diff options
author | Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com> | 2011-11-08 23:15:17 -0800 |
---|---|---|
committer | Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com> | 2011-11-08 23:15:17 -0800 |
commit | cf55b8419d76ce015ea5ec1ad2a002a546ad48f2 (patch) | |
tree | 76a8d3d13f5718a1315f63086ed6adc7dbdfd042 | |
parent | 1ea6b8f48918282bdca0b32a34095504ee65bab5 (diff) | |
parent | 600bd2872f3265a393a46ad96942f93a4467b062 (diff) | |
download | xen-cf55b8419d76ce015ea5ec1ad2a002a546ad48f2.tar.gz |
Merge branch 'upstream/pvticketlock-slowflag' into xen/next-3.2
* upstream/pvticketlock-slowflag:
xen: enable PV ticketlocks on HVM Xen
xen/pvticketlock: allow interrupts to be enabled while blocking
x86/ticketlock: add slowpath logic
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
x86/cmpxchg: add a locked add() helper
-rw-r--r-- | arch/x86/Kconfig | 3 | ||||
-rw-r--r-- | arch/x86/include/asm/cmpxchg.h | 42 | ||||
-rw-r--r-- | arch/x86/include/asm/paravirt.h | 30 | ||||
-rw-r--r-- | arch/x86/include/asm/paravirt_types.h | 10 | ||||
-rw-r--r-- | arch/x86/include/asm/spinlock.h | 139 | ||||
-rw-r--r-- | arch/x86/include/asm/spinlock_types.h | 16 | ||||
-rw-r--r-- | arch/x86/kernel/paravirt-spinlocks.c | 18 | ||||
-rw-r--r-- | arch/x86/xen/smp.c | 3 | ||||
-rw-r--r-- | arch/x86/xen/spinlock.c | 331 | ||||
-rw-r--r-- | kernel/Kconfig.locks | 2 |
10 files changed, 252 insertions, 342 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index cb9a1044a771b..5d8152d772526 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -584,6 +584,9 @@ config PARAVIRT_SPINLOCKS If you are unsure how to answer this question, answer N. +config ARCH_NOINLINE_SPIN_UNLOCK + def_bool PARAVIRT_SPINLOCKS + config PARAVIRT_CLOCK bool diff --git a/arch/x86/include/asm/cmpxchg.h b/arch/x86/include/asm/cmpxchg.h index 5d3acdf5a7a68..49eade13161cd 100644 --- a/arch/x86/include/asm/cmpxchg.h +++ b/arch/x86/include/asm/cmpxchg.h @@ -14,6 +14,8 @@ extern void __cmpxchg_wrong_size(void) __compiletime_error("Bad argument size for cmpxchg"); extern void __xadd_wrong_size(void) __compiletime_error("Bad argument size for xadd"); +extern void __add_wrong_size(void) + __compiletime_error("Bad argument size for add"); /* * Constants for operation sizes. On 32-bit, the 64-bit size it set to @@ -207,4 +209,44 @@ extern void __xadd_wrong_size(void) #define xadd_sync(ptr, inc) __xadd((ptr), (inc), "lock; ") #define xadd_local(ptr, inc) __xadd((ptr), (inc), "") +#define __add(ptr, inc, lock) \ + ({ \ + __typeof__ (*(ptr)) __ret = (inc); \ + switch (sizeof(*(ptr))) { \ + case __X86_CASE_B: \ + asm volatile (lock "addb %b1, %0\n" \ + : "+m" (*(ptr)) : "ri" (inc) \ + : "memory", "cc"); \ + break; \ + case __X86_CASE_W: \ + asm volatile (lock "addw %w1, %0\n" \ + : "+m" (*(ptr)) : "ri" (inc) \ + : "memory", "cc"); \ + break; \ + case __X86_CASE_L: \ + asm volatile (lock "addl %1, %0\n" \ + : "+m" (*(ptr)) : "ri" (inc) \ + : "memory", "cc"); \ + break; \ + case __X86_CASE_Q: \ + asm volatile (lock "addq %1, %0\n" \ + : "+m" (*(ptr)) : "ri" (inc) \ + : "memory", "cc"); \ + break; \ + default: \ + __add_wrong_size(); \ + } \ + __ret; \ + }) + +/* + * add_*() adds "inc" to "*ptr" + * + * __add() takes a lock prefix + * add_smp() is locked when multiple CPUs are online + * add_sync() is always locked + */ +#define add_smp(ptr, inc) __add((ptr), (inc), LOCK_PREFIX) +#define