From 545ac13892ab391049a92108cf59a0d05de7e28c Mon Sep 17 00:00:00 2001 From: Jeremy Fitzhardinge Date: Fri, 9 Aug 2013 19:51:49 +0530 Subject: [PATCH 01/15] x86, spinlock: Replace pv spinlocks with pv ticketlocks 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. Results: ======= setup: 32 core machine with 32 vcpu KVM guest (HT off) with 8GB RAM base = 3.11-rc patched = base + pvspinlock V12 +-----------------+----------------+--------+ dbench (Throughput in MB/sec. Higher is better) +-----------------+----------------+--------+ | base (stdev %)|patched(stdev%) | %gain | +-----------------+----------------+--------+ | 15035.3 (0.3) |15150.0 (0.6) | 0.8 | | 1470.0 (2.2) | 1713.7 (1.9) | 16.6 | | 848.6 (4.3) | 967.8 (4.3) | 14.0 | | 652.9 (3.5) | 685.3 (3.7) | 5.0 | +-----------------+----------------+--------+ pvspinlock shows benefits for overcommit ratio > 1 for PLE enabled cases, and undercommits results are flat Signed-off-by: Jeremy Fitzhardinge Link: http://lkml.kernel.org/r/1376058122-8248-2-git-send-email-raghavendra.kt@linux.vnet.ibm.com Reviewed-by: Konrad Rzeszutek Wilk Tested-by: Attilio Rao [ Raghavendra: Changed SPIN_THRESHOLD, fixed redefinition of arch_spinlock_t] Signed-off-by: Raghavendra K T Acked-by: Ingo Molnar Signed-off-by: H. Peter Anvin --- arch/x86/include/asm/paravirt.h | 32 +++------------- arch/x86/include/asm/paravirt_types.h | 14 ++++--- 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, 65 insertions(+), 61 deletions(-) diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h index cfdc9ee4c900..040e72db5ea9 100644 --- a/arch/x86/include/asm/paravirt.h +++ b/arch/x86/include/asm/paravirt.h @@ -712,36 +712,16 @@ 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 0db1fcac668c..346a07c1e71d 100644 --- a/arch/x86/include/asm/paravirt_types.h +++ b/arch/x86/include/asm/paravirt_types.h @@ -327,13 +327,15 @@ struct pv_mmu_ops { }; struct arch_spinlock; +#ifdef CONFIG_SMP +#include +#else +typedef u16 __ticket_t; +#endif + 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 33692eaabab5..4d542444bea3 100644 --- a/arch/x86/include/asm/spinlock.h +++ b/arch/x86/include/asm/spinlock.h @@ -34,6 +34,35 @@ # define UNLOCK_LOCK_PREFIX #endif +/* How long a lock should spin before we consider blocking */ +#define SPIN_THRESHOLD (1 << 15) + +#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 @@ -47,19 +76,24 @@ * 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) @@ -78,7 +112,10 @@ 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) @@ -95,8 +132,6 @@ 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); @@ -129,8 +164,6 @@ 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 ad0ad07fc006..83fd3c75d45c 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 676b8c77a976..c2e010e5fbce 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 cf3caee356b3..d50962936af4 100644 --- a/arch/x86/xen/spinlock.c +++ b/arch/x86/xen/spinlock.c @@ -139,6 +139,9 @@ 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; @@ -167,7 +170,6 @@ static int xen_spin_trylock(struct arch_spinlock *lock) } static DEFINE_PER_CPU(char *, irq_name); -static DEFINE_PER_CPU(int, lock_kicker_irq) = -1; static DEFINE_PER_CPU(struct xen_spinlock *, lock_spinners); /* @@ -354,6 +356,7 @@ 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) { @@ -418,13 +421,14 @@ void __init xen_init_spinlocks(void) return; 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 From 8db732668a48e93d00d881517a08136e8fa71000 Mon Sep 17 00:00:00 2001 From: Raghavendra K T Date: Fri, 9 Aug 2013 19:51:50 +0530 Subject: [PATCH 02/15] x86, ticketlock: Don't inline _spin_unlock when using paravirt spinlocks The code size expands somewhat, and its better to just call a function rather than inline it. Thanks Jeremy for original version of ARCH_NOINLINE_SPIN_UNLOCK config patch, which is simplified. Suggested-by: Linus Torvalds Reviewed-by: Konrad Rzeszutek Wilk Signed-off-by: Raghavendra K T Link: http://lkml.kernel.org/r/1376058122-8248-3-git-send-email-raghavendra.kt@linux.vnet.ibm.com Acked-by: Ingo Molnar Signed-off-by: H. Peter Anvin --- arch/x86/Kconfig | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index b32ebf92b0ce..112e71264542 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -632,6 +632,7 @@ config PARAVIRT_DEBUG config PARAVIRT_SPINLOCKS bool "Paravirtualization layer for spinlocks" depends on PARAVIRT && SMP + select UNINLINE_SPIN_UNLOCK ---help--- Paravirtualized spinlocks allow a pvops backend to replace the spinlock implementation with something virtualization-friendly From b798df09f919c52823110a74bd568c6a4e98e6b2 Mon Sep 17 00:00:00 2001 From: Jeremy Fitzhardinge Date: Fri, 9 Aug 2013 19:51:51 +0530 Subject: [PATCH 03/15] x86, ticketlock: Collapse a layer of functions Now that the paravirtualization layer doesn't exist at the spinlock level any more, we can collapse the __ticket_ functions into the arch_ functions. Signed-off-by: Jeremy Fitzhardinge Link: http://lkml.kernel.org/r/1376058122-8248-4-git-send-email-raghavendra.kt@linux.vnet.ibm.com Reviewed-by: Konrad Rzeszutek Wilk Tested-by: Attilio Rao Signed-off-by: Raghavendra K T Acked-by: Ingo Molnar Signed-off-by: H. Peter Anvin --- arch/x86/include/asm/spinlock.h | 35 +++++---------------------------- 1 file changed, 5 insertions(+), 30 deletions(-) diff --git a/arch/x86/include/asm/spinlock.h b/arch/x86/include/asm/spinlock.h index 4d542444bea3..744241048a11 100644 --- a/arch/x86/include/asm/spinlock.h +++ b/arch/x86/include/asm/spinlock.h @@ -76,7 +76,7 @@ static __always_inline void __ticket_unlock_kick(struct arch_spinlock *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(struct arch_spinlock *lock) +static __always_inline void arch_spin_lock(struct arch_spinlock *lock) { register struct __raw_tickets inc = { .tail = 1 }; @@ -96,7 +96,7 @@ static __always_inline void __ticket_spin_lock(struct arch_spinlock *lock) 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; @@ -110,7 +110,7 @@ static __always_inline int __ticket_spin_trylock(arch_spinlock_t *lock) 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 __always_inline void arch_spin_unlock(arch_spinlock_t *lock) { __ticket_t next = lock->tickets.head + 1; @@ -118,46 +118,21 @@ static __always_inline void __ticket_spin_unlock(arch_spinlock_t *lock) __ticket_unlock_kick(lock, next); } -static