Initial import of qemu-2.4.1HEADmaster

31 files changed, 28724 insertions, 0 deletions

diff --git a/tcg/LICENSE b/tcg/LICENSE
new file mode 100644
index 00000000..be817fa1
--- /dev/null
+++ b/tcg/LICENSE
@@ -0,0 +1,3 @@
+All the files in this directory and subdirectories are released under
+a BSD like license (see header in each file). No other license is
+accepted.
diff --git a/tcg/README b/tcg/README
new file mode 100644
index 00000000..a550ff17
--- /dev/null
+++ b/tcg/README
@@ -0,0 +1,551 @@
+Tiny Code Generator - Fabrice Bellard.
+
+1) Introduction
+
+TCG (Tiny Code Generator) began as a generic backend for a C
+compiler. It was simplified to be used in QEMU. It also has its roots
+in the QOP code generator written by Paul Brook. 
+
+2) Definitions
+
+The TCG "target" is the architecture for which we generate the
+code. It is of course not the same as the "target" of QEMU which is
+the emulated architecture. As TCG started as a generic C backend used
+for cross compiling, it is assumed that the TCG target is different
+from the host, although it is never the case for QEMU.
+
+In this document, we use "guest" to specify what architecture we are
+emulating; "target" always means the TCG target, the machine on which
+we are running QEMU.
+
+A TCG "function" corresponds to a QEMU Translated Block (TB).
+
+A TCG "temporary" is a variable only live in a basic
+block. Temporaries are allocated explicitly in each function.
+
+A TCG "local temporary" is a variable only live in a function. Local
+temporaries are allocated explicitly in each function.
+
+A TCG "global" is a variable which is live in all the functions
+(equivalent of a C global variable). They are defined before the
+functions defined. A TCG global can be a memory location (e.g. a QEMU
+CPU register), a fixed host register (e.g. the QEMU CPU state pointer)
+or a memory location which is stored in a register outside QEMU TBs
+(not implemented yet).
+
+A TCG "basic block" corresponds to a list of instructions terminated
+by a branch instruction. 
+
+An operation with "undefined behavior" may result in a crash.
+
+An operation with "unspecified behavior" shall not crash.  However,
+the result may be one of several possibilities so may be considered
+an "undefined result".
+
+3) Intermediate representation
+
+3.1) Introduction
+
+TCG instructions operate on variables which are temporaries, local
+temporaries or globals. TCG instructions and variables are strongly
+typed. Two types are supported: 32 bit integers and 64 bit
+integers. Pointers are defined as an alias to 32 bit or 64 bit
+integers depending on the TCG target word size.
+
+Each instruction has a fixed number of output variable operands, input
+variable operands and always constant operands.
+
+The notable exception is the call instruction which has a variable
+number of outputs and inputs.
+
+In the textual form, output operands usually come first, followed by
+input operands, followed by constant operands. The output type is
+included in the instruction name. Constants are prefixed with a '$'.
+
+add_i32 t0, t1, t2  (t0 <- t1 + t2)
+
+3.2) Assumptions
+
+* Basic blocks
+
+- Basic blocks end after branches (e.g. brcond_i32 instruction),
+  goto_tb and exit_tb instructions.
+- Basic blocks start after the end of a previous basic block, or at a
+  set_label instruction.
+
+After the end of a basic block, the content of temporaries is
+destroyed, but local temporaries and globals are preserved.
+
+* Floating point types are not supported yet
+
+* Pointers: depending on the TCG target, pointer size is 32 bit or 64
+  bit. The type TCG_TYPE_PTR is an alias to TCG_TYPE_I32 or
+  TCG_TYPE_I64.
+
+* Helpers:
+
+Using the tcg_gen_helper_x_y it is possible to call any function
+taking i32, i64 or pointer types. By default, before calling a helper,
+all globals are stored at their canonical location and it is assumed
+that the function can modify them. By default, the helper is allowed to
+modify the CPU state or raise an exception.
+
+This can be overridden using the following function modifiers:
+- TCG_CALL_NO_READ_GLOBALS means that the helper does not read globals,
+  either directly or via an exception. They will not be saved to their
+  canonical locations before calling the helper.
+- TCG_CALL_NO_WRITE_GLOBALS means that the helper does not modify any globals.
+  They will only be saved to their canonical location before calling helpers,
+  but they won't be reloaded afterwise.
+- TCG_CALL_NO_SIDE_EFFECTS means that the call to the function is removed if
+  the return value is not used.
+
+Note that TCG_CALL_NO_READ_GLOBALS implies TCG_CALL_NO_WRITE_GLOBALS.
+
+On some TCG targets (e.g. x86), several calling conventions are
+supported.
+
+* Branches:
+
+Use the instruction 'br' to jump to a label.
+
+3.3) Code Optimizations
+
+When generating instructions, you can count on at least the following
+optimizations:
+
+- Single instructions are simplified, e.g.
+
+   and_i32 t0, t0, $0xffffffff
+    
+  is suppressed.
+
+- A liveness analysis is done at the basic block level. The
+  information is used to suppress moves from a dead variable to
+  another one. It is also used to remove instructions which compute
+  dead results. The later is especially useful for condition code
+  optimization in QEMU.
+
+  In the following example:
+
+  add_i32 t0, t1, t2
+  add_i32 t0, t0, $1
+  mov_i32 t0, $1
+
+  only the last instruction is kept.
+
+3.4) Instruction Reference
+
+********* Function call
+
+* call <ret> <params> ptr
+
+call function 'ptr' (pointer type)
+
+<ret> optional 32 bit or 64 bit return value
+<params> optional 32 bit or 64 bit parameters
+
+********* Jumps/Labels
+
+* set_label $label
+
+Define label 'label' at the current program point.
+
+* br $label
+
+Jump to label.
+
+* brcond_i32/i64 t0, t1, cond, label
+
+Conditional jump if t0 cond t1 is true. cond can be:
+    TCG_COND_EQ
+    TCG_COND_NE
+    TCG_COND_LT /* signed */
+    TCG_COND_GE /* signed */
+    TCG_COND_LE /* signed */
+    TCG_COND_GT /* signed */
+    TCG_COND_LTU /* unsigned */
+    TCG_COND_GEU /* unsigned */
+    TCG_COND_LEU /* unsigned */
+    TCG_COND_GTU /* unsigned */
+
+********* Arithmetic
+
+* add_i32/i64 t0, t1, t2
+
+t0=t1+t2
+
+* sub_i32/i64 t0, t1, t2
+
+t0=t1-t2
+
+* neg_i32/i64 t0, t1
+
+t0=-t1 (two's complement)
+
+* mul_i32/i64 t0, t1, t2
+
+t0=t1*t2
+
+* div_i32/i64 t0, t1, t2
+
+t0=t1/t2 (signed). Undefined behavior if division by zero or overflow.
+
+* divu_i32/i64 t0, t1, t2
+
+t0=t1/t2 (unsigned). Undefined behavior if division by zero.
+
+* rem_i32/i64 t0, t1, t2
+
+t0=t1%t2 (signed). Undefined behavior if division by zero or overflow.
+
+* remu_i32/i64 t0, t1, t2
+
+t0=t1%t2 (unsigned). Undefined behavior if division by zero.
+
+********* Logical
+
+* and_i32/i64 t0, t1, t2
+
+t0=t1&t2
+
+* or_i32/i64 t0, t1, t2
+
+t0=t1|t2
+
+* xor_i32/i64 t0, t1, t2
+
+t0=t1^t2
+
+* not_i32/i64 t0, t1
+
+t0=~t1
+
+* andc_i32/i64 t0, t1, t2
+
+t0=t1&~t2
+
+* eqv_i32/i64 t0, t1, t2
+
+t0=~(t1^t2), or equivalently, t0=t1^~t2
+
+* nand_i32/i64 t0, t1, t2
+
+t0=~(t1&t2)
+
+* nor_i32/i64 t0, t1, t2
+
+t0=~(t1|t2)
+
+* orc_i32/i64 t0, t1, t2
+
+t0=t1|~t2
+
+********* Shifts/Rotates
+
+* shl_i32/i64 t0, t1, t2
+
+t0=t1 << t2. Unspecified behavior if t2 < 0 or t2 >= 32 (resp 64)
+
+* shr_i32/i64 t0, t1, t2
+
+t0=t1 >> t2 (unsigned). Unspecified behavior if t2 < 0 or t2 >= 32 (resp 64)
+
+* sar_i32/i64 t0, t1, t2
+
+t0=t1 >> t2 (signed). Unspecified behavior if t2 < 0 or t2 >= 32 (resp 64)
+
+* rotl_i32/i64 t0, t1, t2
+
+Rotation of t2 bits to the left.
+Unspecified behavior if t2 < 0 or t2 >= 32 (resp 64)
+
+* rotr_i32/i64 t0, t1, t2
+
+Rotation of t2 bits to the right.
+Unspecified behavior if t2 < 0 or t2 >= 32 (resp 64)
+
+********* Misc
+
+* mov_i32/i64 t0, t1
+
+t0 = t1
+
+Move t1 to t0 (both operands must have the same type).
+
+* ext8s_i32/i64 t0, t1
+ext8u_i32/i64 t0, t1
+ext16s_i32/i64 t0, t1
+ext16u_i32/i64 t0, t1
+ext32s_i64 t0, t1
+ext32u_i64 t0, t1
+
+8, 16 or 32 bit sign/zero extension (both operands must have the same type)
+
+* bswap16_i32/i64 t0, t1
+
+16 bit byte swap on a 32/64 bit value. It assumes that the two/six high order
+bytes are set to zero.
+
+* bswap32_i32/i64 t0, t1
+
+32 bit byte swap on a 32/64 bit value. With a 64 bit value, it assumes that
+the four high order bytes are set to zero.
+
+* bswap64_i64 t0, t1
+
+64 bit byte swap
+
+* discard_i32/i64 t0
+
+Indicate that the value of t0 won't be used later. It is useful to
+force dead code elimination.
+
+* deposit_i32/i64 dest, t1, t2, pos, len
+
+Deposit T2 as a bitfield into T1, placing the result in DEST.
+The bitfield is described by POS/LEN, which are immediate values:
+
+  LEN - the length of the bitfield
+  POS - the position of the first bit, counting from the LSB
+
+For example, pos=8, len=4 indicates a 4-bit field at bit 8.
+This operation would be equivalent to
+
+  dest = (t1 & ~0x0f00) | ((t2 << 8) & 0x0f00)
+
+* trunc_shr_i32 t0, t1, pos
+
+For 64-bit hosts only, right shift the 64-bit input T1 by POS and
+truncate to 32-bit output T0.  Depending on the host, this may be
+a simple mov/shift, or may require additional canonicalization.
+
+********* Conditional moves
+
+* setcond_i32/i64 dest, t1, t2, cond
+
+dest = (t1 cond t2)
+
+Set DEST to 1 if (T1 cond T2) is true, otherwise set to 0.
+
+* movcond_i32/i64 dest, c1, c2, v1, v2, cond
+
+dest = (c1 cond c2 ? v1 : v2)
+
+Set DEST to V1 if (C1 cond C2) is true, otherwise set to V2.
+
+********* Type conversions
+
+* ext_i32_i64 t0, t1
+Convert t1 (32 bit) to t0 (64 bit) and does sign extension
+
+* extu_i32_i64 t0, t1
+Convert t1 (32 bit) to t0 (64 bit) and does zero extension
+
+* trunc_i64_i32 t0, t1
+Truncate t1 (64 bit) to t0 (32 bit)
+
+* concat_i32_i64 t0, t1, t2
+Construct t0 (64-bit) taking the low half from t1 (32 bit) and the high half
+from t2 (32 bit).
+
+* concat32_i64 t0, t1, t2
+Construct t0 (64-bit) taking the low half from t1 (64 bit) and the high half
+from t2 (64 bit).
+
+********* Load/Store
+
+* ld_i32/i64 t0, t1, offset
+ld8s_i32/i64 t0, t1, offset
+ld8u_i32/i64 t0, t1, offset
+ld16s_i32/i64 t0, t1, offset
+ld16u_i32/i64 t0, t1, offset
+ld32s_i64 t0, t1, offset
+ld32u_i64 t0, t1, offset
+
+t0 = read(t1 + offset)
+Load 8, 16, 32 or 64 bits with or without sign extension from host memory. 
+offset must be a constant.
+
+* st_i32/i64 t0, t1, offset
+st8_i32/i64 t0, t1, offset
+st16_i32/i64 t0, t1, offset
+st32_i64 t0, t1, offset
+
+write(t0, t1 + offset)
+Write 8, 16, 32 or 64 bits to host memory.
+
+All this opcodes assume that the pointed host memory doesn't correspond
+to a global. In the latter case the behaviour is unpredictable.
+
+********* Multiword arithmetic support
+
+* add2_i32/i64 t0_low, t0_high, t1_low, t1_high, t2_low, t2_high
+* sub2_i32/i64 t0_low, t0_high, t1_low, t1_high, t2_low, t2_high
+
+Similar to add/sub, except that the double-word inputs T1 and T2 are
+formed from two single-word arguments, and the double-word output T0
+is returned in two single-word outputs.
+
+* mulu2_i32/i64 t0_low, t0_high, t1, t2
+
+Similar to mul, except two unsigned inputs T1 and T2 yielding the full
+double-word product T0.  The later is returned in two single-word outputs.
+
+* muls2_i32/i64 t0_low, t0_high, t1, t2
+
+Similar to mulu2, except the two inputs T1 and T2 are signed.
+
+********* 64-bit guest on 32-bit host support
+
+The following opcodes are internal to TCG.  Thus they are to be implemented by
+32-bit host code generators, but are not to be emitted by guest translators.
+They are emitted as needed by inline functions within "tcg-op.h".
+
+* brcond2_i32 t0_low, t0_high, t1_low, t1_high, cond, label
+
+Similar to brcond, except that the 64-bit values T0 and T1
+are formed from two 32-bit arguments.
+
+* setcond2_i32 dest, t1_low, t1_high, t2_low, t2_high, cond
+
+Similar to setcond, except that the 64-bit values T1 and T2 are
+formed from two 32-bit arguments.  The result is a 32-bit value.
+
+********* QEMU specific operations
+
+* exit_tb t0
+
+Exit the current TB and return the value t0 (word type).
+
+* goto_tb index
+
+Exit the current TB and jump to the TB index 'index' (constant) if the
+current TB was linked to this TB. Otherwise execute the next
+instructions. Only indices 0 and 1 are valid and tcg_gen_goto_tb may be issued
+at most once with each slot index per TB.
+
+* qemu_ld_i32/i64 t0, t1, flags, memidx
+* qemu_st_i32/i64 t0, t1, flags, memidx
+
+Load data at the guest address t1 into t0, or store data in t0 at guest
+address t1.  The _i32/_i64 size applies to the size of the input/output
+register t0 only.  The address t1 is always sized according to the guest,
+and the width of the memory operation is controlled by flags.
+
+Both t0 and t1 may be split into little-endian ordered pairs of registers
+if dealing with 64-bit quantities on a 32-bit host.
+
+The memidx selects the qemu tlb index to use (e.g. user or kernel access).
+The flags are the TCGMemOp bits, selecting the sign, width, and endianness
+of the memory access.
+
+For a 32-bit host, qemu_ld/st_i64 is guaranteed to only be used with a
+64-bit memory access specified in flags.
+
+*********
+
+Note 1: Some shortcuts are defined when the last operand is known to be
+a constant (e.g. addi for add, movi for mov).
+
+Note 2: When using TCG, the opcodes must never be generated directly
+as some of them may not be available as "real" opcodes. Always use the
+function tcg_gen_xxx(args).
+
+4) Backend
+
+tcg-target.h contains the target specific definitions. tcg-target.c
+contains the target specific code.
+
+4.1) Assumptions
+
+The target word size (TCG_TARGET_REG_BITS) is expected to be 32 bit or
+64 bit. It is expected that the pointer has the same size as the word.
+
+On a 32 bit target, all 64 bit operations are converted to 32 bits. A
+few specific operations must be implemented to allow it (see add2_i32,
+sub2_i32, brcond2_i32).
+
+Floating point operations are not supported in this version. A
+previous incarnation of the code generator had full support of them,
+but it is better to concentrate on integer operations first.
+
+On a 64 bit target, no assumption is made in TCG about the storage of
+the 32 bit values in 64 bit registers.
+
+4.2) Constraints
+
+GCC like constraints are used to define the constraints of every
+instruction. Memory constraints are not supported in this
+version. Aliases are specified in the input operands as for GCC.
+
+The same register may be used for both an input and an output, even when
+they are not explicitly aliased.  If an op expands to multiple target
+instructions then care must be taken to avoid clobbering input values.
+GCC style "early clobber" outputs are not currently supported.
+
+A target can define specific register or constant constraints. If an
+operation uses a constant input constraint which does not allow all
+constants, it must also accept registers in order to have a fallback.
+
+The movi_i32 and movi_i64 operations must accept any constants.
+
+The mov_i32 and mov_i64 operations must accept any registers of the
+same type.
+
+The ld/st instructions must accept signed 32 bit constant offsets. It
+can be implemented by reserving a specific register to compute the
+address if the offset is too big.
+
+The ld/st instructions must accept any destination (ld) or source (st)
+register.
+
+4.3) Function call assumptions
+
+- The only supported types for parameters and return value are: 32 and
+  64 bit integers and pointer.
+- The stack grows downwards.
+- The first N parameters are passed in registers.
+- The next parameters are passed on the stack by storing them as words.
+- Some registers are clobbered during the call. 
+- The function can return 0 or 1 value in registers. On a 32 bit
+  target, functions must be able to return 2 values in registers for
+  64 bit return type.
+
+5) Recommended coding rules for best performance
+
+- Use globals to represent the parts of the QEMU CPU state which are
+  often modified, e.g. the integer registers and the condition
+  codes. TCG will be able to use host registers to store them.
+
+- Avoid globals stored in fixed registers. They must be used only to
+  store the pointer to the CPU state and possibly to store a pointer
+  to a register window.
+
+- Use temporaries. Use local temporaries only when really needed,
+  e.g. when you need to use a value after a jump. Local temporaries
+  introduce a performance hit in the current TCG implementation: their
+  content is saved to memory at end of each basic block.
+
+- Free temporaries and local temporaries when they are no longer used
+  (tcg_temp_free). Since tcg_const_x() also creates a temporary, you
+  should free it after it is used. Freeing temporaries does not yield
+  a better generated code, but it reduces the memory usage of TCG and
+  the speed of the translation.
+
+- Don't hesitate to use helpers for complicated or seldom used guest
+  instructions. There is little performance advantage in using TCG to
+  implement guest instructions taking more than about twenty TCG
+  instructions. Note that this rule of thumb is more applicable to
+  helpers doing complex logic or arithmetic, where the C compiler has
+  scope to do a good job of optimisation; it is less relevant where
+  the instruction is mostly doing loads and stores, and in those cases
+  inline TCG may still be faster for longer sequences.
+
+- The hard limit on the number of TCG instructions you can generate
+  per guest instruction is set by MAX_OP_PER_INSTR in exec-all.h --
+  you cannot exceed this without risking a buffer overrun.
+
+- Use the 'discard' instruction if you know that TCG won't be able to
+  prove that a given global is "dead" at a given program point. The
+  x86 guest uses it to improve the condition codes optimisation.
diff --git a/tcg/TODO b/tcg/TODO
new file mode 100644
index 00000000..07478477
--- /dev/null
+++ b/tcg/TODO
@@ -0,0 +1,14 @@
+- Add new instructions such as: clz, ctz, popcnt.
+
+- See if it is worth exporting mul2, mulu2, div2, divu2. 
+
+- Support of globals saved in fixed registers between TBs.
+
+Ideas:
+
+- Move the slow part of the qemu_ld/st ops after the end of the TB.
+
+- Change exception syntax to get closer to QOP system (exception
+  parameters given with a specific instruction).
+
+- Add float and vector support.
diff --git a/tcg/aarch64/tcg-target.c b/tcg/aarch64/tcg-target.c
new file mode 100644
index 00000000..bad8b1de
--- /dev/null
+++ b/tcg/aarch64/tcg-target.c
@@ -0,0 +1,1882 @@
+/*
+ * Initial TCG Implementation for aarch64
+ *
+ * Copyright (c) 2013 Huawei Technologies Duesseldorf GmbH
+ * Written by Claudio Fontana
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2 or
+ * (at your option) any later version.
+ *
+ * See the COPYING file in the top-level directory for details.
+ */
+
+#include "tcg-be-ldst.h"
+#include "qemu/bitops.h"
+
+/* We're going to re-use TCGType in setting of the SF bit, which controls
+   the size of the operation performed.  If we know the values match, it
+   makes things much cleaner.  */
+QEMU_BUILD_BUG_ON(TCG_TYPE_I32 != 0 || TCG_TYPE_I64 != 1);
+
+#ifndef NDEBUG
+static const char * const tcg_target_reg_names[TCG_TARGET_NB_REGS] = {
+    "%x0", "%x1", "%x2", "%x3", "%x4", "%x5", "%x6", "%x7",
+    "%x8", "%x9", "%x10", "%x11", "%x12", "%x13", "%x14", "%x15",
+    "%x16", "%x17", "%x18", "%x19", "%x20", "%x21", "%x22", "%x23",
+    "%x24", "%x25", "%x26", "%x27", "%x28", "%fp", "%x30", "%sp",
+};
+#endif /* NDEBUG */
+
+static const int tcg_target_reg_alloc_order[] = {
+    TCG_REG_X20, TCG_REG_X21, TCG_REG_X22, TCG_REG_X23,
+    TCG_REG_X24, TCG_REG_X25, TCG_REG_X26, TCG_REG_X27,
+    TCG_REG_X28, /* we will reserve this for GUEST_BASE if configured */
+
+    TCG_REG_X8, TCG_REG_X9, TCG_REG_X10, TCG_REG_X11,
+    TCG_REG_X12, TCG_REG_X13, TCG_REG_X14, TCG_REG_X15,
+    TCG_REG_X16, TCG_REG_X17,
+
+    TCG_REG_X0, TCG_REG_X1, TCG_REG_X2, TCG_REG_X3,
+    TCG_REG_X4, TCG_REG_X5, TCG_REG_X6, TCG_REG_X7,
+
+    /* X18 reserved by system */
+    /* X19 reserved for AREG0 */
+    /* X29 reserved as fp */
+    /* X30 reserved as temporary */
+};
+
+static const int tcg_target_call_iarg_regs[8] = {
+    TCG_REG_X0, TCG_REG_X1, TCG_REG_X2, TCG_REG_X3,
+    TCG_REG_X4, TCG_REG_X5, TCG_REG_X6, TCG_REG_X7
+};
+static const int tcg_target_call_oarg_regs[1] = {
+    TCG_REG_X0
+};
+
+#define TCG_REG_TMP TCG_REG_X30
+
+#ifndef CONFIG_SOFTMMU
+/* Note that XZR cannot be encoded in the address base register slot,
+   as that actaully encodes SP.  So if we need to zero-extend the guest
+   address, via the address index register slot, we need to load even
+   a zero guest base into a register.  */
+#define USE_GUEST_BASE     (GUEST_BASE != 0 || TARGET_LONG_BITS == 32)
+
+# ifdef CONFIG_USE_GUEST_BASE
+#  define TCG_REG_GUEST_BASE TCG_REG_X28
+# else
+#  define TCG_REG_GUEST_BASE TCG_REG_XZR
+# endif
+#endif
+
+static inline void reloc_pc26(tcg_insn_unit *code_ptr, tcg_insn_unit *target)
+{
+    ptrdiff_t offset = target - code_ptr;
+    assert(offset == sextract64(offset, 0, 26));
+    /* read instruction, mask away previous PC_REL26 parameter contents,
+       set the proper offset, then write back the instruction. */
+    *code_ptr = deposit32(*code_ptr, 0, 26, offset);
+}
+
+static inline void reloc_pc19(tcg_insn_unit *code_ptr, tcg_insn_unit *target)
+{
+    ptrdiff_t offset = target - code_ptr;
+    assert(offset == sextract64(offset, 0, 19));
+    *code_ptr = deposit32(*code_ptr, 5, 19, offset);
+}
+
+static inline void patch_reloc(tcg_insn_unit *code_ptr, int type,
+                               intptr_t value, intptr_t addend)
+{
+    assert(addend == 0);
+    switch (type) {
+    case R_AARCH64_JUMP26:
+    case R_AARCH64_CALL26:
+        reloc_pc26(code_ptr, (tcg_insn_unit *)value);
+        break;
+    case R_AARCH64_CONDBR19:
+        reloc_pc19(code_ptr, (tcg_insn_unit *)value);
+        break;
+    default:
+        tcg_abort();
+    }
+}
+
+#define TCG_CT_CONST_AIMM 0x100
+#define TCG_CT_CONST_LIMM 0x200
+#define TCG_CT_CONST_ZERO 0x400
+#define TCG_CT_CONST_MONE 0x800
+
+/* parse target specific constraints */
+static int target_parse_constraint(TCGArgConstraint *ct,
+                                   const char **pct_str)
+{
+    const char *ct_str = *pct_str;
+
+    switch (ct_str[0]) {
+    case 'r':
+        ct->ct |= TCG_CT_REG;
+        tcg_regset_set32(ct->u.regs, 0, (1ULL << TCG_TARGET_NB_REGS) - 1);
+        break;
+    case 'l': /* qemu_ld / qemu_st address, data_reg */
+        ct->ct |= TCG_CT_REG;
+        tcg_regset_set32(ct->u.regs, 0, (1ULL << TCG_TARGET_NB_REGS) - 1);
+#ifdef CONFIG_SOFTMMU
+        /* x0 and x1 will be overwritten when reading the tlb entry,
+           and x2, and x3 for helper args, better to avoid using them. */
+        tcg_regset_reset_reg(ct->u.regs, TCG_REG_X0);
+        tcg_regset_reset_reg(ct->u.regs, TCG_REG_X1);
+        tcg_regset_reset_reg(ct->u.regs, TCG_REG_X2);
+        tcg_regset_reset_reg(ct->u.regs, TCG_REG_X3);
+#endif
+        break;
+    case 'A': /* Valid for arithmetic immediate (positive or negative).  */
+        ct->ct |= TCG_CT_CONST_AIMM;
+        break;
+    case 'L': /* Valid for logical immediate.  */
+        ct->ct |= TCG_CT_CONST_LIMM;
+        break;
+    case 'M': /* minus one */
+        ct->ct |= TCG_CT_CONST_MONE;
+        break;
+    case 'Z': /* zero */
+        ct->ct |= TCG_CT_CONST_ZERO;
+        break;
+    default:
+        return -1;
+    }
+
+    ct_str++;
+    *pct_str = ct_str;
+    return 0;
+}
+
+static inline bool is_aimm(uint64_t val)
+{
+    return (val & ~0xfff) == 0 || (val & ~0xfff000) == 0;
+}
+
+static inline bool is_limm(uint64_t val)
+{
+    /* Taking a simplified view of the logical immediates for now, ignoring
+       the replication that can happen across the field.  Match bit patterns
+       of the forms
+           0....01....1
+           0..01..10..0
+       and their inverses.  */
+
+    /* Make things easier below, by testing the form with msb clear. */
+    if ((int64_t)val < 0) {
+        val = ~val;
+    }
+    if (val == 0) {
+        return false;
+    }
+    val += val & -val;
+    return (val & (val - 1)) == 0;
+}
+
+static int tcg_target_const_match(tcg_target_long val, TCGType type,
+                                  const TCGArgConstraint *arg_ct)
+{
+    int ct = arg_ct->ct;
+
+    if (ct & TCG_CT_CONST) {
+        return 1;
+    }
+    if (type == TCG_TYPE_I32) {
+        val = (int32_t)val;
+    }
+    if ((ct & TCG_CT_CONST_AIMM) && (is_aimm(val) || is_aimm(-val))) {
+        return 1;
+    }
+    if ((ct & TCG_CT_CONST_LIMM) && is_limm(val)) {
+        return 1;
+    }
+    if ((ct & TCG_CT_CONST_ZERO) && val == 0) {
+        return 1;
+    }
+    if ((ct & TCG_CT_CONST_MONE) && val == -1) {
+        return 1;
+    }
+
+    return 0;
+}
+
+enum aarch64_cond_code {
+    COND_EQ = 0x0,
+    COND_NE = 0x1,
+    COND_CS = 0x2,     /* Unsigned greater or equal */
+    COND_HS = COND_CS, /* ALIAS greater or equal */
+    COND_CC = 0x3,     /* Unsigned less than */
+    COND_LO = COND_CC, /* ALIAS Lower */
+    COND_MI = 0x4,     /* Negative */
+    COND_PL = 0x5,     /* Zero or greater */
+    COND_VS = 0x6,     /* Overflow */
+    COND_VC = 0x7,     /* No overflow */
+    COND_HI = 0x8,     /* Unsigned greater than */
+    COND_LS = 0x9,     /* Unsigned less or equal */
+    COND_GE = 0xa,
+    COND_LT = 0xb,
+    COND_GT = 0xc,
+    COND_LE = 0xd,
+    COND_AL = 0xe,
+    COND_NV = 0xf, /* behaves like COND_AL here */
+};
+
+static const enum aarch64_cond_code tcg_cond_to_aarch64[] = {
+    [TCG_COND_EQ] = COND_EQ,
+    [TCG_COND_NE] = COND_NE,
+    [TCG_COND_LT] = COND_LT,
+    [TCG_COND_GE] = COND_GE,
+    [TCG_COND_LE] = COND_LE,
+    [TCG_COND_GT] = COND_GT,
+    /* unsigned */
+    [TCG_COND_LTU] = COND_LO,
+    [TCG_COND_GTU] = COND_HI,
+    [TCG_COND_GEU] = COND_HS,
+    [TCG_COND_LEU] = COND_LS,
+};
+
+typedef enum {
+    LDST_ST = 0,    /* store */
+    LDST_LD = 1,    /* load */
+    LDST_LD_S_X = 2,  /* load and sign-extend into Xt */
+    LDST_LD_S_W = 3,  /* load and sign-extend into Wt */
+} AArch64LdstType;
+
+/* We encode the format of the insn into the beginning of the name, so that
+   we can have the preprocessor help "typecheck" the insn vs the output
+   function.  Arm didn't provide us with nice names for the formats, so we
+   use the section number of the architecture reference manual in which the
+   instruction group is described.  */
+typedef enum {
+    /* Compare and branch (immediate).  */
+    I3201_CBZ       = 0x34000000,
+    I3201_CBNZ      = 0x35000000,
+
+    /* Conditional branch (immediate).  */
+    I3202_B_C       = 0x54000000,
+
+    /* Unconditional branch (immediate).  */
+    I3206_B         = 0x14000000,
+    I3206_BL        = 0x94000000,
+
+    /* Unconditional branch (register).  */
+    I3207_BR        = 0xd61f0000,
+    I3207_BLR       = 0xd63f0000,
+    I3207_RET       = 0xd65f0000,
+
+    /* Load/store register.  Described here as 3.3.12, but the helper
+       that emits them can transform to 3.3.10 or 3.3.13.  */
+    I3312_STRB      = 0x38000000 | LDST_ST << 22 | MO_8 << 30,
+    I3312_STRH      = 0x38000000 | LDST_ST << 22 | MO_16 << 30,
+    I3312_STRW      = 0x38000000 | LDST_ST << 22 | MO_32 << 30,
+    I3312_STRX      = 0x38000000 | LDST_ST << 22 | MO_64 << 30,
+
+    I3312_LDRB      = 0x38000000 | LDST_LD << 22 | MO_8 << 30,
+    I3312_LDRH      = 0x38000000 | LDST_LD << 22 | MO_16 << 30,
+    I3312_LDRW      = 0x38000000 | LDST_LD << 22 | MO_32 << 30,
+    I3312_LDRX      = 0x38000000 | LDST_LD << 22 | MO_64 << 30,
+
+    I3312_LDRSBW    = 0x38000000 | LDST_LD_S_W << 22 | MO_8 << 30,
+    I3312_LDRSHW    = 0x38000000 | LDST_LD_S_W << 22 | MO_16 << 30,
+
+    I3312_LDRSBX    = 0x38000000 | LDST_LD_S_X << 22 | MO_8 << 30,
+    I3312_LDRSHX    = 0x38000000 | LDST_LD_S_X << 22 | MO_16 << 30,
+    I3312_LDRSWX    = 0x38000000 | LDST_LD_S_X << 22 | MO_32 << 30,
+
+    I3312_TO_I3310  = 0x00200800,
+    I3312_TO_I3313  = 0x01000000,
+
+    /* Load/store register pair instructions.  */
+    I3314_LDP       = 0x28400000,
+    I3314_STP       = 0x28000000,
+
+    /* Add/subtract immediate instructions.  */
+    I3401_ADDI      = 0x11000000,
+    I3401_ADDSI     = 0x31000000,
+    I3401_SUBI      = 0x51000000,
+    I3401_SUBSI     = 0x71000000,
+
+    /* Bitfield instructions.  */
+    I3402_BFM       = 0x33000000,
+    I3402_SBFM      = 0x13000000,
+    I3402_UBFM      = 0x53000000,
+
+    /* Extract instruction.  */
+    I3403_EXTR      = 0x13800000,
+
+    /* Logical immediate instructions.  */
+    I3404_ANDI      = 0x12000000,
+    I3404_ORRI      = 0x32000000,
+    I3404_EORI      = 0x52000000,
+
+    /* Move wide immediate instructions.  */
+    I3405_MOVN      = 0x12800000,
+    I3405_MOVZ      = 0x52800000,
+    I3405_MOVK      = 0x72800000,
+
+    /* PC relative addressing instructions.  */
+    I3406_ADR       = 0x10000000,
+    I3406_ADRP      = 0x90000000,
+
+    /* Add/subtract shifted register instructions (without a shift).  */
+    I3502_ADD       = 0x0b000000,
+    I3502_ADDS      = 0x2b000000,
+    I3502_SUB       = 0x4b000000,
+    I3502_SUBS      = 0x6b000000,
+
+    /* Add/subtract shifted register instructions (with a shift).  */
+    I3502S_ADD_LSL  = I3502_ADD,
+
+    /* Add/subtract with carry instructions.  */
+    I3503_ADC       = 0x1a000000,
+    I3503_SBC       = 0x5a000000,
+
+    /* Conditional select instructions.  */
+    I3506_CSEL      = 0x1a800000,
+    I3506_CSINC     = 0x1a800400,
+
+    /* Data-processing (1 source) instructions.  */
+    I3507_REV16     = 0x5ac00400,
+    I3507_REV32     = 0x5ac00800,
+    I3507_REV64     = 0x5ac00c00,
+
+    /* Data-processing (2 source) instructions.  */
+    I3508_LSLV      = 0x1ac02000,
+    I3508_LSRV      = 0x1ac02400,
+    I3508_ASRV      = 0x1ac02800,
+    I3508_RORV      = 0x1ac02c00,
+    I3508_SMULH     = 0x9b407c00,
+    I3508_UMULH     = 0x9bc07c00,
+    I3508_UDIV      = 0x1ac00800,
+    I3508_SDIV      = 0x1ac00c00,
+
+    /* Data-processing (3 source) instructions.  */
+    I3509_MADD      = 0x1b000000,
+    I3509_MSUB      = 0x1b008000,
+
+    /* Logical shifted register instructions (without a shift).  */
+    I3510_AND       = 0x0a000000,
+    I3510_BIC       = 0x0a200000,
+    I3510_ORR       = 0x2a000000,
+    I3510_ORN       = 0x2a200000,
+    I3510_EOR       = 0x4a000000,
+    I3510_EON       = 0x4a200000,
+    I3510_ANDS      = 0x6a000000,
+} AArch64Insn;
+
+static inline uint32_t tcg_in32(TCGContext *s)
+{
+    uint32_t v = *(uint32_t *)s->code_ptr;
+    return v;
+}
+
+/* Emit an opcode with "type-checking" of the format.  */
+#define tcg_out_insn(S, FMT, OP, ...) \
+    glue(tcg_out_insn_,FMT)(S, glue(glue(glue(I,FMT),_),OP), ## __VA_ARGS__)
+
+static void tcg_out_insn_3201(TCGContext *s, AArch64Insn insn, TCGType ext,
+                              TCGReg rt, int imm19)
+{
+    tcg_out32(s, insn | ext << 31 | (imm19 & 0x7ffff) << 5 | rt);
+}
+
+static void tcg_out_insn_3202(TCGContext *s, AArch64Insn insn,
+                              TCGCond c, int imm19)
+{
+    tcg_out32(s, insn | tcg_cond_to_aarch64[c] | (imm19 & 0x7ffff) << 5);
+}
+
+static void tcg_out_insn_3206(TCGContext *s, AArch64Insn insn, int imm26)
+{
+    tcg_out32(s, insn | (imm26 & 0x03ffffff));
+}
+
+static void tcg_out_insn_3207(TCGContext *s, AArch64Insn insn, TCGReg rn)
+{
+    tcg_out32(s, insn | rn << 5);
+}
+
+static void tcg_out_insn_3314(TCGContext *s, AArch64Insn insn,
+                              TCGReg r1, TCGReg r2, TCGReg rn,
+                              tcg_target_long ofs, bool pre, bool w)
+{
+    insn |= 1u << 31; /* ext */
+    insn |= pre << 24;
+    insn |= w << 23;
+
+    assert(ofs >= -0x200 && ofs < 0x200 && (ofs & 7) == 0);
+    insn |= (ofs & (0x7f << 3)) << (15 - 3);
+
+    tcg_out32(s, insn | r2 << 10 | rn << 5 | r1);
+}
+
+static void tcg_out_insn_3401(TCGContext *s, AArch64Insn insn, TCGType ext,
+                              TCGReg rd, TCGReg rn, uint64_t aimm)
+{
+    if (aimm > 0xfff) {
+        assert((aimm & 0xfff) == 0);
+        aimm >>= 12;
+        assert(aimm <= 0xfff);
+        aimm |= 1 << 12;  /* apply LSL 12 */
+    }
+    tcg_out32(s, insn | ext << 31 | aimm << 10 | rn << 5 | rd);
+}
+
+/* This function can be used for both 3.4.2 (Bitfield) and 3.4.4
+   (Logical immediate).  Both insn groups have N, IMMR and IMMS fields
+   that feed the DecodeBitMasks pseudo function.  */
+static void tcg_out_insn_3402(TCGContext *s, AArch64Insn insn, TCGType ext,
+                              TCGReg rd, TCGReg rn, int n, int immr, int imms)
+{
+    tcg_out32(s, insn | ext << 31 | n << 22 | immr << 16 | imms << 10
+              | rn << 5 | rd);
+}
+
+#define tcg_out_insn_3404  tcg_out_insn_3402
+
+static void tcg_out_insn_3403(TCGContext *s, AArch64Insn insn, TCGType ext,
+                              TCGReg rd, TCGReg rn, TCGReg rm, int imms)
+{
+    tcg_out32(s, insn | ext << 31 | ext << 22 | rm << 16 | imms << 10
+              | rn << 5 | rd);
+}
+
+/* This function is used for the Move (wide immediate) instruction group.
+   Note that SHIFT is a full shift count, not the 2 bit HW field. */
+static void tcg_out_insn_3405(TCGContext *s, AArch64Insn insn, TCGType ext,
+                              TCGReg rd, uint16_t half, unsigned shift)
+{
+    assert((shift & ~0x30) == 0);
+    tcg_out32(s, insn | ext << 31 | shift << (21 - 4) | half << 5 | rd);
+}
+
+static void tcg_out_insn_3406(TCGContext *s, AArch64Insn insn,
+                              TCGReg rd, int64_t disp)
+{
+    tcg_out32(s, insn | (disp & 3) << 29 | (disp & 0x1ffffc) << (5 - 2) | rd);
+}
+
+/* This function is for both 3.5.2 (Add/Subtract shifted register), for
+   the rare occasion when we actually want to supply a shift amount.  */
+static inline void tcg_out_insn_3502S(TCGContext *s, AArch64Insn insn,
+                                      TCGType ext, TCGReg rd, TCGReg rn,
+                                      TCGReg rm, int imm6)
+{
+    tcg_out32(s, insn | ext << 31 | rm << 16 | imm6 << 10 | rn << 5 | rd);
+}
+
+/* This function is for 3.5.2 (Add/subtract shifted register),
+   and 3.5.10 (Logical shifted register), for the vast majorty of cases
+   when we don't want to apply a shift.  Thus it can also be used for
+   3.5.3 (Add/subtract with carry) and 3.5.8 (Data processing 2 source).  */
+static void tcg_out_insn_3502(TCGContext *s, AArch64Insn insn, TCGType ext,
+                              TCGReg rd, TCGReg rn, TCGReg rm)
+{
+    tcg_out32(s, insn | ext << 31 | rm << 16 | rn << 5 | rd);
+}
+
+#define tcg_out_insn_3503  tcg_out_insn_3502
+#define tcg_out_insn_3508  tcg_out_insn_3502
+#define tcg_out_insn_3510  tcg_out_insn_3502
+
+static void tcg_out_insn_3506(TCGContext *s, AArch64Insn insn, TCGType ext,
+                              TCGReg rd, TCGReg rn, TCGReg rm, TCGCond c)
+{
+    tcg_out32(s, insn | ext << 31 | rm << 16 | rn << 5 | rd
+              | tcg_cond_to_aarch64[c] << 12);
+}
+
+static void tcg_out_insn_3507(TCGContext *s, AArch64Insn insn, TCGType ext,
+                              TCGReg rd, TCGReg rn)
+{
+    tcg_out32(s, insn | ext << 31 | rn << 5 | rd);
+}
+
+static void tcg_out_insn_3509(TCGContext *s, AArch64Insn insn, TCGType ext,
+                              TCGReg rd, TCGReg rn, TCGReg rm, TCGReg ra)
+{
+    tcg_out32(s, insn | ext << 31 | rm << 16 | ra << 10 | rn << 5 | rd);
+}
+
+static void tcg_out_insn_3310(TCGContext *s, AArch64Insn insn,
+                              TCGReg rd, TCGReg base, TCGType ext,
+                              TCGReg regoff)
+{
+    /* Note the AArch64Insn constants above are for C3.3.12.  Adjust.  */
+    tcg_out32(s, insn | I3312_TO_I3310 | regoff << 16 |
+              0x4000 | ext << 13 | base << 5 | rd);
+}
+
+static void tcg_out_insn_3312(TCGContext *s, AArch64Insn insn,
+                              TCGReg rd, TCGReg rn, intptr_t offset)
+{
+    tcg_out32(s, insn | (offset & 0x1ff) << 12 | rn << 5 | rd);
+}
+
+static void tcg_out_insn_3313(TCGContext *s, AArch64Insn insn,
+                              TCGReg rd, TCGReg rn, uintptr_t scaled_uimm)
+{
+    /* Note the AArch64Insn constants above are for C3.3.12.  Adjust.  */
+    tcg_out32(s, insn | I3312_TO_I3313 | scaled_uimm << 10 | rn << 5 | rd);
+}
+
+/* Register to register move using ORR (shifted register with no shift). */
+static void tcg_out_movr(TCGContext *s, TCGType ext, TCGReg rd, TCGReg rm)
+{
+    tcg_out_insn(s, 3510, ORR, ext, rd, TCG_REG_XZR, rm);
+}
+
+/* Register to register move using ADDI (move to/from SP).  */
+static void tcg_out_movr_sp(TCGContext *s, TCGType ext, TCGReg rd, TCGReg rn)
+{
+    tcg_out_insn(s, 3401, ADDI, ext, rd, rn, 0);
+}
+
+/* This function is used for the Logical (immediate) instruction group.
+   The value of LIMM must satisfy IS_LIMM.  See the comment above about
+   only supporting simplified logical immediates.  */
+static void tcg_out_logicali(TCGContext *s, AArch64Insn insn, TCGType ext,
+                             TCGReg rd, TCGReg rn, uint64_t limm)
+{
+    unsigned h, l, r, c;
+
+    assert(is_limm(limm));
+
+    h = clz64(limm);
+    l = ctz64(limm);
+    if (l == 0) {
+        r = 0;                  /* form 0....01....1 */
+        c = ctz64(~limm) - 1;
+        if (h == 0) {
+            r = clz64(~limm);   /* form 1..10..01..1 */
+            c += r;
+        }
+    } else {
+        r = 64 - l;             /* form 1....10....0 or 0..01..10..0 */
+        c = r - h - 1;
+    }
+    if (ext == TCG_TYPE_I32) {
+        r &= 31;
+        c &= 31;
+    }
+
+    tcg_out_insn_3404(s, insn, ext, rd, rn, ext, r, c);
+}
+
+static void tcg_out_movi(TCGContext *s, TCGType type, TCGReg rd,
+                         tcg_target_long value)
+{
+    AArch64Insn insn;
+    int i, wantinv, shift;
+    tcg_target_long svalue = value;
+    tcg_target_long ivalue = ~value;
+    tcg_target_long imask;
+
+    /* For 32-bit values, discard potential garbage in value.  For 64-bit
+       values within [2**31, 2**32-1], we can create smaller sequences by
+       interpreting this as a negative 32-bit number, while ensuring that
+       the high 32 bits are cleared by setting SF=0.  */
+    if (type == TCG_TYPE_I32 || (value & ~0xffffffffull) == 0) {
+        svalue = (int32_t)value;
+        value = (uint32_t)value;
+        ivalue = (uint32_t)ivalue;
+        type = TCG_TYPE_I32;
+    }
+
+    /* Speed things up by handling the common case of small positive
+       and negative values specially.  */
+    if ((value & ~0xffffull) == 0) {
+        tcg_out_insn(s, 3405, MOVZ, type, rd, value, 0);
+        return;
+    } else if ((ivalue & ~0xffffull) == 0) {
+        tcg_out_insn(s, 3405, MOVN, type, rd, ivalue, 0);
+        return;
+    }
+
+    /* Check for bitfield immediates.  For the benefit of 32-bit quantities,
+       use the sign-extended value.  That lets us match rotated values such
+       as 0xff0000ff with the same 64-bit logic matching 0xffffffffff0000ff. */
+    if (is_limm(svalue)) {
+        tcg_out_logicali(s, I3404_ORRI, type, rd, TCG_REG_XZR, svalue);
+        return;
+    }
+
+    /* Look for host pointer values within 4G of the PC.  This happens
+       often when loading pointers to QEMU's own data structures.  */
+    if (type == TCG_TYPE_I64) {
+        tcg_target_long disp = (value >> 12) - ((intptr_t)s->code_ptr >> 12);
+        if (disp == sextract64(disp, 0, 21)) {
+            tcg_out_insn(s, 3406, ADRP, rd, disp);
+            if (value & 0xfff) {
+                tcg_out_insn(s, 3401, ADDI, type, rd, rd, value & 0xfff);
+            }
+            return;
+        }
+    }
+
+    /* Would it take fewer insns to begin with MOVN?  For the value and its
+       inverse, count the number of 16-bit lanes that are 0.  */
+    for (i = wantinv = imask = 0; i < 64; i += 16) {
+        tcg_target_long mask = 0xffffull << i;
+        if ((value & mask) == 0) {
+            wantinv -= 1;
+        }
+        if ((ivalue & mask) == 0) {
+            wantinv += 1;
+            imask |= mask;
+        }
+    }
+
+    /* If we had more 0xffff than 0x0000, invert VALUE and use MOVN.  */
+    insn = I3405_MOVZ;
+    if (wantinv > 0) {
+        value = ivalue;
+        insn = I3405_MOVN;
+    }
+
+    /* Find the lowest lane that is not 0x0000.  */
+    shift = ctz64(value) & (63 & -16);
+    tcg_out_insn_3405(s, insn, type, rd, value >> shift, shift);
+
+    if (wantinv > 0) {
+        /* Re-invert the value, so MOVK sees non-inverted bits.  */
+        value = ~value;
+        /* Clear out all the 0xffff lanes.  */
+        value ^= imask;
+    }
+    /* Clear out the lane that we just set.  */
+    value &= ~(0xffffUL << shift);
+
+    /* Iterate until all lanes have been set, and thus cleared from VALUE.  */
+    while (value) {
+        shift = ctz64(value) & (63 & -16);
+        tcg_out_insn(s, 3405, MOVK, type, rd, value >> shift, shift);
+        value &= ~(0xffffUL << shift);
+    }
+}
+
+/* Define something more legible for general use.  */
+#define tcg_out_ldst_r  tcg_out_insn_3310
+
+static void tcg_out_ldst(TCGContext *s, AArch64Insn insn,
+                         TCGReg rd, TCGReg rn, intptr_t offset)
+{
+    TCGMemOp size = (uint32_t)insn >> 30;
+
+    /* If the offset is naturally aligned and in range, then we can
+       use the scaled uimm12 encoding */
+    if (offset >= 0 && !(offset & ((1 << size) - 1))) {
+        uintptr_t scaled_uimm = offset >> size;
+        if (scaled_uimm <= 0xfff) {
+            tcg_out_insn_3313(s, insn, rd, rn, scaled_uimm);
+            return;
+        }
+    }
+
+    /* Small signed offsets can use the unscaled encoding.  */
+    if (offset >= -256 && offset < 256) {
+        tcg_out_insn_3312(s, insn, rd, rn, offset);
+        return;
+    }
+
+    /* Worst-case scenario, move offset to temp register, use reg offset.  */
+    tcg_out_movi(s, TCG_TYPE_I64, TCG_REG_TMP, offset);
+    tcg_out_ldst_r(s, insn, rd, rn, TCG_TYPE_I64, TCG_REG_TMP);
+}
+
+static inline void tcg_out_mov(TCGContext *s,
+                               TCGType type, TCGReg ret, TCGReg arg)
+{
+    if (ret != arg) {
+        tcg_out_movr(s, type, ret, arg);
+    }
+}
+
+static inline void tcg_out_ld(TCGContext *s, TCGType type, TCGReg arg,
+                              TCGReg arg1, intptr_t arg2)
+{
+    tcg_out_ldst(s, type == TCG_TYPE_I32 ? I3312_LDRW : I3312_LDRX,
+                 arg, arg1, arg2);
+}
+
+static inline void tcg_out_st(TCGContext *s, TCGType type, TCGReg arg,
+                              TCGReg arg1, intptr_t arg2)
+{
+    tcg_out_ldst(s, type == TCG_TYPE_I32 ? I3312_STRW : I3312_STRX,
+                 arg, arg1, arg2);
+}
+
+static inline void tcg_out_bfm(TCGContext *s, TCGType ext, TCGReg rd,
+                               TCGReg rn, unsigned int a, unsigned int b)
+{
+    tcg_out_insn(s, 3402, BFM, ext, rd, rn, ext, a, b);
+}
+
+static inline void tcg_out_ubfm(TCGContext *s, TCGType ext, TCGReg rd,
+                                TCGReg rn, unsigned int a, unsigned int b)
+{
+    tcg_out_insn(s, 3402, UBFM, ext, rd, rn, ext, a, b);
+}
+
+static inline void tcg_out_sbfm(TCGContext *s, TCGType ext, TCGReg rd,
+                                TCGReg rn, unsigned int a, unsigned int b)
+{
+    tcg_out_insn(s, 3402, SBFM, ext, rd, rn, ext, a, b);
+}
+
+static inline void tcg_out_extr(TCGContext *s, TCGType ext, TCGReg rd,
+                                TCGReg rn, TCGReg rm, unsigned int a)
+{
+    tcg_out_insn(s, 3403, EXTR, ext, rd, rn, rm, a);
+}
+
+static inline void tcg_out_shl(TCGContext *s, TCGType ext,
+                               TCGReg rd, TCGReg rn, unsigned int m)
+{
+    int bits = ext ? 64 : 32;
+    int max = bits - 1;
+    tcg_out_ubfm(s, ext, rd, rn, bits - (m & max), max - (m & max));
+}
+
+static inline void tcg_out_shr(TCGContext *s, TCGType ext,
+                               TCGReg rd, TCGReg rn, unsigned int m)
+{
+    int max = ext ? 63 : 31;
+    tcg_out_ubfm(s, ext, rd, rn, m & max, max);
+}
+
+static inline void tcg_out_sar(TCGContext *s, TCGType ext,
+                               TCGReg rd, TCGReg rn, unsigned int m)
+{
+    int max = ext ? 63 : 31;
+    tcg_out_sbfm(s, ext, rd, rn, m & max, max);
+}
+
+static inline void tcg_out_rotr(TCGContext *s, TCGType ext,
+                                TCGReg rd, TCGReg rn, unsigned int m)
+{
+    int max = ext ? 63 : 31;
+    tcg_out_extr(s, ext, rd, rn, rn, m & max);
+}
+
+static inline void tcg_out_rotl(TCGContext *s, TCGType ext,
+                                TCGReg rd, TCGReg rn, unsigned int m)
+{
+    int bits = ext ? 64 : 32;
+    int max = bits - 1;
+    tcg_out_extr(s, ext, rd, rn, rn, bits - (m & max));
+}
+
+static inline void tcg_out_dep(TCGContext *s, TCGType ext, TCGReg rd,
+                               TCGReg rn, unsigned lsb, unsigned width)
+{
+    unsigned size = ext ? 64 : 32;
+    unsigned a = (size - lsb) & (size - 1);
+    unsigned b = width - 1;
+    tcg_out_bfm(s, ext, rd, rn, a, b);
+}
+
+static void tcg_out_cmp(TCGContext *s, TCGType ext, TCGReg a,
+                        tcg_target_long b, bool const_b)
+{
+    if (const_b) {
+        /* Using CMP or CMN aliases.  */
+        if (b >= 0) {
+            tcg_out_insn(s, 3401, SUBSI, ext, TCG_REG_XZR, a, b);
+        } else {
+            tcg_out_insn(s, 3401, ADDSI, ext, TCG_REG_XZR, a, -b);
+        }
+    } else {
+        /* Using CMP alias SUBS wzr, Wn, Wm */
+        tcg_out_insn(s, 3502, SUBS, ext, TCG_REG_XZR, a, b);
+    }
+}
+
+static inline void tcg_out_goto(TCGContext *s, tcg_insn_unit *target)
+{
+    ptrdiff_t offset = target - s->code_ptr;
+    assert(offset == sextract64(offset, 0, 26));
+    tcg_out_insn(s, 3206, B, offset);
+}
+
+static inline void tcg_out_goto_noaddr(TCGContext *s)
+{
+    /* We pay attention here to not modify the branch target by reading from
+       the buffer. This ensure that caches and memory are kept coherent during
+       retranslation.  Mask away possible garbage in the high bits for the
+       first translation, while keeping the offset bits for retranslation. */
+    uint32_t old = tcg_in32(s);
+    tcg_out_insn(s, 3206, B, old);
+}
+
+static inline void tcg_out_goto_cond_noaddr(TCGContext *s, TCGCond c)
+{
+    /* See comments in tcg_out_goto_noaddr.  */
+    uint32_t old = tcg_in32(s) >> 5;
+    tcg_out_insn(s, 3202, B_C, c, old);
+}
+
+static inline void tcg_out_callr(TCGContext *s, TCGReg reg)
+{
+    tcg_out_insn(s, 3207, BLR, reg);
+}
+
+static inline void tcg_out_call(TCGContext *s, tcg_insn_unit *target)
+{
+    ptrdiff_t offset = target - s->code_ptr;
+    if (offset == sextract64(offset, 0, 26)) {
+        tcg_out_insn(s, 3206, BL, offset);
+    } else {
+        tcg_out_movi(s, TCG_TYPE_I64, TCG_REG_TMP, (intptr_t)target);
+        tcg_out_callr(s, TCG_REG_TMP);
+    }
+}
+
+void aarch64_tb_set_jmp_target(uintptr_t jmp_addr, uintptr_t addr)
+{
+    tcg_insn_unit *code_ptr = (tcg_insn_unit *)jmp_addr;
+    tcg_insn_unit *target = (tcg_insn_unit *)addr;
+
+    reloc_pc26(code_ptr, target);
+    flush_icache_range(jmp_addr, jmp_addr + 4);
+}
+
+static inline void tcg_out_goto_label(TCGContext *s, TCGLabel *l)
+{
+    if (!l->has_value) {
+        tcg_out_reloc(s, s->code_ptr, R_AARCH64_JUMP26, l, 0);
+        tcg_out_goto_noaddr(s);
+    } else {
+        tcg_out_goto(s, l->u.value_ptr);
+    }
+}
+
+static void tcg_out_brcond(TCGContext *s, TCGMemOp ext, TCGCond c, TCGArg a,
+                           TCGArg b, bool b_const, TCGLabel *l)
+{
+    intptr_t offset;
+    bool need_cmp;
+
+    if (b_const && b == 0 && (c == TCG_COND_EQ || c == TCG_COND_NE)) {
+        need_cmp = false;
+    } else {
+        need_cmp = true;
+        tcg_out_cmp(s, ext, a, b, b_const);
+    }
+
+    if (!l->has_value) {
+        tcg_out_reloc(s, s->code_ptr, R_AARCH64_CONDBR19, l, 0);
+        offset = tcg_in32(s) >> 5;
+    } else {
+        offset = l->u.value_ptr - s->code_ptr;
+        assert(offset == sextract64(offset, 0, 19));
+    }
+
+    if (need_cmp) {
+        tcg_out_insn(s, 3202, B_C, c, offset);
+    } else if (c == TCG_COND_EQ) {
+        tcg_out_insn(s, 3201, CBZ, ext, a, offset);
+    } else {
+        tcg_out_insn(s, 3201, CBNZ, ext, a, offset);
+    }
+}
+
+static inline void tcg_out_rev64(TCGContext *s, TCGReg rd, TCGReg rn)
+{
+    tcg_out_insn(s, 3507, REV64, TCG_TYPE_I64, rd, rn);
+}
+
+static inline void tcg_out_rev32(TCGContext *s, TCGReg rd, TCGReg rn)
+{
+    tcg_out_insn(s, 3507, REV32, TCG_TYPE_I32, rd, rn);
+}
+
+static inline void tcg_out_rev16(TCGContext *s, TCGReg rd, TCGReg rn)
+{
+    tcg_out_insn(s, 3507, REV16, TCG_TYPE_I32, rd, rn);
+}
+
+static inline void tcg_out_sxt(TCGContext *s, TCGType ext, TCGMemOp s_bits,
+                               TCGReg rd, TCGReg rn)
+{
+    /* Using ALIASes SXTB, SXTH, SXTW, of SBFM Xd, Xn, #0, #7|15|31 */
+    int bits = (8 << s_bits) - 1;
+    tcg_out_sbfm(s, ext, rd, rn, 0, bits);
+}
+
+static inline void tcg_out_uxt(TCGContext *s, TCGMemOp s_bits,
+                               TCGReg rd, TCGReg rn)
+{
+    /* Using ALIASes UXTB, UXTH of UBFM Wd, Wn, #0, #7|15 */
+    int bits = (8 << s_bits) - 1;
+    tcg_out_ubfm(s, 0, rd, rn, 0, bits);
+}
+
+static void tcg_out_addsubi(TCGContext *s, int ext, TCGReg rd,
+                            TCGReg rn, int64_t aimm)
+{
+    if (aimm >= 0) {
+        tcg_out_insn(s, 3401, ADDI, ext, rd, rn, aimm);
+    } else {
+        tcg_out_insn(s, 3401, SUBI, ext, rd, rn, -aimm);
+    }
+}
+
+static inline void tcg_out_addsub2(TCGContext *s, int ext, TCGReg rl,
+                                   TCGReg rh, TCGReg al, TCGReg ah,
+                                   tcg_target_long bl, tcg_target_long bh,
+                                   bool const_bl, bool const_bh, bool sub)
+{
+    TCGReg orig_rl = rl;
+    AArch64Insn insn;
+
+    if (rl == ah || (!const_bh && rl == bh)) {
+        rl = TCG_REG_TMP;
+    }
+
+    if (const_bl) {
+        insn = I3401_ADDSI;
+        if ((bl < 0) ^ sub) {
+            insn = I3401_SUBSI;
+            bl = -bl;
+        }
+        tcg_out_insn_3401(s, insn, ext, rl, al, bl);
+    } else {
+        tcg_out_insn_3502(s, sub ? I3502_SUBS : I3502_ADDS, ext, rl, al, bl);
+    }
+
+    insn = I3503_ADC;
+    if (const_bh) {
+        /* Note that the only two constants we support are 0 and -1, and
+           that SBC = rn + ~rm + c, so adc -1 is sbc 0, and vice-versa.  */
+        if ((bh != 0) ^ sub) {
+            insn = I3503_SBC;
+        }
+        bh = TCG_REG_XZR;
+    } else if (sub) {
+        insn = I3503_SBC;
+    }
+    tcg_out_insn_3503(s, insn, ext, rh, ah, bh);
+
+    tcg_out_mov(s, ext, orig_rl, rl);
+}
+
+#ifdef CONFIG_SOFTMMU
+/* helper signature: helper_ret_ld_mmu(CPUState *env, target_ulong addr,
+ *                                     TCGMemOpIdx oi, uintptr_t ra)
+ */
+static void * const qemu_ld_helpers[16] = {
+    [MO_UB]   = helper_ret_ldub_mmu,
+    [MO_LEUW] = helper_le_lduw_mmu,
+    [MO_LEUL] = helper_le_ldul_mmu,
+    [MO_LEQ]  = helper_le_ldq_mmu,
+    [MO_BEUW] = helper_be_lduw_mmu,
+    [MO_BEUL] = helper_be_ldul_mmu,
+    [MO_BEQ]  = helper_be_ldq_mmu,
+};
+
+/* helper signature: helper_ret_st_mmu(CPUState *env, target_ulong addr,
+ *                                     uintxx_t val, TCGMemOpIdx oi,
+ *                                     uintptr_t ra)
+ */
+static void * const qemu_st_helpers[16] = {
+    [MO_UB]   = helper_ret_stb_mmu,
+    [MO_LEUW] = helper_le_stw_mmu,
+    [MO_LEUL] = helper_le_stl_mmu,
+    [MO_LEQ]  = helper_le_stq_mmu,
+    [MO_BEUW] = helper_be_stw_mmu,
+    [MO_BEUL] = helper_be_stl_mmu,
+    [MO_BEQ]  = helper_be_stq_mmu,
+};
+
+static inline void tcg_out_adr(TCGContext *s, TCGReg rd, void *target)
+{
+    ptrdiff_t offset = tcg_pcrel_diff(s, target);
+    assert(offset == sextract64(offset, 0, 21));
+    tcg_out_insn(s, 3406, ADR, rd, offset);
+}
+
+static void tcg_out_qemu_ld_slow_path(TCGContext *s, TCGLabelQemuLdst *lb)
+{
+    TCGMemOpIdx oi = lb->oi;
+    TCGMemOp opc = get_memop(oi);
+    TCGMemOp size = opc & MO_SIZE;
+
+    reloc_pc19(lb->label_ptr[0], s->code_ptr);
+
+    tcg_out_mov(s, TCG_TYPE_PTR, TCG_REG_X0, TCG_AREG0);
+    tcg_out_mov(s, TARGET_LONG_BITS == 64, TCG_REG_X1, lb->addrlo_reg);
+    tcg_out_movi(s, TCG_TYPE_I32, TCG_REG_X2, oi);
+    tcg_out_adr(s, TCG_REG_X3, lb->raddr);
+    tcg_out_call(s, qemu_ld_helpers[opc & (MO_BSWAP | MO_SIZE)]);
+    if (opc & MO_SIGN) {
+        tcg_out_sxt(s, lb->type, size, lb->datalo_reg, TCG_REG_X0);
+    } else {
+        tcg_out_mov(s, size == MO_64, lb->datalo_reg, TCG_REG_X0);
+    }
+
+    tcg_out_goto(s, lb->raddr);
+}
+
+static void tcg_out_qemu_st_slow_path(TCGContext *s, TCGLabelQemuLdst *lb)
+{
+    TCGMemOpIdx oi = lb->oi;
+    TCGMemOp opc = get_memop(oi);
+    TCGMemOp size = opc & MO_SIZE;
+
+    reloc_pc19(lb->label_ptr[0], s->code_ptr);
+
+    tcg_out_mov(s, TCG_TYPE_PTR, TCG_REG_X0, TCG_AREG0);
+    tcg_out_mov(s, TARGET_LONG_BITS == 64, TCG_REG_X1, lb->addrlo_reg);
+    tcg_out_mov(s, size == MO_64, TCG_REG_X2, lb->datalo_reg);
+    tcg_out_movi(s, TCG_TYPE_I32, TCG_REG_X3, oi);
+    tcg_out_adr(s, TCG_REG_X4, lb->raddr);
+    tcg_out_call(s, qemu_st_helpers[opc & (MO_BSWAP | MO_SIZE)]);
+    tcg_out_goto(s, lb->raddr);
+}
+
+static void add_qemu_ldst_label(TCGContext *s, bool is_ld, TCGMemOpIdx oi,
+                                TCGType ext, TCGReg data_reg, TCGReg addr_reg,
+                                tcg_insn_unit *raddr, tcg_insn_unit *label_ptr)
+{
+    TCGLabelQemuLdst *label = new_ldst_label(s);
+
+    label->is_ld = is_ld;
+    label->oi = oi;
+    label->type = ext;
+    label->datalo_reg = data_reg;
+    label->addrlo_reg = addr_reg;
+    label->raddr = raddr;
+    label->label_ptr[0] = label_ptr;
+}
+
+/* Load and compare a TLB entry, emitting the conditional jump to the
+   slow path for the failure case, which will be patched later when finalizing
+   the slow path. Generated code returns the host addend in X1,
+   clobbers X0,X2,X3,TMP. */
+static void tcg_out_tlb_read(TCGContext *s, TCGReg addr_reg, TCGMemOp s_bits,
+                             tcg_insn_unit **label_ptr, int mem_index,
+                             bool is_read)
+{
+    TCGReg base = TCG_AREG0;
+    int tlb_offset = is_read ?
+        offsetof(CPUArchState, tlb_table[mem_index][0].addr_read)
+        : offsetof(CPUArchState, tlb_table[mem_index][0].addr_write);
+
+    /* Extract the TLB index from the address into X0.
+       X0<CPU_TLB_BITS:0> =
+       addr_reg<TARGET_PAGE_BITS+CPU_TLB_BITS:TARGET_PAGE_BITS> */
+    tcg_out_ubfm(s, TARGET_LONG_BITS == 64, TCG_REG_X0, addr_reg,
+                 TARGET_PAGE_BITS, TARGET_PAGE_BITS + CPU_TLB_BITS);
+
+    /* Store the page mask part of the address and the low s_bits into X3.
+       Later this allows checking for equality and alignment at the same time.
+       X3 = addr_reg & (PAGE_MASK | ((1 << s_bits) - 1)) */
+    tcg_out_logicali(s, I3404_ANDI, TARGET_LONG_BITS == 64, TCG_REG_X3,
+                     addr_reg, TARGET_PAGE_MASK | ((1 << s_bits) - 1));
+
+    /* Add any "high bits" from the tlb offset to the env address into X2,
+       to take advantage of the LSL12 form of the ADDI instruction.
+       X2 = env + (tlb_offset & 0xfff000) */
+    if (tlb_offset & 0xfff000) {
+        tcg_out_insn(s, 3401, ADDI, TCG_TYPE_I64, TCG_REG_X2, base,
+                     tlb_offset & 0xfff000);
+        base = TCG_REG_X2;
+    }
+
+    /* Merge the tlb index contribution into X2.
+       X2 = X2 + (X0 << CPU_TLB_ENTRY_BITS) */
+    tcg_out_insn(s, 3502S, ADD_LSL, TCG_TYPE_I64, TCG_REG_X2, base,
+                 TCG_REG_X0, CPU_TLB_ENTRY_BITS);
+
+    /* Merge "low bits" from tlb offset, load the tlb comparator into X0.
+       X0 = load [X2 + (tlb_offset & 0x000fff)] */
+    tcg_out_ldst(s, TARGET_LONG_BITS == 32 ? I3312_LDRW : I3312_LDRX,
+                 TCG_REG_X0, TCG_REG_X2, tlb_offset & 0xfff);
+
+    /* Load the tlb addend. Do that early to avoid stalling.
+       X1 = load [X2 + (tlb_offset & 0xfff) + offsetof(addend)] */
+    tcg_out_ldst(s, I3312_LDRX, TCG_REG_X1, TCG_REG_X2,
+                 (tlb_offset & 0xfff) + (offsetof(CPUTLBEntry, addend)) -
+                 (is_read ? offsetof(CPUTLBEntry, addr_read)
+                  : offsetof(CPUTLBEntry, addr_write)));
+
+    /* Perform the address comparison. */
+    tcg_out_cmp(s, (TARGET_LONG_BITS == 64), TCG_REG_X0, TCG_REG_X3, 0);
+
+    /* If not equal, we jump to the slow path. */
+    *label_ptr = s->code_ptr;
+    tcg_out_goto_cond_noaddr(s, TCG_COND_NE);
+}
+
+#endif /* CONFIG_SOFTMMU */
+
+static void tcg_out_qemu_ld_direct(TCGContext *s, TCGMemOp memop, TCGType ext,
+                                   TCGReg data_r, TCGReg addr_r,
+                                   TCGType otype, TCGReg off_r)
+{
+    const TCGMemOp bswap = memop & MO_BSWAP;
+
+    switch (memop & MO_SSIZE) {
+    case MO_UB:
+        tcg_out_ldst_r(s, I3312_LDRB, data_r, addr_r, otype, off_r);
+        break;
+    case MO_SB:
+        tcg_out_ldst_r(s, ext ? I3312_LDRSBX : I3312_LDRSBW,
+                       data_r, addr_r, otype, off_r);
+        break;
+    case MO_UW:
+        tcg_out_ldst_r(s, I3312_LDRH, data_r, addr_r, otype, off_r);
+        if (bswap) {
+            tcg_out_rev16(s, data_r, data_r);
+        }
+        break;
+    case MO_SW:
+        if (bswap) {
+            tcg_out_ldst_r(s, I3312_LDRH, data_r, addr_r, otype, off_r);
+            tcg_out_rev16(s, data_r, data_r);
+            tcg_out_sxt(s, ext, MO_16, data_r, data_r);
+        } else {
+            tcg_out_ldst_r(s, (ext ? I3312_LDRSHX : I3312_LDRSHW),
+                           data_r, addr_r, otype, off_r);
+        }
+        break;
+    case MO_UL:
+        tcg_out_ldst_r(s, I3312_LDRW, data_r, addr_r, otype, off_r);
+        if (bswap) {
+            tcg_out_rev32(s, data_r, data_r);
+        }
+        break;
+    case MO_SL:
+        if (bswap) {
+            tcg_out_ldst_r(s, I3312_LDRW, data_r, addr_r, otype, off_r);
+            tcg_out_rev32(s, data_r, data_r);
+            tcg_out_sxt(s, TCG_TYPE_I64, MO_32, data_r, data_r);
+        } else {
+            tcg_out_ldst_r(s, I3312_LDRSWX, data_r, addr_r, otype, off_r);
+        }
+        break;
+    case MO_Q:
+        tcg_out_ldst_r(s, I3312_LDRX, data_r, addr_r, otype, off_r);
+        if (bswap) {
+            tcg_out_rev64(s, data_r, data_r);
+        }
+        break;
+    default:
+        tcg_abort();
+    }
+}
+
+static void tcg_out_qemu_st_direct(TCGContext *s, TCGMemOp memop,
+                                   TCGReg data_r, TCGReg addr_r,
+                                   TCGType otype, TCGReg off_r)
+{
+    const TCGMemOp bswap = memop & MO_BSWAP;
+
+    switch (memop & MO_SIZE) {
+    case MO_8:
+        tcg_out_ldst_r(s, I3312_STRB, data_r, addr_r, otype, off_r);
+        break;
+    case MO_16:
+        if (bswap && data_r != TCG_REG_XZR) {
+            tcg_out_rev16(s, TCG_REG_TMP, data_r);
+            data_r = TCG_REG_TMP;
+        }
+        tcg_out_ldst_r(s, I3312_STRH, data_r, addr_r, otype, off_r);
+        break;
+    case MO_32:
+        if (bswap && data_r != TCG_REG_XZR) {
+            tcg_out_rev32(s, TCG_REG_TMP, data_r);
+            data_r = TCG_REG_TMP;
+        }
+        tcg_out_ldst_r(s, I3312_STRW, data_r, addr_r, otype, off_r);
+        break;
+    case MO_64:
+        if (bswap && data_r != TCG_REG_XZR) {
+            tcg_out_rev64(s, TCG_REG_TMP, data_r);
+            data_r = TCG_REG_TMP;
+        }
+        tcg_out_ldst_r(s, I3312_STRX, data_r, addr_r, otype, off_r);
+        break;
+    default:
+        tcg_abort();
+    }
+}
+
+static void tcg_out_qemu_ld(TCGContext *s, TCGReg data_reg, TCGReg addr_reg,
+                            TCGMemOpIdx oi, TCGType ext)
+{
+    TCGMemOp memop = get_memop(oi);
+    const TCGType otype = TARGET_LONG_BITS == 64 ? TCG_TYPE_I64 : TCG_TYPE_I32;
+#ifdef CONFIG_SOFTMMU
+    unsigned mem_index = get_mmuidx(oi);
+    TCGMemOp s_bits = memop & MO_SIZE;
+    tcg_insn_unit *label_ptr;
+
+    tcg_out_tlb_read(s, addr_reg, s_bits, &label_ptr, mem_index, 1);
+    tcg_out_qemu_ld_direct(s, memop, ext, data_reg,
+                           TCG_REG_X1, otype, addr_reg);
+    add_qemu_ldst_label(s, true, oi, ext, data_reg, addr_reg,
+                        s->code_ptr, label_ptr);
+#else /* !CONFIG_SOFTMMU */
+    if (USE_GUEST_BASE) {
+        tcg_out_qemu_ld_direct(s, memop, ext, data_reg,
+                               TCG_REG_GUEST_BASE, otype, addr_reg);
+    } else {
+        tcg_out_qemu_ld_direct(s, memop, ext, data_reg,
+                               addr_reg, TCG_TYPE_I64, TCG_REG_XZR);
+    }
+#endif /* CONFIG_SOFTMMU */
+}
+
+static void tcg_out_qemu_st(TCGContext *s, TCGReg data_reg, TCGReg addr_reg,
+                            TCGMemOpIdx oi)
+{
+    TCGMemOp memop = get_memop(oi);
+    const TCGType otype = TARGET_LONG_BITS == 64 ? TCG_TYPE_I64 : TCG_TYPE_I32;
+#ifdef CONFIG_SOFTMMU
+    unsigned mem_index = get_mmuidx(oi);
+    TCGMemOp s_bits = memop & MO_SIZE;
+    tcg_insn_unit *label_ptr;
+
+    tcg_out_tlb_read(s, addr_reg, s_bits, &label_ptr, mem_index, 0);
+    tcg_out_qemu_st_direct(s, memop, data_reg,
+                           TCG_REG_X1, otype, addr_reg);
+    add_qemu_ldst_label(s, false, oi, s_bits == MO_64, data_reg, addr_reg,
+                        s->code_ptr, label_ptr);
+#else /* !CONFIG_SOFTMMU */
+    if (USE_GUEST_BASE) {
+        tcg_out_qemu_st_direct(s, memop, data_reg,
+                               TCG_REG_GUEST_BASE, otype, addr_reg);
+    } else {
+        tcg_out_qemu_st_direct(s, memop, data_reg,
+                               addr_reg, TCG_TYPE_I64, TCG_REG_XZR);
+    }
+#endif /* CONFIG_SOFTMMU */
+}
+
+static tcg_insn_unit *tb_ret_addr;
+
+static void tcg_out_op(TCGContext *s, TCGOpcode opc,
+                       const TCGArg args[TCG_MAX_OP_ARGS],
+                       const int const_args[TCG_MAX_OP_ARGS])
+{
+    /* 99% of the time, we can signal the use of extension registers
+       by looking to see if the opcode handles 64-bit data.  */
+    TCGType ext = (tcg_op_defs[opc].flags & TCG_OPF_64BIT) != 0;
+
+    /* Hoist the loads of the most common arguments.  */
+    TCGArg a0 = args[0];
+    TCGArg a1 = args[1];
+    TCGArg a2 = args[2];
+    int c2 = const_args[2];
+
+    /* Some operands are defined with "rZ" constraint, a register or
+       the zero register.  These need not actually test args[I] == 0.  */
+#define REG0(I)  (const_args[I] ? TCG_REG_XZR : (TCGReg)args[I])
+
+    switch (opc) {
+    case INDEX_op_exit_tb:
+        tcg_out_movi(s, TCG_TYPE_I64, TCG_REG_X0, a0);
+        tcg_out_goto(s, tb_ret_addr);
+        break;
+
+    case INDEX_op_goto_tb:
+#ifndef USE_DIRECT_JUMP
+#error "USE_DIRECT_JUMP required for aarch64"
+#endif
+        assert(s->tb_jmp_offset != NULL); /* consistency for USE_DIRECT_JUMP */
+        s->tb_jmp_offset[a0] = tcg_current_code_size(s);
+        /* actual branch destination will be patched by
+           aarch64_tb_set_jmp_target later, beware retranslation. */
+        tcg_out_goto_noaddr(s);
+        s->tb_next_offset[a0] = tcg_current_code_size(s);
+        break;
+
+    case INDEX_op_br:
+        tcg_out_goto_label(s, arg_label(a0));
+        break;
+
+    case INDEX_op_ld8u_i32:
+    case INDEX_op_ld8u_i64:
+        tcg_out_ldst(s, I3312_LDRB, a0, a1, a2);
+        break;
+    case INDEX_op_ld8s_i32:
+        tcg_out_ldst(s, I3312_LDRSBW, a0, a1, a2);
+        break;
+    case INDEX_op_ld8s_i64:
+        tcg_out_ldst(s, I3312_LDRSBX, a0, a1, a2);
+        break;
+    case INDEX_op_ld16u_i32:
+    case INDEX_op_ld16u_i64:
+        tcg_out_ldst(s, I3312_LDRH, a0, a1, a2);
+        break;
+    case INDEX_op_ld16s_i32:
+        tcg_out_ldst(s, I3312_LDRSHW, a0, a1, a2);
+        break;
+    case INDEX_op_ld16s_i64:
+        tcg_out_ldst(s, I3312_LDRSHX, a0, a1, a2);
+        break;
+    case INDEX_op_ld_i32:
+    case INDEX_op_ld32u_i64:
+        tcg_out_ldst(s, I3312_LDRW, a0, a1, a2);
+        break;
+    case INDEX_op_ld32s_i64:
+        tcg_out_ldst(s, I3312_LDRSWX, a0, a1, a2);
+        break;
+    case INDEX_op_ld_i64:
+        tcg_out_ldst(s, I3312_LDRX, a0, a1, a2);
+        break;
+
+    case INDEX_op_st8_i32:
+    case INDEX_op_st8_i64:
+        tcg_out_ldst(s, I3312_STRB, REG0(0), a1, a2);
+        break;
+    case INDEX_op_st16_i32:
+    case INDEX_op_st16_i64:
+        tcg_out_ldst(s, I3312_STRH, REG0(0), a1, a2);
+        break;
+    case INDEX_op_st_i32:
+    case INDEX_op_st32_i64:
+        tcg_out_ldst(s, I3312_STRW, REG0(0), a1, a2);
+        break;
+    case INDEX_op_st_i64:
+        tcg_out_ldst(s, I3312_STRX, REG0(0), a1, a2);
+        break;
+
+    case INDEX_op_add_i32:
+        a2 = (int32_t)a2;
+        /* FALLTHRU */
+    case INDEX_op_add_i64:
+        if (c2) {
+            tcg_out_addsubi(s, ext, a0, a1, a2);
+        } else {
+            tcg_out_insn(s, 3502, ADD, ext, a0, a1, a2);
+        }
+        break;
+
+    case INDEX_op_sub_i32:
+        a2 = (int32_t)a2;
+        /* FALLTHRU */
+    case INDEX_op_sub_i64:
+        if (c2) {
+            tcg_out_addsubi(s, ext, a0, a1, -a2);
+        } else {
+            tcg_out_insn(s, 3502, SUB, ext, a0, a1, a2);
+        }
+        break;
+
+    case INDEX_op_neg_i64:
+    case INDEX_op_neg_i32:
+        tcg_out_insn(s, 3502, SUB, ext, a0, TCG_REG_XZR, a1);
+        break;
+
+    case INDEX_op_and_i32:
+        a2 = (int32_t)a2;
+        /* FALLTHRU */
+    case INDEX_op_and_i64:
+        if (c2) {
+            tcg_out_logicali(s, I3404_ANDI, ext, a0, a1, a2);
+        } else {
+            tcg_out_insn(s, 3510, AND, ext, a0, a1, a2);
+        }
+        break;
+
+    case INDEX_op_andc_i32:
+        a2 = (int32_t)a2;
+        /* FALLTHRU */
+    case INDEX_op_andc_i64:
+        if (c2) {
+            tcg_out_logicali(s, I3404_ANDI, ext, a0, a1, ~a2);
+        } else {
+            tcg_out_insn(s, 3510, BIC, ext, a0, a1, a2);
+        }
+        break;
+
+    case INDEX_op_or_i32:
+        a2 = (int32_t)a2;
+        /* FALLTHRU */
+    case INDEX_op_or_i64:
+        if (c2) {
+            tcg_out_logicali(s, I3404_ORRI, ext, a0, a1, a2);
+        } else {
+            tcg_out_insn(s, 3510, ORR, ext, a0, a1, a2);
+        }
+        break;
+
+    case INDEX_op_orc_i32:
+        a2 = (int32_t)a2;
+        /* FALLTHRU */
+    case INDEX_op_orc_i64:
+        if (c2) {
+            tcg_out_logicali(s, I3404_ORRI, ext, a0, a1, ~a2);
+        } else {
+            tcg_out_insn(s, 3510, ORN, ext, a0, a1, a2);
+        }
+        break;
+
+    case INDEX_op_xor_i32:
+        a2 = (int32_t)a2;
+        /* FALLTHRU */
+    case INDEX_op_xor_i64:
+        if (c2) {
+            tcg_out_logicali(s, I3404_EORI, ext, a0, a1, a2);
+        } else {
+            tcg_out_insn(s, 3510, EOR, ext, a0, a1, a2);
+        }
+        break;
+
+    case INDEX_op_eqv_i32:
+        a2 = (int32_t)a2;
+        /* FALLTHRU */
+    case INDEX_op_eqv_i64:
+        if (c2) {
+            tcg_out_logicali(s, I3404_EORI, ext, a0, a1, ~a2);
+        } else {
+            tcg_out_insn(s, 3510, EON, ext, a0, a1, a2);
+        }
+        break;
+
+    case INDEX_op_not_i64:
+    case INDEX_op_not_i32:
+        tcg_out_insn(s, 3510, ORN, ext, a0, TCG_REG_XZR, a1);
+        break;
+
+    case INDEX_op_mul_i64:
+    case INDEX_op_mul_i32:
+        tcg_out_insn(s, 3509, MADD, ext, a0, a1, a2, TCG_REG_XZR);
+        break;
+
+    case INDEX_op_div_i64:
+    case INDEX_op_div_i32:
+        tcg_out_insn(s, 3508, SDIV, ext, a0, a1, a2);
+        break;
+    case INDEX_op_divu_i64:
+    case INDEX_op_divu_i32:
+        tcg_out_insn(s, 3508, UDIV, ext, a0, a1, a2);
+        break;
+
+    case INDEX_op_rem_i64:
+    case INDEX_op_rem_i32:
+        tcg_out_insn(s, 3508, SDIV, ext, TCG_REG_TMP, a1, a2);
+        tcg_out_insn(s, 3509, MSUB, ext, a0, TCG_REG_TMP, a2, a1);
+        break;
+    case INDEX_op_remu_i64:
+    case INDEX_op_remu_i32:
+        tcg_out_insn(s, 3508, UDIV, ext, TCG_REG_TMP, a1, a2);
+        tcg_out_insn(s, 3509, MSUB, ext, a0, TCG_REG_TMP, a2, a1);
+        break;
+
+    case INDEX_op_shl_i64:
+    case INDEX_op_shl_i32:
+        if (c2) {
+            tcg_out_shl(s, ext, a0, a1, a2);
+        } else {
+            tcg_out_insn(s, 3508, LSLV, ext, a0, a1, a2);
+        }
+        break;
+
+    case INDEX_op_shr_i64:
+    case INDEX_op_shr_i32:
+        if (c2) {
+            tcg_out_shr(s, ext, a0, a1, a2);
+        } else {
+            tcg_out_insn(s, 3508, LSRV, ext, a0, a1, a2);
+        }
+        break;
+
+    case INDEX_op_sar_i64:
+    case INDEX_op_sar_i32:
+        if (c2) {
+            tcg_out_sar(s, ext, a0, a1, a2);
+        } else {
+            tcg_out_insn(s, 3508, ASRV, ext, a0, a1, a2);
+        }
+        break;
+
+    case INDEX_op_rotr_i64:
+    case INDEX_op_rotr_i32:
+        if (c2) {
+            tcg_out_rotr(s, ext, a0, a1, a2);
+        } else {
+            tcg_out_insn(s, 3508, RORV, ext, a0, a1, a2);
+        }
+        break;
+
+    case INDEX_op_rotl_i64:
+    case INDEX_op_rotl_i32:
+        if (c2) {
+            tcg_out_rotl(s, ext, a0, a1, a2);
+        } else {
+            tcg_out_insn(s, 3502, SUB, 0, TCG_REG_TMP, TCG_REG_XZR, a2);
+            tcg_out_insn(s, 3508, RORV, ext, a0, a1, TCG_REG_TMP);
+        }
+        break;
+
+    case INDEX_op_brcond_i32:
+        a1 = (int32_t)a1;
+        /* FALLTHRU */
+    case INDEX_op_brcond_i64:
+        tcg_out_brcond(s, ext, a2, a0, a1, const_args[1], arg_label(args[3]));
+        break;
+
+    case INDEX_op_setcond_i32:
+        a2 = (int32_t)a2;
+        /* FALLTHRU */
+    case INDEX_op_setcond_i64:
+        tcg_out_cmp(s, ext, a1, a2, c2);
+        /* Use CSET alias of CSINC Wd, WZR, WZR, invert(cond).  */
+        tcg_out_insn(s, 3506, CSINC, TCG_TYPE_I32, a0, TCG_REG_XZR,
+                     TCG_REG_XZR, tcg_invert_cond(args[3]));
+        break;
+
+    case INDEX_op_movcond_i32:
+        a2 = (int32_t)a2;
+        /* FALLTHRU */
+    case INDEX_op_movcond_i64:
+        tcg_out_cmp(s, ext, a1, a2, c2);
+        tcg_out_insn(s, 3506, CSEL, ext, a0, REG0(3), REG0(4), args[5]);
+        break;
+
+    case INDEX_op_qemu_ld_i32:
+    case INDEX_op_qemu_ld_i64:
+        tcg_out_qemu_ld(s, a0, a1, a2, ext);
+        break;
+    case INDEX_op_qemu_st_i32:
+    case INDEX_op_qemu_st_i64:
+        tcg_out_qemu_st(s, REG0(0), a1, a2);
+        break;
+
+    case INDEX_op_bswap64_i64:
+        tcg_out_rev64(s, a0, a1);
+        break;
+    case INDEX_op_bswap32_i64:
+    case INDEX_op_bswap32_i32:
+        tcg_out_rev32(s, a0, a1);
+        break;
+    case INDEX_op_bswap16_i64:
+    case INDEX_op_bswap16_i32:
+        tcg_out_rev16(s, a0, a1);
+        break;
+
+    case INDEX_op_ext8s_i64:
+    case INDEX_op_ext8s_i32:
+        tcg_out_sxt(s, ext, MO_8, a0, a1);
+        break;
+    case INDEX_op_ext16s_i64:
+    case INDEX_op_ext16s_i32:
+        tcg_out_sxt(s, ext, MO_16, a0, a1);
+        break;
+    case INDEX_op_ext32s_i64:
+        tcg_out_sxt(s, TCG_TYPE_I64, MO_32, a0, a1);
+        break;
+    case INDEX_op_ext8u_i64:
+    case INDEX_op_ext8u_i32:
+        tcg_out_uxt(s, MO_8, a0, a1);
+        break;
+    case INDEX_op_ext16u_i64:
+    case INDEX_op_ext16u_i32:
+        tcg_out_uxt(s, MO_16, a0, a1);
+        break;
+    case INDEX_op_ext32u_i64:
+        tcg_out_movr(s, TCG_TYPE_I32, a0, a1);
+        break;
+
+    case INDEX_op_deposit_i64:
+    case INDEX_op_deposit_i32:
+        tcg_out_dep(s, ext, a0, REG0(2), args[3], args[4]);
+        break;
+
+    case INDEX_op_add2_i32:
+        tcg_out_addsub2(s, TCG_TYPE_I32, a0, a1, REG0(2), REG0(3),
+                        (int32_t)args[4], args[5], const_args[4],
+                        const_args[5], false);
+        break;
+    case INDEX_op_add2_i64:
+        tcg_out_addsub2(s, TCG_TYPE_I64, a0, a1, REG0(2), REG0(3), args[4],
+                        args[5], const_args[4], const_args[5], false);
+        break;
+    case INDEX_op_sub2_i32:
+        tcg_out_addsub2(s, TCG_TYPE_I32, a0, a1, REG0(2), REG0(3),
+                        (int32_t)args[4], args[5], const_args[4],
+                        const_args[5], true);
+        break;
+    case INDEX_op_sub2_i64:
+        tcg_out_addsub2(s, TCG_TYPE_I64, a0, a1, REG0(2), REG0(3), args[4],
+                        args[5], const_args[4], const_args[5], true);
+        break;
+
+    case INDEX_op_muluh_i64:
+        tcg_out_insn(s, 3508, UMULH, TCG_TYPE_I64, a0, a1, a2);
+        break;
+    case INDEX_op_mulsh_i64:
+        tcg_out_insn(s, 3508, SMULH, TCG_TYPE_I64, a0, a1, a2);
+        break;
+
+    case INDEX_op_mov_i32:  /* Always emitted via tcg_out_mov.  */
+    case INDEX_op_mov_i64:
+    case INDEX_op_movi_i32: /* Always emitted via tcg_out_movi.  */
+    case INDEX_op_movi_i64:
+    case INDEX_op_call:     /* Always emitted via tcg_out_call.  */
+    default:
+        tcg_abort();
+    }
+
+#undef REG0
+}
+
+static const TCGTargetOpDef aarch64_op_defs[] = {
+    { INDEX_op_exit_tb, { } },
+    { INDEX_op_goto_tb, { } },
+    { INDEX_op_br, { } },
+
+    { INDEX_op_ld8u_i32, { "r", "r" } },
+    { INDEX_op_ld8s_i32, { "r", "r" } },
+    { INDEX_op_ld16u_i32, { "r", "r" } },
+    { INDEX_op_ld16s_i32, { "r", "r" } },
+    { INDEX_op_ld_i32, { "r", "r" } },
+    { INDEX_op_ld8u_i64, { "r", "r" } },
+    { INDEX_op_ld8s_i64, { "r", "r" } },
+    { INDEX_op_ld16u_i64, { "r", "r" } },
+    { INDEX_op_ld16s_i64, { "r", "r" } },
+    { INDEX_op_ld32u_i64, { "r", "r" } },
+    { INDEX_op_ld32s_i64, { "r", "r" } },
+    { INDEX_op_ld_i64, { "r", "r" } },
+
+    { INDEX_op_st8_i32, { "rZ", "r" } },
+    { INDEX_op_st16_i32, { "rZ", "r" } },
+    { INDEX_op_st_i32, { "rZ", "r" } },
+    { INDEX_op_st8_i64, { "rZ", "r" } },
+    { INDEX_op_st16_i64, { "rZ", "r" } },
+    { INDEX_op_st32_i64, { "rZ", "r" } },
+    { INDEX_op_st_i64, { "rZ", "r" } },
+
+    { INDEX_op_add_i32, { "r", "r", "rA" } },
+    { INDEX_op_add_i64, { "r", "r", "rA" } },
+    { INDEX_op_sub_i32, { "r", "r", "rA" } },
+    { INDEX_op_sub_i64, { "r", "r", "rA" } },
+    { INDEX_op_mul_i32, { "r", "r", "r" } },
+    { INDEX_op_mul_i64, { "r", "r", "r" } },
+    { INDEX_op_div_i32, { "r", "r", "r" } },
+    { INDEX_op_div_i64, { "r", "r", "r" } },
+    { INDEX_op_divu_i32, { "r", "r", "r" } },
+    { INDEX_op_divu_i64, { "r", "r", "r" } },
+    { INDEX_op_rem_i32, { "r", "r", "r" } },
+    { INDEX_op_rem_i64, { "r", "r", "r" } },
+    { INDEX_op_remu_i32, { "r", "r", "r" } },
+    { INDEX_op_remu_i64, { "r", "r", "r" } },
+    { INDEX_op_and_i32, { "r", "r", "rL" } },
+    { INDEX_op_and_i64, { "r", "r", "rL" } },
+    { INDEX_op_or_i32, { "r", "r", "rL" } },
+    { INDEX_op_or_i64, { "r", "r", "rL" } },
+    { INDEX_op_xor_i32, { "r", "r", "rL" } },
+    { INDEX_op_xor_i64, { "r", "r", "rL" } },
+    { INDEX_op_andc_i32, { "r", "r", "rL" } },
+    { INDEX_op_andc_i64, { "r", "r", "rL" } },
+    { INDEX_op_orc_i32, { "r", "r", "rL" } },
+    { INDEX_op_orc_i64, { "r", "r", "rL" } },
+    { INDEX_op_eqv_i32, { "r", "r", "rL" } },
+    { INDEX_op_eqv_i64, { "r", "r", "rL" } },
+
+    { INDEX_op_neg_i32, { "r", "r" } },
+    { INDEX_op_neg_i64, { "r", "r" } },
+    { INDEX_op_not_i32, { "r", "r" } },
+    { INDEX_op_not_i64, { "r", "r" } },
+
+    { INDEX_op_shl_i32, { "r", "r", "ri" } },
+    { INDEX_op_shr_i32, { "r", "r", "ri" } },
+    { INDEX_op_sar_i32, { "r", "r", "ri" } },
+    { INDEX_op_rotl_i32, { "r", "r", "ri" } },
+    { INDEX_op_rotr_i32, { "r", "r", "ri" } },
+    { INDEX_op_shl_i64, { "r", "r", "ri" } },
+    { INDEX_op_shr_i64, { "r", "r", "ri" } },
+    { INDEX_op_sar_i64, { "r", "r", "ri" } },
+    { INDEX_op_rotl_i64, { "r", "r", "ri" } },
+    { INDEX_op_rotr_i64, { "r", "r", "ri" } },
+
+    { INDEX_op_brcond_i32, { "r", "rA" } },
+    { INDEX_op_brcond_i64, { "r", "rA" } },
+    { INDEX_op_setcond_i32, { "r", "r", "rA" } },
+    { INDEX_op_setcond_i64, { "r", "r", "rA" } },
+    { INDEX_op_movcond_i32, { "r", "r", "rA", "rZ", "rZ" } },
+    { INDEX_op_movcond_i64, { "r", "r", "rA", "rZ", "rZ" } },
+
+    { INDEX_op_qemu_ld_i32, { "r", "l" } },
+    { INDEX_op_qemu_ld_i64, { "r", "l" } },
+    { INDEX_op_qemu_st_i32, { "lZ", "l" } },
+    { INDEX_op_qemu_st_i64, { "lZ", "l" } },
+
+    { INDEX_op_bswap16_i32, { "r", "r" } },
+    { INDEX_op_bswap32_i32, { "r", "r" } },
+    { INDEX_op_bswap16_i64, { "r", "r" } },
+    { INDEX_op_bswap32_i64, { "r", "r" } },
+    { INDEX_op_bswap64_i64, { "r", "r" } },
+
+    { INDEX_op_ext8s_i32, { "r", "r" } },
+    { INDEX_op_ext16s_i32, { "r", "r" } },
+    { INDEX_op_ext8u_i32, { "r", "r" } },
+    { INDEX_op_ext16u_i32, { "r", "r" } },
+
+    { INDEX_op_ext8s_i64, { "r", "r" } },
+    { INDEX_op_ext16s_i64, { "r", "r" } },
+    { INDEX_op_ext32s_i64, { "r", "r" } },
+    { INDEX_op_ext8u_i64, { "r", "r" } },
+    { INDEX_op_ext16u_i64, { "r", "r" } },
+    { INDEX_op_ext32u_i64, { "r", "r" } },
+
+    { INDEX_op_deposit_i32, { "r", "0", "rZ" } },
+    { INDEX_op_deposit_i64, { "r", "0", "rZ" } },
+
+    { INDEX_op_add2_i32, { "r", "r", "rZ", "rZ", "rA", "rMZ" } },
+    { INDEX_op_add2_i64, { "r", "r", "rZ", "rZ", "rA", "rMZ" } },
+    { INDEX_op_sub2_i32, { "r", "r", "rZ", "rZ", "rA", "rMZ" } },
+    { INDEX_op_sub2_i64, { "r", "r", "rZ", "rZ", "rA", "rMZ" } },
+
+    { INDEX_op_muluh_i64, { "r", "r", "r" } },
+    { INDEX_op_mulsh_i64, { "r", "r", "r" } },
+
+    { -1 },
+};
+
+static void tcg_target_init(TCGContext *s)
+{
+    tcg_regset_set32(tcg_target_available_regs[TCG_TYPE_I32], 0, 0xffffffff);
+    tcg_regset_set32(tcg_target_available_regs[TCG_TYPE_I64], 0, 0xffffffff);
+
+    tcg_regset_set32(tcg_target_call_clobber_regs, 0,
+                     (1 << TCG_REG_X0) | (1 << TCG_REG_X1) |
+                     (1 << TCG_REG_X2) | (1 << TCG_REG_X3) |
+                     (1 << TCG_REG_X4) | (1 << TCG_REG_X5) |
+                     (1 << TCG_REG_X6) | (1 << TCG_REG_X7) |
+                     (1 << TCG_REG_X8) | (1 << TCG_REG_X9) |
+                     (1 << TCG_REG_X10) | (1 << TCG_REG_X11) |
+                     (1 << TCG_REG_X12) | (1 << TCG_REG_X13) |
+                     (1 << TCG_REG_X14) | (1 << TCG_REG_X15) |
+                     (1 << TCG_REG_X16) | (1 << TCG_REG_X17) |
+                     (1 << TCG_REG_X18) | (1 << TCG_REG_X30));
+
+    tcg_regset_clear(s->reserved_regs);
+    tcg_regset_set_reg(s->reserved_regs, TCG_REG_SP);
+    tcg_regset_set_reg(s->reserved_regs, TCG_REG_FP);
+    tcg_regset_set_reg(s->reserved_regs, TCG_REG_TMP);
+    tcg_regset_set_reg(s->reserved_regs, TCG_REG_X18); /* platform register */
+
+    tcg_add_target_add_op_defs(aarch64_op_defs);
+}
+
+/* Saving pairs: (X19, X20) .. (X27, X28), (X29(fp), X30(lr)).  */
+#define PUSH_SIZE  ((30 - 19 + 1) * 8)
+
+#define FRAME_SIZE \
+    ((PUSH_SIZE \
+      + TCG_STATIC_CALL_ARGS_SIZE \
+      + CPU_TEMP_BUF_NLONGS * sizeof(long) \
+      + TCG_TARGET_STACK_ALIGN - 1) \
+     & ~(TCG_TARGET_STACK_ALIGN - 1))
+
+/* We're expecting a 2 byte uleb128 encoded value.  */
+QEMU_BUILD_BUG_ON(FRAME_SIZE >= (1 << 14));
+
+/* We're expecting to use a single ADDI insn.  */
+QEMU_BUILD_BUG_ON(FRAME_SIZE - PUSH_SIZE > 0xfff);
+
+static void tcg_target_qemu_prologue(TCGContext *s)
+{
+    TCGReg r;
+
+    /* Push (FP, LR) and allocate space for all saved registers.  */
+    tcg_out_insn(s, 3314, STP, TCG_REG_FP, TCG_REG_LR,
+                 TCG_REG_SP, -PUSH_SIZE, 1, 1);
+
+    /* Set up frame pointer for canonical unwinding.  */
+    tcg_out_movr_sp(s, TCG_TYPE_I64, TCG_REG_FP, TCG_REG_SP);
+
+    /* Store callee-preserved regs x19..x28.  */
+    for (r = TCG_REG_X19; r <= TCG_REG_X27; r += 2) {
+        int ofs = (r - TCG_REG_X19 + 2) * 8;
+        tcg_out_insn(s, 3314, STP, r, r + 1, TCG_REG_SP, ofs, 1, 0);
+    }
+
+    /* Make stack space for TCG locals.  */
+    tcg_out_insn(s, 3401, SUBI, TCG_TYPE_I64, TCG_REG_SP, TCG_REG_SP,
+                 FRAME_SIZE - PUSH_SIZE);
+
+    /* Inform TCG about how to find TCG locals with register, offset, size.  */
+    tcg_set_frame(s, TCG_REG_SP, TCG_STATIC_CALL_ARGS_SIZE,
+                  CPU_TEMP_BUF_NLONGS * sizeof(long));
+
+#if defined(CONFIG_USE_GUEST_BASE)
+    if (USE_GUEST_BASE) {
+        tcg_out_movi(s, TCG_TYPE_PTR, TCG_REG_GUEST_BASE, GUEST_BASE);
+        tcg_regset_set_reg(s->reserved_regs, TCG_REG_GUEST_BASE);
+    }
+#endif
+
+    tcg_out_mov(s, TCG_TYPE_PTR, TCG_AREG0, tcg_target_call_iarg_regs[0]);
+    tcg_out_insn(s, 3207, BR, tcg_target_call_iarg_regs[1]);
+
+    tb_ret_addr = s->code_ptr;
+
+    /* Remove TCG locals stack space.  */
+    tcg_out_insn(s, 3401, ADDI, TCG_TYPE_I64, TCG_REG_SP, TCG_REG_SP,
+                 FRAME_SIZE - PUSH_SIZE);
+
+    /* Restore registers x19..x28.  */
+    for (r = TCG_REG_X19; r <= TCG_REG_X27; r += 2) {
+        int ofs = (r - TCG_REG_X19 + 2) * 8;
+        tcg_out_insn(s, 3314, LDP, r, r + 1, TCG_REG_SP, ofs, 1, 0);
+    }
+
+    /* Pop (FP, LR), restore SP to previous frame.  */
+    tcg_out_insn(s, 3314, LDP, TCG_REG_FP, TCG_REG_LR,
+                 TCG_REG_SP, PUSH_SIZE, 0, 1);
+    tcg_out_insn(s, 3207, RET, TCG_REG_LR);
+}
+
+typedef struct {
+    DebugFrameHeader h;
+    uint8_t fde_def_cfa[4];
+    uint8_t fde_reg_ofs[24];
+} DebugFrame;
+
+#define ELF_HOST_MACHINE EM_AARCH64
+
+static const DebugFrame debug_frame = {
+    .h.cie.len = sizeof(DebugFrameCIE)-4, /* length after .len member */
+    .h.cie.id = -1,
+    .h.cie.version = 1,
+    .h.cie.code_align = 1,
+    .h.cie.data_align = 0x78,             /* sleb128 -8 */
+    .h.cie.return_column = TCG_REG_LR,
+
+    /* Total FDE size does not include the "len" member.  */
+    .h.fde.len = sizeof(DebugFrame) - offsetof(DebugFrame, h.fde.cie_offset),
+
+    .fde_def_cfa = {
+        12, TCG_REG_SP,                 /* DW_CFA_def_cfa sp, ... */
+        (FRAME_SIZE & 0x7f) | 0x80,     /* ... uleb128 FRAME_SIZE */
+        (FRAME_SIZE >> 7)
+    },
+    .fde_reg_ofs = {
+        0x80 + 28, 1,                   /* DW_CFA_offset, x28,  -8 */
+        0x80 + 27, 2,                   /* DW_CFA_offset, x27, -16 */
+        0x80 + 26, 3,                   /* DW_CFA_offset, x26, -24 */
+        0x80 + 25, 4,                   /* DW_CFA_offset, x25, -32 */
+        0x80 + 24, 5,                   /* DW_CFA_offset, x24, -40 */
+        0x80 + 23, 6,                   /* DW_CFA_offset, x23, -48 */
+        0x80 + 22, 7,                   /* DW_CFA_offset, x22, -56 */
+        0x80 + 21, 8,                   /* DW_CFA_offset, x21, -64 */
+        0x80 + 20, 9,                   /* DW_CFA_offset, x20, -72 */
+        0x80 + 19, 10,                  /* DW_CFA_offset, x1p, -80 */
+        0x80 + 30, 11,                  /* DW_CFA_offset,  lr, -88 */
+        0x80 + 29, 12,                  /* DW_CFA_offset,  fp, -96 */
+    }
+};
+
+void tcg_register_jit(void *buf, size_t buf_size)
+{
+    tcg_register_jit_int(buf, buf_size, &debug_frame, sizeof(debug_frame));
+}
diff --git a/tcg/aarch64/tcg-target.h b/tcg/aarch64/tcg-target.h
new file mode 100644
index 00000000..8aec04d2
--- /dev/null
+++ b/tcg/aarch64/tcg-target.h
@@ -0,0 +1,108 @@
+/*
+ * Initial TCG Implementation for aarch64
+ *
+ * Copyright (c) 2013 Huawei Technologies Duesseldorf GmbH
+ * Written by Claudio Fontana
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2 or
+ * (at your option) any later version.
+ *
+ * See the COPYING file in the top-level directory for details.
+ */
+
+#ifndef TCG_TARGET_AARCH64
+#define TCG_TARGET_AARCH64 1
+
+#define TCG_TARGET_INSN_UNIT_SIZE  4
+#define TCG_TARGET_TLB_DISPLACEMENT_BITS 24
+#undef TCG_TARGET_STACK_GROWSUP
+
+typedef enum {
+    TCG_REG_X0, TCG_REG_X1, TCG_REG_X2, TCG_REG_X3,
+    TCG_REG_X4, TCG_REG_X5, TCG_REG_X6, TCG_REG_X7,
+    TCG_REG_X8, TCG_REG_X9, TCG_REG_X10, TCG_REG_X11,
+    TCG_REG_X12, TCG_REG_X13, TCG_REG_X14, TCG_REG_X15,
+    TCG_REG_X16, TCG_REG_X17, TCG_REG_X18, TCG_REG_X19,
+    TCG_REG_X20, TCG_REG_X21, TCG_REG_X22, TCG_REG_X23,
+    TCG_REG_X24, TCG_REG_X25, TCG_REG_X26, TCG_REG_X27,
+    TCG_REG_X28, TCG_REG_X29, TCG_REG_X30,
+
+    /* X31 is either the stack pointer or zero, depending on context.  */
+    TCG_REG_SP = 31,
+    TCG_REG_XZR = 31,
+
+    /* Aliases.  */
+    TCG_REG_FP = TCG_REG_X29,
+    TCG_REG_LR = TCG_REG_X30,
+    TCG_AREG0  = TCG_REG_X19,
+} TCGReg;
+
+#define TCG_TARGET_NB_REGS 32
+
+/* used for function call generation */
+#define TCG_REG_CALL_STACK              TCG_REG_SP
+#define TCG_TARGET_STACK_ALIGN          16
+#define TCG_TARGET_CALL_ALIGN_ARGS      1
+#define TCG_TARGET_CALL_STACK_OFFSET    0
+
+/* optional instructions */
+#define TCG_TARGET_HAS_div_i32          1
+#define TCG_TARGET_HAS_rem_i32          1
+#define TCG_TARGET_HAS_ext8s_i32        1
+#define TCG_TARGET_HAS_ext16s_i32       1
+#define TCG_TARGET_HAS_ext8u_i32        1
+#define TCG_TARGET_HAS_ext16u_i32       1
+#define TCG_TARGET_HAS_bswap16_i32      1
+#define TCG_TARGET_HAS_bswap32_i32      1
+#define TCG_TARGET_HAS_not_i32          1
+#define TCG_TARGET_HAS_neg_i32          1
+#define TCG_TARGET_HAS_rot_i32          1
+#define TCG_TARGET_HAS_andc_i32         1
+#define TCG_TARGET_HAS_orc_i32          1
+#define TCG_TARGET_HAS_eqv_i32          1
+#define TCG_TARGET_HAS_nand_i32         0
+#define TCG_TARGET_HAS_nor_i32          0
+#define TCG_TARGET_HAS_deposit_i32      1
+#define TCG_TARGET_HAS_movcond_i32      1
+#define TCG_TARGET_HAS_add2_i32         1
+#define TCG_TARGET_HAS_sub2_i32         1
+#define TCG_TARGET_HAS_mulu2_i32        0
+#define TCG_TARGET_HAS_muls2_i32        0
+#define TCG_TARGET_HAS_muluh_i32        0
+#define TCG_TARGET_HAS_mulsh_i32        0
+#define TCG_TARGET_HAS_trunc_shr_i32    0
+
+#define TCG_TARGET_HAS_div_i64          1
+#define TCG_TARGET_HAS_rem_i64          1
+#define TCG_TARGET_HAS_ext8s_i64        1
+#define TCG_TARGET_HAS_ext16s_i64       1
+#define TCG_TARGET_HAS_ext32s_i64       1
+#define TCG_TARGET_HAS_ext8u_i64        1
+#define TCG_TARGET_HAS_ext16u_i64       1
+#define TCG_TARGET_HAS_ext32u_i64       1
+#define TCG_TARGET_HAS_bswap16_i64      1
+#define TCG_TARGET_HAS_bswap32_i64      1
+#define TCG_TARGET_HAS_bswap64_i64      1
+#define TCG_TARGET_HAS_not_i64          1
+#define TCG_TARGET_HAS_neg_i64          1
+#define TCG_TARGET_HAS_rot_i64          1
+#define TCG_TARGET_HAS_andc_i64         1
+#define TCG_TARGET_HAS_orc_i64          1
+#define TCG_TARGET_HAS_eqv_i64          1
+#define TCG_TARGET_HAS_nand_i64         0
+#define TCG_TARGET_HAS_nor_i64          0
+#define TCG_TARGET_HAS_deposit_i64      1
+#define TCG_TARGET_HAS_movcond_i64      1
+#define TCG_TARGET_HAS_add2_i64         1
+#define TCG_TARGET_HAS_sub2_i64         1
+#define TCG_TARGET_HAS_mulu2_i64        0
+#define TCG_TARGET_HAS_muls2_i64        0
+#define TCG_TARGET_HAS_muluh_i64        1
+#define TCG_TARGET_HAS_mulsh_i64        1
+
+static inline void flush_icache_range(uintptr_t start, uintptr_t stop)
+{
+    __builtin___clear_cache((char *)start, (char *)stop);
+}
+
+#endif /* TCG_TARGET_AARCH64 */
diff --git a/tcg/arm/tcg-target.c b/tcg/arm/tcg-target.c
new file mode 100644
index 00000000..ae2ec7a9
--- /dev/null
+++ b/tcg/arm/tcg-target.c
@@ -0,0 +1,2128 @@
+/*
+ * Tiny Code Generator for QEMU
+ *
+ * Copyright (c) 2008 Andrzej Zaborowski
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (the "Software"), to deal
+ * in the Software without restriction, including without limitation the rights
+ * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+ * copies of the Software, and to permit persons to whom the Software is
+ * furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+ * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+ * THE SOFTWARE.
+ */
+
+#include "elf.h"
+#include "tcg-be-ldst.h"
+
+/* The __ARM_ARCH define is provided by gcc 4.8.  Construct it otherwise.  */
+#ifndef __ARM_ARCH
+# if defined(__ARM_ARCH_7__) || defined(__ARM_ARCH_7A__) \
+     || defined(__ARM_ARCH_7R__) || defined(__ARM_ARCH_7M__) \
+     || defined(__ARM_ARCH_7EM__)
+#  define __ARM_ARCH 7
+# elif defined(__ARM_ARCH_6__) || defined(__ARM_ARCH_6J__) \
+       || defined(__ARM_ARCH_6Z__) || defined(__ARM_ARCH_6ZK__) \
+       || defined(__ARM_ARCH_6K__) || defined(__ARM_ARCH_6T2__)
+#  define __ARM_ARCH 6
+# elif defined(__ARM_ARCH_5__) || defined(__ARM_ARCH_5E__) \
+       || defined(__ARM_ARCH_5T__) || defined(__ARM_ARCH_5TE__) \
+       || defined(__ARM_ARCH_5TEJ__)
+#  define __ARM_ARCH 5
+# else
+#  define __ARM_ARCH 4
+# endif
+#endif
+
+static int arm_arch = __ARM_ARCH;
+
+#if defined(__ARM_ARCH_5T__) \
+    || defined(__ARM_ARCH_5TE__) || defined(__ARM_ARCH_5TEJ__)
+# define use_armv5t_instructions 1
+#else
+# define use_armv5t_instructions use_armv6_instructions
+#endif
+
+#define use_armv6_instructions  (__ARM_ARCH >= 6 || arm_arch >= 6)
+#define use_armv7_instructions  (__ARM_ARCH >= 7 || arm_arch >= 7)
+
+#ifndef use_idiv_instructions
+bool use_idiv_instructions;
+#endif
+
+/* ??? Ought to think about changing CONFIG_SOFTMMU to always defined.  */
+#ifdef CONFIG_SOFTMMU
+# define USING_SOFTMMU 1
+#else
+# define USING_SOFTMMU 0
+#endif
+
+#ifndef NDEBUG
+static const char * const tcg_target_reg_names[TCG_TARGET_NB_REGS] = {
+    "%r0",
+    "%r1",
+    "%r2",
+    "%r3",
+    "%r4",
+    "%r5",
+    "%r6",
+    "%r7",
+    "%r8",
+    "%r9",
+    "%r10",
+    "%r11",
+    "%r12",
+    "%r13",
+    "%r14",
+    "%pc",
+};
+#endif
+
+static const int tcg_target_reg_alloc_order[] = {
+    TCG_REG_R4,
+    TCG_REG_R5,
+    TCG_REG_R6,
+    TCG_REG_R7,
+    TCG_REG_R8,
+    TCG_REG_R9,
+    TCG_REG_R10,
+    TCG_REG_R11,
+    TCG_REG_R13,
+    TCG_REG_R0,
+    TCG_REG_R1,
+    TCG_REG_R2,
+    TCG_REG_R3,
+    TCG_REG_R12,
+    TCG_REG_R14,
+};
+
+static const int tcg_target_call_iarg_regs[4] = {
+    TCG_REG_R0, TCG_REG_R1, TCG_REG_R2, TCG_REG_R3
+};
+static const int tcg_target_call_oarg_regs[2] = {
+    TCG_REG_R0, TCG_REG_R1
+};
+
+#define TCG_REG_TMP  TCG_REG_R12
+
+static inline void reloc_pc24(tcg_insn_unit *code_ptr, tcg_insn_unit *target)
+{
+    ptrdiff_t offset = (tcg_ptr_byte_diff(target, code_ptr) - 8) >> 2;
+    *code_ptr = (*code_ptr & ~0xffffff) | (offset & 0xffffff);
+}
+
+static void patch_reloc(tcg_insn_unit *code_ptr, int type,
+                        intptr_t value, intptr_t addend)
+{
+    assert(type == R_ARM_PC24);
+    assert(addend == 0);
+    reloc_pc24(code_ptr, (tcg_insn_unit *)value);
+}
+
+#define TCG_CT_CONST_ARM  0x100
+#define TCG_CT_CONST_INV  0x200
+#define TCG_CT_CONST_NEG  0x400
+#define TCG_CT_CONST_ZERO 0x800
+
+/* parse target specific constraints */
+static int target_parse_constraint(TCGArgConstraint *ct, const char **pct_str)
+{
+    const char *ct_str;
+
+    ct_str = *pct_str;
+    switch (ct_str[0]) {
+    case 'I':
+        ct->ct |= TCG_CT_CONST_ARM;
+        break;
+    case 'K':
+        ct->ct |= TCG_CT_CONST_INV;
+        break;
+    case 'N': /* The gcc constraint letter is L, already used here.  */
+        ct->ct |= TCG_CT_CONST_NEG;
+        break;
+    case 'Z':
+        ct->ct |= TCG_CT_CONST_ZERO;
+        break;
+
+    case 'r':
+        ct->ct |= TCG_CT_REG;
+        tcg_regset_set32(ct->u.regs, 0, (1 << TCG_TARGET_NB_REGS) - 1);
+        break;
+
+    /* qemu_ld address */
+    case 'l':
+        ct->ct |= TCG_CT_REG;
+        tcg_regset_set32(ct->u.regs, 0, (1 << TCG_TARGET_NB_REGS) - 1);
+#ifdef CONFIG_SOFTMMU
+        /* r0-r2,lr will be overwritten when reading the tlb entry,
+           so don't use these. */
+        tcg_regset_reset_reg(ct->u.regs, TCG_REG_R0);
+        tcg_regset_reset_reg(ct->u.regs, TCG_REG_R1);
+        tcg_regset_reset_reg(ct->u.regs, TCG_REG_R2);
+        tcg_regset_reset_reg(ct->u.regs, TCG_REG_R14);
+#endif
+        break;
+
+    /* qemu_st address & data */
+    case 's':
+        ct->ct |= TCG_CT_REG;
+        tcg_regset_set32(ct->u.regs, 0, (1 << TCG_TARGET_NB_REGS) - 1);
+        /* r0-r2 will be overwritten when reading the tlb entry (softmmu only)
+           and r0-r1 doing the byte swapping, so don't use these. */
+        tcg_regset_reset_reg(ct->u.regs, TCG_REG_R0);
+        tcg_regset_reset_reg(ct->u.regs, TCG_REG_R1);
+#if defined(CONFIG_SOFTMMU)
+        /* Avoid clashes with registers being used for helper args */
+        tcg_regset_reset_reg(ct->u.regs, TCG_REG_R2);
+#if TARGET_LONG_BITS == 64
+        /* Avoid clashes with registers being used for helper args */
+        tcg_regset_reset_reg(ct->u.regs, TCG_REG_R3);
+#endif
+        tcg_regset_reset_reg(ct->u.regs, TCG_REG_R14);
+#endif
+        break;
+
+    default:
+        return -1;
+    }
+    ct_str++;
+    *pct_str = ct_str;
+
+    return 0;
+}
+
+static inline uint32_t rotl(uint32_t val, int n)
+{
+  return (val << n) | (val >> (32 - n));
+}
+
+/* ARM immediates for ALU instructions are made of an unsigned 8-bit
+   right-rotated by an even amount between 0 and 30. */
+static inline int encode_imm(uint32_t imm)
+{
+    int shift;
+
+    /* simple case, only lower bits */
+    if ((imm & ~0xff) == 0)
+        return 0;
+    /* then try a simple even shift */
+    shift = ctz32(imm) & ~1;
+    if (((imm >> shift) & ~0xff) == 0)
+        return 32 - shift;
+    /* now try harder with rotations */
+    if ((rotl(imm, 2) & ~0xff) == 0)
+        return 2;
+    if ((rotl(imm, 4) & ~0xff) == 0)
+        return 4;
+    if ((rotl(imm, 6) & ~0xff) == 0)
+        return 6;
+    /* imm can't be encoded */
+    return -1;
+}
+
+static inline int check_fit_imm(uint32_t imm)
+{
+    return encode_imm(imm) >= 0;
+}
+
+/* Test if a constant matches the constraint.
+ * TODO: define constraints for:
+ *
+ * ldr/str offset:   between -0xfff and 0xfff
+ * ldrh/strh offset: between -0xff and 0xff
+ * mov operand2:     values represented with x << (2 * y), x < 0x100
+ * add, sub, eor...: ditto
+ */
+static inline int tcg_target_const_match(tcg_target_long val, TCGType type,
+                                         const TCGArgConstraint *arg_ct)
+{
+    int ct;
+    ct = arg_ct->ct;
+    if (ct & TCG_CT_CONST) {
+        return 1;
+    } else if ((ct & TCG_CT_CONST_ARM) && check_fit_imm(val)) {
+        return 1;
+    } else if ((ct & TCG_CT_CONST_INV) && check_fit_imm(~val)) {
+        return 1;
+    } else if ((ct & TCG_CT_CONST_NEG) && check_fit_imm(-val)) {
+        return 1;
+    } else if ((ct & TCG_CT_CONST_ZERO) && val == 0) {
+        return 1;
+    } else {
+        return 0;
+    }
+}
+
+#define TO_CPSR (1 << 20)
+
+typedef enum {
+    ARITH_AND = 0x0 << 21,
+    ARITH_EOR = 0x1 << 21,
+    ARITH_SUB = 0x2 << 21,
+    ARITH_RSB = 0x3 << 21,
+    ARITH_ADD = 0x4 << 21,
+    ARITH_ADC = 0x5 << 21,
+    ARITH_SBC = 0x6 << 21,
+    ARITH_RSC = 0x7 << 21,
+    ARITH_TST = 0x8 << 21 | TO_CPSR,
+    ARITH_CMP = 0xa << 21 | TO_CPSR,
+    ARITH_CMN = 0xb << 21 | TO_CPSR,
+    ARITH_ORR = 0xc << 21,
+    ARITH_MOV = 0xd << 21,
+    ARITH_BIC = 0xe << 21,
+    ARITH_MVN = 0xf << 21,
+
+    INSN_LDR_IMM   = 0x04100000,
+    INSN_LDR_REG   = 0x06100000,
+    INSN_STR_IMM   = 0x04000000,
+    INSN_STR_REG   = 0x06000000,
+
+    INSN_LDRH_IMM  = 0x005000b0,
+    INSN_LDRH_REG  = 0x001000b0,
+    INSN_LDRSH_IMM = 0x005000f0,
+    INSN_LDRSH_REG = 0x001000f0,
+    INSN_STRH_IMM  = 0x004000b0,
+    INSN_STRH_REG  = 0x000000b0,
+
+    INSN_LDRB_IMM  = 0x04500000,
+    INSN_LDRB_REG  = 0x06500000,
+    INSN_LDRSB_IMM = 0x005000d0,
+    INSN_LDRSB_REG = 0x001000d0,
+    INSN_STRB_IMM  = 0x04400000,
+    INSN_STRB_REG  = 0x06400000,
+
+    INSN_LDRD_IMM  = 0x004000d0,
+    INSN_LDRD_REG  = 0x000000d0,
+    INSN_STRD_IMM  = 0x004000f0,
+    INSN_STRD_REG  = 0x000000f0,
+} ARMInsn;
+
+#define SHIFT_IMM_LSL(im)	(((im) << 7) | 0x00)
+#define SHIFT_IMM_LSR(im)	(((im) << 7) | 0x20)
+#define SHIFT_IMM_ASR(im)	(((im) << 7) | 0x40)
+#define SHIFT_IMM_ROR(im)	(((im) << 7) | 0x60)
+#define SHIFT_REG_LSL(rs)	(((rs) << 8) | 0x10)
+#define SHIFT_REG_LSR(rs)	(((rs) << 8) | 0x30)
+#define SHIFT_REG_ASR(rs)	(((rs) << 8) | 0x50)
+#define SHIFT_REG_ROR(rs)	(((rs) << 8) | 0x70)
+
+enum arm_cond_code_e {
+    COND_EQ = 0x0,
+    COND_NE = 0x1,
+    COND_CS = 0x2,	/* Unsigned greater or equal */
+    COND_CC = 0x3,	/* Unsigned less than */
+    COND_MI = 0x4,	/* Negative */
+    COND_PL = 0x5,	/* Zero or greater */
+    COND_VS = 0x6,	/* Overflow */
+    COND_VC = 0x7,	/* No overflow */
+    COND_HI = 0x8,	/* Unsigned greater than */
+    COND_LS = 0x9,	/* Unsigned less or equal */
+    COND_GE = 0xa,
+    COND_LT = 0xb,
+    COND_GT = 0xc,
+    COND_LE = 0xd,
+    COND_AL = 0xe,
+};
+
+static const uint8_t tcg_cond_to_arm_cond[] = {
+    [TCG_COND_EQ] = COND_EQ,
+    [TCG_COND_NE] = COND_NE,
+    [TCG_COND_LT] = COND_LT,
+    [TCG_COND_GE] = COND_GE,
+    [TCG_COND_LE] = COND_LE,
+    [TCG_COND_GT] = COND_GT,
+    /* unsigned */
+    [TCG_COND_LTU] = COND_CC,
+    [TCG_COND_GEU] = COND_CS,
+    [TCG_COND_LEU] = COND_LS,
+    [TCG_COND_GTU] = COND_HI,
+};
+
+static inline void tcg_out_bx(TCGContext *s, int cond, int rn)
+{
+    tcg_out32(s, (cond << 28) | 0x012fff10 | rn);
+}
+
+static inline void tcg_out_b(TCGContext *s, int cond, int32_t offset)
+{
+    tcg_out32(s, (cond << 28) | 0x0a000000 |
+                    (((offset - 8) >> 2) & 0x00ffffff));
+}
+
+static inline void tcg_out_b_noaddr(TCGContext *s, int cond)
+{
+    /* We pay attention here to not modify the branch target by masking
+       the corresponding bytes.  This ensure that caches and memory are
+       kept coherent during retranslation. */
+    tcg_out32(s, deposit32(*s->code_ptr, 24, 8, (cond << 4) | 0x0a));
+}
+
+static inline void tcg_out_bl_noaddr(TCGContext *s, int cond)
+{
+    /* We pay attention here to not modify the branch target by masking
+       the corresponding bytes.  This ensure that caches and memory are
+       kept coherent during retranslation. */
+    tcg_out32(s, deposit32(*s->code_ptr, 24, 8, (cond << 4) | 0x0b));
+}
+
+static inline void tcg_out_bl(TCGContext *s, int cond, int32_t offset)
+{
+    tcg_out32(s, (cond << 28) | 0x0b000000 |
+                    (((offset - 8) >> 2) & 0x00ffffff));
+}
+
+static inline void tcg_out_blx(TCGContext *s, int cond, int rn)
+{
+    tcg_out32(s, (cond << 28) | 0x012fff30 | rn);
+}
+
+static inline void tcg_out_blx_imm(TCGContext *s, int32_t offset)
+{
+    tcg_out32(s, 0xfa000000 | ((offset & 2) << 23) |
+                (((offset - 8) >> 2) & 0x00ffffff));
+}
+
+static inline void tcg_out_dat_reg(TCGContext *s,
+                int cond, int opc, int rd, int rn, int rm, int shift)
+{
+    tcg_out32(s, (cond << 28) | (0 << 25) | opc |
+                    (rn << 16) | (rd << 12) | shift | rm);
+}
+
+static inline void tcg_out_nop(TCGContext *s)
+{
+    if (use_armv7_instructions) {
+        /* Architected nop introduced in v6k.  */
+        /* ??? This is an MSR (imm) 0,0,0 insn.  Anyone know if this
+           also Just So Happened to do nothing on pre-v6k so that we
+           don't need to conditionalize it?  */
+        tcg_out32(s, 0xe320f000);
+    } else {
+        /* Prior to that the assembler uses mov r0, r0.  */
+        tcg_out_dat_reg(s, COND_AL, ARITH_MOV, 0, 0, 0, SHIFT_IMM_LSL(0));
+    }
+}
+
+static inline void tcg_out_mov_reg(TCGContext *s, int cond, int rd, int rm)
+{
+    /* Simple reg-reg move, optimising out the 'do nothing' case */
+    if (rd != rm) {
+        tcg_out_dat_reg(s, cond, ARITH_MOV, rd, 0, rm, SHIFT_IMM_LSL(0));
+    }
+}
+
+static inline void tcg_out_dat_imm(TCGContext *s,
+                int cond, int opc, int rd, int rn, int im)
+{
+    tcg_out32(s, (cond << 28) | (1 << 25) | opc |
+                    (rn << 16) | (rd << 12) | im);
+}
+
+static void tcg_out_movi32(TCGContext *s, int cond, int rd, uint32_t arg)
+{
+    int rot, opc, rn;
+
+    /* For armv7, make sure not to use movw+movt when mov/mvn would do.
+       Speed things up by only checking when movt would be required.
+       Prior to armv7, have one go at fully rotated immediates before
+       doing the decomposition thing below.  */
+    if (!use_armv7_instructions || (arg & 0xffff0000)) {
+        rot = encode_imm(arg);
+        if (rot >= 0) {
+            tcg_out_dat_imm(s, cond, ARITH_MOV, rd, 0,
+                            rotl(arg, rot) | (rot << 7));
+            return;
+        }
+        rot = encode_imm(~arg);
+        if (rot >= 0) {
+            tcg_out_dat_imm(s, cond, ARITH_MVN, rd, 0,
+                            rotl(~arg, rot) | (rot << 7));
+            return;
+        }
+    }
+
+    /* Use movw + movt.  */
+    if (use_armv7_instructions) {
+        /* movw */
+        tcg_out32(s, (cond << 28) | 0x03000000 | (rd << 12)
+                  | ((arg << 4) & 0x000f0000) | (arg & 0xfff));
+        if (arg & 0xffff0000) {
+            /* movt */
+            tcg_out32(s, (cond << 28) | 0x03400000 | (rd << 12)
+                      | ((arg >> 12) & 0x000f0000) | ((arg >> 16) & 0xfff));
+        }
+        return;
+    }
+
+    /* TODO: This is very suboptimal, we can easily have a constant
+       pool somewhere after all the instructions.  */
+    opc = ARITH_MOV;
+    rn = 0;
+    /* If we have lots of leading 1's, we can shorten the sequence by
+       beginning with mvn and then clearing higher bits with eor.  */
+    if (clz32(~arg) > clz32(arg)) {
+        opc = ARITH_MVN, arg = ~arg;
+    }
+    do {
+        int i = ctz32(arg) & ~1;
+        rot = ((32 - i) << 7) & 0xf00;
+        tcg_out_dat_imm(s, cond, opc, rd, rn, ((arg >> i) & 0xff) | rot);
+        arg &= ~(0xff << i);
+
+        opc = ARITH_EOR;
+        rn = rd;
+    } while (arg);
+}
+
+static inline void tcg_out_dat_rI(TCGContext *s, int cond, int opc, TCGArg dst,
+                                  TCGArg lhs, TCGArg rhs, int rhs_is_const)
+{
+    /* Emit either the reg,imm or reg,reg form of a data-processing insn.
+     * rhs must satisfy the "rI" constraint.
+     */
+    if (rhs_is_const) {
+        int rot = encode_imm(rhs);
+        assert(rot >= 0);
+        tcg_out_dat_imm(s, cond, opc, dst, lhs, rotl(rhs, rot) | (rot << 7));
+    } else {
+        tcg_out_dat_reg(s, cond, opc, dst, lhs, rhs, SHIFT_IMM_LSL(0));
+    }
+}
+
+static void tcg_out_dat_rIK(TCGContext *s, int cond, int opc, int opinv,
+                            TCGReg dst, TCGReg lhs, TCGArg rhs,
+                            bool rhs_is_const)
+{
+    /* Emit either the reg,imm or reg,reg form of a data-processing insn.
+     * rhs must satisfy the "rIK" constraint.
+     */
+    if (rhs_is_const) {
+        int rot = encode_imm(rhs);
+        if (rot < 0) {
+            rhs = ~rhs;
+            rot = encode_imm(rhs);
+            assert(rot >= 0);
+            opc = opinv;
+        }
+        tcg_out_dat_imm(s, cond, opc, dst, lhs, rotl(rhs, rot) | (rot << 7));
+    } else {
+        tcg_out_dat_reg(s, cond, opc, dst, lhs, rhs, SHIFT_IMM_LSL(0));
+    }
+}
+
+static void tcg_out_dat_rIN(TCGContext *s, int cond, int opc, int opneg,
+                            TCGArg dst, TCGArg lhs, TCGArg rhs,
+                            bool rhs_is_const)
+{
+    /* Emit either the reg,imm or reg,reg form of a data-processing insn.
+     * rhs must satisfy the "rIN" constraint.
+     */
+    if (rhs_is_const) {
+        int rot = encode_imm(rhs);
+        if (rot < 0) {
+            rhs = -rhs;
+            rot = encode_imm(rhs);
+            assert(rot >= 0);
+            opc = opneg;
+        }
+        tcg_out_dat_imm(s, cond, opc, dst, lhs, rotl(rhs, rot) | (rot << 7));
+    } else {
+        tcg_out_dat_reg(s, cond, opc, dst, lhs, rhs, SHIFT_IMM_LSL(0));
+    }
+}
+
+static inline void tcg_out_mul32(TCGContext *s, int cond, TCGReg rd,
+                                 TCGReg rn, TCGReg rm)
+{
+    /* if ArchVersion() < 6 && d == n then UNPREDICTABLE;  */
+    if (!use_armv6_instructions && rd == rn) {
+        if (rd == rm) {
+            /* rd == rn == rm; copy an input to tmp first.  */
+            tcg_out_mov_reg(s, cond, TCG_REG_TMP, rn);
+            rm = rn = TCG_REG_TMP;
+        } else {
+            rn = rm;
+            rm = rd;
+        }
+    }
+    /* mul */
+    tcg_out32(s, (cond << 28) | 0x90 | (rd << 16) | (rm << 8) | rn);
+}
+
+static inline void tcg_out_umull32(TCGContext *s, int cond, TCGReg rd0,
+                                   TCGReg rd1, TCGReg rn, TCGReg rm)
+{
+    /* if ArchVersion() < 6 && (dHi == n || dLo == n) then UNPREDICTABLE;  */
+    if (!use_armv6_instructions && (rd0 == rn || rd1 == rn)) {
+        if (rd0 == rm || rd1 == rm) {
+            tcg_out_mov_reg(s, cond, TCG_REG_TMP, rn);
+            rn = TCG_REG_TMP;
+        } else {
+            TCGReg t = rn;
+            rn = rm;
+            rm = t;
+        }
+    }
+    /* umull */
+    tcg_out32(s, (cond << 28) | 0x00800090 |
+              (rd1 << 16) | (rd0 << 12) | (rm << 8) | rn);
+}
+
+static inline void tcg_out_smull32(TCGContext *s, int cond, TCGReg rd0,
+                                   TCGReg rd1, TCGReg rn, TCGReg rm)
+{
+    /* if ArchVersion() < 6 && (dHi == n || dLo == n) then UNPREDICTABLE;  */
+    if (!use_armv6_instructions && (rd0 == rn || rd1 == rn)) {
+        if (rd0 == rm || rd1 == rm) {
+            tcg_out_mov_reg(s, cond, TCG_REG_TMP, rn);
+            rn = TCG_REG_TMP;
+        } else {
+            TCGReg t = rn;
+            rn = rm;
+            rm = t;
+        }
+    }
+    /* smull */
+    tcg_out32(s, (cond << 28) | 0x00c00090 |
+              (rd1 << 16) | (rd0 << 12) | (rm << 8) | rn);
+}
+
+static inline void tcg_out_sdiv(TCGContext *s, int cond, int rd, int rn, int rm)
+{
+    tcg_out32(s, 0x0710f010 | (cond << 28) | (rd << 16) | rn | (rm << 8));
+}
+
+static inline void tcg_out_udiv(TCGContext *s, int cond, int rd, int rn, int rm)
+{
+    tcg_out32(s, 0x0730f010 | (cond << 28) | (rd << 16) | rn | (rm << 8));
+}
+
+static inline void tcg_out_ext8s(TCGContext *s, int cond,
+                                 int rd, int rn)
+{
+    if (use_armv6_instructions) {
+        /* sxtb */
+        tcg_out32(s, 0x06af0070 | (cond << 28) | (rd << 12) | rn);
+    } else {
+        tcg_out_dat_reg(s, cond, ARITH_MOV,
+                        rd, 0, rn, SHIFT_IMM_LSL(24));
+        tcg_out_dat_reg(s, cond, ARITH_MOV,
+                        rd, 0, rd, SHIFT_IMM_ASR(24));
+    }
+}
+
+static inline void tcg_out_ext8u(TCGContext *s, int cond,
+                                 int rd, int rn)
+{
+    tcg_out_dat_imm(s, cond, ARITH_AND, rd, rn, 0xff);
+}
+
+static inline void tcg_out_ext16s(TCGContext *s, int cond,
+                                  int rd, int rn)
+{
+    if (use_armv6_instructions) {
+        /* sxth */
+        tcg_out32(s, 0x06bf0070 | (cond << 28) | (rd << 12) | rn);
+    } else {
+        tcg_out_dat_reg(s, cond, ARITH_MOV,
+                        rd, 0, rn, SHIFT_IMM_LSL(16));
+        tcg_out_dat_reg(s, cond, ARITH_MOV,
+                        rd, 0, rd, SHIFT_IMM_ASR(16));
+    }
+}
+
+static inline void tcg_out_ext16u(TCGContext *s, int cond,
+                                  int rd, int rn)
+{
+    if (use_armv6_instructions) {
+        /* uxth */
+        tcg_out32(s, 0x06ff0070 | (cond << 28) | (rd << 12) | rn);
+    } else {
+        tcg_out_dat_reg(s, cond, ARITH_MOV,
+                        rd, 0, rn, SHIFT_IMM_LSL(16));
+        tcg_out_dat_reg(s, cond, ARITH_MOV,
+                        rd, 0, rd, SHIFT_IMM_LSR(16));
+    }
+}
+
+static inline void tcg_out_bswap16s(TCGContext *s, int cond, int rd, int rn)
+{
+    if (use_armv6_instructions) {
+        /* revsh */
+        tcg_out32(s, 0x06ff0fb0 | (cond << 28) | (rd << 12) | rn);
+    } else {
+        tcg_out_dat_reg(s, cond, ARITH_MOV,
+                        TCG_REG_TMP, 0, rn, SHIFT_IMM_LSL(24));
+        tcg_out_dat_reg(s, cond, ARITH_MOV,
+                        TCG_REG_TMP, 0, TCG_REG_TMP, SHIFT_IMM_ASR(16));
+        tcg_out_dat_reg(s, cond, ARITH_ORR,
+                        rd, TCG_REG_TMP, rn, SHIFT_IMM_LSR(8));
+    }
+}
+
+static inline void tcg_out_bswap16(TCGContext *s, int cond, int rd, int rn)
+{
+    if (use_armv6_instructions) {
+        /* rev16 */
+        tcg_out32(s, 0x06bf0fb0 | (cond << 28) | (rd << 12) | rn);
+    } else {
+        tcg_out_dat_reg(s, cond, ARITH_MOV,
+                        TCG_REG_TMP, 0, rn, SHIFT_IMM_LSL(24));
+        tcg_out_dat_reg(s, cond, ARITH_MOV,
+                        TCG_REG_TMP, 0, TCG_REG_TMP, SHIFT_IMM_LSR(16));
+        tcg_out_dat_reg(s, cond, ARITH_ORR,
+                        rd, TCG_REG_TMP, rn, SHIFT_IMM_LSR(8));
+    }
+}
+
+/* swap the two low bytes assuming that the two high input bytes and the
+   two high output bit can hold any value. */
+static inline void tcg_out_bswap16st(TCGContext *s, int cond, int rd, int rn)
+{
+    if (use_armv6_instructions) {
+        /* rev16 */
+        tcg_out32(s, 0x06bf0fb0 | (cond << 28) | (rd << 12) | rn);
+    } else {
+        tcg_out_dat_reg(s, cond, ARITH_MOV,
+                        TCG_REG_TMP, 0, rn, SHIFT_IMM_LSR(8));
+        tcg_out_dat_imm(s, cond, ARITH_AND, TCG_REG_TMP, TCG_REG_TMP, 0xff);
+        tcg_out_dat_reg(s, cond, ARITH_ORR,
+                        rd, TCG_REG_TMP, rn, SHIFT_IMM_LSL(8));
+    }
+}
+
+static inline void tcg_out_bswap32(TCGContext *s, int cond, int rd, int rn)
+{
+    if (use_armv6_instructions) {
+        /* rev */
+        tcg_out32(s, 0x06bf0f30 | (cond << 28) | (rd << 12) | rn);
+    } else {
+        tcg_out_dat_reg(s, cond, ARITH_EOR,
+                        TCG_REG_TMP, rn, rn, SHIFT_IMM_ROR(16));
+        tcg_out_dat_imm(s, cond, ARITH_BIC,
+                        TCG_REG_TMP, TCG_REG_TMP, 0xff | 0x800);
+        tcg_out_dat_reg(s, cond, ARITH_MOV,
+                        rd, 0, rn, SHIFT_IMM_ROR(8));
+        tcg_out_dat_reg(s, cond, ARITH_EOR,
+                        rd, rd, TCG_REG_TMP, SHIFT_IMM_LSR(8));
+    }
+}
+
+bool tcg_target_deposit_valid(int ofs, int len)
+{
+    /* ??? Without bfi, we could improve over generic code by combining
+       the right-shift from a non-zero ofs with the orr.  We do run into
+       problems when rd == rs, and the mask generated from ofs+len doesn't
+       fit into an immediate.  We would have to be careful not to pessimize
+       wrt the optimizations performed on the expanded code.  */
+    return use_armv7_instructions;
+}
+
+static inline void tcg_out_deposit(TCGContext *s, int cond, TCGReg rd,
+                                   TCGArg a1, int ofs, int len, bool const_a1)
+{
+    if (const_a1) {
+        /* bfi becomes bfc with rn == 15.  */
+        a1 = 15;
+    }
+    /* bfi/bfc */
+    tcg_out32(s, 0x07c00010 | (cond << 28) | (rd << 12) | a1
+              | (ofs << 7) | ((ofs + len - 1) << 16));
+}
+
+/* Note that this routine is used for both LDR and LDRH formats, so we do
+   not wish to include an immediate shift at this point.  */
+static void tcg_out_memop_r(TCGContext *s, int cond, ARMInsn opc, TCGReg rt,
+                            TCGReg rn, TCGReg rm, bool u, bool p, bool w)
+{
+    tcg_out32(s, (cond << 28) | opc | (u << 23) | (p << 24)
+              | (w << 21) | (rn << 16) | (rt << 12) | rm);
+}
+
+static void tcg_out_memop_8(TCGContext *s, int cond, ARMInsn opc, TCGReg rt,
+                            TCGReg rn, int imm8, bool p, bool w)
+{
+    bool u = 1;
+    if (imm8 < 0) {
+        imm8 = -imm8;
+        u = 0;
+    }
+    tcg_out32(s, (cond << 28) | opc | (u << 23) | (p << 24) | (w << 21) |
+              (rn << 16) | (rt << 12) | ((imm8 & 0xf0) << 4) | (imm8 & 0xf));
+}
+
+static void tcg_out_memop_12(TCGContext *s, int cond, ARMInsn opc, TCGReg rt,
+                             TCGReg rn, int imm12, bool p, bool w)
+{
+    bool u = 1;
+    if (imm12 < 0) {
+        imm12 = -imm12;
+        u = 0;
+    }
+    tcg_out32(s, (cond << 28) | opc | (u << 23) | (p << 24) | (w << 21) |
+              (rn << 16) | (rt << 12) | imm12);
+}
+
+static inline void tcg_out_ld32_12(TCGContext *s, int cond, TCGReg rt,
+                                   TCGReg rn, int imm12)
+{
+    tcg_out_memop_12(s, cond, INSN_LDR_IMM, rt, rn, imm12, 1, 0);
+}
+
+static inline void tcg_out_st32_12(TCGContext *s, int cond, TCGReg rt,
+                                   TCGReg rn, int imm12)
+{
+    tcg_out_memop_12(s, cond, INSN_STR_IMM, rt, rn, imm12, 1, 0);
+}
+
+static inline void tcg_out_ld32_r(TCGContext *s, int cond, TCGReg rt,
+                                  TCGReg rn, TCGReg rm)
+{
+    tcg_out_memop_r(s, cond, INSN_LDR_REG, rt, rn, rm, 1, 1, 0);
+}
+
+static inline void tcg_out_st32_r(TCGContext *s, int cond, TCGReg rt,
+                                  TCGReg rn, TCGReg rm)
+{
+    tcg_out_memop_r(s, cond, INSN_STR_REG, rt, rn, rm, 1, 1, 0);
+}
+
+static inline void tcg_out_ldrd_8(TCGContext *s, int cond, TCGReg rt,
+                                   TCGReg rn, int imm8)
+{
+    tcg_out_memop_8(s, cond, INSN_LDRD_IMM, rt, rn, imm8, 1, 0);
+}
+
+static inline void tcg_out_ldrd_r(TCGContext *s, int cond, TCGReg rt,
+                                  TCGReg rn, TCGReg rm)
+{
+    tcg_out_memop_r(s, cond, INSN_LDRD_REG, rt, rn, rm, 1, 1, 0);
+}
+
+static inline void tcg_out_strd_8(TCGContext *s, int cond, TCGReg rt,
+                                   TCGReg rn, int imm8)
+{
+    tcg_out_memop_8(s, cond, INSN_STRD_IMM, rt, rn, imm8, 1, 0);
+}
+
+static inline void tcg_out_strd_r(TCGContext *s, int cond, TCGReg rt,
+                                  TCGReg rn, TCGReg rm)
+{
+    tcg_out_memop_r(s, cond, INSN_STRD_REG, rt, rn, rm, 1, 1, 0);
+}
+
+/* Register pre-increment with base writeback.  */
+static inline void tcg_out_ld32_rwb(TCGContext *s, int cond, TCGReg rt,
+                                    TCGReg rn, TCGReg rm)
+{
+    tcg_out_memop_r(s, cond, INSN_LDR_REG, rt, rn, rm, 1, 1, 1);
+}
+
+static inline void tcg_out_st32_rwb(TCGContext *s, int cond, TCGReg rt,
+                                    TCGReg rn, TCGReg rm)
+{
+    tcg_out_memop_r(s, cond, INSN_STR_REG, rt, rn, rm, 1, 1, 1);
+}
+
+static inline void tcg_out_ld16u_8(TCGContext *s, int cond, TCGReg rt,
+                                   TCGReg rn, int imm8)
+{
+    tcg_out_memop_8(s, cond, INSN_LDRH_IMM, rt, rn, imm8, 1, 0);
+}
+
+static inline void tcg_out_st16_8(TCGContext *s, int cond, TCGReg rt,
+                                  TCGReg rn, int imm8)
+{
+    tcg_out_memop_8(s, cond, INSN_STRH_IMM, rt, rn, imm8, 1, 0);
+}
+
+static inline void tcg_out_ld16u_r(TCGContext *s, int cond, TCGReg rt,
+                                   TCGReg rn, TCGReg rm)
+{
+    tcg_out_memop_r(s, cond, INSN_LDRH_REG, rt, rn, rm, 1, 1, 0);
+}
+
+static inline void tcg_out_st16_r(TCGContext *s, int cond, TCGReg rt,
+                                  TCGReg rn, TCGReg rm)
+{
+    tcg_out_memop_r(s, cond, INSN_STRH_REG, rt, rn, rm, 1, 1, 0);
+}
+
+static inline void tcg_out_ld16s_8(TCGContext *s, int cond, TCGReg rt,
+                                   TCGReg rn, int imm8)
+{
+    tcg_out_memop_8(s, cond, INSN_LDRSH_IMM, rt, rn, imm8, 1, 0);
+}
+
+static inline void tcg_out_ld16s_r(TCGContext *s, int cond, TCGReg rt,
+                                   TCGReg rn, TCGReg rm)
+{
+    tcg_out_memop_r(s, cond, INSN_LDRSH_REG, rt, rn, rm, 1, 1, 0);
+}
+
+static inline void tcg_out_ld8_12(TCGContext *s, int cond, TCGReg rt,
+                                  TCGReg rn, int imm12)
+{
+    tcg_out_memop_12(s, cond, INSN_LDRB_IMM, rt, rn, imm12, 1, 0);
+}
+
+static inline void tcg_out_st8_12(TCGContext *s, int cond, TCGReg rt,
+                                  TCGReg rn, int imm12)
+{
+    tcg_out_memop_12(s, cond, INSN_STRB_IMM, rt, rn, imm12, 1, 0);
+}
+
+static inline void tcg_out_ld8_r(TCGContext *s, int cond, TCGReg rt,
+                                 TCGReg rn, TCGReg rm)
+{
+    tcg_out_memop_r(s, cond, INSN_LDRB_REG, rt, rn, rm, 1, 1, 0);
+}
+
+static inline void tcg_out_st8_r(TCGContext *s, int cond, TCGReg rt,
+                                 TCGReg rn, TCGReg rm)
+{
+    tcg_out_memop_r(s, cond, INSN_STRB_REG, rt, rn, rm, 1, 1, 0);
+}
+
+static inline void tcg_out_ld8s_8(TCGContext *s, int cond, TCGReg rt,
+                                  TCGReg rn, int imm8)
+{
+    tcg_out_memop_8(s, cond, INSN_LDRSB_IMM, rt, rn, imm8, 1, 0);
+}
+
+static inline void tcg_out_ld8s_r(TCGContext *s, int cond, TCGReg rt,
+                                  TCGReg rn, TCGReg rm)
+{
+    tcg_out_memop_r(s, cond, INSN_LDRSB_REG, rt, rn, rm, 1, 1, 0);
+}
+
+static inline void tcg_out_ld32u(TCGContext *s, int cond,
+                int rd, int rn, int32_t offset)
+{
+    if (offset > 0xfff || offset < -0xfff) {
+        tcg_out_movi32(s, cond, TCG_REG_TMP, offset);
+        tcg_out_ld32_r(s, cond, rd, rn, TCG_REG_TMP);
+    } else
+        tcg_out_ld32_12(s, cond, rd, rn, offset);
+}
+
+static inline void tcg_out_st32(TCGContext *s, int cond,
+                int rd, int rn, int32_t offset)
+{
+    if (offset > 0xfff || offset < -0xfff) {
+        tcg_out_movi32(s, cond, TCG_REG_TMP, offset);
+        tcg_out_st32_r(s, cond, rd, rn, TCG_REG_TMP);
+    } else
+        tcg_out_st32_12(s, cond, rd, rn, offset);
+}
+
+static inline void tcg_out_ld16u(TCGContext *s, int cond,
+                int rd, int rn, int32_t offset)
+{
+    if (offset > 0xff || offset < -0xff) {
+        tcg_out_movi32(s, cond, TCG_REG_TMP, offset);
+        tcg_out_ld16u_r(s, cond, rd, rn, TCG_REG_TMP);
+    } else
+        tcg_out_ld16u_8(s, cond, rd, rn, offset);
+}
+
+static inline void tcg_out_ld16s(TCGContext *s, int cond,
+                int rd, int rn, int32_t offset)
+{
+    if (offset > 0xff || offset < -0xff) {
+        tcg_out_movi32(s, cond, TCG_REG_TMP, offset);
+        tcg_out_ld16s_r(s, cond, rd, rn, TCG_REG_TMP);
+    } else
+        tcg_out_ld16s_8(s, cond, rd, rn, offset);
+}
+
+static inline void tcg_out_st16(TCGContext *s, int cond,
+                int rd, int rn, int32_t offset)
+{
+    if (offset > 0xff || offset < -0xff) {
+        tcg_out_movi32(s, cond, TCG_REG_TMP, offset);
+        tcg_out_st16_r(s, cond, rd, rn, TCG_REG_TMP);
+    } else
+        tcg_out_st16_8(s, cond, rd, rn, offset);
+}
+
+static inline void tcg_out_ld8u(TCGContext *s, int cond,
+                int rd, int rn, int32_t offset)
+{
+    if (offset > 0xfff || offset < -0xfff) {
+        tcg_out_movi32(s, cond, TCG_REG_TMP, offset);
+        tcg_out_ld8_r(s, cond, rd, rn, TCG_REG_TMP);
+    } else
+        tcg_out_ld8_12(s, cond, rd, rn, offset);
+}
+
+static inline void tcg_out_ld8s(TCGContext *s, int cond,
+                int rd, int rn, int32_t offset)
+{
+    if (offset > 0xff || offset < -0xff) {
+        tcg_out_movi32(s, cond, TCG_REG_TMP, offset);
+        tcg_out_ld8s_r(s, cond, rd, rn, TCG_REG_TMP);
+    } else
+        tcg_out_ld8s_8(s, cond, rd, rn, offset);
+}
+
+static inline void tcg_out_st8(TCGContext *s, int cond,
+                int rd, int rn, int32_t offset)
+{
+    if (offset > 0xfff || offset < -0xfff) {
+        tcg_out_movi32(s, cond, TCG_REG_TMP, offset);
+        tcg_out_st8_r(s, cond, rd, rn, TCG_REG_TMP);
+    } else
+        tcg_out_st8_12(s, cond, rd, rn, offset);
+}
+
+/* The _goto case is normally between TBs within the same code buffer, and
+ * with the code buffer limited to 16MB we wouldn't need the long case.
+ * But we also use it for the tail-call to the qemu_ld/st helpers, which does.
