Merge tag 'kvm-riscv-5.19-1' of https://github.com/kvm-riscv/linux into HEAD

KVM/riscv changes for 5.19

- Added Sv57x4 support for G-stage page table
- Added range based local HFENCE functions
- Added remote HFENCE functions based on VCPU requests
- Added ISA extension registers in ONE_REG interface
- Updated KVM RISC-V maintainers entry to cover selftests support

13 files changed, 56 insertions, 31 deletions

diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
index 9390bfd9f1cd..71a418858a5e 100644
--- a/kernel/cgroup/cpuset.c
+++ b/kernel/cgroup/cpuset.c
@@ -3390,8 +3390,11 @@ static struct notifier_block cpuset_track_online_nodes_nb = {
  */
 void __init cpuset_init_smp(void)
 {
-	cpumask_copy(top_cpuset.cpus_allowed, cpu_active_mask);
-	top_cpuset.mems_allowed = node_states[N_MEMORY];
+	/*
+	 * cpus_allowd/mems_allowed set to v2 values in the initial
+	 * cpuset_bind() call will be reset to v1 values in another
+	 * cpuset_bind() call when v1 cpuset is mounted.
+	 */
 	top_cpuset.old_mems_allowed = top_cpuset.mems_allowed;
 
 	cpumask_copy(top_cpuset.effective_cpus, cpu_active_mask);
diff --git a/kernel/fork.c b/kernel/fork.c
index 9796897560ab..35a3beff140b 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -792,6 +792,7 @@ void __mmdrop(struct mm_struct *mm)
 	mmu_notifier_subscriptions_destroy(mm);
 	check_mm(mm);
 	put_user_ns(mm->user_ns);
+	mm_pasid_drop(mm);
 	free_mm(mm);
 }
 EXPORT_SYMBOL_GPL(__mmdrop);
@@ -1190,7 +1191,6 @@ static inline void __mmput(struct mm_struct *mm)
 	}
 	if (mm->binfmt)
 		module_put(mm->binfmt->module);
-	mm_pasid_drop(mm);
 	mmdrop(mm);
 }
 
diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h
index 99cbdf55a8bd..f09c60393e55 100644
--- a/kernel/irq/internals.h
+++ b/kernel/irq/internals.h
@@ -29,12 +29,14 @@ extern struct irqaction chained_action;
  * IRQTF_WARNED    - warning "IRQ_WAKE_THREAD w/o thread_fn" has been printed
  * IRQTF_AFFINITY  - irq thread is requested to adjust affinity
  * IRQTF_FORCED_THREAD  - irq action is force threaded
+ * IRQTF_READY     - signals that irq thread is ready
  */
 enum {
 	IRQTF_RUNTHREAD,
 	IRQTF_WARNED,
 	IRQTF_AFFINITY,
 	IRQTF_FORCED_THREAD,
+	IRQTF_READY,
 };
 
 /*
diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c
index 939d21cd55c3..d323b180b0f3 100644
--- a/kernel/irq/irqdesc.c
+++ b/kernel/irq/irqdesc.c
@@ -407,6 +407,7 @@ static struct irq_desc *alloc_desc(int irq, int node, unsigned int flags,
 	lockdep_set_class(&desc->lock, &irq_desc_lock_class);
 	mutex_init(&desc->request_mutex);
 	init_rcu_head(&desc->rcu);
+	init_waitqueue_head(&desc->wait_for_threads);
 
 	desc_set_defaults(irq, desc, node, affinity, owner);
 	irqd_set(&desc->irq_data, flags);
@@ -575,6 +576,7 @@ int __init early_irq_init(void)
 		raw_spin_lock_init(&desc[i].lock);
 		lockdep_set_class(&desc[i].lock, &irq_desc_lock_class);
 		mutex_init(&desc[i].request_mutex);
+		init_waitqueue_head(&desc[i].wait_for_threads);
 		desc_set_defaults(i, &desc[i], node, NULL, NULL);
 	}
 	return arch_early_irq_init();
@@ -699,7 +701,6 @@ EXPORT_SYMBOL_GPL(generic_handle_irq_safe);
  */
 int generic_handle_domain_irq(struct irq_domain *domain, unsigned int hwirq)
 {
-	WARN_ON_ONCE(!in_hardirq());
 	return handle_irq_desc(irq_resolve_mapping(domain, hwirq));
 }
 EXPORT_SYMBOL_GPL(generic_handle_domain_irq);
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index c03f71d5ec10..e3e245a4fd70 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -1249,6 +1249,31 @@ static void irq_wake_secondary(struct irq_desc *desc, struct irqaction *action)
 }
 
