target/riscv: Add Zvkg ISA extension support

This commit adds support for the Zvkg vector-crypto extension, which
consists of the following instructions:

* vgmul.vv
* vghsh.vv

Translation functions are defined in
`target/riscv/insn_trans/trans_rvvk.c.inc` and helpers are defined in
`target/riscv/vcrypto_helper.c`.

Co-authored-by: Lawrence Hunter <lawrence.hunter@codethink.co.uk>
[max.chou@sifive.com: Replaced vstart checking by TCG op]
Signed-off-by: Lawrence Hunter <lawrence.hunter@codethink.co.uk>
Signed-off-by: Nazar Kazakov <nazar.kazakov@codethink.co.uk>
Signed-off-by: Max Chou <max.chou@sifive.com>
Reviewed-by: Daniel Henrique Barboza <dbarboza@ventanamicro.com>
[max.chou@sifive.com: Exposed x-zvkg property]
[max.chou@sifive.com: Replaced uint by int for cross win32 build]
Message-ID: <20230711165917.2629866-13-max.chou@sifive.com>
Signed-off-by: Alistair Francis <alistair.francis@wdc.com>

target/riscv/cpu.c

@@ -129,6 +129,7 @@ static const struct isa_ext_data isa_edata_arr[] = {
     ISA_EXT_DATA_ENTRY(zvfbfwma, PRIV_VERSION_1_12_0, ext_zvfbfwma),
     ISA_EXT_DATA_ENTRY(zvfh, PRIV_VERSION_1_12_0, ext_zvfh),
     ISA_EXT_DATA_ENTRY(zvfhmin, PRIV_VERSION_1_12_0, ext_zvfhmin),
+    ISA_EXT_DATA_ENTRY(zvkg, PRIV_VERSION_1_12_0, ext_zvkg),
     ISA_EXT_DATA_ENTRY(zvkned, PRIV_VERSION_1_12_0, ext_zvkned),
     ISA_EXT_DATA_ENTRY(zvknha, PRIV_VERSION_1_12_0, ext_zvknha),
     ISA_EXT_DATA_ENTRY(zvknhb, PRIV_VERSION_1_12_0, ext_zvknhb),
@@ -1281,8 +1282,8 @@ void riscv_cpu_validate_set_extensions(RISCVCPU *cpu, Error **errp)
      * In principle Zve*x would also suffice here, were they supported
      * in qemu
      */
-    if ((cpu->cfg.ext_zvbb || cpu->cfg.ext_zvkned || cpu->cfg.ext_zvknha ||
+    if ((cpu->cfg.ext_zvbb || cpu->cfg.ext_zvkg || cpu->cfg.ext_zvkned ||
-         cpu->cfg.ext_zvksh) && !cpu->cfg.ext_zve32f) {
+         cpu->cfg.ext_zvknha || cpu->cfg.ext_zvksh) && !cpu->cfg.ext_zve32f) {
         error_setg(errp,
                    "Vector crypto extensions require V or Zve* extensions");
         return;
@@ -1880,6 +1881,7 @@ static Property riscv_cpu_extensions[] = {
     /* Vector cryptography extensions */
     DEFINE_PROP_BOOL("x-zvbb", RISCVCPU, cfg.ext_zvbb, false),
     DEFINE_PROP_BOOL("x-zvbc", RISCVCPU, cfg.ext_zvbc, false),
+    DEFINE_PROP_BOOL("x-zvkg", RISCVCPU, cfg.ext_zvkg, false),
     DEFINE_PROP_BOOL("x-zvkned", RISCVCPU, cfg.ext_zvkned, false),
     DEFINE_PROP_BOOL("x-zvknha", RISCVCPU, cfg.ext_zvknha, false),
     DEFINE_PROP_BOOL("x-zvknhb", RISCVCPU, cfg.ext_zvknhb, false),

target/riscv/cpu_cfg.h

@@ -87,6 +87,7 @@ struct RISCVCPUConfig {
     bool ext_zve64d;
     bool ext_zvbb;
     bool ext_zvbc;
+    bool ext_zvkg;
     bool ext_zvkned;
     bool ext_zvknha;
     bool ext_zvknhb;

target/riscv/helper.h

@@ -1273,3 +1273,6 @@ DEF_HELPER_5(vsha2cl64_vv, void, ptr, ptr, ptr, env, i32)
 
 DEF_HELPER_5(vsm3me_vv, void, ptr, ptr, ptr, env, i32)
 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)

target/riscv/insn32.decode

@@ -995,3 +995,7 @@ vsha2cl_vv  101111 1 ..... ..... 010 ..... 1110111 @r_vm_1
 # *** Zvksh vector crypto extension ***
 vsm3me_vv   100000 1 ..... ..... 010 ..... 1110111 @r_vm_1
 vsm3c_vi    101011 1 ..... ..... 010 ..... 1110111 @r_vm_1
+
+# *** Zvkg vector crypto extension ***
+vghsh_vv    101100 1 ..... ..... 010 ..... 1110111 @r_vm_1
+vgmul_vv    101000 1 ..... 10001 010 ..... 1110111 @r2_vm_1

target/riscv/insn_trans/trans_rvvk.c.inc

@@ -531,3 +531,33 @@ static inline bool vsm3c_check(DisasContext *s, arg_rmrr *a)
 
