rqspinlock: Add a test-and-set fallback

Include a test-and-set fallback when queued spinlock support is not
available. Introduce a rqspinlock type to act as a fallback when
qspinlock support is absent.

Include ifdef guards to ensure the slow path in this file is only
compiled when CONFIG_QUEUED_SPINLOCKS=y. Subsequent patches will add
further logic to ensure fallback to the test-and-set implementation
when queued spinlock support is unavailable on an architecture.

Unlike other waiting loops in rqspinlock code, the one for test-and-set
has no theoretical upper bound under contention, therefore we need a
longer timeout than usual. Bump it up to a second in this case.

Signed-off-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Link: https://lore.kernel.org/r/20250316040541.108729-14-memxor@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

Author: kkdwivedi

include/asm-generic/rqspinlock.h

@@ -12,11 +12,28 @@
 #include <linux/types.h>
 #include <vdso/time64.h>
 #include <linux/percpu.h>
+#ifdef CONFIG_QUEUED_SPINLOCKS
+#include <asm/qspinlock.h>
+#endif
+
+struct rqspinlock {
+	union {
+		atomic_t val;
+		u32 locked;
+	};
+};
 
 struct qspinlock;
+#ifdef CONFIG_QUEUED_SPINLOCKS
 typedef struct qspinlock rqspinlock_t;
+#else
+typedef struct rqspinlock rqspinlock_t;
+#endif
 
+extern int resilient_tas_spin_lock(rqspinlock_t *lock);
+#ifdef CONFIG_QUEUED_SPINLOCKS
 extern int resilient_queued_spin_lock_slowpath(rqspinlock_t *lock, u32 val);
+#endif
 
 /*
  * Default timeout for waiting loops is 0.25 seconds

kernel/bpf/rqspinlock.c

@@ -21,17 +21,22 @@
 #include <linux/mutex.h>
 #include <linux/prefetch.h>
 #include <asm/byteorder.h>
+#ifdef CONFIG_QUEUED_SPINLOCKS
 #include <asm/qspinlock.h>
+#endif
 #include <trace/events/lock.h>
 #include <asm/rqspinlock.h>
 #include <linux/timekeeping.h>
 
 /*
  * Include queued spinlock definitions and statistics code
  */
+#ifdef CONFIG_QUEUED_SPINLOCKS
 #include "../locking/qspinlock.h"
 #include "../locking/lock_events.h"
 #include "rqspinlock.h"
+#include "../locking/mcs_spinlock.h"
+#endif
 
 /*
  * The basic principle of a queue-based spinlock can best be understood
@@ -70,8 +75,6 @@
  *
  */
 
-#include "../locking/mcs_spinlock.h"
-
 struct rqspinlock_timeout {
 	u64 timeout_end;
 	u64 duration;
@@ -263,6 +266,43 @@ static noinline int check_timeout(rqspinlock_t *lock, u32 mask,
  */
 #define RES_RESET_TIMEOUT(ts, _duration) ({ (ts).timeout_end = 0; (ts).duration = _duration; })
 
+/*
+ * Provide a test-and-set fallback for cases when queued spin lock support is
+ * absent from the architecture.
+ */
+int __lockfunc resilient_tas_spin_lock(rqspinlock_t *lock)
+{
+	struct rqspinlock_timeout ts;
+	int val, ret = 0;
+
+	RES_INIT_TIMEOUT(ts);
+	grab_held_lock_entry(lock);
+
+	/*
+	 * Since the waiting loop's time is dependent on the amount of
+	 * contention, a short timeout unlike rqspinlock waiting loops
+	 * isn't enough. Choose a second as the timeout value.
+	 */
+	RES_RESET_TIMEOUT(ts, NSEC_PER_SEC);
+retry:
+	val = atomic_read(&lock->val);
+
+	if (val || !atomic_try_cmpxchg(&lock->val, &val, 1)) {
+		if (RES_CHECK_TIMEOUT(ts, ret, ~0u))
+			goto out;
+		cpu_relax();
+		goto retry;
+	}
+
+	return 0;
+out:
+	release_held_lock_entry();
+	return ret;
+}
+EXPORT_SYMBOL_GPL(resilient_tas_spin_lock);
+
+#ifdef CONFIG_QUEUED_SPINLOCKS
+
 /*
  * Per-CPU queue node structures; we can never have more than 4 nested
  * contexts: task, softirq, hardirq, nmi.
@@ -616,3 +656,5 @@ int __lockfunc resilient_queued_spin_lock_slowpath(rqspinlock_t *lock, u32 val)
 	return ret;
 }
 EXPORT_SYMBOL_GPL(resilient_queued_spin_lock_slowpath);
+
+#endif /* CONFIG_QUEUED_SPINLOCKS */