[patch 1/3] x86/process: Optimize TIF checks in switch_to_extra()

[Thomas Gleixner]

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.

x8664: arch/x86/kernel/process.o
text	   data	    bss	    dec	    hex
3726	   8505	     16	  12247	   2fd7	Before
3694	   8505	     16	  12215	   2fb7	After

i386:  No change

Originally-from: Kyle Huey <khuey@xxxxxxxxxxxx>
Signed-off-by: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
---
 arch/x86/kernel/process.c |   54 ++++++++++++++++++++++++++--------------------
 1 file changed, 31 insertions(+), 23 deletions(-)

--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -174,48 +174,56 @@ 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 = task_thread_info(next_p)->flags;
+	tifp = 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);
 }
 
 /*