[POWERPC] Handle alignment faults on SPE load/store instructions

This adds code to handle alignment traps generated by the following
SPE (signal processing engine) load/store instructions, by emulating
the instruction in the kernel (as is done for other instructions that
generate alignment traps):

evldd[x]         Vector Load Double Word into Double Word [Indexed]
evldw[x]         Vector Load Double into Two Words [Indexed]
evldh[x]         Vector Load Double into Four Half Words [Indexed]
evlhhesplat[x]   Vector Load Half Word into Half Words Even and Splat [Indexed]
evlhhousplat[x]  Vector Load Half Word into Half Word Odd Unsigned and Splat [Indexed]
evlhhossplat[x]  Vector Load Half Word into Half Word Odd Signed and Splat [Indexed]
evlwhe[x]        Vector Load Word into Two Half Words Even [Indexed]
evlwhou[x]       Vector Load Word into Two Half Words Odd Unsigned (zero-extended) [Indexed]
evlwhos[x]       Vector Load Word into Two Half Words Odd Signed (with sign extension) [Indexed]
evlwwsplat[x]    Vector Load Word into Word and Splat [Indexed]
evlwhsplat[x]    Vector Load Word into Two Half Words and Splat [Indexed]
evstdd[x]        Vector Store Double of Double [Indexed]
evstdw[x]        Vector Store Double of Two Words [Indexed]
evstdh[x]        Vector Store Double of Four Half Words [Indexed]
evstwhe[x]       Vector Store Word of Two Half Words from Even [Indexed]
evstwho[x]       Vector Store Word of Two Half Words from Odd [Indexed]
evstwwe[x]       Vector Store Word of Word from Even [Indexed]
evstwwo[x]       Vector Store Word of Word from Odd [Indexed]

Signed-off-by: Kumar Gala <galak@kernel.crashing.org>

arch/powerpc/kernel/align.c

@@ -46,6 +46,8 @@ struct aligninfo {
 #define S	0x40	/* single-precision fp or... */
 #define SX	0x40	/* ... byte count in XER */
 #define HARD	0x80	/* string, stwcx. */
+#define E4	0x40	/* SPE endianness is word */
+#define E8	0x80	/* SPE endianness is double word */
 
 /* DSISR bits reported for a DCBZ instruction: */
 #define DCBZ	0x5f	/* 8xx/82xx dcbz faults when cache not enabled */
@@ -392,6 +394,248 @@ static int emulate_fp_pair(struct pt_regs *regs, unsigned char __user *addr,
 	return 1;	/* exception handled and fixed up */
 }
 
