powerpc/qspinlock: powerpc qspinlock implementation

Add a powerpc specific implementation of queued spinlocks. This is the
build framework with a very simple (non-queued) spinlock implementation
to begin with. Later changes add queueing, and other features and
optimisations one-at-a-time. It is done this way to more easily see how
the queued spinlocks are built, and to make performance and correctness
bisects more useful.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
[mpe: Drop paravirt.h & processor.h changes to fix 32-bit build]
[mpe: Fix 32-bit build of qspinlock.o & disallow GENERIC_LOCKBREAK per Nick]
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/CONLLQB6DCJU.2ZPOS7T6S5GRR@bobo

arch/powerpc/Kconfig

@@ -96,7 +96,7 @@ config LOCKDEP_SUPPORT
 config GENERIC_LOCKBREAK
 	bool
 	default y
-	depends on SMP && PREEMPTION
+	depends on SMP && PREEMPTION && !PPC_QUEUED_SPINLOCKS
 
 config GENERIC_HWEIGHT
 	bool
@@ -154,7 +154,6 @@ config PPC
 	select ARCH_USE_CMPXCHG_LOCKREF		if PPC64
 	select ARCH_USE_MEMTEST
 	select ARCH_USE_QUEUED_RWLOCKS		if PPC_QUEUED_SPINLOCKS
-	select ARCH_USE_QUEUED_SPINLOCKS	if PPC_QUEUED_SPINLOCKS
 	select ARCH_WANT_DEFAULT_TOPDOWN_MMAP_LAYOUT
 	select ARCH_WANT_IPC_PARSE_VERSION
 	select ARCH_WANT_IRQS_OFF_ACTIVATE_MM

arch/powerpc/include/asm/qspinlock.h

@@ -2,83 +2,55 @@
 #ifndef _ASM_POWERPC_QSPINLOCK_H
 #define _ASM_POWERPC_QSPINLOCK_H
 
-#include <asm-generic/qspinlock_types.h>
+#include <linux/atomic.h>
+#include <linux/compiler.h>
+#include <asm/qspinlock_types.h>
 #include <asm/paravirt.h>
 
-#define _Q_PENDING_LOOPS	(1 << 9) /* not tuned */
-
-#ifdef CONFIG_PARAVIRT_SPINLOCKS
-extern void native_queued_spin_lock_slowpath(struct qspinlock *lock, u32 val);
-extern void __pv_queued_spin_lock_slowpath(struct qspinlock *lock, u32 val);
-extern void __pv_queued_spin_unlock(struct qspinlock *lock);
-
-static __always_inline void queued_spin_lock_slowpath(struct qspinlock *lock, u32 val)
+static __always_inline int queued_spin_is_locked(struct qspinlock *lock)
 {
-	if (!is_shared_processor())
-		native_queued_spin_lock_slowpath(lock, val);
-	else
-		__pv_queued_spin_lock_slowpath(lock, val);
+	return atomic_read(&lock->val);
 }
 
-#define queued_spin_unlock queued_spin_unlock
-static inline void queued_spin_unlock(struct qspinlock *lock)
+static __always_inline int queued_spin_value_unlocked(struct qspinlock lock)
 {
-	if (!is_shared_processor())
-		smp_store_release(&lock->locked, 0);
-	else
-		__pv_queued_spin_unlock(lock);
+	return !atomic_read(&lock.val);
 }
 
-#else
-extern void queued_spin_lock_slowpath(struct qspinlock *lock, u32 val);
-#endif
-
-static __always_inline void queued_spin_lock(struct qspinlock *lock)
+static __always_inline int queued_spin_is_contended(struct qspinlock *lock)
 {
-	u32 val = 0;
-
-	if (likely(arch_atomic_try_cmpxchg_lock(&lock->val, &val, _Q_LOCKED_VAL)))
-		return;
-
-	queued_spin_lock_slowpath(lock, val);
+	return 0;
 }
-#define queued_spin_lock queued_spin_lock
 
-#ifdef CONFIG_PARAVIRT_SPINLOCKS
-#define SPIN_THRESHOLD (1<<15) /* not tuned */
-
-static __always_inline void pv_wait(u8 *ptr, u8 val)
+static __always_inline int queued_spin_trylock(struct qspinlock *lock)
 {
-	if (*ptr != val)
-		return;
-	yield_to_any();
-	/*
-	 * We could pass in a CPU here if waiting in the queue and yield to
-	 * the previous CPU in the queue.
-	 */
+	return atomic_cmpxchg_acquire(&lock->val, 0, 1) == 0;
 }
 
