powerpc/qspinlock: store owner CPU in lock word

Store the owner CPU number in the lock word so it may be yielded to,
as powerpc's paravirtualised simple spinlocks do.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20221126095932.1234527-7-npiggin@gmail.com

arch/powerpc/include/asm/qspinlock.h

@@ -21,8 +21,15 @@ static __always_inline int queued_spin_is_contended(struct qspinlock *lock)
 	return !!(READ_ONCE(lock->val) & _Q_TAIL_CPU_MASK);
 }
 
+static __always_inline u32 queued_spin_encode_locked_val(void)
+{
+	/* XXX: make this use lock value in paca like simple spinlocks? */
+	return _Q_LOCKED_VAL | (smp_processor_id() << _Q_OWNER_CPU_OFFSET);
+}
+
 static __always_inline int queued_spin_trylock(struct qspinlock *lock)
 {
+	u32 new = queued_spin_encode_locked_val();
 	u32 prev;
 
 	asm volatile(
@@ -34,7 +41,7 @@ static __always_inline int queued_spin_trylock(struct qspinlock *lock)
 "\t"	PPC_ACQUIRE_BARRIER "						\n"
 "2:									\n"
 	: "=&r" (prev)
-	: "r" (&lock->val), "r" (_Q_LOCKED_VAL),
+	: "r" (&lock->val), "r" (new),
 	  "i" (IS_ENABLED(CONFIG_PPC64))
 	: "cr0", "memory");
 
@@ -43,6 +50,7 @@ static __always_inline int queued_spin_trylock(struct qspinlock *lock)
 
 static __always_inline int __queued_spin_trylock_steal(struct qspinlock *lock)
 {
+	u32 new = queued_spin_encode_locked_val();
 	u32 prev, tmp;
 
 	/* Trylock may get ahead of queued nodes if it finds unlocked */
@@ -57,7 +65,7 @@ static __always_inline int __queued_spin_trylock_steal(struct qspinlock *lock)
 "\t"	PPC_ACQUIRE_BARRIER "						\n"
 "2:									\n"
 	: "=&r" (prev), "=&r" (tmp)
-	: "r" (&lock->val), "r" (_Q_LOCKED_VAL), "r" (_Q_TAIL_CPU_MASK),
+	: "r" (&lock->val), "r" (new), "r" (_Q_TAIL_CPU_MASK),
 	  "i" (IS_ENABLED(CONFIG_PPC64))
 	: "cr0", "memory");
 

arch/powerpc/include/asm/qspinlock_types.h

@@ -29,7 +29,8 @@ typedef struct qspinlock {
  * Bitfields in the lock word:
  *
  *     0: locked bit
- *  1-15: unused bits
+ *  1-14: lock holder cpu
+ *    15: unused bit
  *    16: must queue bit
  * 17-31: tail cpu (+1)
  */
@@ -40,6 +41,15 @@ typedef struct qspinlock {
 #define _Q_LOCKED_BITS		1
 #define _Q_LOCKED_VAL		(1U << _Q_LOCKED_OFFSET)
 
+/* 0x00007ffe */
+#define _Q_OWNER_CPU_OFFSET	1
+#define _Q_OWNER_CPU_BITS	14
+#define _Q_OWNER_CPU_MASK	_Q_SET_MASK(OWNER_CPU)
+
+#if CONFIG_NR_CPUS > (1U << _Q_OWNER_CPU_BITS)
+#error "qspinlock does not support such large CONFIG_NR_CPUS"
+#endif
+
 /* 0x00010000 */
 #define _Q_MUST_Q_OFFSET	16
 #define _Q_MUST_Q_BITS		1

arch/powerpc/lib/qspinlock.c

@@ -55,7 +55,7 @@ static inline int decode_tail_cpu(u32 val)
  */
 static __always_inline u32 trylock_clean_tail(struct qspinlock *lock, u32 tail)
 {
-	u32 newval = _Q_LOCKED_VAL;
+	u32 newval = queued_spin_encode_locked_val();
 	u32 prev, tmp;
 
 	asm volatile(