ARM: vfp ptrace: no point flushing hw context for PTRACE_GETVFPREGS

If we're only reading the VFP context via the ptrace call, there's
no need to invalidate the hardware context - we only need to do that
on PTRACE_SETVFPREGS.  This allows more efficient monitoring of a
traced task.
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>

arch/arm/include/asm/thread_info.h

@@ -115,7 +115,8 @@ extern void iwmmxt_task_restore(struct thread_info *, void *);
 extern void iwmmxt_task_release(struct thread_info *);
 extern void iwmmxt_task_switch(struct thread_info *);
 
-extern void vfp_sync_state(struct thread_info *thread);
+extern void vfp_sync_hwstate(struct thread_info *);
+extern void vfp_flush_hwstate(struct thread_info *);
 
 #endif
 

arch/arm/kernel/ptrace.c

@@ -700,7 +700,7 @@ static int ptrace_getvfpregs(struct task_struct *tsk, void __user *data)
 	union vfp_state *vfp = &thread->vfpstate;
 	struct user_vfp __user *ufp = data;
 
-	vfp_sync_state(thread);
+	vfp_sync_hwstate(thread);
 
 	/* copy the floating point registers */
 	if (copy_to_user(&ufp->fpregs, &vfp->hard.fpregs,
@@ -723,7 +723,7 @@ static int ptrace_setvfpregs(struct task_struct *tsk, void __user *data)
 	union vfp_state *vfp = &thread->vfpstate;
 	struct user_vfp __user *ufp = data;
 
-	vfp_sync_state(thread);
+	vfp_sync_hwstate(thread);
 
 	/* copy the floating point registers */
 	if (copy_from_user(&vfp->hard.fpregs, &ufp->fpregs,
@@ -734,6 +734,8 @@ static int ptrace_setvfpregs(struct task_struct *tsk, void __user *data)
 	if (get_user(vfp->hard.fpscr, &ufp->fpscr))
 		return -EFAULT;
 
+	vfp_flush_hwstate(thread);
+
 	return 0;
 }
 #endif

arch/arm/vfp/vfpmodule.c

@@ -430,7 +430,11 @@ static inline void vfp_pm_init(void) { }
  * saved one. This function is used by the ptrace mechanism.
  */
 #ifdef CONFIG_SMP
-void vfp_sync_state(struct thread_info *thread)
+void vfp_sync_hwstate(struct thread_info *thread)
+{
+}
+
+void vfp_flush_hwstate(struct thread_info *thread)
 {
 	/*
 	 * On SMP systems, the VFP state is automatically saved at every
@@ -441,7 +445,7 @@ void vfp_sync_state(struct thread_info *thread)
 	thread->vfpstate.hard.cpu = NR_CPUS;
 }
 #else
-void vfp_sync_state(struct thread_info *thread)
+void vfp_sync_hwstate(struct thread_info *thread)
 {
 	unsigned int cpu = get_cpu();
 
@@ -457,6 +461,23 @@ void vfp_sync_state(struct thread_info *thread)
 		 */
 		fmxr(FPEXC, fpexc | FPEXC_EN);
 		vfp_save_state(&thread->vfpstate, fpexc | FPEXC_EN);
+		fmxr(FPEXC, fpexc);
+	}
+
+	put_cpu();
+}
+
+void vfp_flush_hwstate(struct thread_info *thread)
+{
+	unsigned int cpu = get_cpu();
+
+	/*
+	 * If the thread we're interested in is the current owner of the
+	 * hardware VFP state, then we need to save its state.
+	 */
+	if (last_VFP_context[cpu] == &thread->vfpstate) {
+		u32 fpexc = fmrx(FPEXC);
+
 		fmxr(FPEXC, fpexc & ~FPEXC_EN);
 
 		/*