diff options
author | Ronan Collobert <locronan@fb.com> | 2015-11-24 00:15:07 +0300 |
---|---|---|
committer | Ronan Collobert <locronan@fb.com> | 2015-11-24 00:15:07 +0300 |
commit | 1fbc546d4be2ef7228bd47e2adc61afa6473c26d (patch) | |
tree | c4b4f3709d4dbd38010729a2b348d3d2c6d7b733 | |
parent | 81d43338bc6346936720b69a16fadb837d14e6d2 (diff) | |
parent | 320a2b2b39e8b01a632d2bf5411eee0c0b3aef4f (diff) |
Merge commit '320a2b2b39e8b01a632d2bf5411eee0c0b3aef4f'
67 files changed, 6327 insertions, 617 deletions
diff --git a/luajit-2.1/Makefile b/luajit-2.1/Makefile index dce52e5..8ce773e 100644 --- a/luajit-2.1/Makefile +++ b/luajit-2.1/Makefile @@ -16,7 +16,7 @@ MAJVER= 2 MINVER= 1 RELVER= 0 -PREREL= -alpha +PREREL= -beta1 VERSION= $(MAJVER).$(MINVER).$(RELVER)$(PREREL) ABIVER= 5.1 diff --git a/luajit-2.1/README b/luajit-2.1/README index 6dcd9b9..ca70dd8 100644 --- a/luajit-2.1/README +++ b/luajit-2.1/README @@ -1,4 +1,4 @@ -README for LuaJIT 2.1.0-alpha +README for LuaJIT 2.1.0-beta1 ----------------------------- LuaJIT is a Just-In-Time (JIT) compiler for the Lua programming language. diff --git a/luajit-2.1/doc/changes.html b/luajit-2.1/doc/changes.html index 0d3e5ae..826cd24 100644 --- a/luajit-2.1/doc/changes.html +++ b/luajit-2.1/doc/changes.html @@ -65,7 +65,7 @@ div.major { max-width: 600px; padding: 1em; margin: 1em 0 1em 0; } <div id="main"> <p> This is a list of changes between the released versions of LuaJIT.<br> -The current <span style="color: #0000c0;">stable version</span> is <strong>LuaJIT 2.0.3</strong>.<br> +The current <span style="color: #0000c0;">stable version</span> is <strong>LuaJIT 2.0.4</strong>.<br> </p> <p> Please check the @@ -74,6 +74,112 @@ to see whether newer versions are available. </p> <div class="major" style="background: #d0d0ff;"> +<h2 id="LuaJIT-2.1.0-beta1">LuaJIT 2.1.0-beta1 — 2015-08-25</h2> +<p> +This is a brief summary of the major changes in LuaJIT 2.1 compared to 2.0. +Please take a look at the commit history for more details. +</p> +<ul> +<li>Changes to the VM core: +<ul> +<li>Add low-overhead profiler (<tt>-jp</tt>).</li> +<li>Add <tt>LJ_GC64</tt> mode: 64 bit GC object references (really: 47 bit). Interpreter-only for now.</li> +<li>Add <tt>LJ_FR2</tt> mode: Two-slot frame info. Required by <tt>LJ_GC64</tt> mode.</li> +<li>Add <tt>table.new()</tt> and <tt>table.clear()</tt>.</li> +<li>Parse Unicode escape <tt>'\u{XX...}'</tt> in string literals.</li> +<li>Parse binary number literals (<tt>0bxxx</tt>).</li> +</ul></li> +<li>Improvements to the JIT compiler: +<ul> +<li>Add trace stitching.</li> +<li>Compile various builtins: <tt>string.char()</tt>, <tt>string.reverse()</tt>, <tt>string.lower()</tt>, <tt>string.upper()</tt>, <tt>string.rep()</tt>, <tt>string.format()</tt>, <tt>table.concat()</tt>, <tt>bit.tohex()</tt>, <tt>getfenv(0)</tt>, <tt>debug.getmetatable()</tt>.</li> +<li>Compile <tt>string.find()</tt> for fixed string searches (no patterns).</li> +<li>Compile <tt>BC_TSETM</tt>, e.g. <tt>{1,2,3,f()}</tt>.</li> +<li>Compile string concatenations (<tt>BC_CAT</tt>).</li> +<li>Compile <tt>__concat</tt> metamethod.</li> +<li>Various minor optimizations.</li> +</ul></li> +<li>Internal Changes: +<ul> +<li>Add support for embedding LuaJIT bytecode for builtins.</li> +<li>Replace various builtins with embedded bytecode.</li> +<li>Refactor string buffers and string formatting.</li> +<li>Remove obsolete non-truncating number to integer conversions.</li> +</ul></li> +<li>Ports: +<ul> +<li>Add Xbox One port (<tt>LJ_GC64</tt> mode).</li> +<li>ARM64: Add port of the interpreter (<tt>LJ_GC64</tt> mode).</li> +<li>x64: Add separate port of the interpreter to <tt>LJ_GC64</tt> mode.</li> +<li>x86/x64: Drop internal x87 math functions. Use libm functions.</li> +<li>x86: Remove x87 support from interpreter. SSE2 is mandatory now.</li> +<li>x86/x64: Add support for AES-NI, AVX and AVX2 to DynASM.</li> +<li>PPC/e500: Drop support for this architecture.</li> +</ul></li> +<li>FFI library: +<ul> +<li>FFI: Add 64 bit bitwise operations.</li> +<li>FFI: Compile VLA/VLS and large cdata allocations with default initialization.</li> +<li>FFI: Compile conversions from functions to function pointers.</li> +<li>FFI: Compile lightuserdata to <tt>void *</tt> conversion.</li> +<li>FFI: Compile <tt>ffi.gc(cdata, nil)</tt>, too.</li> +<li>FFI: Add <tt>ffi.typeinfo()</tt>.</li> +<li>FFI: Add <tt>ssize_t</tt> declaration.</li> +</ul></li> +</ul> +</div> + +<div class="major" style="background: #ffffd0;"> +<h2 id="LuaJIT-2.0.4">LuaJIT 2.0.4 — 2015-05-14</h2> +<ul> +<li>Fix stack check in narrowing optimization.</li> +<li>Fix Lua/C API typecheck error for special indexes.</li> +<li>Fix string to number conversion.</li> +<li>Fix lexer error for chunks without tokens.</li> +<li>Don't compile <tt>IR_RETF</tt> after <tt>CALLT</tt> to ff with-side effects.</li> +<li>Fix <tt>BC_UCLO</tt>/<tt>BC_JMP</tt> join optimization in Lua parser.</li> +<li>Fix corner case in string to number conversion.</li> +<li>Gracefully handle <tt>lua_error()</tt> for a suspended coroutine.</li> +<li>Avoid error messages when building with Clang.</li> +<li>Fix snapshot #0 handling for traces with a stack check on entry.</li> +<li>Fix fused constant loads under high register pressure.</li> +<li>Invalidate backpropagation cache after DCE.</li> +<li>Fix ABC elimination.</li> +<li>Fix debug info for main chunk of stripped bytecode.</li> +<li>Fix FOLD rule for <tt>string.sub(s, ...) == k</tt>.</li> +<li>Fix FOLD rule for <tt>STRREF</tt> of <tt>SNEW</tt>.</li> +<li>Fix frame traversal while searching for error function.</li> +<li>Prevent GC estimate miscalculation due to buffer growth.</li> +<li>Prevent adding side traces for stack checks.</li> +<li>Fix top slot calculation for snapshots with continuations.</li> +<li>Fix check for reuse of SCEV results in <tt>FORL</tt>.</li> +<li>Add PS Vita port.</li> +<li>Fix compatibility issues with Illumos.</li> +<li>Fix DragonFly build (unsupported).</li> +<li>OpenBSD/x86: Better executable memory allocation for W^X mode.</li> +<li>x86: Fix argument checks for <tt>ipairs()</tt> iterator.</li> +<li>x86: <tt>lj_math_random_step()</tt> clobbers XMM regs on OSX Clang.</li> +<li>x86: Fix code generation for unused result of <tt>math.random()</tt>.</li> +<li>x64: Allow building with <tt>LUAJIT_USE_SYSMALLOC</tt> and <tt>LUAJIT_USE_VALGRIND</tt>.</li> +<li>x86/x64: Fix argument check for bit shifts.</li> +<li>x86/x64: Fix code generation for fused test/arith ops.</li> +<li>ARM: Fix write barrier check in <tt>BC_USETS</tt>.</li> +<li>PPC: Fix red zone overflow in machine code generation.</li> +<li>PPC: Don't use <tt>mcrxr</tt> on PPE.</li> +<li>Various archs: Fix excess stack growth in interpreter.</li> +<li>FFI: Fix FOLD rule for <tt>TOBIT</tt> + <tt>CONV num.u32</tt>.</li> +<li>FFI: Prevent DSE across <tt>ffi.string()</tt>.</li> +<li>FFI: No meta fallback when indexing pointer to incomplete struct.</li> +<li>FFI: Fix initialization of unions of subtypes.</li> +<li>FFI: Fix cdata vs. non-cdata arithmetic and comparisons.</li> +<li>FFI: Fix <tt>__index</tt>/<tt>__newindex</tt> metamethod resolution for ctypes.</li> +<li>FFI: Fix compilation of reference field access.</li> +<li>FFI: Fix frame traversal for backtraces with FFI callbacks.</li> +<li>FFI: Fix recording of indexing a struct pointer ctype object itself.</li> +<li>FFI: Allow non-scalar cdata to be compared for equality by address.</li> +<li>FFI: Fix pseudo type conversions for type punning.</li> +</ul> + <h2 id="LuaJIT-2.0.3">LuaJIT 2.0.3 — 2014-03-12</h2> <ul> <li>Add PS4 port.</li> @@ -687,235 +793,6 @@ This matches the behavior of Lua 5.1, but not the specification.</li> no point in listing differences over earlier versions.</li> </ul> </div> - -<div class="major" style="background: #ffff80;"> -<h2 id="LuaJIT-1.1.8">LuaJIT 1.1.8 — 2012-04-16</h2> -<ul> -<li>Merged with Lua 5.1.5. Also integrated fixes for all -<a href="http://www.lua.org/bugs.html#5.1.5"><span class="ext">»</span> <span class="ext">»</span> currently known bugs in Lua 5.1.5</a>.</li> -</ul> - -<h2 id="LuaJIT-1.1.7">LuaJIT 1.1.7 — 2011-05-05</h2> -<ul> -<li>Added fixes for the -<a href="http://www.lua.org/bugs.html#5.1.4"><span class="ext">»</span> currently known bugs in Lua 5.1.4</a>.</li> -</ul> - -<h2 id="LuaJIT-1.1.6">LuaJIT 1.1.6 — 2010-03-28</h2> -<ul> -<li>Added fixes for the -<a href="http://www.lua.org/bugs.html#5.1.4"><span class="ext">»</span> currently known bugs in Lua 5.1.4</a>.</li> -<li>Removed wrong GC check in <tt>jit_createstate()</tt>. -Thanks to Tim Mensch.</li> -<li>Fixed bad assertions while compiling <tt>table.insert()</tt> and -<tt>table.remove()</tt>.</li> -</ul> - -<h2 id="LuaJIT-1.1.5">LuaJIT 1.1.5 — 2008-10-25</h2> -<ul> -<li>Merged with Lua 5.1.4. Fixes all -<a href="http://www.lua.org/bugs.html#5.1.3"><span class="ext">»</span> known bugs in Lua 5.1.3</a>.</li> -</ul> - -<h2 id="LuaJIT-1.1.4">LuaJIT 1.1.4 — 2008-02-05</h2> -<ul> -<li>Merged with Lua 5.1.3. Fixes all -<a href="http://www.lua.org/bugs.html#5.1.2"><span class="ext">»</span> known bugs in Lua 5.1.2</a>.</li> -<li>Fixed possible (but unlikely) stack corruption while compiling -<tt>k^x</tt> expressions.</li> -<li>Fixed DynASM template for cmpss instruction.</li> -</ul> - -<h2 id="LuaJIT-1.1.3">LuaJIT 1.1.3 — 2007-05-24</h2> -<ul> -<li>Merged with Lua 5.1.2. Fixes all -<a href="http://www.lua.org/bugs.html#5.1.1"><span class="ext">»</span> known bugs in Lua 5.1.1</a>.</li> -<li>Merged pending Lua 5.1.x fixes: "return -nil" bug, spurious count hook call.</li> -<li>Remove a (sometimes) wrong assertion in <tt>luaJIT_findpc()</tt>.</li> -<li>DynASM now allows labels for displacements and <tt>.aword</tt>.</li> -<li>Fix some compiler warnings for DynASM glue (internal API change).</li> -<li>Correct naming for SSSE3 (temporarily known as SSE4) in DynASM and x86 disassembler.</li> -<li>The loadable debug modules now handle redirection to stdout -(e.g. <tt>-j trace=-</tt>).</li> -</ul> - -<h2 id="LuaJIT-1.1.2">LuaJIT 1.1.2 — 2006-06-24</h2> -<ul> -<li>Fix MSVC inline assembly: use only local variables with -<tt>lua_number2int()</tt>.</li> -<li>Fix "attempt to call a thread value" bug on Mac OS X: -make values of consts used as lightuserdata keys unique -to avoid joining by the compiler/linker.</li> -</ul> - -<h2 id="LuaJIT-1.1.1">LuaJIT 1.1.1 — 2006-06-20</h2> -<ul> -<li>Merged with Lua 5.1.1. Fixes all -<a href="http://www.lua.org/bugs.html#5.1"><span class="ext">»</span> known bugs in Lua 5.1</a>.</li> -<li>Enforce (dynamic) linker error for EXE/DLL version mismatches.</li> -<li>Minor changes to DynASM: faster pre-processing, smaller encoding -for some immediates.</li> -</ul> -<p> -This release is in sync with Coco 1.1.1 (see the -<a href="http://coco.luajit.org/changes.html"><span class="ext">»</span> Coco Change History</a>). -</p> - -<h2 id="LuaJIT-1.1.0">LuaJIT 1.1.0 — 2006-03-13</h2> -<ul> -<li>Merged with Lua 5.1 (final).</li> - -<li>New JIT call frame setup: -<ul> -<li>The C stack is kept 16 byte aligned (faster). -Mandatory for Mac OS X on Intel, too.</li> -<li>Faster calling conventions for internal C helper functions.</li> -<li>Better instruction scheduling for function prologue, OP_CALL and -OP_RETURN.</li> -</ul></li> - -<li>Miscellaneous optimizations: -<ul> -<li>Faster loads of FP constants. Remove narrow-to-wide store-to-load -forwarding stalls.</li> -<li>Use (scalar) SSE2 ops (if the CPU supports it) to speed up slot moves -and FP to integer conversions.</li> -<li>Optimized the two-argument form of <tt>OP_CONCAT</tt> (<tt>a..b</tt>).</li> -<li>Inlined <tt>OP_MOD</tt> (<tt>a%b</tt>). -With better accuracy than the C variant, too.</li> -<li>Inlined <tt>OP_POW</tt> (<tt>a^b</tt>). Unroll <tt>x^k</tt> or -use <tt>k^x = 2^(log2(k)*x)</tt> or call <tt>pow()</tt>.</li> -</ul></li> - -<li>Changes in the optimizer: -<ul> -<li>Improved hinting for table keys derived from table values -(<tt>t1[t2[x]]</tt>).</li> -<li>Lookup hinting now works with arbitrary object types and -supports index chains, too.</li> -<li>Generate type hints for arithmetic and comparison operators, -OP_LEN, OP_CONCAT and OP_FORPREP.</li> -<li>Remove several hint definitions in favour of a generic COMBINE hint.</li> -<li>Complete rewrite of <tt>jit.opt_inline</tt> module -(ex <tt>jit.opt_lib</tt>).</li> -</ul></li> - -<li>Use adaptive deoptimization: -<ul> -<li>If runtime verification of a contract fails, the affected -instruction is recompiled and patched on-the-fly. -Regular programs will trigger deoptimization only occasionally.</li> -<li>This avoids generating code for uncommon fallback cases -most of the time. Generated code is up to 30% smaller compared to -LuaJIT 1.0.3.</li> -<li>Deoptimization is used for many opcodes and contracts: -<ul> -<li>OP_CALL, OP_TAILCALL: type mismatch for callable.</li> -<li>Inlined calls: closure mismatch, parameter number and type mismatches.</li> -<li>OP_GETTABLE, OP_SETTABLE: table or key type and range mismatches.</li> -<li>All arithmetic and comparison operators, OP_LEN, OP_CONCAT, -OP_FORPREP: operand type and range mismatches.</li> -</ul></li> -<li>Complete redesign of the debug and traceback info -(bytecode ↔ mcode) to support deoptimization. -Much more flexible and needs only 50% of the space.</li> -<li>The modules <tt>jit.trace</tt>, <tt>jit.dumphints</tt> and -<tt>jit.dump</tt> handle deoptimization.</li> -</ul></li> - -<li>Inlined many popular library functions -(for commonly used arguments only): -<ul> -<li>Most <tt>math.*</tt> functions (the 18 most used ones) -[2x-10x faster].</li> -<li><tt>string.len</tt>, <tt>string.sub</tt> and <tt>string.char</tt> -[2x-10x faster].</li> -<li><tt>table.insert</tt>, <tt>table.remove</tt> and <tt>table.getn</tt> -[3x-5x faster].</li> -<li><tt>coroutine.yield</tt> and <tt>coroutine.resume</tt> -[3x-5x faster].</li> -<li><tt>pairs</tt>, <tt>ipairs</tt> and the corresponding iterators -[8x-15x faster].</li> -</ul></li> - -<li>Changes in the core and loadable modules and the stand-alone executable: -<ul> -<li>Added <tt>jit.version</tt>, <tt>jit.version_num</tt> -and <tt>jit.arch</tt>.</li> -<li>Reorganized some internal API functions (<tt>jit.util.*mcode*</tt>).</li> -<li>The <tt>-j dump</tt> output now shows JSUB names, too.</li> -<li>New x86 disassembler module written in pure Lua. No dependency -on ndisasm anymore. Flexible API, very compact (500 lines) -and complete (x87, MMX, SSE, SSE2, SSE3, SSSE3, privileged instructions).</li> -<li><tt>luajit -v</tt> prints the LuaJIT version and copyright -on a separate line.</li> -</ul></li> - -<li>Added SSE, SSE2, SSE3 and SSSE3 support to DynASM.</li> -<li>Miscellaneous doc changes. Added a section about -<a href="install.html#embedding">embedding LuaJIT</a>.</li> -</ul> -<p> -This release is in sync with Coco 1.1.0 (see the -<a href="http://coco.luajit.org/changes.html"><span class="ext">»</span> Coco Change History</a>). -</p> -</div> - -<div class="major" style="background: #ffffd0;"> -<h2 id="LuaJIT-1.0.3">LuaJIT 1.0.3 — 2005-09-08</h2> -<ul> -<li>Even more docs.</li> -<li>Unified closure checks in <tt>jit.*</tt>.</li> -<li>Fixed some range checks in <tt>jit.util.*</tt>.</li> -<li>Fixed __newindex call originating from <tt>jit_settable_str()</tt>.</li> -<li>Merged with Lua 5.1 alpha (including early bug fixes).</li> -</ul> -<p> -This is the first public release of LuaJIT. -</p> - -<h2 id="LuaJIT-1.0.2">LuaJIT 1.0.2 — 2005-09-02</h2> -<ul> -<li>Add support for flushing the Valgrind translation cache <br> -(<tt>MYCFLAGS= -DUSE_VALGRIND</tt>).</li> -<li>Add support for freeing executable mcode memory to the <tt>mmap()</tt>-based -variant for POSIX systems.</li> -<li>Reorganized the C function signature handling in -<tt>jit.opt_lib</tt>.</li> -<li>Changed to index-based hints for inlining C functions. -Still no support in the backend for inlining.</li> -<li>Hardcode <tt>HEAP_CREATE_ENABLE_EXECUTE</tt> value if undefined.</li> -<li>Misc. changes to the <tt>jit.*</tt> modules.</li> -<li>Misc. changes to the Makefiles.</li> -<li>Lots of new docs.</li> -<li>Complete doc reorg.</li> -</ul> -<p> -Not released because Lua 5.1 alpha came out today. -</p> - -<h2 id="LuaJIT-1.0.1">LuaJIT 1.0.1 — 2005-08-31</h2> -<ul> -<li>Missing GC step in <tt>OP_CONCAT</tt>.</li> -<li>Fix result handling for C –> JIT calls.</li> -<li>Detect CPU feature bits.</li> -<li>Encode conditional moves (<tt>fucomip</tt>) only when supported.</li> -<li>Add fallback instructions for FP compares.</li> -<li>Add support for <tt>LUA_COMPAT_VARARG</tt>. Still disabled by default.</li> -<li>MSVC needs a specific place for the <tt>CALLBACK</tt> attribute -(David Burgess).</li> -<li>Misc. doc updates.</li> -</ul> -<p> -Interim non-public release. -Special thanks to Adam D. Moss for reporting most of the bugs. -</p> - -<h2 id="LuaJIT-1.0.0">LuaJIT 1.0.0 — 2005-08-29</h2> -<p> -This is the initial non-public release of LuaJIT. -</p> -</div> <br class="flush"> </div> <div id="foot"> diff --git a/luajit-2.1/doc/ext_ffi_api.html b/luajit-2.1/doc/ext_ffi_api.html index 8cf48dc..b095c05 100644 --- a/luajit-2.1/doc/ext_ffi_api.html +++ b/luajit-2.1/doc/ext_ffi_api.html @@ -546,8 +546,8 @@ corresponding ctype. The parser for Lua source code treats numeric literals with the suffixes <tt>LL</tt> or <tt>ULL</tt> as signed or unsigned 64 bit integers. Case doesn't matter, but uppercase is recommended for -readability. It handles both decimal (<tt>42LL</tt>) and hexadecimal -(<tt>0x2aLL</tt>) literals. +readability. It handles decimal (<tt>42LL</tt>), hexadecimal +(<tt>0x2aLL</tt>) and binary (<tt>0b101010LL</tt>) literals. </p> <p> The imaginary part of complex numbers can be specified by suffixing diff --git a/luajit-2.1/doc/ext_ffi_semantics.html b/luajit-2.1/doc/ext_ffi_semantics.html index 889d44d..f65fe8f 100644 --- a/luajit-2.1/doc/ext_ffi_semantics.html +++ b/luajit-2.1/doc/ext_ffi_semantics.html @@ -185,6 +185,8 @@ a <tt>typedef</tt>, except re-declarations will be ignored): <tt>uint16_t</tt>, <tt>uint32_t</tt>, <tt>uint64_t</tt>, <tt>intptr_t</tt>, <tt>uintptr_t</tt>.</li> +<li>From <tt><unistd.h></tt> (POSIX): <tt>ssize_t</tt>.</li> + </ul> <p> You're encouraged to use these types in preference to diff --git a/luajit-2.1/doc/extensions.html b/luajit-2.1/doc/extensions.html index d2f8d7b..e034e1d 100644 --- a/luajit-2.1/doc/extensions.html +++ b/luajit-2.1/doc/extensions.html @@ -183,7 +183,7 @@ in <tt>"-inf"</tt>. <h3 id="tonumber"><tt>tonumber()</tt> etc. use builtin string to number conversion</h3> <p> All string-to-number conversions consistently convert integer and -floating-point inputs in decimal and hexadecimal on all platforms. +floating-point inputs in decimal, hexadecimal and binary on all platforms. <tt>strtod()</tt> is <em>not</em> used anymore, which avoids numerous problems with poor C library implementations. The builtin conversion function provides full precision according to the IEEE-754 standard, it @@ -207,6 +207,11 @@ for dot releases (x.y.0 → x.y.1), but may change with major or minor releases (2.0 → 2.1) or between any beta release. Foreign bytecode (e.g. from Lua 5.1) is incompatible and cannot be loaded. </p> +<p> +Note: <tt>LJ_GC64</tt> mode requires a different frame layout, which implies +a different, incompatible bytecode format for ports that use this mode (e.g. +ARM64). This may be rectified in the future. +</p> <h3 id="table_new"><tt>table.new(narray, nhash)</tt> allocates a pre-sized table</h3> <p> @@ -339,6 +344,13 @@ Lua 5.1, which prevents implementing features that would otherwise break the Lua/C API and ABI (e.g. <tt>_ENV</tt>). </p> +<h2 id="lua53">Extensions from Lua 5.3</h2> +<p> +LuaJIT supports some extensions from Lua 5.3: +<ul> +<li>Unicode escape <tt>'\u{XX...}'</tt> embeds the UTF-8 encoding in string literals.</li> +</ul> + <h2 id="exceptions">C++ Exception Interoperability</h2> <p> LuaJIT has built-in support for interoperating with C++ exceptions. diff --git a/luajit-2.1/doc/install.html b/luajit-2.1/doc/install.html index 9fe0c08..a4cc721 100644 --- a/luajit-2.1/doc/install.html +++ b/luajit-2.1/doc/install.html @@ -114,30 +114,30 @@ operating systems, CPUs and compilers: </tr> <tr class="odd separate"> <td class="compatcpu">x86 (32 bit)</td> -<td class="compatos">GCC 4.x<br>GCC 3.4</td> -<td class="compatos">GCC 4.x<br>GCC 3.4</td> -<td class="compatos">GCC 4.x<br>GCC 3.4</td> +<td class="compatos">GCC 4.2+</td> +<td class="compatos">GCC 4.2+</td> +<td class="compatos">XCode 5.0+<br>Clang</td> <td class="compatos">MSVC, MSVC/EE<br>WinSDK<br>MinGW, Cygwin</td> </tr> <tr class="even"> <td class="compatcpu">x64 (64 bit)</td> -<td class="compatos">GCC 4.x</td> +<td class="compatos">GCC 4.2+</td> <td class="compatos">ORBIS (<a href="#ps4">PS4</a>)</td> -<td class="compatos">GCC 4.x</td> -<td class="compatos">MSVC + SDK v7.0<br>WinSDK v7.0</td> +<td class="compatos">XCode 5.0+<br>Clang</td> +<td class="compatos">MSVC + SDK v7.0<br>WinSDK v7.0<br>Durango (<a href="#xboxone">Xbox One</a>)</td> </tr> <tr class="odd"> <td class="compatcpu"><a href="#cross2">ARMv5+<br>ARM9E+</a></td> <td class="compatos">GCC 4.2+</td> <td class="compatos">GCC 4.2+<br>PSP2 (<a href="#psvita">PS VITA</a>)</td> -<td class="compatos">GCC 4.2+</td> +<td class="compatos">XCode 5.0+<br>Clang</td> <td class="compatos compatno"> </td> </tr> <tr class="even"> <td class="compatcpu"><a href="#cross2">ARM64</a></td> <td class="compatos">GCC 4.8+</td> <td class="compatos compatno"> </td> -<td class="compatos">Clang 3.5+</td> +<td class="compatos">XCode 6.0+<br>Clang 3.5+</td> <td class="compatos compatno"> </td> </tr> <tr class="odd"> @@ -190,8 +190,8 @@ open a terminal window and change to this directory. Now unpack the archive and change to the newly created directory: </p> <pre class="code"> -tar zxf LuaJIT-2.0.3.tar.gz -cd LuaJIT-2.0.3</pre> +tar zxf LuaJIT-2.0.4.tar.gz +cd LuaJIT-2.0.4</pre> <h3>Building LuaJIT</h3> <p> The supplied Makefiles try to auto-detect the settings needed for your @@ -442,8 +442,7 @@ NDKF="--sysroot $NDK/platforms/android-$NDKABI/arch-x86" make HOST_CC="gcc -m32" CROSS=$NDKP TARGET_FLAGS="$NDKF" </pre> <p> -You can cross-compile for <b id="ios">iOS 3.0+</b> (iPhone/iPad) using the <a href="http://developer.apple.com/devcenter/ios/index.action"><span class="ext">»</span> iOS SDK</a>. -The environment variables need to match the iOS SDK version: +You can cross-compile for <b id="ios">iOS 3.0+</b> (iPhone/iPad) using the <a href="http://developer.apple.com/devcenter/ios/index.action"><span class="ext">»</span> iOS SDK</a>: </p> <p style="font-size: 8pt;"> Note: <b>the JIT compiler is disabled for iOS</b>, because regular iOS Apps @@ -453,13 +452,18 @@ much slower than the JIT compiler. Please complain to Apple, not me. Or use Android. :-p </p> <pre class="code"> -IXCODE=`xcode-select -print-path` -ISDK=$IXCODE/Platforms/iPhoneOS.platform/Developer -ISDKVER=iPhoneOS6.0.sdk -ISDKP=$ISDK/usr/bin/ -ISDKF="-arch armv7 -isysroot $ISDK/SDKs/$ISDKVER" -make HOST_CC="gcc -m32 -arch i386" CROSS=$ISDKP TARGET_FLAGS="$ISDKF" \ - TARGET_SYS=iOS +# iOS/ARM (32 bit) +ISDKP=$(xcrun --sdk iphoneos --show-sdk-path) +ICC=$(xcrun --sdk iphoneos --find clang) +ISDKF="-arch armv7 -isysroot $ISDKP" +make HOST_CC="clang -m32 -arch i386" CROSS="$(dirname $ICC)/" \ + TARGET_FLAGS="$ISDKF" TARGET_SYS=iOS + +# iOS/ARM64 +ISDKP=$(xcrun --sdk iphoneos --show-sdk-path) +ICC=$(xcrun --sdk iphoneos --find clang) +ISDKF="-arch arm64 -isysroot $ISDKP" +make CROSS="$(dirname $ICC)/" TARGET_FLAGS="$ISDKF" TARGET_SYS=iOS </pre> <h3 id="consoles">Cross-compiling for consoles</h3> @@ -516,6 +520,16 @@ the following commands: cd src xedkbuild </pre> +<p> +To cross-compile for <b id="xboxone">Xbox One</b> from a Windows host, +open a "Visual Studio .NET Command Prompt" (64 bit host compiler), +<tt>cd</tt> to the directory where you've unpacked the sources and run +the following commands: +</p> +<pre class="code"> +cd src +xb1build +</pre> <h2 id="embed">Embedding LuaJIT</h2> <p> diff --git a/luajit-2.1/doc/luajit.html b/luajit-2.1/doc/luajit.html index 721f636..8a653e2 100644 --- a/luajit-2.1/doc/luajit.html +++ b/luajit-2.1/doc/luajit.html @@ -166,7 +166,7 @@ LuaJIT is Copyright © 2005-2015 Mike Pall, released under the <tr><td><span style="font-size:90%;">Embedded</span></td><td>Android</td><td>iOS</td></tr> </table> <table class="feature os os3"> -<tr><td>PS3</td><td>PS4</td><td>PS Vita</td><td>Xbox 360</td></tr> +<tr><td>PS3</td><td>PS4</td><td>PS Vita</td><td>Xbox 360</td><td>Xbox One</td></tr> </table> <table class="feature compiler"> <tr><td>GCC</td><td>CLANG<br>LLVM</td><td>MSVC</td></tr> diff --git a/luajit-2.1/doc/running.html b/luajit-2.1/doc/running.html index 2b764dc..5ee67c9 100644 --- a/luajit-2.1/doc/running.html +++ b/luajit-2.1/doc/running.html @@ -189,7 +189,7 @@ itself. For a description of their options and output format, please read the comment block at the start of their source. They can be found in the <tt>lib</tt> directory of the source distribution or installed under the <tt>jit</tt> directory. By default -this is <tt>/usr/local/share/luajit-2.0.3/jit</tt> on POSIX +this is <tt>/usr/local/share/luajit-2.0.4/jit</tt> on POSIX systems. </p> diff --git a/luajit-2.1/doc/status.html b/luajit-2.1/doc/status.html index cf137ee..91ed9cb 100644 --- a/luajit-2.1/doc/status.html +++ b/luajit-2.1/doc/status.html @@ -1,7 +1,7 @@ <!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01//EN" "http://www.w3.org/TR/html4/strict.dtd"> <html> <head> -<title>Status & Roadmap</title> +<title>Status</title> <meta http-equiv="Content-Type" content="text/html; charset=iso-8859-1"> <meta name="Author" content="Mike Pall"> <meta name="Copyright" content="Copyright (C) 2005-2015, Mike Pall"> @@ -17,7 +17,7 @@ ul li { padding-bottom: 0.3em; } <a href="http://luajit.org"><span>Lua<span id="logo">JIT</span></span></a> </div> <div id="head"> -<h1>Status & Roadmap</h1> +<h1>Status</h1> </div> <div id="nav"> <ul><li> @@ -104,15 +104,6 @@ handled correctly. The error may fall through an on-trace garbage collector. </li> </ul> - -<h2>Roadmap</h2> -<p> -Please refer to the -<a href="http://www.freelists.org/post/luajit/LuaJIT-Roadmap-20122013"><span class="ext">»</span> LuaJIT Roadmap 2012/2013</a> and an -<a href="http://www.freelists.org/post/luajit/LuaJIT-Roadmap-20122013-UPDATE"><span class="ext">»</span> update on release planning</a> for details. -</p> -<p> -</p> <br class="flush"> </div> <div id="foot"> diff --git a/luajit-2.1/dynasm/dasm_arm.lua b/luajit-2.1/dynasm/dasm_arm.lua index 90a259c..6a1d1d5 100644 --- a/luajit-2.1/dynasm/dasm_arm.lua +++ b/luajit-2.1/dynasm/dasm_arm.lua @@ -9,9 +9,9 @@ local _info = { arch = "arm", description = "DynASM ARM module", - version = "1.3.0", - vernum = 10300, - release = "2011-05-05", + version = "1.4.0", + vernum = 10400, + release = "2015-10-18", author = "Mike Pall", license = "MIT", } diff --git a/luajit-2.1/dynasm/dasm_arm64.lua b/luajit-2.1/dynasm/dasm_arm64.lua index 9766e47..c1e3a81 100644 --- a/luajit-2.1/dynasm/dasm_arm64.lua +++ b/luajit-2.1/dynasm/dasm_arm64.lua @@ -9,9 +9,9 @@ local _info = { arch = "arm", description = "DynASM ARM64 module", - version = "1.3.0", - vernum = 10300, - release = "2014-12-03", + version = "1.4.0", + vernum = 10400, + release = "2015-10-18", author = "Mike Pall", license = "MIT", } diff --git a/luajit-2.1/dynasm/dasm_mips.lua b/luajit-2.1/dynasm/dasm_mips.lua index ae0dbd7..ef38343 100644 --- a/luajit-2.1/dynasm/dasm_mips.lua +++ b/luajit-2.1/dynasm/dasm_mips.lua @@ -9,9 +9,9 @@ local _info = { arch = "mips", description = "DynASM MIPS module", - version = "1.3.0", - vernum = 10300, - release = "2012-01-23", + version = "1.4.0", + vernum = 10400, + release = "2015-10-18", author = "Mike Pall", license = "MIT", } diff --git a/luajit-2.1/dynasm/dasm_ppc.h b/luajit-2.1/dynasm/dasm_ppc.h index 2ded258..332c64d 100644 --- a/luajit-2.1/dynasm/dasm_ppc.h +++ b/luajit-2.1/dynasm/dasm_ppc.h @@ -21,7 +21,7 @@ enum { /* The following actions need a buffer position. */ DASM_ALIGN, DASM_REL_LG, DASM_LABEL_LG, /* The following actions also have an argument. */ - DASM_REL_PC, DASM_LABEL_PC, DASM_IMM, + DASM_REL_PC, DASM_LABEL_PC, DASM_IMM, DASM_IMMSH, DASM__MAX }; @@ -244,6 +244,10 @@ void dasm_put(Dst_DECL, int start, ...) #endif b[pos++] = n; break; + case DASM_IMMSH: + CK((n >> 6) == 0, RANGE_I); + b[pos++] = n; + break; } } } @@ -299,7 +303,7 @@ int dasm_link(Dst_DECL, size_t *szp) case DASM_ALIGN: ofs -= (b[pos++] + ofs) & (ins & 255); break; case DASM_REL_LG: case DASM_REL_PC: pos++; break; case DASM_LABEL_LG: case DASM_LABEL_PC: b[pos++] += ofs; break; - case DASM_IMM: pos++; break; + case DASM_IMM: case DASM_IMMSH: pos++; break; } } stop: (void)0; @@ -366,6 +370,9 @@ int dasm_encode(Dst_DECL, void *buffer) case DASM_IMM: cp[-1] |= (n & ((1<<((ins>>5)&31))-1)) << (ins&31); break; + case DASM_IMMSH: + cp[-1] |= (ins & 1) ? ((n&31)<<11)|((n&32)>>4) : ((n&31)<<6)|(n&32); + break; default: *cp++ = ins; break; } } diff --git a/luajit-2.1/dynasm/dasm_ppc.lua b/luajit-2.1/dynasm/dasm_ppc.lua index 3744707..1e9bcca 100644 --- a/luajit-2.1/dynasm/dasm_ppc.lua +++ b/luajit-2.1/dynasm/dasm_ppc.lua @@ -11,9 +11,9 @@ local _info = { arch = "ppc", description = "DynASM PPC module", - version = "1.3.0", - vernum = 10300, - release = "2015-01-14", + version = "1.4.0", + vernum = 10400, + release = "2015-10-18", author = "Mike Pall", license = "MIT", } @@ -41,7 +41,7 @@ local wline, werror, wfatal, wwarn local action_names = { "STOP", "SECTION", "ESC", "REL_EXT", "ALIGN", "REL_LG", "LABEL_LG", - "REL_PC", "LABEL_PC", "IMM", + "REL_PC", "LABEL_PC", "IMM", "IMMSH" } -- Maximum number of section buffer positions for dasm_put(). @@ -230,8 +230,18 @@ local map_cond = { ------------------------------------------------------------------------------ +local map_op, op_template + +local function op_alias(opname, f) + return function(params, nparams) + if not params then return "-> "..opname:sub(1, -3) end + f(params, nparams) + op_template(params, map_op[opname], nparams) + end +end + -- Template strings for PPC instructions. -local map_op = { +map_op = { tdi_3 = "08000000ARI", twi_3 = "0c000000ARI", mulli_3 = "1c000000RRI", @@ -299,6 +309,33 @@ local map_op = { std_2 = "f8000000RD", stdu_2 = "f8000001RD", + subi_3 = op_alias("addi_3", function(p) p[3] = "-("..p[3]..")" end), + subis_3 = op_alias("addis_3", function(p) p[3] = "-("..p[3]..")" end), + subic_3 = op_alias("addic_3", function(p) p[3] = "-("..p[3]..")" end), + ["subic._3"] = op_alias("addic._3", function(p) p[3] = "-("..p[3]..")" end), + + rotlwi_3 = op_alias("rlwinm_5", function(p) + p[4] = "0"; p[5] = "31" + end), + rotrwi_3 = op_alias("rlwinm_5", function(p) + p[3] = "32-("..p[3]..")"; p[4] = "0"; p[5] = "31" + end), + rotlw_3 = op_alias("rlwnm_5", function(p) + p[4] = "0"; p[5] = "31" + end), + slwi_3 = op_alias("rlwinm_5", function(p) + p[5] = "31-("..p[3]..")"; p[4] = "0" + end), + srwi_3 = op_alias("rlwinm_5", function(p) + p[4] = p[3]; p[3] = "32-("..p[3]..")"; p[5] = "31" + end), + clrlwi_3 = op_alias("rlwinm_5", function(p) + p[4] = p[3]; p[3] = "0"; p[5] = "31" + end), + clrrwi_3 = op_alias("rlwinm_5", function(p) + p[5] = "31-("..p[3]..")"; p[3] = "0"; p[4] = "0" + end), + -- Primary opcode 4: mulhhwu_3 = "10000010RRR.", machhwu_3 = "10000018RRR.", @@ -790,6 +827,28 @@ local map_op = { rldcl_4 = "78000010RR~RM.", rldcr_4 = "78000012RR~RM.", + rotldi_3 = op_alias("rldicl_4", function(p) + p[4] = "0" + end), + rotrdi_3 = op_alias("rldicl_4", function(p) + p[3] = "64-("..p[3]..")"; p[4] = "0" + end), + rotld_3 = op_alias("rldcl_4", function(p) + p[4] = "0" + end), + sldi_3 = op_alias("rldicr_4", function(p) + p[4] = "63-("..p[3]..")" + end), + srdi_3 = op_alias("rldicl_4", function(p) + p[4] = p[3]; p[3] = "64-("..p[3]..")" + end), + clrldi_3 = op_alias("rldicl_4", function(p) + p[4] = p[3]; p[3] = "0" + end), + clrrdi_3 = op_alias("rldicr_4", function(p) + p[4] = "63-("..p[3]..")"; p[3] = "0" + end), + -- Primary opcode 56: lq_2 = "e0000000R:D", -- NYI: displacement must be divisible by 8. @@ -1358,7 +1417,7 @@ local map_op = { do local t = {} for k,v in pairs(map_op) do - if sub(v, -1) == "." then + if type(v) == "string" and sub(v, -1) == "." then local v2 = sub(v, 1, 7)..char(byte(v, 8)+1)..sub(v, 9, -2) t[sub(k, 1, -3).."."..sub(k, -2)] = v2 end @@ -1454,8 +1513,30 @@ local function parse_cond(expr) werror("bad condition bit name `"..expr.."'") end +local parse_ctx = {} + +local loadenv = setfenv and function(s) + local code = loadstring(s, "") + if code then setfenv(code, parse_ctx) end + return code +end or function(s) + return load(s, "", nil, parse_ctx) +end + +-- Try to parse simple arithmetic, too, since some basic ops are aliases. +local function parse_number(n) + local x = tonumber(n) + if x then return x end + local code = loadenv("return "..n) + if code then + local ok, y = pcall(code) + if ok then return y end + end + return nil +end + local function parse_imm(imm, bits, shift, scale, signed) - local n = tonumber(imm) + local n = parse_number(imm) if n then local m = sar(n, scale) if shl(m, scale) == n then @@ -1479,11 +1560,11 @@ local function parse_imm(imm, bits, shift, scale, signed) end local function parse_shiftmask(imm, isshift) - local n = tonumber(imm) + local n = parse_number(imm) if n then if shr(n, 6) == 0 then - local lsb = band(imm, 31) - local msb = imm - lsb + local lsb = band(n, 31) + local msb = n - lsb return isshift and (shl(lsb, 11)+shr(msb, 4)) or (shl(lsb, 6)+msb) end werror("out of range immediate `"..imm.."'") @@ -1491,7 +1572,8 @@ local function parse_shiftmask(imm, isshift) match(imm, "^([%w_]+):(r[1-3]?