tcg/arm: Support bswap flags

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.

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
This commit is contained in:
Richard Henderson 2021-06-13 00:42:55 -07:00
parent 8fcfc6bff6
commit 2ec89a78a5
1 changed files with 63 additions and 38 deletions

View File

@ -1013,50 +1013,71 @@ 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) { if (use_armv6_instructions) {
/* revsh */ if (flags & TCG_BSWAP_OS) {
tcg_out32(s, 0x06ff0fb0 | (cond << 28) | (rd << 12) | rn); /* revsh */
} else { tcg_out32(s, 0x06ff0fb0 | (cond << 28) | (rd << 12) | rn);
tcg_out_dat_reg(s, cond, ARITH_MOV, return;
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));
}
}
static inline void tcg_out_bswap16(TCGContext *s, int cond, int rd, int rn)
{
if (use_armv6_instructions) {
/* rev16 */ /* rev16 */
tcg_out32(s, 0x06bf0fb0 | (cond << 28) | (rd << 12) | rn); tcg_out32(s, 0x06bf0fb0 | (cond << 28) | (rd << 12) | rn);
} else { if ((flags & (TCG_BSWAP_IZ | TCG_BSWAP_OZ)) == TCG_BSWAP_OZ) {
tcg_out_dat_reg(s, cond, ARITH_MOV, /* uxth */
TCG_REG_TMP, 0, rn, SHIFT_IMM_LSL(24)); tcg_out32(s, 0x06ff0070 | (cond << 28) | (rd << 12) | rd);
tcg_out_dat_reg(s, cond, ARITH_MOV, }
TCG_REG_TMP, 0, TCG_REG_TMP, SHIFT_IMM_LSR(16)); return;
tcg_out_dat_reg(s, cond, ARITH_ORR,
rd, TCG_REG_TMP, rn, SHIFT_IMM_LSR(8));
} }
}
/* swap the two low bytes assuming that the two high input bytes and the if (flags == 0) {
two high output bit can hold any value. */ /*
static inline void tcg_out_bswap16st(TCGContext *s, int cond, int rd, int rn) * For stores, no input or output extension:
{ * rn = xxAB
if (use_armv6_instructions) { * lsr tmp, rn, #8 tmp = 0xxA
/* rev16 */ * and tmp, tmp, #0xff tmp = 000A
tcg_out32(s, 0x06bf0fb0 | (cond << 28) | (rd << 12) | rn); * orr rd, tmp, rn, lsl #8 rd = xABA
} else { */
tcg_out_dat_reg(s, cond, ARITH_MOV, tcg_out_dat_reg(s, cond, ARITH_MOV,
TCG_REG_TMP, 0, rn, SHIFT_IMM_LSR(8)); TCG_REG_TMP, 0, rn, SHIFT_IMM_LSR(8));
tcg_out_dat_imm(s, cond, ARITH_AND, TCG_REG_TMP, TCG_REG_TMP, 0xff); tcg_out_dat_imm(s, cond, ARITH_AND, TCG_REG_TMP, TCG_REG_TMP, 0xff);
tcg_out_dat_reg(s, cond, ARITH_ORR, tcg_out_dat_reg(s, cond, ARITH_ORR,
rd, TCG_REG_TMP, rn, SHIFT_IMM_LSL(8)); rd, TCG_REG_TMP, rn, SHIFT_IMM_LSL(8));
return;
} }
/*
* Byte swap, leaving the result at the top of the register.
* We will then shift down, zero or sign-extending.
*/
if (flags & TCG_BSWAP_IZ) {
/*
* rn = 00AB
* ror tmp, rn, #8 tmp = B00A
* orr tmp, tmp, tmp, lsl #16 tmp = BA00
*/
tcg_out_dat_reg(s, cond, ARITH_MOV,
TCG_REG_TMP, 0, rn, SHIFT_IMM_ROR(8));
tcg_out_dat_reg(s, cond, ARITH_ORR,
TCG_REG_TMP, TCG_REG_TMP, TCG_REG_TMP,
SHIFT_IMM_LSL(16));
} else {
/*
* rn = xxAB
* and tmp, rn, #0xff00 tmp = 00A0
