powerpc: Handle VSX alignment faults correctly in little-endian mode
This patch fixes the handling of VSX alignment faults in little-endian mode (the current code assumes the processor is in big-endian mode). The patch also makes the handlers clear the top 8 bytes of the register when handling an 8 byte VSX load. This is based on 2.6.32. Signed-off-by: Neil Campbell <neilc@linux.vnet.ibm.com> Cc: <stable@kernel.org> Acked-by: Michael Neuling <mikey@neuling.org> Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
This commit is contained in:
parent
f04b10cddb
commit
bb7f20b1c6
|
@ -642,10 +642,14 @@ static int emulate_spe(struct pt_regs *regs, unsigned int reg,
|
|||
*/
|
||||
static int emulate_vsx(unsigned char __user *addr, unsigned int reg,
|
||||
unsigned int areg, struct pt_regs *regs,
|
||||
unsigned int flags, unsigned int length)
|
||||
unsigned int flags, unsigned int length,
|
||||
unsigned int elsize)
|
||||
{
|
||||
char *ptr;
|
||||
unsigned long *lptr;
|
||||
int ret = 0;
|
||||
int sw = 0;
|
||||
int i, j;
|
||||
|
||||
flush_vsx_to_thread(current);
|
||||
|
||||
|
@ -654,19 +658,35 @@ static int emulate_vsx(unsigned char __user *addr, unsigned int reg,
|
|||
else
|
||||
ptr = (char *) ¤t->thread.vr[reg - 32];
|
||||
|
||||
if (flags & ST)
|
||||
ret = __copy_to_user(addr, ptr, length);
|
||||
else {
|
||||
if (flags & SPLT){
|
||||
ret = __copy_from_user(ptr, addr, length);
|
||||
ptr += length;
|
||||
lptr = (unsigned long *) ptr;
|
||||
|
||||
if (flags & SW)
|
||||
sw = elsize-1;
|
||||
|
||||
for (j = 0; j < length; j += elsize) {
|
||||
for (i = 0; i < elsize; ++i) {
|
||||
if (flags & ST)
|
||||
ret |= __put_user(ptr[i^sw], addr + i);
|
||||
else
|
||||
ret |= __get_user(ptr[i^sw], addr + i);
|
||||
}
|
||||
ret |= __copy_from_user(ptr, addr, length);
|
||||
ptr += elsize;
|
||||
addr += elsize;
|
||||
}
|
||||
if (flags & U)
|
||||
regs->gpr[areg] = regs->dar;
|
||||
if (ret)
|
||||
|
||||
if (!ret) {
|
||||
if (flags & U)
|
||||
regs->gpr[areg] = regs->dar;
|
||||
|
||||
/* Splat load copies the same data to top and bottom 8 bytes */
|
||||
if (flags & SPLT)
|
||||
lptr[1] = lptr[0];
|
||||
/* For 8 byte loads, zero the top 8 bytes */
|
||||
else if (!(flags & ST) && (8 == length))
|
||||
lptr[1] = 0;
|
||||
} else
|
||||
return -EFAULT;
|
||||
|
||||
return 1;
|
||||
}
|
||||
#endif
|
||||
|
@ -767,16 +787,25 @@ int fix_alignment(struct pt_regs *regs)
|
|||
|
||||
#ifdef CONFIG_VSX
|
||||
if ((instruction & 0xfc00003e) == 0x7c000018) {
|
||||
/* Additional register addressing bit (64 VSX vs 32 FPR/GPR */
|
||||
unsigned int elsize;
|
||||
|
||||
/* Additional register addressing bit (64 VSX vs 32 FPR/GPR) */
|
||||
reg |= (instruction & 0x1) << 5;
|
||||
/* Simple inline decoder instead of a table */
|
||||
/* VSX has only 8 and 16 byte memory accesses */
|
||||
nb = 8;
|
||||
if (instruction & 0x200)
|
||||
nb = 16;
|
||||
else if (instruction & 0x080)
|
||||
nb = 8;
|
||||
else
|
||||
nb = 4;
|
||||
|
||||
/* Vector stores in little-endian mode swap individual
|
||||
elements, so process them separately */
|
||||
elsize = 4;
|
||||
if (instruction & 0x80)
|
||||
elsize = 8;
|
||||
|
||||
flags = 0;
|
||||
if (regs->msr & MSR_LE)
|
||||
flags |= SW;
|
||||
if (instruction & 0x100)
|
||||
flags |= ST;
|
||||
if (instruction & 0x040)
|
||||
|
@ -787,7 +816,7 @@ int fix_alignment(struct pt_regs *regs)
|
|||
nb = 8;
|
||||
}
|
||||
PPC_WARN_ALIGNMENT(vsx, regs);
|
||||
return emulate_vsx(addr, reg, areg, regs, flags, nb);
|
||||
return emulate_vsx(addr, reg, areg, regs, flags, nb, elsize);
|
||||
}
|
||||
#endif
|
||||
/* A size of 0 indicates an instruction we don't support, with
|
||||
|
|
Loading…
Reference in New Issue