Merge branch 'locking/rcuref' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pulling rcurefs from Peter for tglx's work.

Link: https://lore.kernel.org/all/[e-mail]/
Signed-off-by: Jakub Kicinski <[e-mail]>

include/linux/atomic/atomic-arch-fallback.h

···
 #define arch_atomic_inc_and_test arch_atomic_inc_and_test
 #endif
 
+#ifndef arch_atomic_add_negative_relaxed
+#ifdef arch_atomic_add_negative
+#define arch_atomic_add_negative_acquire arch_atomic_add_negative
+#define arch_atomic_add_negative_release arch_atomic_add_negative
+#define arch_atomic_add_negative_relaxed arch_atomic_add_negative
+#endif /* arch_atomic_add_negative */
+
 #ifndef arch_atomic_add_negative
 /**
- * arch_atomic_add_negative - add and test if negative
+ * arch_atomic_add_negative - Add and test if negative
  * @i: integer value to add
  * @v: pointer of type atomic_t
  *
- * Atomically adds @i to @v and returns true
- * if the result is negative, or false when
- * result is greater than or equal to zero.
+ * Atomically adds @i to @v and returns true if the result is negative,
+ * or false when the result is greater than or equal to zero.
  */
 static __always_inline bool
 arch_atomic_add_negative(int i, atomic_t *v)
···
 }
 #define arch_atomic_add_negative arch_atomic_add_negative
 #endif
+
+#ifndef arch_atomic_add_negative_acquire
+/**
+ * arch_atomic_add_negative_acquire - Add and test if negative
+ * @i: integer value to add
+ * @v: pointer of type atomic_t
+ *
+ * Atomically adds @i to @v and returns true if the result is negative,
+ * or false when the result is greater than or equal to zero.
+ */
+static __always_inline bool
+arch_atomic_add_negative_acquire(int i, atomic_t *v)
+{
+	return arch_atomic_add_return_acquire(i, v) < 0;
+}
+#define arch_atomic_add_negative_acquire arch_atomic_add_negative_acquire
+#endif
+
+#ifndef arch_atomic_add_negative_release
+/**
+ * arch_atomic_add_negative_release - Add and test if negative
+ * @i: integer value to add
+ * @v: pointer of type atomic_t
+ *
+ * Atomically adds @i to @v and returns true if the result is negative,
+ * or false when the result is greater than or equal to zero.
+ */
+static __always_inline bool
+arch_atomic_add_negative_release(int i, atomic_t *v)
+{
+	return arch_atomic_add_return_release(i, v) < 0;
+}
+#define arch_atomic_add_negative_release arch_atomic_add_negative_release
+#endif
+
+#ifndef arch_atomic_add_negative_relaxed
+/**
+ * arch_atomic_add_negative_relaxed - Add and test if negative
+ * @i: integer value to add
+ * @v: pointer of type atomic_t
+ *
+ * Atomically adds @i to @v and returns true if the result is negative,
+ * or false when the result is greater than or equal to zero.
+ */
+static __always_inline bool
+arch_atomic_add_negative_relaxed(int i, atomic_t *v)
+{
+	return arch_atomic_add_return_relaxed(i, v) < 0;
+}
+#define arch_atomic_add_negative_relaxed arch_atomic_add_negative_relaxed
+#endif
+
+#else /* arch_atomic_add_negative_relaxed */
+
+#ifndef arch_atomic_add_negative_acquire
+static __always_inline bool
+arch_atomic_add_negative_acquire(int i, atomic_t *v)
+{
+	bool ret = arch_atomic_add_negative_relaxed(i, v);
+	__atomic_acquire_fence();
+	return ret;
+}
+#define arch_atomic_add_negative_acquire arch_atomic_add_negative_acquire
+#endif
+
+#ifndef arch_atomic_add_negative_release
+static __always_inline bool
+arch_atomic_add_negative_release(int i, atomic_t *v)
+{
+	__atomic_release_fence();
+	return arch_atomic_add_negative_relaxed(i, v);
+}
+#define arch_atomic_add_negative_release arch_atomic_add_negative_release
+#endif
+
+#ifndef arch_atomic_add_negative
+static __always_inline bool
+arch_atomic_add_negative(int i, atomic_t *v)
+{
+	bool ret;
+	__atomic_pre_full_fence();
+	ret = arch_atomic_add_negative_relaxed(i, v);
+	__atomic_post_full_fence();
+	return ret;
+}
+#define arch_atomic_add_negative arch_atomic_add_negative
+#endif
+
+#endif /* arch_atomic_add_negative_relaxed */
 
