powerpc: Put FP/VSX and VR state into structures

This creates new 'thread_fp_state' and 'thread_vr_state' structures
to store FP/VSX state (including FPSCR) and Altivec/VSX state
(including VSCR), and uses them in the thread_struct.  In the
thread_fp_state, the FPRs and VSRs are represented as u64 rather
than double, since we rarely perform floating-point computations
on the values, and this will enable the structures to be used
in KVM code as well.  Similarly FPSCR is now a u64 rather than
a structure of two 32-bit values.

This takes the offsets out of the macros such as SAVE_32FPRS,
REST_32FPRS, etc.  This enables the same macros to be used for normal
and transactional state, enabling us to delete the transactional
versions of the macros.   This also removes the unused do_load_up_fpu
and do_load_up_altivec, which were in fact buggy since they didn't
create large enough stack frames to account for the fact that
load_up_fpu and load_up_altivec are not designed to be called from C
and assume that their caller's stack frame is an interrupt frame.

Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>

17 files changed, 200 insertions, 358 deletions

diff --git a/arch/powerpc/include/asm/ppc_asm.h b/arch/powerpc/include/asm/ppc_asm.h
index 599545738af..140f67090f0 100644
--- a/arch/powerpc/include/asm/ppc_asm.h
+++ b/arch/powerpc/include/asm/ppc_asm.h
@@ -98,123 +98,40 @@ END_FW_FTR_SECTION_IFSET(FW_FEATURE_SPLPAR)
 #define REST_8GPRS(n, base)	REST_4GPRS(n, base); REST_4GPRS(n+4, base)
 #define REST_10GPRS(n, base)	REST_8GPRS(n, base); REST_2GPRS(n+8, base)
 
-#define SAVE_FPR(n, base)	stfd	n,THREAD_FPR0+8*TS_FPRWIDTH*(n)(base)
+#define SAVE_FPR(n, base)	stfd	n,8*TS_FPRWIDTH*(n)(base)
 #define SAVE_2FPRS(n, base)	SAVE_FPR(n, base); SAVE_FPR(n+1, base)
 #define SAVE_4FPRS(n, base)	SAVE_2FPRS(n, base); SAVE_2FPRS(n+2, base)
 #define SAVE_8FPRS(n, base)	SAVE_4FPRS(n, base); SAVE_4FPRS(n+4, base)
 #define SAVE_16FPRS(n, base)	SAVE_8FPRS(n, base); SAVE_8FPRS(n+8, base)
 #define SAVE_32FPRS(n, base)	SAVE_16FPRS(n, base); SAVE_16FPRS(n+16, base)
-#define REST_FPR(n, base)	lfd	n,THREAD_FPR0+8*TS_FPRWIDTH*(n)(base)
+#define REST_FPR(n, base)	lfd	n,8*TS_FPRWIDTH*(n)(base)
 #define REST_2FPRS(n, base)	REST_FPR(n, base); REST_FPR(n+1, base)
 #define REST_4FPRS(n, base)	REST_2FPRS(n, base); REST_2FPRS(n+2, base)
 #define REST_8FPRS(n, base)	REST_4FPRS(n, base); REST_4FPRS(n+4, base)
 #define REST_16FPRS(n, base)	REST_8FPRS(n, base); REST_8FPRS(n+8, base)
 #define REST_32FPRS(n, base)	REST_16FPRS(n, base); REST_16FPRS(n+16, base)
 
-#define SAVE_VR(n,b,base)	li b,THREAD_VR0+(16*(n));  stvx n,base,b
+#define SAVE_VR(n,b,base)	li b,16*(n);  stvx n,base,b
 #define SAVE_2VRS(n,b,base)	SAVE_VR(n,b,base); SAVE_VR(n+1,b,base)
 #define SAVE_4VRS(n,b,base)	SAVE_2VRS(n,b,base); SAVE_2VRS(n+2,b,base)
 #define SAVE_8VRS(n,b,base)	SAVE_4VRS(n,b,base); SAVE_4VRS(n+4,b,base)
 #define SAVE_16VRS(n,b,base)	SAVE_8VRS(n,b,base); SAVE_8VRS(n+8,b,base)
 #define SAVE_32VRS(n,b,base)	SAVE_16VRS(n,b,base); SAVE_16VRS(n+16,b,base)
-#define REST_VR(n,b,base)	li b,THREAD_VR0+(16*(n)); lvx n,base,b
+#define REST_VR(n,b,base)	li b,16*(n); lvx n,base,b
 #define REST_2VRS(n,b,base)	REST_VR(n,b,base); REST_VR(n+1,b,base)
 #define REST_4VRS(n,b,base)	REST_2VRS(n,b,base); REST_2VRS(n+2,b,base)
 #define REST_8VRS(n,b,base)	REST_4VRS(n,b,base); REST_4VRS(n+4,b,base)
 #define REST_16VRS(n,b,base)	REST_8VRS(n,b,base); REST_8VRS(n+8,b,base)
 #define REST_32VRS(n,b,base)	REST_16VRS(n,b,base); REST_16VRS(n+16,b,base)
 
