From: Lawrence Hunter <lawrence.hunter@codethink.co.uk>
To: qemu-devel@nongnu.org
Cc: dickon.hood@codethink.co.uk, nazar.kazakov@codethink.co.uk,
kiran.ostrolenk@codethink.co.uk, frank.chang@sifive.com,
palmer@dabbelt.com, alistair.francis@wdc.com,
bin.meng@windriver.com, pbonzini@redhat.com,
philipp.tomsich@vrull.eu, kvm@vger.kernel.org,
Max Chou <max.chou@sifive.com>
Subject: [PATCH 38/39] target/riscv: Add Zvksed support
Date: Thu, 2 Feb 2023 12:42:29 +0000 [thread overview]
Message-ID: <20230202124230.295997-39-lawrence.hunter@codethink.co.uk> (raw)
In-Reply-To: <20230202124230.295997-1-lawrence.hunter@codethink.co.uk>
From: Max Chou <max.chou@sifive.com>
- add vsm4k, vsm4r instructions
Signed-off-by: Max Chou <max.chou@sifive.com>
Reviewed-by: Frank Chang <frank.chang@sifive.com>
[lawrence.hunter@codethink.co.uk: Moved SM4 functions from
crypto_helper.c to vcrypto_helper.c]
[nazar.kazakov@codethink.co.uk: Added alignment checks, refactored code to
use macros, and minor style changes]
---
target/riscv/crypto_helper.c | 1 +
target/riscv/helper.h | 4 +
target/riscv/insn32.decode | 5 +
target/riscv/insn_trans/trans_rvzvksed.c.inc | 35 +++++
target/riscv/translate.c | 1 +
target/riscv/vcrypto_helper.c | 139 +++++++++++++++++++
6 files changed, 185 insertions(+)
create mode 100644 target/riscv/insn_trans/trans_rvzvksed.c.inc
diff --git a/target/riscv/crypto_helper.c b/target/riscv/crypto_helper.c
index 2ef30281b1..760ce22570 100644
--- a/target/riscv/crypto_helper.c
+++ b/target/riscv/crypto_helper.c
@@ -23,6 +23,7 @@
#include "exec/helper-proto.h"
#include "crypto/aes.h"
#include "crypto/sm4.h"
+#include "vector_internals.h"
#define AES_XTIME(a) \
((a << 1) ^ ((a & 0x80) ? 0x1b : 0))
diff --git a/target/riscv/helper.h b/target/riscv/helper.h
index 6272294d50..07fad2568c 100644
--- a/target/riscv/helper.h
+++ b/target/riscv/helper.h
@@ -1201,3 +1201,7 @@ 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(vghmac_vv, void, ptr, 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 ff044f8288..3e83884f43 100644
--- a/target/riscv/insn32.decode
+++ b/target/riscv/insn32.decode
@@ -933,3 +933,8 @@ vsm3c_vi 101011 1 ..... ..... 010 ..... 1110111 @r_vm_1
# *** RV64 Zvkg vector crypto extension ***
vghmac_vv 101100 1 ..... ..... 010 ..... 1110111 @r_vm_1
+
+# *** RV64 Zvksed Standart 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..a30e0862e0
--- /dev/null
+++ b/target/riscv/insn_trans/trans_rvzvksed.c.inc
@@ -0,0 +1,35 @@
+#define ZVKSED_EGS 4
+
+static bool zvksed_check(DisasContext *s)
+{
+ return s->cfg_ptr->ext_zvksed == true && vext_check_isa_ill(s) &&
+ 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) &&
+ a->rs1 >= 0 && a->rs1 <= 7;
+}
+
+GEN_VI_UNMASKED_TRANS(vsm4k_vi, vsm4k_vi_check)
+
+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 0bc1c9db65..2ffb1827c5 100644
--- a/target/riscv/translate.c
+++ b/target/riscv/translate.c
