Compare commits

..

29 Commits

Author SHA1 Message Date
IntoTheNight da8dc69ea0 Merge pull request 'master' (#1) from AbleOS/holey-bytes:master into master
Reviewed-on: IntoTheNight/holey-bytes#1
2023-07-11 09:28:48 +00:00
MunirG05 82ce817802 the design is very human 2023-07-11 14:54:49 +05:30
MunirG05 08e413de72 add fancy errors 2023-07-11 14:38:20 +05:30
ondra05 e7c014f6e4
doc 2023-07-11 10:33:55 +02:00
MunirG05 7e363c465f tried to shove the timer back in 2023-07-11 14:03:25 +05:30
ondra05 32b63c0f23
Moved 2023-07-11 10:32:26 +02:00
ondra05 9c93a0fa8f
wrap around timer 2023-07-11 10:31:03 +02:00
ondra05 d8ee65b873
Implement timer 2023-07-11 10:29:23 +02:00
ondra05 8a9e485d45
Improved assembler library 2023-07-11 02:08:55 +02:00
ondra05 3ec7e5f29f
Moved 2023-07-10 23:18:23 +02:00
ondra05 b6ea49a1b5
Rename 2023-07-07 15:23:53 +02:00
ondra05 5852a640bb
Updated flots 2023-07-07 15:22:03 +02:00
ondra05 9bc3000782
assert char bit 2023-07-07 14:36:40 +02:00
ondra05 e01e2ea7a7
Updated C header 2023-07-07 14:33:08 +02:00
ondra05 3c19cd4c9a
Updated spec 2023-07-07 14:33:07 +02:00
able b7c34775e4 HBASM: derp forgot that deps also need to be nostd 2023-06-26 05:23:52 -05:00
able 69d2516ca3 HBASM: no_std compatible now 2023-06-26 05:18:14 -05:00
ondra05 8a3616b352
Improved unhandled trap handling 2023-06-25 00:28:20 +02:00
ondra05 1ff31e47a4
Stole docs 2023-06-25 00:21:40 +02:00
ondra05 45d1265007
docs 2023-06-25 00:18:31 +02:00
ondra05 42e4cb6273
Implemented traps 2023-06-25 00:16:14 +02:00
able 8ab55e801f Initial work on a simple serial driver for ableos 2023-06-21 08:22:56 -05:00
able eefde51ddf Update to stable 2023-06-21 08:22:21 -05:00
able 453309f2a4 clear out assets 2023-06-21 07:54:10 -05:00
able 5edf0a1b9b NIX: fix nix-shell 2023-06-21 07:53:01 -05:00
ondra05 c0fb38d717
HoleyBytes, almost adhering the spec
- Changed instruction encoding to be faster to match on
- Implemented all instructions defined in spec
- Bytecode validation
- Assembler
- Implemented 5 level paging (based on SV57)
- Implemented some degree of interrupts (though not fully adhering the spec yet)
2023-06-21 02:07:48 +02:00
ondra05 64745257b2
a 2023-05-28 23:38:26 +02:00
ondra05 f99f729be6
fixup32 2023-05-28 23:37:43 +02:00
ondra05 908ee5b922
Changed register handling 2023-05-28 16:49:01 +02:00
123 changed files with 2166 additions and 8944 deletions

View File

@ -1,2 +0,0 @@
[alias]
xtask = "r -p xtask --"

540
Cargo.lock generated
View File

@ -2,101 +2,38 @@
# It is not intended for manual editing.
version = 3
[[package]]
name = "addr2line"
version = "0.21.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "8a30b2e23b9e17a9f90641c7ab1549cd9b44f296d3ccbf309d2863cfe398a0cb"
dependencies = [
"gimli",
]
[[package]]
name = "adler"
version = "1.0.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "f26201604c87b1e01bd3d98f8d5d9a8fcbb815e8cedb41ffccbeb4bf593a35fe"
[[package]]
name = "ahash"
version = "0.8.8"
version = "0.8.3"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "42cd52102d3df161c77a887b608d7a4897d7cc112886a9537b738a887a03aaff"
checksum = "2c99f64d1e06488f620f932677e24bc6e2897582980441ae90a671415bd7ec2f"
dependencies = [
"cfg-if",
"const-random",
"getrandom",
"once_cell",
"version_check",
"zerocopy",
]
[[package]]
name = "argh"
version = "0.1.12"
name = "allocator-api2"
version = "0.2.15"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "7af5ba06967ff7214ce4c7419c7d185be7ecd6cc4965a8f6e1d8ce0398aad219"
checksum = "56fc6cf8dc8c4158eed8649f9b8b0ea1518eb62b544fe9490d66fa0b349eafe9"
[[package]]
name = "ariadne"
version = "0.3.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "72fe02fc62033df9ba41cba57ee19acf5e742511a140c7dbc3a873e19a19a1bd"
dependencies = [
"argh_derive",
"argh_shared",
"unicode-width",
"yansi",
]
[[package]]
name = "argh_derive"
version = "0.1.12"
name = "beef"
version = "0.5.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "56df0aeedf6b7a2fc67d06db35b09684c3e8da0c95f8f27685cb17e08413d87a"
dependencies = [
"argh_shared",
"proc-macro2",
"quote",
"syn 2.0.48",
]
[[package]]
name = "argh_shared"
version = "0.1.12"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "5693f39141bda5760ecc4111ab08da40565d1771038c4a0250f03457ec707531"
dependencies = [
"serde",
]
[[package]]
name = "autocfg"
version = "1.1.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "d468802bab17cbc0cc575e9b053f41e72aa36bfa6b7f55e3529ffa43161b97fa"
[[package]]
name = "backtrace"
version = "0.3.69"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "2089b7e3f35b9dd2d0ed921ead4f6d318c27680d4a5bd167b3ee120edb105837"
dependencies = [
"addr2line",
"cc",
"cfg-if",
"libc",
"miniz_oxide",
"object",
"rustc-demangle",
]
[[package]]
name = "bitflags"
version = "2.4.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "ed570934406eb16438a4e976b1b4500774099c13b8cb96eec99f620f05090ddf"
[[package]]
name = "cc"
version = "1.0.83"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "f1174fb0b6ec23863f8b971027804a42614e347eafb0a95bf0b12cdae21fc4d0"
dependencies = [
"libc",
]
checksum = "3a8241f3ebb85c056b509d4327ad0358fbbba6ffb340bf388f26350aeda225b1"
[[package]]
name = "cfg-if"
@ -105,314 +42,190 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "baf1de4339761588bc0619e3cbc0120ee582ebb74b53b4efbf79117bd2da40fd"
[[package]]
name = "color-eyre"
version = "0.6.2"
name = "convert_case"
version = "0.4.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "5a667583cca8c4f8436db8de46ea8233c42a7d9ae424a82d338f2e4675229204"
checksum = "6245d59a3e82a7fc217c5828a6692dbc6dfb63a0c8c90495621f7b9d79704a0e"
[[package]]
name = "delegate"
version = "0.9.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "d358e0ec5c59a5e1603b933def447096886121660fc680dc1e64a0753981fe3c"
dependencies = [
"backtrace",
"color-spantrace",
"eyre",
"indenter",
"once_cell",
"owo-colors",
"tracing-error",
"proc-macro2",
"quote",
"syn 1.0.109",
]
[[package]]
name = "color-spantrace"
version = "0.2.1"
name = "derive_more"
version = "0.99.17"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "cd6be1b2a7e382e2b98b43b2adcca6bb0e465af0bdd38123873ae61eb17a72c2"
checksum = "4fb810d30a7c1953f91334de7244731fc3f3c10d7fe163338a35b9f640960321"
dependencies = [
"once_cell",
"owo-colors",
"tracing-core",
"tracing-error",
"convert_case",
"proc-macro2",
"quote",
"rustc_version",
"syn 1.0.109",
]
[[package]]
name = "const-random"
version = "0.1.17"
name = "fnv"
version = "1.0.7"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "5aaf16c9c2c612020bcfd042e170f6e32de9b9d75adb5277cdbbd2e2c8c8299a"
checksum = "3f9eec918d3f24069decb9af1554cad7c880e2da24a9afd88aca000531ab82c1"
[[package]]
name = "hashbrown"
version = "0.13.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "43a3c133739dddd0d2990f9a4bdf8eb4b21ef50e4851ca85ab661199821d510e"
dependencies = [
"const-random-macro",
"ahash",
]
[[package]]
name = "const-random-macro"
version = "0.1.16"
name = "hashbrown"
version = "0.14.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "f9d839f2a20b0aee515dc581a6172f2321f96cab76c1a38a4c584a194955390e"
checksum = "2c6201b9ff9fd90a5a3bac2e56a830d0caa509576f0e503818ee82c181b3437a"
dependencies = [
"getrandom",
"once_cell",
"tiny-keccak",
"ahash",
"allocator-api2",
]
[[package]]
name = "crunchy"
version = "0.2.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "7a81dae078cea95a014a339291cec439d2f232ebe854a9d672b796c6afafa9b7"
[[package]]
name = "eyre"
version = "0.6.12"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "7cd915d99f24784cdc19fd37ef22b97e3ff0ae756c7e492e9fbfe897d61e2aec"
dependencies = [
"indenter",
"once_cell",
]
[[package]]
name = "getrandom"
version = "0.2.12"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "190092ea657667030ac6a35e305e62fc4dd69fd98ac98631e5d3a2b1575a12b5"
dependencies = [
"cfg-if",
"libc",
"wasi",
]
[[package]]
name = "gimli"
version = "0.28.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "4271d37baee1b8c7e4b708028c57d816cf9d2434acb33a549475f78c181f6253"
[[package]]
name = "hbasm"
version = "0.1.0"
dependencies = [
"ariadne",
"hashbrown 0.14.0",
"hbbytecode",
"lasso",
"logos",
"paste",
"rhai",
"with_builtin_macros",
]
[[package]]
name = "hbbytecode"
version = "0.1.0"
dependencies = [
"paste",
"with_builtin_macros",
]
[[package]]
name = "hblang"
version = "0.1.0"
dependencies = [
"hbvm",
]
[[package]]
name = "hbvm"
version = "0.1.0"
dependencies = [
"delegate",
"derive_more",
"hashbrown 0.13.2",
"hbbytecode",
"log",
"paste",
"static_assertions",
]
[[package]]
name = "hbxrt"
version = "0.1.0"
name = "lasso"
version = "0.7.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "4644821e1c3d7a560fe13d842d13f587c07348a1a05d3a797152d41c90c56df2"
dependencies = [
"hbvm",
"memmap2",
"ahash",
"hashbrown 0.13.2",
]
[[package]]
name = "indenter"
version = "0.3.3"
name = "log"
version = "0.4.17"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "ce23b50ad8242c51a442f3ff322d56b02f08852c77e4c0b4d3fd684abc89c683"
[[package]]
name = "instant"
version = "0.1.12"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "7a5bbe824c507c5da5956355e86a746d82e0e1464f65d862cc5e71da70e94b2c"
checksum = "abb12e687cfb44aa40f41fc3978ef76448f9b6038cad6aef4259d3c095a2382e"
dependencies = [
"cfg-if",
]
[[package]]
name = "lazy_static"
version = "1.4.0"
name = "logos"
version = "0.13.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "e2abad23fbc42b3700f2f279844dc832adb2b2eb069b2df918f455c4e18cc646"
[[package]]
name = "libc"
version = "0.2.153"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "9c198f91728a82281a64e1f4f9eeb25d82cb32a5de251c6bd1b5154d63a8e7bd"
[[package]]
name = "memchr"
version = "2.7.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "523dc4f511e55ab87b694dc30d0f820d60906ef06413f93d4d7a1385599cc149"
[[package]]
name = "memmap2"
version = "0.9.4"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "fe751422e4a8caa417e13c3ea66452215d7d63e19e604f4980461212f3ae1322"
checksum = "c000ca4d908ff18ac99b93a062cb8958d331c3220719c52e77cb19cc6ac5d2c1"
dependencies = [
"libc",
"logos-derive",
]
[[package]]
name = "miniz_oxide"
version = "0.7.2"
name = "logos-codegen"
version = "0.13.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "9d811f3e15f28568be3407c8e7fdb6514c1cda3cb30683f15b6a1a1dc4ea14a7"
checksum = "dc487311295e0002e452025d6b580b77bb17286de87b57138f3b5db711cded68"
dependencies = [
"adler",
"beef",
"fnv",
"proc-macro2",
"quote",
"regex-syntax",
"syn 2.0.18",
]
[[package]]
name = "num-traits"
version = "0.2.18"
name = "logos-derive"
version = "0.13.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "da0df0e5185db44f69b44f26786fe401b6c293d1907744beaa7fa62b2e5a517a"
checksum = "dbfc0d229f1f42d790440136d941afd806bc9e949e2bcb8faa813b0f00d1267e"
dependencies = [
"autocfg",
]
[[package]]
name = "object"
version = "0.32.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "a6a622008b6e321afc04970976f62ee297fdbaa6f95318ca343e3eebb9648441"
dependencies = [
"memchr",
"logos-codegen",
]
[[package]]
name = "once_cell"
version = "1.19.0"
version = "1.17.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "3fdb12b2476b595f9358c5161aa467c2438859caa136dec86c26fdd2efe17b92"
[[package]]
name = "owo-colors"
version = "3.5.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "c1b04fb49957986fdce4d6ee7a65027d55d4b6d2265e5848bbb507b58ccfdb6f"
checksum = "b7e5500299e16ebb147ae15a00a942af264cf3688f47923b8fc2cd5858f23ad3"
[[package]]
name = "paste"
version = "1.0.14"
version = "1.0.12"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "de3145af08024dea9fa9914f381a17b8fc6034dfb00f3a84013f7ff43f29ed4c"
[[package]]
name = "pin-project-lite"
version = "0.2.13"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "8afb450f006bf6385ca15ef45d71d2288452bc3683ce2e2cacc0d18e4be60b58"
checksum = "9f746c4065a8fa3fe23974dd82f15431cc8d40779821001404d10d2e79ca7d79"
[[package]]
name = "proc-macro2"
version = "1.0.78"
version = "1.0.59"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "e2422ad645d89c99f8f3e6b88a9fdeca7fabeac836b1002371c4367c8f984aae"
checksum = "6aeca18b86b413c660b781aa319e4e2648a3e6f9eadc9b47e9038e6fe9f3451b"
dependencies = [
"unicode-ident",
]
[[package]]
name = "quote"
version = "1.0.35"
version = "1.0.28"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "291ec9ab5efd934aaf503a6466c5d5251535d108ee747472c3977cc5acc868ef"
checksum = "1b9ab9c7eadfd8df19006f1cf1a4aed13540ed5cbc047010ece5826e10825488"
dependencies = [
"proc-macro2",
]
[[package]]
name = "rhai"
version = "1.17.1"
name = "regex-syntax"
version = "0.6.29"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "f6273372244d04a8a4b0bec080ea1e710403e88c5d9d83f9808b2bfa64f0982a"
checksum = "f162c6dd7b008981e4d40210aca20b4bd0f9b60ca9271061b07f78537722f2e1"
[[package]]
name = "rustc_version"
version = "0.4.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "bfa0f585226d2e68097d4f95d113b15b83a82e819ab25717ec0590d9584ef366"
dependencies = [
"ahash",
"bitflags",
"instant",
"num-traits",
"once_cell",
"rhai_codegen",
"smallvec",
"smartstring",
"thin-vec",
"semver",
]
[[package]]
name = "rhai_codegen"
version = "2.0.0"
name = "semver"
version = "1.0.17"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "9db7f8dc4c9d48183a17ce550574c42995252b82d267eaca3fcd1b979159856c"
dependencies = [
"proc-macro2",
"quote",
"syn 2.0.48",
]
[[package]]
name = "rustc-demangle"
version = "0.1.23"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "d626bb9dae77e28219937af045c257c28bfd3f69333c512553507f5f9798cb76"
[[package]]
name = "serde"
version = "1.0.196"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "870026e60fa08c69f064aa766c10f10b1d62db9ccd4d0abb206472bee0ce3b32"
dependencies = [
"serde_derive",
]
[[package]]
name = "serde_derive"
version = "1.0.196"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "33c85360c95e7d137454dc81d9a4ed2b8efd8fbe19cee57357b32b9771fccb67"
dependencies = [
"proc-macro2",
"quote",
"syn 2.0.48",
]
[[package]]
name = "sharded-slab"
version = "0.1.7"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "f40ca3c46823713e0d4209592e8d6e826aa57e928f09752619fc696c499637f6"
dependencies = [
"lazy_static",
]
[[package]]
name = "smallvec"
version = "1.13.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "e6ecd384b10a64542d77071bd64bd7b231f4ed5940fba55e98c3de13824cf3d7"
[[package]]
name = "smartstring"
version = "1.0.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "3fb72c633efbaa2dd666986505016c32c3044395ceaf881518399d2f4127ee29"
dependencies = [
"autocfg",
"static_assertions",
"version_check",
]
checksum = "bebd363326d05ec3e2f532ab7660680f3b02130d780c299bca73469d521bc0ed"
[[package]]
name = "static_assertions"
@ -433,92 +246,26 @@ dependencies = [
[[package]]
name = "syn"
version = "2.0.48"
version = "2.0.18"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "0f3531638e407dfc0814761abb7c00a5b54992b849452a0646b7f65c9f770f3f"
checksum = "32d41677bcbe24c20c52e7c70b0d8db04134c5d1066bf98662e2871ad200ea3e"
dependencies = [
"proc-macro2",
"quote",
"unicode-ident",
]
[[package]]
name = "thin-vec"
version = "0.2.13"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "a38c90d48152c236a3ab59271da4f4ae63d678c5d7ad6b7714d7cb9760be5e4b"
[[package]]
name = "thread_local"
version = "1.1.7"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "3fdd6f064ccff2d6567adcb3873ca630700f00b5ad3f060c25b5dcfd9a4ce152"
dependencies = [
"cfg-if",
"once_cell",
]
[[package]]
name = "tiny-keccak"
version = "2.0.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "2c9d3793400a45f954c52e73d068316d76b6f4e36977e3fcebb13a2721e80237"
dependencies = [
"crunchy",
]
[[package]]
name = "tracing"
version = "0.1.40"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "c3523ab5a71916ccf420eebdf5521fcef02141234bbc0b8a49f2fdc4544364ef"
dependencies = [
"pin-project-lite",
"tracing-core",
]
[[package]]
name = "tracing-core"
version = "0.1.32"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "c06d3da6113f116aaee68e4d601191614c9053067f9ab7f6edbcb161237daa54"
dependencies = [
"once_cell",
"valuable",
]
[[package]]
name = "tracing-error"
version = "0.2.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "d686ec1c0f384b1277f097b2f279a2ecc11afe8c133c1aabf036a27cb4cd206e"
dependencies = [
"tracing",
"tracing-subscriber",
]
[[package]]
name = "tracing-subscriber"
version = "0.3.18"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "ad0f048c97dbd9faa9b7df56362b8ebcaa52adb06b498c050d2f4e32f90a7a8b"
dependencies = [
"sharded-slab",
"thread_local",
"tracing-core",
]
[[package]]
name = "unicode-ident"
version = "1.0.12"
version = "1.0.9"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "3354b9ac3fae1ff6755cb6db53683adb661634f67557942dea4facebec0fee4b"
checksum = "b15811caf2415fb889178633e7724bad2509101cde276048e013b9def5e51fa0"
[[package]]
name = "valuable"
version = "0.1.0"
name = "unicode-width"
version = "0.1.10"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "830b7e5d4d90034032940e4ace0d9a9a057e7a45cd94e6c007832e39edb82f6d"
checksum = "c0edd1e5b14653f783770bce4a4dabb4a5108a5370a5f5d8cfe8710c361f6c8b"
[[package]]
name = "version_check"
@ -527,56 +274,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "49874b5167b65d7193b8aba1567f5c7d93d001cafc34600cee003eda787e483f"
[[package]]
name = "wasi"
version = "0.11.0+wasi-snapshot-preview1"
name = "yansi"
version = "0.5.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "9c8d87e72b64a3b4db28d11ce29237c246188f4f51057d65a7eab63b7987e423"
[[package]]
name = "with_builtin_macros"
version = "0.0.3"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "a59d55032495429b87f9d69954c6c8602e4d3f3e0a747a12dea6b0b23de685da"
dependencies = [
"with_builtin_macros-proc_macros",
]
[[package]]
name = "with_builtin_macros-proc_macros"
version = "0.0.3"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "15bd7679c15e22924f53aee34d4e448c45b674feb6129689af88593e129f8f42"
dependencies = [
"proc-macro2",
"quote",
"syn 1.0.109",
]
[[package]]
name = "xtask"
version = "0.1.0"
dependencies = [
"argh",
"color-eyre",
"once_cell",
]
[[package]]
name = "zerocopy"
version = "0.7.32"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "74d4d3961e53fa4c9a25a8637fc2bfaf2595b3d3ae34875568a5cf64787716be"
dependencies = [
"zerocopy-derive",
]
[[package]]
name = "zerocopy-derive"
version = "0.7.32"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "9ce1b18ccd8e73a9321186f97e46f9f04b778851177567b1975109d26a08d2a6"
dependencies = [
"proc-macro2",
"quote",
"syn 2.0.48",
]
checksum = "09041cd90cf85f7f8b2df60c646f853b7f535ce68f85244eb6731cf89fa498ec"

View File

@ -1,3 +1,2 @@
[workspace]
resolver = "2"
members = ["hbasm", "hbbytecode", "hbvm", "hbxrt", "xtask", "hblang"]
members = ["hbasm", "hbbytecode", "hbvm"]

View File

@ -1,100 +0,0 @@
jmp entry
puts:
-- Write string to console
-- r2: [IN] *const u8 String pointer
-- r3: [IN] usize String length
li8 r1, 0x1 -- Write syscall
brc r2, r3, 2 -- Copy parameters
li8 r2, 0x1 -- STDOUT
eca
jal r0, r31, 0
gets:
-- Read string until end of buffer or LF
-- r2: [IN] *mut u8 Buffer
-- r3: [IN] usize Buffer length
-- Register allocations:
-- r33: *mut u8 Buffer end
-- r34: u8 Immediate char
-- r35: u8 Const [0x0A = LF]
li8 r35, 0x0A
add64 r33, r2, r3
-- Setup syscall
li8 r2, 0x1 -- Stdin
cp r3, r2
li8 r4, 0x1 -- Read one char
jeq r3, r33, end
loop:
li8 r1, 0x1 -- Read syscall
eca
addi64 r3, r3, 1
ld r34, r3, 0, 1
jeq r34, r35, end
jne r3, r33, loop
end:
-- Set copied amount
sub64 r1, r33, r3
addi64 r1, -1
jal r0, r31, 0
alloc-pages:
-- Allocate pages
-- r1: [OUT] *mut u8 Pointer to page
-- r2: [IN] u16 Page count
muli16 r3, r2, 4096 -- page count
li8 r1, 0x9 -- mmap syscall
li8 r2, 0x0 -- no address set, kernel chosen
li8 r4, 0x2 -- PROT_WRITE
li8 r5, 0x20 -- MAP_ANONYMOUS
li64 r6, -1 -- Doesn't map file
li8 r7, 0x0 -- Doesn't map file
eca
jal r0, r31, 0
entry:
-- Program entrypoint
-- Register allocations:
-- r32: *mut u8 Buffer
-- r36: usize Read buffer length
-- Allocate one page (4096 KiB)
li8 r2, 1
jal r31, 0, alloc-pages
cp r32, r1
-- Print message
lra16 r2, r0, #enter-your-name
li8 r3, 17
jal r31, r0, puts
-- Read name
cp r2, r32
li16 r3, 4096
jal r31, r0, gets
cp r36, r1
-- Print your name is
lra16 r2, r0, #your-name-is
li8 r3, 15
jal r31, r0, puts
-- And now print the name
cp r2, r32
cp r3, r36
jal r31, r0, puts
tx
#enter-your-name: "Enter your name: "
#your-name-is : "\nYour name is: "

Binary file not shown.

Binary file not shown.