[0-9])$") then werror("expected immediate operand, got register") else - werror("NYI: parameterized 64 bit shift/mask") + waction("IMMSH", isshift and 1 or 0, imm) + return 0; end end @@ -1566,7 +1648,7 @@ end ------------------------------------------------------------------------------ -- Handle opcodes defined with template strings. -map_op[".template__"] = function(params, template, nparams) +op_template = function(params, template, nparams) if not params then return sub(template, 9) end local op = tonumber(sub(template, 1, 8), 16) local n, rs = 1, 26 @@ -1668,6 +1750,8 @@ map_op[".template__"] = function(params, template, nparams) wputpos(pos, op) end +map_op[".template__"] = op_template + ------------------------------------------------------------------------------ -- Pseudo-opcode to mark the position where the action list is to be emitted. diff --git a/luajit-2.1/dynasm/dasm_proto.h b/luajit-2.1/dynasm/dasm_proto.h index a8bc6fd..93ca065 100644 --- a/luajit-2.1/dynasm/dasm_proto.h +++ b/luajit-2.1/dynasm/dasm_proto.h @@ -10,8 +10,8 @@ #include <stddef.h> #include <stdarg.h> -#define DASM_IDENT "DynASM 1.3.0" -#define DASM_VERSION 10300 /* 1.3.0 */ +#define DASM_IDENT "DynASM 1.4.0" +#define DASM_VERSION 10400 /* 1.4.0 */ #ifndef Dst_DECL #define Dst_DECL dasm_State **Dst diff --git a/luajit-2.1/dynasm/dasm_x86.h b/luajit-2.1/dynasm/dasm_x86.h index 652e8c9..175febe 100644 --- a/luajit-2.1/dynasm/dasm_x86.h +++ b/luajit-2.1/dynasm/dasm_x86.h @@ -391,7 +391,12 @@ int dasm_encode(Dst_DECL, void *buffer) case DASM_IMM_D: wd: dasmd(n); break; case DASM_IMM_WB: if (((n+128)&-256) == 0) goto db; else mark = NULL; case DASM_IMM_W: dasmw(n); break; - case DASM_VREG: { int t = *p++; if (t >= 2) n<<=3; cp[-1] |= n; break; } + case DASM_VREG: { + int t = *p++; + if (t >= 5) n <<= 4; else if (t >= 2) n <<= 3; + cp[-1] ^= n; + break; + } case DASM_REL_LG: p++; if (n >= 0) goto rel_pc; b++; n = (int)(ptrdiff_t)D->globals[-n]; case DASM_REL_A: rel_a: n -= (int)(ptrdiff_t)(cp+4); goto wd; /* !x64 */ diff --git a/luajit-2.1/dynasm/dasm_x86.lua b/luajit-2.1/dynasm/dasm_x86.lua index 7ca061d..1fa80b5 100644 --- a/luajit-2.1/dynasm/dasm_x86.lua +++ b/luajit-2.1/dynasm/dasm_x86.lua @@ -11,9 +11,9 @@ local x64 = x64 local _info = { arch = x64 and "x64" or "x86", description = "DynASM x86/x64 module", - version = "1.3.0", - vernum = 10300, - release = "2011-05-05", + version = "1.4.0", + vernum = 10400, + release = "2015-10-18", author = "Mike Pall", license = "MIT", } @@ -27,9 +27,9 @@ local assert, unpack, setmetatable = assert, unpack or table.unpack, setmetatabl local _s = string local sub, format, byte, char = _s.sub, _s.format, _s.byte, _s.char local find, match, gmatch, gsub = _s.find, _s.match, _s.gmatch, _s.gsub -local concat, sort = table.concat, table.sort +local concat, sort, remove = table.concat, table.sort, table.remove local bit = bit or require("bit") -local band, shl, shr = bit.band, bit.lshift, bit.rshift +local band, bxor, shl, shr = bit.band, bit.bxor, bit.lshift, bit.rshift -- Inherited tables and callbacks. local g_opt, g_arch @@ -299,7 +299,7 @@ local function mkrmap(sz, cl, names) local iname = format("@%s%x%s", sz, i, needrex and "R" or "") if needrex then map_reg_needrex[iname] = true end local name - if sz == "o" then name = format("xmm%d", i) + if sz == "o" or sz == "y" then name = format("%s%d", cl, i) elseif sz == "f" then name = format("st%d", i) else name = format("r%d%s", i, sz == addrsize and "" or sz) end map_archdef[name] = iname @@ -334,21 +334,24 @@ mkrmap("f", "Rf") -- SSE registers (oword sized, but qword and dword accessible). mkrmap("o", "xmm") +-- AVX registers (yword sized, but oword, qword and dword accessible). +mkrmap("y", "ymm") + -- Operand size prefixes to codes. local map_opsize = { - byte = "b", word = "w", dword = "d", qword = "q", oword = "o", tword = "t", - aword = addrsize, + byte = "b", word = "w", dword = "d", qword = "q", oword = "o", yword = "y", + tword = "t", aword = addrsize, } -- Operand size code to number. local map_opsizenum = { - b = 1, w = 2, d = 4, q = 8, o = 16, t = 10, + b = 1, w = 2, d = 4, q = 8, o = 16, y = 32, t = 10, } -- Operand size code to name. local map_opsizename = { - b = "byte", w = "word", d = "dword", q = "qword", o = "oword", t = "tword", - f = "fpword", + b = "byte", w = "word", d = "dword", q = "qword", o = "oword", y = "yword", + t = "tword", f = "fpword", } -- Valid index register scale factors. @@ -460,7 +463,29 @@ local function wputszarg(sz, n) end -- Put multi-byte opcode with operand-size dependent modifications. -local function wputop(sz, op, rex) +local function wputop(sz, op, rex, vex) + if vex then + local tail + if vex.m == 1 and band(rex, 11) == 0 then + wputb(0xc5) + tail = shl(bxor(band(rex, 4), 4), 5) + else + wputb(0xc4) + wputb(shl(bxor(band(rex, 7), 7), 5) + vex.m) + tail = shl(band(rex, 8), 4) + end + local reg, vreg = 0, nil + if vex.v then + reg = vex.v.reg + if not reg then werror("bad vex operand") end + if reg < 0 then reg = 0; vreg = vex.v.vreg end + end + if sz == "y" or vex.l then tail = tail + 4 end + wputb(tail + shl(bxor(reg, 15), 3) + vex.p) + if vreg then waction("VREG", vreg); wputxb(4) end + rex = 0 + if op >= 256 then werror("bad vex opcode") end + end local r if rex ~= 0 and not x64 then werror("bad operand size") end if sz == "w" then wputb(102) end @@ -881,9 +906,15 @@ end -- "m"/"M" generates ModRM/SIB from the 1st/2nd operand. -- The spare 3 bits are either filled with the last hex digit or -- the result from a previous "r"/"R". The opcode is restored. +-- "u" Use VEX encoding, vvvv unused. +-- "v"/"V" Use VEX encoding, vvvv from 1st/2nd operand (the operand is +-- removed from the list used by future characters). +-- "L" Force VEX.L -- -- All of the following characters force a flush of the opcode: -- "o"/"O" stores a pure 32 bit disp (offset) from the 1st/2nd operand. +-- "s" stores a 4 bit immediate from the last register operand, +-- followed by 4 zero bits. -- "S" stores a signed 8 bit immediate from the last operand. -- "U" stores an unsigned 8 bit immediate from the last operand. -- "W" stores an unsigned 16 bit immediate from the last operand. @@ -1081,10 +1112,11 @@ local map_op = { btr_2 = "mrqdw:0FB3Rm|miqdw:0FBA6mU", bts_2 = "mrqdw:0FABRm|miqdw:0FBA5mU", - shld_3 = "mriqdw:0FA4RmU|mrCqdw:0FA5Rm", - shrd_3 = "mriqdw:0FACRmU|mrCqdw:0FADRm", + shld_3 = "mriqdw:0FA4RmU|mrC/qq:0FA5Rm|mrC/dd:|mrC/ww:", + shrd_3 = "mriqdw:0FACRmU|mrC/qq:0FADRm|mrC/dd:|mrC/ww:", rdtsc_0 = "0F31", -- P1+ + rdpmc_0 = "0F33", -- P6+ cpuid_0 = "0FA2", -- P1+ -- floating point ops @@ -1190,7 +1222,7 @@ local map_op = { cvtsi2sd_2 = "rm/od:F20F2ArM|rm/oq:F20F2ArXM", cvtsi2ss_2 = "rm/od:F30F2ArM|rm/oq:F30F2ArXM", cvtss2sd_2 = "rro:F30F5ArM|rx/od:", - cvtss2si_2 = "rr/do:F20F2CrM|rr/qo:|rxd:|rx/qd:", + cvtss2si_2 = "rr/do:F30F2DrM|rr/qo:|rxd:|rx/qd:", cvttpd2dq_2 = "rmo:660FE6rM", cvttps2dq_2 = "rmo:F30F5BrM", cvttsd2si_2 = "rr/do:F20F2CrM|rr/qo:|rx/dq:|rxq:", @@ -1225,46 +1257,14 @@ local map_op = { movups_2 = "rmo:0F10rM|mro:0F11Rm", orpd_2 = "rmo:660F56rM", orps_2 = "rmo:0F56rM", - packssdw_2 = "rmo:660F6BrM", - packsswb_2 = "rmo:660F63rM", - packuswb_2 = "rmo:660F67rM", - paddb_2 = "rmo:660FFCrM", - paddd_2 = "rmo:660FFErM", - paddq_2 = "rmo:660FD4rM", - paddsb_2 = "rmo:660FECrM", - paddsw_2 = "rmo:660FEDrM", - paddusb_2 = "rmo:660FDCrM", - paddusw_2 = "rmo:660FDDrM", - paddw_2 = "rmo:660FFDrM", - pand_2 = "rmo:660FDBrM", - pandn_2 = "rmo:660FDFrM", pause_0 = "F390", - pavgb_2 = "rmo:660FE0rM", - pavgw_2 = "rmo:660FE3rM", - pcmpeqb_2 = "rmo:660F74rM", - pcmpeqd_2 = "rmo:660F76rM", - pcmpeqw_2 = "rmo:660F75rM", - pcmpgtb_2 = "rmo:660F64rM", - pcmpgtd_2 = "rmo:660F66rM", - pcmpgtw_2 = "rmo:660F65rM", - pextrw_3 = "rri/do:660FC5rMU|xri/wo:660F3A15nrMU", -- Mem op: SSE4.1 only. + pextrw_3 = "rri/do:660FC5rMU|xri/wo:660F3A15nRmU", -- Mem op: SSE4.1 only. pinsrw_3 = "rri/od:660FC4rMU|rxi/ow:", - pmaddwd_2 = "rmo:660FF5rM", - pmaxsw_2 = "rmo:660FEErM", - pmaxub_2 = "rmo:660FDErM", - pminsw_2 = "rmo:660FEArM", - pminub_2 = "rmo:660FDArM", pmovmskb_2 = "rr/do:660FD7rM", - pmulhuw_2 = "rmo:660FE4rM", - pmulhw_2 = "rmo:660FE5rM", - pmullw_2 = "rmo:660FD5rM", - pmuludq_2 = "rmo:660FF4rM", - por_2 = "rmo:660FEBrM", prefetchnta_1 = "xb:n0F180m", prefetcht0_1 = "xb:n0F181m", prefetcht1_1 = "xb:n0F182m", prefetcht2_1 = "xb:n0F183m", - psadbw_2 = "rmo:660FF6rM", pshufd_3 = "rmio:660F70rMU", pshufhw_3 = "rmio:F30F70rMU", pshuflw_3 = "rmio:F20F70rMU", @@ -1278,23 +1278,6 @@ local map_op = { psrldq_2 = "rio:660F733mU", psrlq_2 = "rmo:660FD3rM|rio:660F732mU", psrlw_2 = "rmo:660FD1rM|rio:660F712mU", - psubb_2 = "rmo:660FF8rM", - psubd_2 = "rmo:660FFArM", - psubq_2 = "rmo:660FFBrM", - psubsb_2 = "rmo:660FE8rM", - psubsw_2 = "rmo:660FE9rM", - psubusb_2 = "rmo:660FD8rM", - psubusw_2 = "rmo:660FD9rM", - psubw_2 = "rmo:660FF9rM", - punpckhbw_2 = "rmo:660F68rM", - punpckhdq_2 = "rmo:660F6ArM", - punpckhqdq_2 = "rmo:660F6DrM", - punpckhwd_2 = "rmo:660F69rM", - punpcklbw_2 = "rmo:660F60rM", - punpckldq_2 = "rmo:660F62rM", - punpcklqdq_2 = "rmo:660F6CrM", - punpcklwd_2 = "rmo:660F61rM", - pxor_2 = "rmo:660FEFrM", rcpps_2 = "rmo:0F53rM", rcpss_2 = "rro:F30F53rM|rx/od:", rsqrtps_2 = "rmo:0F52rM", @@ -1352,7 +1335,7 @@ local map_op = { dpps_3 = "rmio:660F3A40rMU", extractps_3 = "mri/do:660F3A17RmU|rri/qo:660F3A17RXmU", insertps_3 = "rrio:660F3A41rMU|rxi/od:", - movntdqa_2 = "rmo:660F382ArM", + movntdqa_2 = "rxo:660F382ArM", mpsadbw_3 = "rmio:660F3A42rMU", packusdw_2 = "rmo:660F382BrM", pblendvb_3 = "rmRo:660F3810rM", @@ -1412,6 +1395,232 @@ local map_op = { movntsd_2 = "xr/qo:nF20F2BRm", movntss_2 = "xr/do:F30F2BRm", -- popcnt is also in SSE4.2 + + -- AES-NI + aesdec_2 = "rmo:660F38DErM", + aesdeclast_2 = "rmo:660F38DFrM", + aesenc_2 = "rmo:660F38DCrM", + aesenclast_2 = "rmo:660F38DDrM", + aesimc_2 = "rmo:660F38DBrM", + aeskeygenassist_3 = "rmio:660F3ADFrMU", + pclmulqdq_3 = "rmio:660F3A44rMU", + + -- AVX FP ops + vaddsubpd_3 = "rrmoy:660FVD0rM", + vaddsubps_3 = "rrmoy:F20FVD0rM", + vandpd_3 = "rrmoy:660FV54rM", + vandps_3 = "rrmoy:0FV54rM", + vandnpd_3 = "rrmoy:660FV55rM", + vandnps_3 = "rrmoy:0FV55rM", + vblendpd_4 = "rrmioy:660F3AV0DrMU", + vblendps_4 = "rrmioy:660F3AV0CrMU", + vblendvpd_4 = "rrmroy:660F3AV4BrMs", + vblendvps_4 = "rrmroy:660F3AV4ArMs", + vbroadcastf128_2 = "rx/yo:660F38u1ArM", + vcmppd_4 = "rrmioy:660FVC2rMU", + vcmpps_4 = "rrmioy:0FVC2rMU", + vcmpsd_4 = "rrrio:F20FVC2rMU|rrxi/ooq:", + vcmpss_4 = "rrrio:F30FVC2rMU|rrxi/ood:", + vcomisd_2 = "rro:660Fu2FrM|rx/oq:", + vcomiss_2 = "rro:0Fu2FrM|rx/od:", + vcvtdq2pd_2 = "rro:F30FuE6rM|rx/oq:|rm/yo:", + vcvtdq2ps_2 = "rmoy:0Fu5BrM", + vcvtpd2dq_2 = "rmoy:F20FuE6rM", + vcvtpd2ps_2 = "rmoy:660Fu5ArM", + vcvtps2dq_2 = "rmoy:660Fu5BrM", + vcvtps2pd_2 = "rro:0Fu5ArM|rx/oq:|rm/yo:", + vcvtsd2si_2 = "rr/do:F20Fu2DrM|rx/dq:|rr/qo:|rxq:", + vcvtsd2ss_3 = "rrro:F20FV5ArM|rrx/ooq:", + vcvtsi2sd_3 = "rrm/ood:F20FV2ArM|rrm/ooq:F20FVX2ArM", + vcvtsi2ss_3 = "rrm/ood:F30FV2ArM|rrm/ooq:F30FVX2ArM", + vcvtss2sd_3 = "rrro:F30FV5ArM|rrx/ood:", + vcvtss2si_2 = "rr/do:F30Fu2DrM|rxd:|rr/qo:|rx/qd:", + vcvttpd2dq_2 = "rmo:660FuE6rM|rm/oy:660FuLE6rM", + vcvttps2dq_2 = "rmoy:F30Fu5BrM", + vcvttsd2si_2 = "rr/do:F20Fu2CrM|rx/dq:|rr/qo:|rxq:", + vcvttss2si_2 = "rr/do:F30Fu2CrM|rxd:|rr/qo:|rx/qd:", + vdppd_4 = "rrmio:660F3AV41rMU", + vdpps_4 = "rrmioy:660F3AV40rMU", + vextractf128_3 = "mri/oy:660F3AuL19RmU", + vextractps_3 = "mri/do:660F3Au17RmU", + vhaddpd_3 = "rrmoy:660FV7CrM", + vhaddps_3 = "rrmoy:F20FV7CrM", + vhsubpd_3 = "rrmoy:660FV7DrM", + vhsubps_3 = "rrmoy:F20FV7DrM", + vinsertf128_4 = "rrmi/yyo:660F3AV18rMU", + vinsertps_4 = "rrrio:660F3AV21rMU|rrxi/ood:", + vldmxcsr_1 = "xd:0FuAE2m", + vmaskmovps_3 = "rrxoy:660F38V2CrM|xrroy:660F38V2ERm", + vmaskmovpd_3 = "rrxoy:660F38V2DrM|xrroy:660F38V2FRm", + vmovapd_2 = "rmoy:660Fu28rM|mroy:660Fu29Rm", + vmovaps_2 = "rmoy:0Fu28rM|mroy:0Fu29Rm", + vmovd_2 = "rm/od:660Fu6ErM|rm/oq:660FuX6ErM|mr/do:660Fu7ERm|mr/qo:", + vmovq_2 = "rro:F30Fu7ErM|rx/oq:|xr/qo:660FuD6Rm", + vmovddup_2 = "rmy:F20Fu12rM|rro:|rx/oq:", + vmovhlps_3 = "rrro:0FV12rM", + vmovhpd_2 = "xr/qo:660Fu17Rm", + vmovhpd_3 = "rrx/ooq:660FV16rM", + vmovhps_2 = "xr/qo:0Fu17Rm", + vmovhps_3 = "rrx/ooq:0FV16rM", + vmovlhps_3 = "rrro:0FV16rM", + vmovlpd_2 = "xr/qo:660Fu13Rm", + vmovlpd_3 = "rrx/ooq:660FV12rM", + vmovlps_2 = "xr/qo:0Fu13Rm", + vmovlps_3 = "rrx/ooq:0FV12rM", + vmovmskpd_2 = "rr/do:660Fu50rM|rr/dy:660FuL50rM", + vmovmskps_2 = "rr/do:0Fu50rM|rr/dy:0FuL50rM", + vmovntpd_2 = "xroy:660Fu2BRm", + vmovntps_2 = "xroy:0Fu2BRm", + vmovsd_2 = "rx/oq:F20Fu10rM|xr/qo:F20Fu11Rm", + vmovsd_3 = "rrro:F20FV10rM", + vmovshdup_2 = "rmoy:F30Fu16rM", + vmovsldup_2 = "rmoy:F30Fu12rM", + vmovss_2 = "rx/od:F30Fu10rM|xr/do:F30Fu11Rm", + vmovss_3 = "rrro:F30FV10rM", + vmovupd_2 = "rmoy:660Fu10rM|mroy:660Fu11Rm", + vmovups_2 = "rmoy:0Fu10rM|mroy:0Fu11Rm", + vorpd_3 = "rrmoy:660FV56rM", + vorps_3 = "rrmoy:0FV56rM", + vpermilpd_3 = "rrmoy:660F38V0DrM|rmioy:660F3Au05rMU", + vpermilps_3 = "rrmoy:660F38V0CrM|rmioy:660F3Au04rMU", + vperm2f128_4 = "rrmiy:660F3AV06rMU", + vptestpd_2 = "rmoy:660F38u0FrM", + vptestps_2 = "rmoy:660F38u0ErM", + vrcpps_2 = "rmoy:0Fu53rM", + vrcpss_3 = "rrro:F30FV53rM|rrx/ood:", + vrsqrtps_2 = "rmoy:0Fu52rM", + vrsqrtss_3 = "rrro:F30FV52rM|rrx/ood:", + vroundpd_3 = "rmioy:660F3AV09rMU", + vroundps_3 = "rmioy:660F3AV08rMU", + vroundsd_4 = "rrrio:660F3AV0BrMU|rrxi/ooq:", + vroundss_4 = "rrrio:660F3AV0ArMU|rrxi/ood:", + vshufpd_4 = "rrmioy:660FVC6rMU", + vshufps_4 = "rrmioy:0FVC6rMU", + vsqrtps_2 = "rmoy:0Fu51rM", + vsqrtss_2 = "rro:F30Fu51rM|rx/od:", + vsqrtpd_2 = "rmoy:660Fu51rM", + vsqrtsd_2 = "rro:F20Fu51rM|rx/oq:", + vstmxcsr_1 = "xd:0FuAE3m", + vucomisd_2 = "rro:660Fu2ErM|rx/oq:", + vucomiss_2 = "rro:0Fu2ErM|rx/od:", + vunpckhpd_3 = "rrmoy:660FV15rM", + vunpckhps_3 = "rrmoy:0FV15rM", + vunpcklpd_3 = "rrmoy:660FV14rM", + vunpcklps_3 = "rrmoy:0FV14rM", + vxorpd_3 = "rrmoy:660FV57rM", + vxorps_3 = "rrmoy:0FV57rM", + vzeroall_0 = "0FuL77", + vzeroupper_0 = "0Fu77", + + -- AVX2 FP ops + vbroadcastss_2 = "rx/od:660F38u18rM|rx/yd:|rro:|rr/yo:", + vbroadcastsd_2 = "rx/yq:660F38u19rM|rr/yo:", + -- *vgather* (!vsib) + vpermpd_3 = "rmiy:660F3AuX01rMU", + vpermps_3 = "rrmy:660F38V16rM", + + -- AVX, AVX2 integer ops + -- In general, xmm requires AVX, ymm requires AVX2. + vlddqu_2 = "rxoy:F20FuF0rM", + vmaskmovdqu_2 = "rro:660FuF7rM", + vmovdqa_2 = "rmoy:660Fu6FrM|mroy:660Fu7FRm", + vmovdqu_2 = "rmoy:F30Fu6FrM|mroy:F30Fu7FRm", + vmovntdq_2 = "xroy:660FuE7Rm", + vmovntdqa_2 = "rxoy:660F38u2ArM", + vmpsadbw_4 = "rrmioy:660F3AV42rMU", + vpabsb_2 = "rmoy:660F38u1CrM", + vpabsd_2 = "rmoy:660F38u1ErM", + vpabsw_2 = "rmoy:660F38u1DrM", + vpackusdw_3 = "rrmoy:660F38V2BrM", + vpalignr_4 = "rrmioy:660F3AV0FrMU", + vpblendvb_4 = "rrmroy:660F3AV4CrMs", + vpblendw_4 = "rrmioy:660F3AV0ErMU", + vpclmulqdq_4 = "rrmio:660F3AV44rMU", + vpcmpeqq_3 = "rrmoy:660F38V29rM", + vpcmpestri_3 = "rmio:660F3Au61rMU", + vpcmpestrm_3 = "rmio:660F3Au60rMU", + vpcmpgtq_3 = "rrmoy:660F38V37rM", + vpcmpistri_3 = "rmio:660F3Au63rMU", + vpcmpistrm_3 = "rmio:660F3Au62rMU", + vpextrb_3 = "rri/do:660F3Au14nRmU|rri/qo:|xri/bo:", + vpextrw_3 = "rri/do:660FuC5rMU|xri/wo:660F3Au15nRmU", + vpextrd_3 = "mri/do:660F3Au16RmU", + vpextrq_3 = "mri/qo:660F3Au16RmU", + vphaddw_3 = "rrmoy:660F38V01rM", + vphaddd_3 = "rrmoy:660F38V02rM", + vphaddsw_3 = "rrmoy:660F38V03rM", + vphminposuw_2 = "rmo:660F38u41rM", + vphsubw_3 = "rrmoy:660F38V05rM", + vphsubd_3 = "rrmoy:660F38V06rM", + vphsubsw_3 = "rrmoy:660F38V07rM", + vpinsrb_4 = "rrri/ood:660F3AV20rMU|rrxi/oob:", + vpinsrw_4 = "rrri/ood:660FVC4rMU|rrxi/oow:", + vpinsrd_4 = "rrmi/ood:660F3AV22rMU", + vpinsrq_4 = "rrmi/ooq:660F3AVX22rMU", + vpmaddubsw_3 = "rrmoy:660F38V04rM", + vpmaxsb_3 = "rrmoy:660F38V3CrM", + vpmaxsd_3 = "rrmoy:660F38V3DrM", + vpmaxuw_3 = "rrmoy:660F38V3ErM", + vpmaxud_3 = "rrmoy:660F38V3FrM", + vpminsb_3 = "rrmoy:660F38V38rM", + vpminsd_3 = "rrmoy:660F38V39rM", + vpminuw_3 = "rrmoy:660F38V3ArM", + vpminud_3 = "rrmoy:660F38V3BrM", + vpmovmskb_2 = "rr/do:660FuD7rM|rr/dy:660FuLD7rM", + vpmovsxbw_2 = "rroy:660F38u20rM|rx/oq:|rx/yo:", + vpmovsxbd_2 = "rroy:660F38u21rM|rx/od:|rx/yq:", + vpmovsxbq_2 = "rroy:660F38u22rM|rx/ow:|rx/yd:", + vpmovsxwd_2 = "rroy:660F38u23rM|rx/oq:|rx/yo:", + vpmovsxwq_2 = "rroy:660F38u24rM|rx/od:|rx/yq:", + vpmovsxdq_2 = "rroy:660F38u25rM|rx/oq:|rx/yo:", + vpmovzxbw_2 = "rroy:660F38u30rM|rx/oq:|rx/yo:", + vpmovzxbd_2 = "rroy:660F38u31rM|rx/od:|rx/yq:", + vpmovzxbq_2 = "rroy:660F38u32rM|rx/ow:|rx/yd:", + vpmovzxwd_2 = "rroy:660F38u33rM|rx/oq:|rx/yo:", + vpmovzxwq_2 = "rroy:660F38u34rM|rx/od:|rx/yq:", + vpmovzxdq_2 = "rroy:660F38u35rM|rx/oq:|rx/yo:", + vpmuldq_3 = "rrmoy:660F38V28rM", + vpmulhrsw_3 = "rrmoy:660F38V0BrM", + vpmulld_3 = "rrmoy:660F38V40rM", + vpshufb_3 = "rrmoy:660F38V00rM", + vpshufd_3 = "rmioy:660Fu70rMU", + vpshufhw_3 = "rmioy:F30Fu70rMU", + vpshuflw_3 = "rmioy:F20Fu70rMU", + vpsignb_3 = "rrmoy:660F38V08rM", + vpsignw_3 = "rrmoy:660F38V09rM", + vpsignd_3 = "rrmoy:660F38V0ArM", + vpslldq_3 = "rrioy:660Fv737mU", + vpsllw_3 = "rrmoy:660FVF1rM|rrioy:660Fv716mU", + vpslld_3 = "rrmoy:660FVF2rM|rrioy:660Fv726mU", + vpsllq_3 = "rrmoy:660FVF3rM|rrioy:660Fv736mU", + vpsraw_3 = "rrmoy:660FVE1rM|rrioy:660Fv714mU", + vpsrad_3 = "rrmoy:660FVE2rM|rrioy:660Fv724mU", + vpsrldq_3 = "rrioy:660Fv733mU", + vpsrlw_3 = "rrmoy:660FVD1rM|rrioy:660Fv712mU", + vpsrld_3 = "rrmoy:660FVD2rM|rrioy:660Fv722mU", + vpsrlq_3 = "rrmoy:660FVD3rM|rrioy:660Fv732mU", + vptest_2 = "rmoy:660F38u17rM", + + -- AVX2 integer ops + vbroadcasti128_2 = "rx/yo:660F38u5ArM", + vinserti128_4 = "rrmi/yyo:660F3AV38rMU", + vextracti128_3 = "mri/oy:660F3AuL39RmU", + vpblendd_4 = "rrmioy:660F3AV02rMU", + vpbroadcastb_2 = "rro:660F38u78rM|rx/ob:|rr/yo:|rx/yb:", + vpbroadcastw_2 = "rro:660F38u79rM|rx/ow:|rr/yo:|rx/yw:", + vpbroadcastd_2 = "rro:660F38u58rM|rx/od:|rr/yo:|rx/yd:", + vpbroadcastq_2 = "rro:660F38u59rM|rx/oq:|rr/yo:|rx/yq:", + vpermd_3 = "rrmy:660F38V36rM", + vpermq_3 = "rmiy:660F3AuX00rMU", + -- *vpgather* (!vsib) + vperm2i128_4 = "rrmiy:660F3AV46rMU", + vpmaskmovd_3 = "rrxoy:660F38V8CrM|xrroy:660F38V8ERm", + vpmaskmovq_3 = "rrxoy:660F38VX8CrM|xrroy:660F38VX8ERm", + vpsllvd_3 = "rrmoy:660F38V47rM", + vpsllvq_3 = "rrmoy:660F38VX47rM", + vpsravd_3 = "rrmoy:660F38V46rM", + vpsrlvd_3 = "rrmoy:660F38V45rM", + vpsrlvq_3 = "rrmoy:660F38VX45rM", } ------------------------------------------------------------------------------ @@ -1462,28 +1671,58 @@ for cc,n in pairs{ b=0, e=1, be=2, u=3, nb=4, ne=5, nbe=6, nu=7 } do map_op["fcmov"..cc.."_2"] = format("Fff:%04XR", nc) -- P6+ end --- SSE FP arithmetic ops. +-- SSE / AVX FP arithmetic ops. for name,n in pairs{ sqrt = 1, add = 8, mul = 9, sub = 12, min = 13, div = 14, max = 15 } do map_op[name.."ps_2"] = format("rmo:0F5%XrM", n) map_op[name.."ss_2"] = format("rro:F30F5%XrM|rx/od:", n) map_op[name.."pd_2"] = format("rmo:660F5%XrM", n) map_op[name.."sd_2"] = format("rro:F20F5%XrM|rx/oq:", n) + if n ~= 1 then + map_op["v"..name.."ps_3"] = format("rrmoy:0FV5%XrM", n) + map_op["v"..name.."ss_3"] = format("rrro:F30FV5%XrM|rrx/ood:", n) + map_op["v"..name.."pd_3"] = format("rrmoy:660FV5%XrM", n) + map_op["v"..name.."sd_3"] = format("rrro:F20FV5%XrM|rrx/ooq:", n) + end +end + +-- SSE2 / AVX / AVX2 integer arithmetic ops (66 0F leaf). +for name,n in pairs{ + paddb = 0xFC, paddw = 0xFD, paddd = 0xFE, paddq = 0xD4, + paddsb = 0xEC, paddsw = 0xED, packssdw = 0x6B, + packsswb = 0x63, packuswb = 0x67, paddusb = 0xDC, + paddusw = 0xDD, pand = 0xDB, pandn = 0xDF, pavgb = 0xE0, + pavgw = 0xE3, pcmpeqb = 0x74, pcmpeqd = 0x76, + pcmpeqw = 0x75, pcmpgtb = 0x64, pcmpgtd = 0x66, + pcmpgtw = 0x65, pmaddwd = 0xF5, pmaxsw = 0xEE, + pmaxub = 0xDE, pminsw = 0xEA, pminub = 0xDA, + pmulhuw = 0xE4, pmulhw = 0xE5, pmullw = 0xD5, + pmuludq = 0xF4, por = 0xEB, psadbw = 0xF6, psubb = 0xF8, + psubw = 0xF9, psubd = 0xFA, psubq = 0xFB, psubsb = 0xE8, + psubsw = 0xE9, psubusb = 0xD8, psubusw = 0xD9, + punpckhbw = 0x68, punpckhwd = 0x69, punpckhdq = 0x6A, + punpckhqdq = 0x6D, punpcklbw = 0x60, punpcklwd = 0x61, + punpckldq = 0x62, punpcklqdq = 0x6C, pxor = 0xEF +} do + map_op[name.."_2"] = format("rmo:660F%02XrM", n) + map_op["v"..name.."_3"] = format("rrmoy:660FV%02XrM", n) end ------------------------------------------------------------------------------ +local map_vexarg = { u = false, v = 1, V = 2 } + -- Process pattern string. local function dopattern(pat, args, sz, op, needrex) - local digit, addin + local digit, addin, vex local opcode = 0 local szov = sz local narg = 1 local rex = 0 -- Limit number of section buffer positions used by a single dasm_put(). - -- A single opcode needs a maximum of 5 positions. - if secpos+5 > maxsecpos then wflush() end + -- A single opcode needs a maximum of 6 positions. + if secpos+6 > maxsecpos then wflush() end -- Process each character. for c in gmatch(pat.."|", ".") do @@ -1497,6 +1736,8 @@ local function dopattern(pat, args, sz, op, needrex) szov = nil elseif c == "X" then -- Force REX.W. rex = 8 + elseif c == "L" then -- Force VEX.L. + vex.l = true elseif c == "r" then -- Merge 1st operand regno. into opcode. addin = args[1]; opcode = opcode + (addin.reg % 8) if narg < 2 then narg = 2 end @@ -1520,21 +1761,41 @@ local function dopattern(pat, args, sz, op, needrex) if t.xreg and t.xreg > 7 then rex = rex + 2 end if s > 7 then rex = rex + 4 end if needrex then rex = rex + 16 end - wputop(szov, opcode, rex); opcode = nil + wputop(szov, opcode, rex, vex); opcode = nil local imark = sub(pat, -1) -- Force a mark (ugly). -- Put ModRM/SIB with regno/last digit as spare. wputmrmsib(t, imark, s, addin and addin.vreg) addin = nil + elseif map_vexarg[c] ~= nil then -- Encode using VEX prefix + local b = band(opcode, 255); opcode = shr(opcode, 8) + local m = 1 + if b == 0x38 then m = 2 + elseif b == 0x3a then m = 3 end + if m ~= 1 then b = band(opcode, 255); opcode = shr(opcode, 8) end + if b ~= 0x0f then + werror("expected `0F', `0F38', or `0F3A' to precede `"..c.. + "' in pattern `"..pat.."' for `"..op.."'") + end + local v = map_vexarg[c] + if v then v = remove(args, v) end + b = band(opcode, 255) + local p = 0 + if b == 0x66 then p = 1 + elseif b == 0xf3 then p = 2 + elseif b == 0xf2 then p = 3 end + if p ~= 0 then opcode = shr(opcode, 8) end + if opcode ~= 0 then wputop(nil, opcode, 0); opcode = 0 end + vex = { m = m, p = p, v = v } else if opcode then -- Flush opcode. if szov == "q" and rex == 0 then rex = rex + 8 end if needrex then rex = rex + 16 end if addin and addin.reg == -1 then - wputop(szov, opcode - 7, rex) + wputop(szov, opcode - 7, rex, vex) waction("VREG", addin.vreg); wputxb(0) else if addin and addin.reg > 7 then rex = rex + 1 end - wputop(szov, opcode, rex) + wputop(szov, opcode, rex, vex) end opcode = nil end @@ -1571,6 +1832,14 @@ local function dopattern(pat, args, sz, op, needrex) else wputlabel("REL_", imm, 2) end + elseif c == "s" then + local reg = a.reg + if reg < 0 then + wputb(0) + waction("VREG", a.vreg); wputxb(5) + else + wputb(shl(reg, 4)) + end else werror("bad char `"..c.."' in pattern `"..pat.."' for `"..op.."'") end @@ -1647,11 +1916,14 @@ map_op[".template__"] = function(params, template, nparams) if pat == "" then pat = lastpat else lastpat = pat end if matchtm(tm, args) then local prefix = sub(szm, 1, 1) - if prefix == "/" then -- Match both operand sizes. - if args[1].opsize == sub(szm, 2, 2) and - args[2].opsize == sub(szm, 3, 3) then - dopattern(pat, args, sz, params.op, needrex) -- Process pattern. - return + if prefix == "/" then -- Exactly match leading operand sizes. + for i = #szm,1,-1 do + if i == 1 then + dopattern(pat, args, sz, params.op, needrex) -- Process pattern. + return + elseif args[i-1].opsize ~= sub(szm, i, i) then + break + end end else -- Match common operand size. local szp = sz diff --git a/luajit-2.1/dynasm/dynasm.lua b/luajit-2.1/dynasm/dynasm.lua index fffda75..145fb0c 100644 --- a/luajit-2.1/dynasm/dynasm.lua +++ b/luajit-2.1/dynasm/dynasm.lua @@ -10,9 +10,9 @@ local _info = { name = "DynASM", description = "A dynamic assembler for code generation engines", - version = "1.3.0", - vernum = 10300, - release = "2011-05-05", + version = "1.4.0", + vernum = 10400, + release = "2015-10-18", author = "Mike Pall", url = "http://luajit.org/dynasm.html", license = "MIT", diff --git a/luajit-2.1/etc/luajit.pc b/luajit-2.1/etc/luajit.pc index 5ec2c35..c99057f 100644 --- a/luajit-2.1/etc/luajit.pc +++ b/luajit-2.1/etc/luajit.pc @@ -2,7 +2,7 @@ majver=2 minver=1 relver=0 -version=${majver}.${minver}.${relver}-alpha +version=${majver}.${minver}.${relver}-beta1 abiver=5.1 prefix=/usr/local diff --git a/luajit-2.1/src/Makefile b/luajit-2.1/src/Makefile index d7539fd..9845f6a 100644 --- a/luajit-2.1/src/Makefile +++ b/luajit-2.1/src/Makefile @@ -24,11 +24,13 @@ NODOTABIVER= 51 # removing the '#' in front of them. Make sure you force a full recompile # with "make clean", followed by "make" if you change any options. # +DEFAULT_CC = gcc +# # LuaJIT builds as a native 32 or 64 bit binary by default. -CC= gcc +CC= $(DEFAULT_CC) # # Use this if you want to force a 32 bit build on a 64 bit multilib OS. -#CC= gcc -m32 +#CC= $(DEFAULT_CC) -m32 # # Since the assembler part does NOT maintain a frame pointer, it's pointless # to slow down the C part by not omitting it. Debugging, tracebacks and @@ -148,6 +150,29 @@ XCFLAGS= ############################################################################## ############################################################################## +# Host system detection. +############################################################################## + +ifeq (Windows,$(findstring Windows,$(OS))$(MSYSTEM)$(TERM)) + HOST_SYS= Windows + HOST_RM= del +else + HOST_SYS:= $(shell uname -s) + ifneq (,$(findstring MINGW,$(HOST_SYS))) + HOST_SYS= Windows + HOST_MSYS= mingw + endif + ifneq (,$(findstring CYGWIN,$(HOST_SYS))) + HOST_SYS= Windows + HOST_MSYS= cygwin + endif + # Use Clang for OSX host. + ifeq (Darwin,$(HOST_SYS)) + DEFAULT_CC= clang + endif +endif + +############################################################################## # Flags and options for host and target. ############################################################################## @@ -221,6 +246,11 @@ ifneq (,$(findstring LJ_TARGET_ARM64 ,$(TARGET_TESTARCH))) TARGET_LJARCH= arm64 else ifneq (,$(findstring LJ_TARGET_PPC ,$(TARGET_TESTARCH))) + ifneq (,$(findstring LJ_LE 1,$(TARGET_TESTARCH))) + TARGET_ARCH= -DLJ_ARCH_ENDIAN=LUAJIT_LE + else + TARGET_ARCH= -DLJ_ARCH_ENDIAN=LUAJIT_BE + endif TARGET_LJARCH= ppc else ifneq (,$(findstring LJ_TARGET_MIPS ,$(TARGET_TESTARCH))) @@ -243,9 +273,6 @@ ifneq (,$(findstring LJ_TARGET_PS3 1,$(TARGET_TESTARCH))) TARGET_XCFLAGS+= -DLUAJIT_USE_SYSMALLOC TARGET_XLIBS+= -lpthread endif -ifneq (,$(findstring LJ_NO_UNWIND 1,$(TARGET_TESTARCH))) - TARGET_ARCH+= -DLUAJIT_NO_UNWIND -endif TARGET_XCFLAGS+= $(CCOPT_$(TARGET_LJARCH)) TARGET_ARCH+= $(patsubst %,-DLUAJIT_TARGET=LUAJIT_ARCH_%,$(TARGET_LJARCH)) @@ -266,24 +293,9 @@ ifneq (,$(LMULTILIB)) endif ############################################################################## -# System detection. +# Target system detection. ############################################################################## -ifeq (Windows,$(findstring Windows,$(OS))$(MSYSTEM)$(TERM)) - HOST_SYS= Windows - HOST_RM= del -else - HOST_SYS:= $(shell uname -s) - ifneq (,$(findstring MINGW,$(HOST_SYS))) - HOST_SYS= Windows - HOST_MSYS= mingw - endif - ifneq (,$(findstring CYGWIN,$(HOST_SYS))) - HOST_SYS= Windows - HOST_MSYS= cygwin - endif -endif - TARGET_SYS?= $(HOST_SYS) ifeq (Windows,$(TARGET_SYS)) TARGET_STRIP+= --strip-unneeded @@ -400,6 +412,10 @@ ifeq (,$(findstring LJ_ABI_SOFTFP 1,$(TARGET_TESTARCH))) else TARGET_ARCH+= -DLJ_ABI_SOFTFP=1 endif +ifneq (,$(findstring LJ_NO_UNWIND 1,$(TARGET_TESTARCH))) + DASM_AFLAGS+= -D NO_UNWIND + TARGET_ARCH+= -DLUAJIT_NO_UNWIND +endif DASM_AFLAGS+= -D VER=$(subst LJ_ARCH_VERSION_,,$(filter LJ_ARCH_VERSION_%,$(subst LJ_ARCH_VERSION ,LJ_ARCH_VERSION_,$(TARGET_TESTARCH)))) ifeq (Windows,$(TARGET_SYS)) DASM_AFLAGS+= -D WIN diff --git a/luajit-2.1/src/jit/bcsave.lua b/luajit-2.1/src/jit/bcsave.lua index ef5a1aa..38fc61f 100644 --- a/luajit-2.1/src/jit/bcsave.lua +++ b/luajit-2.1/src/jit/bcsave.lua @@ -63,7 +63,7 @@ local map_type = { } local map_arch = { - x86 = true, x64 = true, arm = true, ppc = true, + x86 = true, x64 = true, arm = true, arm64 = true, ppc = true, mips = true, mipsel = true, } @@ -200,7 +200,7 @@ typedef struct { ]] local symname = LJBC_PREFIX..ctx.modname local is64, isbe = false, false - if ctx.arch == "x64" then + if ctx.arch == "x64" or ctx.arch == "arm64" then is64 = true elseif ctx.arch == "ppc" or ctx.arch == "mips" then isbe = true @@ -237,7 +237,7 @@ typedef struct { hdr.eendian = isbe and 2 or 1 hdr.eversion = 1 hdr.type = f16(1) - hdr.machine = f16(({ x86=3, x64=62, arm=40, ppc=20, mips=8, mipsel=8 })[ctx.arch]) + hdr.machine = f16(({ x86=3, x64=62, arm=40, arm64=183, ppc=20, mips=8, mipsel=8 })[ctx.arch]) if ctx.arch == "mips" or ctx.arch == "mipsel" then hdr.flags = 0x50001006 end @@ -477,13 +477,13 @@ typedef struct { } mach_obj_64; typedef struct { mach_fat_header fat; - mach_fat_arch fat_arch[4]; + mach_fat_arch fat_arch[2]; struct { mach_header hdr; mach_segment_command seg; mach_section sec; mach_symtab_command sym; - } arch[4]; + } arch[2]; mach_nlist sym_entry; uint8_t space[4096]; } mach_fat_obj; @@ -494,6 +494,8 @@ typedef struct { is64, align, mobj = true, 8, "mach_obj_64" elseif ctx.arch == "arm" then isfat, mobj = true, "mach_fat_obj" + elseif ctx.arch == "arm64" then + is64, align, isfat, mobj = true, 8, true, "mach_fat_obj" else check(ctx.arch == "x86", "unsupported architecture for OSX") end @@ -503,8 +505,8 @@ typedef struct { -- Create Mach-O object and fill in header. local o = ffi.new(mobj) local mach_size = aligned(ffi.offsetof(o, "space")+#symname+2, align) - local cputype = ({ x86={7}, x64={0x01000007}, arm={7,12,12,12} })[ctx.arch] - local cpusubtype = ({ x86={3}, x64={3}, arm={3,6,9,11} })[ctx.arch] + local cputype = ({ x86={7}, x64={0x01000007}, arm={7,12}, arm64={0x01000007,0x0100000c} })[ctx.arch] + local cpusubtype = ({ x86={3}, x64={3}, arm={3,9}, arm64={3,0} })[ctx.arch] if isfat then o.fat.magic = be32(0xcafebabe) o.fat.nfat_arch = be32(#cpusubtype) diff --git a/luajit-2.1/src/jit/dis_x86.lua b/luajit-2.1/src/jit/dis_x86.lua index 6bc3806..49bbcad 100644 --- a/luajit-2.1/src/jit/dis_x86.lua +++ b/luajit-2.1/src/jit/dis_x86.lua @@ -15,13 +15,12 @@ -- Intel and AMD manuals. The supported instruction set is quite extensive -- and reflects what a current generation Intel or AMD CPU implements in -- 32 bit and 64 bit mode. Yes, this includes MMX, SSE, SSE2, SSE3, SSSE3, --- SSE4.1, SSE4.2, SSE4a and even privileged and hypervisor (VMX/SVM) --- instructions. +-- SSE4.1, SSE4.2, SSE4a, AVX, AVX2 and even privileged and hypervisor +-- (VMX/SVM) instructions. -- -- Notes: -- * The (useless) a16 prefix, 3DNow and pre-586 opcodes are unsupported. -- * No attempt at optimization has been made -- it's fast enough for my needs. --- * The public API may change when more architectures are added. ------------------------------------------------------------------------------ local type = type @@ -78,7 +77,7 @@ local map_opc1_32 = { "movBRi","movBRi","movBRi","movBRi","movBRi","movBRi","movBRi","movBRi", "movVRI","movVRI","movVRI","movVRI","movVRI","movVRI","movVRI","movVRI", --Cx -"shift!Bmu","shift!Vmu","retBw","ret","$lesVrm","$ldsVrm","movBmi","movVmi", +"shift!Bmu","shift!Vmu","retBw","ret","vex*3$lesVrm","vex*2$ldsVrm","movBmi","movVmi", "enterBwu","leave","retfBw","retf","int3","intBu","into","iretVS", --Dx "shift!Bm1","shift!Vm1","shift!Bmc","shift!Vmc","aamBu","aadBu","salc","xlatb", @@ -103,7 +102,7 @@ local map_opc1_64 = setmetatable({ [0x44]="rex*r", [0x45]="rex*rb", [0x46]="rex*rx", [0x47]="rex*rxb", [0x48]="rex*w", [0x49]="rex*wb", [0x4a]="rex*wx", [0x4b]="rex*wxb", [0x4c]="rex*wr", [0x4d]="rex*wrb", [0x4e]="rex*wrx", [0x4f]="rex*wrxb", - [0x82]=false, [0x9a]=false, [0xc4]=false, [0xc5]=false, [0xce]=false, + [0x82]=false, [0x9a]=false, [0xc4]="vex*3", [0xc5]="vex*2", [0xce]=false, [0xd4]=false, [0xd5]=false, [0xd6]=false, [0xea]=false, }, { __index = map_opc1_32 }) @@ -114,12 +113,12 @@ local map_opc2 = { [0]="sldt!Dmp","sgdt!Ump","larVrm","lslVrm",nil,"syscall","clts","sysret", "invd","wbinvd",nil,"ud1",nil,"$prefetch!Bm","femms","3dnowMrmu", --1x -"movupsXrm|movssXrm|movupdXrm|movsdXrm", -"movupsXmr|movssXmr|movupdXmr|movsdXmr", +"movupsXrm|movssXrvm|movupdXrm|movsdXrvm", +"movupsXmr|movssXmvr|movupdXmr|movsdXmvr", "movhlpsXrm$movlpsXrm|movsldupXrm|movlpdXrm|movddupXrm", "movlpsXmr||movlpdXmr", -"unpcklpsXrm||unpcklpdXrm", -"unpckhpsXrm||unpckhpdXrm", +"unpcklpsXrvm||unpcklpdXrvm", +"unpckhpsXrvm||unpckhpdXrvm", "movlhpsXrm$movhpsXrm|movshdupXrm|movhpdXrm", "movhpsXmr||movhpdXmr", "$prefetcht!Bm","hintnopVm","hintnopVm","hintnopVm", @@ -128,7 +127,7 @@ local map_opc2 = { "movUmx$","movUmy$","movUxm$","movUym$","movUmz$",nil,"movUzm$",nil, "movapsXrm||movapdXrm", "movapsXmr||movapdXmr", -"cvtpi2psXrMm|cvtsi2ssXrVmt|cvtpi2pdXrMm|cvtsi2sdXrVmt", +"cvtpi2psXrMm|cvtsi2ssXrvVmt|cvtpi2pdXrMm|cvtsi2sdXrvVmt", "movntpsXmr|movntssXmr|movntpdXmr|movntsdXmr", "cvttps2piMrXm|cvttss2siVrXm|cvttpd2piMrXm|cvttsd2siVrXm", "cvtps2piMrXm|cvtss2siVrXm|cvtpd2piMrXm|cvtsd2siVrXm", @@ -144,27 +143,27 @@ local map_opc2 = { "cmovlVrm","cmovgeVrm","cmovleVrm","cmovgVrm", --5x "movmskpsVrXm$||movmskpdVrXm$","sqrtpsXrm|sqrtssXrm|sqrtpdXrm|sqrtsdXrm", -"rsqrtpsXrm|rsqrtssXrm","rcppsXrm|rcpssXrm", -"andpsXrm||andpdXrm","andnpsXrm||andnpdXrm", -"orpsXrm||orpdXrm","xorpsXrm||xorpdXrm", -"addpsXrm|addssXrm|addpdXrm|addsdXrm","mulpsXrm|mulssXrm|mulpdXrm|mulsdXrm", -"cvtps2pdXrm|cvtss2sdXrm|cvtpd2psXrm|cvtsd2ssXrm", +"rsqrtpsXrm|rsqrtssXrvm","rcppsXrm|rcpssXrvm", +"andpsXrvm||andpdXrvm","andnpsXrvm||andnpdXrvm", +"orpsXrvm||orpdXrvm","xorpsXrvm||xorpdXrvm", +"addpsXrvm|addssXrvm|addpdXrvm|addsdXrvm","mulpsXrvm|mulssXrvm|mulpdXrvm|mulsdXrvm", +"cvtps2pdXrm|cvtss2sdXrvm|cvtpd2psXrm|cvtsd2ssXrvm", "cvtdq2psXrm|cvttps2dqXrm|cvtps2dqXrm", -"subpsXrm|subssXrm|subpdXrm|subsdXrm","minpsXrm|minssXrm|minpdXrm|minsdXrm", -"divpsXrm|divssXrm|divpdXrm|divsdXrm","maxpsXrm|maxssXrm|maxpdXrm|maxsdXrm", +"subpsXrvm|subssXrvm|subpdXrvm|subsdXrvm","minpsXrvm|minssXrvm|minpdXrvm|minsdXrvm", +"divpsXrvm|divssXrvm|divpdXrvm|divsdXrvm","maxpsXrvm|maxssXrvm|maxpdXrvm|maxsdXrvm", --6x -"punpcklbwPrm","punpcklwdPrm","punpckldqPrm","packsswbPrm", -"pcmpgtbPrm","pcmpgtwPrm","pcmpgtdPrm","packuswbPrm", -"punpckhbwPrm","punpckhwdPrm","punpckhdqPrm","packssdwPrm", -"||punpcklqdqXrm","||punpckhqdqXrm", +"punpcklbwPrvm","punpcklwdPrvm","punpckldqPrvm","packsswbPrvm", +"pcmpgtbPrvm","pcmpgtwPrvm","pcmpgtdPrvm","packuswbPrvm", +"punpckhbwPrvm","punpckhwdPrvm","punpckhdqPrvm","packssdwPrvm", +"||punpcklqdqXrvm","||punpckhqdqXrvm", "movPrVSm","movqMrm|movdquXrm|movdqaXrm", --7x "pshufwMrmu|pshufhwXrmu|pshufdXrmu|pshuflwXrmu","pshiftw!Pmu", "pshiftd!Pmu","pshiftq!Mmu||pshiftdq!Xmu", -"pcmpeqbPrm","pcmpeqwPrm","pcmpeqdPrm","emms|", +"pcmpeqbPrvm","pcmpeqwPrvm","pcmpeqdPrvm","emms*|", "vmreadUmr||extrqXmuu$|insertqXrmuu$","vmwriteUrm||extrqXrm$|insertqXrm$", nil,nil, -"||haddpdXrm|haddpsXrm","||hsubpdXrm|hsubpsXrm", +"||haddpdXrvm|haddpsXrvm","||hsubpdXrvm|hsubpsXrvm", "movVSmMr|movqXrm|movVSmXr","movqMmr|movdquXmr|movdqaXmr", --8x "joVj","jnoVj","jbVj","jnbVj","jzVj","jnzVj","jbeVj","jaVj", @@ -182,27 +181,27 @@ nil,nil, "bsfVrm","bsrVrm|lzcntVrm|bsrWrm","movsxVrBmt","movsxVrWmt", --Cx "xaddBmr","xaddVmr", -"cmppsXrmu|cmpssXrmu|cmppdXrmu|cmpsdXrmu","$movntiVmr|", -"pinsrwPrWmu","pextrwDrPmu", -"shufpsXrmu||shufpdXrmu","$cmpxchg!Qmp", +"cmppsXrvmu|cmpssXrvmu|cmppdXrvmu|cmpsdXrvmu","$movntiVmr|", +"pinsrwPrvWmu","pextrwDrPmu", +"shufpsXrvmu||shufpdXrvmu","$cmpxchg!Qmp", "bswapVR","bswapVR","bswapVR","bswapVR","bswapVR","bswapVR","bswapVR","bswapVR", --Dx -"||addsubpdXrm|addsubpsXrm","psrlwPrm","psrldPrm","psrlqPrm", -"paddqPrm","pmullwPrm", +"||addsubpdXrvm|addsubpsXrvm","psrlwPrvm","psrldPrvm","psrlqPrvm", +"paddqPrvm","pmullwPrvm", "|movq2dqXrMm|movqXmr|movdq2qMrXm$","pmovmskbVrMm||pmovmskbVrXm", -"psubusbPrm","psubuswPrm","pminubPrm","pandPrm", -"paddusbPrm","padduswPrm","pmaxubPrm","pandnPrm", +"psubusbPrvm","psubuswPrvm","pminubPrvm","pandPrvm", +"paddusbPrvm","padduswPrvm","pmaxubPrvm","pandnPrvm", --Ex -"pavgbPrm","psrawPrm","psradPrm","pavgwPrm", -"pmulhuwPrm","pmulhwPrm", +"pavgbPrvm","psrawPrvm","psradPrvm","pavgwPrvm", +"pmulhuwPrvm","pmulhwPrvm", "|cvtdq2pdXrm|cvttpd2dqXrm|cvtpd2dqXrm","$movntqMmr||$movntdqXmr", -"psubsbPrm","psubswPrm","pminswPrm","porPrm", -"paddsbPrm","paddswPrm","pmaxswPrm","pxorPrm", +"psubsbPrvm","psubswPrvm","pminswPrvm","porPrvm", +"paddsbPrvm","paddswPrvm","pmaxswPrvm","pxorPrvm", --Fx -"|||lddquXrm","psllwPrm","pslldPrm","psllqPrm", -"pmuludqPrm","pmaddwdPrm","psadbwPrm","maskmovqMrm||maskmovdquXrm$", -"psubbPrm","psubwPrm","psubdPrm","psubqPrm", -"paddbPrm","paddwPrm","padddPrm","ud", +"|||lddquXrm","psllwPrvm","pslldPrvm","psllqPrvm", +"pmuludqPrvm","pmaddwdPrvm","psadbwPrvm","maskmovqMrm||maskmovdquXrm$", +"psubbPrvm","psubwPrvm","psubdPrvm","psubqPrvm", +"paddbPrvm","paddwPrvm","padddPrvm","ud", } assert(map_opc2[255] == "ud") @@ -210,46 +209,62 @@ assert(map_opc2[255] == "ud") local map_opc3 = { ["38"] = { -- [66] 0f 38 xx --0x -[0]="pshufbPrm","phaddwPrm","phadddPrm","phaddswPrm", -"pmaddubswPrm","phsubwPrm","phsubdPrm","phsubswPrm", -"psignbPrm","psignwPrm","psigndPrm","pmulhrswPrm", -nil,nil,nil,nil, +[0]="pshufbPrvm","phaddwPrvm","phadddPrvm","phaddswPrvm", +"pmaddubswPrvm","phsubwPrvm","phsubdPrvm","phsubswPrvm", +"psignbPrvm","psignwPrvm","psigndPrvm","pmulhrswPrvm", +"||permilpsXrvm","||permilpdXrvm",nil,nil, --1x "||pblendvbXrma",nil,nil,nil, -"||blendvpsXrma","||blendvpdXrma",nil,"||ptestXrm", -nil,nil,nil,nil, +"||blendvpsXrma","||blendvpdXrma","||permpsXrvm","||ptestXrm", +"||broadcastssXrm","||broadcastsdXrm","||broadcastf128XrlXm",nil, "pabsbPrm","pabswPrm","pabsdPrm",nil, --2x "||pmovsxbwXrm","||pmovsxbdXrm","||pmovsxbqXrm","||pmovsxwdXrm", "||pmovsxwqXrm","||pmovsxdqXrm",nil,nil, -"||pmuldqXrm","||pcmpeqqXrm","||$movntdqaXrm","||packusdwXrm", -nil,nil,nil,nil, +"||pmuldqXrvm","||pcmpeqqXrvm","||$movntdqaXrm","||packusdwXrvm", +"||maskmovpsXrvm","||maskmovpdXrvm","||maskmovpsXmvr","||maskmovpdXmvr", --3x "||pmovzxbwXrm","||pmovzxbdXrm","||pmovzxbqXrm","||pmovzxwdXrm", -"||pmovzxwqXrm","||pmovzxdqXrm",nil,"||pcmpgtqXrm", -"||pminsbXrm","||pminsdXrm","||pminuwXrm","||pminudXrm", -"||pmaxsbXrm","||pmaxsdXrm","||pmaxuwXrm","||pmaxudXrm", +"||pmovzxwqXrm","||pmovzxdqXrm","||permdXrvm","||pcmpgtqXrvm", +"||pminsbXrvm","||pminsdXrvm","||pminuwXrvm","||pminudXrvm", +"||pmaxsbXrvm","||pmaxsdXrvm","||pmaxuwXrvm","||pmaxudXrvm", --4x -"||pmulddXrm","||phminposuwXrm", +"||pmulddXrvm","||phminposuwXrm",nil,nil, +nil,"||psrlvVSXrvm","||psravdXrvm","||psllvVSXrvm", +--5x +[0x58] = "||pbroadcastdXrlXm",[0x59] = "||pbroadcastqXrlXm", +[0x5a] = "||broadcasti128XrlXm", +--7x +[0x78] = "||pbroadcastbXrlXm",[0x79] = "||pbroadcastwXrlXm", +--8x +[0x8c] = "||pmaskmovXrvVSm", +[0x8e] = "||pmaskmovVSmXvr", --Fx [0xf0] = "|||crc32TrBmt",[0xf1] = "|||crc32TrVmt", }, ["3a"] = { -- [66] 0f 3a xx --0x -[0x00]=nil,nil,nil,nil,nil,nil,nil,nil, -"||roundpsXrmu","||roundpdXrmu","||roundssXrmu","||roundsdXrmu", -"||blendpsXrmu","||blendpdXrmu","||pblendwXrmu","palignrPrmu", +[0x00]="||permqXrmu","||permpdXrmu","||pblenddXrvmu",nil, +"||permilpsXrmu","||permilpdXrmu","||perm2f128Xrvmu",nil, +"||roundpsXrmu","||roundpdXrmu","||roundssXrvmu","||roundsdXrvmu", +"||blendpsXrvmu","||blendpdXrvmu","||pblendwXrvmu","palignrPrvmu", --1x nil,nil,nil,nil, "||pextrbVmXru","||pextrwVmXru","||pextrVmSXru","||extractpsVmXru", -nil,nil,nil,nil,nil,nil,nil,nil, +"||insertf128XrvlXmu","||extractf128XlXmYru",nil,nil, +nil,nil,nil,nil, --2x -"||pinsrbXrVmu","||insertpsXrmu","||pinsrXrVmuS",nil, +"||pinsrbXrvVmu","||insertpsXrvmu","||pinsrXrvVmuS",nil, +--3x +[0x38] = "||inserti128Xrvmu",[0x39] = "||extracti128XlXmYru", --4x -[0x40] = "||dppsXrmu", -[0x41] = "||dppdXrmu", -[0x42] = "||mpsadbwXrmu", +[0x40] = "||dppsXrvmu", +[0x41] = "||dppdXrvmu", +[0x42] = "||mpsadbwXrvmu", +[0x46] = "||perm2i128Xrvmu", +[0x4a] = "||blendvpsXrvmb",[0x4b] = "||blendvpdXrvmb", +[0x4c] = "||pblendvbXrvmb", --6x [0x60] = "||pcmpestrmXrmu",[0x61] = "||pcmpestriXrmu", [0x62] = "||pcmpistrmXrmu",[0x63] = "||pcmpistriXrmu", @@ -356,17 +371,19 @@ local map_regs = { "mm0", "mm1", "mm2", "mm3", "mm4", "mm5", "mm6", "mm7" }, -- No x64 ext! X = { "xmm0", "xmm1", "xmm2", "xmm3", "xmm4", "xmm5", "xmm6", "xmm7", "xmm8", "xmm9", "xmm10", "xmm11", "xmm12", "xmm13", "xmm14", "xmm15" }, + Y = { "ymm0", "ymm1", "ymm2", "ymm3", "ymm4", "ymm5", "ymm6", "ymm7", + "ymm8", "ymm9", "ymm10", "ymm11", "ymm12", "ymm13", "ymm14", "ymm15" }, } local map_segregs = { "es", "cs", "ss", "ds", "fs", "gs", "segr6", "segr7" } -- Maps for size names. local map_sz2n = { - B = 1, W = 2, D = 4, Q = 8, M = 8, X = 16, + B = 1, W = 2, D = 4, Q = 8, M = 8, X = 16, Y = 32, } local map_sz2prefix = { B = "byte", W = "word", D = "dword", Q = "qword", - M = "qword", X = "xword", + M = "qword", X = "xword", Y = "yword", F = "dword", G = "qword", -- No need for sizes/register names for these two. } @@ -389,10 +406,13 @@ local function putop(ctx, text, operands) if ctx.rep then text = ctx.rep.." "..text; ctx.rep = false end if ctx.rex then local t = (ctx.rexw and "w" or "")..(ctx.rexr and "r" or "").. - (ctx.rexx and "x" or "")..(ctx.rexb and "b" or "") - if t ~= "" then text = "rex."..t.." "..text end + (ctx.rexx and "x" or "")..(ctx.rexb and "b" or "").. + (ctx.vexl and "l" or "") + if ctx.vexv and ctx.vexv ~= 0 then t = t.."v"..ctx.vexv end + if t ~= "" then text = ctx.rex.."."..t.." "..text + elseif ctx.rex == "vex" then text = "v"..text end ctx.rexw = false; ctx.rexr = false; ctx.rexx = false; ctx.rexb = false - ctx.rex = false + ctx.rex = false; ctx.vexl = false; ctx.vexv = false end if ctx.seg then local text2, n = gsub(text, "%[", "["..ctx.seg..":") @@ -407,6 +427,7 @@ local function putop(ctx, text, operands) end ctx.out(format("%08x %s%s\n", ctx.addr+ctx.start, hex, text)) ctx.mrm = false + ctx.vexv = false ctx.start = pos ctx.imm = nil end @@ -415,7 +436,7 @@ end local function clearprefixes(ctx) ctx.o16 = false; ctx.seg = false; ctx.lock = false; ctx.rep = false ctx.rexw = false; ctx.rexr = false; ctx.rexx = false; ctx.rexb = false - ctx.rex = false; ctx.a32 = false + ctx.rex = false; ctx.a32 = false; ctx.vexl = false end -- Fallback for incomplete opcodes at the end. @@ -452,9 +473,9 @@ end -- Process pattern string and generate the operands. local function putpat(ctx, name, pat) local operands, regs, sz, mode, sp, rm, sc, rx, sdisp - local code, pos, stop = ctx.code, ctx.pos, ctx.stop + local code, pos, stop, vexl = ctx.code, ctx.pos, ctx.stop, ctx.vexl - -- Chars used: 1DFGIMPQRSTUVWXacdfgijmoprstuwxyz + -- Chars used: 1DFGIMPQRSTUVWXYabcdfgijlmoprstuvwxyz for p in gmatch(pat, ".") do local x = nil if p == "V" or p == "U" then @@ -469,11 +490,13 @@ local function putpat(ctx, name, pat) elseif p == "B" then sz = "B" regs = ctx.rex and map_regs.B64 or map_regs.B - elseif match(p, "[WDQMXFG]") then + elseif match(p, "[WDQMXYFG]") then sz = p + if sz == "X" and vexl then sz = "Y"; ctx.vexl = false end regs = map_regs[sz] elseif p == "P" then sz = ctx.o16 and "X" or "M"; ctx.o16 = false + if sz == "X" and vexl then sz = "Y"; ctx.vexl = false end regs = map_regs[sz] elseif p == "S" then name = name..lower(sz) @@ -486,6 +509,10 @@ local function putpat(ctx, name, pat) local imm = getimm(ctx, pos, 1); if not imm then return end x = format("0x%02x", imm) pos = pos+1 + elseif p == "b" then + local imm = getimm(ctx, pos, 1); if not imm then return end + x = regs[imm/16+1] + pos = pos+1 elseif p == "w" then local imm = getimm(ctx, pos, 2); if not imm then return end x = format("0x%x", imm) @@ -618,8 +645,13 @@ local function putpat(ctx, name, pat) else x = "CR"..sp end + elseif p == "v" then + if ctx.vexv then + x = regs[ctx.vexv+1]; ctx.vexv = false + end elseif p == "y" then x = "DR"..sp elseif p == "z" then x = "TR"..sp + elseif p == "l" then vexl = false elseif p == "t" then else error("bad pattern `"..pat.."'") @@ -694,7 +726,7 @@ map_act = { B = putpat, W = putpat, D = putpat, Q = putpat, V = putpat, U = putpat, T = putpat, M = putpat, X = putpat, P = putpat, - F = putpat, G = putpat, + F = putpat, G = putpat, Y = putpat, -- Collect prefixes. [":"] = function(ctx, name, pat) @@ -755,15 +787,68 @@ map_act = { -- REX prefix. rex = function(ctx, name, pat) - if ctx.rex then return unknown(ctx) end -- Only 1 REX prefix allowed. + if ctx.rex then return unknown(ctx) end -- Only 1 REX or VEX prefix allowed. for p in gmatch(pat, ".") do ctx["rex"..p] = true end - ctx.rex = true + ctx.rex = "rex" + end, + + -- VEX prefix. + vex = function(ctx, name, pat) + if ctx.rex then return unknown(ctx) end -- Only 1 REX or VEX prefix allowed. + ctx.rex = "vex" + local pos = ctx.pos + if ctx.mrm then + ctx.mrm = nil + pos = pos-1 + end + local b = byte(ctx.code, pos, pos) + if not b then return incomplete(ctx) end + pos = pos+1 + if b < 128 then ctx.rexr = true end + local m = 1 + if pat == "3" then + m = b%32; b = (b-m)/32 + local nb = b%2; b = (b-nb)/2 + if nb == 0 then ctx.rexb = true end + local nx = b%2; b = (b-nx)/2 + if nx == 0 then ctx.rexx = true end + b = byte(ctx.code, pos, pos) + if not b then return incomplete(ctx) end + pos = pos+1 + if b >= 128 then ctx.rexw = true end + end + ctx.pos = pos + local map + if m == 1 then map = map_opc2 + elseif m == 2 then map = map_opc3["38"] + elseif m == 3 then map = map_opc3["3a"] + else return unknown(ctx) end + local p = b%4; b = (b-p)/4 + if p == 1 then ctx.o16 = "o16" + elseif p == 2 then ctx.rep = "rep" + elseif p == 3 then ctx.rep = "repne" end + local l = b%2; b = (b-l)/2 + if l ~= 0 then ctx.vexl = true end + ctx.vexv = (-1-b)%16 + return dispatchmap(ctx, map) end, -- Special case for nop with REX prefix. nop = function(ctx, name, pat) return dispatch(ctx, ctx.rex and pat or "nop") end, + + -- Special case for 0F 77. + emms = function(ctx, name, pat) + if ctx.rex ~= "vex" then + return putop(ctx, "emms") + elseif ctx.vexl then + ctx.vexl = false + return putop(ctx, "zeroall") + else + return putop(ctx, "zeroupper") + end + end, } ------------------------------------------------------------------------------ diff --git a/luajit-2.1/src/jit/dump.lua b/luajit-2.1/src/jit/dump.lua index 5f85849..b1cdcfe 100644 --- a/luajit-2.1/src/jit/dump.lua +++ b/luajit-2.1/src/jit/dump.lua @@ -571,6 +571,7 @@ local function dump_trace(what, tr, func, pc, otr, oex) end if dumpmode.H then out:write("</pre>\n\n") else out:write("\n") end else + if what == "flush" then symtab, nexitsym = {}, 0 end out:write("---- TRACE ", what, "\n\n") end out:flush() diff --git a/luajit-2.1/src/lib_base.c b/luajit-2.1/src/lib_base.c index 35ccdbc..ca268b1 100644 --- a/luajit-2.1/src/lib_base.c +++ b/luajit-2.1/src/lib_base.c @@ -428,20 +428,20 @@ LJLIB_CF(dofile) LJLIB_CF(gcinfo) { - setintV(L->top++, (G(L)->gc.total >> 10)); + setintV(L->top++, (int32_t)(G(L)->gc.total >> 10)); return 1; } LJLIB_CF(collectgarbage) { int opt = lj_lib_checkopt(L, 1, LUA_GCCOLLECT, /* ORDER LUA_GC* */ - "\4stop\7restart\7collect\5count\1\377\4step\10setpause\12setstepmul"); + "\4stop\7restart\7collect\5count\1\377\4step\10setpause\12setstepmul\1\377\11isrunning"); int32_t data = lj_lib_optint(L, 2, 0); if (opt == LUA_GCCOUNT) { setnumV(L->top, (lua_Number)G(L)->gc.total/1024.0); } else { int res = lua_gc(L, opt, data); - if (opt == LUA_GCSTEP) + if (opt == LUA_GCSTEP || opt == LUA_GCISRUNNING) setboolV(L->top, res); else setintV(L->top, res); diff --git a/luajit-2.1/src/lib_io.c b/luajit-2.1/src/lib_io.c index 468d327..2aa8347 100644 --- a/luajit-2.1/src/lib_io.c +++ b/luajit-2.1/src/lib_io.c @@ -99,7 +99,7 @@ static int io_file_close(lua_State *L, IOFileUD *iof) int stat = -1; #if LJ_TARGET_POSIX stat = pclose(iof->fp); -#elif LJ_TARGET_WINDOWS +#elif LJ_TARGET_WINDOWS && !LJ_TARGET_XBOXONE stat = _pclose(iof->fp); #else lua_assert(0); @@ -273,6 +273,15 @@ static int io_file_iter(lua_State *L) return n; } +static int io_file_lines(lua_State *L) +{ + int n = (int)(L->top - L->base); + if (n > LJ_MAX_UPVAL) + lj_err_caller(L, LJ_ERR_UNPACK); + lua_pushcclosure(L, io_file_iter, n); + return 1; +} + /* -- I/O file methods ---------------------------------------------------- */ #define LJLIB_MODULE_io_method @@ -356,8 +365,7 @@ LJLIB_CF(io_method_setvbuf) LJLIB_CF(io_method_lines) { io_tofile(L); - lua_pushcclosure(L, io_file_iter, (int)(L->top - L->base)); - return 1; + return io_file_lines(L); } LJLIB_CF(io_method___gc) @@ -400,7 +408,7 @@ LJLIB_CF(io_open) LJLIB_CF(io_popen) { -#if LJ_TARGET_POSIX || LJ_TARGET_WINDOWS +#if LJ_TARGET_POSIX || (LJ_TARGET_WINDOWS && !LJ_TARGET_XBOXONE) const char *fname = strdata(lj_lib_checkstr(L, 1)); GCstr *s = lj_lib_optstr(L, 2); const char *mode = s ? strdata(s) : "r"; @@ -487,8 +495,7 @@ LJLIB_CF(io_lines) } else { /* io.lines() iterates over stdin. */ setudataV(L, L->base, IOSTDF_UD(L, GCROOT_IO_INPUT)); } - lua_pushcclosure(L, io_file_iter, (int)(L->top - L->base)); - return 1; + return io_file_lines(L); } LJLIB_CF(io_type) diff --git a/luajit-2.1/src/lib_os.c b/luajit-2.1/src/lib_os.c index 7b5873a..37d7d5b 100644 --- a/luajit-2.1/src/lib_os.c +++ b/luajit-2.1/src/lib_os.c @@ -39,7 +39,7 @@ LJLIB_CF(os_execute) { -#if LJ_TARGET_CONSOLE +#if LJ_NO_SYSTEM #if LJ_52 errno = ENOSYS; return luaL_fileresult(L, 0, NULL); diff --git a/luajit-2.1/src/lib_package.c b/luajit-2.1/src/lib_package.c index 6b6eb8f..32ba4d3 100644 --- a/luajit-2.1/src/lib_package.c +++ b/luajit-2.1/src/lib_package.c @@ -96,9 +96,17 @@ static void setprogdir(lua_State *L) static void pusherror(lua_State *L) { DWORD error = GetLastError(); +#if LJ_TARGET_XBOXONE + wchar_t wbuffer[128]; + char buffer[128*2]; + if (FormatMessageW(FORMAT_MESSAGE_IGNORE_INSERTS | FORMAT_MESSAGE_FROM_SYSTEM, + NULL, error, 0, wbuffer, sizeof(wbuffer)/sizeof(wchar_t), NULL) && + WideCharToMultiByte(CP_ACP, 0, wbuffer, 128, buffer, 128*2, NULL, NULL)) +#else char buffer[128]; if (FormatMessageA(FORMAT_MESSAGE_IGNORE_INSERTS | FORMAT_MESSAGE_FROM_SYSTEM, NULL, error, 0, buffer, sizeof(buffer), NULL)) +#endif lua_pushstring(L, buffer); else lua_pushfstring(L, "system error %d\n", error); @@ -111,7 +119,7 @@ static void ll_unloadlib(void *lib) static void *ll_load(lua_State *L, const char *path, int gl) { - HINSTANCE lib = LoadLibraryA(path); + HINSTANCE lib = LoadLibraryExA(path, NULL, 0); if (lib == NULL) pusherror(L); UNUSED(gl); return lib; diff --git a/luajit-2.1/src/lj.supp b/luajit-2.1/src/lj.supp index 411f261..acb9e78 100644 --- a/luajit-2.1/src/lj.supp +++ b/luajit-2.1/src/lj.supp @@ -24,3 +24,18 @@ Memcheck:Cond fun:lj_str_new } +{ + Optimized string compare + Memcheck:Addr4 + fun:lj_str_fastcmp +} +{ + Optimized string compare + Memcheck:Addr1 + fun:lj_str_fastcmp +} +{ + Optimized string compare + Memcheck:Cond + fun:lj_str_fastcmp +} diff --git a/luajit-2.1/src/lj_alloc.c b/luajit-2.1/src/lj_alloc.c index 0aad826..ddd50ca 100644 --- a/luajit-2.1/src/lj_alloc.c +++ b/luajit-2.1/src/lj_alloc.c @@ -196,7 +196,7 @@ static LJ_AINLINE void *CALL_MMAP(size_t size) return ptr; } -#elif LJ_TARGET_OSX || LJ_TARGET_PS4 || defined(__FreeBSD__) || defined(__FreeBSD_kernel__) || defined(__NetBSD__) || defined(__OpenBSD__) || defined(__DragonFly__) || defined(__sun__) +#elif LJ_TARGET_OSX || LJ_TARGET_PS4 || defined(__FreeBSD__) || defined(__FreeBSD_kernel__) || defined(__NetBSD__) || defined(__OpenBSD__) || defined(__DragonFly__) || defined(__sun__) || defined(__CYGWIN__) /* OSX and FreeBSD mmap() use a naive first-fit linear search. ** That's perfect for us. Except that -pagezero_size must be set for OSX, diff --git a/luajit-2.1/src/lj_api.c b/luajit-2.1/src/lj_api.c index 1f09284..042b0d9 100644 --- a/luajit-2.1/src/lj_api.c +++ b/luajit-2.1/src/lj_api.c @@ -1188,6 +1188,9 @@ LUA_API int lua_gc(lua_State *L, int what, int data) res = (int)(g->gc.stepmul); g->gc.stepmul = (MSize)data; break; + case LUA_GCISRUNNING: + res = (g->gc.threshold != LJ_MAX_MEM); + break; default: res = -1; /* Invalid option. */ } diff --git a/luajit-2.1/src/lj_arch.h b/luajit-2.1/src/lj_arch.h index 61c7e19..c66a11c 100644 --- a/luajit-2.1/src/lj_arch.h +++ b/luajit-2.1/src/lj_arch.h @@ -120,6 +120,12 @@ #define LJ_TARGET_CONSOLE 1 #endif +#ifdef _DURANGO +#define LJ_TARGET_XBOXONE 1 +#define LJ_TARGET_CONSOLE 1 +#define LJ_TARGET_GC64 1 +#endif + #define LJ_NUMMODE_SINGLE 0 /* Single-number mode only. */ #define LJ_NUMMODE_SINGLE_DUAL 1 /* Default to single-number mode. */ #define LJ_NUMMODE_DUAL 2 /* Dual-number mode only. */ @@ -149,7 +155,11 @@ #define LJ_ARCH_NAME "x64" #define LJ_ARCH_BITS 64 #define LJ_ARCH_ENDIAN LUAJIT_LE -#define LJ_ABI_WIN LJ_TARGET_WINDOWS +#if LJ_TARGET_WINDOWS || __CYGWIN__ +#define LJ_ABI_WIN 1 +#else +#define LJ_ABI_WIN 0 +#endif #define LJ_TARGET_X64 1 #define LJ_TARGET_X86ORX64 1 #define LJ_TARGET_EHRETREG 0 @@ -158,6 +168,9 @@ #define LJ_TARGET_MASKROT 1 #define LJ_TARGET_UNALIGNED 1 #define LJ_ARCH_NUMMODE LJ_NUMMODE_SINGLE_DUAL +#ifdef LUAJIT_ENABLE_GC64 +#define LJ_TARGET_GC64 1 +#endif #elif LUAJIT_TARGET == LUAJIT_ARCH_ARM @@ -210,11 +223,13 @@ #elif LUAJIT_TARGET == LUAJIT_ARCH_PPC +#ifndef LJ_ARCH_ENDIAN #if __BYTE_ORDER__ != __ORDER_BIG_ENDIAN__ #define LJ_ARCH_ENDIAN LUAJIT_LE #else #define LJ_ARCH_ENDIAN LUAJIT_BE #endif +#endif #if _LP64 #define LJ_ARCH_BITS 64 @@ -483,8 +498,11 @@ #if defined(__symbian__) || LJ_TARGET_WINDOWS #define LUAJIT_NO_EXP2 #endif +#if LJ_TARGET_CONSOLE || (LJ_TARGET_IOS && __IPHONE_OS_VERSION_MIN_REQUIRED >= __IPHONE_8_0) +#define LJ_NO_SYSTEM 1 +#endif -#if defined(LUAJIT_NO_UNWIND) || defined(__symbian__) || LJ_TARGET_IOS || LJ_TARGET_PS3 +#if defined(LUAJIT_NO_UNWIND) || defined(__symbian__) || LJ_TARGET_IOS || LJ_TARGET_PS3 || LJ_TARGET_PS4 #define LJ_NO_UNWIND 1 #endif diff --git a/luajit-2.1/src/lj_ccallback.c b/luajit-2.1/src/lj_ccallback.c index 66a0944..065c329 100644 --- a/luajit-2.1/src/lj_ccallback.c +++ b/luajit-2.1/src/lj_ccallback.c @@ -35,7 +35,7 @@ #elif LJ_TARGET_X86ORX64 #define CALLBACK_MCODE_HEAD (LJ_64 ? 8 : 0) -#define CALLBACK_MCODE_GROUP (-2+1+2+5+(LJ_64 ? 6 : 5)) +#define CALLBACK_MCODE_GROUP (-2+1+2+(LJ_GC64 ? 10 : 5)+(LJ_64 ? 6 : 5)) #define CALLBACK_SLOT2OFS(slot) \ (CALLBACK_MCODE_HEAD + CALLBACK_MCODE_GROUP*((slot)/32) + 4*(slot)) @@ -120,8 +120,13 @@ static void callback_mcode_init(global_State *g, uint8_t *page) /* push ebp/rbp; mov ah, slot>>8; mov ebp, &g. */ *p++ = XI_PUSH + RID_EBP; *p++ = XI_MOVrib | (RID_EAX+4); *p++ = (uint8_t)(slot >> 8); +#if LJ_GC64 + *p++ = 0x48; *p++ = XI_MOVri | RID_EBP; + *(uint64_t *)p = (uint64_t)(g); p += 8; +#else *p++ = XI_MOVri | RID_EBP; *(int32_t *)p = i32ptr(g); p += 4; +#endif #if LJ_64 /* jmp [rip-pageofs] where lj_vm_ffi_callback is stored. */ *p++ = XI_GROUP5; *p++ = XM_OFS0 + (XOg_JMP<<3) + RID_EBP; diff --git a/luajit-2.1/src/lj_cdata.c b/luajit-2.1/src/lj_cdata.c index fccf7f1..5cd2c11 100644 --- a/luajit-2.1/src/lj_cdata.c +++ b/luajit-2.1/src/lj_cdata.c @@ -121,7 +121,12 @@ collect_attrib: idx = (ptrdiff_t)intV(key); goto integer_key; } else if (tvisnum(key)) { /* Numeric key. */ - idx = LJ_64 ? (ptrdiff_t)numV(key) : (ptrdiff_t)lj_num2int(numV(key)); +#ifdef _MSC_VER + /* Workaround for MSVC bug. */ + volatile +#endif + lua_Number n = numV(key); + idx = LJ_64 ? (ptrdiff_t)n : (ptrdiff_t)lj_num2int(n); integer_key: if (ctype_ispointer(ct->info)) { CTSize sz = lj_ctype_size(cts, ctype_cid(ct->info)); /* Element size. */ diff --git a/luajit-2.1/src/lj_clib.c b/luajit-2.1/src/lj_clib.c index 6bdad67..1e927eb 100644 --- a/luajit-2.1/src/lj_clib.c +++ b/luajit-2.1/src/lj_clib.c @@ -172,9 +172,17 @@ LJ_NORET LJ_NOINLINE static void clib_error(lua_State *L, const char *fmt, const char *name) { DWORD err = GetLastError(); +#if LJ_TARGET_XBOXONE + wchar_t wbuf[128]; + char buf[128*2]; + if (!FormatMessageW(FORMAT_MESSAGE_IGNORE_INSERTS|FORMAT_MESSAGE_FROM_SYSTEM, + NULL, err, 0, wbuf, sizeof(wbuf)/sizeof(wchar_t), NULL) || + !WideCharToMultiByte(CP_ACP, 0, wbuf, 128, buf, 128*2, NULL, NULL)) +#else char buf[128]; if (!FormatMessageA(FORMAT_MESSAGE_IGNORE_INSERTS|FORMAT_MESSAGE_FROM_SYSTEM, NULL, err, 0, buf, sizeof(buf), NULL)) +#endif buf[0] = '\0'; lj_err_callermsg(L, lj_strfmt_pushf(L, fmt, name, buf)); } @@ -200,7 +208,7 @@ static const char *clib_extname(lua_State *L, const char *name) static void *clib_loadlib(lua_State *L, const char *name, int global) { DWORD oldwerr = GetLastError(); - void *h = (void *)LoadLibraryA(clib_extname(L, name)); + void *h = (void *)LoadLibraryExA(clib_extname(L, name), NULL, 0); if (!h) clib_error(L, "cannot load module " LUA_QS ": %s", name); SetLastError(oldwerr); UNUSED(global); @@ -241,9 +249,9 @@ static void *clib_getsym(CLibrary *cl, const char *name) GetModuleHandleExA(GET_MODULE_HANDLE_EX_FLAG_FROM_ADDRESS|GET_MODULE_HANDLE_EX_FLAG_UNCHANGED_REFCOUNT, (const char *)&_fmode, &h); break; - case CLIB_HANDLE_KERNEL32: h = LoadLibraryA("kernel32.dll"); break; - case CLIB_HANDLE_USER32: h = LoadLibraryA("user32.dll"); break; - case CLIB_HANDLE_GDI32: h = LoadLibraryA("gdi32.dll"); break; + case CLIB_HANDLE_KERNEL32: h = LoadLibraryExA("kernel32.dll", NULL, 0); break; + case CLIB_HANDLE_USER32: h = LoadLibraryExA("user32.dll", NULL, 0); break; + case CLIB_HANDLE_GDI32: h = LoadLibraryExA("gdi32.dll", NULL, 0); break; } if (!h) continue; clib_def_handle[i] = (void *)h; diff --git a/luajit-2.1/src/lj_cparse.c b/luajit-2.1/src/lj_cparse.c index d87932f..5d3874a 100644 --- a/luajit-2.1/src/lj_cparse.c +++ b/luajit-2.1/src/lj_cparse.c @@ -784,6 +784,10 @@ static void cp_push_type(CPDecl *decl, CTypeID id) cp_push(decl, info & ~CTMASK_CID, size); /* Copy type. */ break; case CT_ARRAY: + if ((ct->info & (CTF_VECTOR|CTF_COMPLEX))) { + info |= (decl->attr & CTF_QUAL); + decl->attr &= ~CTF_QUAL; + } cp_push_type(decl, ctype_cid(info)); /* Unroll. */ cp_push(decl, info & ~CTMASK_CID, size); /* Copy type. */ decl->stack[decl->pos].sib = 1; /* Mark as already checked and sized. */ diff --git a/luajit-2.1/src/lj_ctype.c b/luajit-2.1/src/lj_ctype.c index 2e23c99..eda070c 100644 --- a/luajit-2.1/src/lj_ctype.c +++ b/luajit-2.1/src/lj_ctype.c @@ -38,6 +38,8 @@ _("uint64_t", UINT64) \ _("intptr_t", INT_PSZ) \ _("uintptr_t", UINT_PSZ) \ + /* From POSIX. */ \ + _("ssize_t", INT_PSZ) \ /* End of typedef list. */ /* Keywords (only the ones we actually care for). */ diff --git a/luajit-2.1/src/lj_err.c b/luajit-2.1/src/lj_err.c index 4f13494..9ac0c98 100644 --- a/luajit-2.1/src/lj_err.c +++ b/luajit-2.1/src/lj_err.c @@ -58,10 +58,10 @@ ** EXT cannot be enabled on WIN32 since system exceptions use code-driven SEH. ** EXT is mandatory on WIN64 since the calling convention has an abundance ** of callee-saved registers (rbx, rbp, rsi, rdi, r12-r15, xmm6-xmm15). -** EXT is mandatory on POSIX/x64 since the interpreter doesn't save r12/r13. +** The POSIX/x64 interpreter only saves r12/r13 for INT (e.g. PS4). */ -#if defined(__GNUC__) && (LJ_TARGET_X64 || defined(LUAJIT_UNWIND_EXTERNAL)) +#if defined(__GNUC__) && (LJ_TARGET_X64 || defined(LUAJIT_UNWIND_EXTERNAL)) && !LJ_NO_UNWIND #define LJ_UNWIND_EXT 1 #elif LJ_TARGET_X64 && LJ_TARGET_WINDOWS #define LJ_UNWIND_EXT 1 @@ -119,7 +119,7 @@ static void *err_unwind(lua_State *L, void *stopcf, int errcode) if (errcode) { L->base = frame_prevd(frame) + 1; L->cframe = cframe_prev(cf); - unwindstack(L, frame); + unwindstack(L, frame - LJ_FR2); } else if (cf != stopcf) { cf = cframe_prev(cf); frame = frame_prevd(frame); @@ -144,7 +144,7 @@ static void *err_unwind(lua_State *L, void *stopcf, int errcode) if (errcode) { L->base = frame_prevd(frame) + 1; L->cframe = cframe_prev(cf); - unwindstack(L, frame); + unwindstack(L, frame - LJ_FR2); } return cf; case FRAME_CONT: /* Continuation frame. */ @@ -183,7 +183,7 @@ static void *err_unwind(lua_State *L, void *stopcf, int errcode) /* -- External frame unwinding -------------------------------------------- */ -#if defined(__GNUC__) && !LJ_NO_UNWIND && !LJ_TARGET_WINDOWS +#if defined(__GNUC__) && !LJ_NO_UNWIND && !LJ_ABI_WIN /* ** We have to use our own definitions instead of the mandatory (!) unwind.h, @@ -349,7 +349,7 @@ LJ_FUNCA int lj_err_unwind_arm(int state, void *ucb, _Unwind_Context *ctx) #endif -#elif LJ_TARGET_X64 && LJ_TARGET_WINDOWS +#elif LJ_TARGET_X64 && LJ_ABI_WIN /* ** Someone in Redmond owes me several days of my life. A lot of this is @@ -414,7 +414,9 @@ LJ_FUNCA EXCEPTION_DISPOSITION lj_err_unwind_win64(EXCEPTION_RECORD *rec, if (cf2) { /* We catch it, so start unwinding the upper frames. */ if (rec->ExceptionCode == LJ_MSVC_EXCODE || rec->ExceptionCode == LJ_GCC_EXCODE) { +#if LJ_TARGET_WINDOWS __DestructExceptionObject(rec, 1); +#endif setstrV(L, L->top++, lj_err_str(L, LJ_ERR_ERRCPP)); } else if (!LJ_EXCODE_CHECK(rec->ExceptionCode)) { /* Don't catch access violations etc. */ diff --git a/luajit-2.1/src/lj_ffrecord.c b/luajit-2.1/src/lj_ffrecord.c index e17f681..281f017 100644 --- a/luajit-2.1/src/lj_ffrecord.c +++ b/luajit-2.1/src/lj_ffrecord.c @@ -100,7 +100,6 @@ static ptrdiff_t results_wanted(jit_State *J) static void recff_stitch(jit_State *J) { ASMFunction cont = lj_cont_stitch; - TraceNo traceno = J->cur.traceno; lua_State *L = J->L; TValue *base = L->base; const BCIns *pc = frame_pc(base-1); @@ -113,7 +112,7 @@ static void recff_stitch(jit_State *J) setframe_ftsz(base+1, ((char *)(base+1) - (char *)pframe) + FRAME_CONT); setcont(base, cont); setframe_pc(base, pc); - if (LJ_DUALNUM) setintV(base-1, traceno); else base[-1].u64 = traceno; + setnilV(base-1); /* Incorrect, but rec_check_slots() won't run anymore. */ L->base += 2; L->top += 2; @@ -125,7 +124,9 @@ static void recff_stitch(jit_State *J) trcont = lj_ir_kptr(J, (void *)cont); #endif J->base[0] = trcont | TREF_CONT; - J->base[-1] = LJ_DUALNUM ? lj_ir_kint(J,traceno) : lj_ir_knum_u64(J,traceno); + J->ktracep = lj_ir_k64_reserve(J); + lua_assert(irt_toitype_(IRT_P64) == LJ_TTRACE); + J->base[-1] = emitir(IRT(IR_XLOAD, IRT_P64), lj_ir_kptr(J, &J->ktracep->gcr), 0); J->base += 2; J->baseslot += 2; J->framedepth++; @@ -434,11 +435,12 @@ static void LJ_FASTCALL recff_ipairs_aux(jit_State *J, RecordFFData *rd) static void LJ_FASTCALL recff_xpairs(jit_State *J, RecordFFData *rd) { - if (!(LJ_52 && recff_metacall(J, rd, MM_ipairs))) { - TRef tab = J->base[0]; - if (tref_istab(tab)) { + TRef tr = J->base[0]; + if (!((LJ_52 || (LJ_HASFFI && tref_iscdata(tr))) && + recff_metacall(J, rd, MM_pairs + rd->data))) { + if (tref_istab(tr)) { J->base[0] = lj_ir_kfunc(J, funcV(&J->fn->c.upvalue[0])); - J->base[1] = tab; + J->base[1] = tr; J->base[2] = rd->data ? lj_ir_kint(J, 0) : TREF_NIL; rd->nres = 3; } /* else: Interpreter will throw. */ diff --git a/luajit-2.1/src/lj_frame.h b/luajit-2.1/src/lj_frame.h index b9595a5..a86c36b 100644 --- a/luajit-2.1/src/lj_frame.h +++ b/luajit-2.1/src/lj_frame.h @@ -127,22 +127,42 @@ enum { LJ_CONT_TAILCALL, LJ_CONT_FFI_CALLBACK }; /* Special continuations. */ #elif LJ_TARGET_X64 #if LJ_ABI_WIN #define CFRAME_OFS_PREV (13*8) +#if LJ_GC64 +#define CFRAME_OFS_PC (12*8) +#define CFRAME_OFS_L (11*8) +#define CFRAME_OFS_ERRF (21*4) +#define CFRAME_OFS_NRES (20*4) +#define CFRAME_OFS_MULTRES (8*4) +#else #define CFRAME_OFS_PC (25*4) #define CFRAME_OFS_L (24*4) #define CFRAME_OFS_ERRF (23*4) #define CFRAME_OFS_NRES (22*4) #define CFRAME_OFS_MULTRES (21*4) +#endif #define CFRAME_SIZE (10*8) #define CFRAME_SIZE_JIT (CFRAME_SIZE + 9*16 + 4*8) #define CFRAME_SHIFT_MULTRES 0 #else #define CFRAME_OFS_PREV (4*8) +#if LJ_GC64 +#define CFRAME_OFS_PC (3*8) +#define CFRAME_OFS_L (2*8) +#define CFRAME_OFS_ERRF (3*4) +#define CFRAME_OFS_NRES (2*4) +#define CFRAME_OFS_MULTRES (0*4) +#else #define CFRAME_OFS_PC (7*4) #define CFRAME_OFS_L (6*4) #define CFRAME_OFS_ERRF (5*4) #define CFRAME_OFS_NRES (4*4) #define CFRAME_OFS_MULTRES (1*4) +#endif +#if LJ_NO_UNWIND +#define CFRAME_SIZE (12*8) +#else #define CFRAME_SIZE (10*8) +#endif #define CFRAME_SIZE_JIT (CFRAME_SIZE + 16) #define CFRAME_SHIFT_MULTRES 0 #endif diff --git a/luajit-2.1/src/lj_gc.c b/luajit-2.1/src/lj_gc.c index 99d664a..afd3997 100644 --- a/luajit-2.1/src/lj_gc.c +++ b/luajit-2.1/src/lj_gc.c @@ -69,7 +69,7 @@ static void gc_mark(global_State *g, GCobj *o) gray2black(o); /* Closed upvalues are never gray. */ } else if (gct != ~LJ_TSTR && gct != ~LJ_TCDATA) { lua_assert(gct == ~LJ_TFUNC || gct == ~LJ_TTAB || - gct == ~LJ_TTHREAD || gct == ~LJ_TPROTO); + gct == ~LJ_TTHREAD || gct == ~LJ_TPROTO || gct == ~LJ_TTRACE); setgcrefr(o->gch.gclist, g->gc.gray); setgcref(g->gc.gray, o); } diff --git a/luajit-2.1/src/lj_gdbjit.c b/luajit-2.1/src/lj_gdbjit.c index c289cd8..9b95e52 100644 --- a/luajit-2.1/src/lj_gdbjit.c +++ b/luajit-2.1/src/lj_gdbjit.c @@ -556,8 +556,8 @@ static void LJ_FASTCALL gdbjit_ehframe(GDBJITctx *ctx) DB(DW_CFA_offset|DW_REG_15); DUV(4); DB(DW_CFA_offset|DW_REG_14); DUV(5); /* Extra registers saved for JIT-compiled code. */ - DB(DW_CFA_offset|DW_REG_13); DUV(9); - DB(DW_CFA_offset|DW_REG_12); DUV(10); + DB(DW_CFA_offset|DW_REG_13); DUV(LJ_GC64 ? 10 : 9); + DB(DW_CFA_offset|DW_REG_12); DUV(LJ_GC64 ? 11 : 10); #elif LJ_TARGET_ARM { int i; diff --git a/luajit-2.1/src/lj_ir.c b/luajit-2.1/src/lj_ir.c index 9682e05..567aec8 100644 --- a/luajit-2.1/src/lj_ir.c +++ b/luajit-2.1/src/lj_ir.c @@ -209,24 +209,13 @@ void lj_ir_k64_freeall(jit_State *J) lj_mem_free(J2G(J), k, sizeof(K64Array)); k = next; } + setmref(J->k64, NULL); } -/* Find 64 bit constant in chained array or add it. */ -cTValue *lj_ir_k64_find(jit_State *J, uint64_t u64) +/* Get new 64 bit constant slot. */ +static TValue *ir_k64_add(jit_State *J, K64Array *kp, uint64_t u64) { - K64Array *k, *kp = NULL; TValue *ntv; - MSize idx; - /* Search for the constant in the whole chain of arrays. */ - for (k = mref(J->k64, K64Array); k; k = mref(k->next, K64Array)) { - kp = k; /* Remember previous element in list. */ - for (idx = 0; idx < k->numk; idx++) { /* Search one array. */ - TValue *tv = &k->k[idx]; - if (tv->u64 == u64) /* Needed for +-0/NaN/absmask. */ - return tv; - } - } - /* Constant was not found, need to add it. */ if (!