeat:
kunmap_atomic(mapped_data, KM_USER0);
}

- /* keep subsequent assertions sane */
- new_bh->b_state = 0;
- init_buffer(new_bh, NULL, NULL);
- atomic_set(&new_bh->b_count, 1);
- jbd_unlock_bh_state(bh_in);
-
- new_jh = jbd2_journal_add_journal_head(new_bh); /* This sleeps */
-
set_bh_page(new_bh, new_page, new_offset);
new_jh->b_transaction = NULL;
new_bh->b_size = jh2bh(jh_in)->b_size;
@@ -412,7 +411,11 @@ repeat:
* copying is moved to the transaction's shadow queue.
*/
JBUFFER_TRACE(jh_in, "file as BJ_Shadow");
- jbd2_journal_file_buffer(jh_in, transaction, BJ_Shadow);
+ spin_lock(&journal->j_list_lock);
+ __jbd2_journal_file_buffer(jh_in, transaction, BJ_Shadow);
+ spin_unlock(&journal->j_list_lock);
+ jbd_unlock_bh_state(bh_in);
+
JBUFFER_TRACE(new_jh, "file as BJ_IO");
jbd2_journal_file_buffer(new_jh, transaction, BJ_IO);

--- fs/jbd/journal.c.old 2009-06-21 16:27:37.000000000 +0800
+++ fs/jbd/journal.c 2009-06-21 16:45:06.000000000 +0800
@@ -287,6 +287,7 @@ int journal_write_metadata_buffer(transa
struct page *new_page;
unsigned int new_offset;
struct buffer_head *bh_in = jh2bh(jh_in);
+ journal_t *journal = transaction->t_journal;

/*
* The buffer really shouldn't be locked: only the current committing
@@ -300,6 +301,11 @@ int journal_write_metadata_buffer(transa
J_ASSERT_BH(bh_in, buffer_jbddirty(bh_in));

new_bh = alloc_buffer_head(GFP_NOFS|__GFP_NOFAIL);
+ /* keep subsequent assertions sane */
+ new_bh->b_state = 0;
+ init_buffer(new_bh, NULL, NULL);
+ atomic_set(&new_bh->b_count, 1);
+ new_jh = journal_add_journal_head(new_bh); /* This sleeps */

/*
* If a new transaction has already done a buffer copy-out, then
@@ -361,14 +367,6 @@ repeat:
kunmap_atomic(mapped_data, KM_USER0);
}

- /* keep subsequent assertions sane */
- new_bh->b_state = 0;
- init_buffer(new_bh, NULL, NULL);
- atomic_set(&new_bh->b_count, 1);
- jbd_unlock_bh_state(bh_in);
-
- new_jh = journal_add_journal_head(new_bh); /* This sleeps */