inline int __ticket_spin_is_locked(arch_spinlock_t *lock) +static inline int arch_spin_is_locked(arch_spinlock_t *lock) { struct __raw_tickets tmp = ACCESS_ONCE(lock->tickets); return tmp.tail != tmp.head; } -static inline int __ticket_spin_is_contended(arch_spinlock_t *lock) +static inline int arch_spin_is_contended(arch_spinlock_t *lock) { struct __raw_tickets tmp = ACCESS_ONCE(lock->tickets); return (__ticket_t)(tmp.tail - tmp.head) > 1; } - -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 -static __always_inline void arch_spin_lock(arch_spinlock_t *lock) -{ - __ticket_spin_lock(lock); -} - -static __always_inline int arch_spin_trylock(arch_spinlock_t *lock) -{ - return __ticket_spin_trylock(lock); -} - -static __always_inline void arch_spin_unlock(arch_spinlock_t *lock) -{ - __ticket_spin_unlock(lock); -} - static __always_inline void arch_spin_lock_flags(arch_spinlock_t *lock, unsigned long flags) { From bf7aab3ad4b4364a293421d628a912a2153ee1ee Mon Sep 17 00:00:00 2001 From: Jeremy Fitzhardinge Date: Fri, 9 Aug 2013 19:51:52 +0530 Subject: [PATCH 04/15] xen: Defer spinlock setup until boot CPU setup There's no need to do it at very early init, and doing it there makes it impossible to use the jump_label machinery. Signed-off-by: Jeremy Fitzhardinge Link: http://lkml.kernel.org/r/1376058122-8248-5-git-send-email-raghavendra.kt@linux.vnet.ibm.com Reviewed-by: Konrad Rzeszutek Wilk Signed-off-by: Raghavendra K T Acked-by: Ingo Molnar Signed-off-by: H. Peter Anvin --- arch/x86/xen/smp.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c index ca92754eb846..3b52d8075e47 100644 --- a/arch/x86/xen/smp.c +++ b/arch/x86/xen/smp.c @@ -279,6 +279,7 @@ 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) @@ -680,7 +681,6 @@ 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) From 80bd58fef495d000a02fc5b55ca76d423400e748 Mon Sep 17 00:00:00 2001 From: Jeremy Fitzhardinge Date: Fri, 9 Aug 2013 19:51:53 +0530 Subject: [PATCH 05/15] xen, pvticketlock: Xen implementation for PV ticket locks Replace the old Xen implementation of PV spinlocks with and implementation of xen_lock_spinning and xen_unlock_kick. xen_lock_spinning simply registers the cpu in its entry in lock_waiting, adds itself to the waiting_cpus set, and blocks on an event channel until the channel becomes pending. xen_unlock_kick searches the cpus in waiting_cpus looking for the one which next wants this lock with the next ticket, if any. If found, it kicks it by making its event channel pending, which wakes it up. We need to make sure interrupts are disabled while we're relying on the contents of the per-cpu lock_waiting values, otherwise an interrupt handler could come in, try to take some other lock, block, and overwrite our values. Signed-off-by: Jeremy Fitzhardinge Link: http://lkml.kernel.org/r/1376058122-8248-6-git-send-email-raghavendra.kt@linux.vnet.ibm.com Reviewed-by: Konrad Rzeszutek Wilk [ Raghavendra: use function + enum instead of macro, cmpxchg for zero status reset Reintroduce break since we know the exact vCPU to send IPI as suggested by Konrad.] Signed-off-by: Raghavendra K T Acked-by: Ingo Molnar Signed-off-by: H. Peter Anvin --- arch/x86/xen/spinlock.c | 348 +++++++++------------------------------- 1 file changed, 79 insertions(+), 269 deletions(-) diff --git a/arch/x86/xen/spinlock.c b/arch/x86/xen/spinlock.c index d50962936af4..a458729be25f 100644 --- a/arch/x86/xen/spinlock.c +++ b/arch/x86/xen/spinlock.c @@ -17,45 +17,44 @@ #include "xen-ops.h" #include "debugfs.h" +enum xen_contention_stat { + TAKEN_SLOW, + TAKEN_SLOW_PICKUP, + TAKEN_SLOW_SPURIOUS, + RELEASED_SLOW, + RELEASED_SLOW_KICKED, + NR_CONTENTION_STATS +}; + + #ifdef CONFIG_XEN_DEBUG_FS +#define HISTO_BUCKETS 30 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 contention_stats[NR_CONTENTION_STATS]; 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)) { - memset(&spinlock_stats, 0, sizeof(spinlock_stats)); - zero_stats = 0; + u8 ret; + u8 old = ACCESS_ONCE(zero_stats); + if (unlikely(old)) { + ret = cmpxchg(&zero_stats, old, 0); + /* This ensures only one fellow resets the stat */ + if (ret == old) + memset(&spinlock_stats, 0, sizeof(spinlock_stats)); } } -#define ADD_STATS(elem, val) \ - do { check_zero(); spinlock_stats.elem += (val); } while(0) +static inline void add_stats(enum xen_contention_stat var, u32 val) +{ + check_zero(); + spinlock_stats.contention_stats[var] += val; +} static inline u64 spin_time_start(void) { @@ -74,22 +73,6 @@ 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; @@ -99,19 +82,15 @@ static inline void spin_time_accum_blocked(u64 start) } #else /* !CONFIG_XEN_DEBUG_FS */ #define TIMEOUT (1 << 10) -#define ADD_STATS(elem, val) do { (void)(val); } while(0) +static inline void add_stats(enum xen_contention_stat var, u32 val) +{ +} 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) { } @@ -134,230 +113,84 @@ typedef u16 xen_spinners_t; asm(LOCK_PREFIX " decw %0" : "+m" ((xl)->spinners) : : "memory"); #endif -struct xen_spinlock { - unsigned char lock; /* 0 -> free; 1 -> locked */ - xen_spinners_t spinners; /* count of waiting cpus */ +struct xen_lock_waiting { + struct arch_spinlock *lock; + __ticket_t want; }; 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; - - 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(char *, irq_name); -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 */ - - inc_spinners(xl); - - 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) -{ - dec_spinners(xl); - 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); + /* + * Make sure an interrupt handler can't upset things in a + * partially setup state. + */ + local_irq_save(flags); - ADD_STATS(taken_slow, 1); - ADD_STATS(taken_slow_nested, prev != NULL); + w->want = want; + smp_wmb(); + w->lock = lock; - do { - unsigned long flags; + /* This uses set_bit, which atomic and therefore a barrier */ + cpumask_set_cpu(cpu, &waiting_cpus); + add_stats(TAKEN_SLOW, 1); - /* clear pending */ - xen_clear_irq_pending(irq); + /* 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); - - raw_local_irq_restore(flags); - - ADD_STATS(taken_slow_spurious, !xen_test_irq_pending(irq)); - } while (!xen_test_irq_pending(irq)); /* check for spurious wakeups */ + /* Only check lock once pending cleared */ + barrier(); + /* 