powerpc: Add VSX context save/restore, ptrace and signal support

This patch extends the floating point save and restore code to use the
VSX load/stores when VSX is available.  This will make FP context
save/restore marginally slower on FP only code, when VSX is available,
as it has to load/store 128bits rather than just 64bits.

Mixing FP, VMX and VSX code will get constant architected state.

The signals interface is extended to enable access to VSR 0-31
doubleword 1 after discussions with tool chain maintainers.  Backward
compatibility is maintained.

The ptrace interface is also extended to allow access to VSR 0-31 full
registers.

Signed-off-by: Michael Neuling <mikey@neuling.org>
Signed-off-by: Paul Mackerras <paulus@samba.org>

16 files changed, 451 insertions, 8 deletions

diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S
index 6ca3044..12eb95a 100644
--- a/arch/powerpc/kernel/entry_64.S
+++ b/arch/powerpc/kernel/entry_64.S
@@ -353,6 +353,11 @@ _GLOBAL(_switch)
 	mflr	r20		/* Return to switch caller */
 	mfmsr	r22
 	li	r0, MSR_FP
+#ifdef CONFIG_VSX
+BEGIN_FTR_SECTION
+	oris	r0,r0,MSR_VSX@h	/* Disable VSX */
+END_FTR_SECTION_IFSET(CPU_FTR_VSX)
+#endif /* CONFIG_VSX */
 #ifdef CONFIG_ALTIVEC
 BEGIN_FTR_SECTION
 	oris	r0,r0,MSR_VEC@h	/* Disable altivec */
diff --git a/arch/powerpc/kernel/fpu.S b/arch/powerpc/kernel/fpu.S
index 15247fe..a088c06 100644
--- a/arch/powerpc/kernel/fpu.S
+++ b/arch/powerpc/kernel/fpu.S
@@ -57,6 +57,11 @@ END_FTR_SECTION_IFSET(CPU_FTR_VSX);					\
 _GLOBAL(load_up_fpu)
 	mfmsr	r5
 	ori	r5,r5,MSR_FP
+#ifdef CONFIG_VSX
+BEGIN_FTR_SECTION
+	oris	r5,r5,MSR_VSX@h
+END_FTR_SECTION_IFSET(CPU_FTR_VSX)
+#endif
 	SYNC
 	MTMSRD(r5)			/* enable use of fpu now */
 	isync
@@ -73,7 +78,7 @@ _GLOBAL(load_up_fpu)
 	beq	1f
 	toreal(r4)
 	addi	r4,r4,THREAD		/* want last_task_used_math->thread */
-	SAVE_32FPRS(0, r4)
+	SAVE_32FPVSRS(0, r5, r4)
 	mffs	fr0
 	stfd	fr0,THREAD_FPSCR(r4)
 	PPC_LL	r5,PT_REGS(r4)
@@ -100,7 +105,7 @@ _GLOBAL(load_up_fpu)
 #endif
 	lfd	fr0,THREAD_FPSCR(r5)
 	MTFSF_L(fr0)
-	REST_32FPRS(0, r5)
+	REST_32FPVSRS(0, r4, r5)
 #ifndef CONFIG_SMP
 	subi	r4,r5,THREAD
 	fromreal(r4)
@@ -119,6 +124,11 @@ _GLOBAL(load_up_fpu)
 _GLOBAL(giveup_fpu)
 	mfmsr	r5
 	ori	r5,r5,MSR_FP
+#ifdef CONFIG_VSX
+BEGIN_FTR_SECTION
+	oris	r5,r5,MSR_VSX@h
+END_FTR_SECTION_IFSET(CPU_FTR_VSX)
+#endif
 	SYNC_601
 	ISYNC_601
 	MTMSRD(r5)			/* enable use of fpu now */
@@ -129,7 +139,7 @@ _GLOBAL(giveup_fpu)
 	addi	r3,r3,THREAD	        /* want THREAD of task */
 	PPC_LL	r5,PT_REGS(r3)
 	PPC_LCMPI	0,r5,0
-	SAVE_32FPRS(0, r3)
+	SAVE_32FPVSRS(0, r4 ,r3)
 	mffs	fr0
 	stfd	fr0,THREAD_FPSCR(r3)
 	beq	1f
diff --git a/arch/powerpc/kernel/head_64.S b/arch/powerpc/kernel/head_64.S
index 6443373..ecced1e 100644
--- a/arch/powerpc/kernel/head_64.S
+++ b/arch/powerpc/kernel/head_64.S
@@ -278,6 +278,9 @@ END_FTR_SECTION_IFSET(CPU_FTR_REAL_LE)
 	. = 0xf20
 	b	altivec_unavailable_pSeries
 
