sh: move fpu_counter into ARCH specific thread_struct

Only a couple of arches (sh/x86) use fpu_counter in task_struct so it can
be moved out into ARCH specific thread_struct, reducing the size of
task_struct for other arches.

Compile tested sh defconfig + sh4-linux-gcc (4.6.3)
Signed-off-by: Vineet Gupta <vgupta@synopsys.com>
Cc: Paul Mundt <paul.mundt@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

arch/sh/include/asm/fpu.h

@@ -46,7 +46,7 @@ static inline void __unlazy_fpu(struct task_struct *tsk, struct pt_regs *regs)
 		save_fpu(tsk);
 		release_fpu(regs);
 	} else
-		tsk->fpu_counter = 0;
+		tsk->thread.fpu_counter = 0;
 }
 
 static inline void unlazy_fpu(struct task_struct *tsk, struct pt_regs *regs)

arch/sh/include/asm/processor_32.h

@@ -111,6 +111,16 @@ struct thread_struct {
 
 	/* Extended processor state */
 	union thread_xstate *xstate;
+
+	/*
+	 * 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;
 };
 
 #define INIT_THREAD  {						\

arch/sh/include/asm/processor_64.h

@@ -126,6 +126,16 @@ struct thread_struct {
 
 	/* floating point info */
 	union thread_xstate *xstate;
+
+	/*
+	 * 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;
 };
 
 #define INIT_MMAP \

arch/sh/kernel/cpu/fpu.c

@@ -44,7 +44,7 @@ void __fpu_state_restore(void)
 	restore_fpu(tsk);
 
 	task_thread_info(tsk)->status |= TS_USEDFPU;
-	tsk->fpu_counter++;
+	tsk->thread.fpu_counter++;
 }
 
 void fpu_state_restore(struct pt_regs *regs)

arch/sh/kernel/process_32.c

@@ -156,7 +156,7 @@ int copy_thread(unsigned long clone_flags, unsigned long usp,
 #endif
 		ti->addr_limit = KERNEL_DS;
 		ti->status &= ~TS_USEDFPU;
-		p->fpu_counter = 0;
+		p->thread.fpu_counter = 0;
 		return 0;
 	}
 	*childregs = *current_pt_regs();
@@ -189,7 +189,7 @@ __switch_to(struct task_struct *prev, struct task_struct *next)
 	unlazy_fpu(prev, task_pt_regs(prev));
 
 	/* we're going to use this soon, after a few expensive things */
-	if (next->fpu_counter > 5)
+	if (next->thread.fpu_counter > 5)
 		prefetch(next_t->xstate);
 
 #ifdef CONFIG_MMU
@@ -207,7 +207,7 @@ __switch_to(struct task_struct *prev, struct task_struct *next)
 	 * restore of the math state immediately to avoid the trap; the
 	 * chances of needing FPU soon are obviously high now
 	 */
-	if (next->fpu_counter > 5)
+	if (next->thread.fpu_counter > 5)
 		__fpu_state_restore();
 
 	return prev;