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; + } + /* Block until irq becomes pending (or perhaps a spurious wakeup) */ + xen_poll_irq(irq); + add_stats(TAKEN_SLOW_SPURIOUS, !xen_test_irq_pending(irq)); kstat_incr_irqs_this_cpu(irq, irq_to_desc(irq)); - out: - unspinning_lock(xl, prev); + cpumask_clear_cpu(cpu, &waiting_cpus); + w->lock = NULL; + local_irq_restore(flags); spin_time_accum_blocked(start); - - return ret; } -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); - - start_spin = spin_time_start(); - - do { - u64 start_spin_fast = spin_time_start(); - - timeout = TIMEOUT; - - 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"); - - spin_time_accum_spinning(start_spin_fast); - - } while (unlikely(oldval != 0 && - (TIMEOUT == ~0 || !xen_spin_lock_slow(lock, irq_enable)))); - - spin_time_accum_total(start_spin); -} - -static void xen_spin_lock(struct arch_spinlock *lock) -{ - __xen_spin_lock(lock, false); -} - -static void xen_spin_lock_flags(struct arch_spinlock *lock, unsigned long flags) -{ - __xen_spin_lock(lock, !raw_irqs_disabled_flags(flags)); -} - -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); + add_stats(RELEASED_SLOW, 1); - for_each_online_cpu(cpu) { - /* XXX should mix up next cpu selection */ - if (per_cpu(lock_spinners, cpu) == xl) { - ADD_STATS(released_slow_kicked, 1); + for_each_cpu(cpu, &waiting_cpus) { + const struct xen_lock_waiting *w = &per_cpu(lock_waiting, cpu); + + if (w->lock == lock && w->want == next) { + add_stats(RELEASED_SLOW_KICKED, 1); xen_send_IPI_one(cpu, XEN_SPIN_UNLOCK_VECTOR); + break; } } } -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); -} -#endif - static irqreturn_t dummy_handler(int irq, void *dev_id) { BUG(); @@ -420,15 +253,8 @@ void __init xen_init_spinlocks(void) if (xen_hvm_domain()) return; - 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 + pv_lock_ops.lock_spinning = xen_lock_spinning; + pv_lock_ops.unlock_kick = xen_unlock_kick; } #ifdef CONFIG_XEN_DEBUG_FS @@ -446,37 +272,21 @@ 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); + &spinlock_stats.contention_stats[TAKEN_SLOW]); debugfs_create_u32("taken_slow_pickup", 0444, d_spin_debug, - &spinlock_stats.taken_slow_pickup); + &spinlock_stats.contention_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); + &spinlock_stats.contention_stats[TAKEN_SLOW_SPURIOUS]); - debugfs_create_u64("released", 0444, d_spin_debug, &spinlock_stats.released); debugfs_create_u32("released_slow", 0444, d_spin_debug, - &spinlock_stats.released_slow); + &spinlock_stats.contention_stats[RELEASED_SLOW]); debugfs_create_u32("released_slow_kicked", 0444, d_spin_debug, - &spinlock_stats.released_slow_kicked); + &spinlock_stats.contention_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); - debugfs_create_u32_array("histo_total", 0444, d_spin_debug, - spinlock_stats.histo_spin_total, HISTO_BUCKETS + 1); - debugfs_create_u32_array("histo_spinning", 0444, d_spin_debug, - spinlock_stats.histo_spin_spinning, HISTO_BUCKETS + 1); debugfs_create_u32_array("histo_blocked", 0444, d_spin_debug, spinlock_stats.histo_spin_blocked, HISTO_BUCKETS + 1); From b8fa70b51aa76737bdb6b493901ef7376977489c Mon Sep 17 00:00:00 2001 From: Jeremy Fitzhardinge Date: Fri, 9 Aug 2013 19:51:54 +0530 Subject: [PATCH 06/15] xen, pvticketlocks: Add xen_nopvspin parameter to disable xen pv ticketlocks Signed-off-by: Jeremy Fitzhardinge Link: http://lkml.kernel.org/r/1376058122-8248-7-git-send-email-raghavendra.kt@linux.vnet.ibm.com Reviewed-by: Konrad Rzeszutek Wilk Signed-off-by: Raghavendra K T Acked-by: Ingo Molnar Signed-off-by: H. Peter Anvin --- arch/x86/xen/spinlock.c | 14 ++++++++++++++ 1 file changed, 14 insertions(+) diff --git a/arch/x86/xen/spinlock.c b/arch/x86/xen/spinlock.c index a458729be25f..669a971c78fd 100644 --- a/arch/x86/xen/spinlock.c +++ b/arch/x86/xen/spinlock.c @@ -244,6 +244,8 @@ void xen_uninit_lock_cpu(int cpu) per_cpu(irq_name, cpu) = NULL; } +static bool xen_pvspin __initdata = true; + void __init xen_init_spinlocks(void) { /* @@ -253,10 +255,22 @@ void __init xen_init_spinlocks(void) if (xen_hvm_domain()) return; + if (!xen_pvspin) { + printk(KERN_DEBUG "xen: PV spinlocks disabled\n"); + return; + } + pv_lock_ops.lock_spinning = 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; From 354714dd2607778692db53947ab93b74956494e5 Mon Sep 17 00:00:00 2001 From: Jeremy Fitzhardinge Date: Fri, 9 Aug 2013 19:51:55 +0530 Subject: [PATCH 07/15] x86, pvticketlock: Use callee-save for lock_spinning Although the lock_spinning calls in the spinlock code are on the uncommon path, their presence can cause the compiler to generate many more register save/restores in the function pre/postamble, which is in the fast path. To avoid this, convert it to using the pvops callee-save calling convention, which defers all the save/restores until the actual function is called, keeping the fastpath clean. Signed-off-by: Jeremy Fitzhardinge Link: http://lkml.kernel.org/r/1376058122-8248-8-git-send-email-raghavendra.kt@linux.vnet.ibm.com Reviewed-by: Konrad Rzeszutek Wilk Tested-by: Attilio Rao Signed-off-by: Raghavendra K T Acked-by: Ingo Molnar Signed-off-by: H. Peter Anvin --- arch/x86/include/asm/paravirt.h | 2 +- arch/x86/include/asm/paravirt_types.h | 2 +- arch/x86/kernel/paravirt-spinlocks.c | 2 +- arch/x86/xen/spinlock.c | 3 ++- 4 files changed, 5 insertions(+), 4 deletions(-) diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h index 040e72db5ea9..7131e12cefa1 100644 --- a/arch/x86/include/asm/paravirt.h +++ b/arch/x86/include/asm/paravirt.h @@ -715,7 +715,7 @@ static inline void __set_fixmap(unsigned /* enum fixed_addresses */ idx, static __always_inline void __ticket_lock_spinning(struct arch_spinlock *lock, __ticket_t ticket) { - PVOP_VCALL2(pv_lock_ops.lock_spinning, lock, ticket); + PVOP_VCALLEE2(pv_lock_ops.lock_spinning, lock, ticket); } static __always_inline void ____ticket_unlock_kick(struct arch_spinlock *lock, diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h index 346a07c1e71d..04ac40e192eb 100644 --- a/arch/x86/include/asm/paravirt_types.h +++ b/arch/x86/include/asm/paravirt_types.h @@ -334,7 +334,7 @@ typedef u16 __ticket_t; #endif struct pv_lock_ops { - void (*lock_spinning)(struct arch_spinlock *lock, __ticket_t ticket); + struct paravirt_callee_save lock_spinning; void (*unlock_kick)(struct