View File

@ -4,6 +4,17 @@ version = "0.1.0"
edition = "2021"
[dependencies]
paste = "1.0"
rhai = "1.16"
with_builtin_macros = "0.0.3"
hbbytecode = { path = "../hbbytecode" }
paste = "1.0"
hashbrown = "0.14.0"
ariadne = "0.3.0"
[dependencies.lasso]
version = "0.7"
default-features = false
features = ["no-std"]
[dependencies.logos]
version = "0.13"
default-features = false
features = ["export_derive"]

View File

@ -0,0 +1,18 @@
jmp r0, start
start:
jmp r0, init_serial_port
-- Uses r20 to set the port
init_serial_port:
add r20, r30, r10
li r20, 00
-- outb(PORT + 1, 0x00); // Disable all interrupts
-- outb(PORT + 3, 0x80); // Enable DLAB (set baud rate divisor)
-- outb(PORT + 0, 0x03); // Set divisor to 3 (lo byte) 38400 baud
-- outb(PORT + 1, 0x00); // (hi byte)
-- outb(PORT + 3, 0x03); // 8 bits, no parity, one stop bit
-- outb(PORT + 2, 0xC7); // Enable FIFO, clear them, with 14-byte threshold
-- outb(PORT + 4, 0x0B); // IRQs enabled, RTS/DSR set
-- outb(PORT + 4, 0x1E); // Set in loopback mode, test the serial chip
-- outb(PORT + 0, 0xAE); // Test serial chip (send byte 0xAE and check if serial returns same byte)

View File

@ -1,13 +0,0 @@
import "hbasm/examples/ableos/std" as std;
fn main(){
std::Error(":+)");
std::Warn("Your mom fell in a well!");
std::Info("Hello, world!");
std::Debug("ABC");
std::Trace("Trace Deez");
tx();
}
main();

View File

@ -1,24 +0,0 @@
fn ipc_send(buffer_id, mem_addr, length){
// set the ecall
li8(r1, 3);
// Set the buffer ID to be the BufferID
li64(r2, buffer_id);
lra(r3, r0, mem_addr);
// set the length
li64(r4, length);
// ecall
eca();
}
private fn log(log_level, string){
let str = data::str(string);
ipc_send(1, str, str.len);
}
fn Error(string) {log(0, string);}
fn Warn(string) {log(1, string);}
fn Info(string) {log(2, string);}
// Due to rhai limitations this cannot be debug
// because of this all of the log levels are upper case
fn Debug(string) {log(3, string);}
fn Trace(string) {log(4, string);}

View File

@ -1,9 +0,0 @@
let hello = data::str("Hello, world!");
li8 (r1, 1); // Write syscall
li8 (r2, 1); // Stdout FD
lra16 (r3, r0, hello); // String buffer
li8 (r4, hello.len); // String length
eca (); // System call
tx (); // End program

View File

@ -1,33 +0,0 @@
li8(r1, 69);
li8(r2, 0);
if_eq(r1, r2,
|| puts("Equals!"),
|| puts("Not equals!"),
);
tx(); // END OF MAIN
/// Inline function write text to stdout
fn puts(string) {
let d = data::str(string);
li8 (r1, 1); // Write syscall
li8 (r2, 1); // Stdout handle
lra16 (r3, r0, d);
li64 (r4, d.len);
eca ();
}
fn if_eq(a, b, thenblk, elseblk) {
let elselbl = declabel();
let endlbl = declabel();
jne(a, b, elselbl);
thenblk.call();
jmp16(endlbl);
elselbl.here();
elseblk.call();
endlbl.here();
}

View File

@ -1,101 +0,0 @@
//! Data section inserts
use {
crate::{object::SymbolRef, SharedObject},
rhai::{CustomType, Engine, FuncRegistration, ImmutableString, Module},
};
/// Generate insertions for data types
///
/// `gen_data_instructions!($module, $obj, [$type, …]);`
/// - `$module`: Rhai module
/// - `$obj`: Code object
/// - `$type`: Type of single array item
macro_rules! gen_data_insertions {
($module:expr, $obj:expr, [$($ty:ident),* $(,)?] $(,)?) => {{
let (module, obj) = ($module, $obj);
$({
// Clone object to each function
let obj = ::std::rc::Rc::clone(obj);
FuncRegistration::new(stringify!($ty))
.with_namespace(rhai::FnNamespace::Global)
.set_into_module::<_, 1, false, _, true, _>(module, move |arr: ::rhai::Array| {
let obj = &mut *obj.borrow_mut();
let symbol = obj.symbol($crate::object::Section::Data);
// Reserve space for object so we don't resize it
// all the time
obj.sections
.data
.reserve(arr.len() * ::std::mem::size_of::<$ty>());
// For every item…
for item in arr {
// … try do conversions from i32 to desired type
// and insert it.
obj.sections.data.extend(
match item.as_int() {
Ok(num) => $ty::try_from(num).map_err(|_| "i64".to_owned()),
Err(ty) => Err(ty.to_owned()),
}
.map_err(|err| {
::rhai::EvalAltResult::ErrorMismatchDataType(
stringify!($ty).to_owned(),
err,
::rhai::Position::NONE,
)
})?
.to_le_bytes(),
);
}
Ok(DataRef {
symbol,
len: obj.sections.data.len() - symbol.0,
})
});
})*
}};
}
/// Reference to entry in data section
#[derive(Clone, Copy, Debug)]
pub struct DataRef {
pub symbol: SymbolRef,
pub len: usize,
}
impl CustomType for DataRef {
fn build(mut builder: rhai::TypeBuilder<Self>) {
builder
.with_name("DataRef")
.with_get("symbol", |this: &mut Self| this.symbol)
.with_get("len", |this: &mut Self| this.len as u64 as i64);
}
}
pub fn module(engine: &mut Engine, obj: SharedObject) -> Module {
let mut module = Module::new();
gen_data_insertions!(&mut module, &obj, [i8, i16, i32, i64]);
// Specialisation for strings, they should be
// inserted as plain UTF-8 arrays
FuncRegistration::new("str")
.with_namespace(rhai::FnNamespace::Global)
.set_into_module::<_, 1, false, _, true, _>(&mut module, move |s: ImmutableString| {
let obj = &mut *obj.borrow_mut();
let symbol = obj.symbol(crate::object::Section::Data);
obj.sections.data.extend(s.as_bytes());
Ok(DataRef {
symbol,
len: s.len(),
})
});
engine.build_type::<DataRef>();
module
}

View File

@ -1,321 +0,0 @@
//! Functions for inserting instructions
//!
//! Most of the code you see is just metaprogramming stuff.
//! This ensures that adding new instructions won't need any
//! specific changes and consistent behaviour.
//!
//! > I tried to comment stuff here, but I meanwhile forgor how it works.
//!
//! — Erin
use {
crate::object::Object,
rhai::{FuncRegistration, Module},
std::{cell::RefCell, rc::Rc},
};
/// Operand types and their insertions
pub mod optypes {
use {
crate::{
label::UnboundLabel,
object::{Object, RelocKey, RelocType, SymbolRef},
},
rhai::{Dynamic, EvalAltResult, ImmutableString, Position},
};
// These types represent operand types to be inserted
pub type R = u8;
pub type B = i8;
pub type H = i16;
pub type W = i32;
pub type D = i64;
pub type A = Dynamic;
pub type O = Dynamic;
pub type P = Dynamic;
/// Insert relocation into code
///
/// - If integer, just write it to the code
/// - Otherwise insert entry into relocation table
/// and fill zeroes
pub fn insert_reloc(
obj: &mut Object,
ty: RelocType,
val: &Dynamic,
) -> Result<(), EvalAltResult> {
match () {
// Direct references insert directly to table
_ if val.is::<SymbolRef>() => {
obj.relocation(RelocKey::Symbol(val.clone_cast::<SymbolRef>().0), ty)
}
_ if val.is::<UnboundLabel>() => {
obj.relocation(RelocKey::Symbol(val.clone_cast::<UnboundLabel>().0), ty)
}
_ if val.is::<DataRef>() => {
obj.relocation(RelocKey::Symbol(val.clone_cast::<DataRef>().symbol.0), ty)
}
// String (indirect) reference
_ if val.is_string() => {
obj.relocation(RelocKey::Label(val.clone_cast::<ImmutableString>()), ty)
}
// Manual offset
_ if val.is_int() => {
let int = val.clone_cast::<i64>();
match ty {
RelocType::Rel32 => obj.sections.text.extend((int as i32).to_le_bytes()),
RelocType::Rel16 => obj.sections.text.extend((int as i16).to_le_bytes()),
RelocType::Abs64 => obj.sections.text.extend(int.to_le_bytes()),
}
}
_ => {
return Err(EvalAltResult::ErrorMismatchDataType(
"SymbolRef, UnboundLabel, String or Int".to_owned(),
val.type_name().to_owned(),
Position::NONE,
))
}
}
Ok(())
}
/// Generate macro for inserting item into the output object
///
/// Pre-defines inserts for absolute address and relative offsets.
/// These are inserted with function [`insert_reloc`]
/// # le_bytes
/// `gen_insert!(le_bytes: [B, …]);`
///
/// Takes sequence of operand types which should be inserted
/// by invoking `to_le_bytes` method on it.
macro_rules! gen_insert {
(le_bytes: [$($lety:ident),* $(,)?]) => {
/// `insert!($thing, $obj, $type)` where
/// - `$thing`: Value you want to insert
/// - `$obj`: Code object
/// - `$type`: Type of inserted value
///
/// Eg. `insert!(69_u8, obj, B);`
macro_rules! insert {
$(($thing:expr, $obj: expr, $lety) => {
$obj.sections.text.extend($thing.to_le_bytes());
};)*
($thing:expr, $obj:expr, A) => {
$crate::ins::optypes::insert_reloc(
$obj,
$crate::object::RelocType::Abs64,
$thing
)?
};
($thing:expr, $obj:expr, O) => {
$crate::ins::optypes::insert_reloc(
$obj,
$crate::object::RelocType::Rel32,
$thing
)?
};
($thing:expr, $obj:expr, P) => {
$crate::ins::optypes::insert_reloc(
$obj,
$crate::object::RelocType::Rel16,
$thing
)?
};
}
};
}
gen_insert!(le_bytes: [R, B, H, W, D]);
#[allow(clippy::single_component_path_imports)]
pub(super) use insert;
use crate::data::DataRef;
}
/// Rhai Types (types for function parameters as Rhai uses only 64bit signed integers)
pub mod rity {
pub use super::optypes::{A, O, P, R};
pub type B = i64;
pub type H = i64;
pub type W = i64;
pub type D = i64;
}
/// Generic instruction (instruction of certain operands type) inserts
pub mod generic {
use {crate::object::Object, rhai::EvalAltResult};
pub(super) fn convert_op<A, B>(from: A) -> Result<B, EvalAltResult>
where
B: TryFrom<A>,
<B as TryFrom<A>>::Error: std::error::Error + Sync + Send + 'static,
{
B::try_from(from).map_err(|e| {
EvalAltResult::ErrorSystem("Data conversion error".to_owned(), Box::new(e))
})
}
/// Generate opcode-generic instruction insert macro
macro_rules! gen_ins {
($($($name:ident : $ty:ty),*;)*) => {
paste::paste! {
$(
/// Instruction-generic opcode insertion function
/// - `obj`: Code object
/// - `opcode`: opcode, not checked if valid for instruction type
/// - … for operands
#[inline]
pub fn [<$($ty:lower)*>](
obj: &mut Object,
opcode: u8,
$($name: $crate::ins::optypes::$ty),*,
) -> Result<(), EvalAltResult> {
// Push opcode
obj.sections.text.push(opcode);
// Insert based on type
$($crate::ins::optypes::insert!(&$name, obj, $ty);)*
Ok(())
}
)*
/// Generate Rhai opcode-specific instruction insertion functions
///
/// `gen_ins_fn!($obj, $opcode, $optype);` where:
/// - `$obj`: Code object
/// - `$opcode`: Opcode value
macro_rules! gen_ins_fn {
$(
($obj:expr, $opcode:expr, [<$($ty)*>]) => {
// Opcode-specific insertion function
// - Parameters = operands
move |$($name: $crate::ins::rity::$ty),*| {
// Invoke generic function
$crate::ins::generic::[<$($ty:lower)*>](
&mut *$obj.borrow_mut(),
$opcode,
$(
// Convert to desired type (from Rhai-provided values)
$crate::ins::generic::convert_op::<
_,
$crate::ins::optypes::$ty
>($name)?
),*
)?;
Ok(())
}
};
// Internal-use: count args
(@arg_count [<$($ty)*>]) => {
{ ["", $(stringify!($ty)),*].len() - 1 }
};
)*
// Specialisation for no-operand instructions
($obj:expr, $opcode:expr, N) => {
move || {
$crate::ins::generic::n(&mut *$obj.borrow_mut(), $opcode);
Ok(())
}
};
// Internal-use specialisation: no-operand instructions
(@arg_count N) => {
{ 0 }
};
}
}
};
}
/// Specialisation for no-operand instructions simply just push opcode
#[inline]
pub fn n(obj: &mut Object, opcode: u8) {
obj.sections.text.push(opcode);
}
// Generate opcode-generic instruction inserters
// (operand identifiers are arbitrary)
//
// New instruction types have to be added manually here
gen_ins! {
o0: R, o1: R;
o0: R, o1: R, o2: R;
o0: R, o1: R, o2: R, o3: R;
o0: R, o1: R, o2: B;
o0: R, o1: R, o2: H;
o0: R, o1: R, o2: W;
o0: R, o1: R, o2: D;
o0: R, o1: B;
o0: R, o1: H;
o0: R, o1: W;
o0: R, o1: D;
o0: R, o1: R, o2: A;
o0: R, o1: R, o2: A, o3: H;
o0: R, o1: R, o2: O, o3: H;
o0: R, o1: R, o2: P, o3: H;
o0: R, o1: R, o2: O;
o0: R, o1: R, o2: P;
o0: O;
o0: P;
}
#[allow(clippy::single_component_path_imports)]
pub(super) use gen_ins_fn;
}
/// Generate instructions from instruction table
///
/// ```ignore
/// instructions!(($module, $obj) {
/// // Data from instruction table
/// $opcode, $mnemonic, $opty, $doc;
/// …
/// });
/// ```
/// - `$module`: Rhai module
/// - `$obj`: Code object
macro_rules! instructions {
(
($module:expr, $obj:expr $(,)?)
{ $($opcode:expr, $mnemonic:ident, $ops:tt, $doc:literal;)* }
) => {{
paste::paste! {
let (module, obj) = ($module, $obj);
$({
// Object is shared across all functions
let obj = Rc::clone(&obj);
// Register newly generated function for each instruction
FuncRegistration::new(stringify!([<$mnemonic:lower>]))
.with_namespace(rhai::FnNamespace::Global)
.set_into_module::<_, { generic::gen_ins_fn!(@arg_count $ops) }, false, _, true, _>(
module,
generic::gen_ins_fn!(
obj,
$opcode,
$ops
)
);
})*
}
}};
}
/// Setup instruction insertors
pub fn setup(module: &mut Module, obj: Rc<RefCell<Object>>) {
// Import instructions table and use it for generation
with_builtin_macros::with_builtin! {
let $spec = include_from_root!("../hbbytecode/instructions.in") in {
instructions!((module, obj) { $spec });
}
}
}

View File

@ -1,112 +0,0 @@
//! Stuff related to labels
use {
crate::SharedObject,
rhai::{Engine, FuncRegistration, ImmutableString, Module},
};
/// Macro for creating functions for Rhai which
/// is bit more friendly
///
/// ```ignore
/// shdm_fns!{
/// module: $module;
/// shared: $shared => $shname;
///
/// $vis fn $name($param_name: $param_ty, …) -> $ret { … }
/// …
/// }
/// ```
/// - `$module`: Rhai module
/// - `$shared`: Data to be shared across the functions
/// - `$shname`: The binding name inside functions
/// - `$vis`: Function visibility for Rhai
/// - Lowercased [`rhai::FnNamespace`] variants
/// - `$name`: Function name
/// - `$param_name`: Parameter name
/// - `$param_ty`: Rust parameter type
/// - `$ret`: Optional return type (otherwise infer)
macro_rules! shdm_fns {
(
module: $module:expr;
shared: $shared:expr => $shname:ident;
$(
$vis:ident fn $name:ident($($param_name:ident: $param_ty:ty),*) $(-> $ret:ty)? $blk:block
)*
) => {{
let module = $module;
let shared = $shared;
paste::paste! {
$({
let $shname = SharedObject::clone(&shared);
FuncRegistration::new(stringify!($name))
.with_namespace(rhai::FnNamespace::[<$vis:camel>])
.set_into_module::<_, { ["", $(stringify!($param_name)),*].len() - 1 }, false, _, true, _>(
module,
move |$($param_name: $param_ty),*| $(-> $ret)? {
let mut $shname = $shname.borrow_mut();
$blk
}
);
})*
}
}};
}
/// Label without any place bound
#[derive(Clone, Copy, Debug)]
pub struct UnboundLabel(pub usize);
pub fn setup(engine: &mut Engine, module: &mut Module, object: SharedObject) {
shdm_fns! {
module: module;
shared: object => obj;
// Insert unnamed label
global fn label() {
let symbol = obj.symbol(crate::object::Section::Text);
Ok(symbol)
}
// Insert string-labeled label
global fn label(label: ImmutableString) {
let symbol = obj.symbol(crate::object::Section::Text);
obj.labels.insert(label, symbol.0);
Ok(symbol)
}
// Declare unbound label (to be bound later)
global fn declabel() {
let index = obj.symbols.len();
obj.symbols.push(None);
Ok(UnboundLabel(index))
}
// Declare unbound label (to be bound later)
// with string label
global fn declabel(label: ImmutableString) {
let index = obj.symbols.len();
obj.symbols.push(None);
obj.labels.insert(label, index);
Ok(UnboundLabel(index))
}
// Set location for unbound label
global fn here(label: UnboundLabel) {
obj.symbols[label.0] = Some(crate::object::SymbolEntry {
location: crate::object::Section::Text,
offset: obj.sections.text.len(),
});
Ok(())
}
}
engine.register_type_with_name::<UnboundLabel>("UnboundLabel");
}

View File

@ -1,45 +1,65 @@
pub mod data;
pub mod ins;
pub mod label;
pub mod linker;
pub mod object;
#![no_std]
#![feature(error_in_core)]
use {
object::Object,
rhai::{Engine, Module},
std::{cell::RefCell, rc::Rc},
};
extern crate alloc;
type SharedObject = Rc<RefCell<Object>>;
pub mod text;
pub fn assembler(
linkout: &mut impl std::io::Write,
loader: impl FnOnce(&mut Engine) -> Result<(), Box<rhai::EvalAltResult>>,
) -> Result<(), Box<dyn std::error::Error>> {
let mut engine = Engine::new();
let mut module = Module::new();
let obj = Rc::new(RefCell::new(Object::default()));
ins::setup(&mut module, Rc::clone(&obj));
label::setup(&mut engine, &mut module, Rc::clone(&obj));
mod macros;
// Registers
for n in 0_u8..=255 {
module.set_var(format!("r{n}"), n);
}
use {alloc::vec::Vec, hashbrown::HashSet};
module.set_native_fn("reg", |n: i64| {
Ok(u8::try_from(n).map_err(|_| {
rhai::EvalAltResult::ErrorRuntime("Invalid register value".into(), rhai::Position::NONE)
})?)
});
module.set_native_fn("as_i64", |n: u8| Ok(n as i64));
let datamod = Rc::new(data::module(&mut engine, SharedObject::clone(&obj)));
engine.register_global_module(Rc::new(module));
engine.register_static_module("data", datamod);
engine.register_type_with_name::<object::SymbolRef>("SymbolRef");
loader(&mut engine)?;
linker::link(obj, linkout)?;
Ok(())
#[derive(Default)]
pub struct Assembler {
pub buf: Vec<u8>,
sub: HashSet<usize>,
}
impl Assembler {
macros::impl_asm!(
bbbb(p0: u8, p1: u8, p2: u8, p3: u8)
=> [DIR, DIRF, FMAF],
bbb(p0: u8, p1: u8, p2: u8)
=> [ADD, SUB, MUL, AND, OR, XOR, SL, SR, SRS, CMP, CMPU, BRC, ADDF, SUBF, MULF],
bbdh(p0: u8, p1: u8, p2: impl Imm, p3: u16)
=> [LD, ST],
bbd(p0: u8, p1: u8, p2: impl Imm)
=> [ADDI, MULI, ANDI, ORI, XORI, SLI, SRI, SRSI, CMPI, CMPUI,
BMC, JEQ, JNE, JLT, JGT, JLTU, JGTU, ADDFI, MULFI],
bb(p0: u8, p1: u8)
=> [NEG, NOT, CP, SWA, NEGF, ITF, FTI],
bd(p0: u8, p1: impl Imm)
=> [LI, JMP],
n()
=> [NOP, ECALL],
);
}
pub trait Imm {
fn insert(&self, asm: &mut Assembler);
}
macro_rules! impl_imm_le_bytes {
($($ty:ty),* $(,)?) => {
$(
impl Imm for $ty {
#[inline(always)]
fn insert(&self, asm: &mut Assembler) {
asm.buf.extend(self.to_le_bytes());
}
}
)*
};
}
impl_imm_le_bytes!(u64, i64, f64);
#[derive(Clone, Copy, Debug, PartialEq, Eq)]
pub struct Symbol(pub u64);
impl Imm for Symbol {
#[inline(always)]
fn insert(&self, asm: &mut Assembler) {
asm.sub.insert(asm.buf.len());
asm.buf.extend(self.0.to_le_bytes());
}
}

View File

@ -1,47 +0,0 @@
//! Simple flat-bytecode linker
use {
crate::{
object::{RelocKey, RelocType, Section},
SharedObject,
},
std::io::Write,
};
pub fn link(object: SharedObject, out: &mut impl Write) -> std::io::Result<()> {
let obj = &mut *object.borrow_mut();
// Walk relocation table entries
for (&loc, entry) in &obj.relocs {
let value = match &entry.key {
// Symbol direct reference
RelocKey::Symbol(sym) => obj.symbols[*sym],
// Label indirect label reference
RelocKey::Label(label) => obj.symbols[obj.labels[label]],
}
.ok_or_else(|| std::io::Error::other("Invalid symbol"))?;
let offset = match value.location {
// Text section is on the beginning
Section::Text => value.offset,
// Data section follows text section immediately
Section::Data => value.offset + obj.sections.text.len(),
};
// Insert address or calulate relative offset
match entry.ty {
RelocType::Rel32 => obj.sections.text[loc..loc + 4]
.copy_from_slice(&((offset as isize - loc as isize) as i32).to_le_bytes()),
RelocType::Rel16 => obj.sections.text[loc..loc + 2]
.copy_from_slice(&((offset as isize - loc as isize) as i16).to_le_bytes()),
RelocType::Abs64 => obj.sections.text[loc..loc + 8]
.copy_from_slice(&(offset as isize - loc as isize).to_le_bytes()),
}
}
// Write to output
out.write_all(&obj.sections.text)?;
out.write_all(&obj.sections.data)
}

72
hbasm/src/macros.rs Normal file
View File

@ -0,0 +1,72 @@
macro_rules! impl_asm_opcodes {
(
$generic:ident
($($param_i:ident: $param_ty:ty),*)
=> []
) => {};
(
$generic:ident
($($param_i:ident: $param_ty:ty),*)
=> [$opcode:ident, $($rest:tt)*]
) => {
paste::paste! {
#[allow(dead_code)]
#[inline(always)]
pub fn [<i_ $opcode:lower>](&mut self, $($param_i: $param_ty),*) {
self.$generic(hbbytecode::opcode::$opcode, $($param_i),*)
}
}
macros::impl_asm_opcodes!(
$generic($($param_i: $param_ty),*)
=> [$($rest)*]
);
};
}
macro_rules! gen_impl_asm_insert {
($($ty:ident),* $(,)?) => {
macro_rules! impl_asm_insert {
$(($self:expr, $id:ident, $ty) => {
$self.buf.extend($id.to_le_bytes())
};)*
($self:expr, $id:ident, $_:ty) => {
Imm::insert(&$id, $self)
};
}
};
}
gen_impl_asm_insert!(u8, u16, u64);
macro_rules! impl_asm {
(
$(
$ityn:ident
($($param_i:ident: $param_ty:ty),* $(,)?)
=> [$($opcode:ident),* $(,)?],
)*
) => {
paste::paste! {
$(
#[allow(dead_code)]
fn [<i_param_ $ityn>](&mut self, opcode: u8, $($param_i: $param_ty),*) {
self.buf.push(opcode);
$(macros::impl_asm_insert!(self, $param_i, $param_ty);)*
}
macros::impl_asm_opcodes!(
[<i_param_ $ityn>]($($param_i: $param_ty),*)
=> [$($opcode,)*]
);
)*
}
};
}
pub(super) use {impl_asm, impl_asm_opcodes};
#[allow(clippy::single_component_path_imports)]
pub(super) use impl_asm_insert;

View File

@ -1,8 +1,46 @@
use std::{io::stdout, path::PathBuf};
use {
ariadne::{ColorGenerator, Label, Report, ReportKind, Source},
std::{
error::Error,
io::{stdin, Read},
},
};
fn main() -> Result<(), Box<dyn Error>> {
let mut code = String::new();
stdin().read_to_string(&mut code)?;
let mut buf = vec![];
if let Err(e) = hbasm::text::assembly(&code, &mut buf) {
let mut colors = ColorGenerator::new();
let e_code = match e.kind {
hbasm::text::ErrorKind::UnexpectedToken => 1,
hbasm::text::ErrorKind::InvalidToken => 2,
hbasm::text::ErrorKind::UnexpectedEnd => 3,
hbasm::text::ErrorKind::InvalidSymbol => 4,
};
let message = match e.kind {
hbasm::text::ErrorKind::UnexpectedToken => "This token is not expected!",
hbasm::text::ErrorKind::InvalidToken => "The token is not valid!",
hbasm::text::ErrorKind::UnexpectedEnd => "The assembler reached the end of input unexpectedly!",
hbasm::text::ErrorKind::InvalidSymbol => "This referenced symbol doesn't have a corresponding label!",
};
let a = colors.next();
Report::build(ReportKind::Error, "engine_internal", e.span.clone().start)
.with_code(e_code)
.with_message(format!("{:?}", e.kind))
.with_label(
Label::new(("engine_internal", e.span.clone()))
.with_message(message)
.with_color(a),
)
.finish()
.eprint(("engine_internal", Source::from(&code)))
.unwrap();
}
fn main() -> Result<(), Box<dyn std::error::Error>> {
let path = PathBuf::from(std::env::args().nth(1).ok_or("Missing path")?);
hbasm::assembler(&mut stdout(), |engine| engine.run_file(path))?;
Ok(())
}