-/* Save/restore FPRs, VRs and VSRs from their checkpointed backups in
- * thread_struct:
- */
-#define SAVE_FPR_TRANSACT(n, base)	stfd n,THREAD_TRANSACT_FPR0+	\
-					8*TS_FPRWIDTH*(n)(base)
-#define SAVE_2FPRS_TRANSACT(n, base)	SAVE_FPR_TRANSACT(n, base);	\
-					SAVE_FPR_TRANSACT(n+1, base)
-#define SAVE_4FPRS_TRANSACT(n, base)	SAVE_2FPRS_TRANSACT(n, base);	\
-					SAVE_2FPRS_TRANSACT(n+2, base)
-#define SAVE_8FPRS_TRANSACT(n, base)	SAVE_4FPRS_TRANSACT(n, base);	\
-					SAVE_4FPRS_TRANSACT(n+4, base)
-#define SAVE_16FPRS_TRANSACT(n, base)	SAVE_8FPRS_TRANSACT(n, base);	\
-					SAVE_8FPRS_TRANSACT(n+8, base)
-#define SAVE_32FPRS_TRANSACT(n, base)	SAVE_16FPRS_TRANSACT(n, base);	\
-					SAVE_16FPRS_TRANSACT(n+16, base)
-
-#define REST_FPR_TRANSACT(n, base)	lfd	n,THREAD_TRANSACT_FPR0+	\
-					8*TS_FPRWIDTH*(n)(base)
-#define REST_2FPRS_TRANSACT(n, base)	REST_FPR_TRANSACT(n, base);	\
-					REST_FPR_TRANSACT(n+1, base)
-#define REST_4FPRS_TRANSACT(n, base)	REST_2FPRS_TRANSACT(n, base);	\
-					REST_2FPRS_TRANSACT(n+2, base)
-#define REST_8FPRS_TRANSACT(n, base)	REST_4FPRS_TRANSACT(n, base);	\
-					REST_4FPRS_TRANSACT(n+4, base)
-#define REST_16FPRS_TRANSACT(n, base)	REST_8FPRS_TRANSACT(n, base);	\
-					REST_8FPRS_TRANSACT(n+8, base)
-#define REST_32FPRS_TRANSACT(n, base)	REST_16FPRS_TRANSACT(n, base);	\
-					REST_16FPRS_TRANSACT(n+16, base)
-
-
-#define SAVE_VR_TRANSACT(n,b,base)	li b,THREAD_TRANSACT_VR0+(16*(n)); \
-					stvx n,b,base
-#define SAVE_2VRS_TRANSACT(n,b,base)	SAVE_VR_TRANSACT(n,b,base);	\
-					SAVE_VR_TRANSACT(n+1,b,base)
-#define SAVE_4VRS_TRANSACT(n,b,base)	SAVE_2VRS_TRANSACT(n,b,base);	\
-					SAVE_2VRS_TRANSACT(n+2,b,base)
-#define SAVE_8VRS_TRANSACT(n,b,base)	SAVE_4VRS_TRANSACT(n,b,base);	\
-					SAVE_4VRS_TRANSACT(n+4,b,base)
-#define SAVE_16VRS_TRANSACT(n,b,base)	SAVE_8VRS_TRANSACT(n,b,base);	\
-					SAVE_8VRS_TRANSACT(n+8,b,base)
-#define SAVE_32VRS_TRANSACT(n,b,base)	SAVE_16VRS_TRANSACT(n,b,base);	\
-					SAVE_16VRS_TRANSACT(n+16,b,base)
-
-#define REST_VR_TRANSACT(n,b,base)	li b,THREAD_TRANSACT_VR0+(16*(n)); \
-					lvx n,b,base
-#define REST_2VRS_TRANSACT(n,b,base)	REST_VR_TRANSACT(n,b,base);	\
-					REST_VR_TRANSACT(n+1,b,base)
-#define REST_4VRS_TRANSACT(n,b,base)	REST_2VRS_TRANSACT(n,b,base);	\
-					REST_2VRS_TRANSACT(n+2,b,base)
-#define REST_8VRS_TRANSACT(n,b,base)	REST_4VRS_TRANSACT(n,b,base);	\
-					REST_4VRS_TRANSACT(n+4,b,base)
-#define REST_16VRS_TRANSACT(n,b,base)	REST_8VRS_TRANSACT(n,b,base);	\
-					REST_8VRS_TRANSACT(n+8,b,base)
-#define REST_32VRS_TRANSACT(n,b,base)	REST_16VRS_TRANSACT(n,b,base);	\
-					REST_16VRS_TRANSACT(n+16,b,base)
-
-
-#define SAVE_VSR_TRANSACT(n,b,base)	li b,THREAD_TRANSACT_VSR0+(16*(n)); \
-					STXVD2X(n,R##base,R##b)
-#define SAVE_2VSRS_TRANSACT(n,b,base)	SAVE_VSR_TRANSACT(n,b,base);	\
-	                                SAVE_VSR_TRANSACT(n+1,b,base)
-#define SAVE_4VSRS_TRANSACT(n,b,base)	SAVE_2VSRS_TRANSACT(n,b,base);	\
-	                                SAVE_2VSRS_TRANSACT(n+2,b,base)
-#define SAVE_8VSRS_TRANSACT(n,b,base)	SAVE_4VSRS_TRANSACT(n,b,base);	\
-	                                SAVE_4VSRS_TRANSACT(n+4,b,base)
-#define SAVE_16VSRS_TRANSACT(n,b,base)	SAVE_8VSRS_TRANSACT(n,b,base);	\
-	                                SAVE_8VSRS_TRANSACT(n+8,b,base)
-#define SAVE_32VSRS_TRANSACT(n,b,base)	SAVE_16VSRS_TRANSACT(n,b,base);	\
-	                                SAVE_16VSRS_TRANSACT(n+16,b,base)
-
-#define REST_VSR_TRANSACT(n,b,base)	li b,THREAD_TRANSACT_VSR0+(16*(n)); \
-					LXVD2X(n,R##base,R##b)
-#define REST_2VSRS_TRANSACT(n,b,base)	REST_VSR_TRANSACT(n,b,base);    \
-	                                REST_VSR_TRANSACT(n+1,b,base)
-#define REST_4VSRS_TRANSACT(n,b,base)	REST_2VSRS_TRANSACT(n,b,base);	\
-	                                REST_2VSRS_TRANSACT(n+2,b,base)
-#define REST_8VSRS_TRANSACT(n,b,base)	REST_4VSRS_TRANSACT(n,b,base);	\
-	                                REST_4VSRS_TRANSACT(n+4,b,base)
-#define REST_16VSRS_TRANSACT(n,b,base)	REST_8VSRS_TRANSACT(n,b,base);	\
-	                                REST_8VSRS_TRANSACT(n+8,b,base)
-#define REST_32VSRS_TRANSACT(n,b,base)	REST_16VSRS_TRANSACT(n,b,base);	\
-	                                REST_16VSRS_TRANSACT(n+16,b,base)
-
 /* Save the lower 32 VSRs in the thread VSR region */
-#define SAVE_VSR(n,b,base)	li b,THREAD_VSR0+(16*(n));  STXVD2X(n,R##base,R##b)
+#define SAVE_VSR(n,b,base)	li b,16*(n);  STXVD2X(n,R##base,R##b)
 #define SAVE_2VSRS(n,b,base)	SAVE_VSR(n,b,base); SAVE_VSR(n+1,b,base)
 #define SAVE_4VSRS(n,b,base)	SAVE_2VSRS(n,b,base); SAVE_2VSRS(n+2,b,base)
 #define SAVE_8VSRS(n,b,base)	SAVE_4VSRS(n,b,base); SAVE_4VSRS(n+4,b,base)
 #define SAVE_16VSRS(n,b,base)	SAVE_8VSRS(n,b,base); SAVE_8VSRS(n+8,b,base)
 #define SAVE_32VSRS(n,b,base)	SAVE_16VSRS(n,b,base); SAVE_16VSRS(n+16,b,base)
-#define REST_VSR(n,b,base)	li b,THREAD_VSR0+(16*(n)); LXVD2X(n,R##base,R##b)
+#define REST_VSR(n,b,base)	li b,16*(n); LXVD2X(n,R##base,R##b)
 #define REST_2VSRS(n,b,base)	REST_VSR(n,b,base); REST_VSR(n+1,b,base)
 #define REST_4VSRS(n,b,base)	REST_2VSRS(n,b,base); REST_2VSRS(n+2,b,base)
 #define REST_8VSRS(n,b,base)	REST_4VSRS(n,b,base); REST_4VSRS(n+4,b,base)
diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h
index ce4de5aed7b..afe695e9feb 100644
--- a/arch/powerpc/include/asm/processor.h
+++ b/arch/powerpc/include/asm/processor.h
@@ -144,8 +144,20 @@ typedef struct {
 