arch_spinlock *lock, __ticket_t ticket); }; diff --git a/arch/x86/kernel/paravirt-spinlocks.c b/arch/x86/kernel/paravirt-spinlocks.c index c2e010e5fbce..4251c1d4c0be 100644 --- a/arch/x86/kernel/paravirt-spinlocks.c +++ b/arch/x86/kernel/paravirt-spinlocks.c @@ -9,7 +9,7 @@ struct pv_lock_ops pv_lock_ops = { #ifdef CONFIG_SMP - .lock_spinning = paravirt_nop, + .lock_spinning = __PV_IS_CALLEE_SAVE(paravirt_nop), .unlock_kick = paravirt_nop, #endif }; diff --git a/arch/x86/xen/spinlock.c b/arch/x86/xen/spinlock.c index 669a971c78fd..6c8792b298ed 100644 --- a/arch/x86/xen/spinlock.c +++ b/arch/x86/xen/spinlock.c @@ -173,6 +173,7 @@ out: local_irq_restore(flags); spin_time_accum_blocked(start); } +PV_CALLEE_SAVE_REGS_THUNK(xen_lock_spinning); static void xen_unlock_kick(struct arch_spinlock *lock, __ticket_t next) { @@ -260,7 +261,7 @@ void __init xen_init_spinlocks(void) return; } - pv_lock_ops.lock_spinning = xen_lock_spinning; + pv_lock_ops.lock_spinning = PV_CALLEE_SAVE(xen_lock_spinning); pv_lock_ops.unlock_kick = xen_unlock_kick; } From 4a1ed4ca681e7df38ed1b609a11aab38cbc515b3 Mon Sep 17 00:00:00 2001 From: Jeremy Fitzhardinge Date: Fri, 9 Aug 2013 19:51:56 +0530 Subject: [PATCH 08/15] x86, pvticketlock: When paravirtualizing ticket locks, increment by 2 Increment ticket head/tails by 2 rather than 1 to leave the LSB free to store a "is in slowpath state" bit. This halves the number of possible CPUs for a given ticket size, but this shouldn't matter in practice - kernels built for 32k+ CPU systems are probably specially built for the hardware rather than a generic distro kernel. Signed-off-by: Jeremy Fitzhardinge Link: http://lkml.kernel.org/r/1376058122-8248-9-git-send-email-raghavendra.kt@linux.vnet.ibm.com Reviewed-by: Konrad Rzeszutek Wilk Tested-by: Attilio Rao Signed-off-by: Raghavendra K T Acked-by: Ingo Molnar Signed-off-by: H. Peter Anvin --- arch/x86/include/asm/spinlock.h | 10 +++++----- arch/x86/include/asm/spinlock_types.h | 10 +++++++++- 2 files changed, 14 insertions(+), 6 deletions(-) diff --git a/arch/x86/include/asm/spinlock.h b/arch/x86/include/asm/spinlock.h index 744241048a11..04a5cd5e97cb 100644 --- a/arch/x86/include/asm/spinlock.h +++ b/arch/x86/include/asm/spinlock.h @@ -78,7 +78,7 @@ static __always_inline void __ticket_unlock_kick(struct arch_spinlock *lock, */ static __always_inline void arch_spin_lock(struct arch_spinlock *lock) { - register struct __raw_tickets inc = { .tail = 1 }; + register struct __raw_tickets inc = { .tail = TICKET_LOCK_INC }; inc = xadd(&lock->tickets, inc); @@ -104,7 +104,7 @@ static __always_inline int arch_spin_trylock(arch_spinlock_t *lock) if (old.tickets.head != old.tickets.tail) 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; @@ -112,9 +112,9 @@ static __always_inline int arch_spin_trylock(arch_spinlock_t *lock) static __always_inline void arch_spin_unlock(arch_spinlock_t *lock) { - __ticket_t next = lock->tickets.head + 1; + __ticket_t next = lock->tickets.head + TICKET_LOCK_INC; - __add(&lock->tickets.head, 1, UNLOCK_LOCK_PREFIX); + __add(&lock->tickets.head, TICKET_LOCK_INC, UNLOCK_LOCK_PREFIX); __ticket_unlock_kick(lock, next); } @@ -129,7 +129,7 @@ static inline int arch_spin_is_contended(arch_spinlock_t *lock) { struct __raw_tickets tmp = ACCESS_ONCE(lock->tickets); - return (__ticket_t)(tmp.tail - tmp.head) > 1; + return (__ticket_t)(tmp.tail - tmp.head) > TICKET_LOCK_INC; } #define arch_spin_is_contended arch_spin_is_contended diff --git a/arch/x86/include/asm/spinlock_types.h b/arch/x86/include/asm/spinlock_types.h index 83fd3c75d45c..e96fcbdfbc07 100644 --- a/arch/x86/include/asm/spinlock_types.h +++ b/arch/x86/include/asm/spinlock_types.h @@ -3,7 +3,13 @@ #include -#if (CONFIG_NR_CPUS < 256) +#ifdef CONFIG_PARAVIRT_SPINLOCKS +#define __TICKET_LOCK_INC 2 +#else +#define __TICKET_LOCK_INC 1 +#endif + +#if (CONFIG_NR_CPUS < (256 / __TICKET_LOCK_INC)) typedef u8 __ticket_t; typedef u16 __ticketpair_t; #else @@ -11,6 +17,8 @@ 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) typedef struct arch_spinlock { From 851cf6e7d6366195d4ee033cdc7787df1a649a14 Mon Sep 17 00:00:00 2001 From: Andrew Jones Date: Fri, 9 Aug 2013 19:51:57 +0530 Subject: [PATCH 09/15] jump_label: Split jumplabel ratelimit Commit b202952075f62603bea9bfb6ebc6b0420db11949 ("perf, core: Rate limit perf_sched_events jump_label patching") introduced rate limiting for jump label disabling. The changes were made in the jump label code in order to be more widely available and to keep things tidier. This is all fine, except now jump_label.h includes linux/workqueue.h, which makes it impossible to include jump_label.h from anything that workqueue.h needs. For example, it's now impossible to include jump_label.h from asm/spinlock.h, which is done in proposed pv-ticketlock patches. This patch splits out the rate limiting related changes from jump_label.h into a new file, jump_label_ratelimit.h, to resolve the issue. Signed-off-by: Andrew Jones Link: http://lkml.kernel.org/r/1376058122-8248-10-git-send-email-raghavendra.kt@linux.vnet.ibm.com Reviewed-by: Konrad Rzeszutek Wilk Signed-off-by: Raghavendra K T Acked-by: Ingo Molnar Signed-off-by: H. Peter Anvin --- include/linux/jump_label.h | 28 +---------------------- include/linux/jump_label_ratelimit.h | 34 ++++++++++++++++++++++++++++ include/linux/perf_event.h | 1 + kernel/jump_label.c | 1 + 4 files changed, 37 insertions(+), 27 deletions(-) create mode 100644 include/linux/jump_label_ratelimit.h diff --git a/include/linux/jump_label.h b/include/linux/jump_label.h index 0976fc46d1e0..a5079072da66 100644 --- a/include/linux/jump_label.h +++ b/include/linux/jump_label.h @@ -48,7 +48,6 @@ #include #include -#include #if defined(CC_HAVE_ASM_GOTO) && defined(CONFIG_JUMP_LABEL) @@ -61,12 +60,6 @@ struct static_key { #endif }; -struct static_key_deferred { - struct static_key key; - unsigned long timeout; - struct delayed_work work; -}; - # include # define HAVE_JUMP_LABEL #endif /* CC_HAVE_ASM_GOTO && CONFIG_JUMP_LABEL */ @@ -78,6 +71,7 @@ enum jump_label_type { struct module; +#include #ifdef HAVE_JUMP_LABEL #define JUMP_LABEL_TRUE_BRANCH 1UL @@ -119,10 +113,7 @@ extern void arch_jump_label_transform_static(struct jump_entry *entry, extern int jump_label_text_reserved(void *start, void *end); extern void static_key_slow_inc(struct