 #ifndef arch_atomic_fetch_add_unless
 /**
···
 #define arch_atomic64_inc_and_test arch_atomic64_inc_and_test
 #endif
 
+#ifndef arch_atomic64_add_negative_relaxed
+#ifdef arch_atomic64_add_negative
+#define arch_atomic64_add_negative_acquire arch_atomic64_add_negative
+#define arch_atomic64_add_negative_release arch_atomic64_add_negative
+#define arch_atomic64_add_negative_relaxed arch_atomic64_add_negative
+#endif /* arch_atomic64_add_negative */
+
 #ifndef arch_atomic64_add_negative
 /**
- * arch_atomic64_add_negative - add and test if negative
+ * arch_atomic64_add_negative - Add and test if negative
  * @i: integer value to add
  * @v: pointer of type atomic64_t
  *
- * Atomically adds @i to @v and returns true
- * if the result is negative, or false when
- * result is greater than or equal to zero.
+ * Atomically adds @i to @v and returns true if the result is negative,
+ * or false when the result is greater than or equal to zero.
  */
 static __always_inline bool
 arch_atomic64_add_negative(s64 i, atomic64_t *v)
···
 }
 #define arch_atomic64_add_negative arch_atomic64_add_negative
 #endif
+
+#ifndef arch_atomic64_add_negative_acquire
+/**
+ * arch_atomic64_add_negative_acquire - Add and test if negative
+ * @i: integer value to add
+ * @v: pointer of type atomic64_t
+ *
+ * Atomically adds @i to @v and returns true if the result is negative,
+ * or false when the result is greater than or equal to zero.
+ */
+static __always_inline bool
+arch_atomic64_add_negative_acquire(s64 i, atomic64_t *v)
+{
+	return arch_atomic64_add_return_acquire(i, v) < 0;
+}
+#define arch_atomic64_add_negative_acquire arch_atomic64_add_negative_acquire
+#endif
+
+#ifndef arch_atomic64_add_negative_release
+/**
+ * arch_atomic64_add_negative_release - Add and test if negative
+ * @i: integer value to add
+ * @v: pointer of type atomic64_t
+ *
+ * Atomically adds @i to @v and returns true if the result is negative,
+ * or false when the result is greater than or equal to zero.
+ */
+static __always_inline bool
+arch_atomic64_add_negative_release(s64 i, atomic64_t *v)
+{
+	return arch_atomic64_add_return_release(i, v) < 0;
+}
+#define arch_atomic64_add_negative_release arch_atomic64_add_negative_release
+#endif
+
+#ifndef arch_atomic64_add_negative_relaxed
+/**
+ * arch_atomic64_add_negative_relaxed - Add and test if negative
+ * @i: integer value to add
+ * @v: pointer of type atomic64_t
+ *
+ * Atomically adds @i to @v and returns true if the result is negative,
+ * or false when the result is greater than or equal to zero.
+ */
+static __always_inline bool
+arch_atomic64_add_negative_relaxed(s64 i, atomic64_t *v)
+{
+	return arch_atomic64_add_return_relaxed(i, v) < 0;
+}
+#define arch_atomic64_add_negative_relaxed arch_atomic64_add_negative_relaxed
+#endif
+
+#else /* arch_atomic64_add_negative_relaxed */
+
+#ifndef arch_atomic64_add_negative_acquire
+static __always_inline bool
+arch_atomic64_add_negative_acquire(s64 i, atomic64_t *v)
+{
+	bool ret = arch_atomic64_add_negative_relaxed(i, v);
+	__atomic_acquire_fence();
+	return ret;
+}
+#define arch_atomic64_add_negative_acquire arch_atomic64_add_negative_acquire
+#endif
+
+#ifndef arch_atomic64_add_negative_release
+static __always_inline bool
+arch_atomic64_add_negative_release(s64 i, atomic64_t *v)
+{
+	__atomic_release_fence();
+	return arch_atomic64_add_negative_relaxed(i, v);
+}
+#define arch_atomic64_add_negative_release arch_atomic64_add_negative_release
+#endif
+
+#ifndef arch_atomic64_add_negative
+static __always_inline bool
+arch_atomic64_add_negative(s64 i, atomic64_t *v)
+{
+	bool ret;
+	__atomic_pre_full_fence();
+	ret = arch_atomic64_add_negative_relaxed(i, v);
+	__atomic_post_full_fence();
+	return ret;
+}
+#define arch_atomic64_add_negative arch_atomic64_add_negative
+#endif
+
+#endif /* arch_atomic64_add_negative_relaxed */
 
