From: Max Chou <max.chou@xxxxxxxxxx>
- add vsm4k, vsm4r instructions
Signed-off-by: Max Chou <max.chou@xxxxxxxxxx>
Reviewed-by: Frank Chang <frank.chang@xxxxxxxxxx>
[lawrence.hunter@xxxxxxxxxxxxxxx: Moved SM4 functions from
crypto_helper.c to vcrypto_helper.c]
[nazar.kazakov@xxxxxxxxxxxxxxx: Added alignment checks, refactored code to
use macros, and minor style changes]
---
target/riscv/helper.h | 4 +
target/riscv/insn32.decode | 5 +
target/riscv/insn_trans/trans_rvzvksed.c.inc | 57 +++++++++
target/riscv/translate.c | 1 +
target/riscv/vcrypto_helper.c | 127 +++++++++++++++++++
5 files changed, 194 insertions(+)
create mode 100644 target/riscv/insn_trans/trans_rvzvksed.c.inc
diff --git a/target/riscv/helper.h b/target/riscv/helper.h
index 3c4aa4b5df..4e71738b38 100644
--- a/target/riscv/helper.h
+++ b/target/riscv/helper.h
@@ -1209,3 +1209,7 @@ DEF_HELPER_5(vsm3c_vi, void, ptr, ptr, i32, env, i32)
DEF_HELPER_5(vghsh_vv, void, ptr, ptr, ptr, env, i32)
DEF_HELPER_4(vgmul_vv, void, ptr, ptr, env, i32)
+
+DEF_HELPER_5(vsm4k_vi, void, ptr, ptr, i32, env, i32)
+DEF_HELPER_4(vsm4r_vv, void, ptr, ptr, env, i32)
+DEF_HELPER_4(vsm4r_vs, void, ptr, ptr, env, i32)
diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode
index 856e088bad..543e58ef18 100644
--- a/target/riscv/insn32.decode
+++ b/target/riscv/insn32.decode
@@ -952,3 +952,8 @@ vsm3c_vi 101011 1 ..... ..... 010 ..... 1110111 @r_vm_1
# *** RV64 Zvkg vector crypto extension ***
vghsh_vv 101100 1 ..... ..... 010 ..... 1110111 @r_vm_1
vgmul_vv 101000 1 ..... 10001 010 ..... 1110111 @r2_vm_1
+
+# *** RV64 Zvksed vector crypto extension ***
+vsm4k_vi 100001 1 ..... ..... 010 ..... 1110111 @r_vm_1
+vsm4r_vv 101000 1 ..... 10000 010 ..... 1110111 @r2_vm_1
+vsm4r_vs 101001 1 ..... 10000 010 ..... 1110111 @r2_vm_1
diff --git a/target/riscv/insn_trans/trans_rvzvksed.c.inc b/target/riscv/insn_trans/trans_rvzvksed.c.inc
new file mode 100644
index 0000000000..0025919fdb
--- /dev/null
+++ b/target/riscv/insn_trans/trans_rvzvksed.c.inc
@@ -0,0 +1,57 @@
+/*
+ * RISC-V translation routines for the Zvksed Extension.
+ *
+ * Copyright (C) 2023 SiFive, Inc.
+ * Written by Codethink Ltd and SiFive.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2 or later, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#define ZVKSED_EGS 4
+
+static bool zvksed_check(DisasContext *s)
+{
+ return s->cfg_ptr->ext_zvksed == true &&
+ require_rvv(s) &&
+ vext_check_isa_ill(s) &&
+ MAXSZ(s) >= (128 / 8) && /* EGW in bytes */
+ s->vstart % ZVKSED_EGS == 0 &&
+ s->sew == MO_32;
+}
+
+static bool vsm4k_vi_check(DisasContext *s, arg_rmrr *a)
+{
+ return zvksed_check(s) &&
+ require_align(a->rd, s->lmul) &&
+ require_align(a->rs2, s->lmul);
+}
+
+GEN_VI_UNMASKED_TRANS(vsm4k_vi, vsm4k_vi_check, ZVKSED_EGS)
+
+static bool vsm4r_vv_check(DisasContext *s, arg_rmr *a)
+{
+ return zvksed_check(s) &&
+ require_align(a->rd, s->lmul) &&
+ require_align(a->rs2, s->lmul);
+}
+
+GEN_V_UNMASKED_TRANS(vsm4r_vv, vsm4r_vv_check)
+
+static bool vsm4r_vs_check(DisasContext *s, arg_rmr *a)
+{
+ return zvksed_check(s) &&
+ !is_overlapped(a->rd, 1 << MAX(s->lmul, 0), a->rs2, 1) &&
+ require_align(a->rd, s->lmul);
+}
+
+GEN_V_UNMASKED_TRANS(vsm4r_vs, vsm4r_vs_check)
diff --git a/target/riscv/translate.c b/target/riscv/translate.c
index fdb5c3364e..521bc2e3a9 100644
--- a/target/riscv/translate.c
+++ b/target/riscv/translate.c
@@ -1088,6 +1088,7 @@ static uint32_t opcode_at(DisasContextBase *dcbase, target_ulong pc)
#include "insn_trans/trans_rvzvknh.c.inc"
#include "insn_trans/trans_rvzvksh.c.inc"
#include "insn_trans/trans_rvzvkg.c.inc"
+#include "insn_trans/trans_rvzvksed.c.inc"
#include "insn_trans/trans_privileged.c.inc"
#include "insn_trans/trans_svinval.c.inc"
#include "decode-xthead.c.inc"