+	. = 0xf40
+	b	vsx_unavailable_pSeries
+
 #ifdef CONFIG_CBE_RAS
 	HSTD_EXCEPTION_PSERIES(0x1200, cbe_system_error)
 #endif /* CONFIG_CBE_RAS */
@@ -297,6 +300,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_REAL_LE)
 	/* moved from 0xf00 */
 	STD_EXCEPTION_PSERIES(., performance_monitor)
 	STD_EXCEPTION_PSERIES(., altivec_unavailable)
+	STD_EXCEPTION_PSERIES(., vsx_unavailable)
 
 /*
  * An interrupt came in while soft-disabled; clear EE in SRR1,
@@ -836,6 +840,67 @@ _STATIC(load_up_altivec)
 	blr
 #endif /* CONFIG_ALTIVEC */
 
+	.align	7
+	.globl vsx_unavailable_common
+vsx_unavailable_common:
+	EXCEPTION_PROLOG_COMMON(0xf40, PACA_EXGEN)
+#ifdef CONFIG_VSX
+BEGIN_FTR_SECTION
+	bne	.load_up_vsx
+1:
+END_FTR_SECTION_IFSET(CPU_FTR_VSX)
+#endif
+	bl	.save_nvgprs
+	addi	r3,r1,STACK_FRAME_OVERHEAD
+	ENABLE_INTS
+	bl	.vsx_unavailable_exception
+	b	.ret_from_except
+
+#ifdef CONFIG_VSX
+/*
+ * load_up_vsx(unused, unused, tsk)
+ * Disable VSX for the task which had it previously,
+ * and save its vector registers in its thread_struct.
+ * Reuse the fp and vsx saves, but first check to see if they have
+ * been saved already.
+ * On entry: r13 == 'current' && last_task_used_vsx != 'current'
+ */
+_STATIC(load_up_vsx)
+/* Load FP and VSX registers if they haven't been done yet */
+	andi.	r5,r12,MSR_FP
+	beql+	load_up_fpu		/* skip if already loaded */
+	andis.	r5,r12,MSR_VEC@h
+	beql+	load_up_altivec		/* skip if already loaded */
+
+#ifndef CONFIG_SMP
+	ld	r3,last_task_used_vsx@got(r2)
+	ld	r4,0(r3)
+	cmpdi	0,r4,0
+	beq	1f
+	/* Disable VSX for last_task_used_vsx */
+	addi	r4,r4,THREAD
+	ld	r5,PT_REGS(r4)
+	ld	r4,_MSR-STACK_FRAME_OVERHEAD(r5)
+	lis	r6,MSR_VSX@h
+	andc	r6,r4,r6
+	std	r6,_MSR-STACK_FRAME_OVERHEAD(r5)
+1:
+#endif /* CONFIG_SMP */
+	ld	r4,PACACURRENT(r13)
+	addi	r4,r4,THREAD		/* Get THREAD */
+	li	r6,1
+	stw	r6,THREAD_USED_VSR(r4) /* ... also set thread used vsr */
+	/* enable use of VSX after return */
+	oris	r12,r12,MSR_VSX@h
+	std	r12,_MSR(r1)
+#ifndef CONFIG_SMP
+	/* Update last_task_used_math to 'current' */
+	ld	r4,PACACURRENT(r13)
+	std	r4,0(r3)
+#endif /* CONFIG_SMP */
+	b	fast_exception_return
+#endif /* CONFIG_VSX */
+
 /*
  * Hash table stuff
  */
diff --git a/arch/powerpc/kernel/misc_64.S b/arch/powerpc/kernel/misc_64.S
index 942951e..31b9026 100644
--- a/arch/powerpc/kernel/misc_64.S
+++ b/arch/powerpc/kernel/misc_64.S
@@ -506,6 +506,39 @@ _GLOBAL(giveup_altivec)
 
