Merge branch 'x86-spinlocks-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 spinlock changes from Ingo Molnar:
 "The biggest change here are paravirtualized ticket spinlocks (PV
  spinlocks), which bring a nice speedup on various benchmarks.

  The KVM host side will come to you via the KVM tree"

* 'x86-spinlocks-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/kvm/guest: Fix sparse warning: "symbol 'klock_waiting' was not declared as static"
  kvm: Paravirtual ticketlocks support for linux guests running on KVM hypervisor
  kvm guest: Add configuration support to enable debug information for KVM Guests
  kvm uapi: Add KICK_CPU and PV_UNHALT definition to uapi
  xen, pvticketlock: Allow interrupts to be enabled while blocking
  x86, ticketlock: Add slowpath logic
  jump_label: Split jumplabel ratelimit
  x86, pvticketlock: When paravirtualizing ticket locks, increment by 2
  x86, pvticketlock: Use callee-save for lock_spinning
  xen, pvticketlocks: Add xen_nopvspin parameter to disable xen pv ticketlocks
  xen, pvticketlock: Xen implementation for PV ticket locks
  xen: Defer spinlock setup until boot CPU setup
  x86, ticketlock: Collapse a layer of functions
  x86, ticketlock: Don't inline _spin_unlock when using paravirt spinlocks
  x86, spinlock: Replace pv spinlocks with pv ticketlocks

6 files changed, 125 insertions, 80 deletions

diff --git a/arch/x86/include/asm/kvm_para.h b/arch/x86/include/asm/kvm_para.h
index 0644129..1df1159 100644
--- a/arch/x86/include/asm/kvm_para.h
+++ b/arch/x86/include/asm/kvm_para.h
@@ -112,10 +112,20 @@ 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/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index cfdc9ee..401f350 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_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 0617ff2..aab8f67 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 <asm/spinlock_types.h>
+#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);
+	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 e0e6684..bf156de 100644
--- a/arch/x86/include/asm/spinlock.h
+++ b/arch/x86/include/asm/spinlock.h
@@ -1,11 +1,14 @@
 #ifndef _ASM_X86_SPINLOCK_H
 #define _ASM_X86_SPINLOCK_H
 
+#include <linux/jump_label.h>
 #include <linux/atomic.h>
 #include <asm/page.h>
 #include <asm/processor.h>
 #include <linux/compiler.h>
 #include <asm/paravirt.h>
+#include <asm/bitops.h>
+
 /*
  * Your basic SMP spinlocks, allowing only a single CPU anywhere
  *
@@ -34,6 +37,31 @@
 # define UNLOCK_LOCK_PREFIX
 #endif
 
+/* How long a lock should spin before we consider blocking */
+#define SPIN_THRESHOLD	(1 << 15)
+
+extern struct static_key paravirt_ticketlocks_enabled;
+static __always_inline bool static_key_false(struct static_key *key);
+
+#ifdef CONFIG_PARAVIRT_SPINLOCKS
+
+static inline void __ticket_enter_slowpath(arch_spinlock_t *lock)
+{
+	set_bit(0, (volatile unsigned long *)&lock->tickets.tail);
+}
+
+#else  /* !CONFIG_PARAVIRT_SPINLOCKS */
+static __always_inline void __ticket_lock_spinning(arch_spinlock_t *lock,
+							__ticket_t ticket)
+{
+}
+static inline void __ticket_unlock_kick(arch_spinlock_t *lock,
+							__ticket_t ticket)
+{
+}
+
+#endif /* CONFIG_PARAVIRT_SPINLOCKS */
+
 static __always_inline int arch_spin_value_unlocked(arch_spinlock_t lock)
 {
 	return lock.tickets.head == lock.tickets.tail;
@@ -52,81 +80,101 @@ static __always_inline int arch_spin_value_unlocked(arch_spinlock_t lock)
  * in the high part, because a wide xadd increment of the low part would carry
  * up and contaminate the high part.
  */
-static __always_inline void __ticket_spin_lock(arch_spinlock_t *lock)
+static __always_inline void arch_spin_lock(arch_spinlock_t *lock)
 {
-	register struct __raw_tickets inc = { .tail = 1 };
+	register struct __raw_tickets inc = { .tail = TICKET_LOCK_INC };
 
 	inc = xadd(&lock->tickets, inc);
+	if (likely(inc.head == inc.tail))
+		goto out;
 
+	inc.tail &= ~TICKET_SLOWPATH_FLAG;
 	for (;;) {
-		if (inc.head == inc.tail)
-			break;
-		cpu_relax();
-		inc.head = ACCESS_ONCE(lock->tickets.head);
+		unsigned count = SPIN_THRESHOLD;
+
+		do {
+			if (ACCESS_ONCE(lock->tickets.head) == inc.tail)
+				goto out;
+			cpu_relax();
+		} while (--count);
+		__ticket_lock_spinning(lock, inc.tail);
 	}
-	barrier();		/* make sure nothing creeps before the lock is taken */
+out:	barrier();	/* make sure nothing creeps before the lock is taken */
 }
 
