[PATCH v15 0/4] xfs: avoid transaction reservation recursion

[PATCH v15 0/4] xfs: avoid transaction reservation recursion

[Yafang Shao]

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.

Patch #1 and #2 are to use the memalloc_nofs_{save,restore} API 
Patch #1 is picked form Willy's patchset "Overhaul memalloc_no*"[1]

Patch #3 is the refactor of xfs_trans context, which is activated when
xfs_trans is allocated and deactivated when xfs_trans is freed.

Patch #4 is the implementation of reusing current->journal_info to
avoid transaction reservation recursion.

No obvious error occurred after running xfstests
(with CONFIG_XFS_ASSERT_FATAL enabled).

[1]. https://lore.kernel.org/linux-mm/20200625113122.7540-1-willy@infradead.org

v15:
- fix Assertion_failed reported by kernel test robot
- run xfstests with CONFIG_XFS_ASSERT_FATAL enabled

v14:
- minor optimze in restore_kswapd(), per Dave.
- don't need to refactor xfs_trans_context_{set,clear} 
- remove redundant comments in patch #4

v13:
- move xfs_trans_context_swap() into patch #3 and set NOFS to the old 
  transaction

v12:
Per Darrick's suggestion,
- add the check before calling xfs_trans_context_clear() in
  xfs_trans_context_free().
- move t_pflags into xfs_trans_context_swap()

v11:
- add the warning at the callsite of xfs_trans_context_active()
- improve the commit log of patch #2

v10:
- refactor the code, per Dave.

v9:
- rebase it on xfs tree.
- Darrick fixed an error occurred in xfs/141
- run xfstests, and no obvious error occurred.

v8:
- check xfs_trans_context_active() in xfs_vm_writepage(s), per Dave.

v7:
- check fstrans recursion for XFS only, by introducing a new member in
  struct writeback_control.

v6:
- add Michal's ack and comment in patch #1.

v5:
- pick one of Willy's patch
- introduce four new helpers, per Dave

v4:
- retitle from "xfs: introduce task->in_fstrans for transaction reservation
  recursion protection"
- reuse current->journal_info, per Willy

Matthew Wilcox (Oracle) (1):
  mm: Add become_kswapd and restore_kswapd

Yafang Shao (3):
  xfs: use memalloc_nofs_{save,restore} in xfs transaction
  xfs: refactor the usage around xfs_trans_context_{set,clear}
  xfs: use current->journal_info to avoid transaction reservation
    recursion

 fs/iomap/buffered-io.c    |  7 -------
 fs/xfs/libxfs/xfs_btree.c | 14 ++++++++------
 fs/xfs/xfs_aops.c         | 14 ++++++++++++--
 fs/xfs/xfs_linux.h        |  4 ----
 fs/xfs/xfs_trans.c        | 26 ++++++++++++--------------
 fs/xfs/xfs_trans.h        | 36 ++++++++++++++++++++++++++++++++++++
 include/linux/sched/mm.h  | 22 ++++++++++++++++++++++
 mm/vmscan.c               | 16 +---------------
 8 files changed, 91 insertions(+), 48 deletions(-)

-- 
2.17.1

[PATCH v15 1/4] mm: Add become_kswapd and restore_kswapd

[Yafang Shao]

From: "Matthew Wilcox (Oracle)" <willy@infradead.org>

Since XFS needs to pretend to be kswapd in some of its worker threads,
create methods to save & restore kswapd state.  Don't bother restoring
kswapd state in kswapd -- the only time we reach this code is when we're
exiting and the task_struct is about to be destroyed anyway.

Cc: Dave Chinner <david@fromorbit.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Signed-off-by: Yafang Shao <laoar.shao@gmail.com>
---
 fs/xfs/libxfs/xfs_btree.c | 14 ++++++++------
 include/linux/sched/mm.h  | 22 ++++++++++++++++++++++
 mm/vmscan.c               | 16 +---------------
 3 files changed, 31 insertions(+), 21 deletions(-)

diff --git a/fs/xfs/libxfs/xfs_btree.c b/fs/xfs/libxfs/xfs_btree.c
index c4d7a9241dc3..c43f2ad85af9 100644
--- a/fs/xfs/libxfs/xfs_btree.c
+++ b/fs/xfs/libxfs/xfs_btree.c
@@ -2813,8 +2813,9 @@ xfs_btree_split_worker(
 {
 	struct xfs_btree_split_args	*args = container_of(work,
 						struct xfs_btree_split_args, work);
+	bool			is_kswapd = args->kswapd;
 	unsigned long		pflags;
-	unsigned long		new_pflags = PF_MEMALLOC_NOFS;
+	int			memalloc_nofs;
 