 #endif /* CONFIG_ALTIVEC */
 
+#ifdef CONFIG_VSX
+/*
+ * giveup_vsx(tsk)
+ * Disable VSX for the task given as the argument,
+ * and save the vector registers in its thread_struct.
+ * Enables the VSX for use in the kernel on return.
+ */
+_GLOBAL(giveup_vsx)
+	mfmsr	r5
+	oris	r5,r5,MSR_VSX@h
+	mtmsrd	r5			/* enable use of VSX now */
+	isync
+
+	cmpdi	0,r3,0
+	beqlr-				/* if no previous owner, done */
+	addi	r3,r3,THREAD		/* want THREAD of task */
+	ld	r5,PT_REGS(r3)
+	cmpdi	0,r5,0
+	beq	1f
+	ld	r4,_MSR-STACK_FRAME_OVERHEAD(r5)
+	lis	r3,MSR_VSX@h
+	andc	r4,r4,r3		/* disable VSX for previous task */
+	std	r4,_MSR-STACK_FRAME_OVERHEAD(r5)
+1:
+#ifndef CONFIG_SMP
+	li	r5,0
+	ld	r4,last_task_used_vsx@got(r2)
+	std	r5,0(r4)
+#endif /* CONFIG_SMP */
+	blr
+
+#endif /* CONFIG_VSX */
+
 /* kexec_wait(phys_cpu)
  *
  * wait for the flag to change, indicating this kernel is going away but
diff --git a/arch/powerpc/kernel/ppc32.h b/arch/powerpc/kernel/ppc32.h
index 90e5627..dc16aef 100644
--- a/arch/powerpc/kernel/ppc32.h
+++ b/arch/powerpc/kernel/ppc32.h
@@ -120,6 +120,7 @@ struct mcontext32 {
 	elf_fpregset_t		mc_fregs;
 	unsigned int		mc_pad[2];
 	elf_vrregset_t32	mc_vregs __attribute__((__aligned__(16)));
+	elf_vsrreghalf_t32      mc_vsregs __attribute__((__aligned__(16)));
 };
 
 struct ucontext32 { 
diff --git a/arch/powerpc/kernel/ppc_ksyms.c b/arch/powerpc/kernel/ppc_ksyms.c
index d3ac631..958ecb9 100644
--- a/arch/powerpc/kernel/ppc_ksyms.c
+++ b/arch/powerpc/kernel/ppc_ksyms.c
@@ -102,6 +102,9 @@ EXPORT_SYMBOL(giveup_fpu);
 #ifdef CONFIG_ALTIVEC
 EXPORT_SYMBOL(giveup_altivec);
 #endif /* CONFIG_ALTIVEC */
+#ifdef CONFIG_VSX
+EXPORT_SYMBOL(giveup_vsx);
+#endif /* CONFIG_VSX */
 #ifdef CONFIG_SPE
 EXPORT_SYMBOL(giveup_spe);
 #endif /* CONFIG_SPE */
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index 582df704..d52ded36 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -53,6 +53,7 @@ extern unsigned long _get_SP(void);
 #ifndef CONFIG_SMP
 struct task_struct *last_task_used_math = NULL;
 struct task_struct *last_task_used_altivec = NULL;
+struct task_struct *last_task_used_vsx = NULL;
 struct task_struct *last_task_used_spe = NULL;
 #endif
 
@@ -106,11 +107,23 @@ EXPORT_SYMBOL(enable_kernel_fp);
 
 int dump_task_fpu(struct task_struct *tsk, elf_fpregset_t *fpregs)
 {
+#ifdef CONFIG_VSX
+	int i;
+	elf_fpreg_t *reg;
+#endif
+
 	if (!tsk->thread.regs)
 		return 0;
 	flush_fp_to_thread(current);
 
+#ifdef CONFIG_VSX
+	reg = (elf_fpreg_t *)fpregs;
+	for (i = 0; i < ELF_NFPREG - 1; i++, reg++)
+		*reg = tsk->thread.TS_FPR(i);
+	memcpy(reg, &tsk->thread.fpscr, sizeof(elf_fpreg_t));
+#else
 	memcpy(fpregs, &tsk->thread.TS_FPR(0), sizeof(*fpregs));
+#endif
 
 	return 1;
 }
@@ -149,7 +162,7 @@ void flush_altivec_to_thread(struct task_struct *tsk)
 	}
 }
 
-int dump_task_altivec(struct task_struct *tsk, elf_vrregset_t *vrregs)
+int dump_task_altivec(struct task_struct *tsk, elf_vrreg_t *vrregs)
 {
 	/* ELF_NVRREG includes the VSCR and VRSAVE which we need to save
 	 * separately, see below */
@@ -179,6 +192,80 @@ int dump_task_altivec(struct task_struct *tsk, elf_vrregset_t *vrregs)
 }
 #endif /* CONFIG_ALTIVEC */
 
