19 files changed, 106 insertions, 98 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/kprobes.c b/kernel/kprobes.c
index dbe57df2e199..dd58c0be9ce2 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -2126,7 +2126,7 @@ static void kretprobe_rethook_handler(struct rethook_node *rh, void *data,
 	struct kprobe_ctlblk *kcb;
 
 	/* The data must NOT be null. This means rethook data structure is broken. */
-	if (WARN_ON_ONCE(!data))
+	if (WARN_ON_ONCE(!data) || !rp->handler)
 		return;
 
 	__this_cpu_write(current_kprobe, &rp->kp);
diff --git a/kernel/power/Makefile b/kernel/power/Makefile
index 5899260a8bef..874ad834dc8d 100644
--- a/kernel/power/Makefile
+++ b/kernel/power/Makefile
@@ -1,6 +1,10 @@
 # SPDX-License-Identifier: GPL-2.0
 
-ccflags-$(CONFIG_PM_DEBUG)	:= -DDEBUG
+ifeq ($(CONFIG_DYNAMIC_DEBUG), y)
+CFLAGS_swap.o                   := -DDEBUG
+CFLAGS_snapshot.o               := -DDEBUG
+CFLAGS_energy_model.o           := -DDEBUG
+endif
 
 KASAN_SANITIZE_snapshot.o	:= n
 
diff --git a/kernel/power/energy_model.c b/kernel/power/energy_model.c
index 0153b0ca7b23..6c373f2960e7 100644
--- a/kernel/power/energy_model.c
+++ b/kernel/power/energy_model.c
@@ -54,28 +54,15 @@ static int em_debug_cpus_show(struct seq_file *s, void *unused)
 }
 DEFINE_SHOW_ATTRIBUTE(em_debug_cpus);
 
-static int em_debug_units_show(struct seq_file *s, void *unused)
+static int em_debug_flags_show(struct seq_file *s, void *unused)
 {
 	struct em_perf_domain *pd = s->private;
-	char *units = (pd->flags & EM_PERF_DOMAIN_MILLIWATTS) ?
-		"milliWatts" : "bogoWatts";
 
-	seq_printf(s, "%s\n", units);
+	seq_printf(s, "%#lx\n", pd->flags);
 
 	return 0;
 }
-DEFINE_SHOW_ATTRIBUTE(em_debug_units);
-
-static int em_debug_skip_inefficiencies_show(struct seq_file *s, void *unused)
-{
-	struct em_perf_domain *pd = s->private;
-	int enabled = (pd->flags & EM_PERF_DOMAIN_SKIP_INEFFICIENCIES) ? 1 : 0;
-
-	seq_printf(s, "%d\n", enabled);
-
-	return 0;
-}
-DEFINE_SHOW_ATTRIBUTE(em_debug_skip_inefficiencies);
+DEFINE_SHOW_ATTRIBUTE(em_debug_flags);
 
 static void em_debug_create_pd(struct device *dev)
 {
@@ -89,9 +76,8 @@ static void em_debug_create_pd(struct device *dev)
 		debugfs_create_file("cpus", 0444, d, dev->em_pd->cpus,
 				    &em_debug_cpus_fops);
 
-	debugfs_create_file("units", 0444, d, dev->em_pd, &em_debug_units_fops);
-	debugfs_create_file("skip-inefficiencies", 0444, d, dev->em_pd,
-			    &em_debug_skip_inefficiencies_fops);
+	debugfs_create_file("flags", 0444, d, dev->em_pd,
+			    &em_debug_flags_fops);
 
