Skip to content

Commit

Permalink
tcg: Add flags argument to tcg_gen_bswap16_*, tcg_gen_bswap32_i64
Browse files Browse the repository at this point in the history
Implement the new semantics in the fallback expansion.
Change all callers to supply the flags that keep the
semantics unchanged locally.

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
  • Loading branch information
rth7680 committed Jun 29, 2021
1 parent 0b76ff8 commit 2b836c2
Show file tree
Hide file tree
Showing 8 changed files with 100 additions and 55 deletions.
8 changes: 4 additions & 4 deletions include/tcg/tcg-op.h
Expand Up @@ -330,7 +330,7 @@ void tcg_gen_ext8s_i32(TCGv_i32 ret, TCGv_i32 arg);
void tcg_gen_ext16s_i32(TCGv_i32 ret, TCGv_i32 arg);
void tcg_gen_ext8u_i32(TCGv_i32 ret, TCGv_i32 arg);
void tcg_gen_ext16u_i32(TCGv_i32 ret, TCGv_i32 arg);
void tcg_gen_bswap16_i32(TCGv_i32 ret, TCGv_i32 arg);
void tcg_gen_bswap16_i32(TCGv_i32 ret, TCGv_i32 arg, int flags);
void tcg_gen_bswap32_i32(TCGv_i32 ret, TCGv_i32 arg);
void tcg_gen_smin_i32(TCGv_i32, TCGv_i32 arg1, TCGv_i32 arg2);
void tcg_gen_smax_i32(TCGv_i32, TCGv_i32 arg1, TCGv_i32 arg2);
Expand Down Expand Up @@ -528,8 +528,8 @@ void tcg_gen_ext32s_i64(TCGv_i64 ret, TCGv_i64 arg);
void tcg_gen_ext8u_i64(TCGv_i64 ret, TCGv_i64 arg);
void tcg_gen_ext16u_i64(TCGv_i64 ret, TCGv_i64 arg);
void tcg_gen_ext32u_i64(TCGv_i64 ret, TCGv_i64 arg);
void tcg_gen_bswap16_i64(TCGv_i64 ret, TCGv_i64 arg);
void tcg_gen_bswap32_i64(TCGv_i64 ret, TCGv_i64 arg);
void tcg_gen_bswap16_i64(TCGv_i64 ret, TCGv_i64 arg, int flags);
void tcg_gen_bswap32_i64(TCGv_i64 ret, TCGv_i64 arg, int flags);
void tcg_gen_bswap64_i64(TCGv_i64 ret, TCGv_i64 arg);
void tcg_gen_smin_i64(TCGv_i64, TCGv_i64 arg1, TCGv_i64 arg2);
void tcg_gen_smax_i64(TCGv_i64, TCGv_i64 arg1, TCGv_i64 arg2);
Expand Down Expand Up @@ -1192,7 +1192,7 @@ void tcg_gen_stl_vec(TCGv_vec r, TCGv_ptr base, TCGArg offset, TCGType t);
#define tcg_gen_ext32u_tl tcg_gen_mov_i32
#define tcg_gen_ext32s_tl tcg_gen_mov_i32
#define tcg_gen_bswap16_tl tcg_gen_bswap16_i32
#define tcg_gen_bswap32_tl tcg_gen_bswap32_i32
#define tcg_gen_bswap32_tl(D, S, F) tcg_gen_bswap32_i32(D, S)
#define tcg_gen_bswap_tl tcg_gen_bswap32_i32
#define tcg_gen_concat_tl_i64 tcg_gen_concat_i32_i64
#define tcg_gen_extr_i64_tl tcg_gen_extr_i64_i32
Expand Down
12 changes: 7 additions & 5 deletions target/arm/translate-a64.c
Expand Up @@ -5437,15 +5437,15 @@ static void handle_rev32(DisasContext *s, unsigned int sf,

