/* Bits in the flags field */
#define LD 0 /* load */
#define ST 1 /* store */
-#define SE 2 /* sign-extend value */
+#define SE 2 /* sign-extend value, or FP ld/st as word */
#define F 4 /* to/from fp regs */
#define U 8 /* update index register */
#define M 0x10 /* multiple load/store */
#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 */
{ 8, LD+F+U }, /* 00 1 1001: lfdu */
{ 4, ST+F+S+U }, /* 00 1 1010: stfsu */
{ 8, ST+F+U }, /* 00 1 1011: stfdu */
- INVALID, /* 00 1 1100 */
+ { 16, LD+F }, /* 00 1 1100: lfdp */
INVALID, /* 00 1 1101 */
- INVALID, /* 00 1 1110 */
+ { 16, ST+F }, /* 00 1 1110: stfdp */
INVALID, /* 00 1 1111 */
{ 8, LD }, /* 01 0 0000: ldx */
INVALID, /* 01 0 0001 */
{ 8, LD+F }, /* 11 0 1001: lfdx */
{ 4, ST+F+S }, /* 11 0 1010: stfsx */
{ 8, ST+F }, /* 11 0 1011: stfdx */
- INVALID, /* 11 0 1100 */
- { 8, LD+M }, /* 11 0 1101: lmd */
- INVALID, /* 11 0 1110 */
- { 8, ST+M }, /* 11 0 1111: stmd */
+ { 16, LD+F }, /* 11 0 1100: lfdpx */
+ { 4, LD+F+SE }, /* 11 0 1101: lfiwax */
+ { 16, ST+F }, /* 11 0 1110: stfdpx */
+ { 4, ST+F }, /* 11 0 1111: stfiwx */
{ 4, LD+U }, /* 11 1 0000: lwzux */
INVALID, /* 11 1 0001 */
{ 4, ST+U }, /* 11 1 0010: stwux */
if (user_mode(regs) && !access_ok(VERIFY_WRITE, p, size))
return -EFAULT;
for (i = 0; i < size / sizeof(long); ++i)
- if (__put_user(0, p+i))
+ if (__put_user_inatomic(0, p+i))
return -EFAULT;
return 1;
}
} else {
unsigned long pc = regs->nip ^ (swiz & 4);
- if (__get_user(instr, (unsigned int __user *)pc))
+ if (__get_user_inatomic(instr,
+ (unsigned int __user *)pc))
return -EFAULT;
if (swiz == 0 && (flags & SW))
instr = cpu_to_le32(instr);
((nb0 + 3) / 4) * sizeof(unsigned long));
for (i = 0; i < nb; ++i, ++p)
- if (__get_user(REG_BYTE(rptr, i ^ bswiz), SWIZ_PTR(p)))
+ if (__get_user_inatomic(REG_BYTE(rptr, i ^ bswiz),
+ SWIZ_PTR(p)))
return -EFAULT;
if (nb0 > 0) {
rptr = ®s->gpr[0];
addr += nb;
for (i = 0; i < nb0; ++i, ++p)
- if (__get_user(REG_BYTE(rptr, i ^ bswiz),
- SWIZ_PTR(p)))
+ if (__get_user_inatomic(REG_BYTE(rptr,
+ i ^ bswiz),
+ SWIZ_PTR(p)))
return -EFAULT;
}
} else {
for (i = 0; i < nb; ++i, ++p)
- if (__put_user(REG_BYTE(rptr, i ^ bswiz), SWIZ_PTR(p)))
+ if (__put_user_inatomic(REG_BYTE(rptr, i ^ bswiz),
+ SWIZ_PTR(p)))
return -EFAULT;
if (nb0 > 0) {
rptr = ®s->gpr[0];
addr += nb;
for (i = 0; i < nb0; ++i, ++p)
- if (__put_user(REG_BYTE(rptr, i ^ bswiz),
- SWIZ_PTR(p)))
+ if (__put_user_inatomic(REG_BYTE(rptr,
+ i ^ bswiz),
+ SWIZ_PTR(p)))
return -EFAULT;
}
}
return 1;
}
+/*
+ * Emulate floating-point pair loads and stores.
+ * Only POWER6 has these instructions, and it does true little-endian,
+ * so we don't need the address swizzling.
