From 72430bf5eb7f7309e705705af9798d13aa94e80d Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Alex=20Benn=C3=A9e?= <alex.bennee@linaro.org>
Date: Fri, 31 Jan 2014 14:47:30 +0000
Subject: [PATCH 01/34] target-arm: A64: Add SIMD ld/st multiple
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This adds support support for the SIMD load/store
multiple category of instructions.

This also brings in a couple of helper functions for manipulating
sections of the SIMD registers:

  * do_vec_get - fetch value from a slice of a vector register
  * do_vec_set - set a slice of a vector register

which use vec_reg_offset for consistent processing of offsets in an
endian aware manner. There are also additional helpers:

  * do_vec_ld - load value into SIMD
  * do_vec_st - store value from SIMD

which load or store a slice of a vector register to memory.
These don't zero extend like the fp variants.

Signed-off-by: Alex Bennée <alex.bennee@linaro.org>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <rth@twiddle.net>
---
 target-arm/translate-a64.c | 250 ++++++++++++++++++++++++++++++++++++-
 1 file changed, 248 insertions(+), 2 deletions(-)

diff --git a/target-arm/translate-a64.c b/target-arm/translate-a64.c
index cf80c46b90..e4fdf00793 100644
--- a/target-arm/translate-a64.c
+++ b/target-arm/translate-a64.c
@@ -308,6 +308,28 @@ static TCGv_i64 read_cpu_reg_sp(DisasContext *s, int reg, int sf)
     return v;
 }
 
+/* Return the offset into CPUARMState of an element of specified
+ * size, 'element' places in from the least significant end of
+ * the FP/vector register Qn.
+ */
+static inline int vec_reg_offset(int regno, int element, TCGMemOp size)
+{
+    int offs = offsetof(CPUARMState, vfp.regs[regno * 2]);
+#ifdef HOST_WORDS_BIGENDIAN
+    /* This is complicated slightly because vfp.regs[2n] is
+     * still the low half and  vfp.regs[2n+1] the high half
+     * of the 128 bit vector, even on big endian systems.
+     * Calculate the offset assuming a fully bigendian 128 bits,
+     * then XOR to account for the order of the two 64 bit halves.
+     */
+    offs += (16 - ((element + 1) * (1 << size)));
+    offs ^= 8;
+#else
+    offs += element * (1 << size);
+#endif
+    return offs;
+}
+
 /* Return the offset into CPUARMState of a slice (from
  * the least significant end) of FP register Qn (ie
  * Dn, Sn, Hn or Bn).
@@ -660,6 +682,108 @@ static void do_fp_ld(DisasContext *s, int destidx, TCGv_i64 tcg_addr, int size)
     tcg_temp_free_i64(tmphi);
 }
 
+/*
+ * Vector load/store helpers.
+ *
+ * The principal difference between this and a FP load is that we don't
+ * zero extend as we are filling a partial chunk of the vector register.
+ * These functions don't support 128 bit loads/stores, which would be
+ * normal load/store operations.
+ */
+
+/* Get value of an element within a vector register */
+static void read_vec_element(DisasContext *s, TCGv_i64 tcg_dest, int srcidx,
+                             int element, TCGMemOp memop)
+{
+    int vect_off = vec_reg_offset(srcidx, element, memop & MO_SIZE);
+    switch (memop) {
+    case MO_8:
+        tcg_gen_ld8u_i64(tcg_dest, cpu_env, vect_off);
+        break;
+    case MO_16:
+        tcg_gen_ld16u_i64(tcg_dest, cpu_env, vect_off);
+        break;
+    case MO_32:
+        tcg_gen_ld32u_i64(tcg_dest, cpu_env, vect_off);
+        break;
+    case MO_8|MO_SIGN:
+        tcg_gen_ld8s_i64(tcg_dest, cpu_env, vect_off);
+        break;
+    case MO_16|MO_SIGN:
+        tcg_gen_ld16s_i64(tcg_dest, cpu_env, vect_off);
+        break;
+    case MO_32|MO_SIGN:
+        tcg_gen_ld32s_i64(tcg_dest, cpu_env, vect_off);
+        break;
+    case MO_64:
+    case MO_64|MO_SIGN:
+        tcg_gen_ld_i64(tcg_dest, cpu_env, vect_off);
+        break;
+    default:
+        g_assert_not_reached();
+    }
+}
+
+/* Set value of an element within a vector register */
+static void write_vec_element(DisasContext *s, TCGv_i64 tcg_src, int destidx,
+                              int element, TCGMemOp memop)
+{
+    int vect_off = vec_reg_offset(destidx, element, memop & MO_SIZE);
+    switch (memop) {
+    case MO_8:
+        tcg_gen_st8_i64(tcg_src, cpu_env, vect_off);
+        break;
+    case MO_16:
+        tcg_gen_st16_i64(tcg_src, cpu_env, vect_off);
+        break;
+    case MO_32:
+        tcg_gen_st32_i64(tcg_src, cpu_env, vect_off);
+        break;
+    case MO_64:
+        tcg_gen_st_i64(tcg_src, cpu_env, vect_off);
+        break;
+    default:
+        g_assert_not_reached();
+    }
+}
+
+/* Clear the high 64 bits of a 128 bit vector (in general non-quad
+ * vector ops all need to do this).
+ */
+static void clear_vec_high(DisasContext *s, int rd)
+{
+    TCGv_i64 tcg_zero = tcg_const_i64(0);
+
+    write_vec_element(s, tcg_zero, rd, 1, MO_64);
+    tcg_temp_free_i64(tcg_zero);
+}
+
+/* Store from vector register to memory */
+static void do_vec_st(DisasContext *s, int srcidx, int element,
+                      TCGv_i64 tcg_addr, int size)
+{
+    TCGMemOp memop = MO_TE + size;
+    TCGv_i64 tcg_tmp = tcg_temp_new_i64();
+
+    read_vec_element(s, tcg_tmp, srcidx, element, size);
+    tcg_gen_qemu_st_i64(tcg_tmp, tcg_addr, get_mem_index(s), memop);
+
+    tcg_temp_free_i64(tcg_tmp);
+}
+
+/* Load from memory to vector register */
+static void do_vec_ld(DisasContext *s, int destidx, int element,
+                      TCGv_i64 tcg_addr, int size)
+{
+    TCGMemOp memop = MO_TE + size;
+    TCGv_i64 tcg_tmp = tcg_temp_new_i64();
+
+    tcg_gen_qemu_ld_i64(tcg_tmp, tcg_addr, get_mem_index(s), memop);
+    write_vec_element(s, tcg_tmp, destidx, element, size);
+
+    tcg_temp_free_i64(tcg_tmp);
+}
+
 /*
  * This utility function is for doing register extension with an
  * optional shift. You will likely want to pass a temporary for the
@@ -1835,10 +1959,132 @@ static void disas_ldst_reg(DisasContext *s, uint32_t insn)
     }
 }
 
-/* AdvSIMD load/store multiple structures */
+/* C3.3.1 AdvSIMD load/store multiple structures
+ *
+ *  31  30  29           23 22  21         16 15    12 11  10 9    5 4    0
+ * +---+---+---------------+---+-------------+--------+------+------+------+
+ * | 0 | Q | 0 0 1 1 0 0 0 | L | 0 0 0 0 0 0 | opcode | size |  Rn  |  Rt  |
+ * +---+---+---------------+---+-------------+--------+------+------+------+
+ *
+ * C3.3.2 AdvSIMD load/store multiple structures (post-indexed)
+ *
+ *  31  30  29           23 22  21  20     16 15    12 11  10 9    5 4    0
+ * +---+---+---------------+---+---+---------+--------+------+------+------+
+ * | 0 | Q | 0 0 1 1 0 0 1 | L | 0 |   Rm    | opcode | size |  Rn  |  Rt  |
+ * +---+---+---------------+---+---+---------+--------+------+------+------+
+ *
+ * Rt: first (or only) SIMD&FP register to be transferred
+ * Rn: base address or SP
+ * Rm (post-index only): post-index register (when !31) or size dependent #imm
+ */
 static void disas_ldst_multiple_struct(DisasContext *s, uint32_t insn)
 {
-    unsupported_encoding(s, insn);
+    int rt = extract32(insn, 0, 5);
+    int rn = extract32(insn, 5, 5);
+    int size = extract32(insn, 10, 2);
+    int opcode = extract32(insn, 12, 4);
+    bool is_store = !extract32(insn, 22, 1);
+    bool is_postidx = extract32(insn, 23, 1);
+    bool is_q = extract32(insn, 30, 1);
+    TCGv_i64 tcg_addr, tcg_rn;
+
+    int ebytes = 1 << size;
+    int elements = (is_q ? 128 : 64) / (8 << size);
+    int rpt;    /* num iterations */
+    int selem;  /* structure elements */
+    int r;
+
+    if (extract32(insn, 31, 1) || extract32(insn, 21, 1)) {
+        unallocated_encoding(s);
+        return;
+    }
+
+    /* From the shared decode logic */
+    switch (opcode) {
+    case 0x0:
+        rpt = 1;
+        selem = 4;
+        break;
+    case 0x2:
+        rpt = 4;
+        selem = 1;
+        break;
+    case 0x4:
+        rpt = 1;
+        selem = 3;
+        break;
+    case 0x6:
+        rpt = 3;
+        selem = 1;
+        break;
+    case 0x7:
+        rpt = 1;
+        selem = 1;
+        break;
+    case 0x8:
+        rpt = 1;
+        selem = 2;
+        break;
+    case 0xa:
+        rpt = 2;
+        selem = 1;
+        break;
+    default:
+        unallocated_encoding(s);
+        return;
+    }
+
+    if (size == 3 && !is_q && selem != 1) {
+        /* reserved */
+        unallocated_encoding(s);
+        return;
+    }
+
+    if (rn == 31) {
+        gen_check_sp_alignment(s);
+    }
+
+    tcg_rn = cpu_reg_sp(s, rn);
+    tcg_addr = tcg_temp_new_i64();
+    tcg_gen_mov_i64(tcg_addr, tcg_rn);
+
+    for (r = 0; r < rpt; r++) {
+        int e;
+        for (e = 0; e < elements; e++) {
+            int tt = (rt + r) % 32;
+            int xs;
+            for (xs = 0; xs < selem; xs++) {
+                if (is_store) {
+                    do_vec_st(s, tt, e, tcg_addr, size);
+                } else {
+                    do_vec_ld(s, tt, e, tcg_addr, size);
+
+                    /* For non-quad operations, setting a slice of the low
+                     * 64 bits of the register clears the high 64 bits (in
+                     * the ARM ARM pseudocode this is implicit in the fact
+                     * that 'rval' is a 64 bit wide variable). We optimize
+                     * by noticing that we only need to do this the first
+                     * time we touch a register.
+                     */
+                    if (!is_q && e == 0 && (r == 0 || xs == selem - 1)) {
+                        clear_vec_high(s, tt);
+                    }
+                }
+                tcg_gen_addi_i64(tcg_addr, tcg_addr, ebytes);
+                tt = (tt + 1) % 32;
+            }
+        }
+    }
+
+    if (is_postidx) {
+        int rm = extract32(insn, 16, 5);
+        if (rm == 31) {
+            tcg_gen_mov_i64(tcg_rn, tcg_addr);
+        } else {
+            tcg_gen_add_i64(tcg_rn, tcg_rn, cpu_reg(s, rm));
+        }
+    }
+    tcg_temp_free_i64(tcg_addr);
 }
 
 /* AdvSIMD load/store single structure */

From df54e47d2b86c636b4d22f663dbffce6a3cffd81 Mon Sep 17 00:00:00 2001
From: Peter Maydell <peter.maydell@linaro.org>
Date: Fri, 31 Jan 2014 14:47:30 +0000
Subject: [PATCH 02/34] target-arm: A64: Add SIMD ld/st single

Implement the SIMD ld/st single structure instructions.

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <rth@twiddle.net>
---
 target-arm/translate-a64.c | 144 ++++++++++++++++++++++++++++++++++++-
 1 file changed, 142 insertions(+), 2 deletions(-)

diff --git a/target-arm/translate-a64.c b/target-arm/translate-a64.c
index e4fdf00793..6e317406af 100644
--- a/target-arm/translate-a64.c
+++ b/target-arm/translate-a64.c
@@ -2087,10 +2087,150 @@ static void disas_ldst_multiple_struct(DisasContext *s, uint32_t insn)
     tcg_temp_free_i64(tcg_addr);
 }
 
-/* AdvSIMD load/store single structure */
+/* C3.3.3 AdvSIMD load/store single structure
+ *
+ *  31  30  29           23 22 21 20       16 15 13 12  11  10 9    5 4    0
+ * +---+---+---------------+-----+-----------+-----+---+------+------+------+
+ * | 0 | Q | 0 0 1 1 0 1 0 | L R | 0 0 0 0 0 | opc | S | size |  Rn  |  Rt  |
+ * +---+---+---------------+-----+-----------+-----+---+------+------+------+
+ *
+ * C3.3.4 AdvSIMD load/store single structure (post-indexed)
+ *
+ *  31  30  29           23 22 21 20       16 15 13 12  11  10 9    5 4    0
+ * +---+---+---------------+-----+-----------+-----+---+------+------+------+
+ * | 0 | Q | 0 0 1 1 0 1 1 | L R |     Rm    | opc | S | size |  Rn  |  Rt  |
+ * +---+---+---------------+-----+-----------+-----+---+------+------+------+
+ *
+ * Rt: first (or only) SIMD&FP register to be transferred
+ * Rn: base address or SP
+ * Rm (post-index only): post-index register (when !31) or size dependent #imm
+ * index = encoded in Q:S:size dependent on size
+ *
+ * lane_size = encoded in R, opc
+ * transfer width = encoded in opc, S, size
+ */
 static void disas_ldst_single_struct(DisasContext *s, uint32_t insn)
 {
-    unsupported_encoding(s, insn);
+    int rt = extract32(insn, 0, 5);
+    int rn = extract32(insn, 5, 5);
+    int size = extract32(insn, 10, 2);
+    int S = extract32(insn, 12, 1);
+    int opc = extract32(insn, 13, 3);
+    int R = extract32(insn, 21, 1);
+    int is_load = extract32(insn, 22, 1);
+    int is_postidx = extract32(insn, 23, 1);
+    int is_q = extract32(insn, 30, 1);
+
+    int scale = extract32(opc, 1, 2);
+    int selem = (extract32(opc, 0, 1) << 1 | R) + 1;
+    bool replicate = false;
+    int index = is_q << 3 | S << 2 | size;
+    int ebytes, xs;
+    TCGv_i64 tcg_addr, tcg_rn;
+
+    switch (scale) {
+    case 3:
+        if (!is_load || S) {
+            unallocated_encoding(s);
+            return;
+        }
+        scale = size;
+        replicate = true;
+        break;
+    case 0:
+        break;
+    case 1:
+        if (extract32(size, 0, 1)) {
+            unallocated_encoding(s);
+            return;
+        }
+        index >>= 1;
+        break;
+    case 2:
+        if (extract32(size, 1, 1)) {
+            unallocated_encoding(s);
+            return;
+        }
+        if (!extract32(size, 0, 1)) {
+            index >>= 2;
+        } else {
+            if (S) {
+                unallocated_encoding(s);
+                return;
+            }
+            index >>= 3;
+            scale = 3;
+        }
+        break;
+    default:
+        g_assert_not_reached();
+    }
+
+    ebytes = 1 << scale;
+
+    if (rn == 31) {
+        gen_check_sp_alignment(s);
+    }
+
+    tcg_rn = cpu_reg_sp(s, rn);
+    tcg_addr = tcg_temp_new_i64();
+    tcg_gen_mov_i64(tcg_addr, tcg_rn);
+
+    for (xs = 0; xs < selem; xs++) {
+        if (replicate) {
+            /* Load and replicate to all elements */
+            uint64_t mulconst;
+            TCGv_i64 tcg_tmp = tcg_temp_new_i64();
+
+            tcg_gen_qemu_ld_i64(tcg_tmp, tcg_addr,
+                                get_mem_index(s), MO_TE + scale);
+            switch (scale) {
+            case 0:
+                mulconst = 0x0101010101010101ULL;
+                break;
+            case 1:
+                mulconst = 0x0001000100010001ULL;
+                break;
+            case 2:
+                mulconst = 0x0000000100000001ULL;
+                break;
+            case 3:
+                mulconst = 0;
+                break;
+            default:
+                g_assert_not_reached();
+            }
+            if (mulconst) {
+                tcg_gen_muli_i64(tcg_tmp, tcg_tmp, mulconst);
+            }
+            write_vec_element(s, tcg_tmp, rt, 0, MO_64);
+            if (is_q) {
+                write_vec_element(s, tcg_tmp, rt, 1, MO_64);
+            } else {
+                clear_vec_high(s, rt);
+            }
+            tcg_temp_free_i64(tcg_tmp);
+        } else {
+            /* Load/store one element per register */
+            if (is_load) {
+                do_vec_ld(s, rt, index, tcg_addr, MO_TE + scale);
+            } else {
+                do_vec_st(s, rt, index, tcg_addr, MO_TE + scale);
+            }
+        }
+        tcg_gen_addi_i64(tcg_addr, tcg_addr, ebytes);
+        rt = (rt + 1) % 32;
+    }
+
+    if (is_postidx) {
+        int rm = extract32(insn, 16, 5);
+        if (rm == 31) {
+            tcg_gen_mov_i64(tcg_rn, tcg_addr);
+        } else {
+            tcg_gen_add_i64(tcg_rn, tcg_rn, cpu_reg(s, rm));
+        }
+    }
+    tcg_temp_free_i64(tcg_addr);
 }
 
 /* C3.3 Loads and stores */

From 384b26fb06f72e822730d3b8f51fd71a5fec5eee Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Alex=20Benn=C3=A9e?= <alex.bennee@linaro.org>
Date: Fri, 31 Jan 2014 14:47:30 +0000
Subject: [PATCH 03/34] target-arm: A64: Add decode skeleton for SIMD data
 processing insns
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add decode skeleton and function placeholders for all the SIMD data
processing instructions. Due to the complexity of this part of the
table the normal extract and switch approach gets very messy very
quickly, so we use a simple data-driven pattern-and-mask approach.

Signed-off-by: Alex Bennée <alex.bennee@linaro.org>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <rth@twiddle.net>
---
 target-arm/translate-a64.c | 306 ++++++++++++++++++++++++++++++++++++-
 1 file changed, 305 insertions(+), 1 deletion(-)

diff --git a/target-arm/translate-a64.c b/target-arm/translate-a64.c
index 6e317406af..8060c9fc81 100644
--- a/target-arm/translate-a64.c
+++ b/target-arm/translate-a64.c
@@ -61,6 +61,17 @@ enum a64_shift_type {
     A64_SHIFT_TYPE_ROR = 3
 };
 
+/* Table based decoder typedefs - used when the relevant bits for decode
+ * are too awkwardly scattered across the instruction (eg SIMD).
+ */
+typedef void AArch64DecodeFn(DisasContext *s, uint32_t insn);
+
+typedef struct AArch64DecodeTable {
+    uint32_t pattern;
+    uint32_t mask;
+    AArch64DecodeFn *disas_fn;
+} AArch64DecodeTable;
+
 /* initialize TCG globals.  */
 void a64_translate_init(void)
 {
@@ -845,6 +856,31 @@ static inline void gen_check_sp_alignment(DisasContext *s)
      */
 }
 
+/*
+ * This provides a simple table based table lookup decoder. It is
+ * intended to be used when the relevant bits for decode are too
+ * awkwardly placed and switch/if based logic would be confusing and
+ * deeply nested. Since it's a linear search through the table, tables
+ * should be kept small.
+ *
+ * It returns the first handler where insn & mask == pattern, or
+ * NULL if there is no match.
+ * The table is terminated by an empty mask (i.e. 0)
+ */
+static inline AArch64DecodeFn *lookup_disas_fn(const AArch64DecodeTable *table,
+                                               uint32_t insn)
+{
+    const AArch64DecodeTable *tptr = table;
+
+    while (tptr->mask) {
+        if ((insn & tptr->mask) == tptr->pattern) {
+            return tptr->disas_fn;
+        }
+        tptr++;
+    }
+    return NULL;
+}
+
 /*
  * the instruction disassembly implemented here matches
  * the instruction encoding classifications in chapter 3 (C3)
@@ -4610,13 +4646,281 @@ static void disas_data_proc_fp(DisasContext *s, uint32_t insn)
     }
 }
 