(kp && kp->numk < LJ_MIN_K64SZ)) { /* Allocate a new array. */ K64Array *kn = lj_mem_newt(J->L, sizeof(K64Array), K64Array); setmref(kn->next, NULL); @@ -242,6 +231,33 @@ cTValue *lj_ir_k64_find(jit_State *J, uint64_t u64) return ntv; } +/* Find 64 bit constant in chained array or add it. */ +cTValue *lj_ir_k64_find(jit_State *J, uint64_t u64) +{ + K64Array *k, *kp = NULL; + MSize idx; + /* Search for the constant in the whole chain of arrays. */ + for (k = mref(J->k64, K64Array); k; k = mref(k->next, K64Array)) { + kp = k; /* Remember previous element in list. */ + for (idx = 0; idx < k->numk; idx++) { /* Search one array. */ + TValue *tv = &k->k[idx]; + if (tv->u64 == u64) /* Needed for +-0/NaN/absmask. */ + return tv; + } + } + /* Otherwise add a new constant. */ + return ir_k64_add(J, kp, u64); +} + +TValue *lj_ir_k64_reserve(jit_State *J) +{ + K64Array *k, *kp = NULL; + lj_ir_k64_find(J, 0); /* Intern dummy 0 to protect the reserved slot. */ + /* Find last K64Array, if any. */ + for (k = mref(J->k64, K64Array); k; k = mref(k->next, K64Array)) kp = k; + return ir_k64_add(J, kp, 0); /* Set to 0. Final value is set later. */ +} + /* Intern 64 bit constant, given by its address. */ TRef lj_ir_k64(jit_State *J, IROp op, cTValue *tv) { diff --git a/luajit-2.1/src/lj_iropt.h b/luajit-2.1/src/lj_iropt.h index 4e424e7..4106ef8 100644 --- a/luajit-2.1/src/lj_iropt.h +++ b/luajit-2.1/src/lj_iropt.h @@ -40,6 +40,7 @@ static LJ_AINLINE IRRef lj_ir_nextins(jit_State *J) LJ_FUNC TRef LJ_FASTCALL lj_ir_kint(jit_State *J, int32_t k); LJ_FUNC void lj_ir_k64_freeall(jit_State *J); LJ_FUNC TRef lj_ir_k64(jit_State *J, IROp op, cTValue *tv); +LJ_FUNC TValue *lj_ir_k64_reserve(jit_State *J); LJ_FUNC cTValue *lj_ir_k64_find(jit_State *J, uint64_t u64); LJ_FUNC TRef lj_ir_knum_u64(jit_State *J, uint64_t u64); LJ_FUNC TRef lj_ir_knumint(jit_State *J, lua_Number n); diff --git a/luajit-2.1/src/lj_jit.h b/luajit-2.1/src/lj_jit.h index 4b51bae..10900bf 100644 --- a/luajit-2.1/src/lj_jit.h +++ b/luajit-2.1/src/lj_jit.h @@ -290,6 +290,16 @@ typedef struct ScEvEntry { uint8_t dir; /* Direction. 1: +, 0: -. */ } ScEvEntry; +/* Reverse bytecode map (IRRef -> PC). Only for selected instructions. */ +typedef struct RBCHashEntry { + MRef pc; /* Bytecode PC. */ + GCRef pt; /* Prototype. */ + IRRef ref; /* IR reference. */ +} RBCHashEntry; + +/* Number of slots in the reverse bytecode hash table. Must be a power of 2. */ +#define RBCHASH_SLOTS 8 + /* 128 bit SIMD constants. */ enum { LJ_KSIMD_ABS, @@ -364,12 +374,14 @@ typedef struct jit_State { PostProc postproc; /* Required post-processing after execution. */ #if LJ_SOFTFP || (LJ_32 && LJ_HASFFI) - int needsplit; /* Need SPLIT pass. */ + uint8_t needsplit; /* Need SPLIT pass. */ #endif + uint8_t retryrec; /* Retry recording. */ GCRef *trace; /* Array of traces. */ TraceNo freetrace; /* Start of scan for next free trace. */ MSize sizetrace; /* Size of trace array. */ + TValue *ktracep; /* Pointer to K64Array slot with GCtrace pointer. */ IRRef1 chain[IR__MAX]; /* IR instruction skip-list chain anchors. */ TRef slot[LJ_MAX_JSLOTS+LJ_STACK_EXTRA]; /* Stack slot map. */ @@ -382,6 +394,10 @@ typedef struct jit_State { uint32_t penaltyslot; /* Round-robin index into penalty slots. */ uint32_t prngstate; /* PRNG state. */ +#ifdef LUAJIT_ENABLE_TABLE_BUMP + RBCHashEntry rbchash[RBCHASH_SLOTS]; /* Reverse bytecode map. */ +#endif + BPropEntry bpropcache[BPROP_SLOTS]; /* Backpropagation cache slots. */ uint32_t bpropslot; /* Round-robin index into bpropcache slots. */ diff --git a/luajit-2.1/src/lj_lex.c b/luajit-2.1/src/lj_lex.c index 8409cd7..5a918f7 100644 --- a/luajit-2.1/src/lj_lex.c +++ b/luajit-2.1/src/lj_lex.c @@ -214,6 +214,33 @@ static void lex_string(LexState *ls, TValue *tv) c += 9; } break; + case 'u': /* Unicode escape '\u{XX...}'. */ + if (lex_next(ls) != '{') goto err_xesc; + lex_next(ls); + c = 0; + do { + c = (c << 4) | (ls->c & 15u); + if (!lj_char_isdigit(ls->c)) { + if (!lj_char_isxdigit(ls->c)) goto err_xesc; + c += 9; + } + if (c >= 0x110000) goto err_xesc; /* Out of Unicode range. */ + } while (lex_next(ls) != '}'); + if (c < 0x800) { + if (c < 0x80) break; + lex_save(ls, 0xc0 | (c >> 6)); + } else { + if (c >= 0x10000) { + lex_save(ls, 0xf0 | (c >> 18)); + lex_save(ls, 0x80 | ((c >> 12) & 0x3f)); + } else { + if (c >= 0xd800 && c < 0xe000) goto err_xesc; /* No surrogates. */ + lex_save(ls, 0xe0 | (c >> 12)); + } + lex_save(ls, 0x80 | ((c >> 6) & 0x3f)); + } + c = 0x80 | (c & 0x3f); + break; case 'z': /* Skip whitespace. */ lex_next(ls); while (lj_char_isspace(ls->c)) diff --git a/luajit-2.1/src/lj_opt_narrow.c b/luajit-2.1/src/lj_opt_narrow.c index d221c30..d199345 100644 --- a/luajit-2.1/src/lj_opt_narrow.c +++ b/luajit-2.1/src/lj_opt_narrow.c @@ -205,7 +205,6 @@ typedef struct NarrowConv { jit_State *J; /* JIT compiler state. */ NarrowIns *sp; /* Current stack pointer. */ NarrowIns *maxsp; /* Maximum stack pointer minus redzone. */ - int lim; /* Limit on the number of emitted conversions. */ IRRef mode; /* Conversion mode (IRCONV_*). */ IRType t; /* Destination type: IRT_INT or IRT_I64. */ NarrowIns stack[NARROW_MAX_STACK]; /* Stack holding stack-machine code. */ @@ -247,10 +246,16 @@ static void narrow_stripov_backprop(NarrowConv *nc, IRRef ref, int depth) if (bp) { ref = bp->val; } else if (++depth < NARROW_MAX_BACKPROP && nc->sp < nc->maxsp) { + NarrowIns *savesp = nc->sp; narrow_stripov_backprop(nc, ir->op1, depth); - narrow_stripov_backprop(nc, ir->op2, depth); - *nc->sp++ = NARROWINS(IRT(ir->o - IR_ADDOV + IR_ADD, IRT_INT), ref); - return; + if (nc->sp < nc->maxsp) { + narrow_stripov_backprop(nc, ir->op2, depth); + if (nc->sp < nc->maxsp) { + *nc->sp++ = NARROWINS(IRT(ir->o - IR_ADDOV + IR_ADD, IRT_INT), ref); + return; + } + } + nc->sp = savesp; /* Path too deep, need to backtrack. */ } } *nc->sp++ = NARROWINS(NARROW_REF, ref); @@ -263,6 +268,8 @@ static int narrow_conv_backprop(NarrowConv *nc, IRRef ref, int depth) IRIns *ir = IR(ref); IRRef cref; + if (nc->sp >= nc->maxsp) return 10; /* Path too deep. */ + /* Check the easy cases first. */ if (ir->o == IR_CONV && (ir->op2 & IRCONV_SRCMASK) == IRT_INT) { if ((nc->mode & IRCONV_CONVMASK) <= IRCONV_ANY) @@ -334,7 +341,7 @@ static int narrow_conv_backprop(NarrowConv *nc, IRRef ref, int depth) NarrowIns *savesp = nc->sp; int count = narrow_conv_backprop(nc, ir->op1, depth); count += narrow_conv_backprop(nc, ir->op2, depth); - if (count <= nc->lim) { /* Limit total number of conversions. */ + if (count <= 1) { /* Limit total number of conversions. */ *nc->sp++ = NARROWINS(IRT(ir->o, nc->t), ref); return count; } @@ -406,12 +413,10 @@ TRef LJ_FASTCALL lj_opt_narrow_convert(jit_State *J) nc.t = irt_type(fins->t); if (fins->o == IR_TOBIT) { nc.mode = IRCONV_TOBIT; /* Used only in the backpropagation cache. */ - nc.lim = 2; /* TOBIT can use a more optimistic rule. */ } else { nc.mode = fins->op2; - nc.lim = 1; } - if (narrow_conv_backprop(&nc, fins->op1, 0) <= nc.lim) + if (narrow_conv_backprop(&nc, fins->op1, 0) <= 1) return narrow_conv_emit(J, &nc); } return NEXTFOLD; diff --git a/luajit-2.1/src/lj_profile.c b/luajit-2.1/src/lj_profile.c index 0136701..c7e5396 100644 --- a/luajit-2.1/src/lj_profile.c +++ b/luajit-2.1/src/lj_profile.c @@ -266,7 +266,7 @@ static void profile_timer_start(ProfileState *ps) { #if LJ_TARGET_WINDOWS if (!ps->wmm) { /* Load WinMM library on-demand. */ - ps->wmm = LoadLibraryA("winmm.dll"); + ps->wmm = LoadLibraryExA("winmm.dll", NULL, 0); if (ps->wmm) { ps->wmm_tbp = (WMM_TPFUNC)GetProcAddress(ps->wmm, "timeBeginPeriod"); ps->wmm_tep = (WMM_TPFUNC)GetProcAddress(ps->wmm, "timeEndPeriod"); diff --git a/luajit-2.1/src/lj_record.c b/luajit-2.1/src/lj_record.c index 5603815..dc5f2d5 100644 --- a/luajit-2.1/src/lj_record.c +++ b/luajit-2.1/src/lj_record.c @@ -235,6 +235,10 @@ static void canonicalize_slots(jit_State *J) /* Stop recording. */ void lj_record_stop(jit_State *J, TraceLink linktype, TraceNo lnk) { +#ifdef LUAJIT_ENABLE_TABLE_BUMP + if (J->retryrec) + lj_trace_err(J, LJ_TRERR_RETRY); +#endif lj_trace_end(J); J->cur.linktype = (uint8_t)linktype; J->cur.link = (uint16_t)lnk; @@ -1127,6 +1131,72 @@ static void rec_mm_comp_cdata(jit_State *J, RecordIndex *ix, int op, MMS mm) /* -- Indexed access ------------------------------------------------------ */ +#ifdef LUAJIT_ENABLE_TABLE_BUMP +/* Bump table allocations in bytecode when they grow during recording. */ +static void rec_idx_bump(jit_State *J, RecordIndex *ix) +{ + RBCHashEntry *rbc = &J->rbchash[(ix->tab & (RBCHASH_SLOTS-1))]; + if (tref_ref(ix->tab) == rbc->ref) { + const BCIns *pc = mref(rbc->pc, const BCIns); + GCtab *tb = tabV(&ix->tabv); + uint32_t nhbits; + IRIns *ir; + if (!tvisnil(&ix->keyv)) + (void)lj_tab_set(J->L, tb, &ix->keyv); /* Grow table right now. */ + nhbits = tb->hmask > 0 ? lj_fls(tb->hmask)+1 : 0; + ir = IR(tref_ref(ix->tab)); + if (ir->o == IR_TNEW) { + uint32_t ah = bc_d(*pc); + uint32_t asize = ah & 0x7ff, hbits = ah >> 11; + if (nhbits > hbits) hbits = nhbits; + if (tb->asize > asize) { + asize = tb->asize <= 0x7ff ? tb->asize : 0x7ff; + } + if ((asize | (hbits<<11)) != ah) { /* Has the size changed? */ + /* Patch bytecode, but continue recording (for more patching). */ + setbc_d(pc, (asize | (hbits<<11))); + /* Patching TNEW operands is only safe if the trace is aborted. */ + ir->op1 = asize; ir->op2 = hbits; + J->retryrec = 1; /* Abort the trace at the end of recording. */ + } + } else if (ir->o == IR_TDUP) { + GCtab *tpl = gco2tab(proto_kgc(&gcref(rbc->pt)->pt, ~(ptrdiff_t)bc_d(*pc))); + /* Grow template table, but preserve keys with nil values. */ + if ((tb->asize > tpl->asize && (1u << nhbits)-1 == tpl->hmask) || + (tb->asize == tpl->asize && (1u << nhbits)-1 > tpl->hmask)) { + Node *node = noderef(tpl->node); + uint32_t i, hmask = tpl->hmask, asize; + TValue *array; + for (i = 0; i <= hmask; i++) { + if (!tvisnil(&node[i].key) && tvisnil(&node[i].val)) + settabV(J->L, &node[i].val, tpl); + } + if (!tvisnil(&ix->keyv) && tref_isk(ix->key)) { + TValue *o = lj_tab_set(J->L, tpl, &ix->keyv); + if (tvisnil(o)) settabV(J->L, o, tpl); + } + lj_tab_resize(J->L, tpl, tb->asize, nhbits); + node = noderef(tpl->node); + hmask = tpl->hmask; + for (i = 0; i <= hmask; i++) { + /* This is safe, since template tables only hold immutable values. */ + if (tvistab(&node[i].val)) + setnilV(&node[i].val); + } + /* The shape of the table may have changed. Clean up array part, too. */ + asize = tpl->asize; + array = tvref(tpl->array); + for (i = 0; i < asize; i++) { + if (tvistab(&array[i])) + setnilV(&array[i]); + } + J->retryrec = 1; /* Abort the trace at the end of recording. */ + } + } + } +} +#endif + /* Record bounds-check. */ static void rec_idx_abc(jit_State *J, TRef asizeref, TRef ikey, uint32_t asize) { @@ -1352,6 +1422,10 @@ TRef lj_record_idx(jit_State *J, RecordIndex *ix) key = emitir(IRTN(IR_CONV), key, IRCONV_NUM_INT); xref = emitir(IRT(IR_NEWREF, IRT_P32), ix->tab, key); keybarrier = 0; /* NEWREF already takes care of the key barrier. */ +#ifdef LUAJIT_ENABLE_TABLE_BUMP + if ((J->flags & JIT_F_OPT_SINK)) /* Avoid a separate flag. */ + rec_idx_bump(J, ix); +#endif } } else if (!lj_opt_fwd_wasnonnil(J, loadop, tref_ref(xref))) { /* Cannot derive that the previous value was non-nil, must do checks. */ @@ -1390,9 +1464,18 @@ static void rec_tsetm(jit_State *J, BCReg ra, BCReg rn, int32_t i) { RecordIndex ix; cTValue *basev = J->L->base; - copyTV(J->L, &ix.tabv, &basev[ra-1]); + GCtab *t = tabV(&basev[ra-1]); + settabV(J->L, &ix.tabv, t); ix.tab = getslot(J, ra-1); ix.idxchain = 0; +#ifdef LUAJIT_ENABLE_TABLE_BUMP + if ((J->flags & JIT_F_OPT_SINK)) { + if (t->asize < i+rn-ra) + lj_tab_reasize(J->L, t, i+rn-ra); + setnilV(&ix.keyv); + rec_idx_bump(J, &ix); + } +#endif for (; ra < rn; i++, ra++) { setintV(&ix.keyv, i); ix.key = lj_ir_kint(J, i); @@ -1712,8 +1795,15 @@ static TRef rec_tnew(jit_State *J, uint32_t ah) { uint32_t asize = ah & 0x7ff; uint32_t hbits = ah >> 11; + TRef tr; if (asize == 0x7ff) asize = 0x801; - return emitir(IRTG(IR_TNEW, IRT_TAB), asize, hbits); + tr = emitir(IRTG(IR_TNEW, IRT_TAB), asize, hbits); +#ifdef LUAJIT_ENABLE_TABLE_BUMP + J->rbchash[(tr & (RBCHASH_SLOTS-1))].ref = tref_ref(tr); + setmref(J->rbchash[(tr & (RBCHASH_SLOTS-1))].pc, J->pc); + setgcref(J->rbchash[(tr & (RBCHASH_SLOTS-1))].pt, obj2gco(J->pt)); +#endif + return tr; } /* -- Concatenation ------------------------------------------------------- */ @@ -2139,6 +2229,11 @@ void lj_record_ins(jit_State *J) case BC_TDUP: rc = emitir(IRTG(IR_TDUP, IRT_TAB), lj_ir_ktab(J, gco2tab(proto_kgc(J->pt, ~(ptrdiff_t)rc))), 0); +#ifdef LUAJIT_ENABLE_TABLE_BUMP + J->rbchash[(rc & (RBCHASH_SLOTS-1))].ref = tref_ref(rc); + setmref(J->rbchash[(rc & (RBCHASH_SLOTS-1))].pc, pc); + setgcref(J->rbchash[(rc & (RBCHASH_SLOTS-1))].pt, obj2gco(J->pt)); +#endif break; /* -- Calls and vararg handling ----------------------------------------- */ @@ -2352,6 +2447,9 @@ void lj_record_setup(jit_State *J) /* Initialize state related to current trace. */ memset(J->slot, 0, sizeof(J->slot)); memset(J->chain, 0, sizeof(J->chain)); +#ifdef LUAJIT_ENABLE_TABLE_BUMP + memset(J->rbchash, 0, sizeof(J->rbchash)); +#endif memset(J->bpropcache, 0, sizeof(J->bpropcache)); J->scev.idx = REF_NIL; setmref(J->scev.pc, NULL); diff --git a/luajit-2.1/src/lj_snap.c b/luajit-2.1/src/lj_snap.c index d8e7987..7c78f8a 100644 --- a/luajit-2.1/src/lj_snap.c +++ b/luajit-2.1/src/lj_snap.c @@ -26,9 +26,6 @@ #include "lj_cdata.h" #endif -/* Some local macros to save typing. Undef'd at the end. */ -#define IR(ref) (&J->cur.ir[(ref)]) - /* Pass IR on to next optimization in chain (FOLD). */ #define emitir(ot, a, b) (lj_ir_set(J, (ot), (a), (b)), lj_opt_fold(J)) @@ -73,7 +70,7 @@ static MSize snapshot_slots(jit_State *J, SnapEntry *map, BCReg nslots) IRRef ref = tref_ref(tr); if (ref) { SnapEntry sn = SNAP_TR(s, tr); - IRIns *ir = IR(ref); + IRIns *ir = &J->cur.ir[ref]; if (!(sn & (SNAP_CONT|SNAP_FRAME)) && ir->o == IR_SLOAD && ir->op1 == s && ref > retf) { /* No need to snapshot unmodified non-inherited slots. */ @@ -407,24 +404,24 @@ static TRef snap_pref(jit_State *J, GCtrace *T, SnapEntry *map, MSize nmax, } /* Check whether a sunk store corresponds to an allocation. Slow path. */ -static int snap_sunk_store2(jit_State *J, IRIns *ira, IRIns *irs) +static int snap_sunk_store2(GCtrace *T, IRIns *ira, IRIns *irs) { if (irs->o == IR_ASTORE || irs->o == IR_HSTORE || irs->o == IR_FSTORE || irs->o == IR_XSTORE) { - IRIns *irk = IR(irs->op1); + IRIns *irk = &T->ir[irs->op1]; if (irk->o == IR_AREF || irk->o == IR_HREFK) - irk = IR(irk->op1); - return (IR(irk->op1) == ira); + irk = &T->ir[irk->op1]; + return (&T->ir[irk->op1] == ira); } return 0; } /* Check whether a sunk store corresponds to an allocation. Fast path. */ -static LJ_AINLINE int snap_sunk_store(jit_State *J, IRIns *ira, IRIns *irs) +static LJ_AINLINE int snap_sunk_store(GCtrace *T, IRIns *ira, IRIns *irs) { if (irs->s != 255) return (ira + irs->s == irs); /* Fast check. */ - return snap_sunk_store2(J, ira, irs); + return snap_sunk_store2(T, ira, irs); } /* Replay snapshot state to setup side trace. */ @@ -487,7 +484,7 @@ void lj_snap_replay(jit_State *J, GCtrace *T) } else { IRIns *irs; for (irs = ir+1; irs < irlast; irs++) - if (irs->r == RID_SINK && snap_sunk_store(J, ir, irs)) { + if (irs->r == RID_SINK && snap_sunk_store(T, ir, irs)) { if (snap_pref(J, T, map, nent, seen, irs->op2) == 0) snap_pref(J, T, map, nent, seen, T->ir[irs->op2].op1); else if ((LJ_SOFTFP || (LJ_32 && LJ_HASFFI)) && @@ -521,13 +518,13 @@ void lj_snap_replay(jit_State *J, GCtrace *T) op2 = emitir_raw(IRT(IR_HIOP, IRT_I64), op2, snap_pref(J, T, map, nent, seen, (ir+1)->op2)); } - J->slot[snap_slot(sn)] = emitir(ir->ot, op1, op2); + J->slot[snap_slot(sn)] = emitir(ir->ot & ~(IRT_MARK|IRT_ISPHI), op1, op2); } else { IRIns *irs; TRef tr = emitir(ir->ot, op1, op2); J->slot[snap_slot(sn)] = tr; for (irs = ir+1; irs < irlast; irs++) - if (irs->r == RID_SINK && snap_sunk_store(J, ir, irs)) { + if (irs->r == RID_SINK && snap_sunk_store(T, ir, irs)) { IRIns *irr = &T->ir[irs->op1]; TRef val, key = irr->op2, tmp = tr; if (irr->o != IR_FREF) { @@ -631,8 +628,8 @@ static void snap_restoreval(jit_State *J, GCtrace *T, ExitState *ex, } else if (irt_isnum(t)) { setnumV(o, ex->fpr[r-RID_MIN_FPR]); #endif - } else if (LJ_64 && irt_islightud(t)) { - /* 64 bit lightuserdata which may escape already has the tag bits. */ + } else if (LJ_64 && irt_is64(t)) { + /* 64 bit values that already have the tag bits. */ o->u64 = ex->gpr[r-RID_MIN_GPR]; } else if (irt_ispri(t)) { setpriV(o, irt_toitype(t)); @@ -729,7 +726,7 @@ static void snap_unsink(jit_State *J, GCtrace *T, ExitState *ex, } else { IRIns *irs, *irlast = &T->ir[T->snap[snapno].ref]; for (irs = ir+1; irs < irlast; irs++) - if (irs->r == RID_SINK && snap_sunk_store(J, ir, irs)) { + if (irs->r == RID_SINK && snap_sunk_store(T, ir, irs)) { IRIns *iro = &T->ir[T->ir[irs->op1].op2]; uint8_t *p = (uint8_t *)cd; CTSize szs; @@ -762,7 +759,7 @@ static void snap_unsink(jit_State *J, GCtrace *T, ExitState *ex, settabV(J->L, o, t); irlast = &T->ir[T->snap[snapno].ref]; for (irs = ir+1; irs < irlast; irs++) - if (irs->r == RID_SINK && snap_sunk_store(J, ir, irs)) { + if (irs->r == RID_SINK && snap_sunk_store(T, ir, irs)) { IRIns *irk = &T->ir[irs->op1]; TValue tmp, *val; lua_assert(irs->o == IR_ASTORE || irs->o == IR_HSTORE || @@ -863,7 +860,6 @@ const BCIns *lj_snap_restore(jit_State *J, void *exptr) return pc; } -#undef IR #undef emitir_raw #undef emitir diff --git a/luajit-2.1/src/lj_strscan.c b/luajit-2.1/src/lj_strscan.c index 568f647..d3c5ba9 100644 --- a/luajit-2.1/src/lj_strscan.c +++ b/luajit-2.1/src/lj_strscan.c @@ -140,7 +140,7 @@ static StrScanFmt strscan_hex(const uint8_t *p, TValue *o, break; } - /* Reduce range then convert to double. */ + /* Reduce range, then convert to double. */ if ((x & U64x(c0000000,0000000))) { x = (x >> 2) | (x & 3); ex2 += 2; } strscan_double(x, o, ex2, neg); return fmt; @@ -326,6 +326,49 @@ static StrScanFmt strscan_dec(const uint8_t *p, TValue *o, return fmt; } +/* Parse binary number. */ +static StrScanFmt strscan_bin(const uint8_t *p, TValue *o, + StrScanFmt fmt, uint32_t opt, + int32_t ex2, int32_t neg, uint32_t dig) +{ + uint64_t x = 0; + uint32_t i; + + if (ex2 || dig > 64) return STRSCAN_ERROR; + + /* Scan binary digits. */ + for (i = dig; i; i--, p++) { + if ((*p & ~1) != '0') return STRSCAN_ERROR; + x = (x << 1) | (*p & 1); + } + + /* Format-specific handling. */ + switch (fmt) { + case STRSCAN_INT: + if (!(opt & STRSCAN_OPT_TONUM) && x < 0x80000000u+neg) { + o->i = neg ? -(int32_t)x : (int32_t)x; + return STRSCAN_INT; /* Fast path for 32 bit integers. */ + } + if (!(opt & STRSCAN_OPT_C)) { fmt = STRSCAN_NUM; break; } + /* fallthrough */ + case STRSCAN_U32: + if (dig > 32) return STRSCAN_ERROR; + o->i = neg ? -(int32_t)x : (int32_t)x; + return STRSCAN_U32; + case STRSCAN_I64: + case STRSCAN_U64: + o->u64 = neg ? (uint64_t)-(int64_t)x : x; + return fmt; + default: + break; + } + + /* Reduce range, then convert to double. */ + if ((x & U64x(c0000000,0000000))) { x = (x >> 2) | (x & 3); ex2 += 2; } + strscan_double(x, o, ex2, neg); + return fmt; +} + /* Scan string containing a number. Returns format. Returns value in o. */ StrScanFmt lj_strscan_scan(const uint8_t *p, TValue *o, uint32_t opt) { @@ -364,8 +407,12 @@ StrScanFmt lj_strscan_scan(const uint8_t *p, TValue *o, uint32_t opt) /* Determine base and skip leading zeros. */ if (LJ_UNLIKELY(*p <= '0')) { - if (*p == '0' && casecmp(p[1], 'x')) - base = 16, cmask = LJ_CHAR_XDIGIT, p += 2; + if (*p == '0') { + if (casecmp(p[1], 'x')) + base = 16, cmask = LJ_CHAR_XDIGIT, p += 2; + else if (casecmp(p[1], 'b')) + base = 2, cmask = LJ_CHAR_DIGIT, p += 2; + } for ( ; ; p++) { if (*p == '0') { hasdig = 1; @@ -403,7 +450,7 @@ StrScanFmt lj_strscan_scan(const uint8_t *p, TValue *o, uint32_t opt) } /* Parse exponent. */ - if (casecmp(*p, (uint32_t)(base == 16 ? 'p' : 'e'))) { + if (base >= 10 && casecmp(*p, (uint32_t)(base == 16 ? 'p' : 'e'))) { uint32_t xx; int negx = 0; fmt = STRSCAN_NUM; p++; @@ -460,6 +507,8 @@ StrScanFmt lj_strscan_scan(const uint8_t *p, TValue *o, uint32_t opt) return strscan_oct(sp, o, fmt, neg, dig); if (base == 16) fmt = strscan_hex(sp, o, fmt, opt, ex, neg, dig); + else if (base == 2) + fmt = strscan_bin(sp, o, fmt, opt, ex, neg, dig); else fmt = strscan_dec(sp, o, fmt, opt, ex, neg, dig); diff --git a/luajit-2.1/src/lj_tab.c b/luajit-2.1/src/lj_tab.c index a9f4383..88bf108 100644 --- a/luajit-2.1/src/lj_tab.c +++ b/luajit-2.1/src/lj_tab.c @@ -246,7 +246,7 @@ void LJ_FASTCALL lj_tab_free(global_State *g, GCtab *t) /* -- Table resizing ------------------------------------------------------ */ /* Resize a table to fit the new array/hash part sizes. */ -static void resizetab(lua_State *L, GCtab *t, uint32_t asize, uint32_t hbits) +void lj_tab_resize(lua_State *L, GCtab *t, uint32_t asize, uint32_t hbits) { Node *oldnode = noderef(t->node); uint32_t oldasize = t->asize; @@ -383,7 +383,7 @@ static void rehashtab(lua_State *L, GCtab *t, cTValue *ek) asize += countint(ek, bins); na = bestasize(bins, &asize); total -= na; - resizetab(L, t, asize, hsize2hbits(total)); + lj_tab_resize(L, t, asize, hsize2hbits(total)); } #if LJ_HASFFI @@ -395,7 +395,7 @@ void lj_tab_rehash(lua_State *L, GCtab *t) void lj_tab_reasize(lua_State *L, GCtab *t, uint32_t nasize) { - resizetab(L, t, nasize+1, t->hmask > 0 ? lj_fls(t->hmask)+1 : 0); + lj_tab_resize(L, t, nasize+1, t->hmask > 0 ? lj_fls(t->hmask)+1 : 0); } /* -- Table getters ------------------------------------------------------- */ diff --git a/luajit-2.1/src/lj_tab.h b/luajit-2.1/src/lj_tab.h index 1da28bd..7cf031b 100644 --- a/luajit-2.1/src/lj_tab.h +++ b/luajit-2.1/src/lj_tab.h @@ -44,6 +44,7 @@ LJ_FUNC void LJ_FASTCALL lj_tab_free(global_State *g, GCtab *t); #if LJ_HASFFI LJ_FUNC void lj_tab_rehash(lua_State *L, GCtab *t); #endif +LJ_FUNC void lj_tab_resize(lua_State *L, GCtab *t, uint32_t asize, uint32_t hbits); LJ_FUNCA void lj_tab_reasize(lua_State *L, GCtab *t, uint32_t nasize); /* Caveat: all getters except lj_tab_get() can return NULL! */ diff --git a/luajit-2.1/src/lj_target_x86.h b/luajit-2.1/src/lj_target_x86.h index 65e438f..fc9d370 100644 --- a/luajit-2.1/src/lj_target_x86.h +++ b/luajit-2.1/src/lj_target_x86.h @@ -132,7 +132,11 @@ enum { #define SPS_FIXED (4*2) #define SPS_FIRST (4*2) /* Don't use callee register save area. */ #else +#if LJ_GC64 +#define SPS_FIXED 2 +#else #define SPS_FIXED 4 +#endif #define SPS_FIRST 2 #endif #else diff --git a/luajit-2.1/src/lj_trace.c b/luajit-2.1/src/lj_trace.c index 39ff046..1d0c2e5 100644 --- a/luajit-2.1/src/lj_trace.c +++ b/luajit-2.1/src/lj_trace.c @@ -117,15 +117,22 @@ static void perftools_addtrace(GCtrace *T) } #endif -/* Save current trace by copying and compacting it. */ -static void trace_save(jit_State *J) +/* Allocate space for copy of trace. */ +static GCtrace *trace_save_alloc(jit_State *J) { size_t sztr = ((sizeof(GCtrace)+7)&~7); size_t szins = (J->cur.nins-J->cur.nk)*sizeof(IRIns); size_t sz = sztr + szins + J->cur.nsnap*sizeof(SnapShot) + J->cur.nsnapmap*sizeof(SnapEntry); - GCtrace *T = lj_mem_newt(J->L, (MSize)sz, GCtrace); + return lj_mem_newt(J->L, (MSize)sz, GCtrace); +} + +/* Save current trace by copying and compacting it. */ +static void trace_save(jit_State *J, GCtrace *T) +{ + size_t sztr = ((sizeof(GCtrace)+7)&~7); + size_t szins = (J->cur.nins-J->cur.nk)*sizeof(IRIns); char *p = (char *)T + sztr; memcpy(T, &J->cur, sizeof(GCtrace)); setgcrefr(T->nextgc, J2G(J)->gc.root); @@ -267,7 +274,7 @@ int lj_trace_flushall(lua_State *L) if (T->root == 0) trace_flushroot(J, T); lj_gdbjit_deltrace(J, T); - T->traceno = 0; + T->traceno = T->link = 0; /* Blacklist the link for cont_stitch. */ setgcrefnull(J->trace[i]); } } @@ -277,6 +284,7 @@ int lj_trace_flushall(lua_State *L) memset(J->penalty, 0, sizeof(J->penalty)); /* Free the whole machine code and invalidate all exit stub groups. */ lj_mcode_free(J); + lj_ir_k64_freeall(J); memset(J->exitstubgroup, 0, sizeof(J->exitstubgroup)); lj_vmevent_send(L, TRACE, setstrV(L, L->top++, lj_str_newlit(L, "flush")); @@ -394,6 +402,8 @@ static void trace_start(jit_State *J) J->guardemit.irt = 0; J->postproc = LJ_POST_NONE; lj_resetsplit(J); + J->retryrec = 0; + J->ktracep = NULL; setgcref(J->cur.startpt, obj2gco(J->pt)); L = J->L; @@ -417,6 +427,7 @@ static void trace_stop(jit_State *J) BCOp op = bc_op(J->cur.startins); GCproto *pt = &gcref(J->cur.startpt)->pt; TraceNo traceno = J->cur.traceno; + GCtrace *T = trace_save_alloc(J); /* Do this first. May throw OOM. */ lua_State *L; switch (op) { @@ -467,7 +478,10 @@ static void trace_stop(jit_State *J) /* Commit new mcode only after all patching is done. */ lj_mcode_commit(J, J->cur.mcode); J->postproc = LJ_POST_NONE; - trace_save(J); + trace_save(J, T); + if (J->ktracep) { /* Patch K64Array slot with the final GCtrace pointer. */ + setgcV(J->L, J->ktracep, obj2gco(T), LJ_TTRACE); + } L = J->L; lj_vmevent_send(L, TRACE, @@ -510,10 +524,15 @@ static int trace_abort(jit_State *J) } /* Penalize or blacklist starting bytecode instruction. */ if (J->parent == 0 && !bc_isret(bc_op(J->cur.startins))) { - if (J->exitno == 0) - penalty_pc(J, &gcref(J->cur.startpt)->pt, mref(J->cur.startpc, BCIns), e); - else + if (J->exitno == 0) { + BCIns *startpc = mref(J->cur.startpc, BCIns); + if (e == LJ_TRERR_RETRY) + hotcount_set(J2GG(J), startpc+1, 1); /* Immediate retry. */ + else + penalty_pc(J, &gcref(J->cur.startpt)->pt, startpc, e); + } else { traceref(J, J->exitno)->link = J->exitno; /* Self-link is blacklisted. */ + } } /* Is there anything to abort? */ diff --git a/luajit-2.1/src/lj_traceerr.h b/luajit-2.1/src/lj_traceerr.h index 6b377cb..d434be1 100644 --- a/luajit-2.1/src/lj_traceerr.h +++ b/luajit-2.1/src/lj_traceerr.h @@ -12,6 +12,7 @@ TREDEF(TRACEOV, "trace too long") TREDEF(STACKOV, "trace too deep") TREDEF(SNAPOV, "too many snapshots") TREDEF(BLACKL, "blacklisted") +TREDEF(RETRY, "retry recording") TREDEF(NYIBC, "NYI: bytecode %d") /* Recording loop ops. */ diff --git a/luajit-2.1/src/lua.h b/luajit-2.1/src/lua.h index c83fd3b..352d29f 100644 --- a/luajit-2.1/src/lua.h +++ b/luajit-2.1/src/lua.h @@ -226,6 +226,7 @@ LUA_API int (lua_status) (lua_State *L); #define LUA_GCSTEP 5 #define LUA_GCSETPAUSE 6 #define LUA_GCSETSTEPMUL 7 +#define LUA_GCISRUNNING 9 LUA_API int (lua_gc) (lua_State *L, int what, int data); diff --git a/luajit-2.1/src/luaconf.h b/luajit-2.1/src/luaconf.h index b2baf7b..6375ed3 100644 --- a/luajit-2.1/src/luaconf.h +++ b/luajit-2.1/src/luaconf.h @@ -37,7 +37,7 @@ #endif #define LUA_LROOT "/usr/local" #define LUA_LUADIR "/lua/5.1/" -#define LUA_LJDIR "/luajit-2.1.0-alpha/" +#define LUA_LJDIR "/luajit-2.1.0-beta1/" #ifdef LUA_ROOT #define LUA_JROOT LUA_ROOT diff --git a/luajit-2.1/src/luajit.h b/luajit-2.1/src/luajit.h index 3db4bba..9604185 100644 --- a/luajit-2.1/src/luajit.h +++ b/luajit-2.1/src/luajit.h @@ -30,9 +30,9 @@ #include "lua.h" -#define LUAJIT_VERSION "LuaJIT 2.1.0-alpha" +#define LUAJIT_VERSION "LuaJIT 2.1.0-beta1" #define LUAJIT_VERSION_NUM 20100 /* Version 2.1.0 = 02.01.00. */ -#define LUAJIT_VERSION_SYM luaJIT_version_2_1_0_alpha +#define LUAJIT_VERSION_SYM luaJIT_version_2_1_0_beta1 #define LUAJIT_COPYRIGHT "Copyright (C) 2005-2015 Mike Pall" #define LUAJIT_URL "http://luajit.org/" diff --git a/luajit-2.1/src/ps4build.bat b/luajit-2.1/src/ps4build.bat index 42fc9a6..337a44f 100644 --- a/luajit-2.1/src/ps4build.bat +++ b/luajit-2.1/src/ps4build.bat @@ -27,11 +27,11 @@ if exist minilua.exe.manifest^ @minilua
@if not errorlevel 8 goto :FAIL
-@set DASMFLAGS=-D P64
+@set DASMFLAGS=-D P64 -D NO_UNWIND
minilua %DASM% -LN %DASMFLAGS% -o host\buildvm_arch.h vm_x86.dasc
@if errorlevel 1 goto :BAD
-%LJCOMPILE% /I "." /I %DASMDIR% -DLUAJIT_TARGET=LUAJIT_ARCH_X64 -DLUAJIT_OS=LUAJIT_OS_OTHER -DLUAJIT_DISABLE_JIT -DLUAJIT_DISABLE_FFI host\buildvm*.c
+%LJCOMPILE% /I "." /I %DASMDIR% -DLUAJIT_TARGET=LUAJIT_ARCH_X64 -DLUAJIT_OS=LUAJIT_OS_OTHER -DLUAJIT_DISABLE_JIT -DLUAJIT_DISABLE_FFI -DLUAJIT_NO_UNWIND host\buildvm*.c
@if errorlevel 1 goto :BAD
%LJLINK% /out:buildvm.exe buildvm*.obj
@if errorlevel 1 goto :BAD
diff --git a/luajit-2.1/src/vm_arm.dasc b/luajit-2.1/src/vm_arm.dasc index 0bd9b14..af722f9 100644 --- a/luajit-2.1/src/vm_arm.dasc +++ b/luajit-2.1/src/vm_arm.dasc @@ -2086,7 +2086,7 @@ static void build_subroutines(BuildCtx *ctx) | // RA = resultptr, CARG4 = meta base | ldr RB, SAVE_MULTRES | ldr INS, [PC, #-4] - | ldr CARG3, [CARG4, #-24] // Save previous trace number. + | ldr TRACE:CARG3, [CARG4, #-24] // Save previous trace. | subs RB, RB, #8 | decode_RA8 RC, INS // Call base. | beq >2 @@ -2101,23 +2101,20 @@ static void build_subroutines(BuildCtx *ctx) | decode_RA8 RA, INS | decode_RB8 RB, INS | add RA, RA, RB - | ldr CARG1, [DISPATCH, #DISPATCH_J(trace)] |3: | cmp RA, RC | mvn CARG2, #~LJ_TNIL | bhi >9 // More results wanted? | - | ldr TRACE:RA, [CARG1, CARG3, lsl #2] - | cmp TRACE:RA, #0 - | beq ->cont_nop - | ldrh RC, TRACE:RA->link - | cmp RC, CARG3 + | ldrh RA, TRACE:CARG3->traceno + | ldrh RC, TRACE:CARG3->link + | cmp RC, RA | beq ->cont_nop // Blacklisted. | cmp RC, #0 | bne =>BC_JLOOP // Jump to stitched trace. | | // Stitch a new trace to the previous trace. - | str CARG3, [DISPATCH, #DISPATCH_J(exitno)] + | str RA, [DISPATCH, #DISPATCH_J(exitno)] | str L, [DISPATCH, #DISPATCH_J(L)] | str BASE, L->base | sub CARG1, DISPATCH, #-GG_DISP2J diff --git a/luajit-2.1/src/vm_arm64.dasc b/luajit-2.1/src/vm_arm64.dasc index a31cbb3..f1251f2 100644 --- a/luajit-2.1/src/vm_arm64.dasc +++ b/luajit-2.1/src/vm_arm64.dasc @@ -853,10 +853,10 @@ static void build_subroutines(BuildCtx *ctx) | str PC, SAVE_PC | add CARG3, RA, NARGS8:RC | bl extern lj_meta_call // (lua_State *L, TValue *func, TValue *top) - | ldr LFUNC:CARG3, [RA, FRAME_FUNC] // Guaranteed to be a function here. + | ldr TMP1, [RA, FRAME_FUNC] // Guaranteed to be a function here. | ldr PC, [BASE, FRAME_PC] | add NARGS8:RC, NARGS8:RC, #8 // Got one more argument now. - | and LFUNC:CARG3, CARG3, #LJ_GCVMASK + | and LFUNC:CARG3, TMP1, #LJ_GCVMASK | b ->BC_CALLT2_Z | |//-- Argument coercion for 'for' statement ------------------------------ @@ -1309,6 +1309,7 @@ static void build_subroutines(BuildCtx *ctx) | blo ->fff_fallback | cmp TISNUMhi, CARG1, lsr #32 | beq ->fff_restv + | blo ->fff_fallback | round d0, d0 | b ->fff_resn |.endmacro diff --git a/luajit-2.1/src/vm_mips.dasc b/luajit-2.1/src/vm_mips.dasc index 7cfdf4b..134ed56 100644 --- a/luajit-2.1/src/vm_mips.dasc +++ b/luajit-2.1/src/vm_mips.dasc @@ -2015,7 +2015,7 @@ static void build_subroutines(BuildCtx *ctx) |.if JIT | // RA = resultptr, RB = meta base | lw INS, -4(PC) - | lw TMP3, -24+LO(RB) // Save previous trace number. + | lw TMP2, -24+LO(RB) // Save previous trace. | decode_RA8a RC, INS | addiu AT, MULTRES, -8 | decode_RA8b RC @@ -2034,17 +2034,13 @@ static void build_subroutines(BuildCtx *ctx) | decode_RA8b RA | decode_RB8b RB | addu RA, RA, RB - | lw TMP1, DISPATCH_J(trace)(DISPATCH) | addu RA, BASE, RA |3: | sltu AT, RC, RA | bnez AT, >9 // More results wanted? - |. sll TMP2, TMP3, 2 + |. nop | - | addu TMP2, TMP1, TMP2 - | lw TRACE:TMP2, 0(TMP2) - | beqz TRACE:TMP2, ->cont_nop - |. nop + | lhu TMP3, TRACE:TMP2->traceno | lhu RD, TRACE:TMP2->link | beq RD, TMP3, ->cont_nop // Blacklisted. |. load_got lj_dispatch_stitch diff --git a/luajit-2.1/src/vm_ppc.dasc b/luajit-2.1/src/vm_ppc.dasc index 2a7a745..0d6915f 100644 --- a/luajit-2.1/src/vm_ppc.dasc +++ b/luajit-2.1/src/vm_ppc.dasc @@ -320,13 +320,6 @@ | |//----------------------------------------------------------------------- | -|// These basic macros should really be part of DynASM. -|.macro srwi, rx, ry, n; rlwinm rx, ry, 32-n, n, 31; .endmacro -|.macro slwi, rx, ry, n; rlwinm rx, ry, n, 0, 31-n; .endmacro -|.macro rotlwi, rx, ry, n; rlwinm rx, ry, n, 0, 31; .endmacro -|.macro rotlw, rx, ry, rn; rlwnm rx, ry, rn, 0, 31; .endmacro -|.macro subi, rx, ry, i; addi rx, ry, -i; .endmacro -| |// Trap for not-yet-implemented parts. |.macro NYI; tw 4, sp, sp; .endmacro | @@ -2532,7 +2525,7 @@ static void build_subroutines(BuildCtx *ctx) |.if JIT | // RA = resultptr, RB = meta base | lwz INS, -4(PC) - | lwz TMP3, -20(RB) // Save previous trace number. + | lwz TRACE:TMP2, -20(RB) // Save previous trace. | addic. TMP1, MULTRES, -8 | decode_RA8 RC, INS // Call base. | beq >2 @@ -2547,15 +2540,11 @@ static void build_subroutines(BuildCtx *ctx) | decode_RA8 RA, INS | decode_RB8 RB, INS | add RA, RA, RB - | lwz TMP1, DISPATCH_J(trace)(DISPATCH) |3: | cmplw RA, RC | bgt >9 // More results wanted? | - | slwi TMP2, TMP3, 2 - | lwzx TRACE:TMP2, TMP1, TMP2 - | cmpwi TRACE:TMP2, 0 - | beq ->cont_nop + | lhz TMP3, TRACE:TMP2->traceno | lhz RD, TRACE:TMP2->link | cmpw RD, TMP3 | cmpwi cr1, RD, 0 @@ -4289,13 +4278,13 @@ static void build_ins(BuildCtx *ctx, BCOp op, int defop) | lwz TAB:CARG2, 4(RB) |.if DUALNUM | add RC, BASE, RC - | lbz TMP3, TAB:RB->marked + | lbz TMP3, TAB:CARG2->marked | lwz TMP0, TAB:CARG2->asize | lwz CARG3, 4(RC) | lwz TMP1, TAB:CARG2->array |.else | lfdx f0, BASE, RC - | lbz TMP3, TAB:RB->marked + | lbz TMP3, TAB:CARG2->marked | lwz TMP0, TAB:CARG2->asize | toint CARG3, f0 | lwz TMP1, TAB:CARG2->array diff --git a/luajit-2.1/src/vm_x64.dasc b/luajit-2.1/src/vm_x64.dasc new file mode 100644 index 0000000..bba89aa --- /dev/null +++ b/luajit-2.1/src/vm_x64.dasc @@ -0,0 +1,4902 @@ +|// Low-level VM code for x64 CPUs in LJ_GC64 mode. +|// Bytecode interpreter, fast functions and helper functions. +|// Copyright (C) 