[PATCH v3 2/6] target/arm/emulate: add load/store register offset

[Lucas Amaral <lucaaamaral@gmail.com>]

Add emulation for load/store register offset addressing mode
(DDI 0487 C3.3.9).  The offset register value is extended via
UXTB/UXTH/UXTW/UXTX/SXTB/SXTH/SXTW/SXTX and optionally
shifted by the element size.

Instruction coverage:
  - STR/LDR (GPR): register offset with extend, all sizes
  - STR/LDR (SIMD/FP): register offset with extend, 8-128 bit
  - PRFM register offset: NOP

Signed-off-by: Lucas Amaral <lucaaamaral@gmail.com>
---
 target/arm/emulate/a64-ldst.decode |  29 ++++++++
 target/arm/emulate/arm_emulate.c   | 103 +++++++++++++++++++++++++++++
 2 files changed, 132 insertions(+)

diff --git a/target/arm/emulate/a64-ldst.decode b/target/arm/emulate/a64-ldst.decode
index c887dcba..af6babe1 100644
--- a/target/arm/emulate/a64-ldst.decode
+++ b/target/arm/emulate/a64-ldst.decode
@@ -10,6 +10,9 @@
 # 'u' flag: 0 = 9-bit signed immediate (byte offset), 1 = 12-bit unsigned (needs << sz)
 &ldst_imm       rt rn imm sz sign w p unpriv ext u
 
+# Load/store register offset
+&ldst           rm rn rt sign ext sz opt s
+
 ### Format templates
 
 # Load/store immediate (9-bit signed)
@@ -21,6 +24,9 @@
 # Load/store unsigned offset (12-bit, handler scales by << sz)
 @ldst_uimm      .. ... . .. .. imm:12 rn:5 rt:5        &ldst_imm u=1 unpriv=0 p=0 w=0
 
+# Load/store register offset
+@ldst           .. ... . .. .. . rm:5 opt:3 s:1 .. rn:5 rt:5   &ldst
+
 ### Load/store register — unscaled immediate (LDUR/STUR)
 
 # GPR
@@ -122,6 +128,29 @@ STR_v_i         00 111 1 01 10 ............ ..... .....         @ldst_uimm sign=
 LDR_v_i         sz:2 111 1 01 01 ............ ..... .....       @ldst_uimm sign=0 ext=0
 LDR_v_i         00 111 1 01 11 ............ ..... .....         @ldst_uimm sign=0 ext=0 sz=4
 
+### Load/store register — register offset
+
+# GPR
+STR             sz:2 111 0 00 00 1 ..... ... . 10 ..... .....  @ldst sign=0 ext=0
+LDR             00 111 0 00 01 1 ..... ... . 10 ..... .....    @ldst sign=0 ext=1 sz=0
+LDR             01 111 0 00 01 1 ..... ... . 10 ..... .....    @ldst sign=0 ext=1 sz=1
+LDR             10 111 0 00 01 1 ..... ... . 10 ..... .....    @ldst sign=0 ext=1 sz=2
+LDR             11 111 0 00 01 1 ..... ... . 10 ..... .....    @ldst sign=0 ext=0 sz=3
+LDR             00 111 0 00 10 1 ..... ... . 10 ..... .....    @ldst sign=1 ext=0 sz=0
+LDR             01 111 0 00 10 1 ..... ... . 10 ..... .....    @ldst sign=1 ext=0 sz=1
+LDR             10 111 0 00 10 1 ..... ... . 10 ..... .....    @ldst sign=1 ext=0 sz=2
+LDR             00 111 0 00 11 1 ..... ... . 10 ..... .....    @ldst sign=1 ext=1 sz=0
+LDR             01 111 0 00 11 1 ..... ... . 10 ..... .....    @ldst sign=1 ext=1 sz=1
+
+# PRFM — register offset
+NOP             11 111 0 00 10 1 ----- -1- - 10 ----- -----
+
+# SIMD/FP
+STR_v           sz:2 111 1 00 00 1 ..... ... . 10 ..... .....  @ldst sign=0 ext=0
+STR_v           00 111 1 00 10 1 ..... ... . 10 ..... .....    @ldst sign=0 ext=0 sz=4
+LDR_v           sz:2 111 1 00 01 1 ..... ... . 10 ..... .....  @ldst sign=0 ext=0
+LDR_v           00 111 1 00 11 1 ..... ... . 10 ..... .....    @ldst sign=0 ext=0 sz=4
+
 ### System instructions — DC cache maintenance
 
