[Qemu-devel] [PATCH v2 0/8] target-arm: A64 decoder set 3: loads, stores, misc integer

[Qemu-devel] [PATCH v2 0/8] target-arm: A64 decoder set 3: loads, stores, misc integer

[Peter Maydell]

Here's version 2 of the third set of A64 decoder patches
(loads, stores, misc integer).

Changes v1->v2:
 * merged ldp and stp into one function/patch
 * minor cleanup as per RTH review
 * use the new tcg ops for guest load/store
 * catch the missing UNALLOCATED cases for load/store
 * add missing returns after unallocated_encoding() calls
   in vector load/store decode
 * use tcg ops for mul[su]h

thanks
-- PMM

Alex Bennée (6):
  target-arm: A64: add support for ld/st pair
  target-arm: A64: add support for ld/st unsigned imm
  target-arm: A64: add support for ld/st with reg offset
  target-arm: A64: add support for ld/st with index
  target-arm: A64: add support for add, addi, sub, subi
  target-arm: A64: add support for move wide instructions

Alexander Graf (2):
  target-arm: A64: add support for 3 src data proc insns
  target-arm: A64: implement SVC, BRK

 target-arm/translate-a64.c | 1114 +++++++++++++++++++++++++++++++++++++++++++-
 1 file changed, 1092 insertions(+), 22 deletions(-)

-- 
1.8.5

[Qemu-devel] [PATCH v2 1/8] target-arm: A64: add support for ld/st pair

[Peter Maydell]

From: Alex Bennée <alex.bennee@linaro.org>

This patch support the basic load and store pair instructions and
includes the generic helper functions:

  * do_gpr_st()
  * do_fp_st()
  * do_gpr_ld()
  * do_fp_ld()
  * read_cpu_reg_sp()
  * gen_check_sp_alignment()

The last function gen_check_sp_alignment() is a NULL op currently but
put in place to make it easy to add SP alignment checking later.

Signed-off-by: Alex Bennée <alex.bennee@linaro.org>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>

---

Changes
  - merge ldp/stp together
  - add read_cpu_reg_sp() and use
  - only reference registers as needed
  - use common tcg ops for gpr/fp loads/store
---
 target-arm/translate-a64.c | 268 ++++++++++++++++++++++++++++++++++++++++++++-
 1 file changed, 263 insertions(+), 5 deletions(-)

diff --git a/target-arm/translate-a64.c b/target-arm/translate-a64.c
index 0a76130..018b3ee 100644
--- a/target-arm/translate-a64.c
+++ b/target-arm/translate-a64.c
@@ -99,6 +99,15 @@ void aarch64_cpu_dump_state(CPUState *cs, FILE *f,
     cpu_fprintf(f, "\n");
 }
 
+static int get_mem_index(DisasContext *s)
+{
+#ifdef CONFIG_USER_ONLY
+    return 1;
+#else
+    return s->user;
+#endif
+}
+
 void gen_a64_set_pc_im(uint64_t val)
 {
     tcg_gen_movi_i64(cpu_pc, val);
@@ -250,6 +259,17 @@ static TCGv_i64 read_cpu_reg(DisasContext *s, int reg, int sf)
     return v;
 }
 
+static TCGv_i64 read_cpu_reg_sp(DisasContext *s, int reg, int sf)
+{
+    TCGv_i64 v = new_tmp_a64(s);
+    if (sf) {
+        tcg_gen_mov_i64(v, cpu_X[reg]);
+    } else {
+        tcg_gen_ext32u_i64(v, cpu_X[reg]);
+    }
+    return v;
+}
+
 /* Set ZF and NF based on a 64 bit result. This is alas fiddlier
  * than the 32 bit equivalent.
  */
@@ -278,6 +298,124 @@ static inline void gen_logic_CC(int sf, TCGv_i64 result)
 }
 
 /*
+ * Load/Store generators
+ */
+
+/*
+ *  Store from GPR register to memory
+ */
+static void do_gpr_st(DisasContext *s, TCGv_i64 source,
+                      TCGv_i64 tcg_addr, int size)
+{
+    g_assert(size <= 3);
+    tcg_gen_qemu_st_i64(source, tcg_addr, get_mem_index(s), MO_TE + size);
+}
+
+/*
+ * Load from memory to GPR register
+ */
+static void do_gpr_ld(DisasContext *s, TCGv_i64 dest, TCGv_i64 tcg_addr,
+                      int size, bool is_signed, bool extend)
+{
+    TCGMemOp memop =  MO_TE + size;
+
+    g_assert(size <= 3);
+
+    if (is_signed) {
+        memop += MO_SIGN;
+    }
+
+    tcg_gen_qemu_ld_i64(dest, tcg_addr, get_mem_index(s), memop);
+
+    if (extend && is_signed) {
+        g_assert(size < 3);
+        tcg_gen_ext32u_i64(dest, dest);
+    }
+}
+
+/*
+ * Store from FP register to memory
+ */
+static void do_fp_st(DisasContext *s, int srcidx, TCGv_i64 tcg_addr, int size)
+{
+    /* This writes the bottom N bits of a 128 bit wide vector to memory */
+    int freg_offs = offsetof(CPUARMState, vfp.regs[srcidx * 2]);
+    TCGv_i64 tmp = tcg_temp_new_i64();
+
+    if (size < 4) {
+        switch (size) {
+        case 0:
+            tcg_gen_ld8u_i64(tmp, cpu_env, freg_offs);
+            break;
+        case 1:
+            tcg_gen_ld16u_i64(tmp, cpu_env, freg_offs);
+            break;
+        case 2:
+            tcg_gen_ld32u_i64(tmp, cpu_env, freg_offs);
+            break;
+        case 3:
+            tcg_gen_ld_i64(tmp, cpu_env, freg_offs);
+            break;
+        }
+        tcg_gen_qemu_st_i64(tmp, tcg_addr, get_mem_index(s), MO_TE + size);
+    } else {
+        TCGv_i64 tcg_hiaddr = tcg_temp_new_i64();
+        tcg_gen_ld_i64(tmp, cpu_env, freg_offs);
+        tcg_gen_qemu_st_i64(tmp, tcg_addr, get_mem_index(s), MO_TEQ);
+        tcg_gen_qemu_st64(tmp, tcg_addr, get_mem_index(s));
+        tcg_gen_ld_i64(tmp, cpu_env, freg_offs + sizeof(float64));
+        tcg_gen_addi_i64(tcg_hiaddr, tcg_addr, 8);
+        tcg_gen_qemu_st_i64(tmp, tcg_hiaddr, get_mem_index(s), MO_TEQ);
+        tcg_temp_free_i64(tcg_hiaddr);
+    }
+
+    tcg_temp_free_i64(tmp);
+}
+
+/* Load from memory to FP register */
+static void do_fp_ld(DisasContext *s, int destidx, TCGv_i64 tcg_addr, int size)
+{
+    /* This always zero-extends and writes to a full 128 bit wide vector */
+    int freg_offs = offsetof(CPUARMState, vfp.regs[destidx * 2]);
+    TCGv_i64 tmplo = tcg_temp_new_i64();
+    TCGv_i64 tmphi;
+
+    if (size < 4) {
+        TCGMemOp memop =  MO_TE + size;
+        tmphi = tcg_const_i64(0);
+        tcg_gen_qemu_ld_i64(tmplo, tcg_addr, get_mem_index(s), memop);
+    } else {
+        TCGv_i64 tcg_hiaddr;
+        tmphi = tcg_temp_new_i64();
+        tcg_hiaddr = tcg_temp_new_i64();
+
+        tcg_gen_qemu_ld_i64(tmplo, tcg_addr, get_mem_index(s), MO_TEQ);
+        tcg_gen_addi_i64(tcg_hiaddr, tcg_addr, 8);
+        tcg_gen_qemu_ld_i64(tmphi, tcg_hiaddr, get_mem_index(s), MO_TEQ);
+        tcg_temp_free_i64(tcg_hiaddr);
+    }
+
+    tcg_gen_st_i64(tmplo, cpu_env, freg_offs);
+    tcg_gen_st_i64(tmphi, cpu_env, freg_offs + sizeof(float64));
+
+    tcg_temp_free_i64(tmplo);
+    tcg_temp_free_i64(tmphi);
+}
+
+static inline void gen_check_sp_alignment(DisasContext *s)
+{
+    /* The AArch64 architecture mandates that (if enabled via PSTATE
+     * or SCTLR bits) there is a check that SP is 16-aligned on every
+     * SP-relative load or store (with an exception generated if it is not).
+     * In line with general QEMU practice regarding misaligned accesses,
+     * we omit these checks for the sake of guest program performance.
+     * This function is provided as a hook so we can more easily add these
+     * checks in future (possibly as a "favour catching guest program bugs
+     * over speed" user selectable option).
+     */
+}
+
+/*
  * the instruction disassembly implemented here matches
  * the instruction encoding classifications in chapter 3 (C3)
  * of the ARM Architecture Reference Manual (DDI0487A_a)
@@ -620,10 +758,130 @@ static void disas_ld_lit(DisasContext *s, uint32_t insn)
     unsupported_encoding(s, insn);
 }
 
