aboutsummaryrefslogtreecommitdiff
path: root/target
diff options
context:
space:
mode:
Diffstat (limited to 'target')
-rw-r--r--target/arm/cpu.c2
-rw-r--r--target/arm/cpu.h2
-rw-r--r--target/arm/cpu64.c10
-rw-r--r--target/arm/kvm.c4
-rw-r--r--target/arm/kvm64.c14
-rw-r--r--target/arm/kvm_arm.h21
-rw-r--r--target/arm/neon-dp.decode106
-rw-r--r--target/arm/translate-a64.c20
-rw-r--r--target/arm/translate-neon.inc.c1191
-rw-r--r--target/arm/translate-vfp.inc.c7
-rw-r--r--target/arm/translate.c1064
-rw-r--r--target/arm/translate.h8
12 files changed, 1337 insertions, 1112 deletions
diff --git a/target/arm/cpu.c b/target/arm/cpu.c
index 5b7a36b5d7..e44e18062c 100644
--- a/target/arm/cpu.c
+++ b/target/arm/cpu.c
@@ -1108,7 +1108,7 @@ static void arm_set_pmu(Object *obj, bool value, Error **errp)
ARMCPU *cpu = ARM_CPU(obj);
if (value) {
- if (kvm_enabled() && !kvm_arm_pmu_supported(CPU(cpu))) {
+ if (kvm_enabled() && !kvm_arm_pmu_supported()) {
error_setg(errp, "'pmu' feature not supported by KVM on this host");
return;
}
diff --git a/target/arm/cpu.h b/target/arm/cpu.h
index 677584e5da..cf66b8c7fb 100644
--- a/target/arm/cpu.h
+++ b/target/arm/cpu.h
@@ -2334,7 +2334,7 @@ static inline uint64_t cpreg_to_kvm_id(uint32_t cpregid)
* migration or KVM state synchronization. (Typically this is for "registers"
* which are actually used as instructions for cache maintenance and so on.)
* IO indicates that this register does I/O and therefore its accesses
- * need to be surrounded by gen_io_start()/gen_io_end(). In particular,
+ * need to be marked with gen_io_start() and also end the TB. In particular,
* registers which implement clocks or timers require this.
* RAISES_EXC is for when the read or write hook might raise an exception;
* the generated code will synchronize the CPU state before calling the hook
diff --git a/target/arm/cpu64.c b/target/arm/cpu64.c
index 778cecc2e6..a0c1d8894b 100644
--- a/target/arm/cpu64.c
+++ b/target/arm/cpu64.c
@@ -266,7 +266,7 @@ void arm_cpu_sve_finalize(ARMCPU *cpu, Error **errp)
/* Collect the set of vector lengths supported by KVM. */
bitmap_zero(kvm_supported, ARM_MAX_VQ);
- if (kvm_enabled() && kvm_arm_sve_supported(CPU(cpu))) {
+ if (kvm_enabled() && kvm_arm_sve_supported()) {
kvm_arm_sve_get_vls(CPU(cpu), kvm_supported);
} else if (kvm_enabled()) {
assert(!cpu_isar_feature(aa64_sve, cpu));
@@ -473,7 +473,7 @@ static void cpu_max_set_sve_max_vq(Object *obj, Visitor *v, const char *name,
return;
}
- if (kvm_enabled() && !kvm_arm_sve_supported(CPU(cpu))) {
+ if (kvm_enabled() && !kvm_arm_sve_supported()) {
error_setg(errp, "cannot set sve-max-vq");
error_append_hint(errp, "SVE not supported by KVM on this host\n");
return;
@@ -519,7 +519,7 @@ static void cpu_arm_set_sve_vq(Object *obj, Visitor *v, const char *name,
return;
}
- if (value && kvm_enabled() && !kvm_arm_sve_supported(CPU(cpu))) {
+ if (value && kvm_enabled() && !kvm_arm_sve_supported()) {
error_setg(errp, "cannot enable %s", name);
error_append_hint(errp, "SVE not supported by KVM on this host\n");
return;
@@ -556,7 +556,7 @@ static void cpu_arm_set_sve(Object *obj, Visitor *v, const char *name,
return;
}
- if (value && kvm_enabled() && !kvm_arm_sve_supported(CPU(cpu))) {
+ if (value && kvm_enabled() && !kvm_arm_sve_supported()) {
error_setg(errp, "'sve' feature not supported by KVM on this host");
return;
}
@@ -751,7 +751,7 @@ static void aarch64_cpu_set_aarch64(Object *obj, bool value, Error **errp)
* uniform execution state like do_interrupt.
*/
if (value == false) {
- if (!kvm_enabled() || !kvm_arm_aarch32_supported(CPU(cpu))) {
+ if (!kvm_enabled() || !kvm_arm_aarch32_supported()) {
error_setg(errp, "'aarch64' feature cannot be disabled "
"unless KVM is enabled and 32-bit EL1 "
"is supported");
diff --git a/target/arm/kvm.c b/target/arm/kvm.c
index eef3bbd1cc..7c672c78b8 100644
--- a/target/arm/kvm.c
+++ b/target/arm/kvm.c
@@ -208,9 +208,9 @@ void kvm_arm_add_vcpu_properties(Object *obj)
}
}
-bool kvm_arm_pmu_supported(CPUState *cpu)
+bool kvm_arm_pmu_supported(void)
{
- return kvm_check_extension(cpu->kvm_state, KVM_CAP_ARM_PMU_V3);
+ return kvm_check_extension(kvm_state, KVM_CAP_ARM_PMU_V3);
}
int kvm_arm_get_max_vm_ipa_size(MachineState *ms)
diff --git a/target/arm/kvm64.c b/target/arm/kvm64.c
index f09ed9f4df..3dc494aaa7 100644
--- a/target/arm/kvm64.c
+++ b/target/arm/kvm64.c
@@ -652,18 +652,14 @@ bool kvm_arm_get_host_cpu_features(ARMHostCPUFeatures *ahcf)
return true;
}
-bool kvm_arm_aarch32_supported(CPUState *cpu)
+bool kvm_arm_aarch32_supported(void)
{
- KVMState *s = KVM_STATE(current_accel());
-
- return kvm_check_extension(s, KVM_CAP_ARM_EL1_32BIT);
+ return kvm_check_extension(kvm_state, KVM_CAP_ARM_EL1_32BIT);
}
-bool kvm_arm_sve_supported(CPUState *cpu)
+bool kvm_arm_sve_supported(void)
{
- KVMState *s = KVM_STATE(current_accel());
-
- return kvm_check_extension(s, KVM_CAP_ARM_SVE);
+ return kvm_check_extension(kvm_state, KVM_CAP_ARM_SVE);
}
QEMU_BUILD_BUG_ON(KVM_ARM64_SVE_VQ_MIN != 1);
@@ -798,7 +794,7 @@ int kvm_arch_init_vcpu(CPUState *cs)
env->features &= ~(1ULL << ARM_FEATURE_PMU);
}
if (cpu_isar_feature(aa64_sve, cpu)) {
- assert(kvm_arm_sve_supported(cs));
+ assert(kvm_arm_sve_supported());
cpu->kvm_init_features[0] |= 1 << KVM_ARM_VCPU_SVE;
}
diff --git a/target/arm/kvm_arm.h b/target/arm/kvm_arm.h
index 48bf5e16d5..a4ce4fd93d 100644
--- a/target/arm/kvm_arm.h
+++ b/target/arm/kvm_arm.h
@@ -269,29 +269,26 @@ void kvm_arm_add_vcpu_properties(Object *obj);
/**
* kvm_arm_aarch32_supported:
- * @cs: CPUState
*
- * Returns: true if the KVM VCPU can enable AArch32 mode
+ * Returns: true if KVM can enable AArch32 mode
* and false otherwise.
*/
-bool kvm_arm_aarch32_supported(CPUState *cs);
+bool kvm_arm_aarch32_supported(void);
/**
* kvm_arm_pmu_supported:
- * @cs: CPUState
*
- * Returns: true if the KVM VCPU can enable its PMU
+ * Returns: true if KVM can enable the PMU
* and false otherwise.
*/
-bool kvm_arm_pmu_supported(CPUState *cs);
+bool kvm_arm_pmu_supported(void);
/**
* kvm_arm_sve_supported:
- * @cs: CPUState
*
- * Returns true if the KVM VCPU can enable SVE and false otherwise.
+ * Returns true if KVM can enable SVE and false otherwise.
*/
-bool kvm_arm_sve_supported(CPUState *cs);
+bool kvm_arm_sve_supported(void);
/**
* kvm_arm_get_max_vm_ipa_size:
@@ -359,17 +356,17 @@ static inline void kvm_arm_set_cpu_features_from_host(ARMCPU *cpu)
static inline void kvm_arm_add_vcpu_properties(Object *obj) {}
-static inline bool kvm_arm_aarch32_supported(CPUState *cs)
+static inline bool kvm_arm_aarch32_supported(void)
{
return false;
}
-static inline bool kvm_arm_pmu_supported(CPUState *cs)
+static inline bool kvm_arm_pmu_supported(void)
{
return false;
}
-static inline bool kvm_arm_sve_supported(CPUState *cs)
+static inline bool kvm_arm_sve_supported(void)
{
return false;
}
diff --git a/target/arm/neon-dp.decode b/target/arm/neon-dp.decode
index 6d890b2161..686f9fbf46 100644
--- a/target/arm/neon-dp.decode
+++ b/target/arm/neon-dp.decode
@@ -429,6 +429,112 @@ Vimm_1r 1111 001 . 1 . 000 ... .... cmode:4 0 . op:1 1 .... @1reg_imm
vm=%vm_dp vd=%vd_dp size=1
VDUP_scalar 1111 001 1 1 . 11 index:1 100 .... 11 000 q:1 . 0 .... \
vm=%vm_dp vd=%vd_dp size=2
+
+ ##################################################################
+ # 2-reg-misc grouping:
+ # 1111 001 11 D 11 size:2 opc1:2 Vd:4 0 opc2:4 q:1 M 0 Vm:4
+ ##################################################################
+
+ &2misc vd vm q size
+
+ @2misc .... ... .. . .. size:2 .. .... . .... q:1 . . .... \
+ &2misc vm=%vm_dp vd=%vd_dp
+ @2misc_q0 .... ... .. . .. size:2 .. .... . .... . . . .... \
+ &2misc vm=%vm_dp vd=%vd_dp q=0
+ @2misc_q1 .... ... .. . .. size:2 .. .... . .... . . . .... \
+ &2misc vm=%vm_dp vd=%vd_dp q=1
+
+ VREV64 1111 001 11 . 11 .. 00 .... 0 0000 . . 0 .... @2misc
+ VREV32 1111 001 11 . 11 .. 00 .... 0 0001 . . 0 .... @2misc
+ VREV16 1111 001 11 . 11 .. 00 .... 0 0010 . . 0 .... @2misc
+
+ VPADDL_S 1111 001 11 . 11 .. 00 .... 0 0100 . . 0 .... @2misc
+ VPADDL_U 1111 001 11 . 11 .. 00 .... 0 0101 . . 0 .... @2misc
+
+ AESE 1111 001 11 . 11 .. 00 .... 0 0110 0 . 0 .... @2misc_q1
+ AESD 1111 001 11 . 11 .. 00 .... 0 0110 1 . 0 .... @2misc_q1
+ AESMC 1111 001 11 . 11 .. 00 .... 0 0111 0 . 0 .... @2misc_q1
+ AESIMC 1111 001 11 . 11 .. 00 .... 0 0111 1 . 0 .... @2misc_q1
+
+ VCLS 1111 001 11 . 11 .. 00 .... 0 1000 . . 0 .... @2misc
+ VCLZ 1111 001 11 . 11 .. 00 .... 0 1001 . . 0 .... @2misc
+ VCNT 1111 001 11 . 11 .. 00 .... 0 1010 . . 0 .... @2misc
+
+ VMVN 1111 001 11 . 11 .. 00 .... 0 1011 . . 0 .... @2misc
+
+ VPADAL_S 1111 001 11 . 11 .. 00 .... 0 1100 . . 0 .... @2misc
+ VPADAL_U 1111 001 11 . 11 .. 00 .... 0 1101 . . 0 .... @2misc
+
+ VQABS 1111 001 11 . 11 .. 00 .... 0 1110 . . 0 .... @2misc
+ VQNEG 1111 001 11 . 11 .. 00 .... 0 1111 . . 0 .... @2misc
+
+ VCGT0 1111 001 11 . 11 .. 01 .... 0 0000 . . 0 .... @2misc
+ VCGE0 1111 001 11 . 11 .. 01 .... 0 0001 . . 0 .... @2misc
+ VCEQ0 1111 001 11 . 11 .. 01 .... 0 0010 . . 0 .... @2misc
+ VCLE0 1111 001 11 . 11 .. 01 .... 0 0011 . . 0 .... @2misc