 #ifndef arch_atomic64_fetch_add_unless
 /**
···
 #endif
 
 #endif /* _LINUX_ATOMIC_FALLBACK_H */
-// b5e87bdd5ede61470c29f7a7e4de781af3770f09
+// 00071fffa021cec66f6290d706d69c91df87bade

include/linux/atomic/atomic-instrumented.h

···
 	return arch_atomic_add_negative(i, v);
 }
 
+static __always_inline bool
+atomic_add_negative_acquire(int i, atomic_t *v)
+{
+	instrument_atomic_read_write(v, sizeof(*v));
+	return arch_atomic_add_negative_acquire(i, v);
+}
+
+static __always_inline bool
+atomic_add_negative_release(int i, atomic_t *v)
+{
+	kcsan_release();
+	instrument_atomic_read_write(v, sizeof(*v));
+	return arch_atomic_add_negative_release(i, v);
+}
+
+static __always_inline bool
+atomic_add_negative_relaxed(int i, atomic_t *v)
+{
+	instrument_atomic_read_write(v, sizeof(*v));
+	return arch_atomic_add_negative_relaxed(i, v);
+}
+
 static __always_inline int
 atomic_fetch_add_unless(atomic_t *v, int a, int u)
 {
···
 	kcsan_mb();
 	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic64_add_negative(i, v);
+}
+
+static __always_inline bool
+atomic64_add_negative_acquire(s64 i, atomic64_t *v)
+{
+	instrument_atomic_read_write(v, sizeof(*v));
+	return arch_atomic64_add_negative_acquire(i, v);
+}
+
+static __always_inline bool
+atomic64_add_negative_release(s64 i, atomic64_t *v)
+{
+	kcsan_release();
+	instrument_atomic_read_write(v, sizeof(*v));
+	return arch_atomic64_add_negative_release(i, v);
+}
+
+static __always_inline bool
+atomic64_add_negative_relaxed(s64 i, atomic64_t *v)
+{
+	instrument_atomic_read_write(v, sizeof(*v));
+	return arch_atomic64_add_negative_relaxed(i, v);
 }
 
 static __always_inline s64
···
 	return arch_atomic_long_add_negative(i, v);
 }
 
+static __always_inline bool
+atomic_long_add_negative_acquire(long i, atomic_long_t *v)
+{
+	instrument_atomic_read_write(v, sizeof(*v));
+	return arch_atomic_long_add_negative_acquire(i, v);
+}
+
+static __always_inline bool
+atomic_long_add_negative_release(long i, atomic_long_t *v)
+{
+	kcsan_release();
+	instrument_atomic_read_write(v, sizeof(*v));
+	return arch_atomic_long_add_negative_release(i, v);
+}
+
+static __always_inline bool
+atomic_long_add_negative_relaxed(long i, atomic_long_t *v)
+{
+	instrument_atomic_read_write(v, sizeof(*v));
+	return arch_atomic_long_add_negative_relaxed(i, v);
+}
+
 static __always_inline long
 atomic_long_fetch_add_unless(atomic_long_t *v, long a, long u)
 {
···
 })
 
