locking/refcount: Move the bulk of the REFCOUNT_FULL implementation into the <linux/refcount.h> header

In an effort to improve performance of the REFCOUNT_FULL implementation,
move the bulk of its functions into linux/refcount.h. This allows them
to be inlined in the same way as if they had been provided via
CONFIG_ARCH_HAS_REFCOUNT.

Signed-off-by: Will Deacon <[email protected]>
Reviewed-by: Ard Biesheuvel <[email protected]>
Reviewed-by: Kees Cook <[email protected]>
Tested-by: Hanjun Guo <[email protected]>
Cc: Ard Biesheuvel <[email protected]>
Cc: Elena Reshetova <[email protected]>
Cc: Linus Torvalds <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Thomas Gleixner <[email protected]>
Link: https://lkml.kernel.org/r/[email protected]
Signed-off-by: Ingo Molnar <[email protected]>

Author: willdeacon

include/linux/refcount.h

@@ -45,22 +45,241 @@ static inline unsigned int refcount_read(const refcount_t *r)
 }
 
 #ifdef CONFIG_REFCOUNT_FULL
+#include <linux/bug.h>
 
 #define REFCOUNT_MAX		(UINT_MAX - 1)
 #define REFCOUNT_SATURATED	UINT_MAX
 
-extern __must_check bool refcount_add_not_zero(int i, refcount_t *r);
-extern void refcount_add(int i, refcount_t *r);
+/*
+ * Variant of atomic_t specialized for reference counts.
+ *
+ * The interface matches the atomic_t interface (to aid in porting) but only
+ * provides the few functions one should use for reference counting.
+ *
+ * It differs in that the counter saturates at REFCOUNT_SATURATED and will not
+ * move once there. This avoids wrapping the counter and causing 'spurious'
+ * use-after-free issues.
+ *
+ * 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 we're increasing 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.
+ *
+ * Do note that inc_not_zero() provides a control dependency which will order
+ * future stores against the inc, this ensures we'll never modify the object
+ * if we did not in fact acquire a reference.
+ *
+ * The decrements will provide release order, such that all the prior loads and
+ * stores will be issued before, it also provides a control dependency, which
+ * will order us against the subsequent free().
+ *
+ * The control dependency is against the load of the cmpxchg (ll/sc) that
+ * succeeded. This means the stores aren't fully ordered, but this is fine
+ * because the 1->0 transition indicates no concurrency.
+ *
+ * Note that the allocator is responsible for ordering things between free()
+ * and alloc().
+ *
+ * The decrements dec_and_test() and sub_and_test() also provide acquire
+ * ordering on success.
+ *
+ */
+
+/**
+ * refcount_add_not_zero - add a value to a refcount unless it is 0
+ * @i: the value to add to the refcount
+ * @r: the refcount
+ *
+ * Will saturate at REFCOUNT_SATURATED and WARN.
+ *
+ * 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 the comment on top.
+ *
+ * Use of this function is not recommended for the normal reference counting
+ * use case in which references are taken and released one at a time.  In these
+ * cases, refcount_inc(), or one of its variants, should instead be used to
+ * increment a reference count.
+ *
+ * Return: false if the passed refcount is 0, true otherwise
+ */
+static inline __must_check bool refcount_add_not_zero(int i, refcount_t *r)
+{
+	unsigned int new, val = atomic_read(&r->refs);
+
+	do {
+		if (!val)
+			return false;
+
+		if (unlikely(val == REFCOUNT_SATURATED))
+			return true;
+
+		new = val + i;
+		if (new < val)
+			new = REFCOUNT_SATURATED;
+
+	} while (!atomic_try_cmpxchg_relaxed(&r->refs, &val, new));
+
+	WARN_ONCE(new == REFCOUNT_SATURATED,
+		  "refcount_t: saturated; leaking memory.\n");
+
+	return true;
+}
+
+/**
+ * refcount_add - add a value to a refcount
+ * @i: the value to add to the refcount
+ * @r: the refcount
+ *
+ * Similar to atomic_add(), but will saturate at REFCOUNT_SATURATED and WARN.
+ *
+ * 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 the comment on top.
+ *
+ * Use of this function is not recommended for the normal reference counting
+ * use case in which references are taken and released one at a time.  In these
+ * cases, refcount_inc(), or one of its variants, should instead be used to
+ * increment a reference count.
+ */
+static inline void refcount_add(int i, refcount_t *r)
+{
+	WARN_ONCE(!refcount_add_not_zero(i, r), "refcount_t: addition on 0; use-after-free.\n");
+}
+
+/**
+ * refcount_inc_not_zero - increment a refcount unless it is 0
+ * @r: the refcount to increment
+ *
+ * Similar to atomic_inc_not_zero(), but will saturate at REFCOUNT_SATURATED
+ * and WARN.
+ *
+ * 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 the comment on top.
+ *
+ * Return: true if the increment was successful, false otherwise
+ */
+static inline __must_check bool refcount_inc_not_zero(refcount_t *r)
+{
+	unsigned int new, val = atomic_read(&r->refs);
+
+	do {
+		new = val + 1;
 