static_key *key); extern void static_key_slow_dec(struct static_key *key); -extern void static_key_slow_dec_deferred(struct static_key_deferred *key); extern void jump_label_apply_nops(struct module *mod); -extern void -jump_label_rate_limit(struct static_key_deferred *key, unsigned long rl); #define STATIC_KEY_INIT_TRUE ((struct static_key) \ { .enabled = ATOMIC_INIT(1), .entries = (void *)1 }) @@ -131,8 +122,6 @@ jump_label_rate_limit(struct static_key_deferred *key, unsigned long rl); #else /* !HAVE_JUMP_LABEL */ -#include - struct static_key { atomic_t enabled; }; @@ -141,10 +130,6 @@ static __always_inline void jump_label_init(void) { } -struct static_key_deferred { - struct static_key key; -}; - static __always_inline bool static_key_false(struct static_key *key) { if (unlikely(atomic_read(&key->enabled)) > 0) @@ -169,11 +154,6 @@ static inline void static_key_slow_dec(struct static_key *key) atomic_dec(&key->enabled); } -static inline void static_key_slow_dec_deferred(struct static_key_deferred *key) -{ - static_key_slow_dec(&key->key); -} - static inline int jump_label_text_reserved(void *start, void *end) { return 0; @@ -187,12 +167,6 @@ static inline int jump_label_apply_nops(struct module *mod) return 0; } -static inline void -jump_label_rate_limit(struct static_key_deferred *key, - unsigned long rl) -{ -} - #define STATIC_KEY_INIT_TRUE ((struct static_key) \ { .enabled = ATOMIC_INIT(1) }) #define STATIC_KEY_INIT_FALSE ((struct static_key) \ diff --git a/include/linux/jump_label_ratelimit.h b/include/linux/jump_label_ratelimit.h new file mode 100644 index 000000000000..113788389b3d --- /dev/null +++ b/include/linux/jump_label_ratelimit.h @@ -0,0 +1,34 @@ +#ifndef _LINUX_JUMP_LABEL_RATELIMIT_H +#define _LINUX_JUMP_LABEL_RATELIMIT_H + +#include +#include + +#if defined(CC_HAVE_ASM_GOTO) && defined(CONFIG_JUMP_LABEL) +struct static_key_deferred { + struct static_key key; + unsigned long timeout; + struct delayed_work work; +}; +#endif + +#ifdef HAVE_JUMP_LABEL +extern void static_key_slow_dec_deferred(struct static_key_deferred *key); +extern void +jump_label_rate_limit(struct static_key_deferred *key, unsigned long rl); + +#else /* !HAVE_JUMP_LABEL */ +struct static_key_deferred { + struct static_key key; +}; +static inline void static_key_slow_dec_deferred(struct static_key_deferred *key) +{ + static_key_slow_dec(&key->key); +} +static inline void +jump_label_rate_limit(struct static_key_deferred *key, + unsigned long rl) +{ +} +#endif /* HAVE_JUMP_LABEL */ +#endif /* _LINUX_JUMP_LABEL_RATELIMIT_H */ diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index c43f6eabad5b..226be8da3f85 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -48,6 +48,7 @@ struct perf_guest_info_callbacks { #include #include #include +#include #include #include #include diff --git a/kernel/jump_label.c b/kernel/jump_label.c index 60f48fa0fd0d..297a9247a3b3 100644 --- a/kernel/jump_label.c +++ b/kernel/jump_label.c @@ -13,6 +13,7 @@ #include #include #include +#include #ifdef HAVE_JUMP_LABEL From 96f853eaa889c7a22718d275b0df7bebdbd6780e Mon Sep 17 00:00:00 2001 From: Jeremy Fitzhardinge Date: Fri, 9 Aug 2013 19:51:58 +0530 Subject: [PATCH 10/15] x86, ticketlock: Add slowpath logic Maintain a flag in the LSB of the ticket lock tail which indicates whether anyone is in the lock slowpath and may need kicking when the current holder unlocks. The flags are set when the first locker enters the slowpath, and cleared when unlocking to an empty queue (ie, no contention). In the specific implementation of lock_spinning(), make sure to set the slowpath flags on the lock just before blocking. We must do this before the last-chance pickup test to prevent a deadlock with the unlocker: Unlocker Locker test for lock pickup -> fail unlock test slowpath -> false set slowpath flags block Whereas this works in any ordering: Unlocker Locker set slowpath flags test for lock pickup -> fail block unlock test slowpath -> true, kick If the unlocker finds that the lock has the slowpath flag set but it is actually uncontended (ie, head == tail, so nobody is waiting), then it clears the slowpath flag. The unlock code uses a locked add to update the head counter. This also acts as a full memory barrier so that its safe to subsequently read back the slowflag state, knowing that the updated lock is visible to the other CPUs. If it were an unlocked add, then the flag read may just be forwarded from the store buffer before it was visible to the other CPUs, which could result in a deadlock. Unfortunately this means we need to do a locked instruction when unlocking with PV ticketlocks. However, if PV ticketlocks are not enabled, then the old non-locked "add" is the only unlocking code. Note: this code relies on gcc making sure that unlikely() code is out of line of the fastpath, which only happens when OPTIMIZE_SIZE=n. If it doesn't the generated code isn't too bad, but its definitely suboptimal. Thanks to Srivatsa Vaddagiri for providing a bugfix to the original version of this change, which has been folded in. Thanks to Stephan Diestelhorst for commenting on some code which relied on an inaccurate reading of the x86 memory ordering rules. Signed-off-by: Jeremy Fitzhardinge Link: http://lkml.kernel.org/r/1376058122-8248-11-git-send-email-raghavendra.kt@linux.vnet.ibm.com Signed-off-by: Srivatsa Vaddagiri Reviewed-by: Konrad Rzeszutek Wilk Cc: Stephan Diestelhorst Signed-off-by: Raghavendra K T Acked-by: Ingo Molnar Signed-off-by: H. Peter Anvin --- arch/x86/include/asm/paravirt.h | 2 +- arch/x86/include/asm/spinlock.h | 92 +++++++++++++++++++-------- arch/x86/include/asm/spinlock_types.h | 2 + arch/x86/kernel/paravirt-spinlocks.c | 3 + arch/x86/xen/spinlock.c | 6 ++ 5 files changed, 77 insertions(+), 28 deletions(-) diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h index 7131e12cefa1..401f350ef71b 100644 --- a/arch/x86/include/asm/paravirt.h +++ b/arch/x86/include/asm/paravirt.h @@ -718,7 +718,7 @@ static __always_inline void __ticket_lock_spinning(struct arch_spinlock *lock, PVOP_VCALLEE2(pv_lock_ops.lock_spinning, lock, ticket); } -static __always_inline void ____ticket_unlock_kick(struct arch_spinlock *lock, +static __always_inline void __ticket_unlock_kick(struct arch_spinlock *lock, __ticket_t ticket) { PVOP_VCALL2(pv_lock_ops.unlock_kick, lock, ticket); diff --git a/arch/x86/include/asm/spinlock.h b/arch/x86/include/asm/spinlock.h index 04a5cd5e97cb..d68883dd133c 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 #include #include #include #include #include +#include + /* * Your basic SMP spinlocks, allowing only a single CPU anywhere * @@ -37,31 +40,27 @@ /* How long a lock should spin before we consider blocking */ #define SPIN_THRESHOLD (1 << 15) -#ifndef CONFIG_PARAVIRT_SPINLOCKS +extern struct static_key paravirt_ticketlocks_enabled; +static __always_inline bool static_key_false(struct static_key *key); -static __always_inline void __ticket_lock_spinning(struct arch_spinlock *lock, +#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) { } -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); -} +#endif /* CONFIG_PARAVIRT_SPINLOCKS */ /* * Ticket locks are conceptually two parts, one indicating the current head of @@ -76,20 +75,22 @@ static __always_inline void __ticket_unlock_kick(struct arch_spinlock *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 arch_spin_lock(struct arch_spinlock *lock) +static __always_inline void arch_spin_lock(arch_spinlock_t *lock) { 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 (;;) { unsigned count = SPIN_THRESHOLD; do { - if (inc.head == inc.tail) + if (ACCESS_ONCE(lock->tickets.head) == inc.tail) goto out; cpu_relax(); - inc.head = ACCESS_ONCE(lock->tickets.head); } while (--count); __ticket_lock_spinning(lock, inc.tail); } @@ -101,7 +102,7 @@ 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 + (TICKET_LOCK_INC << TICKET_SHIFT); @@ -110,12 +111,49 @@ static __always_inline int arch_spin_trylock(arch_spinlock_t *lock) return cmpxchg(&lock->head_tail, old.head_tail, new.head_tail) == old.head_tail; } +static inline void __ticket_unlock_slowpath(arch_spinlock_t *lock, + arch_spinlock_t old) +{ + 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 __always_inline void arch_spin_unlock(arch_spinlock_t *lock) { - __ticket_t next = lock->tickets.head + TICKET_LOCK_INC; + if (TICKET_SLOWPATH_FLAG && + static_key_false(¶virt_ticketlocks_enabled)) { + arch_spinlock_t prev; - __add(&lock->tickets.head, TICKET_LOCK_INC, UNLOCK_LOCK_PREFIX); - __ticket_unlock_kick(lock, next); + prev = *lock; + add_smp(&lock->tickets.head, TICKET_LOCK_INC); + + /* add_smp() is a full mb() */ + + if (unlikely(lock->tickets.tail & TICKET_SLOWPATH_FLAG)) + __ticket_unlock_slowpath(lock, prev); + } else + __add(&lock->tickets.head, TICKET_LOCK_INC, UNLOCK_LOCK_PREFIX); } static inline int arch_spin_is_locked(arch_spinlock_t *lock) diff --git a/arch/x86/include/asm/spinlock_types.h b/arch/x86/include/asm/spinlock_types.h index e96fcbdfbc07..4f1bea19945b 100644 --- a/arch/x86/include/asm/spinlock_types.h +++ b/arch/x86/include/asm/spinlock_types.h @@ -5,8 +5,10 @@ #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)) diff --git a/arch/x86/kernel/paravirt-spinlocks.c b/arch/x86/kernel/paravirt-spinlocks.c index 4251c1d4c0be..bbb6c7316341 100644 --- a/arch/x86/kernel/paravirt-spinlocks.c +++ b/arch/x86/kernel/paravirt-spinlocks.c @@ -4,6 +4,7 @@ */ #include #include +#include #include @@ -15,3 +16,5 @@ struct pv_lock_ops pv_lock_ops = { }; EXPORT_SYMBOL(pv_lock_ops); +struct static_key paravirt_ticketlocks_enabled = STATIC_KEY_INIT_FALSE; +EXPORT_SYMBOL(paravirt_ticketlocks_enabled); diff --git a/arch/x86/xen/spinlock.c b/arch/x86/xen/spinlock.c index 6c8792b298ed..546112ed463f 100644 --- a/arch/x86/xen/spinlock.c +++ b/arch/x86/xen/spinlock.c @@ -157,6 +157,10 @@ static void xen_lock_spinning(struct arch_spinlock *lock, __ticket_t want) /* Only check lock once pending cleared */ barrier(); + /* Mark entry to slowpath before doing the pickup test to make + sure we don't deadlock with an unlocker. */ + __ticket_enter_slowpath(lock); + /* check again make sure it didn't become free while we weren't looking */ if (ACCESS_ONCE(lock->tickets.head) == want) { @@ -261,6 +265,8 @@ void __init xen_init_spinlocks(void) return; } + static_key_slow_inc(¶virt_ticketlocks_enabled); + pv_lock_ops.lock_spinning = PV_CALLEE_SAVE(xen_lock_spinning); pv_lock_ops.unlock_kick = xen_unlock_kick; } From 1ed7bf5f5227169b661c619636f754b98001ec30 Mon Sep 17 00:00:00 2001 From: Jeremy Fitzhardinge Date: Fri, 9 Aug 2013 19:51:59 +0530 Subject: [PATCH 11/15] xen, pvticketlock: Allow interrupts to be enabled while blocking If interrupts were enabled when taking the spinlock, we can leave them enabled while blocking to get the lock. If we can enable interrupts while waiting for the lock to become available, and we take an interrupt before entering the poll, and the handler takes a spinlock which ends up going into the slow state (invalidating the per-cpu "lock" and "want" values), then when the interrupt handler returns the event channel will remain pending so the poll will return immediately, causing it to return out to the main spinlock loop. Signed-off-by: Jeremy Fitzhardinge Link: http://lkml.kernel.org/r/1376058122-8248-12-git-send-email-raghavendra.kt@linux.vnet.ibm.com Reviewed-by: Konrad Rzeszutek Wilk Signed-off-by: Raghavendra K T Acked-by: Ingo Molnar Signed-off-by: H. Peter Anvin --- arch/x86/xen/spinlock.c | 46 +++++++++++++++++++++++++++++++++++------ 1 file changed, 40 insertions(+), 6 deletions(-) diff --git a/arch/x86/xen/spinlock.c b/arch/x86/xen/spinlock.c index 546112ed463f..0438b9324a72 100644 --- a/arch/x86/xen/spinlock.c +++ b/arch/x86/xen/spinlock.c @@ -142,7 +142,20 @@ static void xen_lock_spinning(struct arch_spinlock *lock, __ticket_t want) * partially setup state. */ local_irq_save(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; @@ -157,24 +170,43 @@ static void xen_lock_spinning(struct arch_spinlock *lock, __ticket_t want) /* Only check lock once pending cleared */ barrier(); - /* Mark entry to slowpath before doing the pickup test to make - sure we don't deadlock with an unlocker. */ + /* + * Mark entry to slowpath before doing the pickup test to make + * sure we don't deadlock with an unlocker. + */ __ticket_enter_slowpath(lock); - /* check again make sure it didn't become free while - we weren't looking */ + /* + * 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; } + + /* Allow interrupts while blocked */ + local_irq_restore(flags); + + /* + * If an interrupt happens here, it will leave the