View File

@ -1,94 +0,0 @@
//! Code object
use {rhai::ImmutableString, std::collections::HashMap};
/// Section tabel
#[derive(Clone, Copy, Debug, PartialEq, Eq)]
pub enum Section {
Text,
Data,
}
/// Symbol entry (in what section, where)
#[derive(Clone, Copy, Debug)]
pub struct SymbolEntry {
pub location: Section,
pub offset: usize,
}
/// Relocation table key
#[derive(Clone, Debug)]
pub enum RelocKey {
/// Direct reference
Symbol(usize),
/// Indirect reference
Label(ImmutableString),
}
/// Relocation type
#[derive(Clone, Copy, Debug)]
pub enum RelocType {
Rel32,
Rel16,
Abs64,
}
/// Relocation table entry
#[derive(Clone, Debug)]
pub struct RelocEntry {
pub key: RelocKey,
pub ty: RelocType,
}
/// Object code
#[derive(Clone, Debug, Default)]
pub struct Sections {
pub text: Vec<u8>,
pub data: Vec<u8>,
}
/// Object
#[derive(Clone, Debug, Default)]
pub struct Object {
/// Vectors with sections
pub sections: Sections,
/// Symbol table
pub symbols: Vec<Option<SymbolEntry>>,
/// Labels to symbols table
pub labels: HashMap<ImmutableString, usize>,
/// Relocation table
pub relocs: HashMap<usize, RelocEntry>,
}
#[derive(Clone, Copy, Debug)]
#[repr(transparent)]
pub struct SymbolRef(pub usize);
impl Object {
/// Insert symbol at current location in specified section
pub fn symbol(&mut self, section: Section) -> SymbolRef {
let section_buf = match section {
Section::Text => &mut self.sections.text,
Section::Data => &mut self.sections.data,
};
self.symbols.push(Some(SymbolEntry {
location: section,
offset: section_buf.len(),
}));
SymbolRef(self.symbols.len() - 1)
}
/// Insert to relocation table and write zeroes to code
pub fn relocation(&mut self, key: RelocKey, ty: RelocType) {
self.relocs
.insert(self.sections.text.len(), RelocEntry { key, ty });
self.sections.text.extend(match ty {
RelocType::Rel32 => &[0_u8; 4] as &[u8],
RelocType::Rel16 => &[0; 2],
RelocType::Abs64 => &[0; 8],
});
}
}

273
hbasm/src/text.rs Normal file
View File

@ -0,0 +1,273 @@
extern crate alloc;
use alloc::vec::Vec;
use {
core::fmt::{Display, Formatter},
hashbrown::HashMap,
lasso::{Rodeo, Spur},
logos::{Lexer, Logos, Span},
};
macro_rules! tokendef {
($($opcode:literal),* $(,)?) => {
paste::paste! {
#[derive(Clone, Copy, Debug, PartialEq, Eq, Logos)]
#[logos(extras = Rodeo)]
#[logos(skip r"[ \t\f]+")]
#[logos(skip r"-- .*")]
pub enum Token {
$(#[token($opcode, |_| hbbytecode::opcode::[<$opcode:upper>])])*
OpCode(u8),
#[regex("[0-9]+", |l| l.slice().parse().ok())]
#[regex(
"-[0-9]+",
|lexer| {
Some(u64::from_ne_bytes(lexer.slice().parse::<i64>().ok()?.to_ne_bytes()))
},
)] Integer(u64),
#[regex(
"r[0-9]+",
|lexer| match lexer.slice()[1..].parse() {
Ok(n) => Some(n),
_ => None
},
)] Register(u8),
#[regex(
r"\p{XID_Start}\p{XID_Continue}*:",
|lexer| lexer.extras.get_or_intern(&lexer.slice()[..lexer.slice().len() - 1]),
)] Label(Spur),
#[regex(
r"\p{XID_Start}\p{XID_Continue}*",
|lexer| lexer.extras.get_or_intern(lexer.slice()),
)] Symbol(Spur),
#[token("\n")]
#[token(";")] ISep,
#[token(",")] PSep,
}
}
};
}
#[rustfmt::skip]
tokendef![
"nop", "add", "sub", "mul", "and", "or", "xor", "sl", "sr", "srs", "cmp", "cmpu",
"dir", "neg", "not", "addi", "muli", "andi", "ori", "xori", "sli", "sri", "srsi",
"cmpi", "cmpui", "cp", "swa", "li", "ld", "st", "bmc", "brc", "jmp", "jeq", "jne",
"jlt", "jgt", "jltu", "jgtu", "ecall", "addf", "subf", "mulf", "dirf", "fmaf", "negf",
"itf", "fti", "addfi", "mulfi",
];
#[derive(Copy, Clone, Debug, PartialEq, Eq)]
pub enum ErrorKind {
UnexpectedToken,
InvalidToken,
UnexpectedEnd,
InvalidSymbol,
}
#[derive(Clone, Debug, PartialEq, Eq)]
pub struct Error {
pub kind: ErrorKind,
pub span: Span,
}
impl Display for Error {
fn fmt(&self, f: &mut Formatter<'_>) -> core::fmt::Result {
write!(f, "Error {:?} at {:?}", self.kind, self.span)
}
}
impl core::error::Error for Error {}
macro_rules! expect_matches {
($self:expr, $($pat:pat),* $(,)?) => {$(
let $pat = $self.next()?
else { return Err(ErrorKind::UnexpectedToken) };
)*}
}
pub fn assembly(code: &str, buf: &mut Vec<u8>) -> Result<(), Error> {
struct Assembler<'a> {
lexer: Lexer<'a, Token>,
buf: &'a mut Vec<u8>,
label_map: HashMap<Spur, u64>,
to_sub_label: HashMap<usize, Spur>,
}
impl<'a> Assembler<'a> {
fn next(&mut self) -> Result<Token, ErrorKind> {
match self.lexer.next() {
Some(Ok(t)) => Ok(t),
Some(Err(())) => Err(ErrorKind::InvalidToken),
None => Err(ErrorKind::UnexpectedEnd),
}
}
fn assemble(&mut self) -> Result<(), ErrorKind> {
use hbbytecode::opcode::*;
loop {
match self.lexer.next() {
Some(Ok(Token::OpCode(op))) => {
self.buf.push(op);
match op {
NOP | ECALL => Ok(()),
DIR | DIRF => {
expect_matches!(
self,
Token::Register(r0),
Token::PSep,
Token::Register(r1),
Token::PSep,
Token::Register(r2),
Token::PSep,
Token::Register(r3),
);
self.buf.extend([r0, r1, r2, r3]);
Ok(())
}
ADD..=CMPU | ADDF..=MULF => {
expect_matches!(
self,
Token::Register(r0),
Token::PSep,
Token::Register(r1),
Token::PSep,
Token::Register(r2),
);
self.buf.extend([r0, r1, r2]);
Ok(())
}
BRC => {
expect_matches!(
self,
Token::Register(r0),
Token::PSep,
Token::Register(r1),
Token::PSep,
Token::Integer(count),
);
self.buf.extend([
r0,
r1,
u8::try_from(count).map_err(|_| ErrorKind::UnexpectedToken)?,
]);
Ok(())
}
NEG..=NOT | CP..=SWA | NEGF..=FTI => {
expect_matches!(
self,
Token::Register(r0),
Token::PSep,
Token::Register(r1),
);
self.buf.extend([r0, r1]);
Ok(())
}
LI | JMP => {
expect_matches!(self, Token::Register(r0), Token::PSep);
self.buf.push(r0);
self.insert_imm()?;
Ok(())
}
ADDI..=CMPUI | BMC | JEQ..=JGTU | ADDFI..=MULFI => {
expect_matches!(
self,
Token::Register(r0),
Token::PSep,
Token::Register(r1),
Token::PSep,
);
self.buf.extend([r0, r1]);
self.insert_imm()?;
Ok(())
}
LD..=ST => {
expect_matches!(
self,
Token::Register(r0),
Token::PSep,
Token::Register(r1),
Token::PSep,
Token::Integer(offset),
Token::PSep,
Token::Integer(len),
);
self.buf.extend([r0, r1]);
self.buf.extend(offset.to_le_bytes());
self.buf.extend(
u16::try_from(len)
.map_err(|_| ErrorKind::InvalidToken)?
.to_le_bytes(),
);
Ok(())
}
_ => unreachable!(),
}?;
match self.next() {
Ok(Token::ISep) => (),
Ok(_) => return Err(ErrorKind::UnexpectedToken),
Err(ErrorKind::UnexpectedEnd) => return Ok(()),
Err(e) => return Err(e),
}
}
Some(Ok(Token::Label(lbl))) => {
self.label_map.insert(lbl, self.buf.len() as u64);
}
Some(Ok(Token::ISep)) => (),
Some(Ok(_)) => return Err(ErrorKind::UnexpectedToken),
Some(Err(())) => return Err(ErrorKind::InvalidToken),
None => return Ok(()),
}
}
}
fn link_local_syms(&mut self) -> Result<(), ErrorKind> {
for (ix, sym) in &self.to_sub_label {
self.label_map
.get(sym)
.ok_or(ErrorKind::InvalidSymbol)?
.to_le_bytes()
.iter()
.enumerate()
.for_each(|(i, b)| {
self.buf[ix + i] = *b;
});
}
Ok(())
}
fn insert_imm(&mut self) -> Result<(), ErrorKind> {
let imm = match self.next()? {
Token::Integer(i) => i.to_le_bytes(),
Token::Symbol(s) => {
self.to_sub_label.insert(self.buf.len(), s);
[0; 8]
}
_ => return Err(ErrorKind::UnexpectedToken),
};
self.buf.extend(imm);
Ok(())
}
}
let mut asm = Assembler {
lexer: Token::lexer(code),
label_map: Default::default(),
to_sub_label: Default::default(),
buf,
};
asm.assemble().map_err(|kind| Error {
kind,
span: asm.lexer.span(),
})?;
asm.link_local_syms()
.map_err(|kind| Error { kind, span: 0..0 })
}

View File

@ -1,8 +1,6 @@
[package]
name = "hbbytecode"
version = "0.1.0"
edition = "2018"
edition = "2021"
[dependencies]
paste = "1.0.14"
with_builtin_macros = "0.0.3"

View File

@ -1,8 +1,5 @@
/* HoleyBytes Bytecode representation in C
* Requires C23 compiler or better
*
* Uses MSVC pack pragma extension,
* proved to work with Clang and GNU® GCC.
*/
#pragma once
@ -13,16 +10,15 @@
static_assert(CHAR_BIT == 8, "Cursed architectures are not supported");
enum hbbc_Opcode: uint8_t {
hbbc_Op_UN , hbbc_Op_TX , hbbc_Op_NOP , hbbc_Op_ADD , hbbc_Op_SUB , hbbc_Op_MUL ,
hbbc_Op_AND , hbbc_Op_OR , hbbc_Op_XOR , hbbc_Op_SL , hbbc_Op_SR , hbbc_Op_SRS ,
hbbc_Op_CMP , hbbc_Op_CMPU , hbbc_Op_DIR , hbbc_Op_NEG , hbbc_Op_NOT , hbbc_Op_ADDI ,
hbbc_Op_MULI , hbbc_Op_ANDI , hbbc_Op_ORI , hbbc_Op_XORI , hbbc_Op_SLI , hbbc_Op_SRI ,
hbbc_Op_SRSI , hbbc_Op_CMPI , hbbc_Op_CMPUI , hbbc_Op_CP , hbbc_Op_SWA , hbbc_Op_LI ,
hhbc_Op_LRA , hbbc_Op_LD , hbbc_Op_ST , hbbc_Op_LDR , hhbc_Op_STR , hbbc_Op_BMC ,
hbbc_Op_BRC , hbbc_Op_JMP , hbbc_Op_JMPR , hbbc_Op_JAL , hbbc_Op_JALR , hbbc_Op_JEQ ,
hbbc_Op_JNE , hbbc_Op_JLT , hbbc_Op_JGT , hbbc_Op_JLTU , hbbc_Op_JGTU , hbbc_Op_ECALL ,
hbbc_Op_ADDF , hbbc_Op_SUBF , hbbc_Op_MULF , hbbc_Op_DIRF , hbbc_Op_FMAF , hbbc_Op_NEGF ,
hbbc_Op_ITF , hbbc_Op_FTI , hbbc_Op_ADDFI , hbbc_Op_MULFI ,
hbbc_Op_NOP , hbbc_Op_ADD , hbbc_Op_SUB , hbbc_Op_MUL , hbbc_Op_AND , hbbc_Op_OR ,
hbbc_Op_XOR , hbbc_Op_SL , hbbc_Op_SR , hbbc_Op_SRS , hbbc_Op_CMP , hbbc_Op_CMPU ,
hbbc_Op_DIR , hbbc_Op_NEG , hbbc_Op_NOT , hbbc_Op_ADDI , hbbc_Op_MULI , hbbc_Op_ANDI ,
hbbc_Op_ORI , hbbc_Op_XORI , hbbc_Op_SLI , hbbc_Op_SRI , hbbc_Op_SRSI , hbbc_Op_CMPI ,
hbbc_Op_CMPUI , hbbc_Op_CP , hbbc_Op_SWA , hbbc_Op_LI , hbbc_Op_LD , hbbc_Op_ST ,
hbbc_Op_BMC , hbbc_Op_BRC , hbbc_Op_JMP , hbbc_Op_JEQ , hbbc_Op_JNE , hbbc_Op_JLT ,
hbbc_Op_JGT , hbbc_Op_JLTU , hbbc_Op_JGTU , hbbc_Op_ECALL , hbbc_Op_ADDF , hbbc_Op_SUBF ,
hbbc_Op_MULF , hbbc_Op_DIRF , hbbc_Op_FMAF , hbbc_Op_NEGF , hbbc_Op_ITF , hbbc_Op_FTI ,
hbbc_Op_ADDFI , hbbc_Op_MULFI ,
} typedef hbbc_Opcode;
static_assert(sizeof(hbbc_Opcode) == 1);
@ -43,22 +39,11 @@ struct hbbc_ParamBBDH
typedef hbbc_ParamBBDH;
static_assert(sizeof(hbbc_ParamBBDH) == 96 / 8);
struct hbbc_ParamBBWH
{ uint8_t _0; uint8_t _1; uint32_t _2; uint16_t _3; }
typedef hbbc_ParamBBWH;
static_assert(sizeof(hbbc_ParamBBWH) == 64 / 8);
struct hbbc_ParamBBD
{ uint8_t _0; uint8_t _1; uint64_t _2; }
typedef hbbc_ParamBBD;
static_assert(sizeof(hbbc_ParamBBD) == 80 / 8);
struct hbbc_ParamBBW
{ uint8_t _0; uint8_t _1; uint32_t _2; }
typedef hbbc_ParamBBW;
static_assert(sizeof(hbbc_ParamBBW) == 48 / 8);
struct hbbc_ParamBB
{ uint8_t _0; uint8_t _1; }
typedef hbbc_ParamBB;

View File

@ -1,120 +0,0 @@
0x00, UN, N, "Cause an unreachable code trap" ;
0x01, TX, N, "Termiante execution" ;
0x02, NOP, N, "Do nothing" ;
0x03, ADD8, RRR, "Addition (8b)" ;
0x04, ADD16, RRR, "Addition (16b)" ;
0x05, ADD32, RRR, "Addition (32b)" ;
0x06, ADD64, RRR, "Addition (64b)" ;
0x07, SUB8, RRR, "Subtraction (8b)" ;
0x08, SUB16, RRR, "Subtraction (16b)" ;
0x09, SUB32, RRR, "Subtraction (32b)" ;
0x0A, SUB64, RRR, "Subtraction (64b)" ;
0x0B, MUL8, RRR, "Multiplication (8b)" ;
0x0C, MUL16, RRR, "Multiplication (16b)" ;
0x0D, MUL32, RRR, "Multiplication (32b)" ;
0x0E, MUL64, RRR, "Multiplication (64b)" ;
0x0F, AND, RRR, "Bitand" ;
0x10, OR, RRR, "Bitor" ;
0x11, XOR, RRR, "Bitxor" ;
0x12, SLU8, RRR, "Unsigned left bitshift (8b)" ;
0x13, SLU16, RRR, "Unsigned left bitshift (16b)" ;
0x14, SLU32, RRR, "Unsigned left bitshift (32b)" ;
0x15, SLU64, RRR, "Unsigned left bitshift (64b)" ;
0x16, SRU8, RRR, "Unsigned right bitshift (8b)" ;
0x17, SRU16, RRR, "Unsigned right bitshift (16b)" ;
0x18, SRU32, RRR, "Unsigned right bitshift (32b)" ;
0x19, SRU64, RRR, "Unsigned right bitshift (64b)" ;
0x1A, SRS8, RRR, "Signed right bitshift (8b)" ;
0x1B, SRS16, RRR, "Signed right bitshift (16b)" ;
0x1C, SRS32, RRR, "Signed right bitshift (32b)" ;
0x1D, SRS64, RRR, "Signed right bitshift (64b)" ;
0x1E, CMPU, RRR, "Unsigned comparsion" ;
0x1F, CMPS, RRR, "Signed comparsion" ;
0x20, DIRU8, RRRR, "Merged divide-remainder (unsigned 8b)" ;
0x21, DIRU16, RRRR, "Merged divide-remainder (unsigned 16b)" ;
0x22, DIRU32, RRRR, "Merged divide-remainder (unsigned 32b)" ;
0x23, DIRU64, RRRR, "Merged divide-remainder (unsigned 64b)" ;
0x24, DIRS8, RRRR, "Merged divide-remainder (signed 8b)" ;
0x25, DIRS16, RRRR, "Merged divide-remainder (signed 16b)" ;
0x26, DIRS32, RRRR, "Merged divide-remainder (signed 32b)" ;
0x27, DIRS64, RRRR, "Merged divide-remainder (signed 64b)" ;
0x28, NEG, RR, "Bit negation" ;
0x29, NOT, RR, "Logical negation" ;
0x2A, SXT8, RR, "Sign extend 8b to 64b" ;
0x2B, SXT16, RR, "Sign extend 16b to 64b" ;
0x2C, SXT32, RR, "Sign extend 32b to 64b" ;
0x2D, ADDI8, RRB, "Addition with immediate (8b)" ;
0x2E, ADDI16, RRH, "Addition with immediate (16b)" ;
0x2F, ADDI32, RRW, "Addition with immediate (32b)" ;
0x30, ADDI64, RRD, "Addition with immediate (64b)" ;
0x31, MULI8, RRB, "Multiplication with immediate (8b)" ;
0x32, MULI16, RRH, "Multiplication with immediate (16b)" ;
0x33, MULI32, RRW, "Multiplication with immediate (32b)" ;
0x34, MULI64, RRD, "Multiplication with immediate (64b)" ;
0x35, ANDI, RRD, "Bitand with immediate" ;
0x36, ORI, RRD, "Bitor with immediate" ;
0x37, XORI, RRD, "Bitxor with immediate" ;
0x38, SLUI8, RRB, "Unsigned left bitshift with immedidate (8b)" ;
0x39, SLUI16, RRB, "Unsigned left bitshift with immedidate (16b)";
0x3A, SLUI32, RRB, "Unsigned left bitshift with immedidate (32b)";
0x3B, SLUI64, RRB, "Unsigned left bitshift with immedidate (64b)";
0x3C, SRUI8, RRB, "Unsigned right bitshift with immediate (8b)" ;
0x3D, SRUI16, RRB, "Unsigned right bitshift with immediate (16b)";
0x3E, SRUI32, RRB, "Unsigned right bitshift with immediate (32b)";
0x3F, SRUI64, RRB, "Unsigned right bitshift with immediate (64b)";
0x40, SRSI8, RRB, "Signed right bitshift with immediate" ;
0x41, SRSI16, RRB, "Signed right bitshift with immediate" ;
0x42, SRSI32, RRB, "Signed right bitshift with immediate" ;
0x43, SRSI64, RRB, "Signed right bitshift with immediate" ;
0x44, CMPUI, RRD, "Unsigned compare with immediate" ;
0x45, CMPSI, RRD, "Signed compare with immediate" ;
0x46, CP, RR, "Copy register" ;
0x47, SWA, RR, "Swap registers" ;
0x48, LI8, RB, "Load immediate (8b)" ;
0x49, LI16, RH, "Load immediate (16b)" ;
0x4A, LI32, RW, "Load immediate (32b)" ;
0x4B, LI64, RD, "Load immediate (64b)" ;
0x4C, LRA, RRO, "Load relative address" ;
0x4D, LD, RRAH, "Load from absolute address" ;
0x4E, ST, RRAH, "Store to absolute address" ;
0x4F, LDR, RROH, "Load from relative address" ;
0x50, STR, RROH, "Store to relative address" ;
0x51, BMC, RRH, "Copy block of memory" ;
0x52, BRC, RRB, "Copy register block" ;
0x53, JMP, O, "Relative jump" ;
0x54, JAL, RRO, "Linking relative jump" ;
0x55, JALA, RRA, "Linking absolute jump" ;
0x56, JEQ, RRP, "Branch on equal" ;
0x57, JNE, RRP, "Branch on nonequal" ;
0x58, JLTU, RRP, "Branch on lesser-than (unsigned)" ;
0x59, JGTU, RRP, "Branch on greater-than (unsigned)" ;
0x5A, JLTS, RRP, "Branch on lesser-than (signed)" ;
0x5B, JGTS, RRP, "Branch on greater-than (signed)" ;
0x5C, ECA, N, "Environment call trap" ;
0x5D, EBP, N, "Environment breakpoint" ;
0x5E, FADD32, RRR, "Floating point addition (32b)" ;
0x5F, FADD64, RRR, "Floating point addition (64b)" ;
0x60, FSUB32, RRR, "Floating point subtraction (32b)" ;
0x61, FSUB64, RRR, "Floating point subtraction (64b)" ;
0x62, FMUL32, RRR, "Floating point multiply (32b)" ;
0x63, FMUL64, RRR, "Floating point multiply (64b)" ;
0x64, FDIV32, RRR, "Floating point division (32b)" ;
0x65, FDIV64, RRR, "Floating point division (64b)" ;
0x66, FMA32, RRRR, "Float fused multiply-add (32b)" ;
0x67, FMA64, RRRR, "Float fused multiply-add (64b)" ;
0x68, FINV32, RR, "Float reciprocal (32b)" ;
0x69, FINV64, RR, "Float reciprocal (64b)" ;
0x6A, FCMPLT32, RRR, "Flaot compare less than (32b)" ;
0x6B, FCMPLT64, RRR, "Flaot compare less than (64b)" ;
0x6C, FCMPGT32, RRR, "Flaot compare greater than (32b)" ;
0x6D, FCMPGT64, RRR, "Flaot compare greater than (64b)" ;
0x6E, ITF32, RR, "Int to 32 bit float" ;
0x6F, ITF64, RR, "Int to 64 bit float" ;
0x70, FTI32, RRB, "Float 32 to int" ;
0x71, FTI64, RRB, "Float 64 to int" ;
0x72, FC32T64, RR, "Float 64 to Float 32" ;
0x73, FC64T32, RRB, "Float 32 to Float 64" ;
0x74, LRA16, RRP, "Load relative immediate (16 bit)" ;
0x75, LDR16, RRPH, "Load from relative address (16 bit)" ;
0x76, STR16, RRPH, "Store to relative address (16 bit)" ;
0x77, JMP16, P, "Relative jump (16 bit)" ;