+ VCLT0 1111 001 11 . 11 .. 01 .... 0 0100 . . 0 .... @2misc
+
+ SHA1H 1111 001 11 . 11 .. 01 .... 0 0101 1 . 0 .... @2misc_q1
+
+ VABS 1111 001 11 . 11 .. 01 .... 0 0110 . . 0 .... @2misc
+ VNEG 1111 001 11 . 11 .. 01 .... 0 0111 . . 0 .... @2misc
+
+ VCGT0_F 1111 001 11 . 11 .. 01 .... 0 1000 . . 0 .... @2misc
+ VCGE0_F 1111 001 11 . 11 .. 01 .... 0 1001 . . 0 .... @2misc
+ VCEQ0_F 1111 001 11 . 11 .. 01 .... 0 1010 . . 0 .... @2misc
+ VCLE0_F 1111 001 11 . 11 .. 01 .... 0 1011 . . 0 .... @2misc
+ VCLT0_F 1111 001 11 . 11 .. 01 .... 0 1100 . . 0 .... @2misc
+
+ VABS_F 1111 001 11 . 11 .. 01 .... 0 1110 . . 0 .... @2misc
+ VNEG_F 1111 001 11 . 11 .. 01 .... 0 1111 . . 0 .... @2misc
+
+ VSWP 1111 001 11 . 11 .. 10 .... 0 0000 . . 0 .... @2misc
+ VTRN 1111 001 11 . 11 .. 10 .... 0 0001 . . 0 .... @2misc
+ VUZP 1111 001 11 . 11 .. 10 .... 0 0010 . . 0 .... @2misc
+ VZIP 1111 001 11 . 11 .. 10 .... 0 0011 . . 0 .... @2misc
+
+ VMOVN 1111 001 11 . 11 .. 10 .... 0 0100 0 . 0 .... @2misc_q0
+ # VQMOVUN: unsigned result (source is always signed)
+ VQMOVUN 1111 001 11 . 11 .. 10 .... 0 0100 1 . 0 .... @2misc_q0
+ # VQMOVN: signed result, source may be signed (_S) or unsigned (_U)
+ VQMOVN_S 1111 001 11 . 11 .. 10 .... 0 0101 0 . 0 .... @2misc_q0
+ VQMOVN_U 1111 001 11 . 11 .. 10 .... 0 0101 1 . 0 .... @2misc_q0
+
+ VSHLL 1111 001 11 . 11 .. 10 .... 0 0110 0 . 0 .... @2misc_q0
+
+ SHA1SU1 1111 001 11 . 11 .. 10 .... 0 0111 0 . 0 .... @2misc_q1
+ SHA256SU0 1111 001 11 . 11 .. 10 .... 0 0111 1 . 0 .... @2misc_q1
+
+ VRINTN 1111 001 11 . 11 .. 10 .... 0 1000 . . 0 .... @2misc
+ VRINTX 1111 001 11 . 11 .. 10 .... 0 1001 . . 0 .... @2misc
+ VRINTA 1111 001 11 . 11 .. 10 .... 0 1010 . . 0 .... @2misc
+ VRINTZ 1111 001 11 . 11 .. 10 .... 0 1011 . . 0 .... @2misc
+
+ VCVT_F16_F32 1111 001 11 . 11 .. 10 .... 0 1100 0 . 0 .... @2misc_q0
+
+ VRINTM 1111 001 11 . 11 .. 10 .... 0 1101 . . 0 .... @2misc
+
+ VCVT_F32_F16 1111 001 11 . 11 .. 10 .... 0 1110 0 . 0 .... @2misc_q0
+
+ VRINTP 1111 001 11 . 11 .. 10 .... 0 1111 . . 0 .... @2misc
+
+ VCVTAS 1111 001 11 . 11 .. 11 .... 0 0000 . . 0 .... @2misc
+ VCVTAU 1111 001 11 . 11 .. 11 .... 0 0001 . . 0 .... @2misc
+ VCVTNS 1111 001 11 . 11 .. 11 .... 0 0010 . . 0 .... @2misc
+ VCVTNU 1111 001 11 . 11 .. 11 .... 0 0011 . . 0 .... @2misc
+ VCVTPS 1111 001 11 . 11 .. 11 .... 0 0100 . . 0 .... @2misc
+ VCVTPU 1111 001 11 . 11 .. 11 .... 0 0101 . . 0 .... @2misc
+ VCVTMS 1111 001 11 . 11 .. 11 .... 0 0110 . . 0 .... @2misc
+ VCVTMU 1111 001 11 . 11 .. 11 .... 0 0111 . . 0 .... @2misc
+
+ VRECPE 1111 001 11 . 11 .. 11 .... 0 1000 . . 0 .... @2misc
+ VRSQRTE 1111 001 11 . 11 .. 11 .... 0 1001 . . 0 .... @2misc
+ VRECPE_F 1111 001 11 . 11 .. 11 .... 0 1010 . . 0 .... @2misc
+ VRSQRTE_F 1111 001 11 . 11 .. 11 .... 0 1011 . . 0 .... @2misc
+ VCVT_FS 1111 001 11 . 11 .. 11 .... 0 1100 . . 0 .... @2misc
+ VCVT_FU 1111 001 11 . 11 .. 11 .... 0 1101 . . 0 .... @2misc
+ VCVT_SF 1111 001 11 . 11 .. 11 .... 0 1110 . . 0 .... @2misc
+ VCVT_UF 1111 001 11 . 11 .. 11 .... 0 1111 . . 0 .... @2misc
]
# Subgroup for size != 0b11
diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c
index a0e72ad694..4cef862c41 100644
--- a/target/arm/translate-a64.c
+++ b/target/arm/translate-a64.c
@@ -9534,7 +9534,7 @@ static void handle_2misc_fcmp_zero(DisasContext *s, int opcode,
TCGv_i64 tcg_op = tcg_temp_new_i64();
TCGv_i64 tcg_zero = tcg_const_i64(0);
TCGv_i64 tcg_res = tcg_temp_new_i64();
- NeonGenTwoDoubleOPFn *genfn;
+ NeonGenTwoDoubleOpFn *genfn;
bool swap = false;
int pass;
@@ -9576,7 +9576,7 @@ static void handle_2misc_fcmp_zero(DisasContext *s, int opcode,
TCGv_i32 tcg_op = tcg_temp_new_i32();
TCGv_i32 tcg_zero = tcg_const_i32(0);
TCGv_i32 tcg_res = tcg_temp_new_i32();
- NeonGenTwoSingleOPFn *genfn;
+ NeonGenTwoSingleOpFn *genfn;
bool swap = false;
int pass, maxpasses;
@@ -11370,18 +11370,6 @@ static void disas_simd_3same_int(DisasContext *s, uint32_t insn)
genfn(tcg_res, tcg_op1, tcg_op2);
}
- if (opcode == 0xf) {
- /* SABA, UABA: accumulating ops */
- static NeonGenTwoOpFn * const fns[3] = {
- gen_helper_neon_add_u8,
- gen_helper_neon_add_u16,
- tcg_gen_add_i32,
- };
-
- read_vec_element_i32(s, tcg_op1, rd, pass, MO_32);
- fns[size](tcg_res, tcg_op1, tcg_res);
- }
-
write_vec_element_i32(s, tcg_res, rd, pass, MO_32);
tcg_temp_free_i32(tcg_res);
@@ -11917,8 +11905,8 @@ static void handle_2misc_pairwise(DisasContext *s, int opcode, bool u,
} else {
for (pass = 0; pass < maxpass; pass++) {
TCGv_i64 tcg_op = tcg_temp_new_i64();
- NeonGenOneOpFn *genfn;
- static NeonGenOneOpFn * const fns[2][2] = {
+ NeonGenOne64OpFn *genfn;
+ static NeonGenOne64OpFn * const fns[2][2] = {
{ gen_helper_neon_addlp_s8, gen_helper_neon_addlp_u8 },
{ gen_helper_neon_addlp_s16, gen_helper_neon_addlp_u16 },
};
diff --git a/target/arm/translate-neon.inc.c b/target/arm/translate-neon.inc.c
index a5aa56bbde..f6cb921573 100644
--- a/target/arm/translate-neon.inc.c
+++ b/target/arm/translate-neon.inc.c
@@ -54,6 +54,107 @@ static inline int rsub_8(DisasContext *s, int x)
#include "decode-neon-ls.inc.c"
#include "decode-neon-shared.inc.c"
+/* Return the offset of a 2**SIZE piece of a NEON register, at index ELE,
+ * where 0 is the least significant end of the register.
+ */
+static inline long
+neon_element_offset(int reg, int element, MemOp size)
+{
+ int element_size = 1 << size;
+ int ofs = element * element_size;
+#ifdef HOST_WORDS_BIGENDIAN
+ /* Calculate the offset assuming fully little-endian,
+ * then XOR to account for the order of the 8-byte units.
+ */
+ if (element_size < 8) {
+ ofs ^= 8 - element_size;
+ }
+#endif
+ return neon_reg_offset(reg, 0) + ofs;
+}
+
+static void neon_load_element(TCGv_i32 var, int reg, int ele, MemOp mop)
+{
+ long offset = neon_element_offset(reg, ele, mop & MO_SIZE);
+
+ switch (mop) {
+ case MO_UB:
+ tcg_gen_ld8u_i32(var, cpu_env, offset);
+ break;
+ case MO_UW:
+ tcg_gen_ld16u_i32(var, cpu_env, offset);
+ break;
+ case MO_UL:
+ tcg_gen_ld_i32(var, cpu_env, offset);
+ break;
+ default:
+ g_assert_not_reached();
+ }
+}
+
+static void neon_load_element64(TCGv_i64 var, int reg, int ele, MemOp mop)
+{
+ long offset = neon_element_offset(reg, ele, mop & MO_SIZE);
+
+ switch (mop) {
+ case MO_UB:
+ tcg_gen_ld8u_i64(var, cpu_env, offset);
+ break;
+ case MO_UW:
+ tcg_gen_ld16u_i64(var, cpu_env, offset);
+ break;
+ case MO_UL:
+ tcg_gen_ld32u_i64(var, cpu_env, offset);
+ break;
+ case MO_Q:
+ tcg_gen_ld_i64(var, cpu_env, offset);
+ break;
+ default:
+ g_assert_not_reached();
+ }
+}
+
+static void neon_store_element(int reg, int ele, MemOp size, TCGv_i32 var)
+{
+ long offset = neon_element_offset(reg, ele, size);
+
+ switch (size) {
+ case MO_8:
+ tcg_gen_st8_i32(var, cpu_env, offset);
+ break;
+ case MO_16:
+ tcg_gen_st16_i32(var, cpu_env, offset);
+ break;
+ case MO_32:
+ tcg_gen_st_i32(var, cpu_env, offset);
+ break;
+ default:
+ g_assert_not_reached();
+ }
+}
+
+static void neon_store_element64(int reg, int ele, MemOp size, TCGv_i64 var)
+{
+ long offset = neon_element_offset(reg, ele, size);
+
+ switch (size) {
+ case MO_8:
+ tcg_gen_st8_i64(var, cpu_env, offset);
+ break;
+ case MO_16:
+ tcg_gen_st16_i64(var, cpu_env, offset);
+ break;
+ case MO_32:
+ tcg_gen_st32_i64(var, cpu_env, offset);
+ break;
+ case MO_64:
+ tcg_gen_st_i64(var, cpu_env, offset);
+ break;
+ default:
+ g_assert_not_reached();
+ }
+}
+
static bool trans_VCMLA(DisasContext *s, arg_VCMLA *a)
{
int opr_sz;
@@ -1664,7 +1765,7 @@ static bool trans_VSHLL_U_2sh(DisasContext *s, arg_2reg_shift *a)
}
static bool do_fp_2sh(DisasContext *s, arg_2reg_shift *a,
- NeonGenTwoSingleOPFn *fn)
+ NeonGenTwoSingleOpFn *fn)
{
/* FP operations in 2-reg-and-shift group */
TCGv_i32 tmp, shiftv;
@@ -2970,3 +3071,1091 @@ static bool trans_VDUP_scalar(DisasContext *s, arg_VDUP_scalar *a)
a->q ? 16 : 8, a->q ? 16 : 8);
return true;
}
+
+static bool trans_VREV64(DisasContext *s, arg_VREV64 *a)
+{
+ int pass, half;
+
+ if (!arm_dc_feature(s, ARM_FEATURE_NEON)) {
+ return false;
+ }
+
+ /* UNDEF accesses to D16-D31 if they don't exist. */
+ if (!dc_isar_feature(aa32_simd_r32, s) &&
+ ((a->vd | a->vm) & 0x10)) {
+ return false;
+ }
+
+ if ((a->vd | a->vm) & a->q) {
+ return false;
+ }
+
+ if (a->size == 3) {
+ return false;
+ }
+
+ if (!vfp_access_check(s)) {
+ return true;
+ }
+
+ for (pass = 0; pass < (a->q ? 2 : 1); pass++) {
+ TCGv_i32 tmp[2];
+
+ for (half = 0; half < 2; half++) {
+ tmp[half] = neon_load_reg(a->vm, pass * 2 + half);
+ switch (a->size) {
+ case 0:
+ tcg_gen_bswap32_i32(tmp[half], tmp[half]);
+ break;
+ case 1:
+ gen_swap_half(tmp[half], tmp[half]);
+ break;
+ case 2:
+ break;
+ default:
+ g_assert_not_reached();
+ }
+ }
+ neon_store_reg(a->vd, pass * 2, tmp[1]);
+ neon_store_reg(a->vd, pass * 2 + 1, tmp[0]);
+ }
+ return true;
+}
+
+static bool do_2misc_pairwise(DisasContext *s, arg_2misc *a,
+ NeonGenWidenFn *widenfn,
+ NeonGenTwo64OpFn *opfn,
+ NeonGenTwo64OpFn *accfn)
+{
+ /*
+ * Pairwise long operations: widen both halves of the pair,
+ * combine the pairs with the opfn, and then possibly accumulate
+ * into the destination with the accfn.
