Merge tag 'v1.9.3'

Introduction of ports subdirectory where all ports are moved to

The main change in this release is the introduction of a "ports/"
subdirectory at the top-level of the repository, and all of the ports are
moved here.  In the process the "stmhal" port is renamed to "stm32" to
better reflect the MCU that it targets.  In addition, the STM32 CMSIS and
HAL sources are moved to a new submodule called "stm32lib".

The bytecode has changed in this release, compared to the previous release,
and as a consequence the .mpy version number has increased to version 3.
This means that scripts compiled with the previous mpy-cross must be
recompiled to work with this new version.

There have also been various enhancements and optimisations, such as:
check for valid UTF-8 when creating str objects, support for reverse
special binary operations like __radd__, full domain checking in the math
module, support for floor-division and modulo in the viper emitter,
and addition of stack overflow checking when executing a regex.

The stm32 port sees improved support for F7 MCUs, addition of a new board
B_L475E_IOT01A based on the STM32L475, and support for the Wiznet W5500
chipset along with improved socket behaviour.

A detailed list of changes follows.

py core:
- objstr: startswith, endswith: check arg to be a string
- nlrx86,x64: replace #define of defined() with portable macro usage
- objtype: handle NotImplemented return from binary special methods
- objtype: mp_obj_class_lookup: improve debug logging
- map: remove unused new/free functions
- make m_malloc_fail() have void return type, since it doesn't return
- modstruct: in struct.pack, stop converting if there are no args left
- modstruct: check and prevent buffer-read overflow in struct unpacking
- modstruct: check and prevent buffer-write overflow in struct packing
- nlrthumb: get working again on standard Thumb arch (ie not Thumb2)
- objfloat: fix binary ops with incompatible objects
- obj: fix comparison of float/complex NaN with itself
- objtype: implement fallback for instance inplace special methods
- objtuple: properly implement comparison with incompatible types
- objstr: add check for valid UTF-8 when making a str from bytes
- objlist: properly implement comparison with incompatible types
- runtime0.h: move relational ops to the beginning of mp_binary_op_t
- runtime0.h: move MP_BINARY_OP_DIVMOD to the end of mp_binary_op_t
- objtype: make sure mp_binary_op_method_name has full size again
- runtime0.h: put inplace arith ops in front of normal operations
- builtinhelp: simplify code slightly by extracting object type
- runtime: implement dispatch for "reverse op" special methods
- nlrx86: fix building for Android/x86
- builtinhelp: change signature of help text var from pointer to array
- runtime.h: change empty mp_warning macro so var-args are non empty
- modbuiltins: implement abs() by dispatching to MP_UNARY_OP_ABS
- {objfloat,objcomplex}: optimise MP_UNARY_OP_ABS by reusing variables
- mpconfig.h: add note that using computed gotos in VM is not C99
- objstr: strip: don't strip "\0" by default
- objexcept: prevent infinite recursion when allocating exceptions
- stream: remove unnecessary checks for NULL return from vstr_add_len
- vstr: raise a RuntimeError if fixed vstr buffer overflows
- vm: use lowercase letter at start of exception message
- persistentcode: define mp_raw_code_save_file() for any unix target
- add config option to print warnings/errors to stderr
- objfloat: support raising a negative number to a fractional power
- objset: simplify set and frozenset by separating their locals dicts
- objset: check that RHS of a binary op is a set/frozenset
- objset: include the failed key in a KeyError raised from set.remove
- objtype: change type of enum-to-qstr table to uint16_t to save space
- objstr: make empty bytes object have a null-terminating byte
- mpprint: only check for null string printing when NDEBUG not defined
- objtype: clean up unary- and binary-op enum-to-qstr mapping tables
- persistentcode: bump .mpy version number to version 3
- bc: update opcode_format_table to match the bytecode
- modmath: add full checks for math domain errors
- modmath: convert log2 macro into a function
- formatfloat: don't print the negative sign of a NaN value
- formatfloat: use standard isinf, isnan funcs instead of custom ones
- modbuiltins: use existing utf8_get_char helper in builtin ord func
- emitnative: implement floor-division and modulo for viper emitter
- objtype: use CPython compatible method name for sizeof
- objtype: fit qstrs for special methods in byte type
- objtype: define all special methods if requested
- objtype: introduce MICROPY_PY_ALL_INPLACE_SPECIAL_METHODS

extmod:
- modubinascii: only include uzlib/tinf.h when it's really needed
- modussl_mbedtls: allow to compile with MBEDTLS_DEBUG_C disabled
- machine_pinbase: put PinBase singleton in ROM
- re1.5: upgrade to v0.8.2, adds hook for stack overflow checking
- modure: add stack overflow checking when executing a regex
- uos_dupterm: update uos.dupterm() and helper funcs to have index
- uos_dupterm: swallow any errors from dupterm closing the stream
- vfs: replace VLA in proxy func with small, static sized array
- modussl: add finaliser support for ussl objects
- modussl_mbedtls: allow to compile with unix coverage build

lib:
- add new submodule, stm32lib containing STM32 CMSIS and HAL source
- embed/abort_: use mp_raise_msg helper function
- libm: fix tanhf so that it correctly handles +/- infinity args
- libm: remove implementation of log2f, use MP_NEED_LOG2 instead
- axtls: update, support for SSL_EAGAIN return code
- berkeley-db-1.xx: update, allow to override MINCACHE, DEFPSIZE

drivers:
- memory/spiflash: change from hard-coded soft SPI to generic SPI
- display/ssd1306.py: improve performance of graphics methods
- nrf24l01: make nRF24L01 test script more portable
- display/ssd1306: implement SSD1306_I2C poweron method
- display/ssd1306: make poweron() work the same with SSD1306_SPI
- wiznet5k: improve the performance of socket ops with threading
- wiznet5k: get low-level W5500 driver working

tools:
- upip: upgrade to 1.2.2
- pyboard: use repr() when quoting data in error messages
- pyboard: update docstring for additional device support

tests:
- object_new: better messages, check user __new__() method
- class_new: add checks for __init__ being called and other improvements
- class_new: add another testcase for __new__/__init__ interaction
- class_inplace_op: test for inplace op fallback to normal one
- run-bench-tests: update locations of executables, now in ports/
- class_reverse_op: test for reverse arith ops special methods
- run-tests: skip class_inplace_op for minimal profile
- run-tests: fix copy-paste mistake in var name
- cpydiff: add cases for locals() discrepancies
- extmod: add test for ure regexes leading to infinite recursion
- extmod: add test for '-' in character class in regex
- run-tests: close device under test using "finally"
- net_inet: update tls test to work with CPython and incl new site

unix port:
- rename modsocket.c to modusocket.c
- modusocket: remove #if MICROPY_SOCKET_EXTRA code blocks
- enable MICROPY_PY_REVERSE_SPECIAL_METHODS