-static __always_inline void pv_kick(int cpu)
+void queued_spin_lock_slowpath(struct qspinlock *lock);
+
+static __always_inline void queued_spin_lock(struct qspinlock *lock)
 {
-	prod_cpu(cpu);
+	if (!queued_spin_trylock(lock))
+		queued_spin_lock_slowpath(lock);
 }
 
-extern void __pv_init_lock_hash(void);
-
-static inline void pv_spinlocks_init(void)
+static inline void queued_spin_unlock(struct qspinlock *lock)
 {
-	__pv_init_lock_hash();
+	atomic_set_release(&lock->val, 0);
 }
 
-#endif
-
-/*
- * Queued spinlocks rely heavily on smp_cond_load_relaxed() to busy-wait,
- * which was found to have performance problems if implemented with
- * the preferred spin_begin()/spin_end() SMT priority pattern. Use the
- * generic version instead.
- */
+#define arch_spin_is_locked(l)		queued_spin_is_locked(l)
+#define arch_spin_is_contended(l)	queued_spin_is_contended(l)
+#define arch_spin_value_unlocked(l)	queued_spin_value_unlocked(l)
+#define arch_spin_lock(l)		queued_spin_lock(l)
+#define arch_spin_trylock(l)		queued_spin_trylock(l)
+#define arch_spin_unlock(l)		queued_spin_unlock(l)
 
-#include <asm-generic/qspinlock.h>
+#ifdef CONFIG_PARAVIRT_SPINLOCKS
+void pv_spinlocks_init(void);
+#else
+static inline void pv_spinlocks_init(void) { }
+#endif
 
 #endif /* _ASM_POWERPC_QSPINLOCK_H */

arch/powerpc/include/asm/qspinlock_paravirt.h

-/* SPDX-License-Identifier: GPL-2.0-or-later */
-#ifndef _ASM_POWERPC_QSPINLOCK_PARAVIRT_H
-#define _ASM_POWERPC_QSPINLOCK_PARAVIRT_H
-
-EXPORT_SYMBOL(__pv_queued_spin_unlock);
-
-#endif /* _ASM_POWERPC_QSPINLOCK_PARAVIRT_H */

arch/powerpc/include/asm/qspinlock_types.h

+/* SPDX-License-Identifier: GPL-2.0-or-later */
+#ifndef _ASM_POWERPC_QSPINLOCK_TYPES_H
+#define _ASM_POWERPC_QSPINLOCK_TYPES_H
+
+#include <linux/types.h>
+
+typedef struct qspinlock {
+	atomic_t val;
+} arch_spinlock_t;
+
+#define	__ARCH_SPIN_LOCK_UNLOCKED	{ .val = ATOMIC_INIT(0) }
+
+#endif /* _ASM_POWERPC_QSPINLOCK_TYPES_H */

arch/powerpc/include/asm/spinlock.h

@@ -13,7 +13,7 @@
 /* See include/linux/spinlock.h */
 #define smp_mb__after_spinlock()	smp_mb()
 
-#ifndef CONFIG_PARAVIRT_SPINLOCKS
+#ifndef CONFIG_PPC_QUEUED_SPINLOCKS
 static inline void pv_spinlocks_init(void) { }
 #endif
 

arch/powerpc/include/asm/spinlock_types.h

@@ -7,7 +7,7 @@
 #endif
 
 #ifdef CONFIG_PPC_QUEUED_SPINLOCKS
-#include <asm-generic/qspinlock_types.h>
+#include <asm/qspinlock_types.h>
 #include <asm-generic/qrwlock_types.h>
 #else
 #include <asm/simple_spinlock_types.h>

arch/powerpc/lib/Makefile

@@ -52,7 +52,9 @@ obj-$(CONFIG_PPC_BOOK3S_64) += copyuser_power7.o copypage_power7.o \
 obj64-y	+= copypage_64.o copyuser_64.o mem_64.o hweight_64.o \
 	   memcpy_64.o copy_mc_64.o
 
-ifndef CONFIG_PPC_QUEUED_SPINLOCKS
+ifdef CONFIG_PPC_QUEUED_SPINLOCKS
+obj-$(CONFIG_SMP)	+= qspinlock.o
+else
 obj64-$(CONFIG_SMP)	+= locks.o
 endif
 

arch/powerpc/lib/qspinlock.c

+// SPDX-License-Identifier: GPL-2.0-or-later
+#include <linux/export.h>
+#include <linux/processor.h>
+#include <asm/qspinlock.h>
+
+void queued_spin_lock_slowpath(struct qspinlock *lock)
+{
+	while (!queued_spin_trylock(lock))
+		cpu_relax();
+}
+EXPORT_SYMBOL(queued_spin_lock_slowpath);
+
+#ifdef CONFIG_PARAVIRT_SPINLOCKS
+void pv_spinlocks_init(void)
+{
+}
+#endif