+ */
+ int pass;
+
+ if (!arm_dc_feature(s, ARM_FEATURE_NEON)) {
+ return false;
+ }
+
+ /* UNDEF accesses to D16-D31 if they don't exist. */
+ if (!dc_isar_feature(aa32_simd_r32, s) &&
+ ((a->vd | a->vm) & 0x10)) {
+ return false;
+ }
+
+ if ((a->vd | a->vm) & a->q) {
+ return false;
+ }
+
+ if (!widenfn) {
+ return false;
+ }
+
+ if (!vfp_access_check(s)) {
+ return true;
+ }
+
+ for (pass = 0; pass < a->q + 1; pass++) {
+ TCGv_i32 tmp;
+ TCGv_i64 rm0_64, rm1_64, rd_64;
+
+ rm0_64 = tcg_temp_new_i64();
+ rm1_64 = tcg_temp_new_i64();
+ rd_64 = tcg_temp_new_i64();
+ tmp = neon_load_reg(a->vm, pass * 2);
+ widenfn(rm0_64, tmp);
+ tcg_temp_free_i32(tmp);
+ tmp = neon_load_reg(a->vm, pass * 2 + 1);
+ widenfn(rm1_64, tmp);
+ tcg_temp_free_i32(tmp);
+ opfn(rd_64, rm0_64, rm1_64);
+ tcg_temp_free_i64(rm0_64);
+ tcg_temp_free_i64(rm1_64);
+
+ if (accfn) {
+ TCGv_i64 tmp64 = tcg_temp_new_i64();
+ neon_load_reg64(tmp64, a->vd + pass);
+ accfn(rd_64, tmp64, rd_64);
+ tcg_temp_free_i64(tmp64);
+ }
+ neon_store_reg64(rd_64, a->vd + pass);
+ tcg_temp_free_i64(rd_64);
+ }
+ return true;
+}
+
+static bool trans_VPADDL_S(DisasContext *s, arg_2misc *a)
+{
+ static NeonGenWidenFn * const widenfn[] = {
+ gen_helper_neon_widen_s8,
+ gen_helper_neon_widen_s16,
+ tcg_gen_ext_i32_i64,
+ NULL,
+ };
+ static NeonGenTwo64OpFn * const opfn[] = {
+ gen_helper_neon_paddl_u16,
+ gen_helper_neon_paddl_u32,
+ tcg_gen_add_i64,
+ NULL,
+ };
+
+ return do_2misc_pairwise(s, a, widenfn[a->size], opfn[a->size], NULL);
+}
+
+static bool trans_VPADDL_U(DisasContext *s, arg_2misc *a)
+{
+ static NeonGenWidenFn * const widenfn[] = {
+ gen_helper_neon_widen_u8,
+ gen_helper_neon_widen_u16,
+ tcg_gen_extu_i32_i64,
+ NULL,
+ };
+ static NeonGenTwo64OpFn * const opfn[] = {
+ gen_helper_neon_paddl_u16,
+ gen_helper_neon_paddl_u32,
+ tcg_gen_add_i64,
+ NULL,
+ };
+
+ return do_2misc_pairwise(s, a, widenfn[a->size], opfn[a->size], NULL);
+}
+
+static bool trans_VPADAL_S(DisasContext *s, arg_2misc *a)
+{
+ static NeonGenWidenFn * const widenfn[] = {
+ gen_helper_neon_widen_s8,
+ gen_helper_neon_widen_s16,
+ tcg_gen_ext_i32_i64,
+ NULL,
+ };
+ static NeonGenTwo64OpFn * const opfn[] = {
+ gen_helper_neon_paddl_u16,
+ gen_helper_neon_paddl_u32,
+ tcg_gen_add_i64,
+ NULL,
+ };
+ static NeonGenTwo64OpFn * const accfn[] = {
+ gen_helper_neon_addl_u16,
+ gen_helper_neon_addl_u32,
+ tcg_gen_add_i64,
+ NULL,
+ };
+
+ return do_2misc_pairwise(s, a, widenfn[a->size], opfn[a->size],
+ accfn[a->size]);
+}
+
+static bool trans_VPADAL_U(DisasContext *s, arg_2misc *a)
+{
+ static NeonGenWidenFn * const widenfn[] = {
+ gen_helper_neon_widen_u8,
+ gen_helper_neon_widen_u16,
+ tcg_gen_extu_i32_i64,
+ NULL,
+ };
+ static NeonGenTwo64OpFn * const opfn[] = {
+ gen_helper_neon_paddl_u16,
+ gen_helper_neon_paddl_u32,
+ tcg_gen_add_i64,
+ NULL,
+ };
+ static NeonGenTwo64OpFn * const accfn[] = {
+ gen_helper_neon_addl_u16,
+ gen_helper_neon_addl_u32,
+ tcg_gen_add_i64,
+ NULL,
+ };
+
+ return do_2misc_pairwise(s, a, widenfn[a->size], opfn[a->size],
+ accfn[a->size]);
+}
+
+typedef void ZipFn(TCGv_ptr, TCGv_ptr);
+
+static bool do_zip_uzp(DisasContext *s, arg_2misc *a,
+ ZipFn *fn)
+{
+ TCGv_ptr pd, pm;
+
+ if (!arm_dc_feature(s, ARM_FEATURE_NEON)) {
+ return false;
+ }
+
+ /* UNDEF accesses to D16-D31 if they don't exist. */
+ if (!dc_isar_feature(aa32_simd_r32, s) &&
+ ((a->vd | a->vm) & 0x10)) {
+ return false;
+ }
+
+ if ((a->vd | a->vm) & a->q) {
+ return false;
+ }
+
+ if (!fn) {
+ /* Bad size or size/q combination */
+ return false;
+ }
+
+ if (!vfp_access_check(s)) {
+ return true;
+ }
+
+ pd = vfp_reg_ptr(true, a->vd);
+ pm = vfp_reg_ptr(true, a->vm);
+ fn(pd, pm);
+ tcg_temp_free_ptr(pd);
+ tcg_temp_free_ptr(pm);
+ return true;
+}
+
+static bool trans_VUZP(DisasContext *s, arg_2misc *a)
+{
+ static ZipFn * const fn[2][4] = {
+ {
+ gen_helper_neon_unzip8,
+ gen_helper_neon_unzip16,
+ NULL,
+ NULL,
+ }, {
+ gen_helper_neon_qunzip8,
+ gen_helper_neon_qunzip16,
+ gen_helper_neon_qunzip32,
+ NULL,
+ }
+ };
+ return do_zip_uzp(s, a, fn[a->q][a->size]);
+}
+
+static bool trans_VZIP(DisasContext *s, arg_2misc *a)
+{
+ static ZipFn * const fn[2][4] = {
+ {
+ gen_helper_neon_zip8,
+ gen_helper_neon_zip16,
+ NULL,
+ NULL,
+ }, {
+ gen_helper_neon_qzip8,
+ gen_helper_neon_qzip16,
+ gen_helper_neon_qzip32,
+ NULL,
+ }
+ };
+ return do_zip_uzp(s, a, fn[a->q][a->size]);
+}
+
+static bool do_vmovn(DisasContext *s, arg_2misc *a,
+ NeonGenNarrowEnvFn *narrowfn)
+{
+ TCGv_i64 rm;
+ TCGv_i32 rd0, rd1;
+
+ if (!arm_dc_feature(s, ARM_FEATURE_NEON)) {
+ return false;
+ }
+
+ /* UNDEF accesses to D16-D31 if they don't exist. */
+ if (!dc_isar_feature(aa32_simd_r32, s) &&
+ ((a->vd | a->vm) & 0x10)) {
+ return false;
+ }
+
+ if (a->vm & 1) {
+ return false;
+ }
+
+ if (!narrowfn) {
+ return false;
+ }
+
+ if (!vfp_access_check(s)) {
+ return true;
+ }
+
+ rm = tcg_temp_new_i64();
+ rd0 = tcg_temp_new_i32();
+ rd1 = tcg_temp_new_i32();
+
+ neon_load_reg64(rm, a->vm);
+ narrowfn(rd0, cpu_env, rm);
+ neon_load_reg64(rm, a->vm + 1);
+ narrowfn(rd1, cpu_env, rm);
+ neon_store_reg(a->vd, 0, rd0);
+ neon_store_reg(a->vd, 1, rd1);
+ tcg_temp_free_i64(rm);
+ return true;
+}
+
+#define DO_VMOVN(INSN, FUNC) \
+ static bool trans_##INSN(DisasContext *s, arg_2misc *a) \
+ { \
+ static NeonGenNarrowEnvFn * const narrowfn[] = { \
+ FUNC##8, \
+ FUNC##16, \
+ FUNC##32, \
+ NULL, \
+ }; \
+ return do_vmovn(s, a, narrowfn[a->size]); \
+ }
+
+DO_VMOVN(VMOVN, gen_neon_narrow_u)
+DO_VMOVN(VQMOVUN, gen_helper_neon_unarrow_sat)
+DO_VMOVN(VQMOVN_S, gen_helper_neon_narrow_sat_s)
+DO_VMOVN(VQMOVN_U, gen_helper_neon_narrow_sat_u)
+
+static bool trans_VSHLL(DisasContext *s, arg_2misc *a)
+{
+ TCGv_i32 rm0, rm1;
+ TCGv_i64 rd;
+ static NeonGenWidenFn * const widenfns[] = {
+ gen_helper_neon_widen_u8,
+ gen_helper_neon_widen_u16,
+ tcg_gen_extu_i32_i64,
+ NULL,
+ };
+ NeonGenWidenFn *widenfn = widenfns[a->size];
+
+ if (!arm_dc_feature(s, ARM_FEATURE_NEON)) {
+ return false;
+ }
+
+ /* UNDEF accesses to D16-D31 if they don't exist. */
+ if (!dc_isar_feature(aa32_simd_r32, s) &&
+ ((a->vd | a->vm) & 0x10)) {
+ return false;
+ }
+
+ if (a->vd & 1) {
+ return false;
+ }
+
+ if (!widenfn) {
+ return false;
+ }
+
+ if (!vfp_access_check(s)) {
+ return true;
+ }
+
+ rd = tcg_temp_new_i64();
+
+ rm0 = neon_load_reg(a->vm, 0);
+ rm1 = neon_load_reg(a->vm, 1);
+
+ widenfn(rd, rm0);
+ tcg_gen_shli_i64(rd, rd, 8 << a->size);
+ neon_store_reg64(rd, a->vd);
+ widenfn(rd, rm1);
+ tcg_gen_shli_i64(rd, rd, 8 << a->size);
+ neon_store_reg64(rd, a->vd + 1);
+
+ tcg_temp_free_i64(rd);
+ tcg_temp_free_i32(rm0);
+ tcg_temp_free_i32(rm1);
+ return true;
+}
+
+static bool trans_VCVT_F16_F32(DisasContext *s, arg_2misc *a)
+{
+ TCGv_ptr fpst;
+ TCGv_i32 ahp, tmp, tmp2, tmp3;
+
+ if (!arm_dc_feature(s, ARM_FEATURE_NEON) ||
+ !dc_isar_feature(aa32_fp16_spconv, s)) {
+ return false;
+ }
+
+ /* UNDEF accesses to D16-D31 if they don't exist. */
+ if (!dc_isar_feature(aa32_simd_r32, s) &&
+ ((a->vd | a->vm) & 0x10)) {
+ return false;
+ }
+
+ if ((a->vm & 1) || (a->size != 1)) {
+ return false;
+ }
+
+ if (!vfp_access_check(s)) {
+ return true;
+ }
+
+ fpst = get_fpstatus_ptr(true);
+ ahp = get_ahp_flag();
+ tmp = neon_load_reg(a->vm, 0);
+ gen_helper_vfp_fcvt_f32_to_f16(tmp, tmp, fpst, ahp);
+ tmp2 = neon_load_reg(a->vm, 1);
+ gen_helper_vfp_fcvt_f32_to_f16(tmp2, tmp2, fpst, ahp);
+ tcg_gen_shli_i32(tmp2, tmp2, 16);
+ tcg_gen_or_i32(tmp2, tmp2, tmp);
+ tcg_temp_free_i32(tmp);
+ tmp = neon_load_reg(a->vm, 2);
+ gen_helper_vfp_fcvt_f32_to_f16(tmp, tmp, fpst, ahp);
+ tmp3 = neon_load_reg(a->vm, 3);
+ neon_store_reg(a->vd, 0, tmp2);
+ gen_helper_vfp_fcvt_f32_to_f16(tmp3, tmp3, fpst, ahp);
+ tcg_gen_shli_i32(tmp3, tmp3, 16);
+ tcg_gen_or_i32(tmp3, tmp3, tmp);
+ neon_store_reg(a->vd, 1, tmp3);
+ tcg_temp_free_i32(tmp);
+ tcg_temp_free_i32(ahp);
+ tcg_temp_free_ptr(fpst);
+
+ return true;
+}
+
+static bool trans_VCVT_F32_F16(DisasContext *s, arg_2misc *a)
+{
+ TCGv_ptr fpst;
+ TCGv_i32 ahp, tmp, tmp2, tmp3;
+
+ if (!arm_dc_feature(s, ARM_FEATURE_NEON) ||
+ !dc_isar_feature(aa32_fp16_spconv, s)) {
+ return false;
+ }
+
+ /* UNDEF accesses to D16-D31 if they don't exist. */
+ if (!dc_isar_feature(aa32_simd_r32, s) &&
+ ((a->vd | a->vm) & 0x10)) {
+ return false;
+ }
+
+ if ((a->vd & 1) || (a->size != 1)) {
+ return false;
+ }
+
+ if (!vfp_access_check(s)) {
+ return true;
+ }
+
+ fpst = get_fpstatus_ptr(true);
+ ahp = get_ahp_flag();
+ tmp3 = tcg_temp_new_i32();
+ tmp = neon_load_reg(a->vm, 0);
+ tmp2 = neon_load_reg(a->vm, 1);
+ tcg_gen_ext16u_i32(tmp3, tmp);
+ gen_helper_vfp_fcvt_f16_to_f32(tmp3, tmp3, fpst, ahp);
+ neon_store_reg(a->vd, 0, tmp3);
+ tcg_gen_shri_i32(tmp, tmp, 16);
+ gen_helper_vfp_fcvt_f16_to_f32(tmp, tmp, fpst, ahp);