-/* Load/store pair (all forms) */
-static void disas_ldst_pair(DisasContext *s, uint32_t insn)
-{
-    unsupported_encoding(s, insn);
+/*
+ * C5.6.81 LDP (Load Pair - non vector)
+ * C5.6.82 LDPSW (Load Pair Signed Word - non vector)
+ * C5.6.177 STP (Store Pair - non vector)
+ * C6.3.165 LDP (Load Pair of SIMD&FP)
+ * C6.3.284 STP (Store Pair of SIMD&FP)
+ *
+ *  31 30 29   27  26 25   23  22 21   15 14   10 9    5 4    0
+ * +-----+-------+---+-------+---+-----------------------------+
+ * | opc | 1 0 1 | V | index | L |  imm7 |  Rt2  |  Rn  | Rt   |
+ * +-----+-------+---+-------+---+-------+-------+------+------+
+ *
+ * opc: LDP&STP       00 -> 32 bit, 10 -> 64 bit
+ *      LDPSW         01
+ *      LDP&STP(SIMD) 00 -> 32 bit, 01 -> 64 bit, 10 -> 128 bit
+ *   V: 0 -> GPR, 1 -> Vector
+ * idx: 001 -> post-index, 011 -> pre-index, 010 -> signed off
+ *   L: 0 -> Store 1 -> Load
+ *
+ * Rt, Rt2 = GPR or SIMD registers to be stored
+ * Rn = general purpose register containing address
+ * imm7 = signed offset (multiple of 4 or 8 depending on size)
+ */
+static void handle_ldst_pair(DisasContext *s, uint32_t insn)
+{
+    int rt = extract32(insn, 0, 5);
+    int rn = extract32(insn, 5, 5);
+    int rt2 = extract32(insn, 10, 5);
+    int64_t offset = sextract32(insn, 15, 7);
+    int index = extract32(insn, 23, 2);
+    bool is_vector = extract32(insn, 26, 1);
+    bool is_load = extract32(insn, 22, 1);
+    int opc = extract32(insn, 30, 2);
+
+    bool is_signed = false;
+    bool postindex = false;
+    bool wback = false;
+
+    TCGv_i64 tcg_addr; /* calculated address */
+    int size;
+
+    if (is_vector) {
+        if (opc == 3) {
+            unallocated_encoding(s);
+            return;
+        }
+        size = 2 + opc;
+    } else {
+        size = 2 + extract32(opc, 1, 1);
+        if (is_load) {
+            is_signed = opc & 1;
+        } else if (opc & 1) {
+            unallocated_encoding(s);
+            return;
+        }
+    }
+
+    switch (index) {
+    case 1: /* post-index */
+        postindex = true;
+        wback = true;
+        break;
+    case 2: /* signed offset, rn not updated */
+        postindex = false;
+        break;
+    case 3: /* pre-index */
+        postindex = false;
+        wback = true;
+        break;
+    default: /* Failed decoder tree? */
+        unallocated_encoding(s);
+        break;
+    }
+
+    offset <<= size;
+
+    if (rn == 31) {
+        gen_check_sp_alignment(s);
+    }
+
+    tcg_addr = read_cpu_reg_sp(s, rn, 1);
+
+    if (!postindex) {
+        tcg_gen_addi_i64(tcg_addr, tcg_addr, offset);
+    }
+
+    if (is_vector) {
+        if (is_load) {
+            do_fp_ld(s, rt, tcg_addr, size);
+        } else {
+            do_fp_st(s, rt, tcg_addr, size);
+        }
+    } else {
+        TCGv_i64 tcg_rt = cpu_reg(s, rt);
+        if (is_load) {
+            do_gpr_ld(s, tcg_rt, tcg_addr, size, is_signed, false);
+        } else {
+            do_gpr_st(s, tcg_rt, tcg_addr, size);
+        }
+    }
+    tcg_gen_addi_i64(tcg_addr, tcg_addr, 1 << size);
+    if (is_vector) {
+        if (is_load) {
+            do_fp_ld(s, rt2, tcg_addr, size);
+        } else {
+            do_fp_st(s, rt2, tcg_addr, size);
+        }
+    } else {
+        TCGv_i64 tcg_rt2 = cpu_reg(s, rt2);
+        if (is_load) {
+            do_gpr_ld(s, tcg_rt2, tcg_addr, size, is_signed, false);
+        } else {
+            do_gpr_st(s, tcg_rt2, tcg_addr, size);
+        }
+    }
+
+    if (wback) {
+        if (postindex) {
+            tcg_gen_addi_i64(tcg_addr, tcg_addr, offset - (1 << size));
+        } else {
+            tcg_gen_subi_i64(tcg_addr, tcg_addr, 1 << size);
+        }
+        tcg_gen_mov_i64(cpu_reg_sp(s, rn), tcg_addr);
+    }
 }
 
 /* Load/store register (all forms) */
@@ -656,7 +914,7 @@ static void disas_ldst(DisasContext *s, uint32_t insn)
         break;
     case 0x28: case 0x29:
     case 0x2c: case 0x2d: /* Load/store pair (all forms) */
-        disas_ldst_pair(s, insn);
+        handle_ldst_pair(s, insn);
         break;
     case 0x38: case 0x39:
     case 0x3c: case 0x3d: /* Load/store register (all forms) */
-- 
1.8.5

[Qemu-devel] [PATCH v2 2/8] target-arm: A64: add support for ld/st unsigned imm

[Peter Maydell]

From: Alex Bennée <alex@bennee.com>

This adds support for the forms of ld/st with a 12 bit
unsigned immediate offset.

Signed-off-by: Alex Bennée <alex.bennee@linaro.org>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>

---

Changes
   - split off cpu_read_reg_sp for earlier use
---
 target-arm/translate-a64.c | 89 +++++++++++++++++++++++++++++++++++++++++++++-
 1 file changed, 88 insertions(+), 1 deletion(-)

diff --git a/target-arm/translate-a64.c b/target-arm/translate-a64.c
index 018b3ee..7d3f432 100644
--- a/target-arm/translate-a64.c
+++ b/target-arm/translate-a64.c
@@ -884,10 +884,97 @@ static void handle_ldst_pair(DisasContext *s, uint32_t insn)
     }
 }
 
+/*
+ * C3.3.13 Load/store (unsigned immediate)
+ *
+ * 31 30 29   27  26 25 24 23 22 21        10 9     5
+ * +----+-------+---+-----+-----+------------+-------+------+
+ * |size| 1 1 1 | V | 0 1 | opc |   imm12    |  Rn   |  Rt  |
+ * +----+-------+---+-----+-----+------------+-------+------+
+ *
+ * For non-vector:
+ *   size: 00-> byte, 01 -> 16 bit, 10 -> 32bit, 11 -> 64bit
+ *   opc: 00 -> store, 01 -> loadu, 10 -> loads 64, 11 -> loads 32
+ * For vector:
+ *   size is opc<1>:size<1:0> so 100 -> 128 bit; 110 and 111 unallocated
+ *   opc<0>: 0 -> store, 1 -> load
+ * Rn: base address register (inc SP)
+ * Rt: target register
+ */
+static void handle_ldst_reg_unsigned_imm(DisasContext *s, uint32_t insn)
+{
+    int rt = extract32(insn, 0, 5);
+    int rn = extract32(insn, 5, 5);
+    unsigned int imm12 = extract32(insn, 10, 12);
+    bool is_vector = extract32(insn, 26, 1);
+    int size = extract32(insn, 30, 2);
+    int opc = extract32(insn, 22, 2);
+    unsigned int offset;
+
+    TCGv_i64 tcg_addr;
+
+    bool is_store;
+    bool is_signed = false;
+    bool is_extended = false;
+
+    if (is_vector) {
+        size |= (opc & 2) << 1;
+        if (size > 4) {
+            unallocated_encoding(s);
+            return;
+        }
+        is_store = ((opc & 1) == 0);
+    } else {
+        if (size == 3 && opc == 2) {
+            /* PRFM - prefetch */
+            return;
+        }
+        if (opc == 3 && size > 1) {
+            unallocated_encoding(s);
+            return;
+        }
+        is_store = (opc == 0);
+        is_signed = opc & (1<<1);
+        is_extended = (size < 3) && (opc & 1);
+    }
+
+    if (rn == 31) {
+        gen_check_sp_alignment(s);
+    }
+    tcg_addr = read_cpu_reg_sp(s, rn, 1);
+    offset = imm12 << size;
+    tcg_gen_addi_i64(tcg_addr, tcg_addr, offset);
+
+    if (is_vector) {
+        if (is_store) {
+            do_fp_st(s, rt, tcg_addr, size);
+        } else {
+            do_fp_ld(s, rt, tcg_addr, size);
+        }
+    } else {
+        TCGv_i64 tcg_rt = cpu_reg(s, rt);
+        if (is_store) {
+            do_gpr_st(s, tcg_rt, tcg_addr, size);
+        } else {
+            do_gpr_ld(s, tcg_rt, tcg_addr, size, is_signed, is_extended);
+        }
+    }
+}
+
 /* Load/store register (all forms) */
 static void disas_ldst_reg(DisasContext *s, uint32_t insn)
 {
-    unsupported_encoding(s, insn);
+    switch (extract32(insn, 24, 2)) {
+    case 0:
+        unsupported_encoding(s, insn);
+        break;
+    case 1:
+        handle_ldst_reg_unsigned_imm(s, insn);
+        break;
+    default:
+        unallocated_encoding(s);
+        break;
+    }
 }
 
 /* AdvSIMD load/store multiple structures */
-- 
1.8.5

[Qemu-devel] [PATCH v2 3/8] target-arm: A64: add support for ld/st with reg offset

[Peter Maydell]

From: Alex Bennée <alex@bennee.com>

This adds support for the load/store forms using a register offset.