+ */
+static inline void tcg_out_goto(TCGContext *s, int cond, tcg_insn_unit *addr)
+{
+    intptr_t addri = (intptr_t)addr;
+    ptrdiff_t disp = tcg_pcrel_diff(s, addr);
+
+    if ((addri & 1) == 0 && disp - 8 < 0x01fffffd && disp - 8 > -0x01fffffd) {
+        tcg_out_b(s, cond, disp);
+        return;
+    }
+
+    tcg_out_movi32(s, cond, TCG_REG_TMP, addri);
+    if (use_armv5t_instructions) {
+        tcg_out_bx(s, cond, TCG_REG_TMP);
+    } else {
+        if (addri & 1) {
+            tcg_abort();
+        }
+        tcg_out_mov_reg(s, cond, TCG_REG_PC, TCG_REG_TMP);
+    }
+}
+
+/* The call case is mostly used for helpers - so it's not unreasonable
+ * for them to be beyond branch range */
+static void tcg_out_call(TCGContext *s, tcg_insn_unit *addr)
+{
+    intptr_t addri = (intptr_t)addr;
+    ptrdiff_t disp = tcg_pcrel_diff(s, addr);
+
+    if (disp - 8 < 0x02000000 && disp - 8 >= -0x02000000) {
+        if (addri & 1) {
+            /* Use BLX if the target is in Thumb mode */
+            if (!use_armv5t_instructions) {
+                tcg_abort();
+            }
+            tcg_out_blx_imm(s, disp);
+        } else {
+            tcg_out_bl(s, COND_AL, disp);
+        }
+    } else if (use_armv7_instructions) {
+        tcg_out_movi32(s, COND_AL, TCG_REG_TMP, addri);
+        tcg_out_blx(s, COND_AL, TCG_REG_TMP);
+    } else {
+        tcg_out_dat_imm(s, COND_AL, ARITH_ADD, TCG_REG_R14, TCG_REG_PC, 4);
+        tcg_out_ld32_12(s, COND_AL, TCG_REG_PC, TCG_REG_PC, -4);
+        tcg_out32(s, addri);
+    }
+}
+
+static inline void tcg_out_goto_label(TCGContext *s, int cond, TCGLabel *l)
+{
+    if (l->has_value) {
+        tcg_out_goto(s, cond, l->u.value_ptr);
+    } else {
+        tcg_out_reloc(s, s->code_ptr, R_ARM_PC24, l, 0);
+        tcg_out_b_noaddr(s, cond);
+    }
+}
+
+#ifdef CONFIG_SOFTMMU
+/* helper signature: helper_ret_ld_mmu(CPUState *env, target_ulong addr,
+ *                                     int mmu_idx, uintptr_t ra)
+ */
+static void * const qemu_ld_helpers[16] = {
+    [MO_UB]   = helper_ret_ldub_mmu,
+    [MO_SB]   = helper_ret_ldsb_mmu,
+
+    [MO_LEUW] = helper_le_lduw_mmu,
+    [MO_LEUL] = helper_le_ldul_mmu,
+    [MO_LEQ]  = helper_le_ldq_mmu,
+    [MO_LESW] = helper_le_ldsw_mmu,
+    [MO_LESL] = helper_le_ldul_mmu,
+
+    [MO_BEUW] = helper_be_lduw_mmu,
+    [MO_BEUL] = helper_be_ldul_mmu,
+    [MO_BEQ]  = helper_be_ldq_mmu,
+    [MO_BESW] = helper_be_ldsw_mmu,
+    [MO_BESL] = helper_be_ldul_mmu,
+};
+
+/* helper signature: helper_ret_st_mmu(CPUState *env, target_ulong addr,
+ *                                     uintxx_t val, int mmu_idx, uintptr_t ra)
+ */
+static void * const qemu_st_helpers[16] = {
+    [MO_UB]   = helper_ret_stb_mmu,
+    [MO_LEUW] = helper_le_stw_mmu,
+    [MO_LEUL] = helper_le_stl_mmu,
+    [MO_LEQ]  = helper_le_stq_mmu,
+    [MO_BEUW] = helper_be_stw_mmu,
+    [MO_BEUL] = helper_be_stl_mmu,
+    [MO_BEQ]  = helper_be_stq_mmu,
+};
+
+/* Helper routines for marshalling helper function arguments into
+ * the correct registers and stack.
+ * argreg is where we want to put this argument, arg is the argument itself.
+ * Return value is the updated argreg ready for the next call.
+ * Note that argreg 0..3 is real registers, 4+ on stack.
+ *
+ * We provide routines for arguments which are: immediate, 32 bit
+ * value in register, 16 and 8 bit values in register (which must be zero
+ * extended before use) and 64 bit value in a lo:hi register pair.
+ */
+#define DEFINE_TCG_OUT_ARG(NAME, ARGTYPE, MOV_ARG, EXT_ARG)                \
+static TCGReg NAME(TCGContext *s, TCGReg argreg, ARGTYPE arg)              \
+{                                                                          \
+    if (argreg < 4) {                                                      \
+        MOV_ARG(s, COND_AL, argreg, arg);                                  \
+    } else {                                                               \
+        int ofs = (argreg - 4) * 4;                                        \
+        EXT_ARG;                                                           \
+        assert(ofs + 4 <= TCG_STATIC_CALL_ARGS_SIZE);                      \
+        tcg_out_st32_12(s, COND_AL, arg, TCG_REG_CALL_STACK, ofs);         \
+    }                                                                      \
+    return argreg + 1;                                                     \
+}
+
+DEFINE_TCG_OUT_ARG(tcg_out_arg_imm32, uint32_t, tcg_out_movi32,
+    (tcg_out_movi32(s, COND_AL, TCG_REG_TMP, arg), arg = TCG_REG_TMP))
+DEFINE_TCG_OUT_ARG(tcg_out_arg_reg8, TCGReg, tcg_out_ext8u,
+    (tcg_out_ext8u(s, COND_AL, TCG_REG_TMP, arg), arg = TCG_REG_TMP))
+DEFINE_TCG_OUT_ARG(tcg_out_arg_reg16, TCGReg, tcg_out_ext16u,
+    (tcg_out_ext16u(s, COND_AL, TCG_REG_TMP, arg), arg = TCG_REG_TMP))
+DEFINE_TCG_OUT_ARG(tcg_out_arg_reg32, TCGReg, tcg_out_mov_reg, )
+
+static TCGReg tcg_out_arg_reg64(TCGContext *s, TCGReg argreg,
+                                TCGReg arglo, TCGReg arghi)
+{
+    /* 64 bit arguments must go in even/odd register pairs
+     * and in 8-aligned stack slots.
+     */
+    if (argreg & 1) {
+        argreg++;
+    }
+    if (use_armv6_instructions && argreg >= 4
+        && (arglo & 1) == 0 && arghi == arglo + 1) {
+        tcg_out_strd_8(s, COND_AL, arglo,
+                       TCG_REG_CALL_STACK, (argreg - 4) * 4);
+        return argreg + 2;
+    } else {
+        argreg = tcg_out_arg_reg32(s, argreg, arglo);
+        argreg = tcg_out_arg_reg32(s, argreg, arghi);
+        return argreg;
+    }
+}
+
+#define TLB_SHIFT	(CPU_TLB_ENTRY_BITS + CPU_TLB_BITS)
+
+/* We're expecting to use an 8-bit immediate and to mask.  */
+QEMU_BUILD_BUG_ON(CPU_TLB_BITS > 8);
+
+/* We're expecting to use an 8-bit immediate add + 8-bit ldrd offset.
+   Using the offset of the second entry in the last tlb table ensures
+   that we can index all of the elements of the first entry.  */
+QEMU_BUILD_BUG_ON(offsetof(CPUArchState, tlb_table[NB_MMU_MODES - 1][1])
+                  > 0xffff);
+
+/* Load and compare a TLB entry, leaving the flags set.  Returns the register
+   containing the addend of the tlb entry.  Clobbers R0, R1, R2, TMP.  */
+
+static TCGReg tcg_out_tlb_read(TCGContext *s, TCGReg addrlo, TCGReg addrhi,
+                               TCGMemOp s_bits, int mem_index, bool is_load)
+{
+    TCGReg base = TCG_AREG0;
+    int cmp_off =
+        (is_load
+         ? offsetof(CPUArchState, tlb_table[mem_index][0].addr_read)
+         : offsetof(CPUArchState, tlb_table[mem_index][0].addr_write));
+    int add_off = offsetof(CPUArchState, tlb_table[mem_index][0].addend);
+
+    /* Should generate something like the following:
+     *   shr    tmp, addrlo, #TARGET_PAGE_BITS                    (1)
+     *   add    r2, env, #high
+     *   and    r0, tmp, #(CPU_TLB_SIZE - 1)                      (2)
+     *   add    r2, r2, r0, lsl #CPU_TLB_ENTRY_BITS               (3)
+     *   ldr    r0, [r2, #cmp]                                    (4)
+     *   tst    addrlo, #s_mask
+     *   ldr    r2, [r2, #add]                                    (5)
+     *   cmpeq  r0, tmp, lsl #TARGET_PAGE_BITS
+     */
+    tcg_out_dat_reg(s, COND_AL, ARITH_MOV, TCG_REG_TMP,
+                    0, addrlo, SHIFT_IMM_LSR(TARGET_PAGE_BITS));
+
+    /* We checked that the offset is contained within 16 bits above.  */
+    if (add_off > 0xfff || (use_armv6_instructions && cmp_off > 0xff)) {
+        tcg_out_dat_imm(s, COND_AL, ARITH_ADD, TCG_REG_R2, base,
+                        (24 << 7) | (cmp_off >> 8));
+        base = TCG_REG_R2;
+        add_off -= cmp_off & 0xff00;
+        cmp_off &= 0xff;
+    }
+
+    tcg_out_dat_imm(s, COND_AL, ARITH_AND,
+                    TCG_REG_R0, TCG_REG_TMP, CPU_TLB_SIZE - 1);
+    tcg_out_dat_reg(s, COND_AL, ARITH_ADD, TCG_REG_R2, base,
+                    TCG_REG_R0, SHIFT_IMM_LSL(CPU_TLB_ENTRY_BITS));
+
+    /* Load the tlb comparator.  Use ldrd if needed and available,
+       but due to how the pointer needs setting up, ldm isn't useful.
+       Base arm5 doesn't have ldrd, but armv5te does.  */
+    if (use_armv6_instructions && TARGET_LONG_BITS == 64) {
+        tcg_out_ldrd_8(s, COND_AL, TCG_REG_R0, TCG_REG_R2, cmp_off);
+    } else {
+        tcg_out_ld32_12(s, COND_AL, TCG_REG_R0, TCG_REG_R2, cmp_off);
+        if (TARGET_LONG_BITS == 64) {
+            tcg_out_ld32_12(s, COND_AL, TCG_REG_R1, TCG_REG_R2, cmp_off + 4);
+        }
+    }
+
+    /* Check alignment.  */
+    if (s_bits) {
+        tcg_out_dat_imm(s, COND_AL, ARITH_TST,
+                        0, addrlo, (1 << s_bits) - 1);
+    }
+
+    /* Load the tlb addend.  */
+    tcg_out_ld32_12(s, COND_AL, TCG_REG_R2, TCG_REG_R2, add_off);
+
+    tcg_out_dat_reg(s, (s_bits ? COND_EQ : COND_AL), ARITH_CMP, 0,
+                    TCG_REG_R0, TCG_REG_TMP, SHIFT_IMM_LSL(TARGET_PAGE_BITS));
+
+    if (TARGET_LONG_BITS == 64) {
+        tcg_out_dat_reg(s, COND_EQ, ARITH_CMP, 0,
+                        TCG_REG_R1, addrhi, SHIFT_IMM_LSL(0));
+    }
+
+    return TCG_REG_R2;
+}
+
+/* Record the context of a call to the out of line helper code for the slow
+   path for a load or store, so that we can later generate the correct
+   helper code.  */
+static void add_qemu_ldst_label(TCGContext *s, bool is_ld, TCGMemOpIdx oi,
+                                TCGReg datalo, TCGReg datahi, TCGReg addrlo,
+                                TCGReg addrhi, tcg_insn_unit *raddr,
+                                tcg_insn_unit *label_ptr)
+{
+    TCGLabelQemuLdst *label = new_ldst_label(s);
+
+    label->is_ld = is_ld;
+    label->oi = oi;
+    label->datalo_reg = datalo;
+    label->datahi_reg = datahi;
+    label->addrlo_reg = addrlo;
+    label->addrhi_reg = addrhi;
+    label->raddr = raddr;
+    label->label_ptr[0] = label_ptr;
+}
+
+static void tcg_out_qemu_ld_slow_path(TCGContext *s, TCGLabelQemuLdst *lb)
+{
+    TCGReg argreg, datalo, datahi;
+    TCGMemOpIdx oi = lb->oi;
+    TCGMemOp opc = get_memop(oi);
+    void *func;
+
+    reloc_pc24(lb->label_ptr[0], s->code_ptr);
+
+    argreg = tcg_out_arg_reg32(s, TCG_REG_R0, TCG_AREG0);
+    if (TARGET_LONG_BITS == 64) {
+        argreg = tcg_out_arg_reg64(s, argreg, lb->addrlo_reg, lb->addrhi_reg);
+    } else {
+        argreg = tcg_out_arg_reg32(s, argreg, lb->addrlo_reg);
+    }
+    argreg = tcg_out_arg_imm32(s, argreg, oi);
+    argreg = tcg_out_arg_reg32(s, argreg, TCG_REG_R14);
+
+    /* For armv6 we can use the canonical unsigned helpers and minimize
+       icache usage.  For pre-armv6, use the signed helpers since we do
+       not have a single insn sign-extend.  */
+    if (use_armv6_instructions) {
+        func = qemu_ld_helpers[opc & (MO_BSWAP | MO_SIZE)];
+    } else {
+        func = qemu_ld_helpers[opc & (MO_BSWAP | MO_SSIZE)];
+        if (opc & MO_SIGN) {
+            opc = MO_UL;
+        }
+    }
+    tcg_out_call(s, func);
+
+    datalo = lb->datalo_reg;
+    datahi = lb->datahi_reg;
+    switch (opc & MO_SSIZE) {
+    case MO_SB:
+        tcg_out_ext8s(s, COND_AL, datalo, TCG_REG_R0);
+        break;
+    case MO_SW:
+        tcg_out_ext16s(s, COND_AL, datalo, TCG_REG_R0);
+        break;
+    default:
+        tcg_out_mov_reg(s, COND_AL, datalo, TCG_REG_R0);
+        break;
+    case MO_Q:
+        if (datalo != TCG_REG_R1) {
+            tcg_out_mov_reg(s, COND_AL, datalo, TCG_REG_R0);
+            tcg_out_mov_reg(s, COND_AL, datahi, TCG_REG_R1);
+        } else if (datahi != TCG_REG_R0) {
+            tcg_out_mov_reg(s, COND_AL, datahi, TCG_REG_R1);
+            tcg_out_mov_reg(s, COND_AL, datalo, TCG_REG_R0);
+        } else {
+            tcg_out_mov_reg(s, COND_AL, TCG_REG_TMP, TCG_REG_R0);
+            tcg_out_mov_reg(s, COND_AL, datahi, TCG_REG_R1);
+            tcg_out_mov_reg(s, COND_AL, datalo, TCG_REG_TMP);
+        }
+        break;
+    }
+
+    tcg_out_goto(s, COND_AL, lb->raddr);
+}
+
+static void tcg_out_qemu_st_slow_path(TCGContext *s, TCGLabelQemuLdst *lb)
+{
+    TCGReg argreg, datalo, datahi;
+    TCGMemOpIdx oi = lb->oi;
+    TCGMemOp opc = get_memop(oi);
+
+    reloc_pc24(lb->label_ptr[0], s->code_ptr);
+
+    argreg = TCG_REG_R0;
+    argreg = tcg_out_arg_reg32(s, argreg, TCG_AREG0);
+    if (TARGET_LONG_BITS == 64) {
+        argreg = tcg_out_arg_reg64(s, argreg, lb->addrlo_reg, lb->addrhi_reg);
+    } else {
+        argreg = tcg_out_arg_reg32(s, argreg, lb->addrlo_reg);
+    }
+
+    datalo = lb->datalo_reg;
+    datahi = lb->datahi_reg;
+    switch (opc & MO_SIZE) {
+    case MO_8:
+        argreg = tcg_out_arg_reg8(s, argreg, datalo);
+        break;
+    case MO_16:
+        argreg = tcg_out_arg_reg16(s, argreg, datalo);
+        break;
+    case MO_32:
+    default:
+        argreg = tcg_out_arg_reg32(s, argreg, datalo);
+        break;
+    case MO_64:
+        argreg = tcg_out_arg_reg64(s, argreg, datalo, datahi);
+        break;
+    }
+
+    argreg = tcg_out_arg_imm32(s, argreg, oi);
+    argreg = tcg_out_arg_reg32(s, argreg, TCG_REG_R14);
+
+    /* Tail-call to the helper, which will return to the fast path.  */
+    tcg_out_goto(s, COND_AL, qemu_st_helpers[opc & (MO_BSWAP | MO_SIZE)]);
+}
+#endif /* SOFTMMU */
+
+static inline void tcg_out_qemu_ld_index(TCGContext *s, TCGMemOp opc,
+                                         TCGReg datalo, TCGReg datahi,
+                                         TCGReg addrlo, TCGReg addend)
+{
+    TCGMemOp bswap = opc & MO_BSWAP;
+
+    switch (opc & MO_SSIZE) {
+    case MO_UB:
+        tcg_out_ld8_r(s, COND_AL, datalo, addrlo, addend);
+        break;
+    case MO_SB:
+        tcg_out_ld8s_r(s, COND_AL, datalo, addrlo, addend);
+        break;
+    case MO_UW:
+        tcg_out_ld16u_r(s, COND_AL, datalo, addrlo, addend);
+        if (bswap) {
+            tcg_out_bswap16(s, COND_AL, datalo, datalo);
+        }
+        break;
+    case MO_SW:
+        if (bswap) {
+            tcg_out_ld16u_r(s, COND_AL, datalo, addrlo, addend);
+            tcg_out_bswap16s(s, COND_AL, datalo, datalo);
+        } else {
+            tcg_out_ld16s_r(s, COND_AL, datalo, addrlo, addend);
+        }
+        break;
+    case MO_UL:
+    default:
+        tcg_out_ld32_r(s, COND_AL, datalo, addrlo, addend);
+        if (bswap) {
+            tcg_out_bswap32(s, COND_AL, datalo, datalo);
+        }
+        break;
+    case MO_Q:
+        {
+            TCGReg dl = (bswap ? datahi : datalo);
+            TCGReg dh = (bswap ? datalo : datahi);
+
+            /* Avoid ldrd for user-only emulation, to handle unaligned.  */
+            if (USING_SOFTMMU && use_armv6_instructions
+                && (dl & 1) == 0 && dh == dl + 1) {
+                tcg_out_ldrd_r(s, COND_AL, dl, addrlo, addend);
+            } else if (dl != addend) {
+                tcg_out_ld32_rwb(s, COND_AL, dl, addend, addrlo);
+                tcg_out_ld32_12(s, COND_AL, dh, addend, 4);
+            } else {
+                tcg_out_dat_reg(s, COND_AL, ARITH_ADD, TCG_REG_TMP,
+                                addend, addrlo, SHIFT_IMM_LSL(0));
+                tcg_out_ld32_12(s, COND_AL, dl, TCG_REG_TMP, 0);
+                tcg_out_ld32_12(s, COND_AL, dh, TCG_REG_TMP, 4);
+            }
+            if (bswap) {
+                tcg_out_bswap32(s, COND_AL, dl, dl);
+                tcg_out_bswap32(s, COND_AL, dh, dh);
+            }
+        }
+        break;
+    }
+}
+
+static inline void tcg_out_qemu_ld_direct(TCGContext *s, TCGMemOp opc,
+                                          TCGReg datalo, TCGReg datahi,
+                                          TCGReg addrlo)
+{
+    TCGMemOp bswap = opc & MO_BSWAP;
+
+    switch (opc & MO_SSIZE) {
+    case MO_UB:
+        tcg_out_ld8_12(s, COND_AL, datalo, addrlo, 0);
+        break;
+    case MO_SB:
+        tcg_out_ld8s_8(s, COND_AL, datalo, addrlo, 0);
+        break;
+    case MO_UW:
+        tcg_out_ld16u_8(s, COND_AL, datalo, addrlo, 0);
+        if (bswap) {
+            tcg_out_bswap16(s, COND_AL, datalo, datalo);
+        }
+        break;
+    case MO_SW:
+        if (bswap) {
+            tcg_out_ld16u_8(s, COND_AL, datalo, addrlo, 0);
+            tcg_out_bswap16s(s, COND_AL, datalo, datalo);
+        } else {
+            tcg_out_ld16s_8(s, COND_AL, datalo, addrlo, 0);
+        }
+        break;
+    case MO_UL:
+    default:
+        tcg_out_ld32_12(s, COND_AL, datalo, addrlo, 0);
+        if (bswap) {
+            tcg_out_bswap32(s, COND_AL, datalo, datalo);
+        }
+        break;
+    case MO_Q:
+        {
+            TCGReg dl = (bswap ? datahi : datalo);
+            TCGReg dh = (bswap ? datalo : datahi);
+
+            /* Avoid ldrd for user-only emulation, to handle unaligned.  */
+            if (USING_SOFTMMU && use_armv6_instructions
+                && (dl & 1) == 0 && dh == dl + 1) {
+                tcg_out_ldrd_8(s, COND_AL, dl, addrlo, 0);
+            } else if (dl == addrlo) {
+                tcg_out_ld32_12(s, COND_AL, dh, addrlo, bswap ? 0 : 4);
+                tcg_out_ld32_12(s, COND_AL, dl, addrlo, bswap ? 4 : 0);
+            } else {
+                tcg_out_ld32_12(s, COND_AL, dl, addrlo, bswap ? 4 : 0);
+                tcg_out_ld32_12(s, COND_AL, dh, addrlo, bswap ? 0 : 4);
+            }
+            if (bswap) {
+                tcg_out_bswap32(s, COND_AL, dl, dl);
+                tcg_out_bswap32(s, COND_AL, dh, dh);
+            }
+        }
+        break;
+    }
+}
+
+static void tcg_out_qemu_ld(TCGContext *s, const TCGArg *args, bool is64)
+{
+    TCGReg addrlo, datalo, datahi, addrhi __attribute__((unused));
+    TCGMemOpIdx oi;
+    TCGMemOp opc;
+#ifdef CONFIG_SOFTMMU
+    int mem_index;
+    TCGReg addend;
+    tcg_insn_unit *label_ptr;
+#endif
+
+    datalo = *args++;
+    datahi = (is64 ? *args++ : 0);
+    addrlo = *args++;
+    addrhi = (TARGET_LONG_BITS == 64 ? *args++ : 0);
+    oi = *args++;
+    opc = get_memop(oi);
+
+#ifdef CONFIG_SOFTMMU
+    mem_index = get_mmuidx(oi);
+    addend = tcg_out_tlb_read(s, addrlo, addrhi, opc & MO_SIZE, mem_index, 1);
+
+    /* This a conditional BL only to load a pointer within this opcode into LR
+       for the slow path.  We will not be using the value for a tail call.  */
+    label_ptr = s->code_ptr;
+    tcg_out_bl_noaddr(s, COND_NE);
+
+    tcg_out_qemu_ld_index(s, opc, datalo, datahi, addrlo, addend);
+
+    add_qemu_ldst_label(s, true, oi, datalo, datahi, addrlo, addrhi,
+                        s->code_ptr, label_ptr);
+#else /* !CONFIG_SOFTMMU */
+    if (GUEST_BASE) {
+        tcg_out_movi(s, TCG_TYPE_PTR, TCG_REG_TMP, GUEST_BASE);
+        tcg_out_qemu_ld_index(s, opc, datalo, datahi, addrlo, TCG_REG_TMP);
+    } else {
+        tcg_out_qemu_ld_direct(s, opc, datalo, datahi, addrlo);
+    }
+#endif
+}
+
+static inline void tcg_out_qemu_st_index(TCGContext *s, int cond, TCGMemOp opc,
+                                         TCGReg datalo, TCGReg datahi,
+                                         TCGReg addrlo, TCGReg addend)
+{
+    TCGMemOp bswap = opc & MO_BSWAP;
+
+    switch (opc & MO_SIZE) {
+    case MO_8:
+        tcg_out_st8_r(s, cond, datalo, addrlo, addend);
+        break;
+    case MO_16:
+        if (bswap) {
+            tcg_out_bswap16st(s, cond, TCG_REG_R0, datalo);
+            tcg_out_st16_r(s, cond, TCG_REG_R0, addrlo, addend);
+        } else {
+            tcg_out_st16_r(s, cond, datalo, addrlo, addend);
+        }
+        break;
+    case MO_32:
+    default:
+        if (bswap) {
+            tcg_out_bswap32(s, cond, TCG_REG_R0, datalo);
+            tcg_out_st32_r(s, cond, TCG_REG_R0, addrlo, addend);
+        } else {
+            tcg_out_st32_r(s, cond, datalo, addrlo, addend);
+        }
+        break;
+    case MO_64:
+        /* Avoid strd for user-only emulation, to handle unaligned.  */
+        if (bswap) {
+            tcg_out_bswap32(s, cond, TCG_REG_R0, datahi);
+            tcg_out_st32_rwb(s, cond, TCG_REG_R0, addend, addrlo);
+            tcg_out_bswap32(s, cond, TCG_REG_R0, datalo);
+            tcg_out_st32_12(s, cond, TCG_REG_R0, addend, 4);
+        } else if (USING_SOFTMMU && use_armv6_instructions
+                   && (datalo & 1) == 0 && datahi == datalo + 1) {
+            tcg_out_strd_r(s, cond, datalo, addrlo, addend);
+        } else {
+            tcg_out_st32_rwb(s, cond, datalo, addend, addrlo);
+            tcg_out_st32_12(s, cond, datahi, addend, 4);
+        }
+        break;
+    }
+}
+
+static inline void tcg_out_qemu_st_direct(TCGContext *s, TCGMemOp opc,
+                                          TCGReg datalo, TCGReg datahi,
+                                          TCGReg addrlo)
+{
+    TCGMemOp bswap = opc & MO_BSWAP;
+
+    switch (opc & MO_SIZE) {
+    case MO_8:
+        tcg_out_st8_12(s, COND_AL, datalo, addrlo, 0);
+        break;
+    case MO_16:
+        if (bswap) {
+            tcg_out_bswap16st(s, COND_AL, TCG_REG_R0, datalo);
+            tcg_out_st16_8(s, COND_AL, TCG_REG_R0, addrlo, 0);
+        } else {
+            tcg_out_st16_8(s, COND_AL, datalo, addrlo, 0);
+        }
+        break;
+    case MO_32:
+    default:
+        if (bswap) {
+            tcg_out_bswap32(s, COND_AL, TCG_REG_R0, datalo);
+            tcg_out_st32_12(s, COND_AL, TCG_REG_R0, addrlo, 0);
+        } else {
+            tcg_out_st32_12(s, COND_AL, datalo, addrlo, 0);
+        }
+        break;
+    case MO_64:
+        /* Avoid strd for user-only emulation, to handle unaligned.  */
+        if (bswap) {
+            tcg_out_bswap32(s, COND_AL, TCG_REG_R0, datahi);
+            tcg_out_st32_12(s, COND_AL, TCG_REG_R0, addrlo, 0);
+            tcg_out_bswap32(s, COND_AL, TCG_REG_R0, datalo);
+            tcg_out_st32_12(s, COND_AL, TCG_REG_R0, addrlo, 4);
+        } else if (USING_SOFTMMU && use_armv6_instructions
+                   && (datalo & 1) == 0 && datahi == datalo + 1) {
+            tcg_out_strd_8(s, COND_AL, datalo, addrlo, 0);
+        } else {
+            tcg_out_st32_12(s, COND_AL, datalo, addrlo, 0);
+            tcg_out_st32_12(s, COND_AL, datahi, addrlo, 4);
+        }
+        break;
+    }
+}
+
+static void tcg_out_qemu_st(TCGContext *s, const TCGArg *args, bool is64)
+{
+    TCGReg addrlo, datalo, datahi, addrhi __attribute__((unused));
+    TCGMemOpIdx oi;
+    TCGMemOp opc;
+#ifdef CONFIG_SOFTMMU
+    int mem_index;
+    TCGReg addend;
+    tcg_insn_unit *label_ptr;
+#endif
+
+    datalo = *args++;
+    datahi = (is64 ? *args++ : 0);
+    addrlo = *args++;
+    addrhi = (TARGET_LONG_BITS == 64 ? *args++ : 0);
+    oi = *args++;
+    opc = get_memop(oi);
+
+#ifdef CONFIG_SOFTMMU
+    mem_index = get_mmuidx(oi);
+    addend = tcg_out_tlb_read(s, addrlo, addrhi, opc & MO_SIZE, mem_index, 0);
+
+    tcg_out_qemu_st_index(s, COND_EQ, opc, datalo, datahi, addrlo, addend);
+
+    /* The conditional call must come last, as we're going to return here.  */
+    label_ptr = s->code_ptr;
+    tcg_out_bl_noaddr(s, COND_NE);
+
+    add_qemu_ldst_label(s, false, oi, datalo, datahi, addrlo, addrhi,
+                        s->code_ptr, label_ptr);
+#else /* !CONFIG_SOFTMMU */
+    if (GUEST_BASE) {
+        tcg_out_movi(s, TCG_TYPE_PTR, TCG_REG_TMP, GUEST_BASE);
+        tcg_out_qemu_st_index(s, COND_AL, opc, datalo,
+                              datahi, addrlo, TCG_REG_TMP);
+    } else {
+        tcg_out_qemu_st_direct(s, opc, datalo, datahi, addrlo);
+    }
+#endif
+}
+
+static tcg_insn_unit *tb_ret_addr;
+
+static inline void tcg_out_op(TCGContext *s, TCGOpcode opc,
+                const TCGArg *args, const int *const_args)
+{
+    TCGArg a0, a1, a2, a3, a4, a5;
+    int c;
+
+    switch (opc) {
+    case INDEX_op_exit_tb:
+        tcg_out_movi32(s, COND_AL, TCG_REG_R0, args[0]);
+        tcg_out_goto(s, COND_AL, tb_ret_addr);
+        break;
+    case INDEX_op_goto_tb:
+        if (s->tb_jmp_offset) {
+            /* Direct jump method */
+            s->tb_jmp_offset[args[0]] = tcg_current_code_size(s);
+            tcg_out_b_noaddr(s, COND_AL);
+        } else {
+            /* Indirect jump method */
+            intptr_t ptr = (intptr_t)(s->tb_next + args[0]);
+            tcg_out_movi32(s, COND_AL, TCG_REG_R0, ptr & ~0xfff);
+            tcg_out_ld32_12(s, COND_AL, TCG_REG_PC, TCG_REG_R0, ptr & 0xfff);
+        }
+        s->tb_next_offset[args[0]] = tcg_current_code_size(s);
+        break;
+    case INDEX_op_br:
+        tcg_out_goto_label(s, COND_AL, arg_label(args[0]));
+        break;
+
+    case INDEX_op_ld8u_i32:
+        tcg_out_ld8u(s, COND_AL, args[0], args[1], args[2]);
+        break;
+    case INDEX_op_ld8s_i32:
+        tcg_out_ld8s(s, COND_AL, args[0], args[1], args[2]);
+        break;
+    case INDEX_op_ld16u_i32:
+        tcg_out_ld16u(s, COND_AL, args[0], args[1], args[2]);
+        break;
+    case INDEX_op_ld16s_i32:
+        tcg_out_ld16s(s, COND_AL, args[0], args[1], args[2]);
+        break;
+    case INDEX_op_ld_i32:
+        tcg_out_ld32u(s, COND_AL, args[0], args[1], args[2]);
+        break;
+    case INDEX_op_st8_i32:
+        tcg_out_st8(s, COND_AL, args[0], args[1], args[2]);
+        break;
+    case INDEX_op_st16_i32:
+        tcg_out_st16(s, COND_AL, args[0], args[1], args[2]);
+        break;
+    case INDEX_op_st_i32:
+        tcg_out_st32(s, COND_AL, args[0], args[1], args[2]);
+        break;
+
+    case INDEX_op_movcond_i32:
+        /* Constraints mean that v2 is always in the same register as dest,
+         * so we only need to do "if condition passed, move v1 to dest".
+         */
+        tcg_out_dat_rIN(s, COND_AL, ARITH_CMP, ARITH_CMN, 0,
+                        args[1], args[2], const_args[2]);
+        tcg_out_dat_rIK(s, tcg_cond_to_arm_cond[args[5]], ARITH_MOV,
+                        ARITH_MVN, args[0], 0, args[3], const_args[3]);
+        break;
+    case INDEX_op_add_i32:
+        tcg_out_dat_rIN(s, COND_AL, ARITH_ADD, ARITH_SUB,
+                        args[0], args[1], args[2], const_args[2]);
+        break;
+    case INDEX_op_sub_i32:
+        if (const_args[1]) {
+            if (const_args[2]) {
+                tcg_out_movi32(s, COND_AL, args[0], args[1] - args[2]);
+            } else {
+                tcg_out_dat_rI(s, COND_AL, ARITH_RSB,
+                               args[0], args[2], args[1], 1);
+            }
+        } else {
+            tcg_out_dat_rIN(s, COND_AL, ARITH_SUB, ARITH_ADD,
+                            args[0], args[1], args[2], const_args[2]);
+        }
+        break;
+    case INDEX_op_and_i32:
+        tcg_out_dat_rIK(s, COND_AL, ARITH_AND, ARITH_BIC,
+                        args[0], args[1], args[2], const_args[2]);
+        break;
+    case INDEX_op_andc_i32:
+        tcg_out_dat_rIK(s, COND_AL, ARITH_BIC, ARITH_AND,
+                        args[0], args[1], args[2], const_args[2]);
+        break;
+    case INDEX_op_or_i32:
+        c = ARITH_ORR;
+        goto gen_arith;
+    case INDEX_op_xor_i32:
+        c = ARITH_EOR;
+        /* Fall through.  */
+    gen_arith:
+        tcg_out_dat_rI(s, COND_AL, c, args[0], args[1], args[2], const_args[2]);
+        break;
+    case INDEX_op_add2_i32:
+        a0 = args[0], a1 = args[1], a2 = args[2];
+        a3 = args[3], a4 = args[4], a5 = args[5];
+        if (a0 == a3 || (a0 == a5 && !const_args[5])) {
+            a0 = TCG_REG_TMP;
+        }
+        tcg_out_dat_rIN(s, COND_AL, ARITH_ADD | TO_CPSR, ARITH_SUB | TO_CPSR,
+                        a0, a2, a4, const_args[4]);
+        tcg_out_dat_rIK(s, COND_AL, ARITH_ADC, ARITH_SBC,
+                        a1, a3, a5, const_args[5]);
+        tcg_out_mov_reg(s, COND_AL, args[0], a0);
+        break;
+    case INDEX_op_sub2_i32:
+        a0 = args[0], a1 = args[1], a2 = args[2];
+        a3 = args[3], a4 = args[4], a5 = args[5];
+        if ((a0 == a3 && !const_args[3]) || (a0 == a5 && !const_args[5])) {
+            a0 = TCG_REG_TMP;
+        }
+        if (const_args[2]) {
+            if (const_args[4]) {
+                tcg_out_movi32(s, COND_AL, a0, a4);
+                a4 = a0;
+            }
+            tcg_out_dat_rI(s, COND_AL, ARITH_RSB | TO_CPSR, a0, a4, a2, 1);
+        } else {
+            tcg_out_dat_rIN(s, COND_AL, ARITH_SUB | TO_CPSR,
+                            ARITH_ADD | TO_CPSR, a0, a2, a4, const_args[4]);
+        }
+        if (const_args[3]) {
+            if (const_args[5]) {
+                tcg_out_movi32(s, COND_AL, a1, a5);
+                a5 = a1;
+            }
+            tcg_out_dat_rI(s, COND_AL, ARITH_RSC, a1, a5, a3, 1);
+        } else {
+            tcg_out_dat_rIK(s, COND_AL, ARITH_SBC, ARITH_ADC,
+                            a1, a3, a5, const_args[5]);
+        }
+        tcg_out_mov_reg(s, COND_AL, args[0], a0);
+        break;
+    case INDEX_op_neg_i32:
+        tcg_out_dat_imm(s, COND_AL, ARITH_RSB, args[0], args[1], 0);
+        break;
+    case INDEX_op_not_i32:
+        tcg_out_dat_reg(s, COND_AL,
+                        ARITH_MVN, args[0], 0, args[1], SHIFT_IMM_LSL(0));
+        break;
+    case INDEX_op_mul_i32:
+        tcg_out_mul32(s, COND_AL, args[0], args[1], args[2]);
+        break;
+    case INDEX_op_mulu2_i32:
+        tcg_out_umull32(s, COND_AL, args[0], args[1], args[2], args[3]);
+        break;
+    case INDEX_op_muls2_i32:
+        tcg_out_smull32(s, COND_AL, args[0], args[1], args[2], args[3]);
+        break;
+    /* XXX: Perhaps args[2] & 0x1f is wrong */
+    case INDEX_op_shl_i32:
+        c = const_args[2] ?
+                SHIFT_IMM_LSL(args[2] & 0x1f) : SHIFT_REG_LSL(args[2]);
+        goto gen_shift32;
+    case INDEX_op_shr_i32:
+        c = const_args[2] ? (args[2] & 0x1f) ? SHIFT_IMM_LSR(args[2] & 0x1f) :
+                SHIFT_IMM_LSL(0) : SHIFT_REG_LSR(args[2]);
+        goto gen_shift32;
+    case INDEX_op_sar_i32:
+        c = const_args[2] ? (args[2] & 0x1f) ? SHIFT_IMM_ASR(args[2] & 0x1f) :
+                SHIFT_IMM_LSL(0) : SHIFT_REG_ASR(args[2]);
+        goto gen_shift32;
+    case INDEX_op_rotr_i32:
+        c = const_args[2] ? (args[2] & 0x1f) ? SHIFT_IMM_ROR(args[2] & 0x1f) :
+                SHIFT_IMM_LSL(0) : SHIFT_REG_ROR(args[2]);
+        /* Fall through.  */
+    gen_shift32:
+        tcg_out_dat_reg(s, COND_AL, ARITH_MOV, args[0], 0, args[1], c);
+        break;
+
+    case INDEX_op_rotl_i32:
+        if (const_args[2]) {
+            tcg_out_dat_reg(s, COND_AL, ARITH_MOV, args[0], 0, args[1],
+                            ((0x20 - args[2]) & 0x1f) ?
+                            SHIFT_IMM_ROR((0x20 - args[2]) & 0x1f) :
+                            SHIFT_IMM_LSL(0));
+        } else {
+            tcg_out_dat_imm(s, COND_AL, ARITH_RSB, TCG_REG_TMP, args[2], 0x20);
+            tcg_out_dat_reg(s, COND_AL, ARITH_MOV, args[0], 0, args[1],
+                            SHIFT_REG_ROR(TCG_REG_TMP));
+        }
+        break;
+
+    case INDEX_op_brcond_i32:
+        tcg_out_dat_rIN(s, COND_AL, ARITH_CMP, ARITH_CMN, 0,
+                       args[0], args[1], const_args[1]);
+        tcg_out_goto_label(s, tcg_cond_to_arm_cond[args[2]],
+                           arg_label(args[3]));
+        break;
+    case INDEX_op_brcond2_i32:
+        /* The resulting conditions are:
+         * TCG_COND_EQ    -->  a0 == a2 && a1 == a3,
+         * TCG_COND_NE    --> (a0 != a2 && a1 == a3) ||  a1 != a3,
+         * TCG_COND_LT(U) --> (a0 <  a2 && a1 == a3) ||  a1 <  a3,
+         * TCG_COND_GE(U) --> (a0 >= a2 && a1 == a3) || (a1 >= a3 && a1 != a3),
+         * TCG_COND_LE(U) --> (a0 <= a2 && a1 == a3) || (a1 <= a3 && a1 != a3),
+         * TCG_COND_GT(U) --> (a0 >  a2 && a1 == a3) ||  a1 >  a3,
+         */
+        tcg_out_dat_rIN(s, COND_AL, ARITH_CMP, ARITH_CMN, 0,
+                        args[1], args[3], const_args[3]);
+        tcg_out_dat_rIN(s, COND_EQ, ARITH_CMP, ARITH_CMN, 0,
+                        args[0], args[2], const_args[2]);
+        tcg_out_goto_label(s, tcg_cond_to_arm_cond[args[4]],
+                           arg_label(args[5]));
+        break;
+    case INDEX_op_setcond_i32:
+        tcg_out_dat_rIN(s, COND_AL, ARITH_CMP, ARITH_CMN, 0,
+                        args[1], args[2], const_args[2]);
+        tcg_out_dat_imm(s, tcg_cond_to_arm_cond[args[3]],
+                        ARITH_MOV, args[0], 0, 1);
+        tcg_out_dat_imm(s, tcg_cond_to_arm_cond[tcg_invert_cond(args[3])],
+                        ARITH_MOV, args[0], 0, 0);
+        break;
+    case INDEX_op_setcond2_i32:
+        /* See brcond2_i32 comment */
+        tcg_out_dat_rIN(s, COND_AL, ARITH_CMP, ARITH_CMN, 0,
+                        args[2], args[4], const_args[4]);
+        tcg_out_dat_rIN(s, COND_EQ, ARITH_CMP, ARITH_CMN, 0,
+                        args[1], args[3], const_args[3]);
+        tcg_out_dat_imm(s, tcg_cond_to_arm_cond[args[5]],
+                        ARITH_MOV, args[0], 0, 1);
+        tcg_out_dat_imm(s, tcg_cond_to_arm_cond[tcg_invert_cond(args[5])],
+                        ARITH_MOV, args[0], 0, 0);
+        break;
+
+    case INDEX_op_qemu_ld_i32:
+        tcg_out_qemu_ld(s, args, 0);
+        break;
+    case INDEX_op_qemu_ld_i64:
+        tcg_out_qemu_ld(s, args, 1);
+        break;
+    case INDEX_op_qemu_st_i32:
+        tcg_out_qemu_st(s, args, 0);
+        break;
+    case INDEX_op_qemu_st_i64:
+        tcg_out_qemu_st(s, args, 1);
+        break;
+
+    case INDEX_op_bswap16_i32:
+        tcg_out_bswap16(s, COND_AL, args[0], args[1]);
+        break;
+    case INDEX_op_bswap32_i32:
+        tcg_out_bswap32(s, COND_AL, args[0], args[1]);
+        break;
+
+    case INDEX_op_ext8s_i32:
+        tcg_out_ext8s(s, COND_AL, args[0], args[1]);
+        break;
+    case INDEX_op_ext16s_i32:
+        tcg_out_ext16s(s, COND_AL, args[0], args[1]);
+        break;
+    case INDEX_op_ext16u_i32:
+        tcg_out_ext16u(s, COND_AL, args[0], args[1]);
+        break;
+
+    case INDEX_op_deposit_i32:
+        tcg_out_deposit(s, COND_AL, args[0], args[2],
+                        args[3], args[4], const_args[2]);
+        break;
+
+    case INDEX_op_div_i32:
+        tcg_out_sdiv(s, COND_AL, args[0], args[1], args[2]);
+        break;
+    case INDEX_op_divu_i32:
+        tcg_out_udiv(s, COND_AL, args[0], args[1], args[2]);
+        break;
+
+    case INDEX_op_mov_i32:  /* Always emitted via tcg_out_mov.  */
+    case INDEX_op_movi_i32: /* Always emitted via tcg_out_movi.  */
+    case INDEX_op_call:     /* Always emitted via tcg_out_call.  */
+    default:
+        tcg_abort();
+    }
+}
+
+static const TCGTargetOpDef arm_op_defs[] = {
+    { INDEX_op_exit_tb, { } },
+    { INDEX_op_goto_tb, { } },
+    { INDEX_op_br, { } },
+
+    { INDEX_op_ld8u_i32, { "r", "r" } },
+    { INDEX_op_ld8s_i32, { "r", "r" } },
+    { INDEX_op_ld16u_i32, { "r", "r" } },
+    { INDEX_op_ld16s_i32, { "r", "r" } },
+    { INDEX_op_ld_i32, { "r", "r" } },
+    { INDEX_op_st8_i32, { "r", "r" } },
+    { INDEX_op_st16_i32, { "r", "r" } },
+    { INDEX_op_st_i32, { "r", "r" } },
+
+    /* TODO: "r", "r", "ri" */
+    { INDEX_op_add_i32, { "r", "r", "rIN" } },
+    { INDEX_op_sub_i32, { "r", "rI", "rIN" } },
+    { INDEX_op_mul_i32, { "r", "r", "r" } },
+    { INDEX_op_mulu2_i32, { "r", "r", "r", "r" } },
+    { INDEX_op_muls2_i32, { "r", "r", "r", "r" } },
+    { INDEX_op_and_i32, { "r", "r", "rIK" } },
+    { INDEX_op_andc_i32, { "r", "r", "rIK" } },
+    { INDEX_op_or_i32, { "r", "r", "rI" } },
+    { INDEX_op_xor_i32, { "r", "r", "rI" } },
+    { INDEX_op_neg_i32, { "r", "r" } },
+    { INDEX_op_not_i32, { "r", "r" } },
+
+    { INDEX_op_shl_i32, { "r", "r", "ri" } },
+    { INDEX_op_shr_i32, { "r", "r", "ri" } },
+    { INDEX_op_sar_i32, { "r", "r", "ri" } },
+    { INDEX_op_rotl_i32, { "r", "r", "ri" } },
+    { INDEX_op_rotr_i32, { "r", "r", "ri" } },
+
+    { INDEX_op_brcond_i32, { "r", "rIN" } },
+    { INDEX_op_setcond_i32, { "r", "r", "rIN" } },
+    { INDEX_op_movcond_i32, { "r", "r", "rIN", "rIK", "0" } },
+
+    { INDEX_op_add2_i32, { "r", "r", "r", "r", "rIN", "rIK" } },
+    { INDEX_op_sub2_i32, { "r", "r", "rI", "rI", "rIN", "rIK" } },
+    { INDEX_op_brcond2_i32, { "r", "r", "rIN", "rIN" } },
+    { INDEX_op_setcond2_i32, { "r", "r", "r", "rIN", "rIN" } },
+
+#if TARGET_LONG_BITS == 32
+    { INDEX_op_qemu_ld_i32, { "r", "l" } },
+    { INDEX_op_qemu_ld_i64, { "r", "r", "l" } },
+    { INDEX_op_qemu_st_i32, { "s", "s" } },
+    { INDEX_op_qemu_st_i64, { "s", "s", "s" } },
+#else
+    { INDEX_op_qemu_ld_i32, { "r", "l", "l" } },
+    { INDEX_op_qemu_ld_i64, { "r", "r", "l", "l" } },
+    { INDEX_op_qemu_st_i32, { "s", "s", "s" } },
+    { INDEX_op_qemu_st_i64, { "s", "s", "s", "s" } },
+#endif
+
+    { INDEX_op_bswap16_i32, { "r", "r" } },
+    { INDEX_op_bswap32_i32, { "r", "r" } },
+
+    { INDEX_op_ext8s_i32, { "r", "r" } },
+    { INDEX_op_ext16s_i32, { "r", "r" } },
+    { INDEX_op_ext16u_i32, { "r", "r" } },
+
+    { INDEX_op_deposit_i32, { "r", "0", "rZ" } },
+
+    { INDEX_op_div_i32, { "r", "r", "r" } },
+    { INDEX_op_divu_i32, { "r", "r", "r" } },
+
+    { -1 },
+};
+
+static void tcg_target_init(TCGContext *s)
+{
+    /* Only probe for the platform and capabilities if we havn't already
+       determined maximum values at compile time.  */
+#ifndef use_idiv_instructions
+    {
+        unsigned long hwcap = qemu_getauxval(AT_HWCAP);
+        use_idiv_instructions = (hwcap & HWCAP_ARM_IDIVA) != 0;
+    }
+#endif
+    if (__ARM_ARCH < 7) {
+        const char *pl = (const char *)qemu_getauxval(AT_PLATFORM);
+        if (pl != NULL && pl[0] == 'v' && pl[1] >= '4' && pl[1] <= '9') {
+            arm_arch = pl[1] - '0';
+        }
+    }
+
+    tcg_regset_set32(tcg_target_available_regs[TCG_TYPE_I32], 0, 0xffff);
+    tcg_regset_set32(tcg_target_call_clobber_regs, 0,
+                     (1 << TCG_REG_R0) |
+                     (1 << TCG_REG_R1) |
+                     (1 << TCG_REG_R2) |
+                     (1 << TCG_REG_R3) |
+                     (1 << TCG_REG_R12) |
+                     (1 << TCG_REG_R14));
+
+    tcg_regset_clear(s->reserved_regs);
+    tcg_regset_set_reg(s->reserved_regs, TCG_REG_CALL_STACK);
+    tcg_regset_set_reg(s->reserved_regs, TCG_REG_TMP);
+    tcg_regset_set_reg(s->reserved_regs, TCG_REG_PC);
+
+    tcg_add_target_add_op_defs(arm_op_defs);
+}
+
+static inline void tcg_out_ld(TCGContext *s, TCGType type, TCGReg arg,
+                              TCGReg arg1, intptr_t arg2)
+{
+    tcg_out_ld32u(s, COND_AL, arg, arg1, arg2);
+}
+
+static inline void tcg_out_st(TCGContext *s, TCGType type, TCGReg arg,
+                              TCGReg arg1, intptr_t arg2)
+{
+    tcg_out_st32(s, COND_AL, arg, arg1, arg2);
+}
+
+static inline void tcg_out_mov(TCGContext *s, TCGType type,
+                               TCGReg ret, TCGReg arg)
+{
+    tcg_out_dat_reg(s, COND_AL, ARITH_MOV, ret, 0, arg, SHIFT_IMM_LSL(0));
+}
+
+static inline void tcg_out_movi(TCGContext *s, TCGType type,
+                                TCGReg ret, tcg_target_long arg)
+{
+    tcg_out_movi32(s, COND_AL, ret, arg);
+}
+
+/* Compute frame size via macros, to share between tcg_target_qemu_prologue
+   and tcg_register_jit.  */
+
+#define PUSH_SIZE  ((11 - 4 + 1 + 1) * sizeof(tcg_target_long))
+
+#define FRAME_SIZE \
+    ((PUSH_SIZE \
+      + TCG_STATIC_CALL_ARGS_SIZE \
+      + CPU_TEMP_BUF_NLONGS * sizeof(long) \
+      + TCG_TARGET_STACK_ALIGN - 1) \
+     & -TCG_TARGET_STACK_ALIGN)
+
+static void tcg_target_qemu_prologue(TCGContext *s)
+{
+    int stack_addend;
+
+    /* Calling convention requires us to save r4-r11 and lr.  */
+    /* stmdb sp!, { r4 - r11, lr } */
+    tcg_out32(s, (COND_AL << 28) | 0x092d4ff0);
+
+    /* Reserve callee argument and tcg temp space.  */
+    stack_addend = FRAME_SIZE - PUSH_SIZE;
+
+    tcg_out_dat_rI(s, COND_AL, ARITH_SUB, TCG_REG_CALL_STACK,
+                   TCG_REG_CALL_STACK, stack_addend, 1);
+    tcg_set_frame(s, TCG_REG_CALL_STACK, TCG_STATIC_CALL_ARGS_SIZE,
+                  CPU_TEMP_BUF_NLONGS * sizeof(long));
+
+    tcg_out_mov(s, TCG_TYPE_PTR, TCG_AREG0, tcg_target_call_iarg_regs[0]);
+
+    tcg_out_bx(s, COND_AL, tcg_target_call_iarg_regs[1]);
+    tb_ret_addr = s->code_ptr;
+
+    /* Epilogue.  We branch here via tb_ret_addr.  */
+    tcg_out_dat_rI(s, COND_AL, ARITH_ADD, TCG_REG_CALL_STACK,
+                   TCG_REG_CALL_STACK, stack_addend, 1);
+
+    /* ldmia sp!, { r4 - r11, pc } */
+    tcg_out32(s, (COND_AL << 28) | 0x08bd8ff0);
+}
+
+typedef struct {
+    DebugFrameHeader h;
+    uint8_t fde_def_cfa[4];
+    uint8_t fde_reg_ofs[18];
+} DebugFrame;
+
+#define ELF_HOST_MACHINE EM_ARM
+
+/* We're expecting a 2 byte uleb128 encoded value.  */
+QEMU_BUILD_BUG_ON(FRAME_SIZE >= (1 << 14));
+
+static const DebugFrame debug_frame = {
+    .h.cie.len = sizeof(DebugFrameCIE)-4, /* length after .len member */
+    .h.cie.id = -1,
+    .h.cie.version = 1,
+    .h.cie.code_align = 1,
+    .h.cie.data_align = 0x7c,             /* sleb128 -4 */
+    .h.cie.return_column = 14,
+
+    /* Total FDE size does not include the "len" member.  */
+    .h.fde.len = sizeof(DebugFrame) - offsetof(DebugFrame, h.fde.cie_offset),
+
+    .fde_def_cfa = {
+        12, 13,                         /* DW_CFA_def_cfa sp, ... */
+        (FRAME_SIZE & 0x7f) | 0x80,     /* ... uleb128 FRAME_SIZE */
+        (FRAME_SIZE >> 7)
+    },
+    .fde_reg_ofs = {
+        /* The following must match the stmdb in the prologue.  */
+        0x8e, 1,                        /* DW_CFA_offset, lr, -4 */
+        0x8b, 2,                        /* DW_CFA_offset, r11, -8 */
+        0x8a, 3,                        /* DW_CFA_offset, r10, -12 */
+        0x89, 4,                        /* DW_CFA_offset, r9, -16 */
+        0x88, 5,                        /* DW_CFA_offset, r8, -20 */
+        0x87, 6,                        /* DW_CFA_offset, r7, -24 */
+        0x86, 7,                        /* DW_CFA_offset, r6, -28 */
+        0x85, 8,                        /* DW_CFA_offset, r5, -32 */
+        0x84, 9,                        /* DW_CFA_offset, r4, -36 */
+    }
+};
+
+void tcg_register_jit(void *buf, size_t buf_size)
+{
+    tcg_register_jit_int(buf, buf_size, &debug_frame, sizeof(debug_frame));
+}
diff --git a/tcg/arm/tcg-target.h b/tcg/arm/tcg-target.h
new file mode 100644
index 00000000..6559f80b
--- /dev/null
+++ b/tcg/arm/tcg-target.h
@@ -0,0 +1,109 @@
+/*
+ * Tiny Code Generator for QEMU
+ *
+ * Copyright (c) 2008 Fabrice Bellard
+ * Copyright (c) 2008 Andrzej Zaborowski
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (the "Software"), to deal
+ * in the Software without restriction, including without limitation the rights
+ * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+ * copies of the Software, and to permit persons to whom the Software is
+ * furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+ * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+ * THE SOFTWARE.
+ */
+#ifndef TCG_TARGET_ARM 
+#define TCG_TARGET_ARM 1
+
+#undef TCG_TARGET_STACK_GROWSUP
+#define TCG_TARGET_INSN_UNIT_SIZE 4
+#define TCG_TARGET_TLB_DISPLACEMENT_BITS 16
+
+typedef enum {
+    TCG_REG_R0 = 0,
+    TCG_REG_R1,
+    TCG_REG_R2,
+    TCG_REG_R3,
+    TCG_REG_R4,
+    TCG_REG_R5,
+    TCG_REG_R6,
+    TCG_REG_R7,
+    TCG_REG_R8,
+    TCG_REG_R9,
+    TCG_REG_R10,
+    TCG_REG_R11,
+    TCG_REG_R12,
+    TCG_REG_R13,
+    TCG_REG_R14,
+    TCG_REG_PC,
+} TCGReg;
+
+#define TCG_TARGET_NB_REGS 16
+
+#ifdef __ARM_ARCH_EXT_IDIV__
+#define use_idiv_instructions  1
+#else
+extern bool use_idiv_instructions;
+#endif
+
+
+/* used for function call generation */
+#define TCG_REG_CALL_STACK		TCG_REG_R13
+#define TCG_TARGET_STACK_ALIGN		8
+#define TCG_TARGET_CALL_ALIGN_ARGS	1
+#define TCG_TARGET_CALL_STACK_OFFSET	0
+
+/* optional instructions */
+#define TCG_TARGET_HAS_ext8s_i32        1
+#define TCG_TARGET_HAS_ext16s_i32       1
+#define TCG_TARGET_HAS_ext8u_i32        0 /* and r0, r1, #0xff */
+#define TCG_TARGET_HAS_ext16u_i32       1
+#define TCG_TARGET_HAS_bswap16_i32      1
+#define TCG_TARGET_HAS_bswap32_i32      1
+#define TCG_TARGET_HAS_not_i32          1
+#define TCG_TARGET_HAS_neg_i32          1
+#define TCG_TARGET_HAS_rot_i32          1
+#define TCG_TARGET_HAS_andc_i32         1
+#define TCG_TARGET_HAS_orc_i32          0
+#define TCG_TARGET_HAS_eqv_i32          0
+#define TCG_TARGET_HAS_nand_i32         0
+#define TCG_TARGET_HAS_nor_i32          0
+#define TCG_TARGET_HAS_deposit_i32      1
+#define TCG_TARGET_HAS_movcond_i32      1
+#define TCG_TARGET_HAS_mulu2_i32        1
+#define TCG_TARGET_HAS_muls2_i32        1
+#define TCG_TARGET_HAS_muluh_i32        0
+#define TCG_TARGET_HAS_mulsh_i32        0
+#define TCG_TARGET_HAS_div_i32          use_idiv_instructions
+#define TCG_TARGET_HAS_rem_i32          0
+
+extern bool tcg_target_deposit_valid(int ofs, int len);
+#define TCG_TARGET_deposit_i32_valid  tcg_target_deposit_valid
+
+enum {
+    TCG_AREG0 = TCG_REG_R6,
+};
+
+static inline void flush_icache_range(uintptr_t start, uintptr_t stop)
+{
+#if QEMU_GNUC_PREREQ(4, 1)
+    __builtin___clear_cache((char *) start, (char *) stop);
+#else
+    register uintptr_t _beg __asm("a1") = start;
+    register uintptr_t _end __asm("a2") = stop;
+    register uintptr_t _flg __asm("a3") = 0;
+    __asm __volatile__ ("swi 0x9f0002" : : "r" (_beg), "r" (_end), "r" (_flg));
+#endif
+}
+
+#endif
diff --git a/tcg/i386/tcg-target.c b/tcg/i386/tcg-target.c
new file mode 100644
index 00000000..887f22f6
--- /dev/null
+++ b/tcg/i386/tcg-target.c
@@ -0,0 +1,2451 @@
+/*
+ * Tiny Code Generator for QEMU
+ *
+ * Copyright (c) 2008 Fabrice Bellard
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (the "Software"), to deal
+ * in the Software without restriction, including without limitation the rights
+ * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+ * copies of the Software, and to permit persons to whom the Software is
+ * furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+ * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+ * THE SOFTWARE.
+ */
+
+#include "tcg-be-ldst.h"
+
+#ifndef NDEBUG
+static const char * const tcg_target_reg_names[TCG_TARGET_NB_REGS] = {
+#if TCG_TARGET_REG_BITS == 64
+    "%rax", "%rcx", "%rdx", "%rbx", "%rsp", "%rbp", "%rsi", "%rdi",
+    "%r8",  "%r9",  "%r10", "%r11", "%r12", "%r13", "%r14", "%r15",
+#else
+    "%eax", "%ecx", "%edx", "%ebx", "%esp", "%ebp", "%esi", "%edi",
+#endif
+};
+#endif
+
+static const int tcg_target_reg_alloc_order[] = {
+#if TCG_TARGET_REG_BITS == 64
+    TCG_REG_RBP,
+    TCG_REG_RBX,
+    TCG_REG_R12,
+    TCG_REG_R13,
+    TCG_REG_R14,
+    TCG_REG_R15,
+    TCG_REG_R10,
+    TCG_REG_R11,
+    TCG_REG_R9,
+    TCG_REG_R8,
+    TCG_REG_RCX,
+    TCG_REG_RDX,
+    TCG_REG_RSI,
+    TCG_REG_RDI,
+    TCG_REG_RAX,
+#else
+    TCG_REG_EBX,
+    TCG_REG_ESI,
+    TCG_REG_EDI,
+    TCG_REG_EBP,
+    TCG_REG_ECX,
+    TCG_REG_EDX,
+    TCG_REG_EAX,
+#endif
+};
+
+static const int tcg_target_call_iarg_regs[] = {
+#if TCG_TARGET_REG_BITS == 64
+#if defined(_WIN64)
+    TCG_REG_RCX,
+    TCG_REG_RDX,
+#else
+    TCG_REG_RDI,
+    TCG_REG_RSI,
+    TCG_REG_RDX,
+    TCG_REG_RCX,
+#endif
+    TCG_REG_R8,
+    TCG_REG_R9,
+#else
+    /* 32 bit mode uses stack based calling convention (GCC default). */
+#endif
+};
+
+static const int tcg_target_call_oarg_regs[] = {
+    TCG_REG_EAX,
+#if TCG_TARGET_REG_BITS == 32
+    TCG_REG_EDX
+#endif
+};
+
+/* Constants we accept.  */
+#define TCG_CT_CONST_S32 0x100
+#define TCG_CT_CONST_U32 0x200
+#define TCG_CT_CONST_I32 0x400
+
+/* Registers used with L constraint, which are the first argument 
+   registers on x86_64, and two random call clobbered registers on
+   i386. */
+#if TCG_TARGET_REG_BITS == 64
+# define TCG_REG_L0 tcg_target_call_iarg_regs[0]
+# define TCG_REG_L1 tcg_target_call_iarg_regs[1]
+#else
+# define TCG_REG_L0 TCG_REG_EAX
+# define TCG_REG_L1 TCG_REG_EDX
+#endif
+
+/* The host compiler should supply <cpuid.h> to enable runtime features
+   detection, as we're not going to go so far as our own inline assembly.
+   If not available, default values will be assumed.  */
+#if defined(CONFIG_CPUID_H)
+#include <cpuid.h>
+#endif
+
+/* For 32-bit, we are going to attempt to determine at runtime whether cmov
+   is available.  */
+#if TCG_TARGET_REG_BITS == 64
+# define have_cmov 1
+#elif defined(CONFIG_CPUID_H) && defined(bit_CMOV)
+static bool have_cmov;
+#else
+# define have_cmov 0
+#endif
+
+/* If bit_MOVBE is defined in cpuid.h (added in GCC version 4.6), we are
+   going to attempt to determine at runtime whether movbe is available.  */
+#if defined(CONFIG_CPUID_H) && defined(bit_MOVBE)
+static bool have_movbe;
+#else
+# define have_movbe 0
+#endif
+
+/* We need this symbol in tcg-target.h, and we can't properly conditionalize
+   it there.  Therefore we always define the variable.  */
+bool have_bmi1;
+
+#if defined(CONFIG_CPUID_H) && defined(bit_BMI2)
+static bool have_bmi2;
+#else
+# define have_bmi2 0
+#endif
+
+static tcg_insn_unit *tb_ret_addr;
+
+static void patch_reloc(tcg_insn_unit *code_ptr, int type,
+                        intptr_t value, intptr_t addend)
+{
+    value += addend;
+    switch(type) {
+    case R_386_PC32:
+        value -= (uintptr_t)code_ptr;
+        if (value != (int32_t)value) {
+            tcg_abort();
+        }
+        tcg_patch32(code_ptr, value);
+        break;
+    case R_386_PC8:
+        value -= (uintptr_t)code_ptr;
+        if (value != (int8_t)value) {
+            tcg_abort();
+        }
+        tcg_patch8(code_ptr, value);
+        break;
+    default:
+        tcg_abort();
+    }
+}
+
+/* parse target specific constraints */
+static int target_parse_constraint(TCGArgConstraint *ct, const char **pct_str)
+{
+    const char *ct_str;
+
+    ct_str = *pct_str;
+    switch(ct_str[0]) {
+    case 'a':
+        ct->ct |= TCG_CT_REG;
+        tcg_regset_set_reg(ct->u.regs, TCG_REG_EAX);
+        break;
+    case 'b':
+        ct->ct |= TCG_CT_REG;
+        tcg_regset_set_reg(ct->u.regs, TCG_REG_EBX);
+        break;
+    case 'c':
+    case_c:
+        ct->ct |= TCG_CT_REG;
+        tcg_regset_set_reg(ct->u.regs, TCG_REG_ECX);
+        break;
+    case 'd':
+        ct->ct |= TCG_CT_REG;
+        tcg_regset_set_reg(ct->u.regs, TCG_REG_EDX);
+        break;
+    case 'S':
+        ct->ct |= TCG_CT_REG;
+        tcg_regset_set_reg(ct->u.regs, TCG_REG_ESI);
+        break;
+    case 'D':
+        ct->ct |= TCG_CT_REG;
+        tcg_regset_set_reg(ct->u.regs, TCG_REG_EDI);
+        break;
+    case 'q':
+        ct->ct |= TCG_CT_REG;
+        if (TCG_TARGET_REG_BITS == 64) {
+            tcg_regset_set32(ct->u.regs, 0, 0xffff);
+        } else {
+            tcg_regset_set32(ct->u.regs, 0, 0xf);
+        }
+        break;
+    case 'Q':
+        ct->ct |= TCG_CT_REG;
+        tcg_regset_set32(ct->u.regs, 0, 0xf);
+        break;
+    case 'r':
+    case_r:
+        ct->ct |= TCG_CT_REG;
+        if (TCG_TARGET_REG_BITS == 64) {
+            tcg_regset_set32(ct->u.regs, 0, 0xffff);
+        } else {
+            tcg_regset_set32(ct->u.regs, 0, 0xff);
+        }
+        break;
+    case 'C':
+        /* With SHRX et al, we need not use ECX as shift count register.  */
+        if (have_bmi2) {
+            goto case_r;
+        } else {
+            goto case_c;
+        }
+
+        /* qemu_ld/st address constraint */
+    case 'L':
+        ct->ct |= TCG_CT_REG;
+        if (TCG_TARGET_REG_BITS == 64) {
+            tcg_regset_set32(ct->u.regs, 0, 0xffff);
+        } else {
+            tcg_regset_set32(ct->u.regs, 0, 0xff);
+        }
+        tcg_regset_reset_reg(ct->u.regs, TCG_REG_L0);
+        tcg_regset_reset_reg(ct->u.regs, TCG_REG_L1);
+        break;
+
+    case 'e':
+        ct->ct |= TCG_CT_CONST_S32;
+        break;
+    case 'Z':
+        ct->ct |= TCG_CT_CONST_U32;
+        break;
+    case 'I':
+        ct->ct |= TCG_CT_CONST_I32;
+        break;
+
+    default:
+        return -1;
+    }
+    ct_str++;
+    *pct_str = ct_str;
+    return 0;
+}
+
+/* test if a constant matches the constraint */
+static inline int tcg_target_const_match(tcg_target_long val, TCGType type,
+                                         const TCGArgConstraint *arg_ct)
+{
+    int ct = arg_ct->ct;
+    if (ct & TCG_CT_CONST) {
+        return 1;
+    }
+    if ((ct & TCG_CT_CONST_S32) && val == (int32_t)val) {
+        return 1;
+    }
+    if ((ct & TCG_CT_CONST_U32) && val == (uint32_t)val) {
+        return 1;
+    }
+    if ((ct & TCG_CT_CONST_I32) && ~val == (int32_t)~val) {
+        return 1;
+    }
+    return 0;
+}
+
+#if TCG_TARGET_REG_BITS == 64
+# define LOWREGMASK(x)	((x) & 7)
+#else
+# define LOWREGMASK(x)	(x)
+#endif
+
+#define P_EXT		0x100		/* 0x0f opcode prefix */
+#define P_EXT38         0x200           /* 0x0f 0x38 opcode prefix */
+#define P_DATA16        0x400           /* 0x66 opcode prefix */
+#if TCG_TARGET_REG_BITS == 64
+# define P_ADDR32       0x800           /* 0x67 opcode prefix */
+# define P_REXW         0x1000          /* Set REX.W = 1 */
+# define P_REXB_R       0x2000          /* REG field as byte register */
+# define P_REXB_RM      0x4000          /* R/M field as byte register */
+# define P_GS           0x8000          /* gs segment override */
+#else
+# define P_ADDR32	0
+# define P_REXW		0
+# define P_REXB_R	0
+# define P_REXB_RM	0
+# define P_GS           0
+#endif
+#define P_SIMDF3        0x10000         /* 0xf3 opcode prefix */
+#define P_SIMDF2        0x20000         /* 0xf2 opcode prefix */
+
+#define OPC_ARITH_EvIz	(0x81)
+#define OPC_ARITH_EvIb	(0x83)
+#define OPC_ARITH_GvEv	(0x03)		/* ... plus (ARITH_FOO << 3) */
+#define OPC_ANDN        (0xf2 | P_EXT38)
+#define OPC_ADD_GvEv	(OPC_ARITH_GvEv | (ARITH_ADD << 3))
+#define OPC_BSWAP	(0xc8 | P_EXT)
+#define OPC_CALL_Jz	(0xe8)
+#define OPC_CMOVCC      (0x40 | P_EXT)  /* ... plus condition code */
+#define OPC_CMP_GvEv	(OPC_ARITH_GvEv | (ARITH_CMP << 3))
+#define OPC_DEC_r32	(0x48)
+#define OPC_IMUL_GvEv	(0xaf | P_EXT)
+#define OPC_IMUL_GvEvIb	(0x6b)
+#define OPC_IMUL_GvEvIz	(0x69)
+#define OPC_INC_r32	(0x40)
+#define OPC_JCC_long	(0x80 | P_EXT)	/* ... plus condition code */
+#define OPC_JCC_short	(0x70)		/* ... plus condition code */
+#define OPC_JMP_long	(0xe9)
+#define OPC_JMP_short	(0xeb)
+#define OPC_LEA         (0x8d)
+#define OPC_MOVB_EvGv	(0x88)		/* stores, more or less */
+#define OPC_MOVL_EvGv	(0x89)		/* stores, more or less */
+#define OPC_MOVL_GvEv	(0x8b)		/* loads, more or less */
+#define OPC_MOVB_EvIz   (0xc6)
+#define OPC_MOVL_EvIz	(0xc7)
+#define OPC_MOVL_Iv     (0xb8)
+#define OPC_MOVBE_GyMy  (0xf0 | P_EXT38)
+#define OPC_MOVBE_MyGy  (0xf1 | P_EXT38)
+#define OPC_MOVSBL	(0xbe | P_EXT)
+#define OPC_MOVSWL	(0xbf | P_EXT)
+#define OPC_MOVSLQ	(0x63 | P_REXW)
+#define OPC_MOVZBL	(0xb6 | P_EXT)
+#define OPC_MOVZWL	(0xb7 | P_EXT)
+#define OPC_POP_r32	(0x58)
+#define OPC_PUSH_r32	(0x50)
+#define OPC_PUSH_Iv	(0x68)
+#define OPC_PUSH_Ib	(0x6a)
+#define OPC_RET		(0xc3)
+#define OPC_SETCC	(0x90 | P_EXT | P_REXB_RM) /* ... plus cc */
+#define OPC_SHIFT_1	(0xd1)
+#define OPC_SHIFT_Ib	(0xc1)
+#define OPC_SHIFT_cl	(0xd3)
+#define OPC_SARX        (0xf7 | P_EXT38 | P_SIMDF3)
+#define OPC_SHLX        (0xf7 | P_EXT38 | P_DATA16)
+#define OPC_SHRX        (0xf7 | P_EXT38 | P_SIMDF2)
+#define OPC_TESTL	(0x85)
+#define OPC_XCHG_ax_r32	(0x90)
+
+#define OPC_GRP3_Ev	(0xf7)
+#define OPC_GRP5	(0xff)
+
+/* Group 1 opcode extensions for 0x80-0x83.
+   These are also used as modifiers for OPC_ARITH.  */
+#define ARITH_ADD 0
+#define ARITH_OR  1
+#define ARITH_ADC 2
+#define ARITH_SBB 3
+#define ARITH_AND 4
+#define ARITH_SUB 5
+#define ARITH_XOR 6
+#define ARITH_CMP 7
+
+/* Group 2 opcode extensions for 0xc0, 0xc1, 0xd0-0xd3.  */
+#define SHIFT_ROL 0
+#define SHIFT_ROR 1
+#define SHIFT_SHL 4
+#define SHIFT_SHR 5
+#define SHIFT_SAR 7
+
+/* Group 3 opcode extensions for 0xf6, 0xf7.  To be used with OPC_GRP3.  */
+#define EXT3_NOT   2
+#define EXT3_NEG   3
+#define EXT3_MUL   4
+#define EXT3_IMUL  5
+#define EXT3_DIV   6
+#define EXT3_IDIV  7
+
+/* Group 5 opcode extensions for 0xff.  To be used with OPC_GRP5.  */
+#define EXT5_INC_Ev	0
+#define EXT5_DEC_Ev	1
+#define EXT5_CALLN_Ev	2
+#define EXT5_JMPN_Ev	4
+
+/* Condition codes to be added to OPC_JCC_{long,short}.  */
+#define JCC_JMP (-1)
+#define JCC_JO  0x0
+#define JCC_JNO 0x1
+#define JCC_JB  0x2
+#define JCC_JAE 0x3
+#define JCC_JE  0x4
+#define JCC_JNE 0x5
+#define JCC_JBE 0x6
+#define JCC_JA  0x7
+#define JCC_JS  0x8
+#define JCC_JNS 0x9
+#define JCC_JP  0xa
+#define JCC_JNP 0xb
+#define JCC_JL  0xc
+#define JCC_JGE 0xd
+#define JCC_JLE 0xe
+#define JCC_JG  0xf
+
+static const uint8_t tcg_cond_to_jcc[] = {
+    [TCG_COND_EQ] = JCC_JE,
+    [TCG_COND_NE] = JCC_JNE,
+    [TCG_COND_LT] = JCC_JL,
+    [TCG_COND_GE] = JCC_JGE,
+    [TCG_COND_LE] = JCC_JLE,
+    [TCG_COND_GT] = JCC_JG,
+    [TCG_COND_LTU] = JCC_JB,
+    [TCG_COND_GEU] = JCC_JAE,
+    [TCG_COND_LEU] = JCC_JBE,
+    [TCG_COND_GTU] = JCC_JA,
+};
+
+#if TCG_TARGET_REG_BITS == 64
+static void tcg_out_opc(TCGContext *s, int opc, int r, int rm, int x)
+{
+    int rex;
+
+    if (opc & P_GS) {
+        tcg_out8(s, 0x65);
+    }
+    if (opc & P_DATA16) {
+        /* We should never be asking for both 16 and 64-bit operation.  */
+        assert((opc & P_REXW) == 0);
+        tcg_out8(s, 0x66);
+    }
+    if (opc & P_ADDR32) {
+        tcg_out8(s, 0x67);
+    }
+
+    rex = 0;
+    rex |= (opc & P_REXW) ? 0x8 : 0x0;  /* REX.W */
+    rex |= (r & 8) >> 1;                /* REX.R */
+    rex |= (x & 8) >> 2;                /* REX.X */
+    rex |= (rm & 8) >> 3;               /* REX.B */
+
+    /* P_REXB_{R,RM} indicates that the given register is the low byte.
+       For %[abcd]l we need no REX prefix, but for %{si,di,bp,sp}l we do,
+       as otherwise the encoding indicates %[abcd]h.  Note that the values
+       that are ORed in merely indicate that the REX byte must be present;
+       those bits get discarded in output.  */
+    rex |= opc & (r >= 4 ? P_REXB_R : 0);
+    rex |= opc & (rm >= 4 ? P_REXB_RM : 0);
+
+    if (rex) {
+        tcg_out8(s, (uint8_t)(rex | 0x40));
+    }
+
+    if (opc & (P_EXT | P_EXT38)) {
+        tcg_out8(s, 0x0f);
+        if (opc & P_EXT38) {
+            tcg_out8(s, 0x38);
+        }
+    }
+
+    tcg_out8(s, opc);
+}
+#else
+static void tcg_out_opc(TCGContext *s, int opc)
+{
+    if (opc & P_DATA16) {
+        tcg_out8(s, 0x66);
+    }
+    if (opc & (P_EXT | P_EXT38)) {
+        tcg_out8(s, 0x0f);
+        if (opc & P_EXT38) {
+            tcg_out8(s, 0x38);
+        }
+    }
+    tcg_out8(s, opc);
+}
+/* Discard the register arguments to tcg_out_opc early, so as not to penalize
+   the 32-bit compilation paths.  This method works with all versions of gcc,
+   whereas relying on optimization may not be able to exclude them.  */
+#define tcg_out_opc(s, opc, r, rm, x)  (tcg_out_opc)(s, opc)
+#endif
+
+static void tcg_out_modrm(TCGContext *s, int opc, int r, int rm)
+{
+    tcg_out_opc(s, opc, r, rm, 0);
+    tcg_out8(s, 0xc0 | (LOWREGMASK(r) << 3) | LOWREGMASK(rm));
+}
+
+static void tcg_out_vex_modrm(TCGContext *s, int opc, int r, int v, int rm)
+{
+    int tmp;
+
+    if ((opc & (P_REXW | P_EXT | P_EXT38)) || (rm & 8)) {
+        /* Three byte VEX prefix.  */
+        tcg_out8(s, 0xc4);
+
+        /* VEX.m-mmmm */
+        if (opc & P_EXT38) {
+            tmp = 2;
+        } else if (opc & P_EXT) {
+            tmp = 1;
+        } else {
+            tcg_abort();
+        }
+        tmp |= 0x40;                       /* VEX.X */
+        tmp |= (r & 8 ? 0 : 0x80);         /* VEX.R */
+        tmp |= (rm & 8 ? 0 : 0x20);        /* VEX.B */
+        tcg_out8(s, tmp);
+
+        tmp = (opc & P_REXW ? 0x80 : 0);   /* VEX.W */
+    } else {
+        /* Two byte VEX prefix.  */
+        tcg_out8(s, 0xc5);
+
+        tmp = (r & 8 ? 0 : 0x80);          /* VEX.R */
+    }
+    /* VEX.pp */
+    if (opc & P_DATA16) {
+        tmp |= 1;                          /* 0x66 */
+    } else if (opc & P_SIMDF3) {
+        tmp |= 2;                          /* 0xf3 */
+    } else if (opc & P_SIMDF2) {
+        tmp |= 3;                          /* 0xf2 */
+    }
+    tmp |= (~v & 15) << 3;                 /* VEX.vvvv */
+    tcg_out8(s, tmp);
+    tcg_out8(s, opc);
+    tcg_out8(s, 0xc0 | (LOWREGMASK(r) << 3) | LOWREGMASK(rm));
+}
+
+/* Output an opcode with a full "rm + (index<<shift) + offset" address mode.
+   We handle either RM and INDEX missing with a negative value.  In 64-bit
+   mode for absolute addresses, ~RM is the size of the immediate operand
+   that will follow the instruction.  */
+
+static void tcg_out_modrm_sib_offset(TCGContext *s, int opc, int r, int rm,
+                                     int index, int shift, intptr_t offset)
+{
+    int mod, len;
+
+    if (index < 0 && rm < 0) {
+        if (TCG_TARGET_REG_BITS == 64) {
+            /* Try for a rip-relative addressing mode.  This has replaced
+               the 32-bit-mode absolute addressing encoding.  */
+            intptr_t pc = (intptr_t)s->code_ptr + 5 + ~rm;
+            intptr_t disp = offset - pc;
+            if (disp == (int32_t)disp) {
+                tcg_out_opc(s, opc, r, 0, 0);
+                tcg_out8(s, (LOWREGMASK(r) << 3) | 5);
+                tcg_out32(s, disp);
+                return;
+            }
+
+            /* Try for an absolute address encoding.  This requires the
+               use of the MODRM+SIB encoding and is therefore larger than
+               rip-relative addressing.  */
+            if (offset == (int32_t)offset) {
+                tcg_out_opc(s, opc, r, 0, 0);
+                tcg_out8(s, (LOWREGMASK(r) << 3) | 4);
+                tcg_out8(s, (4 << 3) | 5);
+                tcg_out32(s, offset);
+                return;
+            }
+
+            /* ??? The memory isn't directly addressable.  */
+            tcg_abort();
+        } else {
+            /* Absolute address.  */
+            tcg_out_opc(s, opc, r, 0, 0);
+            tcg_out8(s, (r << 3) | 5);
+            tcg_out32(s, offset);
+            return;
+        }
+    }
+
+    /* Find the length of the immediate addend.  Note that the encoding
+       that would be used for (%ebp) indicates absolute addressing.  */
+    if (rm < 0) {
+        mod = 0, len = 4, rm = 5;
+    } else if (offset == 0 && LOWREGMASK(rm) != TCG_REG_EBP) {
+        mod = 0, len = 0;
+    } else if (offset == (int8_t)offset) {
+        mod = 0x40, len = 1;
+    } else {
+        mod = 0x80, len = 4;
+    }
+
+    /* Use a single byte MODRM format if possible.  Note that the encoding
+       that would be used for %esp is the escape to the two byte form.  */
+    if (index < 0 && LOWREGMASK(rm) != TCG_REG_ESP) {
+        /* Single byte MODRM format.  */
+        tcg_out_opc(s, opc, r, rm, 0);
+        tcg_out8(s, mod | (LOWREGMASK(r) << 3) | LOWREGMASK(rm));
+    } else {
+        /* Two byte MODRM+SIB format.  */
+
+        /* Note that the encoding that would place %esp into the index
+           field indicates no index register.  In 64-bit mode, the REX.X
+           bit counts, so %r12 can be used as the index.  */
+        if (index < 0) {
+            index = 4;
+        } else {
+            assert(index != TCG_REG_ESP);
+        }
+
+        tcg_out_opc(s, opc, r, rm, index);
+        tcg_out8(s, mod | (LOWREGMASK(r) << 3) | 4);
+        tcg_out8(s, (shift << 6) | (LOWREGMASK(index) << 3) | LOWREGMASK(rm));
+    }
+
+    if (len == 1) {
+        tcg_out8(s, offset);
+    } else if (len == 4) {
+        tcg_out32(s, offset);
+    }
+}
+
+/* A simplification of the above with no index or shift.  */
+static inline void tcg_out_modrm_offset(TCGContext *s, int opc, int r,
+                                        int rm, intptr_t offset)
+{
+    tcg_out_modrm_sib_offset(s, opc, r, rm, -1, 0, offset);
+}
+
+/* Generate dest op= src.  Uses the same ARITH_* codes as tgen_arithi.  */
+static inline void tgen_arithr(TCGContext *s, int subop, int dest, int src)
+{
+    /* Propagate an opcode prefix, such as P_REXW.  */
+    int ext = subop & ~0x7;
+    subop &= 0x7;
+
+    tcg_out_modrm(s, OPC_ARITH_GvEv + (subop << 3) + ext, dest, src);
+}
+
+static inline void tcg_out_mov(TCGContext *s, TCGType type,
+                               TCGReg ret, TCGReg arg)
+{
+    if (arg != ret) {
+        int opc = OPC_MOVL_GvEv + (type == TCG_TYPE_I64 ? P_REXW : 0);
+        tcg_out_modrm(s, opc, ret, arg);
+    }
+}
+
+static void tcg_out_movi(TCGContext *s, TCGType type,
+                         TCGReg ret, tcg_target_long arg)
+{
+    tcg_target_long diff;
+
+    if (arg == 0) {
+        tgen_arithr(s, ARITH_XOR, ret, ret);
+        return;
+    }
+    if (arg == (uint32_t)arg || type == TCG_TYPE_I32) {
+        tcg_out_opc(s, OPC_MOVL_Iv + LOWREGMASK(ret), 0, ret, 0);
+        tcg_out32(s, arg);
+        return;
+    }
+    if (arg == (int32_t)arg) {
+        tcg_out_modrm(s, OPC_MOVL_EvIz + P_REXW, 0, ret);
+        tcg_out32(s, arg);
+        return;
+    }
+
+    /* Try a 7 byte pc-relative lea before the 10 byte movq.  */
+    diff = arg - ((uintptr_t)s->code_ptr + 7);
+    if (diff == (int32_t)diff) {
+        tcg_out_opc(s, OPC_LEA | P_REXW, ret, 0, 0);
+        tcg_out8(s, (LOWREGMASK(ret) << 3) | 5);
+        tcg_out32(s, diff);
+        return;
+    }
+
+    tcg_out_opc(s, OPC_MOVL_Iv + P_REXW + LOWREGMASK(ret), 0, ret, 0);
+    tcg_out64(s, arg);
+}
+
+static inline void tcg_out_pushi(TCGContext *s, tcg_target_long val)
+{
+    if (val == (int8_t)val) {
+        tcg_out_opc(s, OPC_PUSH_Ib, 0, 0, 0);
+        tcg_out8(s, val);
+    } else if (val == (int32_t)val) {
+        tcg_out_opc(s, OPC_PUSH_Iv, 0, 0, 0);
+        tcg_out32(s, val);
+    } else {
+        tcg_abort();
+    }
+}
+
+static inline void tcg_out_push(TCGContext *s, int reg)
+{
+    tcg_out_opc(s, OPC_PUSH_r32 + LOWREGMASK(reg), 0, reg, 0);
+}
+
+static inline void tcg_out_pop(TCGContext *s, int reg)
+{
+    tcg_out_opc(s, OPC_POP_r32 + LOWREGMASK(reg), 0, reg, 0);
+}
+
+static inline void tcg_out_ld(TCGContext *s, TCGType type, TCGReg ret,
+                              TCGReg arg1, intptr_t arg2)
+{
+    int opc = OPC_MOVL_GvEv + (type == TCG_TYPE_I64 ? P_REXW : 0);
+    tcg_out_modrm_offset(s, opc, ret, arg1, arg2);
+}
+
+static inline void tcg_out_st(TCGContext *s, TCGType type, TCGReg arg,
+                              TCGReg arg1, intptr_t arg2)
+{
+    int opc = OPC_MOVL_EvGv + (type == TCG_TYPE_I64 ? P_REXW : 0);
+    tcg_out_modrm_offset(s, opc, arg, arg1, arg2);
+}
+
+static inline void tcg_out_sti(TCGContext *s, TCGType type, TCGReg base,
+                               tcg_target_long ofs, tcg_target_long val)
+{
+    int opc = OPC_MOVL_EvIz + (type == TCG_TYPE_I64 ? P_REXW : 0);
+    tcg_out_modrm_offset(s, opc, 0, base, ofs);
+    tcg_out32(s, val);
+}
+
+static void tcg_out_shifti(TCGContext *s, int subopc, int reg, int count)
+{
+    /* Propagate an opcode prefix, such as P_DATA16.  */
+    int ext = subopc & ~0x7;
+    subopc &= 0x7;
+
+    if (count == 1) {
+        tcg_out_modrm(s, OPC_SHIFT_1 + ext, subopc, reg);
+    } else {
+        tcg_out_modrm(s, OPC_SHIFT_Ib + ext, subopc, reg);
+        tcg_out8(s, count);
+    }
+}
+
+static inline void tcg_out_bswap32(TCGContext *s, int reg)
+{
+    tcg_out_opc(s, OPC_BSWAP + LOWREGMASK(reg), 0, reg, 0);
+}
+
+static inline void tcg_out_rolw_8(TCGContext *s, int reg)
+{
+    tcg_out_shifti(s, SHIFT_ROL + P_DATA16, reg, 8);
+}
+
+static inline void tcg_out_ext8u(TCGContext *s, int dest, int src)
+{
+    /* movzbl */
+    assert(src < 4 || TCG_TARGET_REG_BITS == 64);
+    tcg_out_modrm(s, OPC_MOVZBL + P_REXB_RM, dest, src);
+}
+
+static void tcg_out_ext8s(TCGContext *s, int dest, int src, int rexw)
+{
+    /* movsbl */
+    assert(src < 4 || TCG_TARGET_REG_BITS == 64);
+    tcg_out_modrm(s, OPC_MOVSBL + P_REXB_RM + rexw, dest, src);
+}
+
+static inline void tcg_out_ext16u(TCGContext *s, int dest, int src)
+{
+    /* movzwl */
+    tcg_out_modrm(s, OPC_MOVZWL, dest, src);
+}
+
+static inline void tcg_out_ext16s(TCGContext *s, int dest, int src, int rexw)
+{
+    /* movsw[lq] */
+    tcg_out_modrm(s, OPC_MOVSWL + rexw, dest, src);
+}
+
+static inline void tcg_out_ext32u(TCGContext *s, int dest, int src)
+{
+    /* 32-bit mov zero extends.  */
+    tcg_out_modrm(s, OPC_MOVL_GvEv, dest, src);
+}
+
+static inline void tcg_out_ext32s(TCGContext *s, int dest, int src)
+{
+    tcg_out_modrm(s, OPC_MOVSLQ, dest, src);
+}
+
+static inline void tcg_out_bswap64(TCGContext *s, int reg)
+{
+    tcg_out_opc(s, OPC_BSWAP + P_REXW + LOWREGMASK(reg), 0, reg, 0);
+}
+
+static void tgen_arithi(TCGContext *s, int c, int r0,
+                        tcg_target_long val, int cf)
+{
+    int rexw = 0;
+
+    if (TCG_TARGET_REG_BITS == 64) {
+        rexw = c & -8;
+        c &= 7;
+    }
+
+    /* ??? While INC is 2 bytes shorter than ADDL $1, they also induce
+       partial flags update stalls on Pentium4 and are not recommended
+       by current Intel optimization manuals.  */
+    if (!cf && (c == ARITH_ADD || c == ARITH_SUB) && (val == 1 || val == -1)) {
+        int is_inc = (c == ARITH_ADD) ^ (val < 0);
+        if (TCG_TARGET_REG_BITS == 64) {
+            /* The single-byte increment encodings are re-tasked as the
+               REX prefixes.  Use the MODRM encoding.  */
+            tcg_out_modrm(s, OPC_GRP5 + rexw,
+                          (is_inc ? EXT5_INC_Ev : EXT5_DEC_Ev), r0);
+        } else {
+            tcg_out8(s, (is_inc ? OPC_INC_r32 : OPC_DEC_r32) + r0);
+        }
+        return;
+    }
+
+    if (c == ARITH_AND) {
+        if (TCG_TARGET_REG_BITS == 64) {
+            if (val == 0xffffffffu) {
+                tcg_out_ext32u(s, r0, r0);
+                return;
+            }
+            if (val == (uint32_t)val) {
+                /* AND with no high bits set can use a 32-bit operation.  */
+                rexw = 0;
+            }
+        }
+        if (val == 0xffu && (r0 < 4 || TCG_TARGET_REG_BITS == 64)) {
+            tcg_out_ext8u(s, r0, r0);
+            return;
+        }
+        if (val == 0xffffu) {
+            tcg_out_ext16u(s, r0, r0);
+            return;
+        }
+    }
+
+    if (val == (int8_t)val) {
+        tcg_out_modrm(s, OPC_ARITH_EvIb + rexw, c, r0);
+        tcg_out8(s, val);
+        return;
+    }
+    if (rexw == 0 || val == (int32_t)val) {
+        tcg_out_modrm(s, OPC_ARITH_EvIz + rexw, c, r0);
+        tcg_out32(s, val);
+        return;
+    }
+
+    tcg_abort();
+}
+
+static void tcg_out_addi(TCGContext *s, int reg, tcg_target_long val)
+{
+    if (val != 0) {
+        tgen_arithi(s, ARITH_ADD + P_REXW, reg, val, 0);
+    }
+}
+
+/* Use SMALL != 0 to force a short forward branch.  */
+static void tcg_out_jxx(TCGContext *s, int opc, TCGLabel *l, int small)
+{
+    int32_t val, val1;
+
+    if (l->has_value) {
+        val = tcg_pcrel_diff(s, l->u.value_ptr);
+        val1 = val - 2;
+        if ((int8_t)val1 == val1) {
+            if (opc == -1) {
+                tcg_out8(s, OPC_JMP_short);
+            } else {
+                tcg_out8(s, OPC_JCC_short + opc);
+            }
+            tcg_out8(s, val1);
+        } else {
+            if (small) {
+                tcg_abort();
+            }
+            if (opc == -1) {
+                tcg_out8(s, OPC_JMP_long);
+                tcg_out32(s, val - 5);
+            } else {
+                tcg_out_opc(s, OPC_JCC_long + opc, 0, 0, 0);
+                tcg_out32(s, val - 6);
+            }
+        }
+    } else if (small) {
+        if (opc == -1) {
+            tcg_out8(s, OPC_JMP_short);
+        } else {
+            tcg_out8(s, OPC_JCC_short + opc);
+        }
+        tcg_out_reloc(s, s->code_ptr, R_386_PC8, l, -1);
+        s->code_ptr += 1;
+    } else {
+        if (opc == -1) {
+            tcg_out8(s, OPC_JMP_long);
+        } else {
+            tcg_out_opc(s, OPC_JCC_long + opc, 0, 0, 0);
+        }
+        tcg_out_reloc(s, s->code_ptr, R_386_PC32, l, -4);
+        s->code_ptr += 4;
+    }
+}
+
+static void tcg_out_cmp(TCGContext *s, TCGArg arg1, TCGArg arg2,
+                        int const_arg2, int rexw)
+{
+    if (const_arg2) {
+        if (arg2 == 0) {
+            /* test r, r */
+            tcg_out_modrm(s, OPC_TESTL + rexw, arg1, arg1);
+        } else {
+            tgen_arithi(s, ARITH_CMP + rexw, arg1, arg2, 0);
+        }
+    } else {
+        tgen_arithr(s, ARITH_CMP + rexw, arg1, arg2);
+    }
+}
+
+static void tcg_out_brcond32(TCGContext *s, TCGCond cond,
+                             TCGArg arg1, TCGArg arg2, int const_arg2,
+                             TCGLabel *label, int small)
+{
+    tcg_out_cmp(s, arg1, arg2, const_arg2, 0);
+    tcg_out_jxx(s, tcg_cond_to_jcc[cond], label, small);
+}
+
+#if TCG_TARGET_REG_BITS == 64
+static void tcg_out_brcond64(TCGContext *s, TCGCond cond,
+                             TCGArg arg1, TCGArg arg2, int const_arg2,
+                             TCGLabel *label, int small)
+{
+    tcg_out_cmp(s, arg1, arg2, const_arg2, P_REXW);
+    tcg_out_jxx(s, tcg_cond_to_jcc[cond], label, small);
+}
+#else
+/* XXX: we implement it at the target level to avoid having to
+   handle cross basic blocks temporaries */
+static void tcg_out_brcond2(TCGContext *s, const TCGArg *args,
+                            const int *const_args, int small)
+{
+    TCGLabel *label_next = gen_new_label();
+    TCGLabel *label_this = arg_label(args[5]);
+
+    switch(args[4]) {
+    case TCG_COND_EQ:
+        tcg_out_brcond32(s, TCG_COND_NE, args[0], args[2], const_args[2],
+                         label_next, 1);
+        tcg_out_brcond32(s, TCG_COND_EQ, args[1], args[3], const_args[3],
+                         label_this, small);
+        break;
+    case TCG_COND_NE:
+        tcg_out_brcond32(s, TCG_COND_NE, args[0], args[2], const_args[2],
+                         label_this, small);
+        tcg_out_brcond32(s, TCG_COND_NE, args[1], args[3], const_args[3],
+                         label_this, small);
+        break;
+    case TCG_COND_LT:
+        tcg_out_brcond32(s, TCG_COND_LT, args[1], args[3], const_args[3],
+                         label_this, small);
+        tcg_out_jxx(s, JCC_JNE, label_next, 1);
+        tcg_out_brcond32(s, TCG_COND_LTU, args[0], args[2], const_args[2],
+                         label_this, small);
+        break;
+    case TCG_COND_LE:
+        tcg_out_brcond32(s, TCG_COND_LT, args[1], args[3], const_args[3],
+                         label_this, small);
+        tcg_out_jxx(s, JCC_JNE, label_next, 1);
+        tcg_out_brcond32(s, TCG_COND_LEU, args[0], args[2], const_args[2],
+                         label_this, small);
+        break;
+    case TCG_COND_GT:
+        tcg_out_brcond32(s, TCG_COND_GT, args[1], args[3], const_args[3],
+                         label_this, small);
+        tcg_out_jxx(s, JCC_JNE, label_next, 1);
+        tcg_out_brcond32(s, TCG_COND_GTU, args[0], args[2], const_args[2],
+                         label_this, small);
+        break;
+    case TCG_COND_GE:
+        tcg_out_brcond32(s, TCG_COND_GT, args[1], args[3], const_args[3],
+                         label_this, small);
+        tcg_out_jxx(s, JCC_JNE, label_next, 1);
+        tcg_out_brcond32(s, TCG_COND_GEU, args[0], args[2], const_args[2],
+                         label_this, small);
+        break;
+    case TCG_COND_LTU:
+        tcg_out_brcond32(s, TCG_COND_LTU, args[1], args[3], const_args[3],
+                         label_this, small);
+        tcg_out_jxx(s, JCC_JNE, label_next, 1);
+        tcg_out_brcond32(s, TCG_COND_LTU, args[0], args[2], const_args[2],
+                         label_this, small);
+        break;
+    case TCG_COND_LEU:
+        tcg_out_brcond32(s, TCG_COND_LTU, args[1], args[3], const_args[3],
+                         label_this, small);
+        tcg_out_jxx(s, JCC_JNE, label_next, 1);
+        tcg_out_brcond32(s, TCG_COND_LEU, args[0], args[2], const_args[2],
+                         label_this, small);
+        break;
+    case TCG_COND_GTU:
+        tcg_out_brcond32(s, TCG_COND_GTU, args[1], args[3], const_args[3],
+                         label_this, small);
+        tcg_out_jxx(s, JCC_JNE, label_next, 1);
+        tcg_out_brcond32(s, TCG_COND_GTU, args[0], args[2], const_args[2],
+                         label_this, small);
+        break;
+    case TCG_COND_GEU:
+        tcg_out_brcond32(s, TCG_COND_GTU, args[1], args[3], const_args[3],
+                         label_this, small);
+        tcg_out_jxx(s, JCC_JNE, label_next, 1);
+        tcg_out_brcond32(s, TCG_COND_GEU, args[0], args[2], const_args[2],
+                         label_this, small);
+        break;
+    default:
+        tcg_abort();
+    }
+    tcg_out_label(s, label_next, s->code_ptr);
+}
+#endif
+
+static void tcg_out_setcond32(TCGContext *s, TCGCond cond, TCGArg dest,
+                              TCGArg arg1, TCGArg arg2, int const_arg2)
+{
+    tcg_out_cmp(s, arg1, arg2, const_arg2, 0);
+    tcg_out_modrm(s, OPC_SETCC | tcg_cond_to_jcc[cond], 0, dest);
+    tcg_out_ext8u(s, dest, dest);
+}
+
+#if TCG_TARGET_REG_BITS == 64
+static void tcg_out_setcond64(TCGContext *s, TCGCond cond, TCGArg dest,
+                              TCGArg arg1, TCGArg arg2, int const_arg2)
+{
+    tcg_out_cmp(s, arg1, arg2, const_arg2, P_REXW);
+    tcg_out_modrm(s, OPC_SETCC | tcg_cond_to_jcc[cond], 0, dest);
+    tcg_out_ext8u(s, dest, dest);
+}
+#else
+static void tcg_out_setcond2(TCGContext *s, const TCGArg *args,
+                             const int *const_args)
+{
+    TCGArg new_args[6];
+    TCGLabel *label_true, *label_over;
+
+    memcpy(new_args, args+1, 5*sizeof(TCGArg));
+
+    if (args[0] == args[1] || args[0] == args[2]
+        || (!const_args[3] && args[0] == args[3])
+        || (!const_args[4] && args[0] == args[4])) {
+        /* When the destination overlaps with one of the argument
+           registers, don't do anything tricky.  */
+        label_true = gen_new_label();
+        label_over = gen_new_label();
+
+        new_args[5] = label_arg(label_true);
+        tcg_out_brcond2(s, new_args, const_args+1, 1);
+
+        tcg_out_movi(s, TCG_TYPE_I32, args[0], 0);
+        tcg_out_jxx(s, JCC_JMP, label_over, 1);
+        tcg_out_label(s, label_true, s->code_ptr);
+
+        tcg_out_movi(s, TCG_TYPE_I32, args[0], 1);
+        tcg_out_label(s, label_over, s->code_ptr);
+    } else {
+        /* When the destination does not overlap one of the arguments,
+           clear the destination first, jump if cond false, and emit an
+           increment in the true case.  This results in smaller code.  */
+
+        tcg_out_movi(s, TCG_TYPE_I32, args[0], 0);
+
+        label_over = gen_new_label();
+        new_args[4] = tcg_invert_cond(new_args[4]);
+        new_args[5] = label_arg(label_over);
+        tcg_out_brcond2(s, new_args, const_args+1, 1);
+
+        tgen_arithi(s, ARITH_ADD, args[0], 1, 0);
+        tcg_out_label(s, label_over, s->code_ptr);
+    }
+}
+#endif
+
+static void tcg_out_movcond32(TCGContext *s, TCGCond cond, TCGArg dest,
+                              TCGArg c1, TCGArg c2, int const_c2,
+                              TCGArg v1)
+{
+    tcg_out_cmp(s, c1, c2, const_c2, 0);
+    if (have_cmov) {
+        tcg_out_modrm(s, OPC_CMOVCC | tcg_cond_to_jcc[cond], dest, v1);
+    } else {
+        TCGLabel *over = gen_new_label();
+        tcg_out_jxx(s, tcg_cond_to_jcc[tcg_invert_cond(cond)], over, 1);
+        tcg_out_mov(s, TCG_TYPE_I32, dest, v1);
+        tcg_out_label(s, over, s->code_ptr);
+    }
+}
+
+#if TCG_TARGET_REG_BITS == 64
+static void tcg_out_movcond64(TCGContext *s, TCGCond cond, TCGArg dest,
+                              TCGArg c1, TCGArg c2, int const_c2,
+                              TCGArg v1)
+{
+    tcg_out_cmp(s, c1, c2, const_c2, P_REXW);
+    tcg_out_modrm(s, OPC_CMOVCC | tcg_cond_to_jcc[cond] | P_REXW, dest, v1);
+}
+#endif
+
+static void tcg_out_branch(TCGContext *s, int call, tcg_insn_unit *dest)
+{
+    intptr_t disp = tcg_pcrel_diff(s, dest) - 5;
+
+    if (disp == (int32_t)disp) {
+        tcg_out_opc(s, call ? OPC_CALL_Jz : OPC_JMP_long, 0, 0, 0);
+        tcg_out32(s, disp);
+    } else {
+        tcg_out_movi(s, TCG_TYPE_PTR, TCG_REG_R10, (uintptr_t)dest);
+        tcg_out_modrm(s, OPC_GRP5,
+                      call ? EXT5_CALLN_Ev : EXT5_JMPN_Ev, TCG_REG_R10);
+    }
+}
+
+static inline void tcg_out_call(TCGContext *s, tcg_insn_unit *dest)
+{
+    tcg_out_branch(s, 1, dest);
+}
+
+static void tcg_out_jmp(TCGContext *s, tcg_insn_unit *dest)
+{
+    tcg_out_branch(s, 0, dest);
+}
+
+#if defined(CONFIG_SOFTMMU)
+/* helper signature: helper_ret_ld_mmu(CPUState *env, target_ulong addr,
+ *                                     int mmu_idx, uintptr_t ra)
+ */
+static void * const qemu_ld_helpers[16] = {
+    [MO_UB]   = helper_ret_ldub_mmu,
+    [MO_LEUW] = helper_le_lduw_mmu,
+    [MO_LEUL] = helper_le_ldul_mmu,
+    [MO_LEQ]  = helper_le_ldq_mmu,
+    [MO_BEUW] = helper_be_lduw_mmu,
+    [MO_BEUL] = helper_be_ldul_mmu,
+    [MO_BEQ]  = helper_be_ldq_mmu,
+};
+
+/* helper signature: helper_ret_st_mmu(CPUState *env, target_ulong addr,
+ *                                     uintxx_t val, int mmu_idx, uintptr_t ra)
+ */
+static void * const qemu_st_helpers[16] = {
+    [MO_UB]   = helper_ret_stb_mmu,
+    [MO_LEUW] = helper_le_stw_mmu,
+    [MO_LEUL] = helper_le_stl_mmu,
+    [MO_LEQ]  = helper_le_stq_mmu,
+    [MO_BEUW] = helper_be_stw_mmu,
+    [MO_BEUL] = helper_be_stl_mmu,
+    [MO_BEQ]  = helper_be_stq_mmu,
+};
+
+/* Perform the TLB load and compare.
+
+   Inputs:
+   ADDRLO and ADDRHI contain the low and high part of the address.
+
+   MEM_INDEX and S_BITS are the memory context and log2 size of the load.
+
+   WHICH is the offset into the CPUTLBEntry structure of the slot to read.
+   This should be offsetof addr_read or addr_write.
+
+   Outputs:
+   LABEL_PTRS is filled with 1 (32-bit addresses) or 2 (64-bit addresses)
+   positions of the displacements of forward jumps to the TLB miss case.
+
+   Second argument register is loaded with the low part of the address.
+   In the TLB hit case, it has been adjusted as indicated by the TLB
+   and so is a host address.  In the TLB miss case, it continues to
+   hold a guest address.
+
+   First argument register is clobbered.  */
+
+static inline void tcg_out_tlb_load(TCGContext *s, TCGReg addrlo, TCGReg addrhi,
+                                    int mem_index, TCGMemOp s_bits,
+                                    tcg_insn_unit **label_ptr, int which)
+{
+    const TCGReg r0 = TCG_REG_L0;
+    const TCGReg r1 = TCG_REG_L1;
+    TCGType ttype = TCG_TYPE_I32;
+    TCGType htype = TCG_TYPE_I32;
+    int trexw = 0, hrexw = 0;
+
+    if (TCG_TARGET_REG_BITS == 64) {
+        if (TARGET_LONG_BITS == 64) {
+            ttype = TCG_TYPE_I64;
+            trexw = P_REXW;
+        }
+        if (TCG_TYPE_PTR == TCG_TYPE_I64) {
+            htype = TCG_TYPE_I64;
+            hrexw = P_REXW;
+        }
+    }
+
+    tcg_out_mov(s, htype, r0, addrlo);
+    tcg_out_mov(s, ttype, r1, addrlo);
+
+    tcg_out_shifti(s, SHIFT_SHR + hrexw, r0,
+                   TARGET_PAGE_BITS - CPU_TLB_ENTRY_BITS);
+
+    tgen_arithi(s, ARITH_AND + trexw, r1,
+                TARGET_PAGE_MASK | ((1 << s_bits) - 1), 0);
+    tgen_arithi(s, ARITH_AND + hrexw, r0,
+                (CPU_TLB_SIZE - 1) << CPU_TLB_ENTRY_BITS, 0);
+
+    tcg_out_modrm_sib_offset(s, OPC_LEA + hrexw, r0, TCG_AREG0, r0, 0,
+                             offsetof(CPUArchState, tlb_table[mem_index][0])
+                             + which);
+
+    /* cmp 0(r0), r1 */
+    tcg_out_modrm_offset(s, OPC_CMP_GvEv + trexw, r1, r0, 0);
+
+    /* Prepare for both the fast path add of the tlb addend, and the slow
+       path function argument setup.  There are two cases worth note:
+       For 32-bit guest and x86_64 host, MOVL zero-extends the guest address
+       before the fastpath ADDQ below.  For 64-bit guest and x32 host, MOVQ
+       copies the entire guest address for the slow path, while truncation
+       for the 32-bit host happens with the fastpath ADDL below.  */
+    tcg_out_mov(s, ttype, r1, addrlo);
+
+    /* jne slow_path */
+    tcg_out_opc(s, OPC_JCC_long + JCC_JNE, 0, 0, 0);
+    label_ptr[0] = s->code_ptr;
+    s->code_ptr += 4;
+
+    if (TARGET_LONG_BITS > TCG_TARGET_REG_BITS) {
+        /* cmp 4(r0), addrhi */
+        tcg_out_modrm_offset(s, OPC_CMP_GvEv, addrhi, r0, 4);
+
+        /* jne slow_path */
+        tcg_out_opc(s, OPC_JCC_long + JCC_JNE, 0, 0, 0);
+        label_ptr[1] = s->code_ptr;
+        s->code_ptr += 4;
+    }
+
+    /* TLB Hit.  */
+
+    /* add addend(r0), r1 */
+    tcg_out_modrm_offset(s, OPC_ADD_GvEv + hrexw, r1, r0,
+                         offsetof(CPUTLBEntry, addend) - which);
+}
+
+/*
+ * Record the context of a call to the out of line helper code for the slow path
+ * for a load or store, so that we can later generate the correct helper code
+ */
+static void add_qemu_ldst_label(TCGContext *s, bool is_ld, TCGMemOpIdx oi,
+                                TCGReg datalo, TCGReg datahi,
+                                TCGReg addrlo, TCGReg addrhi,
+                                tcg_insn_unit *raddr,
+                                tcg_insn_unit **label_ptr)
+{
+    TCGLabelQemuLdst *label = new_ldst_label(s);
+
+    label->is_ld = is_ld;
+    label->oi = oi;
+    label->datalo_reg = datalo;
+    label->datahi_reg = datahi;
+    label->addrlo_reg = addrlo;
+    label->addrhi_reg = addrhi;
+    label->raddr = raddr;
+    label->label_ptr[0] = label_ptr[0];
+    if (TARGET_LONG_BITS > TCG_TARGET_REG_BITS) {
+        label->label_ptr[1] = label_ptr[1];
+    }
+}
+
+/*
+ * Generate code for the slow path for a load at the end of block
+ */
+static void tcg_out_qemu_ld_slow_path(TCGContext *s, TCGLabelQemuLdst *l)
+{
+    TCGMemOpIdx oi = l->oi;
+    TCGMemOp opc = get_memop(oi);
+    TCGReg data_reg;
+    tcg_insn_unit **label_ptr = &l->label_ptr[0];
+
+    /* resolve label address */
+    tcg_patch32(label_ptr[0], s->code_ptr - label_ptr[0] - 4);
+    if (TARGET_LONG_BITS > TCG_TARGET_REG_BITS) {
+        tcg_patch32(label_ptr[1], s->code_ptr - label_ptr[1] - 4);
+    }
+
+    if (TCG_TARGET_REG_BITS == 32) {
+        int ofs = 0;
+
+        tcg_out_st(s, TCG_TYPE_PTR, TCG_AREG0, TCG_REG_ESP, ofs);
+        ofs += 4;
+
+        tcg_out_st(s, TCG_TYPE_I32, l->addrlo_reg, TCG_REG_ESP, ofs);
+        ofs += 4;
+
+        if (TARGET_LONG_BITS == 64) {
+            tcg_out_st(s, TCG_TYPE_I32, l->addrhi_reg, TCG_REG_ESP, ofs);
+            ofs += 4;
+        }
+
+        tcg_out_sti(s, TCG_TYPE_I32, TCG_REG_ESP, ofs, oi);
+        ofs += 4;
+
+        tcg_out_sti(s, TCG_TYPE_PTR, TCG_REG_ESP, ofs, (uintptr_t)l->raddr);
+    } else {
+        tcg_out_mov(s, TCG_TYPE_PTR, tcg_target_call_iarg_regs[0], TCG_AREG0);
+        /* The second argument is already loaded with addrlo.  */
+        tcg_out_movi(s, TCG_TYPE_I32, tcg_target_call_iarg_regs[2], oi);
+        tcg_out_movi(s, TCG_TYPE_PTR, tcg_target_call_iarg_regs[3],
+                     (uintptr_t)l->raddr);
+    }
+
+    tcg_out_call(s, qemu_ld_helpers[opc & (MO_BSWAP | MO_SIZE)]);
+
+    data_reg = l->datalo_reg;
+    switch (opc & MO_SSIZE) {
+    case MO_SB:
+        tcg_out_ext8s(s, data_reg, TCG_REG_EAX, P_REXW);
+        break;
+    case MO_SW:
+        tcg_out_ext16s(s, data_reg, TCG_REG_EAX, P_REXW);
+        break;
+#if TCG_TARGET_REG_BITS == 64
+    case MO_SL:
+        tcg_out_ext32s(s, data_reg, TCG_REG_EAX);
+        break;
+#endif
+    case MO_UB:
+    case MO_UW:
+        /* Note that the helpers have zero-extended to tcg_target_long.  */
+    case MO_UL:
+        tcg_out_mov(s, TCG_TYPE_I32, data_reg, TCG_REG_EAX);
+        break;
+    case MO_Q:
+        if (TCG_TARGET_REG_BITS == 64) {
+            tcg_out_mov(s, TCG_TYPE_I64, data_reg, TCG_REG_RAX);
+        } else if (data_reg == TCG_REG_EDX) {
+            /* xchg %edx, %eax */
+            tcg_out_opc(s, OPC_XCHG_ax_r32 + TCG_REG_EDX, 0, 0, 0);
+            tcg_out_mov(s, TCG_TYPE_I32, l->datahi_reg, TCG_REG_EAX);
+        } else {
+            tcg_out_mov(s, TCG_TYPE_I32, data_reg, TCG_REG_EAX);
+            tcg_out_mov(s, TCG_TYPE_I32, l->datahi_reg, TCG_REG_EDX);
+        }
+        break;
+    default:
+        tcg_abort();
+    }
+
+    /* Jump to the code corresponding to next IR of qemu_st */
+    tcg_out_jmp(s, l->raddr);
+}
+
+/*
+ * Generate code for the slow path for a store at the end of block
+ */
+static void tcg_out_qemu_st_slow_path(TCGContext *s, TCGLabelQemuLdst *l)
+{
+    TCGMemOpIdx oi = l->oi;
+    TCGMemOp opc = get_memop(oi);
+    TCGMemOp s_bits = opc & MO_SIZE;
+    tcg_insn_unit **label_ptr = &l->label_ptr[0];
+    TCGReg retaddr;
+
+    /* resolve label address */
+    tcg_patch32(label_ptr[0], s->code_ptr - label_ptr[0] - 4);
+    if (TARGET_LONG_BITS > TCG_TARGET_REG_BITS) {
+        tcg_patch32(label_ptr[1], s->code_ptr - label_ptr[1] - 4);
+    }
+
+    if (TCG_TARGET_REG_BITS == 32) {
+        int ofs = 0;
+
+        tcg_out_st(s, TCG_TYPE_PTR, TCG_AREG0, TCG_REG_ESP, ofs);
+        ofs += 4;
+
+        tcg_out_st(s, TCG_TYPE_I32, l->addrlo_reg, TCG_REG_ESP, ofs);
+        ofs += 4;
+
+        if (TARGET_LONG_BITS == 64) {
+            tcg_out_st(s, TCG_TYPE_I32, l->addrhi_reg, TCG_REG_ESP, ofs);
+            ofs += 4;
+        }
+
+        tcg_out_st(s, TCG_TYPE_I32, l->datalo_reg, TCG_REG_ESP, ofs);
+        ofs += 4;
+
+        if (s_bits == MO_64) {
+            tcg_out_st(s, TCG_TYPE_I32, l->datahi_reg, TCG_REG_ESP, ofs);
+            ofs += 4;
+        }
+
+        tcg_out_sti(s, TCG_TYPE_I32, TCG_REG_ESP, ofs, oi);
+        ofs += 4;
+
+        retaddr = TCG_REG_EAX;
+        tcg_out_movi(s, TCG_TYPE_PTR, retaddr, (uintptr_t)l->raddr);
+        tcg_out_st(s, TCG_TYPE_PTR, retaddr, TCG_REG_ESP, ofs);
+    } else {
+        tcg_out_mov(s, TCG_TYPE_PTR, tcg_target_call_iarg_regs[0], TCG_AREG0);
+        /* The second argument is already loaded with addrlo.  */
+        tcg_out_mov(s, (s_bits == MO_64 ? TCG_TYPE_I64 : TCG_TYPE_I32),
+                    tcg_target_call_iarg_regs[2], l->datalo_reg);
+        tcg_out_movi(s, TCG_TYPE_I32, tcg_target_call_iarg_regs[3], oi);
+
+        if (ARRAY_SIZE(tcg_target_call_iarg_regs) > 4) {
+            retaddr = tcg_target_call_iarg_regs[4];
+            tcg_out_movi(s, TCG_TYPE_PTR, retaddr, (uintptr_t)l->raddr);
+        } else {
+            retaddr = TCG_REG_RAX;
+            tcg_out_movi(s, TCG_TYPE_PTR, retaddr, (uintptr_t)l->raddr);
+            tcg_out_st(s, TCG_TYPE_PTR, retaddr, TCG_REG_ESP,
+                       TCG_TARGET_CALL_STACK_OFFSET);
+        }
+    }
+
+    /* "Tail call" to the helper, with the return address back inline.  */
+    tcg_out_push(s, retaddr);
+    tcg_out_jmp(s, qemu_st_helpers[opc & (MO_BSWAP | MO_SIZE)]);
+}
+#elif defined(__x86_64__) && defined(__linux__)
+# include <asm/prctl.h>
+# include <sys/prctl.h>
+
+int arch_prctl(int code, unsigned long addr);
+
+static int guest_base_flags;
+static inline void setup_guest_base_seg(void)
+{
+    if (arch_prctl(ARCH_SET_GS, GUEST_BASE) == 0) {
+        guest_base_flags = P_GS;
+    }
+}
+#else
+# define guest_base_flags 0
+static inline void setup_guest_base_seg(void) { }
+#endif /* SOFTMMU */
+
+static void tcg_out_qemu_ld_direct(TCGContext *s, TCGReg datalo, TCGReg datahi,
+                                   TCGReg base, int index, intptr_t ofs,
+                                   int seg, TCGMemOp memop)
+{
+    const TCGMemOp real_bswap = memop & MO_BSWAP;
+    TCGMemOp bswap = real_bswap;
+    int movop = OPC_MOVL_GvEv;
+
+    if (have_movbe && real_bswap) {
+        bswap = 0;
+        movop = OPC_MOVBE_GyMy;
+    }
+
+    switch (memop & MO_SSIZE) {
+    case MO_UB:
+        tcg_out_modrm_sib_offset(s, OPC_MOVZBL + seg, datalo,
+                                 base, index, 0, ofs);
+        break;
+    case MO_SB:
+        tcg_out_modrm_sib_offset(s, OPC_MOVSBL + P_REXW + seg, datalo,
+                                 base, index, 0, ofs);
+        break;
+    case MO_UW:
+        tcg_out_modrm_sib_offset(s, OPC_MOVZWL + seg, datalo,
+                                 base, index, 0, ofs);
+        if (real_bswap) {
+            tcg_out_rolw_8(s, datalo);
+        }
+        break;
+    case MO_SW:
+        if (real_bswap) {
+            if (have_movbe) {
+                tcg_out_modrm_sib_offset(s, OPC_MOVBE_GyMy + P_DATA16 + seg,
+                                         datalo, base, index, 0, ofs);
+            } else {
+                tcg_out_modrm_sib_offset(s, OPC_MOVZWL + seg, datalo,
+                                         base, index, 0, ofs);
+                tcg_out_rolw_8(s, datalo);
+            }
+            tcg_out_modrm(s, OPC_MOVSWL + P_REXW, datalo, datalo);
+        } else {
+            tcg_out_modrm_sib_offset(s, OPC_MOVSWL + P_REXW + seg,
+                                     datalo, base, index, 0, ofs);
+        }
+        break;
+    case MO_UL:
+        tcg_out_modrm_sib_offset(s, movop + seg, datalo, base, index, 0, ofs);
+        if (bswap) {
+            tcg_out_bswap32(s, datalo);
+        }
+        break;
+#if TCG_TARGET_REG_BITS == 64
+    case MO_SL:
+        if (real_bswap) {
+            tcg_out_modrm_sib_offset(s, movop + seg, datalo,
+                                     base, index, 0, ofs);
+            if (bswap) {
+                tcg_out_bswap32(s, datalo);
+            }
+            tcg_out_ext32s(s, datalo, datalo);
+        } else {
+            tcg_out_modrm_sib_offset(s, OPC_MOVSLQ + seg, datalo,
+                                     base, index, 0, ofs);
+        }
+        break;
+#endif
+    case MO_Q:
+        if (TCG_TARGET_REG_BITS == 64) {
+            tcg_out_modrm_sib_offset(s, movop + P_REXW + seg, datalo,
+                                     base, index, 0, ofs);
+            if (bswap) {
+                tcg_out_bswap64(s, datalo);
+            }
+        } else {
+            if (real_bswap) {
+                int t = datalo;
+                datalo = datahi;
+                datahi = t;
+            }
+            if (base != datalo) {
+                tcg_out_modrm_sib_offset(s, movop + seg, datalo,
+                                         base, index, 0, ofs);
+                tcg_out_modrm_sib_offset(s, movop + seg, datahi,
+                                         base, index, 0, ofs + 4);
+            } else {
+                tcg_out_modrm_sib_offset(s, movop + seg, datahi,
+                                         base, index, 0, ofs + 4);
+                tcg_out_modrm_sib_offset(s, movop + seg, datalo,
+                                         base, index, 0, ofs);
+            }
+            if (bswap) {
+                tcg_out_bswap32(s, datalo);
+                tcg_out_bswap32(s, datahi);
+            }
+        }
+        break;
+    default:
+        tcg_abort();
+    }
+}
+
+/* XXX: qemu_ld and qemu_st could be modified to clobber only EDX and
+   EAX. It will be useful once fixed registers globals are less
+   common. */
+static void tcg_out_qemu_ld(TCGContext *s, const TCGArg *args, bool is64)
+{
+    TCGReg datalo, datahi, addrlo;
+    TCGReg addrhi __attribute__((unused));
+    TCGMemOpIdx oi;
+    TCGMemOp opc;
+#if defined(CONFIG_SOFTMMU)
+    int mem_index;
+    TCGMemOp s_bits;
+    tcg_insn_unit *label_ptr[2];
+#endif
+
+    datalo = *args++;
+    datahi = (TCG_TARGET_REG_BITS == 32 && is64 ? *args++ : 0);
+    addrlo = *args++;
+    addrhi = (TARGET_LONG_BITS > TCG_TARGET_REG_BITS ? *args++ : 0);
+    oi = *args++;
+    opc = get_memop(oi);
+
+#if defined(CONFIG_SOFTMMU)
+    mem_index = get_mmuidx(oi);
+    s_bits = opc & MO_SIZE;
+
+    tcg_out_tlb_load(s, addrlo, addrhi, mem_index, s_bits,
+                     label_ptr, offsetof(CPUTLBEntry, addr_read));
+
+    /* TLB Hit.  */
+    tcg_out_qemu_ld_direct(s, datalo, datahi, TCG_REG_L1, -1, 0, 0, opc);
+
+    /* Record the current context of a load into ldst label */
+    add_qemu_ldst_label(s, true, oi, datalo, datahi, addrlo, addrhi,
+                        s->code_ptr, label_ptr);
+#else
+    {
+        int32_t offset = GUEST_BASE;
+        TCGReg base = addrlo;
+        int index = -1;
+        int seg = 0;
+
+        /* For a 32-bit guest, the high 32 bits may contain garbage.
+           We can do this with the ADDR32 prefix if we're not using
+           a guest base, or when using segmentation.  Otherwise we
+           need to zero-extend manually.  */
+        if (GUEST_BASE == 0 || guest_base_flags) {
+            seg = guest_base_flags;
+            offset = 0;
+            if (TCG_TARGET_REG_BITS > TARGET_LONG_BITS) {
+                seg |= P_ADDR32;
+            }
+        } else if (TCG_TARGET_REG_BITS == 64) {
+            if (TARGET_LONG_BITS == 32) {
+                tcg_out_ext32u(s, TCG_REG_L0, base);
+                base = TCG_REG_L0;
+            }
+            if (offset != GUEST_BASE) {
+                tcg_out_movi(s, TCG_TYPE_I64, TCG_REG_L1, GUEST_BASE);
+                index = TCG_REG_L1;
+                offset = 0;
+            }
+        }
+
+        tcg_out_qemu_ld_direct(s, datalo, datahi,
+                               base, index, offset, seg, opc);
+    }
+#endif
+}
+
+static void tcg_out_qemu_st_direct(TCGContext *s, TCGReg datalo, TCGReg datahi,
+                                   TCGReg base, intptr_t ofs, int seg,
+                                   TCGMemOp memop)
+{
+    /* ??? Ideally we wouldn't need a scratch register.  For user-only,
+       we could perform the bswap twice to restore the original value
+       instead of moving to the scratch.  But as it is, the L constraint
+       means that TCG_REG_L0 is definitely free here.  */
+    const TCGReg scratch = TCG_REG_L0;
+    const TCGMemOp real_bswap = memop & MO_BSWAP;
+    TCGMemOp bswap = real_bswap;
+    int movop = OPC_MOVL_EvGv;
+
+    if (have_movbe && real_bswap) {
+        bswap = 0;
+        movop = OPC_MOVBE_MyGy;
+    }
+
+    switch (memop & MO_SIZE) {
+    case MO_8:
+        /* In 32-bit mode, 8-bit stores can only happen from [abcd]x.
+           Use the scratch register if necessary.  */
+        if (TCG_TARGET_REG_BITS == 32 && datalo >= 4) {
+            tcg_out_mov(s, TCG_TYPE_I32, scratch, datalo);
+            datalo = scratch;
+        }
+        tcg_out_modrm_offset(s, OPC_MOVB_EvGv + P_REXB_R + seg,
+                             datalo, base, ofs);
+        break;
+    case MO_16:
+        if (bswap) {
+            tcg_out_mov(s, TCG_TYPE_I32, scratch, datalo);
+            tcg_out_rolw_8(s, scratch);
+            datalo = scratch;
+        }
+        tcg_out_modrm_offset(s, movop + P_DATA16 + seg, datalo, base, ofs);
+        break;
+    case MO_32:
+        if (bswap) {
+            tcg_out_mov(s, TCG_TYPE_I32, scratch, datalo);
+            tcg_out_bswap32(s, scratch);
+            datalo = scratch;
+        }
+        tcg_out_modrm_offset(s, movop + seg, datalo, base, ofs);
+        break;
+    case MO_64:
+        if (TCG_TARGET_REG_BITS == 64) {
+            if (bswap) {
+                tcg_out_mov(s, TCG_TYPE_I64, scratch, datalo);
+                tcg_out_bswap64(s, scratch);
+                datalo = scratch;
+            }
+            tcg_out_modrm_offset(s, movop + P_REXW + seg, datalo, base, ofs);
+        } else if (bswap) {
+            tcg_out_mov(s, TCG_TYPE_I32, scratch, datahi);
+            tcg_out_bswap32(s, scratch);
+            tcg_out_modrm_offset(s, OPC_MOVL_EvGv + seg, scratch, base, ofs);
+            tcg_out_mov(s, TCG_TYPE_I32, scratch, datalo);
+            tcg_out_bswap32(s, scratch);
+            tcg_out_modrm_offset(s, OPC_MOVL_EvGv + seg, scratch, base, ofs+4);
+        } else {
+            if (real_bswap) {
+                int t = datalo;
+                datalo = datahi;
+                datahi = t;
+            }
+            tcg_out_modrm_offset(s, movop + seg, datalo, base, ofs);
+            tcg_out_modrm_offset(s, movop + seg, datahi, base, ofs+4);
+        }
+        break;
+    default:
+        tcg_abort();
+    }
+}
+
+static void tcg_out_qemu_st(TCGContext *s, const TCGArg *args, bool is64)
+{
+    TCGReg datalo, datahi, addrlo;
+    TCGReg addrhi __attribute__((unused));
+    TCGMemOpIdx oi;
+    TCGMemOp opc;
+#if defined(CONFIG_SOFTMMU)
+    int mem_index;
+    TCGMemOp s_bits;
+    tcg_insn_unit *label_ptr[2];
+#endif
+
+    datalo = *args++;
+    datahi = (TCG_TARGET_REG_BITS == 32 && is64 ? *args++ : 0);
+    addrlo = *args++;
+    addrhi = (TARGET_LONG_BITS > TCG_TARGET_REG_BITS ? *args++ : 0);
+    oi = *args++;
+    opc = get_memop(oi);
+
+#if defined(CONFIG_SOFTMMU)
+    mem_index = get_mmuidx(oi);
+    s_bits = opc & MO_SIZE;
+
+    tcg_out_tlb_load(s, addrlo, addrhi, mem_index, s_bits,
+                     label_ptr, offsetof(CPUTLBEntry, addr_write));
+
+    /* TLB Hit.  */
+    tcg_out_qemu_st_direct(s, datalo, datahi, TCG_REG_L1, 0, 0, opc);
+
+    /* Record the current context of a store into ldst label */
+    add_qemu_ldst_label(s, false, oi, datalo, datahi, addrlo, addrhi,
+                        s->code_ptr, label_ptr);
+#else
+    {
+        int32_t offset = GUEST_BASE;
+        TCGReg base = addrlo;
+        int seg = 0;
+
+        /* See comment in tcg_out_qemu_ld re zero-extension of addrlo.  */
+        if (GUEST_BASE == 0 || guest_base_flags) {
+            seg = guest_base_flags;
+            offset = 0;
+            if (TCG_TARGET_REG_BITS > TARGET_LONG_BITS) {
+                seg |= P_ADDR32;
+            }
+        } else if (TCG_TARGET_REG_BITS == 64) {
+            /* ??? Note that we can't use the same SIB addressing scheme
+               as for loads, since we require L0 free for bswap.  */
+            if (offset != GUEST_BASE) {
+                if (TARGET_LONG_BITS == 32) {
+                    tcg_out_ext32u(s, TCG_REG_L0, base);
+                    base = TCG_REG_L0;
+                }
+                tcg_out_movi(s, TCG_TYPE_I64, TCG_REG_L1, GUEST_BASE);
+                tgen_arithr(s, ARITH_ADD + P_REXW, TCG_REG_L1, base);
+                base = TCG_REG_L1;
+                offset = 0;
+            } else if (TARGET_LONG_BITS == 32) {
+                tcg_out_ext32u(s, TCG_REG_L1, base);
+                base = TCG_REG_L1;
+            }
+        }
+
+        tcg_out_qemu_st_direct(s, datalo, datahi, base, offset, seg, opc);
+    }
+#endif
+}
+
+static inline void tcg_out_op(TCGContext *s, TCGOpcode opc,
+                              const TCGArg *args, const int *const_args)
+{
+    int c, vexop, rexw = 0;
+
+#if TCG_TARGET_REG_BITS == 64
+# define OP_32_64(x) \
+        case glue(glue(INDEX_op_, x), _i64): \
+            rexw = P_REXW; /* FALLTHRU */    \
+        case glue(glue(INDEX_op_, x), _i32)
+#else
+# define OP_32_64(x) \
+        case glue(glue(INDEX_op_, x), _i32)
+#endif
+
+    switch(opc) {
+    case INDEX_op_exit_tb:
+        tcg_out_movi(s, TCG_TYPE_PTR, TCG_REG_EAX, args[0]);
+        tcg_out_jmp(s, tb_ret_addr);
+        break;
+    case INDEX_op_goto_tb:
+        if (s->tb_jmp_offset) {
+            /* direct jump method */
+            tcg_out8(s, OPC_JMP_long); /* jmp im */
+            s->tb_jmp_offset[args[0]] = tcg_current_code_size(s);
+            tcg_out32(s, 0);
+        } else {
+            /* indirect jump method */
+            tcg_out_modrm_offset(s, OPC_GRP5, EXT5_JMPN_Ev, -1,
+                                 (intptr_t)(s->tb_next + args[0]));
+        }
+        s->tb_next_offset[args[0]] = tcg_current_code_size(s);
+        break;
+    case INDEX_op_br:
+        tcg_out_jxx(s, JCC_JMP, arg_label(args[0]), 0);
+        break;
+    OP_32_64(ld8u):
+        /* Note that we can ignore REXW for the zero-extend to 64-bit.  */
+        tcg_out_modrm_offset(s, OPC_MOVZBL, args[0], args[1], args[2]);
+        break;
+    OP_32_64(ld8s):
+        tcg_out_modrm_offset(s, OPC_MOVSBL + rexw, args[0], args[1], args[2]);
+        break;
+    OP_32_64(ld16u):
+        /* Note that we can ignore REXW for the zero-extend to 64-bit.  */
+        tcg_out_modrm_offset(s, OPC_MOVZWL, args[0], args[1], args[2]);
+        break;
+    OP_32_64(ld16s):
+        tcg_out_modrm_offset(s, OPC_MOVSWL + rexw, args[0], args[1], args[2]);
+        break;
+#if TCG_TARGET_REG_BITS == 64
+    case INDEX_op_ld32u_i64:
+#endif
+    case INDEX_op_ld_i32:
+        tcg_out_ld(s, TCG_TYPE_I32, args[0], args[1], args[2]);
+        break;
+
+    OP_32_64(st8):
+        if (const_args[0]) {
+            tcg_out_modrm_offset(s, OPC_MOVB_EvIz,
+                                 0, args[1], args[2]);
+            tcg_out8(s, args[0]);
+        } else {
+            tcg_out_modrm_offset(s, OPC_MOVB_EvGv | P_REXB_R,
+                                 args[0], args[1], args[2]);
+        }
+        break;
+    OP_32_64(st16):
+        if (const_args[0]) {
+            tcg_out_modrm_offset(s, OPC_MOVL_EvIz | P_DATA16,
+                                 0, args[1], args[2]);
+            tcg_out16(s, args[0]);
+        } else {
+            tcg_out_modrm_offset(s, OPC_MOVL_EvGv | P_DATA16,
+                                 args[0], args[1], args[2]);
+        }
+        break;
+#if TCG_TARGET_REG_BITS == 64
+    case INDEX_op_st32_i64:
+#endif
+    case INDEX_op_st_i32:
+        if (const_args[0]) {
+            tcg_out_modrm_offset(s, OPC_MOVL_EvIz, 0, args[1], args[2]);
+            tcg_out32(s, args[0]);
+        } else {
+            tcg_out_st(s, TCG_TYPE_I32, args[0], args[1], args[2]);
+        }
+        break;
+
+    OP_32_64(add):
+        /* For 3-operand addition, use LEA.  */
+        if (args[0] != args[1]) {
+            TCGArg a0 = args[0], a1 = args[1], a2 = args[2], c3 = 0;
+
+            if (const_args[2]) {
+                c3 = a2, a2 = -1;
+            } else if (a0 == a2) {
+                /* Watch out for dest = src + dest, since we've removed
+                   the matching constraint on the add.  */
+                tgen_arithr(s, ARITH_ADD + rexw, a0, a1);
+                break;
+            }
+
+            tcg_out_modrm_sib_offset(s, OPC_LEA + rexw, a0, a1, a2, 0, c3);
+            break;
+        }
+        c = ARITH_ADD;
+        goto gen_arith;
+    OP_32_64(sub):
+        c = ARITH_SUB;
+        goto gen_arith;
+    OP_32_64(and):
+        c = ARITH_AND;
+        goto gen_arith;
+    OP_32_64(or):
+        c = ARITH_OR;
+        goto gen_arith;
+    OP_32_64(xor):
+        c = ARITH_XOR;
+        goto gen_arith;
+    gen_arith:
+        if (const_args[2]) {
+            tgen_arithi(s, c + rexw, args[0], args[2], 0);
+        } else {
+            tgen_arithr(s, c + rexw, args[0], args[2]);
+        }
+        break;
+
+    OP_32_64(andc):
+        if (const_args[2]) {
+            tcg_out_mov(s, rexw ? TCG_TYPE_I64 : TCG_TYPE_I32,
+                        args[0], args[1]);
+            tgen_arithi(s, ARITH_AND + rexw, args[0], ~args[2], 0);
+        } else {
+            tcg_out_vex_modrm(s, OPC_ANDN + rexw, args[0], args[2], args[1]);
+        }
+        break;
+
+    OP_32_64(mul):
+        if (const_args[2]) {
+            int32_t val;
+            val = args[2];
+            if (val == (int8_t)val) {
+                tcg_out_modrm(s, OPC_IMUL_GvEvIb + rexw, args[0], args[0]);
+                tcg_out8(s, val);
+            } else {
+                tcg_out_modrm(s, OPC_IMUL_GvEvIz + rexw, args[0], args[0]);
+                tcg_out32(s, val);
+            }
+        } else {
+            tcg_out_modrm(s, OPC_IMUL_GvEv + rexw, args[0], args[2]);
+        }
+        break;
+
+    OP_32_64(div2):
+        tcg_out_modrm(s, OPC_GRP3_Ev + rexw, EXT3_IDIV, args[4]);
+        break;
+    OP_32_64(divu2):
+        tcg_out_modrm(s, OPC_GRP3_Ev + rexw, EXT3_DIV, args[4]);
+        break;
+
+    OP_32_64(shl):
+        c = SHIFT_SHL;
+        vexop = OPC_SHLX;
+        goto gen_shift_maybe_vex;
+    OP_32_64(shr):
+        c = SHIFT_SHR;
+        vexop = OPC_SHRX;
+        goto gen_shift_maybe_vex;
+    OP_32_64(sar):
+        c = SHIFT_SAR;
+        vexop = OPC_SARX;
+        goto gen_shift_maybe_vex;
+    OP_32_64(rotl):
+        c = SHIFT_ROL;
+        goto gen_shift;
+    OP_32_64(rotr):
+        c = SHIFT_ROR;
+        goto gen_shift;
+    gen_shift_maybe_vex:
+        if (have_bmi2 && !const_args[2]) {
+            tcg_out_vex_modrm(s, vexop + rexw, args[0], args[2], args[1]);
+            break;
+        }
+        /* FALLTHRU */
+    gen_shift:
+        if (const_args[2]) {
+            tcg_out_shifti(s, c + rexw, args[0], args[2]);
+        } else {
+            tcg_out_modrm(s, OPC_SHIFT_cl + rexw, c, args[0]);
+        }
+        break;
+
+    case INDEX_op_brcond_i32:
+        tcg_out_brcond32(s, args[2], args[0], args[1], const_args[1],
+                         arg_label(args[3]), 0);
+        break;
+    case INDEX_op_setcond_i32:
+        tcg_out_setcond32(s, args[3], args[0], args[1],
+                          args[2], const_args[2]);
+        break;
+    case INDEX_op_movcond_i32:
+        tcg_out_movcond32(s, args[5], args[0], args[1],
+                          args[2], const_args[2], args[3]);
+        break;
+
+    OP_32_64(bswap16):
+        tcg_out_rolw_8(s, args[0]);
+        break;
+    OP_32_64(bswap32):
+        tcg_out_bswap32(s, args[0]);
+        break;
+
+    OP_32_64(neg):
+        tcg_out_modrm(s, OPC_GRP3_Ev + rexw, EXT3_NEG, args[0]);
+        break;
+    OP_32_64(not):
+        tcg_out_modrm(s, OPC_GRP3_Ev + rexw, EXT3_NOT, args[0]);
+        break;
+
+    OP_32_64(ext8s):
+        tcg_out_ext8s(s, args[0], args[1], rexw);
+        break;
+    OP_32_64(ext16s):
+        tcg_out_ext16s(s, args[0], args[1], rexw);
+        break;
+    OP_32_64(ext8u):
+        tcg_out_ext8u(s, args[0], args[1]);
+        break;
+    OP_32_64(ext16u):
+        tcg_out_ext16u(s, args[0], args[1]);
+        break;
+
+    case INDEX_op_qemu_ld_i32:
+        tcg_out_qemu_ld(s, args, 0);
+        break;
+    case INDEX_op_qemu_ld_i64:
+        tcg_out_qemu_ld(s, args, 1);
+        break;
+    case INDEX_op_qemu_st_i32:
+        tcg_out_qemu_st(s, args, 0);
+        break;
+    case INDEX_op_qemu_st_i64:
+        tcg_out_qemu_st(s, args, 1);
+        break;
+
+    OP_32_64(mulu2):
+        tcg_out_modrm(s, OPC_GRP3_Ev + rexw, EXT3_MUL, args[3]);
+        break;
+    OP_32_64(muls2):
+        tcg_out_modrm(s, OPC_GRP3_Ev + rexw, EXT3_IMUL, args[3]);
+        break;
+    OP_32_64(add2):
+        if (const_args[4]) {
+            tgen_arithi(s, ARITH_ADD + rexw, args[0], args[4], 1);
+        } else {
+            tgen_arithr(s, ARITH_ADD + rexw, args[0], args[4]);
+        }
+        if (const_args[5]) {
+            tgen_arithi(s, ARITH_ADC + rexw, args[1], args[5], 1);
+        } else {
+            tgen_arithr(s, ARITH_ADC + rexw, args[1], args[5]);
+        }
+        break;
+    OP_32_64(sub2):
+        if (const_args[4]) {
+            tgen_arithi(s, ARITH_SUB + rexw, args[0], args[4], 1);
+        } else {
+            tgen_arithr(s, ARITH_SUB + rexw, args[0], args[4]);
+        }
+        if (const_args[5]) {
+            tgen_arithi(s, ARITH_SBB + rexw, args[1], args[5], 1);
+        } else {
+            tgen_arithr(s, ARITH_SBB + rexw, args[1], args[5]);
+        }
+        break;
+
+#if TCG_TARGET_REG_BITS == 32
+    case INDEX_op_brcond2_i32:
+        tcg_out_brcond2(s, args, const_args, 0);
+        break;
+    case INDEX_op_setcond2_i32:
+        tcg_out_setcond2(s, args, const_args);
+        break;
+#else /* TCG_TARGET_REG_BITS == 64 */
+    case INDEX_op_ld32s_i64:
+        tcg_out_modrm_offset(s, OPC_MOVSLQ, args[0], args[1], args[2]);
+        break;
+    case INDEX_op_ld_i64:
+        tcg_out_ld(s, TCG_TYPE_I64, args[0], args[1], args[2]);
+        break;
+    case INDEX_op_st_i64:
+        if (const_args[0]) {
+            tcg_out_modrm_offset(s, OPC_MOVL_EvIz | P_REXW,
+                                 0, args[1], args[2]);
+            tcg_out32(s, args[0]);
+        } else {
+            tcg_out_st(s, TCG_TYPE_I64, args[0], args[1], args[2]);
+        }
+        break;
+
+    case INDEX_op_brcond_i64:
+        tcg_out_brcond64(s, args[2], args[0], args[1], const_args[1],
+                         arg_label(args[3]), 0);
+        break;
+    case INDEX_op_setcond_i64:
+        tcg_out_setcond64(s, args[3], args[0], args[1],
+                          args[2], const_args[2]);
+        break;
+    case INDEX_op_movcond_i64:
+        tcg_out_movcond64(s, args[5], args[0], args[1],
+                          args[2], const_args[2], args[3]);
+        break;
+
+    case INDEX_op_bswap64_i64:
+        tcg_out_bswap64(s, args[0]);
+        break;
+    case INDEX_op_ext32u_i64:
+        tcg_out_ext32u(s, args[0], args[1]);
+        break;
+    case INDEX_op_ext32s_i64:
+        tcg_out_ext32s(s, args[0], args[1]);
+        break;
+#endif
+
+    OP_32_64(deposit):
+        if (args[3] == 0 && args[4] == 8) {
+            /* load bits 0..7 */
+            tcg_out_modrm(s, OPC_MOVB_EvGv | P_REXB_R | P_REXB_RM,
+                          args[2], args[0]);
+        } else if (args[3] == 8 && args[4] == 8) {
+            /* load bits 8..15 */
+            tcg_out_modrm(s, OPC_MOVB_EvGv, args[2], args[0] + 4);
+        } else if (args[3] == 0 && args[4] == 16) {
+            /* load bits 0..15 */
+            tcg_out_modrm(s, OPC_MOVL_EvGv | P_DATA16, args[2], args[0]);
+        } else {
+            tcg_abort();
+        }
+        break;
+
+    case INDEX_op_mov_i32:  /* Always emitted via tcg_out_mov.  */
+    case INDEX_op_mov_i64:
+    case INDEX_op_movi_i32: /* Always emitted via tcg_out_movi.  */
+    case INDEX_op_movi_i64:
+    case INDEX_op_call:     /* Always emitted via tcg_out_call.  */
+    default:
+        tcg_abort();
+    }
+
+#undef OP_32_64
+}
+
+static const TCGTargetOpDef x86_op_defs[] = {
+    { INDEX_op_exit_tb, { } },
+    { INDEX_op_goto_tb, { } },
+    { INDEX_op_br, { } },
+    { INDEX_op_ld8u_i32, { "r", "r" } },
+    { INDEX_op_ld8s_i32, { "r", "r" } },
+    { INDEX_op_ld16u_i32, { "r", "r" } },
+    { INDEX_op_ld16s_i32, { "r", "r" } },
+    { INDEX_op_ld_i32, { "r", "r" } },
+    { INDEX_op_st8_i32, { "qi", "r" } },
+    { INDEX_op_st16_i32, { "ri", "r" } },
+    { INDEX_op_st_i32, { "ri", "r" } },
+
+    { INDEX_op_add_i32, { "r", "r", "ri" } },
+    { INDEX_op_sub_i32, { "r", "0", "ri" } },
+    { INDEX_op_mul_i32, { "r", "0", "ri" } },
+    { INDEX_op_div2_i32, { "a", "d", "0", "1", "r" } },
+    { INDEX_op_divu2_i32, { "a", "d", "0", "1", "r" } },
+    { INDEX_op_and_i32, { "r", "0", "ri" } },
+    { INDEX_op_or_i32, { "r", "0", "ri" } },
+    { INDEX_op_xor_i32, { "r", "0", "ri" } },
+    { INDEX_op_andc_i32, { "r", "r", "ri" } },
+
+    { INDEX_op_shl_i32, { "r", "0", "Ci" } },
+    { INDEX_op_shr_i32, { "r", "0", "Ci" } },
+    { INDEX_op_sar_i32, { "r", "0", "Ci" } },
+    { INDEX_op_rotl_i32, { "r", "0", "ci" } },
+    { INDEX_op_rotr_i32, { "r", "0", "ci" } },
+
+    { INDEX_op_brcond_i32, { "r", "ri" } },
+
+    { INDEX_op_bswap16_i32, { "r", "0" } },
+    { INDEX_op_bswap32_i32, { "r", "0" } },
+
+    { INDEX_op_neg_i32, { "r", "0" } },
+
+    { INDEX_op_not_i32, { "r", "0" } },
+
+    { INDEX_op_ext8s_i32, { "r", "q" } },
+    { INDEX_op_ext16s_i32, { "r", "r" } },
+    { INDEX_op_ext8u_i32, { "r", "q" } },
+    { INDEX_op_ext16u_i32, { "r", "r" } },
+
+    { INDEX_op_setcond_i32, { "q", "r", "ri" } },
+
+    { INDEX_op_deposit_i32, { "Q", "0", "Q" } },
+    { INDEX_op_movcond_i32, { "r", "r", "ri", "r", "0" } },
+
+    { INDEX_op_mulu2_i32, { "a", "d", "a", "r" } },
+    { INDEX_op_muls2_i32, { "a", "d", "a", "r" } },
+    { INDEX_op_add2_i32, { "r", "r", "0", "1", "ri", "ri" } },
+    { INDEX_op_sub2_i32, { "r", "r", "0", "1", "ri", "ri" } },
+
+#if TCG_TARGET_REG_BITS == 32
+    { INDEX_op_brcond2_i32, { "r", "r", "ri", "ri" } },
+    { INDEX_op_setcond2_i32, { "r", "r", "r", "ri", "ri" } },
+#else
+    { INDEX_op_ld8u_i64, { "r", "r" } },
+    { INDEX_op_ld8s_i64, { "r", "r" } },
+    { INDEX_op_ld16u_i64, { "r", "r" } },
+    { INDEX_op_ld16s_i64, { "r", "r" } },
+    { INDEX_op_ld32u_i64, { "r", "r" } },
+    { INDEX_op_ld32s_i64, { "r", "r" } },
+    { INDEX_op_ld_i64, { "r", "r" } },
+    { INDEX_op_st8_i64, { "ri", "r" } },
+    { INDEX_op_st16_i64, { "ri", "r" } },
+    { INDEX_op_st32_i64, { "ri", "r" } },
+    { INDEX_op_st_i64, { "re", "r" } },
+
+    { INDEX_op_add_i64, { "r", "r", "re" } },
+    { INDEX_op_mul_i64, { "r", "0", "re" } },
+    { INDEX_op_div2_i64, { "a", "d", "0", "1", "r" } },
+    { INDEX_op_divu2_i64, { "a", "d", "0", "1", "r" } },
+    { INDEX_op_sub_i64, { "r", "0", "re" } },
+    { INDEX_op_and_i64, { "r", "0", "reZ" } },
+    { INDEX_op_or_i64, { "r", "0", "re" } },
+    { INDEX_op_xor_i64, { "r", "0", "re" } },
+    { INDEX_op_andc_i64, { "r", "r", "rI" } },
+
+    { INDEX_op_shl_i64, { "r", "0", "Ci" } },
+    { INDEX_op_shr_i64, { "r", "0", "Ci" } },
+    { INDEX_op_sar_i64, { "r", "0", "Ci" } },
+    { INDEX_op_rotl_i64, { "r", "0", "ci" } },
+    { INDEX_op_rotr_i64, { "r", "0", "ci" } },
+
+    { INDEX_op_brcond_i64, { "r", "re" } },
+    { INDEX_op_setcond_i64, { "r", "r", "re" } },
+
+    { INDEX_op_bswap16_i64, { "r", "0" } },
+    { INDEX_op_bswap32_i64, { "r", "0" } },
+    { INDEX_op_bswap64_i64, { "r", "0" } },
+    { INDEX_op_neg_i64, { "r", "0" } },
+    { INDEX_op_not_i64, { "r", "0" } },
+
+    { INDEX_op_ext8s_i64, { "r", "r" } },
+    { INDEX_op_ext16s_i64, { "r", "r" } },
+    { INDEX_op_ext32s_i64, { "r", "r" } },
+    { INDEX_op_ext8u_i64, { "r", "r" } },
+    { INDEX_op_ext16u_i64, { "r", "r" } },
+    { INDEX_op_ext32u_i64, { "r", "r" } },
+
+    { INDEX_op_deposit_i64, { "Q", "0", "Q" } },
+    { INDEX_op_movcond_i64, { "r", "r", "re", "r", "0" } },
+
+    { INDEX_op_mulu2_i64, { "a", "d", "a", "r" } },
+    { INDEX_op_muls2_i64, { "a", "d", "a", "r" } },
+    { INDEX_op_add2_i64, { "r", "r", "0", "1", "re", "re" } },
+    { INDEX_op_sub2_i64, { "r", "r", "0", "1", "re", "re" } },
+#endif
+
+#if TCG_TARGET_REG_BITS == 64
+    { INDEX_op_qemu_ld_i32, { "r", "L" } },
+    { INDEX_op_qemu_st_i32, { "L", "L" } },
+    { INDEX_op_qemu_ld_i64, { "r", "L" } },
+    { INDEX_op_qemu_st_i64, { "L", "L" } },
+#elif TARGET_LONG_BITS <= TCG_TARGET_REG_BITS
+    { INDEX_op_qemu_ld_i32, { "r", "L" } },
+    { INDEX_op_qemu_st_i32, { "L", "L" } },
+    { INDEX_op_qemu_ld_i64, { "r", "r", "L" } },
+    { INDEX_op_qemu_st_i64, { "L", "L", "L" } },
+#else
+    { INDEX_op_qemu_ld_i32, { "r", "L", "L" } },
+    { INDEX_op_qemu_st_i32, { "L", "L", "L" } },
+    { INDEX_op_qemu_ld_i64, { "r", "r", "L", "L" } },
+    { INDEX_op_qemu_st_i64, { "L", "L", "L", "L" } },
+#endif
+    { -1 },
+};
+
+static int tcg_target_callee_save_regs[] = {
+#if TCG_TARGET_REG_BITS == 64
+    TCG_REG_RBP,
+    TCG_REG_RBX,
+#if defined(_WIN64)
+    TCG_REG_RDI,
+    TCG_REG_RSI,
+#endif
+    TCG_REG_R12,
+    TCG_REG_R13,
+    TCG_REG_R14, /* Currently used for the global env. */
+    TCG_REG_R15,
+#else
+    TCG_REG_EBP, /* Currently used for the global env. */
+    TCG_REG_EBX,
+    TCG_REG_ESI,
+    TCG_REG_EDI,
+#endif
+};
+
+/* Compute frame size via macros, to share between tcg_target_qemu_prologue
+   and tcg_register_jit.  */
+
+#define PUSH_SIZE \
+    ((1 + ARRAY_SIZE(tcg_target_callee_save_regs)) \
+     * (TCG_TARGET_REG_BITS / 8))
+
+#define FRAME_SIZE \
+    ((PUSH_SIZE \
+      + TCG_STATIC_CALL_ARGS_SIZE \
+      + CPU_TEMP_BUF_NLONGS * sizeof(long) \
+      + TCG_TARGET_STACK_ALIGN - 1) \
+     & ~(TCG_TARGET_STACK_ALIGN - 1))
+
+/* Generate global QEMU prologue and epilogue code */
+static void tcg_target_qemu_prologue(TCGContext *s)
+{
+    int i, stack_addend;
+
+    /* TB prologue */
+
+    /* Reserve some stack space, also for TCG temps.  */
+    stack_addend = FRAME_SIZE - PUSH_SIZE;
+    tcg_set_frame(s, TCG_REG_CALL_STACK, TCG_STATIC_CALL_ARGS_SIZE,
+                  CPU_TEMP_BUF_NLONGS * sizeof(long));
+
+    /* Save all callee saved registers.  */
+    for (i = 0; i < ARRAY_SIZE(tcg_target_callee_save_regs); i++) {
+        tcg_out_push(s, tcg_target_callee_save_regs[i]);
+    }
+
+#if TCG_TARGET_REG_BITS == 32
+    tcg_out_ld(s, TCG_TYPE_PTR, TCG_AREG0, TCG_REG_ESP,
+               (ARRAY_SIZE(tcg_target_callee_save_regs) + 1) * 4);
+    tcg_out_addi(s, TCG_REG_ESP, -stack_addend);
+    /* jmp *tb.  */
+    tcg_out_modrm_offset(s, OPC_GRP5, EXT5_JMPN_Ev, TCG_REG_ESP,
+		         (ARRAY_SIZE(tcg_target_callee_save_regs) + 2) * 4
+			 + stack_addend);
+#else
+    tcg_out_mov(s, TCG_TYPE_PTR, TCG_AREG0, tcg_target_call_iarg_regs[0]);
+    tcg_out_addi(s, TCG_REG_ESP, -stack_addend);
+    /* jmp *tb.  */
+    tcg_out_modrm(s, OPC_GRP5, EXT5_JMPN_Ev, tcg_target_call_iarg_regs[1]);
+#endif
+
+    /* TB epilogue */
+    tb_ret_addr = s->code_ptr;
+
+    tcg_out_addi(s, TCG_REG_CALL_STACK, stack_addend);
+
+    for (i = ARRAY_SIZE(tcg_target_callee_save_regs) - 1; i >= 0; i--) {
+        tcg_out_pop(s, tcg_target_callee_save_regs[i]);
+    }
+    tcg_out_opc(s, OPC_RET, 0, 0, 0);
+
+#if !defined(CONFIG_SOFTMMU)
+    /* Try to set up a segment register to point to GUEST_BASE.  */
+    if (GUEST_BASE) {
+        setup_guest_base_seg();
+    }
+#endif
+}
+
+static void tcg_target_init(TCGContext *s)
+{
+#ifdef CONFIG_CPUID_H
+    unsigned a, b, c, d;
+    int max = __get_cpuid_max(0, 0);
+
+    if (max >= 1) {
+        __cpuid(1, a, b, c, d);
+#ifndef have_cmov
+        /* For 32-bit, 99% certainty that we're running on hardware that
+           supports cmov, but we still need to check.  In case cmov is not
+           available, we'll use a small forward branch.  */
+        have_cmov = (d & bit_CMOV) != 0;
+#endif
+#ifndef have_movbe
+        /* MOVBE is only available on Intel Atom and Haswell CPUs, so we
+           need to probe for it.  */
+        have_movbe = (c & bit_MOVBE) != 0;
+#endif
+    }
+
+    if (max >= 7) {
+        /* BMI1 is available on AMD Piledriver and Intel Haswell CPUs.  */
+        __cpuid_count(7, 0, a, b, c, d);
+#ifdef bit_BMI
+        have_bmi1 = (b & bit_BMI) != 0;
+#endif
+#ifndef have_bmi2
+        have_bmi2 = (b & bit_BMI2) != 0;
+#endif
+    }
+#endif
+
+    if (TCG_TARGET_REG_BITS == 64) {
+        tcg_regset_set32(tcg_target_available_regs[TCG_TYPE_I32], 0, 0xffff);
+        tcg_regset_set32(tcg_target_available_regs[TCG_TYPE_I64], 0, 0xffff);
+    } else {
+        tcg_regset_set32(tcg_target_available_regs[TCG_TYPE_I32], 0, 0xff);
+    }
+
+    tcg_regset_clear(tcg_target_call_clobber_regs);
+    tcg_regset_set_reg(tcg_target_call_clobber_regs, TCG_REG_EAX);
+    tcg_regset_set_reg(tcg_target_call_clobber_regs, TCG_REG_EDX);
+    tcg_regset_set_reg(tcg_target_call_clobber_regs, TCG_REG_ECX);
+    if (TCG_TARGET_REG_BITS == 64) {
+#if !defined(_WIN64)
+        tcg_regset_set_reg(tcg_target_call_clobber_regs, TCG_REG_RDI);
+        tcg_regset_set_reg(tcg_target_call_clobber_regs, TCG_REG_RSI);
+#endif
+        tcg_regset_set_reg(tcg_target_call_clobber_regs, TCG_REG_R8);
+        tcg_regset_set_reg(tcg_target_call_clobber_regs, TCG_REG_R9);
+        tcg_regset_set_reg(tcg_target_call_clobber_regs, TCG_REG_R10);
+        tcg_regset_set_reg(tcg_target_call_clobber_regs, TCG_REG_R11);
+    }
+
+    tcg_regset_clear(s->reserved_regs);
+    tcg_regset_set_reg(s->reserved_regs, TCG_REG_CALL_STACK);
+
+    tcg_add_target_add_op_defs(x86_op_defs);
+}
+
+typedef struct {
+    DebugFrameHeader h;
+    uint8_t fde_def_cfa[4];
+    uint8_t fde_reg_ofs[14];
+} DebugFrame;
+
+/* We're expecting a 2 byte uleb128 encoded value.  */
+QEMU_BUILD_BUG_ON(FRAME_SIZE >= (1 << 14));
+
+#if !defined(__ELF__)
+    /* Host machine without ELF. */
+#elif TCG_TARGET_REG_BITS == 64
+#define ELF_HOST_MACHINE EM_X86_64
+static const DebugFrame debug_frame = {
+    .h.cie.len = sizeof(DebugFrameCIE)-4, /* length after .len member */
+    .h.cie.id = -1,
+    .h.cie.version = 1,
+    .h.cie.code_align = 1,
+    .h.cie.data_align = 0x78,             /* sleb128 -8 */
+    .h.cie.return_column = 16,
+
+    /* Total FDE size does not include the "len" member.  */
+    .h.fde.len = sizeof(DebugFrame) - offsetof(DebugFrame, h.fde.cie_offset),
+
+    .fde_def_cfa = {
+        12, 7,                          /* DW_CFA_def_cfa %rsp, ... */
+        (FRAME_SIZE & 0x7f) | 0x80,     /* ... uleb128 FRAME_SIZE */
+        (FRAME_SIZE >> 7)
+    },
+    .fde_reg_ofs = {
+        0x90, 1,                        /* DW_CFA_offset, %rip, -8 */
+        /* The following ordering must match tcg_target_callee_save_regs.  */
+        0x86, 2,                        /* DW_CFA_offset, %rbp, -16 */
+        0x83, 3,                        /* DW_CFA_offset, %rbx, -24 */
+        0x8c, 4,                        /* DW_CFA_offset, %r12, -32 */
+        0x8d, 5,                        /* DW_CFA_offset, %r13, -40 */
+        0x8e, 6,                        /* DW_CFA_offset, %r14, -48 */
+        0x8f, 7,                        /* DW_CFA_offset, %r15, -56 */
+    }
+};
+#else
+#define ELF_HOST_MACHINE EM_386
+static const DebugFrame debug_frame = {
+    .h.cie.len = sizeof(DebugFrameCIE)-4, /* length after .len member */
+    .h.cie.id = -1,
+    .h.cie.version = 1,
+    .h.cie.code_align = 1,
+    .h.cie.data_align = 0x7c,             /* sleb128 -4 */
+    .h.cie.return_column = 8,
+
+    /* Total FDE size does not include the "len" member.  */
+    .h.fde.len = sizeof(DebugFrame) - offsetof(DebugFrame, h.fde.cie_offset),
+
+    .fde_def_cfa = {
+        12, 4,                          /* DW_CFA_def_cfa %esp, ... */
+        (FRAME_SIZE & 0x7f) | 0x80,     /* ... uleb128 FRAME_SIZE */
+        (FRAME_SIZE >> 7)
+    },
+    .fde_reg_ofs = {
+        0x88, 1,                        /* DW_CFA_offset, %eip, -4 */
+        /* The following ordering must match tcg_target_callee_save_regs.  */
+        0x85, 2,                        /* DW_CFA_offset, %ebp, -8 */
+        0x83, 3,                        /* DW_CFA_offset, %ebx, -12 */
+        0x86, 4,                        /* DW_CFA_offset, %esi, -16 */
+        0x87, 5,                        /* DW_CFA_offset, %edi, -20 */
+    }
+};
+#endif
+
+#if defined(ELF_HOST_MACHINE)
+void tcg_register_jit(void *buf, size_t buf_size)
+{
+    tcg_register_jit_int(buf, buf_size, &debug_frame, sizeof(debug_frame));
+}
+#endif
diff --git a/tcg/i386/tcg-target.h b/tcg/i386/tcg-target.h
new file mode 100644
index 00000000..25b51335
--- /dev/null
+++ b/tcg/i386/tcg-target.h
@@ -0,0 +1,149 @@
+/*
+ * Tiny Code Generator for QEMU
+ *
+ * Copyright (c) 2008 Fabrice Bellard
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (the "Software"), to deal
+ * in the Software without restriction, including without limitation the rights
+ * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+ * copies of the Software, and to permit persons to whom the Software is
+ * furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+ * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+ * THE SOFTWARE.