+/* C3.6.1 EXT
+ *   31  30 29         24 23 22  21 20  16 15  14  11 10  9    5 4    0
+ * +---+---+-------------+-----+---+------+---+------+---+------+------+
+ * | 0 | Q | 1 0 1 1 1 0 | op2 | 0 |  Rm  | 0 | imm4 | 0 |  Rn  |  Rd  |
+ * +---+---+-------------+-----+---+------+---+------+---+------+------+
+ */
+static void disas_simd_ext(DisasContext *s, uint32_t insn)
+{
+    unsupported_encoding(s, insn);
+}
+
+/* C3.6.2 TBL/TBX
+ *   31  30 29         24 23 22  21 20  16 15  14 13  12  11 10 9    5 4    0
+ * +---+---+-------------+-----+---+------+---+-----+----+-----+------+------+
+ * | 0 | Q | 0 0 1 1 1 0 | op2 | 0 |  Rm  | 0 | len | op | 0 0 |  Rn  |  Rd  |
+ * +---+---+-------------+-----+---+------+---+-----+----+-----+------+------+
+ */
+static void disas_simd_tb(DisasContext *s, uint32_t insn)
+{
+    unsupported_encoding(s, insn);
+}
+
+/* C3.6.3 ZIP/UZP/TRN
+ *   31  30 29         24 23  22  21 20   16 15 14 12 11 10 9    5 4    0
+ * +---+---+-------------+------+---+------+---+------------------+------+
+ * | 0 | Q | 0 0 1 1 1 0 | size | 0 |  Rm  | 0 | opc | 1 0 |  Rn  |  Rd  |
+ * +---+---+-------------+------+---+------+---+------------------+------+
+ */
+static void disas_simd_zip_trn(DisasContext *s, uint32_t insn)
+{
+    unsupported_encoding(s, insn);
+}
+
+/* C3.6.4 AdvSIMD across lanes
+ *   31  30  29 28       24 23  22 21       17 16    12 11 10 9    5 4    0
+ * +---+---+---+-----------+------+-----------+--------+-----+------+------+
+ * | 0 | Q | U | 0 1 1 1 0 | size | 1 1 0 0 0 | opcode | 1 0 |  Rn  |  Rd  |
+ * +---+---+---+-----------+------+-----------+--------+-----+------+------+
+ */
+static void disas_simd_across_lanes(DisasContext *s, uint32_t insn)
+{
+    unsupported_encoding(s, insn);
+}
+
+/* C3.6.5 AdvSIMD copy
+ *   31  30  29  28             21 20  16 15  14  11 10  9    5 4    0
+ * +---+---+----+-----------------+------+---+------+---+------+------+
+ * | 0 | Q | op | 0 1 1 1 0 0 0 0 | imm5 | 0 | imm4 | 1 |  Rn  |  Rd  |
+ * +---+---+----+-----------------+------+---+------+---+------+------+
+ */
+static void disas_simd_copy(DisasContext *s, uint32_t insn)
+{
+    unsupported_encoding(s, insn);
+}
+
+/* C3.6.6 AdvSIMD modified immediate
+ *  31  30   29  28                 19 18 16 15   12  11  10  9     5 4    0
+ * +---+---+----+---------------------+-----+-------+----+---+-------+------+
+ * | 0 | Q | op | 0 1 1 1 1 0 0 0 0 0 | abc | cmode | o2 | 1 | defgh |  Rd  |
+ * +---+---+----+---------------------+-----+-------+----+---+-------+------+
+ */
+static void disas_simd_mod_imm(DisasContext *s, uint32_t insn)
+{
+    unsupported_encoding(s, insn);
+}
+
+/* C3.6.7 AdvSIMD scalar copy
+ *  31 30  29  28             21 20  16 15  14  11 10  9    5 4    0
+ * +-----+----+-----------------+------+---+------+---+------+------+
+ * | 0 1 | op | 1 1 1 1 0 0 0 0 | imm5 | 0 | imm4 | 1 |  Rn  |  Rd  |
+ * +-----+----+-----------------+------+---+------+---+------+------+
+ */
+static void disas_simd_scalar_copy(DisasContext *s, uint32_t insn)
+{
+    unsupported_encoding(s, insn);
+}
+
+/* C3.6.8 AdvSIMD scalar pairwise
+ *  31 30  29 28       24 23  22 21       17 16    12 11 10 9    5 4    0
+ * +-----+---+-----------+------+-----------+--------+-----+------+------+
+ * | 0 1 | U | 1 1 1 1 0 | size | 1 1 0 0 0 | opcode | 1 0 |  Rn  |  Rd  |
+ * +-----+---+-----------+------+-----------+--------+-----+------+------+
+ */
+static void disas_simd_scalar_pairwise(DisasContext *s, uint32_t insn)
+{
+    unsupported_encoding(s, insn);
+}
+
+/* C3.6.9 AdvSIMD scalar shift by immediate
+ *  31 30  29 28         23 22  19 18  16 15    11  10 9    5 4    0
+ * +-----+---+-------------+------+------+--------+---+------+------+
+ * | 0 1 | U | 1 1 1 1 1 0 | immh | immb | opcode | 1 |  Rn  |  Rd  |
+ * +-----+---+-------------+------+------+--------+---+------+------+
+ */
+static void disas_simd_scalar_shift_imm(DisasContext *s, uint32_t insn)
+{
+    unsupported_encoding(s, insn);
+}
+
+/* C3.6.10 AdvSIMD scalar three different
+ *  31 30  29 28       24 23  22  21 20  16 15    12 11 10 9    5 4    0
+ * +-----+---+-----------+------+---+------+--------+-----+------+------+
+ * | 0 1 | U | 1 1 1 1 0 | size | 1 |  Rm  | opcode | 0 0 |  Rn  |  Rd  |
+ * +-----+---+-----------+------+---+------+--------+-----+------+------+
+ */
+static void disas_simd_scalar_three_reg_diff(DisasContext *s, uint32_t insn)
+{
+    unsupported_encoding(s, insn);
+}
+
+/* C3.6.11 AdvSIMD scalar three same
+ *  31 30  29 28       24 23  22  21 20  16 15    11  10 9    5 4    0
+ * +-----+---+-----------+------+---+------+--------+---+------+------+
+ * | 0 1 | U | 1 1 1 1 0 | size | 1 |  Rm  | opcode | 1 |  Rn  |  Rd  |
+ * +-----+---+-----------+------+---+------+--------+---+------+------+
+ */
+static void disas_simd_scalar_three_reg_same(DisasContext *s, uint32_t insn)
+{
+    unsupported_encoding(s, insn);
+}
+
+/* C3.6.12 AdvSIMD scalar two reg misc
+ *  31 30  29 28       24 23  22 21       17 16    12 11 10 9    5 4    0
+ * +-----+---+-----------+------+-----------+--------+-----+------+------+
+ * | 0 1 | U | 1 1 1 1 0 | size | 1 0 0 0 0 | opcode | 1 0 |  Rn  |  Rd  |
+ * +-----+---+-----------+------+-----------+--------+-----+------+------+
+ */
+static void disas_simd_scalar_two_reg_misc(DisasContext *s, uint32_t insn)
+{
+    unsupported_encoding(s, insn);
+}
+
+/* C3.6.13 AdvSIMD scalar x indexed element
+ *  31 30  29 28       24 23  22 21  20  19  16 15 12  11  10 9    5 4    0
+ * +-----+---+-----------+------+---+---+------+-----+---+---+------+------+
+ * | 0 1 | U | 1 1 1 1 1 | size | L | M |  Rm  | opc | H | 0 |  Rn  |  Rd  |
+ * +-----+---+-----------+------+---+---+------+-----+---+---+------+------+
+ */
+static void disas_simd_scalar_indexed(DisasContext *s, uint32_t insn)
+{
+    unsupported_encoding(s, insn);
+}
+
+/* C3.6.14 AdvSIMD shift by immediate
+ *  31  30   29 28         23 22  19 18  16 15    11  10 9    5 4    0
+ * +---+---+---+-------------+------+------+--------+---+------+------+
+ * | 0 | Q | U | 0 1 1 1 1 0 | immh | immb | opcode | 1 |  Rn  |  Rd  |
+ * +---+---+---+-------------+------+------+--------+---+------+------+
+ */
+static void disas_simd_shift_imm(DisasContext *s, uint32_t insn)
+{
+    unsupported_encoding(s, insn);
+}
+
+/* C3.6.15 AdvSIMD three different
+ *   31  30  29 28       24 23  22  21 20  16 15    12 11 10 9    5 4    0
+ * +---+---+---+-----------+------+---+------+--------+-----+------+------+
+ * | 0 | Q | U | 0 1 1 1 0 | size | 1 |  Rm  | opcode | 0 0 |  Rn  |  Rd  |
+ * +---+---+---+-----------+------+---+------+--------+-----+------+------+
+ */
+static void disas_simd_three_reg_diff(DisasContext *s, uint32_t insn)
+{
+    unsupported_encoding(s, insn);
+}
+
+/* C3.6.16 AdvSIMD three same
+ *  31  30  29  28       24 23  22  21 20  16 15    11  10 9    5 4    0
+ * +---+---+---+-----------+------+---+------+--------+---+------+------+
+ * | 0 | Q | U | 0 1 1 1 0 | size | 1 |  Rm  | opcode | 1 |  Rn  |  Rd  |
+ * +---+---+---+-----------+------+---+------+--------+---+------+------+
+ */
+static void disas_simd_three_reg_same(DisasContext *s, uint32_t insn)
+{
+    unsupported_encoding(s, insn);
+}
+
+/* C3.6.17 AdvSIMD two reg misc
+ *   31  30  29 28       24 23  22 21       17 16    12 11 10 9    5 4    0
+ * +---+---+---+-----------+------+-----------+--------+-----+------+------+
+ * | 0 | Q | U | 0 1 1 1 0 | size | 1 0 0 0 0 | opcode | 1 0 |  Rn  |  Rd  |
+ * +---+---+---+-----------+------+-----------+--------+-----+------+------+
+ */
+static void disas_simd_two_reg_misc(DisasContext *s, uint32_t insn)
+{
+    unsupported_encoding(s, insn);
+}
+
+/* C3.6.18 AdvSIMD vector x indexed element
+ *   31  30  29 28       24 23  22 21  20  19  16 15 12  11  10 9    5 4    0
+ * +---+---+---+-----------+------+---+---+------+-----+---+---+------+------+
+ * | 0 | Q | U | 0 1 1 1 1 | size | L | M |  Rm  | opc | H | 0 |  Rn  |  Rd  |
+ * +---+---+---+-----------+------+---+---+------+-----+---+---+------+------+
+ */
+static void disas_simd_indexed_vector(DisasContext *s, uint32_t insn)
+{
+    unsupported_encoding(s, insn);
+}
+
+/* C3.6.19 Crypto AES
+ *  31             24 23  22 21       17 16    12 11 10 9    5 4    0
+ * +-----------------+------+-----------+--------+-----+------+------+
+ * | 0 1 0 0 1 1 1 0 | size | 1 0 1 0 0 | opcode | 1 0 |  Rn  |  Rd  |
+ * +-----------------+------+-----------+--------+-----+------+------+
+ */
+static void disas_crypto_aes(DisasContext *s, uint32_t insn)
+{
+    unsupported_encoding(s, insn);
+}
+
+/* C3.6.20 Crypto three-reg SHA
+ *  31             24 23  22  21 20  16  15 14    12 11 10 9    5 4    0
+ * +-----------------+------+---+------+---+--------+-----+------+------+
+ * | 0 1 0 1 1 1 1 0 | size | 0 |  Rm  | 0 | opcode | 0 0 |  Rn  |  Rd  |
+ * +-----------------+------+---+------+---+--------+-----+------+------+
+ */
+static void disas_crypto_three_reg_sha(DisasContext *s, uint32_t insn)
+{
+    unsupported_encoding(s, insn);
+}
+
+/* C3.6.21 Crypto two-reg SHA
+ *  31             24 23  22 21       17 16    12 11 10 9    5 4    0
+ * +-----------------+------+-----------+--------+-----+------+------+
+ * | 0 1 0 1 1 1 1 0 | size | 1 0 1 0 0 | opcode | 1 0 |  Rn  |  Rd  |
+ * +-----------------+------+-----------+--------+-----+------+------+
+ */
+static void disas_crypto_two_reg_sha(DisasContext *s, uint32_t insn)
+{
+    unsupported_encoding(s, insn);
+}
+
+/* C3.6 Data processing - SIMD, inc Crypto
+ *
+ * As the decode gets a little complex we are using a table based
+ * approach for this part of the decode.
+ */
+static const AArch64DecodeTable data_proc_simd[] = {
+    /* pattern  ,  mask     ,  fn                        */
+    { 0x0e200400, 0x9f200400, disas_simd_three_reg_same },
+    { 0x0e200000, 0x9f200c00, disas_simd_three_reg_diff },
+    { 0x0e200800, 0x9f3e0c00, disas_simd_two_reg_misc },
+    { 0x0e300800, 0x9f3e0c00, disas_simd_across_lanes },
+    { 0x0e000400, 0x9fe08400, disas_simd_copy },
+    { 0x0f000000, 0x9f000400, disas_simd_indexed_vector },
+    /* simd_mod_imm decode is a subset of simd_shift_imm, so must precede it */
+    { 0x0f000400, 0x9ff80400, disas_simd_mod_imm },
+    { 0x0f000400, 0x9f800400, disas_simd_shift_imm },
+    { 0x0e000000, 0xbf208c00, disas_simd_tb },
+    { 0x0e000800, 0xbf208c00, disas_simd_zip_trn },
+    { 0x2e000000, 0xbf208400, disas_simd_ext },
+    { 0x5e200400, 0xdf200400, disas_simd_scalar_three_reg_same },
+    { 0x5e200000, 0xdf200c00, disas_simd_scalar_three_reg_diff },
+    { 0x5e200800, 0xdf3e0c00, disas_simd_scalar_two_reg_misc },
+    { 0x5e300800, 0xdf3e0c00, disas_simd_scalar_pairwise },
+    { 0x5e000400, 0xdfe08400, disas_simd_scalar_copy },
+    { 0x5f000000, 0xdf000400, disas_simd_scalar_indexed },
+    { 0x5f000400, 0xdf800400, disas_simd_scalar_shift_imm },
+    { 0x4e280800, 0xff3e0c00, disas_crypto_aes },
+    { 0x5e000000, 0xff208c00, disas_crypto_three_reg_sha },
+    { 0x5e280800, 0xff3e0c00, disas_crypto_two_reg_sha },
+    { 0x00000000, 0x00000000, NULL }
+};
+
 static void disas_data_proc_simd(DisasContext *s, uint32_t insn)
 {
     /* Note that this is called with all non-FP cases from
      * table C3-6 so it must UNDEF for entries not specifically
      * allocated to instructions in that table.
      */
-    unsupported_encoding(s, insn);
+    AArch64DecodeFn *fn = lookup_disas_fn(&data_proc_simd[0], insn);
+    if (fn) {
+        fn(s, insn);
+    } else {
+        unallocated_encoding(s);
+    }
 }
 
 /* C3.6 Data processing - SIMD and floating point */

From 5c73747f3cc29471f9fbfe630ef15902e65f53b3 Mon Sep 17 00:00:00 2001
From: Peter Maydell <peter.maydell@linaro.org>
Date: Fri, 31 Jan 2014 14:47:30 +0000
Subject: [PATCH 04/34] target-arm: A64: Add SIMD EXT

Add support for the SIMD EXT instruction (the only one in its
group, C3.6.1).

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <rth@twiddle.net>
---
 target-arm/translate-a64.c | 79 +++++++++++++++++++++++++++++++++++++-
 1 file changed, 78 insertions(+), 1 deletion(-)

diff --git a/target-arm/translate-a64.c b/target-arm/translate-a64.c
index 8060c9fc81..75b00392bc 100644
--- a/target-arm/translate-a64.c
+++ b/target-arm/translate-a64.c
@@ -4646,6 +4646,25 @@ static void disas_data_proc_fp(DisasContext *s, uint32_t insn)
     }
 }
 
+static void do_ext64(DisasContext *s, TCGv_i64 tcg_left, TCGv_i64 tcg_right,
+                     int pos)
+{
+    /* Extract 64 bits from the middle of two concatenated 64 bit
+     * vector register slices left:right. The extracted bits start
+     * at 'pos' bits into the right (least significant) side.
+     * We return the result in tcg_right, and guarantee not to
+     * trash tcg_left.
+     */
+    TCGv_i64 tcg_tmp = tcg_temp_new_i64();
+    assert(pos > 0 && pos < 64);
+
+    tcg_gen_shri_i64(tcg_right, tcg_right, pos);
+    tcg_gen_shli_i64(tcg_tmp, tcg_left, 64 - pos);
+    tcg_gen_or_i64(tcg_right, tcg_right, tcg_tmp);
+
+    tcg_temp_free_i64(tcg_tmp);
+}
+
 /* C3.6.1 EXT
  *   31  30 29         24 23 22  21 20  16 15  14  11 10  9    5 4    0
  * +---+---+-------------+-----+---+------+---+------+---+------+------+
@@ -4654,7 +4673,65 @@ static void disas_data_proc_fp(DisasContext *s, uint32_t insn)
  */
 static void disas_simd_ext(DisasContext *s, uint32_t insn)
 {
-    unsupported_encoding(s, insn);
+    int is_q = extract32(insn, 30, 1);
+    int op2 = extract32(insn, 22, 2);
+    int imm4 = extract32(insn, 11, 4);
+    int rm = extract32(insn, 16, 5);
+    int rn = extract32(insn, 5, 5);
+    int rd = extract32(insn, 0, 5);
+    int pos = imm4 << 3;
+    TCGv_i64 tcg_resl, tcg_resh;
+
+    if (op2 != 0 || (!is_q && extract32(imm4, 3, 1))) {
+        unallocated_encoding(s);
+        return;
+    }
+
+    tcg_resh = tcg_temp_new_i64();
+    tcg_resl = tcg_temp_new_i64();
+
+    /* Vd gets bits starting at pos bits into Vm:Vn. This is
+     * either extracting 128 bits from a 128:128 concatenation, or
+     * extracting 64 bits from a 64:64 concatenation.
+     */
+    if (!is_q) {
+        read_vec_element(s, tcg_resl, rn, 0, MO_64);
+        if (pos != 0) {
+            read_vec_element(s, tcg_resh, rm, 0, MO_64);
+            do_ext64(s, tcg_resh, tcg_resl, pos);
+        }
+        tcg_gen_movi_i64(tcg_resh, 0);
+    } else {
+        TCGv_i64 tcg_hh;
+        typedef struct {
+            int reg;
+            int elt;
+        } EltPosns;
+        EltPosns eltposns[] = { {rn, 0}, {rn, 1}, {rm, 0}, {rm, 1} };
+        EltPosns *elt = eltposns;
+
+        if (pos >= 64) {
+            elt++;
+            pos -= 64;
+        }
+
+        read_vec_element(s, tcg_resl, elt->reg, elt->elt, MO_64);
+        elt++;
+        read_vec_element(s, tcg_resh, elt->reg, elt->elt, MO_64);
+        elt++;
+        if (pos != 0) {
+            do_ext64(s, tcg_resh, tcg_resl, pos);
+            tcg_hh = tcg_temp_new_i64();
+            read_vec_element(s, tcg_hh, elt->reg, elt->elt, MO_64);
+            do_ext64(s, tcg_hh, tcg_resh, pos);
+            tcg_temp_free_i64(tcg_hh);
+        }
+    }
+
+    write_vec_element(s, tcg_resl, rd, 0, MO_64);
+    tcg_temp_free_i64(tcg_resl);
+    write_vec_element(s, tcg_resh, rd, 1, MO_64);
+    tcg_temp_free_i64(tcg_resh);
 }
 
 /* C3.6.2 TBL/TBX

From 7c51048fa918f64806adf0f76166e9940d772eb1 Mon Sep 17 00:00:00 2001
From: Michael Matz <matz@suse.de>
Date: Fri, 31 Jan 2014 14:47:31 +0000
Subject: [PATCH 05/34] target-arm: A64: Add SIMD TBL/TBLX

Add support for the SIMD TBL/TBLX instructions (group C3.6.2).

Signed-off-by: Michael Matz <matz@suse.de>
[PMM: rewritten to do more of the decode in translate-a64.c,
 and to do only one 64 bit pass at a time in the helper]
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <rth@twiddle.net>
---
 target-arm/helper-a64.c    | 31 +++++++++++++++++++++
 target-arm/helper-a64.h    |  1 +
 target-arm/translate-a64.c | 55 +++++++++++++++++++++++++++++++++++++-
 3 files changed, 86 insertions(+), 1 deletion(-)

diff --git a/target-arm/helper-a64.c b/target-arm/helper-a64.c
index 4ce0d01a85..6ca958afb1 100644
--- a/target-arm/helper-a64.c
+++ b/target-arm/helper-a64.c
@@ -122,3 +122,34 @@ uint64_t HELPER(vfp_cmped_a64)(float64 x, float64 y, void *fp_status)
 {
     return float_rel_to_flags(float64_compare(x, y, fp_status));
 }
+
+uint64_t HELPER(simd_tbl)(CPUARMState *env, uint64_t result, uint64_t indices,
+                          uint32_t rn, uint32_t numregs)
+{
+    /* Helper function for SIMD TBL and TBX. We have to do the table
+     * lookup part for the 64 bits worth of indices we're passed in.
+     * result is the initial results vector (either zeroes for TBL
+     * or some guest values for TBX), rn the register number where
+     * the table starts, and numregs the number of registers in the table.
+     * We return the results of the lookups.
+     */
+    int shift;
+
+    for (shift = 0; shift < 64; shift += 8) {
+        int index = extract64(indices, shift, 8);
+        if (index < 16 * numregs) {
+            /* Convert index (a byte offset into the virtual table
+             * which is a series of 128-bit vectors concatenated)
+             * into the correct vfp.regs[] element plus a bit offset
+             * into that element, bearing in mind that the table
+             * can wrap around from V31 to V0.
+             */
+            int elt = (rn * 2 + (index >> 3)) % 64;
+            int bitidx = (index & 7) * 8;
+            uint64_t val = extract64(env->vfp.regs[elt], bitidx, 8);
+
+            result = deposit64(result, shift, 8, val);
+        }
+    }
+    return result;
+}
diff --git a/target-arm/helper-a64.h b/target-arm/helper-a64.h
index bca19f3dea..99832ee55e 100644
--- a/target-arm/helper-a64.h
+++ b/target-arm/helper-a64.h
@@ -26,3 +26,4 @@ DEF_HELPER_3(vfp_cmps_a64, i64, f32, f32, ptr)
 DEF_HELPER_3(vfp_cmpes_a64, i64, f32, f32, ptr)
 DEF_HELPER_3(vfp_cmpd_a64, i64, f64, f64, ptr)
 DEF_HELPER_3(vfp_cmped_a64, i64, f64, f64, ptr)
+DEF_HELPER_FLAGS_5(simd_tbl, TCG_CALL_NO_RWG_SE, i64, env, i64, i64, i32, i32)
diff --git a/target-arm/translate-a64.c b/target-arm/translate-a64.c
index 75b00392bc..7a6b00a938 100644
--- a/target-arm/translate-a64.c
+++ b/target-arm/translate-a64.c
@@ -4742,7 +4742,60 @@ static void disas_simd_ext(DisasContext *s, uint32_t insn)
  */
 static void disas_simd_tb(DisasContext *s, uint32_t insn)
 {
-    unsupported_encoding(s, insn);
+    int op2 = extract32(insn, 22, 2);
+    int is_q = extract32(insn, 30, 1);
+    int rm = extract32(insn, 16, 5);
+    int rn = extract32(insn, 5, 5);
+    int rd = extract32(insn, 0, 5);
+    int is_tblx = extract32(insn, 12, 1);
+    int len = extract32(insn, 13, 2);
+    TCGv_i64 tcg_resl, tcg_resh, tcg_idx;
+    TCGv_i32 tcg_regno, tcg_numregs;
+
+    if (op2 != 0) {
+        unallocated_encoding(s);
+        return;
+    }
+
+    /* This does a table lookup: for every byte element in the input
+     * we index into a table formed from up to four vector registers,
+     * and then the output is the result of the lookups. Our helper
+     * function does the lookup operation for a single 64 bit part of
+     * the input.
+     */
+    tcg_resl = tcg_temp_new_i64();
+    tcg_resh = tcg_temp_new_i64();
+
+    if (is_tblx) {
+        read_vec_element(s, tcg_resl, rd, 0, MO_64);
+    } else {
+        tcg_gen_movi_i64(tcg_resl, 0);
+    }
+    if (is_tblx && is_q) {
+        read_vec_element(s, tcg_resh, rd, 1, MO_64);
+    } else {
+        tcg_gen_movi_i64(tcg_resh, 0);
+    }
+
+    tcg_idx = tcg_temp_new_i64();
+    tcg_regno = tcg_const_i32(rn);
+    tcg_numregs = tcg_const_i32(len + 1);
+    read_vec_element(s, tcg_idx, rm, 0, MO_64);
+    gen_helper_simd_tbl(tcg_resl, cpu_env, tcg_resl, tcg_idx,
+                        tcg_regno, tcg_numregs);
+    if (is_q) {
+        read_vec_element(s, tcg_idx, rm, 1, MO_64);
+        gen_helper_simd_tbl(tcg_resh, cpu_env, tcg_resh, tcg_idx,
+                            tcg_regno, tcg_numregs);
+    }
+    tcg_temp_free_i64(tcg_idx);
+    tcg_temp_free_i32(tcg_regno);
+    tcg_temp_free_i32(tcg_numregs);
+
+    write_vec_element(s, tcg_resl, rd, 0, MO_64);
+    tcg_temp_free_i64(tcg_resl);
+    write_vec_element(s, tcg_resh, rd, 1, MO_64);
+    tcg_temp_free_i64(tcg_resh);
 }
 
 /* C3.6.3 ZIP/UZP/TRN

From 5fa5469c08f6e51eed26d6d54e0be8682723d3df Mon Sep 17 00:00:00 2001
From: Michael Matz <matz@suse.de>
Date: Fri, 31 Jan 2014 14:47:31 +0000
Subject: [PATCH 06/34] target-arm: A64: Add SIMD ZIP/UZP/TRN

Add support for the SIMD ZIP/UZIP/TRN instruction group
(C3.6.3).

