target/arm: Convert load/store tags insns to decodetree

Convert the instructions in the load/store memory tags instruction
group to decodetree.

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20230602155223.2040685-21-peter.maydell@linaro.org

2 files changed, 190 insertions, 177 deletions

diff --git a/target/arm/tcg/a64.decode b/target/arm/tcg/a64.decode
index 4ffdc91..ef64a3f 100644
--- a/target/arm/tcg/a64.decode
+++ b/target/arm/tcg/a64.decode
@@ -528,3 +528,28 @@ LD_single          0 . 001101 . 1 . ..... 10 . 001 ..... .....  @ldst_single_d
 
 # Replicating load case
 LD_single_repl  0 q:1 001101 p:1 1 . rm:5 11 . 0 scale:2 rn:5 rt:5 selem=%ldst_single_selem
+
+%tag_offset     12:s9 !function=scale_by_log2_tag_granule
+&ldst_tag       rn rt imm p w
+@ldst_tag       ........ .. . ......... .. rn:5 rt:5 &ldst_tag imm=%tag_offset
+@ldst_tag_mult  ........ .. . 000000000 .. rn:5 rt:5 &ldst_tag imm=0
+
+STZGM           11011001 00 1 ......... 00 ..... ..... @ldst_tag_mult p=0 w=0
+STG             11011001 00 1 ......... 01 ..... ..... @ldst_tag p=1 w=1
+STG             11011001 00 1 ......... 10 ..... ..... @ldst_tag p=0 w=0
+STG             11011001 00 1 ......... 11 ..... ..... @ldst_tag p=0 w=1
+
+LDG             11011001 01 1 ......... 00 ..... ..... @ldst_tag p=0 w=0
+STZG            11011001 01 1 ......... 01 ..... ..... @ldst_tag p=1 w=1
+STZG            11011001 01 1 ......... 10 ..... ..... @ldst_tag p=0 w=0
+STZG            11011001 01 1 ......... 11 ..... ..... @ldst_tag p=0 w=1
+
+STGM            11011001 10 1 ......... 00 ..... ..... @ldst_tag_mult p=0 w=0
+ST2G            11011001 10 1 ......... 01 ..... ..... @ldst_tag p=1 w=1
+ST2G            11011001 10 1 ......... 10 ..... ..... @ldst_tag p=0 w=0
+ST2G            11011001 10 1 ......... 11 ..... ..... @ldst_tag p=0 w=1
+
+LDGM            11011001 11 1 ......... 00 ..... ..... @ldst_tag_mult p=0 w=0
+STZ2G           11011001 11 1 ......... 01 ..... ..... @ldst_tag p=1 w=1
+STZ2G           11011001 11 1 ......... 10 ..... ..... @ldst_tag p=0 w=0
+STZ2G           11011001 11 1 ......... 11 ..... ..... @ldst_tag p=0 w=1
diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c
index f9a7614..3baab6a 100644
--- a/target/arm/tcg/translate-a64.c
+++ b/target/arm/tcg/translate-a64.c
@@ -62,6 +62,12 @@ static int uimm_scaled(DisasContext *s, int x)
     return imm << scale;
 }
 
+/* For load/store memory tags: scale offset by LOG2_TAG_GRANULE */
+static int scale_by_log2_tag_granule(DisasContext *s, int x)
+{
+    return x << LOG2_TAG_GRANULE;
+}
+
 /*
  * Include the generated decoders.
  */
@@ -3709,185 +3715,184 @@ static bool trans_LD_single_repl(DisasContext *s, arg_LD_single_repl *a)
     return true;
 }
 
-/*
- * Load/Store memory tags
- *
- *  31 30 29         24     22  21     12    10      5      0
- * +-----+-------------+-----+---+------+-----+------+------+
- * | 1 1 | 0 1 1 0 0 1 | op1 | 1 | imm9 | op2 |  Rn  |  Rt  |
- * +-----+-------------+-----+---+------+-----+------+------+
- */
-static void disas_ldst_tag(DisasContext *s, uint32_t insn)
+static bool trans_STZGM(DisasContext *s, arg_ldst_tag *a)
 {
-    int rt = extract32(insn, 0, 5);
-    int rn = extract32(insn, 5, 5);
-    uint64_t offset = sextract64(insn, 12, 9) << LOG2_TAG_GRANULE;
-    int op2 = extract32(insn, 10, 2);
-    int op1 = extract32(insn, 22, 2);
-    bool is_load = false, is_pair = false, is_zero = false, is_mult = false;
-    int index = 0;
     TCGv_i64 addr, clean_addr, tcg_rt;
+    int size = 4 << s->dcz_blocksize;
 
