From: Will Deacon <will.deacon@arm.com> To: linux-kernel@vger.kernel.org Cc: linux-arm-kernel@lists.infradead.org, Jeremy.Linton@arm.com, peterz@infradead.org, mingo@redhat.com, longman@redhat.com, boqun.feng@gmail.com, paulmck@linux.vnet.ibm.com, Will Deacon <will.deacon@arm.com> Subject: [PATCH v2 4/5] arm64: locking: Move rwlock implementation over to qrwlocks Date: Fri, 6 Oct 2017 14:34:41 +0100 [thread overview] Message-ID: <1507296882-18721-5-git-send-email-will.deacon@arm.com> (raw) In-Reply-To: <1507296882-18721-1-git-send-email-will.deacon@arm.com> Now that the qrwlock can make use of WFE, remove our homebrew rwlock code in favour of the generic queued implementation. Signed-off-by: Will Deacon <will.deacon@arm.com> --- arch/arm64/Kconfig | 17 ++++ arch/arm64/include/asm/Kbuild | 1 + arch/arm64/include/asm/spinlock.h | 164 +------------------------------- arch/arm64/include/asm/spinlock_types.h | 6 +- 4 files changed, 20 insertions(+), 168 deletions(-) diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 0df64a6a56d4..6d32c9b0d4bb 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -22,7 +22,24 @@ config ARM64 select ARCH_HAS_STRICT_MODULE_RWX select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST select ARCH_HAVE_NMI_SAFE_CMPXCHG if ACPI_APEI_SEA + select ARCH_INLINE_READ_LOCK if !PREEMPT + select ARCH_INLINE_READ_LOCK_BH if !PREEMPT + select ARCH_INLINE_READ_LOCK_IRQ if !PREEMPT + select ARCH_INLINE_READ_LOCK_IRQSAVE if !PREEMPT + select ARCH_INLINE_READ_UNLOCK if !PREEMPT + select ARCH_INLINE_READ_UNLOCK_BH if !PREEMPT + select ARCH_INLINE_READ_UNLOCK_IRQ if !PREEMPT + select ARCH_INLINE_READ_UNLOCK_IRQSAVE if !PREEMPT + select ARCH_INLINE_WRITE_LOCK if !PREEMPT + select ARCH_INLINE_WRITE_LOCK_BH if !PREEMPT + select ARCH_INLINE_WRITE_LOCK_IRQ if !PREEMPT + select ARCH_INLINE_WRITE_LOCK_IRQSAVE if !PREEMPT + select ARCH_INLINE_WRITE_UNLOCK if !PREEMPT + select ARCH_INLINE_WRITE_UNLOCK_BH if !PREEMPT + select ARCH_INLINE_WRITE_UNLOCK_IRQ if !PREEMPT + select ARCH_INLINE_WRITE_UNLOCK_IRQSAVE if !PREEMPT select ARCH_USE_CMPXCHG_LOCKREF + select ARCH_USE_QUEUED_RWLOCKS select ARCH_SUPPORTS_MEMORY_FAILURE select ARCH_SUPPORTS_ATOMIC_RMW select ARCH_SUPPORTS_NUMA_BALANCING diff --git a/arch/arm64/include/asm/Kbuild b/arch/arm64/include/asm/Kbuild index 2326e39d5892..e63d0a8312de 100644 --- a/arch/arm64/include/asm/Kbuild +++ b/arch/arm64/include/asm/Kbuild @@ -16,6 +16,7 @@ generic-y += mcs_spinlock.h generic-y += mm-arch-hooks.h generic-y += msi.h generic-y += preempt.h +generic-y += qrwlock.h generic-y += rwsem.h generic-y += segment.h generic-y += serial.h diff --git a/arch/arm64/include/asm/spinlock.h b/arch/arm64/include/asm/spinlock.h index aa51a38e46e4..fdb827c7832f 100644 --- a/arch/arm64/include/asm/spinlock.h +++ b/arch/arm64/include/asm/spinlock.h @@ -137,169 +137,7 @@ static