/* bswap32_i64 requires zero high word */
tcg_gen_ext32u_i64(tcg_tmp, tcg_rn);
tcg_gen_bswap32_i64(tcg_rd, tcg_tmp);
tcg_gen_bswap32_i64(tcg_rd, tcg_tmp, TCG_BSWAP_IZ | TCG_BSWAP_OZ);
tcg_gen_shri_i64(tcg_tmp, tcg_rn, 32);
tcg_gen_bswap32_i64(tcg_tmp, tcg_tmp);
tcg_gen_bswap32_i64(tcg_tmp, tcg_tmp, TCG_BSWAP_IZ | TCG_BSWAP_OZ);
tcg_gen_concat32_i64(tcg_rd, tcg_rd, tcg_tmp);

tcg_temp_free_i64(tcg_tmp);
} else {
tcg_gen_ext32u_i64(tcg_rd, cpu_reg(s, rn));
tcg_gen_bswap32_i64(tcg_rd, tcg_rd);
tcg_gen_bswap32_i64(tcg_rd, tcg_rd, TCG_BSWAP_IZ | TCG_BSWAP_OZ);
}
}

Expand Down Expand Up @@ -12453,10 +12453,12 @@ static void handle_rev(DisasContext *s, int opcode, bool u,
read_vec_element(s, tcg_tmp, rn, i, grp_size);
switch (grp_size) {
case MO_16:
tcg_gen_bswap16_i64(tcg_tmp, tcg_tmp);
tcg_gen_bswap16_i64(tcg_tmp, tcg_tmp,
TCG_BSWAP_IZ | TCG_BSWAP_OZ);
break;
case MO_32:
tcg_gen_bswap32_i64(tcg_tmp, tcg_tmp);
tcg_gen_bswap32_i64(tcg_tmp, tcg_tmp,
TCG_BSWAP_IZ | TCG_BSWAP_OZ);
break;
case MO_64:
tcg_gen_bswap64_i64(tcg_tmp, tcg_tmp);
Expand Down
2 changes: 1 addition & 1 deletion target/arm/translate.c
Expand Up @@ -355,7 +355,7 @@ void gen_rev16(TCGv_i32 dest, TCGv_i32 var)
static void gen_revsh(TCGv_i32 dest, TCGv_i32 var)
{
tcg_gen_ext16u_i32(var, var);
tcg_gen_bswap16_i32(var, var);
tcg_gen_bswap16_i32(var, var, TCG_BSWAP_IZ | TCG_BSWAP_OZ);
tcg_gen_ext16s_i32(dest, var);
}

Expand Down
2 changes: 1 addition & 1 deletion target/i386/tcg/translate.c
Expand Up @@ -7203,7 +7203,7 @@ static target_ulong disas_insn(DisasContext *s, CPUState *cpu)
{
gen_op_mov_v_reg(s, MO_32, s->T0, reg);
tcg_gen_ext32u_tl(s->T0, s->T0);
tcg_gen_bswap32_tl(s->T0, s->T0);
tcg_gen_bswap32_tl(s->T0, s->T0, TCG_BSWAP_IZ | TCG_BSWAP_OZ);
gen_op_mov_reg_v(s, MO_32, reg, s->T0);
}
break;
Expand Down
2 changes: 1 addition & 1 deletion target/mips/tcg/mxu_translate.c
Expand Up @@ -861,7 +861,7 @@ static void gen_mxu_s32ldd_s32lddr(DisasContext *ctx)

if (sel == 1) {
/* S32LDDR */
tcg_gen_bswap32_tl(t1, t1);
tcg_gen_bswap32_tl(t1, t1, TCG_BSWAP_IZ | TCG_BSWAP_OZ);
}
gen_store_mxu_gpr(t1, XRa);

Expand Down
4 changes: 2 additions & 2 deletions target/s390x/translate.c
Expand Up @@ -3939,13 +3939,13 @@ static DisasJumpType op_rosbg(DisasContext *s, DisasOps *o)

static DisasJumpType op_rev16(DisasContext *s, DisasOps *o)
{
tcg_gen_bswap16_i64(o->out, o->in2);
tcg_gen_bswap16_i64(o->out, o->in2, TCG_BSWAP_IZ | TCG_BSWAP_OZ);
return DISAS_NEXT;
}

static DisasJumpType op_rev32(DisasContext *s, DisasOps *o)
{
tcg_gen_bswap32_i64(o->out, o->in2);
tcg_gen_bswap32_i64(o->out, o->in2, TCG_BSWAP_IZ | TCG_BSWAP_OZ);
return DISAS_NEXT;
}