+#ifdef CONFIG_VSX
+#if 0
+/* not currently used, but some crazy RAID module might want to later */
+void enable_kernel_vsx(void)
+{
+	WARN_ON(preemptible());
+
+#ifdef CONFIG_SMP
+	if (current->thread.regs && (current->thread.regs->msr & MSR_VSX))
+		giveup_vsx(current);
+	else
+		giveup_vsx(NULL);	/* just enable vsx for kernel - force */
+#else
+	giveup_vsx(last_task_used_vsx);
+#endif /* CONFIG_SMP */
+}
+EXPORT_SYMBOL(enable_kernel_vsx);
+#endif
+
+void flush_vsx_to_thread(struct task_struct *tsk)
+{
+	if (tsk->thread.regs) {
+		preempt_disable();
+		if (tsk->thread.regs->msr & MSR_VSX) {
+#ifdef CONFIG_SMP
+			BUG_ON(tsk != current);
+#endif
+			giveup_vsx(tsk);
+		}
+		preempt_enable();
+	}
+}
+
+/*
+ * This dumps the lower half 64bits of the first 32 VSX registers.
+ * This needs to be called with dump_task_fp and dump_task_altivec to
+ * get all the VSX state.
+ */
+int dump_task_vsx(struct task_struct *tsk, elf_vrreg_t *vrregs)
+{
+	elf_vrreg_t *reg;
+	double buf[32];
+	int i;
+
+	if (tsk == current)
+		flush_vsx_to_thread(tsk);
+
+	reg = (elf_vrreg_t *)vrregs;
+
+	for (i = 0; i < 32 ; i++)
+		buf[i] = current->thread.fpr[i][TS_VSRLOWOFFSET];
+	memcpy(reg, buf, sizeof(buf));
+
+	return 1;
+}
+#endif /* CONFIG_VSX */
+
+int dump_task_vector(struct task_struct *tsk, elf_vrregset_t *vrregs)
+{
+	int rc = 0;
+	elf_vrreg_t *regs = (elf_vrreg_t *)vrregs;
+#ifdef CONFIG_ALTIVEC
+	rc = dump_task_altivec(tsk, regs);
+	if (rc)
+		return rc;
+	regs += ELF_NVRREG;
+#endif
+
+#ifdef CONFIG_VSX
+	rc = dump_task_vsx(tsk, regs);
+#endif
+	return rc;
+}
+
 #ifdef CONFIG_SPE
 
 void enable_kernel_spe(void)
@@ -233,6 +320,10 @@ void discard_lazy_cpu_state(void)
 	if (last_task_used_altivec == current)
 		last_task_used_altivec = NULL;
 #endif /* CONFIG_ALTIVEC */
+#ifdef CONFIG_VSX
+	if (last_task_used_vsx == current)
+		last_task_used_vsx = NULL;
+#endif /* CONFIG_VSX */
 #ifdef CONFIG_SPE
 	if (last_task_used_spe == current)
 		last_task_used_spe = NULL;
@@ -297,6 +388,10 @@ struct task_struct *__switch_to(struct task_struct *prev,
 	if (prev->thread.regs && (prev->thread.regs->msr & MSR_VEC))
 		giveup_altivec(prev);
 #endif /* CONFIG_ALTIVEC */
+#ifdef CONFIG_VSX
+	if (prev->thread.regs && (prev->thread.regs->msr & MSR_VSX))
+		giveup_vsx(prev);
+#endif /* CONFIG_VSX */
 #ifdef CONFIG_SPE
 	/*
 	 * If the previous thread used spe in the last quantum
@@ -317,6 +412,10 @@ struct task_struct *__switch_to(struct task_struct *prev,
 	if (new->thread.regs && last_task_used_altivec == new)
 		new->thread.regs->msr |= MSR_VEC;
 #endif /* CONFIG_ALTIVEC */
+#ifdef CONFIG_VSX
+	if (new->thread.regs && last_task_used_vsx == new)
+		new->thread.regs->msr |= MSR_VSX;
+#endif /* CONFIG_VSX */
 #ifdef CONFIG_SPE
 	/* Avoid the trap.  On smp this this never happens since
 	 * we don't set last_task_used_spe
@@ -417,6 +516,8 @@ static struct regbit {
 	{MSR_EE,	"EE"},
 	{MSR_PR,	"PR"},
 	{MSR_FP,	"FP"},
+	{MSR_VEC,	"VEC"},
+	{MSR_VSX,	"VSX"},
 	{MSR_ME,	"ME"},
 	{MSR_IR,	"IR"},
 	{MSR_DR,	"DR"},
@@ -534,6 +635,7 @@ void prepare_to_copy(struct task_struct *tsk)
 {
 	flush_fp_to_thread(current);
 	flush_altivec_to_thread(current);
+	flush_vsx_to_thread(current);
 	flush_spe_to_thread(current);
 }
 
@@ -689,6 +791,9 @@ void start_thread(struct pt_regs *regs, unsigned long start, unsigned long sp)
 #endif
 
 	discard_lazy_cpu_state();
+#ifdef CONFIG_VSX
+	current->thread.used_vsr = 0;
+#endif
 	memset(current->thread.fpr, 0, sizeof(current->thread.fpr));
 	current->thread.fpscr.val = 0;
 #ifdef CONFIG_ALTIVEC
diff --git a/arch/powerpc/kernel/ptrace.c b/arch/powerpc/kernel/ptrace.c
index 70fbde8..4e203a8 100644
--- a/arch/powerpc/kernel/ptrace.c
+++ b/arch/powerpc/kernel/ptrace.c
@@ -350,6 +350,51 @@ static int vr_set(struct task_struct *target, const struct user_regset *regset,
 }
 #endif /* CONFIG_ALTIVEC */
 
