Merge tag 'tai-for-tracing' into timers/core

Pull in the NMI safe TAI accessor which was provided for the tracing tree
to prepare for further changes in this area.

11 files changed, 632 insertions, 715 deletions

diff --git a/kernel/Makefile b/kernel/Makefile
index 471d71935e90..847a82bfe0e3 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -114,7 +114,8 @@ obj-$(CONFIG_CPU_PM) += cpu_pm.o
 obj-$(CONFIG_BPF) += bpf/
 obj-$(CONFIG_KCSAN) += kcsan/
 obj-$(CONFIG_SHADOW_CALL_STACK) += scs.o
-obj-$(CONFIG_HAVE_STATIC_CALL_INLINE) += static_call.o
+obj-$(CONFIG_HAVE_STATIC_CALL) += static_call.o
+obj-$(CONFIG_HAVE_STATIC_CALL_INLINE) += static_call_inline.o
 obj-$(CONFIG_CFI_CLANG) += cfi.o
 
 obj-$(CONFIG_PERF_EVENTS) += events/
diff --git a/kernel/entry/common.c b/kernel/entry/common.c
index e57a224d6b79..93c3b86e781c 100644
--- a/kernel/entry/common.c
+++ b/kernel/entry/common.c
@@ -392,7 +392,7 @@ DEFINE_STATIC_CALL(irqentry_exit_cond_resched, raw_irqentry_exit_cond_resched);
 DEFINE_STATIC_KEY_TRUE(sk_dynamic_irqentry_exit_cond_resched);
 void dynamic_irqentry_exit_cond_resched(void)
 {
-	if (!static_key_unlikely(&sk_dynamic_irqentry_exit_cond_resched))
+	if (!static_branch_unlikely(&sk_dynamic_irqentry_exit_cond_resched))
 		return;
 	raw_irqentry_exit_cond_resched();
 }
diff --git a/kernel/events/core.c b/kernel/events/core.c
index cfde994ce61c..23bb19716ad3 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -574,8 +574,7 @@ static void cpu_ctx_sched_out(struct perf_cpu_context *cpuctx,
 			      enum event_type_t event_type);
 
 static void cpu_ctx_sched_in(struct perf_cpu_context *cpuctx,
-			     enum event_type_t event_type,
-			     struct task_struct *task);
+			     enum event_type_t event_type);
 
 static void update_context_time(struct perf_event_context *ctx);
 static u64 perf_event_time(struct perf_event *event);
@@ -781,7 +780,6 @@ static inline void update_cgrp_time_from_cpuctx(struct perf_cpu_context *cpuctx,
 static inline void update_cgrp_time_from_event(struct perf_event *event)
 {
 	struct perf_cgroup_info *info;
-	struct perf_cgroup *cgrp;
 
 	/*
 	 * ensure we access cgroup data only when needed and
@@ -790,21 +788,19 @@ static inline void update_cgrp_time_from_event(struct perf_event *event)
 	if (!is_cgroup_event(event))
 		return;
 
-	cgrp = perf_cgroup_from_task(current, event->ctx);
+	info = this_cpu_ptr(event->cgrp->info);
 	/*
 	 * Do not update time when cgroup is not active
 	 */
-	if (cgroup_is_descendant(cgrp->css.cgroup, event->cgrp->css.cgroup)) {
-		info = this_cpu_ptr(event->cgrp->info);
+	if (info->active)
 		__update_cgrp_time(info, perf_clock(), true);
-	}
 }
 
 static inline void
-perf_cgroup_set_timestamp(struct task_struct *task,
-			  struct perf_event_context *ctx)
+perf_cgroup_set_timestamp(struct perf_cpu_context *cpuctx)
 {
-	struct perf_cgroup *cgrp;
+	struct perf_event_context *ctx = &cpuctx->ctx;
+	struct perf_cgroup *cgrp = cpuctx->cgrp;
 	struct perf_cgroup_info *info;
 	struct cgroup_subsys_state *css;
 
@@ -813,10 +809,10 @@ perf_cgroup_set_timestamp(struct task_struct *task,
 	 * ensure we do not access cgroup data
 	 * unless we have the cgroup pinned (css_get)
 	 */
-	if (!task || !ctx->nr_cgroups)
+	if (!cgrp)
 		return;
 
-	cgrp = perf_cgroup_from_task(task, ctx);
+	WARN_ON_ONCE(!ctx->nr_cgroups);
 
 	for (css = &cgrp->css; css; css = css->parent) {
 		cgrp = container_of(css, struct perf_cgroup, css);
@@ -828,17 +824,12 @@ perf_cgroup_set_timestamp(struct task_struct *task,
 
 static DEFINE_PER_CPU(struct list_head, cgrp_cpuctx_list);
 
-#define PERF_CGROUP_SWOUT	0x1 /* cgroup switch out every event */
-#define PERF_CGROUP_SWIN	0x2 /* cgroup switch in events based on task */
-
 /*
  * reschedule events based on the cgroup constraint of task.
- *
- * mode SWOUT : schedule out everything
- * mode SWIN : schedule in based on cgroup for next
  */
-static void perf_cgroup_switch(struct task_struct *task, int mode)
+static void perf_cgroup_switch(struct task_struct *task)
 {
+	struct perf_cgroup *cgrp;
 	struct perf_cpu_context *cpuctx, *tmp;
 	struct list_head *list;
 	unsigned long flags;
@@ -849,35 +840,31 @@ static void perf_cgroup_switch(struct task_struct *task, int mode)
 	 */
 	local_irq_save(flags);
 
+	cgrp = perf_cgroup_from_task(task, NULL);
+
 	list = this_cpu_ptr(&cgrp_cpuctx_list);
 	list_for_each_entry_safe(cpuctx, tmp, list, cgrp_cpuctx_entry) {
 		WARN_ON_ONCE(cpuctx->ctx.nr_cgroups == 0);
+		if (READ_ONCE(cpuctx->cgrp) == cgrp)
+			continue;
 
 		perf_ctx_lock(cpuctx, cpuctx->task_ctx);
 		perf_pmu_disable(cpuctx->ctx.pmu);
 
-		if (mode & PERF_CGROUP_SWOUT) {
-			cpu_ctx_sched_out(cpuctx, EVENT_ALL);
-			/*
-			 * must not be done before ctxswout due
-			 * to event_filter_match() in event_sched_out()
-			 */
-			cpuctx->cgrp = NULL;
-		}
+		cpu_ctx_sched_out(cpuctx, EVENT_ALL);
+		/*
+		 * must not be done before ctxswout due
+		 * to update_cgrp_time_from_cpuctx() in
+		 * ctx_sched_out()
+		 */
+		cpuctx->cgrp = cgrp;
+		/*
+		 * set cgrp before ctxsw in to allow
+		 * perf_cgroup_set_timestamp() in ctx_sched_in()
+		 * to not have to pass task around
+		 */
+		cpu_ctx_sched_in(cpuctx, EVENT_ALL);
 