Expand Down
2 changes: 1 addition & 1 deletion target/sh4/translate.c
Expand Up @@ -677,7 +677,7 @@ static void _decode_opc(DisasContext * ctx)
{
TCGv low = tcg_temp_new();
tcg_gen_ext16u_i32(low, REG(B7_4));
tcg_gen_bswap16_i32(low, low);
tcg_gen_bswap16_i32(low, low, TCG_BSWAP_IZ | TCG_BSWAP_OZ);
tcg_gen_deposit_i32(REG(B11_8), REG(B7_4), low, 0, 16);
tcg_temp_free(low);
}
Expand Down
123 changes: 83 additions & 40 deletions tcg/tcg-op.c
Expand Up @@ -1001,20 +1001,35 @@ void tcg_gen_ext16u_i32(TCGv_i32 ret, TCGv_i32 arg)
}
}

/* Note: we assume the two high bytes are set to zero */
void tcg_gen_bswap16_i32(TCGv_i32 ret, TCGv_i32 arg)
void tcg_gen_bswap16_i32(TCGv_i32 ret, TCGv_i32 arg, int flags)
{
/* Only one extension flag may be present. */
tcg_debug_assert(!(flags & TCG_BSWAP_OS) || !(flags & TCG_BSWAP_OZ));

if (TCG_TARGET_HAS_bswap16_i32) {
tcg_gen_op3i_i32(INDEX_op_bswap16_i32, ret, arg,
TCG_BSWAP_IZ | TCG_BSWAP_OZ);
tcg_gen_op3i_i32(INDEX_op_bswap16_i32, ret, arg, flags);
} else {
TCGv_i32 t0 = tcg_temp_new_i32();
TCGv_i32 t1 = tcg_temp_new_i32();

tcg_gen_shri_i32(t0, arg, 8);
if (!(flags & TCG_BSWAP_IZ)) {
tcg_gen_ext8u_i32(t0, t0);
}

tcg_gen_ext8u_i32(t0, arg);
tcg_gen_shli_i32(t0, t0, 8);
tcg_gen_shri_i32(ret, arg, 8);
tcg_gen_or_i32(ret, ret, t0);
if (flags & TCG_BSWAP_OS) {
tcg_gen_shli_i32(t1, arg, 24);
tcg_gen_sari_i32(t1, t1, 16);
} else if (flags & TCG_BSWAP_OZ) {
tcg_gen_ext8u_i32(t1, arg);
tcg_gen_shli_i32(t1, t1, 8);
} else {
tcg_gen_shli_i32(t1, arg, 8);
}

tcg_gen_or_i32(ret, t0, t1);
tcg_temp_free_i32(t0);
tcg_temp_free_i32(t1);
}
}

Expand Down Expand Up @@ -1655,51 +1670,79 @@ void tcg_gen_ext32u_i64(TCGv_i64 ret, TCGv_i64 arg)
}
}

/* Note: we assume the six high bytes are set to zero */
void tcg_gen_bswap16_i64(TCGv_i64 ret, TCGv_i64 arg)
void tcg_gen_bswap16_i64(TCGv_i64 ret, TCGv_i64 arg, int flags)
{
/* Only one extension flag may be present. */
tcg_debug_assert(!(flags & TCG_BSWAP_OS) || !(flags & TCG_BSWAP_OZ));

