Re: [Qemu-devel] [PATCH 2/4] memory: Single byte swap along the I/O path

2019-07-17 Thread Richard Henderson
On 7/16/19 11:06 PM, tony.ngu...@bt.com wrote: > +++ b/include/exec/poison.h > @@ -38,7 +38,6 @@ > #pragma GCC poison TARGET_HAS_BFLT > #pragma GCC poison TARGET_NAME > #pragma GCC poison TARGET_SUPPORTS_MTTCG > -#pragma GCC poison TARGET_WORDS_BIGENDIAN You can't do this. This is here for a v

Re: [Qemu-devel] [PATCH 2/4] memory: Single byte swap along the I/O path

2019-07-17 Thread Paolo Bonzini
On 17/07/19 08:06, tony.ngu...@bt.com wrote: > + > +static inline MemOp MEMOP(unsigned size) > +{ > +switch (size) { > +case 1: > +return MO_8; > +case 2: > +return MO_16; > +case 4: > +return MO_32; > +case 8: > +return MO_64; > +default: > +

[Qemu-devel] [PATCH 2/4] memory: Single byte swap along the I/O path

2019-07-16 Thread tony.nguyen
Collapsed adjust_endianess and handle_bswap into the former. A single byte swap avoids redundant re-swapping. This is preparation for upcoming SPARC64 TTE invert endian bit which would be a third(!) byte swap along the I/O path. Signed-off-by: Tony Nguyen --- accel/tcg/cputlb.c | 58