-		if (mode & PERF_CGROUP_SWIN) {
-			WARN_ON_ONCE(cpuctx->cgrp);
-			/*
-			 * set cgrp before ctxsw in to allow
-			 * event_filter_match() to not have to pass
-			 * task around
-			 * we pass the cpuctx->ctx to perf_cgroup_from_task()
-			 * because cgorup events are only per-cpu
-			 */
-			cpuctx->cgrp = perf_cgroup_from_task(task,
-							     &cpuctx->ctx);
-			cpu_ctx_sched_in(cpuctx, EVENT_ALL, task);
-		}
 		perf_pmu_enable(cpuctx->ctx.pmu);
 		perf_ctx_unlock(cpuctx, cpuctx->task_ctx);
 	}
@@ -885,58 +872,6 @@ static void perf_cgroup_switch(struct task_struct *task, int mode)
 	local_irq_restore(flags);
 }
 
-static inline void perf_cgroup_sched_out(struct task_struct *task,
-					 struct task_struct *next)
-{
-	struct perf_cgroup *cgrp1;
-	struct perf_cgroup *cgrp2 = NULL;
-
-	rcu_read_lock();
-	/*
-	 * we come here when we know perf_cgroup_events > 0
-	 * we do not need to pass the ctx here because we know
-	 * we are holding the rcu lock
-	 */
-	cgrp1 = perf_cgroup_from_task(task, NULL);
-	cgrp2 = perf_cgroup_from_task(next, NULL);
-
-	/*
-	 * only schedule out current cgroup events if we know
-	 * that we are switching to a different cgroup. Otherwise,
-	 * do no touch the cgroup events.
-	 */
-	if (cgrp1 != cgrp2)
-		perf_cgroup_switch(task, PERF_CGROUP_SWOUT);
-
-	rcu_read_unlock();
-}
-
-static inline void perf_cgroup_sched_in(struct task_struct *prev,
-					struct task_struct *task)
-{
-	struct perf_cgroup *cgrp1;
-	struct perf_cgroup *cgrp2 = NULL;
-
-	rcu_read_lock();
-	/*
-	 * we come here when we know perf_cgroup_events > 0
-	 * we do not need to pass the ctx here because we know
-	 * we are holding the rcu lock
-	 */
-	cgrp1 = perf_cgroup_from_task(task, NULL);
-	cgrp2 = perf_cgroup_from_task(prev, NULL);
-
-	/*
-	 * only need to schedule in cgroup events if we are changing
-	 * cgroup during ctxsw. Cgroup events were not scheduled
-	 * out of ctxsw out if that was not the case.
-	 */
-	if (cgrp1 != cgrp2)
-		perf_cgroup_switch(task, PERF_CGROUP_SWIN);
-
-	rcu_read_unlock();
-}
-
 static int perf_cgroup_ensure_storage(struct perf_event *event,
 				struct cgroup_subsys_state *css)
 {
@@ -1032,22 +967,10 @@ perf_cgroup_event_enable(struct perf_event *event, struct perf_event_context *ct
 	 */
 	cpuctx = container_of(ctx, struct perf_cpu_context, ctx);
 
-	/*
-	 * Since setting cpuctx->cgrp is conditional on the current @cgrp
-	 * matching the event's cgroup, we must do this for every new event,
-	 * because if the first would mismatch, the second would not try again
-	 * and we would leave cpuctx->cgrp unset.
-	 */
-	if (ctx->is_active && !cpuctx->cgrp) {
-		struct perf_cgroup *cgrp = perf_cgroup_from_task(current, ctx);
-
-		if (cgroup_is_descendant(cgrp->css.cgroup, event->cgrp->css.cgroup))
-			cpuctx->cgrp = cgrp;
-	}
-
 	if (ctx->nr_cgroups++)
 		return;
 
+	cpuctx->cgrp = perf_cgroup_from_task(current, ctx);
 	list_add(&cpuctx->cgrp_cpuctx_entry,
 			per_cpu_ptr(&cgrp_cpuctx_list, event->cpu));
 }
@@ -1069,9 +992,7 @@ perf_cgroup_event_disable(struct perf_event *event, struct perf_event_context *c
 	if (--ctx->nr_cgroups)
 		return;
 
-	if (ctx->is_active && cpuctx->cgrp)
-		cpuctx->cgrp = NULL;
-
+	cpuctx->cgrp = NULL;
 	list_del(&cpuctx->cgrp_cpuctx_entry);
 }
 
@@ -1100,16 +1021,6 @@ static inline void update_cgrp_time_from_cpuctx(struct perf_cpu_context *cpuctx,
 {
 }
 
-static inline void perf_cgroup_sched_out(struct task_struct *task,
-					 struct task_struct *next)
-{
-}
-
-static inline void perf_cgroup_sched_in(struct task_struct *prev,
-					struct task_struct *task)
-{
-}
-
 static inline int perf_cgroup_connect(pid_t pid, struct perf_event *event,
 				      struct perf_event_attr *attr,
 				      struct perf_event *group_leader)
@@ -1118,13 +1029,7 @@ static inline int perf_cgroup_connect(pid_t pid, struct perf_event *event,
 }
 
 static inline void
-perf_cgroup_set_timestamp(struct task_struct *task,
-			  struct perf_event_context *ctx)
-{
-}
-
-static inline void
-perf_cgroup_switch(struct task_struct *task, struct task_struct *next)
+perf_cgroup_set_timestamp(struct perf_cpu_context *cpuctx)
 {
 }
 
@@ -1147,6 +1052,10 @@ static inline void
 perf_cgroup_event_disable(struct perf_event *event, struct perf_event_context *ctx)
 {
 }
+
+static void perf_cgroup_switch(struct task_struct *task)
+{
+}
 #endif
 
 /*
@@ -2713,8 +2622,7 @@ static void ctx_sched_out(struct perf_event_context *ctx,
 static void
 ctx_sched_in(struct perf_event_context *ctx,
 	     struct perf_cpu_context *cpuctx,
-	     enum event_type_t event_type,
-	     struct task_struct *task);
+	     enum event_type_t event_type);
 
 static void task_ctx_sched_out(struct perf_cpu_context *cpuctx,
 			       struct perf_event_context *ctx,
@@ -2730,15 +2638,14 @@ static void task_ctx_sched_out(struct perf_cpu_context *cpuctx,
 }
 
 static void perf_event_sched_in(struct perf_cpu_context *cpuctx,
-				struct perf_event_context *ctx,
-				struct task_struct *task)
+				struct perf_event_context *ctx)
 {
-	cpu_ctx_sched_in(cpuctx, EVENT_PINNED, task);
+	cpu_ctx_sched_in(cpuctx, EVENT_PINNED);
 	if (ctx)
-		ctx_sched_in(ctx, cpuctx, EVENT_PINNED, task);
-	cpu_ctx_sched_in(cpuctx, EVENT_FLEXIBLE, task);
+		ctx_sched_in(ctx, cpuctx, EVENT_PINNED);
+	cpu_ctx_sched_in(cpuctx, EVENT_FLEXIBLE);
 	if (ctx)
-		ctx_sched_in(ctx, cpuctx, EVENT_FLEXIBLE, task);
+		ctx_sched_in(ctx, cpuctx, EVENT_FLEXIBLE);
 }
 
