diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2013-09-04 11:55:10 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2013-09-04 11:55:10 -0700 |
commit | 816434ec4a674fcdb3c2221a6dffdc8f34020550 (patch) | |
tree | 6b8a319171270b20bf1b2e1c98d333f47988553a /arch/x86/include/asm/spinlock.h | |
parent | f357a82048ff1e5645861475b014570e11ad1911 (diff) | |
parent | 36bd621337c91a1ecda588e5bbbae8dd9698bae7 (diff) | |
download | linux-stable-816434ec4a674fcdb3c2221a6dffdc8f34020550.tar.gz linux-stable-816434ec4a674fcdb3c2221a6dffdc8f34020550.tar.bz2 linux-stable-816434ec4a674fcdb3c2221a6dffdc8f34020550.zip |
Merge branch 'x86-spinlocks-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull x86 spinlock changes from Ingo Molnar:
"The biggest change here are paravirtualized ticket spinlocks (PV
spinlocks), which bring a nice speedup on various benchmarks.
The KVM host side will come to you via the KVM tree"
* 'x86-spinlocks-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
x86/kvm/guest: Fix sparse warning: "symbol 'klock_waiting' was not declared as static"
kvm: Paravirtual ticketlocks support for linux guests running on KVM hypervisor
kvm guest: Add configuration support to enable debug information for KVM Guests
kvm uapi: Add KICK_CPU and PV_UNHALT definition to uapi
xen, pvticketlock: Allow interrupts to be enabled while blocking
x86, ticketlock: Add slowpath logic
jump_label: Split jumplabel ratelimit
x86, pvticketlock: When paravirtualizing ticket locks, increment by 2
x86, pvticketlock: Use callee-save for lock_spinning
xen, pvticketlocks: Add xen_nopvspin parameter to disable xen pv ticketlocks
xen, pvticketlock: Xen implementation for PV ticket locks
xen: Defer spinlock setup until boot CPU setup
x86, ticketlock: Collapse a layer of functions
x86, ticketlock: Don't inline _spin_unlock when using paravirt spinlocks
x86, spinlock: Replace pv spinlocks with pv ticketlocks
Diffstat (limited to 'arch/x86/include/asm/spinlock.h')
-rw-r--r-- | arch/x86/include/asm/spinlock.h | 128 |
1 files changed, 87 insertions, 41 deletions
diff --git a/arch/x86/include/asm/spinlock.h b/arch/x86/include/asm/spinlock.h index e0e668422c75..bf156ded74b5 100644 --- a/arch/x86/include/asm/spinlock.h +++ b/arch/x86/include/asm/spinlock.h @@ -1,11 +1,14 @@ #ifndef _ASM_X86_SPINLOCK_H #define _ASM_X86_SPINLOCK_H +#include <linux/jump_label.h> #include <linux/atomic.h> #include <asm/page.h> #include <asm/processor.h> #include <linux/compiler.h> #include <asm/paravirt.h> +#include <asm/bitops.h> + /* * Your basic SMP spinlocks, allowing only a single CPU anywhere * @@ -34,6 +37,31 @@ # define UNLOCK_LOCK_PREFIX #endif +/* How long a lock should spin before we consider blocking */ +#define SPIN_THRESHOLD (1 << 15) + +extern struct static_key paravirt_ticketlocks_enabled; +static __always_inline bool static_key_false(struct static_key *key); + +#ifdef CONFIG_PARAVIRT_SPINLOCKS + +static inline void __ticket_enter_slowpath(arch_spinlock_t *lock) +{ + set_bit(0, (volatile unsigned long *)&lock->tickets.tail); +} + +#else /* !CONFIG_PARAVIRT_SPINLOCKS */ +static __always_inline void __ticket_lock_spinning(arch_spinlock_t *lock, + __ticket_t ticket) +{ +} +static inline void __ticket_unlock_kick(arch_spinlock_t *lock, + __ticket_t ticket) +{ +} + +#endif /* CONFIG_PARAVIRT_SPINLOCKS */ + static __always_inline int arch_spin_value_unlocked(arch_spinlock_t lock) { return lock.tickets.head == lock.tickets.tail; @@ -52,81 +80,101 @@ static __always_inline int arch_spin_value_unlocked(arch_spinlock_t lock) * in the high part, because a wide xadd increment of the low part would carry * up and contaminate the high part. */ -static __always_inline void __ticket_spin_lock(arch_spinlock_t *lock) +static __always_inline void arch_spin_lock(arch_spinlock_t *lock) { - register struct __raw_tickets inc = { .tail = 1 }; + register struct __raw_tickets inc = { .tail = TICKET_LOCK_INC }; inc = xadd(&lock->tickets, inc); + if (likely(inc.head == inc.tail)) + goto out; + inc.tail &= ~TICKET_SLOWPATH_FLAG; for (;;) { - if (inc.head == inc.tail) - break; - cpu_relax(); - inc.head = ACCESS_ONCE(lock->tickets.head); + unsigned count = SPIN_THRESHOLD; + + do { + if (ACCESS_ONCE(lock->tickets.head) == inc.tail) + goto out; + cpu_relax(); + } while (--count); + __ticket_lock_spinning(lock, inc.tail); } - barrier(); /* make sure nothing creeps before the lock is taken */ +out: barrier(); /* make sure nothing creeps before the lock is taken */ } -static __always_inline int __ticket_spin_trylock(arch_spinlock_t *lock) +static __always_inline int arch_spin_trylock(arch_spinlock_t *lock) { arch_spinlock_t old, new; old.tickets = ACCESS_ONCE(lock->tickets); - if (old.tickets.head != old.tickets.tail) + if (old.tickets.head != (old.tickets.tail & ~TICKET_SLOWPATH_FLAG)) return 0; - new.head_tail = old.head_tail + (1 << TICKET_SHIFT); + new.head_tail = old.head_tail + (TICKET_LOCK_INC << TICKET_SHIFT); /* cmpxchg is a full barrier, so nothing can move before it */ return cmpxchg(&lock->head_tail, old.head_tail, new.head_tail) == old.head_tail; } -static __always_inline void __ticket_spin_unlock(arch_spinlock_t *lock) +static inline void __ticket_unlock_slowpath(arch_spinlock_t *lock, + arch_spinlock_t old) { - __add(&lock->tickets.head, 1, UNLOCK_LOCK_PREFIX); + arch_spinlock_t new; + + BUILD_BUG_ON(((__ticket_t)NR_CPUS) != NR_CPUS); + + /* Perform the unlock on the "before" copy */ + old.tickets.head += TICKET_LOCK_INC; + + /* Clear the slowpath flag */ + new.head_tail = old.head_tail & ~(TICKET_SLOWPATH_FLAG << TICKET_SHIFT); + + /* + * If the lock is uncontended, clear the flag - use cmpxchg in + * case it changes behind our back though. + */ + if (new.tickets.head != new.tickets.tail || + cmpxchg(&lock->head_tail, old.head_tail, + new.head_tail) != old.head_tail) { + /* + * Lock still has someone queued for it, so wake up an + * appropriate waiter. + */ + __ticket_unlock_kick(lock, old.tickets.head); + } } -static inline int __ticket_spin_is_locked(arch_spinlock_t *lock) +static __always_inline void arch_spin_unlock(arch_spinlock_t *lock) { - struct __raw_tickets tmp = ACCESS_ONCE(lock->tickets); + if (TICKET_SLOWPATH_FLAG && + static_key_false(¶virt_ticketlocks_enabled)) { + arch_spinlock_t prev; - return tmp.tail != tmp.head; -} + prev = *lock; + add_smp(&lock->tickets.head, TICKET_LOCK_INC); -static inline int __ticket_spin_is_contended(arch_spinlock_t *lock) -{ - struct __raw_tickets tmp = ACCESS_ONCE(lock->tickets); + /* add_smp() is a full mb() */ - return (__ticket_t)(tmp.tail - tmp.head) > 1; + if (unlikely(lock->tickets.tail & TICKET_SLOWPATH_FLAG)) + __ticket_unlock_slowpath(lock, prev); + } else + __add(&lock->tickets.head, TICKET_LOCK_INC, UNLOCK_LOCK_PREFIX); } -#ifndef CONFIG_PARAVIRT_SPINLOCKS - static inline int arch_spin_is_locked(arch_spinlock_t *lock) { - return __ticket_spin_is_locked(lock); -} - -static inline int arch_spin_is_contended(arch_spinlock_t *lock) -{ - return __ticket_spin_is_contended(lock); -} -#define arch_spin_is_contended arch_spin_is_contended + struct __raw_tickets tmp = ACCESS_ONCE(lock->tickets); -static __always_inline void arch_spin_lock(arch_spinlock_t *lock) -{ - __ticket_spin_lock(lock); + return tmp.tail != tmp.head; } -static __always_inline int arch_spin_trylock(arch_spinlock_t *lock) +static inline int arch_spin_is_contended(arch_spinlock_t *lock) { - return __ticket_spin_trylock(lock); -} + struct __raw_tickets tmp = ACCESS_ONCE(lock->tickets); -static __always_inline void arch_spin_unlock(arch_spinlock_t *lock) -{ - __ticket_spin_unlock(lock); + return (__ticket_t)(tmp.tail - tmp.head) > TICKET_LOCK_INC; } +#define arch_spin_is_contended arch_spin_is_contended static __always_inline void arch_spin_lock_flags(arch_spinlock_t *lock, unsigned long flags) @@ -134,8 +182,6 @@ static __always_inline void arch_spin_lock_flags(arch_spinlock_t *lock, arch_spin_lock(lock); } -#endif /* CONFIG_PARAVIRT_SPINLOCKS */ - static inline void arch_spin_unlock_wait(arch_spinlock_t *lock) { while (arch_spin_is_locked(lock)) |