+ neon_store_reg(a->vd, 1, tmp);
+ tmp3 = tcg_temp_new_i32();
+ tcg_gen_ext16u_i32(tmp3, tmp2);
+ gen_helper_vfp_fcvt_f16_to_f32(tmp3, tmp3, fpst, ahp);
+ neon_store_reg(a->vd, 2, tmp3);
+ tcg_gen_shri_i32(tmp2, tmp2, 16);
+ gen_helper_vfp_fcvt_f16_to_f32(tmp2, tmp2, fpst, ahp);
+ neon_store_reg(a->vd, 3, tmp2);
+ tcg_temp_free_i32(ahp);
+ tcg_temp_free_ptr(fpst);
+
+ return true;
+}
+
+static bool do_2misc_vec(DisasContext *s, arg_2misc *a, GVecGen2Fn *fn)
+{
+ int vec_size = a->q ? 16 : 8;
+ int rd_ofs = neon_reg_offset(a->vd, 0);
+ int rm_ofs = neon_reg_offset(a->vm, 0);
+
+ if (!arm_dc_feature(s, ARM_FEATURE_NEON)) {
+ return false;
+ }
+
+ /* UNDEF accesses to D16-D31 if they don't exist. */
+ if (!dc_isar_feature(aa32_simd_r32, s) &&
+ ((a->vd | a->vm) & 0x10)) {
+ return false;
+ }
+
+ if (a->size == 3) {
+ return false;
+ }
+
+ if ((a->vd | a->vm) & a->q) {
+ return false;
+ }
+
+ if (!vfp_access_check(s)) {
+ return true;
+ }
+
+ fn(a->size, rd_ofs, rm_ofs, vec_size, vec_size);
+
+ return true;
+}
+
+#define DO_2MISC_VEC(INSN, FN) \
+ static bool trans_##INSN(DisasContext *s, arg_2misc *a) \
+ { \
+ return do_2misc_vec(s, a, FN); \
+ }
+
+DO_2MISC_VEC(VNEG, tcg_gen_gvec_neg)
+DO_2MISC_VEC(VABS, tcg_gen_gvec_abs)
+DO_2MISC_VEC(VCEQ0, gen_gvec_ceq0)
+DO_2MISC_VEC(VCGT0, gen_gvec_cgt0)
+DO_2MISC_VEC(VCLE0, gen_gvec_cle0)
+DO_2MISC_VEC(VCGE0, gen_gvec_cge0)
+DO_2MISC_VEC(VCLT0, gen_gvec_clt0)
+
+static bool trans_VMVN(DisasContext *s, arg_2misc *a)
+{
+ if (a->size != 0) {
+ return false;
+ }
+ return do_2misc_vec(s, a, tcg_gen_gvec_not);
+}
+
+#define WRAP_2M_3_OOL_FN(WRAPNAME, FUNC, DATA) \
+ static void WRAPNAME(unsigned vece, uint32_t rd_ofs, \
+ uint32_t rm_ofs, uint32_t oprsz, \
+ uint32_t maxsz) \
+ { \
+ tcg_gen_gvec_3_ool(rd_ofs, rd_ofs, rm_ofs, oprsz, maxsz, \
+ DATA, FUNC); \
+ }
+
+#define WRAP_2M_2_OOL_FN(WRAPNAME, FUNC, DATA) \
+ static void WRAPNAME(unsigned vece, uint32_t rd_ofs, \
+ uint32_t rm_ofs, uint32_t oprsz, \
+ uint32_t maxsz) \
+ { \
+ tcg_gen_gvec_2_ool(rd_ofs, rm_ofs, oprsz, maxsz, DATA, FUNC); \
+ }
+
+WRAP_2M_3_OOL_FN(gen_AESE, gen_helper_crypto_aese, 0)
+WRAP_2M_3_OOL_FN(gen_AESD, gen_helper_crypto_aese, 1)
+WRAP_2M_2_OOL_FN(gen_AESMC, gen_helper_crypto_aesmc, 0)
+WRAP_2M_2_OOL_FN(gen_AESIMC, gen_helper_crypto_aesmc, 1)
+WRAP_2M_2_OOL_FN(gen_SHA1H, gen_helper_crypto_sha1h, 0)
+WRAP_2M_2_OOL_FN(gen_SHA1SU1, gen_helper_crypto_sha1su1, 0)
+WRAP_2M_2_OOL_FN(gen_SHA256SU0, gen_helper_crypto_sha256su0, 0)
+
+#define DO_2M_CRYPTO(INSN, FEATURE, SIZE) \
+ static bool trans_##INSN(DisasContext *s, arg_2misc *a) \
+ { \
+ if (!dc_isar_feature(FEATURE, s) || a->size != SIZE) { \
+ return false; \
+ } \
+ return do_2misc_vec(s, a, gen_##INSN); \
+ }
+
+DO_2M_CRYPTO(AESE, aa32_aes, 0)
+DO_2M_CRYPTO(AESD, aa32_aes, 0)
+DO_2M_CRYPTO(AESMC, aa32_aes, 0)
+DO_2M_CRYPTO(AESIMC, aa32_aes, 0)
+DO_2M_CRYPTO(SHA1H, aa32_sha1, 2)
+DO_2M_CRYPTO(SHA1SU1, aa32_sha1, 2)
+DO_2M_CRYPTO(SHA256SU0, aa32_sha2, 2)
+
+static bool do_2misc(DisasContext *s, arg_2misc *a, NeonGenOneOpFn *fn)
+{
+ int pass;
+
+ /* Handle a 2-reg-misc operation by iterating 32 bits at a time */
+ if (!arm_dc_feature(s, ARM_FEATURE_NEON)) {
+ return false;
+ }
+
+ /* UNDEF accesses to D16-D31 if they don't exist. */
+ if (!dc_isar_feature(aa32_simd_r32, s) &&
+ ((a->vd | a->vm) & 0x10)) {
+ return false;
+ }
+
+ if (!fn) {
+ return false;
+ }
+
+ if ((a->vd | a->vm) & a->q) {
+ return false;
+ }
+
+ if (!vfp_access_check(s)) {
+ return true;
+ }
+
+ for (pass = 0; pass < (a->q ? 4 : 2); pass++) {
+ TCGv_i32 tmp = neon_load_reg(a->vm, pass);
+ fn(tmp, tmp);
+ neon_store_reg(a->vd, pass, tmp);
+ }
+
+ return true;
+}
+
+static bool trans_VREV32(DisasContext *s, arg_2misc *a)
+{
+ static NeonGenOneOpFn * const fn[] = {
+ tcg_gen_bswap32_i32,
+ gen_swap_half,
+ NULL,
+ NULL,
+ };
+ return do_2misc(s, a, fn[a->size]);
+}
+
+static bool trans_VREV16(DisasContext *s, arg_2misc *a)
+{
+ if (a->size != 0) {
+ return false;
+ }
+ return do_2misc(s, a, gen_rev16);
+}
+
+static bool trans_VCLS(DisasContext *s, arg_2misc *a)
+{
+ static NeonGenOneOpFn * const fn[] = {
+ gen_helper_neon_cls_s8,
+ gen_helper_neon_cls_s16,
+ gen_helper_neon_cls_s32,
+ NULL,
+ };
+ return do_2misc(s, a, fn[a->size]);
+}
+
+static void do_VCLZ_32(TCGv_i32 rd, TCGv_i32 rm)
+{
+ tcg_gen_clzi_i32(rd, rm, 32);
+}
+
+static bool trans_VCLZ(DisasContext *s, arg_2misc *a)
+{
+ static NeonGenOneOpFn * const fn[] = {
+ gen_helper_neon_clz_u8,
+ gen_helper_neon_clz_u16,
+ do_VCLZ_32,
+ NULL,
+ };
+ return do_2misc(s, a, fn[a->size]);
+}
+
+static bool trans_VCNT(DisasContext *s, arg_2misc *a)
+{
+ if (a->size != 0) {
+ return false;
+ }
+ return do_2misc(s, a, gen_helper_neon_cnt_u8);
+}
+
+static bool trans_VABS_F(DisasContext *s, arg_2misc *a)
+{
+ if (a->size != 2) {
+ return false;
+ }
+ /* TODO: FP16 : size == 1 */
+ return do_2misc(s, a, gen_helper_vfp_abss);
+}
+
+static bool trans_VNEG_F(DisasContext *s, arg_2misc *a)
+{
+ if (a->size != 2) {
+ return false;
+ }
+ /* TODO: FP16 : size == 1 */
+ return do_2misc(s, a, gen_helper_vfp_negs);
+}
+
+static bool trans_VRECPE(DisasContext *s, arg_2misc *a)
+{
+ if (a->size != 2) {
+ return false;
+ }
+ return do_2misc(s, a, gen_helper_recpe_u32);
+}
+
+static bool trans_VRSQRTE(DisasContext *s, arg_2misc *a)
+{
+ if (a->size != 2) {
+ return false;
+ }
+ return do_2misc(s, a, gen_helper_rsqrte_u32);
+}
+
+#define WRAP_1OP_ENV_FN(WRAPNAME, FUNC) \
+ static void WRAPNAME(TCGv_i32 d, TCGv_i32 m) \
+ { \
+ FUNC(d, cpu_env, m); \
+ }
+
+WRAP_1OP_ENV_FN(gen_VQABS_s8, gen_helper_neon_qabs_s8)
+WRAP_1OP_ENV_FN(gen_VQABS_s16, gen_helper_neon_qabs_s16)
+WRAP_1OP_ENV_FN(gen_VQABS_s32, gen_helper_neon_qabs_s32)
+WRAP_1OP_ENV_FN(gen_VQNEG_s8, gen_helper_neon_qneg_s8)
+WRAP_1OP_ENV_FN(gen_VQNEG_s16, gen_helper_neon_qneg_s16)
+WRAP_1OP_ENV_FN(gen_VQNEG_s32, gen_helper_neon_qneg_s32)
+
+static bool trans_VQABS(DisasContext *s, arg_2misc *a)
+{
+ static NeonGenOneOpFn * const fn[] = {
+ gen_VQABS_s8,
+ gen_VQABS_s16,
+ gen_VQABS_s32,
+ NULL,
+ };
+ return do_2misc(s, a, fn[a->size]);
+}
+
+static bool trans_VQNEG(DisasContext *s, arg_2misc *a)
+{
+ static NeonGenOneOpFn * const fn[] = {
+ gen_VQNEG_s8,
+ gen_VQNEG_s16,
+ gen_VQNEG_s32,
+ NULL,
+ };
+ return do_2misc(s, a, fn[a->size]);
+}
+
+static bool do_2misc_fp(DisasContext *s, arg_2misc *a,
+ NeonGenOneSingleOpFn *fn)
+{
+ int pass;
+ TCGv_ptr fpst;
+
+ /* Handle a 2-reg-misc operation by iterating 32 bits at a time */
+ if (!arm_dc_feature(s, ARM_FEATURE_NEON)) {
+ return false;
+ }
+
+ /* UNDEF accesses to D16-D31 if they don't exist. */
+ if (!dc_isar_feature(aa32_simd_r32, s) &&
+ ((a->vd | a->vm) & 0x10)) {
+ return false;
+ }
+
+ if (a->size != 2) {
+ /* TODO: FP16 will be the size == 1 case */
+ return false;
+ }
+
+ if ((a->vd | a->vm) & a->q) {
+ return false;
+ }
+
+ if (!vfp_access_check(s)) {
+ return true;
+ }
+
+ fpst = get_fpstatus_ptr(1);
+ for (pass = 0; pass < (a->q ? 4 : 2); pass++) {
+ TCGv_i32 tmp = neon_load_reg(a->vm, pass);
+ fn(tmp, tmp, fpst);
+ neon_store_reg(a->vd, pass, tmp);
+ }
+ tcg_temp_free_ptr(fpst);
+
+ return true;
+}
+
+#define DO_2MISC_FP(INSN, FUNC) \
+ static bool trans_##INSN(DisasContext *s, arg_2misc *a) \
+ { \
+ return do_2misc_fp(s, a, FUNC); \
+ }
+
+DO_2MISC_FP(VRECPE_F, gen_helper_recpe_f32)
+DO_2MISC_FP(VRSQRTE_F, gen_helper_rsqrte_f32)
+DO_2MISC_FP(VCVT_FS, gen_helper_vfp_sitos)
+DO_2MISC_FP(VCVT_FU, gen_helper_vfp_uitos)
+DO_2MISC_FP(VCVT_SF, gen_helper_vfp_tosizs)
+DO_2MISC_FP(VCVT_UF, gen_helper_vfp_touizs)
+
+static bool trans_VRINTX(DisasContext *s, arg_2misc *a)
+{
+ if (!arm_dc_feature(s, ARM_FEATURE_V8)) {
+ return false;
+ }
+ return do_2misc_fp(s, a, gen_helper_rints_exact);
+}
+
+#define WRAP_FP_CMP0_FWD(WRAPNAME, FUNC) \
+ static void WRAPNAME(TCGv_i32 d, TCGv_i32 m, TCGv_ptr fpst) \
+ { \
+ TCGv_i32 zero = tcg_const_i32(0); \
+ FUNC(d, m, zero, fpst); \
+ tcg_temp_free_i32(zero); \
+ }
+#define WRAP_FP_CMP0_REV(WRAPNAME, FUNC) \
+ static void WRAPNAME(TCGv_i32 d, TCGv_i32 m, TCGv_ptr fpst) \
+ { \
+ TCGv_i32 zero = tcg_const_i32(0); \
+ FUNC(d, zero, m, fpst); \
+ tcg_temp_free_i32(zero); \
+ }
+
+#define DO_FP_CMP0(INSN, FUNC, REV) \
+ WRAP_FP_CMP0_##REV(gen_##INSN, FUNC) \
+ static bool trans_##INSN(DisasContext *s, arg_2misc *a) \
+ { \
+ return do_2misc_fp(s, a, gen_##INSN); \
+ }
+
+DO_FP_CMP0(VCGT0_F, gen_helper_neon_cgt_f32, FWD)
+DO_FP_CMP0(VCGE0_F, gen_helper_neon_cge_f32, FWD)
+DO_FP_CMP0(VCEQ0_F, gen_helper_neon_ceq_f32, FWD)
+DO_FP_CMP0(VCLE0_F, gen_helper_neon_cge_f32, REV)
+DO_FP_CMP0(VCLT0_F, gen_helper_neon_cgt_f32, REV)
+
+static bool do_vrint(DisasContext *s, arg_2misc *a, int rmode)
+{
+ /*
+ * Handle a VRINT* operation by iterating 32 bits at a time,
+ * with a specified rounding mode in operation.
