diff mbox series

[v11,4/4] xfs: use current->journal_info to avoid transaction reservation recursion

Message ID 20201208122824.16118-5-laoar.shao@gmail.com (mailing list archive)
State New, archived
Headers show
Series xfs: avoid transaction reservation recursion | expand

Commit Message

Yafang Shao Dec. 8, 2020, 12:28 p.m. UTC
PF_FSTRANS which is used to avoid transaction reservation recursion, is
dropped since commit 9070733b4efa ("xfs: abstract PF_FSTRANS to
PF_MEMALLOC_NOFS") and commit 7dea19f9ee63 ("mm: introduce
memalloc_nofs_{save,restore} API") and replaced by PF_MEMALLOC_NOFS which
means to avoid filesystem reclaim recursion.

As these two flags have different meanings, we'd better reintroduce
PF_FSTRANS back. To avoid wasting the space of PF_* flags in task_struct,
we can reuse the current->journal_info to do that, per Willy. As the
check of transaction reservation recursion is used by XFS only, we can
move the check into xfs_vm_writepage(s), per Dave.

To better abstract that behavoir, two new helpers are introduced, as
follows,
- xfs_trans_context_active
  To check whehter current is in fs transcation or not
- xfs_trans_context_swap
  Transfer the transaction context when rolling a permanent transaction

These two new helpers are instroduced in xfs_trans.h.

Cc: Darrick J. Wong <darrick.wong@oracle.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Dave Chinner <david@fromorbit.com>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: David Howells <dhowells@redhat.com>
Cc: Jeff Layton <jlayton@redhat.com>
Signed-off-by: Yafang Shao <laoar.shao@gmail.com>
---
 fs/iomap/buffered-io.c |  7 -------
 fs/xfs/xfs_aops.c      | 17 +++++++++++++++++
 fs/xfs/xfs_trans.c     |  3 +++
 fs/xfs/xfs_trans.h     | 22 ++++++++++++++++++++++
 4 files changed, 42 insertions(+), 7 deletions(-)

