aboutsummaryrefslogtreecommitdiff
path: root/target/arm/translate.c
diff options
context:
space:
mode:
Diffstat (limited to 'target/arm/translate.c')
-rw-r--r--target/arm/translate.c539
1 files changed, 22 insertions, 517 deletions
diff --git a/target/arm/translate.c b/target/arm/translate.c
index c8296116d4..bcdfec34d2 100644
--- a/target/arm/translate.c
+++ b/target/arm/translate.c
@@ -3011,29 +3011,6 @@ static inline void gen_neon_rsb(int size, TCGv_i32 t0, TCGv_i32 t1)
}
}
-#define GEN_NEON_INTEGER_OP_ENV(name) do { \
- switch ((size << 1) | u) { \
- case 0: \
- gen_helper_neon_##name##_s8(tmp, cpu_env, tmp, tmp2); \
- break; \
- case 1: \
- gen_helper_neon_##name##_u8(tmp, cpu_env, tmp, tmp2); \
- break; \
- case 2: \
- gen_helper_neon_##name##_s16(tmp, cpu_env, tmp, tmp2); \
- break; \
- case 3: \
- gen_helper_neon_##name##_u16(tmp, cpu_env, tmp, tmp2); \
- break; \
- case 4: \
- gen_helper_neon_##name##_s32(tmp, cpu_env, tmp, tmp2); \
- break; \
- case 5: \
- gen_helper_neon_##name##_u32(tmp, cpu_env, tmp, tmp2); \
- break; \
- default: return 1; \
- }} while (0)
-
static TCGv_i32 neon_load_scratch(int scratch)
{
TCGv_i32 tmp = tcg_temp_new_i32();
@@ -3224,40 +3201,6 @@ static inline void gen_neon_unarrow_sats(int size, TCGv_i32 dest, TCGv_i64 src)
}
}
-static inline void gen_neon_shift_narrow(int size, TCGv_i32 var, TCGv_i32 shift,
- int q, int u)
-{
- if (q) {
- if (u) {
- switch (size) {
- case 1: gen_helper_neon_rshl_u16(var, var, shift); break;
- case 2: gen_helper_neon_rshl_u32(var, var, shift); break;
- default: abort();
- }
- } else {
- switch (size) {
- case 1: gen_helper_neon_rshl_s16(var, var, shift); break;
- case 2: gen_helper_neon_rshl_s32(var, var, shift); break;
- default: abort();
- }
- }
- } else {
- if (u) {
- switch (size) {
- case 1: gen_helper_neon_shl_u16(var, var, shift); break;
- case 2: gen_ushl_i32(var, var, shift); break;
- default: abort();
- }
- } else {
- switch (size) {
- case 1: gen_helper_neon_shl_s16(var, var, shift); break;
- case 2: gen_sshl_i32(var, var, shift); break;
- default: abort();
- }
- }
- }
-}
-
static inline void gen_neon_widen(TCGv_i64 dest, TCGv_i32 src, int size, int u)
{
if (u) {
@@ -5250,14 +5193,12 @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn)
int q;
int rd, rn, rm, rd_ofs, rn_ofs, rm_ofs;
int size;
- int shift;
int pass;
- int count;
int u;
int vec_size;
uint32_t imm;
TCGv_i32 tmp, tmp2, tmp3, tmp4, tmp5;
- TCGv_ptr ptr1, ptr2;
+ TCGv_ptr ptr1;
TCGv_i64 tmp64;
if (!arm_dc_feature(s, ARM_FEATURE_NEON)) {
@@ -5291,433 +5232,8 @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn)
/* Three register same length: handled by decodetree */
return 1;
} else if (insn & (1 << 4)) {
- if ((insn & 0x00380080) != 0) {
- /* Two registers and shift. */
- op = (insn >> 8) & 0xf;
- if (insn & (1 << 7)) {
- /* 64-bit shift. */
- if (op > 7) {
- return 1;
- }
- size = 3;
- } else {
- size = 2;
- while ((insn & (1 << (size + 19))) == 0)
- size--;
- }
- shift = (insn >> 16) & ((1 << (3 + size)) - 1);
- if (op < 8) {
- /* Shift by immediate:
- VSHR, VSRA, VRSHR, VRSRA, VSRI, VSHL, VQSHL, VQSHLU. */
- if (q && ((rd | rm) & 1)) {
- return 1;
- }
- if (!u && (op == 4 || op == 6)) {
- return 1;
- }
- /* Right shifts are encoded as N - shift, where N is the
- element size in bits. */
- if (op <= 4) {
- shift = shift - (1 << (size + 3));
- }
-
- switch (op) {
- case 0: /* VSHR */
- /* Right shift comes here negative. */
- shift = -shift;
- /* Shifts larger than the element size are architecturally
- * valid. Unsigned results in all zeros; signed results
- * in all sign bits.