 	/*
 	 * we are in a transaction context here, but may also be doing work
@@ -2822,16 +2823,17 @@ xfs_btree_split_worker(
 	 * temporarily to ensure that we don't block waiting for memory reclaim
 	 * in any way.
 	 */
-	if (args->kswapd)
-		new_pflags |= PF_MEMALLOC | PF_SWAPWRITE | PF_KSWAPD;
-
-	current_set_flags_nested(&pflags, new_pflags);
+	if (is_kswapd)
+		pflags = become_kswapd();
+	memalloc_nofs = memalloc_nofs_save();
 
 	args->result = __xfs_btree_split(args->cur, args->level, args->ptrp,
 					 args->key, args->curp, args->stat);
 	complete(args->done);
 
-	current_restore_flags_nested(&pflags, new_pflags);
+	memalloc_nofs_restore(memalloc_nofs);
+	if (is_kswapd)
+		restore_kswapd(pflags);
 }
 
 /*
diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h
index d5ece7a9a403..7195e542a54d 100644
--- a/include/linux/sched/mm.h
+++ b/include/linux/sched/mm.h
@@ -278,6 +278,28 @@ static inline void memalloc_nocma_restore(unsigned int flags)
 }
 #endif
 
+/*
+ * Tell the memory management code that this thread is working on behalf
+ * of background memory reclaim (like kswapd).  That means that it will
+ * get access to memory reserves should it need to allocate memory in
+ * order to make forward progress.  With this great power comes great
+ * responsibility to not exhaust those reserves.
+ */
+#define KSWAPD_PF_FLAGS		(PF_MEMALLOC | PF_SWAPWRITE | PF_KSWAPD)
+
+static inline unsigned long become_kswapd(void)
+{
+	unsigned long flags = current->flags & KSWAPD_PF_FLAGS;
+
+	current->flags |= KSWAPD_PF_FLAGS;
+	return flags;
+}
+
+static inline void restore_kswapd(unsigned long flags)
+{
+	current->flags = (current->flags & ~KSWAPD_PF_FLAGS) | flags;
+}
+
 #ifdef CONFIG_MEMCG
 DECLARE_PER_CPU(struct mem_cgroup *, int_active_memcg);
 /**
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 7b4e31eac2cf..15af99d1f3f7 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -3870,19 +3870,7 @@ static int kswapd(void *p)
 	if (!cpumask_empty(cpumask))
 		set_cpus_allowed_ptr(tsk, cpumask);
 
-	/*
-	 * Tell the memory management that we're a "memory allocator",
-	 * and that if we need more memory we should get access to it
-	 * regardless (see "__alloc_pages()"). "kswapd" should
-	 * never get caught in the normal page freeing logic.
-	 *
-	 * (Kswapd normally doesn't need memory anyway, but sometimes
-	 * you need a small amount of memory in order to be able to
-	 * page out something else, and this flag essentially protects
-	 * us from recursively trying to free more memory as we're
-	 * trying to free the first piece of memory in the first place).
-	 */
-	tsk->flags |= PF_MEMALLOC | PF_SWAPWRITE | PF_KSWAPD;
+	become_kswapd();
 	set_freezable();
 
 	WRITE_ONCE(pgdat->kswapd_order, 0);
@@ -3932,8 +3920,6 @@ static int kswapd(void *p)
 			goto kswapd_try_sleep;
 	}
 
-	tsk->flags &= ~(PF_MEMALLOC | PF_SWAPWRITE | PF_KSWAPD);
-
 	return 0;
 }
 
-- 
2.17.1

[PATCH v15 2/4] xfs: use memalloc_nofs_{save,restore} in xfs transaction

[Yafang Shao]

Introduce a new API to mark the start and end of XFS transactions.
For now, just save and restore the memalloc_nofs flags.