Comments

Darrick J. Wong Dec. 8, 2020, 6:59 p.m. UTC | #1
On Tue, Dec 08, 2020 at 08:28:24PM +0800, Yafang Shao wrote:
> PF_FSTRANS which is used to avoid transaction reservation recursion, is
> dropped since commit 9070733b4efa ("xfs: abstract PF_FSTRANS to
> PF_MEMALLOC_NOFS") and commit 7dea19f9ee63 ("mm: introduce
> memalloc_nofs_{save,restore} API") and replaced by PF_MEMALLOC_NOFS which
> means to avoid filesystem reclaim recursion.
> 
> As these two flags have different meanings, we'd better reintroduce
> PF_FSTRANS back. To avoid wasting the space of PF_* flags in task_struct,
> we can reuse the current->journal_info to do that, per Willy. As the
> check of transaction reservation recursion is used by XFS only, we can
> move the check into xfs_vm_writepage(s), per Dave.
> 
> To better abstract that behavoir, two new helpers are introduced, as
> follows,
> - xfs_trans_context_active
>   To check whehter current is in fs transcation or not
> - xfs_trans_context_swap
>   Transfer the transaction context when rolling a permanent transaction
> 
> These two new helpers are instroduced in xfs_trans.h.
> 
> Cc: Darrick J. Wong <darrick.wong@oracle.com>
> Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
> Cc: Christoph Hellwig <hch@lst.de>
> Cc: Dave Chinner <david@fromorbit.com>
> Cc: Michal Hocko <mhocko@kernel.org>
> Cc: David Howells <dhowells@redhat.com>
> Cc: Jeff Layton <jlayton@redhat.com>
> Signed-off-by: Yafang Shao <laoar.shao@gmail.com>
> ---
>  fs/iomap/buffered-io.c |  7 -------
>  fs/xfs/xfs_aops.c      | 17 +++++++++++++++++
>  fs/xfs/xfs_trans.c     |  3 +++
>  fs/xfs/xfs_trans.h     | 22 ++++++++++++++++++++++
>  4 files changed, 42 insertions(+), 7 deletions(-)
> 
> diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c
> index 10cc7979ce38..3c53fa6ce64d 100644
> --- a/fs/iomap/buffered-io.c
> +++ b/fs/iomap/buffered-io.c
> @@ -1458,13 +1458,6 @@ iomap_do_writepage(struct page *page, struct writeback_control *wbc, void *data)
>  			PF_MEMALLOC))
>  		goto redirty;
>  
> -	/*
> -	 * Given that we do not allow direct reclaim to call us, we should
> -	 * never be called in a recursive filesystem reclaim context.
> -	 */
> -	if (WARN_ON_ONCE(current->flags & PF_MEMALLOC_NOFS))
> -		goto redirty;
> -
>  	/*
>  	 * Is this page beyond the end of the file?
>  	 *
> diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
> index 2371187b7615..0da0242d42c3 100644
> --- a/fs/xfs/xfs_aops.c
> +++ b/fs/xfs/xfs_aops.c
> @@ -568,6 +568,16 @@ xfs_vm_writepage(
>  {
>  	struct xfs_writepage_ctx wpc = { };
>  
> +	/*
> +	 * Given that we do not allow direct reclaim to call us, we should
> +	 * never be called while in a filesystem transaction.
> +	 */
> +	if (WARN_ON_ONCE(xfs_trans_context_active())) {
> +		redirty_page_for_writepage(wbc, page);
> +		unlock_page(page);
> +		return 0;
> +	}
> +
>  	return iomap_writepage(page, wbc, &wpc.ctx, &xfs_writeback_ops);
>  }
>  
> @@ -579,6 +589,13 @@ xfs_vm_writepages(
>  	struct xfs_writepage_ctx wpc = { };
>  
>  	xfs_iflags_clear(XFS_I(mapping->host), XFS_ITRUNCATED);
> +	/*
> +	 * Given that we do not allow direct reclaim to call us, we should
> +	 * never be called while in a filesystem transaction.
> +	 */
> +	if (WARN_ON_ONCE(xfs_trans_context_active()))
> +		return 0;
> +
>  	return iomap_writepages(mapping, wbc, &wpc.ctx, &xfs_writeback_ops);
>  }
>  
> diff --git a/fs/xfs/xfs_trans.c b/fs/xfs/xfs_trans.c
> index fe20398a214e..08d4916ffb13 100644
> --- a/fs/xfs/xfs_trans.c
> +++ b/fs/xfs/xfs_trans.c
> @@ -124,6 +124,9 @@ xfs_trans_dup(
>  	tp->t_rtx_res = tp->t_rtx_res_used;
>  	ntp->t_pflags = tp->t_pflags;

This one line (ntp->t_pflags = tp->t_pflags) should move to
xfs_trans_context_swap.