+#ifdef CONFIG_VSX
+/*
+ * Currently to set and and get all the vsx state, you need to call
+ * the fp and VMX calls aswell.  This only get/sets the lower 32
+ * 128bit VSX registers.
+ */
+
+static int vsr_active(struct task_struct *target,
+		      const struct user_regset *regset)
+{
+	flush_vsx_to_thread(target);
+	return target->thread.used_vsr ? regset->n : 0;
+}
+
+static int vsr_get(struct task_struct *target, const struct user_regset *regset,
+		   unsigned int pos, unsigned int count,
+		   void *kbuf, void __user *ubuf)
+{
+	int ret;
+
+	flush_vsx_to_thread(target);
+
+	ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf,
+				  target->thread.fpr, 0,
+				  32 * sizeof(vector128));
+
+	return ret;
+}
+
+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)
+{
+	int ret;
+
+	flush_vsx_to_thread(target);
+
+	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+				 target->thread.fpr, 0,
+				 32 * sizeof(vector128));
+
+	return ret;
+}
+#endif /* CONFIG_VSX */
+
 #ifdef CONFIG_SPE
 
 /*
@@ -426,6 +471,9 @@ enum powerpc_regset {
 #ifdef CONFIG_ALTIVEC
 	REGSET_VMX,
 #endif
+#ifdef CONFIG_VSX
+	REGSET_VSX,
+#endif
 #ifdef CONFIG_SPE
 	REGSET_SPE,
 #endif
@@ -449,6 +497,13 @@ static const struct user_regset native_regsets[] = {
 		.active = vr_active, .get = vr_get, .set = vr_set
 	},
 #endif
+#ifdef CONFIG_VSX
+	[REGSET_VSX] = {
+		.n = 32,
+		.size = sizeof(vector128), .align = sizeof(vector128),
+		.active = vsr_active, .get = vsr_get, .set = vsr_set
+	},
+#endif
 #ifdef CONFIG_SPE
 	[REGSET_SPE] = {
 		.n = 35,
@@ -849,6 +904,21 @@ long arch_ptrace(struct task_struct *child, long request, long addr, long data)
 						 sizeof(u32)),
 					     (const void __user *) data);
 #endif
+#ifdef CONFIG_VSX
+	case PTRACE_GETVSRREGS:
+		return copy_regset_to_user(child, &user_ppc_native_view,
+					   REGSET_VSX,
+					   0, (32 * sizeof(vector128) +
+					       sizeof(u32)),
+					   (void __user *) data);
+
+	case PTRACE_SETVSRREGS:
+		return copy_regset_from_user(child, &user_ppc_native_view,
+					     REGSET_VSX,
+					     0, (32 * sizeof(vector128) +
+						 sizeof(u32)),
+					     (const void __user *) data);
+#endif
 #ifdef CONFIG_SPE
 	case PTRACE_GETEVRREGS:
 		/* Get the child spe register state. */
diff --git a/arch/powerpc/kernel/signal_32.c b/arch/powerpc/kernel/signal_32.c
index f7fa395..349d348 100644
--- a/arch/powerpc/kernel/signal_32.c
+++ b/arch/powerpc/kernel/signal_32.c
@@ -378,6 +378,21 @@ static int save_user_regs(struct pt_regs *regs, struct mcontext __user *frame,
 	memcpy(&buf[i], &current->thread.fpscr, sizeof(double));
 	if (__copy_to_user(&frame->mc_fregs, buf, ELF_NFPREG * sizeof(double)))
 		return 1;
+	/*
+	 * Copy VSR 0-31 upper half from thread_struct to local
+	 * buffer, then write that to userspace.  Also set MSR_VSX in
+	 * the saved MSR value to indicate that frame->mc_vregs
+	 * contains valid data
+	 */
+	if (current->thread.used_vsr) {
+		flush_vsx_to_thread(current);
+		for (i = 0; i < 32 ; i++)
+			buf[i] = current->thread.fpr[i][TS_VSRLOWOFFSET];
+		if (__copy_to_user(&frame->mc_vsregs, buf,
+				   ELF_NVSRHALFREG  * sizeof(double)))
+			return 1;
+		msr |= MSR_VSX;
+	}
 #else
 	/* save floating-point registers */
 	if (__copy_to_user(&frame->mc_fregs, current->thread.fpr,
@@ -482,6 +497,24 @@ static long restore_user_regs(struct pt_regs *regs,
 	for (i = 0; i < 32 ; i++)
 		current->thread.TS_FPR(i) = buf[i];
 	memcpy(&current->thread.fpscr, &buf[i], sizeof(double));
+	/*
+	 * Force the process to reload the VSX registers from
+	 * current->thread when it next does VSX instruction.
+	 */
+	regs->msr &= ~MSR_VSX;
+	if (msr & MSR_VSX) {
+		/*
+		 * Restore altivec registers from the stack to a local
+		 * buffer, then write this out to the thread_struct
+		 */
+		if (__copy_from_user(buf, &sr->mc_vsregs,
+				     sizeof(sr->mc_vsregs)))
+			return 1;
+		for (i = 0; i < 32 ; i++)
+			current->thread.fpr[i][TS_VSRLOWOFFSET] = buf[i];
+	} else if (current->thread.used_vsr)
+		for (i = 0; i < 32 ; i++)
+			current->thread.fpr[i][TS_VSRLOWOFFSET] = 0;
 #else
 	if (__copy_from_user(current->thread.fpr, &sr->mc_fregs,
 			     sizeof(sr->mc_fregs)))
diff --git a/arch/powerpc/kernel/signal_64.c b/arch/powerpc/kernel/signal_64.c
index a587b33..34f37e5 100644
--- a/arch/powerpc/kernel/signal_64.c
+++ b/arch/powerpc/kernel/signal_64.c
@@ -123,6 +123,22 @@ static long setup_sigcontext(struct sigcontext __user *sc, struct pt_regs *regs,
 		buf[i] = current->thread.TS_FPR(i);
 	memcpy(&buf[i], &current->thread.fpscr, sizeof(double));
 	err |= __copy_to_user(&sc->fp_regs, buf, FP_REGS_SIZE);
+	/*
+	 * Copy VSX low doubleword to local buffer for formatting,
+	 * then out to userspace.  Update v_regs to point after the
+	 * VMX data.
+	 */
+	if (current->thread.used_vsr) {
+		flush_vsx_to_thread(current);
+		v_regs += ELF_NVRREG;
+		for (i = 0; i < 32 ; i++)
+			buf[i] = current->thread.fpr[i][TS_VSRLOWOFFSET];
+		err |= __copy_to_user(v_regs, buf, 32 * sizeof(double));
+		/* set MSR_VSX in the MSR value in the frame to
+		 * indicate that sc->vs_reg) contains valid data.
+		 */
+		msr |= MSR_VSX;
+	}
 #else /* CONFIG_VSX */
 	/* copy fpr regs and fpscr */
 	err |= __copy_to_user(&sc->fp_regs, &current->thread.fpr, FP_REGS_SIZE);
@@ -197,7 +213,7 @@ static long restore_sigcontext(struct pt_regs *regs, sigset_t *set, int sig,
 	 * This has to be done before copying stuff into current->thread.fpr/vr
 	 * for the reasons explained in the previous comment.
 	 */
-	regs->msr &= ~(MSR_FP | MSR_FE0 | MSR_FE1 | MSR_VEC);
+	regs->msr &= ~(MSR_FP | MSR_FE0 | MSR_FE1 | MSR_VEC | MSR_VSX);
 
