From 2b836c2ac1d040bbe2e47fd000924083fbcef414 Mon Sep 17 00:00:00 2001 From: Richard Henderson Date: Sun, 13 Jun 2021 14:58:05 -0700 Subject: [PATCH] tcg: Add flags argument to tcg_gen_bswap16_*, tcg_gen_bswap32_i64 MIME-Version: 1.0 Content-Type: text/plain; charset=utf8 Content-Transfer-Encoding: 8bit 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 Reviewed-by: Philippe Mathieu-Daudé Signed-off-by: Richard Henderson --- include/tcg/tcg-op.h | 8 +-- target/arm/translate-a64.c | 12 ++-- target/arm/translate.c | 2 +- target/i386/tcg/translate.c | 2 +- target/mips/tcg/mxu_translate.c | 2 +- target/s390x/translate.c | 4 +- target/sh4/translate.c | 2 +- tcg/tcg-op.c | 123 +++++++++++++++++++++++++++------------- 8 files changed, 100 insertions(+), 55 deletions(-) diff --git a/include/tcg/tcg-op.h b/include/tcg/tcg-op.h index 1a2ae93758..2a654f350c 100644 --- a/include/tcg/tcg-op.h +++ b/include/tcg/tcg-op.h @@ -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); @@ -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); @@ -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 diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c index 7f74d0e81a..f2641a37ba 100644 --- a/target/arm/translate-a64.c +++ b/target/arm/translate-a64.c @@ -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); } } @@ -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); diff --git a/target/arm/translate.c b/target/arm/translate.c index 9e2cca7707..669b0be578 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -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); } diff --git a/target/i386/tcg/translate.c b/target/i386/tcg/translate.c index a7f5c0c8f2..e8a9dcd21a 100644 --- a/target/i386/tcg/translate.c +++ b/target/i386/tcg/translate.c @@ -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; diff --git a/target/mips/tcg/mxu_translate.c b/target/mips/tcg/mxu_translate.c index 963d4ba8b1..3f35e46399 100644 --- a/target/mips/tcg/mxu_translate.c +++ b/target/mips/tcg/mxu_translate.c @@ -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); diff --git a/target/s390x/translate.c b/target/s390x/translate.c index e243624d2a..03dab9f350 100644 --- a/target/s390x/translate.c +++ b/target/s390x/translate.c @@ -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; } diff --git a/target/sh4/translate.c b/target/sh4/translate.c index 9312790623..147219759b 100644 --- a/target/sh4/translate.c +++ b/target/sh4/translate.c @@ -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); } diff --git a/tcg/tcg-op.c b/tcg/tcg-op.c index dc65577e2f..949cbf2f03 100644 --- a/tcg/tcg-op.c +++ b/tcg/tcg-op.c @@ -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); } } @@ -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); @@ -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); } @@ -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); @@ -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); } @@ -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); -- 2.11.4.GIT