-    /* We checked insn bits [29:24,21] in the caller.  */
-    if (extract32(insn, 30, 2) != 3) {
-        goto do_unallocated;
+    if (!dc_isar_feature(aa64_mte, s)) {
+        return false;
+    }
+    if (s->current_el == 0) {
+        return false;
+    }
+
+    if (a->rn == 31) {
+        gen_check_sp_alignment(s);
     }
 
+    addr = read_cpu_reg_sp(s, a->rn, true);
+    tcg_gen_addi_i64(addr, addr, a->imm);
+    tcg_rt = cpu_reg(s, a->rt);
+
+    if (s->ata) {
+        gen_helper_stzgm_tags(cpu_env, addr, tcg_rt);
+    }
     /*
-     * @index is a tri-state variable which has 3 states:
-     * < 0 : post-index, writeback
-     * = 0 : signed offset
-     * > 0 : pre-index, writeback
+     * The non-tags portion of STZGM is mostly like DC_ZVA,
+     * except the alignment happens before the access.
      */
-    switch (op1) {
-    case 0:
-        if (op2 != 0) {
-            /* STG */
-            index = op2 - 2;
-        } else {
-            /* STZGM */
-            if (s->current_el == 0 || offset != 0) {
-                goto do_unallocated;
-            }
-            is_mult = is_zero = true;
-        }
-        break;
-    case 1:
-        if (op2 != 0) {
-            /* STZG */
-            is_zero = true;
-            index = op2 - 2;
-        } else {
-            /* LDG */
-            is_load = true;
-        }
-        break;
-    case 2:
-        if (op2 != 0) {
-            /* ST2G */
-            is_pair = true;
-            index = op2 - 2;
-        } else {
-            /* STGM */
-            if (s->current_el == 0 || offset != 0) {
-                goto do_unallocated;
-            }
-            is_mult = true;
-        }
-        break;
-    case 3:
-        if (op2 != 0) {
-            /* STZ2G */
-            is_pair = is_zero = true;
-            index = op2 - 2;
-        } else {
-            /* LDGM */
-            if (s->current_el == 0 || offset != 0) {
-                goto do_unallocated;
-            }
-            is_mult = is_load = true;
-        }
-        break;
+    clean_addr = clean_data_tbi(s, addr);
+    tcg_gen_andi_i64(clean_addr, clean_addr, -size);
+    gen_helper_dc_zva(cpu_env, clean_addr);
+    return true;
+}
 
-    default:
-    do_unallocated:
-        unallocated_encoding(s);
-        return;
+static bool trans_STGM(DisasContext *s, arg_ldst_tag *a)
+{
+    TCGv_i64 addr, clean_addr, tcg_rt;
+
+    if (!dc_isar_feature(aa64_mte, s)) {
+        return false;
+    }
+    if (s->current_el == 0) {
+        return false;
     }
 
-    if (is_mult
-        ? !dc_isar_feature(aa64_mte, s)
-        : !dc_isar_feature(aa64_mte_insn_reg, s)) {
-        goto do_unallocated;
+    if (a->rn == 31) {
+        gen_check_sp_alignment(s);
     }
 
-    if (rn == 31) {
+    addr = read_cpu_reg_sp(s, a->rn, true);
+    tcg_gen_addi_i64(addr, addr, a->imm);
+    tcg_rt = cpu_reg(s, a->rt);
+
+    if (s->ata) {
+        gen_helper_stgm(cpu_env, addr, tcg_rt);
+    } else {
+        MMUAccessType acc = MMU_DATA_STORE;
+        int size = 4 << GMID_EL1_BS;
+
+        clean_addr = clean_data_tbi(s, addr);
+        tcg_gen_andi_i64(clean_addr, clean_addr, -size);
+        gen_probe_access(s, clean_addr, acc, size);
+    }
+    return true;
+}
+
+static bool trans_LDGM(DisasContext *s, arg_ldst_tag *a)
+{
+    TCGv_i64 addr, clean_addr, tcg_rt;
+
+    if (!dc_isar_feature(aa64_mte, s)) {
+        return false;
+    }
+    if (s->current_el == 0) {
+        return false;
+    }
+
+    if (a->rn == 31) {
         gen_check_sp_alignment(s);
     }
 