- */
- if (!u) {
- tcg_gen_gvec_sari(size, rd_ofs, rm_ofs,
- MIN(shift, (8 << size) - 1),
- vec_size, vec_size);
- } else if (shift >= 8 << size) {
- tcg_gen_gvec_dup_imm(MO_8, rd_ofs, vec_size,
- vec_size, 0);
- } else {
- tcg_gen_gvec_shri(size, rd_ofs, rm_ofs, shift,
- vec_size, vec_size);
- }
- return 0;
-
- case 1: /* VSRA */
- /* Right shift comes here negative. */
- shift = -shift;
- if (u) {
- gen_gvec_usra(size, rd_ofs, rm_ofs, shift,
- vec_size, vec_size);
- } else {
- gen_gvec_ssra(size, rd_ofs, rm_ofs, shift,
- vec_size, vec_size);
- }
- return 0;
-
- case 2: /* VRSHR */
- /* Right shift comes here negative. */
- shift = -shift;
- if (u) {
- gen_gvec_urshr(size, rd_ofs, rm_ofs, shift,
- vec_size, vec_size);
- } else {
- gen_gvec_srshr(size, rd_ofs, rm_ofs, shift,
- vec_size, vec_size);
- }
- return 0;
-
- case 3: /* VRSRA */
- /* Right shift comes here negative. */
- shift = -shift;
- if (u) {
- gen_gvec_ursra(size, rd_ofs, rm_ofs, shift,
- vec_size, vec_size);
- } else {
- gen_gvec_srsra(size, rd_ofs, rm_ofs, shift,
- vec_size, vec_size);
- }
- return 0;
-
- case 4: /* VSRI */
- if (!u) {
- return 1;
- }
- /* Right shift comes here negative. */
- shift = -shift;
- gen_gvec_sri(size, rd_ofs, rm_ofs, shift,
- vec_size, vec_size);
- return 0;
-
- case 5: /* VSHL, VSLI */
- if (u) { /* VSLI */
- gen_gvec_sli(size, rd_ofs, rm_ofs, shift,
- vec_size, vec_size);
- } else { /* VSHL */
- tcg_gen_gvec_shli(size, rd_ofs, rm_ofs, shift,
- vec_size, vec_size);
- }
- return 0;
- }
-
- if (size == 3) {
- count = q + 1;
- } else {
- count = q ? 4: 2;
- }
-
- /* To avoid excessive duplication of ops we implement shift
- * by immediate using the variable shift operations.