 /*
+ * Internal function to notify that a interrupt thread is ready.
+ */
+static void irq_thread_set_ready(struct irq_desc *desc,
+				 struct irqaction *action)
+{
+	set_bit(IRQTF_READY, &action->thread_flags);
+	wake_up(&desc->wait_for_threads);
+}
+
+/*
+ * Internal function to wake up a interrupt thread and wait until it is
+ * ready.
+ */
+static void wake_up_and_wait_for_irq_thread_ready(struct irq_desc *desc,
+						  struct irqaction *action)
+{
+	if (!action || !action->thread)
+		return;
+
+	wake_up_process(action->thread);
+	wait_event(desc->wait_for_threads,
+		   test_bit(IRQTF_READY, &action->thread_flags));
+}
+
+/*
  * Interrupt handler thread
  */
 static int irq_thread(void *data)
@@ -1259,6 +1284,8 @@ static int irq_thread(void *data)
 	irqreturn_t (*handler_fn)(struct irq_desc *desc,
 			struct irqaction *action);
 
+	irq_thread_set_ready(desc, action);
+
 	sched_set_fifo(current);
 
 	if (force_irqthreads() && test_bit(IRQTF_FORCED_THREAD,
@@ -1683,8 +1710,6 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new)
 	}
 
 	if (!shared) {
-		init_waitqueue_head(&desc->wait_for_threads);
-
 		/* Setup the type (level, edge polarity) if configured: */
 		if (new->flags & IRQF_TRIGGER_MASK) {
 			ret = __irq_set_trigger(desc,
@@ -1780,14 +1805,8 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new)
 
 	irq_setup_timings(desc, new);
 
-	/*
-	 * Strictly no need to wake it up, but hung_task complains
-	 * when no hard interrupt wakes the thread up.
-	 */
-	if (new->thread)
-		wake_up_process(new->thread);
-	if (new->secondary)
-		wake_up_process(new->secondary->thread);
+	wake_up_and_wait_for_irq_thread_ready(desc, new);
+	wake_up_and_wait_for_irq_thread_ready(desc, new->secondary);
 
 	register_irq_proc(irq, desc);
 	new->dir = NULL;
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 51efaabac3e4..d58c0389eb23 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -6382,7 +6382,7 @@ static void __sched notrace __schedule(unsigned int sched_mode)
 		migrate_disable_switch(rq, prev);
 		psi_sched_switch(prev, next, !task_on_rq_queued(prev));
 
-		trace_sched_switch(sched_mode & SM_MASK_PREEMPT, prev_state, prev, next);
+		trace_sched_switch(sched_mode & SM_MASK_PREEMPT, prev, next, prev_state);
 
 		/* Also unlocks the rq: */
 		rq = context_switch(rq, prev, next, &rf);
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index dcdcb85121e4..3b1398fbddaf 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -482,7 +482,7 @@ static __always_inline u64 __ktime_get_fast_ns(struct tk_fast *tkf)
  * of the following timestamps. Callers need to be aware of that and
  * deal with it.
  */
-u64 ktime_get_mono_fast_ns(void)
+u64 notrace ktime_get_mono_fast_ns(void)
 {
 	return __ktime_get_fast_ns(&tk_fast_mono);
 }
@@ -494,7 +494,7 @@ EXPORT_SYMBOL_GPL(ktime_get_mono_fast_ns);
  * Contrary to ktime_get_mono_fast_ns() this is always correct because the
  * conversion factor is not affected by NTP/PTP correction.
  */
-u64 ktime_get_raw_fast_ns(void)
+u64 notrace ktime_get_raw_fast_ns(void)
 {
 	return __ktime_get_fast_ns(&tk_fast_raw);
 }
diff --git a/kernel/trace/fgraph.c b/kernel/trace/fgraph.c
index 8f4fb328133a..a7e84c8543cb 100644
--- a/kernel/trace/fgraph.c
+++ b/kernel/trace/fgraph.c
@@ -404,9 +404,9 @@ free:
 
