asm-generic: ticket-lock: Optimize arch_spin_value_unlocked()

The arch_spin_value_unlocked() of ticket-lock would cause the compiler to
generate inefficient asm code in riscv architecture because of
unnecessary memory access to the contended value.

Before the patch:

	void lockref_get(struct lockref *lockref)
	{
	  78:   fd010113                add     sp,sp,-48
	  7c:   02813023                sd      s0,32(sp)
	  80:   02113423                sd      ra,40(sp)
	  84:   03010413                add     s0,sp,48

	0000000000000088 <.LBB296>:
		CMPXCHG_LOOP(
	  88:   00053783                ld      a5,0(a0)

After the patch:

	void lockref_get(struct lockref *lockref)
	{
		CMPXCHG_LOOP(
	  78:   00053783                ld      a5,0(a0)

After the patch, the lockref_get() could get in a fast path instead of the
function's prologue. This is because ticket lock complex logic would
limit compiler optimization for the spinlock fast path, and qspinlock
won't.

The caller of arch_spin_value_unlocked() could benefit from this
change. Currently, the only caller is lockref.

Signed-off-by: Guo Ren <[email protected]>
Signed-off-by: Guo Ren <[email protected]>
Signed-off-by: Ingo Molnar <[email protected]>
Acked-by: Waiman Long <[email protected]>
Acked-by: Will Deacon <[email protected]>
Link: https://lore.kernel.org/r/[email protected]

Author: guoren83

include/asm-generic/spinlock.h

@@ -68,11 +68,18 @@ static __always_inline void arch_spin_unlock(arch_spinlock_t *lock)
 	smp_store_release(ptr, (u16)val + 1);
 }
 
+static __always_inline int arch_spin_value_unlocked(arch_spinlock_t lock)
+{
+	u32 val = lock.counter;
+
+	return ((val >> 16) == (val & 0xffff));
+}
+
 static __always_inline int arch_spin_is_locked(arch_spinlock_t *lock)
 {
-	u32 val = atomic_read(lock);
+	arch_spinlock_t val = READ_ONCE(*lock);
 
-	return ((val >> 16) != (val & 0xffff));
+	return !arch_spin_value_unlocked(val);
 }
 
 static __always_inline int arch_spin_is_contended(arch_spinlock_t *lock)
@@ -82,11 +89,6 @@ static __always_inline int arch_spin_is_contended(arch_spinlock_t *lock)
 	return (s16)((val >> 16) - (val & 0xffff)) > 1;
 }
 
-static __always_inline int arch_spin_value_unlocked(arch_spinlock_t lock)
-{
-	return !arch_spin_is_locked(&lock);
-}
-
 #include <asm/qrwlock.h>
 
 #endif /* __ASM_GENERIC_SPINLOCK_H */