 /*
@@ -2788,7 +2695,7 @@ static void ctx_resched(struct perf_cpu_context *cpuctx,
 	else if (ctx_event_type & EVENT_PINNED)
 		cpu_ctx_sched_out(cpuctx, EVENT_FLEXIBLE);
 
-	perf_event_sched_in(cpuctx, task_ctx, current);
+	perf_event_sched_in(cpuctx, task_ctx);
 	perf_pmu_enable(cpuctx->ctx.pmu);
 }
 
@@ -3011,7 +2918,7 @@ static void __perf_event_enable(struct perf_event *event,
 		return;
 
 	if (!event_filter_match(event)) {
-		ctx_sched_in(ctx, cpuctx, EVENT_TIME, current);
+		ctx_sched_in(ctx, cpuctx, EVENT_TIME);
 		return;
 	}
 
@@ -3020,7 +2927,7 @@ static void __perf_event_enable(struct perf_event *event,
 	 * then don't put it on unless the group is on.
 	 */
 	if (leader != event && leader->state != PERF_EVENT_STATE_ACTIVE) {
-		ctx_sched_in(ctx, cpuctx, EVENT_TIME, current);
+		ctx_sched_in(ctx, cpuctx, EVENT_TIME);
 		return;
 	}
 
@@ -3668,7 +3575,7 @@ void __perf_event_task_sched_out(struct task_struct *task,
 	 * cgroup event are system-wide mode only
 	 */
 	if (atomic_read(this_cpu_ptr(&perf_cgroup_events)))
-		perf_cgroup_sched_out(task, next);
+		perf_cgroup_switch(next);
 }
 
 /*
@@ -3865,8 +3772,7 @@ ctx_flexible_sched_in(struct perf_event_context *ctx,
 static void
 ctx_sched_in(struct perf_event_context *ctx,
 	     struct perf_cpu_context *cpuctx,
-	     enum event_type_t event_type,
-	     struct task_struct *task)
+	     enum event_type_t event_type)
 {
 	int is_active = ctx->is_active;
 
@@ -3878,7 +3784,7 @@ ctx_sched_in(struct perf_event_context *ctx,
 	if (is_active ^ EVENT_TIME) {
 		/* start ctx time */
 		__update_context_time(ctx, false);
-		perf_cgroup_set_timestamp(task, ctx);
+		perf_cgroup_set_timestamp(cpuctx);
 		/*
 		 * CPU-release for the below ->is_active store,
 		 * see __load_acquire() in perf_event_time_now()
@@ -3909,12 +3815,11 @@ ctx_sched_in(struct perf_event_context *ctx,
 }
 
 static void cpu_ctx_sched_in(struct perf_cpu_context *cpuctx,
-			     enum event_type_t event_type,
-			     struct task_struct *task)
+			     enum event_type_t event_type)
 {
 	struct perf_event_context *ctx = &cpuctx->ctx;
 
-	ctx_sched_in(ctx, cpuctx, event_type, task);
+	ctx_sched_in(ctx, cpuctx, event_type);
 }
 
 static void perf_event_context_sched_in(struct perf_event_context *ctx,
@@ -3956,7 +3861,7 @@ static void perf_event_context_sched_in(struct perf_event_context *ctx,
 	 */
 	if (!RB_EMPTY_ROOT(&ctx->pinned_groups.tree))
 		cpu_ctx_sched_out(cpuctx, EVENT_FLEXIBLE);
-	perf_event_sched_in(cpuctx, ctx, task);
+	perf_event_sched_in(cpuctx, ctx);
 
 	if (cpuctx->sched_cb_usage && pmu->sched_task)
 		pmu->sched_task(cpuctx->task_ctx, true);
@@ -3984,16 +3889,6 @@ void __perf_event_task_sched_in(struct task_struct *prev,
 	struct perf_event_context *ctx;
 	int ctxn;
 
-	/*
-	 * If cgroup events exist on this CPU, then we need to check if we have
-	 * to switch in PMU state; cgroup event are system-wide mode only.
-	 *
-	 * Since cgroup events are CPU events, we must schedule these in before
-	 * we schedule in the task events.
-	 */
-	if (atomic_read(this_cpu_ptr(&perf_cgroup_events)))
-		perf_cgroup_sched_in(prev, task);
-
 	for_each_task_context_nr(ctxn) {
 		ctx = task->perf_event_ctxp[ctxn];
 		if (likely(!ctx))
@@ -4267,7 +4162,7 @@ static bool perf_rotate_context(struct perf_cpu_context *cpuctx)
 	if (cpu_event)
 		rotate_ctx(&cpuctx->ctx, cpu_event);
 
-	perf_event_sched_in(cpuctx, task_ctx, current);
+	perf_event_sched_in(cpuctx, task_ctx);
 
 	perf_pmu_enable(cpuctx->ctx.pmu);
 	perf_ctx_unlock(cpuctx, cpuctx->task_ctx);
@@ -4339,7 +4234,7 @@ static void perf_event_enable_on_exec(int ctxn)
 		clone_ctx = unclone_ctx(ctx);
 		ctx_resched(cpuctx, ctx, event_type);
 	} else {
-		ctx_sched_in(ctx, cpuctx, EVENT_TIME, current);
+		ctx_sched_in(ctx, cpuctx, EVENT_TIME);
 	}
 	perf_ctx_unlock(cpuctx, ctx);
 
@@ -11635,6 +11530,9 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu,
 
 	event->state		= PERF_EVENT_STATE_INACTIVE;
 
+	if (parent_event)
+		event->event_caps = parent_event->event_caps;
+
 	if (event->attr.sigtrap)
 		atomic_set(&event->event_limit, 1);
 
@@ -13562,7 +13460,7 @@ static int __perf_cgroup_move(void *info)
 {
 	struct task_struct *task = info;
 	rcu_read_lock();
-	perf_cgroup_switch(task, PERF_CGROUP_SWOUT | PERF_CGROUP_SWIN);
+	perf_cgroup_switch(task);
 	rcu_read_unlock();
 	return 0;
 }
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index d575b4914925..51efaabac3e4 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -5752,6 +5752,8 @@ static inline struct task_struct *pick_task(struct rq *rq)
 
 extern void task_vruntime_update(struct rq *rq, struct task_struct *p, bool in_fi);
 
+static void queue_core_balance(struct rq *rq);
+
 static struct task_struct *
 pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
 {
@@ -5801,7 +5803,7 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
 		}
 
 		rq->core_pick = NULL;
-		return next;
+		goto out;
 	}
 
 	put_prev_task_balance(rq, prev, rf);
@@ -5851,7 +5853,7 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
 			 */
 			WARN_ON_ONCE(fi_before);
 			task_vruntime_update(rq, next, false);
-			goto done;
+			goto out_set_next;
 		}
 	}
 
@@ -5970,8 +5972,12 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
 		resched_curr(rq_i);
 	}
 
-done:
+out_set_next:
 	set_next_task(rq, next);
+out:
+	if (rq->core->core_forceidle_count && next == rq->idle)
+		queue_core_balance(rq);
+
 	return next;
 }
 
@@ -6000,7 +6006,7 @@ static bool try_steal_cookie(int this, int that)
 		if (p == src->core_pick || p == src->curr)
 			goto next;
 