 static void
 ftrace_graph_probe_sched_switch(void *ignore, bool preempt,
-				unsigned int prev_state,
 				struct task_struct *prev,
-				struct task_struct *next)
+				struct task_struct *next,
+				unsigned int prev_state)
 {
 	unsigned long long timestamp;
 	int index;
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 4f1d2f5e7263..af899b058c8d 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -7420,9 +7420,9 @@ ftrace_func_t ftrace_ops_get_func(struct ftrace_ops *ops)
 
 static void
 ftrace_filter_pid_sched_switch_probe(void *data, bool preempt,
-				     unsigned int prev_state,
 				     struct task_struct *prev,
-				     struct task_struct *next)
+				     struct task_struct *next,
+				     unsigned int prev_state)
 {
 	struct trace_array *tr = data;
 	struct trace_pid_list *pid_list;
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index e11e167b7809..f97de82d1342 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -773,9 +773,9 @@ void trace_event_follow_fork(struct trace_array *tr, bool enable)
 
 static void
 event_filter_pid_sched_switch_probe_pre(void *data, bool preempt,
-					unsigned int prev_state,
 					struct task_struct *prev,
-					struct task_struct *next)
+					struct task_struct *next,
+					unsigned int prev_state)
 {
 	struct trace_array *tr = data;
 	struct trace_pid_list *no_pid_list;
@@ -799,9 +799,9 @@ event_filter_pid_sched_switch_probe_pre(void *data, bool preempt,
 
 static void
 event_filter_pid_sched_switch_probe_post(void *data, bool preempt,
-					 unsigned int prev_state,
 					 struct task_struct *prev,
-					 struct task_struct *next)
+					 struct task_struct *next,
+					 unsigned int prev_state)
 {
 	struct trace_array *tr = data;
 	struct trace_pid_list *no_pid_list;
diff --git a/kernel/trace/trace_osnoise.c b/kernel/trace/trace_osnoise.c
index e9ae1f33a7f0..afb92e2f0aea 100644
--- a/kernel/trace/trace_osnoise.c
+++ b/kernel/trace/trace_osnoise.c
@@ -1168,9 +1168,9 @@ thread_exit(struct osnoise_variables *osn_var, struct task_struct *t)
  */
 static void
 trace_sched_switch_callback(void *data, bool preempt,
-			    unsigned int prev_state,
 			    struct task_struct *p,
-			    struct task_struct *n)
+			    struct task_struct *n,
+			    unsigned int prev_state)
 {
 	struct osnoise_variables *osn_var = this_cpu_osn_var();
 
diff --git a/kernel/trace/trace_sched_switch.c b/kernel/trace/trace_sched_switch.c
index 45796d8bd4b2..c9ffdcfe622e 100644
--- a/kernel/trace/trace_sched_switch.c
+++ b/kernel/trace/trace_sched_switch.c
@@ -22,8 +22,8 @@ static DEFINE_MUTEX(sched_register_mutex);
 
 static void
 probe_sched_switch(void *ignore, bool preempt,
-		   unsigned int prev_state,
-		   struct task_struct *prev, struct task_struct *next)
+		   struct task_struct *prev, struct task_struct *next,
+		   unsigned int prev_state)
 {
 	int flags;
 
diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c
index 46429f9a96fa..330aee1c1a49 100644
--- a/kernel/trace/trace_sched_wakeup.c
+++ b/kernel/trace/trace_sched_wakeup.c
@@ -426,8 +426,8 @@ tracing_sched_wakeup_trace(struct trace_array *tr,
 
 static void notrace
 probe_wakeup_sched_switch(void *ignore, bool preempt,
-			  unsigned int prev_state,
-			  struct task_struct *prev, struct task_struct *next)
+			  struct task_struct *prev, struct task_struct *next,
+			  unsigned int prev_state)
 {
 	struct trace_array_cpu *data;
 	u64 T0, T1, delta;