[PATCH v5 3/6] target/arm/emulate: add load/store pair

[Lucas Amaral <lucaaamaral@gmail.com>]

Add emulation for load/store pair instructions (DDI 0487 C3.3.14 --
C3.3.16).  All addressing modes are covered: non-temporal (STNP/LDNP),
post-indexed, signed offset, and pre-indexed.

Instruction coverage:
  - STP/LDP (GPR): 32/64-bit pairs, all addressing modes
  - STP/LDP (SIMD/FP): 32/64/128-bit pairs, all addressing modes
  - LDPSW: sign-extending 32-bit pair load
  - STGP: store allocation tag pair (tag operation is NOP for MMIO)

Signed-off-by: Lucas Amaral <lucaaamaral@gmail.com>
---
 target/arm/emulate/a64-ldst.decode |  68 ++++++++++++++++++
 target/arm/emulate/arm_emulate.c   | 111 +++++++++++++++++++++++++++++
 2 files changed, 179 insertions(+)

diff --git a/target/arm/emulate/a64-ldst.decode b/target/arm/emulate/a64-ldst.decode
index af6babe1..f3de3f86 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 pair (GPR and SIMD/FP)
+&ldstpair       rt2 rt rn imm sz sign w p
+
 # Load/store register offset
 &ldst           rm rn rt sign ext sz opt s
 
@@ -24,6 +27,9 @@
 # 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 pair: imm7 is signed, scaled by element size in handler
+@ldstpair       .. ... . ... . imm:s7 rt2:5 rn:5 rt:5          &ldstpair
+
 # Load/store register offset
 @ldst           .. ... . .. .. . rm:5 opt:3 s:1 .. rn:5 rt:5   &ldst
 