Signed-off-by: Alex Bennée <alex.bennee@linaro.org>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target-arm/translate-a64.c | 144 ++++++++++++++++++++++++++++++++++++++++++++-
 1 file changed, 143 insertions(+), 1 deletion(-)

diff --git a/target-arm/translate-a64.c b/target-arm/translate-a64.c
index 7d3f432..1ea3c0e 100644
--- a/target-arm/translate-a64.c
+++ b/target-arm/translate-a64.c
@@ -402,6 +402,54 @@ static void do_fp_ld(DisasContext *s, int destidx, TCGv_i64 tcg_addr, int size)
     tcg_temp_free_i64(tmphi);
 }
 
+/*
+ * This utility function is for doing register extension with an
+ * optional shift. You will likely want to pass a temporary for the
+ * destination register. See DecodeRegExtend() in the ARM ARM.
+ */
+static void ext_and_shift_reg(TCGv_i64 tcg_out, TCGv_i64 tcg_in,
+                              int option, unsigned int shift)
+{
+    int extsize = extract32(option, 0, 2);
+    bool is_signed = extract32(option, 2, 1);
+
+    if (is_signed) {
+        switch (extsize) {
+        case 0:
+            tcg_gen_ext8s_i64(tcg_out, tcg_in);
+            break;
+        case 1:
+            tcg_gen_ext16s_i64(tcg_out, tcg_in);
+            break;
+        case 2:
+            tcg_gen_ext32s_i64(tcg_out, tcg_in);
+            break;
+        case 3:
+            tcg_gen_mov_i64(tcg_out, tcg_in);
+            break;
+        }
+    } else {
+        switch (extsize) {
+        case 0:
+            tcg_gen_ext8u_i64(tcg_out, tcg_in);
+            break;
+        case 1:
+            tcg_gen_ext16u_i64(tcg_out, tcg_in);
+            break;
+        case 2:
+            tcg_gen_ext32u_i64(tcg_out, tcg_in);
+            break;
+        case 3:
+            tcg_gen_mov_i64(tcg_out, tcg_in);
+            break;
+        }
+    }
+
+    if (shift) {
+        tcg_gen_shli_i64(tcg_out, tcg_out, shift);
+    }
+}
+
 static inline void gen_check_sp_alignment(DisasContext *s)
 {
     /* The AArch64 architecture mandates that (if enabled via PSTATE
@@ -885,6 +933,96 @@ static void handle_ldst_pair(DisasContext *s, uint32_t insn)
 }
 
 /*
+ * C3.3.10 Load/store (register offset)
+ *
+ * 31 30 29   27  26 25 24 23 22 21  20  16 15 13 12 11 10 9  5 4  0
+ * +----+-------+---+-----+-----+---+------+-----+--+-----+----+----+
+ * |size| 1 1 1 | V | 0 0 | opc | 1 |  Rm  | opt | S| 1 0 | Rn | Rt |
+ * +----+-------+---+-----+-----+---+------+-----+--+-----+----+----+
+ *
+ * For non-vector:
+ *   size: 00-> byte, 01 -> 16 bit, 10 -> 32bit, 11 -> 64bit
+ *   opc: 00 -> store, 01 -> loadu, 10 -> loads 64, 11 -> loads 32
+ * For vector:
+ *   size is opc<1>:size<1:0> so 100 -> 128 bit; 110 and 111 unallocated
+ *   opc<0>: 0 -> store, 1 -> load
+ * V: 1 -> vector/simd
+ * opt: extend encoding (see DecodeRegExtend)
+ * S: if S=1 then scale (essentially index by sizeof(size))
+ * Rt: register to transfer into/out of
+ * Rn: address register or SP for base
+ * Rm: offset register or ZR for offset
+ */
+static void handle_ldst_reg_roffset(DisasContext *s, uint32_t insn)
+{
+    int rt = extract32(insn, 0, 5);
+    int rn = extract32(insn, 5, 5);
+    int shift = extract32(insn, 12, 1);
+    int rm = extract32(insn, 16, 5);
+    int opc = extract32(insn, 22, 2);
+    int opt = extract32(insn, 13, 3);
+    int size = extract32(insn, 30, 2);
+    bool is_signed = false;
+    bool is_store = false;
+    bool is_extended = false;
+    bool is_vector = extract32(insn, 26, 1);
+
+    TCGv_i64 tcg_rm;
+    TCGv_i64 tcg_addr;
+
+    if (extract32(opt, 1, 1) == 0) {
+        unallocated_encoding(s);
+        return;
+    }
+
+    if (is_vector) {
+        size |= (opc & 2) << 1;
+        if (size > 4) {
+            unallocated_encoding(s);
+            return;
+        }
+        is_store = ((opc & 1) == 0);
+    } else {
+        if (size == 3 && opc == 2) {
+            /* PRFM - prefetch */
+            return;
+        }
+        if (opc == 3 && size > 1) {
+            unallocated_encoding(s);
+            return;
+        }
+        is_store = (opc == 0);
+        is_signed = opc & (1<<1);
+        is_extended = (size < 3) && (opc & 1);
+    }
+
+    if (rn == 31) {
+        gen_check_sp_alignment(s);
+    }
+    tcg_addr = read_cpu_reg_sp(s, rn, 1);
+
+    tcg_rm = read_cpu_reg(s, rm, 1);
+    ext_and_shift_reg(tcg_rm, tcg_rm, opt, shift ? size : 0);
+
+    tcg_gen_add_i64(tcg_addr, tcg_addr, tcg_rm);
+
+    if (is_vector) {
+        if (is_store) {
+            do_fp_st(s, rt, tcg_addr, size);
+        } else {
+            do_fp_ld(s, rt, tcg_addr, size);
+        }
+    } else {
+        TCGv_i64 tcg_rt = cpu_reg(s, rt);
+        if (is_store) {
+            do_gpr_st(s, tcg_rt, tcg_addr, size);
+        } else {
+            do_gpr_ld(s, tcg_rt, tcg_addr, size, is_signed, is_extended);
+        }
+    }
+}
+
+/*
  * C3.3.13 Load/store (unsigned immediate)
  *
  * 31 30 29   27  26 25 24 23 22 21        10 9     5
@@ -966,7 +1104,11 @@ static void disas_ldst_reg(DisasContext *s, uint32_t insn)
 {
     switch (extract32(insn, 24, 2)) {
     case 0:
-        unsupported_encoding(s, insn);
+        if (extract32(insn, 21, 1) == 1 && extract32(insn, 10, 2) == 2) {
+            handle_ldst_reg_roffset(s, insn);
+        } else {
+            unsupported_encoding(s, insn);
+        }
         break;
     case 1:
         handle_ldst_reg_unsigned_imm(s, insn);
-- 
1.8.5

[Qemu-devel] [PATCH v2 4/8] target-arm: A64: add support for ld/st with index

[Peter Maydell]

From: Alex Bennée <alex@bennee.com>

This adds support for the pre/post-index ld/st forms with immediate
offsets as well as the un-scaled immediate form (which are all
variations on the same 9-bit immediate instruction form).

Signed-off-by: Alex Bennée <alex.bennee@linaro.org>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target-arm/translate-a64.c | 125 ++++++++++++++++++++++++++++++++++++++++++++-
 1 file changed, 124 insertions(+), 1 deletion(-)

diff --git a/target-arm/translate-a64.c b/target-arm/translate-a64.c
index 1ea3c0e..791555d 100644
--- a/target-arm/translate-a64.c
+++ b/target-arm/translate-a64.c
@@ -933,6 +933,110 @@ static void handle_ldst_pair(DisasContext *s, uint32_t insn)
 }
 