-extern __must_check bool refcount_inc_not_zero(refcount_t *r);
-extern void refcount_inc(refcount_t *r);
+		if (!val)
+			return false;
 
-extern __must_check bool refcount_sub_and_test(int i, refcount_t *r);
+		if (unlikely(!new))
+			return true;
 
-extern __must_check bool refcount_dec_and_test(refcount_t *r);
-extern void refcount_dec(refcount_t *r);
+	} while (!atomic_try_cmpxchg_relaxed(&r->refs, &val, new));
+
+	WARN_ONCE(new == REFCOUNT_SATURATED,
+		  "refcount_t: saturated; leaking memory.\n");
+
+	return true;
+}
+
+/**
+ * refcount_inc - increment a refcount
+ * @r: the refcount to increment
+ *
+ * Similar to atomic_inc(), but will saturate at REFCOUNT_SATURATED and WARN.
+ *
+ * Provides no memory ordering, it is assumed the caller already has a
+ * reference on the object.
+ *
+ * Will WARN if the refcount is 0, as this represents a possible use-after-free
+ * condition.
+ */
+static inline void refcount_inc(refcount_t *r)
+{
+	WARN_ONCE(!refcount_inc_not_zero(r), "refcount_t: increment on 0; use-after-free.\n");
+}
+
+/**
+ * refcount_sub_and_test - subtract from a refcount and test if it is 0
+ * @i: amount to subtract from the refcount
+ * @r: the refcount
+ *
+ * Similar to atomic_dec_and_test(), but it will WARN, return false and
+ * ultimately leak on underflow and will fail to decrement when saturated
+ * at REFCOUNT_SATURATED.
+ *
+ * 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.
+ *
+ * Use of this function is not recommended for the normal reference counting
+ * use case in which references are taken and released one at a time.  In these
+ * cases, refcount_dec(), or one of its variants, should instead be used to
+ * decrement a reference count.
+ *
+ * Return: true if the resulting refcount is 0, false otherwise
+ */
+static inline __must_check bool refcount_sub_and_test(int i, refcount_t *r)
+{
+	unsigned int new, val = atomic_read(&r->refs);
+
+	do {
+		if (unlikely(val == REFCOUNT_SATURATED))
+			return false;
+
+		new = val - i;
+		if (new > val) {
+			WARN_ONCE(new > val, "refcount_t: underflow; use-after-free.\n");
+			return false;
+		}
+
+	} while (!atomic_try_cmpxchg_release(&r->refs, &val, new));
+
+	if (!new) {
+		smp_acquire__after_ctrl_dep();
+		return true;
+	}
+	return false;
+
+}
+
+/**
+ * refcount_dec_and_test - decrement a refcount and test if it is 0
+ * @r: the refcount
+ *
+ * Similar to atomic_dec_and_test(), it will WARN on underflow and fail to
+ * decrement when saturated at REFCOUNT_SATURATED.
+ *
+ * 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 the resulting refcount is 0, false otherwise
+ */
+static inline __must_check bool refcount_dec_and_test(refcount_t *r)
+{
+	return refcount_sub_and_test(1, r);
+}
+
+/**
+ * refcount_dec - decrement a refcount
+ * @r: the refcount
+ *
+ * Similar to atomic_dec(), it will WARN on underflow and fail to decrement
+ * when saturated at REFCOUNT_SATURATED.
+ *
+ * Provides release memory ordering, such that prior loads and stores are done
+ * before.
+ */
+static inline void refcount_dec(refcount_t *r)
+{
+	WARN_ONCE(refcount_dec_and_test(r), "refcount_t: decrement hit 0; leaking memory.\n");
+}
 
-#else
+#else /* CONFIG_REFCOUNT_FULL */
 
 #define REFCOUNT_MAX		INT_MAX
 #define REFCOUNT_SATURATED	(INT_MIN / 2)
@@ -103,7 +322,7 @@ static inline void refcount_dec(refcount_t *r)
 	atomic_dec(&r->refs);
 }
 # endif /* !CONFIG_ARCH_HAS_REFCOUNT */
-#endif /* CONFIG_REFCOUNT_FULL */
+#endif /* !CONFIG_REFCOUNT_FULL */
 
 extern __must_check bool refcount_dec_if_one(refcount_t *r);
 extern __must_check bool refcount_dec_not_one(refcount_t *r);