Signed-off-by: Michael Matz <matz@suse.de>
[PMM: use new do_vec_get/set etc functions and generally update to new
 codebase standards; refactor to pull per-element loop outside switch]
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <rth@twiddle.net>
---
 target-arm/translate-a64.c | 76 +++++++++++++++++++++++++++++++++++++-
 1 file changed, 75 insertions(+), 1 deletion(-)

diff --git a/target-arm/translate-a64.c b/target-arm/translate-a64.c
index 7a6b00a938..59e2a85cf3 100644
--- a/target-arm/translate-a64.c
+++ b/target-arm/translate-a64.c
@@ -4806,7 +4806,81 @@ static void disas_simd_tb(DisasContext *s, uint32_t insn)
  */
 static void disas_simd_zip_trn(DisasContext *s, uint32_t insn)
 {
-    unsupported_encoding(s, insn);
+    int rd = extract32(insn, 0, 5);
+    int rn = extract32(insn, 5, 5);
+    int rm = extract32(insn, 16, 5);
+    int size = extract32(insn, 22, 2);
+    /* opc field bits [1:0] indicate ZIP/UZP/TRN;
+     * bit 2 indicates 1 vs 2 variant of the insn.
+     */
+    int opcode = extract32(insn, 12, 2);
+    bool part = extract32(insn, 14, 1);
+    bool is_q = extract32(insn, 30, 1);
+    int esize = 8 << size;
+    int i, ofs;
+    int datasize = is_q ? 128 : 64;
+    int elements = datasize / esize;
+    TCGv_i64 tcg_res, tcg_resl, tcg_resh;
+
+    if (opcode == 0 || (size == 3 && !is_q)) {
+        unallocated_encoding(s);
+        return;
+    }
+
+    tcg_resl = tcg_const_i64(0);
+    tcg_resh = tcg_const_i64(0);
+    tcg_res = tcg_temp_new_i64();
+
+    for (i = 0; i < elements; i++) {
+        switch (opcode) {
+        case 1: /* UZP1/2 */
+        {
+            int midpoint = elements / 2;
+            if (i < midpoint) {
+                read_vec_element(s, tcg_res, rn, 2 * i + part, size);
+            } else {
+                read_vec_element(s, tcg_res, rm,
+                                 2 * (i - midpoint) + part, size);
+            }
+            break;
+        }
+        case 2: /* TRN1/2 */
+            if (i & 1) {
+                read_vec_element(s, tcg_res, rm, (i & ~1) + part, size);
+            } else {
+                read_vec_element(s, tcg_res, rn, (i & ~1) + part, size);
+            }
+            break;
+        case 3: /* ZIP1/2 */
+        {
+            int base = part * elements / 2;
+            if (i & 1) {
+                read_vec_element(s, tcg_res, rm, base + (i >> 1), size);
+            } else {
+                read_vec_element(s, tcg_res, rn, base + (i >> 1), size);
+            }
+            break;
+        }
+        default:
+            g_assert_not_reached();
+        }
+
+        ofs = i * esize;
+        if (ofs < 64) {
+            tcg_gen_shli_i64(tcg_res, tcg_res, ofs);
+            tcg_gen_or_i64(tcg_resl, tcg_resl, tcg_res);
+        } else {
+            tcg_gen_shli_i64(tcg_res, tcg_res, ofs - 64);
+            tcg_gen_or_i64(tcg_resh, tcg_resh, tcg_res);
+        }
+    }
+
+    tcg_temp_free_i64(tcg_res);
+
+    write_vec_element(s, tcg_resl, rd, 0, MO_64);
+    tcg_temp_free_i64(tcg_resl);
+    write_vec_element(s, tcg_resh, rd, 1, MO_64);
+    tcg_temp_free_i64(tcg_resh);
 }
 
 /* C3.6.4 AdvSIMD across lanes

From 4a0ff1ce73a9e06ecb655019820229de74244432 Mon Sep 17 00:00:00 2001
From: Michael Matz <matz@suse.de>
Date: Fri, 31 Jan 2014 14:47:31 +0000
Subject: [PATCH 07/34] target-arm: A64: Add SIMD across-lanes instructions

Add support for the SIMD "across lanes" instruction group (C3.6.4).

Signed-off-by: Michael Matz <matz@suse.de>
[PMM: Updated to current codebase, added fp min/max ops,
 added unallocated encoding checks]
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <rth@twiddle.net>
---
 target-arm/translate-a64.c | 177 ++++++++++++++++++++++++++++++++++++-
 1 file changed, 176 insertions(+), 1 deletion(-)

diff --git a/target-arm/translate-a64.c b/target-arm/translate-a64.c
index 59e2a85cf3..de4f518bcc 100644
--- a/target-arm/translate-a64.c
+++ b/target-arm/translate-a64.c
@@ -4883,6 +4883,29 @@ static void disas_simd_zip_trn(DisasContext *s, uint32_t insn)
     tcg_temp_free_i64(tcg_resh);
 }
 
+static void do_minmaxop(DisasContext *s, TCGv_i32 tcg_elt1, TCGv_i32 tcg_elt2,
+                        int opc, bool is_min, TCGv_ptr fpst)
+{
+    /* Helper function for disas_simd_across_lanes: do a single precision
+     * min/max operation on the specified two inputs,
+     * and return the result in tcg_elt1.
+     */
+    if (opc == 0xc) {
+        if (is_min) {
+            gen_helper_vfp_minnums(tcg_elt1, tcg_elt1, tcg_elt2, fpst);
+        } else {
+            gen_helper_vfp_maxnums(tcg_elt1, tcg_elt1, tcg_elt2, fpst);
+        }
+    } else {
+        assert(opc == 0xf);
+        if (is_min) {
+            gen_helper_vfp_mins(tcg_elt1, tcg_elt1, tcg_elt2, fpst);
+        } else {
+            gen_helper_vfp_maxs(tcg_elt1, tcg_elt1, tcg_elt2, fpst);
+        }
+    }
+}
+
 /* C3.6.4 AdvSIMD across lanes
  *   31  30  29 28       24 23  22 21       17 16    12 11 10 9    5 4    0
  * +---+---+---+-----------+------+-----------+--------+-----+------+------+
@@ -4891,7 +4914,159 @@ static void disas_simd_zip_trn(DisasContext *s, uint32_t insn)
  */
 static void disas_simd_across_lanes(DisasContext *s, uint32_t insn)
 {
-    unsupported_encoding(s, insn);
+    int rd = extract32(insn, 0, 5);
+    int rn = extract32(insn, 5, 5);
+    int size = extract32(insn, 22, 2);
+    int opcode = extract32(insn, 12, 5);
+    bool is_q = extract32(insn, 30, 1);
+    bool is_u = extract32(insn, 29, 1);
+    bool is_fp = false;
+    bool is_min = false;
+    int esize;
+    int elements;
+    int i;
+    TCGv_i64 tcg_res, tcg_elt;
+
+    switch (opcode) {
+    case 0x1b: /* ADDV */
+        if (is_u) {
+            unallocated_encoding(s);
+            return;
+        }
+        /* fall through */
+    case 0x3: /* SADDLV, UADDLV */
+    case 0xa: /* SMAXV, UMAXV */
+    case 0x1a: /* SMINV, UMINV */
+        if (size == 3 || (size == 2 && !is_q)) {
+            unallocated_encoding(s);
+            return;
+        }
+        break;
+    case 0xc: /* FMAXNMV, FMINNMV */
+    case 0xf: /* FMAXV, FMINV */
+        if (!is_u || !is_q || extract32(size, 0, 1)) {
+            unallocated_encoding(s);
+            return;
+        }
+        /* Bit 1 of size field encodes min vs max, and actual size is always
+         * 32 bits: adjust the size variable so following code can rely on it
+         */
+        is_min = extract32(size, 1, 1);
+        is_fp = true;
+        size = 2;
+        break;
+    default:
+        unallocated_encoding(s);
+        return;
+    }
+
+    esize = 8 << size;
+    elements = (is_q ? 128 : 64) / esize;
+
+    tcg_res = tcg_temp_new_i64();
+    tcg_elt = tcg_temp_new_i64();
+
+    /* These instructions operate across all lanes of a vector
+     * to produce a single result. We can guarantee that a 64
+     * bit intermediate is sufficient:
+     *  + for [US]ADDLV the maximum element size is 32 bits, and
+     *    the result type is 64 bits
+     *  + for FMAX*V, FMIN*V, ADDV the intermediate type is the
+     *    same as the element size, which is 32 bits at most
+     * For the integer operations we can choose to work at 64
+     * or 32 bits and truncate at the end; for simplicity
+     * we use 64 bits always. The floating point
+     * ops do require 32 bit intermediates, though.
+     */
+    if (!is_fp) {
+        read_vec_element(s, tcg_res, rn, 0, size | (is_u ? 0 : MO_SIGN));
+
+        for (i = 1; i < elements; i++) {
+            read_vec_element(s, tcg_elt, rn, i, size | (is_u ? 0 : MO_SIGN));
+
+            switch (opcode) {
+            case 0x03: /* SADDLV / UADDLV */
+            case 0x1b: /* ADDV */
+                tcg_gen_add_i64(tcg_res, tcg_res, tcg_elt);
+                break;
+            case 0x0a: /* SMAXV / UMAXV */
+                tcg_gen_movcond_i64(is_u ? TCG_COND_GEU : TCG_COND_GE,
+                                    tcg_res,
+                                    tcg_res, tcg_elt, tcg_res, tcg_elt);
+                break;
+            case 0x1a: /* SMINV / UMINV */
+                tcg_gen_movcond_i64(is_u ? TCG_COND_LEU : TCG_COND_LE,
+                                    tcg_res,
+                                    tcg_res, tcg_elt, tcg_res, tcg_elt);
+                break;
+                break;
+            default:
+                g_assert_not_reached();
+            }
+
+        }
+    } else {
+        /* Floating point ops which work on 32 bit (single) intermediates.
+         * Note that correct NaN propagation requires that we do these
+         * operations in exactly the order specified by the pseudocode.
+         */
+        TCGv_i32 tcg_elt1 = tcg_temp_new_i32();
+        TCGv_i32 tcg_elt2 = tcg_temp_new_i32();
+        TCGv_i32 tcg_elt3 = tcg_temp_new_i32();
+        TCGv_ptr fpst = get_fpstatus_ptr();
+
+        assert(esize == 32);
+        assert(elements == 4);
+
+        read_vec_element(s, tcg_elt, rn, 0, MO_32);
+        tcg_gen_trunc_i64_i32(tcg_elt1, tcg_elt);
+        read_vec_element(s, tcg_elt, rn, 1, MO_32);
+        tcg_gen_trunc_i64_i32(tcg_elt2, tcg_elt);
+
+        do_minmaxop(s, tcg_elt1, tcg_elt2, opcode, is_min, fpst);
+
+        read_vec_element(s, tcg_elt, rn, 2, MO_32);
+        tcg_gen_trunc_i64_i32(tcg_elt2, tcg_elt);
+        read_vec_element(s, tcg_elt, rn, 3, MO_32);
+        tcg_gen_trunc_i64_i32(tcg_elt3, tcg_elt);
+
+        do_minmaxop(s, tcg_elt2, tcg_elt3, opcode, is_min, fpst);
+
+        do_minmaxop(s, tcg_elt1, tcg_elt2, opcode, is_min, fpst);
+
+        tcg_gen_extu_i32_i64(tcg_res, tcg_elt1);
+        tcg_temp_free_i32(tcg_elt1);
+        tcg_temp_free_i32(tcg_elt2);
+        tcg_temp_free_i32(tcg_elt3);
+        tcg_temp_free_ptr(fpst);
+    }
+
+    tcg_temp_free_i64(tcg_elt);
+
+    /* Now truncate the result to the width required for the final output */
+    if (opcode == 0x03) {
+        /* SADDLV, UADDLV: result is 2*esize */
+        size++;
+    }
+
+    switch (size) {
+    case 0:
+        tcg_gen_ext8u_i64(tcg_res, tcg_res);
+        break;
+    case 1:
+        tcg_gen_ext16u_i64(tcg_res, tcg_res);
+        break;
+    case 2:
+        tcg_gen_ext32u_i64(tcg_res, tcg_res);
+        break;
+    case 3:
+        break;
+    default:
+        g_assert_not_reached();
+    }
+
+    write_fp_dreg(s, rd, tcg_res);
+    tcg_temp_free_i64(tcg_res);
 }
 
 /* C3.6.5 AdvSIMD copy

From 67bb93890d7b435f294f1e47ee7adc5662cc0842 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Alex=20Benn=C3=A9e?= <alex.bennee@linaro.org>
Date: Fri, 31 Jan 2014 14:47:31 +0000
Subject: [PATCH 08/34] target-arm: A64: Add SIMD copy operations
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This adds support for the all the AdvSIMD vector copy operations
(ARM ARM 3.6.5).

Signed-off-by: Alex Bennée <alex.bennee@linaro.org>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <rth@twiddle.net>
---
 target-arm/translate-a64.c | 210 ++++++++++++++++++++++++++++++++++++-
 1 file changed, 209 insertions(+), 1 deletion(-)

diff --git a/target-arm/translate-a64.c b/target-arm/translate-a64.c
index de4f518bcc..6521f73c26 100644
--- a/target-arm/translate-a64.c
+++ b/target-arm/translate-a64.c
@@ -5069,6 +5069,173 @@ static void disas_simd_across_lanes(DisasContext *s, uint32_t insn)
     tcg_temp_free_i64(tcg_res);
 }
 
+/* C6.3.31 DUP (Element, Vector)
+ *
+ *  31  30   29              21 20    16 15        10  9    5 4    0
+ * +---+---+-------------------+--------+-------------+------+------+
+ * | 0 | Q | 0 0 1 1 1 0 0 0 0 |  imm5  | 0 0 0 0 0 1 |  Rn  |  Rd  |
+ * +---+---+-------------------+--------+-------------+------+------+
+ *
+ * size: encoded in imm5 (see ARM ARM LowestSetBit())
+ */
+static void handle_simd_dupe(DisasContext *s, int is_q, int rd, int rn,
+                             int imm5)
+{
+    int size = ctz32(imm5);
+    int esize = 8 << size;
+    int elements = (is_q ? 128 : 64) / esize;
+    int index, i;
+    TCGv_i64 tmp;
+
+    if (size > 3 || (size == 3 && !is_q)) {
+        unallocated_encoding(s);
+        return;
+    }
+
+    index = imm5 >> (size + 1);
+
+    tmp = tcg_temp_new_i64();
+    read_vec_element(s, tmp, rn, index, size);
+
+    for (i = 0; i < elements; i++) {
+        write_vec_element(s, tmp, rd, i, size);
+    }
+
+    if (!is_q) {
+        clear_vec_high(s, rd);
+    }
+
+    tcg_temp_free_i64(tmp);
+}
+
+/* C6.3.32 DUP (General)
+ *
+ *  31  30   29              21 20    16 15        10  9    5 4    0
+ * +---+---+-------------------+--------+-------------+------+------+
+ * | 0 | Q | 0 0 1 1 1 0 0 0 0 |  imm5  | 0 0 0 0 1 1 |  Rn  |  Rd  |
+ * +---+---+-------------------+--------+-------------+------+------+
+ *
+ * size: encoded in imm5 (see ARM ARM LowestSetBit())
+ */
+static void handle_simd_dupg(DisasContext *s, int is_q, int rd, int rn,
+                             int imm5)
+{
+    int size = ctz32(imm5);
+    int esize = 8 << size;
+    int elements = (is_q ? 128 : 64)/esize;
+    int i = 0;
+
+    if (size > 3 || ((size == 3) && !is_q)) {
+        unallocated_encoding(s);
+        return;
+    }
+    for (i = 0; i < elements; i++) {
+        write_vec_element(s, cpu_reg(s, rn), rd, i, size);
+    }
+    if (!is_q) {
+        clear_vec_high(s, rd);
+    }
+}
+
+/* C6.3.150 INS (Element)
+ *
+ *  31                   21 20    16 15  14    11  10 9    5 4    0
+ * +-----------------------+--------+------------+---+------+------+
+ * | 0 1 1 0 1 1 1 0 0 0 0 |  imm5  | 0 |  imm4  | 1 |  Rn  |  Rd  |
+ * +-----------------------+--------+------------+---+------+------+
+ *
+ * size: encoded in imm5 (see ARM ARM LowestSetBit())
+ * index: encoded in imm5<4:size+1>
+ */
+static void handle_simd_inse(DisasContext *s, int rd, int rn,
+                             int imm4, int imm5)
+{
+    int size = ctz32(imm5);
+    int src_index, dst_index;
+    TCGv_i64 tmp;
+
+    if (size > 3) {
+        unallocated_encoding(s);
+        return;
+    }
+    dst_index = extract32(imm5, 1+size, 5);
+    src_index = extract32(imm4, size, 4);
+
+    tmp = tcg_temp_new_i64();
+
+    read_vec_element(s, tmp, rn, src_index, size);
+    write_vec_element(s, tmp, rd, dst_index, size);
+
+    tcg_temp_free_i64(tmp);
+}
+
+
+/* C6.3.151 INS (General)
+ *
+ *  31                   21 20    16 15        10  9    5 4    0
+ * +-----------------------+--------+-------------+------+------+
+ * | 0 1 0 0 1 1 1 0 0 0 0 |  imm5  | 0 0 0 1 1 1 |  Rn  |  Rd  |
+ * +-----------------------+--------+-------------+------+------+
+ *
+ * size: encoded in imm5 (see ARM ARM LowestSetBit())
+ * index: encoded in imm5<4:size+1>
+ */
+static void handle_simd_insg(DisasContext *s, int rd, int rn, int imm5)
+{
+    int size = ctz32(imm5);
+    int idx;
+
+    if (size > 3) {
+        unallocated_encoding(s);
+        return;
+    }
+
+    idx = extract32(imm5, 1 + size, 4 - size);
+    write_vec_element(s, cpu_reg(s, rn), rd, idx, size);
+}
+
+/*
+ * C6.3.321 UMOV (General)
+ * C6.3.237 SMOV (General)
+ *
+ *  31  30   29              21 20    16 15    12   10 9    5 4    0
+ * +---+---+-------------------+--------+-------------+------+------+
+ * | 0 | Q | 0 0 1 1 1 0 0 0 0 |  imm5  | 0 0 1 U 1 1 |  Rn  |  Rd  |
+ * +---+---+-------------------+--------+-------------+------+------+
+ *
+ * U: unsigned when set
+ * size: encoded in imm5 (see ARM ARM LowestSetBit())
+ */
+static void handle_simd_umov_smov(DisasContext *s, int is_q, int is_signed,
+                                  int rn, int rd, int imm5)
+{
+    int size = ctz32(imm5);
+    int element;
+    TCGv_i64 tcg_rd;
+
+    /* Check for UnallocatedEncodings */
+    if (is_signed) {
+        if (size > 2 || (size == 2 && !is_q)) {
+            unallocated_encoding(s);
+            return;
+        }
+    } else {
+        if (size > 3
+            || (size < 3 && is_q)
+            || (size == 3 && !is_q)) {
+            unallocated_encoding(s);
+            return;
+        }
+    }
+    element = extract32(imm5, 1+size, 4);
+
+    tcg_rd = cpu_reg(s, rd);
+    read_vec_element(s, tcg_rd, rn, element, size | (is_signed ? MO_SIGN : 0));
+    if (is_signed && !is_q) {
+        tcg_gen_ext32u_i64(tcg_rd, tcg_rd);
+    }
+}
+
 /* C3.6.5 AdvSIMD copy
  *   31  30  29  28             21 20  16 15  14  11 10  9    5 4    0
  * +---+---+----+-----------------+------+---+------+---+------+------+
@@ -5077,7 +5244,48 @@ static void disas_simd_across_lanes(DisasContext *s, uint32_t insn)
  */
 static void disas_simd_copy(DisasContext *s, uint32_t insn)
 {
-    unsupported_encoding(s, insn);
+    int rd = extract32(insn, 0, 5);
+    int rn = extract32(insn, 5, 5);
+    int imm4 = extract32(insn, 11, 4);
+    int op = extract32(insn, 29, 1);
+    int is_q = extract32(insn, 30, 1);
+    int imm5 = extract32(insn, 16, 5);
+
+    if (op) {
+        if (is_q) {
+            /* INS (element) */
+            handle_simd_inse(s, rd, rn, imm4, imm5);
+        } else {
+            unallocated_encoding(s);
+        }
+    } else {
+        switch (imm4) {
+        case 0:
+            /* DUP (element - vector) */
+            handle_simd_dupe(s, is_q, rd, rn, imm5);
+            break;
+        case 1:
+            /* DUP (general) */
+            handle_simd_dupg(s, is_q, rd, rn, imm5);
+            break;
+        case 3:
+            if (is_q) {
+                /* INS (general) */
+                handle_simd_insg(s, rd, rn, imm5);
+            } else {
+                unallocated_encoding(s);
+            }
+            break;
+        case 5:
+        case 7:
+            /* UMOV/SMOV (is_q indicates 32/64; imm4 indicates signedness) */
+            handle_simd_umov_smov(s, is_q, (imm4 == 5), rn, rd, imm5);
+            break;
+        default:
+            unallocated_encoding(s);
+            break;
+        }
+    }
 }
 
 /* C3.6.6 AdvSIMD modified immediate

From f3f8c4f4d2fc7dda192393f998e63c7a83fb7554 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Alex=20Benn=C3=A9e?= <alex.bennee@linaro.org>
Date: Fri, 31 Jan 2014 14:47:32 +0000
Subject: [PATCH 09/34] target-arm: A64: Add SIMD modified immediate group
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This patch adds support for the AdvSIMD modified immediate group
(C3.6.6) with all its suboperations (movi, orr, fmov, mvni, bic).

Signed-off-by: Alexander Graf <agraf@suse.de>
[AJB: new decode struct, minor bug fixes, optimisation]
Signed-off-by: Alex Bennée <alex.bennee@linaro.org>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <rth@twiddle.net>
---
 target-arm/translate-a64.c | 120 ++++++++++++++++++++++++++++++++++++-
 1 file changed, 119 insertions(+), 1 deletion(-)

diff --git a/target-arm/translate-a64.c b/target-arm/translate-a64.c
index 6521f73c26..69c75c0000 100644
--- a/target-arm/translate-a64.c
+++ b/target-arm/translate-a64.c
@@ -5293,10 +5293,128 @@ static void disas_simd_copy(DisasContext *s, uint32_t insn)
  * +---+---+----+---------------------+-----+-------+----+---+-------+------+
  * | 0 | Q | op | 0 1 1 1 1 0 0 0 0 0 | abc | cmode | o2 | 1 | defgh |  Rd  |
  * +---+---+----+---------------------+-----+-------+----+---+-------+------+
+ *
+ * There are a number of operations that can be carried out here:
+ *   MOVI - move (shifted) imm into register
+ *   MVNI - move inverted (shifted) imm into register
+ *   ORR  - bitwise OR of (shifted) imm with register
+ *   BIC  - bitwise clear of (shifted) imm with register
  */
 static void disas_simd_mod_imm(DisasContext *s, uint32_t insn)
 {
-    unsupported_encoding(s, insn);
+    int rd = extract32(insn, 0, 5);
+    int cmode = extract32(insn, 12, 4);
+    int cmode_3_1 = extract32(cmode, 1, 3);
+    int cmode_0 = extract32(cmode, 0, 1);
+    int o2 = extract32(insn, 11, 1);
+    uint64_t abcdefgh = extract32(insn, 5, 5) | (extract32(insn, 16, 3) << 5);
+    bool is_neg = extract32(insn, 29, 1);
+    bool is_q = extract32(insn, 30, 1);
+    uint64_t imm = 0;
+    TCGv_i64 tcg_rd, tcg_imm;
+    int i;
+
+    if (o2 != 0 || ((cmode == 0xf) && is_neg && !is_q)) {
+        unallocated_encoding(s);
+        return;
+    }
+
+    /* See AdvSIMDExpandImm() in ARM ARM */
+    switch (cmode_3_1) {
+    case 0: /* Replicate(Zeros(24):imm8, 2) */
+    case 1: /* Replicate(Zeros(16):imm8:Zeros(8), 2) */
+    case 2: /* Replicate(Zeros(8):imm8:Zeros(16), 2) */
+    case 3: /* Replicate(imm8:Zeros(24), 2) */
+    {
+        int shift = cmode_3_1 * 8;
+        imm = bitfield_replicate(abcdefgh << shift, 32);
+        break;
+    }
+    case 4: /* Replicate(Zeros(8):imm8, 4) */
+    case 5: /* Replicate(imm8:Zeros(8), 4) */
+    {
+        int shift = (cmode_3_1 & 0x1) * 8;
+        imm = bitfield_replicate(abcdefgh << shift, 16);
+        break;
+    }
+    case 6:
+        if (cmode_0) {
+            /* Replicate(Zeros(8):imm8:Ones(16), 2) */
+            imm = (abcdefgh << 16) | 0xffff;
+        } else {
+            /* Replicate(Zeros(16):imm8:Ones(8), 2) */
+            imm = (abcdefgh << 8) | 0xff;
+        }
+        imm = bitfield_replicate(imm, 32);
+        break;
+    case 7:
+        if (!cmode_0 && !is_neg) {
+            imm = bitfield_replicate(abcdefgh, 8);
+        } else if (!cmode_0 && is_neg) {
+            int i;
+            imm = 0;
+            for (i = 0; i < 8; i++) {
+                if ((abcdefgh) & (1 << i)) {
+                    imm |= 0xffULL << (i * 8);
+                }
+            }
+        } else if (cmode_0) {
+            if (is_neg) {
+                imm = (abcdefgh & 0x3f) << 48;
+                if (abcdefgh & 0x80) {
+                    imm |= 0x8000000000000000ULL;
+                }
+                if (abcdefgh & 0x40) {
+                    imm |= 0x3fc0000000000000ULL;
+                } else {
+                    imm |= 0x4000000000000000ULL;
+                }
+            } else {
+                imm = (abcdefgh & 0x3f) << 19;
+                if (abcdefgh & 0x80) {
+                    imm |= 0x80000000;
+                }
+                if (abcdefgh & 0x40) {
+                    imm |= 0x3e000000;
+                } else {
+                    imm |= 0x40000000;
+                }
+                imm |= (imm << 32);
+            }
+        }
+        break;
+    }
+
+    if (cmode_3_1 != 7 && is_neg) {
+        imm = ~imm;
+    }
+
+    tcg_imm = tcg_const_i64(imm);
+    tcg_rd = new_tmp_a64(s);
+
+    for (i = 0; i < 2; i++) {
+        int foffs = i ? fp_reg_hi_offset(rd) : fp_reg_offset(rd, MO_64);
+
+        if (i == 1 && !is_q) {
+            /* non-quad ops clear high half of vector */
+            tcg_gen_movi_i64(tcg_rd, 0);
+        } else if ((cmode & 0x9) == 0x1 || (cmode & 0xd) == 0x9) {
+            tcg_gen_ld_i64(tcg_rd, cpu_env, foffs);
+            if (is_neg) {
+                /* AND (BIC) */
+                tcg_gen_and_i64(tcg_rd, tcg_rd, tcg_imm);
+            } else {
+                /* ORR */
+                tcg_gen_or_i64(tcg_rd, tcg_rd, tcg_imm);
+            }
+        } else {
+            /* MOVI */
+            tcg_gen_mov_i64(tcg_rd, tcg_imm);
+        }
+        tcg_gen_st_i64(tcg_rd, cpu_env, foffs);
+    }
+
+    tcg_temp_free_i64(tcg_imm);
 }
 
 /* C3.6.7 AdvSIMD scalar copy

From 360a6f2dbde39211107620a3d38b8cc8cc5281ee Mon Sep 17 00:00:00 2001
From: Peter Maydell <peter.maydell@linaro.org>
Date: Fri, 31 Jan 2014 14:47:32 +0000
Subject: [PATCH 10/34] target-arm: A64: Add SIMD scalar copy instructions

Add support for the SIMD scalar copy instruction group (C3.6.7),
which consists of the single instruction DUP (element, scalar).