 #endif /* _LINUX_ATOMIC_INSTRUMENTED_H */
-// 764f741eb77a7ad565dc8d99ce2837d5542e8aee
+// 1b485de9cbaa4900de59e14ee2084357eaeb1c3a

include/linux/atomic/atomic-long.h

···
 	return arch_atomic64_add_negative(i, v);
 }
 
+static __always_inline bool
+arch_atomic_long_add_negative_acquire(long i, atomic_long_t *v)
+{
+	return arch_atomic64_add_negative_acquire(i, v);
+}
+
+static __always_inline bool
+arch_atomic_long_add_negative_release(long i, atomic_long_t *v)
+{
+	return arch_atomic64_add_negative_release(i, v);
+}
+
+static __always_inline bool
+arch_atomic_long_add_negative_relaxed(long i, atomic_long_t *v)
+{
+	return arch_atomic64_add_negative_relaxed(i, v);
+}
+
 static __always_inline long
 arch_atomic_long_fetch_add_unless(atomic_long_t *v, long a, long u)
 {
···
 	return arch_atomic_add_negative(i, v);
 }
 
+static __always_inline bool
+arch_atomic_long_add_negative_acquire(long i, atomic_long_t *v)
+{
+	return arch_atomic_add_negative_acquire(i, v);
+}
+
+static __always_inline bool
+arch_atomic_long_add_negative_release(long i, atomic_long_t *v)
+{
+	return arch_atomic_add_negative_release(i, v);
+}
+
+static __always_inline bool
+arch_atomic_long_add_negative_relaxed(long i, atomic_long_t *v)
+{
+	return arch_atomic_add_negative_relaxed(i, v);
+}
+
 static __always_inline long
 arch_atomic_long_fetch_add_unless(atomic_long_t *v, long a, long u)
 {
···
 
 #endif /* CONFIG_64BIT */
 #endif /* _LINUX_ATOMIC_LONG_H */
-// e8f0e08ff072b74d180eabe2ad001282b38c2c88
+// a194c07d7d2f4b0e178d3c118c919775d5d65f50

