├── .gitignore ├── LICENSE ├── README.md ├── build.sbt └── scasm.scala /.gitignore: -------------------------------------------------------------------------------- 1 | target/ 2 | project/ 3 | -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- 1 | Apache License 2 | Version 2.0, January 2004 3 | http://www.apache.org/licenses/ 4 | 5 | TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION 6 | 7 | 1. Definitions. 8 | 9 | "License" shall mean the terms and conditions for use, reproduction, 10 | and distribution as defined by Sections 1 through 9 of this document. 11 | 12 | "Licensor" shall mean the copyright owner or entity authorized by 13 | the copyright owner that is granting the License. 14 | 15 | "Legal Entity" shall mean the union of the acting entity and all 16 | other entities that control, are controlled by, or are under common 17 | control with that entity. For the purposes of this definition, 18 | "control" means (i) the power, direct or indirect, to cause the 19 | direction or management of such entity, whether by contract or 20 | otherwise, or (ii) ownership of fifty percent (50%) or more of the 21 | outstanding shares, or (iii) beneficial ownership of such entity. 22 | 23 | "You" (or "Your") shall mean an individual or Legal Entity 24 | exercising permissions granted by this License. 25 | 26 | "Source" form shall mean the preferred form for making modifications, 27 | including but not limited to software source code, documentation 28 | source, and configuration files. 29 | 30 | "Object" form shall mean any form resulting from mechanical 31 | transformation or translation of a Source form, including but 32 | not limited to compiled object code, generated documentation, 33 | and conversions to other media types. 34 | 35 | "Work" shall mean the work of authorship, whether in Source or 36 | Object form, made available under the License, as indicated by a 37 | copyright notice that is included in or attached to the work 38 | (an example is provided in the Appendix below). 39 | 40 | "Derivative Works" shall mean any work, whether in Source or Object 41 | form, that is based on (or derived from) the Work and for which the 42 | editorial revisions, annotations, elaborations, or other modifications 43 | represent, as a whole, an original work of authorship. For the purposes 44 | of this License, Derivative Works shall not include works that remain 45 | separable from, or merely link (or bind by name) to the interfaces of, 46 | the Work and Derivative Works thereof. 47 | 48 | "Contribution" shall mean any work of authorship, including 49 | the original version of the Work and any modifications or additions 50 | to that Work or Derivative Works thereof, that is intentionally 51 | submitted to Licensor for inclusion in the Work by the copyright owner 52 | or by an individual or Legal Entity authorized to submit on behalf of 53 | the copyright owner. For the purposes of this definition, "submitted" 54 | means any form of electronic, verbal, or written communication sent 55 | to the Licensor or its representatives, including but not limited to 56 | communication on electronic mailing lists, source code control systems, 57 | and issue tracking systems that are managed by, or on behalf of, the 58 | Licensor for the purpose of discussing and improving the Work, but 59 | excluding communication that is conspicuously marked or otherwise 60 | designated in writing by the copyright owner as "Not a Contribution." 61 | 62 | "Contributor" shall mean Licensor and any individual or Legal Entity 63 | on behalf of whom a Contribution has been received by Licensor and 64 | subsequently incorporated within the Work. 65 | 66 | 2. Grant of Copyright License. Subject to the terms and conditions of 67 | this License, each Contributor hereby grants to You a perpetual, 68 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 69 | copyright license to reproduce, prepare Derivative Works of, 70 | publicly display, publicly perform, sublicense, and distribute the 71 | Work and such Derivative Works in Source or Object form. 72 | 73 | 3. Grant of Patent License. Subject to the terms and conditions of 74 | this License, each Contributor hereby grants to You a perpetual, 75 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 76 | (except as stated in this section) patent license to make, have made, 77 | use, offer to sell, sell, import, and otherwise transfer the Work, 78 | where such license applies only to those patent claims licensable 79 | by such Contributor that are necessarily infringed by their 80 | Contribution(s) alone or by combination of their Contribution(s) 81 | with the Work to which such Contribution(s) was submitted. If You 82 | institute patent litigation against any entity (including a 83 | cross-claim or counterclaim in a lawsuit) alleging that the Work 84 | or a Contribution incorporated within the Work constitutes direct 85 | or contributory patent infringement, then any patent licenses 86 | granted to You under this License for that Work shall terminate 87 | as of the date such litigation is filed. 88 | 89 | 4. Redistribution. You may reproduce and distribute copies of the 90 | Work or Derivative Works thereof in any medium, with or without 91 | modifications, and in Source or Object form, provided that You 92 | meet the following conditions: 93 | 94 | (a) You must give any other recipients of the Work or 95 | Derivative Works a copy of this License; and 96 | 97 | (b) You must cause any modified files to carry prominent notices 98 | stating that You changed the files; and 99 | 100 | (c) You must retain, in the Source form of any Derivative Works 101 | that You distribute, all copyright, patent, trademark, and 102 | attribution notices from the Source form of the Work, 103 | excluding those notices that do not pertain to any part of 104 | the Derivative Works; and 105 | 106 | (d) If the Work includes a "NOTICE" text file as part of its 107 | distribution, then any Derivative Works that You distribute must 108 | include a readable copy of the attribution notices contained 109 | within such NOTICE file, excluding those notices that do not 110 | pertain to any part of the Derivative Works, in at least one 111 | of the following places: within a NOTICE text file distributed 112 | as part of the Derivative Works; within the Source form or 113 | documentation, if provided along with the Derivative Works; or, 114 | within a display generated by the Derivative Works, if and 115 | wherever such third-party notices normally appear. The contents 116 | of the NOTICE file are for informational purposes only and 117 | do not modify the License. You may add Your own attribution 118 | notices within Derivative Works that You distribute, alongside 119 | or as an addendum to the NOTICE text from the Work, provided 120 | that such additional attribution notices cannot be construed 121 | as modifying the License. 122 | 123 | You may add Your own copyright statement to Your modifications and 124 | may provide additional or different license terms and conditions 125 | for use, reproduction, or distribution of Your modifications, or 126 | for any such Derivative Works as a whole, provided Your use, 127 | reproduction, and distribution of the Work otherwise complies with 128 | the conditions stated in this License. 129 | 130 | 5. Submission of Contributions. Unless You explicitly state otherwise, 131 | any Contribution intentionally submitted for inclusion in the Work 132 | by You to the Licensor shall be under the terms and conditions of 133 | this License, without any additional terms or conditions. 134 | Notwithstanding the above, nothing herein shall supersede or modify 135 | the terms of any separate license agreement you may have executed 136 | with Licensor regarding such Contributions. 137 | 138 | 6. Trademarks. This License does not grant permission to use the trade 139 | names, trademarks, service marks, or product names of the Licensor, 140 | except as required for reasonable and customary use in describing the 141 | origin of the Work and reproducing the content of the NOTICE file. 142 | 143 | 7. Disclaimer of Warranty. Unless required by applicable law or 144 | agreed to in writing, Licensor provides the Work (and each 145 | Contributor provides its Contributions) on an "AS IS" BASIS, 146 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or 147 | implied, including, without limitation, any warranties or conditions 148 | of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A 149 | PARTICULAR PURPOSE. You are solely responsible for determining the 150 | appropriateness of using or redistributing the Work and assume any 151 | risks associated with Your exercise of permissions under this License. 