Combine the three bswap16 routines, and differentiate via the flags. Use the correct flags combination from the load/store routines, and pass along the constant parameter from tcg_out_op.
Signed-off-by: Richard Henderson <richard.hender...@linaro.org> --- tcg/arm/tcg-target.c.inc | 78 ++++++++++++++++++++-------------------- 1 file changed, 38 insertions(+), 40 deletions(-) diff --git a/tcg/arm/tcg-target.c.inc b/tcg/arm/tcg-target.c.inc index 5157143246..9824e215be 100644 --- a/tcg/arm/tcg-target.c.inc +++ b/tcg/arm/tcg-target.c.inc @@ -1013,50 +1013,44 @@ static inline void tcg_out_ext16u(TCGContext *s, int cond, } } -static inline void tcg_out_bswap16s(TCGContext *s, int cond, int rd, int rn) +static void tcg_out_bswap16(TCGContext *s, int cond, int rd, int rn, int flags) { if (use_armv6_instructions) { - /* revsh */ - tcg_out32(s, 0x06ff0fb0 | (cond << 28) | (rd << 12) | rn); - } else { - tcg_out_dat_reg(s, cond, ARITH_MOV, - TCG_REG_TMP, 0, rn, SHIFT_IMM_LSL(24)); - tcg_out_dat_reg(s, cond, ARITH_MOV, - TCG_REG_TMP, 0, TCG_REG_TMP, SHIFT_IMM_ASR(16)); - tcg_out_dat_reg(s, cond, ARITH_ORR, - rd, TCG_REG_TMP, rn, SHIFT_IMM_LSR(8)); - } -} + if (flags & TCG_BSWAP_OS) { + /* revsh */ + tcg_out32(s, 0x06ff0fb0 | (cond << 28) | (rd << 12) | rn); + return; + } -static inline void tcg_out_bswap16(TCGContext *s, int cond, int rd, int rn) -{ - if (use_armv6_instructions) { /* rev16 */ tcg_out32(s, 0x06bf0fb0 | (cond << 28) | (rd << 12) | rn); - } else { - tcg_out_dat_reg(s, cond, ARITH_MOV, - TCG_REG_TMP, 0, rn, SHIFT_IMM_LSL(24)); - tcg_out_dat_reg(s, cond, ARITH_MOV, - TCG_REG_TMP, 0, TCG_REG_TMP, SHIFT_IMM_LSR(16)); - tcg_out_dat_reg(s, cond, ARITH_ORR, - rd, TCG_REG_TMP, rn, SHIFT_IMM_LSR(8)); + if ((flags & (TCG_BSWAP_IZ | TCG_BSWAP_OZ)) == TCG_BSWAP_OZ) { + /* uxth */ + tcg_out32(s, 0x06ff0070 | (cond << 28) | (rd << 12) | rd); + } + return; } -} -/* swap the two low bytes assuming that the two high input bytes and the - two high output bit can hold any value. */ -static inline void tcg_out_bswap16st(TCGContext *s, int cond, int rd, int rn) -{ - if (use_armv6_instructions) { - /* rev16 */ - tcg_out32(s, 0x06bf0fb0 | (cond << 28) | (rd << 12) | rn); - } else { - tcg_out_dat_reg(s, cond, ARITH_MOV, - TCG_REG_TMP, 0, rn, SHIFT_IMM_LSR(8)); + /* Move the high byte down and isolate it. */ + /* rn=xxAB -> tmp=0xxA -> tmp=000A */ + tcg_out_dat_reg(s, cond, ARITH_MOV, TCG_REG_TMP, 0, rn, SHIFT_IMM_LSR(8)); + if (!(flags & TCG_BSWAP_IZ)) { tcg_out_dat_imm(s, cond, ARITH_AND, TCG_REG_TMP, TCG_REG_TMP, 0xff); + } + + /* Move the low byte up and extend it. */ + if (!