-		if (!cpumask_test_cpu(this, &p->cpus_mask))
+		if (!is_cpu_allowed(p, this))
 			goto next;
 
 		if (p->core_occupation > dst->idle->core_occupation)
@@ -6066,7 +6072,7 @@ static void sched_core_balance(struct rq *rq)
 
 static DEFINE_PER_CPU(struct callback_head, core_balance_head);
 
-void queue_core_balance(struct rq *rq)
+static void queue_core_balance(struct rq *rq)
 {
 	if (!sched_core_enabled(rq))
 		return;
diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c
index 8f8b5020e76a..ecb0d7052877 100644
--- a/kernel/sched/idle.c
+++ b/kernel/sched/idle.c
@@ -434,7 +434,6 @@ static void set_next_task_idle(struct rq *rq, struct task_struct *next, bool fir
 {
 	update_idle_core(rq);
 	schedstat_inc(rq->sched_goidle);
-	queue_core_balance(rq);
 }
 
 #ifdef CONFIG_SMP
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 58263f90c559..8dccb34eb190 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1232,8 +1232,6 @@ static inline bool sched_group_cookie_match(struct rq *rq,
 	return false;
 }
 
-extern void queue_core_balance(struct rq *rq);
-
 static inline bool sched_core_enqueued(struct task_struct *p)
 {
 	return !RB_EMPTY_NODE(&p->core_node);
@@ -1267,10 +1265,6 @@ static inline raw_spinlock_t *__rq_lockp(struct rq *rq)
 	return &rq->__lock;
 }
 