 /*
+ * C3.3.8 Load/store (immediate post-indexed)
+ * C3.3.9 Load/store (immediate pre-indexed)
+ * C3.3.12 Load/store (unscaled immediate)
+ *
+ * 31 30 29   27  26 25 24 23 22 21  20    12 11 10 9    5 4    0
+ * +----+-------+---+-----+-----+---+--------+-----+------+------+
+ * |size| 1 1 1 | V | 0 0 | opc | 0 |  imm9  | idx |  Rn  |  Rt  |
+ * +----+-------+---+-----+-----+---+--------+-----+------+------+
+ *
+ * idx = 01 -> post-indexed, 11 pre-indexed, 00 unscaled imm. (no writeback)
+ * V = 0 -> non-vector
+ * size: 00 -> 8 bit, 01 -> 16 bit, 10 -> 32 bit, 11 -> 64bit
+ * opc: 00 -> store, 01 -> loadu, 10 -> loads 64, 11 -> loads 32
+ */
+static void handle_ldst_reg_imm9(DisasContext *s, uint32_t insn)
+{
+    int rt = extract32(insn, 0, 5);
+    int rn = extract32(insn, 5, 5);
+    int imm9 = sextract32(insn, 12, 9);
+    int opc = extract32(insn, 22, 2);
+    int size = extract32(insn, 30, 2);
+    int idx = extract32(insn, 10, 2);
+    bool is_signed = false;
+    bool is_store = false;
+    bool is_extended = false;
+    bool is_vector = extract32(insn, 26, 1);
+    bool post_index;
+    bool writeback;
+
+    TCGv_i64 tcg_addr;
+
+    if (is_vector) {
+        size |= (opc & 2) << 1;
+        if (size > 4) {
+            unallocated_encoding(s);
+            return;
+        }
+        is_store = ((opc & 1) == 0);
+    } else {
+        if (size == 3 && opc == 2) {
+            /* PRFM - prefetch */
+            return;
+        }
+        if (opc == 3 && size > 1) {
+            unallocated_encoding(s);
+            return;
+        }
+        is_store = (opc == 0);
+        is_signed = opc & (1<<1);
+        is_extended = (size < 3) && (opc & 1);
+    }
+
+    switch (idx) {
+    case 0:
+        post_index = false;
+        writeback = false;
+        break;
+    case 1:
+        post_index = true;
+        writeback = true;
+        break;
+    case 3:
+        post_index = false;
+        writeback = true;
+        break;
+    case 2:
+        g_assert(false);
+        break;
+    }
+
+    if (rn == 31) {
+        gen_check_sp_alignment(s);
+    }
+    tcg_addr = read_cpu_reg_sp(s, rn, 1);
+
+    if (!post_index) {
+        tcg_gen_addi_i64(tcg_addr, tcg_addr, imm9);
+    }
+
+    if (is_vector) {
+        if (is_store) {
+            do_fp_st(s, rt, tcg_addr, size);
+        } else {
+            do_fp_ld(s, rt, tcg_addr, size);
+        }
+    } else {
+        TCGv_i64 tcg_rt = cpu_reg(s, rt);
+        if (is_store) {
+            do_gpr_st(s, tcg_rt, tcg_addr, size);
+        } else {
+            do_gpr_ld(s, tcg_rt, tcg_addr, size, is_signed, is_extended);
+        }
+    }
+
+    if (writeback) {
+        TCGv_i64 tcg_rn = cpu_reg_sp(s, rn);
+        if (post_index) {
+            tcg_gen_addi_i64(tcg_addr, tcg_addr, imm9);
+        }
+        tcg_gen_mov_i64(tcg_rn, tcg_addr);
+    }
+}
+
+/*
  * C3.3.10 Load/store (register offset)
  *
  * 31 30 29   27  26 25 24 23 22 21  20  16 15 13 12 11 10 9  5 4  0
@@ -1099,6 +1203,25 @@ static void handle_ldst_reg_unsigned_imm(DisasContext *s, uint32_t insn)
     }
 }
 
+/* Load/store register (immediate forms) */
+static void disas_ldst_reg_imm(DisasContext *s, uint32_t insn)
+{
+    switch (extract32(insn, 10, 2)) {
+    case 0: case 1: case 3:
+        /* Load/store register (unscaled immediate) */
+        /* Load/store immediate pre/post-indexed */
+        handle_ldst_reg_imm9(s, insn);
+        break;
+    case 2:
+        /* Load/store register unprivileged */
+        unsupported_encoding(s, insn);
+        break;
+    default:
+        unallocated_encoding(s);
+        break;
+    }
+}
+
 /* Load/store register (all forms) */
 static void disas_ldst_reg(DisasContext *s, uint32_t insn)
 {
@@ -1107,7 +1230,7 @@ static void disas_ldst_reg(DisasContext *s, uint32_t insn)
         if (extract32(insn, 21, 1) == 1 && extract32(insn, 10, 2) == 2) {
             handle_ldst_reg_roffset(s, insn);
         } else {
-            unsupported_encoding(s, insn);
+            disas_ldst_reg_imm(s, insn);
         }
         break;
     case 1:
-- 
1.8.5

[Qemu-devel] [PATCH v2 5/8] target-arm: A64: add support for add, addi, sub, subi

[Peter Maydell]

From: Alex Bennée <alex.bennee@linaro.org>

Implement the non-carry forms of addition and subtraction
(immediate, extended register and shifted register).
This includes the code to calculate NZCV if the instruction
calls for setting the flags.

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>

---
Changes:
  - remove pointless mov op (we already have a copy)
---
 target-arm/translate-a64.c | 299 +++++++++++++++++++++++++++++++++++++++++++--
 1 file changed, 289 insertions(+), 10 deletions(-)

diff --git a/target-arm/translate-a64.c b/target-arm/translate-a64.c
index 791555d..59393f3 100644
--- a/target-arm/translate-a64.c
+++ b/target-arm/translate-a64.c
@@ -297,6 +297,102 @@ static inline void gen_logic_CC(int sf, TCGv_i64 result)
     tcg_gen_movi_i32(cpu_VF, 0);
 }
 
+/* dest = T0 + T1; compute C, N, V and Z flags */
+static void gen_add_CC(int sf, TCGv_i64 dest, TCGv_i64 t0, TCGv_i64 t1)
+{
+    if (sf) {
+        TCGv_i64 result, flag, tmp;
+        result = tcg_temp_new_i64();
+        flag = tcg_temp_new_i64();
+        tmp = tcg_temp_new_i64();
+
+        tcg_gen_movi_i64(tmp, 0);
+        tcg_gen_add2_i64(result, flag, t0, tmp, t1, tmp);
+
+        tcg_gen_trunc_i64_i32(cpu_CF, flag);
+
+        gen_set_NZ64(result);
+
+        tcg_gen_xor_i64(flag, result, t0);
+        tcg_gen_xor_i64(tmp, t0, t1);
+        tcg_gen_andc_i64(flag, flag, tmp);
+        tcg_temp_free_i64(tmp);
+        tcg_gen_shri_i64(flag, flag, 32);
+        tcg_gen_trunc_i64_i32(cpu_VF, flag);
+
+        tcg_gen_mov_i64(dest, result);
+        tcg_temp_free_i64(result);
+        tcg_temp_free_i64(flag);
+    } else {
+        /* 32 bit arithmetic */
+        TCGv_i32 t0_32 = tcg_temp_new_i32();
+        TCGv_i32 t1_32 = tcg_temp_new_i32();
+        TCGv_i32 tmp = tcg_temp_new_i32();
+
+        tcg_gen_movi_i32(tmp, 0);
+        tcg_gen_trunc_i64_i32(t0_32, t0);
+        tcg_gen_trunc_i64_i32(t1_32, t1);
+        tcg_gen_add2_i32(cpu_NF, cpu_CF, t0_32, tmp, t1_32, tmp);
+        tcg_gen_mov_i32(cpu_ZF, cpu_NF);
+        tcg_gen_xor_i32(cpu_VF, cpu_NF, t0_32);
+        tcg_gen_xor_i32(tmp, t0_32, t1_32);
+        tcg_gen_andc_i32(cpu_VF, cpu_VF, tmp);
+        tcg_gen_extu_i32_i64(dest, cpu_NF);
+
+        tcg_temp_free_i32(tmp);
+        tcg_temp_free_i32(t0_32);
+        tcg_temp_free_i32(t1_32);
+    }
+}
+
+/* dest = T0 - T1; compute C, N, V and Z flags */
+static void gen_sub_CC(int sf, TCGv_i64 dest, TCGv_i64 t0, TCGv_i64 t1)
+{
+    if (sf) {
+        /* 64 bit arithmetic */
+        TCGv_i64 result, flag, tmp;
+
+        result = tcg_temp_new_i64();
+        flag = tcg_temp_new_i64();
+        tcg_gen_sub_i64(result, t0, t1);
+
+        gen_set_NZ64(result);
+
+        tcg_gen_setcond_i64(TCG_COND_GEU, flag, t0, t1);
+        tcg_gen_trunc_i64_i32(cpu_CF, flag);
+
+        tcg_gen_xor_i64(flag, result, t0);
+        tmp = tcg_temp_new_i64();
+        tcg_gen_xor_i64(tmp, t0, t1);
+        tcg_gen_and_i64(flag, flag, tmp);
+        tcg_temp_free_i64(tmp);
+        tcg_gen_shri_i64(flag, flag, 32);
+        tcg_gen_trunc_i64_i32(cpu_VF, flag);
+        tcg_gen_mov_i64(dest, result);
+        tcg_temp_free_i64(flag);
+        tcg_temp_free_i64(result);
+    } else {
+        /* 32 bit arithmetic */
+        TCGv_i32 t0_32 = tcg_temp_new_i32();
+        TCGv_i32 t1_32 = tcg_temp_new_i32();
+        TCGv_i32 tmp;
+
+        tcg_gen_trunc_i64_i32(t0_32, t0);
+        tcg_gen_trunc_i64_i32(t1_32, t1);
+        tcg_gen_sub_i32(cpu_NF, t0_32, t1_32);
+        tcg_gen_mov_i32(cpu_ZF, cpu_NF);
+        tcg_gen_setcond_i32(TCG_COND_GEU, cpu_CF, t0_32, t1_32);
+        tcg_gen_xor_i32(cpu_VF, cpu_NF, t0_32);
+        tmp = tcg_temp_new_i32();
+        tcg_gen_xor_i32(tmp, t0_32, t1_32);
+        tcg_temp_free_i32(t0_32);
+        tcg_temp_free_i32(t1_32);
+        tcg_gen_and_i32(cpu_VF, cpu_VF, tmp);
+        tcg_temp_free_i32(tmp);
+        tcg_gen_extu_i32_i64(dest, cpu_NF);
+    }
+}
+
 /*
  * Load/Store generators
  */
@@ -1311,10 +1407,67 @@ static void disas_pc_rel_adr(DisasContext *s, uint32_t insn)
     tcg_gen_movi_i64(cpu_reg(s, rd), base + offset);
 }
 
