Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1752733Ab2EBKGw (ORCPT ); Wed, 2 May 2012 06:06:52 -0400 Received: from e23smtp04.au.ibm.com ([202.81.31.146]:55710 "EHLO e23smtp04.au.ibm.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752356Ab2EBKGt (ORCPT ); Wed, 2 May 2012 06:06:49 -0400 From: Raghavendra K T To: Jeremy Fitzhardinge , Greg Kroah-Hartman , Konrad Rzeszutek Wilk , "H. Peter Anvin" , Avi Kivity , X86 , Gleb Natapov , Ingo Molnar , Marcelo Tosatti Cc: Attilio Rao , Srivatsa Vaddagiri , linux-doc@vger.kernel.org, Virtualization , Xen Devel , Linus Torvalds , KVM , Andi Kleen , Raghavendra K T , Stefano Stabellini , Stephan Diestelhorst , LKML Date: Wed, 02 May 2012 15:36:25 +0530 Message-Id: <20120502100625.13206.42167.sendpatchset@codeblue.in.ibm.com> In-Reply-To: <20120502100610.13206.40.sendpatchset@codeblue.in.ibm.com> References: <20120502100610.13206.40.sendpatchset@codeblue.in.ibm.com> Subject: [PATCH RFC V8 1/17] x86/spinlock: Replace pv spinlocks with pv ticketlocks x-cbid: 12050123-9264-0000-0000-000001604C33 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 10418 Lines: 305 From: Jeremy Fitzhardinge Rather than outright replacing the entire spinlock implementation in order to paravirtualize it, keep the ticket lock implementation but add a couple of pvops hooks on the slow patch (long spin on lock, unlocking a contended lock). Ticket locks have a number of nice properties, but they also have some surprising behaviours in virtual environments. They enforce a strict FIFO ordering on cpus trying to take a lock; however, if the hypervisor scheduler does not schedule the cpus in the correct order, the system can waste a huge amount of time spinning until the next cpu can take the lock. (See Thomas Friebel's talk "Prevent Guests from Spinning Around" http://www.xen.org/files/xensummitboston08/LHP.pdf for more details.) To address this, we add two hooks: - __ticket_spin_lock which is called after the cpu has been spinning on the lock for a significant number of iterations but has failed to take the lock (presumably because the cpu holding the lock has been descheduled). The lock_spinning pvop is expected to block the cpu until it has been kicked by the current lock holder. - __ticket_spin_unlock, which on releasing a contended lock (there are more cpus with tail tickets), it looks to see if the next cpu is blocked and wakes it if so. When compiled with CONFIG_PARAVIRT_SPINLOCKS disabled, a set of stub functions causes all the extra code to go away. Signed-off-by: Jeremy Fitzhardinge Reviewed-by: Konrad Rzeszutek Wilk Tested-by: Attilio Rao Signed-off-by: Raghavendra K T --- arch/x86/include/asm/paravirt.h | 32 ++++---------------- arch/x86/include/asm/paravirt_types.h | 10 ++---- arch/x86/include/asm/spinlock.h | 53 ++++++++++++++++++++++++++------ arch/x86/include/asm/spinlock_types.h | 4 -- arch/x86/kernel/paravirt-spinlocks.c | 15 +-------- arch/x86/xen/spinlock.c | 8 ++++- 6 files changed, 61 insertions(+), 61 deletions(-) diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h index aa0f913..4bcd146 100644 --- a/arch/x86/include/asm/paravirt.h +++ b/arch/x86/include/asm/paravirt.h @@ -751,36 +751,16 @@ static inline void __set_fixmap(unsigned /* enum fixed_addresses */ idx, #if defined(CONFIG_SMP) && defined(CONFIG_PARAVIRT_SPINLOCKS) -static inline int arch_spin_is_locked(struct arch_spinlock *lock) +static __always_inline void __ticket_lock_spinning(struct arch_spinlock *lock, + __ticket_t ticket) { - return PVOP_CALL1(int, pv_lock_ops.spin_is_locked, lock); + PVOP_VCALL2(pv_lock_ops.lock_spinning, lock, ticket); } -static inline int arch_spin_is_contended(struct arch_spinlock *lock) +static __always_inline void ____ticket_unlock_kick(struct arch_spinlock *lock, + __ticket_t ticket) { - return PVOP_CALL1(int, pv_lock_ops.spin_is_contended, lock); -} -#define arch_spin_is_contended arch_spin_is_contended - -static __always_inline void arch_spin_lock(struct arch_spinlock *lock) -{ - PVOP_VCALL1(pv_lock_ops.spin_lock, lock); -} - -static __always_inline void arch_spin_lock_flags(struct arch_spinlock *lock, - unsigned long flags) -{ - PVOP_VCALL2(pv_lock_ops.spin_lock_flags, lock, flags); -} - -static __always_inline int arch_spin_trylock(struct arch_spinlock *lock) -{ - return PVOP_CALL1(int, pv_lock_ops.spin_trylock, lock); -} - -static __always_inline void arch_spin_unlock(struct arch_spinlock *lock) -{ - PVOP_VCALL1(pv_lock_ops.spin_unlock, lock); + PVOP_VCALL2(pv_lock_ops.unlock_kick, lock, ticket); } #endif diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h index 8e8b9a4..005e24d 100644 --- a/arch/x86/include/asm/paravirt_types.h +++ b/arch/x86/include/asm/paravirt_types.h @@ -327,13 +327,11 @@ struct pv_mmu_ops { }; struct arch_spinlock; +#include + struct pv_lock_ops { - int (*spin_is_locked)(struct arch_spinlock *lock); - int (*spin_is_contended)(struct arch_spinlock *lock); - void (*spin_lock)(struct arch_spinlock *lock); - void (*spin_lock_flags)(struct arch_spinlock *lock, unsigned long flags); - int (*spin_trylock)(struct arch_spinlock *lock); - void (*spin_unlock)(struct arch_spinlock *lock); + void (*lock_spinning)(struct arch_spinlock *lock, __ticket_t ticket); + void (*unlock_kick)(struct arch_spinlock *lock, __ticket_t ticket); }; /* This contains all the paravirt structures: we get a convenient diff --git a/arch/x86/include/asm/spinlock.h b/arch/x86/include/asm/spinlock.h index 76bfa2c..3e47608 100644 --- a/arch/x86/include/asm/spinlock.h +++ b/arch/x86/include/asm/spinlock.h @@ -37,6 +37,35 @@ # define UNLOCK_LOCK_PREFIX #endif +/* How long a lock should spin before we consider blocking */ +#define SPIN_THRESHOLD (1 << 11) + +#ifndef CONFIG_PARAVIRT_SPINLOCKS + +static __always_inline void __ticket_lock_spinning(struct arch_spinlock *lock, + __ticket_t ticket) +{ +} + +static __always_inline void ____ticket_unlock_kick(struct arch_spinlock *lock, + __ticket_t ticket) +{ +} + +#endif /* CONFIG_PARAVIRT_SPINLOCKS */ + + +/* + * If a spinlock has someone waiting on it, then kick the appropriate + * waiting cpu. + */ +static __always_inline void __ticket_unlock_kick(struct arch_spinlock *lock, + __ticket_t next) +{ + if (unlikely(lock->tickets.tail != next)) + ____ticket_unlock_kick(lock, next); +} + /* * Ticket locks are conceptually two parts, one indicating the current head of * the queue, and the other indicating the current tail. The lock is acquired @@ -50,19 +79,24 @@ * 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 __ticket_spin_lock(struct arch_spinlock *lock) { register struct __raw_tickets inc = { .tail = 1 }; inc = xadd(&lock->tickets, inc); for (;;) { - if (inc.head == inc.tail) - break; - cpu_relax(); - inc.head = ACCESS_ONCE(lock->tickets.head); + unsigned count = SPIN_THRESHOLD; + + do { + if (inc.head == inc.tail) + goto