-static inline void queue_core_balance(struct rq *rq)
-{
-}
-
 static inline bool sched_cpu_cookie_match(struct rq *rq, struct task_struct *p)
 {
 	return true;
diff --git a/kernel/static_call.c b/kernel/static_call.c
index f2b8baea35d2..e9c3e69f3837 100644
--- a/kernel/static_call.c
+++ b/kernel/static_call.c
@@ -1,549 +1,8 @@
 // SPDX-License-Identifier: GPL-2.0
-#include <linux/init.h>
 #include <linux/static_call.h>
-#include <linux/bug.h>
-#include <linux/smp.h>
-#include <linux/sort.h>
-#include <linux/slab.h>
-#include <linux/module.h>
-#include <linux/cpu.h>
-#include <linux/processor.h>
-#include <asm/sections.h>
-
-extern struct static_call_site __start_static_call_sites[],
-			       __stop_static_call_sites[];
-extern struct static_call_tramp_key __start_static_call_tramp_key[],
-				    __stop_static_call_tramp_key[];
-
-static bool static_call_initialized;
-
-/* mutex to protect key modules/sites */
-static DEFINE_MUTEX(static_call_mutex);
-
-static void static_call_lock(void)
-{
-	mutex_lock(&static_call_mutex);
-}
-
-static void static_call_unlock(void)
-{
-	mutex_unlock(&static_call_mutex);
-}
-
-static inline void *static_call_addr(struct static_call_site *site)
-{
-	return (void *)((long)site->addr + (long)&site->addr);
-}
-
-static inline unsigned long __static_call_key(const struct static_call_site *site)
-{
-	return (long)site->key + (long)&site->key;
-}
-
-static inline struct static_call_key *static_call_key(const struct static_call_site *site)
-{
-	return (void *)(__static_call_key(site) & ~STATIC_CALL_SITE_FLAGS);
-}
-
-/* These assume the key is word-aligned. */
-static inline bool static_call_is_init(struct static_call_site *site)
-{
-	return __static_call_key(site) & STATIC_CALL_SITE_INIT;
-}
-
-static inline bool static_call_is_tail(struct static_call_site *site)
-{
-	return __static_call_key(site) & STATIC_CALL_SITE_TAIL;
-}
-
-static inline void static_call_set_init(struct static_call_site *site)
-{
-	site->key = (__static_call_key(site) | STATIC_CALL_SITE_INIT) -
-		    (long)&site->key;
-}
-
-static int static_call_site_cmp(const void *_a, const void *_b)
-{
-	const struct static_call_site *a = _a;
-	const struct static_call_site *b = _b;
-	const struct static_call_key *key_a = static_call_key(a);
-	const struct static_call_key *key_b = static_call_key(b);
-
-	if (key_a < key_b)
-		return -1;
-
-	if (key_a > key_b)
-		return 1;
-
-	return 0;
-}
-
-static void static_call_site_swap(void *_a, void *_b, int size)
-{
-	long delta = (unsigned long)_a - (unsigned long)_b;
-	struct static_call_site *a = _a;
-	struct static_call_site *b = _b;
-	struct static_call_site tmp = *a;
-
-	a->addr = b->addr  - delta;
-	a->key  = b->key   - delta;
-
-	b->addr = tmp.addr + delta;
-	b->key  = tmp.key  + delta;
-}
-
-static inline void static_call_sort_entries(struct static_call_site *start,
-					    struct static_call_site *stop)
-{
-	sort(start, stop - start, sizeof(struct static_call_site),
-	     static_call_site_cmp, static_call_site_swap);
-}
-
-static inline bool static_call_key_has_mods(struct static_call_key *key)
-{
-	return !(key->type & 1);
-}
-
-static inline struct static_call_mod *static_call_key_next(struct static_call_key *key)
-{
-	if (!static_call_key_has_mods(key))
-		return NULL;
-
-	return key->mods;
-}
-
-static inline struct static_call_site *static_call_key_sites(struct static_call_key *key)
-{
-	if (static_call_key_has_mods(key))
-		return NULL;
-
-	return (struct static_call_site *)(key->type & ~1);
-}
-
-void __static_call_update(struct static_call_key *key, void *tramp, void *func)
-{
-	struct static_call_site *site, *stop;
-	struct static_call_mod *site_mod, first;
-
-	cpus_read_lock();
-	static_call_lock();
-
-	if (key->func == func)
-		goto done;
-
-	key->func = func;
-
-	arch_static_call_transform(NULL, tramp, func, false);
-
-	/*
-	 * If uninitialized, we'll not update the callsites, but they still
-	 * point to the trampoline and we just patched that.
-	 */
-	if (WARN_ON_ONCE(!static_call_initialized))
-		goto done;
-
-	first = (struct static_call_mod){
-		.next = static_call_key_next(key),
-		.mod = NULL,
-		.sites = static_call_key_sites(key),
-	};
-
-	for (site_mod = &first; site_mod; site_mod = site_mod->next) {
-		bool init = system_state < SYSTEM_RUNNING;
-		struct module *mod = site_mod->mod;
-
-		if (!site_mod->sites) {
-			/*
-			 * This can happen if the static call key is defined in
-			 * a module which doesn't use it.
-			 *
-			 * It also happens in the has_mods case, where the
-			 * 'first' entry has no sites associated with it.
-			 */
-			continue;
-		}
-
-		stop = __stop_static_call_sites;
-
-		if (mod) {
-#ifdef CONFIG_MODULES
-			stop = mod->static_call_sites +
-			       mod->num_static_call_sites;
-			init = mod->state == MODULE_STATE_COMING;
-#endif
-		}
-
-		for (site = site_mod->sites;
-		     site < stop && static_call_key(site) == key; site++) {
-			void *site_addr = static_call_addr(site);
-
-			if (!init && static_call_is_init(site))
-				continue;
-
-			if (!kernel_text_address((unsigned long)site_addr)) {
-				/*
-				 * This skips patching built-in __exit, which
-				 * is part of init_section_contains() but is
-				 * not part of kernel_text_address().
-				 *
-				 * Skipping built-in __exit is fine since it
-				 * will never be executed.
-				 */
-				WARN_ONCE(!static_call_is_init(site),
-					  "can't patch static call site at %pS",
-					  site_addr);
-				continue;
-			}
-
-			arch_static_call_transform(site_addr, NULL, func,
-						   static_call_is_tail(site));
-		}
-	}
-
-done:
-	static_call_unlock();
-	cpus_read_unlock();
-}
-EXPORT_SYMBOL_GPL(__static_call_update);
-
-static int __static_call_init(struct module *mod,
-			      struct static_call_site *start,
-			      struct static_call_site *stop)
-{
-	struct static_call_site *site;
-	struct static_call_key *key, *prev_key = NULL;
-	struct static_call_mod *site_mod;
-
-	if (start == stop)
-		return 0;
-
-	static_call_sort_entries(start, stop);
-
-	for (site = start; site < stop; site++) {
-		void *site_addr = static_call_addr(site);
-
-		if ((mod && within_module_init((unsigned long)site_addr, mod)) ||
-		    (!mod && init_section_contains(site_addr, 1)))
-			static_call_set_init(site);
-
-		key = static_call_key(site);
-		if (key != prev_key) {
-			prev_key = key;
-
-			/*
-			 * For vmlinux (!mod) avoid the allocation by storing
-			 * the sites pointer in the key itself. Also see
-			 * __static_call_update()'s @first.
-			 *
-			 * This allows architectures (eg. x86) to call
-			 * static_call_init() before memory allocation works.
-			 */
-			if (!mod) {
-				key->sites = site;
-				key->type |= 1;
-				goto do_transform;
-			}
-
-			site_mod = kzalloc(sizeof(*site_mod), GFP_KERNEL);
-			if (!site_mod)
-				return -ENOMEM;
-
-			/*
-			 * When the key has a direct sites pointer, extract
-			 * that into an explicit struct static_call_mod, so we
-			 * can have a list of modules.
-			 */
-			if (static_call_key_sites(key)) {
-				site_mod->mod = NULL;
-				site_mod->next = NULL;
-				site_mod->sites = static_call_key_sites(key);
-
-				key->mods = site_mod;
-
-				site_mod = kzalloc(sizeof(*site_mod), GFP_KERNEL);
-				if (!site_mod)
-					return -ENOMEM;
-			}
-
-			site_mod->mod = mod;
-			site_mod->sites = site;
-			site_mod->next = static_call_key_next(key);
-			key->mods = site_mod;
-		}
-
-do_transform:
-		arch_static_call_transform(site_addr, NULL, key->func,
-				static_call_is_tail(site));
-	}
-
-	return 0;
-}
-
-static int addr_conflict(struct static_call_site *site, void *start, void *end)
-{
-	unsigned long addr = (unsigned long)static_call_addr(site);
-
-	if (addr <= (unsigned long)end &&
-	    addr + CALL_INSN_SIZE > (unsigned long)start)
-		return 1;
-
-	return 0;
-}
-
-static int __static_call_text_reserved(struct static_call_site *iter_start,
-				       struct static_call_site *iter_stop,
-				       void *start, void *end, bool init)
-{
-	struct static_call_site *iter = iter_start;
-
-	while (iter < iter_stop) {
-		if (init || !static_call_is_init(iter)) {
-			if (addr_conflict(iter, start, end))
-				return 1;
-		}
-		iter++;
-	}
-
-	return 0;
-}
-
-#ifdef CONFIG_MODULES
-
-static int __static_call_mod_text_reserved(void *start, void *end)
-{
-	struct module *mod;
-	int ret;
-
-	preempt_disable();
-	mod = __module_text_address((unsigned long)start);
-	WARN_ON_ONCE(__module_text_address((unsigned long)end) != mod);
-	if (!try_module_get(mod))
-		mod = NULL;
-	preempt_enable();
-
-	if (!mod)
-		return 0;
-
-	ret = __static_call_text_reserved(mod->static_call_sites,
-			mod->static_call_sites + mod->num_static_call_sites,
-			start, end, mod->state == MODULE_STATE_COMING);
-
-	module_put(mod);
-
-	return ret;
-}
-
-static unsigned long tramp_key_lookup(unsigned long addr)
-{
-	struct static_call_tramp_key *start = __start_static_call_tramp_key;
-	struct static_call_tramp_key *stop = __stop_static_call_tramp_key;
-	struct static_call_tramp_key *tramp_key;
-
-	for (tramp_key = start; tramp_key != stop; tramp_key++) {
-		unsigned long tramp;
-
-		tramp = (long)tramp_key->tramp + (long)&tramp_key->tramp;
-		if (tramp == addr)
-			return (long)tramp_key->key + (long)&tramp_key->key;
-	}
-
-	return 0;
-}
-
-static int static_call_add_module(struct module *mod)
-{
-	struct static_call_site *start = mod->static_call_sites;
-	struct static_call_site *stop = start + mod->num_static_call_sites;
-	struct static_call_site *site;
-
-	for (site = start; site != stop; site++) {
-		unsigned long s_key = __static_call_key(site);
-		unsigned long addr = s_key & ~STATIC_CALL_SITE_FLAGS;
-		unsigned long key;
-
-		/*
-		 * Is the key is exported, 'addr' points to the key, which
-		 * means modules are allowed to call static_call_update() on
-		 * it.
-		 *
-		 * Otherwise, the key isn't exported, and 'addr' points to the
-		 * trampoline so we need to lookup the key.
-		 *
-		 * We go through this dance to prevent crazy modules from
-		 * abusing sensitive static calls.
-		 */
-		if (!kernel_text_address(addr))
-			continue;
-
-		key = tramp_key_lookup(addr);
-		if (!key) {
-			pr_warn("Failed to fixup __raw_static_call() usage at: %ps\n",
-				static_call_addr(site));
-			return -EINVAL;
-		}
-
-		key |= s_key & STATIC_CALL_SITE_FLAGS;
-		site->key = key - (long)&site->key;
-	}
-
-	return __static_call_init(mod, start, stop);
-}
-
-static void static_call_del_module(struct module *mod)
-{
-	struct static_call_site *start = mod->static_call_sites;
-	struct static_call_site *stop = mod->static_call_sites +
-					mod->num_static_call_sites;
-	struct static_call_key *key, *prev_key = NULL;
-	struct static_call_mod *site_mod, **prev;
-	struct static_call_site *site;
-
-	for (site = start; site < stop; site++) {
-		key = static_call_key(site);
-		if (key == prev_key)
-			continue;
-
-		prev_key = key;
-
-		for (prev = &key->mods, site_mod = key->mods;
-		     site_mod && site_mod->mod != mod;
-		     prev = &site_mod->next, site_mod = site_mod->next)
-			;
-
-		if (!site_mod)
-			continue;
-
-		*prev = site_mod->next;
-		kfree(site_mod);
-	}
-}
-
-static int static_call_module_notify(struct notifier_block *nb,
-				     unsigned long val, void *data)
-{
-	struct module *mod = data;
-	int ret = 0;
-
-	cpus_read_lock();
-	static_call_lock();
-
-	switch (val) {
-	case MODULE_STATE_COMING:
-		ret = static_call_add_module(mod);
-		if (ret) {
-			WARN(1, "Failed to allocate memory for static calls");
-			static_call_del_module(mod);
-		}
-		break;
-	case MODULE_STATE_GOING:
-		static_call_del_module(mod);
-		break;
-	}
-
-	static_call_unlock();
-	cpus_read_unlock();
-
-	return notifier_from_errno(ret);
-}
-
-static struct notifier_block static_call_module_nb = {
-	.notifier_call = static_call_module_notify,
-};
-
-#else
-
-static inline int __static_call_mod_text_reserved(void *start, void *end)
-{
-	return 0;
-}
-
-#endif /* CONFIG_MODULES */
-
-int static_call_text_reserved(void *start, void *end)
-{
-	bool init = system_state < SYSTEM_RUNNING;
-	int ret = __static_call_text_reserved(__start_static_call_sites,
-			__stop_static_call_sites, start, end, init);
-
-	if (ret)
-		return ret;
-
-	return __static_call_mod_text_reserved(start, end);
-}
-
-int __init static_call_init(void)
-{
-	int ret;
-
-	if (static_call_initialized)
-		return 0;
-
-	cpus_read_lock();
-	static_call_lock();
-	ret = __static_call_init(NULL, __start_static_call_sites,
-				 __stop_static_call_sites);
-	static_call_unlock();
-	cpus_read_unlock();
-
-	if (ret) {
-		pr_err("Failed to allocate memory for static_call!\n");
-		BUG();
-	}
-
-	static_call_initialized = true;
-
-#ifdef CONFIG_MODULES
-	register_module_notifier(&static_call_module_nb);
-#endif
-	return 0;
-}
-early_initcall(static_call_init);
 