View File

@ -1,185 +1,107 @@
#![no_std]
use core::convert::TryFrom;
macro_rules! constmod {
($vis:vis $mname:ident($repr:ty) {
$(#![doc = $mdoc:literal])?
$($cname:ident = $val:expr $(,$doc:literal)?;)*
}) => {
$(#[doc = $mdoc])?
$vis mod $mname {
$(
$(#[doc = $doc])?
pub const $cname: $repr = $val;
)*
}
};
}
type OpR = u8;
constmod!(pub opcode(u8) {
//! Opcode constant module
type OpA = u64;
type OpO = i32;
type OpP = i16;
NOP = 0, "N; Do nothing";
type OpB = u8;
type OpH = u16;
type OpW = u32;
type OpD = u64;
ADD = 1, "BBB; #0 ← #1 + #2";
SUB = 2, "BBB; #0 ← #1 - #2";
MUL = 3, "BBB; #0 ← #1 × #2";
AND = 4, "BBB; #0 ← #1 & #2";
OR = 5, "BBB; #0 ← #1 | #2";
XOR = 6, "BBB; #0 ← #1 ^ #2";
SL = 7, "BBB; #0 ← #1 « #2";
SR = 8, "BBB; #0 ← #1 » #2";
SRS = 9, "BBB; #0 ← #1 » #2 (signed)";
CMP = 10, "BBB; #0 ← #1 <=> #2";
CMPU = 11, "BBB; #0 ← #1 <=> #2 (unsigned)";
DIR = 12, "BBBB; #0 ← #2 / #3, #1 ← #2 % #3";
NEG = 13, "BB; #0 ← -#1";
NOT = 14, "BB; #0 ← !#1";
ADDI = 15, "BBD; #0 ← #1 + imm #2";
MULI = 16, "BBD; #0 ← #1 × imm #2";
ANDI = 17, "BBD; #0 ← #1 & imm #2";
ORI = 18, "BBD; #0 ← #1 | imm #2";
XORI = 19, "BBD; #0 ← #1 ^ imm #2";
SLI = 20, "BBD; #0 ← #1 « imm #2";
SRI = 21, "BBD; #0 ← #1 » imm #2";
SRSI = 22, "BBD; #0 ← #1 » imm #2 (signed)";
CMPI = 23, "BBD; #0 ← #1 <=> imm #2";
CMPUI = 24, "BBD; #0 ← #1 <=> imm #2 (unsigned)";
CP = 25, "BB; Copy #0 ← #1";
SWA = 26, "BB; Swap #0 and #1";
LI = 27, "BD; #0 ← imm #1";
LD = 28, "BBDB; #0 ← [#1 + imm #3], imm #4 bytes, overflowing";
ST = 29, "BBDB; [#1 + imm #3] ← #0, imm #4 bytes, overflowing";
BMC = 30, "BBD; [#0] ← [#1], imm #2 bytes";
BRC = 31, "BBB; #0 ← #1, imm #2 registers";
JMP = 32, "BD; Unconditional jump [#0 + imm #1]";
JEQ = 33, "BBD; if #0 = #1 → jump imm #2";
JNE = 34, "BBD; if #0 ≠ #1 → jump imm #2";
JLT = 35, "BBD; if #0 < #1 → jump imm #2";
JGT = 36, "BBD; if #0 > #1 → jump imm #2";
JLTU = 37, "BBD; if #0 < #1 → jump imm #2 (unsigned)";
JGTU = 38, "BBD; if #0 > #1 → jump imm #2 (unsigned)";
ECALL = 39, "N; Issue system call";
ADDF = 40, "BBB; #0 ← #1 +. #2";
SUBF = 41, "BBB; #0 ← #1 -. #2";
MULF = 42, "BBB; #0 ← #1 +. #2";
DIRF = 43, "BBBB; #0 ← #2 / #3, #1 ← #2 % #3";
FMAF = 44, "BBBB; #0 ← (#1 * #2) + #3";
NEGF = 45, "BB; #0 ← -#1";
ITF = 46, "BB; #0 ← #1 as float";
FTI = 47, "BB; #0 ← #1 as int";
ADDFI = 48, "BBD; #0 ← #1 +. imm #2";
MULFI = 49, "BBD; #0 ← #1 *. imm #2";
});
#[repr(packed)]
pub struct ParamBBBB(pub u8, pub u8, pub u8, pub u8);
#[repr(packed)]
pub struct ParamBBB(pub u8, pub u8, pub u8);
#[repr(packed)]
pub struct ParamBBDH(pub u8, pub u8, pub u64, pub u16);
#[repr(packed)]
pub struct ParamBBD(pub u8, pub u8, pub u64);
#[repr(packed)]
pub struct ParamBB(pub u8, pub u8);
#[repr(packed)]
pub struct ParamBD(pub u8, pub u64);
/// # Safety
/// Has to be valid to be decoded from bytecode.
pub unsafe trait BytecodeItem {}
macro_rules! define_items {
($($name:ident ($($nm:ident: $item:ident),* $(,)?)),* $(,)?) => {
$(
#[derive(Clone, Copy, Debug)]
#[repr(packed)]
pub struct $name($(pub $item),*);
unsafe impl BytecodeItem for $name {}
impl Encodable for $name {
fn encode(self, _buffer: &mut impl Buffer) {
let Self($($nm),*) = self;
$(
for byte in $nm.to_le_bytes() {
unsafe { _buffer.write(byte) };
}
)*
}
fn encode_len(self) -> usize {
core::mem::size_of::<Self>()
}
}
)*
};
}
define_items! {
OpsRR (a: OpR, b: OpR ),
OpsRRR (a: OpR, b: OpR, c: OpR ),
OpsRRRR (a: OpR, b: OpR, c: OpR, d: OpR),
OpsRRB (a: OpR, b: OpR, c: OpB ),
OpsRRH (a: OpR, b: OpR, c: OpH ),
OpsRRW (a: OpR, b: OpR, c: OpW ),
OpsRRD (a: OpR, b: OpR, c: OpD ),
OpsRB (a: OpR, b: OpB ),
OpsRH (a: OpR, b: OpH ),
OpsRW (a: OpR, b: OpW ),
OpsRD (a: OpR, b: OpD ),
OpsRRA (a: OpR, b: OpR, c: OpA ),
OpsRRAH (a: OpR, b: OpR, c: OpA, d: OpH),
OpsRROH (a: OpR, b: OpR, c: OpO, d: OpH),
OpsRRPH (a: OpR, b: OpR, c: OpP, d: OpH),
OpsRRO (a: OpR, b: OpR, c: OpO ),
OpsRRP (a: OpR, b: OpR, c: OpP ),
OpsO (a: OpO, ),
OpsP (a: OpP, ),
OpsN ( ),
}
unsafe impl BytecodeItem for u8 {}
::with_builtin_macros::with_builtin! {
let $spec = include_from_root!("instructions.in") in {
/// Invoke macro with bytecode definition
///
/// # Format
/// ```text
/// Opcode, Mnemonic, Type, Docstring;
/// ```
///
/// # Type
/// ```text
/// Types consist of letters meaning a single field
/// | Type | Size (B) | Meaning |
/// |:-----|:---------|:------------------------|
/// | N | 0 | Empty |
/// | R | 1 | Register |
/// | A | 8 | Absolute address |
/// | O | 4 | Relative address offset |
/// | P | 2 | Relative address offset |
/// | B | 1 | Immediate |
/// | H | 2 | Immediate |
/// | W | 4 | Immediate |
/// | D | 8 | Immediate |
/// ```
#[macro_export]
macro_rules! invoke_with_def {
($($macro:tt)*) => {
$($macro)*! { $spec }
};
}
}
}
pub trait Buffer {
fn reserve(&mut self, bytes: usize);
/// # Safety
/// Reserve needs to be called before this function, and only reserved amount can be written.
unsafe fn write(&mut self, byte: u8);
}
pub trait Encodable {
fn encode(self, buffer: &mut impl Buffer);
fn encode_len(self) -> usize;
}
macro_rules! gen_opcodes {
($($opcode:expr, $mnemonic:ident, $ty:ident, $doc:literal;)*) => {
pub mod opcode {
$(
#[doc = $doc]
pub const $mnemonic: u8 = $opcode;
)*
paste::paste! {
#[derive(Clone, Copy, Debug)]
#[repr(u8)]
pub enum Op { $(
[< $mnemonic:lower:camel >](super::[<Ops $ty>]),
)* }
impl Op {
pub fn size(&self) -> usize {
(match self {
$(Self::[<$mnemonic:lower:camel>] { .. } => core::mem::size_of::<super::[<Ops $ty>]>(),)*
}) + 1
}
}
impl crate::Encodable for Op {
fn encode(self, buffer: &mut impl crate::Buffer) {
match self {
$(
Self::[< $mnemonic:lower:camel >](op) => {
unsafe { buffer.write($opcode) };
op.encode(buffer);
}
)*
}
}
fn encode_len(self) -> usize {
match self {
$(
Self::[< $mnemonic:lower:camel >](op) => {
1 + crate::Encodable::encode_len(op)
}
)*
}
}
}
}
}
};
}
/// Rounding mode
#[derive(Clone, Copy, Debug, PartialEq, Eq)]
#[repr(u8)]
pub enum RoundingMode {
NearestEven = 0,
Truncate = 1,
Up = 2,
Down = 3,
}
impl TryFrom<u8> for RoundingMode {
type Error = ();
fn try_from(value: u8) -> Result<Self, Self::Error> {
(value <= 3)
.then(|| unsafe { core::mem::transmute(value) })
.ok_or(())
}
}
invoke_with_def!(gen_opcodes);
pub unsafe trait OpParam {}
unsafe impl OpParam for ParamBBBB {}
unsafe impl OpParam for ParamBBB {}
unsafe impl OpParam for ParamBBDH {}
unsafe impl OpParam for ParamBBD {}
unsafe impl OpParam for ParamBB {}
unsafe impl OpParam for ParamBD {}
unsafe impl OpParam for u64 {}
unsafe impl OpParam for () {}

View File

@ -1,13 +0,0 @@
[package]
name = "hblang"
version = "0.1.0"
edition = "2021"
[[bin]]
name = "hbc"
path = "src/main.rs"
[dependencies]
[dev-dependencies]
hbvm = { path = "../hbvm", features = ["nightly"] }

View File

@ -1,136 +0,0 @@
#![feature(iter_next_chunk)]
use std::fmt::Write;
fn main() -> Result<(), Box<dyn std::error::Error>> {
println!("cargo:rerun-if-changed=build.rs");
println!("cargo:rerun-if-changed=../hbbytecode/instructions.in");
let mut generated = String::new();
gen_max_size(&mut generated)?;
gen_encodes(&mut generated)?;
gen_structs(&mut generated)?;
gen_name_list(&mut generated)?;
std::fs::write("src/instrs.rs", generated)?;
Ok(())
}
fn gen_name_list(generated: &mut String) -> Result<(), Box<dyn std::error::Error>> {
writeln!(
generated,
"pub const NAMES: [&str; {}] = [",
instructions().count()
)?;
for [_, name, _, _] in instructions() {
writeln!(generated, " \"{}\",", name.to_lowercase())?;
}
writeln!(generated, "];")?;
Ok(())
}
fn gen_max_size(generated: &mut String) -> Result<(), Box<dyn std::error::Error>> {
let max = instructions()
.map(|[_, _, ty, _]| {
if ty == "N" {
1
} else {
iter_args(ty).map(|(_, c)| arg_to_width(c)).sum::<usize>() + 1
}
})
.max()
.unwrap();
writeln!(generated, "pub const MAX_SIZE: usize = {};", max)?;
Ok(())
}
fn gen_encodes(generated: &mut String) -> Result<(), Box<dyn std::error::Error>> {
for [op, name, ty, doc] in instructions() {
writeln!(generated, "/// {}", doc.trim_matches('"'))?;
let name = name.to_lowercase();
let args = comma_sep(
iter_args(ty).map(|(i, c)| format!("{}{i}: {}", arg_to_name(c), arg_to_type(c))),
);
writeln!(
generated,
"pub fn {name}({args}) -> (usize, [u8; MAX_SIZE]) {{"
)?;
let arg_names = comma_sep(iter_args(ty).map(|(i, c)| format!("{}{i}", arg_to_name(c))));
writeln!(
generated,
" unsafe {{ crate::encode({ty}({op}, {arg_names})) }}"
)?;
writeln!(generated, "}}")?;
}
Ok(())
}
fn gen_structs(generated: &mut String) -> Result<(), Box<dyn std::error::Error>> {
let mut seen = std::collections::HashSet::new();
for [_, _, ty, _] in instructions() {
if !seen.insert(ty) {
continue;
}
let types = comma_sep(iter_args(ty).map(|(_, c)| arg_to_type(c).to_string()));
writeln!(generated, "#[repr(packed)] pub struct {ty}(u8, {types});")?;
}
Ok(())
}
fn comma_sep(items: impl Iterator<Item = String>) -> String {
items
.map(|item| item.to_string())
.collect::<Vec<_>>()
.join(", ")
}
fn instructions() -> impl Iterator<Item = [&'static str; 4]> {
include_str!("../hbbytecode/instructions.in")
.lines()
.filter_map(|line| line.strip_suffix(';'))
.map(|line| line.splitn(4, ',').map(str::trim).next_chunk().unwrap())
}
fn arg_to_type(arg: char) -> &'static str {
match arg {
'R' | 'B' => "u8",
'H' => "u16",
'W' => "u32",
'D' | 'A' => "u64",
'P' => "i16",
'O' => "i32",
_ => panic!("unknown type: {}", arg),
}
}
fn arg_to_width(arg: char) -> usize {
match arg {
'R' | 'B' => 1,
'H' => 2,
'W' => 4,
'D' | 'A' => 8,
'P' => 2,
'O' => 4,
_ => panic!("unknown type: {}", arg),
}
}
fn arg_to_name(arg: char) -> &'static str {
match arg {
'R' => "reg",
'B' | 'H' | 'W' | 'D' => "imm",
'P' | 'O' => "offset",
'A' => "addr",
_ => panic!("unknown type: {}", arg),
}
}
fn iter_args(ty: &'static str) -> impl Iterator<Item = (usize, char)> {
ty.chars().enumerate().filter(|(_, c)| *c != 'N')
}

View File

@ -1,3 +0,0 @@
main := fn(): int {
return 10 - 20 / 2 + 4 * (2 + 2) - 4 * 4 + 1;
}

View File

@ -1,43 +0,0 @@
Color := struct {
r: u8,
g: u8,
b: u8,
a: u8,
}
Point := struct {
x: u32,
y: u32,
}
Pixel := struct {
color: Color,
point: Point,
}
main := fn(): int {
pixel := Pixel.{
color: Color.{
r: 255,
g: 0,
b: 0,
a: 255,
},
point: Point.{
x: 0,
y: 2,
},
};
if *(&pixel.point.x + 1) != 2 {
return 0;
}
if *(&pixel.point.y - 1) != 0 {
return 64;
}
return pixel.point.x + pixel.point.y + pixel.color.r
+ pixel.color.g + pixel.color.b + pixel.color.a;
}

View File

@ -1,9 +0,0 @@
Type := struct {
brah: int,
blah: int,
}
main := fn(): int {
return @eca(int, 1, Type.(10, 20), @sizeof(Type), @alignof(Type), 5, 6);
}

View File

@ -1,36 +0,0 @@
arm_fb_ptr := fn(): int return 100;
x86_fb_ptr := fn(): int return 100;
check_platform := fn(): int {
return x86_fb_ptr();
}
set_pixel := fn(x: int, y: int, width: int): int {
pix_offset := y * width + x;
return 0;
}
main := fn(): int {
fb_ptr := check_platform();
width := 100;
height := 30;
x:= 0;
y:= 0;
loop {
if x <= height + 1 {
set_pixel(x,y,width);
x = x + 1;
} else {
set_pixel(x,y,width);
x = 0;
y = y + 1;
}
if y == width {
break;
}
}
return 0;
}

View File

@ -1,14 +0,0 @@
main := fn(): int {
return add_one(10) + add_two(20);
}
add_two := fn(x: int): int {
return x + 2;
}
add_one := fn(x: int): int {
return x + 1;
}

View File

@ -1,12 +0,0 @@
main := fn(): int {
return fib(10);
}
fib := fn(x: int): int {
if x <= 2 {
return 1;
} else {
return fib(x - 1) + fib(x - 2);
}
}

View File

@ -1,22 +0,0 @@
main := fn(): int {
return fib(10);
}
fib := fn(n: int): int {
a := 0;
b := 1;
loop {
if n == 0 {
break;
}
c := a + b;
a = b;
b = c;
n = n - 1;
stack_reclamation_edge_case := 0;
continue;
}
return a;
}

View File

@ -1,3 +0,0 @@
main := fn(): int {
return 1;
}

View File

@ -1,17 +0,0 @@
main := fn(): int {
a := 1;
b := &a;
modify(b);
drop(a);
stack_reclamation_edge_case := 0;
return *b - 2;
}
modify := fn(a: *int): void {
*a = 2;
return;
}
drop := fn(a: int): void {
return;
}

View File

@ -1,21 +0,0 @@
Point := struct {
x: int,
y: int,
}
Rect := struct {
a: Point,
b: Point,
}
main := fn(): int {
a := Point.(1, 2);
b := Point.(3, 4);
d := Rect.(a + b, b - a);
d2 := Rect.(Point.(0, 0) - b, a);
d2 = d2 + d;
c := d2.a + d2.b;
return c.x + c.y;
}

View File

@ -1,26 +0,0 @@
Ty := struct {
a: int,
b: int,
}
Ty2 := struct {
ty: Ty,
c: int,
}
main := fn(): int {
finst := Ty2.{ ty: Ty.{ a: 4, b: 1 }, c: 3 };
inst := odher_pass(finst);
if inst.c == 3 {
return pass(&inst.ty);
}
return 0;
}
pass := fn(t: *Ty): int {
return t.a - t.b;
}
odher_pass := fn(t: Ty2): Ty2 {
return t;
}

View File

@ -1,6 +0,0 @@
main := fn(): int {
a := 1;
b := 2;
a = a + 1;
return a - b;
}

File diff suppressed because it is too large Load Diff

View File

@ -1,25 +0,0 @@
pub type Ident = u32;
const LEN_BITS: u32 = 6;
pub fn len(ident: Ident) -> u32 {
ident & ((1 << LEN_BITS) - 1)
}
pub fn is_null(ident: Ident) -> bool {
(ident >> LEN_BITS) == 0
}
pub fn pos(ident: Ident) -> u32 {
(ident >> LEN_BITS).saturating_sub(1)
}
pub fn new(pos: u32, len: u32) -> Ident {
debug_assert!(len < (1 << LEN_BITS));
((pos + 1) << LEN_BITS) | len
}
pub fn range(ident: Ident) -> std::ops::Range<usize> {
let (len, pos) = (len(ident) as usize, pos(ident) as usize);
pos..pos + len
}