+ */
+#ifndef TCG_TARGET_I386 
+#define TCG_TARGET_I386 1
+
+#define TCG_TARGET_INSN_UNIT_SIZE  1
+#define TCG_TARGET_TLB_DISPLACEMENT_BITS 31
+
+#ifdef __x86_64__
+# define TCG_TARGET_REG_BITS  64
+# define TCG_TARGET_NB_REGS   16
+#else
+# define TCG_TARGET_REG_BITS  32
+# define TCG_TARGET_NB_REGS    8
+#endif
+
+typedef enum {
+    TCG_REG_EAX = 0,
+    TCG_REG_ECX,
+    TCG_REG_EDX,
+    TCG_REG_EBX,
+    TCG_REG_ESP,
+    TCG_REG_EBP,
+    TCG_REG_ESI,
+    TCG_REG_EDI,
+
+    /* 64-bit registers; always define the symbols to avoid
+       too much if-deffing.  */
+    TCG_REG_R8,
+    TCG_REG_R9,
+    TCG_REG_R10,
+    TCG_REG_R11,
+    TCG_REG_R12,
+    TCG_REG_R13,
+    TCG_REG_R14,
+    TCG_REG_R15,
+    TCG_REG_RAX = TCG_REG_EAX,
+    TCG_REG_RCX = TCG_REG_ECX,
+    TCG_REG_RDX = TCG_REG_EDX,
+    TCG_REG_RBX = TCG_REG_EBX,
+    TCG_REG_RSP = TCG_REG_ESP,
+    TCG_REG_RBP = TCG_REG_EBP,
+    TCG_REG_RSI = TCG_REG_ESI,
+    TCG_REG_RDI = TCG_REG_EDI,
+} TCGReg;
+
+/* used for function call generation */
+#define TCG_REG_CALL_STACK TCG_REG_ESP 
+#define TCG_TARGET_STACK_ALIGN 16
+#if defined(_WIN64)
+#define TCG_TARGET_CALL_STACK_OFFSET 32
+#else
+#define TCG_TARGET_CALL_STACK_OFFSET 0
+#endif
+
+extern bool have_bmi1;
+
+/* optional instructions */
+#define TCG_TARGET_HAS_div2_i32         1
+#define TCG_TARGET_HAS_rot_i32          1
+#define TCG_TARGET_HAS_ext8s_i32        1
+#define TCG_TARGET_HAS_ext16s_i32       1
+#define TCG_TARGET_HAS_ext8u_i32        1
+#define TCG_TARGET_HAS_ext16u_i32       1
+#define TCG_TARGET_HAS_bswap16_i32      1
+#define TCG_TARGET_HAS_bswap32_i32      1
+#define TCG_TARGET_HAS_neg_i32          1
+#define TCG_TARGET_HAS_not_i32          1
+#define TCG_TARGET_HAS_andc_i32         have_bmi1
+#define TCG_TARGET_HAS_orc_i32          0
+#define TCG_TARGET_HAS_eqv_i32          0
+#define TCG_TARGET_HAS_nand_i32         0
+#define TCG_TARGET_HAS_nor_i32          0
+#define TCG_TARGET_HAS_deposit_i32      1
+#define TCG_TARGET_HAS_movcond_i32      1
+#define TCG_TARGET_HAS_add2_i32         1
+#define TCG_TARGET_HAS_sub2_i32         1
+#define TCG_TARGET_HAS_mulu2_i32        1
+#define TCG_TARGET_HAS_muls2_i32        1
+#define TCG_TARGET_HAS_muluh_i32        0
+#define TCG_TARGET_HAS_mulsh_i32        0
+
+#if TCG_TARGET_REG_BITS == 64
+#define TCG_TARGET_HAS_trunc_shr_i32    0
+#define TCG_TARGET_HAS_div2_i64         1
+#define TCG_TARGET_HAS_rot_i64          1
+#define TCG_TARGET_HAS_ext8s_i64        1
+#define TCG_TARGET_HAS_ext16s_i64       1
+#define TCG_TARGET_HAS_ext32s_i64       1
+#define TCG_TARGET_HAS_ext8u_i64        1
+#define TCG_TARGET_HAS_ext16u_i64       1
+#define TCG_TARGET_HAS_ext32u_i64       1
+#define TCG_TARGET_HAS_bswap16_i64      1
+#define TCG_TARGET_HAS_bswap32_i64      1
+#define TCG_TARGET_HAS_bswap64_i64      1
+#define TCG_TARGET_HAS_neg_i64          1
+#define TCG_TARGET_HAS_not_i64          1
+#define TCG_TARGET_HAS_andc_i64         have_bmi1
+#define TCG_TARGET_HAS_orc_i64          0
+#define TCG_TARGET_HAS_eqv_i64          0
+#define TCG_TARGET_HAS_nand_i64         0
+#define TCG_TARGET_HAS_nor_i64          0
+#define TCG_TARGET_HAS_deposit_i64      1
+#define TCG_TARGET_HAS_movcond_i64      1
+#define TCG_TARGET_HAS_add2_i64         1
+#define TCG_TARGET_HAS_sub2_i64         1
+#define TCG_TARGET_HAS_mulu2_i64        1
+#define TCG_TARGET_HAS_muls2_i64        1
+#define TCG_TARGET_HAS_muluh_i64        0
+#define TCG_TARGET_HAS_mulsh_i64        0
+#endif
+
+#define TCG_TARGET_deposit_i32_valid(ofs, len) \
+    (((ofs) == 0 && (len) == 8) || ((ofs) == 8 && (len) == 8) || \
+     ((ofs) == 0 && (len) == 16))
+#define TCG_TARGET_deposit_i64_valid    TCG_TARGET_deposit_i32_valid
+
+#if TCG_TARGET_REG_BITS == 64
+# define TCG_AREG0 TCG_REG_R14
+#else
+# define TCG_AREG0 TCG_REG_EBP
+#endif
+
+static inline void flush_icache_range(uintptr_t start, uintptr_t stop)
+{
+}
+
+#endif
diff --git a/tcg/ia64/tcg-target.c b/tcg/ia64/tcg-target.c
new file mode 100644
index 00000000..81cb9f79
--- /dev/null
+++ b/tcg/ia64/tcg-target.c
@@ -0,0 +1,2445 @@
+/*
+ * Tiny Code Generator for QEMU
+ *
+ * Copyright (c) 2009-2010 Aurelien Jarno <aurelien@aurel32.net>
+ * Based on i386/tcg-target.c - Copyright (c) 2008 Fabrice Bellard
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (the "Software"), to deal
+ * in the Software without restriction, including without limitation the rights
+ * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+ * copies of the Software, and to permit persons to whom the Software is
+ * furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+ * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+ * THE SOFTWARE.
+ */
+
+/*
+ * Register definitions
+ */
+
+#ifndef NDEBUG
+static const char * const tcg_target_reg_names[TCG_TARGET_NB_REGS] = {
+     "r0",  "r1",  "r2",  "r3",  "r4",  "r5",  "r6",  "r7",
+     "r8",  "r9", "r10", "r11", "r12", "r13", "r14", "r15",
+    "r16", "r17", "r18", "r19", "r20", "r21", "r22", "r23",
+    "r24", "r25", "r26", "r27", "r28", "r29", "r30", "r31",
+    "r32", "r33", "r34", "r35", "r36", "r37", "r38", "r39",
+    "r40", "r41", "r42", "r43", "r44", "r45", "r46", "r47",
+    "r48", "r49", "r50", "r51", "r52", "r53", "r54", "r55",
+    "r56", "r57", "r58", "r59", "r60", "r61", "r62", "r63",
+};
+#endif
+
+#ifdef CONFIG_USE_GUEST_BASE
+#define TCG_GUEST_BASE_REG TCG_REG_R55
+#else
+#define TCG_GUEST_BASE_REG TCG_REG_R0
+#endif
+#ifndef GUEST_BASE
+#define GUEST_BASE 0
+#endif
+
+/* Branch registers */
+enum {
+    TCG_REG_B0 = 0,
+    TCG_REG_B1,
+    TCG_REG_B2,
+    TCG_REG_B3,
+    TCG_REG_B4,
+    TCG_REG_B5,
+    TCG_REG_B6,
+    TCG_REG_B7,
+};
+
+/* Floating point registers */
+enum {
+    TCG_REG_F0 = 0,
+    TCG_REG_F1,
+    TCG_REG_F2,
+    TCG_REG_F3,
+    TCG_REG_F4,
+    TCG_REG_F5,
+    TCG_REG_F6,
+    TCG_REG_F7,
+    TCG_REG_F8,
+    TCG_REG_F9,
+    TCG_REG_F10,
+    TCG_REG_F11,
+    TCG_REG_F12,
+    TCG_REG_F13,
+    TCG_REG_F14,
+    TCG_REG_F15,
+};
+
+/* Predicate registers */
+enum {
+    TCG_REG_P0 = 0,
+    TCG_REG_P1,
+    TCG_REG_P2,
+    TCG_REG_P3,
+    TCG_REG_P4,
+    TCG_REG_P5,
+    TCG_REG_P6,
+    TCG_REG_P7,
+    TCG_REG_P8,
+    TCG_REG_P9,
+    TCG_REG_P10,
+    TCG_REG_P11,
+    TCG_REG_P12,
+    TCG_REG_P13,
+    TCG_REG_P14,
+    TCG_REG_P15,
+};
+
+/* Application registers */
+enum {
+    TCG_REG_PFS = 64,
+};
+
+static const int tcg_target_reg_alloc_order[] = {
+    TCG_REG_R35,
+    TCG_REG_R36,
+    TCG_REG_R37,
+    TCG_REG_R38,
+    TCG_REG_R39,
+    TCG_REG_R40,
+    TCG_REG_R41,
+    TCG_REG_R42,
+    TCG_REG_R43,
+    TCG_REG_R44,
+    TCG_REG_R45,
+    TCG_REG_R46,
+    TCG_REG_R47,
+    TCG_REG_R48,
+    TCG_REG_R49,
+    TCG_REG_R50,
+    TCG_REG_R51,
+    TCG_REG_R52,
+    TCG_REG_R53,
+    TCG_REG_R54,
+    TCG_REG_R55,
+    TCG_REG_R14,
+    TCG_REG_R15,
+    TCG_REG_R16,
+    TCG_REG_R17,
+    TCG_REG_R18,
+    TCG_REG_R19,
+    TCG_REG_R20,
+    TCG_REG_R21,
+    TCG_REG_R22,
+    TCG_REG_R23,
+    TCG_REG_R24,
+    TCG_REG_R25,
+    TCG_REG_R26,
+    TCG_REG_R27,
+    TCG_REG_R28,
+    TCG_REG_R29,
+    TCG_REG_R30,
+    TCG_REG_R31,
+    TCG_REG_R56,
+    TCG_REG_R57,
+    TCG_REG_R58,
+    TCG_REG_R59,
+    TCG_REG_R60,
+    TCG_REG_R61,
+    TCG_REG_R62,
+    TCG_REG_R63,
+    TCG_REG_R8,
+    TCG_REG_R9,
+    TCG_REG_R10,
+    TCG_REG_R11
+};
+
+static const int tcg_target_call_iarg_regs[8] = {
+    TCG_REG_R56,
+    TCG_REG_R57,
+    TCG_REG_R58,
+    TCG_REG_R59,
+    TCG_REG_R60,
+    TCG_REG_R61,
+    TCG_REG_R62,
+    TCG_REG_R63,
+};
+
+static const int tcg_target_call_oarg_regs[] = {
+    TCG_REG_R8
+};
+
+/*
+ * opcode formation
+ */
+
+/* bundle templates: stops (double bar in the IA64 manual) are marked with
+   an uppercase letter. */
+enum {
+    mii = 0x00,
+    miI = 0x01,
+    mIi = 0x02,
+    mII = 0x03,
+    mlx = 0x04,
+    mLX = 0x05,
+    mmi = 0x08,
+    mmI = 0x09,
+    Mmi = 0x0a,
+    MmI = 0x0b,
+    mfi = 0x0c,
+    mfI = 0x0d,
+    mmf = 0x0e,
+    mmF = 0x0f,
+    mib = 0x10,
+    miB = 0x11,
+    mbb = 0x12,
+    mbB = 0x13,
+    bbb = 0x16,
+    bbB = 0x17,
+    mmb = 0x18,
+    mmB = 0x19,
+    mfb = 0x1c,
+    mfB = 0x1d,
+};
+
+enum {
+    OPC_ADD_A1                = 0x10000000000ull,
+    OPC_AND_A1                = 0x10060000000ull,
+    OPC_AND_A3                = 0x10160000000ull,
+    OPC_ANDCM_A1              = 0x10068000000ull,
+    OPC_ANDCM_A3              = 0x10168000000ull,
+    OPC_ADDS_A4               = 0x10800000000ull,
+    OPC_ADDL_A5               = 0x12000000000ull,
+    OPC_ALLOC_M34             = 0x02c00000000ull,
+    OPC_BR_DPTK_FEW_B1        = 0x08400000000ull,
+    OPC_BR_SPTK_MANY_B1       = 0x08000001000ull,
+    OPC_BR_CALL_SPNT_FEW_B3   = 0x0a200000000ull,
+    OPC_BR_SPTK_MANY_B4       = 0x00100001000ull,
+    OPC_BR_CALL_SPTK_MANY_B5  = 0x02100001000ull,
+    OPC_BR_RET_SPTK_MANY_B4   = 0x00108001100ull,
+    OPC_BRL_SPTK_MANY_X3      = 0x18000001000ull,
+    OPC_BRL_CALL_SPNT_MANY_X4 = 0x1a200001000ull,
+    OPC_BRL_CALL_SPTK_MANY_X4 = 0x1a000001000ull,
+    OPC_CMP_LT_A6             = 0x18000000000ull,
+    OPC_CMP_LTU_A6            = 0x1a000000000ull,
+    OPC_CMP_EQ_A6             = 0x1c000000000ull,
+    OPC_CMP4_LT_A6            = 0x18400000000ull,
+    OPC_CMP4_LTU_A6           = 0x1a400000000ull,
+    OPC_CMP4_EQ_A6            = 0x1c400000000ull,
+    OPC_DEP_I14               = 0x0ae00000000ull,
+    OPC_DEP_I15               = 0x08000000000ull,
+    OPC_DEP_Z_I12             = 0x0a600000000ull,
+    OPC_EXTR_I11              = 0x0a400002000ull,
+    OPC_EXTR_U_I11            = 0x0a400000000ull,
+    OPC_FCVT_FX_TRUNC_S1_F10  = 0x004d0000000ull,
+    OPC_FCVT_FXU_TRUNC_S1_F10 = 0x004d8000000ull,
+    OPC_FCVT_XF_F11           = 0x000e0000000ull,
+    OPC_FMA_S1_F1             = 0x10400000000ull,
+    OPC_FNMA_S1_F1            = 0x18400000000ull,
+    OPC_FRCPA_S1_F6           = 0x00600000000ull,
+    OPC_GETF_SIG_M19          = 0x08708000000ull,
+    OPC_LD1_M1                = 0x08000000000ull,
+    OPC_LD1_M3                = 0x0a000000000ull,
+    OPC_LD2_M1                = 0x08040000000ull,
+    OPC_LD2_M3                = 0x0a040000000ull,
+    OPC_LD4_M1                = 0x08080000000ull,
+    OPC_LD4_M3                = 0x0a080000000ull,
+    OPC_LD8_M1                = 0x080c0000000ull,
+    OPC_LD8_M3                = 0x0a0c0000000ull,
+    OPC_MUX1_I3               = 0x0eca0000000ull,
+    OPC_NOP_B9                = 0x04008000000ull,
+    OPC_NOP_F16               = 0x00008000000ull,
+    OPC_NOP_I18               = 0x00008000000ull,
+    OPC_NOP_M48               = 0x00008000000ull,
+    OPC_MOV_I21               = 0x00e00100000ull,
+    OPC_MOV_RET_I21           = 0x00e00500000ull,
+    OPC_MOV_I22               = 0x00188000000ull,
+    OPC_MOV_I_I26             = 0x00150000000ull,
+    OPC_MOVL_X2               = 0x0c000000000ull,
+    OPC_OR_A1                 = 0x10070000000ull,
+    OPC_OR_A3                 = 0x10170000000ull,
+    OPC_SETF_EXP_M18          = 0x0c748000000ull,
+    OPC_SETF_SIG_M18          = 0x0c708000000ull,
+    OPC_SHL_I7                = 0x0f240000000ull,
+    OPC_SHR_I5                = 0x0f220000000ull,
+    OPC_SHR_U_I5              = 0x0f200000000ull,
+    OPC_SHRP_I10              = 0x0ac00000000ull,
+    OPC_SXT1_I29              = 0x000a0000000ull,
+    OPC_SXT2_I29              = 0x000a8000000ull,
+    OPC_SXT4_I29              = 0x000b0000000ull,
+    OPC_ST1_M4                = 0x08c00000000ull,
+    OPC_ST2_M4                = 0x08c40000000ull,
+    OPC_ST4_M4                = 0x08c80000000ull,
+    OPC_ST8_M4                = 0x08cc0000000ull,
+    OPC_SUB_A1                = 0x10028000000ull,
+    OPC_SUB_A3                = 0x10128000000ull,
+    OPC_UNPACK4_L_I2          = 0x0f860000000ull,
+    OPC_XMA_L_F2              = 0x1d000000000ull,
+    OPC_XOR_A1                = 0x10078000000ull,
+    OPC_XOR_A3                = 0x10178000000ull,
+    OPC_ZXT1_I29              = 0x00080000000ull,
+    OPC_ZXT2_I29              = 0x00088000000ull,
+    OPC_ZXT4_I29              = 0x00090000000ull,
+
+    INSN_NOP_M                = OPC_NOP_M48,  /* nop.m 0 */
+    INSN_NOP_I                = OPC_NOP_I18,  /* nop.i 0 */
+};
+
+static inline uint64_t tcg_opc_a1(int qp, uint64_t opc, int r1,
+                                  int r2, int r3)
+{
+    return opc
+           | ((r3 & 0x7f) << 20)
+           | ((r2 & 0x7f) << 13)
+           | ((r1 & 0x7f) << 6)
+           | (qp & 0x3f);
+}
+
+static inline uint64_t tcg_opc_a3(int qp, uint64_t opc, int r1,
+                                  uint64_t imm, int r3)
+{
+    return opc
+           | ((imm & 0x80) << 29) /* s */
+           | ((imm & 0x7f) << 13) /* imm7b */
+           | ((r3 & 0x7f) << 20)
+           | ((r1 & 0x7f) << 6)
+           | (qp & 0x3f);
+}
+
+static inline uint64_t tcg_opc_a4(int qp, uint64_t opc, int r1,
+                                  uint64_t imm, int r3)
+{
+    return opc
+           | ((imm & 0x2000) << 23) /* s */
+           | ((imm & 0x1f80) << 20) /* imm6d */
+           | ((imm & 0x007f) << 13) /* imm7b */
+           | ((r3 & 0x7f) << 20)
+           | ((r1 & 0x7f) << 6)
+           | (qp & 0x3f);
+}
+
+static inline uint64_t tcg_opc_a5(int qp, uint64_t opc, int r1,
+                                  uint64_t imm, int r3)
+{
+    return opc
+           | ((imm & 0x200000) << 15) /* s */
+           | ((imm & 0x1f0000) <<  6) /* imm5c */
+           | ((imm & 0x00ff80) << 20) /* imm9d */
+           | ((imm & 0x00007f) << 13) /* imm7b */
+           | ((r3 & 0x03) << 20)
+           | ((r1 & 0x7f) << 6)
+           | (qp & 0x3f);
+}
+
+static inline uint64_t tcg_opc_a6(int qp, uint64_t opc, int p1,
+                                  int p2, int r2, int r3)
+{
+    return opc
+           | ((p2 & 0x3f) << 27)
+           | ((r3 & 0x7f) << 20)
+           | ((r2 & 0x7f) << 13)
+           | ((p1 & 0x3f) << 6)
+           | (qp & 0x3f);
+}
+
+static inline uint64_t tcg_opc_b1(int qp, uint64_t opc, uint64_t imm)
+{
+    return opc
+           | ((imm & 0x100000) << 16) /* s */
+           | ((imm & 0x0fffff) << 13) /* imm20b */
+           | (qp & 0x3f);
+}
+
+static inline uint64_t tcg_opc_b3(int qp, uint64_t opc, int b1, uint64_t imm)
+{
+    return opc
+           | ((imm & 0x100000) << 16) /* s */
+           | ((imm & 0x0fffff) << 13) /* imm20b */
+           | ((b1 & 0x7) << 6)
+           | (qp & 0x3f);
+}
+
+static inline uint64_t tcg_opc_b4(int qp, uint64_t opc, int b2)
+{
+    return opc
+           | ((b2 & 0x7) << 13)
+           | (qp & 0x3f);
+}
+
+static inline uint64_t tcg_opc_b5(int qp, uint64_t opc, int b1, int b2)
+{
+    return opc
+           | ((b2 & 0x7) << 13)
+           | ((b1 & 0x7) << 6)
+           | (qp & 0x3f);
+}
+
+
+static inline uint64_t tcg_opc_b9(int qp, uint64_t opc, uint64_t imm)
+{
+    return opc
+           | ((imm & 0x100000) << 16) /* i */
+           | ((imm & 0x0fffff) << 6)  /* imm20a */
+           | (qp & 0x3f);
+}
+
+static inline uint64_t tcg_opc_f1(int qp, uint64_t opc, int f1,
+                                  int f3, int f4, int f2)
+{
+    return opc
+           | ((f4 & 0x7f) << 27)
+           | ((f3 & 0x7f) << 20)
+           | ((f2 & 0x7f) << 13)
+           | ((f1 & 0x7f) << 6)
+           | (qp & 0x3f);
+}
+
+static inline uint64_t tcg_opc_f2(int qp, uint64_t opc, int f1,
+                                  int f3, int f4, int f2)
+{
+    return opc
+           | ((f4 & 0x7f) << 27)
+           | ((f3 & 0x7f) << 20)
+           | ((f2 & 0x7f) << 13)
+           | ((f1 & 0x7f) << 6)
+           | (qp & 0x3f);
+}
+
+static inline uint64_t tcg_opc_f6(int qp, uint64_t opc, int f1,
+                                  int p2, int f2, int f3)
+{
+    return opc
+           | ((p2 & 0x3f) << 27)
+           | ((f3 & 0x7f) << 20)
+           | ((f2 & 0x7f) << 13)
+           | ((f1 & 0x7f) << 6)
+           | (qp & 0x3f);
+}
+
+static inline uint64_t tcg_opc_f10(int qp, uint64_t opc, int f1, int f2)
+{
+    return opc
+           | ((f2 & 0x7f) << 13)
+           | ((f1 & 0x7f) << 6)
+           | (qp & 0x3f);
+}
+
+static inline uint64_t tcg_opc_f11(int qp, uint64_t opc, int f1, int f2)
+{
+    return opc
+           | ((f2 & 0x7f) << 13)
+           | ((f1 & 0x7f) << 6)
+           | (qp & 0x3f);
+}
+
+static inline uint64_t tcg_opc_f16(int qp, uint64_t opc, uint64_t imm)
+{
+    return opc
+           | ((imm & 0x100000) << 16) /* i */
+           | ((imm & 0x0fffff) << 6)  /* imm20a */
+           | (qp & 0x3f);
+}
+
+static inline uint64_t tcg_opc_i2(int qp, uint64_t opc, int r1,
+                                  int r2, int r3)
+{
+    return opc
+           | ((r3 & 0x7f) << 20)
+           | ((r2 & 0x7f) << 13)
+           | ((r1 & 0x7f) << 6)
+           | (qp & 0x3f);
+}
+
+static inline uint64_t tcg_opc_i3(int qp, uint64_t opc, int r1,
+                                  int r2, int mbtype)
+{
+    return opc
+           | ((mbtype & 0x0f) << 20)
+           | ((r2 & 0x7f) << 13)
+           | ((r1 & 0x7f) << 6)
+           | (qp & 0x3f);
+}
+
+static inline uint64_t tcg_opc_i5(int qp, uint64_t opc, int r1,
+                                  int r3, int r2)
+{
+    return opc
+           | ((r3 & 0x7f) << 20)
+           | ((r2 & 0x7f) << 13)
+           | ((r1 & 0x7f) << 6)
+           | (qp & 0x3f);
+}
+
+static inline uint64_t tcg_opc_i7(int qp, uint64_t opc, int r1,
+                                  int r2, int r3)
+{
+    return opc
+           | ((r3 & 0x7f) << 20)
+           | ((r2 & 0x7f) << 13)
+           | ((r1 & 0x7f) << 6)
+           | (qp & 0x3f);
+}
+
+static inline uint64_t tcg_opc_i10(int qp, uint64_t opc, int r1,
+                                   int r2, int r3, uint64_t count)
+{
+    return opc
+           | ((count & 0x3f) << 27)
+           | ((r3 & 0x7f) << 20)
+           | ((r2 & 0x7f) << 13)
+           | ((r1 & 0x7f) << 6)
+           | (qp & 0x3f);
+}
+
+static inline uint64_t tcg_opc_i11(int qp, uint64_t opc, int r1,
+                                   int r3, uint64_t pos, uint64_t len)
+{
+    return opc
+           | ((len & 0x3f) << 27)
+           | ((r3 & 0x7f) << 20)
+           | ((pos & 0x3f) << 14)
+           | ((r1 & 0x7f) << 6)
+           | (qp & 0x3f);
+}
+
+static inline uint64_t tcg_opc_i12(int qp, uint64_t opc, int r1,
+                                   int r2, uint64_t pos, uint64_t len)
+{
+    return opc
+           | ((len & 0x3f) << 27)
+           | ((pos & 0x3f) << 20)
+           | ((r2 & 0x7f) << 13)
+           | ((r1 & 0x7f) << 6)
+           | (qp & 0x3f);
+}
+
+static inline uint64_t tcg_opc_i14(int qp, uint64_t opc, int r1, uint64_t imm,
+                                   int r3, uint64_t pos, uint64_t len)
+{
+    return opc
+           | ((imm & 0x01) << 36)
+           | ((len & 0x3f) << 27)
+           | ((r3 & 0x7f) << 20)
+           | ((pos & 0x3f) << 14)
+           | ((r1 & 0x7f) << 6)
+           | (qp & 0x3f);
+}
+
+static inline uint64_t tcg_opc_i15(int qp, uint64_t opc, int r1, int r2,
+                                   int r3, uint64_t pos, uint64_t len)
+{
+    return opc
+           | ((pos & 0x3f) << 31)
+           | ((len & 0x0f) << 27)
+           | ((r3 & 0x7f) << 20)
+           | ((r2 & 0x7f) << 13)
+           | ((r1 & 0x7f) << 6)
+           | (qp & 0x3f);
+}
+
+static inline uint64_t tcg_opc_i18(int qp, uint64_t opc, uint64_t imm)
+{
+    return opc
+           | ((imm & 0x100000) << 16) /* i */
+           | ((imm & 0x0fffff) << 6)  /* imm20a */
+           | (qp & 0x3f);
+}
+
+static inline uint64_t tcg_opc_i21(int qp, uint64_t opc, int b1,
+                                   int r2, uint64_t imm)
+{
+    return opc
+           | ((imm & 0x1ff) << 24)
+           | ((r2 & 0x7f) << 13)
+           | ((b1 & 0x7) << 6)
+           | (qp & 0x3f);
+}
+
+static inline uint64_t tcg_opc_i22(int qp, uint64_t opc, int r1, int b2)
+{
+    return opc
+           | ((b2 & 0x7) << 13)
+           | ((r1 & 0x7f) << 6)
+           | (qp & 0x3f);
+}
+
+static inline uint64_t tcg_opc_i26(int qp, uint64_t opc, int ar3, int r2)
+{
+    return opc
+           | ((ar3 & 0x7f) << 20)
+           | ((r2 & 0x7f) << 13)
+           | (qp & 0x3f);
+}
+
+static inline uint64_t tcg_opc_i29(int qp, uint64_t opc, int r1, int r3)
+{
+    return opc
+           | ((r3 & 0x7f) << 20)
+           | ((r1 & 0x7f) << 6)
+           | (qp & 0x3f);
+}
+
+static inline uint64_t tcg_opc_l2(uint64_t imm)
+{
+    return (imm & 0x7fffffffffc00000ull) >> 22;
+}
+
+static inline uint64_t tcg_opc_l3(uint64_t imm)
+{
+    return (imm & 0x07fffffffff00000ull) >> 18;
+}
+
+#define tcg_opc_l4  tcg_opc_l3
+
+static inline uint64_t tcg_opc_m1(int qp, uint64_t opc, int r1, int r3)
+{
+    return opc
+           | ((r3 & 0x7f) << 20)
+           | ((r1 & 0x7f) << 6)
+           | (qp & 0x3f);
+}
+
+static inline uint64_t tcg_opc_m3(int qp, uint64_t opc, int r1,
+                                  int r3, uint64_t imm)
+{
+    return opc
+           | ((imm & 0x100) << 28) /* s */
+           | ((imm & 0x080) << 20) /* i */
+           | ((imm & 0x07f) << 13) /* imm7b */
+           | ((r3 & 0x7f) << 20)
+           | ((r1 & 0x7f) << 6)
+           | (qp & 0x3f);
+}
+
+static inline uint64_t tcg_opc_m4(int qp, uint64_t opc, int r2, int r3)
+{
+    return opc
+           | ((r3 & 0x7f) << 20)
+           | ((r2 & 0x7f) << 13)
+           | (qp & 0x3f);
+}
+
+static inline uint64_t tcg_opc_m18(int qp, uint64_t opc, int f1, int r2)
+{
+    return opc
+           | ((r2 & 0x7f) << 13)
+           | ((f1 & 0x7f) << 6)
+           | (qp & 0x3f);
+}
+
+static inline uint64_t tcg_opc_m19(int qp, uint64_t opc, int r1, int f2)
+{
+    return opc
+           | ((f2 & 0x7f) << 13)
+           | ((r1 & 0x7f) << 6)
+           | (qp & 0x3f);
+}
+
+static inline uint64_t tcg_opc_m34(int qp, uint64_t opc, int r1,
+                                   int sof, int sol, int sor)
+{
+    return opc
+           | ((sor & 0x0f) << 27)
+           | ((sol & 0x7f) << 20)
+           | ((sof & 0x7f) << 13)
+           | ((r1 & 0x7f) << 6)
+           | (qp & 0x3f);
+}
+
+static inline uint64_t tcg_opc_m48(int qp, uint64_t opc, uint64_t imm)
+{
+    return opc
+           | ((imm & 0x100000) << 16) /* i */
+           | ((imm & 0x0fffff) << 6)  /* imm20a */
+           | (qp & 0x3f);
+}
+
+static inline uint64_t tcg_opc_x2(int qp, uint64_t opc,
+                                  int r1, uint64_t imm)
+{
+    return opc
+           | ((imm & 0x8000000000000000ull) >> 27) /* i */
+           |  (imm & 0x0000000000200000ull)        /* ic */
+           | ((imm & 0x00000000001f0000ull) << 6)  /* imm5c */
+           | ((imm & 0x000000000000ff80ull) << 20) /* imm9d */
+           | ((imm & 0x000000000000007full) << 13) /* imm7b */
+           | ((r1 & 0x7f) << 6)
+           | (qp & 0x3f);
+}
+
+static inline uint64_t tcg_opc_x3(int qp, uint64_t opc, uint64_t imm)
+{
+    return opc
+           | ((imm & 0x0800000000000000ull) >> 23) /* i */
+           | ((imm & 0x00000000000fffffull) << 13) /* imm20b */
+           | (qp & 0x3f);
+}
+
+static inline uint64_t tcg_opc_x4(int qp, uint64_t opc, int b1, uint64_t imm)
+{
+    return opc
+           | ((imm & 0x0800000000000000ull) >> 23) /* i */
+           | ((imm & 0x00000000000fffffull) << 13) /* imm20b */
+           | ((b1 & 0x7) << 6)
+           | (qp & 0x3f);
+}
+
+
+/*
+ * Relocations - Note that we never encode branches elsewhere than slot 2.
+ */
+
+static void reloc_pcrel21b_slot2(tcg_insn_unit *pc, tcg_insn_unit *target)
+{
+    uint64_t imm = target - pc;
+
+    pc->hi = (pc->hi & 0xf700000fffffffffull)
+             | ((imm & 0x100000) << 39)  /* s */
+             | ((imm & 0x0fffff) << 36); /* imm20b */
+}
+
+static uint64_t get_reloc_pcrel21b_slot2(tcg_insn_unit *pc)
+{
+    int64_t high = pc->hi;
+
+    return ((high >> 39) & 0x100000) + /* s */
+           ((high >> 36) & 0x0fffff);  /* imm20b */
+}
+
+static void patch_reloc(tcg_insn_unit *code_ptr, int type,
+                        intptr_t value, intptr_t addend)
+{
+    assert(addend == 0);
+    assert(type == R_IA64_PCREL21B);
+    reloc_pcrel21b_slot2(code_ptr, (tcg_insn_unit *)value);
+}
+
+/*
+ * Constraints
+ */
+
+/* parse target specific constraints */
+static int target_parse_constraint(TCGArgConstraint *ct, const char **pct_str)
+{
+    const char *ct_str;
+
+    ct_str = *pct_str;
+    switch(ct_str[0]) {
+    case 'r':
+        ct->ct |= TCG_CT_REG;
+        tcg_regset_set(ct->u.regs, 0xffffffffffffffffull);
+        break;
+    case 'I':
+        ct->ct |= TCG_CT_CONST_S22;
+        break;
+    case 'S':
+        ct->ct |= TCG_CT_REG;
+        tcg_regset_set(ct->u.regs, 0xffffffffffffffffull);
+#if defined(CONFIG_SOFTMMU)
+        tcg_regset_reset_reg(ct->u.regs, TCG_REG_R56);
+        tcg_regset_reset_reg(ct->u.regs, TCG_REG_R57);
+        tcg_regset_reset_reg(ct->u.regs, TCG_REG_R58);
+#endif
+        break;
+    case 'Z':
+        /* We are cheating a bit here, using the fact that the register
+           r0 is also the register number 0. Hence there is no need
+           to check for const_args in each instruction. */
+        ct->ct |= TCG_CT_CONST_ZERO;
+        break;
+    default:
+        return -1;
+    }
+    ct_str++;
+    *pct_str = ct_str;
+    return 0;
+}
+
+/* test if a constant matches the constraint */
+static inline int tcg_target_const_match(tcg_target_long val, TCGType type,
+                                         const TCGArgConstraint *arg_ct)
+{
+    int ct;
+    ct = arg_ct->ct;
+    if (ct & TCG_CT_CONST)
+        return 1;
+    else if ((ct & TCG_CT_CONST_ZERO) && val == 0)
+        return 1;
+    else if ((ct & TCG_CT_CONST_S22) && val == ((int32_t)val << 10) >> 10)
+        return 1;
+    else
+        return 0;
+}
+
+/*
+ * Code generation
+ */
+
+static tcg_insn_unit *tb_ret_addr;
+
+static inline void tcg_out_bundle(TCGContext *s, int template,
+                                  uint64_t slot0, uint64_t slot1,
+                                  uint64_t slot2)
+{
+    template &= 0x1f;          /* 5 bits */
+    slot0 &= 0x1ffffffffffull; /* 41 bits */
+    slot1 &= 0x1ffffffffffull; /* 41 bits */
+    slot2 &= 0x1ffffffffffull; /* 41 bits */
+
+    *s->code_ptr++ = (tcg_insn_unit){
+        (slot1 << 46) | (slot0 << 5) | template,
+        (slot2 << 23) | (slot1 >> 18)
+    };
+}
+
+static inline uint64_t tcg_opc_mov_a(int qp, TCGReg dst, TCGReg src)
+{
+    return tcg_opc_a4(qp, OPC_ADDS_A4, dst, 0, src);
+}
+
+static inline void tcg_out_mov(TCGContext *s, TCGType type,
+                               TCGReg ret, TCGReg arg)
+{
+    tcg_out_bundle(s, mmI,
+                   INSN_NOP_M,
+                   INSN_NOP_M,
+                   tcg_opc_mov_a(TCG_REG_P0, ret, arg));
+}
+
+static inline uint64_t tcg_opc_movi_a(int qp, TCGReg dst, int64_t src)
+{
+    assert(src == sextract64(src, 0, 22));
+    return tcg_opc_a5(qp, OPC_ADDL_A5, dst, src, TCG_REG_R0);
+}
+
+static inline void tcg_out_movi(TCGContext *s, TCGType type,
+                                TCGReg reg, tcg_target_long arg)
+{
+    tcg_out_bundle(s, mLX,
+                   INSN_NOP_M,
+                   tcg_opc_l2 (arg),
+                   tcg_opc_x2 (TCG_REG_P0, OPC_MOVL_X2, reg, arg));
+}
+
+static void tcg_out_br(TCGContext *s, TCGLabel *l)
+{
+    uint64_t imm;
+
+    /* We pay attention here to not modify the branch target by reading
+       the existing value and using it again. This ensure that caches and
+       memory are kept coherent during retranslation. */
+    if (l->has_value) {
+        imm = l->u.value_ptr -  s->code_ptr;
+    } else {
+        imm = get_reloc_pcrel21b_slot2(s->code_ptr);
+        tcg_out_reloc(s, s->code_ptr, R_IA64_PCREL21B, l, 0);
+    }
+
+    tcg_out_bundle(s, mmB,
+                   INSN_NOP_M,
+                   INSN_NOP_M,
+                   tcg_opc_b1(TCG_REG_P0, OPC_BR_SPTK_MANY_B1, imm));
+}
+
+static inline void tcg_out_call(TCGContext *s, tcg_insn_unit *desc)
+{
+    uintptr_t func = desc->lo, gp = desc->hi, disp;
+
+    /* Look through the function descriptor.  */
+    tcg_out_bundle(s, mlx,
+                   INSN_NOP_M,
+                   tcg_opc_l2 (gp),
+                   tcg_opc_x2 (TCG_REG_P0, OPC_MOVL_X2, TCG_REG_R1, gp));
+    disp = (tcg_insn_unit *)func - s->code_ptr;
+    tcg_out_bundle(s, mLX,
+                   INSN_NOP_M,
+                   tcg_opc_l4 (disp),
+                   tcg_opc_x4 (TCG_REG_P0, OPC_BRL_CALL_SPTK_MANY_X4,
+                               TCG_REG_B0, disp));
+}
+
+static void tcg_out_exit_tb(TCGContext *s, tcg_target_long arg)
+{
+    uint64_t imm, opc1;
+
+    /* At least arg == 0 is a common operation.  */
+    if (arg == sextract64(arg, 0, 22)) {
+        opc1 = tcg_opc_movi_a(TCG_REG_P0, TCG_REG_R8, arg);
+    } else {
+        tcg_out_movi(s, TCG_TYPE_PTR, TCG_REG_R8, arg);
+        opc1 = INSN_NOP_M;
+    }
+
+    imm = tb_ret_addr - s->code_ptr;
+
+    tcg_out_bundle(s, mLX,
+                   opc1,
+                   tcg_opc_l3 (imm),
+                   tcg_opc_x3 (TCG_REG_P0, OPC_BRL_SPTK_MANY_X3, imm));
+}
+
+static inline void tcg_out_goto_tb(TCGContext *s, TCGArg arg)
+{
+    if (s->tb_jmp_offset) {
+        /* direct jump method */
+        tcg_abort();
+    } else {
+        /* indirect jump method */
+        tcg_out_movi(s, TCG_TYPE_PTR, TCG_REG_R2,
+                     (tcg_target_long)(s->tb_next + arg));
+        tcg_out_bundle(s, MmI,
+                       tcg_opc_m1 (TCG_REG_P0, OPC_LD8_M1,
+                                   TCG_REG_R2, TCG_REG_R2),
+                       INSN_NOP_M,
+                       tcg_opc_i21(TCG_REG_P0, OPC_MOV_I21, TCG_REG_B6,
+                                   TCG_REG_R2, 0));
+        tcg_out_bundle(s, mmB,
+                       INSN_NOP_M,
+                       INSN_NOP_M,
+                       tcg_opc_b4 (TCG_REG_P0, OPC_BR_SPTK_MANY_B4,
+                                   TCG_REG_B6));
+    }
+    s->tb_next_offset[arg] = tcg_current_code_size(s);
+}
+
+static inline void tcg_out_jmp(TCGContext *s, TCGArg addr)
+{
+    tcg_out_bundle(s, mmI,
+                   INSN_NOP_M,
+                   INSN_NOP_M,
+                   tcg_opc_i21(TCG_REG_P0, OPC_MOV_I21, TCG_REG_B6, addr, 0));
+    tcg_out_bundle(s, mmB,
+                   INSN_NOP_M,
+                   INSN_NOP_M,
+                   tcg_opc_b4(TCG_REG_P0, OPC_BR_SPTK_MANY_B4, TCG_REG_B6));
+}
+
+static inline void tcg_out_ld_rel(TCGContext *s, uint64_t opc_m4, TCGArg arg,
+                                  TCGArg arg1, tcg_target_long arg2)
+{
+    if (arg2 == ((int16_t)arg2 >> 2) << 2) {
+        tcg_out_bundle(s, MmI,
+                       tcg_opc_a4(TCG_REG_P0, OPC_ADDS_A4,
+                                  TCG_REG_R2, arg2, arg1),
+                       tcg_opc_m1 (TCG_REG_P0, opc_m4, arg, TCG_REG_R2),
+                       INSN_NOP_I);
+    } else {
+        tcg_out_movi(s, TCG_TYPE_PTR, TCG_REG_R2, arg2);
+        tcg_out_bundle(s, MmI,
+                       tcg_opc_a1 (TCG_REG_P0, OPC_ADD_A1,
+                                   TCG_REG_R2, TCG_REG_R2, arg1),
+                       tcg_opc_m1 (TCG_REG_P0, opc_m4, arg, TCG_REG_R2),
+                       INSN_NOP_I);
+    }
+}
+
+static inline void tcg_out_st_rel(TCGContext *s, uint64_t opc_m4, TCGArg arg,
+                                  TCGArg arg1, tcg_target_long arg2)
+{
+    if (arg2 == ((int16_t)arg2 >> 2) << 2) {
+        tcg_out_bundle(s, MmI,
+                       tcg_opc_a4(TCG_REG_P0, OPC_ADDS_A4,
+                                  TCG_REG_R2, arg2, arg1),
+                       tcg_opc_m4 (TCG_REG_P0, opc_m4, arg, TCG_REG_R2),
+                       INSN_NOP_I);
+    } else {
+        tcg_out_movi(s, TCG_TYPE_PTR, TCG_REG_R2, arg2);
+        tcg_out_bundle(s, MmI,
+                       tcg_opc_a1 (TCG_REG_P0, OPC_ADD_A1,
+                                   TCG_REG_R2, TCG_REG_R2, arg1),
+                       tcg_opc_m4 (TCG_REG_P0, opc_m4, arg, TCG_REG_R2),
+                       INSN_NOP_I);
+    }
+}
+
+static inline void tcg_out_ld(TCGContext *s, TCGType type, TCGReg arg,
+                              TCGReg arg1, intptr_t arg2)
+{
+    if (type == TCG_TYPE_I32) {
+        tcg_out_ld_rel(s, OPC_LD4_M1, arg, arg1, arg2);
+    } else {
+        tcg_out_ld_rel(s, OPC_LD8_M1, arg, arg1, arg2);
+    }
+}
+
+static inline void tcg_out_st(TCGContext *s, TCGType type, TCGReg arg,
+                              TCGReg arg1, intptr_t arg2)
+{
+    if (type == TCG_TYPE_I32) {
+        tcg_out_st_rel(s, OPC_ST4_M4, arg, arg1, arg2);
+    } else {
+        tcg_out_st_rel(s, OPC_ST8_M4, arg, arg1, arg2);
+    }
+}
+
+static inline void tcg_out_alu(TCGContext *s, uint64_t opc_a1, uint64_t opc_a3,
+                               TCGReg ret, TCGArg arg1, int const_arg1,
+                               TCGArg arg2, int const_arg2)
+{
+    uint64_t opc1 = 0, opc2 = 0, opc3 = 0;
+
+    if (const_arg2 && arg2 != 0) {
+        opc2 = tcg_opc_movi_a(TCG_REG_P0, TCG_REG_R3, arg2);
+        arg2 = TCG_REG_R3;
+    }
+    if (const_arg1 && arg1 != 0) {
+        if (opc_a3 && arg1 == (int8_t)arg1) {
+            opc3 = tcg_opc_a3(TCG_REG_P0, opc_a3, ret, arg1, arg2);
+        } else {
+            opc1 = tcg_opc_movi_a(TCG_REG_P0, TCG_REG_R2, arg1);
+            arg1 = TCG_REG_R2;
+        }
+    }
+    if (opc3 == 0) {
+        opc3 = tcg_opc_a1(TCG_REG_P0, opc_a1, ret, arg1, arg2);
+    }
+
+    tcg_out_bundle(s, (opc1 || opc2 ? mII : miI),
+                   opc1 ? opc1 : INSN_NOP_M,
+                   opc2 ? opc2 : INSN_NOP_I,
+                   opc3);
+}
+
+static inline void tcg_out_add(TCGContext *s, TCGReg ret, TCGReg arg1,
+                               TCGArg arg2, int const_arg2)
+{
+    if (const_arg2 && arg2 == sextract64(arg2, 0, 14)) {
+        tcg_out_bundle(s, mmI,
+                       INSN_NOP_M,
+                       INSN_NOP_M,
+                       tcg_opc_a4(TCG_REG_P0, OPC_ADDS_A4, ret, arg2, arg1));
+    } else {
+        tcg_out_alu(s, OPC_ADD_A1, 0, ret, arg1, 0, arg2, const_arg2);
+    }
+}
+
+static inline void tcg_out_sub(TCGContext *s, TCGReg ret, TCGArg arg1,
+                               int const_arg1, TCGArg arg2, int const_arg2)
+{
+    if (!const_arg1 && const_arg2 && -arg2 == sextract64(-arg2, 0, 14)) {
+        tcg_out_bundle(s, mmI,
+                       INSN_NOP_M,
+                       INSN_NOP_M,
+                       tcg_opc_a4(TCG_REG_P0, OPC_ADDS_A4, ret, -arg2, arg1));
+    } else {
+        tcg_out_alu(s, OPC_SUB_A1, OPC_SUB_A3, ret,
+                    arg1, const_arg1, arg2, const_arg2);
+    }
+}
+
+static inline void tcg_out_eqv(TCGContext *s, TCGArg ret,
+                               TCGArg arg1, int const_arg1,
+                               TCGArg arg2, int const_arg2)
+{
+    tcg_out_bundle(s, mII,
+                   INSN_NOP_M,
+                   tcg_opc_a1 (TCG_REG_P0, OPC_XOR_A1, ret, arg1, arg2),
+                   tcg_opc_a3 (TCG_REG_P0, OPC_ANDCM_A3, ret, -1, ret));
+}
+
+static inline void tcg_out_nand(TCGContext *s, TCGArg ret,
+                                TCGArg arg1, int const_arg1,
+                                TCGArg arg2, int const_arg2)
+{
+    tcg_out_bundle(s, mII,
+                   INSN_NOP_M,
+                   tcg_opc_a1 (TCG_REG_P0, OPC_AND_A1, ret, arg1, arg2),
+                   tcg_opc_a3 (TCG_REG_P0, OPC_ANDCM_A3, ret, -1, ret));
+}
+
+static inline void tcg_out_nor(TCGContext *s, TCGArg ret,
+                               TCGArg arg1, int const_arg1,
+                               TCGArg arg2, int const_arg2)
+{
+    tcg_out_bundle(s, mII,
+                   INSN_NOP_M,
+                   tcg_opc_a1 (TCG_REG_P0, OPC_OR_A1, ret, arg1, arg2),
+                   tcg_opc_a3 (TCG_REG_P0, OPC_ANDCM_A3, ret, -1, ret));
+}
+
+static inline void tcg_out_orc(TCGContext *s, TCGArg ret,
+                               TCGArg arg1, int const_arg1,
+                               TCGArg arg2, int const_arg2)
+{
+    tcg_out_bundle(s, mII,
+                   INSN_NOP_M,
+                   tcg_opc_a3 (TCG_REG_P0, OPC_ANDCM_A3, TCG_REG_R2, -1, arg2),
+                   tcg_opc_a1 (TCG_REG_P0, OPC_OR_A1, ret, arg1, TCG_REG_R2));
+}
+
+static inline void tcg_out_mul(TCGContext *s, TCGArg ret,
+                               TCGArg arg1, TCGArg arg2)
+{
+    tcg_out_bundle(s, mmI,
+                   tcg_opc_m18(TCG_REG_P0, OPC_SETF_SIG_M18, TCG_REG_F6, arg1),
+                   tcg_opc_m18(TCG_REG_P0, OPC_SETF_SIG_M18, TCG_REG_F7, arg2),
+                   INSN_NOP_I);
+    tcg_out_bundle(s, mmF,
+                   INSN_NOP_M,
+                   INSN_NOP_M,
+                   tcg_opc_f2 (TCG_REG_P0, OPC_XMA_L_F2, TCG_REG_F6, TCG_REG_F6,
+                               TCG_REG_F7, TCG_REG_F0));
+    tcg_out_bundle(s, miI,
+                   tcg_opc_m19(TCG_REG_P0, OPC_GETF_SIG_M19, ret, TCG_REG_F6),
+                   INSN_NOP_I,
+                   INSN_NOP_I);
+}
+
+static inline void tcg_out_sar_i32(TCGContext *s, TCGArg ret, TCGArg arg1,
+                                   TCGArg arg2, int const_arg2)
+{
+    if (const_arg2) {
+        tcg_out_bundle(s, miI,
+                       INSN_NOP_M,
+                       INSN_NOP_I,
+                       tcg_opc_i11(TCG_REG_P0, OPC_EXTR_I11,
+                                   ret, arg1, arg2, 31 - arg2));
+    } else {
+        tcg_out_bundle(s, mII,
+                       tcg_opc_a3 (TCG_REG_P0, OPC_AND_A3,
+                                   TCG_REG_R3, 0x1f, arg2),
+                       tcg_opc_i29(TCG_REG_P0, OPC_SXT4_I29, TCG_REG_R2, arg1),
+                       tcg_opc_i5 (TCG_REG_P0, OPC_SHR_I5, ret,
+                                   TCG_REG_R2, TCG_REG_R3));
+    }
+}
+
+static inline void tcg_out_sar_i64(TCGContext *s, TCGArg ret, TCGArg arg1,
+                                   TCGArg arg2, int const_arg2)
+{
+    if (const_arg2) {
+        tcg_out_bundle(s, miI,
+                       INSN_NOP_M,
+                       INSN_NOP_I,
+                       tcg_opc_i11(TCG_REG_P0, OPC_EXTR_I11,
+                                   ret, arg1, arg2, 63 - arg2));
+    } else {
+        tcg_out_bundle(s, miI,
+                       INSN_NOP_M,
+                       INSN_NOP_I,
+                       tcg_opc_i5 (TCG_REG_P0, OPC_SHR_I5, ret, arg1, arg2));
+    }
+}
+
+static inline void tcg_out_shl_i32(TCGContext *s, TCGArg ret, TCGArg arg1,
+                                   TCGArg arg2, int const_arg2)
+{
+    if (const_arg2) {
+        tcg_out_bundle(s, miI,
+                       INSN_NOP_M,
+                       INSN_NOP_I,
+                       tcg_opc_i12(TCG_REG_P0, OPC_DEP_Z_I12, ret,
+                                   arg1, 63 - arg2, 31 - arg2));
+    } else {
+        tcg_out_bundle(s, mII,
+                       INSN_NOP_M,
+                       tcg_opc_a3 (TCG_REG_P0, OPC_AND_A3, TCG_REG_R2,
+                                   0x1f, arg2),
+                       tcg_opc_i7 (TCG_REG_P0, OPC_SHL_I7, ret,
+                                   arg1, TCG_REG_R2));
+    }
+}
+
+static inline void tcg_out_shl_i64(TCGContext *s, TCGArg ret, TCGArg arg1,
+                                   TCGArg arg2, int const_arg2)
+{
+    if (const_arg2) {
+        tcg_out_bundle(s, miI,
+                       INSN_NOP_M,
+                       INSN_NOP_I,
+                       tcg_opc_i12(TCG_REG_P0, OPC_DEP_Z_I12, ret,
+                                   arg1, 63 - arg2, 63 - arg2));
+    } else {
+        tcg_out_bundle(s, miI,
+                       INSN_NOP_M,
+                       INSN_NOP_I,
+                       tcg_opc_i7 (TCG_REG_P0, OPC_SHL_I7, ret,
+                                   arg1, arg2));
+    }
+}
+
+static inline void tcg_out_shr_i32(TCGContext *s, TCGArg ret, TCGArg arg1,
+                                   TCGArg arg2, int const_arg2)
+{
+    if (const_arg2) {
+        tcg_out_bundle(s, miI,
+                       INSN_NOP_M,
+                       INSN_NOP_I,
+                       tcg_opc_i11(TCG_REG_P0, OPC_EXTR_U_I11, ret,
+                                   arg1, arg2, 31 - arg2));
+    } else {
+        tcg_out_bundle(s, mII,
+                       tcg_opc_a3 (TCG_REG_P0, OPC_AND_A3, TCG_REG_R3,
+                                   0x1f, arg2),
+                       tcg_opc_i29(TCG_REG_P0, OPC_ZXT4_I29, TCG_REG_R2, arg1),
+                       tcg_opc_i5 (TCG_REG_P0, OPC_SHR_U_I5, ret,
+                                   TCG_REG_R2, TCG_REG_R3));
+    }
+}
+
+static inline void tcg_out_shr_i64(TCGContext *s, TCGArg ret, TCGArg arg1,
+                                   TCGArg arg2, int const_arg2)
+{
+    if (const_arg2) {
+        tcg_out_bundle(s, miI,
+                       INSN_NOP_M,
+                       INSN_NOP_I,
+                       tcg_opc_i11(TCG_REG_P0, OPC_EXTR_U_I11, ret,
+                                   arg1, arg2, 63 - arg2));
+    } else {
+        tcg_out_bundle(s, miI,
+                       INSN_NOP_M,
+                       INSN_NOP_I,
+                       tcg_opc_i5 (TCG_REG_P0, OPC_SHR_U_I5, ret,
+                                   arg1, arg2));
+    }
+}
+
+static inline void tcg_out_rotl_i32(TCGContext *s, TCGArg ret, TCGArg arg1,
+                                    TCGArg arg2, int const_arg2)
+{
+    if (const_arg2) {
+        tcg_out_bundle(s, mII,
+                       INSN_NOP_M,
+                       tcg_opc_i2 (TCG_REG_P0, OPC_UNPACK4_L_I2,
+                                   TCG_REG_R2, arg1, arg1),
+                       tcg_opc_i11(TCG_REG_P0, OPC_EXTR_U_I11, ret,
+                                   TCG_REG_R2, 32 - arg2, 31));
+    } else {
+        tcg_out_bundle(s, miI,
+                       INSN_NOP_M,
+                       tcg_opc_i2 (TCG_REG_P0, OPC_UNPACK4_L_I2,
+                                   TCG_REG_R2, arg1, arg1),
+                       tcg_opc_a3 (TCG_REG_P0, OPC_AND_A3, TCG_REG_R3,
+                                   0x1f, arg2));
+        tcg_out_bundle(s, mII,
+                       INSN_NOP_M,
+                       tcg_opc_a3 (TCG_REG_P0, OPC_SUB_A3, TCG_REG_R3,
+                                   0x20, TCG_REG_R3),
+                       tcg_opc_i5 (TCG_REG_P0, OPC_SHR_U_I5, ret,
+                                   TCG_REG_R2, TCG_REG_R3));
+    }
+}
+
+static inline void tcg_out_rotl_i64(TCGContext *s, TCGArg ret, TCGArg arg1,
+                                    TCGArg arg2, int const_arg2)
+{
+    if (const_arg2) {
+        tcg_out_bundle(s, miI,
+                       INSN_NOP_M,
+                       INSN_NOP_I,
+                       tcg_opc_i10(TCG_REG_P0, OPC_SHRP_I10, ret, arg1,
+                                   arg1, 0x40 - arg2));
+    } else {
+        tcg_out_bundle(s, mII,
+                       tcg_opc_a3 (TCG_REG_P0, OPC_SUB_A3, TCG_REG_R2,
+                                   0x40, arg2),
+                       tcg_opc_i7 (TCG_REG_P0, OPC_SHL_I7, TCG_REG_R3,
+                                   arg1, arg2),
+                       tcg_opc_i5 (TCG_REG_P0, OPC_SHR_U_I5, TCG_REG_R2,
+                                   arg1, TCG_REG_R2));
+        tcg_out_bundle(s, miI,
+                       INSN_NOP_M,
+                       INSN_NOP_I,
+                       tcg_opc_a1 (TCG_REG_P0, OPC_OR_A1, ret,
+                                   TCG_REG_R2, TCG_REG_R3));
+    }
+}
+
+static inline void tcg_out_rotr_i32(TCGContext *s, TCGArg ret, TCGArg arg1,
+                                    TCGArg arg2, int const_arg2)
+{
+    if (const_arg2) {
+        tcg_out_bundle(s, mII,
+                       INSN_NOP_M,
+                       tcg_opc_i2 (TCG_REG_P0, OPC_UNPACK4_L_I2,
+                                   TCG_REG_R2, arg1, arg1),
+                       tcg_opc_i11(TCG_REG_P0, OPC_EXTR_U_I11, ret,
+                                   TCG_REG_R2, arg2, 31));
+    } else {
+        tcg_out_bundle(s, mII,
+                       tcg_opc_a3 (TCG_REG_P0, OPC_AND_A3, TCG_REG_R3,
+                                   0x1f, arg2),
+                       tcg_opc_i2 (TCG_REG_P0, OPC_UNPACK4_L_I2,
+                                   TCG_REG_R2, arg1, arg1),
+                       tcg_opc_i5 (TCG_REG_P0, OPC_SHR_U_I5, ret,
+                                   TCG_REG_R2, TCG_REG_R3));
+    }
+}
+
+static inline void tcg_out_rotr_i64(TCGContext *s, TCGArg ret, TCGArg arg1,
+                                    TCGArg arg2, int const_arg2)
+{
+    if (const_arg2) {
+        tcg_out_bundle(s, miI,
+                       INSN_NOP_M,
+                       INSN_NOP_I,
+                       tcg_opc_i10(TCG_REG_P0, OPC_SHRP_I10, ret, arg1,
+                                   arg1, arg2));
+    } else {
+        tcg_out_bundle(s, mII,
+                       tcg_opc_a3 (TCG_REG_P0, OPC_SUB_A3, TCG_REG_R2,
+                                   0x40, arg2),
+                       tcg_opc_i5 (TCG_REG_P0, OPC_SHR_U_I5, TCG_REG_R3,
+                                   arg1, arg2),
+                       tcg_opc_i7 (TCG_REG_P0, OPC_SHL_I7, TCG_REG_R2,
+                                   arg1, TCG_REG_R2));
+        tcg_out_bundle(s, miI,
+                       INSN_NOP_M,
+                       INSN_NOP_I,
+                       tcg_opc_a1 (TCG_REG_P0, OPC_OR_A1, ret,
+                                   TCG_REG_R2, TCG_REG_R3));
+    }
+}
+
+static const uint64_t opc_ext_i29[8] = {
+    OPC_ZXT1_I29, OPC_ZXT2_I29, OPC_ZXT4_I29, 0,
+    OPC_SXT1_I29, OPC_SXT2_I29, OPC_SXT4_I29, 0
+};
+
+static inline uint64_t tcg_opc_ext_i(int qp, TCGMemOp opc, TCGReg d, TCGReg s)
+{
+    if ((opc & MO_SIZE) == MO_64) {
+        return tcg_opc_mov_a(qp, d, s);
+    } else {
+        return tcg_opc_i29(qp, opc_ext_i29[opc & MO_SSIZE], d, s);
+    }
+}
+
+static inline void tcg_out_ext(TCGContext *s, uint64_t opc_i29,
+                               TCGArg ret, TCGArg arg)
+{
+    tcg_out_bundle(s, miI,
+                   INSN_NOP_M,
+                   INSN_NOP_I,
+                   tcg_opc_i29(TCG_REG_P0, opc_i29, ret, arg));
+}
+
+static inline uint64_t tcg_opc_bswap64_i(int qp, TCGReg d, TCGReg s)
+{
+    return tcg_opc_i3(qp, OPC_MUX1_I3, d, s, 0xb);
+}
+
+static inline void tcg_out_bswap16(TCGContext *s, TCGArg ret, TCGArg arg)
+{
+    tcg_out_bundle(s, mII,
+                   INSN_NOP_M,
+                   tcg_opc_i12(TCG_REG_P0, OPC_DEP_Z_I12, ret, arg, 15, 15),
+                   tcg_opc_bswap64_i(TCG_REG_P0, ret, ret));
+}
+
+static inline void tcg_out_bswap32(TCGContext *s, TCGArg ret, TCGArg arg)
+{
+    tcg_out_bundle(s, mII,
+                   INSN_NOP_M,
+                   tcg_opc_i12(TCG_REG_P0, OPC_DEP_Z_I12, ret, arg, 31, 31),
+                   tcg_opc_bswap64_i(TCG_REG_P0, ret, ret));
+}
+
+static inline void tcg_out_bswap64(TCGContext *s, TCGArg ret, TCGArg arg)
+{
+    tcg_out_bundle(s, miI,
+                   INSN_NOP_M,
+                   INSN_NOP_I,
+                   tcg_opc_bswap64_i(TCG_REG_P0, ret, arg));
+}
+
+static inline void tcg_out_deposit(TCGContext *s, TCGArg ret, TCGArg a1,
+                                   TCGArg a2, int const_a2, int pos, int len)
+{
+    uint64_t i1 = 0, i2 = 0;
+    int cpos = 63 - pos, lm1 = len - 1;
+
+    if (const_a2) {
+        /* Truncate the value of a constant a2 to the width of the field.  */
+        int mask = (1u << len) - 1;
+        a2 &= mask;
+
+        if (a2 == 0 || a2 == mask) {
+            /* 1-bit signed constant inserted into register.  */
+            i2 = tcg_opc_i14(TCG_REG_P0, OPC_DEP_I14, ret, a2, a1, cpos, lm1);
+        } else {
+            /* Otherwise, load any constant into a temporary.  Do this into
+               the first I slot to help out with cross-unit delays.  */
+            i1 = tcg_opc_movi_a(TCG_REG_P0, TCG_REG_R2, a2);
+            a2 = TCG_REG_R2;
+        }
+    }
+    if (i2 == 0) {
+        i2 = tcg_opc_i15(TCG_REG_P0, OPC_DEP_I15, ret, a2, a1, cpos, lm1);
+    }
+    tcg_out_bundle(s, (i1 ? mII : miI),
+                   INSN_NOP_M,
+                   i1 ? i1 : INSN_NOP_I,
+                   i2);
+}
+
+static inline uint64_t tcg_opc_cmp_a(int qp, TCGCond cond, TCGArg arg1,
+                                     TCGArg arg2, int cmp4)
+{
+    uint64_t opc_eq_a6, opc_lt_a6, opc_ltu_a6;
+
+    if (cmp4) {
+        opc_eq_a6 = OPC_CMP4_EQ_A6;
+        opc_lt_a6 = OPC_CMP4_LT_A6;
+        opc_ltu_a6 = OPC_CMP4_LTU_A6;
+    } else {
+        opc_eq_a6 = OPC_CMP_EQ_A6;
+        opc_lt_a6 = OPC_CMP_LT_A6;
+        opc_ltu_a6 = OPC_CMP_LTU_A6;
+    }
+
+    switch (cond) {
+    case TCG_COND_EQ:
+        return tcg_opc_a6 (qp, opc_eq_a6,  TCG_REG_P6, TCG_REG_P7, arg1, arg2);
+    case TCG_COND_NE:
+        return tcg_opc_a6 (qp, opc_eq_a6,  TCG_REG_P7, TCG_REG_P6, arg1, arg2);
+    case TCG_COND_LT:
+        return tcg_opc_a6 (qp, opc_lt_a6,  TCG_REG_P6, TCG_REG_P7, arg1, arg2);
+    case TCG_COND_LTU:
+        return tcg_opc_a6 (qp, opc_ltu_a6, TCG_REG_P6, TCG_REG_P7, arg1, arg2);
+    case TCG_COND_GE:
+        return tcg_opc_a6 (qp, opc_lt_a6,  TCG_REG_P7, TCG_REG_P6, arg1, arg2);
+    case TCG_COND_GEU:
+        return tcg_opc_a6 (qp, opc_ltu_a6, TCG_REG_P7, TCG_REG_P6, arg1, arg2);
+    case TCG_COND_LE:
+        return tcg_opc_a6 (qp, opc_lt_a6,  TCG_REG_P7, TCG_REG_P6, arg2, arg1);
+    case TCG_COND_LEU:
+        return tcg_opc_a6 (qp, opc_ltu_a6, TCG_REG_P7, TCG_REG_P6, arg2, arg1);
+    case TCG_COND_GT:
+        return tcg_opc_a6 (qp, opc_lt_a6,  TCG_REG_P6, TCG_REG_P7, arg2, arg1);
+    case TCG_COND_GTU:
+        return tcg_opc_a6 (qp, opc_ltu_a6, TCG_REG_P6, TCG_REG_P7, arg2, arg1);
+    default:
+        tcg_abort();
+        break;
+    }
+}
+
+static inline void tcg_out_brcond(TCGContext *s, TCGCond cond, TCGReg arg1,
+                                  TCGReg arg2, TCGLabel *l, int cmp4)
+{
+    uint64_t imm;
+
+    /* We pay attention here to not modify the branch target by reading
+       the existing value and using it again. This ensure that caches and
+       memory are kept coherent during retranslation. */
+    if (l->has_value) {
+        imm = l->u.value_ptr - s->code_ptr;
+    } else {
+        imm = get_reloc_pcrel21b_slot2(s->code_ptr);
+        tcg_out_reloc(s, s->code_ptr, R_IA64_PCREL21B, l, 0);
+    }
+
+    tcg_out_bundle(s, miB,
+                   INSN_NOP_M,
+                   tcg_opc_cmp_a(TCG_REG_P0, cond, arg1, arg2, cmp4),
+                   tcg_opc_b1(TCG_REG_P6, OPC_BR_DPTK_FEW_B1, imm));
+}
+
+static inline void tcg_out_setcond(TCGContext *s, TCGCond cond, TCGArg ret,
+                                   TCGArg arg1, TCGArg arg2, int cmp4)
+{
+    tcg_out_bundle(s, MmI,
+                   tcg_opc_cmp_a(TCG_REG_P0, cond, arg1, arg2, cmp4),
+                   tcg_opc_movi_a(TCG_REG_P6, ret, 1),
+                   tcg_opc_movi_a(TCG_REG_P7, ret, 0));
+}
+
+static inline void tcg_out_movcond(TCGContext *s, TCGCond cond, TCGArg ret,
+                                   TCGArg c1, TCGArg c2,
+                                   TCGArg v1, int const_v1,
+                                   TCGArg v2, int const_v2, int cmp4)
+{
+    uint64_t opc1, opc2;
+
+    if (const_v1) {
+        opc1 = tcg_opc_movi_a(TCG_REG_P6, ret, v1);
+    } else if (ret == v1) {
+        opc1 = INSN_NOP_M;
+    } else {
+        opc1 = tcg_opc_mov_a(TCG_REG_P6, ret, v1);
+    }
+    if (const_v2) {
+        opc2 = tcg_opc_movi_a(TCG_REG_P7, ret, v2);
+    } else if (ret == v2) {
+        opc2 = INSN_NOP_I;
+    } else {
+        opc2 = tcg_opc_mov_a(TCG_REG_P7, ret, v2);
+    }
+
+    tcg_out_bundle(s, MmI,
+                   tcg_opc_cmp_a(TCG_REG_P0, cond, c1, c2, cmp4),
+                   opc1,
+                   opc2);
+}
+
+#if defined(CONFIG_SOFTMMU)
+/* We're expecting to use an signed 22-bit immediate add.  */
+QEMU_BUILD_BUG_ON(offsetof(CPUArchState, tlb_table[NB_MMU_MODES - 1][1])
+                  > 0x1fffff)
+
+/* Load and compare a TLB entry, and return the result in (p6, p7).
+   R2 is loaded with the addend TLB entry.
+   R57 is loaded with the address, zero extented on 32-bit targets.
+   R1, R3 are clobbered, leaving R56 free for...
+   BSWAP_1, BSWAP_2 and I-slot insns for swapping data for store.  */
+static inline void tcg_out_qemu_tlb(TCGContext *s, TCGReg addr_reg,
+                                    TCGMemOp s_bits, int off_rw, int off_add,
+                                    uint64_t bswap1, uint64_t bswap2)
+{
+     /*
+        .mii
+        mov	r2 = off_rw
+        extr.u	r3 = addr_reg, ...		# extract tlb page
+        zxt4	r57 = addr_reg                  # or mov for 64-bit guest
+        ;;
+        .mii
+        addl	r2 = r2, areg0
+        shl	r3 = r3, cteb                   # via dep.z
+        dep	r1 = 0, r57, ...                # zero page ofs, keep align
+        ;;
+        .mmi
+        add	r2 = r2, r3
+        ;;
+        ld4	r3 = [r2], off_add-off_rw	# or ld8 for 64-bit guest
+        nop
+        ;;
+        .mmi
+        nop
+        cmp.eq	p6, p7 = r3, r58
+        nop
+        ;;
+      */
+    tcg_out_bundle(s, miI,
+                   tcg_opc_movi_a(TCG_REG_P0, TCG_REG_R2, off_rw),
+                   tcg_opc_i11(TCG_REG_P0, OPC_EXTR_U_I11, TCG_REG_R3,
+                               addr_reg, TARGET_PAGE_BITS, CPU_TLB_BITS - 1),
+                   tcg_opc_ext_i(TCG_REG_P0,
+                                 TARGET_LONG_BITS == 32 ? MO_UL : MO_Q,
+                                 TCG_REG_R57, addr_reg));
+    tcg_out_bundle(s, miI,
+                   tcg_opc_a1 (TCG_REG_P0, OPC_ADD_A1, TCG_REG_R2,
+                               TCG_REG_R2, TCG_AREG0),
+                   tcg_opc_i12(TCG_REG_P0, OPC_DEP_Z_I12, TCG_REG_R3,
+                               TCG_REG_R3, 63 - CPU_TLB_ENTRY_BITS,
+                               63 - CPU_TLB_ENTRY_BITS),
+                   tcg_opc_i14(TCG_REG_P0, OPC_DEP_I14, TCG_REG_R1, 0,
+                               TCG_REG_R57, 63 - s_bits,
+                               TARGET_PAGE_BITS - s_bits - 1));
+    tcg_out_bundle(s, MmI,
+                   tcg_opc_a1 (TCG_REG_P0, OPC_ADD_A1,
+                               TCG_REG_R2, TCG_REG_R2, TCG_REG_R3),
+                   tcg_opc_m3 (TCG_REG_P0,
+                               (TARGET_LONG_BITS == 32
+                                ? OPC_LD4_M3 : OPC_LD8_M3), TCG_REG_R3,
+                               TCG_REG_R2, off_add - off_rw),
+                   bswap1);
+    tcg_out_bundle(s, mmI,
+                   tcg_opc_m1 (TCG_REG_P0, OPC_LD8_M1, TCG_REG_R2, TCG_REG_R2),
+                   tcg_opc_a6 (TCG_REG_P0, OPC_CMP_EQ_A6, TCG_REG_P6,
+                               TCG_REG_P7, TCG_REG_R1, TCG_REG_R3),
+                   bswap2);
+}
+
+typedef struct TCGLabelQemuLdst {
+    bool is_ld;
+    TCGMemOp size;
+    tcg_insn_unit *label_ptr;     /* label pointers to be updated */
+    struct TCGLabelQemuLdst *next;
+} TCGLabelQemuLdst;
+
+typedef struct TCGBackendData {
+    TCGLabelQemuLdst *labels;
+} TCGBackendData;
+
+static inline void tcg_out_tb_init(TCGContext *s)
+{
+    s->be->labels = NULL;
+}
+
+static void add_qemu_ldst_label(TCGContext *s, bool is_ld, TCGMemOp opc,
+                                tcg_insn_unit *label_ptr)
+{
+    TCGBackendData *be = s->be;
+    TCGLabelQemuLdst *l = tcg_malloc(sizeof(*l));
+
+    l->is_ld = is_ld;
+    l->size = opc & MO_SIZE;
+    l->label_ptr = label_ptr;
+    l->next = be->labels;
+    be->labels = l;
+}
+
+static void tcg_out_tb_finalize(TCGContext *s)
+{
+    static const void * const helpers[8] = {
+        helper_ret_stb_mmu,
+        helper_le_stw_mmu,
+        helper_le_stl_mmu,
+        helper_le_stq_mmu,
+        helper_ret_ldub_mmu,
+        helper_le_lduw_mmu,
+        helper_le_ldul_mmu,
+        helper_le_ldq_mmu,
+    };
+    tcg_insn_unit *thunks[8] = { };
+    TCGLabelQemuLdst *l;
+
+    for (l = s->be->labels; l != NULL; l = l->next) {
+        long x = l->is_ld * 4 + l->size;
+        tcg_insn_unit *dest = thunks[x];
+
+        /* The out-of-line thunks are all the same; load the return address
+           from B0, load the GP, and branch to the code.  Note that we are
+           always post-call, so the register window has rolled, so we're
+           using incomming parameter register numbers, not outgoing.  */
+        if (dest == NULL) {
+            uintptr_t *desc = (uintptr_t *)helpers[x];
+            uintptr_t func = desc[0], gp = desc[1], disp;
+
+            thunks[x] = dest = s->code_ptr;
+
+            tcg_out_bundle(s, mlx,
+                           INSN_NOP_M,
+                           tcg_opc_l2 (gp),
+                           tcg_opc_x2 (TCG_REG_P0, OPC_MOVL_X2,
+                                       TCG_REG_R1, gp));
+            tcg_out_bundle(s, mii,
+                           INSN_NOP_M,
+                           INSN_NOP_I,
+                           tcg_opc_i22(TCG_REG_P0, OPC_MOV_I22,
+                                       l->is_ld ? TCG_REG_R35 : TCG_REG_R36,
+                                       TCG_REG_B0));
+            disp = (tcg_insn_unit *)func - s->code_ptr;
+            tcg_out_bundle(s, mLX,
+                           INSN_NOP_M,
+                           tcg_opc_l3 (disp),
+                           tcg_opc_x3 (TCG_REG_P0, OPC_BRL_SPTK_MANY_X3, disp));
+        }
+
+        reloc_pcrel21b_slot2(l->label_ptr, dest);
+    }
+}
+
+static inline void tcg_out_qemu_ld(TCGContext *s, const TCGArg *args)
+{
+    static const uint64_t opc_ld_m1[4] = {
+        OPC_LD1_M1, OPC_LD2_M1, OPC_LD4_M1, OPC_LD8_M1
+    };
+    int addr_reg, data_reg, mem_index;
+    TCGMemOpIdx oi;
+    TCGMemOp opc, s_bits;
+    uint64_t fin1, fin2;
+    tcg_insn_unit *label_ptr;
+
+    data_reg = args[0];
+    addr_reg = args[1];
+    oi = args[2];
+    opc = get_memop(oi);
+    mem_index = get_mmuidx(oi);
+    s_bits = opc & MO_SIZE;
+
+    /* Read the TLB entry */
+    tcg_out_qemu_tlb(s, addr_reg, s_bits,
+                     offsetof(CPUArchState, tlb_table[mem_index][0].addr_read),
+                     offsetof(CPUArchState, tlb_table[mem_index][0].addend),
+                     INSN_NOP_I, INSN_NOP_I);
+
+    /* P6 is the fast path, and P7 the slow path */
+
+    fin2 = 0;
+    if (opc & MO_BSWAP) {
+        fin1 = tcg_opc_bswap64_i(TCG_REG_P0, data_reg, TCG_REG_R8);
+        if (s_bits < MO_64) {
+            int shift = 64 - (8 << s_bits);
+            fin2 = (opc & MO_SIGN ? OPC_EXTR_I11 : OPC_EXTR_U_I11);
+            fin2 = tcg_opc_i11(TCG_REG_P0, fin2,
+                               data_reg, data_reg, shift, 63 - shift);
+        }
+    } else {
+        fin1 = tcg_opc_ext_i(TCG_REG_P0, opc, data_reg, TCG_REG_R8);
+    }
+
+    tcg_out_bundle(s, mmI,
+                   tcg_opc_mov_a(TCG_REG_P7, TCG_REG_R56, TCG_AREG0),
+                   tcg_opc_a1 (TCG_REG_P6, OPC_ADD_A1, TCG_REG_R2,
+                               TCG_REG_R2, TCG_REG_R57),
+                   tcg_opc_movi_a(TCG_REG_P7, TCG_REG_R58, oi));
+    label_ptr = s->code_ptr;
+    tcg_out_bundle(s, miB,
+                   tcg_opc_m1 (TCG_REG_P6, opc_ld_m1[s_bits],
+                               TCG_REG_R8, TCG_REG_R2),
+                   INSN_NOP_I,
+                   tcg_opc_b3 (TCG_REG_P7, OPC_BR_CALL_SPNT_FEW_B3, TCG_REG_B0,
+                               get_reloc_pcrel21b_slot2(label_ptr)));
+
+    add_qemu_ldst_label(s, 1, opc, label_ptr);
+
+    /* Note that we always use LE helper functions, so the bswap insns
+       here for the fast path also apply to the slow path.  */
+    tcg_out_bundle(s, (fin2 ? mII : miI),
+                   INSN_NOP_M,
+                   fin1,
+                   fin2 ? fin2 : INSN_NOP_I);
+}
+
+static inline void tcg_out_qemu_st(TCGContext *s, const TCGArg *args)
+{
+    static const uint64_t opc_st_m4[4] = {
+        OPC_ST1_M4, OPC_ST2_M4, OPC_ST4_M4, OPC_ST8_M4
+    };
+    TCGReg addr_reg, data_reg;
+    int mem_index;
+    uint64_t pre1, pre2;
+    TCGMemOpIdx oi;
+    TCGMemOp opc, s_bits;
+    tcg_insn_unit *label_ptr;
+
+    data_reg = args[0];
+    addr_reg = args[1];
+    oi = args[2];
+    opc = get_memop(oi);
+    mem_index = get_mmuidx(oi);
+    s_bits = opc & MO_SIZE;
+
+    /* Note that we always use LE helper functions, so the bswap insns
+       that are here for the fast path also apply to the slow path,
+       and move the data into the argument register.  */
+    pre2 = INSN_NOP_I;
+    if (opc & MO_BSWAP) {
+        pre1 = tcg_opc_bswap64_i(TCG_REG_P0, TCG_REG_R58, data_reg);
+        if (s_bits < MO_64) {
+            int shift = 64 - (8 << s_bits);
+            pre2 = tcg_opc_i11(TCG_REG_P0, OPC_EXTR_U_I11,
+                               TCG_REG_R58, TCG_REG_R58, shift, 63 - shift);
+        }
+    } else {
+        /* Just move the data into place for the slow path.  */
+        pre1 = tcg_opc_ext_i(TCG_REG_P0, opc, TCG_REG_R58, data_reg);
+    }
+
+    tcg_out_qemu_tlb(s, addr_reg, s_bits,
+                     offsetof(CPUArchState, tlb_table[mem_index][0].addr_write),
+                     offsetof(CPUArchState, tlb_table[mem_index][0].addend),
+                     pre1, pre2);
+
+    /* P6 is the fast path, and P7 the slow path */
+    tcg_out_bundle(s, mmI,
+                   tcg_opc_mov_a(TCG_REG_P7, TCG_REG_R56, TCG_AREG0),
+                   tcg_opc_a1 (TCG_REG_P6, OPC_ADD_A1, TCG_REG_R2,
+                               TCG_REG_R2, TCG_REG_R57),
+                   tcg_opc_movi_a(TCG_REG_P7, TCG_REG_R59, oi));
+    label_ptr = s->code_ptr;
+    tcg_out_bundle(s, miB,
+                   tcg_opc_m4 (TCG_REG_P6, opc_st_m4[s_bits],
+                               TCG_REG_R58, TCG_REG_R2),
+                   INSN_NOP_I,
+                   tcg_opc_b3 (TCG_REG_P7, OPC_BR_CALL_SPNT_FEW_B3, TCG_REG_B0,
+                               get_reloc_pcrel21b_slot2(label_ptr)));
+
+    add_qemu_ldst_label(s, 0, opc, label_ptr);
+}
+
+#else /* !CONFIG_SOFTMMU */
+# include "tcg-be-null.h"
+
+static inline void tcg_out_qemu_ld(TCGContext *s, const TCGArg *args)
+{
+    static uint64_t const opc_ld_m1[4] = {
+        OPC_LD1_M1, OPC_LD2_M1, OPC_LD4_M1, OPC_LD8_M1
+    };
+    int addr_reg, data_reg;
+    TCGMemOp opc, s_bits, bswap;
+
+    data_reg = args[0];
+    addr_reg = args[1];
+    opc = args[2];
+    s_bits = opc & MO_SIZE;
+    bswap = opc & MO_BSWAP;
+
+#if TARGET_LONG_BITS == 32
+    if (GUEST_BASE != 0) {
+        tcg_out_bundle(s, mII,
+                       INSN_NOP_M,
+                       tcg_opc_i29(TCG_REG_P0, OPC_ZXT4_I29,
+                                   TCG_REG_R3, addr_reg),
+                       tcg_opc_a1 (TCG_REG_P0, OPC_ADD_A1, TCG_REG_R2,
+                                   TCG_GUEST_BASE_REG, TCG_REG_R3));
+    } else {
+        tcg_out_bundle(s, miI,
+                       INSN_NOP_M,
+                       tcg_opc_i29(TCG_REG_P0, OPC_ZXT4_I29,
+                                   TCG_REG_R2, addr_reg),
+                       INSN_NOP_I);
+    }
+
+    if (!bswap) {
+        if (!(opc & MO_SIGN)) {
+            tcg_out_bundle(s, miI,
+                           tcg_opc_m1 (TCG_REG_P0, opc_ld_m1[s_bits],
+                                       data_reg, TCG_REG_R2),
+                           INSN_NOP_I,
+                           INSN_NOP_I);
+        } else {
+            tcg_out_bundle(s, mII,
+                           tcg_opc_m1 (TCG_REG_P0, opc_ld_m1[s_bits],
+                                       data_reg, TCG_REG_R2),
+                           INSN_NOP_I,
+                           tcg_opc_ext_i(TCG_REG_P0, opc, data_reg, data_reg));
+        }
+    } else if (s_bits == MO_64) {
+            tcg_out_bundle(s, mII,
+                           tcg_opc_m1 (TCG_REG_P0, opc_ld_m1[s_bits],
+                                       data_reg, TCG_REG_R2),
+                           INSN_NOP_I,
+                           tcg_opc_bswap64_i(TCG_REG_P0, data_reg, data_reg));
+    } else {
+        if (s_bits == MO_16) {
+            tcg_out_bundle(s, mII,
+                           tcg_opc_m1 (TCG_REG_P0, opc_ld_m1[s_bits],
+                                       data_reg, TCG_REG_R2),
+                           INSN_NOP_I,
+                           tcg_opc_i12(TCG_REG_P0, OPC_DEP_Z_I12,
+                                      data_reg, data_reg, 15, 15));
+        } else {
+            tcg_out_bundle(s, mII,
+                           tcg_opc_m1 (TCG_REG_P0, opc_ld_m1[s_bits],
+                                       data_reg, TCG_REG_R2),
+                           INSN_NOP_I,
+                           tcg_opc_i12(TCG_REG_P0, OPC_DEP_Z_I12,
+                                      data_reg, data_reg, 31, 31));
+        }
+        if (!(opc & MO_SIGN)) {
+            tcg_out_bundle(s, miI,
+                           INSN_NOP_M,
+                           INSN_NOP_I,
+                           tcg_opc_bswap64_i(TCG_REG_P0, data_reg, data_reg));
+        } else {
+            tcg_out_bundle(s, mII,
+                           INSN_NOP_M,
+                           tcg_opc_bswap64_i(TCG_REG_P0, data_reg, data_reg),
+                           tcg_opc_ext_i(TCG_REG_P0, opc, data_reg, data_reg));
+        }
+    }
+#else
+    if (GUEST_BASE != 0) {
+        tcg_out_bundle(s, MmI,
+                       tcg_opc_a1 (TCG_REG_P0, OPC_ADD_A1, TCG_REG_R2,
+                                   TCG_GUEST_BASE_REG, addr_reg),
+                       tcg_opc_m1 (TCG_REG_P0, opc_ld_m1[s_bits],
+                                   data_reg, TCG_REG_R2),
+                       INSN_NOP_I);
+    } else {
+        tcg_out_bundle(s, mmI,
+                       INSN_NOP_M,
+                       tcg_opc_m1 (TCG_REG_P0, opc_ld_m1[s_bits],
+                                   data_reg, addr_reg),
+                       INSN_NOP_I);
+    }
+
+    if (bswap && s_bits == MO_16) {
+        tcg_out_bundle(s, mII,
+                       INSN_NOP_M,
+                       tcg_opc_i12(TCG_REG_P0, OPC_DEP_Z_I12,
+                                   data_reg, data_reg, 15, 15),
+                       tcg_opc_bswap64_i(TCG_REG_P0, data_reg, data_reg));
+    } else if (bswap && s_bits == MO_32) {
+        tcg_out_bundle(s, mII,
+                       INSN_NOP_M,
+                       tcg_opc_i12(TCG_REG_P0, OPC_DEP_Z_I12,
+                                   data_reg, data_reg, 31, 31),
+                       tcg_opc_bswap64_i(TCG_REG_P0, data_reg, data_reg));
+    } else if (bswap && s_bits == MO_64) {
+        tcg_out_bundle(s, miI,
+                       INSN_NOP_M,
+                       INSN_NOP_I,
+                       tcg_opc_bswap64_i(TCG_REG_P0, data_reg, data_reg));
+    }
+    if (opc & MO_SIGN) {
+        tcg_out_bundle(s, miI,
+                       INSN_NOP_M,
+                       INSN_NOP_I,
+                       tcg_opc_ext_i(TCG_REG_P0, opc, data_reg, data_reg));
+    }
+#endif
+}
+
+static inline void tcg_out_qemu_st(TCGContext *s, const TCGArg *args)
+{
+    static uint64_t const opc_st_m4[4] = {
+        OPC_ST1_M4, OPC_ST2_M4, OPC_ST4_M4, OPC_ST8_M4
+    };
+    int addr_reg, data_reg;
+#if TARGET_LONG_BITS == 64
+    uint64_t add_guest_base;
+#endif
+    TCGMemOp opc, s_bits, bswap;
+
+    data_reg = args[0];
+    addr_reg = args[1];
+    opc = args[2];
+    s_bits = opc & MO_SIZE;
+    bswap = opc & MO_BSWAP;
+
+#if TARGET_LONG_BITS == 32
+    if (GUEST_BASE != 0) {
+        tcg_out_bundle(s, mII,
+                       INSN_NOP_M,
+                       tcg_opc_i29(TCG_REG_P0, OPC_ZXT4_I29,
+                                   TCG_REG_R3, addr_reg),
+                       tcg_opc_a1 (TCG_REG_P0, OPC_ADD_A1, TCG_REG_R2,
+                                   TCG_GUEST_BASE_REG, TCG_REG_R3));
+    } else {
+        tcg_out_bundle(s, miI,
+                       INSN_NOP_M,
+                       tcg_opc_i29(TCG_REG_P0, OPC_ZXT4_I29,
+                                   TCG_REG_R2, addr_reg),
+                       INSN_NOP_I);
+    }
+
+    if (bswap) {
+        if (s_bits == MO_16) {
+            tcg_out_bundle(s, mII,
+                           INSN_NOP_M,
+                           tcg_opc_i12(TCG_REG_P0, OPC_DEP_Z_I12,
+                                       TCG_REG_R3, data_reg, 15, 15),
+                           tcg_opc_bswap64_i(TCG_REG_P0,
+                                             TCG_REG_R3, TCG_REG_R3));
+            data_reg = TCG_REG_R3;
+        } else if (s_bits == MO_32) {
+            tcg_out_bundle(s, mII,
+                           INSN_NOP_M,
+                           tcg_opc_i12(TCG_REG_P0, OPC_DEP_Z_I12,
+                                       TCG_REG_R3, data_reg, 31, 31),
+                           tcg_opc_bswap64_i(TCG_REG_P0,
+                                             TCG_REG_R3, TCG_REG_R3));
+            data_reg = TCG_REG_R3;
+        } else if (s_bits == MO_64) {
+            tcg_out_bundle(s, miI,
+                           INSN_NOP_M,
+                           INSN_NOP_I,
+                           tcg_opc_bswap64_i(TCG_REG_P0, TCG_REG_R3, data_reg));
+            data_reg = TCG_REG_R3;
+        }
+    }
+    tcg_out_bundle(s, mmI,
+                   tcg_opc_m4 (TCG_REG_P0, opc_st_m4[s_bits],
+                               data_reg, TCG_REG_R2),
+                   INSN_NOP_M,
+                   INSN_NOP_I);
+#else
+    if (GUEST_BASE != 0) {
+        add_guest_base = tcg_opc_a1 (TCG_REG_P0, OPC_ADD_A1, TCG_REG_R2,
+                                     TCG_GUEST_BASE_REG, addr_reg);
+        addr_reg = TCG_REG_R2;
+    } else {
+        add_guest_base = INSN_NOP_M;
+    }
+
+    if (!bswap) {
+        tcg_out_bundle(s, (GUEST_BASE ? MmI : mmI),
+                       add_guest_base,
+                       tcg_opc_m4 (TCG_REG_P0, opc_st_m4[s_bits],
+                                   data_reg, addr_reg),
+                       INSN_NOP_I);
+    } else {
+        if (s_bits == MO_16) {
+            tcg_out_bundle(s, mII,
+                           add_guest_base,
+                           tcg_opc_i12(TCG_REG_P0, OPC_DEP_Z_I12,
+                                       TCG_REG_R3, data_reg, 15, 15),
+                           tcg_opc_bswap64_i(TCG_REG_P0,
+                                             TCG_REG_R3, TCG_REG_R3));
+            data_reg = TCG_REG_R3;
+        } else if (s_bits == MO_32) {
+            tcg_out_bundle(s, mII,
+                           add_guest_base,
+                           tcg_opc_i12(TCG_REG_P0, OPC_DEP_Z_I12,
+                                       TCG_REG_R3, data_reg, 31, 31),
+                           tcg_opc_bswap64_i(TCG_REG_P0,
+                                             TCG_REG_R3, TCG_REG_R3));
+            data_reg = TCG_REG_R3;
+        } else if (s_bits == MO_64) {
+            tcg_out_bundle(s, miI,
+                           add_guest_base,
+                           INSN_NOP_I,
+                           tcg_opc_bswap64_i(TCG_REG_P0, TCG_REG_R3, data_reg));
+            data_reg = TCG_REG_R3;
+        }
+        tcg_out_bundle(s, miI,
+                       tcg_opc_m4 (TCG_REG_P0, opc_st_m4[s_bits],
+                                   data_reg, addr_reg),
+                       INSN_NOP_I,
+                       INSN_NOP_I);
+    }
+#endif
+}
+
+#endif
+
+static inline void tcg_out_op(TCGContext *s, TCGOpcode opc,
+                              const TCGArg *args, const int *const_args)
+{
+    switch(opc) {
+    case INDEX_op_exit_tb:
+        tcg_out_exit_tb(s, args[0]);
+        break;
+    case INDEX_op_br:
+        tcg_out_br(s, arg_label(args[0]));
+        break;
+    case INDEX_op_goto_tb:
+        tcg_out_goto_tb(s, args[0]);
+        break;
+
+    case INDEX_op_ld8u_i32:
+    case INDEX_op_ld8u_i64:
+        tcg_out_ld_rel(s, OPC_LD1_M1, args[0], args[1], args[2]);
+        break;
+    case INDEX_op_ld8s_i32:
+    case INDEX_op_ld8s_i64:
+        tcg_out_ld_rel(s, OPC_LD1_M1, args[0], args[1], args[2]);
+        tcg_out_ext(s, OPC_SXT1_I29, args[0], args[0]);
+        break;
+    case INDEX_op_ld16u_i32:
+    case INDEX_op_ld16u_i64:
+        tcg_out_ld_rel(s, OPC_LD2_M1, args[0], args[1], args[2]);
+        break;
+    case INDEX_op_ld16s_i32:
+    case INDEX_op_ld16s_i64:
+        tcg_out_ld_rel(s, OPC_LD2_M1, args[0], args[1], args[2]);
+        tcg_out_ext(s, OPC_SXT2_I29, args[0], args[0]);
+        break;
+    case INDEX_op_ld_i32:
+    case INDEX_op_ld32u_i64:
+        tcg_out_ld_rel(s, OPC_LD4_M1, args[0], args[1], args[2]);
+        break;
+    case INDEX_op_ld32s_i64:
+        tcg_out_ld_rel(s, OPC_LD4_M1, args[0], args[1], args[2]);
+        tcg_out_ext(s, OPC_SXT4_I29, args[0], args[0]);
+        break;
+    case INDEX_op_ld_i64:
+        tcg_out_ld_rel(s, OPC_LD8_M1, args[0], args[1], args[2]);
+        break;
+    case INDEX_op_st8_i32:
+    case INDEX_op_st8_i64:
+        tcg_out_st_rel(s, OPC_ST1_M4, args[0], args[1], args[2]);
+        break;
+    case INDEX_op_st16_i32:
+    case INDEX_op_st16_i64:
+        tcg_out_st_rel(s, OPC_ST2_M4, args[0], args[1], args[2]);
+        break;
+    case INDEX_op_st_i32:
+    case INDEX_op_st32_i64:
+        tcg_out_st_rel(s, OPC_ST4_M4, args[0], args[1], args[2]);
+        break;
+    case INDEX_op_st_i64:
+        tcg_out_st_rel(s, OPC_ST8_M4, args[0], args[1], args[2]);
+        break;
+
+    case INDEX_op_add_i32:
+    case INDEX_op_add_i64:
+        tcg_out_add(s, args[0], args[1], args[2], const_args[2]);
+        break;
+    case INDEX_op_sub_i32:
+    case INDEX_op_sub_i64:
+        tcg_out_sub(s, args[0], args[1], const_args[1], args[2], const_args[2]);
+        break;
+
+    case INDEX_op_and_i32:
+    case INDEX_op_and_i64:
+        /* TCG expects arg2 constant; A3 expects arg1 constant.  Swap.  */
+        tcg_out_alu(s, OPC_AND_A1, OPC_AND_A3, args[0],
+                    args[2], const_args[2], args[1], const_args[1]);
+        break;
+    case INDEX_op_andc_i32:
+    case INDEX_op_andc_i64:
+        tcg_out_alu(s, OPC_ANDCM_A1, OPC_ANDCM_A3, args[0],
+                    args[1], const_args[1], args[2], const_args[2]);
+        break;
+    case INDEX_op_eqv_i32:
+    case INDEX_op_eqv_i64:
+        tcg_out_eqv(s, args[0], args[1], const_args[1],
+                    args[2], const_args[2]);
+        break;
+    case INDEX_op_nand_i32:
+    case INDEX_op_nand_i64:
+        tcg_out_nand(s, args[0], args[1], const_args[1],
+                     args[2], const_args[2]);
+        break;
+    case INDEX_op_nor_i32:
+    case INDEX_op_nor_i64:
+        tcg_out_nor(s, args[0], args[1], const_args[1],
+                    args[2], const_args[2]);
+        break;
+    case INDEX_op_or_i32:
+    case INDEX_op_or_i64:
+        /* TCG expects arg2 constant; A3 expects arg1 constant.  Swap.  */
+        tcg_out_alu(s, OPC_OR_A1, OPC_OR_A3, args[0],
+                    args[2], const_args[2], args[1], const_args[1]);
+        break;
+    case INDEX_op_orc_i32:
+    case INDEX_op_orc_i64:
+        tcg_out_orc(s, args[0], args[1], const_args[1],
+                    args[2], const_args[2]);
+        break;
+    case INDEX_op_xor_i32:
+    case INDEX_op_xor_i64:
+        /* TCG expects arg2 constant; A3 expects arg1 constant.  Swap.  */
+        tcg_out_alu(s, OPC_XOR_A1, OPC_XOR_A3, args[0],
+                    args[2], const_args[2], args[1], const_args[1]);
+        break;
+
+    case INDEX_op_mul_i32:
+    case INDEX_op_mul_i64:
+        tcg_out_mul(s, args[0], args[1], args[2]);
+        break;
+
+    case INDEX_op_sar_i32:
+        tcg_out_sar_i32(s, args[0], args[1], args[2], const_args[2]);
+        break;
+    case INDEX_op_sar_i64:
+        tcg_out_sar_i64(s, args[0], args[1], args[2], const_args[2]);
+        break;
+    case INDEX_op_shl_i32:
+        tcg_out_shl_i32(s, args[0], args[1], args[2], const_args[2]);
+        break;
+    case INDEX_op_shl_i64:
+        tcg_out_shl_i64(s, args[0], args[1], args[2], const_args[2]);
+        break;
+    case INDEX_op_shr_i32:
+        tcg_out_shr_i32(s, args[0], args[1], args[2], const_args[2]);
+        break;
+    case INDEX_op_shr_i64:
+        tcg_out_shr_i64(s, args[0], args[1], args[2], const_args[2]);
+        break;
+    case INDEX_op_rotl_i32:
+        tcg_out_rotl_i32(s, args[0], args[1], args[2], const_args[2]);
+        break;
+    case INDEX_op_rotl_i64:
+        tcg_out_rotl_i64(s, args[0], args[1], args[2], const_args[2]);
+        break;
+    case INDEX_op_rotr_i32:
+        tcg_out_rotr_i32(s, args[0], args[1], args[2], const_args[2]);
+        break;
+    case INDEX_op_rotr_i64:
+        tcg_out_rotr_i64(s, args[0], args[1], args[2], const_args[2]);
+        break;
+
+    case INDEX_op_ext8s_i32:
+    case INDEX_op_ext8s_i64:
+        tcg_out_ext(s, OPC_SXT1_I29, args[0], args[1]);
+        break;
+    case INDEX_op_ext8u_i32:
+    case INDEX_op_ext8u_i64:
+        tcg_out_ext(s, OPC_ZXT1_I29, args[0], args[1]);
+        break;
+    case INDEX_op_ext16s_i32:
+    case INDEX_op_ext16s_i64:
+        tcg_out_ext(s, OPC_SXT2_I29, args[0], args[1]);
+        break;
+    case INDEX_op_ext16u_i32:
+    case INDEX_op_ext16u_i64:
+        tcg_out_ext(s, OPC_ZXT2_I29, args[0], args[1]);
+        break;
+    case INDEX_op_ext32s_i64:
+        tcg_out_ext(s, OPC_SXT4_I29, args[0], args[1]);
+        break;
+    case INDEX_op_ext32u_i64:
+        tcg_out_ext(s, OPC_ZXT4_I29, args[0], args[1]);
+        break;
+
+    case INDEX_op_bswap16_i32:
+    case INDEX_op_bswap16_i64:
+        tcg_out_bswap16(s, args[0], args[1]);
+        break;
+    case INDEX_op_bswap32_i32:
+    case INDEX_op_bswap32_i64:
+        tcg_out_bswap32(s, args[0], args[1]);
+        break;
+    case INDEX_op_bswap64_i64:
+        tcg_out_bswap64(s, args[0], args[1]);
+        break;
+
+    case INDEX_op_deposit_i32:
+    case INDEX_op_deposit_i64:
+        tcg_out_deposit(s, args[0], args[1], args[2], const_args[2],
+                        args[3], args[4]);
+        break;
+
+    case INDEX_op_brcond_i32:
+        tcg_out_brcond(s, args[2], args[0], args[1], arg_label(args[3]), 1);
+        break;
+    case INDEX_op_brcond_i64:
+        tcg_out_brcond(s, args[2], args[0], args[1], arg_label(args[3]), 0);
+        break;
+    case INDEX_op_setcond_i32:
+        tcg_out_setcond(s, args[3], args[0], args[1], args[2], 1);
+        break;
+    case INDEX_op_setcond_i64:
+        tcg_out_setcond(s, args[3], args[0], args[1], args[2], 0);
+        break;
+    case INDEX_op_movcond_i32:
+        tcg_out_movcond(s, args[5], args[0], args[1], args[2],
+                        args[3], const_args[3], args[4], const_args[4], 1);
+        break;
+    case INDEX_op_movcond_i64:
+        tcg_out_movcond(s, args[5], args[0], args[1], args[2],
+                        args[3], const_args[3], args[4], const_args[4], 0);
+        break;
+
+    case INDEX_op_qemu_ld_i32:
+        tcg_out_qemu_ld(s, args);
+        break;
+    case INDEX_op_qemu_ld_i64:
+        tcg_out_qemu_ld(s, args);
+        break;
+    case INDEX_op_qemu_st_i32:
+        tcg_out_qemu_st(s, args);
+        break;
+    case INDEX_op_qemu_st_i64:
+        tcg_out_qemu_st(s, args);
+        break;
+
+    case INDEX_op_mov_i32:  /* Always emitted via tcg_out_mov.  */
+    case INDEX_op_mov_i64:
+    case INDEX_op_movi_i32: /* Always emitted via tcg_out_movi.  */
+    case INDEX_op_movi_i64:
+    case INDEX_op_call:     /* Always emitted via tcg_out_call.  */
+    default:
+        tcg_abort();
+    }
+}
+
+static const TCGTargetOpDef ia64_op_defs[] = {
+    { INDEX_op_br, { } },
+    { INDEX_op_exit_tb, { } },
+    { INDEX_op_goto_tb, { } },
+
+    { INDEX_op_ld8u_i32, { "r", "r" } },
+    { INDEX_op_ld8s_i32, { "r", "r" } },
+    { INDEX_op_ld16u_i32, { "r", "r" } },
+    { INDEX_op_ld16s_i32, { "r", "r" } },
+    { INDEX_op_ld_i32, { "r", "r" } },
+    { INDEX_op_st8_i32, { "rZ", "r" } },
+    { INDEX_op_st16_i32, { "rZ", "r" } },
+    { INDEX_op_st_i32, { "rZ", "r" } },
+
+    { INDEX_op_add_i32, { "r", "rZ", "rI" } },
+    { INDEX_op_sub_i32, { "r", "rI", "rI" } },
+
+    { INDEX_op_and_i32, { "r", "rI", "rI" } },
+    { INDEX_op_andc_i32, { "r", "rI", "rI" } },
+    { INDEX_op_eqv_i32, { "r", "rZ", "rZ" } },
+    { INDEX_op_nand_i32, { "r", "rZ", "rZ" } },
+    { INDEX_op_nor_i32, { "r", "rZ", "rZ" } },
+    { INDEX_op_or_i32, { "r", "rI", "rI" } },
+    { INDEX_op_orc_i32, { "r", "rZ", "rZ" } },
+    { INDEX_op_xor_i32, { "r", "rI", "rI" } },
+
+    { INDEX_op_mul_i32, { "r", "rZ", "rZ" } },
+
+    { INDEX_op_sar_i32, { "r", "rZ", "ri" } },
+    { INDEX_op_shl_i32, { "r", "rZ", "ri" } },
+    { INDEX_op_shr_i32, { "r", "rZ", "ri" } },
+    { INDEX_op_rotl_i32, { "r", "rZ", "ri" } },
+    { INDEX_op_rotr_i32, { "r", "rZ", "ri" } },
+
+    { INDEX_op_ext8s_i32, { "r", "rZ"} },
+    { INDEX_op_ext8u_i32, { "r", "rZ"} },
+    { INDEX_op_ext16s_i32, { "r", "rZ"} },
+    { INDEX_op_ext16u_i32, { "r", "rZ"} },
+
+    { INDEX_op_bswap16_i32, { "r", "rZ" } },
+    { INDEX_op_bswap32_i32, { "r", "rZ" } },
+
+    { INDEX_op_brcond_i32, { "rZ", "rZ" } },
+    { INDEX_op_setcond_i32, { "r", "rZ", "rZ" } },
+    { INDEX_op_movcond_i32, { "r", "rZ", "rZ", "rI", "rI" } },
+
+    { INDEX_op_ld8u_i64, { "r", "r" } },
+    { INDEX_op_ld8s_i64, { "r", "r" } },
+    { INDEX_op_ld16u_i64, { "r", "r" } },
+    { INDEX_op_ld16s_i64, { "r", "r" } },
+    { INDEX_op_ld32u_i64, { "r", "r" } },
+    { INDEX_op_ld32s_i64, { "r", "r" } },
+    { INDEX_op_ld_i64, { "r", "r" } },
+    { INDEX_op_st8_i64, { "rZ", "r" } },
+    { INDEX_op_st16_i64, { "rZ", "r" } },
+    { INDEX_op_st32_i64, { "rZ", "r" } },
+    { INDEX_op_st_i64, { "rZ", "r" } },
+
+    { INDEX_op_add_i64, { "r", "rZ", "rI" } },
+    { INDEX_op_sub_i64, { "r", "rI", "rI" } },
+
+    { INDEX_op_and_i64, { "r", "rI", "rI" } },
+    { INDEX_op_andc_i64, { "r", "rI", "rI" } },
+    { INDEX_op_eqv_i64, { "r", "rZ", "rZ" } },
+    { INDEX_op_nand_i64, { "r", "rZ", "rZ" } },
+    { INDEX_op_nor_i64, { "r", "rZ", "rZ" } },
+    { INDEX_op_or_i64, { "r", "rI", "rI" } },
+    { INDEX_op_orc_i64, { "r", "rZ", "rZ" } },
+    { INDEX_op_xor_i64, { "r", "rI", "rI" } },
+
+    { INDEX_op_mul_i64, { "r", "rZ", "rZ" } },
+
+    { INDEX_op_sar_i64, { "r", "rZ", "ri" } },
+    { INDEX_op_shl_i64, { "r", "rZ", "ri" } },
+    { INDEX_op_shr_i64, { "r", "rZ", "ri" } },
+    { INDEX_op_rotl_i64, { "r", "rZ", "ri" } },
+    { INDEX_op_rotr_i64, { "r", "rZ", "ri" } },
+
+    { INDEX_op_ext8s_i64, { "r", "rZ"} },
+    { INDEX_op_ext8u_i64, { "r", "rZ"} },
+    { INDEX_op_ext16s_i64, { "r", "rZ"} },
+    { INDEX_op_ext16u_i64, { "r", "rZ"} },
+    { INDEX_op_ext32s_i64, { "r", "rZ"} },
+    { INDEX_op_ext32u_i64, { "r", "rZ"} },
+
+    { INDEX_op_bswap16_i64, { "r", "rZ" } },
+    { INDEX_op_bswap32_i64, { "r", "rZ" } },
+    { INDEX_op_bswap64_i64, { "r", "rZ" } },
+
+    { INDEX_op_brcond_i64, { "rZ", "rZ" } },
+    { INDEX_op_setcond_i64, { "r", "rZ", "rZ" } },
+    { INDEX_op_movcond_i64, { "r", "rZ", "rZ", "rI", "rI" } },
+
+    { INDEX_op_deposit_i32, { "r", "rZ", "ri" } },
+    { INDEX_op_deposit_i64, { "r", "rZ", "ri" } },
+
+    { INDEX_op_qemu_ld_i32, { "r", "r" } },
+    { INDEX_op_qemu_ld_i64, { "r", "r" } },
+    { INDEX_op_qemu_st_i32, { "SZ", "r" } },
+    { INDEX_op_qemu_st_i64, { "SZ", "r" } },
+
+    { -1 },
+};
+
+/* Generate global QEMU prologue and epilogue code */
+static void tcg_target_qemu_prologue(TCGContext *s)
+{
+    int frame_size;
+
+    /* reserve some stack space */
+    frame_size = TCG_STATIC_CALL_ARGS_SIZE +
+                 CPU_TEMP_BUF_NLONGS * sizeof(long);
+    frame_size = (frame_size + TCG_TARGET_STACK_ALIGN - 1) &
+                 ~(TCG_TARGET_STACK_ALIGN - 1);
+    tcg_set_frame(s, TCG_REG_CALL_STACK, TCG_STATIC_CALL_ARGS_SIZE,
+                  CPU_TEMP_BUF_NLONGS * sizeof(long));
+
+    /* First emit adhoc function descriptor */
+    *s->code_ptr = (tcg_insn_unit){
+        (uint64_t)(s->code_ptr + 1), /* entry point */
+        0                            /* skip gp */
+    };
+    s->code_ptr++;
+
+    /* prologue */
+    tcg_out_bundle(s, miI,
+                   tcg_opc_m34(TCG_REG_P0, OPC_ALLOC_M34,
+                               TCG_REG_R34, 32, 24, 0),
+                   INSN_NOP_I,
+                   tcg_opc_i21(TCG_REG_P0, OPC_MOV_I21,
+                               TCG_REG_B6, TCG_REG_R33, 0));
+
+    /* ??? If GUEST_BASE < 0x200000, we could load the register via
+       an ADDL in the M slot of the next bundle.  */
+    if (GUEST_BASE != 0) {
+        tcg_out_bundle(s, mlx,
+                       INSN_NOP_M,
+                       tcg_opc_l2 (GUEST_BASE),
+                       tcg_opc_x2 (TCG_REG_P0, OPC_MOVL_X2,
+                                   TCG_GUEST_BASE_REG, GUEST_BASE));
+        tcg_regset_set_reg(s->reserved_regs, TCG_GUEST_BASE_REG);
+    }
+
+    tcg_out_bundle(s, miB,
+                   tcg_opc_a4 (TCG_REG_P0, OPC_ADDS_A4,
+                               TCG_REG_R12, -frame_size, TCG_REG_R12),
+                   tcg_opc_i22(TCG_REG_P0, OPC_MOV_I22,
+                               TCG_REG_R33, TCG_REG_B0),
+                   tcg_opc_b4 (TCG_REG_P0, OPC_BR_SPTK_MANY_B4, TCG_REG_B6));
+
+    /* epilogue */
+    tb_ret_addr = s->code_ptr;
+    tcg_out_bundle(s, miI,
+                   INSN_NOP_M,
+                   tcg_opc_i21(TCG_REG_P0, OPC_MOV_I21,
+                               TCG_REG_B0, TCG_REG_R33, 0),
+                   tcg_opc_a4 (TCG_REG_P0, OPC_ADDS_A4,
+                               TCG_REG_R12, frame_size, TCG_REG_R12));
+    tcg_out_bundle(s, miB,
+                   INSN_NOP_M,
+                   tcg_opc_i26(TCG_REG_P0, OPC_MOV_I_I26,
+                               TCG_REG_PFS, TCG_REG_R34),
+                   tcg_opc_b4 (TCG_REG_P0, OPC_BR_RET_SPTK_MANY_B4,
+                               TCG_REG_B0));
+}
+
+static void tcg_target_init(TCGContext *s)
+{
+    tcg_regset_set(tcg_target_available_regs[TCG_TYPE_I32],
+                   0xffffffffffffffffull);
+    tcg_regset_set(tcg_target_available_regs[TCG_TYPE_I64],
+                   0xffffffffffffffffull);
+
+    tcg_regset_clear(tcg_target_call_clobber_regs);
+    tcg_regset_set_reg(tcg_target_call_clobber_regs, TCG_REG_R8);
+    tcg_regset_set_reg(tcg_target_call_clobber_regs, TCG_REG_R9);
+    tcg_regset_set_reg(tcg_target_call_clobber_regs, TCG_REG_R10);
+    tcg_regset_set_reg(tcg_target_call_clobber_regs, TCG_REG_R11);
+    tcg_regset_set_reg(tcg_target_call_clobber_regs, TCG_REG_R14);
+    tcg_regset_set_reg(tcg_target_call_clobber_regs, TCG_REG_R15);
+    tcg_regset_set_reg(tcg_target_call_clobber_regs, TCG_REG_R16);
+    tcg_regset_set_reg(tcg_target_call_clobber_regs, TCG_REG_R17);
+    tcg_regset_set_reg(tcg_target_call_clobber_regs, TCG_REG_R18);
+    tcg_regset_set_reg(tcg_target_call_clobber_regs, TCG_REG_R19);
+    tcg_regset_set_reg(tcg_target_call_clobber_regs, TCG_REG_R20);
+    tcg_regset_set_reg(tcg_target_call_clobber_regs, TCG_REG_R21);
+    tcg_regset_set_reg(tcg_target_call_clobber_regs, TCG_REG_R22);
+    tcg_regset_set_reg(tcg_target_call_clobber_regs, TCG_REG_R23);
+    tcg_regset_set_reg(tcg_target_call_clobber_regs, TCG_REG_R24);
+    tcg_regset_set_reg(tcg_target_call_clobber_regs, TCG_REG_R25);
+    tcg_regset_set_reg(tcg_target_call_clobber_regs, TCG_REG_R26);
+    tcg_regset_set_reg(tcg_target_call_clobber_regs, TCG_REG_R27);
+    tcg_regset_set_reg(tcg_target_call_clobber_regs, TCG_REG_R28);
+    tcg_regset_set_reg(tcg_target_call_clobber_regs, TCG_REG_R29);
+    tcg_regset_set_reg(tcg_target_call_clobber_regs, TCG_REG_R30);
+    tcg_regset_set_reg(tcg_target_call_clobber_regs, TCG_REG_R31);
+    tcg_regset_set_reg(tcg_target_call_clobber_regs, TCG_REG_R56);
+    tcg_regset_set_reg(tcg_target_call_clobber_regs, TCG_REG_R57);
+    tcg_regset_set_reg(tcg_target_call_clobber_regs, TCG_REG_R58);
+    tcg_regset_set_reg(tcg_target_call_clobber_regs, TCG_REG_R59);
+    tcg_regset_set_reg(tcg_target_call_clobber_regs, TCG_REG_R60);
+    tcg_regset_set_reg(tcg_target_call_clobber_regs, TCG_REG_R61);
+    tcg_regset_set_reg(tcg_target_call_clobber_regs, TCG_REG_R62);
+    tcg_regset_set_reg(tcg_target_call_clobber_regs, TCG_REG_R63);
+
+    tcg_regset_clear(s->reserved_regs);
+    tcg_regset_set_reg(s->reserved_regs, TCG_REG_R0);   /* zero register */
+    tcg_regset_set_reg(s->reserved_regs, TCG_REG_R1);   /* global pointer */
+    tcg_regset_set_reg(s->reserved_regs, TCG_REG_R2);   /* internal use */
+    tcg_regset_set_reg(s->reserved_regs, TCG_REG_R3);   /* internal use */
+    tcg_regset_set_reg(s->reserved_regs, TCG_REG_R12);  /* stack pointer */
+    tcg_regset_set_reg(s->reserved_regs, TCG_REG_R13);  /* thread pointer */
+    tcg_regset_set_reg(s->reserved_regs, TCG_REG_R33);  /* return address */
+    tcg_regset_set_reg(s->reserved_regs, TCG_REG_R34);  /* PFS */
+
+    /* The following 4 are not in use, are call-saved, but *not* saved
+       by the prologue.  Therefore we cannot use them without modifying
+       the prologue.  There doesn't seem to be any good reason to use
+       these as opposed to the windowed registers.  */
+    tcg_regset_set_reg(s->reserved_regs, TCG_REG_R4);
+    tcg_regset_set_reg(s->reserved_regs, TCG_REG_R5);
+    tcg_regset_set_reg(s->reserved_regs, TCG_REG_R6);
+    tcg_regset_set_reg(s->reserved_regs, TCG_REG_R7);
+
+    tcg_add_target_add_op_defs(ia64_op_defs);
+}
diff --git a/tcg/ia64/tcg-target.h b/tcg/ia64/tcg-target.h
new file mode 100644
index 00000000..a04ed812
--- /dev/null
+++ b/tcg/ia64/tcg-target.h
@@ -0,0 +1,185 @@
+/*
+ * Tiny Code Generator for QEMU
+ *
+ * Copyright (c) 2009-2010 Aurelien Jarno <aurelien@aurel32.net>
+ * Based on i386/tcg-target.c - Copyright (c) 2008 Fabrice Bellard
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (the "Software"), to deal
+ * in the Software without restriction, including without limitation the rights
+ * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+ * copies of the Software, and to permit persons to whom the Software is
+ * furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+ * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+ * THE SOFTWARE.
+ */
+#ifndef TCG_TARGET_IA64 
+#define TCG_TARGET_IA64 1
+
+#define TCG_TARGET_INSN_UNIT_SIZE 16
+#define TCG_TARGET_TLB_DISPLACEMENT_BITS 21
+
+typedef struct {
+    uint64_t lo __attribute__((aligned(16)));
+    uint64_t hi;
+} tcg_insn_unit;
+
+/* We only map the first 64 registers */
+#define TCG_TARGET_NB_REGS 64
+typedef enum {
+    TCG_REG_R0 = 0,
+    TCG_REG_R1,
+    TCG_REG_R2,
+    TCG_REG_R3,
+    TCG_REG_R4,
+    TCG_REG_R5,
+    TCG_REG_R6,
+    TCG_REG_R7,
+    TCG_REG_R8,
+    TCG_REG_R9,
+    TCG_REG_R10,
+    TCG_REG_R11,
+    TCG_REG_R12,
+    TCG_REG_R13,
+    TCG_REG_R14,
+    TCG_REG_R15,
+    TCG_REG_R16,
+    TCG_REG_R17,
+    TCG_REG_R18,
+    TCG_REG_R19,
+    TCG_REG_R20,
+    TCG_REG_R21,
+    TCG_REG_R22,
+    TCG_REG_R23,
+    TCG_REG_R24,
+    TCG_REG_R25,
+    TCG_REG_R26,
+    TCG_REG_R27,
+    TCG_REG_R28,
+    TCG_REG_R29,
+    TCG_REG_R30,
+    TCG_REG_R31,
+    TCG_REG_R32,
+    TCG_REG_R33,
+    TCG_REG_R34,
+    TCG_REG_R35,
+    TCG_REG_R36,
+    TCG_REG_R37,
+    TCG_REG_R38,
+    TCG_REG_R39,
+    TCG_REG_R40,
+    TCG_REG_R41,
+    TCG_REG_R42,
+    TCG_REG_R43,
+    TCG_REG_R44,
+    TCG_REG_R45,
+    TCG_REG_R46,
+    TCG_REG_R47,
+    TCG_REG_R48,
+    TCG_REG_R49,
+    TCG_REG_R50,
+    TCG_REG_R51,
+    TCG_REG_R52,
+    TCG_REG_R53,
+    TCG_REG_R54,
+    TCG_REG_R55,
+    TCG_REG_R56,
+    TCG_REG_R57,
+    TCG_REG_R58,
+    TCG_REG_R59,
+    TCG_REG_R60,
+    TCG_REG_R61,
+    TCG_REG_R62,
+    TCG_REG_R63,
+
+    TCG_AREG0 = TCG_REG_R32,
+} TCGReg;
+
+#define TCG_CT_CONST_ZERO 0x100
+#define TCG_CT_CONST_S22 0x200
+
+/* used for function call generation */
+#define TCG_REG_CALL_STACK TCG_REG_R12
+#define TCG_TARGET_STACK_ALIGN 16
+#define TCG_TARGET_CALL_STACK_OFFSET 16
+
+/* optional instructions */
+#define TCG_TARGET_HAS_div_i32          0
+#define TCG_TARGET_HAS_rem_i32          0
+#define TCG_TARGET_HAS_div_i64          0
+#define TCG_TARGET_HAS_rem_i64          0
+#define TCG_TARGET_HAS_andc_i32         1
+#define TCG_TARGET_HAS_andc_i64         1
+#define TCG_TARGET_HAS_bswap16_i32      1
+#define TCG_TARGET_HAS_bswap16_i64      1
+#define TCG_TARGET_HAS_bswap32_i32      1
+#define TCG_TARGET_HAS_bswap32_i64      1
+#define TCG_TARGET_HAS_bswap64_i64      1
+#define TCG_TARGET_HAS_eqv_i32          1
+#define TCG_TARGET_HAS_eqv_i64          1
+#define TCG_TARGET_HAS_ext8s_i32        1
+#define TCG_TARGET_HAS_ext16s_i32       1
+#define TCG_TARGET_HAS_ext8s_i64        1
+#define TCG_TARGET_HAS_ext16s_i64       1
+#define TCG_TARGET_HAS_ext32s_i64       1
+#define TCG_TARGET_HAS_ext8u_i32        1
+#define TCG_TARGET_HAS_ext16u_i32       1
+#define TCG_TARGET_HAS_ext8u_i64        1
+#define TCG_TARGET_HAS_ext16u_i64       1
+#define TCG_TARGET_HAS_ext32u_i64       1
+#define TCG_TARGET_HAS_nand_i32         1
+#define TCG_TARGET_HAS_nand_i64         1
+#define TCG_TARGET_HAS_nor_i32          1
+#define TCG_TARGET_HAS_nor_i64          1
+#define TCG_TARGET_HAS_orc_i32          1
+#define TCG_TARGET_HAS_orc_i64          1
+#define TCG_TARGET_HAS_rot_i32          1
+#define TCG_TARGET_HAS_rot_i64          1
+#define TCG_TARGET_HAS_movcond_i32      1
+#define TCG_TARGET_HAS_movcond_i64      1
+#define TCG_TARGET_HAS_deposit_i32      1
+#define TCG_TARGET_HAS_deposit_i64      1
+#define TCG_TARGET_HAS_add2_i32         0
+#define TCG_TARGET_HAS_add2_i64         0
+#define TCG_TARGET_HAS_sub2_i32         0
+#define TCG_TARGET_HAS_sub2_i64         0
+#define TCG_TARGET_HAS_mulu2_i32        0
+#define TCG_TARGET_HAS_mulu2_i64        0
+#define TCG_TARGET_HAS_muls2_i32        0
+#define TCG_TARGET_HAS_muls2_i64        0
+#define TCG_TARGET_HAS_muluh_i32        0
+#define TCG_TARGET_HAS_muluh_i64        0
+#define TCG_TARGET_HAS_mulsh_i32        0
+#define TCG_TARGET_HAS_mulsh_i64        0
+#define TCG_TARGET_HAS_trunc_shr_i32    0
+
+#define TCG_TARGET_deposit_i32_valid(ofs, len) ((len) <= 16)
+#define TCG_TARGET_deposit_i64_valid(ofs, len) ((len) <= 16)
+
+/* optional instructions automatically implemented */
+#define TCG_TARGET_HAS_neg_i32          0 /* sub r1, r0, r3 */
+#define TCG_TARGET_HAS_neg_i64          0 /* sub r1, r0, r3 */
+#define TCG_TARGET_HAS_not_i32          0 /* xor r1, -1, r3 */
+#define TCG_TARGET_HAS_not_i64          0 /* xor r1, -1, r3 */
+
+static inline void flush_icache_range(uintptr_t start, uintptr_t stop)
+{
+    start = start & ~(32UL - 1UL);
+    stop = (stop + (32UL - 1UL)) & ~(32UL - 1UL);
+
+    for (; start < stop; start += 32UL) {
+        asm volatile ("fc.i %0" :: "r" (start));
+    }
+    asm volatile (";;sync.i;;srlz.i;;");
+}
+
+#endif
diff --git a/tcg/mips/tcg-target.c b/tcg/mips/tcg-target.c
new file mode 100644
index 00000000..2ccd0e82
--- /dev/null
+++ b/tcg/mips/tcg-target.c
@@ -0,0 +1,1828 @@
+/*
+ * Tiny Code Generator for QEMU
+ *
+ * Copyright (c) 2008-2009 Arnaud Patard <arnaud.patard@rtp-net.org>
+ * Copyright (c) 2009 Aurelien Jarno <aurelien@aurel32.net>
+ * Based on i386/tcg-target.c - Copyright (c) 2008 Fabrice Bellard
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (the "Software"), to deal
+ * in the Software without restriction, including without limitation the rights
+ * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+ * copies of the Software, and to permit persons to whom the Software is
+ * furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+ * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+ * THE SOFTWARE.
+ */
+
+#include "tcg-be-ldst.h"
+
+#ifdef HOST_WORDS_BIGENDIAN
+# define MIPS_BE  1
+#else
+# define MIPS_BE  0
+#endif
+
+#define LO_OFF    (MIPS_BE * 4)
+#define HI_OFF    (4 - LO_OFF)
+
+#ifndef NDEBUG
+static const char * const tcg_target_reg_names[TCG_TARGET_NB_REGS] = {
+    "zero",
+    "at",
+    "v0",
+    "v1",
+    "a0",
+    "a1",
+    "a2",
+    "a3",
+    "t0",
+    "t1",
+    "t2",
+    "t3",
+    "t4",
+    "t5",
+    "t6",
+    "t7",
+    "s0",
+    "s1",
+    "s2",
+    "s3",
+    "s4",
+    "s5",
+    "s6",
+    "s7",
+    "t8",
+    "t9",
+    "k0",
+    "k1",
+    "gp",
+    "sp",
+    "s8",
+    "ra",
+};
+#endif
+
+#define TCG_TMP0  TCG_REG_AT
+#define TCG_TMP1  TCG_REG_T9
+
+/* check if we really need so many registers :P */
+static const TCGReg tcg_target_reg_alloc_order[] = {
+    /* Call saved registers.  */
+    TCG_REG_S0,
+    TCG_REG_S1,
+    TCG_REG_S2,
+    TCG_REG_S3,
+    TCG_REG_S4,
+    TCG_REG_S5,
+    TCG_REG_S6,
+    TCG_REG_S7,
+    TCG_REG_S8,
+
+    /* Call clobbered registers.  */
+    TCG_REG_T0,
+    TCG_REG_T1,
+    TCG_REG_T2,
+    TCG_REG_T3,
+    TCG_REG_T4,
+    TCG_REG_T5,
+    TCG_REG_T6,
+    TCG_REG_T7,
+    TCG_REG_T8,
+    TCG_REG_T9,
+    TCG_REG_V1,
+    TCG_REG_V0,
+
+    /* Argument registers, opposite order of allocation.  */
+    TCG_REG_A3,
+    TCG_REG_A2,
+    TCG_REG_A1,
+    TCG_REG_A0,
+};
+
+static const TCGReg tcg_target_call_iarg_regs[4] = {
+    TCG_REG_A0,
+    TCG_REG_A1,
+    TCG_REG_A2,
+    TCG_REG_A3
+};
+
+static const TCGReg tcg_target_call_oarg_regs[2] = {
+    TCG_REG_V0,
+    TCG_REG_V1
+};
+
+static tcg_insn_unit *tb_ret_addr;
+
+static inline uint32_t reloc_pc16_val(tcg_insn_unit *pc, tcg_insn_unit *target)
+{
+    /* Let the compiler perform the right-shift as part of the arithmetic.  */
+    ptrdiff_t disp = target - (pc + 1);
+    assert(disp == (int16_t)disp);
+    return disp & 0xffff;
+}
+
+static inline void reloc_pc16(tcg_insn_unit *pc, tcg_insn_unit *target)
+{
+    *pc = deposit32(*pc, 0, 16, reloc_pc16_val(pc, target));
+}
+
+static inline uint32_t reloc_26_val(tcg_insn_unit *pc, tcg_insn_unit *target)
+{
+    assert((((uintptr_t)pc ^ (uintptr_t)target) & 0xf0000000) == 0);
+    return ((uintptr_t)target >> 2) & 0x3ffffff;
+}
+
+static inline void reloc_26(tcg_insn_unit *pc, tcg_insn_unit *target)
+{
+    *pc = deposit32(*pc, 0, 26, reloc_26_val(pc, target));
+}
+
+static void patch_reloc(tcg_insn_unit *code_ptr, int type,
+                        intptr_t value, intptr_t addend)
+{
+    assert(type == R_MIPS_PC16);
+    assert(addend == 0);
+    reloc_pc16(code_ptr, (tcg_insn_unit *)value);
+}
+
+#define TCG_CT_CONST_ZERO 0x100
+#define TCG_CT_CONST_U16  0x200    /* Unsigned 16-bit: 0 - 0xffff.  */
+#define TCG_CT_CONST_S16  0x400    /* Signed 16-bit: -32768 - 32767 */
+#define TCG_CT_CONST_P2M1 0x800    /* Power of 2 minus 1.  */
+#define TCG_CT_CONST_N16  0x1000   /* "Negatable" 16-bit: -32767 - 32767 */
+
+static inline bool is_p2m1(tcg_target_long val)
+{
+    return val && ((val + 1) & val) == 0;
+}
+
+/* parse target specific constraints */
+static int target_parse_constraint(TCGArgConstraint *ct, const char **pct_str)
+{
+    const char *ct_str;
+
+    ct_str = *pct_str;
+    switch(ct_str[0]) {
+    case 'r':
+        ct->ct |= TCG_CT_REG;
+        tcg_regset_set(ct->u.regs, 0xffffffff);
+        break;
+    case 'L': /* qemu_ld output arg constraint */
+        ct->ct |= TCG_CT_REG;
+        tcg_regset_set(ct->u.regs, 0xffffffff);
+        tcg_regset_reset_reg(ct->u.regs, TCG_REG_V0);
+        break;
+    case 'l': /* qemu_ld input arg constraint */
+        ct->ct |= TCG_CT_REG;
+        tcg_regset_set(ct->u.regs, 0xffffffff);
+        tcg_regset_reset_reg(ct->u.regs, TCG_REG_A0);
+#if defined(CONFIG_SOFTMMU)
+        if (TARGET_LONG_BITS == 64) {
+            tcg_regset_reset_reg(ct->u.regs, TCG_REG_A2);
+        }
+#endif
+        break;
+    case 'S': /* qemu_st constraint */
+        ct->ct |= TCG_CT_REG;
+        tcg_regset_set(ct->u.regs, 0xffffffff);
+        tcg_regset_reset_reg(ct->u.regs, TCG_REG_A0);
+#if defined(CONFIG_SOFTMMU)
+        if (TARGET_LONG_BITS == 32) {
+            tcg_regset_reset_reg(ct->u.regs, TCG_REG_A1);
+        } else {
+            tcg_regset_reset_reg(ct->u.regs, TCG_REG_A2);
+            tcg_regset_reset_reg(ct->u.regs, TCG_REG_A3);
+        }
+#endif
+        break;
+    case 'I':
+        ct->ct |= TCG_CT_CONST_U16;
+        break;
+    case 'J':
+        ct->ct |= TCG_CT_CONST_S16;
+        break;
+    case 'K':
+        ct->ct |= TCG_CT_CONST_P2M1;
+        break;
+    case 'N':
+        ct->ct |= TCG_CT_CONST_N16;
+        break;
+    case 'Z':
+        /* We are cheating a bit here, using the fact that the register
+           ZERO is also the register number 0. Hence there is no need
+           to check for const_args in each instruction. */
+        ct->ct |= TCG_CT_CONST_ZERO;
+        break;
+    default:
+        return -1;
+    }
+    ct_str++;
+    *pct_str = ct_str;
+    return 0;
+}
+
+/* test if a constant matches the constraint */
+static inline int tcg_target_const_match(tcg_target_long val, TCGType type,
+                                         const TCGArgConstraint *arg_ct)
+{
+    int ct;
+    ct = arg_ct->ct;
+    if (ct & TCG_CT_CONST) {
+        return 1;
+    } else if ((ct & TCG_CT_CONST_ZERO) && val == 0) {
+        return 1;
+    } else if ((ct & TCG_CT_CONST_U16) && val == (uint16_t)val) {
+        return 1;
+    } else if ((ct & TCG_CT_CONST_S16) && val == (int16_t)val) {
+        return 1;
+    } else if ((ct & TCG_CT_CONST_N16) && val >= -32767 && val <= 32767) {
+        return 1;
+    } else if ((ct & TCG_CT_CONST_P2M1)
+               && use_mips32r2_instructions && is_p2m1(val)) {
+        return 1;
+    }
+    return 0;
+}
+
+/* instruction opcodes */
+typedef enum {
+    OPC_J        = 0x02 << 26,
+    OPC_JAL      = 0x03 << 26,
+    OPC_BEQ      = 0x04 << 26,
+    OPC_BNE      = 0x05 << 26,
+    OPC_BLEZ     = 0x06 << 26,
+    OPC_BGTZ     = 0x07 << 26,
+    OPC_ADDIU    = 0x09 << 26,
+    OPC_SLTI     = 0x0A << 26,
+    OPC_SLTIU    = 0x0B << 26,
+    OPC_ANDI     = 0x0C << 26,
+    OPC_ORI      = 0x0D << 26,
+    OPC_XORI     = 0x0E << 26,
+    OPC_LUI      = 0x0F << 26,
+    OPC_LB       = 0x20 << 26,
+    OPC_LH       = 0x21 << 26,
+    OPC_LW       = 0x23 << 26,
+    OPC_LBU      = 0x24 << 26,
+    OPC_LHU      = 0x25 << 26,
+    OPC_LWU      = 0x27 << 26,
+    OPC_SB       = 0x28 << 26,
+    OPC_SH       = 0x29 << 26,
+    OPC_SW       = 0x2B << 26,
+
+    OPC_SPECIAL  = 0x00 << 26,
+    OPC_SLL      = OPC_SPECIAL | 0x00,
+    OPC_SRL      = OPC_SPECIAL | 0x02,
+    OPC_ROTR     = OPC_SPECIAL | (0x01 << 21) | 0x02,
+    OPC_SRA      = OPC_SPECIAL | 0x03,
+    OPC_SLLV     = OPC_SPECIAL | 0x04,
+    OPC_SRLV     = OPC_SPECIAL | 0x06,
+    OPC_ROTRV    = OPC_SPECIAL | (0x01 <<  6) | 0x06,
+    OPC_SRAV     = OPC_SPECIAL | 0x07,
+    OPC_JR       = OPC_SPECIAL | 0x08,
+    OPC_JALR     = OPC_SPECIAL | 0x09,
+    OPC_MOVZ     = OPC_SPECIAL | 0x0A,
+    OPC_MOVN     = OPC_SPECIAL | 0x0B,
+    OPC_MFHI     = OPC_SPECIAL | 0x10,
+    OPC_MFLO     = OPC_SPECIAL | 0x12,
+    OPC_MULT     = OPC_SPECIAL | 0x18,
+    OPC_MULTU    = OPC_SPECIAL | 0x19,
+    OPC_DIV      = OPC_SPECIAL | 0x1A,
+    OPC_DIVU     = OPC_SPECIAL | 0x1B,
+    OPC_ADDU     = OPC_SPECIAL | 0x21,
+    OPC_SUBU     = OPC_SPECIAL | 0x23,
+    OPC_AND      = OPC_SPECIAL | 0x24,
+    OPC_OR       = OPC_SPECIAL | 0x25,
+    OPC_XOR      = OPC_SPECIAL | 0x26,
+    OPC_NOR      = OPC_SPECIAL | 0x27,
+    OPC_SLT      = OPC_SPECIAL | 0x2A,
+    OPC_SLTU     = OPC_SPECIAL | 0x2B,
+
+    OPC_REGIMM   = 0x01 << 26,
+    OPC_BLTZ     = OPC_REGIMM | (0x00 << 16),
+    OPC_BGEZ     = OPC_REGIMM | (0x01 << 16),
+
+    OPC_SPECIAL2 = 0x1c << 26,
+    OPC_MUL      = OPC_SPECIAL2 | 0x002,
+
+    OPC_SPECIAL3 = 0x1f << 26,
+    OPC_EXT      = OPC_SPECIAL3 | 0x000,
+    OPC_INS      = OPC_SPECIAL3 | 0x004,
+    OPC_WSBH     = OPC_SPECIAL3 | 0x0a0,
+    OPC_SEB      = OPC_SPECIAL3 | 0x420,
+    OPC_SEH      = OPC_SPECIAL3 | 0x620,
+} MIPSInsn;
+
+/*
+ * Type reg
+ */
+static inline void tcg_out_opc_reg(TCGContext *s, MIPSInsn opc,
+                                   TCGReg rd, TCGReg rs, TCGReg rt)
+{
+    int32_t inst;
+
+    inst = opc;
+    inst |= (rs & 0x1F) << 21;
+    inst |= (rt & 0x1F) << 16;
+    inst |= (rd & 0x1F) << 11;
+    tcg_out32(s, inst);
+}
+
+/*
+ * Type immediate
+ */
+static inline void tcg_out_opc_imm(TCGContext *s, MIPSInsn opc,
+                                   TCGReg rt, TCGReg rs, TCGArg imm)
+{
+    int32_t inst;
+
+    inst = opc;
+    inst |= (rs & 0x1F) << 21;
+    inst |= (rt & 0x1F) << 16;
+    inst |= (imm & 0xffff);
+    tcg_out32(s, inst);
+}
+
+/*
+ * Type bitfield
+ */
+static inline void tcg_out_opc_bf(TCGContext *s, MIPSInsn opc, TCGReg rt,
+                                  TCGReg rs, int msb, int lsb)
+{
+    int32_t inst;
+
+    inst = opc;
+    inst |= (rs & 0x1F) << 21;
+    inst |= (rt & 0x1F) << 16;
+    inst |= (msb & 0x1F) << 11;
+    inst |= (lsb & 0x1F) << 6;
+    tcg_out32(s, inst);
+}
+
+/*
+ * Type branch
+ */
+static inline void tcg_out_opc_br(TCGContext *s, MIPSInsn opc,
+                                  TCGReg rt, TCGReg rs)
+{
+    /* We pay attention here to not modify the branch target by reading
+       the existing value and using it again. This ensure that caches and
+       memory are kept coherent during retranslation. */
+    uint16_t offset = (uint16_t)*s->code_ptr;
+
+    tcg_out_opc_imm(s, opc, rt, rs, offset);
+}
+
+/*
+ * Type sa
+ */
+static inline void tcg_out_opc_sa(TCGContext *s, MIPSInsn opc,
+                                  TCGReg rd, TCGReg rt, TCGArg sa)
+{
+    int32_t inst;
+
+    inst = opc;
+    inst |= (rt & 0x1F) << 16;
+    inst |= (rd & 0x1F) << 11;
+    inst |= (sa & 0x1F) <<  6;
+    tcg_out32(s, inst);
+
+}
+
+/*
+ * Type jump.
+ * Returns true if the branch was in range and the insn was emitted.
+ */
+static bool tcg_out_opc_jmp(TCGContext *s, MIPSInsn opc, void *target)
+{
+    uintptr_t dest = (uintptr_t)target;
+    uintptr_t from = (uintptr_t)s->code_ptr + 4;
+    int32_t inst;
+
+    /* The pc-region branch happens within the 256MB region of
+       the delay slot (thus the +4).  */
+    if ((from ^ dest) & -(1 << 28)) {
+        return false;
+    }
+    assert((dest & 3) == 0);
+
+    inst = opc;
+    inst |= (dest >> 2) & 0x3ffffff;
+    tcg_out32(s, inst);
+    return true;
+}
+
+static inline void tcg_out_nop(TCGContext *s)
+{
+    tcg_out32(s, 0);
+}
+
+static inline void tcg_out_mov(TCGContext *s, TCGType type,
+                               TCGReg ret, TCGReg arg)
+{
+    /* Simple reg-reg move, optimising out the 'do nothing' case */
+    if (ret != arg) {
+        tcg_out_opc_reg(s, OPC_ADDU, ret, arg, TCG_REG_ZERO);
+    }
+}
+
+static inline void tcg_out_movi(TCGContext *s, TCGType type,
+                                TCGReg reg, tcg_target_long arg)
+{
+    if (arg == (int16_t)arg) {
+        tcg_out_opc_imm(s, OPC_ADDIU, reg, TCG_REG_ZERO, arg);
+    } else if (arg == (uint16_t)arg) {
+        tcg_out_opc_imm(s, OPC_ORI, reg, TCG_REG_ZERO, arg);
+    } else {
+        tcg_out_opc_imm(s, OPC_LUI, reg, TCG_REG_ZERO, arg >> 16);
+        if (arg & 0xffff) {
+            tcg_out_opc_imm(s, OPC_ORI, reg, reg, arg & 0xffff);
+        }
+    }
+}
+
+static inline void tcg_out_bswap16(TCGContext *s, TCGReg ret, TCGReg arg)
+{
+    if (use_mips32r2_instructions) {
+        tcg_out_opc_reg(s, OPC_WSBH, ret, 0, arg);
+    } else {
+        /* ret and arg can't be register at */
+        if (ret == TCG_TMP0 || arg == TCG_TMP0) {
+            tcg_abort();
+        }
+
+        tcg_out_opc_sa(s, OPC_SRL, TCG_TMP0, arg, 8);
+        tcg_out_opc_sa(s, OPC_SLL, ret, arg, 8);
+        tcg_out_opc_imm(s, OPC_ANDI, ret, ret, 0xff00);
+        tcg_out_opc_reg(s, OPC_OR, ret, ret, TCG_TMP0);
+    }
+}
+
+static inline void tcg_out_bswap16s(TCGContext *s, TCGReg ret, TCGReg arg)
+{
+    if (use_mips32r2_instructions) {
+        tcg_out_opc_reg(s, OPC_WSBH, ret, 0, arg);
+        tcg_out_opc_reg(s, OPC_SEH, ret, 0, ret);
+    } else {
+        /* ret and arg can't be register at */
+        if (ret == TCG_TMP0 || arg == TCG_TMP0) {
+            tcg_abort();
+        }
+
+        tcg_out_opc_sa(s, OPC_SRL, TCG_TMP0, arg, 8);
+        tcg_out_opc_sa(s, OPC_SLL, ret, arg, 24);
+        tcg_out_opc_sa(s, OPC_SRA, ret, ret, 16);
+        tcg_out_opc_reg(s, OPC_OR, ret, ret, TCG_TMP0);
+    }
+}
+
+static inline void tcg_out_bswap32(TCGContext *s, TCGReg ret, TCGReg arg)
+{
+    if (use_mips32r2_instructions) {
+        tcg_out_opc_reg(s, OPC_WSBH, ret, 0, arg);
+        tcg_out_opc_sa(s, OPC_ROTR, ret, ret, 16);
+    } else {
+        /* ret and arg must be different and can't be register at */
+        if (ret == arg || ret == TCG_TMP0 || arg == TCG_TMP0) {
+            tcg_abort();
+        }
+
+        tcg_out_opc_sa(s, OPC_SLL, ret, arg, 24);
+
+        tcg_out_opc_sa(s, OPC_SRL, TCG_TMP0, arg, 24);
+        tcg_out_opc_reg(s, OPC_OR, ret, ret, TCG_TMP0);
+
+        tcg_out_opc_imm(s, OPC_ANDI, TCG_TMP0, arg, 0xff00);
+        tcg_out_opc_sa(s, OPC_SLL, TCG_TMP0, TCG_TMP0, 8);
+        tcg_out_opc_reg(s, OPC_OR, ret, ret, TCG_TMP0);
+
+        tcg_out_opc_sa(s, OPC_SRL, TCG_TMP0, arg, 8);
+        tcg_out_opc_imm(s, OPC_ANDI, TCG_TMP0, TCG_TMP0, 0xff00);
+        tcg_out_opc_reg(s, OPC_OR, ret, ret, TCG_TMP0);
+    }
+}
+
+static inline void tcg_out_ext8s(TCGContext *s, TCGReg ret, TCGReg arg)
+{
+    if (use_mips32r2_instructions) {
+        tcg_out_opc_reg(s, OPC_SEB, ret, 0, arg);
+    } else {
+        tcg_out_opc_sa(s, OPC_SLL, ret, arg, 24);
+        tcg_out_opc_sa(s, OPC_SRA, ret, ret, 24);
+    }
+}
+
+static inline void tcg_out_ext16s(TCGContext *s, TCGReg ret, TCGReg arg)
+{
+    if (use_mips32r2_instructions) {
+        tcg_out_opc_reg(s, OPC_SEH, ret, 0, arg);
+    } else {
+        tcg_out_opc_sa(s, OPC_SLL, ret, arg, 16);
+        tcg_out_opc_sa(s, OPC_SRA, ret, ret, 16);
+    }
+}
+
+static void tcg_out_ldst(TCGContext *s, MIPSInsn opc, TCGReg data,
+                         TCGReg addr, intptr_t ofs)
+{
+    int16_t lo = ofs;
+    if (ofs != lo) {
+        tcg_out_movi(s, TCG_TYPE_PTR, TCG_TMP0, ofs - lo);
+        if (addr != TCG_REG_ZERO) {
+            tcg_out_opc_reg(s, OPC_ADDU, TCG_TMP0, TCG_TMP0, addr);
+        }
+        addr = TCG_TMP0;
+    }
+    tcg_out_opc_imm(s, opc, data, addr, lo);
+}
+
+static inline void tcg_out_ld(TCGContext *s, TCGType type, TCGReg arg,
+                              TCGReg arg1, intptr_t arg2)
+{
+    tcg_out_ldst(s, OPC_LW, arg, arg1, arg2);
+}
+
+static inline void tcg_out_st(TCGContext *s, TCGType type, TCGReg arg,
+                              TCGReg arg1, intptr_t arg2)
+{
+    tcg_out_ldst(s, OPC_SW, arg, arg1, arg2);
+}
+
+static inline void tcg_out_addi(TCGContext *s, TCGReg reg, TCGArg val)
+{
+    if (val == (int16_t)val) {
+        tcg_out_opc_imm(s, OPC_ADDIU, reg, reg, val);
+    } else {
+        tcg_out_movi(s, TCG_TYPE_PTR, TCG_TMP0, val);
+        tcg_out_opc_reg(s, OPC_ADDU, reg, reg, TCG_TMP0);
+    }
+}
+
+/* Bit 0 set if inversion required; bit 1 set if swapping required.  */
+#define MIPS_CMP_INV  1
+#define MIPS_CMP_SWAP 2
+
+static const uint8_t mips_cmp_map[16] = {
+    [TCG_COND_LT]  = 0,
+    [TCG_COND_LTU] = 0,
+    [TCG_COND_GE]  = MIPS_CMP_INV,
+    [TCG_COND_GEU] = MIPS_CMP_INV,
+    [TCG_COND_LE]  = MIPS_CMP_INV | MIPS_CMP_SWAP,
+    [TCG_COND_LEU] = MIPS_CMP_INV | MIPS_CMP_SWAP,
+    [TCG_COND_GT]  = MIPS_CMP_SWAP,
+    [TCG_COND_GTU] = MIPS_CMP_SWAP,
+};
+
+static void tcg_out_setcond(TCGContext *s, TCGCond cond, TCGReg ret,
+                            TCGReg arg1, TCGReg arg2)
+{
+    MIPSInsn s_opc = OPC_SLTU;
+    int cmp_map;
+
+    switch (cond) {
+    case TCG_COND_EQ:
+        if (arg2 != 0) {
+            tcg_out_opc_reg(s, OPC_XOR, ret, arg1, arg2);
+            arg1 = ret;
+        }
+        tcg_out_opc_imm(s, OPC_SLTIU, ret, arg1, 1);
+        break;
+
+    case TCG_COND_NE:
+        if (arg2 != 0) {
+            tcg_out_opc_reg(s, OPC_XOR, ret, arg1, arg2);
+            arg1 = ret;
+        }
+        tcg_out_opc_reg(s, OPC_SLTU, ret, TCG_REG_ZERO, arg1);
+        break;
+
+    case TCG_COND_LT:
+    case TCG_COND_GE:
+    case TCG_COND_LE:
+    case TCG_COND_GT:
+        s_opc = OPC_SLT;
+        /* FALLTHRU */
+
+    case TCG_COND_LTU:
+    case TCG_COND_GEU:
+    case TCG_COND_LEU:
+    case TCG_COND_GTU:
+        cmp_map = mips_cmp_map[cond];
+        if (cmp_map & MIPS_CMP_SWAP) {
+            TCGReg t = arg1;
+            arg1 = arg2;
+            arg2 = t;
+        }
+        tcg_out_opc_reg(s, s_opc, ret, arg1, arg2);
+        if (cmp_map & MIPS_CMP_INV) {
+            tcg_out_opc_imm(s, OPC_XORI, ret, ret, 1);
+        }
+        break;
+
+     default:
+         tcg_abort();
+         break;
+     }
+}
+
+static void tcg_out_brcond(TCGContext *s, TCGCond cond, TCGReg arg1,
+                           TCGReg arg2, TCGLabel *l)
+{
+    static const MIPSInsn b_zero[16] = {
+        [TCG_COND_LT] = OPC_BLTZ,
+        [TCG_COND_GT] = OPC_BGTZ,
+        [TCG_COND_LE] = OPC_BLEZ,
+        [TCG_COND_GE] = OPC_BGEZ,
+    };
+
+    MIPSInsn s_opc = OPC_SLTU;
+    MIPSInsn b_opc;
+    int cmp_map;
+
+    switch (cond) {
+    case TCG_COND_EQ:
+        b_opc = OPC_BEQ;
+        break;
+    case TCG_COND_NE:
+        b_opc = OPC_BNE;
+        break;
+
+    case TCG_COND_LT:
+    case TCG_COND_GT:
+    case TCG_COND_LE:
+    case TCG_COND_GE:
+        if (arg2 == 0) {
+            b_opc = b_zero[cond];
+            arg2 = arg1;
+            arg1 = 0;
+            break;
+        }
+        s_opc = OPC_SLT;
+        /* FALLTHRU */
+
+    case TCG_COND_LTU:
+    case TCG_COND_GTU:
+    case TCG_COND_LEU:
+    case TCG_COND_GEU:
+        cmp_map = mips_cmp_map[cond];
+        if (cmp_map & MIPS_CMP_SWAP) {
+            TCGReg t = arg1;
+            arg1 = arg2;
+            arg2 = t;
+        }
+        tcg_out_opc_reg(s, s_opc, TCG_TMP0, arg1, arg2);
+        b_opc = (cmp_map & MIPS_CMP_INV ? OPC_BEQ : OPC_BNE);
+        arg1 = TCG_TMP0;
+        arg2 = TCG_REG_ZERO;
+        break;
+
+    default:
+        tcg_abort();
+        break;
+    }
+
+    tcg_out_opc_br(s, b_opc, arg1, arg2);
+    if (l->has_value) {
+        reloc_pc16(s->code_ptr - 1, l->u.value_ptr);
+    } else {
+        tcg_out_reloc(s, s->code_ptr - 1, R_MIPS_PC16, l, 0);
+    }
+    tcg_out_nop(s);
+}
+
+static TCGReg tcg_out_reduce_eq2(TCGContext *s, TCGReg tmp0, TCGReg tmp1,
+                                 TCGReg al, TCGReg ah,
+                                 TCGReg bl, TCGReg bh)
+{
+    /* Merge highpart comparison into AH.  */
+    if (bh != 0) {
+        if (ah != 0) {
+            tcg_out_opc_reg(s, OPC_XOR, tmp0, ah, bh);
+            ah = tmp0;
+        } else {
+            ah = bh;
+        }
+    }
+    /* Merge lowpart comparison into AL.  */
+    if (bl != 0) {
+        if (al != 0) {
+            tcg_out_opc_reg(s, OPC_XOR, tmp1, al, bl);
+            al = tmp1;
+        } else {
+            al = bl;
+        }
+    }
+    /* Merge high and low part comparisons into AL.  */
+    if (ah != 0) {
+        if (al != 0) {
+            tcg_out_opc_reg(s, OPC_OR, tmp0, ah, al);
+            al = tmp0;
+        } else {
+            al = ah;
+        }
+    }
+    return al;
+}
+
+static void tcg_out_setcond2(TCGContext *s, TCGCond cond, TCGReg ret,
+                             TCGReg al, TCGReg ah, TCGReg bl, TCGReg bh)
+{
+    TCGReg tmp0 = TCG_TMP0;
+    TCGReg tmp1 = ret;
+
+    assert(ret != TCG_TMP0);
+    if (ret == ah || ret == bh) {
+        assert(ret != TCG_TMP1);
+        tmp1 = TCG_TMP1;
+    }
+
+    switch (cond) {
+    case TCG_COND_EQ:
+    case TCG_COND_NE:
+        tmp1 = tcg_out_reduce_eq2(s, tmp0, tmp1, al, ah, bl, bh);
+        tcg_out_setcond(s, cond, ret, tmp1, TCG_REG_ZERO);
+        break;
+
+    default:
+        tcg_out_setcond(s, TCG_COND_EQ, tmp0, ah, bh);
+        tcg_out_setcond(s, tcg_unsigned_cond(cond), tmp1, al, bl);
+        tcg_out_opc_reg(s, OPC_AND, tmp1, tmp1, tmp0);
+        tcg_out_setcond(s, tcg_high_cond(cond), tmp0, ah, bh);
+        tcg_out_opc_reg(s, OPC_OR, ret, tmp1, tmp0);
+        break;
+    }
+}
+
+static void tcg_out_brcond2(TCGContext *s, TCGCond cond, TCGReg al, TCGReg ah,
+                            TCGReg bl, TCGReg bh, TCGLabel *l)
+{
+    TCGCond b_cond = TCG_COND_NE;
+    TCGReg tmp = TCG_TMP1;
+
+    /* With branches, we emit between 4 and 9 insns with 2 or 3 branches.