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <rth@twiddle.net>
---
 target-arm/translate-a64.c | 43 +++++++++++++++++++++++++++++++++++++-
 1 file changed, 42 insertions(+), 1 deletion(-)

diff --git a/target-arm/translate-a64.c b/target-arm/translate-a64.c
index 69c75c0000..7cfb55bdc6 100644
--- a/target-arm/translate-a64.c
+++ b/target-arm/translate-a64.c
@@ -5108,6 +5108,35 @@ static void handle_simd_dupe(DisasContext *s, int is_q, int rd, int rn,
     tcg_temp_free_i64(tmp);
 }
 
+/* C6.3.31 DUP (element, scalar)
+ *  31                   21 20    16 15        10  9    5 4    0
+ * +-----------------------+--------+-------------+------+------+
+ * | 0 1 0 1 1 1 1 0 0 0 0 |  imm5  | 0 0 0 0 0 1 |  Rn  |  Rd  |
+ * +-----------------------+--------+-------------+------+------+
+ */
+static void handle_simd_dupes(DisasContext *s, int rd, int rn,
+                              int imm5)
+{
+    int size = ctz32(imm5);
+    int index;
+    TCGv_i64 tmp;
+
+    if (size > 3) {
+        unallocated_encoding(s);
+        return;
+    }
+
+    index = imm5 >> (size + 1);
+
+    /* This instruction just extracts the specified element and
+     * zero-extends it into the bottom of the destination register.
+     */
+    tmp = tcg_temp_new_i64();
+    read_vec_element(s, tmp, rn, index, size);
+    write_fp_dreg(s, rd, tmp);
+    tcg_temp_free_i64(tmp);
+}
+
 /* C6.3.32 DUP (General)
  *
  *  31  30   29              21 20    16 15        10  9    5 4    0
@@ -5425,7 +5454,19 @@ static void disas_simd_mod_imm(DisasContext *s, uint32_t insn)
  */
 static void disas_simd_scalar_copy(DisasContext *s, uint32_t insn)
 {
-    unsupported_encoding(s, insn);
+    int rd = extract32(insn, 0, 5);
+    int rn = extract32(insn, 5, 5);
+    int imm4 = extract32(insn, 11, 4);
+    int imm5 = extract32(insn, 16, 5);
+    int op = extract32(insn, 29, 1);
+
+    if (op != 0 || imm4 != 0) {
+        unallocated_encoding(s);
+        return;
+    }
+
+    /* DUP (element, scalar) */
+    handle_simd_dupes(s, rd, rn, imm5);
 }
 
 /* C3.6.8 AdvSIMD scalar pairwise

From 83bfffec72ad447dfc80a4eab320403175ffe4e3 Mon Sep 17 00:00:00 2001
From: Peter Maydell <peter.maydell@linaro.org>
Date: Fri, 31 Jan 2014 14:47:32 +0000
Subject: [PATCH 11/34] hw/arm/boot: Don't set up ATAGS for autogenerated dtb
 booting

The code which decides whether to set up the ATAGS data structure on
reset was using the wrong conditional, which meant we were creating
an ATAGS structure when doing a device-tree boot if the dtb was
autogenerated by the board. This is harmless, but unnecessary, so
bring it in to line with user-provided-dtb boots.

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Peter Crosthwaite <peter.crosthwaite@xilinx.com>
Message-id: 1388326833-656-1-git-send-email-peter.maydell@linaro.org
---
 hw/arm/boot.c | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/hw/arm/boot.c b/hw/arm/boot.c
index 1c1b0e5258..4036262f50 100644
--- a/hw/arm/boot.c
+++ b/hw/arm/boot.c
@@ -173,6 +173,11 @@ static void default_reset_secondary(ARMCPU *cpu,
     env->regs[15] = info->smp_loader_start;
 }
 
+static inline bool have_dtb(const struct arm_boot_info *info)
+{
+    return info->dtb_filename || info->get_dtb;
+}
+
 #define WRITE_WORD(p, value) do { \
     stl_phys_notdirty(p, value);  \
     p += 4;                       \
@@ -421,7 +426,7 @@ static void do_cpu_reset(void *opaque)
                     env->regs[15] = info->loader_start;
                 }
 
-                if (!info->dtb_filename) {
+                if (!have_dtb(info)) {
                     if (old_param) {
                         set_kernel_args_old(info);
                     } else {
@@ -542,7 +547,7 @@ void arm_load_kernel(ARMCPU *cpu, struct arm_boot_info *info)
         /* for device tree boot, we pass the DTB directly in r2. Otherwise
          * we point to the kernel args.
          */
-        if (info->dtb_filename || info->get_dtb) {
+        if (have_dtb(info)) {
             /* Place the DTB after the initrd in memory. Note that some
              * kernels will trash anything in the 4K page the initrd
              * ends in, so make sure the DTB isn't caught up in that.

From 51a9b04bd3b01e11a1db4fc2ac2f1d324fbd30aa Mon Sep 17 00:00:00 2001
From: Alistair Francis <alistair.francis@xilinx.com>
Date: Fri, 31 Jan 2014 14:47:32 +0000
Subject: [PATCH 12/34] ARM: Convert MIDR to a property

Convert the MIDR register to a property. This allows boards to later set
a custom MIDR value. This has been done in such a way to maintain
compatibility with all existing CPUs and boards

Signed-off-by: Alistair Francis <alistair.francis@xilinx.com>
Reviewed-by: Peter Crosthwaite <peter.crosthwaite@xilinx.com>
Message-id: 878613f2f12d4162f12629522fd99de8df904856.1390176489.git.alistair.francis@xilinx.com
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target-arm/cpu.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/target-arm/cpu.c b/target-arm/cpu.c
index 52efd5d66f..45ad7f0260 100644
--- a/target-arm/cpu.c
+++ b/target-arm/cpu.c
@@ -982,6 +982,7 @@ static const ARMCPUInfo arm_cpus[] = {
 
 static Property arm_cpu_properties[] = {
     DEFINE_PROP_BOOL("start-powered-off", ARMCPU, start_powered_off, false),
+    DEFINE_PROP_UINT32("midr", ARMCPU, midr, 0),
     DEFINE_PROP_END_OF_LIST()
 };
 

From b48adc0d301464d627d6d0f83dee911a2138187f Mon Sep 17 00:00:00 2001
From: Alistair Francis <alistair.francis@xilinx.com>
Date: Fri, 31 Jan 2014 14:47:33 +0000
Subject: [PATCH 13/34] ZYNQ: Implement board MIDR control for Zynq

This patch uses the fact that the midr variable is now a property
This patch sets the midr variable to the boards custom midr

Signed-off-by: Alistair Francis <alistair.francis@xilinx.com>
Message-id: a3754b10d150af72e4688a993e484fa2b9b8fa21.1390176489.git.alistair.francis@xilinx.com
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 hw/arm/xilinx_zynq.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/hw/arm/xilinx_zynq.c b/hw/arm/xilinx_zynq.c
index 98e0958a77..9ee21e726a 100644
--- a/hw/arm/xilinx_zynq.c
+++ b/hw/arm/xilinx_zynq.c
@@ -37,6 +37,7 @@
 #define IRQ_OFFSET 32 /* pic interrupts start from index 32 */
 
 #define MPCORE_PERIPHBASE 0xF8F00000
+#define ZYNQ_BOARD_MIDR 0x413FC090
 
 static const int dma_irqs[8] = {
     46, 47, 48, 49, 72, 73, 74, 75
@@ -125,6 +126,12 @@ static void zynq_init(QEMUMachineInitArgs *args)
 
     cpu = ARM_CPU(object_new(object_class_get_name(cpu_oc)));
 
+    object_property_set_int(OBJECT(cpu), ZYNQ_BOARD_MIDR, "midr", &err);
+    if (err) {
+        error_report("%s", error_get_pretty(err));
+        exit(1);
+    }
+
     object_property_set_int(OBJECT(cpu), MPCORE_PERIPHBASE, "reset-cbar", &err);
     if (err) {
         error_report("%s", error_get_pretty(err));

From 2cdaca90ddf3291f308a10623c1a802ef760bac1 Mon Sep 17 00:00:00 2001
From: Paolo Bonzini <pbonzini@redhat.com>
Date: Fri, 31 Jan 2014 14:47:33 +0000
Subject: [PATCH 14/34] display: avoid multi-statement macro

For blizzard, pl110 and tc6393xb this is harmless, but for pxa2xx
Coverity noticed that it is used inside an "if" statement.
Fix it because it's the file with the highest number of defects
in the whole QEMU tree!  Use "do...while (0)", or just remove the
semicolon if there's a single statement in the macro.

Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 hw/display/blizzard_template.h | 40 +++++++++++++++++++++-------------
 hw/display/pl110_template.h    | 12 ++++++----
 hw/display/pxa2xx_template.h   | 22 ++++++++++++++-----
 hw/display/tc6393xb_template.h | 14 +++++++-----
 4 files changed, 59 insertions(+), 29 deletions(-)

diff --git a/hw/display/blizzard_template.h b/hw/display/blizzard_template.h
index a8a8899478..b7ef27c808 100644
--- a/hw/display/blizzard_template.h
+++ b/hw/display/blizzard_template.h
@@ -18,25 +18,35 @@
  * with this program; if not, see <http://www.gnu.org/licenses/>.
  */
 
-#define SKIP_PIXEL(to)		to += deststep
+#define SKIP_PIXEL(to)         (to += deststep)
 #if DEPTH == 8
-# define PIXEL_TYPE		uint8_t
-# define COPY_PIXEL(to, from)	*to = from; SKIP_PIXEL(to)
-# define COPY_PIXEL1(to, from)	*to ++ = from
+# define PIXEL_TYPE            uint8_t
+# define COPY_PIXEL(to, from)  do { *to = from; SKIP_PIXEL(to); } while (0)
+# define COPY_PIXEL1(to, from) (*to++ = from)
 #elif DEPTH == 15 || DEPTH == 16
-# define PIXEL_TYPE		uint16_t
-# define COPY_PIXEL(to, from)	*to = from; SKIP_PIXEL(to)
-# define COPY_PIXEL1(to, from)	*to ++ = from
+# define PIXEL_TYPE            uint16_t
+# define COPY_PIXEL(to, from)  do { *to = from; SKIP_PIXEL(to); } while (0)
+# define COPY_PIXEL1(to, from) (*to++ = from)
 #elif DEPTH == 24
-# define PIXEL_TYPE		uint8_t
-# define COPY_PIXEL(to, from)	\
-    to[0] = from; to[1] = (from) >> 8; to[2] = (from) >> 16; SKIP_PIXEL(to)
-# define COPY_PIXEL1(to, from)	\
-    *to ++ = from; *to ++ = (from) >> 8; *to ++ = (from) >> 16
+# define PIXEL_TYPE            uint8_t
+# define COPY_PIXEL(to, from) \
+    do {                      \
+        to[0] = from;         \
+        to[1] = (from) >> 8;  \
+        to[2] = (from) >> 16; \
+        SKIP_PIXEL(to);       \
+    } while (0)
+
+# define COPY_PIXEL1(to, from) \
+    do {                       \
+        *to++ = from;          \
+        *to++ = (from) >> 8;   \
+        *to++ = (from) >> 16;  \
+    } while (0)
 #elif DEPTH == 32
-# define PIXEL_TYPE		uint32_t
-# define COPY_PIXEL(to, from)	*to = from; SKIP_PIXEL(to)
-# define COPY_PIXEL1(to, from)	*to ++ = from
+# define PIXEL_TYPE            uint32_t
+# define COPY_PIXEL(to, from)  do { *to = from; SKIP_PIXEL(to); } while (0)
+# define COPY_PIXEL1(to, from) (*to++ = from)
 #else
 # error unknown bit depth
 #endif
diff --git a/hw/display/pl110_template.h b/hw/display/pl110_template.h
index e738e4a241..36ba791c6f 100644
--- a/hw/display/pl110_template.h
+++ b/hw/display/pl110_template.h
@@ -14,12 +14,16 @@
 #if BITS == 8
 #define COPY_PIXEL(to, from) *(to++) = from
 #elif BITS == 15 || BITS == 16
-#define COPY_PIXEL(to, from) *(uint16_t *)to = from; to += 2;
+#define COPY_PIXEL(to, from) do { *(uint16_t *)to = from; to += 2; } while (0)
 #elif BITS == 24
-#define COPY_PIXEL(to, from) \
-  *(to++) = from; *(to++) = (from) >> 8; *(to++) = (from) >> 16
+#define COPY_PIXEL(to, from)    \
+    do {                        \
+        *(to++) = from;         \
+        *(to++) = (from) >> 8;  \
+        *(to++) = (from) >> 16; \
+    } while (0)
 #elif BITS == 32
-#define COPY_PIXEL(to, from) *(uint32_t *)to = from; to += 4;
+#define COPY_PIXEL(to, from) do { *(uint32_t *)to = from; to += 4; } while (0)
 #else
 #error unknown bit depth
 #endif
diff --git a/hw/display/pxa2xx_template.h b/hw/display/pxa2xx_template.h
index 1cbe36cb80..c64eebc4b6 100644
--- a/hw/display/pxa2xx_template.h
+++ b/hw/display/pxa2xx_template.h
@@ -11,14 +11,26 @@
 
 # define SKIP_PIXEL(to)		to += deststep
 #if BITS == 8
-# define COPY_PIXEL(to, from)	*to = from; SKIP_PIXEL(to)
+# define COPY_PIXEL(to, from)  do { *to = from; SKIP_PIXEL(to); } while (0)
 #elif BITS == 15 || BITS == 16
-# define COPY_PIXEL(to, from)	*(uint16_t *) to = from; SKIP_PIXEL(to)
+# define COPY_PIXEL(to, from)    \
+    do {                         \
+        *(uint16_t *) to = from; \
+        SKIP_PIXEL(to);          \
+    } while (0)
 #elif BITS == 24
-# define COPY_PIXEL(to, from)	\
-	*(uint16_t *) to = from; *(to + 2) = (from) >> 16; SKIP_PIXEL(to)
+# define COPY_PIXEL(to, from)     \
+    do {                          \
+        *(uint16_t *) to = from;  \
+        *(to + 2) = (from) >> 16; \
+        SKIP_PIXEL(to);           \
+    } while (0)
 #elif BITS == 32
-# define COPY_PIXEL(to, from)	*(uint32_t *) to = from; SKIP_PIXEL(to)
+# define COPY_PIXEL(to, from)    \
+    do {                         \
+        *(uint32_t *) to = from; \
+        SKIP_PIXEL(to);          \
+    } while (0)
 #else
 # error unknown bit depth
 #endif
diff --git a/hw/display/tc6393xb_template.h b/hw/display/tc6393xb_template.h
index 154aafd400..78629c07f9 100644
--- a/hw/display/tc6393xb_template.h
+++ b/hw/display/tc6393xb_template.h
@@ -22,14 +22,18 @@
  */
 
 #if BITS == 8
-# define SET_PIXEL(addr, color)	*(uint8_t*)addr = color;
+# define SET_PIXEL(addr, color)  (*(uint8_t *)addr = color)
 #elif BITS == 15 || BITS == 16
-# define SET_PIXEL(addr, color)	*(uint16_t*)addr = color;
+# define SET_PIXEL(addr, color)  (*(uint16_t *)addr = color)
 #elif BITS == 24
-# define SET_PIXEL(addr, color)	\
-    addr[0] = color; addr[1] = (color) >> 8; addr[2] = (color) >> 16;
+# define SET_PIXEL(addr, color)  \
+    do {                         \
+        addr[0] = color;         \
+        addr[1] = (color) >> 8;  \
+        addr[2] = (color) >> 16; \
+    } while (0)
 #elif BITS == 32
-# define SET_PIXEL(addr, color)	*(uint32_t*)addr = color;
+# define SET_PIXEL(addr, color)  (*(uint32_t *)addr = color)
 #else
 # error unknown bit depth
 #endif

From 9972da669fd3d3e3423d2bf6cb2c11fa9239f862 Mon Sep 17 00:00:00 2001
From: Will Newton <will.newton@linaro.org>
Date: Fri, 31 Jan 2014 14:47:33 +0000
Subject: [PATCH 15/34] target-arm: Move arm_rmode_to_sf to a shared location.

This function will be needed for AArch32 ARMv8 support, so move it to
helper.c where it can be used by both targets. Also moves the code out
of line, but as it is quite a large function I don't believe this
should be a significant performance impact.

Signed-off-by: Will Newton <will.newton@linaro.org>
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target-arm/cpu.h           |  2 ++
 target-arm/helper.c        | 28 ++++++++++++++++++++++++++++
 target-arm/translate-a64.c | 28 ----------------------------
 3 files changed, 30 insertions(+), 28 deletions(-)

diff --git a/target-arm/cpu.h b/target-arm/cpu.h
index 198b6b8d4e..383c58221e 100644
--- a/target-arm/cpu.h
+++ b/target-arm/cpu.h
@@ -496,6 +496,8 @@ enum arm_fprounding {
     FPROUNDING_ODD
 };
 
+int arm_rmode_to_sf(int rmode);
+
 enum arm_cpu_mode {
   ARM_CPU_MODE_USR = 0x10,
   ARM_CPU_MODE_FIQ = 0x11,
diff --git a/target-arm/helper.c b/target-arm/helper.c
index c708f15e27..b1541b9c40 100644
--- a/target-arm/helper.c
+++ b/target-arm/helper.c
@@ -4418,3 +4418,31 @@ float64 HELPER(rintd)(float64 x, void *fp_status)
 
     return ret;
 }
+
+/* Convert ARM rounding mode to softfloat */
+int arm_rmode_to_sf(int rmode)
+{
+    switch (rmode) {
+    case FPROUNDING_TIEAWAY:
+        rmode = float_round_ties_away;
+        break;
+    case FPROUNDING_ODD:
+        /* FIXME: add support for TIEAWAY and ODD */
+        qemu_log_mask(LOG_UNIMP, "arm: unimplemented rounding mode: %d\n",
+                      rmode);
+    case FPROUNDING_TIEEVEN:
+    default:
+        rmode = float_round_nearest_even;
+        break;
+    case FPROUNDING_POSINF:
+        rmode = float_round_up;
+        break;
+    case FPROUNDING_NEGINF:
+        rmode = float_round_down;
+        break;
+    case FPROUNDING_ZERO:
+        rmode = float_round_to_zero;
+        break;
+    }
+    return rmode;
+}
diff --git a/target-arm/translate-a64.c b/target-arm/translate-a64.c
index 7cfb55bdc6..c22bbb5cf3 100644
--- a/target-arm/translate-a64.c
+++ b/target-arm/translate-a64.c
@@ -3608,34 +3608,6 @@ static void disas_data_proc_reg(DisasContext *s, uint32_t insn)
     }
 }
 
-/* Convert ARM rounding mode to softfloat */
-static inline int arm_rmode_to_sf(int rmode)
-{
-    switch (rmode) {
-    case FPROUNDING_TIEAWAY:
-        rmode = float_round_ties_away;
-        break;
-    case FPROUNDING_ODD:
-        /* FIXME: add support for TIEAWAY and ODD */
-        qemu_log_mask(LOG_UNIMP, "arm: unimplemented rounding mode: %d\n",
-                      rmode);
-    case FPROUNDING_TIEEVEN:
-    default:
-        rmode = float_round_nearest_even;
-        break;
-    case FPROUNDING_POSINF:
-        rmode = float_round_up;
-        break;
-    case FPROUNDING_NEGINF:
-        rmode = float_round_down;
-        break;
-    case FPROUNDING_ZERO:
-        rmode = float_round_to_zero;
-        break;
-    }
-    return rmode;
-}
-
 static void handle_fp_compare(DisasContext *s, bool is_double,
                               unsigned int rn, unsigned int rm,
                               bool cmp_with_zero, bool signal_all_nans)

From 7655f39bde5de92b4a3c154a5a8735476c34f458 Mon Sep 17 00:00:00 2001
From: Will Newton <will.newton@linaro.org>
Date: Fri, 31 Jan 2014 14:47:33 +0000
Subject: [PATCH 16/34] target-arm: Add AArch32 FP VRINTA, VRINTN, VRINTP and
 VRINTM

Add support for AArch32 ARMv8 FP VRINTA, VRINTN, VRINTP and VRINTM
instructions.