- */
- imm = dup_const(size, shift);
-
- for (pass = 0; pass < count; pass++) {
- if (size == 3) {
- neon_load_reg64(cpu_V0, rm + pass);
- tcg_gen_movi_i64(cpu_V1, imm);
- switch (op) {
- case 6: /* VQSHLU */
- gen_helper_neon_qshlu_s64(cpu_V0, cpu_env,
- cpu_V0, cpu_V1);
- break;
- case 7: /* VQSHL */
- if (u) {
- gen_helper_neon_qshl_u64(cpu_V0, cpu_env,
- cpu_V0, cpu_V1);
- } else {
- gen_helper_neon_qshl_s64(cpu_V0, cpu_env,
- cpu_V0, cpu_V1);
- }
- break;
- default:
- g_assert_not_reached();
- }
- neon_store_reg64(cpu_V0, rd + pass);
- } else { /* size < 3 */
- /* Operands in T0 and T1. */
- tmp = neon_load_reg(rm, pass);
- tmp2 = tcg_temp_new_i32();
- tcg_gen_movi_i32(tmp2, imm);
- switch (op) {
- case 6: /* VQSHLU */
- switch (size) {
- case 0:
- gen_helper_neon_qshlu_s8(tmp, cpu_env,
- tmp, tmp2);
- break;
- case 1:
- gen_helper_neon_qshlu_s16(tmp, cpu_env,
- tmp, tmp2);
- break;
- case 2:
- gen_helper_neon_qshlu_s32(tmp, cpu_env,
- tmp, tmp2);
- break;
- default:
- abort();
- }
- break;
- case 7: /* VQSHL */
- GEN_NEON_INTEGER_OP_ENV(qshl);
- break;
- default:
- g_assert_not_reached();
- }
- tcg_temp_free_i32(tmp2);
- neon_store_reg(rd, pass, tmp);
- }
- } /* for pass */
- } else if (op < 10) {
- /* Shift by immediate and narrow:
- VSHRN, VRSHRN, VQSHRN, VQRSHRN. */
- int input_unsigned = (op == 8) ? !u : u;
- if (rm & 1) {
- return 1;
- }
- shift = shift - (1 << (size + 3));
- size++;
- if (size == 3) {
- tmp64 = tcg_const_i64(shift);
- neon_load_reg64(cpu_V0, rm);
- neon_load_reg64(cpu_V1, rm + 1);
- for (pass = 0; pass < 2; pass++) {
- TCGv_i64 in;
- if (pass == 0) {
- in = cpu_V0;
- } else {
- in = cpu_V1;
- }
- if (q) {
- if (input_unsigned) {
- gen_helper_neon_rshl_u64(cpu_V0, in, tmp64);
- } else {
- gen_helper_neon_rshl_s64(cpu_V0, in, tmp64);
- }
- } else {
- if (input_unsigned) {
- gen_ushl_i64(cpu_V0, in, tmp64);
- } else {
- gen_sshl_i64(cpu_V0, in, tmp64);
- }
- }
- tmp = tcg_temp_new_i32();
- gen_neon_narrow_op(op == 8, u, size - 1, tmp, cpu_V0);
- neon_store_reg(rd, pass, tmp);
- } /* for pass */
- tcg_temp_free_i64(tmp64);
- } else {
- if (size == 1) {
- imm = (uint16_t)shift;
- imm |= imm << 16;
- } else {
- /* size == 2 */
- imm = (uint32_t)shift;
- }
- tmp2 = tcg_const_i32(imm);
- tmp4 = neon_load_reg(rm + 1, 0);
- tmp5 = neon_load_reg(rm + 1, 1);
- for (pass = 0; pass < 2; pass++) {
- if (pass == 0) {
- tmp = neon_load_reg(rm, 0);
- } else {
- tmp = tmp4;
- }
- gen_neon_shift_narrow(size, tmp, tmp2, q,
- input_unsigned);
- if (pass == 0) {
- tmp3 = neon_load_reg(rm, 1);
- } else {
- tmp3 = tmp5;
- }
- gen_neon_shift_narrow(size, tmp3, tmp2, q,
- input_unsigned);
- tcg_gen_concat_i32_i64(cpu_V0, tmp, tmp3);
- tcg_temp_free_i32(tmp);
- tcg_temp_free_i32(tmp3);
- tmp = tcg_temp_new_i32();
- gen_neon_narrow_op(op == 8, u, size - 1, tmp, cpu_V0);
- neon_store_reg(rd, pass, tmp);
- } /* for pass */
- tcg_temp_free_i32(tmp2);
- }
- } else if (op == 10) {
- /* VSHLL, VMOVL */
- if (q || (rd & 1)) {
- return 1;
- }
- tmp = neon_load_reg(rm, 0);
- tmp2 = neon_load_reg(rm, 1);
- for (pass = 0; pass < 2; pass++) {