+ */
+ int pass;
+ TCGv_ptr fpst;
+ TCGv_i32 tcg_rmode;
+
+ if (!arm_dc_feature(s, ARM_FEATURE_NEON) ||
+ !arm_dc_feature(s, ARM_FEATURE_V8)) {
+ return false;
+ }
+
+ /* UNDEF accesses to D16-D31 if they don't exist. */
+ if (!dc_isar_feature(aa32_simd_r32, s) &&
+ ((a->vd | a->vm) & 0x10)) {
+ return false;
+ }
+
+ if (a->size != 2) {
+ /* TODO: FP16 will be the size == 1 case */
+ return false;
+ }
+
+ if ((a->vd | a->vm) & a->q) {
+ return false;
+ }
+
+ if (!vfp_access_check(s)) {
+ return true;
+ }
+
+ fpst = get_fpstatus_ptr(1);
+ tcg_rmode = tcg_const_i32(arm_rmode_to_sf(rmode));
+ gen_helper_set_neon_rmode(tcg_rmode, tcg_rmode, cpu_env);
+ for (pass = 0; pass < (a->q ? 4 : 2); pass++) {
+ TCGv_i32 tmp = neon_load_reg(a->vm, pass);
+ gen_helper_rints(tmp, tmp, fpst);
+ neon_store_reg(a->vd, pass, tmp);
+ }
+ gen_helper_set_neon_rmode(tcg_rmode, tcg_rmode, cpu_env);
+ tcg_temp_free_i32(tcg_rmode);
+ tcg_temp_free_ptr(fpst);
+
+ return true;
+}
+
+#define DO_VRINT(INSN, RMODE) \
+ static bool trans_##INSN(DisasContext *s, arg_2misc *a) \
+ { \
+ return do_vrint(s, a, RMODE); \
+ }
+
+DO_VRINT(VRINTN, FPROUNDING_TIEEVEN)
+DO_VRINT(VRINTA, FPROUNDING_TIEAWAY)
+DO_VRINT(VRINTZ, FPROUNDING_ZERO)
+DO_VRINT(VRINTM, FPROUNDING_NEGINF)
+DO_VRINT(VRINTP, FPROUNDING_POSINF)
+
+static bool do_vcvt(DisasContext *s, arg_2misc *a, int rmode, bool is_signed)
+{
+ /*
+ * Handle a VCVT* operation by iterating 32 bits at a time,
+ * with a specified rounding mode in operation.
+ */
+ int pass;
+ TCGv_ptr fpst;
+ TCGv_i32 tcg_rmode, tcg_shift;
+
+ if (!arm_dc_feature(s, ARM_FEATURE_NEON) ||
+ !arm_dc_feature(s, ARM_FEATURE_V8)) {
+ return false;
+ }
+
+ /* UNDEF accesses to D16-D31 if they don't exist. */
+ if (!dc_isar_feature(aa32_simd_r32, s) &&
+ ((a->vd | a->vm) & 0x10)) {
+ return false;
+ }
+
+ if (a->size != 2) {
+ /* TODO: FP16 will be the size == 1 case */
+ return false;
+ }
+
+ if ((a->vd | a->vm) & a->q) {
+ return false;
+ }
+
+ if (!vfp_access_check(s)) {
+ return true;
+ }
+
+ fpst = get_fpstatus_ptr(1);
+ tcg_shift = tcg_const_i32(0);
+ tcg_rmode = tcg_const_i32(arm_rmode_to_sf(rmode));
+ gen_helper_set_neon_rmode(tcg_rmode, tcg_rmode, cpu_env);
+ for (pass = 0; pass < (a->q ? 4 : 2); pass++) {
+ TCGv_i32 tmp = neon_load_reg(a->vm, pass);
+ if (is_signed) {
+ gen_helper_vfp_tosls(tmp, tmp, tcg_shift, fpst);
+ } else {
+ gen_helper_vfp_touls(tmp, tmp, tcg_shift, fpst);
+ }
+ neon_store_reg(a->vd, pass, tmp);
+ }
+ gen_helper_set_neon_rmode(tcg_rmode, tcg_rmode, cpu_env);
+ tcg_temp_free_i32(tcg_rmode);
+ tcg_temp_free_i32(tcg_shift);
+ tcg_temp_free_ptr(fpst);
+
+ return true;
+}
+
+#define DO_VCVT(INSN, RMODE, SIGNED) \
+ static bool trans_##INSN(DisasContext *s, arg_2misc *a) \
+ { \
+ return do_vcvt(s, a, RMODE, SIGNED); \
+ }
+
+DO_VCVT(VCVTAU, FPROUNDING_TIEAWAY, false)
+DO_VCVT(VCVTAS, FPROUNDING_TIEAWAY, true)
+DO_VCVT(VCVTNU, FPROUNDING_TIEEVEN, false)
+DO_VCVT(VCVTNS, FPROUNDING_TIEEVEN, true)
+DO_VCVT(VCVTPU, FPROUNDING_POSINF, false)
+DO_VCVT(VCVTPS, FPROUNDING_POSINF, true)
+DO_VCVT(VCVTMU, FPROUNDING_NEGINF, false)
+DO_VCVT(VCVTMS, FPROUNDING_NEGINF, true)
+
+static bool trans_VSWP(DisasContext *s, arg_2misc *a)
+{
+ TCGv_i64 rm, rd;
+ int pass;
+
+ if (!arm_dc_feature(s, ARM_FEATURE_NEON)) {
+ return false;
+ }
+
+ /* UNDEF accesses to D16-D31 if they don't exist. */
+ if (!dc_isar_feature(aa32_simd_r32, s) &&
+ ((a->vd | a->vm) & 0x10)) {
+ return false;
+ }
+
+ if (a->size != 0) {
+ return false;
+ }
+
+ if ((a->vd | a->vm) & a->q) {
+ return false;
+ }
+
+ if (!vfp_access_check(s)) {
+ return true;
+ }
+
+ rm = tcg_temp_new_i64();
+ rd = tcg_temp_new_i64();
+ for (pass = 0; pass < (a->q ? 2 : 1); pass++) {
+ neon_load_reg64(rm, a->vm + pass);
+ neon_load_reg64(rd, a->vd + pass);
+ neon_store_reg64(rm, a->vd + pass);
+ neon_store_reg64(rd, a->vm + pass);
+ }
+ tcg_temp_free_i64(rm);
+ tcg_temp_free_i64(rd);
+
+ return true;
+}
+static void gen_neon_trn_u8(TCGv_i32 t0, TCGv_i32 t1)
+{
+ TCGv_i32 rd, tmp;
+
+ rd = tcg_temp_new_i32();
+ tmp = tcg_temp_new_i32();
+
+ tcg_gen_shli_i32(rd, t0, 8);
+ tcg_gen_andi_i32(rd, rd, 0xff00ff00);
+ tcg_gen_andi_i32(tmp, t1, 0x00ff00ff);
+ tcg_gen_or_i32(rd, rd, tmp);
+
+ tcg_gen_shri_i32(t1, t1, 8);
+ tcg_gen_andi_i32(t1, t1, 0x00ff00ff);
+ tcg_gen_andi_i32(tmp, t0, 0xff00ff00);
+ tcg_gen_or_i32(t1, t1, tmp);
+ tcg_gen_mov_i32(t0, rd);
+
+ tcg_temp_free_i32(tmp);
+ tcg_temp_free_i32(rd);
+}
+
+static void gen_neon_trn_u16(TCGv_i32 t0, TCGv_i32 t1)
+{
+ TCGv_i32 rd, tmp;
+
+ rd = tcg_temp_new_i32();
+ tmp = tcg_temp_new_i32();
+
+ tcg_gen_shli_i32(rd, t0, 16);
+ tcg_gen_andi_i32(tmp, t1, 0xffff);
+ tcg_gen_or_i32(rd, rd, tmp);
+ tcg_gen_shri_i32(t1, t1, 16);
+ tcg_gen_andi_i32(tmp, t0, 0xffff0000);
+ tcg_gen_or_i32(t1, t1, tmp);
+ tcg_gen_mov_i32(t0, rd);
+
+ tcg_temp_free_i32(tmp);
+ tcg_temp_free_i32(rd);
+}
+
+static bool trans_VTRN(DisasContext *s, arg_2misc *a)
+{
+ TCGv_i32 tmp, tmp2;
+ int pass;
+
+ if (!arm_dc_feature(s, ARM_FEATURE_NEON)) {
+ return false;
+ }
+
+ /* UNDEF accesses to D16-D31 if they don't exist. */
+ if (!dc_isar_feature(aa32_simd_r32, s) &&
+ ((a->vd | a->vm) & 0x10)) {
+ return false;
+ }
+
+ if ((a->vd | a->vm) & a->q) {
+ return false;
+ }
+
+ if (a->size == 3) {
+ return false;
+ }
+
+ if (!vfp_access_check(s)) {
+ return true;
+ }
+
+ if (a->size == 2) {
+ for (pass = 0; pass < (a->q ? 4 : 2); pass += 2) {
+ tmp = neon_load_reg(a->vm, pass);
+ tmp2 = neon_load_reg(a->vd, pass + 1);
+ neon_store_reg(a->vm, pass, tmp2);
+ neon_store_reg(a->vd, pass + 1, tmp);
+ }
+ } else {
+ for (pass = 0; pass < (a->q ? 4 : 2); pass++) {
+ tmp = neon_load_reg(a->vm, pass);
+ tmp2 = neon_load_reg(a->vd, pass);
+ if (a->size == 0) {
+ gen_neon_trn_u8(tmp, tmp2);
+ } else {
+ gen_neon_trn_u16(tmp, tmp2);
+ }
+ neon_store_reg(a->vm, pass, tmp2);
+ neon_store_reg(a->vd, pass, tmp);
+ }
+ }
+ return true;
+}
diff --git a/target/arm/translate-vfp.inc.c b/target/arm/translate-vfp.inc.c
index e1a9017598..bf31b18657 100644
--- a/target/arm/translate-vfp.inc.c
+++ b/target/arm/translate-vfp.inc.c
@@ -119,15 +119,14 @@ static bool full_vfp_access_check(DisasContext *s, bool ignore_vfp_enabled)
if (s->v7m_lspact) {
/*
* Lazy state saving affects external memory and also the NVIC,
- * so we must mark it as an IO operation for icount.
+ * so we must mark it as an IO operation for icount (and cause
+ * this to be the last insn in the TB).
*/
if (tb_cflags(s->base.tb) & CF_USE_ICOUNT) {
+ s->base.is_jmp = DISAS_UPDATE;
gen_io_start();
}
gen_helper_v7m_preserve_fp_state(cpu_env);
- if (tb_cflags(s->base.tb) & CF_USE_ICOUNT) {
- gen_io_end();
- }
/*
* If the preserve_fp_state helper doesn't throw an exception
* then it will clear LSPACT; we don't need to repeat this for
diff --git a/target/arm/translate.c b/target/arm/translate.c
index 6d18892ade..795964da1f 100644
--- a/target/arm/translate.c
+++ b/target/arm/translate.c
@@ -378,9 +378,9 @@ static void gen_revsh(TCGv_i32 dest, TCGv_i32 var)
}
/* Swap low and high halfwords. */
-static void gen_swap_half(TCGv_i32 var)
+static void gen_swap_half(TCGv_i32 dest, TCGv_i32 var)
{
- tcg_gen_rotri_i32(var, var, 16);
+ tcg_gen_rotri_i32(dest, var, 16);
}
/* Dual 16-bit add. Result placed in t0 and t1 is marked as dead.
@@ -1133,25 +1133,6 @@ neon_reg_offset (int reg, int n)
return vfp_reg_offset(0, sreg);
}
-/* Return the offset of a 2**SIZE piece of a NEON register, at index ELE,
- * where 0 is the least significant end of the register.
- */
-static inline long
-neon_element_offset(int reg, int element, MemOp size)
-{
- int element_size = 1 << size;
- int ofs = element * element_size;
-#ifdef HOST_WORDS_BIGENDIAN
- /* Calculate the offset assuming fully little-endian,
- * then XOR to account for the order of the 8-byte units.