add_sync(ptr, inc) __add((ptr), (inc), "lock; ") + #endif /* ASM_X86_CMPXCHG_H */ diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h index a7d2db9a74fbc..13b3d8b13c930 100644 --- a/arch/x86/include/asm/paravirt.h +++ b/arch/x86/include/asm/paravirt.h @@ -750,36 +750,14 @@ 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_VCALLEE2(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 8e8b9a4987ee0..5e0c1386a2741 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 <asm/spinlock_types.h> + 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); + struct paravirt_callee_save lock_spinning; + 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 972c260919a39..8e0b9cfa45ba9 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 * @@ -37,6 +40,30 @@ # define UNLOCK_LOCK_PREFIX #endif +/* How long a lock should spin before we consider blocking */ +#define SPIN_THRESHOLD (1 << 11) + +extern struct jump_label_key paravirt_ticketlocks_enabled; + +#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 */ + + /* * 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 @@ -50,94 +77,100 @@ * 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; } -#if (NR_CPUS < 256) -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) { - asm volatile(UNLOCK_LOCK_PREFIX "incb %0" - : "+m" (lock->head_tail) - : - : "memory", "cc"); -} -#else -static __always_inline void __ticket_spin_unlock(arch_spinlock_t *lock) -{ - asm volatile(UNLOCK_LOCK_PREFIX "incw %0" - : "+m" (lock->head_tail) - : - : "memory", "cc"); + 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); + } } -#endif -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 && + unlikely(static_branch(¶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 ((tmp.tail - tmp.head) & TICKET_MASK) > 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 ((tmp.tail - tmp.head) & TICKET_MASK) > 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) @@ -145,8 +178,6 @@ 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 8ebd5df7451e2..407f7f7f28609 100644 --- a/arch/x86/include/asm/spinlock_types.h +++ b/arch/x86/include/asm/spinlock_types.h @@ -1,13 +1,17 @@ #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 <linux/types.h> -#if (CONFIG_NR_CPUS < 256) +#ifdef CONFIG_PARAVIRT_SPINLOCKS +#define __TICKET_LOCK_INC 2 +#define TICKET_SLOWPATH_FLAG ((__ticket_t)1) +#else +#define __TICKET_LOCK_INC 1 +#define TICKET_SLOWPATH_FLAG ((__ticket_t)0) +#endif + +#if (CONFIG_NR_CPUS < (256 / __TICKET_LOCK_INC)) typedef u8 __ticket_t; typedef u16 __ticketpair_t; #else @@ -15,6 +19,8 @@ typedef u16 __ticket_t; typedef u32 __ticketpair_t; #endif +#define TICKET_LOCK_INC ((__ticket_t)__TICKET_LOCK_INC) + #define TICKET_SHIFT (sizeof(__ticket_t) * 8) #define TICKET_MASK ((__ticket_t)((1 << TICKET_SHIFT) - 1)) diff --git a/arch/x86/kernel/paravirt-spinlocks.c b/arch/x86/kernel/paravirt-spinlocks.c index 676b8c77a9761..6ca1d333b67a9 100644 --- a/arch/x86/kernel/paravirt-spinlocks.c +++ b/arch/x86/kernel/paravirt-spinlocks.c @@ -4,25 +4,17 @@ */ #include <linux/spinlock.h> #include <linux/module.h> +#include <linux/jump_label.h> #include <asm/paravirt.h> -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 = __PV_IS_CALLEE_SAVE(paravirt_nop), + .unlock_kick = paravirt_nop, #endif }; EXPORT_SYMBOL(pv_lock_ops); +struct jump_label_key paravirt_ticketlocks_enabled = JUMP_LABEL_INIT; +EXPORT_SYMBOL(paravirt_ticketlocks_enabled); diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c index 041d4fe9dfe4b..02b70ac3c92cd 100644 --- a/arch/x86/xen/smp.c +++ b/arch/x86/xen/smp.c @@ -201,6 +201,7 @@ static void __init xen_smp_prepare_boot_cpu(void) xen_filter_cpu_maps(); xen_setup_vcpu_info_placement(); + xen_init_spinlocks(); } static void __init xen_smp_prepare_cpus(unsigned int max_cpus) @@ -523,7 +524,6 @@ void __init xen_smp_init(void) { smp_ops = xen_smp_ops; xen_fill_possible_map(); - xen_init_spinlocks(); } static void __init xen_hvm_smp_prepare_cpus(unsigned int max_cpus) @@ -561,4 +561,5 @@ void __init xen_hvm_smp_init(void) smp_ops.cpu_die = xen_hvm_cpu_die; smp_ops.send_call_func_ipi = xen_smp_send_call_function_ipi; smp_ops.send_call_func_single_ipi = xen_smp_send_call_function_single_ipi; + xen_init_spinlocks(); } diff --git a/arch/x86/xen/spinlock.c b/arch/x86/xen/spinlock.c index cc9b1e182fcfa..fc506e647c4f8 100644 --- a/arch/x86/xen/spinlock.c +++ b/arch/x86/xen/spinlock.c @@ -19,32 +19,21 @@ #ifdef CONFIG_XEN_DEBUG_FS static struct xen_spinlock_stats { - u64 taken; u32 taken_slow; - u32 taken_slow_nested; u32 taken_slow_pickup; u32 taken_slow_spurious; - u32 taken_slow_irqenable; - u64 released; u32 released_slow; u32 released_slow_kicked; #define HISTO_BUCKETS 30 - u32 histo_spin_total[HISTO_BUCKETS+1]; - u32 histo_spin_spinning[HISTO_BUCKETS+1]; u32 histo_spin_blocked[HISTO_BUCKETS+1]; - u64 time_total; - u64 time_spinning; u64 time_blocked; } spinlock_stats; static u8 zero_stats; -static unsigned lock_timeout = 1 << 10; -#define TIMEOUT lock_timeout - static inline void check_zero(void) { if (unlikely(zero_stats)) { @@ -73,22 +62,6 @@ static void __spin_time_accum(u64 delta, u32 *array) array[HISTO_BUCKETS]++; } -static inline void spin_time_accum_spinning(u64 start) -{ - u32 delta = xen_clocksource_read() - start; - - __spin_time_accum(delta, spinlock_stats.histo_spin_spinning); - spinlock_stats.time_spinning += delta; -} - -static inline void spin_time_accum_total(u64 start) -{ - u32 delta = xen_clocksource_read() - start; - - __spin_time_accum(delta, spinlock_stats.histo_spin_total); - spinlock_stats.time_total += delta; -} - static inline void spin_time_accum_blocked(u64 start) { u32 delta = xen_clocksource_read() - start; @@ -105,212 +78,123 @@ static inline u64 spin_time_start(void) return 0; } -static inline void spin_time_accum_total(u64 start) -{ -} -static inline void spin_time_accum_spinning(u64 start) -{ -} static inline void spin_time_accum_blocked(u64 start) { } #endif /* CONFIG_XEN_DEBUG_FS */ -struct xen_spinlock { - unsigned char lock; /* 0 -> free; 1 -> locked */ - unsigned short spinners; /* count of waiting cpus */ +struct xen_lock_waiting { + struct arch_spinlock *lock; + __ticket_t want; }; -static int xen_spin_is_locked(struct arch_spinlock *lock) -{ - struct xen_spinlock *xl = (struct xen_spinlock *)lock; - - return xl->lock != 0; -} - -static int xen_spin_is_contended(struct arch_spinlock *lock) -{ - struct xen_spinlock *xl = (struct xen_spinlock *)lock; - - /* Not strictly true; this is only the count of contended - lock-takers entering the slow path. */ - return xl->spinners != 0; -} - -static int xen_spin_trylock(struct arch_spinlock *lock) -{ - struct xen_spinlock *xl = (struct xen_spinlock *)lock; - u8 old = 1; - - asm("xchgb %b0,%1" - : "+q" (old), "+m" (xl->lock) : : "memory"); - - return old == 0; -} - static DEFINE_PER_CPU(int, lock_kicker_irq) = -1; -static DEFINE_PER_CPU(struct xen_spinlock *, lock_spinners); +static DEFINE_PER_CPU(struct xen_lock_waiting, lock_waiting); +static cpumask_t waiting_cpus; -/* - * Mark a cpu as interested in a lock. Returns the CPU's previous - * lock of interest, in case we got preempted by an interrupt. - */ -static inline struct xen_spinlock *spinning_lock(struct xen_spinlock *xl) +static void xen_lock_spinning(struct arch_spinlock *lock, __ticket_t want) { - struct xen_spinlock *prev; - - prev = __this_cpu_read(lock_spinners); - __this_cpu_write(lock_spinners, xl); - - wmb(); /* set lock of interest before count */ - - asm(LOCK_PREFIX " incw %0" - : "+m" (xl->spinners) : : "memory"); - - return prev; -} - -/* - * Mark a cpu as no longer interested in a lock. Restores previous - * lock of interest (NULL for none). - */ -static inline void unspinning_lock(struct xen_spinlock *xl, struct xen_spinlock *prev) -{ - asm(LOCK_PREFIX " decw %0" - : "+m" (xl->spinners) : : "memory"); - wmb(); /* decrement count before restoring lock */ - __this_cpu_write(lock_spinners, prev); -} - -static noinline int xen_spin_lock_slow(struct arch_spinlock *lock, bool irq_enable) -{ - struct xen_spinlock *xl = (struct xen_spinlock *)lock; - struct xen_spinlock *prev; int irq = __this_cpu_read(lock_kicker_irq); - int ret; + struct xen_lock_waiting *w = &__get_cpu_var(lock_waiting); + int cpu = smp_processor_id(); u64 start; + unsigned long flags; /* If kicker interrupts not initialized yet, just spin */ if (irq == -1) - return 0; + return; start = spin_time_start(); - /* announce we're spinning */ - prev = spinning_lock(xl); - - ADD_STATS(taken_slow, 1); - ADD_STATS(taken_slow_nested, prev != NULL); - - do { - unsigned long flags; - - /* clear pending */ - xen_clear_irq_pending(irq); - - /* check again make sure it didn't become free while - we weren't looking */ - ret = xen_spin_trylock(lock); - if (ret) { - ADD_STATS(taken_slow_pickup, 1); - - /* - * If we interrupted another spinlock while it - * was blocking, make sure it doesn't block - * without rechecking the lock. - */ - if (prev != NULL) - xen_set_irq_pending(irq); - goto out; - } - - flags = arch_local_save_flags(); - if (irq_enable) { - ADD_STATS(taken_slow_irqenable, 1); - raw_local_irq_enable(); - } - - /* - * Block until irq becomes pending. If we're - * interrupted at this point (after the trylock but - * before entering the block), then the nested lock - * handler guarantees that the irq will be left - * pending if there's any chance the lock became free; - * xen_poll_irq() returns immediately if the irq is - * pending. - */ - xen_poll_irq(irq); + /* + * Make sure an interrupt handler can't upset things in a + * partially setup state. + */ + local_irq_save(flags); - raw_local_irq_restore(flags); + /* + * We don't really care if we're overwriting some other + * (lock,want) pair, as that would mean that we're currently + * in an interrupt context, and the outer context had + * interrupts enabled. That has already kicked the VCPU out + * of xen_poll_irq(), so it will just return spuriously and + * retry with newly setup (lock,want). + * + * The ordering protocol on this is that the "lock" pointer + * may only be set non-NULL if the "want" ticket is correct. + * If we're updating "want", we