+       With setcond, we emit between 3 and 10 insns and only 1 branch,
+       which ought to get better branch prediction.  */
+     switch (cond) {
+     case TCG_COND_EQ:
+     case TCG_COND_NE:
+        b_cond = cond;
+        tmp = tcg_out_reduce_eq2(s, TCG_TMP0, TCG_TMP1, al, ah, bl, bh);
+        break;
+
+    default:
+        /* Minimize code size by preferring a compare not requiring INV.  */
+        if (mips_cmp_map[cond] & MIPS_CMP_INV) {
+            cond = tcg_invert_cond(cond);
+            b_cond = TCG_COND_EQ;
+        }
+        tcg_out_setcond2(s, cond, tmp, al, ah, bl, bh);
+        break;
+    }
+
+    tcg_out_brcond(s, b_cond, tmp, TCG_REG_ZERO, l);
+}
+
+static void tcg_out_movcond(TCGContext *s, TCGCond cond, TCGReg ret,
+                            TCGReg c1, TCGReg c2, TCGReg v)
+{
+    MIPSInsn m_opc = OPC_MOVN;
+
+    switch (cond) {
+    case TCG_COND_EQ:
+        m_opc = OPC_MOVZ;
+        /* FALLTHRU */
+    case TCG_COND_NE:
+        if (c2 != 0) {
+            tcg_out_opc_reg(s, OPC_XOR, TCG_TMP0, c1, c2);
+            c1 = TCG_TMP0;
+        }
+        break;
+
+    default:
+        /* Minimize code size by preferring a compare not requiring INV.  */
+        if (mips_cmp_map[cond] & MIPS_CMP_INV) {
+            cond = tcg_invert_cond(cond);
+            m_opc = OPC_MOVZ;
+        }
+        tcg_out_setcond(s, cond, TCG_TMP0, c1, c2);
+        c1 = TCG_TMP0;
+        break;
+    }
+
+    tcg_out_opc_reg(s, m_opc, ret, v, c1);
+}
+
+static void tcg_out_call_int(TCGContext *s, tcg_insn_unit *arg, bool tail)
+{
+    /* Note that the ABI requires the called function's address to be
+       loaded into T9, even if a direct branch is in range.  */
+    tcg_out_movi(s, TCG_TYPE_PTR, TCG_REG_T9, (uintptr_t)arg);
+
+    /* But do try a direct branch, allowing the cpu better insn prefetch.  */
+    if (tail) {
+        if (!tcg_out_opc_jmp(s, OPC_J, arg)) {
+            tcg_out_opc_reg(s, OPC_JR, 0, TCG_REG_T9, 0);
+        }
+    } else {
+        if (!tcg_out_opc_jmp(s, OPC_JAL, arg)) {
+            tcg_out_opc_reg(s, OPC_JALR, TCG_REG_RA, TCG_REG_T9, 0);
+        }
+    }
+}
+
+static void tcg_out_call(TCGContext *s, tcg_insn_unit *arg)
+{
+    tcg_out_call_int(s, arg, false);
+    tcg_out_nop(s);
+}
+
+#if defined(CONFIG_SOFTMMU)
+static void * const qemu_ld_helpers[16] = {
+    [MO_UB]   = helper_ret_ldub_mmu,
+    [MO_SB]   = helper_ret_ldsb_mmu,
+    [MO_LEUW] = helper_le_lduw_mmu,
+    [MO_LESW] = helper_le_ldsw_mmu,
+    [MO_LEUL] = helper_le_ldul_mmu,
+    [MO_LEQ]  = helper_le_ldq_mmu,
+    [MO_BEUW] = helper_be_lduw_mmu,
+    [MO_BESW] = helper_be_ldsw_mmu,
+    [MO_BEUL] = helper_be_ldul_mmu,
+    [MO_BEQ]  = helper_be_ldq_mmu,
+};
+
+static void * const qemu_st_helpers[16] = {
+    [MO_UB]   = helper_ret_stb_mmu,
+    [MO_LEUW] = helper_le_stw_mmu,
+    [MO_LEUL] = helper_le_stl_mmu,
+    [MO_LEQ]  = helper_le_stq_mmu,
+    [MO_BEUW] = helper_be_stw_mmu,
+    [MO_BEUL] = helper_be_stl_mmu,
+    [MO_BEQ]  = helper_be_stq_mmu,
+};
+
+/* Helper routines for marshalling helper function arguments into
+ * the correct registers and stack.
+ * I is where we want to put this argument, and is updated and returned
+ * for the next call. ARG is the argument itself.
+ *
+ * We provide routines for arguments which are: immediate, 32 bit
+ * value in register, 16 and 8 bit values in register (which must be zero
+ * extended before use) and 64 bit value in a lo:hi register pair.
+ */
+
+static int tcg_out_call_iarg_reg(TCGContext *s, int i, TCGReg arg)
+{
+    if (i < ARRAY_SIZE(tcg_target_call_iarg_regs)) {
+        tcg_out_mov(s, TCG_TYPE_REG, tcg_target_call_iarg_regs[i], arg);
+    } else {
+        tcg_out_st(s, TCG_TYPE_REG, arg, TCG_REG_SP, 4 * i);
+    }
+    return i + 1;
+}
+
+static int tcg_out_call_iarg_reg8(TCGContext *s, int i, TCGReg arg)
+{
+    TCGReg tmp = TCG_TMP0;
+    if (i < ARRAY_SIZE(tcg_target_call_iarg_regs)) {
+        tmp = tcg_target_call_iarg_regs[i];
+    }
+    tcg_out_opc_imm(s, OPC_ANDI, tmp, arg, 0xff);
+    return tcg_out_call_iarg_reg(s, i, tmp);
+}
+
+static int tcg_out_call_iarg_reg16(TCGContext *s, int i, TCGReg arg)
+{
+    TCGReg tmp = TCG_TMP0;
+    if (i < ARRAY_SIZE(tcg_target_call_iarg_regs)) {
+        tmp = tcg_target_call_iarg_regs[i];
+    }
+    tcg_out_opc_imm(s, OPC_ANDI, tmp, arg, 0xffff);
+    return tcg_out_call_iarg_reg(s, i, tmp);
+}
+
+static int tcg_out_call_iarg_imm(TCGContext *s, int i, TCGArg arg)
+{
+    TCGReg tmp = TCG_TMP0;
+    if (arg == 0) {
+        tmp = TCG_REG_ZERO;
+    } else {
+        if (i < ARRAY_SIZE(tcg_target_call_iarg_regs)) {
+            tmp = tcg_target_call_iarg_regs[i];
+        }
+        tcg_out_movi(s, TCG_TYPE_REG, tmp, arg);
+    }
+    return tcg_out_call_iarg_reg(s, i, tmp);
+}
+
+static int tcg_out_call_iarg_reg2(TCGContext *s, int i, TCGReg al, TCGReg ah)
+{
+    i = (i + 1) & ~1;
+    i = tcg_out_call_iarg_reg(s, i, (MIPS_BE ? ah : al));
+    i = tcg_out_call_iarg_reg(s, i, (MIPS_BE ? al : ah));
+    return i;
+}
+
+/* Perform the tlb comparison operation.  The complete host address is
+   placed in BASE.  Clobbers AT, T0, A0.  */
+static void tcg_out_tlb_load(TCGContext *s, TCGReg base, TCGReg addrl,
+                             TCGReg addrh, int mem_index, TCGMemOp s_bits,
+                             tcg_insn_unit *label_ptr[2], bool is_load)
+{
+    int cmp_off
+        = (is_load
+           ? offsetof(CPUArchState, tlb_table[mem_index][0].addr_read)
+           : offsetof(CPUArchState, tlb_table[mem_index][0].addr_write));
+    int add_off = offsetof(CPUArchState, tlb_table[mem_index][0].addend);
+
+    tcg_out_opc_sa(s, OPC_SRL, TCG_REG_A0, addrl,
+                   TARGET_PAGE_BITS - CPU_TLB_ENTRY_BITS);
+    tcg_out_opc_imm(s, OPC_ANDI, TCG_REG_A0, TCG_REG_A0,
+                    (CPU_TLB_SIZE - 1) << CPU_TLB_ENTRY_BITS);
+    tcg_out_opc_reg(s, OPC_ADDU, TCG_REG_A0, TCG_REG_A0, TCG_AREG0);
+
+    /* Compensate for very large offsets.  */
+    if (add_off >= 0x8000) {
+        /* Most target env are smaller than 32k; none are larger than 64k.
+           Simplify the logic here merely to offset by 0x7ff0, giving us a
+           range just shy of 64k.  Check this assumption.  */
+        QEMU_BUILD_BUG_ON(offsetof(CPUArchState,
+                                   tlb_table[NB_MMU_MODES - 1][1])
+                          > 0x7ff0 + 0x7fff);
+        tcg_out_opc_imm(s, OPC_ADDIU, TCG_REG_A0, TCG_REG_A0, 0x7ff0);
+        cmp_off -= 0x7ff0;
+        add_off -= 0x7ff0;
+    }
+
+    /* Load the (low half) tlb comparator.  */
+    tcg_out_opc_imm(s, OPC_LW, TCG_TMP0, TCG_REG_A0,
+                    cmp_off + (TARGET_LONG_BITS == 64 ? LO_OFF : 0));
+
+    /* Mask the page bits, keeping the alignment bits to compare against.
+       In between on 32-bit targets, load the tlb addend for the fast path.  */
+    tcg_out_movi(s, TCG_TYPE_I32, TCG_TMP1,
+                 TARGET_PAGE_MASK | ((1 << s_bits) - 1));
+    if (TARGET_LONG_BITS == 32) {
+        tcg_out_opc_imm(s, OPC_LW, TCG_REG_A0, TCG_REG_A0, add_off);
+    }
+    tcg_out_opc_reg(s, OPC_AND, TCG_TMP1, TCG_TMP1, addrl);
+
+    label_ptr[0] = s->code_ptr;
+    tcg_out_opc_br(s, OPC_BNE, TCG_TMP1, TCG_TMP0);
+
+    /* Load and test the high half tlb comparator.  */
+    if (TARGET_LONG_BITS == 64) {
+        /* delay slot */
+        tcg_out_opc_imm(s, OPC_LW, TCG_TMP0, TCG_REG_A0, cmp_off + HI_OFF);
+
+        /* Load the tlb addend for the fast path. We can't do it earlier with
+           64-bit targets or we'll clobber a0 before reading the high half tlb
+           comparator.  */
+        tcg_out_opc_imm(s, OPC_LW, TCG_REG_A0, TCG_REG_A0, add_off);
+
+        label_ptr[1] = s->code_ptr;
+        tcg_out_opc_br(s, OPC_BNE, addrh, TCG_TMP0);
+    }
+
+    /* delay slot */
+    tcg_out_opc_reg(s, OPC_ADDU, base, TCG_REG_A0, addrl);
+}
+
+static void add_qemu_ldst_label(TCGContext *s, int is_ld, TCGMemOpIdx oi,
+                                TCGReg datalo, TCGReg datahi,
+                                TCGReg addrlo, TCGReg addrhi,
+                                void *raddr, tcg_insn_unit *label_ptr[2])
+{
+    TCGLabelQemuLdst *label = new_ldst_label(s);
+
+    label->is_ld = is_ld;
+    label->oi = oi;
+    label->datalo_reg = datalo;
+    label->datahi_reg = datahi;
+    label->addrlo_reg = addrlo;
+    label->addrhi_reg = addrhi;
+    label->raddr = raddr;
+    label->label_ptr[0] = label_ptr[0];
+    if (TARGET_LONG_BITS == 64) {
+        label->label_ptr[1] = label_ptr[1];
+    }
+}
+
+static void tcg_out_qemu_ld_slow_path(TCGContext *s, TCGLabelQemuLdst *l)
+{
+    TCGMemOpIdx oi = l->oi;
+    TCGMemOp opc = get_memop(oi);
+    TCGReg v0;
+    int i;
+
+    /* resolve label address */
+    reloc_pc16(l->label_ptr[0], s->code_ptr);
+    if (TARGET_LONG_BITS == 64) {
+        reloc_pc16(l->label_ptr[1], s->code_ptr);
+    }
+
+    i = 1;
+    if (TARGET_LONG_BITS == 64) {
+        i = tcg_out_call_iarg_reg2(s, i, l->addrlo_reg, l->addrhi_reg);
+    } else {
+        i = tcg_out_call_iarg_reg(s, i, l->addrlo_reg);
+    }
+    i = tcg_out_call_iarg_imm(s, i, oi);
+    i = tcg_out_call_iarg_imm(s, i, (intptr_t)l->raddr);
+    tcg_out_call_int(s, qemu_ld_helpers[opc & (MO_BSWAP | MO_SSIZE)], false);
+    /* delay slot */
+    tcg_out_mov(s, TCG_TYPE_PTR, tcg_target_call_iarg_regs[0], TCG_AREG0);
+
+    v0 = l->datalo_reg;
+    if ((opc & MO_SIZE) == MO_64) {
+        /* We eliminated V0 from the possible output registers, so it
+           cannot be clobbered here.  So we must move V1 first.  */
+        if (MIPS_BE) {
+            tcg_out_mov(s, TCG_TYPE_I32, v0, TCG_REG_V1);
+            v0 = l->datahi_reg;
+        } else {
+            tcg_out_mov(s, TCG_TYPE_I32, l->datahi_reg, TCG_REG_V1);
+        }
+    }
+
+    reloc_pc16(s->code_ptr, l->raddr);
+    tcg_out_opc_br(s, OPC_BEQ, TCG_REG_ZERO, TCG_REG_ZERO);
+    /* delay slot */
+    tcg_out_mov(s, TCG_TYPE_REG, v0, TCG_REG_V0);
+}
+
+static void tcg_out_qemu_st_slow_path(TCGContext *s, TCGLabelQemuLdst *l)
+{
+    TCGMemOpIdx oi = l->oi;
+    TCGMemOp opc = get_memop(oi);
+    TCGMemOp s_bits = opc & MO_SIZE;
+    int i;
+
+    /* resolve label address */
+    reloc_pc16(l->label_ptr[0], s->code_ptr);
+    if (TARGET_LONG_BITS == 64) {
+        reloc_pc16(l->label_ptr[1], s->code_ptr);
+    }
+
+    i = 1;
+    if (TARGET_LONG_BITS == 64) {
+        i = tcg_out_call_iarg_reg2(s, i, l->addrlo_reg, l->addrhi_reg);
+    } else {
+        i = tcg_out_call_iarg_reg(s, i, l->addrlo_reg);
+    }
+    switch (s_bits) {
+    case MO_8:
+        i = tcg_out_call_iarg_reg8(s, i, l->datalo_reg);
+        break;
+    case MO_16:
+        i = tcg_out_call_iarg_reg16(s, i, l->datalo_reg);
+        break;
+    case MO_32:
+        i = tcg_out_call_iarg_reg(s, i, l->datalo_reg);
+        break;
+    case MO_64:
+        i = tcg_out_call_iarg_reg2(s, i, l->datalo_reg, l->datahi_reg);
+        break;
+    default:
+        tcg_abort();
+    }
+    i = tcg_out_call_iarg_imm(s, i, oi);
+
+    /* Tail call to the store helper.  Thus force the return address
+       computation to take place in the return address register.  */
+    tcg_out_movi(s, TCG_TYPE_PTR, TCG_REG_RA, (intptr_t)l->raddr);
+    i = tcg_out_call_iarg_reg(s, i, TCG_REG_RA);
+    tcg_out_call_int(s, qemu_st_helpers[opc & (MO_BSWAP | MO_SIZE)], true);
+    /* delay slot */
+    tcg_out_mov(s, TCG_TYPE_PTR, tcg_target_call_iarg_regs[0], TCG_AREG0);
+}
+#endif
+
+static void tcg_out_qemu_ld_direct(TCGContext *s, TCGReg datalo, TCGReg datahi,
+                                   TCGReg base, TCGMemOp opc)
+{
+    switch (opc & (MO_SSIZE | MO_BSWAP)) {
+    case MO_UB:
+        tcg_out_opc_imm(s, OPC_LBU, datalo, base, 0);
+        break;
+    case MO_SB:
+        tcg_out_opc_imm(s, OPC_LB, datalo, base, 0);
+        break;
+    case MO_UW | MO_BSWAP:
+        tcg_out_opc_imm(s, OPC_LHU, TCG_TMP1, base, 0);
+        tcg_out_bswap16(s, datalo, TCG_TMP1);
+        break;
+    case MO_UW:
+        tcg_out_opc_imm(s, OPC_LHU, datalo, base, 0);
+        break;
+    case MO_SW | MO_BSWAP:
+        tcg_out_opc_imm(s, OPC_LHU, TCG_TMP1, base, 0);
+        tcg_out_bswap16s(s, datalo, TCG_TMP1);
+        break;
+    case MO_SW:
+        tcg_out_opc_imm(s, OPC_LH, datalo, base, 0);
+        break;
+    case MO_UL | MO_BSWAP:
+        tcg_out_opc_imm(s, OPC_LW, TCG_TMP1, base, 0);
+        tcg_out_bswap32(s, datalo, TCG_TMP1);
+        break;
+    case MO_UL:
+        tcg_out_opc_imm(s, OPC_LW, datalo, base, 0);
+        break;
+    case MO_Q | MO_BSWAP:
+        tcg_out_opc_imm(s, OPC_LW, TCG_TMP1, base, HI_OFF);
+        tcg_out_bswap32(s, datalo, TCG_TMP1);
+        tcg_out_opc_imm(s, OPC_LW, TCG_TMP1, base, LO_OFF);
+        tcg_out_bswap32(s, datahi, TCG_TMP1);
+        break;
+    case MO_Q:
+        tcg_out_opc_imm(s, OPC_LW, datalo, base, LO_OFF);
+        tcg_out_opc_imm(s, OPC_LW, datahi, base, HI_OFF);
+        break;
+    default:
+        tcg_abort();
+    }
+}
+
+static void tcg_out_qemu_ld(TCGContext *s, const TCGArg *args, bool is_64)
+{
+    TCGReg addr_regl, addr_regh __attribute__((unused));
+    TCGReg data_regl, data_regh;
+    TCGMemOpIdx oi;
+    TCGMemOp opc;
+#if defined(CONFIG_SOFTMMU)
+    tcg_insn_unit *label_ptr[2];
+    int mem_index;
+    TCGMemOp s_bits;
+#endif
+    /* Note that we've eliminated V0 from the output registers,
+       so we won't overwrite the base register during loading.  */
+    TCGReg base = TCG_REG_V0;
+
+    data_regl = *args++;
+    data_regh = (is_64 ? *args++ : 0);
+    addr_regl = *args++;
+    addr_regh = (TARGET_LONG_BITS == 64 ? *args++ : 0);
+    oi = *args++;
+    opc = get_memop(oi);
+
+#if defined(CONFIG_SOFTMMU)
+    mem_index = get_mmuidx(oi);
+    s_bits = opc & MO_SIZE;
+
+    tcg_out_tlb_load(s, base, addr_regl, addr_regh, mem_index,
+                     s_bits, label_ptr, 1);
+    tcg_out_qemu_ld_direct(s, data_regl, data_regh, base, opc);
+    add_qemu_ldst_label(s, 1, oi, data_regl, data_regh, addr_regl, addr_regh,
+                        s->code_ptr, label_ptr);
+#else
+    if (GUEST_BASE == 0 && data_regl != addr_regl) {
+        base = addr_regl;
+    } else if (GUEST_BASE == (int16_t)GUEST_BASE) {
+        tcg_out_opc_imm(s, OPC_ADDIU, base, addr_regl, GUEST_BASE);
+    } else {
+        tcg_out_movi(s, TCG_TYPE_PTR, base, GUEST_BASE);
+        tcg_out_opc_reg(s, OPC_ADDU, base, base, addr_regl);
+    }
+    tcg_out_qemu_ld_direct(s, data_regl, data_regh, base, opc);
+#endif
+}
+
+static void tcg_out_qemu_st_direct(TCGContext *s, TCGReg datalo, TCGReg datahi,
+                                   TCGReg base, TCGMemOp opc)
+{
+    switch (opc & (MO_SIZE | MO_BSWAP)) {
+    case MO_8:
+        tcg_out_opc_imm(s, OPC_SB, datalo, base, 0);
+        break;
+
+    case MO_16 | MO_BSWAP:
+        tcg_out_opc_imm(s, OPC_ANDI, TCG_TMP1, datalo, 0xffff);
+        tcg_out_bswap16(s, TCG_TMP1, TCG_TMP1);
+        datalo = TCG_TMP1;
+        /* FALLTHRU */
+    case MO_16:
+        tcg_out_opc_imm(s, OPC_SH, datalo, base, 0);
+        break;
+
+    case MO_32 | MO_BSWAP:
+        tcg_out_bswap32(s, TCG_TMP1, datalo);
+        datalo = TCG_TMP1;
+        /* FALLTHRU */
+    case MO_32:
+        tcg_out_opc_imm(s, OPC_SW, datalo, base, 0);
+        break;
+
+    case MO_64 | MO_BSWAP:
+        tcg_out_bswap32(s, TCG_TMP1, datalo);
+        tcg_out_opc_imm(s, OPC_SW, TCG_TMP1, base, HI_OFF);
+        tcg_out_bswap32(s, TCG_TMP1, datahi);
+        tcg_out_opc_imm(s, OPC_SW, TCG_TMP1, base, LO_OFF);
+        break;
+    case MO_64:
+        tcg_out_opc_imm(s, OPC_SW, datalo, base, LO_OFF);
+        tcg_out_opc_imm(s, OPC_SW, datahi, base, HI_OFF);
+        break;
+
+    default:
+        tcg_abort();
+    }
+}
+
+static void tcg_out_addsub2(TCGContext *s, TCGReg rl, TCGReg rh, TCGReg al,
+                            TCGReg ah, TCGArg bl, TCGArg bh, bool cbl,
+                            bool cbh, bool is_sub)
+{
+    TCGReg th = TCG_TMP1;
+
+    /* If we have a negative constant such that negating it would
+       make the high part zero, we can (usually) eliminate one insn.  */
+    if (cbl && cbh && bh == -1 && bl != 0) {
+        bl = -bl;
+        bh = 0;
+        is_sub = !is_sub;
+    }
+
+    /* By operating on the high part first, we get to use the final
+       carry operation to move back from the temporary.  */
+    if (!cbh) {
+        tcg_out_opc_reg(s, (is_sub ? OPC_SUBU : OPC_ADDU), th, ah, bh);
+    } else if (bh != 0 || ah == rl) {
+        tcg_out_opc_imm(s, OPC_ADDIU, th, ah, (is_sub ? -bh : bh));
+    } else {
+        th = ah;
+    }
+
+    /* Note that tcg optimization should eliminate the bl == 0 case.  */
+    if (is_sub) {
+        if (cbl) {
+            tcg_out_opc_imm(s, OPC_SLTIU, TCG_TMP0, al, bl);
+            tcg_out_opc_imm(s, OPC_ADDIU, rl, al, -bl);
+        } else {
+            tcg_out_opc_reg(s, OPC_SLTU, TCG_TMP0, al, bl);
+            tcg_out_opc_reg(s, OPC_SUBU, rl, al, bl);
+        }
+        tcg_out_opc_reg(s, OPC_SUBU, rh, th, TCG_TMP0);
+    } else {
+        if (cbl) {
+            tcg_out_opc_imm(s, OPC_ADDIU, rl, al, bl);
+            tcg_out_opc_imm(s, OPC_SLTIU, TCG_TMP0, rl, bl);
+        } else if (rl == al && rl == bl) {
+            tcg_out_opc_sa(s, OPC_SRL, TCG_TMP0, al, 31);
+            tcg_out_opc_reg(s, OPC_ADDU, rl, al, bl);
+        } else {
+            tcg_out_opc_reg(s, OPC_ADDU, rl, al, bl);
+            tcg_out_opc_reg(s, OPC_SLTU, TCG_TMP0, rl, (rl == bl ? al : bl));
+        }
+        tcg_out_opc_reg(s, OPC_ADDU, rh, th, TCG_TMP0);
+    }
+}
+
+static void tcg_out_qemu_st(TCGContext *s, const TCGArg *args, bool is_64)
+{
+    TCGReg addr_regl, addr_regh __attribute__((unused));
+    TCGReg data_regl, data_regh, base;
+    TCGMemOpIdx oi;
+    TCGMemOp opc;
+#if defined(CONFIG_SOFTMMU)
+    tcg_insn_unit *label_ptr[2];
+    int mem_index;
+    TCGMemOp s_bits;
+#endif
+
+    data_regl = *args++;
+    data_regh = (is_64 ? *args++ : 0);
+    addr_regl = *args++;
+    addr_regh = (TARGET_LONG_BITS == 64 ? *args++ : 0);
+    oi = *args++;
+    opc = get_memop(oi);
+
+#if defined(CONFIG_SOFTMMU)
+    mem_index = get_mmuidx(oi);
+    s_bits = opc & 3;
+
+    /* Note that we eliminated the helper's address argument,
+       so we can reuse that for the base.  */
+    base = (TARGET_LONG_BITS == 32 ? TCG_REG_A1 : TCG_REG_A2);
+    tcg_out_tlb_load(s, base, addr_regl, addr_regh, mem_index,
+                     s_bits, label_ptr, 0);
+    tcg_out_qemu_st_direct(s, data_regl, data_regh, base, opc);
+    add_qemu_ldst_label(s, 0, oi, data_regl, data_regh, addr_regl, addr_regh,
+                        s->code_ptr, label_ptr);
+#else
+    if (GUEST_BASE == 0) {
+        base = addr_regl;
+    } else {
+        base = TCG_REG_A0;
+        if (GUEST_BASE == (int16_t)GUEST_BASE) {
+            tcg_out_opc_imm(s, OPC_ADDIU, base, addr_regl, GUEST_BASE);
+        } else {
+            tcg_out_movi(s, TCG_TYPE_PTR, base, GUEST_BASE);
+            tcg_out_opc_reg(s, OPC_ADDU, base, base, addr_regl);
+        }
+    }
+    tcg_out_qemu_st_direct(s, data_regl, data_regh, base, opc);
+#endif
+}
+
+static inline void tcg_out_op(TCGContext *s, TCGOpcode opc,
+                              const TCGArg *args, const int *const_args)
+{
+    MIPSInsn i1, i2;
+    TCGArg a0, a1, a2;
+    int c2;
+
+    a0 = args[0];
+    a1 = args[1];
+    a2 = args[2];
+    c2 = const_args[2];
+
+    switch (opc) {
+    case INDEX_op_exit_tb:
+        {
+            TCGReg b0 = TCG_REG_ZERO;
+
+            if (a0 & ~0xffff) {
+                tcg_out_movi(s, TCG_TYPE_PTR, TCG_REG_V0, a0 & ~0xffff);
+                b0 = TCG_REG_V0;
+            }
+            if (!tcg_out_opc_jmp(s, OPC_J, tb_ret_addr)) {
+                tcg_out_movi(s, TCG_TYPE_PTR, TCG_TMP0,
+                             (uintptr_t)tb_ret_addr);
+                tcg_out_opc_reg(s, OPC_JR, 0, TCG_TMP0, 0);
+            }
+            tcg_out_opc_imm(s, OPC_ORI, TCG_REG_V0, b0, a0 & 0xffff);
+        }
+        break;
+    case INDEX_op_goto_tb:
+        if (s->tb_jmp_offset) {
+            /* direct jump method */
+            s->tb_jmp_offset[a0] = tcg_current_code_size(s);
+            /* Avoid clobbering the address during retranslation.  */
+            tcg_out32(s, OPC_J | (*(uint32_t *)s->code_ptr & 0x3ffffff));
+        } else {
+            /* indirect jump method */
+            tcg_out_ld(s, TCG_TYPE_PTR, TCG_TMP0, TCG_REG_ZERO,
+                       (uintptr_t)(s->tb_next + a0));
+            tcg_out_opc_reg(s, OPC_JR, 0, TCG_TMP0, 0);
+        }
+        tcg_out_nop(s);
+        s->tb_next_offset[a0] = tcg_current_code_size(s);
+        break;
+    case INDEX_op_br:
+        tcg_out_brcond(s, TCG_COND_EQ, TCG_REG_ZERO, TCG_REG_ZERO,
+                       arg_label(a0));
+        break;
+
+    case INDEX_op_ld8u_i32:
+        i1 = OPC_LBU;
+        goto do_ldst;
+    case INDEX_op_ld8s_i32:
+        i1 = OPC_LB;
+        goto do_ldst;
+    case INDEX_op_ld16u_i32:
+        i1 = OPC_LHU;
+        goto do_ldst;
+    case INDEX_op_ld16s_i32:
+        i1 = OPC_LH;
+        goto do_ldst;
+    case INDEX_op_ld_i32:
+        i1 = OPC_LW;
+        goto do_ldst;
+    case INDEX_op_st8_i32:
+        i1 = OPC_SB;
+        goto do_ldst;
+    case INDEX_op_st16_i32:
+        i1 = OPC_SH;
+        goto do_ldst;
+    case INDEX_op_st_i32:
+        i1 = OPC_SW;
+    do_ldst:
+        tcg_out_ldst(s, i1, a0, a1, a2);
+        break;
+
+    case INDEX_op_add_i32:
+        i1 = OPC_ADDU, i2 = OPC_ADDIU;
+        goto do_binary;
+    case INDEX_op_or_i32:
+        i1 = OPC_OR, i2 = OPC_ORI;
+        goto do_binary;
+    case INDEX_op_xor_i32:
+        i1 = OPC_XOR, i2 = OPC_XORI;
+    do_binary:
+        if (c2) {
+            tcg_out_opc_imm(s, i2, a0, a1, a2);
+            break;
+        }
+    do_binaryv:
+        tcg_out_opc_reg(s, i1, a0, a1, a2);
+        break;
+
+    case INDEX_op_sub_i32:
+        if (c2) {
+            tcg_out_opc_imm(s, OPC_ADDIU, a0, a1, -a2);
+            break;
+        }
+        i1 = OPC_SUBU;
+        goto do_binary;
+    case INDEX_op_and_i32:
+        if (c2 && a2 != (uint16_t)a2) {
+            int msb = ctz32(~a2) - 1;
+            assert(use_mips32r2_instructions);
+            assert(is_p2m1(a2));
+            tcg_out_opc_bf(s, OPC_EXT, a0, a1, msb, 0);
+            break;
+        }
+        i1 = OPC_AND, i2 = OPC_ANDI;
+        goto do_binary;
+    case INDEX_op_nor_i32:
+        i1 = OPC_NOR;
+        goto do_binaryv;
+
+    case INDEX_op_mul_i32:
+        if (use_mips32_instructions) {
+            tcg_out_opc_reg(s, OPC_MUL, a0, a1, a2);
+            break;
+        }
+        i1 = OPC_MULT, i2 = OPC_MFLO;
+        goto do_hilo1;
+    case INDEX_op_mulsh_i32:
+        i1 = OPC_MULT, i2 = OPC_MFHI;
+        goto do_hilo1;
+    case INDEX_op_muluh_i32:
+        i1 = OPC_MULTU, i2 = OPC_MFHI;
+        goto do_hilo1;
+    case INDEX_op_div_i32:
+        i1 = OPC_DIV, i2 = OPC_MFLO;
+        goto do_hilo1;
+    case INDEX_op_divu_i32:
+        i1 = OPC_DIVU, i2 = OPC_MFLO;
+        goto do_hilo1;
+    case INDEX_op_rem_i32:
+        i1 = OPC_DIV, i2 = OPC_MFHI;
+        goto do_hilo1;
+    case INDEX_op_remu_i32:
+        i1 = OPC_DIVU, i2 = OPC_MFHI;
+    do_hilo1:
+        tcg_out_opc_reg(s, i1, 0, a1, a2);
+        tcg_out_opc_reg(s, i2, a0, 0, 0);
+        break;
+
+    case INDEX_op_muls2_i32:
+        i1 = OPC_MULT;
+        goto do_hilo2;
+    case INDEX_op_mulu2_i32:
+        i1 = OPC_MULTU;
+    do_hilo2:
+        tcg_out_opc_reg(s, i1, 0, a2, args[3]);
+        tcg_out_opc_reg(s, OPC_MFLO, a0, 0, 0);
+        tcg_out_opc_reg(s, OPC_MFHI, a1, 0, 0);
+        break;
+
+    case INDEX_op_not_i32:
+        i1 = OPC_NOR;
+        goto do_unary;
+    case INDEX_op_bswap16_i32:
+        i1 = OPC_WSBH;
+        goto do_unary;
+    case INDEX_op_ext8s_i32:
+        i1 = OPC_SEB;
+        goto do_unary;
+    case INDEX_op_ext16s_i32:
+        i1 = OPC_SEH;
+    do_unary:
+        tcg_out_opc_reg(s, i1, a0, TCG_REG_ZERO, a1);
+        break;
+
+    case INDEX_op_sar_i32:
+        i1 = OPC_SRAV, i2 = OPC_SRA;
+        goto do_shift;
+    case INDEX_op_shl_i32:
+        i1 = OPC_SLLV, i2 = OPC_SLL;
+        goto do_shift;
+    case INDEX_op_shr_i32:
+        i1 = OPC_SRLV, i2 = OPC_SRL;
+        goto do_shift;
+    case INDEX_op_rotr_i32:
+        i1 = OPC_ROTRV, i2 = OPC_ROTR;
+    do_shift:
+        if (c2) {
+            tcg_out_opc_sa(s, i2, a0, a1, a2);
+        } else {
+            tcg_out_opc_reg(s, i1, a0, a2, a1);
+        }
+        break;
+    case INDEX_op_rotl_i32:
+        if (c2) {
+            tcg_out_opc_sa(s, OPC_ROTR, a0, a1, 32 - a2);
+        } else {
+            tcg_out_opc_reg(s, OPC_SUBU, TCG_TMP0, TCG_REG_ZERO, a2);
+            tcg_out_opc_reg(s, OPC_ROTRV, a0, TCG_TMP0, a1);
+        }
+        break;
+
+    case INDEX_op_bswap32_i32:
+        tcg_out_opc_reg(s, OPC_WSBH, a0, 0, a1);
+        tcg_out_opc_sa(s, OPC_ROTR, a0, a0, 16);
+        break;
+
+    case INDEX_op_deposit_i32:
+        tcg_out_opc_bf(s, OPC_INS, a0, a2, args[3] + args[4] - 1, args[3]);
+        break;
+
+    case INDEX_op_brcond_i32:
+        tcg_out_brcond(s, a2, a0, a1, arg_label(args[3]));
+        break;
+    case INDEX_op_brcond2_i32:
+        tcg_out_brcond2(s, args[4], a0, a1, a2, args[3], arg_label(args[5]));
+        break;
+
+    case INDEX_op_movcond_i32:
+        tcg_out_movcond(s, args[5], a0, a1, a2, args[3]);
+        break;
+
+    case INDEX_op_setcond_i32:
+        tcg_out_setcond(s, args[3], a0, a1, a2);
+        break;
+    case INDEX_op_setcond2_i32:
+        tcg_out_setcond2(s, args[5], a0, a1, a2, args[3], args[4]);
+        break;
+
+    case INDEX_op_qemu_ld_i32:
+        tcg_out_qemu_ld(s, args, false);
+        break;
+    case INDEX_op_qemu_ld_i64:
+        tcg_out_qemu_ld(s, args, true);
+        break;
+    case INDEX_op_qemu_st_i32:
+        tcg_out_qemu_st(s, args, false);
+        break;
+    case INDEX_op_qemu_st_i64:
+        tcg_out_qemu_st(s, args, true);
+        break;
+
+    case INDEX_op_add2_i32:
+        tcg_out_addsub2(s, a0, a1, a2, args[3], args[4], args[5],
+                        const_args[4], const_args[5], false);
+        break;
+    case INDEX_op_sub2_i32:
+        tcg_out_addsub2(s, a0, a1, a2, args[3], args[4], args[5],
+                        const_args[4], const_args[5], true);
+        break;
+
+    case INDEX_op_mov_i32:  /* Always emitted via tcg_out_mov.  */
+    case INDEX_op_movi_i32: /* Always emitted via tcg_out_movi.  */
+    case INDEX_op_call:     /* Always emitted via tcg_out_call.  */
+    default:
+        tcg_abort();
+    }
+}
+
+static const TCGTargetOpDef mips_op_defs[] = {
+    { INDEX_op_exit_tb, { } },
+    { INDEX_op_goto_tb, { } },
+    { INDEX_op_br, { } },
+
+    { INDEX_op_ld8u_i32, { "r", "r" } },
+    { INDEX_op_ld8s_i32, { "r", "r" } },
+    { INDEX_op_ld16u_i32, { "r", "r" } },
+    { INDEX_op_ld16s_i32, { "r", "r" } },
+    { INDEX_op_ld_i32, { "r", "r" } },
+    { INDEX_op_st8_i32, { "rZ", "r" } },
+    { INDEX_op_st16_i32, { "rZ", "r" } },
+    { INDEX_op_st_i32, { "rZ", "r" } },
+
+    { INDEX_op_add_i32, { "r", "rZ", "rJ" } },
+    { INDEX_op_mul_i32, { "r", "rZ", "rZ" } },
+    { INDEX_op_muls2_i32, { "r", "r", "rZ", "rZ" } },
+    { INDEX_op_mulu2_i32, { "r", "r", "rZ", "rZ" } },
+    { INDEX_op_mulsh_i32, { "r", "rZ", "rZ" } },
+    { INDEX_op_muluh_i32, { "r", "rZ", "rZ" } },
+    { INDEX_op_div_i32, { "r", "rZ", "rZ" } },
+    { INDEX_op_divu_i32, { "r", "rZ", "rZ" } },
+    { INDEX_op_rem_i32, { "r", "rZ", "rZ" } },
+    { INDEX_op_remu_i32, { "r", "rZ", "rZ" } },
+    { INDEX_op_sub_i32, { "r", "rZ", "rN" } },
+
+    { INDEX_op_and_i32, { "r", "rZ", "rIK" } },
+    { INDEX_op_nor_i32, { "r", "rZ", "rZ" } },
+    { INDEX_op_not_i32, { "r", "rZ" } },
+    { INDEX_op_or_i32, { "r", "rZ", "rIZ" } },
+    { INDEX_op_xor_i32, { "r", "rZ", "rIZ" } },
+
+    { INDEX_op_shl_i32, { "r", "rZ", "ri" } },
+    { INDEX_op_shr_i32, { "r", "rZ", "ri" } },
+    { INDEX_op_sar_i32, { "r", "rZ", "ri" } },
+    { INDEX_op_rotr_i32, { "r", "rZ", "ri" } },
+    { INDEX_op_rotl_i32, { "r", "rZ", "ri" } },
+
+    { INDEX_op_bswap16_i32, { "r", "r" } },
+    { INDEX_op_bswap32_i32, { "r", "r" } },
+
+    { INDEX_op_ext8s_i32, { "r", "rZ" } },
+    { INDEX_op_ext16s_i32, { "r", "rZ" } },
+
+    { INDEX_op_deposit_i32, { "r", "0", "rZ" } },
+
+    { INDEX_op_brcond_i32, { "rZ", "rZ" } },
+    { INDEX_op_movcond_i32, { "r", "rZ", "rZ", "rZ", "0" } },
+    { INDEX_op_setcond_i32, { "r", "rZ", "rZ" } },
+    { INDEX_op_setcond2_i32, { "r", "rZ", "rZ", "rZ", "rZ" } },
+
+    { INDEX_op_add2_i32, { "r", "r", "rZ", "rZ", "rN", "rN" } },
+    { INDEX_op_sub2_i32, { "r", "r", "rZ", "rZ", "rN", "rN" } },
+    { INDEX_op_brcond2_i32, { "rZ", "rZ", "rZ", "rZ" } },
+
+#if TARGET_LONG_BITS == 32
+    { INDEX_op_qemu_ld_i32, { "L", "lZ" } },
+    { INDEX_op_qemu_st_i32, { "SZ", "SZ" } },
+    { INDEX_op_qemu_ld_i64, { "L", "L", "lZ" } },
+    { INDEX_op_qemu_st_i64, { "SZ", "SZ", "SZ" } },
+#else
+    { INDEX_op_qemu_ld_i32, { "L", "lZ", "lZ" } },
+    { INDEX_op_qemu_st_i32, { "SZ", "SZ", "SZ" } },
+    { INDEX_op_qemu_ld_i64, { "L", "L", "lZ", "lZ" } },
+    { INDEX_op_qemu_st_i64, { "SZ", "SZ", "SZ", "SZ" } },
+#endif
+    { -1 },
+};
+
+static int tcg_target_callee_save_regs[] = {
+    TCG_REG_S0,       /* used for the global env (TCG_AREG0) */
+    TCG_REG_S1,
+    TCG_REG_S2,
+    TCG_REG_S3,
+    TCG_REG_S4,
+    TCG_REG_S5,
+    TCG_REG_S6,
+    TCG_REG_S7,
+    TCG_REG_S8,
+    TCG_REG_RA,       /* should be last for ABI compliance */
+};
+
+/* The Linux kernel doesn't provide any information about the available
+   instruction set. Probe it using a signal handler. */
+
+#include <signal.h>
+
+#ifndef use_movnz_instructions
+bool use_movnz_instructions = false;
+#endif
+
+#ifndef use_mips32_instructions
+bool use_mips32_instructions = false;
+#endif
+
+#ifndef use_mips32r2_instructions
+bool use_mips32r2_instructions = false;
+#endif
+
+static volatile sig_atomic_t got_sigill;
+
+static void sigill_handler(int signo, siginfo_t *si, void *data)
+{
+    /* Skip the faulty instruction */
+    ucontext_t *uc = (ucontext_t *)data;
+    uc->uc_mcontext.pc += 4;
+
+    got_sigill = 1;
+}
+
+static void tcg_target_detect_isa(void)
+{
+    struct sigaction sa_old, sa_new;
+
+    memset(&sa_new, 0, sizeof(sa_new));
+    sa_new.sa_flags = SA_SIGINFO;
+    sa_new.sa_sigaction = sigill_handler;
+    sigaction(SIGILL, &sa_new, &sa_old);
+
+    /* Probe for movn/movz, necessary to implement movcond. */
+#ifndef use_movnz_instructions
+    got_sigill = 0;
+    asm volatile(".set push\n"
+                 ".set mips32\n"
+                 "movn $zero, $zero, $zero\n"
+                 "movz $zero, $zero, $zero\n"
+                 ".set pop\n"
+                 : : : );
+    use_movnz_instructions = !got_sigill;
+#endif
+
+    /* Probe for MIPS32 instructions. As no subsetting is allowed
+       by the specification, it is only necessary to probe for one
+       of the instructions. */
+#ifndef use_mips32_instructions
+    got_sigill = 0;
+    asm volatile(".set push\n"
+                 ".set mips32\n"
+                 "mul $zero, $zero\n"
+                 ".set pop\n"
+                 : : : );
+    use_mips32_instructions = !got_sigill;
+#endif
+
+    /* Probe for MIPS32r2 instructions if MIPS32 instructions are
+       available. As no subsetting is allowed by the specification,
+       it is only necessary to probe for one of the instructions. */
+#ifndef use_mips32r2_instructions
+    if (use_mips32_instructions) {
+        got_sigill = 0;
+        asm volatile(".set push\n"
+                     ".set mips32r2\n"
+                     "seb $zero, $zero\n"
+                     ".set pop\n"
+                     : : : );
+        use_mips32r2_instructions = !got_sigill;
+    }
+#endif
+
+    sigaction(SIGILL, &sa_old, NULL);
+}
+
+/* Generate global QEMU prologue and epilogue code */
+static void tcg_target_qemu_prologue(TCGContext *s)
+{
+    int i, frame_size;
+
+    /* reserve some stack space, also for TCG temps. */
+    frame_size = ARRAY_SIZE(tcg_target_callee_save_regs) * 4
+                 + TCG_STATIC_CALL_ARGS_SIZE
+                 + CPU_TEMP_BUF_NLONGS * sizeof(long);
+    frame_size = (frame_size + TCG_TARGET_STACK_ALIGN - 1) &
+                 ~(TCG_TARGET_STACK_ALIGN - 1);
+    tcg_set_frame(s, TCG_REG_SP, ARRAY_SIZE(tcg_target_callee_save_regs) * 4
+                  + TCG_STATIC_CALL_ARGS_SIZE,
+                  CPU_TEMP_BUF_NLONGS * sizeof(long));
+
+    /* TB prologue */
+    tcg_out_addi(s, TCG_REG_SP, -frame_size);
+    for(i = 0 ; i < ARRAY_SIZE(tcg_target_callee_save_regs) ; i++) {
+        tcg_out_st(s, TCG_TYPE_I32, tcg_target_callee_save_regs[i],
+                   TCG_REG_SP, TCG_STATIC_CALL_ARGS_SIZE + i * 4);
+    }
+
+    /* Call generated code */
+    tcg_out_opc_reg(s, OPC_JR, 0, tcg_target_call_iarg_regs[1], 0);
+    tcg_out_mov(s, TCG_TYPE_PTR, TCG_AREG0, tcg_target_call_iarg_regs[0]);
+    tb_ret_addr = s->code_ptr;
+
+    /* TB epilogue */
+    for(i = 0 ; i < ARRAY_SIZE(tcg_target_callee_save_regs) ; i++) {
+        tcg_out_ld(s, TCG_TYPE_I32, tcg_target_callee_save_regs[i],
+                   TCG_REG_SP, TCG_STATIC_CALL_ARGS_SIZE + i * 4);
+    }
+
+    tcg_out_opc_reg(s, OPC_JR, 0, TCG_REG_RA, 0);
+    tcg_out_addi(s, TCG_REG_SP, frame_size);
+}
+
+static void tcg_target_init(TCGContext *s)
+{
+    tcg_target_detect_isa();
+    tcg_regset_set(tcg_target_available_regs[TCG_TYPE_I32], 0xffffffff);
+    tcg_regset_set(tcg_target_call_clobber_regs,
+                   (1 << TCG_REG_V0) |
+                   (1 << TCG_REG_V1) |
+                   (1 << TCG_REG_A0) |
+                   (1 << TCG_REG_A1) |
+                   (1 << TCG_REG_A2) |
+                   (1 << TCG_REG_A3) |
+                   (1 << TCG_REG_T0) |
+                   (1 << TCG_REG_T1) |
+                   (1 << TCG_REG_T2) |
+                   (1 << TCG_REG_T3) |
+                   (1 << TCG_REG_T4) |
+                   (1 << TCG_REG_T5) |
+                   (1 << TCG_REG_T6) |
+                   (1 << TCG_REG_T7) |
+                   (1 << TCG_REG_T8) |
+                   (1 << TCG_REG_T9));
+
+    tcg_regset_clear(s->reserved_regs);
+    tcg_regset_set_reg(s->reserved_regs, TCG_REG_ZERO); /* zero register */
+    tcg_regset_set_reg(s->reserved_regs, TCG_REG_K0);   /* kernel use only */
+    tcg_regset_set_reg(s->reserved_regs, TCG_REG_K1);   /* kernel use only */
+    tcg_regset_set_reg(s->reserved_regs, TCG_TMP0);     /* internal use */
+    tcg_regset_set_reg(s->reserved_regs, TCG_TMP1);     /* internal use */
+    tcg_regset_set_reg(s->reserved_regs, TCG_REG_RA);   /* return address */
+    tcg_regset_set_reg(s->reserved_regs, TCG_REG_SP);   /* stack pointer */
+    tcg_regset_set_reg(s->reserved_regs, TCG_REG_GP);   /* global pointer */
+
+    tcg_add_target_add_op_defs(mips_op_defs);
+}
+
+void tb_set_jmp_target1(uintptr_t jmp_addr, uintptr_t addr)
+{
+    uint32_t *ptr = (uint32_t *)jmp_addr;
+    *ptr = deposit32(*ptr, 0, 26, addr >> 2);
+    flush_icache_range(jmp_addr, jmp_addr + 4);
+}
diff --git a/tcg/mips/tcg-target.h b/tcg/mips/tcg-target.h
new file mode 100644
index 00000000..f5ba52ca
--- /dev/null
+++ b/tcg/mips/tcg-target.h
@@ -0,0 +1,138 @@
+/*
+ * Tiny Code Generator for QEMU
+ *
+ * Copyright (c) 2008-2009 Arnaud Patard <arnaud.patard@rtp-net.org>
+ * Copyright (c) 2009 Aurelien Jarno <aurelien@aurel32.net>
+ * Based on i386/tcg-target.c - Copyright (c) 2008 Fabrice Bellard
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (the "Software"), to deal
+ * in the Software without restriction, including without limitation the rights
+ * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+ * copies of the Software, and to permit persons to whom the Software is
+ * furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+ * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+ * THE SOFTWARE.
+ */
+#ifndef TCG_TARGET_MIPS 
+#define TCG_TARGET_MIPS 1
+
+#define TCG_TARGET_INSN_UNIT_SIZE 4
+#define TCG_TARGET_TLB_DISPLACEMENT_BITS 16
+#define TCG_TARGET_NB_REGS 32
+
+typedef enum {
+    TCG_REG_ZERO = 0,
+    TCG_REG_AT,
+    TCG_REG_V0,
+    TCG_REG_V1,
+    TCG_REG_A0,
+    TCG_REG_A1,
+    TCG_REG_A2,
+    TCG_REG_A3,
+    TCG_REG_T0,
+    TCG_REG_T1,
+    TCG_REG_T2,
+    TCG_REG_T3,
+    TCG_REG_T4,
+    TCG_REG_T5,
+    TCG_REG_T6,
+    TCG_REG_T7,
+    TCG_REG_S0,
+    TCG_REG_S1,
+    TCG_REG_S2,
+    TCG_REG_S3,
+    TCG_REG_S4,
+    TCG_REG_S5,
+    TCG_REG_S6,
+    TCG_REG_S7,
+    TCG_REG_T8,
+    TCG_REG_T9,
+    TCG_REG_K0,
+    TCG_REG_K1,
+    TCG_REG_GP,
+    TCG_REG_SP,
+    TCG_REG_S8,
+    TCG_REG_RA,
+
+    TCG_REG_CALL_STACK = TCG_REG_SP,
+    TCG_AREG0 = TCG_REG_S0,
+} TCGReg;
+
+/* used for function call generation */
+#define TCG_TARGET_STACK_ALIGN 8
+#define TCG_TARGET_CALL_STACK_OFFSET 16
+#define TCG_TARGET_CALL_ALIGN_ARGS 1
+
+/* MOVN/MOVZ instructions detection */
+#if (defined(__mips_isa_rev) && (__mips_isa_rev >= 1)) || \
+    defined(_MIPS_ARCH_LOONGSON2E) || defined(_MIPS_ARCH_LOONGSON2F) || \
+    defined(_MIPS_ARCH_MIPS4)
+#define use_movnz_instructions  1
+#else
+extern bool use_movnz_instructions;
+#endif
+
+/* MIPS32 instruction set detection */
+#if defined(__mips_isa_rev) && (__mips_isa_rev >= 1)
+#define use_mips32_instructions  1
+#else
+extern bool use_mips32_instructions;
+#endif
+
+/* MIPS32R2 instruction set detection */
+#if defined(__mips_isa_rev) && (__mips_isa_rev >= 2)
+#define use_mips32r2_instructions  1
+#else
+extern bool use_mips32r2_instructions;
+#endif
+
+/* optional instructions */
+#define TCG_TARGET_HAS_div_i32          1
+#define TCG_TARGET_HAS_rem_i32          1
+#define TCG_TARGET_HAS_not_i32          1
+#define TCG_TARGET_HAS_nor_i32          1
+#define TCG_TARGET_HAS_andc_i32         0
+#define TCG_TARGET_HAS_orc_i32          0
+#define TCG_TARGET_HAS_eqv_i32          0
+#define TCG_TARGET_HAS_nand_i32         0
+#define TCG_TARGET_HAS_mulu2_i32        1
+#define TCG_TARGET_HAS_muls2_i32        1
+#define TCG_TARGET_HAS_muluh_i32        1
+#define TCG_TARGET_HAS_mulsh_i32        1
+
+/* optional instructions detected at runtime */
+#define TCG_TARGET_HAS_movcond_i32      use_movnz_instructions
+#define TCG_TARGET_HAS_bswap16_i32      use_mips32r2_instructions
+#define TCG_TARGET_HAS_bswap32_i32      use_mips32r2_instructions
+#define TCG_TARGET_HAS_deposit_i32      use_mips32r2_instructions
+#define TCG_TARGET_HAS_ext8s_i32        use_mips32r2_instructions
+#define TCG_TARGET_HAS_ext16s_i32       use_mips32r2_instructions
+#define TCG_TARGET_HAS_rot_i32          use_mips32r2_instructions
+
+/* optional instructions automatically implemented */
+#define TCG_TARGET_HAS_neg_i32          0 /* sub  rd, zero, rt   */
+#define TCG_TARGET_HAS_ext8u_i32        0 /* andi rt, rs, 0xff   */
+#define TCG_TARGET_HAS_ext16u_i32       0 /* andi rt, rs, 0xffff */
+
+#ifdef __OpenBSD__
+#include <machine/sysarch.h>
+#else
+#include <sys/cachectl.h>
+#endif
+
+static inline void flush_icache_range(uintptr_t start, uintptr_t stop)
+{
+    cacheflush ((void *)start, stop-start, ICACHE);
+}
+
+#endif
diff --git a/tcg/optimize.c b/tcg/optimize.c
new file mode 100644
index 00000000..18283cfd
--- /dev/null
+++ b/tcg/optimize.c
@@ -0,0 +1,1330 @@
+/*
+ * Optimizations for Tiny Code Generator for QEMU
+ *
+ * Copyright (c) 2010 Samsung Electronics.
+ * Contributed by Kirill Batuzov <batuzovk@ispras.ru>
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (the "Software"), to deal
+ * in the Software without restriction, including without limitation the rights
+ * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+ * copies of the Software, and to permit persons to whom the Software is
+ * furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+ * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+ * THE SOFTWARE.
+ */
+
+#include "config.h"
+
+#include <stdlib.h>
+#include <stdio.h>
+
+#include "qemu-common.h"
+#include "tcg-op.h"
+
+#define CASE_OP_32_64(x)                        \
+        glue(glue(case INDEX_op_, x), _i32):    \
+        glue(glue(case INDEX_op_, x), _i64)
+
+typedef enum {
+    TCG_TEMP_UNDEF = 0,
+    TCG_TEMP_CONST,
+    TCG_TEMP_COPY,
+} tcg_temp_state;
+
+struct tcg_temp_info {
+    tcg_temp_state state;
+    uint16_t prev_copy;
+    uint16_t next_copy;
+    tcg_target_ulong val;
+    tcg_target_ulong mask;
+};
+
+static struct tcg_temp_info temps[TCG_MAX_TEMPS];
+
+/* Reset TEMP's state to TCG_TEMP_UNDEF.  If TEMP only had one copy, remove
+   the copy flag from the left temp.  */
+static void reset_temp(TCGArg temp)
+{
+    if (temps[temp].state == TCG_TEMP_COPY) {
+        if (temps[temp].prev_copy == temps[temp].next_copy) {
+            temps[temps[temp].next_copy].state = TCG_TEMP_UNDEF;
+        } else {
+            temps[temps[temp].next_copy].prev_copy = temps[temp].prev_copy;
+            temps[temps[temp].prev_copy].next_copy = temps[temp].next_copy;
+        }
+    }
+    temps[temp].state = TCG_TEMP_UNDEF;
+    temps[temp].mask = -1;
+}
+
+static TCGOp *insert_op_before(TCGContext *s, TCGOp *old_op,
+                                TCGOpcode opc, int nargs)
+{
+    int oi = s->gen_next_op_idx;
+    int pi = s->gen_next_parm_idx;
+    int prev = old_op->prev;
+    int next = old_op - s->gen_op_buf;
+    TCGOp *new_op;
+
+    tcg_debug_assert(oi < OPC_BUF_SIZE);
+    tcg_debug_assert(pi + nargs <= OPPARAM_BUF_SIZE);
+    s->gen_next_op_idx = oi + 1;
+    s->gen_next_parm_idx = pi + nargs;
+
+    new_op = &s->gen_op_buf[oi];
+    *new_op = (TCGOp){
+        .opc = opc,
+        .args = pi,
+        .prev = prev,
+        .next = next
+    };
+    if (prev >= 0) {
+        s->gen_op_buf[prev].next = oi;
+    } else {
+        s->gen_first_op_idx = oi;
+    }
+    old_op->prev = oi;
+
+    return new_op;
+}
+
+/* Reset all temporaries, given that there are NB_TEMPS of them.  */
+static void reset_all_temps(int nb_temps)
+{
+    int i;
+    for (i = 0; i < nb_temps; i++) {
+        temps[i].state = TCG_TEMP_UNDEF;
+        temps[i].mask = -1;
+    }
+}
+
+static int op_bits(TCGOpcode op)
+{
+    const TCGOpDef *def = &tcg_op_defs[op];
+    return def->flags & TCG_OPF_64BIT ? 64 : 32;
+}
+
+static TCGOpcode op_to_mov(TCGOpcode op)
+{
+    switch (op_bits(op)) {
+    case 32:
+        return INDEX_op_mov_i32;
+    case 64:
+        return INDEX_op_mov_i64;
+    default:
+        fprintf(stderr, "op_to_mov: unexpected return value of "
+                "function op_bits.\n");
+        tcg_abort();
+    }
+}
+
+static TCGOpcode op_to_movi(TCGOpcode op)
+{
+    switch (op_bits(op)) {
+    case 32:
+        return INDEX_op_movi_i32;
+    case 64:
+        return INDEX_op_movi_i64;
+    default:
+        fprintf(stderr, "op_to_movi: unexpected return value of "
+                "function op_bits.\n");
+        tcg_abort();
+    }
+}
+
+static TCGArg find_better_copy(TCGContext *s, TCGArg temp)
+{
+    TCGArg i;
+
+    /* If this is already a global, we can't do better. */
+    if (temp < s->nb_globals) {
+        return temp;
+    }
+
+    /* Search for a global first. */
+    for (i = temps[temp].next_copy ; i != temp ; i = temps[i].next_copy) {
+        if (i < s->nb_globals) {
+            return i;
+        }
+    }
+
+    /* If it is a temp, search for a temp local. */
+    if (!s->temps[temp].temp_local) {
+        for (i = temps[temp].next_copy ; i != temp ; i = temps[i].next_copy) {
+            if (s->temps[i].temp_local) {
+                return i;
+            }
+        }
+    }
+
+    /* Failure to find a better representation, return the same temp. */
+    return temp;
+}
+
+static bool temps_are_copies(TCGArg arg1, TCGArg arg2)
+{
+    TCGArg i;
+
+    if (arg1 == arg2) {
+        return true;
+    }
+
+    if (temps[arg1].state != TCG_TEMP_COPY
+        || temps[arg2].state != TCG_TEMP_COPY) {
+        return false;
+    }
+
+    for (i = temps[arg1].next_copy ; i != arg1 ; i = temps[i].next_copy) {
+        if (i == arg2) {
+            return true;
+        }
+    }
+
+    return false;
+}
+
+static void tcg_opt_gen_movi(TCGContext *s, TCGOp *op, TCGArg *args,
+                             TCGArg dst, TCGArg val)
+{
+    TCGOpcode new_op = op_to_movi(op->opc);
+    tcg_target_ulong mask;
+
+    op->opc = new_op;
+
+    reset_temp(dst);
+    temps[dst].state = TCG_TEMP_CONST;
+    temps[dst].val = val;
+    mask = val;
+    if (TCG_TARGET_REG_BITS > 32 && new_op == INDEX_op_movi_i32) {
+        /* High bits of the destination are now garbage.  */
+        mask |= ~0xffffffffull;
+    }
+    temps[dst].mask = mask;
+
+    args[0] = dst;
+    args[1] = val;
+}
+
+static void tcg_opt_gen_mov(TCGContext *s, TCGOp *op, TCGArg *args,
+                            TCGArg dst, TCGArg src)
+{
+    if (temps_are_copies(dst, src)) {
+        tcg_op_remove(s, op);
+        return;
+    }
+
+    if (temps[src].state == TCG_TEMP_CONST) {
+        tcg_opt_gen_movi(s, op, args, dst, temps[src].val);
+        return;
+    }
+
+    TCGOpcode new_op = op_to_mov(op->opc);
+    tcg_target_ulong mask;
+
+    op->opc = new_op;
+
+    reset_temp(dst);
+    mask = temps[src].mask;
+    if (TCG_TARGET_REG_BITS > 32 && new_op == INDEX_op_mov_i32) {
+        /* High bits of the destination are now garbage.  */
+        mask |= ~0xffffffffull;
+    }
+    temps[dst].mask = mask;
+
+    assert(temps[src].state != TCG_TEMP_CONST);
+
+    if (s->temps[src].type == s->temps[dst].type) {
+        if (temps[src].state != TCG_TEMP_COPY) {
+            temps[src].state = TCG_TEMP_COPY;
+            temps[src].next_copy = src;
+            temps[src].prev_copy = src;
+        }
+        temps[dst].state = TCG_TEMP_COPY;
+        temps[dst].next_copy = temps[src].next_copy;
+        temps[dst].prev_copy = src;
+        temps[temps[dst].next_copy].prev_copy = dst;
+        temps[src].next_copy = dst;
+    }
+
+    args[0] = dst;
+    args[1] = src;
+}
+
+static TCGArg do_constant_folding_2(TCGOpcode op, TCGArg x, TCGArg y)
+{
+    uint64_t l64, h64;
+
+    switch (op) {
+    CASE_OP_32_64(add):
+        return x + y;
+
+    CASE_OP_32_64(sub):
+        return x - y;
+
+    CASE_OP_32_64(mul):
+        return x * y;
+
+    CASE_OP_32_64(and):
+        return x & y;
+
+    CASE_OP_32_64(or):
+        return x | y;
+
+    CASE_OP_32_64(xor):
+        return x ^ y;
+
+    case INDEX_op_shl_i32:
+        return (uint32_t)x << (y & 31);
+
+    case INDEX_op_shl_i64:
+        return (uint64_t)x << (y & 63);
+
+    case INDEX_op_shr_i32:
+        return (uint32_t)x >> (y & 31);
+
+    case INDEX_op_trunc_shr_i32:
+    case INDEX_op_shr_i64:
+        return (uint64_t)x >> (y & 63);
+
+    case INDEX_op_sar_i32:
+        return (int32_t)x >> (y & 31);
+
+    case INDEX_op_sar_i64:
+        return (int64_t)x >> (y & 63);
+
+    case INDEX_op_rotr_i32:
+        return ror32(x, y & 31);
+
+    case INDEX_op_rotr_i64:
+        return ror64(x, y & 63);
+
+    case INDEX_op_rotl_i32:
+        return rol32(x, y & 31);
+
+    case INDEX_op_rotl_i64:
+        return rol64(x, y & 63);
+
+    CASE_OP_32_64(not):
+        return ~x;
+
+    CASE_OP_32_64(neg):
+        return -x;
+
+    CASE_OP_32_64(andc):
+        return x & ~y;
+
+    CASE_OP_32_64(orc):
+        return x | ~y;
+
+    CASE_OP_32_64(eqv):
+        return ~(x ^ y);
+
+    CASE_OP_32_64(nand):
+        return ~(x & y);
+
+    CASE_OP_32_64(nor):
+        return ~(x | y);
+
+    CASE_OP_32_64(ext8s):
+        return (int8_t)x;
+
+    CASE_OP_32_64(ext16s):
+        return (int16_t)x;
+
+    CASE_OP_32_64(ext8u):
+        return (uint8_t)x;
+
+    CASE_OP_32_64(ext16u):
+        return (uint16_t)x;
+
+    case INDEX_op_ext32s_i64:
+        return (int32_t)x;
+
+    case INDEX_op_ext32u_i64:
+        return (uint32_t)x;
+
+    case INDEX_op_muluh_i32:
+        return ((uint64_t)(uint32_t)x * (uint32_t)y) >> 32;
+    case INDEX_op_mulsh_i32:
+        return ((int64_t)(int32_t)x * (int32_t)y) >> 32;
+
+    case INDEX_op_muluh_i64:
+        mulu64(&l64, &h64, x, y);
+        return h64;
+    case INDEX_op_mulsh_i64:
+        muls64(&l64, &h64, x, y);
+        return h64;
+
+    case INDEX_op_div_i32:
+        /* Avoid crashing on divide by zero, otherwise undefined.  */
+        return (int32_t)x / ((int32_t)y ? : 1);
+    case INDEX_op_divu_i32:
+        return (uint32_t)x / ((uint32_t)y ? : 1);
+    case INDEX_op_div_i64:
+        return (int64_t)x / ((int64_t)y ? : 1);
+    case INDEX_op_divu_i64:
+        return (uint64_t)x / ((uint64_t)y ? : 1);
+
+    case INDEX_op_rem_i32:
+        return (int32_t)x % ((int32_t)y ? : 1);
+    case INDEX_op_remu_i32:
+        return (uint32_t)x % ((uint32_t)y ? : 1);
+    case INDEX_op_rem_i64:
+        return (int64_t)x % ((int64_t)y ? : 1);
+    case INDEX_op_remu_i64:
+        return (uint64_t)x % ((uint64_t)y ? : 1);
+
+    default:
+        fprintf(stderr,
+                "Unrecognized operation %d in do_constant_folding.\n", op);
+        tcg_abort();
+    }
+}
+
+static TCGArg do_constant_folding(TCGOpcode op, TCGArg x, TCGArg y)
+{
+    TCGArg res = do_constant_folding_2(op, x, y);
+    if (op_bits(op) == 32) {
+        res &= 0xffffffff;
+    }
+    return res;
+}
+
+static bool do_constant_folding_cond_32(uint32_t x, uint32_t y, TCGCond c)
+{
+    switch (c) {
+    case TCG_COND_EQ:
+        return x == y;
+    case TCG_COND_NE:
+        return x != y;
+    case TCG_COND_LT:
+        return (int32_t)x < (int32_t)y;
+    case TCG_COND_GE:
+        return (int32_t)x >= (int32_t)y;
+    case TCG_COND_LE:
+        return (int32_t)x <= (int32_t)y;
+    case TCG_COND_GT:
+        return (int32_t)x > (int32_t)y;
+    case TCG_COND_LTU:
+        return x < y;
+    case TCG_COND_GEU:
+        return x >= y;
+    case TCG_COND_LEU:
+        return x <= y;
+    case TCG_COND_GTU:
+        return x > y;
+    default:
+        tcg_abort();
+    }
+}
+
+static bool do_constant_folding_cond_64(uint64_t x, uint64_t y, TCGCond c)
+{
+    switch (c) {
+    case TCG_COND_EQ:
+        return x == y;
+    case TCG_COND_NE:
+        return x != y;
+    case TCG_COND_LT:
+        return (int64_t)x < (int64_t)y;
+    case TCG_COND_GE:
+        return (int64_t)x >= (int64_t)y;
+    case TCG_COND_LE:
+        return (int64_t)x <= (int64_t)y;
+    case TCG_COND_GT:
+        return (int64_t)x > (int64_t)y;
+    case TCG_COND_LTU:
+        return x < y;
+    case TCG_COND_GEU:
+        return x >= y;
+    case TCG_COND_LEU:
+        return x <= y;
+    case TCG_COND_GTU:
+        return x > y;
+    default:
+        tcg_abort();
+    }
+}
+
+static bool do_constant_folding_cond_eq(TCGCond c)
+{
+    switch (c) {
+    case TCG_COND_GT:
+    case TCG_COND_LTU:
+    case TCG_COND_LT:
+    case TCG_COND_GTU:
+    case TCG_COND_NE:
+        return 0;
+    case TCG_COND_GE:
+    case TCG_COND_GEU:
+    case TCG_COND_LE:
+    case TCG_COND_LEU:
+    case TCG_COND_EQ:
+        return 1;
+    default:
+        tcg_abort();
+    }
+}
+
+/* Return 2 if the condition can't be simplified, and the result
+   of the condition (0 or 1) if it can */
+static TCGArg do_constant_folding_cond(TCGOpcode op, TCGArg x,
+                                       TCGArg y, TCGCond c)
+{
+    if (temps[x].state == TCG_TEMP_CONST && temps[y].state == TCG_TEMP_CONST) {
+        switch (op_bits(op)) {
+        case 32:
+            return do_constant_folding_cond_32(temps[x].val, temps[y].val, c);
+        case 64:
+            return do_constant_folding_cond_64(temps[x].val, temps[y].val, c);
+        default:
+            tcg_abort();
+        }
+    } else if (temps_are_copies(x, y)) {
+        return do_constant_folding_cond_eq(c);
+    } else if (temps[y].state == TCG_TEMP_CONST && temps[y].val == 0) {
+        switch (c) {
+        case TCG_COND_LTU:
+            return 0;
+        case TCG_COND_GEU:
+            return 1;
+        default:
+            return 2;
+        }
+    } else {
+        return 2;
+    }
+}
+
+/* Return 2 if the condition can't be simplified, and the result
+   of the condition (0 or 1) if it can */
+static TCGArg do_constant_folding_cond2(TCGArg *p1, TCGArg *p2, TCGCond c)
+{
+    TCGArg al = p1[0], ah = p1[1];
+    TCGArg bl = p2[0], bh = p2[1];
+
+    if (temps[bl].state == TCG_TEMP_CONST
+        && temps[bh].state == TCG_TEMP_CONST) {
+        uint64_t b = ((uint64_t)temps[bh].val << 32) | (uint32_t)temps[bl].val;
+
+        if (temps[al].state == TCG_TEMP_CONST
+            && temps[ah].state == TCG_TEMP_CONST) {
+            uint64_t a;
+            a = ((uint64_t)temps[ah].val << 32) | (uint32_t)temps[al].val;
+            return do_constant_folding_cond_64(a, b, c);
+        }
+        if (b == 0) {
+            switch (c) {
+            case TCG_COND_LTU:
+                return 0;
+            case TCG_COND_GEU:
+                return 1;
+            default:
+                break;
+            }
+        }
+    }
+    if (temps_are_copies(al, bl) && temps_are_copies(ah, bh)) {
+        return do_constant_folding_cond_eq(c);
+    }
+    return 2;
+}
+
+static bool swap_commutative(TCGArg dest, TCGArg *p1, TCGArg *p2)
+{
+    TCGArg a1 = *p1, a2 = *p2;
+    int sum = 0;
+    sum += temps[a1].state == TCG_TEMP_CONST;
+    sum -= temps[a2].state == TCG_TEMP_CONST;
+
+    /* Prefer the constant in second argument, and then the form
+       op a, a, b, which is better handled on non-RISC hosts. */
+    if (sum > 0 || (sum == 0 && dest == a2)) {
+        *p1 = a2;
+        *p2 = a1;
+        return true;
+    }
+    return false;
+}
+
+static bool swap_commutative2(TCGArg *p1, TCGArg *p2)
+{
+    int sum = 0;
+    sum += temps[p1[0]].state == TCG_TEMP_CONST;
+    sum += temps[p1[1]].state == TCG_TEMP_CONST;
+    sum -= temps[p2[0]].state == TCG_TEMP_CONST;
+    sum -= temps[p2[1]].state == TCG_TEMP_CONST;
+    if (sum > 0) {
+        TCGArg t;
+        t = p1[0], p1[0] = p2[0], p2[0] = t;
+        t = p1[1], p1[1] = p2[1], p2[1] = t;
+        return true;
+    }
+    return false;
+}
+
+/* Propagate constants and copies, fold constant expressions. */
+void tcg_optimize(TCGContext *s)
+{
+    int oi, oi_next, nb_temps, nb_globals;
+
+    /* Array VALS has an element for each temp.
+       If this temp holds a constant then its value is kept in VALS' element.
+       If this temp is a copy of other ones then the other copies are
+       available through the doubly linked circular list. */
+
+    nb_temps = s->nb_temps;
+    nb_globals = s->nb_globals;
+    reset_all_temps(nb_temps);
+
+    for (oi = s->gen_first_op_idx; oi >= 0; oi = oi_next) {
+        tcg_target_ulong mask, partmask, affected;
+        int nb_oargs, nb_iargs, i;
+        TCGArg tmp;
+
+        TCGOp * const op = &s->gen_op_buf[oi];
+        TCGArg * const args = &s->gen_opparam_buf[op->args];
+        TCGOpcode opc = op->opc;
+        const TCGOpDef *def = &tcg_op_defs[opc];
+
+        oi_next = op->next;
+        if (opc == INDEX_op_call) {
+            nb_oargs = op->callo;
+            nb_iargs = op->calli;
+        } else {
+            nb_oargs = def->nb_oargs;
+            nb_iargs = def->nb_iargs;
+        }
+
+        /* Do copy propagation */
+        for (i = nb_oargs; i < nb_oargs + nb_iargs; i++) {
+            if (temps[args[i]].state == TCG_TEMP_COPY) {
+                args[i] = find_better_copy(s, args[i]);
+            }
+        }
+
+        /* For commutative operations make constant second argument */
+        switch (opc) {
+        CASE_OP_32_64(add):
+        CASE_OP_32_64(mul):
+        CASE_OP_32_64(and):
+        CASE_OP_32_64(or):
+        CASE_OP_32_64(xor):
+        CASE_OP_32_64(eqv):
+        CASE_OP_32_64(nand):
+        CASE_OP_32_64(nor):
+        CASE_OP_32_64(muluh):
+        CASE_OP_32_64(mulsh):
+            swap_commutative(args[0], &args[1], &args[2]);
+            break;
+        CASE_OP_32_64(brcond):
+            if (swap_commutative(-1, &args[0], &args[1])) {
+                args[2] = tcg_swap_cond(args[2]);
+            }
+            break;
+        CASE_OP_32_64(setcond):
+            if (swap_commutative(args[0], &args[1], &args[2])) {
+                args[3] = tcg_swap_cond(args[3]);
+            }
+            break;
+        CASE_OP_32_64(movcond):
+            if (swap_commutative(-1, &args[1], &args[2])) {
+                args[5] = tcg_swap_cond(args[5]);
+            }
+            /* For movcond, we canonicalize the "false" input reg to match
+               the destination reg so that the tcg backend can implement
+               a "move if true" operation.  */
+            if (swap_commutative(args[0], &args[4], &args[3])) {
+                args[5] = tcg_invert_cond(args[5]);
+            }
+            break;
+        CASE_OP_32_64(add2):
+            swap_commutative(args[0], &args[2], &args[4]);
+            swap_commutative(args[1], &args[3], &args[5]);
+            break;
+        CASE_OP_32_64(mulu2):
+        CASE_OP_32_64(muls2):
+            swap_commutative(args[0], &args[2], &args[3]);
+            break;
+        case INDEX_op_brcond2_i32:
+            if (swap_commutative2(&args[0], &args[2])) {
+                args[4] = tcg_swap_cond(args[4]);
+            }
+            break;
+        case INDEX_op_setcond2_i32:
+            if (swap_commutative2(&args[1], &args[3])) {
+                args[5] = tcg_swap_cond(args[5]);
+            }
+            break;
+        default:
+            break;
+        }
+
+        /* Simplify expressions for "shift/rot r, 0, a => movi r, 0",
+           and "sub r, 0, a => neg r, a" case.  */
+        switch (opc) {
+        CASE_OP_32_64(shl):
+        CASE_OP_32_64(shr):
+        CASE_OP_32_64(sar):
+        CASE_OP_32_64(rotl):
+        CASE_OP_32_64(rotr):
+            if (temps[args[1]].state == TCG_TEMP_CONST
+                && temps[args[1]].val == 0) {
+                tcg_opt_gen_movi(s, op, args, args[0], 0);
+                continue;
+            }
+            break;
+        CASE_OP_32_64(sub):
+            {
+                TCGOpcode neg_op;
+                bool have_neg;
+
+                if (temps[args[2]].state == TCG_TEMP_CONST) {
+                    /* Proceed with possible constant folding. */
+                    break;
+                }
+                if (opc == INDEX_op_sub_i32) {
+                    neg_op = INDEX_op_neg_i32;
+                    have_neg = TCG_TARGET_HAS_neg_i32;
+                } else {
+                    neg_op = INDEX_op_neg_i64;
+                    have_neg = TCG_TARGET_HAS_neg_i64;
+                }
+                if (!have_neg) {
+                    break;
+                }
+                if (temps[args[1]].state == TCG_TEMP_CONST
+                    && temps[args[1]].val == 0) {
+                    op->opc = neg_op;
+                    reset_temp(args[0]);
+                    args[1] = args[2];
+                    continue;
+                }
+            }
+            break;
+        CASE_OP_32_64(xor):
+        CASE_OP_32_64(nand):
+            if (temps[args[1]].state != TCG_TEMP_CONST
+                && temps[args[2]].state == TCG_TEMP_CONST
+                && temps[args[2]].val == -1) {
+                i = 1;
+                goto try_not;
+            }
+            break;
+        CASE_OP_32_64(nor):
+            if (temps[args[1]].state != TCG_TEMP_CONST
+                && temps[args[2]].state == TCG_TEMP_CONST
+                && temps[args[2]].val == 0) {
+                i = 1;
+                goto try_not;
+            }
+            break;
+        CASE_OP_32_64(andc):
+            if (temps[args[2]].state != TCG_TEMP_CONST
+                && temps[args[1]].state == TCG_TEMP_CONST
+                && temps[args[1]].val == -1) {
+                i = 2;
+                goto try_not;
+            }
+            break;
+        CASE_OP_32_64(orc):
+        CASE_OP_32_64(eqv):
+            if (temps[args[2]].state != TCG_TEMP_CONST
+                && temps[args[1]].state == TCG_TEMP_CONST
+                && temps[args[1]].val == 0) {
+                i = 2;
+                goto try_not;
+            }
+            break;
+        try_not:
+            {
+                TCGOpcode not_op;
+                bool have_not;
+
+                if (def->flags & TCG_OPF_64BIT) {
+                    not_op = INDEX_op_not_i64;
+                    have_not = TCG_TARGET_HAS_not_i64;
+                } else {
+                    not_op = INDEX_op_not_i32;
+                    have_not = TCG_TARGET_HAS_not_i32;
+                }
+                if (!have_not) {
+                    break;
+                }
+                op->opc = not_op;
+                reset_temp(args[0]);
+                args[1] = args[i];
+                continue;
+            }
+        default:
+            break;
+        }
+
+        /* Simplify expression for "op r, a, const => mov r, a" cases */
+        switch (opc) {
+        CASE_OP_32_64(add):
+        CASE_OP_32_64(sub):
+        CASE_OP_32_64(shl):
+        CASE_OP_32_64(shr):
+        CASE_OP_32_64(sar):
+        CASE_OP_32_64(rotl):
+        CASE_OP_32_64(rotr):
+        CASE_OP_32_64(or):
+        CASE_OP_32_64(xor):
+        CASE_OP_32_64(andc):
+            if (temps[args[1]].state != TCG_TEMP_CONST
+                && temps[args[2]].state == TCG_TEMP_CONST
+                && temps[args[2]].val == 0) {
+                tcg_opt_gen_mov(s, op, args, args[0], args[1]);
+                continue;
+            }
+            break;
+        CASE_OP_32_64(and):
+        CASE_OP_32_64(orc):
+        CASE_OP_32_64(eqv):
+            if (temps[args[1]].state != TCG_TEMP_CONST
+                && temps[args[2]].state == TCG_TEMP_CONST
+                && temps[args[2]].val == -1) {
+                tcg_opt_gen_mov(s, op, args, args[0], args[1]);
+                continue;
+            }
+            break;
+        default:
+            break;
+        }
+
+        /* Simplify using known-zero bits. Currently only ops with a single
+           output argument is supported. */
+        mask = -1;
+        affected = -1;
+        switch (opc) {
+        CASE_OP_32_64(ext8s):
+            if ((temps[args[1]].mask & 0x80) != 0) {
+                break;
+            }
+        CASE_OP_32_64(ext8u):
+            mask = 0xff;
+            goto and_const;
+        CASE_OP_32_64(ext16s):
+            if ((temps[args[1]].mask & 0x8000) != 0) {
+                break;
+            }
+        CASE_OP_32_64(ext16u):
+            mask = 0xffff;
+            goto and_const;
+        case INDEX_op_ext32s_i64:
+            if ((temps[args[1]].mask & 0x80000000) != 0) {
+                break;
+            }
+        case INDEX_op_ext32u_i64:
+            mask = 0xffffffffU;
+            goto and_const;
+
+        CASE_OP_32_64(and):
+            mask = temps[args[2]].mask;
+            if (temps[args[2]].state == TCG_TEMP_CONST) {
+        and_const:
+                affected = temps[args[1]].mask & ~mask;
+            }
+            mask = temps[args[1]].mask & mask;
+            break;
+
+        CASE_OP_32_64(andc):
+            /* Known-zeros does not imply known-ones.  Therefore unless
+               args[2] is constant, we can't infer anything from it.  */
+            if (temps[args[2]].state == TCG_TEMP_CONST) {
+                mask = ~temps[args[2]].mask;
+                goto and_const;
+            }
+            /* But we certainly know nothing outside args[1] may be set. */
+            mask = temps[args[1]].mask;
+            break;
+
+        case INDEX_op_sar_i32:
+            if (temps[args[2]].state == TCG_TEMP_CONST) {
+                tmp = temps[args[2]].val & 31;
+                mask = (int32_t)temps[args[1]].mask >> tmp;
+            }
+            break;
+        case INDEX_op_sar_i64:
+            if (temps[args[2]].state == TCG_TEMP_CONST) {
+                tmp = temps[args[2]].val & 63;
+                mask = (int64_t)temps[args[1]].mask >> tmp;
+            }
+            break;
+
+        case INDEX_op_shr_i32:
+            if (temps[args[2]].state == TCG_TEMP_CONST) {
+                tmp = temps[args[2]].val & 31;
+                mask = (uint32_t)temps[args[1]].mask >> tmp;
+            }
+            break;
+        case INDEX_op_shr_i64:
+            if (temps[args[2]].state == TCG_TEMP_CONST) {
+                tmp = temps[args[2]].val & 63;
+                mask = (uint64_t)temps[args[1]].mask >> tmp;
+            }
+            break;
+
+        case INDEX_op_trunc_shr_i32:
+            mask = (uint64_t)temps[args[1]].mask >> args[2];
+            break;
+
+        CASE_OP_32_64(shl):
+            if (temps[args[2]].state == TCG_TEMP_CONST) {
+                tmp = temps[args[2]].val & (TCG_TARGET_REG_BITS - 1);
+                mask = temps[args[1]].mask << tmp;
+            }
+            break;
+
+        CASE_OP_32_64(neg):
+            /* Set to 1 all bits to the left of the rightmost.  */
+            mask = -(temps[args[1]].mask & -temps[args[1]].mask);
+            break;
+
+        CASE_OP_32_64(deposit):
+            mask = deposit64(temps[args[1]].mask, args[3], args[4],
+                             temps[args[2]].mask);
+            break;
+
+        CASE_OP_32_64(or):
+        CASE_OP_32_64(xor):
+            mask = temps[args[1]].mask | temps[args[2]].mask;
+            break;
+
+        CASE_OP_32_64(setcond):
+        case INDEX_op_setcond2_i32:
+            mask = 1;
+            break;
+
+        CASE_OP_32_64(movcond):
+            mask = temps[args[3]].mask | temps[args[4]].mask;
+            break;
+
+        CASE_OP_32_64(ld8u):
+            mask = 0xff;
+            break;
+        CASE_OP_32_64(ld16u):
+            mask = 0xffff;
+            break;
+        case INDEX_op_ld32u_i64:
+            mask = 0xffffffffu;
+            break;
+
+        CASE_OP_32_64(qemu_ld):
+            {
+                TCGMemOpIdx oi = args[nb_oargs + nb_iargs];
+                TCGMemOp mop = get_memop(oi);
+                if (!(mop & MO_SIGN)) {
+                    mask = (2ULL << ((8 << (mop & MO_SIZE)) - 1)) - 1;
+                }
+            }
+            break;
+
+        default:
+            break;
+        }
+
+        /* 32-bit ops generate 32-bit results.  For the result is zero test
+           below, we can ignore high bits, but for further optimizations we
+           need to record that the high bits contain garbage.  */
+        partmask = mask;
+        if (!(def->flags & TCG_OPF_64BIT)) {
+            mask |= ~(tcg_target_ulong)0xffffffffu;
+            partmask &= 0xffffffffu;
+            affected &= 0xffffffffu;
+        }
+
+        if (partmask == 0) {
+            assert(nb_oargs == 1);
+            tcg_opt_gen_movi(s, op, args, args[0], 0);
+            continue;
+        }
+        if (affected == 0) {
+            assert(nb_oargs == 1);
+            tcg_opt_gen_mov(s, op, args, args[0], args[1]);
+            continue;
+        }
+
+        /* Simplify expression for "op r, a, 0 => movi r, 0" cases */
+        switch (opc) {
+        CASE_OP_32_64(and):
+        CASE_OP_32_64(mul):
+        CASE_OP_32_64(muluh):
+        CASE_OP_32_64(mulsh):
+            if ((temps[args[2]].state == TCG_TEMP_CONST
+                && temps[args[2]].val == 0)) {
+                tcg_opt_gen_movi(s, op, args, args[0], 0);
+                continue;
+            }
+            break;
+        default:
+            break;
+        }
+
+        /* Simplify expression for "op r, a, a => mov r, a" cases */
+        switch (opc) {
+        CASE_OP_32_64(or):
+        CASE_OP_32_64(and):
+            if (temps_are_copies(args[1], args[2])) {
+                tcg_opt_gen_mov(s, op, args, args[0], args[1]);
+                continue;
+            }
+            break;
+        default:
+            break;
+        }
+
+        /* Simplify expression for "op r, a, a => movi r, 0" cases */
+        switch (opc) {
+        CASE_OP_32_64(andc):
+        CASE_OP_32_64(sub):
+        CASE_OP_32_64(xor):
+            if (temps_are_copies(args[1], args[2])) {
+                tcg_opt_gen_movi(s, op, args, args[0], 0);
+                continue;
+            }
+            break;
+        default:
+            break;
+        }
+
+        /* Propagate constants through copy operations and do constant
+           folding.  Constants will be substituted to arguments by register
+           allocator where needed and possible.  Also detect copies. */
+        switch (opc) {
+        CASE_OP_32_64(mov):
+            tcg_opt_gen_mov(s, op, args, args[0], args[1]);
+            break;
+        CASE_OP_32_64(movi):
+            tcg_opt_gen_movi(s, op, args, args[0], args[1]);
+            break;
+
+        CASE_OP_32_64(not):
+        CASE_OP_32_64(neg):
+        CASE_OP_32_64(ext8s):
+        CASE_OP_32_64(ext8u):
+        CASE_OP_32_64(ext16s):
+        CASE_OP_32_64(ext16u):
+        case INDEX_op_ext32s_i64:
+        case INDEX_op_ext32u_i64:
+            if (temps[args[1]].state == TCG_TEMP_CONST) {
+                tmp = do_constant_folding(opc, temps[args[1]].val, 0);
+                tcg_opt_gen_movi(s, op, args, args[0], tmp);
+                break;
+            }
+            goto do_default;
+
+        case INDEX_op_trunc_shr_i32:
+            if (temps[args[1]].state == TCG_TEMP_CONST) {
+                tmp = do_constant_folding(opc, temps[args[1]].val, args[2]);
+                tcg_opt_gen_movi(s, op, args, args[0], tmp);
+                break;
+            }
+            goto do_default;
+
+        CASE_OP_32_64(add):
+        CASE_OP_32_64(sub):
+        CASE_OP_32_64(mul):
+        CASE_OP_32_64(or):
+        CASE_OP_32_64(and):
+        CASE_OP_32_64(xor):
+        CASE_OP_32_64(shl):
+        CASE_OP_32_64(shr):
+        CASE_OP_32_64(sar):
+        CASE_OP_32_64(rotl):
+        CASE_OP_32_64(rotr):
+        CASE_OP_32_64(andc):
+        CASE_OP_32_64(orc):
+        CASE_OP_32_64(eqv):
+        CASE_OP_32_64(nand):
+        CASE_OP_32_64(nor):
+        CASE_OP_32_64(muluh):
+        CASE_OP_32_64(mulsh):
+        CASE_OP_32_64(div):
+        CASE_OP_32_64(divu):
+        CASE_OP_32_64(rem):
+        CASE_OP_32_64(remu):
+            if (temps[args[1]].state == TCG_TEMP_CONST
+                && temps[args[2]].state == TCG_TEMP_CONST) {
+                tmp = do_constant_folding(opc, temps[args[1]].val,
+                                          temps[args[2]].val);
+                tcg_opt_gen_movi(s, op, args, args[0], tmp);
+                break;
+            }
+            goto do_default;
+
+        CASE_OP_32_64(deposit):
+            if (temps[args[1]].state == TCG_TEMP_CONST
+                && temps[args[2]].state == TCG_TEMP_CONST) {
+                tmp = deposit64(temps[args[1]].val, args[3], args[4],
+                                temps[args[2]].val);
+                tcg_opt_gen_movi(s, op, args, args[0], tmp);
+                break;
+            }
+            goto do_default;
+
+        CASE_OP_32_64(setcond):
+            tmp = do_constant_folding_cond(opc, args[1], args[2], args[3]);
+            if (tmp != 2) {
+                tcg_opt_gen_movi(s, op, args, args[0], tmp);
+                break;
+            }
+            goto do_default;
+
+        CASE_OP_32_64(brcond):
+            tmp = do_constant_folding_cond(opc, args[0], args[1], args[2]);
+            if (tmp != 2) {
+                if (tmp) {
+                    reset_all_temps(nb_temps);
+                    op->opc = INDEX_op_br;
+                    args[0] = args[3];
+                } else {
+                    tcg_op_remove(s, op);
+                }
+                break;
+            }
+            goto do_default;
+
+        CASE_OP_32_64(movcond):
+            tmp = do_constant_folding_cond(opc, args[1], args[2], args[5]);
+            if (tmp != 2) {
+                tcg_opt_gen_mov(s, op, args, args[0], args[4-tmp]);
+                break;
+            }
+            goto do_default;
+
+        case INDEX_op_add2_i32:
+        case INDEX_op_sub2_i32:
+            if (temps[args[2]].state == TCG_TEMP_CONST
+                && temps[args[3]].state == TCG_TEMP_CONST
+                && temps[args[4]].state == TCG_TEMP_CONST
+                && temps[args[5]].state == TCG_TEMP_CONST) {
+                uint32_t al = temps[args[2]].val;
+                uint32_t ah = temps[args[3]].val;
+                uint32_t bl = temps[args[4]].val;
+                uint32_t bh = temps[args[5]].val;
+                uint64_t a = ((uint64_t)ah << 32) | al;
+                uint64_t b = ((uint64_t)bh << 32) | bl;
+                TCGArg rl, rh;
+                TCGOp *op2 = insert_op_before(s, op, INDEX_op_movi_i32, 2);
+                TCGArg *args2 = &s->gen_opparam_buf[op2->args];
+
+                if (opc == INDEX_op_add2_i32) {
+                    a += b;
+                } else {
+                    a -= b;
+                }
+
+                rl = args[0];
+                rh = args[1];
+                tcg_opt_gen_movi(s, op, args, rl, (uint32_t)a);
+                tcg_opt_gen_movi(s, op2, args2, rh, (uint32_t)(a >> 32));
+
+                /* We've done all we need to do with the movi.  Skip it.  */
+                oi_next = op2->next;
+                break;
+            }
+            goto do_default;
+
+        case INDEX_op_mulu2_i32:
+            if (temps[args[2]].state == TCG_TEMP_CONST
+                && temps[args[3]].state == TCG_TEMP_CONST) {
+                uint32_t a = temps[args[2]].val;
+                uint32_t b = temps[args[3]].val;
+                uint64_t r = (uint64_t)a * b;
+                TCGArg rl, rh;
+                TCGOp *op2 = insert_op_before(s, op, INDEX_op_movi_i32, 2);
+                TCGArg *args2 = &s->gen_opparam_buf[op2->args];
+
+                rl = args[0];
+                rh = args[1];
+                tcg_opt_gen_movi(s, op, args, rl, (uint32_t)r);
+                tcg_opt_gen_movi(s, op2, args2, rh, (uint32_t)(r >> 32));
+
+                /* We've done all we need to do with the movi.  Skip it.  */
+                oi_next = op2->next;
+                break;
+            }
+            goto do_default;
+
+        case INDEX_op_brcond2_i32:
+            tmp = do_constant_folding_cond2(&args[0], &args[2], args[4]);
+            if (tmp != 2) {
+                if (tmp) {
+            do_brcond_true:
+                    reset_all_temps(nb_temps);
+                    op->opc = INDEX_op_br;
+                    args[0] = args[5];
+                } else {
+            do_brcond_false:
+                    tcg_op_remove(s, op);
+                }
+            } else if ((args[4] == TCG_COND_LT || args[4] == TCG_COND_GE)
+                       && temps[args[2]].state == TCG_TEMP_CONST
+                       && temps[args[3]].state == TCG_TEMP_CONST
+                       && temps[args[2]].val == 0
+                       && temps[args[3]].val == 0) {
+                /* Simplify LT/GE comparisons vs zero to a single compare
+                   vs the high word of the input.  */
+            do_brcond_high:
+                reset_all_temps(nb_temps);
+                op->opc = INDEX_op_brcond_i32;
+                args[0] = args[1];
+                args[1] = args[3];
+                args[2] = args[4];
+                args[3] = args[5];
+            } else if (args[4] == TCG_COND_EQ) {
+                /* Simplify EQ comparisons where one of the pairs
+                   can be simplified.  */
+                tmp = do_constant_folding_cond(INDEX_op_brcond_i32,
+                                               args[0], args[2], TCG_COND_EQ);
+                if (tmp == 0) {
+                    goto do_brcond_false;
+                } else if (tmp == 1) {
+                    goto do_brcond_high;
+                }
+                tmp = do_constant_folding_cond(INDEX_op_brcond_i32,
+                                               args[1], args[3], TCG_COND_EQ);
+                if (tmp == 0) {
+                    goto do_brcond_false;
+                } else if (tmp != 1) {
+                    goto do_default;
+                }
+            do_brcond_low:
+                reset_all_temps(nb_temps);
+                op->opc = INDEX_op_brcond_i32;
+                args[1] = args[2];
+                args[2] = args[4];
+                args[3] = args[5];
+            } else if (args[4] == TCG_COND_NE) {
+                /* Simplify NE comparisons where one of the pairs
+                   can be simplified.  */
+                tmp = do_constant_folding_cond(INDEX_op_brcond_i32,
+                                               args[0], args[2], TCG_COND_NE);
+                if (tmp == 0) {
+                    goto do_brcond_high;
+                } else if (tmp == 1) {
+                    goto do_brcond_true;
+                }
+                tmp = do_constant_folding_cond(INDEX_op_brcond_i32,
+                                               args[1], args[3], TCG_COND_NE);
+                if (tmp == 0) {
+                    goto do_brcond_low;
+                } else if (tmp == 1) {
+                    goto do_brcond_true;
+                }
+                goto do_default;
+            } else {
+                goto do_default;
+            }
+            break;
+
+        case INDEX_op_setcond2_i32:
+            tmp = do_constant_folding_cond2(&args[1], &args[3], args[5]);
+            if (tmp != 2) {
+            do_setcond_const:
+                tcg_opt_gen_movi(s, op, args, args[0], tmp);
+            } else if ((args[5] == TCG_COND_LT || args[5] == TCG_COND_GE)
+                       && temps[args[3]].state == TCG_TEMP_CONST
+                       && temps[args[4]].state == TCG_TEMP_CONST
+                       && temps[args[3]].val == 0
+                       && temps[args[4]].val == 0) {
+                /* Simplify LT/GE comparisons vs zero to a single compare
+                   vs the high word of the input.  */
+            do_setcond_high:
+                reset_temp(args[0]);
+                temps[args[0]].mask = 1;
+                op->opc = INDEX_op_setcond_i32;
+                args[1] = args[2];
+                args[2] = args[4];
+                args[3] = args[5];
+            } else if (args[5] == TCG_COND_EQ) {
+                /* Simplify EQ comparisons where one of the pairs
+                   can be simplified.  */
+                tmp = do_constant_folding_cond(INDEX_op_setcond_i32,
+                                               args[1], args[3], TCG_COND_EQ);
+                if (tmp == 0) {
+                    goto do_setcond_const;
+                } else if (tmp == 1) {
+                    goto do_setcond_high;
+                }
+                tmp = do_constant_folding_cond(INDEX_op_setcond_i32,
+                                               args[2], args[4], TCG_COND_EQ);
+                if (tmp == 0) {
+                    goto do_setcond_high;
+                } else if (tmp != 1) {
+                    goto do_default;
+                }
+            do_setcond_low:
+                reset_temp(args[0]);
+                temps[args[0]].mask = 1;
+                op->opc = INDEX_op_setcond_i32;
+                args[2] = args[3];
+                args[3] = args[5];
+            } else if (args[5] == TCG_COND_NE) {
+                /* Simplify NE comparisons where one of the pairs
+                   can be simplified.  */
+                tmp = do_constant_folding_cond(INDEX_op_setcond_i32,
+                                               args[1], args[3], TCG_COND_NE);
+                if (tmp == 0) {
+                    goto do_setcond_high;
+                } else if (tmp == 1) {
+                    goto do_setcond_const;
+                }
+                tmp = do_constant_folding_cond(INDEX_op_setcond_i32,
+                                               args[2], args[4], TCG_COND_NE);
+                if (tmp == 0) {
+                    goto do_setcond_low;
+                } else if (tmp == 1) {
+                    goto do_setcond_const;
+                }
+                goto do_default;
+            } else {
+                goto do_default;
+            }
+            break;
+
+        case INDEX_op_call:
+            if (!(args[nb_oargs + nb_iargs + 1]
+                  & (TCG_CALL_NO_READ_GLOBALS | TCG_CALL_NO_WRITE_GLOBALS))) {
+                for (i = 0; i < nb_globals; i++) {
+                    reset_temp(i);
+                }
+            }
+            goto do_reset_output;
+
+        default:
+        do_default:
+            /* Default case: we know nothing about operation (or were unable
+               to compute the operation result) so no propagation is done.
+               We trash everything if the operation is the end of a basic
+               block, otherwise we only trash the output args.  "mask" is
+               the non-zero bits mask for the first output arg.  */
+            if (def->flags & TCG_OPF_BB_END) {
+                reset_all_temps(nb_temps);
+            } else {
+        do_reset_output:
+                for (i = 0; i < nb_oargs; i++) {
+                    reset_temp(args[i]);
+                    /* Save the corresponding known-zero bits mask for the
+                       first output argument (only one supported so far). */
+                    if (i == 0) {
+                        temps[args[i]].mask = mask;
+                    }
+                }
+            }
+            break;
+        }
+    }
+}
diff --git a/tcg/ppc/tcg-target.c b/tcg/ppc/tcg-target.c
new file mode 100644
index 00000000..2b6eafa0
--- /dev/null
+++ b/tcg/ppc/tcg-target.c
@@ -0,0 +1,2722 @@
+/*
+ * Tiny Code Generator for QEMU
+ *
+ * Copyright (c) 2008 Fabrice Bellard
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (the "Software"), to deal
+ * in the Software without restriction, including without limitation the rights
+ * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+ * copies of the Software, and to permit persons to whom the Software is
+ * furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+ * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+ * THE SOFTWARE.
+ */
+
+#include "tcg-be-ldst.h"
+
+#if defined _CALL_DARWIN || defined __APPLE__
+#define TCG_TARGET_CALL_DARWIN
+#endif
+#ifdef _CALL_SYSV
+# define TCG_TARGET_CALL_ALIGN_ARGS   1
+#endif
+
+/* For some memory operations, we need a scratch that isn't R0.  For the AIX
+   calling convention, we can re-use the TOC register since we'll be reloading
+   it at every call.  Otherwise R12 will do nicely as neither a call-saved
+   register nor a parameter register.  */
+#ifdef _CALL_AIX
+# define TCG_REG_TMP1   TCG_REG_R2
+#else
+# define TCG_REG_TMP1   TCG_REG_R12
+#endif
+
+/* For the 64-bit target, we don't like the 5 insn sequence needed to build
+   full 64-bit addresses.  Better to have a base register to which we can
+   apply a 32-bit displacement.
+
+   There are generally three items of interest:
+   (1) helper functions in the main executable,
+   (2) TranslationBlock data structures,
+   (3) the return address in the epilogue.
+
+   For user-only, we USE_STATIC_CODE_GEN_BUFFER, so the code_gen_buffer
+   will be inside the main executable, and thus near enough to make a
+   pointer to the epilogue be within 2GB of all helper functions.
+
+   For softmmu, we'll let the kernel choose the address of code_gen_buffer,
+   and odds are it'll be somewhere close to the main malloc arena, and so
+   a pointer to the epilogue will be within 2GB of the TranslationBlocks.
+
+   For --enable-pie, everything will be kinda near everything else,
+   somewhere in high memory.
+
+   Thus we choose to keep the return address in a call-saved register.  */
+#define TCG_REG_RA     TCG_REG_R31
+#define USE_REG_RA     (TCG_TARGET_REG_BITS == 64)
+
+/* Shorthand for size of a pointer.  Avoid promotion to unsigned.  */
+#define SZP  ((int)sizeof(void *))
+
+/* Shorthand for size of a register.  */
+#define SZR  (TCG_TARGET_REG_BITS / 8)
+
+#define TCG_CT_CONST_S16  0x100
+#define TCG_CT_CONST_U16  0x200
+#define TCG_CT_CONST_S32  0x400
+#define TCG_CT_CONST_U32  0x800
+#define TCG_CT_CONST_ZERO 0x1000
+#define TCG_CT_CONST_MONE 0x2000
+
+static tcg_insn_unit *tb_ret_addr;
+
+#ifndef GUEST_BASE
+#define GUEST_BASE 0
+#endif
+
+#include "elf.h"
+static bool have_isa_2_06;
+#define HAVE_ISA_2_06  have_isa_2_06
+#define HAVE_ISEL      have_isa_2_06
+
+#ifdef CONFIG_USE_GUEST_BASE
+#define TCG_GUEST_BASE_REG 30
+#else
+#define TCG_GUEST_BASE_REG 0
+#endif
+
+#ifndef NDEBUG
+static const char * const tcg_target_reg_names[TCG_TARGET_NB_REGS] = {
+    "r0",
+    "r1",
+    "r2",
+    "r3",
+    "r4",
+    "r5",
+    "r6",
+    "r7",
+    "r8",
+    "r9",
+    "r10",
+    "r11",
+    "r12",
+    "r13",
+    "r14",
+    "r15",
+    "r16",
+    "r17",
+    "r18",
+    "r19",
+    "r20",
+    "r21",
+    "r22",
+    "r23",
+    "r24",
+    "r25",
+    "r26",
+    "r27",
+    "r28",
+    "r29",
+    "r30",
+    "r31"
+};
+#endif
+
+static const int tcg_target_reg_alloc_order[] = {
+    TCG_REG_R14,  /* call saved registers */
+    TCG_REG_R15,
+    TCG_REG_R16,
+    TCG_REG_R17,
+    TCG_REG_R18,
+    TCG_REG_R19,
+    TCG_REG_R20,
+    TCG_REG_R21,
+    TCG_REG_R22,
+    TCG_REG_R23,
+    TCG_REG_R24,
+    TCG_REG_R25,
+    TCG_REG_R26,
+    TCG_REG_R27,
+    TCG_REG_R28,
+    TCG_REG_R29,
+    TCG_REG_R30,
+    TCG_REG_R31,
+    TCG_REG_R12,  /* call clobbered, non-arguments */
+    TCG_REG_R11,
+    TCG_REG_R2,
+    TCG_REG_R13,
+    TCG_REG_R10,  /* call clobbered, arguments */
+    TCG_REG_R9,
+    TCG_REG_R8,
+    TCG_REG_R7,
+    TCG_REG_R6,
+    TCG_REG_R5,
+    TCG_REG_R4,
+    TCG_REG_R3,
+};
+
+static const int tcg_target_call_iarg_regs[] = {
+    TCG_REG_R3,
+    TCG_REG_R4,
+    TCG_REG_R5,
+    TCG_REG_R6,
+    TCG_REG_R7,
+    TCG_REG_R8,
+    TCG_REG_R9,
+    TCG_REG_R10
+};
+
+static const int tcg_target_call_oarg_regs[] = {
+    TCG_REG_R3,
+    TCG_REG_R4
+};
+
+static const int tcg_target_callee_save_regs[] = {
+#ifdef TCG_TARGET_CALL_DARWIN
+    TCG_REG_R11,
+#endif
+    TCG_REG_R14,
+    TCG_REG_R15,
+    TCG_REG_R16,
+    TCG_REG_R17,
+    TCG_REG_R18,
+    TCG_REG_R19,
+    TCG_REG_R20,
+    TCG_REG_R21,
+    TCG_REG_R22,
+    TCG_REG_R23,
+    TCG_REG_R24,
+    TCG_REG_R25,
+    TCG_REG_R26,
+    TCG_REG_R27, /* currently used for the global env */
+    TCG_REG_R28,
+    TCG_REG_R29,
+    TCG_REG_R30,
+    TCG_REG_R31
+};
+
+static inline bool in_range_b(tcg_target_long target)
+{
+    return target == sextract64(target, 0, 26);
+}
+
+static uint32_t reloc_pc24_val(tcg_insn_unit *pc, tcg_insn_unit *target)
+{
+    ptrdiff_t disp = tcg_ptr_byte_diff(target, pc);
+    assert(in_range_b(disp));
+    return disp & 0x3fffffc;
+}
+
+static void reloc_pc24(tcg_insn_unit *pc, tcg_insn_unit *target)
+{
+    *pc = (*pc & ~0x3fffffc) | reloc_pc24_val(pc, target);
+}
+
+static uint16_t reloc_pc14_val(tcg_insn_unit *pc, tcg_insn_unit *target)
+{
+    ptrdiff_t disp = tcg_ptr_byte_diff(target, pc);
+    assert(disp == (int16_t) disp);
+    return disp & 0xfffc;
+}
+
+static void reloc_pc14(tcg_insn_unit *pc, tcg_insn_unit *target)
+{
+    *pc = (*pc & ~0xfffc) | reloc_pc14_val(pc, target);
+}
+
+static inline void tcg_out_b_noaddr(TCGContext *s, int insn)
+{
+    unsigned retrans = *s->code_ptr & 0x3fffffc;
+    tcg_out32(s, insn | retrans);
+}
+
+static inline void tcg_out_bc_noaddr(TCGContext *s, int insn)
+{
+    unsigned retrans = *s->code_ptr & 0xfffc;
+    tcg_out32(s, insn | retrans);
+}
+
+static void patch_reloc(tcg_insn_unit *code_ptr, int type,
+                        intptr_t value, intptr_t addend)
+{
+    tcg_insn_unit *target = (tcg_insn_unit *)value;
+
+    assert(addend == 0);
+    switch (type) {
+    case R_PPC_REL14:
+        reloc_pc14(code_ptr, target);
+        break;
+    case R_PPC_REL24:
+        reloc_pc24(code_ptr, target);
+        break;
+    default:
+        tcg_abort();
+    }
+}
+
+/* parse target specific constraints */
+static int target_parse_constraint(TCGArgConstraint *ct, const char **pct_str)
+{
+    const char *ct_str;
+
+    ct_str = *pct_str;
+    switch (ct_str[0]) {
+    case 'A': case 'B': case 'C': case 'D':
+        ct->ct |= TCG_CT_REG;
+        tcg_regset_set_reg(ct->u.regs, 3 + ct_str[0] - 'A');
+        break;
+    case 'r':
+        ct->ct |= TCG_CT_REG;
+        tcg_regset_set32(ct->u.regs, 0, 0xffffffff);
+        break;
+    case 'L':                   /* qemu_ld constraint */
+        ct->ct |= TCG_CT_REG;
+        tcg_regset_set32(ct->u.regs, 0, 0xffffffff);
+        tcg_regset_reset_reg(ct->u.regs, TCG_REG_R3);
+#ifdef CONFIG_SOFTMMU
+        tcg_regset_reset_reg(ct->u.regs, TCG_REG_R4);
+        tcg_regset_reset_reg(ct->u.regs, TCG_REG_R5);
+#endif
+        break;
+    case 'S':                   /* qemu_st constraint */
+        ct->ct |= TCG_CT_REG;
+        tcg_regset_set32(ct->u.regs, 0, 0xffffffff);
+        tcg_regset_reset_reg(ct->u.regs, TCG_REG_R3);
+#ifdef CONFIG_SOFTMMU
+        tcg_regset_reset_reg(ct->u.regs, TCG_REG_R4);
+        tcg_regset_reset_reg(ct->u.regs, TCG_REG_R5);
+        tcg_regset_reset_reg(ct->u.regs, TCG_REG_R6);
+#endif
+        break;
+    case 'I':
+        ct->ct |= TCG_CT_CONST_S16;
+        break;
+    case 'J':
+        ct->ct |= TCG_CT_CONST_U16;
+        break;
+    case 'M':
+        ct->ct |= TCG_CT_CONST_MONE;
+        break;
+    case 'T':
+        ct->ct |= TCG_CT_CONST_S32;
+        break;
+    case 'U':
+        ct->ct |= TCG_CT_CONST_U32;
+        break;
+    case 'Z':
+        ct->ct |= TCG_CT_CONST_ZERO;
+        break;
+    default:
+        return -1;
+    }
+    ct_str++;
+    *pct_str = ct_str;
+    return 0;
+}
+
+/* test if a constant matches the constraint */
+static int tcg_target_const_match(tcg_target_long val, TCGType type,
+                                  const TCGArgConstraint *arg_ct)
+{
+    int ct = arg_ct->ct;
+    if (ct & TCG_CT_CONST) {
+        return 1;
+    }
+
+    /* The only 32-bit constraint we use aside from
+       TCG_CT_CONST is TCG_CT_CONST_S16.  */
+    if (type == TCG_TYPE_I32) {
+        val = (int32_t)val;
+    }
+
+    if ((ct & TCG_CT_CONST_S16) && val == (int16_t)val) {
+        return 1;
+    } else if ((ct & TCG_CT_CONST_U16) && val == (uint16_t)val) {
+        return 1;
+    } else if ((ct & TCG_CT_CONST_S32) && val == (int32_t)val) {
+        return 1;
+    } else if ((ct & TCG_CT_CONST_U32) && val == (uint32_t)val) {
+        return 1;
+    } else if ((ct & TCG_CT_CONST_ZERO) && val == 0) {
+        return 1;
+    } else if ((ct & TCG_CT_CONST_MONE) && val == -1) {
+        return 1;
+    }
+    return 0;
+}
+
+#define OPCD(opc) ((opc)<<26)
+#define XO19(opc) (OPCD(19)|((opc)<<1))
+#define MD30(opc) (OPCD(30)|((opc)<<2))
+#define MDS30(opc) (OPCD(30)|((opc)<<1))
+#define XO31(opc) (OPCD(31)|((opc)<<1))
+#define XO58(opc) (OPCD(58)|(opc))
+#define XO62(opc) (OPCD(62)|(opc))
+
+#define B      OPCD( 18)
+#define BC     OPCD( 16)
+#define LBZ    OPCD( 34)
+#define LHZ    OPCD( 40)
+#define LHA    OPCD( 42)
+#define LWZ    OPCD( 32)
+#define STB    OPCD( 38)
+#define STH    OPCD( 44)
+#define STW    OPCD( 36)
+
+#define STD    XO62(  0)
+#define STDU   XO62(  1)
+#define STDX   XO31(149)
+
+#define LD     XO58(  0)
+#define LDX    XO31( 21)
+#define LDU    XO58(  1)
+#define LWA    XO58(  2)
+#define LWAX   XO31(341)
+
+#define ADDIC  OPCD( 12)
+#define ADDI   OPCD( 14)
+#define ADDIS  OPCD( 15)
+#define ORI    OPCD( 24)
+#define ORIS   OPCD( 25)
+#define XORI   OPCD( 26)
+#define XORIS  OPCD( 27)
+#define ANDI   OPCD( 28)
+#define ANDIS  OPCD( 29)
+#define MULLI  OPCD(  7)
+#define CMPLI  OPCD( 10)
+#define CMPI   OPCD( 11)
+#define SUBFIC OPCD( 8)
+
+#define LWZU   OPCD( 33)
+#define STWU   OPCD( 37)
+
+#define RLWIMI OPCD( 20)
+#define RLWINM OPCD( 21)
+#define RLWNM  OPCD( 23)
+
+#define RLDICL MD30(  0)
+#define RLDICR MD30(  1)
+#define RLDIMI MD30(  3)
+#define RLDCL  MDS30( 8)
+
+#define BCLR   XO19( 16)
+#define BCCTR  XO19(528)
+#define CRAND  XO19(257)
+#define CRANDC XO19(129)
+#define CRNAND XO19(225)
+#define CROR   XO19(449)
+#define CRNOR  XO19( 33)
+
+#define EXTSB  XO31(954)
+#define EXTSH  XO31(922)
+#define EXTSW  XO31(986)
+#define ADD    XO31(266)
+#define ADDE   XO31(138)
+#define ADDME  XO31(234)
+#define ADDZE  XO31(202)
+#define ADDC   XO31( 10)
+#define AND    XO31( 28)
+#define SUBF   XO31( 40)
+#define SUBFC  XO31(  8)
+#define SUBFE  XO31(136)
+#define SUBFME XO31(232)
+#define SUBFZE XO31(200)
+#define OR     XO31(444)
+#define XOR    XO31(316)
+#define MULLW  XO31(235)
+#define MULHW  XO31( 75)
+#define MULHWU XO31( 11)
+#define DIVW   XO31(491)
+#define DIVWU  XO31(459)
+#define CMP    XO31(  0)
+#define CMPL   XO31( 32)
+#define LHBRX  XO31(790)
+#define LWBRX  XO31(534)
+#define LDBRX  XO31(532)
+#define STHBRX XO31(918)
+#define STWBRX XO31(662)
+#define STDBRX XO31(660)
+#define MFSPR  XO31(339)
+#define MTSPR  XO31(467)
+#define SRAWI  XO31(824)
+#define NEG    XO31(104)
+#define MFCR   XO31( 19)
+#define MFOCRF (MFCR | (1u << 20))
+#define NOR    XO31(124)
+#define CNTLZW XO31( 26)
+#define CNTLZD XO31( 58)
+#define ANDC   XO31( 60)
+#define ORC    XO31(412)
+#define EQV    XO31(284)
+#define NAND   XO31(476)
+#define ISEL   XO31( 15)
+
+#define MULLD  XO31(233)
+#define MULHD  XO31( 73)
+#define MULHDU XO31(  9)
+#define DIVD   XO31(489)
+#define DIVDU  XO31(457)
+
+#define LBZX   XO31( 87)
+#define LHZX   XO31(279)
+#define LHAX   XO31(343)
+#define LWZX   XO31( 23)
+#define STBX   XO31(215)
+#define STHX   XO31(407)
+#define STWX   XO31(151)
+
+#define SPR(a, b) ((((a)<<5)|(b))<<11)
+#define LR     SPR(8, 0)
+#define CTR    SPR(9, 0)
+
+#define SLW    XO31( 24)
+#define SRW    XO31(536)
+#define SRAW   XO31(792)
+
+#define SLD    XO31( 27)
+#define SRD    XO31(539)
+#define SRAD   XO31(794)
+#define SRADI  XO31(413<<1)
+
+#define TW     XO31( 4)
+#define TRAP   (TW | TO(31))
+
+#define NOP    ORI  /* ori 0,0,0 */
+
+#define RT(r) ((r)<<21)
+#define RS(r) ((r)<<21)
+#define RA(r) ((r)<<16)
+#define RB(r) ((r)<<11)
+#define TO(t) ((t)<<21)
+#define SH(s) ((s)<<11)
+#define MB(b) ((b)<<6)
+#define ME(e) ((e)<<1)
+#define BO(o) ((o)<<21)
+#define MB64(b) ((b)<<5)
+#define FXM(b) (1 << (19 - (b)))
+
+#define LK    1
+
+#define TAB(t, a, b) (RT(t) | RA(a) | RB(b))
+#define SAB(s, a, b) (RS(s) | RA(a) | RB(b))
+#define TAI(s, a, i) (RT(s) | RA(a) | ((i) & 0xffff))
+#define SAI(s, a, i) (RS(s) | RA(a) | ((i) & 0xffff))
+
+#define BF(n)    ((n)<<23)
+#define BI(n, c) (((c)+((n)*4))<<16)
+#define BT(n, c) (((c)+((n)*4))<<21)
+#define BA(n, c) (((c)+((n)*4))<<16)
+#define BB(n, c) (((c)+((n)*4))<<11)
+#define BC_(n, c) (((c)+((n)*4))<<6)
+
+#define BO_COND_TRUE  BO(12)
+#define BO_COND_FALSE BO( 4)
+#define BO_ALWAYS     BO(20)
+
+enum {
+    CR_LT,
+    CR_GT,
+    CR_EQ,
+    CR_SO
+};
+
+static const uint32_t tcg_to_bc[] = {
+    [TCG_COND_EQ]  = BC | BI(7, CR_EQ) | BO_COND_TRUE,
+    [TCG_COND_NE]  = BC | BI(7, CR_EQ) | BO_COND_FALSE,
+    [TCG_COND_LT]  = BC | BI(7, CR_LT) | BO_COND_TRUE,
+    [TCG_COND_GE]  = BC | BI(7, CR_LT) | BO_COND_FALSE,
+    [TCG_COND_LE]  = BC | BI(7, CR_GT) | BO_COND_FALSE,
+    [TCG_COND_GT]  = BC | BI(7, CR_GT) | BO_COND_TRUE,
+    [TCG_COND_LTU] = BC | BI(7, CR_LT) | BO_COND_TRUE,
+    [TCG_COND_GEU] = BC | BI(7, CR_LT) | BO_COND_FALSE,
+    [TCG_COND_LEU] = BC | BI(7, CR_GT) | BO_COND_FALSE,
+    [TCG_COND_GTU] = BC | BI(7, CR_GT) | BO_COND_TRUE,
+};
+
+/* The low bit here is set if the RA and RB fields must be inverted.  */
+static const uint32_t tcg_to_isel[] = {
+    [TCG_COND_EQ]  = ISEL | BC_(7, CR_EQ),
+    [TCG_COND_NE]  = ISEL | BC_(7, CR_EQ) | 1,
+    [TCG_COND_LT]  = ISEL | BC_(7, CR_LT),
+    [TCG_COND_GE]  = ISEL | BC_(7, CR_LT) | 1,
+    [TCG_COND_LE]  = ISEL | BC_(7, CR_GT) | 1,
+    [TCG_COND_GT]  = ISEL | BC_(7, CR_GT),
+    [TCG_COND_LTU] = ISEL | BC_(7, CR_LT),
+    [TCG_COND_GEU] = ISEL | BC_(7, CR_LT) | 1,
+    [TCG_COND_LEU] = ISEL | BC_(7, CR_GT) | 1,
+    [TCG_COND_GTU] = ISEL | BC_(7, CR_GT),
+};
+
+static void tcg_out_mem_long(TCGContext *s, int opi, int opx, TCGReg rt,
+                             TCGReg base, tcg_target_long offset);
+
+static void tcg_out_mov(TCGContext *s, TCGType type, TCGReg ret, TCGReg arg)
+{
+    tcg_debug_assert(TCG_TARGET_REG_BITS == 64 || type == TCG_TYPE_I32);
+    if (ret != arg) {
+        tcg_out32(s, OR | SAB(arg, ret, arg));
+    }
+}
+
+static inline void tcg_out_rld(TCGContext *s, int op, TCGReg ra, TCGReg rs,
+                               int sh, int mb)
+{
+    assert(TCG_TARGET_REG_BITS == 64);
+    sh = SH(sh & 0x1f) | (((sh >> 5) & 1) << 1);
+    mb = MB64((mb >> 5) | ((mb << 1) & 0x3f));
+    tcg_out32(s, op | RA(ra) | RS(rs) | sh | mb);
+}
+
+static inline void tcg_out_rlw(TCGContext *s, int op, TCGReg ra, TCGReg rs,
+                               int sh, int mb, int me)
+{
+    tcg_out32(s, op | RA(ra) | RS(rs) | SH(sh) | MB(mb) | ME(me));
+}
+
+static inline void tcg_out_ext32u(TCGContext *s, TCGReg dst, TCGReg src)
+{
+    tcg_out_rld(s, RLDICL, dst, src, 0, 32);
+}
+
+static inline void tcg_out_shli32(TCGContext *s, TCGReg dst, TCGReg src, int c)
+{
+    tcg_out_rlw(s, RLWINM, dst, src, c, 0, 31 - c);
+}
+
+static inline void tcg_out_shli64(TCGContext *s, TCGReg dst, TCGReg src, int c)
+{
+    tcg_out_rld(s, RLDICR, dst, src, c, 63 - c);
+}
+
+static inline void tcg_out_shri32(TCGContext *s, TCGReg dst, TCGReg src, int c)
+{
+    tcg_out_rlw(s, RLWINM, dst, src, 32 - c, c, 31);
+}
+
+static inline void tcg_out_shri64(TCGContext *s, TCGReg dst, TCGReg src, int c)
+{
+    tcg_out_rld(s, RLDICL, dst, src, 64 - c, c);
+}
+
+static void tcg_out_movi32(TCGContext *s, TCGReg ret, int32_t arg)
+{
+    if (arg == (int16_t) arg) {
+        tcg_out32(s, ADDI | TAI(ret, 0, arg));
+    } else {
+        tcg_out32(s, ADDIS | TAI(ret, 0, arg >> 16));
+        if (arg & 0xffff) {
+            tcg_out32(s, ORI | SAI(ret, ret, arg));
+        }
+    }
+}
+
+static void tcg_out_movi(TCGContext *s, TCGType type, TCGReg ret,
+                         tcg_target_long arg)
+{
+    tcg_debug_assert(TCG_TARGET_REG_BITS == 64 || type == TCG_TYPE_I32);
+    if (type == TCG_TYPE_I32 || arg == (int32_t)arg) {
+        tcg_out_movi32(s, ret, arg);
+    } else if (arg == (uint32_t)arg && !(arg & 0x8000)) {
+        tcg_out32(s, ADDI | TAI(ret, 0, arg));
+        tcg_out32(s, ORIS | SAI(ret, ret, arg >> 16));
+    } else {
+        int32_t high;
+
+        if (USE_REG_RA) {
+            intptr_t diff = arg - (intptr_t)tb_ret_addr;
+            if (diff == (int32_t)diff) {
+                tcg_out_mem_long(s, ADDI, ADD, ret, TCG_REG_RA, diff);
+                return;
+            }
+        }
+
+        high = arg >> 31 >> 1;
+        tcg_out_movi32(s, ret, high);
+        if (high) {
+            tcg_out_shli64(s, ret, ret, 32);
+        }
+        if (arg & 0xffff0000) {
+            tcg_out32(s, ORIS | SAI(ret, ret, arg >> 16));
+        }
+        if (arg & 0xffff) {
+            tcg_out32(s, ORI | SAI(ret, ret, arg));
+        }
+    }
+}
+
+static bool mask_operand(uint32_t c, int *mb, int *me)
+{
+    uint32_t lsb, test;
+
+    /* Accept a bit pattern like:
+           0....01....1
+           1....10....0
+           0..01..10..0
+       Keep track of the transitions.  */
+    if (c == 0 || c == -1) {
+        return false;
+    }
+    test = c;
+    lsb = test & -test;
+    test += lsb;
+    if (test & (test - 1)) {
+        return false;
+    }
+
+    *me = clz32(lsb);
+    *mb = test ? clz32(test & -test) + 1 : 0;
+    return true;
+}
+
+static bool mask64_operand(uint64_t c, int *mb, int *me)
+{
+    uint64_t lsb;
+
+    if (c == 0) {
+        return false;
+    }
+
+    lsb = c & -c;
+    /* Accept 1..10..0.  */
+    if (c == -lsb) {
+        *mb = 0;
+        *me = clz64(lsb);
+        return true;
+    }
+    /* Accept 0..01..1.  */
+    if (lsb == 1 && (c & (c + 1)) == 0) {
+        *mb = clz64(c + 1) + 1;
+        *me = 63;
+        return true;
+    }
+    return false;
+}
+
+static void tcg_out_andi32(TCGContext *s, TCGReg dst, TCGReg src, uint32_t c)
+{
+    int mb, me;
+
+    if ((c & 0xffff) == c) {
+        tcg_out32(s, ANDI | SAI(src, dst, c));
+        return;
+    } else if ((c & 0xffff0000) == c) {
+        tcg_out32(s, ANDIS | SAI(src, dst, c >> 16));
+        return;
+    } else if (mask_operand(c, &mb, &me)) {
+        tcg_out_rlw(s, RLWINM, dst, src, 0, mb, me);
+    } else {
+        tcg_out_movi(s, TCG_TYPE_I32, TCG_REG_R0, c);
+        tcg_out32(s, AND | SAB(src, dst, TCG_REG_R0));
+    }
+}
+
+static void tcg_out_andi64(TCGContext *s, TCGReg dst, TCGReg src, uint64_t c)
+{
+    int mb, me;
+
+    assert(TCG_TARGET_REG_BITS == 64);
+    if ((c & 0xffff) == c) {
+        tcg_out32(s, ANDI | SAI(src, dst, c));
+        return;
+    } else if ((c & 0xffff0000) == c) {
+        tcg_out32(s, ANDIS | SAI(src, dst, c >> 16));
+        return;
+    } else if (mask64_operand(c, &mb, &me)) {
+        if (mb == 0) {
+            tcg_out_rld(s, RLDICR, dst, src, 0, me);
+        } else {
+            tcg_out_rld(s, RLDICL, dst, src, 0, mb);
+        }
+    } else {
+        tcg_out_movi(s, TCG_TYPE_I64, TCG_REG_R0, c);
+        tcg_out32(s, AND | SAB(src, dst, TCG_REG_R0));
+    }
+}
+
+static void tcg_out_zori32(TCGContext *s, TCGReg dst, TCGReg src, uint32_t c,
+                           int op_lo, int op_hi)
+{
+    if (c >> 16) {
+        tcg_out32(s, op_hi | SAI(src, dst, c >> 16));
+        src = dst;
+    }
+    if (c & 0xffff) {
+        tcg_out32(s, op_lo | SAI(src, dst, c));
+        src = dst;
+    }
+}
+
+static void tcg_out_ori32(TCGContext *s, TCGReg dst, TCGReg src, uint32_t c)
+{
+    tcg_out_zori32(s, dst, src, c, ORI, ORIS);
+}
+
+static void tcg_out_xori32(TCGContext *s, TCGReg dst, TCGReg src, uint32_t c)
+{
+    tcg_out_zori32(s, dst, src, c, XORI, XORIS);
+}
+
+static void tcg_out_b(TCGContext *s, int mask, tcg_insn_unit *target)
+{
+    ptrdiff_t disp = tcg_pcrel_diff(s, target);
+    if (in_range_b(disp)) {
+        tcg_out32(s, B | (disp & 0x3fffffc) | mask);
+    } else {
+        tcg_out_movi(s, TCG_TYPE_PTR, TCG_REG_R0, (uintptr_t)target);
+        tcg_out32(s, MTSPR | RS(TCG_REG_R0) | CTR);
+        tcg_out32(s, BCCTR | BO_ALWAYS | mask);
+    }
+}
+
+static void tcg_out_mem_long(TCGContext *s, int opi, int opx, TCGReg rt,
+                             TCGReg base, tcg_target_long offset)
+{
+    tcg_target_long orig = offset, l0, l1, extra = 0, align = 0;
+    bool is_store = false;
+    TCGReg rs = TCG_REG_TMP1;
+
+    switch (opi) {
+    case LD: case LWA:
+        align = 3;
+        /* FALLTHRU */
+    default:
+        if (rt != TCG_REG_R0) {
+            rs = rt;
+            break;
+        }
+        break;
+    case STD:
+        align = 3;
+        /* FALLTHRU */
+    case STB: case STH: case STW:
+        is_store = true;
+        break;
+    }
+
+    /* For unaligned, or very large offsets, use the indexed form.  */
+    if (offset & align || offset != (int32_t)offset) {
+        if (rs == base) {
+            rs = TCG_REG_R0;
+        }
+        tcg_debug_assert(!is_store || rs != rt);
+        tcg_out_movi(s, TCG_TYPE_PTR, rs, orig);
+        tcg_out32(s, opx | TAB(rt, base, rs));
+        return;
+    }
+
+    l0 = (int16_t)offset;
+    offset = (offset - l0) >> 16;
+    l1 = (int16_t)offset;
+
+    if (l1 < 0 && orig >= 0) {
+        extra = 0x4000;
+        l1 = (int16_t)(offset - 0x4000);
+    }
+    if (l1) {
+        tcg_out32(s, ADDIS | TAI(rs, base, l1));
+        base = rs;
+    }
+    if (extra) {
+        tcg_out32(s, ADDIS | TAI(rs, base, extra));
+        base = rs;
+    }
+    if (opi != ADDI || base != rt || l0 != 0) {
+        tcg_out32(s, opi | TAI(rt, base, l0));
+    }
+}
+
+static inline void tcg_out_ld(TCGContext *s, TCGType type, TCGReg ret,
+                              TCGReg arg1, intptr_t arg2)
+{
+    int opi, opx;
+
+    assert(TCG_TARGET_REG_BITS == 64 || type == TCG_TYPE_I32);
+    if (type == TCG_TYPE_I32) {
+        opi = LWZ, opx = LWZX;
+    } else {
+        opi = LD, opx = LDX;
+    }
+    tcg_out_mem_long(s, opi, opx, ret, arg1, arg2);
+}
+
+static inline void tcg_out_st(TCGContext *s, TCGType type, TCGReg arg,
+                              TCGReg arg1, intptr_t arg2)
+{
+    int opi, opx;
+
+    assert(TCG_TARGET_REG_BITS == 64 || type == TCG_TYPE_I32);
+    if (type == TCG_TYPE_I32) {
+        opi = STW, opx = STWX;
+    } else {
+        opi = STD, opx = STDX;
+    }
+    tcg_out_mem_long(s, opi, opx, arg, arg1, arg2);
+}
+
+static void tcg_out_cmp(TCGContext *s, int cond, TCGArg arg1, TCGArg arg2,
+                        int const_arg2, int cr, TCGType type)
+{
+    int imm;
+    uint32_t op;
+
+    tcg_debug_assert(TCG_TARGET_REG_BITS == 64 || type == TCG_TYPE_I32);
+
+    /* Simplify the comparisons below wrt CMPI.  */
+    if (type == TCG_TYPE_I32) {
+        arg2 = (int32_t)arg2;
+    }
+
+    switch (cond) {
+    case TCG_COND_EQ:
+    case TCG_COND_NE:
+        if (const_arg2) {
+            if ((int16_t) arg2 == arg2) {
+                op = CMPI;
+                imm = 1;
+                break;
+            } else if ((uint16_t) arg2 == arg2) {
+                op = CMPLI;
+                imm = 1;
+                break;
+            }
+        }
+        op = CMPL;
+        imm = 0;
+        break;
+
+    case TCG_COND_LT:
+    case TCG_COND_GE:
+    case TCG_COND_LE:
+    case TCG_COND_GT:
+        if (const_arg2) {
+            if ((int16_t) arg2 == arg2) {
+                op = CMPI;
+                imm = 1;
+                break;
+            }
+        }
+        op = CMP;
+        imm = 0;
+        break;
+
+    case TCG_COND_LTU:
+    case TCG_COND_GEU:
+    case TCG_COND_LEU:
+    case TCG_COND_GTU:
+        if (const_arg2) {
+            if ((uint16_t) arg2 == arg2) {
+                op = CMPLI;
+                imm = 1;
+                break;
+            }
+        }
+        op = CMPL;
+        imm = 0;
+        break;
+
+    default:
+        tcg_abort();
+    }
+    op |= BF(cr) | ((type == TCG_TYPE_I64) << 21);
+
+    if (imm) {
+        tcg_out32(s, op | RA(arg1) | (arg2 & 0xffff));
+    } else {
+        if (const_arg2) {
+            tcg_out_movi(s, type, TCG_REG_R0, arg2);
+            arg2 = TCG_REG_R0;
+        }
+        tcg_out32(s, op | RA(arg1) | RB(arg2));
+    }
+}
+
+static void tcg_out_setcond_eq0(TCGContext *s, TCGType type,
+                                TCGReg dst, TCGReg src)
+{
+    if (type == TCG_TYPE_I32) {
+        tcg_out32(s, CNTLZW | RS(src) | RA(dst));
+        tcg_out_shri32(s, dst, dst, 5);
+    } else {
+        tcg_out32(s, CNTLZD | RS(src) | RA(dst));
+        tcg_out_shri64(s, dst, dst, 6);
+    }
+}
+
+static void tcg_out_setcond_ne0(TCGContext *s, TCGReg dst, TCGReg src)
+{
+    /* X != 0 implies X + -1 generates a carry.  Extra addition
+       trickery means: R = X-1 + ~X + C = X-1 + (-X+1) + C = C.  */
+    if (dst != src) {
+        tcg_out32(s, ADDIC | TAI(dst, src, -1));
+        tcg_out32(s, SUBFE | TAB(dst, dst, src));
+    } else {
+        tcg_out32(s, ADDIC | TAI(TCG_REG_R0, src, -1));
+        tcg_out32(s, SUBFE | TAB(dst, TCG_REG_R0, src));
+    }
+}
+
+static TCGReg tcg_gen_setcond_xor(TCGContext *s, TCGReg arg1, TCGArg arg2,
+                                  bool const_arg2)
+{
+    if (const_arg2) {
+        if ((uint32_t)arg2 == arg2) {
+            tcg_out_xori32(s, TCG_REG_R0, arg1, arg2);
+        } else {
+            tcg_out_movi(s, TCG_TYPE_I64, TCG_REG_R0, arg2);
+            tcg_out32(s, XOR | SAB(arg1, TCG_REG_R0, TCG_REG_R0));
+        }
+    } else {
+        tcg_out32(s, XOR | SAB(arg1, TCG_REG_R0, arg2));
+    }
+    return TCG_REG_R0;
+}
+
+static void tcg_out_setcond(TCGContext *s, TCGType type, TCGCond cond,
+                            TCGArg arg0, TCGArg arg1, TCGArg arg2,
+                            int const_arg2)
+{
+    int crop, sh;
+
+    assert(TCG_TARGET_REG_BITS == 64 || type == TCG_TYPE_I32);
+
+    /* Ignore high bits of a potential constant arg2.  */
+    if (type == TCG_TYPE_I32) {
+        arg2 = (uint32_t)arg2;
+    }
+
+    /* Handle common and trivial cases before handling anything else.  */
+    if (arg2 == 0) {
+        switch (cond) {
+        case TCG_COND_EQ:
+            tcg_out_setcond_eq0(s, type, arg0, arg1);
+            return;
+        case TCG_COND_NE:
+            if (TCG_TARGET_REG_BITS == 64 && type == TCG_TYPE_I32) {
+                tcg_out_ext32u(s, TCG_REG_R0, arg1);
+                arg1 = TCG_REG_R0;
+            }
+            tcg_out_setcond_ne0(s, arg0, arg1);
+            return;
+        case TCG_COND_GE:
+            tcg_out32(s, NOR | SAB(arg1, arg0, arg1));
+            arg1 = arg0;
+            /* FALLTHRU */
+        case TCG_COND_LT:
+            /* Extract the sign bit.  */
+            if (type == TCG_TYPE_I32) {
+                tcg_out_shri32(s, arg0, arg1, 31);
+            } else {
+                tcg_out_shri64(s, arg0, arg1, 63);
+            }
+            return;
+        default:
+            break;
+        }
+    }
+
+    /* If we have ISEL, we can implement everything with 3 or 4 insns.
+       All other cases below are also at least 3 insns, so speed up the
+       code generator by not considering them and always using ISEL.  */
+    if (HAVE_ISEL) {
+        int isel, tab;
+
+        tcg_out_cmp(s, cond, arg1, arg2, const_arg2, 7, type);
+
+        isel = tcg_to_isel[cond];
+
+        tcg_out_movi(s, type, arg0, 1);
+        if (isel & 1) {
+            /* arg0 = (bc ? 0 : 1) */
+            tab = TAB(arg0, 0, arg0);
+            isel &= ~1;
+        } else {
+            /* arg0 = (bc ? 1 : 0) */
+            tcg_out_movi(s, type, TCG_REG_R0, 0);
+            tab = TAB(arg0, arg0, TCG_REG_R0);
+        }
+        tcg_out32(s, isel | tab);
+        return;
+    }
+
+    switch (cond) {
+    case TCG_COND_EQ:
+        arg1 = tcg_gen_setcond_xor(s, arg1, arg2, const_arg2);
+        tcg_out_setcond_eq0(s, type, arg0, arg1);
+        return;
+
+    case TCG_COND_NE:
+        arg1 = tcg_gen_setcond_xor(s, arg1, arg2, const_arg2);
+        /* Discard the high bits only once, rather than both inputs.  */
+        if (TCG_TARGET_REG_BITS == 64 && type == TCG_TYPE_I32) {
+            tcg_out_ext32u(s, TCG_REG_R0, arg1);
+            arg1 = TCG_REG_R0;
+        }
+        tcg_out_setcond_ne0(s, arg0, arg1);
+        return;
+
+    case TCG_COND_GT:
+    case TCG_COND_GTU:
+        sh = 30;
+        crop = 0;
+        goto crtest;
+
+    case TCG_COND_LT:
+    case TCG_COND_LTU:
+        sh = 29;
+        crop = 0;
+        goto crtest;
+
+    case TCG_COND_GE:
+    case TCG_COND_GEU:
+        sh = 31;
+        crop = CRNOR | BT(7, CR_EQ) | BA(7, CR_LT) | BB(7, CR_LT);
+        goto crtest;
+
+    case TCG_COND_LE:
+    case TCG_COND_LEU:
+        sh = 31;
+        crop = CRNOR | BT(7, CR_EQ) | BA(7, CR_GT) | BB(7, CR_GT);
+    crtest:
+        tcg_out_cmp(s, cond, arg1, arg2, const_arg2, 7, type);
+        if (crop) {
+            tcg_out32(s, crop);
+        }
+        tcg_out32(s, MFOCRF | RT(TCG_REG_R0) | FXM(7));
+        tcg_out_rlw(s, RLWINM, arg0, TCG_REG_R0, sh, 31, 31);
+        break;
+
+    default:
+        tcg_abort();
+    }
+}
+
+static void tcg_out_bc(TCGContext *s, int bc, TCGLabel *l)
+{
+    if (l->has_value) {
+        tcg_out32(s, bc | reloc_pc14_val(s->code_ptr, l->u.value_ptr));
+    } else {
+        tcg_out_reloc(s, s->code_ptr, R_PPC_REL14, l, 0);
+        tcg_out_bc_noaddr(s, bc);
+    }
+}
+
+static void tcg_out_brcond(TCGContext *s, TCGCond cond,
+                           TCGArg arg1, TCGArg arg2, int const_arg2,
+                           TCGLabel *l, TCGType type)
+{
+    tcg_out_cmp(s, cond, arg1, arg2, const_arg2, 7, type);
+    tcg_out_bc(s, tcg_to_bc[cond], l);
+}
+
+static void tcg_out_movcond(TCGContext *s, TCGType type, TCGCond cond,
+                            TCGArg dest, TCGArg c1, TCGArg c2, TCGArg v1,
+                            TCGArg v2, bool const_c2)
+{
+    /* If for some reason both inputs are zero, don't produce bad code.  */
+    if (v1 == 0 && v2 == 0) {
+        tcg_out_movi(s, type, dest, 0);
+        return;
+    }
+
+    tcg_out_cmp(s, cond, c1, c2, const_c2, 7, type);
+
+    if (HAVE_ISEL) {
+        int isel = tcg_to_isel[cond];
+
+        /* Swap the V operands if the operation indicates inversion.  */
+        if (isel & 1) {
+            int t = v1;
+            v1 = v2;
+            v2 = t;
+            isel &= ~1;
+        }
+        /* V1 == 0 is handled by isel; V2 == 0 must be handled by hand.  */
+        if (v2 == 0) {
+            tcg_out_movi(s, type, TCG_REG_R0, 0);
+        }
+        tcg_out32(s, isel | TAB(dest, v1, v2));
+    } else {
+        if (dest == v2) {
+            cond = tcg_invert_cond(cond);
+            v2 = v1;
+        } else if (dest != v1) {
+            if (v1 == 0) {
+                tcg_out_movi(s, type, dest, 0);
+            } else {
+                tcg_out_mov(s, type, dest, v1);
+            }
+        }
+        /* Branch forward over one insn */
+        tcg_out32(s, tcg_to_bc[cond] | 8);
+        if (v2 == 0) {
+            tcg_out_movi(s, type, dest, 0);
+        } else {
+            tcg_out_mov(s, type, dest, v2);
+        }
+    }
+}
+
+static void tcg_out_cmp2(TCGContext *s, const TCGArg *args,
+                         const int *const_args)
+{
+    static const struct { uint8_t bit1, bit2; } bits[] = {
+        [TCG_COND_LT ] = { CR_LT, CR_LT },
+        [TCG_COND_LE ] = { CR_LT, CR_GT },
+        [TCG_COND_GT ] = { CR_GT, CR_GT },
+        [TCG_COND_GE ] = { CR_GT, CR_LT },
+        [TCG_COND_LTU] = { CR_LT, CR_LT },
+        [TCG_COND_LEU] = { CR_LT, CR_GT },
+        [TCG_COND_GTU] = { CR_GT, CR_GT },
+        [TCG_COND_GEU] = { CR_GT, CR_LT },
+    };
+
+    TCGCond cond = args[4], cond2;
+    TCGArg al, ah, bl, bh;
+    int blconst, bhconst;
+    int op, bit1, bit2;
+
+    al = args[0];
+    ah = args[1];
+    bl = args[2];
+    bh = args[3];
+    blconst = const_args[2];
+    bhconst = const_args[3];
+
+    switch (cond) {
+    case TCG_COND_EQ:
+        op = CRAND;
+        goto do_equality;
+    case TCG_COND_NE:
+        op = CRNAND;
+    do_equality:
+        tcg_out_cmp(s, cond, al, bl, blconst, 6, TCG_TYPE_I32);
+        tcg_out_cmp(s, cond, ah, bh, bhconst, 7, TCG_TYPE_I32);
+        tcg_out32(s, op | BT(7, CR_EQ) | BA(6, CR_EQ) | BB(7, CR_EQ));
+        break;
+
+    case TCG_COND_LT:
+    case TCG_COND_LE:
+    case TCG_COND_GT:
+    case TCG_COND_GE:
+    case TCG_COND_LTU:
+    case TCG_COND_LEU:
+    case TCG_COND_GTU:
+    case TCG_COND_GEU:
+        bit1 = bits[cond].bit1;
+        bit2 = bits[cond].bit2;
+        op = (bit1 != bit2 ? CRANDC : CRAND);
+        cond2 = tcg_unsigned_cond(cond);
+
+        tcg_out_cmp(s, cond, ah, bh, bhconst, 6, TCG_TYPE_I32);
+        tcg_out_cmp(s, cond2, al, bl, blconst, 7, TCG_TYPE_I32);
+        tcg_out32(s, op | BT(7, CR_EQ) | BA(6, CR_EQ) | BB(7, bit2));
+        tcg_out32(s, CROR | BT(7, CR_EQ) | BA(6, bit1) | BB(7, CR_EQ));
+        break;
+
+    default:
+        tcg_abort();
+    }
+}
+
+static void tcg_out_setcond2(TCGContext *s, const TCGArg *args,
+                             const int *const_args)
+{
+    tcg_out_cmp2(s, args + 1, const_args + 1);
+    tcg_out32(s, MFOCRF | RT(TCG_REG_R0) | FXM(7));
+    tcg_out_rlw(s, RLWINM, args[0], TCG_REG_R0, 31, 31, 31);
+}
+
+static void tcg_out_brcond2 (TCGContext *s, const TCGArg *args,
+                             const int *const_args)
+{
+    tcg_out_cmp2(s, args, const_args);
+    tcg_out_bc(s, BC | BI(7, CR_EQ) | BO_COND_TRUE, arg_label(args[5]));
+}
+
+void ppc_tb_set_jmp_target(uintptr_t jmp_addr, uintptr_t addr)
+{
+    TCGContext s;
+
+    s.code_buf = s.code_ptr = (tcg_insn_unit *)jmp_addr;
+    tcg_out_b(&s, 0, (tcg_insn_unit *)addr);
+    flush_icache_range(jmp_addr, jmp_addr + tcg_current_code_size(&s));
+}
+
+static void tcg_out_call(TCGContext *s, tcg_insn_unit *target)
+{
+#ifdef _CALL_AIX
+    /* Look through the descriptor.  If the branch is in range, and we
+       don't have to spend too much effort on building the toc.  */
+    void *tgt = ((void **)target)[0];
+    uintptr_t toc = ((uintptr_t *)target)[1];
+    intptr_t diff = tcg_pcrel_diff(s, tgt);
+
+    if (in_range_b(diff) && toc == (uint32_t)toc) {
+        tcg_out_movi(s, TCG_TYPE_PTR, TCG_REG_TMP1, toc);
+        tcg_out_b(s, LK, tgt);
+    } else {
+        /* Fold the low bits of the constant into the addresses below.  */
+        intptr_t arg = (intptr_t)target;
+        int ofs = (int16_t)arg;
+
+        if (ofs + 8 < 0x8000) {
+            arg -= ofs;
+        } else {
+            ofs = 0;
+        }
+        tcg_out_movi(s, TCG_TYPE_PTR, TCG_REG_TMP1, arg);
+        tcg_out_ld(s, TCG_TYPE_PTR, TCG_REG_R0, TCG_REG_TMP1, ofs);
+        tcg_out32(s, MTSPR | RA(TCG_REG_R0) | CTR);
+        tcg_out_ld(s, TCG_TYPE_PTR, TCG_REG_R2, TCG_REG_TMP1, ofs + SZP);
+        tcg_out32(s, BCCTR | BO_ALWAYS | LK);
+    }
+#elif defined(_CALL_ELF) && _CALL_ELF == 2
+    intptr_t diff;
+
+    /* In the ELFv2 ABI, we have to set up r12 to contain the destination
+       address, which the callee uses to compute its TOC address.  */
+    /* FIXME: when the branch is in range, we could avoid r12 load if we
+       knew that the destination uses the same TOC, and what its local
+       entry point offset is.  */
+    tcg_out_movi(s, TCG_TYPE_PTR, TCG_REG_R12, (intptr_t)target);
+
+    diff = tcg_pcrel_diff(s, target);
+    if (in_range_b(diff)) {
+        tcg_out_b(s, LK, target);
+    } else {
+        tcg_out32(s, MTSPR | RS(TCG_REG_R12) | CTR);
+        tcg_out32(s, BCCTR | BO_ALWAYS | LK);
+    }
+#else
+    tcg_out_b(s, LK, target);
+#endif
+}
+
+static const uint32_t qemu_ldx_opc[16] = {
+    [MO_UB] = LBZX,
+    [MO_UW] = LHZX,
+    [MO_UL] = LWZX,
+    [MO_Q]  = LDX,
+    [MO_SW] = LHAX,
+    [MO_SL] = LWAX,
+    [MO_BSWAP | MO_UB] = LBZX,
+    [MO_BSWAP | MO_UW] = LHBRX,
+    [MO_BSWAP | MO_UL] = LWBRX,
+    [MO_BSWAP | MO_Q]  = LDBRX,
+};
+
+static const uint32_t qemu_stx_opc[16] = {
+    [MO_UB] = STBX,
+    [MO_UW] = STHX,
+    [MO_UL] = STWX,
+    [MO_Q]  = STDX,
+    [MO_BSWAP | MO_UB] = STBX,
+    [MO_BSWAP | MO_UW] = STHBRX,
+    [MO_BSWAP | MO_UL] = STWBRX,
+    [MO_BSWAP | MO_Q]  = STDBRX,
+};
+
+static const uint32_t qemu_exts_opc[4] = {
+    EXTSB, EXTSH, EXTSW, 0
+};
+
+#if defined (CONFIG_SOFTMMU)
+/* helper signature: helper_ld_mmu(CPUState *env, target_ulong addr,
+ *                                 int mmu_idx, uintptr_t ra)
+ */
+static void * const qemu_ld_helpers[16] = {
+    [MO_UB]   = helper_ret_ldub_mmu,
+    [MO_LEUW] = helper_le_lduw_mmu,
+    [MO_LEUL] = helper_le_ldul_mmu,
+    [MO_LEQ]  = helper_le_ldq_mmu,
+    [MO_BEUW] = helper_be_lduw_mmu,
+    [MO_BEUL] = helper_be_ldul_mmu,
+    [MO_BEQ]  = helper_be_ldq_mmu,
+};
+
+/* helper signature: helper_st_mmu(CPUState *env, target_ulong addr,
+ *                                 uintxx_t val, int mmu_idx, uintptr_t ra)
+ */
+static void * const qemu_st_helpers[16] = {
+    [MO_UB]   = helper_ret_stb_mmu,
+    [MO_LEUW] = helper_le_stw_mmu,
+    [MO_LEUL] = helper_le_stl_mmu,
+    [MO_LEQ]  = helper_le_stq_mmu,
+    [MO_BEUW] = helper_be_stw_mmu,
+    [MO_BEUL] = helper_be_stl_mmu,
+    [MO_BEQ]  = helper_be_stq_mmu,
+};
+
+/* Perform the TLB load and compare.  Places the result of the comparison
+   in CR7, loads the addend of the TLB into R3, and returns the register
+   containing the guest address (zero-extended into R4).  Clobbers R0 and R2. */
+
+static TCGReg tcg_out_tlb_read(TCGContext *s, TCGMemOp s_bits,
+                               TCGReg addrlo, TCGReg addrhi,
+                               int mem_index, bool is_read)
+{
+    int cmp_off
+        = (is_read
+           ? offsetof(CPUArchState, tlb_table[mem_index][0].addr_read)
+           : offsetof(CPUArchState, tlb_table[mem_index][0].addr_write));
+    int add_off = offsetof(CPUArchState, tlb_table[mem_index][0].addend);
+    TCGReg base = TCG_AREG0;
+
+    /* Extract the page index, shifted into place for tlb index.  */
+    if (TCG_TARGET_REG_BITS == 64) {
+        if (TARGET_LONG_BITS == 32) {
+            /* Zero-extend the address into a place helpful for further use. */
+            tcg_out_ext32u(s, TCG_REG_R4, addrlo);
+            addrlo = TCG_REG_R4;
+        } else {
+            tcg_out_rld(s, RLDICL, TCG_REG_R3, addrlo,
+                        64 - TARGET_PAGE_BITS, 64 - CPU_TLB_BITS);
+        }
+    }
+
+    /* Compensate for very large offsets.  */
+    if (add_off >= 0x8000) {
+        /* Most target env are smaller than 32k; none are larger than 64k.