inline int arch_spin_is_contended(arch_spinlock_t *lock) } #define arch_spin_is_contended arch_spin_is_contended -/* - * Write lock implementation. - * - * Write locks set bit 31. Unlocking, is done by writing 0 since the lock is - * exclusively held. - * - * The memory barriers are implicit with the load-acquire and store-release - * instructions. - */ - -static inline void arch_write_lock(arch_rwlock_t *rw) -{ - unsigned int tmp; - - asm volatile(ARM64_LSE_ATOMIC_INSN( - /* LL/SC */ - " sevl\n" - "1: wfe\n" - "2: ldaxr %w0, %1\n" - " cbnz %w0, 1b\n" - " stxr %w0, %w2, %1\n" - " cbnz %w0, 2b\n" - __nops(1), - /* LSE atomics */ - "1: mov %w0, wzr\n" - "2: casa %w0, %w2, %1\n" - " cbz %w0, 3f\n" - " ldxr %w0, %1\n" - " cbz %w0, 2b\n" - " wfe\n" - " b 1b\n" - "3:") - : "=&r" (tmp), "+Q" (rw->lock) - : "r" (0x80000000) - : "memory"); -} - -static inline int arch_write_trylock(arch_rwlock_t *rw) -{ - unsigned int tmp; - - asm volatile(ARM64_LSE_ATOMIC_INSN( - /* LL/SC */ - "1: ldaxr %w0, %1\n" - " cbnz %w0, 2f\n" - " stxr %w0, %w2, %1\n" - " cbnz %w0, 1b\n" - "2:", - /* LSE atomics */ - " mov %w0, wzr\n" - " casa %w0, %w2, %1\n" - __nops(2)) - : "=&r" (tmp), "+Q" (rw->lock) - : "r" (0x80000000) - : "memory"); - - return !tmp; -} - -static inline void arch_write_unlock(arch_rwlock_t *rw) -{ - asm volatile(ARM64_LSE_ATOMIC_INSN( - " stlr wzr, %0", - " swpl wzr, wzr, %0") - : "=Q" (rw->lock) :: "memory"); -} - -/* write_can_lock - would write_trylock() succeed? */ -#define arch_write_can_lock(x) ((x)->lock == 0) - -/* - * Read lock implementation. - * - * It exclusively loads the lock value, increments it and stores the new value - * back if positive and the CPU still exclusively owns the location. If the - * value is negative, the lock is already held. - * - * During unlocking there may be multiple active read locks but no write lock. - * - * The memory barriers are implicit with the load-acquire and store-release - * instructions. - * - * Note that in UNDEFINED cases, such as unlocking a lock twice, the LL/SC - * and LSE implementations may exhibit different behaviour (although this - * will have no effect on lockdep). - */ -static inline void arch_read_lock(arch_rwlock_t *rw) -{ - unsigned int tmp, tmp2; - - asm volatile( - " sevl\n" - ARM64_LSE_ATOMIC_INSN( - /* LL/SC */ - "1: wfe\n" - "2: ldaxr %w0, %2\n" - " add %w0, %w0, #1\n" - " tbnz %w0, #31, 1b\n" - " stxr %w1, %w0, %2\n" - " cbnz %w1, 2b\n" - __nops(1), - /* LSE atomics */ - "1: wfe\n" - "2: ldxr %w0, %2\n" - " adds %w1, %w0, #1\n" - " tbnz %w1, #31, 1b\n" - " casa %w0, %w1, %2\n" - " sbc %w0, %w1, %w0\n" - " cbnz %w0, 2b") - : "=&r" (tmp), "=&r" (tmp2), "+Q" (rw->lock) - : - : "cc", "memory"); -} - -static inline void arch_read_unlock(arch_rwlock_t *rw) -{ - unsigned int tmp, tmp2; - - asm volatile(ARM64_LSE_ATOMIC_INSN( - /* LL/SC */ - "1: ldxr %w0, %2\n" - " sub %w0, %w0, #1\n" - " stlxr %w1, %w0, %2\n" - " cbnz %w1, 1b", - /* LSE atomics */ - " movn %w0, #0\n" - " staddl %w0, %2\n" - __nops(2)) - : "=&r" (tmp), "=&r" (tmp2), "+Q" (rw->lock) - : - : "memory"); -} - -static inline int arch_read_trylock(arch_rwlock_t *rw) -{ - unsigned int tmp, tmp2; - - asm volatile(ARM64_LSE_ATOMIC_INSN( - /* LL/SC */ - " mov %w1, #1\n" - "1: ldaxr %w0, %2\n" - " add %w0, %w0, #1\n" - " tbnz %w0, #31, 2f\n" - " stxr %w1, %w0, %2\n" - " cbnz %w1, 1b\n" - "2:", - /* LSE atomics */ - " ldr %w0, %2\n" - " adds %w1, %w0, #1\n" - " tbnz %w1, #31, 1f\n" - " casa %w0, %w1, %2\n" - " sbc %w1, %w1, %w0\n" - __nops(1) - "1:") - : "=&r" (tmp), "=&r" (tmp2), "+Q" (rw->lock) - : - : "cc", "memory"); - - return !tmp2; -} - -/* read_can_lock - would read_trylock() succeed? */ -#define arch_read_can_lock(x) ((x)->lock < 0x80000000) +#include <asm/qrwlock.h> /* See include/linux/spinlock.h */ #define smp_mb__after_spinlock() smp_mb() diff --git a/arch/arm64/include/asm/spinlock_types.h b/arch/arm64/include/asm/spinlock_types.h index 55be59a35e3f..6b856012c51b 100644 --- a/arch/arm64/include/asm/spinlock_types.h +++ b/arch/arm64/include/asm/spinlock_types.h @@ -36,10 +36,6 @@ typedef struct { #define __ARCH_SPIN_LOCK_UNLOCKED { 0 , 0 } -typedef struct { - volatile unsigned int lock; -} arch_rwlock_t; - -#define __ARCH_RW_LOCK_UNLOCKED { 0 } +#include <asm-generic/qrwlock_types.h> #endif -- 2.1.4
WARNING: multiple messages have this Message-ID (diff)
From: will.deacon@arm.com (Will Deacon) To: linux-arm-kernel@lists.infradead.org Subject: [PATCH v2 4/5] arm64: locking: Move rwlock implementation over to qrwlocks Date: Fri, 6 Oct 2017 14:34:41 +0100 [thread overview] Message-ID: <1507296882-18721-5-git-send-email-will.deacon@arm.com> (raw) In-Reply-To: <1507296882-18721-1-git-send-email-will.deacon@arm.com> Now that the qrwlock can make use of WFE, remove our homebrew rwlock code in favour of the generic queued implementation. Signed-off-by: Will Deacon <will.deacon@arm.com> --- arch/arm64/Kconfig | 17 ++++ arch/arm64/include/asm/Kbuild | 1 + arch/arm64/include/asm/spinlock.h | 164 +------------------------------- arch/arm64/include/asm/spinlock_types.h | 6 +- 4 files changed, 20 insertions(+), 168 deletions(-) diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 0df64a6a56d4..6d32c9b0d4bb 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -22,7 +22,24 @@ config ARM64 select ARCH_HAS_STRICT_MODULE_RWX select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST select ARCH_HAVE_NMI_SAFE_CMPXCHG if ACPI_APEI_SEA + select ARCH_INLINE_READ_LOCK if !PREEMPT + select ARCH_INLINE_READ_LOCK_BH if !PREEMPT + select ARCH_INLINE_READ_LOCK_IRQ if !PREEMPT + select ARCH_INLINE_READ_LOCK_IRQSAVE if !PREEMPT + select ARCH_INLINE_READ_UNLOCK if !PREEMPT + select ARCH_INLINE_READ_UNLOCK_BH if !PREEMPT + select ARCH_INLINE_READ_UNLOCK_IRQ if !PREEMPT + select ARCH_INLINE_READ_UNLOCK_IRQSAVE if !PREEMPT + select ARCH_INLINE_WRITE_LOCK if !PREEMPT + select ARCH_INLINE_WRITE_LOCK_BH if !PREEMPT + select ARCH_INLINE_WRITE_LOCK_IRQ if !PREEMPT + select ARCH_INLINE_WRITE_LOCK_IRQSAVE if !PREEMPT + select ARCH_INLINE_WRITE_UNLOCK if !PREEMPT + select ARCH_INLINE_WRITE_UNLOCK_BH if !PREEMPT + select ARCH_INLINE_WRITE_UNLOCK_IRQ if !PREEMPT + select ARCH_INLINE_WRITE_UNLOCK_IRQSAVE if !PREEMPT select ARCH_USE_CMPXCHG_LOCKREF + select ARCH_USE_QUEUED_RWLOCKS select ARCH_SUPPORTS_MEMORY_FAILURE select ARCH_SUPPORTS_ATOMIC_RMW select ARCH_SUPPORTS_NUMA_BALANCING diff --git a/arch/arm64/include/asm/Kbuild b/arch/arm64/include/asm/Kbuild index 2326e39d5892..e63d0a8312de 100644 --- a/arch/arm64/include/asm/Kbuild +++ b/arch/arm64/include/asm/Kbuild @@ -16,6 +16,7 @@ generic-y += mcs_spinlock.h generic-y += mm-arch-hooks.h generic-y += msi.h generic-y += preempt.h +generic-y += qrwlock.h generic-y += rwsem.h generic-y += segment.h generic-y += serial.h diff --git a/arch/arm64/include/asm/spinlock.h b/arch/arm64/include/asm/spinlock.h index aa51a38e46e4..fdb827c7832f 100644 --- a/arch/arm64/include/asm/spinlock.h +++ b/arch/arm64/include/asm/spinlock.h @@ -137,169 +137,7 @@ static inline int arch_spin_is_contended(arch_spinlock_t *lock) } #define arch_spin_is_contended arch_spin_is_contended -/* - * Write lock implementation. - * - * Write locks set bit 31. Unlocking, is done by writing 0 since the lock is - * exclusively held. - * - * The memory barriers are implicit with the load-acquire and store-release - * instructions. - */ - -static inline void arch_write_lock(arch_rwlock_t *rw) -{ - unsigned int tmp; - - asm volatile(ARM64_LSE_ATOMIC_INSN( - /* LL/SC */ - " sevl\n" - "1: wfe\n" - "2: ldaxr %w0, %1\n" - " cbnz %w0, 1b\n" - " stxr %w0, %w2, %1\n" - " cbnz %w0, 2b\n" - __nops(1), - /* LSE atomics */ - "1: mov %w0, wzr\n" - "2: casa %w0, %w2, %1\n" - " cbz %w0, 3f\n" - " ldxr %w0, %1\n" - " cbz %w0, 2b\n" - " wfe\n" - " b 1b\n" - "3:") - : "=&r" (tmp), "+Q" (rw->lock) - : "r" (0x80000000) - : "memory"); -} - -static inline int arch_write_trylock(arch_rwlock_t *rw) -{ - unsigned int tmp; - - asm volatile(ARM64_LSE_ATOMIC_INSN( - /* LL/SC */ - "1: ldaxr %w0, %1\n" - " cbnz %w0, 2f\n" - " stxr %w0, %w2, %1\n" - " cbnz %w0, 1b\n" - "2:", - /* LSE atomics */ - " mov %w0, wzr\n" - " casa %w0, %w2, %1\n" - __nops(2)) - : "=&r" (tmp), "+Q" (rw->lock) - : "r" (0x80000000) - : "memory"); - - return !tmp; -} - -static inline void arch_write_unlock(arch_rwlock_t *rw) -{ - asm volatile(ARM64_LSE_ATOMIC_INSN( - " stlr wzr, %0", - " swpl wzr, wzr, %0") - : "=Q" (rw->lock) :: "memory"); -} - -/* write_can_lock - would write_trylock() succeed? */ -#define arch_write_can_lock(x) ((x)->lock == 0) - -/* - * Read lock implementation. - * - * It