stm32 port:
- modmachine: make machine.bootloader() work when MPU is enabled
- modmachine: improve support for sleep/deepsleep on F7 MCUs
- compute PLL freq table during build instead of at run time
- modmachine: for F7 MCU, save power by reducing internal volt reg
- boards/pllvalues.py: make script work with both Python 2 and 3
- Makefile: use lib/stm32lib instead of local cmsis and hal files
- remove cmsis and hal files, they are now a submodule
- Makefile: automatically fetch stm32lib submodule if needed
- update to new STM Cube HAL library
- fix clock initialisation of L4 MCUs
- rename stmhal port directory to stm32
- remove unused usbd_msc.c file
- boards: change remaining stm32f4xx_hal_conf.h to unix line ending
- boards: change linker scripts to use "K" instead of hex byte size
- boards: fix I2C1 pin mapping on NUCLEO_F401RE/F411RE boards
- i2c: when scanning for I2C devices only do 1 probe per address
- modnwwiznet5k: release the GIL on blocking network operations
- boards: add new board B_L475E_IOT01A based on STM32L475
- make-stmconst.py: make sure mpz const data lives in ROM
- timer: make pyb.Timer() instances persistent
- mpconfigport.h: add configuration for max periphs on L4 series
- usbdev: make the USBD callback struct const so it can go in ROM
- usbdev: change static function variable to non-static
- usbdev: put all CDC state in a struct
- usbdev: put all HID state in a struct
- usbdev: simplify CDC tx/rx buffer passing
- usbdev: simplify HID tx/rx buffer passing
- usbdev/core: add state parameter to all callback functions
- usbdev: put all state for the USB device driver in a struct
- usbdev: simplify pointers to MSC state and block dev operations
- usbdev: merge all global USB device state into a single struct
- usbdev: make device descriptor callbacks take a state pointer
- usbdev: move all the USB device descriptor state into its struct
- timer: enable ARPE so that timer freq can be changed smoothly
- modnwwiznet5k: get the IP address of an established socket
- boards: fix typos in stm32f767_af.csv table
- usbd_cdc_interface: don't reset CDC output buf on initialisation
- modnwwiznet5k: implement WIZNET5K.isconnected() method
- modusocket: make getaddrinfo() work when passed an IP address
- modusocket: return OSError(-2) if getaddrinfo fails
- mpconfigport.h: add MICROPY_THREAD_YIELD() macro
- modnwwiznet5k: add support for W5500 Ethernet chip
- modnwwiznet5k: increase SPI bus speed to 42MHz
- modnwwiznet5k: implement stream ioctl for the Wiznet driver
- mphalport: improve efficiency of mp_hal_stdout_tx_strn_cooked
- make uos.dupterm() conform to specs by using extmod version

cc3200 port:
- enable micropython.kbd_intr() method
- use standard implementation of keyboard interrupt

esp8266 port:
- rename axtls_helpers.c to posix_helpers.c
- posix_helpers: set ENOMEM on memory alloc failure
- set DEFPSIZE=1024, MINCACHE=3 for "btree" module
- esp_mphal: send data in chunks to mp_uos_dupterm_tx_strn
- modnetwork: add "bssid" keyword arg to WLAN.connect() method
- modules/webrepl_setup: add info about allowed password length

zephyr port:
- Makefile: revamp "test" target after ports were moved to ports/
- use CONFIG_NET_APP_SETTINGS to setup initial network addresses
- switch to interrupt-driven pull-style console

pic16bit port:
- add definition of SEEK_SET to unistd.h

docs:
- pyboard/tutorial: add "timeout=0" to UART in pass-through example
- more xrefs to "MicroPython port" in glossary
- library/network: fix ref to "socket" module (should be "usocket")
- machine.Signal: improve style/grammar and add usage example
- library: add description of "index" parameter to uos.dupterm()
- library/micropython: fix typo in RST formatting
- library/framebuf.rst: generalise constructor to all colour formats
- btree: describe page caching policy of the underlying implementation
- esp8266/tutorial: update neopixel with example of using 4 bbp
- library/network: clarify usage of "bssid" arg in connect() method
- pyboard/quickref: add info for Switch, RTC, CAN, Accel classes
- pyboard/tutorial: update now that yellow LED also supports PWM
- esp8266/quickref: add quickref info for RTC class
- library: add missing cross-ref links for classes in pyb module
- library/network: update docs to state that W5500 is supported
- uselect: document one-shot polling mode
- usocket: elaborate descriptions
- usocket: document inet_ntop(), inet_pton()
- library/network: add dhcp_hostname parameter
- reference/isr_rules: minor typo correction
- ussl: fix module name refs and use "MicroPython port" term
- esp8266/general: add section on TLS limitations
- usocket: document that settimeout() isn't supported by all ports
- ure: add "|" (alternative) to the list of supported operators
- reference/isr_rules.rst: add tutorial on use of micropython.schedule()

travis:
- use --upgrade when pip is installing cpp-coveralls
- update build command now that stm32 Wiznet config has changed

examples:
- hwconfig_console: add .on()/.off() methods

all:
- convert mp_uint_t to mp_unary_op_t/mp_binary_op_t where appropriate
- convert remaining "mp_uint_t n_args" to "size_t n_args"
- make new ports/ sub-directory and move all ports there
- update Makefiles and others to build with new ports/ dir layout
- remove inclusion of internal py header files
- use NULL instead of "" when calling mp_raise exception helpers

README:
- update "Dependencies" section
- add explicit section on contributing
- add gcc and arm-none-eabi-newlib to list of required components

.gitattributes:
- remove obsolete entries for stmhal/hal, stmhal/cmsis
- add entries for files that will move to ports/ dir

22 files changed, 223 insertions, 155 deletions

diff --git a/py/argcheck.c b/py/argcheck.c
index 46be126ac..2a606d613 100644
--- a/py/argcheck.c
+++ b/py/argcheck.c
@@ -136,11 +136,9 @@ void mp_arg_parse_all_kw_array(size_t n_pos, size_t n_kw, const mp_obj_t *args,
     mp_arg_parse_all(n_pos, args, &kw_args, n_allowed, allowed, out_vals);
 }
 
-#if MICROPY_ERROR_REPORTING == MICROPY_ERROR_REPORTING_TERSE || defined(_MSC_VER)
 NORETURN void mp_arg_error_terse_mismatch(void) {
     mp_raise_TypeError("argument num/types mismatch");
 }
-#endif
 
 #if MICROPY_CPYTHON_COMPAT
 NORETURN void mp_arg_error_unimpl_kw(void) {
diff --git a/py/bc.c b/py/bc.c
index 1f6819295..381daa24d 100644
--- a/py/bc.c
+++ b/py/bc.c
@@ -322,7 +322,7 @@ STATIC const byte opcode_format_table[64] = {
     OC4(O, O, U, U), // 0x38-0x3b
     OC4(U, O, B, O), // 0x3c-0x3f
     OC4(O, B, B, O), // 0x40-0x43
-    OC4(B, B, O, U), // 0x44-0x47
+    OC4(B, B, O, B), // 0x44-0x47
     OC4(U, U, U, U), // 0x48-0x4b
     OC4(U, U, U, U), // 0x4c-0x4f
     OC4(V, V, U, V), // 0x50-0x53
@@ -362,7 +362,7 @@ STATIC const byte opcode_format_table[64] = {
     OC4(B, B, B, B), // 0xcc-0xcf
 
     OC4(B, B, B, B), // 0xd0-0xd3
-    OC4(B, B, B, B), // 0xd4-0xd7
+    OC4(U, U, U, B), // 0xd4-0xd7
     OC4(B, B, B, B), // 0xd8-0xdb
     OC4(B, B, B, B), // 0xdc-0xdf
 
@@ -373,7 +373,7 @@ STATIC const byte opcode_format_table[64] = {
 
     OC4(B, B, B, B), // 0xf0-0xf3
     OC4(B, B, B, B), // 0xf4-0xf7
-    OC4(B, B, B, U), // 0xf8-0xfb
+    OC4(U, U, U, U), // 0xf8-0xfb
     OC4(U, U, U, U), // 0xfc-0xff
 };
 #undef OC4
diff --git a/py/bc0.h b/py/bc0.h
index 38e23c0fd..70acfb0ca 100644
--- a/py/bc0.h
+++ b/py/bc0.h
@@ -113,7 +113,7 @@
 #define MP_BC_LOAD_CONST_SMALL_INT_MULTI (0x70) // + N(64)
 #define MP_BC_LOAD_FAST_MULTI            (0xb0) // + N(16)
 #define MP_BC_STORE_FAST_MULTI           (0xc0) // + N(16)
-#define MP_BC_UNARY_OP_MULTI             (0xd0) // + op(<MP_UNARY_OP_NON_BYTECODE)
-#define MP_BC_BINARY_OP_MULTI            (0xd7) // + op(36)
+#define MP_BC_UNARY_OP_MULTI             (0xd0) // + op(<MP_UNARY_OP_NUM_BYTECODE)
+#define MP_BC_BINARY_OP_MULTI            (0xd7) // + op(<MP_BINARY_OP_NUM_BYTECODE)
 
