Message-Id: <55f8f62ffbdd2d0269398a33e879afad2853b48f.1317763862.git.jeremy.fitzhardinge@citrix.com>
Date:	Tue,  4 Oct 2011 16:31:15 -0700
From:	Jeremy Fitzhardinge <jeremy@...p.org>
To:	"H. Peter Anvin" <hpa@...or.com>
Cc:	Linus Torvalds <torvalds@...ux-foundation.org>,
	Peter Zijlstra <peterz@...radead.org>,
	Ingo Molnar <mingo@...e.hu>,
	the arch/x86 maintainers <x86@...nel.org>,
	Linux Kernel Mailing List <linux-kernel@...r.kernel.org>,
	Nick Piggin <npiggin@...nel.dk>, Avi Kivity <avi@...hat.com>,
	Marcelo Tosatti <mtosatti@...hat.com>,
	KVM <kvm@...r.kernel.org>, Andi Kleen <andi@...stfloor.org>,
	Xen Devel <xen-devel@...ts.xensource.com>,
	Jeremy Fitzhardinge <jeremy.fitzhardinge@...rix.com>,
	Srivatsa Vaddagiri <vatsa@...ux.vnet.ibm.com>,
	Stephan Diestelhorst <stephan.diestelhorst@....com>
Subject: [PATCH RFC V4 09/11] x86/ticketlock: add slowpath logic

From: Jeremy Fitzhardinge <jeremy.fitzhardinge@...rix.com>

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 xadd to atomically update the head counter
and fetch the tail to read the slowpath flag.  Since "head" is in the
least-significant position, there's a possibility that it could overflow
into "tail".  If this is about to happen, then we can also add "-1" to
tail to compensate for the carry overlflow.  This is safe because while
we hold the lock, we own "head", so we can inspect it without risk of
it changing.

(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 <jeremy.fitzhardinge@...rix.com>
Signed-off-by: Srivatsa Vaddagiri <vatsa@...ux.vnet.ibm.com>
Cc: Stephan Diestelhorst <stephan.diestelhorst@....com>
---
 arch/x86/include/asm/paravirt.h       |    2 +-
 arch/x86/include/asm/spinlock.h       |   90 +++++++++++++++++++++++++--------
 arch/x86/include/asm/spinlock_types.h |    2 +
 arch/x86/kernel/paravirt-spinlocks.c  |    3 +
 arch/x86/xen/spinlock.c               |    6 ++
 5 files changed, 81 insertions(+), 22 deletions(-)

diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index 50281c7..13b3d8b 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -755,7 +755,7 @@ 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, __ticket_t ticket)
+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 dd155f7..7dbe028 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
  *
@@ -40,29 +43,27 @@
 /* How long a lock should spin before we consider blocking */
 #define SPIN_THRESHOLD	(1 << 11)
 
-#ifndef CONFIG_PARAVIRT_SPINLOCKS
+#ifdef CONFIG_PARAVIRT_SPINLOCKS
+
+extern struct jump_label_key paravirt_ticketlocks_enabled;
 
-static __always_inline void __ticket_lock_spinning(struct arch_spinlock *lock, __ticket_t ticket)
+static inline void __ticket_enter_slowpath(arch_spinlock_t *lock)
 {
+	set_bit(0, (volatile unsigned long *)&lock->tickets.tail);
 }
 
-static __always_inline void ____ticket_unlock_kick(struct arch_spinlock *lock, __ticket_t ticket)
+#else  /* !CONFIG_PARAVIRT_SPINLOCKS */
+static __always_inline void __ticket_lock_spinning(arch_spinlock_t *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)
+static inline void __ticket_unlock_kick(arch_spinlock_t *lock, __ticket_t ticket)
 {
-	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
  * the queue, and the other indicating the current tail. The lock is acquired
@@ -76,20 +77,22 @@ static __always_inline void __ticket_unlock_kick(struct arch_spinlock *lock, __t
  * 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 +104,7 @@ 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 +113,57 @@ 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 __always_inline void arch_spin_unlock(arch_spinlock_t *lock)
+static inline void __ticket_unlock_slowpath(arch_spinlock_t *lock,
+					    arch_spinlock_t old)
 {
-	__ticket_t next = lock->tickets.head + TICKET_LOCK_INC;
+	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);
+	}
+}
 
-	__add(&lock->tickets.head, TICKET_LOCK_INC, UNLOCK_LOCK_PREFIX);
-	__ticket_unlock_kick(lock, next);
+static __always_inline void arch_spin_unlock(arch_spinlock_t *lock)
+{
+	if (TICKET_SLOWPATH_FLAG &&
+	    unlikely(static_branch(&paravirt_ticketlocks_enabled))) {
+		arch_spinlock_t prev;
+		__ticketpair_t inc = TICKET_LOCK_INC;
+
+		/*
+		 * Use xadd to update "head" to perform the unlock and
+		 * atomically fetch the state of the flag.  Since
+		 * "head" is the least-significant part of the
+		 * head_tail pair, it may overflow into tail if it is
+		 * about to wrap.  If this happens, compensate by
+		 * adding -1 to tail as well.
+		 */
+		if (lock->tickets.head >= (1 << TICKET_SHIFT) - TICKET_LOCK_INC)
+			inc += -1 << TICKET_SHIFT;
+
+		prev.head_tail = xadd(&lock->head_tail, inc);
+
+		if (unlikely(prev.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 aa9a205..407f7f7 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 4251c1d..6ca1d33 100644
--- a/arch/x86/kernel/paravirt-spinlocks.c
+++ b/arch/x86/kernel/paravirt-spinlocks.c
@@ -4,6 +4,7 @@
  */
 #include <linux/spinlock.h>
 #include <linux/module.h>
+#include <linux/jump_label.h>
 
 #include <asm/paravirt.h>
 
@@ -15,3 +16,5 @@ struct pv_lock_ops pv_lock_ops = {
 };
 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/spinlock.c b/arch/x86/xen/spinlock.c
index 431d231..0a552ec 100644
--- a/arch/x86/xen/spinlock.c
+++ b/arch/x86/xen/spinlock.c
@@ -124,6 +124,10 @@ 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) {
@@ -205,6 +209,8 @@ void __init xen_init_spinlocks(void)
 		return;
 	}
 
+	jump_label_inc(&paravirt_ticketlocks_enabled);
+
 	pv_lock_ops.lock_spinning = PV_CALLEE_SAVE(xen_lock_spinning);
 	pv_lock_ops.unlock_kick = xen_unlock_kick;
 }
-- 
1.7.6.4

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/

Powered by blists - more mailing lists