[PATCH v4 0/3] Optimize code generation during context switching

[PATCH v4 0/3] Optimize code generation during context switching

[Xie Yuanbin]

The purpose of this series of patches is to optimize the performance of
context switching. It does not change the code logic, but only modifies
the inline attributes of some functions.

It is found that finish_task_switch() is not inlined even in the O2 level
optimization. This may affect performance for the following reasons:
1. It is in the context switching code, which is a hot code path.
2. Because of the modern CPU vulnerabilities, kernel is likely to perform
some mitigations inside switch_mm_irq_off(), such as branch prediction
hardening or l1d flushing, the instruction pipeline and cache may be
flushed. finish_task_switch() is right after that, so the performance
here is greatly affected by function calls and branch jumps.
3. The __schedule function has __sched attribute, which makes it be
placed in the ".sched.text" section, while finish_task_switch() does not,
which causes their distance to be very far in binary, aggravating the
above performance degradation.

This series of patches primarily make some functions called in context
switching as always inline to optimize performance. Here is the
performance test data for these patches:
Time spent on calling finish_task_switch(), the unit is tsc from x86:
 | test scenario             | old   | new   | delta          |
 | gcc 15.2                  | 13.94 | 12.40 | 1.54  (-11.1%) |
 | gcc 15.2 + spectre_v2     | 24.78 | 13.70 | 11.08 (-44.7%) |
 | clang 21.1.4              | 13.90 | 12.71 | 1.19  (- 8.6%) |
 | clang 21.1.4 + spectre_v2 | 29.01 | 18.91 | 10.1  (-34.8%) |

Additional information:
1. The testing kernel source is commit 9c0826a5d9aa4d52206d ("Add
linux-next specific files for 20251107") from linux-next branch.

2. Testing machine:
cpu: intel i5-8300h@4Ghz
mem: DDR4 2666MHz
Bare-metal boot, non-virtualized environment

3. Testing compiler:
gcc: gcc version 15.2.0 (Debian 15.2.0-7) with
GNU ld (GNU Binutils for Debian) 2.45
clang: Debian clang version 21.1.4 (8) with
Debian LLD 21.1.4 (compatible with GNU linkers)

4. Testing config:
base on default x86_64_defconfig, and setting:
CONFIG_HZ=100
CONFIG_DEBUG_ENTRY=n
CONFIG_X86_DEBUG_FPU=n
CONFIG_EXPERT=y
CONFIG_MODIFY_LDT_SYSCALL=n
CONFIG_CGROUPS=n
CONFIG_BLK_DEV_NVME=y

5. Test method:
Use rdtsc (cntvct_el0 can be use on arm64/arm) to obtain timestamps
before and after finish_task_switch() calling point, and created multiple
processes to trigger context switches, then calculated the average
duration of the finish_task_switch() call.
Note that using multiple processes rather than threads is recommended for
testing, because this will trigger switch_mm_irqs_off(), where
spectre_v2 mitigations may be performed, during context switching.

