2 files changed, 41 insertions, 249 deletions

diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index e2cf8fcea6bb..f1d2182e071f 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -1924,6 +1924,45 @@ static void xen_set_cpu_features(struct cpuinfo_x86 *c)
 	}
 }
 
+static void xen_pin_vcpu(int cpu)
+{
+	static bool disable_pinning;
+	struct sched_pin_override pin_override;
+	int ret;
+
+	if (disable_pinning)
+		return;
+
+	pin_override.pcpu = cpu;
+	ret = HYPERVISOR_sched_op(SCHEDOP_pin_override, &pin_override);
+
+	/* Ignore errors when removing override. */
+	if (cpu < 0)
+		return;
+
+	switch (ret) {
+	case -ENOSYS:
+		pr_warn("Unable to pin on physical cpu %d. In case of problems consider vcpu pinning.\n",
+			cpu);
+		disable_pinning = true;
+		break;
+	case -EPERM:
+		WARN(1, "Trying to pin vcpu without having privilege to do so\n");
+		disable_pinning = true;
+		break;
+	case -EINVAL:
+	case -EBUSY:
+		pr_warn("Physical cpu %d not available for pinning. Check Xen cpu configuration.\n",
+			cpu);
+		break;
+	case 0:
+		break;
+	default:
+		WARN(1, "rc %d while trying to pin vcpu\n", ret);
+		disable_pinning = true;
+	}
+}
+
 const struct hypervisor_x86 x86_hyper_xen = {
 	.name			= "Xen",
 	.detect			= xen_platform,
@@ -1932,6 +1971,7 @@ const struct hypervisor_x86 x86_hyper_xen = {
 #endif
 	.x2apic_available	= xen_x2apic_para_available,
 	.set_cpu_features       = xen_set_cpu_features,
+	.pin_vcpu               = xen_pin_vcpu,
 };
 EXPORT_SYMBOL(x86_hyper_xen);
 
diff --git a/arch/x86/xen/spinlock.c b/arch/x86/xen/spinlock.c
index f42e78de1e10..3d6e0064cbfc 100644
--- a/arch/x86/xen/spinlock.c
+++ b/arch/x86/xen/spinlock.c
@@ -21,8 +21,6 @@ static DEFINE_PER_CPU(int, lock_kicker_irq) = -1;
 static DEFINE_PER_CPU(char *, irq_name);
 static bool xen_pvspin = true;
 
-#ifdef CONFIG_QUEUED_SPINLOCKS
-
 #include <asm/qspinlock.h>
 
 static void xen_qlock_kick(int cpu)
@@ -71,207 +69,6 @@ static void xen_qlock_wait(u8 *byte, u8 val)
 	xen_poll_irq(irq);
 }
 
-#else /* CONFIG_QUEUED_SPINLOCKS */
-
-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
-{
-	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 = READ_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 xen_contention_stat var, u32 val)
-{
-	check_zero();
-	spinlock_stats.contention_stats[var] += val;
-}
-
-static inline u64 spin_time_start(void)
-{
-	return xen_clocksource_read();
-}
-
-static void __spin_time_accum(u64 delta, u32 *array)
-{
-	unsigned 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 = xen_clocksource_read() - start;
-
-	__spin_time_accum(delta, spinlock_stats.histo_spin_blocked);
-	spinlock_stats.time_blocked += delta;
-}
-#else  /* !CONFIG_XEN_DEBUG_FS */
-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_blocked(u64 start)
-{
-}
-#endif  /* CONFIG_XEN_DEBUG_FS */
-
-struct xen_lock_waiting {
-	struct arch_spinlock *lock;
-	__ticket_t want;
-};
-
-static DEFINE_PER_CPU(struct xen_lock_waiting, lock_waiting);
-static cpumask_t waiting_cpus;
-
-__visible void xen_lock_spinning(struct arch_spinlock *lock, __ticket_t want)
-{
-	int irq = __this_cpu_read(lock_kicker_irq);
-	struct xen_lock_waiting *w = this_cpu_ptr(&lock_waiting);
-	int cpu = smp_processor_id();
-	u64 start;
-	__ticket_t head;
-	unsigned long flags;
-
-	/* If kicker interrupts not initialized yet, just spin */
-	if (irq == -1)
-		return;
-
-	start = spin_time_start();
-
-	/*
-	 * Make sure an interrupt handler can't upset things in a
-	 * 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;
-
-	/* 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);
-
-	/* 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);
-
-	/* make sure enter_slowpath, which is atomic does not cross the read */
-	smp_mb__after_atomic();
-
-	/*
-	 * check again make sure it didn't become free while
-	 * we weren't looking
-	 */
-	head = READ_ONCE(lock->tickets.head);
-	if (__tickets_equal(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_irq_this_cpu(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);
-
-static void xen_unlock_kick(struct arch_spinlock *lock, __ticket_t next)
-{
-	int cpu;
-
-	add_stats(RELEASED_SLOW, 1);
-
-	for_each_cpu(cpu, &waiting_cpus) {
-		const struct xen_lock_waiting *w = &per_cpu(lock_waiting, cpu);
-
-		/* Make sure we read lock before want */
-		if (READ_ONCE(w->lock) == lock &&
-		    READ_ONCE(w->want) == next) {
-			add_stats(RELEASED_SLOW_KICKED, 1);
-			xen_send_IPI_one(cpu, XEN_SPIN_UNLOCK_VECTOR);
-			break;
-		}
-	}
-}
-#endif /* CONFIG_QUEUED_SPINLOCKS */
-
 static irqreturn_t dummy_handler(int irq, void *dev_id)
 {
 	BUG();
@@ -334,16 +131,12 @@ void __init xen_init_spinlocks(void)
 		return;
 	}
 	printk(KERN_DEBUG "xen: PV spinlocks enabled\n");
-#ifdef CONFIG_QUEUED_SPINLOCKS
+
 	__pv_init_lock_hash();
 	pv_lock_ops.queued_spin_lock_slowpath = __pv_queued_spin_lock_slowpath;
 	pv_lock_ops.queued_spin_unlock = PV_CALLEE_SAVE(__pv_queued_spin_unlock);
 	pv_lock_ops.wait = xen_qlock_wait;
 	pv_lock_ops.kick = xen_qlock_kick;
-#else
-	pv_lock_ops.lock_spinning = PV_CALLEE_SAVE(xen_lock_spinning);
-	pv_lock_ops.unlock_kick = xen_unlock_kick;
-#endif
 }
 
 /*
@@ -372,44 +165,3 @@ static __init int xen_parse_nopvspin(char *arg)
 }
 early_param("xen_nopvspin", xen_parse_nopvspin);
 
-#if defined(CONFIG_XEN_DEBUG_FS) && !defined(CONFIG_QUEUED_SPINLOCKS)
-
-static struct dentry *d_spin_debug;
-
-static int __init xen_spinlock_debugfs(void)
-{
-	struct dentry *d_xen = xen_init_debugfs();
-
-	if (d_xen == NULL)
-		return -ENOMEM;
-
-	if (!xen_pvspin)
-		return 0;
-
-	d_spin_debug = debugfs_create_dir("spinlocks", d_xen);
-
-	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("taken_slow_spurious", 0444, d_spin_debug,
-			   &spinlock_stats.contention_stats[TAKEN_SLOW_SPURIOUS]);
-
-	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(xen_spinlock_debugfs);
-
-#endif	/* CONFIG_XEN_DEBUG_FS */