- */
- if (element_size < 8) {
- ofs ^= 8 - element_size;
- }
-#endif
- return neon_reg_offset(reg, 0) + ofs;
-}
-
static TCGv_i32 neon_load_reg(int reg, int pass)
{
TCGv_i32 tmp = tcg_temp_new_i32();
@@ -1159,94 +1140,12 @@ static TCGv_i32 neon_load_reg(int reg, int pass)
return tmp;
}
-static void neon_load_element(TCGv_i32 var, int reg, int ele, MemOp mop)
-{
- long offset = neon_element_offset(reg, ele, mop & MO_SIZE);
-
- switch (mop) {
- case MO_UB:
- tcg_gen_ld8u_i32(var, cpu_env, offset);
- break;
- case MO_UW:
- tcg_gen_ld16u_i32(var, cpu_env, offset);
- break;
- case MO_UL:
- tcg_gen_ld_i32(var, cpu_env, offset);
- break;
- default:
- g_assert_not_reached();
- }
-}
-
-static void neon_load_element64(TCGv_i64 var, int reg, int ele, MemOp mop)
-{
- long offset = neon_element_offset(reg, ele, mop & MO_SIZE);
-
- switch (mop) {
- case MO_UB:
- tcg_gen_ld8u_i64(var, cpu_env, offset);
- break;
- case MO_UW:
- tcg_gen_ld16u_i64(var, cpu_env, offset);
- break;
- case MO_UL:
- tcg_gen_ld32u_i64(var, cpu_env, offset);
- break;
- case MO_Q:
- tcg_gen_ld_i64(var, cpu_env, offset);
- break;
- default:
- g_assert_not_reached();
- }
-}
-
static void neon_store_reg(int reg, int pass, TCGv_i32 var)
{
tcg_gen_st_i32(var, cpu_env, neon_reg_offset(reg, pass));
tcg_temp_free_i32(var);
}
-static void neon_store_element(int reg, int ele, MemOp size, TCGv_i32 var)
-{
- long offset = neon_element_offset(reg, ele, size);
-
- switch (size) {
- case MO_8:
- tcg_gen_st8_i32(var, cpu_env, offset);
- break;
- case MO_16:
- tcg_gen_st16_i32(var, cpu_env, offset);
- break;
- case MO_32:
- tcg_gen_st_i32(var, cpu_env, offset);
- break;
- default:
- g_assert_not_reached();
- }
-}
-
-static void neon_store_element64(int reg, int ele, MemOp size, TCGv_i64 var)
-{
- long offset = neon_element_offset(reg, ele, size);
-
- switch (size) {
- case MO_8:
- tcg_gen_st8_i64(var, cpu_env, offset);
- break;
- case MO_16:
- tcg_gen_st16_i64(var, cpu_env, offset);
- break;
- case MO_32:
- tcg_gen_st32_i64(var, cpu_env, offset);
- break;
- case MO_64:
- tcg_gen_st_i64(var, cpu_env, offset);
- break;
- default:
- g_assert_not_reached();
- }
-}
-
static inline void neon_load_reg64(TCGv_i64 var, int reg)
{
tcg_gen_ld_i64(var, cpu_env, vfp_reg_offset(1, reg));
@@ -2934,377 +2833,6 @@ static void gen_exception_return(DisasContext *s, TCGv_i32 pc)
gen_rfe(s, pc, load_cpu_field(spsr));
}
-#define CPU_V001 cpu_V0, cpu_V0, cpu_V1
-
-static int gen_neon_unzip(int rd, int rm, int size, int q)
-{
- TCGv_ptr pd, pm;
-
- if (!q && size == 2) {
- return 1;
- }
- pd = vfp_reg_ptr(true, rd);
- pm = vfp_reg_ptr(true, rm);
- if (q) {
- switch (size) {
- case 0:
- gen_helper_neon_qunzip8(pd, pm);
- break;
- case 1:
- gen_helper_neon_qunzip16(pd, pm);
- break;
- case 2:
- gen_helper_neon_qunzip32(pd, pm);
- break;
- default:
- abort();
- }
- } else {
- switch (size) {
- case 0:
- gen_helper_neon_unzip8(pd, pm);
- break;
- case 1:
- gen_helper_neon_unzip16(pd, pm);
- break;
- default:
- abort();
- }
- }
- tcg_temp_free_ptr(pd);
- tcg_temp_free_ptr(pm);
- return 0;
-}
-
-static int gen_neon_zip(int rd, int rm, int size, int q)
-{
- TCGv_ptr pd, pm;
-
- if (!q && size == 2) {
- return 1;
- }
- pd = vfp_reg_ptr(true, rd);
- pm = vfp_reg_ptr(true, rm);
- if (q) {
- switch (size) {
- case 0:
- gen_helper_neon_qzip8(pd, pm);
- break;
- case 1:
- gen_helper_neon_qzip16(pd, pm);
- break;
- case 2:
- gen_helper_neon_qzip32(pd, pm);
- break;
- default:
- abort();
- }
- } else {
- switch (size) {
- case 0:
- gen_helper_neon_zip8(pd, pm);
- break;
- case 1:
- gen_helper_neon_zip16(pd, pm);
- break;
- default:
- abort();
- }
- }
- tcg_temp_free_ptr(pd);
- tcg_temp_free_ptr(pm);
- return 0;
-}
-
-static void gen_neon_trn_u8(TCGv_i32 t0, TCGv_i32 t1)
-{
- TCGv_i32 rd, tmp;
-
- rd = tcg_temp_new_i32();
- tmp = tcg_temp_new_i32();
-
- tcg_gen_shli_i32(rd, t0, 8);
- tcg_gen_andi_i32(rd, rd, 0xff00ff00);
- tcg_gen_andi_i32(tmp, t1, 0x00ff00ff);
- tcg_gen_or_i32(rd, rd, tmp);
-
- tcg_gen_shri_i32(t1, t1, 8);
- tcg_gen_andi_i32(t1, t1, 0x00ff00ff);
- tcg_gen_andi_i32(tmp, t0, 0xff00ff00);
- tcg_gen_or_i32(t1, t1, tmp);
- tcg_gen_mov_i32(t0, rd);
-
- tcg_temp_free_i32(tmp);
- tcg_temp_free_i32(rd);
-}
-
-static void gen_neon_trn_u16(TCGv_i32 t0, TCGv_i32 t1)
-{
- TCGv_i32 rd, tmp;
-
- rd = tcg_temp_new_i32();
- tmp = tcg_temp_new_i32();
-
- tcg_gen_shli_i32(rd, t0, 16);
- tcg_gen_andi_i32(tmp, t1, 0xffff);
- tcg_gen_or_i32(rd, rd, tmp);
- tcg_gen_shri_i32(t1, t1, 16);
- tcg_gen_andi_i32(tmp, t0, 0xffff0000);
- tcg_gen_or_i32(t1, t1, tmp);
- tcg_gen_mov_i32(t0, rd);
-
- tcg_temp_free_i32(tmp);
- tcg_temp_free_i32(rd);
-}
-
-static inline void gen_neon_narrow(int size, TCGv_i32 dest, TCGv_i64 src)
-{
- switch (size) {
- case 0: gen_helper_neon_narrow_u8(dest, src); break;
- case 1: gen_helper_neon_narrow_u16(dest, src); break;
- case 2: tcg_gen_extrl_i64_i32(dest, src); break;
- default: abort();
- }
-}
-
-static inline void gen_neon_narrow_sats(int size, TCGv_i32 dest, TCGv_i64 src)
-{
- switch (size) {
- case 0: gen_helper_neon_narrow_sat_s8(dest, cpu_env, src); break;
- case 1: gen_helper_neon_narrow_sat_s16(dest, cpu_env, src); break;
- case 2: gen_helper_neon_narrow_sat_s32(dest, cpu_env, src); break;
- default: abort();
- }
-}
-
-static inline void gen_neon_narrow_satu(int size, TCGv_i32 dest, TCGv_i64 src)
-{
- switch (size) {
- case 0: gen_helper_neon_narrow_sat_u8(dest, cpu_env, src); break;
- case 1: gen_helper_neon_narrow_sat_u16(dest, cpu_env, src); break;
- case 2: gen_helper_neon_narrow_sat_u32(dest, cpu_env, src); break;
- default: abort();
- }
-}
-
-static inline void gen_neon_unarrow_sats(int size, TCGv_i32 dest, TCGv_i64 src)
-{
- switch (size) {
- case 0: gen_helper_neon_unarrow_sat8(dest, cpu_env, src); break;
- case 1: gen_helper_neon_unarrow_sat16(dest, cpu_env, src); break;
- case 2: gen_helper_neon_unarrow_sat32(dest, cpu_env, src); break;
- default: abort();
- }
-}
-
-static inline void gen_neon_widen(TCGv_i64 dest, TCGv_i32 src, int size, int u)
-{
- if (u) {
- switch (size) {
- case 0: gen_helper_neon_widen_u8(dest, src); break;
- case 1: gen_helper_neon_widen_u16(dest, src); break;
- case 2: tcg_gen_extu_i32_i64(dest, src); break;
- default: abort();
- }
- } else {
- switch (size) {
- case 0: gen_helper_neon_widen_s8(dest, src); break;
- case 1: gen_helper_neon_widen_s16(dest, src); break;
- case 2: tcg_gen_ext_i32_i64(dest, src); break;
- default: abort();
- }
- }
- tcg_temp_free_i32(src);
-}
-
-static inline void gen_neon_addl(int size)
-{
- switch (size) {
- case 0: gen_helper_neon_addl_u16(CPU_V001); break;
- case 1: gen_helper_neon_addl_u32(CPU_V001); break;
- case 2: tcg_gen_add_i64(CPU_V001); break;
- default: abort();
- }
-}
-
-static void gen_neon_narrow_op(int op, int u, int size,
- TCGv_i32 dest, TCGv_i64 src)
-{
- if (op) {
- if (u) {
- gen_neon_unarrow_sats(size, dest, src);
- } else {
- gen_neon_narrow(size, dest, src);
- }
- } else {
- if (u) {
- gen_neon_narrow_satu(size, dest, src);
- } else {
- gen_neon_narrow_sats(size, dest, src);
- }
- }
-}
-
-/* Symbolic constants for op fields for Neon 2-register miscellaneous.
- * The values correspond to bits [17:16,10:7]; see the ARM ARM DDI0406B
- * table A7-13.
- */
-#define NEON_2RM_VREV64 0
-#define NEON_2RM_VREV32 1
-#define NEON_2RM_VREV16 2
-#define NEON_2RM_VPADDL 4
-#define NEON_2RM_VPADDL_U 5
-#define NEON_2RM_AESE 6 /* Includes AESD */
-#define NEON_2RM_AESMC 7 /* Includes AESIMC */
-#define NEON_2RM_VCLS 8
-#define NEON_2RM_VCLZ 9
-#define NEON_2RM_VCNT 10
-#define NEON_2RM_VMVN 11
-#define NEON_2RM_VPADAL 12
-#define NEON_2RM_VPADAL_U 13
-#define NEON_2RM_VQABS 14
-#define NEON_2RM_VQNEG 15
-#define NEON_2RM_VCGT0 16
-#define NEON_2RM_VCGE0 17
-#define NEON_2RM_VCEQ0 18
-#define NEON_2RM_VCLE0 19
-#define NEON_2RM_VCLT0 20
-#define NEON_2RM_SHA1H 21
-#define NEON_2RM_VABS 22
-#define NEON_2RM_VNEG 23
-#define NEON_2RM_VCGT0_F 24
-#define NEON_2RM_VCGE0_F 25
-#define NEON_2RM_VCEQ0_F 26
-#define NEON_2RM_VCLE0_F 27
-#define NEON_2RM_VCLT0_F 28
-#define NEON_2RM_VABS_F 30
-#define NEON_2RM_VNEG_F 31
-#define NEON_2RM_VSWP 32
-#define NEON_2RM_VTRN 33
-#define NEON_2RM_VUZP 34
-#define NEON_2RM_VZIP 35
-#define NEON_2RM_VMOVN 36 /* Includes VQMOVN, VQMOVUN */
-#define NEON_2RM_VQMOVN 37 /* Includes VQMOVUN */
-#define NEON_2RM_VSHLL 38
-#define NEON_2RM_SHA1SU1 39 /* Includes SHA256SU0 */
-#define NEON_2RM_VRINTN 40
-#define NEON_2RM_VRINTX 41
-#define NEON_2RM_VRINTA 42
-#define NEON_2RM_VRINTZ 43
-#define NEON_2RM_VCVT_F16_F32 44
-#define NEON_2RM_VRINTM 45
-#define NEON_2RM_VCVT_F32_F16 46
-#define NEON_2RM_VRINTP 47
-#define NEON_2RM_VCVTAU 48
-#define NEON_2RM_VCVTAS 49
-#define NEON_2RM_VCVTNU 50
-#define NEON_2RM_VCVTNS 51
-#define NEON_2RM_VCVTPU 52
-#define NEON_2RM_VCVTPS 53
-#define NEON_2RM_VCVTMU 54
-#define NEON_2RM_VCVTMS 55
-#define NEON_2RM_VRECPE 56
-#define NEON_2RM_VRSQRTE 57
-#define NEON_2RM_VRECPE_F 58
-#define NEON_2RM_VRSQRTE_F 59
-#define NEON_2RM_VCVT_FS 60
-#define NEON_2RM_VCVT_FU 61
-#define NEON_2RM_VCVT_SF 62
-#define NEON_2RM_VCVT_UF 63
-
-static bool neon_2rm_is_v8_op(int op)
-{
- /* Return true if this neon 2reg-misc op is ARMv8 and up */
- switch (op) {
- case NEON_2RM_VRINTN:
- case NEON_2RM_VRINTA:
- case NEON_2RM_VRINTM:
- case NEON_2RM_VRINTP:
- case NEON_2RM_VRINTZ:
- case NEON_2RM_VRINTX:
- case NEON_2RM_VCVTAU:
- case NEON_2RM_VCVTAS:
- case NEON_2RM_VCVTNU:
- case NEON_2RM_VCVTNS:
- case NEON_2RM_VCVTPU:
- case NEON_2RM_VCVTPS:
- case NEON_2RM_VCVTMU:
- case NEON_2RM_VCVTMS:
- return true;
- default:
- return false;
- }
-}
-
-/* Each entry in this array has bit n set if the insn allows
- * size value n (otherwise it will UNDEF). Since unallocated
- * op values will have no bits set they always UNDEF.