@@ -1068,6 +1068,7 @@ 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 "insn_trans/trans_xventanacondops.c.inc"
diff --git a/target/riscv/vcrypto_helper.c b/target/riscv/vcrypto_helper.c
index a309ac3f03..fd9fc3c6d7 100644
--- a/target/riscv/vcrypto_helper.c
+++ b/target/riscv/vcrypto_helper.c
@@ -4,6 +4,7 @@
#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 +873,141 @@ void HELPER(vghmac_vv)(void *vd_vptr, void *vs1_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;
+ 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);
+
+ if (env->vl % egs != 0) {
+ riscv_raise_exception(env, RISCV_EXCP_ILLEGAL_INST, GETPC());
+ }
+
+ 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_SBOXWORD(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_SBOXWORD(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);
+
+ if (env->vl % egs != 0) {
+ riscv_raise_exception(env, RISCV_EXCP_ILLEGAL_INST, GETPC());
+ }
+
+ 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);
+
+ if (env->vl % egs != 0) {
+ riscv_raise_exception(env, RISCV_EXCP_ILLEGAL_INST, GETPC());
+ }
+
+ 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);
+}
--
2.39.1
next prev parent reply other threads:[~2023-02-02 14:54 UTC|newest]
Thread overview: 55+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-02-02 12:41 [PATCH 00/39] Add RISC-V vector cryptography extensions Lawrence Hunter
2023-02-02 12:41 ` [PATCH 01/39] target/riscv: add zvkb cpu property Lawrence Hunter
2023-02-02 12:41 ` [PATCH 02/39] target/riscv: Add vclmul.vv decoding, translation and execution support Lawrence Hunter
2023-02-02 13:53 ` Philipp Tomsich
2023-02-02 12:41 ` [PATCH 03/39] target/riscv: Add vclmul.vx " Lawrence Hunter
2023-02-02 13:59 ` Philipp Tomsich
2023-02-02 12:41 ` [PATCH 04/39] target/riscv: Add vclmulh.vv " Lawrence Hunter
2023-02-02 14:03 ` Philipp Tomsich
2023-02-02 16:54 ` Richard Henderson
2023-02-02 12:41 ` [PATCH 05/39] target/riscv: Add vclmulh.vx " Lawrence Hunter
2023-02-02 12:41 ` [PATCH 06/39] target/riscv: Add vrol.[vv, vx] and vror.[vv, vx, vi] " Lawrence Hunter
2023-02-02 14:13 ` Philipp Tomsich
2023-02-02 14:30 ` Philipp Tomsich
2023-02-02 17:35 ` Richard Henderson
2023-02-02 18:07 ` Philipp Tomsich
2023-02-02 23:14 ` Richard Henderson
2023-02-02 12:41 ` [PATCH 07/39] target/riscv: Add vbrev8.v " Lawrence Hunter
2023-02-02 14:21 ` Philipp Tomsich
2023-02-02 12:41 ` [PATCH 08/39] target/riscv: Add vrev8.v " Lawrence Hunter
2023-02-02 14:22 ` Philipp Tomsich
2023-02-02 12:42 ` [PATCH 09/39] target/riscv: Add vandn.[vv, vx, vi] " Lawrence Hunter
2023-02-02 14:29 ` [PATCH 09/39] target/riscv: Add vandn.[vv,vx,vi] " Philipp Tomsich
2023-02-02 12:42 ` [PATCH 10/39] target/riscv: expose zvkb cpu property Lawrence Hunter
2023-02-02 14:23 ` Philipp Tomsich
2023-02-02 14:24 ` Philipp Tomsich
2023-02-02 12:42 ` [PATCH 11/39] target/riscv: add zvkns " Lawrence Hunter
2023-02-02 12:42 ` [PATCH 12/39] target/riscv: Add vaesef.vv decoding, translation and execution support Lawrence Hunter