 #ifdef CONFIG_ALTIVEC
 	err |= __get_user(v_regs, &sc->v_regs);
@@ -226,6 +242,19 @@ static long restore_sigcontext(struct pt_regs *regs, sigset_t *set, int sig,
 		current->thread.TS_FPR(i) = buf[i];
 	memcpy(&current->thread.fpscr, &buf[i], sizeof(double));
 
+	/*
+	 * Get additional VSX data. Update v_regs to point after the
+	 * VMX data.  Copy VSX low doubleword from userspace to local
+	 * buffer for formatting, then into the taskstruct.
+	 */
+	v_regs += ELF_NVRREG;
+	if ((msr & MSR_VSX) != 0)
+		err |= __copy_from_user(buf, v_regs, 32 * sizeof(double));
+	else
+		memset(buf, 0, 32 * sizeof(double));
+
+	for (i = 0; i < 32 ; i++)
+		current->thread.fpr[i][TS_VSRLOWOFFSET] = buf[i];
 #else
 	err |= __copy_from_user(&current->thread.fpr, &sc->fp_regs, FP_REGS_SIZE);
 #endif
diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c
index b463d48..878fbdd 100644
--- a/arch/powerpc/kernel/traps.c
+++ b/arch/powerpc/kernel/traps.c
@@ -967,6 +967,20 @@ void altivec_unavailable_exception(struct pt_regs *regs)
 	die("Unrecoverable VMX/Altivec Unavailable Exception", regs, SIGABRT);
 }
 
