diff --git a/arch/arm/include/asm/mmu_context.h b/arch/arm/include/asm/mmu_context.h
--- a/arch/arm/include/asm/mmu_context.h
+++ b/arch/arm/include/asm/mmu_context.h
@@ -80,7 +80,7 @@ static inline void check_and_switch_context(struct mm_struct *mm,
 #ifndef MODULE
 #define finish_arch_post_lock_switch \
 	finish_arch_post_lock_switch
-static inline void finish_arch_post_lock_switch(void)
+static __always_inline void finish_arch_post_lock_switch(void)
 {
 	struct mm_struct *mm = current->mm;
 
diff --git a/arch/riscv/include/asm/sync_core.h b/arch/riscv/include/asm/sync_core.h
--- a/arch/riscv/include/asm/sync_core.h
+++ b/arch/riscv/include/asm/sync_core.h
@@ -6,7 +6,7 @@
  * RISC-V implements return to user-space through an xRET instruction,
  * which is not core serializing.
  */
-static inline void sync_core_before_usermode(void)
+static __always_inline void sync_core_before_usermode(void)
 {
 	asm volatile ("fence.i" ::: "memory");
 }
diff --git a/arch/s390/include/asm/mmu_context.h b/arch/s390/include/asm/mmu_context.h
--- a/arch/s390/include/asm/mmu_context.h
+++ b/arch/s390/include/asm/mmu_context.h
@@ -93,7 +93,7 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next,
 }
 
 #define finish_arch_post_lock_switch finish_arch_post_lock_switch
-static inline void finish_arch_post_lock_switch(void)
+static __always_inline void finish_arch_post_lock_switch(void)
 {
 	struct task_struct *tsk = current;
 	struct mm_struct *mm = tsk->mm;
diff --git a/arch/sparc/include/asm/mmu_context_64.h b/arch/sparc/include/asm/mmu_context_64.h
--- a/arch/sparc/include/asm/mmu_context_64.h
+++ b/arch/sparc/include/asm/mmu_context_64.h
@@ -160,7 +160,7 @@ static inline void arch_start_context_switch(struct task_struct *prev)
 }
 
 #define finish_arch_post_lock_switch	finish_arch_post_lock_switch
-static inline void finish_arch_post_lock_switch(void)
+static __always_inline void finish_arch_post_lock_switch(void)
 {
 	/* Restore the state of MCDPER register for the new process
 	 * just switched to.
diff --git a/arch/x86/include/asm/sync_core.h b/arch/x86/include/asm/sync_core.h
--- a/arch/x86/include/asm/sync_core.h
+++ b/arch/x86/include/asm/sync_core.h
@@ -93,7 +93,7 @@ static __always_inline void sync_core(void)
  * to user-mode. x86 implements return to user-space through sysexit,
  * sysrel, and sysretq, which are not core serializing.
  */
-static inline void sync_core_before_usermode(void)
+static __always_inline void sync_core_before_usermode(void)
 {
 	/* With PTI, we unconditionally serialize before running user code. */
 	if (static_cpu_has(X86_FEATURE_PTI))
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -1632,7 +1632,7 @@ static inline void perf_event_task_migrate(struct task_struct *task)
 		task->sched_migrated = 1;
 }
 
-static inline void perf_event_task_sched_in(struct task_struct *prev,
+static __always_inline void perf_event_task_sched_in(struct task_struct *prev,
 					    struct task_struct *task)
 {
 	if (static_branch_unlikely(&perf_sched_events))
diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h
--- a/include/linux/sched/mm.h
+++ b/include/linux/sched/mm.h
@@ -32,7 +32,7 @@ extern struct mm_struct *mm_alloc(void);
  * See also <Documentation/mm/active_mm.rst> for an in-depth explanation
  * of &mm_struct.mm_count vs &mm_struct.mm_users.
  */
-static inline void mmgrab(struct mm_struct *mm)
+static __always_inline void mmgrab(struct mm_struct *mm)
 {
 	atomic_inc(&mm->mm_count);
 }
@@ -44,7 +44,7 @@ static inline void smp_mb__after_mmgrab(void)
 
 extern void __mmdrop(struct mm_struct *mm);
 