+           Simplify the logic here merely to offset by 0x7ff0, giving us a
+           range just shy of 64k.  Check this assumption.  */
+        QEMU_BUILD_BUG_ON(offsetof(CPUArchState,
+                                   tlb_table[NB_MMU_MODES - 1][1])
+                          > 0x7ff0 + 0x7fff);
+        tcg_out32(s, ADDI | TAI(TCG_REG_TMP1, base, 0x7ff0));
+        base = TCG_REG_TMP1;
+        cmp_off -= 0x7ff0;
+        add_off -= 0x7ff0;
+    }
+
+    /* Extraction and shifting, part 2.  */
+    if (TCG_TARGET_REG_BITS == 32 || TARGET_LONG_BITS == 32) {
+        tcg_out_rlw(s, RLWINM, TCG_REG_R3, addrlo,
+                    32 - (TARGET_PAGE_BITS - CPU_TLB_ENTRY_BITS),
+                    32 - (CPU_TLB_BITS + CPU_TLB_ENTRY_BITS),
+                    31 - CPU_TLB_ENTRY_BITS);
+    } else {
+        tcg_out_shli64(s, TCG_REG_R3, TCG_REG_R3, CPU_TLB_ENTRY_BITS);
+    }
+
+    tcg_out32(s, ADD | TAB(TCG_REG_R3, TCG_REG_R3, base));
+
+    /* Load the tlb comparator.  */
+    if (TCG_TARGET_REG_BITS < TARGET_LONG_BITS) {
+        tcg_out_ld(s, TCG_TYPE_I32, TCG_REG_R4, TCG_REG_R3, cmp_off);
+        tcg_out_ld(s, TCG_TYPE_I32, TCG_REG_TMP1, TCG_REG_R3, cmp_off + 4);
+    } else {
+        tcg_out_ld(s, TCG_TYPE_TL, TCG_REG_TMP1, TCG_REG_R3, cmp_off);
+    }
+
+    /* Load the TLB addend for use on the fast path.  Do this asap
+       to minimize any load use delay.  */
+    tcg_out_ld(s, TCG_TYPE_PTR, TCG_REG_R3, TCG_REG_R3, add_off);
+
+    /* Clear the non-page, non-alignment bits from the address.  */
+    if (TCG_TARGET_REG_BITS == 32 || TARGET_LONG_BITS == 32) {
+        tcg_out_rlw(s, RLWINM, TCG_REG_R0, addrlo, 0,
+                    (32 - s_bits) & 31, 31 - TARGET_PAGE_BITS);
+    } else if (!s_bits) {
+        tcg_out_rld(s, RLDICR, TCG_REG_R0, addrlo,
+                    0, 63 - TARGET_PAGE_BITS);
+    } else {
+        tcg_out_rld(s, RLDICL, TCG_REG_R0, addrlo,
+                    64 - TARGET_PAGE_BITS, TARGET_PAGE_BITS - s_bits);
+        tcg_out_rld(s, RLDICL, TCG_REG_R0, TCG_REG_R0, TARGET_PAGE_BITS, 0);
+    }
+
+    if (TCG_TARGET_REG_BITS < TARGET_LONG_BITS) {
+        tcg_out_cmp(s, TCG_COND_EQ, TCG_REG_R0, TCG_REG_TMP1,
+                    0, 7, TCG_TYPE_I32);
+        tcg_out_cmp(s, TCG_COND_EQ, addrhi, TCG_REG_R4, 0, 6, TCG_TYPE_I32);
+        tcg_out32(s, CRAND | BT(7, CR_EQ) | BA(6, CR_EQ) | BB(7, CR_EQ));
+    } else {
+        tcg_out_cmp(s, TCG_COND_EQ, TCG_REG_R0, TCG_REG_TMP1,
+                    0, 7, TCG_TYPE_TL);
+    }
+
+    return addrlo;
+}
+
+/* Record the context of a call to the out of line helper code for the slow
+   path for a load or store, so that we can later generate the correct
+   helper code.  */
+static void add_qemu_ldst_label(TCGContext *s, bool is_ld, TCGMemOpIdx oi,
+                                TCGReg datalo_reg, TCGReg datahi_reg,
+                                TCGReg addrlo_reg, TCGReg addrhi_reg,
+                                tcg_insn_unit *raddr, tcg_insn_unit *lptr)
+{
+    TCGLabelQemuLdst *label = new_ldst_label(s);
+
+    label->is_ld = is_ld;
+    label->oi = oi;
+    label->datalo_reg = datalo_reg;
+    label->datahi_reg = datahi_reg;
+    label->addrlo_reg = addrlo_reg;
+    label->addrhi_reg = addrhi_reg;
+    label->raddr = raddr;
+    label->label_ptr[0] = lptr;
+}
+
+static void tcg_out_qemu_ld_slow_path(TCGContext *s, TCGLabelQemuLdst *lb)
+{
+    TCGMemOpIdx oi = lb->oi;
+    TCGMemOp opc = get_memop(oi);
+    TCGReg hi, lo, arg = TCG_REG_R3;
+
+    reloc_pc14(lb->label_ptr[0], s->code_ptr);
+
+    tcg_out_mov(s, TCG_TYPE_PTR, arg++, TCG_AREG0);
+
+    lo = lb->addrlo_reg;
+    hi = lb->addrhi_reg;
+    if (TCG_TARGET_REG_BITS < TARGET_LONG_BITS) {
+#ifdef TCG_TARGET_CALL_ALIGN_ARGS
+        arg |= 1;
+#endif
+        tcg_out_mov(s, TCG_TYPE_I32, arg++, hi);
+        tcg_out_mov(s, TCG_TYPE_I32, arg++, lo);
+    } else {
+        /* If the address needed to be zero-extended, we'll have already
+           placed it in R4.  The only remaining case is 64-bit guest.  */
+        tcg_out_mov(s, TCG_TYPE_TL, arg++, lo);
+    }
+
+    tcg_out_movi(s, TCG_TYPE_I32, arg++, oi);
+    tcg_out32(s, MFSPR | RT(arg) | LR);
+
+    tcg_out_call(s, qemu_ld_helpers[opc & (MO_BSWAP | MO_SIZE)]);
+
+    lo = lb->datalo_reg;
+    hi = lb->datahi_reg;
+    if (TCG_TARGET_REG_BITS == 32 && (opc & MO_SIZE) == MO_64) {
+        tcg_out_mov(s, TCG_TYPE_I32, lo, TCG_REG_R4);
+        tcg_out_mov(s, TCG_TYPE_I32, hi, TCG_REG_R3);
+    } else if (opc & MO_SIGN) {
+        uint32_t insn = qemu_exts_opc[opc & MO_SIZE];
+        tcg_out32(s, insn | RA(lo) | RS(TCG_REG_R3));
+    } else {
+        tcg_out_mov(s, TCG_TYPE_REG, lo, TCG_REG_R3);
+    }
+
+    tcg_out_b(s, 0, lb->raddr);
+}
+
+static void tcg_out_qemu_st_slow_path(TCGContext *s, TCGLabelQemuLdst *lb)
+{
+    TCGMemOpIdx oi = lb->oi;
+    TCGMemOp opc = get_memop(oi);
+    TCGMemOp s_bits = opc & MO_SIZE;
+    TCGReg hi, lo, arg = TCG_REG_R3;
+
+    reloc_pc14(lb->label_ptr[0], s->code_ptr);
+
+    tcg_out_mov(s, TCG_TYPE_PTR, arg++, TCG_AREG0);
+
+    lo = lb->addrlo_reg;
+    hi = lb->addrhi_reg;
+    if (TCG_TARGET_REG_BITS < TARGET_LONG_BITS) {
+#ifdef TCG_TARGET_CALL_ALIGN_ARGS
+        arg |= 1;
+#endif
+        tcg_out_mov(s, TCG_TYPE_I32, arg++, hi);
+        tcg_out_mov(s, TCG_TYPE_I32, arg++, lo);
+    } else {
+        /* If the address needed to be zero-extended, we'll have already
+           placed it in R4.  The only remaining case is 64-bit guest.  */
+        tcg_out_mov(s, TCG_TYPE_TL, arg++, lo);
+    }
+
+    lo = lb->datalo_reg;
+    hi = lb->datahi_reg;
+    if (TCG_TARGET_REG_BITS == 32) {
+        switch (s_bits) {
+        case MO_64:
+#ifdef TCG_TARGET_CALL_ALIGN_ARGS
+            arg |= 1;
+#endif
+            tcg_out_mov(s, TCG_TYPE_I32, arg++, hi);
+            /* FALLTHRU */
+        case MO_32:
+            tcg_out_mov(s, TCG_TYPE_I32, arg++, lo);
+            break;
+        default:
+            tcg_out_rlw(s, RLWINM, arg++, lo, 0, 32 - (8 << s_bits), 31);
+            break;
+        }
+    } else {
+        if (s_bits == MO_64) {
+            tcg_out_mov(s, TCG_TYPE_I64, arg++, lo);
+        } else {
+            tcg_out_rld(s, RLDICL, arg++, lo, 0, 64 - (8 << s_bits));
+        }
+    }
+
+    tcg_out_movi(s, TCG_TYPE_I32, arg++, oi);
+    tcg_out32(s, MFSPR | RT(arg) | LR);
+
+    tcg_out_call(s, qemu_st_helpers[opc & (MO_BSWAP | MO_SIZE)]);
+
+    tcg_out_b(s, 0, lb->raddr);
+}
+#endif /* SOFTMMU */
+
+static void tcg_out_qemu_ld(TCGContext *s, const TCGArg *args, bool is_64)
+{
+    TCGReg datalo, datahi, addrlo, rbase;
+    TCGReg addrhi __attribute__((unused));
+    TCGMemOpIdx oi;
+    TCGMemOp opc, s_bits;
+#ifdef CONFIG_SOFTMMU
+    int mem_index;
+    tcg_insn_unit *label_ptr;
+#endif
+
+    datalo = *args++;
+    datahi = (TCG_TARGET_REG_BITS == 32 && is_64 ? *args++ : 0);
+    addrlo = *args++;
+    addrhi = (TCG_TARGET_REG_BITS < TARGET_LONG_BITS ? *args++ : 0);
+    oi = *args++;
+    opc = get_memop(oi);
+    s_bits = opc & MO_SIZE;
+
+#ifdef CONFIG_SOFTMMU
+    mem_index = get_mmuidx(oi);
+    addrlo = tcg_out_tlb_read(s, s_bits, addrlo, addrhi, mem_index, true);
+
+    /* Load a pointer into the current opcode w/conditional branch-link. */
+    label_ptr = s->code_ptr;
+    tcg_out_bc_noaddr(s, BC | BI(7, CR_EQ) | BO_COND_FALSE | LK);
+
+    rbase = TCG_REG_R3;
+#else  /* !CONFIG_SOFTMMU */
+    rbase = GUEST_BASE ? TCG_GUEST_BASE_REG : 0;
+    if (TCG_TARGET_REG_BITS > TARGET_LONG_BITS) {
+        tcg_out_ext32u(s, TCG_REG_TMP1, addrlo);
+        addrlo = TCG_REG_TMP1;
+    }
+#endif
+
+    if (TCG_TARGET_REG_BITS == 32 && s_bits == MO_64) {
+        if (opc & MO_BSWAP) {
+            tcg_out32(s, ADDI | TAI(TCG_REG_R0, addrlo, 4));
+            tcg_out32(s, LWBRX | TAB(datalo, rbase, addrlo));
+            tcg_out32(s, LWBRX | TAB(datahi, rbase, TCG_REG_R0));
+        } else if (rbase != 0) {
+            tcg_out32(s, ADDI | TAI(TCG_REG_R0, addrlo, 4));
+            tcg_out32(s, LWZX | TAB(datahi, rbase, addrlo));
+            tcg_out32(s, LWZX | TAB(datalo, rbase, TCG_REG_R0));
+        } else if (addrlo == datahi) {
+            tcg_out32(s, LWZ | TAI(datalo, addrlo, 4));
+            tcg_out32(s, LWZ | TAI(datahi, addrlo, 0));
+        } else {
+            tcg_out32(s, LWZ | TAI(datahi, addrlo, 0));
+            tcg_out32(s, LWZ | TAI(datalo, addrlo, 4));
+        }
+    } else {
+        uint32_t insn = qemu_ldx_opc[opc & (MO_BSWAP | MO_SSIZE)];
+        if (!HAVE_ISA_2_06 && insn == LDBRX) {
+            tcg_out32(s, ADDI | TAI(TCG_REG_R0, addrlo, 4));
+            tcg_out32(s, LWBRX | TAB(datalo, rbase, addrlo));
+            tcg_out32(s, LWBRX | TAB(TCG_REG_R0, rbase, TCG_REG_R0));
+            tcg_out_rld(s, RLDIMI, datalo, TCG_REG_R0, 32, 0);
+        } else if (insn) {
+            tcg_out32(s, insn | TAB(datalo, rbase, addrlo));
+        } else {
+            insn = qemu_ldx_opc[opc & (MO_SIZE | MO_BSWAP)];
+            tcg_out32(s, insn | TAB(datalo, rbase, addrlo));
+            insn = qemu_exts_opc[s_bits];
+            tcg_out32(s, insn | RA(datalo) | RS(datalo));
+        }
+    }
+
+#ifdef CONFIG_SOFTMMU
+    add_qemu_ldst_label(s, true, oi, datalo, datahi, addrlo, addrhi,
+                        s->code_ptr, label_ptr);
+#endif
+}
+
+static void tcg_out_qemu_st(TCGContext *s, const TCGArg *args, bool is_64)
+{
+    TCGReg datalo, datahi, addrlo, rbase;
+    TCGReg addrhi __attribute__((unused));
+    TCGMemOpIdx oi;
+    TCGMemOp opc, s_bits;
+#ifdef CONFIG_SOFTMMU
+    int mem_index;
+    tcg_insn_unit *label_ptr;
+#endif
+
+    datalo = *args++;
+    datahi = (TCG_TARGET_REG_BITS == 32 && is_64 ? *args++ : 0);
+    addrlo = *args++;
+    addrhi = (TCG_TARGET_REG_BITS < TARGET_LONG_BITS ? *args++ : 0);
+    oi = *args++;
+    opc = get_memop(oi);
+    s_bits = opc & MO_SIZE;
+
+#ifdef CONFIG_SOFTMMU
+    mem_index = get_mmuidx(oi);
+    addrlo = tcg_out_tlb_read(s, s_bits, addrlo, addrhi, mem_index, false);
+
+    /* Load a pointer into the current opcode w/conditional branch-link. */
+    label_ptr = s->code_ptr;
+    tcg_out_bc_noaddr(s, BC | BI(7, CR_EQ) | BO_COND_FALSE | LK);
+
+    rbase = TCG_REG_R3;
+#else  /* !CONFIG_SOFTMMU */
+    rbase = GUEST_BASE ? TCG_GUEST_BASE_REG : 0;
+    if (TCG_TARGET_REG_BITS > TARGET_LONG_BITS) {
+        tcg_out_ext32u(s, TCG_REG_TMP1, addrlo);
+        addrlo = TCG_REG_TMP1;
+    }
+#endif
+
+    if (TCG_TARGET_REG_BITS == 32 && s_bits == MO_64) {
+        if (opc & MO_BSWAP) {
+            tcg_out32(s, ADDI | TAI(TCG_REG_R0, addrlo, 4));
+            tcg_out32(s, STWBRX | SAB(datalo, rbase, addrlo));
+            tcg_out32(s, STWBRX | SAB(datahi, rbase, TCG_REG_R0));
+        } else if (rbase != 0) {
+            tcg_out32(s, ADDI | TAI(TCG_REG_R0, addrlo, 4));
+            tcg_out32(s, STWX | SAB(datahi, rbase, addrlo));
+            tcg_out32(s, STWX | SAB(datalo, rbase, TCG_REG_R0));
+        } else {
+            tcg_out32(s, STW | TAI(datahi, addrlo, 0));
+            tcg_out32(s, STW | TAI(datalo, addrlo, 4));
+        }
+    } else {
+        uint32_t insn = qemu_stx_opc[opc & (MO_BSWAP | MO_SIZE)];
+        if (!HAVE_ISA_2_06 && insn == STDBRX) {
+            tcg_out32(s, STWBRX | SAB(datalo, rbase, addrlo));
+            tcg_out32(s, ADDI | TAI(TCG_REG_TMP1, addrlo, 4));
+            tcg_out_shri64(s, TCG_REG_R0, datalo, 32);
+            tcg_out32(s, STWBRX | SAB(TCG_REG_R0, rbase, TCG_REG_TMP1));
+        } else {
+            tcg_out32(s, insn | SAB(datalo, rbase, addrlo));
+        }
+    }
+
+#ifdef CONFIG_SOFTMMU
+    add_qemu_ldst_label(s, false, oi, datalo, datahi, addrlo, addrhi,
+                        s->code_ptr, label_ptr);
+#endif
+}
+
+/* Parameters for function call generation, used in tcg.c.  */
+#define TCG_TARGET_STACK_ALIGN       16
+#define TCG_TARGET_EXTEND_ARGS       1
+
+#ifdef _CALL_AIX
+# define LINK_AREA_SIZE                (6 * SZR)
+# define LR_OFFSET                     (1 * SZR)
+# define TCG_TARGET_CALL_STACK_OFFSET  (LINK_AREA_SIZE + 8 * SZR)
+#elif defined(TCG_TARGET_CALL_DARWIN)
+# define LINK_AREA_SIZE                (6 * SZR)
+# define LR_OFFSET                     (2 * SZR)
+#elif TCG_TARGET_REG_BITS == 64
+# if defined(_CALL_ELF) && _CALL_ELF == 2
+#  define LINK_AREA_SIZE               (4 * SZR)
+#  define LR_OFFSET                    (1 * SZR)
+# endif
+#else /* TCG_TARGET_REG_BITS == 32 */
+# if defined(_CALL_SYSV)
+#  define LINK_AREA_SIZE               (2 * SZR)
+#  define LR_OFFSET                    (1 * SZR)
+# endif
+#endif
+#ifndef LR_OFFSET
+# error "Unhandled abi"
+#endif
+#ifndef TCG_TARGET_CALL_STACK_OFFSET
+# define TCG_TARGET_CALL_STACK_OFFSET  LINK_AREA_SIZE
+#endif
+
+#define CPU_TEMP_BUF_SIZE  (CPU_TEMP_BUF_NLONGS * (int)sizeof(long))
+#define REG_SAVE_SIZE      ((int)ARRAY_SIZE(tcg_target_callee_save_regs) * SZR)
+
+#define FRAME_SIZE ((TCG_TARGET_CALL_STACK_OFFSET   \
+                     + TCG_STATIC_CALL_ARGS_SIZE    \
+                     + CPU_TEMP_BUF_SIZE            \
+                     + REG_SAVE_SIZE                \
+                     + TCG_TARGET_STACK_ALIGN - 1)  \
+                    & -TCG_TARGET_STACK_ALIGN)
+
+#define REG_SAVE_BOT (FRAME_SIZE - REG_SAVE_SIZE)
+
+static void tcg_target_qemu_prologue(TCGContext *s)
+{
+    int i;
+
+#ifdef _CALL_AIX
+    void **desc = (void **)s->code_ptr;
+    desc[0] = desc + 2;                   /* entry point */
+    desc[1] = 0;                          /* environment pointer */
+    s->code_ptr = (void *)(desc + 2);     /* skip over descriptor */
+#endif
+
+    tcg_set_frame(s, TCG_REG_CALL_STACK, REG_SAVE_BOT - CPU_TEMP_BUF_SIZE,
+                  CPU_TEMP_BUF_SIZE);
+
+    /* Prologue */
+    tcg_out32(s, MFSPR | RT(TCG_REG_R0) | LR);
+    tcg_out32(s, (SZR == 8 ? STDU : STWU)
+              | SAI(TCG_REG_R1, TCG_REG_R1, -FRAME_SIZE));
+
+    for (i = 0; i < ARRAY_SIZE(tcg_target_callee_save_regs); ++i) {
+        tcg_out_st(s, TCG_TYPE_REG, tcg_target_callee_save_regs[i],
+                   TCG_REG_R1, REG_SAVE_BOT + i * SZR);
+    }
+    tcg_out_st(s, TCG_TYPE_PTR, TCG_REG_R0, TCG_REG_R1, FRAME_SIZE+LR_OFFSET);
+
+#ifdef CONFIG_USE_GUEST_BASE
+    if (GUEST_BASE) {
+        tcg_out_movi(s, TCG_TYPE_PTR, TCG_GUEST_BASE_REG, GUEST_BASE);
+        tcg_regset_set_reg(s->reserved_regs, TCG_GUEST_BASE_REG);
+    }
+#endif
+
+    tcg_out_mov(s, TCG_TYPE_PTR, TCG_AREG0, tcg_target_call_iarg_regs[0]);
+    tcg_out32(s, MTSPR | RS(tcg_target_call_iarg_regs[1]) | CTR);
+
+    if (USE_REG_RA) {
+#ifdef _CALL_AIX
+        /* Make the caller load the value as the TOC into R2.  */
+        tb_ret_addr = s->code_ptr + 2;
+        desc[1] = tb_ret_addr;
+        tcg_out_mov(s, TCG_TYPE_PTR, TCG_REG_RA, TCG_REG_R2);
+        tcg_out32(s, BCCTR | BO_ALWAYS);
+#elif defined(_CALL_ELF) && _CALL_ELF == 2
+        /* Compute from the incoming R12 value.  */
+        tb_ret_addr = s->code_ptr + 2;
+        tcg_out32(s, ADDI | TAI(TCG_REG_RA, TCG_REG_R12,
+                                tcg_ptr_byte_diff(tb_ret_addr, s->code_buf)));
+        tcg_out32(s, BCCTR | BO_ALWAYS);
+#else
+        /* Reserve max 5 insns for the constant load.  */
+        tb_ret_addr = s->code_ptr + 6;
+        tcg_out_movi(s, TCG_TYPE_PTR, TCG_REG_RA, (intptr_t)tb_ret_addr);
+        tcg_out32(s, BCCTR | BO_ALWAYS);
+        while (s->code_ptr < tb_ret_addr) {
+            tcg_out32(s, NOP);
+        }
+#endif
+    } else {
+        tcg_out32(s, BCCTR | BO_ALWAYS);
+        tb_ret_addr = s->code_ptr;
+    }
+
+    /* Epilogue */
+    assert(tb_ret_addr == s->code_ptr);
+
+    tcg_out_ld(s, TCG_TYPE_PTR, TCG_REG_R0, TCG_REG_R1, FRAME_SIZE+LR_OFFSET);
+    for (i = 0; i < ARRAY_SIZE(tcg_target_callee_save_regs); ++i) {
+        tcg_out_ld(s, TCG_TYPE_REG, tcg_target_callee_save_regs[i],
+                   TCG_REG_R1, REG_SAVE_BOT + i * SZR);
+    }
+    tcg_out32(s, MTSPR | RS(TCG_REG_R0) | LR);
+    tcg_out32(s, ADDI | TAI(TCG_REG_R1, TCG_REG_R1, FRAME_SIZE));
+    tcg_out32(s, BCLR | BO_ALWAYS);
+}
+
+static void tcg_out_op(TCGContext *s, TCGOpcode opc, const TCGArg *args,
+                       const int *const_args)
+{
+    TCGArg a0, a1, a2;
+    int c;
+
+    switch (opc) {
+    case INDEX_op_exit_tb:
+        if (USE_REG_RA) {
+            ptrdiff_t disp = tcg_pcrel_diff(s, tb_ret_addr);
+
+            /* If we can use a direct branch, otherwise use the value in RA.
+               Note that the direct branch is always forward.  If it's in
+               range now, it'll still be in range after the movi.  Don't
+               bother about the 20 bytes where the test here fails but it
+               would succeed below.  */
+            if (!in_range_b(disp)) {
+                tcg_out32(s, MTSPR | RS(TCG_REG_RA) | CTR);
+                tcg_out_movi(s, TCG_TYPE_PTR, TCG_REG_R3, args[0]);
+                tcg_out32(s, BCCTR | BO_ALWAYS);
+                break;
+            }
+        }
+        tcg_out_movi(s, TCG_TYPE_PTR, TCG_REG_R3, args[0]);
+        tcg_out_b(s, 0, tb_ret_addr);
+        break;
+    case INDEX_op_goto_tb:
+        if (s->tb_jmp_offset) {
+            /* Direct jump method.  */
+            s->tb_jmp_offset[args[0]] = tcg_current_code_size(s);
+            s->code_ptr += 7;
+        } else {
+            /* Indirect jump method.  */
+            tcg_abort();
+        }
+        s->tb_next_offset[args[0]] = tcg_current_code_size(s);
+        break;
+    case INDEX_op_br:
+        {
+            TCGLabel *l = arg_label(args[0]);
+
+            if (l->has_value) {
+                tcg_out_b(s, 0, l->u.value_ptr);
+            } else {
+                tcg_out_reloc(s, s->code_ptr, R_PPC_REL24, l, 0);
+                tcg_out_b_noaddr(s, B);
+            }
+        }
+        break;
+    case INDEX_op_ld8u_i32:
+    case INDEX_op_ld8u_i64:
+        tcg_out_mem_long(s, LBZ, LBZX, args[0], args[1], args[2]);
+        break;
+    case INDEX_op_ld8s_i32:
+    case INDEX_op_ld8s_i64:
+        tcg_out_mem_long(s, LBZ, LBZX, args[0], args[1], args[2]);
+        tcg_out32(s, EXTSB | RS(args[0]) | RA(args[0]));
+        break;
+    case INDEX_op_ld16u_i32:
+    case INDEX_op_ld16u_i64:
+        tcg_out_mem_long(s, LHZ, LHZX, args[0], args[1], args[2]);
+        break;
+    case INDEX_op_ld16s_i32:
+    case INDEX_op_ld16s_i64:
+        tcg_out_mem_long(s, LHA, LHAX, args[0], args[1], args[2]);
+        break;
+    case INDEX_op_ld_i32:
+    case INDEX_op_ld32u_i64:
+        tcg_out_mem_long(s, LWZ, LWZX, args[0], args[1], args[2]);
+        break;
+    case INDEX_op_ld32s_i64:
+        tcg_out_mem_long(s, LWA, LWAX, args[0], args[1], args[2]);
+        break;
+    case INDEX_op_ld_i64:
+        tcg_out_mem_long(s, LD, LDX, args[0], args[1], args[2]);
+        break;
+    case INDEX_op_st8_i32:
+    case INDEX_op_st8_i64:
+        tcg_out_mem_long(s, STB, STBX, args[0], args[1], args[2]);
+        break;
+    case INDEX_op_st16_i32:
+    case INDEX_op_st16_i64:
+        tcg_out_mem_long(s, STH, STHX, args[0], args[1], args[2]);
+        break;
+    case INDEX_op_st_i32:
+    case INDEX_op_st32_i64:
+        tcg_out_mem_long(s, STW, STWX, args[0], args[1], args[2]);
+        break;
+    case INDEX_op_st_i64:
+        tcg_out_mem_long(s, STD, STDX, args[0], args[1], args[2]);
+        break;
+
+    case INDEX_op_add_i32:
+        a0 = args[0], a1 = args[1], a2 = args[2];
+        if (const_args[2]) {
+        do_addi_32:
+            tcg_out_mem_long(s, ADDI, ADD, a0, a1, (int32_t)a2);
+        } else {
+            tcg_out32(s, ADD | TAB(a0, a1, a2));
+        }
+        break;
+    case INDEX_op_sub_i32:
+        a0 = args[0], a1 = args[1], a2 = args[2];
+        if (const_args[1]) {
+            if (const_args[2]) {
+                tcg_out_movi(s, TCG_TYPE_I32, a0, a1 - a2);
+            } else {
+                tcg_out32(s, SUBFIC | TAI(a0, a2, a1));
+            }
+        } else if (const_args[2]) {
+            a2 = -a2;
+            goto do_addi_32;
+        } else {
+            tcg_out32(s, SUBF | TAB(a0, a2, a1));
+        }
+        break;
+
+    case INDEX_op_and_i32:
+        a0 = args[0], a1 = args[1], a2 = args[2];
+        if (const_args[2]) {
+            tcg_out_andi32(s, a0, a1, a2);
+        } else {
+            tcg_out32(s, AND | SAB(a1, a0, a2));
+        }
+        break;
+    case INDEX_op_and_i64:
+        a0 = args[0], a1 = args[1], a2 = args[2];
+        if (const_args[2]) {
+            tcg_out_andi64(s, a0, a1, a2);
+        } else {
+            tcg_out32(s, AND | SAB(a1, a0, a2));
+        }
+        break;
+    case INDEX_op_or_i64:
+    case INDEX_op_or_i32:
+        a0 = args[0], a1 = args[1], a2 = args[2];
+        if (const_args[2]) {
+            tcg_out_ori32(s, a0, a1, a2);
+        } else {
+            tcg_out32(s, OR | SAB(a1, a0, a2));
+        }
+        break;
+    case INDEX_op_xor_i64:
+    case INDEX_op_xor_i32:
+        a0 = args[0], a1 = args[1], a2 = args[2];
+        if (const_args[2]) {
+            tcg_out_xori32(s, a0, a1, a2);
+        } else {
+            tcg_out32(s, XOR | SAB(a1, a0, a2));
+        }
+        break;
+    case INDEX_op_andc_i32:
+        a0 = args[0], a1 = args[1], a2 = args[2];
+        if (const_args[2]) {
+            tcg_out_andi32(s, a0, a1, ~a2);
+        } else {
+            tcg_out32(s, ANDC | SAB(a1, a0, a2));
+        }
+        break;
+    case INDEX_op_andc_i64:
+        a0 = args[0], a1 = args[1], a2 = args[2];
+        if (const_args[2]) {
+            tcg_out_andi64(s, a0, a1, ~a2);
+        } else {
+            tcg_out32(s, ANDC | SAB(a1, a0, a2));
+        }
+        break;
+    case INDEX_op_orc_i32:
+        if (const_args[2]) {
+            tcg_out_ori32(s, args[0], args[1], ~args[2]);
+            break;
+        }
+        /* FALLTHRU */
+    case INDEX_op_orc_i64:
+        tcg_out32(s, ORC | SAB(args[1], args[0], args[2]));
+        break;
+    case INDEX_op_eqv_i32:
+        if (const_args[2]) {
+            tcg_out_xori32(s, args[0], args[1], ~args[2]);
+            break;
+        }
+        /* FALLTHRU */
+    case INDEX_op_eqv_i64:
+        tcg_out32(s, EQV | SAB(args[1], args[0], args[2]));
+        break;
+    case INDEX_op_nand_i32:
+    case INDEX_op_nand_i64:
+        tcg_out32(s, NAND | SAB(args[1], args[0], args[2]));
+        break;
+    case INDEX_op_nor_i32:
+    case INDEX_op_nor_i64:
+        tcg_out32(s, NOR | SAB(args[1], args[0], args[2]));
+        break;
+
+    case INDEX_op_mul_i32:
+        a0 = args[0], a1 = args[1], a2 = args[2];
+        if (const_args[2]) {
+            tcg_out32(s, MULLI | TAI(a0, a1, a2));
+        } else {
+            tcg_out32(s, MULLW | TAB(a0, a1, a2));
+        }
+        break;
+
+    case INDEX_op_div_i32:
+        tcg_out32(s, DIVW | TAB(args[0], args[1], args[2]));
+        break;
+
+    case INDEX_op_divu_i32:
+        tcg_out32(s, DIVWU | TAB(args[0], args[1], args[2]));
+        break;
+
+    case INDEX_op_shl_i32:
+        if (const_args[2]) {
+            tcg_out_shli32(s, args[0], args[1], args[2]);
+        } else {
+            tcg_out32(s, SLW | SAB(args[1], args[0], args[2]));
+        }
+        break;
+    case INDEX_op_shr_i32:
+        if (const_args[2]) {
+            tcg_out_shri32(s, args[0], args[1], args[2]);
+        } else {
+            tcg_out32(s, SRW | SAB(args[1], args[0], args[2]));
+        }
+        break;
+    case INDEX_op_sar_i32:
+        if (const_args[2]) {
+            tcg_out32(s, SRAWI | RS(args[1]) | RA(args[0]) | SH(args[2]));
+        } else {
+            tcg_out32(s, SRAW | SAB(args[1], args[0], args[2]));
+        }
+        break;
+    case INDEX_op_rotl_i32:
+        if (const_args[2]) {
+            tcg_out_rlw(s, RLWINM, args[0], args[1], args[2], 0, 31);
+        } else {
+            tcg_out32(s, RLWNM | SAB(args[1], args[0], args[2])
+                         | MB(0) | ME(31));
+        }
+        break;
+    case INDEX_op_rotr_i32:
+        if (const_args[2]) {
+            tcg_out_rlw(s, RLWINM, args[0], args[1], 32 - args[2], 0, 31);
+        } else {
+            tcg_out32(s, SUBFIC | TAI(TCG_REG_R0, args[2], 32));
+            tcg_out32(s, RLWNM | SAB(args[1], args[0], TCG_REG_R0)
+                         | MB(0) | ME(31));
+        }
+        break;
+
+    case INDEX_op_brcond_i32:
+        tcg_out_brcond(s, args[2], args[0], args[1], const_args[1],
+                       arg_label(args[3]), TCG_TYPE_I32);
+        break;
+    case INDEX_op_brcond_i64:
+        tcg_out_brcond(s, args[2], args[0], args[1], const_args[1],
+                       arg_label(args[3]), TCG_TYPE_I64);
+        break;
+    case INDEX_op_brcond2_i32:
+        tcg_out_brcond2(s, args, const_args);
+        break;
+
+    case INDEX_op_neg_i32:
+    case INDEX_op_neg_i64:
+        tcg_out32(s, NEG | RT(args[0]) | RA(args[1]));
+        break;
+
+    case INDEX_op_not_i32:
+    case INDEX_op_not_i64:
+        tcg_out32(s, NOR | SAB(args[1], args[0], args[1]));
+        break;
+
+    case INDEX_op_add_i64:
+        a0 = args[0], a1 = args[1], a2 = args[2];
+        if (const_args[2]) {
+        do_addi_64:
+            tcg_out_mem_long(s, ADDI, ADD, a0, a1, a2);
+        } else {
+            tcg_out32(s, ADD | TAB(a0, a1, a2));
+        }
+        break;
+    case INDEX_op_sub_i64:
+        a0 = args[0], a1 = args[1], a2 = args[2];
+        if (const_args[1]) {
+            if (const_args[2]) {
+                tcg_out_movi(s, TCG_TYPE_I64, a0, a1 - a2);
+            } else {
+                tcg_out32(s, SUBFIC | TAI(a0, a2, a1));
+            }
+        } else if (const_args[2]) {
+            a2 = -a2;
+            goto do_addi_64;
+        } else {
+            tcg_out32(s, SUBF | TAB(a0, a2, a1));
+        }
+        break;
+
+    case INDEX_op_shl_i64:
+        if (const_args[2]) {
+            tcg_out_shli64(s, args[0], args[1], args[2]);
+        } else {
+            tcg_out32(s, SLD | SAB(args[1], args[0], args[2]));
+        }
+        break;
+    case INDEX_op_shr_i64:
+        if (const_args[2]) {
+            tcg_out_shri64(s, args[0], args[1], args[2]);
+        } else {
+            tcg_out32(s, SRD | SAB(args[1], args[0], args[2]));
+        }
+        break;
+    case INDEX_op_sar_i64:
+        if (const_args[2]) {
+            int sh = SH(args[2] & 0x1f) | (((args[2] >> 5) & 1) << 1);
+            tcg_out32(s, SRADI | RA(args[0]) | RS(args[1]) | sh);
+        } else {
+            tcg_out32(s, SRAD | SAB(args[1], args[0], args[2]));
+        }
+        break;
+    case INDEX_op_rotl_i64:
+        if (const_args[2]) {
+            tcg_out_rld(s, RLDICL, args[0], args[1], args[2], 0);
+        } else {
+            tcg_out32(s, RLDCL | SAB(args[1], args[0], args[2]) | MB64(0));
+        }
+        break;
+    case INDEX_op_rotr_i64:
+        if (const_args[2]) {
+            tcg_out_rld(s, RLDICL, args[0], args[1], 64 - args[2], 0);
+        } else {
+            tcg_out32(s, SUBFIC | TAI(TCG_REG_R0, args[2], 64));
+            tcg_out32(s, RLDCL | SAB(args[1], args[0], TCG_REG_R0) | MB64(0));
+        }
+        break;
+
+    case INDEX_op_mul_i64:
+        a0 = args[0], a1 = args[1], a2 = args[2];
+        if (const_args[2]) {
+            tcg_out32(s, MULLI | TAI(a0, a1, a2));
+        } else {
+            tcg_out32(s, MULLD | TAB(a0, a1, a2));
+        }
+        break;
+    case INDEX_op_div_i64:
+        tcg_out32(s, DIVD | TAB(args[0], args[1], args[2]));
+        break;
+    case INDEX_op_divu_i64:
+        tcg_out32(s, DIVDU | TAB(args[0], args[1], args[2]));
+        break;
+
+    case INDEX_op_qemu_ld_i32:
+        tcg_out_qemu_ld(s, args, false);
+        break;
+    case INDEX_op_qemu_ld_i64:
+        tcg_out_qemu_ld(s, args, true);
+        break;
+    case INDEX_op_qemu_st_i32:
+        tcg_out_qemu_st(s, args, false);
+        break;
+    case INDEX_op_qemu_st_i64:
+        tcg_out_qemu_st(s, args, true);
+        break;
+
+    case INDEX_op_ext8s_i32:
+    case INDEX_op_ext8s_i64:
+        c = EXTSB;
+        goto gen_ext;
+    case INDEX_op_ext16s_i32:
+    case INDEX_op_ext16s_i64:
+        c = EXTSH;
+        goto gen_ext;
+    case INDEX_op_ext32s_i64:
+        c = EXTSW;
+        goto gen_ext;
+    gen_ext:
+        tcg_out32(s, c | RS(args[1]) | RA(args[0]));
+        break;
+
+    case INDEX_op_setcond_i32:
+        tcg_out_setcond(s, TCG_TYPE_I32, args[3], args[0], args[1], args[2],
+                        const_args[2]);
+        break;
+    case INDEX_op_setcond_i64:
+        tcg_out_setcond(s, TCG_TYPE_I64, args[3], args[0], args[1], args[2],
+                        const_args[2]);
+        break;
+    case INDEX_op_setcond2_i32:
+        tcg_out_setcond2(s, args, const_args);
+        break;
+
+    case INDEX_op_bswap16_i32:
+    case INDEX_op_bswap16_i64:
+        a0 = args[0], a1 = args[1];
+        /* a1 = abcd */
+        if (a0 != a1) {
+            /* a0 = (a1 r<< 24) & 0xff # 000c */
+            tcg_out_rlw(s, RLWINM, a0, a1, 24, 24, 31);
+            /* a0 = (a0 & ~0xff00) | (a1 r<< 8) & 0xff00 # 00dc */
+            tcg_out_rlw(s, RLWIMI, a0, a1, 8, 16, 23);
+        } else {
+            /* r0 = (a1 r<< 8) & 0xff00 # 00d0 */
+            tcg_out_rlw(s, RLWINM, TCG_REG_R0, a1, 8, 16, 23);
+            /* a0 = (a1 r<< 24) & 0xff # 000c */
+            tcg_out_rlw(s, RLWINM, a0, a1, 24, 24, 31);
+            /* a0 = a0 | r0 # 00dc */
+            tcg_out32(s, OR | SAB(TCG_REG_R0, a0, a0));
+        }
+        break;
+
+    case INDEX_op_bswap32_i32:
+    case INDEX_op_bswap32_i64:
+        /* Stolen from gcc's builtin_bswap32 */
+        a1 = args[1];
+        a0 = args[0] == a1 ? TCG_REG_R0 : args[0];
+
+        /* a1 = args[1] # abcd */
+        /* a0 = rotate_left (a1, 8) # bcda */
+        tcg_out_rlw(s, RLWINM, a0, a1, 8, 0, 31);
+        /* a0 = (a0 & ~0xff000000) | ((a1 r<< 24) & 0xff000000) # dcda */
+        tcg_out_rlw(s, RLWIMI, a0, a1, 24, 0, 7);
+        /* a0 = (a0 & ~0x0000ff00) | ((a1 r<< 24) & 0x0000ff00) # dcba */
+        tcg_out_rlw(s, RLWIMI, a0, a1, 24, 16, 23);
+
+        if (a0 == TCG_REG_R0) {
+            tcg_out_mov(s, TCG_TYPE_REG, args[0], a0);
+        }
+        break;
+
+    case INDEX_op_bswap64_i64:
+        a0 = args[0], a1 = args[1], a2 = TCG_REG_R0;
+        if (a0 == a1) {
+            a0 = TCG_REG_R0;
+            a2 = a1;
+        }
+
+        /* a1 = # abcd efgh */
+        /* a0 = rl32(a1, 8) # 0000 fghe */
+        tcg_out_rlw(s, RLWINM, a0, a1, 8, 0, 31);
+        /* a0 = dep(a0, rl32(a1, 24), 0xff000000) # 0000 hghe */
+        tcg_out_rlw(s, RLWIMI, a0, a1, 24, 0, 7);
+        /* a0 = dep(a0, rl32(a1, 24), 0x0000ff00) # 0000 hgfe */
+        tcg_out_rlw(s, RLWIMI, a0, a1, 24, 16, 23);
+
+        /* a0 = rl64(a0, 32) # hgfe 0000 */
+        /* a2 = rl64(a1, 32) # efgh abcd */
+        tcg_out_rld(s, RLDICL, a0, a0, 32, 0);
+        tcg_out_rld(s, RLDICL, a2, a1, 32, 0);
+
+        /* a0 = dep(a0, rl32(a2, 8), 0xffffffff)  # hgfe bcda */
+        tcg_out_rlw(s, RLWIMI, a0, a2, 8, 0, 31);
+        /* a0 = dep(a0, rl32(a2, 24), 0xff000000) # hgfe dcda */
+        tcg_out_rlw(s, RLWIMI, a0, a2, 24, 0, 7);
+        /* a0 = dep(a0, rl32(a2, 24), 0x0000ff00) # hgfe dcba */
+        tcg_out_rlw(s, RLWIMI, a0, a2, 24, 16, 23);
+
+        if (a0 == 0) {
+            tcg_out_mov(s, TCG_TYPE_REG, args[0], a0);
+        }
+        break;
+
+    case INDEX_op_deposit_i32:
+        if (const_args[2]) {
+            uint32_t mask = ((2u << (args[4] - 1)) - 1) << args[3];
+            tcg_out_andi32(s, args[0], args[0], ~mask);
+        } else {
+            tcg_out_rlw(s, RLWIMI, args[0], args[2], args[3],
+                        32 - args[3] - args[4], 31 - args[3]);
+        }
+        break;
+    case INDEX_op_deposit_i64:
+        if (const_args[2]) {
+            uint64_t mask = ((2ull << (args[4] - 1)) - 1) << args[3];
+            tcg_out_andi64(s, args[0], args[0], ~mask);
+        } else {
+            tcg_out_rld(s, RLDIMI, args[0], args[2], args[3],
+                        64 - args[3] - args[4]);
+        }
+        break;
+
+    case INDEX_op_movcond_i32:
+        tcg_out_movcond(s, TCG_TYPE_I32, args[5], args[0], args[1], args[2],
+                        args[3], args[4], const_args[2]);
+        break;
+    case INDEX_op_movcond_i64:
+        tcg_out_movcond(s, TCG_TYPE_I64, args[5], args[0], args[1], args[2],
+                        args[3], args[4], const_args[2]);
+        break;
+
+#if TCG_TARGET_REG_BITS == 64
+    case INDEX_op_add2_i64:
+#else
+    case INDEX_op_add2_i32:
+#endif
+        /* Note that the CA bit is defined based on the word size of the
+           environment.  So in 64-bit mode it's always carry-out of bit 63.
+           The fallback code using deposit works just as well for 32-bit.  */
+        a0 = args[0], a1 = args[1];
+        if (a0 == args[3] || (!const_args[5] && a0 == args[5])) {
+            a0 = TCG_REG_R0;
+        }
+        if (const_args[4]) {
+            tcg_out32(s, ADDIC | TAI(a0, args[2], args[4]));
+        } else {
+            tcg_out32(s, ADDC | TAB(a0, args[2], args[4]));
+        }
+        if (const_args[5]) {
+            tcg_out32(s, (args[5] ? ADDME : ADDZE) | RT(a1) | RA(args[3]));
+        } else {
+            tcg_out32(s, ADDE | TAB(a1, args[3], args[5]));
+        }
+        if (a0 != args[0]) {
+            tcg_out_mov(s, TCG_TYPE_REG, args[0], a0);
+        }
+        break;
+
+#if TCG_TARGET_REG_BITS == 64
+    case INDEX_op_sub2_i64:
+#else
+    case INDEX_op_sub2_i32:
+#endif
+        a0 = args[0], a1 = args[1];
+        if (a0 == args[5] || (!const_args[3] && a0 == args[3])) {
+            a0 = TCG_REG_R0;
+        }
+        if (const_args[2]) {
+            tcg_out32(s, SUBFIC | TAI(a0, args[4], args[2]));
+        } else {
+            tcg_out32(s, SUBFC | TAB(a0, args[4], args[2]));
+        }
+        if (const_args[3]) {
+            tcg_out32(s, (args[3] ? SUBFME : SUBFZE) | RT(a1) | RA(args[5]));
+        } else {
+            tcg_out32(s, SUBFE | TAB(a1, args[5], args[3]));
+        }
+        if (a0 != args[0]) {
+            tcg_out_mov(s, TCG_TYPE_REG, args[0], a0);
+        }
+        break;
+
+    case INDEX_op_muluh_i32:
+        tcg_out32(s, MULHWU | TAB(args[0], args[1], args[2]));
+        break;
+    case INDEX_op_mulsh_i32:
+        tcg_out32(s, MULHW | TAB(args[0], args[1], args[2]));
+        break;
+    case INDEX_op_muluh_i64:
+        tcg_out32(s, MULHDU | TAB(args[0], args[1], args[2]));
+        break;
+    case INDEX_op_mulsh_i64:
+        tcg_out32(s, MULHD | TAB(args[0], args[1], args[2]));
+        break;
+
+    case INDEX_op_mov_i32:   /* Always emitted via tcg_out_mov.  */
+    case INDEX_op_mov_i64:
+    case INDEX_op_movi_i32:  /* Always emitted via tcg_out_movi.  */
+    case INDEX_op_movi_i64:
+    case INDEX_op_call:      /* Always emitted via tcg_out_call.  */
+    default:
+        tcg_abort();
+    }
+}
+
+static const TCGTargetOpDef ppc_op_defs[] = {
+    { INDEX_op_exit_tb, { } },
+    { INDEX_op_goto_tb, { } },
+    { INDEX_op_br, { } },
+
+    { INDEX_op_ld8u_i32, { "r", "r" } },
+    { INDEX_op_ld8s_i32, { "r", "r" } },
+    { INDEX_op_ld16u_i32, { "r", "r" } },
+    { INDEX_op_ld16s_i32, { "r", "r" } },
+    { INDEX_op_ld_i32, { "r", "r" } },
+
+    { INDEX_op_st8_i32, { "r", "r" } },
+    { INDEX_op_st16_i32, { "r", "r" } },
+    { INDEX_op_st_i32, { "r", "r" } },
+
+    { INDEX_op_add_i32, { "r", "r", "ri" } },
+    { INDEX_op_mul_i32, { "r", "r", "rI" } },
+    { INDEX_op_div_i32, { "r", "r", "r" } },
+    { INDEX_op_divu_i32, { "r", "r", "r" } },
+    { INDEX_op_sub_i32, { "r", "rI", "ri" } },
+    { INDEX_op_and_i32, { "r", "r", "ri" } },
+    { INDEX_op_or_i32, { "r", "r", "ri" } },
+    { INDEX_op_xor_i32, { "r", "r", "ri" } },
+    { INDEX_op_andc_i32, { "r", "r", "ri" } },
+    { INDEX_op_orc_i32, { "r", "r", "ri" } },
+    { INDEX_op_eqv_i32, { "r", "r", "ri" } },
+    { INDEX_op_nand_i32, { "r", "r", "r" } },
+    { INDEX_op_nor_i32, { "r", "r", "r" } },
+
+    { INDEX_op_shl_i32, { "r", "r", "ri" } },
+    { INDEX_op_shr_i32, { "r", "r", "ri" } },
+    { INDEX_op_sar_i32, { "r", "r", "ri" } },
+    { INDEX_op_rotl_i32, { "r", "r", "ri" } },
+    { INDEX_op_rotr_i32, { "r", "r", "ri" } },
+
+    { INDEX_op_neg_i32, { "r", "r" } },
+    { INDEX_op_not_i32, { "r", "r" } },
+    { INDEX_op_ext8s_i32, { "r", "r" } },
+    { INDEX_op_ext16s_i32, { "r", "r" } },
+    { INDEX_op_bswap16_i32, { "r", "r" } },
+    { INDEX_op_bswap32_i32, { "r", "r" } },
+
+    { INDEX_op_brcond_i32, { "r", "ri" } },
+    { INDEX_op_setcond_i32, { "r", "r", "ri" } },
+    { INDEX_op_movcond_i32, { "r", "r", "ri", "rZ", "rZ" } },
+
+    { INDEX_op_deposit_i32, { "r", "0", "rZ" } },
+
+    { INDEX_op_muluh_i32, { "r", "r", "r" } },
+    { INDEX_op_mulsh_i32, { "r", "r", "r" } },
+
+#if TCG_TARGET_REG_BITS == 64
+    { INDEX_op_ld8u_i64, { "r", "r" } },
+    { INDEX_op_ld8s_i64, { "r", "r" } },
+    { INDEX_op_ld16u_i64, { "r", "r" } },
+    { INDEX_op_ld16s_i64, { "r", "r" } },
+    { INDEX_op_ld32u_i64, { "r", "r" } },
+    { INDEX_op_ld32s_i64, { "r", "r" } },
+    { INDEX_op_ld_i64, { "r", "r" } },
+
+    { INDEX_op_st8_i64, { "r", "r" } },
+    { INDEX_op_st16_i64, { "r", "r" } },
+    { INDEX_op_st32_i64, { "r", "r" } },
+    { INDEX_op_st_i64, { "r", "r" } },
+
+    { INDEX_op_add_i64, { "r", "r", "rT" } },
+    { INDEX_op_sub_i64, { "r", "rI", "rT" } },
+    { INDEX_op_and_i64, { "r", "r", "ri" } },
+    { INDEX_op_or_i64, { "r", "r", "rU" } },
+    { INDEX_op_xor_i64, { "r", "r", "rU" } },
+    { INDEX_op_andc_i64, { "r", "r", "ri" } },
+    { INDEX_op_orc_i64, { "r", "r", "r" } },
+    { INDEX_op_eqv_i64, { "r", "r", "r" } },
+    { INDEX_op_nand_i64, { "r", "r", "r" } },
+    { INDEX_op_nor_i64, { "r", "r", "r" } },
+
+    { INDEX_op_shl_i64, { "r", "r", "ri" } },
+    { INDEX_op_shr_i64, { "r", "r", "ri" } },
+    { INDEX_op_sar_i64, { "r", "r", "ri" } },
+    { INDEX_op_rotl_i64, { "r", "r", "ri" } },
+    { INDEX_op_rotr_i64, { "r", "r", "ri" } },
+
+    { INDEX_op_mul_i64, { "r", "r", "rI" } },
+    { INDEX_op_div_i64, { "r", "r", "r" } },
+    { INDEX_op_divu_i64, { "r", "r", "r" } },
+
+    { INDEX_op_neg_i64, { "r", "r" } },
+    { INDEX_op_not_i64, { "r", "r" } },
+    { INDEX_op_ext8s_i64, { "r", "r" } },
+    { INDEX_op_ext16s_i64, { "r", "r" } },
+    { INDEX_op_ext32s_i64, { "r", "r" } },
+    { INDEX_op_bswap16_i64, { "r", "r" } },
+    { INDEX_op_bswap32_i64, { "r", "r" } },
+    { INDEX_op_bswap64_i64, { "r", "r" } },
+
+    { INDEX_op_brcond_i64, { "r", "ri" } },
+    { INDEX_op_setcond_i64, { "r", "r", "ri" } },
+    { INDEX_op_movcond_i64, { "r", "r", "ri", "rZ", "rZ" } },
+
+    { INDEX_op_deposit_i64, { "r", "0", "rZ" } },
+
+    { INDEX_op_mulsh_i64, { "r", "r", "r" } },
+    { INDEX_op_muluh_i64, { "r", "r", "r" } },
+#endif
+
+#if TCG_TARGET_REG_BITS == 32
+    { INDEX_op_brcond2_i32, { "r", "r", "ri", "ri" } },
+    { INDEX_op_setcond2_i32, { "r", "r", "r", "ri", "ri" } },
+#endif
+
+#if TCG_TARGET_REG_BITS == 64
+    { INDEX_op_add2_i64, { "r", "r", "r", "r", "rI", "rZM" } },
+    { INDEX_op_sub2_i64, { "r", "r", "rI", "rZM", "r", "r" } },
+#else
+    { INDEX_op_add2_i32, { "r", "r", "r", "r", "rI", "rZM" } },
+    { INDEX_op_sub2_i32, { "r", "r", "rI", "rZM", "r", "r" } },
+#endif
+
+#if TCG_TARGET_REG_BITS == 64
+    { INDEX_op_qemu_ld_i32, { "r", "L" } },
+    { INDEX_op_qemu_st_i32, { "S", "S" } },
+    { INDEX_op_qemu_ld_i64, { "r", "L" } },
+    { INDEX_op_qemu_st_i64, { "S", "S" } },
+#elif TARGET_LONG_BITS == 32
+    { INDEX_op_qemu_ld_i32, { "r", "L" } },
+    { INDEX_op_qemu_st_i32, { "S", "S" } },
+    { INDEX_op_qemu_ld_i64, { "L", "L", "L" } },
+    { INDEX_op_qemu_st_i64, { "S", "S", "S" } },
+#else
+    { INDEX_op_qemu_ld_i32, { "r", "L", "L" } },
+    { INDEX_op_qemu_st_i32, { "S", "S", "S" } },
+    { INDEX_op_qemu_ld_i64, { "L", "L", "L", "L" } },
+    { INDEX_op_qemu_st_i64, { "S", "S", "S", "S" } },
+#endif
+
+    { -1 },
+};
+
+static void tcg_target_init(TCGContext *s)
+{
+    unsigned long hwcap = qemu_getauxval(AT_HWCAP);
+    if (hwcap & PPC_FEATURE_ARCH_2_06) {
+        have_isa_2_06 = true;
+    }
+
+    tcg_regset_set32(tcg_target_available_regs[TCG_TYPE_I32], 0, 0xffffffff);
+    tcg_regset_set32(tcg_target_available_regs[TCG_TYPE_I64], 0, 0xffffffff);
+    tcg_regset_set32(tcg_target_call_clobber_regs, 0,
+                     (1 << TCG_REG_R0) |
+                     (1 << TCG_REG_R2) |
+                     (1 << TCG_REG_R3) |
+                     (1 << TCG_REG_R4) |
+                     (1 << TCG_REG_R5) |
+                     (1 << TCG_REG_R6) |
+                     (1 << TCG_REG_R7) |
+                     (1 << TCG_REG_R8) |
+                     (1 << TCG_REG_R9) |
+                     (1 << TCG_REG_R10) |
+                     (1 << TCG_REG_R11) |
+                     (1 << TCG_REG_R12));
+
+    tcg_regset_clear(s->reserved_regs);
+    tcg_regset_set_reg(s->reserved_regs, TCG_REG_R0); /* tcg temp */
+    tcg_regset_set_reg(s->reserved_regs, TCG_REG_R1); /* stack pointer */
+#if defined(_CALL_SYSV)
+    tcg_regset_set_reg(s->reserved_regs, TCG_REG_R2); /* toc pointer */
+#endif
+#if defined(_CALL_SYSV) || TCG_TARGET_REG_BITS == 64
+    tcg_regset_set_reg(s->reserved_regs, TCG_REG_R13); /* thread pointer */
+#endif
+    tcg_regset_set_reg(s->reserved_regs, TCG_REG_TMP1); /* mem temp */
+    if (USE_REG_RA) {
+        tcg_regset_set_reg(s->reserved_regs, TCG_REG_RA);  /* return addr */
+    }
+
+    tcg_add_target_add_op_defs(ppc_op_defs);
+}
+
+#ifdef __ELF__
+typedef struct {
+    DebugFrameCIE cie;
+    DebugFrameFDEHeader fde;
+    uint8_t fde_def_cfa[4];
+    uint8_t fde_reg_ofs[ARRAY_SIZE(tcg_target_callee_save_regs) * 2 + 3];
+} DebugFrame;
+
+/* We're expecting a 2 byte uleb128 encoded value.  */
+QEMU_BUILD_BUG_ON(FRAME_SIZE >= (1 << 14));
+
+#if TCG_TARGET_REG_BITS == 64
+# define ELF_HOST_MACHINE EM_PPC64
+#else
+# define ELF_HOST_MACHINE EM_PPC
+#endif
+
+static DebugFrame debug_frame = {
+    .cie.len = sizeof(DebugFrameCIE)-4, /* length after .len member */
+    .cie.id = -1,
+    .cie.version = 1,
+    .cie.code_align = 1,
+    .cie.data_align = (-SZR & 0x7f),         /* sleb128 -SZR */
+    .cie.return_column = 65,
+
+    /* Total FDE size does not include the "len" member.  */
+    .fde.len = sizeof(DebugFrame) - offsetof(DebugFrame, fde.cie_offset),
+
+    .fde_def_cfa = {
+        12, TCG_REG_R1,                 /* DW_CFA_def_cfa r1, ... */
+        (FRAME_SIZE & 0x7f) | 0x80,     /* ... uleb128 FRAME_SIZE */
+        (FRAME_SIZE >> 7)
+    },
+    .fde_reg_ofs = {
+        /* DW_CFA_offset_extended_sf, lr, LR_OFFSET */
+        0x11, 65, (LR_OFFSET / -SZR) & 0x7f,
+    }
+};
+
+void tcg_register_jit(void *buf, size_t buf_size)
+{
+    uint8_t *p = &debug_frame.fde_reg_ofs[3];
+    int i;
+
+    for (i = 0; i < ARRAY_SIZE(tcg_target_callee_save_regs); ++i, p += 2) {
+        p[0] = 0x80 + tcg_target_callee_save_regs[i];
+        p[1] = (FRAME_SIZE - (REG_SAVE_BOT + i * SZR)) / SZR;
+    }
+
+    debug_frame.fde.func_start = (uintptr_t)buf;
+    debug_frame.fde.func_len = buf_size;
+
+    tcg_register_jit_int(buf, buf_size, &debug_frame, sizeof(debug_frame));
+}
+#endif /* __ELF__ */
+
+static size_t dcache_bsize = 16;
+static size_t icache_bsize = 16;
+
+void flush_icache_range(uintptr_t start, uintptr_t stop)
+{
+    uintptr_t p, start1, stop1;
+    size_t dsize = dcache_bsize;
+    size_t isize = icache_bsize;
+
+    start1 = start & ~(dsize - 1);
+    stop1 = (stop + dsize - 1) & ~(dsize - 1);
+    for (p = start1; p < stop1; p += dsize) {
+        asm volatile ("dcbst 0,%0" : : "r"(p) : "memory");
+    }
+    asm volatile ("sync" : : : "memory");
+
+    start &= start & ~(isize - 1);
+    stop1 = (stop + isize - 1) & ~(isize - 1);
+    for (p = start1; p < stop1; p += isize) {
+        asm volatile ("icbi 0,%0" : : "r"(p) : "memory");
+    }
+    asm volatile ("sync" : : : "memory");
+    asm volatile ("isync" : : : "memory");
+}
+
+#if defined _AIX
+#include <sys/systemcfg.h>
+
+static void __attribute__((constructor)) tcg_cache_init(void)
+{
+    icache_bsize = _system_configuration.icache_line;
+    dcache_bsize = _system_configuration.dcache_line;
+}
+
+#elif defined __linux__
+static void __attribute__((constructor)) tcg_cache_init(void)
+{
+    unsigned long dsize = qemu_getauxval(AT_DCACHEBSIZE);
+    unsigned long isize = qemu_getauxval(AT_ICACHEBSIZE);
+
+    if (dsize == 0 || isize == 0) {
+        if (dsize == 0) {
+            fprintf(stderr, "getauxval AT_DCACHEBSIZE failed\n");
+        }
+        if (isize == 0) {
+            fprintf(stderr, "getauxval AT_ICACHEBSIZE failed\n");
+        }
+        exit(1);
+    }
+    dcache_bsize = dsize;
+    icache_bsize = isize;
+}
+
+#elif defined __APPLE__
+#include <stdio.h>
+#include <sys/types.h>
+#include <sys/sysctl.h>
+
+static void __attribute__((constructor)) tcg_cache_init(void)
+{
+    size_t len;
+    unsigned cacheline;
+    int name[2] = { CTL_HW, HW_CACHELINE };
+
+    len = sizeof(cacheline);
+    if (sysctl(name, 2, &cacheline, &len, NULL, 0)) {
+        perror("sysctl CTL_HW HW_CACHELINE failed");
+        exit(1);
+    }
+    dcache_bsize = cacheline;
+    icache_bsize = cacheline;
+}
+
+#elif defined(__FreeBSD__) || defined(__FreeBSD_kernel__)
+#include <errno.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/types.h>
+#include <sys/sysctl.h>
+
+static void __attribute__((constructor)) tcg_cache_init(void)
+{
+    size_t len = 4;
+    unsigned cacheline;
+
+    if (sysctlbyname ("machdep.cacheline_size", &cacheline, &len, NULL, 0)) {
+        fprintf(stderr, "sysctlbyname machdep.cacheline_size failed: %s\n",
+                strerror(errno));
+        exit(1);
+    }
+    dcache_bsize = cacheline;
+    icache_bsize = cacheline;
+}
+#endif
diff --git a/tcg/ppc/tcg-target.h b/tcg/ppc/tcg-target.h
new file mode 100644
index 00000000..7ce70488
--- /dev/null
+++ b/tcg/ppc/tcg-target.h
@@ -0,0 +1,112 @@
+/*
+ * Tiny Code Generator for QEMU
+ *
+ * Copyright (c) 2008 Fabrice Bellard
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (the "Software"), to deal
+ * in the Software without restriction, including without limitation the rights
+ * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+ * copies of the Software, and to permit persons to whom the Software is
+ * furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+ * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+ * THE SOFTWARE.
+ */
+#ifndef TCG_TARGET_PPC64 
+#define TCG_TARGET_PPC64 1
+
+#ifdef _ARCH_PPC64
+# define TCG_TARGET_REG_BITS  64
+#else
+# define TCG_TARGET_REG_BITS  32
+#endif
+
+#define TCG_TARGET_NB_REGS 32
+#define TCG_TARGET_INSN_UNIT_SIZE 4
+#define TCG_TARGET_TLB_DISPLACEMENT_BITS 16
+
+typedef enum {
+    TCG_REG_R0,  TCG_REG_R1,  TCG_REG_R2,  TCG_REG_R3,
+    TCG_REG_R4,  TCG_REG_R5,  TCG_REG_R6,  TCG_REG_R7,
+    TCG_REG_R8,  TCG_REG_R9,  TCG_REG_R10, TCG_REG_R11,
+    TCG_REG_R12, TCG_REG_R13, TCG_REG_R14, TCG_REG_R15,
+    TCG_REG_R16, TCG_REG_R17, TCG_REG_R18, TCG_REG_R19,
+    TCG_REG_R20, TCG_REG_R21, TCG_REG_R22, TCG_REG_R23,
+    TCG_REG_R24, TCG_REG_R25, TCG_REG_R26, TCG_REG_R27,
+    TCG_REG_R28, TCG_REG_R29, TCG_REG_R30, TCG_REG_R31,
+
+    TCG_REG_CALL_STACK = TCG_REG_R1,
+    TCG_AREG0 = TCG_REG_R27
+} TCGReg;
+
+/* optional instructions automatically implemented */
+#define TCG_TARGET_HAS_ext8u_i32        0 /* andi */
+#define TCG_TARGET_HAS_ext16u_i32       0
+
+/* optional instructions */
+#define TCG_TARGET_HAS_div_i32          1
+#define TCG_TARGET_HAS_rem_i32          0
+#define TCG_TARGET_HAS_rot_i32          1
+#define TCG_TARGET_HAS_ext8s_i32        1
+#define TCG_TARGET_HAS_ext16s_i32       1
+#define TCG_TARGET_HAS_bswap16_i32      1
+#define TCG_TARGET_HAS_bswap32_i32      1
+#define TCG_TARGET_HAS_not_i32          1
+#define TCG_TARGET_HAS_neg_i32          1
+#define TCG_TARGET_HAS_andc_i32         1
+#define TCG_TARGET_HAS_orc_i32          1
+#define TCG_TARGET_HAS_eqv_i32          1
+#define TCG_TARGET_HAS_nand_i32         1
+#define TCG_TARGET_HAS_nor_i32          1
+#define TCG_TARGET_HAS_deposit_i32      1
+#define TCG_TARGET_HAS_movcond_i32      1
+#define TCG_TARGET_HAS_mulu2_i32        0
+#define TCG_TARGET_HAS_muls2_i32        0
+#define TCG_TARGET_HAS_muluh_i32        1
+#define TCG_TARGET_HAS_mulsh_i32        1
+
+#if TCG_TARGET_REG_BITS == 64
+#define TCG_TARGET_HAS_add2_i32         0
+#define TCG_TARGET_HAS_sub2_i32         0
+#define TCG_TARGET_HAS_trunc_shr_i32    0
+#define TCG_TARGET_HAS_div_i64          1
+#define TCG_TARGET_HAS_rem_i64          0
+#define TCG_TARGET_HAS_rot_i64          1
+#define TCG_TARGET_HAS_ext8s_i64        1
+#define TCG_TARGET_HAS_ext16s_i64       1
+#define TCG_TARGET_HAS_ext32s_i64       1
+#define TCG_TARGET_HAS_ext8u_i64        0
+#define TCG_TARGET_HAS_ext16u_i64       0
+#define TCG_TARGET_HAS_ext32u_i64       0
+#define TCG_TARGET_HAS_bswap16_i64      1
+#define TCG_TARGET_HAS_bswap32_i64      1
+#define TCG_TARGET_HAS_bswap64_i64      1
+#define TCG_TARGET_HAS_not_i64          1
+#define TCG_TARGET_HAS_neg_i64          1
+#define TCG_TARGET_HAS_andc_i64         1
+#define TCG_TARGET_HAS_orc_i64          1
+#define TCG_TARGET_HAS_eqv_i64          1
+#define TCG_TARGET_HAS_nand_i64         1
+#define TCG_TARGET_HAS_nor_i64          1
+#define TCG_TARGET_HAS_deposit_i64      1
+#define TCG_TARGET_HAS_movcond_i64      1
+#define TCG_TARGET_HAS_add2_i64         1
+#define TCG_TARGET_HAS_sub2_i64         1
+#define TCG_TARGET_HAS_mulu2_i64        0
+#define TCG_TARGET_HAS_muls2_i64        0
+#define TCG_TARGET_HAS_muluh_i64        1
+#define TCG_TARGET_HAS_mulsh_i64        1
+#endif
+
+void flush_icache_range(uintptr_t start, uintptr_t stop);
+
+#endif
diff --git a/tcg/s390/tcg-target.c b/tcg/s390/tcg-target.c
new file mode 100644
index 00000000..aa718eca
--- /dev/null
+++ b/tcg/s390/tcg-target.c
@@ -0,0 +1,2393 @@
+/*
+ * Tiny Code Generator for QEMU
+ *
+ * Copyright (c) 2009 Ulrich Hecht <uli@suse.de>
+ * Copyright (c) 2009 Alexander Graf <agraf@suse.de>
+ * Copyright (c) 2010 Richard Henderson <rth@twiddle.net>
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (the "Software"), to deal
+ * in the Software without restriction, including without limitation the rights
+ * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+ * copies of the Software, and to permit persons to whom the Software is
+ * furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+ * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+ * THE SOFTWARE.
+ */
+
+#include "tcg-be-ldst.h"
+
+/* We only support generating code for 64-bit mode.  */
+#if TCG_TARGET_REG_BITS != 64
+#error "unsupported code generation mode"
+#endif
+
+#include "elf.h"
+
+/* ??? The translation blocks produced by TCG are generally small enough to
+   be entirely reachable with a 16-bit displacement.  Leaving the option for
+   a 32-bit displacement here Just In Case.  */
+#define USE_LONG_BRANCHES 0
+
+#define TCG_CT_CONST_MULI  0x100
+#define TCG_CT_CONST_ORI   0x200
+#define TCG_CT_CONST_XORI  0x400
+#define TCG_CT_CONST_CMPI  0x800
+#define TCG_CT_CONST_ADLI  0x1000
+
+/* Several places within the instruction set 0 means "no register"
+   rather than TCG_REG_R0.  */
+#define TCG_REG_NONE    0
+
+/* A scratch register that may be be used throughout the backend.  */
+#define TCG_TMP0        TCG_REG_R14
+
+#ifdef CONFIG_USE_GUEST_BASE
+#define TCG_GUEST_BASE_REG TCG_REG_R13
+#else
+#define TCG_GUEST_BASE_REG TCG_REG_R0
+#endif
+
+#ifndef GUEST_BASE
+#define GUEST_BASE 0
+#endif
+
+
+/* All of the following instructions are prefixed with their instruction
+   format, and are defined as 8- or 16-bit quantities, even when the two
+   halves of the 16-bit quantity may appear 32 bits apart in the insn.
+   This makes it easy to copy the values from the tables in Appendix B.  */
+typedef enum S390Opcode {
+    RIL_AFI     = 0xc209,
+    RIL_AGFI    = 0xc208,
+    RIL_ALFI    = 0xc20b,
+    RIL_ALGFI   = 0xc20a,
+    RIL_BRASL   = 0xc005,
+    RIL_BRCL    = 0xc004,
+    RIL_CFI     = 0xc20d,
+    RIL_CGFI    = 0xc20c,
+    RIL_CLFI    = 0xc20f,
+    RIL_CLGFI   = 0xc20e,
+    RIL_IIHF    = 0xc008,
+    RIL_IILF    = 0xc009,
+    RIL_LARL    = 0xc000,
+    RIL_LGFI    = 0xc001,
+    RIL_LGRL    = 0xc408,
+    RIL_LLIHF   = 0xc00e,
+    RIL_LLILF   = 0xc00f,
+    RIL_LRL     = 0xc40d,
+    RIL_MSFI    = 0xc201,
+    RIL_MSGFI   = 0xc200,
+    RIL_NIHF    = 0xc00a,
+    RIL_NILF    = 0xc00b,
+    RIL_OIHF    = 0xc00c,
+    RIL_OILF    = 0xc00d,
+    RIL_SLFI    = 0xc205,
+    RIL_SLGFI   = 0xc204,
+    RIL_XIHF    = 0xc006,
+    RIL_XILF    = 0xc007,
+
+    RI_AGHI     = 0xa70b,
+    RI_AHI      = 0xa70a,
+    RI_BRC      = 0xa704,
+    RI_IIHH     = 0xa500,
+    RI_IIHL     = 0xa501,
+    RI_IILH     = 0xa502,
+    RI_IILL     = 0xa503,
+    RI_LGHI     = 0xa709,
+    RI_LLIHH    = 0xa50c,
+    RI_LLIHL    = 0xa50d,
+    RI_LLILH    = 0xa50e,
+    RI_LLILL    = 0xa50f,
+    RI_MGHI     = 0xa70d,
+    RI_MHI      = 0xa70c,
+    RI_NIHH     = 0xa504,
+    RI_NIHL     = 0xa505,
+    RI_NILH     = 0xa506,
+    RI_NILL     = 0xa507,
+    RI_OIHH     = 0xa508,
+    RI_OIHL     = 0xa509,
+    RI_OILH     = 0xa50a,
+    RI_OILL     = 0xa50b,
+
+    RIE_CGIJ    = 0xec7c,
+    RIE_CGRJ    = 0xec64,
+    RIE_CIJ     = 0xec7e,
+    RIE_CLGRJ   = 0xec65,
+    RIE_CLIJ    = 0xec7f,
+    RIE_CLGIJ   = 0xec7d,
+    RIE_CLRJ    = 0xec77,
+    RIE_CRJ     = 0xec76,
+    RIE_RISBG   = 0xec55,
+
+    RRE_AGR     = 0xb908,
+    RRE_ALGR    = 0xb90a,
+    RRE_ALCR    = 0xb998,
+    RRE_ALCGR   = 0xb988,
+    RRE_CGR     = 0xb920,
+    RRE_CLGR    = 0xb921,
+    RRE_DLGR    = 0xb987,
+    RRE_DLR     = 0xb997,
+    RRE_DSGFR   = 0xb91d,
+    RRE_DSGR    = 0xb90d,
+    RRE_LGBR    = 0xb906,
+    RRE_LCGR    = 0xb903,
+    RRE_LGFR    = 0xb914,
+    RRE_LGHR    = 0xb907,
+    RRE_LGR     = 0xb904,
+    RRE_LLGCR   = 0xb984,
+    RRE_LLGFR   = 0xb916,
+    RRE_LLGHR   = 0xb985,
+    RRE_LRVR    = 0xb91f,
+    RRE_LRVGR   = 0xb90f,
+    RRE_LTGR    = 0xb902,
+    RRE_MLGR    = 0xb986,
+    RRE_MSGR    = 0xb90c,
+    RRE_MSR     = 0xb252,
+    RRE_NGR     = 0xb980,
+    RRE_OGR     = 0xb981,
+    RRE_SGR     = 0xb909,
+    RRE_SLGR    = 0xb90b,
+    RRE_SLBR    = 0xb999,
+    RRE_SLBGR   = 0xb989,
+    RRE_XGR     = 0xb982,
+
+    RRF_LOCR    = 0xb9f2,
+    RRF_LOCGR   = 0xb9e2,
+
+    RR_AR       = 0x1a,
+    RR_ALR      = 0x1e,
+    RR_BASR     = 0x0d,
+    RR_BCR      = 0x07,
+    RR_CLR      = 0x15,
+    RR_CR       = 0x19,
+    RR_DR       = 0x1d,
+    RR_LCR      = 0x13,
+    RR_LR       = 0x18,
+    RR_LTR      = 0x12,
+    RR_NR       = 0x14,
+    RR_OR       = 0x16,
+    RR_SR       = 0x1b,
+    RR_SLR      = 0x1f,
+    RR_XR       = 0x17,
+
+    RSY_RLL     = 0xeb1d,
+    RSY_RLLG    = 0xeb1c,
+    RSY_SLLG    = 0xeb0d,
+    RSY_SRAG    = 0xeb0a,
+    RSY_SRLG    = 0xeb0c,
+
+    RS_SLL      = 0x89,
+    RS_SRA      = 0x8a,
+    RS_SRL      = 0x88,
+
+    RXY_AG      = 0xe308,
+    RXY_AY      = 0xe35a,
+    RXY_CG      = 0xe320,
+    RXY_CY      = 0xe359,
+    RXY_LAY     = 0xe371,
+    RXY_LB      = 0xe376,
+    RXY_LG      = 0xe304,
+    RXY_LGB     = 0xe377,
+    RXY_LGF     = 0xe314,
+    RXY_LGH     = 0xe315,
+    RXY_LHY     = 0xe378,
+    RXY_LLGC    = 0xe390,
+    RXY_LLGF    = 0xe316,
+    RXY_LLGH    = 0xe391,
+    RXY_LMG     = 0xeb04,
+    RXY_LRV     = 0xe31e,
+    RXY_LRVG    = 0xe30f,
+    RXY_LRVH    = 0xe31f,
+    RXY_LY      = 0xe358,
+    RXY_STCY    = 0xe372,
+    RXY_STG     = 0xe324,
+    RXY_STHY    = 0xe370,
+    RXY_STMG    = 0xeb24,
+    RXY_STRV    = 0xe33e,
+    RXY_STRVG   = 0xe32f,
+    RXY_STRVH   = 0xe33f,
+    RXY_STY     = 0xe350,
+
+    RX_A        = 0x5a,
+    RX_C        = 0x59,
+    RX_L        = 0x58,
+    RX_LA       = 0x41,
+    RX_LH       = 0x48,
+    RX_ST       = 0x50,
+    RX_STC      = 0x42,
+    RX_STH      = 0x40,
+} S390Opcode;
+
+#ifndef NDEBUG
+static const char * const tcg_target_reg_names[TCG_TARGET_NB_REGS] = {
+    "%r0", "%r1", "%r2", "%r3", "%r4", "%r5", "%r6", "%r7",
+    "%r8", "%r9", "%r10" "%r11" "%r12" "%r13" "%r14" "%r15"
+};
+#endif
+
+/* Since R6 is a potential argument register, choose it last of the
+   call-saved registers.  Likewise prefer the call-clobbered registers
+   in reverse order to maximize the chance of avoiding the arguments.  */
+static const int tcg_target_reg_alloc_order[] = {
+    /* Call saved registers.  */
+    TCG_REG_R13,
+    TCG_REG_R12,
+    TCG_REG_R11,
+    TCG_REG_R10,
+    TCG_REG_R9,
+    TCG_REG_R8,
+    TCG_REG_R7,
+    TCG_REG_R6,
+    /* Call clobbered registers.  */
+    TCG_REG_R14,
+    TCG_REG_R0,
+    TCG_REG_R1,
+    /* Argument registers, in reverse order of allocation.  */
+    TCG_REG_R5,
+    TCG_REG_R4,
+    TCG_REG_R3,
+    TCG_REG_R2,
+};
+
+static const int tcg_target_call_iarg_regs[] = {
+    TCG_REG_R2,
+    TCG_REG_R3,
+    TCG_REG_R4,
+    TCG_REG_R5,
+    TCG_REG_R6,
+};
+
+static const int tcg_target_call_oarg_regs[] = {
+    TCG_REG_R2,
+};
+
+#define S390_CC_EQ      8
+#define S390_CC_LT      4
+#define S390_CC_GT      2
+#define S390_CC_OV      1
+#define S390_CC_NE      (S390_CC_LT | S390_CC_GT)
+#define S390_CC_LE      (S390_CC_LT | S390_CC_EQ)
+#define S390_CC_GE      (S390_CC_GT | S390_CC_EQ)
+#define S390_CC_NEVER   0
+#define S390_CC_ALWAYS  15
+
+/* Condition codes that result from a COMPARE and COMPARE LOGICAL.  */
+static const uint8_t tcg_cond_to_s390_cond[] = {
+    [TCG_COND_EQ]  = S390_CC_EQ,
+    [TCG_COND_NE]  = S390_CC_NE,
+    [TCG_COND_LT]  = S390_CC_LT,
+    [TCG_COND_LE]  = S390_CC_LE,
+    [TCG_COND_GT]  = S390_CC_GT,
+    [TCG_COND_GE]  = S390_CC_GE,
+    [TCG_COND_LTU] = S390_CC_LT,
+    [TCG_COND_LEU] = S390_CC_LE,
+    [TCG_COND_GTU] = S390_CC_GT,
+    [TCG_COND_GEU] = S390_CC_GE,
+};
+
+/* Condition codes that result from a LOAD AND TEST.  Here, we have no
+   unsigned instruction variation, however since the test is vs zero we
+   can re-map the outcomes appropriately.  */
+static const uint8_t tcg_cond_to_ltr_cond[] = {
+    [TCG_COND_EQ]  = S390_CC_EQ,
+    [TCG_COND_NE]  = S390_CC_NE,
+    [TCG_COND_LT]  = S390_CC_LT,
+    [TCG_COND_LE]  = S390_CC_LE,
+    [TCG_COND_GT]  = S390_CC_GT,
+    [TCG_COND_GE]  = S390_CC_GE,
+    [TCG_COND_LTU] = S390_CC_NEVER,
+    [TCG_COND_LEU] = S390_CC_EQ,
+    [TCG_COND_GTU] = S390_CC_NE,
+    [TCG_COND_GEU] = S390_CC_ALWAYS,
+};
+
+#ifdef CONFIG_SOFTMMU
+static void * const qemu_ld_helpers[16] = {
+    [MO_UB]   = helper_ret_ldub_mmu,
+    [MO_SB]   = helper_ret_ldsb_mmu,
+    [MO_LEUW] = helper_le_lduw_mmu,
+    [MO_LESW] = helper_le_ldsw_mmu,
+    [MO_LEUL] = helper_le_ldul_mmu,
+    [MO_LESL] = helper_le_ldsl_mmu,
+    [MO_LEQ]  = helper_le_ldq_mmu,
+    [MO_BEUW] = helper_be_lduw_mmu,
+    [MO_BESW] = helper_be_ldsw_mmu,
+    [MO_BEUL] = helper_be_ldul_mmu,
+    [MO_BESL] = helper_be_ldsl_mmu,
+    [MO_BEQ]  = helper_be_ldq_mmu,
+};
+
+static void * const qemu_st_helpers[16] = {
+    [MO_UB]   = helper_ret_stb_mmu,
+    [MO_LEUW] = helper_le_stw_mmu,
+    [MO_LEUL] = helper_le_stl_mmu,
+    [MO_LEQ]  = helper_le_stq_mmu,
+    [MO_BEUW] = helper_be_stw_mmu,
+    [MO_BEUL] = helper_be_stl_mmu,
+    [MO_BEQ]  = helper_be_stq_mmu,
+};
+#endif
+
+static tcg_insn_unit *tb_ret_addr;
+
+/* A list of relevant facilities used by this translator.  Some of these
+   are required for proper operation, and these are checked at startup.  */
+
+#define FACILITY_ZARCH_ACTIVE	(1ULL << (63 - 2))
+#define FACILITY_LONG_DISP	(1ULL << (63 - 18))
+#define FACILITY_EXT_IMM	(1ULL << (63 - 21))
+#define FACILITY_GEN_INST_EXT	(1ULL << (63 - 34))
+#define FACILITY_LOAD_ON_COND   (1ULL << (63 - 45))
+
+static uint64_t facilities;
+
+static void patch_reloc(tcg_insn_unit *code_ptr, int type,
+                        intptr_t value, intptr_t addend)
+{
+    intptr_t pcrel2 = (tcg_insn_unit *)value - (code_ptr - 1);
+    assert(addend == -2);
+
+    switch (type) {
+    case R_390_PC16DBL:
+        assert(pcrel2 == (int16_t)pcrel2);
+        tcg_patch16(code_ptr, pcrel2);
+        break;
+    case R_390_PC32DBL:
+        assert(pcrel2 == (int32_t)pcrel2);
+        tcg_patch32(code_ptr, pcrel2);
+        break;
+    default:
+        tcg_abort();
+        break;
+    }
+}
+
+/* parse target specific constraints */
+static int target_parse_constraint(TCGArgConstraint *ct, const char **pct_str)
+{
+    const char *ct_str = *pct_str;
+
+    switch (ct_str[0]) {
+    case 'r':                  /* all registers */
+        ct->ct |= TCG_CT_REG;
+        tcg_regset_set32(ct->u.regs, 0, 0xffff);
+        break;
+    case 'R':                  /* not R0 */
+        ct->ct |= TCG_CT_REG;
+        tcg_regset_set32(ct->u.regs, 0, 0xffff);
+        tcg_regset_reset_reg(ct->u.regs, TCG_REG_R0);
+        break;
+    case 'L':                  /* qemu_ld/st constraint */
+        ct->ct |= TCG_CT_REG;
+        tcg_regset_set32(ct->u.regs, 0, 0xffff);
+        tcg_regset_reset_reg (ct->u.regs, TCG_REG_R2);
+        tcg_regset_reset_reg (ct->u.regs, TCG_REG_R3);
+        tcg_regset_reset_reg (ct->u.regs, TCG_REG_R4);
+        break;
+    case 'a':                  /* force R2 for division */
+        ct->ct |= TCG_CT_REG;
+        tcg_regset_clear(ct->u.regs);
+        tcg_regset_set_reg(ct->u.regs, TCG_REG_R2);
+        break;
+    case 'b':                  /* force R3 for division */
+        ct->ct |= TCG_CT_REG;
+        tcg_regset_clear(ct->u.regs);
+        tcg_regset_set_reg(ct->u.regs, TCG_REG_R3);
+        break;
+    case 'A':
+        ct->ct |= TCG_CT_CONST_ADLI;
+        break;
+    case 'K':
+        ct->ct |= TCG_CT_CONST_MULI;
+        break;
+    case 'O':
+        ct->ct |= TCG_CT_CONST_ORI;
+        break;
+    case 'X':
+        ct->ct |= TCG_CT_CONST_XORI;
+        break;
+    case 'C':
+        ct->ct |= TCG_CT_CONST_CMPI;
+        break;
+    default:
+        return -1;
+    }
+    ct_str++;
+    *pct_str = ct_str;
+
+    return 0;
+}
+
+/* Immediates to be used with logical OR.  This is an optimization only,
+   since a full 64-bit immediate OR can always be performed with 4 sequential
+   OI[LH][LH] instructions.  What we're looking for is immediates that we
+   can load efficiently, and the immediate load plus the reg-reg OR is
+   smaller than the sequential OI's.  */
+
+static int tcg_match_ori(TCGType type, tcg_target_long val)
+{
+    if (facilities & FACILITY_EXT_IMM) {
+        if (type == TCG_TYPE_I32) {
+            /* All 32-bit ORs can be performed with 1 48-bit insn.  */
+            return 1;
+        }
+    }
+
+    /* Look for negative values.  These are best to load with LGHI.  */
+    if (val < 0) {
+        if (val == (int16_t)val) {
+            return 0;
+        }
+        if (facilities & FACILITY_EXT_IMM) {
+            if (val == (int32_t)val) {
+                return 0;
+            }
+        }
+    }
+
+    return 1;
+}
+
+/* Immediates to be used with logical XOR.  This is almost, but not quite,
+   only an optimization.  XOR with immediate is only supported with the
+   extended-immediate facility.  That said, there are a few patterns for
+   which it is better to load the value into a register first.  */
+
+static int tcg_match_xori(TCGType type, tcg_target_long val)
+{
+    if ((facilities & FACILITY_EXT_IMM) == 0) {
+        return 0;
+    }
+
+    if (type == TCG_TYPE_I32) {
+        /* All 32-bit XORs can be performed with 1 48-bit insn.  */
+        return 1;
+    }
+
+    /* Look for negative values.  These are best to load with LGHI.  */
+    if (val < 0 && val == (int32_t)val) {
+        return 0;
+    }
+
+    return 1;
+}
+
+/* Imediates to be used with comparisons.  */
+
+static int tcg_match_cmpi(TCGType type, tcg_target_long val)
+{
+    if (facilities & FACILITY_EXT_IMM) {
+        /* The COMPARE IMMEDIATE instruction is available.  */
+        if (type == TCG_TYPE_I32) {
+            /* We have a 32-bit immediate and can compare against anything.  */
+            return 1;
+        } else {
+            /* ??? We have no insight here into whether the comparison is
+               signed or unsigned.  The COMPARE IMMEDIATE insn uses a 32-bit
+               signed immediate, and the COMPARE LOGICAL IMMEDIATE insn uses
+               a 32-bit unsigned immediate.  If we were to use the (semi)
+               obvious "val == (int32_t)val" we would be enabling unsigned
+               comparisons vs very large numbers.  The only solution is to
+               take the intersection of the ranges.  */
+            /* ??? Another possible solution is to simply lie and allow all
+               constants here and force the out-of-range values into a temp
+               register in tgen_cmp when we have knowledge of the actual
+               comparison code in use.  */
+            return val >= 0 && val <= 0x7fffffff;
+        }
+    } else {
+        /* Only the LOAD AND TEST instruction is available.  */
+        return val == 0;
+    }
+}
+
+/* Immediates to be used with add2/sub2.  */
+
+static int tcg_match_add2i(TCGType type, tcg_target_long val)
+{
+    if (facilities & FACILITY_EXT_IMM) {
+        if (type == TCG_TYPE_I32) {
+            return 1;
+        } else if (val >= -0xffffffffll && val <= 0xffffffffll) {
+            return 1;
+        }
+    }
+    return 0;
+}
+
+/* Test if a constant matches the constraint. */
+static int tcg_target_const_match(tcg_target_long val, TCGType type,
+                                  const TCGArgConstraint *arg_ct)
+{
+    int ct = arg_ct->ct;
+
+    if (ct & TCG_CT_CONST) {
+        return 1;
+    }
+
+    if (type == TCG_TYPE_I32) {
+        val = (int32_t)val;
+    }
+
+    /* The following are mutually exclusive.  */
+    if (ct & TCG_CT_CONST_MULI) {
+        /* Immediates that may be used with multiply.  If we have the
+           general-instruction-extensions, then we have MULTIPLY SINGLE
+           IMMEDIATE with a signed 32-bit, otherwise we have only
+           MULTIPLY HALFWORD IMMEDIATE, with a signed 16-bit.  */
+        if (facilities & FACILITY_GEN_INST_EXT) {
+            return val == (int32_t)val;
+        } else {
+            return val == (int16_t)val;
+        }
+    } else if (ct & TCG_CT_CONST_ADLI) {
+        return tcg_match_add2i(type, val);
+    } else if (ct & TCG_CT_CONST_ORI) {
+        return tcg_match_ori(type, val);
+    } else if (ct & TCG_CT_CONST_XORI) {
+        return tcg_match_xori(type, val);
+    } else if (ct & TCG_CT_CONST_CMPI) {
+        return tcg_match_cmpi(type, val);
+    }
+
+    return 0;
+}
+
+/* Emit instructions according to the given instruction format.  */
+
+static void tcg_out_insn_RR(TCGContext *s, S390Opcode op, TCGReg r1, TCGReg r2)
+{
+    tcg_out16(s, (op << 8) | (r1 << 4) | r2);
+}
+
+static void tcg_out_insn_RRE(TCGContext *s, S390Opcode op,
+                             TCGReg r1, TCGReg r2)
+{
+    tcg_out32(s, (op << 16) | (r1 << 4) | r2);
+}
+
+static void tcg_out_insn_RRF(TCGContext *s, S390Opcode op,
+                             TCGReg r1, TCGReg r2, int m3)
+{
+    tcg_out32(s, (op << 16) | (m3 << 12) | (r1 << 4) | r2);
+}
+
+static void tcg_out_insn_RI(TCGContext *s, S390Opcode op, TCGReg r1, int i2)
+{
+    tcg_out32(s, (op << 16) | (r1 << 20) | (i2 & 0xffff));
+}
+
+static void tcg_out_insn_RIL(TCGContext *s, S390Opcode op, TCGReg r1, int i2)
+{
+    tcg_out16(s, op | (r1 << 4));
+    tcg_out32(s, i2);
+}
+
+static void tcg_out_insn_RS(TCGContext *s, S390Opcode op, TCGReg r1,
+                            TCGReg b2, TCGReg r3, int disp)
+{
+    tcg_out32(s, (op << 24) | (r1 << 20) | (r3 << 16) | (b2 << 12)
+              | (disp & 0xfff));
+}
+
+static void tcg_out_insn_RSY(TCGContext *s, S390Opcode op, TCGReg r1,
+                             TCGReg b2, TCGReg r3, int disp)
+{
+    tcg_out16(s, (op & 0xff00) | (r1 << 4) | r3);
+    tcg_out32(s, (op & 0xff) | (b2 << 28)
+              | ((disp & 0xfff) << 16) | ((disp & 0xff000) >> 4));
+}
+
+#define tcg_out_insn_RX   tcg_out_insn_RS
+#define tcg_out_insn_RXY  tcg_out_insn_RSY
+
+/* Emit an opcode with "type-checking" of the format.  */
+#define tcg_out_insn(S, FMT, OP, ...) \
+    glue(tcg_out_insn_,FMT)(S, glue(glue(FMT,_),OP), ## __VA_ARGS__)
+
+
+/* emit 64-bit shifts */
+static void tcg_out_sh64(TCGContext* s, S390Opcode op, TCGReg dest,
+                         TCGReg src, TCGReg sh_reg, int sh_imm)
+{
+    tcg_out_insn_RSY(s, op, dest, sh_reg, src, sh_imm);
+}
+
+/* emit 32-bit shifts */
+static void tcg_out_sh32(TCGContext* s, S390Opcode op, TCGReg dest,
+                         TCGReg sh_reg, int sh_imm)
+{
+    tcg_out_insn_RS(s, op, dest, sh_reg, 0, sh_imm);
+}
+
+static void tcg_out_mov(TCGContext *s, TCGType type, TCGReg dst, TCGReg src)
+{
+    if (src != dst) {
+        if (type == TCG_TYPE_I32) {
+            tcg_out_insn(s, RR, LR, dst, src);
+        } else {
+            tcg_out_insn(s, RRE, LGR, dst, src);
+        }
+    }
+}
+
+/* load a register with an immediate value */
+static void tcg_out_movi(TCGContext *s, TCGType type,
+                         TCGReg ret, tcg_target_long sval)
+{
+    static const S390Opcode lli_insns[4] = {
+        RI_LLILL, RI_LLILH, RI_LLIHL, RI_LLIHH
+    };
+
+    tcg_target_ulong uval = sval;
+    int i;
+
+    if (type == TCG_TYPE_I32) {
+        uval = (uint32_t)sval;
+        sval = (int32_t)sval;
+    }
+
+    /* Try all 32-bit insns that can load it in one go.  */
+    if (sval >= -0x8000 && sval < 0x8000) {
+        tcg_out_insn(s, RI, LGHI, ret, sval);
+        return;
+    }
+
+    for (i = 0; i < 4; i++) {
+        tcg_target_long mask = 0xffffull << i*16;
+        if ((uval & mask) == uval) {
+            tcg_out_insn_RI(s, lli_insns[i], ret, uval >> i*16);
+            return;
+        }
+    }
+
+    /* Try all 48-bit insns that can load it in one go.  */
+    if (facilities & FACILITY_EXT_IMM) {
+        if (sval == (int32_t)sval) {
+            tcg_out_insn(s, RIL, LGFI, ret, sval);
+            return;
+        }
+        if (uval <= 0xffffffff) {
+            tcg_out_insn(s, RIL, LLILF, ret, uval);
+            return;
+        }
+        if ((uval & 0xffffffff) == 0) {
+            tcg_out_insn(s, RIL, LLIHF, ret, uval >> 31 >> 1);
+            return;
+        }
+    }
+
+    /* Try for PC-relative address load.  */
+    if ((sval & 1) == 0) {
+        ptrdiff_t off = tcg_pcrel_diff(s, (void *)sval) >> 1;
+        if (off == (int32_t)off) {
+            tcg_out_insn(s, RIL, LARL, ret, off);
+            return;
+        }
+    }
+
+    /* If extended immediates are not present, then we may have to issue
+       several instructions to load the low 32 bits.  */
+    if (!(facilities & FACILITY_EXT_IMM)) {
+        /* A 32-bit unsigned value can be loaded in 2 insns.  And given
+           that the lli_insns loop above did not succeed, we know that
+           both insns are required.  */
+        if (uval <= 0xffffffff) {
+            tcg_out_insn(s, RI, LLILL, ret, uval);
+            tcg_out_insn(s, RI, IILH, ret, uval >> 16);
+            return;
+        }
+
+        /* If all high bits are set, the value can be loaded in 2 or 3 insns.
+           We first want to make sure that all the high bits get set.  With
+           luck the low 16-bits can be considered negative to perform that for
+           free, otherwise we load an explicit -1.  */
+        if (sval >> 31 >> 1 == -1) {
+            if (uval & 0x8000) {
+                tcg_out_insn(s, RI, LGHI, ret, uval);
+            } else {
+                tcg_out_insn(s, RI, LGHI, ret, -1);
+                tcg_out_insn(s, RI, IILL, ret, uval);
+            }
+            tcg_out_insn(s, RI, IILH, ret, uval >> 16);
+            return;
+        }
+    }
+
+    /* If we get here, both the high and low parts have non-zero bits.  */
+
+    /* Recurse to load the lower 32-bits.  */
+    tcg_out_movi(s, TCG_TYPE_I64, ret, uval & 0xffffffff);
+
+    /* Insert data into the high 32-bits.  */
+    uval = uval >> 31 >> 1;
+    if (facilities & FACILITY_EXT_IMM) {
+        if (uval < 0x10000) {
+            tcg_out_insn(s, RI, IIHL, ret, uval);
+        } else if ((uval & 0xffff) == 0) {
+            tcg_out_insn(s, RI, IIHH, ret, uval >> 16);
+        } else {
+            tcg_out_insn(s, RIL, IIHF, ret, uval);
+        }
+    } else {
+        if (uval & 0xffff) {
+            tcg_out_insn(s, RI, IIHL, ret, uval);
+        }
+        if (uval & 0xffff0000) {
+            tcg_out_insn(s, RI, IIHH, ret, uval >> 16);
+        }
+    }
+}
+
+
+/* Emit a load/store type instruction.  Inputs are:
+   DATA:     The register to be loaded or stored.
+   BASE+OFS: The effective address.
+   OPC_RX:   If the operation has an RX format opcode (e.g. STC), otherwise 0.
+   OPC_RXY:  The RXY format opcode for the operation (e.g. STCY).  */
+
+static void tcg_out_mem(TCGContext *s, S390Opcode opc_rx, S390Opcode opc_rxy,
+                        TCGReg data, TCGReg base, TCGReg index,
+                        tcg_target_long ofs)
+{
+    if (ofs < -0x80000 || ofs >= 0x80000) {
+        /* Combine the low 20 bits of the offset with the actual load insn;
+           the high 44 bits must come from an immediate load.  */
+        tcg_target_long low = ((ofs & 0xfffff) ^ 0x80000) - 0x80000;
+        tcg_out_movi(s, TCG_TYPE_PTR, TCG_TMP0, ofs - low);
+        ofs = low;
+
+        /* If we were already given an index register, add it in.  */
+        if (index != TCG_REG_NONE) {
+            tcg_out_insn(s, RRE, AGR, TCG_TMP0, index);
+        }
+        index = TCG_TMP0;
+    }
+
+    if (opc_rx && ofs >= 0 && ofs < 0x1000) {
+        tcg_out_insn_RX(s, opc_rx, data, base, index, ofs);
+    } else {
+        tcg_out_insn_RXY(s, opc_rxy, data, base, index, ofs);
+    }
+}
+
+
+/* load data without address translation or endianness conversion */
+static inline void tcg_out_ld(TCGContext *s, TCGType type, TCGReg data,
+                              TCGReg base, intptr_t ofs)
+{
+    if (type == TCG_TYPE_I32) {
+        tcg_out_mem(s, RX_L, RXY_LY, data, base, TCG_REG_NONE, ofs);
+    } else {
+        tcg_out_mem(s, 0, RXY_LG, data, base, TCG_REG_NONE, ofs);
+    }
+}
+
+static inline void tcg_out_st(TCGContext *s, TCGType type, TCGReg data,
+                              TCGReg base, intptr_t ofs)
+{
+    if (type == TCG_TYPE_I32) {
+        tcg_out_mem(s, RX_ST, RXY_STY, data, base, TCG_REG_NONE, ofs);
+    } else {
+        tcg_out_mem(s, 0, RXY_STG, data, base, TCG_REG_NONE, ofs);
+    }
+}
+
+/* load data from an absolute host address */
+static void tcg_out_ld_abs(TCGContext *s, TCGType type, TCGReg dest, void *abs)
+{
+    intptr_t addr = (intptr_t)abs;
+
+    if ((facilities & FACILITY_GEN_INST_EXT) && !(addr & 1)) {
+        ptrdiff_t disp = tcg_pcrel_diff(s, abs) >> 1;
+        if (disp == (int32_t)disp) {
+            if (type == TCG_TYPE_I32) {
+                tcg_out_insn(s, RIL, LRL, dest, disp);
+            } else {
+                tcg_out_insn(s, RIL, LGRL, dest, disp);
+            }
+            return;
+        }
+    }
+
+    tcg_out_movi(s, TCG_TYPE_PTR, dest, addr & ~0xffff);
+    tcg_out_ld(s, type, dest, dest, addr & 0xffff);
+}
+
+static inline void tcg_out_risbg(TCGContext *s, TCGReg dest, TCGReg src,
+                                 int msb, int lsb, int ofs, int z)
+{
+    /* Format RIE-f */
+    tcg_out16(s, (RIE_RISBG & 0xff00) | (dest << 4) | src);
+    tcg_out16(s, (msb << 8) | (z << 7) | lsb);
+    tcg_out16(s, (ofs << 8) | (RIE_RISBG & 0xff));
+}
+
+static void tgen_ext8s(TCGContext *s, TCGType type, TCGReg dest, TCGReg src)
+{
+    if (facilities & FACILITY_EXT_IMM) {
+        tcg_out_insn(s, RRE, LGBR, dest, src);
+        return;
+    }
+
+    if (type == TCG_TYPE_I32) {
+        if (dest == src) {
+            tcg_out_sh32(s, RS_SLL, dest, TCG_REG_NONE, 24);
+        } else {
+            tcg_out_sh64(s, RSY_SLLG, dest, src, TCG_REG_NONE, 24);
+        }
+        tcg_out_sh32(s, RS_SRA, dest, TCG_REG_NONE, 24);
+    } else {
+        tcg_out_sh64(s, RSY_SLLG, dest, src, TCG_REG_NONE, 56);
+        tcg_out_sh64(s, RSY_SRAG, dest, dest, TCG_REG_NONE, 56);
+    }
+}
+
+static void tgen_ext8u(TCGContext *s, TCGType type, TCGReg dest, TCGReg src)
+{
+    if (facilities & FACILITY_EXT_IMM) {
+        tcg_out_insn(s, RRE, LLGCR, dest, src);
+        return;
+    }
+
+    if (dest == src) {
+        tcg_out_movi(s, type, TCG_TMP0, 0xff);
+        src = TCG_TMP0;
+    } else {
+        tcg_out_movi(s, type, dest, 0xff);
+    }
+    if (type == TCG_TYPE_I32) {
+        tcg_out_insn(s, RR, NR, dest, src);
+    } else {
+        tcg_out_insn(s, RRE, NGR, dest, src);
+    }
+}
+
+static void tgen_ext16s(TCGContext *s, TCGType type, TCGReg dest, TCGReg src)
+{
+    if (facilities & FACILITY_EXT_IMM) {
+        tcg_out_insn(s, RRE, LGHR, dest, src);
+        return;
+    }
+
+    if (type == TCG_TYPE_I32) {
+        if (dest == src) {
+            tcg_out_sh32(s, RS_SLL, dest, TCG_REG_NONE, 16);
+        } else {
+            tcg_out_sh64(s, RSY_SLLG, dest, src, TCG_REG_NONE, 16);
+        }
+        tcg_out_sh32(s, RS_SRA, dest, TCG_REG_NONE, 16);
+    } else {
+        tcg_out_sh64(s, RSY_SLLG, dest, src, TCG_REG_NONE, 48);
+        tcg_out_sh64(s, RSY_SRAG, dest, dest, TCG_REG_NONE, 48);
+    }
+}
+
+static void tgen_ext16u(TCGContext *s, TCGType type, TCGReg dest, TCGReg src)
+{
+    if (facilities & FACILITY_EXT_IMM) {
+        tcg_out_insn(s, RRE, LLGHR, dest, src);
+        return;
+    }
+
+    if (dest == src) {
+        tcg_out_movi(s, type, TCG_TMP0, 0xffff);
+        src = TCG_TMP0;
+    } else {
+        tcg_out_movi(s, type, dest, 0xffff);
+    }
+    if (type == TCG_TYPE_I32) {
+        tcg_out_insn(s, RR, NR, dest, src);
+    } else {
+        tcg_out_insn(s, RRE, NGR, dest, src);
+    }
+}
+
+static inline void tgen_ext32s(TCGContext *s, TCGReg dest, TCGReg src)
+{
+    tcg_out_insn(s, RRE, LGFR, dest, src);
+}
+
+static inline void tgen_ext32u(TCGContext *s, TCGReg dest, TCGReg src)
+{
+    tcg_out_insn(s, RRE, LLGFR, dest, src);
+}
+
+/* Accept bit patterns like these:
+    0....01....1
+    1....10....0
+    1..10..01..1
+    0..01..10..0
+   Copied from gcc sources.  */
+static inline bool risbg_mask(uint64_t c)
+{
+    uint64_t lsb;
+    /* We don't change the number of transitions by inverting,
+       so make sure we start with the LSB zero.  */
+    if (c & 1) {
+        c = ~c;
+    }
+    /* Reject all zeros or all ones.  */
+    if (c == 0) {
+        return false;
+    }
+    /* Find the first transition.  */
+    lsb = c & -c;
+    /* Invert to look for a second transition.  */
+    c = ~c;
+    /* Erase the first transition.  */
+    c &= -lsb;
+    /* Find the second transition, if any.  */
+    lsb = c & -c;
+    /* Match if all the bits are 1's, or if c is zero.  */
+    return c == -lsb;
+}
+
+static void tgen_andi_risbg(TCGContext *s, TCGReg out, TCGReg in, uint64_t val)
+{
+    int msb, lsb;
+    if ((val & 0x8000000000000001ull) == 0x8000000000000001ull) {
+        /* Achieve wraparound by swapping msb and lsb.  */
+        msb = 64 - ctz64(~val);
+        lsb = clz64(~val) - 1;
+    } else {
+        msb = clz64(val);
+        lsb = 63 - ctz64(val);
+    }
+    tcg_out_risbg(s, out, in, msb, lsb, 0, 1);
+}
+
+static void tgen_andi(TCGContext *s, TCGType type, TCGReg dest, uint64_t val)
+{
+    static const S390Opcode ni_insns[4] = {
+        RI_NILL, RI_NILH, RI_NIHL, RI_NIHH
+    };
+    static const S390Opcode nif_insns[2] = {
+        RIL_NILF, RIL_NIHF
+    };
+    uint64_t valid = (type == TCG_TYPE_I32 ? 0xffffffffull : -1ull);
+    int i;
+
+    /* Look for the zero-extensions.  */
+    if ((val & valid) == 0xffffffff) {
+        tgen_ext32u(s, dest, dest);
+        return;
+    }
+    if (facilities & FACILITY_EXT_IMM) {
+        if ((val & valid) == 0xff) {
+            tgen_ext8u(s, TCG_TYPE_I64, dest, dest);
+            return;
+        }
+        if ((val & valid) == 0xffff) {
+            tgen_ext16u(s, TCG_TYPE_I64, dest, dest);
+            return;
+        }
+    }
+
+    /* Try all 32-bit insns that can perform it in one go.  */
+    for (i = 0; i < 4; i++) {
+        tcg_target_ulong mask = ~(0xffffull << i*16);
+        if (((val | ~valid) & mask) == mask) {
+            tcg_out_insn_RI(s, ni_insns[i], dest, val >> i*16);
+            return;
+        }
+    }
+
+    /* Try all 48-bit insns that can perform it in one go.  */
+    if (facilities & FACILITY_EXT_IMM) {
+        for (i = 0; i < 2; i++) {
+            tcg_target_ulong mask = ~(0xffffffffull << i*32);
+            if (((val | ~valid) & mask) == mask) {
+                tcg_out_insn_RIL(s, nif_insns[i], dest, val >> i*32);
+                return;
+            }
+        }
+    }
+    if ((facilities & FACILITY_GEN_INST_EXT) && risbg_mask(val)) {
+        tgen_andi_risbg(s, dest, dest, val);
+        return;
+    }
+
+    /* Fall back to loading the constant.  */
+    tcg_out_movi(s, type, TCG_TMP0, val);
+    if (type == TCG_TYPE_I32) {
+        tcg_out_insn(s, RR, NR, dest, TCG_TMP0);
+    } else {
+        tcg_out_insn(s, RRE, NGR, dest, TCG_TMP0);
+    }
+}
+
+static void tgen64_ori(TCGContext *s, TCGReg dest, tcg_target_ulong val)
+{
+    static const S390Opcode oi_insns[4] = {
+        RI_OILL, RI_OILH, RI_OIHL, RI_OIHH
+    };
+    static const S390Opcode nif_insns[2] = {
+        RIL_OILF, RIL_OIHF
+    };
+
+    int i;
+
+    /* Look for no-op.  */
+    if (val == 0) {
+        return;
+    }
+
+    if (facilities & FACILITY_EXT_IMM) {
+        /* Try all 32-bit insns that can perform it in one go.  */
+        for (i = 0; i < 4; i++) {
+            tcg_target_ulong mask = (0xffffull << i*16);
+            if ((val & mask) != 0 && (val & ~mask) == 0) {
+                tcg_out_insn_RI(s, oi_insns[i], dest, val >> i*16);
+                return;
+            }
+        }
+
+        /* Try all 48-bit insns that can perform it in one go.  */
+        for (i = 0; i < 2; i++) {
+            tcg_target_ulong mask = (0xffffffffull << i*32);
+            if ((val & mask) != 0 && (val & ~mask) == 0) {
+                tcg_out_insn_RIL(s, nif_insns[i], dest, val >> i*32);
+                return;
+            }
+        }
+
+        /* Perform the OR via sequential modifications to the high and
+           low parts.  Do this via recursion to handle 16-bit vs 32-bit
+           masks in each half.  */
+        tgen64_ori(s, dest, val & 0x00000000ffffffffull);
+        tgen64_ori(s, dest, val & 0xffffffff00000000ull);
+    } else {
+        /* With no extended-immediate facility, we don't need to be so
+           clever.  Just iterate over the insns and mask in the constant.  */
+        for (i = 0; i < 4; i++) {
+            tcg_target_ulong mask = (0xffffull << i*16);
+            if ((val & mask) != 0) {
+                tcg_out_insn_RI(s, oi_insns[i], dest, val >> i*16);
+            }
+        }
+    }
+}
+
+static void tgen64_xori(TCGContext *s, TCGReg dest, tcg_target_ulong val)
+{
+    /* Perform the xor by parts.  */
+    if (val & 0xffffffff) {
+        tcg_out_insn(s, RIL, XILF, dest, val);
+    }
+    if (val > 0xffffffff) {
+        tcg_out_insn(s, RIL, XIHF, dest, val >> 31 >> 1);
+    }
+}
+
+static int tgen_cmp(TCGContext *s, TCGType type, TCGCond c, TCGReg r1,
+                    TCGArg c2, int c2const)
+{
+    bool is_unsigned = is_unsigned_cond(c);
+    if (c2const) {
+        if (c2 == 0) {
+            if (type == TCG_TYPE_I32) {
+                tcg_out_insn(s, RR, LTR, r1, r1);
+            } else {
+                tcg_out_insn(s, RRE, LTGR, r1, r1);
+            }
+            return tcg_cond_to_ltr_cond[c];
+        } else {
+            if (is_unsigned) {
+                if (type == TCG_TYPE_I32) {
+                    tcg_out_insn(s, RIL, CLFI, r1, c2);
+                } else {
+                    tcg_out_insn(s, RIL, CLGFI, r1, c2);
+                }
+            } else {
+                if (type == TCG_TYPE_I32) {
+                    tcg_out_insn(s, RIL, CFI, r1, c2);
+                } else {
+                    tcg_out_insn(s, RIL, CGFI, r1, c2);
+                }
+            }
+        }
+    } else {
+        if (is_unsigned) {
+            if (type == TCG_TYPE_I32) {
+                tcg_out_insn(s, RR, CLR, r1, c2);
+            } else {
+                tcg_out_insn(s, RRE, CLGR, r1, c2);
+            }
+        } else {
+            if (type == TCG_TYPE_I32) {
+                tcg_out_insn(s, RR, CR, r1, c2);
+            } else {
+                tcg_out_insn(s, RRE, CGR, r1, c2);
+            }
+        }
+    }
+    return tcg_cond_to_s390_cond[c];
+}
+
+static void tgen_setcond(TCGContext *s, TCGType type, TCGCond cond,
+                         TCGReg dest, TCGReg c1, TCGArg c2, int c2const)
+{
+    int cc;
+
+    switch (cond) {
+    case TCG_COND_GTU:
+    case TCG_COND_GT:
+    do_greater:
+        /* The result of a compare has CC=2 for GT and CC=3 unused.
+           ADD LOGICAL WITH CARRY considers (CC & 2) the carry bit.  */
+        tgen_cmp(s, type, cond, c1, c2, c2const);
+        tcg_out_movi(s, type, dest, 0);
+        tcg_out_insn(s, RRE, ALCGR, dest, dest);
+        return;
+
+    case TCG_COND_GEU:
+    do_geu:
+        /* We need "real" carry semantics, so use SUBTRACT LOGICAL
+           instead of COMPARE LOGICAL.  This needs an extra move.  */
+        tcg_out_mov(s, type, TCG_TMP0, c1);
+        if (c2const) {
+            tcg_out_movi(s, TCG_TYPE_I64, dest, 0);
+            if (type == TCG_TYPE_I32) {
+                tcg_out_insn(s, RIL, SLFI, TCG_TMP0, c2);
+            } else {
+                tcg_out_insn(s, RIL, SLGFI, TCG_TMP0, c2);
+            }
+        } else {
+            if (type == TCG_TYPE_I32) {
+                tcg_out_insn(s, RR, SLR, TCG_TMP0, c2);
+            } else {
+                tcg_out_insn(s, RRE, SLGR, TCG_TMP0, c2);
+            }
+            tcg_out_movi(s, TCG_TYPE_I64, dest, 0);
+        }
+        tcg_out_insn(s, RRE, ALCGR, dest, dest);
+        return;
+
+    case TCG_COND_LEU:
+    case TCG_COND_LTU:
+    case TCG_COND_LT:
+        /* Swap operands so that we can use GEU/GTU/GT.  */
+        if (c2const) {
+            tcg_out_movi(s, type, TCG_TMP0, c2);
+            c2 = c1;
+            c2const = 0;
+            c1 = TCG_TMP0;
+        } else {
+            TCGReg t = c1;
+            c1 = c2;
+            c2 = t;
+        }
+        if (cond == TCG_COND_LEU) {
+            goto do_geu;
+        }
+        cond = tcg_swap_cond(cond);
+        goto do_greater;
+
+    case TCG_COND_NE:
+        /* X != 0 is X > 0.  */
+        if (c2const && c2 == 0) {
+            cond = TCG_COND_GTU;
+            goto do_greater;
+        }
+        break;
+
+    case TCG_COND_EQ:
+        /* X == 0 is X <= 0 is 0 >= X.  */
+        if (c2const && c2 == 0) {
+            tcg_out_movi(s, TCG_TYPE_I64, TCG_TMP0, 0);
+            c2 = c1;
+            c2const = 0;
+            c1 = TCG_TMP0;
+            goto do_geu;
+        }
+        break;
+
+    default:
+        break;
+    }
+
+    cc = tgen_cmp(s, type, cond, c1, c2, c2const);
+    if (facilities & FACILITY_LOAD_ON_COND) {
+        /* Emit: d = 0, t = 1, d = (cc ? t : d).  */
+        tcg_out_movi(s, TCG_TYPE_I64, dest, 0);
+        tcg_out_movi(s, TCG_TYPE_I64, TCG_TMP0, 1);
+        tcg_out_insn(s, RRF, LOCGR, dest, TCG_TMP0, cc);
+    } else {
+        /* Emit: d = 1; if (cc) goto over; d = 0; over:  */
+        tcg_out_movi(s, type, dest, 1);
+        tcg_out_insn(s, RI, BRC, cc, (4 + 4) >> 1);
+        tcg_out_movi(s, type, dest, 0);
+    }
+}
+
+static void tgen_movcond(TCGContext *s, TCGType type, TCGCond c, TCGReg dest,
+                         TCGReg c1, TCGArg c2, int c2const, TCGReg r3)
+{
+    int cc;
+    if (facilities & FACILITY_LOAD_ON_COND) {
+        cc = tgen_cmp(s, type, c, c1, c2, c2const);
+        tcg_out_insn(s, RRF, LOCGR, dest, r3, cc);
+    } else {
+        c = tcg_invert_cond(c);
+        cc = tgen_cmp(s, type, c, c1, c2, c2const);
+
+        /* Emit: if (cc) goto over; dest = r3; over:  */
+        tcg_out_insn(s, RI, BRC, cc, (4 + 4) >> 1);
+        tcg_out_insn(s, RRE, LGR, dest, r3);
+    }
+}
+
+bool tcg_target_deposit_valid(int ofs, int len)
+{
+    return (facilities & FACILITY_GEN_INST_EXT) != 0;
+}
+
+static void tgen_deposit(TCGContext *s, TCGReg dest, TCGReg src,
+                         int ofs, int len)
+{
+    int lsb = (63 - ofs);
+    int msb = lsb - (len - 1);
+    tcg_out_risbg(s, dest, src, msb, lsb, ofs, 0);
+}
+
+static void tgen_gotoi(TCGContext *s, int cc, tcg_insn_unit *dest)
+{
+    ptrdiff_t off = dest - s->code_ptr;
+    if (off == (int16_t)off) {
+        tcg_out_insn(s, RI, BRC, cc, off);
+    } else if (off == (int32_t)off) {
+        tcg_out_insn(s, RIL, BRCL, cc, off);
+    } else {
+        tcg_out_movi(s, TCG_TYPE_PTR, TCG_TMP0, (uintptr_t)dest);
+        tcg_out_insn(s, RR, BCR, cc, TCG_TMP0);
+    }
+}
+
+static void tgen_branch(TCGContext *s, int cc, TCGLabel *l)
+{
+    if (l->has_value) {
+        tgen_gotoi(s, cc, l->u.value_ptr);
+    } else if (USE_LONG_BRANCHES) {
+        tcg_out16(s, RIL_BRCL | (cc << 4));
+        tcg_out_reloc(s, s->code_ptr, R_390_PC32DBL, l, -2);
+        s->code_ptr += 2;
+    } else {
+        tcg_out16(s, RI_BRC | (cc << 4));
+        tcg_out_reloc(s, s->code_ptr, R_390_PC16DBL, l, -2);
+        s->code_ptr += 1;
+    }
+}
+
+static void tgen_compare_branch(TCGContext *s, S390Opcode opc, int cc,
+                                TCGReg r1, TCGReg r2, TCGLabel *l)
+{
+    intptr_t off;
+
+    if (l->has_value) {
+        off = l->u.value_ptr - s->code_ptr;
+    } else {
+        /* We need to keep the offset unchanged for retranslation.  */
+        off = s->code_ptr[1];
+        tcg_out_reloc(s, s->code_ptr + 1, R_390_PC16DBL, l, -2);
+    }
+
+    tcg_out16(s, (opc & 0xff00) | (r1 << 4) | r2);
+    tcg_out16(s, off);
+    tcg_out16(s, cc << 12 | (opc & 0xff));
+}
+
+static void tgen_compare_imm_branch(TCGContext *s, S390Opcode opc, int cc,
+                                    TCGReg r1, int i2, TCGLabel *l)
+{
+    tcg_target_long off;
+
+    if (l->has_value) {
+        off = l->u.value_ptr - s->code_ptr;
+    } else {
+        /* We need to keep the offset unchanged for retranslation.  */
+        off = s->code_ptr[1];
+        tcg_out_reloc(s, s->code_ptr + 1, R_390_PC16DBL, l, -2);
+    }
+
+    tcg_out16(s, (opc & 0xff00) | (r1 << 4) | cc);
+    tcg_out16(s, off);
+    tcg_out16(s, (i2 << 8) | (opc & 0xff));
+}
+
+static void tgen_brcond(TCGContext *s, TCGType type, TCGCond c,
+                        TCGReg r1, TCGArg c2, int c2const, TCGLabel *l)
+{
+    int cc;
+
+    if (facilities & FACILITY_GEN_INST_EXT) {
+        bool is_unsigned = is_unsigned_cond(c);
+        bool in_range;
+        S390Opcode opc;
+
+        cc = tcg_cond_to_s390_cond[c];
+
+        if (!c2const) {
+            opc = (type == TCG_TYPE_I32
+                   ? (is_unsigned ? RIE_CLRJ : RIE_CRJ)
+                   : (is_unsigned ? RIE_CLGRJ : RIE_CGRJ));
+            tgen_compare_branch(s, opc, cc, r1, c2, l);
+            return;
+        }
+
+        /* COMPARE IMMEDIATE AND BRANCH RELATIVE has an 8-bit immediate field.
+           If the immediate we've been given does not fit that range, we'll
+           fall back to separate compare and branch instructions using the
+           larger comparison range afforded by COMPARE IMMEDIATE.  */
+        if (type == TCG_TYPE_I32) {
+            if (is_unsigned) {
+                opc = RIE_CLIJ;
+                in_range = (uint32_t)c2 == (uint8_t)c2;
+            } else {
+                opc = RIE_CIJ;
+                in_range = (int32_t)c2 == (int8_t)c2;
+            }
+        } else {
+            if (is_unsigned) {
+                opc = RIE_CLGIJ;
+                in_range = (uint64_t)c2 == (uint8_t)c2;
+            } else {
+                opc = RIE_CGIJ;
+                in_range = (int64_t)c2 == (int8_t)c2;
+            }
+        }
+        if (in_range) {
+            tgen_compare_imm_branch(s, opc, cc, r1, c2, l);
+            return;
+        }
+    }
+
+    cc = tgen_cmp(s, type, c, r1, c2, c2const);
+    tgen_branch(s, cc, l);
+}
+
+static void tcg_out_call(TCGContext *s, tcg_insn_unit *dest)
+{
+    ptrdiff_t off = dest - s->code_ptr;
+    if (off == (int32_t)off) {
+        tcg_out_insn(s, RIL, BRASL, TCG_REG_R14, off);
+    } else {
+        tcg_out_movi(s, TCG_TYPE_PTR, TCG_TMP0, (uintptr_t)dest);
+        tcg_out_insn(s, RR, BASR, TCG_REG_R14, TCG_TMP0);
+    }
+}
+
+static void tcg_out_qemu_ld_direct(TCGContext *s, TCGMemOp opc, TCGReg data,
+                                   TCGReg base, TCGReg index, int disp)
+{
+    switch (opc & (MO_SSIZE | MO_BSWAP)) {
+    case MO_UB:
+        tcg_out_insn(s, RXY, LLGC, data, base, index, disp);
+        break;
+    case MO_SB:
+        tcg_out_insn(s, RXY, LGB, data, base, index, disp);
+        break;
+
+    case MO_UW | MO_BSWAP:
+        /* swapped unsigned halfword load with upper bits zeroed */
+        tcg_out_insn(s, RXY, LRVH, data, base, index, disp);
+        tgen_ext16u(s, TCG_TYPE_I64, data, data);
+        break;
+    case MO_UW:
+        tcg_out_insn(s, RXY, LLGH, data, base, index, disp);
+        break;
+
+    case MO_SW | MO_BSWAP:
+        /* swapped sign-extended halfword load */
+        tcg_out_insn(s, RXY, LRVH, data, base, index, disp);
+        tgen_ext16s(s, TCG_TYPE_I64, data, data);
+        break;
+    case MO_SW:
+        tcg_out_insn(s, RXY, LGH, data, base, index, disp);
+        break;
+
+    case MO_UL | MO_BSWAP:
+        /* swapped unsigned int load with upper bits zeroed */
+        tcg_out_insn(s, RXY, LRV, data, base, index, disp);
+        tgen_ext32u(s, data, data);
+        break;
+    case MO_UL:
+        tcg_out_insn(s, RXY, LLGF, data, base, index, disp);
+        break;
+
+    case MO_SL | MO_BSWAP:
+        /* swapped sign-extended int load */
+        tcg_out_insn(s, RXY, LRV, data, base, index, disp);
+        tgen_ext32s(s, data, data);
+        break;
+    case MO_SL:
+        tcg_out_insn(s, RXY, LGF, data, base, index, disp);
+        break;
+
+    case MO_Q | MO_BSWAP:
+        tcg_out_insn(s, RXY, LRVG, data, base, index, disp);
+        break;
+    case MO_Q:
+        tcg_out_insn(s, RXY, LG, data, base, index, disp);
+        break;
+
+    default:
+        tcg_abort();
+    }
+}
+
+static void tcg_out_qemu_st_direct(TCGContext *s, TCGMemOp opc, TCGReg data,
+                                   TCGReg base, TCGReg index, int disp)
+{
+    switch (opc & (MO_SIZE | MO_BSWAP)) {
+    case MO_UB:
+        if (disp >= 0 && disp < 0x1000) {
+            tcg_out_insn(s, RX, STC, data, base, index, disp);
+        } else {
+            tcg_out_insn(s, RXY, STCY, data, base, index, disp);
+        }
+        break;
+
+    case MO_UW | MO_BSWAP:
+        tcg_out_insn(s, RXY, STRVH, data, base, index, disp);
+        break;
+    case MO_UW:
+        if (disp >= 0 && disp < 0x1000) {
+            tcg_out_insn(s, RX, STH, data, base, index, disp);
+        } else {
+            tcg_out_insn(s, RXY, STHY, data, base, index, disp);
+        }
+        break;
+
+    case MO_UL | MO_BSWAP:
+        tcg_out_insn(s, RXY, STRV, data, base, index, disp);
+        break;
+    case MO_UL:
+        if (disp >= 0 && disp < 0x1000) {
+            tcg_out_insn(s, RX, ST, data, base, index, disp);
+        } else {
+            tcg_out_insn(s, RXY, STY, data, base, index, disp);
+        }
+        break;
+
+    case MO_Q | MO_BSWAP:
+        tcg_out_insn(s, RXY, STRVG, data, base, index, disp);
+        break;
+    case MO_Q:
+        tcg_out_insn(s, RXY, STG, data, base, index, disp);
+        break;
+
+    default:
+        tcg_abort();
+    }
+}
+
+#if defined(CONFIG_SOFTMMU)
+/* We're expecting to use a 20-bit signed offset on the tlb memory ops.
+   Using the offset of the second entry in the last tlb table ensures
+   that we can index all of the elements of the first entry.  */
+QEMU_BUILD_BUG_ON(offsetof(CPUArchState, tlb_table[NB_MMU_MODES - 1][1])
+                  > 0x7ffff);
+
+/* Load and compare a TLB entry, leaving the flags set.  Loads the TLB
+   addend into R2.  Returns a register with the santitized guest address.  */
+static TCGReg tcg_out_tlb_read(TCGContext* s, TCGReg addr_reg, TCGMemOp opc,
+                               int mem_index, bool is_ld)
+{
+    TCGMemOp s_bits = opc & MO_SIZE;
+    uint64_t tlb_mask = TARGET_PAGE_MASK | ((1 << s_bits) - 1);
+    int ofs;
+
+    if (facilities & FACILITY_GEN_INST_EXT) {
+        tcg_out_risbg(s, TCG_REG_R2, addr_reg,
+                      64 - CPU_TLB_BITS - CPU_TLB_ENTRY_BITS,
+                      63 - CPU_TLB_ENTRY_BITS,
+                      64 + CPU_TLB_ENTRY_BITS - TARGET_PAGE_BITS, 1);
+        tgen_andi_risbg(s, TCG_REG_R3, addr_reg, tlb_mask);
+    } else {
+        tcg_out_sh64(s, RSY_SRLG, TCG_REG_R2, addr_reg, TCG_REG_NONE,
+                     TARGET_PAGE_BITS - CPU_TLB_ENTRY_BITS);
+        tcg_out_movi(s, TCG_TYPE_TL, TCG_REG_R3, addr_reg);
+        tgen_andi(s, TCG_TYPE_I64, TCG_REG_R2,
+                  (CPU_TLB_SIZE - 1) << CPU_TLB_ENTRY_BITS);
+        tgen_andi(s, TCG_TYPE_TL, TCG_REG_R3, tlb_mask);
+    }
+
+    if (is_ld) {
+        ofs = offsetof(CPUArchState, tlb_table[mem_index][0].addr_read);
+    } else {
+        ofs = offsetof(CPUArchState, tlb_table[mem_index][0].addr_write);
+    }
+    if (TARGET_LONG_BITS == 32) {
+        tcg_out_mem(s, RX_C, RXY_CY, TCG_REG_R3, TCG_REG_R2, TCG_AREG0, ofs);
+    } else {
+        tcg_out_mem(s, 0, RXY_CG, TCG_REG_R3, TCG_REG_R2, TCG_AREG0, ofs);
+    }
+
+    ofs = offsetof(CPUArchState, tlb_table[mem_index][0].addend);
+    tcg_out_mem(s, 0, RXY_LG, TCG_REG_R2, TCG_REG_R2, TCG_AREG0, ofs);
+
+    if (TARGET_LONG_BITS == 32) {
+        tgen_ext32u(s, TCG_REG_R3, addr_reg);
+        return TCG_REG_R3;
+    }
+    return addr_reg;
+}
+
+static void add_qemu_ldst_label(TCGContext *s, bool is_ld, TCGMemOpIdx oi,
+                                TCGReg data, TCGReg addr,
+                                tcg_insn_unit *raddr, tcg_insn_unit *label_ptr)
+{
+    TCGLabelQemuLdst *label = new_ldst_label(s);
+
+    label->is_ld = is_ld;
+    label->oi = oi;
+    label->datalo_reg = data;
+    label->addrlo_reg = addr;
+    label->raddr = raddr;
+    label->label_ptr[0] = label_ptr;
+}
+
+static void tcg_out_qemu_ld_slow_path(TCGContext *s, TCGLabelQemuLdst *lb)
+{
+    TCGReg addr_reg = lb->addrlo_reg;
+    TCGReg data_reg = lb->datalo_reg;
+    TCGMemOpIdx oi = lb->oi;
+    TCGMemOp opc = get_memop(oi);
+
+    patch_reloc(lb->label_ptr[0], R_390_PC16DBL, (intptr_t)s->code_ptr, -2);
+
+    tcg_out_mov(s, TCG_TYPE_PTR, TCG_REG_R2, TCG_AREG0);
+    if (TARGET_LONG_BITS == 64) {
+        tcg_out_mov(s, TCG_TYPE_I64, TCG_REG_R3, addr_reg);
+    }
+    tcg_out_movi(s, TCG_TYPE_I32, TCG_REG_R4, oi);
+    tcg_out_movi(s, TCG_TYPE_PTR, TCG_REG_R5, (uintptr_t)lb->raddr);
+    tcg_out_call(s, qemu_ld_helpers[opc & (MO_BSWAP | MO_SSIZE)]);
+    tcg_out_mov(s, TCG_TYPE_I64, data_reg, TCG_REG_R2);
+
+    tgen_gotoi(s, S390_CC_ALWAYS, lb->raddr);
+}
+
+static void tcg_out_qemu_st_slow_path(TCGContext *s, TCGLabelQemuLdst *lb)
+{
+    TCGReg addr_reg = lb->addrlo_reg;
+    TCGReg data_reg = lb->datalo_reg;
+    TCGMemOpIdx oi = lb->oi;
+    TCGMemOp opc = get_memop(oi);
+
+    patch_reloc(lb->label_ptr[0], R_390_PC16DBL, (intptr_t)s->code_ptr, -2);
+
+    tcg_out_mov(s, TCG_TYPE_PTR, TCG_REG_R2, TCG_AREG0);
+    if (TARGET_LONG_BITS == 64) {
+        tcg_out_mov(s, TCG_TYPE_I64, TCG_REG_R3, addr_reg);
+    }
+    switch (opc & MO_SIZE) {
+    case MO_UB:
+        tgen_ext8u(s, TCG_TYPE_I64, TCG_REG_R4, data_reg);
+        break;
+    case MO_UW:
+        tgen_ext16u(s, TCG_TYPE_I64, TCG_REG_R4, data_reg);
+        break;
+    case MO_UL:
+        tgen_ext32u(s, TCG_REG_R4, data_reg);
+        break;
+    case MO_Q:
+        tcg_out_mov(s, TCG_TYPE_I64, TCG_REG_R4, data_reg);
+        break;
+    default:
+        tcg_abort();
+    }
+    tcg_out_movi(s, TCG_TYPE_I32, TCG_REG_R5, oi);
+    tcg_out_movi(s, TCG_TYPE_PTR, TCG_REG_R6, (uintptr_t)lb->raddr);
+    tcg_out_call(s, qemu_st_helpers[opc & (MO_BSWAP | MO_SIZE)]);
+
+    tgen_gotoi(s, S390_CC_ALWAYS, lb->raddr);
+}
+#else
+static void tcg_prepare_user_ldst(TCGContext *s, TCGReg *addr_reg,
+                                  TCGReg *index_reg, tcg_target_long *disp)
+{
+    if (TARGET_LONG_BITS == 32) {
+        tgen_ext32u(s, TCG_TMP0, *addr_reg);
+        *addr_reg = TCG_TMP0;
+    }
+    if (GUEST_BASE < 0x80000) {
+        *index_reg = TCG_REG_NONE;
+        *disp = GUEST_BASE;
+    } else {
+        *index_reg = TCG_GUEST_BASE_REG;
+        *disp = 0;
+    }
+}
+#endif /* CONFIG_SOFTMMU */
+
+static void tcg_out_qemu_ld(TCGContext* s, TCGReg data_reg, TCGReg addr_reg,
+                            TCGMemOpIdx oi)
+{
+    TCGMemOp opc = get_memop(oi);
+#ifdef CONFIG_SOFTMMU
+    unsigned mem_index = get_mmuidx(oi);
+    tcg_insn_unit *label_ptr;
+    TCGReg base_reg;
+
+    base_reg = tcg_out_tlb_read(s, addr_reg, opc, mem_index, 1);
+
+    /* We need to keep the offset unchanged for retranslation.  */
+    tcg_out16(s, RI_BRC | (S390_CC_NE << 4));
+    label_ptr = s->code_ptr;
+    s->code_ptr += 1;
+
+    tcg_out_qemu_ld_direct(s, opc, data_reg, base_reg, TCG_REG_R2, 0);
+
+    add_qemu_ldst_label(s, 1, oi, data_reg, addr_reg, s->code_ptr, label_ptr);
+#else
+    TCGReg index_reg;
+    tcg_target_long disp;
+
+    tcg_prepare_user_ldst(s, &addr_reg, &index_reg, &disp);
+    tcg_out_qemu_ld_direct(s, opc, data_reg, addr_reg, index_reg, disp);
+#endif
+}
+
+static void tcg_out_qemu_st(TCGContext* s, TCGReg data_reg, TCGReg addr_reg,
+                            TCGMemOpIdx oi)
+{
+    TCGMemOp opc = get_memop(oi);
+#ifdef CONFIG_SOFTMMU
+    unsigned mem_index = get_mmuidx(oi);
+    tcg_insn_unit *label_ptr;
+    TCGReg base_reg;
+
+    base_reg = tcg_out_tlb_read(s, addr_reg, opc, mem_index, 0);
+
+    /* We need to keep the offset unchanged for retranslation.  */
+    tcg_out16(s, RI_BRC | (S390_CC_NE << 4));
+    label_ptr = s->code_ptr;
+    s->code_ptr += 1;
+
+    tcg_out_qemu_st_direct(s, opc, data_reg, base_reg, TCG_REG_R2, 0);
+
+    add_qemu_ldst_label(s, 0, oi, data_reg, addr_reg, s->code_ptr, label_ptr);
+#else
+    TCGReg index_reg;
+    tcg_target_long disp;
+
+    tcg_prepare_user_ldst(s, &addr_reg, &index_reg, &disp);
+    tcg_out_qemu_st_direct(s, opc, data_reg, addr_reg, index_reg, disp);
+#endif
+}
+
+# define OP_32_64(x) \
+        case glue(glue(INDEX_op_,x),_i32): \
+        case glue(glue(INDEX_op_,x),_i64)
+
+static inline void tcg_out_op(TCGContext *s, TCGOpcode opc,
+                const TCGArg *args, const int *const_args)
+{
+    S390Opcode op;
+    TCGArg a0, a1, a2;
+
+    switch (opc) {
+    case INDEX_op_exit_tb:
+        /* return value */
+        tcg_out_movi(s, TCG_TYPE_PTR, TCG_REG_R2, args[0]);
+        tgen_gotoi(s, S390_CC_ALWAYS, tb_ret_addr);
+        break;
+
+    case INDEX_op_goto_tb:
+        if (s->tb_jmp_offset) {
+            tcg_out16(s, RIL_BRCL | (S390_CC_ALWAYS << 4));
+            s->tb_jmp_offset[args[0]] = tcg_current_code_size(s);
+            s->code_ptr += 2;
+        } else {
+            /* load address stored at s->tb_next + args[0] */
+            tcg_out_ld_abs(s, TCG_TYPE_PTR, TCG_TMP0, s->tb_next + args[0]);
+            /* and go there */
+            tcg_out_insn(s, RR, BCR, S390_CC_ALWAYS, TCG_TMP0);
+        }
+        s->tb_next_offset[args[0]] = tcg_current_code_size(s);
+        break;
+
+    OP_32_64(ld8u):
+        /* ??? LLC (RXY format) is only present with the extended-immediate
+           facility, whereas LLGC is always present.  */
+        tcg_out_mem(s, 0, RXY_LLGC, args[0], args[1], TCG_REG_NONE, args[2]);
+        break;
+
+    OP_32_64(ld8s):
+        /* ??? LB is no smaller than LGB, so no point to using it.  */
+        tcg_out_mem(s, 0, RXY_LGB, args[0], args[1], TCG_REG_NONE, args[2]);
+        break;
+
+    OP_32_64(ld16u):
+        /* ??? LLH (RXY format) is only present with the extended-immediate
+           facility, whereas LLGH is always present.  */
+        tcg_out_mem(s, 0, RXY_LLGH, args[0], args[1], TCG_REG_NONE, args[2]);
+        break;
+
+    case INDEX_op_ld16s_i32:
+        tcg_out_mem(s, RX_LH, RXY_LHY, args[0], args[1], TCG_REG_NONE, args[2]);
+        break;
+
+    case INDEX_op_ld_i32:
+        tcg_out_ld(s, TCG_TYPE_I32, args[0], args[1], args[2]);
+        break;
+
+    OP_32_64(st8):
+        tcg_out_mem(s, RX_STC, RXY_STCY, args[0], args[1],
+                    TCG_REG_NONE, args[2]);
+        break;
+
+    OP_32_64(st16):
+        tcg_out_mem(s, RX_STH, RXY_STHY, args[0], args[1],
+                    TCG_REG_NONE, args[2]);
+        break;
+
+    case INDEX_op_st_i32:
+        tcg_out_st(s, TCG_TYPE_I32, args[0], args[1], args[2]);
+        break;
+
+    case INDEX_op_add_i32:
+        a0 = args[0], a1 = args[1], a2 = (int32_t)args[2];
+        if (const_args[2]) {
+        do_addi_32:
+            if (a0 == a1) {
+                if (a2 == (int16_t)a2) {
+                    tcg_out_insn(s, RI, AHI, a0, a2);
+                    break;
+                }
+                if (facilities & FACILITY_EXT_IMM) {
+                    tcg_out_insn(s, RIL, AFI, a0, a2);
+                    break;
+                }
+            }
+            tcg_out_mem(s, RX_LA, RXY_LAY, a0, a1, TCG_REG_NONE, a2);
+        } else if (a0 == a1) {
+            tcg_out_insn(s, RR, AR, a0, a2);
+        } else {
+            tcg_out_insn(s, RX, LA, a0, a1, a2, 0);
+        }
+        break;
+    case INDEX_op_sub_i32:
+        a0 = args[0], a1 = args[1], a2 = (int32_t)args[2];
+        if (const_args[2]) {
+            a2 = -a2;
+            goto do_addi_32;
+        }
+        tcg_out_insn(s, RR, SR, args[0], args[2]);
+        break;
+
+    case INDEX_op_and_i32:
+        if (const_args[2]) {
+            tgen_andi(s, TCG_TYPE_I32, args[0], args[2]);
+        } else {
+            tcg_out_insn(s, RR, NR, args[0], args[2]);
+        }
+        break;
+    case INDEX_op_or_i32:
+        if (const_args[2]) {
+            tgen64_ori(s, args[0], args[2] & 0xffffffff);
+        } else {
+            tcg_out_insn(s, RR, OR, args[0], args[2]);
+        }
+        break;
+    case INDEX_op_xor_i32:
+        if (const_args[2]) {
+            tgen64_xori(s, args[0], args[2] & 0xffffffff);
+        } else {
+            tcg_out_insn(s, RR, XR, args[0], args[2]);
+        }
+        break;
+
+    case INDEX_op_neg_i32:
+        tcg_out_insn(s, RR, LCR, args[0], args[1]);
+        break;
+
+    case INDEX_op_mul_i32:
+        if (const_args[2]) {
+            if ((int32_t)args[2] == (int16_t)args[2]) {
+                tcg_out_insn(s, RI, MHI, args[0], args[2]);
+            } else {
+                tcg_out_insn(s, RIL, MSFI, args[0], args[2]);
+            }
+        } else {
+            tcg_out_insn(s, RRE, MSR, args[0], args[2]);
+        }
+        break;
+
+    case INDEX_op_div2_i32:
+        tcg_out_insn(s, RR, DR, TCG_REG_R2, args[4]);
+        break;
+    case INDEX_op_divu2_i32:
+        tcg_out_insn(s, RRE, DLR, TCG_REG_R2, args[4]);
+        break;
+
+    case INDEX_op_shl_i32:
+        op = RS_SLL;
+    do_shift32:
+        if (const_args[2]) {
+            tcg_out_sh32(s, op, args[0], TCG_REG_NONE, args[2]);
+        } else {
+            tcg_out_sh32(s, op, args[0], args[2], 0);
+        }
+        break;
+    case INDEX_op_shr_i32:
+        op = RS_SRL;
+        goto do_shift32;
+    case INDEX_op_sar_i32:
+        op = RS_SRA;
+        goto do_shift32;
+
+    case INDEX_op_rotl_i32:
+        /* ??? Using tcg_out_sh64 here for the format; it is a 32-bit rol.  */
+        if (const_args[2]) {
+            tcg_out_sh64(s, RSY_RLL, args[0], args[1], TCG_REG_NONE, args[2]);
+        } else {
+            tcg_out_sh64(s, RSY_RLL, args[0], args[1], args[2], 0);
+        }
+        break;
+    case INDEX_op_rotr_i32:
+        if (const_args[2]) {
+            tcg_out_sh64(s, RSY_RLL, args[0], args[1],
+                         TCG_REG_NONE, (32 - args[2]) & 31);
+        } else {
+            tcg_out_insn(s, RR, LCR, TCG_TMP0, args[2]);
+            tcg_out_sh64(s, RSY_RLL, args[0], args[1], TCG_TMP0, 0);
+        }
+        break;
+
+    case INDEX_op_ext8s_i32:
+        tgen_ext8s(s, TCG_TYPE_I32, args[0], args[1]);
+        break;
+    case INDEX_op_ext16s_i32:
+        tgen_ext16s(s, TCG_TYPE_I32, args[0], args[1]);
+        break;
+    case INDEX_op_ext8u_i32:
+        tgen_ext8u(s, TCG_TYPE_I32, args[0], args[1]);
+        break;
+    case INDEX_op_ext16u_i32:
+        tgen_ext16u(s, TCG_TYPE_I32, args[0], args[1]);
+        break;
+
+    OP_32_64(bswap16):
+        /* The TCG bswap definition requires bits 0-47 already be zero.
