target/arm: Implement v8.4-RCPC

The v8.4-RCPC extension implements some new instructions:
* LDAPUR, LDAPURB, LDAPURH, LDAPRSB, LDAPRSH, LDAPRSW
* STLUR, STLURB, STLURH

These are all in a new subgroup of encodings that sits below the
top-level "Loads and Stores" group in the Arm ARM.

The STLUR* instructions have standard store-release semantics; the
LDAPUR* have Load-AcquirePC semantics, but (as with LDAPR*) we choose
to implement them as the slightly stronger Load-Acquire.

Backports commit a1229109dec4375259d3fff99f362405aab7917a from qemu

qemu/target/arm/cpu.h

@@ -3652,6 +3652,11 @@ static inline bool isar_feature_aa64_rcpc_8_3(const ARMISARegisters *id)
     return FIELD_EX64(id->id_aa64isar1, ID_AA64ISAR1, LRCPC) != 0;
 }
 
+static inline bool isar_feature_aa64_rcpc_8_4(const ARMISARegisters *id)
+{
+    return FIELD_EX64(id->id_aa64isar1, ID_AA64ISAR1, LRCPC) >= 2;
+}
+
 /*
  * Feature tests for "does this exist in either 32-bit or 64-bit?"
  */

qemu/target/arm/cpu64.c

@@ -298,7 +298,7 @@ static void aarch64_max_initfn(struct uc_struct *uc, Object *obj, void *opaque)
     t = FIELD_DP64(t, ID_AA64ISAR1, SB, 1);
     t = FIELD_DP64(t, ID_AA64ISAR1, SPECRES, 1);
     t = FIELD_DP64(t, ID_AA64ISAR1, FRINTTS, 1);
-    t = FIELD_DP64(t, ID_AA64ISAR1, LRCPC, 1); /* ARMv8.3-RCPC */
+    t = FIELD_DP64(t, ID_AA64ISAR1, LRCPC, 2); /* ARMv8.4-RCPC */
     cpu->isar.id_aa64isar1 = t;
 
     t = cpu->isar.id_aa64pfr0;

qemu/target/arm/translate-a64.c

@@ -3478,6 +3478,89 @@ static void disas_ldst_pac(DisasContext *s, uint32_t insn,
     }
 }
 
+/*
+ * LDAPR/STLR (unscaled immediate)
+ *
+ *  31  30            24    22  21       12    10    5     0
+ * +------+-------------+-----+---+--------+-----+----+-----+
+ * | size | 0 1 1 0 0 1 | opc | 0 |  imm9  | 0 0 | Rn |  Rt |
+ * +------+-------------+-----+---+--------+-----+----+-----+
+ *
+ * Rt: source or destination register
+ * Rn: base register
+ * imm9: unscaled immediate offset
+ * opc: 00: STLUR*, 01/10/11: various LDAPUR*
+ * size: size of load/store
+ */
+static void disas_ldst_ldapr_stlr(DisasContext *s, uint32_t insn)
+{
+    TCGContext *tcg_ctx = s->uc->tcg_ctx;
+    int rt = extract32(insn, 0, 5);
+    int rn = extract32(insn, 5, 5);
+    int offset = sextract32(insn, 12, 9);
+    int opc = extract32(insn, 22, 2);
+    int size = extract32(insn, 30, 2);
+    TCGv_i64 clean_addr, dirty_addr;
+    bool is_store = false;
+    bool is_signed = false;
+    bool extend = false;
+    bool iss_sf;
+
+    if (!dc_isar_feature(aa64_rcpc_8_4, s)) {
+        unallocated_encoding(s);
+        return;
+    }
+
+    switch (opc) {
+    case 0: /* STLURB */
+        is_store = true;
+        break;
+    case 1: /* LDAPUR* */
+        break;
+    case 2: /* LDAPURS* 64-bit variant */
+        if (size == 3) {
+            unallocated_encoding(s);
+            return;
+        }
+        is_signed = true;
+        break;
+    case 3: /* LDAPURS* 32-bit variant */
+        if (size > 1) {
+            unallocated_encoding(s);
+            return;
+        }
+        is_signed = true;
+        extend = true; /* zero-extend 32->64 after signed load */
+        break;
+    default:
+        g_assert_not_reached();
+    }
+
+    iss_sf = disas_ldst_compute_iss_sf(size, is_signed, opc);
+
+    if (rn == 31) {
+        gen_check_sp_alignment(s);
+    }
+
+    dirty_addr = read_cpu_reg_sp(s, rn, 1);
+    tcg_gen_addi_i64(tcg_ctx, dirty_addr, dirty_addr, offset);
+    clean_addr = clean_data_tbi(s, dirty_addr);
+
+    if (is_store) {
+        /* Store-Release semantics */
+        tcg_gen_mb(tcg_ctx, TCG_MO_ALL | TCG_BAR_STRL);
+        do_gpr_st(s, cpu_reg(s, rt), clean_addr, size, true, rt, iss_sf, true);
+    } else {
+        /*
+         * Load-AcquirePC semantics; we implement as the slightly more
+         * restrictive Load-Acquire.
+         */
+        do_gpr_ld(s, cpu_reg(s, rt), clean_addr, size, is_signed, extend,
+                  true, rt, iss_sf, true);
+        tcg_gen_mb(tcg_ctx, TCG_MO_ALL | TCG_BAR_LDAQ);
+    }
+}
+
 /* Load/store register (all forms) */
 static void disas_ldst_reg(DisasContext *s, uint32_t insn)
 {
@@ -3831,6 +3914,14 @@ static void disas_ldst(DisasContext *s, uint32_t insn)
     case 0x0d: /* AdvSIMD load/store single structure */
         disas_ldst_single_struct(s, insn);
         break;
+    case 0x19: /* LDAPR/STLR (unscaled immediate) */
+        if (extract32(insn, 10, 2) != 0 ||
+            extract32(insn, 21, 1) != 0) {
+            unallocated_encoding(s);
+            break;
+        }
+        disas_ldst_ldapr_stlr(s, insn);
+        break;
     default:
         unallocated_encoding(s);
         break;