-static inline void mmdrop(struct mm_struct *mm)
+static __always_inline void mmdrop(struct mm_struct *mm)
 {
 	/*
 	 * The implicit full barrier implied by atomic_dec_and_test() is
@@ -71,27 +71,27 @@ static inline void __mmdrop_delayed(struct rcu_head *rhp)
  * Invoked from finish_task_switch(). Delegates the heavy lifting on RT
  * kernels via RCU.
  */
-static inline void mmdrop_sched(struct mm_struct *mm)
+static __always_inline void mmdrop_sched(struct mm_struct *mm)
 {
 	/* Provides a full memory barrier. See mmdrop() */
 	if (atomic_dec_and_test(&mm->mm_count))
 		call_rcu(&mm->delayed_drop, __mmdrop_delayed);
 }
 #else
-static inline void mmdrop_sched(struct mm_struct *mm)
+static __always_inline void mmdrop_sched(struct mm_struct *mm)
 {
 	mmdrop(mm);
 }
 #endif
 
 /* Helpers for lazy TLB mm refcounting */
-static inline void mmgrab_lazy_tlb(struct mm_struct *mm)
+static __always_inline void mmgrab_lazy_tlb(struct mm_struct *mm)
 {
 	if (IS_ENABLED(CONFIG_MMU_LAZY_TLB_REFCOUNT))
 		mmgrab(mm);
 }
 
-static inline void mmdrop_lazy_tlb(struct mm_struct *mm)
+static __always_inline void mmdrop_lazy_tlb(struct mm_struct *mm)
 {
 	if (IS_ENABLED(CONFIG_MMU_LAZY_TLB_REFCOUNT)) {
 		mmdrop(mm);
@@ -104,7 +104,7 @@ static inline void mmdrop_lazy_tlb(struct mm_struct *mm)
 	}
 }
 
-static inline void mmdrop_lazy_tlb_sched(struct mm_struct *mm)
+static __always_inline void mmdrop_lazy_tlb_sched(struct mm_struct *mm)
 {
 	if (IS_ENABLED(CONFIG_MMU_LAZY_TLB_REFCOUNT))
 		mmdrop_sched(mm);
@@ -128,12 +128,12 @@ static inline void mmdrop_lazy_tlb_sched(struct mm_struct *mm)
  * See also <Documentation/mm/active_mm.rst> for an in-depth explanation
  * of &mm_struct.mm_count vs &mm_struct.mm_users.
  */
-static inline void mmget(struct mm_struct *mm)
+static __always_inline void mmget(struct mm_struct *mm)
 {
 	atomic_inc(&mm->mm_users);
 }
 
-static inline bool mmget_not_zero(struct mm_struct *mm)
+static __always_inline bool mmget_not_zero(struct mm_struct *mm)
 {
 	return atomic_inc_not_zero(&mm->mm_users);
 }
@@ -532,7 +532,7 @@ enum {
 #include <asm/membarrier.h>
 #endif
 
-static inline void membarrier_mm_sync_core_before_usermode(struct mm_struct *mm)
+static __always_inline void membarrier_mm_sync_core_before_usermode(struct mm_struct *mm)
 {
 	/*
 	 * The atomic_read() below prevents CSE. The following should
diff --git a/include/linux/tick.h b/include/linux/tick.h
--- a/include/linux/tick.h
+++ b/include/linux/tick.h
@@ -175,7 +175,7 @@ extern cpumask_var_t tick_nohz_full_mask;
 #ifdef CONFIG_NO_HZ_FULL
 extern bool tick_nohz_full_running;
 
-static inline bool tick_nohz_full_enabled(void)
+static __always_inline bool tick_nohz_full_enabled(void)
 {
 	if (!context_tracking_enabled())
 		return false;
@@ -299,7 +299,7 @@ static inline void __tick_nohz_task_switch(void) { }
 static inline void tick_nohz_full_setup(cpumask_var_t cpumask) { }
 #endif
 