2005-2015 Mike Pall. See Copyright Notice in luajit.h +| +|.arch x64 +|.section code_op, code_sub +| +|.actionlist build_actionlist +|.globals GLOB_ +|.globalnames globnames +|.externnames extnames +| +|//----------------------------------------------------------------------- +| +|.if WIN +|.define X64WIN, 1 // Windows/x64 calling conventions. +|.endif +| +|// Fixed register assignments for the interpreter. +|// This is very fragile and has many dependencies. Caveat emptor. +|.define BASE, rdx // Not C callee-save, refetched anyway. +|.if X64WIN +|.define KBASE, rdi // Must be C callee-save. +|.define PC, rsi // Must be C callee-save. +|.define DISPATCH, rbx // Must be C callee-save. +|.define KBASEd, edi +|.define PCd, esi +|.define DISPATCHd, ebx +|.else +|.define KBASE, r15 // Must be C callee-save. +|.define PC, rbx // Must be C callee-save. +|.define DISPATCH, r14 // Must be C callee-save. +|.define KBASEd, r15d +|.define PCd, ebx +|.define DISPATCHd, r14d +|.endif +| +|.define RA, rcx +|.define RAd, ecx +|.define RAH, ch +|.define RAL, cl +|.define RB, rbp // Must be rbp (C callee-save). +|.define RBd, ebp +|.define RC, rax // Must be rax. +|.define RCd, eax +|.define RCW, ax +|.define RCH, ah +|.define RCL, al +|.define OP, RBd +|.define RD, RC +|.define RDd, RCd +|.define RDW, RCW +|.define RDL, RCL +|.define TMPR, r10 +|.define TMPRd, r10d +|.define ITYPE, r11 +|.define ITYPEd, r11d +| +|.if X64WIN +|.define CARG1, rcx // x64/WIN64 C call arguments. +|.define CARG2, rdx +|.define CARG3, r8 +|.define CARG4, r9 +|.define CARG1d, ecx +|.define CARG2d, edx +|.define CARG3d, r8d +|.define CARG4d, r9d +|.else +|.define CARG1, rdi // x64/POSIX C call arguments. +|.define CARG2, rsi +|.define CARG3, rdx +|.define CARG4, rcx +|.define CARG5, r8 +|.define CARG6, r9 +|.define CARG1d, edi +|.define CARG2d, esi +|.define CARG3d, edx +|.define CARG4d, ecx +|.define CARG5d, r8d +|.define CARG6d, r9d +|.endif +| +|// Type definitions. Some of these are only used for documentation. +|.type L, lua_State +|.type GL, global_State +|.type TVALUE, TValue +|.type GCOBJ, GCobj +|.type STR, GCstr +|.type TAB, GCtab +|.type LFUNC, GCfuncL +|.type CFUNC, GCfuncC +|.type PROTO, GCproto +|.type UPVAL, GCupval +|.type NODE, Node +|.type NARGS, int +|.type TRACE, GCtrace +|.type SBUF, SBuf +| +|// Stack layout while in interpreter. Must match with lj_frame.h. +|//----------------------------------------------------------------------- +|.if X64WIN // x64/Windows stack layout +| +|.define CFRAME_SPACE, aword*5 // Delta for rsp (see <--). +|.macro saveregs_ +| push rdi; push rsi; push rbx +| sub rsp, CFRAME_SPACE +|.endmacro +|.macro saveregs +| push rbp; saveregs_ +|.endmacro +|.macro restoreregs +| add rsp, CFRAME_SPACE +| pop rbx; pop rsi; pop rdi; pop rbp +|.endmacro +| +|.define SAVE_CFRAME, aword [rsp+aword*13] +|.define SAVE_PC, aword [rsp+aword*12] +|.define SAVE_L, aword [rsp+aword*11] +|.define SAVE_ERRF, dword [rsp+dword*21] +|.define SAVE_NRES, dword [rsp+dword*20] +|//----- 16 byte aligned, ^^^ 32 byte register save area, owned by interpreter +|.define SAVE_RET, aword [rsp+aword*9] //<-- rsp entering interpreter. +|.define SAVE_R4, aword [rsp+aword*8] +|.define SAVE_R3, aword [rsp+aword*7] +|.define SAVE_R2, aword [rsp+aword*6] +|.define SAVE_R1, aword [rsp+aword*5] //<-- rsp after register saves. +|.define ARG5, aword [rsp+aword*4] +|.define CSAVE_4, aword [rsp+aword*3] +|.define CSAVE_3, aword [rsp+aword*2] +|.define CSAVE_2, aword [rsp+aword*1] +|.define CSAVE_1, aword [rsp] //<-- rsp while in interpreter. +|//----- 16 byte aligned, ^^^ 32 byte register save area, owned by callee +| +|.define ARG5d, dword [rsp+dword*8] +|.define TMP1, ARG5 // TMP1 overlaps ARG5 +|.define TMP1d, ARG5d +|.define TMP1hi, dword [rsp+dword*9] +|.define MULTRES, TMP1d // MULTRES overlaps TMP1d. +| +|//----------------------------------------------------------------------- +|.else // x64/POSIX stack layout +| +|.define CFRAME_SPACE, aword*5 // Delta for rsp (see <--). +|.macro saveregs_ +| push rbx; push r15; push r14 +|.if NO_UNWIND +| push r13; push r12 +|.endif +| sub rsp, CFRAME_SPACE +|.endmacro +|.macro saveregs +| push rbp; saveregs_ +|.endmacro +|.macro restoreregs +| add rsp, CFRAME_SPACE +|.if NO_UNWIND +| pop r12; pop r13 +|.endif +| pop r14; pop r15; pop rbx; pop rbp +|.endmacro +| +|//----- 16 byte aligned, +|.if NO_UNWIND +|.define SAVE_RET, aword [rsp+aword*11] //<-- rsp entering interpreter. +|.define SAVE_R4, aword [rsp+aword*10] +|.define SAVE_R3, aword [rsp+aword*9] +|.define SAVE_R2, aword [rsp+aword*8] +|.define SAVE_R1, aword [rsp+aword*7] +|.define SAVE_RU2, aword [rsp+aword*6] +|.define SAVE_RU1, aword [rsp+aword*5] //<-- rsp after register saves. +|.else +|.define SAVE_RET, aword [rsp+aword*9] //<-- rsp entering interpreter. +|.define SAVE_R4, aword [rsp+aword*8] +|.define SAVE_R3, aword [rsp+aword*7] +|.define SAVE_R2, aword [rsp+aword*6] +|.define SAVE_R1, aword [rsp+aword*5] //<-- rsp after register saves. +|.endif +|.define SAVE_CFRAME, aword [rsp+aword*4] +|.define SAVE_PC, aword [rsp+aword*3] +|.define SAVE_L, aword [rsp+aword*2] +|.define SAVE_ERRF, dword [rsp+dword*3] +|.define SAVE_NRES, dword [rsp+dword*2] +|.define TMP1, aword [rsp] //<-- rsp while in interpreter. +|//----- 16 byte aligned +| +|.define TMP1d, dword [rsp] +|.define TMP1hi, dword [rsp+dword*1] +|.define MULTRES, TMP1d // MULTRES overlaps TMP1d. +| +|.endif +| +|//----------------------------------------------------------------------- +| +|// Instruction headers. +|.macro ins_A; .endmacro +|.macro ins_AD; .endmacro +|.macro ins_AJ; .endmacro +|.macro ins_ABC; movzx RBd, RCH; movzx RCd, RCL; .endmacro +|.macro ins_AB_; movzx RBd, RCH; .endmacro +|.macro ins_A_C; movzx RCd, RCL; .endmacro +|.macro ins_AND; not RD; .endmacro +| +|// Instruction decode+dispatch. Carefully tuned (nope, lodsd is not faster). +|.macro ins_NEXT +| mov RCd, [PC] +| movzx RAd, RCH +| movzx OP, RCL +| add PC, 4 +| shr RCd, 16 +| jmp aword [DISPATCH+OP*8] +|.endmacro +| +|// Instruction footer. +|.if 1 +| // Replicated dispatch. Less unpredictable branches, but higher I-Cache use. +| .define ins_next, ins_NEXT +| .define ins_next_, ins_NEXT +|.else +| // Common dispatch. Lower I-Cache use, only one (very) unpredictable branch. +| // Affects only certain kinds of benchmarks (and only with -j off). +| // Around 10%-30% slower on Core2, a lot more slower on P4. +| .macro ins_next +| jmp ->ins_next +| .endmacro +| .macro ins_next_ +| ->ins_next: +| ins_NEXT +| .endmacro +|.endif +| +|// Call decode and dispatch. +|.macro ins_callt +| // BASE = new base, RB = LFUNC, RD = nargs+1, [BASE-8] = PC +| mov PC, LFUNC:RB->pc +| mov RAd, [PC] +| movzx OP, RAL +| movzx RAd, RAH +| add PC, 4 +| jmp aword [DISPATCH+OP*8] +|.endmacro +| +|.macro ins_call +| // BASE = new base, RB = LFUNC, RD = nargs+1 +| mov [BASE-8], PC +| ins_callt +|.endmacro +| +|//----------------------------------------------------------------------- +| +|// Macros to clear or set tags. +|.macro cleartp, reg; shl reg, 17; shr reg, 17; .endmacro +|.macro settp, reg, tp +| mov64 ITYPE, ((int64_t)tp<<47) +| or reg, ITYPE +|.endmacro +|.macro settp, dst, reg, tp +| mov64 dst, ((int64_t)tp<<47) +| or dst, reg +|.endmacro +|.macro setint, reg +| settp reg, LJ_TISNUM +|.endmacro +|.macro setint, dst, reg +| settp dst, reg, LJ_TISNUM +|.endmacro +| +|// Macros to test operand types. +|.macro checktp_nc, reg, tp, target +| mov ITYPE, reg +| sar ITYPE, 47 +| cmp ITYPEd, tp +| jne target +|.endmacro +|.macro checktp, reg, tp, target +| mov ITYPE, reg +| cleartp reg +| sar ITYPE, 47 +| cmp ITYPEd, tp +| jne target +|.endmacro +|.macro checktptp, src, tp, target +| mov ITYPE, src +| sar ITYPE, 47 +| cmp ITYPEd, tp +| jne target +|.endmacro +|.macro checkstr, reg, target; checktp reg, LJ_TSTR, target; .endmacro +|.macro checktab, reg, target; checktp reg, LJ_TTAB, target; .endmacro +|.macro checkfunc, reg, target; checktp reg, LJ_TFUNC, target; .endmacro +| +|.macro checknumx, reg, target, jump +| mov ITYPE, reg +| sar ITYPE, 47 +| cmp ITYPEd, LJ_TISNUM +| jump target +|.endmacro +|.macro checkint, reg, target; checknumx reg, target, jne; .endmacro +|.macro checkinttp, src, target; checknumx src, target, jne; .endmacro +|.macro checknum, reg, target; checknumx reg, target, jae; .endmacro +|.macro checknumtp, src, target; checknumx src, target, jae; .endmacro +|.macro checknumber, src, target; checknumx src, target, ja; .endmacro +| +|.macro mov_false, reg; mov64 reg, (int64_t)~((uint64_t)1<<47); .endmacro +|.macro mov_true, reg; mov64 reg, (int64_t)~((uint64_t)2<<47); .endmacro +| +|// These operands must be used with movzx. +|.define PC_OP, byte [PC-4] +|.define PC_RA, byte [PC-3] +|.define PC_RB, byte [PC-1] +|.define PC_RC, byte [PC-2] +|.define PC_RD, word [PC-2] +| +|.macro branchPC, reg +| lea PC, [PC+reg*4-BCBIAS_J*4] +|.endmacro +| +|// Assumes DISPATCH is relative to GL. +#define DISPATCH_GL(field) (GG_DISP2G + (int)offsetof(global_State, field)) +#define DISPATCH_J(field) (GG_DISP2J + (int)offsetof(jit_State, field)) +| +#define PC2PROTO(field) ((int)offsetof(GCproto, field)-(int)sizeof(GCproto)) +| +|// Decrement hashed hotcount and trigger trace recorder if zero. +|.macro hotloop, reg +| mov reg, PCd +| shr reg, 1 +| and reg, HOTCOUNT_PCMASK +| sub word [DISPATCH+reg+GG_DISP2HOT], HOTCOUNT_LOOP +| jb ->vm_hotloop +|.endmacro +| +|.macro hotcall, reg +| mov reg, PCd +| shr reg, 1 +| and reg, HOTCOUNT_PCMASK +| sub word [DISPATCH+reg+GG_DISP2HOT], HOTCOUNT_CALL +| jb ->vm_hotcall +|.endmacro +| +|// Set current VM state. +|.macro set_vmstate, st +| mov dword [DISPATCH+DISPATCH_GL(vmstate)], ~LJ_VMST_..st +|.endmacro +| +|.macro fpop1; fstp st1; .endmacro +| +|// Synthesize SSE FP constants. +|.macro sseconst_abs, reg, tmp // Synthesize abs mask. +| mov64 tmp, U64x(7fffffff,ffffffff); movd reg, tmp +|.endmacro +| +|.macro sseconst_hi, reg, tmp, val // Synthesize hi-32 bit const. +| mov64 tmp, U64x(val,00000000); movd reg, tmp +|.endmacro +| +|.macro sseconst_sign, reg, tmp // Synthesize sign mask. +| sseconst_hi reg, tmp, 80000000 +|.endmacro +|.macro sseconst_1, reg, tmp // Synthesize 1.0. +| sseconst_hi reg, tmp, 3ff00000 +|.endmacro +|.macro sseconst_m1, reg, tmp // Synthesize -1.0. +| sseconst_hi reg, tmp, bff00000 +|.endmacro +|.macro sseconst_2p52, reg, tmp // Synthesize 2^52. +| sseconst_hi reg, tmp, 43300000 +|.endmacro +|.macro sseconst_tobit, reg, tmp // Synthesize 2^52 + 2^51. +| sseconst_hi reg, tmp, 43380000 +|.endmacro +| +|// Move table write barrier back. Overwrites reg. +|.macro barrierback, tab, reg +| and byte tab->marked, (uint8_t)~LJ_GC_BLACK // black2gray(tab) +| mov reg, [DISPATCH+DISPATCH_GL(gc.grayagain)] +| mov [DISPATCH+DISPATCH_GL(gc.grayagain)], tab +| mov tab->gclist, reg +|.endmacro +| +|//----------------------------------------------------------------------- + +/* Generate subroutines used by opcodes and other parts of the VM. */ +/* The .code_sub section should be last to help static branch prediction. */ +static void build_subroutines(BuildCtx *ctx) +{ + |.code_sub + | + |//----------------------------------------------------------------------- + |//-- Return handling ---------------------------------------------------- + |//----------------------------------------------------------------------- + | + |->vm_returnp: + | test PCd, FRAME_P + | jz ->cont_dispatch + | + | // Return from pcall or xpcall fast func. + | and PC, -8 + | sub BASE, PC // Restore caller base. + | lea RA, [RA+PC-8] // Rebase RA and prepend one result. + | mov PC, [BASE-8] // Fetch PC of previous frame. + | // Prepending may overwrite the pcall frame, so do it at the end. + | mov_true ITYPE + | mov aword [BASE+RA], ITYPE // Prepend true to results. + | + |->vm_returnc: + | add RDd, 1 // RD = nresults+1 + | jz ->vm_unwind_yield + | mov MULTRES, RDd + | test PC, FRAME_TYPE + | jz ->BC_RET_Z // Handle regular return to Lua. + | + |->vm_return: + | // BASE = base, RA = resultofs, RD = nresults+1 (= MULTRES), PC = return + | xor PC, FRAME_C + | test PCd, FRAME_TYPE + | jnz ->vm_returnp + | + | // Return to C. + | set_vmstate C + | and PC, -8 + | sub PC, BASE + | neg PC // Previous base = BASE - delta. + | + | sub RDd, 1 + | jz >2 + |1: // Move results down. + | mov RB, [BASE+RA] + | mov [BASE-16], RB + | add BASE, 8 + | sub RDd, 1 + | jnz <1 + |2: + | mov L:RB, SAVE_L + | mov L:RB->base, PC + |3: + | mov RDd, MULTRES + | mov RAd, SAVE_NRES // RA = wanted nresults+1 + |4: + | cmp RAd, RDd + | jne >6 // More/less results wanted? + |5: + | sub BASE, 16 + | mov L:RB->top, BASE + | + |->vm_leave_cp: + | mov RA, SAVE_CFRAME // Restore previous C frame. + | mov L:RB->cframe, RA + | xor eax, eax // Ok return status for vm_pcall. + | + |->vm_leave_unw: + | restoreregs + | ret + | + |6: + | jb >7 // Less results wanted? + | // More results wanted. Check stack size and fill up results with nil. + | cmp BASE, L:RB->maxstack + | ja >8 + | mov aword [BASE-16], LJ_TNIL + | add BASE, 8 + | add RDd, 1 + | jmp <4 + | + |7: // Less results wanted. + | test RAd, RAd + | jz <5 // But check for LUA_MULTRET+1. + | sub RA, RD // Negative result! + | lea BASE, [BASE+RA*8] // Correct top. + | jmp <5 + | + |8: // Corner case: need to grow stack for filling up results. + | // This can happen if: + | // - A C function grows the stack (a lot). + | // - The GC shrinks the stack in between. + | // - A return back from a lua_call() with (high) nresults adjustment. + | mov L:RB->top, BASE // Save current top held in BASE (yes). + | mov MULTRES, RDd // Need to fill only remainder with nil. + | mov CARG2d, RAd + | mov CARG1, L:RB + | call extern lj_state_growstack // (lua_State *L, int n) + | mov BASE, L:RB->top // Need the (realloced) L->top in BASE. + | jmp <3 + | + |->vm_unwind_yield: + | mov al, LUA_YIELD + | jmp ->vm_unwind_c_eh + | + |->vm_unwind_c: // Unwind C stack, return from vm_pcall. + | // (void *cframe, int errcode) + | mov eax, CARG2d // Error return status for vm_pcall. + | mov rsp, CARG1 + |->vm_unwind_c_eh: // Landing pad for external unwinder. + | mov L:RB, SAVE_L + | mov GL:RB, L:RB->glref + | mov dword GL:RB->vmstate, ~LJ_VMST_C + | jmp ->vm_leave_unw + | + |->vm_unwind_rethrow: + |.if not X64WIN + | mov CARG1, SAVE_L + | mov CARG2d, eax + | restoreregs + | jmp extern lj_err_throw // (lua_State *L, int errcode) + |.endif + | + |->vm_unwind_ff: // Unwind C stack, return from ff pcall. + | // (void *cframe) + | and CARG1, CFRAME_RAWMASK + | mov rsp, CARG1 + |->vm_unwind_ff_eh: // Landing pad for external unwinder. + | mov L:RB, SAVE_L + | mov RDd, 1+1 // Really 1+2 results, incr. later. + | mov BASE, L:RB->base + | mov DISPATCH, L:RB->glref // Setup pointer to dispatch table. + | add DISPATCH, GG_G2DISP + | mov PC, [BASE-8] // Fetch PC of previous frame. + | mov_false RA + | mov RB, [BASE] + | mov [BASE-16], RA // Prepend false to error message. + | mov [BASE-8], RB + | mov RA, -16 // Results start at BASE+RA = BASE-16. + | set_vmstate INTERP + | jmp ->vm_returnc // Increments RD/MULTRES and returns. + | + |//----------------------------------------------------------------------- + |//-- Grow stack for calls ----------------------------------------------- + |//----------------------------------------------------------------------- + | + |->vm_growstack_c: // Grow stack for C function. + | mov CARG2d, LUA_MINSTACK + | jmp >2 + | + |->vm_growstack_v: // Grow stack for vararg Lua function. + | sub RD, 16 // LJ_FR2 + | jmp >1 + | + |->vm_growstack_f: // Grow stack for fixarg Lua function. + | // BASE = new base, RD = nargs+1, RB = L, PC = first PC + | lea RD, [BASE+NARGS:RD*8-8] + |1: + | movzx RAd, byte [PC-4+PC2PROTO(framesize)] + | add PC, 4 // Must point after first instruction. + | mov L:RB->base, BASE + | mov L:RB->top, RD + | mov SAVE_PC, PC + | mov CARG2, RA + |2: + | // RB = L, L->base = new base, L->top = top + | mov CARG1, L:RB + | call extern lj_state_growstack // (lua_State *L, int n) + | mov BASE, L:RB->base + | mov RD, L:RB->top + | mov LFUNC:RB, [BASE-16] + | cleartp LFUNC:RB + | sub RD, BASE + | shr RDd, 3 + | add NARGS:RDd, 1 + | // BASE = new base, RB = LFUNC, RD = nargs+1 + | ins_callt // Just retry the call. + | + |//----------------------------------------------------------------------- + |//-- Entry points into the assembler VM --------------------------------- + |//----------------------------------------------------------------------- + | + |->vm_resume: // Setup C frame and resume thread. + | // (lua_State *L, TValue *base, int nres1 = 0, ptrdiff_t ef = 0) + | saveregs + | mov L:RB, CARG1 // Caveat: CARG1 may be RA. + | mov SAVE_L, CARG1 + | mov RA, CARG2 + | mov PCd, FRAME_CP + | xor RDd, RDd + | lea KBASE, [esp+CFRAME_RESUME] + | mov DISPATCH, L:RB->glref // Setup pointer to dispatch table. + | add DISPATCH, GG_G2DISP + | mov SAVE_PC, RD // Any value outside of bytecode is ok. + | mov SAVE_CFRAME, RD + | mov SAVE_NRES, RDd + | mov SAVE_ERRF, RDd + | mov L:RB->cframe, KBASE + | cmp byte L:RB->status, RDL + | je >2 // Initial resume (like a call). + | + | // Resume after yield (like a return). + | mov [DISPATCH+DISPATCH_GL(cur_L)], L:RB + | set_vmstate INTERP + | mov byte L:RB->status, RDL + | mov BASE, L:RB->base + | mov RD, L:RB->top + | sub RD, RA + | shr RDd, 3 + | add RDd, 1 // RD = nresults+1 + | sub RA, BASE // RA = resultofs + | mov PC, [BASE-8] + | mov MULTRES, RDd + | test PCd, FRAME_TYPE + | jz ->BC_RET_Z + | jmp ->vm_return + | + |->vm_pcall: // Setup protected C frame and enter VM. + | // (lua_State *L, TValue *base, int nres1, ptrdiff_t ef) + | saveregs + | mov PCd, FRAME_CP + | mov SAVE_ERRF, CARG4d + | jmp >1 + | + |->vm_call: // Setup C frame and enter VM. + | // (lua_State *L, TValue *base, int nres1) + | saveregs + | mov PCd, FRAME_C + | + |1: // Entry point for vm_pcall above (PC = ftype). + | mov SAVE_NRES, CARG3d + | mov L:RB, CARG1 // Caveat: CARG1 may be RA. + | mov SAVE_L, CARG1 + | mov RA, CARG2 + | + | mov DISPATCH, L:RB->glref // Setup pointer to dispatch table. + | mov KBASE, L:RB->cframe // Add our C frame to cframe chain. + | mov SAVE_CFRAME, KBASE + | mov SAVE_PC, L:RB // Any value outside of bytecode is ok. + | add DISPATCH, GG_G2DISP + | mov L:RB->cframe, rsp + | + |2: // Entry point for vm_resume/vm_cpcall (RA = base, RB = L, PC = ftype). + | mov [DISPATCH+DISPATCH_GL(cur_L)], L:RB + | set_vmstate INTERP + | mov BASE, L:RB->base // BASE = old base (used in vmeta_call). + | add PC, RA + | sub PC, BASE // PC = frame delta + frame type + | + | mov RD, L:RB->top + | sub RD, RA + | shr NARGS:RDd, 3 + | add NARGS:RDd, 1 // RD = nargs+1 + | + |->vm_call_dispatch: + | mov LFUNC:RB, [RA-16] + | checkfunc LFUNC:RB, ->vmeta_call // Ensure KBASE defined and != BASE. + | + |->vm_call_dispatch_f: + | mov BASE, RA + | ins_call + | // BASE = new base, RB = func, RD = nargs+1, PC = caller PC + | + |->vm_cpcall: // Setup protected C frame, call C. + | // (lua_State *L, lua_CFunction func, void *ud, lua_CPFunction cp) + | saveregs + | mov L:RB, CARG1 // Caveat: CARG1 may be RA. + | mov SAVE_L, CARG1 + | mov SAVE_PC, L:RB // Any value outside of bytecode is ok. + | + | mov KBASE, L:RB->stack // Compute -savestack(L, L->top). + | sub KBASE, L:RB->top + | mov DISPATCH, L:RB->glref // Setup pointer to dispatch table. + | mov SAVE_ERRF, 0 // No error function. + | mov SAVE_NRES, KBASEd // Neg. delta means cframe w/o frame. + | add DISPATCH, GG_G2DISP + | // Handler may change cframe_nres(L->cframe) or cframe_errfunc(L->cframe). + | + | mov KBASE, L:RB->cframe // Add our C frame to cframe chain. + | mov SAVE_CFRAME, KBASE + | mov L:RB->cframe, rsp + | mov [DISPATCH+DISPATCH_GL(cur_L)], L:RB + | + | call CARG4 // (lua_State *L, lua_CFunction func, void *ud) + | // TValue * (new base) or NULL returned in eax (RC). + | test RC, RC + | jz ->vm_leave_cp // No base? Just remove C frame. + | mov RA, RC + | mov PCd, FRAME_CP + | jmp <2 // Else continue with the call. + | + |//----------------------------------------------------------------------- + |//-- Metamethod handling ------------------------------------------------ + |//----------------------------------------------------------------------- + | + |//-- Continuation dispatch ---------------------------------------------- + | + |->cont_dispatch: + | // BASE = meta base, RA = resultofs, RD = nresults+1 (also in MULTRES) + | add RA, BASE + | and PC, -8 + | mov RB, BASE + | sub BASE, PC // Restore caller BASE. + | mov aword [RA+RD*8-8], LJ_TNIL // Ensure one valid arg. + | mov RC, RA // ... in [RC] + | mov PC, [RB-24] // Restore PC from [cont|PC]. + | mov RA, qword [RB-32] // May be negative on WIN64 with debug. + |.if FFI + | cmp RA, 1 + | jbe >1 + |.endif + | mov LFUNC:KBASE, [BASE-16] + | cleartp LFUNC:KBASE + | mov KBASE, LFUNC:KBASE->pc + | mov KBASE, [KBASE+PC2PROTO(k)] + | // BASE = base, RC = result, RB = meta base + | jmp RA // Jump to continuation. + | + |.if FFI + |1: + | je ->cont_ffi_callback // cont = 1: return from FFI callback. + | // cont = 0: Tail call from C function. + | sub RB, BASE + | shr RBd, 3 + | lea RDd, [RBd-3] + | jmp ->vm_call_tail + |.endif + | + |->cont_cat: // BASE = base, RC = result, RB = mbase + | movzx RAd, PC_RB + | sub RB, 32 + | lea RA, [BASE+RA*8] + | sub RA, RB + | je ->cont_ra + | neg RA + | shr RAd, 3 + |.if X64WIN + | mov CARG3d, RAd + | mov L:CARG1, SAVE_L + | mov L:CARG1->base, BASE + | mov RC, [RC] + | mov [RB], RC + | mov CARG2, RB + |.else + | mov L:CARG1, SAVE_L + | mov L:CARG1->base, BASE + | mov CARG3d, RAd + | mov RA, [RC] + | mov [RB], RA + | mov CARG2, RB + |.endif + | jmp ->BC_CAT_Z + | + |//-- Table indexing metamethods ----------------------------------------- + | + |->vmeta_tgets: + | settp STR:RC, LJ_TSTR // STR:RC = GCstr * + | mov TMP1, STR:RC + | lea RC, TMP1 + | cmp PC_OP, BC_GGET + | jne >1 + | settp TAB:RA, TAB:RB, LJ_TTAB // TAB:RB = GCtab * + | lea RB, [DISPATCH+DISPATCH_GL(tmptv)] // Store fn->l.env in g->tmptv. + | mov [RB], TAB:RA + | jmp >2 + | + |->vmeta_tgetb: + | movzx RCd, PC_RC + |.if DUALNUM + | setint RC + | mov TMP1, RC + |.else + | cvtsi2sd xmm0, RCd + | movsd TMP1, xmm0 + |.endif + | lea RC, TMP1 + | jmp >1 + | + |->vmeta_tgetv: + | movzx RCd, PC_RC // Reload TValue *k from RC. + | lea RC, [BASE+RC*8] + |1: + | movzx RBd, PC_RB // Reload TValue *t from RB. + | lea RB, [BASE+RB*8] + |2: + | mov L:CARG1, SAVE_L + | mov L:CARG1->base, BASE // Caveat: CARG2/CARG3 may be BASE. + | mov CARG2, RB + | mov CARG3, RC + | mov L:RB, L:CARG1 + | mov SAVE_PC, PC + | call extern lj_meta_tget // (lua_State *L, TValue *o, TValue *k) + | // TValue * (finished) or NULL (metamethod) returned in eax (RC). + | mov BASE, L:RB->base + | test RC, RC + | jz >3 + |->cont_ra: // BASE = base, RC = result + | movzx RAd, PC_RA + | mov RB, [RC] + | mov [BASE+RA*8], RB + | ins_next + | + |3: // Call __index metamethod. + | // BASE = base, L->top = new base, stack = cont/func/t/k + | mov RA, L:RB->top + | mov [RA-24], PC // [cont|PC] + | lea PC, [RA+FRAME_CONT] + | sub PC, BASE + | mov LFUNC:RB, [RA-16] // Guaranteed to be a function here. + | mov NARGS:RDd, 2+1 // 2 args for func(t, k). + | cleartp LFUNC:RB + | jmp ->vm_call_dispatch_f + | + |->vmeta_tgetr: + | mov CARG1, TAB:RB + | mov RB, BASE // Save BASE. + | mov CARG2d, RCd // Caveat: CARG2 == BASE + | call extern lj_tab_getinth // (GCtab *t, int32_t key) + | // cTValue * or NULL returned in eax (RC). + | movzx RAd, PC_RA + | mov BASE, RB // Restore BASE. + | test RC, RC + | jnz ->BC_TGETR_Z + | mov ITYPE, LJ_TNIL + | jmp ->BC_TGETR2_Z + | + |//----------------------------------------------------------------------- + | + |->vmeta_tsets: + | settp STR:RC, LJ_TSTR // STR:RC = GCstr * + | mov TMP1, STR:RC + | lea RC, TMP1 + | cmp PC_OP, BC_GSET + | jne >1 + | settp TAB:RA, TAB:RB, LJ_TTAB // TAB:RB = GCtab * + | lea RB, [DISPATCH+DISPATCH_GL(tmptv)] // Store fn->l.env in g->tmptv. + | mov [RB], TAB:RA + | jmp >2 + | + |->vmeta_tsetb: + | movzx RCd, PC_RC + |.if DUALNUM + | setint RC + | mov TMP1, RC + |.else + | cvtsi2sd xmm0, RCd + | movsd TMP1, xmm0 + |.endif + | lea RC, TMP1 + | jmp >1 + | + |->vmeta_tsetv: + | movzx RCd, PC_RC // Reload TValue *k from RC. + | lea RC, [BASE+RC*8] + |1: + | movzx RBd, PC_RB // Reload TValue *t from RB. + | lea RB, [BASE+RB*8] + |2: + | mov L:CARG1, SAVE_L + | mov L:CARG1->base, BASE // Caveat: CARG2/CARG3 may be BASE. + | mov CARG2, RB + | mov CARG3, RC + | mov L:RB, L:CARG1 + | mov SAVE_PC, PC + | call extern lj_meta_tset // (lua_State *L, TValue *o, TValue *k) + | // TValue * (finished) or NULL (metamethod) returned in eax (RC). + | mov BASE, L:RB->base + | test RC, RC + | jz >3 + | // NOBARRIER: lj_meta_tset ensures the table is not black. + | movzx RAd, PC_RA + | mov RB, [BASE+RA*8] + | mov [RC], RB + |->cont_nop: // BASE = base, (RC = result) + | ins_next + | + |3: // Call __newindex metamethod. + | // BASE = base, L->top = new base, stack = cont/func/t/k/(v) + | mov RA, L:RB->top + | mov [RA-24], PC // [cont|PC] + | movzx RCd, PC_RA + | // Copy value to third argument. + | mov RB, [BASE+RC*8] + | mov [RA+16], RB + | lea PC, [RA+FRAME_CONT] + | sub PC, BASE + | mov LFUNC:RB, [RA-16] // Guaranteed to be a function here. + | mov NARGS:RDd, 3+1 // 3 args for func(t, k, v). + | cleartp LFUNC:RB + | jmp ->vm_call_dispatch_f + | + |->vmeta_tsetr: + |.if X64WIN + | mov L:CARG1, SAVE_L + | mov CARG3d, RCd + | mov L:CARG1->base, BASE + | xchg CARG2, TAB:RB // Caveat: CARG2 == BASE. + |.else + | mov L:CARG1, SAVE_L + | mov CARG2, TAB:RB + | mov L:CARG1->base, BASE + | mov RB, BASE // Save BASE. + | mov CARG3d, RCd // Caveat: CARG3 == BASE. + |.endif + | mov SAVE_PC, PC + | call extern lj_tab_setinth // (lua_State *L, GCtab *t, int32_t key) + | // TValue * returned in eax (RC). + | movzx RAd, PC_RA + | mov BASE, RB // Restore BASE. + | jmp ->BC_TSETR_Z + | + |//-- Comparison metamethods --------------------------------------------- + | + |->vmeta_comp: + | movzx RDd, PC_RD + | movzx RAd, PC_RA + | mov L:RB, SAVE_L + | mov L:RB->base, BASE // Caveat: CARG2/CARG3 == BASE. + |.if X64WIN + | lea CARG3, [BASE+RD*8] + | lea CARG2, [BASE+RA*8] + |.else + | lea CARG2, [BASE+RA*8] + | lea CARG3, [BASE+RD*8] + |.endif + | mov CARG1, L:RB // Caveat: CARG1/CARG4 == RA. + | movzx CARG4d, PC_OP + | mov SAVE_PC, PC + | call extern lj_meta_comp // (lua_State *L, TValue *o1, *o2, int op) + | // 0/1 or TValue * (metamethod) returned in eax (RC). + |3: + | mov BASE, L:RB->base + | cmp RC, 1 + | ja ->vmeta_binop + |4: + | lea PC, [PC+4] + | jb >6 + |5: + | movzx RDd, PC_RD + | branchPC RD + |6: + | ins_next + | + |->cont_condt: // BASE = base, RC = result + | add PC, 4 + | mov ITYPE, [RC] + | sar ITYPE, 47 + | cmp ITYPEd, LJ_TISTRUECOND // Branch if result is true. + | jb <5 + | jmp <6 + | + |->cont_condf: // BASE = base, RC = result + | mov ITYPE, [RC] + | sar ITYPE, 47 + | cmp ITYPEd, LJ_TISTRUECOND // Branch if result is false. + | jmp <4 + | + |->vmeta_equal: + | cleartp TAB:RD + | sub PC, 4 + |.if X64WIN + | mov CARG3, RD + | mov CARG4d, RBd + | mov L:RB, SAVE_L + | mov L:RB->base, BASE // Caveat: CARG2 == BASE. + | mov CARG2, RA + | mov CARG1, L:RB // Caveat: CARG1 == RA. + |.else + | mov CARG2, RA + | mov CARG4d, RBd // Caveat: CARG4 == RA. + | mov L:RB, SAVE_L + | mov L:RB->base, BASE // Caveat: CARG3 == BASE. + | mov CARG3, RD + | mov CARG1, L:RB + |.endif + | mov SAVE_PC, PC + | call extern lj_meta_equal // (lua_State *L, GCobj *o1, *o2, int ne) + | // 0/1 or TValue * (metamethod) returned in eax (RC). + | jmp <3 + | + |->vmeta_equal_cd: + |.if FFI + | sub PC, 4 + | mov L:RB, SAVE_L + | mov L:RB->base, BASE + | mov CARG1, L:RB + | mov CARG2d, dword [PC-4] + | mov SAVE_PC, PC + | call extern lj_meta_equal_cd // (lua_State *L, BCIns ins) + | // 0/1 or TValue * (metamethod) returned in eax (RC). + | jmp <3 + |.endif + | + |->vmeta_istype: + | mov L:RB, SAVE_L + | mov L:RB->base, BASE // Caveat: CARG2/CARG3 may be BASE. + | mov CARG2d, RAd + | mov CARG3d, RDd + | mov L:CARG1, L:RB + | mov SAVE_PC, PC + | call extern lj_meta_istype // (lua_State *L, BCReg ra, BCReg tp) + | mov BASE, L:RB->base + | jmp <6 + | + |//-- Arithmetic metamethods --------------------------------------------- + | + |->vmeta_arith_vno: + |.if DUALNUM + | movzx RBd, PC_RB + | movzx RCd, PC_RC + |.endif + |->vmeta_arith_vn: + | lea RC, [KBASE+RC*8] + | jmp >1 + | + |->vmeta_arith_nvo: + |.if DUALNUM + | movzx RBd, PC_RB + | movzx RCd, PC_RC + |.endif + |->vmeta_arith_nv: + | lea TMPR, [KBASE+RC*8] + | lea RC, [BASE+RB*8] + | mov RB, TMPR + | jmp >2 + | + |->vmeta_unm: + | lea RC, [BASE+RD*8] + | mov RB, RC + | jmp >2 + | + |->vmeta_arith_vvo: + |.if DUALNUM + | movzx RBd, PC_RB + | movzx RCd, PC_RC + |.endif + |->vmeta_arith_vv: + | lea RC, [BASE+RC*8] + |1: + | lea RB, [BASE+RB*8] + |2: + | lea RA, [BASE+RA*8] + |.if X64WIN + | mov CARG3, RB + | mov CARG4, RC + | movzx RCd, PC_OP + | mov ARG5d, RCd + | mov L:RB, SAVE_L + | mov L:RB->base, BASE // Caveat: CARG2 == BASE. + | mov CARG2, RA + | mov CARG1, L:RB // Caveat: CARG1 == RA. + |.else + | movzx CARG5d, PC_OP + | mov CARG2, RA + | mov CARG4, RC // Caveat: CARG4 == RA. + | mov L:CARG1, SAVE_L + | mov L:CARG1->base, BASE // Caveat: CARG3 == BASE. + | mov CARG3, RB + | mov L:RB, L:CARG1 + |.endif + | mov SAVE_PC, PC + | call extern lj_meta_arith // (lua_State *L, TValue *ra,*rb,*rc, BCReg op) + | // NULL (finished) or TValue * (metamethod) returned in eax (RC). + | mov BASE, L:RB->base + | test RC, RC + | jz ->cont_nop + | + | // Call metamethod for binary op. + |->vmeta_binop: + | // BASE = base, RC = new base, stack = cont/func/o1/o2 + | mov RA, RC + | sub RC, BASE + | mov [RA-24], PC // [cont|PC] + | lea PC, [RC+FRAME_CONT] + | mov NARGS:RDd, 2+1 // 2 args for func(o1, o2). + | jmp ->vm_call_dispatch + | + |->vmeta_len: + | movzx RDd, PC_RD + | mov L:RB, SAVE_L + | mov L:RB->base, BASE + | lea CARG2, [BASE+RD*8] // Caveat: CARG2 == BASE + | mov L:CARG1, L:RB + | mov SAVE_PC, PC + | call extern lj_meta_len // (lua_State *L, TValue *o) + | // NULL (retry) or TValue * (metamethod) returned in eax (RC). + | mov BASE, L:RB->base +#if LJ_52 + | test RC, RC + | jne ->vmeta_binop // Binop call for compatibility. + | movzx RDd, PC_RD + | mov TAB:CARG1, [BASE+RD*8] + | cleartp TAB:CARG1 + | jmp ->BC_LEN_Z +#else + | jmp ->vmeta_binop // Binop call for compatibility. +#endif + | + |//-- Call metamethod ---------------------------------------------------- + | + |->vmeta_call_ra: + | lea RA, [BASE+RA*8+16] + |->vmeta_call: // Resolve and call __call metamethod. + | // BASE = old base, RA = new base, RC = nargs+1, PC = return + | mov TMP1d, NARGS:RDd // Save RA, RC for us. + | mov RB, RA + |.if X64WIN + | mov L:TMPR, SAVE_L + | mov L:TMPR->base, BASE // Caveat: CARG2 is BASE. + | lea CARG2, [RA-16] + | lea CARG3, [RA+NARGS:RD*8-8] + | mov CARG1, L:TMPR // Caveat: CARG1 is RA. + |.else + | mov L:CARG1, SAVE_L + | mov L:CARG1->base, BASE // Caveat: CARG3 is BASE. + | lea CARG2, [RA-16] + | lea CARG3, [RA+NARGS:RD*8-8] + |.endif + | mov SAVE_PC, PC + | call extern lj_meta_call // (lua_State *L, TValue *func, TValue *top) + | mov RA, RB + | mov L:RB, SAVE_L + | mov BASE, L:RB->base + | mov NARGS:RDd, TMP1d + | mov LFUNC:RB, [RA-16] + | cleartp LFUNC:RB + | add NARGS:RDd, 1 + | // This is fragile. L->base must not move, KBASE must always be defined. + | cmp KBASE, BASE // Continue with CALLT if flag set. + | je ->BC_CALLT_Z + | mov BASE, RA + | ins_call // Otherwise call resolved metamethod. + | + |//-- Argument coercion for 'for' statement ------------------------------ + | + |->vmeta_for: + | mov L:RB, SAVE_L + | mov L:RB->base, BASE + | mov CARG2, RA // Caveat: CARG2 == BASE + | mov L:CARG1, L:RB // Caveat: CARG1 == RA + | mov SAVE_PC, PC + | call extern lj_meta_for // (lua_State *L, TValue *base) + | mov BASE, L:RB->base + | mov RCd, [PC-4] + | movzx RAd, RCH + | movzx OP, RCL + | shr RCd, 16 + | jmp aword [DISPATCH+OP*8+GG_DISP2STATIC] // Retry FORI or JFORI. + | + |//----------------------------------------------------------------------- + |//-- Fast functions ----------------------------------------------------- + |//----------------------------------------------------------------------- + | + |.macro .ffunc, name + |->ff_ .. name: + |.endmacro + | + |.macro .ffunc_1, name + |->ff_ .. name: + | cmp NARGS:RDd, 1+1; jb ->fff_fallback + |.endmacro + | + |.macro .ffunc_2, name + |->ff_ .. name: + | cmp NARGS:RDd, 2+1; jb ->fff_fallback + |.endmacro + | + |.macro .ffunc_n, name, op + | .ffunc_1 name + | checknumtp [BASE], ->fff_fallback + | op xmm0, qword [BASE] + |.endmacro + | + |.macro .ffunc_n, name + | .ffunc_n name, movsd + |.endmacro + | + |.macro .ffunc_nn, name + | .ffunc_2 name + | checknumtp [BASE], ->fff_fallback + | checknumtp [BASE+8], ->fff_fallback + | movsd xmm0, qword [BASE] + | movsd xmm1, qword [BASE+8] + |.endmacro + | + |// Inlined GC threshold check. Caveat: uses label 1. + |.macro ffgccheck + | mov RB, [DISPATCH+DISPATCH_GL(gc.total)] + | cmp RB, [DISPATCH+DISPATCH_GL(gc.threshold)] + | jb >1 + | call ->fff_gcstep + |1: + |.endmacro + | + |//-- Base library: checks ----------------------------------------------- + | + |.ffunc_1 assert + | mov ITYPE, [BASE] + | mov RB, ITYPE + | sar ITYPE, 47 + | cmp ITYPEd, LJ_TISTRUECOND; jae ->fff_fallback + | mov PC, [BASE-8] + | mov MULTRES, RDd + | mov RB, [BASE] + | mov [BASE-16], RB + | sub RDd, 2 + | jz >2 + | mov RA, BASE + |1: + | add RA, 8 + | mov RB, [RA] + | mov [RA-16], RB + | sub RDd, 1 + | jnz <1 + |2: + | mov RDd, MULTRES + | jmp ->fff_res_ + | + |.ffunc_1 type + | mov RC, [BASE] + | sar RC, 47 + | mov RBd, LJ_TISNUM + | cmp RCd, RBd + | cmovb RCd, RBd + | not RCd + |2: + | mov CFUNC:RB, [BASE-16] + | cleartp CFUNC:RB + | mov STR:RC, [CFUNC:RB+RC*8+((char *)(&((GCfuncC *)0)->upvalue))] + | mov PC, [BASE-8] + | settp STR:RC, LJ_TSTR + | mov [BASE-16], STR:RC + | jmp ->fff_res1 + | + |//-- Base library: getters and setters --------------------------------- + | + |.ffunc_1 getmetatable + | mov TAB:RB, [BASE] + | mov PC, [BASE-8] + | checktab TAB:RB, >6 + |1: // Field metatable must be at same offset for GCtab and GCudata! + | mov TAB:RB, TAB:RB->metatable + |2: + | test TAB:RB, TAB:RB + | mov aword [BASE-16], LJ_TNIL + | jz ->fff_res1 + | settp TAB:RC, TAB:RB, LJ_TTAB + | mov [BASE-16], TAB:RC // Store metatable as default result. + | mov STR:RC, [DISPATCH+DISPATCH_GL(gcroot)+8*(GCROOT_MMNAME+MM_metatable)] + | mov RAd, TAB:RB->hmask + | and RAd, STR:RC->hash + | settp STR:RC, LJ_TSTR + | imul RAd, #NODE + | add NODE:RA, TAB:RB->node + |3: // Rearranged logic, because we expect _not_ to find the key. + | cmp NODE:RA->key, STR:RC + | je >5 + |4: + | mov NODE:RA, NODE:RA->next + | test NODE:RA, NODE:RA + | jnz <3 + | jmp ->fff_res1 // Not found, keep default result. + |5: + | mov RB, NODE:RA->val + | cmp RB, LJ_TNIL; je ->fff_res1 // Ditto for nil value. + | mov [BASE-16], RB // Return value of mt.