must first clear "lock". + */ + w->lock = NULL; + smp_wmb(); + w->want = want; + smp_wmb(); + w->lock = lock; - ADD_STATS(taken_slow_spurious, !xen_test_irq_pending(irq)); - } while (!xen_test_irq_pending(irq)); /* check for spurious wakeups */ + /* This uses set_bit, which atomic and therefore a barrier */ + cpumask_set_cpu(cpu, &waiting_cpus); - kstat_incr_irqs_this_cpu(irq, irq_to_desc(irq)); + ADD_STATS(taken_slow, 1); -out: - unspinning_lock(xl, prev); - spin_time_accum_blocked(start); + /* clear pending */ + xen_clear_irq_pending(irq); - return ret; -} + /* Only check lock once pending cleared */ + barrier(); -static inline void __xen_spin_lock(struct arch_spinlock *lock, bool irq_enable) -{ - struct xen_spinlock *xl = (struct xen_spinlock *)lock; - unsigned timeout; - u8 oldval; - u64 start_spin; - - ADD_STATS(taken, 1); + /* + * Mark entry to slowpath before doing the pickup test to make + * sure we don't deadlock with an unlocker. + */ + __ticket_enter_slowpath(lock); - start_spin = spin_time_start(); + /* + * check again make sure it didn't become free while + * we weren't looking + */ + if (ACCESS_ONCE(lock->tickets.head) == want) { + ADD_STATS(taken_slow_pickup, 1); + goto out; + } - do { - u64 start_spin_fast = spin_time_start(); + /* Allow interrupts while blocked */ + local_irq_restore(flags); - timeout = TIMEOUT; + /* + * If an interrupt happens here, it will leave the wakeup irq + * pending, which will cause xen_poll_irq() to return + * immediately. + */ - asm("1: xchgb %1,%0\n" - " testb %1,%1\n" - " jz 3f\n" - "2: rep;nop\n" - " cmpb $0,%0\n" - " je 1b\n" - " dec %2\n" - " jnz 2b\n" - "3:\n" - : "+m" (xl->lock), "=q" (oldval), "+r" (timeout) - : "1" (1) - : "memory"); + /* Block until irq becomes pending (or perhaps a spurious wakeup) */ + xen_poll_irq(irq); + ADD_STATS(taken_slow_spurious, !xen_test_irq_pending(irq)); - spin_time_accum_spinning(start_spin_fast); + local_irq_save(flags); - } while (unlikely(oldval != 0 && - (TIMEOUT == ~0 || !xen_spin_lock_slow(lock, irq_enable)))); + kstat_incr_irqs_this_cpu(irq, irq_to_desc(irq)); - spin_time_accum_total(start_spin); -} +out: + cpumask_clear_cpu(cpu, &waiting_cpus); + w->lock = NULL; -static void xen_spin_lock(struct arch_spinlock *lock) -{ - __xen_spin_lock(lock, false); -} + local_irq_restore(flags); -static void xen_spin_lock_flags(struct arch_spinlock *lock, unsigned long flags) -{ - __xen_spin_lock(lock, !raw_irqs_disabled_flags(flags)); + spin_time_accum_blocked(start); } +PV_CALLEE_SAVE_REGS_THUNK(xen_lock_spinning); -static noinline void xen_spin_unlock_slow(struct xen_spinlock *xl) +static void xen_unlock_kick(struct arch_spinlock *lock, __ticket_t next) { int cpu; ADD_STATS(released_slow, 1); - for_each_online_cpu(cpu) { - /* XXX should mix up next cpu selection */ - if (per_cpu(lock_spinners, cpu) == xl) { + for_each_cpu(cpu, &waiting_cpus) { + const struct xen_lock_waiting *w = &per_cpu(lock_waiting, cpu); + + /* Make sure we read lock before want */ + if (ACCESS_ONCE(w->lock) == lock && + ACCESS_ONCE(w->want) == next) { ADD_STATS(released_slow_kicked, 1); xen_send_IPI_one(cpu, XEN_SPIN_UNLOCK_VECTOR); break; @@ -318,27 +202,6 @@ static noinline void xen_spin_unlock_slow(struct xen_spinlock *xl) } } -static void xen_spin_unlock(struct arch_spinlock *lock) -{ - struct xen_spinlock *xl = (struct xen_spinlock *)lock; - - ADD_STATS(released, 