 #endif // MICROPY_INCLUDED_PY_BC0_H
diff --git a/py/emitnative.c b/py/emitnative.c
index b2c9a7366..8e97dda11 100644
--- a/py/emitnative.c
+++ b/py/emitnative.c
@@ -123,6 +123,8 @@ STATIC byte mp_f_n_args[MP_F_NUMBER_OF] = {
     [MP_F_NEW_CELL] = 1,
     [MP_F_MAKE_CLOSURE_FROM_RAW_CODE] = 3,
     [MP_F_SETUP_CODE_STATE] = 5,
+    [MP_F_SMALL_INT_FLOOR_DIVIDE] = 2,
+    [MP_F_SMALL_INT_MODULO] = 2,
 };
 
 #include "py/asmx86.h"
@@ -1823,18 +1825,20 @@ STATIC void emit_native_binary_op(emit_t *emit, mp_binary_op_t op) {
     vtype_kind_t vtype_lhs = peek_vtype(emit, 1);
     vtype_kind_t vtype_rhs = peek_vtype(emit, 0);
     if (vtype_lhs == VTYPE_INT && vtype_rhs == VTYPE_INT) {
+        // for integers, inplace and normal ops are equivalent, so use just normal ops
+        if (MP_BINARY_OP_INPLACE_OR <= op && op <= MP_BINARY_OP_INPLACE_POWER) {
+            op += MP_BINARY_OP_OR - MP_BINARY_OP_INPLACE_OR;
+        }
+
         #if N_X64 || N_X86
         // special cases for x86 and shifting
-        if (op == MP_BINARY_OP_LSHIFT
-            || op == MP_BINARY_OP_INPLACE_LSHIFT
-            || op == MP_BINARY_OP_RSHIFT
-            || op == MP_BINARY_OP_INPLACE_RSHIFT) {
+        if (op == MP_BINARY_OP_LSHIFT || op == MP_BINARY_OP_RSHIFT) {
             #if N_X64
             emit_pre_pop_reg_reg(emit, &vtype_rhs, ASM_X64_REG_RCX, &vtype_lhs, REG_RET);
             #else
             emit_pre_pop_reg_reg(emit, &vtype_rhs, ASM_X86_REG_ECX, &vtype_lhs, REG_RET);
             #endif
-            if (op == MP_BINARY_OP_LSHIFT || op == MP_BINARY_OP_INPLACE_LSHIFT) {
+            if (op == MP_BINARY_OP_LSHIFT) {
                 ASM_LSL_REG(emit->as, REG_RET);
             } else {
                 ASM_ASR_REG(emit->as, REG_RET);
@@ -1843,35 +1847,48 @@ STATIC void emit_native_binary_op(emit_t *emit, mp_binary_op_t op) {
             return;
         }
         #endif
+
+        // special cases for floor-divide and module because we dispatch to helper functions
+        if (op == MP_BINARY_OP_FLOOR_DIVIDE || op == MP_BINARY_OP_MODULO) {
+            emit_pre_pop_reg_reg(emit, &vtype_rhs, REG_ARG_2, &vtype_lhs, REG_ARG_1);
+            if (op == MP_BINARY_OP_FLOOR_DIVIDE) {
+                emit_call(emit, MP_F_SMALL_INT_FLOOR_DIVIDE);
+            } else {
+                emit_call(emit, MP_F_SMALL_INT_MODULO);
+            }
+            emit_post_push_reg(emit, VTYPE_INT, REG_RET);
+            return;
+        }
+
         int reg_rhs = REG_ARG_3;
         emit_pre_pop_reg_flexible(emit, &vtype_rhs, &reg_rhs, REG_RET, REG_ARG_2);
         emit_pre_pop_reg(emit, &vtype_lhs, REG_ARG_2);
         if (0) {
             // dummy
         #if !(N_X64 || N_X86)
-        } else if (op == MP_BINARY_OP_LSHIFT || op == MP_BINARY_OP_INPLACE_LSHIFT) {
+        } else if (op == MP_BINARY_OP_LSHIFT) {
             ASM_LSL_REG_REG(emit->as, REG_ARG_2, reg_rhs);
             emit_post_push_reg(emit, VTYPE_INT, REG_ARG_2);
-        } else if (op == MP_BINARY_OP_RSHIFT || op == MP_BINARY_OP_INPLACE_RSHIFT) {
+        } else if (op == MP_BINARY_OP_RSHIFT) {
             ASM_ASR_REG_REG(emit->as, REG_ARG_2, reg_rhs);
             emit_post_push_reg(emit, VTYPE_INT, REG_ARG_2);
         #endif
-        } else if (op == MP_BINARY_OP_OR || op == MP_BINARY_OP_INPLACE_OR) {
+        } else if (op == MP_BINARY_OP_OR) {
             ASM_OR_REG_REG(emit->as, REG_ARG_2, reg_rhs);
             emit_post_push_reg(emit, VTYPE_INT, REG_ARG_2);
-        } else if (op == MP_BINARY_OP_XOR || op == MP_BINARY_OP_INPLACE_XOR) {
+        } else if (op == MP_BINARY_OP_XOR) {
             ASM_XOR_REG_REG(emit->as, REG_ARG_2, reg_rhs);
             emit_post_push_reg(emit, VTYPE_INT, REG_ARG_2);
-        } else if (op == MP_BINARY_OP_AND || op == MP_BINARY_OP_INPLACE_AND) {
+        } else if (op == MP_BINARY_OP_AND) {
             ASM_AND_REG_REG(emit->as, REG_ARG_2, reg_rhs);
             emit_post_push_reg(emit, VTYPE_INT, REG_ARG_2);
-        } else if (op == MP_BINARY_OP_ADD || op == MP_BINARY_OP_INPLACE_ADD) {
+        } else if (op == MP_BINARY_OP_ADD) {
             ASM_ADD_REG_REG(emit->as, REG_ARG_2, reg_rhs);
             emit_post_push_reg(emit, VTYPE_INT, REG_ARG_2);
-        } else if (op == MP_BINARY_OP_SUBTRACT || op == MP_BINARY_OP_INPLACE_SUBTRACT) {
+        } else if (op == MP_BINARY_OP_SUBTRACT) {
             ASM_SUB_REG_REG(emit->as, REG_ARG_2, reg_rhs);
             emit_post_push_reg(emit, VTYPE_INT, REG_ARG_2);
-        } else if (op == MP_BINARY_OP_MULTIPLY || op == MP_BINARY_OP_INPLACE_MULTIPLY) {
+        } else if (op == MP_BINARY_OP_MULTIPLY) {
             ASM_MUL_REG_REG(emit->as, REG_ARG_2, reg_rhs);
             emit_post_push_reg(emit, VTYPE_INT, REG_ARG_2);
         } else if (MP_BINARY_OP_LESS <= op && op <= MP_BINARY_OP_NOT_EQUAL) {
diff --git a/py/formatfloat.c b/py/formatfloat.c
index 35cd5d51a..4228f99ff 100644
--- a/py/formatfloat.c
+++ b/py/formatfloat.c
@@ -30,6 +30,7 @@
 #include <assert.h>
 #include <stdlib.h>
 #include <stdint.h>
+#include <math.h>
 #include "py/formatfloat.h"
 
 /***********************************************************************
@@ -68,12 +69,10 @@ union floatbits {
     uint32_t u;
 };
 static inline int fp_signbit(float x) { union floatbits fb = {x}; return fb.u & FLT_SIGN_MASK; }
-static inline int fp_isspecial(float x) { union floatbits fb = {x}; return (fb.u & FLT_EXP_MASK) == FLT_EXP_MASK; }
-static inline int fp_isinf(float x) { union floatbits fb = {x}; return (fb.u & FLT_MAN_MASK) == 0; }
+#define fp_isnan(x) isnan(x)
+#define fp_isinf(x) isinf(x)
 static inline int fp_iszero(float x) { union floatbits fb = {x}; return fb.u == 0; }
 static inline int fp_isless1(float x) { union floatbits fb = {x}; return fb.u < 0x3f800000; }
-// Assumes both fp_isspecial() and fp_isinf() were applied before
-#define fp_isnan(x) 1
 