View File

@ -1,623 +0,0 @@
pub const MAX_SIZE: usize = 13;
/// Cause an unreachable code trap
pub fn un() -> (usize, [u8; MAX_SIZE]) {
unsafe { crate::encode(N(0x00, )) }
}
/// Termiante execution
pub fn tx() -> (usize, [u8; MAX_SIZE]) {
unsafe { crate::encode(N(0x01, )) }
}
/// Do nothing
pub fn nop() -> (usize, [u8; MAX_SIZE]) {
unsafe { crate::encode(N(0x02, )) }
}
/// Addition (8b)
pub fn add8(reg0: u8, reg1: u8, reg2: u8) -> (usize, [u8; MAX_SIZE]) {
unsafe { crate::encode(RRR(0x03, reg0, reg1, reg2)) }
}
/// Addition (16b)
pub fn add16(reg0: u8, reg1: u8, reg2: u8) -> (usize, [u8; MAX_SIZE]) {
unsafe { crate::encode(RRR(0x04, reg0, reg1, reg2)) }
}
/// Addition (32b)
pub fn add32(reg0: u8, reg1: u8, reg2: u8) -> (usize, [u8; MAX_SIZE]) {
unsafe { crate::encode(RRR(0x05, reg0, reg1, reg2)) }
}
/// Addition (64b)
pub fn add64(reg0: u8, reg1: u8, reg2: u8) -> (usize, [u8; MAX_SIZE]) {
unsafe { crate::encode(RRR(0x06, reg0, reg1, reg2)) }
}
/// Subtraction (8b)
pub fn sub8(reg0: u8, reg1: u8, reg2: u8) -> (usize, [u8; MAX_SIZE]) {
unsafe { crate::encode(RRR(0x07, reg0, reg1, reg2)) }
}
/// Subtraction (16b)
pub fn sub16(reg0: u8, reg1: u8, reg2: u8) -> (usize, [u8; MAX_SIZE]) {
unsafe { crate::encode(RRR(0x08, reg0, reg1, reg2)) }
}
/// Subtraction (32b)
pub fn sub32(reg0: u8, reg1: u8, reg2: u8) -> (usize, [u8; MAX_SIZE]) {
unsafe { crate::encode(RRR(0x09, reg0, reg1, reg2)) }
}
/// Subtraction (64b)
pub fn sub64(reg0: u8, reg1: u8, reg2: u8) -> (usize, [u8; MAX_SIZE]) {
unsafe { crate::encode(RRR(0x0A, reg0, reg1, reg2)) }
}
/// Multiplication (8b)
pub fn mul8(reg0: u8, reg1: u8, reg2: u8) -> (usize, [u8; MAX_SIZE]) {
unsafe { crate::encode(RRR(0x0B, reg0, reg1, reg2)) }
}
/// Multiplication (16b)
pub fn mul16(reg0: u8, reg1: u8, reg2: u8) -> (usize, [u8; MAX_SIZE]) {
unsafe { crate::encode(RRR(0x0C, reg0, reg1, reg2)) }
}
/// Multiplication (32b)
pub fn mul32(reg0: u8, reg1: u8, reg2: u8) -> (usize, [u8; MAX_SIZE]) {
unsafe { crate::encode(RRR(0x0D, reg0, reg1, reg2)) }
}
/// Multiplication (64b)
pub fn mul64(reg0: u8, reg1: u8, reg2: u8) -> (usize, [u8; MAX_SIZE]) {
unsafe { crate::encode(RRR(0x0E, reg0, reg1, reg2)) }
}
/// Bitand
pub fn and(reg0: u8, reg1: u8, reg2: u8) -> (usize, [u8; MAX_SIZE]) {
unsafe { crate::encode(RRR(0x0F, reg0, reg1, reg2)) }
}
/// Bitor
pub fn or(reg0: u8, reg1: u8, reg2: u8) -> (usize, [u8; MAX_SIZE]) {
unsafe { crate::encode(RRR(0x10, reg0, reg1, reg2)) }
}
/// Bitxor
pub fn xor(reg0: u8, reg1: u8, reg2: u8) -> (usize, [u8; MAX_SIZE]) {
unsafe { crate::encode(RRR(0x11, reg0, reg1, reg2)) }
}
/// Unsigned left bitshift (8b)
pub fn slu8(reg0: u8, reg1: u8, reg2: u8) -> (usize, [u8; MAX_SIZE]) {
unsafe { crate::encode(RRR(0x12, reg0, reg1, reg2)) }
}
/// Unsigned left bitshift (16b)
pub fn slu16(reg0: u8, reg1: u8, reg2: u8) -> (usize, [u8; MAX_SIZE]) {
unsafe { crate::encode(RRR(0x13, reg0, reg1, reg2)) }
}
/// Unsigned left bitshift (32b)
pub fn slu32(reg0: u8, reg1: u8, reg2: u8) -> (usize, [u8; MAX_SIZE]) {
unsafe { crate::encode(RRR(0x14, reg0, reg1, reg2)) }
}
/// Unsigned left bitshift (64b)
pub fn slu64(reg0: u8, reg1: u8, reg2: u8) -> (usize, [u8; MAX_SIZE]) {
unsafe { crate::encode(RRR(0x15, reg0, reg1, reg2)) }
}
/// Unsigned right bitshift (8b)
pub fn sru8(reg0: u8, reg1: u8, reg2: u8) -> (usize, [u8; MAX_SIZE]) {
unsafe { crate::encode(RRR(0x16, reg0, reg1, reg2)) }
}
/// Unsigned right bitshift (16b)
pub fn sru16(reg0: u8, reg1: u8, reg2: u8) -> (usize, [u8; MAX_SIZE]) {
unsafe { crate::encode(RRR(0x17, reg0, reg1, reg2)) }
}
/// Unsigned right bitshift (32b)
pub fn sru32(reg0: u8, reg1: u8, reg2: u8) -> (usize, [u8; MAX_SIZE]) {
unsafe { crate::encode(RRR(0x18, reg0, reg1, reg2)) }
}
/// Unsigned right bitshift (64b)
pub fn sru64(reg0: u8, reg1: u8, reg2: u8) -> (usize, [u8; MAX_SIZE]) {
unsafe { crate::encode(RRR(0x19, reg0, reg1, reg2)) }
}
/// Signed right bitshift (8b)
pub fn srs8(reg0: u8, reg1: u8, reg2: u8) -> (usize, [u8; MAX_SIZE]) {
unsafe { crate::encode(RRR(0x1A, reg0, reg1, reg2)) }
}
/// Signed right bitshift (16b)
pub fn srs16(reg0: u8, reg1: u8, reg2: u8) -> (usize, [u8; MAX_SIZE]) {
unsafe { crate::encode(RRR(0x1B, reg0, reg1, reg2)) }
}
/// Signed right bitshift (32b)
pub fn srs32(reg0: u8, reg1: u8, reg2: u8) -> (usize, [u8; MAX_SIZE]) {
unsafe { crate::encode(RRR(0x1C, reg0, reg1, reg2)) }
}
/// Signed right bitshift (64b)
pub fn srs64(reg0: u8, reg1: u8, reg2: u8) -> (usize, [u8; MAX_SIZE]) {
unsafe { crate::encode(RRR(0x1D, reg0, reg1, reg2)) }
}
/// Unsigned comparsion
pub fn cmpu(reg0: u8, reg1: u8, reg2: u8) -> (usize, [u8; MAX_SIZE]) {
unsafe { crate::encode(RRR(0x1E, reg0, reg1, reg2)) }
}
/// Signed comparsion
pub fn cmps(reg0: u8, reg1: u8, reg2: u8) -> (usize, [u8; MAX_SIZE]) {
unsafe { crate::encode(RRR(0x1F, reg0, reg1, reg2)) }
}
/// Merged divide-remainder (unsigned 8b)
pub fn diru8(reg0: u8, reg1: u8, reg2: u8, reg3: u8) -> (usize, [u8; MAX_SIZE]) {
unsafe { crate::encode(RRRR(0x20, reg0, reg1, reg2, reg3)) }
}
/// Merged divide-remainder (unsigned 16b)
pub fn diru16(reg0: u8, reg1: u8, reg2: u8, reg3: u8) -> (usize, [u8; MAX_SIZE]) {
unsafe { crate::encode(RRRR(0x21, reg0, reg1, reg2, reg3)) }
}
/// Merged divide-remainder (unsigned 32b)
pub fn diru32(reg0: u8, reg1: u8, reg2: u8, reg3: u8) -> (usize, [u8; MAX_SIZE]) {
unsafe { crate::encode(RRRR(0x22, reg0, reg1, reg2, reg3)) }
}
/// Merged divide-remainder (unsigned 64b)
pub fn diru64(reg0: u8, reg1: u8, reg2: u8, reg3: u8) -> (usize, [u8; MAX_SIZE]) {
unsafe { crate::encode(RRRR(0x23, reg0, reg1, reg2, reg3)) }
}
/// Merged divide-remainder (signed 8b)
pub fn dirs8(reg0: u8, reg1: u8, reg2: u8, reg3: u8) -> (usize, [u8; MAX_SIZE]) {
unsafe { crate::encode(RRRR(0x24, reg0, reg1, reg2, reg3)) }
}
/// Merged divide-remainder (signed 16b)
pub fn dirs16(reg0: u8, reg1: u8, reg2: u8, reg3: u8) -> (usize, [u8; MAX_SIZE]) {
unsafe { crate::encode(RRRR(0x25, reg0, reg1, reg2, reg3)) }
}
/// Merged divide-remainder (signed 32b)
pub fn dirs32(reg0: u8, reg1: u8, reg2: u8, reg3: u8) -> (usize, [u8; MAX_SIZE]) {
unsafe { crate::encode(RRRR(0x26, reg0, reg1, reg2, reg3)) }
}
/// Merged divide-remainder (signed 64b)
pub fn dirs64(reg0: u8, reg1: u8, reg2: u8, reg3: u8) -> (usize, [u8; MAX_SIZE]) {
unsafe { crate::encode(RRRR(0x27, reg0, reg1, reg2, reg3)) }
}
/// Bit negation
pub fn neg(reg0: u8, reg1: u8) -> (usize, [u8; MAX_SIZE]) {
unsafe { crate::encode(RR(0x28, reg0, reg1)) }
}
/// Logical negation
pub fn not(reg0: u8, reg1: u8) -> (usize, [u8; MAX_SIZE]) {
unsafe { crate::encode(RR(0x29, reg0, reg1)) }
}
/// Sign extend 8b to 64b
pub fn sxt8(reg0: u8, reg1: u8) -> (usize, [u8; MAX_SIZE]) {
unsafe { crate::encode(RR(0x2A, reg0, reg1)) }
}
/// Sign extend 16b to 64b
pub fn sxt16(reg0: u8, reg1: u8) -> (usize, [u8; MAX_SIZE]) {
unsafe { crate::encode(RR(0x2B, reg0, reg1)) }
}
/// Sign extend 32b to 64b
pub fn sxt32(reg0: u8, reg1: u8) -> (usize, [u8; MAX_SIZE]) {
unsafe { crate::encode(RR(0x2C, reg0, reg1)) }
}
/// Addition with immediate (8b)
pub fn addi8(reg0: u8, reg1: u8, imm2: u8) -> (usize, [u8; MAX_SIZE]) {
unsafe { crate::encode(RRB(0x2D, reg0, reg1, imm2)) }
}
/// Addition with immediate (16b)
pub fn addi16(reg0: u8, reg1: u8, imm2: u16) -> (usize, [u8; MAX_SIZE]) {
unsafe { crate::encode(RRH(0x2E, reg0, reg1, imm2)) }
}
/// Addition with immediate (32b)
pub fn addi32(reg0: u8, reg1: u8, imm2: u32) -> (usize, [u8; MAX_SIZE]) {
unsafe { crate::encode(RRW(0x2F, reg0, reg1, imm2)) }
}
/// Addition with immediate (64b)
pub fn addi64(reg0: u8, reg1: u8, imm2: u64) -> (usize, [u8; MAX_SIZE]) {
unsafe { crate::encode(RRD(0x30, reg0, reg1, imm2)) }
}
/// Multiplication with immediate (8b)
pub fn muli8(reg0: u8, reg1: u8, imm2: u8) -> (usize, [u8; MAX_SIZE]) {
unsafe { crate::encode(RRB(0x31, reg0, reg1, imm2)) }
}
/// Multiplication with immediate (16b)
pub fn muli16(reg0: u8, reg1: u8, imm2: u16) -> (usize, [u8; MAX_SIZE]) {
unsafe { crate::encode(RRH(0x32, reg0, reg1, imm2)) }
}
/// Multiplication with immediate (32b)
pub fn muli32(reg0: u8, reg1: u8, imm2: u32) -> (usize, [u8; MAX_SIZE]) {
unsafe { crate::encode(RRW(0x33, reg0, reg1, imm2)) }
}
/// Multiplication with immediate (64b)
pub fn muli64(reg0: u8, reg1: u8, imm2: u64) -> (usize, [u8; MAX_SIZE]) {
unsafe { crate::encode(RRD(0x34, reg0, reg1, imm2)) }
}
/// Bitand with immediate
pub fn andi(reg0: u8, reg1: u8, imm2: u64) -> (usize, [u8; MAX_SIZE]) {
unsafe { crate::encode(RRD(0x35, reg0, reg1, imm2)) }
}
/// Bitor with immediate
pub fn ori(reg0: u8, reg1: u8, imm2: u64) -> (usize, [u8; MAX_SIZE]) {
unsafe { crate::encode(RRD(0x36, reg0, reg1, imm2)) }
}
/// Bitxor with immediate
pub fn xori(reg0: u8, reg1: u8, imm2: u64) -> (usize, [u8; MAX_SIZE]) {
unsafe { crate::encode(RRD(0x37, reg0, reg1, imm2)) }
}
/// Unsigned left bitshift with immedidate (8b)
pub fn slui8(reg0: u8, reg1: u8, imm2: u8) -> (usize, [u8; MAX_SIZE]) {
unsafe { crate::encode(RRB(0x38, reg0, reg1, imm2)) }
}
/// Unsigned left bitshift with immedidate (16b)
pub fn slui16(reg0: u8, reg1: u8, imm2: u8) -> (usize, [u8; MAX_SIZE]) {
unsafe { crate::encode(RRB(0x39, reg0, reg1, imm2)) }
}
/// Unsigned left bitshift with immedidate (32b)
pub fn slui32(reg0: u8, reg1: u8, imm2: u8) -> (usize, [u8; MAX_SIZE]) {
unsafe { crate::encode(RRB(0x3A, reg0, reg1, imm2)) }
}
/// Unsigned left bitshift with immedidate (64b)
pub fn slui64(reg0: u8, reg1: u8, imm2: u8) -> (usize, [u8; MAX_SIZE]) {
unsafe { crate::encode(RRB(0x3B, reg0, reg1, imm2)) }
}
/// Unsigned right bitshift with immediate (8b)
pub fn srui8(reg0: u8, reg1: u8, imm2: u8) -> (usize, [u8; MAX_SIZE]) {
unsafe { crate::encode(RRB(0x3C, reg0, reg1, imm2)) }
}
/// Unsigned right bitshift with immediate (16b)
pub fn srui16(reg0: u8, reg1: u8, imm2: u8) -> (usize, [u8; MAX_SIZE]) {
unsafe { crate::encode(RRB(0x3D, reg0, reg1, imm2)) }
}
/// Unsigned right bitshift with immediate (32b)
pub fn srui32(reg0: u8, reg1: u8, imm2: u8) -> (usize, [u8; MAX_SIZE]) {
unsafe { crate::encode(RRB(0x3E, reg0, reg1, imm2)) }
}
/// Unsigned right bitshift with immediate (64b)
pub fn srui64(reg0: u8, reg1: u8, imm2: u8) -> (usize, [u8; MAX_SIZE]) {
unsafe { crate::encode(RRB(0x3F, reg0, reg1, imm2)) }
}
/// Signed right bitshift with immediate
pub fn srsi8(reg0: u8, reg1: u8, imm2: u8) -> (usize, [u8; MAX_SIZE]) {
unsafe { crate::encode(RRB(0x40, reg0, reg1, imm2)) }
}
/// Signed right bitshift with immediate
pub fn srsi16(reg0: u8, reg1: u8, imm2: u8) -> (usize, [u8; MAX_SIZE]) {
unsafe { crate::encode(RRB(0x41, reg0, reg1, imm2)) }
}
/// Signed right bitshift with immediate
pub fn srsi32(reg0: u8, reg1: u8, imm2: u8) -> (usize, [u8; MAX_SIZE]) {
unsafe { crate::encode(RRB(0x42, reg0, reg1, imm2)) }
}
/// Signed right bitshift with immediate
pub fn srsi64(reg0: u8, reg1: u8, imm2: u8) -> (usize, [u8; MAX_SIZE]) {
unsafe { crate::encode(RRB(0x43, reg0, reg1, imm2)) }
}
/// Unsigned compare with immediate
pub fn cmpui(reg0: u8, reg1: u8, imm2: u64) -> (usize, [u8; MAX_SIZE]) {
unsafe { crate::encode(RRD(0x44, reg0, reg1, imm2)) }
}
/// Signed compare with immediate
pub fn cmpsi(reg0: u8, reg1: u8, imm2: u64) -> (usize, [u8; MAX_SIZE]) {
unsafe { crate::encode(RRD(0x45, reg0, reg1, imm2)) }
}
/// Copy register
pub fn cp(reg0: u8, reg1: u8) -> (usize, [u8; MAX_SIZE]) {
unsafe { crate::encode(RR(0x46, reg0, reg1)) }
}
/// Swap registers
pub fn swa(reg0: u8, reg1: u8) -> (usize, [u8; MAX_SIZE]) {
unsafe { crate::encode(RR(0x47, reg0, reg1)) }
}
/// Load immediate (8b)
pub fn li8(reg0: u8, imm1: u8) -> (usize, [u8; MAX_SIZE]) {
unsafe { crate::encode(RB(0x48, reg0, imm1)) }
}
/// Load immediate (16b)
pub fn li16(reg0: u8, imm1: u16) -> (usize, [u8; MAX_SIZE]) {
unsafe { crate::encode(RH(0x49, reg0, imm1)) }
}
/// Load immediate (32b)
pub fn li32(reg0: u8, imm1: u32) -> (usize, [u8; MAX_SIZE]) {
unsafe { crate::encode(RW(0x4A, reg0, imm1)) }
}
/// Load immediate (64b)
pub fn li64(reg0: u8, imm1: u64) -> (usize, [u8; MAX_SIZE]) {
unsafe { crate::encode(RD(0x4B, reg0, imm1)) }
}
/// Load relative address
pub fn lra(reg0: u8, reg1: u8, offset2: i32) -> (usize, [u8; MAX_SIZE]) {
unsafe { crate::encode(RRO(0x4C, reg0, reg1, offset2)) }
}
/// Load from absolute address
pub fn ld(reg0: u8, reg1: u8, addr2: u64, imm3: u16) -> (usize, [u8; MAX_SIZE]) {
unsafe { crate::encode(RRAH(0x4D, reg0, reg1, addr2, imm3)) }
}
/// Store to absolute address
pub fn st(reg0: u8, reg1: u8, addr2: u64, imm3: u16) -> (usize, [u8; MAX_SIZE]) {
unsafe { crate::encode(RRAH(0x4E, reg0, reg1, addr2, imm3)) }
}
/// Load from relative address
pub fn ldr(reg0: u8, reg1: u8, offset2: i32, imm3: u16) -> (usize, [u8; MAX_SIZE]) {
unsafe { crate::encode(RROH(0x4F, reg0, reg1, offset2, imm3)) }
}
/// Store to relative address
pub fn str(reg0: u8, reg1: u8, offset2: i32, imm3: u16) -> (usize, [u8; MAX_SIZE]) {
unsafe { crate::encode(RROH(0x50, reg0, reg1, offset2, imm3)) }
}
/// Copy block of memory
pub fn bmc(reg0: u8, reg1: u8, imm2: u16) -> (usize, [u8; MAX_SIZE]) {
unsafe { crate::encode(RRH(0x51, reg0, reg1, imm2)) }
}
/// Copy register block
pub fn brc(reg0: u8, reg1: u8, imm2: u8) -> (usize, [u8; MAX_SIZE]) {
unsafe { crate::encode(RRB(0x52, reg0, reg1, imm2)) }
}
/// Relative jump
pub fn jmp(offset0: i32) -> (usize, [u8; MAX_SIZE]) {
unsafe { crate::encode(O(0x53, offset0)) }
}
/// Linking relative jump
pub fn jal(reg0: u8, reg1: u8, offset2: i32) -> (usize, [u8; MAX_SIZE]) {
unsafe { crate::encode(RRO(0x54, reg0, reg1, offset2)) }
}
/// Linking absolute jump
pub fn jala(reg0: u8, reg1: u8, addr2: u64) -> (usize, [u8; MAX_SIZE]) {
unsafe { crate::encode(RRA(0x55, reg0, reg1, addr2)) }
}
/// Branch on equal
pub fn jeq(reg0: u8, reg1: u8, offset2: i16) -> (usize, [u8; MAX_SIZE]) {
unsafe { crate::encode(RRP(0x56, reg0, reg1, offset2)) }
}
/// Branch on nonequal
pub fn jne(reg0: u8, reg1: u8, offset2: i16) -> (usize, [u8; MAX_SIZE]) {
unsafe { crate::encode(RRP(0x57, reg0, reg1, offset2)) }
}
/// Branch on lesser-than (unsigned)
pub fn jltu(reg0: u8, reg1: u8, offset2: i16) -> (usize, [u8; MAX_SIZE]) {
unsafe { crate::encode(RRP(0x58, reg0, reg1, offset2)) }
}
/// Branch on greater-than (unsigned)
pub fn jgtu(reg0: u8, reg1: u8, offset2: i16) -> (usize, [u8; MAX_SIZE]) {
unsafe { crate::encode(RRP(0x59, reg0, reg1, offset2)) }
}
/// Branch on lesser-than (signed)
pub fn jlts(reg0: u8, reg1: u8, offset2: i16) -> (usize, [u8; MAX_SIZE]) {
unsafe { crate::encode(RRP(0x5A, reg0, reg1, offset2)) }
}
/// Branch on greater-than (signed)
pub fn jgts(reg0: u8, reg1: u8, offset2: i16) -> (usize, [u8; MAX_SIZE]) {
unsafe { crate::encode(RRP(0x5B, reg0, reg1, offset2)) }
}
/// Environment call trap
pub fn eca() -> (usize, [u8; MAX_SIZE]) {
unsafe { crate::encode(N(0x5C, )) }
}
/// Environment breakpoint
pub fn ebp() -> (usize, [u8; MAX_SIZE]) {
unsafe { crate::encode(N(0x5D, )) }
}
/// Floating point addition (32b)
pub fn fadd32(reg0: u8, reg1: u8, reg2: u8) -> (usize, [u8; MAX_SIZE]) {
unsafe { crate::encode(RRR(0x5E, reg0, reg1, reg2)) }
}
/// Floating point addition (64b)
pub fn fadd64(reg0: u8, reg1: u8, reg2: u8) -> (usize, [u8; MAX_SIZE]) {
unsafe { crate::encode(RRR(0x5F, reg0, reg1, reg2)) }
}
/// Floating point subtraction (32b)
pub fn fsub32(reg0: u8, reg1: u8, reg2: u8) -> (usize, [u8; MAX_SIZE]) {
unsafe { crate::encode(RRR(0x60, reg0, reg1, reg2)) }
}
/// Floating point subtraction (64b)
pub fn fsub64(reg0: u8, reg1: u8, reg2: u8) -> (usize, [u8; MAX_SIZE]) {
unsafe { crate::encode(RRR(0x61, reg0, reg1, reg2)) }
}
/// Floating point multiply (32b)
pub fn fmul32(reg0: u8, reg1: u8, reg2: u8) -> (usize, [u8; MAX_SIZE]) {
unsafe { crate::encode(RRR(0x62, reg0, reg1, reg2)) }
}
/// Floating point multiply (64b)
pub fn fmul64(reg0: u8, reg1: u8, reg2: u8) -> (usize, [u8; MAX_SIZE]) {
unsafe { crate::encode(RRR(0x63, reg0, reg1, reg2)) }
}
/// Floating point division (32b)
pub fn fdiv32(reg0: u8, reg1: u8, reg2: u8) -> (usize, [u8; MAX_SIZE]) {
unsafe { crate::encode(RRR(0x64, reg0, reg1, reg2)) }
}
/// Floating point division (64b)
pub fn fdiv64(reg0: u8, reg1: u8, reg2: u8) -> (usize, [u8; MAX_SIZE]) {
unsafe { crate::encode(RRR(0x65, reg0, reg1, reg2)) }
}
/// Float fused multiply-add (32b)
pub fn fma32(reg0: u8, reg1: u8, reg2: u8, reg3: u8) -> (usize, [u8; MAX_SIZE]) {
unsafe { crate::encode(RRRR(0x66, reg0, reg1, reg2, reg3)) }
}
/// Float fused multiply-add (64b)
pub fn fma64(reg0: u8, reg1: u8, reg2: u8, reg3: u8) -> (usize, [u8; MAX_SIZE]) {
unsafe { crate::encode(RRRR(0x67, reg0, reg1, reg2, reg3)) }
}
/// Float reciprocal (32b)
pub fn finv32(reg0: u8, reg1: u8) -> (usize, [u8; MAX_SIZE]) {
unsafe { crate::encode(RR(0x68, reg0, reg1)) }
}
/// Float reciprocal (64b)
pub fn finv64(reg0: u8, reg1: u8) -> (usize, [u8; MAX_SIZE]) {
unsafe { crate::encode(RR(0x69, reg0, reg1)) }
}
/// Flaot compare less than (32b)
pub fn fcmplt32(reg0: u8, reg1: u8, reg2: u8) -> (usize, [u8; MAX_SIZE]) {
unsafe { crate::encode(RRR(0x6A, reg0, reg1, reg2)) }
}
/// Flaot compare less than (64b)
pub fn fcmplt64(reg0: u8, reg1: u8, reg2: u8) -> (usize, [u8; MAX_SIZE]) {
unsafe { crate::encode(RRR(0x6B, reg0, reg1, reg2)) }
}
/// Flaot compare greater than (32b)
pub fn fcmpgt32(reg0: u8, reg1: u8, reg2: u8) -> (usize, [u8; MAX_SIZE]) {
unsafe { crate::encode(RRR(0x6C, reg0, reg1, reg2)) }
}
/// Flaot compare greater than (64b)
pub fn fcmpgt64(reg0: u8, reg1: u8, reg2: u8) -> (usize, [u8; MAX_SIZE]) {
unsafe { crate::encode(RRR(0x6D, reg0, reg1, reg2)) }
}
/// Int to 32 bit float
pub fn itf32(reg0: u8, reg1: u8) -> (usize, [u8; MAX_SIZE]) {
unsafe { crate::encode(RR(0x6E, reg0, reg1)) }
}
/// Int to 64 bit float
pub fn itf64(reg0: u8, reg1: u8) -> (usize, [u8; MAX_SIZE]) {
unsafe { crate::encode(RR(0x6F, reg0, reg1)) }
}
/// Float 32 to int
pub fn fti32(reg0: u8, reg1: u8, imm2: u8) -> (usize, [u8; MAX_SIZE]) {
unsafe { crate::encode(RRB(0x70, reg0, reg1, imm2)) }
}
/// Float 64 to int
pub fn fti64(reg0: u8, reg1: u8, imm2: u8) -> (usize, [u8; MAX_SIZE]) {
unsafe { crate::encode(RRB(0x71, reg0, reg1, imm2)) }
}
/// Float 64 to Float 32
pub fn fc32t64(reg0: u8, reg1: u8) -> (usize, [u8; MAX_SIZE]) {
unsafe { crate::encode(RR(0x72, reg0, reg1)) }
}
/// Float 32 to Float 64
pub fn fc64t32(reg0: u8, reg1: u8, imm2: u8) -> (usize, [u8; MAX_SIZE]) {
unsafe { crate::encode(RRB(0x73, reg0, reg1, imm2)) }
}
/// Load relative immediate (16 bit)
pub fn lra16(reg0: u8, reg1: u8, offset2: i16) -> (usize, [u8; MAX_SIZE]) {
unsafe { crate::encode(RRP(0x74, reg0, reg1, offset2)) }
}
/// Load from relative address (16 bit)
pub fn ldr16(reg0: u8, reg1: u8, offset2: i16, imm3: u16) -> (usize, [u8; MAX_SIZE]) {
unsafe { crate::encode(RRPH(0x75, reg0, reg1, offset2, imm3)) }
}
/// Store to relative address (16 bit)
pub fn str16(reg0: u8, reg1: u8, offset2: i16, imm3: u16) -> (usize, [u8; MAX_SIZE]) {
unsafe { crate::encode(RRPH(0x76, reg0, reg1, offset2, imm3)) }
}
/// Relative jump (16 bit)
pub fn jmp16(offset0: i16) -> (usize, [u8; MAX_SIZE]) {
unsafe { crate::encode(P(0x77, offset0)) }
}
#[repr(packed)] pub struct N(u8, );
#[repr(packed)] pub struct RRR(u8, u8, u8, u8);
#[repr(packed)] pub struct RRRR(u8, u8, u8, u8, u8);
#[repr(packed)] pub struct RR(u8, u8, u8);
#[repr(packed)] pub struct RRB(u8, u8, u8, u8);
#[repr(packed)] pub struct RRH(u8, u8, u8, u16);
#[repr(packed)] pub struct RRW(u8, u8, u8, u32);
#[repr(packed)] pub struct RRD(u8, u8, u8, u64);
#[repr(packed)] pub struct RB(u8, u8, u8);
#[repr(packed)] pub struct RH(u8, u8, u16);
#[repr(packed)] pub struct RW(u8, u8, u32);
#[repr(packed)] pub struct RD(u8, u8, u64);
#[repr(packed)] pub struct RRO(u8, u8, u8, i32);
#[repr(packed)] pub struct RRAH(u8, u8, u8, u64, u16);
#[repr(packed)] pub struct RROH(u8, u8, u8, i32, u16);
#[repr(packed)] pub struct O(u8, i32);
#[repr(packed)] pub struct RRA(u8, u8, u8, u64);
#[repr(packed)] pub struct RRP(u8, u8, u8, i16);
#[repr(packed)] pub struct RRPH(u8, u8, u8, i16, u16);
#[repr(packed)] pub struct P(u8, i16);
pub const NAMES: [&str; 120] = [
"un",
"tx",
"nop",
"add8",
"add16",
"add32",
"add64",
"sub8",
"sub16",
"sub32",
"sub64",
"mul8",
"mul16",
"mul32",
"mul64",
"and",
"or",
"xor",
"slu8",
"slu16",
"slu32",
"slu64",
"sru8",
"sru16",
"sru32",
"sru64",
"srs8",
"srs16",
"srs32",
"srs64",
"cmpu",
"cmps",
"diru8",
"diru16",
"diru32",
"diru64",
"dirs8",
"dirs16",
"dirs32",
"dirs64",
"neg",
"not",
"sxt8",
"sxt16",
"sxt32",
"addi8",
"addi16",
"addi32",
"addi64",
"muli8",
"muli16",
"muli32",
"muli64",
"andi",
"ori",
"xori",
"slui8",
"slui16",
"slui32",
"slui64",
"srui8",
"srui16",
"srui32",
"srui64",
"srsi8",
"srsi16",
"srsi32",
"srsi64",
"cmpui",
"cmpsi",
"cp",
"swa",
"li8",
"li16",
"li32",
"li64",
"lra",
"ld",
"st",
"ldr",
"str",
"bmc",
"brc",
"jmp",
"jal",
"jala",
"jeq",
"jne",
"jltu",
"jgtu",
"jlts",
"jgts",
"eca",
"ebp",
"fadd32",
"fadd64",
"fsub32",
"fsub64",
"fmul32",
"fmul64",
"fdiv32",
"fdiv64",
"fma32",
"fma64",
"finv32",
"finv64",
"fcmplt32",
"fcmplt64",
"fcmpgt32",
"fcmpgt64",
"itf32",
"itf64",
"fti32",
"fti64",
"fc32t64",
"fc64t32",
"lra16",
"ldr16",
"str16",
"jmp16",
];