1); - - smp_wmb(); /* make sure no writes get moved after unlock */ - xl->lock = 0; /* release lock */ - - /* - * Make sure unlock happens before checking for waiting - * spinners. We need a strong barrier to enforce the - * write-read ordering to different memory locations, as the - * CPU makes no implied guarantees about their ordering. - */ - mb(); - - if (unlikely(xl->spinners)) - xen_spin_unlock_slow(xl); -} - static irqreturn_t dummy_handler(int irq, void *dev_id) { BUG(); @@ -371,16 +234,28 @@ void xen_uninit_lock_cpu(int cpu) unbind_from_irqhandler(per_cpu(lock_kicker_irq, cpu), NULL); } +static bool xen_pvspin __initdata = true; + void __init xen_init_spinlocks(void) { - 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; + if (!xen_pvspin) { + printk(KERN_DEBUG "xen: PV spinlocks disabled\n"); + return; + } + + jump_label_inc(¶virt_ticketlocks_enabled); + + pv_lock_ops.lock_spinning = PV_CALLEE_SAVE(xen_lock_spinning); + pv_lock_ops.unlock_kick = xen_unlock_kick; } +static __init int xen_parse_nopvspin(char *arg) +{ + xen_pvspin = false; + return 0; +} +early_param("xen_nopvspin", xen_parse_nopvspin); + #ifdef CONFIG_XEN_DEBUG_FS static struct dentry *d_spin_debug; @@ -396,37 +271,21 @@ static int __init xen_spinlock_debugfs(void) debugfs_create_u8("zero_stats", 0644, d_spin_debug, &zero_stats); - debugfs_create_u32("timeout", 0644, d_spin_debug, &lock_timeout); - - debugfs_create_u64("taken", 0444, d_spin_debug, &spinlock_stats.taken); debugfs_create_u32("taken_slow", 0444, d_spin_debug, &spinlock_stats.taken_slow); - debugfs_create_u32("taken_slow_nested", 0444, d_spin_debug, - &spinlock_stats.taken_slow_nested); debugfs_create_u32("taken_slow_pickup", 0444, d_spin_debug, &spinlock_stats.taken_slow_pickup); debugfs_create_u32("taken_slow_spurious", 0444, d_spin_debug, &spinlock_stats.taken_slow_spurious); - debugfs_create_u32("taken_slow_irqenable", 0444, d_spin_debug, - &spinlock_stats.taken_slow_irqenable); - debugfs_create_u64("released", 0444, d_spin_debug, &spinlock_stats.released); debugfs_create_u32("released_slow", 0444, d_spin_debug, &spinlock_stats.released_slow); debugfs_create_u32("released_slow_kicked", 0444, d_spin_debug, &spinlock_stats.released_slow_kicked); - debugfs_create_u64("time_spinning", 0444, d_spin_debug, - &spinlock_stats.time_spinning); debugfs_create_u64("time_blocked", 0444, d_spin_debug, &spinlock_stats.time_blocked); - debugfs_create_u64("time_total", 0444, d_spin_debug, - &spinlock_stats.time_total); - xen_debugfs_create_u32_array("histo_total", 0444, d_spin_debug, - spinlock_stats.histo_spin_total, HISTO_BUCKETS + 1); - xen_debugfs_create_u32_array("histo_spinning", 0444, d_spin_debug, - spinlock_stats.histo_spin_spinning, HISTO_BUCKETS + 1); xen_debugfs_create_u32_array("histo_blocked", 0444, d_spin_debug, spinlock_stats.histo_spin_blocked, HISTO_BUCKETS + 1); diff --git a/kernel/Kconfig.locks b/kernel/Kconfig.locks index 5068e2a4e75f0..584637b21fc1a 100644 --- a/kernel/Kconfig.locks +++ b/kernel/Kconfig.locks @@ -125,7 +125,7 @@ config INLINE_SPIN_LOCK_IRQSAVE ARCH_INLINE_SPIN_LOCK_IRQSAVE config INLINE_SPIN_UNLOCK - def_bool !DEBUG_SPINLOCK && (!PREEMPT || ARCH_INLINE_SPIN_UNLOCK) + def_bool !DEBUG_SPINLOCK && (!PREEMPT || ARCH_INLINE_SPIN_UNLOCK) && !ARCH_NOINLINE_SPIN_UNLOCK config INLINE_SPIN_UNLOCK_BH def_bool !DEBUG_SPINLOCK && ARCH_INLINE_SPIN_UNLOCK_BH |