[PATCH v8 1/3] x86/mm/tlb: Make enter_lazy_tlb() always inline on x86

[Xie Yuanbin <qq570070308@gmail.com>]

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.

Cc: Thomas Gleixner <tglx@kernel.org>
Cc: Rik van Riel <riel@surriel.com>
Cc: David Hildenbrand (Arm) <david@kernel.org>
Cc: Dave Hansen <dave.hansen@intel.com>
Suggested-by: Dave Hansen <dave.hansen@intel.com>
Signed-off-by: Xie Yuanbin <qq570070308@gmail.com>
---
 arch/x86/include/asm/mmu_context.h |  3 ---
 arch/x86/include/asm/tlbflush.h    | 26 ++++++++++++++++++++++++++
 arch/x86/mm/tlb.c                  | 21 ---------------------
 3 files changed, 26 insertions(+), 24 deletions(-)

diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h
index 1acafb1c6a93..ef5b507de34e 100644
--- a/arch/x86/include/asm/mmu_context.h
+++ b/arch/x86/include/asm/mmu_context.h
@@ -136,9 +136,6 @@ static inline void mm_reset_untag_mask(struct mm_struct *mm)
 }
 #endif
 
-#define enter_lazy_tlb enter_lazy_tlb
-extern void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk);
-
 extern void mm_init_global_asid(struct mm_struct *mm);
 extern void mm_free_global_asid(struct mm_struct *mm);
 
diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h
index 5a3cdc439e38..0545fe75c3fa 100644
--- a/arch/x86/include/asm/tlbflush.h
+++ b/arch/x86/include/asm/tlbflush.h
@@ -172,6 +172,28 @@ struct tlb_state_shared {
 };
 DECLARE_PER_CPU_SHARED_ALIGNED(struct tlb_state_shared, cpu_tlbstate_shared);
 
+/*
+ * 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
+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);
+}
+
 bool nmi_uaccess_okay(void);
 #define nmi_uaccess_okay nmi_uaccess_okay
 
@@ -480,6 +502,10 @@ static inline void cpu_tlbstate_update_lam(unsigned long lam, u64 untag_mask)
 {
 }
 #endif
+#else /* !MODULE */
+#define enter_lazy_tlb enter_lazy_tlb
+extern void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk)
+	__compiletime_error("enter_lazy_tlb() should not be used in modules");
 #endif /* !MODULE */
 
 static inline void __native_tlb_flush_global(unsigned long cr4)
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index 621e09d049cb..af43d177087e 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