+           Thus we don't need the G-type insns to implement bswap16_i64.  */
+        tcg_out_insn(s, RRE, LRVR, args[0], args[1]);
+        tcg_out_sh32(s, RS_SRL, args[0], TCG_REG_NONE, 16);
+        break;
+    OP_32_64(bswap32):
+        tcg_out_insn(s, RRE, LRVR, args[0], args[1]);
+        break;
+
+    case INDEX_op_add2_i32:
+        if (const_args[4]) {
+            tcg_out_insn(s, RIL, ALFI, args[0], args[4]);
+        } else {
+            tcg_out_insn(s, RR, ALR, args[0], args[4]);
+        }
+        tcg_out_insn(s, RRE, ALCR, args[1], args[5]);
+        break;
+    case INDEX_op_sub2_i32:
+        if (const_args[4]) {
+            tcg_out_insn(s, RIL, SLFI, args[0], args[4]);
+        } else {
+            tcg_out_insn(s, RR, SLR, args[0], args[4]);
+        }
+        tcg_out_insn(s, RRE, SLBR, args[1], args[5]);
+        break;
+
+    case INDEX_op_br:
+        tgen_branch(s, S390_CC_ALWAYS, arg_label(args[0]));
+        break;
+
+    case INDEX_op_brcond_i32:
+        tgen_brcond(s, TCG_TYPE_I32, args[2], args[0],
+                    args[1], const_args[1], arg_label(args[3]));
+        break;
+    case INDEX_op_setcond_i32:
+        tgen_setcond(s, TCG_TYPE_I32, args[3], args[0], args[1],
+                     args[2], const_args[2]);
+        break;
+    case INDEX_op_movcond_i32:
+        tgen_movcond(s, TCG_TYPE_I32, args[5], args[0], args[1],
+                     args[2], const_args[2], args[3]);
+        break;
+
+    case INDEX_op_qemu_ld_i32:
+        /* ??? Technically we can use a non-extending instruction.  */
+    case INDEX_op_qemu_ld_i64:
+        tcg_out_qemu_ld(s, args[0], args[1], args[2]);
+        break;
+    case INDEX_op_qemu_st_i32:
+    case INDEX_op_qemu_st_i64:
+        tcg_out_qemu_st(s, args[0], args[1], args[2]);
+        break;
+
+    case INDEX_op_ld16s_i64:
+        tcg_out_mem(s, 0, RXY_LGH, args[0], args[1], TCG_REG_NONE, args[2]);
+        break;
+    case INDEX_op_ld32u_i64:
+        tcg_out_mem(s, 0, RXY_LLGF, args[0], args[1], TCG_REG_NONE, args[2]);
+        break;
+    case INDEX_op_ld32s_i64:
+        tcg_out_mem(s, 0, RXY_LGF, args[0], args[1], TCG_REG_NONE, args[2]);
+        break;
+    case INDEX_op_ld_i64:
+        tcg_out_ld(s, TCG_TYPE_I64, args[0], args[1], args[2]);
+        break;
+
+    case INDEX_op_st32_i64:
+        tcg_out_st(s, TCG_TYPE_I32, args[0], args[1], args[2]);
+        break;
+    case INDEX_op_st_i64:
+        tcg_out_st(s, TCG_TYPE_I64, args[0], args[1], args[2]);
+        break;
+
+    case INDEX_op_add_i64:
+        a0 = args[0], a1 = args[1], a2 = args[2];
+        if (const_args[2]) {
+        do_addi_64:
+            if (a0 == a1) {
+                if (a2 == (int16_t)a2) {
+                    tcg_out_insn(s, RI, AGHI, a0, a2);
+                    break;
+                }
+                if (facilities & FACILITY_EXT_IMM) {
+                    if (a2 == (int32_t)a2) {
+                        tcg_out_insn(s, RIL, AGFI, a0, a2);
+                        break;
+                    } else if (a2 == (uint32_t)a2) {
+                        tcg_out_insn(s, RIL, ALGFI, a0, a2);
+                        break;
+                    } else if (-a2 == (uint32_t)-a2) {
+                        tcg_out_insn(s, RIL, SLGFI, a0, -a2);
+                        break;
+                    }
+                }
+            }
+            tcg_out_mem(s, RX_LA, RXY_LAY, a0, a1, TCG_REG_NONE, a2);
+        } else if (a0 == a1) {
+            tcg_out_insn(s, RRE, AGR, a0, a2);
+        } else {
+            tcg_out_insn(s, RX, LA, a0, a1, a2, 0);
+        }
+        break;
+    case INDEX_op_sub_i64:
+        a0 = args[0], a1 = args[1], a2 = args[2];
+        if (const_args[2]) {
+            a2 = -a2;
+            goto do_addi_64;
+        } else {
+            tcg_out_insn(s, RRE, SGR, args[0], args[2]);
+        }
+        break;
+
+    case INDEX_op_and_i64:
+        if (const_args[2]) {
+            tgen_andi(s, TCG_TYPE_I64, args[0], args[2]);
+        } else {
+            tcg_out_insn(s, RRE, NGR, args[0], args[2]);
+        }
+        break;
+    case INDEX_op_or_i64:
+        if (const_args[2]) {
+            tgen64_ori(s, args[0], args[2]);
+        } else {
+            tcg_out_insn(s, RRE, OGR, args[0], args[2]);
+        }
+        break;
+    case INDEX_op_xor_i64:
+        if (const_args[2]) {
+            tgen64_xori(s, args[0], args[2]);
+        } else {
+            tcg_out_insn(s, RRE, XGR, args[0], args[2]);
+        }
+        break;
+
+    case INDEX_op_neg_i64:
+        tcg_out_insn(s, RRE, LCGR, args[0], args[1]);
+        break;
+    case INDEX_op_bswap64_i64:
+        tcg_out_insn(s, RRE, LRVGR, args[0], args[1]);
+        break;
+
+    case INDEX_op_mul_i64:
+        if (const_args[2]) {
+            if (args[2] == (int16_t)args[2]) {
+                tcg_out_insn(s, RI, MGHI, args[0], args[2]);
+            } else {
+                tcg_out_insn(s, RIL, MSGFI, args[0], args[2]);
+            }
+        } else {
+            tcg_out_insn(s, RRE, MSGR, args[0], args[2]);
+        }
+        break;
+
+    case INDEX_op_div2_i64:
+        /* ??? We get an unnecessary sign-extension of the dividend
+           into R3 with this definition, but as we do in fact always
+           produce both quotient and remainder using INDEX_op_div_i64
+           instead requires jumping through even more hoops.  */
+        tcg_out_insn(s, RRE, DSGR, TCG_REG_R2, args[4]);
+        break;
+    case INDEX_op_divu2_i64:
+        tcg_out_insn(s, RRE, DLGR, TCG_REG_R2, args[4]);
+        break;
+    case INDEX_op_mulu2_i64:
+        tcg_out_insn(s, RRE, MLGR, TCG_REG_R2, args[3]);
+        break;
+
+    case INDEX_op_shl_i64:
+        op = RSY_SLLG;
+    do_shift64:
+        if (const_args[2]) {
+            tcg_out_sh64(s, op, args[0], args[1], TCG_REG_NONE, args[2]);
+        } else {
+            tcg_out_sh64(s, op, args[0], args[1], args[2], 0);
+        }
+        break;
+    case INDEX_op_shr_i64:
+        op = RSY_SRLG;
+        goto do_shift64;
+    case INDEX_op_sar_i64:
+        op = RSY_SRAG;
+        goto do_shift64;
+
+    case INDEX_op_rotl_i64:
+        if (const_args[2]) {
+            tcg_out_sh64(s, RSY_RLLG, args[0], args[1],
+                         TCG_REG_NONE, args[2]);
+        } else {
+            tcg_out_sh64(s, RSY_RLLG, args[0], args[1], args[2], 0);
+        }
+        break;
+    case INDEX_op_rotr_i64:
+        if (const_args[2]) {
+            tcg_out_sh64(s, RSY_RLLG, args[0], args[1],
+                         TCG_REG_NONE, (64 - args[2]) & 63);
+        } else {
+            /* We can use the smaller 32-bit negate because only the
+               low 6 bits are examined for the rotate.  */
+            tcg_out_insn(s, RR, LCR, TCG_TMP0, args[2]);
+            tcg_out_sh64(s, RSY_RLLG, args[0], args[1], TCG_TMP0, 0);
+        }
+        break;
+
+    case INDEX_op_ext8s_i64:
+        tgen_ext8s(s, TCG_TYPE_I64, args[0], args[1]);
+        break;
+    case INDEX_op_ext16s_i64:
+        tgen_ext16s(s, TCG_TYPE_I64, args[0], args[1]);
+        break;
+    case INDEX_op_ext32s_i64:
+        tgen_ext32s(s, args[0], args[1]);
+        break;
+    case INDEX_op_ext8u_i64:
+        tgen_ext8u(s, TCG_TYPE_I64, args[0], args[1]);
+        break;
+    case INDEX_op_ext16u_i64:
+        tgen_ext16u(s, TCG_TYPE_I64, args[0], args[1]);
+        break;
+    case INDEX_op_ext32u_i64:
+        tgen_ext32u(s, args[0], args[1]);
+        break;
+
+    case INDEX_op_add2_i64:
+        if (const_args[4]) {
+            if ((int64_t)args[4] >= 0) {
+                tcg_out_insn(s, RIL, ALGFI, args[0], args[4]);
+            } else {
+                tcg_out_insn(s, RIL, SLGFI, args[0], -args[4]);
+            }
+        } else {
+            tcg_out_insn(s, RRE, ALGR, args[0], args[4]);
+        }
+        tcg_out_insn(s, RRE, ALCGR, args[1], args[5]);
+        break;
+    case INDEX_op_sub2_i64:
+        if (const_args[4]) {
+            if ((int64_t)args[4] >= 0) {
+                tcg_out_insn(s, RIL, SLGFI, args[0], args[4]);
+            } else {
+                tcg_out_insn(s, RIL, ALGFI, args[0], -args[4]);
+            }
+        } else {
+            tcg_out_insn(s, RRE, SLGR, args[0], args[4]);
+        }
+        tcg_out_insn(s, RRE, SLBGR, args[1], args[5]);
+        break;
+
+    case INDEX_op_brcond_i64:
+        tgen_brcond(s, TCG_TYPE_I64, args[2], args[0],
+                    args[1], const_args[1], arg_label(args[3]));
+        break;
+    case INDEX_op_setcond_i64:
+        tgen_setcond(s, TCG_TYPE_I64, args[3], args[0], args[1],
+                     args[2], const_args[2]);
+        break;
+    case INDEX_op_movcond_i64:
+        tgen_movcond(s, TCG_TYPE_I64, args[5], args[0], args[1],
+                     args[2], const_args[2], args[3]);
+        break;
+
+    OP_32_64(deposit):
+        tgen_deposit(s, args[0], args[2], args[3], args[4]);
+        break;
+
+    case INDEX_op_mov_i32:  /* Always emitted via tcg_out_mov.  */
+    case INDEX_op_mov_i64:
+    case INDEX_op_movi_i32: /* Always emitted via tcg_out_movi.  */
+    case INDEX_op_movi_i64:
+    case INDEX_op_call:     /* Always emitted via tcg_out_call.  */
+    default:
+        tcg_abort();
+    }
+}
+
+static const TCGTargetOpDef s390_op_defs[] = {
+    { INDEX_op_exit_tb, { } },
+    { INDEX_op_goto_tb, { } },
+    { INDEX_op_br, { } },
+
+    { INDEX_op_ld8u_i32, { "r", "r" } },
+    { INDEX_op_ld8s_i32, { "r", "r" } },
+    { INDEX_op_ld16u_i32, { "r", "r" } },
+    { INDEX_op_ld16s_i32, { "r", "r" } },
+    { INDEX_op_ld_i32, { "r", "r" } },
+    { INDEX_op_st8_i32, { "r", "r" } },
+    { INDEX_op_st16_i32, { "r", "r" } },
+    { INDEX_op_st_i32, { "r", "r" } },
+
+    { INDEX_op_add_i32, { "r", "r", "ri" } },
+    { INDEX_op_sub_i32, { "r", "0", "ri" } },
+    { INDEX_op_mul_i32, { "r", "0", "rK" } },
+
+    { INDEX_op_div2_i32, { "b", "a", "0", "1", "r" } },
+    { INDEX_op_divu2_i32, { "b", "a", "0", "1", "r" } },
+
+    { INDEX_op_and_i32, { "r", "0", "ri" } },
+    { INDEX_op_or_i32, { "r", "0", "rO" } },
+    { INDEX_op_xor_i32, { "r", "0", "rX" } },
+
+    { INDEX_op_neg_i32, { "r", "r" } },
+
+    { INDEX_op_shl_i32, { "r", "0", "Ri" } },
+    { INDEX_op_shr_i32, { "r", "0", "Ri" } },
+    { INDEX_op_sar_i32, { "r", "0", "Ri" } },
+
+    { INDEX_op_rotl_i32, { "r", "r", "Ri" } },
+    { INDEX_op_rotr_i32, { "r", "r", "Ri" } },
+
+    { INDEX_op_ext8s_i32, { "r", "r" } },
+    { INDEX_op_ext8u_i32, { "r", "r" } },
+    { INDEX_op_ext16s_i32, { "r", "r" } },
+    { INDEX_op_ext16u_i32, { "r", "r" } },
+
+    { INDEX_op_bswap16_i32, { "r", "r" } },
+    { INDEX_op_bswap32_i32, { "r", "r" } },
+
+    { INDEX_op_add2_i32, { "r", "r", "0", "1", "rA", "r" } },
+    { INDEX_op_sub2_i32, { "r", "r", "0", "1", "rA", "r" } },
+
+    { INDEX_op_brcond_i32, { "r", "rC" } },
+    { INDEX_op_setcond_i32, { "r", "r", "rC" } },
+    { INDEX_op_movcond_i32, { "r", "r", "rC", "r", "0" } },
+    { INDEX_op_deposit_i32, { "r", "0", "r" } },
+
+    { INDEX_op_qemu_ld_i32, { "r", "L" } },
+    { INDEX_op_qemu_ld_i64, { "r", "L" } },
+    { INDEX_op_qemu_st_i32, { "L", "L" } },
+    { INDEX_op_qemu_st_i64, { "L", "L" } },
+
+    { INDEX_op_ld8u_i64, { "r", "r" } },
+    { INDEX_op_ld8s_i64, { "r", "r" } },
+    { INDEX_op_ld16u_i64, { "r", "r" } },
+    { INDEX_op_ld16s_i64, { "r", "r" } },
+    { INDEX_op_ld32u_i64, { "r", "r" } },
+    { INDEX_op_ld32s_i64, { "r", "r" } },
+    { INDEX_op_ld_i64, { "r", "r" } },
+
+    { INDEX_op_st8_i64, { "r", "r" } },
+    { INDEX_op_st16_i64, { "r", "r" } },
+    { INDEX_op_st32_i64, { "r", "r" } },
+    { INDEX_op_st_i64, { "r", "r" } },
+
+    { INDEX_op_add_i64, { "r", "r", "ri" } },
+    { INDEX_op_sub_i64, { "r", "0", "ri" } },
+    { INDEX_op_mul_i64, { "r", "0", "rK" } },
+
+    { INDEX_op_div2_i64, { "b", "a", "0", "1", "r" } },
+    { INDEX_op_divu2_i64, { "b", "a", "0", "1", "r" } },
+    { INDEX_op_mulu2_i64, { "b", "a", "0", "r" } },
+
+    { INDEX_op_and_i64, { "r", "0", "ri" } },
+    { INDEX_op_or_i64, { "r", "0", "rO" } },
+    { INDEX_op_xor_i64, { "r", "0", "rX" } },
+
+    { INDEX_op_neg_i64, { "r", "r" } },
+
+    { INDEX_op_shl_i64, { "r", "r", "Ri" } },
+    { INDEX_op_shr_i64, { "r", "r", "Ri" } },
+    { INDEX_op_sar_i64, { "r", "r", "Ri" } },
+
+    { INDEX_op_rotl_i64, { "r", "r", "Ri" } },
+    { INDEX_op_rotr_i64, { "r", "r", "Ri" } },
+
+    { INDEX_op_ext8s_i64, { "r", "r" } },
+    { INDEX_op_ext8u_i64, { "r", "r" } },
+    { INDEX_op_ext16s_i64, { "r", "r" } },
+    { INDEX_op_ext16u_i64, { "r", "r" } },
+    { INDEX_op_ext32s_i64, { "r", "r" } },
+    { INDEX_op_ext32u_i64, { "r", "r" } },
+
+    { INDEX_op_bswap16_i64, { "r", "r" } },
+    { INDEX_op_bswap32_i64, { "r", "r" } },
+    { INDEX_op_bswap64_i64, { "r", "r" } },
+
+    { INDEX_op_add2_i64, { "r", "r", "0", "1", "rA", "r" } },
+    { INDEX_op_sub2_i64, { "r", "r", "0", "1", "rA", "r" } },
+
+    { INDEX_op_brcond_i64, { "r", "rC" } },
+    { INDEX_op_setcond_i64, { "r", "r", "rC" } },
+    { INDEX_op_movcond_i64, { "r", "r", "rC", "r", "0" } },
+    { INDEX_op_deposit_i64, { "r", "0", "r" } },
+
+    { -1 },
+};
+
+static void query_facilities(void)
+{
+    unsigned long hwcap = qemu_getauxval(AT_HWCAP);
+
+    /* Is STORE FACILITY LIST EXTENDED available?  Honestly, I believe this
+       is present on all 64-bit systems, but let's check for it anyway.  */
+    if (hwcap & HWCAP_S390_STFLE) {
+        register int r0 __asm__("0");
+        register void *r1 __asm__("1");
+
+        /* stfle 0(%r1) */
+        r1 = &facilities;
+        asm volatile(".word 0xb2b0,0x1000"
+                     : "=r"(r0) : "0"(0), "r"(r1) : "memory", "cc");
+    }
+}
+
+static void tcg_target_init(TCGContext *s)
+{
+    query_facilities();
+
+    tcg_regset_set32(tcg_target_available_regs[TCG_TYPE_I32], 0, 0xffff);
+    tcg_regset_set32(tcg_target_available_regs[TCG_TYPE_I64], 0, 0xffff);
+
+    tcg_regset_clear(tcg_target_call_clobber_regs);
+    tcg_regset_set_reg(tcg_target_call_clobber_regs, TCG_REG_R0);
+    tcg_regset_set_reg(tcg_target_call_clobber_regs, TCG_REG_R1);
+    tcg_regset_set_reg(tcg_target_call_clobber_regs, TCG_REG_R2);
+    tcg_regset_set_reg(tcg_target_call_clobber_regs, TCG_REG_R3);
+    tcg_regset_set_reg(tcg_target_call_clobber_regs, TCG_REG_R4);
+    tcg_regset_set_reg(tcg_target_call_clobber_regs, TCG_REG_R5);
+    /* The r6 register is technically call-saved, but it's also a parameter
+       register, so it can get killed by setup for the qemu_st helper.  */
+    tcg_regset_set_reg(tcg_target_call_clobber_regs, TCG_REG_R6);
+    /* The return register can be considered call-clobbered.  */
+    tcg_regset_set_reg(tcg_target_call_clobber_regs, TCG_REG_R14);
+
+    tcg_regset_clear(s->reserved_regs);
+    tcg_regset_set_reg(s->reserved_regs, TCG_TMP0);
+    /* XXX many insns can't be used with R0, so we better avoid it for now */
+    tcg_regset_set_reg(s->reserved_regs, TCG_REG_R0);
+    tcg_regset_set_reg(s->reserved_regs, TCG_REG_CALL_STACK);
+
+    tcg_add_target_add_op_defs(s390_op_defs);
+}
+
+#define FRAME_SIZE  ((int)(TCG_TARGET_CALL_STACK_OFFSET          \
+                           + TCG_STATIC_CALL_ARGS_SIZE           \
+                           + CPU_TEMP_BUF_NLONGS * sizeof(long)))
+
+static void tcg_target_qemu_prologue(TCGContext *s)
+{
+    /* stmg %r6,%r15,48(%r15) (save registers) */
+    tcg_out_insn(s, RXY, STMG, TCG_REG_R6, TCG_REG_R15, TCG_REG_R15, 48);
+
+    /* aghi %r15,-frame_size */
+    tcg_out_insn(s, RI, AGHI, TCG_REG_R15, -FRAME_SIZE);
+
+    tcg_set_frame(s, TCG_REG_CALL_STACK,
+                  TCG_STATIC_CALL_ARGS_SIZE + TCG_TARGET_CALL_STACK_OFFSET,
+                  CPU_TEMP_BUF_NLONGS * sizeof(long));
+
+    if (GUEST_BASE >= 0x80000) {
+        tcg_out_movi(s, TCG_TYPE_PTR, TCG_GUEST_BASE_REG, GUEST_BASE);
+        tcg_regset_set_reg(s->reserved_regs, TCG_GUEST_BASE_REG);
+    }
+
+    tcg_out_mov(s, TCG_TYPE_PTR, TCG_AREG0, tcg_target_call_iarg_regs[0]);
+    /* br %r3 (go to TB) */
+    tcg_out_insn(s, RR, BCR, S390_CC_ALWAYS, tcg_target_call_iarg_regs[1]);
+
+    tb_ret_addr = s->code_ptr;
+
+    /* lmg %r6,%r15,fs+48(%r15) (restore registers) */
+    tcg_out_insn(s, RXY, LMG, TCG_REG_R6, TCG_REG_R15, TCG_REG_R15,
+                 FRAME_SIZE + 48);
+
+    /* br %r14 (return) */
+    tcg_out_insn(s, RR, BCR, S390_CC_ALWAYS, TCG_REG_R14);
+}
+
+typedef struct {
+    DebugFrameHeader h;
+    uint8_t fde_def_cfa[4];
+    uint8_t fde_reg_ofs[18];
+} DebugFrame;
+
+/* We're expecting a 2 byte uleb128 encoded value.  */
+QEMU_BUILD_BUG_ON(FRAME_SIZE >= (1 << 14));
+
+#define ELF_HOST_MACHINE  EM_S390
+
+static const DebugFrame debug_frame = {
+    .h.cie.len = sizeof(DebugFrameCIE)-4, /* length after .len member */
+    .h.cie.id = -1,
+    .h.cie.version = 1,
+    .h.cie.code_align = 1,
+    .h.cie.data_align = 8,                /* sleb128 8 */
+    .h.cie.return_column = TCG_REG_R14,
+
+    /* Total FDE size does not include the "len" member.  */
+    .h.fde.len = sizeof(DebugFrame) - offsetof(DebugFrame, h.fde.cie_offset),
+
+    .fde_def_cfa = {
+        12, TCG_REG_CALL_STACK,         /* DW_CFA_def_cfa %r15, ... */
+        (FRAME_SIZE & 0x7f) | 0x80,     /* ... uleb128 FRAME_SIZE */
+        (FRAME_SIZE >> 7)
+    },
+    .fde_reg_ofs = {
+        0x86, 6,                        /* DW_CFA_offset, %r6, 48 */
+        0x87, 7,                        /* DW_CFA_offset, %r7, 56 */
+        0x88, 8,                        /* DW_CFA_offset, %r8, 64 */
+        0x89, 9,                        /* DW_CFA_offset, %r92, 72 */
+        0x8a, 10,                       /* DW_CFA_offset, %r10, 80 */
+        0x8b, 11,                       /* DW_CFA_offset, %r11, 88 */
+        0x8c, 12,                       /* DW_CFA_offset, %r12, 96 */
+        0x8d, 13,                       /* DW_CFA_offset, %r13, 104 */
+        0x8e, 14,                       /* DW_CFA_offset, %r14, 112 */
+    }
+};
+
+void tcg_register_jit(void *buf, size_t buf_size)
+{
+    tcg_register_jit_int(buf, buf_size, &debug_frame, sizeof(debug_frame));
+}
diff --git a/tcg/s390/tcg-target.h b/tcg/s390/tcg-target.h
new file mode 100644
index 00000000..91576d59
--- /dev/null
+++ b/tcg/s390/tcg-target.h
@@ -0,0 +1,123 @@
+/*
+ * Tiny Code Generator for QEMU
+ *
+ * Copyright (c) 2009 Ulrich Hecht <uli@suse.de>
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (the "Software"), to deal
+ * in the Software without restriction, including without limitation the rights
+ * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+ * copies of the Software, and to permit persons to whom the Software is
+ * furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+ * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+ * THE SOFTWARE.
+ */
+#ifndef TCG_TARGET_S390 
+#define TCG_TARGET_S390 1
+
+#define TCG_TARGET_INSN_UNIT_SIZE 2
+#define TCG_TARGET_TLB_DISPLACEMENT_BITS 19
+
+typedef enum TCGReg {
+    TCG_REG_R0 = 0,
+    TCG_REG_R1,
+    TCG_REG_R2,
+    TCG_REG_R3,
+    TCG_REG_R4,
+    TCG_REG_R5,
+    TCG_REG_R6,
+    TCG_REG_R7,
+    TCG_REG_R8,
+    TCG_REG_R9,
+    TCG_REG_R10,
+    TCG_REG_R11,
+    TCG_REG_R12,
+    TCG_REG_R13,
+    TCG_REG_R14,
+    TCG_REG_R15
+} TCGReg;
+
+#define TCG_TARGET_NB_REGS 16
+
+/* optional instructions */
+#define TCG_TARGET_HAS_div2_i32         1
+#define TCG_TARGET_HAS_rot_i32          1
+#define TCG_TARGET_HAS_ext8s_i32        1
+#define TCG_TARGET_HAS_ext16s_i32       1
+#define TCG_TARGET_HAS_ext8u_i32        1
+#define TCG_TARGET_HAS_ext16u_i32       1
+#define TCG_TARGET_HAS_bswap16_i32      1
+#define TCG_TARGET_HAS_bswap32_i32      1
+#define TCG_TARGET_HAS_not_i32          0
+#define TCG_TARGET_HAS_neg_i32          1
+#define TCG_TARGET_HAS_andc_i32         0
+#define TCG_TARGET_HAS_orc_i32          0
+#define TCG_TARGET_HAS_eqv_i32          0
+#define TCG_TARGET_HAS_nand_i32         0
+#define TCG_TARGET_HAS_nor_i32          0
+#define TCG_TARGET_HAS_deposit_i32      1
+#define TCG_TARGET_HAS_movcond_i32      1
+#define TCG_TARGET_HAS_add2_i32         1
+#define TCG_TARGET_HAS_sub2_i32         1
+#define TCG_TARGET_HAS_mulu2_i32        0
+#define TCG_TARGET_HAS_muls2_i32        0
+#define TCG_TARGET_HAS_muluh_i32        0
+#define TCG_TARGET_HAS_mulsh_i32        0
+#define TCG_TARGET_HAS_trunc_shr_i32    0
+
+#define TCG_TARGET_HAS_div2_i64         1
+#define TCG_TARGET_HAS_rot_i64          1
+#define TCG_TARGET_HAS_ext8s_i64        1
+#define TCG_TARGET_HAS_ext16s_i64       1
+#define TCG_TARGET_HAS_ext32s_i64       1
+#define TCG_TARGET_HAS_ext8u_i64        1
+#define TCG_TARGET_HAS_ext16u_i64       1
+#define TCG_TARGET_HAS_ext32u_i64       1
+#define TCG_TARGET_HAS_bswap16_i64      1
+#define TCG_TARGET_HAS_bswap32_i64      1
+#define TCG_TARGET_HAS_bswap64_i64      1
+#define TCG_TARGET_HAS_not_i64          0
+#define TCG_TARGET_HAS_neg_i64          1
+#define TCG_TARGET_HAS_andc_i64         0
+#define TCG_TARGET_HAS_orc_i64          0
+#define TCG_TARGET_HAS_eqv_i64          0
+#define TCG_TARGET_HAS_nand_i64         0
+#define TCG_TARGET_HAS_nor_i64          0
+#define TCG_TARGET_HAS_deposit_i64      1
+#define TCG_TARGET_HAS_movcond_i64      1
+#define TCG_TARGET_HAS_add2_i64         1
+#define TCG_TARGET_HAS_sub2_i64         1
+#define TCG_TARGET_HAS_mulu2_i64        1
+#define TCG_TARGET_HAS_muls2_i64        0
+#define TCG_TARGET_HAS_muluh_i64        0
+#define TCG_TARGET_HAS_mulsh_i64        0
+
+extern bool tcg_target_deposit_valid(int ofs, int len);
+#define TCG_TARGET_deposit_i32_valid  tcg_target_deposit_valid
+#define TCG_TARGET_deposit_i64_valid  tcg_target_deposit_valid
+
+/* used for function call generation */
+#define TCG_REG_CALL_STACK		TCG_REG_R15
+#define TCG_TARGET_STACK_ALIGN		8
+#define TCG_TARGET_CALL_STACK_OFFSET	160
+
+#define TCG_TARGET_EXTEND_ARGS 1
+
+enum {
+    TCG_AREG0 = TCG_REG_R10,
+};
+
+static inline void flush_icache_range(uintptr_t start, uintptr_t stop)
+{
+}
+
+#endif
diff --git a/tcg/sparc/tcg-target.c b/tcg/sparc/tcg-target.c
new file mode 100644
index 00000000..1a870a81
--- /dev/null
+++ b/tcg/sparc/tcg-target.c
@@ -0,0 +1,1650 @@
+/*
+ * Tiny Code Generator for QEMU
+ *
+ * Copyright (c) 2008 Fabrice Bellard
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (the "Software"), to deal
+ * in the Software without restriction, including without limitation the rights
+ * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+ * copies of the Software, and to permit persons to whom the Software is
+ * furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+ * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+ * THE SOFTWARE.
+ */
+
+#include "tcg-be-null.h"
+
+#ifndef NDEBUG
+static const char * const tcg_target_reg_names[TCG_TARGET_NB_REGS] = {
+    "%g0",
+    "%g1",
+    "%g2",
+    "%g3",
+    "%g4",
+    "%g5",
+    "%g6",
+    "%g7",
+    "%o0",
+    "%o1",
+    "%o2",
+    "%o3",
+    "%o4",
+    "%o5",
+    "%o6",
+    "%o7",
+    "%l0",
+    "%l1",
+    "%l2",
+    "%l3",
+    "%l4",
+    "%l5",
+    "%l6",
+    "%l7",
+    "%i0",
+    "%i1",
+    "%i2",
+    "%i3",
+    "%i4",
+    "%i5",
+    "%i6",
+    "%i7",
+};
+#endif
+
+#ifdef __arch64__
+# define SPARC64 1
+#else
+# define SPARC64 0
+#endif
+
+/* Note that sparcv8plus can only hold 64 bit quantities in %g and %o
+   registers.  These are saved manually by the kernel in full 64-bit
+   slots.  The %i and %l registers are saved by the register window
+   mechanism, which only allocates space for 32 bits.  Given that this
+   window spill/fill can happen on any signal, we must consider the
+   high bits of the %i and %l registers garbage at all times.  */
+#if SPARC64
+# define ALL_64  0xffffffffu
+#else
+# define ALL_64  0xffffu
+#endif
+
+/* Define some temporary registers.  T2 is used for constant generation.  */
+#define TCG_REG_T1  TCG_REG_G1
+#define TCG_REG_T2  TCG_REG_O7
+
+#ifdef CONFIG_USE_GUEST_BASE
+# define TCG_GUEST_BASE_REG TCG_REG_I5
+#else
+# define TCG_GUEST_BASE_REG TCG_REG_G0
+#endif
+
+static const int tcg_target_reg_alloc_order[] = {
+    TCG_REG_L0,
+    TCG_REG_L1,
+    TCG_REG_L2,
+    TCG_REG_L3,
+    TCG_REG_L4,
+    TCG_REG_L5,
+    TCG_REG_L6,
+    TCG_REG_L7,
+
+    TCG_REG_I0,
+    TCG_REG_I1,
+    TCG_REG_I2,
+    TCG_REG_I3,
+    TCG_REG_I4,
+    TCG_REG_I5,
+
+    TCG_REG_G2,
+    TCG_REG_G3,
+    TCG_REG_G4,
+    TCG_REG_G5,
+
+    TCG_REG_O0,
+    TCG_REG_O1,
+    TCG_REG_O2,
+    TCG_REG_O3,
+    TCG_REG_O4,
+    TCG_REG_O5,
+};
+
+static const int tcg_target_call_iarg_regs[6] = {
+    TCG_REG_O0,
+    TCG_REG_O1,
+    TCG_REG_O2,
+    TCG_REG_O3,
+    TCG_REG_O4,
+    TCG_REG_O5,
+};
+
+static const int tcg_target_call_oarg_regs[] = {
+    TCG_REG_O0,
+    TCG_REG_O1,
+    TCG_REG_O2,
+    TCG_REG_O3,
+};
+
+#define INSN_OP(x)  ((x) << 30)
+#define INSN_OP2(x) ((x) << 22)
+#define INSN_OP3(x) ((x) << 19)
+#define INSN_OPF(x) ((x) << 5)
+#define INSN_RD(x)  ((x) << 25)
+#define INSN_RS1(x) ((x) << 14)
+#define INSN_RS2(x) (x)
+#define INSN_ASI(x) ((x) << 5)
+
+#define INSN_IMM10(x) ((1 << 13) | ((x) & 0x3ff))
+#define INSN_IMM11(x) ((1 << 13) | ((x) & 0x7ff))
+#define INSN_IMM13(x) ((1 << 13) | ((x) & 0x1fff))
+#define INSN_OFF16(x) ((((x) >> 2) & 0x3fff) | ((((x) >> 16) & 3) << 20))
+#define INSN_OFF19(x) (((x) >> 2) & 0x07ffff)
+#define INSN_COND(x) ((x) << 25)
+
+#define COND_N     0x0
+#define COND_E     0x1
+#define COND_LE    0x2
+#define COND_L     0x3
+#define COND_LEU   0x4
+#define COND_CS    0x5
+#define COND_NEG   0x6
+#define COND_VS    0x7
+#define COND_A     0x8
+#define COND_NE    0x9
+#define COND_G     0xa
+#define COND_GE    0xb
+#define COND_GU    0xc
+#define COND_CC    0xd
+#define COND_POS   0xe
+#define COND_VC    0xf
+#define BA         (INSN_OP(0) | INSN_COND(COND_A) | INSN_OP2(0x2))
+
+#define RCOND_Z    1
+#define RCOND_LEZ  2
+#define RCOND_LZ   3
+#define RCOND_NZ   5
+#define RCOND_GZ   6
+#define RCOND_GEZ  7
+
+#define MOVCC_ICC  (1 << 18)
+#define MOVCC_XCC  (1 << 18 | 1 << 12)
+
+#define BPCC_ICC   0
+#define BPCC_XCC   (2 << 20)
+#define BPCC_PT    (1 << 19)
+#define BPCC_PN    0
+#define BPCC_A     (1 << 29)
+
+#define BPR_PT     BPCC_PT
+
+#define ARITH_ADD  (INSN_OP(2) | INSN_OP3(0x00))
+#define ARITH_ADDCC (INSN_OP(2) | INSN_OP3(0x10))
+#define ARITH_AND  (INSN_OP(2) | INSN_OP3(0x01))
+#define ARITH_ANDN (INSN_OP(2) | INSN_OP3(0x05))
+#define ARITH_OR   (INSN_OP(2) | INSN_OP3(0x02))
+#define ARITH_ORCC (INSN_OP(2) | INSN_OP3(0x12))
+#define ARITH_ORN  (INSN_OP(2) | INSN_OP3(0x06))
+#define ARITH_XOR  (INSN_OP(2) | INSN_OP3(0x03))
+#define ARITH_SUB  (INSN_OP(2) | INSN_OP3(0x04))
+#define ARITH_SUBCC (INSN_OP(2) | INSN_OP3(0x14))
+#define ARITH_ADDC (INSN_OP(2) | INSN_OP3(0x08))
+#define ARITH_SUBC (INSN_OP(2) | INSN_OP3(0x0c))
+#define ARITH_UMUL (INSN_OP(2) | INSN_OP3(0x0a))
+#define ARITH_SMUL (INSN_OP(2) | INSN_OP3(0x0b))
+#define ARITH_UDIV (INSN_OP(2) | INSN_OP3(0x0e))
+#define ARITH_SDIV (INSN_OP(2) | INSN_OP3(0x0f))
+#define ARITH_MULX (INSN_OP(2) | INSN_OP3(0x09))
+#define ARITH_UDIVX (INSN_OP(2) | INSN_OP3(0x0d))
+#define ARITH_SDIVX (INSN_OP(2) | INSN_OP3(0x2d))
+#define ARITH_MOVCC (INSN_OP(2) | INSN_OP3(0x2c))
+#define ARITH_MOVR (INSN_OP(2) | INSN_OP3(0x2f))
+
+#define ARITH_ADDXC (INSN_OP(2) | INSN_OP3(0x36) | INSN_OPF(0x11))
+#define ARITH_UMULXHI (INSN_OP(2) | INSN_OP3(0x36) | INSN_OPF(0x16))
+
+#define SHIFT_SLL  (INSN_OP(2) | INSN_OP3(0x25))
+#define SHIFT_SRL  (INSN_OP(2) | INSN_OP3(0x26))
+#define SHIFT_SRA  (INSN_OP(2) | INSN_OP3(0x27))
+
+#define SHIFT_SLLX (INSN_OP(2) | INSN_OP3(0x25) | (1 << 12))
+#define SHIFT_SRLX (INSN_OP(2) | INSN_OP3(0x26) | (1 << 12))
+#define SHIFT_SRAX (INSN_OP(2) | INSN_OP3(0x27) | (1 << 12))
+
+#define RDY        (INSN_OP(2) | INSN_OP3(0x28) | INSN_RS1(0))
+#define WRY        (INSN_OP(2) | INSN_OP3(0x30) | INSN_RD(0))
+#define JMPL       (INSN_OP(2) | INSN_OP3(0x38))
+#define RETURN     (INSN_OP(2) | INSN_OP3(0x39))
+#define SAVE       (INSN_OP(2) | INSN_OP3(0x3c))
+#define RESTORE    (INSN_OP(2) | INSN_OP3(0x3d))
+#define SETHI      (INSN_OP(0) | INSN_OP2(0x4))
+#define CALL       INSN_OP(1)
+#define LDUB       (INSN_OP(3) | INSN_OP3(0x01))
+#define LDSB       (INSN_OP(3) | INSN_OP3(0x09))
+#define LDUH       (INSN_OP(3) | INSN_OP3(0x02))
+#define LDSH       (INSN_OP(3) | INSN_OP3(0x0a))
+#define LDUW       (INSN_OP(3) | INSN_OP3(0x00))
+#define LDSW       (INSN_OP(3) | INSN_OP3(0x08))
+#define LDX        (INSN_OP(3) | INSN_OP3(0x0b))
+#define STB        (INSN_OP(3) | INSN_OP3(0x05))
+#define STH        (INSN_OP(3) | INSN_OP3(0x06))
+#define STW        (INSN_OP(3) | INSN_OP3(0x04))
+#define STX        (INSN_OP(3) | INSN_OP3(0x0e))
+#define LDUBA      (INSN_OP(3) | INSN_OP3(0x11))
+#define LDSBA      (INSN_OP(3) | INSN_OP3(0x19))
+#define LDUHA      (INSN_OP(3) | INSN_OP3(0x12))
+#define LDSHA      (INSN_OP(3) | INSN_OP3(0x1a))
+#define LDUWA      (INSN_OP(3) | INSN_OP3(0x10))
+#define LDSWA      (INSN_OP(3) | INSN_OP3(0x18))
+#define LDXA       (INSN_OP(3) | INSN_OP3(0x1b))
+#define STBA       (INSN_OP(3) | INSN_OP3(0x15))
+#define STHA       (INSN_OP(3) | INSN_OP3(0x16))
+#define STWA       (INSN_OP(3) | INSN_OP3(0x14))
+#define STXA       (INSN_OP(3) | INSN_OP3(0x1e))
+
+#ifndef ASI_PRIMARY_LITTLE
+#define ASI_PRIMARY_LITTLE 0x88
+#endif
+
+#define LDUH_LE    (LDUHA | INSN_ASI(ASI_PRIMARY_LITTLE))
+#define LDSH_LE    (LDSHA | INSN_ASI(ASI_PRIMARY_LITTLE))
+#define LDUW_LE    (LDUWA | INSN_ASI(ASI_PRIMARY_LITTLE))
+#define LDSW_LE    (LDSWA | INSN_ASI(ASI_PRIMARY_LITTLE))
+#define LDX_LE     (LDXA  | INSN_ASI(ASI_PRIMARY_LITTLE))
+
+#define STH_LE     (STHA  | INSN_ASI(ASI_PRIMARY_LITTLE))
+#define STW_LE     (STWA  | INSN_ASI(ASI_PRIMARY_LITTLE))
+#define STX_LE     (STXA  | INSN_ASI(ASI_PRIMARY_LITTLE))
+
+#ifndef use_vis3_instructions
+bool use_vis3_instructions;
+#endif
+
+static inline int check_fit_i64(int64_t val, unsigned int bits)
+{
+    return val == sextract64(val, 0, bits);
+}
+
+static inline int check_fit_i32(int32_t val, unsigned int bits)
+{
+    return val == sextract32(val, 0, bits);
+}
+
+#define check_fit_tl    check_fit_i64
+#if SPARC64
+# define check_fit_ptr  check_fit_i64
+#else
+# define check_fit_ptr  check_fit_i32
+#endif
+
+static void patch_reloc(tcg_insn_unit *code_ptr, int type,
+                        intptr_t value, intptr_t addend)
+{
+    uint32_t insn;
+
+    assert(addend == 0);
+    value = tcg_ptr_byte_diff((tcg_insn_unit *)value, code_ptr);
+
+    switch (type) {
+    case R_SPARC_WDISP16:
+        if (!check_fit_ptr(value >> 2, 16)) {
+            tcg_abort();
+        }
+        insn = *code_ptr;
+        insn &= ~INSN_OFF16(-1);
+        insn |= INSN_OFF16(value);
+        *code_ptr = insn;
+        break;
+    case R_SPARC_WDISP19:
+        if (!check_fit_ptr(value >> 2, 19)) {
+            tcg_abort();
+        }
+        insn = *code_ptr;
+        insn &= ~INSN_OFF19(-1);
+        insn |= INSN_OFF19(value);
+        *code_ptr = insn;
+        break;
+    default:
+        tcg_abort();
+    }
+}
+
+/* parse target specific constraints */
+static int target_parse_constraint(TCGArgConstraint *ct, const char **pct_str)
+{
+    const char *ct_str;
+
+    ct_str = *pct_str;
+    switch (ct_str[0]) {
+    case 'r':
+        ct->ct |= TCG_CT_REG;
+        tcg_regset_set32(ct->u.regs, 0, 0xffffffff);
+        break;
+    case 'R':
+        ct->ct |= TCG_CT_REG;
+        tcg_regset_set32(ct->u.regs, 0, ALL_64);
+        break;
+    case 'A': /* qemu_ld/st address constraint */
+        ct->ct |= TCG_CT_REG;
+        tcg_regset_set32(ct->u.regs, 0,
+                         TARGET_LONG_BITS == 64 ? ALL_64 : 0xffffffff);
+    reserve_helpers:
+        tcg_regset_reset_reg(ct->u.regs, TCG_REG_O0);
+        tcg_regset_reset_reg(ct->u.regs, TCG_REG_O1);
+        tcg_regset_reset_reg(ct->u.regs, TCG_REG_O2);
+        break;
+    case 's': /* qemu_st data 32-bit constraint */
+        ct->ct |= TCG_CT_REG;
+        tcg_regset_set32(ct->u.regs, 0, 0xffffffff);
+        goto reserve_helpers;
+    case 'S': /* qemu_st data 64-bit constraint */
+        ct->ct |= TCG_CT_REG;
+        tcg_regset_set32(ct->u.regs, 0, ALL_64);
+        goto reserve_helpers;
+    case 'I':
+        ct->ct |= TCG_CT_CONST_S11;
+        break;
+    case 'J':
+        ct->ct |= TCG_CT_CONST_S13;
+        break;
+    case 'Z':
+        ct->ct |= TCG_CT_CONST_ZERO;
+        break;
+    default:
+        return -1;
+    }
+    ct_str++;
+    *pct_str = ct_str;
+    return 0;
+}
+
+/* test if a constant matches the constraint */
+static inline int tcg_target_const_match(tcg_target_long val, TCGType type,
+                                         const TCGArgConstraint *arg_ct)
+{
+    int ct = arg_ct->ct;
+
+    if (ct & TCG_CT_CONST) {
+        return 1;
+    }
+
+    if (type == TCG_TYPE_I32) {
+        val = (int32_t)val;
+    }
+
+    if ((ct & TCG_CT_CONST_ZERO) && val == 0) {
+        return 1;
+    } else if ((ct & TCG_CT_CONST_S11) && check_fit_tl(val, 11)) {
+        return 1;
+    } else if ((ct & TCG_CT_CONST_S13) && check_fit_tl(val, 13)) {
+        return 1;
+    } else {
+        return 0;
+    }
+}
+
+static inline void tcg_out_arith(TCGContext *s, TCGReg rd, TCGReg rs1,
+                                 TCGReg rs2, int op)
+{
+    tcg_out32(s, op | INSN_RD(rd) | INSN_RS1(rs1) | INSN_RS2(rs2));
+}
+
+static inline void tcg_out_arithi(TCGContext *s, TCGReg rd, TCGReg rs1,
+                                  int32_t offset, int op)
+{
+    tcg_out32(s, op | INSN_RD(rd) | INSN_RS1(rs1) | INSN_IMM13(offset));
+}
+
+static void tcg_out_arithc(TCGContext *s, TCGReg rd, TCGReg rs1,
+			   int32_t val2, int val2const, int op)
+{
+    tcg_out32(s, op | INSN_RD(rd) | INSN_RS1(rs1)
+              | (val2const ? INSN_IMM13(val2) : INSN_RS2(val2)));
+}
+
+static inline void tcg_out_mov(TCGContext *s, TCGType type,
+                               TCGReg ret, TCGReg arg)
+{
+    if (ret != arg) {
+        tcg_out_arith(s, ret, arg, TCG_REG_G0, ARITH_OR);
+    }
+}
+
+static inline void tcg_out_sethi(TCGContext *s, TCGReg ret, uint32_t arg)
+{
+    tcg_out32(s, SETHI | INSN_RD(ret) | ((arg & 0xfffffc00) >> 10));
+}
+
+static inline void tcg_out_movi_imm13(TCGContext *s, TCGReg ret, int32_t arg)
+{
+    tcg_out_arithi(s, ret, TCG_REG_G0, arg, ARITH_OR);
+}
+
+static void tcg_out_movi(TCGContext *s, TCGType type,
+                         TCGReg ret, tcg_target_long arg)
+{
+    tcg_target_long hi, lo = (int32_t)arg;
+
+    /* Make sure we test 32-bit constants for imm13 properly.  */
+    if (type == TCG_TYPE_I32) {
+        arg = lo;
+    }
+
+    /* A 13-bit constant sign-extended to 64-bits.  */
+    if (check_fit_tl(arg, 13)) {
+        tcg_out_movi_imm13(s, ret, arg);
+        return;
+    }
+
+    /* A 32-bit constant, or 32-bit zero-extended to 64-bits.  */
+    if (type == TCG_TYPE_I32 || arg == (uint32_t)arg) {
+        tcg_out_sethi(s, ret, arg);
+        if (arg & 0x3ff) {
+            tcg_out_arithi(s, ret, ret, arg & 0x3ff, ARITH_OR);
+        }
+        return;
+    }
+
+    /* A 32-bit constant sign-extended to 64-bits.  */
+    if (arg == lo) {
+        tcg_out_sethi(s, ret, ~arg);
+        tcg_out_arithi(s, ret, ret, (arg & 0x3ff) | -0x400, ARITH_XOR);
+        return;
+    }
+
+    /* A 64-bit constant decomposed into 2 32-bit pieces.  */
+    if (check_fit_i32(lo, 13)) {
+        hi = (arg - lo) >> 32;
+        tcg_out_movi(s, TCG_TYPE_I32, ret, hi);
+        tcg_out_arithi(s, ret, ret, 32, SHIFT_SLLX);
+        tcg_out_arithi(s, ret, ret, lo, ARITH_ADD);
+    } else {
+        hi = arg >> 32;
+        tcg_out_movi(s, TCG_TYPE_I32, ret, hi);
+        tcg_out_movi(s, TCG_TYPE_I32, TCG_REG_T2, lo);
+        tcg_out_arithi(s, ret, ret, 32, SHIFT_SLLX);
+        tcg_out_arith(s, ret, ret, TCG_REG_T2, ARITH_OR);
+    }
+}
+
+static inline void tcg_out_ldst_rr(TCGContext *s, TCGReg data, TCGReg a1,
+                                   TCGReg a2, int op)
+{
+    tcg_out32(s, op | INSN_RD(data) | INSN_RS1(a1) | INSN_RS2(a2));
+}
+
+static void tcg_out_ldst(TCGContext *s, TCGReg ret, TCGReg addr,
+                         intptr_t offset, int op)
+{
+    if (check_fit_ptr(offset, 13)) {
+        tcg_out32(s, op | INSN_RD(ret) | INSN_RS1(addr) |
+                  INSN_IMM13(offset));
+    } else {
+        tcg_out_movi(s, TCG_TYPE_PTR, TCG_REG_T1, offset);
+        tcg_out_ldst_rr(s, ret, addr, TCG_REG_T1, op);
+    }
+}
+
+static inline void tcg_out_ld(TCGContext *s, TCGType type, TCGReg ret,
+                              TCGReg arg1, intptr_t arg2)
+{
+    tcg_out_ldst(s, ret, arg1, arg2, (type == TCG_TYPE_I32 ? LDUW : LDX));
+}
+
+static inline void tcg_out_st(TCGContext *s, TCGType type, TCGReg arg,
+                              TCGReg arg1, intptr_t arg2)
+{
+    tcg_out_ldst(s, arg, arg1, arg2, (type == TCG_TYPE_I32 ? STW : STX));
+}
+
+static void tcg_out_ld_ptr(TCGContext *s, TCGReg ret, uintptr_t arg)
+{
+    tcg_out_movi(s, TCG_TYPE_PTR, ret, arg & ~0x3ff);
+    tcg_out_ld(s, TCG_TYPE_PTR, ret, ret, arg & 0x3ff);
+}
+
+static inline void tcg_out_sety(TCGContext *s, TCGReg rs)
+{
+    tcg_out32(s, WRY | INSN_RS1(TCG_REG_G0) | INSN_RS2(rs));
+}
+
+static inline void tcg_out_rdy(TCGContext *s, TCGReg rd)
+{
+    tcg_out32(s, RDY | INSN_RD(rd));
+}
+
+static void tcg_out_div32(TCGContext *s, TCGReg rd, TCGReg rs1,
+                          int32_t val2, int val2const, int uns)
+{
+    /* Load Y with the sign/zero extension of RS1 to 64-bits.  */
+    if (uns) {
+        tcg_out_sety(s, TCG_REG_G0);
+    } else {
+        tcg_out_arithi(s, TCG_REG_T1, rs1, 31, SHIFT_SRA);
+        tcg_out_sety(s, TCG_REG_T1);
+    }
+
+    tcg_out_arithc(s, rd, rs1, val2, val2const,
+                   uns ? ARITH_UDIV : ARITH_SDIV);
+}
+
+static inline void tcg_out_nop(TCGContext *s)
+{
+    tcg_out_sethi(s, TCG_REG_G0, 0);
+}
+
+static const uint8_t tcg_cond_to_bcond[] = {
+    [TCG_COND_EQ] = COND_E,
+    [TCG_COND_NE] = COND_NE,
+    [TCG_COND_LT] = COND_L,
+    [TCG_COND_GE] = COND_GE,
+    [TCG_COND_LE] = COND_LE,
+    [TCG_COND_GT] = COND_G,
+    [TCG_COND_LTU] = COND_CS,
+    [TCG_COND_GEU] = COND_CC,
+    [TCG_COND_LEU] = COND_LEU,
+    [TCG_COND_GTU] = COND_GU,
+};
+
+static const uint8_t tcg_cond_to_rcond[] = {
+    [TCG_COND_EQ] = RCOND_Z,
+    [TCG_COND_NE] = RCOND_NZ,
+    [TCG_COND_LT] = RCOND_LZ,
+    [TCG_COND_GT] = RCOND_GZ,
+    [TCG_COND_LE] = RCOND_LEZ,
+    [TCG_COND_GE] = RCOND_GEZ
+};
+
+static void tcg_out_bpcc0(TCGContext *s, int scond, int flags, int off19)
+{
+    tcg_out32(s, INSN_OP(0) | INSN_OP2(1) | INSN_COND(scond) | flags | off19);
+}
+
+static void tcg_out_bpcc(TCGContext *s, int scond, int flags, TCGLabel *l)
+{
+    int off19;
+
+    if (l->has_value) {
+        off19 = INSN_OFF19(tcg_pcrel_diff(s, l->u.value_ptr));
+    } else {
+        /* Make sure to preserve destinations during retranslation.  */
+        off19 = *s->code_ptr & INSN_OFF19(-1);
+        tcg_out_reloc(s, s->code_ptr, R_SPARC_WDISP19, l, 0);
+    }
+    tcg_out_bpcc0(s, scond, flags, off19);
+}
+
+static void tcg_out_cmp(TCGContext *s, TCGReg c1, int32_t c2, int c2const)
+{
+    tcg_out_arithc(s, TCG_REG_G0, c1, c2, c2const, ARITH_SUBCC);
+}
+
+static void tcg_out_brcond_i32(TCGContext *s, TCGCond cond, TCGReg arg1,
+                               int32_t arg2, int const_arg2, TCGLabel *l)
+{
+    tcg_out_cmp(s, arg1, arg2, const_arg2);
+    tcg_out_bpcc(s, tcg_cond_to_bcond[cond], BPCC_ICC | BPCC_PT, l);
+    tcg_out_nop(s);
+}
+
+static void tcg_out_movcc(TCGContext *s, TCGCond cond, int cc, TCGReg ret,
+                          int32_t v1, int v1const)
+{
+    tcg_out32(s, ARITH_MOVCC | cc | INSN_RD(ret)
+              | INSN_RS1(tcg_cond_to_bcond[cond])
+              | (v1const ? INSN_IMM11(v1) : INSN_RS2(v1)));
+}
+
+static void tcg_out_movcond_i32(TCGContext *s, TCGCond cond, TCGReg ret,
+                                TCGReg c1, int32_t c2, int c2const,
+                                int32_t v1, int v1const)
+{
+    tcg_out_cmp(s, c1, c2, c2const);
+    tcg_out_movcc(s, cond, MOVCC_ICC, ret, v1, v1const);
+}
+
+static void tcg_out_brcond_i64(TCGContext *s, TCGCond cond, TCGReg arg1,
+                               int32_t arg2, int const_arg2, TCGLabel *l)
+{
+    /* For 64-bit signed comparisons vs zero, we can avoid the compare.  */
+    if (arg2 == 0 && !is_unsigned_cond(cond)) {
+        int off16;
+
+        if (l->has_value) {
+            off16 = INSN_OFF16(tcg_pcrel_diff(s, l->u.value_ptr));
+        } else {
+            /* Make sure to preserve destinations during retranslation.  */
+            off16 = *s->code_ptr & INSN_OFF16(-1);
+            tcg_out_reloc(s, s->code_ptr, R_SPARC_WDISP16, l, 0);
+        }
+        tcg_out32(s, INSN_OP(0) | INSN_OP2(3) | BPR_PT | INSN_RS1(arg1)
+                  | INSN_COND(tcg_cond_to_rcond[cond]) | off16);
+    } else {
+        tcg_out_cmp(s, arg1, arg2, const_arg2);
+        tcg_out_bpcc(s, tcg_cond_to_bcond[cond], BPCC_XCC | BPCC_PT, l);
+    }
+    tcg_out_nop(s);
+}
+
+static void tcg_out_movr(TCGContext *s, TCGCond cond, TCGReg ret, TCGReg c1,
+                         int32_t v1, int v1const)
+{
+    tcg_out32(s, ARITH_MOVR | INSN_RD(ret) | INSN_RS1(c1)
+              | (tcg_cond_to_rcond[cond] << 10)
+              | (v1const ? INSN_IMM10(v1) : INSN_RS2(v1)));
+}
+
+static void tcg_out_movcond_i64(TCGContext *s, TCGCond cond, TCGReg ret,
+                                TCGReg c1, int32_t c2, int c2const,
+                                int32_t v1, int v1const)
+{
+    /* For 64-bit signed comparisons vs zero, we can avoid the compare.
+       Note that the immediate range is one bit smaller, so we must check
+       for that as well.  */
+    if (c2 == 0 && !is_unsigned_cond(cond)
+        && (!v1const || check_fit_i32(v1, 10))) {
+        tcg_out_movr(s, cond, ret, c1, v1, v1const);
+    } else {
+        tcg_out_cmp(s, c1, c2, c2const);
+        tcg_out_movcc(s, cond, MOVCC_XCC, ret, v1, v1const);
+    }
+}
+
+static void tcg_out_setcond_i32(TCGContext *s, TCGCond cond, TCGReg ret,
+                                TCGReg c1, int32_t c2, int c2const)
+{
+    /* For 32-bit comparisons, we can play games with ADDC/SUBC.  */
+    switch (cond) {
+    case TCG_COND_LTU:
+    case TCG_COND_GEU:
+        /* The result of the comparison is in the carry bit.  */
+        break;
+
+    case TCG_COND_EQ:
+    case TCG_COND_NE:
+        /* For equality, we can transform to inequality vs zero.  */
+        if (c2 != 0) {
+            tcg_out_arithc(s, TCG_REG_T1, c1, c2, c2const, ARITH_XOR);
+            c2 = TCG_REG_T1;
+        } else {
+            c2 = c1;
+        }
+        c1 = TCG_REG_G0, c2const = 0;
+        cond = (cond == TCG_COND_EQ ? TCG_COND_GEU : TCG_COND_LTU);
+	break;
+
+    case TCG_COND_GTU:
+    case TCG_COND_LEU:
+        /* If we don't need to load a constant into a register, we can
+           swap the operands on GTU/LEU.  There's no benefit to loading
+           the constant into a temporary register.  */
+        if (!c2const || c2 == 0) {
+            TCGReg t = c1;
+            c1 = c2;
+            c2 = t;
+            c2const = 0;
+            cond = tcg_swap_cond(cond);
+            break;
+        }
+        /* FALLTHRU */
+
+    default:
+        tcg_out_cmp(s, c1, c2, c2const);
+        tcg_out_movi_imm13(s, ret, 0);
+        tcg_out_movcc(s, cond, MOVCC_ICC, ret, 1, 1);
+        return;
+    }
+
+    tcg_out_cmp(s, c1, c2, c2const);
+    if (cond == TCG_COND_LTU) {
+        tcg_out_arithi(s, ret, TCG_REG_G0, 0, ARITH_ADDC);
+    } else {
+        tcg_out_arithi(s, ret, TCG_REG_G0, -1, ARITH_SUBC);
+    }
+}
+
+static void tcg_out_setcond_i64(TCGContext *s, TCGCond cond, TCGReg ret,
+                                TCGReg c1, int32_t c2, int c2const)
+{
+    if (use_vis3_instructions) {
+        switch (cond) {
+        case TCG_COND_NE:
+            if (c2 != 0) {
+                break;
+            }
+            c2 = c1, c2const = 0, c1 = TCG_REG_G0;
+            /* FALLTHRU */
+        case TCG_COND_LTU:
+            tcg_out_cmp(s, c1, c2, c2const);
+            tcg_out_arith(s, ret, TCG_REG_G0, TCG_REG_G0, ARITH_ADDXC);
+            return;
+        default:
+            break;
+        }
+    }
+
+    /* For 64-bit signed comparisons vs zero, we can avoid the compare
+       if the input does not overlap the output.  */
+    if (c2 == 0 && !is_unsigned_cond(cond) && c1 != ret) {
+        tcg_out_movi_imm13(s, ret, 0);
+        tcg_out_movr(s, cond, ret, c1, 1, 1);
+    } else {
+        tcg_out_cmp(s, c1, c2, c2const);
+        tcg_out_movi_imm13(s, ret, 0);
+        tcg_out_movcc(s, cond, MOVCC_XCC, ret, 1, 1);
+    }
+}
+
+static void tcg_out_addsub2_i32(TCGContext *s, TCGReg rl, TCGReg rh,
+                                TCGReg al, TCGReg ah, int32_t bl, int blconst,
+                                int32_t bh, int bhconst, int opl, int oph)
+{
+    TCGReg tmp = TCG_REG_T1;
+
+    /* Note that the low parts are fully consumed before tmp is set.  */
+    if (rl != ah && (bhconst || rl != bh)) {
+        tmp = rl;
+    }
+
+    tcg_out_arithc(s, tmp, al, bl, blconst, opl);
+    tcg_out_arithc(s, rh, ah, bh, bhconst, oph);
+    tcg_out_mov(s, TCG_TYPE_I32, rl, tmp);
+}
+
+static void tcg_out_addsub2_i64(TCGContext *s, TCGReg rl, TCGReg rh,
+                                TCGReg al, TCGReg ah, int32_t bl, int blconst,
+                                int32_t bh, int bhconst, bool is_sub)
+{
+    TCGReg tmp = TCG_REG_T1;
+
+    /* Note that the low parts are fully consumed before tmp is set.  */
+    if (rl != ah && (bhconst || rl != bh)) {
+        tmp = rl;
+    }
+
+    tcg_out_arithc(s, tmp, al, bl, blconst, is_sub ? ARITH_SUBCC : ARITH_ADDCC);
+
+    if (use_vis3_instructions && !is_sub) {
+        /* Note that ADDXC doesn't accept immediates.  */
+        if (bhconst && bh != 0) {
+           tcg_out_movi(s, TCG_TYPE_I64, TCG_REG_T2, bh);
+           bh = TCG_REG_T2;
+        }
+        tcg_out_arith(s, rh, ah, bh, ARITH_ADDXC);
+    } else if (bh == TCG_REG_G0) {
+	/* If we have a zero, we can perform the operation in two insns,
+           with the arithmetic first, and a conditional move into place.  */
+	if (rh == ah) {
+            tcg_out_arithi(s, TCG_REG_T2, ah, 1,
+			   is_sub ? ARITH_SUB : ARITH_ADD);
+            tcg_out_movcc(s, TCG_COND_LTU, MOVCC_XCC, rh, TCG_REG_T2, 0);
+	} else {
+            tcg_out_arithi(s, rh, ah, 1, is_sub ? ARITH_SUB : ARITH_ADD);
+	    tcg_out_movcc(s, TCG_COND_GEU, MOVCC_XCC, rh, ah, 0);
+	}
+    } else {
+        /* Otherwise adjust BH as if there is carry into T2 ... */
+        if (bhconst) {
+            tcg_out_movi(s, TCG_TYPE_I64, TCG_REG_T2, bh + (is_sub ? -1 : 1));
+        } else {
+            tcg_out_arithi(s, TCG_REG_T2, bh, 1,
+                           is_sub ? ARITH_SUB : ARITH_ADD);
+        }
+        /* ... smoosh T2 back to original BH if carry is clear ... */
+        tcg_out_movcc(s, TCG_COND_GEU, MOVCC_XCC, TCG_REG_T2, bh, bhconst);
+	/* ... and finally perform the arithmetic with the new operand.  */
+        tcg_out_arith(s, rh, ah, TCG_REG_T2, is_sub ? ARITH_SUB : ARITH_ADD);
+    }
+
+    tcg_out_mov(s, TCG_TYPE_I64, rl, tmp);
+}
+
+static void tcg_out_call_nodelay(TCGContext *s, tcg_insn_unit *dest)
+{
+    ptrdiff_t disp = tcg_pcrel_diff(s, dest);
+
+    if (disp == (int32_t)disp) {
+        tcg_out32(s, CALL | (uint32_t)disp >> 2);
+    } else {
+        uintptr_t desti = (uintptr_t)dest;
+        tcg_out_movi(s, TCG_TYPE_PTR, TCG_REG_T1, desti & ~0xfff);
+        tcg_out_arithi(s, TCG_REG_O7, TCG_REG_T1, desti & 0xfff, JMPL);
+    }
+}
+
+static void tcg_out_call(TCGContext *s, tcg_insn_unit *dest)
+{
+    tcg_out_call_nodelay(s, dest);
+    tcg_out_nop(s);
+}
+
+#ifdef CONFIG_SOFTMMU
+static tcg_insn_unit *qemu_ld_trampoline[16];
+static tcg_insn_unit *qemu_st_trampoline[16];
+
+static void build_trampolines(TCGContext *s)
+{
+    static void * const qemu_ld_helpers[16] = {
+        [MO_UB]   = helper_ret_ldub_mmu,
+        [MO_SB]   = helper_ret_ldsb_mmu,
+        [MO_LEUW] = helper_le_lduw_mmu,
+        [MO_LESW] = helper_le_ldsw_mmu,
+        [MO_LEUL] = helper_le_ldul_mmu,
+        [MO_LEQ]  = helper_le_ldq_mmu,
+        [MO_BEUW] = helper_be_lduw_mmu,
+        [MO_BESW] = helper_be_ldsw_mmu,
+        [MO_BEUL] = helper_be_ldul_mmu,
+        [MO_BEQ]  = helper_be_ldq_mmu,
+    };
+    static void * const qemu_st_helpers[16] = {
+        [MO_UB]   = helper_ret_stb_mmu,
+        [MO_LEUW] = helper_le_stw_mmu,
+        [MO_LEUL] = helper_le_stl_mmu,
+        [MO_LEQ]  = helper_le_stq_mmu,
+        [MO_BEUW] = helper_be_stw_mmu,
+        [MO_BEUL] = helper_be_stl_mmu,
+        [MO_BEQ]  = helper_be_stq_mmu,
+    };
+
+    int i;
+    TCGReg ra;
+
+    for (i = 0; i < 16; ++i) {
+        if (qemu_ld_helpers[i] == NULL) {
+            continue;
+        }
+
+        /* May as well align the trampoline.  */
+        while ((uintptr_t)s->code_ptr & 15) {
+            tcg_out_nop(s);
+        }
+        qemu_ld_trampoline[i] = s->code_ptr;
+
+        if (SPARC64 || TARGET_LONG_BITS == 32) {
+            ra = TCG_REG_O3;
+        } else {
+            /* Install the high part of the address.  */
+            tcg_out_arithi(s, TCG_REG_O1, TCG_REG_O2, 32, SHIFT_SRLX);
+            ra = TCG_REG_O4;
+        }
+
+        /* Set the retaddr operand.  */
+        tcg_out_mov(s, TCG_TYPE_PTR, ra, TCG_REG_O7);
+        /* Set the env operand.  */
+        tcg_out_mov(s, TCG_TYPE_PTR, TCG_REG_O0, TCG_AREG0);
+        /* Tail call.  */
+        tcg_out_call_nodelay(s, qemu_ld_helpers[i]);
+        tcg_out_mov(s, TCG_TYPE_PTR, TCG_REG_O7, ra);
+    }
+
+    for (i = 0; i < 16; ++i) {
+        if (qemu_st_helpers[i] == NULL) {
+            continue;
+        }
+
+        /* May as well align the trampoline.  */
+        while ((uintptr_t)s->code_ptr & 15) {
+            tcg_out_nop(s);
+        }
+        qemu_st_trampoline[i] = s->code_ptr;
+
+        if (SPARC64) {
+            ra = TCG_REG_O4;
+        } else {
+            ra = TCG_REG_O1;
+            if (TARGET_LONG_BITS == 64) {
+                /* Install the high part of the address.  */
+                tcg_out_arithi(s, ra, ra + 1, 32, SHIFT_SRLX);
+                ra += 2;
+            } else {
+                ra += 1;
+            }
+            if ((i & MO_SIZE) == MO_64) {
+                /* Install the high part of the data.  */
+                tcg_out_arithi(s, ra, ra + 1, 32, SHIFT_SRLX);
+                ra += 2;
+            } else {
+                ra += 1;
+            }
+            /* Skip the oi argument.  */
+            ra += 1;
+        }
+                
+        /* Set the retaddr operand.  */
+        if (ra >= TCG_REG_O6) {
+            tcg_out_st(s, TCG_TYPE_PTR, TCG_REG_O7, TCG_REG_CALL_STACK,
+                       TCG_TARGET_CALL_STACK_OFFSET);
+            ra = TCG_REG_G1;
+        }
+        tcg_out_mov(s, TCG_TYPE_PTR, ra, TCG_REG_O7);
+        /* Set the env operand.  */
+        tcg_out_mov(s, TCG_TYPE_PTR, TCG_REG_O0, TCG_AREG0);
+        /* Tail call.  */
+        tcg_out_call_nodelay(s, qemu_st_helpers[i]);
+        tcg_out_mov(s, TCG_TYPE_PTR, TCG_REG_O7, ra);
+    }
+}
+#endif
+
+/* Generate global QEMU prologue and epilogue code */
+static void tcg_target_qemu_prologue(TCGContext *s)
+{
+    int tmp_buf_size, frame_size;
+
+    /* The TCG temp buffer is at the top of the frame, immediately
+       below the frame pointer.  */
+    tmp_buf_size = CPU_TEMP_BUF_NLONGS * (int)sizeof(long);
+    tcg_set_frame(s, TCG_REG_I6, TCG_TARGET_STACK_BIAS - tmp_buf_size,
+                  tmp_buf_size);
+
+    /* TCG_TARGET_CALL_STACK_OFFSET includes the stack bias, but is
+       otherwise the minimal frame usable by callees.  */
+    frame_size = TCG_TARGET_CALL_STACK_OFFSET - TCG_TARGET_STACK_BIAS;
+    frame_size += TCG_STATIC_CALL_ARGS_SIZE + tmp_buf_size;
+    frame_size += TCG_TARGET_STACK_ALIGN - 1;
+    frame_size &= -TCG_TARGET_STACK_ALIGN;
+    tcg_out32(s, SAVE | INSN_RD(TCG_REG_O6) | INSN_RS1(TCG_REG_O6) |
+              INSN_IMM13(-frame_size));
+
+#ifdef CONFIG_USE_GUEST_BASE
+    if (GUEST_BASE != 0) {
+        tcg_out_movi(s, TCG_TYPE_PTR, TCG_GUEST_BASE_REG, GUEST_BASE);
+        tcg_regset_set_reg(s->reserved_regs, TCG_GUEST_BASE_REG);
+    }
+#endif
+
+    tcg_out_arithi(s, TCG_REG_G0, TCG_REG_I1, 0, JMPL);
+    /* delay slot */
+    tcg_out_nop(s);
+
+    /* No epilogue required.  We issue ret + restore directly in the TB.  */
+
+#ifdef CONFIG_SOFTMMU
+    build_trampolines(s);
+#endif
+}
+
+#if defined(CONFIG_SOFTMMU)
+/* Perform the TLB load and compare.
+
+   Inputs:
+   ADDRLO and ADDRHI contain the possible two parts of the address.
+
+   MEM_INDEX and S_BITS are the memory context and log2 size of the load.
+
+   WHICH is the offset into the CPUTLBEntry structure of the slot to read.
+   This should be offsetof addr_read or addr_write.
+
+   The result of the TLB comparison is in %[ix]cc.  The sanitized address
+   is in the returned register, maybe %o0.  The TLB addend is in %o1.  */
+
+static TCGReg tcg_out_tlb_load(TCGContext *s, TCGReg addr, int mem_index,
+                               TCGMemOp s_bits, int which)
+{
+    const TCGReg r0 = TCG_REG_O0;
+    const TCGReg r1 = TCG_REG_O1;
+    const TCGReg r2 = TCG_REG_O2;
+    int tlb_ofs;
+
+    /* Shift the page number down.  */
+    tcg_out_arithi(s, r1, addr, TARGET_PAGE_BITS, SHIFT_SRL);
+
+    /* Mask out the page offset, except for the required alignment.  */
+    tcg_out_movi(s, TCG_TYPE_TL, TCG_REG_T1,
+                 TARGET_PAGE_MASK | ((1 << s_bits) - 1));
+
+    /* Mask the tlb index.  */
+    tcg_out_arithi(s, r1, r1, CPU_TLB_SIZE - 1, ARITH_AND);
+    
+    /* Mask page, part 2.  */
+    tcg_out_arith(s, r0, addr, TCG_REG_T1, ARITH_AND);
+
+    /* Shift the tlb index into place.  */
+    tcg_out_arithi(s, r1, r1, CPU_TLB_ENTRY_BITS, SHIFT_SLL);
+
+    /* Relative to the current ENV.  */
+    tcg_out_arith(s, r1, TCG_AREG0, r1, ARITH_ADD);
+
+    /* Find a base address that can load both tlb comparator and addend.  */
+    tlb_ofs = offsetof(CPUArchState, tlb_table[mem_index][0]);
+    if (!check_fit_ptr(tlb_ofs + sizeof(CPUTLBEntry), 13)) {
+        if (tlb_ofs & ~0x3ff) {
+            tcg_out_movi(s, TCG_TYPE_PTR, TCG_REG_T1, tlb_ofs & ~0x3ff);
+            tcg_out_arith(s, r1, r1, TCG_REG_T1, ARITH_ADD);
+        }
+        tlb_ofs &= 0x3ff;
+    }
+
+    /* Load the tlb comparator and the addend.  */
+    tcg_out_ld(s, TCG_TYPE_TL, r2, r1, tlb_ofs + which);
+    tcg_out_ld(s, TCG_TYPE_PTR, r1, r1, tlb_ofs+offsetof(CPUTLBEntry, addend));
+
+    /* subcc arg0, arg2, %g0 */
+    tcg_out_cmp(s, r0, r2, 0);
+
+    /* If the guest address must be zero-extended, do so now.  */
+    if (SPARC64 && TARGET_LONG_BITS == 32) {
+        tcg_out_arithi(s, r0, addr, 0, SHIFT_SRL);
+        return r0;
+    }
+    return addr;
+}
+#endif /* CONFIG_SOFTMMU */
+
+static const int qemu_ld_opc[16] = {
+    [MO_UB]   = LDUB,
+    [MO_SB]   = LDSB,
+
+    [MO_BEUW] = LDUH,
+    [MO_BESW] = LDSH,
+    [MO_BEUL] = LDUW,
+    [MO_BESL] = LDSW,
+    [MO_BEQ]  = LDX,
+
+    [MO_LEUW] = LDUH_LE,
+    [MO_LESW] = LDSH_LE,
+    [MO_LEUL] = LDUW_LE,
+    [MO_LESL] = LDSW_LE,
+    [MO_LEQ]  = LDX_LE,
+};
+
+static const int qemu_st_opc[16] = {
+    [MO_UB]   = STB,
+
+    [MO_BEUW] = STH,
+    [MO_BEUL] = STW,
+    [MO_BEQ]  = STX,
+
+    [MO_LEUW] = STH_LE,
+    [MO_LEUL] = STW_LE,
+    [MO_LEQ]  = STX_LE,
+};
+
+static void tcg_out_qemu_ld(TCGContext *s, TCGReg data, TCGReg addr,
+                            TCGMemOpIdx oi, bool is_64)
+{
+    TCGMemOp memop = get_memop(oi);
+#ifdef CONFIG_SOFTMMU
+    unsigned memi = get_mmuidx(oi);
+    TCGReg addrz, param;
+    tcg_insn_unit *func;
+    tcg_insn_unit *label_ptr;
+
+    addrz = tcg_out_tlb_load(s, addr, memi, memop & MO_SIZE,
+                             offsetof(CPUTLBEntry, addr_read));
+
+    /* The fast path is exactly one insn.  Thus we can perform the
+       entire TLB Hit in the (annulled) delay slot of the branch
+       over the TLB Miss case.  */
+
+    /* beq,a,pt %[xi]cc, label0 */
+    label_ptr = s->code_ptr;
+    tcg_out_bpcc0(s, COND_E, BPCC_A | BPCC_PT
+                  | (TARGET_LONG_BITS == 64 ? BPCC_XCC : BPCC_ICC), 0);
+    /* delay slot */
+    tcg_out_ldst_rr(s, data, addrz, TCG_REG_O1,
+                    qemu_ld_opc[memop & (MO_BSWAP | MO_SSIZE)]);
+
+    /* TLB Miss.  */
+
+    param = TCG_REG_O1;
+    if (!SPARC64 && TARGET_LONG_BITS == 64) {
+        /* Skip the high-part; we'll perform the extract in the trampoline.  */
+        param++;
+    }
+    tcg_out_mov(s, TCG_TYPE_REG, param++, addr);
+
+    /* We use the helpers to extend SB and SW data, leaving the case
+       of SL needing explicit extending below.  */
+    if ((memop & MO_SSIZE) == MO_SL) {
+        func = qemu_ld_trampoline[memop & (MO_BSWAP | MO_SIZE)];
+    } else {
+        func = qemu_ld_trampoline[memop & (MO_BSWAP | MO_SSIZE)];
+    }
+    assert(func != NULL);
+    tcg_out_call_nodelay(s, func);
+    /* delay slot */
+    tcg_out_movi(s, TCG_TYPE_I32, param, oi);
+
+    /* Recall that all of the helpers return 64-bit results.
+       Which complicates things for sparcv8plus.  */
+    if (SPARC64) {
+        /* We let the helper sign-extend SB and SW, but leave SL for here.  */
+        if (is_64 && (memop & MO_SSIZE) == MO_SL) {
+            tcg_out_arithi(s, data, TCG_REG_O0, 0, SHIFT_SRA);
+        } else {
+            tcg_out_mov(s, TCG_TYPE_REG, data, TCG_REG_O0);
+        }
+    } else {
+        if ((memop & MO_SIZE) == MO_64) {
+            tcg_out_arithi(s, TCG_REG_O0, TCG_REG_O0, 32, SHIFT_SLLX);
+            tcg_out_arithi(s, TCG_REG_O1, TCG_REG_O1, 0, SHIFT_SRL);
+            tcg_out_arith(s, data, TCG_REG_O0, TCG_REG_O1, ARITH_OR);
+        } else if (is_64) {
+            /* Re-extend from 32-bit rather than reassembling when we
+               know the high register must be an extension.  */
+            tcg_out_arithi(s, data, TCG_REG_O1, 0,
+                           memop & MO_SIGN ? SHIFT_SRA : SHIFT_SRL);
+        } else {
+            tcg_out_mov(s, TCG_TYPE_I32, data, TCG_REG_O1);
+        }
+    }
+
+    *label_ptr |= INSN_OFF19(tcg_ptr_byte_diff(s->code_ptr, label_ptr));
+#else
+    if (SPARC64 && TARGET_LONG_BITS == 32) {
+        tcg_out_arithi(s, TCG_REG_T1, addr, 0, SHIFT_SRL);
+        addr = TCG_REG_T1;
+    }
+    tcg_out_ldst_rr(s, data, addr,
+                    (GUEST_BASE ? TCG_GUEST_BASE_REG : TCG_REG_G0),
+                    qemu_ld_opc[memop & (MO_BSWAP | MO_SSIZE)]);
+#endif /* CONFIG_SOFTMMU */
+}
+
+static void tcg_out_qemu_st(TCGContext *s, TCGReg data, TCGReg addr,
+                            TCGMemOpIdx oi)
+{
+    TCGMemOp memop = get_memop(oi);
+#ifdef CONFIG_SOFTMMU
+    unsigned memi = get_mmuidx(oi);
+    TCGReg addrz, param;
+    tcg_insn_unit *func;
+    tcg_insn_unit *label_ptr;
+
+    addrz = tcg_out_tlb_load(s, addr, memi, memop & MO_SIZE,
+                             offsetof(CPUTLBEntry, addr_write));
+
+    /* The fast path is exactly one insn.  Thus we can perform the entire
+       TLB Hit in the (annulled) delay slot of the branch over TLB Miss.  */
+    /* beq,a,pt %[xi]cc, label0 */
+    label_ptr = s->code_ptr;
+    tcg_out_bpcc0(s, COND_E, BPCC_A | BPCC_PT
+                  | (TARGET_LONG_BITS == 64 ? BPCC_XCC : BPCC_ICC), 0);
+    /* delay slot */
+    tcg_out_ldst_rr(s, data, addrz, TCG_REG_O1,
+                    qemu_st_opc[memop & (MO_BSWAP | MO_SIZE)]);
+
+    /* TLB Miss.  */
+
+    param = TCG_REG_O1;
+    if (!SPARC64 && TARGET_LONG_BITS == 64) {
+        /* Skip the high-part; we'll perform the extract in the trampoline.  */
+        param++;
+    }
+    tcg_out_mov(s, TCG_TYPE_REG, param++, addr);
+    if (!SPARC64 && (memop & MO_SIZE) == MO_64) {
+        /* Skip the high-part; we'll perform the extract in the trampoline.  */
+        param++;
+    }
+    tcg_out_mov(s, TCG_TYPE_REG, param++, data);
+
+    func = qemu_st_trampoline[memop & (MO_BSWAP | MO_SIZE)];
+    assert(func != NULL);
+    tcg_out_call_nodelay(s, func);
+    /* delay slot */
+    tcg_out_movi(s, TCG_TYPE_I32, param, oi);
+
+    *label_ptr |= INSN_OFF19(tcg_ptr_byte_diff(s->code_ptr, label_ptr));
+#else
+    if (SPARC64 && TARGET_LONG_BITS == 32) {
+        tcg_out_arithi(s, TCG_REG_T1, addr, 0, SHIFT_SRL);
+        addr = TCG_REG_T1;
+    }
+    tcg_out_ldst_rr(s, data, addr,
+                    (GUEST_BASE ? TCG_GUEST_BASE_REG : TCG_REG_G0),
+                    qemu_st_opc[memop & (MO_BSWAP | MO_SIZE)]);
+#endif /* CONFIG_SOFTMMU */
+}
+
+static void tcg_out_op(TCGContext *s, TCGOpcode opc,
+                       const TCGArg args[TCG_MAX_OP_ARGS],
+                       const int const_args[TCG_MAX_OP_ARGS])
+{
+    TCGArg a0, a1, a2;
+    int c, c2;
+
+    /* Hoist the loads of the most common arguments.  */
+    a0 = args[0];
+    a1 = args[1];
+    a2 = args[2];
+    c2 = const_args[2];
+
+    switch (opc) {
+    case INDEX_op_exit_tb:
+        if (check_fit_ptr(a0, 13)) {
+            tcg_out_arithi(s, TCG_REG_G0, TCG_REG_I7, 8, RETURN);
+            tcg_out_movi_imm13(s, TCG_REG_O0, a0);
+        } else {
+            tcg_out_movi(s, TCG_TYPE_PTR, TCG_REG_I0, a0 & ~0x3ff);
+            tcg_out_arithi(s, TCG_REG_G0, TCG_REG_I7, 8, RETURN);
+            tcg_out_arithi(s, TCG_REG_O0, TCG_REG_O0, a0 & 0x3ff, ARITH_OR);
+        }
+        break;
+    case INDEX_op_goto_tb:
+        if (s->tb_jmp_offset) {
+            /* direct jump method */
+            s->tb_jmp_offset[a0] = tcg_current_code_size(s);
+            /* Make sure to preserve links during retranslation.  */
+            tcg_out32(s, CALL | (*s->code_ptr & ~INSN_OP(-1)));
+        } else {
+            /* indirect jump method */
+            tcg_out_ld_ptr(s, TCG_REG_T1, (uintptr_t)(s->tb_next + a0));
+            tcg_out_arithi(s, TCG_REG_G0, TCG_REG_T1, 0, JMPL);
+        }
+        tcg_out_nop(s);
+        s->tb_next_offset[a0] = tcg_current_code_size(s);
+        break;
+    case INDEX_op_br:
+        tcg_out_bpcc(s, COND_A, BPCC_PT, arg_label(a0));
+        tcg_out_nop(s);
+        break;
+
+#define OP_32_64(x)                             \
+        glue(glue(case INDEX_op_, x), _i32):    \
+        glue(glue(case INDEX_op_, x), _i64)
+
+    OP_32_64(ld8u):
+        tcg_out_ldst(s, a0, a1, a2, LDUB);
+        break;
+    OP_32_64(ld8s):
+        tcg_out_ldst(s, a0, a1, a2, LDSB);
+        break;
+    OP_32_64(ld16u):
+        tcg_out_ldst(s, a0, a1, a2, LDUH);
+        break;
+    OP_32_64(ld16s):
+        tcg_out_ldst(s, a0, a1, a2, LDSH);
+        break;
+    case INDEX_op_ld_i32:
+    case INDEX_op_ld32u_i64:
+        tcg_out_ldst(s, a0, a1, a2, LDUW);
+        break;
+    OP_32_64(st8):
+        tcg_out_ldst(s, a0, a1, a2, STB);
+        break;
+    OP_32_64(st16):
+        tcg_out_ldst(s, a0, a1, a2, STH);
+        break;
+    case INDEX_op_st_i32:
+    case INDEX_op_st32_i64:
+        tcg_out_ldst(s, a0, a1, a2, STW);
+        break;
+    OP_32_64(add):
+        c = ARITH_ADD;
+        goto gen_arith;
+    OP_32_64(sub):
+        c = ARITH_SUB;
+        goto gen_arith;
+    OP_32_64(and):
+        c = ARITH_AND;
+        goto gen_arith;
+    OP_32_64(andc):
+        c = ARITH_ANDN;
+        goto gen_arith;
+    OP_32_64(or):
+        c = ARITH_OR;
+        goto gen_arith;
+    OP_32_64(orc):
+        c = ARITH_ORN;
+        goto gen_arith;
+    OP_32_64(xor):
+        c = ARITH_XOR;
+        goto gen_arith;
+    case INDEX_op_shl_i32:
+        c = SHIFT_SLL;
+    do_shift32:
+        /* Limit immediate shift count lest we create an illegal insn.  */
+        tcg_out_arithc(s, a0, a1, a2 & 31, c2, c);
+        break;
+    case INDEX_op_shr_i32:
+        c = SHIFT_SRL;
+        goto do_shift32;
+    case INDEX_op_sar_i32:
+        c = SHIFT_SRA;
+        goto do_shift32;
+    case INDEX_op_mul_i32:
+        c = ARITH_UMUL;
+        goto gen_arith;
+
+    OP_32_64(neg):
+	c = ARITH_SUB;
+	goto gen_arith1;
+    OP_32_64(not):
+	c = ARITH_ORN;
+	goto gen_arith1;
+
+    case INDEX_op_div_i32:
+        tcg_out_div32(s, a0, a1, a2, c2, 0);
+        break;
+    case INDEX_op_divu_i32:
+        tcg_out_div32(s, a0, a1, a2, c2, 1);
+        break;
+
+    case INDEX_op_brcond_i32:
+        tcg_out_brcond_i32(s, a2, a0, a1, const_args[1], arg_label(args[3]));
+        break;
+    case INDEX_op_setcond_i32:
+        tcg_out_setcond_i32(s, args[3], a0, a1, a2, c2);
+        break;
+    case INDEX_op_movcond_i32:
+        tcg_out_movcond_i32(s, args[5], a0, a1, a2, c2, args[3], const_args[3]);
+        break;
+
+    case INDEX_op_add2_i32:
+        tcg_out_addsub2_i32(s, args[0], args[1], args[2], args[3],
+                            args[4], const_args[4], args[5], const_args[5],
+                            ARITH_ADDCC, ARITH_ADDC);
+        break;
+    case INDEX_op_sub2_i32:
+        tcg_out_addsub2_i32(s, args[0], args[1], args[2], args[3],
+                            args[4], const_args[4], args[5], const_args[5],
+                            ARITH_SUBCC, ARITH_SUBC);
+        break;
+    case INDEX_op_mulu2_i32:
+        c = ARITH_UMUL;
+        goto do_mul2;
+    case INDEX_op_muls2_i32:
+        c = ARITH_SMUL;
+    do_mul2:
+        /* The 32-bit multiply insns produce a full 64-bit result.  If the
+           destination register can hold it, we can avoid the slower RDY.  */
+        tcg_out_arithc(s, a0, a2, args[3], const_args[3], c);
+        if (SPARC64 || a0 <= TCG_REG_O7) {
+            tcg_out_arithi(s, a1, a0, 32, SHIFT_SRLX);
+        } else {
+            tcg_out_rdy(s, a1);
+        }
+        break;
+
+    case INDEX_op_qemu_ld_i32:
+        tcg_out_qemu_ld(s, a0, a1, a2, false);
+        break;
+    case INDEX_op_qemu_ld_i64:
+        tcg_out_qemu_ld(s, a0, a1, a2, true);
+        break;
+    case INDEX_op_qemu_st_i32:
+    case INDEX_op_qemu_st_i64:
+        tcg_out_qemu_st(s, a0, a1, a2);
+        break;
+
+    case INDEX_op_ld32s_i64:
+        tcg_out_ldst(s, a0, a1, a2, LDSW);
+        break;
+    case INDEX_op_ld_i64:
+        tcg_out_ldst(s, a0, a1, a2, LDX);
+        break;
+    case INDEX_op_st_i64:
+        tcg_out_ldst(s, a0, a1, a2, STX);
+        break;
+    case INDEX_op_shl_i64:
+        c = SHIFT_SLLX;
+    do_shift64:
+        /* Limit immediate shift count lest we create an illegal insn.  */
+        tcg_out_arithc(s, a0, a1, a2 & 63, c2, c);
+        break;
+    case INDEX_op_shr_i64:
+        c = SHIFT_SRLX;
+        goto do_shift64;
+    case INDEX_op_sar_i64:
+        c = SHIFT_SRAX;
+        goto do_shift64;
+    case INDEX_op_mul_i64:
+        c = ARITH_MULX;
+        goto gen_arith;
+    case INDEX_op_div_i64:
+        c = ARITH_SDIVX;
+        goto gen_arith;
+    case INDEX_op_divu_i64:
+        c = ARITH_UDIVX;
+        goto gen_arith;
+    case INDEX_op_ext32s_i64:
+        tcg_out_arithi(s, a0, a1, 0, SHIFT_SRA);
+        break;
+    case INDEX_op_ext32u_i64:
+        tcg_out_arithi(s, a0, a1, 0, SHIFT_SRL);
+        break;
+    case INDEX_op_trunc_shr_i32:
+        if (a2 == 0) {
+            tcg_out_mov(s, TCG_TYPE_I32, a0, a1);
+        } else {
+            tcg_out_arithi(s, a0, a1, a2, SHIFT_SRLX);
+        }
+        break;
+
+    case INDEX_op_brcond_i64:
+        tcg_out_brcond_i64(s, a2, a0, a1, const_args[1], arg_label(args[3]));
+        break;
+    case INDEX_op_setcond_i64:
+        tcg_out_setcond_i64(s, args[3], a0, a1, a2, c2);
+        break;
+    case INDEX_op_movcond_i64:
+        tcg_out_movcond_i64(s, args[5], a0, a1, a2, c2, args[3], const_args[3]);
+        break;
+    case INDEX_op_add2_i64:
+        tcg_out_addsub2_i64(s, args[0], args[1], args[2], args[3], args[4],
+                            const_args[4], args[5], const_args[5], false);
+        break;
+    case INDEX_op_sub2_i64:
+        tcg_out_addsub2_i64(s, args[0], args[1], args[2], args[3], args[4],
+                            const_args[4], args[5], const_args[5], true);
+        break;
+    case INDEX_op_muluh_i64:
+        tcg_out_arith(s, args[0], args[1], args[2], ARITH_UMULXHI);
+        break;
+
+    gen_arith:
+        tcg_out_arithc(s, a0, a1, a2, c2, c);
+        break;
+
+    gen_arith1:
+	tcg_out_arithc(s, a0, TCG_REG_G0, a1, const_args[1], c);
+	break;
+
+    case INDEX_op_mov_i32:  /* Always emitted via tcg_out_mov.  */
+    case INDEX_op_mov_i64:
+    case INDEX_op_movi_i32: /* Always emitted via tcg_out_movi.  */
+    case INDEX_op_movi_i64:
+    case INDEX_op_call:     /* Always emitted via tcg_out_call.  */
+    default:
+        tcg_abort();
+    }
+}
+
+static const TCGTargetOpDef sparc_op_defs[] = {
+    { INDEX_op_exit_tb, { } },
+    { INDEX_op_goto_tb, { } },
+    { INDEX_op_br, { } },
+
+    { INDEX_op_ld8u_i32, { "r", "r" } },
+    { INDEX_op_ld8s_i32, { "r", "r" } },
+    { INDEX_op_ld16u_i32, { "r", "r" } },
+    { INDEX_op_ld16s_i32, { "r", "r" } },
+    { INDEX_op_ld_i32, { "r", "r" } },
+    { INDEX_op_st8_i32, { "rZ", "r" } },
+    { INDEX_op_st16_i32, { "rZ", "r" } },
+    { INDEX_op_st_i32, { "rZ", "r" } },
+
+    { INDEX_op_add_i32, { "r", "rZ", "rJ" } },
+    { INDEX_op_mul_i32, { "r", "rZ", "rJ" } },
+    { INDEX_op_div_i32, { "r", "rZ", "rJ" } },
+    { INDEX_op_divu_i32, { "r", "rZ", "rJ" } },
+    { INDEX_op_sub_i32, { "r", "rZ", "rJ" } },
+    { INDEX_op_and_i32, { "r", "rZ", "rJ" } },
+    { INDEX_op_andc_i32, { "r", "rZ", "rJ" } },
+    { INDEX_op_or_i32, { "r", "rZ", "rJ" } },
+    { INDEX_op_orc_i32, { "r", "rZ", "rJ" } },
+    { INDEX_op_xor_i32, { "r", "rZ", "rJ" } },
+
+    { INDEX_op_shl_i32, { "r", "rZ", "rJ" } },
+    { INDEX_op_shr_i32, { "r", "rZ", "rJ" } },
+    { INDEX_op_sar_i32, { "r", "rZ", "rJ" } },
+
+    { INDEX_op_neg_i32, { "r", "rJ" } },
+    { INDEX_op_not_i32, { "r", "rJ" } },
+
+    { INDEX_op_brcond_i32, { "rZ", "rJ" } },
+    { INDEX_op_setcond_i32, { "r", "rZ", "rJ" } },
+    { INDEX_op_movcond_i32, { "r", "rZ", "rJ", "rI", "0" } },
+
+    { INDEX_op_add2_i32, { "r", "r", "rZ", "rZ", "rJ", "rJ" } },
+    { INDEX_op_sub2_i32, { "r", "r", "rZ", "rZ", "rJ", "rJ" } },
+    { INDEX_op_mulu2_i32, { "r", "r", "rZ", "rJ" } },
+    { INDEX_op_muls2_i32, { "r", "r", "rZ", "rJ" } },
+
+    { INDEX_op_ld8u_i64, { "R", "r" } },
+    { INDEX_op_ld8s_i64, { "R", "r" } },
+    { INDEX_op_ld16u_i64, { "R", "r" } },
+    { INDEX_op_ld16s_i64, { "R", "r" } },
+    { INDEX_op_ld32u_i64, { "R", "r" } },
+    { INDEX_op_ld32s_i64, { "R", "r" } },
+    { INDEX_op_ld_i64, { "R", "r" } },
+    { INDEX_op_st8_i64, { "RZ", "r" } },
+    { INDEX_op_st16_i64, { "RZ", "r" } },
+    { INDEX_op_st32_i64, { "RZ", "r" } },
+    { INDEX_op_st_i64, { "RZ", "r" } },
+
+    { INDEX_op_add_i64, { "R", "RZ", "RJ" } },
+    { INDEX_op_mul_i64, { "R", "RZ", "RJ" } },
+    { INDEX_op_div_i64, { "R", "RZ", "RJ" } },
+    { INDEX_op_divu_i64, { "R", "RZ", "RJ" } },
+    { INDEX_op_sub_i64, { "R", "RZ", "RJ" } },
+    { INDEX_op_and_i64, { "R", "RZ", "RJ" } },
+    { INDEX_op_andc_i64, { "R", "RZ", "RJ" } },
+    { INDEX_op_or_i64, { "R", "RZ", "RJ" } },
+    { INDEX_op_orc_i64, { "R", "RZ", "RJ" } },
+    { INDEX_op_xor_i64, { "R", "RZ", "RJ" } },
+
+    { INDEX_op_shl_i64, { "R", "RZ", "RJ" } },
+    { INDEX_op_shr_i64, { "R", "RZ", "RJ" } },
+    { INDEX_op_sar_i64, { "R", "RZ", "RJ" } },
+
+    { INDEX_op_neg_i64, { "R", "RJ" } },
+    { INDEX_op_not_i64, { "R", "RJ" } },
+
+    { INDEX_op_ext32s_i64, { "R", "r" } },
+    { INDEX_op_ext32u_i64, { "R", "r" } },
+    { INDEX_op_trunc_shr_i32,  { "r", "R" } },
+
+    { INDEX_op_brcond_i64, { "RZ", "RJ" } },
+    { INDEX_op_setcond_i64, { "R", "RZ", "RJ" } },
+    { INDEX_op_movcond_i64, { "R", "RZ", "RJ", "RI", "0" } },
+
+    { INDEX_op_add2_i64, { "R", "R", "RZ", "RZ", "RJ", "RI" } },
+    { INDEX_op_sub2_i64, { "R", "R", "RZ", "RZ", "RJ", "RI" } },
+    { INDEX_op_muluh_i64, { "R", "RZ", "RZ" } },
+
+    { INDEX_op_qemu_ld_i32, { "r", "A" } },
+    { INDEX_op_qemu_ld_i64, { "R", "A" } },
+    { INDEX_op_qemu_st_i32, { "sZ", "A" } },
+    { INDEX_op_qemu_st_i64, { "SZ", "A" } },
+
+    { -1 },
+};
+
+static void tcg_target_init(TCGContext *s)
+{
+    /* Only probe for the platform and capabilities if we havn't already
+       determined maximum values at compile time.  */
+#ifndef use_vis3_instructions
+    {
+        unsigned long hwcap = qemu_getauxval(AT_HWCAP);
+        use_vis3_instructions = (hwcap & HWCAP_SPARC_VIS3) != 0;
+    }
+#endif
+
+    tcg_regset_set32(tcg_target_available_regs[TCG_TYPE_I32], 0, 0xffffffff);
+    tcg_regset_set32(tcg_target_available_regs[TCG_TYPE_I64], 0, ALL_64);
+
+    tcg_regset_set32(tcg_target_call_clobber_regs, 0,
+                     (1 << TCG_REG_G1) |
+                     (1 << TCG_REG_G2) |
+                     (1 << TCG_REG_G3) |
+                     (1 << TCG_REG_G4) |
+                     (1 << TCG_REG_G5) |
+                     (1 << TCG_REG_G6) |
+                     (1 << TCG_REG_G7) |
+                     (1 << TCG_REG_O0) |
+                     (1 << TCG_REG_O1) |
+                     (1 << TCG_REG_O2) |
+                     (1 << TCG_REG_O3) |
+                     (1 << TCG_REG_O4) |
+                     (1 << TCG_REG_O5) |
+                     (1 << TCG_REG_O7));
+
+    tcg_regset_clear(s->reserved_regs);
+    tcg_regset_set_reg(s->reserved_regs, TCG_REG_G0); /* zero */
+    tcg_regset_set_reg(s->reserved_regs, TCG_REG_G6); /* reserved for os */
+    tcg_regset_set_reg(s->reserved_regs, TCG_REG_G7); /* thread pointer */
+    tcg_regset_set_reg(s->reserved_regs, TCG_REG_I6); /* frame pointer */
+    tcg_regset_set_reg(s->reserved_regs, TCG_REG_I7); /* return address */
+    tcg_regset_set_reg(s->reserved_regs, TCG_REG_O6); /* stack pointer */
+    tcg_regset_set_reg(s->reserved_regs, TCG_REG_T1); /* for internal use */
+    tcg_regset_set_reg(s->reserved_regs, TCG_REG_T2); /* for internal use */
+
+    tcg_add_target_add_op_defs(sparc_op_defs);
+}
+
+#if SPARC64
+# define ELF_HOST_MACHINE  EM_SPARCV9
+#else
+# define ELF_HOST_MACHINE  EM_SPARC32PLUS
+# define ELF_HOST_FLAGS    EF_SPARC_32PLUS
+#endif
+
+typedef struct {
+    DebugFrameHeader h;
+    uint8_t fde_def_cfa[SPARC64 ? 4 : 2];
+    uint8_t fde_win_save;
+    uint8_t fde_ret_save[3];
+} DebugFrame;
+
+static const DebugFrame debug_frame = {
+    .h.cie.len = sizeof(DebugFrameCIE)-4, /* length after .len member */
+    .h.cie.id = -1,
+    .h.cie.version = 1,
+    .h.cie.code_align = 1,
+    .h.cie.data_align = -sizeof(void *) & 0x7f,
+    .h.cie.return_column = 15,            /* o7 */
+
+    /* Total FDE size does not include the "len" member.  */
+    .h.fde.len = sizeof(DebugFrame) - offsetof(DebugFrame, h.fde.cie_offset),
+
+    .fde_def_cfa = {
+#if SPARC64
+        12, 30,                         /* DW_CFA_def_cfa i6, 2047 */
+        (2047 & 0x7f) | 0x80, (2047 >> 7)
+#else
+        13, 30                          /* DW_CFA_def_cfa_register i6 */
+#endif
+    },
+    .fde_win_save = 0x2d,               /* DW_CFA_GNU_window_save */
+    .fde_ret_save = { 9, 15, 31 },      /* DW_CFA_register o7, i7 */
+};
+
+void tcg_register_jit(void *buf, size_t buf_size)
+{
+    tcg_register_jit_int(buf, buf_size, &debug_frame, sizeof(debug_frame));
+}
+
+void tb_set_jmp_target1(uintptr_t jmp_addr, uintptr_t addr)
+{
+    uint32_t *ptr = (uint32_t *)jmp_addr;
+    uintptr_t disp = addr - jmp_addr;
+
+    /* We can reach the entire address space for 32-bit.  For 64-bit
+       the code_gen_buffer can't be larger than 2GB.  */
+    assert(disp == (int32_t)disp);
+
+    *ptr = CALL | (uint32_t)disp >> 2;
+    flush_icache_range(jmp_addr, jmp_addr + 4);
+}
diff --git a/tcg/sparc/tcg-target.h b/tcg/sparc/tcg-target.h
new file mode 100644
index 00000000..f584de47
--- /dev/null
+++ b/tcg/sparc/tcg-target.h
@@ -0,0 +1,160 @@
+/*
+ * Tiny Code Generator for QEMU
+ *
+ * Copyright (c) 2008 Fabrice Bellard
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (the "Software"), to deal
+ * in the Software without restriction, including without limitation the rights
+ * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+ * copies of the Software, and to permit persons to whom the Software is
+ * furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+ * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+ * THE SOFTWARE.
+ */
+#ifndef TCG_TARGET_SPARC 
+#define TCG_TARGET_SPARC 1
+
+#define TCG_TARGET_REG_BITS 64
+
+#define TCG_TARGET_INSN_UNIT_SIZE 4
+#define TCG_TARGET_TLB_DISPLACEMENT_BITS 32
+#define TCG_TARGET_NB_REGS 32
+
+typedef enum {
+    TCG_REG_G0 = 0,
+    TCG_REG_G1,
+    TCG_REG_G2,
+    TCG_REG_G3,
+    TCG_REG_G4,
+    TCG_REG_G5,
+    TCG_REG_G6,
+    TCG_REG_G7,
+    TCG_REG_O0,
+    TCG_REG_O1,
+    TCG_REG_O2,
+    TCG_REG_O3,
+    TCG_REG_O4,
+    TCG_REG_O5,
+    TCG_REG_O6,
+    TCG_REG_O7,
+    TCG_REG_L0,
+    TCG_REG_L1,
+    TCG_REG_L2,
+    TCG_REG_L3,
+    TCG_REG_L4,
+    TCG_REG_L5,
+    TCG_REG_L6,
+    TCG_REG_L7,
+    TCG_REG_I0,
+    TCG_REG_I1,
+    TCG_REG_I2,
+    TCG_REG_I3,
+    TCG_REG_I4,
+    TCG_REG_I5,
+    TCG_REG_I6,
+    TCG_REG_I7,
+} TCGReg;
+
+#define TCG_CT_CONST_S11  0x100
+#define TCG_CT_CONST_S13  0x200
+#define TCG_CT_CONST_ZERO 0x400
+
+/* used for function call generation */
+#define TCG_REG_CALL_STACK TCG_REG_O6
+
+#ifdef __arch64__
+#define TCG_TARGET_STACK_BIAS           2047
+#define TCG_TARGET_STACK_ALIGN          16
+#define TCG_TARGET_CALL_STACK_OFFSET    (128 + 6*8 + TCG_TARGET_STACK_BIAS)
+#else
+#define TCG_TARGET_STACK_BIAS           0
+#define TCG_TARGET_STACK_ALIGN          8
+#define TCG_TARGET_CALL_STACK_OFFSET    (64 + 4 + 6*4)
+#endif
+
+#ifdef __arch64__
+#define TCG_TARGET_EXTEND_ARGS 1
+#endif
+
+#if defined(__VIS__) && __VIS__ >= 0x300
+#define use_vis3_instructions  1
+#else
+extern bool use_vis3_instructions;
+#endif
+
+/* optional instructions */
+#define TCG_TARGET_HAS_div_i32		1
+#define TCG_TARGET_HAS_rem_i32		0
+#define TCG_TARGET_HAS_rot_i32          0
+#define TCG_TARGET_HAS_ext8s_i32        0
+#define TCG_TARGET_HAS_ext16s_i32       0
+#define TCG_TARGET_HAS_ext8u_i32        0
+#define TCG_TARGET_HAS_ext16u_i32       0
+#define TCG_TARGET_HAS_bswap16_i32      0
+#define TCG_TARGET_HAS_bswap32_i32      0
+#define TCG_TARGET_HAS_neg_i32          1
+#define TCG_TARGET_HAS_not_i32          1
+#define TCG_TARGET_HAS_andc_i32         1
+#define TCG_TARGET_HAS_orc_i32          1
+#define TCG_TARGET_HAS_eqv_i32          0
+#define TCG_TARGET_HAS_nand_i32         0
+#define TCG_TARGET_HAS_nor_i32          0
+#define TCG_TARGET_HAS_deposit_i32      0
+#define TCG_TARGET_HAS_movcond_i32      1
+#define TCG_TARGET_HAS_add2_i32         1
+#define TCG_TARGET_HAS_sub2_i32         1
+#define TCG_TARGET_HAS_mulu2_i32        1
+#define TCG_TARGET_HAS_muls2_i32        1
+#define TCG_TARGET_HAS_muluh_i32        0
+#define TCG_TARGET_HAS_mulsh_i32        0
+
+#define TCG_TARGET_HAS_trunc_shr_i32    1
+#define TCG_TARGET_HAS_div_i64          1
+#define TCG_TARGET_HAS_rem_i64          0
+#define TCG_TARGET_HAS_rot_i64          0
+#define TCG_TARGET_HAS_ext8s_i64        0
+#define TCG_TARGET_HAS_ext16s_i64       0
+#define TCG_TARGET_HAS_ext32s_i64       1
+#define TCG_TARGET_HAS_ext8u_i64        0
+#define TCG_TARGET_HAS_ext16u_i64       0
+#define TCG_TARGET_HAS_ext32u_i64       1
+#define TCG_TARGET_HAS_bswap16_i64      0
+#define TCG_TARGET_HAS_bswap32_i64      0
+#define TCG_TARGET_HAS_bswap64_i64      0
+#define TCG_TARGET_HAS_neg_i64          1
+#define TCG_TARGET_HAS_not_i64          1
+#define TCG_TARGET_HAS_andc_i64         1
+#define TCG_TARGET_HAS_orc_i64          1
+#define TCG_TARGET_HAS_eqv_i64          0
+#define TCG_TARGET_HAS_nand_i64         0
+#define TCG_TARGET_HAS_nor_i64          0
+#define TCG_TARGET_HAS_deposit_i64      0
+#define TCG_TARGET_HAS_movcond_i64      1
+#define TCG_TARGET_HAS_add2_i64         1
+#define TCG_TARGET_HAS_sub2_i64         1
+#define TCG_TARGET_HAS_mulu2_i64        0
+#define TCG_TARGET_HAS_muls2_i64        0
+#define TCG_TARGET_HAS_muluh_i64        use_vis3_instructions
+#define TCG_TARGET_HAS_mulsh_i64        0
+
+#define TCG_AREG0 TCG_REG_I0
+
+static inline void flush_icache_range(uintptr_t start, uintptr_t stop)
+{
+    uintptr_t p;
+    for (p = start & -8; p < ((stop + 7) & -8); p += 8) {
+        __asm__ __volatile__("flush\t%0" : : "r" (p));
+    }
+}
+
+#endif
diff --git a/tcg/tcg-be-ldst.h b/tcg/tcg-be-ldst.h
new file mode 100644
index 00000000..40a2369b
--- /dev/null
+++ b/tcg/tcg-be-ldst.h
@@ -0,0 +1,88 @@
+/*
+ * TCG Backend Data: load-store optimization only.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (the "Software"), to deal
+ * in the Software without restriction, including without limitation the rights
+ * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+ * copies of the Software, and to permit persons to whom the Software is
+ * furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+ * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+ * THE SOFTWARE.
+ */
+
+#ifdef CONFIG_SOFTMMU
+
+typedef struct TCGLabelQemuLdst {
+    bool is_ld;             /* qemu_ld: true, qemu_st: false */
+    TCGMemOpIdx oi;
+    TCGType type;           /* result type of a load */
+    TCGReg addrlo_reg;      /* reg index for low word of guest virtual addr */
+    TCGReg addrhi_reg;      /* reg index for high word of guest virtual addr */
+    TCGReg datalo_reg;      /* reg index for low word to be loaded or stored */
+    TCGReg datahi_reg;      /* reg index for high word to be loaded or stored */
+    tcg_insn_unit *raddr;   /* gen code addr of the next IR of qemu_ld/st IR */
+    tcg_insn_unit *label_ptr[2]; /* label pointers to be updated */
+    struct TCGLabelQemuLdst *next;
+} TCGLabelQemuLdst;
+
+typedef struct TCGBackendData {
+    TCGLabelQemuLdst *labels;
+} TCGBackendData;
+
+
+/*
+ * Initialize TB backend data at the beginning of the TB.
+ */
+
+static inline void tcg_out_tb_init(TCGContext *s)
+{
+    s->be->labels = NULL;
+}
+
+/*
+ * Generate TB finalization at the end of block
+ */
+
+static void tcg_out_qemu_ld_slow_path(TCGContext *s, TCGLabelQemuLdst *l);
+static void tcg_out_qemu_st_slow_path(TCGContext *s, TCGLabelQemuLdst *l);
+
+static void tcg_out_tb_finalize(TCGContext *s)
+{
+    TCGLabelQemuLdst *lb;
+
+    /* qemu_ld/st slow paths */
+    for (lb = s->be->labels; lb != NULL; lb = lb->next) {
+        if (lb->is_ld) {
+            tcg_out_qemu_ld_slow_path(s, lb);
+        } else {
+            tcg_out_qemu_st_slow_path(s, lb);
+        }
+    }
+}
+
+/*
+ * Allocate a new TCGLabelQemuLdst entry.
+ */
+
+static inline TCGLabelQemuLdst *new_ldst_label(TCGContext *s)
+{
+    TCGBackendData *be = s->be;
+    TCGLabelQemuLdst *l = tcg_malloc(sizeof(*l));
+
+    l->next = be->labels;
+    be->labels = l;
+    return l;
+}
+#else
+#include "tcg-be-null.h"
+#endif /* CONFIG_SOFTMMU */
diff --git a/tcg/tcg-be-null.h b/tcg/tcg-be-null.h
new file mode 100644
index 00000000..74c57d5a
--- /dev/null
+++ b/tcg/tcg-be-null.h
@@ -0,0 +1,43 @@
+/*
+ * TCG Backend Data: No backend data
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (the "Software"), to deal
+ * in the Software without restriction, including without limitation the rights
+ * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+ * copies of the Software, and to permit persons to whom the Software is
+ * furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+ * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+ * THE SOFTWARE.
+ */
+
+typedef struct TCGBackendData {
+    /* Empty */
+    char dummy;
+} TCGBackendData;
+
+
+/*
+ * Initialize TB backend data at the beginning of the TB.
+ */
+
+static inline void tcg_out_tb_init(TCGContext *s)
+{
+}
+
+/*
+ * Generate TB finalization at the end of block
+ */
+
+static inline void tcg_out_tb_finalize(TCGContext *s)
+{
+}
diff --git a/tcg/tcg-op.c b/tcg/tcg-op.c
new file mode 100644
index 00000000..45098c31
--- /dev/null
+++ b/tcg/tcg-op.c
@@ -0,0 +1,1945 @@
+/*
+ * Tiny Code Generator for QEMU
+ *
+ * Copyright (c) 2008 Fabrice Bellard
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (the "Software"), to deal
+ * in the Software without restriction, including without limitation the rights
+ * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+ * copies of the Software, and to permit persons to whom the Software is
+ * furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+ * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+ * THE SOFTWARE.
+ */
+
+#include "tcg.h"
+#include "tcg-op.h"
+
+/* Reduce the number of ifdefs below.  This assumes that all uses of
+   TCGV_HIGH and TCGV_LOW are properly protected by a conditional that
+   the compiler can eliminate.  */
+#if TCG_TARGET_REG_BITS == 64
+extern TCGv_i32 TCGV_LOW_link_error(TCGv_i64);
+extern TCGv_i32 TCGV_HIGH_link_error(TCGv_i64);
+#define TCGV_LOW  TCGV_LOW_link_error
+#define TCGV_HIGH TCGV_HIGH_link_error
+#endif
+
+/* Note that this is optimized for sequential allocation during translate.
+   Up to and including filling in the forward link immediately.  We'll do
+   proper termination of the end of the list after we finish translation.  */
+
+static void tcg_emit_op(TCGContext *ctx, TCGOpcode opc, int args)
+{
+    int oi = ctx->gen_next_op_idx;
+    int ni = oi + 1;
+    int pi = oi - 1;
+
+    tcg_debug_assert(oi < OPC_BUF_SIZE);
+    ctx->gen_last_op_idx = oi;
+    ctx->gen_next_op_idx = ni;
+
+    ctx->gen_op_buf[oi] = (TCGOp){
+        .opc = opc,
+        .args = args,
+        .prev = pi,
+        .next = ni
+    };
+}
+
+void tcg_gen_op1(TCGContext *ctx, TCGOpcode opc, TCGArg a1)
+{
+    int pi = ctx->gen_next_parm_idx;
+
+    tcg_debug_assert(pi + 1 <= OPPARAM_BUF_SIZE);
+    ctx->gen_next_parm_idx = pi + 1;
+    ctx->gen_opparam_buf[pi] = a1;
+
+    tcg_emit_op(ctx, opc, pi);
+}
+
+void tcg_gen_op2(TCGContext *ctx, TCGOpcode opc, TCGArg a1, TCGArg a2)
+{
+    int pi = ctx->gen_next_parm_idx;
+
+    tcg_debug_assert(pi + 2 <= OPPARAM_BUF_SIZE);
+    ctx->gen_next_parm_idx = pi + 2;
+    ctx->gen_opparam_buf[pi + 0] = a1;
+    ctx->gen_opparam_buf[pi + 1] = a2;
+
+    tcg_emit_op(ctx, opc, pi);
+}
+
+void tcg_gen_op3(TCGContext *ctx, TCGOpcode opc, TCGArg a1,
+                 TCGArg a2, TCGArg a3)
+{
+    int pi = ctx->gen_next_parm_idx;
+
+    tcg_debug_assert(pi + 3 <= OPPARAM_BUF_SIZE);
+    ctx->gen_next_parm_idx = pi + 3;
+    ctx->gen_opparam_buf[pi + 0] = a1;
+    ctx->gen_opparam_buf[pi + 1] = a2;
+    ctx->gen_opparam_buf[pi + 2] = a3;
+
+    tcg_emit_op(ctx, opc, pi);
+}
+
+void tcg_gen_op4(TCGContext *ctx, TCGOpcode opc, TCGArg a1,
+                 TCGArg a2, TCGArg a3, TCGArg a4)
+{
+    int pi = ctx->gen_next_parm_idx;
+
+    tcg_debug_assert(pi + 4 <= OPPARAM_BUF_SIZE);
+    ctx->gen_next_parm_idx = pi + 4;
+    ctx->gen_opparam_buf[pi + 0] = a1;
+    ctx->gen_opparam_buf[pi + 1] = a2;
+    ctx->gen_opparam_buf[pi + 2] = a3;
+    ctx->gen_opparam_buf[pi + 3] = a4;
+
+    tcg_emit_op(ctx, opc, pi);
+}
+
+void tcg_gen_op5(TCGContext *ctx, TCGOpcode opc, TCGArg a1,
+                 TCGArg a2, TCGArg a3, TCGArg a4, TCGArg a5)
+{
+    int pi = ctx->gen_next_parm_idx;
+
+    tcg_debug_assert(pi + 5 <= OPPARAM_BUF_SIZE);
+    ctx->gen_next_parm_idx = pi + 5;
+    ctx->gen_opparam_buf[pi + 0] = a1;
+    ctx->gen_opparam_buf[pi + 1] = a2;
+    ctx->gen_opparam_buf[pi + 2] = a3;
+    ctx->gen_opparam_buf[pi + 3] = a4;
+    ctx->gen_opparam_buf[pi + 4] = a5;
+
+    tcg_emit_op(ctx, opc, pi);
+}
+
+void tcg_gen_op6(TCGContext *ctx, TCGOpcode opc, TCGArg a1, TCGArg a2,
+                 TCGArg a3, TCGArg a4, TCGArg a5, TCGArg a6)
+{
+    int pi = ctx->gen_next_parm_idx;
+
+    tcg_debug_assert(pi + 6 <= OPPARAM_BUF_SIZE);
+    ctx->gen_next_parm_idx = pi + 6;
+    ctx->gen_opparam_buf[pi + 0] = a1;
+    ctx->gen_opparam_buf[pi + 1] = a2;
+    ctx->gen_opparam_buf[pi + 2] = a3;
+    ctx->gen_opparam_buf[pi + 3] = a4;
+    ctx->gen_opparam_buf[pi + 4] = a5;
+    ctx->gen_opparam_buf[pi + 5] = a6;
+
+    tcg_emit_op(ctx, opc, pi);
+}
+
+/* 32 bit ops */
+
+void tcg_gen_addi_i32(TCGv_i32 ret, TCGv_i32 arg1, int32_t arg2)
+{
+    /* some cases can be optimized here */
+    if (arg2 == 0) {
+        tcg_gen_mov_i32(ret, arg1);
+    } else {
+        TCGv_i32 t0 = tcg_const_i32(arg2);
+        tcg_gen_add_i32(ret, arg1, t0);
+        tcg_temp_free_i32(t0);
+    }
+}
+
+void tcg_gen_subfi_i32(TCGv_i32 ret, int32_t arg1, TCGv_i32 arg2)
+{
+    if (arg1 == 0 && TCG_TARGET_HAS_neg_i32) {
+        /* Don't recurse with tcg_gen_neg_i32.  */
+        tcg_gen_op2_i32(INDEX_op_neg_i32, ret, arg2);
+    } else {
+        TCGv_i32 t0 = tcg_const_i32(arg1);
+        tcg_gen_sub_i32(ret, t0, arg2);
+        tcg_temp_free_i32(t0);
+    }
+}
+
+void tcg_gen_subi_i32(TCGv_i32 ret, TCGv_i32 arg1, int32_t arg2)
+{
+    /* some cases can be optimized here */
+    if (arg2 == 0) {
+        tcg_gen_mov_i32(ret, arg1);
+    } else {
+        TCGv_i32 t0 = tcg_const_i32(arg2);
+        tcg_gen_sub_i32(ret, arg1, t0);
+        tcg_temp_free_i32(t0);
+    }
+}
+
+void tcg_gen_andi_i32(TCGv_i32 ret, TCGv_i32 arg1, uint32_t arg2)
+{
+    TCGv_i32 t0;
+    /* Some cases can be optimized here.  */
+    switch (arg2) {
+    case 0:
+        tcg_gen_movi_i32(ret, 0);
+        return;
+    case 0xffffffffu:
+        tcg_gen_mov_i32(ret, arg1);
+        return;
+    case 0xffu:
+        /* Don't recurse with tcg_gen_ext8u_i32.  */
+        if (TCG_TARGET_HAS_ext8u_i32) {
+            tcg_gen_op2_i32(INDEX_op_ext8u_i32, ret, arg1);
+            return;
+        }
+        break;
+    case 0xffffu:
+        if (TCG_TARGET_HAS_ext16u_i32) {
+            tcg_gen_op2_i32(INDEX_op_ext16u_i32, ret, arg1);
+            return;
+        }
+        break;
+    }
+    t0 = tcg_const_i32(arg2);
+    tcg_gen_and_i32(ret, arg1, t0);
+    tcg_temp_free_i32(t0);
+}
+
+void tcg_gen_ori_i32(TCGv_i32 ret, TCGv_i32 arg1, int32_t arg2)
+{
+    /* Some cases can be optimized here.  */
+    if (arg2 == -1) {
+        tcg_gen_movi_i32(ret, -1);
+    } else if (arg2 == 0) {
+        tcg_gen_mov_i32(ret, arg1);
+    } else {
+        TCGv_i32 t0 = tcg_const_i32(arg2);
+        tcg_gen_or_i32(ret, arg1, t0);
+        tcg_temp_free_i32(t0);
+    }
+}
+
+void tcg_gen_xori_i32(TCGv_i32 ret, TCGv_i32 arg1, int32_t arg2)
+{
+    /* Some cases can be optimized here.  */
+    if (arg2 == 0) {
+        tcg_gen_mov_i32(ret, arg1);
+    } else if (arg2 == -1 && TCG_TARGET_HAS_not_i32) {
+        /* Don't recurse with tcg_gen_not_i32.  */
+        tcg_gen_op2_i32(INDEX_op_not_i32, ret, arg1);
+    } else {
+        TCGv_i32 t0 = tcg_const_i32(arg2);
+        tcg_gen_xor_i32(ret, arg1, t0);
+        tcg_temp_free_i32(t0);
+    }
+}
+
+void tcg_gen_shli_i32(TCGv_i32 ret, TCGv_i32 arg1, unsigned arg2)
+{
+    tcg_debug_assert(arg2 < 32);
+    if (arg2 == 0) {
+        tcg_gen_mov_i32(ret, arg1);
+    } else {
+        TCGv_i32 t0 = tcg_const_i32(arg2);
+        tcg_gen_shl_i32(ret, arg1, t0);
+        tcg_temp_free_i32(t0);
+    }
+}
+
+void tcg_gen_shri_i32(TCGv_i32 ret, TCGv_i32 arg1, unsigned arg2)
+{
+    tcg_debug_assert(arg2 < 32);
+    if (arg2 == 0) {
+        tcg_gen_mov_i32(ret, arg1);
+    } else {
+        TCGv_i32 t0 = tcg_const_i32(arg2);
+        tcg_gen_shr_i32(ret, arg1, t0);
+        tcg_temp_free_i32(t0);
+    }
+}
+
+void tcg_gen_sari_i32(TCGv_i32 ret, TCGv_i32 arg1, unsigned arg2)
+{
+    tcg_debug_assert(arg2 < 32);
+    if (arg2 == 0) {
+        tcg_gen_mov_i32(ret, arg1);
+    } else {
+        TCGv_i32 t0 = tcg_const_i32(arg2);
+        tcg_gen_sar_i32(ret, arg1, t0);
+        tcg_temp_free_i32(t0);
+    }
+}
+
+void tcg_gen_brcond_i32(TCGCond cond, TCGv_i32 arg1, TCGv_i32 arg2, TCGLabel *l)
+{
+    if (cond == TCG_COND_ALWAYS) {
+        tcg_gen_br(l);
+    } else if (cond != TCG_COND_NEVER) {
+        tcg_gen_op4ii_i32(INDEX_op_brcond_i32, arg1, arg2, cond, label_arg(l));
+    }
+}
+
+void tcg_gen_brcondi_i32(TCGCond cond, TCGv_i32 arg1, int32_t arg2, TCGLabel *l)
+{
+    if (cond == TCG_COND_ALWAYS) {
+        tcg_gen_br(l);
+    } else if (cond != TCG_COND_NEVER) {
+        TCGv_i32 t0 = tcg_const_i32(arg2);
+        tcg_gen_brcond_i32(cond, arg1, t0, l);
+        tcg_temp_free_i32(t0);
+    }
+}
+
+void tcg_gen_setcond_i32(TCGCond cond, TCGv_i32 ret,
+                         TCGv_i32 arg1, TCGv_i32 arg2)
+{
+    if (cond == TCG_COND_ALWAYS) {
+        tcg_gen_movi_i32(ret, 1);
+    } else if (cond == TCG_COND_NEVER) {
+        tcg_gen_movi_i32(ret, 0);
+    } else {
+        tcg_gen_op4i_i32(INDEX_op_setcond_i32, ret, arg1, arg2, cond);
+    }
+}
+
+void tcg_gen_setcondi_i32(TCGCond cond, TCGv_i32 ret,
+                          TCGv_i32 arg1, int32_t arg2)
+{
+    TCGv_i32 t0 = tcg_const_i32(arg2);
+    tcg_gen_setcond_i32(cond, ret, arg1, t0);
+    tcg_temp_free_i32(t0);
+}
+
+void tcg_gen_muli_i32(TCGv_i32 ret, TCGv_i32 arg1, int32_t arg2)
+{
+    TCGv_i32 t0 = tcg_const_i32(arg2);
+    tcg_gen_mul_i32(ret, arg1, t0);
+    tcg_temp_free_i32(t0);
+}
+
+void tcg_gen_div_i32(TCGv_i32 ret, TCGv_i32 arg1, TCGv_i32 arg2)
+{
+    if (TCG_TARGET_HAS_div_i32) {
+        tcg_gen_op3_i32(INDEX_op_div_i32, ret, arg1, arg2);
+    } else if (TCG_TARGET_HAS_div2_i32) {
+        TCGv_i32 t0 = tcg_temp_new_i32();
+        tcg_gen_sari_i32(t0, arg1, 31);
+        tcg_gen_op5_i32(INDEX_op_div2_i32, ret, t0, arg1, t0, arg2);
+        tcg_temp_free_i32(t0);
+    } else {
+        gen_helper_div_i32(ret, arg1, arg2);
+    }
+}
+
+void tcg_gen_rem_i32(TCGv_i32 ret, TCGv_i32 arg1, TCGv_i32 arg2)
+{
+    if (TCG_TARGET_HAS_rem_i32) {
+        tcg_gen_op3_i32(INDEX_op_rem_i32, ret, arg1, arg2);
+    } else if (TCG_TARGET_HAS_div_i32) {
+        TCGv_i32 t0 = tcg_temp_new_i32();
+        tcg_gen_op3_i32(INDEX_op_div_i32, t0, arg1, arg2);
+        tcg_gen_mul_i32(t0, t0, arg2);
+        tcg_gen_sub_i32(ret, arg1, t0);
+        tcg_temp_free_i32(t0);
+    } else if (TCG_TARGET_HAS_div2_i32) {
+        TCGv_i32 t0 = tcg_temp_new_i32();
+        tcg_gen_sari_i32(t0, arg1, 31);
+        tcg_gen_op5_i32(INDEX_op_div2_i32, t0, ret, arg1, t0, arg2);
+        tcg_temp_free_i32(t0);
+    } else {
+        gen_helper_rem_i32(ret, arg1, arg2);
+    }
+}
+
+void tcg_gen_divu_i32(TCGv_i32 ret, TCGv_i32 arg1, TCGv_i32 arg2)
+{
+    if (TCG_TARGET_HAS_div_i32) {
+        tcg_gen_op3_i32(INDEX_op_divu_i32, ret, arg1, arg2);
+    } else if (TCG_TARGET_HAS_div2_i32) {
+        TCGv_i32 t0 = tcg_temp_new_i32();
+        tcg_gen_movi_i32(t0, 0);
+        tcg_gen_op5_i32(INDEX_op_divu2_i32, ret, t0, arg1, t0, arg2);
+        tcg_temp_free_i32(t0);
+    } else {
+        gen_helper_divu_i32(ret, arg1, arg2);
+    }
+}
+
+void tcg_gen_remu_i32(TCGv_i32 ret, TCGv_i32 arg1, TCGv_i32 arg2)
+{
+    if (TCG_TARGET_HAS_rem_i32) {
+        tcg_gen_op3_i32(INDEX_op_remu_i32, ret, arg1, arg2);
+    } else if (TCG_TARGET_HAS_div_i32) {
+        TCGv_i32 t0 = tcg_temp_new_i32();
+        tcg_gen_op3_i32(INDEX_op_divu_i32, t0, arg1, arg2);
+        tcg_gen_mul_i32(t0, t0, arg2);
+        tcg_gen_sub_i32(ret, arg1, t0);
+        tcg_temp_free_i32(t0);
+    } else if (TCG_TARGET_HAS_div2_i32) {
+        TCGv_i32 t0 = tcg_temp_new_i32();
+        tcg_gen_movi_i32(t0, 0);
+        tcg_gen_op5_i32(INDEX_op_divu2_i32, t0, ret, arg1, t0, arg2);
+        tcg_temp_free_i32(t0);
+    } else {
+        gen_helper_remu_i32(ret, arg1, arg2);
+    }
+}
+
+void tcg_gen_andc_i32(TCGv_i32 ret, TCGv_i32 arg1, TCGv_i32 arg2)
+{
+    if (TCG_TARGET_HAS_andc_i32) {
+        tcg_gen_op3_i32(INDEX_op_andc_i32, ret, arg1, arg2);
+    } else {
+        TCGv_i32 t0 = tcg_temp_new_i32();
+        tcg_gen_not_i32(t0, arg2);
+        tcg_gen_and_i32(ret, arg1, t0);
+        tcg_temp_free_i32(t0);
+    }
+}
+
+void tcg_gen_eqv_i32(TCGv_i32 ret, TCGv_i32 arg1, TCGv_i32 arg2)
+{
+    if (TCG_TARGET_HAS_eqv_i32) {
+        tcg_gen_op3_i32(INDEX_op_eqv_i32, ret, arg1, arg2);
+    } else {
+        tcg_gen_xor_i32(ret, arg1, arg2);
+        tcg_gen_not_i32(ret, ret);
+    }
+}
+
+void tcg_gen_nand_i32(TCGv_i32 ret, TCGv_i32 arg1, TCGv_i32 arg2)
+{
+    if (TCG_TARGET_HAS_nand_i32) {
+        tcg_gen_op3_i32(INDEX_op_nand_i32, ret, arg1, arg2);
+    } else {
+        tcg_gen_and_i32(ret, arg1, arg2);
+        tcg_gen_not_i32(ret, ret);
+    }
+}
+
+void tcg_gen_nor_i32(TCGv_i32 ret, TCGv_i32 arg1, TCGv_i32 arg2)
+{
+    if (TCG_TARGET_HAS_nor_i32) {
+        tcg_gen_op3_i32(INDEX_op_nor_i32, ret, arg1, arg2);
+    } else {
+        tcg_gen_or_i32(ret, arg1, arg2);
+        tcg_gen_not_i32(ret, ret);
+    }
+}
+
+void tcg_gen_orc_i32(TCGv_i32 ret, TCGv_i32 arg1, TCGv_i32 arg2)
+{
+    if (TCG_TARGET_HAS_orc_i32) {
+        tcg_gen_op3_i32(INDEX_op_orc_i32, ret, arg1, arg2);
+    } else {
+        TCGv_i32 t0 = tcg_temp_new_i32();
+        tcg_gen_not_i32(t0, arg2);
+        tcg_gen_or_i32(ret, arg1, t0);
+        tcg_temp_free_i32(t0);
+    }
+}
+
+void tcg_gen_rotl_i32(TCGv_i32 ret, TCGv_i32 arg1, TCGv_i32 arg2)
+{
+    if (TCG_TARGET_HAS_rot_i32) {
+        tcg_gen_op3_i32(INDEX_op_rotl_i32, ret, arg1, arg2);
+    } else {
+        TCGv_i32 t0, t1;
+
+        t0 = tcg_temp_new_i32();
+        t1 = tcg_temp_new_i32();
+        tcg_gen_shl_i32(t0, arg1, arg2);
+        tcg_gen_subfi_i32(t1, 32, arg2);
+        tcg_gen_shr_i32(t1, arg1, t1);
+        tcg_gen_or_i32(ret, t0, t1);
+        tcg_temp_free_i32(t0);
+        tcg_temp_free_i32(t1);
+    }
+}
+
+void tcg_gen_rotli_i32(TCGv_i32 ret, TCGv_i32 arg1, unsigned arg2)
+{
+    tcg_debug_assert(arg2 < 32);
+    /* some cases can be optimized here */
+    if (arg2 == 0) {
+        tcg_gen_mov_i32(ret, arg1);
+    } else if (TCG_TARGET_HAS_rot_i32) {
+        TCGv_i32 t0 = tcg_const_i32(arg2);
+        tcg_gen_rotl_i32(ret, arg1, t0);
+        tcg_temp_free_i32(t0);
+    } else {
+        TCGv_i32 t0, t1;
+        t0 = tcg_temp_new_i32();
+        t1 = tcg_temp_new_i32();
+        tcg_gen_shli_i32(t0, arg1, arg2);
+        tcg_gen_shri_i32(t1, arg1, 32 - arg2);
+        tcg_gen_or_i32(ret, t0, t1);
+        tcg_temp_free_i32(t0);
+        tcg_temp_free_i32(t1);
+    }
+}
+
+void tcg_gen_rotr_i32(TCGv_i32 ret, TCGv_i32 arg1, TCGv_i32 arg2)
+{
+    if (TCG_TARGET_HAS_rot_i32) {
+        tcg_gen_op3_i32(INDEX_op_rotr_i32, ret, arg1, arg2);
+    } else {
+        TCGv_i32 t0, t1;
+
+        t0 = tcg_temp_new_i32();
+        t1 = tcg_temp_new_i32();
+        tcg_gen_shr_i32(t0, arg1, arg2);
+        tcg_gen_subfi_i32(t1, 32, arg2);
+        tcg_gen_shl_i32(t1, arg1, t1);
+        tcg_gen_or_i32(ret, t0, t1);
+        tcg_temp_free_i32(t0);
+        tcg_temp_free_i32(t1);
+    }
+}
+
+void tcg_gen_rotri_i32(TCGv_i32 ret, TCGv_i32 arg1, unsigned arg2)
+{
+    tcg_debug_assert(arg2 < 32);
+    /* some cases can be optimized here */
+    if (arg2 == 0) {
+        tcg_gen_mov_i32(ret, arg1);
+    } else {
+        tcg_gen_rotli_i32(ret, arg1, 32 - arg2);
+    }
+}
+
+void tcg_gen_deposit_i32(TCGv_i32 ret, TCGv_i32 arg1, TCGv_i32 arg2,
+                         unsigned int ofs, unsigned int len)
+{
+    uint32_t mask;
+    TCGv_i32 t1;
+
+    tcg_debug_assert(ofs < 32);
+    tcg_debug_assert(len <= 32);
+    tcg_debug_assert(ofs + len <= 32);
+
+    if (ofs == 0 && len == 32) {
+        tcg_gen_mov_i32(ret, arg2);
+        return;
+    }
+    if (TCG_TARGET_HAS_deposit_i32 && TCG_TARGET_deposit_i32_valid(ofs, len)) {
+        tcg_gen_op5ii_i32(INDEX_op_deposit_i32, ret, arg1, arg2, ofs, len);
+        return;
+    }
+
+    mask = (1u << len) - 1;
+    t1 = tcg_temp_new_i32();
+
+    if (ofs + len < 32) {
+        tcg_gen_andi_i32(t1, arg2, mask);
+        tcg_gen_shli_i32(t1, t1, ofs);
+    } else {
+        tcg_gen_shli_i32(t1, arg2, ofs);
+    }
+    tcg_gen_andi_i32(ret, arg1, ~(mask << ofs));
+    tcg_gen_or_i32(ret, ret, t1);
+
+    tcg_temp_free_i32(t1);
+}
+
+void tcg_gen_movcond_i32(TCGCond cond, TCGv_i32 ret, TCGv_i32 c1,
+                         TCGv_i32 c2, TCGv_i32 v1, TCGv_i32 v2)
+{
+    if (cond == TCG_COND_ALWAYS) {
+        tcg_gen_mov_i32(ret, v1);
+    } else if (cond == TCG_COND_NEVER) {
+        tcg_gen_mov_i32(ret, v2);
+    } else if (TCG_TARGET_HAS_movcond_i32) {
+        tcg_gen_op6i_i32(INDEX_op_movcond_i32, ret, c1, c2, v1, v2, cond);
+    } else {
+        TCGv_i32 t0 = tcg_temp_new_i32();
+        TCGv_i32 t1 = tcg_temp_new_i32();
+        tcg_gen_setcond_i32(cond, t0, c1, c2);
+        tcg_gen_neg_i32(t0, t0);
+        tcg_gen_and_i32(t1, v1, t0);
+        tcg_gen_andc_i32(ret, v2, t0);
+        tcg_gen_or_i32(ret, ret, t1);
+        tcg_temp_free_i32(t0);
+        tcg_temp_free_i32(t1);
+    }
+}
+
+void tcg_gen_add2_i32(TCGv_i32 rl, TCGv_i32 rh, TCGv_i32 al,
+                      TCGv_i32 ah, TCGv_i32 bl, TCGv_i32 bh)
+{
+    if (TCG_TARGET_HAS_add2_i32) {
+        tcg_gen_op6_i32(INDEX_op_add2_i32, rl, rh, al, ah, bl, bh);
+    } else {
+        TCGv_i64 t0 = tcg_temp_new_i64();
+        TCGv_i64 t1 = tcg_temp_new_i64();
+        tcg_gen_concat_i32_i64(t0, al, ah);
+        tcg_gen_concat_i32_i64(t1, bl, bh);
+        tcg_gen_add_i64(t0, t0, t1);
+        tcg_gen_extr_i64_i32(rl, rh, t0);
+        tcg_temp_free_i64(t0);
+        tcg_temp_free_i64(t1);
+    }
+}
+
+void tcg_gen_sub2_i32(TCGv_i32 rl, TCGv_i32 rh, TCGv_i32 al,
+                      TCGv_i32 ah, TCGv_i32 bl, TCGv_i32 bh)
+{
+    if (TCG_TARGET_HAS_sub2_i32) {
+        tcg_gen_op6_i32(INDEX_op_sub2_i32, rl, rh, al, ah, bl, bh);
+    } else {
+        TCGv_i64 t0 = tcg_temp_new_i64();
+        TCGv_i64 t1 = tcg_temp_new_i64();
+        tcg_gen_concat_i32_i64(t0, al, ah);
+        tcg_gen_concat_i32_i64(t1, bl, bh);
+        tcg_gen_sub_i64(t0, t0, t1);
+        tcg_gen_extr_i64_i32(rl, rh, t0);
+        tcg_temp_free_i64(t0);
+        tcg_temp_free_i64(t1);
+    }
+}
+
+void tcg_gen_mulu2_i32(TCGv_i32 rl, TCGv_i32 rh, TCGv_i32 arg1, TCGv_i32 arg2)
+{
+    if (TCG_TARGET_HAS_mulu2_i32) {
+        tcg_gen_op4_i32(INDEX_op_mulu2_i32, rl, rh, arg1, arg2);
+    } else if (TCG_TARGET_HAS_muluh_i32) {
+        TCGv_i32 t = tcg_temp_new_i32();
+        tcg_gen_op3_i32(INDEX_op_mul_i32, t, arg1, arg2);
+        tcg_gen_op3_i32(INDEX_op_muluh_i32, rh, arg1, arg2);
+        tcg_gen_mov_i32(rl, t);
+        tcg_temp_free_i32(t);
+    } else {
+        TCGv_i64 t0 = tcg_temp_new_i64();
+        TCGv_i64 t1 = tcg_temp_new_i64();
+        tcg_gen_extu_i32_i64(t0, arg1);
+        tcg_gen_extu_i32_i64(t1, arg2);
+        tcg_gen_mul_i64(t0, t0, t1);
+        tcg_gen_extr_i64_i32(rl, rh, t0);
+        tcg_temp_free_i64(t0);
+        tcg_temp_free_i64(t1);
+    }
+}
+
+void tcg_gen_muls2_i32(TCGv_i32 rl, TCGv_i32 rh, TCGv_i32 arg1, TCGv_i32 arg2)
+{
+    if (TCG_TARGET_HAS_muls2_i32) {
+        tcg_gen_op4_i32(INDEX_op_muls2_i32, rl, rh, arg1, arg2);
+    } else if (TCG_TARGET_HAS_mulsh_i32) {
+        TCGv_i32 t = tcg_temp_new_i32();
+        tcg_gen_op3_i32(INDEX_op_mul_i32, t, arg1, arg2);
+        tcg_gen_op3_i32(INDEX_op_mulsh_i32, rh, arg1, arg2);
+        tcg_gen_mov_i32(rl, t);
+        tcg_temp_free_i32(t);
+    } else if (TCG_TARGET_REG_BITS == 32) {
+        TCGv_i32 t0 = tcg_temp_new_i32();
+        TCGv_i32 t1 = tcg_temp_new_i32();
+        TCGv_i32 t2 = tcg_temp_new_i32();
+        TCGv_i32 t3 = tcg_temp_new_i32();
+        tcg_gen_mulu2_i32(t0, t1, arg1, arg2);
+        /* Adjust for negative inputs.  */
+        tcg_gen_sari_i32(t2, arg1, 31);
+        tcg_gen_sari_i32(t3, arg2, 31);
+        tcg_gen_and_i32(t2, t2, arg2);
+        tcg_gen_and_i32(t3, t3, arg1);
+        tcg_gen_sub_i32(rh, t1, t2);
+        tcg_gen_sub_i32(rh, rh, t3);
+        tcg_gen_mov_i32(rl, t0);
+        tcg_temp_free_i32(t0);
+        tcg_temp_free_i32(t1);
+        tcg_temp_free_i32(t2);
+        tcg_temp_free_i32(t3);
+    } else {
+        TCGv_i64 t0 = tcg_temp_new_i64();
+        TCGv_i64 t1 = tcg_temp_new_i64();
+        tcg_gen_ext_i32_i64(t0, arg1);
+        tcg_gen_ext_i32_i64(t1, arg2);
+        tcg_gen_mul_i64(t0, t0, t1);
+        tcg_gen_extr_i64_i32(rl, rh, t0);
+        tcg_temp_free_i64(t0);
+        tcg_temp_free_i64(t1);
+    }
+}
+
+void tcg_gen_ext8s_i32(TCGv_i32 ret, TCGv_i32 arg)
+{
+    if (TCG_TARGET_HAS_ext8s_i32) {
+        tcg_gen_op2_i32(INDEX_op_ext8s_i32, ret, arg);
+    } else {
+        tcg_gen_shli_i32(ret, arg, 24);
+        tcg_gen_sari_i32(ret, ret, 24);
+    }
+}
+
+void tcg_gen_ext16s_i32(TCGv_i32 ret, TCGv_i32 arg)
+{
+    if (TCG_TARGET_HAS_ext16s_i32) {
+        tcg_gen_op2_i32(INDEX_op_ext16s_i32, ret, arg);
+    } else {
+        tcg_gen_shli_i32(ret, arg, 16);
+        tcg_gen_sari_i32(ret, ret, 16);
+    }
+}
+
+void tcg_gen_ext8u_i32(TCGv_i32 ret, TCGv_i32 arg)
+{
+    if (TCG_TARGET_HAS_ext8u_i32) {
+        tcg_gen_op2_i32(INDEX_op_ext8u_i32, ret, arg);
+    } else {
+        tcg_gen_andi_i32(ret, arg, 0xffu);
+    }
+}
+
+void tcg_gen_ext16u_i32(TCGv_i32 ret, TCGv_i32 arg)
+{
+    if (TCG_TARGET_HAS_ext16u_i32) {
+        tcg_gen_op2_i32(INDEX_op_ext16u_i32, ret, arg);
+    } else {
+        tcg_gen_andi_i32(ret, arg, 0xffffu);
+    }
+}
+
+/* Note: we assume the two high bytes are set to zero */
+void tcg_gen_bswap16_i32(TCGv_i32 ret, TCGv_i32 arg)
+{
+    if (TCG_TARGET_HAS_bswap16_i32) {
+        tcg_gen_op2_i32(INDEX_op_bswap16_i32, ret, arg);
+    } else {
+        TCGv_i32 t0 = tcg_temp_new_i32();
+
+        tcg_gen_ext8u_i32(t0, arg);
+        tcg_gen_shli_i32(t0, t0, 8);
+        tcg_gen_shri_i32(ret, arg, 8);
+        tcg_gen_or_i32(ret, ret, t0);
+        tcg_temp_free_i32(t0);
+    }
+}
+
+void tcg_gen_bswap32_i32(TCGv_i32 ret, TCGv_i32 arg)
+{
+    if (TCG_TARGET_HAS_bswap32_i32) {
+        tcg_gen_op2_i32(INDEX_op_bswap32_i32, ret, arg);
+    } else {
+        TCGv_i32 t0, t1;
+        t0 = tcg_temp_new_i32();
+        t1 = tcg_temp_new_i32();
+
+        tcg_gen_shli_i32(t0, arg, 24);
+
+        tcg_gen_andi_i32(t1, arg, 0x0000ff00);
+        tcg_gen_shli_i32(t1, t1, 8);
+        tcg_gen_or_i32(t0, t0, t1);
+
+        tcg_gen_shri_i32(t1, arg, 8);
+        tcg_gen_andi_i32(t1, t1, 0x0000ff00);
+        tcg_gen_or_i32(t0, t0, t1);
+
+        tcg_gen_shri_i32(t1, arg, 24);
+        tcg_gen_or_i32(ret, t0, t1);
+        tcg_temp_free_i32(t0);
+        tcg_temp_free_i32(t1);
+    }
+}
+
+/* 64-bit ops */
+
+#if TCG_TARGET_REG_BITS == 32
+/* These are all inline for TCG_TARGET_REG_BITS == 64.  */
+
+void tcg_gen_discard_i64(TCGv_i64 arg)
+{
+    tcg_gen_discard_i32(TCGV_LOW(arg));
+    tcg_gen_discard_i32(TCGV_HIGH(arg));
+}
+
+void tcg_gen_mov_i64(TCGv_i64 ret, TCGv_i64 arg)
+{
+    tcg_gen_mov_i32(TCGV_LOW(ret), TCGV_LOW(arg));
+    tcg_gen_mov_i32(TCGV_HIGH(ret), TCGV_HIGH(arg));
+}
+
+void tcg_gen_movi_i64(TCGv_i64 ret, int64_t arg)
+{
+    tcg_gen_movi_i32(TCGV_LOW(ret), arg);
+    tcg_gen_movi_i32(TCGV_HIGH(ret), arg >> 32);
+}
+
+void tcg_gen_ld8u_i64(TCGv_i64 ret, TCGv_ptr arg2, tcg_target_long offset)
+{
+    tcg_gen_ld8u_i32(TCGV_LOW(ret), arg2, offset);
+    tcg_gen_movi_i32(TCGV_HIGH(ret), 0);
+}
+
+void tcg_gen_ld8s_i64(TCGv_i64 ret, TCGv_ptr arg2, tcg_target_long offset)
+{
+    tcg_gen_ld8s_i32(TCGV_LOW(ret), arg2, offset);
+    tcg_gen_sari_i32(TCGV_HIGH(ret), TCGV_HIGH(ret), 31);
+}
+
+void tcg_gen_ld16u_i64(TCGv_i64 ret, TCGv_ptr arg2, tcg_target_long offset)
+{
+    tcg_gen_ld16u_i32(TCGV_LOW(ret), arg2, offset);
+    tcg_gen_movi_i32(TCGV_HIGH(ret), 0);
+}
+
+void tcg_gen_ld16s_i64(TCGv_i64 ret, TCGv_ptr arg2, tcg_target_long offset)
+{
+    tcg_gen_ld16s_i32(TCGV_LOW(ret), arg2, offset);
+    tcg_gen_sari_i32(TCGV_HIGH(ret), TCGV_LOW(ret), 31);
+}
+
+void tcg_gen_ld32u_i64(TCGv_i64 ret, TCGv_ptr arg2, tcg_target_long offset)
+{
+    tcg_gen_ld_i32(TCGV_LOW(ret), arg2, offset);
+    tcg_gen_movi_i32(TCGV_HIGH(ret), 0);
+}
+
+void tcg_gen_ld32s_i64(TCGv_i64 ret, TCGv_ptr arg2, tcg_target_long offset)
+{
+    tcg_gen_ld_i32(TCGV_LOW(ret), arg2, offset);
+    tcg_gen_sari_i32(TCGV_HIGH(ret), TCGV_LOW(ret), 31);
+}
+
+void tcg_gen_ld_i64(TCGv_i64 ret, TCGv_ptr arg2, tcg_target_long offset)
+{
+    /* Since arg2 and ret have different types,
+       they cannot be the same temporary */
+#ifdef HOST_WORDS_BIGENDIAN
+    tcg_gen_ld_i32(TCGV_HIGH(ret), arg2, offset);
+    tcg_gen_ld_i32(TCGV_LOW(ret), arg2, offset + 4);
+#else
+    tcg_gen_ld_i32(TCGV_LOW(ret), arg2, offset);
+    tcg_gen_ld_i32(TCGV_HIGH(ret), arg2, offset + 4);
+#endif
+}
+
+void tcg_gen_st_i64(TCGv_i64 arg1, TCGv_ptr arg2, tcg_target_long offset)
+{
+#ifdef HOST_WORDS_BIGENDIAN
+    tcg_gen_st_i32(TCGV_HIGH(arg1), arg2, offset);
+    tcg_gen_st_i32(TCGV_LOW(arg1), arg2, offset + 4);
+#else
+    tcg_gen_st_i32(TCGV_LOW(arg1), arg2, offset);
+    tcg_gen_st_i32(TCGV_HIGH(arg1), arg2, offset + 4);
+#endif
+}
+
+void tcg_gen_and_i64(TCGv_i64 ret, TCGv_i64 arg1, TCGv_i64 arg2)
+{
+    tcg_gen_and_i32(TCGV_LOW(ret), TCGV_LOW(arg1), TCGV_LOW(arg2));
+    tcg_gen_and_i32(TCGV_HIGH(ret), TCGV_HIGH(arg1), TCGV_HIGH(arg2));
+}
+
+void tcg_gen_or_i64(TCGv_i64 ret, TCGv_i64 arg1, TCGv_i64 arg2)
+{
+    tcg_gen_or_i32(TCGV_LOW(ret), TCGV_LOW(arg1), TCGV_LOW(arg2));
+    tcg_gen_or_i32(TCGV_HIGH(ret), TCGV_HIGH(arg1), TCGV_HIGH(arg2));
+}
+
+void tcg_gen_xor_i64(TCGv_i64 ret, TCGv_i64 arg1, TCGv_i64 arg2)
+{
+    tcg_gen_xor_i32(TCGV_LOW(ret), TCGV_LOW(arg1), TCGV_LOW(arg2));
+    tcg_gen_xor_i32(TCGV_HIGH(ret), TCGV_HIGH(arg1), TCGV_HIGH(arg2));
+}
+
+void tcg_gen_shl_i64(TCGv_i64 ret, TCGv_i64 arg1, TCGv_i64 arg2)
+{
+    gen_helper_shl_i64(ret, arg1, arg2);
+}
+
+void tcg_gen_shr_i64(TCGv_i64 ret, TCGv_i64 arg1, TCGv_i64 arg2)
+{
+    gen_helper_shr_i64(ret, arg1, arg2);
+}
+
+void tcg_gen_sar_i64(TCGv_i64 ret, TCGv_i64 arg1, TCGv_i64 arg2)
+{
+    gen_helper_sar_i64(ret, arg1, arg2);
+}
+
+void tcg_gen_mul_i64(TCGv_i64 ret, TCGv_i64 arg1, TCGv_i64 arg2)
+{
+    TCGv_i64 t0;
+    TCGv_i32 t1;
+
+    t0 = tcg_temp_new_i64();
+    t1 = tcg_temp_new_i32();
+
+    tcg_gen_mulu2_i32(TCGV_LOW(t0), TCGV_HIGH(t0),
+                      TCGV_LOW(arg1), TCGV_LOW(arg2));
+
+    tcg_gen_mul_i32(t1, TCGV_LOW(arg1), TCGV_HIGH(arg2));
+    tcg_gen_add_i32(TCGV_HIGH(t0), TCGV_HIGH(t0), t1);
+    tcg_gen_mul_i32(t1, TCGV_HIGH(arg1), TCGV_LOW(arg2));
+    tcg_gen_add_i32(TCGV_HIGH(t0), TCGV_HIGH(t0), t1);
+
+    tcg_gen_mov_i64(ret, t0);
+    tcg_temp_free_i64(t0);
+    tcg_temp_free_i32(t1);
+}
+#endif /* TCG_TARGET_REG_SIZE == 32 */
+
+void tcg_gen_addi_i64(TCGv_i64 ret, TCGv_i64 arg1, int64_t arg2)
+{
+    /* some cases can be optimized here */
+    if (arg2 == 0) {
+        tcg_gen_mov_i64(ret, arg1);
+    } else {
+        TCGv_i64 t0 = tcg_const_i64(arg2);
+        tcg_gen_add_i64(ret, arg1, t0);
+        tcg_temp_free_i64(t0);
+    }
+}
+
+void tcg_gen_subfi_i64(TCGv_i64 ret, int64_t arg1, TCGv_i64 arg2)
+{
+    if (arg1 == 0 && TCG_TARGET_HAS_neg_i64) {
+        /* Don't recurse with tcg_gen_neg_i64.  */
+        tcg_gen_op2_i64(INDEX_op_neg_i64, ret, arg2);
+    } else {
+        TCGv_i64 t0 = tcg_const_i64(arg1);
+        tcg_gen_sub_i64(ret, t0, arg2);
+        tcg_temp_free_i64(t0);
+    }
+}
+
+void tcg_gen_subi_i64(TCGv_i64 ret, TCGv_i64 arg1, int64_t arg2)
+{
+    /* some cases can be optimized here */
+    if (arg2 == 0) {
+        tcg_gen_mov_i64(ret, arg1);
+    } else {
+        TCGv_i64 t0 = tcg_const_i64(arg2);
+        tcg_gen_sub_i64(ret, arg1, t0);
+        tcg_temp_free_i64(t0);
+    }
+}
+
+void tcg_gen_andi_i64(TCGv_i64 ret, TCGv_i64 arg1, uint64_t arg2)
+{
+    TCGv_i64 t0;
+
+    if (TCG_TARGET_REG_BITS == 32) {
+        tcg_gen_andi_i32(TCGV_LOW(ret), TCGV_LOW(arg1), arg2);
+        tcg_gen_andi_i32(TCGV_HIGH(ret), TCGV_HIGH(arg1), arg2 >> 32);
+        return;
+    }
+
+    /* Some cases can be optimized here.  */
+    switch (arg2) {
+    case 0:
+        tcg_gen_movi_i64(ret, 0);
+        return;
+    case 0xffffffffffffffffull:
+        tcg_gen_mov_i64(ret, arg1);
+        return;
+    case 0xffull:
+        /* Don't recurse with tcg_gen_ext8u_i64.  */
+        if (TCG_TARGET_HAS_ext8u_i64) {
+            tcg_gen_op2_i64(INDEX_op_ext8u_i64, ret, arg1);
+            return;
+        }
+        break;
+    case 0xffffu:
+        if (TCG_TARGET_HAS_ext16u_i64) {
+            tcg_gen_op2_i64(INDEX_op_ext16u_i64, ret, arg1);
+            return;
+        }
+        break;
+    case 0xffffffffull:
+        if (TCG_TARGET_HAS_ext32u_i64) {
+            tcg_gen_op2_i64(INDEX_op_ext32u_i64, ret, arg1);
+            return;
+        }
+        break;
+    }
+    t0 = tcg_const_i64(arg2);
+    tcg_gen_and_i64(ret, arg1, t0);
+    tcg_temp_free_i64(t0);
+}
+
+void tcg_gen_ori_i64(TCGv_i64 ret, TCGv_i64 arg1, int64_t arg2)
+{
+    if (TCG_TARGET_REG_BITS == 32) {
+        tcg_gen_ori_i32(TCGV_LOW(ret), TCGV_LOW(arg1), arg2);
+        tcg_gen_ori_i32(TCGV_HIGH(ret), TCGV_HIGH(arg1), arg2 >> 32);
+        return;
+    }
+    /* Some cases can be optimized here.  */
+    if (arg2 == -1) {
+        tcg_gen_movi_i64(ret, -1);
+    } else if (arg2 == 0) {
+        tcg_gen_mov_i64(ret, arg1);
+    } else {
+        TCGv_i64 t0 = tcg_const_i64(arg2);
+        tcg_gen_or_i64(ret, arg1, t0);
+        tcg_temp_free_i64(t0);
+    }
+}
+
+void tcg_gen_xori_i64(TCGv_i64 ret, TCGv_i64 arg1, int64_t arg2)
+{
+    if (TCG_TARGET_REG_BITS == 32) {
+        tcg_gen_xori_i32(TCGV_LOW(ret), TCGV_LOW(arg1), arg2);
+        tcg_gen_xori_i32(TCGV_HIGH(ret), TCGV_HIGH(arg1), arg2 >> 32);
+        return;
+    }
+    /* Some cases can be optimized here.  */
+    if (arg2 == 0) {
+        tcg_gen_mov_i64(ret, arg1);
+    } else if (arg2 == -1 && TCG_TARGET_HAS_not_i64) {
+        /* Don't recurse with tcg_gen_not_i64.  */
+        tcg_gen_op2_i64(INDEX_op_not_i64, ret, arg1);
+    } else {
+        TCGv_i64 t0 = tcg_const_i64(arg2);
+        tcg_gen_xor_i64(ret, arg1, t0);
+        tcg_temp_free_i64(t0);
+    }
+}
+
+static inline void tcg_gen_shifti_i64(TCGv_i64 ret, TCGv_i64 arg1,
+                                      unsigned c, bool right, bool arith)
+{
+    tcg_debug_assert(c < 64);
+    if (c == 0) {
+        tcg_gen_mov_i32(TCGV_LOW(ret), TCGV_LOW(arg1));
+        tcg_gen_mov_i32(TCGV_HIGH(ret), TCGV_HIGH(arg1));
+    } else if (c >= 32) {
+        c -= 32;
+        if (right) {
+            if (arith) {
+                tcg_gen_sari_i32(TCGV_LOW(ret), TCGV_HIGH(arg1), c);
+                tcg_gen_sari_i32(TCGV_HIGH(ret), TCGV_HIGH(arg1), 31);
+            } else {
+                tcg_gen_shri_i32(TCGV_LOW(ret), TCGV_HIGH(arg1), c);
+                tcg_gen_movi_i32(TCGV_HIGH(ret), 0);
+            }
+        } else {
+            tcg_gen_shli_i32(TCGV_HIGH(ret), TCGV_LOW(arg1), c);
+            tcg_gen_movi_i32(TCGV_LOW(ret), 0);
+        }
+    } else {
+        TCGv_i32 t0, t1;
+
+        t0 = tcg_temp_new_i32();
+        t1 = tcg_temp_new_i32();
+        if (right) {
+            tcg_gen_shli_i32(t0, TCGV_HIGH(arg1), 32 - c);
+            if (arith) {
+                tcg_gen_sari_i32(t1, TCGV_HIGH(arg1), c);
+            } else {
+                tcg_gen_shri_i32(t1, TCGV_HIGH(arg1), c);
+            }
+            tcg_gen_shri_i32(TCGV_LOW(ret), TCGV_LOW(arg1), c);
+            tcg_gen_or_i32(TCGV_LOW(ret), TCGV_LOW(ret), t0);
+            tcg_gen_mov_i32(TCGV_HIGH(ret), t1);
+        } else {
+            tcg_gen_shri_i32(t0, TCGV_LOW(arg1), 32 - c);
+            /* Note: ret can be the same as arg1, so we use t1 */
+            tcg_gen_shli_i32(t1, TCGV_LOW(arg1), c);
+            tcg_gen_shli_i32(TCGV_HIGH(ret), TCGV_HIGH(arg1), c);
+            tcg_gen_or_i32(TCGV_HIGH(ret), TCGV_HIGH(ret), t0);
+            tcg_gen_mov_i32(TCGV_LOW(ret), t1);
+        }
+        tcg_temp_free_i32(t0);
+        tcg_temp_free_i32(t1);
+    }
+}
+
+void tcg_gen_shli_i64(TCGv_i64 ret, TCGv_i64 arg1, unsigned arg2)
+{
+    tcg_debug_assert(arg2 < 64);
+    if (TCG_TARGET_REG_BITS == 32) {
+        tcg_gen_shifti_i64(ret, arg1, arg2, 0, 0);
+    } else if (arg2 == 0) {
+        tcg_gen_mov_i64(ret, arg1);
+    } else {
+        TCGv_i64 t0 = tcg_const_i64(arg2);
+        tcg_gen_shl_i64(ret, arg1, t0);
+        tcg_temp_free_i64(t0);
+    }
+}
+
+void tcg_gen_shri_i64(TCGv_i64 ret, TCGv_i64 arg1, unsigned arg2)
+{
+    tcg_debug_assert(arg2 < 64);
+    if (TCG_TARGET_REG_BITS == 32) {
+        tcg_gen_shifti_i64(ret, arg1, arg2, 1, 0);
+    } else if (arg2 == 0) {
+        tcg_gen_mov_i64(ret, arg1);
+    } else {
+        TCGv_i64 t0 = tcg_const_i64(arg2);
+        tcg_gen_shr_i64(ret, arg1, t0);
+        tcg_temp_free_i64(t0);
+    }
+}
+
+void tcg_gen_sari_i64(TCGv_i64 ret, TCGv_i64 arg1, unsigned arg2)
+{
+    tcg_debug_assert(arg2 < 64);
+    if (TCG_TARGET_REG_BITS == 32) {
+        tcg_gen_shifti_i64(ret, arg1, arg2, 1, 1);
+    } else if (arg2 == 0) {
+        tcg_gen_mov_i64(ret, arg1);
+    } else {
+        TCGv_i64 t0 = tcg_const_i64(arg2);
+        tcg_gen_sar_i64(ret, arg1, t0);
+        tcg_temp_free_i64(t0);
+    }
+}
+
+void tcg_gen_brcond_i64(TCGCond cond, TCGv_i64 arg1, TCGv_i64 arg2, TCGLabel *l)
+{
+    if (cond == TCG_COND_ALWAYS) {
+        tcg_gen_br(l);
+    } else if (cond != TCG_COND_NEVER) {
+        if (TCG_TARGET_REG_BITS == 32) {
+            tcg_gen_op6ii_i32(INDEX_op_brcond2_i32, TCGV_LOW(arg1),
+                              TCGV_HIGH(arg1), TCGV_LOW(arg2),
+                              TCGV_HIGH(arg2), cond, label_arg(l));
+        } else {
+            tcg_gen_op4ii_i64(INDEX_op_brcond_i64, arg1, arg2, cond,
+                              label_arg(l));
+        }
+    }
+}
+
+void tcg_gen_brcondi_i64(TCGCond cond, TCGv_i64 arg1, int64_t arg2, TCGLabel *l)
+{
+    if (cond == TCG_COND_ALWAYS) {
+        tcg_gen_br(l);
+    } else if (cond != TCG_COND_NEVER) {
+        TCGv_i64 t0 = tcg_const_i64(arg2);
+        tcg_gen_brcond_i64(cond, arg1, t0, l);
+        tcg_temp_free_i64(t0);
+    }
+}
+
+void tcg_gen_setcond_i64(TCGCond cond, TCGv_i64 ret,
+                         TCGv_i64 arg1, TCGv_i64 arg2)
+{
+    if (cond == TCG_COND_ALWAYS) {
+        tcg_gen_movi_i64(ret, 1);
+    } else if (cond == TCG_COND_NEVER) {
+        tcg_gen_movi_i64(ret, 0);
+    } else {
+        if (TCG_TARGET_REG_BITS == 32) {
+            tcg_gen_op6i_i32(INDEX_op_setcond2_i32, TCGV_LOW(ret),
+                             TCGV_LOW(arg1), TCGV_HIGH(arg1),
+                             TCGV_LOW(arg2), TCGV_HIGH(arg2), cond);
+            tcg_gen_movi_i32(TCGV_HIGH(ret), 0);
+        } else {
+            tcg_gen_op4i_i64(INDEX_op_setcond_i64, ret, arg1, arg2, cond);
+        }
+    }
+}
+
+void tcg_gen_setcondi_i64(TCGCond cond, TCGv_i64 ret,
+                          TCGv_i64 arg1, int64_t arg2)
+{
+    TCGv_i64 t0 = tcg_const_i64(arg2);
+    tcg_gen_setcond_i64(cond, ret, arg1, t0);
+    tcg_temp_free_i64(t0);
+}
+
+void tcg_gen_muli_i64(TCGv_i64 ret, TCGv_i64 arg1, int64_t arg2)
+{
+    TCGv_i64 t0 = tcg_const_i64(arg2);
+    tcg_gen_mul_i64(ret, arg1, t0);
+    tcg_temp_free_i64(t0);
+}
+
+void tcg_gen_div_i64(TCGv_i64 ret, TCGv_i64 arg1, TCGv_i64 arg2)
+{
+    if (TCG_TARGET_HAS_div_i64) {
+        tcg_gen_op3_i64(INDEX_op_div_i64, ret, arg1, arg2);
+    } else if (TCG_TARGET_HAS_div2_i64) {
+        TCGv_i64 t0 = tcg_temp_new_i64();
+        tcg_gen_sari_i64(t0, arg1, 63);
+        tcg_gen_op5_i64(INDEX_op_div2_i64, ret, t0, arg1, t0, arg2);
+        tcg_temp_free_i64(t0);
+    } else {
+        gen_helper_div_i64(ret, arg1, arg2);
+    }
+}
+
+void tcg_gen_rem_i64(TCGv_i64 ret, TCGv_i64 arg1, TCGv_i64 arg2)
+{
+    if (TCG_TARGET_HAS_rem_i64) {
+        tcg_gen_op3_i64(INDEX_op_rem_i64, ret, arg1, arg2);
+    } else if (TCG_TARGET_HAS_div_i64) {
+        TCGv_i64 t0 = tcg_temp_new_i64();
+        tcg_gen_op3_i64(INDEX_op_div_i64, t0, arg1, arg2);
+        tcg_gen_mul_i64(t0, t0, arg2);
+        tcg_gen_sub_i64(ret, arg1, t0);
+        tcg_temp_free_i64(t0);
+    } else if (TCG_TARGET_HAS_div2_i64) {
+        TCGv_i64 t0 = tcg_temp_new_i64();
+        tcg_gen_sari_i64(t0, arg1, 63);
+        tcg_gen_op5_i64(INDEX_op_div2_i64, t0, ret, arg1, t0, arg2);
+        tcg_temp_free_i64(t0);
+    } else {
+        gen_helper_rem_i64(ret, arg1, arg2);
+    }
+}
+
+void tcg_gen_divu_i64(TCGv_i64 ret, TCGv_i64 arg1, TCGv_i64 arg2)
+{
+    if (TCG_TARGET_HAS_div_i64) {
+        tcg_gen_op3_i64(INDEX_op_divu_i64, ret, arg1, arg2);
+    } else if (TCG_TARGET_HAS_div2_i64) {
+        TCGv_i64 t0 = tcg_temp_new_i64();
+        tcg_gen_movi_i64(t0, 0);
+        tcg_gen_op5_i64(INDEX_op_divu2_i64, ret, t0, arg1, t0, arg2);
+        tcg_temp_free_i64(t0);
+    } else {
+        gen_helper_divu_i64(ret, arg1, arg2);
+    }
+}
+
+void tcg_gen_remu_i64(TCGv_i64 ret, TCGv_i64 arg1, TCGv_i64 arg2)
+{
+    if (TCG_TARGET_HAS_rem_i64) {
+        tcg_gen_op3_i64(INDEX_op_remu_i64, ret, arg1, arg2);
+    } else if (TCG_TARGET_HAS_div_i64) {
+        TCGv_i64 t0 = tcg_temp_new_i64();
+        tcg_gen_op3_i64(INDEX_op_divu_i64, t0, arg1, arg2);
+        tcg_gen_mul_i64(t0, t0, arg2);
+        tcg_gen_sub_i64(ret, arg1, t0);
+        tcg_temp_free_i64(t0);
+    } else if (TCG_TARGET_HAS_div2_i64) {
+        TCGv_i64 t0 = tcg_temp_new_i64();
+        tcg_gen_movi_i64(t0, 0);
+        tcg_gen_op5_i64(INDEX_op_divu2_i64, t0, ret, arg1, t0, arg2);
+        tcg_temp_free_i64(t0);
+    } else {
+        gen_helper_remu_i64(ret, arg1, arg2);
+    }
+}
+
+void tcg_gen_ext8s_i64(TCGv_i64 ret, TCGv_i64 arg)
+{
+    if (TCG_TARGET_REG_BITS == 32) {
+        tcg_gen_ext8s_i32(TCGV_LOW(ret), TCGV_LOW(arg));
+        tcg_gen_sari_i32(TCGV_HIGH(ret), TCGV_LOW(ret), 31);
+    } else if (TCG_TARGET_HAS_ext8s_i64) {
+        tcg_gen_op2_i64(INDEX_op_ext8s_i64, ret, arg);
+    } else {
+        tcg_gen_shli_i64(ret, arg, 56);
+        tcg_gen_sari_i64(ret, ret, 56);
+    }
+}
+
+void tcg_gen_ext16s_i64(TCGv_i64 ret, TCGv_i64 arg)
+{
+    if (TCG_TARGET_REG_BITS == 32) {
+        tcg_gen_ext16s_i32(TCGV_LOW(ret), TCGV_LOW(arg));
+        tcg_gen_sari_i32(TCGV_HIGH(ret), TCGV_LOW(ret), 31);
+    } else if (TCG_TARGET_HAS_ext16s_i64) {
+        tcg_gen_op2_i64(INDEX_op_ext16s_i64, ret, arg);
+    } else {
+        tcg_gen_shli_i64(ret, arg, 48);
+        tcg_gen_sari_i64(ret, ret, 48);
+    }
+}
+
+void tcg_gen_ext32s_i64(TCGv_i64 ret, TCGv_i64 arg)
+{
+    if (TCG_TARGET_REG_BITS == 32) {
+        tcg_gen_mov_i32(TCGV_LOW(ret), TCGV_LOW(arg));
+        tcg_gen_sari_i32(TCGV_HIGH(ret), TCGV_LOW(ret), 31);
+    } else if (TCG_TARGET_HAS_ext32s_i64) {
+        tcg_gen_op2_i64(INDEX_op_ext32s_i64, ret, arg);
+    } else {
+        tcg_gen_shli_i64(ret, arg, 32);
+        tcg_gen_sari_i64(ret, ret, 32);
+    }
+}
+
+void tcg_gen_ext8u_i64(TCGv_i64 ret, TCGv_i64 arg)
+{
+    if (TCG_TARGET_REG_BITS == 32) {
+        tcg_gen_ext8u_i32(TCGV_LOW(ret), TCGV_LOW(arg));
+        tcg_gen_movi_i32(TCGV_HIGH(ret), 0);
+    } else if (TCG_TARGET_HAS_ext8u_i64) {
+        tcg_gen_op2_i64(INDEX_op_ext8u_i64, ret, arg);
+    } else {
+        tcg_gen_andi_i64(ret, arg, 0xffu);
+    }
+}
+
+void tcg_gen_ext16u_i64(TCGv_i64 ret, TCGv_i64 arg)
+{
+    if (TCG_TARGET_REG_BITS == 32) {
+        tcg_gen_ext16u_i32(TCGV_LOW(ret), TCGV_LOW(arg));
+        tcg_gen_movi_i32(TCGV_HIGH(ret), 0);
+    } else if (TCG_TARGET_HAS_ext16u_i64) {
+        tcg_gen_op2_i64(INDEX_op_ext16u_i64, ret, arg);
+    } else {
+        tcg_gen_andi_i64(ret, arg, 0xffffu);
+    }
+}
+
+void tcg_gen_ext32u_i64(TCGv_i64 ret, TCGv_i64 arg)
+{
+    if (TCG_TARGET_REG_BITS == 32) {
+        tcg_gen_mov_i32(TCGV_LOW(ret), TCGV_LOW(arg));
+        tcg_gen_movi_i32(TCGV_HIGH(ret), 0);
+    } else if (TCG_TARGET_HAS_ext32u_i64) {
+        tcg_gen_op2_i64(INDEX_op_ext32u_i64, ret, arg);
+    } else {
+        tcg_gen_andi_i64(ret, arg, 0xffffffffu);
+    }
+}
+
+/* Note: we assume the six high bytes are set to zero */
+void tcg_gen_bswap16_i64(TCGv_i64 ret, TCGv_i64 arg)
+{
+    if (TCG_TARGET_REG_BITS == 32) {
+        tcg_gen_bswap16_i32(TCGV_LOW(ret), TCGV_LOW(arg));
+        tcg_gen_movi_i32(TCGV_HIGH(ret), 0);
+    } else if (TCG_TARGET_HAS_bswap16_i64) {
+        tcg_gen_op2_i64(INDEX_op_bswap16_i64, ret, arg);
+    } else {
+        TCGv_i64 t0 = tcg_temp_new_i64();
+
+        tcg_gen_ext8u_i64(t0, arg);
+        tcg_gen_shli_i64(t0, t0, 8);
+        tcg_gen_shri_i64(ret, arg, 8);
+        tcg_gen_or_i64(ret, ret, t0);
+        tcg_temp_free_i64(t0);
+    }
+}
+
+/* Note: we assume the four high bytes are set to zero */
+void tcg_gen_bswap32_i64(TCGv_i64 ret, TCGv_i64 arg)
+{
+    if (TCG_TARGET_REG_BITS == 32) {
+        tcg_gen_bswap32_i32(TCGV_LOW(ret), TCGV_LOW(arg));
+        tcg_gen_movi_i32(TCGV_HIGH(ret), 0);
+    } else if (TCG_TARGET_HAS_bswap32_i64) {
+        tcg_gen_op2_i64(INDEX_op_bswap32_i64, ret, arg);
+    } else {
+        TCGv_i64 t0, t1;
+        t0 = tcg_temp_new_i64();
+        t1 = tcg_temp_new_i64();
+
+        tcg_gen_shli_i64(t0, arg, 24);
+        tcg_gen_ext32u_i64(t0, t0);
+
+        tcg_gen_andi_i64(t1, arg, 0x0000ff00);
+        tcg_gen_shli_i64(t1, t1, 8);
+        tcg_gen_or_i64(t0, t0, t1);
+
+        tcg_gen_shri_i64(t1, arg, 8);
+        tcg_gen_andi_i64(t1, t1, 0x0000ff00);
+        tcg_gen_or_i64(t0, t0, t1);
+
+        tcg_gen_shri_i64(t1, arg, 24);
+        tcg_gen_or_i64(ret, t0, t1);
+        tcg_temp_free_i64(t0);
+        tcg_temp_free_i64(t1);
+    }
+}
+
+void tcg_gen_bswap64_i64(TCGv_i64 ret, TCGv_i64 arg)
+{
+    if (TCG_TARGET_REG_BITS == 32) {
+        TCGv_i32 t0, t1;
+        t0 = tcg_temp_new_i32();
+        t1 = tcg_temp_new_i32();
+
+        tcg_gen_bswap32_i32(t0, TCGV_LOW(arg));
+        tcg_gen_bswap32_i32(t1, TCGV_HIGH(arg));
+        tcg_gen_mov_i32(TCGV_LOW(ret), t1);
+        tcg_gen_mov_i32(TCGV_HIGH(ret), t0);
+        tcg_temp_free_i32(t0);
+        tcg_temp_free_i32(t1);
+    } else if (TCG_TARGET_HAS_bswap64_i64) {
+        tcg_gen_op2_i64(INDEX_op_bswap64_i64, ret, arg);
+    } else {
+        TCGv_i64 t0 = tcg_temp_new_i64();
+        TCGv_i64 t1 = tcg_temp_new_i64();
+
+        tcg_gen_shli_i64(t0, arg, 56);
+
+        tcg_gen_andi_i64(t1, arg, 0x0000ff00);
+        tcg_gen_shli_i64(t1, t1, 40);
+        tcg_gen_or_i64(t0, t0, t1);
+
+        tcg_gen_andi_i64(t1, arg, 0x00ff0000);
+        tcg_gen_shli_i64(t1, t1, 24);
+        tcg_gen_or_i64(t0, t0, t1);
+
+        tcg_gen_andi_i64(t1, arg, 0xff000000);
+        tcg_gen_shli_i64(t1, t1, 8);
+        tcg_gen_or_i64(t0, t0, t1);
+
+        tcg_gen_shri_i64(t1, arg, 8);
+        tcg_gen_andi_i64(t1, t1, 0xff000000);
+        tcg_gen_or_i64(t0, t0, t1);
+
+        tcg_gen_shri_i64(t1, arg, 24);
+        tcg_gen_andi_i64(t1, t1, 0x00ff0000);
+        tcg_gen_or_i64(t0, t0, t1);
+
+        tcg_gen_shri_i64(t1, arg, 40);
+        tcg_gen_andi_i64(t1, t1, 0x0000ff00);
+        tcg_gen_or_i64(t0, t0, t1);
+
+        tcg_gen_shri_i64(t1, arg, 56);
+        tcg_gen_or_i64(ret, t0, t1);
+        tcg_temp_free_i64(t0);
+        tcg_temp_free_i64(t1);
+    }
+}
+
+void tcg_gen_not_i64(TCGv_i64 ret, TCGv_i64 arg)
+{
+    if (TCG_TARGET_REG_BITS == 32) {
+        tcg_gen_not_i32(TCGV_LOW(ret), TCGV_LOW(arg));
+        tcg_gen_not_i32(TCGV_HIGH(ret), TCGV_HIGH(arg));
+    } else if (TCG_TARGET_HAS_not_i64) {
+        tcg_gen_op2_i64(INDEX_op_not_i64, ret, arg);
+    } else {
+        tcg_gen_xori_i64(ret, arg, -1);
+    }
+}
+
+void tcg_gen_andc_i64(TCGv_i64 ret, TCGv_i64 arg1, TCGv_i64 arg2)
+{
+    if (TCG_TARGET_REG_BITS == 32) {
+        tcg_gen_andc_i32(TCGV_LOW(ret), TCGV_LOW(arg1), TCGV_LOW(arg2));
+        tcg_gen_andc_i32(TCGV_HIGH(ret), TCGV_HIGH(arg1), TCGV_HIGH(arg2));
+    } else if (TCG_TARGET_HAS_andc_i64) {
+        tcg_gen_op3_i64(INDEX_op_andc_i64, ret, arg1, arg2);
+    } else {
+        TCGv_i64 t0 = tcg_temp_new_i64();
+        tcg_gen_not_i64(t0, arg2);
+        tcg_gen_and_i64(ret, arg1, t0);
+        tcg_temp_free_i64(t0);
+    }
+}
+
+void tcg_gen_eqv_i64(TCGv_i64 ret, TCGv_i64 arg1, TCGv_i64 arg2)
+{
+    if (TCG_TARGET_REG_BITS == 32) {
+        tcg_gen_eqv_i32(TCGV_LOW(ret), TCGV_LOW(arg1), TCGV_LOW(arg2));
+        tcg_gen_eqv_i32(TCGV_HIGH(ret), TCGV_HIGH(arg1), TCGV_HIGH(arg2));
+    } else if (TCG_TARGET_HAS_eqv_i64) {
+        tcg_gen_op3_i64(INDEX_op_eqv_i64, ret, arg1, arg2);
+    } else {
+        tcg_gen_xor_i64(ret, arg1, arg2);
+        tcg_gen_not_i64(ret, ret);
+    }
+}
+
+void tcg_gen_nand_i64(TCGv_i64 ret, TCGv_i64 arg1, TCGv_i64 arg2)
+{
+    if (TCG_TARGET_REG_BITS == 32) {
+        tcg_gen_nand_i32(TCGV_LOW(ret), TCGV_LOW(arg1), TCGV_LOW(arg2));
+        tcg_gen_nand_i32(TCGV_HIGH(ret), TCGV_HIGH(arg1), TCGV_HIGH(arg2));
+    } else if (TCG_TARGET_HAS_nand_i64) {
+        tcg_gen_op3_i64(INDEX_op_nand_i64, ret, arg1, arg2);
+    } else {
+        tcg_gen_and_i64(ret, arg1, arg2);
+        tcg_gen_not_i64(ret, ret);
+    }
+}
+
+void tcg_gen_nor_i64(TCGv_i64 ret, TCGv_i64 arg1, TCGv_i64 arg2)
+{
+    if (TCG_TARGET_REG_BITS == 32) {
+        tcg_gen_nor_i32(TCGV_LOW(ret), TCGV_LOW(arg1), TCGV_LOW(arg2));
+        tcg_gen_nor_i32(TCGV_HIGH(ret), TCGV_HIGH(arg1), TCGV_HIGH(arg2));
+    } else if (TCG_TARGET_HAS_nor_i64) {
+        tcg_gen_op3_i64(INDEX_op_nor_i64, ret, arg1, arg2);
+    } else {
+        tcg_gen_or_i64(ret, arg1, arg2);
+        tcg_gen_not_i64(ret, ret);
+    }
+}
+
+void tcg_gen_orc_i64(TCGv_i64 ret, TCGv_i64 arg1, TCGv_i64 arg2)
+{
+    if (TCG_TARGET_REG_BITS == 32) {
+        tcg_gen_orc_i32(TCGV_LOW(ret), TCGV_LOW(arg1), TCGV_LOW(arg2));
+        tcg_gen_orc_i32(TCGV_HIGH(ret), TCGV_HIGH(arg1), TCGV_HIGH(arg2));
+    } else if (TCG_TARGET_HAS_orc_i64) {
+        tcg_gen_op3_i64(INDEX_op_orc_i64, ret, arg1, arg2);
+    } else {
+        TCGv_i64 t0 = tcg_temp_new_i64();
+        tcg_gen_not_i64(t0, arg2);
+        tcg_gen_or_i64(ret, arg1, t0);
+        tcg_temp_free_i64(t0);
+    }
+}
+
+void tcg_gen_rotl_i64(TCGv_i64 ret, TCGv_i64 arg1, TCGv_i64 arg2)
+{
+    if (TCG_TARGET_HAS_rot_i64) {
+        tcg_gen_op3_i64(INDEX_op_rotl_i64, ret, arg1, arg2);
+    } else {
+        TCGv_i64 t0, t1;
+        t0 = tcg_temp_new_i64();
+        t1 = tcg_temp_new_i64();
+        tcg_gen_shl_i64(t0, arg1, arg2);
+        tcg_gen_subfi_i64(t1, 64, arg2);
+        tcg_gen_shr_i64(t1, arg1, t1);
+        tcg_gen_or_i64(ret, t0, t1);
+        tcg_temp_free_i64(t0);
+        tcg_temp_free_i64(t1);
+    }
+}
+
+void tcg_gen_rotli_i64(TCGv_i64 ret, TCGv_i64 arg1, unsigned arg2)
+{
+    tcg_debug_assert(arg2 < 64);
+    /* some cases can be optimized here */
+    if (arg2 == 0) {
+        tcg_gen_mov_i64(ret, arg1);
+    } else if (TCG_TARGET_HAS_rot_i64) {
+        TCGv_i64 t0 = tcg_const_i64(arg2);
+        tcg_gen_rotl_i64(ret, arg1, t0);
+        tcg_temp_free_i64(t0);
+    } else {
+        TCGv_i64 t0, t1;
+        t0 = tcg_temp_new_i64();
+        t1 = tcg_temp_new_i64();
+        tcg_gen_shli_i64(t0, arg1, arg2);
+        tcg_gen_shri_i64(t1, arg1, 64 - arg2);
+        tcg_gen_or_i64(ret, t0, t1);
+        tcg_temp_free_i64(t0);
+        tcg_temp_free_i64(t1);
+    }
+}
+
+void tcg_gen_rotr_i64(TCGv_i64 ret, TCGv_i64 arg1, TCGv_i64 arg2)
+{
+    if (TCG_TARGET_HAS_rot_i64) {
+        tcg_gen_op3_i64(INDEX_op_rotr_i64, ret, arg1, arg2);
+    } else {
+        TCGv_i64 t0, t1;
+        t0 = tcg_temp_new_i64();
+        t1 = tcg_temp_new_i64();
+        tcg_gen_shr_i64(t0, arg1, arg2);
+        tcg_gen_subfi_i64(t1, 64, arg2);
+        tcg_gen_shl_i64(t1, arg1, t1);
+        tcg_gen_or_i64(ret, t0, t1);
+        tcg_temp_free_i64(t0);
+        tcg_temp_free_i64(t1);
+    }
+}
+
+void tcg_gen_rotri_i64(TCGv_i64 ret, TCGv_i64 arg1, unsigned arg2)
+{
+    tcg_debug_assert(arg2 < 64);
+    /* some cases can be optimized here */
+    if (arg2 == 0) {
+        tcg_gen_mov_i64(ret, arg1);
+    } else {
+        tcg_gen_rotli_i64(ret, arg1, 64 - arg2);
+    }
+}
+
+void tcg_gen_deposit_i64(TCGv_i64 ret, TCGv_i64 arg1, TCGv_i64 arg2,
+                         unsigned int ofs, unsigned int len)
+{
+    uint64_t mask;
+    TCGv_i64 t1;
+
+    tcg_debug_assert(ofs < 64);
+    tcg_debug_assert(len <= 64);
+    tcg_debug_assert(ofs + len <= 64);
+
+    if (ofs == 0 && len == 64) {
+        tcg_gen_mov_i64(ret, arg2);
+        return;
+    }
+    if (TCG_TARGET_HAS_deposit_i64 && TCG_TARGET_deposit_i64_valid(ofs, len)) {
+        tcg_gen_op5ii_i64(INDEX_op_deposit_i64, ret, arg1, arg2, ofs, len);
+        return;
+    }
+
+    if (TCG_TARGET_REG_BITS == 32) {
+        if (ofs >= 32) {
+            tcg_gen_deposit_i32(TCGV_HIGH(ret), TCGV_HIGH(arg1),
+                                TCGV_LOW(arg2), ofs - 32, len);
+            tcg_gen_mov_i32(TCGV_LOW(ret), TCGV_LOW(arg1));
+            return;
+        }
+        if (ofs + len <= 32) {
+            tcg_gen_deposit_i32(TCGV_LOW(ret), TCGV_LOW(arg1),
+                                TCGV_LOW(arg2), ofs, len);
+            tcg_gen_mov_i32(TCGV_HIGH(ret), TCGV_HIGH(arg1));
+            return;
+        }
+    }
+
+    mask = (1ull << len) - 1;
+    t1 = tcg_temp_new_i64();
+
+    if (ofs + len < 64) {
+        tcg_gen_andi_i64(t1, arg2, mask);
+        tcg_gen_shli_i64(t1, t1, ofs);
+    } else {
+        tcg_gen_shli_i64(t1, arg2, ofs);
+    }
+    tcg_gen_andi_i64(ret, arg1, ~(mask << ofs));
+    tcg_gen_or_i64(ret, ret, t1);
+
+    tcg_temp_free_i64(t1);
+}
+
+void tcg_gen_movcond_i64(TCGCond cond, TCGv_i64 ret, TCGv_i64 c1,
+                         TCGv_i64 c2, TCGv_i64 v1, TCGv_i64 v2)
+{
+    if (cond == TCG_COND_ALWAYS) {
+        tcg_gen_mov_i64(ret, v1);
+    } else if (cond == TCG_COND_NEVER) {
+        tcg_gen_mov_i64(ret, v2);
+    } else if (TCG_TARGET_REG_BITS == 32) {
+        TCGv_i32 t0 = tcg_temp_new_i32();
+        TCGv_i32 t1 = tcg_temp_new_i32();
+        tcg_gen_op6i_i32(INDEX_op_setcond2_i32, t0,
+                         TCGV_LOW(c1), TCGV_HIGH(c1),
+                         TCGV_LOW(c2), TCGV_HIGH(c2), cond);
+
+        if (TCG_TARGET_HAS_movcond_i32) {
+            tcg_gen_movi_i32(t1, 0);
+            tcg_gen_movcond_i32(TCG_COND_NE, TCGV_LOW(ret), t0, t1,
+                                TCGV_LOW(v1), TCGV_LOW(v2));
+            tcg_gen_movcond_i32(TCG_COND_NE, TCGV_HIGH(ret), t0, t1,
+                                TCGV_HIGH(v1), TCGV_HIGH(v2));
+        } else {
+            tcg_gen_neg_i32(t0, t0);
+
+            tcg_gen_and_i32(t1, TCGV_LOW(v1), t0);
+            tcg_gen_andc_i32(TCGV_LOW(ret), TCGV_LOW(v2), t0);
+            tcg_gen_or_i32(TCGV_LOW(ret), TCGV_LOW(ret), t1);
+
+            tcg_gen_and_i32(t1, TCGV_HIGH(v1), t0);
+            tcg_gen_andc_i32(TCGV_HIGH(ret), TCGV_HIGH(v2), t0);
+            tcg_gen_or_i32(TCGV_HIGH(ret), TCGV_HIGH(ret), t1);
+        }
+        tcg_temp_free_i32(t0);
+        tcg_temp_free_i32(t1);
+    } else if (TCG_TARGET_HAS_movcond_i64) {
+        tcg_gen_op6i_i64(INDEX_op_movcond_i64, ret, c1, c2, v1, v2, cond);
+    } else {
+        TCGv_i64 t0 = tcg_temp_new_i64();
+        TCGv_i64 t1 = tcg_temp_new_i64();
+        tcg_gen_setcond_i64(cond, t0, c1, c2);
+        tcg_gen_neg_i64(t0, t0);
+        tcg_gen_and_i64(t1, v1, t0);
+        tcg_gen_andc_i64(ret, v2, t0);
+        tcg_gen_or_i64(ret, ret, t1);
+        tcg_temp_free_i64(t0);
+        tcg_temp_free_i64(t1);
+    }
+}
+
+void tcg_gen_add2_i64(TCGv_i64 rl, TCGv_i64 rh, TCGv_i64 al,
+                      TCGv_i64 ah, TCGv_i64 bl, TCGv_i64 bh)
+{
+    if (TCG_TARGET_HAS_add2_i64) {
+        tcg_gen_op6_i64(INDEX_op_add2_i64, rl, rh, al, ah, bl, bh);
+    } else {
+        TCGv_i64 t0 = tcg_temp_new_i64();
+        TCGv_i64 t1 = tcg_temp_new_i64();
+        tcg_gen_add_i64(t0, al, bl);
+        tcg_gen_setcond_i64(TCG_COND_LTU, t1, t0, al);
+        tcg_gen_add_i64(rh, ah, bh);
+        tcg_gen_add_i64(rh, rh, t1);
+        tcg_gen_mov_i64(rl, t0);
+        tcg_temp_free_i64(t0);
+        tcg_temp_free_i64(t1);
+    }
+}
+
+void tcg_gen_sub2_i64(TCGv_i64 rl, TCGv_i64 rh, TCGv_i64 al,
+                      TCGv_i64 ah, TCGv_i64 bl, TCGv_i64 bh)
+{
+    if (TCG_TARGET_HAS_sub2_i64) {
+        tcg_gen_op6_i64(INDEX_op_sub2_i64, rl, rh, al, ah, bl, bh);
+    } else {
+        TCGv_i64 t0 = tcg_temp_new_i64();
+        TCGv_i64 t1 = tcg_temp_new_i64();
+        tcg_gen_sub_i64(t0, al, bl);
+        tcg_gen_setcond_i64(TCG_COND_LTU, t1, al, bl);
+        tcg_gen_sub_i64(rh, ah, bh);
+        tcg_gen_sub_i64(rh, rh, t1);
+        tcg_gen_mov_i64(rl, t0);
+        tcg_temp_free_i64(t0);
+        tcg_temp_free_i64(t1);
+    }
+}
+
+void tcg_gen_mulu2_i64(TCGv_i64 rl, TCGv_i64 rh, TCGv_i64 arg1, TCGv_i64 arg2)
+{
+    if (TCG_TARGET_HAS_mulu2_i64) {
+        tcg_gen_op4_i64(INDEX_op_mulu2_i64, rl, rh, arg1, arg2);
+    } else if (TCG_TARGET_HAS_muluh_i64) {
+        TCGv_i64 t = tcg_temp_new_i64();
+        tcg_gen_op3_i64(INDEX_op_mul_i64, t, arg1, arg2);
+        tcg_gen_op3_i64(INDEX_op_muluh_i64, rh, arg1, arg2);
+        tcg_gen_mov_i64(rl, t);
+        tcg_temp_free_i64(t);
+    } else {
+        TCGv_i64 t0 = tcg_temp_new_i64();
+        tcg_gen_mul_i64(t0, arg1, arg2);
+        gen_helper_muluh_i64(rh, arg1, arg2);
+        tcg_gen_mov_i64(rl, t0);
+        tcg_temp_free_i64(t0);
+    }
+}
+
+void tcg_gen_muls2_i64(TCGv_i64 rl, TCGv_i64 rh, TCGv_i64 arg1, TCGv_i64 arg2)
+{
+    if (TCG_TARGET_HAS_muls2_i64) {
+        tcg_gen_op4_i64(INDEX_op_muls2_i64, rl, rh, arg1, arg2);
+    } else if (TCG_TARGET_HAS_mulsh_i64) {
+        TCGv_i64 t = tcg_temp_new_i64();
+        tcg_gen_op3_i64(INDEX_op_mul_i64, t, arg1, arg2);
+        tcg_gen_op3_i64(INDEX_op_mulsh_i64, rh, arg1, arg2);
+        tcg_gen_mov_i64(rl, t);
+        tcg_temp_free_i64(t);
+    } else if (TCG_TARGET_HAS_mulu2_i64 || TCG_TARGET_HAS_muluh_i64) {
+        TCGv_i64 t0 = tcg_temp_new_i64();
+        TCGv_i64 t1 = tcg_temp_new_i64();
+        TCGv_i64 t2 = tcg_temp_new_i64();
+        TCGv_i64 t3 = tcg_temp_new_i64();
+        tcg_gen_mulu2_i64(t0, t1, arg1, arg2);
+        /* Adjust for negative inputs.  */
+        tcg_gen_sari_i64(t2, arg1, 63);
+        tcg_gen_sari_i64(t3, arg2, 63);
+        tcg_gen_and_i64(t2, t2, arg2);
+        tcg_gen_and_i64(t3, t3, arg1);
+        tcg_gen_sub_i64(rh, t1, t2);
+        tcg_gen_sub_i64(rh, rh, t3);
+        tcg_gen_mov_i64(rl, t0);
+        tcg_temp_free_i64(t0);
+        tcg_temp_free_i64(t1);
+        tcg_temp_free_i64(t2);
+        tcg_temp_free_i64(t3);
+    } else {
+        TCGv_i64 t0 = tcg_temp_new_i64();
+        tcg_gen_mul_i64(t0, arg1, arg2);
+        gen_helper_mulsh_i64(rh, arg1, arg2);
+        tcg_gen_mov_i64(rl, t0);
+        tcg_temp_free_i64(t0);
+    }
+}
+
+/* Size changing operations.  */
+
+void tcg_gen_trunc_shr_i64_i32(TCGv_i32 ret, TCGv_i64 arg, unsigned count)
+{
+    tcg_debug_assert(count < 64);
+    if (TCG_TARGET_REG_BITS == 32) {
+        if (count >= 32) {
+            tcg_gen_shri_i32(ret, TCGV_HIGH(arg), count - 32);
+        } else if (count == 0) {
+            tcg_gen_mov_i32(ret, TCGV_LOW(arg));
+        } else {
+            TCGv_i64 t = tcg_temp_new_i64();
+            tcg_gen_shri_i64(t, arg, count);
+            tcg_gen_mov_i32(ret, TCGV_LOW(t));
+            tcg_temp_free_i64(t);
+        }
+    } else if (TCG_TARGET_HAS_trunc_shr_i32) {
+        tcg_gen_op3i_i32(INDEX_op_trunc_shr_i32, ret,
+                         MAKE_TCGV_I32(GET_TCGV_I64(arg)), count);
+    } else if (count == 0) {
+        tcg_gen_mov_i32(ret, MAKE_TCGV_I32(GET_TCGV_I64(arg)));
+    } else {
+        TCGv_i64 t = tcg_temp_new_i64();
+        tcg_gen_shri_i64(t, arg, count);
+        tcg_gen_mov_i32(ret, MAKE_TCGV_I32(GET_TCGV_I64(t)));
+        tcg_temp_free_i64(t);
+    }
+}
+
+void tcg_gen_extu_i32_i64(TCGv_i64 ret, TCGv_i32 arg)
+{
+    if (TCG_TARGET_REG_BITS == 32) {
+        tcg_gen_mov_i32(TCGV_LOW(ret), arg);
+        tcg_gen_movi_i32(TCGV_HIGH(ret), 0);
+    } else {
+        /* Note: we assume the target supports move between
+           32 and 64 bit registers.  */
+        tcg_gen_ext32u_i64(ret, MAKE_TCGV_I64(GET_TCGV_I32(arg)));
+    }
+}
+
+void tcg_gen_ext_i32_i64(TCGv_i64 ret, TCGv_i32 arg)
+{
+    if (TCG_TARGET_REG_BITS == 32) {
+        tcg_gen_mov_i32(TCGV_LOW(ret), arg);
+        tcg_gen_sari_i32(TCGV_HIGH(ret), TCGV_LOW(ret), 31);
+    } else {
+        /* Note: we assume the target supports move between
+           32 and 64 bit registers.  */
+        tcg_gen_ext32s_i64(ret, MAKE_TCGV_I64(GET_TCGV_I32(arg)));
+    }
+}
+
+void tcg_gen_concat_i32_i64(TCGv_i64 dest, TCGv_i32 low, TCGv_i32 high)
+{
+    TCGv_i64 tmp;
+
+    if (TCG_TARGET_REG_BITS == 32) {
+        tcg_gen_mov_i32(TCGV_LOW(dest), low);
+        tcg_gen_mov_i32(TCGV_HIGH(dest), high);
+        return;
+    }
+
+    tmp = tcg_temp_new_i64();
+    /* These extensions are only needed for type correctness.