--D

>  
> +	/* Associate the new transaction with this thread. */
> +	xfs_trans_context_swap(tp, ntp);
> +
>  	/* move deferred ops over to the new tp */
>  	xfs_defer_move(ntp, tp);
>  
> diff --git a/fs/xfs/xfs_trans.h b/fs/xfs/xfs_trans.h
> index 44b11c64a15e..d596a375e3bf 100644
> --- a/fs/xfs/xfs_trans.h
> +++ b/fs/xfs/xfs_trans.h
> @@ -268,16 +268,38 @@ xfs_trans_item_relog(
>  	return lip->li_ops->iop_relog(lip, tp);
>  }
>  
> +static inline bool
> +xfs_trans_context_active(void)
> +{
> +	/* Use journal_info to indicate current is in a transaction */
> +	return current->journal_info != NULL;
> +}
> +
>  static inline void
>  xfs_trans_context_set(struct xfs_trans *tp)
>  {
> +	ASSERT(!current->journal_info);
> +	current->journal_info = tp;
>  	tp->t_pflags = memalloc_nofs_save();
>  }
>  
>  static inline void
>  xfs_trans_context_clear(struct xfs_trans *tp)
>  {
> +	ASSERT(current->journal_info == tp);
> +	current->journal_info = NULL;
>  	memalloc_nofs_restore(tp->t_pflags);
>  }
>  
> +/*
> + * Transfer the transaction context when rolling a permanent
> + * transaction.
> + */
> +static inline void
> +xfs_trans_context_swap(struct xfs_trans *tp, struct xfs_trans *ntp)
> +{
> +	ASSERT(current->journal_info == tp);
> +	current->journal_info = ntp;
> +}
> +
>  #endif	/* __XFS_TRANS_H__ */
> -- 
> 2.18.4
>
Yafang Shao Dec. 9, 2020, 1:40 a.m. UTC | #2
On Wed, Dec 9, 2020 at 3:00 AM Darrick J. Wong <darrick.wong@oracle.com> wrote:
>
> On Tue, Dec 08, 2020 at 08:28:24PM +0800, Yafang Shao wrote:
> > PF_FSTRANS which is used to avoid transaction reservation recursion, is
> > dropped since commit 9070733b4efa ("xfs: abstract PF_FSTRANS to
> > PF_MEMALLOC_NOFS") and commit 7dea19f9ee63 ("mm: introduce
> > memalloc_nofs_{save,restore} API") and replaced by PF_MEMALLOC_NOFS which
> > means to avoid filesystem reclaim recursion.
> >
> > As these two flags have different meanings, we'd better reintroduce
> > PF_FSTRANS back. To avoid wasting the space of PF_* flags in task_struct,
> > we can reuse the current->journal_info to do that, per Willy. As the
> > check of transaction reservation recursion is used by XFS only, we can
> > move the check into xfs_vm_writepage(s), per Dave.
> >
> > To better abstract that behavoir, two new helpers are introduced, as
> > follows,
> > - xfs_trans_context_active
> >   To check whehter current is in fs transcation or not
> > - xfs_trans_context_swap
> >   Transfer the transaction context when rolling a permanent transaction
> >
> > These two new helpers are instroduced in xfs_trans.h.
> >
> > Cc: Darrick J. Wong <darrick.wong@oracle.com>
> > Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
> > Cc: Christoph Hellwig <hch@lst.de>
> > Cc: Dave Chinner <david@fromorbit.com>
> > Cc: Michal Hocko <mhocko@kernel.org>
> > Cc: David Howells <dhowells@redhat.com>
> > Cc: Jeff Layton <jlayton@redhat.com>
> > Signed-off-by: Yafang Shao <laoar.shao@gmail.com>
> > ---
> >  fs/iomap/buffered-io.c |  7 -------
> >  fs/xfs/xfs_aops.c      | 17 +++++++++++++++++
> >  fs/xfs/xfs_trans.c     |  3 +++
> >  fs/xfs/xfs_trans.h     | 22 ++++++++++++++++++++++
> >  4 files changed, 42 insertions(+), 7 deletions(-)
> >
> > diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c
> > index 10cc7979ce38..3c53fa6ce64d 100644
> > --- a/fs/iomap/buffered-io.c
> > +++ b/fs/iomap/buffered-io.c
> > @@ -1458,13 +1458,6 @@ iomap_do_writepage(struct page *page, struct writeback_control *wbc, void *data)
> >                       PF_MEMALLOC))
> >               goto redirty;
> >
> > -     /*
> > -      * Given that we do not allow direct reclaim to call us, we should
> > -      * never be called in a recursive filesystem reclaim context.
> > -      */
> > -     if (WARN_ON_ONCE(current->flags & PF_MEMALLOC_NOFS))
> > -             goto redirty;
> > -
> >       /*
> >        * Is this page beyond the end of the file?
> >        *
> > diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
> > index 2371187b7615..0da0242d42c3 100644
> > --- a/fs/xfs/xfs_aops.c
> > +++ b/fs/xfs/xfs_aops.c
> > @@ -568,6 +568,16 @@ xfs_vm_writepage(
> >  {
> >       struct xfs_writepage_ctx wpc = { };
> >
> > +     /*
> > +      * Given that we do not allow direct reclaim to call us, we should
> > +      * never be called while in a filesystem transaction.
> > +      */
> > +     if (WARN_ON_ONCE(xfs_trans_context_active())) {
> > +             redirty_page_for_writepage(wbc, page);
> > +             unlock_page(page);
> > +             return 0;
> > +     }
> > +
> >       return iomap_writepage(page, wbc, &wpc.ctx, &xfs_writeback_ops);
> >  }
> >
> > @@ -579,6 +589,13 @@ xfs_vm_writepages(
> >       struct xfs_writepage_ctx wpc = { };
> >
> >       xfs_iflags_clear(XFS_I(mapping->host), XFS_ITRUNCATED);
> > +     /*
> > +      * Given that we do not allow direct reclaim to call us, we should
> > +      * never be called while in a filesystem transaction.
> > +      */
> > +     if (WARN_ON_ONCE(xfs_trans_context_active()))
> > +             return 0;
> > +
> >       return iomap_writepages(mapping, wbc, &wpc.ctx, &xfs_writeback_ops);
> >  }
> >
> > diff --git a/fs/xfs/xfs_trans.c b/fs/xfs/xfs_trans.c
> > index fe20398a214e..08d4916ffb13 100644
> > --- a/fs/xfs/xfs_trans.c
> > +++ b/fs/xfs/xfs_trans.c
> > @@ -124,6 +124,9 @@ xfs_trans_dup(
> >       tp->t_rtx_res = tp->t_rtx_res_used;
> >       ntp->t_pflags = tp->t_pflags;
>
> This one line (ntp->t_pflags = tp->t_pflags) should move to
> xfs_trans_context_swap.
>