__metatable. + | jmp ->fff_res1 + | + |6: + | cmp ITYPEd, LJ_TUDATA; je <1 + | cmp ITYPEd, LJ_TISNUM; ja >7 + | mov ITYPEd, LJ_TISNUM + |7: + | not ITYPEd + | mov TAB:RB, [DISPATCH+ITYPE*8+DISPATCH_GL(gcroot[GCROOT_BASEMT])] + | jmp <2 + | + |.ffunc_2 setmetatable + | mov TAB:RB, [BASE] + | mov TAB:TMPR, TAB:RB + | checktab TAB:RB, ->fff_fallback + | // Fast path: no mt for table yet and not clearing the mt. + | cmp aword TAB:RB->metatable, 0; jne ->fff_fallback + | mov TAB:RA, [BASE+8] + | checktab TAB:RA, ->fff_fallback + | mov TAB:RB->metatable, TAB:RA + | mov PC, [BASE-8] + | mov [BASE-16], TAB:TMPR // Return original table. + | test byte TAB:RB->marked, LJ_GC_BLACK // isblack(table) + | jz >1 + | // Possible write barrier. Table is black, but skip iswhite(mt) check. + | barrierback TAB:RB, RC + |1: + | jmp ->fff_res1 + | + |.ffunc_2 rawget + |.if X64WIN + | mov TAB:RA, [BASE] + | checktab TAB:RA, ->fff_fallback + | mov RB, BASE // Save BASE. + | lea CARG3, [BASE+8] + | mov CARG2, TAB:RA // Caveat: CARG2 == BASE. + | mov CARG1, SAVE_L + |.else + | mov TAB:CARG2, [BASE] + | checktab TAB:CARG2, ->fff_fallback + | mov RB, BASE // Save BASE. + | lea CARG3, [BASE+8] // Caveat: CARG3 == BASE. + | mov CARG1, SAVE_L + |.endif + | call extern lj_tab_get // (lua_State *L, GCtab *t, cTValue *key) + | // cTValue * returned in eax (RD). + | mov BASE, RB // Restore BASE. + | // Copy table slot. + | mov RB, [RD] + | mov PC, [BASE-8] + | mov [BASE-16], RB + | jmp ->fff_res1 + | + |//-- Base library: conversions ------------------------------------------ + | + |.ffunc tonumber + | // Only handles the number case inline (without a base argument). + | cmp NARGS:RDd, 1+1; jne ->fff_fallback // Exactly one argument. + | mov RB, [BASE] + | checknumber RB, ->fff_fallback + | mov PC, [BASE-8] + | mov [BASE-16], RB + | jmp ->fff_res1 + | + |.ffunc_1 tostring + | // Only handles the string or number case inline. + | mov PC, [BASE-8] + | mov STR:RB, [BASE] + | checktp_nc STR:RB, LJ_TSTR, >3 + | // A __tostring method in the string base metatable is ignored. + |2: + | mov [BASE-16], STR:RB + | jmp ->fff_res1 + |3: // Handle numbers inline, unless a number base metatable is present. + | cmp ITYPEd, LJ_TISNUM; ja ->fff_fallback_1 + | cmp aword [DISPATCH+DISPATCH_GL(gcroot[GCROOT_BASEMT_NUM])], 0 + | jne ->fff_fallback + | ffgccheck // Caveat: uses label 1. + | mov L:RB, SAVE_L + | mov L:RB->base, BASE // Add frame since C call can throw. + | mov SAVE_PC, PC // Redundant (but a defined value). + |.if not X64WIN + | mov CARG2, BASE // Otherwise: CARG2 == BASE + |.endif + | mov L:CARG1, L:RB + |.if DUALNUM + | call extern lj_strfmt_number // (lua_State *L, cTValue *o) + |.else + | call extern lj_strfmt_num // (lua_State *L, lua_Number *np) + |.endif + | // GCstr returned in eax (RD). + | mov BASE, L:RB->base + | settp STR:RB, RD, LJ_TSTR + | jmp <2 + | + |//-- Base library: iterators ------------------------------------------- + | + |.ffunc_1 next + | je >2 // Missing 2nd arg? + |1: + |.if X64WIN + | mov RA, [BASE] + | checktab RA, ->fff_fallback + |.else + | mov CARG2, [BASE] + | checktab CARG2, ->fff_fallback + |.endif + | mov L:RB, SAVE_L + | mov L:RB->base, BASE // Add frame since C call can throw. + | mov L:RB->top, BASE // Dummy frame length is ok. + | mov PC, [BASE-8] + |.if X64WIN + | lea CARG3, [BASE+8] + | mov CARG2, RA // Caveat: CARG2 == BASE. + | mov CARG1, L:RB + |.else + | lea CARG3, [BASE+8] // Caveat: CARG3 == BASE. + | mov CARG1, L:RB + |.endif + | mov SAVE_PC, PC // Needed for ITERN fallback. + | call extern lj_tab_next // (lua_State *L, GCtab *t, TValue *key) + | // Flag returned in eax (RD). + | mov BASE, L:RB->base + | test RDd, RDd; jz >3 // End of traversal? + | // Copy key and value to results. + | mov RB, [BASE+8] + | mov RD, [BASE+16] + | mov [BASE-16], RB + | mov [BASE-8], RD + |->fff_res2: + | mov RDd, 1+2 + | jmp ->fff_res + |2: // Set missing 2nd arg to nil. + | mov aword [BASE+8], LJ_TNIL + | jmp <1 + |3: // End of traversal: return nil. + | mov aword [BASE-16], LJ_TNIL + | jmp ->fff_res1 + | + |.ffunc_1 pairs + | mov TAB:RB, [BASE] + | mov TMPR, TAB:RB + | checktab TAB:RB, ->fff_fallback +#if LJ_52 + | cmp aword TAB:RB->metatable, 0; jne ->fff_fallback +#endif + | mov CFUNC:RD, [BASE-16] + | cleartp CFUNC:RD + | mov CFUNC:RD, CFUNC:RD->upvalue[0] + | settp CFUNC:RD, LJ_TFUNC + | mov PC, [BASE-8] + | mov [BASE-16], CFUNC:RD + | mov [BASE-8], TMPR + | mov aword [BASE], LJ_TNIL + | mov RDd, 1+3 + | jmp ->fff_res + | + |.ffunc_2 ipairs_aux + | mov TAB:RB, [BASE] + | checktab TAB:RB, ->fff_fallback + |.if DUALNUM + | mov RA, [BASE+8] + | checkint RA, ->fff_fallback + |.else + | checknumtp [BASE+8], ->fff_fallback + | movsd xmm0, qword [BASE+8] + |.endif + | mov PC, [BASE-8] + |.if DUALNUM + | add RAd, 1 + | setint ITYPE, RA + | mov [BASE-16], ITYPE + |.else + | sseconst_1 xmm1, TMPR + | addsd xmm0, xmm1 + | cvttsd2si RAd, xmm0 + | movsd qword [BASE-16], xmm0 + |.endif + | cmp RAd, TAB:RB->asize; jae >2 // Not in array part? + | mov RD, TAB:RB->array + | lea RD, [RD+RA*8] + |1: + | cmp aword [RD], LJ_TNIL; je ->fff_res0 + | // Copy array slot. + | mov RB, [RD] + | mov [BASE-8], RB + | jmp ->fff_res2 + |2: // Check for empty hash part first. Otherwise call C function. + | cmp dword TAB:RB->hmask, 0; je ->fff_res0 + |.if X64WIN + | mov TMPR, BASE + | mov CARG2d, RAd + | mov CARG1, TAB:RB + | mov RB, TMPR + |.else + | mov CARG1, TAB:RB + | mov RB, BASE // Save BASE. + | mov CARG2d, RAd // Caveat: CARG2 == BASE + |.endif + | call extern lj_tab_getinth // (GCtab *t, int32_t key) + | // cTValue * or NULL returned in eax (RD). + | mov BASE, RB + | test RD, RD + | jnz <1 + |->fff_res0: + | mov RDd, 1+0 + | jmp ->fff_res + | + |.ffunc_1 ipairs + | mov TAB:RB, [BASE] + | mov TMPR, TAB:RB + | checktab TAB:RB, ->fff_fallback +#if LJ_52 + | cmp aword TAB:RB->metatable, 0; jne ->fff_fallback +#endif + | mov CFUNC:RD, [BASE-16] + | cleartp CFUNC:RD + | mov CFUNC:RD, CFUNC:RD->upvalue[0] + | settp CFUNC:RD, LJ_TFUNC + | mov PC, [BASE-8] + | mov [BASE-16], CFUNC:RD + | mov [BASE-8], TMPR + |.if DUALNUM + | mov64 RD, ((int64_t)LJ_TISNUM<<47) + | mov [BASE], RD + |.else + | mov qword [BASE], 0 + |.endif + | mov RDd, 1+3 + | jmp ->fff_res + | + |//-- Base library: catch errors ---------------------------------------- + | + |.ffunc_1 pcall + | lea RA, [BASE+16] + | sub NARGS:RDd, 1 + | mov PCd, 16+FRAME_PCALL + |1: + | movzx RBd, byte [DISPATCH+DISPATCH_GL(hookmask)] + | shr RB, HOOK_ACTIVE_SHIFT + | and RB, 1 + | add PC, RB // Remember active hook before pcall. + | // Note: this does a (harmless) copy of the function to the PC slot, too. + | mov KBASE, RD + |2: + | mov RB, [RA+KBASE*8-24] + | mov [RA+KBASE*8-16], RB + | sub KBASE, 1 + | ja <2 + | jmp ->vm_call_dispatch + | + |.ffunc_2 xpcall + | mov LFUNC:RA, [BASE+8] + | checktp_nc LFUNC:RA, LJ_TFUNC, ->fff_fallback + | mov LFUNC:RB, [BASE] // Swap function and traceback. + | mov [BASE], LFUNC:RA + | mov [BASE+8], LFUNC:RB + | lea RA, [BASE+24] + | sub NARGS:RDd, 2 + | mov PCd, 24+FRAME_PCALL + | jmp <1 + | + |//-- Coroutine library -------------------------------------------------- + | + |.macro coroutine_resume_wrap, resume + |.if resume + |.ffunc_1 coroutine_resume + | mov L:RB, [BASE] + | cleartp L:RB + |.else + |.ffunc coroutine_wrap_aux + | mov CFUNC:RB, [BASE-16] + | cleartp CFUNC:RB + | mov L:RB, CFUNC:RB->upvalue[0].gcr + | cleartp L:RB + |.endif + | mov PC, [BASE-8] + | mov SAVE_PC, PC + | mov TMP1, L:RB + |.if resume + | checktptp [BASE], LJ_TTHREAD, ->fff_fallback + |.endif + | cmp aword L:RB->cframe, 0; jne ->fff_fallback + | cmp byte L:RB->status, LUA_YIELD; ja ->fff_fallback + | mov RA, L:RB->top + | je >1 // Status != LUA_YIELD (i.e. 0)? + | cmp RA, L:RB->base // Check for presence of initial func. + | je ->fff_fallback + | mov PC, [RA-8] // Move initial function up. + | mov [RA], PC + | add RA, 8 + |1: + |.if resume + | lea PC, [RA+NARGS:RD*8-16] // Check stack space (-1-thread). + |.else + | lea PC, [RA+NARGS:RD*8-8] // Check stack space (-1). + |.endif + | cmp PC, L:RB->maxstack; ja ->fff_fallback + | mov L:RB->top, PC + | + | mov L:RB, SAVE_L + | mov L:RB->base, BASE + |.if resume + | add BASE, 8 // Keep resumed thread in stack for GC. + |.endif + | mov L:RB->top, BASE + |.if resume + | lea RB, [BASE+NARGS:RD*8-24] // RB = end of source for stack move. + |.else + | lea RB, [BASE+NARGS:RD*8-16] // RB = end of source for stack move. + |.endif + | sub RB, PC // Relative to PC. + | + | cmp PC, RA + | je >3 + |2: // Move args to coroutine. + | mov RC, [PC+RB] + | mov [PC-8], RC + | sub PC, 8 + | cmp PC, RA + | jne <2 + |3: + | mov CARG2, RA + | mov CARG1, TMP1 + | call ->vm_resume // (lua_State *L, TValue *base, 0, 0) + | + | mov L:RB, SAVE_L + | mov L:PC, TMP1 + | mov BASE, L:RB->base + | mov [DISPATCH+DISPATCH_GL(cur_L)], L:RB + | set_vmstate INTERP + | + | cmp eax, LUA_YIELD + | ja >8 + |4: + | mov RA, L:PC->base + | mov KBASE, L:PC->top + | mov L:PC->top, RA // Clear coroutine stack. + | mov PC, KBASE + | sub PC, RA + | je >6 // No results? + | lea RD, [BASE+PC] + | shr PCd, 3 + | cmp RD, L:RB->maxstack + | ja >9 // Need to grow stack? + | + | mov RB, BASE + | sub RB, RA + |5: // Move results from coroutine. + | mov RD, [RA] + | mov [RA+RB], RD + | add RA, 8 + | cmp RA, KBASE + | jne <5 + |6: + |.if resume + | lea RDd, [PCd+2] // nresults+1 = 1 + true + results. + | mov_true ITYPE // Prepend true to results. + | mov [BASE-8], ITYPE + |.else + | lea RDd, [PCd+1] // nresults+1 = 1 + results. + |.endif + |7: + | mov PC, SAVE_PC + | mov MULTRES, RDd + |.if resume + | mov RA, -8 + |.else + | xor RAd, RAd + |.endif + | test PCd, FRAME_TYPE + | jz ->BC_RET_Z + | jmp ->vm_return + | + |8: // Coroutine returned with error (at co->top-1). + |.if resume + | mov_false ITYPE // Prepend false to results. + | mov [BASE-8], ITYPE + | mov RA, L:PC->top + | sub RA, 8 + | mov L:PC->top, RA // Clear error from coroutine stack. + | // Copy error message. + | mov RD, [RA] + | mov [BASE], RD + | mov RDd, 1+2 // nresults+1 = 1 + false + error. + | jmp <7 + |.else + | mov CARG2, L:PC + | mov CARG1, L:RB + | call extern lj_ffh_coroutine_wrap_err // (lua_State *L, lua_State *co) + | // Error function does not return. + |.endif + | + |9: // Handle stack expansion on return from yield. + | mov L:RA, TMP1 + | mov L:RA->top, KBASE // Undo coroutine stack clearing. + | mov CARG2, PC + | mov CARG1, L:RB + | call extern lj_state_growstack // (lua_State *L, int n) + | mov L:PC, TMP1 + | mov BASE, L:RB->base + | jmp <4 // Retry the stack move. + |.endmacro + | + | coroutine_resume_wrap 1 // coroutine.resume + | coroutine_resume_wrap 0 // coroutine.wrap + | + |.ffunc coroutine_yield + | mov L:RB, SAVE_L + | test aword L:RB->cframe, CFRAME_RESUME + | jz ->fff_fallback + | mov L:RB->base, BASE + | lea RD, [BASE+NARGS:RD*8-8] + | mov L:RB->top, RD + | xor RDd, RDd + | mov aword L:RB->cframe, RD + | mov al, LUA_YIELD + | mov byte L:RB->status, al + | jmp ->vm_leave_unw + | + |//-- Math library ------------------------------------------------------- + | + | .ffunc_1 math_abs + | mov RB, [BASE] + |.if DUALNUM + | checkint RB, >3 + | cmp RBd, 0; jns ->fff_resi + | neg RBd; js >2 + |->fff_resbit: + |->fff_resi: + | setint RB + |->fff_resRB: + | mov PC, [BASE-8] + | mov [BASE-16], RB + | jmp ->fff_res1 + |2: + | mov64 RB, U64x(41e00000,00000000) // 2^31. + | jmp ->fff_resRB + |3: + | ja ->fff_fallback + |.else + | checknum RB, ->fff_fallback + |.endif + | shl RB, 1 + | shr RB, 1 + | mov PC, [BASE-8] + | mov [BASE-16], RB + | jmp ->fff_res1 + | + |.ffunc_n math_sqrt, sqrtsd + |->fff_resxmm0: + | mov PC, [BASE-8] + | movsd qword [BASE-16], xmm0 + | // fallthrough + | + |->fff_res1: + | mov RDd, 1+1 + |->fff_res: + | mov MULTRES, RDd + |->fff_res_: + | test PCd, FRAME_TYPE + | jnz >7 + |5: + | cmp PC_RB, RDL // More results expected? + | ja >6 + | // Adjust BASE. KBASE is assumed to be set for the calling frame. + | movzx RAd, PC_RA + | neg RA + | lea BASE, [BASE+RA*8-16] // base = base - (RA+2)*8 + | ins_next + | + |6: // Fill up results with nil. + | mov aword [BASE+RD*8-24], LJ_TNIL + | add RD, 1 + | jmp <5 + | + |7: // Non-standard return case. + | mov RA, -16 // Results start at BASE+RA = BASE-16. + | jmp ->vm_return + | + |.macro math_round, func + | .ffunc math_ .. func + |.if DUALNUM + | mov RB, [BASE] + | checknumx RB, ->fff_resRB, je + | ja ->fff_fallback + |.else + | checknumtp [BASE], ->fff_fallback + |.endif + | movsd xmm0, qword [BASE] + | call ->vm_ .. func .. _sse + |.if DUALNUM + | cvttsd2si RBd, xmm0 + | cmp RBd, 0x80000000 + | jne ->fff_resi + | cvtsi2sd xmm1, RBd + | ucomisd xmm0, xmm1 + | jp ->fff_resxmm0 + | je ->fff_resi + |.endif + | jmp ->fff_resxmm0 + |.endmacro + | + | math_round floor + | math_round ceil + | + |.ffunc math_log + | cmp NARGS:RDd, 1+1; jne ->fff_fallback // Exactly one argument. + | checknumtp [BASE], ->fff_fallback + | movsd xmm0, qword [BASE] + | mov RB, BASE + | call extern log + | mov BASE, RB + | jmp ->fff_resxmm0 + | + |.macro math_extern, func + | .ffunc_n math_ .. func + | mov RB, BASE + | call extern func + | mov BASE, RB + | jmp ->fff_resxmm0 + |.endmacro + | + |.macro math_extern2, func + | .ffunc_nn math_ .. func + | mov RB, BASE + | call extern func + | mov BASE, RB + | jmp ->fff_resxmm0 + |.endmacro + | + | math_extern log10 + | math_extern exp + | math_extern sin + | math_extern cos + | math_extern tan + | math_extern asin + | math_extern acos + | math_extern atan + | math_extern sinh + | math_extern cosh + | math_extern tanh + | math_extern2 pow + | math_extern2 atan2 + | math_extern2 fmod + | + |.ffunc_2 math_ldexp + | checknumtp [BASE], ->fff_fallback + | checknumtp [BASE+8], ->fff_fallback + | fld qword [BASE+8] + | fld qword [BASE] + | fscale + | fpop1 + | mov PC, [BASE-8] + | fstp qword [BASE-16] + | jmp ->fff_res1 + | + |.ffunc_n math_frexp + | lea CARG1, TMP1 + | mov RB, BASE + | call extern frexp + | mov BASE, RB + | mov RBd, TMP1d + | mov PC, [BASE-8] + | movsd qword [BASE-16], xmm0 + |.if DUALNUM + | setint RB + | mov [BASE-8], RB + |.else + | cvtsi2sd xmm1, RBd + | movsd qword [BASE-8], xmm1 + |.endif + | mov RDd, 1+2 + | jmp ->fff_res + | + |.ffunc_n math_modf + | lea CARG1, [BASE-16] + | mov PC, [BASE-8] + | mov RB, BASE + | call extern modf + | mov BASE, RB + | mov PC, [BASE-8] + | movsd qword [BASE-8], xmm0 + | mov RDd, 1+2 + | jmp ->fff_res + | + |.macro math_minmax, name, cmovop, sseop + | .ffunc name + | mov RAd, 2 + |.if DUALNUM + | mov RB, [BASE] + | checkint RB, >4 + |1: // Handle integers. + | cmp RAd, RDd; jae ->fff_resRB + | mov TMPR, [BASE+RA*8-8] + | checkint TMPR, >3 + | cmp RBd, TMPRd + | cmovop RB, TMPR + | add RAd, 1 + | jmp <1 + |3: + | ja ->fff_fallback + | // Convert intermediate result to number and continue below. + | cvtsi2sd xmm0, RBd + | jmp >6 + |4: + | ja ->fff_fallback + |.else + | checknumtp [BASE], ->fff_fallback + |.endif + | + | movsd xmm0, qword [BASE] + |5: // Handle numbers or integers. + | cmp RAd, RDd; jae ->fff_resxmm0 + |.if DUALNUM + | mov RB, [BASE+RA*8-8] + | checknumx RB, >6, jb + | ja ->fff_fallback + | cvtsi2sd xmm1, RBd + | jmp >7 + |.else + | checknumtp [BASE+RA*8-8], ->fff_fallback + |.endif + |6: + | movsd xmm1, qword [BASE+RA*8-8] + |7: + | sseop xmm0, xmm1 + | add RAd, 1 + | jmp <5 + |.endmacro + | + | math_minmax math_min, cmovg, minsd + | math_minmax math_max, cmovl, maxsd + | + |//-- String library ----------------------------------------------------- + | + |.ffunc string_byte // Only handle the 1-arg case here. + | cmp NARGS:RDd, 1+1; jne ->fff_fallback + | mov STR:RB, [BASE] + | checkstr STR:RB, ->fff_fallback + | mov PC, [BASE-8] + | cmp dword STR:RB->len, 1 + | jb ->fff_res0 // Return no results for empty string. + | movzx RBd, byte STR:RB[1] + |.if DUALNUM + | jmp ->fff_resi + |.else + | cvtsi2sd xmm0, RBd; jmp ->fff_resxmm0 + |.endif + | + |.ffunc string_char // Only handle the 1-arg case here. + | ffgccheck + | cmp NARGS:RDd, 1+1; jne ->fff_fallback // *Exactly* 1 arg. + |.if DUALNUM + | mov RB, [BASE] + | checkint RB, ->fff_fallback + |.else + | checknumtp [BASE], ->fff_fallback + | cvttsd2si RBd, qword [BASE] + |.endif + | cmp RBd, 255; ja ->fff_fallback + | mov TMP1d, RBd + | mov TMPRd, 1 + | lea RD, TMP1 // Points to stack. Little-endian. + |->fff_newstr: + | mov L:RB, SAVE_L + | mov L:RB->base, BASE + | mov CARG3d, TMPRd // Zero-extended to size_t. + | mov CARG2, RD + | mov CARG1, L:RB + | mov SAVE_PC, PC + | call extern lj_str_new // (lua_State *L, char *str, size_t l) + |->fff_resstr: + | // GCstr * returned in eax (RD). + | mov BASE, L:RB->base + | mov PC, [BASE-8] + | settp STR:RD, LJ_TSTR + | mov [BASE-16], STR:RD + | jmp ->fff_res1 + | + |.ffunc string_sub + | ffgccheck + | mov TMPRd, -1 + | cmp NARGS:RDd, 1+2; jb ->fff_fallback + | jna >1 + |.if DUALNUM + | mov TMPR, [BASE+16] + | checkint TMPR, ->fff_fallback + |.else + | checknumtp [BASE+16], ->fff_fallback + | cvttsd2si TMPRd, qword [BASE+16] + |.endif + |1: + | mov STR:RB, [BASE] + | checkstr STR:RB, ->fff_fallback + |.if DUALNUM + | mov ITYPE, [BASE+8] + | mov RAd, ITYPEd // Must clear hiword for lea below. + | sar ITYPE, 47 + | cmp ITYPEd, LJ_TISNUM + | jne ->fff_fallback + |.else + | checknumtp [BASE+8], ->fff_fallback + | cvttsd2si RAd, qword [BASE+8] + |.endif + | mov RCd, STR:RB->len + | cmp RCd, TMPRd // len < end? (unsigned compare) + | jb >5 + |2: + | test RAd, RAd // start <= 0? + | jle >7 + |3: + | sub TMPRd, RAd // start > end? + | jl ->fff_emptystr + | lea RD, [STR:RB+RAd+#STR-1] + | add TMPRd, 1 + |4: + | jmp ->fff_newstr + | + |5: // Negative end or overflow. + | jl >6 + | lea TMPRd, [TMPRd+RCd+1] // end = end+(len+1) + | jmp <2 + |6: // Overflow. + | mov TMPRd, RCd // end = len + | jmp <2 + | + |7: // Negative start or underflow. + | je >8 + | add RAd, RCd // start = start+(len+1) + | add RAd, 1 + | jg <3 // start > 0? + |8: // Underflow. + | mov RAd, 1 // start = 1 + | jmp <3 + | + |->fff_emptystr: // Range underflow. + | xor TMPRd, TMPRd // Zero length. Any ptr in RD is ok. + | jmp <4 + | + |.macro ffstring_op, name + | .ffunc_1 string_ .. name + | ffgccheck + |.if X64WIN + | mov STR:TMPR, [BASE] + | checkstr STR:TMPR, ->fff_fallback + |.else + | mov STR:CARG2, [BASE] + | checkstr STR:CARG2, ->fff_fallback + |.endif + | mov L:RB, SAVE_L + | lea SBUF:CARG1, [DISPATCH+DISPATCH_GL(tmpbuf)] + | mov L:RB->base, BASE + |.if X64WIN + | mov STR:CARG2, STR:TMPR // Caveat: CARG2 == BASE + |.endif + | mov RC, SBUF:CARG1->b + | mov SBUF:CARG1->L, L:RB + | mov SBUF:CARG1->p, RC + | mov SAVE_PC, PC + | call extern lj_buf_putstr_ .. name + | mov CARG1, rax + | call extern lj_buf_tostr + | jmp ->fff_resstr + |.endmacro + | + |ffstring_op reverse + |ffstring_op lower + |ffstring_op upper + | + |//-- Bit library -------------------------------------------------------- + | + |.macro .ffunc_bit, name, kind, fdef + | fdef name + |.if kind == 2 + | sseconst_tobit xmm1, RB + |.endif + |.if DUALNUM + | mov RB, [BASE] + | checkint RB, >1 + |.if kind > 0 + | jmp >2 + |.else + | jmp ->fff_resbit + |.endif + |1: + | ja ->fff_fallback + | movd xmm0, RB + |.else + | checknumtp [BASE], ->fff_fallback + | movsd xmm0, qword [BASE] + |.endif + |.if kind < 2 + | sseconst_tobit xmm1, RB + |.endif + | addsd xmm0, xmm1 + | movd RBd, xmm0 + |2: + |.endmacro + | + |.macro .ffunc_bit, name, kind + | .ffunc_bit name, kind, .ffunc_1 + |.endmacro + | + |.ffunc_bit bit_tobit, 0 + | jmp ->fff_resbit + | + |.macro .ffunc_bit_op, name, ins + | .ffunc_bit name, 2 + | mov TMPRd, NARGS:RDd // Save for fallback. + | lea RD, [BASE+NARGS:RD*8-16] + |1: + | cmp RD, BASE + | jbe ->fff_resbit + |.if DUALNUM + | mov RA, [RD] + | checkint RA, >2 + | ins RBd, RAd + | sub RD, 8 + | jmp <1 + |2: + | ja ->fff_fallback_bit_op + | movd xmm0, RA + |.else + | checknumtp [RD], ->fff_fallback_bit_op + | movsd xmm0, qword [RD] + |.endif + | addsd xmm0, xmm1 + | movd RAd, xmm0 + | ins RBd, RAd + | sub RD, 8 + | jmp <1 + |.endmacro + | + |.ffunc_bit_op bit_band, and + |.ffunc_bit_op bit_bor, or + |.ffunc_bit_op bit_bxor, xor + | + |.ffunc_bit bit_bswap, 1 + | bswap RBd + | jmp ->fff_resbit + | + |.ffunc_bit bit_bnot, 1 + | not RBd + |.if DUALNUM + | jmp ->fff_resbit + |.else + |->fff_resbit: + | cvtsi2sd xmm0, RBd + | jmp ->fff_resxmm0 + |.endif + | + |->fff_fallback_bit_op: + | mov NARGS:RDd, TMPRd // Restore for fallback + | jmp ->fff_fallback + | + |.macro .ffunc_bit_sh, name, ins + |.if DUALNUM + | .ffunc_bit name, 1, .ffunc_2 + | // Note: no inline conversion from number for 2nd argument! + | mov RA, [BASE+8] + | checkint RA, ->fff_fallback + |.else + | .ffunc_nn name + | sseconst_tobit xmm2, RB + | addsd xmm0, xmm2 + | addsd xmm1, xmm2 + | movd RBd, xmm0 + | movd RAd, xmm1 + |.endif + | ins RBd, cl // Assumes RA is ecx. + | jmp ->fff_resbit + |.endmacro + | + |.ffunc_bit_sh bit_lshift, shl + |.ffunc_bit_sh bit_rshift, shr + |.ffunc_bit_sh bit_arshift, sar + |.ffunc_bit_sh bit_rol, rol + |.ffunc_bit_sh bit_ror, ror + | + |//----------------------------------------------------------------------- + | + |->fff_fallback_2: + | mov NARGS:RDd, 1+2 // Other args are ignored, anyway. + | jmp ->fff_fallback + |->fff_fallback_1: + | mov NARGS:RDd, 1+1 // Other args are ignored, anyway. + |->fff_fallback: // Call fast function fallback handler. + | // BASE = new base, RD = nargs+1 + | mov L:RB, SAVE_L + | mov PC, [BASE-8] // Fallback may overwrite PC. + | mov SAVE_PC, PC // Redundant (but a defined value). + | mov L:RB->base, BASE + | lea RD, [BASE+NARGS:RD*8-8] + | lea RA, [RD+8*LUA_MINSTACK] // Ensure enough space for handler. + | mov L:RB->top, RD + | mov CFUNC:RD, [BASE-16] + | cleartp CFUNC:RD + | cmp RA, L:RB->maxstack + | ja >5 // Need to grow stack. + | mov CARG1, L:RB + | call aword CFUNC:RD->f // (lua_State *L) + | mov BASE, L:RB->base + | // Either throws an error, or recovers and returns -1, 0 or nresults+1. + | test RDd, RDd; jg ->fff_res // Returned nresults+1? + |1: + | mov RA, L:RB->top + | sub RA, BASE + | shr RAd, 3 + | test RDd, RDd + | lea NARGS:RDd, [RAd+1] + | mov LFUNC:RB, [BASE-16] + | jne ->vm_call_tail // Returned -1? + | cleartp LFUNC:RB + | ins_callt // Returned 0: retry fast path. + | + |// Reconstruct previous base for vmeta_call during tailcall. + |->vm_call_tail: + | mov RA, BASE + | test PCd, FRAME_TYPE + | jnz >3 + | movzx RBd, PC_RA + | neg RB + | lea BASE, [BASE+RB*8-16] // base = base - (RB+2)*8 + | jmp ->vm_call_dispatch // Resolve again for tailcall. + |3: + | mov RB, PC + | and RB, -8 + | sub BASE, RB + | jmp ->vm_call_dispatch // Resolve again for tailcall. + | + |5: // Grow stack for fallback handler. + | mov CARG2d, LUA_MINSTACK + | mov CARG1, L:RB + | call extern lj_state_growstack // (lua_State *L, int n) + | mov BASE, L:RB->base + | xor RDd, RDd // Simulate a return 0. + | jmp <1 // Dumb retry (goes through ff first). + | + |->fff_gcstep: // Call GC step function. + | // BASE = new base, RD = nargs+1 + | pop RB // Must keep stack at same level. + | mov TMP1, RB // Save return address + | mov L:RB, SAVE_L + | mov SAVE_PC, PC // Redundant (but a defined value). + | mov L:RB->base, BASE + | lea RD, [BASE+NARGS:RD*8-8] + | mov CARG1, L:RB + | mov L:RB->top, RD + | call extern lj_gc_step // (lua_State *L) + | mov BASE, L:RB->base + | mov RD, L:RB->top + | sub RD, BASE + | shr RDd, 3 + | add NARGS:RDd, 1 + | mov RB, TMP1 + | push RB // Restore return address. + | ret + | + |//----------------------------------------------------------------------- + |//-- Special dispatch targets ------------------------------------------- + |//----------------------------------------------------------------------- + | + |->vm_record: // Dispatch target for recording phase. + |.if JIT + | movzx RDd, byte [DISPATCH+DISPATCH_GL(hookmask)] + | test RDL, HOOK_VMEVENT // No recording while in vmevent. + | jnz >5 + | // Decrement the hookcount for consistency, but always do the call. + | test RDL, HOOK_ACTIVE + | jnz >1 + | test RDL, LUA_MASKLINE|LUA_MASKCOUNT + | jz >1 + | dec dword [DISPATCH+DISPATCH_GL(hookcount)] + | jmp >1 + |.endif + | + |->vm_rethook: // Dispatch target for return hooks. + | movzx RDd, byte [DISPATCH+DISPATCH_GL(hookmask)] + | test RDL, HOOK_ACTIVE // Hook already active? + | jnz >5 + | jmp >1 + | + |->vm_inshook: // Dispatch target for instr/line hooks. + | movzx RDd, byte [DISPATCH+DISPATCH_GL(hookmask)] + | test RDL, HOOK_ACTIVE // Hook already active? + | jnz >5 + | + | test RDL, LUA_MASKLINE|LUA_MASKCOUNT + | jz >5 + | dec dword [DISPATCH+DISPATCH_GL(hookcount)] + | jz >1 + | test RDL, LUA_MASKLINE + | jz >5 + |1: + | mov L:RB, SAVE_L + | mov L:RB->base, BASE + | mov CARG2, PC // Caveat: CARG2 == BASE + | mov CARG1, L:RB + | // SAVE_PC must hold the _previous_ PC. The callee updates it with PC. + | call extern lj_dispatch_ins // (lua_State *L, const BCIns *pc) + |3: + | mov BASE, L:RB->base + |4: + | movzx RAd, PC_RA + |5: + | movzx OP, PC_OP + | movzx RDd, PC_RD + | jmp aword [DISPATCH+OP*8+GG_DISP2STATIC] // Re-dispatch to static ins. + | + |->cont_hook: // Continue from hook yield. + | add PC, 4 + | mov RA, [RB-40] + | mov MULTRES, RAd // Restore MULTRES for *M ins. + | jmp <4 + | + |->vm_hotloop: // Hot loop counter underflow. + |.if JIT + | mov LFUNC:RB, [BASE-16] // Same as curr_topL(L). + | cleartp LFUNC:RB + | mov RB, LFUNC:RB->pc + | movzx RDd, byte [RB+PC2PROTO(framesize)] + | lea RD, [BASE+RD*8] + | mov L:RB, SAVE_L + | mov L:RB->base, BASE + | mov L:RB->top, RD + | mov CARG2, PC + | lea CARG1, [DISPATCH+GG_DISP2J] + | mov aword [DISPATCH+DISPATCH_J(L)], L:RB + | mov SAVE_PC, PC + | call extern lj_trace_hot // (jit_State *J, const BCIns *pc) + | jmp <3 + |.endif + | + |->vm_callhook: // Dispatch target for call hooks. + | mov SAVE_PC, PC + |.if JIT + | jmp >1 + |.endif + | + |->vm_hotcall: // Hot call counter underflow. + |.if JIT + | mov SAVE_PC, PC + | or PC, 1 // Marker for hot call. + |1: + |.endif + | lea RD, [BASE+NARGS:RD*8-8] + | mov L:RB, SAVE_L + | mov L:RB->base, BASE + | mov L:RB->top, RD + | mov CARG2, PC + | mov CARG1, L:RB + | call extern lj_dispatch_call // (lua_State *L, const BCIns *pc) + | // ASMFunction returned in eax/rax (RD). + | mov SAVE_PC, 0 // Invalidate for subsequent line hook. + |.if JIT + | and PC, -2 + |.endif + | mov BASE, L:RB->base + | mov RA, RD + | mov RD, L:RB->top + | sub RD, BASE + | mov RB, RA + | movzx RAd, PC_RA + | shr RDd, 3 + | add NARGS:RDd, 1 + | jmp RB + | + |->cont_stitch: // Trace stitching. + |.if JIT + | // BASE = base, RC = result, RB = mbase + | mov ITYPEd, [RB-24] // Save previous trace number. + | mov TMPRd, MULTRES + | movzx RAd, PC_RA + | lea RA, [BASE+RA*8] // Call base. + | sub TMPRd, 1 + | jz >2 + |1: // Move results down. + | mov RB, [RC] + | mov [RA], RB + | add RC, 8 + | add RA, 8 + | sub TMPRd, 1 + | jnz <1 + |2: + | movzx RCd, PC_RA + | movzx RBd, PC_RB + | add RC, RB + | lea RC, [BASE+RC*8-8] + |3: + | cmp RC, RA + | ja >9 // More results wanted? + | + | mov RA, [DISPATCH+DISPATCH_J(trace)] + | mov TRACE:RD, [RA+ITYPE*8] + | test TRACE:RD, TRACE:RD + | jz ->cont_nop + | movzx RDd, word TRACE:RD->link + | cmp RDd, RBd + | je ->cont_nop // Blacklisted. + | test RDd, RDd + | jne =>BC_JLOOP // Jump to stitched trace. + | + | // Stitch a new trace to the previous trace. + | mov [DISPATCH+DISPATCH_J(exitno)], RB + | mov L:RB, SAVE_L + | mov L:RB->base, BASE + | mov CARG2, PC + | lea CARG1, [DISPATCH+GG_DISP2J] + | mov aword [DISPATCH+DISPATCH_J(L)], L:RB + | call extern lj_dispatch_stitch // (jit_State *J, const BCIns *pc) + | mov BASE, L:RB->base + | jmp ->cont_nop + | + |9: // Fill up results with nil. + | mov aword [RA], LJ_TNIL + | add RA, 8 + | jmp <3 + |.endif + | + |->vm_profhook: // Dispatch target for profiler hook. +#if LJ_HASPROFILE + | mov L:RB, SAVE_L + | mov L:RB->base, BASE + | mov CARG2, PC // Caveat: CARG2 == BASE + | mov CARG1, L:RB + | call extern lj_dispatch_profile // (lua_State *L, const BCIns *pc) + | mov BASE, L:RB->base + | // HOOK_PROFILE is off again, so re-dispatch to dynamic instruction. + | sub PC, 4 + | jmp ->cont_nop +#endif + | + |//----------------------------------------------------------------------- + |//-- Trace exit handler ------------------------------------------------- + |//----------------------------------------------------------------------- + | + |// Called from an exit stub with the exit number on the stack. + |// The 16 bit exit number is stored with two (sign-extended) push imm8. + |->vm_exit_handler: + |.if JIT + | push r13; push r12 + | push r11; push r10; push r9; push r8 + | push rdi; push rsi; push rbp; lea rbp, [rsp+88]; push rbp + | push rbx; push rdx; push rcx; push rax + | movzx RCd, byte [rbp-8] // Reconstruct exit number. + | mov RCH, byte [rbp-16] + | mov [rbp-8], r15; mov [rbp-16], r14 + | // Caveat: DISPATCH is rbx. + | mov DISPATCH, [ebp] + | mov RA, [DISPATCH+DISPATCH_GL(vmstate)] // Get trace number. + | set_vmstate EXIT + | mov [DISPATCH+DISPATCH_J(exitno)], RC + | mov [DISPATCH+DISPATCH_J(parent)], RA + |.if X64WIN + | sub rsp, 16*8+4*8 // Room for SSE regs + save area. + |.else + | sub rsp, 16*8 // Room for SSE regs. + |.endif + | add rbp, -128 + | movsd qword [rbp-8], xmm15; movsd qword [rbp-16], xmm14 + | movsd qword [rbp-24], xmm13; movsd qword [rbp-32], xmm12 + | movsd qword [rbp-40], xmm11; movsd qword [rbp-48], xmm10 + | movsd qword [rbp-56], xmm9; movsd qword [rbp-64], xmm8 + | movsd qword [rbp-72], xmm7; movsd qword [rbp-80], xmm6 + | movsd qword [rbp-88], xmm5; movsd qword [rbp-96], xmm4 + | movsd qword [rbp-104], xmm3; movsd qword [rbp-112], xmm2 + | movsd qword [rbp-120], xmm1; movsd qword [rbp-128], xmm0 + | // Caveat: RB is rbp. + | mov L:RB, [DISPATCH+DISPATCH_GL(cur_L)] + | mov BASE, [DISPATCH+DISPATCH_GL(jit_base)] + | mov aword [DISPATCH+DISPATCH_J(L)], L:RB + | mov L:RB->base, BASE + |.if X64WIN + | lea CARG2, [rsp+4*8] + |.else + | mov CARG2, rsp + |.endif + | lea CARG1, [DISPATCH+GG_DISP2J] + | mov dword [DISPATCH+DISPATCH_GL(jit_base)], 0 + | call extern lj_trace_exit // (jit_State *J, ExitState *ex) + | // MULTRES or negated error code returned in eax (RD). + | mov RA, L:RB->cframe + | and RA, CFRAME_RAWMASK + | mov [RA+CFRAME_OFS_L], L:RB // Set SAVE_L (on-trace resume/yield). + | mov BASE, L:RB->base + | mov PC, [RA+CFRAME_OFS_PC] // Get SAVE_PC. + | jmp >1 + |.endif + |->vm_exit_interp: + | // RD = MULTRES or negated error code, BASE, PC and DISPATCH set. + |.if JIT + | // Restore additional callee-save registers only used in compiled code. + |.if X64WIN + | lea RA, [rsp+10*16+4*8] + |1: + | movdqa xmm15, [RA-10*16] + | movdqa xmm14, [RA-9*16] + | movdqa xmm13, [RA-8*16] + | movdqa xmm12, [RA-7*16] + | movdqa xmm11, [RA-6*16] + | movdqa xmm10, [RA-5*16] + | movdqa xmm9, [RA-4*16] + | movdqa xmm8, [RA-3*16] + | movdqa xmm7, [RA-2*16] + | mov rsp, RA // Reposition stack to C frame. + | movdqa xmm6, [RA-1*16] + | mov r15, CSAVE_1 + | mov r14, CSAVE_2 + | mov r13, CSAVE_3 + | mov r12, CSAVE_4 + |.else + | lea RA, [rsp+16] + |1: + | mov r13, [RA-8] + | mov r12, [RA] + | mov rsp, RA // Reposition stack to C frame. + |.endif + | test RDd, RDd; js >9 // Check for error from exit. + | mov L:RB, SAVE_L + | mov MULTRES, RDd + | mov LFUNC:KBASE, [BASE-16] + | cleartp LFUNC:KBASE + | mov KBASE, LFUNC:KBASE->pc + | mov KBASE, [KBASE+PC2PROTO(k)] + | mov L:RB->base, BASE + | mov dword [DISPATCH+DISPATCH_GL(jit_base)], 0 + | set_vmstate INTERP + | // Modified copy of ins_next which handles function header dispatch, too. + | mov RCd, [PC] + | movzx RAd, RCH + | movzx OP, RCL + | add PC, 4 + | shr RCd, 16 + | cmp OP, BC_FUNCF // Function header? + | jb >3 + | cmp OP, BC_FUNCC+2 // Fast function? + | jae >4 + |2: + | mov RCd, MULTRES // RC/RD holds nres+1. + |3: + | jmp aword [DISPATCH+OP*8] + | + |4: // Check frame below fast function. + | mov RC, [BASE-8] + | test RCd, FRAME_TYPE + | jnz <2 // Trace stitching continuation? + | // Otherwise set KBASE for Lua function below fast function. + | movzx