[PATCH 0/3] Cavium Octeon MIPS extensions

[PATCH 0/3] Cavium Octeon MIPS extensions

[Pavel Dovgalyuk]

The following series includes emulation of the platform-specific MIPS extension
for Cavium Octeon CPUS:
- basic Octeon vCPU model
- custom instruction decoder for Octeon
- implementation of arithmetic and logic instructions

---

Pavel Dovgalyuk (3):
      target/mips: introduce generic Cavium Octeon CPU model
      target/mips: implement Octeon-specific BBIT instructions
      target/mips: implement Octeon-specific arithmetic instructions


 target/mips/helper.h                |   1 +
 target/mips/tcg/meson.build         |   3 +
 target/mips/tcg/octeon.decode       |  39 +++++
 target/mips/tcg/octeon_helper.c     |  22 +++
 target/mips/tcg/octeon_helper.h.inc |  10 ++
 target/mips/tcg/octeon_translate.c  | 235 ++++++++++++++++++++++++++++
 target/mips/tcg/translate.c         |   5 +
 target/mips/tcg/translate.h         |   1 +
 8 files changed, 316 insertions(+)
 create mode 100644 target/mips/tcg/octeon.decode
 create mode 100644 target/mips/tcg/octeon_helper.c
 create mode 100644 target/mips/tcg/octeon_helper.h.inc
 create mode 100644 target/mips/tcg/octeon_translate.c

--
Pavel Dovgalyuk

[PATCH 1/3] target/mips: introduce generic Cavium Octeon CPU model

[Pavel Dovgalyuk]

This patch adds generic Octeon vCPU for providing
Octeon-specific instructions.

Signed-off-by: Pavel Dovgalyuk <Pavel.Dovgalyuk@ispras.ru>
---
 target/mips/cpu-defs.c.inc |   30 ++++++++++++++++++++++++++++++
 target/mips/mips-defs.h    |    1 +
 2 files changed, 31 insertions(+)

diff --git a/target/mips/cpu-defs.c.inc b/target/mips/cpu-defs.c.inc
index 582f940070..a60e48433c 100644
--- a/target/mips/cpu-defs.c.inc
+++ b/target/mips/cpu-defs.c.inc
@@ -921,6 +921,36 @@ const mips_def_t mips_defs[] =
         .insn_flags = CPU_MIPS64R2 | ASE_DSP | ASE_DSP_R2,
         .mmu_type = MMU_TYPE_R4000,
     },
+    {
+        /*
+         * A generic CPU providing MIPS64 Cavium Octeon features.
+         * PRid is taken from Octeon 68xx CPUs
+         * FIXME: Eventually this should be replaced by a real CPU model.
+         */
+        .name = "Octeon",
+        .CP0_PRid = 0x000D9100,
+        .CP0_Config0 = MIPS_CONFIG0 | (0x1 << CP0C0_AR) | (0x2 << CP0C0_AT) |
+                       (MMU_TYPE_R4000 << CP0C0_MT),
+        .CP0_Config1 = MIPS_CONFIG1 | (0x3F << CP0C1_MMU) |
+                       (1 << CP0C1_IS) | (4 << CP0C1_IL) | (1 << CP0C1_IA) |
+                       (1 << CP0C1_DS) | (4 << CP0C1_DL) | (1 << CP0C1_DA) |
+                       (1 << CP0C1_PC) | (1 << CP0C1_WR) | (1 << CP0C1_EP),
+        .CP0_Config2 = MIPS_CONFIG2,
+        .CP0_Config3 = MIPS_CONFIG3 | (1 << CP0C3_LPA) | (1 << CP0C3_DSPP) ,
+        .CP0_Config4 = MIPS_CONFIG4 | (1U << CP0C4_M) |
+                       (0x3c << CP0C4_KScrExist) | (1U << CP0C4_MMUExtDef) |
+                       (3U << CP0C4_MMUSizeExt),
+        .CP0_LLAddr_rw_bitmask = 0,
+        .CP0_LLAddr_shift = 4,
+        .CP0_PageGrain = (1 << CP0PG_ELPA),
+        .SYNCI_Step = 32,
+        .CCRes = 2,
+        .CP0_Status_rw_bitmask = 0x12F8FFFF,
+        .SEGBITS = 42,
+        .PABITS = 49,
+        .insn_flags = CPU_MIPS64R2 | INSN_OCTEON | ASE_DSP,
+        .mmu_type = MMU_TYPE_R4000,
+    },
 
