On Wed, Mar 31, 2021 at 10:32 PM <guoren@xxxxxxxxxx> wrote:
>
> From: Guo Ren <guoren@xxxxxxxxxxxxxxxxx>
>
> This patch introduces a ticket lock implementation for riscv, along the
> same lines as the implementation for arch/arm & arch/csky.
>
> We still use qspinlock as default.
>
> Signed-off-by: Guo Ren <guoren@xxxxxxxxxxxxxxxxx>
> Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
> Cc: Anup Patel <anup@xxxxxxxxxxxxxx>
> Cc: Arnd Bergmann <arnd@xxxxxxxx>
> ---
> arch/riscv/Kconfig | 7 ++-
> arch/riscv/include/asm/spinlock.h | 84 +++++++++++++++++++++++++
> arch/riscv/include/asm/spinlock_types.h | 17 +++++
> 3 files changed, 107 insertions(+), 1 deletion(-)
>
> diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
> index 67cc65ba1ea1..34d0276f01d5 100644
> --- a/arch/riscv/Kconfig
> +++ b/arch/riscv/Kconfig
> @@ -34,7 +34,7 @@ config RISCV
> select ARCH_WANT_FRAME_POINTERS
> select ARCH_WANT_HUGE_PMD_SHARE if 64BIT
> select ARCH_USE_QUEUED_RWLOCKS
> - select ARCH_USE_QUEUED_SPINLOCKS
> + select ARCH_USE_QUEUED_SPINLOCKS if !RISCV_TICKET_LOCK
> select ARCH_USE_QUEUED_SPINLOCKS_XCHG32
> select CLONE_BACKWARDS
> select CLINT_TIMER if !MMU
> @@ -344,6 +344,11 @@ config NEED_PER_CPU_EMBED_FIRST_CHUNK
> def_bool y
> depends on NUMA
>
> +config RISCV_TICKET_LOCK
> + bool "Ticket-based spin-locking"
> + help
> + Say Y here to use ticket-based spin-locking.
> +
> config RISCV_ISA_C
> bool "Emit compressed instructions when building Linux"
> default y
> diff --git a/arch/riscv/include/asm/spinlock.h b/arch/riscv/include/asm/spinlock.h
> index a557de67a425..90b7eaa950cf 100644
> --- a/arch/riscv/include/asm/spinlock.h
> +++ b/arch/riscv/include/asm/spinlock.h
> @@ -7,7 +7,91 @@
> #ifndef _ASM_RISCV_SPINLOCK_H
> #define _ASM_RISCV_SPINLOCK_H
>
> +#ifdef CONFIG_RISCV_TICKET_LOCK
> +#ifdef CONFIG_32BIT
> +#define __ASM_SLLIW "slli\t"
> +#define __ASM_SRLIW "srli\t"
> +#else
> +#define __ASM_SLLIW "slliw\t"
> +#define __ASM_SRLIW "srliw\t"
> +#endif
> +
> +/*
> + * Ticket-based spin-locking.
