x86/fpu: Move thread_info::fpu_counter into thread_info::fpu.counter

This field is kept separate from the main FPU state structure for
no good reason.

Reviewed-by: Borislav Petkov <bp@alien8.de>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Fenghua Yu <fenghua.yu@intel.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Ingo Molnar <mingo@kernel.org>

arch/x86/include/asm/fpu-internal.h

@@ -384,7 +384,7 @@ static inline void drop_fpu(struct task_struct *tsk)
 	 * Forget coprocessor state..
 	 */
 	preempt_disable();
-	tsk->thread.fpu_counter = 0;
+	tsk->thread.fpu.counter = 0;
 
 	if (__thread_has_fpu(tsk)) {
 		/* Ignore delayed exceptions from user space */
@@ -441,7 +441,7 @@ static inline fpu_switch_t switch_fpu_prepare(struct task_struct *old, struct ta
 	 * or if the past 5 consecutive context-switches used math.
 	 */
 	fpu.preload = tsk_used_math(new) &&
-		      (use_eager_fpu() || new->thread.fpu_counter > 5);
+		      (use_eager_fpu() || new->thread.fpu.counter > 5);
 
 	if (__thread_has_fpu(old)) {
 		if (!__save_init_fpu(old))
@@ -454,16 +454,16 @@ static inline fpu_switch_t switch_fpu_prepare(struct task_struct *old, struct ta
 
 		/* Don't change CR0.TS if we just switch! */
 		if (fpu.preload) {
-			new->thread.fpu_counter++;
+			new->thread.fpu.counter++;
 			__thread_set_has_fpu(new);
 			prefetch(new->thread.fpu.state);
 		} else if (!use_eager_fpu())
 			stts();
 	} else {
-		old->thread.fpu_counter = 0;
+		old->thread.fpu.counter = 0;
 		task_disable_lazy_fpu_restore(old);
 		if (fpu.preload) {
-			new->thread.fpu_counter++;
+			new->thread.fpu.counter++;
 			if (fpu_lazy_restore(new, cpu))
 				fpu.preload = 0;
 			else

arch/x86/include/asm/processor.h

@@ -433,6 +433,15 @@ struct fpu {
 	unsigned int last_cpu;
 	unsigned int has_fpu;
 	union thread_xstate *state;
+	/*
+	 * This counter contains the number of consecutive context switches
+	 * that the FPU is used. If this is over a threshold, the lazy fpu
+	 * saving becomes unlazy to save the trap. This is an unsigned char
+	 * so that after 256 times the counter wraps and the behavior turns
+	 * lazy again; this to deal with bursty apps that only use FPU for
+	 * a short time
+	 */
+	unsigned char counter;
 };
 
 #ifdef CONFIG_X86_64
@@ -535,15 +544,6 @@ struct thread_struct {
 	unsigned long		iopl;
 	/* Max allowed port in the bitmap, in bytes: */
 	unsigned		io_bitmap_max;
-	/*
-	 * fpu_counter contains the number of consecutive context switches
-	 * that the FPU is used. If this is over a threshold, the lazy fpu
-	 * saving becomes unlazy to save the trap. This is an unsigned char
-	 * so that after 256 times the counter wraps and the behavior turns
-	 * lazy again; this to deal with bursty apps that only use FPU for
-	 * a short time
-	 */
-	unsigned char fpu_counter;
 };
 
 /*

arch/x86/kernel/process.c

@@ -87,7 +87,7 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
 {
 	*dst = *src;
 
-	dst->thread.fpu_counter = 0;
+	dst->thread.fpu.counter = 0;
 	dst->thread.fpu.has_fpu = 0;
 	dst->thread.fpu.state = NULL;
 	task_disable_lazy_fpu_restore(dst);

arch/x86/kernel/traps.c

@@ -863,7 +863,7 @@ void math_state_restore(void)
 		fpu_reset_state(tsk);
 		force_sig_info(SIGSEGV, SEND_SIG_PRIV, tsk);
 	} else {
-		tsk->thread.fpu_counter++;
+		tsk->thread.fpu.counter++;
 	}
 	kernel_fpu_enable();
 }