wakeup irq + * pending, which will cause xen_poll_irq() to return + * immediately. + */ + /* Block until irq becomes pending (or perhaps a spurious wakeup) */ xen_poll_irq(irq); add_stats(TAKEN_SLOW_SPURIOUS, !xen_test_irq_pending(irq)); + + local_irq_save(flags); + kstat_incr_irqs_this_cpu(irq, irq_to_desc(irq)); out: cpumask_clear_cpu(cpu, &waiting_cpus); w->lock = NULL; + local_irq_restore(flags); + spin_time_accum_blocked(start); } PV_CALLEE_SAVE_REGS_THUNK(xen_lock_spinning); @@ -188,7 +220,9 @@ static void xen_unlock_kick(struct arch_spinlock *lock, __ticket_t next) for_each_cpu(cpu, &waiting_cpus) { const struct xen_lock_waiting *w = &per_cpu(lock_waiting, cpu); - if (w->lock == lock && w->want == next) { + /* 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; From 3a3bb00d5c73f3ae7833f6534982b5b2f56ac9b4 Mon Sep 17 00:00:00 2001 From: Raghavendra K T Date: Fri, 9 Aug 2013 19:52:00 +0530 Subject: [PATCH 12/15] kvm uapi: Add KICK_CPU and PV_UNHALT definition to uapi These are needed by both guest and host. Originally-from: Srivatsa Vaddagiri Signed-off-by: Raghavendra K T Link: http://lkml.kernel.org/r/1376058122-8248-13-git-send-email-raghavendra.kt@linux.vnet.ibm.com Acked-by: Gleb Natapov Acked-by: Ingo Molnar Signed-off-by: H. Peter Anvin --- arch/x86/include/uapi/asm/kvm_para.h | 1 + include/uapi/linux/kvm_para.h | 1 + 2 files changed, 2 insertions(+) diff --git a/arch/x86/include/uapi/asm/kvm_para.h b/arch/x86/include/uapi/asm/kvm_para.h index 06fdbd987e97..94dc8ca434e0 100644 --- a/arch/x86/include/uapi/asm/kvm_para.h +++ b/arch/x86/include/uapi/asm/kvm_para.h @@ -23,6 +23,7 @@ #define KVM_FEATURE_ASYNC_PF 4 #define KVM_FEATURE_STEAL_TIME 5 #define KVM_FEATURE_PV_EOI 6 +#define KVM_FEATURE_PV_UNHALT 7 /* The last 8 bits are used to indicate how to interpret the flags field * in pvclock structure. If no bits are set, all flags are ignored. diff --git a/include/uapi/linux/kvm_para.h b/include/uapi/linux/kvm_para.h index cea2c5c72d26..2841f86eae0b 100644 --- a/include/uapi/linux/kvm_para.h +++ b/include/uapi/linux/kvm_para.h @@ -19,6 +19,7 @@ #define KVM_HC_MMU_OP 2 #define KVM_HC_FEATURES 3 #define KVM_HC_PPC_MAP_MAGIC_PAGE 4 +#define KVM_HC_KICK_CPU 5 /* * hypercalls use architecture specific From 1e20eb8557cdabf76473b09572be8aa8a2bb9bc0 Mon Sep 17 00:00:00 2001 From: Srivatsa Vaddagiri Date: Fri, 9 Aug 2013 19:52:01 +0530 Subject: [PATCH 13/15] kvm guest: Add configuration support to enable debug information for KVM Guests Signed-off-by: Srivatsa Vaddagiri Link: http://lkml.kernel.org/r/1376058122-8248-14-git-send-email-raghavendra.kt@linux.vnet.ibm.com Signed-off-by: Suzuki Poulose Signed-off-by: Raghavendra K T Acked-by: Gleb Natapov Acked-by: Ingo Molnar Signed-off-by: H. Peter Anvin --- arch/x86/Kconfig | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 112e71264542..b1fb846e6dac 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -657,6 +657,15 @@ config KVM_GUEST underlying device model, the host provides the guest with timing infrastructure such as time of day, and system time +config KVM_DEBUG_FS + bool "Enable debug information for KVM Guests in debugfs" + depends on KVM_GUEST && DEBUG_FS + default n + ---help--- + This option enables collection of various statistics for KVM guest. + Statistics are displayed in debugfs filesystem. Enabling this option + may incur significant overhead. + source "arch/x86/lguest/Kconfig" config PARAVIRT_TIME_ACCOUNTING From 92b75202e5e8790905f9441ccaea2456cc4621a5 Mon Sep 17 00:00:00 2001 From: Srivatsa Vaddagiri Date: Tue, 6 Aug 2013 14:55:41 +0530 Subject: [PATCH 14/15] kvm: Paravirtual ticketlocks support for linux guests running on KVM hypervisor During smp_boot_cpus paravirtualied KVM guest detects if the hypervisor has required feature (KVM_FEATURE_PV_UNHALT) to support pv-ticketlocks. If so, support for pv-ticketlocks is registered via pv_lock_ops. Use KVM_HC_KICK_CPU hypercall to wakeup waiting/halted vcpu. Signed-off-by: Srivatsa Vaddagiri Link: http://lkml.kernel.org/r/20130810193849.GA25260@linux.vnet.ibm.com Signed-off-by: Suzuki Poulose [Raghu: check_zero race fix, enum for kvm_contention_stat, jumplabel related changes, addition of safe_halt for irq enabled case, bailout spinning in nmi case(Gleb)] Signed-off-by: Raghavendra K T Acked-by: Gleb Natapov Acked-by: Ingo Molnar Signed-off-by: H. Peter Anvin --- arch/x86/include/asm/kvm_para.h | 14 +- arch/x86/kernel/kvm.c | 262 ++++++++++++++++++++++++++++++++ 2 files changed, 274 insertions(+), 2 deletions(-) diff --git a/arch/x86/include/asm/kvm_para.h b/arch/x86/include/asm/kvm_para.h index 695399f2d5eb..427afcbf3d55 100644 --- a/arch/x86/include/asm/kvm_para.h +++ b/arch/x86/include/asm/kvm_para.h @@ -118,10 +118,20 @@ void kvm_async_pf_task_wait(u32 token); void kvm_async_pf_task_wake(u32 token); u32 kvm_read_and_reset_pf_reason(void); extern void kvm_disable_steal_time(void); -#else -#define kvm_guest_init() do { } while (0) + +#ifdef CONFIG_PARAVIRT_SPINLOCKS +void __init kvm_spinlock_init(void); +#else /* !CONFIG_PARAVIRT_SPINLOCKS */ +static inline void kvm_spinlock_init(void) +{ +} +#endif /* CONFIG_PARAVIRT_SPINLOCKS */ + +#else /* CONFIG_KVM_GUEST */ +#define kvm_guest_init() do {} while (0) #define kvm_async_pf_task_wait(T) do {} while(0) #define kvm_async_pf_task_wake(T) do {} while(0) + static inline u32 kvm_read_and_reset_pf_reason(void) { return 0; diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index a96d32cc55b8..b8ef6305cf35 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -34,6 +34,7 @@ #include #include #include +#include #include #include #include @@ -419,6 +420,7 @@ static void __init kvm_smp_prepare_boot_cpu(void) WARN_ON(kvm_register_clock("primary cpu clock")); kvm_guest_cpu_init(); native_smp_prepare_boot_cpu(); + kvm_spinlock_init(); } static void kvm_guest_cpu_online(void *dummy) @@ -523,3 +525,263 @@ static __init int activate_jump_labels(void) return 0; } arch_initcall(activate_jump_labels); + +#ifdef CONFIG_PARAVIRT_SPINLOCKS + +/* Kick a cpu by its apicid. Used to wake up a halted vcpu */ +void kvm_kick_cpu(int cpu) +{ + int apicid; + unsigned long flags = 0; + + apicid = per_cpu(x86_cpu_to_apicid, cpu); + kvm_hypercall2(KVM_HC_KICK_CPU, flags, apicid); +} + +enum kvm_contention_stat { + TAKEN_SLOW, + TAKEN_SLOW_PICKUP, + RELEASED_SLOW, + RELEASED_SLOW_KICKED, + NR_CONTENTION_STATS +}; + +#ifdef CONFIG_KVM_DEBUG_FS +#define HISTO_BUCKETS 30 + +static struct kvm_spinlock_stats +{ + u32 contention_stats[NR_CONTENTION_STATS]; + u32 histo_spin_blocked[HISTO_BUCKETS+1]; + u64 time_blocked; +} spinlock_stats; + +static u8 zero_stats; + +static inline void check_zero(void) +{ + u8 ret; + u8 old; + + old = ACCESS_ONCE(zero_stats); + if (unlikely(old)) { + ret = cmpxchg(&zero_stats, old, 0); + /* This ensures only one fellow resets the stat */ + if (ret == old) + memset(&spinlock_stats, 0, sizeof(spinlock_stats)); + } +} + +static inline void add_stats(enum kvm_contention_stat var, u32 val) +{ + check_zero(); + spinlock_stats.contention_stats[var] += val; +} + + +static inline u64 spin_time_start(void) +{ + return sched_clock(); +} + +static void __spin_time_accum(u64 delta, u32 *array) +{ + unsigned index; + + index = ilog2(delta); + check_zero(); + + if (index < HISTO_BUCKETS) + array[index]++; + else + array[HISTO_BUCKETS]++; +} + +static inline void spin_time_accum_blocked(u64 start) +{ + u32 delta; + + delta = sched_clock() - start; + __spin_time_accum(delta, spinlock_stats.histo_spin_blocked); + spinlock_stats.time_blocked += delta; +} + +static struct dentry *d_spin_debug; +static struct dentry *d_kvm_debug; + +struct dentry *kvm_init_debugfs(void) +{ + d_kvm_debug = debugfs_create_dir("kvm", NULL); + if (!d_kvm_debug) + printk(KERN_WARNING "Could not create 'kvm' debugfs directory\n"); + + return d_kvm_debug; +} + +static int __init kvm_spinlock_debugfs(void) +{ + struct dentry *d_kvm; + + d_kvm = kvm_init_debugfs(); + if (d_kvm == NULL) + return -ENOMEM; + + d_spin_debug = debugfs_create_dir("spinlocks", d_kvm); + + debugfs_create_u8("zero_stats", 0644, d_spin_debug, &zero_stats); + + debugfs_create_u32("taken_slow", 0444, d_spin_debug, + &spinlock_stats.contention_stats[TAKEN_SLOW]); + debugfs_create_u32("taken_slow_pickup", 0444, d_spin_debug, + &spinlock_stats.contention_stats[TAKEN_SLOW_PICKUP]); + + debugfs_create_u32("released_slow", 0444, d_spin_debug, + &spinlock_stats.contention_stats[RELEASED_SLOW]); + debugfs_create_u32("released_slow_kicked", 0444, d_spin_debug, + &spinlock_stats.contention_stats[RELEASED_SLOW_KICKED]); + + debugfs_create_u64("time_blocked", 0444, d_spin_debug, + &spinlock_stats.time_blocked); + + debugfs_create_u32_array("histo_blocked", 0444, d_spin_debug, + spinlock_stats.histo_spin_blocked, HISTO_BUCKETS + 1); + + return 0; +} +fs_initcall(kvm_spinlock_debugfs); +#else /* !CONFIG_KVM_DEBUG_FS */ +static inline void add_stats(enum kvm_contention_stat var, u32 val) +{ +} + +static inline u64 spin_time_start(void) +{ + return 0; +} + +static inline void spin_time_accum_blocked(u64 start) +{ +} +#endif /* CONFIG_KVM_DEBUG_FS */ + +struct kvm_lock_waiting { + struct arch_spinlock *lock; + __ticket_t want; +}; + +/* cpus 'waiting' on a spinlock to become available */ +static cpumask_t waiting_cpus; + +/* Track spinlock on which a cpu is waiting */ +static DEFINE_PER_CPU(struct kvm_lock_waiting, klock_waiting); + +static void kvm_lock_spinning(struct arch_spinlock *lock, __ticket_t want) +{ + struct kvm_lock_waiting *w; + int cpu; + u64 start; + unsigned long flags; + + if (in_nmi()) + return; + + w = &__get_cpu_var(klock_waiting); + cpu = smp_processor_id(); + start = spin_time_start(); + + /* + * Make sure an interrupt handler can't upset things in a + * partially setup state. + */ + local_irq_save(flags); + + /* + * 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, 1); + + /* + * This uses set_bit, which is atomic but we should not rely on its + * reordering gurantees. So barrier is needed after this call. + */ + cpumask_set_cpu(cpu, &waiting_cpus); + + barrier(); + + /* + * Mark entry to slowpath before doing the pickup test to make + * sure we don't deadlock with an unlocker. + */ + __ticket_enter_slowpath(lock); + + /* + * 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; + } + + /* + * halt until it's our turn and kicked. Note that we do safe halt + * for irq enabled case to avoid hang when lock info is overwritten + * in irq spinlock slowpath and no spurious interrupt occur to save us. + */ + if (arch_irqs_disabled_flags(flags)) + halt(); + else + safe_halt(); + +out: + cpumask_clear_cpu(cpu, &waiting_cpus); + w->lock = NULL; + local_irq_restore(flags); + spin_time_accum_blocked(start); +} +PV_CALLEE_SAVE_REGS_THUNK(kvm_lock_spinning); + +/* Kick vcpu waiting on @lock->head to reach value @ticket */ +static void kvm_unlock_kick(struct arch_spinlock *lock, __ticket_t ticket) +{ + int cpu; + + add_stats(RELEASED_SLOW, 1); + for_each_cpu(cpu, &waiting_cpus) { + const struct kvm_lock_waiting *w = &per_cpu(klock_waiting, cpu); + if (ACCESS_ONCE(w->lock) == lock && + ACCESS_ONCE(w->want) == ticket) { + add_stats(RELEASED_SLOW_KICKED, 1); + kvm_kick_cpu(cpu); + break; + } + } +} + +/* + * Setup pv_lock_ops to exploit KVM_FEATURE_PV_UNHALT if present. + */ +void __init kvm_spinlock_init(void) +{ + if (!kvm_para_available()) + return; + /* Does host kernel support KVM_FEATURE_PV_UNHALT? */ + if (!kvm_para_has_feature(KVM_FEATURE_PV_UNHALT)) + return; + + printk(KERN_INFO "KVM setup paravirtual spinlock\n"); + + static_key_slow_inc(¶virt_ticketlocks_enabled); + + pv_lock_ops.lock_spinning = PV_CALLEE_SAVE(kvm_lock_spinning); + pv_lock_ops.unlock_kick = kvm_unlock_kick; +} +#endif /* CONFIG_PARAVIRT_SPINLOCKS */ From 36bd621337c91a1ecda588e5bbbae8dd9698bae7 Mon Sep 17 00:00:00 2001 From: Raghavendra K T Date: Fri, 16 Aug 2013 15:08:41 +0530 Subject: [PATCH 15/15] x86/kvm/guest: Fix sparse warning: "symbol 'klock_waiting' was not declared as static" It was not declared as static since it was thought to be used by pv-flushtlb earlier. Signed-off-by: Raghavendra K T Cc: Cc: Cc: Jiri Kosina Link: http://lkml.kernel.org/r/1376645921-8056-1-git-send-email-raghavendra.kt@linux.vnet.ibm.com Signed-off-by: Ingo Molnar --- arch/x86/kernel/kvm.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index b8ef6305cf35..56e2fa4a8b13 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -529,7 +529,7 @@ arch_initcall(activate_jump_labels); #ifdef CONFIG_PARAVIRT_SPINLOCKS /* Kick a cpu by its apicid. Used to wake up a halted vcpu */ -void kvm_kick_cpu(int cpu) +static void kvm_kick_cpu(int cpu) { int apicid; unsigned long flags = 0;