The new helpers as follows,
- xfs_trans_context_set
  Mark the start of XFS transactions
- xfs_trans_context_clear
  Mark the end of XFS transactions

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>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Yafang Shao <laoar.shao@gmail.com>
---
 fs/xfs/xfs_aops.c  |  4 ++--
 fs/xfs/xfs_linux.h |  4 ----
 fs/xfs/xfs_trans.c | 13 +++++++------
 fs/xfs/xfs_trans.h | 12 ++++++++++++
 4 files changed, 21 insertions(+), 12 deletions(-)

diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index 4304c6416fbb..2371187b7615 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -62,7 +62,7 @@ xfs_setfilesize_trans_alloc(
 	 * We hand off the transaction to the completion thread now, so
 	 * clear the flag here.
 	 */
-	current_restore_flags_nested(&tp->t_pflags, PF_MEMALLOC_NOFS);
+	xfs_trans_context_clear(tp);
 	return 0;
 }
 
@@ -125,7 +125,7 @@ xfs_setfilesize_ioend(
 	 * thus we need to mark ourselves as being in a transaction manually.
 	 * Similarly for freeze protection.
 	 */
-	current_set_flags_nested(&tp->t_pflags, PF_MEMALLOC_NOFS);
+	xfs_trans_context_set(tp);
 	__sb_writers_acquired(VFS_I(ip)->i_sb, SB_FREEZE_FS);
 
 	/* we abort the update if there was an IO error */
diff --git a/fs/xfs/xfs_linux.h b/fs/xfs/xfs_linux.h
index 5b7a1e201559..6ab0f8043c73 100644
--- a/fs/xfs/xfs_linux.h
+++ b/fs/xfs/xfs_linux.h
@@ -102,10 +102,6 @@ typedef __u32			xfs_nlink_t;
 #define xfs_cowb_secs		xfs_params.cowb_timer.val
 
 #define current_cpu()		(raw_smp_processor_id())
-#define current_set_flags_nested(sp, f)		\
-		(*(sp) = current->flags, current->flags |= (f))
-#define current_restore_flags_nested(sp, f)	\
-		(current->flags = ((current->flags & ~(f)) | (*(sp) & (f))))
 
 #define NBBY		8		/* number of bits per byte */
 
diff --git a/fs/xfs/xfs_trans.c b/fs/xfs/xfs_trans.c
index e72730f85af1..43107af569fe 100644
--- a/fs/xfs/xfs_trans.c
+++ b/fs/xfs/xfs_trans.c
@@ -154,7 +154,7 @@ xfs_trans_reserve(
 	bool			rsvd = (tp->t_flags & XFS_TRANS_RESERVE) != 0;
 
 	/* Mark this thread as being in a transaction */
-	current_set_flags_nested(&tp->t_pflags, PF_MEMALLOC_NOFS);
+	xfs_trans_context_set(tp);
 
 	/*
 	 * Attempt to reserve the needed disk blocks by decrementing
@@ -164,7 +164,7 @@ xfs_trans_reserve(
 	if (blocks > 0) {
 		error = xfs_mod_fdblocks(mp, -((int64_t)blocks), rsvd);
 		if (error != 0) {
-			current_restore_flags_nested(&tp->t_pflags, PF_MEMALLOC_NOFS);
+			xfs_trans_context_clear(tp);
 			return -ENOSPC;
 		}
 		tp->t_blk_res += blocks;
@@ -241,7 +241,7 @@ xfs_trans_reserve(
 		tp->t_blk_res = 0;
 	}
 
-	current_restore_flags_nested(&tp->t_pflags, PF_MEMALLOC_NOFS);
+	xfs_trans_context_clear(tp);
 
 	return error;
 }
@@ -878,7 +878,7 @@ __xfs_trans_commit(
 
 	xfs_log_commit_cil(mp, tp, &commit_lsn, regrant);
 
-	current_restore_flags_nested(&tp->t_pflags, PF_MEMALLOC_NOFS);
+	xfs_trans_context_clear(tp);
 	xfs_trans_free(tp);
 
 	/*
@@ -910,7 +910,8 @@ __xfs_trans_commit(
 			xfs_log_ticket_ungrant(mp->m_log, tp->t_ticket);
 		tp->t_ticket = NULL;
 	}
-	current_restore_flags_nested(&tp->t_pflags, PF_MEMALLOC_NOFS);
+
+	xfs_trans_context_clear(tp);
 	xfs_trans_free_items(tp, !!error);
 	xfs_trans_free(tp);
 
@@ -971,7 +972,7 @@ xfs_trans_cancel(
 	}
 
 	/* mark this thread as no longer being in a transaction */
-	current_restore_flags_nested(&tp->t_pflags, PF_MEMALLOC_NOFS);
+	xfs_trans_context_clear(tp);
 
 	xfs_trans_free_items(tp, dirty);
 	xfs_trans_free(tp);
diff --git a/fs/xfs/xfs_trans.h b/fs/xfs/xfs_trans.h
index 084658946cc8..44b11c64a15e 100644
--- a/fs/xfs/xfs_trans.h
+++ b/fs/xfs/xfs_trans.h
@@ -268,4 +268,16 @@ xfs_trans_item_relog(
 	return lip->li_ops->iop_relog(lip, tp);
 }
 