> + */
> +static inline void arch_spin_lock(arch_spinlock_t *lock)
> +{
> + arch_spinlock_t lockval;
> + u32 tmp;
> +
> + asm volatile (
> + "1: lr.w %0, %2 \n"
> + " mv %1, %0 \n"
> + " addw %0, %0, %3 \n"
> + " sc.w %0, %0, %2 \n"
> + " bnez %0, 1b \n"
> + : "=&r" (tmp), "=&r" (lockval), "+A" (lock->lock)
> + : "r" (1 << TICKET_NEXT)
> + : "memory");
It's could be optimized by amoadd.w with Anup advice, and I'll update
it in the next patchset version:
diff --git a/arch/riscv/include/asm/spinlock.h
b/arch/riscv/include/asm/spinlock.h
index 90b7eaa950cf..435286ad342b 100644
--- a/arch/riscv/include/asm/spinlock.h
+++ b/arch/riscv/include/asm/spinlock.h
@@ -22,15 +22,10 @@
static inline void arch_spin_lock(arch_spinlock_t *lock)
{
arch_spinlock_t lockval;
- u32 tmp;
asm volatile (
- "1: lr.w %0, %2 \n"
- " mv %1, %0 \n"
- " addw %0, %0, %3 \n"
- " sc.w %0, %0, %2 \n"
- " bnez %0, 1b \n"
- : "=&r" (tmp), "=&r" (lockval), "+A" (lock->lock)
+ " amoadd.w %0, %2, %1 \n"
+ : "=&r" (lockval), "+A" (lock->lock)
: "r" (1 << TICKET_NEXT)
: "memory");
> +
> + smp_cond_load_acquire(&lock->tickets.owner,
> + VAL == lockval.tickets.next);
> +}
> +
> +static inline int arch_spin_trylock(arch_spinlock_t *lock)
> +{
> + u32 tmp, contended, res;
> +
> + do {
> + asm volatile (
> + " lr.w %0, %3 \n"
> + __ASM_SRLIW "%1, %0, %5 \n"
> + __ASM_SLLIW "%2, %0, %5 \n"
> + " or %1, %2, %1 \n"
> + " li %2, 0 \n"
> + " sub %1, %1, %0 \n"
> + " bnez %1, 1f \n"
> + " addw %0, %0, %4 \n"
> + " sc.w %2, %0, %3 \n"
> + "1: \n"
> + : "=&r" (tmp), "=&r" (contended), "=&r" (res),
> + "+A" (lock->lock)
> + : "r" (1 << TICKET_NEXT), "I" (TICKET_NEXT)
> + : "memory");
> + } while (res);
> +
> + if (!contended)
> + __atomic_acquire_fence();
> +
> + return !contended;
> +}
> +
> +static inline void arch_spin_unlock(arch_spinlock_t *lock)
> +{
> + smp_store_release(&lock->tickets.owner, lock->tickets.owner + 1);
> +}
> +
> +static inline int arch_spin_value_unlocked(arch_spinlock_t lock)
> +{
> + return lock.tickets.owner == lock.tickets.next;
> +}
> +
> +static inline int arch_spin_is_locked(arch_spinlock_t *lock)
> +{
> + return !arch_spin_value_unlocked(READ_ONCE(*lock));
> +}
> +
> +static inline int arch_spin_is_contended(arch_spinlock_t *lock)
> +{
> + struct __raw_tickets tickets = READ_ONCE(lock->tickets);
> +
> + return (tickets.next - tickets.owner) > 1;
> +}
> +#define arch_spin_is_contended arch_spin_is_contended
> +#else /* CONFIG_RISCV_TICKET_LOCK */
> #include <asm/qspinlock.h>
> +#endif /* CONFIG_RISCV_TICKET_LOCK */
> +
> #include <asm/qrwlock.h>
>
> #endif /* _ASM_RISCV_SPINLOCK_H */
> diff --git a/arch/riscv/include/asm/spinlock_types.h b/arch/riscv/include/asm/spinlock_types.h
> index d033a973f287..afbb19841d0f 100644
> --- a/arch/riscv/include/asm/spinlock_types.h
> +++ b/arch/riscv/include/asm/spinlock_types.h
> @@ -10,7 +10,24 @@
> # error "please don't include this file directly"
> #endif
>
> +#ifdef CONFIG_RISCV_TICKET_LOCK
> +#define TICKET_NEXT 16
> +
> +typedef struct {
> + union {
> + u32 lock;
> + struct __raw_tickets {
> + /* little endian */
> + u16 owner;
> + u16 next;
> + } tickets;
> + };
> +} arch_spinlock_t;
> +
> +#define __ARCH_SPIN_LOCK_UNLOCKED { { 0 } }
> +#else
> #include <asm-generic/qspinlock_types.h>
> +#endif
> #include <asm-generic/qrwlock_types.h>
>
> #endif /* _ASM_RISCV_SPINLOCK_TYPES_H */
> --
> 2.17.1
>
--
Best Regards
Guo Ren
ML: https://lore.kernel.org/linux-csky/