 #elif MICROPY_FLOAT_IMPL == MICROPY_FLOAT_IMPL_DOUBLE
 
@@ -82,9 +81,7 @@ static inline int fp_isless1(float x) { union floatbits fb = {x}; return fb.u <
 #define FPROUND_TO_ONE 0.999999999995
 #define FPDECEXP 256
 #define FPMIN_BUF_SIZE 7 // +9e+199
-#include <math.h>
 #define fp_signbit(x) signbit(x)
-#define fp_isspecial(x) 1
 #define fp_isnan(x) isnan(x)
 #define fp_isinf(x) isinf(x)
 #define fp_iszero(x) (x == 0)
@@ -122,7 +119,7 @@ int mp_format_float(FPTYPE f, char *buf, size_t buf_size, char fmt, int prec, ch
         }
         return buf_size >= 2;
     }
-    if (fp_signbit(f)) {
+    if (fp_signbit(f) && !fp_isnan(f)) {
         *s++ = '-';
         f = -f;
     } else {
@@ -135,7 +132,7 @@ int mp_format_float(FPTYPE f, char *buf, size_t buf_size, char fmt, int prec, ch
     // It is buf_size minus room for the sign and null byte.
     int buf_remaining = buf_size - 1 - (s - buf);
 
-    if (fp_isspecial(f)) {
+    {
         char uc = fmt & 0x20;
         if (fp_isinf(f)) {
             *s++ = 'I' ^ uc;
diff --git a/py/makeqstrdata.py b/py/makeqstrdata.py
index 7249769f4..38fde1a9c 100644
--- a/py/makeqstrdata.py
+++ b/py/makeqstrdata.py
@@ -108,7 +108,15 @@ def parse_input_headers(infiles):
                     continue
 
                 # add the qstr to the list, with order number to retain original order in file
-                qstrs[ident] = (len(qstrs), ident, qstr)
+                order = len(qstrs)
+                # but put special method names like __add__ at the top of list, so
+                # that their id's fit into a byte
+                if ident == "":
+                    # Sort empty qstr above all still
+                    order = -200000
+                elif ident.startswith("__"):
+                    order -= 100000
+                qstrs[ident] = (order, ident, qstr)
 
     if not qcfgs:
         sys.stderr.write("ERROR: Empty preprocessor output - check for errors above\n")
diff --git a/py/mkenv.mk b/py/mkenv.mk
index 507fa6eab..5a118854a 100644
--- a/py/mkenv.mk
+++ b/py/mkenv.mk
@@ -68,13 +68,7 @@ LD += -m32
 endif
 
 MAKE_FROZEN = $(TOP)/tools/make-frozen.py
-# allow mpy-cross (for WSL) and mpy-cross.exe (for cygwin) to coexist
-ifeq ($(OS),Windows_NT)
-MPY_CROSS = $(TOP)/mpy-cross/mpy-cross.exe
-PROG_EXT = .exe
-else
 MPY_CROSS = $(TOP)/mpy-cross/mpy-cross
-endif
 MPY_TOOL = $(TOP)/tools/mpy-tool.py
 
 all:
diff --git a/py/mkrules.mk b/py/mkrules.mk
index e26b94939..1d6f11fc9 100644
--- a/py/mkrules.mk
+++ b/py/mkrules.mk
@@ -144,13 +144,13 @@ $(PROG): $(OBJ)
 # we may want to compile using Thumb, but link with non-Thumb libc.
 	$(Q)$(CC) -o $@ $^ $(LIB) $(LDFLAGS)
 ifndef DEBUG
-	$(Q)$(STRIP) $(STRIPFLAGS_EXTRA) $(PROG)$(PROG_EXT)
+	$(Q)$(STRIP) $(STRIPFLAGS_EXTRA) $(PROG)
 endif
-	$(Q)$(SIZE) $$(find $(BUILD) -path "$(BUILD)/build/frozen*.o") $(PROG)$(PROG_EXT)
+	$(Q)$(SIZE) $$(find $(BUILD) -path "$(BUILD)/build/frozen*.o") $(PROG)
 
 clean: clean-prog
 clean-prog:
-	$(RM) -f $(PROG)$(PROG_EXT)
+	$(RM) -f $(PROG)
 	$(RM) -f $(PROG).map
 
 .PHONY: clean-prog
diff --git a/py/modbuiltins.c b/py/modbuiltins.c
index 991feda8c..728309292 100644
--- a/py/modbuiltins.c
+++ b/py/modbuiltins.c
@@ -348,31 +348,16 @@ STATIC mp_obj_t mp_builtin_ord(mp_obj_t o_in) {
     if (MP_OBJ_IS_STR(o_in)) {
         len = unichar_charlen(str, len);
         if (len == 1) {
-            if (!UTF8_IS_NONASCII(*str)) {
-                goto return_first_byte;
-            }
-            mp_int_t ord = *str++ & 0x7F;
-            for (mp_int_t mask = 0x40; ord & mask; mask >>= 1) {
-                ord &= ~mask;
-            }
-            while (UTF8_IS_CONT(*str)) {
-                ord = (ord << 6) | (*str++ & 0x3F);
-            }
-            return mp_obj_new_int(ord);
+            return mp_obj_new_int(utf8_get_char((const byte*)str));
         }
-    } else {
-        // a bytes object
+    } else
+    #endif
+    {
+        // a bytes object, or a str without unicode support (don't sign extend the char)
         if (len == 1) {
-        return_first_byte:
             return MP_OBJ_NEW_SMALL_INT(((const byte*)str)[0]);
         }
     }
-    #else
-    if (len == 1) {
-        // don't sign extend when converting to ord
-        return mp_obj_new_int(((const byte*)str)[0]);
-    }
-    #endif
 
     if (MICROPY_ERROR_REPORTING == MICROPY_ERROR_REPORTING_TERSE) {
         mp_raise_TypeError("ord expects a character");
diff --git a/py/modmath.c b/py/modmath.c
index 909780596..56ceb14bd 100644
--- a/py/modmath.c
+++ b/py/modmath.c
@@ -3,7 +3,7 @@
  *
  * The MIT License (MIT)
  *
- * Copyright (c) 2013, 2014 Damien P. George
+ * Copyright (c) 2013-2017 Damien P. George
  *
  * Permission is hereby granted, free of charge, to any person obtaining a copy
  * of this software and associated documentation files (the "Software"), to deal
@@ -40,14 +40,31 @@ STATIC NORETURN void math_error(void) {
     mp_raise_ValueError("math domain error");
 }
 
+STATIC mp_obj_t math_generic_1(mp_obj_t x_obj, mp_float_t (*f)(mp_float_t)) {
+    mp_float_t x = mp_obj_get_float(x_obj);
+    mp_float_t ans = f(x);
+    if ((isnan(ans) && !isnan(x)) || (isinf(ans) && !isinf(x))) {
+        math_error();
+    }
+    return mp_obj_new_float(ans);
+}
+
+STATIC mp_obj_t math_generic_2(mp_obj_t x_obj, mp_obj_t y_obj, mp_float_t (*f)(mp_float_t, mp_float_t)) {
+    mp_float_t x = mp_obj_get_float(x_obj);
+    mp_float_t y = mp_obj_get_float(y_obj);
+    mp_float_t ans = f(x, y);
+    if ((isnan(ans) && !isnan(x) && !isnan(y)) || (isinf(ans) && !isinf(x))) {
+        math_error();
+    }
+    return mp_obj_new_float(ans);
+}
+
 #define MATH_FUN_1(py_name, c_name) \
-    STATIC mp_obj_t mp_math_ ## py_name(mp_obj_t x_obj) { return mp_obj_new_float(MICROPY_FLOAT_C_FUN(c_name)(mp_obj_get_float(x_obj))); } \
+    STATIC mp_obj_t mp_math_ ## py_name(mp_obj_t x_obj) { \
+        return math_generic_1(x_obj, MICROPY_FLOAT_C_FUN(c_name)); \
+    } \
     STATIC MP_DEFINE_CONST_FUN_OBJ_1(mp_math_## py_name ## _obj, mp_math_ ## py_name);
 