+static inline void
+xfs_trans_context_set(struct xfs_trans *tp)
+{
+	tp->t_pflags = memalloc_nofs_save();
+}
+
+static inline void
+xfs_trans_context_clear(struct xfs_trans *tp)
+{
+	memalloc_nofs_restore(tp->t_pflags);
+}
+
 #endif	/* __XFS_TRANS_H__ */
-- 
2.17.1

[PATCH v15 3/4] xfs: refactor the usage around xfs_trans_context_{set,clear}

[Yafang Shao]

The xfs_trans context should be active after it is allocated, and
deactive when it is freed.
The rolling transaction should be specially considered, because in the
case when we clear the old transaction the thread's NOFS state shouldn't
be changed, as a result we have to set NOFS in the old transaction's
t_pflags in xfs_trans_context_swap().

So these helpers are refactored as,
- xfs_trans_context_set()
  Used in xfs_trans_alloc()
- xfs_trans_context_clear()
  Used in xfs_trans_free()

And a new helper is instroduced to handle the rolling transaction,
- xfs_trans_context_swap()
  Used in rolling transaction

This patch is based on Darrick's work[1] to fix the issue in xfs/141 in the
earlier version and Dave's suggestion[2].

[1]. https://lore.kernel.org/linux-xfs/20201104001649.GN7123@magnolia
[2]. https://lore.kernel.org/linux-xfs/20201218000705.GR632069@dread.disaster.area

Cc: Dave Chinner <david@fromorbit.com>
Cc: Darrick J. Wong <darrick.wong@oracle.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Christoph Hellwig <hch@lst.de>
Signed-off-by: Yafang Shao <laoar.shao@gmail.com>
---
 fs/xfs/xfs_trans.c | 25 +++++++++++--------------
 fs/xfs/xfs_trans.h | 10 +++++++++-
 2 files changed, 20 insertions(+), 15 deletions(-)

diff --git a/fs/xfs/xfs_trans.c b/fs/xfs/xfs_trans.c
index 43107af569fe..b76e850c9ae7 100644
--- a/fs/xfs/xfs_trans.c
+++ b/fs/xfs/xfs_trans.c
@@ -67,6 +67,10 @@ xfs_trans_free(
 	xfs_extent_busy_sort(&tp->t_busy);
 	xfs_extent_busy_clear(tp->t_mountp, &tp->t_busy, false);
 
+
+	/* Detach the transaction from this thread. */
+	xfs_trans_context_clear(tp);
+
 	trace_xfs_trans_free(tp, _RET_IP_);
 	if (!(tp->t_flags & XFS_TRANS_NO_WRITECOUNT))
 		sb_end_intwrite(tp->t_mountp->m_super);
@@ -119,7 +123,9 @@ xfs_trans_dup(
 
 	ntp->t_rtx_res = tp->t_rtx_res - tp->t_rtx_res_used;
 	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);
@@ -153,9 +159,6 @@ xfs_trans_reserve(
 	int			error = 0;
 	bool			rsvd = (tp->t_flags & XFS_TRANS_RESERVE) != 0;
 
-	/* Mark this thread as being in a transaction */
-	xfs_trans_context_set(tp);
-
 	/*
 	 * Attempt to reserve the needed disk blocks by decrementing
 	 * the number needed from the number available.  This will
@@ -163,10 +166,9 @@ xfs_trans_reserve(
 	 */
 	if (blocks > 0) {
 		error = xfs_mod_fdblocks(mp, -((int64_t)blocks), rsvd);
-		if (error != 0) {
-			xfs_trans_context_clear(tp);
+		if (error != 0)
 			return -ENOSPC;
-		}
+
 		tp->t_blk_res += blocks;
 	}
 
@@ -241,8 +243,6 @@ xfs_trans_reserve(
 		tp->t_blk_res = 0;
 	}
 
-	xfs_trans_context_clear(tp);
-
 	return error;
 }
 
@@ -284,6 +284,8 @@ xfs_trans_alloc(
 	INIT_LIST_HEAD(&tp->t_dfops);
 	tp->t_firstblock = NULLFSBLOCK;
 