-/* Add/subtract (immediate) */
+/*
+ * C3.4.1 Add/subtract (immediate)
+ *
+ *  31 30 29 28       24 23 22 21         10 9   5 4   0
+ * +--+--+--+-----------+-----+-------------+-----+-----+
+ * |sf|op| S| 1 0 0 0 1 |shift|    imm12    |  Rn | Rd  |
+ * +--+--+--+-----------+-----+-------------+-----+-----+
+ *
+ *    sf: 0 -> 32bit, 1 -> 64bit
+ *    op: 0 -> add  , 1 -> sub
+ *     S: 1 -> set flags
+ * shift: 00 -> LSL imm by 0, 01 -> LSL imm by 12
+ */
 static void disas_add_sub_imm(DisasContext *s, uint32_t insn)
 {
-    unsupported_encoding(s, insn);
+    int rd = extract32(insn, 0, 5);
+    int rn = extract32(insn, 5, 5);
+    uint64_t imm = extract32(insn, 10, 12);
+    int shift = extract32(insn, 22, 2);
+    bool setflags = extract32(insn, 29, 1);
+    bool sub_op = extract32(insn, 30, 1);
+    bool is_64bit = extract32(insn, 31, 1);
+
+    TCGv_i64 tcg_rn = cpu_reg_sp(s, rn);
+    TCGv_i64 tcg_rd = setflags ? cpu_reg(s, rd) : cpu_reg_sp(s, rd);
+    TCGv_i64 tcg_result;
+
+    switch (shift) {
+    case 0x0:
+        break;
+    case 0x1:
+        imm <<= 12;
+        break;
+    default:
+        unallocated_encoding(s);
+    }
+
+    tcg_result = tcg_temp_new_i64();
+    if (!setflags) {
+        if (sub_op) {
+            tcg_gen_subi_i64(tcg_result, tcg_rn, imm);
+        } else {
+            tcg_gen_addi_i64(tcg_result, tcg_rn, imm);
+        }
+    } else {
+        TCGv_i64 tcg_imm = tcg_const_i64(imm);
+        if (sub_op) {
+            gen_sub_CC(is_64bit, tcg_result, tcg_rn, tcg_imm);
+        } else {
+            gen_add_CC(is_64bit, tcg_result, tcg_rn, tcg_imm);
+        }
+        tcg_temp_free_i64(tcg_imm);
+    }
+
+    if (is_64bit) {
+        tcg_gen_mov_i64(tcg_rd, tcg_result);
+    } else {
+        tcg_gen_ext32u_i64(tcg_rd, tcg_result);
+    }
+
+    tcg_temp_free_i64(tcg_result);
 }
 
 /* The input should be a value in the bottom e bits (with higher
@@ -1772,16 +1925,142 @@ static void disas_logic_reg(DisasContext *s, uint32_t insn)
     }
 }
 
-/* Add/subtract (extended register) */
-static void disas_add_sub_ext_reg(DisasContext *s, uint32_t insn)
+/*
+ * C3.5.1 Add/subtract (extended register)
+ *
+ *  31|30|29|28       24|23 22|21|20   16|15  13|12  10|9  5|4  0|
+ * +--+--+--+-----------+-----+--+-------+------+------+----+----+
+ * |sf|op| S| 0 1 0 1 1 | opt | 1|  Rm   |option| imm3 | Rn | Rd |
+ * +--+--+--+-----------+-----+--+-------+------+------+----+----+
+ *
+ *  sf: 0 -> 32bit, 1 -> 64bit
+ *  op: 0 -> add  , 1 -> sub
+ *   S: 1 -> set flags
+ * opt: 00
+ * option: extension type (see DecodeRegExtend)
+ * imm3: optional shift to Rm
+ *
+ * Rd = Rn + LSL(extend(Rm), amount)
+ */
+static void handle_add_sub_ext_reg(DisasContext *s, uint32_t insn)
 {
-    unsupported_encoding(s, insn);
+    int rd = extract32(insn, 0, 5);
+    int rn = extract32(insn, 5, 5);
+    int imm3 = extract32(insn, 10, 3);
+    int option = extract32(insn, 13, 3);
+    int rm = extract32(insn, 16, 5);
+    bool setflags = extract32(insn, 29, 1);
+    bool sub_op = extract32(insn, 30, 1);
+    bool sf = extract32(insn, 31, 1);
+
+    TCGv_i64 tcg_rm, tcg_rn; /* temps */
+    TCGv_i64 tcg_rd;
+    TCGv_i64 tcg_result;
+
+    if (imm3 > 4) {
+        unallocated_encoding(s);
+        return;
+    }
+
+    /* non-flag setting ops may use SP */
+    if (!setflags) {
+        tcg_rn = read_cpu_reg_sp(s, rn, sf);
+        tcg_rd = cpu_reg_sp(s, rd);
+    } else {
+        tcg_rn = read_cpu_reg(s, rn, sf);
+        tcg_rd = cpu_reg(s, rd);
+    }
+
+    tcg_rm = read_cpu_reg(s, rm, sf);
+    ext_and_shift_reg(tcg_rm, tcg_rm, option, imm3);
+
+    tcg_result = tcg_temp_new_i64();
+
+    if (!setflags) {
+        if (sub_op) {
+            tcg_gen_sub_i64(tcg_result, tcg_rn, tcg_rm);
+        } else {
+            tcg_gen_add_i64(tcg_result, tcg_rn, tcg_rm);
+        }
+    } else {
+        if (sub_op) {
+            gen_sub_CC(sf, tcg_result, tcg_rn, tcg_rm);
+        } else {
+            gen_add_CC(sf, tcg_result, tcg_rn, tcg_rm);
+        }
+    }
+
+    if (sf) {
+        tcg_gen_mov_i64(tcg_rd, tcg_result);
+    } else {
+        tcg_gen_ext32u_i64(tcg_rd, tcg_result);
+    }
+
+    tcg_temp_free_i64(tcg_result);
 }
 
-/* Add/subtract (shifted register) */
-static void disas_add_sub_reg(DisasContext *s, uint32_t insn)
+/*
+ * C3.5.2 Add/subtract (shifted register)
+ *
+ *  31 30 29 28       24 23 22 21 20   16 15     10 9    5 4    0
+ * +--+--+--+-----------+-----+--+-------+---------+------+------+
+ * |sf|op| S| 0 1 0 1 1 |shift| 0|  Rm   |  imm6   |  Rn  |  Rd  |
+ * +--+--+--+-----------+-----+--+-------+---------+------+------+
+ *
+ *    sf: 0 -> 32bit, 1 -> 64bit
+ *    op: 0 -> add  , 1 -> sub
+ *     S: 1 -> set flags
+ * shift: 00 -> LSL, 01 -> LSR, 10 -> ASR, 11 -> RESERVED
+ *  imm6: Shift amount to apply to Rm before the add/sub
+ */
+static void handle_add_sub_reg(DisasContext *s, uint32_t insn)
 {
-    unsupported_encoding(s, insn);
+    int rd = extract32(insn, 0, 5);
+    int rn = extract32(insn, 5, 5);
+    int imm6 = extract32(insn, 10, 6);
+    int rm = extract32(insn, 16, 5);
+    int shift_type = extract32(insn, 22, 2);
+    bool setflags = extract32(insn, 29, 1);
+    bool sub_op = extract32(insn, 30, 1);
+    bool sf = extract32(insn, 31, 1);
+
+    TCGv_i64 tcg_rd = cpu_reg(s, rd);
+    TCGv_i64 tcg_rn, tcg_rm;
+    TCGv_i64 tcg_result;
+
+    if ((shift_type == 3) || (!sf && (imm6 > 31))) {
+        unallocated_encoding(s);
+        return;
+    }
+
+    tcg_rn = read_cpu_reg(s, rn, sf);
+    tcg_rm = read_cpu_reg(s, rm, sf);
+
+    shift_reg_imm(tcg_rm, tcg_rm, sf, shift_type, imm6);
+
+    tcg_result = tcg_temp_new_i64();
+
+    if (!setflags) {
+        if (sub_op) {
+            tcg_gen_sub_i64(tcg_result, tcg_rn, tcg_rm);
+        } else {
+            tcg_gen_add_i64(tcg_result, tcg_rn, tcg_rm);
+        }
+    } else {
+        if (sub_op) {
+            gen_sub_CC(sf, tcg_result, tcg_rn, tcg_rm);
+        } else {
+            gen_add_CC(sf, tcg_result, tcg_rn, tcg_rm);
+        }
+    }
+
+    if (sf) {
+        tcg_gen_mov_i64(tcg_rd, tcg_result);
+    } else {
+        tcg_gen_ext32u_i64(tcg_rd, tcg_result);
+    }
+
+    tcg_temp_free_i64(tcg_result);
 }
 
 /* Data-processing (3 source) */
@@ -2145,9 +2424,9 @@ static void disas_data_proc_reg(DisasContext *s, uint32_t insn)
         break;
     case 0x0b: /* Add/subtract */
         if (insn & (1 << 21)) { /* (extended register) */
-            disas_add_sub_ext_reg(s, insn);
+            handle_add_sub_ext_reg(s, insn);
         } else {
-            disas_add_sub_reg(s, insn);
+            handle_add_sub_reg(s, insn);
         }
         break;
     case 0x1b: /* Data-processing (3 source) */
-- 
1.8.5

[Qemu-devel] [PATCH v2 6/8] target-arm: A64: add support for move wide instructions

[Peter Maydell]

From: Alex Bennée <alex.bennee@linaro.org>

This patch adds emulation for the mov wide instructions
(MOVN, MOVZ, MOVK).

