powerpc: Add the ability to save FPU without giving it up

This patch adds the ability to be able to save the FPU registers to the
thread struct without giving up (disabling the facility) next time the
process returns to userspace.

This patch optimises the thread copy path (as a result of a fork() or
clone()) so that the parent thread can return to userspace with hot
registers avoiding a possibly pointless reload of FPU register state.
Signed-off-by: Cyril Bur <cyrilbur@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>

arch/powerpc/include/asm/switch_to.h

@@ -28,13 +28,14 @@ extern void giveup_all(struct task_struct *);
 extern void enable_kernel_fp(void);
 extern void flush_fp_to_thread(struct task_struct *);
 extern void giveup_fpu(struct task_struct *);
-extern void __giveup_fpu(struct task_struct *);
+extern void save_fpu(struct task_struct *);
 static inline void disable_kernel_fp(void)
 {
 	msr_check_and_clear(MSR_FP);
 }
 #else
 static inline void __giveup_fpu(struct task_struct *t) { }
+static inline void save_fpu(struct task_struct *t) { }
 static inline void flush_fp_to_thread(struct task_struct *t) { }
 #endif
 

arch/powerpc/kernel/fpu.S

@@ -143,33 +143,20 @@ END_FTR_SECTION_IFSET(CPU_FTR_VSX)
 	blr
 
 /*
- * __giveup_fpu(tsk)
- * Disable FP for the task given as the argument,
- * and save the floating-point registers in its thread_struct.
+ * save_fpu(tsk)
+ * Save the floating-point registers in its thread_struct.
  * Enables the FPU for use in the kernel on return.
  */
-_GLOBAL(__giveup_fpu)
+_GLOBAL(save_fpu)
 	addi	r3,r3,THREAD	        /* want THREAD of task */
 	PPC_LL	r6,THREAD_FPSAVEAREA(r3)
 	PPC_LL	r5,PT_REGS(r3)
 	PPC_LCMPI	0,r6,0
 	bne	2f
 	addi	r6,r3,THREAD_FPSTATE
-2:	PPC_LCMPI	0,r5,0
-	SAVE_32FPVSRS(0, R4, R6)
+2:	SAVE_32FPVSRS(0, R4, R6)
 	mffs	fr0
 	stfd	fr0,FPSTATE_FPSCR(r6)
-	beq	1f
-	PPC_LL	r4,_MSR-STACK_FRAME_OVERHEAD(r5)
-	li	r3,MSR_FP|MSR_FE0|MSR_FE1
-#ifdef CONFIG_VSX
-BEGIN_FTR_SECTION
-	oris	r3,r3,MSR_VSX@h
-END_FTR_SECTION_IFSET(CPU_FTR_VSX)
-#endif
-	andc	r4,r4,r3		/* disable FP for previous task */
-	PPC_STL	r4,_MSR-STACK_FRAME_OVERHEAD(r5)
-1:
 	blr
 
 /*

arch/powerpc/kernel/process.c

@@ -133,6 +133,16 @@ void __msr_check_and_clear(unsigned long bits)
 EXPORT_SYMBOL(__msr_check_and_clear);
 
 #ifdef CONFIG_PPC_FPU
+void __giveup_fpu(struct task_struct *tsk)
+{
+	save_fpu(tsk);
+	tsk->thread.regs->msr &= ~MSR_FP;
+#ifdef CONFIG_VSX
+	if (cpu_has_feature(CPU_FTR_VSX))
+		tsk->thread.regs->msr &= ~MSR_VSX;
+#endif
+}
+
 void giveup_fpu(struct task_struct *tsk)
 {
 	check_if_tm_restore_required(tsk);
@@ -459,7 +469,7 @@ void save_all(struct task_struct *tsk)
 	msr_check_and_set(msr_all_available);
 
 	if (usermsr & MSR_FP)
-		__giveup_fpu(tsk);
+		save_fpu(tsk);
 
 	if (usermsr & MSR_VEC)
 		__giveup_altivec(tsk);