 #endif
 };
diff --git a/target/mips/mips-defs.h b/target/mips/mips-defs.h
index 0a12d982a7..a6cebe0265 100644
--- a/target/mips/mips-defs.h
+++ b/target/mips/mips-defs.h
@@ -42,6 +42,7 @@
 #define INSN_LOONGSON2E   0x0000040000000000ULL
 #define INSN_LOONGSON2F   0x0000080000000000ULL
 #define INSN_LOONGSON3A   0x0000100000000000ULL
+#define INSN_OCTEON       0x0000200000000000ULL
 /*
  *   bits 52-63: vendor-specific ASEs
  */

Re: [PATCH 1/3] target/mips: introduce generic Cavium Octeon CPU model

[Richard Henderson]

On 6/7/22 01:59, Pavel Dovgalyuk wrote:
> +    {
> +        /*
> +         * A generic CPU providing MIPS64 Cavium Octeon features.
> +         * PRid is taken from Octeon 68xx CPUs
> +         * FIXME: Eventually this should be replaced by a real CPU model.
> +         */

You should just add the real cpu model.  No one will ever address this FIXME otherwise.


r~

[PATCH 2/3] target/mips: implement Octeon-specific BBIT instructions

[Pavel Dovgalyuk]

This patch introduces Octeon-specific decoder and implements
check-bit-and-jump instructions.

Signed-off-by: Pavel Dovgalyuk <Pavel.Dovgalyuk@ispras.ru>
---
 target/mips/tcg/meson.build        |    2 +
 target/mips/tcg/octeon.decode      |   14 ++++++++++
 target/mips/tcg/octeon_translate.c |   53 ++++++++++++++++++++++++++++++++++++
 target/mips/tcg/translate.c        |    5 +++
 target/mips/tcg/translate.h        |    1 +
 5 files changed, 75 insertions(+)
 create mode 100644 target/mips/tcg/octeon.decode
 create mode 100644 target/mips/tcg/octeon_translate.c

diff --git a/target/mips/tcg/meson.build b/target/mips/tcg/meson.build
index 98003779ae..7ee969ec8f 100644
--- a/target/mips/tcg/meson.build
+++ b/target/mips/tcg/meson.build
@@ -3,6 +3,7 @@ gen = [
   decodetree.process('msa.decode', extra_args: '--decode=decode_ase_msa'),
   decodetree.process('tx79.decode', extra_args: '--static-decode=decode_tx79'),
   decodetree.process('vr54xx.decode', extra_args: '--decode=decode_ext_vr54xx'),
+  decodetree.process('octeon.decode', extra_args: '--decode=decode_ext_octeon'),
 ]
 