if (TCG_TARGET_REG_BITS == 32) {
tcg_gen_bswap16_i32(TCGV_LOW(ret), TCGV_LOW(arg));
tcg_gen_movi_i32(TCGV_HIGH(ret), 0);
tcg_gen_bswap16_i32(TCGV_LOW(ret), TCGV_LOW(arg), flags);
if (flags & TCG_BSWAP_OS) {
tcg_gen_sari_i32(TCGV_HIGH(ret), TCGV_LOW(ret), 31);
} else {
tcg_gen_movi_i32(TCGV_HIGH(ret), 0);
}
} else if (TCG_TARGET_HAS_bswap16_i64) {
tcg_gen_op3i_i64(INDEX_op_bswap16_i64, ret, arg,
TCG_BSWAP_IZ | TCG_BSWAP_OZ);
tcg_gen_op3i_i64(INDEX_op_bswap16_i64, ret, arg, flags);
} else {
TCGv_i64 t0 = tcg_temp_new_i64();
TCGv_i64 t1 = tcg_temp_new_i64();

tcg_gen_ext8u_i64(t0, arg);
tcg_gen_shli_i64(t0, t0, 8);
tcg_gen_shri_i64(ret, arg, 8);
tcg_gen_or_i64(ret, ret, t0);
tcg_gen_shri_i64(t0, arg, 8);
if (!(flags & TCG_BSWAP_IZ)) {
tcg_gen_ext8u_i64(t0, t0);
}

if (flags & TCG_BSWAP_OS) {
tcg_gen_shli_i64(t1, arg, 56);
tcg_gen_sari_i64(t1, t1, 48);
} else if (flags & TCG_BSWAP_OZ) {
tcg_gen_ext8u_i64(t1, arg);
tcg_gen_shli_i64(t1, t1, 8);
} else {
tcg_gen_shli_i64(t1, arg, 8);
}

tcg_gen_or_i64(ret, t0, t1);
tcg_temp_free_i64(t0);
tcg_temp_free_i64(t1);
}
}

/* Note: we assume the four high bytes are set to zero */
void tcg_gen_bswap32_i64(TCGv_i64 ret, TCGv_i64 arg)
void tcg_gen_bswap32_i64(TCGv_i64 ret, TCGv_i64 arg, int flags)
{
/* Only one extension flag may be present. */
tcg_debug_assert(!(flags & TCG_BSWAP_OS) || !(flags & TCG_BSWAP_OZ));

if (TCG_TARGET_REG_BITS == 32) {
tcg_gen_bswap32_i32(TCGV_LOW(ret), TCGV_LOW(arg));
tcg_gen_movi_i32(TCGV_HIGH(ret), 0);
if (flags & TCG_BSWAP_OS) {
tcg_gen_sari_i32(TCGV_HIGH(ret), TCGV_LOW(ret), 31);
} else {
tcg_gen_movi_i32(TCGV_HIGH(ret), 0);
}
} else if (TCG_TARGET_HAS_bswap32_i64) {
tcg_gen_op3i_i64(INDEX_op_bswap32_i64, ret, arg,
TCG_BSWAP_IZ | TCG_BSWAP_OZ);
tcg_gen_op3i_i64(INDEX_op_bswap32_i64, ret, arg, flags);
} else {
TCGv_i64 t0 = tcg_temp_new_i64();
TCGv_i64 t1 = tcg_temp_new_i64();
TCGv_i64 t2 = tcg_constant_i64(0x00ff00ff);

/* arg = ....abcd */
tcg_gen_shri_i64(t0, arg, 8); /* t0 = .....abc */
tcg_gen_and_i64(t1, arg, t2); /* t1 = .....b.d */
tcg_gen_and_i64(t0, t0, t2); /* t0 = .....a.c */
tcg_gen_shli_i64(t1, t1, 8); /* t1 = ....b.d. */
tcg_gen_or_i64(ret, t0, t1); /* ret = ....badc */