exclusively loads the lock value, increments it and stores the new value - * back if positive and the CPU still exclusively owns the location. If the - * value is negative, the lock is already held. - * - * During unlocking there may be multiple active read locks but no write lock. - * - * The memory barriers are implicit with the load-acquire and store-release - * instructions. - * - * Note that in UNDEFINED cases, such as unlocking a lock twice, the LL/SC - * and LSE implementations may exhibit different behaviour (although this - * will have no effect on lockdep). - */ -static inline void arch_read_lock(arch_rwlock_t *rw) -{ - unsigned int tmp, tmp2; - - asm volatile( - " sevl\n" - ARM64_LSE_ATOMIC_INSN( - /* LL/SC */ - "1: wfe\n" - "2: ldaxr %w0, %2\n" - " add %w0, %w0, #1\n" - " tbnz %w0, #31, 1b\n" - " stxr %w1, %w0, %2\n" - " cbnz %w1, 2b\n" - __nops(1), - /* LSE atomics */ - "1: wfe\n" - "2: ldxr %w0, %2\n" - " adds %w1, %w0, #1\n" - " tbnz %w1, #31, 1b\n" - " casa %w0, %w1, %2\n" - " sbc %w0, %w1, %w0\n" - " cbnz %w0, 2b") - : "=&r" (tmp), "=&r" (tmp2), "+Q" (rw->lock) - : - : "cc", "memory"); -} - -static inline void arch_read_unlock(arch_rwlock_t *rw) -{ - unsigned int tmp, tmp2; - - asm volatile(ARM64_LSE_ATOMIC_INSN( - /* LL/SC */ - "1: ldxr %w0, %2\n" - " sub %w0, %w0, #1\n" - " stlxr %w1, %w0, %2\n" - " cbnz %w1, 1b", - /* LSE atomics */ - " movn %w0, #0\n" - " staddl %w0, %2\n" - __nops(2)) - : "=&r" (tmp), "=&r" (tmp2), "+Q" (rw->lock) - : - : "memory"); -} - -static inline int arch_read_trylock(arch_rwlock_t *rw) -{ - unsigned int tmp, tmp2; - - asm volatile(ARM64_LSE_ATOMIC_INSN( - /* LL/SC */ - " mov %w1, #1\n" - "1: ldaxr %w0, %2\n" - " add %w0, %w0, #1\n" - " tbnz %w0, #31, 2f\n" - " stxr %w1, %w0, %2\n" - " cbnz %w1, 1b\n" - "2:", - /* LSE atomics */ - " ldr %w0, %2\n" - " adds %w1, %w0, #1\n" - " tbnz %w1, #31, 1f\n" - " casa %w0, %w1, %2\n" - " sbc %w1, %w1, %w0\n" - __nops(1) - "1:") - : "=&r" (tmp), "=&r" (tmp2), "+Q" (rw->lock) - : - : "cc", "memory"); - - return !tmp2; -} - -/* read_can_lock - would read_trylock() succeed? */ -#define arch_read_can_lock(x) ((x)->lock < 0x80000000) +#include <asm/qrwlock.h> /* See include/linux/spinlock.h */ #define smp_mb__after_spinlock() smp_mb() diff --git a/arch/arm64/include/asm/spinlock_types.h b/arch/arm64/include/asm/spinlock_types.h index 55be59a35e3f..6b856012c51b 100644 --- a/arch/arm64/include/asm/spinlock_types.h +++ b/arch/arm64/include/asm/spinlock_types.h @@ -36,10 +36,6 @@ typedef struct { #define __ARCH_SPIN_LOCK_UNLOCKED { 0 , 0 } -typedef struct { - volatile unsigned int lock; -} arch_rwlock_t; - -#define __ARCH_RW_LOCK_UNLOCKED { 0 } +#include <asm-generic/qrwlock_types.h> #endif -- 2.1.4
