From: "Matthew Wilcox (Oracle)" <willy@xxxxxxxxxxxxx>
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@xxxxxxxxxxxxx>
Cc: Christoph Hellwig <hch@xxxxxxxxxxxxx>
Cc: Darrick J. Wong <darrick.wong@xxxxxxxxxx>
Cc: Matthew Wilcox <willy@xxxxxxxxxxxxx>
Acked-by: Michal Hocko <mhocko@xxxxxxxx>
Signed-off-by: Matthew Wilcox (Oracle) <willy@xxxxxxxxxxxxx>
Signed-off-by: Yafang Shao <laoar.shao@xxxxxxxxx>
---
fs/xfs/libxfs/xfs_btree.c | 14 ++++++++------
include/linux/sched/mm.h | 23 +++++++++++++++++++++++
mm/vmscan.c | 16 +---------------
3 files changed, 32 insertions(+), 21 deletions(-)
diff --git a/fs/xfs/libxfs/xfs_btree.c b/fs/xfs/libxfs/xfs_btree.c
index 2d25bab68764..a04a44238aab 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 f889e332912f..b38fdcb977a4 100644
--- a/include/linux/sched/mm.h
+++ b/include/linux/sched/mm.h
@@ -303,6 +303,29 @@ 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 &= ~(flags ^ KSWAPD_PF_FLAGS);
+}
+
#ifdef CONFIG_MEMCG
/**
* memalloc_use_memcg - Starts the remote memcg charging scope.
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 99e1796eb833..3a2615bfde35 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -3859,19 +3859,7 @@ 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);
@@ -3921,8 +3909,6 @@ static int kswapd(void *p)
goto kswapd_try_sleep;
}
- tsk->flags &= ~(PF_MEMALLOC | PF_SWAPWRITE | PF_KSWAPD);
-
return 0;
}
--
2.18.1