+void vsx_unavailable_exception(struct pt_regs *regs)
+{
+	if (user_mode(regs)) {
+		/* A user program has executed an vsx instruction,
+		   but this kernel doesn't support vsx. */
+		_exception(SIGILL, regs, ILL_ILLOPC, regs->nip);
+		return;
+	}
+
+	printk(KERN_EMERG "Unrecoverable VSX Unavailable Exception "
+			"%lx at %lx\n", regs->trap, regs->nip);
+	die("Unrecoverable VSX Unavailable Exception", regs, SIGABRT);
+}
+
 void performance_monitor_exception(struct pt_regs *regs)
 {
 	perf_irq(regs);
@@ -1099,6 +1113,21 @@ void altivec_assist_exception(struct pt_regs *regs)
 }
 #endif /* CONFIG_ALTIVEC */
 
+#ifdef CONFIG_VSX
+void vsx_assist_exception(struct pt_regs *regs)
+{
+	if (!user_mode(regs)) {
+		printk(KERN_EMERG "VSX assist exception in kernel mode"
+		       " at %lx\n", regs->nip);
+		die("Kernel VSX assist exception", regs, SIGILL);
+	}
+
+	flush_vsx_to_thread(current);
+	printk(KERN_INFO "VSX assist not supported at %lx\n", regs->nip);
+	_exception(SIGILL, regs, ILL_ILLOPC, regs->nip);
+}
+#endif /* CONFIG_VSX */
+
 #ifdef CONFIG_FSL_BOOKE
 void CacheLockingException(struct pt_regs *regs, unsigned long address,
 			   unsigned long error_code)
diff --git a/include/asm-powerpc/elf.h b/include/asm-powerpc/elf.h
index d1e3bda..746e53d 100644
--- a/include/asm-powerpc/elf.h
+++ b/include/asm-powerpc/elf.h
@@ -109,6 +109,7 @@ typedef elf_gregset_t32 compat_elf_gregset_t;
 #ifdef __powerpc64__
 # define ELF_NVRREG32	33	/* includes vscr & vrsave stuffed together */
 # define ELF_NVRREG	34	/* includes vscr & vrsave in split vectors */
+# define ELF_NVSRHALFREG 32	/* Half the vsx registers */
 # define ELF_GREG_TYPE	elf_greg_t64
 #else
 # define ELF_NEVRREG	34	/* includes acc (as 2) */
@@ -158,6 +159,7 @@ typedef __vector128 elf_vrreg_t;
 typedef elf_vrreg_t elf_vrregset_t[ELF_NVRREG];
 #ifdef __powerpc64__
 typedef elf_vrreg_t elf_vrregset_t32[ELF_NVRREG32];
+typedef elf_fpreg_t elf_vsrreghalf_t32[ELF_NVSRHALFREG];
 #endif
 
 #ifdef __KERNEL__
@@ -219,8 +221,8 @@ extern int dump_task_fpu(struct task_struct *, elf_fpregset_t *);
 typedef elf_vrregset_t elf_fpxregset_t;
 
 #ifdef CONFIG_ALTIVEC
-extern int dump_task_altivec(struct task_struct *, elf_vrregset_t *vrregs);
-#define ELF_CORE_COPY_XFPREGS(tsk, regs) dump_task_altivec(tsk, regs)
+extern int dump_task_vector(struct task_struct *, elf_vrregset_t *vrregs);
+#define ELF_CORE_COPY_XFPREGS(tsk, regs) dump_task_vector(tsk, regs)
 #define ELF_CORE_XFPREG_TYPE NT_PPC_VMX
 #endif
 
diff --git a/include/asm-powerpc/ptrace.h b/include/asm-powerpc/ptrace.h
index 38d87e5..3d6e310 100644
--- a/include/asm-powerpc/ptrace.h
+++ b/include/asm-powerpc/ptrace.h
@@ -224,6 +224,14 @@ extern void user_disable_single_step(struct task_struct *);
 #define PT_VRSAVE_32 (PT_VR0 + 33*4)
 #endif
 
+/*
+ * Only store first 32 VSRs here. The second 32 VSRs in VR0-31
+ */
+#define PT_VSR0 150	/* each VSR reg occupies 2 slots in 64-bit */
+#define PT_VSR31 (PT_VSR0 + 2*31)
+#ifdef __KERNEL__
+#define PT_VSR0_32 300 	/* each VSR reg occupies 4 slots in 32-bit */
+#endif
 #endif /* __powerpc64__ */
 
 /*
@@ -246,6 +254,10 @@ extern void user_disable_single_step(struct task_struct *);
 #define PTRACE_GETEVRREGS	20
 #define PTRACE_SETEVRREGS	21
 