RCd, byte [RC-3] + | neg RC + | mov LFUNC:KBASE, [BASE+RC*8-24] + | cleartp LFUNC:KBASE + | mov KBASE, LFUNC:KBASE->pc + | mov KBASE, [KBASE+PC2PROTO(k)] + | jmp <2 + | + |9: // Rethrow error from the right C frame. + | neg RD + | mov CARG1, L:RB + | mov CARG2, RD + | call extern lj_err_throw // (lua_State *L, int errcode) + |.endif + | + |//----------------------------------------------------------------------- + |//-- Math helper functions ---------------------------------------------- + |//----------------------------------------------------------------------- + | + |// FP value rounding. Called by math.floor/math.ceil fast functions + |// and from JIT code. arg/ret is xmm0. xmm0-xmm3 and RD (eax) modified. + |.macro vm_round, name, mode, cond + |->name: + |->name .. _sse: + | sseconst_abs xmm2, RD + | sseconst_2p52 xmm3, RD + | movaps xmm1, xmm0 + | andpd xmm1, xmm2 // |x| + | ucomisd xmm3, xmm1 // No truncation if 2^52 <= |x|. + | jbe >1 + | andnpd xmm2, xmm0 // Isolate sign bit. + |.if mode == 2 // trunc(x)? + | movaps xmm0, xmm1 + | addsd xmm1, xmm3 // (|x| + 2^52) - 2^52 + | subsd xmm1, xmm3 + | sseconst_1 xmm3, RD + | cmpsd xmm0, xmm1, 1 // |x| < result? + | andpd xmm0, xmm3 + | subsd xmm1, xmm0 // If yes, subtract -1. + | orpd xmm1, xmm2 // Merge sign bit back in. + |.else + | addsd xmm1, xmm3 // (|x| + 2^52) - 2^52 + | subsd xmm1, xmm3 + | orpd xmm1, xmm2 // Merge sign bit back in. + | .if mode == 1 // ceil(x)? + | sseconst_m1 xmm2, RD // Must subtract -1 to preserve -0. + | cmpsd xmm0, xmm1, 6 // x > result? + | .else // floor(x)? + | sseconst_1 xmm2, RD + | cmpsd xmm0, xmm1, 1 // x < result? + | .endif + | andpd xmm0, xmm2 + | subsd xmm1, xmm0 // If yes, subtract +-1. + |.endif + | movaps xmm0, xmm1 + |1: + | ret + |.endmacro + | + | vm_round vm_floor, 0, 1 + | vm_round vm_ceil, 1, JIT + | vm_round vm_trunc, 2, JIT + | + |// FP modulo x%y. Called by BC_MOD* and vm_arith. + |->vm_mod: + |// Args in xmm0/xmm1, return value in xmm0. + |// Caveat: xmm0-xmm5 and RC (eax) modified! + | movaps xmm5, xmm0 + | divsd xmm0, xmm1 + | sseconst_abs xmm2, RD + | sseconst_2p52 xmm3, RD + | movaps xmm4, xmm0 + | andpd xmm4, xmm2 // |x/y| + | ucomisd xmm3, xmm4 // No truncation if 2^52 <= |x/y|. + | jbe >1 + | andnpd xmm2, xmm0 // Isolate sign bit. + | addsd xmm4, xmm3 // (|x/y| + 2^52) - 2^52 + | subsd xmm4, xmm3 + | orpd xmm4, xmm2 // Merge sign bit back in. + | sseconst_1 xmm2, RD + | cmpsd xmm0, xmm4, 1 // x/y < result? + | andpd xmm0, xmm2 + | subsd xmm4, xmm0 // If yes, subtract 1.0. + | movaps xmm0, xmm5 + | mulsd xmm1, xmm4 + | subsd xmm0, xmm1 + | ret + |1: + | mulsd xmm1, xmm0 + | movaps xmm0, xmm5 + | subsd xmm0, xmm1 + | ret + | + |// Args in xmm0/eax. Ret in xmm0. xmm0-xmm1 and eax modified. + |->vm_powi_sse: + | cmp eax, 1; jle >6 // i<=1? + | // Now 1 < (unsigned)i <= 0x80000000. + |1: // Handle leading zeros. + | test eax, 1; jnz >2 + | mulsd xmm0, xmm0 + | shr eax, 1 + | jmp <1 + |2: + | shr eax, 1; jz >5 + | movaps xmm1, xmm0 + |3: // Handle trailing bits. + | mulsd xmm0, xmm0 + | shr eax, 1; jz >4 + | jnc <3 + | mulsd xmm1, xmm0 + | jmp <3 + |4: + | mulsd xmm0, xmm1 + |5: + | ret + |6: + | je <5 // x^1 ==> x + | jb >7 // x^0 ==> 1 + | neg eax + | call <1 + | sseconst_1 xmm1, RD + | divsd xmm1, xmm0 + | movaps xmm0, xmm1 + | ret + |7: + | sseconst_1 xmm0, RD + | ret + | + |//----------------------------------------------------------------------- + |//-- Miscellaneous functions -------------------------------------------- + |//----------------------------------------------------------------------- + | + |// int lj_vm_cpuid(uint32_t f, uint32_t res[4]) + |->vm_cpuid: + | mov eax, CARG1d + | .if X64WIN; push rsi; mov rsi, CARG2; .endif + | push rbx + | cpuid + | mov [rsi], eax + | mov [rsi+4], ebx + | mov [rsi+8], ecx + | mov [rsi+12], edx + | pop rbx + | .if X64WIN; pop rsi; .endif + | ret + | + |//----------------------------------------------------------------------- + |//-- Assertions --------------------------------------------------------- + |//----------------------------------------------------------------------- + | + |->assert_bad_for_arg_type: +#ifdef LUA_USE_ASSERT + | int3 +#endif + | int3 + | + |//----------------------------------------------------------------------- + |//-- FFI helper functions ----------------------------------------------- + |//----------------------------------------------------------------------- + | + |// Handler for callback functions. Callback slot number in ah/al. + |->vm_ffi_callback: + |.if FFI + |.type CTSTATE, CTState, PC + | saveregs_ // ebp/rbp already saved. ebp now holds global_State *. + | lea DISPATCH, [ebp+GG_G2DISP] + | mov CTSTATE, GL:ebp->ctype_state + | movzx eax, ax + | mov CTSTATE->cb.slot, eax + | mov CTSTATE->cb.gpr[0], CARG1 + | mov CTSTATE->cb.gpr[1], CARG2 + | mov CTSTATE->cb.gpr[2], CARG3 + | mov CTSTATE->cb.gpr[3], CARG4 + | movsd qword CTSTATE->cb.fpr[0], xmm0 + | movsd qword CTSTATE->cb.fpr[1], xmm1 + | movsd qword CTSTATE->cb.fpr[2], xmm2 + | movsd qword CTSTATE->cb.fpr[3], xmm3 + |.if X64WIN + | lea rax, [rsp+CFRAME_SIZE+4*8] + |.else + | lea rax, [rsp+CFRAME_SIZE] + | mov CTSTATE->cb.gpr[4], CARG5 + | mov CTSTATE->cb.gpr[5], CARG6 + | movsd qword CTSTATE->cb.fpr[4], xmm4 + | movsd qword CTSTATE->cb.fpr[5], xmm5 + | movsd qword CTSTATE->cb.fpr[6], xmm6 + | movsd qword CTSTATE->cb.fpr[7], xmm7 + |.endif + | mov CTSTATE->cb.stack, rax + | mov CARG2, rsp + | mov SAVE_PC, CTSTATE // Any value outside of bytecode is ok. + | mov CARG1, CTSTATE + | call extern lj_ccallback_enter // (CTState *cts, void *cf) + | // lua_State * returned in eax (RD). + | set_vmstate INTERP + | mov BASE, L:RD->base + | mov RD, L:RD->top + | sub RD, BASE + | mov LFUNC:RB, [BASE-16] + | cleartp LFUNC:RB + | shr RD, 3 + | add RD, 1 + | ins_callt + |.endif + | + |->cont_ffi_callback: // Return from FFI callback. + |.if FFI + | mov L:RA, SAVE_L + | mov CTSTATE, [DISPATCH+DISPATCH_GL(ctype_state)] + | mov aword CTSTATE->L, L:RA + | mov L:RA->base, BASE + | mov L:RA->top, RB + | mov CARG1, CTSTATE + | mov CARG2, RC + | call extern lj_ccallback_leave // (CTState *cts, TValue *o) + | mov rax, CTSTATE->cb.gpr[0] + | movsd xmm0, qword CTSTATE->cb.fpr[0] + | jmp ->vm_leave_unw + |.endif + | + |->vm_ffi_call: // Call C function via FFI. + | // Caveat: needs special frame unwinding, see below. + |.if FFI + | .type CCSTATE, CCallState, rbx + | push rbp; mov rbp, rsp; push rbx; mov CCSTATE, CARG1 + | + | // Readjust stack. + | mov eax, CCSTATE->spadj + | sub rsp, rax + | + | // Copy stack slots. + | movzx ecx, byte CCSTATE->nsp + | sub ecx, 1 + | js >2 + |1: + | mov rax, [CCSTATE+rcx*8+offsetof(CCallState, stack)] + | mov [rsp+rcx*8+CCALL_SPS_EXTRA*8], rax + | sub ecx, 1 + | jns <1 + |2: + | + | movzx eax, byte CCSTATE->nfpr + | mov CARG1, CCSTATE->gpr[0] + | mov CARG2, CCSTATE->gpr[1] + | mov CARG3, CCSTATE->gpr[2] + | mov CARG4, CCSTATE->gpr[3] + |.if not X64WIN + | mov CARG5, CCSTATE->gpr[4] + | mov CARG6, CCSTATE->gpr[5] + |.endif + | test eax, eax; jz >5 + | movaps xmm0, CCSTATE->fpr[0] + | movaps xmm1, CCSTATE->fpr[1] + | movaps xmm2, CCSTATE->fpr[2] + | movaps xmm3, CCSTATE->fpr[3] + |.if not X64WIN + | cmp eax, 4; jbe >5 + | movaps xmm4, CCSTATE->fpr[4] + | movaps xmm5, CCSTATE->fpr[5] + | movaps xmm6, CCSTATE->fpr[6] + | movaps xmm7, CCSTATE->fpr[7] + |.endif + |5: + | + | call aword CCSTATE->func + | + | mov CCSTATE->gpr[0], rax + | movaps CCSTATE->fpr[0], xmm0 + |.if not X64WIN + | mov CCSTATE->gpr[1], rdx + | movaps CCSTATE->fpr[1], xmm1 + |.endif + | + | mov rbx, [rbp-8]; leave; ret + |.endif + |// Note: vm_ffi_call must be the last function in this object file! + | + |//----------------------------------------------------------------------- +} + +/* Generate the code for a single instruction. */ +static void build_ins(BuildCtx *ctx, BCOp op, int defop) +{ + int vk = 0; + |// Note: aligning all instructions does not pay off. + |=>defop: + + switch (op) { + + /* -- Comparison ops ---------------------------------------------------- */ + + /* Remember: all ops branch for a true comparison, fall through otherwise. */ + + |.macro jmp_comp, lt, ge, le, gt, target + ||switch (op) { + ||case BC_ISLT: + | lt target + ||break; + ||case BC_ISGE: + | ge target + ||break; + ||case BC_ISLE: + | le target + ||break; + ||case BC_ISGT: + | gt target + ||break; + ||default: break; /* Shut up GCC. */ + ||} + |.endmacro + + case BC_ISLT: case BC_ISGE: case BC_ISLE: case BC_ISGT: + | // RA = src1, RD = src2, JMP with RD = target + | ins_AD + | mov ITYPE, [BASE+RA*8] + | mov RB, [BASE+RD*8] + | mov RA, ITYPE + | mov RD, RB + | sar ITYPE, 47 + | sar RB, 47 + |.if DUALNUM + | cmp ITYPEd, LJ_TISNUM; jne >7 + | cmp RBd, LJ_TISNUM; jne >8 + | add PC, 4 + | cmp RAd, RDd + | jmp_comp jge, jl, jg, jle, >9 + |6: + | movzx RDd, PC_RD + | branchPC RD + |9: + | ins_next + | + |7: // RA is not an integer. + | ja ->vmeta_comp + | // RA is a number. + | cmp RBd, LJ_TISNUM; jb >1; jne ->vmeta_comp + | // RA is a number, RD is an integer. + | cvtsi2sd xmm0, RDd + | jmp >2 + | + |8: // RA is an integer, RD is not an integer. + | ja ->vmeta_comp + | // RA is an integer, RD is a number. + | cvtsi2sd xmm1, RAd + | movd xmm0, RD + | jmp >3 + |.else + | cmp ITYPEd, LJ_TISNUM; jae ->vmeta_comp + | cmp RBd, LJ_TISNUM; jae ->vmeta_comp + |.endif + |1: + | movd xmm0, RD + |2: + | movd xmm1, RA + |3: + | add PC, 4 + | ucomisd xmm0, xmm1 + | // Unordered: all of ZF CF PF set, ordered: PF clear. + | // To preserve NaN semantics GE/GT branch on unordered, but LT/LE don't. + |.if DUALNUM + | jmp_comp jbe, ja, jb, jae, <9 + | jmp <6 + |.else + | jmp_comp jbe, ja, jb, jae, >1 + | movzx RDd, PC_RD + | branchPC RD + |1: + | ins_next + |.endif + break; + + case BC_ISEQV: case BC_ISNEV: + vk = op == BC_ISEQV; + | ins_AD // RA = src1, RD = src2, JMP with RD = target + | mov RB, [BASE+RD*8] + | mov ITYPE, [BASE+RA*8] + | add PC, 4 + | mov RD, RB + | mov RA, ITYPE + | sar RB, 47 + | sar ITYPE, 47 + |.if DUALNUM + | cmp RBd, LJ_TISNUM; jne >7 + | cmp ITYPEd, LJ_TISNUM; jne >8 + | cmp RDd, RAd + if (vk) { + | jne >9 + } else { + | je >9 + } + | movzx RDd, PC_RD + | branchPC RD + |9: + | ins_next + | + |7: // RD is not an integer. + | ja >5 + | // RD is a number. + | movd xmm1, RD + | cmp ITYPEd, LJ_TISNUM; jb >1; jne >5 + | // RD is a number, RA is an integer. + | cvtsi2sd xmm0, RAd + | jmp >2 + | + |8: // RD is an integer, RA is not an integer. + | ja >5 + | // RD is an integer, RA is a number. + | cvtsi2sd xmm1, RDd + | jmp >1 + | + |.else + | cmp RBd, LJ_TISNUM; jae >5 + | cmp ITYPEd, LJ_TISNUM; jae >5 + | movd xmm1, RD + |.endif + |1: + | movd xmm0, RA + |2: + | ucomisd xmm0, xmm1 + |4: + iseqne_fp: + if (vk) { + | jp >2 // Unordered means not equal. + | jne >2 + } else { + | jp >2 // Unordered means not equal. + | je >1 + } + iseqne_end: + if (vk) { + |1: // EQ: Branch to the target. + | movzx RDd, PC_RD + | branchPC RD + |2: // NE: Fallthrough to next instruction. + |.if not FFI + |3: + |.endif + } else { + |.if not FFI + |3: + |.endif + |2: // NE: Branch to the target. + | movzx RDd, PC_RD + | branchPC RD + |1: // EQ: Fallthrough to next instruction. + } + if (LJ_DUALNUM && (op == BC_ISEQV || op == BC_ISNEV || + op == BC_ISEQN || op == BC_ISNEN)) { + | jmp <9 + } else { + | ins_next + } + | + if (op == BC_ISEQV || op == BC_ISNEV) { + |5: // Either or both types are not numbers. + |.if FFI + | cmp RBd, LJ_TCDATA; je ->vmeta_equal_cd + | cmp ITYPEd, LJ_TCDATA; je ->vmeta_equal_cd + |.endif + | cmp RA, RD + | je <1 // Same GCobjs or pvalues? + | cmp RBd, ITYPEd + | jne <2 // Not the same type? + | cmp RBd, LJ_TISTABUD + | ja <2 // Different objects and not table/ud? + | + | // Different tables or userdatas. Need to check __eq metamethod. + | // Field metatable must be at same offset for GCtab and GCudata! + | cleartp TAB:RA + | mov TAB:RB, TAB:RA->metatable + | test TAB:RB, TAB:RB + | jz <2 // No metatable? + | test byte TAB:RB->nomm, 1<<MM_eq + | jnz <2 // Or 'no __eq' flag set? + if (vk) { + | xor RBd, RBd // ne = 0 + } else { + | mov RBd, 1 // ne = 1 + } + | jmp ->vmeta_equal // Handle __eq metamethod. + } else { + |.if FFI + |3: + | cmp ITYPEd, LJ_TCDATA + if (LJ_DUALNUM && vk) { + | jne <9 + } else { + | jne <2 + } + | jmp ->vmeta_equal_cd + |.endif + } + break; + case BC_ISEQS: case BC_ISNES: + vk = op == BC_ISEQS; + | ins_AND // RA = src, RD = str const, JMP with RD = target + | mov RB, [BASE+RA*8] + | add PC, 4 + | checkstr RB, >3 + | cmp RB, [KBASE+RD*8] + iseqne_test: + if (vk) { + | jne >2 + } else { + | je >1 + } + goto iseqne_end; + case BC_ISEQN: case BC_ISNEN: + vk = op == BC_ISEQN; + | ins_AD // RA = src, RD = num const, JMP with RD = target + | mov RB, [BASE+RA*8] + | add PC, 4 + |.if DUALNUM + | checkint RB, >7 + | mov RD, [KBASE+RD*8] + | checkint RD, >8 + | cmp RBd, RDd + if (vk) { + | jne >9 + } else { + | je >9 + } + | movzx RDd, PC_RD + | branchPC RD + |9: + | ins_next + | + |7: // RA is not an integer. + | ja >3 + | // RA is a number. + | mov RD, [KBASE+RD*8] + | checkint RD, >1 + | // RA is a number, RD is an integer. + | cvtsi2sd xmm0, RDd + | jmp >2 + | + |8: // RA is an integer, RD is a number. + | cvtsi2sd xmm0, RBd + | movd xmm1, RD + | ucomisd xmm0, xmm1 + | jmp >4 + |1: + | movd xmm0, RD + |.else + | checknum RB, >3 + |1: + | movsd xmm0, qword [KBASE+RD*8] + |.endif + |2: + | ucomisd xmm0, qword [BASE+RA*8] + |4: + goto iseqne_fp; + case BC_ISEQP: case BC_ISNEP: + vk = op == BC_ISEQP; + | ins_AND // RA = src, RD = primitive type (~), JMP with RD = target + | mov RB, [BASE+RA*8] + | sar RB, 47 + | add PC, 4 + | cmp RBd, RDd + if (!LJ_HASFFI) goto iseqne_test; + if (vk) { + | jne >3 + | movzx RDd, PC_RD + | branchPC RD + |2: + | ins_next + |3: + | cmp RBd, LJ_TCDATA; jne <2 + | jmp ->vmeta_equal_cd + } else { + | je >2 + | cmp RBd, LJ_TCDATA; je ->vmeta_equal_cd + | movzx RDd, PC_RD + | branchPC RD + |2: + | ins_next + } + break; + + /* -- Unary test and copy ops ------------------------------------------- */ + + case BC_ISTC: case BC_ISFC: case BC_IST: case BC_ISF: + | ins_AD // RA = dst or unused, RD = src, JMP with RD = target + | mov ITYPE, [BASE+RD*8] + | add PC, 4 + if (op == BC_ISTC || op == BC_ISFC) { + | mov RB, ITYPE + } + | sar ITYPE, 47 + | cmp ITYPEd, LJ_TISTRUECOND + if (op == BC_IST || op == BC_ISTC) { + | jae >1 + } else { + | jb >1 + } + if (op == BC_ISTC || op == BC_ISFC) { + | mov [BASE+RA*8], RB + } + | movzx RDd, PC_RD + | branchPC RD + |1: // Fallthrough to the next instruction. + | ins_next + break; + + case BC_ISTYPE: + | ins_AD // RA = src, RD = -type + | mov RB, [BASE+RA*8] + | sar RB, 47 + | add RBd, RDd + | jne ->vmeta_istype + | ins_next + break; + case BC_ISNUM: + | ins_AD // RA = src, RD = -(TISNUM-1) + | checknumtp [BASE+RA*8], ->vmeta_istype + | ins_next + break; + + /* -- Unary ops --------------------------------------------------------- */ + + case BC_MOV: + | ins_AD // RA = dst, RD = src + | mov RB, [BASE+RD*8] + | mov [BASE+RA*8], RB + | ins_next_ + break; + case BC_NOT: + | ins_AD // RA = dst, RD = src + | mov RB, [BASE+RD*8] + | sar RB, 47 + | mov RCd, 2 + | cmp RB, LJ_TISTRUECOND + | sbb RCd, 0 + | shl RC, 47 + | not RC + | mov [BASE+RA*8], RC + | ins_next + break; + case BC_UNM: + | ins_AD // RA = dst, RD = src + | mov RB, [BASE+RD*8] + |.if DUALNUM + | checkint RB, >5 + | neg RBd + | jo >4 + | setint RB + |9: + | mov [BASE+RA*8], RB + | ins_next + |4: + | mov64 RB, U64x(41e00000,00000000) // 2^31. + | jmp <9 + |5: + | ja ->vmeta_unm + |.else + | checknum RB, ->vmeta_unm + |.endif + | mov64 RD, U64x(80000000,00000000) + | xor RB, RD + |.if DUALNUM + | jmp <9 + |.else + | mov [BASE+RA*8], RB + | ins_next + |.endif + break; + case BC_LEN: + | ins_AD // RA = dst, RD = src + | mov RD, [BASE+RD*8] + | checkstr RD, >2 + |.if DUALNUM + | mov RDd, dword STR:RD->len + |1: + | setint RD + | mov [BASE+RA*8], RD + |.else + | xorps xmm0, xmm0 + | cvtsi2sd xmm0, dword STR:RD->len + |1: + | movsd qword [BASE+RA*8], xmm0 + |.endif + | ins_next + |2: + | cmp ITYPEd, LJ_TTAB; jne ->vmeta_len + | mov TAB:CARG1, TAB:RD +#if LJ_52 + | mov TAB:RB, TAB:RD->metatable + | cmp TAB:RB, 0 + | jnz >9 + |3: +#endif + |->BC_LEN_Z: + | mov RB, BASE // Save BASE. + | call extern lj_tab_len // (GCtab *t) + | // Length of table returned in eax (RD). + |.if DUALNUM + | // Nothing to do. + |.else + | cvtsi2sd xmm0, RDd + |.endif + | mov BASE, RB // Restore BASE. + | movzx RAd, PC_RA + | jmp <1 +#if LJ_52 + |9: // Check for __len. + | test byte TAB:RB->nomm, 1<<MM_len + | jnz <3 + | jmp ->vmeta_len // 'no __len' flag NOT set: check. +#endif + break; + + /* -- Binary ops -------------------------------------------------------- */ + + |.macro ins_arithpre, sseins, ssereg + | ins_ABC + ||vk = ((int)op - BC_ADDVN) / (BC_ADDNV-BC_ADDVN); + ||switch (vk) { + ||case 0: + | checknumtp [BASE+RB*8], ->vmeta_arith_vn + | .if DUALNUM + | checknumtp [KBASE+RC*8], ->vmeta_arith_vn + | .endif + | movsd xmm0, qword [BASE+RB*8] + | sseins ssereg, qword [KBASE+RC*8] + || break; + ||case 1: + | checknumtp [BASE+RB*8], ->vmeta_arith_nv + | .if DUALNUM + | checknumtp [KBASE+RC*8], ->vmeta_arith_nv + | .endif + | movsd xmm0, qword [KBASE+RC*8] + | sseins ssereg, qword [BASE+RB*8] + || break; + ||default: + | checknumtp [BASE+RB*8], ->vmeta_arith_vv + | checknumtp [BASE+RC*8], ->vmeta_arith_vv + | movsd xmm0, qword [BASE+RB*8] + | sseins ssereg, qword [BASE+RC*8] + || break; + ||} + |.endmacro + | + |.macro ins_arithdn, intins + | ins_ABC + ||vk = ((int)op - BC_ADDVN) / (BC_ADDNV-BC_ADDVN); + ||switch (vk) { + ||case 0: + | mov RB, [BASE+RB*8] + | mov RC, [KBASE+RC*8] + | checkint RB, ->vmeta_arith_vno + | checkint RC, ->vmeta_arith_vno + | intins RBd, RCd; jo ->vmeta_arith_vno + || break; + ||case 1: + | mov RB, [BASE+RB*8] + | mov RC, [KBASE+RC*8] + | checkint RB, ->vmeta_arith_nvo + | checkint RC, ->vmeta_arith_nvo + | intins RCd, RBd; jo ->vmeta_arith_nvo + || break; + ||default: + | mov RB, [BASE+RB*8] + | mov RC, [BASE+RC*8] + | checkint RB, ->vmeta_arith_vvo + | checkint RC, ->vmeta_arith_vvo + | intins RBd, RCd; jo ->vmeta_arith_vvo + || break; + ||} + ||if (vk == 1) { + | setint RC + | mov [BASE+RA*8], RC + ||} else { + | setint RB + | mov [BASE+RA*8], RB + ||} + | ins_next + |.endmacro + | + |.macro ins_arithpost + | movsd qword [BASE+RA*8], xmm0 + |.endmacro + | + |.macro ins_arith, sseins + | ins_arithpre sseins, xmm0 + | ins_arithpost + | ins_next + |.endmacro + | + |.macro ins_arith, intins, sseins + |.if DUALNUM + | ins_arithdn intins + |.else + | ins_arith, sseins + |.endif + |.endmacro + + | // RA = dst, RB = src1 or num const, RC = src2 or num const + case BC_ADDVN: case BC_ADDNV: case BC_ADDVV: + | ins_arith add, addsd + break; + case BC_SUBVN: case BC_SUBNV: case BC_SUBVV: + | ins_arith sub, subsd + break; + case BC_MULVN: case BC_MULNV: case BC_MULVV: + | ins_arith imul, mulsd + break; + case BC_DIVVN: case BC_DIVNV: case BC_DIVVV: + | ins_arith divsd + break; + case BC_MODVN: + | ins_arithpre movsd, xmm1 + |->BC_MODVN_Z: + | call ->vm_mod + | ins_arithpost + | ins_next + break; + case BC_MODNV: case BC_MODVV: + | ins_arithpre movsd, xmm1 + | jmp ->BC_MODVN_Z // Avoid 3 copies. It's slow anyway. + break; + case BC_POW: + | ins_arithpre movsd, xmm1 + | mov RB, BASE + | call extern pow + | movzx RAd, PC_RA + | mov BASE, RB + | ins_arithpost + | ins_next + break; + + case BC_CAT: + | ins_ABC // RA = dst, RB = src_start, RC = src_end + | mov L:CARG1, SAVE_L + | mov L:CARG1->base, BASE + | lea CARG2, [BASE+RC*8] + | mov CARG3d, RCd + | sub CARG3d, RBd + |->BC_CAT_Z: + | mov L:RB, L:CARG1 + | mov SAVE_PC, PC + | call extern lj_meta_cat // (lua_State *L, TValue *top, int left) + | // NULL (finished) or TValue * (metamethod) returned in eax (RC). + | mov BASE, L:RB->base + | test RC, RC + | jnz ->vmeta_binop + | movzx RBd, PC_RB // Copy result to Stk[RA] from Stk[RB]. + | movzx RAd, PC_RA + | mov RC, [BASE+RB*8] + | mov [BASE+RA*8], RC + | ins_next + break; + + /* -- Constant ops ------------------------------------------------------ */ + + case BC_KSTR: + | ins_AND // RA = dst, RD = str const (~) + | mov RD, [KBASE+RD*8] + | settp RD, LJ_TSTR + | mov [BASE+RA*8], RD + | ins_next + break; + case BC_KCDATA: + |.if FFI + | ins_AND // RA = dst, RD = cdata const (~) + | mov RD, [KBASE+RD*8] + | settp RD, LJ_TCDATA + | mov [BASE+RA*8], RD + | ins_next + |.endif + break; + case BC_KSHORT: + | ins_AD // RA = dst, RD = signed int16 literal + |.if DUALNUM + | movsx RDd, RDW + | setint RD + | mov [BASE+RA*8], RD + |.else + | movsx RDd, RDW // Sign-extend literal. + | cvtsi2sd xmm0, RDd + | movsd qword [BASE+RA*8], xmm0 + |.endif + | ins_next + break; + case BC_KNUM: + | ins_AD // RA = dst, RD = num const + | movsd xmm0, qword [KBASE+RD*8] + | movsd qword [BASE+RA*8], xmm0 + | ins_next + break; + case BC_KPRI: + | ins_AD // RA = dst, RD = primitive type (~) + | shl RD, 47 + | not RD + | mov [BASE+RA*8], RD + | ins_next + break; + case BC_KNIL: + | ins_AD // RA = dst_start, RD = dst_end + | lea RA, [BASE+RA*8+8] + | lea RD, [BASE+RD*8] + | mov RB, LJ_TNIL + | mov [RA-8], RB // Sets minimum 2 slots. + |1: + | mov [RA], RB + | add RA, 8 + | cmp RA, RD + | jbe <1 + | ins_next + break; + + /* -- Upvalue and function ops ------------------------------------------ */ + + case BC_UGET: + | ins_AD // RA = dst, RD = upvalue # + | mov LFUNC:RB, [BASE-16] + | cleartp LFUNC:RB + | mov UPVAL:RB, [LFUNC:RB+RD*8+offsetof(GCfuncL, uvptr)] + | mov RB, UPVAL:RB->v + | mov RD, [RB] + | mov [BASE+RA*8], RD + | ins_next + break; + case BC_USETV: +#define TV2MARKOFS \ + ((int32_t)offsetof(GCupval, marked)-(int32_t)offsetof(GCupval, tv)) + | ins_AD // RA = upvalue #, RD = src + | mov LFUNC:RB, [BASE-16] + | cleartp LFUNC:RB + | mov UPVAL:RB, [LFUNC:RB+RA*8+offsetof(GCfuncL, uvptr)] + | cmp byte UPVAL:RB->closed, 0 + | mov RB, UPVAL:RB->v + | mov RA, [BASE+RD*8] + | mov [RB], RA + | jz >1 + | // Check barrier for closed upvalue. + | test byte [RB+TV2MARKOFS], LJ_GC_BLACK // isblack(uv) + | jnz >2 + |1: + | ins_next + | + |2: // Upvalue is black. Check if new value is collectable and white. + | mov RD, RA + | sar RD, 47 + | sub RDd, LJ_TISGCV + | cmp RDd, LJ_TNUMX - LJ_TISGCV // tvisgcv(v) + | jbe <1 + | cleartp GCOBJ:RA + | test byte GCOBJ:RA->gch.marked, LJ_GC_WHITES // iswhite(v) + | jz <1 + | // Crossed a write barrier. Move the barrier forward. + |.if not X64WIN + | mov CARG2, RB + | mov RB, BASE // Save BASE. + |.else + | xchg CARG2, RB // Save BASE (CARG2 == BASE). + |.endif + | lea GL:CARG1, [DISPATCH+GG_DISP2G] + | call extern lj_gc_barrieruv // (global_State *g, TValue *tv) + | mov BASE, RB // Restore BASE. + | jmp <1 + break; +#undef TV2MARKOFS + case BC_USETS: + | ins_AND // RA = upvalue #, RD = str const (~) + | mov LFUNC:RB, [BASE-16] + | cleartp LFUNC:RB + | mov UPVAL:RB, [LFUNC:RB+RA*8+offsetof(GCfuncL, uvptr)] + | mov STR:RA, [KBASE+RD*8] + | mov RD, UPVAL:RB->v + | settp STR:ITYPE, STR:RA, LJ_TSTR + | mov [RD], STR:ITYPE + | test byte UPVAL:RB->marked, LJ_GC_BLACK // isblack(uv) + | jnz >2 + |1: + | ins_next + | + |2: // Check if string is white and ensure upvalue is closed. + | test byte GCOBJ:RA->gch.marked, LJ_GC_WHITES // iswhite(str) + | jz <1 + | cmp byte UPVAL:RB->closed, 0 + | jz <1 + | // Crossed a write barrier. Move the barrier forward. + | mov RB, BASE // Save BASE (CARG2 == BASE). + | mov CARG2, RD + | lea GL:CARG1, [DISPATCH+GG_DISP2G] + | call extern lj_gc_barrieruv // (global_State *g, TValue *tv) + | mov BASE, RB // Restore BASE. + | jmp <1 + break; + case BC_USETN: + | ins_AD // RA = upvalue #, RD = num const + | mov LFUNC:RB, [BASE-16] + | cleartp LFUNC:RB + | movsd xmm0, qword [KBASE+RD*8] + | mov UPVAL:RB, [LFUNC:RB+RA*8+offsetof(GCfuncL, uvptr)] + | mov RA, UPVAL:RB->v + | movsd qword [RA], xmm0 + | ins_next + break; + case BC_USETP: + | ins_AD // RA = upvalue #, RD = primitive type (~) + | mov LFUNC:RB, [BASE-16] + | cleartp LFUNC:RB + | mov UPVAL:RB, [LFUNC:RB+RA*8+offsetof(GCfuncL, uvptr)] + | shl RD, 47 + | not RD + | mov RA, UPVAL:RB->v + | mov [RA], RD + | ins_next + break; + case BC_UCLO: + | ins_AD // RA = level, RD = target + | branchPC RD // Do this first to free RD. + | mov L:RB, SAVE_L + | cmp dword L:RB->openupval, 0 + | je >1 + | mov L:RB->base, BASE + | lea CARG2, [BASE+RA*8] // Caveat: CARG2 == BASE + | mov L:CARG1, L:RB // Caveat: CARG1 == RA + | call extern lj_func_closeuv // (lua_State *L, TValue *level) + | mov BASE, L:RB->base + |1: + | ins_next + break; + + case BC_FNEW: + | ins_AND // RA = dst, RD = proto const (~) (holding function prototype) + | mov L:RB, SAVE_L + | mov L:RB->base, BASE // Caveat: CARG2/CARG3 may be BASE. + | mov CARG3, [BASE-16] + | cleartp CARG3 + | mov CARG2, [KBASE+RD*8] // Fetch GCproto *. + | mov CARG1, L:RB + | mov SAVE_PC, PC + | // (lua_State *L, GCproto *pt, GCfuncL *parent) + | call extern lj_func_newL_gc + | // GCfuncL * returned in eax (RC). + | mov BASE, L:RB->base + | movzx RAd, PC_RA + | settp LFUNC:RC, LJ_TFUNC + | mov [BASE+RA*8], LFUNC:RC + | ins_next + break; + + /* -- Table ops --------------------------------------------------------- */ + + case BC_TNEW: + | ins_AD // RA = dst, RD = hbits|asize + | mov L:RB, SAVE_L + | mov L:RB->base, BASE + | mov RA, [DISPATCH+DISPATCH_GL(gc.total)] + | cmp RA, [DISPATCH+DISPATCH_GL(gc.threshold)] + | mov SAVE_PC, PC + | jae >5 + |1: + | mov CARG3d, RDd + | and RDd, 0x7ff + | shr CARG3d, 11 + | cmp RDd, 0x7ff + | je >3 + |2: + | mov L:CARG1, L:RB + | mov CARG2d, RDd + | call extern lj_tab_new // (lua_State *L, int32_t asize, uint32_t hbits) + | // Table * returned in eax (RC). + | mov BASE, L:RB->base + | movzx RAd, PC_RA + | settp TAB:RC, LJ_TTAB + | mov [BASE+RA*8], TAB:RC + | ins_next + |3: // Turn 0x7ff into 0x801. + | mov RDd, 0x801 + | jmp <2 + |5: + | mov L:CARG1, L:RB + | call extern lj_gc_step_fixtop // (lua_State *L) + | movzx RDd, PC_RD + | jmp <1 + break; + case BC_TDUP: + | ins_AND // RA = dst, RD = table const (~) (holding template table) + | mov L:RB, SAVE_L + | mov RA, [DISPATCH+DISPATCH_GL(gc.total)] + | mov SAVE_PC, PC + | cmp RA, [DISPATCH+DISPATCH_GL(gc.threshold)] + | mov L:RB->base, BASE + | jae >3 + |2: + | mov TAB:CARG2, [KBASE+RD*8] // Caveat: CARG2 == BASE + | mov L:CARG1, L:RB // Caveat: CARG1 == RA + | call extern lj_tab_dup // (lua_State *L, Table *kt) + | // Table * returned in eax (RC). + | mov BASE, L:RB->base + | movzx RAd, PC_RA + | settp TAB:RC, LJ_TTAB + | mov [BASE+RA*8], TAB:RC + | ins_next + |3: + | mov L:CARG1, L:RB + | call extern lj_gc_step_fixtop // (lua_State *L) + | movzx RDd, PC_RD // Need to reload RD. + | not RD + | jmp <2 + break; + + case BC_GGET: + | ins_AND // RA = dst, RD = str const (~) + | mov LFUNC:RB, [BASE-16] + | cleartp LFUNC:RB + | mov TAB:RB, LFUNC:RB->env + | mov STR:RC, [KBASE+RD*8] + | jmp ->BC_TGETS_Z + break; + case BC_GSET: + | ins_AND // RA = src, RD = str const (~) + | mov LFUNC:RB, [BASE-16] + | cleartp LFUNC:RB + | mov TAB:RB, LFUNC:RB->env + | mov STR:RC, [KBASE+RD*8] + | jmp ->BC_TSETS_Z + break; + + case BC_TGETV: + | ins_ABC // RA = dst, RB = table, RC = key + | mov TAB:RB, [BASE+RB*8] + | mov RC, [BASE+RC*8] + | checktab TAB:RB, ->vmeta_tgetv + | + | // Integer key? + |.if DUALNUM + | checkint RC, >5 + |.else + | // Convert number to int and back and compare. + | checknum RC, >5 + | movd xmm0, RC + | cvttsd2si RCd, xmm0 + | cvtsi2sd xmm1, RCd + | ucomisd xmm0, xmm1 + | jne ->vmeta_tgetv // Generic numeric key? Use fallback. + |.endif + | cmp RCd, TAB:RB->asize // Takes care of unordered, too. + | jae ->vmeta_tgetv // Not in array part? Use fallback. + | shl RCd, 3 + | add RC, TAB:RB->array + | // Get array slot. + | mov ITYPE, [RC] + | cmp ITYPE, LJ_TNIL // Avoid overwriting RB in fastpath. + | je >2 + |1: + | mov [BASE+RA*8], ITYPE + | ins_next + | + |2: // Check for __index if table value is nil. + | mov TAB:TMPR, TAB:RB->metatable + | test TAB:TMPR, TAB:TMPR + | jz <1 + | test byte TAB:TMPR->nomm, 1<<MM_index + | jz ->vmeta_tgetv // 'no __index' flag NOT set: check. + | jmp <1 + | + |5: // String key? + | cmp ITYPEd, LJ_TSTR; jne ->vmeta_tgetv + | cleartp STR:RC + | jmp ->BC_TGETS_Z + break; + case BC_TGETS: + | ins_ABC // RA = dst, RB = table, RC = str const (~) + | mov TAB:RB, [BASE+RB*8] + | not RC + | mov STR:RC, [KBASE+RC*8] + | checktab TAB:RB, ->vmeta_tgets + |->BC_TGETS_Z: // RB = GCtab *, RC = GCstr * + | mov TMPRd, TAB:RB->hmask + | and TMPRd, STR:RC->hash + | imul TMPRd, #NODE + | add NODE:TMPR, TAB:RB->node + | settp ITYPE, STR:RC, LJ_TSTR + |1: + | cmp NODE:TMPR->key, ITYPE + | jne >4 + | // Get node value. + | mov ITYPE, NODE:TMPR->val + | cmp ITYPE, LJ_TNIL + | je >5 // Key found, but nil value? + |2: + | mov [BASE+RA*8], ITYPE + | ins_next + | + |4: // Follow hash chain. + | mov NODE:TMPR, NODE:TMPR->next + | test NODE:TMPR, NODE:TMPR + | jnz <1 + | // End of hash chain: key not found, nil result. + | mov ITYPE, LJ_TNIL + | + |5: // Check for __index if table value is nil. + | mov TAB:TMPR, TAB:RB->metatable + | test TAB:TMPR, TAB:TMPR + | jz <2 // No metatable: done. + | test byte TAB:TMPR->nomm, 1<<MM_index + | jnz <2 // 'no __index' flag set: done. + | jmp ->vmeta_tgets // Caveat: preserve STR:RC. + break; + case BC_TGETB: + | ins_ABC // RA = dst, RB = table, RC = byte literal + | mov TAB:RB, [BASE+RB*8] + | checktab TAB:RB, ->vmeta_tgetb + | cmp RCd, TAB:RB->asize + | jae ->vmeta_tgetb + | shl RCd, 3 + | add RC, TAB:RB->array + | // Get array slot. + | mov ITYPE, [RC] + | cmp ITYPE, LJ_TNIL + | je >2 + |1: + | mov [BASE+RA*8], ITYPE + | ins_next + | + |2: // Check for __index if table value is nil. + | mov TAB:TMPR, TAB:RB->metatable + | test TAB:TMPR, TAB:TMPR + | jz <1 + | test byte TAB:TMPR->nomm, 1<<MM_index + | jz ->vmeta_tgetb // 'no __index' flag NOT set: check. + | jmp <1 + break; + case BC_TGETR: + | ins_ABC // RA = dst, RB = table, RC = key + | mov TAB:RB, [BASE+RB*8] + | cleartp TAB:RB + |.if DUALNUM + | mov RCd, dword [BASE+RC*8] + |.else + | cvttsd2si RCd, qword [BASE+RC*8] + |.endif + | cmp RCd, TAB:RB->asize + | jae ->vmeta_tgetr // Not in array part? Use fallback. + | shl RCd, 3 + | add RC, TAB:RB->array + | // Get array slot. + |->BC_TGETR_Z: + | mov ITYPE, [RC] + |->BC_TGETR2_Z: + | mov [BASE+RA*8], ITYPE + | ins_next + break; + + case BC_TSETV: + | ins_ABC // RA = src, RB = table, RC = key + | mov TAB:RB, [BASE+RB*8] + | mov RC, [BASE+RC*8] + | checktab TAB:RB, ->vmeta_tsetv + | + | // Integer key? + |.if DUALNUM + | checkint RC, >5 + |.else + | // Convert number to int and back and compare. + | checknum RC, >5 + | movd xmm0, RC + | cvttsd2si RCd, xmm0 + | cvtsi2sd xmm1, RCd + | ucomisd xmm0, xmm1 + | jne ->vmeta_tsetv // Generic numeric key? Use fallback. + |.endif + | cmp RCd, TAB:RB->asize // Takes care of unordered, too. + | jae ->vmeta_tsetv + | shl RCd, 3 + | add RC, TAB:RB->array + | cmp aword [RC], LJ_TNIL + | je >3 // Previous value is nil? + |1: + | test byte TAB:RB->marked, LJ_GC_BLACK // isblack(table) + | jnz >7 + |2: // Set array slot. + | mov RB, [BASE+RA*8] + | mov [RC], RB + | ins_next + | + |3: // Check for __newindex if previous value is nil. + | mov TAB:TMPR, TAB:RB->metatable + | test TAB:TMPR, TAB:TMPR + | jz <1 + | test byte TAB:TMPR->nomm, 1<<MM_newindex + | jz ->vmeta_tsetv // 'no __newindex' flag NOT set: check. + | jmp <1 + | + |5: // String key? + | cmp ITYPEd, LJ_TSTR; jne ->vmeta_tsetv + | cleartp STR:RC + | jmp ->BC_TSETS_Z + | + |7: // Possible table write barrier for the value. Skip valiswhite check. + | barrierback TAB:RB, TMPR + | jmp <2 + break; + case BC_TSETS: + | ins_ABC // RA = src, RB = table, RC = str const (~) + | mov TAB:RB, [BASE+RB*8] + | not RC + | mov STR:RC, [KBASE+RC*8] + | checktab TAB:RB, ->vmeta_tsets + |->BC_TSETS_Z: // RB = GCtab *, RC = GCstr * + | mov TMPRd, TAB:RB->hmask + | and TMPRd, STR:RC->hash + | imul TMPRd, #NODE + | mov byte TAB:RB->nomm, 0 // Clear metamethod cache. + | add NODE:TMPR, TAB:RB->node + | settp ITYPE, STR:RC, LJ_TSTR + |1: + | cmp NODE:TMPR->key, ITYPE + | jne >5 + | // Ok, key found. Assumes: offsetof(Node, val) == 0 + | cmp aword [TMPR], LJ_TNIL + | je >4 // Previous value is nil? + |2: + | test byte TAB:RB->marked, LJ_GC_BLACK // isblack(table) + | jnz >7 + |3: // Set node value. + | mov ITYPE, [BASE+RA*8] + | mov [TMPR], ITYPE + | ins_next + | + |4: // Check for __newindex if previous value is nil. + | mov TAB:ITYPE, TAB:RB->metatable + | test TAB:ITYPE, TAB:ITYPE + | jz <2 + | test byte TAB:ITYPE->nomm, 1<<MM_newindex + | jz ->vmeta_tsets // 'no __newindex' flag NOT set: check. + | jmp <2 + | + |5: // Follow hash chain. + | mov NODE:TMPR, NODE:TMPR->next + | test NODE:TMPR, NODE:TMPR + | jnz <1 + | // End of hash chain: key not found, add a new one. + | + | // But check for __newindex first. + | mov TAB:TMPR, TAB:RB->metatable + | test TAB:TMPR, TAB:TMPR + | jz >6 // No metatable: continue. + | test byte TAB:TMPR->nomm, 1<<MM_newindex + | jz ->vmeta_tsets // 'no __newindex' flag NOT set: check. + |6: + | mov TMP1, ITYPE + | mov L:CARG1, SAVE_L + | mov L:CARG1->base, BASE + | lea CARG3, TMP1 + | mov CARG2, TAB:RB + | mov SAVE_PC, PC + | call extern lj_tab_newkey // (lua_State *L, GCtab *t, TValue *k) + | // Handles write barrier for the new key. TValue * returned in eax (RC). + | mov L:CARG1, SAVE_L + | mov BASE, L:CARG1->base + | mov TMPR, rax + | movzx RAd, PC_RA + | jmp <2 // Must check write barrier for value. + | + |7: // Possible table write barrier for