Merge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull kvm updates from Paolo Bonzini:
 "ARM:
   - Move the arch-specific code into arch/arm64/kvm

   - Start the post-32bit cleanup

   - Cherry-pick a few non-invasive pre-NV patches

  x86:
   - Rework of TLB flushing

   - Rework of event injection, especially with respect to nested
     virtualization

   - Nested AMD event injection facelift, building on the rework of
     generic code and fixing a lot of corner cases

   - Nested AMD live migration support

   - Optimization for TSC deadline MSR writes and IPIs

   - Various cleanups

   - Asynchronous page fault cleanups (from tglx, common topic branch
     with tip tree)

   - Interrupt-based delivery of asynchronous "page ready" events (host
     side)

   - Hyper-V MSRs and hypercalls for guest debugging

   - VMX preemption timer fixes

  s390:
   - Cleanups

  Generic:
   - switch vCPU thread wakeup from swait to rcuwait

  The other architectures, and the guest side of the asynchronous page
  fault work, will come next week"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (256 commits)
  KVM: selftests: fix rdtsc() for vmx_tsc_adjust_test
  KVM: check userspace_addr for all memslots
  KVM: selftests: update hyperv_cpuid with SynDBG tests
  x86/kvm/hyper-v: Add support for synthetic debugger via hypercalls
  x86/kvm/hyper-v: enable hypercalls regardless of hypercall page
  x86/kvm/hyper-v: Add support for synthetic debugger interface
  x86/hyper-v: Add synthetic debugger definitions
  KVM: selftests: VMX preemption timer migration test
  KVM: nVMX: Fix VMX preemption timer migration
  x86/kvm/hyper-v: Explicitly align hcall param for kvm_hyperv_exit
  KVM: x86/pmu: Support full width counting
  KVM: x86/pmu: Tweak kvm_pmu_get_msr to pass 'struct msr_data' in
  KVM: x86: announce KVM_FEATURE_ASYNC_PF_INT
  KVM: x86: acknowledgment mechanism for async pf page ready notifications
  KVM: x86: interrupt based APF 'page ready' event delivery
  KVM: introduce kvm_read_guest_offset_cached()
  KVM: rename kvm_arch_can_inject_async_page_present() to kvm_arch_can_dequeue_async_page_present()
  KVM: x86: extend struct kvm_vcpu_pv_apf_data with token info
  Revert "KVM: async_pf: Fix #DF due to inject "Page not Present" and "Page Ready" exceptions simultaneously"
  KVM: VMX: Replace zero-length array with flexible-array
  ...

3 files changed, 110 insertions, 24 deletions

diff --git a/kernel/exit.c b/kernel/exit.c
index c81805a6e03b..c300253a7b8e 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -228,8 +228,9 @@ repeat:
 		goto repeat;
 }
 
-void rcuwait_wake_up(struct rcuwait *w)
+int rcuwait_wake_up(struct rcuwait *w)
 {
+	int ret = 0;
 	struct task_struct *task;
 
 	rcu_read_lock();
@@ -237,7 +238,7 @@ void rcuwait_wake_up(struct rcuwait *w)
 	/*
 	 * Order condition vs @task, such that everything prior to the load
 	 * of @task is visible. This is the condition as to why the user called
-	 * rcuwait_trywake() in the first place. Pairs with set_current_state()
+	 * rcuwait_wake() in the first place. Pairs with set_current_state()
 	 * barrier (A) in rcuwait_wait_event().
 	 *
 	 *    WAIT                WAKE
@@ -249,8 +250,10 @@ void rcuwait_wake_up(struct rcuwait *w)
 
 	task = rcu_dereference(w->task);
 	if (task)
-		wake_up_process(task);
+		ret = wake_up_process(task);
 	rcu_read_unlock();
+
+	return ret;
 }
 EXPORT_SYMBOL_GPL(rcuwait_wake_up);
 
diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index dd3cc0854c32..4c057dd8e93b 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -3616,13 +3616,10 @@ mark_held_locks(struct task_struct *curr, enum lock_usage_bit base_bit)
 /*
  * Hardirqs will be enabled:
  */
-static void __trace_hardirqs_on_caller(unsigned long ip)
+static void __trace_hardirqs_on_caller(void)
 {
 	struct task_struct *curr = current;
 