 long __static_call_return0(void)
 {
 	return 0;
 }
 EXPORT_SYMBOL_GPL(__static_call_return0);
-
-#ifdef CONFIG_STATIC_CALL_SELFTEST
-
-static int func_a(int x)
-{
-	return x+1;
-}
-
-static int func_b(int x)
-{
-	return x+2;
-}
-
-DEFINE_STATIC_CALL(sc_selftest, func_a);
-
-static struct static_call_data {
-      int (*func)(int);
-      int val;
-      int expect;
-} static_call_data [] __initdata = {
-      { NULL,   2, 3 },
-      { func_b, 2, 4 },
-      { func_a, 2, 3 }
-};
-
-static int __init test_static_call_init(void)
-{
-      int i;
-
-      for (i = 0; i < ARRAY_SIZE(static_call_data); i++ ) {
-	      struct static_call_data *scd = &static_call_data[i];
-
-              if (scd->func)
-                      static_call_update(sc_selftest, scd->func);
-
-              WARN_ON(static_call(sc_selftest)(scd->val) != scd->expect);
-      }
-
-      return 0;
-}
-early_initcall(test_static_call_init);
-
-#endif /* CONFIG_STATIC_CALL_SELFTEST */
diff --git a/kernel/static_call_inline.c b/kernel/static_call_inline.c
new file mode 100644
index 000000000000..dc5665b62814
--- /dev/null
+++ b/kernel/static_call_inline.c
@@ -0,0 +1,543 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/init.h>
+#include <linux/static_call.h>
+#include <linux/bug.h>
+#include <linux/smp.h>
+#include <linux/sort.h>
+#include <linux/slab.h>
+#include <linux/module.h>
+#include <linux/cpu.h>
+#include <linux/processor.h>
+#include <asm/sections.h>
+
+extern struct static_call_site __start_static_call_sites[],
+			       __stop_static_call_sites[];
+extern struct static_call_tramp_key __start_static_call_tramp_key[],
+				    __stop_static_call_tramp_key[];
+
+static bool static_call_initialized;
+
+/* mutex to protect key modules/sites */
+static DEFINE_MUTEX(static_call_mutex);
+
+static void static_call_lock(void)
+{
+	mutex_lock(&static_call_mutex);
+}
+
+static void static_call_unlock(void)
+{
+	mutex_unlock(&static_call_mutex);
+}
+
+static inline void *static_call_addr(struct static_call_site *site)
+{
+	return (void *)((long)site->addr + (long)&site->addr);
+}
+
+static inline unsigned long __static_call_key(const struct static_call_site *site)
+{
+	return (long)site->key + (long)&site->key;
+}
+
+static inline struct static_call_key *static_call_key(const struct static_call_site *site)
+{
+	return (void *)(__static_call_key(site) & ~STATIC_CALL_SITE_FLAGS);
+}
+
+/* These assume the key is word-aligned. */
+static inline bool static_call_is_init(struct static_call_site *site)
+{
+	return __static_call_key(site) & STATIC_CALL_SITE_INIT;
+}
+
+static inline bool static_call_is_tail(struct static_call_site *site)
+{
+	return __static_call_key(site) & STATIC_CALL_SITE_TAIL;
+}
+
+static inline void static_call_set_init(struct static_call_site *site)
+{
+	site->key = (__static_call_key(site) | STATIC_CALL_SITE_INIT) -
+		    (long)&site->key;
+}
+
+static int static_call_site_cmp(const void *_a, const void *_b)
+{
+	const struct static_call_site *a = _a;
+	const struct static_call_site *b = _b;
+	const struct static_call_key *key_a = static_call_key(a);
+	const struct static_call_key *key_b = static_call_key(b);
+
+	if (key_a < key_b)
+		return -1;
+
+	if (key_a > key_b)
+		return 1;
+
+	return 0;
+}
+
+static void static_call_site_swap(void *_a, void *_b, int size)
+{
+	long delta = (unsigned long)_a - (unsigned long)_b;
+	struct static_call_site *a = _a;
+	struct static_call_site *b = _b;
+	struct static_call_site tmp = *a;
+
+	a->addr = b->addr  - delta;
+	a->key  = b->key   - delta;
+
+	b->addr = tmp.addr + delta;
+	b->key  = tmp.key  + delta;
+}
+
+static inline void static_call_sort_entries(struct static_call_site *start,
+					    struct static_call_site *stop)
+{
+	sort(start, stop - start, sizeof(struct static_call_site),
+	     static_call_site_cmp, static_call_site_swap);
+}
+
+static inline bool static_call_key_has_mods(struct static_call_key *key)
+{
+	return !(key->type & 1);
+}
+
+static inline struct static_call_mod *static_call_key_next(struct static_call_key *key)
+{
+	if (!static_call_key_has_mods(key))
+		return NULL;
+
+	return key->mods;
+}
+
+static inline struct static_call_site *static_call_key_sites(struct static_call_key *key)
+{
+	if (static_call_key_has_mods(key))
+		return NULL;
+
+	return (struct static_call_site *)(key->type & ~1);
+}
+
+void __static_call_update(struct static_call_key *key, void *tramp, void *func)
+{
+	struct static_call_site *site, *stop;
+	struct static_call_mod *site_mod, first;
+
+	cpus_read_lock();
+	static_call_lock();
+
+	if (key->func == func)
+		goto done;
+
+	key->func = func;
+
+	arch_static_call_transform(NULL, tramp, func, false);
+
+	/*
+	 * If uninitialized, we'll not update the callsites, but they still
+	 * point to the trampoline and we just patched that.
+	 */
+	if (WARN_ON_ONCE(!static_call_initialized))
+		goto done;
+
+	first = (struct static_call_mod){
+		.next = static_call_key_next(key),
+		.mod = NULL,
+		.sites = static_call_key_sites(key),
+	};
+
+	for (site_mod = &first; site_mod; site_mod = site_mod->next) {
+		bool init = system_state < SYSTEM_RUNNING;
+		struct module *mod = site_mod->mod;
+
+		if (!site_mod->sites) {
+			/*
+			 * This can happen if the static call key is defined in
+			 * a module which doesn't use it.
+			 *
+			 * It also happens in the has_mods case, where the
+			 * 'first' entry has no sites associated with it.
+			 */
+			continue;
+		}
+
+		stop = __stop_static_call_sites;
+
+		if (mod) {
+#ifdef CONFIG_MODULES
+			stop = mod->static_call_sites +
+			       mod->num_static_call_sites;
+			init = mod->state == MODULE_STATE_COMING;
+#endif
+		}
+
+		for (site = site_mod->sites;
+		     site < stop && static_call_key(site) == key; site++) {
+			void *site_addr = static_call_addr(site);
+
+			if (!init && static_call_is_init(site))
+				continue;
+
+			if (!kernel_text_address((unsigned long)site_addr)) {
+				/*
+				 * This skips patching built-in __exit, which
+				 * is part of init_section_contains() but is
+				 * not part of kernel_text_address().
+				 *
+				 * Skipping built-in __exit is fine since it
+				 * will never be executed.
+				 */
+				WARN_ONCE(!static_call_is_init(site),
+					  "can't patch static call site at %pS",
+					  site_addr);
+				continue;
+			}
+
+			arch_static_call_transform(site_addr, NULL, func,
+						   static_call_is_tail(site));
+		}
+	}
+
+done:
+	static_call_unlock();
+	cpus_read_unlock();
+}
+EXPORT_SYMBOL_GPL(__static_call_update);
+
+static int __static_call_init(struct module *mod,
+			      struct static_call_site *start,
+			      struct static_call_site *stop)
+{
+	struct static_call_site *site;
+	struct static_call_key *key, *prev_key = NULL;
+	struct static_call_mod *site_mod;
+
+	if (start == stop)
+		return 0;
+
+	static_call_sort_entries(start, stop);
+
+	for (site = start; site < stop; site++) {
+		void *site_addr = static_call_addr(site);
+
+		if ((mod && within_module_init((unsigned long)site_addr, mod)) ||
+		    (!mod && init_section_contains(site_addr, 1)))
+			static_call_set_init(site);
+
+		key = static_call_key(site);
+		if (key != prev_key) {
+			prev_key = key;
+
+			/*
+			 * For vmlinux (!mod) avoid the allocation by storing
+			 * the sites pointer in the key itself. Also see
+			 * __static_call_update()'s @first.
+			 *
+			 * This allows architectures (eg. x86) to call