View File

@ -1,279 +0,0 @@
#[derive(Debug, PartialEq, Eq, Clone, Copy)]
pub struct Token {
pub kind: TokenKind,
pub start: u32,
pub end: u32,
}
impl Token {
pub fn range(&self) -> std::ops::Range<usize> {
self.start as usize..self.end as usize
}
pub fn len(&self) -> u32 {
self.end - self.start
}
}
macro_rules! gen_token_kind {
($(
#[$atts:meta])*
$vis:vis enum $name:ident {
#[patterns] $(
$pattern:ident,
)*
#[keywords] $(
$keyword:ident = $keyword_lit:literal,
)*
#[punkt] $(
$punkt:ident = $punkt_lit:literal,
)*
#[ops] $(
#[prec = $prec:literal] $(
$op:ident = $op_lit:literal,
)*
)*
}
) => {
impl std::fmt::Display for $name {
fn fmt(&self, f: &mut std::fmt::Formatter) -> std::fmt::Result {
let s = match *self {
$( Self::$pattern => concat!('<', stringify!($pattern), '>'), )*
$( Self::$keyword => stringify!($keyword_lit), )*
$( Self::$punkt => stringify!($punkt_lit), )*
$($( Self::$op => $op_lit, )*)*
};
f.write_str(s)
}
}
impl $name {
#[inline(always)]
pub fn precedence(&self) -> Option<u8> {
Some(match self {
$($(Self::$op)|* => $prec,)*
_ => return None,
})
}
#[inline(always)]
fn from_ident(ident: &[u8]) -> Self {
match ident {
$($keyword_lit => Self::$keyword,)*
_ => Self::Ident,
}
}
}
#[derive(Debug, PartialEq, Eq, Clone, Copy)]
$vis enum $name {
$( $pattern, )*
$( $keyword, )*
$( $punkt, )*
$($( $op, )*)*
}
};
}
gen_token_kind! {
pub enum TokenKind {
#[patterns]
Ident,
Number,
Eof,
Error,
Driective,
#[keywords]
Return = b"return",
If = b"if",
Else = b"else",
Loop = b"loop",
Break = b"break",
Continue = b"continue",
Fn = b"fn",
Struct = b"struct",
True = b"true",
#[punkt]
LParen = "(",
RParen = ")",
LBrace = "{",
RBrace = "}",
Semi = ";",
Colon = ":",
Comma = ",",
Dot = ".",
Ctor = ".{",
Tupl = ".(",
#[ops]
#[prec = 1]
Decl = ":=",
Assign = "=",
#[prec = 21]
Le = "<=",
Ge = ">=",
Lt = "<",
Gt = ">",
Eq = "==",
Ne = "!=",
#[prec = 22]
Amp = "&",
#[prec = 23]
Plus = "+",
Minus = "-",
#[prec = 24]
Star = "*",
FSlash = "/",
}
}
pub struct Lexer<'a> {
pos: u32,
bytes: &'a [u8],
}
impl<'a> Lexer<'a> {
pub fn new(input: &'a str) -> Self {
Self {
pos: 0,
bytes: input.as_bytes(),
}
}
pub fn slice(&self, tok: std::ops::Range<usize>) -> &'a str {
unsafe { std::str::from_utf8_unchecked(&self.bytes[tok]) }
}
fn peek(&self) -> Option<u8> {
self.bytes.get(self.pos as usize).copied()
}
fn advance(&mut self) -> Option<u8> {
let c = self.peek()?;
self.pos += 1;
Some(c)
}
pub fn next(&mut self) -> Token {
Iterator::next(self).unwrap_or(Token {
kind: TokenKind::Eof,
start: self.pos,
end: self.pos,
})
}
fn advance_if(&mut self, arg: u8) -> bool {
if self.peek() == Some(arg) {
self.advance();
true
} else {
false
}
}
pub fn line_col(&self, pos: u32) -> (usize, usize) {
line_col(self.bytes, pos)
}
}
pub fn line_col(bytes: &[u8], mut start: u32) -> (usize, usize) {
bytes
.split(|&b| b == b'\n')
.enumerate()
.find_map(|(i, line)| {
if start < line.len() as u32 {
return Some((i + 1, start as usize + 1));
}
start -= line.len() as u32 + 1;
None
})
.unwrap_or((1, 1))
}
impl<'a> Iterator for Lexer<'a> {
type Item = Token;
fn next(&mut self) -> Option<Self::Item> {
use TokenKind as T;
loop {
let mut start = self.pos;
let kind = match self.advance()? {
b'\n' | b'\r' | b'\t' | b' ' => continue,
b'0'..=b'9' => {
while let Some(b'0'..=b'9') = self.peek() {
self.advance();
}
T::Number
}
c @ (b'a'..=b'z' | b'A'..=b'Z' | b'_' | b'@') => {
while let Some(b'a'..=b'z' | b'A'..=b'Z' | b'0'..=b'9' | b'_') = self.peek() {
self.advance();
}
if c == b'@' {
start += 1;
T::Driective
} else {
let ident = &self.bytes[start as usize..self.pos as usize];
T::from_ident(ident)
}
}
b':' if self.advance_if(b'=') => T::Decl,
b':' => T::Colon,
b',' => T::Comma,
b'.' if self.advance_if(b'{') => T::Ctor,
b'.' if self.advance_if(b'(') => T::Tupl,
b'.' => T::Dot,
b';' => T::Semi,
b'!' if self.advance_if(b'=') => T::Ne,
b'=' if self.advance_if(b'=') => T::Eq,
b'=' => T::Assign,
b'<' if self.advance_if(b'=') => T::Le,
b'<' => T::Lt,
b'>' if self.advance_if(b'=') => T::Ge,
b'>' => T::Gt,
b'+' => T::Plus,
b'-' => T::Minus,
b'*' => T::Star,
b'/' => T::FSlash,
b'&' => T::Amp,
b'(' => T::LParen,
b')' => T::RParen,
b'{' => T::LBrace,
b'}' => T::RBrace,
_ => T::Error,
};
return Some(Token {
kind,
start,
end: self.pos,
});
}
}
}
#[cfg(test)]
mod tests {
fn lex(input: &'static str, output: &mut String) {
use {
super::{Lexer, TokenKind as T},
std::fmt::Write,
};
let mut lexer = Lexer::new(input);
loop {
let token = lexer.next();
writeln!(output, "{:?} {:?}", token.kind, &input[token.range()],).unwrap();
if token.kind == T::Eof {
break;
}
}
}
crate::run_tests! { lex:
empty => "";
whitespace => " \t\n\r";
example => include_str!("../examples/main_fn.hb");
arithmetic => include_str!("../examples/arithmetic.hb");
}
}

View File

@ -1,32 +0,0 @@
#![feature(noop_waker)]
#![feature(macro_metavar_expr)]
#![feature(let_chains)]
#![feature(non_null_convenience)]
#![allow(dead_code)]
#![feature(const_mut_refs)]
#[macro_export]
macro_rules! run_tests {
($runner:path: $($name:ident => $input:expr;)*) => {$(
#[test]
fn $name() {
$crate::tests::run_test(std::any::type_name_of_val(&$name), $input, $runner);
}
)*};
}
pub mod codegen;
mod ident;
mod instrs;
mod lexer;
mod log;
pub mod parser;
mod tests;
mod typechk;
#[inline]
unsafe fn encode<T>(instr: T) -> (usize, [u8; instrs::MAX_SIZE]) {
let mut buf = [0; instrs::MAX_SIZE];
std::ptr::write(buf.as_mut_ptr() as *mut T, instr);
(std::mem::size_of::<T>(), buf)
}

View File

@ -1,48 +0,0 @@
#![allow(unused_macros)]
#[derive(PartialOrd, PartialEq, Ord, Eq, Debug)]
pub enum Level {
Err,
Wrn,
Inf,
Dbg,
}
pub const LOG_LEVEL: Level = match option_env!("LOG_LEVEL") {
Some(val) => match val.as_bytes()[0] {
b'e' => Level::Err,
b'w' => Level::Wrn,
b'i' => Level::Inf,
b'd' => Level::Dbg,
_ => panic!("Invalid log level."),
},
None => {
if cfg!(debug_assertions) {
Level::Dbg
} else {
Level::Err
}
}
};
macro_rules! log {
($level:expr, $fmt:literal $($expr:tt)*) => {
if $level <= $crate::log::LOG_LEVEL {
println!("{:?}: {}", $level, format_args!($fmt $($expr)*));
}
};
($level:expr, $($arg:expr),*) => {
if $level <= $crate::log::LOG_LEVEL {
$(println!("[{}{}{}][{:?}]: {} = {:?}", line!(), column!(), file!(), $level, stringify!($arg), $arg);)*
}
};
}
macro_rules! err { ($($arg:tt)*) => { $crate::log::log!($crate::log::Level::Err, $($arg)*) }; }
macro_rules! wrn { ($($arg:tt)*) => { $crate::log::log!($crate::log::Level::Wrn, $($arg)*) }; }
macro_rules! inf { ($($arg:tt)*) => { $crate::log::log!($crate::log::Level::Inf, $($arg)*) }; }
macro_rules! dbg { ($($arg:tt)*) => { $crate::log::log!($crate::log::Level::Dbg, $($arg)*) }; }
#[allow(unused_imports)]
pub(crate) use {dbg, err, inf, log, wrn};

View File

@ -1,25 +0,0 @@
use std::io;
use hblang::{codegen, parser};
fn main() -> io::Result<()> {
if std::env::args().len() == 1 {
eprintln!("Usage: hblang <file1> <file2> ...");
eprintln!(" 1. compiled binary will be printed to stdout");
eprintln!(" 2. order of files matters");
std::process::exit(1);
}
let files = std::env::args()
.skip(1)
.map(|path| std::fs::read_to_string(&path).map(|src| (path, src)))
.collect::<io::Result<Vec<_>>>()?;
let arena = parser::Arena::default();
let mut parser = parser::Parser::new(&arena);
let mut codegen = codegen::Codegen::default();
for (path, content) in files.iter() {
let file = parser.file(&path, content.as_str());
codegen.file(path, content.as_bytes(), file);
}
codegen.dump(&mut std::io::stdout())
}

View File

@ -1,774 +0,0 @@
use std::{cell::Cell, ops::Not, ptr::NonNull};
use crate::{
codegen::bt,
ident::{self, Ident},
lexer::{Lexer, Token, TokenKind},
};
pub type Pos = u32;
struct ScopeIdent<'a> {
ident: Ident,
declared: bool,
last: &'a Cell<bool>,
}
pub struct Parser<'a, 'b> {
path: &'a str,
lexer: Lexer<'a>,
arena: &'b Arena<'a>,
token: Token,
idents: Vec<ScopeIdent<'a>>,
}
impl<'a, 'b> Parser<'a, 'b> {
pub fn new(arena: &'b Arena<'a>) -> Self {
let mut lexer = Lexer::new("");
let token = lexer.next();
Self {
lexer,
token,
path: "",
arena,
idents: Vec::new(),
}
}
pub fn file(&mut self, input: &'a str, path: &'a str) -> &'a [Expr<'a>] {
self.path = path;
self.lexer = Lexer::new(input);
self.token = self.lexer.next();
let f = self.collect(|s| (s.token.kind != TokenKind::Eof).then(|| s.expr()));
self.pop_scope(0);
let has_undeclared = !self.idents.is_empty();
for id in self.idents.drain(..) {
let (line, col) = self.lexer.line_col(ident::pos(id.ident));
eprintln!(
"{}:{}:{} => undeclared identifier: {}",
self.path,
line,
col,
self.lexer.slice(ident::range(id.ident))
);
}
if has_undeclared {
unreachable!();
}
f
}
fn next(&mut self) -> Token {
std::mem::replace(&mut self.token, self.lexer.next())
}
fn ptr_expr(&mut self) -> &'a Expr<'a> {
self.arena.alloc(self.expr())
}
fn expr(&mut self) -> Expr<'a> {
let left = self.unit_expr();
self.bin_expr(left, 0)
}
fn bin_expr(&mut self, mut left: Expr<'a>, min_prec: u8) -> Expr<'a> {
loop {
let Some(prec) = self.token.kind.precedence() else {
break;
};
if prec <= min_prec {
break;
}
let op = self.next().kind;
let right = self.unit_expr();
let right = self.bin_expr(right, prec);
left = Expr::BinOp {
left: self.arena.alloc(left),
right: self.arena.alloc(right),
op,
};
}
left
}
fn try_resolve_builtin(name: &str) -> Option<Ident> {
// FIXME: we actually do this the second time in the codegen
Some(match name {
"int" | "i64" => bt::INT,
"i8" => bt::I8,
"i16" => bt::I16,
"i32" => bt::I32,
"u8" => bt::U8,
"u16" => bt::U16,
"uint" | "u32" => bt::U32,
"bool" => bt::BOOL,
"void" => bt::VOID,
"never" => bt::NEVER,
_ => return None,
})
}
fn resolve_ident(&mut self, token: Token, decl: bool) -> (Ident, Option<&'a Cell<bool>>) {
let name = self.lexer.slice(token.range());
if let Some(builtin) = Self::try_resolve_builtin(name) {
return (builtin, None);
}
let last = self.arena.alloc(Cell::new(false));
let id = match self
.idents
.iter_mut()
.rfind(|elem| self.lexer.slice(ident::range(elem.ident)) == name)
{
Some(elem) if decl && elem.declared => {
self.report(format_args!("redeclaration of identifier: {name}"))
}
Some(elem) => elem,
None => {
let id = ident::new(token.start, name.len() as _);
self.idents.push(ScopeIdent {
ident: id,
declared: false,
last,
});
self.idents.last_mut().unwrap()
}
};
id.last = last;
id.declared |= decl;
(id.ident, Some(last))
}
fn unit_expr(&mut self) -> Expr<'a> {
use {Expr as E, TokenKind as T};
let frame = self.idents.len();
let token = self.next();
let mut expr = match token.kind {
T::Driective => E::Directive {
pos: token.start,
name: self.lexer.slice(token.range()),
args: {
self.expect_advance(T::LParen);
self.collect_list(T::Comma, T::RParen, Self::expr)
},
},
T::True => E::Bool {
pos: token.start,
value: true,
},
T::Struct => E::Struct {
pos: token.start,
fields: {
self.expect_advance(T::LBrace);
self.collect_list(T::Comma, T::RBrace, |s| {
let name = s.expect_advance(T::Ident);
s.expect_advance(T::Colon);
let ty = s.expr();
(s.lexer.slice(name.range()), ty)
})
},
},
T::Ident => {
let (id, last) = self.resolve_ident(token, self.token.kind == T::Decl);
let name = self.lexer.slice(token.range());
E::Ident { name, id, last }
}
T::If => E::If {
pos: token.start,
cond: self.ptr_expr(),
then: self.ptr_expr(),
else_: self.advance_if(T::Else).then(|| self.ptr_expr()),
},
T::Loop => E::Loop {
pos: token.start,
body: self.ptr_expr(),
},
T::Break => E::Break { pos: token.start },
T::Continue => E::Continue { pos: token.start },
T::Return => E::Return {
pos: token.start,
val: (self.token.kind != T::Semi).then(|| self.ptr_expr()),
},
T::Fn => E::Closure {
pos: token.start,
args: {
self.expect_advance(T::LParen);
self.collect_list(T::Comma, T::RParen, |s| {
let name = s.expect_advance(T::Ident);
let (id, last) = s.resolve_ident(name, true);
s.expect_advance(T::Colon);
Arg {
name: s.lexer.slice(name.range()),
id,
last,
ty: s.expr(),
}
})
},
ret: {
self.expect_advance(T::Colon);
self.ptr_expr()
},
body: self.ptr_expr(),
},
T::Amp | T::Star => E::UnOp {
pos: token.start,
op: token.kind,
val: self.ptr_unit_expr(),
},
T::LBrace => E::Block {
pos: token.start,
stmts: self.collect_list(T::Semi, T::RBrace, Self::expr),
},
T::Number => E::Number {
pos: token.start,
value: match self.lexer.slice(token.range()).parse() {
Ok(value) => value,
Err(e) => self.report(format_args!("invalid number: {e}")),
},
},
T::LParen => {
let expr = self.expr();
self.expect_advance(T::RParen);
expr
}
tok => self.report(format_args!("unexpected token: {tok:?}")),
};
loop {
let token = self.token;
if matches!(token.kind, T::LParen | T::Ctor | T::Dot | T::Tupl) {
self.next();
}
expr = match token.kind {
T::LParen => Expr::Call {
func: self.arena.alloc(expr),
args: self.collect_list(T::Comma, T::RParen, Self::expr),
},
T::Ctor => E::Ctor {
pos: token.start,
ty: Some(self.arena.alloc(expr)),
fields: self.collect_list(T::Comma, T::RBrace, |s| {
let name = s.expect_advance(T::Ident);
s.expect_advance(T::Colon);
let val = s.expr();
(Some(s.lexer.slice(name.range())), val)
}),
},
T::Tupl => E::Ctor {
pos: token.start,
ty: Some(self.arena.alloc(expr)),
fields: self.collect_list(T::Comma, T::RParen, |s| (None, s.expr())),
},
T::Dot => E::Field {
target: self.arena.alloc(expr),
field: {
let token = self.expect_advance(T::Ident);
self.lexer.slice(token.range())
},
},
_ => break,
}
}
if matches!(token.kind, T::Return) {
self.expect_advance(T::Semi);
}
if matches!(token.kind, T::Loop | T::LBrace | T::Fn) {
self.pop_scope(frame);
}
expr
}
fn pop_scope(&mut self, frame: usize) {
let mut undeclared_count = frame;
for i in frame..self.idents.len() {
if !self.idents[i].declared {
self.idents.swap(i, undeclared_count);
undeclared_count += 1;
}
}
for id in self.idents.drain(undeclared_count..) {
id.last.set(true);
}
}
fn ptr_unit_expr(&mut self) -> &'a Expr<'a> {
self.arena.alloc(self.unit_expr())
}
fn collect_list<T: Copy>(
&mut self,
delim: TokenKind,
end: TokenKind,
mut f: impl FnMut(&mut Self) -> T,
) -> &'a [T] {
self.collect(|s| {
s.advance_if(end).not().then(|| {
let val = f(s);
s.advance_if(delim);
val
})
})
}
fn collect<T: Copy>(&mut self, mut f: impl FnMut(&mut Self) -> Option<T>) -> &'a [T] {
let vec = std::iter::from_fn(|| f(self)).collect::<Vec<_>>();
self.arena.alloc_slice(&vec)
}
fn advance_if(&mut self, kind: TokenKind) -> bool {
if self.token.kind == kind {
self.next();
true
} else {
false
}
}
fn expect_advance(&mut self, kind: TokenKind) -> Token {
if self.token.kind != kind {
self.report(format_args!(
"expected {:?}, found {:?}",
kind, self.token.kind
));
}
self.next()
}
fn report(&self, msg: impl std::fmt::Display) -> ! {
let (line, col) = self.lexer.line_col(self.token.start);
eprintln!("{}:{}:{} => {}", self.path, line, col, msg);
unreachable!();
}
}
#[derive(Debug, Clone, Copy, PartialEq, Eq)]
pub struct Arg<'a> {
pub name: &'a str,
pub id: Ident,
pub last: Option<&'a Cell<bool>>,
pub ty: Expr<'a>,
}
#[derive(Debug, Clone, Copy, PartialEq, Eq)]
pub enum Expr<'a> {
Break {
pos: Pos,
},
Continue {
pos: Pos,
},
Closure {
pos: Pos,
args: &'a [Arg<'a>],
ret: &'a Self,
body: &'a Self,
},
Call {
func: &'a Self,
args: &'a [Self],
},
Return {
pos: Pos,
val: Option<&'a Self>,
},
Ident {
name: &'a str,
id: Ident,
last: Option<&'a Cell<bool>>,
},
Block {
pos: Pos,
stmts: &'a [Self],
},
Number {
pos: Pos,
value: u64,
},
BinOp {
left: &'a Self,
op: TokenKind,
right: &'a Self,
},
If {
pos: Pos,
cond: &'a Self,
then: &'a Self,
else_: Option<&'a Self>,
},
Loop {
pos: Pos,
body: &'a Self,
},
UnOp {
pos: Pos,
op: TokenKind,
val: &'a Self,
},
Struct {
pos: Pos,
fields: &'a [(&'a str, Self)],
},
Ctor {
pos: Pos,
ty: Option<&'a Self>,
fields: &'a [(Option<&'a str>, Self)],
},
Field {
target: &'a Self,
field: &'a str,
},
Bool {
pos: Pos,
value: bool,
},
Directive {
pos: u32,
name: &'a str,
args: &'a [Self],
},
}
impl<'a> Expr<'a> {
pub fn pos(&self) -> Pos {
match self {
Self::Call { func, .. } => func.pos(),
Self::Ident { id, .. } => ident::pos(*id),
Self::Break { pos }
| Self::Directive { pos, .. }
| Self::Continue { pos }
| Self::Closure { pos, .. }
| Self::Block { pos, .. }
| Self::Number { pos, .. }
| Self::Return { pos, .. }
| Self::If { pos, .. }
| Self::Loop { pos, .. }
| Self::UnOp { pos, .. }
| Self::Struct { pos, .. }
| Self::Ctor { pos, .. }
| Self::Bool { pos, .. } => *pos,
Self::BinOp { left, .. } => left.pos(),
Self::Field { target, .. } => target.pos(),
}
}
}
impl<'a> std::fmt::Display for Expr<'a> {
fn fmt(&self, f: &mut std::fmt::Formatter) -> std::fmt::Result {
thread_local! {
static INDENT: Cell<usize> = Cell::new(0);
}
fn fmt_list<'a, T>(
f: &mut std::fmt::Formatter,
end: &str,
list: &'a [T],
fmt: impl Fn(&T, &mut std::fmt::Formatter) -> std::fmt::Result,
) -> std::fmt::Result {
let first = &mut true;
for expr in list {
if !std::mem::take(first) {
write!(f, ", ")?;
}
fmt(expr, f)?;
}
write!(f, "{end}")
}
match *self {
Self::Field { target, field } => write!(f, "{target}.{field}"),
Self::Directive { name, args, .. } => {
write!(f, "@{name}(")?;
fmt_list(f, ")", args, std::fmt::Display::fmt)
}
Self::Struct { fields, .. } => {
write!(f, "struct {{")?;
fmt_list(f, "}", fields, |(name, val), f| write!(f, "{name}: {val}",))
}
Self::Ctor { ty, fields, .. } => {
let (left, rith) = if fields.iter().any(|(name, _)| name.is_some()) {
('{', '}')
} else {
('(', ')')
};
if let Some(ty) = ty {
write!(f, "{ty}")?;
}
write!(f, ".{left}")?;
let first = &mut true;
for (name, val) in fields {
if !std::mem::take(first) {
write!(f, ", ")?;
}
if let Some(name) = name {
write!(f, "{name}: ")?;
}
write!(f, "{val}")?;
}
write!(f, "{rith}")
}
Self::UnOp { op, val, .. } => write!(f, "{op}{val}"),
Self::Break { .. } => write!(f, "break;"),
Self::Continue { .. } => write!(f, "continue;"),
Self::If {
cond, then, else_, ..
} => {
write!(f, "if {cond} {then}")?;
if let Some(else_) = else_ {
write!(f, " else {else_}")?;
}
Ok(())
}
Self::Loop { body, .. } => write!(f, "loop {body}"),
Self::Closure {
ret, body, args, ..
} => {
write!(f, "fn(")?;
fmt_list(f, "", args, |arg, f| write!(f, "{}: {}", arg.name, arg.ty))?;
write!(f, "): {ret} {body}")
}
Self::Call { func, args } => {
write!(f, "{func}(")?;
fmt_list(f, ")", args, std::fmt::Display::fmt)
}
Self::Return { val: Some(val), .. } => write!(f, "return {val};"),
Self::Return { val: None, .. } => write!(f, "return;"),
Self::Ident { name, .. } => write!(f, "{name}"),
Self::Block { stmts, .. } => {
writeln!(f, "{{")?;
INDENT.with(|i| i.set(i.get() + 1));
let res = (|| {
for stmt in stmts {
for _ in 0..INDENT.with(|i| i.get()) {
write!(f, " ")?;
}
writeln!(f, "{stmt}")?;
}
Ok(())
})();
INDENT.with(|i| i.set(i.get() - 1));
write!(f, "}}")?;
res
}
Self::Number { value, .. } => write!(f, "{value}"),
Self::Bool { value, .. } => write!(f, "{value}"),
Self::BinOp { left, right, op } => {
let display_branch = |f: &mut std::fmt::Formatter, expr: &Self| {
if let Self::BinOp { op: lop, .. } = expr
&& op.precedence() > lop.precedence()
{
write!(f, "({expr})")
} else {
write!(f, "{expr}")
}
};
display_branch(f, left)?;
write!(f, " {op} ")?;
display_branch(f, right)
}
}
}
}
#[derive(Default)]
pub struct Arena<'a> {
chunk: Cell<ArenaChunk>,
ph: std::marker::PhantomData<&'a ()>,
}
impl<'a> Arena<'a> {
pub fn alloc_str(&self, token: &str) -> &'a str {
let ptr = self.alloc_slice(token.as_bytes());
unsafe { std::str::from_utf8_unchecked_mut(ptr) }
}
pub fn alloc<T>(&self, value: T) -> &'a mut T {
let layout = std::alloc::Layout::new::<T>();
let ptr = self.alloc_low(layout);
unsafe { ptr.cast::<T>().write(value) };
unsafe { ptr.cast::<T>().as_mut() }
}
pub fn alloc_slice<T: Copy>(&self, slice: &[T]) -> &'a mut [T] {
let layout = std::alloc::Layout::array::<T>(slice.len()).unwrap();
let ptr = self.alloc_low(layout);
unsafe {
ptr.as_ptr()
.cast::<T>()
.copy_from_nonoverlapping(slice.as_ptr(), slice.len())
};
unsafe { std::slice::from_raw_parts_mut(ptr.as_ptr() as _, slice.len()) }
}
pub fn clear(&mut self) {
let chunk = self.chunk.get_mut();
if chunk.base.is_null() {
return;
}
loop {
let prev = ArenaChunk::prev(chunk.base);
if prev.is_null() {
break;
}
chunk.base = prev;
}
chunk.end = unsafe { chunk.base.add(ArenaChunk::PREV_OFFSET) };
}
fn with_chunk<R>(&self, f: impl FnOnce(&mut ArenaChunk) -> R) -> R {
let mut chunk = self.chunk.get();
let r = f(&mut chunk);
self.chunk.set(chunk);
r
}
fn alloc_low(&self, layout: std::alloc::Layout) -> NonNull<u8> {
assert!(layout.align() <= ArenaChunk::ALIGN);
assert!(layout.size() <= ArenaChunk::CHUNK_SIZE);
self.with_chunk(|chunk| {
if let Some(ptr) = chunk.alloc(layout) {
return ptr;
}
if let Some(prev) = ArenaChunk::reset(ArenaChunk::prev(chunk.base)) {
*chunk = prev;
} else {
*chunk = ArenaChunk::new(chunk.base);
}
chunk.alloc(layout).unwrap()
})
}
}
impl<'a> Drop for Arena<'a> {
fn drop(&mut self) {
use ArenaChunk as AC;
let mut current = self.chunk.get().base;
let mut prev = AC::prev(current);
while !prev.is_null() {
let next = AC::next(prev);
unsafe { std::alloc::dealloc(prev, AC::LAYOUT) };
prev = next;
}
while !current.is_null() {
let next = AC::next(current);
unsafe { std::alloc::dealloc(current, AC::LAYOUT) };
current = next;
}
}
}
#[derive(Clone, Copy)]
struct ArenaChunk {
base: *mut u8,
end: *mut u8,
}
impl Default for ArenaChunk {
fn default() -> Self {
Self {
base: std::ptr::null_mut(),
end: std::ptr::null_mut(),
}
}
}
impl ArenaChunk {
const CHUNK_SIZE: usize = 1 << 16;
const ALIGN: usize = std::mem::align_of::<Self>();
const NEXT_OFFSET: usize = Self::CHUNK_SIZE - std::mem::size_of::<*mut u8>();
const PREV_OFFSET: usize = Self::NEXT_OFFSET - std::mem::size_of::<*mut u8>();
const LAYOUT: std::alloc::Layout =
unsafe { std::alloc::Layout::from_size_align_unchecked(Self::CHUNK_SIZE, Self::ALIGN) };
fn new(next: *mut u8) -> Self {
let base = unsafe { std::alloc::alloc(Self::LAYOUT) };
let end = unsafe { base.add(Self::PREV_OFFSET) };
if !next.is_null() {
Self::set_prev(next, base);
}
Self::set_next(base, next);
Self::set_prev(base, std::ptr::null_mut());
Self { base, end }
}
fn set_next(curr: *mut u8, next: *mut u8) {
unsafe { std::ptr::write(curr.add(Self::NEXT_OFFSET) as *mut _, next) };
}
fn set_prev(curr: *mut u8, prev: *mut u8) {
unsafe { std::ptr::write(curr.add(Self::PREV_OFFSET) as *mut _, prev) };
}
fn next(curr: *mut u8) -> *mut u8 {
unsafe { std::ptr::read(curr.add(Self::NEXT_OFFSET) as *mut _) }
}
fn prev(curr: *mut u8) -> *mut u8 {
if curr.is_null() {
return std::ptr::null_mut();
}
unsafe { std::ptr::read(curr.add(Self::PREV_OFFSET) as *mut _) }
}
fn reset(prev: *mut u8) -> Option<Self> {
if prev.is_null() {
return None;
}
Some(Self {
base: prev,
end: unsafe { prev.add(Self::CHUNK_SIZE) },
})
}
fn alloc(&mut self, layout: std::alloc::Layout) -> Option<NonNull<u8>> {
let padding = self.end as usize - (self.end as usize & !(layout.align() - 1));
let size = layout.size() + padding;
if size > self.end as usize - self.base as usize {
return None;
}
unsafe { self.end = self.end.sub(size) };
unsafe { Some(NonNull::new_unchecked(self.end)) }
}
}
#[cfg(test)]
mod tests {
fn parse(input: &'static str, output: &mut String) {
use std::fmt::Write;
let mut arena = super::Arena::default();
let mut parser = super::Parser::new(&arena);
for expr in parser.file(input, "test") {
writeln!(output, "{}", expr).unwrap();
}
arena.clear();
}
crate::run_tests! { parse:
example => include_str!("../examples/main_fn.hb");
arithmetic => include_str!("../examples/arithmetic.hb");
}
}

