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

Pull locking updates from Ingo Molnar:
 "The main changes in this cycle were:

   - rwsem micro-optimizations (Davidlohr Bueso)

   - Improve the implementation and optimize the performance of
     percpu-rwsems. (Peter Zijlstra.)

   - Convert all lglock users to better facilities such as percpu-rwsems
     or percpu-spinlocks and remove lglocks. (Peter Zijlstra)

   - Remove the ticket (spin)lock implementation. (Peter Zijlstra)

   - Korean translation of memory-barriers.txt and related fixes to the
     English document. (SeongJae Park)

   - misc fixes and cleanups"

* 'locking-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (24 commits)
  x86/cmpxchg, locking/atomics: Remove superfluous definitions
  x86, locking/spinlocks: Remove ticket (spin)lock implementation
  locking/lglock: Remove lglock implementation
  stop_machine: Remove stop_cpus_lock and lg_double_lock/unlock()
  fs/locks: Use percpu_down_read_preempt_disable()
  locking/percpu-rwsem: Add down_read_preempt_disable()
  fs/locks: Replace lg_local with a per-cpu spinlock
  fs/locks: Replace lg_global with a percpu-rwsem
  locking/percpu-rwsem: Add DEFINE_STATIC_PERCPU_RWSEMand percpu_rwsem_assert_held()
  locking/pv-qspinlock: Use cmpxchg_release() in __pv_queued_spin_unlock()
  locking/rwsem, x86: Drop a bogus cc clobber
  futex: Add some more function commentry
  locking/hung_task: Show all locks
  locking/rwsem: Scan the wait_list for readers only once
  locking/rwsem: Remove a few useless comments
  locking/rwsem: Return void in __rwsem_mark_wake()
  locking, rcu, cgroup: Avoid synchronize_sched() in __cgroup_procs_write()
  locking/Documentation: Add Korean translation
  locking/Documentation: Fix a typo of example result
  locking/Documentation: Fix wrong section reference
  ...

4 files changed, 4 insertions, 256 deletions

diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index 1726c4c12336..865058d087ac 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -575,9 +575,6 @@ static void kvm_kick_cpu(int cpu)
 	kvm_hypercall2(KVM_HC_KICK_CPU, flags, apicid);
 }
 
-
-#ifdef CONFIG_QUEUED_SPINLOCKS
-
 #include <asm/qspinlock.h>
 
 static void kvm_wait(u8 *ptr, u8 val)
@@ -606,243 +603,6 @@ out:
 	local_irq_restore(flags);
 }
 
-#else /* !CONFIG_QUEUED_SPINLOCKS */
-
-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 = 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 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;
-
-static struct dentry *kvm_init_debugfs(void)
-{
-	d_kvm_debug = debugfs_create_dir("kvm-guest", 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);
-
-__visible void kvm_lock_spinning(struct arch_spinlock *lock, __ticket_t want)
-{
-	struct kvm_lock_waiting *w;
-	int cpu;
-	u64 start;
-	unsigned long flags;
-	__ticket_t head;
-
-	if (in_nmi())
-		return;
-
-	w = this_cpu_ptr(&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);
-
-	/* 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;
-	}
-
-	/*
-	 * 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 (READ_ONCE(w->lock) == lock &&
-		    READ_ONCE(w->want) == ticket) {
-			add_stats(RELEASED_SLOW_KICKED, 1);
-			kvm_kick_cpu(cpu);
-			break;
-		}
-	}
-}
-
-#endif /* !CONFIG_QUEUED_SPINLOCKS */
-
 /*
  * Setup pv_lock_ops to exploit KVM_FEATURE_PV_UNHALT if present.
  */
@@ -854,16 +614,11 @@ void __init kvm_spinlock_init(void)
 	if (!kvm_para_has_feature(KVM_FEATURE_PV_UNHALT))
 		return;
 
-#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 = kvm_wait;
 	pv_lock_ops.kick = kvm_kick_cpu;
-#else /* !CONFIG_QUEUED_SPINLOCKS */
-	pv_lock_ops.lock_spinning = PV_CALLEE_SAVE(kvm_lock_spinning);
-	pv_lock_ops.unlock_kick = kvm_unlock_kick;
-#endif
 }
 
 static __init int kvm_spinlock_init_jump(void)
diff --git a/arch/x86/kernel/paravirt-spinlocks.c b/arch/x86/kernel/paravirt-spinlocks.c
index 1939a0269377..2c55a003b793 100644
--- a/arch/x86/kernel/paravirt-spinlocks.c
+++ b/arch/x86/kernel/paravirt-spinlocks.c
@@ -8,7 +8,6 @@
 