+			 * static_call_init() before memory allocation works.
+			 */
+			if (!mod) {
+				key->sites = site;
+				key->type |= 1;
+				goto do_transform;
+			}
+
+			site_mod = kzalloc(sizeof(*site_mod), GFP_KERNEL);
+			if (!site_mod)
+				return -ENOMEM;
+
+			/*
+			 * When the key has a direct sites pointer, extract
+			 * that into an explicit struct static_call_mod, so we
+			 * can have a list of modules.
+			 */
+			if (static_call_key_sites(key)) {
+				site_mod->mod = NULL;
+				site_mod->next = NULL;
+				site_mod->sites = static_call_key_sites(key);
+
+				key->mods = site_mod;
+
+				site_mod = kzalloc(sizeof(*site_mod), GFP_KERNEL);
+				if (!site_mod)
+					return -ENOMEM;
+			}
+
+			site_mod->mod = mod;
+			site_mod->sites = site;
+			site_mod->next = static_call_key_next(key);
+			key->mods = site_mod;
+		}
+
+do_transform:
+		arch_static_call_transform(site_addr, NULL, key->func,
+				static_call_is_tail(site));
+	}
+
+	return 0;
+}
+
+static int addr_conflict(struct static_call_site *site, void *start, void *end)
+{
+	unsigned long addr = (unsigned long)static_call_addr(site);
+
+	if (addr <= (unsigned long)end &&
+	    addr + CALL_INSN_SIZE > (unsigned long)start)
+		return 1;
+
+	return 0;
+}
+
+static int __static_call_text_reserved(struct static_call_site *iter_start,
+				       struct static_call_site *iter_stop,
+				       void *start, void *end, bool init)
+{
+	struct static_call_site *iter = iter_start;
+
+	while (iter < iter_stop) {
+		if (init || !static_call_is_init(iter)) {
+			if (addr_conflict(iter, start, end))
+				return 1;
+		}
+		iter++;
+	}
+
+	return 0;
+}
+
+#ifdef CONFIG_MODULES
+
+static int __static_call_mod_text_reserved(void *start, void *end)
+{
+	struct module *mod;
+	int ret;
+
+	preempt_disable();
+	mod = __module_text_address((unsigned long)start);
+	WARN_ON_ONCE(__module_text_address((unsigned long)end) != mod);
+	if (!try_module_get(mod))
+		mod = NULL;
+	preempt_enable();
+
+	if (!mod)
+		return 0;
+
+	ret = __static_call_text_reserved(mod->static_call_sites,
+			mod->static_call_sites + mod->num_static_call_sites,
+			start, end, mod->state == MODULE_STATE_COMING);
+
+	module_put(mod);
+
+	return ret;
+}
+
+static unsigned long tramp_key_lookup(unsigned long addr)
+{
+	struct static_call_tramp_key *start = __start_static_call_tramp_key;
+	struct static_call_tramp_key *stop = __stop_static_call_tramp_key;
+	struct static_call_tramp_key *tramp_key;
+
+	for (tramp_key = start; tramp_key != stop; tramp_key++) {
+		unsigned long tramp;
+
+		tramp = (long)tramp_key->tramp + (long)&tramp_key->tramp;
+		if (tramp == addr)
+			return (long)tramp_key->key + (long)&tramp_key->key;
+	}
+
+	return 0;
+}
+
+static int static_call_add_module(struct module *mod)
+{
+	struct static_call_site *start = mod->static_call_sites;
+	struct static_call_site *stop = start + mod->num_static_call_sites;
+	struct static_call_site *site;
+
+	for (site = start; site != stop; site++) {
+		unsigned long s_key = __static_call_key(site);
+		unsigned long addr = s_key & ~STATIC_CALL_SITE_FLAGS;
+		unsigned long key;
+
+		/*
+		 * Is the key is exported, 'addr' points to the key, which
+		 * means modules are allowed to call static_call_update() on
+		 * it.
+		 *
+		 * Otherwise, the key isn't exported, and 'addr' points to the
+		 * trampoline so we need to lookup the key.
+		 *
+		 * We go through this dance to prevent crazy modules from
+		 * abusing sensitive static calls.
+		 */
+		if (!kernel_text_address(addr))
+			continue;
+
+		key = tramp_key_lookup(addr);
+		if (!key) {
+			pr_warn("Failed to fixup __raw_static_call() usage at: %ps\n",
+				static_call_addr(site));
+			return -EINVAL;
+		}
+
+		key |= s_key & STATIC_CALL_SITE_FLAGS;
+		site->key = key - (long)&site->key;
+	}
+
+	return __static_call_init(mod, start, stop);
+}
+
+static void static_call_del_module(struct module *mod)
+{
+	struct static_call_site *start = mod->static_call_sites;
+	struct static_call_site *stop = mod->static_call_sites +
+					mod->num_static_call_sites;
+	struct static_call_key *key, *prev_key = NULL;
+	struct static_call_mod *site_mod, **prev;
+	struct static_call_site *site;
+
+	for (site = start; site < stop; site++) {
+		key = static_call_key(site);
+		if (key == prev_key)
+			continue;
+
+		prev_key = key;
+
+		for (prev = &key->mods, site_mod = key->mods;
+		     site_mod && site_mod->mod != mod;
+		     prev = &site_mod->next, site_mod = site_mod->next)
+			;
+
+		if (!site_mod)
+			continue;
+
+		*prev = site_mod->next;
+		kfree(site_mod);
+	}
+}
+
+static int static_call_module_notify(struct notifier_block *nb,
+				     unsigned long val, void *data)
+{
+	struct module *mod = data;
+	int ret = 0;
+
+	cpus_read_lock();
+	static_call_lock();
+
+	switch (val) {
+	case MODULE_STATE_COMING:
+		ret = static_call_add_module(mod);
+		if (ret) {
+			WARN(1, "Failed to allocate memory for static calls");
+			static_call_del_module(mod);
+		}
+		break;
+	case MODULE_STATE_GOING:
+		static_call_del_module(mod);
+		break;
+	}
+
+	static_call_unlock();
+	cpus_read_unlock();
+
+	return notifier_from_errno(ret);
+}
+
+static struct notifier_block static_call_module_nb = {
+	.notifier_call = static_call_module_notify,
+};
+
+#else
+
+static inline int __static_call_mod_text_reserved(void *start, void *end)
+{
+	return 0;
+}
+
+#endif /* CONFIG_MODULES */
+
+int static_call_text_reserved(void *start, void *end)
+{
+	bool init = system_state < SYSTEM_RUNNING;
+	int ret = __static_call_text_reserved(__start_static_call_sites,
+			__stop_static_call_sites, start, end, init);
+
+	if (ret)
+		return ret;
+
+	return __static_call_mod_text_reserved(start, end);
+}
+
+int __init static_call_init(void)
+{
+	int ret;
+
+	if (static_call_initialized)
+		return 0;
+
+	cpus_read_lock();
+	static_call_lock();
+	ret = __static_call_init(NULL, __start_static_call_sites,
+				 __stop_static_call_sites);
+	static_call_unlock();
+	cpus_read_unlock();
+
+	if (ret) {
+		pr_err("Failed to allocate memory for static_call!\n");
+		BUG();
+	}
+
+	static_call_initialized = true;
+
+#ifdef CONFIG_MODULES
+	register_module_notifier(&static_call_module_nb);
+#endif
+	return 0;
+}
+early_initcall(static_call_init);
+
+#ifdef CONFIG_STATIC_CALL_SELFTEST
+
+static int func_a(int x)
+{
+	return x+1;
+}
+
+static int func_b(int x)
+{
+	return x+2;
+}
+
+DEFINE_STATIC_CALL(sc_selftest, func_a);
+
+static struct static_call_data {
+      int (*func)(int);
+      int val;
+      int expect;
+} static_call_data [] __initdata = {
+      { NULL,   2, 3 },
+      { func_b, 2, 4 },
+      { func_a, 2, 3 }
+};
+
+static int __init test_static_call_init(void)
+{
+      int i;
+
+      for (i = 0; i < ARRAY_SIZE(static_call_data); i++ ) {
+	      struct static_call_data *scd = &static_call_data[i];
+
+              if (scd->func)
+                      static_call_update(sc_selftest, scd->func);
+
+              WARN_ON(static_call(sc_selftest)(scd->val) != scd->expect);
+      }
+
+      return 0;
+}
+early_initcall(test_static_call_init);
+
+#endif /* CONFIG_STATIC_CALL_SELFTEST */
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index dcdcb85121e4..2c22023fbf5f 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -532,6 +532,23 @@ u64 notrace ktime_get_boot_fast_ns(void)
 }
 EXPORT_SYMBOL_GPL(ktime_get_boot_fast_ns);
 