+       We may be able to do better given target specific information.  */
+    tcg_gen_extu_i32_i64(tmp, high);
+    tcg_gen_extu_i32_i64(dest, low);
+    /* If deposit is available, use it.  Otherwise use the extra
+       knowledge that we have of the zero-extensions above.  */
+    if (TCG_TARGET_HAS_deposit_i64 && TCG_TARGET_deposit_i64_valid(32, 32)) {
+        tcg_gen_deposit_i64(dest, dest, tmp, 32, 32);
+    } else {
+        tcg_gen_shli_i64(tmp, tmp, 32);
+        tcg_gen_or_i64(dest, dest, tmp);
+    }
+    tcg_temp_free_i64(tmp);
+}
+
+void tcg_gen_extr_i64_i32(TCGv_i32 lo, TCGv_i32 hi, TCGv_i64 arg)
+{
+    if (TCG_TARGET_REG_BITS == 32) {
+        tcg_gen_mov_i32(lo, TCGV_LOW(arg));
+        tcg_gen_mov_i32(hi, TCGV_HIGH(arg));
+    } else {
+        tcg_gen_trunc_shr_i64_i32(lo, arg, 0);
+        tcg_gen_trunc_shr_i64_i32(hi, arg, 32);
+    }
+}
+
+void tcg_gen_extr32_i64(TCGv_i64 lo, TCGv_i64 hi, TCGv_i64 arg)
+{
+    tcg_gen_ext32u_i64(lo, arg);
+    tcg_gen_shri_i64(hi, arg, 32);
+}
+
+/* QEMU specific operations.  */
+
+void tcg_gen_goto_tb(unsigned idx)
+{
+    /* We only support two chained exits.  */
+    tcg_debug_assert(idx <= 1);
+#ifdef CONFIG_DEBUG_TCG
+    /* Verify that we havn't seen this numbered exit before.  */
+    tcg_debug_assert((tcg_ctx.goto_tb_issue_mask & (1 << idx)) == 0);
+    tcg_ctx.goto_tb_issue_mask |= 1 << idx;
+#endif
+    tcg_gen_op1i(INDEX_op_goto_tb, idx);
+}
+
+static inline TCGMemOp tcg_canonicalize_memop(TCGMemOp op, bool is64, bool st)
+{
+    switch (op & MO_SIZE) {
+    case MO_8:
+        op &= ~MO_BSWAP;
+        break;
+    case MO_16:
+        break;
+    case MO_32:
+        if (!is64) {
+            op &= ~MO_SIGN;
+        }
+        break;
+    case MO_64:
+        if (!is64) {
+            tcg_abort();
+        }
+        break;
+    }
+    if (st) {
+        op &= ~MO_SIGN;
+    }
+    return op;
+}
+
+static void gen_ldst_i32(TCGOpcode opc, TCGv_i32 val, TCGv addr,
+                         TCGMemOp memop, TCGArg idx)
+{
+    TCGMemOpIdx oi = make_memop_idx(memop, idx);
+#if TARGET_LONG_BITS == 32
+    tcg_gen_op3i_i32(opc, val, addr, oi);
+#else
+    if (TCG_TARGET_REG_BITS == 32) {
+        tcg_gen_op4i_i32(opc, val, TCGV_LOW(addr), TCGV_HIGH(addr), oi);
+    } else {
+        tcg_gen_op3(&tcg_ctx, opc, GET_TCGV_I32(val), GET_TCGV_I64(addr), oi);
+    }
+#endif
+}
+
+static void gen_ldst_i64(TCGOpcode opc, TCGv_i64 val, TCGv addr,
+                         TCGMemOp memop, TCGArg idx)
+{
+    TCGMemOpIdx oi = make_memop_idx(memop, idx);
+#if TARGET_LONG_BITS == 32
+    if (TCG_TARGET_REG_BITS == 32) {
+        tcg_gen_op4i_i32(opc, TCGV_LOW(val), TCGV_HIGH(val), addr, oi);
+    } else {
+        tcg_gen_op3(&tcg_ctx, opc, GET_TCGV_I64(val), GET_TCGV_I32(addr), oi);
+    }
+#else
+    if (TCG_TARGET_REG_BITS == 32) {
+        tcg_gen_op5i_i32(opc, TCGV_LOW(val), TCGV_HIGH(val),
+                         TCGV_LOW(addr), TCGV_HIGH(addr), oi);
+    } else {
+        tcg_gen_op3i_i64(opc, val, addr, oi);
+    }
+#endif
+}
+
+void tcg_gen_qemu_ld_i32(TCGv_i32 val, TCGv addr, TCGArg idx, TCGMemOp memop)
+{
+    memop = tcg_canonicalize_memop(memop, 0, 0);
+    gen_ldst_i32(INDEX_op_qemu_ld_i32, val, addr, memop, idx);
+}
+
+void tcg_gen_qemu_st_i32(TCGv_i32 val, TCGv addr, TCGArg idx, TCGMemOp memop)
+{
+    memop = tcg_canonicalize_memop(memop, 0, 1);
+    gen_ldst_i32(INDEX_op_qemu_st_i32, val, addr, memop, idx);
+}
+
+void tcg_gen_qemu_ld_i64(TCGv_i64 val, TCGv addr, TCGArg idx, TCGMemOp memop)
+{
+    if (TCG_TARGET_REG_BITS == 32 && (memop & MO_SIZE) < MO_64) {
+        tcg_gen_qemu_ld_i32(TCGV_LOW(val), addr, idx, memop);
+        if (memop & MO_SIGN) {
+            tcg_gen_sari_i32(TCGV_HIGH(val), TCGV_LOW(val), 31);
+        } else {
+            tcg_gen_movi_i32(TCGV_HIGH(val), 0);
+        }
+        return;
+    }
+
+    memop = tcg_canonicalize_memop(memop, 1, 0);
+    gen_ldst_i64(INDEX_op_qemu_ld_i64, val, addr, memop, idx);
+}
+
+void tcg_gen_qemu_st_i64(TCGv_i64 val, TCGv addr, TCGArg idx, TCGMemOp memop)
+{
+    if (TCG_TARGET_REG_BITS == 32 && (memop & MO_SIZE) < MO_64) {
+        tcg_gen_qemu_st_i32(TCGV_LOW(val), addr, idx, memop);
+        return;
+    }
+
+    memop = tcg_canonicalize_memop(memop, 1, 1);
+    gen_ldst_i64(INDEX_op_qemu_st_i64, val, addr, memop, idx);
+}
diff --git a/tcg/tcg-op.h b/tcg/tcg-op.h
new file mode 100644
index 00000000..d1d763f6
--- /dev/null
+++ b/tcg/tcg-op.h
@@ -0,0 +1,991 @@
+/*
+ * Tiny Code Generator for QEMU
+ *
+ * Copyright (c) 2008 Fabrice Bellard
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (the "Software"), to deal
+ * in the Software without restriction, including without limitation the rights
+ * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+ * copies of the Software, and to permit persons to whom the Software is
+ * furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+ * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+ * THE SOFTWARE.
+ */
+
+#include "tcg.h"
+#include "exec/helper-proto.h"
+#include "exec/helper-gen.h"
+
+/* Basic output routines.  Not for general consumption.  */
+
+void tcg_gen_op1(TCGContext *, TCGOpcode, TCGArg);
+void tcg_gen_op2(TCGContext *, TCGOpcode, TCGArg, TCGArg);
+void tcg_gen_op3(TCGContext *, TCGOpcode, TCGArg, TCGArg, TCGArg);
+void tcg_gen_op4(TCGContext *, TCGOpcode, TCGArg, TCGArg, TCGArg, TCGArg);
+void tcg_gen_op5(TCGContext *, TCGOpcode, TCGArg, TCGArg, TCGArg,
+                 TCGArg, TCGArg);
+void tcg_gen_op6(TCGContext *, TCGOpcode, TCGArg, TCGArg, TCGArg,
+                 TCGArg, TCGArg, TCGArg);
+
+
+static inline void tcg_gen_op1_i32(TCGOpcode opc, TCGv_i32 a1)
+{
+    tcg_gen_op1(&tcg_ctx, opc, GET_TCGV_I32(a1));
+}
+
+static inline void tcg_gen_op1_i64(TCGOpcode opc, TCGv_i64 a1)
+{
+    tcg_gen_op1(&tcg_ctx, opc, GET_TCGV_I64(a1));
+}
+
+static inline void tcg_gen_op1i(TCGOpcode opc, TCGArg a1)
+{
+    tcg_gen_op1(&tcg_ctx, opc, a1);
+}
+
+static inline void tcg_gen_op2_i32(TCGOpcode opc, TCGv_i32 a1, TCGv_i32 a2)
+{
+    tcg_gen_op2(&tcg_ctx, opc, GET_TCGV_I32(a1), GET_TCGV_I32(a2));
+}
+
+static inline void tcg_gen_op2_i64(TCGOpcode opc, TCGv_i64 a1, TCGv_i64 a2)
+{
+    tcg_gen_op2(&tcg_ctx, opc, GET_TCGV_I64(a1), GET_TCGV_I64(a2));
+}
+
+static inline void tcg_gen_op2i_i32(TCGOpcode opc, TCGv_i32 a1, TCGArg a2)
+{
+    tcg_gen_op2(&tcg_ctx, opc, GET_TCGV_I32(a1), a2);
+}
+
+static inline void tcg_gen_op2i_i64(TCGOpcode opc, TCGv_i64 a1, TCGArg a2)
+{
+    tcg_gen_op2(&tcg_ctx, opc, GET_TCGV_I64(a1), a2);
+}
+
+static inline void tcg_gen_op2ii(TCGOpcode opc, TCGArg a1, TCGArg a2)
+{
+    tcg_gen_op2(&tcg_ctx, opc, a1, a2);
+}
+
+static inline void tcg_gen_op3_i32(TCGOpcode opc, TCGv_i32 a1,
+                                   TCGv_i32 a2, TCGv_i32 a3)
+{
+    tcg_gen_op3(&tcg_ctx, opc, GET_TCGV_I32(a1),
+                GET_TCGV_I32(a2), GET_TCGV_I32(a3));
+}
+
+static inline void tcg_gen_op3_i64(TCGOpcode opc, TCGv_i64 a1,
+                                   TCGv_i64 a2, TCGv_i64 a3)
+{
+    tcg_gen_op3(&tcg_ctx, opc, GET_TCGV_I64(a1),
+                GET_TCGV_I64(a2), GET_TCGV_I64(a3));
+}
+
+static inline void tcg_gen_op3i_i32(TCGOpcode opc, TCGv_i32 a1,
+                                    TCGv_i32 a2, TCGArg a3)
+{
+    tcg_gen_op3(&tcg_ctx, opc, GET_TCGV_I32(a1), GET_TCGV_I32(a2), a3);
+}
+
+static inline void tcg_gen_op3i_i64(TCGOpcode opc, TCGv_i64 a1,
+                                    TCGv_i64 a2, TCGArg a3)
+{
+    tcg_gen_op3(&tcg_ctx, opc, GET_TCGV_I64(a1), GET_TCGV_I64(a2), a3);
+}
+
+static inline void tcg_gen_ldst_op_i32(TCGOpcode opc, TCGv_i32 val,
+                                       TCGv_ptr base, TCGArg offset)
+{
+    tcg_gen_op3(&tcg_ctx, opc, GET_TCGV_I32(val), GET_TCGV_PTR(base), offset);
+}
+
+static inline void tcg_gen_ldst_op_i64(TCGOpcode opc, TCGv_i64 val,
+                                       TCGv_ptr base, TCGArg offset)
+{
+    tcg_gen_op3(&tcg_ctx, opc, GET_TCGV_I64(val), GET_TCGV_PTR(base), offset);
+}
+
+static inline void tcg_gen_op4_i32(TCGOpcode opc, TCGv_i32 a1, TCGv_i32 a2,
+                                   TCGv_i32 a3, TCGv_i32 a4)
+{
+    tcg_gen_op4(&tcg_ctx, opc, GET_TCGV_I32(a1), GET_TCGV_I32(a2),
+                GET_TCGV_I32(a3), GET_TCGV_I32(a4));
+}
+
+static inline void tcg_gen_op4_i64(TCGOpcode opc, TCGv_i64 a1, TCGv_i64 a2,
+                                   TCGv_i64 a3, TCGv_i64 a4)
+{
+    tcg_gen_op4(&tcg_ctx, opc, GET_TCGV_I64(a1), GET_TCGV_I64(a2),
+                GET_TCGV_I64(a3), GET_TCGV_I64(a4));
+}
+
+static inline void tcg_gen_op4i_i32(TCGOpcode opc, TCGv_i32 a1, TCGv_i32 a2,
+                                    TCGv_i32 a3, TCGArg a4)
+{
+    tcg_gen_op4(&tcg_ctx, opc, GET_TCGV_I32(a1), GET_TCGV_I32(a2),
+                GET_TCGV_I32(a3), a4);
+}
+
+static inline void tcg_gen_op4i_i64(TCGOpcode opc, TCGv_i64 a1, TCGv_i64 a2,
+                                    TCGv_i64 a3, TCGArg a4)
+{
+    tcg_gen_op4(&tcg_ctx, opc, GET_TCGV_I64(a1), GET_TCGV_I64(a2),
+                GET_TCGV_I64(a3), a4);
+}
+
+static inline void tcg_gen_op4ii_i32(TCGOpcode opc, TCGv_i32 a1, TCGv_i32 a2,
+                                     TCGArg a3, TCGArg a4)
+{
+    tcg_gen_op4(&tcg_ctx, opc, GET_TCGV_I32(a1), GET_TCGV_I32(a2), a3, a4);
+}
+
+static inline void tcg_gen_op4ii_i64(TCGOpcode opc, TCGv_i64 a1, TCGv_i64 a2,
+                                     TCGArg a3, TCGArg a4)
+{
+    tcg_gen_op4(&tcg_ctx, opc, GET_TCGV_I64(a1), GET_TCGV_I64(a2), a3, a4);
+}
+
+static inline void tcg_gen_op5_i32(TCGOpcode opc, TCGv_i32 a1, TCGv_i32 a2,
+                                   TCGv_i32 a3, TCGv_i32 a4, TCGv_i32 a5)
+{
+    tcg_gen_op5(&tcg_ctx, opc, GET_TCGV_I32(a1), GET_TCGV_I32(a2),
+                GET_TCGV_I32(a3), GET_TCGV_I32(a4), GET_TCGV_I32(a5));
+}
+
+static inline void tcg_gen_op5_i64(TCGOpcode opc, TCGv_i64 a1, TCGv_i64 a2,
+                                   TCGv_i64 a3, TCGv_i64 a4, TCGv_i64 a5)
+{
+    tcg_gen_op5(&tcg_ctx, opc, GET_TCGV_I64(a1), GET_TCGV_I64(a2),
+                GET_TCGV_I64(a3), GET_TCGV_I64(a4), GET_TCGV_I64(a5));
+}
+
+static inline void tcg_gen_op5i_i32(TCGOpcode opc, TCGv_i32 a1, TCGv_i32 a2,
+                                    TCGv_i32 a3, TCGv_i32 a4, TCGArg a5)
+{
+    tcg_gen_op5(&tcg_ctx, opc, GET_TCGV_I32(a1), GET_TCGV_I32(a2),
+                GET_TCGV_I32(a3), GET_TCGV_I32(a4), a5);
+}
+
+static inline void tcg_gen_op5i_i64(TCGOpcode opc, TCGv_i64 a1, TCGv_i64 a2,
+                                    TCGv_i64 a3, TCGv_i64 a4, TCGArg a5)
+{
+    tcg_gen_op5(&tcg_ctx, opc, GET_TCGV_I64(a1), GET_TCGV_I64(a2),
+                GET_TCGV_I64(a3), GET_TCGV_I64(a4), a5);
+}
+
+static inline void tcg_gen_op5ii_i32(TCGOpcode opc, TCGv_i32 a1, TCGv_i32 a2,
+                                     TCGv_i32 a3, TCGArg a4, TCGArg a5)
+{
+    tcg_gen_op5(&tcg_ctx, opc, GET_TCGV_I32(a1), GET_TCGV_I32(a2),
+                GET_TCGV_I32(a3), a4, a5);
+}
+
+static inline void tcg_gen_op5ii_i64(TCGOpcode opc, TCGv_i64 a1, TCGv_i64 a2,
+                                     TCGv_i64 a3, TCGArg a4, TCGArg a5)
+{
+    tcg_gen_op5(&tcg_ctx, opc, GET_TCGV_I64(a1), GET_TCGV_I64(a2),
+                GET_TCGV_I64(a3), a4, a5);
+}
+
+static inline void tcg_gen_op6_i32(TCGOpcode opc, TCGv_i32 a1, TCGv_i32 a2,
+                                   TCGv_i32 a3, TCGv_i32 a4,
+                                   TCGv_i32 a5, TCGv_i32 a6)
+{
+    tcg_gen_op6(&tcg_ctx, opc, GET_TCGV_I32(a1), GET_TCGV_I32(a2),
+                GET_TCGV_I32(a3), GET_TCGV_I32(a4), GET_TCGV_I32(a5),
+                GET_TCGV_I32(a6));
+}
+
+static inline void tcg_gen_op6_i64(TCGOpcode opc, TCGv_i64 a1, TCGv_i64 a2,
+                                   TCGv_i64 a3, TCGv_i64 a4,
+                                   TCGv_i64 a5, TCGv_i64 a6)
+{
+    tcg_gen_op6(&tcg_ctx, opc, GET_TCGV_I64(a1), GET_TCGV_I64(a2),
+                GET_TCGV_I64(a3), GET_TCGV_I64(a4), GET_TCGV_I64(a5),
+                GET_TCGV_I64(a6));
+}
+
+static inline void tcg_gen_op6i_i32(TCGOpcode opc, TCGv_i32 a1, TCGv_i32 a2,
+                                    TCGv_i32 a3, TCGv_i32 a4,
+                                    TCGv_i32 a5, TCGArg a6)
+{
+    tcg_gen_op6(&tcg_ctx, opc, GET_TCGV_I32(a1), GET_TCGV_I32(a2),
+                GET_TCGV_I32(a3), GET_TCGV_I32(a4), GET_TCGV_I32(a5), a6);
+}
+
+static inline void tcg_gen_op6i_i64(TCGOpcode opc, TCGv_i64 a1, TCGv_i64 a2,
+                                    TCGv_i64 a3, TCGv_i64 a4,
+                                    TCGv_i64 a5, TCGArg a6)
+{
+    tcg_gen_op6(&tcg_ctx, opc, GET_TCGV_I64(a1), GET_TCGV_I64(a2),
+                GET_TCGV_I64(a3), GET_TCGV_I64(a4), GET_TCGV_I64(a5), a6);
+}
+
+static inline void tcg_gen_op6ii_i32(TCGOpcode opc, TCGv_i32 a1, TCGv_i32 a2,
+                                     TCGv_i32 a3, TCGv_i32 a4,
+                                     TCGArg a5, TCGArg a6)
+{
+    tcg_gen_op6(&tcg_ctx, opc, GET_TCGV_I32(a1), GET_TCGV_I32(a2),
+                GET_TCGV_I32(a3), GET_TCGV_I32(a4), a5, a6);
+}
+
+static inline void tcg_gen_op6ii_i64(TCGOpcode opc, TCGv_i64 a1, TCGv_i64 a2,
+                                     TCGv_i64 a3, TCGv_i64 a4,
+                                     TCGArg a5, TCGArg a6)
+{
+    tcg_gen_op6(&tcg_ctx, opc, GET_TCGV_I64(a1), GET_TCGV_I64(a2),
+                GET_TCGV_I64(a3), GET_TCGV_I64(a4), a5, a6);
+}
+
+
+/* Generic ops.  */
+
+static inline void gen_set_label(TCGLabel *l)
+{
+    tcg_gen_op1(&tcg_ctx, INDEX_op_set_label, label_arg(l));
+}
+
+static inline void tcg_gen_br(TCGLabel *l)
+{
+    tcg_gen_op1(&tcg_ctx, INDEX_op_br, label_arg(l));
+}
+
+/* Helper calls. */
+
+/* 32 bit ops */
+
+void tcg_gen_addi_i32(TCGv_i32 ret, TCGv_i32 arg1, int32_t arg2);
+void tcg_gen_subfi_i32(TCGv_i32 ret, int32_t arg1, TCGv_i32 arg2);
+void tcg_gen_subi_i32(TCGv_i32 ret, TCGv_i32 arg1, int32_t arg2);
+void tcg_gen_andi_i32(TCGv_i32 ret, TCGv_i32 arg1, uint32_t arg2);
+void tcg_gen_ori_i32(TCGv_i32 ret, TCGv_i32 arg1, int32_t arg2);
+void tcg_gen_xori_i32(TCGv_i32 ret, TCGv_i32 arg1, int32_t arg2);
+void tcg_gen_shli_i32(TCGv_i32 ret, TCGv_i32 arg1, unsigned arg2);
+void tcg_gen_shri_i32(TCGv_i32 ret, TCGv_i32 arg1, unsigned arg2);
+void tcg_gen_sari_i32(TCGv_i32 ret, TCGv_i32 arg1, unsigned arg2);
+void tcg_gen_muli_i32(TCGv_i32 ret, TCGv_i32 arg1, int32_t arg2);
+void tcg_gen_div_i32(TCGv_i32 ret, TCGv_i32 arg1, TCGv_i32 arg2);
+void tcg_gen_rem_i32(TCGv_i32 ret, TCGv_i32 arg1, TCGv_i32 arg2);
+void tcg_gen_divu_i32(TCGv_i32 ret, TCGv_i32 arg1, TCGv_i32 arg2);
+void tcg_gen_remu_i32(TCGv_i32 ret, TCGv_i32 arg1, TCGv_i32 arg2);
+void tcg_gen_andc_i32(TCGv_i32 ret, TCGv_i32 arg1, TCGv_i32 arg2);
+void tcg_gen_eqv_i32(TCGv_i32 ret, TCGv_i32 arg1, TCGv_i32 arg2);
+void tcg_gen_nand_i32(TCGv_i32 ret, TCGv_i32 arg1, TCGv_i32 arg2);
+void tcg_gen_nor_i32(TCGv_i32 ret, TCGv_i32 arg1, TCGv_i32 arg2);
+void tcg_gen_orc_i32(TCGv_i32 ret, TCGv_i32 arg1, TCGv_i32 arg2);
+void tcg_gen_rotl_i32(TCGv_i32 ret, TCGv_i32 arg1, TCGv_i32 arg2);
+void tcg_gen_rotli_i32(TCGv_i32 ret, TCGv_i32 arg1, unsigned arg2);
+void tcg_gen_rotr_i32(TCGv_i32 ret, TCGv_i32 arg1, TCGv_i32 arg2);
+void tcg_gen_rotri_i32(TCGv_i32 ret, TCGv_i32 arg1, unsigned arg2);
+void tcg_gen_deposit_i32(TCGv_i32 ret, TCGv_i32 arg1, TCGv_i32 arg2,
+                         unsigned int ofs, unsigned int len);
+void tcg_gen_brcond_i32(TCGCond cond, TCGv_i32 arg1, TCGv_i32 arg2, TCGLabel *);
+void tcg_gen_brcondi_i32(TCGCond cond, TCGv_i32 arg1, int32_t arg2, TCGLabel *);
+void tcg_gen_setcond_i32(TCGCond cond, TCGv_i32 ret,
+                         TCGv_i32 arg1, TCGv_i32 arg2);
+void tcg_gen_setcondi_i32(TCGCond cond, TCGv_i32 ret,
+                          TCGv_i32 arg1, int32_t arg2);
+void tcg_gen_movcond_i32(TCGCond cond, TCGv_i32 ret, TCGv_i32 c1,
+                         TCGv_i32 c2, TCGv_i32 v1, TCGv_i32 v2);
+void tcg_gen_add2_i32(TCGv_i32 rl, TCGv_i32 rh, TCGv_i32 al,
+                      TCGv_i32 ah, TCGv_i32 bl, TCGv_i32 bh);
+void tcg_gen_sub2_i32(TCGv_i32 rl, TCGv_i32 rh, TCGv_i32 al,
+                      TCGv_i32 ah, TCGv_i32 bl, TCGv_i32 bh);
+void tcg_gen_mulu2_i32(TCGv_i32 rl, TCGv_i32 rh, TCGv_i32 arg1, TCGv_i32 arg2);
+void tcg_gen_muls2_i32(TCGv_i32 rl, TCGv_i32 rh, TCGv_i32 arg1, TCGv_i32 arg2);
+void tcg_gen_ext8s_i32(TCGv_i32 ret, TCGv_i32 arg);
+void tcg_gen_ext16s_i32(TCGv_i32 ret, TCGv_i32 arg);
+void tcg_gen_ext8u_i32(TCGv_i32 ret, TCGv_i32 arg);
+void tcg_gen_ext16u_i32(TCGv_i32 ret, TCGv_i32 arg);
+void tcg_gen_bswap16_i32(TCGv_i32 ret, TCGv_i32 arg);
+void tcg_gen_bswap32_i32(TCGv_i32 ret, TCGv_i32 arg);
+
+static inline void tcg_gen_discard_i32(TCGv_i32 arg)
+{
+    tcg_gen_op1_i32(INDEX_op_discard, arg);
+}
+
+static inline void tcg_gen_mov_i32(TCGv_i32 ret, TCGv_i32 arg)
+{
+    if (!TCGV_EQUAL_I32(ret, arg)) {
+        tcg_gen_op2_i32(INDEX_op_mov_i32, ret, arg);
+    }
+}
+
+static inline void tcg_gen_movi_i32(TCGv_i32 ret, int32_t arg)
+{
+    tcg_gen_op2i_i32(INDEX_op_movi_i32, ret, arg);
+}
+
+static inline void tcg_gen_ld8u_i32(TCGv_i32 ret, TCGv_ptr arg2,
+                                    tcg_target_long offset)
+{
+    tcg_gen_ldst_op_i32(INDEX_op_ld8u_i32, ret, arg2, offset);
+}
+
+static inline void tcg_gen_ld8s_i32(TCGv_i32 ret, TCGv_ptr arg2,
+                                    tcg_target_long offset)
+{
+    tcg_gen_ldst_op_i32(INDEX_op_ld8s_i32, ret, arg2, offset);
+}
+
+static inline void tcg_gen_ld16u_i32(TCGv_i32 ret, TCGv_ptr arg2,
+                                     tcg_target_long offset)
+{
+    tcg_gen_ldst_op_i32(INDEX_op_ld16u_i32, ret, arg2, offset);
+}
+
+static inline void tcg_gen_ld16s_i32(TCGv_i32 ret, TCGv_ptr arg2,
+                                     tcg_target_long offset)
+{
+    tcg_gen_ldst_op_i32(INDEX_op_ld16s_i32, ret, arg2, offset);
+}
+
+static inline void tcg_gen_ld_i32(TCGv_i32 ret, TCGv_ptr arg2,
+                                  tcg_target_long offset)
+{
+    tcg_gen_ldst_op_i32(INDEX_op_ld_i32, ret, arg2, offset);
+}
+
+static inline void tcg_gen_st8_i32(TCGv_i32 arg1, TCGv_ptr arg2,
+                                   tcg_target_long offset)
+{
+    tcg_gen_ldst_op_i32(INDEX_op_st8_i32, arg1, arg2, offset);
+}
+
+static inline void tcg_gen_st16_i32(TCGv_i32 arg1, TCGv_ptr arg2,
+                                    tcg_target_long offset)
+{
+    tcg_gen_ldst_op_i32(INDEX_op_st16_i32, arg1, arg2, offset);
+}
+
+static inline void tcg_gen_st_i32(TCGv_i32 arg1, TCGv_ptr arg2,
+                                  tcg_target_long offset)
+{
+    tcg_gen_ldst_op_i32(INDEX_op_st_i32, arg1, arg2, offset);
+}
+
+static inline void tcg_gen_add_i32(TCGv_i32 ret, TCGv_i32 arg1, TCGv_i32 arg2)
+{
+    tcg_gen_op3_i32(INDEX_op_add_i32, ret, arg1, arg2);
+}
+
+static inline void tcg_gen_sub_i32(TCGv_i32 ret, TCGv_i32 arg1, TCGv_i32 arg2)
+{
+    tcg_gen_op3_i32(INDEX_op_sub_i32, ret, arg1, arg2);
+}
+
+static inline void tcg_gen_and_i32(TCGv_i32 ret, TCGv_i32 arg1, TCGv_i32 arg2)
+{
+    tcg_gen_op3_i32(INDEX_op_and_i32, ret, arg1, arg2);
+}
+
+static inline void tcg_gen_or_i32(TCGv_i32 ret, TCGv_i32 arg1, TCGv_i32 arg2)
+{
+    tcg_gen_op3_i32(INDEX_op_or_i32, ret, arg1, arg2);
+}
+
+static inline void tcg_gen_xor_i32(TCGv_i32 ret, TCGv_i32 arg1, TCGv_i32 arg2)
+{
+    tcg_gen_op3_i32(INDEX_op_xor_i32, ret, arg1, arg2);
+}
+
+static inline void tcg_gen_shl_i32(TCGv_i32 ret, TCGv_i32 arg1, TCGv_i32 arg2)
+{
+    tcg_gen_op3_i32(INDEX_op_shl_i32, ret, arg1, arg2);
+}
+
+static inline void tcg_gen_shr_i32(TCGv_i32 ret, TCGv_i32 arg1, TCGv_i32 arg2)
+{
+    tcg_gen_op3_i32(INDEX_op_shr_i32, ret, arg1, arg2);
+}
+
+static inline void tcg_gen_sar_i32(TCGv_i32 ret, TCGv_i32 arg1, TCGv_i32 arg2)
+{
+    tcg_gen_op3_i32(INDEX_op_sar_i32, ret, arg1, arg2);
+}
+
+static inline void tcg_gen_mul_i32(TCGv_i32 ret, TCGv_i32 arg1, TCGv_i32 arg2)
+{
+    tcg_gen_op3_i32(INDEX_op_mul_i32, ret, arg1, arg2);
+}
+
+static inline void tcg_gen_neg_i32(TCGv_i32 ret, TCGv_i32 arg)
+{
+    if (TCG_TARGET_HAS_neg_i32) {
+        tcg_gen_op2_i32(INDEX_op_neg_i32, ret, arg);
+    } else {
+        tcg_gen_subfi_i32(ret, 0, arg);
+    }
+}
+
+static inline void tcg_gen_not_i32(TCGv_i32 ret, TCGv_i32 arg)
+{
+    if (TCG_TARGET_HAS_not_i32) {
+        tcg_gen_op2_i32(INDEX_op_not_i32, ret, arg);
+    } else {
+        tcg_gen_xori_i32(ret, arg, -1);
+    }
+}
+
+/* 64 bit ops */
+
+void tcg_gen_addi_i64(TCGv_i64 ret, TCGv_i64 arg1, int64_t arg2);
+void tcg_gen_subfi_i64(TCGv_i64 ret, int64_t arg1, TCGv_i64 arg2);
+void tcg_gen_subi_i64(TCGv_i64 ret, TCGv_i64 arg1, int64_t arg2);
+void tcg_gen_andi_i64(TCGv_i64 ret, TCGv_i64 arg1, uint64_t arg2);
+void tcg_gen_ori_i64(TCGv_i64 ret, TCGv_i64 arg1, int64_t arg2);
+void tcg_gen_xori_i64(TCGv_i64 ret, TCGv_i64 arg1, int64_t arg2);
+void tcg_gen_shli_i64(TCGv_i64 ret, TCGv_i64 arg1, unsigned arg2);
+void tcg_gen_shri_i64(TCGv_i64 ret, TCGv_i64 arg1, unsigned arg2);
+void tcg_gen_sari_i64(TCGv_i64 ret, TCGv_i64 arg1, unsigned arg2);
+void tcg_gen_muli_i64(TCGv_i64 ret, TCGv_i64 arg1, int64_t arg2);
+void tcg_gen_div_i64(TCGv_i64 ret, TCGv_i64 arg1, TCGv_i64 arg2);
+void tcg_gen_rem_i64(TCGv_i64 ret, TCGv_i64 arg1, TCGv_i64 arg2);
+void tcg_gen_divu_i64(TCGv_i64 ret, TCGv_i64 arg1, TCGv_i64 arg2);
+void tcg_gen_remu_i64(TCGv_i64 ret, TCGv_i64 arg1, TCGv_i64 arg2);
+void tcg_gen_andc_i64(TCGv_i64 ret, TCGv_i64 arg1, TCGv_i64 arg2);
+void tcg_gen_eqv_i64(TCGv_i64 ret, TCGv_i64 arg1, TCGv_i64 arg2);
+void tcg_gen_nand_i64(TCGv_i64 ret, TCGv_i64 arg1, TCGv_i64 arg2);
+void tcg_gen_nor_i64(TCGv_i64 ret, TCGv_i64 arg1, TCGv_i64 arg2);
+void tcg_gen_orc_i64(TCGv_i64 ret, TCGv_i64 arg1, TCGv_i64 arg2);
+void tcg_gen_rotl_i64(TCGv_i64 ret, TCGv_i64 arg1, TCGv_i64 arg2);
+void tcg_gen_rotli_i64(TCGv_i64 ret, TCGv_i64 arg1, unsigned arg2);
+void tcg_gen_rotr_i64(TCGv_i64 ret, TCGv_i64 arg1, TCGv_i64 arg2);
+void tcg_gen_rotri_i64(TCGv_i64 ret, TCGv_i64 arg1, unsigned arg2);
+void tcg_gen_deposit_i64(TCGv_i64 ret, TCGv_i64 arg1, TCGv_i64 arg2,
+                         unsigned int ofs, unsigned int len);
+void tcg_gen_brcond_i64(TCGCond cond, TCGv_i64 arg1, TCGv_i64 arg2, TCGLabel *);
+void tcg_gen_brcondi_i64(TCGCond cond, TCGv_i64 arg1, int64_t arg2, TCGLabel *);
+void tcg_gen_setcond_i64(TCGCond cond, TCGv_i64 ret,
+                         TCGv_i64 arg1, TCGv_i64 arg2);
+void tcg_gen_setcondi_i64(TCGCond cond, TCGv_i64 ret,
+                          TCGv_i64 arg1, int64_t arg2);
+void tcg_gen_movcond_i64(TCGCond cond, TCGv_i64 ret, TCGv_i64 c1,
+                         TCGv_i64 c2, TCGv_i64 v1, TCGv_i64 v2);
+void tcg_gen_add2_i64(TCGv_i64 rl, TCGv_i64 rh, TCGv_i64 al,
+                      TCGv_i64 ah, TCGv_i64 bl, TCGv_i64 bh);
+void tcg_gen_sub2_i64(TCGv_i64 rl, TCGv_i64 rh, TCGv_i64 al,
+                      TCGv_i64 ah, TCGv_i64 bl, TCGv_i64 bh);
+void tcg_gen_mulu2_i64(TCGv_i64 rl, TCGv_i64 rh, TCGv_i64 arg1, TCGv_i64 arg2);
+void tcg_gen_muls2_i64(TCGv_i64 rl, TCGv_i64 rh, TCGv_i64 arg1, TCGv_i64 arg2);
+void tcg_gen_not_i64(TCGv_i64 ret, TCGv_i64 arg);
+void tcg_gen_ext8s_i64(TCGv_i64 ret, TCGv_i64 arg);
+void tcg_gen_ext16s_i64(TCGv_i64 ret, TCGv_i64 arg);
+void tcg_gen_ext32s_i64(TCGv_i64 ret, TCGv_i64 arg);
+void tcg_gen_ext8u_i64(TCGv_i64 ret, TCGv_i64 arg);
+void tcg_gen_ext16u_i64(TCGv_i64 ret, TCGv_i64 arg);
+void tcg_gen_ext32u_i64(TCGv_i64 ret, TCGv_i64 arg);
+void tcg_gen_bswap16_i64(TCGv_i64 ret, TCGv_i64 arg);
+void tcg_gen_bswap32_i64(TCGv_i64 ret, TCGv_i64 arg);
+void tcg_gen_bswap64_i64(TCGv_i64 ret, TCGv_i64 arg);
+
+#if TCG_TARGET_REG_BITS == 64
+static inline void tcg_gen_discard_i64(TCGv_i64 arg)
+{
+    tcg_gen_op1_i64(INDEX_op_discard, arg);
+}
+
+static inline void tcg_gen_mov_i64(TCGv_i64 ret, TCGv_i64 arg)
+{
+    if (!TCGV_EQUAL_I64(ret, arg)) {
+        tcg_gen_op2_i64(INDEX_op_mov_i64, ret, arg);
+    }
+}
+
+static inline void tcg_gen_movi_i64(TCGv_i64 ret, int64_t arg)
+{
+    tcg_gen_op2i_i64(INDEX_op_movi_i64, ret, arg);
+}
+
+static inline void tcg_gen_ld8u_i64(TCGv_i64 ret, TCGv_ptr arg2,
+                                    tcg_target_long offset)
+{
+    tcg_gen_ldst_op_i64(INDEX_op_ld8u_i64, ret, arg2, offset);
+}
+
+static inline void tcg_gen_ld8s_i64(TCGv_i64 ret, TCGv_ptr arg2,
+                                    tcg_target_long offset)
+{
+    tcg_gen_ldst_op_i64(INDEX_op_ld8s_i64, ret, arg2, offset);
+}
+
+static inline void tcg_gen_ld16u_i64(TCGv_i64 ret, TCGv_ptr arg2,
+                                     tcg_target_long offset)
+{
+    tcg_gen_ldst_op_i64(INDEX_op_ld16u_i64, ret, arg2, offset);
+}
+
+static inline void tcg_gen_ld16s_i64(TCGv_i64 ret, TCGv_ptr arg2,
+                                     tcg_target_long offset)
+{
+    tcg_gen_ldst_op_i64(INDEX_op_ld16s_i64, ret, arg2, offset);
+}
+
+static inline void tcg_gen_ld32u_i64(TCGv_i64 ret, TCGv_ptr arg2,
+                                     tcg_target_long offset)
+{
+    tcg_gen_ldst_op_i64(INDEX_op_ld32u_i64, ret, arg2, offset);
+}
+
+static inline void tcg_gen_ld32s_i64(TCGv_i64 ret, TCGv_ptr arg2,
+                                     tcg_target_long offset)
+{
+    tcg_gen_ldst_op_i64(INDEX_op_ld32s_i64, ret, arg2, offset);
+}
+
+static inline void tcg_gen_ld_i64(TCGv_i64 ret, TCGv_ptr arg2,
+                                  tcg_target_long offset)
+{
+    tcg_gen_ldst_op_i64(INDEX_op_ld_i64, ret, arg2, offset);
+}
+
+static inline void tcg_gen_st8_i64(TCGv_i64 arg1, TCGv_ptr arg2,
+                                   tcg_target_long offset)
+{
+    tcg_gen_ldst_op_i64(INDEX_op_st8_i64, arg1, arg2, offset);
+}
+
+static inline void tcg_gen_st16_i64(TCGv_i64 arg1, TCGv_ptr arg2,
+                                    tcg_target_long offset)
+{
+    tcg_gen_ldst_op_i64(INDEX_op_st16_i64, arg1, arg2, offset);
+}
+
+static inline void tcg_gen_st32_i64(TCGv_i64 arg1, TCGv_ptr arg2,
+                                    tcg_target_long offset)
+{
+    tcg_gen_ldst_op_i64(INDEX_op_st32_i64, arg1, arg2, offset);
+}
+
+static inline void tcg_gen_st_i64(TCGv_i64 arg1, TCGv_ptr arg2,
+                                  tcg_target_long offset)
+{
+    tcg_gen_ldst_op_i64(INDEX_op_st_i64, arg1, arg2, offset);
+}
+
+static inline void tcg_gen_add_i64(TCGv_i64 ret, TCGv_i64 arg1, TCGv_i64 arg2)
+{
+    tcg_gen_op3_i64(INDEX_op_add_i64, ret, arg1, arg2);
+}
+
+static inline void tcg_gen_sub_i64(TCGv_i64 ret, TCGv_i64 arg1, TCGv_i64 arg2)
+{
+    tcg_gen_op3_i64(INDEX_op_sub_i64, ret, arg1, arg2);
+}
+
+static inline void tcg_gen_and_i64(TCGv_i64 ret, TCGv_i64 arg1, TCGv_i64 arg2)
+{
+    tcg_gen_op3_i64(INDEX_op_and_i64, ret, arg1, arg2);
+}
+
+static inline void tcg_gen_or_i64(TCGv_i64 ret, TCGv_i64 arg1, TCGv_i64 arg2)
+{
+    tcg_gen_op3_i64(INDEX_op_or_i64, ret, arg1, arg2);
+}
+
+static inline void tcg_gen_xor_i64(TCGv_i64 ret, TCGv_i64 arg1, TCGv_i64 arg2)
+{
+    tcg_gen_op3_i64(INDEX_op_xor_i64, ret, arg1, arg2);
+}
+
+static inline void tcg_gen_shl_i64(TCGv_i64 ret, TCGv_i64 arg1, TCGv_i64 arg2)
+{
+    tcg_gen_op3_i64(INDEX_op_shl_i64, ret, arg1, arg2);
+}
+
+static inline void tcg_gen_shr_i64(TCGv_i64 ret, TCGv_i64 arg1, TCGv_i64 arg2)
+{
+    tcg_gen_op3_i64(INDEX_op_shr_i64, ret, arg1, arg2);
+}
+
+static inline void tcg_gen_sar_i64(TCGv_i64 ret, TCGv_i64 arg1, TCGv_i64 arg2)
+{
+    tcg_gen_op3_i64(INDEX_op_sar_i64, ret, arg1, arg2);
+}
+
+static inline void tcg_gen_mul_i64(TCGv_i64 ret, TCGv_i64 arg1, TCGv_i64 arg2)
+{
+    tcg_gen_op3_i64(INDEX_op_mul_i64, ret, arg1, arg2);
+}
+#else /* TCG_TARGET_REG_BITS == 32 */
+static inline void tcg_gen_st8_i64(TCGv_i64 arg1, TCGv_ptr arg2,
+                                   tcg_target_long offset)
+{
+    tcg_gen_st8_i32(TCGV_LOW(arg1), arg2, offset);
+}
+
+static inline void tcg_gen_st16_i64(TCGv_i64 arg1, TCGv_ptr arg2,
+                                    tcg_target_long offset)
+{
+    tcg_gen_st16_i32(TCGV_LOW(arg1), arg2, offset);
+}
+
+static inline void tcg_gen_st32_i64(TCGv_i64 arg1, TCGv_ptr arg2,
+                                    tcg_target_long offset)
+{
+    tcg_gen_st_i32(TCGV_LOW(arg1), arg2, offset);
+}
+
+static inline void tcg_gen_add_i64(TCGv_i64 ret, TCGv_i64 arg1, TCGv_i64 arg2)
+{
+    tcg_gen_add2_i32(TCGV_LOW(ret), TCGV_HIGH(ret), TCGV_LOW(arg1),
+                     TCGV_HIGH(arg1), TCGV_LOW(arg2), TCGV_HIGH(arg2));
+}
+
+static inline void tcg_gen_sub_i64(TCGv_i64 ret, TCGv_i64 arg1, TCGv_i64 arg2)
+{
+    tcg_gen_sub2_i32(TCGV_LOW(ret), TCGV_HIGH(ret), TCGV_LOW(arg1),
+                     TCGV_HIGH(arg1), TCGV_LOW(arg2), TCGV_HIGH(arg2));
+}
+
+void tcg_gen_discard_i64(TCGv_i64 arg);
+void tcg_gen_mov_i64(TCGv_i64 ret, TCGv_i64 arg);
+void tcg_gen_movi_i64(TCGv_i64 ret, int64_t arg);
+void tcg_gen_ld8u_i64(TCGv_i64 ret, TCGv_ptr arg2, tcg_target_long offset);
+void tcg_gen_ld8s_i64(TCGv_i64 ret, TCGv_ptr arg2, tcg_target_long offset);
+void tcg_gen_ld16u_i64(TCGv_i64 ret, TCGv_ptr arg2, tcg_target_long offset);
+void tcg_gen_ld16s_i64(TCGv_i64 ret, TCGv_ptr arg2, tcg_target_long offset);
+void tcg_gen_ld32u_i64(TCGv_i64 ret, TCGv_ptr arg2, tcg_target_long offset);
+void tcg_gen_ld32s_i64(TCGv_i64 ret, TCGv_ptr arg2, tcg_target_long offset);
+void tcg_gen_ld_i64(TCGv_i64 ret, TCGv_ptr arg2, tcg_target_long offset);
+void tcg_gen_st_i64(TCGv_i64 arg1, TCGv_ptr arg2, tcg_target_long offset);
+void tcg_gen_and_i64(TCGv_i64 ret, TCGv_i64 arg1, TCGv_i64 arg2);
+void tcg_gen_or_i64(TCGv_i64 ret, TCGv_i64 arg1, TCGv_i64 arg2);
+void tcg_gen_xor_i64(TCGv_i64 ret, TCGv_i64 arg1, TCGv_i64 arg2);
+void tcg_gen_shl_i64(TCGv_i64 ret, TCGv_i64 arg1, TCGv_i64 arg2);
+void tcg_gen_shr_i64(TCGv_i64 ret, TCGv_i64 arg1, TCGv_i64 arg2);
+void tcg_gen_sar_i64(TCGv_i64 ret, TCGv_i64 arg1, TCGv_i64 arg2);
+void tcg_gen_mul_i64(TCGv_i64 ret, TCGv_i64 arg1, TCGv_i64 arg2);
+#endif /* TCG_TARGET_REG_BITS */
+
+static inline void tcg_gen_neg_i64(TCGv_i64 ret, TCGv_i64 arg)
+{
+    if (TCG_TARGET_HAS_neg_i64) {
+        tcg_gen_op2_i64(INDEX_op_neg_i64, ret, arg);
+    } else {
+        tcg_gen_subfi_i64(ret, 0, arg);
+    }
+}
+
+/* Size changing operations.  */
+
+void tcg_gen_extu_i32_i64(TCGv_i64 ret, TCGv_i32 arg);
+void tcg_gen_ext_i32_i64(TCGv_i64 ret, TCGv_i32 arg);
+void tcg_gen_concat_i32_i64(TCGv_i64 dest, TCGv_i32 low, TCGv_i32 high);
+void tcg_gen_trunc_shr_i64_i32(TCGv_i32 ret, TCGv_i64 arg, unsigned int c);
+void tcg_gen_extr_i64_i32(TCGv_i32 lo, TCGv_i32 hi, TCGv_i64 arg);
+void tcg_gen_extr32_i64(TCGv_i64 lo, TCGv_i64 hi, TCGv_i64 arg);
+
+static inline void tcg_gen_concat32_i64(TCGv_i64 ret, TCGv_i64 lo, TCGv_i64 hi)
+{
+    tcg_gen_deposit_i64(ret, lo, hi, 32, 32);
+}
+
+static inline void tcg_gen_trunc_i64_i32(TCGv_i32 ret, TCGv_i64 arg)
+{
+    tcg_gen_trunc_shr_i64_i32(ret, arg, 0);
+}
+
+/* QEMU specific operations.  */
+
+#ifndef TARGET_LONG_BITS
+#error must include QEMU headers
+#endif
+
+/* debug info: write the PC of the corresponding QEMU CPU instruction */
+static inline void tcg_gen_debug_insn_start(uint64_t pc)
+{
+    /* XXX: must really use a 32 bit size for TCGArg in all cases */
+#if TARGET_LONG_BITS > TCG_TARGET_REG_BITS
+    tcg_gen_op2ii(INDEX_op_debug_insn_start,
+                  (uint32_t)(pc), (uint32_t)(pc >> 32));
+#else
+    tcg_gen_op1i(INDEX_op_debug_insn_start, pc);
+#endif
+}
+
+static inline void tcg_gen_exit_tb(uintptr_t val)
+{
+    tcg_gen_op1i(INDEX_op_exit_tb, val);
+}
+
+void tcg_gen_goto_tb(unsigned idx);
+
+#if TARGET_LONG_BITS == 32
+#define TCGv TCGv_i32
+#define tcg_temp_new() tcg_temp_new_i32()
+#define tcg_global_reg_new tcg_global_reg_new_i32
+#define tcg_global_mem_new tcg_global_mem_new_i32
+#define tcg_temp_local_new() tcg_temp_local_new_i32()
+#define tcg_temp_free tcg_temp_free_i32
+#define TCGV_UNUSED(x) TCGV_UNUSED_I32(x)
+#define TCGV_IS_UNUSED(x) TCGV_IS_UNUSED_I32(x)
+#define TCGV_EQUAL(a, b) TCGV_EQUAL_I32(a, b)
+#define tcg_gen_qemu_ld_tl tcg_gen_qemu_ld_i32
+#define tcg_gen_qemu_st_tl tcg_gen_qemu_st_i32
+#else
+#define TCGv TCGv_i64
+#define tcg_temp_new() tcg_temp_new_i64()
+#define tcg_global_reg_new tcg_global_reg_new_i64
+#define tcg_global_mem_new tcg_global_mem_new_i64
+#define tcg_temp_local_new() tcg_temp_local_new_i64()
+#define tcg_temp_free tcg_temp_free_i64
+#define TCGV_UNUSED(x) TCGV_UNUSED_I64(x)
+#define TCGV_IS_UNUSED(x) TCGV_IS_UNUSED_I64(x)
+#define TCGV_EQUAL(a, b) TCGV_EQUAL_I64(a, b)
+#define tcg_gen_qemu_ld_tl tcg_gen_qemu_ld_i64
+#define tcg_gen_qemu_st_tl tcg_gen_qemu_st_i64
+#endif
+
+void tcg_gen_qemu_ld_i32(TCGv_i32, TCGv, TCGArg, TCGMemOp);
+void tcg_gen_qemu_st_i32(TCGv_i32, TCGv, TCGArg, TCGMemOp);
+void tcg_gen_qemu_ld_i64(TCGv_i64, TCGv, TCGArg, TCGMemOp);
+void tcg_gen_qemu_st_i64(TCGv_i64, TCGv, TCGArg, TCGMemOp);
+
+static inline void tcg_gen_qemu_ld8u(TCGv ret, TCGv addr, int mem_index)
+{
+    tcg_gen_qemu_ld_tl(ret, addr, mem_index, MO_UB);
+}
+
+static inline void tcg_gen_qemu_ld8s(TCGv ret, TCGv addr, int mem_index)
+{
+    tcg_gen_qemu_ld_tl(ret, addr, mem_index, MO_SB);
+}
+
+static inline void tcg_gen_qemu_ld16u(TCGv ret, TCGv addr, int mem_index)
+{
+    tcg_gen_qemu_ld_tl(ret, addr, mem_index, MO_TEUW);
+}
+
+static inline void tcg_gen_qemu_ld16s(TCGv ret, TCGv addr, int mem_index)
+{
+    tcg_gen_qemu_ld_tl(ret, addr, mem_index, MO_TESW);
+}
+
+static inline void tcg_gen_qemu_ld32u(TCGv ret, TCGv addr, int mem_index)
+{
+    tcg_gen_qemu_ld_tl(ret, addr, mem_index, MO_TEUL);
+}
+
+static inline void tcg_gen_qemu_ld32s(TCGv ret, TCGv addr, int mem_index)
+{
+    tcg_gen_qemu_ld_tl(ret, addr, mem_index, MO_TESL);
+}
+
+static inline void tcg_gen_qemu_ld64(TCGv_i64 ret, TCGv addr, int mem_index)
+{
+    tcg_gen_qemu_ld_i64(ret, addr, mem_index, MO_TEQ);
+}
+
+static inline void tcg_gen_qemu_st8(TCGv arg, TCGv addr, int mem_index)
+{
+    tcg_gen_qemu_st_tl(arg, addr, mem_index, MO_UB);
+}
+
+static inline void tcg_gen_qemu_st16(TCGv arg, TCGv addr, int mem_index)
+{
+    tcg_gen_qemu_st_tl(arg, addr, mem_index, MO_TEUW);
+}
+
+static inline void tcg_gen_qemu_st32(TCGv arg, TCGv addr, int mem_index)
+{
+    tcg_gen_qemu_st_tl(arg, addr, mem_index, MO_TEUL);
+}
+
+static inline void tcg_gen_qemu_st64(TCGv_i64 arg, TCGv addr, int mem_index)
+{
+    tcg_gen_qemu_st_i64(arg, addr, mem_index, MO_TEQ);
+}
+
+#if TARGET_LONG_BITS == 64
+#define tcg_gen_movi_tl tcg_gen_movi_i64
+#define tcg_gen_mov_tl tcg_gen_mov_i64
+#define tcg_gen_ld8u_tl tcg_gen_ld8u_i64
+#define tcg_gen_ld8s_tl tcg_gen_ld8s_i64
+#define tcg_gen_ld16u_tl tcg_gen_ld16u_i64
+#define tcg_gen_ld16s_tl tcg_gen_ld16s_i64
+#define tcg_gen_ld32u_tl tcg_gen_ld32u_i64
+#define tcg_gen_ld32s_tl tcg_gen_ld32s_i64
+#define tcg_gen_ld_tl tcg_gen_ld_i64
+#define tcg_gen_st8_tl tcg_gen_st8_i64
+#define tcg_gen_st16_tl tcg_gen_st16_i64
+#define tcg_gen_st32_tl tcg_gen_st32_i64
+#define tcg_gen_st_tl tcg_gen_st_i64
+#define tcg_gen_add_tl tcg_gen_add_i64
+#define tcg_gen_addi_tl tcg_gen_addi_i64
+#define tcg_gen_sub_tl tcg_gen_sub_i64
+#define tcg_gen_neg_tl tcg_gen_neg_i64
+#define tcg_gen_subfi_tl tcg_gen_subfi_i64
+#define tcg_gen_subi_tl tcg_gen_subi_i64
+#define tcg_gen_and_tl tcg_gen_and_i64
+#define tcg_gen_andi_tl tcg_gen_andi_i64
+#define tcg_gen_or_tl tcg_gen_or_i64
+#define tcg_gen_ori_tl tcg_gen_ori_i64
+#define tcg_gen_xor_tl tcg_gen_xor_i64
+#define tcg_gen_xori_tl tcg_gen_xori_i64
+#define tcg_gen_not_tl tcg_gen_not_i64
+#define tcg_gen_shl_tl tcg_gen_shl_i64
+#define tcg_gen_shli_tl tcg_gen_shli_i64
+#define tcg_gen_shr_tl tcg_gen_shr_i64
+#define tcg_gen_shri_tl tcg_gen_shri_i64
+#define tcg_gen_sar_tl tcg_gen_sar_i64
+#define tcg_gen_sari_tl tcg_gen_sari_i64
+#define tcg_gen_brcond_tl tcg_gen_brcond_i64
+#define tcg_gen_brcondi_tl tcg_gen_brcondi_i64
+#define tcg_gen_setcond_tl tcg_gen_setcond_i64
+#define tcg_gen_setcondi_tl tcg_gen_setcondi_i64
+#define tcg_gen_mul_tl tcg_gen_mul_i64
+#define tcg_gen_muli_tl tcg_gen_muli_i64
+#define tcg_gen_div_tl tcg_gen_div_i64
+#define tcg_gen_rem_tl tcg_gen_rem_i64
+#define tcg_gen_divu_tl tcg_gen_divu_i64
+#define tcg_gen_remu_tl tcg_gen_remu_i64
+#define tcg_gen_discard_tl tcg_gen_discard_i64
+#define tcg_gen_trunc_tl_i32 tcg_gen_trunc_i64_i32
+#define tcg_gen_trunc_i64_tl tcg_gen_mov_i64
+#define tcg_gen_extu_i32_tl tcg_gen_extu_i32_i64
+#define tcg_gen_ext_i32_tl tcg_gen_ext_i32_i64
+#define tcg_gen_extu_tl_i64 tcg_gen_mov_i64
+#define tcg_gen_ext_tl_i64 tcg_gen_mov_i64
+#define tcg_gen_ext8u_tl tcg_gen_ext8u_i64
+#define tcg_gen_ext8s_tl tcg_gen_ext8s_i64
+#define tcg_gen_ext16u_tl tcg_gen_ext16u_i64
+#define tcg_gen_ext16s_tl tcg_gen_ext16s_i64
+#define tcg_gen_ext32u_tl tcg_gen_ext32u_i64
+#define tcg_gen_ext32s_tl tcg_gen_ext32s_i64
+#define tcg_gen_bswap16_tl tcg_gen_bswap16_i64
+#define tcg_gen_bswap32_tl tcg_gen_bswap32_i64
+#define tcg_gen_bswap64_tl tcg_gen_bswap64_i64
+#define tcg_gen_concat_tl_i64 tcg_gen_concat32_i64
+#define tcg_gen_extr_i64_tl tcg_gen_extr32_i64
+#define tcg_gen_andc_tl tcg_gen_andc_i64
+#define tcg_gen_eqv_tl tcg_gen_eqv_i64
+#define tcg_gen_nand_tl tcg_gen_nand_i64
+#define tcg_gen_nor_tl tcg_gen_nor_i64
+#define tcg_gen_orc_tl tcg_gen_orc_i64
+#define tcg_gen_rotl_tl tcg_gen_rotl_i64
+#define tcg_gen_rotli_tl tcg_gen_rotli_i64
+#define tcg_gen_rotr_tl tcg_gen_rotr_i64
+#define tcg_gen_rotri_tl tcg_gen_rotri_i64
+#define tcg_gen_deposit_tl tcg_gen_deposit_i64
+#define tcg_const_tl tcg_const_i64
+#define tcg_const_local_tl tcg_const_local_i64
+#define tcg_gen_movcond_tl tcg_gen_movcond_i64
+#define tcg_gen_add2_tl tcg_gen_add2_i64
+#define tcg_gen_sub2_tl tcg_gen_sub2_i64
+#define tcg_gen_mulu2_tl tcg_gen_mulu2_i64
+#define tcg_gen_muls2_tl tcg_gen_muls2_i64
+#else
+#define tcg_gen_movi_tl tcg_gen_movi_i32
+#define tcg_gen_mov_tl tcg_gen_mov_i32
+#define tcg_gen_ld8u_tl tcg_gen_ld8u_i32
+#define tcg_gen_ld8s_tl tcg_gen_ld8s_i32
+#define tcg_gen_ld16u_tl tcg_gen_ld16u_i32
+#define tcg_gen_ld16s_tl tcg_gen_ld16s_i32
+#define tcg_gen_ld32u_tl tcg_gen_ld_i32
+#define tcg_gen_ld32s_tl tcg_gen_ld_i32
+#define tcg_gen_ld_tl tcg_gen_ld_i32
+#define tcg_gen_st8_tl tcg_gen_st8_i32
+#define tcg_gen_st16_tl tcg_gen_st16_i32
+#define tcg_gen_st32_tl tcg_gen_st_i32
+#define tcg_gen_st_tl tcg_gen_st_i32
+#define tcg_gen_add_tl tcg_gen_add_i32
+#define tcg_gen_addi_tl tcg_gen_addi_i32
+#define tcg_gen_sub_tl tcg_gen_sub_i32
+#define tcg_gen_neg_tl tcg_gen_neg_i32
+#define tcg_gen_subfi_tl tcg_gen_subfi_i32
+#define tcg_gen_subi_tl tcg_gen_subi_i32
+#define tcg_gen_and_tl tcg_gen_and_i32
+#define tcg_gen_andi_tl tcg_gen_andi_i32
+#define tcg_gen_or_tl tcg_gen_or_i32
+#define tcg_gen_ori_tl tcg_gen_ori_i32
+#define tcg_gen_xor_tl tcg_gen_xor_i32
+#define tcg_gen_xori_tl tcg_gen_xori_i32
+#define tcg_gen_not_tl tcg_gen_not_i32
+#define tcg_gen_shl_tl tcg_gen_shl_i32
+#define tcg_gen_shli_tl tcg_gen_shli_i32
+#define tcg_gen_shr_tl tcg_gen_shr_i32
+#define tcg_gen_shri_tl tcg_gen_shri_i32
+#define tcg_gen_sar_tl tcg_gen_sar_i32
+#define tcg_gen_sari_tl tcg_gen_sari_i32
+#define tcg_gen_brcond_tl tcg_gen_brcond_i32
+#define tcg_gen_brcondi_tl tcg_gen_brcondi_i32
+#define tcg_gen_setcond_tl tcg_gen_setcond_i32
+#define tcg_gen_setcondi_tl tcg_gen_setcondi_i32
+#define tcg_gen_mul_tl tcg_gen_mul_i32
+#define tcg_gen_muli_tl tcg_gen_muli_i32
+#define tcg_gen_div_tl tcg_gen_div_i32
+#define tcg_gen_rem_tl tcg_gen_rem_i32
+#define tcg_gen_divu_tl tcg_gen_divu_i32
+#define tcg_gen_remu_tl tcg_gen_remu_i32
+#define tcg_gen_discard_tl tcg_gen_discard_i32
+#define tcg_gen_trunc_tl_i32 tcg_gen_mov_i32
+#define tcg_gen_trunc_i64_tl tcg_gen_trunc_i64_i32
+#define tcg_gen_extu_i32_tl tcg_gen_mov_i32
+#define tcg_gen_ext_i32_tl tcg_gen_mov_i32
+#define tcg_gen_extu_tl_i64 tcg_gen_extu_i32_i64
+#define tcg_gen_ext_tl_i64 tcg_gen_ext_i32_i64
+#define tcg_gen_ext8u_tl tcg_gen_ext8u_i32
+#define tcg_gen_ext8s_tl tcg_gen_ext8s_i32
+#define tcg_gen_ext16u_tl tcg_gen_ext16u_i32
+#define tcg_gen_ext16s_tl tcg_gen_ext16s_i32
+#define tcg_gen_ext32u_tl tcg_gen_mov_i32
+#define tcg_gen_ext32s_tl tcg_gen_mov_i32
+#define tcg_gen_bswap16_tl tcg_gen_bswap16_i32
+#define tcg_gen_bswap32_tl tcg_gen_bswap32_i32
+#define tcg_gen_concat_tl_i64 tcg_gen_concat_i32_i64
+#define tcg_gen_extr_i64_tl tcg_gen_extr_i64_i32
+#define tcg_gen_andc_tl tcg_gen_andc_i32
+#define tcg_gen_eqv_tl tcg_gen_eqv_i32
+#define tcg_gen_nand_tl tcg_gen_nand_i32
+#define tcg_gen_nor_tl tcg_gen_nor_i32
+#define tcg_gen_orc_tl tcg_gen_orc_i32
+#define tcg_gen_rotl_tl tcg_gen_rotl_i32
+#define tcg_gen_rotli_tl tcg_gen_rotli_i32
+#define tcg_gen_rotr_tl tcg_gen_rotr_i32
+#define tcg_gen_rotri_tl tcg_gen_rotri_i32
+#define tcg_gen_deposit_tl tcg_gen_deposit_i32
+#define tcg_const_tl tcg_const_i32
+#define tcg_const_local_tl tcg_const_local_i32
+#define tcg_gen_movcond_tl tcg_gen_movcond_i32
+#define tcg_gen_add2_tl tcg_gen_add2_i32
+#define tcg_gen_sub2_tl tcg_gen_sub2_i32
+#define tcg_gen_mulu2_tl tcg_gen_mulu2_i32
+#define tcg_gen_muls2_tl tcg_gen_muls2_i32
+#endif
+
+#if UINTPTR_MAX == UINT32_MAX
+# define tcg_gen_ld_ptr(R, A, O) \
+    tcg_gen_ld_i32(TCGV_PTR_TO_NAT(R), (A), (O))
+# define tcg_gen_discard_ptr(A) \
+    tcg_gen_discard_i32(TCGV_PTR_TO_NAT(A))
+# define tcg_gen_add_ptr(R, A, B) \
+    tcg_gen_add_i32(TCGV_PTR_TO_NAT(R), TCGV_PTR_TO_NAT(A), TCGV_PTR_TO_NAT(B))
+# define tcg_gen_addi_ptr(R, A, B) \
+    tcg_gen_addi_i32(TCGV_PTR_TO_NAT(R), TCGV_PTR_TO_NAT(A), (B))
+# define tcg_gen_ext_i32_ptr(R, A) \
+    tcg_gen_mov_i32(TCGV_PTR_TO_NAT(R), (A))
+#else
+# define tcg_gen_ld_ptr(R, A, O) \
+    tcg_gen_ld_i64(TCGV_PTR_TO_NAT(R), (A), (O))
+# define tcg_gen_discard_ptr(A) \
+    tcg_gen_discard_i64(TCGV_PTR_TO_NAT(A))
+# define tcg_gen_add_ptr(R, A, B) \
+    tcg_gen_add_i64(TCGV_PTR_TO_NAT(R), TCGV_PTR_TO_NAT(A), TCGV_PTR_TO_NAT(B))
+# define tcg_gen_addi_ptr(R, A, B) \
+    tcg_gen_addi_i64(TCGV_PTR_TO_NAT(R), TCGV_PTR_TO_NAT(A), (B))
+# define tcg_gen_ext_i32_ptr(R, A) \
+    tcg_gen_ext_i32_i64(TCGV_PTR_TO_NAT(R), (A))
+#endif /* UINTPTR_MAX == UINT32_MAX */
diff --git a/tcg/tcg-opc.h b/tcg/tcg-opc.h
new file mode 100644
index 00000000..13ccb60a
--- /dev/null
+++ b/tcg/tcg-opc.h
@@ -0,0 +1,195 @@
+/*
+ * Tiny Code Generator for QEMU
+ *
+ * Copyright (c) 2008 Fabrice Bellard
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (the "Software"), to deal
+ * in the Software without restriction, including without limitation the rights
+ * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+ * copies of the Software, and to permit persons to whom the Software is
+ * furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+ * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+ * THE SOFTWARE.
+ */
+
+/*
+ * DEF(name, oargs, iargs, cargs, flags)
+ */
+
+/* predefined ops */
+DEF(discard, 1, 0, 0, TCG_OPF_NOT_PRESENT)
+DEF(set_label, 0, 0, 1, TCG_OPF_BB_END | TCG_OPF_NOT_PRESENT)
+
+/* variable number of parameters */
+DEF(call, 0, 0, 3, TCG_OPF_CALL_CLOBBER | TCG_OPF_NOT_PRESENT)
+
+DEF(br, 0, 0, 1, TCG_OPF_BB_END)
+
+#define IMPL(X) (__builtin_constant_p(X) && !(X) ? TCG_OPF_NOT_PRESENT : 0)
+#if TCG_TARGET_REG_BITS == 32
+# define IMPL64  TCG_OPF_64BIT | TCG_OPF_NOT_PRESENT
+#else
+# define IMPL64  TCG_OPF_64BIT
+#endif
+
+DEF(mov_i32, 1, 1, 0, TCG_OPF_NOT_PRESENT)
+DEF(movi_i32, 1, 0, 1, TCG_OPF_NOT_PRESENT)
+DEF(setcond_i32, 1, 2, 1, 0)
+DEF(movcond_i32, 1, 4, 1, IMPL(TCG_TARGET_HAS_movcond_i32))
+/* load/store */
+DEF(ld8u_i32, 1, 1, 1, 0)
+DEF(ld8s_i32, 1, 1, 1, 0)
+DEF(ld16u_i32, 1, 1, 1, 0)
+DEF(ld16s_i32, 1, 1, 1, 0)
+DEF(ld_i32, 1, 1, 1, 0)
+DEF(st8_i32, 0, 2, 1, 0)
+DEF(st16_i32, 0, 2, 1, 0)
+DEF(st_i32, 0, 2, 1, 0)
+/* arith */
+DEF(add_i32, 1, 2, 0, 0)
+DEF(sub_i32, 1, 2, 0, 0)
+DEF(mul_i32, 1, 2, 0, 0)
+DEF(div_i32, 1, 2, 0, IMPL(TCG_TARGET_HAS_div_i32))
+DEF(divu_i32, 1, 2, 0, IMPL(TCG_TARGET_HAS_div_i32))
+DEF(rem_i32, 1, 2, 0, IMPL(TCG_TARGET_HAS_rem_i32))
+DEF(remu_i32, 1, 2, 0, IMPL(TCG_TARGET_HAS_rem_i32))
+DEF(div2_i32, 2, 3, 0, IMPL(TCG_TARGET_HAS_div2_i32))
+DEF(divu2_i32, 2, 3, 0, IMPL(TCG_TARGET_HAS_div2_i32))
+DEF(and_i32, 1, 2, 0, 0)
+DEF(or_i32, 1, 2, 0, 0)
+DEF(xor_i32, 1, 2, 0, 0)
+/* shifts/rotates */
+DEF(shl_i32, 1, 2, 0, 0)
+DEF(shr_i32, 1, 2, 0, 0)
+DEF(sar_i32, 1, 2, 0, 0)
+DEF(rotl_i32, 1, 2, 0, IMPL(TCG_TARGET_HAS_rot_i32))
+DEF(rotr_i32, 1, 2, 0, IMPL(TCG_TARGET_HAS_rot_i32))
+DEF(deposit_i32, 1, 2, 2, IMPL(TCG_TARGET_HAS_deposit_i32))
+
+DEF(brcond_i32, 0, 2, 2, TCG_OPF_BB_END)
+
+DEF(add2_i32, 2, 4, 0, IMPL(TCG_TARGET_HAS_add2_i32))
+DEF(sub2_i32, 2, 4, 0, IMPL(TCG_TARGET_HAS_sub2_i32))
+DEF(mulu2_i32, 2, 2, 0, IMPL(TCG_TARGET_HAS_mulu2_i32))
+DEF(muls2_i32, 2, 2, 0, IMPL(TCG_TARGET_HAS_muls2_i32))
+DEF(muluh_i32, 1, 2, 0, IMPL(TCG_TARGET_HAS_muluh_i32))
+DEF(mulsh_i32, 1, 2, 0, IMPL(TCG_TARGET_HAS_mulsh_i32))
+DEF(brcond2_i32, 0, 4, 2, TCG_OPF_BB_END | IMPL(TCG_TARGET_REG_BITS == 32))
+DEF(setcond2_i32, 1, 4, 1, IMPL(TCG_TARGET_REG_BITS == 32))
+
+DEF(ext8s_i32, 1, 1, 0, IMPL(TCG_TARGET_HAS_ext8s_i32))
+DEF(ext16s_i32, 1, 1, 0, IMPL(TCG_TARGET_HAS_ext16s_i32))
+DEF(ext8u_i32, 1, 1, 0, IMPL(TCG_TARGET_HAS_ext8u_i32))
+DEF(ext16u_i32, 1, 1, 0, IMPL(TCG_TARGET_HAS_ext16u_i32))
+DEF(bswap16_i32, 1, 1, 0, IMPL(TCG_TARGET_HAS_bswap16_i32))
+DEF(bswap32_i32, 1, 1, 0, IMPL(TCG_TARGET_HAS_bswap32_i32))
+DEF(not_i32, 1, 1, 0, IMPL(TCG_TARGET_HAS_not_i32))
+DEF(neg_i32, 1, 1, 0, IMPL(TCG_TARGET_HAS_neg_i32))
+DEF(andc_i32, 1, 2, 0, IMPL(TCG_TARGET_HAS_andc_i32))
+DEF(orc_i32, 1, 2, 0, IMPL(TCG_TARGET_HAS_orc_i32))
+DEF(eqv_i32, 1, 2, 0, IMPL(TCG_TARGET_HAS_eqv_i32))
+DEF(nand_i32, 1, 2, 0, IMPL(TCG_TARGET_HAS_nand_i32))
+DEF(nor_i32, 1, 2, 0, IMPL(TCG_TARGET_HAS_nor_i32))
+
+DEF(mov_i64, 1, 1, 0, TCG_OPF_64BIT | TCG_OPF_NOT_PRESENT)
+DEF(movi_i64, 1, 0, 1, TCG_OPF_64BIT | TCG_OPF_NOT_PRESENT)
+DEF(setcond_i64, 1, 2, 1, IMPL64)
+DEF(movcond_i64, 1, 4, 1, IMPL64 | IMPL(TCG_TARGET_HAS_movcond_i64))
+/* load/store */
+DEF(ld8u_i64, 1, 1, 1, IMPL64)
+DEF(ld8s_i64, 1, 1, 1, IMPL64)
+DEF(ld16u_i64, 1, 1, 1, IMPL64)
+DEF(ld16s_i64, 1, 1, 1, IMPL64)
+DEF(ld32u_i64, 1, 1, 1, IMPL64)
+DEF(ld32s_i64, 1, 1, 1, IMPL64)
+DEF(ld_i64, 1, 1, 1, IMPL64)
+DEF(st8_i64, 0, 2, 1, IMPL64)
+DEF(st16_i64, 0, 2, 1, IMPL64)
+DEF(st32_i64, 0, 2, 1, IMPL64)
+DEF(st_i64, 0, 2, 1, IMPL64)
+/* arith */
+DEF(add_i64, 1, 2, 0, IMPL64)
+DEF(sub_i64, 1, 2, 0, IMPL64)
+DEF(mul_i64, 1, 2, 0, IMPL64)
+DEF(div_i64, 1, 2, 0, IMPL64 | IMPL(TCG_TARGET_HAS_div_i64))
+DEF(divu_i64, 1, 2, 0, IMPL64 | IMPL(TCG_TARGET_HAS_div_i64))
+DEF(rem_i64, 1, 2, 0, IMPL64 | IMPL(TCG_TARGET_HAS_rem_i64))
+DEF(remu_i64, 1, 2, 0, IMPL64 | IMPL(TCG_TARGET_HAS_rem_i64))
+DEF(div2_i64, 2, 3, 0, IMPL64 | IMPL(TCG_TARGET_HAS_div2_i64))
+DEF(divu2_i64, 2, 3, 0, IMPL64 | IMPL(TCG_TARGET_HAS_div2_i64))
+DEF(and_i64, 1, 2, 0, IMPL64)
+DEF(or_i64, 1, 2, 0, IMPL64)
+DEF(xor_i64, 1, 2, 0, IMPL64)
+/* shifts/rotates */
+DEF(shl_i64, 1, 2, 0, IMPL64)
+DEF(shr_i64, 1, 2, 0, IMPL64)
+DEF(sar_i64, 1, 2, 0, IMPL64)
+DEF(rotl_i64, 1, 2, 0, IMPL64 | IMPL(TCG_TARGET_HAS_rot_i64))
+DEF(rotr_i64, 1, 2, 0, IMPL64 | IMPL(TCG_TARGET_HAS_rot_i64))
+DEF(deposit_i64, 1, 2, 2, IMPL64 | IMPL(TCG_TARGET_HAS_deposit_i64))
+
+DEF(trunc_shr_i32, 1, 1, 1,
+    IMPL(TCG_TARGET_HAS_trunc_shr_i32)
+    | (TCG_TARGET_REG_BITS == 32 ? TCG_OPF_NOT_PRESENT : 0))
+
+DEF(brcond_i64, 0, 2, 2, TCG_OPF_BB_END | IMPL64)
+DEF(ext8s_i64, 1, 1, 0, IMPL64 | IMPL(TCG_TARGET_HAS_ext8s_i64))
+DEF(ext16s_i64, 1, 1, 0, IMPL64 | IMPL(TCG_TARGET_HAS_ext16s_i64))
+DEF(ext32s_i64, 1, 1, 0, IMPL64 | IMPL(TCG_TARGET_HAS_ext32s_i64))
+DEF(ext8u_i64, 1, 1, 0, IMPL64 | IMPL(TCG_TARGET_HAS_ext8u_i64))
+DEF(ext16u_i64, 1, 1, 0, IMPL64 | IMPL(TCG_TARGET_HAS_ext16u_i64))
+DEF(ext32u_i64, 1, 1, 0, IMPL64 | IMPL(TCG_TARGET_HAS_ext32u_i64))
+DEF(bswap16_i64, 1, 1, 0, IMPL64 | IMPL(TCG_TARGET_HAS_bswap16_i64))
+DEF(bswap32_i64, 1, 1, 0, IMPL64 | IMPL(TCG_TARGET_HAS_bswap32_i64))
+DEF(bswap64_i64, 1, 1, 0, IMPL64 | IMPL(TCG_TARGET_HAS_bswap64_i64))
+DEF(not_i64, 1, 1, 0, IMPL64 | IMPL(TCG_TARGET_HAS_not_i64))
+DEF(neg_i64, 1, 1, 0, IMPL64 | IMPL(TCG_TARGET_HAS_neg_i64))
+DEF(andc_i64, 1, 2, 0, IMPL64 | IMPL(TCG_TARGET_HAS_andc_i64))
+DEF(orc_i64, 1, 2, 0, IMPL64 | IMPL(TCG_TARGET_HAS_orc_i64))
+DEF(eqv_i64, 1, 2, 0, IMPL64 | IMPL(TCG_TARGET_HAS_eqv_i64))
+DEF(nand_i64, 1, 2, 0, IMPL64 | IMPL(TCG_TARGET_HAS_nand_i64))
+DEF(nor_i64, 1, 2, 0, IMPL64 | IMPL(TCG_TARGET_HAS_nor_i64))
+
+DEF(add2_i64, 2, 4, 0, IMPL64 | IMPL(TCG_TARGET_HAS_add2_i64))
+DEF(sub2_i64, 2, 4, 0, IMPL64 | IMPL(TCG_TARGET_HAS_sub2_i64))
+DEF(mulu2_i64, 2, 2, 0, IMPL64 | IMPL(TCG_TARGET_HAS_mulu2_i64))
+DEF(muls2_i64, 2, 2, 0, IMPL64 | IMPL(TCG_TARGET_HAS_muls2_i64))
+DEF(muluh_i64, 1, 2, 0, IMPL(TCG_TARGET_HAS_muluh_i64))
+DEF(mulsh_i64, 1, 2, 0, IMPL(TCG_TARGET_HAS_mulsh_i64))
+
+/* QEMU specific */
+#if TARGET_LONG_BITS > TCG_TARGET_REG_BITS
+DEF(debug_insn_start, 0, 0, 2, TCG_OPF_NOT_PRESENT)
+#else
+DEF(debug_insn_start, 0, 0, 1, TCG_OPF_NOT_PRESENT)
+#endif
+DEF(exit_tb, 0, 0, 1, TCG_OPF_BB_END)
+DEF(goto_tb, 0, 0, 1, TCG_OPF_BB_END)
+
+#define TLADDR_ARGS    (TARGET_LONG_BITS <= TCG_TARGET_REG_BITS ? 1 : 2)
+#define DATA64_ARGS  (TCG_TARGET_REG_BITS == 64 ? 1 : 2)
+
+DEF(qemu_ld_i32, 1, TLADDR_ARGS, 1,
+    TCG_OPF_CALL_CLOBBER | TCG_OPF_SIDE_EFFECTS)
+DEF(qemu_st_i32, 0, TLADDR_ARGS + 1, 1,
+    TCG_OPF_CALL_CLOBBER | TCG_OPF_SIDE_EFFECTS)
+DEF(qemu_ld_i64, DATA64_ARGS, TLADDR_ARGS, 1,
+    TCG_OPF_CALL_CLOBBER | TCG_OPF_SIDE_EFFECTS | TCG_OPF_64BIT)
+DEF(qemu_st_i64, 0, TLADDR_ARGS + DATA64_ARGS, 1,
+    TCG_OPF_CALL_CLOBBER | TCG_OPF_SIDE_EFFECTS | TCG_OPF_64BIT)
+
+#undef TLADDR_ARGS
+#undef DATA64_ARGS
+#undef IMPL
+#undef IMPL64
+#undef DEF
diff --git a/tcg/tcg-runtime.h b/tcg/tcg-runtime.h
new file mode 100644
index 00000000..23a0c377
--- /dev/null
+++ b/tcg/tcg-runtime.h
@@ -0,0 +1,16 @@
+DEF_HELPER_FLAGS_2(div_i32, TCG_CALL_NO_RWG_SE, s32, s32, s32)
+DEF_HELPER_FLAGS_2(rem_i32, TCG_CALL_NO_RWG_SE, s32, s32, s32)
+DEF_HELPER_FLAGS_2(divu_i32, TCG_CALL_NO_RWG_SE, i32, i32, i32)
+DEF_HELPER_FLAGS_2(remu_i32, TCG_CALL_NO_RWG_SE, i32, i32, i32)
+
+DEF_HELPER_FLAGS_2(div_i64, TCG_CALL_NO_RWG_SE, s64, s64, s64)
+DEF_HELPER_FLAGS_2(rem_i64, TCG_CALL_NO_RWG_SE, s64, s64, s64)
+DEF_HELPER_FLAGS_2(divu_i64, TCG_CALL_NO_RWG_SE, i64, i64, i64)
+DEF_HELPER_FLAGS_2(remu_i64, TCG_CALL_NO_RWG_SE, i64, i64, i64)
+
+DEF_HELPER_FLAGS_2(shl_i64, TCG_CALL_NO_RWG_SE, i64, i64, i64)
+DEF_HELPER_FLAGS_2(shr_i64, TCG_CALL_NO_RWG_SE, i64, i64, i64)
+DEF_HELPER_FLAGS_2(sar_i64, TCG_CALL_NO_RWG_SE, s64, s64, s64)
+
+DEF_HELPER_FLAGS_2(mulsh_i64, TCG_CALL_NO_RWG_SE, s64, s64, s64)
+DEF_HELPER_FLAGS_2(muluh_i64, TCG_CALL_NO_RWG_SE, i64, i64, i64)
diff --git a/tcg/tcg.c b/tcg/tcg.c
new file mode 100644
index 00000000..0892a9bb
--- /dev/null
+++ b/tcg/tcg.c
@@ -0,0 +1,2764 @@
+/*
+ * Tiny Code Generator for QEMU
+ *
+ * Copyright (c) 2008 Fabrice Bellard
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (the "Software"), to deal
+ * in the Software without restriction, including without limitation the rights
+ * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+ * copies of the Software, and to permit persons to whom the Software is
+ * furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+ * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+ * THE SOFTWARE.
+ */
+
+/* define it to use liveness analysis (better code) */
+#define USE_LIVENESS_ANALYSIS
+#define USE_TCG_OPTIMIZATIONS
+
+#include "config.h"
+
+/* Define to jump the ELF file used to communicate with GDB.  */
+#undef DEBUG_JIT
+
+#if !defined(CONFIG_DEBUG_TCG) && !defined(NDEBUG)
+/* define it to suppress various consistency checks (faster) */
+#define NDEBUG
+#endif
+
+#include "qemu-common.h"
+#include "qemu/host-utils.h"
+#include "qemu/timer.h"
+
+/* Note: the long term plan is to reduce the dependencies on the QEMU
+   CPU definitions. Currently they are used for qemu_ld/st
+   instructions */
+#define NO_CPU_IO_DEFS
+#include "cpu.h"
+
+#include "tcg-op.h"
+
+#if UINTPTR_MAX == UINT32_MAX
+# define ELF_CLASS  ELFCLASS32
+#else
+# define ELF_CLASS  ELFCLASS64
+#endif
+#ifdef HOST_WORDS_BIGENDIAN
+# define ELF_DATA   ELFDATA2MSB
+#else
+# define ELF_DATA   ELFDATA2LSB
+#endif
+
+#include "elf.h"
+
+/* Forward declarations for functions declared in tcg-target.c and used here. */
+static void tcg_target_init(TCGContext *s);
+static void tcg_target_qemu_prologue(TCGContext *s);
+static void patch_reloc(tcg_insn_unit *code_ptr, int type,
+                        intptr_t value, intptr_t addend);
+
+/* The CIE and FDE header definitions will be common to all hosts.  */
+typedef struct {
+    uint32_t len __attribute__((aligned((sizeof(void *)))));
+    uint32_t id;
+    uint8_t version;
+    char augmentation[1];
+    uint8_t code_align;
+    uint8_t data_align;
+    uint8_t return_column;
+} DebugFrameCIE;
+
+typedef struct QEMU_PACKED {
+    uint32_t len __attribute__((aligned((sizeof(void *)))));
+    uint32_t cie_offset;
+    uintptr_t func_start;
+    uintptr_t func_len;
+} DebugFrameFDEHeader;
+
+typedef struct QEMU_PACKED {
+    DebugFrameCIE cie;
+    DebugFrameFDEHeader fde;
+} DebugFrameHeader;
+
+static void tcg_register_jit_int(void *buf, size_t size,
+                                 const void *debug_frame,
+                                 size_t debug_frame_size)
+    __attribute__((unused));
+
+/* Forward declarations for functions declared and used in tcg-target.c. */
+static int target_parse_constraint(TCGArgConstraint *ct, const char **pct_str);
+static void tcg_out_ld(TCGContext *s, TCGType type, TCGReg ret, TCGReg arg1,
+                       intptr_t arg2);
+static void tcg_out_mov(TCGContext *s, TCGType type, TCGReg ret, TCGReg arg);
+static void tcg_out_movi(TCGContext *s, TCGType type,
+                         TCGReg ret, tcg_target_long arg);
+static void tcg_out_op(TCGContext *s, TCGOpcode opc, const TCGArg *args,
+                       const int *const_args);
+static void tcg_out_st(TCGContext *s, TCGType type, TCGReg arg, TCGReg arg1,
+                       intptr_t arg2);
+static void tcg_out_call(TCGContext *s, tcg_insn_unit *target);
+static int tcg_target_const_match(tcg_target_long val, TCGType type,
+                                  const TCGArgConstraint *arg_ct);
+static void tcg_out_tb_init(TCGContext *s);
+static void tcg_out_tb_finalize(TCGContext *s);
+
+
+TCGOpDef tcg_op_defs[] = {
+#define DEF(s, oargs, iargs, cargs, flags) { #s, oargs, iargs, cargs, iargs + oargs + cargs, flags },
+#include "tcg-opc.h"
+#undef DEF
+};
+const size_t tcg_op_defs_max = ARRAY_SIZE(tcg_op_defs);
+
+static TCGRegSet tcg_target_available_regs[2];
+static TCGRegSet tcg_target_call_clobber_regs;
+
+#if TCG_TARGET_INSN_UNIT_SIZE == 1
+static __attribute__((unused)) inline void tcg_out8(TCGContext *s, uint8_t v)
+{
+    *s->code_ptr++ = v;
+}
+
+static __attribute__((unused)) inline void tcg_patch8(tcg_insn_unit *p,
+                                                      uint8_t v)
+{
+    *p = v;
+}
+#endif
+
+#if TCG_TARGET_INSN_UNIT_SIZE <= 2
+static __attribute__((unused)) inline void tcg_out16(TCGContext *s, uint16_t v)
+{
+    if (TCG_TARGET_INSN_UNIT_SIZE == 2) {
+        *s->code_ptr++ = v;
+    } else {
+        tcg_insn_unit *p = s->code_ptr;
+        memcpy(p, &v, sizeof(v));
+        s->code_ptr = p + (2 / TCG_TARGET_INSN_UNIT_SIZE);
+    }
+}
+
+static __attribute__((unused)) inline void tcg_patch16(tcg_insn_unit *p,
+                                                       uint16_t v)
+{
+    if (TCG_TARGET_INSN_UNIT_SIZE == 2) {
+        *p = v;
+    } else {
+        memcpy(p, &v, sizeof(v));
+    }
+}
+#endif
+
+#if TCG_TARGET_INSN_UNIT_SIZE <= 4
+static __attribute__((unused)) inline void tcg_out32(TCGContext *s, uint32_t v)
+{
+    if (TCG_TARGET_INSN_UNIT_SIZE == 4) {
+        *s->code_ptr++ = v;
+    } else {
+        tcg_insn_unit *p = s->code_ptr;
+        memcpy(p, &v, sizeof(v));
+        s->code_ptr = p + (4 / TCG_TARGET_INSN_UNIT_SIZE);
+    }
+}
+
+static __attribute__((unused)) inline void tcg_patch32(tcg_insn_unit *p,
+                                                       uint32_t v)
+{
+    if (TCG_TARGET_INSN_UNIT_SIZE == 4) {
+        *p = v;
+    } else {
+        memcpy(p, &v, sizeof(v));
+    }
+}
+#endif
+
+#if TCG_TARGET_INSN_UNIT_SIZE <= 8
+static __attribute__((unused)) inline void tcg_out64(TCGContext *s, uint64_t v)
+{
+    if (TCG_TARGET_INSN_UNIT_SIZE == 8) {
+        *s->code_ptr++ = v;
+    } else {
+        tcg_insn_unit *p = s->code_ptr;
+        memcpy(p, &v, sizeof(v));
+        s->code_ptr = p + (8 / TCG_TARGET_INSN_UNIT_SIZE);
+    }
+}
+
+static __attribute__((unused)) inline void tcg_patch64(tcg_insn_unit *p,
+                                                       uint64_t v)
+{
+    if (TCG_TARGET_INSN_UNIT_SIZE == 8) {
+        *p = v;
+    } else {
+        memcpy(p, &v, sizeof(v));
+    }
+}
+#endif
+
+/* label relocation processing */
+
+static void tcg_out_reloc(TCGContext *s, tcg_insn_unit *code_ptr, int type,
+                          TCGLabel *l, intptr_t addend)
+{
+    TCGRelocation *r;
+
+    if (l->has_value) {
+        /* FIXME: This may break relocations on RISC targets that
+           modify instruction fields in place.  The caller may not have 
+           written the initial value.  */
+        patch_reloc(code_ptr, type, l->u.value, addend);
+    } else {
+        /* add a new relocation entry */
+        r = tcg_malloc(sizeof(TCGRelocation));
+        r->type = type;
+        r->ptr = code_ptr;
+        r->addend = addend;
+        r->next = l->u.first_reloc;
+        l->u.first_reloc = r;
+    }
+}
+
+static void tcg_out_label(TCGContext *s, TCGLabel *l, tcg_insn_unit *ptr)
+{
+    intptr_t value = (intptr_t)ptr;
+    TCGRelocation *r;
+
+    assert(!l->has_value);
+
+    for (r = l->u.first_reloc; r != NULL; r = r->next) {
+        patch_reloc(r->ptr, r->type, value, r->addend);
+    }
+
+    l->has_value = 1;
+    l->u.value_ptr = ptr;
+}
+
+TCGLabel *gen_new_label(void)
+{
+    TCGContext *s = &tcg_ctx;
+    TCGLabel *l = tcg_malloc(sizeof(TCGLabel));
+
+    *l = (TCGLabel){
+        .id = s->nb_labels++
+    };
+
+    return l;
+}
+
+#include "tcg-target.c"
+
+/* pool based memory allocation */
+void *tcg_malloc_internal(TCGContext *s, int size)
+{
+    TCGPool *p;
+    int pool_size;
+    
+    if (size > TCG_POOL_CHUNK_SIZE) {
+        /* big malloc: insert a new pool (XXX: could optimize) */
+        p = g_malloc(sizeof(TCGPool) + size);
+        p->size = size;
+        p->next = s->pool_first_large;
+        s->pool_first_large = p;
+        return p->data;
+    } else {
+        p = s->pool_current;
+        if (!p) {
+            p = s->pool_first;
+            if (!p)
+                goto new_pool;
+        } else {
+            if (!p->next) {
+            new_pool:
+                pool_size = TCG_POOL_CHUNK_SIZE;
+                p = g_malloc(sizeof(TCGPool) + pool_size);
+                p->size = pool_size;
+                p->next = NULL;
+                if (s->pool_current) 
+                    s->pool_current->next = p;
+                else
+                    s->pool_first = p;
+            } else {
+                p = p->next;
+            }
+        }
+    }
+    s->pool_current = p;
+    s->pool_cur = p->data + size;
+    s->pool_end = p->data + p->size;
+    return p->data;
+}
+
+void tcg_pool_reset(TCGContext *s)
+{
+    TCGPool *p, *t;
+    for (p = s->pool_first_large; p; p = t) {
+        t = p->next;
+        g_free(p);
+    }
+    s->pool_first_large = NULL;
+    s->pool_cur = s->pool_end = NULL;
+    s->pool_current = NULL;
+}
+
+typedef struct TCGHelperInfo {
+    void *func;
+    const char *name;
+    unsigned flags;
+    unsigned sizemask;
+} TCGHelperInfo;
+
+#include "exec/helper-proto.h"
+
+static const TCGHelperInfo all_helpers[] = {
+#include "exec/helper-tcg.h"
+};
+
+void tcg_context_init(TCGContext *s)
+{
+    int op, total_args, n, i;
+    TCGOpDef *def;
+    TCGArgConstraint *args_ct;
+    int *sorted_args;
+    GHashTable *helper_table;
+
+    memset(s, 0, sizeof(*s));
+    s->nb_globals = 0;
+    
+    /* Count total number of arguments and allocate the corresponding
+       space */
+    total_args = 0;
+    for(op = 0; op < NB_OPS; op++) {
+        def = &tcg_op_defs[op];
+        n = def->nb_iargs + def->nb_oargs;
+        total_args += n;
+    }
+
+    args_ct = g_malloc(sizeof(TCGArgConstraint) * total_args);
+    sorted_args = g_malloc(sizeof(int) * total_args);
+
+    for(op = 0; op < NB_OPS; op++) {
+        def = &tcg_op_defs[op];
+        def->args_ct = args_ct;
+        def->sorted_args = sorted_args;
+        n = def->nb_iargs + def->nb_oargs;
+        sorted_args += n;
+        args_ct += n;
+    }
+
+    /* Register helpers.  */
+    /* Use g_direct_hash/equal for direct pointer comparisons on func.  */
+    s->helpers = helper_table = g_hash_table_new(NULL, NULL);
+
+    for (i = 0; i < ARRAY_SIZE(all_helpers); ++i) {
+        g_hash_table_insert(helper_table, (gpointer)all_helpers[i].func,
+                            (gpointer)&all_helpers[i]);
+    }
+
+    tcg_target_init(s);
+}
+
+void tcg_prologue_init(TCGContext *s)
+{
+    /* init global prologue and epilogue */
+    s->code_buf = s->code_gen_prologue;
+    s->code_ptr = s->code_buf;
+    tcg_target_qemu_prologue(s);
+    flush_icache_range((uintptr_t)s->code_buf, (uintptr_t)s->code_ptr);
+
+#ifdef DEBUG_DISAS
+    if (qemu_loglevel_mask(CPU_LOG_TB_OUT_ASM)) {
+        size_t size = tcg_current_code_size(s);
+        qemu_log("PROLOGUE: [size=%zu]\n", size);
+        log_disas(s->code_buf, size);
+        qemu_log("\n");
+        qemu_log_flush();
+    }
+#endif
+}
+
+void tcg_set_frame(TCGContext *s, int reg, intptr_t start, intptr_t size)
+{
+    s->frame_start = start;
+    s->frame_end = start + size;
+    s->frame_reg = reg;
+}
+
+void tcg_func_start(TCGContext *s)
+{
+    tcg_pool_reset(s);
+    s->nb_temps = s->nb_globals;
+
+    /* No temps have been previously allocated for size or locality.  */
+    memset(s->free_temps, 0, sizeof(s->free_temps));
+
+    s->nb_labels = 0;
+    s->current_frame_offset = s->frame_start;
+
+#ifdef CONFIG_DEBUG_TCG
+    s->goto_tb_issue_mask = 0;
+#endif
+
+    s->gen_first_op_idx = 0;
+    s->gen_last_op_idx = -1;
+    s->gen_next_op_idx = 0;
+    s->gen_next_parm_idx = 0;
+
+    s->be = tcg_malloc(sizeof(TCGBackendData));
+}
+
+static inline void tcg_temp_alloc(TCGContext *s, int n)
+{
+    if (n > TCG_MAX_TEMPS)
+        tcg_abort();
+}
+
+static inline int tcg_global_reg_new_internal(TCGType type, int reg,
+                                              const char *name)
+{
+    TCGContext *s = &tcg_ctx;
+    TCGTemp *ts;
+    int idx;
+
+#if TCG_TARGET_REG_BITS == 32
+    if (type != TCG_TYPE_I32)
+        tcg_abort();
+#endif
+    if (tcg_regset_test_reg(s->reserved_regs, reg))
+        tcg_abort();
+    idx = s->nb_globals;
+    tcg_temp_alloc(s, s->nb_globals + 1);
+    ts = &s->temps[s->nb_globals];
+    ts->base_type = type;
+    ts->type = type;
+    ts->fixed_reg = 1;
+    ts->reg = reg;
+    ts->name = name;
+    s->nb_globals++;
+    tcg_regset_set_reg(s->reserved_regs, reg);
+    return idx;
+}
+
+TCGv_i32 tcg_global_reg_new_i32(int reg, const char *name)
+{
+    int idx;
+
+    idx = tcg_global_reg_new_internal(TCG_TYPE_I32, reg, name);
+    return MAKE_TCGV_I32(idx);
+}
+
+TCGv_i64 tcg_global_reg_new_i64(int reg, const char *name)
+{
+    int idx;
+
+    idx = tcg_global_reg_new_internal(TCG_TYPE_I64, reg, name);
+    return MAKE_TCGV_I64(idx);
+}
+
+static inline int tcg_global_mem_new_internal(TCGType type, int reg,
+                                              intptr_t offset,
+                                              const char *name)
+{
+    TCGContext *s = &tcg_ctx;
+    TCGTemp *ts;
+    int idx;
+
+    idx = s->nb_globals;
+#if TCG_TARGET_REG_BITS == 32
+    if (type == TCG_TYPE_I64) {
+        char buf[64];
+        tcg_temp_alloc(s, s->nb_globals + 2);
+        ts = &s->temps[s->nb_globals];
+        ts->base_type = type;
+        ts->type = TCG_TYPE_I32;
+        ts->fixed_reg = 0;
+        ts->mem_allocated = 1;
+        ts->mem_reg = reg;
+#ifdef HOST_WORDS_BIGENDIAN
+        ts->mem_offset = offset + 4;
+#else
+        ts->mem_offset = offset;
+#endif
+        pstrcpy(buf, sizeof(buf), name);
+        pstrcat(buf, sizeof(buf), "_0");
+        ts->name = strdup(buf);
+        ts++;
+
+        ts->base_type = type;
+        ts->type = TCG_TYPE_I32;
+        ts->fixed_reg = 0;
+        ts->mem_allocated = 1;
+        ts->mem_reg = reg;
+#ifdef HOST_WORDS_BIGENDIAN
+        ts->mem_offset = offset;
+#else
+        ts->mem_offset = offset + 4;
+#endif
+        pstrcpy(buf, sizeof(buf), name);
+        pstrcat(buf, sizeof(buf), "_1");
+        ts->name = strdup(buf);
+
+        s->nb_globals += 2;
+    } else
+#endif
+    {
+        tcg_temp_alloc(s, s->nb_globals + 1);
+        ts = &s->temps[s->nb_globals];
+        ts->base_type = type;
+        ts->type = type;
+        ts->fixed_reg = 0;
+        ts->mem_allocated = 1;
+        ts->mem_reg = reg;
+        ts->mem_offset = offset;
+        ts->name = name;
+        s->nb_globals++;
+    }
+    return idx;
+}
+
+TCGv_i32 tcg_global_mem_new_i32(int reg, intptr_t offset, const char *name)
+{
+    int idx = tcg_global_mem_new_internal(TCG_TYPE_I32, reg, offset, name);
+    return MAKE_TCGV_I32(idx);
+}
+
+TCGv_i64 tcg_global_mem_new_i64(int reg, intptr_t offset, const char *name)
+{
+    int idx = tcg_global_mem_new_internal(TCG_TYPE_I64, reg, offset, name);
+    return MAKE_TCGV_I64(idx);
+}
+
+static inline int tcg_temp_new_internal(TCGType type, int temp_local)
+{
+    TCGContext *s = &tcg_ctx;
+    TCGTemp *ts;
+    int idx, k;
+
+    k = type + (temp_local ? TCG_TYPE_COUNT : 0);
+    idx = find_first_bit(s->free_temps[k].l, TCG_MAX_TEMPS);
+    if (idx < TCG_MAX_TEMPS) {
+        /* There is already an available temp with the right type.  */
+        clear_bit(idx, s->free_temps[k].l);
+
+        ts = &s->temps[idx];
+        ts->temp_allocated = 1;
+        assert(ts->base_type == type);
+        assert(ts->temp_local == temp_local);
+    } else {
+        idx = s->nb_temps;
+#if TCG_TARGET_REG_BITS == 32
+        if (type == TCG_TYPE_I64) {
+            tcg_temp_alloc(s, s->nb_temps + 2);
+            ts = &s->temps[s->nb_temps];
+            ts->base_type = type;
+            ts->type = TCG_TYPE_I32;
+            ts->temp_allocated = 1;
+            ts->temp_local = temp_local;
+            ts->name = NULL;
+            ts++;
+            ts->base_type = type;
+            ts->type = TCG_TYPE_I32;
+            ts->temp_allocated = 1;
+            ts->temp_local = temp_local;
+            ts->name = NULL;
+            s->nb_temps += 2;
+        } else
+#endif
+        {
+            tcg_temp_alloc(s, s->nb_temps + 1);
+            ts = &s->temps[s->nb_temps];
+            ts->base_type = type;
+            ts->type = type;
+            ts->temp_allocated = 1;
+            ts->temp_local = temp_local;
+            ts->name = NULL;
+            s->nb_temps++;
+        }
+    }
+
+#if defined(CONFIG_DEBUG_TCG)
+    s->temps_in_use++;
+#endif
+    return idx;
+}
+
+TCGv_i32 tcg_temp_new_internal_i32(int temp_local)
+{
+    int idx;
+
+    idx = tcg_temp_new_internal(TCG_TYPE_I32, temp_local);
+    return MAKE_TCGV_I32(idx);
+}
+
+TCGv_i64 tcg_temp_new_internal_i64(int temp_local)
+{
+    int idx;
+
+    idx = tcg_temp_new_internal(TCG_TYPE_I64, temp_local);
+    return MAKE_TCGV_I64(idx);
+}
+
+static void tcg_temp_free_internal(int idx)
+{
+    TCGContext *s = &tcg_ctx;
+    TCGTemp *ts;
+    int k;
+
+#if defined(CONFIG_DEBUG_TCG)
+    s->temps_in_use--;
+    if (s->temps_in_use < 0) {
+        fprintf(stderr, "More temporaries freed than allocated!\n");
+    }
+#endif
+
+    assert(idx >= s->nb_globals && idx < s->nb_temps);
+    ts = &s->temps[idx];
+    assert(ts->temp_allocated != 0);
+    ts->temp_allocated = 0;
+
+    k = ts->base_type + (ts->temp_local ? TCG_TYPE_COUNT : 0);
+    set_bit(idx, s->free_temps[k].l);
+}
+
+void tcg_temp_free_i32(TCGv_i32 arg)
+{
+    tcg_temp_free_internal(GET_TCGV_I32(arg));
+}
+
+void tcg_temp_free_i64(TCGv_i64 arg)
+{
+    tcg_temp_free_internal(GET_TCGV_I64(arg));
+}
+
+TCGv_i32 tcg_const_i32(int32_t val)
+{
+    TCGv_i32 t0;
+    t0 = tcg_temp_new_i32();
+    tcg_gen_movi_i32(t0, val);
+    return t0;
+}
+
+TCGv_i64 tcg_const_i64(int64_t val)
+{
+    TCGv_i64 t0;
+    t0 = tcg_temp_new_i64();
+    tcg_gen_movi_i64(t0, val);
+    return t0;
+}
+
+TCGv_i32 tcg_const_local_i32(int32_t val)
+{
+    TCGv_i32 t0;
+    t0 = tcg_temp_local_new_i32();
+    tcg_gen_movi_i32(t0, val);
+    return t0;
+}
+
+TCGv_i64 tcg_const_local_i64(int64_t val)
+{
+    TCGv_i64 t0;
+    t0 = tcg_temp_local_new_i64();
+    tcg_gen_movi_i64(t0, val);
+    return t0;
+}
+
+#if defined(CONFIG_DEBUG_TCG)
+void tcg_clear_temp_count(void)
+{
+    TCGContext *s = &tcg_ctx;
+    s->temps_in_use = 0;
+}
+
+int tcg_check_temp_count(void)
+{
+    TCGContext *s = &tcg_ctx;
+    if (s->temps_in_use) {
+        /* Clear the count so that we don't give another
+         * warning immediately next time around.
+         */
+        s->temps_in_use = 0;
+        return 1;
+    }
+    return 0;
+}
+#endif
+
+/* Note: we convert the 64 bit args to 32 bit and do some alignment
+   and endian swap. Maybe it would be better to do the alignment
+   and endian swap in tcg_reg_alloc_call(). */
+void tcg_gen_callN(TCGContext *s, void *func, TCGArg ret,
+                   int nargs, TCGArg *args)
+{
+    int i, real_args, nb_rets, pi, pi_first;
+    unsigned sizemask, flags;
+    TCGHelperInfo *info;
+
+    info = g_hash_table_lookup(s->helpers, (gpointer)func);
+    flags = info->flags;
+    sizemask = info->sizemask;
+
+#if defined(__sparc__) && !defined(__arch64__) \
+    && !defined(CONFIG_TCG_INTERPRETER)
+    /* We have 64-bit values in one register, but need to pass as two
+       separate parameters.  Split them.  */
+    int orig_sizemask = sizemask;
+    int orig_nargs = nargs;
+    TCGv_i64 retl, reth;
+
+    TCGV_UNUSED_I64(retl);
+    TCGV_UNUSED_I64(reth);
+    if (sizemask != 0) {
+        TCGArg *split_args = __builtin_alloca(sizeof(TCGArg) * nargs * 2);
+        for (i = real_args = 0; i < nargs; ++i) {
+            int is_64bit = sizemask & (1 << (i+1)*2);
+            if (is_64bit) {
+                TCGv_i64 orig = MAKE_TCGV_I64(args[i]);
+                TCGv_i32 h = tcg_temp_new_i32();
+                TCGv_i32 l = tcg_temp_new_i32();
+                tcg_gen_extr_i64_i32(l, h, orig);
+                split_args[real_args++] = GET_TCGV_I32(h);
+                split_args[real_args++] = GET_TCGV_I32(l);
+            } else {
+                split_args[real_args++] = args[i];
+            }
+        }
+        nargs = real_args;
+        args = split_args;
+        sizemask = 0;
+    }
+#elif defined(TCG_TARGET_EXTEND_ARGS) && TCG_TARGET_REG_BITS == 64
+    for (i = 0; i < nargs; ++i) {
+        int is_64bit = sizemask & (1 << (i+1)*2);
+        int is_signed = sizemask & (2 << (i+1)*2);
+        if (!is_64bit) {
+            TCGv_i64 temp = tcg_temp_new_i64();
+            TCGv_i64 orig = MAKE_TCGV_I64(args[i]);
+            if (is_signed) {
+                tcg_gen_ext32s_i64(temp, orig);
+            } else {
+                tcg_gen_ext32u_i64(temp, orig);
+            }
+            args[i] = GET_TCGV_I64(temp);
+        }
+    }
+#endif /* TCG_TARGET_EXTEND_ARGS */
+
+    pi_first = pi = s->gen_next_parm_idx;
+    if (ret != TCG_CALL_DUMMY_ARG) {
+#if defined(__sparc__) && !defined(__arch64__) \
+    && !defined(CONFIG_TCG_INTERPRETER)
+        if (orig_sizemask & 1) {
+            /* The 32-bit ABI is going to return the 64-bit value in
+               the %o0/%o1 register pair.  Prepare for this by using
+               two return temporaries, and reassemble below.  */
+            retl = tcg_temp_new_i64();
+            reth = tcg_temp_new_i64();
+            s->gen_opparam_buf[pi++] = GET_TCGV_I64(reth);
+            s->gen_opparam_buf[pi++] = GET_TCGV_I64(retl);
+            nb_rets = 2;
+        } else {
+            s->gen_opparam_buf[pi++] = ret;
+            nb_rets = 1;
+        }
+#else
+        if (TCG_TARGET_REG_BITS < 64 && (sizemask & 1)) {
+#ifdef HOST_WORDS_BIGENDIAN
+            s->gen_opparam_buf[pi++] = ret + 1;
+            s->gen_opparam_buf[pi++] = ret;
+#else
+            s->gen_opparam_buf[pi++] = ret;
+            s->gen_opparam_buf[pi++] = ret + 1;
+#endif
+            nb_rets = 2;
+        } else {
+            s->gen_opparam_buf[pi++] = ret;
+            nb_rets = 1;
+        }
+#endif
+    } else {
+        nb_rets = 0;
+    }
+    real_args = 0;
+    for (i = 0; i < nargs; i++) {
+        int is_64bit = sizemask & (1 << (i+1)*2);
+        if (TCG_TARGET_REG_BITS < 64 && is_64bit) {
+#ifdef TCG_TARGET_CALL_ALIGN_ARGS
+            /* some targets want aligned 64 bit args */
+            if (real_args & 1) {
+                s->gen_opparam_buf[pi++] = TCG_CALL_DUMMY_ARG;
+                real_args++;
+            }
+#endif
+	    /* If stack grows up, then we will be placing successive
+	       arguments at lower addresses, which means we need to
+	       reverse the order compared to how we would normally
+	       treat either big or little-endian.  For those arguments
+	       that will wind up in registers, this still works for
+	       HPPA (the only current STACK_GROWSUP target) since the
+	       argument registers are *also* allocated in decreasing
+	       order.  If another such target is added, this logic may
+	       have to get more complicated to differentiate between
+	       stack arguments and register arguments.  */
+#if defined(HOST_WORDS_BIGENDIAN) != defined(TCG_TARGET_STACK_GROWSUP)
+            s->gen_opparam_buf[pi++] = args[i] + 1;
+            s->gen_opparam_buf[pi++] = args[i];
+#else
+            s->gen_opparam_buf[pi++] = args[i];
+            s->gen_opparam_buf[pi++] = args[i] + 1;
+#endif
+            real_args += 2;
+            continue;
+        }
+
+        s->gen_opparam_buf[pi++] = args[i];
+        real_args++;
+    }
+    s->gen_opparam_buf[pi++] = (uintptr_t)func;
+    s->gen_opparam_buf[pi++] = flags;
+
+    i = s->gen_next_op_idx;
+    tcg_debug_assert(i < OPC_BUF_SIZE);
+    tcg_debug_assert(pi <= OPPARAM_BUF_SIZE);
+
+    /* Set links for sequential allocation during translation.  */
+    s->gen_op_buf[i] = (TCGOp){
+        .opc = INDEX_op_call,
+        .callo = nb_rets,
+        .calli = real_args,
+        .args = pi_first,
+        .prev = i - 1,
+        .next = i + 1
+    };
+
+    /* Make sure the calli field didn't overflow.  */
+    tcg_debug_assert(s->gen_op_buf[i].calli == real_args);
+
+    s->gen_last_op_idx = i;
+    s->gen_next_op_idx = i + 1;
+    s->gen_next_parm_idx = pi;
+
+#if defined(__sparc__) && !defined(__arch64__) \
+    && !defined(CONFIG_TCG_INTERPRETER)
+    /* Free all of the parts we allocated above.  */
+    for (i = real_args = 0; i < orig_nargs; ++i) {
+        int is_64bit = orig_sizemask & (1 << (i+1)*2);
+        if (is_64bit) {
+            TCGv_i32 h = MAKE_TCGV_I32(args[real_args++]);
+            TCGv_i32 l = MAKE_TCGV_I32(args[real_args++]);
+            tcg_temp_free_i32(h);
+            tcg_temp_free_i32(l);
+        } else {
+            real_args++;
+        }
+    }
+    if (orig_sizemask & 1) {
+        /* The 32-bit ABI returned two 32-bit pieces.  Re-assemble them.
