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 <jeremy@goop.org>
Link: http://lkml.kernel.org/r/1376058122-8248-6-git-send-email-raghavendra.kt@linux.vnet.ibm.com
Reviewed-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
 [ 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 <raghavendra.kt@linux.vnet.ibm.com>
Acked-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>

arch/x86/xen/spinlock.c

@@ -17,45 +17,44 @@
 #include "xen-ops.h"
 #include "debugfs.h"
 
-#ifdef CONFIG_XEN_DEBUG_FS
-static struct xen_spinlock_stats
-{
-	u64 taken;
-	u32 taken_slow;
-	u32 taken_slow_nested;
-	u32 taken_slow_pickup;
-	u32 taken_slow_spurious;
-	u32 taken_slow_irqenable;
+enum xen_contention_stat {
+	TAKEN_SLOW,
+	TAKEN_SLOW_PICKUP,
+	TAKEN_SLOW_SPURIOUS,
+	RELEASED_SLOW,
+	RELEASED_SLOW_KICKED,
+	NR_CONTENTION_STATS
+};
 
-	u64 released;
-	u32 released_slow;
-	u32 released_slow_kicked;
 
+#ifdef CONFIG_XEN_DEBUG_FS
 #define HISTO_BUCKETS	30
-	u32 histo_spin_total[HISTO_BUCKETS+1];
-	u32 histo_spin_spinning[HISTO_BUCKETS+1];
+static struct xen_spinlock_stats
+{
+	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);
-
-	ADD_STATS(taken_slow, 1);
-	ADD_STATS(taken_slow_nested, prev != NULL);
-
-	do {
-		unsigned long flags;
-
-		/* clear pending */
-		xen_clear_irq_pending(irq);
-
-		/* check again make sure it didn't become free while
-		   we weren't looking  */
-		ret = xen_spin_trylock(lock);
-		if (ret) {
-			ADD_STATS(taken_slow_pickup, 1);
-
-			/*
-			 * If we interrupted another spinlock while it
-			 * was blocking, make sure it doesn't block
-			 * without rechecking the lock.
-			 */
-			if (prev != NULL)
-				xen_set_irq_pending(irq);
-			goto out;
-		}
+	/*
+	 * Make sure an interrupt handler can't upset things in a
+	 * partially setup state.
+	 */
+	local_irq_save(flags);
 
-		flags = arch_local_save_flags();
-		if (irq_enable) {
-			ADD_STATS(taken_slow_irqenable, 1);
-			raw_local_irq_enable();
-		}
+	w->want = want;
+	smp_wmb();
+	w->lock = lock;
 
-		/*
-		 * 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);
+	/* This uses set_bit, which atomic and therefore a barrier */
+	cpumask_set_cpu(cpu, &waiting_cpus);
+	add_stats(TAKEN_SLOW, 1);
 
-		raw_local_irq_restore(flags);
+	/* clear pending */
+	xen_clear_irq_pending(irq);
 
-		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_cpu(cpu, &waiting_cpus) {
+		const struct xen_lock_waiting *w = &per_cpu(lock_waiting, cpu);
 
-	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);
+		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);