Signed-off-by: Will Newton <will.newton@linaro.org>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target-arm/translate.c | 54 ++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 54 insertions(+)

diff --git a/target-arm/translate.c b/target-arm/translate.c
index 8d240e160d..2db681287d 100644
--- a/target-arm/translate.c
+++ b/target-arm/translate.c
@@ -2759,6 +2759,56 @@ static int handle_vminmaxnm(uint32_t insn, uint32_t rd, uint32_t rn,
     return 0;
 }
 
+static int handle_vrint(uint32_t insn, uint32_t rd, uint32_t rm, uint32_t dp,
+                        int rounding)
+{
+    TCGv_ptr fpst = get_fpstatus_ptr(0);
+    TCGv_i32 tcg_rmode;
+
+    tcg_rmode = tcg_const_i32(arm_rmode_to_sf(rounding));
+    gen_helper_set_rmode(tcg_rmode, tcg_rmode, cpu_env);
+
+    if (dp) {
+        TCGv_i64 tcg_op;
+        TCGv_i64 tcg_res;
+        tcg_op = tcg_temp_new_i64();
+        tcg_res = tcg_temp_new_i64();
+        tcg_gen_ld_f64(tcg_op, cpu_env, vfp_reg_offset(dp, rm));
+        gen_helper_rintd(tcg_res, tcg_op, fpst);
+        tcg_gen_st_f64(tcg_res, cpu_env, vfp_reg_offset(dp, rd));
+        tcg_temp_free_i64(tcg_op);
+        tcg_temp_free_i64(tcg_res);
+    } else {
+        TCGv_i32 tcg_op;
+        TCGv_i32 tcg_res;
+        tcg_op = tcg_temp_new_i32();
+        tcg_res = tcg_temp_new_i32();
+        tcg_gen_ld_f32(tcg_op, cpu_env, vfp_reg_offset(dp, rm));
+        gen_helper_rints(tcg_res, tcg_op, fpst);
+        tcg_gen_st_f32(tcg_res, cpu_env, vfp_reg_offset(dp, rd));
+        tcg_temp_free_i32(tcg_op);
+        tcg_temp_free_i32(tcg_res);
+    }
+
+    gen_helper_set_rmode(tcg_rmode, tcg_rmode, cpu_env);
+    tcg_temp_free_i32(tcg_rmode);
+
+    tcg_temp_free_ptr(fpst);
+    return 0;
+}
+
+
+/* Table for converting the most common AArch32 encoding of
+ * rounding mode to arm_fprounding order (which matches the
+ * common AArch64 order); see ARM ARM pseudocode FPDecodeRM().
+ */
+static const uint8_t fp_decode_rm[] = {
+    FPROUNDING_TIEAWAY,
+    FPROUNDING_TIEEVEN,
+    FPROUNDING_POSINF,
+    FPROUNDING_NEGINF,
+};
+
 static int disas_vfp_v8_insn(CPUARMState *env, DisasContext *s, uint32_t insn)
 {
     uint32_t rd, rn, rm, dp = extract32(insn, 8, 1);
@@ -2781,6 +2831,10 @@ static int disas_vfp_v8_insn(CPUARMState *env, DisasContext *s, uint32_t insn)
         return handle_vsel(insn, rd, rn, rm, dp);
     } else if ((insn & 0x0fb00e10) == 0x0e800a00) {
         return handle_vminmaxnm(insn, rd, rn, rm, dp);
+    } else if ((insn & 0x0fbc0ed0) == 0x0eb80a40) {
+        /* VRINTA, VRINTN, VRINTP, VRINTM */
+        int rounding = fp_decode_rm[extract32(insn, 16, 2)];
+        return handle_vrint(insn, rd, rm, dp, rounding);
     }
     return 1;
 }

From 664c6733d72c589cd9f6ccee305e7b7ce36ea06d Mon Sep 17 00:00:00 2001
From: Will Newton <will.newton@linaro.org>
Date: Fri, 31 Jan 2014 14:47:34 +0000
Subject: [PATCH 17/34] target-arm: Add support for AArch32 FP VRINTR

Add support for the AArch32 floating-point VRINTR instruction.

Signed-off-by: Will Newton <will.newton@linaro.org>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target-arm/translate.c | 11 +++++++++++
 1 file changed, 11 insertions(+)

diff --git a/target-arm/translate.c b/target-arm/translate.c
index 2db681287d..2b3157cabd 100644
--- a/target-arm/translate.c
+++ b/target-arm/translate.c
@@ -3379,6 +3379,17 @@ static int disas_vfp_insn(CPUARMState * env, DisasContext *s, uint32_t insn)
                         gen_vfp_F1_ld0(dp);
                         gen_vfp_cmpe(dp);
                         break;
+                    case 12: /* vrintr */
+                    {
+                        TCGv_ptr fpst = get_fpstatus_ptr(0);
+                        if (dp) {
+                            gen_helper_rintd(cpu_F0d, cpu_F0d, fpst);
+                        } else {
+                            gen_helper_rints(cpu_F0s, cpu_F0s, fpst);
+                        }
+                        tcg_temp_free_ptr(fpst);
+                        break;
+                    }
                     case 15: /* single<->double conversion */
                         if (dp)
                             gen_helper_vfp_fcvtsd(cpu_F0s, cpu_F0d, cpu_env);

From a290c62a7521a5695e12bb9022f8b953c2f50f54 Mon Sep 17 00:00:00 2001
From: Will Newton <will.newton@linaro.org>
Date: Fri, 31 Jan 2014 14:47:34 +0000
Subject: [PATCH 18/34] target-arm: Add support for AArch32 FP VRINTZ

Add support for the AArch32 floating-point VRINTZ instruction.

Signed-off-by: Will Newton <will.newton@linaro.org>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target-arm/translate.c | 16 ++++++++++++++++
 1 file changed, 16 insertions(+)

diff --git a/target-arm/translate.c b/target-arm/translate.c
index 2b3157cabd..9afb19fedc 100644
--- a/target-arm/translate.c
+++ b/target-arm/translate.c
@@ -3390,6 +3390,22 @@ static int disas_vfp_insn(CPUARMState * env, DisasContext *s, uint32_t insn)
                         tcg_temp_free_ptr(fpst);
                         break;
                     }
+                    case 13: /* vrintz */
+                    {
+                        TCGv_ptr fpst = get_fpstatus_ptr(0);
+                        TCGv_i32 tcg_rmode;
+                        tcg_rmode = tcg_const_i32(float_round_to_zero);
+                        gen_helper_set_rmode(tcg_rmode, tcg_rmode, cpu_env);
+                        if (dp) {
+                            gen_helper_rintd(cpu_F0d, cpu_F0d, fpst);
+                        } else {
+                            gen_helper_rints(cpu_F0s, cpu_F0s, fpst);
+                        }
+                        gen_helper_set_rmode(tcg_rmode, tcg_rmode, cpu_env);
+                        tcg_temp_free_i32(tcg_rmode);
+                        tcg_temp_free_ptr(fpst);
+                        break;
+                    }
                     case 15: /* single<->double conversion */
                         if (dp)
                             gen_helper_vfp_fcvtsd(cpu_F0s, cpu_F0d, cpu_env);

From 4e82bc01ecc46e90346f731065528b1d47971eba Mon Sep 17 00:00:00 2001
From: Will Newton <will.newton@linaro.org>
Date: Fri, 31 Jan 2014 14:47:34 +0000
Subject: [PATCH 19/34] target-arm: Add support for AArch32 FP VRINTX

Add support for the AArch32 floating-point VRINTX instruction.

Signed-off-by: Will Newton <will.newton@linaro.org>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target-arm/translate.c | 11 +++++++++++
 1 file changed, 11 insertions(+)

diff --git a/target-arm/translate.c b/target-arm/translate.c
index 9afb19fedc..9eb5b929cc 100644
--- a/target-arm/translate.c
+++ b/target-arm/translate.c
@@ -3406,6 +3406,17 @@ static int disas_vfp_insn(CPUARMState * env, DisasContext *s, uint32_t insn)
                         tcg_temp_free_ptr(fpst);
                         break;
                     }
+                    case 14: /* vrintx */
+                    {
+                        TCGv_ptr fpst = get_fpstatus_ptr(0);
+                        if (dp) {
+                            gen_helper_rintd_exact(cpu_F0d, cpu_F0d, fpst);
+                        } else {
+                            gen_helper_rints_exact(cpu_F0s, cpu_F0s, fpst);
+                        }
+                        tcg_temp_free_ptr(fpst);
+                        break;
+                    }
                     case 15: /* single<->double conversion */
                         if (dp)
                             gen_helper_vfp_fcvtsd(cpu_F0s, cpu_F0d, cpu_env);

From 2ce7062501c715aae0ad37c3923a3710dd8914df Mon Sep 17 00:00:00 2001
From: Will Newton <will.newton@linaro.org>
Date: Fri, 31 Jan 2014 14:47:34 +0000
Subject: [PATCH 20/34] target-arm: Add support for AArch32 SIMD VRINTX

Add support for the AArch32 Advanced SIMD VRINTX instruction.

Signed-off-by: Will Newton <will.newton@linaro.org>
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target-arm/translate.c | 11 ++++++++++-
 1 file changed, 10 insertions(+), 1 deletion(-)

diff --git a/target-arm/translate.c b/target-arm/translate.c
index 9eb5b929cc..c179817f22 100644
--- a/target-arm/translate.c
+++ b/target-arm/translate.c
@@ -4709,6 +4709,7 @@ static const uint8_t neon_3r_sizes[] = {
 #define NEON_2RM_VMOVN 36 /* Includes VQMOVN, VQMOVUN */
 #define NEON_2RM_VQMOVN 37 /* Includes VQMOVUN */
 #define NEON_2RM_VSHLL 38
+#define NEON_2RM_VRINTX 41
 #define NEON_2RM_VCVT_F16_F32 44
 #define NEON_2RM_VCVT_F32_F16 46
 #define NEON_2RM_VRECPE 56
@@ -4724,7 +4725,7 @@ static int neon_2rm_is_float_op(int op)
 {
     /* Return true if this neon 2reg-misc op is float-to-float */
     return (op == NEON_2RM_VABS_F || op == NEON_2RM_VNEG_F ||
-            op >= NEON_2RM_VRECPE_F);
+            op == NEON_2RM_VRINTX || op >= NEON_2RM_VRECPE_F);
 }
 
 /* Each entry in this array has bit n set if the insn allows
@@ -4768,6 +4769,7 @@ static const uint8_t neon_2rm_sizes[] = {
     [NEON_2RM_VMOVN] = 0x7,
     [NEON_2RM_VQMOVN] = 0x7,
     [NEON_2RM_VSHLL] = 0x7,
+    [NEON_2RM_VRINTX] = 0x4,
     [NEON_2RM_VCVT_F16_F32] = 0x2,
     [NEON_2RM_VCVT_F32_F16] = 0x2,
     [NEON_2RM_VRECPE] = 0x4,
@@ -6480,6 +6482,13 @@ static int disas_neon_data_insn(CPUARMState * env, DisasContext *s, uint32_t ins
                             }
                             neon_store_reg(rm, pass, tmp2);
                             break;
+                        case NEON_2RM_VRINTX:
+                        {
+                            TCGv_ptr fpstatus = get_fpstatus_ptr(1);
+                            gen_helper_rints_exact(cpu_F0s, cpu_F0s, fpstatus);
+                            tcg_temp_free_ptr(fpstatus);
+                            break;
+                        }
                         case NEON_2RM_VRECPE:
                             gen_helper_recpe_u32(tmp, tmp, cpu_env);
                             break;

From 43630e585300465b72ecf328822c8611724307de Mon Sep 17 00:00:00 2001
From: Will Newton <will.newton@linaro.org>
Date: Fri, 31 Jan 2014 14:47:35 +0000
Subject: [PATCH 21/34] target-arm: Add set_neon_rmode helper

This helper sets the rounding mode in the standard_fp_status word to
allow NEON instructions to modify the rounding mode whilst using the
standard FPSCR values for everything else.

Signed-off-by: Will Newton <will.newton@linaro.org>
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target-arm/helper.c | 17 +++++++++++++++++
 target-arm/helper.h |  1 +
 2 files changed, 18 insertions(+)

diff --git a/target-arm/helper.c b/target-arm/helper.c
index b1541b9c40..ca5b0000ad 100644
--- a/target-arm/helper.c
+++ b/target-arm/helper.c
@@ -4048,6 +4048,23 @@ uint32_t HELPER(set_rmode)(uint32_t rmode, CPUARMState *env)
     return prev_rmode;
 }
 
+/* Set the current fp rounding mode in the standard fp status and return
+ * the old one. This is for NEON instructions that need to change the
+ * rounding mode but wish to use the standard FPSCR values for everything
+ * else. Always set the rounding mode back to the correct value after
+ * modifying it.
+ * The argument is a softfloat float_round_ value.
+ */
+uint32_t HELPER(set_neon_rmode)(uint32_t rmode, CPUARMState *env)
+{
+    float_status *fp_status = &env->vfp.standard_fp_status;
+
+    uint32_t prev_rmode = get_float_rounding_mode(fp_status);
+    set_float_rounding_mode(rmode, fp_status);
+
+    return prev_rmode;
+}
+
 /* Half precision conversions.  */
 static float32 do_fcvt_f16_to_f32(uint32_t a, CPUARMState *env, float_status *s)
 {
diff --git a/target-arm/helper.h b/target-arm/helper.h
index 70872dffc6..71b8411120 100644
--- a/target-arm/helper.h
+++ b/target-arm/helper.h
@@ -149,6 +149,7 @@ DEF_HELPER_3(vfp_ultod, f64, i64, i32, ptr)
 DEF_HELPER_3(vfp_uqtod, f64, i64, i32, ptr)
 
 DEF_HELPER_FLAGS_2(set_rmode, TCG_CALL_NO_RWG, i32, i32, env)
+DEF_HELPER_FLAGS_2(set_neon_rmode, TCG_CALL_NO_RWG, i32, i32, env)
 
 DEF_HELPER_2(vfp_fcvt_f16_to_f32, f32, i32, env)
 DEF_HELPER_2(vfp_fcvt_f32_to_f16, i32, f32, env)

From 34f7b0a276ed2679c5e420ed1bc6525689ac5abd Mon Sep 17 00:00:00 2001
From: Will Newton <will.newton@linaro.org>
Date: Fri, 31 Jan 2014 14:47:35 +0000
Subject: [PATCH 22/34] target-arm: Add AArch32 SIMD VRINTA, VRINTN, VRINTP,
 VRINTM, VRINTZ

Add support for the AArch32 Advanced SIMD VRINTA, VRINTN, VRINTP
VRINTM and VRINTZ instructions.

Signed-off-by: Will Newton <will.newton@linaro.org>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target-arm/translate.c | 40 +++++++++++++++++++++++++++++++++++++++-
 1 file changed, 39 insertions(+), 1 deletion(-)

diff --git a/target-arm/translate.c b/target-arm/translate.c
index c179817f22..5a8ca240c2 100644
--- a/target-arm/translate.c
+++ b/target-arm/translate.c
@@ -4709,9 +4709,14 @@ static const uint8_t neon_3r_sizes[] = {
 #define NEON_2RM_VMOVN 36 /* Includes VQMOVN, VQMOVUN */
 #define NEON_2RM_VQMOVN 37 /* Includes VQMOVUN */
 #define NEON_2RM_VSHLL 38
+#define NEON_2RM_VRINTN 40
 #define NEON_2RM_VRINTX 41
+#define NEON_2RM_VRINTA 42
+#define NEON_2RM_VRINTZ 43
 #define NEON_2RM_VCVT_F16_F32 44
+#define NEON_2RM_VRINTM 45
 #define NEON_2RM_VCVT_F32_F16 46
+#define NEON_2RM_VRINTP 47
 #define NEON_2RM_VRECPE 56
 #define NEON_2RM_VRSQRTE 57
 #define NEON_2RM_VRECPE_F 58
@@ -4725,7 +4730,9 @@ static int neon_2rm_is_float_op(int op)
 {
     /* Return true if this neon 2reg-misc op is float-to-float */
     return (op == NEON_2RM_VABS_F || op == NEON_2RM_VNEG_F ||
-            op == NEON_2RM_VRINTX || op >= NEON_2RM_VRECPE_F);
+            (op >= NEON_2RM_VRINTN && op <= NEON_2RM_VRINTZ) ||
+            op == NEON_2RM_VRINTM || op == NEON_2RM_VRINTP ||
+            op >= NEON_2RM_VRECPE_F);
 }
 
 /* Each entry in this array has bit n set if the insn allows
@@ -4769,9 +4776,14 @@ static const uint8_t neon_2rm_sizes[] = {
     [NEON_2RM_VMOVN] = 0x7,
     [NEON_2RM_VQMOVN] = 0x7,
     [NEON_2RM_VSHLL] = 0x7,
+    [NEON_2RM_VRINTN] = 0x4,
     [NEON_2RM_VRINTX] = 0x4,
+    [NEON_2RM_VRINTA] = 0x4,
+    [NEON_2RM_VRINTZ] = 0x4,
     [NEON_2RM_VCVT_F16_F32] = 0x2,
+    [NEON_2RM_VRINTM] = 0x4,
     [NEON_2RM_VCVT_F32_F16] = 0x2,
+    [NEON_2RM_VRINTP] = 0x4,
     [NEON_2RM_VRECPE] = 0x4,
     [NEON_2RM_VRSQRTE] = 0x4,
     [NEON_2RM_VRECPE_F] = 0x4,
@@ -6482,6 +6494,32 @@ static int disas_neon_data_insn(CPUARMState * env, DisasContext *s, uint32_t ins
                             }
                             neon_store_reg(rm, pass, tmp2);
                             break;
+                        case NEON_2RM_VRINTN:
+                        case NEON_2RM_VRINTA:
+                        case NEON_2RM_VRINTM:
+                        case NEON_2RM_VRINTP:
+                        case NEON_2RM_VRINTZ:
+                        {
+                            TCGv_i32 tcg_rmode;
+                            TCGv_ptr fpstatus = get_fpstatus_ptr(1);
+                            int rmode;
+
+                            if (op == NEON_2RM_VRINTZ) {
+                                rmode = FPROUNDING_ZERO;
+                            } else {
+                                rmode = fp_decode_rm[((op & 0x6) >> 1) ^ 1];
+                            }
+
+                            tcg_rmode = tcg_const_i32(arm_rmode_to_sf(rmode));
+                            gen_helper_set_neon_rmode(tcg_rmode, tcg_rmode,
+                                                      cpu_env);
+                            gen_helper_rints(cpu_F0s, cpu_F0s, fpstatus);
+                            gen_helper_set_neon_rmode(tcg_rmode, tcg_rmode,
+                                                      cpu_env);
+                            tcg_temp_free_ptr(fpstatus);
+                            tcg_temp_free_i32(tcg_rmode);
+                            break;
+                        }
                         case NEON_2RM_VRINTX:
                         {
                             TCGv_ptr fpstatus = get_fpstatus_ptr(1);

From c9975a838736c9479b2e17fff7e50a2a83b1009e Mon Sep 17 00:00:00 2001
From: Will Newton <will.newton@linaro.org>
Date: Fri, 31 Jan 2014 14:47:35 +0000
Subject: [PATCH 23/34] target-arm: Add AArch32 FP VCVTA, VCVTN, VCVTP and
 VCVTM

Add support for the AArch32 floating-point VCVTA, VCVTN, VCVTP
and VCVTM instructions.

Signed-off-by: Will Newton <will.newton@linaro.org>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target-arm/translate.c | 61 ++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 61 insertions(+)

diff --git a/target-arm/translate.c b/target-arm/translate.c
index 5a8ca240c2..0fcc159350 100644
--- a/target-arm/translate.c
+++ b/target-arm/translate.c
@@ -2797,6 +2797,63 @@ static int handle_vrint(uint32_t insn, uint32_t rd, uint32_t rm, uint32_t dp,
     return 0;
 }
 
+static int handle_vcvt(uint32_t insn, uint32_t rd, uint32_t rm, uint32_t dp,
+                       int rounding)
+{
+    bool is_signed = extract32(insn, 7, 1);
+    TCGv_ptr fpst = get_fpstatus_ptr(0);
+    TCGv_i32 tcg_rmode, tcg_shift;
+
+    tcg_shift = tcg_const_i32(0);
+
+    tcg_rmode = tcg_const_i32(arm_rmode_to_sf(rounding));
+    gen_helper_set_rmode(tcg_rmode, tcg_rmode, cpu_env);
+
+    if (dp) {
+        TCGv_i64 tcg_double, tcg_res;
+        TCGv_i32 tcg_tmp;
+        /* Rd is encoded as a single precision register even when the source
+         * is double precision.
+         */
+        rd = ((rd << 1) & 0x1e) | ((rd >> 4) & 0x1);
+        tcg_double = tcg_temp_new_i64();
+        tcg_res = tcg_temp_new_i64();
+        tcg_tmp = tcg_temp_new_i32();
+        tcg_gen_ld_f64(tcg_double, cpu_env, vfp_reg_offset(1, rm));
+        if (is_signed) {
+            gen_helper_vfp_tosld(tcg_res, tcg_double, tcg_shift, fpst);
+        } else {
+            gen_helper_vfp_tould(tcg_res, tcg_double, tcg_shift, fpst);
+        }
+        tcg_gen_trunc_i64_i32(tcg_tmp, tcg_res);
+        tcg_gen_st_f32(tcg_tmp, cpu_env, vfp_reg_offset(0, rd));
+        tcg_temp_free_i32(tcg_tmp);
+        tcg_temp_free_i64(tcg_res);
+        tcg_temp_free_i64(tcg_double);
+    } else {
+        TCGv_i32 tcg_single, tcg_res;
+        tcg_single = tcg_temp_new_i32();
+        tcg_res = tcg_temp_new_i32();
+        tcg_gen_ld_f32(tcg_single, cpu_env, vfp_reg_offset(0, rm));
+        if (is_signed) {
+            gen_helper_vfp_tosls(tcg_res, tcg_single, tcg_shift, fpst);
+        } else {
+            gen_helper_vfp_touls(tcg_res, tcg_single, tcg_shift, fpst);
+        }
+        tcg_gen_st_f32(tcg_res, cpu_env, vfp_reg_offset(0, rd));
+        tcg_temp_free_i32(tcg_res);
+        tcg_temp_free_i32(tcg_single);
+    }
+
+    gen_helper_set_rmode(tcg_rmode, tcg_rmode, cpu_env);
+    tcg_temp_free_i32(tcg_rmode);
+
+    tcg_temp_free_i32(tcg_shift);
+
+    tcg_temp_free_ptr(fpst);
+
+    return 0;
+}
 
 /* Table for converting the most common AArch32 encoding of
  * rounding mode to arm_fprounding order (which matches the
@@ -2835,6 +2892,10 @@ static int disas_vfp_v8_insn(CPUARMState *env, DisasContext *s, uint32_t insn)
         /* VRINTA, VRINTN, VRINTP, VRINTM */
         int rounding = fp_decode_rm[extract32(insn, 16, 2)];
         return handle_vrint(insn, rd, rm, dp, rounding);
+    } else if ((insn & 0x0fbc0e50) == 0x0ebc0a40) {
+        /* VCVTA, VCVTN, VCVTP, VCVTM */
+        int rounding = fp_decode_rm[extract32(insn, 16, 2)];
+        return handle_vcvt(insn, rd, rm, dp, rounding);
     }
     return 1;
 }

From 901ad5259fab785537f8c6b3713fce85d2ebceb1 Mon Sep 17 00:00:00 2001
From: Will Newton <will.newton@linaro.org>
Date: Fri, 31 Jan 2014 14:47:35 +0000
Subject: [PATCH 24/34] target-arm: Add AArch32 SIMD VCVTA, VCVTN, VCVTP and
 VCVTM

Add support for the AArch32 Advanced SIMD VCVTA, VCVTN, VCVTP
and VCVTM instructions.