2023-02-02 12:42 ` [PATCH 13/39] target/riscv: Add vaesef.vs " Lawrence Hunter
2023-02-02 12:42 ` [PATCH 14/39] target/riscv: Add vaesdf.vv " Lawrence Hunter
2023-02-02 12:42 ` [PATCH 15/39] target/riscv: Add vaesdf.vs " Lawrence Hunter
2023-02-02 12:42 ` [PATCH 16/39] target/riscv: Add vaesdm.vv " Lawrence Hunter
2023-02-02 12:42 ` [PATCH 17/39] target/riscv: Add vaesdm.vs " Lawrence Hunter
2023-02-02 12:42 ` [PATCH 18/39] target/riscv: Add vaesz.vs " Lawrence Hunter
2023-02-02 12:42 ` [PATCH 19/39] target/riscv: Add vaesem.vv " Lawrence Hunter
2023-02-02 12:42 ` [PATCH 20/39] target/riscv: Add vaesem.vs " Lawrence Hunter
2023-02-02 12:42 ` [PATCH 21/39] target/riscv: Add vaeskf1.vi " Lawrence Hunter
2023-02-02 12:42 ` [PATCH 22/39] target/riscv: Add vaeskf2.vi " Lawrence Hunter
2023-02-02 12:42 ` [PATCH 23/39] target/riscv: expose zvkns cpu property Lawrence Hunter
2023-02-02 12:42 ` [PATCH 24/39] target/riscv: add zvknh cpu properties Lawrence Hunter
2023-02-02 12:42 ` [PATCH 25/39] target/riscv: Add vsha2ms.vv decoding, translation and execution support Lawrence Hunter
2023-02-02 12:42 ` [PATCH 26/39] target/riscv: Add vsha2c[hl].vv " Lawrence Hunter
2023-02-02 12:42 ` [PATCH 27/39] target/riscv: expose zvknh cpu properties Lawrence Hunter
2023-02-02 12:42 ` [PATCH 28/39] target/riscv: add zvksh cpu property Lawrence Hunter
2023-02-02 12:42 ` [PATCH 29/39] target/riscv: Add vsm3me.vv decoding, translation and execution support Lawrence Hunter
2023-02-02 12:42 ` [PATCH 30/39] target/riscv: Add vsm3c.vi " Lawrence Hunter
2023-02-02 12:42 ` [PATCH 31/39] target/riscv: expose zvksh cpu property Lawrence Hunter
2023-02-02 12:42 ` [PATCH 32/39] target/riscv: add zvkg " Lawrence Hunter
2023-02-02 12:42 ` [PATCH 33/39] target/riscv: Add vghmac.vv decoding, translation and execution support Lawrence Hunter
2023-02-02 12:42 ` [PATCH 34/39] target/riscv: expose zvkg cpu property Lawrence Hunter
2023-02-02 12:42 ` [PATCH 35/39] crypto: Move SM4_SBOXWORD from target/riscv Lawrence Hunter
2023-02-02 17:02 ` Richard Henderson
2023-02-02 12:42 ` [PATCH 36/39] crypto: Add SM4 constant parameter CK Lawrence Hunter
2023-02-02 12:42 ` [PATCH 37/39] target/riscv: Add zvksed cfg property Lawrence Hunter
2023-02-02 12:42 ` Lawrence Hunter [this message]
2023-02-02 12:42 ` [PATCH 39/39] target/riscv: Expose Zvksed property Lawrence Hunter
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20230202124230.295997-39-lawrence.hunter@codethink.co.uk \
--to=lawrence.hunter@codethink.co.uk \
--cc=alistair.francis@wdc.com \
--cc=bin.meng@windriver.com \
--cc=dickon.hood@codethink.co.uk \
--cc=frank.chang@sifive.com \
--cc=kiran.ostrolenk@codethink.co.uk \
--cc=kvm@vger.kernel.org \
--cc=max.chou@sifive.com \
--cc=nazar.kazakov@codethink.co.uk \
--cc=palmer@dabbelt.com \
--cc=pbonzini@redhat.com \
--cc=philipp.tomsich@vrull.eu \
--cc=qemu-devel@nongnu.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).