@@ -128,6 +134,68 @@ 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 pair — non-temporal (STNP/LDNP)
+
+# STNP/LDNP: offset only, no writeback.  Non-temporal hint ignored.
+STP             00 101 0 000 0 ....... ..... ..... .....        @ldstpair sz=2 sign=0 p=0 w=0
+LDP             00 101 0 000 1 ....... ..... ..... .....        @ldstpair sz=2 sign=0 p=0 w=0
+STP             10 101 0 000 0 ....... ..... ..... .....        @ldstpair sz=3 sign=0 p=0 w=0
+LDP             10 101 0 000 1 ....... ..... ..... .....        @ldstpair sz=3 sign=0 p=0 w=0
+STP_v           00 101 1 000 0 ....... ..... ..... .....        @ldstpair sz=2 sign=0 p=0 w=0
+LDP_v           00 101 1 000 1 ....... ..... ..... .....        @ldstpair sz=2 sign=0 p=0 w=0
+STP_v           01 101 1 000 0 ....... ..... ..... .....        @ldstpair sz=3 sign=0 p=0 w=0
+LDP_v           01 101 1 000 1 ....... ..... ..... .....        @ldstpair sz=3 sign=0 p=0 w=0
+STP_v           10 101 1 000 0 ....... ..... ..... .....        @ldstpair sz=4 sign=0 p=0 w=0
+LDP_v           10 101 1 000 1 ....... ..... ..... .....        @ldstpair sz=4 sign=0 p=0 w=0
+
+### Load/store pair — post-indexed
+
+STP             00 101 0 001 0 ....... ..... ..... .....        @ldstpair sz=2 sign=0 p=1 w=1
+LDP             00 101 0 001 1 ....... ..... ..... .....        @ldstpair sz=2 sign=0 p=1 w=1
+LDP             01 101 0 001 1 ....... ..... ..... .....        @ldstpair sz=2 sign=1 p=1 w=1
+STP             10 101 0 001 0 ....... ..... ..... .....        @ldstpair sz=3 sign=0 p=1 w=1
+LDP             10 101 0 001 1 ....... ..... ..... .....        @ldstpair sz=3 sign=0 p=1 w=1
+STP_v           00 101 1 001 0 ....... ..... ..... .....        @ldstpair sz=2 sign=0 p=1 w=1
+LDP_v           00 101 1 001 1 ....... ..... ..... .....        @ldstpair sz=2 sign=0 p=1 w=1
+STP_v           01 101 1 001 0 ....... ..... ..... .....        @ldstpair sz=3 sign=0 p=1 w=1
+LDP_v           01 101 1 001 1 ....... ..... ..... .....        @ldstpair sz=3 sign=0 p=1 w=1
+STP_v           10 101 1 001 0 ....... ..... ..... .....        @ldstpair sz=4 sign=0 p=1 w=1
+LDP_v           10 101 1 001 1 ....... ..... ..... .....        @ldstpair sz=4 sign=0 p=1 w=1
+
+### Load/store pair — signed offset
+
+STP             00 101 0 010 0 ....... ..... ..... .....        @ldstpair sz=2 sign=0 p=0 w=0
+LDP             00 101 0 010 1 ....... ..... ..... .....        @ldstpair sz=2 sign=0 p=0 w=0
+LDP             01 101 0 010 1 ....... ..... ..... .....        @ldstpair sz=2 sign=1 p=0 w=0
+STP             10 101 0 010 0 ....... ..... ..... .....        @ldstpair sz=3 sign=0 p=0 w=0
+LDP             10 101 0 010 1 ....... ..... ..... .....        @ldstpair sz=3 sign=0 p=0 w=0
+STP_v           00 101 1 010 0 ....... ..... ..... .....        @ldstpair sz=2 sign=0 p=0 w=0
+LDP_v           00 101 1 010 1 ....... ..... ..... .....        @ldstpair sz=2 sign=0 p=0 w=0
+STP_v           01 101 1 010 0 ....... ..... ..... .....        @ldstpair sz=3 sign=0 p=0 w=0
+LDP_v           01 101 1 010 1 ....... ..... ..... .....        @ldstpair sz=3 sign=0 p=0 w=0
+STP_v           10 101 1 010 0 ....... ..... ..... .....        @ldstpair sz=4 sign=0 p=0 w=0
+LDP_v           10 101 1 010 1 ....... ..... ..... .....        @ldstpair sz=4 sign=0 p=0 w=0
+
+### Load/store pair — pre-indexed
+
+STP             00 101 0 011 0 ....... ..... ..... .....        @ldstpair sz=2 sign=0 p=0 w=1
+LDP             00 101 0 011 1 ....... ..... ..... .....        @ldstpair sz=2 sign=0 p=0 w=1
+LDP             01 101 0 011 1 ....... ..... ..... .....        @ldstpair sz=2 sign=1 p=0 w=1
+STP             10 101 0 011 0 ....... ..... ..... .....        @ldstpair sz=3 sign=0 p=0 w=1
+LDP             10 101 0 011 1 ....... ..... ..... .....        @ldstpair sz=3 sign=0 p=0 w=1
+STP_v           00 101 1 011 0 ....... ..... ..... .....        @ldstpair sz=2 sign=0 p=0 w=1
+LDP_v           00 101 1 011 1 ....... ..... ..... .....        @ldstpair sz=2 sign=0 p=0 w=1
+STP_v           01 101 1 011 0 ....... ..... ..... .....        @ldstpair sz=3 sign=0 p=0 w=1
+LDP_v           01 101 1 011 1 ....... ..... ..... .....        @ldstpair sz=3 sign=0 p=0 w=1
+STP_v           10 101 1 011 0 ....... ..... ..... .....        @ldstpair sz=4 sign=0 p=0 w=1
+LDP_v           10 101 1 011 1 ....... ..... ..... .....        @ldstpair sz=4 sign=0 p=0 w=1
+
+### Load/store pair — STGP (store allocation tag + pair)
+
+STGP            01 101 0 001 0 ....... ..... ..... .....        @ldstpair sz=3 sign=0 p=1 w=1
+STGP            01 101 0 010 0 ....... ..... ..... .....        @ldstpair sz=3 sign=0 p=0 w=0
+STGP            01 101 0 011 0 ....... ..... ..... .....        @ldstpair sz=3 sign=0 p=0 w=1
+
 ### Load/store register — register offset
 
 # GPR
diff --git a/target/arm/emulate/arm_emulate.c b/target/arm/emulate/arm_emulate.c
index bf09e2a6..6c63a0d0 100644
--- a/target/arm/emulate/arm_emulate.c
+++ b/target/arm/emulate/arm_emulate.c
@@ -122,6 +122,117 @@ static uint64_t load_extend(uint64_t val, int sz, int sign, int ext)
     return val;
 }
 
