ia64: Make fph-restore lazy. Patch by Asit K. Mallick.

arch/ia64/kernel/traps.c

@@ -248,10 +248,9 @@ disabled_fph_fault (struct pt_regs *regs)
 
 		if (fpu_owner)
 			ia64_flush_fph(fpu_owner);
-
-		ia64_set_fpu_owner(current);
 	}
 #endif /* !CONFIG_SMP */
+	ia64_set_fpu_owner(current);
 	if ((current->thread.flags & IA64_THREAD_FPH_VALID) != 0) {
 		__ia64_load_fpu(current->thread.fph);
 		psr->mfh = 0;

include/asm-ia64/processor.h

@@ -223,6 +223,7 @@ struct thread_struct {
 	__u64 map_base;			/* base address for get_unmapped_area() */
 	__u64 task_size;		/* limit for task size */
 	struct siginfo *siginfo;	/* current siginfo struct for ptrace() */
+	__u64 last_fph_cpu;		/* CPU that may hold the contents of f32-f127 */
 
 #ifdef CONFIG_IA32_SUPPORT
 	__u64 eflag;			/* IA32 EFLAGS reg */
@@ -389,8 +390,6 @@ ia64_set_kr (unsigned long regnum, unsigned long r)
 	}
 }
 
-#ifndef CONFIG_SMP
-
 static inline struct task_struct *
 ia64_get_fpu_owner (void)
 {
@@ -403,8 +402,6 @@ ia64_set_fpu_owner (struct task_struct *t)
 	ia64_set_kr(IA64_KR_FPU_OWNER, (unsigned long) t);
 }
 
-#endif /* !CONFIG_SMP */
-
 extern void __ia64_init_fpu (void);
 extern void __ia64_save_fpu (struct ia64_fpreg *fph);
 extern void __ia64_load_fpu (struct ia64_fpreg *fph);

include/asm-ia64/system.h

@@ -396,14 +396,23 @@ extern void ia64_load_extra (struct task_struct *task);
  * task->thread.fph, avoiding the complication of having to fetch
  * the latest fph state from another CPU.
  */
-# define switch_to(prev,next,last) do {						\
-	if (ia64_psr(ia64_task_regs(prev))->mfh) {				\
-		ia64_psr(ia64_task_regs(prev))->mfh = 0;			\
-		(prev)->thread.flags |= IA64_THREAD_FPH_VALID;			\
-		__ia64_save_fpu((prev)->thread.fph);				\
-	}									\
-	ia64_psr(ia64_task_regs(prev))->dfh = 1;				\
-	__switch_to(prev,next,last);						\
+# define switch_to(prev,next,last) do {					\
+	if (ia64_psr(ia64_task_regs(prev))->mfh) {			\
+		ia64_psr(ia64_task_regs(prev))->mfh = 0;		\
+		(prev)->thread.flags |= IA64_THREAD_FPH_VALID;		\
+		__ia64_save_fpu((prev)->thread.fph);			\
+		(prev)->thread.last_fph_cpu = smp_processor_id();	\
+	}								\
+	if ((next)->thread.flags & IA64_THREAD_FPH_VALID) {		\
+		if (((next)->thread.last_fph_cpu == smp_processor_id())	\
+		    && (ia64_get_fpu_owner() == next))			\
+		{							\
+			ia64_psr(ia64_task_regs(next))->dfh = 0;	\
+			ia64_psr(ia64_task_regs(next))->mfh = 0;	\
+		} else						\
+			ia64_psr(ia64_task_regs(next))->dfh = 1;	\
+	}								\
+	__switch_to(prev,next,last);					\
   } while (0)
 #else
 # define switch_to(prev,next,last) do {						\