Signed-off-by: Will Newton <will.newton@linaro.org>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target-arm/translate.c | 53 +++++++++++++++++++++++++++++++++++++++++-
 1 file changed, 52 insertions(+), 1 deletion(-)

diff --git a/target-arm/translate.c b/target-arm/translate.c
index 0fcc159350..e701c0f9e1 100644
--- a/target-arm/translate.c
+++ b/target-arm/translate.c
@@ -4778,6 +4778,14 @@ static const uint8_t neon_3r_sizes[] = {
 #define NEON_2RM_VRINTM 45
 #define NEON_2RM_VCVT_F32_F16 46
 #define NEON_2RM_VRINTP 47
+#define NEON_2RM_VCVTAU 48
+#define NEON_2RM_VCVTAS 49
+#define NEON_2RM_VCVTNU 50
+#define NEON_2RM_VCVTNS 51
+#define NEON_2RM_VCVTPU 52
+#define NEON_2RM_VCVTPS 53
+#define NEON_2RM_VCVTMU 54
+#define NEON_2RM_VCVTMS 55
 #define NEON_2RM_VRECPE 56
 #define NEON_2RM_VRSQRTE 57
 #define NEON_2RM_VRECPE_F 58
@@ -4792,7 +4800,8 @@ static int neon_2rm_is_float_op(int op)
     /* Return true if this neon 2reg-misc op is float-to-float */
     return (op == NEON_2RM_VABS_F || op == NEON_2RM_VNEG_F ||
             (op >= NEON_2RM_VRINTN && op <= NEON_2RM_VRINTZ) ||
-            op == NEON_2RM_VRINTM || op == NEON_2RM_VRINTP ||
+            op == NEON_2RM_VRINTM ||
+            (op >= NEON_2RM_VRINTP && op <= NEON_2RM_VCVTMS) ||
             op >= NEON_2RM_VRECPE_F);
 }
 
@@ -4845,6 +4854,14 @@ static const uint8_t neon_2rm_sizes[] = {
     [NEON_2RM_VRINTM] = 0x4,
     [NEON_2RM_VCVT_F32_F16] = 0x2,
     [NEON_2RM_VRINTP] = 0x4,
+    [NEON_2RM_VCVTAU] = 0x4,
+    [NEON_2RM_VCVTAS] = 0x4,
+    [NEON_2RM_VCVTNU] = 0x4,
+    [NEON_2RM_VCVTNS] = 0x4,
+    [NEON_2RM_VCVTPU] = 0x4,
+    [NEON_2RM_VCVTPS] = 0x4,
+    [NEON_2RM_VCVTMU] = 0x4,
+    [NEON_2RM_VCVTMS] = 0x4,
     [NEON_2RM_VRECPE] = 0x4,
     [NEON_2RM_VRSQRTE] = 0x4,
     [NEON_2RM_VRECPE_F] = 0x4,
@@ -6588,6 +6605,40 @@ static int disas_neon_data_insn(CPUARMState * env, DisasContext *s, uint32_t ins
                             tcg_temp_free_ptr(fpstatus);
                             break;
                         }
+                        case NEON_2RM_VCVTAU:
+                        case NEON_2RM_VCVTAS:
+                        case NEON_2RM_VCVTNU:
+                        case NEON_2RM_VCVTNS:
+                        case NEON_2RM_VCVTPU:
+                        case NEON_2RM_VCVTPS:
+                        case NEON_2RM_VCVTMU:
+                        case NEON_2RM_VCVTMS:
+                        {
+                            bool is_signed = !extract32(insn, 7, 1);
+                            TCGv_ptr fpst = get_fpstatus_ptr(1);
+                            TCGv_i32 tcg_rmode, tcg_shift;
+                            int rmode = fp_decode_rm[extract32(insn, 8, 2)];
+
+                            tcg_shift = tcg_const_i32(0);
+                            tcg_rmode = tcg_const_i32(arm_rmode_to_sf(rmode));
+                            gen_helper_set_neon_rmode(tcg_rmode, tcg_rmode,
+                                                      cpu_env);
+
+                            if (is_signed) {
+                                gen_helper_vfp_tosls(cpu_F0s, cpu_F0s,
+                                                     tcg_shift, fpst);
+                            } else {
+                                gen_helper_vfp_touls(cpu_F0s, cpu_F0s,
+                                                     tcg_shift, fpst);
+                            }
+
+                            gen_helper_set_neon_rmode(tcg_rmode, tcg_rmode,
+                                                      cpu_env);
+                            tcg_temp_free_i32(tcg_rmode);
+                            tcg_temp_free_i32(tcg_shift);
+                            tcg_temp_free_ptr(fpst);
+                            break;
+                        }
                         case NEON_2RM_VRECPE:
                             gen_helper_recpe_u32(tmp, tmp, cpu_env);
                             break;

From a08582f41e94b5a7ee3e53ad1e719d24431aa675 Mon Sep 17 00:00:00 2001
From: Peter Maydell <peter.maydell@linaro.org>
Date: Fri, 31 Jan 2014 14:47:36 +0000
Subject: [PATCH 25/34] target-arm: A64: Add SIMD three-different multiply
 accumulate insns

Add support for the multiply-accumulate instructions from the
SIMD three-different instructions group (C3.6.15):
 * skeleton decode of unallocated encodings and split of
   the group into its three sub-parts
 * framework for handling the 64x64->128 widening subpart
 * implementation of the multiply-accumulate instructions
   SMLAL, SMLAL2, UMLAL, UMLAL2, SMLSL, SMLSL2, UMLSL, UMLSL2,
   UMULL, UMULL2, SMULL, SMULL2

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <rth@twiddle.net>
---
 target-arm/translate-a64.c | 233 ++++++++++++++++++++++++++++++++++++-
 1 file changed, 232 insertions(+), 1 deletion(-)

diff --git a/target-arm/translate-a64.c b/target-arm/translate-a64.c
index c22bbb5cf3..e8479a52db 100644
--- a/target-arm/translate-a64.c
+++ b/target-arm/translate-a64.c
@@ -700,6 +700,9 @@ static void do_fp_ld(DisasContext *s, int destidx, TCGv_i64 tcg_addr, int size)
  * zero extend as we are filling a partial chunk of the vector register.
  * These functions don't support 128 bit loads/stores, which would be
  * normal load/store operations.
+ *
+ * The _i32 versions are useful when operating on 32 bit quantities
+ * (eg for floating point single or using Neon helper functions).
  */
 
 /* Get value of an element within a vector register */
@@ -735,6 +738,32 @@ static void read_vec_element(DisasContext *s, TCGv_i64 tcg_dest, int srcidx,
     }
 }
 
+static void read_vec_element_i32(DisasContext *s, TCGv_i32 tcg_dest, int srcidx,
+                                 int element, TCGMemOp memop)
+{
+    int vect_off = vec_reg_offset(srcidx, element, memop & MO_SIZE);
+    switch (memop) {
+    case MO_8:
+        tcg_gen_ld8u_i32(tcg_dest, cpu_env, vect_off);
+        break;
+    case MO_16:
+        tcg_gen_ld16u_i32(tcg_dest, cpu_env, vect_off);
+        break;
+    case MO_8|MO_SIGN:
+        tcg_gen_ld8s_i32(tcg_dest, cpu_env, vect_off);
+        break;
+    case MO_16|MO_SIGN:
+        tcg_gen_ld16s_i32(tcg_dest, cpu_env, vect_off);
+        break;
+    case MO_32:
+    case MO_32|MO_SIGN:
+        tcg_gen_ld_i32(tcg_dest, cpu_env, vect_off);
+        break;
+    default:
+        g_assert_not_reached();
+    }
+}
+
 /* Set value of an element within a vector register */
 static void write_vec_element(DisasContext *s, TCGv_i64 tcg_src, int destidx,
                               int element, TCGMemOp memop)
@@ -5518,6 +5547,150 @@ static void disas_simd_shift_imm(DisasContext *s, uint32_t insn)
     unsupported_encoding(s, insn);
 }
 
+static void handle_3rd_widening(DisasContext *s, int is_q, int is_u, int size,
+                                int opcode, int rd, int rn, int rm)
+{
+    /* 3-reg-different widening insns: 64 x 64 -> 128 */
+    TCGv_i64 tcg_res[2];
+    int pass, accop;
+
+    tcg_res[0] = tcg_temp_new_i64();
+    tcg_res[1] = tcg_temp_new_i64();
+
+    /* Does this op do an adding accumulate, a subtracting accumulate,
+     * or no accumulate at all?
+     */
+    switch (opcode) {
+    case 5:
+    case 8:
+    case 9:
+        accop = 1;
+        break;
+    case 10:
+    case 11:
+        accop = -1;
+        break;
+    default:
+        accop = 0;
+        break;
+    }
+
+    if (accop != 0) {
+        read_vec_element(s, tcg_res[0], rd, 0, MO_64);
+        read_vec_element(s, tcg_res[1], rd, 1, MO_64);
+    }
+
+    /* size == 2 means two 32x32->64 operations; this is worth special
+     * casing because we can generally handle it inline.
+     */
+    if (size == 2) {
+        for (pass = 0; pass < 2; pass++) {
+            TCGv_i64 tcg_op1 = tcg_temp_new_i64();
+            TCGv_i64 tcg_op2 = tcg_temp_new_i64();
+            TCGv_i64 tcg_passres;
+            TCGMemOp memop = MO_32 | (is_u ? 0 : MO_SIGN);
+
+            int elt = pass + is_q * 2;
+
+            read_vec_element(s, tcg_op1, rn, elt, memop);
+            read_vec_element(s, tcg_op2, rm, elt, memop);
+
+            if (accop == 0) {
+                tcg_passres = tcg_res[pass];
+            } else {
+                tcg_passres = tcg_temp_new_i64();
+            }
+
+            switch (opcode) {
+            case 8: /* SMLAL, SMLAL2, UMLAL, UMLAL2 */
+            case 10: /* SMLSL, SMLSL2, UMLSL, UMLSL2 */
+            case 12: /* UMULL, UMULL2, SMULL, SMULL2 */
+                tcg_gen_mul_i64(tcg_passres, tcg_op1, tcg_op2);
+                break;
+            default:
+                g_assert_not_reached();
+            }
+
+            if (accop > 0) {
+                tcg_gen_add_i64(tcg_res[pass], tcg_res[pass], tcg_passres);
+                tcg_temp_free_i64(tcg_passres);
+            } else if (accop < 0) {
+                tcg_gen_sub_i64(tcg_res[pass], tcg_res[pass], tcg_passres);
+                tcg_temp_free_i64(tcg_passres);
+            }
+
+            tcg_temp_free_i64(tcg_op1);
+            tcg_temp_free_i64(tcg_op2);
+        }
+    } else {
+        /* size 0 or 1, generally helper functions */
+        for (pass = 0; pass < 2; pass++) {
+            TCGv_i32 tcg_op1 = tcg_temp_new_i32();
+            TCGv_i32 tcg_op2 = tcg_temp_new_i32();
+            TCGv_i64 tcg_passres;
+            int elt = pass + is_q * 2;
+
+            read_vec_element_i32(s, tcg_op1, rn, elt, MO_32);
+            read_vec_element_i32(s, tcg_op2, rm, elt, MO_32);
+
+            if (accop == 0) {
+                tcg_passres = tcg_res[pass];
+            } else {
+                tcg_passres = tcg_temp_new_i64();
+            }
+
+            switch (opcode) {
+            case 8: /* SMLAL, SMLAL2, UMLAL, UMLAL2 */
+            case 10: /* SMLSL, SMLSL2, UMLSL, UMLSL2 */
+            case 12: /* UMULL, UMULL2, SMULL, SMULL2 */
+                if (size == 0) {
+                    if (is_u) {
+                        gen_helper_neon_mull_u8(tcg_passres, tcg_op1, tcg_op2);
+                    } else {
+                        gen_helper_neon_mull_s8(tcg_passres, tcg_op1, tcg_op2);
+                    }
+                } else {
+                    if (is_u) {
+                        gen_helper_neon_mull_u16(tcg_passres, tcg_op1, tcg_op2);
+                    } else {
+                        gen_helper_neon_mull_s16(tcg_passres, tcg_op1, tcg_op2);
+                    }
+                }
+                break;
+            default:
+                g_assert_not_reached();
+            }
+            tcg_temp_free_i32(tcg_op1);
+            tcg_temp_free_i32(tcg_op2);
+
+            if (accop > 0) {
+                if (size == 0) {
+                    gen_helper_neon_addl_u16(tcg_res[pass], tcg_res[pass],
+                                             tcg_passres);
+                } else {
+                    gen_helper_neon_addl_u32(tcg_res[pass], tcg_res[pass],
+                                             tcg_passres);
+                }
+                tcg_temp_free_i64(tcg_passres);
+            } else if (accop < 0) {
+                if (size == 0) {
+                    gen_helper_neon_subl_u16(tcg_res[pass], tcg_res[pass],
+                                             tcg_passres);
+                } else {
+                    gen_helper_neon_subl_u32(tcg_res[pass], tcg_res[pass],
+                                             tcg_passres);
+                }
+                tcg_temp_free_i64(tcg_passres);
+            }
+        }
+    }
+
+    write_vec_element(s, tcg_res[0], rd, 0, MO_64);
+    write_vec_element(s, tcg_res[1], rd, 1, MO_64);
+    tcg_temp_free_i64(tcg_res[0]);
+    tcg_temp_free_i64(tcg_res[1]);
+}
+
 /* C3.6.15 AdvSIMD three different
  *   31  30  29 28       24 23  22  21 20  16 15    12 11 10 9    5 4    0
  * +---+---+---+-----------+------+---+------+--------+-----+------+------+
@@ -5526,7 +5699,65 @@ static void disas_simd_shift_imm(DisasContext *s, uint32_t insn)
  */
 static void disas_simd_three_reg_diff(DisasContext *s, uint32_t insn)
 {
-    unsupported_encoding(s, insn);
+    /* Instructions in this group fall into three basic classes
+     * (in each case with the operation working on each element in
+     * the input vectors):
+     * (1) widening 64 x 64 -> 128 (with possibly Vd as an extra
+     *     128 bit input)
+     * (2) wide 64 x 128 -> 128
+     * (3) narrowing 128 x 128 -> 64
+     * Here we do initial decode, catch unallocated cases and
+     * dispatch to separate functions for each class.
+     */
+    int is_q = extract32(insn, 30, 1);
+    int is_u = extract32(insn, 29, 1);
+    int size = extract32(insn, 22, 2);
+    int opcode = extract32(insn, 12, 4);
+    int rm = extract32(insn, 16, 5);
+    int rn = extract32(insn, 5, 5);
+    int rd = extract32(insn, 0, 5);
+
+    switch (opcode) {
+    case 1: /* SADDW, SADDW2, UADDW, UADDW2 */
+    case 3: /* SSUBW, SSUBW2, USUBW, USUBW2 */
+        /* 64 x 128 -> 128 */
+        unsupported_encoding(s, insn);
+        break;
+    case 4: /* ADDHN, ADDHN2, RADDHN, RADDHN2 */
+    case 6: /* SUBHN, SUBHN2, RSUBHN, RSUBHN2 */
+        /* 128 x 128 -> 64 */
+        unsupported_encoding(s, insn);
+        break;
+    case 9:
+    case 11:
+    case 13:
+    case 14:
+        if (is_u) {
+            unallocated_encoding(s);
+            return;
+        }
+        /* fall through */
+    case 0:
+    case 2:
+    case 5:
+    case 7:
+        unsupported_encoding(s, insn);
+        break;
+    case 8:
+    case 10:
+    case 12:
+        /* 64 x 64 -> 128 */
+        if (size == 3) {
+            unallocated_encoding(s);
+            return;
+        }
+        handle_3rd_widening(s, is_q, is_u, size, opcode, rd, rn, rm);
+        break;
+    default:
+        /* opcode 15 not allocated */
+        unallocated_encoding(s);
+        break;
+    }
 }
 
 /* C3.6.16 AdvSIMD three same

From 0ae39320bd0783f1a1d4ac63ec9ba48ca41764dc Mon Sep 17 00:00:00 2001
From: Peter Maydell <peter.maydell@linaro.org>
Date: Fri, 31 Jan 2014 14:47:36 +0000
Subject: [PATCH 26/34] target-arm: A64: Add SIMD three-different ABDL
 instructions

Implement the absolute-difference instructions in the SIMD
three-different group: SABAL, SABAL2, UABAL, UABAL2, SABDL,
SABDL2, UABDL, UABDL2.

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <rth@twiddle.net>
---
 target-arm/translate-a64.c | 35 +++++++++++++++++++++++++++++++++--
 1 file changed, 33 insertions(+), 2 deletions(-)

diff --git a/target-arm/translate-a64.c b/target-arm/translate-a64.c
index e8479a52db..e098efd315 100644
--- a/target-arm/translate-a64.c
+++ b/target-arm/translate-a64.c
@@ -5602,6 +5602,21 @@ static void handle_3rd_widening(DisasContext *s, int is_q, int is_u, int size,
             }
 
             switch (opcode) {
+            case 5: /* SABAL, SABAL2, UABAL, UABAL2 */
+            case 7: /* SABDL, SABDL2, UABDL, UABDL2 */
+            {
+                TCGv_i64 tcg_tmp1 = tcg_temp_new_i64();
+                TCGv_i64 tcg_tmp2 = tcg_temp_new_i64();
+
+                tcg_gen_sub_i64(tcg_tmp1, tcg_op1, tcg_op2);
+                tcg_gen_sub_i64(tcg_tmp2, tcg_op2, tcg_op1);
+                tcg_gen_movcond_i64(is_u ? TCG_COND_GEU : TCG_COND_GE,
+                                    tcg_passres,
+                                    tcg_op1, tcg_op2, tcg_tmp1, tcg_tmp2);
+                tcg_temp_free_i64(tcg_tmp1);
+                tcg_temp_free_i64(tcg_tmp2);
+                break;
+            }
             case 8: /* SMLAL, SMLAL2, UMLAL, UMLAL2 */
             case 10: /* SMLSL, SMLSL2, UMLSL, UMLSL2 */
             case 12: /* UMULL, UMULL2, SMULL, SMULL2 */
@@ -5640,6 +5655,22 @@ static void handle_3rd_widening(DisasContext *s, int is_q, int is_u, int size,
             }
 
             switch (opcode) {
+            case 5: /* SABAL, SABAL2, UABAL, UABAL2 */
+            case 7: /* SABDL, SABDL2, UABDL, UABDL2 */
+                if (size == 0) {
+                    if (is_u) {
+                        gen_helper_neon_abdl_u16(tcg_passres, tcg_op1, tcg_op2);
+                    } else {
+                        gen_helper_neon_abdl_s16(tcg_passres, tcg_op1, tcg_op2);
+                    }
+                } else {
+                    if (is_u) {
+                        gen_helper_neon_abdl_u32(tcg_passres, tcg_op1, tcg_op2);
+                    } else {
+                        gen_helper_neon_abdl_s32(tcg_passres, tcg_op1, tcg_op2);
+                    }
+                }
+                break;
             case 8: /* SMLAL, SMLAL2, UMLAL, UMLAL2 */
             case 10: /* SMLSL, SMLSL2, UMLSL, UMLSL2 */
             case 12: /* UMULL, UMULL2, SMULL, SMULL2 */
@@ -5739,10 +5770,10 @@ static void disas_simd_three_reg_diff(DisasContext *s, uint32_t insn)
         /* fall through */
     case 0:
     case 2:
-    case 5:
-    case 7:
         unsupported_encoding(s, insn);
         break;
+    case 5:
+    case 7:
     case 8:
     case 10:
     case 12:

From b305dba6cf2957bc67aa6072978c65026ce478fb Mon Sep 17 00:00:00 2001
From: Peter Maydell <peter.maydell@linaro.org>
Date: Fri, 31 Jan 2014 14:47:36 +0000
Subject: [PATCH 27/34] target-arm: A64: Add SIMD scalar 3 same add, sub and
 compare ops

Implement the add, sub and compare ops from the SIMD "scalar three same"
group.

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <rth@twiddle.net>
---
 target-arm/translate-a64.c | 131 ++++++++++++++++++++++++++++++++++++-
 1 file changed, 130 insertions(+), 1 deletion(-)

diff --git a/target-arm/translate-a64.c b/target-arm/translate-a64.c
index e098efd315..f0ebbb534a 100644
--- a/target-arm/translate-a64.c
+++ b/target-arm/translate-a64.c
@@ -5503,6 +5503,58 @@ static void disas_simd_scalar_three_reg_diff(DisasContext *s, uint32_t insn)
     unsupported_encoding(s, insn);
 }
 
+static void handle_3same_64(DisasContext *s, int opcode, bool u,
+                            TCGv_i64 tcg_rd, TCGv_i64 tcg_rn, TCGv_i64 tcg_rm)
+{
+    /* Handle 64x64->64 opcodes which are shared between the scalar
+     * and vector 3-same groups. We cover every opcode where size == 3
+     * is valid in either the three-reg-same (integer, not pairwise)
+     * or scalar-three-reg-same groups. (Some opcodes are not yet
+     * implemented.)
+     */
+    TCGCond cond;
+
+    switch (opcode) {
+    case 0x6: /* CMGT, CMHI */
+        /* 64 bit integer comparison, result = test ? (2^64 - 1) : 0.
+         * We implement this using setcond (test) and then negating.
+         */
+        cond = u ? TCG_COND_GTU : TCG_COND_GT;
+    do_cmop:
+        tcg_gen_setcond_i64(cond, tcg_rd, tcg_rn, tcg_rm);
+        tcg_gen_neg_i64(tcg_rd, tcg_rd);
+        break;
+    case 0x7: /* CMGE, CMHS */
+        cond = u ? TCG_COND_GEU : TCG_COND_GE;
+        goto do_cmop;
+    case 0x11: /* CMTST, CMEQ */
+        if (u) {
+            cond = TCG_COND_EQ;
+            goto do_cmop;
+        }
+        /* CMTST : test is "if (X & Y != 0)". */
+        tcg_gen_and_i64(tcg_rd, tcg_rn, tcg_rm);
+        tcg_gen_setcondi_i64(TCG_COND_NE, tcg_rd, tcg_rd, 0);
+        tcg_gen_neg_i64(tcg_rd, tcg_rd);
+        break;
+    case 0x10: /* ADD, SUB */
+        if (u) {
+            tcg_gen_sub_i64(tcg_rd, tcg_rn, tcg_rm);
+        } else {
+            tcg_gen_add_i64(tcg_rd, tcg_rn, tcg_rm);
+        }
+        break;
+    case 0x1: /* SQADD */
+    case 0x5: /* SQSUB */
+    case 0x8: /* SSHL, USHL */
+    case 0x9: /* SQSHL, UQSHL */
+    case 0xa: /* SRSHL, URSHL */
+    case 0xb: /* SQRSHL, UQRSHL */
+    default:
+        g_assert_not_reached();
+    }
+}
+
 /* C3.6.11 AdvSIMD scalar three same
  *  31 30  29 28       24 23  22  21 20  16 15    11  10 9    5 4    0
  * +-----+---+-----------+------+---+------+--------+---+------+------+
@@ -5511,7 +5563,84 @@ static void disas_simd_scalar_three_reg_diff(DisasContext *s, uint32_t insn)
  */
 static void disas_simd_scalar_three_reg_same(DisasContext *s, uint32_t insn)
 {
-    unsupported_encoding(s, insn);
+    int rd = extract32(insn, 0, 5);
+    int rn = extract32(insn, 5, 5);
+    int opcode = extract32(insn, 11, 5);
+    int rm = extract32(insn, 16, 5);
+    int size = extract32(insn, 22, 2);
+    bool u = extract32(insn, 29, 1);
+    TCGv_i64 tcg_rn;
+    TCGv_i64 tcg_rm;
+    TCGv_i64 tcg_rd;
+
+    if (opcode >= 0x18) {
+        /* Floating point: U, size[1] and opcode indicate operation */
+        int fpopcode = opcode | (extract32(size, 1, 1) << 5) | (u << 6);
+        switch (fpopcode) {
+        case 0x1b: /* FMULX */
+        case 0x1c: /* FCMEQ */
+        case 0x1f: /* FRECPS */
+        case 0x3f: /* FRSQRTS */
+        case 0x5c: /* FCMGE */
+        case 0x5d: /* FACGE */
+        case 0x7a: /* FABD  */
+        case 0x7c: /* FCMGT */
+        case 0x7d: /* FACGT */
+            unsupported_encoding(s, insn);
+            return;
+        default:
+            unallocated_encoding(s);
+            return;
+        }
+    }
+
+    switch (opcode) {
+    case 0x1: /* SQADD, UQADD */
+    case 0x5: /* SQSUB, UQSUB */
+    case 0x8: /* SSHL, USHL */
+    case 0xa: /* SRSHL, URSHL */
+        unsupported_encoding(s, insn);
+        return;
+    case 0x6: /* CMGT, CMHI */
+    case 0x7: /* CMGE, CMHS */
+    case 0x11: /* CMTST, CMEQ */
+    case 0x10: /* ADD, SUB (vector) */
+        if (size != 3) {
+            unallocated_encoding(s);
+            return;
+        }
+        break;
+    case 0x9: /* SQSHL, UQSHL */
+    case 0xb: /* SQRSHL, UQRSHL */
+        unsupported_encoding(s, insn);
+        return;
+    case 0x16: /* SQDMULH, SQRDMULH (vector) */
+        if (size != 1 && size != 2) {
+            unallocated_encoding(s);
+            return;
+        }
+        unsupported_encoding(s, insn);
+        return;
+    default:
+        unallocated_encoding(s);
+        return;
+    }
+
+    tcg_rn = read_fp_dreg(s, rn);       /* op1 */
+    tcg_rm = read_fp_dreg(s, rm);       /* op2 */
+    tcg_rd = tcg_temp_new_i64();
+
+    /* For the moment we only support the opcodes which are
+     * 64-bit-width only. The size != 3 cases will
+     * be handled later when the relevant ops are implemented.
+     */
+    handle_3same_64(s, opcode, u, tcg_rd, tcg_rn, tcg_rm);
+
+    write_fp_dreg(s, rd, tcg_rd);
+
+    tcg_temp_free_i64(tcg_rn);
+    tcg_temp_free_i64(tcg_rm);
+    tcg_temp_free_i64(tcg_rd);
 }
 
 /* C3.6.12 AdvSIMD scalar two reg misc

From e1cea1144aff6498ddbcd60e2bff4172869b10d4 Mon Sep 17 00:00:00 2001
From: Peter Maydell <peter.maydell@linaro.org>
Date: Fri, 31 Jan 2014 14:47:37 +0000
Subject: [PATCH 28/34] target-arm: A64: Add top level decode for SIMD 3-same
 group

Add top level decode for the A64 SIMD three regs same group
(C3.6.16), splitting it into the pairwise, logical, float and
integer subgroups.