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 | 51 ++++++++++++++++++++++++++++++++++++++++++++--
 1 file changed, 49 insertions(+), 2 deletions(-)

diff --git a/target-arm/translate-a64.c b/target-arm/translate-a64.c
index 59393f3..4a6252e 100644
--- a/target-arm/translate-a64.c
+++ b/target-arm/translate-a64.c
@@ -1626,10 +1626,57 @@ static void disas_logic_imm(DisasContext *s, uint32_t insn)
     }
 }
 
-/* Move wide (immediate) */
+/*
+ * C3.4.5 Move wide (immediate)
+ *
+ *  31 30 29 28         23 22 21 20             5 4    0
+ * +--+-----+-------------+-----+----------------+------+
+ * |sf| opc | 1 0 0 1 0 1 |  hw |  imm16         |  Rd  |
+ * +--+-----+-------------+-----+----------------+------+
+ *
+ * sf: 0 -> 32 bit, 1 -> 64 bit
+ * opc: 00 -> N, 10 -> Z, 11 -> K
+ * hw: shift/16 (0,16, and sf only 32, 48)
+ */
 static void disas_movw_imm(DisasContext *s, uint32_t insn)
 {
-    unsupported_encoding(s, insn);
+    int rd = extract32(insn, 0, 5);
+    uint64_t imm = extract32(insn, 5, 16);
+    int sf = extract32(insn, 31, 1);
+    int opc = extract32(insn, 29, 2);
+    int pos = extract32(insn, 21, 2) << 4;
+    TCGv_i64 tcg_rd = cpu_reg(s, rd);
+    TCGv_i64 tcg_imm;
+
+    if (!sf && (pos >= 32)) {
+        unallocated_encoding(s);
+        return;
+    }
+
+    switch (opc) {
+    case 0: /* MOVN */
+    case 2: /* MOVZ */
+        imm <<= pos;
+        if (opc == 0) {
+            imm = ~imm;
+        }
+        if (!sf) {
+            imm &= 0xffffffffu;
+        }
+        tcg_gen_movi_i64(tcg_rd, imm);
+        break;
+    case 3: /* MOVK */
+        tcg_imm = tcg_const_i64(imm);
+        tcg_gen_deposit_i64(tcg_rd, tcg_rd, tcg_imm, pos, 16);
+        tcg_temp_free_i64(tcg_imm);
+        if (!sf) {
+            tcg_gen_ext32u_i64(tcg_rd, tcg_rd);
+        }
+        break;
+    default:
+        unallocated_encoding(s);
+        break;
+    }
 }
 
 /* C3.4.2 Bitfield
-- 
1.8.5

[Qemu-devel] [PATCH v2 7/8] target-arm: A64: add support for 3 src data proc insns

[Peter Maydell]

From: Alexander Graf <agraf@suse.de>

This patch adds emulation for the "Data-processing (3 source)"
family of instructions, namely MADD, MSUB, SMADDL, SMSUBL, SMULH,
UMADDL, UMSUBL, UMULH.

Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Alex Bennée <alex.bennee@linaro.org>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>

---
Changes:
  - Use tcg ops for mul[su]h (rh comment)
---
 target-arm/translate-a64.c | 91 +++++++++++++++++++++++++++++++++++++++++++++-
 1 file changed, 89 insertions(+), 2 deletions(-)

diff --git a/target-arm/translate-a64.c b/target-arm/translate-a64.c
index 4a6252e..019a6ed 100644
--- a/target-arm/translate-a64.c
+++ b/target-arm/translate-a64.c
@@ -2110,10 +2110,97 @@ static void handle_add_sub_reg(DisasContext *s, uint32_t insn)
     tcg_temp_free_i64(tcg_result);
 }
 
-/* Data-processing (3 source) */
+/* C3.5.9 Data-processing (3 source)
+
+   31 30  29 28       24 23 21  20  16  15  14  10 9    5 4    0
+  +--+------+-----------+------+------+----+------+------+------+
+  |sf| op54 | 1 1 0 1 1 | op31 |  Rm  | o0 |  Ra  |  Rn  |  Rd  |
+  +--+------+-----------+------+------+----+------+------+------+
+
+ */
 static void disas_data_proc_3src(DisasContext *s, uint32_t insn)
 {
-    unsupported_encoding(s, insn);
+    int rd = extract32(insn, 0, 5);
+    int rn = extract32(insn, 5, 5);
+    int ra = extract32(insn, 10, 5);
+    int rm = extract32(insn, 16, 5);
+    int op_id = (extract32(insn, 29, 3) << 4) |
+        (extract32(insn, 21, 3) << 1) |
+        extract32(insn, 15, 1);
+    bool is_32bit = !extract32(insn, 31, 1);
+    bool is_sub = extract32(op_id, 0, 1);
+    bool is_high = extract32(op_id, 2, 1);
+    bool is_signed = false;
+    TCGv_i64 tcg_op1;
+    TCGv_i64 tcg_op2;
+    TCGv_i64 tcg_tmp;
+
+    /* Note that op_id is sf:op54:op31:o0 so it includes the 32/64 size flag */
+    switch (op_id) {
+    case 0x42: /* SMADDL */
+    case 0x43: /* SMSUBL */
+    case 0x44: /* SMULH */
+        is_signed = true;
+        break;
+    case 0x0: /* MADD (32bit) */
+    case 0x1: /* MSUB (32bit) */
+    case 0x40: /* MADD (64bit) */
+    case 0x41: /* MSUB (64bit) */
+    case 0x4a: /* UMADDL */
+    case 0x4b: /* UMSUBL */
+    case 0x4c: /* UMULH */
+        break;
+    default:
+        unallocated_encoding(s);
+    }
+
+    if (is_high) {
+        TCGv_i64 low_bits = tcg_temp_new_i64(); /* low bits discarded */
+        TCGv_i64 tcg_rd = cpu_reg(s, rd);
+        TCGv_i64 tcg_rn = cpu_reg(s, rn);
+        TCGv_i64 tcg_rm = cpu_reg(s, rm);
+
+        if (is_signed) {
+            tcg_gen_muls2_i64(low_bits, tcg_rd, tcg_rn, tcg_rm);
+        } else {
+            tcg_gen_mulu2_i64(low_bits, tcg_rd, tcg_rn, tcg_rm);
+        }
+
+        tcg_temp_free(low_bits);
+        return;
+    }
+
+    tcg_op1 = tcg_temp_new_i64();
+    tcg_op2 = tcg_temp_new_i64();
+    tcg_tmp = tcg_temp_new_i64();
+
+    if (op_id < 0x42) {
+        tcg_gen_mov_i64(tcg_op1, cpu_reg(s, rn));
+        tcg_gen_mov_i64(tcg_op2, cpu_reg(s, rm));
+    } else {
+        if (is_signed) {
+            tcg_gen_ext32s_i64(tcg_op1, cpu_reg(s, rn));
+            tcg_gen_ext32s_i64(tcg_op2, cpu_reg(s, rm));
+        } else {
+            tcg_gen_ext32u_i64(tcg_op1, cpu_reg(s, rn));
+            tcg_gen_ext32u_i64(tcg_op2, cpu_reg(s, rm));
+        }
+    }
+
+    tcg_gen_mul_i64(tcg_tmp, tcg_op1, tcg_op2);
+    if (is_sub) {
+        tcg_gen_sub_i64(cpu_reg(s, rd), cpu_reg(s, ra), tcg_tmp);
+    } else {
+        tcg_gen_add_i64(cpu_reg(s, rd), cpu_reg(s, ra), tcg_tmp);
+    }
+
+    if (is_32bit) {
+        tcg_gen_ext32u_i64(cpu_reg(s, rd), cpu_reg(s, rd));
+    }
+
+    tcg_temp_free_i64(tcg_op1);
+    tcg_temp_free_i64(tcg_op2);
+    tcg_temp_free_i64(tcg_tmp);
 }
 
 /* Add/subtract (with carry) */
-- 
1.8.5

[Qemu-devel] [PATCH v2 8/8] target-arm: A64: implement SVC, BRK

[Peter Maydell]

From: Alexander Graf <agraf@suse.de>

Add decoding for the exception generating instructions, and implement
SVC (syscalls) and BRK (software breakpoint).

Signed-off-by: Alexander Graf <agraf@suse.de>
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 | 51 ++++++++++++++++++++++++++++++++++++++++++++--
 1 file changed, 49 insertions(+), 2 deletions(-)

diff --git a/target-arm/translate-a64.c b/target-arm/translate-a64.c
index 019a6ed..df4409b 100644
--- a/target-arm/translate-a64.c
+++ b/target-arm/translate-a64.c
@@ -806,10 +806,57 @@ static void disas_system(DisasContext *s, uint32_t insn)
     }
 }
 
-/* Exception generation */
+/* C3.2.3 Exception generation
+ *
+ *  31             24 23 21 20                     5 4   2 1  0
+ * +-----------------+-----+------------------------+-----+----+
+ * | 1 1 0 1 0 1 0 0 | opc |          imm16         | op2 | LL |
+ * +-----------------------+------------------------+----------+
+ */
 static void disas_exc(DisasContext *s, uint32_t insn)
 {
-    unsupported_encoding(s, insn);
+    int opc = extract32(insn, 21, 3);
+    int op2_ll = extract32(insn, 0, 5);
+
+    switch (opc) {
+    case 0:
+        /* SVC, HVC, SMC; since we don't support the Virtualization
+         * or TrustZone extensions these all UNDEF except SVC.
+         */
+        if (op2_ll != 1) {
+            unallocated_encoding(s);
+            break;
+        }
+        gen_exception_insn(s, 0, EXCP_SWI);
+        break;
+    case 1:
+        if (op2_ll != 0) {
+            unallocated_encoding(s);
+            break;
+        }
+        /* BRK */
+        gen_exception_insn(s, 0, EXCP_BKPT);
+        break;
+    case 2:
+        if (op2_ll != 0) {
+            unallocated_encoding(s);
+            break;
+        }
+        /* HLT */
+        unsupported_encoding(s, insn);
+        break;
+    case 5:
+        if (op2_ll < 1 || op2_ll > 3) {
+            unallocated_encoding(s);
+            break;
+        }
+        /* DCPS1, DCPS2, DCPS3 */
+        unsupported_encoding(s, insn);
+        break;
+    default:
+        unallocated_encoding(s);
+        break;
+    }
 }
 