 #include <asm/paravirt.h>
 
-#ifdef CONFIG_QUEUED_SPINLOCKS
 __visible void __native_queued_spin_unlock(struct qspinlock *lock)
 {
 	native_queued_spin_unlock(lock);
@@ -21,19 +20,13 @@ bool pv_is_native_spin_unlock(void)
 	return pv_lock_ops.queued_spin_unlock.func ==
 		__raw_callee_save___native_queued_spin_unlock;
 }
-#endif
 
 struct pv_lock_ops pv_lock_ops = {
 #ifdef CONFIG_SMP
-#ifdef CONFIG_QUEUED_SPINLOCKS
 	.queued_spin_lock_slowpath = native_queued_spin_lock_slowpath,
 	.queued_spin_unlock = PV_CALLEE_SAVE(__native_queued_spin_unlock),
 	.wait = paravirt_nop,
 	.kick = paravirt_nop,
-#else /* !CONFIG_QUEUED_SPINLOCKS */
-	.lock_spinning = __PV_IS_CALLEE_SAVE(paravirt_nop),
-	.unlock_kick = paravirt_nop,
-#endif /* !CONFIG_QUEUED_SPINLOCKS */
 #endif /* SMP */
 };
 EXPORT_SYMBOL(pv_lock_ops);
diff --git a/arch/x86/kernel/paravirt_patch_32.c b/arch/x86/kernel/paravirt_patch_32.c
index 158dc0650d5d..920c6ae08592 100644
--- a/arch/x86/kernel/paravirt_patch_32.c
+++ b/arch/x86/kernel/paravirt_patch_32.c
@@ -10,7 +10,7 @@ DEF_NATIVE(pv_mmu_ops, write_cr3, "mov %eax, %cr3");
 DEF_NATIVE(pv_mmu_ops, read_cr3, "mov %cr3, %eax");
 DEF_NATIVE(pv_cpu_ops, clts, "clts");
 
-#if defined(CONFIG_PARAVIRT_SPINLOCKS) && defined(CONFIG_QUEUED_SPINLOCKS)
+#if defined(CONFIG_PARAVIRT_SPINLOCKS)
 DEF_NATIVE(pv_lock_ops, queued_spin_unlock, "movb $0, (%eax)");
 #endif
 
@@ -49,7 +49,7 @@ unsigned native_patch(u8 type, u16 clobbers, void *ibuf,
 		PATCH_SITE(pv_mmu_ops, read_cr3);
 		PATCH_SITE(pv_mmu_ops, write_cr3);
 		PATCH_SITE(pv_cpu_ops, clts);
-#if defined(CONFIG_PARAVIRT_SPINLOCKS) && defined(CONFIG_QUEUED_SPINLOCKS)
+#if defined(CONFIG_PARAVIRT_SPINLOCKS)
 		case PARAVIRT_PATCH(pv_lock_ops.queued_spin_unlock):
 			if (pv_is_native_spin_unlock()) {
 				start = start_pv_lock_ops_queued_spin_unlock;
diff --git a/arch/x86/kernel/paravirt_patch_64.c b/arch/x86/kernel/paravirt_patch_64.c
index e70087a04cc8..bb3840cedb4f 100644
--- a/arch/x86/kernel/paravirt_patch_64.c
+++ b/arch/x86/kernel/paravirt_patch_64.c
@@ -19,7 +19,7 @@ DEF_NATIVE(pv_cpu_ops, swapgs, "swapgs");
 DEF_NATIVE(, mov32, "mov %edi, %eax");
 DEF_NATIVE(, mov64, "mov %rdi, %rax");
 
-#if defined(CONFIG_PARAVIRT_SPINLOCKS) && defined(CONFIG_QUEUED_SPINLOCKS)
+#if defined(CONFIG_PARAVIRT_SPINLOCKS)
 DEF_NATIVE(pv_lock_ops, queued_spin_unlock, "movb $0, (%rdi)");
 #endif
 
@@ -61,7 +61,7 @@ unsigned native_patch(u8 type, u16 clobbers, void *ibuf,
 		PATCH_SITE(pv_cpu_ops, clts);
 		PATCH_SITE(pv_mmu_ops, flush_tlb_single);
 		PATCH_SITE(pv_cpu_ops, wbinvd);
-#if defined(CONFIG_PARAVIRT_SPINLOCKS) && defined(CONFIG_QUEUED_SPINLOCKS)
+#if defined(CONFIG_PARAVIRT_SPINLOCKS)
 		case PARAVIRT_PATCH(pv_lock_ops.queued_spin_unlock):
 			if (pv_is_native_spin_unlock()) {
 				start = start_pv_lock_ops_queued_spin_unlock;