diff --git a/target/riscv/vcrypto_helper.c b/target/riscv/vcrypto_helper.c
index fe9b05253d..63af768e2e 100644
--- a/target/riscv/vcrypto_helper.c
+++ b/target/riscv/vcrypto_helper.c
@@ -23,6 +23,7 @@
#include "qemu/bswap.h"
#include "cpu.h"
#include "crypto/aes.h"
+#include "crypto/sm4.h"
#include "exec/memop.h"
#include "exec/exec-all.h"
#include "exec/helper-proto.h"
@@ -872,3 +873,129 @@ void HELPER(vgmul_vv)(void *vd_vptr, void *vs2_vptr,
vext_set_elems_1s(vd, vta, env->vl * 4, total_elems * 4);
env->vstart = 0;
}
+
+void HELPER(vsm4k_vi)(void *vd, void *vs2, uint32_t uimm5,
+ CPURISCVState *env, uint32_t desc)
+{
+ const uint32_t egs = 4;
+ uint32_t rnd = uimm5 & 0x7;
+ uint32_t group_start = env->vstart / egs;
+ uint32_t group_end = env->vl / egs;
+ uint32_t esz = sizeof(uint32_t);
+ uint32_t total_elems = vext_get_total_elems(env, desc, esz);
+
+ for (uint32_t i = group_start; i < group_end; ++i) {
+ uint32_t vstart = i * egs;
+ uint32_t vend = (i + 1) * egs;
+ uint32_t rk[4] = {0};
+ uint32_t tmp[8] = {0};
+
+ for (uint32_t j = vstart; j < vend; ++j) {
+ rk[j - vstart] = *((uint32_t *)vs2 + H4(j));
+ }
+
+ for (uint32_t j = 0; j < egs; ++j) {
+ tmp[j] = rk[j];
+ }
+
+ for (uint32_t j = 0; j < egs; ++j) {
+ uint32_t b, s;
+ b = tmp[j + 1] ^ tmp[j + 2] ^ tmp[j + 3] ^ sm4_ck[rnd * 4 + j];
+
+ s = sm4_subword(b);
+
+ tmp[j + 4] = tmp[j] ^ (s ^ rol32(s, 13) ^ rol32(s, 23));
+ }
+
+ for (uint32_t j = vstart; j < vend; ++j) {
+ *((uint32_t *)vd + H4(j)) = tmp[egs + (j - vstart)];
+ }
+ }
+
+ env->vstart = 0;
+ /* set tail elements to 1s */
+ vext_set_elems_1s(vd, vext_vta(desc), env->vl * esz, total_elems * esz);
+}
+
+static void do_sm4_round(uint32_t *rk, uint32_t *buf)
+{
+ const uint32_t egs = 4;
+ uint32_t s, b;
+
+ for (uint32_t j = egs; j < egs * 2; ++j) {
+ b = buf[j - 3] ^ buf[j - 2] ^ buf[j - 1] ^ rk[j - 4];
+
+ s = sm4_subword(b);
+
+ buf[j] = buf[j - 4] ^ (s ^ rol32(s, 2) ^ rol32(s, 10) ^
+ rol32(s, 18) ^ rol32(s, 24));
+ }
+}
+
+void HELPER(vsm4r_vv)(void *vd, void *vs2, CPURISCVState *env, uint32_t desc)
+{
+ const uint32_t egs = 4;
+ uint32_t group_start = env->vstart / egs;
+ uint32_t group_end = env->vl / egs;
+ uint32_t esz = sizeof(uint32_t);
+ uint32_t total_elems = vext_get_total_elems(env, desc, esz);
+
+ for (uint32_t i = group_start; i < group_end; ++i) {
+ uint32_t vstart = i * egs;
+ uint32_t vend = (i + 1) * egs;
+ uint32_t rk[4] = {0};
+ uint32_t tmp[8] = {0};
+
+ for (uint32_t j = vstart; j < vend; ++j) {
+ rk[j - vstart] = *((uint32_t *)vs2 + H4(j));
+ }
+
+ for (uint32_t j = vstart; j < vend; ++j) {
+ tmp[j - vstart] = *((uint32_t *)vd + H4(j));
+ }
+
+ do_sm4_round(rk, tmp);
+
+ for (uint32_t j = vstart; j < vend; ++j) {
+ *((uint32_t *)vd + H4(j)) = tmp[egs + (j - vstart)];
+ }
+ }
+
+ env->vstart = 0;
+ /* set tail elements to 1s */
+ vext_set_elems_1s(vd, vext_vta(desc), env->vl * esz, total_elems * esz);
+}
+
+void HELPER(vsm4r_vs)(void *vd, void *vs2, CPURISCVState *env, uint32_t desc)
+{
+ const uint32_t egs = 4;
+ uint32_t group_start = env->vstart / egs;
+ uint32_t group_end = env->vl / egs;
+ uint32_t esz = sizeof(uint32_t);
+ uint32_t total_elems = vext_get_total_elems(env, desc, esz);
+
+ for (uint32_t i = group_start; i < group_end; ++i) {
+ uint32_t vstart = i * egs;
+ uint32_t vend = (i + 1) * egs;
+ uint32_t rk[4] = {0};
+ uint32_t tmp[8] = {0};
+
+ for (uint32_t j = 0; j < egs; ++j) {
+ rk[j] = *((uint32_t *)vs2 + H4(j));
+ }
+
+ for (uint32_t j = vstart; j < vend; ++j) {
+ tmp[j - vstart] = *((uint32_t *)vd + H4(j));
+ }
+
+ do_sm4_round(rk, tmp);
+
+ for (uint32_t j = vstart; j < vend; ++j) {
+ *((uint32_t *)vd + H4(j)) = tmp[egs + (j - vstart)];
+ }
+ }
+
+ env->vstart = 0;
+ /* set tail elements to 1s */
+ vext_set_elems_1s(vd, vext_vta(desc), env->vl * esz, total_elems * esz);
+}
--
2.39.2
