@@ -1180,3 +1180,5 @@ DEF_HELPER_6(vandn_vx_b, void, ptr, ptr, tl, ptr, env, i32)
DEF_HELPER_6(vandn_vx_h, void, ptr, ptr, tl, ptr, env, i32)
DEF_HELPER_6(vandn_vx_w, void, ptr, ptr, tl, ptr, env, i32)
DEF_HELPER_6(vandn_vx_d, void, ptr, ptr, tl, ptr, env, i32)
+
+DEF_HELPER_4(vaesef_vv, void, ptr, ptr, env, i32)
@@ -74,6 +74,7 @@
@r_rm ....... ..... ..... ... ..... ....... %rs2 %rs1 %rm %rd
@r2_rm ....... ..... ..... ... ..... ....... %rs1 %rm %rd
@r2 ....... ..... ..... ... ..... ....... &r2 %rs1 %rd
+@r2_vm_1 ...... . ..... ..... ... ..... ....... &rmr vm=1 %rs2 %rd
@r2_nfvm ... ... vm:1 ..... ..... ... ..... ....... &r2nfvm %nf %rs1 %rd
@r2_vm ...... vm:1 ..... ..... ... ..... ....... &rmr %rs2 %rd
@r1_vm ...... vm:1 ..... ..... ... ..... ....... %rd
@@ -907,3 +908,6 @@ vrev8_v 010010 . ..... 01001 010 ..... 1010111 @r2_vm
vandn_vi 000001 . ..... ..... 011 ..... 1010111 @r_vm
vandn_vv 000001 . ..... ..... 000 ..... 1010111 @r_vm
vandn_vx 000001 . ..... ..... 100 ..... 1010111 @r_vm
+
+# *** RV64 Zvkns vector crypto extension ***
+vaesef_vv 101000 1 ..... 00011 010 ..... 1110111 @r2_vm_1
new file mode 100644
@@ -0,0 +1,40 @@
+#define GEN_V_UNMASKED_TRANS(NAME, CHECK) \
+static bool trans_##NAME(DisasContext *s, arg_##NAME * a) \
+{ \
+ if (CHECK(s, a)) { \
+ TCGv_ptr rd_v, rs2_v; \
+ TCGv_i32 desc; \
+ uint32_t data = 0; \
+ \
+ TCGLabel *over = gen_new_label(); \
+ tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over); \
+ tcg_gen_brcond_tl(TCG_COND_GEU, cpu_vstart, cpu_vl, over); \
+ data = FIELD_DP32(data, VDATA, VM, a->vm); \
+ data = FIELD_DP32(data, VDATA, LMUL, s->lmul); \
+ data = FIELD_DP32(data, VDATA, VTA, s->vta); \
+ data = FIELD_DP32(data, VDATA, VTA_ALL_1S, s->cfg_vta_all_1s); \
+ data = FIELD_DP32(data, VDATA, VMA, s->vma); \
+ rd_v = tcg_temp_new_ptr(); \
+ rs2_v = tcg_temp_new_ptr(); \
+ desc = tcg_constant_i32(simd_desc(s->cfg_ptr->vlen / 8, \
+ s->cfg_ptr->vlen / 8, data)); \
+ tcg_gen_addi_ptr(rd_v, cpu_env, vreg_ofs(s, a->rd)); \
+ tcg_gen_addi_ptr(rs2_v, cpu_env, vreg_ofs(s, a->rs2)); \
+ gen_helper_##NAME(rd_v, rs2_v, cpu_env, desc); \
+ tcg_temp_free_ptr(rd_v); \
+ tcg_temp_free_ptr(rs2_v); \
+ mark_vs_dirty(s); \
+ gen_set_label(over); \
+ return true; \
+ } \
+ return false; \
+}
+
+
+static bool vaes_check_vv(DisasContext *s, arg_rmr *a)
+{
+ return s->cfg_ptr->ext_zvkns == true && vext_check_isa_ill(s) &&
+ require_align(a->rd, s->lmul) && require_align(a->rs2, s->lmul) &&
+ s->vstart % 4 == 0 && s->sew == MO_32;
+}
+GEN_V_UNMASKED_TRANS(vaesef_vv, vaes_check_vv)
@@ -1064,6 +1064,7 @@ static uint32_t opcode_at(DisasContextBase *dcbase, target_ulong pc)
#include "insn_trans/trans_rvzfh.c.inc"
#include "insn_trans/trans_rvk.c.inc"
#include "insn_trans/trans_rvzvkb.c.inc"