-	/* we'll do an OFF -> ON transition: */
-	curr->hardirqs_enabled = 1;
-
 	/*
 	 * We are going to turn hardirqs on, so set the
 	 * usage bit for all held locks:
@@ -3635,15 +3632,19 @@ static void __trace_hardirqs_on_caller(unsigned long ip)
 	 * this bit from being set before)
 	 */
 	if (curr->softirqs_enabled)
-		if (!mark_held_locks(curr, LOCK_ENABLED_SOFTIRQ))
-			return;
-
-	curr->hardirq_enable_ip = ip;
-	curr->hardirq_enable_event = ++curr->irq_events;
-	debug_atomic_inc(hardirqs_on_events);
+		mark_held_locks(curr, LOCK_ENABLED_SOFTIRQ);
 }
 
-void lockdep_hardirqs_on(unsigned long ip)
+/**
+ * lockdep_hardirqs_on_prepare - Prepare for enabling interrupts
+ * @ip:		Caller address
+ *
+ * Invoked before a possible transition to RCU idle from exit to user or
+ * guest mode. This ensures that all RCU operations are done before RCU
+ * stops watching. After the RCU transition lockdep_hardirqs_on() has to be
+ * invoked to set the final state.
+ */
+void lockdep_hardirqs_on_prepare(unsigned long ip)
 {
 	if (unlikely(!debug_locks || current->lockdep_recursion))
 		return;
@@ -3679,20 +3680,62 @@ void lockdep_hardirqs_on(unsigned long ip)
 	if (DEBUG_LOCKS_WARN_ON(current->hardirq_context))
 		return;
 
+	current->hardirq_chain_key = current->curr_chain_key;
+
 	current->lockdep_recursion++;
-	__trace_hardirqs_on_caller(ip);
+	__trace_hardirqs_on_caller();
 	lockdep_recursion_finish();
 }
-NOKPROBE_SYMBOL(lockdep_hardirqs_on);
+EXPORT_SYMBOL_GPL(lockdep_hardirqs_on_prepare);
+
+void noinstr lockdep_hardirqs_on(unsigned long ip)
+{
+	struct task_struct *curr = current;
+
+	if (unlikely(!debug_locks || curr->lockdep_recursion))
+		return;
+
+	if (curr->hardirqs_enabled) {
+		/*
+		 * Neither irq nor preemption are disabled here
+		 * so this is racy by nature but losing one hit
+		 * in a stat is not a big deal.
+		 */
+		__debug_atomic_inc(redundant_hardirqs_on);
+		return;
+	}
+
+	/*
+	 * We're enabling irqs and according to our state above irqs weren't
+	 * already enabled, yet we find the hardware thinks they are in fact
+	 * enabled.. someone messed up their IRQ state tracing.
+	 */
+	if (DEBUG_LOCKS_WARN_ON(!irqs_disabled()))
+		return;
+
+	/*
+	 * Ensure the lock stack remained unchanged between
+	 * lockdep_hardirqs_on_prepare() and lockdep_hardirqs_on().
+	 */
+	DEBUG_LOCKS_WARN_ON(current->hardirq_chain_key !=
+			    current->curr_chain_key);
+
+	/* we'll do an OFF -> ON transition: */
+	curr->hardirqs_enabled = 1;
+	curr->hardirq_enable_ip = ip;
+	curr->hardirq_enable_event = ++curr->irq_events;
+	debug_atomic_inc(hardirqs_on_events);
+}
+EXPORT_SYMBOL_GPL(lockdep_hardirqs_on);
 
 /*
  * Hardirqs were disabled:
  */
-void lockdep_hardirqs_off(unsigned long ip)
+void noinstr lockdep_hardirqs_off(unsigned long ip)
 {
 	struct task_struct *curr = current;
 
-	if (unlikely(!debug_locks || current->lockdep_recursion))
+	if (unlikely(!debug_locks || curr->lockdep_recursion))
 		return;
 
 	/*
@@ -3710,10 +3753,11 @@ void lockdep_hardirqs_off(unsigned long ip)
 		curr->hardirq_disable_ip = ip;
 		curr->hardirq_disable_event = ++curr->irq_events;
 		debug_atomic_inc(hardirqs_off_events);
-	} else
+	} else {
 		debug_atomic_inc(redundant_hardirqs_off);
+	}
 }
-NOKPROBE_SYMBOL(lockdep_hardirqs_off);
+EXPORT_SYMBOL_GPL(lockdep_hardirqs_off);
 