 mips_ss.add(gen)
@@ -24,6 +25,7 @@ mips_ss.add(files(
 ))
 mips_ss.add(when: 'TARGET_MIPS64', if_true: files(
   'tx79_translate.c',
+  'octeon_translate.c',
 ), if_false: files(
   'mxu_translate.c',
 ))
diff --git a/target/mips/tcg/octeon.decode b/target/mips/tcg/octeon.decode
new file mode 100644
index 0000000000..c06d576292
--- /dev/null
+++ b/target/mips/tcg/octeon.decode
@@ -0,0 +1,14 @@
+# Octeon Architecture Module instruction set
+#
+# Copyright (C) 2022 Pavel Dovgalyuk
+#
+# SPDX-License-Identifier: LGPL-2.1-or-later
+#
+
+# Branch on bit set or clear
+# BBIT0      110010 ..... ..... ................
+# BBIT032    110110 ..... ..... ................
+# BBIT1      111010 ..... ..... ................
+# BBIT132    111110 ..... ..... ................
+
+BBIT         11 set:1 shift:1 10 rs:5 p:5 offset:16
diff --git a/target/mips/tcg/octeon_translate.c b/target/mips/tcg/octeon_translate.c
new file mode 100644
index 0000000000..bd87066b01
--- /dev/null
+++ b/target/mips/tcg/octeon_translate.c
@@ -0,0 +1,53 @@
+/*
+ * Octeon-specific instructions translation routines
+ *
+ *  Copyright (c) 2022 Pavel Dovgalyuk
+ *
+ * SPDX-License-Identifier: GPL-2.0-or-later
+ */
+
+#include "qemu/osdep.h"
+#include "tcg/tcg-op.h"
+#include "tcg/tcg-op-gvec.h"
+#include "exec/helper-gen.h"
+#include "translate.h"
+
+/* Include the auto-generated decoder.  */
+#include "decode-octeon.c.inc"
+
+static bool trans_BBIT(DisasContext *ctx, arg_BBIT *a)
+{
+    int p = a->p;
+
+    if (ctx->hflags & MIPS_HFLAG_BMASK) {
+#ifdef MIPS_DEBUG_DISAS
+        LOG_DISAS("Branch in delay / forbidden slot at PC 0x"
+                  TARGET_FMT_lx "\n", ctx->base.pc_next);
+#endif
+        generate_exception_end(ctx, EXCP_RI);
+        return true;
+    }
+
+    /* Load needed operands */
+    TCGv t0 = tcg_temp_new();
+    gen_load_gpr(t0, a->rs);
+
+    if (a->shift) {
+        p += 32;
+    }
+    tcg_gen_andi_tl(t0, t0, 1ULL << p);
+
+    /* Jump conditions */
+    if (a->set) {
+        tcg_gen_setcondi_tl(TCG_COND_NE, bcond, t0, 0);
+    } else {
+        tcg_gen_setcondi_tl(TCG_COND_EQ, bcond, t0, 0);
+    }
+
+    ctx->hflags |= MIPS_HFLAG_BC;
+    ctx->btarget = ctx->base.pc_next + 4 + a->offset * 4;
+    ctx->hflags |= MIPS_HFLAG_BDS32;
+
+    tcg_temp_free(t0);
+    return true;
+}
diff --git a/target/mips/tcg/translate.c b/target/mips/tcg/translate.c
index 6de5b66650..4f41a9b00a 100644
--- a/target/mips/tcg/translate.c
+++ b/target/mips/tcg/translate.c
@@ -15963,6 +15963,11 @@ static void decode_opc(CPUMIPSState *env, DisasContext *ctx)
     if (cpu_supports_isa(env, INSN_VR54XX) && decode_ext_vr54xx(ctx, ctx->opcode)) {
         return;
     }
+#if defined(TARGET_MIPS64)
+    if (cpu_supports_isa(env, INSN_OCTEON) && decode_ext_octeon(ctx, ctx->opcode)) {
+        return;
+    }
+#endif
 
     /* ISA extensions */
     if (ase_msa_available(env) && decode_ase_msa(ctx, ctx->opcode)) {
diff --git a/target/mips/tcg/translate.h b/target/mips/tcg/translate.h
index 9997fe2f3c..55053226ae 100644
--- a/target/mips/tcg/translate.h
+++ b/target/mips/tcg/translate.h
@@ -215,6 +215,7 @@ bool decode_ase_msa(DisasContext *ctx, uint32_t insn);
 bool decode_ext_txx9(DisasContext *ctx, uint32_t insn);
 #if defined(TARGET_MIPS64)
 bool decode_ext_tx79(DisasContext *ctx, uint32_t insn);
+bool decode_ext_octeon(DisasContext *ctx, uint32_t insn);
 #endif
 bool decode_ext_vr54xx(DisasContext *ctx, uint32_t insn);
 

Re: [PATCH 2/3] target/mips: implement Octeon-specific BBIT instructions

[Richard Henderson]

On 6/7/22 01:59, Pavel Dovgalyuk wrote:
> +# Branch on bit set or clear
> +# BBIT0      110010 ..... ..... ................
> +# BBIT032    110110 ..... ..... ................
> +# BBIT1      111010 ..... ..... ................
> +# BBIT132    111110 ..... ..... ................
> +
> +BBIT         11 set:1 shift:1 10 rs:5 p:5 offset:16

shift + p are logically one field -- all you need to do is concatenate them.

%bbit_p         28:1 16:5
BBIT            11 set:1 . 10 rs:5 ..... offset:16  p=%bbit_p

> +    if (ctx->hflags & MIPS_HFLAG_BMASK) {
> +#ifdef MIPS_DEBUG_DISAS
> +        LOG_DISAS("Branch in delay / forbidden slot at PC 0x"
> +                  TARGET_FMT_lx "\n", ctx->base.pc_next);
> +#endif

Ifdef isn't needed -- it's always defined, even to 0.