Make sense to me.
Will update it.


> --D
>
> >
> > +     /* Associate the new transaction with this thread. */
> > +     xfs_trans_context_swap(tp, ntp);
> > +
> >       /* move deferred ops over to the new tp */
> >       xfs_defer_move(ntp, tp);
> >
> > diff --git a/fs/xfs/xfs_trans.h b/fs/xfs/xfs_trans.h
> > index 44b11c64a15e..d596a375e3bf 100644
> > --- a/fs/xfs/xfs_trans.h
> > +++ b/fs/xfs/xfs_trans.h
> > @@ -268,16 +268,38 @@ xfs_trans_item_relog(
> >       return lip->li_ops->iop_relog(lip, tp);
> >  }
> >
> > +static inline bool
> > +xfs_trans_context_active(void)
> > +{
> > +     /* Use journal_info to indicate current is in a transaction */
> > +     return current->journal_info != NULL;
> > +}
> > +
> >  static inline void
> >  xfs_trans_context_set(struct xfs_trans *tp)
> >  {
> > +     ASSERT(!current->journal_info);
> > +     current->journal_info = tp;
> >       tp->t_pflags = memalloc_nofs_save();
> >  }
> >
> >  static inline void
> >  xfs_trans_context_clear(struct xfs_trans *tp)
> >  {
> > +     ASSERT(current->journal_info == tp);
> > +     current->journal_info = NULL;
> >       memalloc_nofs_restore(tp->t_pflags);
> >  }
> >
> > +/*
> > + * Transfer the transaction context when rolling a permanent
> > + * transaction.
> > + */
> > +static inline void
> > +xfs_trans_context_swap(struct xfs_trans *tp, struct xfs_trans *ntp)
> > +{
> > +     ASSERT(current->journal_info == tp);
> > +     current->journal_info = ntp;
> > +}
> > +
> >  #endif       /* __XFS_TRANS_H__ */
> > --
> > 2.18.4
> >