-#define MATH_FUN_2(py_name, c_name) \
-    STATIC mp_obj_t mp_math_ ## py_name(mp_obj_t x_obj, mp_obj_t y_obj) { return mp_obj_new_float(MICROPY_FLOAT_C_FUN(c_name)(mp_obj_get_float(x_obj), mp_obj_get_float(y_obj))); } \
-    STATIC MP_DEFINE_CONST_FUN_OBJ_2(mp_math_## py_name ## _obj, mp_math_ ## py_name);
-
 #define MATH_FUN_1_TO_BOOL(py_name, c_name) \
     STATIC mp_obj_t mp_math_ ## py_name(mp_obj_t x_obj) { return mp_obj_new_bool(c_name(mp_obj_get_float(x_obj))); } \
     STATIC MP_DEFINE_CONST_FUN_OBJ_1(mp_math_## py_name ## _obj, mp_math_ ## py_name);
@@ -56,23 +73,29 @@ STATIC NORETURN void math_error(void) {
     STATIC mp_obj_t mp_math_ ## py_name(mp_obj_t x_obj) { return mp_obj_new_int_from_float(MICROPY_FLOAT_C_FUN(c_name)(mp_obj_get_float(x_obj))); } \
     STATIC MP_DEFINE_CONST_FUN_OBJ_1(mp_math_## py_name ## _obj, mp_math_ ## py_name);
 
-#define MATH_FUN_1_ERRCOND(py_name, c_name, error_condition) \
-    STATIC mp_obj_t mp_math_ ## py_name(mp_obj_t x_obj) { \
-        mp_float_t x = mp_obj_get_float(x_obj); \
-        if (error_condition) { \
-            math_error(); \
-        } \
-        return mp_obj_new_float(MICROPY_FLOAT_C_FUN(c_name)(x)); \
+#define MATH_FUN_2(py_name, c_name) \
+    STATIC mp_obj_t mp_math_ ## py_name(mp_obj_t x_obj, mp_obj_t y_obj) { \
+        return math_generic_2(x_obj, y_obj, MICROPY_FLOAT_C_FUN(c_name)); \
     } \
-    STATIC MP_DEFINE_CONST_FUN_OBJ_1(mp_math_## py_name ## _obj, mp_math_ ## py_name);
+    STATIC MP_DEFINE_CONST_FUN_OBJ_2(mp_math_## py_name ## _obj, mp_math_ ## py_name);
 
-#ifdef MP_NEED_LOG2
+#define MATH_FUN_2_FLT_INT(py_name, c_name) \
+    STATIC mp_obj_t mp_math_ ## py_name(mp_obj_t x_obj, mp_obj_t y_obj) { \
+        return mp_obj_new_float(MICROPY_FLOAT_C_FUN(c_name)(mp_obj_get_float(x_obj), mp_obj_get_int(y_obj))); \
+    } \
+    STATIC MP_DEFINE_CONST_FUN_OBJ_2(mp_math_## py_name ## _obj, mp_math_ ## py_name);
+
+#if MP_NEED_LOG2
+#undef log2
+#undef log2f
 // 1.442695040888963407354163704 is 1/_M_LN2
-#define log2(x) (log(x) * 1.442695040888963407354163704)
+mp_float_t MICROPY_FLOAT_C_FUN(log2)(mp_float_t x) {
+    return MICROPY_FLOAT_C_FUN(log)(x) * MICROPY_FLOAT_CONST(1.442695040888963407354163704);
+}
 #endif
 
 // sqrt(x): returns the square root of x
-MATH_FUN_1_ERRCOND(sqrt, sqrt, (x < (mp_float_t)0.0))
+MATH_FUN_1(sqrt, sqrt)
 // pow(x, y): returns x to the power of y
 MATH_FUN_2(pow, pow)
 // exp(x)
@@ -81,9 +104,9 @@ MATH_FUN_1(exp, exp)
 // expm1(x)
 MATH_FUN_1(expm1, expm1)
 // log2(x)
-MATH_FUN_1_ERRCOND(log2, log2, (x <= (mp_float_t)0.0))
+MATH_FUN_1(log2, log2)
 // log10(x)
-MATH_FUN_1_ERRCOND(log10, log10, (x <= (mp_float_t)0.0))
+MATH_FUN_1(log10, log10)
 // cosh(x)
 MATH_FUN_1(cosh, cosh)
 // sinh(x)
@@ -114,9 +137,15 @@ MATH_FUN_2(atan2, atan2)
 // ceil(x)
 MATH_FUN_1_TO_INT(ceil, ceil)
 // copysign(x, y)
-MATH_FUN_2(copysign, copysign)
+STATIC mp_float_t MICROPY_FLOAT_C_FUN(copysign_func)(mp_float_t x, mp_float_t y) {
+    return MICROPY_FLOAT_C_FUN(copysign)(x, y);
+}
+MATH_FUN_2(copysign, copysign_func)
 // fabs(x)
-MATH_FUN_1(fabs, fabs)
+STATIC mp_float_t MICROPY_FLOAT_C_FUN(fabs_func)(mp_float_t x) {
+    return MICROPY_FLOAT_C_FUN(fabs)(x);
+}
+MATH_FUN_1(fabs, fabs_func)
 // floor(x)
 MATH_FUN_1_TO_INT(floor, floor) //TODO: delegate to x.__floor__() if x is not a float
 // fmod(x, y)
@@ -130,7 +159,7 @@ MATH_FUN_1_TO_BOOL(isnan, isnan)
 // trunc(x)
 MATH_FUN_1_TO_INT(trunc, trunc)
 // ldexp(x, exp)
-MATH_FUN_2(ldexp, ldexp)
+MATH_FUN_2_FLT_INT(ldexp, ldexp)
 #if MICROPY_PY_MATH_SPECIAL_FUNCTIONS
 // erf(x): return the error function of x
 MATH_FUN_1(erf, erf)
diff --git a/py/mpconfig.h b/py/mpconfig.h
index cec9fb748..252ab7f37 100644
--- a/py/mpconfig.h
+++ b/py/mpconfig.h
@@ -775,16 +775,24 @@ typedef double mp_float_t;
 #define MICROPY_PY_BUILTINS_TIMEOUTERROR (0)
 #endif
 
-// Whether to support complete set of special methods
-// for user classes, or only the most used ones. "Reverse"
-// methods are controlled by MICROPY_PY_REVERSE_SPECIAL_METHODS
-// below.
+// Whether to support complete set of special methods for user
+// classes, or only the most used ones. "Inplace" methods are
+// controlled by MICROPY_PY_ALL_INPLACE_SPECIAL_METHODS below.
+// "Reverse" methods are controlled by
+// MICROPY_PY_REVERSE_SPECIAL_METHODS below.
 #ifndef MICROPY_PY_ALL_SPECIAL_METHODS
 #define MICROPY_PY_ALL_SPECIAL_METHODS (0)
 #endif
 
-// Whether to support reverse arithmetic operarions methods
-// (__radd__, etc.)
+// Whether to support all inplace arithmetic operarion methods
+// (__imul__, etc.)
+#ifndef MICROPY_PY_ALL_INPLACE_SPECIAL_METHODS
+#define MICROPY_PY_ALL_INPLACE_SPECIAL_METHODS (0)
+#endif
+
+// Whether to support reverse arithmetic operarion methods
+// (__radd__, etc.). Additionally gated by
+// MICROPY_PY_ALL_SPECIAL_METHODS.
 #ifndef MICROPY_PY_REVERSE_SPECIAL_METHODS
 #define MICROPY_PY_REVERSE_SPECIAL_METHODS (0)
 #endif
@@ -1111,6 +1119,8 @@ typedef double mp_float_t;
 