 #define TS_FPROFFSET 0
 #define TS_VSRLOWOFFSET 1
-#define TS_FPR(i) fpr[i][TS_FPROFFSET]
-#define TS_TRANS_FPR(i) transact_fpr[i][TS_FPROFFSET]
+#define TS_FPR(i) fp_state.fpr[i][TS_FPROFFSET]
+#define TS_TRANS_FPR(i) transact_fp.fpr[i][TS_FPROFFSET]
+
+/* FP and VSX 0-31 register set */
+struct thread_fp_state {
+	u64	fpr[32][TS_FPRWIDTH] __attribute__((aligned(16)));
+	u64	fpscr;		/* Floating point status */
+};
+
+/* Complete AltiVec register set including VSCR */
+struct thread_vr_state {
+	vector128	vr[32] __attribute__((aligned(16)));
+	vector128	vscr __attribute__((aligned(16)));
+};
 
 struct thread_struct {
 	unsigned long	ksp;		/* Kernel stack pointer */
@@ -198,13 +210,7 @@ struct thread_struct {
 	unsigned long	dvc2;
 #endif
 #endif
-	/* FP and VSX 0-31 register set */
-	double		fpr[32][TS_FPRWIDTH] __attribute__((aligned(16)));
-	struct {
-
-		unsigned int pad;
-		unsigned int val;	/* Floating point status */
-	} fpscr;
+	struct thread_fp_state	fp_state;
 	int		fpexc_mode;	/* floating-point exception mode */
 	unsigned int	align_ctl;	/* alignment handling control */
 #ifdef CONFIG_PPC64
@@ -222,10 +228,7 @@ struct thread_struct {
 	struct arch_hw_breakpoint hw_brk; /* info on the hardware breakpoint */
 	unsigned long	trap_nr;	/* last trap # on this thread */
 #ifdef CONFIG_ALTIVEC
-	/* Complete AltiVec register set */
-	vector128	vr[32] __attribute__((aligned(16)));
-	/* AltiVec status */
-	vector128	vscr __attribute__((aligned(16)));
+	struct thread_vr_state vr_state;
 	unsigned long	vrsave;
 	int		used_vr;	/* set if process has used altivec */
 #endif /* CONFIG_ALTIVEC */
@@ -262,13 +265,8 @@ struct thread_struct {
 	 * transact_fpr[] is the new set of transactional values.
 	 * VRs work the same way.
 	 */
-	double		transact_fpr[32][TS_FPRWIDTH];
-	struct {
-		unsigned int pad;
-		unsigned int val;	/* Floating point status */
-	} transact_fpscr;
-	vector128	transact_vr[32] __attribute__((aligned(16)));
-	vector128	transact_vscr __attribute__((aligned(16)));
+	struct thread_fp_state transact_fp;
+	struct thread_vr_state transact_vr;
 	unsigned long	transact_vrsave;
 #endif /* CONFIG_PPC_TRANSACTIONAL_MEM */
 #ifdef CONFIG_KVM_BOOK3S_32_HANDLER
@@ -322,8 +320,6 @@ struct thread_struct {
 	.ksp = INIT_SP, \
 	.regs = (struct pt_regs *)INIT_SP - 1, /* XXX bogus, I think */ \
 	.fs = KERNEL_DS, \
-	.fpr = {{0}}, \
-	.fpscr = { .val = 0, }, \
 	.fpexc_mode = 0, \
 	.ppr = INIT_PPR, \
 }
diff --git a/arch/powerpc/include/asm/sfp-machine.h b/arch/powerpc/include/asm/sfp-machine.h
index 3a7a67a0d00..d89beaba26f 100644
--- a/arch/powerpc/include/asm/sfp-machine.h
+++ b/arch/powerpc/include/asm/sfp-machine.h
@@ -125,7 +125,7 @@
 #define FP_EX_DIVZERO         (1 << (31 - 5))
 #define FP_EX_INEXACT         (1 << (31 - 6))
 