 /* C3.2.7 Unconditional branch (register)
-- 
1.8.5

Re: [Qemu-devel] [PATCH v2 1/8] target-arm: A64: add support for ld/st pair

[C Fontana]

Hi,

I saw a missing return below:

On 11 December 2013 23:01, Peter Maydell <peter.maydell@linaro.org> wrote:
> From: Alex Bennée <alex.bennee@linaro.org>
>
> This patch support the basic load and store pair instructions and
> includes the generic helper functions:
>
>   * do_gpr_st()
>   * do_fp_st()
>   * do_gpr_ld()
>   * do_fp_ld()
>   * read_cpu_reg_sp()
>   * gen_check_sp_alignment()
>
> The last function gen_check_sp_alignment() is a NULL op currently but
> put in place to make it easy to add SP alignment checking later.
>
> Signed-off-by: Alex Bennée <alex.bennee@linaro.org>
> Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
>
> ---
>
> Changes
>   - merge ldp/stp together
>   - add read_cpu_reg_sp() and use
>   - only reference registers as needed
>   - use common tcg ops for gpr/fp loads/store
> ---
>  target-arm/translate-a64.c | 268 ++++++++++++++++++++++++++++++++++++++++++++-
>  1 file changed, 263 insertions(+), 5 deletions(-)
>
> diff --git a/target-arm/translate-a64.c b/target-arm/translate-a64.c
> index 0a76130..018b3ee 100644
> --- a/target-arm/translate-a64.c
> +++ b/target-arm/translate-a64.c
> @@ -99,6 +99,15 @@ void aarch64_cpu_dump_state(CPUState *cs, FILE *f,
>      cpu_fprintf(f, "\n");
>  }
>
> +static int get_mem_index(DisasContext *s)
> +{
> +#ifdef CONFIG_USER_ONLY
> +    return 1;
> +#else
> +    return s->user;
> +#endif
> +}
> +
>  void gen_a64_set_pc_im(uint64_t val)
>  {
>      tcg_gen_movi_i64(cpu_pc, val);
> @@ -250,6 +259,17 @@ static TCGv_i64 read_cpu_reg(DisasContext *s, int reg, int sf)
>      return v;
>  }
>
> +static TCGv_i64 read_cpu_reg_sp(DisasContext *s, int reg, int sf)
> +{
> +    TCGv_i64 v = new_tmp_a64(s);
> +    if (sf) {
> +        tcg_gen_mov_i64(v, cpu_X[reg]);
> +    } else {
> +        tcg_gen_ext32u_i64(v, cpu_X[reg]);
> +    }
> +    return v;
> +}
> +
>  /* Set ZF and NF based on a 64 bit result. This is alas fiddlier
>   * than the 32 bit equivalent.
>   */
> @@ -278,6 +298,124 @@ static inline void gen_logic_CC(int sf, TCGv_i64 result)
>  }
>
>  /*
> + * Load/Store generators
> + */
> +
> +/*
> + *  Store from GPR register to memory
> + */
> +static void do_gpr_st(DisasContext *s, TCGv_i64 source,
> +                      TCGv_i64 tcg_addr, int size)
> +{
> +    g_assert(size <= 3);
> +    tcg_gen_qemu_st_i64(source, tcg_addr, get_mem_index(s), MO_TE + size);
> +}
> +
> +/*
> + * Load from memory to GPR register
> + */
> +static void do_gpr_ld(DisasContext *s, TCGv_i64 dest, TCGv_i64 tcg_addr,
> +                      int size, bool is_signed, bool extend)
> +{
> +    TCGMemOp memop =  MO_TE + size;
> +
> +    g_assert(size <= 3);
> +
> +    if (is_signed) {
> +        memop += MO_SIGN;
> +    }
> +
> +    tcg_gen_qemu_ld_i64(dest, tcg_addr, get_mem_index(s), memop);
> +
> +    if (extend && is_signed) {
> +        g_assert(size < 3);
> +        tcg_gen_ext32u_i64(dest, dest);
> +    }
> +}
> +
> +/*
> + * Store from FP register to memory
> + */
> +static void do_fp_st(DisasContext *s, int srcidx, TCGv_i64 tcg_addr, int size)
> +{
> +    /* This writes the bottom N bits of a 128 bit wide vector to memory */
> +    int freg_offs = offsetof(CPUARMState, vfp.regs[srcidx * 2]);
> +    TCGv_i64 tmp = tcg_temp_new_i64();
> +
> +    if (size < 4) {
> +        switch (size) {
> +        case 0:
> +            tcg_gen_ld8u_i64(tmp, cpu_env, freg_offs);
> +            break;
> +        case 1:
> +            tcg_gen_ld16u_i64(tmp, cpu_env, freg_offs);
> +            break;
> +        case 2:
> +            tcg_gen_ld32u_i64(tmp, cpu_env, freg_offs);
> +            break;
> +        case 3:
> +            tcg_gen_ld_i64(tmp, cpu_env, freg_offs);
> +            break;
> +        }
> +        tcg_gen_qemu_st_i64(tmp, tcg_addr, get_mem_index(s), MO_TE + size);
> +    } else {
> +        TCGv_i64 tcg_hiaddr = tcg_temp_new_i64();
> +        tcg_gen_ld_i64(tmp, cpu_env, freg_offs);
> +        tcg_gen_qemu_st_i64(tmp, tcg_addr, get_mem_index(s), MO_TEQ);
> +        tcg_gen_qemu_st64(tmp, tcg_addr, get_mem_index(s));
> +        tcg_gen_ld_i64(tmp, cpu_env, freg_offs + sizeof(float64));
> +        tcg_gen_addi_i64(tcg_hiaddr, tcg_addr, 8);
> +        tcg_gen_qemu_st_i64(tmp, tcg_hiaddr, get_mem_index(s), MO_TEQ);
> +        tcg_temp_free_i64(tcg_hiaddr);
> +    }
> +
> +    tcg_temp_free_i64(tmp);
> +}
> +
> +/* Load from memory to FP register */
> +static void do_fp_ld(DisasContext *s, int destidx, TCGv_i64 tcg_addr, int size)
> +{
> +    /* This always zero-extends and writes to a full 128 bit wide vector */
> +    int freg_offs = offsetof(CPUARMState, vfp.regs[destidx * 2]);
> +    TCGv_i64 tmplo = tcg_temp_new_i64();
> +    TCGv_i64 tmphi;
> +
> +    if (size < 4) {
> +        TCGMemOp memop =  MO_TE + size;
> +        tmphi = tcg_const_i64(0);
> +        tcg_gen_qemu_ld_i64(tmplo, tcg_addr, get_mem_index(s), memop);
> +    } else {
> +        TCGv_i64 tcg_hiaddr;
> +        tmphi = tcg_temp_new_i64();
> +        tcg_hiaddr = tcg_temp_new_i64();
> +
> +        tcg_gen_qemu_ld_i64(tmplo, tcg_addr, get_mem_index(s), MO_TEQ);
> +        tcg_gen_addi_i64(tcg_hiaddr, tcg_addr, 8);
> +        tcg_gen_qemu_ld_i64(tmphi, tcg_hiaddr, get_mem_index(s), MO_TEQ);
> +        tcg_temp_free_i64(tcg_hiaddr);
> +    }
> +
> +    tcg_gen_st_i64(tmplo, cpu_env, freg_offs);
> +    tcg_gen_st_i64(tmphi, cpu_env, freg_offs + sizeof(float64));
> +
> +    tcg_temp_free_i64(tmplo);
> +    tcg_temp_free_i64(tmphi);
> +}
> +
> +static inline void gen_check_sp_alignment(DisasContext *s)
> +{
> +    /* The AArch64 architecture mandates that (if enabled via PSTATE
> +     * or SCTLR bits) there is a check that SP is 16-aligned on every
> +     * SP-relative load or store (with an exception generated if it is not).
> +     * In line with general QEMU practice regarding misaligned accesses,
> +     * we omit these checks for the sake of guest program performance.
> +     * This function is provided as a hook so we can more easily add these
> +     * checks in future (possibly as a "favour catching guest program bugs
> +     * over speed" user selectable option).
> +     */
> +}
> +
> +/*
>   * the instruction disassembly implemented here matches
>   * the instruction encoding classifications in chapter 3 (C3)
>   * of the ARM Architecture Reference Manual (DDI0487A_a)
> @@ -620,10 +758,130 @@ static void disas_ld_lit(DisasContext *s, uint32_t insn)
>      unsupported_encoding(s, insn);
>  }
>
> -/* Load/store pair (all forms) */
> -static void disas_ldst_pair(DisasContext *s, uint32_t insn)
> -{
> -    unsupported_encoding(s, insn);
> +/*
> + * C5.6.81 LDP (Load Pair - non vector)
> + * C5.6.82 LDPSW (Load Pair Signed Word - non vector)
> + * C5.6.177 STP (Store Pair - non vector)
> + * C6.3.165 LDP (Load Pair of SIMD&FP)
> + * C6.3.284 STP (Store Pair of SIMD&FP)
> + *
> + *  31 30 29   27  26 25   23  22 21   15 14   10 9    5 4    0
> + * +-----+-------+---+-------+---+-----------------------------+
> + * | opc | 1 0 1 | V | index | L |  imm7 |  Rt2  |  Rn  | Rt   |
> + * +-----+-------+---+-------+---+-------+-------+------+------+
> + *
> + * opc: LDP&STP       00 -> 32 bit, 10 -> 64 bit
> + *      LDPSW         01
> + *      LDP&STP(SIMD) 00 -> 32 bit, 01 -> 64 bit, 10 -> 128 bit
> + *   V: 0 -> GPR, 1 -> Vector
> + * idx: 001 -> post-index, 011 -> pre-index, 010 -> signed off
> + *   L: 0 -> Store 1 -> Load
> + *
> + * Rt, Rt2 = GPR or SIMD registers to be stored
> + * Rn = general purpose register containing address
> + * imm7 = signed offset (multiple of 4 or 8 depending on size)
> + */
> +static void handle_ldst_pair(DisasContext *s, uint32_t insn)
> +{
> +    int rt = extract32(insn, 0, 5);
> +    int rn = extract32(insn, 5, 5);
> +    int rt2 = extract32(insn, 10, 5);
> +    int64_t offset = sextract32(insn, 15, 7);
> +    int index = extract32(insn, 23, 2);
> +    bool is_vector = extract32(insn, 26, 1);
> +    bool is_load = extract32(insn, 22, 1);
> +    int opc = extract32(insn, 30, 2);
> +
> +    bool is_signed = false;
> +    bool postindex = false;
> +    bool wback = false;
> +
> +    TCGv_i64 tcg_addr; /* calculated address */
> +    int size;
> +
> +    if (is_vector) {
> +        if (opc == 3) {
> +            unallocated_encoding(s);
> +            return;
> +        }
> +        size = 2 + opc;
> +    } else {
> +        size = 2 + extract32(opc, 1, 1);
> +        if (is_load) {
> +            is_signed = opc & 1;
> +        } else if (opc & 1) {
> +            unallocated_encoding(s);
> +            return;
> +        }
> +    }
> +
> +    switch (index) {
> +    case 1: /* post-index */
> +        postindex = true;
> +        wback = true;
> +        break;
> +    case 2: /* signed offset, rn not updated */
> +        postindex = false;
> +        break;
> +    case 3: /* pre-index */
> +        postindex = false;
> +        wback = true;
> +        break;
> +    default: /* Failed decoder tree? */
> +        unallocated_encoding(s);
> +        break;
> +    }