 #ifndef MICROPY_PY_USSL
 #define MICROPY_PY_USSL (0)
+// Whether to add finaliser code to ussl objects
+#define MICROPY_PY_USSL_FINALISER (0)
 #endif
 
 #ifndef MICROPY_PY_WEBSOCKET
diff --git a/py/mpstate.h b/py/mpstate.h
index 1ffb5213c..23133cb7e 100644
--- a/py/mpstate.h
+++ b/py/mpstate.h
@@ -168,7 +168,7 @@ typedef struct _mp_state_vm_t {
     // root pointers for extmod
 
     #ifdef MICROPY_PY_OS_DUPTERM
-    mp_obj_t term_obj;
+    mp_obj_t dupterm_objs[MICROPY_PY_OS_DUPTERM];
     mp_obj_t dupterm_arr_obj;
     #endif
 
diff --git a/py/nativeglue.c b/py/nativeglue.c
index 61b624ec7..e63c2fcda 100644
--- a/py/nativeglue.c
+++ b/py/nativeglue.c
@@ -29,6 +29,7 @@
 #include <assert.h>
 
 #include "py/runtime.h"
+#include "py/smallint.h"
 #include "py/emitglue.h"
 #include "py/bc.h"
 
@@ -170,6 +171,8 @@ void *const mp_fun_table[MP_F_NUMBER_OF] = {
     mp_obj_new_cell,
     mp_make_closure_from_raw_code,
     mp_setup_code_state,
+    mp_small_int_floor_divide,
+    mp_small_int_modulo,
 };
 
 /*
diff --git a/py/objarray.c b/py/objarray.c
index b8dca32f7..a1a979b56 100644
--- a/py/objarray.c
+++ b/py/objarray.c
@@ -286,7 +286,7 @@ STATIC mp_obj_t array_binary_op(mp_binary_op_t op, mp_obj_t lhs_in, mp_obj_t rhs
 
             // Otherwise, can only look for a scalar numeric value in an array
             if (MP_OBJ_IS_INT(rhs_in) || mp_obj_is_float(rhs_in)) {
-                mp_raise_NotImplementedError("");
+                mp_raise_NotImplementedError(NULL);
             }
 
             return mp_const_false;
diff --git a/py/objlist.c b/py/objlist.c
index c6e85f2c8..0cbf68c2f 100644
--- a/py/objlist.c
+++ b/py/objlist.c
@@ -158,7 +158,7 @@ STATIC mp_obj_t list_subscr(mp_obj_t self_in, mp_obj_t index, mp_obj_t value) {
             mp_obj_list_t *self = MP_OBJ_TO_PTR(self_in);
             mp_bound_slice_t slice;
             if (!mp_seq_get_fast_slice_indexes(self->len, index, &slice)) {
-                mp_raise_NotImplementedError("");
+                mp_raise_NotImplementedError(NULL);
             }
 
             mp_int_t len_adj = slice.start - slice.stop;
@@ -198,7 +198,7 @@ STATIC mp_obj_t list_subscr(mp_obj_t self_in, mp_obj_t index, mp_obj_t value) {
             mp_obj_get_array(value, &value_len, &value_items);
             mp_bound_slice_t slice_out;
             if (!mp_seq_get_fast_slice_indexes(self->len, index, &slice_out)) {
-                mp_raise_NotImplementedError("");
+                mp_raise_NotImplementedError(NULL);
             }
             mp_int_t len_adj = value_len - (slice_out.stop - slice_out.start);
             //printf("Len adj: %d\n", len_adj);
diff --git a/py/objtype.c b/py/objtype.c
index d57cec703..2fefc65ad 100644
--- a/py/objtype.c
+++ b/py/objtype.c
@@ -335,7 +335,9 @@ mp_obj_t mp_obj_instance_make_new(const mp_obj_type_t *self, size_t n_args, size
     return MP_OBJ_FROM_PTR(o);
 }
 
-const uint16_t mp_unary_op_method_name[] = {
+// Qstrs for special methods are guaranteed to have a small value, so we use byte
+// type to represent them.
+const byte mp_unary_op_method_name[MP_UNARY_OP_NUM_RUNTIME] = {
     [MP_UNARY_OP_BOOL] = MP_QSTR___bool__,
     [MP_UNARY_OP_LEN] = MP_QSTR___len__,
     [MP_UNARY_OP_HASH] = MP_QSTR___hash__,
@@ -343,11 +345,11 @@ const uint16_t mp_unary_op_method_name[] = {
     [MP_UNARY_OP_POSITIVE] = MP_QSTR___pos__,
     [MP_UNARY_OP_NEGATIVE] = MP_QSTR___neg__,
     [MP_UNARY_OP_INVERT] = MP_QSTR___invert__,
+    [MP_UNARY_OP_ABS] = MP_QSTR___abs__,
     #endif
     #if MICROPY_PY_SYS_GETSIZEOF
-    [MP_UNARY_OP_SIZEOF] = MP_QSTR_getsizeof,
+    [MP_UNARY_OP_SIZEOF] = MP_QSTR___sizeof__,
     #endif
-    [MP_UNARY_OP_NOT] = MP_QSTR_, // don't need to implement this, used to make sure array has full size
 };
 
 STATIC mp_obj_t instance_unary_op(mp_unary_op_t op, mp_obj_t self_in) {
@@ -409,59 +411,69 @@ STATIC mp_obj_t instance_unary_op(mp_unary_op_t op, mp_obj_t self_in) {
     }
 }
 