6. Testing code:
kernel:
```patch
diff --git a/arch/x86/entry/syscalls/syscall_64.tbl b/arch/x86/entry/syscalls/syscall_64.tbl
index 8a4ac4841be6..5a42ec008620 100644
--- a/arch/x86/entry/syscalls/syscall_64.tbl
+++ b/arch/x86/entry/syscalls/syscall_64.tbl
@@ -395,6 +395,7 @@
 468	common	file_getattr		sys_file_getattr
 469	common	file_setattr		sys_file_setattr
 470	common	listns			sys_listns
+471	common	sched_test		sys_sched_test
 
 #
 # Due to a historical design error, certain syscalls are numbered differently
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 81cf8452449a..d7e2095aeb7d 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -5195,6 +5195,36 @@ asmlinkage __visible void schedule_tail(struct task_struct *prev)
 	calculate_sigpending();
 }
 
+static DEFINE_PER_CPU(uint64_t, start_time);
+static DEFINE_PER_CPU(uint64_t, total_time);
+static DEFINE_PER_CPU(uint64_t, total_count);
+
+static __always_inline uint64_t test_rdtsc(void)
+{
+    register uint64_t rax __asm__("rax");
+    register uint64_t rdx __asm__("rdx");
+
+    __asm__ __volatile__ ("rdtsc" : "=a"(rax), "=d"(rdx));
+    return rax | (rdx << 32);
+}
+
+static __always_inline void test_start(void)
+{
+	raw_cpu_write(start_time, test_rdtsc());
+}
+
+static __always_inline void test_end(void)
+{
+	const uint64_t end_time = test_rdtsc();
+	const uint64_t cost_time = end_time - raw_cpu_read(start_time);
+
+	raw_cpu_add(total_time, cost_time);
+	if (unlikely(raw_cpu_inc_return(total_count) % (1 << 20) == 0)) {
+		pr_emerg("cpu %d total_time %llu\n", raw_smp_processor_id(), raw_cpu_read(total_time));
+		raw_cpu_write(total_time, 0);
+	}
+}
+
 /*
  * context_switch - switch to the new MM and the new thread's register state.
  */
@@ -5264,7 +5294,10 @@ context_switch(struct rq *rq, struct task_struct *prev,
 	switch_to(prev, next, prev);
 	barrier();
 
-	return finish_task_switch(prev);
+	test_start();
+	rq = finish_task_switch(prev);
+	test_end();
+	return rq;
 }
 
 /*
@@ -10861,3 +10894,18 @@ void sched_change_end(struct sched_change_ctx *ctx)
 		p->sched_class->prio_changed(rq, p, ctx->prio);
 	}
 }
+
+static struct task_struct *wait_task;
+
+SYSCALL_DEFINE0(sched_test)
+{
+	preempt_disable();
+	while (1) {
+		if (likely(wait_task))
+			wake_up_process(wait_task);
+		wait_task = current;
+		set_current_state(TASK_UNINTERRUPTIBLE);
+		__schedule(SM_NONE);
+	}
+	return 0;
+}
```

User program:
```c
int main()
{
	cpu_set_t mask;
	if (fork())
		sleep(1);

	CPU_ZERO(&mask);
	CPU_SET(5, &mask); // Assume that cpu5 exists
	assert(sched_setaffinity(0, sizeof(mask), &mask) == 0);
	syscall(471);
	// unreachable
	return 0;
}
```

Usage:
1. set core5 as isolated cpu: add "isolcpus=5" to cmdline
2. run user programe
3. wait for kernel print

v3->v4: https://lore.kernel.org/20251113105227.57650-1-qq570070308@gmail.com
  - Improve the commit message

v2->v3: https://lore.kernel.org/20251108172346.263590-1-qq570070308@gmail.com
  - Fix building error in patch 1
  - Simply add the __always_inline attribute to the existing function,
    Instead of adding the always inline version functions

v1->v2: https://lore.kernel.org/20251024182628.68921-1-qq570070308@gmail.com
  - Make raw_spin_rq_unlock() inline
  - Make __balance_callbacks() inline
  - Add comments for always inline functions
  - Add Performance Test Data

Xie Yuanbin (3):
  x86/mm/tlb: Make enter_lazy_tlb() always inline on x86
  sched: Make raw_spin_rq_unlock() inline
  sched/core: Make finish_task_switch() and its subfunctions always
    inline

 arch/arm/include/asm/mmu_context.h      |  2 +-
 arch/riscv/include/asm/sync_core.h      |  2 +-
 arch/s390/include/asm/mmu_context.h     |  2 +-
 arch/sparc/include/asm/mmu_context_64.h |  2 +-
 arch/x86/include/asm/mmu_context.h      | 23 ++++++++++++++++++++++-
 arch/x86/include/asm/sync_core.h        |  2 +-
 arch/x86/mm/tlb.c                       | 21 ---------------------
 include/linux/perf_event.h              |  2 +-
 include/linux/sched/mm.h                | 10 +++++-----
 include/linux/tick.h                    |  4 ++--
 include/linux/vtime.h                   |  8 ++++----
 kernel/sched/core.c                     | 19 +++++++------------
 kernel/sched/sched.h                    | 24 ++++++++++++++----------
 13 files changed, 60 insertions(+), 61 deletions(-)

-- 
2.51.0

[PATCH v4 1/3] x86/mm/tlb: Make enter_lazy_tlb() always inline on x86

[Xie Yuanbin]

enter_lazy_tlb() on x86 is short enough, and is called in context
switching, which is the hot code path.

Make enter_lazy_tlb() always inline on x86 to optimize performance.