-static __always_inline int __ticket_spin_trylock(arch_spinlock_t *lock)
+static __always_inline int arch_spin_trylock(arch_spinlock_t *lock)
 {
 	arch_spinlock_t old, new;
 
 	old.tickets = ACCESS_ONCE(lock->tickets);
-	if (old.tickets.head != old.tickets.tail)
+	if (old.tickets.head != (old.tickets.tail & ~TICKET_SLOWPATH_FLAG))
 		return 0;
 
-	new.head_tail = old.head_tail + (1 << TICKET_SHIFT);
+	new.head_tail = old.head_tail + (TICKET_LOCK_INC << TICKET_SHIFT);
 
 	/* cmpxchg is a full barrier, so nothing can move before it */
 	return cmpxchg(&lock->head_tail, old.head_tail, new.head_tail) == old.head_tail;
 }
 
-static __always_inline void __ticket_spin_unlock(arch_spinlock_t *lock)
+static inline void __ticket_unlock_slowpath(arch_spinlock_t *lock,
+					    arch_spinlock_t old)
 {
-	__add(&lock->tickets.head, 1, UNLOCK_LOCK_PREFIX);
+	arch_spinlock_t new;
+
+	BUILD_BUG_ON(((__ticket_t)NR_CPUS) != NR_CPUS);
+
+	/* Perform the unlock on the "before" copy */
+	old.tickets.head += TICKET_LOCK_INC;
+
+	/* Clear the slowpath flag */
+	new.head_tail = old.head_tail & ~(TICKET_SLOWPATH_FLAG << TICKET_SHIFT);
+
+	/*
+	 * If the lock is uncontended, clear the flag - use cmpxchg in
+	 * case it changes behind our back though.
+	 */
+	if (new.tickets.head != new.tickets.tail ||
+	    cmpxchg(&lock->head_tail, old.head_tail,
+					new.head_tail) != old.head_tail) {
+		/*
+		 * Lock still has someone queued for it, so wake up an
+		 * appropriate waiter.
+		 */
+		__ticket_unlock_kick(lock, old.tickets.head);
+	}
 }
 
-static inline int __ticket_spin_is_locked(arch_spinlock_t *lock)
+static __always_inline void arch_spin_unlock(arch_spinlock_t *lock)
 {
-	struct __raw_tickets tmp = ACCESS_ONCE(lock->tickets);
+	if (TICKET_SLOWPATH_FLAG &&
+	    static_key_false(&paravirt_ticketlocks_enabled)) {
+		arch_spinlock_t prev;
 
-	return tmp.tail != tmp.head;
-}
+		prev = *lock;
+		add_smp(&lock->tickets.head, TICKET_LOCK_INC);
 
-static inline int __ticket_spin_is_contended(arch_spinlock_t *lock)
-{
-	struct __raw_tickets tmp = ACCESS_ONCE(lock->tickets);
+		/* add_smp() is a full mb() */
 
-	return (__ticket_t)(tmp.tail - tmp.head) > 1;
+		if (unlikely(lock->tickets.tail & TICKET_SLOWPATH_FLAG))
+			__ticket_unlock_slowpath(lock, prev);
+	} else
+		__add(&lock->tickets.head, TICKET_LOCK_INC, UNLOCK_LOCK_PREFIX);
 }
 
-#ifndef CONFIG_PARAVIRT_SPINLOCKS
-
 static inline int arch_spin_is_locked(arch_spinlock_t *lock)
 {
-	return __ticket_spin_is_locked(lock);
-}
-
-static inline int arch_spin_is_contended(arch_spinlock_t *lock)
-{
-	return __ticket_spin_is_contended(lock);
-}
-#define arch_spin_is_contended	arch_spin_is_contended
+	struct __raw_tickets tmp = ACCESS_ONCE(lock->tickets);
 
-static __always_inline void arch_spin_lock(arch_spinlock_t *lock)
-{
-	__ticket_spin_lock(lock);
+	return tmp.tail != tmp.head;
 }
 
-static __always_inline int arch_spin_trylock(arch_spinlock_t *lock)
+static inline int arch_spin_is_contended(arch_spinlock_t *lock)
 {
-	return __ticket_spin_trylock(lock);
-}
+	struct __raw_tickets tmp = ACCESS_ONCE(lock->tickets);
 
-static __always_inline void arch_spin_unlock(arch_spinlock_t *lock)
-{
-	__ticket_spin_unlock(lock);
+	return (__ticket_t)(tmp.tail - tmp.head) > TICKET_LOCK_INC;
 }
+#define arch_spin_is_contended	arch_spin_is_contended
 
 static __always_inline void arch_spin_lock_flags(arch_spinlock_t *lock,
 						  unsigned long flags)
@@ -134,8 +182,6 @@ static __always_inline void arch_spin_lock_flags(arch_spinlock_t *lock,
 	arch_spin_lock(lock);
 }
 
-#endif	/* CONFIG_PARAVIRT_SPINLOCKS */
-
 static inline void arch_spin_unlock_wait(arch_spinlock_t *lock)
 {
 	while (arch_spin_is_locked(lock))
diff --git a/arch/x86/include/asm/spinlock_types.h b/arch/x86/include/asm/spinlock_types.h
index ad0ad07..4f1bea1 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)
 
 typedef struct arch_spinlock {
diff --git a/arch/x86/include/uapi/asm/kvm_para.h b/arch/x86/include/uapi/asm/kvm_para.h
index 06fdbd9..94dc8ca 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.