include/linux/rcuref.h

···
+/* SPDX-License-Identifier: GPL-2.0-only */
+#ifndef _LINUX_RCUREF_H
+#define _LINUX_RCUREF_H
+
+#include <linux/atomic.h>
+#include <linux/bug.h>
+#include <linux/limits.h>
+#include <linux/lockdep.h>
+#include <linux/preempt.h>
+#include <linux/rcupdate.h>
+
+#define RCUREF_ONEREF		0x00000000U
+#define RCUREF_MAXREF		0x7FFFFFFFU
+#define RCUREF_SATURATED	0xA0000000U
+#define RCUREF_RELEASED		0xC0000000U
+#define RCUREF_DEAD		0xE0000000U
+#define RCUREF_NOREF		0xFFFFFFFFU
+
+/**
+ * rcuref_init - Initialize a rcuref reference count with the given reference count
+ * @ref:	Pointer to the reference count
+ * @cnt:	The initial reference count typically '1'
+ */
+static inline void rcuref_init(rcuref_t *ref, unsigned int cnt)
+{
+	atomic_set(&ref->refcnt, cnt - 1);
+}
+
+/**
+ * rcuref_read - Read the number of held reference counts of a rcuref
+ * @ref:	Pointer to the reference count
+ *
+ * Return: The number of held references (0 ... N)
+ */
+static inline unsigned int rcuref_read(rcuref_t *ref)
+{
+	unsigned int c = atomic_read(&ref->refcnt);
+
+	/* Return 0 if within the DEAD zone. */
+	return c >= RCUREF_RELEASED ? 0 : c + 1;
+}
+
+extern __must_check bool rcuref_get_slowpath(rcuref_t *ref);
+
+/**
+ * rcuref_get - Acquire one reference on a rcuref reference count
+ * @ref:	Pointer to the reference count
+ *
+ * Similar to atomic_inc_not_zero() but saturates at RCUREF_MAXREF.
+ *
+ * Provides no memory ordering, it is assumed the caller has guaranteed the
+ * object memory to be stable (RCU, etc.). It does provide a control dependency
+ * and thereby orders future stores. See documentation in lib/rcuref.c
+ *
+ * Return:
+ *	False if the attempt to acquire a reference failed. This happens
+ *	when the last reference has been put already
+ *
+ *	True if a reference was successfully acquired
+ */
+static inline __must_check bool rcuref_get(rcuref_t *ref)
+{
+	/*
+	 * Unconditionally increase the reference count. The saturation and
+	 * dead zones provide enough tolerance for this.
+	 */
+	if (likely(!atomic_add_negative_relaxed(1, &ref->refcnt)))
+		return true;
+
+	/* Handle the cases inside the saturation and dead zones */
+	return rcuref_get_slowpath(ref);
+}
+
+extern __must_check bool rcuref_put_slowpath(rcuref_t *ref);
+
+/*
+ * Internal helper. Do not invoke directly.
+ */
+static __always_inline __must_check bool __rcuref_put(rcuref_t *ref)
+{
+	RCU_LOCKDEP_WARN(!rcu_read_lock_held() && preemptible(),
+			 "suspicious rcuref_put_rcusafe() usage");
+	/*
+	 * Unconditionally decrease the reference count. The saturation and
+	 * dead zones provide enough tolerance for this.
+	 */
+	if (likely(!atomic_add_negative_release(-1, &ref->refcnt)))
+		return false;
+
+	/*
+	 * Handle the last reference drop and cases inside the saturation
+	 * and dead zones.
+	 */
+	return rcuref_put_slowpath(ref);
+}
+
+/**
+ * rcuref_put_rcusafe -- Release one reference for a rcuref reference count RCU safe
+ * @ref:	Pointer to the reference count
+ *
+ * Provides release memory ordering, such that prior loads and stores are done
+ * before, and provides an acquire ordering on success such that free()
+ * must come after.
+ *
+ * Can be invoked from contexts, which guarantee that no grace period can
+ * happen which would free the object concurrently if the decrement drops
+ * the last reference and the slowpath races against a concurrent get() and
+ * put() pair. rcu_read_lock()'ed and atomic contexts qualify.
+ *
+ * Return:
+ *	True if this was the last reference with no future references
+ *	possible. This signals the caller that it can safely release the
+ *	object which is protected by the reference counter.
+ *
+ *	False if there are still active references or the put() raced
+ *	with a concurrent get()/put() pair. Caller is not allowed to
+ *	release the protected object.
+ */
+static inline __must_check bool rcuref_put_rcusafe(rcuref_t *ref)
+{
+	return __rcuref_put(ref);
+}
+
+/**
+ * rcuref_put -- Release one reference for a rcuref reference count
+ * @ref:	Pointer to the reference count
+ *
+ * Can be invoked from any context.
+ *
+ * Provides release memory ordering, such that prior loads and stores are done
+ * before, and provides an acquire ordering on success such that free()
+ * must come after.
+ *
+ * Return:
+ *
+ *	True if this was the last reference with no future references
+ *	possible. This signals the caller that it can safely schedule the
+ *	object, which is protected by the reference counter, for
+ *	deconstruction.
+ *
+ *	False if there are still active references or the put() raced
+ *	with a concurrent get()/put() pair. Caller is not allowed to
+ *	deconstruct the protected object.
+ */
+static inline __must_check bool rcuref_put(rcuref_t *ref)
+{
+	bool released;
+
+	preempt_disable();
+	released = __rcuref_put(ref);
+	preempt_enable();
+	return released;
+}
+
+#endif

include/linux/types.h

···
 } atomic64_t;
 #endif
 
+typedef struct {
+	atomic_t refcnt;
+} rcuref_t;
+
+#define RCUREF_INIT(i)	{ .refcnt = ATOMIC_INIT(i - 1) }
+
 struct list_head {
 	struct list_head *next, *prev;
 };

lib/Makefile

···
 	 list_sort.o uuid.o iov_iter.o clz_ctz.o \
 	 bsearch.o find_bit.o llist.o memweight.o kfifo.o \
 	 percpu-refcount.o rhashtable.o base64.o \
-	 once.o refcount.o usercopy.o errseq.o bucket_locks.o \
+	 once.o refcount.o rcuref.o usercopy.o errseq.o bucket_locks.o \
 	 generic-radix-tree.o
 obj-$(CONFIG_STRING_SELFTEST) += test_string.o
 obj-y += string_helpers.o