152 | 153 | 8. Limitation of Liability. In no event and under no legal theory, 154 | whether in tort (including negligence), contract, or otherwise, 155 | unless required by applicable law (such as deliberate and grossly 156 | negligent acts) or agreed to in writing, shall any Contributor be 157 | liable to You for damages, including any direct, indirect, special, 158 | incidental, or consequential damages of any character arising as a 159 | result of this License or out of the use or inability to use the 160 | Work (including but not limited to damages for loss of goodwill, 161 | work stoppage, computer failure or malfunction, or any and all 162 | other commercial damages or losses), even if such Contributor 163 | has been advised of the possibility of such damages. 164 | 165 | 9. Accepting Warranty or Additional Liability. While redistributing 166 | the Work or Derivative Works thereof, You may choose to offer, 167 | and charge a fee for, acceptance of support, warranty, indemnity, 168 | or other liability obligations and/or rights consistent with this 169 | License. However, in accepting such obligations, You may act only 170 | on Your own behalf and on Your sole responsibility, not on behalf 171 | of any other Contributor, and only if You agree to indemnify, 172 | defend, and hold each Contributor harmless for any liability 173 | incurred by, or claims asserted against, such Contributor by reason 174 | of your accepting any such warranty or additional liability. 175 | 176 | END OF TERMS AND CONDITIONS 177 | 178 | APPENDIX: How to apply the Apache License to your work. 179 | 180 | To apply the Apache License to your work, attach the following 181 | boilerplate notice, with the fields enclosed by brackets "{}" 182 | replaced with your own identifying information. (Don't include 183 | the brackets!) The text should be enclosed in the appropriate 184 | comment syntax for the file format. We also recommend that a 185 | file or class name and description of purpose be included on the 186 | same "printed page" as the copyright notice for easier 187 | identification within third-party archives. 188 | 189 | Copyright {yyyy} {name of copyright owner} 190 | 191 | Licensed under the Apache License, Version 2.0 (the "License"); 192 | you may not use this file except in compliance with the License. 193 | You may obtain a copy of the License at 194 | 195 | http://www.apache.org/licenses/LICENSE-2.0 196 | 197 | Unless required by applicable law or agreed to in writing, software 198 | distributed under the License is distributed on an "AS IS" BASIS, 199 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 200 | See the License for the specific language governing permissions and 201 | limitations under the License. 202 | -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | # scasm 2 | ## writing a dynamic x86_64 assembler in Scala 3 | 4 | This is the final code for my live coding session at **DevoxxFR 2016** I have made with [Criteo Labs](http://labs.criteo.com/). The goal of this presentation was to write a dynamic assembler in Scala; or how to create a Scala function from the final `x86_64` assembly code. 5 | 6 | Have a look at the [final code](https://github.com/guillaumebort/scasm/blob/master/scasm.scala). 7 | 8 | Do not ask for the final goal of this: this is more a learning vehicle to abord several interesting topics. 9 | 10 | As an example function I wanted to generate at runtime, I decided to go with the `add: (Int,Int) => Int` function. The assembly code for that is: 11 | 12 | ```asm 13 | mov rax, rdi 14 | add rax, rsi 15 | ret 16 | ``` 17 | 18 | Which can be read as: 19 | - Move the content of register `rdi` to register `rax`. 20 | - Add the content of register `rsi` to register `rax` and store the result to `rax`. 21 | - Return 22 | 23 | Why do I use these specific registers for that? Because I was doing this presentation using MacOS on a 64bits intel laptop. So I have to follow the _System V x86_64_ ABI. If you want to do this on Linux it should be the same. On Windows you probably need to adapt. On 32bits systems it will be more complicated because the parameters are passed on the stack from the begining, so you need more instructions. 24 | 25 | Check this about the ABI: http://wiki.osdev.org/System_V_ABI 26 | 27 | So the presentation was organized in 2 parts: 28 | - Finding a way to embed the assembly code into Scala. 