Signed-off-by: Xie Yuanbin <qq570070308@gmail.com>
Reviewed-by: Rik van Riel <riel@surriel.com>
Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202511091959.kfmo9kPB-lkp@intel.com/
Closes: https://lore.kernel.org/oe-kbuild-all/202511092219.73aMMES4-lkp@intel.com/
Closes: https://lore.kernel.org/oe-kbuild-all/202511100042.ZklpqjOY-lkp@intel.com/
Cc: David Hildenbrand (Red Hat) <david@kernel.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
---
V3->V4: https://lore.kernel.org/20251113105227.57650-2-qq570070308@gmail.com
  - Revise commit message: changing inline to always inline
V2->V3: https://lore.kernel.org/20251108172346.263590-2-qq570070308@gmail.com
  - Add `#ifndef MODULE` to fix build errors

 arch/x86/include/asm/mmu_context.h | 23 ++++++++++++++++++++++-
 arch/x86/mm/tlb.c                  | 21 ---------------------
 2 files changed, 22 insertions(+), 22 deletions(-)

diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h
index 73bf3b1b44e8..ecd134dcfb34 100644
--- a/arch/x86/include/asm/mmu_context.h
+++ b/arch/x86/include/asm/mmu_context.h
@@ -136,8 +136,29 @@ static inline void mm_reset_untag_mask(struct mm_struct *mm)
 }
 #endif
 
+/*
+ * Please ignore the name of this function.  It should be called
+ * switch_to_kernel_thread().
+ *
+ * enter_lazy_tlb() is a hint from the scheduler that we are entering a
+ * kernel thread or other context without an mm.  Acceptable implementations
+ * include doing nothing whatsoever, switching to init_mm, or various clever
+ * lazy tricks to try to minimize TLB flushes.
+ *
+ * The scheduler reserves the right to call enter_lazy_tlb() several times
+ * in a row.  It will notify us that we're going back to a real mm by
+ * calling switch_mm_irqs_off().
+ */
 #define enter_lazy_tlb enter_lazy_tlb
-extern void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk);
+#ifndef MODULE
+static __always_inline void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk)
+{
+	if (this_cpu_read(cpu_tlbstate.loaded_mm) == &init_mm)
+		return;
+
+	this_cpu_write(cpu_tlbstate_shared.is_lazy, true);
+}
+#endif
 
 #define mm_init_global_asid mm_init_global_asid
 extern void mm_init_global_asid(struct mm_struct *mm);
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index f5b93e01e347..71abaf0bdb91 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -971,27 +971,6 @@ void switch_mm_irqs_off(struct mm_struct *unused, struct mm_struct *next,
 	}
 }
 
-/*
- * Please ignore the name of this function.  It should be called
- * switch_to_kernel_thread().
- *
- * enter_lazy_tlb() is a hint from the scheduler that we are entering a
- * kernel thread or other context without an mm.  Acceptable implementations
- * include doing nothing whatsoever, switching to init_mm, or various clever
- * lazy tricks to try to minimize TLB flushes.
- *
- * The scheduler reserves the right to call enter_lazy_tlb() several times
- * in a row.  It will notify us that we're going back to a real mm by
- * calling switch_mm_irqs_off().
- */
-void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk)
-{
-	if (this_cpu_read(cpu_tlbstate.loaded_mm) == &init_mm)
-		return;
-
-	this_cpu_write(cpu_tlbstate_shared.is_lazy, true);
-}
-
 /*
  * Using a temporary mm allows to set temporary mappings that are not accessible
  * by other CPUs. Such mappings are needed to perform sensitive memory writes
-- 
2.51.0

[PATCH v4 2/3] sched: Make raw_spin_rq_unlock() inline

[Xie Yuanbin]

raw_spin_rq_unlock() is short, and is called in some hot code paths
such as finish_lock_switch.

Make raw_spin_rq_unlock() inline to optimize performance.

Signed-off-by: Xie Yuanbin <qq570070308@gmail.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Rik van Riel <riel@surriel.com>
Cc: Segher Boessenkool <segher@kernel.crashing.org>
Cc: David Hildenbrand (Red Hat) <david@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: H. Peter Anvin (Intel) <hpa@zytor.com>
---
V3->V4: https://lore.kernel.org/20251113105227.57650-3-qq570070308@gmail.com
  -- Revise commit message

 kernel/sched/core.c  | 5 -----
 kernel/sched/sched.h | 6 +++++-
 2 files changed, 5 insertions(+), 6 deletions(-)

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index f2931af76405..0f9e9f54d0a8 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -678,11 +678,6 @@ bool raw_spin_rq_trylock(struct rq *rq)
 	}
 }
 