-#define __FPU_FPSCR	(current->thread.fpscr.val)
+#define __FPU_FPSCR	(current->thread.fp_state.fpscr)
 
 /* We only actually write to the destination register
  * if exceptions signalled (if any) will not trap.
diff --git a/arch/powerpc/kernel/align.c b/arch/powerpc/kernel/align.c
index a27ccd5dc6b..eaa16bc17e9 100644
--- a/arch/powerpc/kernel/align.c
+++ b/arch/powerpc/kernel/align.c
@@ -660,7 +660,7 @@ static int emulate_vsx(unsigned char __user *addr, unsigned int reg,
 	if (reg < 32)
 		ptr = (char *) &current->thread.TS_FPR(reg);
 	else
-		ptr = (char *) &current->thread.vr[reg - 32];
+		ptr = (char *) &current->thread.vr_state.vr[reg - 32];
 
 	lptr = (unsigned long *) ptr;
 
@@ -897,7 +897,7 @@ int fix_alignment(struct pt_regs *regs)
 				return -EFAULT;
 		}
 	} else if (flags & F) {
-		data.dd = current->thread.TS_FPR(reg);
+		data.ll = current->thread.TS_FPR(reg);
 		if (flags & S) {
 			/* Single-precision FP store requires conversion... */
 #ifdef CONFIG_PPC_FPU
@@ -975,7 +975,7 @@ int fix_alignment(struct pt_regs *regs)
 		if (unlikely(ret))
 			return -EFAULT;
 	} else if (flags & F)
-		current->thread.TS_FPR(reg) = data.dd;
+		current->thread.TS_FPR(reg) = data.ll;
 	else
 		regs->gpr[reg] = data.ll;
 
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index 502c7a4e73f..8d27b61c95b 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -90,16 +90,15 @@ int main(void)
 	DEFINE(THREAD_NORMSAVES, offsetof(struct thread_struct, normsave[0]));
 #endif
 	DEFINE(THREAD_FPEXC_MODE, offsetof(struct thread_struct, fpexc_mode));
-	DEFINE(THREAD_FPR0, offsetof(struct thread_struct, fpr[0]));
-	DEFINE(THREAD_FPSCR, offsetof(struct thread_struct, fpscr));
+	DEFINE(THREAD_FPSTATE, offsetof(struct thread_struct, fp_state));
+	DEFINE(FPSTATE_FPSCR, offsetof(struct thread_fp_state, fpscr));
 #ifdef CONFIG_ALTIVEC
-	DEFINE(THREAD_VR0, offsetof(struct thread_struct, vr[0]));
+	DEFINE(THREAD_VRSTATE, offsetof(struct thread_struct, vr_state));
 	DEFINE(THREAD_VRSAVE, offsetof(struct thread_struct, vrsave));
-	DEFINE(THREAD_VSCR, offsetof(struct thread_struct, vscr));
 	DEFINE(THREAD_USED_VR, offsetof(struct thread_struct, used_vr));
+	DEFINE(VRSTATE_VSCR, offsetof(struct thread_vr_state, vscr));
 #endif /* CONFIG_ALTIVEC */
 #ifdef CONFIG_VSX
-	DEFINE(THREAD_VSR0, offsetof(struct thread_struct, fpr));
 	DEFINE(THREAD_USED_VSR, offsetof(struct thread_struct, used_vsr));
 #endif /* CONFIG_VSX */
 #ifdef CONFIG_PPC64
@@ -143,20 +142,12 @@ int main(void)
 	DEFINE(THREAD_TM_PPR, offsetof(struct thread_struct, tm_ppr));
 	DEFINE(THREAD_TM_DSCR, offsetof(struct thread_struct, tm_dscr));
 	DEFINE(PT_CKPT_REGS, offsetof(struct thread_struct, ckpt_regs));
-	DEFINE(THREAD_TRANSACT_VR0, offsetof(struct thread_struct,
-					 transact_vr[0]));
-	DEFINE(THREAD_TRANSACT_VSCR, offsetof(struct thread_struct,
-					  transact_vscr));
+	DEFINE(THREAD_TRANSACT_VRSTATE, offsetof(struct thread_struct,
+						 transact_vr));
 	DEFINE(THREAD_TRANSACT_VRSAVE, offsetof(struct thread_struct,
 					    transact_vrsave));
-	DEFINE(THREAD_TRANSACT_FPR0, offsetof(struct thread_struct,
-					  transact_fpr[0]));
-	DEFINE(THREAD_TRANSACT_FPSCR, offsetof(struct thread_struct,
-					   transact_fpscr));
-#ifdef CONFIG_VSX
-	DEFINE(THREAD_TRANSACT_VSR0, offsetof(struct thread_struct,
-					  transact_fpr[0]));
-#endif
+	DEFINE(THREAD_TRANSACT_FPSTATE, offsetof(struct thread_struct,
+						 transact_fp));
 	/* Local pt_regs on stack for Transactional Memory funcs. */
 	DEFINE(TM_FRAME_SIZE, STACK_FRAME_OVERHEAD +
 	       sizeof(struct pt_regs) + 16);
diff --git a/arch/powerpc/kernel/fpu.S b/arch/powerpc/kernel/fpu.S
index caeaabf11a2..34b96e6d2f0 100644
--- a/arch/powerpc/kernel/fpu.S
+++ b/arch/powerpc/kernel/fpu.S
@@ -35,15 +35,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_VSX);					\
 2:	REST_32VSRS(n,c,base);						\
 3:
 