+/* Get the first 32 128bit VSX registers */
+#define PTRACE_GETVSRREGS	27
+#define PTRACE_SETVSRREGS	28
+
 /*
  * Get or set a debug register. The first 16 are DABR registers and the
  * second 16 are IABR registers.
diff --git a/include/asm-powerpc/reg.h b/include/asm-powerpc/reg.h
index 7256efb..bbccadf 100644
--- a/include/asm-powerpc/reg.h
+++ b/include/asm-powerpc/reg.h
@@ -30,6 +30,7 @@
 #define MSR_ISF_LG	61              /* Interrupt 64b mode valid on 630 */
 #define MSR_HV_LG 	60              /* Hypervisor state */
 #define MSR_VEC_LG	25	        /* Enable AltiVec */
+#define MSR_VSX_LG	23		/* Enable VSX */
 #define MSR_POW_LG	18		/* Enable Power Management */
 #define MSR_WE_LG	18		/* Wait State Enable */
 #define MSR_TGPR_LG	17		/* TLB Update registers in use */
@@ -71,6 +72,7 @@
 #endif
 
 #define MSR_VEC		__MASK(MSR_VEC_LG)	/* Enable AltiVec */
+#define MSR_VSX		__MASK(MSR_VSX_LG)	/* Enable VSX */
 #define MSR_POW		__MASK(MSR_POW_LG)	/* Enable Power Management */
 #define MSR_WE		__MASK(MSR_WE_LG)	/* Wait State Enable */
 #define MSR_TGPR	__MASK(MSR_TGPR_LG)	/* TLB Update registers in use */
diff --git a/include/asm-powerpc/sigcontext.h b/include/asm-powerpc/sigcontext.h
index 165d630..9c1f24f 100644
--- a/include/asm-powerpc/sigcontext.h
+++ b/include/asm-powerpc/sigcontext.h
@@ -43,9 +43,44 @@ struct sigcontext {
  * it must be copied via a vector register to/from storage) or as a word.
  * The entry with index 33 contains the vrsave as the first word (offset 0)
  * within the quadword.
+ *
+ * Part of the VSX data is stored here also by extending vmx_restore
+ * by an additional 32 double words.  Architecturally the layout of
+ * the VSR registers and how they overlap on top of the legacy FPR and
+ * VR registers is shown below:
+ *
+ *                    VSR doubleword 0               VSR doubleword 1
+ *           ----------------------------------------------------------------
+ *   VSR[0]  |             FPR[0]            |                              |
+ *           ----------------------------------------------------------------
+ *   VSR[1]  |             FPR[1]            |                              |
+ *           ----------------------------------------------------------------
+ *           |              ...              |                              |
+ *           |              ...              |                              |
+ *           ----------------------------------------------------------------
+ *   VSR[30] |             FPR[30]           |                              |
+ *           ----------------------------------------------------------------
+ *   VSR[31] |             FPR[31]           |                              |
+ *           ----------------------------------------------------------------
+ *   VSR[32] |                             VR[0]                            |
+ *           ----------------------------------------------------------------
+ *   VSR[33] |                             VR[1]                            |
+ *           ----------------------------------------------------------------
+ *           |                              ...                             |
+ *           |                              ...                             |
+ *           ----------------------------------------------------------------
+ *   VSR[62] |                             VR[30]                           |
+ *           ----------------------------------------------------------------
+ *   VSR[63] |                             VR[31]                           |
+ *           ----------------------------------------------------------------
+ *
+ * FPR/VSR 0-31 doubleword 0 is stored in fp_regs, and VMX/VSR 32-63
+ * is stored at the start of vmx_reserve.  vmx_reserve is extended for
+ * backwards compatility to store VSR 0-31 doubleword 1 after the VMX
+ * registers and vscr/vrsave.
  */
 	elf_vrreg_t	__user *v_regs;
-	long		vmx_reserve[ELF_NVRREG+ELF_NVRREG+1];
+	long		vmx_reserve[ELF_NVRREG+ELF_NVRREG+32+1];
 #endif
 };
 
diff --git a/include/asm-powerpc/system.h b/include/asm-powerpc/system.h
index 2642a92..0c12c66 100644
--- a/include/asm-powerpc/system.h
+++ b/include/asm-powerpc/system.h
@@ -139,6 +139,7 @@ extern void enable_kernel_altivec(void);
 extern void giveup_altivec(struct task_struct *);
 extern void load_up_altivec(struct task_struct *);
 extern int emulate_altivec(struct pt_regs *);
+extern void giveup_vsx(struct task_struct *);
 extern void enable_kernel_spe(void);
 extern void giveup_spe(struct task_struct *);
 extern void load_up_spe(struct task_struct *);
@@ -162,6 +163,14 @@ static inline void flush_altivec_to_thread(struct task_struct *t)
 }
 #endif
 
+#ifdef CONFIG_VSX
+extern void flush_vsx_to_thread(struct task_struct *);
+#else
+static inline void flush_vsx_to_thread(struct task_struct *t)
+{
+}
+#endif
+
 #ifdef CONFIG_SPE
 extern void flush_spe_to_thread(struct task_struct *);
 #else