 /*
  * Softirqs will be enabled:
@@ -4389,8 +4433,8 @@ static void print_unlock_imbalance_bug(struct task_struct *curr,
 	dump_stack();
 }
 
-static int match_held_lock(const struct held_lock *hlock,
-					const struct lockdep_map *lock)
+static noinstr int match_held_lock(const struct held_lock *hlock,
+				   const struct lockdep_map *lock)
 {
 	if (hlock->instance == lock)
 		return 1;
@@ -4677,7 +4721,7 @@ __lock_release(struct lockdep_map *lock, unsigned long ip)
 	return 0;
 }
 
-static nokprobe_inline
+static __always_inline
 int __lock_is_held(const struct lockdep_map *lock, int read)
 {
 	struct task_struct *curr = current;
@@ -4937,7 +4981,7 @@ void lock_release(struct lockdep_map *lock, unsigned long ip)
 }
 EXPORT_SYMBOL_GPL(lock_release);
 
-int lock_is_held_type(const struct lockdep_map *lock, int read)
+noinstr int lock_is_held_type(const struct lockdep_map *lock, int read)
 {
 	unsigned long flags;
 	int ret = 0;
diff --git a/kernel/trace/trace_preemptirq.c b/kernel/trace/trace_preemptirq.c
index 4d8e99fdbbbe..fb0691b8a88d 100644
--- a/kernel/trace/trace_preemptirq.c
+++ b/kernel/trace/trace_preemptirq.c
@@ -19,6 +19,24 @@
 /* Per-cpu variable to prevent redundant calls when IRQs already off */
 static DEFINE_PER_CPU(int, tracing_irq_cpu);
 
+/*
+ * Like trace_hardirqs_on() but without the lockdep invocation. This is
+ * used in the low level entry code where the ordering vs. RCU is important
+ * and lockdep uses a staged approach which splits the lockdep hardirq
+ * tracking into a RCU on and a RCU off section.
+ */
+void trace_hardirqs_on_prepare(void)
+{
+	if (this_cpu_read(tracing_irq_cpu)) {
+		if (!in_nmi())
+			trace_irq_enable(CALLER_ADDR0, CALLER_ADDR1);
+		tracer_hardirqs_on(CALLER_ADDR0, CALLER_ADDR1);
+		this_cpu_write(tracing_irq_cpu, 0);
+	}
+}
+EXPORT_SYMBOL(trace_hardirqs_on_prepare);
+NOKPROBE_SYMBOL(trace_hardirqs_on_prepare);
+
 void trace_hardirqs_on(void)
 {
 	if (this_cpu_read(tracing_irq_cpu)) {
@@ -28,11 +46,31 @@ void trace_hardirqs_on(void)
 		this_cpu_write(tracing_irq_cpu, 0);
 	}
 
+	lockdep_hardirqs_on_prepare(CALLER_ADDR0);
 	lockdep_hardirqs_on(CALLER_ADDR0);
 }
 EXPORT_SYMBOL(trace_hardirqs_on);
 NOKPROBE_SYMBOL(trace_hardirqs_on);
 
+/*
+ * Like trace_hardirqs_off() but without the lockdep invocation. This is
+ * used in the low level entry code where the ordering vs. RCU is important
+ * and lockdep uses a staged approach which splits the lockdep hardirq
+ * tracking into a RCU on and a RCU off section.
+ */
+void trace_hardirqs_off_prepare(void)
+{
+	if (!this_cpu_read(tracing_irq_cpu)) {
+		this_cpu_write(tracing_irq_cpu, 1);
+		tracer_hardirqs_off(CALLER_ADDR0, CALLER_ADDR1);
+		if (!in_nmi())
+			trace_irq_disable(CALLER_ADDR0, CALLER_ADDR1);
+	}
+
+}
+EXPORT_SYMBOL(trace_hardirqs_off_prepare);
+NOKPROBE_SYMBOL(trace_hardirqs_off_prepare);
+
 void trace_hardirqs_off(void)
 {
 	if (!this_cpu_read(tracing_irq_cpu)) {
@@ -56,6 +94,7 @@ __visible void trace_hardirqs_on_caller(unsigned long caller_addr)
 		this_cpu_write(tracing_irq_cpu, 0);
 	}
 
+	lockdep_hardirqs_on_prepare(CALLER_ADDR0);
 	lockdep_hardirqs_on(CALLER_ADDR0);
 }
 EXPORT_SYMBOL(trace_hardirqs_on_caller);