-#define __REST_32FPVSRS_TRANSACT(n,c,base)				\
-BEGIN_FTR_SECTION							\
-	b	2f;							\
-END_FTR_SECTION_IFSET(CPU_FTR_VSX);					\
-	REST_32FPRS_TRANSACT(n,base);					\
-	b	3f;							\
-2:	REST_32VSRS_TRANSACT(n,c,base);					\
-3:
-
 #define __SAVE_32FPVSRS(n,c,base)					\
 BEGIN_FTR_SECTION							\
 	b	2f;							\
@@ -54,40 +45,12 @@ END_FTR_SECTION_IFSET(CPU_FTR_VSX);					\
 3:
 #else
 #define __REST_32FPVSRS(n,b,base)	REST_32FPRS(n, base)
-#define __REST_32FPVSRS_TRANSACT(n,b,base)	REST_32FPRS(n, base)
 #define __SAVE_32FPVSRS(n,b,base)	SAVE_32FPRS(n, base)
 #endif
 #define REST_32FPVSRS(n,c,base) __REST_32FPVSRS(n,__REG_##c,__REG_##base)
-#define REST_32FPVSRS_TRANSACT(n,c,base) \
-	__REST_32FPVSRS_TRANSACT(n,__REG_##c,__REG_##base)
 #define SAVE_32FPVSRS(n,c,base) __SAVE_32FPVSRS(n,__REG_##c,__REG_##base)
 
 #ifdef CONFIG_PPC_TRANSACTIONAL_MEM
-/*
- * Wrapper to call load_up_fpu from C.
- * void do_load_up_fpu(struct pt_regs *regs);
- */
-_GLOBAL(do_load_up_fpu)
-	mflr	r0
-	std	r0, 16(r1)
-	stdu	r1, -112(r1)
-
-	subi	r6, r3, STACK_FRAME_OVERHEAD
-	/* load_up_fpu expects r12=MSR, r13=PACA, and returns
-	 * with r12 = new MSR.
-	 */
-	ld	r12,_MSR(r6)
-	GET_PACA(r13)
-
-	bl	load_up_fpu
-	std	r12,_MSR(r6)
-
-	ld	r0, 112+16(r1)
-	addi	r1, r1, 112
-	mtlr	r0
-	blr
-
-
 /* void do_load_up_transact_fpu(struct thread_struct *thread)
  *
  * This is similar to load_up_fpu but for the transactional version of the FP
@@ -105,9 +68,10 @@ END_FTR_SECTION_IFSET(CPU_FTR_VSX)
 	SYNC
 	MTMSRD(r5)
 
-	lfd	fr0,THREAD_TRANSACT_FPSCR(r3)
+	addi	r7,r3,THREAD_TRANSACT_FPSTATE
+	lfd	fr0,FPSTATE_FPSCR(r7)
 	MTFSF_L(fr0)
-	REST_32FPVSRS_TRANSACT(0, R4, R3)
+	REST_32FPVSRS(0, R4, R7)
 
 	/* FP/VSX off again */
 	MTMSRD(r6)
@@ -147,9 +111,10 @@ END_FTR_SECTION_IFSET(CPU_FTR_VSX)
 	beq	1f
 	toreal(r4)
 	addi	r4,r4,THREAD		/* want last_task_used_math->thread */
-	SAVE_32FPVSRS(0, R5, R4)
+	addi	r8,r4,THREAD_FPSTATE
+	SAVE_32FPVSRS(0, R5, R8)
 	mffs	fr0
-	stfd	fr0,THREAD_FPSCR(r4)
+	stfd	fr0,FPSTATE_FPSCR(r8)
 	PPC_LL	r5,PT_REGS(r4)
 	toreal(r5)
 	PPC_LL	r4,_MSR-STACK_FRAME_OVERHEAD(r5)
@@ -160,7 +125,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_VSX)
 #endif /* CONFIG_SMP */
 	/* enable use of FP after return */
 #ifdef CONFIG_PPC32
-	mfspr	r5,SPRN_SPRG_THREAD		/* current task's THREAD (phys) */
+	mfspr	r5,SPRN_SPRG_THREAD	/* current task's THREAD (phys) */
 	lwz	r4,THREAD_FPEXC_MODE(r5)
 	ori	r9,r9,MSR_FP		/* enable FP for current */
 	or	r9,r9,r4
@@ -172,9 +137,10 @@ END_FTR_SECTION_IFSET(CPU_FTR_VSX)
 	or	r12,r12,r4
 	std	r12,_MSR(r1)
 #endif
-	lfd	fr0,THREAD_FPSCR(r5)
+	addi	r7,r5,THREAD_FPSTATE
+	lfd	fr0,FPSTATE_FPSCR(r7)
 	MTFSF_L(fr0)
-	REST_32FPVSRS(0, R4, R5)
+	REST_32FPVSRS(0, R4, R7)
 #ifndef CONFIG_SMP
 	subi	r4,r5,THREAD
 	fromreal(r4)
@@ -208,9 +174,10 @@ END_FTR_SECTION_IFSET(CPU_FTR_VSX)
 	addi	r3,r3,THREAD	        /* want THREAD of task */
 	PPC_LL	r5,PT_REGS(r3)
 	PPC_LCMPI	0,r5,0
-	SAVE_32FPVSRS(0, R4 ,R3)
+	addi	r6,r3,THREAD_FPSTATE
+	SAVE_32FPVSRS(0, R4, R6)
 	mffs	fr0
-	stfd	fr0,THREAD_FPSCR(r3)
+	stfd	fr0,FPSTATE_FPSCR(r6)
 	beq	1f
 	PPC_LL	r4,_MSR-STACK_FRAME_OVERHEAD(r5)
 	li	r3,MSR_FP|MSR_FE0|MSR_FE1
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index 96d2fdf3aa9..7a281416aff 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -1113,12 +1113,10 @@ void start_thread(struct pt_regs *regs, unsigned long start, unsigned long sp)
 #ifdef CONFIG_VSX
 	current->thread.used_vsr = 0;
 #endif
-	memset(current->thread.fpr, 0, sizeof(current->thread.fpr));
-	current->thread.fpscr.val = 0;
+	memset(&current->thread.fp_state, 0, sizeof(current->thread.fp_state));
 #ifdef CONFIG_ALTIVEC
-	memset(current->thread.vr, 0, sizeof(current->thread.vr));
-	memset(&current->thread.vscr, 0, sizeof(current->thread.vscr));
-	current->thread.vscr.u[3] = 0x00010000; /* Java mode disabled */
+	memset(&current->thread.vr_state, 0, sizeof(current->thread.vr_state));
+	current->thread.vr_state.vscr.u[3] = 0x00010000; /* Java mode disabled */
 	current->thread.vrsave = 0;
 	current->thread.used_vr = 0;
 #endif /* CONFIG_ALTIVEC */
diff --git a/arch/powerpc/kernel/ptrace.c b/arch/powerpc/kernel/ptrace.c
index 9a0d24c390a..238580043d8 100644
--- a/arch/powerpc/kernel/ptrace.c
+++ b/arch/powerpc/kernel/ptrace.c
@@ -362,7 +362,7 @@ static int fpr_get(struct task_struct *target, const struct user_regset *regset,
 		   void *kbuf, void __user *ubuf)
 {
 #ifdef CONFIG_VSX
-	double buf[33];
+	u64 buf[33];
 	int i;
 #endif
 	flush_fp_to_thread(target);
@@ -371,15 +371,15 @@ static int fpr_get(struct task_struct *target, const struct user_regset *regset,
 	/* copy to local buffer then write that out */
 	for (i = 0; i < 32 ; i++)
 		buf[i] = target->thread.TS_FPR(i);
-	memcpy(&buf[32], &target->thread.fpscr, sizeof(double));
+	buf[32] = target->thread.fp_state.fpscr;
 	return user_regset_copyout(&pos, &count, &kbuf, &ubuf, buf, 0, -1);
 