out; + cpu_relax(); + inc.head = ACCESS_ONCE(lock->tickets.head); + } 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) @@ -81,7 +115,10 @@ static __always_inline int __ticket_spin_trylock(arch_spinlock_t *lock) static __always_inline void __ticket_spin_unlock(arch_spinlock_t *lock) { + __ticket_t next = lock->tickets.head + 1; + __add(&lock->tickets.head, 1, UNLOCK_LOCK_PREFIX); + __ticket_unlock_kick(lock, next); } static inline int __ticket_spin_is_locked(arch_spinlock_t *lock) @@ -98,8 +135,6 @@ static inline int __ticket_spin_is_contended(arch_spinlock_t *lock) return (__ticket_t)(tmp.tail - tmp.head) > 1; } -#ifndef CONFIG_PARAVIRT_SPINLOCKS - static inline int arch_spin_is_locked(arch_spinlock_t *lock) { return __ticket_spin_is_locked(lock); @@ -132,8 +167,6 @@ 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)) diff --git a/arch/x86/include/asm/spinlock_types.h b/arch/x86/include/asm/spinlock_types.h index ad0ad07..83fd3c7 100644 --- a/arch/x86/include/asm/spinlock_types.h +++ b/arch/x86/include/asm/spinlock_types.h @@ -1,10 +1,6 @@ #ifndef _ASM_X86_SPINLOCK_TYPES_H #define _ASM_X86_SPINLOCK_TYPES_H -#ifndef __LINUX_SPINLOCK_TYPES_H -# error "please don't include this file directly" -#endif - #include #if (CONFIG_NR_CPUS < 256) diff --git a/arch/x86/kernel/paravirt-spinlocks.c b/arch/x86/kernel/paravirt-spinlocks.c index 676b8c7..c2e010e 100644 --- a/arch/x86/kernel/paravirt-spinlocks.c +++ b/arch/x86/kernel/paravirt-spinlocks.c @@ -7,21 +7,10 @@ #include -static inline void -default_spin_lock_flags(arch_spinlock_t *lock, unsigned long flags) -{ - arch_spin_lock(lock); -} - struct pv_lock_ops pv_lock_ops = { #ifdef CONFIG_SMP - .spin_is_locked = __ticket_spin_is_locked, - .spin_is_contended = __ticket_spin_is_contended, - - .spin_lock = __ticket_spin_lock, - .spin_lock_flags = default_spin_lock_flags, - .spin_trylock = __ticket_spin_trylock, - .spin_unlock = __ticket_spin_unlock, + .lock_spinning = paravirt_nop, + .unlock_kick = paravirt_nop, #endif }; EXPORT_SYMBOL(pv_lock_ops); diff --git a/arch/x86/xen/spinlock.c b/arch/x86/xen/spinlock.c index 00461a4..f1f4540 100644 --- a/arch/x86/xen/spinlock.c +++ b/arch/x86/xen/spinlock.c @@ -138,6 +138,9 @@ struct xen_spinlock { xen_spinners_t spinners; /* count of waiting cpus */ }; +static DEFINE_PER_CPU(int, lock_kicker_irq) = -1; + +#if 0 static int xen_spin_is_locked(struct arch_spinlock *lock) { struct xen_spinlock *xl = (struct xen_spinlock *)lock; @@ -165,7 +168,6 @@ static int xen_spin_trylock(struct arch_spinlock *lock) return old == 0; } -static DEFINE_PER_CPU(int, lock_kicker_irq) = -1; static DEFINE_PER_CPU(struct xen_spinlock *, lock_spinners); /* @@ -353,6 +355,7 @@ static void xen_spin_unlock(struct arch_spinlock *lock) if (unlikely(xl->spinners)) xen_spin_unlock_slow(xl); } +#endif static irqreturn_t dummy_handler(int irq, void *dev_id) { @@ -389,13 +392,14 @@ void xen_uninit_lock_cpu(int cpu) void __init xen_init_spinlocks(void) { BUILD_BUG_ON(sizeof(struct xen_spinlock) > sizeof(arch_spinlock_t)); - +#if 0 pv_lock_ops.spin_is_locked = xen_spin_is_locked; pv_lock_ops.spin_is_contended = xen_spin_is_contended; pv_lock_ops.spin_lock = xen_spin_lock; pv_lock_ops.spin_lock_flags = xen_spin_lock_flags; pv_lock_ops.spin_trylock = xen_spin_trylock; pv_lock_ops.spin_unlock = xen_spin_unlock; +#endif } #ifdef CONFIG_XEN_DEBUG_FS -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/