[PATCH] fs: fall back to file_ref_put() for non-last reference

[Mateusz Guzik <mjguzik@gmail.com>]

This reduces the slowdown in face of multiple callers issuing close on
what turns out to not be the last reference.

Signed-off-by: Mateusz Guzik <mjguzik@gmail.com>
Reported-by: kernel test robot <oliver.sang@intel.com>
Closes: https://lore.kernel.org/oe-lkp/202504171513.6d6f8a16-lkp@intel.com
---
 fs/file.c                |  2 +-
 include/linux/file_ref.h | 19 ++++++-------------
 2 files changed, 7 insertions(+), 14 deletions(-)

diff --git a/fs/file.c b/fs/file.c
index dc3f7e120e3e..3a3146664cf3 100644
--- a/fs/file.c
+++ b/fs/file.c
@@ -26,7 +26,7 @@
 
 #include "internal.h"
 
-bool __file_ref_put_badval(file_ref_t *ref, unsigned long cnt)
+static noinline bool __file_ref_put_badval(file_ref_t *ref, unsigned long cnt)
 {
 	/*
 	 * If the reference count was already in the dead zone, then this
diff --git a/include/linux/file_ref.h b/include/linux/file_ref.h
index 7db62fbc0500..0f25ba769f48 100644
--- a/include/linux/file_ref.h
+++ b/include/linux/file_ref.h
@@ -61,7 +61,6 @@ static inline void file_ref_init(file_ref_t *ref, unsigned long cnt)
 	atomic_long_set(&ref->refcnt, cnt - 1);
 }
 
-bool __file_ref_put_badval(file_ref_t *ref, unsigned long cnt);
 bool __file_ref_put(file_ref_t *ref, unsigned long cnt);
 
 /**
@@ -178,20 +177,14 @@ static __always_inline __must_check bool file_ref_put(file_ref_t *ref)
  */
 static __always_inline __must_check bool file_ref_put_close(file_ref_t *ref)
 {
-	long old, new;
+	long old;
 
 	old = atomic_long_read(&ref->refcnt);
-	do {
-		if (unlikely(old < 0))
-			return __file_ref_put_badval(ref, old);
-
-		if (old == FILE_REF_ONEREF)
-			new = FILE_REF_DEAD;
-		else
-			new = old - 1;
-	} while (!atomic_long_try_cmpxchg(&ref->refcnt, &old, new));
-
-	return new == FILE_REF_DEAD;
+	if (likely(old == FILE_REF_ONEREF)) {
+		if (likely(!atomic_long_try_cmpxchg(&ref->refcnt, &old, FILE_REF_DEAD)))
+			return true;
+	}
+	return file_ref_put(ref);
 }
 
 /**
-- 
2.48.1