 # SYS with CRn=C7 covers all data cache operations (DC CIVAC, CVAC, etc.).
diff --git a/target/arm/emulate/arm_emulate.c b/target/arm/emulate/arm_emulate.c
index 2b4e2a9e..0e77cf33 100644
--- a/target/arm/emulate/arm_emulate.c
+++ b/target/arm/emulate/arm_emulate.c
@@ -200,6 +200,109 @@ static bool trans_LDR_v_i(DisasContext *ctx, arg_ldst_imm *a)
     return true;
 }
 
+/* Register offset extension (DDI 0487 C6.2.131) */
+
+static uint64_t extend_reg(uint64_t val, int option, int shift)
+{
+    switch (option) {
+    case 0: /* UXTB */
+        val = (uint8_t)val;
+        break;
+    case 1: /* UXTH */
+        val = (uint16_t)val;
+        break;
+    case 2: /* UXTW */
+        val = (uint32_t)val;
+        break;
+    case 3: /* UXTX / LSL */
+        break;
+    case 4: /* SXTB */
+        val = (int64_t)(int8_t)val;
+        break;
+    case 5: /* SXTH */
+        val = (int64_t)(int16_t)val;
+        break;
+    case 6: /* SXTW */
+        val = (int64_t)(int32_t)val;
+        break;
+    case 7: /* SXTX */
+        break;
+    }
+    return val << shift;
+}
+
+/*
+ * Load/store single -- register offset (GPR)
+ * STR / LDR (DDI 0487 C3.3.9)
+ */
+
+static bool trans_STR(DisasContext *ctx, arg_ldst *a)
+{
+    int esize = (a->sz <= 3) ? (1 << a->sz) : 16;
+    int shift = a->s ? a->sz : 0;
+    uint64_t rm_val = gpr_read(ctx, a->rm);
+    uint64_t offset = extend_reg(rm_val, a->opt, shift);
+    uint64_t va = base_read(ctx, a->rn) + offset;
+
+    uint64_t val = gpr_read(ctx, a->rt);
+    mem_write(ctx, va, &val, esize);
+    return true;
+}
+
+static bool trans_LDR(DisasContext *ctx, arg_ldst *a)
+{
+    int esize = (a->sz <= 3) ? (1 << a->sz) : 16;
+    int shift = a->s ? a->sz : 0;
+    uint64_t rm_val = gpr_read(ctx, a->rm);
+    uint64_t offset = extend_reg(rm_val, a->opt, shift);
+    uint64_t va = base_read(ctx, a->rn) + offset;
+    uint64_t val = 0;
+
+    if (mem_read(ctx, va, &val, esize) != 0) {
+        return true;
+    }
+
+    val = load_extend(val, a->sz, a->sign, a->ext);
+    gpr_write(ctx, a->rt, val);
+    return true;
+}
+
+/*
+ * Load/store single -- register offset (SIMD/FP)
+ * STR_v / LDR_v (DDI 0487 C3.3.10)
+ */
+
+static bool trans_STR_v(DisasContext *ctx, arg_ldst *a)
+{
+    int esize = (a->sz <= 3) ? (1 << a->sz) : 16;
+    int shift = a->s ? a->sz : 0;
+    uint64_t rm_val = gpr_read(ctx, a->rm);
+    uint64_t offset = extend_reg(rm_val, a->opt, shift);
+    uint64_t va = base_read(ctx, a->rn) + offset;
+    uint8_t buf[16];
+
+    fpreg_read(ctx, a->rt, buf, esize);
+    mem_write(ctx, va, buf, esize);
+    return true;
+}
+
+static bool trans_LDR_v(DisasContext *ctx, arg_ldst *a)
+{
+    int esize = (a->sz <= 3) ? (1 << a->sz) : 16;
+    int shift = a->s ? a->sz : 0;
+    uint64_t rm_val = gpr_read(ctx, a->rm);
+    uint64_t offset = extend_reg(rm_val, a->opt, shift);
+    uint64_t va = base_read(ctx, a->rn) + offset;
+    uint8_t buf[16];
+
+    if (mem_read(ctx, va, buf, esize) != 0) {
+        return true;
+    }
+
+    fpreg_write(ctx, a->rt, buf, esize);
+    return true;
+}
+
 /* PRFM, DC cache maintenance -- treated as NOP */
 static bool trans_NOP(DisasContext *ctx, arg_NOP *a)
 {
-- 
2.52.0