-static inline void tick_nohz_task_switch(void)
+static __always_inline void tick_nohz_task_switch(void)
 {
 	if (tick_nohz_full_enabled())
 		__tick_nohz_task_switch();
diff --git a/include/linux/vtime.h b/include/linux/vtime.h
--- a/include/linux/vtime.h
+++ b/include/linux/vtime.h
@@ -89,24 +89,24 @@ static __always_inline void vtime_account_guest_exit(void)
  * For now vtime state is tied to context tracking. We might want to decouple
  * those later if necessary.
  */
-static inline bool vtime_accounting_enabled(void)
+static __always_inline bool vtime_accounting_enabled(void)
 {
 	return context_tracking_enabled();
 }
 
-static inline bool vtime_accounting_enabled_cpu(int cpu)
+static __always_inline bool vtime_accounting_enabled_cpu(int cpu)
 {
 	return vtime_generic_enabled_cpu(cpu);
 }
 
-static inline bool vtime_accounting_enabled_this_cpu(void)
+static __always_inline bool vtime_accounting_enabled_this_cpu(void)
 {
 	return vtime_generic_enabled_this_cpu();
 }
 
 extern void vtime_task_switch_generic(struct task_struct *prev);
 
-static inline void vtime_task_switch(struct task_struct *prev)
+static __always_inline void vtime_task_switch(struct task_struct *prev)
 {
 	if (vtime_accounting_enabled_this_cpu())
 		vtime_task_switch_generic(prev);
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -5099,7 +5099,7 @@ static inline void prepare_task(struct task_struct *next)
 	WRITE_ONCE(next->on_cpu, 1);
 }
 
-static inline void finish_task(struct task_struct *prev)
+static __always_inline void finish_task(struct task_struct *prev)
 {
 	/*
 	 * This must be the very last reference to @prev from this CPU. After
@@ -5143,7 +5143,7 @@ static void zap_balance_callbacks(struct rq *rq)
 	rq->balance_callback = found ? &balance_push_callback : NULL;
 }
 
-static void do_balance_callbacks(struct rq *rq, struct balance_callback *head)
+static __always_inline void do_balance_callbacks(struct rq *rq, struct balance_callback *head)
 {
 	void (*func)(struct rq *rq);
 	struct balance_callback *next;
@@ -5178,7 +5178,7 @@ struct balance_callback balance_push_callback = {
 	.func = balance_push,
 };
 
-static inline struct balance_callback *
+static __always_inline struct balance_callback *
 __splice_balance_callbacks(struct rq *rq, bool split)
 {
 	struct balance_callback *head = rq->balance_callback;
@@ -5252,7 +5252,7 @@ prepare_lock_switch(struct rq *rq, struct task_struct *next, struct rq_flags *rf
 	__acquire(__rq_lockp(this_rq()));
 }
 
-static inline void finish_lock_switch(struct rq *rq)
+static __always_inline void finish_lock_switch(struct rq *rq)
 	__releases(__rq_lockp(rq))
 {
 	/*
@@ -5286,7 +5286,7 @@ static inline void kmap_local_sched_out(void)
 #endif
 }
 
-static inline void kmap_local_sched_in(void)
+static __always_inline void kmap_local_sched_in(void)
 {
 #ifdef CONFIG_KMAP_LOCAL
 	if (unlikely(current->kmap_ctrl.idx))
@@ -5340,7 +5340,7 @@ prepare_task_switch(struct rq *rq, struct task_struct *prev,
  * past. 'prev == current' is still correct but we need to recalculate this_rq
  * because prev may have moved to another CPU.
  */
-static struct rq *finish_task_switch(struct task_struct *prev)
+static __always_inline struct rq *finish_task_switch(struct task_struct *prev)
 	__releases(__rq_lockp(this_rq()))
 {
 	struct rq *rq = this_rq();
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1460,12 +1460,12 @@ static inline struct cpumask *sched_group_span(struct sched_group *sg);
 
 DECLARE_STATIC_KEY_FALSE(__sched_core_enabled);
 