 	/* Create a sub-directory for each performance state */
 	for (i = 0; i < dev->em_pd->nr_perf_states; i++)
@@ -121,7 +107,8 @@ static void em_debug_remove_pd(struct device *dev) {}
 #endif
 
 static int em_create_perf_table(struct device *dev, struct em_perf_domain *pd,
-				int nr_states, struct em_data_callback *cb)
+				int nr_states, struct em_data_callback *cb,
+				unsigned long flags)
 {
 	unsigned long power, freq, prev_freq = 0, prev_cost = ULONG_MAX;
 	struct em_perf_state *table;
@@ -139,7 +126,7 @@ static int em_create_perf_table(struct device *dev, struct em_perf_domain *pd,
 		 * lowest performance state of 'dev' above 'freq' and updates
 		 * 'power' and 'freq' accordingly.
 		 */
-		ret = cb->active_power(&power, &freq, dev);
+		ret = cb->active_power(dev, &power, &freq);
 		if (ret) {
 			dev_err(dev, "EM: invalid perf. state: %d\n",
 				ret);
@@ -173,10 +160,22 @@ static int em_create_perf_table(struct device *dev, struct em_perf_domain *pd,
 	/* Compute the cost of each performance state. */
 	fmax = (u64) table[nr_states - 1].frequency;
 	for (i = nr_states - 1; i >= 0; i--) {
-		unsigned long power_res = em_scale_power(table[i].power);
+		unsigned long power_res, cost;
+
+		if (flags & EM_PERF_DOMAIN_ARTIFICIAL) {
+			ret = cb->get_cost(dev, table[i].frequency, &cost);
+			if (ret || !cost || cost > EM_MAX_POWER) {
+				dev_err(dev, "EM: invalid cost %lu %d\n",
+					cost, ret);
+				goto free_ps_table;
+			}
+		} else {
+			power_res = em_scale_power(table[i].power);
+			cost = div64_u64(fmax * power_res, table[i].frequency);
+		}
+
+		table[i].cost = cost;
 
-		table[i].cost = div64_u64(fmax * power_res,
-					  table[i].frequency);
 		if (table[i].cost >= prev_cost) {
 			table[i].flags = EM_PERF_STATE_INEFFICIENT;
 			dev_dbg(dev, "EM: OPP:%lu is inefficient\n",
@@ -197,7 +196,8 @@ free_ps_table:
 }
 
 static int em_create_pd(struct device *dev, int nr_states,
-			struct em_data_callback *cb, cpumask_t *cpus)
+			struct em_data_callback *cb, cpumask_t *cpus,
+			unsigned long flags)
 {
 	struct em_perf_domain *pd;
 	struct device *cpu_dev;
@@ -215,7 +215,7 @@ static int em_create_pd(struct device *dev, int nr_states,
 			return -ENOMEM;
 	}
 
-	ret = em_create_perf_table(dev, pd, nr_states, cb);
+	ret = em_create_perf_table(dev, pd, nr_states, cb, flags);
 	if (ret) {
 		kfree(pd);
 		return ret;
@@ -259,6 +259,8 @@ static void em_cpufreq_update_efficiencies(struct device *dev)
 			found++;
 	}
 
+	cpufreq_cpu_put(policy);
+
 	if (!found)
 		return;
 
@@ -332,6 +334,7 @@ int em_dev_register_perf_domain(struct device *dev, unsigned int nr_states,
 				bool milliwatts)
 {
 	unsigned long cap, prev_cap = 0;
+	unsigned long flags = 0;
 	int cpu, ret;
 
 	if (!dev || !nr_states || !cb)
@@ -378,12 +381,16 @@ int em_dev_register_perf_domain(struct device *dev, unsigned int nr_states,
 		}
 	}
 
-	ret = em_create_pd(dev, nr_states, cb, cpus);
+	if (milliwatts)
+		flags |= EM_PERF_DOMAIN_MILLIWATTS;
+	else if (cb->get_cost)
+		flags |= EM_PERF_DOMAIN_ARTIFICIAL;
+
+	ret = em_create_pd(dev, nr_states, cb, cpus, flags);
 	if (ret)
 		goto unlock;
 