lib/rcuref.c

···
+// SPDX-License-Identifier: GPL-2.0-only
+
+/*
+ * rcuref - A scalable reference count implementation for RCU managed objects
+ *
+ * rcuref is provided to replace open coded reference count implementations
+ * based on atomic_t. It protects explicitely RCU managed objects which can
+ * be visible even after the last reference has been dropped and the object
+ * is heading towards destruction.
+ *
+ * A common usage pattern is:
+ *
+ * get()
+ *	rcu_read_lock();
+ *	p = get_ptr();
+ *	if (p && !atomic_inc_not_zero(&p->refcnt))
+ *		p = NULL;
+ *	rcu_read_unlock();
+ *	return p;
+ *
+ * put()
+ *	if (!atomic_dec_return(&->refcnt)) {
+ *		remove_ptr(p);
+ *		kfree_rcu((p, rcu);
+ *	}
+ *
+ * atomic_inc_not_zero() is implemented with a try_cmpxchg() loop which has
+ * O(N^2) behaviour under contention with N concurrent operations.
+ *
+ * rcuref uses atomic_add_negative_relaxed() for the fast path, which scales
+ * better under contention.
+ *
+ * Why not refcount?
+ * =================
+ *
+ * In principle it should be possible to make refcount use the rcuref
+ * scheme, but the destruction race described below cannot be prevented
+ * unless the protected object is RCU managed.
+ *
+ * Theory of operation
+ * ===================
+ *
+ * rcuref uses an unsigned integer reference counter. As long as the
+ * counter value is greater than or equal to RCUREF_ONEREF and not larger
+ * than RCUREF_MAXREF the reference is alive:
+ *
+ * ONEREF   MAXREF               SATURATED             RELEASED      DEAD    NOREF
+ * 0        0x7FFFFFFF 0x8000000 0xA0000000 0xBFFFFFFF 0xC0000000 0xE0000000 0xFFFFFFFF
+ * <---valid --------> <-------saturation zone-------> <-----dead zone----->
+ *
+ * The get() and put() operations do unconditional increments and
+ * decrements. The result is checked after the operation. This optimizes
+ * for the fast path.
+ *
+ * If the reference count is saturated or dead, then the increments and
+ * decrements are not harmful as the reference count still stays in the
+ * respective zones and is always set back to STATURATED resp. DEAD. The
+ * zones have room for 2^28 racing operations in each direction, which
+ * makes it practically impossible to escape the zones.
+ *
+ * Once the last reference is dropped the reference count becomes
+ * RCUREF_NOREF which forces rcuref_put() into the slowpath operation. The
+ * slowpath then tries to set the reference count from RCUREF_NOREF to
+ * RCUREF_DEAD via a cmpxchg(). This opens a small window where a
+ * concurrent rcuref_get() can acquire the reference count and bring it
+ * back to RCUREF_ONEREF or even drop the reference again and mark it DEAD.
+ *
+ * If the cmpxchg() succeeds then a concurrent rcuref_get() will result in
+ * DEAD + 1, which is inside the dead zone. If that happens the reference
+ * count is put back to DEAD.
+ *
+ * The actual race is possible due to the unconditional increment and
+ * decrements in rcuref_get() and rcuref_put():
+ *
+ *	T1				T2
+ *	get()				put()
+ *					if (atomic_add_negative(-1, &ref->refcnt))
+ *		succeeds->			atomic_cmpxchg(&ref->refcnt, NOREF, DEAD);
+ *
+ *	atomic_add_negative(1, &ref->refcnt);	<- Elevates refcount to DEAD + 1
+ *
+ * As the result of T1's add is negative, the get() goes into the slow path
+ * and observes refcnt being in the dead zone which makes the operation fail.
+ *
+ * Possible critical states:
+ *
+ *	Context Counter	References	Operation
+ *	T1	0	1		init()
+ *	T2	1	2		get()
+ *	T1	0	1		put()
+ *	T2     -1	0		put() tries to mark dead
+ *	T1	0	1		get()
+ *	T2	0	1		put() mark dead fails
+ *	T1     -1	0		put() tries to mark dead
+ *	T1    DEAD	0		put() mark dead succeeds