-static inline bool sched_core_enabled(struct rq *rq)
+static __always_inline bool sched_core_enabled(struct rq *rq)
 {
 	return static_branch_unlikely(&__sched_core_enabled) && rq->core_enabled;
 }
 
-static inline bool sched_core_disabled(void)
+static __always_inline bool sched_core_disabled(void)
 {
 	return !static_branch_unlikely(&__sched_core_enabled);
 }
@@ -1474,7 +1474,7 @@ static inline bool sched_core_disabled(void)
  * Be careful with this function; not for general use. The return value isn't
  * stable unless you actually hold a relevant rq->__lock.
  */
-static inline raw_spinlock_t *rq_lockp(struct rq *rq)
+static __always_inline raw_spinlock_t *rq_lockp(struct rq *rq)
 {
 	if (sched_core_enabled(rq))
 		return &rq->core->__lock;
@@ -1482,7 +1482,7 @@ static inline raw_spinlock_t *rq_lockp(struct rq *rq)
 	return &rq->__lock;
 }
 
-static inline raw_spinlock_t *__rq_lockp(struct rq *rq)
+static __always_inline raw_spinlock_t *__rq_lockp(struct rq *rq)
 	__returns_ctx_lock(rq_lockp(rq)) /* alias them */
 {
 	if (rq->core_enabled)
@@ -1585,12 +1585,12 @@ static inline bool sched_core_disabled(void)
 	return true;
 }
 
-static inline raw_spinlock_t *rq_lockp(struct rq *rq)
+static __always_inline raw_spinlock_t *rq_lockp(struct rq *rq)
 {
 	return &rq->__lock;
 }
 
-static inline raw_spinlock_t *__rq_lockp(struct rq *rq)
+static __always_inline raw_spinlock_t *__rq_lockp(struct rq *rq)
 	__returns_ctx_lock(rq_lockp(rq)) /* alias them */
 {
 	return &rq->__lock;
@@ -1650,33 +1650,33 @@ extern void raw_spin_rq_lock_nested(struct rq *rq, int subclass)
 extern bool raw_spin_rq_trylock(struct rq *rq)
 	__cond_acquires(true, __rq_lockp(rq));
 
-static inline void raw_spin_rq_lock(struct rq *rq)
+static __always_inline void raw_spin_rq_lock(struct rq *rq)
 	__acquires(__rq_lockp(rq))
 {
 	raw_spin_rq_lock_nested(rq, 0);
 }
 
-static inline void raw_spin_rq_unlock(struct rq *rq)
+static __always_inline void raw_spin_rq_unlock(struct rq *rq)
 	__releases(__rq_lockp(rq))
 {
 	raw_spin_unlock(rq_lockp(rq));
 }
 
-static inline void raw_spin_rq_lock_irq(struct rq *rq)
+static __always_inline void raw_spin_rq_lock_irq(struct rq *rq)
 	__acquires(__rq_lockp(rq))
 {
 	local_irq_disable();
 	raw_spin_rq_lock(rq);
 }
 
-static inline void raw_spin_rq_unlock_irq(struct rq *rq)
+static __always_inline void raw_spin_rq_unlock_irq(struct rq *rq)
 	__releases(__rq_lockp(rq))
 {
 	raw_spin_rq_unlock(rq);
 	local_irq_enable();
 }
 
-static inline unsigned long _raw_spin_rq_lock_irqsave(struct rq *rq)
+static __always_inline unsigned long _raw_spin_rq_lock_irqsave(struct rq *rq)
 	__acquires(__rq_lockp(rq))
 {
 	unsigned long flags;
@@ -1687,7 +1687,7 @@ static inline unsigned long _raw_spin_rq_lock_irqsave(struct rq *rq)
 	return flags;
 }
 
-static inline void raw_spin_rq_unlock_irqrestore(struct rq *rq, unsigned long flags)
+static __always_inline void raw_spin_rq_unlock_irqrestore(struct rq *rq, unsigned long flags)
 	__releases(__rq_lockp(rq))
 {
 	raw_spin_rq_unlock(rq);