the value. Skip valiswhite check. + | barrierback TAB:RB, ITYPE + | jmp <3 + break; + case BC_TSETB: + | ins_ABC // RA = src, RB = table, RC = byte literal + | mov TAB:RB, [BASE+RB*8] + | checktab TAB:RB, ->vmeta_tsetb + | cmp RCd, TAB:RB->asize + | jae ->vmeta_tsetb + | shl RCd, 3 + | add RC, TAB:RB->array + | cmp aword [RC], LJ_TNIL + | je >3 // Previous value is nil? + |1: + | test byte TAB:RB->marked, LJ_GC_BLACK // isblack(table) + | jnz >7 + |2: // Set array slot. + | mov ITYPE, [BASE+RA*8] + | mov [RC], ITYPE + | ins_next + | + |3: // Check for __newindex if previous value is nil. + | mov TAB:TMPR, TAB:RB->metatable + | test TAB:TMPR, TAB:TMPR + | jz <1 + | test byte TAB:TMPR->nomm, 1<<MM_newindex + | jz ->vmeta_tsetb // 'no __newindex' flag NOT set: check. + | jmp <1 + | + |7: // Possible table write barrier for the value. Skip valiswhite check. + | barrierback TAB:RB, TMPR + | jmp <2 + break; + case BC_TSETR: + | ins_ABC // RA = src, RB = table, RC = key + | mov TAB:RB, [BASE+RB*8] + | cleartp TAB:RB + |.if DUALNUM + | mov RC, [BASE+RC*8] + |.else + | cvttsd2si RCd, qword [BASE+RC*8] + |.endif + | test byte TAB:RB->marked, LJ_GC_BLACK // isblack(table) + | jnz >7 + |2: + | cmp RCd, TAB:RB->asize + | jae ->vmeta_tsetr + | shl RCd, 3 + | add RC, TAB:RB->array + | // Set array slot. + |->BC_TSETR_Z: + | mov ITYPE, [BASE+RA*8] + | mov [RC], ITYPE + | ins_next + | + |7: // Possible table write barrier for the value. Skip valiswhite check. + | barrierback TAB:RB, TMPR + | jmp <2 + break; + + case BC_TSETM: + | ins_AD // RA = base (table at base-1), RD = num const (start index) + |1: + | mov TMPRd, dword [KBASE+RD*8] // Integer constant is in lo-word. + | lea RA, [BASE+RA*8] + | mov TAB:RB, [RA-8] // Guaranteed to be a table. + | cleartp TAB:RB + | test byte TAB:RB->marked, LJ_GC_BLACK // isblack(table) + | jnz >7 + |2: + | mov RDd, MULTRES + | sub RDd, 1 + | jz >4 // Nothing to copy? + | add RDd, TMPRd // Compute needed size. + | cmp RDd, TAB:RB->asize + | ja >5 // Doesn't fit into array part? + | sub RDd, TMPRd + | shl TMPRd, 3 + | add TMPR, TAB:RB->array + |3: // Copy result slots to table. + | mov RB, [RA] + | add RA, 8 + | mov [TMPR], RB + | add TMPR, 8 + | sub RDd, 1 + | jnz <3 + |4: + | ins_next + | + |5: // Need to resize array part. + | mov L:CARG1, SAVE_L + | mov L:CARG1->base, BASE // Caveat: CARG2/CARG3 may be BASE. + | mov CARG2, TAB:RB + | mov CARG3d, RDd + | mov L:RB, L:CARG1 + | mov SAVE_PC, PC + | call extern lj_tab_reasize // (lua_State *L, GCtab *t, int nasize) + | mov BASE, L:RB->base + | movzx RAd, PC_RA // Restore RA. + | movzx RDd, PC_RD // Restore RD. + | jmp <1 // Retry. + | + |7: // Possible table write barrier for any value. Skip valiswhite check. + | barrierback TAB:RB, RD + | jmp <2 + break; + + /* -- Calls and vararg handling ----------------------------------------- */ + + case BC_CALL: case BC_CALLM: + | ins_A_C // RA = base, (RB = nresults+1,) RC = nargs+1 | extra_nargs + if (op == BC_CALLM) { + | add NARGS:RDd, MULTRES + } + | mov LFUNC:RB, [BASE+RA*8] + | checkfunc LFUNC:RB, ->vmeta_call_ra + | lea BASE, [BASE+RA*8+16] + | ins_call + break; + + case BC_CALLMT: + | ins_AD // RA = base, RD = extra_nargs + | add NARGS:RDd, MULTRES + | // Fall through. Assumes BC_CALLT follows and ins_AD is a no-op. + break; + case BC_CALLT: + | ins_AD // RA = base, RD = nargs+1 + | lea RA, [BASE+RA*8+16] + | mov KBASE, BASE // Use KBASE for move + vmeta_call hint. + | mov LFUNC:RB, [RA-16] + | checktp_nc LFUNC:RB, LJ_TFUNC, ->vmeta_call + |->BC_CALLT_Z: + | mov PC, [BASE-8] + | test PCd, FRAME_TYPE + | jnz >7 + |1: + | mov [BASE-16], LFUNC:RB // Copy func+tag down, reloaded below. + | mov MULTRES, NARGS:RDd + | sub NARGS:RDd, 1 + | jz >3 + |2: // Move args down. + | mov RB, [RA] + | add RA, 8 + | mov [KBASE], RB + | add KBASE, 8 + | sub NARGS:RDd, 1 + | jnz <2 + | + | mov LFUNC:RB, [BASE-16] + |3: + | cleartp LFUNC:RB + | mov NARGS:RDd, MULTRES + | cmp byte LFUNC:RB->ffid, 1 // (> FF_C) Calling a fast function? + | ja >5 + |4: + | ins_callt + | + |5: // Tailcall to a fast function. + | test PCd, FRAME_TYPE // Lua frame below? + | jnz <4 + | movzx RAd, PC_RA + | neg RA + | mov LFUNC:KBASE, [BASE+RA*8-32] // Need to prepare KBASE. + | cleartp LFUNC:KBASE + | mov KBASE, LFUNC:KBASE->pc + | mov KBASE, [KBASE+PC2PROTO(k)] + | jmp <4 + | + |7: // Tailcall from a vararg function. + | sub PC, FRAME_VARG + | test PCd, FRAME_TYPEP + | jnz >8 // Vararg frame below? + | sub BASE, PC // Need to relocate BASE/KBASE down. + | mov KBASE, BASE + | mov PC, [BASE-8] + | jmp <1 + |8: + | add PCd, FRAME_VARG + | jmp <1 + break; + + case BC_ITERC: + | ins_A // RA = base, (RB = nresults+1,) RC = nargs+1 (2+1) + | lea RA, [BASE+RA*8+16] // fb = base+2 + | mov RB, [RA-32] // Copy state. fb[0] = fb[-4]. + | mov RC, [RA-24] // Copy control var. fb[1] = fb[-3]. + | mov [RA], RB + | mov [RA+8], RC + | mov LFUNC:RB, [RA-40] // Copy callable. fb[-1] = fb[-5] + | mov [RA-16], LFUNC:RB + | mov NARGS:RDd, 2+1 // Handle like a regular 2-arg call. + | checkfunc LFUNC:RB, ->vmeta_call + | mov BASE, RA + | ins_call + break; + + case BC_ITERN: + | ins_A // RA = base, (RB = nresults+1, RC = nargs+1 (2+1)) + |.if JIT + | // NYI: add hotloop, record BC_ITERN. + |.endif + | mov TAB:RB, [BASE+RA*8-16] + | cleartp TAB:RB + | mov RCd, [BASE+RA*8-8] // Get index from control var. + | mov TMPRd, TAB:RB->asize + | add PC, 4 + | mov ITYPE, TAB:RB->array + |1: // Traverse array part. + | cmp RCd, TMPRd; jae >5 // Index points after array part? + | cmp aword [ITYPE+RC*8], LJ_TNIL; je >4 + |.if not DUALNUM + | cvtsi2sd xmm0, RCd + |.endif + | // Copy array slot to returned value. + | mov RB, [ITYPE+RC*8] + | mov [BASE+RA*8+8], RB + | // Return array index as a numeric key. + |.if DUALNUM + | setint ITYPE, RC + | mov [BASE+RA*8], ITYPE + |.else + | movsd qword [BASE+RA*8], xmm0 + |.endif + | add RCd, 1 + | mov [BASE+RA*8-8], RCd // Update control var. + |2: + | movzx RDd, PC_RD // Get target from ITERL. + | branchPC RD + |3: + | ins_next + | + |4: // Skip holes in array part. + | add RCd, 1 + | jmp <1 + | + |5: // Traverse hash part. + | sub RCd, TMPRd + |6: + | cmp RCd, TAB:RB->hmask; ja <3 // End of iteration? Branch to ITERL+1. + | imul ITYPEd, RCd, #NODE + | add NODE:ITYPE, TAB:RB->node + | cmp aword NODE:ITYPE->val, LJ_TNIL; je >7 + | lea TMPRd, [RCd+TMPRd+1] + | // Copy key and value from hash slot. + | mov RB, NODE:ITYPE->key + | mov RC, NODE:ITYPE->val + | mov [BASE+RA*8], RB + | mov [BASE+RA*8+8], RC + | mov [BASE+RA*8-8], TMPRd + | jmp <2 + | + |7: // Skip holes in hash part. + | add RCd, 1 + | jmp <6 + break; + + case BC_ISNEXT: + | ins_AD // RA = base, RD = target (points to ITERN) + | mov CFUNC:RB, [BASE+RA*8-24] + | checkfunc CFUNC:RB, >5 + | checktptp [BASE+RA*8-16], LJ_TTAB, >5 + | cmp aword [BASE+RA*8-8], LJ_TNIL; jne >5 + | cmp byte CFUNC:RB->ffid, FF_next_N; jne >5 + | branchPC RD + | mov64 TMPR, U64x(fffe7fff, 00000000) + | mov [BASE+RA*8-8], TMPR // Initialize control var. + |1: + | ins_next + |5: // Despecialize bytecode if any of the checks fail. + | mov PC_OP, BC_JMP + | branchPC RD + | mov byte [PC], BC_ITERC + | jmp <1 + break; + + case BC_VARG: + | ins_ABC // RA = base, RB = nresults+1, RC = numparams + | lea TMPR, [BASE+RC*8+(16+FRAME_VARG)] + | lea RA, [BASE+RA*8] + | sub TMPR, [BASE-8] + | // Note: TMPR may now be even _above_ BASE if nargs was < numparams. + | test RB, RB + | jz >5 // Copy all varargs? + | lea RB, [RA+RB*8-8] + | cmp TMPR, BASE // No vararg slots? + | jnb >2 + |1: // Copy vararg slots to destination slots. + | mov RC, [TMPR-16] + | add TMPR, 8 + | mov [RA], RC + | add RA, 8 + | cmp RA, RB // All destination slots filled? + | jnb >3 + | cmp TMPR, BASE // No more vararg slots? + | jb <1 + |2: // Fill up remainder with nil. + | mov aword [RA], LJ_TNIL + | add RA, 8 + | cmp RA, RB + | jb <2 + |3: + | ins_next + | + |5: // Copy all varargs. + | mov MULTRES, 1 // MULTRES = 0+1 + | mov RC, BASE + | sub RC, TMPR + | jbe <3 // No vararg slots? + | mov RBd, RCd + | shr RBd, 3 + | add RBd, 1 + | mov MULTRES, RBd // MULTRES = #varargs+1 + | mov L:RB, SAVE_L + | add RC, RA + | cmp RC, L:RB->maxstack + | ja >7 // Need to grow stack? + |6: // Copy all vararg slots. + | mov RC, [TMPR-16] + | add TMPR, 8 + | mov [RA], RC + | add RA, 8 + | cmp TMPR, BASE // No more vararg slots? + | jb <6 + | jmp <3 + | + |7: // Grow stack for varargs. + | mov L:RB->base, BASE + | mov L:RB->top, RA + | mov SAVE_PC, PC + | sub TMPR, BASE // Need delta, because BASE may change. + | mov TMP1hi, TMPRd + | mov CARG2d, MULTRES + | sub CARG2d, 1 + | mov CARG1, L:RB + | call extern lj_state_growstack // (lua_State *L, int n) + | mov BASE, L:RB->base + | movsxd TMPR, TMP1hi + | mov RA, L:RB->top + | add TMPR, BASE + | jmp <6 + break; + + /* -- Returns ----------------------------------------------------------- */ + + case BC_RETM: + | ins_AD // RA = results, RD = extra_nresults + | add RDd, MULTRES // MULTRES >=1, so RD >=1. + | // Fall through. Assumes BC_RET follows and ins_AD is a no-op. + break; + + case BC_RET: case BC_RET0: case BC_RET1: + | ins_AD // RA = results, RD = nresults+1 + if (op != BC_RET0) { + | shl RAd, 3 + } + |1: + | mov PC, [BASE-8] + | mov MULTRES, RDd // Save nresults+1. + | test PCd, FRAME_TYPE // Check frame type marker. + | jnz >7 // Not returning to a fixarg Lua func? + switch (op) { + case BC_RET: + |->BC_RET_Z: + | mov KBASE, BASE // Use KBASE for result move. + | sub RDd, 1 + | jz >3 + |2: // Move results down. + | mov RB, [KBASE+RA] + | mov [KBASE-16], RB + | add KBASE, 8 + | sub RDd, 1 + | jnz <2 + |3: + | mov RDd, MULTRES // Note: MULTRES may be >255. + | movzx RBd, PC_RB // So cannot compare with RDL! + |5: + | cmp RBd, RDd // More results expected? + | ja >6 + break; + case BC_RET1: + | mov RB, [BASE+RA] + | mov [BASE-16], RB + /* fallthrough */ + case BC_RET0: + |5: + | cmp PC_RB, RDL // More results expected? + | ja >6 + default: + break; + } + | movzx RAd, PC_RA + | neg RA + | lea BASE, [BASE+RA*8-16] // base = base - (RA+2)*8 + | mov LFUNC:KBASE, [BASE-16] + | cleartp LFUNC:KBASE + | mov KBASE, LFUNC:KBASE->pc + | mov KBASE, [KBASE+PC2PROTO(k)] + | ins_next + | + |6: // Fill up results with nil. + if (op == BC_RET) { + | mov aword [KBASE-16], LJ_TNIL // Note: relies on shifted base. + | add KBASE, 8 + } else { + | mov aword [BASE+RD*8-24], LJ_TNIL + } + | add RD, 1 + | jmp <5 + | + |7: // Non-standard return case. + | lea RB, [PC-FRAME_VARG] + | test RBd, FRAME_TYPEP + | jnz ->vm_return + | // Return from vararg function: relocate BASE down and RA up. + | sub BASE, RB + if (op != BC_RET0) { + | add RA, RB + } + | jmp <1 + break; + + /* -- Loops and branches ------------------------------------------------ */ + + |.define FOR_IDX, [RA] + |.define FOR_STOP, [RA+8] + |.define FOR_STEP, [RA+16] + |.define FOR_EXT, [RA+24] + + case BC_FORL: + |.if JIT + | hotloop RBd + |.endif + | // Fall through. Assumes BC_IFORL follows and ins_AJ is a no-op. + break; + + case BC_JFORI: + case BC_JFORL: +#if !LJ_HASJIT + break; +#endif + case BC_FORI: + case BC_IFORL: + vk = (op == BC_IFORL || op == BC_JFORL); + | ins_AJ // RA = base, RD = target (after end of loop or start of loop) + | lea RA, [BASE+RA*8] + if (LJ_DUALNUM) { + | mov RB, FOR_IDX + | checkint RB, >9 + | mov TMPR, FOR_STOP + if (!vk) { + | checkint TMPR, ->vmeta_for + | mov ITYPE, FOR_STEP + | test ITYPEd, ITYPEd; js >5 + | sar ITYPE, 47; + | cmp ITYPEd, LJ_TISNUM; jne ->vmeta_for + } else { +#ifdef LUA_USE_ASSERT + | checkinttp FOR_STOP, ->assert_bad_for_arg_type + | checkinttp FOR_STEP, ->assert_bad_for_arg_type +#endif + | mov ITYPE, FOR_STEP + | test ITYPEd, ITYPEd; js >5 + | add RBd, ITYPEd; jo >1 + | setint RB + | mov FOR_IDX, RB + } + | cmp RBd, TMPRd + | mov FOR_EXT, RB + if (op == BC_FORI) { + | jle >7 + |1: + |6: + | branchPC RD + } else if (op == BC_JFORI) { + | branchPC RD + | movzx RDd, PC_RD + | jle =>BC_JLOOP + |1: + |6: + } else if (op == BC_IFORL) { + | jg >7 + |6: + | branchPC RD + |1: + } else { + | jle =>BC_JLOOP + |1: + |6: + } + |7: + | ins_next + | + |5: // Invert check for negative step. + if (!vk) { + | sar ITYPE, 47; + | cmp ITYPEd, LJ_TISNUM; jne ->vmeta_for + } else { + | add RBd, ITYPEd; jo <1 + | setint RB + | mov FOR_IDX, RB + } + | cmp RBd, TMPRd + | mov FOR_EXT, RB + if (op == BC_FORI) { + | jge <7 + } else if (op == BC_JFORI) { + | branchPC RD + | movzx RDd, PC_RD + | jge =>BC_JLOOP + } else if (op == BC_IFORL) { + | jl <7 + } else { + | jge =>BC_JLOOP + } + | jmp <6 + |9: // Fallback to FP variant. + if (!vk) { + | jae ->vmeta_for + } + } else if (!vk) { + | checknumtp FOR_IDX, ->vmeta_for + } + if (!vk) { + | checknumtp FOR_STOP, ->vmeta_for + } else { +#ifdef LUA_USE_ASSERT + | checknumtp FOR_STOP, ->assert_bad_for_arg_type + | checknumtp FOR_STEP, ->assert_bad_for_arg_type +#endif + } + | mov RB, FOR_STEP + if (!vk) { + | checknum RB, ->vmeta_for + } + | movsd xmm0, qword FOR_IDX + | movsd xmm1, qword FOR_STOP + if (vk) { + | addsd xmm0, qword FOR_STEP + | movsd qword FOR_IDX, xmm0 + | test RB, RB; js >3 + } else { + | jl >3 + } + | ucomisd xmm1, xmm0 + |1: + | movsd qword FOR_EXT, xmm0 + if (op == BC_FORI) { + |.if DUALNUM + | jnb <7 + |.else + | jnb >2 + | branchPC RD + |.endif + } else if (op == BC_JFORI) { + | branchPC RD + | movzx RDd, PC_RD + | jnb =>BC_JLOOP + } else if (op == BC_IFORL) { + |.if DUALNUM + | jb <7 + |.else + | jb >2 + | branchPC RD + |.endif + } else { + | jnb =>BC_JLOOP + } + |.if DUALNUM + | jmp <6 + |.else + |2: + | ins_next + |.endif + | + |3: // Invert comparison if step is negative. + | ucomisd xmm0, xmm1 + | jmp <1 + break; + + case BC_ITERL: + |.if JIT + | hotloop RBd + |.endif + | // Fall through. Assumes BC_IITERL follows and ins_AJ is a no-op. + break; + + case BC_JITERL: +#if !LJ_HASJIT + break; +#endif + case BC_IITERL: + | ins_AJ // RA = base, RD = target + | lea RA, [BASE+RA*8] + | mov RB, [RA] + | cmp RB, LJ_TNIL; je >1 // Stop if iterator returned nil. + if (op == BC_JITERL) { + | mov [RA-8], RB + | jmp =>BC_JLOOP + } else { + | branchPC RD // Otherwise save control var + branch. + | mov [RA-8], RB + } + |1: + | ins_next + break; + + case BC_LOOP: + | ins_A // RA = base, RD = target (loop extent) + | // Note: RA/RD is only used by trace recorder to determine scope/extent + | // This opcode does NOT jump, it's only purpose is to detect a hot loop. + |.if JIT + | hotloop RBd + |.endif + | // Fall through. Assumes BC_ILOOP follows and ins_A is a no-op. + break; + + case BC_ILOOP: + | ins_A // RA = base, RD = target (loop extent) + | ins_next + break; + + case BC_JLOOP: + |.if JIT + | ins_AD // RA = base (ignored), RD = traceno + | mov RA, [DISPATCH+DISPATCH_J(trace)] + | mov TRACE:RD, [RA+RD*8] + | mov RD, TRACE:RD->mcode + | mov L:RB, SAVE_L + | mov [DISPATCH+DISPATCH_GL(jit_base)], BASE + | mov [DISPATCH+DISPATCH_GL(tmpbuf.L)], L:RB + | // Save additional callee-save registers only used in compiled code. + |.if X64WIN + | mov CSAVE_4, r12 + | mov CSAVE_3, r13 + | mov CSAVE_2, r14 + | mov CSAVE_1, r15 + | mov RA, rsp + | sub rsp, 10*16+4*8 + | movdqa [RA-1*16], xmm6 + | movdqa [RA-2*16], xmm7 + | movdqa [RA-3*16], xmm8 + | movdqa [RA-4*16], xmm9 + | movdqa [RA-5*16], xmm10 + | movdqa [RA-6*16], xmm11 + | movdqa [RA-7*16], xmm12 + | movdqa [RA-8*16], xmm13 + | movdqa [RA-9*16], xmm14 + | movdqa [RA-10*16], xmm15 + |.else + | sub rsp, 16 + | mov [rsp+16], r12 + | mov [rsp+8], r13 + |.endif + | jmp RD + |.endif + break; + + case BC_JMP: + | ins_AJ // RA = unused, RD = target + | branchPC RD + | ins_next + break; + + /* -- Function headers -------------------------------------------------- */ + + /* + ** Reminder: A function may be called with func/args above L->maxstack, + ** i.e. occupying EXTRA_STACK slots. And vmeta_call may add one extra slot, + ** too. This means all FUNC* ops (including fast functions) must check + ** for stack overflow _before_ adding more slots! + */ + + case BC_FUNCF: + |.if JIT + | hotcall RBd + |.endif + case BC_FUNCV: /* NYI: compiled vararg functions. */ + | // Fall through. Assumes BC_IFUNCF/BC_IFUNCV follow and ins_AD is a no-op. + break; + + case BC_JFUNCF: +#if !LJ_HASJIT + break; +#endif + case BC_IFUNCF: + | ins_AD // BASE = new base, RA = framesize, RD = nargs+1 + | mov KBASE, [PC-4+PC2PROTO(k)] + | mov L:RB, SAVE_L + | lea RA, [BASE+RA*8] // Top of frame. + | cmp RA, L:RB->maxstack + | ja ->vm_growstack_f + | movzx RAd, byte [PC-4+PC2PROTO(numparams)] + | cmp NARGS:RDd, RAd // Check for missing parameters. + | jbe >3 + |2: + if (op == BC_JFUNCF) { + | movzx RDd, PC_RD + | jmp =>BC_JLOOP + } else { + | ins_next + } + | + |3: // Clear missing parameters. + | mov aword [BASE+NARGS:RD*8-8], LJ_TNIL + | add NARGS:RDd, 1 + | cmp NARGS:RDd, RAd + | jbe <3 + | jmp <2 + break; + + case BC_JFUNCV: +#if !LJ_HASJIT + break; +#endif + | int3 // NYI: compiled vararg functions + break; /* NYI: compiled vararg functions. */ + + case BC_IFUNCV: + | ins_AD // BASE = new base, RA = framesize, RD = nargs+1 + | lea RBd, [NARGS:RD*8+FRAME_VARG+8] + | lea RD, [BASE+NARGS:RD*8+8] + | mov LFUNC:KBASE, [BASE-16] + | mov [RD-8], RB // Store delta + FRAME_VARG. + | mov [RD-16], LFUNC:KBASE // Store copy of LFUNC. + | mov L:RB, SAVE_L + | lea RA, [RD+RA*8] + | cmp RA, L:RB->maxstack + | ja ->vm_growstack_v // Need to grow stack. + | mov RA, BASE + | mov BASE, RD + | movzx RBd, byte [PC-4+PC2PROTO(numparams)] + | test RBd, RBd + | jz >2 + | add RA, 8 + |1: // Copy fixarg slots up to new frame. + | add RA, 8 + | cmp RA, BASE + | jnb >3 // Less args than parameters? + | mov KBASE, [RA-16] + | mov [RD], KBASE + | add RD, 8 + | mov aword [RA-16], LJ_TNIL // Clear old fixarg slot (help the GC). + | sub RBd, 1 + | jnz <1 + |2: + if (op == BC_JFUNCV) { + | movzx RDd, PC_RD + | jmp =>BC_JLOOP + } else { + | mov KBASE, [PC-4+PC2PROTO(k)] + | ins_next + } + | + |3: // Clear missing parameters. + | mov aword [RD], LJ_TNIL + | add RD, 8 + | sub RBd, 1 + | jnz <3 + | jmp <2 + break; + + case BC_FUNCC: + case BC_FUNCCW: + | ins_AD // BASE = new base, RA = ins RA|RD (unused), RD = nargs+1 + | mov CFUNC:RB, [BASE-16] + | cleartp CFUNC:RB + | mov KBASE, CFUNC:RB->f + | mov L:RB, SAVE_L + | lea RD, [BASE+NARGS:RD*8-8] + | mov L:RB->base, BASE + | lea RA, [RD+8*LUA_MINSTACK] + | cmp RA, L:RB->maxstack + | mov L:RB->top, RD + if (op == BC_FUNCC) { + | mov CARG1, L:RB // Caveat: CARG1 may be RA. + } else { + | mov CARG2, KBASE + | mov CARG1, L:RB // Caveat: CARG1 may be RA. + } + | ja ->vm_growstack_c // Need to grow stack. + | set_vmstate C + if (op == BC_FUNCC) { + | call KBASE // (lua_State *L) + } else { + | // (lua_State *L, lua_CFunction f) + | call aword [DISPATCH+DISPATCH_GL(wrapf)] + } + | // nresults returned in eax (RD). + | mov BASE, L:RB->base + | mov [DISPATCH+DISPATCH_GL(cur_L)], L:RB + | set_vmstate INTERP + | lea RA, [BASE+RD*8] + | neg RA + | add RA, L:RB->top // RA = (L->top-(L->base+nresults))*8 + | mov PC, [BASE-8] // Fetch PC of caller. + | jmp ->vm_returnc + break; + + /* ---------------------------------------------------------------------- */ + + default: + fprintf(stderr, "Error: undefined opcode BC_%s\n", bc_names[op]); + exit(2); + break; + } +} + +static int build_backend(BuildCtx *ctx) +{ + int op; + dasm_growpc(Dst, BC__MAX); + build_subroutines(ctx); + |.code_op + for (op = 0; op < BC__MAX; op++) + build_ins(ctx, (BCOp)op, op); + return BC__MAX; +} + +/* Emit pseudo frame-info for all assembler functions. */ +static void emit_asm_debug(BuildCtx *ctx) +{ + int fcofs = (int)((uint8_t *)ctx->glob[GLOB_vm_ffi_call] - ctx->code); + switch (ctx->mode) { + case BUILD_elfasm: + fprintf(ctx->fp, "\t.section .debug_frame,\"\",@progbits\n"); + fprintf(ctx->fp, + ".Lframe0:\n" + "\t.long .LECIE0-.LSCIE0\n" + ".LSCIE0:\n" + "\t.long 0xffffffff\n" + "\t.byte 0x1\n" + "\t.string \"\"\n" + "\t.uleb128 0x1\n" + "\t.sleb128 -8\n" + "\t.byte 0x10\n" + "\t.byte 0xc\n\t.uleb128 0x7\n\t.uleb128 8\n" + "\t.byte 0x80+0x10\n\t.uleb128 0x1\n" + "\t.align 8\n" + ".LECIE0:\n\n"); + fprintf(ctx->fp, + ".LSFDE0:\n" + "\t.long .LEFDE0-.LASFDE0\n" + ".LASFDE0:\n" + "\t.long .Lframe0\n" + "\t.quad .Lbegin\n" + "\t.quad %d\n" + "\t.byte 0xe\n\t.uleb128 %d\n" /* def_cfa_offset */ + "\t.byte 0x86\n\t.uleb128 0x2\n" /* offset rbp */ + "\t.byte 0x83\n\t.uleb128 0x3\n" /* offset rbx */ + "\t.byte 0x8f\n\t.uleb128 0x4\n" /* offset r15 */ + "\t.byte 0x8e\n\t.uleb128 0x5\n" /* offset r14 */ +#if LJ_NO_UNWIND + "\t.byte 0x8d\n\t.uleb128 0x6\n" /* offset r13 */ + "\t.byte 0x8c\n\t.uleb128 0x7\n" /* offset r12 */ +#endif + "\t.align 8\n" + ".LEFDE0:\n\n", fcofs, CFRAME_SIZE); +#if LJ_HASFFI + fprintf(ctx->fp, + ".LSFDE1:\n" + "\t.long .LEFDE1-.LASFDE1\n" + ".LASFDE1:\n" + "\t.long .Lframe0\n" + "\t.quad lj_vm_ffi_call\n" + "\t.quad %d\n" + "\t.byte 0xe\n\t.uleb128 16\n" /* def_cfa_offset */ + "\t.byte 0x86\n\t.uleb128 0x2\n" /* offset rbp */ + "\t.byte 0xd\n\t.uleb128 0x6\n" /* def_cfa_register rbp */ + "\t.byte 0x83\n\t.uleb128 0x3\n" /* offset rbx */ + "\t.align 8\n" + ".LEFDE1:\n\n", (int)ctx->codesz - fcofs); +#endif +#if !LJ_NO_UNWIND +#if (defined(__sun__) && defined(__svr4__)) + fprintf(ctx->fp, "\t.section .eh_frame,\"a\",@unwind\n"); +#else + fprintf(ctx->fp, "\t.section .eh_frame,\"a\",@progbits\n"); +#endif + fprintf(ctx->fp, + ".Lframe1:\n" + "\t.long .LECIE1-.LSCIE1\n" + ".LSCIE1:\n" + "\t.long 0\n" + "\t.byte 0x1\n" + "\t.string \"zPR\"\n" + "\t.uleb128 0x1\n" + "\t.sleb128 -8\n" + "\t.byte 0x10\n" + "\t.uleb128 6\n" /* augmentation length */ + "\t.byte 0x1b\n" /* pcrel|sdata4 */ + "\t.long lj_err_unwind_dwarf-.\n" + "\t.byte 0x1b\n" /* pcrel|sdata4 */ + "\t.byte 0xc\n\t.uleb128 0x7\n\t.uleb128 8\n" + "\t.byte 0x80+0x10\n\t.uleb128 0x1\n" + "\t.align 8\n" + ".LECIE1:\n\n"); + fprintf(ctx->fp, + ".LSFDE2:\n" + "\t.long .LEFDE2-.LASFDE2\n" + ".LASFDE2:\n" + "\t.long .LASFDE2-.Lframe1\n" + "\t.long .Lbegin-.\n" + "\t.long %d\n" + "\t.uleb128 0\n" /* augmentation length */ + "\t.byte 0xe\n\t.uleb128 %d\n" /* def_cfa_offset */ + "\t.byte 0x86\n\t.uleb128 0x2\n" /* offset rbp */ + "\t.byte 0x83\n\t.uleb128 0x3\n" /* offset rbx */ + "\t.byte 0x8f\n\t.uleb128 0x4\n" /* offset r15 */ + "\t.byte 0x8e\n\t.uleb128 0x5\n" /* offset r14 */ + "\t.align 8\n" + ".LEFDE2:\n\n", fcofs, CFRAME_SIZE); +#if LJ_HASFFI + fprintf(ctx->fp, + ".Lframe2:\n" + "\t.long .LECIE2-.LSCIE2\n" + ".LSCIE2:\n" + "\t.long 0\n" + "\t.byte 0x1\n" + "\t.string \"zR\"\n" + "\t.uleb128 0x1\n" + "\t.sleb128 -8\n" + "\t.byte 0x10\n" + "\t.uleb128 1\n" /* augmentation length */ + "\t.byte 0x1b\n" /* pcrel|sdata4 */ + "\t.byte 0xc\n\t.uleb128 0x7\n\t.uleb128 8\n" + "\t.byte 0x80+0x10\n\t.uleb128 0x1\n" + "\t.align 8\n" + ".LECIE2:\n\n"); + fprintf(ctx->fp, + ".LSFDE3:\n" + "\t.long .LEFDE3-.LASFDE3\n" + ".LASFDE3:\n" + "\t.long .LASFDE3-.Lframe2\n" + "\t.long lj_vm_ffi_call-.\n" + "\t.long %d\n" + "\t.uleb128 0\n" /* augmentation length */ + "\t.byte 0xe\n\t.uleb128 16\n" /* def_cfa_offset */ + "\t.byte 0x86\n\t.uleb128 0x2\n" /* offset rbp */ + "\t.byte 0xd\n\t.uleb128 0x6\n" /* def_cfa_register rbp */ + "\t.byte 0x83\n\t.uleb128 0x3\n" /* offset rbx */ + "\t.align 8\n" + ".LEFDE3:\n\n", (int)ctx->codesz - fcofs); +#endif +#endif + break; +#if !LJ_NO_UNWIND + /* Mental note: never let Apple design an assembler. + ** Or a linker. Or a plastic case. But I digress. + */ + case BUILD_machasm: { +#if LJ_HASFFI + int fcsize = 0; +#endif + int i; + fprintf(ctx->fp, "\t.section __TEXT,__eh_frame,coalesced,no_toc+strip_static_syms+live_support\n"); + fprintf(ctx->fp, + "EH_frame1:\n" + "\t.set L$set$x,LECIEX-LSCIEX\n" + "\t.long L$set$x\n" + "LSCIEX:\n" + "\t.long 0\n" + "\t.byte 0x1\n" + "\t.ascii \"zPR\\0\"\n" + "\t.byte 0x1\n" + "\t.byte 128-8\n" + "\t.byte 0x10\n" + "\t.byte 6\n" /* augmentation length */ + "\t.byte 0x9b\n" /* indirect|pcrel|sdata4 */ + "\t.long _lj_err_unwind_dwarf+4@GOTPCREL\n" + "\t.byte 0x1b\n" /* pcrel|sdata4 */ + "\t.byte 0xc\n\t.byte 0x7\n\t.byte 8\n" + "\t.byte 0x80+0x10\n\t.byte 0x1\n" + "\t.align 3\n" + "LECIEX:\n\n"); + for (i = 0; i < ctx->nsym; i++) { + const char *name = ctx->sym[i].name; + int32_t size = ctx->sym[i+1].ofs - ctx->sym[i].ofs; + if (size == 0) continue; +#if LJ_HASFFI + if (!strcmp(name, "_lj_vm_ffi_call")) { fcsize = size; continue; } +#endif + fprintf(ctx->fp, + "%s.eh:\n" + "LSFDE%d:\n" + "\t.set L$set$%d,LEFDE%d-LASFDE%d\n" + "\t.long L$set$%d\n" + "LASFDE%d:\n" + "\t.long LASFDE%d-EH_frame1\n" + "\t.long %s-.\n" + "\t.long %d\n" + "\t.byte 0\n" /* augmentation length */ + "\t.byte 0xe\n\t.byte %d\n" /* def_cfa_offset */ + "\t.byte 0x86\n\t.byte 0x2\n" /* offset rbp */ + "\t.byte 0x83\n\t.byte 0x3\n" /* offset rbx */ + "\t.byte 0x8f\n\t.byte 0x4\n" /* offset r15 */ + "\t.byte 0x8e\n\t.byte 0x5\n" /* offset r14 */ + "\t.align 3\n" + "LEFDE%d:\n\n", + name, i, i, i, i, i, i, i, name, size, CFRAME_SIZE, i); + } +#if LJ_HASFFI + if (fcsize) { + fprintf(ctx->fp, + "EH_frame2:\n" + "\t.set L$set$y,LECIEY-LSCIEY\n" + "\t.long L$set$y\n" + "LSCIEY:\n" + "\t.long 0\n" + "\t.byte 0x1\n" + "\t.ascii \"zR\\0\"\n" + "\t.byte 0x1\n" + "\t.byte 128-8\n" + "\t.byte 0x10\n" + "\t.byte 1\n" /* augmentation length */ + "\t.byte 0x1b\n" /* pcrel|sdata4 */ + "\t.byte 0xc\n\t.byte 0x7\n\t.byte 8\n" + "\t.byte 0x80+0x10\n\t.byte 0x1\n" + "\t.align 3\n" + "LECIEY:\n\n"); + fprintf(ctx->fp, + "_lj_vm_ffi_call.eh:\n" + "LSFDEY:\n" + "\t.set L$set$yy,LEFDEY-LASFDEY\n" + "\t.long L$set$yy\n" + "LASFDEY:\n" + "\t.long LASFDEY-EH_frame2\n" + "\t.long _lj_vm_ffi_call-.\n" + "\t.long %d\n" + "\t.byte 0\n" /* augmentation length */ + "\t.byte 0xe\n\t.byte 16\n" /* def_cfa_offset */ + "\t.byte 0x86\n\t.byte 0x2\n" /* offset rbp */ + "\t.byte 0xd\n\t.byte 0x6\n" /* def_cfa_register rbp */ + "\t.byte 0x83\n\t.byte 0x3\n" /* offset rbx */ + "\t.align 3\n" + "LEFDEY:\n\n", fcsize); + } +#endif + fprintf(ctx->fp, ".subsections_via_symbols\n"); + } + break; +#endif + default: /* Difficult for other modes. */ + break; + } +} + diff --git a/luajit-2.1/src/vm_x86.dasc b/luajit-2.1/src/vm_x86.dasc index ea0415e..96ac1da 100644 --- a/luajit-2.1/src/vm_x86.dasc +++ b/luajit-2.1/src/vm_x86.dasc @@ -222,6 +222,9 @@ |.define CFRAME_SPACE, aword*5 // Delta for rsp (see <--). |.macro saveregs_ | push rbx; push r15; push r14 +|.if NO_UNWIND +| push r13; push r12 +|.endif | sub rsp, CFRAME_SPACE |.endmacro |.macro saveregs @@ -229,15 +232,28 @@ |.endmacro |.macro restoreregs | add rsp, CFRAME_SPACE +|.if NO_UNWIND +| pop r12; pop r13 +|.endif | pop r14; pop r15; pop rbx; pop rbp |.endmacro | |//----- 16 byte aligned, +|.if NO_UNWIND +|.define SAVE_RET, aword [rsp+aword*11] //<-- rsp entering interpreter. +|.define SAVE_R4, aword [rsp+aword*10] +|.define SAVE_R3, aword [rsp+aword*9] +|.define SAVE_R2, aword [rsp+aword*8] +|.define SAVE_R1, aword [rsp+aword*7] +|.define SAVE_RU2, aword [rsp+aword*6] +|.define SAVE_RU1, aword [rsp+aword*5] //<-- rsp after register saves. +|.else |.define SAVE_RET, aword [rsp+aword*9] //<-- rsp entering interpreter. |.define SAVE_R4, aword [rsp+aword*8] |.define SAVE_R3, aword [rsp+aword*7] |.define SAVE_R2, aword [rsp+aword*6] |.define SAVE_R1, aword [rsp+aword*5] //<-- rsp after register saves. +|.endif |.define SAVE_CFRAME, aword [rsp+aword*4] |.define SAVE_PC, dword [rsp+dword*7] |.define SAVE_L, dword [rsp+dword*6] @@ -2348,10 +2364,8 @@ static void build_subroutines(BuildCtx *ctx) | |//-- Bit library -------------------------------------------------------- | - |.define TOBIT_BIAS, 0x59c00000 // 2^52 + 2^51 (float, not double!). - | - |.macro .ffunc_bit, name, kind - | .ffunc_1 name + |.macro .ffunc_bit, name, kind, fdef + | fdef name |.if kind == 2 | sseconst_tobit xmm1, RBa |.endif @@ -2378,6 +2392,10 @@ static void build_subroutines(BuildCtx *ctx) |2: |.endmacro | + |.macro .ffunc_bit, name, kind + | .ffunc_bit name, kind, .ffunc_1 + |.endmacro + | |.ffunc_bit bit_tobit, 0 | jmp ->fff_resbit | @@ -2431,7 +2449,7 @@ static void build_subroutines(BuildCtx *ctx) | |.macro .ffunc_bit_sh, name, ins |.if DUALNUM - | .ffunc_bit name, 1 + | .ffunc_bit name, 1, .ffunc_2 | // Note: no inline conversion from number for 2nd argument! | cmp dword [BASE+12], LJ_TISNUM; jne ->fff_fallback | mov RA, dword [BASE+8] @@ -2649,8 +2667,8 @@ static void build_subroutines(BuildCtx *ctx) |->cont_stitch: // Trace stitching. |.if JIT | // BASE = base, RC = result, RB = mbase - | mov RA, [RB-24] // Save previous trace number. - | mov TMP1, RA + | mov TRACE:RA, [RB-24] // Save previous trace. + | mov TMP1, TRACE:RA | mov TMP3, DISPATCH // Need one more register. | mov DISPATCH, MULTRES | movzx RA, PC_RA @@ -2681,11 +2699,8 @@ static void build_subroutines(BuildCtx *ctx) | ja >9 // More results wanted? | | mov DISPATCH, TMP3 - | mov RB, TMP1 // Get previous trace number. - | mov RA, [DISPATCH+DISPATCH_J(trace)] - | mov TRACE:RD, [RA+RB*4] - | test TRACE:RD, TRACE:RD - | jz ->cont_nop + | mov TRACE:RD, TMP1 // Get previous trace. + | movzx RB, word TRACE:RD->traceno | movzx RD, word TRACE:RD->link | cmp RD, RB | je ->cont_nop // Blacklisted. @@ -5420,6 +5435,10 @@ static void emit_asm_debug(BuildCtx *ctx) "\t.byte 0x83\n\t.uleb128 0x3\n" /* offset rbx */ "\t.byte 0x8f\n\t.uleb128 0x4\n" /* offset r15 */ "\t.byte 0x8e\n\t.uleb128 0x5\n" /* offset r14 */ +#if LJ_NO_UNWIND + "\t.byte 0x8d\n\t.uleb128 0x6\n" /* offset r13 */ + "\t.byte 0x8c\n\t.uleb128 0x7\n" /* offset r12 */ +#endif #else "\t.long .Lbegin\n" "\t.long %d\n" @@ -5455,6 +5474,7 @@ static void emit_asm_debug(BuildCtx *ctx) "\t.align " SZPTR "\n" ".LEFDE1:\n\n", (int)ctx->codesz - fcofs); #endif +#if !LJ_NO_UNWIND #if (defined(__sun__) && defined(__svr4__)) #if LJ_64 fprintf(ctx->fp, "\t.section .eh_frame,\"a\",@unwind\n"); @@ -5543,7 +5563,9 @@ static void emit_asm_debug(BuildCtx *ctx) "\t.align " SZPTR "\n" ".LEFDE3:\n\n", (int)ctx->codesz - fcofs); #endif +#endif break; +#if !LJ_NO_UNWIND /* Mental note: never let Apple design an assembler. ** Or a linker. Or a plastic case. But I digress. */ @@ -5677,6 +5699,7 @@ static void emit_asm_debug(BuildCtx *ctx) fprintf(ctx->fp, ".subsections_via_symbols\n"); } break; +#endif default: /* Difficult for other modes. */ break; } diff --git a/luajit-2.1/src/xb1build.bat b/luajit-2.1/src/xb1build.bat new file mode 100644 index 0000000..847e84a --- /dev/null +++ b/luajit-2.1/src/xb1build.bat @@ -0,0 +1,101 @@ +@rem Script to build LuaJIT with the Xbox One SDK.
+@rem Donated to the public domain.
+@rem
+@rem Open a "Visual Studio .NET Command Prompt" (64 bit host compiler)
+@rem Then cd to this directory and run this script.
+
+@if not defined INCLUDE goto :FAIL
+@if not defined DurangoXDK goto :FAIL
+
+@setlocal
+@echo ---- Host compiler ----
+@set LJCOMPILE=cl /nologo /c /MD /O2 /W3 /D_CRT_SECURE_NO_DEPRECATE /DLUAJIT_ENABLE_GC64
+@set LJLINK=link /nologo
+@set LJMT=mt /nologo
+@set DASMDIR=..\dynasm
+@set DASM=%DASMDIR%\dynasm.lua
+@set ALL_LIB=lib_base.c lib_math.c lib_bit.c lib_string.c lib_table.c lib_io.c lib_os.c lib_package.c lib_debug.c lib_jit.c lib_ffi.c
+
+%LJCOMPILE% host\minilua.c
+@if errorlevel 1 goto :BAD
+%LJLINK% /out:minilua.exe minilua.obj
+@if errorlevel 1 goto :BAD
+if exist minilua.exe.manifest^
+ %LJMT% -manifest minilua.exe.manifest -outputresource:minilua.exe
+
+@rem Error out for 64 bit host compiler
+@minilua
+@if not errorlevel 8 goto :FAIL
+
+@set DASMFLAGS=-D WIN -D FFI -D P64
+minilua %DASM% -LN %DASMFLAGS% -o host\buildvm_arch.h vm_x64.dasc
+@if errorlevel 1 goto :BAD
+
+%LJCOMPILE% /I "." /I %DASMDIR% /D_DURANGO host\buildvm*.c
+@if errorlevel 1 goto :BAD
+%LJLINK% /out:buildvm.exe buildvm*.obj
+@if errorlevel 1 goto :BAD
+if exist buildvm.exe.manifest^
+ %LJMT% -manifest buildvm.exe.manifest -outputresource:buildvm.exe
+
+buildvm -m peobj -o lj_vm.obj
+@if errorlevel 1 goto :BAD
+buildvm -m bcdef -o lj_bcdef.h %ALL_LIB%
+@if errorlevel 1 goto :BAD
+buildvm -m ffdef -o lj_ffdef.h %ALL_LIB%
+@if errorlevel 1 goto :BAD
+buildvm -m libdef -o lj_libdef.h %ALL_LIB%
+@if errorlevel 1 goto :BAD
+buildvm -m recdef -o lj_recdef.h %ALL_LIB%
+@if errorlevel 1 goto :BAD
+buildvm -m vmdef -o jit\vmdef.lua %ALL_LIB%
+@if errorlevel 1 goto :BAD
+buildvm -m folddef -o lj_folddef.h lj_opt_fold.c
+@if errorlevel 1 goto :BAD
+
+@echo ---- Cross compiler ----
+
+@set CWD=%cd%
+@call "%DurangoXDK%\xdk\DurangoVars.cmd" XDK
+@cd /D "%CWD%"
+@shift
+
+@set LJCOMPILE="cl" /nologo /c /W3 /GF /Gm- /GR- /GS- /Gy /openmp- /D_CRT_SECURE_NO_DEPRECATE /D_LIB /D_UNICODE /D_DURANGO
+@set LJLIB="lib" /nologo
+
+@if "%1"=="debug" (
+ @shift
+ @set LJCOMPILE=%LJCOMPILE% /Zi /MDd /Od
+ @set LJLINK=%LJLINK% /debug
+) else (
+ @set LJCOMPILE=%LJCOMPILE% /MD /O2 /DNDEBUG
+)
+
+@if "%1"=="amalg" goto :AMALG
+%LJCOMPILE% /DLUA_BUILD_AS_DLL lj_*.c lib_*.c
+@if errorlevel 1 goto :BAD
+%LJLIB% /OUT:luajit.lib lj_*.obj lib_*.obj
+@if errorlevel 1 goto :BAD
+@goto :NOAMALG
+:AMALG
+%LJCOMPILE% /DLUA_BUILD_AS_DLL ljamalg.c
+@if errorlevel 1 goto :BAD
+%LJLIB% /OUT:luajit.lib ljamalg.obj lj_vm.obj
+@if errorlevel 1 goto :BAD
+:NOAMALG
+
+@del *.obj *.manifest minilua.exe buildvm.exe
+@echo.
+@echo === Successfully built LuaJIT for Xbox One ===
+
+@goto :END
+:BAD
+@echo.
+@echo *******************************************************
+@echo *** Build FAILED -- Please check the error messages ***
+@echo *******************************************************
+@goto :END
+:FAIL
+@echo To run this script you must open a "Visual Studio .NET Command Prompt"
+@echo (64 bit host compiler). The Xbox One SDK must be installed, too.
+:END
|