-    addr = read_cpu_reg_sp(s, rn, true);
-    if (index >= 0) {
-        /* pre-index or signed offset */
-        tcg_gen_addi_i64(addr, addr, offset);
+    addr = read_cpu_reg_sp(s, a->rn, true);
+    tcg_gen_addi_i64(addr, addr, a->imm);
+    tcg_rt = cpu_reg(s, a->rt);
+
+    if (s->ata) {
+        gen_helper_ldgm(tcg_rt, cpu_env, addr);
+    } else {
+        MMUAccessType acc = MMU_DATA_LOAD;
+        int size = 4 << GMID_EL1_BS;
+
+        clean_addr = clean_data_tbi(s, addr);
+        tcg_gen_andi_i64(clean_addr, clean_addr, -size);
+        gen_probe_access(s, clean_addr, acc, size);
+        /* The result tags are zeros.  */
+        tcg_gen_movi_i64(tcg_rt, 0);
     }
+    return true;
+}
 
-    if (is_mult) {
-        tcg_rt = cpu_reg(s, rt);
+static bool trans_LDG(DisasContext *s, arg_ldst_tag *a)
+{
+    TCGv_i64 addr, clean_addr, tcg_rt;
 
-        if (is_zero) {
-            int size = 4 << s->dcz_blocksize;
+    if (!dc_isar_feature(aa64_mte_insn_reg, s)) {
+        return false;
+    }
 
-            if (s->ata) {
-                gen_helper_stzgm_tags(cpu_env, addr, tcg_rt);
-            }
-            /*
-             * The non-tags portion of STZGM is mostly like DC_ZVA,
-             * except the alignment happens before the access.
-             */
-            clean_addr = clean_data_tbi(s, addr);
-            tcg_gen_andi_i64(clean_addr, clean_addr, -size);
-            gen_helper_dc_zva(cpu_env, clean_addr);
-        } else if (s->ata) {
-            if (is_load) {
-                gen_helper_ldgm(tcg_rt, cpu_env, addr);
-            } else {
-                gen_helper_stgm(cpu_env, addr, tcg_rt);
-            }
-        } else {
-            MMUAccessType acc = is_load ? MMU_DATA_LOAD : MMU_DATA_STORE;
-            int size = 4 << GMID_EL1_BS;
+    if (a->rn == 31) {
+        gen_check_sp_alignment(s);
+    }
+
+    addr = read_cpu_reg_sp(s, a->rn, true);
+    if (!a->p) {
+        /* pre-index or signed offset */
+        tcg_gen_addi_i64(addr, addr, a->imm);
+    }
 
-            clean_addr = clean_data_tbi(s, addr);
-            tcg_gen_andi_i64(clean_addr, clean_addr, -size);
-            gen_probe_access(s, clean_addr, acc, size);
+    tcg_gen_andi_i64(addr, addr, -TAG_GRANULE);
+    tcg_rt = cpu_reg(s, a->rt);
+    if (s->ata) {
+        gen_helper_ldg(tcg_rt, cpu_env, addr, tcg_rt);
+    } else {
+        /*
+         * Tag access disabled: we must check for aborts on the load
+         * load from [rn+offset], and then insert a 0 tag into rt.
+         */
+        clean_addr = clean_data_tbi(s, addr);
+        gen_probe_access(s, clean_addr, MMU_DATA_LOAD, MO_8);
+        gen_address_with_allocation_tag0(tcg_rt, tcg_rt);
+    }
 
-            if (is_load) {
-                /* The result tags are zeros.  */
-                tcg_gen_movi_i64(tcg_rt, 0);
-            }
+    if (a->w) {
+        /* pre-index or post-index */
+        if (a->p) {
+            /* post-index */
+            tcg_gen_addi_i64(addr, addr, a->imm);
         }
-        return;
+        tcg_gen_mov_i64(cpu_reg_sp(s, a->rn), addr);
     }
+    return true;
+}
 