-void raw_spin_rq_unlock(struct rq *rq)
-{
-	raw_spin_unlock(rq_lockp(rq));
-}
-
 /*
  * double_rq_lock - safely lock two runqueues
  */
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index bbf513b3e76c..a60b238cb0f5 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1551,13 +1551,17 @@ static inline void lockdep_assert_rq_held(struct rq *rq)
 
 extern void raw_spin_rq_lock_nested(struct rq *rq, int subclass);
 extern bool raw_spin_rq_trylock(struct rq *rq);
-extern void raw_spin_rq_unlock(struct rq *rq);
 
 static inline void raw_spin_rq_lock(struct rq *rq)
 {
 	raw_spin_rq_lock_nested(rq, 0);
 }
 
+static inline void raw_spin_rq_unlock(struct rq *rq)
+{
+	raw_spin_unlock(rq_lockp(rq));
+}
+
 static inline void raw_spin_rq_lock_irq(struct rq *rq)
 {
 	local_irq_disable();
-- 
2.51.0

[PATCH v4 3/3] sched/core: Make finish_task_switch() and its subfunctions always inline

[Xie Yuanbin]

finish_task_switch() is a hot code path in context switching.
When spectre_v2_user is enabled, kernel is likely to perform branch
prediction hardening inside switch_mm_irqs_off(). finish_task_switch()
is right after switch_mm_irqs_off(), so the performance here is
greatly affected by function calls and branch jumps.

Make finish_task_switch() always inline to optimize performance.

After finish_task_switch() is changed as always inline, the number of
calling points of subfunctions increases. According to the compiler
optimization strategy, subfunctions that were originally inline may no
longer be inline.

Also make the subfunctions of finish_task_stwitch() always inline to
prevent performance degradation.

There is a improvement in the performace of finish_task_switch(). When
spectre v2 is enabled, the improvement is significant.

The following are testing results from intel i5-8300h@4Ghz (x86):
Time spent on calling finish_task_switch(), the unit is tsc from x86:
 | test scenario             | old   | new   | delta          |
 | gcc 15.2                  | 13.94 | 12.40 | 1.54  (-11.1%) |
 | gcc 15.2 + spectre_v2     | 24.78 | 13.70 | 11.08 (-44.7%) |
 | clang 21.1.4              | 13.90 | 12.71 | 1.19  (- 8.6%) |
 | clang 21.1.4 + spectre_v2 | 29.01 | 18.91 | 10.1  (-34.8%) |

There is a minor improvement in the size of .text section in vmlinux,
the unit is bytes:
 | test scenario             | old      | new      | delta |
 | gcc 15.2                  | 16208096 | 16208736 | 640   |
 | clang 21.1.4              | 17943328 | 17944224 | 896   |

No size changes were found on bzImage.

Signed-off-by: Xie Yuanbin <qq570070308@gmail.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Rik van Riel <riel@surriel.com>
Cc: Segher Boessenkool <segher@kernel.crashing.org>
Cc: David Hildenbrand (Red Hat) <david@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: H. Peter Anvin (Intel) <hpa@zytor.com>
Cc: Arnd Bergmann <arnd@arndb.de>
---
Additional information:
1. The default spectre_v2 mitigation strategy on x86 is conditional, it
can be set to always by appending "spectre_v2_user=on" to cmdline.
However, on arm64/arm32, spectre v2 mitigation is enabled by default, and
it should be disabled by adding "nospectre_v2" to the cmdline.

2. The testing kernel source is commit 9c0826a5d9aa4d52206d ("Add
linux-next specific files for 20251107") from linux-next branch.

3. When testing for performace, I use the default x86_64_defconfig,
and setting:
CONFIG_HZ=100
CONFIG_DEBUG_ENTRY=n
CONFIG_X86_DEBUG_FPU=n
CONFIG_EXPERT=y
CONFIG_MODIFY_LDT_SYSCALL=n
CONFIG_CGROUPS=n
CONFIG_BLK_DEV_NVME=y
When testing for size, I use the default x86_64_defconfig,
and setting:
CONFIG_SCHED_CORE=y
CONFIG_CC_OPTIMIZE_FOR_SIZE=y
CONFIG_NO_HZ_FULL=y

4. It is recommended that using multiple processes rather than threads to
do the test, because this will trigger switch_mm_irqs_off(), where
spectre_v2 mitigations may be performed, during context switching.