29 | - Making it executable. 30 | 31 | ### Embedding assembly into Scala code 32 | 33 | Actually this part is pretty easy. After having defined all the required data structures to represent Registers, Operands and Instructions, I have used a custom `StringContext` interpolation, and [Scala parser combinator](https://github.com/scala/scala-parser-combinators). 34 | 35 | At the end of this part I was able to write something like: 36 | 37 | ```scala 38 | val add: Seq[Instr] = 39 | asm""" 40 | mov rax, rdi 41 | add rax, rsi 42 | ret 43 | """ 44 | ``` 45 | 46 | ### Making it executable 47 | 48 | The first step is to generate machine code from the asm representation. For that I have just written a minimal assembler supporting the required instructions/access modes. 49 | 50 | Useful resources for that: 51 | - http://www.codeproject.com/Articles/662301/x-Instruction-Encoding-Revealed-Bit-Twiddling-fo 52 | - http://wiki.osdev.org/X86-64_Instruction_Encoding 53 | - http://ref.x86asm.net/coder64.html 54 | 55 | To check the result of this assembler you can compare with a real existing assembler. For example using `nasm`, I have created this asm file: 56 | 57 | ```asm 58 | [bits 64] 59 | 60 | mov rax, rdi 61 | add rax, rsi 62 | ret 63 | ``` 64 | 65 | And I have compared the output with mine by running: 66 | 67 | ``` 68 | $ nasm add.asm && hexdump add 69 | ``` 70 | 71 | Then I had to load this code in memory and to make it executable. For that I have used `sun.misc.Unsafe` to allocate an aligned page of memory (see the hack to get an aligned page). And then I have used **JNA** to make a wrapper to the libc allowing me to call `int mprotect(void *addr, size_t len, int prot);`. 72 | 73 | At this point the code was loaded in memory and marked as executable. I have used **JNA** again to get a native function from the pointer. At the end using Scala implicit conversion I was able to cast it to a proper Scala function type, allowing me to write: 74 | 75 | ```scala 76 | val add: (Int,Int) => Int = nativeFunction( 77 | asm""" 78 | mov rax, rdi 79 | add rax, rsi 80 | ret 81 | """ 82 | ) 83 | 84 | println(add(3,2)) 85 | ``` 86 | 87 | A real Scala function created from assembly code => **CHECK** 88 | -------------------------------------------------------------------------------- /build.sbt: -------------------------------------------------------------------------------- 1 | offline := true 2 | scalaVersion := "2.11.8" 3 | 4 | libraryDependencies += "org.scala-lang" % "scala-reflect" % "2.11.8" 5 | libraryDependencies += "org.scala-lang.modules" %% "scala-parser-combinators" % "1.0.4" 6 | libraryDependencies += "net.java.dev.jna" % "jna" % "4.2.1" 7 | -------------------------------------------------------------------------------- /scasm.scala: -------------------------------------------------------------------------------- 1 | // WARNING! Run only on MacOS 64 bits 2 | 3 | import com.sun.jna._ 4 | import scala.util.parsing.combinator._ 5 | 6 | object Scasm { 7 | 8 | lazy val unsafe = { 9 | val theUnsafe = classOf[sun.misc.Unsafe].getDeclaredField("theUnsafe") 10 | theUnsafe.setAccessible(true) 11 | theUnsafe.get(null).asInstanceOf[sun.misc.Unsafe] 12 | } 13 | 14 | def lebytes(x: Long) = { 15 | import java.nio._ 16 | val buffer = ByteBuffer.allocate(java.lang.Long.BYTES) 17 | buffer.order(ByteOrder.LITTLE_ENDIAN) 18 | buffer.putLong(x) 19 | buffer.array 20 | } 21 | 22 | val rex = 0x40 + 0x08 23 | 24 | sealed trait Instr { 25 | def bytes: Seq[Byte] 26 | } 27 | case class Mov(to: Operand, from: Operand) extends Instr { 28 | def bytes = (to, from) match { 29 | case (RegisterDirect(r1), RegisterDirect(r2)) => 30 | Seq(rex, 0x89, 0xC0 + (r2.code << 3) + r1.code).map(_.toByte) 31 | case (RegisterDirect(r), Immediate(v)) => 32 | Seq(rex, 0xb8 + r.code).map(_.toByte) ++ lebytes(v) 33 | case _ => ??? 34 | } 35 | } 36 | case class Add(to: Operand, from: Operand) extends Instr { 37 | def bytes = (to, from) match { 38 | case (RegisterDirect(r1), RegisterDirect(r2)) => 39 | Seq(rex, 0x01, 0xC0 + (r2.code << 3) + r1.code).map(_.toByte) 40 | case _ => ??? 