> +    tcg_gen_andi_tl(t0, t0, 1ULL << p);
> +
> +    /* Jump conditions */
> +    if (a->set) {
> +        tcg_gen_setcondi_tl(TCG_COND_NE, bcond, t0, 0);
> +    } else {
> +        tcg_gen_setcondi_tl(TCG_COND_EQ, bcond, t0, 0);
> +    }

You don't need to produce a boolean, MIPS_HFLAG_BC tests for non-zero.  Thus you can 
simplify this to

     p = tcg_constant_tl(1ull << a->p);
     if (a->set) {
         tcg_gen_and_tl(bcond, rs, p);
     } else {
         tcg_gen_andc_tl(bcond, p, rs);
     }


r~

Re: [PATCH 2/3] target/mips: implement Octeon-specific BBIT instructions

[Pavel Dovgalyuk]

On 07.06.2022 20:06, Richard Henderson wrote:
> On 6/7/22 01:59, Pavel Dovgalyuk wrote:
>> +# Branch on bit set or clear
>> +# BBIT0      110010 ..... ..... ................
>> +# BBIT032    110110 ..... ..... ................
>> +# BBIT1      111010 ..... ..... ................
>> +# BBIT132    111110 ..... ..... ................
>> +
>> +BBIT         11 set:1 shift:1 10 rs:5 p:5 offset:16
> 
> shift + p are logically one field -- all you need to do is concatenate 
> them.
> 
> %bbit_p         28:1 16:5
> BBIT            11 set:1 . 10 rs:5 ..... offset:16  p=%bbit_p

Thank you.
I will make a new version soon.

> 
>> +    if (ctx->hflags & MIPS_HFLAG_BMASK) {
>> +#ifdef MIPS_DEBUG_DISAS
>> +        LOG_DISAS("Branch in delay / forbidden slot at PC 0x"
>> +                  TARGET_FMT_lx "\n", ctx->base.pc_next);
>> +#endif
> 
> Ifdef isn't needed -- it's always defined, even to 0.
> 
>> +    tcg_gen_andi_tl(t0, t0, 1ULL << p);
>> +
>> +    /* Jump conditions */
>> +    if (a->set) {
>> +        tcg_gen_setcondi_tl(TCG_COND_NE, bcond, t0, 0);
>> +    } else {
>> +        tcg_gen_setcondi_tl(TCG_COND_EQ, bcond, t0, 0);
>> +    }
> 
> You don't need to produce a boolean, MIPS_HFLAG_BC tests for non-zero.  
> Thus you can simplify this to
> 
>      p = tcg_constant_tl(1ull << a->p);
>      if (a->set) {
>          tcg_gen_and_tl(bcond, rs, p);
>      } else {
>          tcg_gen_andc_tl(bcond, p, rs);
>      }
> 
> 
> r~

[PATCH 3/3] target/mips: implement Octeon-specific arithmetic instructions

[Pavel Dovgalyuk]

This patch implements several Octeon-specific instructions:
- BADDU
- DMUL
- EXTS/EXTS32
- CINS/CINS32
- POP/DPOP
- SEQ/SEQI
- SNE/SNEI

Signed-off-by: Pavel Dovgalyuk <Pavel.Dovgalyuk@ispras.ru>
---
 target/mips/helper.h                |    1 
 target/mips/tcg/meson.build         |    1 
 target/mips/tcg/octeon.decode       |   25 +++++
 target/mips/tcg/octeon_helper.c     |   22 ++++
 target/mips/tcg/octeon_helper.h.inc |   10 ++
 target/mips/tcg/octeon_translate.c  |  182 +++++++++++++++++++++++++++++++++++
 6 files changed, 241 insertions(+)
 create mode 100644 target/mips/tcg/octeon_helper.c
 create mode 100644 target/mips/tcg/octeon_helper.h.inc

diff --git a/target/mips/helper.h b/target/mips/helper.h
index de32d82e98..d68abdeac1 100644
--- a/target/mips/helper.h
+++ b/target/mips/helper.h
@@ -597,3 +597,4 @@ DEF_HELPER_FLAGS_2(rddsp, 0, tl, tl, env)
 
