x86/process: Optimize TIF checks in __switch_to_xtra()

commit af8b3cd3 upstream

Help the compiler to avoid reevaluating the thread flags for each checked
bit by reordering the bit checks and providing an explicit xor for
evaluation.

With default defconfigs for each arch,

x86_64: arch/x86/kernel/process.o
text       data     bss     dec     hex
3056       8577      16   11649    2d81	Before
3024	   8577      16	  11617	   2d61	After

i386: arch/x86/kernel/process.o
text       data     bss     dec     hex
2957	   8673	      8	  11638	   2d76	Before
2925	   8673       8	  11606	   2d56	After
Originally-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Kyle Huey <khuey@kylehuey.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Andy Lutomirski <luto@kernel.org>
Link: http://lkml.kernel.org/r/20170214081104.9244-2-khuey@kylehuey.comSigned-off-by: Thomas Gleixner <tglx@linutronix.de>

[dwmw2: backported to make TIF_RDS handling simpler.
        No deferred TR reload.]
Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

arch/x86/kernel/process.c

@@ -192,48 +192,56 @@ int set_tsc_mode(unsigned int val)
 	return 0;
 }
 
+static inline void switch_to_bitmap(struct tss_struct *tss,
+				    struct thread_struct *prev,
+				    struct thread_struct *next,
+				    unsigned long tifp, unsigned long tifn)
+{
+	if (tifn & _TIF_IO_BITMAP) {
+		/*
+		 * Copy the relevant range of the IO bitmap.
+		 * Normally this is 128 bytes or less:
+		 */
+		memcpy(tss->io_bitmap, next->io_bitmap_ptr,
+		       max(prev->io_bitmap_max, next->io_bitmap_max));
+	} else if (tifp & _TIF_IO_BITMAP) {
+		/*
+		 * Clear any possible leftover bits:
+		 */
+		memset(tss->io_bitmap, 0xff, prev->io_bitmap_max);
+	}
+}
+
 void __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p,
 		      struct tss_struct *tss)
 {
 	struct thread_struct *prev, *next;
+	unsigned long tifp, tifn;
 
 	prev = &prev_p->thread;
 	next = &next_p->thread;
 
-	if (test_tsk_thread_flag(prev_p, TIF_BLOCKSTEP) ^
-	    test_tsk_thread_flag(next_p, TIF_BLOCKSTEP)) {
+	tifn = READ_ONCE(task_thread_info(next_p)->flags);
+	tifp = READ_ONCE(task_thread_info(prev_p)->flags);
+	switch_to_bitmap(tss, prev, next, tifp, tifn);
+
+	propagate_user_return_notify(prev_p, next_p);
+
+	if ((tifp ^ tifn) & _TIF_BLOCKSTEP) {
 		unsigned long debugctl = get_debugctlmsr();
 
 		debugctl &= ~DEBUGCTLMSR_BTF;
-		if (test_tsk_thread_flag(next_p, TIF_BLOCKSTEP))
+		if (tifn & _TIF_BLOCKSTEP)
 			debugctl |= DEBUGCTLMSR_BTF;
-
 		update_debugctlmsr(debugctl);
 	}
 
-	if (test_tsk_thread_flag(prev_p, TIF_NOTSC) ^
-	    test_tsk_thread_flag(next_p, TIF_NOTSC)) {
-		/* prev and next are different */
-		if (test_tsk_thread_flag(next_p, TIF_NOTSC))
+	if ((tifp ^ tifn) & _TIF_NOTSC) {
+		if (tifn & _TIF_NOTSC)
 			hard_disable_TSC();
 		else
 			hard_enable_TSC();
 	}
-
-	if (test_tsk_thread_flag(next_p, TIF_IO_BITMAP)) {
-		/*
-		 * Copy the relevant range of the IO bitmap.
-		 * Normally this is 128 bytes or less:
-		 */
-		memcpy(tss->io_bitmap, next->io_bitmap_ptr,
-		       max(prev->io_bitmap_max, next->io_bitmap_max));
-	} else if (test_tsk_thread_flag(prev_p, TIF_IO_BITMAP)) {
-		/*
-		 * Clear any possible leftover bits:
-		 */
-		memset(tss->io_bitmap, 0xff, prev->io_bitmap_max);
-	}
-	propagate_user_return_notify(prev_p, next_p);
 }
 
 /*