+           Note that describing these as TCGv_i64 eliminates an unnecessary
+           zero-extension that tcg_gen_concat_i32_i64 would create.  */
+        tcg_gen_concat32_i64(MAKE_TCGV_I64(ret), retl, reth);
+        tcg_temp_free_i64(retl);
+        tcg_temp_free_i64(reth);
+    }
+#elif defined(TCG_TARGET_EXTEND_ARGS) && TCG_TARGET_REG_BITS == 64
+    for (i = 0; i < nargs; ++i) {
+        int is_64bit = sizemask & (1 << (i+1)*2);
+        if (!is_64bit) {
+            TCGv_i64 temp = MAKE_TCGV_I64(args[i]);
+            tcg_temp_free_i64(temp);
+        }
+    }
+#endif /* TCG_TARGET_EXTEND_ARGS */
+}
+
+static void tcg_reg_alloc_start(TCGContext *s)
+{
+    int i;
+    TCGTemp *ts;
+    for(i = 0; i < s->nb_globals; i++) {
+        ts = &s->temps[i];
+        if (ts->fixed_reg) {
+            ts->val_type = TEMP_VAL_REG;
+        } else {
+            ts->val_type = TEMP_VAL_MEM;
+        }
+    }
+    for(i = s->nb_globals; i < s->nb_temps; i++) {
+        ts = &s->temps[i];
+        if (ts->temp_local) {
+            ts->val_type = TEMP_VAL_MEM;
+        } else {
+            ts->val_type = TEMP_VAL_DEAD;
+        }
+        ts->mem_allocated = 0;
+        ts->fixed_reg = 0;
+    }
+    for(i = 0; i < TCG_TARGET_NB_REGS; i++) {
+        s->reg_to_temp[i] = -1;
+    }
+}
+
+static char *tcg_get_arg_str_idx(TCGContext *s, char *buf, int buf_size,
+                                 int idx)
+{
+    TCGTemp *ts;
+
+    assert(idx >= 0 && idx < s->nb_temps);
+    ts = &s->temps[idx];
+    if (idx < s->nb_globals) {
+        pstrcpy(buf, buf_size, ts->name);
+    } else {
+        if (ts->temp_local) 
+            snprintf(buf, buf_size, "loc%d", idx - s->nb_globals);
+        else
+            snprintf(buf, buf_size, "tmp%d", idx - s->nb_globals);
+    }
+    return buf;
+}
+
+char *tcg_get_arg_str_i32(TCGContext *s, char *buf, int buf_size, TCGv_i32 arg)
+{
+    return tcg_get_arg_str_idx(s, buf, buf_size, GET_TCGV_I32(arg));
+}
+
+char *tcg_get_arg_str_i64(TCGContext *s, char *buf, int buf_size, TCGv_i64 arg)
+{
+    return tcg_get_arg_str_idx(s, buf, buf_size, GET_TCGV_I64(arg));
+}
+
+/* Find helper name.  */
+static inline const char *tcg_find_helper(TCGContext *s, uintptr_t val)
+{
+    const char *ret = NULL;
+    if (s->helpers) {
+        TCGHelperInfo *info = g_hash_table_lookup(s->helpers, (gpointer)val);
+        if (info) {
+            ret = info->name;
+        }
+    }
+    return ret;
+}
+
+static const char * const cond_name[] =
+{
+    [TCG_COND_NEVER] = "never",
+    [TCG_COND_ALWAYS] = "always",
+    [TCG_COND_EQ] = "eq",
+    [TCG_COND_NE] = "ne",
+    [TCG_COND_LT] = "lt",
+    [TCG_COND_GE] = "ge",
+    [TCG_COND_LE] = "le",
+    [TCG_COND_GT] = "gt",
+    [TCG_COND_LTU] = "ltu",
+    [TCG_COND_GEU] = "geu",
+    [TCG_COND_LEU] = "leu",
+    [TCG_COND_GTU] = "gtu"
+};
+
+static const char * const ldst_name[] =
+{
+    [MO_UB]   = "ub",
+    [MO_SB]   = "sb",
+    [MO_LEUW] = "leuw",
+    [MO_LESW] = "lesw",
+    [MO_LEUL] = "leul",
+    [MO_LESL] = "lesl",
+    [MO_LEQ]  = "leq",
+    [MO_BEUW] = "beuw",
+    [MO_BESW] = "besw",
+    [MO_BEUL] = "beul",
+    [MO_BESL] = "besl",
+    [MO_BEQ]  = "beq",
+};
+
+void tcg_dump_ops(TCGContext *s)
+{
+    char buf[128];
+    TCGOp *op;
+    int oi;
+
+    for (oi = s->gen_first_op_idx; oi >= 0; oi = op->next) {
+        int i, k, nb_oargs, nb_iargs, nb_cargs;
+        const TCGOpDef *def;
+        const TCGArg *args;
+        TCGOpcode c;
+
+        op = &s->gen_op_buf[oi];
+        c = op->opc;
+        def = &tcg_op_defs[c];
+        args = &s->gen_opparam_buf[op->args];
+
+        if (c == INDEX_op_debug_insn_start) {
+            uint64_t pc;
+#if TARGET_LONG_BITS > TCG_TARGET_REG_BITS
+            pc = ((uint64_t)args[1] << 32) | args[0];
+#else
+            pc = args[0];
+#endif
+            if (oi != s->gen_first_op_idx) {
+                qemu_log("\n");
+            }
+            qemu_log(" ---- 0x%" PRIx64, pc);
+        } else if (c == INDEX_op_call) {
+            /* variable number of arguments */
+            nb_oargs = op->callo;
+            nb_iargs = op->calli;
+            nb_cargs = def->nb_cargs;
+
+            /* function name, flags, out args */
+            qemu_log(" %s %s,$0x%" TCG_PRIlx ",$%d", def->name,
+                     tcg_find_helper(s, args[nb_oargs + nb_iargs]),
+                     args[nb_oargs + nb_iargs + 1], nb_oargs);
+            for (i = 0; i < nb_oargs; i++) {
+                qemu_log(",%s", tcg_get_arg_str_idx(s, buf, sizeof(buf),
+                                                   args[i]));
+            }
+            for (i = 0; i < nb_iargs; i++) {
+                TCGArg arg = args[nb_oargs + i];
+                const char *t = "<dummy>";
+                if (arg != TCG_CALL_DUMMY_ARG) {
+                    t = tcg_get_arg_str_idx(s, buf, sizeof(buf), arg);
+                }
+                qemu_log(",%s", t);
+            }
+        } else {
+            qemu_log(" %s ", def->name);
+
+            nb_oargs = def->nb_oargs;
+            nb_iargs = def->nb_iargs;
+            nb_cargs = def->nb_cargs;
+
+            k = 0;
+            for (i = 0; i < nb_oargs; i++) {
+                if (k != 0) {
+                    qemu_log(",");
+                }
+                qemu_log("%s", tcg_get_arg_str_idx(s, buf, sizeof(buf),
+                                                   args[k++]));
+            }
+            for (i = 0; i < nb_iargs; i++) {
+                if (k != 0) {
+                    qemu_log(",");
+                }
+                qemu_log("%s", tcg_get_arg_str_idx(s, buf, sizeof(buf),
+                                                   args[k++]));
+            }
+            switch (c) {
+            case INDEX_op_brcond_i32:
+            case INDEX_op_setcond_i32:
+            case INDEX_op_movcond_i32:
+            case INDEX_op_brcond2_i32:
+            case INDEX_op_setcond2_i32:
+            case INDEX_op_brcond_i64:
+            case INDEX_op_setcond_i64:
+            case INDEX_op_movcond_i64:
+                if (args[k] < ARRAY_SIZE(cond_name) && cond_name[args[k]]) {
+                    qemu_log(",%s", cond_name[args[k++]]);
+                } else {
+                    qemu_log(",$0x%" TCG_PRIlx, args[k++]);
+                }
+                i = 1;
+                break;
+            case INDEX_op_qemu_ld_i32:
+            case INDEX_op_qemu_st_i32:
+            case INDEX_op_qemu_ld_i64:
+            case INDEX_op_qemu_st_i64:
+                {
+                    TCGMemOpIdx oi = args[k++];
+                    TCGMemOp op = get_memop(oi);
+                    unsigned ix = get_mmuidx(oi);
+
+                    if (op & ~(MO_AMASK | MO_BSWAP | MO_SSIZE)) {
+                        qemu_log(",$0x%x,%u", op, ix);
+                    } else {
+                        const char *s_al = "", *s_op;
+                        if (op & MO_AMASK) {
+                            if ((op & MO_AMASK) == MO_ALIGN) {
+                                s_al = "al+";
+                            } else {
+                                s_al = "un+";
+                            }
+                        }
+                        s_op = ldst_name[op & (MO_BSWAP | MO_SSIZE)];
+                        qemu_log(",%s%s,%u", s_al, s_op, ix);
+                    }
+                    i = 1;
+                }
+                break;
+            default:
+                i = 0;
+                break;
+            }
+            switch (c) {
+            case INDEX_op_set_label:
+            case INDEX_op_br:
+            case INDEX_op_brcond_i32:
+            case INDEX_op_brcond_i64:
+            case INDEX_op_brcond2_i32:
+                qemu_log("%s$L%d", k ? "," : "", arg_label(args[k])->id);
+                i++, k++;
+                break;
+            default:
+                break;
+            }
+            for (; i < nb_cargs; i++, k++) {
+                qemu_log("%s$0x%" TCG_PRIlx, k ? "," : "", args[k]);
+            }
+        }
+        qemu_log("\n");
+    }
+}
+
+/* we give more priority to constraints with less registers */
+static int get_constraint_priority(const TCGOpDef *def, int k)
+{
+    const TCGArgConstraint *arg_ct;
+
+    int i, n;
+    arg_ct = &def->args_ct[k];
+    if (arg_ct->ct & TCG_CT_ALIAS) {
+        /* an alias is equivalent to a single register */
+        n = 1;
+    } else {
+        if (!(arg_ct->ct & TCG_CT_REG))
+            return 0;
+        n = 0;
+        for(i = 0; i < TCG_TARGET_NB_REGS; i++) {
+            if (tcg_regset_test_reg(arg_ct->u.regs, i))
+                n++;
+        }
+    }
+    return TCG_TARGET_NB_REGS - n + 1;
+}
+
+/* sort from highest priority to lowest */
+static void sort_constraints(TCGOpDef *def, int start, int n)
+{
+    int i, j, p1, p2, tmp;
+
+    for(i = 0; i < n; i++)
+        def->sorted_args[start + i] = start + i;
+    if (n <= 1)
+        return;
+    for(i = 0; i < n - 1; i++) {
+        for(j = i + 1; j < n; j++) {
+            p1 = get_constraint_priority(def, def->sorted_args[start + i]);
+            p2 = get_constraint_priority(def, def->sorted_args[start + j]);
+            if (p1 < p2) {
+                tmp = def->sorted_args[start + i];
+                def->sorted_args[start + i] = def->sorted_args[start + j];
+                def->sorted_args[start + j] = tmp;
+            }
+        }
+    }
+}
+
+void tcg_add_target_add_op_defs(const TCGTargetOpDef *tdefs)
+{
+    TCGOpcode op;
+    TCGOpDef *def;
+    const char *ct_str;
+    int i, nb_args;
+
+    for(;;) {
+        if (tdefs->op == (TCGOpcode)-1)
+            break;
+        op = tdefs->op;
+        assert((unsigned)op < NB_OPS);
+        def = &tcg_op_defs[op];
+#if defined(CONFIG_DEBUG_TCG)
+        /* Duplicate entry in op definitions? */
+        assert(!def->used);
+        def->used = 1;
+#endif
+        nb_args = def->nb_iargs + def->nb_oargs;
+        for(i = 0; i < nb_args; i++) {
+            ct_str = tdefs->args_ct_str[i];
+            /* Incomplete TCGTargetOpDef entry? */
+            assert(ct_str != NULL);
+            tcg_regset_clear(def->args_ct[i].u.regs);
+            def->args_ct[i].ct = 0;
+            if (ct_str[0] >= '0' && ct_str[0] <= '9') {
+                int oarg;
+                oarg = ct_str[0] - '0';
+                assert(oarg < def->nb_oargs);
+                assert(def->args_ct[oarg].ct & TCG_CT_REG);
+                /* TCG_CT_ALIAS is for the output arguments. The input
+                   argument is tagged with TCG_CT_IALIAS. */
+                def->args_ct[i] = def->args_ct[oarg];
+                def->args_ct[oarg].ct = TCG_CT_ALIAS;
+                def->args_ct[oarg].alias_index = i;
+                def->args_ct[i].ct |= TCG_CT_IALIAS;
+                def->args_ct[i].alias_index = oarg;
+            } else {
+                for(;;) {
+                    if (*ct_str == '\0')
+                        break;
+                    switch(*ct_str) {
+                    case 'i':
+                        def->args_ct[i].ct |= TCG_CT_CONST;
+                        ct_str++;
+                        break;
+                    default:
+                        if (target_parse_constraint(&def->args_ct[i], &ct_str) < 0) {
+                            fprintf(stderr, "Invalid constraint '%s' for arg %d of operation '%s'\n",
+                                    ct_str, i, def->name);
+                            exit(1);
+                        }
+                    }
+                }
+            }
+        }
+
+        /* TCGTargetOpDef entry with too much information? */
+        assert(i == TCG_MAX_OP_ARGS || tdefs->args_ct_str[i] == NULL);
+
+        /* sort the constraints (XXX: this is just an heuristic) */
+        sort_constraints(def, 0, def->nb_oargs);
+        sort_constraints(def, def->nb_oargs, def->nb_iargs);
+
+#if 0
+        {
+            int i;
+
+            printf("%s: sorted=", def->name);
+            for(i = 0; i < def->nb_oargs + def->nb_iargs; i++)
+                printf(" %d", def->sorted_args[i]);
+            printf("\n");
+        }
+#endif
+        tdefs++;
+    }
+
+#if defined(CONFIG_DEBUG_TCG)
+    i = 0;
+    for (op = 0; op < ARRAY_SIZE(tcg_op_defs); op++) {
+        const TCGOpDef *def = &tcg_op_defs[op];
+        if (def->flags & TCG_OPF_NOT_PRESENT) {
+            /* Wrong entry in op definitions? */
+            if (def->used) {
+                fprintf(stderr, "Invalid op definition for %s\n", def->name);
+                i = 1;
+            }
+        } else {
+            /* Missing entry in op definitions? */
+            if (!def->used) {
+                fprintf(stderr, "Missing op definition for %s\n", def->name);
+                i = 1;
+            }
+        }
+    }
+    if (i == 1) {
+        tcg_abort();
+    }
+#endif
+}
+
+void tcg_op_remove(TCGContext *s, TCGOp *op)
+{
+    int next = op->next;
+    int prev = op->prev;
+
+    if (next >= 0) {
+        s->gen_op_buf[next].prev = prev;
+    } else {
+        s->gen_last_op_idx = prev;
+    }
+    if (prev >= 0) {
+        s->gen_op_buf[prev].next = next;
+    } else {
+        s->gen_first_op_idx = next;
+    }
+
+    memset(op, -1, sizeof(*op));
+
+#ifdef CONFIG_PROFILER
+    s->del_op_count++;
+#endif
+}
+
+#ifdef USE_LIVENESS_ANALYSIS
+/* liveness analysis: end of function: all temps are dead, and globals
+   should be in memory. */
+static inline void tcg_la_func_end(TCGContext *s, uint8_t *dead_temps,
+                                   uint8_t *mem_temps)
+{
+    memset(dead_temps, 1, s->nb_temps);
+    memset(mem_temps, 1, s->nb_globals);
+    memset(mem_temps + s->nb_globals, 0, s->nb_temps - s->nb_globals);
+}
+
+/* liveness analysis: end of basic block: all temps are dead, globals
+   and local temps should be in memory. */
+static inline void tcg_la_bb_end(TCGContext *s, uint8_t *dead_temps,
+                                 uint8_t *mem_temps)
+{
+    int i;
+
+    memset(dead_temps, 1, s->nb_temps);
+    memset(mem_temps, 1, s->nb_globals);
+    for(i = s->nb_globals; i < s->nb_temps; i++) {
+        mem_temps[i] = s->temps[i].temp_local;
+    }
+}
+
+/* Liveness analysis : update the opc_dead_args array to tell if a
+   given input arguments is dead. Instructions updating dead
+   temporaries are removed. */
+static void tcg_liveness_analysis(TCGContext *s)
+{
+    uint8_t *dead_temps, *mem_temps;
+    int oi, oi_prev, nb_ops;
+
+    nb_ops = s->gen_next_op_idx;
+    s->op_dead_args = tcg_malloc(nb_ops * sizeof(uint16_t));
+    s->op_sync_args = tcg_malloc(nb_ops * sizeof(uint8_t));
+    
+    dead_temps = tcg_malloc(s->nb_temps);
+    mem_temps = tcg_malloc(s->nb_temps);
+    tcg_la_func_end(s, dead_temps, mem_temps);
+
+    for (oi = s->gen_last_op_idx; oi >= 0; oi = oi_prev) {
+        int i, nb_iargs, nb_oargs;
+        TCGOpcode opc_new, opc_new2;
+        bool have_opc_new2;
+        uint16_t dead_args;
+        uint8_t sync_args;
+        TCGArg arg;
+
+        TCGOp * const op = &s->gen_op_buf[oi];
+        TCGArg * const args = &s->gen_opparam_buf[op->args];
+        TCGOpcode opc = op->opc;
+        const TCGOpDef *def = &tcg_op_defs[opc];
+
+        oi_prev = op->prev;
+
+        switch (opc) {
+        case INDEX_op_call:
+            {
+                int call_flags;
+
+                nb_oargs = op->callo;
+                nb_iargs = op->calli;
+                call_flags = args[nb_oargs + nb_iargs + 1];
+
+                /* pure functions can be removed if their result is unused */
+                if (call_flags & TCG_CALL_NO_SIDE_EFFECTS) {
+                    for (i = 0; i < nb_oargs; i++) {
+                        arg = args[i];
+                        if (!dead_temps[arg] || mem_temps[arg]) {
+                            goto do_not_remove_call;
+                        }
+                    }
+                    goto do_remove;
+                } else {
+                do_not_remove_call:
+
+                    /* output args are dead */
+                    dead_args = 0;
+                    sync_args = 0;
+                    for (i = 0; i < nb_oargs; i++) {
+                        arg = args[i];
+                        if (dead_temps[arg]) {
+                            dead_args |= (1 << i);
+                        }
+                        if (mem_temps[arg]) {
+                            sync_args |= (1 << i);
+                        }
+                        dead_temps[arg] = 1;
+                        mem_temps[arg] = 0;
+                    }
+
+                    if (!(call_flags & TCG_CALL_NO_READ_GLOBALS)) {
+                        /* globals should be synced to memory */
+                        memset(mem_temps, 1, s->nb_globals);
+                    }
+                    if (!(call_flags & (TCG_CALL_NO_WRITE_GLOBALS |
+                                        TCG_CALL_NO_READ_GLOBALS))) {
+                        /* globals should go back to memory */
+                        memset(dead_temps, 1, s->nb_globals);
+                    }
+
+                    /* record arguments that die in this helper */
+                    for (i = nb_oargs; i < nb_iargs + nb_oargs; i++) {
+                        arg = args[i];
+                        if (arg != TCG_CALL_DUMMY_ARG) {
+                            if (dead_temps[arg]) {
+                                dead_args |= (1 << i);
+                            }
+                        }
+                    }
+                    /* input arguments are live for preceeding opcodes */
+                    for (i = nb_oargs; i < nb_oargs + nb_iargs; i++) {
+                        arg = args[i];
+                        dead_temps[arg] = 0;
+                    }
+                    s->op_dead_args[oi] = dead_args;
+                    s->op_sync_args[oi] = sync_args;
+                }
+            }
+            break;
+        case INDEX_op_debug_insn_start:
+            break;
+        case INDEX_op_discard:
+            /* mark the temporary as dead */
+            dead_temps[args[0]] = 1;
+            mem_temps[args[0]] = 0;
+            break;
+
+        case INDEX_op_add2_i32:
+            opc_new = INDEX_op_add_i32;
+            goto do_addsub2;
+        case INDEX_op_sub2_i32:
+            opc_new = INDEX_op_sub_i32;
+            goto do_addsub2;
+        case INDEX_op_add2_i64:
+            opc_new = INDEX_op_add_i64;
+            goto do_addsub2;
+        case INDEX_op_sub2_i64:
+            opc_new = INDEX_op_sub_i64;
+        do_addsub2:
+            nb_iargs = 4;
+            nb_oargs = 2;
+            /* Test if the high part of the operation is dead, but not
+               the low part.  The result can be optimized to a simple
+               add or sub.  This happens often for x86_64 guest when the
+               cpu mode is set to 32 bit.  */
+            if (dead_temps[args[1]] && !mem_temps[args[1]]) {
+                if (dead_temps[args[0]] && !mem_temps[args[0]]) {
+                    goto do_remove;
+                }
+                /* Replace the opcode and adjust the args in place,
+                   leaving 3 unused args at the end.  */
+                op->opc = opc = opc_new;
+                args[1] = args[2];
+                args[2] = args[4];
+                /* Fall through and mark the single-word operation live.  */
+                nb_iargs = 2;
+                nb_oargs = 1;
+            }
+            goto do_not_remove;
+
+        case INDEX_op_mulu2_i32:
+            opc_new = INDEX_op_mul_i32;
+            opc_new2 = INDEX_op_muluh_i32;
+            have_opc_new2 = TCG_TARGET_HAS_muluh_i32;
+            goto do_mul2;
+        case INDEX_op_muls2_i32:
+            opc_new = INDEX_op_mul_i32;
+            opc_new2 = INDEX_op_mulsh_i32;
+            have_opc_new2 = TCG_TARGET_HAS_mulsh_i32;
+            goto do_mul2;
+        case INDEX_op_mulu2_i64:
+            opc_new = INDEX_op_mul_i64;
+            opc_new2 = INDEX_op_muluh_i64;
+            have_opc_new2 = TCG_TARGET_HAS_muluh_i64;
+            goto do_mul2;
+        case INDEX_op_muls2_i64:
+            opc_new = INDEX_op_mul_i64;
+            opc_new2 = INDEX_op_mulsh_i64;
+            have_opc_new2 = TCG_TARGET_HAS_mulsh_i64;
+            goto do_mul2;
+        do_mul2:
+            nb_iargs = 2;
+            nb_oargs = 2;
+            if (dead_temps[args[1]] && !mem_temps[args[1]]) {
+                if (dead_temps[args[0]] && !mem_temps[args[0]]) {
+                    /* Both parts of the operation are dead.  */
+                    goto do_remove;
+                }
+                /* The high part of the operation is dead; generate the low. */
+                op->opc = opc = opc_new;
+                args[1] = args[2];
+                args[2] = args[3];
+            } else if (have_opc_new2 && dead_temps[args[0]]
+                       && !mem_temps[args[0]]) {
+                /* The low part of the operation is dead; generate the high. */
+                op->opc = opc = opc_new2;
+                args[0] = args[1];
+                args[1] = args[2];
+                args[2] = args[3];
+            } else {
+                goto do_not_remove;
+            }
+            /* Mark the single-word operation live.  */
+            nb_oargs = 1;
+            goto do_not_remove;
+
+        default:
+            /* XXX: optimize by hardcoding common cases (e.g. triadic ops) */
+            nb_iargs = def->nb_iargs;
+            nb_oargs = def->nb_oargs;
+
+            /* Test if the operation can be removed because all
+               its outputs are dead. We assume that nb_oargs == 0
+               implies side effects */
+            if (!(def->flags & TCG_OPF_SIDE_EFFECTS) && nb_oargs != 0) {
+                for (i = 0; i < nb_oargs; i++) {
+                    arg = args[i];
+                    if (!dead_temps[arg] || mem_temps[arg]) {
+                        goto do_not_remove;
+                    }
+                }
+            do_remove:
+                tcg_op_remove(s, op);
+            } else {
+            do_not_remove:
+                /* output args are dead */
+                dead_args = 0;
+                sync_args = 0;
+                for (i = 0; i < nb_oargs; i++) {
+                    arg = args[i];
+                    if (dead_temps[arg]) {
+                        dead_args |= (1 << i);
+                    }
+                    if (mem_temps[arg]) {
+                        sync_args |= (1 << i);
+                    }
+                    dead_temps[arg] = 1;
+                    mem_temps[arg] = 0;
+                }
+
+                /* if end of basic block, update */
+                if (def->flags & TCG_OPF_BB_END) {
+                    tcg_la_bb_end(s, dead_temps, mem_temps);
+                } else if (def->flags & TCG_OPF_SIDE_EFFECTS) {
+                    /* globals should be synced to memory */
+                    memset(mem_temps, 1, s->nb_globals);
+                }
+
+                /* record arguments that die in this opcode */
+                for (i = nb_oargs; i < nb_oargs + nb_iargs; i++) {
+                    arg = args[i];
+                    if (dead_temps[arg]) {
+                        dead_args |= (1 << i);
+                    }
+                }
+                /* input arguments are live for preceeding opcodes */
+                for (i = nb_oargs; i < nb_oargs + nb_iargs; i++) {
+                    arg = args[i];
+                    dead_temps[arg] = 0;
+                }
+                s->op_dead_args[oi] = dead_args;
+                s->op_sync_args[oi] = sync_args;
+            }
+            break;
+        }
+    }
+}
+#else
+/* dummy liveness analysis */
+static void tcg_liveness_analysis(TCGContext *s)
+{
+    int nb_ops;
+    nb_ops = s->gen_opc_ptr - s->gen_opc_buf;
+
+    s->op_dead_args = tcg_malloc(nb_ops * sizeof(uint16_t));
+    memset(s->op_dead_args, 0, nb_ops * sizeof(uint16_t));
+    s->op_sync_args = tcg_malloc(nb_ops * sizeof(uint8_t));
+    memset(s->op_sync_args, 0, nb_ops * sizeof(uint8_t));
+}
+#endif
+
+#ifndef NDEBUG
+static void dump_regs(TCGContext *s)
+{
+    TCGTemp *ts;
+    int i;
+    char buf[64];
+
+    for(i = 0; i < s->nb_temps; i++) {
+        ts = &s->temps[i];
+        printf("  %10s: ", tcg_get_arg_str_idx(s, buf, sizeof(buf), i));
+        switch(ts->val_type) {
+        case TEMP_VAL_REG:
+            printf("%s", tcg_target_reg_names[ts->reg]);
+            break;
+        case TEMP_VAL_MEM:
+            printf("%d(%s)", (int)ts->mem_offset, tcg_target_reg_names[ts->mem_reg]);
+            break;
+        case TEMP_VAL_CONST:
+            printf("$0x%" TCG_PRIlx, ts->val);
+            break;
+        case TEMP_VAL_DEAD:
+            printf("D");
+            break;
+        default:
+            printf("???");
+            break;
+        }
+        printf("\n");
+    }
+
+    for(i = 0; i < TCG_TARGET_NB_REGS; i++) {
+        if (s->reg_to_temp[i] >= 0) {
+            printf("%s: %s\n", 
+                   tcg_target_reg_names[i], 
+                   tcg_get_arg_str_idx(s, buf, sizeof(buf), s->reg_to_temp[i]));
+        }
+    }
+}
+
+static void check_regs(TCGContext *s)
+{
+    int reg, k;
+    TCGTemp *ts;
+    char buf[64];
+
+    for(reg = 0; reg < TCG_TARGET_NB_REGS; reg++) {
+        k = s->reg_to_temp[reg];
+        if (k >= 0) {
+            ts = &s->temps[k];
+            if (ts->val_type != TEMP_VAL_REG ||
+                ts->reg != reg) {
+                printf("Inconsistency for register %s:\n", 
+                       tcg_target_reg_names[reg]);
+                goto fail;
+            }
+        }
+    }
+    for(k = 0; k < s->nb_temps; k++) {
+        ts = &s->temps[k];
+        if (ts->val_type == TEMP_VAL_REG &&
+            !ts->fixed_reg &&
+            s->reg_to_temp[ts->reg] != k) {
+                printf("Inconsistency for temp %s:\n", 
+                       tcg_get_arg_str_idx(s, buf, sizeof(buf), k));
+        fail:
+                printf("reg state:\n");
+                dump_regs(s);
+                tcg_abort();
+        }
+    }
+}
+#endif
+
+static void temp_allocate_frame(TCGContext *s, int temp)
+{
+    TCGTemp *ts;
+    ts = &s->temps[temp];
+#if !(defined(__sparc__) && TCG_TARGET_REG_BITS == 64)
+    /* Sparc64 stack is accessed with offset of 2047 */
+    s->current_frame_offset = (s->current_frame_offset +
+                               (tcg_target_long)sizeof(tcg_target_long) - 1) &
+        ~(sizeof(tcg_target_long) - 1);
+#endif
+    if (s->current_frame_offset + (tcg_target_long)sizeof(tcg_target_long) >
+        s->frame_end) {
+        tcg_abort();
+    }
+    ts->mem_offset = s->current_frame_offset;
+    ts->mem_reg = s->frame_reg;
+    ts->mem_allocated = 1;
+    s->current_frame_offset += sizeof(tcg_target_long);
+}
+
+/* sync register 'reg' by saving it to the corresponding temporary */
+static inline void tcg_reg_sync(TCGContext *s, int reg)
+{
+    TCGTemp *ts;
+    int temp;
+
+    temp = s->reg_to_temp[reg];
+    ts = &s->temps[temp];
+    assert(ts->val_type == TEMP_VAL_REG);
+    if (!ts->mem_coherent && !ts->fixed_reg) {
+        if (!ts->mem_allocated) {
+            temp_allocate_frame(s, temp);
+        }
+        tcg_out_st(s, ts->type, reg, ts->mem_reg, ts->mem_offset);
+    }
+    ts->mem_coherent = 1;
+}
+
+/* free register 'reg' by spilling the corresponding temporary if necessary */
+static void tcg_reg_free(TCGContext *s, int reg)
+{
+    int temp;
+
+    temp = s->reg_to_temp[reg];
+    if (temp != -1) {
+        tcg_reg_sync(s, reg);
+        s->temps[temp].val_type = TEMP_VAL_MEM;
+        s->reg_to_temp[reg] = -1;
+    }
+}
+
+/* Allocate a register belonging to reg1 & ~reg2 */
+static int tcg_reg_alloc(TCGContext *s, TCGRegSet reg1, TCGRegSet reg2)
+{
+    int i, reg;
+    TCGRegSet reg_ct;
+
+    tcg_regset_andnot(reg_ct, reg1, reg2);
+
+    /* first try free registers */
+    for(i = 0; i < ARRAY_SIZE(tcg_target_reg_alloc_order); i++) {
+        reg = tcg_target_reg_alloc_order[i];
+        if (tcg_regset_test_reg(reg_ct, reg) && s->reg_to_temp[reg] == -1)
+            return reg;
+    }
+
+    /* XXX: do better spill choice */
+    for(i = 0; i < ARRAY_SIZE(tcg_target_reg_alloc_order); i++) {
+        reg = tcg_target_reg_alloc_order[i];
+        if (tcg_regset_test_reg(reg_ct, reg)) {
+            tcg_reg_free(s, reg);
+            return reg;
+        }
+    }
+
+    tcg_abort();
+}
+
+/* mark a temporary as dead. */
+static inline void temp_dead(TCGContext *s, int temp)
+{
+    TCGTemp *ts;
+
+    ts = &s->temps[temp];
+    if (!ts->fixed_reg) {
+        if (ts->val_type == TEMP_VAL_REG) {
+            s->reg_to_temp[ts->reg] = -1;
+        }
+        if (temp < s->nb_globals || ts->temp_local) {
+            ts->val_type = TEMP_VAL_MEM;
+        } else {
+            ts->val_type = TEMP_VAL_DEAD;
+        }
+    }
+}
+
+/* sync a temporary to memory. 'allocated_regs' is used in case a
+   temporary registers needs to be allocated to store a constant. */
+static inline void temp_sync(TCGContext *s, int temp, TCGRegSet allocated_regs)
+{
+    TCGTemp *ts;
+
+    ts = &s->temps[temp];
+    if (!ts->fixed_reg) {
+        switch(ts->val_type) {
+        case TEMP_VAL_CONST:
+            ts->reg = tcg_reg_alloc(s, tcg_target_available_regs[ts->type],
+                                    allocated_regs);
+            ts->val_type = TEMP_VAL_REG;
+            s->reg_to_temp[ts->reg] = temp;
+            ts->mem_coherent = 0;
+            tcg_out_movi(s, ts->type, ts->reg, ts->val);
+            /* fallthrough*/
+        case TEMP_VAL_REG:
+            tcg_reg_sync(s, ts->reg);
+            break;
+        case TEMP_VAL_DEAD:
+        case TEMP_VAL_MEM:
+            break;
+        default:
+            tcg_abort();
+        }
+    }
+}
+
+/* save a temporary to memory. 'allocated_regs' is used in case a
+   temporary registers needs to be allocated to store a constant. */
+static inline void temp_save(TCGContext *s, int temp, TCGRegSet allocated_regs)
+{
+#ifdef USE_LIVENESS_ANALYSIS
+    /* The liveness analysis already ensures that globals are back
+       in memory. Keep an assert for safety. */
+    assert(s->temps[temp].val_type == TEMP_VAL_MEM || s->temps[temp].fixed_reg);
+#else
+    temp_sync(s, temp, allocated_regs);
+    temp_dead(s, temp);
+#endif
+}
+
+/* save globals to their canonical location and assume they can be
+   modified be the following code. 'allocated_regs' is used in case a
+   temporary registers needs to be allocated to store a constant. */
+static void save_globals(TCGContext *s, TCGRegSet allocated_regs)
+{
+    int i;
+
+    for(i = 0; i < s->nb_globals; i++) {
+        temp_save(s, i, allocated_regs);
+    }
+}
+
+/* sync globals to their canonical location and assume they can be
+   read by the following code. 'allocated_regs' is used in case a
+   temporary registers needs to be allocated to store a constant. */
+static void sync_globals(TCGContext *s, TCGRegSet allocated_regs)
+{
+    int i;
+
+    for (i = 0; i < s->nb_globals; i++) {
+#ifdef USE_LIVENESS_ANALYSIS
+        assert(s->temps[i].val_type != TEMP_VAL_REG || s->temps[i].fixed_reg ||
+               s->temps[i].mem_coherent);
+#else
+        temp_sync(s, i, allocated_regs);
+#endif
+    }
+}
+
+/* at the end of a basic block, we assume all temporaries are dead and
+   all globals are stored at their canonical location. */
+static void tcg_reg_alloc_bb_end(TCGContext *s, TCGRegSet allocated_regs)
+{
+    TCGTemp *ts;
+    int i;
+
+    for(i = s->nb_globals; i < s->nb_temps; i++) {
+        ts = &s->temps[i];
+        if (ts->temp_local) {
+            temp_save(s, i, allocated_regs);
+        } else {
+#ifdef USE_LIVENESS_ANALYSIS
+            /* The liveness analysis already ensures that temps are dead.
+               Keep an assert for safety. */
+            assert(ts->val_type == TEMP_VAL_DEAD);
+#else
+            temp_dead(s, i);
+#endif
+        }
+    }
+
+    save_globals(s, allocated_regs);
+}
+
+#define IS_DEAD_ARG(n) ((dead_args >> (n)) & 1)
+#define NEED_SYNC_ARG(n) ((sync_args >> (n)) & 1)
+
+static void tcg_reg_alloc_movi(TCGContext *s, const TCGArg *args,
+                               uint16_t dead_args, uint8_t sync_args)
+{
+    TCGTemp *ots;
+    tcg_target_ulong val;
+
+    ots = &s->temps[args[0]];
+    val = args[1];
+
+    if (ots->fixed_reg) {
+        /* for fixed registers, we do not do any constant
+           propagation */
+        tcg_out_movi(s, ots->type, ots->reg, val);
+    } else {
+        /* The movi is not explicitly generated here */
+        if (ots->val_type == TEMP_VAL_REG)
+            s->reg_to_temp[ots->reg] = -1;
+        ots->val_type = TEMP_VAL_CONST;
+        ots->val = val;
+    }
+    if (NEED_SYNC_ARG(0)) {
+        temp_sync(s, args[0], s->reserved_regs);
+    }
+    if (IS_DEAD_ARG(0)) {
+        temp_dead(s, args[0]);
+    }
+}
+
+static void tcg_reg_alloc_mov(TCGContext *s, const TCGOpDef *def,
+                              const TCGArg *args, uint16_t dead_args,
+                              uint8_t sync_args)
+{
+    TCGRegSet allocated_regs;
+    TCGTemp *ts, *ots;
+    TCGType otype, itype;
+
+    tcg_regset_set(allocated_regs, s->reserved_regs);
+    ots = &s->temps[args[0]];
+    ts = &s->temps[args[1]];
+
+    /* Note that otype != itype for no-op truncation.  */
+    otype = ots->type;
+    itype = ts->type;
+
+    /* If the source value is not in a register, and we're going to be
+       forced to have it in a register in order to perform the copy,
+       then copy the SOURCE value into its own register first.  That way
+       we don't have to reload SOURCE the next time it is used. */
+    if (((NEED_SYNC_ARG(0) || ots->fixed_reg) && ts->val_type != TEMP_VAL_REG)
+        || ts->val_type == TEMP_VAL_MEM) {
+        ts->reg = tcg_reg_alloc(s, tcg_target_available_regs[itype],
+                                allocated_regs);
+        if (ts->val_type == TEMP_VAL_MEM) {
+            tcg_out_ld(s, itype, ts->reg, ts->mem_reg, ts->mem_offset);
+            ts->mem_coherent = 1;
+        } else if (ts->val_type == TEMP_VAL_CONST) {
+            tcg_out_movi(s, itype, ts->reg, ts->val);
+            ts->mem_coherent = 0;
+        }
+        s->reg_to_temp[ts->reg] = args[1];
+        ts->val_type = TEMP_VAL_REG;
+    }
+
+    if (IS_DEAD_ARG(0) && !ots->fixed_reg) {
+        /* mov to a non-saved dead register makes no sense (even with
+           liveness analysis disabled). */
+        assert(NEED_SYNC_ARG(0));
+        /* The code above should have moved the temp to a register. */
+        assert(ts->val_type == TEMP_VAL_REG);
+        if (!ots->mem_allocated) {
+            temp_allocate_frame(s, args[0]);
+        }
+        tcg_out_st(s, otype, ts->reg, ots->mem_reg, ots->mem_offset);
+        if (IS_DEAD_ARG(1)) {
+            temp_dead(s, args[1]);
+        }
+        temp_dead(s, args[0]);
+    } else if (ts->val_type == TEMP_VAL_CONST) {
+        /* propagate constant */
+        if (ots->val_type == TEMP_VAL_REG) {
+            s->reg_to_temp[ots->reg] = -1;
+        }
+        ots->val_type = TEMP_VAL_CONST;
+        ots->val = ts->val;
+        if (IS_DEAD_ARG(1)) {
+            temp_dead(s, args[1]);
+        }
+    } else {
+        /* The code in the first if block should have moved the
+           temp to a register. */
+        assert(ts->val_type == TEMP_VAL_REG);
+        if (IS_DEAD_ARG(1) && !ts->fixed_reg && !ots->fixed_reg) {
+            /* the mov can be suppressed */
+            if (ots->val_type == TEMP_VAL_REG) {
+                s->reg_to_temp[ots->reg] = -1;
+            }
+            ots->reg = ts->reg;
+            temp_dead(s, args[1]);
+        } else {
+            if (ots->val_type != TEMP_VAL_REG) {
+                /* When allocating a new register, make sure to not spill the
+                   input one. */
+                tcg_regset_set_reg(allocated_regs, ts->reg);
+                ots->reg = tcg_reg_alloc(s, tcg_target_available_regs[otype],
+                                         allocated_regs);
+            }
+            tcg_out_mov(s, otype, ots->reg, ts->reg);
+        }
+        ots->val_type = TEMP_VAL_REG;
+        ots->mem_coherent = 0;
+        s->reg_to_temp[ots->reg] = args[0];
+        if (NEED_SYNC_ARG(0)) {
+            tcg_reg_sync(s, ots->reg);
+        }
+    }
+}
+
+static void tcg_reg_alloc_op(TCGContext *s, 
+                             const TCGOpDef *def, TCGOpcode opc,
+                             const TCGArg *args, uint16_t dead_args,
+                             uint8_t sync_args)
+{
+    TCGRegSet allocated_regs;
+    int i, k, nb_iargs, nb_oargs, reg;
+    TCGArg arg;
+    const TCGArgConstraint *arg_ct;
+    TCGTemp *ts;
+    TCGArg new_args[TCG_MAX_OP_ARGS];
+    int const_args[TCG_MAX_OP_ARGS];
+
+    nb_oargs = def->nb_oargs;
+    nb_iargs = def->nb_iargs;
+
+    /* copy constants */
+    memcpy(new_args + nb_oargs + nb_iargs, 
+           args + nb_oargs + nb_iargs, 
+           sizeof(TCGArg) * def->nb_cargs);
+
+    /* satisfy input constraints */ 
+    tcg_regset_set(allocated_regs, s->reserved_regs);
+    for(k = 0; k < nb_iargs; k++) {
+        i = def->sorted_args[nb_oargs + k];
+        arg = args[i];
+        arg_ct = &def->args_ct[i];
+        ts = &s->temps[arg];
+        if (ts->val_type == TEMP_VAL_MEM) {
+            reg = tcg_reg_alloc(s, arg_ct->u.regs, allocated_regs);
+            tcg_out_ld(s, ts->type, reg, ts->mem_reg, ts->mem_offset);
+            ts->val_type = TEMP_VAL_REG;
+            ts->reg = reg;
+            ts->mem_coherent = 1;
+            s->reg_to_temp[reg] = arg;
+        } else if (ts->val_type == TEMP_VAL_CONST) {
+            if (tcg_target_const_match(ts->val, ts->type, arg_ct)) {
+                /* constant is OK for instruction */
+                const_args[i] = 1;
+                new_args[i] = ts->val;
+                goto iarg_end;
+            } else {
+                /* need to move to a register */
+                reg = tcg_reg_alloc(s, arg_ct->u.regs, allocated_regs);
+                tcg_out_movi(s, ts->type, reg, ts->val);
+                ts->val_type = TEMP_VAL_REG;
+                ts->reg = reg;
+                ts->mem_coherent = 0;
+                s->reg_to_temp[reg] = arg;
+            }
+        }
+        assert(ts->val_type == TEMP_VAL_REG);
+        if (arg_ct->ct & TCG_CT_IALIAS) {
+            if (ts->fixed_reg) {
+                /* if fixed register, we must allocate a new register
+                   if the alias is not the same register */
+                if (arg != args[arg_ct->alias_index])
+                    goto allocate_in_reg;
+            } else {
+                /* if the input is aliased to an output and if it is
+                   not dead after the instruction, we must allocate
+                   a new register and move it */
+                if (!IS_DEAD_ARG(i)) {
+                    goto allocate_in_reg;
+                }
+                /* check if the current register has already been allocated
+                   for another input aliased to an output */
+                int k2, i2;
+                for (k2 = 0 ; k2 < k ; k2++) {
+                    i2 = def->sorted_args[nb_oargs + k2];
+                    if ((def->args_ct[i2].ct & TCG_CT_IALIAS) &&
+                        (new_args[i2] == ts->reg)) {
+                        goto allocate_in_reg;
+                    }
+                }
+            }
+        }
+        reg = ts->reg;
+        if (tcg_regset_test_reg(arg_ct->u.regs, reg)) {
+            /* nothing to do : the constraint is satisfied */
+        } else {
+        allocate_in_reg:
+            /* allocate a new register matching the constraint 
+               and move the temporary register into it */
+            reg = tcg_reg_alloc(s, arg_ct->u.regs, allocated_regs);
+            tcg_out_mov(s, ts->type, reg, ts->reg);
+        }
+        new_args[i] = reg;
+        const_args[i] = 0;
+        tcg_regset_set_reg(allocated_regs, reg);
+    iarg_end: ;
+    }
+    
+    /* mark dead temporaries and free the associated registers */
+    for (i = nb_oargs; i < nb_oargs + nb_iargs; i++) {
+        if (IS_DEAD_ARG(i)) {
+            temp_dead(s, args[i]);
+        }
+    }
+
+    if (def->flags & TCG_OPF_BB_END) {
+        tcg_reg_alloc_bb_end(s, allocated_regs);
+    } else {
+        if (def->flags & TCG_OPF_CALL_CLOBBER) {
+            /* XXX: permit generic clobber register list ? */ 
+            for(reg = 0; reg < TCG_TARGET_NB_REGS; reg++) {
+                if (tcg_regset_test_reg(tcg_target_call_clobber_regs, reg)) {
+                    tcg_reg_free(s, reg);
+                }
+            }
+        }
+        if (def->flags & TCG_OPF_SIDE_EFFECTS) {
+            /* sync globals if the op has side effects and might trigger
+               an exception. */
+            sync_globals(s, allocated_regs);
+        }
+        
+        /* satisfy the output constraints */
+        tcg_regset_set(allocated_regs, s->reserved_regs);
+        for(k = 0; k < nb_oargs; k++) {
+            i = def->sorted_args[k];
+            arg = args[i];
+            arg_ct = &def->args_ct[i];
+            ts = &s->temps[arg];
+            if (arg_ct->ct & TCG_CT_ALIAS) {
+                reg = new_args[arg_ct->alias_index];
+            } else {
+                /* if fixed register, we try to use it */
+                reg = ts->reg;
+                if (ts->fixed_reg &&
+                    tcg_regset_test_reg(arg_ct->u.regs, reg)) {
+                    goto oarg_end;
+                }
+                reg = tcg_reg_alloc(s, arg_ct->u.regs, allocated_regs);
+            }
+            tcg_regset_set_reg(allocated_regs, reg);
+            /* if a fixed register is used, then a move will be done afterwards */
+            if (!ts->fixed_reg) {
+                if (ts->val_type == TEMP_VAL_REG) {
+                    s->reg_to_temp[ts->reg] = -1;
+                }
+                ts->val_type = TEMP_VAL_REG;
+                ts->reg = reg;
+                /* temp value is modified, so the value kept in memory is
+                   potentially not the same */
+                ts->mem_coherent = 0;
+                s->reg_to_temp[reg] = arg;
+            }
+        oarg_end:
+            new_args[i] = reg;
+        }
+    }
+
+    /* emit instruction */
+    tcg_out_op(s, opc, new_args, const_args);
+    
+    /* move the outputs in the correct register if needed */
+    for(i = 0; i < nb_oargs; i++) {
+        ts = &s->temps[args[i]];
+        reg = new_args[i];
+        if (ts->fixed_reg && ts->reg != reg) {
+            tcg_out_mov(s, ts->type, ts->reg, reg);
+        }
+        if (NEED_SYNC_ARG(i)) {
+            tcg_reg_sync(s, reg);
+        }
+        if (IS_DEAD_ARG(i)) {
+            temp_dead(s, args[i]);
+        }
+    }
+}
+
+#ifdef TCG_TARGET_STACK_GROWSUP
+#define STACK_DIR(x) (-(x))
+#else
+#define STACK_DIR(x) (x)
+#endif
+
+static void tcg_reg_alloc_call(TCGContext *s, int nb_oargs, int nb_iargs,
+                               const TCGArg * const args, uint16_t dead_args,
+                               uint8_t sync_args)
+{
+    int flags, nb_regs, i, reg;
+    TCGArg arg;
+    TCGTemp *ts;
+    intptr_t stack_offset;
+    size_t call_stack_size;
+    tcg_insn_unit *func_addr;
+    int allocate_args;
+    TCGRegSet allocated_regs;
+
+    func_addr = (tcg_insn_unit *)(intptr_t)args[nb_oargs + nb_iargs];
+    flags = args[nb_oargs + nb_iargs + 1];
+
+    nb_regs = ARRAY_SIZE(tcg_target_call_iarg_regs);
+    if (nb_regs > nb_iargs) {
+        nb_regs = nb_iargs;
+    }
+
+    /* assign stack slots first */
+    call_stack_size = (nb_iargs - nb_regs) * sizeof(tcg_target_long);
+    call_stack_size = (call_stack_size + TCG_TARGET_STACK_ALIGN - 1) & 
+        ~(TCG_TARGET_STACK_ALIGN - 1);
+    allocate_args = (call_stack_size > TCG_STATIC_CALL_ARGS_SIZE);
+    if (allocate_args) {
+        /* XXX: if more than TCG_STATIC_CALL_ARGS_SIZE is needed,
+           preallocate call stack */
+        tcg_abort();
+    }
+
+    stack_offset = TCG_TARGET_CALL_STACK_OFFSET;
+    for(i = nb_regs; i < nb_iargs; i++) {
+        arg = args[nb_oargs + i];
+#ifdef TCG_TARGET_STACK_GROWSUP
+        stack_offset -= sizeof(tcg_target_long);
+#endif
+        if (arg != TCG_CALL_DUMMY_ARG) {
+            ts = &s->temps[arg];
+            if (ts->val_type == TEMP_VAL_REG) {
+                tcg_out_st(s, ts->type, ts->reg, TCG_REG_CALL_STACK, stack_offset);
+            } else if (ts->val_type == TEMP_VAL_MEM) {
+                reg = tcg_reg_alloc(s, tcg_target_available_regs[ts->type], 
+                                    s->reserved_regs);
+                /* XXX: not correct if reading values from the stack */
+                tcg_out_ld(s, ts->type, reg, ts->mem_reg, ts->mem_offset);
+                tcg_out_st(s, ts->type, reg, TCG_REG_CALL_STACK, stack_offset);
+            } else if (ts->val_type == TEMP_VAL_CONST) {
+                reg = tcg_reg_alloc(s, tcg_target_available_regs[ts->type], 
+                                    s->reserved_regs);
+                /* XXX: sign extend may be needed on some targets */
+                tcg_out_movi(s, ts->type, reg, ts->val);
+                tcg_out_st(s, ts->type, reg, TCG_REG_CALL_STACK, stack_offset);
+            } else {
+                tcg_abort();
+            }
+        }
+#ifndef TCG_TARGET_STACK_GROWSUP
+        stack_offset += sizeof(tcg_target_long);
+#endif
+    }
+    
+    /* assign input registers */
+    tcg_regset_set(allocated_regs, s->reserved_regs);
+    for(i = 0; i < nb_regs; i++) {
+        arg = args[nb_oargs + i];
+        if (arg != TCG_CALL_DUMMY_ARG) {
+            ts = &s->temps[arg];
+            reg = tcg_target_call_iarg_regs[i];
+            tcg_reg_free(s, reg);
+            if (ts->val_type == TEMP_VAL_REG) {
+                if (ts->reg != reg) {
+                    tcg_out_mov(s, ts->type, reg, ts->reg);
+                }
+            } else if (ts->val_type == TEMP_VAL_MEM) {
+                tcg_out_ld(s, ts->type, reg, ts->mem_reg, ts->mem_offset);
+            } else if (ts->val_type == TEMP_VAL_CONST) {
+                /* XXX: sign extend ? */
+                tcg_out_movi(s, ts->type, reg, ts->val);
+            } else {
+                tcg_abort();
+            }
+            tcg_regset_set_reg(allocated_regs, reg);
+        }
+    }
+    
+    /* mark dead temporaries and free the associated registers */
+    for(i = nb_oargs; i < nb_iargs + nb_oargs; i++) {
+        if (IS_DEAD_ARG(i)) {
+            temp_dead(s, args[i]);
+        }
+    }
+    
+    /* clobber call registers */
+    for(reg = 0; reg < TCG_TARGET_NB_REGS; reg++) {
+        if (tcg_regset_test_reg(tcg_target_call_clobber_regs, reg)) {
+            tcg_reg_free(s, reg);
+        }
+    }
+
+    /* Save globals if they might be written by the helper, sync them if
+       they might be read. */
+    if (flags & TCG_CALL_NO_READ_GLOBALS) {
+        /* Nothing to do */
+    } else if (flags & TCG_CALL_NO_WRITE_GLOBALS) {
+        sync_globals(s, allocated_regs);
+    } else {
+        save_globals(s, allocated_regs);
+    }
+
+    tcg_out_call(s, func_addr);
+
+    /* assign output registers and emit moves if needed */
+    for(i = 0; i < nb_oargs; i++) {
+        arg = args[i];
+        ts = &s->temps[arg];
+        reg = tcg_target_call_oarg_regs[i];
+        assert(s->reg_to_temp[reg] == -1);
+
+        if (ts->fixed_reg) {
+            if (ts->reg != reg) {
+                tcg_out_mov(s, ts->type, ts->reg, reg);
+            }
+        } else {
+            if (ts->val_type == TEMP_VAL_REG) {
+                s->reg_to_temp[ts->reg] = -1;
+            }
+            ts->val_type = TEMP_VAL_REG;
+            ts->reg = reg;
+            ts->mem_coherent = 0;
+            s->reg_to_temp[reg] = arg;
+            if (NEED_SYNC_ARG(i)) {
+                tcg_reg_sync(s, reg);
+            }
+            if (IS_DEAD_ARG(i)) {
+                temp_dead(s, args[i]);
+            }
+        }
+    }
+}
+
+#ifdef CONFIG_PROFILER
+
+static int64_t tcg_table_op_count[NB_OPS];
+
+void tcg_dump_op_count(FILE *f, fprintf_function cpu_fprintf)
+{
+    int i;
+
+    for (i = 0; i < NB_OPS; i++) {
+        cpu_fprintf(f, "%s %" PRId64 "\n", tcg_op_defs[i].name,
+                    tcg_table_op_count[i]);
+    }
+}
+#else
+void tcg_dump_op_count(FILE *f, fprintf_function cpu_fprintf)
+{
+    cpu_fprintf(f, "[TCG profiler not compiled]\n");
+}
+#endif
+
+
+static inline int tcg_gen_code_common(TCGContext *s,
+                                      tcg_insn_unit *gen_code_buf,
+                                      long search_pc)
+{
+    int oi, oi_next;
+
+#ifdef DEBUG_DISAS
+    if (unlikely(qemu_loglevel_mask(CPU_LOG_TB_OP))) {
+        qemu_log("OP:\n");
+        tcg_dump_ops(s);
+        qemu_log("\n");
+    }
+#endif
+
+#ifdef CONFIG_PROFILER
+    s->opt_time -= profile_getclock();
+#endif
+
+#ifdef USE_TCG_OPTIMIZATIONS
+    tcg_optimize(s);
+#endif
+
+#ifdef CONFIG_PROFILER
+    s->opt_time += profile_getclock();
+    s->la_time -= profile_getclock();
+#endif
+
+    tcg_liveness_analysis(s);
+
+#ifdef CONFIG_PROFILER
+    s->la_time += profile_getclock();
+#endif
+
+#ifdef DEBUG_DISAS
+    if (unlikely(qemu_loglevel_mask(CPU_LOG_TB_OP_OPT))) {
+        qemu_log("OP after optimization and liveness analysis:\n");
+        tcg_dump_ops(s);
+        qemu_log("\n");
+    }
+#endif
+
+    tcg_reg_alloc_start(s);
+
+    s->code_buf = gen_code_buf;
+    s->code_ptr = gen_code_buf;
+
+    tcg_out_tb_init(s);
+
+    for (oi = s->gen_first_op_idx; oi >= 0; oi = oi_next) {
+        TCGOp * const op = &s->gen_op_buf[oi];
+        TCGArg * const args = &s->gen_opparam_buf[op->args];
+        TCGOpcode opc = op->opc;
+        const TCGOpDef *def = &tcg_op_defs[opc];
+        uint16_t dead_args = s->op_dead_args[oi];
+        uint8_t sync_args = s->op_sync_args[oi];
+
+        oi_next = op->next;
+#ifdef CONFIG_PROFILER
+        tcg_table_op_count[opc]++;
+#endif
+
+        switch (opc) {
+        case INDEX_op_mov_i32:
+        case INDEX_op_mov_i64:
+            tcg_reg_alloc_mov(s, def, args, dead_args, sync_args);
+            break;
+        case INDEX_op_movi_i32:
+        case INDEX_op_movi_i64:
+            tcg_reg_alloc_movi(s, args, dead_args, sync_args);
+            break;
+        case INDEX_op_debug_insn_start:
+            break;
+        case INDEX_op_discard:
+            temp_dead(s, args[0]);
+            break;
+        case INDEX_op_set_label:
+            tcg_reg_alloc_bb_end(s, s->reserved_regs);
+            tcg_out_label(s, arg_label(args[0]), s->code_ptr);
+            break;
+        case INDEX_op_call:
+            tcg_reg_alloc_call(s, op->callo, op->calli, args,
+                               dead_args, sync_args);
+            break;
+        default:
+            /* Sanity check that we've not introduced any unhandled opcodes. */
+            if (def->flags & TCG_OPF_NOT_PRESENT) {
+                tcg_abort();
+            }
+            /* Note: in order to speed up the code, it would be much
+               faster to have specialized register allocator functions for
+               some common argument patterns */
+            tcg_reg_alloc_op(s, def, opc, args, dead_args, sync_args);
+            break;
+        }
+        if (search_pc >= 0 && search_pc < tcg_current_code_size(s)) {
+            return oi;
+        }
+#ifndef NDEBUG
+        check_regs(s);
+#endif
+    }
+
+    /* Generate TB finalization at the end of block */
+    tcg_out_tb_finalize(s);
+    return -1;
+}
+
+int tcg_gen_code(TCGContext *s, tcg_insn_unit *gen_code_buf)
+{
+#ifdef CONFIG_PROFILER
+    {
+        int n;
+
+        n = s->gen_last_op_idx + 1;
+        s->op_count += n;
+        if (n > s->op_count_max) {
+            s->op_count_max = n;
+        }
+
+        n = s->nb_temps;
+        s->temp_count += n;
+        if (n > s->temp_count_max) {
+            s->temp_count_max = n;
+        }
+    }
+#endif
+
+    tcg_gen_code_common(s, gen_code_buf, -1);
+
+    /* flush instruction cache */
+    flush_icache_range((uintptr_t)s->code_buf, (uintptr_t)s->code_ptr);
+
+    return tcg_current_code_size(s);
+}
+
+/* Return the index of the micro operation such as the pc after is <
+   offset bytes from the start of the TB.  The contents of gen_code_buf must
+   not be changed, though writing the same values is ok.
+   Return -1 if not found. */
+int tcg_gen_code_search_pc(TCGContext *s, tcg_insn_unit *gen_code_buf,
+                           long offset)
+{
+    return tcg_gen_code_common(s, gen_code_buf, offset);
+}
+
+#ifdef CONFIG_PROFILER
+void tcg_dump_info(FILE *f, fprintf_function cpu_fprintf)
+{
+    TCGContext *s = &tcg_ctx;
+    int64_t tot;
+
+    tot = s->interm_time + s->code_time;
+    cpu_fprintf(f, "JIT cycles          %" PRId64 " (%0.3f s at 2.4 GHz)\n",
+                tot, tot / 2.4e9);
+    cpu_fprintf(f, "translated TBs      %" PRId64 " (aborted=%" PRId64 " %0.1f%%)\n", 
+                s->tb_count, 
+                s->tb_count1 - s->tb_count,
+                s->tb_count1 ? (double)(s->tb_count1 - s->tb_count) / s->tb_count1 * 100.0 : 0);
+    cpu_fprintf(f, "avg ops/TB          %0.1f max=%d\n", 
+                s->tb_count ? (double)s->op_count / s->tb_count : 0, s->op_count_max);
+    cpu_fprintf(f, "deleted ops/TB      %0.2f\n",
+                s->tb_count ? 
+                (double)s->del_op_count / s->tb_count : 0);
+    cpu_fprintf(f, "avg temps/TB        %0.2f max=%d\n",
+                s->tb_count ? 
+                (double)s->temp_count / s->tb_count : 0,
+                s->temp_count_max);
+    
+    cpu_fprintf(f, "cycles/op           %0.1f\n", 
+                s->op_count ? (double)tot / s->op_count : 0);
+    cpu_fprintf(f, "cycles/in byte      %0.1f\n", 
+                s->code_in_len ? (double)tot / s->code_in_len : 0);
+    cpu_fprintf(f, "cycles/out byte     %0.1f\n", 
+                s->code_out_len ? (double)tot / s->code_out_len : 0);
+    if (tot == 0)
+        tot = 1;
+    cpu_fprintf(f, "  gen_interm time   %0.1f%%\n", 
+                (double)s->interm_time / tot * 100.0);
+    cpu_fprintf(f, "  gen_code time     %0.1f%%\n", 
+                (double)s->code_time / tot * 100.0);
+    cpu_fprintf(f, "optim./code time    %0.1f%%\n",
+                (double)s->opt_time / (s->code_time ? s->code_time : 1)
+                * 100.0);
+    cpu_fprintf(f, "liveness/code time  %0.1f%%\n", 
+                (double)s->la_time / (s->code_time ? s->code_time : 1) * 100.0);
+    cpu_fprintf(f, "cpu_restore count   %" PRId64 "\n",
+                s->restore_count);
+    cpu_fprintf(f, "  avg cycles        %0.1f\n",
+                s->restore_count ? (double)s->restore_time / s->restore_count : 0);
+}
+#else
+void tcg_dump_info(FILE *f, fprintf_function cpu_fprintf)
+{
+    cpu_fprintf(f, "[TCG profiler not compiled]\n");
+}
+#endif
+
+#ifdef ELF_HOST_MACHINE
+/* In order to use this feature, the backend needs to do three things:
+
+   (1) Define ELF_HOST_MACHINE to indicate both what value to
+       put into the ELF image and to indicate support for the feature.
+
+   (2) Define tcg_register_jit.  This should create a buffer containing
+       the contents of a .debug_frame section that describes the post-
+       prologue unwind info for the tcg machine.
+
+   (3) Call tcg_register_jit_int, with the constructed .debug_frame.
+*/
+
+/* Begin GDB interface.  THE FOLLOWING MUST MATCH GDB DOCS.  */
+typedef enum {
+    JIT_NOACTION = 0,
+    JIT_REGISTER_FN,
+    JIT_UNREGISTER_FN
+} jit_actions_t;
+
+struct jit_code_entry {
+    struct jit_code_entry *next_entry;
+    struct jit_code_entry *prev_entry;
+    const void *symfile_addr;
+    uint64_t symfile_size;
+};
+
+struct jit_descriptor {
+    uint32_t version;
+    uint32_t action_flag;
+    struct jit_code_entry *relevant_entry;
+    struct jit_code_entry *first_entry;
+};
+
+void __jit_debug_register_code(void) __attribute__((noinline));
+void __jit_debug_register_code(void)
+{
+    asm("");
+}
+
+/* Must statically initialize the version, because GDB may check
+   the version before we can set it.  */
+struct jit_descriptor __jit_debug_descriptor = { 1, 0, 0, 0 };
+
+/* End GDB interface.  */
+
+static int find_string(const char *strtab, const char *str)
+{
+    const char *p = strtab + 1;
+
+    while (1) {
+        if (strcmp(p, str) == 0) {
+            return p - strtab;
+        }
+        p += strlen(p) + 1;
+    }
+}
+
+static void tcg_register_jit_int(void *buf_ptr, size_t buf_size,
+                                 const void *debug_frame,
+                                 size_t debug_frame_size)
+{
+    struct __attribute__((packed)) DebugInfo {
+        uint32_t  len;
+        uint16_t  version;
+        uint32_t  abbrev;
+        uint8_t   ptr_size;
+        uint8_t   cu_die;
+        uint16_t  cu_lang;
+        uintptr_t cu_low_pc;
+        uintptr_t cu_high_pc;
+        uint8_t   fn_die;
+        char      fn_name[16];
+        uintptr_t fn_low_pc;
+        uintptr_t fn_high_pc;
+        uint8_t   cu_eoc;
+    };
+
+    struct ElfImage {
+        ElfW(Ehdr) ehdr;
+        ElfW(Phdr) phdr;
+        ElfW(Shdr) shdr[7];
+        ElfW(Sym)  sym[2];
+        struct DebugInfo di;
+        uint8_t    da[24];
+        char       str[80];
+    };
+
+    struct ElfImage *img;
+
+    static const struct ElfImage img_template = {
+        .ehdr = {
+            .e_ident[EI_MAG0] = ELFMAG0,
+            .e_ident[EI_MAG1] = ELFMAG1,
+            .e_ident[EI_MAG2] = ELFMAG2,
+            .e_ident[EI_MAG3] = ELFMAG3,
+            .e_ident[EI_CLASS] = ELF_CLASS,
+            .e_ident[EI_DATA] = ELF_DATA,
+            .e_ident[EI_VERSION] = EV_CURRENT,
+            .e_type = ET_EXEC,
+            .e_machine = ELF_HOST_MACHINE,
+            .e_version = EV_CURRENT,
+            .e_phoff = offsetof(struct ElfImage, phdr),
+            .e_shoff = offsetof(struct ElfImage, shdr),
+            .e_ehsize = sizeof(ElfW(Shdr)),
+            .e_phentsize = sizeof(ElfW(Phdr)),
+            .e_phnum = 1,
+            .e_shentsize = sizeof(ElfW(Shdr)),
+            .e_shnum = ARRAY_SIZE(img->shdr),
+            .e_shstrndx = ARRAY_SIZE(img->shdr) - 1,
+#ifdef ELF_HOST_FLAGS
+            .e_flags = ELF_HOST_FLAGS,
+#endif
+#ifdef ELF_OSABI
+            .e_ident[EI_OSABI] = ELF_OSABI,
+#endif
+        },
+        .phdr = {
+            .p_type = PT_LOAD,
+            .p_flags = PF_X,
+        },
+        .shdr = {
+            [0] = { .sh_type = SHT_NULL },
+            /* Trick: The contents of code_gen_buffer are not present in
+               this fake ELF file; that got allocated elsewhere.  Therefore
+               we mark .text as SHT_NOBITS (similar to .bss) so that readers
+               will not look for contents.  We can record any address.  */
+            [1] = { /* .text */
+                .sh_type = SHT_NOBITS,
+                .sh_flags = SHF_EXECINSTR | SHF_ALLOC,
+            },
+            [2] = { /* .debug_info */
+                .sh_type = SHT_PROGBITS,
+                .sh_offset = offsetof(struct ElfImage, di),
+                .sh_size = sizeof(struct DebugInfo),
+            },
+            [3] = { /* .debug_abbrev */
+                .sh_type = SHT_PROGBITS,
+                .sh_offset = offsetof(struct ElfImage, da),
+                .sh_size = sizeof(img->da),
+            },
+            [4] = { /* .debug_frame */
+                .sh_type = SHT_PROGBITS,
+                .sh_offset = sizeof(struct ElfImage),
+            },
+            [5] = { /* .symtab */
+                .sh_type = SHT_SYMTAB,
+                .sh_offset = offsetof(struct ElfImage, sym),
+                .sh_size = sizeof(img->sym),
+                .sh_info = 1,
+                .sh_link = ARRAY_SIZE(img->shdr) - 1,
+                .sh_entsize = sizeof(ElfW(Sym)),
+            },
+            [6] = { /* .strtab */
+                .sh_type = SHT_STRTAB,
+                .sh_offset = offsetof(struct ElfImage, str),
+                .sh_size = sizeof(img->str),
+            }
+        },
+        .sym = {
+            [1] = { /* code_gen_buffer */
+                .st_info = ELF_ST_INFO(STB_GLOBAL, STT_FUNC),
+                .st_shndx = 1,
+            }
+        },
+        .di = {
+            .len = sizeof(struct DebugInfo) - 4,
+            .version = 2,
+            .ptr_size = sizeof(void *),
+            .cu_die = 1,
+            .cu_lang = 0x8001,  /* DW_LANG_Mips_Assembler */
+            .fn_die = 2,
+            .fn_name = "code_gen_buffer"
+        },
+        .da = {
+            1,          /* abbrev number (the cu) */
+            0x11, 1,    /* DW_TAG_compile_unit, has children */
+            0x13, 0x5,  /* DW_AT_language, DW_FORM_data2 */
+            0x11, 0x1,  /* DW_AT_low_pc, DW_FORM_addr */
+            0x12, 0x1,  /* DW_AT_high_pc, DW_FORM_addr */
+            0, 0,       /* end of abbrev */
+            2,          /* abbrev number (the fn) */
+            0x2e, 0,    /* DW_TAG_subprogram, no children */
+            0x3, 0x8,   /* DW_AT_name, DW_FORM_string */
+            0x11, 0x1,  /* DW_AT_low_pc, DW_FORM_addr */
+            0x12, 0x1,  /* DW_AT_high_pc, DW_FORM_addr */
+            0, 0,       /* end of abbrev */
+            0           /* no more abbrev */
+        },
+        .str = "\0" ".text\0" ".debug_info\0" ".debug_abbrev\0"
+               ".debug_frame\0" ".symtab\0" ".strtab\0" "code_gen_buffer",
+    };
+
+    /* We only need a single jit entry; statically allocate it.  */
+    static struct jit_code_entry one_entry;
+
+    uintptr_t buf = (uintptr_t)buf_ptr;
+    size_t img_size = sizeof(struct ElfImage) + debug_frame_size;
+    DebugFrameHeader *dfh;
+
+    img = g_malloc(img_size);
+    *img = img_template;
+
+    img->phdr.p_vaddr = buf;
+    img->phdr.p_paddr = buf;
+    img->phdr.p_memsz = buf_size;
+
+    img->shdr[1].sh_name = find_string(img->str, ".text");
+    img->shdr[1].sh_addr = buf;
+    img->shdr[1].sh_size = buf_size;
+
+    img->shdr[2].sh_name = find_string(img->str, ".debug_info");
+    img->shdr[3].sh_name = find_string(img->str, ".debug_abbrev");
+
+    img->shdr[4].sh_name = find_string(img->str, ".debug_frame");
+    img->shdr[4].sh_size = debug_frame_size;
+
+    img->shdr[5].sh_name = find_string(img->str, ".symtab");
+    img->shdr[6].sh_name = find_string(img->str, ".strtab");
+
+    img->sym[1].st_name = find_string(img->str, "code_gen_buffer");
+    img->sym[1].st_value = buf;
+    img->sym[1].st_size = buf_size;
+
+    img->di.cu_low_pc = buf;
+    img->di.cu_high_pc = buf + buf_size;
+    img->di.fn_low_pc = buf;
+    img->di.fn_high_pc = buf + buf_size;
+
+    dfh = (DebugFrameHeader *)(img + 1);
+    memcpy(dfh, debug_frame, debug_frame_size);
+    dfh->fde.func_start = buf;
+    dfh->fde.func_len = buf_size;
+
+#ifdef DEBUG_JIT
+    /* Enable this block to be able to debug the ELF image file creation.
+       One can use readelf, objdump, or other inspection utilities.  */
+    {
+        FILE *f = fopen("/tmp/qemu.jit", "w+b");
+        if (f) {
+            if (fwrite(img, img_size, 1, f) != img_size) {
+                /* Avoid stupid unused return value warning for fwrite.  */
+            }
+            fclose(f);
+        }
+    }
+#endif
+
+    one_entry.symfile_addr = img;
+    one_entry.symfile_size = img_size;
+
+    __jit_debug_descriptor.action_flag = JIT_REGISTER_FN;
+    __jit_debug_descriptor.relevant_entry = &one_entry;
+    __jit_debug_descriptor.first_entry = &one_entry;
+    __jit_debug_register_code();
+}
+#else
+/* No support for the feature.  Provide the entry point expected by exec.c,
+   and implement the internal function we declared earlier.  */
+
+static void tcg_register_jit_int(void *buf, size_t size,
+                                 const void *debug_frame,
+                                 size_t debug_frame_size)
+{
+}
+
+void tcg_register_jit(void *buf, size_t buf_size)
+{
+}
+#endif /* ELF_HOST_MACHINE */
diff --git a/tcg/tcg.h b/tcg/tcg.h
new file mode 100644
index 00000000..231a7815
--- /dev/null
+++ b/tcg/tcg.h
@@ -0,0 +1,1011 @@
+/*
+ * Tiny Code Generator for QEMU
+ *
+ * Copyright (c) 2008 Fabrice Bellard
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (the "Software"), to deal
+ * in the Software without restriction, including without limitation the rights
+ * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+ * copies of the Software, and to permit persons to whom the Software is
+ * furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+ * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+ * THE SOFTWARE.
+ */
+
+#ifndef TCG_H
+#define TCG_H
+
+#include "qemu-common.h"
+#include "qemu/bitops.h"
+#include "tcg-target.h"
+
+#define CPU_TEMP_BUF_NLONGS 128
+
+/* Default target word size to pointer size.  */
+#ifndef TCG_TARGET_REG_BITS
+# if UINTPTR_MAX == UINT32_MAX
+#  define TCG_TARGET_REG_BITS 32
+# elif UINTPTR_MAX == UINT64_MAX
+#  define TCG_TARGET_REG_BITS 64
+# else
+#  error Unknown pointer size for tcg target
+# endif
+#endif
+
+#if TCG_TARGET_REG_BITS == 32
+typedef int32_t tcg_target_long;
+typedef uint32_t tcg_target_ulong;
+#define TCG_PRIlx PRIx32
+#define TCG_PRIld PRId32
+#elif TCG_TARGET_REG_BITS == 64
+typedef int64_t tcg_target_long;
+typedef uint64_t tcg_target_ulong;
+#define TCG_PRIlx PRIx64
+#define TCG_PRIld PRId64
+#else
+#error unsupported
+#endif
+
+#if TCG_TARGET_NB_REGS <= 32
+typedef uint32_t TCGRegSet;
+#elif TCG_TARGET_NB_REGS <= 64
+typedef uint64_t TCGRegSet;
+#else
+#error unsupported
+#endif
+
+#if TCG_TARGET_REG_BITS == 32
+/* Turn some undef macros into false macros.  */
+#define TCG_TARGET_HAS_trunc_shr_i32    0
+#define TCG_TARGET_HAS_div_i64          0
+#define TCG_TARGET_HAS_rem_i64          0
+#define TCG_TARGET_HAS_div2_i64         0
+#define TCG_TARGET_HAS_rot_i64          0
+#define TCG_TARGET_HAS_ext8s_i64        0
+#define TCG_TARGET_HAS_ext16s_i64       0
+#define TCG_TARGET_HAS_ext32s_i64       0
+#define TCG_TARGET_HAS_ext8u_i64        0
+#define TCG_TARGET_HAS_ext16u_i64       0
+#define TCG_TARGET_HAS_ext32u_i64       0
+#define TCG_TARGET_HAS_bswap16_i64      0
+#define TCG_TARGET_HAS_bswap32_i64      0
+#define TCG_TARGET_HAS_bswap64_i64      0
+#define TCG_TARGET_HAS_neg_i64          0
+#define TCG_TARGET_HAS_not_i64          0
+#define TCG_TARGET_HAS_andc_i64         0
+#define TCG_TARGET_HAS_orc_i64          0
+#define TCG_TARGET_HAS_eqv_i64          0
+#define TCG_TARGET_HAS_nand_i64         0
+#define TCG_TARGET_HAS_nor_i64          0
+#define TCG_TARGET_HAS_deposit_i64      0
+#define TCG_TARGET_HAS_movcond_i64      0
+#define TCG_TARGET_HAS_add2_i64         0
+#define TCG_TARGET_HAS_sub2_i64         0
+#define TCG_TARGET_HAS_mulu2_i64        0
+#define TCG_TARGET_HAS_muls2_i64        0
+#define TCG_TARGET_HAS_muluh_i64        0
+#define TCG_TARGET_HAS_mulsh_i64        0
+/* Turn some undef macros into true macros.  */
+#define TCG_TARGET_HAS_add2_i32         1
+#define TCG_TARGET_HAS_sub2_i32         1
+#endif
+
+#ifndef TCG_TARGET_deposit_i32_valid
+#define TCG_TARGET_deposit_i32_valid(ofs, len) 1
+#endif
+#ifndef TCG_TARGET_deposit_i64_valid
+#define TCG_TARGET_deposit_i64_valid(ofs, len) 1
+#endif
+
+/* Only one of DIV or DIV2 should be defined.  */
+#if defined(TCG_TARGET_HAS_div_i32)
+#define TCG_TARGET_HAS_div2_i32         0
+#elif defined(TCG_TARGET_HAS_div2_i32)
+#define TCG_TARGET_HAS_div_i32          0
+#define TCG_TARGET_HAS_rem_i32          0
+#endif
+#if defined(TCG_TARGET_HAS_div_i64)
+#define TCG_TARGET_HAS_div2_i64         0
+#elif defined(TCG_TARGET_HAS_div2_i64)
+#define TCG_TARGET_HAS_div_i64          0
+#define TCG_TARGET_HAS_rem_i64          0
+#endif
+
+/* For 32-bit targets, some sort of unsigned widening multiply is required.  */
+#if TCG_TARGET_REG_BITS == 32 \
+    && !(defined(TCG_TARGET_HAS_mulu2_i32) \
+         || defined(TCG_TARGET_HAS_muluh_i32))
+# error "Missing unsigned widening multiply"
+#endif
+
+typedef enum TCGOpcode {
+#define DEF(name, oargs, iargs, cargs, flags) INDEX_op_ ## name,
+#include "tcg-opc.h"
+#undef DEF
+    NB_OPS,
+} TCGOpcode;
+
+#define tcg_regset_clear(d) (d) = 0
+#define tcg_regset_set(d, s) (d) = (s)
+#define tcg_regset_set32(d, reg, val32) (d) |= (val32) << (reg)
+#define tcg_regset_set_reg(d, r) (d) |= 1L << (r)
+#define tcg_regset_reset_reg(d, r) (d) &= ~(1L << (r))
+#define tcg_regset_test_reg(d, r) (((d) >> (r)) & 1)
+#define tcg_regset_or(d, a, b) (d) = (a) | (b)
+#define tcg_regset_and(d, a, b) (d) = (a) & (b)
+#define tcg_regset_andnot(d, a, b) (d) = (a) & ~(b)
+#define tcg_regset_not(d, a) (d) = ~(a)
+
+#ifndef TCG_TARGET_INSN_UNIT_SIZE
+# error "Missing TCG_TARGET_INSN_UNIT_SIZE"
+#elif TCG_TARGET_INSN_UNIT_SIZE == 1
+typedef uint8_t tcg_insn_unit;
+#elif TCG_TARGET_INSN_UNIT_SIZE == 2
+typedef uint16_t tcg_insn_unit;
+#elif TCG_TARGET_INSN_UNIT_SIZE == 4
+typedef uint32_t tcg_insn_unit;
+#elif TCG_TARGET_INSN_UNIT_SIZE == 8
+typedef uint64_t tcg_insn_unit;
+#else
+/* The port better have done this.  */
+#endif
+
+
+typedef struct TCGRelocation {
+    struct TCGRelocation *next;
+    int type;
+    tcg_insn_unit *ptr;
+    intptr_t addend;
+} TCGRelocation; 
+
+typedef struct TCGLabel {
+    unsigned has_value : 1;
+    unsigned id : 31;
+    union {
+        uintptr_t value;
+        tcg_insn_unit *value_ptr;
+        TCGRelocation *first_reloc;
+    } u;
+} TCGLabel;
+
+typedef struct TCGPool {
+    struct TCGPool *next;
+    int size;
+    uint8_t data[0] __attribute__ ((aligned));
+} TCGPool;
+
+#define TCG_POOL_CHUNK_SIZE 32768
+
+#define TCG_MAX_TEMPS 512
+
+/* when the size of the arguments of a called function is smaller than
+   this value, they are statically allocated in the TB stack frame */
+#define TCG_STATIC_CALL_ARGS_SIZE 128
+
+typedef enum TCGType {
+    TCG_TYPE_I32,
+    TCG_TYPE_I64,
+    TCG_TYPE_COUNT, /* number of different types */
+
+    /* An alias for the size of the host register.  */
+#if TCG_TARGET_REG_BITS == 32
+    TCG_TYPE_REG = TCG_TYPE_I32,
+#else
+    TCG_TYPE_REG = TCG_TYPE_I64,
+#endif
+
+    /* An alias for the size of the native pointer.  */
+#if UINTPTR_MAX == UINT32_MAX
+    TCG_TYPE_PTR = TCG_TYPE_I32,
+#else
+    TCG_TYPE_PTR = TCG_TYPE_I64,
+#endif
+
+    /* An alias for the size of the target "long", aka register.  */
+#if TARGET_LONG_BITS == 64
+    TCG_TYPE_TL = TCG_TYPE_I64,
+#else
+    TCG_TYPE_TL = TCG_TYPE_I32,
+#endif
+} TCGType;
+
+/* Constants for qemu_ld and qemu_st for the Memory Operation field.  */
+typedef enum TCGMemOp {
+    MO_8     = 0,
+    MO_16    = 1,
+    MO_32    = 2,
+    MO_64    = 3,
+    MO_SIZE  = 3,   /* Mask for the above.  */
+
+    MO_SIGN  = 4,   /* Sign-extended, otherwise zero-extended.  */
+
+    MO_BSWAP = 8,   /* Host reverse endian.  */
+#ifdef HOST_WORDS_BIGENDIAN
+    MO_LE    = MO_BSWAP,
+    MO_BE    = 0,
+#else
+    MO_LE    = 0,
+    MO_BE    = MO_BSWAP,
+#endif
+#ifdef TARGET_WORDS_BIGENDIAN
+    MO_TE    = MO_BE,
+#else
+    MO_TE    = MO_LE,
+#endif
+
+    /* MO_UNALN accesses are never checked for alignment.
+       MO_ALIGN accesses will result in a call to the CPU's
+       do_unaligned_access hook if the guest address is not aligned.
+       The default depends on whether the target CPU defines ALIGNED_ONLY.  */
+    MO_AMASK = 16,
+#ifdef ALIGNED_ONLY
+    MO_ALIGN = 0,
+    MO_UNALN = MO_AMASK,
+#else
+    MO_ALIGN = MO_AMASK,
+    MO_UNALN = 0,
+#endif
+
+    /* Combinations of the above, for ease of use.  */
+    MO_UB    = MO_8,
+    MO_UW    = MO_16,
+    MO_UL    = MO_32,
+    MO_SB    = MO_SIGN | MO_8,
+    MO_SW    = MO_SIGN | MO_16,
+    MO_SL    = MO_SIGN | MO_32,
+    MO_Q     = MO_64,
+
+    MO_LEUW  = MO_LE | MO_UW,
+    MO_LEUL  = MO_LE | MO_UL,
+    MO_LESW  = MO_LE | MO_SW,
+    MO_LESL  = MO_LE | MO_SL,
+    MO_LEQ   = MO_LE | MO_Q,
+
+    MO_BEUW  = MO_BE | MO_UW,
+    MO_BEUL  = MO_BE | MO_UL,
+    MO_BESW  = MO_BE | MO_SW,
+    MO_BESL  = MO_BE | MO_SL,
+    MO_BEQ   = MO_BE | MO_Q,
+
+    MO_TEUW  = MO_TE | MO_UW,
+    MO_TEUL  = MO_TE | MO_UL,
+    MO_TESW  = MO_TE | MO_SW,
+    MO_TESL  = MO_TE | MO_SL,
+    MO_TEQ   = MO_TE | MO_Q,
+
+    MO_SSIZE = MO_SIZE | MO_SIGN,
+} TCGMemOp;
+
+typedef tcg_target_ulong TCGArg;
+
+/* Define a type and accessor macros for variables.  Using pointer types
+   is nice because it gives some level of type safely.  Converting to and
+   from intptr_t rather than int reduces the number of sign-extension
+   instructions that get implied on 64-bit hosts.  Users of tcg_gen_* don't
+   need to know about any of this, and should treat TCGv as an opaque type.
+   In addition we do typechecking for different types of variables.  TCGv_i32
+   and TCGv_i64 are 32/64-bit variables respectively.  TCGv and TCGv_ptr
+   are aliases for target_ulong and host pointer sized values respectively.  */
+
+typedef struct TCGv_i32_d *TCGv_i32;
+typedef struct TCGv_i64_d *TCGv_i64;
+typedef struct TCGv_ptr_d *TCGv_ptr;
+
+static inline TCGv_i32 QEMU_ARTIFICIAL MAKE_TCGV_I32(intptr_t i)
+{
+    return (TCGv_i32)i;
+}
+
+static inline TCGv_i64 QEMU_ARTIFICIAL MAKE_TCGV_I64(intptr_t i)
+{
+    return (TCGv_i64)i;
+}
+
+static inline TCGv_ptr QEMU_ARTIFICIAL MAKE_TCGV_PTR(intptr_t i)
+{
+    return (TCGv_ptr)i;
+}
+
+static inline intptr_t QEMU_ARTIFICIAL GET_TCGV_I32(TCGv_i32 t)
+{
+    return (intptr_t)t;
+}
+
+static inline intptr_t QEMU_ARTIFICIAL GET_TCGV_I64(TCGv_i64 t)
+{
+    return (intptr_t)t;
+}
+
+static inline intptr_t QEMU_ARTIFICIAL GET_TCGV_PTR(TCGv_ptr t)
+{
+    return (intptr_t)t;
+}
+
+#if TCG_TARGET_REG_BITS == 32
+#define TCGV_LOW(t) MAKE_TCGV_I32(GET_TCGV_I64(t))
+#define TCGV_HIGH(t) MAKE_TCGV_I32(GET_TCGV_I64(t) + 1)
+#endif
+
+#define TCGV_EQUAL_I32(a, b) (GET_TCGV_I32(a) == GET_TCGV_I32(b))
+#define TCGV_EQUAL_I64(a, b) (GET_TCGV_I64(a) == GET_TCGV_I64(b))
+#define TCGV_EQUAL_PTR(a, b) (GET_TCGV_PTR(a) == GET_TCGV_PTR(b))
+
+/* Dummy definition to avoid compiler warnings.  */
+#define TCGV_UNUSED_I32(x) x = MAKE_TCGV_I32(-1)
+#define TCGV_UNUSED_I64(x) x = MAKE_TCGV_I64(-1)
+#define TCGV_UNUSED_PTR(x) x = MAKE_TCGV_PTR(-1)
+
+#define TCGV_IS_UNUSED_I32(x) (GET_TCGV_I32(x) == -1)
+#define TCGV_IS_UNUSED_I64(x) (GET_TCGV_I64(x) == -1)
+#define TCGV_IS_UNUSED_PTR(x) (GET_TCGV_PTR(x) == -1)
+
+/* call flags */
+/* Helper does not read globals (either directly or through an exception). It
+   implies TCG_CALL_NO_WRITE_GLOBALS. */
+#define TCG_CALL_NO_READ_GLOBALS    0x0010
+/* Helper does not write globals */
+#define TCG_CALL_NO_WRITE_GLOBALS   0x0020
+/* Helper can be safely suppressed if the return value is not used. */
+#define TCG_CALL_NO_SIDE_EFFECTS    0x0040
+
+/* convenience version of most used call flags */
+#define TCG_CALL_NO_RWG         TCG_CALL_NO_READ_GLOBALS
+#define TCG_CALL_NO_WG          TCG_CALL_NO_WRITE_GLOBALS
+#define TCG_CALL_NO_SE          TCG_CALL_NO_SIDE_EFFECTS
+#define TCG_CALL_NO_RWG_SE      (TCG_CALL_NO_RWG | TCG_CALL_NO_SE)
+#define TCG_CALL_NO_WG_SE       (TCG_CALL_NO_WG | TCG_CALL_NO_SE)
+
+/* used to align parameters */
+#define TCG_CALL_DUMMY_TCGV     MAKE_TCGV_I32(-1)
+#define TCG_CALL_DUMMY_ARG      ((TCGArg)(-1))
+
+/* Conditions.  Note that these are laid out for easy manipulation by
+   the functions below:
+     bit 0 is used for inverting;
+     bit 1 is signed,
+     bit 2 is unsigned,
+     bit 3 is used with bit 0 for swapping signed/unsigned.  */
+typedef enum {
+    /* non-signed */
+    TCG_COND_NEVER  = 0 | 0 | 0 | 0,
+    TCG_COND_ALWAYS = 0 | 0 | 0 | 1,
+    TCG_COND_EQ     = 8 | 0 | 0 | 0,
+    TCG_COND_NE     = 8 | 0 | 0 | 1,
+    /* signed */
+    TCG_COND_LT     = 0 | 0 | 2 | 0,
+    TCG_COND_GE     = 0 | 0 | 2 | 1,
+    TCG_COND_LE     = 8 | 0 | 2 | 0,
+    TCG_COND_GT     = 8 | 0 | 2 | 1,
+    /* unsigned */
+    TCG_COND_LTU    = 0 | 4 | 0 | 0,
+    TCG_COND_GEU    = 0 | 4 | 0 | 1,
+    TCG_COND_LEU    = 8 | 4 | 0 | 0,
+    TCG_COND_GTU    = 8 | 4 | 0 | 1,
+} TCGCond;
+
+/* Invert the sense of the comparison.  */
+static inline TCGCond tcg_invert_cond(TCGCond c)
+{
+    return (TCGCond)(c ^ 1);
+}
+
+/* Swap the operands in a comparison.  */
+static inline TCGCond tcg_swap_cond(TCGCond c)
+{
+    return c & 6 ? (TCGCond)(c ^ 9) : c;
+}
+
+/* Create an "unsigned" version of a "signed" comparison.  */
+static inline TCGCond tcg_unsigned_cond(TCGCond c)
+{
+    return c & 2 ? (TCGCond)(c ^ 6) : c;
+}
+
+/* Must a comparison be considered unsigned?  */
+static inline bool is_unsigned_cond(TCGCond c)
+{
+    return (c & 4) != 0;
+}
+
+/* Create a "high" version of a double-word comparison.
+   This removes equality from a LTE or GTE comparison.  */
+static inline TCGCond tcg_high_cond(TCGCond c)
+{
+    switch (c) {
+    case TCG_COND_GE:
+    case TCG_COND_LE:
+    case TCG_COND_GEU:
+    case TCG_COND_LEU:
+        return (TCGCond)(c ^ 8);
+    default:
+        return c;
+    }
+}
+
+typedef enum TCGTempVal {
+    TEMP_VAL_DEAD,
+    TEMP_VAL_REG,
+    TEMP_VAL_MEM,
+    TEMP_VAL_CONST,
+} TCGTempVal;
+
+typedef struct TCGTemp {
+    unsigned int reg:8;
+    unsigned int mem_reg:8;
+    TCGTempVal val_type:8;
+    TCGType base_type:8;
+    TCGType type:8;
+    unsigned int fixed_reg:1;
+    unsigned int mem_coherent:1;
+    unsigned int mem_allocated:1;
+    unsigned int temp_local:1; /* If true, the temp is saved across
+                                  basic blocks. Otherwise, it is not
+                                  preserved across basic blocks. */
+    unsigned int temp_allocated:1; /* never used for code gen */
+
+    tcg_target_long val;
+    intptr_t mem_offset;
+    const char *name;
+} TCGTemp;
+
+typedef struct TCGContext TCGContext;
+
+typedef struct TCGTempSet {
+    unsigned long l[BITS_TO_LONGS(TCG_MAX_TEMPS)];
+} TCGTempSet;
+
+typedef struct TCGOp {
+    TCGOpcode opc   : 8;
+
+    /* The number of out and in parameter for a call.  */
+    unsigned callo  : 2;
+    unsigned calli  : 6;
+
+    /* Index of the arguments for this op, or -1 for zero-operand ops.  */
+    signed args     : 16;
+
+    /* Index of the prex/next op, or -1 for the end of the list.  */
+    signed prev     : 16;
+    signed next     : 16;
+} TCGOp;
+
+QEMU_BUILD_BUG_ON(NB_OPS > 0xff);
+QEMU_BUILD_BUG_ON(OPC_BUF_SIZE >= 0x7fff);
+QEMU_BUILD_BUG_ON(OPPARAM_BUF_SIZE >= 0x7fff);
+
+struct TCGContext {
+    uint8_t *pool_cur, *pool_end;
+    TCGPool *pool_first, *pool_current, *pool_first_large;
+    int nb_labels;
+    int nb_globals;
+    int nb_temps;
+
+    /* goto_tb support */
+    tcg_insn_unit *code_buf;
+    uintptr_t *tb_next;
+    uint16_t *tb_next_offset;
+    uint16_t *tb_jmp_offset; /* != NULL if USE_DIRECT_JUMP */
+
+    /* liveness analysis */
+    uint16_t *op_dead_args; /* for each operation, each bit tells if the
+                               corresponding argument is dead */
+    uint8_t *op_sync_args;  /* for each operation, each bit tells if the
+                               corresponding output argument needs to be
+                               sync to memory. */
+    
+    TCGRegSet reserved_regs;
+    intptr_t current_frame_offset;
+    intptr_t frame_start;
+    intptr_t frame_end;
+    int frame_reg;
+
+    tcg_insn_unit *code_ptr;
+
+    GHashTable *helpers;
+
+#ifdef CONFIG_PROFILER
+    /* profiling info */
+    int64_t tb_count1;
+    int64_t tb_count;
+    int64_t op_count; /* total insn count */
+    int op_count_max; /* max insn per TB */
+    int64_t temp_count;
+    int temp_count_max;
+    int64_t del_op_count;
+    int64_t code_in_len;
+    int64_t code_out_len;
+    int64_t interm_time;
+    int64_t code_time;
+    int64_t la_time;
+    int64_t opt_time;
+    int64_t restore_count;
+    int64_t restore_time;
+#endif
+
+#ifdef CONFIG_DEBUG_TCG
+    int temps_in_use;
+    int goto_tb_issue_mask;
+#endif
+
+    int gen_first_op_idx;
+    int gen_last_op_idx;
+    int gen_next_op_idx;
+    int gen_next_parm_idx;
+
+    /* Code generation.  Note that we specifically do not use tcg_insn_unit
+       here, because there's too much arithmetic throughout that relies
+       on addition and subtraction working on bytes.  Rely on the GCC
+       extension that allows arithmetic on void*.  */
+    int code_gen_max_blocks;
+    void *code_gen_prologue;
+    void *code_gen_buffer;
+    size_t code_gen_buffer_size;
+    /* threshold to flush the translated code buffer */
+    size_t code_gen_buffer_max_size;
+    void *code_gen_ptr;
+
+    TBContext tb_ctx;
+
+    /* The TCGBackendData structure is private to tcg-target.c.  */
+    struct TCGBackendData *be;
+
+    TCGTempSet free_temps[TCG_TYPE_COUNT * 2];
+    TCGTemp temps[TCG_MAX_TEMPS]; /* globals first, temps after */
+
+    /* tells in which temporary a given register is. It does not take
+       into account fixed registers */
+    int reg_to_temp[TCG_TARGET_NB_REGS];
+
+    TCGOp gen_op_buf[OPC_BUF_SIZE];
+    TCGArg gen_opparam_buf[OPPARAM_BUF_SIZE];
+
+    target_ulong gen_opc_pc[OPC_BUF_SIZE];
+    uint16_t gen_opc_icount[OPC_BUF_SIZE];
+    uint8_t gen_opc_instr_start[OPC_BUF_SIZE];
+};
+
+extern TCGContext tcg_ctx;
+
+/* The number of opcodes emitted so far.  */
+static inline int tcg_op_buf_count(void)
+{
+    return tcg_ctx.gen_next_op_idx;
+}
+
+/* Test for whether to terminate the TB for using too many opcodes.  */
+static inline bool tcg_op_buf_full(void)
+{
+    return tcg_op_buf_count() >= OPC_MAX_SIZE;
+}
+
+/* pool based memory allocation */
+
+void *tcg_malloc_internal(TCGContext *s, int size);
+void tcg_pool_reset(TCGContext *s);
+void tcg_pool_delete(TCGContext *s);
+
+static inline void *tcg_malloc(int size)
+{
+    TCGContext *s = &tcg_ctx;
+    uint8_t *ptr, *ptr_end;
+    size = (size + sizeof(long) - 1) & ~(sizeof(long) - 1);
+    ptr = s->pool_cur;
+    ptr_end = ptr + size;
+    if (unlikely(ptr_end > s->pool_end)) {
+        return tcg_malloc_internal(&tcg_ctx, size);
+    } else {
+        s->pool_cur = ptr_end;
+        return ptr;
+    }
+}
+
+void tcg_context_init(TCGContext *s);
+void tcg_prologue_init(TCGContext *s);
+void tcg_func_start(TCGContext *s);
+
+int tcg_gen_code(TCGContext *s, tcg_insn_unit *gen_code_buf);
+int tcg_gen_code_search_pc(TCGContext *s, tcg_insn_unit *gen_code_buf,
+                           long offset);
+
+void tcg_set_frame(TCGContext *s, int reg, intptr_t start, intptr_t size);
+
+TCGv_i32 tcg_global_reg_new_i32(int reg, const char *name);
+TCGv_i32 tcg_global_mem_new_i32(int reg, intptr_t offset, const char *name);
+TCGv_i32 tcg_temp_new_internal_i32(int temp_local);
+static inline TCGv_i32 tcg_temp_new_i32(void)
+{
+    return tcg_temp_new_internal_i32(0);
+}
+static inline TCGv_i32 tcg_temp_local_new_i32(void)
+{
+    return tcg_temp_new_internal_i32(1);
+}
+void tcg_temp_free_i32(TCGv_i32 arg);
+char *tcg_get_arg_str_i32(TCGContext *s, char *buf, int buf_size, TCGv_i32 arg);
+
+TCGv_i64 tcg_global_reg_new_i64(int reg, const char *name);
+TCGv_i64 tcg_global_mem_new_i64(int reg, intptr_t offset, const char *name);
+TCGv_i64 tcg_temp_new_internal_i64(int temp_local);
+static inline TCGv_i64 tcg_temp_new_i64(void)
+{
+    return tcg_temp_new_internal_i64(0);
+}
+static inline TCGv_i64 tcg_temp_local_new_i64(void)
+{
+    return tcg_temp_new_internal_i64(1);
+}
+void tcg_temp_free_i64(TCGv_i64 arg);
+char *tcg_get_arg_str_i64(TCGContext *s, char *buf, int buf_size, TCGv_i64 arg);
+
+#if defined(CONFIG_DEBUG_TCG)
+/* If you call tcg_clear_temp_count() at the start of a section of
+ * code which is not supposed to leak any TCG temporaries, then
+ * calling tcg_check_temp_count() at the end of the section will
+ * return 1 if the section did in fact leak a temporary.
+ */
+void tcg_clear_temp_count(void);
+int tcg_check_temp_count(void);
+#else
+#define tcg_clear_temp_count() do { } while (0)
+#define tcg_check_temp_count() 0
+#endif
+
+void tcg_dump_info(FILE *f, fprintf_function cpu_fprintf);
+void tcg_dump_op_count(FILE *f, fprintf_function cpu_fprintf);
+
+#define TCG_CT_ALIAS  0x80
+#define TCG_CT_IALIAS 0x40
+#define TCG_CT_REG    0x01
+#define TCG_CT_CONST  0x02 /* any constant of register size */
+
+typedef struct TCGArgConstraint {
+    uint16_t ct;
+    uint8_t alias_index;
+    union {
+        TCGRegSet regs;
+    } u;
+} TCGArgConstraint;
+
+#define TCG_MAX_OP_ARGS 16
+
+/* Bits for TCGOpDef->flags, 8 bits available.  */
+enum {
+    /* Instruction defines the end of a basic block.  */
+    TCG_OPF_BB_END       = 0x01,
+    /* Instruction clobbers call registers and potentially update globals.  */
+    TCG_OPF_CALL_CLOBBER = 0x02,
+    /* Instruction has side effects: it cannot be removed if its outputs
+       are not used, and might trigger exceptions.  */
+    TCG_OPF_SIDE_EFFECTS = 0x04,
+    /* Instruction operands are 64-bits (otherwise 32-bits).  */
+    TCG_OPF_64BIT        = 0x08,
+    /* Instruction is optional and not implemented by the host, or insn
+       is generic and should not be implemened by the host.  */
+    TCG_OPF_NOT_PRESENT  = 0x10,
+};
+
+typedef struct TCGOpDef {
+    const char *name;
+    uint8_t nb_oargs, nb_iargs, nb_cargs, nb_args;
+    uint8_t flags;
+    TCGArgConstraint *args_ct;
+    int *sorted_args;
+#if defined(CONFIG_DEBUG_TCG)
+    int used;
+#endif
+} TCGOpDef;
+
+extern TCGOpDef tcg_op_defs[];
+extern const size_t tcg_op_defs_max;
+
+typedef struct TCGTargetOpDef {
+    TCGOpcode op;
+    const char *args_ct_str[TCG_MAX_OP_ARGS];
+} TCGTargetOpDef;
+
+#define tcg_abort() \
+do {\
+    fprintf(stderr, "%s:%d: tcg fatal error\n", __FILE__, __LINE__);\
+    abort();\
+} while (0)
+
+#ifdef CONFIG_DEBUG_TCG
+# define tcg_debug_assert(X) do { assert(X); } while (0)
+#elif QEMU_GNUC_PREREQ(4, 5)
+# define tcg_debug_assert(X) \
+    do { if (!(X)) { __builtin_unreachable(); } } while (0)
+#else
+# define tcg_debug_assert(X) do { (void)(X); } while (0)
+#endif
+
+void tcg_add_target_add_op_defs(const TCGTargetOpDef *tdefs);
+
+#if UINTPTR_MAX == UINT32_MAX
+#define TCGV_NAT_TO_PTR(n) MAKE_TCGV_PTR(GET_TCGV_I32(n))
+#define TCGV_PTR_TO_NAT(n) MAKE_TCGV_I32(GET_TCGV_PTR(n))
+
+#define tcg_const_ptr(V) TCGV_NAT_TO_PTR(tcg_const_i32((intptr_t)(V)))
+#define tcg_global_reg_new_ptr(R, N) \
+    TCGV_NAT_TO_PTR(tcg_global_reg_new_i32((R), (N)))
+#define tcg_global_mem_new_ptr(R, O, N) \
+    TCGV_NAT_TO_PTR(tcg_global_mem_new_i32((R), (O), (N)))
+#define tcg_temp_new_ptr() TCGV_NAT_TO_PTR(tcg_temp_new_i32())
+#define tcg_temp_free_ptr(T) tcg_temp_free_i32(TCGV_PTR_TO_NAT(T))
+#else
+#define TCGV_NAT_TO_PTR(n) MAKE_TCGV_PTR(GET_TCGV_I64(n))
+#define TCGV_PTR_TO_NAT(n) MAKE_TCGV_I64(GET_TCGV_PTR(n))
+
+#define tcg_const_ptr(V) TCGV_NAT_TO_PTR(tcg_const_i64((intptr_t)(V)))
+#define tcg_global_reg_new_ptr(R, N) \
+    TCGV_NAT_TO_PTR(tcg_global_reg_new_i64((R), (N)))
+#define tcg_global_mem_new_ptr(R, O, N) \
+    TCGV_NAT_TO_PTR(tcg_global_mem_new_i64((R), (O), (N)))
+#define tcg_temp_new_ptr() TCGV_NAT_TO_PTR(tcg_temp_new_i64())
+#define tcg_temp_free_ptr(T) tcg_temp_free_i64(TCGV_PTR_TO_NAT(T))
+#endif
+
+void tcg_gen_callN(TCGContext *s, void *func,
+                   TCGArg ret, int nargs, TCGArg *args);
+
+void tcg_op_remove(TCGContext *s, TCGOp *op);
+void tcg_optimize(TCGContext *s);
+
+/* only used for debugging purposes */
+void tcg_dump_ops(TCGContext *s);
+
+void dump_ops(const uint16_t *opc_buf, const TCGArg *opparam_buf);
+TCGv_i32 tcg_const_i32(int32_t val);
+TCGv_i64 tcg_const_i64(int64_t val);
+TCGv_i32 tcg_const_local_i32(int32_t val);
+TCGv_i64 tcg_const_local_i64(int64_t val);
+
+TCGLabel *gen_new_label(void);
+
+/**
+ * label_arg
+ * @l: label
+ *
+ * Encode a label for storage in the TCG opcode stream.
+ */
+
+static inline TCGArg label_arg(TCGLabel *l)
+{
+    return (uintptr_t)l;
+}
+
+/**
+ * arg_label
+ * @i: value
+ *
+ * The opposite of label_arg.  Retrieve a label from the
+ * encoding of the TCG opcode stream.
+ */
+
+static inline TCGLabel *arg_label(TCGArg i)
+{
+    return (TCGLabel *)(uintptr_t)i;
+}
+
+/**
+ * tcg_ptr_byte_diff
+ * @a, @b: addresses to be differenced
+ *
+ * There are many places within the TCG backends where we need a byte
+ * difference between two pointers.  While this can be accomplished
+ * with local casting, it's easy to get wrong -- especially if one is
+ * concerned with the signedness of the result.
+ *
+ * This version relies on GCC's void pointer arithmetic to get the
+ * correct result.
+ */
+
+static inline ptrdiff_t tcg_ptr_byte_diff(void *a, void *b)
+{
+    return a - b;
+}
+
+/**
+ * tcg_pcrel_diff
+ * @s: the tcg context
+ * @target: address of the target
+ *
+ * Produce a pc-relative difference, from the current code_ptr
+ * to the destination address.
+ */
+
+static inline ptrdiff_t tcg_pcrel_diff(TCGContext *s, void *target)
+{
+    return tcg_ptr_byte_diff(target, s->code_ptr);
+}
+
+/**
+ * tcg_current_code_size
+ * @s: the tcg context
+ *
+ * Compute the current code size within the translation block.
+ * This is used to fill in qemu's data structures for goto_tb.
+ */
+
+static inline size_t tcg_current_code_size(TCGContext *s)
+{
+    return tcg_ptr_byte_diff(s->code_ptr, s->code_buf);
+}
+
+/* Combine the TCGMemOp and mmu_idx parameters into a single value.  */
+typedef uint32_t TCGMemOpIdx;
+
+/**
+ * make_memop_idx
+ * @op: memory operation
+ * @idx: mmu index
+ *
+ * Encode these values into a single parameter.
+ */
+static inline TCGMemOpIdx make_memop_idx(TCGMemOp op, unsigned idx)
+{
+    tcg_debug_assert(idx <= 15);
+    return (op << 4) | idx;
+}
+
+/**
+ * get_memop
+ * @oi: combined op/idx parameter
+ *
+ * Extract the memory operation from the combined value.
+ */
+static inline TCGMemOp get_memop(TCGMemOpIdx oi)
+{
+    return oi >> 4;
+}
+
+/**
+ * get_mmuidx
+ * @oi: combined op/idx parameter
+ *
+ * Extract the mmu index from the combined value.
+ */
+static inline unsigned get_mmuidx(TCGMemOpIdx oi)
+{
+    return oi & 15;
+}
+
+/**
+ * tcg_qemu_tb_exec:
+ * @env: CPUArchState * for the CPU
+ * @tb_ptr: address of generated code for the TB to execute
+ *
+ * Start executing code from a given translation block.
+ * Where translation blocks have been linked, execution
+ * may proceed from the given TB into successive ones.
+ * Control eventually returns only when some action is needed
+ * from the top-level loop: either control must pass to a TB
+ * which has not yet been directly linked, or an asynchronous
+ * event such as an interrupt needs handling.
+ *
+ * The return value is a pointer to the next TB to execute
+ * (if known; otherwise zero). This pointer is assumed to be
+ * 4-aligned, and the bottom two bits are used to return further
+ * information:
+ *  0, 1: the link between this TB and the next is via the specified
+ *        TB index (0 or 1). That is, we left the TB via (the equivalent
+ *        of) "goto_tb <index>". The main loop uses this to determine
+ *        how to link the TB just executed to the next.
+ *  2:    we are using instruction counting code generation, and we
+ *        did not start executing this TB because the instruction counter
+ *        would hit zero midway through it. In this case the next-TB pointer
+ *        returned is the TB we were about to execute, and the caller must
+ *        arrange to execute the remaining count of instructions.
+ *  3:    we stopped because the CPU's exit_request flag was set
+ *        (usually meaning that there is an interrupt that needs to be
+ *        handled). The next-TB pointer returned is the TB we were
+ *        about to execute when we noticed the pending exit request.
+ *
+ * If the bottom two bits indicate an exit-via-index then the CPU
+ * state is correctly synchronised and ready for execution of the next
+ * TB (and in particular the guest PC is the address to execute next).
+ * Otherwise, we gave up on execution of this TB before it started, and
+ * the caller must fix up the CPU state by calling the CPU's
+ * synchronize_from_tb() method with the next-TB pointer we return (falling
+ * back to calling the CPU's set_pc method with tb->pb if no
+ * synchronize_from_tb() method exists).
+ *
+ * Note that TCG targets may use a different definition of tcg_qemu_tb_exec
+ * to this default (which just calls the prologue.code emitted by
+ * tcg_target_qemu_prologue()).
+ */
+#define TB_EXIT_MASK 3
+#define TB_EXIT_IDX0 0
+#define TB_EXIT_IDX1 1
+#define TB_EXIT_ICOUNT_EXPIRED 2
+#define TB_EXIT_REQUESTED 3
+
+#ifdef HAVE_TCG_QEMU_TB_EXEC
+uintptr_t tcg_qemu_tb_exec(CPUArchState *env, uint8_t *tb_ptr);
+#else
+# define tcg_qemu_tb_exec(env, tb_ptr) \
+    ((uintptr_t (*)(void *, void *))tcg_ctx.code_gen_prologue)(env, tb_ptr)
+#endif
+
+void tcg_register_jit(void *buf, size_t buf_size);
+
+/*
+ * Memory helpers that will be used by TCG generated code.
+ */
+#ifdef CONFIG_SOFTMMU
+/* Value zero-extended to tcg register size.  */
+tcg_target_ulong helper_ret_ldub_mmu(CPUArchState *env, target_ulong addr,
+                                     TCGMemOpIdx oi, uintptr_t retaddr);
+tcg_target_ulong helper_le_lduw_mmu(CPUArchState *env, target_ulong addr,
+                                    TCGMemOpIdx oi, uintptr_t retaddr);
+tcg_target_ulong helper_le_ldul_mmu(CPUArchState *env, target_ulong addr,
+                                    TCGMemOpIdx oi, uintptr_t retaddr);
+uint64_t helper_le_ldq_mmu(CPUArchState *env, target_ulong addr,
+                           TCGMemOpIdx oi, uintptr_t retaddr);
+tcg_target_ulong helper_be_lduw_mmu(CPUArchState *env, target_ulong addr,
+                                    TCGMemOpIdx oi, uintptr_t retaddr);
+tcg_target_ulong helper_be_ldul_mmu(CPUArchState *env, target_ulong addr,
+                                    TCGMemOpIdx oi, uintptr_t retaddr);
+uint64_t helper_be_ldq_mmu(CPUArchState *env, target_ulong addr,
+                           TCGMemOpIdx oi, uintptr_t retaddr);
+
+/* Value sign-extended to tcg register size.  */
+tcg_target_ulong helper_ret_ldsb_mmu(CPUArchState *env, target_ulong addr,
+                                     TCGMemOpIdx oi, uintptr_t retaddr);
+tcg_target_ulong helper_le_ldsw_mmu(CPUArchState *env, target_ulong addr,
+                                    TCGMemOpIdx oi, uintptr_t retaddr);
+tcg_target_ulong helper_le_ldsl_mmu(CPUArchState *env, target_ulong addr,
+                                    TCGMemOpIdx oi, uintptr_t retaddr);
+tcg_target_ulong helper_be_ldsw_mmu(CPUArchState *env, target_ulong addr,
+                                    TCGMemOpIdx oi, uintptr_t retaddr);
+tcg_target_ulong helper_be_ldsl_mmu(CPUArchState *env, target_ulong addr,
+                                    TCGMemOpIdx oi, uintptr_t retaddr);
+
+void helper_ret_stb_mmu(CPUArchState *env, target_ulong addr, uint8_t val,
+                        TCGMemOpIdx oi, uintptr_t retaddr);
+void helper_le_stw_mmu(CPUArchState *env, target_ulong addr, uint16_t val,
+                       TCGMemOpIdx oi, uintptr_t retaddr);
+void helper_le_stl_mmu(CPUArchState *env, target_ulong addr, uint32_t val,
+                       TCGMemOpIdx oi, uintptr_t retaddr);
+void helper_le_stq_mmu(CPUArchState *env, target_ulong addr, uint64_t val,
+                       TCGMemOpIdx oi, uintptr_t retaddr);
+void helper_be_stw_mmu(CPUArchState *env, target_ulong addr, uint16_t val,
+                       TCGMemOpIdx oi, uintptr_t retaddr);
+void helper_be_stl_mmu(CPUArchState *env, target_ulong addr, uint32_t val,
+                       TCGMemOpIdx oi, uintptr_t retaddr);
+void helper_be_stq_mmu(CPUArchState *env, target_ulong addr, uint64_t val,
+                       TCGMemOpIdx oi, uintptr_t retaddr);
+
+/* Temporary aliases until backends are converted.  */
+#ifdef TARGET_WORDS_BIGENDIAN
+# define helper_ret_ldsw_mmu  helper_be_ldsw_mmu
+# define helper_ret_lduw_mmu  helper_be_lduw_mmu
+# define helper_ret_ldsl_mmu  helper_be_ldsl_mmu
+# define helper_ret_ldul_mmu  helper_be_ldul_mmu
+# define helper_ret_ldq_mmu   helper_be_ldq_mmu
+# define helper_ret_stw_mmu   helper_be_stw_mmu
+# define helper_ret_stl_mmu   helper_be_stl_mmu
+# define helper_ret_stq_mmu   helper_be_stq_mmu
+#else
+# define helper_ret_ldsw_mmu  helper_le_ldsw_mmu
+# define helper_ret_lduw_mmu  helper_le_lduw_mmu
+# define helper_ret_ldsl_mmu  helper_le_ldsl_mmu
+# define helper_ret_ldul_mmu  helper_le_ldul_mmu
+# define helper_ret_ldq_mmu   helper_le_ldq_mmu
+# define helper_ret_stw_mmu   helper_le_stw_mmu
+# define helper_ret_stl_mmu   helper_le_stl_mmu
+# define helper_ret_stq_mmu   helper_le_stq_mmu
+#endif
+
+#endif /* CONFIG_SOFTMMU */
+
+#endif /* TCG_H */
diff --git a/tcg/tci/README b/tcg/tci/README
new file mode 100644
index 00000000..dc57f076
--- /dev/null
+++ b/tcg/tci/README
@@ -0,0 +1,130 @@
+TCG Interpreter (TCI) - Copyright (c) 2011 Stefan Weil.
+
+This file is released under the BSD license.
+
+1) Introduction
+
+TCG (Tiny Code Generator) is a code generator which translates
+code fragments ("basic blocks") from target code (any of the
+targets supported by QEMU) to a code representation which
+can be run on a host.
+
+QEMU can create native code for some hosts (arm, hppa, i386, ia64, ppc, ppc64,
+s390, sparc, x86_64). For others, unofficial host support was written.
+
+By adding a code generator for a virtual machine and using an
+interpreter for the generated bytecode, it is possible to
+support (almost) any host.
+
+This is what TCI (Tiny Code Interpreter) does.
+
+2) Implementation
+
+Like each TCG host frontend, TCI implements the code generator in
+tcg-target.c, tcg-target.h. Both files are in directory tcg/tci.
+
+The additional file tcg/tci.c adds the interpreter.
+
+The bytecode consists of opcodes (same numeric values as those used by
+TCG), command length and arguments of variable size and number.
+
+3) Usage
+
+For hosts without native TCG, the interpreter TCI must be enabled by
+
+        configure --enable-tcg-interpreter
+
+If configure is called without --enable-tcg-interpreter, it will
+suggest using this option. Setting it automatically would need
+additional code in configure which must be fixed when new native TCG
+implementations are added.
+
+System emulation should work on any 32 or 64 bit host.
+User mode emulation might work. Maybe a new linker script (*.ld)
+is needed. Byte order might be wrong (on big endian hosts)
+and need fixes in configure.
+
+For hosts with native TCG, the interpreter TCI can be enabled by
+
+        configure --enable-tcg-interpreter
+
+The only difference from running QEMU with TCI to running without TCI
+should be speed. Especially during development of TCI, it was very
+useful to compare runs with and without TCI. Create /tmp/qemu.log by
+
+        qemu-system-i386 -d in_asm,op_opt,cpu -D /tmp/qemu.log -singlestep
+
+once with interpreter and once without interpreter and compare the resulting
+qemu.log files. This is also useful to see the effects of additional
+registers or additional opcodes (it is easy to modify the virtual machine).
+It can also be used to verify native TCGs.
+
+Hosts with native TCG can also enable TCI by claiming to be unsupported:
+
+        configure --cpu=unknown --enable-tcg-interpreter
+
+configure then no longer uses the native linker script (*.ld) for
+user mode emulation.
+
+
+4) Status
+
+TCI needs special implementation for 32 and 64 bit host, 32 and 64 bit target,
+host and target with same or different endianness.
+
+            | host (le)                     host (be)
+            | 32             64             32             64
+------------+------------------------------------------------------------
+target (le) | s0, u0         s1, u1         s?, u?         s?, u?
+32 bit      |
+            |
+target (le) | sc, uc         s1, u1         s?, u?         s?, u?
+64 bit      |
+            |
+target (be) | sc, u0         sc, uc         s?, u?         s?, u?
+32 bit      |
+            |
+target (be) | sc, uc         sc, uc         s?, u?         s?, u?
+64 bit      |
+            |
+
+System emulation
+s? = untested
+sc = compiles
+s0 = bios works
+s1 = grub works
+s2 = Linux boots
+
+Linux user mode emulation
+u? = untested
+uc = compiles
+u0 = static hello works
+u1 = linux-user-test works
+
+5) Todo list
+
+* TCI is not widely tested. It was written and tested on a x86_64 host
+  running i386 and x86_64 system emulation and Linux user mode.
+  A cross compiled QEMU for i386 host also works with the same basic tests.
+  A cross compiled QEMU for mipsel host works, too. It is terribly slow
+  because I run it in a mips malta emulation, so it is an interpreted
+  emulation in an emulation.
+  A cross compiled QEMU for arm host works (tested with pc bios).
+  A cross compiled QEMU for ppc host works at least partially:
+  i386-linux-user/qemu-i386 can run a simple hello-world program
+  (tested in a ppc emulation).
+
+* Some TCG opcodes are either missing in the code generator and/or
+  in the interpreter. These opcodes raise a runtime exception, so it is
+  possible to see where code must be added.
+
+* The pseudo code is not optimized and still ugly. For hosts with special
+  alignment requirements, it needs some fixes (maybe aligned bytecode
+  would also improve speed for hosts which support byte alignment).
+
+* A better disassembler for the pseudo code would be nice (a very primitive
+  disassembler is included in tcg-target.c).
+
+* It might be useful to have a runtime option which selects the native TCG
+  or TCI, so QEMU would have to include two TCGs. Today, selecting TCI
+  is a configure option, so you need two compilations of QEMU.
diff --git a/tcg/tci/tcg-target.c b/tcg/tci/tcg-target.c
new file mode 100644
index 00000000..83472dbc
--- /dev/null
+++ b/tcg/tci/tcg-target.c
@@ -0,0 +1,875 @@
+/*
+ * Tiny Code Generator for QEMU
+ *
+ * Copyright (c) 2009, 2011 Stefan Weil
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (the "Software"), to deal
+ * in the Software without restriction, including without limitation the rights
+ * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+ * copies of the Software, and to permit persons to whom the Software is
+ * furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+ * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+ * THE SOFTWARE.
+ */
+
+#include "tcg-be-null.h"
+
+/* TODO list:
+ * - See TODO comments in code.
+ */
+
+/* Marker for missing code. */
+#define TODO() \
+    do { \
+        fprintf(stderr, "TODO %s:%u: %s()\n", \
+                __FILE__, __LINE__, __func__); \
+        tcg_abort(); \
+    } while (0)
+
+/* Bitfield n...m (in 32 bit value). */
+#define BITS(n, m) (((0xffffffffU << (31 - n)) >> (31 - n + m)) << m)
+
+/* Macros used in tcg_target_op_defs. */
+#define R       "r"
+#define RI      "ri"
+#if TCG_TARGET_REG_BITS == 32
+# define R64    "r", "r"
+#else
+# define R64    "r"
+#endif
+#if TARGET_LONG_BITS > TCG_TARGET_REG_BITS
+# define L      "L", "L"
+# define S      "S", "S"
+#else
+# define L      "L"
+# define S      "S"
+#endif
+
+/* TODO: documentation. */
+static const TCGTargetOpDef tcg_target_op_defs[] = {
+    { INDEX_op_exit_tb, { NULL } },
+    { INDEX_op_goto_tb, { NULL } },
+    { INDEX_op_br, { NULL } },
+
+    { INDEX_op_ld8u_i32, { R, R } },
+    { INDEX_op_ld8s_i32, { R, R } },
+    { INDEX_op_ld16u_i32, { R, R } },
+    { INDEX_op_ld16s_i32, { R, R } },
+    { INDEX_op_ld_i32, { R, R } },
+    { INDEX_op_st8_i32, { R, R } },
+    { INDEX_op_st16_i32, { R, R } },
+    { INDEX_op_st_i32, { R, R } },
+
+    { INDEX_op_add_i32, { R, RI, RI } },
+    { INDEX_op_sub_i32, { R, RI, RI } },
+    { INDEX_op_mul_i32, { R, RI, RI } },
+#if TCG_TARGET_HAS_div_i32
+    { INDEX_op_div_i32, { R, R, R } },
+    { INDEX_op_divu_i32, { R, R, R } },
+    { INDEX_op_rem_i32, { R, R, R } },
+    { INDEX_op_remu_i32, { R, R, R } },
+#elif TCG_TARGET_HAS_div2_i32
+    { INDEX_op_div2_i32, { R, R, "0", "1", R } },
+    { INDEX_op_divu2_i32, { R, R, "0", "1", R } },
+#endif
+    /* TODO: Does R, RI, RI result in faster code than R, R, RI?
+       If both operands are constants, we can optimize. */
+    { INDEX_op_and_i32, { R, RI, RI } },
+#if TCG_TARGET_HAS_andc_i32
+    { INDEX_op_andc_i32, { R, RI, RI } },
+#endif
+#if TCG_TARGET_HAS_eqv_i32
+    { INDEX_op_eqv_i32, { R, RI, RI } },
+#endif
+#if TCG_TARGET_HAS_nand_i32
+    { INDEX_op_nand_i32, { R, RI, RI } },
+#endif
+#if TCG_TARGET_HAS_nor_i32
+    { INDEX_op_nor_i32, { R, RI, RI } },
+#endif
+    { INDEX_op_or_i32, { R, RI, RI } },
+#if TCG_TARGET_HAS_orc_i32
+    { INDEX_op_orc_i32, { R, RI, RI } },
+#endif
+    { INDEX_op_xor_i32, { R, RI, RI } },
+    { INDEX_op_shl_i32, { R, RI, RI } },
+    { INDEX_op_shr_i32, { R, RI, RI } },
+    { INDEX_op_sar_i32, { R, RI, RI } },
+#if TCG_TARGET_HAS_rot_i32
+    { INDEX_op_rotl_i32, { R, RI, RI } },
+    { INDEX_op_rotr_i32, { R, RI, RI } },
+#endif
+#if TCG_TARGET_HAS_deposit_i32
+    { INDEX_op_deposit_i32, { R, "0", R } },
+#endif
+
+    { INDEX_op_brcond_i32, { R, RI } },
+
+    { INDEX_op_setcond_i32, { R, R, RI } },
+#if TCG_TARGET_REG_BITS == 64
+    { INDEX_op_setcond_i64, { R, R, RI } },
+#endif /* TCG_TARGET_REG_BITS == 64 */
+
+#if TCG_TARGET_REG_BITS == 32
+    /* TODO: Support R, R, R, R, RI, RI? Will it be faster? */
+    { INDEX_op_add2_i32, { R, R, R, R, R, R } },
+    { INDEX_op_sub2_i32, { R, R, R, R, R, R } },
+    { INDEX_op_brcond2_i32, { R, R, RI, RI } },
+    { INDEX_op_mulu2_i32, { R, R, R, R } },
+    { INDEX_op_setcond2_i32, { R, R, R, RI, RI } },
+#endif
+
+#if TCG_TARGET_HAS_not_i32
+    { INDEX_op_not_i32, { R, R } },
+#endif
+#if TCG_TARGET_HAS_neg_i32
+    { INDEX_op_neg_i32, { R, R } },
+#endif
+
+#if TCG_TARGET_REG_BITS == 64
+    { INDEX_op_ld8u_i64, { R, R } },
+    { INDEX_op_ld8s_i64, { R, R } },
+    { INDEX_op_ld16u_i64, { R, R } },
+    { INDEX_op_ld16s_i64, { R, R } },
+    { INDEX_op_ld32u_i64, { R, R } },
+    { INDEX_op_ld32s_i64, { R, R } },
+    { INDEX_op_ld_i64, { R, R } },
+
+    { INDEX_op_st8_i64, { R, R } },
+    { INDEX_op_st16_i64, { R, R } },
+    { INDEX_op_st32_i64, { R, R } },
+    { INDEX_op_st_i64, { R, R } },
+
+    { INDEX_op_add_i64, { R, RI, RI } },
+    { INDEX_op_sub_i64, { R, RI, RI } },
+    { INDEX_op_mul_i64, { R, RI, RI } },
+#if TCG_TARGET_HAS_div_i64
+    { INDEX_op_div_i64, { R, R, R } },
+    { INDEX_op_divu_i64, { R, R, R } },
+    { INDEX_op_rem_i64, { R, R, R } },
+    { INDEX_op_remu_i64, { R, R, R } },
+#elif TCG_TARGET_HAS_div2_i64
+    { INDEX_op_div2_i64, { R, R, "0", "1", R } },
+    { INDEX_op_divu2_i64, { R, R, "0", "1", R } },
+#endif
+    { INDEX_op_and_i64, { R, RI, RI } },
+#if TCG_TARGET_HAS_andc_i64
+    { INDEX_op_andc_i64, { R, RI, RI } },
+#endif
+#if TCG_TARGET_HAS_eqv_i64
+    { INDEX_op_eqv_i64, { R, RI, RI } },
+#endif
+#if TCG_TARGET_HAS_nand_i64
+    { INDEX_op_nand_i64, { R, RI, RI } },
+#endif
+#if TCG_TARGET_HAS_nor_i64
+    { INDEX_op_nor_i64, { R, RI, RI } },
+#endif
+    { INDEX_op_or_i64, { R, RI, RI } },
+#if TCG_TARGET_HAS_orc_i64
+    { INDEX_op_orc_i64, { R, RI, RI } },
+#endif
+    { INDEX_op_xor_i64, { R, RI, RI } },
+    { INDEX_op_shl_i64, { R, RI, RI } },
+    { INDEX_op_shr_i64, { R, RI, RI } },
+    { INDEX_op_sar_i64, { R, RI, RI } },
+#if TCG_TARGET_HAS_rot_i64
+    { INDEX_op_rotl_i64, { R, RI, RI } },
+    { INDEX_op_rotr_i64, { R, RI, RI } },
+#endif
+#if TCG_TARGET_HAS_deposit_i64
+    { INDEX_op_deposit_i64, { R, "0", R } },
+#endif
+    { INDEX_op_brcond_i64, { R, RI } },
+
+#if TCG_TARGET_HAS_ext8s_i64
+    { INDEX_op_ext8s_i64, { R, R } },
+#endif
+#if TCG_TARGET_HAS_ext16s_i64
+    { INDEX_op_ext16s_i64, { R, R } },
+#endif
+#if TCG_TARGET_HAS_ext32s_i64
+    { INDEX_op_ext32s_i64, { R, R } },
+#endif
+#if TCG_TARGET_HAS_ext8u_i64
+    { INDEX_op_ext8u_i64, { R, R } },
+#endif
+#if TCG_TARGET_HAS_ext16u_i64
+    { INDEX_op_ext16u_i64, { R, R } },
+#endif
+#if TCG_TARGET_HAS_ext32u_i64
+    { INDEX_op_ext32u_i64, { R, R } },
+#endif
+#if TCG_TARGET_HAS_bswap16_i64
+    { INDEX_op_bswap16_i64, { R, R } },
+#endif
+#if TCG_TARGET_HAS_bswap32_i64
+    { INDEX_op_bswap32_i64, { R, R } },
+#endif
+#if TCG_TARGET_HAS_bswap64_i64
+    { INDEX_op_bswap64_i64, { R, R } },
+#endif
+#if TCG_TARGET_HAS_not_i64
+    { INDEX_op_not_i64, { R, R } },
+#endif
+#if TCG_TARGET_HAS_neg_i64
+    { INDEX_op_neg_i64, { R, R } },
+#endif
+#endif /* TCG_TARGET_REG_BITS == 64 */
+
+    { INDEX_op_qemu_ld_i32, { R, L } },
+    { INDEX_op_qemu_ld_i64, { R64, L } },
+
+    { INDEX_op_qemu_st_i32, { R, S } },
+    { INDEX_op_qemu_st_i64, { R64, S } },
+
+#if TCG_TARGET_HAS_ext8s_i32
+    { INDEX_op_ext8s_i32, { R, R } },
+#endif
+#if TCG_TARGET_HAS_ext16s_i32
+    { INDEX_op_ext16s_i32, { R, R } },
+#endif
+#if TCG_TARGET_HAS_ext8u_i32
+    { INDEX_op_ext8u_i32, { R, R } },
+#endif
+#if TCG_TARGET_HAS_ext16u_i32
+    { INDEX_op_ext16u_i32, { R, R } },
+#endif
+
+#if TCG_TARGET_HAS_bswap16_i32
+    { INDEX_op_bswap16_i32, { R, R } },
+#endif
+#if TCG_TARGET_HAS_bswap32_i32
+    { INDEX_op_bswap32_i32, { R, R } },
+#endif
+
+    { -1 },
+};
+
+static const int tcg_target_reg_alloc_order[] = {
+    TCG_REG_R0,
+    TCG_REG_R1,
+    TCG_REG_R2,
+    TCG_REG_R3,
+#if 0 /* used for TCG_REG_CALL_STACK */
+    TCG_REG_R4,
+#endif
+    TCG_REG_R5,
+    TCG_REG_R6,
+    TCG_REG_R7,
+#if TCG_TARGET_NB_REGS >= 16
+    TCG_REG_R8,
+    TCG_REG_R9,
+    TCG_REG_R10,
+    TCG_REG_R11,
+    TCG_REG_R12,
+    TCG_REG_R13,
+    TCG_REG_R14,
+    TCG_REG_R15,
+#endif
+};
+
+#if MAX_OPC_PARAM_IARGS != 5
+# error Fix needed, number of supported input arguments changed!
+#endif
+
+static const int tcg_target_call_iarg_regs[] = {
+    TCG_REG_R0,
+    TCG_REG_R1,
+    TCG_REG_R2,
+    TCG_REG_R3,
+#if 0 /* used for TCG_REG_CALL_STACK */
+    TCG_REG_R4,
+#endif
+    TCG_REG_R5,
+#if TCG_TARGET_REG_BITS == 32
+    /* 32 bit hosts need 2 * MAX_OPC_PARAM_IARGS registers. */
+    TCG_REG_R6,
+    TCG_REG_R7,
+#if TCG_TARGET_NB_REGS >= 16
+    TCG_REG_R8,
+    TCG_REG_R9,
+    TCG_REG_R10,
+#else
+# error Too few input registers available
+#endif
+#endif
+};
+
+static const int tcg_target_call_oarg_regs[] = {
+    TCG_REG_R0,
+#if TCG_TARGET_REG_BITS == 32
+    TCG_REG_R1
+#endif
+};
+
+#ifndef NDEBUG
+static const char *const tcg_target_reg_names[TCG_TARGET_NB_REGS] = {
+    "r00",
+    "r01",
+    "r02",
+    "r03",
+    "r04",
+    "r05",
+    "r06",
+    "r07",
+#if TCG_TARGET_NB_REGS >= 16
+    "r08",
+    "r09",
+    "r10",
+    "r11",
+    "r12",
+    "r13",
+    "r14",
+    "r15",
+#if TCG_TARGET_NB_REGS >= 32
+    "r16",
+    "r17",
+    "r18",
+    "r19",
+    "r20",
+    "r21",
+    "r22",
+    "r23",
+    "r24",
+    "r25",
+    "r26",
+    "r27",
+    "r28",
+    "r29",
+    "r30",
+    "r31"
+#endif
+#endif
+};
+#endif
+
+static void patch_reloc(tcg_insn_unit *code_ptr, int type,
+                        intptr_t value, intptr_t addend)
+{
+    /* tcg_out_reloc always uses the same type, addend. */
+    assert(type == sizeof(tcg_target_long));
+    assert(addend == 0);
+    assert(value != 0);
+    if (TCG_TARGET_REG_BITS == 32) {
+        tcg_patch32(code_ptr, value);
+    } else {
+        tcg_patch64(code_ptr, value);
+    }
+}
+
+/* Parse target specific constraints. */
+static int target_parse_constraint(TCGArgConstraint *ct, const char **pct_str)
+{
+    const char *ct_str = *pct_str;
+    switch (ct_str[0]) {
+    case 'r':
+    case 'L':                   /* qemu_ld constraint */
+    case 'S':                   /* qemu_st constraint */
+        ct->ct |= TCG_CT_REG;
+        tcg_regset_set32(ct->u.regs, 0, BIT(TCG_TARGET_NB_REGS) - 1);
+        break;
+    default:
+        return -1;
+    }
+    ct_str++;
+    *pct_str = ct_str;
+    return 0;
+}
+
+#if defined(CONFIG_DEBUG_TCG_INTERPRETER)
+/* Show current bytecode. Used by tcg interpreter. */
+void tci_disas(uint8_t opc)
+{
+    const TCGOpDef *def = &tcg_op_defs[opc];
+    fprintf(stderr, "TCG %s %u, %u, %u\n",
+            def->name, def->nb_oargs, def->nb_iargs, def->nb_cargs);
+}
+#endif
+
+/* Write value (native size). */
+static void tcg_out_i(TCGContext *s, tcg_target_ulong v)
+{
+    if (TCG_TARGET_REG_BITS == 32) {
+        tcg_out32(s, v);
+    } else {
+        tcg_out64(s, v);
+    }
+}
+
+/* Write opcode. */
+static void tcg_out_op_t(TCGContext *s, TCGOpcode op)
+{
+    tcg_out8(s, op);
+    tcg_out8(s, 0);
+}
+
+/* Write register. */
+static void tcg_out_r(TCGContext *s, TCGArg t0)
+{
+    assert(t0 < TCG_TARGET_NB_REGS);
+    tcg_out8(s, t0);
+}
+
+/* Write register or constant (native size). */
+static void tcg_out_ri(TCGContext *s, int const_arg, TCGArg arg)
+{
+    if (const_arg) {
+        assert(const_arg == 1);
+        tcg_out8(s, TCG_CONST);
+        tcg_out_i(s, arg);
+    } else {
+        tcg_out_r(s, arg);
+    }
+}
+
+/* Write register or constant (32 bit). */
+static void tcg_out_ri32(TCGContext *s, int const_arg, TCGArg arg)
+{
+    if (const_arg) {
+        assert(const_arg == 1);
+        tcg_out8(s, TCG_CONST);
+        tcg_out32(s, arg);
+    } else {
+        tcg_out_r(s, arg);
+    }
+}
+
+#if TCG_TARGET_REG_BITS == 64
+/* Write register or constant (64 bit). */
+static void tcg_out_ri64(TCGContext *s, int const_arg, TCGArg arg)
+{
+    if (const_arg) {
+        assert(const_arg == 1);
+        tcg_out8(s, TCG_CONST);
+        tcg_out64(s, arg);
+    } else {
+        tcg_out_r(s, arg);
+    }
+}
+#endif
+
+/* Write label. */
+static void tci_out_label(TCGContext *s, TCGLabel *label)
+{
+    if (label->has_value) {
+        tcg_out_i(s, label->u.value);
+        assert(label->u.value);
+    } else {
+        tcg_out_reloc(s, s->code_ptr, sizeof(tcg_target_ulong), label, 0);
+        s->code_ptr += sizeof(tcg_target_ulong);
+    }
+}
+
+static void tcg_out_ld(TCGContext *s, TCGType type, TCGReg ret, TCGReg arg1,
+                       intptr_t arg2)
+{
+    uint8_t *old_code_ptr = s->code_ptr;
+    if (type == TCG_TYPE_I32) {
+        tcg_out_op_t(s, INDEX_op_ld_i32);
+        tcg_out_r(s, ret);
+        tcg_out_r(s, arg1);
+        tcg_out32(s, arg2);
+    } else {
+        assert(type == TCG_TYPE_I64);
+#if TCG_TARGET_REG_BITS == 64
+        tcg_out_op_t(s, INDEX_op_ld_i64);
+        tcg_out_r(s, ret);
+        tcg_out_r(s, arg1);
+        assert(arg2 == (int32_t)arg2);
+        tcg_out32(s, arg2);
+#else
+        TODO();
+#endif
+    }
+    old_code_ptr[1] = s->code_ptr - old_code_ptr;
+}
+
+static void tcg_out_mov(TCGContext *s, TCGType type, TCGReg ret, TCGReg arg)
+{
+    uint8_t *old_code_ptr = s->code_ptr;
+    assert(ret != arg);
+#if TCG_TARGET_REG_BITS == 32
+    tcg_out_op_t(s, INDEX_op_mov_i32);
+#else
+    tcg_out_op_t(s, INDEX_op_mov_i64);
+#endif
+    tcg_out_r(s, ret);
+    tcg_out_r(s, arg);
+    old_code_ptr[1] = s->code_ptr - old_code_ptr;
+}
+
+static void tcg_out_movi(TCGContext *s, TCGType type,
+                         TCGReg t0, tcg_target_long arg)
+{
+    uint8_t *old_code_ptr = s->code_ptr;
+    uint32_t arg32 = arg;
+    if (type == TCG_TYPE_I32 || arg == arg32) {
+        tcg_out_op_t(s, INDEX_op_movi_i32);
+        tcg_out_r(s, t0);
+        tcg_out32(s, arg32);
+    } else {
+        assert(type == TCG_TYPE_I64);
+#if TCG_TARGET_REG_BITS == 64
+        tcg_out_op_t(s, INDEX_op_movi_i64);
+        tcg_out_r(s, t0);
+        tcg_out64(s, arg);
+#else
+        TODO();
+#endif
+    }
+    old_code_ptr[1] = s->code_ptr - old_code_ptr;
+}
+
+static inline void tcg_out_call(TCGContext *s, tcg_insn_unit *arg)
+{
+    uint8_t *old_code_ptr = s->code_ptr;
+    tcg_out_op_t(s, INDEX_op_call);
+    tcg_out_ri(s, 1, (uintptr_t)arg);
+    old_code_ptr[1] = s->code_ptr - old_code_ptr;
+}
+
+static void tcg_out_op(TCGContext *s, TCGOpcode opc, const TCGArg *args,
+                       const int *const_args)
+{
+    uint8_t *old_code_ptr = s->code_ptr;
+
+    tcg_out_op_t(s, opc);
+
+    switch (opc) {
+    case INDEX_op_exit_tb:
+        tcg_out64(s, args[0]);
+        break;
+    case INDEX_op_goto_tb:
+        if (s->tb_jmp_offset) {
+            /* Direct jump method. */
+            assert(args[0] < ARRAY_SIZE(s->tb_jmp_offset));
+            s->tb_jmp_offset[args[0]] = tcg_current_code_size(s);
+            tcg_out32(s, 0);
+        } else {
+            /* Indirect jump method. */
+            TODO();
+        }
+        assert(args[0] < ARRAY_SIZE(s->tb_next_offset));
+        s->tb_next_offset[args[0]] = tcg_current_code_size(s);
+        break;
+    case INDEX_op_br:
+        tci_out_label(s, arg_label(args[0]));
+        break;
+    case INDEX_op_setcond_i32:
+        tcg_out_r(s, args[0]);
+        tcg_out_r(s, args[1]);
+        tcg_out_ri32(s, const_args[2], args[2]);
+        tcg_out8(s, args[3]);   /* condition */
+        break;
+#if TCG_TARGET_REG_BITS == 32
+    case INDEX_op_setcond2_i32:
+        /* setcond2_i32 cond, t0, t1_low, t1_high, t2_low, t2_high */
+        tcg_out_r(s, args[0]);
+        tcg_out_r(s, args[1]);
+        tcg_out_r(s, args[2]);
+        tcg_out_ri32(s, const_args[3], args[3]);
+        tcg_out_ri32(s, const_args[4], args[4]);
+        tcg_out8(s, args[5]);   /* condition */
+        break;
+#elif TCG_TARGET_REG_BITS == 64
+    case INDEX_op_setcond_i64:
+        tcg_out_r(s, args[0]);
+        tcg_out_r(s, args[1]);
+        tcg_out_ri64(s, const_args[2], args[2]);
+        tcg_out8(s, args[3]);   /* condition */
+        break;
+#endif
+    case INDEX_op_ld8u_i32:
+    case INDEX_op_ld8s_i32:
+    case INDEX_op_ld16u_i32:
+    case INDEX_op_ld16s_i32:
+    case INDEX_op_ld_i32:
+    case INDEX_op_st8_i32:
+    case INDEX_op_st16_i32:
+    case INDEX_op_st_i32:
+    case INDEX_op_ld8u_i64:
+    case INDEX_op_ld8s_i64:
+    case INDEX_op_ld16u_i64:
+    case INDEX_op_ld16s_i64:
+    case INDEX_op_ld32u_i64:
+    case INDEX_op_ld32s_i64:
+    case INDEX_op_ld_i64:
+    case INDEX_op_st8_i64:
+    case INDEX_op_st16_i64:
+    case INDEX_op_st32_i64:
+    case INDEX_op_st_i64:
+        tcg_out_r(s, args[0]);
+        tcg_out_r(s, args[1]);
+        assert(args[2] == (int32_t)args[2]);
+        tcg_out32(s, args[2]);
+        break;
+    case INDEX_op_add_i32:
+    case INDEX_op_sub_i32:
+    case INDEX_op_mul_i32:
+    case INDEX_op_and_i32:
+    case INDEX_op_andc_i32:     /* Optional (TCG_TARGET_HAS_andc_i32). */
+    case INDEX_op_eqv_i32:      /* Optional (TCG_TARGET_HAS_eqv_i32). */
+    case INDEX_op_nand_i32:     /* Optional (TCG_TARGET_HAS_nand_i32). */
+    case INDEX_op_nor_i32:      /* Optional (TCG_TARGET_HAS_nor_i32). */
+    case INDEX_op_or_i32:
+    case INDEX_op_orc_i32:      /* Optional (TCG_TARGET_HAS_orc_i32). */
+    case INDEX_op_xor_i32:
+    case INDEX_op_shl_i32:
+    case INDEX_op_shr_i32:
+    case INDEX_op_sar_i32:
+    case INDEX_op_rotl_i32:     /* Optional (TCG_TARGET_HAS_rot_i32). */
+    case INDEX_op_rotr_i32:     /* Optional (TCG_TARGET_HAS_rot_i32). */
+        tcg_out_r(s, args[0]);
+        tcg_out_ri32(s, const_args[1], args[1]);
+        tcg_out_ri32(s, const_args[2], args[2]);
+        break;
+    case INDEX_op_deposit_i32:  /* Optional (TCG_TARGET_HAS_deposit_i32). */
+        tcg_out_r(s, args[0]);
+        tcg_out_r(s, args[1]);
+        tcg_out_r(s, args[2]);
+        assert(args[3] <= UINT8_MAX);
+        tcg_out8(s, args[3]);
+        assert(args[4] <= UINT8_MAX);
+        tcg_out8(s, args[4]);
+        break;
+
+#if TCG_TARGET_REG_BITS == 64
+    case INDEX_op_add_i64:
+    case INDEX_op_sub_i64:
+    case INDEX_op_mul_i64:
+    case INDEX_op_and_i64:
+    case INDEX_op_andc_i64:     /* Optional (TCG_TARGET_HAS_andc_i64). */
+    case INDEX_op_eqv_i64:      /* Optional (TCG_TARGET_HAS_eqv_i64). */
+    case INDEX_op_nand_i64:     /* Optional (TCG_TARGET_HAS_nand_i64). */
+    case INDEX_op_nor_i64:      /* Optional (TCG_TARGET_HAS_nor_i64). */
+    case INDEX_op_or_i64:
+    case INDEX_op_orc_i64:      /* Optional (TCG_TARGET_HAS_orc_i64). */
+    case INDEX_op_xor_i64:
+    case INDEX_op_shl_i64:
+    case INDEX_op_shr_i64:
+    case INDEX_op_sar_i64:
+    case INDEX_op_rotl_i64:     /* Optional (TCG_TARGET_HAS_rot_i64). */
+    case INDEX_op_rotr_i64:     /* Optional (TCG_TARGET_HAS_rot_i64). */
+        tcg_out_r(s, args[0]);
+        tcg_out_ri64(s, const_args[1], args[1]);
+        tcg_out_ri64(s, const_args[2], args[2]);
+        break;
+    case INDEX_op_deposit_i64:  /* Optional (TCG_TARGET_HAS_deposit_i64). */
+        tcg_out_r(s, args[0]);
+        tcg_out_r(s, args[1]);
+        tcg_out_r(s, args[2]);
+        assert(args[3] <= UINT8_MAX);
+        tcg_out8(s, args[3]);
+        assert(args[4] <= UINT8_MAX);
+        tcg_out8(s, args[4]);
+        break;
+    case INDEX_op_div_i64:      /* Optional (TCG_TARGET_HAS_div_i64). */
+    case INDEX_op_divu_i64:     /* Optional (TCG_TARGET_HAS_div_i64). */
+    case INDEX_op_rem_i64:      /* Optional (TCG_TARGET_HAS_div_i64). */
+    case INDEX_op_remu_i64:     /* Optional (TCG_TARGET_HAS_div_i64). */
+        TODO();
+        break;
+    case INDEX_op_div2_i64:     /* Optional (TCG_TARGET_HAS_div2_i64). */
+    case INDEX_op_divu2_i64:    /* Optional (TCG_TARGET_HAS_div2_i64). */
+        TODO();
+        break;
+    case INDEX_op_brcond_i64:
+        tcg_out_r(s, args[0]);
+        tcg_out_ri64(s, const_args[1], args[1]);
+        tcg_out8(s, args[2]);           /* condition */
+        tci_out_label(s, arg_label(args[3]));
+        break;
+    case INDEX_op_bswap16_i64:  /* Optional (TCG_TARGET_HAS_bswap16_i64). */
+    case INDEX_op_bswap32_i64:  /* Optional (TCG_TARGET_HAS_bswap32_i64). */
+    case INDEX_op_bswap64_i64:  /* Optional (TCG_TARGET_HAS_bswap64_i64). */
+    case INDEX_op_not_i64:      /* Optional (TCG_TARGET_HAS_not_i64). */
+    case INDEX_op_neg_i64:      /* Optional (TCG_TARGET_HAS_neg_i64). */
+    case INDEX_op_ext8s_i64:    /* Optional (TCG_TARGET_HAS_ext8s_i64). */
+    case INDEX_op_ext8u_i64:    /* Optional (TCG_TARGET_HAS_ext8u_i64). */
+    case INDEX_op_ext16s_i64:   /* Optional (TCG_TARGET_HAS_ext16s_i64). */
+    case INDEX_op_ext16u_i64:   /* Optional (TCG_TARGET_HAS_ext16u_i64). */
+    case INDEX_op_ext32s_i64:   /* Optional (TCG_TARGET_HAS_ext32s_i64). */
+    case INDEX_op_ext32u_i64:   /* Optional (TCG_TARGET_HAS_ext32u_i64). */
+#endif /* TCG_TARGET_REG_BITS == 64 */
+    case INDEX_op_neg_i32:      /* Optional (TCG_TARGET_HAS_neg_i32). */
+    case INDEX_op_not_i32:      /* Optional (TCG_TARGET_HAS_not_i32). */
+    case INDEX_op_ext8s_i32:    /* Optional (TCG_TARGET_HAS_ext8s_i32). */
+    case INDEX_op_ext16s_i32:   /* Optional (TCG_TARGET_HAS_ext16s_i32). */
+    case INDEX_op_ext8u_i32:    /* Optional (TCG_TARGET_HAS_ext8u_i32). */
+    case INDEX_op_ext16u_i32:   /* Optional (TCG_TARGET_HAS_ext16u_i32). */
+    case INDEX_op_bswap16_i32:  /* Optional (TCG_TARGET_HAS_bswap16_i32). */
+    case INDEX_op_bswap32_i32:  /* Optional (TCG_TARGET_HAS_bswap32_i32). */
+        tcg_out_r(s, args[0]);
+        tcg_out_r(s, args[1]);
+        break;
+    case INDEX_op_div_i32:      /* Optional (TCG_TARGET_HAS_div_i32). */
+    case INDEX_op_divu_i32:     /* Optional (TCG_TARGET_HAS_div_i32). */
+    case INDEX_op_rem_i32:      /* Optional (TCG_TARGET_HAS_div_i32). */
+    case INDEX_op_remu_i32:     /* Optional (TCG_TARGET_HAS_div_i32). */
+        tcg_out_r(s, args[0]);
+        tcg_out_ri32(s, const_args[1], args[1]);
+        tcg_out_ri32(s, const_args[2], args[2]);
+        break;
+    case INDEX_op_div2_i32:     /* Optional (TCG_TARGET_HAS_div2_i32). */
+    case INDEX_op_divu2_i32:    /* Optional (TCG_TARGET_HAS_div2_i32). */
+        TODO();
+        break;
+#if TCG_TARGET_REG_BITS == 32
+    case INDEX_op_add2_i32:
+    case INDEX_op_sub2_i32:
+        tcg_out_r(s, args[0]);
+        tcg_out_r(s, args[1]);
+        tcg_out_r(s, args[2]);
+        tcg_out_r(s, args[3]);
+        tcg_out_r(s, args[4]);
+        tcg_out_r(s, args[5]);
+        break;
+    case INDEX_op_brcond2_i32:
+        tcg_out_r(s, args[0]);
+        tcg_out_r(s, args[1]);
+        tcg_out_ri32(s, const_args[2], args[2]);
+        tcg_out_ri32(s, const_args[3], args[3]);
+        tcg_out8(s, args[4]);           /* condition */
+        tci_out_label(s, arg_label(args[5]));
+        break;
+    case INDEX_op_mulu2_i32:
+        tcg_out_r(s, args[0]);
+        tcg_out_r(s, args[1]);
+        tcg_out_r(s, args[2]);
+        tcg_out_r(s, args[3]);
+        break;
+#endif
+    case INDEX_op_brcond_i32:
+        tcg_out_r(s, args[0]);
+        tcg_out_ri32(s, const_args[1], args[1]);
+        tcg_out8(s, args[2]);           /* condition */
+        tci_out_label(s, arg_label(args[3]));
+        break;
+    case INDEX_op_qemu_ld_i32:
+        tcg_out_r(s, *args++);
+        tcg_out_r(s, *args++);
+        if (TARGET_LONG_BITS > TCG_TARGET_REG_BITS) {
+            tcg_out_r(s, *args++);
+        }
+        tcg_out_i(s, *args++);
+        break;
+    case INDEX_op_qemu_ld_i64:
+        tcg_out_r(s, *args++);
+        if (TCG_TARGET_REG_BITS == 32) {
+            tcg_out_r(s, *args++);
+        }
+        tcg_out_r(s, *args++);
+        if (TARGET_LONG_BITS > TCG_TARGET_REG_BITS) {
+            tcg_out_r(s, *args++);
+        }
+        tcg_out_i(s, *args++);
+        break;
+    case INDEX_op_qemu_st_i32:
+        tcg_out_r(s, *args++);
+        tcg_out_r(s, *args++);
+        if (TARGET_LONG_BITS > TCG_TARGET_REG_BITS) {
+            tcg_out_r(s, *args++);
+        }
+        tcg_out_i(s, *args++);
+        break;
+    case INDEX_op_qemu_st_i64:
+        tcg_out_r(s, *args++);
+        if (TCG_TARGET_REG_BITS == 32) {
+            tcg_out_r(s, *args++);
+        }
+        tcg_out_r(s, *args++);
+        if (TARGET_LONG_BITS > TCG_TARGET_REG_BITS) {
+            tcg_out_r(s, *args++);
+        }
+        tcg_out_i(s, *args++);
+        break;
+    case INDEX_op_mov_i32:  /* Always emitted via tcg_out_mov.  */
+    case INDEX_op_mov_i64:
+    case INDEX_op_movi_i32: /* Always emitted via tcg_out_movi.  */
+    case INDEX_op_movi_i64:
+    case INDEX_op_call:     /* Always emitted via tcg_out_call.  */
+    default:
+        tcg_abort();
+    }
+    old_code_ptr[1] = s->code_ptr - old_code_ptr;
+}
+
+static void tcg_out_st(TCGContext *s, TCGType type, TCGReg arg, TCGReg arg1,
+                       intptr_t arg2)
+{
+    uint8_t *old_code_ptr = s->code_ptr;
+    if (type == TCG_TYPE_I32) {
+        tcg_out_op_t(s, INDEX_op_st_i32);
+        tcg_out_r(s, arg);
+        tcg_out_r(s, arg1);
+        tcg_out32(s, arg2);
+    } else {
+        assert(type == TCG_TYPE_I64);
+#if TCG_TARGET_REG_BITS == 64
+        tcg_out_op_t(s, INDEX_op_st_i64);
+        tcg_out_r(s, arg);
+        tcg_out_r(s, arg1);
+        tcg_out32(s, arg2);
+#else
+        TODO();
+#endif
+    }
+    old_code_ptr[1] = s->code_ptr - old_code_ptr;
+}
+
+/* Test if a constant matches the constraint. */
+static int tcg_target_const_match(tcg_target_long val, TCGType type,
+                                  const TCGArgConstraint *arg_ct)
+{
+    /* No need to return 0 or 1, 0 or != 0 is good enough. */
+    return arg_ct->ct & TCG_CT_CONST;
+}
+
+static void tcg_target_init(TCGContext *s)
+{
+#if defined(CONFIG_DEBUG_TCG_INTERPRETER)
+    const char *envval = getenv("DEBUG_TCG");
+    if (envval) {
+        qemu_set_log(strtol(envval, NULL, 0));
+    }
+#endif
+
+    /* The current code uses uint8_t for tcg operations. */
+    assert(ARRAY_SIZE(tcg_op_defs) <= UINT8_MAX);
+
+    /* Registers available for 32 bit operations. */
+    tcg_regset_set32(tcg_target_available_regs[TCG_TYPE_I32], 0,
+                     BIT(TCG_TARGET_NB_REGS) - 1);
+    /* Registers available for 64 bit operations. */
+    tcg_regset_set32(tcg_target_available_regs[TCG_TYPE_I64], 0,
+                     BIT(TCG_TARGET_NB_REGS) - 1);
+    /* TODO: Which registers should be set here? */
+    tcg_regset_set32(tcg_target_call_clobber_regs, 0,
+                     BIT(TCG_TARGET_NB_REGS) - 1);
+
+    tcg_regset_clear(s->reserved_regs);
+    tcg_regset_set_reg(s->reserved_regs, TCG_REG_CALL_STACK);
+    tcg_add_target_add_op_defs(tcg_target_op_defs);
+
+    /* We use negative offsets from "sp" so that we can distinguish
+       stores that might pretend to be call arguments.  */
+    tcg_set_frame(s, TCG_REG_CALL_STACK,
+                  -CPU_TEMP_BUF_NLONGS * sizeof(long),
+                  CPU_TEMP_BUF_NLONGS * sizeof(long));
+}
+
+/* Generate global QEMU prologue and epilogue code. */
+static inline void tcg_target_qemu_prologue(TCGContext *s)
+{
+}
diff --git a/tcg/tci/tcg-target.h b/tcg/tci/tcg-target.h
new file mode 100644
index 00000000..cbf3f9b5
--- /dev/null
+++ b/tcg/tci/tcg-target.h
@@ -0,0 +1,185 @@
+/*
+ * Tiny Code Generator for QEMU
+ *
+ * Copyright (c) 2009, 2011 Stefan Weil
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (the "Software"), to deal
+ * in the Software without restriction, including without limitation the rights
+ * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+ * copies of the Software, and to permit persons to whom the Software is
+ * furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+ * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+ * THE SOFTWARE.
+ */
+
+/*
+ * This code implements a TCG which does not generate machine code for some
+ * real target machine but which generates virtual machine code for an
+ * interpreter. Interpreted pseudo code is slow, but it works on any host.
+ *
+ * Some remarks might help in understanding the code:
+ *
+ * "target" or "TCG target" is the machine which runs the generated code.
+ * This is different to the usual meaning in QEMU where "target" is the
+ * emulated machine. So normally QEMU host is identical to TCG target.
+ * Here the TCG target is a virtual machine, but this virtual machine must
+ * use the same word size like the real machine.
+ * Therefore, we need both 32 and 64 bit virtual machines (interpreter).
+ */
+
+#if !defined(TCG_TARGET_H)
+#define TCG_TARGET_H
+
+#include "config-host.h"
+
+#define TCG_TARGET_INTERPRETER 1
+#define TCG_TARGET_INSN_UNIT_SIZE 1
+#define TCG_TARGET_TLB_DISPLACEMENT_BITS 32
+
+#if UINTPTR_MAX == UINT32_MAX
+# define TCG_TARGET_REG_BITS 32
+#elif UINTPTR_MAX == UINT64_MAX
+# define TCG_TARGET_REG_BITS 64
+#else
+# error Unknown pointer size for tci target
+#endif
+
+#ifdef CONFIG_DEBUG_TCG
+/* Enable debug output. */
+#define CONFIG_DEBUG_TCG_INTERPRETER
+#endif
+
+/* Optional instructions. */
+
+#define TCG_TARGET_HAS_bswap16_i32      1
+#define TCG_TARGET_HAS_bswap32_i32      1
+#define TCG_TARGET_HAS_div_i32          1
+#define TCG_TARGET_HAS_rem_i32          1
+#define TCG_TARGET_HAS_ext8s_i32        1
+#define TCG_TARGET_HAS_ext16s_i32       1
+#define TCG_TARGET_HAS_ext8u_i32        1
+#define TCG_TARGET_HAS_ext16u_i32       1
+#define TCG_TARGET_HAS_andc_i32         0
+#define TCG_TARGET_HAS_deposit_i32      1
+#define TCG_TARGET_HAS_eqv_i32          0
+#define TCG_TARGET_HAS_nand_i32         0
+#define TCG_TARGET_HAS_nor_i32          0
+#define TCG_TARGET_HAS_neg_i32          1
+#define TCG_TARGET_HAS_not_i32          1
+#define TCG_TARGET_HAS_orc_i32          0
+#define TCG_TARGET_HAS_rot_i32          1
+#define TCG_TARGET_HAS_movcond_i32      0
+#define TCG_TARGET_HAS_muls2_i32        0
+#define TCG_TARGET_HAS_muluh_i32        0
+#define TCG_TARGET_HAS_mulsh_i32        0
+
+#if TCG_TARGET_REG_BITS == 64
+#define TCG_TARGET_HAS_trunc_shr_i32    0
+#define TCG_TARGET_HAS_bswap16_i64      1
+#define TCG_TARGET_HAS_bswap32_i64      1
+#define TCG_TARGET_HAS_bswap64_i64      1
+#define TCG_TARGET_HAS_deposit_i64      1
+#define TCG_TARGET_HAS_div_i64          0
+#define TCG_TARGET_HAS_rem_i64          0
+#define TCG_TARGET_HAS_ext8s_i64        1
+#define TCG_TARGET_HAS_ext16s_i64       1
+#define TCG_TARGET_HAS_ext32s_i64       1
+#define TCG_TARGET_HAS_ext8u_i64        1
+#define TCG_TARGET_HAS_ext16u_i64       1
+#define TCG_TARGET_HAS_ext32u_i64       1
+#define TCG_TARGET_HAS_andc_i64         0
+#define TCG_TARGET_HAS_eqv_i64          0
+#define TCG_TARGET_HAS_nand_i64         0
+#define TCG_TARGET_HAS_nor_i64          0
+#define TCG_TARGET_HAS_neg_i64          1
+#define TCG_TARGET_HAS_not_i64          1
+#define TCG_TARGET_HAS_orc_i64          0
+#define TCG_TARGET_HAS_rot_i64          1
+#define TCG_TARGET_HAS_movcond_i64      0
+#define TCG_TARGET_HAS_muls2_i64        0
+#define TCG_TARGET_HAS_add2_i32         0
+#define TCG_TARGET_HAS_sub2_i32         0
+#define TCG_TARGET_HAS_mulu2_i32        0
+#define TCG_TARGET_HAS_add2_i64         0
+#define TCG_TARGET_HAS_sub2_i64         0
+#define TCG_TARGET_HAS_mulu2_i64        0
+#define TCG_TARGET_HAS_muluh_i64        0
+#define TCG_TARGET_HAS_mulsh_i64        0
+#else
+#define TCG_TARGET_HAS_mulu2_i32        1
+#endif /* TCG_TARGET_REG_BITS == 64 */
+
+/* Number of registers available.
+   For 32 bit hosts, we need more than 8 registers (call arguments). */
+/* #define TCG_TARGET_NB_REGS 8 */
+#define TCG_TARGET_NB_REGS 16
+/* #define TCG_TARGET_NB_REGS 32 */
+
+/* List of registers which are used by TCG. */
+typedef enum {
+    TCG_REG_R0 = 0,
+    TCG_REG_R1,
+    TCG_REG_R2,
+    TCG_REG_R3,
+    TCG_REG_R4,
+    TCG_REG_R5,
+    TCG_REG_R6,
+    TCG_REG_R7,
+#if TCG_TARGET_NB_REGS >= 16
+    TCG_REG_R8,
+    TCG_REG_R9,
+    TCG_REG_R10,
+    TCG_REG_R11,
+    TCG_REG_R12,
+    TCG_REG_R13,
+    TCG_REG_R14,
+    TCG_REG_R15,
+#if TCG_TARGET_NB_REGS >= 32
+    TCG_REG_R16,
+    TCG_REG_R17,
+    TCG_REG_R18,
+    TCG_REG_R19,
+    TCG_REG_R20,
+    TCG_REG_R21,
+    TCG_REG_R22,
+    TCG_REG_R23,
+    TCG_REG_R24,
+    TCG_REG_R25,
+    TCG_REG_R26,
+    TCG_REG_R27,
+    TCG_REG_R28,
+    TCG_REG_R29,
+    TCG_REG_R30,
+    TCG_REG_R31,
+#endif
+#endif
+    /* Special value UINT8_MAX is used by TCI to encode constant values. */
+    TCG_CONST = UINT8_MAX
+} TCGReg;
+
+#define TCG_AREG0                       (TCG_TARGET_NB_REGS - 2)
+
+/* Used for function call generation. */
+#define TCG_REG_CALL_STACK              (TCG_TARGET_NB_REGS - 1)
+#define TCG_TARGET_CALL_STACK_OFFSET    0
+#define TCG_TARGET_STACK_ALIGN          16
+
+void tci_disas(uint8_t opc);
+
+#define HAVE_TCG_QEMU_TB_EXEC
+
+static inline void flush_icache_range(uintptr_t start, uintptr_t stop)
+{
+}
+
+#endif /* TCG_TARGET_H */