View File

@ -1,56 +0,0 @@
#![cfg(test)]
pub fn run_test(name: &'static str, input: &'static str, test: fn(&'static str, &mut String)) {
use std::{io::Write, path::PathBuf};
let filter = std::env::var("PT_FILTER").unwrap_or_default();
if !filter.is_empty() && !name.contains(&filter) {
return;
}
let mut output = String::new();
test(input, &mut output);
let mut root = PathBuf::from(std::env::var("PT_TEST_ROOT").unwrap_or("tests".to_string()));
root.push(
name.replace("::", "_")
.replace(concat!(env!("CARGO_PKG_NAME"), "_"), ""),
);
root.set_extension("txt");
let expected = std::fs::read_to_string(&root).unwrap_or_default();
if output == expected {
return;
}
if std::env::var("PT_UPDATE").is_ok() {
std::fs::write(&root, output).unwrap();
return;
}
if !root.exists() {
std::fs::create_dir_all(root.parent().unwrap()).unwrap();
std::fs::write(&root, vec![]).unwrap();
}
let mut proc = std::process::Command::new("diff")
.arg("-u")
.arg("--color")
.arg(&root)
.arg("-")
.stdin(std::process::Stdio::piped())
.stdout(std::process::Stdio::inherit())
.spawn()
.unwrap();
proc.stdin
.as_mut()
.unwrap()
.write_all(output.as_bytes())
.unwrap();
proc.wait().unwrap();
panic!();
}

View File

View File

@ -1,3 +0,0 @@
code size: 209
ret: 1
status: Ok(())

View File

@ -1,3 +0,0 @@
code size: 527
ret: 512
status: Ok(())

View File

@ -1,4 +0,0 @@
ev: Ecall
code size: 217
ret: 0
status: Ok(())

View File

@ -1,3 +0,0 @@
code size: 96
ret: 1
status: Ok(())

View File

@ -1,3 +0,0 @@
code size: 997
ret: 0
status: Ok(())

View File

@ -1,3 +0,0 @@
code size: 388
ret: 33
status: Ok(())

View File

@ -1,3 +0,0 @@
code size: 347
ret: 55
status: Ok(())

View File

@ -1,3 +0,0 @@
code size: 475
ret: 55
status: Ok(())

View File

@ -1,3 +0,0 @@
code size: 486
ret: 0
status: Ok(())

View File

@ -1,3 +0,0 @@
code size: 800
ret: 10
status: Ok(())

View File

@ -1,3 +0,0 @@
code size: 530
ret: 3
status: Ok(())

View File

@ -1,3 +0,0 @@
code size: 213
ret: 0
status: Ok(())

View File

@ -1,31 +0,0 @@
Ident "main"
Decl ":="
Fn "fn"
LParen "("
RParen ")"
Colon ":"
Ident "int"
LBrace "{"
Return "return"
Number "10"
Minus "-"
Number "20"
FSlash "/"
Number "2"
Plus "+"
Number "4"
Star "*"
LParen "("
Number "2"
Plus "+"
Number "2"
RParen ")"
Minus "-"
Number "4"
Star "*"
Number "4"
Plus "+"
Number "1"
Semi ";"
RBrace "}"
Eof ""

View File

@ -1 +0,0 @@
Eof ""

View File

@ -1,13 +0,0 @@
Ident "main"
Decl ":="
Fn "fn"
LParen "("
RParen ")"
Colon ":"
Ident "int"
LBrace "{"
Return "return"
Number "1"
Semi ";"
RBrace "}"
Eof ""

View File

@ -1 +0,0 @@
Eof ""

View File

@ -1,3 +0,0 @@
main := fn(): int {
return 10 - 20 / 2 + 4 * (2 + 2) - 4 * 4 + 1;
}

View File

@ -1,3 +0,0 @@
main := fn(): int {
return 1;
}

View File

@ -3,10 +3,14 @@ name = "hbvm"
version = "0.1.0"
edition = "2021"
[features]
default = ["alloc"]
alloc = []
nightly = []
[profile.release]
lto = true
[dependencies]
hbbytecode = { path = "../hbbytecode" }
delegate = "0.9"
derive_more = "0.99"
hashbrown = "0.13"
hbbytecode.path = "../hbbytecode"
log = "0.4"
paste = "1.0"
static_assertions = "1.0"

Binary file not shown.

Binary file not shown.

Binary file not shown.

Binary file not shown.

Binary file not shown.

View File

@ -1,5 +0,0 @@
target
artifacts
corpus
coverage
Cargo.lock

View File

@ -1,30 +0,0 @@
[package]
name = "hbvm-fuzz"
version = "0.0.0"
publish = false
edition = "2021"
[package.metadata]
cargo-fuzz = true
[dependencies]
libfuzzer-sys = "0.4"
[dependencies.hbvm]
path = ".."
[dependencies.hbbytecode]
path = "../../hbbytecode"
# Prevent this from interfering with workspaces
[workspace]
members = ["."]
[profile.release]
debug = 1
[[bin]]
name = "vm"
path = "fuzz_targets/vm.rs"
test = false
doc = false

View File

@ -1,82 +0,0 @@
#![no_main]
use {
hbvm::{
mem::{
softpaging::{
paging::{PageTable, Permission},
HandlePageFault, PageSize, SoftPagedMem,
},
Address, MemoryAccessReason,
},
Vm,
},
libfuzzer_sys::fuzz_target,
};
fuzz_target!(|data: &[u8]| {
let mut vm = unsafe {
Vm::<_, 16384>::new(
SoftPagedMem::<_, true> {
pf_handler: TestTrapHandler,
program: data,
root_pt: Box::into_raw(Default::default()),
icache: Default::default(),
},
Address::new(4),
)
};
// Alloc and map some memory
let pages = [
alloc_and_map(&mut vm.memory, 0),
alloc_and_map(&mut vm.memory, 4096),
];
// Run VM
let _ = vm.run();
// Unmap and dealloc the memory
for (i, page) in pages.into_iter().enumerate() {
unmap_and_dealloc(&mut vm.memory, page, i as u64 * 4096);
}
let _ = unsafe { Box::from_raw(vm.memory.root_pt) };
});
fn alloc_and_map(memory: &mut SoftPagedMem<TestTrapHandler>, at: u64) -> *mut u8 {
let ptr = Box::into_raw(Box::<Page>::default()).cast();
unsafe {
memory
.map(ptr, Address::new(at), Permission::Write, PageSize::Size4K)
.unwrap()
};
ptr
}
fn unmap_and_dealloc(memory: &mut SoftPagedMem<TestTrapHandler>, ptr: *mut u8, from: u64) {
memory.unmap(Address::new(from)).unwrap();
let _ = unsafe { Box::from_raw(ptr.cast::<Page>()) };
}
#[repr(align(4096))]
struct Page([u8; 4096]);
impl Default for Page {
fn default() -> Self {
unsafe { std::mem::MaybeUninit::zeroed().assume_init() }
}
}
struct TestTrapHandler;
impl HandlePageFault for TestTrapHandler {
fn page_fault(
&mut self,
_: MemoryAccessReason,
_: &mut PageTable,
_: Address,
_: PageSize,
_: *mut u8,
) -> bool {
false
}
}

View File

@ -1,141 +0,0 @@
//! Block memory copier state machine
use {
super::{mem::MemoryAccessReason, Memory, VmRunError},
crate::mem::Address,
core::{mem::MaybeUninit, task::Poll},
};
/// Buffer size (defaults to 4 KiB, a smallest page size on most platforms)
const BUF_SIZE: usize = 4096;
/// Buffer of possibly uninitialised bytes, aligned to [`BUF_SIZE`]
#[repr(align(4096))]
struct AlignedBuf([MaybeUninit<u8>; BUF_SIZE]);
/// State for block memory copy
pub struct BlockCopier {
/// Source address
src: Address,
/// Destination address
dst: Address,
/// How many buffer sizes to copy?
n_buffers: usize,
/// …and what remainds after?
rem: usize,
}
impl BlockCopier {
/// Construct a new one
#[inline]
pub fn new(src: Address, dst: Address, count: usize) -> Self {
Self {
src,
dst,
n_buffers: count / BUF_SIZE,
rem: count % BUF_SIZE,
}
}
/// Copy one block
///
/// # Safety
/// - Same as for [`Memory::load`] and [`Memory::store`]
pub unsafe fn poll(&mut self, memory: &mut impl Memory) -> Poll<Result<(), BlkCopyError>> {
// Safety: Assuming uninit of array of MaybeUninit is sound
let mut buf = AlignedBuf(unsafe { MaybeUninit::uninit().assume_init() });
// We have at least one buffer size to copy
if self.n_buffers != 0 {
if let Err(e) = unsafe {
act(
memory,
self.src,
self.dst,
buf.0.as_mut_ptr().cast(),
BUF_SIZE,
)
} {
return Poll::Ready(Err(e));
}
// Bump source and destination address
self.src += BUF_SIZE;
self.dst += BUF_SIZE;
self.n_buffers -= 1;
return if self.n_buffers + self.rem == 0 {
// If there is nothing left, we are done
Poll::Ready(Ok(()))
} else {
// Otherwise let's advice to run it again
Poll::Pending
};
}
if self.rem != 0 {
if let Err(e) = unsafe {
act(
memory,
self.src,
self.dst,
buf.0.as_mut_ptr().cast(),
self.rem,
)
} {
return Poll::Ready(Err(e));
}
}
Poll::Ready(Ok(()))
}
}
/// Load to buffer and store from buffer
#[inline]
unsafe fn act(
memory: &mut impl Memory,
src: Address,
dst: Address,
buf: *mut u8,
count: usize,
) -> Result<(), BlkCopyError> {
unsafe {
// Load to buffer
memory
.load(src, buf, count)
.map_err(|super::mem::LoadError(addr)| BlkCopyError {
access_reason: MemoryAccessReason::Load,
addr,
})?;
// Store from buffer
memory
.store(dst, buf, count)
.map_err(|super::mem::StoreError(addr)| BlkCopyError {
access_reason: MemoryAccessReason::Store,
addr,
})?;
}
Ok(())
}
/// Error occured when copying a block of memory
#[derive(Clone, Copy, Debug, PartialEq, Eq)]
pub struct BlkCopyError {
/// Kind of access
access_reason: MemoryAccessReason,
/// VM Address
addr: Address,
}
impl From<BlkCopyError> for VmRunError {
fn from(value: BlkCopyError) -> Self {
match value.access_reason {
MemoryAccessReason::Load => Self::LoadAccessEx(value.addr),
MemoryAccessReason::Store => Self::StoreAccessEx(value.addr),
}
}
}

View File

@ -1,49 +0,0 @@
use {core::arch::asm, hbbytecode::RoundingMode};
macro_rules! fnsdef {
{$(
$(#[$attr:meta])*
$vis:vis fn $name:ident[$inreg:ident -> $outreg:ident]($from:ident -> $to:ident): $ins:literal;
)*} => {$(
$(#[$attr])*
$vis fn $name(val: $from, mode: RoundingMode) -> $to {
let result: $to;
unsafe {
if mode == RoundingMode::NearestEven {
return;
}
let fpcr: u64;
unsafe { asm!("mrs {}, fpcr", out(reg) fpcr) };
let fpcr_new = fpcr & !(0b11 << 22)
| (match mode {
RoundingMode::NearestEven => 0b00,
RoundingMode::Truncate => 0b11,
RoundingMode::Up => 0b01,
RoundingMode::Down => 0b10,
}) << 22;
unsafe { asm!("msr fpcr, {}", in(reg) fpcr_new) };
asm!(
$ins,
out($outreg) result,
in($inreg) val,
);
unsafe { asm!("msr fpcr, {}", in(reg) fpcr) };
}
result
}
)*};
}
fnsdef! {
/// Convert [`f64`] to [`f32`] with chosen rounding mode
pub fn conv64to32[vreg -> vreg](f64 -> f32): "fcvt {:s}, {:d}";
/// Convert [`f32`] to [`i64`] with chosen rounding mode
pub fn f32toint[vreg -> reg](f32 -> i64): "fcvtzs {}, {:s}";
/// Convert [`f64`] to [`i64`] with chosen rounding mode
pub fn f64toint[vreg -> reg](f64 -> i64): "fcvtzs {}, {:d}";
}

View File

@ -1,31 +0,0 @@
macro_rules! arch_specific {
{
$({$($cfg:tt)*} : $mod:ident;)*
} => {
$(
#[cfg($($cfg)*)]
mod $mod;
#[cfg($($cfg)*)]
pub use $mod::*;
#[cfg($($cfg)*)]
pub const FL_ARCH_SPECIFIC_SUPPORTED: bool = true;
)*
#[cfg(not(any($($($cfg)*),*)))]
mod unsupported;
#[cfg(not(any($($($cfg)*),*)))]
pub use unsupported::*;
#[cfg(not(any($($($cfg)*),*)))]
pub const FL_ARCH_SPECIFIC_SUPPORTED: bool = false;
};
}
arch_specific! {
{target_arch = "x86_64" }: x86_64;
{target_arch = "riscv64"}: riscv64;
{target_arch = "aarch64"}: aarch64;
}

View File

@ -1,59 +0,0 @@
use {core::arch::asm, hbbytecode::RoundingMode};
macro_rules! roundm_op_litmode_internal {
($ins:literal, $in:expr, $out:expr => $outy:ident, $mode:literal $(,)?) => {
asm!(
concat!($ins, " {}, {}, ", $mode),
out($outy) $out,
in(freg) $in,
)
};
}
macro_rules! gen_roundm_op_litmode {
[$($ty:ident => $reg:ident),* $(,)?] => {
macro_rules! roundm_op_litmode {
$(
($ins:literal, $in:expr, $out:expr => $ty, $mode:literal) => {
roundm_op_litmode_internal!($ins, $in, $out => $reg, $mode)
};
)*
}
};
}
gen_roundm_op_litmode![
f32 => freg,
f64 => freg,
i64 => reg,
];
macro_rules! fnsdef {
{$(
$(#[$attr:meta])*
$vis:vis fn $name:ident($from:ident -> $to:ident): $ins:literal;
)*} => {$(
$(#[$attr])*
$vis fn $name(val: $from, mode: RoundingMode) -> $to {
let result: $to;
unsafe {
match mode {
RoundingMode::NearestEven => roundm_op_litmode!($ins, val, result => $to, "rne"),
RoundingMode::Truncate => roundm_op_litmode!($ins, val, result => $to, "rtz"),
RoundingMode::Up => roundm_op_litmode!($ins, val, result => $to, "rup"),
RoundingMode::Down => roundm_op_litmode!($ins, val, result => $to, "rdn"),
}
}
result
}
)*};
}
fnsdef! {
/// Convert [`f64`] to [`f32`] with chosen rounding mode
pub fn conv64to32(f64 -> f32): "fcvt.s.d";
/// Convert [`f32`] to [`i64`] with chosen rounding mode
pub fn f32toint(f32 -> i64): "fcvt.l.s";
/// Convert [`f64`] to [`i64`] with chosen rounding mode
pub fn f64toint(f64 -> i64): "fcvt.l.d";
}

View File

@ -1,16 +0,0 @@
use hbbytecode::RoundingMode;
#[inline(always)]
pub fn conv64to32(_: f64, _: RoundingMode) -> f32 {
f32::NAN
}
#[inline(always)]
pub fn f32toint(_: f32, _: RoundingMode) -> i64 {
i64::MAX
}
#[inline(always)]
pub fn f64toint(_: f64, _: RoundingMode) -> i64 {
i64::MAX
}

View File

@ -1,64 +0,0 @@
use {
core::arch::{asm, x86_64 as arin},
hbbytecode::RoundingMode,
};
macro_rules! gen_op {
[$($ty:ident => $reg:ident),* $(,)?] => {
macro_rules! op {
$(
($ins:literal, $in:expr, $out:expr => $ty) => {
asm!(concat!($ins, " {}, {}"), out($reg) $out, in(xmm_reg) $in)
};
)*
}
};
}
gen_op![
f32 => xmm_reg,
f64 => xmm_reg,
i64 => reg,
];
macro_rules! fnsdef {
{$(
$(#[$attr:meta])*
$vis:vis fn $name:ident($from:ident -> $to:ident): $ins:literal;
)*} => {$(
$(#[$attr])*
$vis fn $name(val: $from, mode: RoundingMode) -> $to {
let result: $to;
unsafe {
let mut mxcsr = 0_u32;
'a: {
asm!("stmxcsr [{}]", in(reg) &mut mxcsr);
asm!(
"ldmxcsr [{}]",
in(reg) &(mxcsr & !arin::_MM_ROUND_MASK | match mode {
RoundingMode::NearestEven => break 'a,
RoundingMode::Truncate => arin::_MM_ROUND_TOWARD_ZERO,
RoundingMode::Up => arin::_MM_ROUND_UP,
RoundingMode::Down => arin::_MM_ROUND_DOWN,
})
);
}
op!($ins, val, result => $to);
// Set MXCSR to original value
asm!("ldmxcsr [{}]", in(reg) &mxcsr);
}
result
}
)*};
}
fnsdef! {
/// Convert [`f64`] to [`f32`] with chosen rounding mode
pub fn conv64to32(f64 -> f32): "cvtsd2ss";
/// Convert [`f32`] to [`i64`] with chosen rounding mode
pub fn f32toint(f32 -> i64): "cvttss2si";
/// Convert [`f64`] to [`i64`] with chosen rounding mode
pub fn f64toint(f64 -> i64): "cvttsd2si";
}

View File

@ -1,143 +1,7 @@
//! HoleyBytes Virtual Machine
//!
//! # Alloc feature
//! - Enabled by default
//! - Provides mapping / unmapping, as well as [`Default`] and [`Drop`]
//! implementations for soft-paged memory implementation
// # General safety notice:
// - Validation has to assure there is 256 registers (r0 - r255)
// - Instructions have to be valid as specified (values and sizes)
// - Mapped pages should be at least 4 KiB
#![doc = include_str!("../README.md")]
#![no_std]
#![cfg_attr(feature = "nightly", feature(fn_align))]
#![deny(unsafe_op_in_unsafe_fn)]
#[cfg(feature = "alloc")]
extern crate alloc;
pub mod mem;
pub mod value;
mod bmc;
mod float;
mod utils;
mod vmrun;
pub use float::FL_ARCH_SPECIFIC_SUPPORTED;
use {
bmc::BlockCopier,
mem::{Address, Memory},
value::{Value, ValueVariant},
};
/// HoleyBytes Virtual Machine
pub struct Vm<Mem, const TIMER_QUOTIENT: usize> {
/// Holds 256 registers
///
/// Writing to register 0 is considered undefined behaviour
/// in terms of HoleyBytes program execution
pub registers: [Value; 256],
/// Memory implementation
pub memory: Mem,
/// Program counter
pub pc: Address,
/// Program timer
timer: usize,
/// Saved block copier
copier: Option<BlockCopier>,
}
impl<Mem, const TIMER_QUOTIENT: usize> Vm<Mem, TIMER_QUOTIENT>
where
Mem: Memory,
{
/// Create a new VM with program and trap handler
///
/// # Safety
/// Program code has to be validated
pub unsafe fn new(memory: Mem, entry: Address) -> Self {
Self {
registers: [Value::from(0_u64); 256],
memory,
pc: entry,
timer: 0,
copier: None,
}
}
/// Read register
#[inline(always)]
pub fn read_reg(&self, n: u8) -> Value {
unsafe { *self.registers.get_unchecked(n as usize) }
}
/// Write a register.
/// Writing to register 0 is no-op.
#[inline(always)]
pub fn write_reg<T: ValueVariant>(&mut self, n: u8, value: T) {
if n != 0 {
unsafe {
core::ptr::copy_nonoverlapping(
(&value as *const T).cast::<u8>(),
self.registers.as_mut_ptr().add(n.into()).cast::<u8>(),
core::mem::size_of::<T>(),
);
};
}
}
}
/// Virtual machine halt error
#[derive(Copy, Clone, Debug, PartialEq, Eq)]
#[repr(u8)]
pub enum VmRunError {
/// Tried to execute invalid instruction
InvalidOpcode(u8),
/// Unhandled load access exception
LoadAccessEx(Address),
/// Unhandled instruction load access exception
ProgramFetchLoadEx(Address),
/// Unhandled store access exception
StoreAccessEx(Address),
/// Register out-of-bounds access
RegOutOfBounds,
/// Address out-of-bounds
AddrOutOfBounds,
/// Reached unreachable code
Unreachable,
/// Invalid operand
InvalidOperand,
/// Unimplemented feature
Unimplemented,
}
/// Virtual machine halt ok
#[derive(Copy, Clone, Debug, PartialEq, Eq)]
pub enum VmRunOk {
/// Program has eached its end
End,
/// Program was interrupted by a timer
Timer,
/// Environment call
Ecall,
/// Breakpoint
Breakpoint,
}
pub mod validate;
pub mod vm;

59
hbvm/src/main.rs Normal file
View File

@ -0,0 +1,59 @@
use hbvm::vm::{
mem::{Memory, MemoryAccessReason, PageSize},
trap::HandleTrap,
value::Value,
};
use {
hbvm::{validate::validate, vm::Vm},
std::io::{stdin, Read},
};
fn main() -> Result<(), Box<dyn std::error::Error>> {
let mut prog = vec![];
stdin().read_to_end(&mut prog)?;
if let Err(e) = validate(&prog) {
eprintln!("Program validation error: {e:?}");
return Ok(());
} else {
unsafe {
let mut vm = Vm::<_, 0>::new_unchecked(&prog, TestTrapHandler);
vm.memory.insert_test_page();
println!("Program interrupt: {:?}", vm.run());
println!("{:?}", vm.registers);
}
}
Ok(())
}
pub fn time() -> u32 {
9
}
struct TestTrapHandler;
impl HandleTrap for TestTrapHandler {
fn page_fault(
&mut self,
_: MemoryAccessReason,
_: &mut Memory,
_: u64,
_: PageSize,
_: *mut u8,
) -> bool {
false
}
fn invalid_op(&mut self, _: &mut [Value; 256], _: &mut usize, _: &mut Memory, _: u8) -> bool
where
Self: Sized,
{
false
}
fn ecall(&mut self, _: &mut [Value; 256], _: &mut usize, _: &mut Memory)
where
Self: Sized,
{
}
}