-    if (is_load) {
-        tcg_gen_andi_i64(addr, addr, -TAG_GRANULE);
-        tcg_rt = cpu_reg(s, rt);
-        if (s->ata) {
-            gen_helper_ldg(tcg_rt, cpu_env, addr, tcg_rt);
+static bool do_STG(DisasContext *s, arg_ldst_tag *a, bool is_zero, bool is_pair)
+{
+    TCGv_i64 addr, tcg_rt;
+
+    if (a->rn == 31) {
+        gen_check_sp_alignment(s);
+    }
+
+    addr = read_cpu_reg_sp(s, a->rn, true);
+    if (!a->p) {
+        /* pre-index or signed offset */
+        tcg_gen_addi_i64(addr, addr, a->imm);
+    }
+    tcg_rt = cpu_reg_sp(s, a->rt);
+    if (!s->ata) {
+        /*
+         * For STG and ST2G, we need to check alignment and probe memory.
+         * TODO: For STZG and STZ2G, we could rely on the stores below,
+         * at least for system mode; user-only won't enforce alignment.
+         */
+        if (is_pair) {
+            gen_helper_st2g_stub(cpu_env, addr);
         } else {
-            /*
-             * Tag access disabled: we must check for aborts on the load
-             * load from [rn+offset], and then insert a 0 tag into rt.
-             */
-            clean_addr = clean_data_tbi(s, addr);
-            gen_probe_access(s, clean_addr, MMU_DATA_LOAD, MO_8);
-            gen_address_with_allocation_tag0(tcg_rt, tcg_rt);
+            gen_helper_stg_stub(cpu_env, addr);
+        }
+    } else if (tb_cflags(s->base.tb) & CF_PARALLEL) {
+        if (is_pair) {
+            gen_helper_st2g_parallel(cpu_env, addr, tcg_rt);
+        } else {
+            gen_helper_stg_parallel(cpu_env, addr, tcg_rt);
         }
     } else {
-        tcg_rt = cpu_reg_sp(s, rt);
-        if (!s->ata) {
-            /*
-             * For STG and ST2G, we need to check alignment and probe memory.
-             * TODO: For STZG and STZ2G, we could rely on the stores below,
-             * at least for system mode; user-only won't enforce alignment.
-             */
-            if (is_pair) {
-                gen_helper_st2g_stub(cpu_env, addr);
-            } else {
-                gen_helper_stg_stub(cpu_env, addr);
-            }
-        } else if (tb_cflags(s->base.tb) & CF_PARALLEL) {
-            if (is_pair) {
-                gen_helper_st2g_parallel(cpu_env, addr, tcg_rt);
-            } else {
-                gen_helper_stg_parallel(cpu_env, addr, tcg_rt);
-            }
+        if (is_pair) {
+            gen_helper_st2g(cpu_env, addr, tcg_rt);
         } else {
-            if (is_pair) {
-                gen_helper_st2g(cpu_env, addr, tcg_rt);
-            } else {
-                gen_helper_stg(cpu_env, addr, tcg_rt);
-            }
+            gen_helper_stg(cpu_env, addr, tcg_rt);
         }
     }
 
@@ -3908,32 +3913,21 @@ static void disas_ldst_tag(DisasContext *s, uint32_t insn)
         }
     }
 
-    if (index != 0) {
+    if (a->w) {
         /* pre-index or post-index */
-        if (index < 0) {
+        if (a->p) {
             /* post-index */
-            tcg_gen_addi_i64(addr, addr, offset);
+            tcg_gen_addi_i64(addr, addr, a->imm);
         }
-        tcg_gen_mov_i64(cpu_reg_sp(s, rn), addr);
+        tcg_gen_mov_i64(cpu_reg_sp(s, a->rn), addr);
     }
+    return true;
 }
 
-/* Loads and stores */
-static void disas_ldst(DisasContext *s, uint32_t insn)
-{
-    switch (extract32(insn, 24, 6)) {
-    case 0x19:
-        if (extract32(insn, 21, 1) != 0) {
-            disas_ldst_tag(s, insn);
-        } else {
-            unallocated_encoding(s);
-        }
-        break;
-    default:
-        unallocated_encoding(s);
-        break;
-    }
-}
+TRANS_FEAT(STG, aa64_mte_insn_reg, do_STG, a, false, false)
+TRANS_FEAT(STZG, aa64_mte_insn_reg, do_STG, a, true, false)
+TRANS_FEAT(ST2G, aa64_mte_insn_reg, do_STG, a, false, true)
+TRANS_FEAT(STZ2G, aa64_mte_insn_reg, do_STG, a, true, true)
 
 typedef void ArithTwoOp(TCGv_i64, TCGv_i64, TCGv_i64);
 
@@ -13829,12 +13823,6 @@ static bool btype_destination_ok(uint32_t insn, bool bt, int btype)
 static void disas_a64_legacy(DisasContext *s, uint32_t insn)
 {
     switch (extract32(insn, 25, 4)) {
-    case 0x4:
-    case 0x6:
-    case 0xc:
-    case 0xe:      /* Loads and stores */
-        disas_ldst(s, insn);
-        break;
     case 0x5:
     case 0xd:      /* Data processing - register */
         disas_data_proc_reg(s, insn);