 #else
-	BUILD_BUG_ON(offsetof(struct thread_struct, fpscr) !=
-		     offsetof(struct thread_struct, TS_FPR(32)));
+	BUILD_BUG_ON(offsetof(struct thread_fp_state, fpscr) !=
+		     offsetof(struct thread_fp_state, fpr[32][0]));
 
 	return user_regset_copyout(&pos, &count, &kbuf, &ubuf,
-				   &target->thread.fpr, 0, -1);
+				   &target->thread.fp_state, 0, -1);
 #endif
 }
 
@@ -388,7 +388,7 @@ static int fpr_set(struct task_struct *target, const struct user_regset *regset,
 		   const void *kbuf, const void __user *ubuf)
 {
 #ifdef CONFIG_VSX
-	double buf[33];
+	u64 buf[33];
 	int i;
 #endif
 	flush_fp_to_thread(target);
@@ -400,14 +400,14 @@ static int fpr_set(struct task_struct *target, const struct user_regset *regset,
 		return i;
 	for (i = 0; i < 32 ; i++)
 		target->thread.TS_FPR(i) = buf[i];
-	memcpy(&target->thread.fpscr, &buf[32], sizeof(double));
+	target->thread.fp_state.fpscr = buf[32];
 	return 0;
 #else
-	BUILD_BUG_ON(offsetof(struct thread_struct, fpscr) !=
-		     offsetof(struct thread_struct, TS_FPR(32)));
+	BUILD_BUG_ON(offsetof(struct thread_fp_state, fpscr) !=
+		     offsetof(struct thread_fp_state, fpr[32][0]));
 
 	return user_regset_copyin(&pos, &count, &kbuf, &ubuf,
-				  &target->thread.fpr, 0, -1);
+				  &target->thread.fp_state, 0, -1);
 #endif
 }
 
@@ -440,11 +440,11 @@ static int vr_get(struct task_struct *target, const struct user_regset *regset,
 
 	flush_altivec_to_thread(target);
 
-	BUILD_BUG_ON(offsetof(struct thread_struct, vscr) !=
-		     offsetof(struct thread_struct, vr[32]));
+	BUILD_BUG_ON(offsetof(struct thread_vr_state, vscr) !=
+		     offsetof(struct thread_vr_state, vr[32]));
 
 	ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf,
-				  &target->thread.vr, 0,
+				  &target->thread.vr_state, 0,
 				  33 * sizeof(vector128));
 	if (!ret) {
 		/*
@@ -471,11 +471,12 @@ static int vr_set(struct task_struct *target, const struct user_regset *regset,
 
 	flush_altivec_to_thread(target);
 
-	BUILD_BUG_ON(offsetof(struct thread_struct, vscr) !=
-		     offsetof(struct thread_struct, vr[32]));
+	BUILD_BUG_ON(offsetof(struct thread_vr_state, vscr) !=
+		     offsetof(struct thread_vr_state, vr[32]));
 
 	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
-				 &target->thread.vr, 0, 33 * sizeof(vector128));
+				 &target->thread.vr_state, 0,
+				 33 * sizeof(vector128));
 	if (!ret && count > 0) {
 		/*
 		 * We use only the first word of vrsave.
@@ -514,13 +515,13 @@ static int vsr_get(struct task_struct *target, const struct user_regset *regset,
 		   unsigned int pos, unsigned int count,
 		   void *kbuf, void __user *ubuf)
 {
-	double buf[32];
+	u64 buf[32];
 	int ret, i;
 
 	flush_vsx_to_thread(target);
 
 	for (i = 0; i < 32 ; i++)
-		buf[i] = target->thread.fpr[i][TS_VSRLOWOFFSET];
+		buf[i] = target->thread.fp_state.fpr[i][TS_VSRLOWOFFSET];
 	ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf,
 				  buf, 0, 32 * sizeof(double));
 