--
Thanks
Yafang
diff mbox series

Patch

diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c
index 10cc7979ce38..3c53fa6ce64d 100644
--- a/fs/iomap/buffered-io.c
+++ b/fs/iomap/buffered-io.c
@@ -1458,13 +1458,6 @@  iomap_do_writepage(struct page *page, struct writeback_control *wbc, void *data)
 			PF_MEMALLOC))
 		goto redirty;
 
-	/*
-	 * Given that we do not allow direct reclaim to call us, we should
-	 * never be called in a recursive filesystem reclaim context.
-	 */
-	if (WARN_ON_ONCE(current->flags & PF_MEMALLOC_NOFS))
-		goto redirty;
-
 	/*
 	 * Is this page beyond the end of the file?
 	 *
diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index 2371187b7615..0da0242d42c3 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -568,6 +568,16 @@  xfs_vm_writepage(
 {
 	struct xfs_writepage_ctx wpc = { };
 
+	/*
+	 * Given that we do not allow direct reclaim to call us, we should
+	 * never be called while in a filesystem transaction.
+	 */
+	if (WARN_ON_ONCE(xfs_trans_context_active())) {
+		redirty_page_for_writepage(wbc, page);
+		unlock_page(page);
+		return 0;
+	}
+
 	return iomap_writepage(page, wbc, &wpc.ctx, &xfs_writeback_ops);
 }
 
@@ -579,6 +589,13 @@  xfs_vm_writepages(
 	struct xfs_writepage_ctx wpc = { };
 
 	xfs_iflags_clear(XFS_I(mapping->host), XFS_ITRUNCATED);
+	/*
+	 * Given that we do not allow direct reclaim to call us, we should
+	 * never be called while in a filesystem transaction.
+	 */
+	if (WARN_ON_ONCE(xfs_trans_context_active()))
+		return 0;
+
 	return iomap_writepages(mapping, wbc, &wpc.ctx, &xfs_writeback_ops);
 }
 
diff --git a/fs/xfs/xfs_trans.c b/fs/xfs/xfs_trans.c
index fe20398a214e..08d4916ffb13 100644
--- a/fs/xfs/xfs_trans.c
+++ b/fs/xfs/xfs_trans.c
@@ -124,6 +124,9 @@  xfs_trans_dup(
 	tp->t_rtx_res = tp->t_rtx_res_used;
 	ntp->t_pflags = tp->t_pflags;
 
+	/* Associate the new transaction with this thread. */
+	xfs_trans_context_swap(tp, ntp);
+
 	/* move deferred ops over to the new tp */
 	xfs_defer_move(ntp, tp);
 
diff --git a/fs/xfs/xfs_trans.h b/fs/xfs/xfs_trans.h
index 44b11c64a15e..d596a375e3bf 100644
--- a/fs/xfs/xfs_trans.h
+++ b/fs/xfs/xfs_trans.h
@@ -268,16 +268,38 @@  xfs_trans_item_relog(
 	return lip->li_ops->iop_relog(lip, tp);
 }
 
+static inline bool
+xfs_trans_context_active(void)
+{
+	/* Use journal_info to indicate current is in a transaction */
+	return current->journal_info != NULL;
+}
+
 static inline void
 xfs_trans_context_set(struct xfs_trans *tp)
 {
+	ASSERT(!current->journal_info);
+	current->journal_info = tp;
 	tp->t_pflags = memalloc_nofs_save();
 }
 
 static inline void
 xfs_trans_context_clear(struct xfs_trans *tp)
 {
+	ASSERT(current->journal_info == tp);
+	current->journal_info = NULL;
 	memalloc_nofs_restore(tp->t_pflags);
 }
 
+/*
+ * Transfer the transaction context when rolling a permanent
+ * transaction.
+ */
+static inline void
+xfs_trans_context_swap(struct xfs_trans *tp, struct xfs_trans *ntp)
+{
+	ASSERT(current->journal_info == tp);
+	current->journal_info = ntp;
+}
+
 #endif	/* __XFS_TRANS_H__ */