+#ifdef CONFIG_SPE
+
+static struct aligninfo spe_aligninfo[32] = {
+	{ 8, LD+E8 },		/* 0 00 00: evldd[x] */
+	{ 8, LD+E4 },		/* 0 00 01: evldw[x] */
+	{ 8, LD },		/* 0 00 10: evldh[x] */
+	INVALID,		/* 0 00 11 */
+	{ 2, LD },		/* 0 01 00: evlhhesplat[x] */
+	INVALID,		/* 0 01 01 */
+	{ 2, LD },		/* 0 01 10: evlhhousplat[x] */
+	{ 2, LD+SE },		/* 0 01 11: evlhhossplat[x] */
+	{ 4, LD },		/* 0 10 00: evlwhe[x] */
+	INVALID,		/* 0 10 01 */
+	{ 4, LD },		/* 0 10 10: evlwhou[x] */
+	{ 4, LD+SE },		/* 0 10 11: evlwhos[x] */
+	{ 4, LD+E4 },		/* 0 11 00: evlwwsplat[x] */
+	INVALID,		/* 0 11 01 */
+	{ 4, LD },		/* 0 11 10: evlwhsplat[x] */
+	INVALID,		/* 0 11 11 */
+
+	{ 8, ST+E8 },		/* 1 00 00: evstdd[x] */
+	{ 8, ST+E4 },		/* 1 00 01: evstdw[x] */
+	{ 8, ST },		/* 1 00 10: evstdh[x] */
+	INVALID,		/* 1 00 11 */
+	INVALID,		/* 1 01 00 */
+	INVALID,		/* 1 01 01 */
+	INVALID,		/* 1 01 10 */
+	INVALID,		/* 1 01 11 */
+	{ 4, ST },		/* 1 10 00: evstwhe[x] */
+	INVALID,		/* 1 10 01 */
+	{ 4, ST },		/* 1 10 10: evstwho[x] */
+	INVALID,		/* 1 10 11 */
+	{ 4, ST+E4 },		/* 1 11 00: evstwwe[x] */
+	INVALID,		/* 1 11 01 */
+	{ 4, ST+E4 },		/* 1 11 10: evstwwo[x] */
+	INVALID,		/* 1 11 11 */
+};
+
+#define	EVLDD		0x00
+#define	EVLDW		0x01
+#define	EVLDH		0x02
+#define	EVLHHESPLAT	0x04
+#define	EVLHHOUSPLAT	0x06
+#define	EVLHHOSSPLAT	0x07
+#define	EVLWHE		0x08
+#define	EVLWHOU		0x0A
+#define	EVLWHOS		0x0B
+#define	EVLWWSPLAT	0x0C
+#define	EVLWHSPLAT	0x0E
+#define	EVSTDD		0x10
+#define	EVSTDW		0x11
+#define	EVSTDH		0x12
+#define	EVSTWHE		0x18
+#define	EVSTWHO		0x1A
+#define	EVSTWWE		0x1C
+#define	EVSTWWO		0x1E
+
+/*
+ * Emulate SPE loads and stores.
+ * Only Book-E has these instructions, and it does true little-endian,
+ * so we don't need the address swizzling.
+ */
+static int emulate_spe(struct pt_regs *regs, unsigned int reg,
+		       unsigned int instr)
+{
+	int t, ret;
+	union {
+		u64 ll;
+		u32 w[2];
+		u16 h[4];
+		u8 v[8];
+	} data, temp;
+	unsigned char __user *p, *addr;
+	unsigned long *evr = &current->thread.evr[reg];
+	unsigned int nb, flags;
+
+	instr = (instr >> 1) & 0x1f;
+
+	/* DAR has the operand effective address */
+	addr = (unsigned char __user *)regs->dar;
+
+	nb = spe_aligninfo[instr].len;
+	flags = spe_aligninfo[instr].flags;
+
+	/* Verify the address of the operand */
+	if (unlikely(user_mode(regs) &&
+		     !access_ok((flags & ST ? VERIFY_WRITE : VERIFY_READ),
+				addr, nb)))
+		return -EFAULT;
+
+	/* userland only */
+	if (unlikely(!user_mode(regs)))
+		return 0;
+
+	flush_spe_to_thread(current);
+
+	/* If we are loading, get the data from user space, else
+	 * get it from register values
+	 */
+	if (flags & ST) {
+		data.ll = 0;
+		switch (instr) {
+		case EVSTDD:
+		case EVSTDW:
+		case EVSTDH:
+			data.w[0] = *evr;
+			data.w[1] = regs->gpr[reg];
+			break;
+		case EVSTWHE:
+			data.h[2] = *evr >> 16;
+			data.h[3] = regs->gpr[reg] >> 16;
+			break;
+		case EVSTWHO:
+			data.h[2] = *evr & 0xffff;
+			data.h[3] = regs->gpr[reg] & 0xffff;
+			break;
+		case EVSTWWE:
+			data.w[1] = *evr;
+			break;
+		case EVSTWWO:
+			data.w[1] = regs->gpr[reg];