@@ -531,7 +532,7 @@ static int vsr_set(struct task_struct *target, const struct user_regset *regset,
 		   unsigned int pos, unsigned int count,
 		   const void *kbuf, const void __user *ubuf)
 {
-	double buf[32];
+	u64 buf[32];
 	int ret,i;
 
 	flush_vsx_to_thread(target);
@@ -539,7 +540,7 @@ static int vsr_set(struct task_struct *target, const struct user_regset *regset,
 	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
 				 buf, 0, 32 * sizeof(double));
 	for (i = 0; i < 32 ; i++)
-		target->thread.fpr[i][TS_VSRLOWOFFSET] = buf[i];
+		target->thread.fp_state.fpr[i][TS_VSRLOWOFFSET] = buf[i];
 
 
 	return ret;
@@ -1554,10 +1555,10 @@ long arch_ptrace(struct task_struct *child, long request,
 
 			flush_fp_to_thread(child);
 			if (fpidx < (PT_FPSCR - PT_FPR0))
-				tmp = ((unsigned long *)child->thread.fpr)
+				tmp = ((unsigned long *)child->thread.fp_state.fpr)
 					[fpidx * TS_FPRWIDTH];
 			else
-				tmp = child->thread.fpscr.val;
+				tmp = child->thread.fp_state.fpscr;
 		}
 		ret = put_user(tmp, datalp);
 		break;
@@ -1587,10 +1588,10 @@ long arch_ptrace(struct task_struct *child, long request,
 
 			flush_fp_to_thread(child);
 			if (fpidx < (PT_FPSCR - PT_FPR0))
-				((unsigned long *)child->thread.fpr)
+				((unsigned long *)child->thread.fp_state.fpr)
 					[fpidx * TS_FPRWIDTH] = data;
 			else
-				child->thread.fpscr.val = data;
+				child->thread.fp_state.fpscr = data;
 			ret = 0;
 		}
 		break;
diff --git a/arch/powerpc/kernel/ptrace32.c b/arch/powerpc/kernel/ptrace32.c
index f51599e941c..097f8dc426a 100644
--- a/arch/powerpc/kernel/ptrace32.c
+++ b/arch/powerpc/kernel/ptrace32.c
@@ -43,7 +43,6 @@
 #define FPRNUMBER(i) (((i) - PT_FPR0) >> 1)
 #define FPRHALF(i) (((i) - PT_FPR0) & 1)
 #define FPRINDEX(i) TS_FPRWIDTH * FPRNUMBER(i) * 2 + FPRHALF(i)
-#define FPRINDEX_3264(i) (TS_FPRWIDTH * ((i) - PT_FPR0))
 
 long compat_arch_ptrace(struct task_struct *child, compat_long_t request,
 			compat_ulong_t caddr, compat_ulong_t cdata)
@@ -105,7 +104,7 @@ long compat_arch_ptrace(struct task_struct *child, compat_long_t request,
 			 * to be an array of unsigned int (32 bits) - the
 			 * index passed in is based on this assumption.
 			 */
-			tmp = ((unsigned int *)child->thread.fpr)
+			tmp = ((unsigned int *)child->thread.fp_state.fpr)
 				[FPRINDEX(index)];
 		}
 		ret = put_user((unsigned int)tmp, (u32 __user *)data);
@@ -147,8 +146,7 @@ long compat_arch_ptrace(struct task_struct *child, compat_long_t request,
 		if (numReg >= PT_FPR0) {
 			flush_fp_to_thread(child);
 			/* get 64 bit FPR */
-			tmp = ((u64 *)child->thread.fpr)
-				[FPRINDEX_3264(numReg)];
+			tmp = child->thread.fp_state.fpr[numReg - PT_FPR0][0];
 		} else { /* register within PT_REGS struct */
 			unsigned long tmp2;
 			ret = ptrace_get_reg(child, numReg, &tmp2);
@@ -207,7 +205,7 @@ long compat_arch_ptrace(struct task_struct *child, compat_long_t request,
 			 * to be an array of unsigned int (32 bits) - the
 			 * index passed in is based on this assumption.
 			 */
-			((unsigned int *)child->thread.fpr)
+			((unsigned int *)child->thread.fp_state.fpr)
 				[FPRINDEX(index)] = data;
 			ret = 0;
 		}
@@ -251,8 +249,7 @@ long compat_arch_ptrace(struct task_struct *child, compat_long_t request,
 			u64 *tmp;
 			flush_fp_to_thread(child);
 			/* get 64 bit FPR ... */
-			tmp = &(((u64 *)child->thread.fpr)
-				[FPRINDEX_3264(numReg)]);
+			tmp = &child->thread.fp_state.fpr[numReg - PT_FPR0][0];
 			/* ... write the 32 bit part we want */
 			((u32 *)tmp)[index % 2] = data;
 			ret = 0;
diff --git a/arch/powerpc/kernel/signal_32.c b/arch/powerpc/kernel/signal_32.c
index bebdf1a1a54..ea25e45ea95 100644
--- a/arch/powerpc/kernel/signal_32.c
+++ b/arch/powerpc/kernel/signal_32.c
@@ -265,27 +265,27 @@ struct rt_sigframe {
 unsigned long copy_fpr_to_user(void __user *to,
 			       struct task_struct *task)
 {
-	double buf[ELF_NFPREG];
+	u64 buf[ELF_NFPREG];
 	int i;
 
 	/* save FPR copy to local buffer then write to the thread_struct */
 	for (i = 0; i < (ELF_NFPREG - 1) ; i++)
 		buf[i] = task->thread.TS_FPR(i);
-	memcpy(&buf[i], &task->thread.fpscr, sizeof(double));
+	buf[i] = task->thread.fp_state.fpscr;
 	return __copy_to_user(to, buf, ELF_NFPREG * sizeof(double));
 }
 
 unsigned long copy_fpr_from_user(struct task_struct *task,
 				 void __user *from)
 {
-	double buf[ELF_NFPREG];
+	u64 buf[ELF_NFPREG];
 	int i;
 
 	if (__copy_from_user(buf, from, ELF_NFPREG * sizeof(double)))
 		return 1;
 	for (i = 0; i < (ELF_NFPREG - 1) ; i++)
 		task->thread.TS_FPR(i) = buf[i];
-	memcpy(&task->thread.fpscr, &buf[i], sizeof(double));
+	task->thread.fp_state.fpscr = buf[i];
 
 	return 0;
 }
@@ -293,25 +293,25 @@ unsigned long copy_fpr_from_user(struct task_struct *task,
 unsigned long copy_vsx_to_user(void __user *to,
 			       struct task_struct *task)
 {
-	double buf[ELF_NVSRHALFREG];
+	u64 buf[ELF_NVSRHALFREG];
 	int i;
 