tcg_gen_shli_i64(t1, ret, 48); /* t1 = dc...... */
tcg_gen_shri_i64(t0, ret, 16); /* t0 = ......ba */
tcg_gen_shri_i64(t1, t1, 32); /* t1 = ....dc.. */
tcg_gen_or_i64(ret, t0, t1); /* ret = ....dcba */
/* arg = xxxxabcd */
tcg_gen_shri_i64(t0, arg, 8); /* t0 = .xxxxabc */
tcg_gen_and_i64(t1, arg, t2); /* t1 = .....b.d */
tcg_gen_and_i64(t0, t0, t2); /* t0 = .....a.c */
tcg_gen_shli_i64(t1, t1, 8); /* t1 = ....b.d. */
tcg_gen_or_i64(ret, t0, t1); /* ret = ....badc */

tcg_gen_shli_i64(t1, ret, 48); /* t1 = dc...... */
tcg_gen_shri_i64(t0, ret, 16); /* t0 = ......ba */
if (flags & TCG_BSWAP_OS) {
tcg_gen_sari_i64(t1, t1, 32); /* t1 = ssssdc.. */
} else {
tcg_gen_shri_i64(t1, t1, 32); /* t1 = ....dc.. */
}
tcg_gen_or_i64(ret, t0, t1); /* ret = ssssdcba */

tcg_temp_free_i64(t0);
tcg_temp_free_i64(t1);
Expand Down Expand Up @@ -2846,7 +2889,7 @@ void tcg_gen_qemu_ld_i32(TCGv_i32 val, TCGv addr, TCGArg idx, MemOp memop)
if ((orig_memop ^ memop) & MO_BSWAP) {
switch (orig_memop & MO_SIZE) {
case MO_16:
tcg_gen_bswap16_i32(val, val);
tcg_gen_bswap16_i32(val, val, TCG_BSWAP_IZ | TCG_BSWAP_OZ);
if (orig_memop & MO_SIGN) {
tcg_gen_ext16s_i32(val, val);
}
Expand Down Expand Up @@ -2874,7 +2917,7 @@ void tcg_gen_qemu_st_i32(TCGv_i32 val, TCGv addr, TCGArg idx, MemOp memop)
switch (memop & MO_SIZE) {
case MO_16:
tcg_gen_ext16u_i32(swap, val);
tcg_gen_bswap16_i32(swap, swap);
tcg_gen_bswap16_i32(swap, swap, TCG_BSWAP_IZ | TCG_BSWAP_OZ);
break;
case MO_32:
tcg_gen_bswap32_i32(swap, val);
Expand Down Expand Up @@ -2935,13 +2978,13 @@ void tcg_gen_qemu_ld_i64(TCGv_i64 val, TCGv addr, TCGArg idx, MemOp memop)
if ((orig_memop ^ memop) & MO_BSWAP) {
switch (orig_memop & MO_SIZE) {
case MO_16:
tcg_gen_bswap16_i64(val, val);
tcg_gen_bswap16_i64(val, val, TCG_BSWAP_IZ | TCG_BSWAP_OZ);
if (orig_memop & MO_SIGN) {
tcg_gen_ext16s_i64(val, val);
}
break;
case MO_32:
tcg_gen_bswap32_i64(val, val);
tcg_gen_bswap32_i64(val, val, TCG_BSWAP_IZ | TCG_BSWAP_OZ);
if (orig_memop & MO_SIGN) {
tcg_gen_ext32s_i64(val, val);
}
Expand Down Expand Up @@ -2975,11 +3018,11 @@ void tcg_gen_qemu_st_i64(TCGv_i64 val, TCGv addr, TCGArg idx, MemOp memop)
switch (memop & MO_SIZE) {
case MO_16:
tcg_gen_ext16u_i64(swap, val);
tcg_gen_bswap16_i64(swap, swap);
tcg_gen_bswap16_i64(swap, swap, TCG_BSWAP_IZ | TCG_BSWAP_OZ);
break;
case MO_32:
tcg_gen_ext32u_i64(swap, val);
tcg_gen_bswap32_i64(swap, swap);
tcg_gen_bswap32_i64(swap, swap, TCG_BSWAP_IZ | TCG_BSWAP_OZ);
break;
case MO_64:
tcg_gen_bswap64_i64(swap, val);
Expand Down

0 comments on commit 2b836c2

Please sign in to comment.