+	/* Mark this thread as being in a transaction */
+	xfs_trans_context_set(tp);
 	error = xfs_trans_reserve(tp, resp, blocks, rtextents);
 	if (error) {
 		xfs_trans_cancel(tp);
@@ -878,7 +880,6 @@ __xfs_trans_commit(
 
 	xfs_log_commit_cil(mp, tp, &commit_lsn, regrant);
 
-	xfs_trans_context_clear(tp);
 	xfs_trans_free(tp);
 
 	/*
@@ -911,7 +912,6 @@ __xfs_trans_commit(
 		tp->t_ticket = NULL;
 	}
 
-	xfs_trans_context_clear(tp);
 	xfs_trans_free_items(tp, !!error);
 	xfs_trans_free(tp);
 
@@ -971,9 +971,6 @@ xfs_trans_cancel(
 		tp->t_ticket = NULL;
 	}
 
-	/* mark this thread as no longer being in a transaction */
-	xfs_trans_context_clear(tp);
-
 	xfs_trans_free_items(tp, dirty);
 	xfs_trans_free(tp);
 }
diff --git a/fs/xfs/xfs_trans.h b/fs/xfs/xfs_trans.h
index 44b11c64a15e..3645fd0d74b8 100644
--- a/fs/xfs/xfs_trans.h
+++ b/fs/xfs/xfs_trans.h
@@ -277,7 +277,15 @@ xfs_trans_context_set(struct xfs_trans *tp)
 static inline void
 xfs_trans_context_clear(struct xfs_trans *tp)
 {
-	memalloc_nofs_restore(tp->t_pflags);
+	if (!tp->t_pflags)
+		memalloc_nofs_restore(tp->t_pflags);
+}
+
+static inline void
+xfs_trans_context_swap(struct xfs_trans *tp, struct xfs_trans *ntp)
+{
+	ntp->t_pflags = tp->t_pflags;
+	tp->t_pflags = -1;
 }
 
 #endif	/* __XFS_TRANS_H__ */
-- 
2.17.1

[PATCH v15 4/4] xfs: use current->journal_info to avoid transaction reservation recursion

[Yafang Shao]

PF_FSTRANS which is used to avoid transaction reservation recursion, is
dropped since commit 9070733b4efa ("xfs: abstract PF_FSTRANS to
PF_MEMALLOC_NOFS") 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.

[oliver.sang@intel.com: reported a Assertion_failed in the prev version]

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>
Cc: kernel test robot <oliver.sang@intel.com>
Signed-off-by: Yafang Shao <laoar.shao@gmail.com>
---
 fs/iomap/buffered-io.c |  7 -------
 fs/xfs/xfs_aops.c      | 10 ++++++++++
 fs/xfs/xfs_trans.h     | 22 +++++++++++++++++++---
 3 files changed, 29 insertions(+), 10 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..eed4881d4461 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -568,6 +568,12 @@ xfs_vm_writepage(
 {
 	struct xfs_writepage_ctx wpc = { };
 
+	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 +585,10 @@ xfs_vm_writepages(
 	struct xfs_writepage_ctx wpc = { };
 
 	xfs_iflags_clear(XFS_I(mapping->host), XFS_ITRUNCATED);
+
+	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.h b/fs/xfs/xfs_trans.h
index 3645fd0d74b8..e2f3251d6cce 100644
--- a/fs/xfs/xfs_trans.h
+++ b/fs/xfs/xfs_trans.h
@@ -268,24 +268,40 @@ xfs_trans_item_relog(
 	return lip->li_ops->iop_relog(lip, tp);
 }
 
+static inline bool
+xfs_trans_context_active(void)
+{
+	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)
 {
-	if (!tp->t_pflags)
-		memalloc_nofs_restore(tp->t_pflags);
+	/*
+	 * If we handed over the context via xfs_trans_context_swap() then
+	 * the context is no longer needed to clear.
+	 */
+	if (current->journal_info != tp)
+		return;
+
+	current->journal_info = NULL;
+	memalloc_nofs_restore(tp->t_pflags);
 }
 
 static inline void
 xfs_trans_context_swap(struct xfs_trans *tp, struct xfs_trans *ntp)
 {
+	ASSERT(current->journal_info == tp);
+	current->journal_info = ntp;
 	ntp->t_pflags = tp->t_pflags;
-	tp->t_pflags = -1;
 }
 
 #endif	/* __XFS_TRANS_H__ */
-- 
2.17.1