* lsl tmp, tmp, #8 tmp = 0A00
* orr tmp, tmp, rn, lsl #24 tmp = BA00
*/
tcg_out_dat_rI(s, cond, ARITH_AND, TCG_REG_TMP, rn, 0xff00, 1);
tcg_out_dat_reg(s, cond, ARITH_MOV,
TCG_REG_TMP, 0, TCG_REG_TMP, SHIFT_IMM_LSL(8));
tcg_out_dat_reg(s, cond, ARITH_ORR,
TCG_REG_TMP, TCG_REG_TMP, rn, SHIFT_IMM_LSL(24));
}
tcg_out_dat_reg(s, cond, ARITH_MOV, rd, 0, TCG_REG_TMP,
(flags & TCG_BSWAP_OS
? SHIFT_IMM_ASR(8) : SHIFT_IMM_LSR(8)));
} }
static inline void tcg_out_bswap32(TCGContext *s, int cond, int rd, int rn) static inline void tcg_out_bswap32(TCGContext *s, int cond, int rd, int rn)
@ -1705,13 +1726,15 @@ static inline void tcg_out_qemu_ld_index(TCGContext *s, MemOp opc,
case MO_UW: case MO_UW:
tcg_out_ld16u_r(s, COND_AL, datalo, addrlo, addend); tcg_out_ld16u_r(s, COND_AL, datalo, addrlo, addend);
if (bswap) { 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; break;
case MO_SW: case MO_SW:
if (bswap) { if (bswap) {
tcg_out_ld16u_r(s, COND_AL, datalo, addrlo, addend); 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 { } else {
tcg_out_ld16s_r(s, COND_AL, datalo, addrlo, addend); tcg_out_ld16s_r(s, COND_AL, datalo, addrlo, addend);
} }
@ -1766,13 +1789,15 @@ static inline void tcg_out_qemu_ld_direct(TCGContext *s, MemOp opc,
case MO_UW: case MO_UW:
tcg_out_ld16u_8(s, COND_AL, datalo, addrlo, 0); tcg_out_ld16u_8(s, COND_AL, datalo, addrlo, 0);
if (bswap) { 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; break;
case MO_SW: case MO_SW:
if (bswap) { if (bswap) {
tcg_out_ld16u_8(s, COND_AL, datalo, addrlo, 0); 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 { } else {
tcg_out_ld16s_8(s, COND_AL, datalo, addrlo, 0); tcg_out_ld16s_8(s, COND_AL, datalo, addrlo, 0);
} }
@ -1862,7 +1887,7 @@ static inline void tcg_out_qemu_st_index(TCGContext *s, int cond, MemOp opc,
break; break;
case MO_16: case MO_16:
if (bswap) { 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); tcg_out_st16_r(s, cond, TCG_REG_R0, addrlo, addend);
} else { } else {
tcg_out_st16_r(s, cond, datalo, addrlo, addend); tcg_out_st16_r(s, cond, datalo, addrlo, addend);
@ -1907,7 +1932,7 @@ static inline void tcg_out_qemu_st_direct(TCGContext *s, MemOp opc,
break; break;
case MO_16: case MO_16:
if (bswap) { 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); tcg_out_st16_8(s, COND_AL, TCG_REG_R0, addrlo, 0);
} else { } else {
tcg_out_st16_8(s, COND_AL, datalo, addrlo, 0); tcg_out_st16_8(s, COND_AL, datalo, addrlo, 0);
@ -2245,7 +2270,7 @@ static inline void tcg_out_op(TCGContext *s, TCGOpcode opc,
break; break;
case INDEX_op_bswap16_i32: 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; break;
case INDEX_op_bswap32_i32: case INDEX_op_bswap32_i32:
tcg_out_bswap32(s, COND_AL, args[0], args[1]); tcg_out_bswap32(s, COND_AL, args[0], args[1]);