+/**
+ * ktime_get_tai_fast_ns - NMI safe and fast access to tai clock.
+ *
+ * The same limitations as described for ktime_get_boot_fast_ns() apply. The
+ * mono time and the TAI offset are not read atomically which may yield wrong
+ * readouts. However, an update of the TAI offset is an rare event e.g., caused
+ * by settime or adjtimex with an offset. The user of this function has to deal
+ * with the possibility of wrong timestamps in post processing.
+ */
+u64 notrace ktime_get_tai_fast_ns(void)
+{
+	struct timekeeper *tk = &tk_core.timekeeper;
+
+	return (ktime_get_mono_fast_ns() + ktime_to_ns(data_race(tk->offs_tai)));
+}
+EXPORT_SYMBOL_GPL(ktime_get_tai_fast_ns);
+
 static __always_inline u64 __ktime_get_real_fast(struct tk_fast *tkf, u64 *mono)
 {
 	struct tk_read_base *tkr;
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 7fa2ebc07f60..d8553f46caa2 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -2349,11 +2349,11 @@ kprobe_multi_link_handler(struct fprobe *fp, unsigned long entry_ip,
 }
 
 static int
-kprobe_multi_resolve_syms(const void *usyms, u32 cnt,
+kprobe_multi_resolve_syms(const void __user *usyms, u32 cnt,
 			  unsigned long *addrs)
 {
 	unsigned long addr, size;
-	const char **syms;
+	const char __user **syms;
 	int err = -ENOMEM;
 	unsigned int i;
 	char *func;
diff --git a/kernel/trace/rethook.c b/kernel/trace/rethook.c
index ab463a4d2b23..b56833700d23 100644
--- a/kernel/trace/rethook.c
+++ b/kernel/trace/rethook.c
@@ -65,7 +65,7 @@ static void rethook_free_rcu(struct rcu_head *head)
  */
 void rethook_free(struct rethook *rh)
 {
-	rcu_assign_pointer(rh->handler, NULL);
+	WRITE_ONCE(rh->handler, NULL);
 
 	call_rcu(&rh->rcu, rethook_free_rcu);
 }