x86/tlb: Move flush_tlb_others() out of line

cpu_tlbstate is exported because various TLB-related functions need
access to it, but cpu_tlbstate is sensitive information which should
only be accessed by well-contained kernel functions and not be directly
exposed to modules.

As a last step, move __flush_tlb_others() out of line and hide the
native function. The latter can be static when CONFIG_PARAVIRT is
disabled.

No functional change.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Borislav Petkov <bp@suse.de>
Reviewed-by: Alexandre Chartre <alexandre.chartre@oracle.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20200421092559.641957686@linutronix.de

arch/x86/include/asm/paravirt.h

@@ -50,6 +50,8 @@ static inline void slow_down_io(void)
 void native_flush_tlb_local(void);
 void native_flush_tlb_global(void);
 void native_flush_tlb_one_user(unsigned long addr);
+void native_flush_tlb_others(const struct cpumask *cpumask,
+			     const struct flush_tlb_info *info);
 
 static inline void __flush_tlb_local(void)
 {
@@ -66,8 +68,8 @@ static inline void __flush_tlb_one_user(unsigned long addr)
 	PVOP_VCALL1(mmu.flush_tlb_one_user, addr);
 }
 
-static inline void flush_tlb_others(const struct cpumask *cpumask,
-				    const struct flush_tlb_info *info)
+static inline void __flush_tlb_others(const struct cpumask *cpumask,
+				      const struct flush_tlb_info *info)
 {
 	PVOP_VCALL2(mmu.flush_tlb_others, cpumask, info);
 }

arch/x86/include/asm/tlbflush.h

@@ -140,10 +140,14 @@ static inline unsigned long build_cr3_noflush(pgd_t *pgd, u16 asid)
 	return __sme_pa(pgd) | kern_pcid(asid) | CR3_NOFLUSH;
 }
 
+struct flush_tlb_info;
+
 void flush_tlb_local(void);
 void flush_tlb_global(void);
 void flush_tlb_one_user(unsigned long addr);
 void flush_tlb_one_kernel(unsigned long addr);
+void flush_tlb_others(const struct cpumask *cpumask,
+		      const struct flush_tlb_info *info);
 
 #ifdef CONFIG_PARAVIRT
 #include <asm/paravirt.h>
@@ -418,9 +422,6 @@ static inline void flush_tlb_page(struct vm_area_struct *vma, unsigned long a)
 	flush_tlb_mm_range(vma->vm_mm, a, a + PAGE_SIZE, PAGE_SHIFT, false);
 }
 
-void native_flush_tlb_others(const struct cpumask *cpumask,
-			     const struct flush_tlb_info *info);
-
 static inline u64 inc_mm_tlb_gen(struct mm_struct *mm)
 {
 	/*
@@ -442,9 +443,6 @@ static inline void arch_tlbbatch_add_mm(struct arch_tlbflush_unmap_batch *batch,
 extern void arch_tlbbatch_flush(struct arch_tlbflush_unmap_batch *batch);
 
 #ifndef CONFIG_PARAVIRT
-#define flush_tlb_others(mask, info)	\
-	native_flush_tlb_others(mask, info)
-
 #define paravirt_tlb_remove_table(tlb, page) \
 	tlb_remove_page(tlb, (void *)(page))
 #endif

arch/x86/mm/tlb.c

@@ -25,6 +25,7 @@
 # define __flush_tlb_local		native_flush_tlb_local
 # define __flush_tlb_global		native_flush_tlb_global
 # define __flush_tlb_one_user(addr)	native_flush_tlb_one_user(addr)
+# define __flush_tlb_others(msk, info)	native_flush_tlb_others(msk, info)
 #endif
 
 /*
@@ -715,8 +716,8 @@ static bool tlb_is_not_lazy(int cpu, void *data)
 	return !per_cpu(cpu_tlbstate.is_lazy, cpu);
 }
 
-void native_flush_tlb_others(const struct cpumask *cpumask,
-			     const struct flush_tlb_info *info)
+STATIC_NOPV void native_flush_tlb_others(const struct cpumask *cpumask,
+					 const struct flush_tlb_info *info)
 {
 	count_vm_tlb_event(NR_TLB_REMOTE_FLUSH);
 	if (info->end == TLB_FLUSH_ALL)
@@ -766,6 +767,12 @@ void native_flush_tlb_others(const struct cpumask *cpumask,
 				(void *)info, 1, cpumask);
 }
 
+void flush_tlb_others(const struct cpumask *cpumask,
+		      const struct flush_tlb_info *info)
+{
+	__flush_tlb_others(cpumask, info);
+}
+
 /*
  * See Documentation/x86/tlb.rst for details.  We choose 33
  * because it is large enough to cover the vast majority (at