- if (pass == 1)
- tmp = tmp2;
-
- gen_neon_widen(cpu_V0, tmp, size, u);
-
- if (shift != 0) {
- /* The shift is less than the width of the source
- type, so we can just shift the whole register. */
- tcg_gen_shli_i64(cpu_V0, cpu_V0, shift);
- /* Widen the result of shift: we need to clear
- * the potential overflow bits resulting from
- * left bits of the narrow input appearing as
- * right bits of left the neighbour narrow
- * input. */
- if (size < 2 || !u) {
- uint64_t imm64;
- if (size == 0) {
- imm = (0xffu >> (8 - shift));
- imm |= imm << 16;
- } else if (size == 1) {
- imm = 0xffff >> (16 - shift);
- } else {
- /* size == 2 */
- imm = 0xffffffff >> (32 - shift);
- }
- if (size < 2) {
- imm64 = imm | (((uint64_t)imm) << 32);
- } else {
- imm64 = imm;
- }
- tcg_gen_andi_i64(cpu_V0, cpu_V0, ~imm64);
- }
- }
- neon_store_reg64(cpu_V0, rd + pass);
- }
- } else if (op >= 14) {
- /* VCVT fixed-point. */
- TCGv_ptr fpst;
- TCGv_i32 shiftv;
- VFPGenFixPointFn *fn;
-
- if (!(insn & (1 << 21)) || (q && ((rd | rm) & 1))) {
- return 1;
- }
-
- if (!(op & 1)) {
- if (u) {
- fn = gen_helper_vfp_ultos;
- } else {
- fn = gen_helper_vfp_sltos;
- }
- } else {
- if (u) {
- fn = gen_helper_vfp_touls_round_to_zero;
- } else {
- fn = gen_helper_vfp_tosls_round_to_zero;
- }
- }
-
- /* We have already masked out the must-be-1 top bit of imm6,
- * hence this 32-shift where the ARM ARM has 64-imm6.
- */
- shift = 32 - shift;
- fpst = get_fpstatus_ptr(1);
- shiftv = tcg_const_i32(shift);
- for (pass = 0; pass < (q ? 4 : 2); pass++) {
- TCGv_i32 tmpf = neon_load_reg(rm, pass);
- fn(tmpf, tmpf, shiftv, fpst);
- neon_store_reg(rd, pass, tmpf);
- }
- tcg_temp_free_ptr(fpst);
- tcg_temp_free_i32(shiftv);
- } else {
- return 1;
- }
- } else { /* (insn & 0x00380080) == 0 */
- int invert, reg_ofs, vec_size;
-
- if (q && (rd & 1)) {
- return 1;
- }
-
- op = (insn >> 8) & 0xf;
- /* One register and immediate. */
- imm = (u << 7) | ((insn >> 12) & 0x70) | (insn & 0xf);
- invert = (insn & (1 << 5)) != 0;
- /* Note that op = 2,3,4,5,6,7,10,11,12,13 imm=0 is UNPREDICTABLE.
- * We choose to not special-case this and will behave as if a
- * valid constant encoding of 0 had been given.
- */
- switch (op) {
- case 0: case 1:
- /* no-op */
- break;
- case 2: case 3:
- imm <<= 8;
- break;
- case 4: case 5:
- imm <<= 16;
- break;
- case 6: case 7:
- imm <<= 24;
- break;
- case 8: case 9:
- imm |= imm << 16;
- break;
- case 10: case 11:
- imm = (imm << 8) | (imm << 24);
- break;
- case 12:
- imm = (imm << 8) | 0xff;
- break;
- case 13:
- imm = (imm << 16) | 0xffff;
- break;
- case 14:
- imm |= (imm << 8) | (imm << 16) | (imm << 24);
- if (invert) {
- imm = ~imm;
- }
- break;
- case 15:
- if (invert) {
- return 1;
- }
- imm = ((imm & 0x80) << 24) | ((imm & 0x3f) << 19)
- | ((imm & 0x40) ? (0x1f << 25) : (1 << 30));
- break;
- }
- if (invert) {
- imm = ~imm;
- }
-
- reg_ofs = neon_reg_offset(rd, 0);
- vec_size = q ? 16 : 8;
-
- if (op & 1 && op < 12) {
- if (invert) {
- /* The immediate value has already been inverted,
- * so BIC becomes AND.