next prev parent reply other threads:[~2017-10-06 13:34 UTC|newest] Thread overview: 40+ messages / expand[flat|nested] mbox.gz Atom feed top 2017-10-06 13:34 [PATCH v2 0/5] Switch arm64 over to qrwlock Will Deacon 2017-10-06 13:34 ` Will Deacon 2017-10-06 13:34 ` [PATCH v2 1/5] kernel/locking: Use struct qrwlock instead of struct __qrwlock Will Deacon 2017-10-06 13:34 ` Will Deacon 2017-10-06 13:34 ` [PATCH v2 2/5] locking/atomic: Add atomic_cond_read_acquire Will Deacon 2017-10-06 13:34 ` Will Deacon 2017-10-06 13:34 ` [PATCH v2 3/5] kernel/locking: Use atomic_cond_read_acquire when spinning in qrwlock Will Deacon 2017-10-06 13:34 ` Will Deacon 2017-10-08 1:03 ` Boqun Feng 2017-10-08 1:03 ` Boqun Feng 2017-10-09 11:30 ` Will Deacon 2017-10-09 11:30 ` Will Deacon 2017-10-06 13:34 ` Will Deacon [this message] 2017-10-06 13:34 ` [PATCH v2 4/5] arm64: locking: Move rwlock implementation over to qrwlocks Will Deacon 2017-10-10 1:34 ` Waiman Long 2017-10-10 1:34 ` Waiman Long 2017-10-11 11:49 ` Will Deacon 2017-10-11 11:49 ` Will Deacon 2017-10-11 14:03 ` Waiman Long 2017-10-11 14:03 ` Waiman Long 2017-10-06 13:34 ` [PATCH v2 5/5] kernel/locking: Prevent slowpath writers getting held up by fastpath Will Deacon 2017-10-06 13:34 ` Will Deacon 2017-10-08 21:30 ` [PATCH v2 0/5] Switch arm64 over to qrwlock Yury Norov 2017-10-08 21:30 ` Yury Norov 2017-10-09 6:52 ` Peter Zijlstra 2017-10-09 6:52 ` Peter Zijlstra 2017-10-09 10:02 ` Will Deacon 2017-10-09 10:02 ` Will Deacon 2017-10-09 9:59 ` Will Deacon 2017-10-09 9:59 ` Will Deacon 2017-10-09 12:49 ` Yury Norov 2017-10-09 12:49 ` Yury Norov 2017-10-09 13:13 ` Will Deacon 2017-10-09 13:13 ` Will Deacon 2017-10-09 21:19 ` Waiman Long 2017-10-09 21:19 ` Waiman Long 2017-10-09 22:31 ` Jeremy Linton 2017-10-09 22:31 ` Jeremy Linton 2017-10-10 18:20 ` Adam Wallis 2017-10-10 18:20 ` Adam Wallis
Reply instructions: You may reply publicly to this message via plain-text email using any one of the following methods: * Save the following mbox file, import it into your mail client, and reply-to-all from there: mbox Avoid top-posting and favor interleaved quoting: https://en.wikipedia.org/wiki/Posting_style#Interleaved_style * Reply using the --to, --cc, and --in-reply-to switches of git-send-email(1): git send-email \ --in-reply-to=1507296882-18721-5-git-send-email-will.deacon@arm.com \ --to=will.deacon@arm.com \ --cc=Jeremy.Linton@arm.com \ --cc=boqun.feng@gmail.com \ --cc=linux-arm-kernel@lists.infradead.org \ --cc=linux-kernel@vger.kernel.org \ --cc=longman@redhat.com \ --cc=mingo@redhat.com \ --cc=paulmck@linux.vnet.ibm.com \ --cc=peterz@infradead.org \ /path/to/YOUR_REPLY https://kernel.org/pub/software/scm/git/docs/git-send-email.html * If your mail client supports setting the In-Reply-To header via mailto: links, try the mailto: linkBe sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes, see mirroring instructions on how to clone and mirror all data and code used by this external index.