[PATCH 03/17] powerpc/qspinlock: use a half-word store to unlock to avoid larx/stcx.
From: Nicholas Piggin <npiggin@gmail.com>
Date: 2022-07-28 06:34:19
Subsystem:
linux for powerpc (32-bit and 64-bit), the rest · Maintainers:
Madhavan Srinivasan, Michael Ellerman, Linus Torvalds
The first 16 bits of the lock are only modified by the owner, and other modifications always use atomic operations on the entire 32 bits, so unlocks can use plain stores on the 16 bits. This is the same kind of optimisation done by core qspinlock code. --- arch/powerpc/include/asm/qspinlock.h | 6 +----- arch/powerpc/include/asm/qspinlock_types.h | 19 +++++++++++++++++-- 2 files changed, 18 insertions(+), 7 deletions(-)
diff --git a/arch/powerpc/include/asm/qspinlock.h b/arch/powerpc/include/asm/qspinlock.h
index f06117aa60e1..79a1936fb68d 100644
--- a/arch/powerpc/include/asm/qspinlock.h
+++ b/arch/powerpc/include/asm/qspinlock.h@@ -38,11 +38,7 @@ static __always_inline void queued_spin_lock(struct qspinlock *lock) static inline void queued_spin_unlock(struct qspinlock *lock) { - for (;;) { - int val = atomic_read(&lock->val); - if (atomic_cmpxchg_release(&lock->val, val, val & ~_Q_LOCKED_VAL) == val) - return; - } + smp_store_release(&lock->locked, 0); } #define arch_spin_is_locked(l) queued_spin_is_locked(l)
diff --git a/arch/powerpc/include/asm/qspinlock_types.h b/arch/powerpc/include/asm/qspinlock_types.h
index 9630e714c70d..3425dab42576 100644
--- a/arch/powerpc/include/asm/qspinlock_types.h
+++ b/arch/powerpc/include/asm/qspinlock_types.h@@ -3,12 +3,27 @@ #define _ASM_POWERPC_QSPINLOCK_TYPES_H #include <linux/types.h> +#include <asm/byteorder.h> typedef struct qspinlock { - atomic_t val; + union { + atomic_t val; + +#ifdef __LITTLE_ENDIAN + struct { + u16 locked; + u8 reserved[2]; + }; +#else + struct { + u8 reserved[2]; + u16 locked; + }; +#endif + }; } arch_spinlock_t; -#define __ARCH_SPIN_LOCK_UNLOCKED { .val = ATOMIC_INIT(0) } +#define __ARCH_SPIN_LOCK_UNLOCKED { { .val = ATOMIC_INIT(0) } } /* * Bitfields in the atomic value:
--
2.35.1