+#include "insn_trans/trans_rvzvkns.c.inc"
#include "insn_trans/trans_privileged.c.inc"
#include "insn_trans/trans_svinval.c.inc"
#include "insn_trans/trans_xventanacondops.c.inc"
@@ -3,6 +3,7 @@
#include "qemu/bitops.h"
#include "qemu/bswap.h"
#include "cpu.h"
+#include "crypto/aes.h"
#include "exec/memop.h"
#include "exec/exec-all.h"
#include "exec/helper-proto.h"
@@ -154,3 +155,77 @@ GEN_VEXT_VX(vandn_vx_b, 1)
GEN_VEXT_VX(vandn_vx_h, 2)
GEN_VEXT_VX(vandn_vx_w, 4)
GEN_VEXT_VX(vandn_vx_d, 8)
+
+static inline void aes_sub_bytes(uint8_t round_state[4][4])
+{
+ for (int j = 0; j < 16; j++) {
+ round_state[j / 4][j % 4] = AES_sbox[round_state[j / 4][j % 4]];
+ }
+}
+
+static inline void aes_shift_bytes(uint8_t round_state[4][4])
+{
+ uint8_t temp;
+ temp = round_state[0][1];
+ round_state[0][1] = round_state[1][1];
+ round_state[1][1] = round_state[2][1];
+ round_state[2][1] = round_state[3][1];
+ round_state[3][1] = temp;
+ temp = round_state[0][2];
+ round_state[0][2] = round_state[2][2];
+ round_state[2][2] = temp;
+ temp = round_state[1][2];
+ round_state[1][2] = round_state[3][2];
+ round_state[3][2] = temp;
+ temp = round_state[0][3];
+ round_state[0][3] = round_state[3][3];
+ round_state[3][3] = round_state[2][3];
+ round_state[2][3] = round_state[1][3];
+ round_state[1][3] = temp;
+}
+
+static inline void xor_round_key(uint8_t round_state[4][4], uint8_t *round_key)
+{
+ for (int j = 0; j < 16; j++) {
+ round_state[j / 4][j % 4] = round_state[j / 4][j % 4] ^ (round_key)[j];
+ }
+}
+
+#define GEN_ZVKNS_HELPER_VV(NAME, ...) \
+void HELPER(NAME)(void *vd_vptr, void *vs2_vptr, CPURISCVState *env, \
+ uint32_t desc) \
+{ \
+ uint64_t *vd = vd_vptr; \
+ uint64_t *vs2 = vs2_vptr; \
+ uint32_t vl = env->vl; \
+ uint32_t total_elems = vext_get_total_elems(env, desc, 4); \
+ uint32_t vta = vext_vta(desc); \
+ if (env->vl % 4 != 0) { \
+ riscv_raise_exception(env, RISCV_EXCP_ILLEGAL_INST, GETPC()); \
+ } \
+ for (uint32_t i = env->vstart / 4; i < env->vl / 4; i++) { \
+ uint64_t round_key[2] = { \
+ cpu_to_le64(vs2[i * 2 + 0]), \
+ cpu_to_le64(vs2[i * 2 + 1]), \
+ }; \
+ uint8_t round_state[4][4]; \
+ cpu_to_le64s(vd + i * 2 + 0); \
+ cpu_to_le64s(vd + i * 2 + 1); \
+ for (int j = 0; j < 16; j++) { \
+ round_state[j / 4][j % 4] = ((uint8_t *)(vd + i * 2))[j]; \
+ } \
+ __VA_ARGS__; \
+ for (int j = 0; j < 16; j++) { \
+ ((uint8_t *)(vd + i * 2))[j] = round_state[j / 4][j % 4]; \
+ } \
+ le64_to_cpus(vd + i * 2 + 0); \
+ le64_to_cpus(vd + i * 2 + 1); \
+ } \
+ env->vstart = 0; \
+ /* set tail elements to 1s */ \
+ vext_set_elems_1s(vd, vta, vl * 4, total_elems * 4); \
+}
+
+GEN_ZVKNS_HELPER_VV(vaesef_vv, aes_sub_bytes(round_state);
+ aes_shift_bytes(round_state);
+ xor_round_key(round_state, (uint8_t *)round_key);)