5. The test code can be found at the end of the cover letter:
Link: https://lore.kernel.org/20251123121827.1304-1-qq570070308@gmail.com

 arch/arm/include/asm/mmu_context.h      |  2 +-
 arch/riscv/include/asm/sync_core.h      |  2 +-
 arch/s390/include/asm/mmu_context.h     |  2 +-
 arch/sparc/include/asm/mmu_context_64.h |  2 +-
 arch/x86/include/asm/sync_core.h        |  2 +-
 include/linux/perf_event.h              |  2 +-
 include/linux/sched/mm.h                | 10 +++++-----
 include/linux/tick.h                    |  4 ++--
 include/linux/vtime.h                   |  8 ++++----
 kernel/sched/core.c                     | 14 +++++++-------
 kernel/sched/sched.h                    | 20 ++++++++++----------
 11 files changed, 34 insertions(+), 34 deletions(-)

diff --git a/arch/arm/include/asm/mmu_context.h b/arch/arm/include/asm/mmu_context.h
index db2cb06aa8cf..bebde469f81a 100644
--- 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
index 9153016da8f1..2fe6b7fe6b12 100644
--- 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
index d9b8501bc93d..c124ef6a01b3 100644
--- a/arch/s390/include/asm/mmu_context.h
+++ b/arch/s390/include/asm/mmu_context.h
@@ -97,7 +97,7 @@ 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
index 78bbacc14d2d..d1967214ef25 100644
--- 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
index 96bda43538ee..4b55fa353bb5 100644
--- 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
index 9870d768db4c..d9de20c20f38 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -1624,7 +1624,7 @@ 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
index 0e1d73955fa5..e7787a6e7d22 100644
--- a/include/linux/sched/mm.h
+++ b/include/linux/sched/mm.h
@@ -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
@@ -71,14 +71,14 @@ 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);
 }
@@ -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);
@@ -531,7 +531,7 @@ 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
index ac76ae9fa36d..fce16aa10ba2 100644
--- 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
index 29dd5b91dd7d..428464bb81b3 100644
--- a/include/linux/vtime.h
+++ b/include/linux/vtime.h
@@ -67,24 +67,24 @@ 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 context_tracking_enabled_cpu(cpu);
 }
 
-static inline bool vtime_accounting_enabled_this_cpu(void)
+static __always_inline bool vtime_accounting_enabled_this_cpu(void)
 {
 	return context_tracking_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
index 0f9e9f54d0a8..e4ede8f7e0e3 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -4865,7 +4865,7 @@ 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
@@ -4881,7 +4881,7 @@ static inline void finish_task(struct task_struct *prev)
 	smp_store_release(&prev->on_cpu, 0);
 }
 
-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;
@@ -4916,7 +4916,7 @@ 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;
@@ -4946,7 +4946,7 @@ struct balance_callback *splice_balance_callbacks(struct rq *rq)
 	return __splice_balance_callbacks(rq, true);
 }
 
-static void __balance_callbacks(struct rq *rq)
+static __always_inline void __balance_callbacks(struct rq *rq)
 {
 	do_balance_callbacks(rq, __splice_balance_callbacks(rq, false));
 }
@@ -4979,7 +4979,7 @@ prepare_lock_switch(struct rq *rq, struct task_struct *next, struct rq_flags *rf
 #endif
 }
 
-static inline void finish_lock_switch(struct rq *rq)
+static __always_inline void finish_lock_switch(struct rq *rq)
 {
 	/*
 	 * If we are tracking spinlock dependencies then we have to
@@ -5011,7 +5011,7 @@ 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))
@@ -5064,7 +5064,7 @@ 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->lock)
 {
 	struct rq *rq = this_rq();
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index a60b238cb0f5..412ff6149570 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1381,12 +1381,12 @@ 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);
 }
@@ -1395,7 +1395,7 @@ 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;
@@ -1403,7 +1403,7 @@ 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)
 {
 	if (rq->core_enabled)
 		return &rq->core->__lock;
@@ -1497,12 +1497,12 @@ 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)
 {
 	return &rq->__lock;
 }
@@ -1552,23 +1552,23 @@ static inline void lockdep_assert_rq_held(struct rq *rq)
 extern void raw_spin_rq_lock_nested(struct rq *rq, int subclass);
 extern bool raw_spin_rq_trylock(struct rq *rq);
 
-static inline void raw_spin_rq_lock(struct rq *rq)
+static __always_inline void raw_spin_rq_lock(struct rq *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)
 {
 	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)
 {
 	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)
 {
 	raw_spin_rq_unlock(rq);
 	local_irq_enable();
-- 
2.51.0