41 | } 42 | } 43 | case object Syscall extends Instr { 44 | def bytes = Seq(0x0f, 0x05).map(_.toByte) 45 | } 46 | case object Ret extends Instr { 47 | def bytes = Seq(0xc3).map(_.toByte) 48 | } 49 | 50 | sealed trait Register { 51 | def code: Byte 52 | } 53 | case object Rax extends Register { 54 | val code = 0x0.toByte 55 | } 56 | case object Rdx extends Register { 57 | val code = 0x2.toByte 58 | } 59 | case object Rsi extends Register { 60 | val code = 0x6.toByte 61 | } 62 | case object Rdi extends Register { 63 | val code = 0x7.toByte 64 | } 65 | 66 | sealed trait Operand 67 | case class RegisterDirect(register: Register) extends Operand 68 | case class Immediate(value: Long) extends Operand 69 | 70 | object AsmParser extends RegexParsers { 71 | def register = 72 | ( "rax" ^^^ Rax 73 | | "rdx" ^^^ Rdx 74 | | "rsi" ^^^ Rsi 75 | | "rdi" ^^^ Rdi 76 | ) 77 | 78 | def directRegister = register ^^ RegisterDirect.apply 79 | def immediate = "(0x)?[0-9]+".r ^^ { case v => Immediate(java.lang.Long.decode(v)) } 80 | def operand = directRegister | immediate 81 | 82 | def instruction = 83 | ( "add" ~> operand ~ "," ~ operand ^^ { case to ~ _ ~ from => Add(to, from) } 84 | | "mov" ~> operand ~ "," ~ operand ^^ { case to ~ _ ~ from => Mov(to, from) } 85 | | "syscall" ^^^ Syscall 86 | | "ret" ^^^ Ret 87 | ) 88 | } 89 | 90 | implicit class InlineAssembly(val sc: StringContext) { 91 | def asm(args: Any*): List[Instr] = { 92 | val code = sc.parts.zipAll(args, "", "").map { case (x,y) => x + y }.mkString 93 | 94 | code 95 | .split("\n") 96 | .map(_.trim) 97 | .filterNot(_.isEmpty) 98 | .map(AsmParser.parse(AsmParser.instruction, _)) 99 | .collect { 100 | case AsmParser.Success(instr, _) => instr 101 | } 102 | .toList 103 | } 104 | } 105 | 106 | implicit class Instructions(val instr: List[Instr]) { 107 | def dump: String = instr.flatMap(_.bytes).map(b => f"${b & 0xFF}%02x").mkString(" ") 108 | } 109 | 110 | def allocateAlignedMemoryPage = { 111 | val pageSize = unsafe.pageSize 112 | val memory = unsafe.allocateMemory(pageSize * 2) 113 | (memory + (pageSize - memory % pageSize), pageSize) 114 | } 115 | 116 | def allocate(str: String) = { 117 | val bytes = str.getBytes("utf-8") 118 | val address = unsafe.allocateMemory(bytes.size) 119 | bytes.zipWithIndex.foreach { 120 | case (b, i) => unsafe.putByte(address + i, b) 121 | } 122 | (address, bytes.size) 123 | } 124 | 125 | trait Libc extends Library { 126 | def mprotect(addr: Pointer, len: Long, prot: Int): Int 127 | } 128 | 129 | object Libc extends Libc { 130 | private val lib = Native.loadLibrary("c", classOf[Libc]).asInstanceOf[Libc] 131 | 132 | val PROT_NONE = 0 133 | val PROT_READ = 1 134 | val PROT_WRITE = 2 135 | val PROT_EXEC = 4 136 | 137 | def mprotect(addr: Pointer, len: Long, prot: Int) = lib.mprotect(addr, len, prot) 138 | } 139 | 140 | def nativeFunction(code: Seq[Instr]) = { 141 | import Libc._ 142 | val (address, size) = allocateAlignedMemoryPage 143 | assert( 144 | 0 == mprotect(new Pointer(address), size, PROT_READ | PROT_WRITE | PROT_EXEC), 145 | "mprotect failed!" 146 | ) 147 | code.flatMap(_.bytes).zipWithIndex.foreach { 148 | case (b, o) => unsafe.putByte(address + o, b) 149 | } 150 | Function.getFunction(new Pointer(address)) 151 | } 152 | 153 | implicit def intFunction1[A](f: Function): A => Int = { (a: A) => 154 | f.invokeInt(Array(a.asInstanceOf[AnyRef])) 155 | } 156 | 157 | implicit def intFunction2[A,B](f: Function): (A,B) => Int = { (a: A, b: B) => 158 | f.invokeInt(Array(a.asInstanceOf[AnyRef], b.asInstanceOf[AnyRef])) 159 | } 160 | 161 | implicit def voidFunction0(f: Function): () => Unit = { () => 162 | f.invokeVoid(Array()) 163 | } 164 | 165 | def main(args: Array[String]) { 166 | 167 | val add: (Int,Int) => Int = nativeFunction( 168 | asm""" 169 | mov rax, rdi 170 | add rax, rsi 171 | ret 172 | """ 173 | ) 174 | 175 | val result = add(5, add(3, 2)) 176 | println(result) 177 | 178 | def adder(m: Int): Int => Int = { 179 | nativeFunction( 180 | asm""" 181 | mov rax, rdi 182 | mov rsi, $m 183 | add rax, rsi 184 | ret 185 | """ 186 | ) 187 | } 188 | 189 | val add4 = adder(4) 190 | println(add4(12)) 191 | 192 | def yoloPrint(msg: String): () => Unit = nativeFunction { 193 | val (pointer, size) = allocate(msg) 194 | asm""" 195 | mov rax, 0x2000004 196 | mov rdx, $size 197 | mov rsi, $pointer 198 | mov rdi, 1 199 | syscall 200 | ret 201 | """ 202 | } 203 | 204 | val helloWorld = yoloPrint("Hello, DevoxxFR!\n") 205 | helloWorld() 206 | } 207 | 208 | } 209 | --------------------------------------------------------------------------------