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <rth@twiddle.net>
---
 target-arm/translate-a64.c | 45 +++++++++++++++++++++++++++++++++++++-
 1 file changed, 44 insertions(+), 1 deletion(-)

diff --git a/target-arm/translate-a64.c b/target-arm/translate-a64.c
index f0ebbb534a..a215f083e0 100644
--- a/target-arm/translate-a64.c
+++ b/target-arm/translate-a64.c
@@ -5920,6 +5920,30 @@ static void disas_simd_three_reg_diff(DisasContext *s, uint32_t insn)
     }
 }
 
+/* Logic op (opcode == 3) subgroup of C3.6.16. */
+static void disas_simd_3same_logic(DisasContext *s, uint32_t insn)
+{
+    unsupported_encoding(s, insn);
+}
+
+/* Pairwise op subgroup of C3.6.16. */
+static void disas_simd_3same_pair(DisasContext *s, uint32_t insn)
+{
+    unsupported_encoding(s, insn);
+}
+
+/* Floating point op subgroup of C3.6.16. */
+static void disas_simd_3same_float(DisasContext *s, uint32_t insn)
+{
+    unsupported_encoding(s, insn);
+}
+
+/* Integer op subgroup of C3.6.16. */
+static void disas_simd_3same_int(DisasContext *s, uint32_t insn)
+{
+    unsupported_encoding(s, insn);
+}
+
 /* C3.6.16 AdvSIMD three same
  *  31  30  29  28       24 23  22  21 20  16 15    11  10 9    5 4    0
  * +---+---+---+-----------+------+---+------+--------+---+------+------+
@@ -5928,7 +5952,26 @@ static void disas_simd_three_reg_diff(DisasContext *s, uint32_t insn)
  */
 static void disas_simd_three_reg_same(DisasContext *s, uint32_t insn)
 {
-    unsupported_encoding(s, insn);
+    int opcode = extract32(insn, 11, 5);
+
+    switch (opcode) {
+    case 0x3: /* logic ops */
+        disas_simd_3same_logic(s, insn);
+        break;
+    case 0x17: /* ADDP */
+    case 0x14: /* SMAXP, UMAXP */
+    case 0x15: /* SMINP, UMINP */
+        /* Pairwise operations */
+        disas_simd_3same_pair(s, insn);
+        break;
+    case 0x18 ... 0x31:
+        /* floating point ops, sz[1] and U are part of opcode */
+        disas_simd_3same_float(s, insn);
+        break;
+    default:
+        disas_simd_3same_int(s, insn);
+        break;
+    }
 }
 
 /* C3.6.17 AdvSIMD two reg misc

From 956d272eb2996e4d95f8a674256f8a63a0c1e8d4 Mon Sep 17 00:00:00 2001
From: Peter Maydell <peter.maydell@linaro.org>
Date: Fri, 31 Jan 2014 14:47:37 +0000
Subject: [PATCH 29/34] target-arm: A64: Add logic ops from SIMD 3 same group
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add support for the logical operations (ORR, AND, BIC, ORN, EOR, BSL,
BIT and BIF) from the SIMD 3 register same group (C3.6.16).

Signed-off-by: Alex Bennée <alex.bennee@linaro.org>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <rth@twiddle.net>
---
 target-arm/translate-a64.c | 73 +++++++++++++++++++++++++++++++++++++-
 1 file changed, 72 insertions(+), 1 deletion(-)

diff --git a/target-arm/translate-a64.c b/target-arm/translate-a64.c
index a215f083e0..aa53ddc381 100644
--- a/target-arm/translate-a64.c
+++ b/target-arm/translate-a64.c
@@ -5923,7 +5923,78 @@ static void disas_simd_three_reg_diff(DisasContext *s, uint32_t insn)
 /* Logic op (opcode == 3) subgroup of C3.6.16. */
 static void disas_simd_3same_logic(DisasContext *s, uint32_t insn)
 {
-    unsupported_encoding(s, insn);
+    int rd = extract32(insn, 0, 5);
+    int rn = extract32(insn, 5, 5);
+    int rm = extract32(insn, 16, 5);
+    int size = extract32(insn, 22, 2);
+    bool is_u = extract32(insn, 29, 1);
+    bool is_q = extract32(insn, 30, 1);
+    TCGv_i64 tcg_op1 = tcg_temp_new_i64();
+    TCGv_i64 tcg_op2 = tcg_temp_new_i64();
+    TCGv_i64 tcg_res[2];
+    int pass;
+
+    tcg_res[0] = tcg_temp_new_i64();
+    tcg_res[1] = tcg_temp_new_i64();
+
+    for (pass = 0; pass < (is_q ? 2 : 1); pass++) {
+        read_vec_element(s, tcg_op1, rn, pass, MO_64);
+        read_vec_element(s, tcg_op2, rm, pass, MO_64);
+
+        if (!is_u) {
+            switch (size) {
+            case 0: /* AND */
+                tcg_gen_and_i64(tcg_res[pass], tcg_op1, tcg_op2);
+                break;
+            case 1: /* BIC */
+                tcg_gen_andc_i64(tcg_res[pass], tcg_op1, tcg_op2);
+                break;
+            case 2: /* ORR */
+                tcg_gen_or_i64(tcg_res[pass], tcg_op1, tcg_op2);
+                break;
+            case 3: /* ORN */
+                tcg_gen_orc_i64(tcg_res[pass], tcg_op1, tcg_op2);
+                break;
+            }
+        } else {
+            if (size != 0) {
+                /* B* ops need res loaded to operate on */
+                read_vec_element(s, tcg_res[pass], rd, pass, MO_64);
+            }
+
+            switch (size) {
+            case 0: /* EOR */
+                tcg_gen_xor_i64(tcg_res[pass], tcg_op1, tcg_op2);
+                break;
+            case 1: /* BSL bitwise select */
+                tcg_gen_xor_i64(tcg_op1, tcg_op1, tcg_op2);
+                tcg_gen_and_i64(tcg_op1, tcg_op1, tcg_res[pass]);
+                tcg_gen_xor_i64(tcg_res[pass], tcg_op2, tcg_op1);
+                break;
+            case 2: /* BIT, bitwise insert if true */
+                tcg_gen_xor_i64(tcg_op1, tcg_op1, tcg_res[pass]);
+                tcg_gen_and_i64(tcg_op1, tcg_op1, tcg_op2);
+                tcg_gen_xor_i64(tcg_res[pass], tcg_res[pass], tcg_op1);
+                break;
+            case 3: /* BIF, bitwise insert if false */
+                tcg_gen_xor_i64(tcg_op1, tcg_op1, tcg_res[pass]);
+                tcg_gen_andc_i64(tcg_op1, tcg_op1, tcg_op2);
+                tcg_gen_xor_i64(tcg_res[pass], tcg_res[pass], tcg_op1);
+                break;
+            }
+        }
+    }
+
+    write_vec_element(s, tcg_res[0], rd, 0, MO_64);
+    if (!is_q) {
+        tcg_gen_movi_i64(tcg_res[1], 0);
+    }
+    write_vec_element(s, tcg_res[1], rd, 1, MO_64);
+
+    tcg_temp_free_i64(tcg_op1);
+    tcg_temp_free_i64(tcg_op2);
+    tcg_temp_free_i64(tcg_res[0]);
+    tcg_temp_free_i64(tcg_res[1]);
 }
 
 /* Pairwise op subgroup of C3.6.16. */

From 1f8a73af12ddfb9cf9a90261338b466b7dbf7ab9 Mon Sep 17 00:00:00 2001
From: Peter Maydell <peter.maydell@linaro.org>
Date: Fri, 31 Jan 2014 14:47:37 +0000
Subject: [PATCH 30/34] target-arm: A64: Add integer ops from SIMD 3-same group

Add some of the integer operations in the SIMD 3-same group:
specifically, the comparisons, addition and subtraction.

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <rth@twiddle.net>
---
 target-arm/translate-a64.c | 165 ++++++++++++++++++++++++++++++++++++-
 1 file changed, 164 insertions(+), 1 deletion(-)

diff --git a/target-arm/translate-a64.c b/target-arm/translate-a64.c
index aa53ddc381..9e7401c5a3 100644
--- a/target-arm/translate-a64.c
+++ b/target-arm/translate-a64.c
@@ -72,6 +72,9 @@ typedef struct AArch64DecodeTable {
     AArch64DecodeFn *disas_fn;
 } AArch64DecodeTable;
 
+/* Function prototype for gen_ functions for calling Neon helpers */
+typedef void NeonGenTwoOpFn(TCGv_i32, TCGv_i32, TCGv_i32);
+
 /* initialize TCG globals.  */
 void a64_translate_init(void)
 {
@@ -787,6 +790,25 @@ static void write_vec_element(DisasContext *s, TCGv_i64 tcg_src, int destidx,
     }
 }
 
+static void write_vec_element_i32(DisasContext *s, TCGv_i32 tcg_src,
+                                  int destidx, int element, TCGMemOp memop)
+{
+    int vect_off = vec_reg_offset(destidx, element, memop & MO_SIZE);
+    switch (memop) {
+    case MO_8:
+        tcg_gen_st8_i32(tcg_src, cpu_env, vect_off);
+        break;
+    case MO_16:
+        tcg_gen_st16_i32(tcg_src, cpu_env, vect_off);
+        break;
+    case MO_32:
+        tcg_gen_st_i32(tcg_src, cpu_env, vect_off);
+        break;
+    default:
+        g_assert_not_reached();
+    }
+}
+
 /* Clear the high 64 bits of a 128 bit vector (in general non-quad
  * vector ops all need to do this).
  */
@@ -6012,7 +6034,148 @@ static void disas_simd_3same_float(DisasContext *s, uint32_t insn)
 /* Integer op subgroup of C3.6.16. */
 static void disas_simd_3same_int(DisasContext *s, uint32_t insn)
 {
-    unsupported_encoding(s, insn);
+    int is_q = extract32(insn, 30, 1);
+    int u = extract32(insn, 29, 1);
+    int size = extract32(insn, 22, 2);
+    int opcode = extract32(insn, 11, 5);
+    int rm = extract32(insn, 16, 5);
+    int rn = extract32(insn, 5, 5);
+    int rd = extract32(insn, 0, 5);
+    int pass;
+
+    switch (opcode) {
+    case 0x13: /* MUL, PMUL */
+        if (u && size != 0) {
+            unallocated_encoding(s);
+            return;
+        }
+        /* fall through */
+    case 0x0: /* SHADD, UHADD */
+    case 0x2: /* SRHADD, URHADD */
+    case 0x4: /* SHSUB, UHSUB */
+    case 0xc: /* SMAX, UMAX */
+    case 0xd: /* SMIN, UMIN */
+    case 0xe: /* SABD, UABD */
+    case 0xf: /* SABA, UABA */
+    case 0x12: /* MLA, MLS */
+        if (size == 3) {
+            unallocated_encoding(s);
+            return;
+        }
+        unsupported_encoding(s, insn);
+        return;
+    case 0x1: /* SQADD */
+    case 0x5: /* SQSUB */
+    case 0x8: /* SSHL, USHL */
+    case 0x9: /* SQSHL, UQSHL */
+    case 0xa: /* SRSHL, URSHL */
+    case 0xb: /* SQRSHL, UQRSHL */
+        if (size == 3 && !is_q) {
+            unallocated_encoding(s);
+            return;
+        }
+        unsupported_encoding(s, insn);
+        return;
+    case 0x16: /* SQDMULH, SQRDMULH */
+        if (size == 0 || size == 3) {
+            unallocated_encoding(s);
+            return;
+        }
+        unsupported_encoding(s, insn);
+        return;
+    default:
+        if (size == 3 && !is_q) {
+            unallocated_encoding(s);
+            return;
+        }
+        break;
+    }
+
+    if (size == 3) {
+        for (pass = 0; pass < (is_q ? 2 : 1); pass++) {
+            TCGv_i64 tcg_op1 = tcg_temp_new_i64();
+            TCGv_i64 tcg_op2 = tcg_temp_new_i64();
+            TCGv_i64 tcg_res = tcg_temp_new_i64();
+
+            read_vec_element(s, tcg_op1, rn, pass, MO_64);
+            read_vec_element(s, tcg_op2, rm, pass, MO_64);
+
+            handle_3same_64(s, opcode, u, tcg_res, tcg_op1, tcg_op2);
+
+            write_vec_element(s, tcg_res, rd, pass, MO_64);
+
+            tcg_temp_free_i64(tcg_res);
+            tcg_temp_free_i64(tcg_op1);
+            tcg_temp_free_i64(tcg_op2);
+        }
+    } else {
+        for (pass = 0; pass < (is_q ? 4 : 2); pass++) {
+            TCGv_i32 tcg_op1 = tcg_temp_new_i32();
+            TCGv_i32 tcg_op2 = tcg_temp_new_i32();
+            TCGv_i32 tcg_res = tcg_temp_new_i32();
+            NeonGenTwoOpFn *genfn;
+
+            read_vec_element_i32(s, tcg_op1, rn, pass, MO_32);
+            read_vec_element_i32(s, tcg_op2, rm, pass, MO_32);
+
+            switch (opcode) {
+            case 0x6: /* CMGT, CMHI */
+            {
+                static NeonGenTwoOpFn * const fns[3][2] = {
+                    { gen_helper_neon_cgt_s8, gen_helper_neon_cgt_u8 },
+                    { gen_helper_neon_cgt_s16, gen_helper_neon_cgt_u16 },
+                    { gen_helper_neon_cgt_s32, gen_helper_neon_cgt_u32 },
+                };
+                genfn = fns[size][u];
+                break;
+            }
+            case 0x7: /* CMGE, CMHS */
+            {
+                static NeonGenTwoOpFn * const fns[3][2] = {
+                    { gen_helper_neon_cge_s8, gen_helper_neon_cge_u8 },
+                    { gen_helper_neon_cge_s16, gen_helper_neon_cge_u16 },
+                    { gen_helper_neon_cge_s32, gen_helper_neon_cge_u32 },
+                };
+                genfn = fns[size][u];
+                break;
+            }
+            case 0x10: /* ADD, SUB */
+            {
+                static NeonGenTwoOpFn * const fns[3][2] = {
+                    { gen_helper_neon_add_u8, gen_helper_neon_sub_u8 },
+                    { gen_helper_neon_add_u16, gen_helper_neon_sub_u16 },
+                    { tcg_gen_add_i32, tcg_gen_sub_i32 },
+                };
+                genfn = fns[size][u];
+                break;
+            }
+            case 0x11: /* CMTST, CMEQ */
+            {
+                static NeonGenTwoOpFn * const fns[3][2] = {
+                    { gen_helper_neon_tst_u8, gen_helper_neon_ceq_u8 },
+                    { gen_helper_neon_tst_u16, gen_helper_neon_ceq_u16 },
+                    { gen_helper_neon_tst_u32, gen_helper_neon_ceq_u32 },
+                };
+                genfn = fns[size][u];
+                break;
+            }
+            default:
+                g_assert_not_reached();
+            }
+
+            genfn(tcg_res, tcg_op1, tcg_op2);
+
+            write_vec_element_i32(s, tcg_res, rd, pass, MO_32);
+
+            tcg_temp_free_i32(tcg_res);
+            tcg_temp_free_i32(tcg_op1);
+            tcg_temp_free_i32(tcg_op2);
+        }
+    }
+
+    if (!is_q) {
+        clear_vec_high(s, rd);
+    }
 }
 
 /* C3.6.16 AdvSIMD three same

From 845ea09acc4b5ab8335530aaaf94531c368ba934 Mon Sep 17 00:00:00 2001
From: Peter Maydell <peter.maydell@linaro.org>
Date: Fri, 31 Jan 2014 14:47:37 +0000
Subject: [PATCH 31/34] target-arm: A64: Add simple SIMD 3-same floating point
 ops

Implement a simple subset of the SIMD 3-same floating point
operations. This includes a common helper function used for both
scalar and vector ops; FABD is the only currently implemented
shared op.

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <rth@twiddle.net>
---
 target-arm/translate-a64.c | 190 ++++++++++++++++++++++++++++++++++++-
 1 file changed, 188 insertions(+), 2 deletions(-)

diff --git a/target-arm/translate-a64.c b/target-arm/translate-a64.c
index 9e7401c5a3..509982c91e 100644
--- a/target-arm/translate-a64.c
+++ b/target-arm/translate-a64.c
@@ -5577,6 +5577,131 @@ static void handle_3same_64(DisasContext *s, int opcode, bool u,
     }
 }
 
+/* Handle the 3-same-operands float operations; shared by the scalar
+ * and vector encodings. The caller must filter out any encodings
+ * not allocated for the encoding it is dealing with.
+ */
+static void handle_3same_float(DisasContext *s, int size, int elements,
+                               int fpopcode, int rd, int rn, int rm)
+{
+    int pass;
+    TCGv_ptr fpst = get_fpstatus_ptr();
+
+    for (pass = 0; pass < elements; pass++) {
+        if (size) {
+            /* Double */
+            TCGv_i64 tcg_op1 = tcg_temp_new_i64();
+            TCGv_i64 tcg_op2 = tcg_temp_new_i64();
+            TCGv_i64 tcg_res = tcg_temp_new_i64();
+
+            read_vec_element(s, tcg_op1, rn, pass, MO_64);
+            read_vec_element(s, tcg_op2, rm, pass, MO_64);
+
+            switch (fpopcode) {
+            case 0x18: /* FMAXNM */
+                gen_helper_vfp_maxnumd(tcg_res, tcg_op1, tcg_op2, fpst);
+                break;
+            case 0x1a: /* FADD */
+                gen_helper_vfp_addd(tcg_res, tcg_op1, tcg_op2, fpst);
+                break;
+            case 0x1e: /* FMAX */
+                gen_helper_vfp_maxd(tcg_res, tcg_op1, tcg_op2, fpst);
+                break;
+            case 0x38: /* FMINNM */
+                gen_helper_vfp_minnumd(tcg_res, tcg_op1, tcg_op2, fpst);
+                break;
+            case 0x3a: /* FSUB */
+                gen_helper_vfp_subd(tcg_res, tcg_op1, tcg_op2, fpst);
+                break;
+            case 0x3e: /* FMIN */
+                gen_helper_vfp_mind(tcg_res, tcg_op1, tcg_op2, fpst);
+                break;
+            case 0x5b: /* FMUL */
+                gen_helper_vfp_muld(tcg_res, tcg_op1, tcg_op2, fpst);
+                break;
+            case 0x5f: /* FDIV */
+                gen_helper_vfp_divd(tcg_res, tcg_op1, tcg_op2, fpst);
+                break;
+            case 0x7a: /* FABD */
+                gen_helper_vfp_subd(tcg_res, tcg_op1, tcg_op2, fpst);
+                gen_helper_vfp_absd(tcg_res, tcg_res);
+                break;
+            default:
+                g_assert_not_reached();
+            }
+
+            write_vec_element(s, tcg_res, rd, pass, MO_64);
+
+            tcg_temp_free_i64(tcg_res);
+            tcg_temp_free_i64(tcg_op1);
+            tcg_temp_free_i64(tcg_op2);
+        } else {
+            /* Single */
+            TCGv_i32 tcg_op1 = tcg_temp_new_i32();
+            TCGv_i32 tcg_op2 = tcg_temp_new_i32();
+            TCGv_i32 tcg_res = tcg_temp_new_i32();
+
+            read_vec_element_i32(s, tcg_op1, rn, pass, MO_32);
+            read_vec_element_i32(s, tcg_op2, rm, pass, MO_32);
+
+            switch (fpopcode) {
+            case 0x1a: /* FADD */
+                gen_helper_vfp_adds(tcg_res, tcg_op1, tcg_op2, fpst);
+                break;
+            case 0x1e: /* FMAX */
+                gen_helper_vfp_maxs(tcg_res, tcg_op1, tcg_op2, fpst);
+                break;
+            case 0x18: /* FMAXNM */
+                gen_helper_vfp_maxnums(tcg_res, tcg_op1, tcg_op2, fpst);
+                break;
+            case 0x38: /* FMINNM */
+                gen_helper_vfp_minnums(tcg_res, tcg_op1, tcg_op2, fpst);
+                break;
+            case 0x3a: /* FSUB */
+                gen_helper_vfp_subs(tcg_res, tcg_op1, tcg_op2, fpst);
+                break;
+            case 0x3e: /* FMIN */
+                gen_helper_vfp_mins(tcg_res, tcg_op1, tcg_op2, fpst);
+                break;
+            case 0x5b: /* FMUL */
+                gen_helper_vfp_muls(tcg_res, tcg_op1, tcg_op2, fpst);
+                break;
+            case 0x5f: /* FDIV */
+                gen_helper_vfp_divs(tcg_res, tcg_op1, tcg_op2, fpst);
+                break;
+            case 0x7a: /* FABD */
+                gen_helper_vfp_subs(tcg_res, tcg_op1, tcg_op2, fpst);
+                gen_helper_vfp_abss(tcg_res, tcg_res);
+                break;
+            default:
+                g_assert_not_reached();
+            }
+
+            if (elements == 1) {
+                /* scalar single so clear high part */
+                TCGv_i64 tcg_tmp = tcg_temp_new_i64();
+
+                tcg_gen_extu_i32_i64(tcg_tmp, tcg_res);
+                write_vec_element(s, tcg_tmp, rd, pass, MO_64);
+                tcg_temp_free_i64(tcg_tmp);
+            } else {
+                write_vec_element_i32(s, tcg_res, rd, pass, MO_32);
+            }
+
+            tcg_temp_free_i32(tcg_res);
+            tcg_temp_free_i32(tcg_op1);
+            tcg_temp_free_i32(tcg_op2);
+        }
+    }
+
+    tcg_temp_free_ptr(fpst);
+
+    if ((elements << size) < 4) {
+        /* scalar, or non-quad vector op */
+        clear_vec_high(s, rd);
+    }
+}
+
 /* C3.6.11 AdvSIMD scalar three same
  *  31 30  29 28       24 23  22  21 20  16 15    11  10 9    5 4    0
  * +-----+---+-----------+------+---+------+--------+---+------+------+
@@ -5605,15 +5730,19 @@ static void disas_simd_scalar_three_reg_same(DisasContext *s, uint32_t insn)
         case 0x3f: /* FRSQRTS */
         case 0x5c: /* FCMGE */
         case 0x5d: /* FACGE */
-        case 0x7a: /* FABD  */
         case 0x7c: /* FCMGT */
         case 0x7d: /* FACGT */
             unsupported_encoding(s, insn);
             return;
+        case 0x7a: /* FABD */
+            break;
         default:
             unallocated_encoding(s);
             return;
         }
+
+        handle_3same_float(s, extract32(size, 0, 1), 1, fpopcode, rd, rn, rm);
+        return;
     }
 
     switch (opcode) {
@@ -6028,7 +6157,64 @@ static void disas_simd_3same_pair(DisasContext *s, uint32_t insn)
 /* Floating point op subgroup of C3.6.16. */
 static void disas_simd_3same_float(DisasContext *s, uint32_t insn)
 {
-    unsupported_encoding(s, insn);
+    /* For floating point ops, the U, size[1] and opcode bits
+     * together indicate the operation. size[0] indicates single
+     * or double.
+     */
+    int fpopcode = extract32(insn, 11, 5)
+        | (extract32(insn, 23, 1) << 5)
+        | (extract32(insn, 29, 1) << 6);
+    int is_q = extract32(insn, 30, 1);
+    int size = extract32(insn, 22, 1);
+    int rm = extract32(insn, 16, 5);
+    int rn = extract32(insn, 5, 5);
+    int rd = extract32(insn, 0, 5);
+
+    int datasize = is_q ? 128 : 64;
+    int esize = 32 << size;
+    int elements = datasize / esize;
+
+    if (size == 1 && !is_q) {
+        unallocated_encoding(s);
+        return;
+    }
+
+    switch (fpopcode) {
+    case 0x58: /* FMAXNMP */
+    case 0x5a: /* FADDP */
+    case 0x5e: /* FMAXP */
+    case 0x78: /* FMINNMP */
+    case 0x7e: /* FMINP */
+        /* pairwise ops */
+        unsupported_encoding(s, insn);
+        return;
+    case 0x1b: /* FMULX */
+    case 0x1c: /* FCMEQ */
+    case 0x1f: /* FRECPS */
+    case 0x3f: /* FRSQRTS */
+    case 0x5c: /* FCMGE */
+    case 0x5d: /* FACGE */
+    case 0x7c: /* FCMGT */
+    case 0x7d: /* FACGT */
+    case 0x19: /* FMLA */
+    case 0x39: /* FMLS */
+        unsupported_encoding(s, insn);
+        return;
+    case 0x18: /* FMAXNM */
+    case 0x1a: /* FADD */
+    case 0x1e: /* FMAX */
+    case 0x38: /* FMINNM */
+    case 0x3a: /* FSUB */
+    case 0x3e: /* FMIN */
+    case 0x5b: /* FMUL */
+    case 0x5f: /* FDIV */
+    case 0x7a: /* FABD */
+        handle_3same_float(s, size, elements, fpopcode, rd, rn, rm);
+        return;
+    default:
+        unallocated_encoding(s);
+        return;
+    }
 }
 
 /* Integer op subgroup of C3.6.16. */

From 4d1cef840d526c80244175c208260f165f9226db Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Alex=20Benn=C3=A9e?= <alex.bennee@linaro.org>
Date: Fri, 31 Jan 2014 14:47:37 +0000
Subject: [PATCH 32/34] target-arm: A64: Add SIMD shift by immediate
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This implements a subset of the AdvSIMD shift operations (namely all the
none saturating or narrowing ones). The actual shift generation code
itself is common for both the scalar and vector cases but wrapped with
either vector element iteration or the fp reg access.