-const uint16_t mp_binary_op_method_name[] = {
-    /*
-    MP_BINARY_OP_OR,
-    MP_BINARY_OP_XOR,
-    MP_BINARY_OP_AND,
-    MP_BINARY_OP_LSHIFT,
-    MP_BINARY_OP_RSHIFT,
-    */
+// Binary-op enum values not listed here will have the default value of 0 in the
+// table, corresponding to MP_QSTR_NULL, and are therefore unsupported (a lookup will
+// fail).  They can be added at the expense of code size for the qstr.
+// Qstrs for special methods are guaranteed to have a small value, so we use byte
+// type to represent them.
+const byte mp_binary_op_method_name[MP_BINARY_OP_NUM_RUNTIME] = {
+    [MP_BINARY_OP_LESS] = MP_QSTR___lt__,
+    [MP_BINARY_OP_MORE] = MP_QSTR___gt__,
+    [MP_BINARY_OP_EQUAL] = MP_QSTR___eq__,
+    [MP_BINARY_OP_LESS_EQUAL] = MP_QSTR___le__,
+    [MP_BINARY_OP_MORE_EQUAL] = MP_QSTR___ge__,
+    // MP_BINARY_OP_NOT_EQUAL, // a != b calls a == b and inverts result
+    [MP_BINARY_OP_IN] = MP_QSTR___contains__,
+
+    // All inplace methods are optional, and normal methods will be used
+    // as a fallback.
+    [MP_BINARY_OP_INPLACE_ADD] = MP_QSTR___iadd__,
+    [MP_BINARY_OP_INPLACE_SUBTRACT] = MP_QSTR___isub__,
+    #if MICROPY_PY_ALL_INPLACE_SPECIAL_METHODS
+    [MP_BINARY_OP_INPLACE_MULTIPLY] = MP_QSTR___imul__,
+    [MP_BINARY_OP_INPLACE_FLOOR_DIVIDE] = MP_QSTR___ifloordiv__,
+    [MP_BINARY_OP_INPLACE_TRUE_DIVIDE] = MP_QSTR___itruediv__,
+    [MP_BINARY_OP_INPLACE_MODULO] = MP_QSTR___imod__,
+    [MP_BINARY_OP_INPLACE_POWER] = MP_QSTR___ipow__,
+    [MP_BINARY_OP_INPLACE_OR] = MP_QSTR___ior__,
+    [MP_BINARY_OP_INPLACE_XOR] = MP_QSTR___ixor__,
+    [MP_BINARY_OP_INPLACE_AND] = MP_QSTR___iand__,
+    [MP_BINARY_OP_INPLACE_LSHIFT] = MP_QSTR___ilshift__,
+    [MP_BINARY_OP_INPLACE_RSHIFT] = MP_QSTR___irshift__,
+    #endif
+
     [MP_BINARY_OP_ADD] = MP_QSTR___add__,
     [MP_BINARY_OP_SUBTRACT] = MP_QSTR___sub__,
     #if MICROPY_PY_ALL_SPECIAL_METHODS
     [MP_BINARY_OP_MULTIPLY] = MP_QSTR___mul__,
     [MP_BINARY_OP_FLOOR_DIVIDE] = MP_QSTR___floordiv__,
     [MP_BINARY_OP_TRUE_DIVIDE] = MP_QSTR___truediv__,
+    [MP_BINARY_OP_MODULO] = MP_QSTR___mod__,
+    [MP_BINARY_OP_DIVMOD] = MP_QSTR___divmod__,
+    [MP_BINARY_OP_POWER] = MP_QSTR___pow__,
+    [MP_BINARY_OP_OR] = MP_QSTR___or__,
+    [MP_BINARY_OP_XOR] = MP_QSTR___xor__,
+    [MP_BINARY_OP_AND] = MP_QSTR___and__,
+    [MP_BINARY_OP_LSHIFT] = MP_QSTR___lshift__,
+    [MP_BINARY_OP_RSHIFT] = MP_QSTR___rshift__,
     #endif
-    /*
-    MP_BINARY_OP_MODULO,
-    MP_BINARY_OP_POWER,
-    MP_BINARY_OP_DIVMOD,
-    MP_BINARY_OP_INPLACE_OR,
-    MP_BINARY_OP_INPLACE_XOR,
-    MP_BINARY_OP_INPLACE_AND,
-    MP_BINARY_OP_INPLACE_LSHIFT,
-    MP_BINARY_OP_INPLACE_RSHIFT,*/
-    #if MICROPY_PY_ALL_SPECIAL_METHODS
-    [MP_BINARY_OP_INPLACE_ADD] = MP_QSTR___iadd__,
-    [MP_BINARY_OP_INPLACE_SUBTRACT] = MP_QSTR___isub__,
-    #endif
-    /*MP_BINARY_OP_INPLACE_MULTIPLY,
-    MP_BINARY_OP_INPLACE_FLOOR_DIVIDE,
-    MP_BINARY_OP_INPLACE_TRUE_DIVIDE,
-    MP_BINARY_OP_INPLACE_MODULO,
-    MP_BINARY_OP_INPLACE_POWER,*/
 
     #if MICROPY_PY_REVERSE_SPECIAL_METHODS
     [MP_BINARY_OP_REVERSE_ADD] = MP_QSTR___radd__,
     [MP_BINARY_OP_REVERSE_SUBTRACT] = MP_QSTR___rsub__,
+    #if MICROPY_PY_ALL_SPECIAL_METHODS
     [MP_BINARY_OP_REVERSE_MULTIPLY] = MP_QSTR___rmul__,
+    [MP_BINARY_OP_REVERSE_FLOOR_DIVIDE] = MP_QSTR___rfloordiv__,
+    [MP_BINARY_OP_REVERSE_TRUE_DIVIDE] = MP_QSTR___rtruediv__,
+    [MP_BINARY_OP_REVERSE_MODULO] = MP_QSTR___rmod__,
+    [MP_BINARY_OP_REVERSE_POWER] = MP_QSTR___rpow__,
+    [MP_BINARY_OP_REVERSE_OR] = MP_QSTR___ror__,
+    [MP_BINARY_OP_REVERSE_XOR] = MP_QSTR___rxor__,
+    [MP_BINARY_OP_REVERSE_AND] = MP_QSTR___rand__,
+    [MP_BINARY_OP_REVERSE_LSHIFT] = MP_QSTR___rlshift__,
+    [MP_BINARY_OP_REVERSE_RSHIFT] = MP_QSTR___rrshift__,
+    #endif
     #endif
-
-    [MP_BINARY_OP_LESS] = MP_QSTR___lt__,
-    [MP_BINARY_OP_MORE] = MP_QSTR___gt__,
-    [MP_BINARY_OP_EQUAL] = MP_QSTR___eq__,
-    [MP_BINARY_OP_LESS_EQUAL] = MP_QSTR___le__,
-    [MP_BINARY_OP_MORE_EQUAL] = MP_QSTR___ge__,
-    /*
-    MP_BINARY_OP_NOT_EQUAL, // a != b calls a == b and inverts result
-    */
-    [MP_BINARY_OP_IN] = MP_QSTR___contains__,
-    /*
-    MP_BINARY_OP_IS,
-    */
-    [MP_BINARY_OP_LAST] = 0, // used to make sure array has full size, TODO: FIXME
 };
 
 STATIC mp_obj_t instance_binary_op(mp_binary_op_t op, mp_obj_t lhs_in, mp_obj_t rhs_in) {
diff --git a/py/persistentcode.c b/py/persistentcode.c
index 42efcbfbb..477ba7501 100644
--- a/py/persistentcode.c
+++ b/py/persistentcode.c
@@ -39,7 +39,7 @@
 #include "py/smallint.h"
 
 // The current version of .mpy files
-#define MPY_VERSION (2)
+#define MPY_VERSION (3)
 
 // The feature flags byte encodes the compile-time config options that
 // affect the generate bytecode.
diff --git a/py/runtime.c b/py/runtime.c
index 4af17dd09..cbec82f17 100644
--- a/py/runtime.c
+++ b/py/runtime.c
@@ -108,6 +108,13 @@ void mp_init(void) {
     MP_STATE_VM(mp_module_builtins_override_dict) = NULL;
     #endif
 
+    #ifdef MICROPY_PY_OS_DUPTERM
+    for (size_t i = 0; i < MICROPY_PY_OS_DUPTERM; ++i) {
+        MP_STATE_VM(dupterm_objs[i]) = MP_OBJ_NULL;
+    }
+    MP_STATE_VM(dupterm_arr_obj) = MP_OBJ_NULL;
+    #endif
+
     #ifdef MICROPY_FSUSERMOUNT
     // zero out the pointers to the user-mounted devices
     memset(MP_STATE_VM(fs_user_mount) + MICROPY_FATFS_NUM_PERSISTENT, 0,
diff --git a/py/runtime.h b/py/runtime.h
index 79f5cbc92..a8b6312ff 100644
--- a/py/runtime.h
+++ b/py/runtime.h
@@ -57,8 +57,8 @@ typedef struct _mp_arg_t {
 } mp_arg_t;
 
 // Tables mapping operator enums to qstrs, defined in objtype.c
-extern const uint16_t mp_unary_op_method_name[];
-extern const uint16_t mp_binary_op_method_name[];
+extern const byte mp_unary_op_method_name[];
+extern const byte mp_binary_op_method_name[];
 
 void mp_init(void);
 void mp_deinit(void);
diff --git a/py/runtime0.h b/py/runtime0.h
index 8e95b68cf..4709430fb 100644
--- a/py/runtime0.h
+++ b/py/runtime0.h
@@ -53,41 +53,38 @@ typedef enum {
     MP_UNARY_OP_NOT,
 
     // Following ops cannot appear in the bytecode
-    MP_UNARY_OP_NON_BYTECODE,
+    MP_UNARY_OP_NUM_BYTECODE,
 
-    MP_UNARY_OP_BOOL = MP_UNARY_OP_NON_BYTECODE, // __bool__
+    MP_UNARY_OP_BOOL = MP_UNARY_OP_NUM_BYTECODE, // __bool__
     MP_UNARY_OP_LEN, // __len__
     MP_UNARY_OP_HASH, // __hash__; must return a small int
     MP_UNARY_OP_ABS, // __abs__
     MP_UNARY_OP_SIZEOF, // for sys.getsizeof()
+
+    MP_UNARY_OP_NUM_RUNTIME,
 } mp_unary_op_t;
 