+			break;
+		default:
+			return -EINVAL;
+		}
+	} else {
+		temp.ll = data.ll = 0;
+		ret = 0;
+		p = addr;
+
+		switch (nb) {
+		case 8:
+			ret |= __get_user_inatomic(temp.v[0], p++);
+			ret |= __get_user_inatomic(temp.v[1], p++);
+			ret |= __get_user_inatomic(temp.v[2], p++);
+			ret |= __get_user_inatomic(temp.v[3], p++);
+		case 4:
+			ret |= __get_user_inatomic(temp.v[4], p++);
+			ret |= __get_user_inatomic(temp.v[5], p++);
+		case 2:
+			ret |= __get_user_inatomic(temp.v[6], p++);
+			ret |= __get_user_inatomic(temp.v[7], p++);
+			if (unlikely(ret))
+				return -EFAULT;
+		}
+
+		switch (instr) {
+		case EVLDD:
+		case EVLDW:
+		case EVLDH:
+			data.ll = temp.ll;
+			break;
+		case EVLHHESPLAT:
+			data.h[0] = temp.h[3];
+			data.h[2] = temp.h[3];
+			break;
+		case EVLHHOUSPLAT:
+		case EVLHHOSSPLAT:
+			data.h[1] = temp.h[3];
+			data.h[3] = temp.h[3];
+			break;
+		case EVLWHE:
+			data.h[0] = temp.h[2];
+			data.h[2] = temp.h[3];
+			break;
+		case EVLWHOU:
+		case EVLWHOS:
+			data.h[1] = temp.h[2];
+			data.h[3] = temp.h[3];
+			break;
+		case EVLWWSPLAT:
+			data.w[0] = temp.w[1];
+			data.w[1] = temp.w[1];
+			break;
+		case EVLWHSPLAT:
+			data.h[0] = temp.h[2];
+			data.h[1] = temp.h[2];
+			data.h[2] = temp.h[3];
+			data.h[3] = temp.h[3];
+			break;
+		default:
+			return -EINVAL;
+		}
+	}
+
+	if (flags & SW) {
+		switch (flags & 0xf0) {
+		case E8:
+			SWAP(data.v[0], data.v[7]);
+			SWAP(data.v[1], data.v[6]);
+			SWAP(data.v[2], data.v[5]);
+			SWAP(data.v[3], data.v[4]);
+			break;
+		case E4:
+
+			SWAP(data.v[0], data.v[3]);
+			SWAP(data.v[1], data.v[2]);
+			SWAP(data.v[4], data.v[7]);
+			SWAP(data.v[5], data.v[6]);
+			break;
+		/* Its half word endian */
+		default:
+			SWAP(data.v[0], data.v[1]);
+			SWAP(data.v[2], data.v[3]);
+			SWAP(data.v[4], data.v[5]);
+			SWAP(data.v[6], data.v[7]);
+			break;
+		}
+	}
+
+	if (flags & SE) {
+		data.w[0] = (s16)data.h[1];
+		data.w[1] = (s16)data.h[3];
+	}
+
+	/* Store result to memory or update registers */
+	if (flags & ST) {
+		ret = 0;
+		p = addr;
+		switch (nb) {
+		case 8:
+			ret |= __put_user_inatomic(data.v[0], p++);
+			ret |= __put_user_inatomic(data.v[1], p++);
+			ret |= __put_user_inatomic(data.v[2], p++);
+			ret |= __put_user_inatomic(data.v[3], p++);
+		case 4:
+			ret |= __put_user_inatomic(data.v[4], p++);
+			ret |= __put_user_inatomic(data.v[5], p++);
+		case 2:
+			ret |= __put_user_inatomic(data.v[6], p++);
+			ret |= __put_user_inatomic(data.v[7], p++);
+		}
+		if (unlikely(ret))
+			return -EFAULT;
+	} else {
+		*evr = data.w[0];
+		regs->gpr[reg] = data.w[1];
+	}
+
+	return 1;
+}
+#endif /* CONFIG_SPE */
 
 /*
  * Called on alignment exception. Attempts to fixup
@@ -450,6 +694,12 @@ int fix_alignment(struct pt_regs *regs)
 	/* extract the operation and registers from the dsisr */
 	reg = (dsisr >> 5) & 0x1f;	/* source/dest register */
 	areg = dsisr & 0x1f;		/* register to update */
+
+#ifdef CONFIG_SPE
+	if ((instr >> 26) == 0x4)
+		return emulate_spe(regs, reg, instr);
+#endif
+
 	instr = (dsisr >> 10) & 0x7f;
 	instr |= (dsisr >> 13) & 0x60;