+/*
+ * Load/store pair: STP, LDP, STNP, LDNP, STGP, LDPSW
+ * (DDI 0487 C3.3.14 -- C3.3.16)
+ */
+
+static bool trans_STP(DisasContext *ctx, arg_ldstpair *a)
+{
+    int esize = 1 << a->sz;                   /* 4 or 8 bytes */
+    int64_t offset = (int64_t)a->imm << a->sz;
+    uint64_t base = base_read(ctx, a->rn);
+    uint64_t va = a->p ? base : base + offset; /* post-index: unmodified base */
+    uint8_t buf[16];                           /* max 2 x 8 bytes */
+
+    uint64_t v1 = gpr_read(ctx, a->rt);
+    uint64_t v2 = gpr_read(ctx, a->rt2);
+    memcpy(buf, &v1, esize);
+    memcpy(buf + esize, &v2, esize);
+
+    if (mem_write(ctx, va, buf, 2 * esize) != 0) {
+        return true;
+    }
+
+    if (a->w) {
+        base_write(ctx, a->rn, base + offset);
+    }
+    return true;
+}
+
+static bool trans_LDP(DisasContext *ctx, arg_ldstpair *a)
+{
+    int esize = 1 << a->sz;
+    int64_t offset = (int64_t)a->imm << a->sz;
+    uint64_t base = base_read(ctx, a->rn);
+    uint64_t va = a->p ? base : base + offset;
+    uint8_t buf[16];
+    uint64_t v1 = 0, v2 = 0;
+
+    if (mem_read(ctx, va, buf, 2 * esize) != 0) {
+        return true;
+    }
+    memcpy(&v1, buf, esize);
+    memcpy(&v2, buf + esize, esize);
+
+    /* LDPSW: sign-extend 32-bit values to 64-bit (sign=1, sz=2) */
+    if (a->sign) {
+        v1 = sign_extend(v1, 8 * esize);
+        v2 = sign_extend(v2, 8 * esize);
+    }
+
+    gpr_write(ctx, a->rt, v1);
+    gpr_write(ctx, a->rt2, v2);
+
+    if (a->w) {
+        base_write(ctx, a->rn, base + offset);
+    }
+    return true;
+}
+
+/* STGP: tag operation is a NOP for emulation; data stored via STP */
+static bool trans_STGP(DisasContext *ctx, arg_ldstpair *a)
+{
+    return trans_STP(ctx, a);
+}
+
+/*
+ * SIMD/FP load/store pair: STP_v, LDP_v
+ * (DDI 0487 C3.3.14 -- C3.3.16)
+ */
+
+static bool trans_STP_v(DisasContext *ctx, arg_ldstpair *a)
+{
+    int esize = 1 << a->sz;                   /* 4, 8, or 16 bytes */
+    int64_t offset = (int64_t)a->imm << a->sz;
+    uint64_t base = base_read(ctx, a->rn);
+    uint64_t va = a->p ? base : base + offset;
+    uint8_t buf[32];                           /* max 2 x 16 bytes */
+
+    fpreg_read(ctx, a->rt, buf, esize);
+    fpreg_read(ctx, a->rt2, buf + esize, esize);
+
+    if (mem_write(ctx, va, buf, 2 * esize) != 0) {
+        return true;
+    }
+
+    if (a->w) {
+        base_write(ctx, a->rn, base + offset);
+    }
+    return true;
+}
+
+static bool trans_LDP_v(DisasContext *ctx, arg_ldstpair *a)
+{
+    int esize = 1 << a->sz;
+    int64_t offset = (int64_t)a->imm << a->sz;
+    uint64_t base = base_read(ctx, a->rn);
+    uint64_t va = a->p ? base : base + offset;
+    uint8_t buf[32];
+
+    if (mem_read(ctx, va, buf, 2 * esize) != 0) {
+        return true;
+    }
+
+    fpreg_write(ctx, a->rt, buf, esize);
+    fpreg_write(ctx, a->rt2, buf + esize, esize);
+
+    if (a->w) {
+        base_write(ctx, a->rn, base + offset);
+    }
+    return true;
+}
+
 /* Load/store single -- immediate (GPR) (DDI 0487 C3.3.8 -- C3.3.13) */
 
 static bool trans_STR_i(DisasContext *ctx, arg_ldst_imm *a)
-- 
2.52.0