-// Note: the first 35 of these are used in bytecode and changing
+// Note: the first 9+12+12 of these are used in bytecode and changing
 // them requires changing the bytecode version.
 typedef enum {
-    // Relational operations, should return a bool
+    // 9 relational operations, should return a bool
     MP_BINARY_OP_LESS,
     MP_BINARY_OP_MORE,
     MP_BINARY_OP_EQUAL,
     MP_BINARY_OP_LESS_EQUAL,
     MP_BINARY_OP_MORE_EQUAL,
     MP_BINARY_OP_NOT_EQUAL,
-
     MP_BINARY_OP_IN,
     MP_BINARY_OP_IS,
     MP_BINARY_OP_EXCEPTION_MATCH,
-    // these are not supported by the runtime and must be synthesised by the emitter
-    MP_BINARY_OP_NOT_IN,
-    MP_BINARY_OP_IS_NOT,
 
-    // Arithmetic operations
+    // 12 inplace arithmetic operations
     MP_BINARY_OP_INPLACE_OR,
     MP_BINARY_OP_INPLACE_XOR,
     MP_BINARY_OP_INPLACE_AND,
     MP_BINARY_OP_INPLACE_LSHIFT,
     MP_BINARY_OP_INPLACE_RSHIFT,
     MP_BINARY_OP_INPLACE_ADD,
-
     MP_BINARY_OP_INPLACE_SUBTRACT,
     MP_BINARY_OP_INPLACE_MULTIPLY,
     MP_BINARY_OP_INPLACE_FLOOR_DIVIDE,
@@ -95,13 +92,13 @@ typedef enum {
     MP_BINARY_OP_INPLACE_MODULO,
     MP_BINARY_OP_INPLACE_POWER,
 
+    // 12 normal arithmetic operations
     MP_BINARY_OP_OR,
     MP_BINARY_OP_XOR,
     MP_BINARY_OP_AND,
     MP_BINARY_OP_LSHIFT,
     MP_BINARY_OP_RSHIFT,
     MP_BINARY_OP_ADD,
-
     MP_BINARY_OP_SUBTRACT,
     MP_BINARY_OP_MULTIPLY,
     MP_BINARY_OP_FLOOR_DIVIDE,
@@ -111,16 +108,16 @@ typedef enum {
 
     // Operations below this line don't appear in bytecode, they
     // just identify special methods.
+    MP_BINARY_OP_NUM_BYTECODE,
 
     // MP_BINARY_OP_REVERSE_* must follow immediately after MP_BINARY_OP_*
 #if MICROPY_PY_REVERSE_SPECIAL_METHODS
-    MP_BINARY_OP_REVERSE_OR,
+    MP_BINARY_OP_REVERSE_OR = MP_BINARY_OP_NUM_BYTECODE,
     MP_BINARY_OP_REVERSE_XOR,
     MP_BINARY_OP_REVERSE_AND,
     MP_BINARY_OP_REVERSE_LSHIFT,
     MP_BINARY_OP_REVERSE_RSHIFT,
     MP_BINARY_OP_REVERSE_ADD,
-
     MP_BINARY_OP_REVERSE_SUBTRACT,
     MP_BINARY_OP_REVERSE_MULTIPLY,
     MP_BINARY_OP_REVERSE_FLOOR_DIVIDE,
@@ -129,9 +126,18 @@ typedef enum {
     MP_BINARY_OP_REVERSE_POWER,
 #endif
 
-    MP_BINARY_OP_DIVMOD, // not emitted by the compiler but supported by the runtime
+    // This is not emitted by the compiler but is supported by the runtime
+    MP_BINARY_OP_DIVMOD
+        #if !MICROPY_PY_REVERSE_SPECIAL_METHODS
+        = MP_BINARY_OP_NUM_BYTECODE
+        #endif
+    ,
+
+    MP_BINARY_OP_NUM_RUNTIME,
 
-    MP_BINARY_OP_LAST,
+    // These 2 are not supported by the runtime and must be synthesised by the emitter
+    MP_BINARY_OP_NOT_IN,
+    MP_BINARY_OP_IS_NOT,
 } mp_binary_op_t;
 
 typedef enum {
@@ -181,6 +187,8 @@ typedef enum {
     MP_F_NEW_CELL,
     MP_F_MAKE_CLOSURE_FROM_RAW_CODE,
     MP_F_SETUP_CODE_STATE,
+    MP_F_SMALL_INT_FLOOR_DIVIDE,
+    MP_F_SMALL_INT_MODULO,
     MP_F_NUMBER_OF,
 } mp_fun_kind_t;
 
diff --git a/py/showbc.c b/py/showbc.c
index 728d8d983..3deb18cd3 100644
--- a/py/showbc.c
+++ b/py/showbc.c
@@ -539,9 +539,9 @@ const byte *mp_bytecode_print_str(const byte *ip) {
                 printf("LOAD_FAST " UINT_FMT, (mp_uint_t)ip[-1] - MP_BC_LOAD_FAST_MULTI);
             } else if (ip[-1] < MP_BC_STORE_FAST_MULTI + 16) {
                 printf("STORE_FAST " UINT_FMT, (mp_uint_t)ip[-1] - MP_BC_STORE_FAST_MULTI);
-            } else if (ip[-1] < MP_BC_UNARY_OP_MULTI + MP_UNARY_OP_NON_BYTECODE) {
+            } else if (ip[-1] < MP_BC_UNARY_OP_MULTI + MP_UNARY_OP_NUM_BYTECODE) {
                 printf("UNARY_OP " UINT_FMT, (mp_uint_t)ip[-1] - MP_BC_UNARY_OP_MULTI);
-            } else if (ip[-1] < MP_BC_BINARY_OP_MULTI + 36) {
+            } else if (ip[-1] < MP_BC_BINARY_OP_MULTI + MP_BINARY_OP_NUM_BYTECODE) {
                 mp_uint_t op = ip[-1] - MP_BC_BINARY_OP_MULTI;
                 printf("BINARY_OP " UINT_FMT " %s", op, qstr_str(mp_binary_op_method_name[op]));
             } else {
diff --git a/py/vmentrytable.h b/py/vmentrytable.h
index e634e2b41..615f4e2ce 100644
--- a/py/vmentrytable.h
+++ b/py/vmentrytable.h
@@ -109,8 +109,8 @@ static const void *const entry_table[256] = {
     [MP_BC_LOAD_CONST_SMALL_INT_MULTI ... MP_BC_LOAD_CONST_SMALL_INT_MULTI + 63] = &&entry_MP_BC_LOAD_CONST_SMALL_INT_MULTI,
     [MP_BC_LOAD_FAST_MULTI ... MP_BC_LOAD_FAST_MULTI + 15] = &&entry_MP_BC_LOAD_FAST_MULTI,
     [MP_BC_STORE_FAST_MULTI ... MP_BC_STORE_FAST_MULTI + 15] = &&entry_MP_BC_STORE_FAST_MULTI,
-    [MP_BC_UNARY_OP_MULTI ... MP_BC_UNARY_OP_MULTI + MP_UNARY_OP_NON_BYTECODE - 1] = &&entry_MP_BC_UNARY_OP_MULTI,
-    [MP_BC_BINARY_OP_MULTI ... MP_BC_BINARY_OP_MULTI + 35] = &&entry_MP_BC_BINARY_OP_MULTI,
+    [MP_BC_UNARY_OP_MULTI ... MP_BC_UNARY_OP_MULTI + MP_UNARY_OP_NUM_BYTECODE - 1] = &&entry_MP_BC_UNARY_OP_MULTI,
+    [MP_BC_BINARY_OP_MULTI ... MP_BC_BINARY_OP_MULTI + MP_BINARY_OP_NUM_BYTECODE - 1] = &&entry_MP_BC_BINARY_OP_MULTI,
 };
 
 #if __clang__