 GEN_VV_UNMASKED_TRANS(vsm3me_vv, vsm3me_check, ZVKSH_EGS)
 GEN_VI_UNMASKED_TRANS(vsm3c_vi, vsm3c_check, ZVKSH_EGS)
+
+/*
+ * Zvkg
+ */
+
+#define ZVKG_EGS 4
+
+static bool vgmul_check(DisasContext *s, arg_rmr *a)
+{
+    int egw_bytes = ZVKG_EGS << s->sew;
+    return s->cfg_ptr->ext_zvkg == true &&
+           vext_check_isa_ill(s) &&
+           require_rvv(s) &&
+           MAXSZ(s) >= egw_bytes &&
+           vext_check_ss(s, a->rd, a->rs2, a->vm) &&
+           s->sew == MO_32;
+}
+
+GEN_V_UNMASKED_TRANS(vgmul_vv, vgmul_check, ZVKG_EGS)
+
+static bool vghsh_check(DisasContext *s, arg_rmrr *a)
+{
+    int egw_bytes = ZVKG_EGS << s->sew;
+    return s->cfg_ptr->ext_zvkg == true &&
+           opivv_check(s, a) &&
+           MAXSZ(s) >= egw_bytes &&
+           s->sew == MO_32;
+}
+
+GEN_VV_UNMASKED_TRANS(vghsh_vv, vghsh_check, ZVKG_EGS)

target/riscv/vcrypto_helper.c

@@ -769,3 +769,75 @@ void HELPER(vsm3c_vi)(void *vd_vptr, void *vs2_vptr, uint32_t uimm,
     vext_set_elems_1s(vd_vptr, vta, env->vl * esz, total_elems * esz);
     env->vstart = 0;
 }
+
+void HELPER(vghsh_vv)(void *vd_vptr, void *vs1_vptr, void *vs2_vptr,
+                      CPURISCVState *env, uint32_t desc)
+{
+    uint64_t *vd = vd_vptr;
+    uint64_t *vs1 = vs1_vptr;
+    uint64_t *vs2 = vs2_vptr;
+    uint32_t vta = vext_vta(desc);
+    uint32_t total_elems = vext_get_total_elems(env, desc, 4);
+
+    for (uint32_t i = env->vstart / 4; i < env->vl / 4; i++) {
+        uint64_t Y[2] = {vd[i * 2 + 0], vd[i * 2 + 1]};
+        uint64_t H[2] = {brev8(vs2[i * 2 + 0]), brev8(vs2[i * 2 + 1])};
+        uint64_t X[2] = {vs1[i * 2 + 0], vs1[i * 2 + 1]};
+        uint64_t Z[2] = {0, 0};
+
+        uint64_t S[2] = {brev8(Y[0] ^ X[0]), brev8(Y[1] ^ X[1])};
+
+        for (int j = 0; j < 128; j++) {
+            if ((S[j / 64] >> (j % 64)) & 1) {
+                Z[0] ^= H[0];
+                Z[1] ^= H[1];
+            }
+            bool reduce = ((H[1] >> 63) & 1);
+            H[1] = H[1] << 1 | H[0] >> 63;
+            H[0] = H[0] << 1;
+            if (reduce) {
+                H[0] ^= 0x87;
+            }
+        }
+
+        vd[i * 2 + 0] = brev8(Z[0]);
+        vd[i * 2 + 1] = brev8(Z[1]);
+    }
+    /* set tail elements to 1s */
+    vext_set_elems_1s(vd, vta, env->vl * 4, total_elems * 4);
+    env->vstart = 0;
+}
+
+void HELPER(vgmul_vv)(void *vd_vptr, void *vs2_vptr, CPURISCVState *env,
+                      uint32_t desc)
+{
+    uint64_t *vd = vd_vptr;
+    uint64_t *vs2 = vs2_vptr;
+    uint32_t vta = vext_vta(desc);
+    uint32_t total_elems = vext_get_total_elems(env, desc, 4);
+
+    for (uint32_t i = env->vstart / 4; i < env->vl / 4; i++) {
+        uint64_t Y[2] = {brev8(vd[i * 2 + 0]), brev8(vd[i * 2 + 1])};
+        uint64_t H[2] = {brev8(vs2[i * 2 + 0]), brev8(vs2[i * 2 + 1])};
+        uint64_t Z[2] = {0, 0};
+
+        for (int j = 0; j < 128; j++) {
+            if ((Y[j / 64] >> (j % 64)) & 1) {
+                Z[0] ^= H[0];
+                Z[1] ^= H[1];
+            }
+            bool reduce = ((H[1] >> 63) & 1);
+            H[1] = H[1] << 1 | H[0] >> 63;
+            H[0] = H[0] << 1;
+            if (reduce) {
+                H[0] ^= 0x87;
+            }
+        }
+
+        vd[i * 2 + 0] = brev8(Z[0]);
+        vd[i * 2 + 1] = brev8(Z[1]);
+    }
+    /* set tail elements to 1s */
+    vext_set_elems_1s(vd, vta, env->vl * 4, total_elems * 4);
+    env->vstart = 0;
+}