This doesn't seem right (break instead of return):

default:
    unallocated_encoding(s);
    return;
}

> +
> +    offset <<= size;
> +
> +    if (rn == 31) {
> +        gen_check_sp_alignment(s);
> +    }
> +
> +    tcg_addr = read_cpu_reg_sp(s, rn, 1);
> +
> +    if (!postindex) {
> +        tcg_gen_addi_i64(tcg_addr, tcg_addr, offset);
> +    }
> +
> +    if (is_vector) {
> +        if (is_load) {
> +            do_fp_ld(s, rt, tcg_addr, size);
> +        } else {
> +            do_fp_st(s, rt, tcg_addr, size);
> +        }
> +    } else {
> +        TCGv_i64 tcg_rt = cpu_reg(s, rt);
> +        if (is_load) {
> +            do_gpr_ld(s, tcg_rt, tcg_addr, size, is_signed, false);
> +        } else {
> +            do_gpr_st(s, tcg_rt, tcg_addr, size);
> +        }
> +    }
> +    tcg_gen_addi_i64(tcg_addr, tcg_addr, 1 << size);
> +    if (is_vector) {
> +        if (is_load) {
> +            do_fp_ld(s, rt2, tcg_addr, size);
> +        } else {
> +            do_fp_st(s, rt2, tcg_addr, size);
> +        }
> +    } else {
> +        TCGv_i64 tcg_rt2 = cpu_reg(s, rt2);
> +        if (is_load) {
> +            do_gpr_ld(s, tcg_rt2, tcg_addr, size, is_signed, false);
> +        } else {
> +            do_gpr_st(s, tcg_rt2, tcg_addr, size);
> +        }
> +    }
> +
> +    if (wback) {
> +        if (postindex) {
> +            tcg_gen_addi_i64(tcg_addr, tcg_addr, offset - (1 << size));
> +        } else {
> +            tcg_gen_subi_i64(tcg_addr, tcg_addr, 1 << size);
> +        }
> +        tcg_gen_mov_i64(cpu_reg_sp(s, rn), tcg_addr);
> +    }
>  }
>
>  /* Load/store register (all forms) */
> @@ -656,7 +914,7 @@ static void disas_ldst(DisasContext *s, uint32_t insn)
>          break;
>      case 0x28: case 0x29:
>      case 0x2c: case 0x2d: /* Load/store pair (all forms) */
> -        disas_ldst_pair(s, insn);
> +        handle_ldst_pair(s, insn);
>          break;
>      case 0x38: case 0x39:
>      case 0x3c: case 0x3d: /* Load/store register (all forms) */
> --
> 1.8.5
>

Re: [Qemu-devel] [PATCH v2 1/8] target-arm: A64: add support for ld/st pair

[Alex Bennée]

claudio.fontana@linaro.org writes:

> Hi,
>
> I saw a missing return below:
<snip>
>> +    default: /* Failed decoder tree? */
>> +        unallocated_encoding(s);
>> +        break;
>> +    }
>
> This doesn't seem right (break instead of return):
>
> default:
>     unallocated_encoding(s);
>     return;
> }

Good catch. I suspect it never hits though (or risu doesn't generate
enough unallocated versions).

-- 
Alex Bennée
QEMU/KVM Hacker for Linaro

Re: [Qemu-devel] [PATCH v2 1/8] target-arm: A64: add support for ld/st pair

[Peter Maydell]

On 12 December 2013 11:43, Alex Bennée <alex.bennee@linaro.org> wrote:
>
> claudio.fontana@linaro.org writes:
>
>> Hi,
>>
>> I saw a missing return below:
> <snip>
>>> +    default: /* Failed decoder tree? */
>>> +        unallocated_encoding(s);
>>> +        break;
>>> +    }
>>
>> This doesn't seem right (break instead of return):
>>
>> default:
>>     unallocated_encoding(s);
>>     return;
>> }
>
> Good catch. I suspect it never hits though (or risu doesn't generate
> enough unallocated versions).

Oh, I saw that and then forgot to mention it.
Either the comment or the code is wrong -- if
the decoder tree prevents us getting to this point
with that value of index then we should be asserting,
not calling unallocated_encoding(). If the encoding
is really supposed to be unallocated then it's not
a failure of the decoder tree that we got here,
it's just another case we need to check. Which is it?

thanks
-- PMM

Re: [Qemu-devel] [PATCH v2 1/8] target-arm: A64: add support for ld/st pair

[C Fontana]

On 12 December 2013 12:45, Peter Maydell <peter.maydell@linaro.org> wrote:
> On 12 December 2013 11:43, Alex Bennée <alex.bennee@linaro.org> wrote:
>>
>> claudio.fontana@linaro.org writes:
>>
>>> Hi,
>>>
>>> I saw a missing return below:
>> <snip>
>>>> +    default: /* Failed decoder tree? */
>>>> +        unallocated_encoding(s);
>>>> +        break;
>>>> +    }
>>>
>>> This doesn't seem right (break instead of return):
>>>
>>> default:
>>>     unallocated_encoding(s);
>>>     return;
>>> }
>>
>> Good catch. I suspect it never hits though (or risu doesn't generate
>> enough unallocated versions).
>
> Oh, I saw that and then forgot to mention it.
> Either the comment or the code is wrong -- if
> the decoder tree prevents us getting to this point
> with that value of index then we should be asserting,
> not calling unallocated_encoding(). If the encoding
> is really supposed to be unallocated then it's not
> a failure of the decoder tree that we got here,
> it's just another case we need to check. Which is it?
>
> thanks
> -- PMM

I think that there is more than the missing return:

we need to handle the case 0 as well, as it's a perfectly valid form
of a load/store pair:
it's the Load/Store no-allocate pair (offset) (LDNP, STNP).

So in my view we need to add a case 0 where we handle  the load/store
no-allocate pair,
and no default case, or a default case where we assert(0) for unreachable code,
since all possible index values (2 bits) should be handled by the
switch statement.

Ref: C3.3 Loads and stores Table C3-3

Claudio

Re: [Qemu-devel] [PATCH v2 1/8] target-arm: A64: add support for ld/st pair

[Peter Maydell]

On 12 December 2013 12:14, C Fontana <claudio.fontana@linaro.org> wrote:
> I think that there is more than the missing return:
>
> we need to handle the case 0 as well, as it's a perfectly valid form
> of a load/store pair:
> it's the Load/Store no-allocate pair (offset) (LDNP, STNP).
>
> So in my view we need to add a case 0 where we handle  the load/store
> no-allocate pair,
> and no default case, or a default case where we assert(0) for unreachable code,
> since all possible index values (2 bits) should be handled by the
> switch statement.

Yep. I've added support for the non-temporal versions
(pretty easy since qemu doesn't care about cache allocation
hints) to my patchstack so we'll get this in the next
version of the patchset.

thanks
-- PMM