 	/* save FPR copy to local buffer then write to the thread_struct */
 	for (i = 0; i < ELF_NVSRHALFREG; i++)
-		buf[i] = task->thread.fpr[i][TS_VSRLOWOFFSET];
+		buf[i] = task->thread.fp_state.fpr[i][TS_VSRLOWOFFSET];
 	return __copy_to_user(to, buf, ELF_NVSRHALFREG * sizeof(double));
 }
 
 unsigned long copy_vsx_from_user(struct task_struct *task,
 				 void __user *from)
 {
-	double buf[ELF_NVSRHALFREG];
+	u64 buf[ELF_NVSRHALFREG];
 	int i;
 
 	if (__copy_from_user(buf, from, ELF_NVSRHALFREG * sizeof(double)))
 		return 1;
 	for (i = 0; i < ELF_NVSRHALFREG ; i++)
-		task->thread.fpr[i][TS_VSRLOWOFFSET] = buf[i];
+		task->thread.fp_state.fpr[i][TS_VSRLOWOFFSET] = buf[i];
 	return 0;
 }
 
@@ -319,27 +319,27 @@ unsigned long copy_vsx_from_user(struct task_struct *task,
 unsigned long copy_transact_fpr_to_user(void __user *to,
 				  struct task_struct *task)
 {
-	double buf[ELF_NFPREG];
+	u64 buf[ELF_NFPREG];
 	int i;
 
 	/* save FPR copy to local buffer then write to the thread_struct */
 	for (i = 0; i < (ELF_NFPREG - 1) ; i++)
 		buf[i] = task->thread.TS_TRANS_FPR(i);
-	memcpy(&buf[i], &task->thread.transact_fpscr, sizeof(double));
+	buf[i] = task->thread.transact_fp.fpscr;
 	return __copy_to_user(to, buf, ELF_NFPREG * sizeof(double));
 }
 
 unsigned long copy_transact_fpr_from_user(struct task_struct *task,
 					  void __user *from)
 {
-	double buf[ELF_NFPREG];
+	u64 buf[ELF_NFPREG];
 	int i;
 
 	if (__copy_from_user(buf, from, ELF_NFPREG * sizeof(double)))
 		return 1;
 	for (i = 0; i < (ELF_NFPREG - 1) ; i++)
 		task->thread.TS_TRANS_FPR(i) = buf[i];
-	memcpy(&task->thread.transact_fpscr, &buf[i], sizeof(double));
+	task->thread.transact_fp.fpscr = buf[i];
 
 	return 0;
 }
@@ -347,25 +347,25 @@ unsigned long copy_transact_fpr_from_user(struct task_struct *task,
 unsigned long copy_transact_vsx_to_user(void __user *to,
 				  struct task_struct *task)
 {
-	double buf[ELF_NVSRHALFREG];
+	u64 buf[ELF_NVSRHALFREG];
 	int i;
 
 	/* save FPR copy to local buffer then write to the thread_struct */
 	for (i = 0; i < ELF_NVSRHALFREG; i++)
-		buf[i] = task->thread.transact_fpr[i][TS_VSRLOWOFFSET];
+		buf[i] = task->thread.transact_fp.fpr[i][TS_VSRLOWOFFSET];
 	return __copy_to_user(to, buf, ELF_NVSRHALFREG * sizeof(double));
 }
 
 unsigned long copy_transact_vsx_from_user(struct task_struct *task,
 					  void __user *from)
 {
-	double buf[ELF_NVSRHALFREG];
+	u64 buf[ELF_NVSRHALFREG];
 	int i;
 
 	if (__copy_from_user(buf, from, ELF_NVSRHALFREG * sizeof(double)))
 		return 1;
 	for (i = 0; i < ELF_NVSRHALFREG ; i++)
-		task->thread.transact_fpr[i][TS_VSRLOWOFFSET] = buf[i];
+		task->thread.transact_fp.fpr[i][TS_VSRLOWOFFSET] = buf[i];
 	return 0;
 }
 #endif /* CONFIG_PPC_TRANSACTIONAL_MEM */
@@ -373,14 +373,14 @@ unsigned long copy_transact_vsx_from_user(struct task_struct *task,
 inline unsigned long copy_fpr_to_user(void __user *to,
 				      struct task_struct *task)
 {
-	return __copy_to_user(to, task->thread.fpr,
+	return __copy_to_user(to, task->thread.fp_state.fpr,
 			      ELF_NFPREG * sizeof(double));
 }
 
 inline unsigned long copy_fpr_from_user(struct task_struct *task,
 					void __user *from)
 {
-	return __copy_from_user(task->thread.fpr, from,
+	return __copy_from_user(task->thread.fp_state.fpr, from,
 			      ELF_NFPREG * sizeof(double));
 }
 
@@ -388,14 +388,14 @@ inline unsigned long copy_fpr_from_user(struct task_struct *task,
 inline unsigned long copy_transact_fpr_to_user(void __user *to,
 					 struct task_struct *task)
 {
-	return __copy_to_user(to, task->thread.transact_fpr,
+	return __copy_to_user(to, task->thread.transact_fp.fpr,
 			      ELF_NFPREG * sizeof(double));
 }
 
 inline unsigned long copy_transact_fpr_from_user(struct task_struct *task,
 						 void __user *from)
 {
-	return __copy_from_user(task->thread.transact_fpr, from,
+	return __copy_from_user(task->thr