- */
-static const uint8_t neon_2rm_sizes[] = {
- [NEON_2RM_VREV64] = 0x7,
- [NEON_2RM_VREV32] = 0x3,
- [NEON_2RM_VREV16] = 0x1,
- [NEON_2RM_VPADDL] = 0x7,
- [NEON_2RM_VPADDL_U] = 0x7,
- [NEON_2RM_AESE] = 0x1,
- [NEON_2RM_AESMC] = 0x1,
- [NEON_2RM_VCLS] = 0x7,
- [NEON_2RM_VCLZ] = 0x7,
- [NEON_2RM_VCNT] = 0x1,
- [NEON_2RM_VMVN] = 0x1,
- [NEON_2RM_VPADAL] = 0x7,
- [NEON_2RM_VPADAL_U] = 0x7,
- [NEON_2RM_VQABS] = 0x7,
- [NEON_2RM_VQNEG] = 0x7,
- [NEON_2RM_VCGT0] = 0x7,
- [NEON_2RM_VCGE0] = 0x7,
- [NEON_2RM_VCEQ0] = 0x7,
- [NEON_2RM_VCLE0] = 0x7,
- [NEON_2RM_VCLT0] = 0x7,
- [NEON_2RM_SHA1H] = 0x4,
- [NEON_2RM_VABS] = 0x7,
- [NEON_2RM_VNEG] = 0x7,
- [NEON_2RM_VCGT0_F] = 0x4,
- [NEON_2RM_VCGE0_F] = 0x4,
- [NEON_2RM_VCEQ0_F] = 0x4,
- [NEON_2RM_VCLE0_F] = 0x4,
- [NEON_2RM_VCLT0_F] = 0x4,
- [NEON_2RM_VABS_F] = 0x4,
- [NEON_2RM_VNEG_F] = 0x4,
- [NEON_2RM_VSWP] = 0x1,
- [NEON_2RM_VTRN] = 0x7,
- [NEON_2RM_VUZP] = 0x7,
- [NEON_2RM_VZIP] = 0x7,
- [NEON_2RM_VMOVN] = 0x7,
- [NEON_2RM_VQMOVN] = 0x7,
- [NEON_2RM_VSHLL] = 0x7,
- [NEON_2RM_SHA1SU1] = 0x4,
- [NEON_2RM_VRINTN] = 0x4,
- [NEON_2RM_VRINTX] = 0x4,
- [NEON_2RM_VRINTA] = 0x4,
- [NEON_2RM_VRINTZ] = 0x4,
- [NEON_2RM_VCVT_F16_F32] = 0x2,
- [NEON_2RM_VRINTM] = 0x4,
- [NEON_2RM_VCVT_F32_F16] = 0x2,
- [NEON_2RM_VRINTP] = 0x4,
- [NEON_2RM_VCVTAU] = 0x4,
- [NEON_2RM_VCVTAS] = 0x4,
- [NEON_2RM_VCVTNU] = 0x4,
- [NEON_2RM_VCVTNS] = 0x4,
- [NEON_2RM_VCVTPU] = 0x4,
- [NEON_2RM_VCVTPS] = 0x4,
- [NEON_2RM_VCVTMU] = 0x4,
- [NEON_2RM_VCVTMS] = 0x4,
- [NEON_2RM_VRECPE] = 0x4,
- [NEON_2RM_VRSQRTE] = 0x4,
- [NEON_2RM_VRECPE_F] = 0x4,
- [NEON_2RM_VRSQRTE_F] = 0x4,
- [NEON_2RM_VCVT_FS] = 0x4,
- [NEON_2RM_VCVT_FU] = 0x4,
- [NEON_2RM_VCVT_SF] = 0x4,
- [NEON_2RM_VCVT_UF] = 0x4,
-};
-
static void gen_gvec_fn3_qc(uint32_t rd_ofs, uint32_t rn_ofs, uint32_t rm_ofs,
uint32_t opr_sz, uint32_t max_sz,
gen_helper_gvec_3_ptr *fn)
@@ -5016,573 +4544,6 @@ void gen_gvec_uaba(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs,
tcg_gen_gvec_3(rd_ofs, rn_ofs, rm_ofs, opr_sz, max_sz, &ops[vece]);
}
-/* Translate a NEON data processing instruction. Return nonzero if the
- instruction is invalid.
- We process data in a mixture of 32-bit and 64-bit chunks.
- Mostly we use 32-bit chunks so we can use normal scalar instructions. */
-
-static int disas_neon_data_insn(DisasContext *s, uint32_t insn)
-{
- int op;
- int q;
- int rd, rm, rd_ofs, rm_ofs;
- int size;
- int pass;
- int u;
- int vec_size;
- TCGv_i32 tmp, tmp2, tmp3;
-
- if (!arm_dc_feature(s, ARM_FEATURE_NEON)) {
- return 1;
- }
-
- /* FIXME: this access check should not take precedence over UNDEF
- * for invalid encodings; we will generate incorrect syndrome information
- * for attempts to execute invalid vfp/neon encodings with FP disabled.
- */
- if (s->fp_excp_el) {
- gen_exception_insn(s, s->pc_curr, EXCP_UDEF,
- syn_simd_access_trap(1, 0xe, false), s->fp_excp_el);
- return 0;
- }
-
- if (!s->vfp_enabled)
- return 1;
- q = (insn & (1 << 6)) != 0;
- u = (insn >> 24) & 1;
- VFP_DREG_D(rd, insn);
- VFP_DREG_M(rm, insn);
- size = (insn >> 20) & 3;
- vec_size = q ? 16 : 8;
- rd_ofs = neon_reg_offset(rd, 0);
- rm_ofs = neon_reg_offset(rm, 0);
-
- if ((insn & (1 << 23)) == 0) {
- /* Three register same length: handled by decodetree */
- return 1;
- } else if (insn & (1 << 4)) {
- /* Two registers and shift or reg and imm: handled by decodetree */
- return 1;
- } else { /* (insn & 0x00800010 == 0x00800000) */
- if (size != 3) {
- /*
- * Three registers of different lengths, or two registers and
- * a scalar: handled by decodetree
- */
- return 1;
- } else { /* size == 3 */
- if (!u) {
- /* Extract: handled by decodetree */
- return 1;
- } else if ((insn & (1 << 11)) == 0) {
- /* Two register misc. */
- op = ((insn >> 12) & 0x30) | ((insn >> 7) & 0xf);
- size = (insn >> 18) & 3;
- /* UNDEF for unknown op values and bad op-size combinations */
- if ((neon_2rm_sizes[op] & (1 << size)) == 0) {
- return 1;
- }
- if (neon_2rm_is_v8_op(op) &&
- !arm_dc_feature(s, ARM_FEATURE_V8)) {
- return 1;
- }
- if ((op != NEON_2RM_VMOVN && op != NEON_2RM_VQMOVN) &&
- q && ((rm | rd) & 1)) {
- return 1;
- }
- switch (op) {
- case NEON_2RM_VREV64:
- for (pass = 0; pass < (q ? 2 : 1); pass++) {
- tmp = neon_load_reg(rm, pass * 2);
- tmp2 = neon_load_reg(rm, pass * 2 + 1);
- switch (size) {
- case 0: tcg_gen_bswap32_i32(tmp, tmp); break;
- case 1: gen_swap_half(tmp); break;
- case 2: /* no-op */ break;
- default: abort();
- }
- neon_store_reg(rd, pass * 2 + 1, tmp);
- if (size == 2) {
- neon_store_reg(rd, pass * 2, tmp2);
- } else {
- switch (size) {
- case 0: tcg_gen_bswap32_i32(tmp2, tmp2); break;
- case 1: gen_swap_half(tmp2); break;
- default: abort();
- }
- neon_store_reg(rd, pass * 2, tmp2);
- }
- }
- break;
- case NEON_2RM_VPADDL: case NEON_2RM_VPADDL_U:
- case NEON_2RM_VPADAL: case NEON_2RM_VPADAL_U:
- for (pass = 0; pass < q + 1; pass++) {
- tmp = neon_load_reg(rm, pass * 2);
- gen_neon_widen(cpu_V0, tmp, size, op & 1);
- tmp = neon_load_reg(rm, pass * 2 + 1);
- gen_neon_widen(cpu_V1, tmp, size, op & 1);
- switch (size) {
- case 0: gen_helper_neon_paddl_u16(CPU_V001); break;
- case 1: gen_helper_neon_paddl_u32(CPU_V001); break;
- case 2: tcg_gen_add_i64(CPU_V001); break;
- default: abort();
- }
- if (op >= NEON_2RM_VPADAL) {
- /* Accumulate. */
- neon_load_reg64(cpu_V1, rd + pass);
- gen_neon_addl(size);
- }
- neon_store_reg64(cpu_V0, rd + pass);
- }
- break;
- case NEON_2RM_VTRN:
- if (size == 2) {
- int n;
- for (n = 0; n < (q ? 4 : 2); n += 2) {
- tmp = neon_load_reg(rm, n);
- tmp2 = neon_load_reg(rd, n + 1);
- neon_store_reg(rm, n, tmp2);
- neon_store_reg(rd, n + 1, tmp);
- }
- } else {
- goto elementwise;
- }
- break;
- case NEON_2RM_VUZP:
- if (gen_neon_unzip(rd, rm, size, q)) {
- return 1;
- }
- break;
- case NEON_2RM_VZIP:
- if (gen_neon_zip(rd, rm, size, q)) {
- return 1;
- }
- break;
- case NEON_2RM_VMOVN: case NEON_2RM_VQMOVN:
- /* also VQMOVUN; op field and mnemonics don't line up */
- if (rm & 1) {
- return 1;
- }
- tmp2 = NULL;
- for (pass = 0; pass < 2; pass++) {
- neon_load_reg64(cpu_V0, rm + pass);
- tmp = tcg_temp_new_i32();
- gen_neon_narrow_op(op == NEON_2RM_VMOVN, q, size,
- tmp, cpu_V0);
- if (pass == 0) {
- tmp2 = tmp;
- } else {
- neon_store_reg(rd, 0, tmp2);
- neon_store_reg(rd, 1, tmp);
- }
- }
- break;
- case NEON_2RM_VSHLL:
- 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, 1);
- tcg_gen_shli_i64(cpu_V0, cpu_V0, 8 << size);
- neon_store_reg64(cpu_V0, rd + pass);
- }
- break;
- case NEON_2RM_VCVT_F16_F32:
- {
- TCGv_ptr fpst;
- TCGv_i32 ahp;
-
- if (!dc_isar_feature(aa32_fp16_spconv, s) ||
- q || (rm & 1)) {
- return 1;
- }
- fpst = get_fpstatus_ptr(true);
- ahp = get_ahp_flag();
- tmp = neon_load_reg(rm, 0);
- gen_helper_vfp_fcvt_f32_to_f16(tmp, tmp, fpst, ahp);
- tmp2 = neon_load_reg(rm, 1);
- gen_helper_vfp_fcvt_f32_to_f16(tmp2, tmp2, fpst, ahp);
- tcg_gen_shli_i32(tmp2, tmp2, 16);
- tcg_gen_or_i32(tmp2, tmp2, tmp);
- tcg_temp_free_i32(tmp);
- tmp = neon_load_reg(rm, 2);
- gen_helper_vfp_fcvt_f32_to_f16(tmp, tmp, fpst, ahp);
- tmp3 = neon_load_reg(rm, 3);
- neon_store_reg(rd, 0, tmp2);
- gen_helper_vfp_fcvt_f32_to_f16(tmp3, tmp3, fpst, ahp);
- tcg_gen_shli_i32(tmp3, tmp3, 16);
- tcg_gen_or_i32(tmp3, tmp3, tmp);
- neon_store_reg(rd, 1, tmp3);
- tcg_temp_free_i32(tmp);
- tcg_temp_free_i32(ahp);
- tcg_temp_free_ptr(fpst);
- break;
- }
- case NEON_2RM_VCVT_F32_F16:
- {
- TCGv_ptr fpst;
- TCGv_i32 ahp;
- if (!dc_isar_feature(aa32_fp16_spconv, s) ||
- q || (rd & 1)) {
- return 1;
- }
- fpst = get_fpstatus_ptr(true);
- ahp = get_ahp_flag();
- tmp3 = tcg_temp_new_i32();
- tmp = neon_load_reg(rm, 0);
- tmp2 = neon_load_reg(rm, 1);
- tcg_gen_ext16u_i32(tmp3, tmp);
- gen_helper_vfp_fcvt_f16_to_f32(tmp3, tmp3, fpst, ahp);
- neon_store_reg(rd, 0, tmp3);
- tcg_gen_shri_i32(tmp, tmp, 16);
- gen_helper_vfp_fcvt_f16_to_f32(tmp, tmp, fpst, ahp);
- neon_store_reg(rd, 1, tmp);
- tmp3 = tcg_temp_new_i32();
- tcg_gen_ext16u_i32(tmp3, tmp2);
- gen_helper_vfp_fcvt_f16_to_f32(tmp3, tmp3, fpst, ahp);
- neon_store_reg(rd, 2, tmp3);
- tcg_gen_shri_i32(tmp2, tmp2, 16);
- gen_helper_vfp_fcvt_f16_to_f32(tmp2, tmp2, fpst, ahp);
- neon_store_reg(rd, 3, tmp2);
- tcg_temp_free_i32(ahp);
- tcg_temp_free_ptr(fpst);
- break;
- }
- case NEON_2RM_AESE: case NEON_2RM_AESMC:
- if (!dc_isar_feature(aa32_aes, s) || ((rm | rd) & 1)) {
- return 1;
- }
- /*
- * Bit 6 is the lowest opcode bit; it distinguishes
- * between encryption (AESE/AESMC) and decryption
- * (AESD/AESIMC).