-	if (milliwatts)
-		dev->em_pd->flags |= EM_PERF_DOMAIN_MILLIWATTS;
+	dev->em_pd->flags |= flags;
 
 	em_cpufreq_update_efficiencies(dev);
 
diff --git a/kernel/power/main.c b/kernel/power/main.c
index 7e646079fbeb..5242bf2ee469 100644
--- a/kernel/power/main.c
+++ b/kernel/power/main.c
@@ -545,35 +545,6 @@ static int __init pm_debug_messages_setup(char *str)
 }
 __setup("pm_debug_messages", pm_debug_messages_setup);
 
-/**
- * __pm_pr_dbg - Print a suspend debug message to the kernel log.
- * @defer: Whether or not to use printk_deferred() to print the message.
- * @fmt: Message format.
- *
- * The message will be emitted if enabled through the pm_debug_messages
- * sysfs attribute.
- */
-void __pm_pr_dbg(bool defer, const char *fmt, ...)
-{
-	struct va_format vaf;
-	va_list args;
-
-	if (!pm_debug_messages_on)
-		return;
-
-	va_start(args, fmt);
-
-	vaf.fmt = fmt;
-	vaf.va = &args;
-
-	if (defer)
-		printk_deferred(KERN_DEBUG "PM: %pV", &vaf);
-	else
-		printk(KERN_DEBUG "PM: %pV", &vaf);
-
-	va_end(args);
-}
-
 #else /* !CONFIG_PM_SLEEP_DEBUG */
 static inline void pm_print_times_init(void) {}
 #endif /* CONFIG_PM_SLEEP_DEBUG */
diff --git a/kernel/power/process.c b/kernel/power/process.c
index 11b570fcf049..3068601e585a 100644
--- a/kernel/power/process.c
+++ b/kernel/power/process.c
@@ -6,9 +6,6 @@
  * Originally from swsusp.
  */
 
-
-#undef DEBUG
-
 #include <linux/interrupt.h>
 #include <linux/oom.h>
 #include <linux/suspend.h>
diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c
index 330d49937692..2a406753af90 100644
--- a/kernel/power/snapshot.c
+++ b/kernel/power/snapshot.c
@@ -326,7 +326,7 @@ static void *chain_alloc(struct chain_allocator *ca, unsigned int size)
 	return ret;
 }
 
-/**
+/*
  * Data types related to memory bitmaps.
  *
  * Memory bitmap is a structure consisting of many linked lists of
@@ -427,6 +427,10 @@ struct memory_bitmap {
 
 /**
  * alloc_rtree_node - Allocate a new node and add it to the radix tree.
+ * @gfp_mask: GFP mask for the allocation.
+ * @safe_needed: Get pages not used before hibernation (restore only)
+ * @ca: Pointer to a linked list of pages ("a chain") to allocate from
+ * @list: Radix Tree node to add.
  *
  * This function is used to allocate inner nodes as well as the
  * leave nodes of the radix tree. It also adds the node to the
@@ -902,7 +906,7 @@ static bool rtree_next_node(struct memory_bitmap *bm)
 }
 
 /**
- * memory_bm_rtree_next_pfn - Find the next set bit in a memory bitmap.
+ * memory_bm_next_pfn - Find the next set bit in a memory bitmap.
  * @bm: Memory bitmap.
  *
  * Starting from the last returned position this function searches for the next
@@ -1937,7 +1941,7 @@ static inline int get_highmem_buffer(int safe_needed)
 }
 
 /**
- * alloc_highmem_image_pages - Allocate some highmem pages for the image.
+ * alloc_highmem_pages - Allocate some highmem pages for the image.
  *
  * Try to allocate as many pages as needed, but if the number of free highmem
  * pages is less than that, allocate them all.
@@ -2224,7 +2228,7 @@ static int check_header(struct swsusp_info *info)
 }
 
 /**
- * load header - Check the image header and copy the data from it.
+ * load_header - Check the image header and copy the data from it.
  */
 static int load_header(struct swsusp_info *info)
 {
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;