- */
- tcg_gen_gvec_andi(MO_32, reg_ofs, reg_ofs, imm,
- vec_size, vec_size);
- } else {
- tcg_gen_gvec_ori(MO_32, reg_ofs, reg_ofs, imm,
- vec_size, vec_size);
- }
- } else {
- /* VMOV, VMVN. */
- if (op == 14 && invert) {
- TCGv_i64 t64 = tcg_temp_new_i64();
-
- for (pass = 0; pass <= q; ++pass) {
- uint64_t val = 0;
- int n;
-
- for (n = 0; n < 8; n++) {
- if (imm & (1 << (n + pass * 8))) {
- val |= 0xffull << (n * 8);
- }
- }
- tcg_gen_movi_i64(t64, val);
- neon_store_reg64(t64, rd + pass);
- }
- tcg_temp_free_i64(t64);
- } else {
- tcg_gen_gvec_dup_imm(MO_32, reg_ofs, vec_size,
- vec_size, imm);
- }
- }
- }
+ /* Two registers and shift or reg and imm: handled by decodetree */
+ return 1;
} else { /* (insn & 0x00800010 == 0x00800000) */
if (size != 3) {
op = (insn >> 8) & 0xf;
@@ -6350,34 +5866,30 @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn)
if (!dc_isar_feature(aa32_aes, s) || ((rm | rd) & 1)) {
return 1;
}
- ptr1 = vfp_reg_ptr(true, rd);
- ptr2 = vfp_reg_ptr(true, rm);
-
- /* Bit 6 is the lowest opcode bit; it distinguishes between
- * encryption (AESE/AESMC) and decryption (AESD/AESIMC)
- */
- tmp3 = tcg_const_i32(extract32(insn, 6, 1));
-
+ /*
+ * Bit 6 is the lowest opcode bit; it distinguishes
+ * between encryption (AESE/AESMC) and decryption
+ * (AESD/AESIMC).
+ */
if (op == NEON_2RM_AESE) {
- gen_helper_crypto_aese(ptr1, ptr2, tmp3);
+ tcg_gen_gvec_3_ool(vfp_reg_offset(true, rd),
+ vfp_reg_offset(true, rd),
+ vfp_reg_offset(true, rm),
+ 16, 16, extract32(insn, 6, 1),
+ gen_helper_crypto_aese);
} else {
- gen_helper_crypto_aesmc(ptr1, ptr2, tmp3);
+ tcg_gen_gvec_2_ool(vfp_reg_offset(true, rd),
+ vfp_reg_offset(true, rm),
+ 16, 16, extract32(insn, 6, 1),
+ gen_helper_crypto_aesmc);
}
- tcg_temp_free_ptr(ptr1);
- tcg_temp_free_ptr(ptr2);
- tcg_temp_free_i32(tmp3);
break;
case NEON_2RM_SHA1H:
if (!dc_isar_feature(aa32_sha1, s) || ((rm | rd) & 1)) {
return 1;
}
- ptr1 = vfp_reg_ptr(true, rd);
- ptr2 = vfp_reg_ptr(true, rm);
-
- gen_helper_crypto_sha1h(ptr1, ptr2);
-
- tcg_temp_free_ptr(ptr1);
- tcg_temp_free_ptr(ptr2);
+ tcg_gen_gvec_2_ool(rd_ofs, rm_ofs, 16, 16, 0,
+ gen_helper_crypto_sha1h);
break;
case NEON_2RM_SHA1SU1:
if ((rm | rd) & 1) {
@@ -6391,17 +5903,10 @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn)
} else if (!dc_isar_feature(aa32_sha1, s)) {
return 1;
}
- ptr1 = vfp_reg_ptr(true, rd);
- ptr2 = vfp_reg_ptr(true, rm);
- if (q) {
- gen_helper_crypto_sha256su0(ptr1, ptr2);
- } else {
- gen_helper_crypto_sha1su1(ptr1, ptr2);
- }
- tcg_temp_free_ptr(ptr1);
- tcg_temp_free_ptr(ptr2);
+ tcg_gen_gvec_2_ool(rd_ofs, rm_ofs, 16, 16, 0,
+ q ? gen_helper_crypto_sha256su0
+ : gen_helper_crypto_sha1su1);
break;
-
case NEON_2RM_VMVN:
tcg_gen_gvec_not(0, rd_ofs, rm_ofs, vec_size, vec_size);
break;
generated by cgit v1.2.3 (git 2.26.2) at 2025-03-04 23:18:01 +0000