- */
- if (op == NEON_2RM_AESE) {
- 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 {
- 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);
- }
- break;
- case NEON_2RM_SHA1H:
- if (!dc_isar_feature(aa32_sha1, s) || ((rm | rd) & 1)) {
- return 1;
- }
- 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) {
- return 1;
- }
- /* bit 6 (q): set -> SHA256SU0, cleared -> SHA1SU1 */
- if (q) {
- if (!dc_isar_feature(aa32_sha2, s)) {
- return 1;
- }
- } else if (!dc_isar_feature(aa32_sha1, s)) {
- return 1;
- }
- 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;
- case NEON_2RM_VNEG:
- tcg_gen_gvec_neg(size, rd_ofs, rm_ofs, vec_size, vec_size);
- break;
- case NEON_2RM_VABS:
- tcg_gen_gvec_abs(size, rd_ofs, rm_ofs, vec_size, vec_size);
- break;
-
- case NEON_2RM_VCEQ0:
- gen_gvec_ceq0(size, rd_ofs, rm_ofs, vec_size, vec_size);
- break;
- case NEON_2RM_VCGT0:
- gen_gvec_cgt0(size, rd_ofs, rm_ofs, vec_size, vec_size);
- break;
- case NEON_2RM_VCLE0:
- gen_gvec_cle0(size, rd_ofs, rm_ofs, vec_size, vec_size);
- break;
- case NEON_2RM_VCGE0:
- gen_gvec_cge0(size, rd_ofs, rm_ofs, vec_size, vec_size);
- break;
- case NEON_2RM_VCLT0:
- gen_gvec_clt0(size, rd_ofs, rm_ofs, vec_size, vec_size);
- break;
-
- default:
- elementwise:
- for (pass = 0; pass < (q ? 4 : 2); pass++) {
- tmp = neon_load_reg(rm, pass);
- switch (op) {
- case NEON_2RM_VREV32:
- switch (size) {
- case 0: tcg_gen_bswap32_i32(tmp, tmp); break;
- case 1: gen_swap_half(tmp); break;
- default: abort();
- }
- break;
- case NEON_2RM_VREV16:
- gen_rev16(tmp, tmp);
- break;
- case NEON_2RM_VCLS:
- switch (size) {
- case 0: gen_helper_neon_cls_s8(tmp, tmp); break;
- case 1: gen_helper_neon_cls_s16(tmp, tmp); break;
- case 2: gen_helper_neon_cls_s32(tmp, tmp); break;
- default: abort();
- }
- break;
- case NEON_2RM_VCLZ:
- switch (size) {
- case 0: gen_helper_neon_clz_u8(tmp, tmp); break;
- case 1: gen_helper_neon_clz_u16(tmp, tmp); break;
- case 2: tcg_gen_clzi_i32(tmp, tmp, 32); break;
- default: abort();
- }
- break;
- case NEON_2RM_VCNT:
- gen_helper_neon_cnt_u8(tmp, tmp);
- break;
- case NEON_2RM_VQABS:
- switch (size) {
- case 0:
- gen_helper_neon_qabs_s8(tmp, cpu_env, tmp);
- break;
- case 1:
- gen_helper_neon_qabs_s16(tmp, cpu_env, tmp);
- break;
- case 2:
- gen_helper_neon_qabs_s32(tmp, cpu_env, tmp);
- break;
- default: abort();
- }
- break;
- case NEON_2RM_VQNEG:
- switch (size) {
- case 0:
- gen_helper_neon_qneg_s8(tmp, cpu_env, tmp);
- break;
- case 1:
- gen_helper_neon_qneg_s16(tmp, cpu_env, tmp);
- break;
- case 2:
- gen_helper_neon_qneg_s32(tmp, cpu_env, tmp);
- break;
- default: abort();
- }
- break;
- case NEON_2RM_VCGT0_F:
- {
- TCGv_ptr fpstatus = get_fpstatus_ptr(1);
- tmp2 = tcg_const_i32(0);
- gen_helper_neon_cgt_f32(tmp, tmp, tmp2, fpstatus);
- tcg_temp_free_i32(tmp2);
- tcg_temp_free_ptr(fpstatus);
- break;
- }
- case NEON_2RM_VCGE0_F:
- {
- TCGv_ptr fpstatus = get_fpstatus_ptr(1);
- tmp2 = tcg_const_i32(0);
- gen_helper_neon_cge_f32(tmp, tmp, tmp2, fpstatus);
- tcg_temp_free_i32(tmp2);
- tcg_temp_free_ptr(fpstatus);
- break;
- }
- case NEON_2RM_VCEQ0_F:
- {
- TCGv_ptr fpstatus = get_fpstatus_ptr(1);
- tmp2 = tcg_const_i32(0);
- gen_helper_neon_ceq_f32(tmp, tmp, tmp2, fpstatus);
- tcg_temp_free_i32(tmp2);
- tcg_temp_free_ptr(fpstatus);
- break;
- }
- case NEON_2RM_VCLE0_F:
- {
- TCGv_ptr fpstatus = get_fpstatus_ptr(1);
- tmp2 = tcg_const_i32(0);
- gen_helper_neon_cge_f32(tmp, tmp2, tmp, fpstatus);
- tcg_temp_free_i32(tmp2);
- tcg_temp_free_ptr(fpstatus);
- break;
- }
- case NEON_2RM_VCLT0_F:
- {
- TCGv_ptr fpstatus = get_fpstatus_ptr(1);
- tmp2 = tcg_const_i32(0);
- gen_helper_neon_cgt_f32(tmp, tmp2, tmp, fpstatus);
- tcg_temp_free_i32(tmp2);
- tcg_temp_free_ptr(fpstatus);
- break;
- }
- case NEON_2RM_VABS_F:
- gen_helper_vfp_abss(tmp, tmp);
- break;
- case NEON_2RM_VNEG_F:
- gen_helper_vfp_negs(tmp, tmp);
- break;
- case NEON_2RM_VSWP:
- tmp2 = neon_load_reg(rd, pass);
- neon_store_reg(rm, pass, tmp2);
- break;
- case NEON_2RM_VTRN:
- tmp2 = neon_load_reg(rd, pass);
- switch (size) {
- case 0: gen_neon_trn_u8(tmp, tmp2); break;
- case 1: gen_neon_trn_u16(tmp, tmp2); break;
- default: abort();
- }
- neon_store_reg(rm, pass, tmp2);
- break;
- case NEON_2RM_VRINTN:
- case NEON_2RM_VRINTA:
- case NEON_2RM_VRINTM:
- case NEON_2RM_VRINTP:
- case NEON_2RM_VRINTZ:
- {
- TCGv_i32 tcg_rmode;
- TCGv_ptr fpstatus = get_fpstatus_ptr(1);
- int rmode;
-
- if (op == NEON_2RM_VRINTZ) {
- rmode = FPROUNDING_ZERO;
- } else {
- rmode = fp_decode_rm[((op & 0x6) >> 1) ^ 1];
- }
-
- tcg_rmode = tcg_const_i32(arm_rmode_to_sf(rmode));
- gen_helper_set_neon_rmode(tcg_rmode, tcg_rmode,
- cpu_env);
- gen_helper_rints(tmp, tmp, fpstatus);
- gen_helper_set_neon_rmode(tcg_rmode, tcg_rmode,
- cpu_env);
- tcg_temp_free_ptr(fpstatus);
- tcg_temp_free_i32(tcg_rmode);
- break;
- }
- case NEON_2RM_VRINTX:
- {
- TCGv_ptr fpstatus = get_fpstatus_ptr(1);
- gen_helper_rints_exact(tmp, tmp, fpstatus);
- tcg_temp_free_ptr(fpstatus);
- break;
- }
- case NEON_2RM_VCVTAU:
- case NEON_2RM_VCVTAS:
- case NEON_2RM_VCVTNU:
- case NEON_2RM_VCVTNS:
- case NEON_2RM_VCVTPU:
- case NEON_2RM_VCVTPS:
- case NEON_2RM_VCVTMU:
- case NEON_2RM_VCVTMS:
- {
- bool is_signed = !extract32(insn, 7, 1);
- TCGv_ptr fpst = get_fpstatus_ptr(1);
- TCGv_i32 tcg_rmode, tcg_shift;
- int rmode = fp_decode_rm[extract32(insn, 8, 2)];
-
- tcg_shift = tcg_const_i32(0);
- tcg_rmode = tcg_const_i32(arm_rmode_to_sf(rmode));
- gen_helper_set_neon_rmode(tcg_rmode, tcg_rmode,
- cpu_env);
-
- if (is_signed) {
- gen_helper_vfp_tosls(tmp, tmp,
- tcg_shift, fpst);
- } else {
- gen_helper_vfp_touls(tmp, tmp,
- tcg_shift, fpst);
- }
-
- gen_helper_set_neon_rmode(tcg_rmode, tcg_rmode,
- cpu_env);
- tcg_temp_free_i32(tcg_rmode);
- tcg_temp_free_i32(tcg_shift);
- tcg_temp_free_ptr(fpst);
- break;
- }
- case NEON_2RM_VRECPE:
- gen_helper_recpe_u32(tmp, tmp);
- break;
- case NEON_2RM_VRSQRTE:
- gen_helper_rsqrte_u32(tmp, tmp);
- break;
- case NEON_2RM_VRECPE_F:
- {
- TCGv_ptr fpstatus = get_fpstatus_ptr(1);
- gen_helper_recpe_f32(tmp, tmp, fpstatus);
- tcg_temp_free_ptr(fpstatus);
- break;
- }
- case NEON_2RM_VRSQRTE_F:
- {
- TCGv_ptr fpstatus = get_fpstatus_ptr(1);
- gen_helper_rsqrte_f32(tmp, tmp, fpstatus);
- tcg_temp_free_ptr(fpstatus);
- break;
- }
- case NEON_2RM_VCVT_FS: /* VCVT.F32.S32 */
- {
- TCGv_ptr fpstatus = get_fpstatus_ptr(1);
- gen_helper_vfp_sitos(tmp, tmp, fpstatus);
- tcg_temp_free_ptr(fpstatus);
- break;
- }
- case NEON_2RM_VCVT_FU: /* VCVT.F32.U32 */
- {
- TCGv_ptr fpstatus = get_fpstatus_ptr(1);
- gen_helper_vfp_uitos(tmp, tmp, fpstatus);
- tcg_temp_free_ptr(fpstatus);
- break;
- }
- case NEON_2RM_VCVT_SF: /* VCVT.S32.F32 */
- {
- TCGv_ptr fpstatus = get_fpstatus_ptr(1);
- gen_helper_vfp_tosizs(tmp, tmp, fpstatus);
- tcg_temp_free_ptr(fpstatus);
- break;
- }
- case NEON_2RM_VCVT_UF: /* VCVT.U32.F32 */
- {
- TCGv_ptr fpstatus = get_fpstatus_ptr(1);
- gen_helper_vfp_touizs(tmp, tmp, fpstatus);
- tcg_temp_free_ptr(fpstatus);
- break;
- }
- default:
- /* Reserved op values were caught by the
- * neon_2rm_sizes[] check earlier.
- */
- abort();
- }
- neon_store_reg(rd, pass, tmp);
- }
- break;
- }
- } else {
- /* VTBL, VTBX, VDUP: handled by decodetree */
- return 1;
- }
- }
- }
- return 0;
-}
-
static int disas_coproc_insn(DisasContext *s, uint32_t insn)
{
int cpnum, is64, crn, crm, opc1, opc2, isread, rt, rt2;
@@ -8417,7 +7378,7 @@ static bool op_smlad(DisasContext *s, arg_rrrr *a, bool m_swap, bool sub)
t1 = load_reg(s, a->rn);
t2 = load_reg(s, a->rm);
if (m_swap) {
- gen_swap_half(t2);
+ gen_swap_half(t2, t2);
}
gen_smul_dual(t1, t2);
@@ -8475,7 +7436,7 @@ static bool op_smlald(DisasContext *s, arg_rrrr *a, bool m_swap, bool sub)
t1 = load_reg(s, a->rn);
t2 = load_reg(s, a->rm);
if (m_swap) {
- gen_swap_half(t2);
+ gen_swap_half(t2, t2);
}
gen_smul_dual(t1, t2);
@@ -8824,9 +7785,6 @@ static bool do_ldm(DisasContext *s, arg_ldst_block *a, int min_n)
gen_io_start();
}
gen_helper_cpsr_write_eret(cpu_env, tmp);
- if (tb_cflags(s->base.tb) & CF_USE_ICOUNT) {
- gen_io_end();
- }
tcg_temp_free_i32(tmp);
/* Must exit loop to check un-masked IRQs */
s->base.is_jmp = DISAS_EXIT;
@@ -9283,13 +8241,6 @@ static void disas_arm_insn(DisasContext *s, unsigned int insn)
}
/* fall back to legacy decoder */
- if (((insn >> 25) & 7) == 1) {
- /* NEON Data processing. */
- if (disas_neon_data_insn(s, insn)) {
- goto illegal_op;
- }
- return;
- }
if ((insn & 0x0e000f00) == 0x0c000100) {
if (arm_dc_feature(s, ARM_FEATURE_IWMMXT)) {
/* iWMMXt register transfer. */
@@ -9477,11 +8428,8 @@ static void disas_thumb2_insn(DisasContext *s, uint32_t insn)
break;
}
if (((insn >> 24) & 3) == 3) {
- /* Translate into the equivalent ARM encoding. */
- insn = (insn & 0xe2ffffff) | ((insn & (1 << 28)) >> 4) | (1 << 28);
- if (disas_neon_data_insn(s, insn)) {
- goto illegal_op;
- }
+ /* Neon DP, but failed disas_neon_dp() */
+ goto illegal_op;
} else if (((insn >> 8) & 0xe) == 10) {
/* VFP, but failed disas_vfp. */
goto illegal_op;
diff --git a/target/arm/translate.h b/target/arm/translate.h
index 62ed5c4780..19650a9e2d 100644
--- a/target/arm/translate.h
+++ b/target/arm/translate.h
@@ -363,6 +363,7 @@ typedef void GVecGen4Fn(unsigned, uint32_t, uint32_t, uint32_t,
uint32_t, uint32_t, uint32_t);
/* Function prototype for gen_ functions for calling Neon helpers */
+typedef void NeonGenOneOpFn(TCGv_i32, TCGv_i32);
typedef void NeonGenOneOpEnvFn(TCGv_i32, TCGv_ptr, TCGv_i32);
typedef void NeonGenTwoOpFn(TCGv_i32, TCGv_i32, TCGv_i32);
typedef void NeonGenTwoOpEnvFn(TCGv_i32, TCGv_ptr, TCGv_i32, TCGv_i32);
@@ -372,9 +373,10 @@ typedef void NeonGenNarrowFn(TCGv_i32, TCGv_i64);
typedef void NeonGenNarrowEnvFn(TCGv_i32, TCGv_ptr, TCGv_i64);
typedef void NeonGenWidenFn(TCGv_i64, TCGv_i32);
typedef void NeonGenTwoOpWidenFn(TCGv_i64, TCGv_i32, TCGv_i32);
-typedef void NeonGenTwoSingleOPFn(TCGv_i32, TCGv_i32, TCGv_i32, TCGv_ptr);
-typedef void NeonGenTwoDoubleOPFn(TCGv_i64, TCGv_i64, TCGv_i64, TCGv_ptr);
-typedef void NeonGenOneOpFn(TCGv_i64, TCGv_i64);
+typedef void NeonGenOneSingleOpFn(TCGv_i32, TCGv_i32, TCGv_ptr);
+typedef void NeonGenTwoSingleOpFn(TCGv_i32, TCGv_i32, TCGv_i32, TCGv_ptr);
+typedef void NeonGenTwoDoubleOpFn(TCGv_i64, TCGv_i64, TCGv_i64, TCGv_ptr);
+typedef void NeonGenOne64OpFn(TCGv_i64, TCGv_i64);
typedef void CryptoTwoOpFn(TCGv_ptr, TCGv_ptr);
typedef void CryptoThreeOpIntFn(TCGv_ptr, TCGv_ptr, TCGv_i32);
typedef void CryptoThreeOpFn(TCGv_ptr, TCGv_ptr, TCGv_ptr);
generated by cgit v1.2.3 (git 2.26.2) at 2025-01-13 00:03:02 +0000