(flags & (TCG_BSWAP_OS | TCG_BSWAP_OZ))) { + /* No output extension: rd=xABA */ tcg_out_dat_reg(s, cond, ARITH_ORR, rd, TCG_REG_TMP, rn, SHIFT_IMM_LSL(8)); + return; } + + /* rn=xxAB -> rd=B000 -> rd=ssBA */ + tcg_out_dat_reg(s, cond, ARITH_MOV, rd, 0, rn, SHIFT_IMM_LSL(24)); + tcg_out_dat_reg(s, cond, ARITH_ORR, rd, TCG_REG_TMP, rd, + flags & TCG_BSWAP_OS + ? SHIFT_IMM_ASR(16) : SHIFT_IMM_LSR(16)); } static inline void tcg_out_bswap32(TCGContext *s, int cond, int rd, int rn) @@ -1705,13 +1699,15 @@ static inline void tcg_out_qemu_ld_index(TCGContext *s, MemOp opc, case MO_UW: tcg_out_ld16u_r(s, COND_AL, datalo, addrlo, addend); if (bswap) { - tcg_out_bswap16(s, COND_AL, datalo, datalo); + tcg_out_bswap16(s, COND_AL, datalo, datalo, + TCG_BSWAP_IZ | TCG_BSWAP_OZ); } break; case MO_SW: if (bswap) { tcg_out_ld16u_r(s, COND_AL, datalo, addrlo, addend); - tcg_out_bswap16s(s, COND_AL, datalo, datalo); + tcg_out_bswap16(s, COND_AL, datalo, datalo, + TCG_BSWAP_IZ | TCG_BSWAP_OS); } else { tcg_out_ld16s_r(s, COND_AL, datalo, addrlo, addend); } @@ -1766,13 +1762,15 @@ static inline void tcg_out_qemu_ld_direct(TCGContext *s, MemOp opc, case MO_UW: tcg_out_ld16u_8(s, COND_AL, datalo, addrlo, 0); if (bswap) { - tcg_out_bswap16(s, COND_AL, datalo, datalo); + tcg_out_bswap16(s, COND_AL, datalo, datalo, + TCG_BSWAP_IZ | TCG_BSWAP_OZ); } break; case MO_SW: if (bswap) { tcg_out_ld16u_8(s, COND_AL, datalo, addrlo, 0); - tcg_out_bswap16s(s, COND_AL, datalo, datalo); + tcg_out_bswap16(s, COND_AL, datalo, datalo, + TCG_BSWAP_IZ | TCG_BSWAP_OS); } else { tcg_out_ld16s_8(s, COND_AL, datalo, addrlo, 0); } @@ -1862,7 +1860,7 @@ static inline void tcg_out_qemu_st_index(TCGContext *s, int cond, MemOp opc, break; case MO_16: if (bswap) { - tcg_out_bswap16st(s, cond, TCG_REG_R0, datalo); + tcg_out_bswap16(s, cond, TCG_REG_R0, datalo, 0); tcg_out_st16_r(s, cond, TCG_REG_R0, addrlo, addend); } else { tcg_out_st16_r(s, cond, datalo, addrlo, addend); @@ -1907,7 +1905,7 @@ static inline void tcg_out_qemu_st_direct(TCGContext *s, MemOp opc, break; case MO_16: if (bswap) { - tcg_out_bswap16st(s, COND_AL, TCG_REG_R0, datalo); + tcg_out_bswap16(s, COND_AL, TCG_REG_R0, datalo, 0); tcg_out_st16_8(s, COND_AL, TCG_REG_R0, addrlo, 0); } else { tcg_out_st16_8(s, COND_AL, datalo, addrlo, 0); @@ -2245,7 +2243,7 @@ static inline void tcg_out_op(TCGContext *s, TCGOpcode opc, break; case INDEX_op_bswap16_i32: - tcg_out_bswap16(s, COND_AL, args[0], args[1]); + tcg_out_bswap16(s, COND_AL, args[0], args[1], args[2]); break; case INDEX_op_bswap32_i32: tcg_out_bswap32(s, COND_AL, args[0], args[1]); -- 2.25.1