+ *	T2    DEAD+1	0		get() fails and puts it back to DEAD
+ *
+ * Of course there are more complex scenarios, but the above illustrates
+ * the working principle. The rest is left to the imagination of the
+ * reader.
+ *
+ * Deconstruction race
+ * ===================
+ *
+ * The release operation must be protected by prohibiting a grace period in
+ * order to prevent a possible use after free:
+ *
+ *	T1				T2
+ *	put()				get()
+ *	// ref->refcnt = ONEREF
+ *	if (!atomic_add_negative(-1, &ref->refcnt))
+ *		return false;				<- Not taken
+ *
+ *	// ref->refcnt == NOREF
+ *	--> preemption
+ *					// Elevates ref->refcnt to ONEREF
+ *					if (!atomic_add_negative(1, &ref->refcnt))
+ *						return true;			<- taken
+ *
+ *					if (put(&p->ref)) { <-- Succeeds
+ *						remove_pointer(p);
+ *						kfree_rcu(p, rcu);
+ *					}
+ *
+ *		RCU grace period ends, object is freed
+ *
+ *	atomic_cmpxchg(&ref->refcnt, NOREF, DEAD);	<- UAF
+ *
+ * This is prevented by disabling preemption around the put() operation as
+ * that's in most kernel configurations cheaper than a rcu_read_lock() /
+ * rcu_read_unlock() pair and in many cases even a NOOP. In any case it
+ * prevents the grace period which keeps the object alive until all put()
+ * operations complete.
+ *
+ * Saturation protection
+ * =====================
+ *
+ * The reference count has a saturation limit RCUREF_MAXREF (INT_MAX).
+ * Once this is exceedded the reference count becomes stale by setting it
+ * to RCUREF_SATURATED, which will cause a memory leak, but it prevents
+ * wrap arounds which obviously cause worse problems than a memory
+ * leak. When saturation is reached a warning is emitted.
+ *
+ * Race conditions
+ * ===============
+ *
+ * All reference count increment/decrement operations are unconditional and
+ * only verified after the fact. This optimizes for the good case and takes
+ * the occasional race vs. a dead or already saturated refcount into
+ * account. The saturation and dead zones are large enough to accomodate
+ * for that.
+ *
+ * Memory ordering
+ * ===============
+ *
+ * Memory ordering rules are slightly relaxed wrt regular atomic_t functions
+ * and provide only what is strictly required for refcounts.
+ *
+ * The increments are fully relaxed; these will not provide ordering. The
+ * rationale is that whatever is used to obtain the object to increase the
+ * reference count on will provide the ordering. For locked data
+ * structures, its the lock acquire, for RCU/lockless data structures its
+ * the dependent load.
+ *
+ * rcuref_get() provides a control dependency ordering future stores which
+ * ensures that the object is not modified when acquiring a reference
+ * fails.
+ *
+ * rcuref_put() provides release order, i.e. all prior loads and stores
+ * will be issued before. It also provides a control dependency ordering
+ * against the subsequent destruction of the object.
+ *
+ * If rcuref_put() successfully dropped the last reference and marked the
+ * object DEAD it also provides acquire ordering.
+ */
+
+#include <linux/export.h>
+#include <linux/rcuref.h>
+
+/**
+ * rcuref_get_slowpath - Slowpath of rcuref_get()
+ * @ref:	Pointer to the reference count
+ *
+ * Invoked when the reference count is outside of the valid zone.
+ *
+ * Return:
+ *	False if the reference count was already marked dead
+ *
+ *	True if the reference count is saturated, which prevents the
+ *	object from being deconstructed ever.
+ */
+bool rcuref_get_slowpath(rcuref_t *ref)
+{
+	unsigned int cnt = atomic_read(&ref->refcnt);
+
+	/*
+	 * If the reference count was already marked dead, undo the
+	 * increment so it stays in the middle of the dead zone and return
