x86/process: Optimize TIF_NOTSC switch

Provide and use a toggle helper instead of doing it with a branch.

x86_64: arch/x86/kernel/process.o
text	   data	    bss	    dec	    hex
3008	   8577	     16	  11601	   2d51 Before
2976       8577      16	  11569	   2d31 After

i386: arch/x86/kernel/process.o
text	   data	    bss	    dec	    hex
2925	   8673	      8	  11606	   2d56 Before
2893	   8673       8	  11574	   2d36 After

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Andy Lutomirski <luto@kernel.org>
Link: http://lkml.kernel.org/r/20170214081104.9244-4-khuey@kylehuey.com
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h
index 6fa8594..ff4923a 100644
--- a/arch/x86/include/asm/tlbflush.h
+++ b/arch/x86/include/asm/tlbflush.h
@@ -110,6 +110,16 @@ static inline void cr4_clear_bits(unsigned long mask)
 	}
 }
 
+static inline void cr4_toggle_bits(unsigned long mask)
+{
+	unsigned long cr4;
+
+	cr4 = this_cpu_read(cpu_tlbstate.cr4);
+	cr4 ^= mask;
+	this_cpu_write(cpu_tlbstate.cr4, cr4);
+	__write_cr4(cr4);
+}
+
 /* Read the CR4 shadow. */
 static inline unsigned long cr4_read_shadow(void)
 {