 /* Vendor extensions */
 #include "tcg/vr54xx_helper.h.inc"
+#include "tcg/octeon_helper.h.inc"
diff --git a/target/mips/tcg/meson.build b/target/mips/tcg/meson.build
index 7ee969ec8f..1852366846 100644
--- a/target/mips/tcg/meson.build
+++ b/target/mips/tcg/meson.build
@@ -26,6 +26,7 @@ mips_ss.add(files(
 mips_ss.add(when: 'TARGET_MIPS64', if_true: files(
   'tx79_translate.c',
   'octeon_translate.c',
+  'octeon_helper.c',
 ), if_false: files(
   'mxu_translate.c',
 ))
diff --git a/target/mips/tcg/octeon.decode b/target/mips/tcg/octeon.decode
index c06d576292..ababf59e42 100644
--- a/target/mips/tcg/octeon.decode
+++ b/target/mips/tcg/octeon.decode
@@ -12,3 +12,28 @@
 # BBIT132    111110 ..... ..... ................
 
 BBIT         11 set:1 shift:1 10 rs:5 p:5 offset:16
+
+# Arithmetic
+# BADDU rd, rs, rt
+# DMUL rd, rs, rt
+# EXTS rt, rs, p, lenm1
+# EXTS32 rt, rs, p, lenm1
+# CINS rt, rs, p, lenm1
+# CINS32 rt, rs, p, lenm1
+# DPOP rd, rs
+# POP rd, rs
+# SEQ rd, rs, rt
+# SEQI rt, rs, immediate
+# SNE rd, rs, rt
+# SNEI rt, rs, immediate
+
+@r3          ...... rs:5 rt:5 rd:5 ..... ......
+@bitfield    ...... rs:5 rt:5 lenm1:5 p:5 ..... shift:1
+
+BADDU        011100 ..... ..... ..... 00000 101000 @r3
+DMUL         011100 ..... ..... ..... 00000 000011 @r3
+EXTS         011100 ..... ..... ..... ..... 11101 . @bitfield
+CINS         011100 ..... ..... ..... ..... 11001 . @bitfield
+POP          011100 rs:5 00000 rd:5 00000 10110 dw:1
+SEQNE        011100 rs:5 rt:5 rd:5 00000 10101 ne:1
+SEQNEI       011100 rs:5 rt:5 imm:s10 10111 ne:1
diff --git a/target/mips/tcg/octeon_helper.c b/target/mips/tcg/octeon_helper.c
new file mode 100644
index 0000000000..e9650c58bd
--- /dev/null
+++ b/target/mips/tcg/octeon_helper.c
@@ -0,0 +1,22 @@
+/*
+ *  MIPS Octeon emulation helpers
+ *
+ *  Copyright (c) 2022 Pavel Dovgalyuk
+ *
+ * SPDX-License-Identifier: LGPL-2.1-or-later
+ */
+#include "qemu/osdep.h"
+#include "cpu.h"
+#include "exec/helper-proto.h"
+
+target_ulong helper_pop(target_ulong arg)
+{
+    int i;
+    int res = 0;
+    for (i = 0 ; i < 64 ; ++i) {
+        res += arg & 1;
+        arg >>= 1;
+    }
+
+    return res;
+}
diff --git a/target/mips/tcg/octeon_helper.h.inc b/target/mips/tcg/octeon_helper.h.inc
new file mode 100644
index 0000000000..cfc051ef47
--- /dev/null
+++ b/target/mips/tcg/octeon_helper.h.inc
@@ -0,0 +1,10 @@
+/*
+ *  MIPS Octeon emulation helpers
+ *
+ *  Copyright (c) 2022 Pavel Dovgalyuk
+ *
+ * SPDX-License-Identifier: LGPL-2.1-or-later
+ */
+#if defined(TARGET_MIPS64)
+DEF_HELPER_1(pop, tl, tl)
+#endif
diff --git a/target/mips/tcg/octeon_translate.c b/target/mips/tcg/octeon_translate.c
index bd87066b01..c4ef3e5bcb 100644
--- a/target/mips/tcg/octeon_translate.c
+++ b/target/mips/tcg/octeon_translate.c
@@ -51,3 +51,185 @@ static bool trans_BBIT(DisasContext *ctx, arg_BBIT *a)
     tcg_temp_free(t0);
     return true;
 }
+
+static bool trans_BADDU(DisasContext *ctx, arg_BADDU *a)
+{
+    TCGv t0, t1;
+
+    if (a->rt == 0) {
+        /* nop */
+        return true;
+    }
+
+    t0 = tcg_temp_new();
+    t1 = tcg_temp_new();
+    gen_load_gpr(t0, a->rs);
+    gen_load_gpr(t1, a->rt);
+
+    tcg_gen_add_tl(t0, t0, t1);
+    tcg_gen_andi_i64(cpu_gpr[a->rd], t0, 0xff);