+	 * fail.
+	 */
+	if (cnt >= RCUREF_RELEASED) {
+		atomic_set(&ref->refcnt, RCUREF_DEAD);
+		return false;
+	}
+
+	/*
+	 * If it was saturated, warn and mark it so. In case the increment
+	 * was already on a saturated value restore the saturation
+	 * marker. This keeps it in the middle of the saturation zone and
+	 * prevents the reference count from overflowing. This leaks the
+	 * object memory, but prevents the obvious reference count overflow
+	 * damage.
+	 */
+	if (WARN_ONCE(cnt > RCUREF_MAXREF, "rcuref saturated - leaking memory"))
+		atomic_set(&ref->refcnt, RCUREF_SATURATED);
+	return true;
+}
+EXPORT_SYMBOL_GPL(rcuref_get_slowpath);
+
+/**
+ * rcuref_put_slowpath - Slowpath of __rcuref_put()
+ * @ref:	Pointer to the reference count
+ *
+ * Invoked when the reference count is outside of the valid zone.
+ *
+ * Return:
+ *	True if this was the last reference with no future references
+ *	possible. This signals the caller that it can safely schedule the
+ *	object, which is protected by the reference counter, for
+ *	deconstruction.
+ *
+ *	False if there are still active references or the put() raced
+ *	with a concurrent get()/put() pair. Caller is not allowed to
+ *	deconstruct the protected object.
+ */
+bool rcuref_put_slowpath(rcuref_t *ref)
+{
+	unsigned int cnt = atomic_read(&ref->refcnt);
+
+	/* Did this drop the last reference? */
+	if (likely(cnt == RCUREF_NOREF)) {
+		/*
+		 * Carefully try to set the reference count to RCUREF_DEAD.
+		 *
+		 * This can fail if a concurrent get() operation has
+		 * elevated it again or the corresponding put() even marked
+		 * it dead already. Both are valid situations and do not
+		 * require a retry. If this fails the caller is not
+		 * allowed to deconstruct the object.
+		 */
+		if (atomic_cmpxchg_release(&ref->refcnt, RCUREF_NOREF, RCUREF_DEAD) != RCUREF_NOREF)
+			return false;
+
+		/*
+		 * The caller can safely schedule the object for
+		 * deconstruction. Provide acquire ordering.
+		 */
+		smp_acquire__after_ctrl_dep();
+		return true;
+	}
+
+	/*
+	 * If the reference count was already in the dead zone, then this
+	 * put() operation is imbalanced. Warn, put the reference count back to
+	 * DEAD and tell the caller to not deconstruct the object.
+	 */
+	if (WARN_ONCE(cnt >= RCUREF_RELEASED, "rcuref - imbalanced put()")) {
+		atomic_set(&ref->refcnt, RCUREF_DEAD);
+		return false;
+	}
+
+	/*
+	 * This is a put() operation on a saturated refcount. Restore the
+	 * mean saturation value and tell the caller to not deconstruct the
+	 * object.
+	 */
+	if (cnt > RCUREF_MAXREF)
+		atomic_set(&ref->refcnt, RCUREF_SATURATED);
+	return false;
+}
+EXPORT_SYMBOL_GPL(rcuref_put_slowpath);

scripts/atomic/atomics.tbl

···
 sub_and_test		b	i	v
 dec_and_test		b	v
 inc_and_test		b	v
-add_negative		b	i	v
+add_negative		B	i	v
 add_unless		fb	v	i:a	i:u
 inc_not_zero		b	v
 inc_unless_negative	b	v

scripts/atomic/fallbacks/add_negative

···
 cat <<EOF
 /**
- * arch_${atomic}_add_negative - add and test if negative
+ * arch_${atomic}_add_negative${order} - Add and test if negative
  * @i: integer value to add
  * @v: pointer of type ${atomic}_t
  *
- * Atomically adds @i to @v and returns true
- * if the result is negative, or false when
- * result is greater than or equal to zero.
+ * Atomically adds @i to @v and returns true if the result is negative,
+ * or false when the result is greater than or equal to zero.
  */
 static __always_inline bool
-arch_${atomic}_add_negative(${int} i, ${atomic}_t *v)
+arch_${atomic}_add_negative${order}(${int} i, ${atomic}_t *v)
 {
-	return arch_${atomic}_add_return(i, v) < 0;
+	return arch_${atomic}_add_return${order}(i, v) < 0;
 }
 EOF