@@ -1500,9 +1500,9 @@ iomap_do_writepage(struct page *page, struct writeback_control *wbc, void *data)
/*
* Given that we do not allow direct reclaim to call us, we should
- * never be called in a recursive filesystem reclaim context.
+ * never be called while in a filesystem transaction.
*/
- if (WARN_ON_ONCE(current->flags & PF_MEMALLOC_NOFS))
+ if (WARN_ON_ONCE(fstrans_context_active()))
goto redirty;
/*
@@ -62,7 +62,8 @@ 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 +126,7 @@ 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 */
@@ -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 */
@@ -153,8 +153,6 @@ xfs_trans_reserve(
int error = 0;
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);
/*
* Attempt to reserve the needed disk blocks by decrementing
@@ -163,10 +161,8 @@ 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);
+ if (error != 0)
return -ENOSPC;
- }
tp->t_blk_res += blocks;
}
@@ -241,8 +237,6 @@ xfs_trans_reserve(
tp->t_blk_res = 0;
}
- current_restore_flags_nested(&tp->t_pflags, PF_MEMALLOC_NOFS);
-
return error;
}
@@ -284,6 +278,8 @@ 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 +874,8 @@ __xfs_trans_commit(
xfs_log_commit_cil(mp, tp, &commit_lsn, regrant);
- current_restore_flags_nested(&tp->t_pflags, PF_MEMALLOC_NOFS);
+ if (!regrant)
+ xfs_trans_context_clear(tp);
xfs_trans_free(tp);
/*
@@ -910,7 +907,8 @@ __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 +969,7 @@ 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);
@@ -1013,6 +1011,7 @@ xfs_trans_roll(
if (error)
return error;
+ xfs_trans_context_update(trans, *tpp);
/*
* Reserve space in the log for the next transaction.
* This also pushes items in the "AIL", the list of logged items,
@@ -243,4 +243,27 @@ void xfs_trans_buf_copy_type(struct xfs_buf *dst_bp,
extern kmem_zone_t *xfs_trans_zone;
+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_update(struct xfs_trans *old, struct xfs_trans *new)
+{
+ ASSERT(current->journal_info == old);
+ current->journal_info = new;
+}
+
+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);
+}
+
#endif /* __XFS_TRANS_H__ */
@@ -271,4 +271,11 @@ int iomap_swapfile_activate(struct swap_info_struct *sis,
# define iomap_swapfile_activate(sis, swapfile, pagespan, ops) (-EIO)
#endif /* CONFIG_SWAP */
+/* Use the journal_info to indicate current is in a transaction */
+static inline bool
+fstrans_context_active(void)
+{
+ return current->journal_info != NULL;
+}
+
#endif /* LINUX_IOMAP_H */
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. That change is subtle. Let's take the exmple of the check of WARN_ON_ONCE(current->flags & PF_MEMALLOC_NOFS)) to explain why this abstraction from PF_FSTRANS to PF_MEMALLOC_NOFS is not proper. Below comment is quoted from Dave, > It wasn't for memory allocation recursion protection in XFS - it was for > transaction reservation recursion protection by something trying to flush > data pages while holding a transaction reservation. Doing > this could deadlock the journal because the existing reservation > could prevent the nested reservation for being able to reserve space > in the journal and that is a self-deadlock vector. > IOWs, this check is not protecting against memory reclaim recursion > bugs at all (that's the previous check [1]). This check is > protecting against the filesystem calling writepages directly from a > context where it can self-deadlock. > So what we are seeing here is that the PF_FSTRANS -> > PF_MEMALLOC_NOFS abstraction lost all the actual useful information > about what type of error this check was protecting against. As a result, we should reintroduce PF_FSTRANS. As current->journal_info isn't used in XFS, we can reuse it to indicate whehter the task is in fstrans or not, Per Willy. To achieve that, four new helpers are introduce in this patch, per Dave: - xfs_trans_context_set() Used in xfs_trans_alloc() - xfs_trans_context_clear() Used in xfs_trans_commit() and xfs_trans_cancel() - xfs_trans_context_update() Used in xfs_trans_roll() - fstrans_context_active() To check whehter current is in fs transcation or not [1]. Below check is to avoid memory reclaim recursion. if (WARN_ON_ONCE((current->flags & (PF_MEMALLOC|PF_KSWAPD)) == PF_MEMALLOC)) goto redirty; Cc: Dave Chinner <david@fromorbit.com> Cc: Christoph Hellwig <hch@infradead.org> Cc: Michal Hocko <mhocko@kernel.org> Cc: Darrick J. Wong <darrick.wong@oracle.com> Cc: Matthew Wilcox <willy@infradead.org> Signed-off-by: Yafang Shao <laoar.shao@gmail.com> --- fs/iomap/buffered-io.c | 4 ++-- fs/xfs/xfs_aops.c | 5 +++-- fs/xfs/xfs_linux.h | 4 ---- fs/xfs/xfs_trans.c | 19 +++++++++---------- fs/xfs/xfs_trans.h | 23 +++++++++++++++++++++++ include/linux/iomap.h | 7 +++++++ 6 files changed, 44 insertions(+), 18 deletions(-)