powerpc: Don't corrupt user registers on 32-bit

Commit de79f7b9f6 ("powerpc: Put FP/VSX and VR state into structures")
modified load_up_fpu() and load_up_altivec() in such a way that they
now use r7 and r8.  Unfortunately, the callers of these functions on
32-bit machines then return to userspace via fast_exception_return,
which doesn't restore all of the volatile GPRs, but only r1, r3 -- r6
and r9 -- r12.  This was causing userspace segfaults and other
userspace misbehaviour on 32-bit machines.

This fixes the problem by changing the register usage of load_up_fpu()
and load_up_altivec() to avoid using r7 and r8 and instead use r6 and
r10.  This also adds comments to those functions saying which registers
may be used.

Signed-off-by: Paul Mackerras <paulus@samba.org>
Tested-by: Scott Wood <scottwood@freescale.com> (on e500mc, so no altivec)
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>

arch/powerpc/kernel/fpu.S

@@ -106,6 +106,8 @@ _GLOBAL(store_fp_state)
  * and save its floating-point registers in its thread_struct.
  * Load up this task's FP registers from its thread_struct,
  * enable the FPU for the current task and return to the task.
+ * Note that on 32-bit this can only use registers that will be
+ * restored by fast_exception_return, i.e. r3 - r6, r10 and r11.
  */
 _GLOBAL(load_up_fpu)
 	mfmsr	r5
@@ -131,10 +133,10 @@ END_FTR_SECTION_IFSET(CPU_FTR_VSX)
 	beq	1f
 	toreal(r4)
 	addi	r4,r4,THREAD		/* want last_task_used_math->thread */
-	addi	r8,r4,THREAD_FPSTATE
-	SAVE_32FPVSRS(0, R5, R8)
+	addi	r10,r4,THREAD_FPSTATE
+	SAVE_32FPVSRS(0, R5, R10)
 	mffs	fr0
-	stfd	fr0,FPSTATE_FPSCR(r8)
+	stfd	fr0,FPSTATE_FPSCR(r10)
 	PPC_LL	r5,PT_REGS(r4)
 	toreal(r5)
 	PPC_LL	r4,_MSR-STACK_FRAME_OVERHEAD(r5)
@@ -157,10 +159,10 @@ END_FTR_SECTION_IFSET(CPU_FTR_VSX)
 	or	r12,r12,r4
 	std	r12,_MSR(r1)
 #endif
-	addi	r7,r5,THREAD_FPSTATE
-	lfd	fr0,FPSTATE_FPSCR(r7)
+	addi	r10,r5,THREAD_FPSTATE
+	lfd	fr0,FPSTATE_FPSCR(r10)
 	MTFSF_L(fr0)
-	REST_32FPVSRS(0, R4, R7)
+	REST_32FPVSRS(0, R4, R10)
 #ifndef CONFIG_SMP
 	subi	r4,r5,THREAD
 	fromreal(r4)

arch/powerpc/kernel/vector.S

@@ -64,6 +64,9 @@ _GLOBAL(store_vr_state)
  * Enables the VMX for use in the kernel on return.
  * On SMP we know the VMX is free, since we give it up every
  * switch (ie, no lazy save of the vector registers).
+ *
+ * Note that on 32-bit this can only use registers that will be
+ * restored by fast_exception_return, i.e. r3 - r6, r10 and r11.
  */
 _GLOBAL(load_up_altivec)
 	mfmsr	r5			/* grab the current MSR */
@@ -89,11 +92,11 @@ _GLOBAL(load_up_altivec)
 	/* Save VMX state to last_task_used_altivec's THREAD struct */
 	toreal(r4)
 	addi	r4,r4,THREAD
-	addi	r7,r4,THREAD_VRSTATE
-	SAVE_32VRS(0,r5,r7)
+	addi	r6,r4,THREAD_VRSTATE
+	SAVE_32VRS(0,r5,r6)
 	mfvscr	vr0
 	li	r10,VRSTATE_VSCR
-	stvx	vr0,r10,r7
+	stvx	vr0,r10,r6
 	/* Disable VMX for last_task_used_altivec */
 	PPC_LL	r5,PT_REGS(r4)
 	toreal(r5)
@@ -125,13 +128,13 @@ _GLOBAL(load_up_altivec)
 	oris	r12,r12,MSR_VEC@h
 	std	r12,_MSR(r1)
 #endif
-	addi	r7,r5,THREAD_VRSTATE
+	addi	r6,r5,THREAD_VRSTATE
 	li	r4,1
 	li	r10,VRSTATE_VSCR
 	stw	r4,THREAD_USED_VR(r5)
-	lvx	vr0,r10,r7
+	lvx	vr0,r10,r6
 	mtvscr	vr0
-	REST_32VRS(0,r4,r7)
+	REST_32VRS(0,r4,r6)
 #ifndef CONFIG_SMP
 	/* Update last_task_used_altivec to 'current' */
 	subi	r4,r5,THREAD		/* Back to 'current' */