+
+    tcg_temp_free(t0);
+    tcg_temp_free(t1);
+
+    return true;
+}
+
+static bool trans_DMUL(DisasContext *ctx, arg_DMUL *a)
+{
+    TCGv t0, t1;
+
+    if (a->rt == 0) {
+        /* nop */
+        return true;
+    }
+
+    t0 = tcg_temp_new();
+    t1 = tcg_temp_new();
+    gen_load_gpr(t0, a->rs);
+    gen_load_gpr(t1, a->rt);
+
+    tcg_gen_mul_i64(cpu_gpr[a->rd], t0, t1);
+
+    tcg_temp_free(t0);
+    tcg_temp_free(t1);
+
+    return true;
+}
+
+static bool trans_EXTS(DisasContext *ctx, arg_EXTS *a)
+{
+    TCGv t0, t1;
+    int p;
+    TCGLabel *l1;
+
+    if (a->rt == 0) {
+        /* nop */
+        return true;
+    }
+
+    p = a->p;
+    if (a->shift) {
+        p += 32;
+    }
+
+    t0 = tcg_temp_new();
+    t1 = tcg_temp_new();
+    gen_load_gpr(t1, a->rs);
+
+    tcg_gen_movi_tl(t0, ((1ULL << (a->lenm1 + 1)) - 1) << p);
+    tcg_gen_and_tl(t1, t1, t0);
+    tcg_gen_movi_tl(t0, p);
+    tcg_gen_shr_tl(cpu_gpr[a->rt], t1, t0);
+
+    l1 = gen_new_label();
+    tcg_gen_movi_tl(t0, 1ULL << a->lenm1);
+    tcg_gen_and_tl(t0, cpu_gpr[a->rt], t0);
+    tcg_gen_brcondi_tl(TCG_COND_EQ, t0, 0, l1);
+    tcg_gen_movi_tl(t0, ~((1ULL << (a->lenm1 + 1)) - 1));
+    tcg_gen_or_tl(cpu_gpr[a->rt], cpu_gpr[a->rt], t0);
+    gen_set_label(l1);
+
+    tcg_temp_free(t0);
+    tcg_temp_free(t1);
+
+    return true;
+}
+
+static bool trans_CINS(DisasContext *ctx, arg_CINS *a)
+{
+    TCGv t0, t1;
+
+    if (a->rt == 0) {
+        /* nop */
+        return true;
+    }
+
+    t0 = tcg_temp_new();
+    t1 = tcg_temp_new();
+    gen_load_gpr(t1, a->rs);
+
+    tcg_gen_movi_tl(t0, (1ULL << (a->lenm1 + 1)) - 1);
+    tcg_gen_and_tl(t1, t1, t0);
+    tcg_gen_movi_tl(t0, a->p + a->shift ? 32 : 0);
+    tcg_gen_shl_tl(cpu_gpr[a->rt], t1, t0);
+
+    tcg_temp_free(t0);
+    tcg_temp_free(t1);
+
+    return true;
+}
+
+static bool trans_POP(DisasContext *ctx, arg_POP *a)
+{
+    TCGv t0;
+
+    if (a->rd == 0) {
+        /* nop */
+        return true;
+    }
+
+    t0 = tcg_temp_new();
+    gen_load_gpr(t0, a->rs);
+    if (!a->dw) {
+        tcg_gen_andi_i64(t0, t0, 0xffffffff);
+    }
+    gen_helper_pop(cpu_gpr[a->rd], t0);
+
+    tcg_temp_free(t0);
+
+    return true;
+}
+
+static bool trans_SEQNE(DisasContext *ctx, arg_SEQNE *a)
+{
+    TCGv t0, t1;
+
+    if (a->rd == 0) {
+        /* nop */
+        return true;
+    }
+
+    t0 = tcg_temp_new();
+    t1 = tcg_temp_new();
+
+    gen_load_gpr(t0, a->rs);
+    gen_load_gpr(t1, a->rt);
+
+    if (a->ne) {
+        tcg_gen_setcond_tl(TCG_COND_NE, cpu_gpr[a->rd], t1, t0);
+    } else {
+        tcg_gen_setcond_tl(TCG_COND_EQ, cpu_gpr[a->rd], t1, t0);
+    }
+
+    tcg_temp_free(t0);
+    tcg_temp_free(t1);
+
+    return true;
+}
+
+static bool trans_SEQNEI(DisasContext *ctx, arg_SEQNEI *a)
+{
+    TCGv t0;
+
+    if (a->rt == 0) {
+        /* nop */
+        return true;
+    }
+
+    t0 = tcg_temp_new();
+
+    gen_load_gpr(t0, a->rs);
+
+    /* Sign-extend to 64 bit value */
+    target_ulong imm = a->imm;
+    if (a->ne) {
+        tcg_gen_setcondi_tl(TCG_COND_NE, cpu_gpr[a->rt], t0, imm);
+    } else {
+        tcg_gen_setcondi_tl(TCG_COND_EQ, cpu_gpr[a->rt], t0, imm);
+    }
+
+    tcg_temp_free(t0);
+
+    return true;
+}

