x86/tlb: Move __flush_tlb_global() 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 second step, move __flush_tlb_global() out of line and hide the
native function. The latter can be static when CONFIG_PARAVIRT is
disabled.

Consolidate the namespace while at it and remove the pointless extra
wrapper in the paravirt code.

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/20200421092559.336916818@linutronix.de

4 files changed, 44 insertions, 45 deletions

diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index f412450668d8..712e059bc7c6 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -48,6 +48,7 @@ static inline void slow_down_io(void)
 }
 
 void native_flush_tlb_local(void);
+void native_flush_tlb_global(void);
 
 static inline void __flush_tlb_local(void)
 {
diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h
index fe1fd02904ba..d66d16e3fd67 100644
--- a/arch/x86/include/asm/tlbflush.h
+++ b/arch/x86/include/asm/tlbflush.h
@@ -141,11 +141,11 @@ static inline unsigned long build_cr3_noflush(pgd_t *pgd, u16 asid)
 }
 
 void flush_tlb_local(void);
+void flush_tlb_global(void);
 
 #ifdef CONFIG_PARAVIRT
 #include <asm/paravirt.h>
 #else
-#define __flush_tlb_global()		__native_flush_tlb_global()
 #define __flush_tlb_one_user(addr)	__native_flush_tlb_one_user(addr)
 #endif
 
@@ -372,40 +372,6 @@ static inline void invalidate_user_asid(u16 asid)
 }
 
 /*
- * flush everything
- */
-static inline void __native_flush_tlb_global(void)
-{
-	unsigned long cr4, flags;
-
-	if (static_cpu_has(X86_FEATURE_INVPCID)) {
-		/*
-		 * Using INVPCID is considerably faster than a pair of writes
-		 * to CR4 sandwiched inside an IRQ flag save/restore.
-		 *
-		 * Note, this works with CR4.PCIDE=0 or 1.
-		 */
-		invpcid_flush_all();
-		return;
-	}
-
-	/*
-	 * Read-modify-write to CR4 - protect it from preemption and
-	 * from interrupts. (Use the raw variant because this code can
-	 * be called from deep inside debugging code.)
-	 */
-	raw_local_irq_save(flags);
-
-	cr4 = this_cpu_read(cpu_tlbstate.cr4);
-	/* toggle PGE */
-	native_write_cr4(cr4 ^ X86_CR4_PGE);
-	/* write old PGE again and flush TLBs */
-	native_write_cr4(cr4);
-
-	raw_local_irq_restore(flags);
-}
-
-/*
  * flush one page in the user mapping
  */
 static inline void __native_flush_tlb_one_user(unsigned long addr)
@@ -439,7 +405,7 @@ static inline void __flush_tlb_all(void)
 	VM_WARN_ON_ONCE(preemptible());
 
 	if (boot_cpu_has(X86_FEATURE_PGE)) {
-		__flush_tlb_global();
+		flush_tlb_global();
 	} else {
 		/*
 		 * !PGE -> !PCID (setup_pcid()), thus every flush is total.
diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c
index 4cb3d822ea09..6094b007979c 100644
--- a/arch/x86/kernel/paravirt.c
+++ b/arch/x86/kernel/paravirt.c
@@ -160,15 +160,6 @@ unsigned paravirt_patch_insns(void *insn_buff, unsigned len,
 	return insn_len;
 }
 
-/*
- * Global pages have to be flushed a bit differently. Not a real
- * performance problem because this does not happen often.
- */
-static void native_flush_tlb_global(void)
-{
-	__native_flush_tlb_global();
-}
-
 static void native_flush_tlb_one_user(unsigned long addr)
 {
 	__native_flush_tlb_one_user(addr);
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index 06116480c343..d548b98e5a49 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -23,6 +23,7 @@
 #else
 # define STATIC_NOPV			static
 # define __flush_tlb_local		native_flush_tlb_local
+# define __flush_tlb_global		native_flush_tlb_global
 #endif
 
 /*
@@ -891,6 +892,46 @@ unsigned long __get_current_cr3_fast(void)
 EXPORT_SYMBOL_GPL(__get_current_cr3_fast);
 
 /*
+ * Flush everything
+ */
+STATIC_NOPV void native_flush_tlb_global(void)
+{
+	unsigned long cr4, flags;
+
+	if (static_cpu_has(X86_FEATURE_INVPCID)) {
+		/*
+		 * Using INVPCID is considerably faster than a pair of writes
+		 * to CR4 sandwiched inside an IRQ flag save/restore.
+		 *
+		 * Note, this works with CR4.PCIDE=0 or 1.
+		 */
+		invpcid_flush_all();
+		return;
+	}
+
+	/*
+	 * Read-modify-write to CR4 - protect it from preemption and
+	 * from interrupts. (Use the raw variant because this code can
+	 * be called from deep inside debugging code.)
+	 */
+	raw_local_irq_save(flags);
+
+	cr4 = this_cpu_read(cpu_tlbstate.cr4);
+	/* toggle PGE */
+	native_write_cr4(cr4 ^ X86_CR4_PGE);
+	/* write old PGE again and flush TLBs */
+	native_write_cr4(cr4);
+
+	raw_local_irq_restore(flags);
+}
+
+void flush_tlb_global(void)
+{
+	__flush_tlb_global();
+}
+EXPORT_SYMBOL_GPL(flush_tlb_global);
+
+/*
  * Flush the entire current user mapping
  */
 STATIC_NOPV void native_flush_tlb_local(void)