+ */
+static int emulate_fp_pair(struct pt_regs *regs, unsigned char __user *addr,
+ unsigned int reg, unsigned int flags)
+{
+ char *ptr = (char *) ¤t->thread.fpr[reg];
+ int i, ret;
+
+ if (!(flags & F))
+ return 0;
+ if (reg & 1)
+ return 0; /* invalid form: FRS/FRT must be even */
+ if (!(flags & SW)) {
+ /* not byte-swapped - easy */
+ if (!(flags & ST))
+ ret = __copy_from_user(ptr, addr, 16);
+ else
+ ret = __copy_to_user(addr, ptr, 16);
+ } else {
+ /* each FPR value is byte-swapped separately */
+ ret = 0;
+ for (i = 0; i < 16; ++i) {
+ if (!(flags & ST))
+ ret |= __get_user(ptr[i^7], addr + i);
+ else
+ ret |= __put_user(ptr[i^7], addr + i);
+ }
+ }
+ if (ret)
+ return -EFAULT;
+ 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 = ¤t->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
if (cpu_has_feature(CPU_FTR_PPC_LE) && (regs->msr & MSR_LE))
pc ^= 4;
- if (unlikely(__get_user(instr, (unsigned int __user *)pc)))
+ if (unlikely(__get_user_inatomic(instr,
+ (unsigned int __user *)pc)))
return -EFAULT;
if (cpu_has_feature(CPU_FTR_REAL_LE) && (regs->msr & MSR_LE))
instr = cpu_to_le32(instr);
/* 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;
flush_fp_to_thread(current);
}
+ /* Special case for 16-byte FP loads and stores */
+ if (nb == 16)
+ return emulate_fp_pair(regs, addr, reg, flags);
+
/* If we are loading, get the data from user space, else
* get it from register values
*/
p = (unsigned long) addr;
switch (nb) {
case 8:
- ret |= __get_user(data.v[0], SWIZ_PTR(p++));
- ret |= __get_user(data.v[1], SWIZ_PTR(p++));
- ret |= __get_user(data.v[2], SWIZ_PTR(p++));
- ret |= __get_user(data.v[3], SWIZ_PTR(p++));
+ ret |= __get_user_inatomic(data.v[0], SWIZ_PTR(p++));
+ ret |= __get_user_inatomic(data.v[1], SWIZ_PTR(p++));
+ ret |= __get_user_inatomic(data.v[2], SWIZ_PTR(p++));
+ ret |= __get_user_inatomic(data.v[3], SWIZ_PTR(p++));
case 4:
- ret |= __get_user(data.v[4], SWIZ_PTR(p++));
- ret |= __get_user(data.v[5], SWIZ_PTR(p++));
+ ret |= __get_user_inatomic(data.v[4], SWIZ_PTR(p++));
+ ret |= __get_user_inatomic(data.v[5], SWIZ_PTR(p++));
case 2:
- ret |= __get_user(data.v[6], SWIZ_PTR(p++));
- ret |= __get_user(data.v[7], SWIZ_PTR(p++));
+ ret |= __get_user_inatomic(data.v[6], SWIZ_PTR(p++));
+ ret |= __get_user_inatomic(data.v[7], SWIZ_PTR(p++));
if (unlikely(ret))
return -EFAULT;
}
* or floating point single precision conversion
*/
switch (flags & ~(U|SW)) {
- case LD+SE: /* sign extend */
+ case LD+SE: /* sign extending integer loads */
+ case LD+F+SE: /* sign extend for lfiwax */
if ( nb == 2 )
data.ll = data.x16.low16;
else /* nb must be 4 */
p = (unsigned long) addr;
switch (nb) {
case 8:
- ret |= __put_user(data.v[0], SWIZ_PTR(p++));
- ret |= __put_user(data.v[1], SWIZ_PTR(p++));
- ret |= __put_user(data.v[2], SWIZ_PTR(p++));
- ret |= __put_user(data.v[3], SWIZ_PTR(p++));
+ ret |= __put_user_inatomic(data.v[0], SWIZ_PTR(p++));
+ ret |= __put_user_inatomic(data.v[1], SWIZ_PTR(p++));
+ ret |= __put_user_inatomic(data.v[2], SWIZ_PTR(p++));
+ ret |= __put_user_inatomic(data.v[3], SWIZ_PTR(p++));
case 4:
- ret |= __put_user(data.v[4], SWIZ_PTR(p++));
- ret |= __put_user(data.v[5], SWIZ_PTR(p++));
+ ret |= __put_user_inatomic(data.v[4], SWIZ_PTR(p++));
+ ret |= __put_user_inatomic(data.v[5], SWIZ_PTR(p++));
case 2:
- ret |= __put_user(data.v[6], SWIZ_PTR(p++));
- ret |= __put_user(data.v[7], SWIZ_PTR(p++));
+ ret |= __put_user_inatomic(data.v[6], SWIZ_PTR(p++));
+ ret |= __put_user_inatomic(data.v[7], SWIZ_PTR(p++));
}
if (unlikely(ret))
return -EFAULT;
projects / linux-2.6-omap-h63xx.git / blobdiff