Re: [PATCH 3/3] target/mips: implement Octeon-specific arithmetic instructions

[Richard Henderson]

On 6/7/22 01:59, Pavel Dovgalyuk wrote:
> +static bool trans_EXTS(DisasContext *ctx, arg_EXTS *a)
> +{
> +    TCGv t0, t1;
> +    int p;
> +    TCGLabel *l1;
> +
> +    if (a->rt == 0) {
> +        /* nop */
> +        return true;
> +    }
> +
> +    p = a->p;
> +    if (a->shift) {
> +        p += 32;
> +    }
> +
> +    t0 = tcg_temp_new();
> +    t1 = tcg_temp_new();
> +    gen_load_gpr(t1, a->rs);
> +
> +    tcg_gen_movi_tl(t0, ((1ULL << (a->lenm1 + 1)) - 1) << p);
> +    tcg_gen_and_tl(t1, t1, t0);
> +    tcg_gen_movi_tl(t0, p);
> +    tcg_gen_shr_tl(cpu_gpr[a->rt], t1, t0);
> +
> +    l1 = gen_new_label();
> +    tcg_gen_movi_tl(t0, 1ULL << a->lenm1);
> +    tcg_gen_and_tl(t0, cpu_gpr[a->rt], t0);
> +    tcg_gen_brcondi_tl(TCG_COND_EQ, t0, 0, l1);
> +    tcg_gen_movi_tl(t0, ~((1ULL << (a->lenm1 + 1)) - 1));
> +    tcg_gen_or_tl(cpu_gpr[a->rt], cpu_gpr[a->rt], t0);
> +    gen_set_label(l1);

This is tcg_gen_sextract_tl.

> +static bool trans_CINS(DisasContext *ctx, arg_CINS *a)
> +{
> +    TCGv t0, t1;
> +
> +    if (a->rt == 0) {
> +        /* nop */
> +        return true;
> +    }
> +
> +    t0 = tcg_temp_new();
> +    t1 = tcg_temp_new();
> +    gen_load_gpr(t1, a->rs);
> +
> +    tcg_gen_movi_tl(t0, (1ULL << (a->lenm1 + 1)) - 1);
> +    tcg_gen_and_tl(t1, t1, t0);
> +    tcg_gen_movi_tl(t0, a->p + a->shift ? 32 : 0);
> +    tcg_gen_shl_tl(cpu_gpr[a->rt], t1, t0);

This is tcg_gen_deposit_z_tl.

> +static bool trans_POP(DisasContext *ctx, arg_POP *a)
> +{
> +    TCGv t0;
> +
> +    if (a->rd == 0) {
> +        /* nop */
> +        return true;
> +    }
> +
> +    t0 = tcg_temp_new();
> +    gen_load_gpr(t0, a->rs);
> +    if (!a->dw) {
> +        tcg_gen_andi_i64(t0, t0, 0xffffffff);
> +    }
> +    gen_helper_pop(cpu_gpr[a->rd], t0);

This is tcg_gen_ctpop_tl.


r~