The rounding operations need to take special care to correctly reflect
the result of adding rounding bits on high bits as the intermediates do
not truncate.

Signed-off-by: Alex Bennée <alex.bennee@linaro.org>
Reviewed-by: Richard Henderson <rth@twiddle.net>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target-arm/translate-a64.c | 375 ++++++++++++++++++++++++++++++++++++-
 1 file changed, 373 insertions(+), 2 deletions(-)

diff --git a/target-arm/translate-a64.c b/target-arm/translate-a64.c
index 509982c91e..6c1ec1edc6 100644
--- a/target-arm/translate-a64.c
+++ b/target-arm/translate-a64.c
@@ -5503,15 +5503,216 @@ static void disas_simd_scalar_pairwise(DisasContext *s, uint32_t insn)
     unsupported_encoding(s, insn);
 }
 
+/*
+ * Common SSHR[RA]/USHR[RA] - Shift right (optional rounding/accumulate)
+ *
+ * This code is handles the common shifting code and is used by both
+ * the vector and scalar code.
+ */
+static void handle_shri_with_rndacc(TCGv_i64 tcg_res, TCGv_i64 tcg_src,
+                                    TCGv_i64 tcg_rnd, bool accumulate,
+                                    bool is_u, int size, int shift)
+{
+    bool extended_result = false;
+    bool round = !TCGV_IS_UNUSED_I64(tcg_rnd);
+    int ext_lshift = 0;
+    TCGv_i64 tcg_src_hi;
+
+    if (round && size == 3) {
+        extended_result = true;
+        ext_lshift = 64 - shift;
+        tcg_src_hi = tcg_temp_new_i64();
+    } else if (shift == 64) {
+        if (!accumulate && is_u) {
+            /* result is zero */
+            tcg_gen_movi_i64(tcg_res, 0);
+            return;
+        }
+    }
+
+    /* Deal with the rounding step */
+    if (round) {
+        if (extended_result) {
+            TCGv_i64 tcg_zero = tcg_const_i64(0);
+            if (!is_u) {
+                /* take care of sign extending tcg_res */
+                tcg_gen_sari_i64(tcg_src_hi, tcg_src, 63);
+                tcg_gen_add2_i64(tcg_src, tcg_src_hi,
+                                 tcg_src, tcg_src_hi,
+                                 tcg_rnd, tcg_zero);
+            } else {
+                tcg_gen_add2_i64(tcg_src, tcg_src_hi,
+                                 tcg_src, tcg_zero,
+                                 tcg_rnd, tcg_zero);
+            }
+            tcg_temp_free_i64(tcg_zero);
+        } else {
+            tcg_gen_add_i64(tcg_src, tcg_src, tcg_rnd);
+        }
+    }
+
+    /* Now do the shift right */
+    if (round && extended_result) {
+        /* extended case, >64 bit precision required */
+        if (ext_lshift == 0) {
+            /* special case, only high bits matter */
+            tcg_gen_mov_i64(tcg_src, tcg_src_hi);
+        } else {
+            tcg_gen_shri_i64(tcg_src, tcg_src, shift);
+            tcg_gen_shli_i64(tcg_src_hi, tcg_src_hi, ext_lshift);
+            tcg_gen_or_i64(tcg_src, tcg_src, tcg_src_hi);
+        }
+    } else {
+        if (is_u) {
+            if (shift == 64) {
+                /* essentially shifting in 64 zeros */
+                tcg_gen_movi_i64(tcg_src, 0);
+            } else {
+                tcg_gen_shri_i64(tcg_src, tcg_src, shift);
+            }
+        } else {
+            if (shift == 64) {
+                /* effectively extending the sign-bit */
+                tcg_gen_sari_i64(tcg_src, tcg_src, 63);
+            } else {
+                tcg_gen_sari_i64(tcg_src, tcg_src, shift);
+            }
+        }
+    }
+
+    if (accumulate) {
+        tcg_gen_add_i64(tcg_res, tcg_res, tcg_src);
+    } else {
+        tcg_gen_mov_i64(tcg_res, tcg_src);
+    }
+
+    if (extended_result) {
+        tcg_temp_free_i64(tcg_src_hi);
+    }
+}
+
+/* Common SHL/SLI - Shift left with an optional insert */
+static void handle_shli_with_ins(TCGv_i64 tcg_res, TCGv_i64 tcg_src,
+                                 bool insert, int shift)
+{
+    if (insert) { /* SLI */
+        tcg_gen_deposit_i64(tcg_res, tcg_res, tcg_src, shift, 64 - shift);
+    } else { /* SHL */
+        tcg_gen_shli_i64(tcg_res, tcg_src, shift);
+    }
+}
+
+/* SSHR[RA]/USHR[RA] - Scalar shift right (optional rounding/accumulate) */
+static void handle_scalar_simd_shri(DisasContext *s,
+                                    bool is_u, int immh, int immb,
+                                    int opcode, int rn, int rd)
+{
+    const int size = 3;
+    int immhb = immh << 3 | immb;
+    int shift = 2 * (8 << size) - immhb;
+    bool accumulate = false;
+    bool round = false;
+    TCGv_i64 tcg_rn;
+    TCGv_i64 tcg_rd;
+    TCGv_i64 tcg_round;
+
+    if (!extract32(immh, 3, 1)) {
+        unallocated_encoding(s);
+        return;
+    }
+
+    switch (opcode) {
+    case 0x02: /* SSRA / USRA (accumulate) */
+        accumulate = true;
+        break;
+    case 0x04: /* SRSHR / URSHR (rounding) */
+        round = true;
+        break;
+    case 0x06: /* SRSRA / URSRA (accum + rounding) */
+        accumulate = round = true;
+        break;
+    }
+
+    if (round) {
+        uint64_t round_const = 1ULL << (shift - 1);
+        tcg_round = tcg_const_i64(round_const);
+    } else {
+        TCGV_UNUSED_I64(tcg_round);
+    }
+
+    tcg_rn = read_fp_dreg(s, rn);
+    tcg_rd = accumulate ? read_fp_dreg(s, rd) : tcg_temp_new_i64();
+
+    handle_shri_with_rndacc(tcg_rd, tcg_rn, tcg_round,
+                               accumulate, is_u, size, shift);
+
+    write_fp_dreg(s, rd, tcg_rd);
+
+    tcg_temp_free_i64(tcg_rn);
+    tcg_temp_free_i64(tcg_rd);
+    if (round) {
+        tcg_temp_free_i64(tcg_round);
+    }
+}
+
+/* SHL/SLI - Scalar shift left */
+static void handle_scalar_simd_shli(DisasContext *s, bool insert,
+                                    int immh, int immb, int opcode,
+                                    int rn, int rd)
+{
+    int size = 32 - clz32(immh) - 1;
+    int immhb = immh << 3 | immb;
+    int shift = immhb - (8 << size);
+    TCGv_i64 tcg_rn = new_tmp_a64(s);
+    TCGv_i64 tcg_rd = new_tmp_a64(s);
+
+    if (!extract32(immh, 3, 1)) {
+        unallocated_encoding(s);
+        return;
+    }
+
+    tcg_rn = read_fp_dreg(s, rn);
+    tcg_rd = insert ? read_fp_dreg(s, rd) : tcg_temp_new_i64();
+
+    handle_shli_with_ins(tcg_rd, tcg_rn, insert, shift);
+
+    write_fp_dreg(s, rd, tcg_rd);
+
+    tcg_temp_free_i64(tcg_rn);
+    tcg_temp_free_i64(tcg_rd);
+}
+
 /* C3.6.9 AdvSIMD scalar shift by immediate
  *  31 30  29 28         23 22  19 18  16 15    11  10 9    5 4    0
  * +-----+---+-------------+------+------+--------+---+------+------+
  * | 0 1 | U | 1 1 1 1 1 0 | immh | immb | opcode | 1 |  Rn  |  Rd  |
  * +-----+---+-------------+------+------+--------+---+------+------+
+ *
+ * This is the scalar version so it works on a fixed sized registers
  */
 static void disas_simd_scalar_shift_imm(DisasContext *s, uint32_t insn)
 {
-    unsupported_encoding(s, insn);
+    int rd = extract32(insn, 0, 5);
+    int rn = extract32(insn, 5, 5);
+    int opcode = extract32(insn, 11, 5);
+    int immb = extract32(insn, 16, 3);
+    int immh = extract32(insn, 19, 4);
+    bool is_u = extract32(insn, 29, 1);
+
+    switch (opcode) {
+    case 0x00: /* SSHR / USHR */
+    case 0x02: /* SSRA / USRA */
+    case 0x04: /* SRSHR / URSHR */
+    case 0x06: /* SRSRA / URSRA */
+        handle_scalar_simd_shri(s, is_u, immh, immb, opcode, rn, rd);
+        break;
+    case 0x0a: /* SHL / SLI */
+        handle_scalar_simd_shli(s, is_u, immh, immb, opcode, rn, rd);
+        break;
+    default:
+        unsupported_encoding(s, insn);
+        break;
+    }
 }
 
 /* C3.6.10 AdvSIMD scalar three different
@@ -5816,6 +6017,148 @@ static void disas_simd_scalar_indexed(DisasContext *s, uint32_t insn)
     unsupported_encoding(s, insn);
 }
 
+/* SSHR[RA]/USHR[RA] - Vector shift right (optional rounding/accumulate) */
+static void handle_vec_simd_shri(DisasContext *s, bool is_q, bool is_u,
+                                 int immh, int immb, int opcode, int rn, int rd)
+{
+    int size = 32 - clz32(immh) - 1;
+    int immhb = immh << 3 | immb;
+    int shift = 2 * (8 << size) - immhb;
+    bool accumulate = false;
+    bool round = false;
+    int dsize = is_q ? 128 : 64;
+    int esize = 8 << size;
+    int elements = dsize/esize;
+    TCGMemOp memop = size | (is_u ? 0 : MO_SIGN);
+    TCGv_i64 tcg_rn = new_tmp_a64(s);
+    TCGv_i64 tcg_rd = new_tmp_a64(s);
+    TCGv_i64 tcg_round;
+    int i;
+
+    if (extract32(immh, 3, 1) && !is_q) {
+        unallocated_encoding(s);
+        return;
+    }
+
+    if (size > 3 && !is_q) {
+        unallocated_encoding(s);
+        return;
+    }
+
+    switch (opcode) {
+    case 0x02: /* SSRA / USRA (accumulate) */
+        accumulate = true;
+        break;
+    case 0x04: /* SRSHR / URSHR (rounding) */
+        round = true;
+        break;
+    case 0x06: /* SRSRA / URSRA (accum + rounding) */
+        accumulate = round = true;
+        break;
+    }
+
+    if (round) {
+        uint64_t round_const = 1ULL << (shift - 1);
+        tcg_round = tcg_const_i64(round_const);
+    } else {
+        TCGV_UNUSED_I64(tcg_round);
+    }
+
+    for (i = 0; i < elements; i++) {
+        read_vec_element(s, tcg_rn, rn, i, memop);
+        if (accumulate) {
+            read_vec_element(s, tcg_rd, rd, i, memop);
+        }
+
+        handle_shri_with_rndacc(tcg_rd, tcg_rn, tcg_round,
+                                accumulate, is_u, size, shift);
+
+        write_vec_element(s, tcg_rd, rd, i, size);
+    }
+
+    if (!is_q) {
+        clear_vec_high(s, rd);
+    }
+
+    if (round) {
+        tcg_temp_free_i64(tcg_round);
+    }
+}
+
+/* SHL/SLI - Vector shift left */
+static void handle_vec_simd_shli(DisasContext *s, bool is_q, bool insert,
+                                int immh, int immb, int opcode, int rn, int rd)
+{
+    int size = 32 - clz32(immh) - 1;
+    int immhb = immh << 3 | immb;
+    int shift = immhb - (8 << size);
+    int dsize = is_q ? 128 : 64;
+    int esize = 8 << size;
+    int elements = dsize/esize;
+    TCGv_i64 tcg_rn = new_tmp_a64(s);
+    TCGv_i64 tcg_rd = new_tmp_a64(s);
+    int i;
+
+    if (extract32(immh, 3, 1) && !is_q) {
+        unallocated_encoding(s);
+        return;
+    }
+
+    if (size > 3 && !is_q) {
+        unallocated_encoding(s);
+        return;
+    }
+
+    for (i = 0; i < elements; i++) {
+        read_vec_element(s, tcg_rn, rn, i, size);
+        if (insert) {
+            read_vec_element(s, tcg_rd, rd, i, size);
+        }
+
+        handle_shli_with_ins(tcg_rd, tcg_rn, insert, shift);
+
+        write_vec_element(s, tcg_rd, rd, i, size);
+    }
+
+    if (!is_q) {
+        clear_vec_high(s, rd);
+    }
+}
+
+/* USHLL/SHLL - Vector shift left with widening */
+static void handle_vec_simd_wshli(DisasContext *s, bool is_q, bool is_u,
+                                 int immh, int immb, int opcode, int rn, int rd)
+{
+    int size = 32 - clz32(immh) - 1;
+    int immhb = immh << 3 | immb;
+    int shift = immhb - (8 << size);
+    int dsize = 64;
+    int esize = 8 << size;
+    int elements = dsize/esize;
+    TCGv_i64 tcg_rn = new_tmp_a64(s);
+    TCGv_i64 tcg_rd = new_tmp_a64(s);
+    int i;
+
+    if (size >= 3) {
+        unallocated_encoding(s);
+        return;
+    }
+
+    /* For the LL variants the store is larger than the load,
+     * so if rd == rn we would overwrite parts of our input.
+     * So load everything right now and use shifts in the main loop.
+     */
+    read_vec_element(s, tcg_rn, rn, is_q ? 1 : 0, MO_64);
+
+    for (i = 0; i < elements; i++) {
+        tcg_gen_shri_i64(tcg_rd, tcg_rn, i * esize);
+        ext_and_shift_reg(tcg_rd, tcg_rd, size | (!is_u << 2), 0);
+        tcg_gen_shli_i64(tcg_rd, tcg_rd, shift);
+        write_vec_element(s, tcg_rd, rd, i, size + 1);
+    }
+}
+
+
 /* C3.6.14 AdvSIMD shift by immediate
  *  31  30   29 28         23 22  19 18  16 15    11  10 9    5 4    0
  * +---+---+---+-------------+------+------+--------+---+------+------+
@@ -5824,7 +6167,35 @@ static void disas_simd_scalar_indexed(DisasContext *s, uint32_t insn)
  */
 static void disas_simd_shift_imm(DisasContext *s, uint32_t insn)
 {
-    unsupported_encoding(s, insn);
+    int rd = extract32(insn, 0, 5);
+    int rn = extract32(insn, 5, 5);
+    int opcode = extract32(insn, 11, 5);
+    int immb = extract32(insn, 16, 3);
+    int immh = extract32(insn, 19, 4);
+    bool is_u = extract32(insn, 29, 1);
+    bool is_q = extract32(insn, 30, 1);
+
+    switch (opcode) {
+    case 0x00: /* SSHR / USHR */
+    case 0x02: /* SSRA / USRA (accumulate) */
+    case 0x04: /* SRSHR / URSHR (rounding) */
+    case 0x06: /* SRSRA / URSRA (accum + rounding) */
+        handle_vec_simd_shri(s, is_q, is_u, immh, immb, opcode, rn, rd);
+        break;
+    case 0x0a: /* SHL / SLI */
+        handle_vec_simd_shli(s, is_q, is_u, immh, immb, opcode, rn, rd);
+        break;
+    case 0x14: /* SSHLL / USHLL */
+        handle_vec_simd_wshli(s, is_q, is_u, immh, immb, opcode, rn, rd);
+        break;
+    default:
+        /* We don't currently implement any of the Narrow or saturating shifts;
+         * nor do we implement the fixed-point conversions in this
+         * encoding group (SCVTF, FCVTZS, UCVTF, FCVTZU).
+         */
+        unsupported_encoding(s, insn);
+        return;
+    }
 }
 
 static void handle_3rd_widening(DisasContext *s, int is_q, int is_u, int size,

From 41ab7b55108e2699e7c2e77788465cb52a0b2c08 Mon Sep 17 00:00:00 2001
From: Christoffer Dall <christoffer.dall@linaro.org>
Date: Fri, 31 Jan 2014 14:47:38 +0000
Subject: [PATCH 33/34] arm_gic: Introduce define for GIC_NR_SGIS

Instead of hardcoding 16 various places in the code, use a define to
make it more clear what is going on.

Signed-off-by: Christoffer Dall <christoffer.dall@linaro.org>
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 hw/intc/arm_gic.c                | 17 +++++++++++------
 include/hw/intc/arm_gic_common.h |  1 +
 2 files changed, 12 insertions(+), 6 deletions(-)

diff --git a/hw/intc/arm_gic.c b/hw/intc/arm_gic.c
index 9409684ce8..98c6ff5ccb 100644
--- a/hw/intc/arm_gic.c
+++ b/hw/intc/arm_gic.c
@@ -380,8 +380,10 @@ static void gic_dist_writeb(void *opaque, hwaddr offset,
         irq = (offset - 0x100) * 8 + GIC_BASE_IRQ;
         if (irq >= s->num_irq)
             goto bad_reg;
-        if (irq < 16)
-          value = 0xff;
+        if (irq < GIC_NR_SGIS) {
+            value = 0xff;
+        }
+
         for (i = 0; i < 8; i++) {
             if (value & (1 << i)) {
                 int mask =
@@ -406,8 +408,10 @@ static void gic_dist_writeb(void *opaque, hwaddr offset,
         irq = (offset - 0x180) * 8 + GIC_BASE_IRQ;
         if (irq >= s->num_irq)
             goto bad_reg;
-        if (irq < 16)
-          value = 0;
+        if (irq < GIC_NR_SGIS) {
+            value = 0;
+        }
+
         for (i = 0; i < 8; i++) {
             if (value & (1 << i)) {
                 int cm = (irq < GIC_INTERNAL) ? (1 << cpu) : ALL_CPU_MASK;
@@ -423,8 +427,9 @@ static void gic_dist_writeb(void *opaque, hwaddr offset,
         irq = (offset - 0x200) * 8 + GIC_BASE_IRQ;
         if (irq >= s->num_irq)
             goto bad_reg;
-        if (irq < 16)
-          irq = 0;
+        if (irq < GIC_NR_SGIS) {
+            irq = 0;
+        }
 
         for (i = 0; i < 8; i++) {
             if (value & (1 << i)) {
diff --git a/include/hw/intc/arm_gic_common.h b/include/hw/intc/arm_gic_common.h
index 0d232dfb67..8a2aa00cee 100644
--- a/include/hw/intc/arm_gic_common.h
+++ b/include/hw/intc/arm_gic_common.h
@@ -27,6 +27,7 @@
 #define GIC_MAXIRQ 1020
 /* First 32 are private to each CPU (SGIs and PPIs). */
 #define GIC_INTERNAL 32
+#define GIC_NR_SGIS 16
 /* Maximum number of possible CPU interfaces, determined by GIC architecture */
 #define GIC_NCPU 8
 

From 5b0adce156216fb24dcc5f1683e8b686f3793fff Mon Sep 17 00:00:00 2001
From: Christoffer Dall <christoffer.dall@linaro.org>
Date: Fri, 31 Jan 2014 14:47:38 +0000
Subject: [PATCH 34/34] arm_gic: Fix GICD_ICPENDR and GICD_ISPENDR writes

Fix two bugs that would allow changing the state of SGIs through the
ICPENDR and ISPENDRs.

Signed-off-by: Christoffer Dall <christoffer.dall@linaro.org>
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 hw/intc/arm_gic.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/hw/intc/arm_gic.c b/hw/intc/arm_gic.c
index 98c6ff5ccb..1c4a1143af 100644
--- a/hw/intc/arm_gic.c
+++ b/hw/intc/arm_gic.c
@@ -428,7 +428,7 @@ static void gic_dist_writeb(void *opaque, hwaddr offset,
         if (irq >= s->num_irq)
             goto bad_reg;
         if (irq < GIC_NR_SGIS) {
-            irq = 0;
+            value = 0;
         }
 
         for (i = 0; i < 8; i++) {
@@ -441,6 +441,10 @@ static void gic_dist_writeb(void *opaque, hwaddr offset,
         irq = (offset - 0x280) * 8 + GIC_BASE_IRQ;
         if (irq >= s->num_irq)
             goto bad_reg;
+        if (irq < GIC_NR_SGIS) {
+            value = 0;
+        }
+
         for (i = 0; i < 8; i++) {
             /* ??? This currently clears the pending bit for all CPUs, even
                for per-CPU interrupts.  It's unclear whether this is the