View File

@ -1,137 +0,0 @@
//! Virtual(?) memory address
use {
crate::utils::impl_display,
core::{fmt::Debug, ops},
};
/// Memory address
#[derive(Clone, Copy, PartialEq, Eq, PartialOrd, Ord)]
pub struct Address(u64);
impl Address {
/// A null address
pub const NULL: Self = Self(0);
/// Saturating integer addition. Computes self + rhs, saturating at the numeric bounds instead of overflowing.
#[inline]
pub fn saturating_add<T: AddressOp>(self, rhs: T) -> Self {
Self(self.0.saturating_add(rhs.cast_u64()))
}
/// Saturating integer subtraction. Computes self - rhs, saturating at the numeric bounds instead of overflowing.
#[inline]
pub fn saturating_sub<T: AddressOp>(self, rhs: T) -> Self {
Self(self.0.saturating_sub(rhs.cast_u64()))
}
/// Wrapping integer addition. Computes self + rhs, wrapping the numeric bounds.
#[inline]
pub fn wrapping_add<T: AddressOp>(self, rhs: T) -> Self {
Self(self.0.wrapping_add(rhs.cast_u64()))
}
/// Wrapping integer subtraction. Computes self + rhs, wrapping the numeric bounds.
#[inline]
pub fn wrapping_sub<T: AddressOp>(self, rhs: T) -> Self {
Self(self.0.wrapping_sub(rhs.cast_u64()))
}
/// Cast or if smaller, truncate to [`usize`]
pub fn truncate_usize(self) -> usize {
self.0 as _
}
/// Get inner value
#[inline(always)]
pub fn get(self) -> u64 {
self.0
}
/// Get ptr to the next instruction
#[inline(always)]
pub fn next<A>(self) -> u64 {
self.0.wrapping_add(core::mem::size_of::<A>() as u64 + 1)
}
/// Construct new address
#[inline(always)]
pub fn new(val: u64) -> Self {
Self(val)
}
/// Do something with inner value
#[inline(always)]
pub fn map(self, f: impl Fn(u64) -> u64) -> Self {
Self(f(self.0))
}
}
impl_display!(for Address =>
|Address(a)| "{a:0x}"
);
impl<T: AddressOp> ops::Add<T> for Address {
type Output = Self;
#[inline]
fn add(self, rhs: T) -> Self::Output {
Self(self.0.wrapping_add(rhs.cast_u64()))
}
}
impl<T: AddressOp> ops::Sub<T> for Address {
type Output = Self;
#[inline]
fn sub(self, rhs: T) -> Self::Output {
Self(self.0.wrapping_sub(rhs.cast_u64()))
}
}
impl<T: AddressOp> ops::AddAssign<T> for Address {
fn add_assign(&mut self, rhs: T) {
self.0 = self.0.wrapping_add(rhs.cast_u64())
}
}
impl<T: AddressOp> ops::SubAssign<T> for Address {
fn sub_assign(&mut self, rhs: T) {
self.0 = self.0.wrapping_sub(rhs.cast_u64())
}
}
impl From<Address> for u64 {
#[inline(always)]
fn from(value: Address) -> Self {
value.0
}
}
impl Debug for Address {
fn fmt(&self, f: &mut core::fmt::Formatter<'_>) -> core::fmt::Result {
write!(f, "[{:0x}]", self.0)
}
}
/// Can perform address operations with
pub trait AddressOp {
/// Cast to u64, truncating or extending
fn cast_u64(self) -> u64;
}
macro_rules! impl_address_ops_u(($($ty:ty),* $(,)?) => {
$(impl AddressOp for $ty {
#[inline(always)]
fn cast_u64(self) -> u64 { self as _ }
})*
});
macro_rules! impl_address_ops_i(($($ty:ty),* $(,)?) => {
$(impl AddressOp for $ty {
#[inline(always)]
fn cast_u64(self) -> u64 { self as i64 as u64 }
})*
});
impl_address_ops_u!(u8, u16, u32, u64, usize);
impl_address_ops_i!(i8, i16, i32, i64, isize);

View File

@ -1,80 +0,0 @@
//! Memory implementations
pub mod softpaging;
pub(crate) mod addr;
pub use addr::Address;
use crate::utils::impl_display;
/// Load-store memory access
pub trait Memory {
/// Load data from memory on address
///
/// # Safety
/// - Shall not overrun the buffer
unsafe fn load(
&mut self,
addr: Address,
target: *mut u8,
count: usize,
) -> Result<(), LoadError>;
/// Store data to memory on address
///
/// # Safety
/// - Shall not overrun the buffer
unsafe fn store(
&mut self,
addr: Address,
source: *const u8,
count: usize,
) -> Result<(), StoreError>;
/// Read from program memory to execute
///
/// # Safety
/// - Data read have to be valid
unsafe fn prog_read<T: Copy>(&mut self, addr: Address) -> T;
}
/// Unhandled load access trap
#[derive(Clone, Copy, Debug, PartialEq, Eq)]
pub struct LoadError(pub Address);
impl_display!(for LoadError =>
|LoadError(a)| "Load access error at address {a}",
);
/// Unhandled store access trap
#[derive(Clone, Copy, Debug, PartialEq, Eq)]
pub struct StoreError(pub Address);
impl_display!(for StoreError =>
|StoreError(a)| "Load access error at address {a}",
);
/// Reason to access memory
#[derive(Clone, Copy, Debug, PartialEq, Eq)]
pub enum MemoryAccessReason {
/// Memory was accessed for load (read)
Load,
/// Memory was accessed for store (write)
Store,
}
impl_display!(for MemoryAccessReason => match {
Self::Load => const "Load";
Self::Store => const "Store";
});
impl From<LoadError> for crate::VmRunError {
fn from(value: LoadError) -> Self {
Self::LoadAccessEx(value.0)
}
}
impl From<StoreError> for crate::VmRunError {
fn from(value: StoreError) -> Self {
Self::StoreAccessEx(value.0)
}
}

View File

@ -1,111 +0,0 @@
//! Program instruction cache
use crate::mem::Address;
use {
super::{lookup::AddrPageLookuper, paging::PageTable, PageSize},
core::{
mem::{size_of, MaybeUninit},
ptr::{copy_nonoverlapping, NonNull},
},
};
/// Instruction cache
#[derive(Clone, Debug)]
pub struct ICache {
/// Current page address base
base: Address,
/// Curent page pointer
data: Option<NonNull<u8>>,
/// Current page size
size: PageSize,
/// Address mask
mask: u64,
}
impl Default for ICache {
fn default() -> Self {
Self {
base: Address::NULL,
data: Default::default(),
size: PageSize::Size4K,
mask: Default::default(),
}
}
}
impl ICache {
/// Fetch instruction from cache
///
/// # Safety
/// `T` should be valid to read from instruction memory
pub(super) unsafe fn fetch<T>(
&mut self,
addr: Address,
root_pt: *const PageTable,
) -> Option<T> {
let mut ret = MaybeUninit::<T>::uninit();
let pbase = self
.data
.or_else(|| unsafe { self.fetch_page(self.base + self.size, root_pt) })?;
// Get address base
let base = addr.map(|x| x & self.mask);
// Base not matching, fetch anew
if base != self.base {
unsafe { self.fetch_page(base, root_pt) }?;
};
let offset = addr.get() & !self.mask;
let requ_size = size_of::<T>();
// Page overflow
let rem = (offset as usize)
.saturating_add(requ_size)
.saturating_sub(self.size as _);
let first_copy = requ_size.saturating_sub(rem);
// Copy non-overflowing part
unsafe { copy_nonoverlapping(pbase.as_ptr(), ret.as_mut_ptr().cast::<u8>(), first_copy) };
// Copy overflow
if rem != 0 {
let pbase = unsafe { self.fetch_page(self.base + self.size, root_pt) }?;
// Unlikely, unsupported scenario
if rem > self.size as _ {
return None;
}
unsafe {
copy_nonoverlapping(
pbase.as_ptr(),
ret.as_mut_ptr().cast::<u8>().add(first_copy),
rem,
)
};
}
Some(unsafe { ret.assume_init() })
}
/// Fetch a page
unsafe fn fetch_page(&mut self, addr: Address, pt: *const PageTable) -> Option<NonNull<u8>> {
let res = AddrPageLookuper::new(addr, 0, pt).next()?.ok()?;
if !super::perm_check::executable(res.perm) {
return None;
}
(self.size, self.mask) = match res.size {
4096 => (PageSize::Size4K, !((1 << 8) - 1)),
2097152 => (PageSize::Size2M, !((1 << (8 * 2)) - 1)),
1073741824 => (PageSize::Size1G, !((1 << (8 * 3)) - 1)),
_ => return None,
};
self.data = Some(NonNull::new(res.ptr)?);
self.base = addr.map(|x| x & self.mask);
self.data
}
}

View File

@ -1,126 +0,0 @@
//! Address lookup
use crate::mem::addr::Address;
use super::{
addr_extract_index,
paging::{PageTable, Permission},
PageSize,
};
/// Good result from address split
pub struct AddrPageLookupOk {
/// Virtual address
pub vaddr: Address,
/// Pointer to the start for perform operation
pub ptr: *mut u8,
/// Size to the end of page / end of desired size
pub size: usize,
/// Page permission
pub perm: Permission,
}
/// Errornous address split result
pub struct AddrPageLookupError {
/// Address of failure
pub addr: Address,
/// Requested page size
pub size: PageSize,
}
/// Address splitter into pages
pub struct AddrPageLookuper {
/// Current address
addr: Address,
/// Size left
size: usize,
/// Page table
pagetable: *const PageTable,
}
impl AddrPageLookuper {
/// Create a new page lookuper
#[inline]
pub const fn new(addr: Address, size: usize, pagetable: *const PageTable) -> Self {
Self {
addr,
size,
pagetable,
}
}
/// Bump address by size X
pub fn bump(&mut self, page_size: PageSize) {
self.addr += page_size;
self.size = self.size.saturating_sub(page_size as _);
}
}
impl Iterator for AddrPageLookuper {
type Item = Result<AddrPageLookupOk, AddrPageLookupError>;
fn next(&mut self) -> Option<Self::Item> {
// The end, everything is fine
if self.size == 0 {
return None;
}
let (base, perm, size, offset) = 'a: {
let mut current_pt = self.pagetable;
// Walk the page table
for lvl in (0..5).rev() {
// Get an entry
unsafe {
let entry = (*current_pt)
.table
.get_unchecked(addr_extract_index(self.addr, lvl));
let ptr = entry.ptr();
match entry.permission() {
// No page → page fault
Permission::Empty => {
return Some(Err(AddrPageLookupError {
addr: self.addr,
size: PageSize::from_lvl(lvl)?,
}))
}
// Node → proceed waking
Permission::Node => current_pt = ptr as _,
// Leaf → return relevant data
perm => {
break 'a (
// Pointer in host memory
ptr as *mut u8,
perm,
PageSize::from_lvl(lvl)?,
// In-page offset
addr_extract_index(self.addr, lvl),
);
}
}
}
}
return None; // Reached the end (should not happen)
};
// Get available byte count in the selected page with offset
let avail = (size as usize).saturating_sub(offset).clamp(0, self.size);
self.bump(size);
Some(Ok(AddrPageLookupOk {
vaddr: self.addr,
ptr: unsafe { base.add(offset) }, // Return pointer to the start of region
size: avail,
perm,
}))
}
}

View File

@ -1,172 +0,0 @@
//! Automatic memory mapping
use crate::{mem::addr::Address, utils::impl_display};
use {
super::{
addr_extract_index,
paging::{PageTable, Permission, PtEntry, PtPointedData},
PageSize, SoftPagedMem,
},
alloc::boxed::Box,
};
impl<'p, A, const OUT_PROG_EXEC: bool> SoftPagedMem<'p, A, OUT_PROG_EXEC> {
/// Maps host's memory into VM's memory
///
/// # Safety
/// - Your faith in the gods of UB
/// - Addr-san claims it's fine but who knows is she isn't lying :ferrisSus:
/// - Alright, Miri-sama is also fine with this, who knows why
pub unsafe fn map(
&mut self,
host: *mut u8,
target: Address,
perm: Permission,
pagesize: PageSize,
) -> Result<(), MapError> {
let mut current_pt = self.root_pt;
// Decide on what level depth are we going
let lookup_depth = match pagesize {
PageSize::Size4K => 0,
PageSize::Size2M => 1,
PageSize::Size1G => 2,
};
// Walk pagetable levels
for lvl in (lookup_depth + 1..5).rev() {
let entry = unsafe {
(*current_pt)
.table
.get_unchecked_mut(addr_extract_index(target, lvl))
};
let ptr = entry.ptr();
match entry.permission() {
// Still not on target and already seeing empty entry?
// No worries! Let's create one (allocates).
Permission::Empty => {
// Increase children count
unsafe { *current_pt }.childen += 1;
let table = Box::into_raw(Box::new(PtPointedData {
pt: PageTable::default(),
}));
unsafe { core::ptr::write(entry, PtEntry::new(table, Permission::Node)) };
current_pt = table as _;
}
// Continue walking
Permission::Node => current_pt = ptr as _,
// There is some entry on place of node
_ => return Err(MapError::PageOnNode),
}
}
let node = unsafe {
(*current_pt)
.table
.get_unchecked_mut(addr_extract_index(target, lookup_depth))
};
// Check if node is not mapped
if node.permission() != Permission::Empty {
return Err(MapError::AlreadyMapped);
}
// Write entry
unsafe {
(*current_pt).childen += 1;
core::ptr::write(node, PtEntry::new(host.cast(), perm));
}
Ok(())
}
/// Unmaps pages from VM's memory
///
/// If errors, it only means there is no entry to unmap and in most cases
/// just should be ignored.
pub fn unmap(&mut self, addr: Address) -> Result<(), NothingToUnmap> {
let mut current_pt = self.root_pt;
let mut page_tables = [core::ptr::null_mut(); 5];
// Walk page table in reverse
for lvl in (0..5).rev() {
let entry = unsafe {
(*current_pt)
.table
.get_unchecked_mut(addr_extract_index(addr, lvl))
};
let ptr = entry.ptr();
match entry.permission() {
// Nothing is there, throw an error, not critical!
Permission::Empty => return Err(NothingToUnmap),
// Node Save to visited pagetables and continue walking
Permission::Node => {
page_tables[lvl as usize] = entry;
current_pt = ptr as _
}
// Page entry zero it out!
// Zero page entry is completely valid entry with
// empty permission - no UB here!
_ => unsafe {
core::ptr::write_bytes(entry, 0, 1);
break;
},
}
}
// Now walk in order visited page tables
for entry in page_tables.into_iter() {
// Level not visited, skip.
if entry.is_null() {
continue;
}
unsafe {
let children = &mut (*(*entry).ptr()).pt.childen;
*children -= 1; // Decrease children count
// If there are no children, deallocate.
if *children == 0 {
let _ = Box::from_raw((*entry).ptr() as *mut PageTable);
// Zero visited entry
core::ptr::write_bytes(entry, 0, 1);
} else {
break;
}
}
}
Ok(())
}
}
/// Error mapping
#[derive(Clone, Copy, Debug, PartialEq, Eq)]
pub enum MapError {
/// Entry was already mapped
AlreadyMapped,
/// When walking a page entry was
/// encounterd.
PageOnNode,
}
impl_display!(for MapError => match {
Self::AlreadyMapped => "There is already a page mapped on specified address";
Self::PageOnNode => "There was a page mapped on the way instead of node";
});
/// There was no entry in page table to unmap
///
/// No worry, don't panic, nothing bad has happened,
/// but if you are 120% sure there should be something,
/// double-check your addresses.
#[derive(Clone, Copy, Debug)]
pub struct NothingToUnmap;
impl_display!(for NothingToUnmap => "There is no entry to unmap");

View File

@ -1,282 +0,0 @@
//! Platform independent, software paged memory implementation
pub mod icache;
pub mod lookup;
pub mod paging;
#[cfg(feature = "alloc")]
pub mod mapping;
use {
super::{addr::Address, LoadError, Memory, MemoryAccessReason, StoreError},
core::mem::size_of,
icache::ICache,
lookup::{AddrPageLookupError, AddrPageLookupOk, AddrPageLookuper},
paging::{PageTable, Permission},
};
/// HoleyBytes software paged memory
///
/// - `OUT_PROG_EXEC`: set to `false` to disable executing program
/// not contained in initially provided program, even the pages
/// are executable
#[derive(Clone, Debug)]
pub struct SoftPagedMem<'p, PfH, const OUT_PROG_EXEC: bool = true> {
/// Root page table
pub root_pt: *mut PageTable,
/// Page fault handler
pub pf_handler: PfH,
/// Program memory segment
pub program: &'p [u8],
/// Program instruction cache
pub icache: ICache,
}
impl<'p, PfH: HandlePageFault, const OUT_PROG_EXEC: bool> Memory
for SoftPagedMem<'p, PfH, OUT_PROG_EXEC>
{
/// Load value from an address
///
/// # Safety
/// Applies same conditions as for [`core::ptr::copy_nonoverlapping`]
unsafe fn load(
&mut self,
addr: Address,
target: *mut u8,
count: usize,
) -> Result<(), LoadError> {
self.memory_access(
MemoryAccessReason::Load,
addr,
target,
count,
perm_check::readable,
|src, dst, count| unsafe { core::ptr::copy_nonoverlapping(src, dst, count) },
)
.map_err(LoadError)
}
/// Store value to an address
///
/// # Safety
/// Applies same conditions as for [`core::ptr::copy_nonoverlapping`]
unsafe fn store(
&mut self,
addr: Address,
source: *const u8,
count: usize,
) -> Result<(), StoreError> {
self.memory_access(
MemoryAccessReason::Store,
addr,
source.cast_mut(),
count,
perm_check::writable,
|dst, src, count| unsafe { core::ptr::copy_nonoverlapping(src, dst, count) },
)
.map_err(StoreError)
}
#[inline(always)]
unsafe fn prog_read<T>(&mut self, addr: Address) -> T {
if OUT_PROG_EXEC && addr.truncate_usize() > self.program.len() {
return unsafe { self.icache.fetch::<T>(addr, self.root_pt) }
.unwrap_or_else(|| unsafe { core::mem::zeroed() });
}
let addr = addr.truncate_usize();
self.program
.get(addr..addr + size_of::<T>())
.map(|x| unsafe { x.as_ptr().cast::<T>().read() })
.unwrap_or_else(|| unsafe { core::mem::zeroed() })
}
}
impl<'p, PfH: HandlePageFault, const OUT_PROG_EXEC: bool> SoftPagedMem<'p, PfH, OUT_PROG_EXEC> {
// Everyone behold, the holy function, the god of HBVM memory accesses!
/// Split address to pages, check their permissions and feed pointers with offset
/// to a specified function.
///
/// If page is not found, execute page fault trap handler.
#[allow(clippy::too_many_arguments)] // Silence peasant
fn memory_access(
&mut self,
reason: MemoryAccessReason,
src: Address,
mut dst: *mut u8,
len: usize,
permission_check: fn(Permission) -> bool,
action: fn(*mut u8, *mut u8, usize),
) -> Result<(), Address> {
// Memory load from program section
let (src, len) = if src.truncate_usize() < self.program.len() as _ {
// Allow only loads
if reason != MemoryAccessReason::Load {
return Err(src);
}
// Determine how much data to copy from here
let to_copy = len.clamp(0, self.program.len().saturating_sub(src.truncate_usize()));
// Perform action
action(
unsafe { self.program.as_ptr().add(src.truncate_usize()).cast_mut() },
dst,
to_copy,
);
// Return shifted from what we've already copied
(
src.saturating_add(to_copy as u64),
len.saturating_sub(to_copy),
)
} else {
(src, len) // Nothing weird!
};
// Nothing to copy? Don't bother doing anything, bail.
if len == 0 {
return Ok(());
}
// Create new splitter
let mut pspl = AddrPageLookuper::new(src, len, self.root_pt);
loop {
match pspl.next() {
// Page is found
Some(Ok(AddrPageLookupOk {
vaddr,
ptr,
size,
perm,
})) => {
if !permission_check(perm) {
return Err(vaddr);
}
// Perform specified memory action and bump destination pointer
action(ptr, dst, size);
dst = unsafe { dst.add(size) };
}
// No page found
Some(Err(AddrPageLookupError { addr, size })) => {
// Attempt to execute page fault handler
if self.pf_handler.page_fault(
reason,
unsafe { &mut *self.root_pt },
addr,
size,
dst,
) {
// Shift the splitter address
pspl.bump(size);
// Bump dst pointer
dst = unsafe { dst.add(size as _) };
} else {
return Err(addr); // Unhandleable, VM will yield.
}
}
// No remaining pages, we are done!
None => return Ok(()),
}
}
}
}
/// Extract index in page table on specified level
///
/// The level shall not be larger than 4, otherwise
/// the output of the function is unspecified (yes, it can also panic :)
pub fn addr_extract_index(addr: Address, lvl: u8) -> usize {
debug_assert!(lvl <= 4);
let addr = addr.get();
usize::try_from((addr >> (lvl * 8 + 12)) & ((1 << 8) - 1)).expect("?conradluget a better CPU")
}
/// Page size
#[derive(Clone, Copy, Debug, PartialEq, Eq)]
pub enum PageSize {
/// 4 KiB page (on level 0)
Size4K = 4096,
/// 2 MiB page (on level 1)
Size2M = 1024 * 1024 * 2,
/// 1 GiB page (on level 2)
Size1G = 1024 * 1024 * 1024,
}
impl PageSize {
/// Convert page table level to size of page
const fn from_lvl(lvl: u8) -> Option<Self> {
match lvl {
0 => Some(PageSize::Size4K),
1 => Some(PageSize::Size2M),
2 => Some(PageSize::Size1G),
_ => None,
}
}
}
impl core::ops::Add<PageSize> for Address {
type Output = Self;
#[inline(always)]
fn add(self, rhs: PageSize) -> Self::Output {
self + (rhs as u64)
}
}
impl core::ops::AddAssign<PageSize> for Address {
#[inline(always)]
fn add_assign(&mut self, rhs: PageSize) {
*self = Self::new(self.get().wrapping_add(rhs as u64));
}
}
/// Permisison checks
pub mod perm_check {
use super::paging::Permission;
/// Page is readable
#[inline(always)]
pub const fn readable(perm: Permission) -> bool {
matches!(
perm,
Permission::Readonly | Permission::Write | Permission::Exec
)
}
/// Page is writable
#[inline(always)]
pub const fn writable(perm: Permission) -> bool {
matches!(perm, Permission::Write)
}
/// Page is executable
#[inline(always)]
pub const fn executable(perm: Permission) -> bool {
matches!(perm, Permission::Exec)
}
}
/// Handle VM traps
pub trait HandlePageFault {
/// Handle page fault
///
/// Return true if handling was sucessful,
/// otherwise the program will be interrupted and will
/// yield an error.
fn page_fault(
&mut self,
reason: MemoryAccessReason,
pagetable: &mut PageTable,
vaddr: Address,
size: PageSize,
dataptr: *mut u8,
) -> bool
where
Self: Sized;
}

View File

@ -1,86 +0,0 @@
//! Page table and associated structures implementation
use core::{fmt::Debug, mem::MaybeUninit};
/// Page entry permission
#[derive(Clone, Copy, Debug, Default, PartialEq, Eq)]
#[repr(u8)]
pub enum Permission {
/// No page present
#[default]
Empty,
/// Points to another pagetable
Node,
/// Page is read only
Readonly,
/// Page is readable and writable
Write,
/// Page is readable and executable
Exec,
}
/// Page table entry
#[derive(Clone, Copy, Default, PartialEq, Eq)]
pub struct PtEntry(u64);
impl PtEntry {
/// Create new
///
/// # Safety
/// - `ptr` has to point to valid data and shall not be deallocated
/// troughout the entry lifetime
#[inline]
pub unsafe fn new(ptr: *mut PtPointedData, permission: Permission) -> Self {
Self(ptr as u64 | permission as u64)
}
/// Get permission
#[inline]
pub fn permission(&self) -> Permission {
unsafe { core::mem::transmute(self.0 as u8 & 0b111) }
}
/// Get pointer to the data (leaf) or next page table (node)
#[inline]
pub fn ptr(&self) -> *mut PtPointedData {
(self.0 & !((1 << 12) - 1)) as _
}
}
impl Debug for PtEntry {
fn fmt(&self, f: &mut core::fmt::Formatter<'_>) -> core::fmt::Result {
f.debug_struct("PtEntry")
.field("ptr", &self.ptr())
.field("permission", &self.permission())
.finish()
}
}
/// Page table
#[derive(Clone, Copy, Debug, PartialEq, Eq)]
#[repr(align(4096))]
pub struct PageTable {
/// How much entries are in use
pub childen: u8,
/// Entries
pub table: [PtEntry; 256],
}
impl Default for PageTable {
fn default() -> Self {
// SAFETY: It's fine, zeroed page table entry is valid (= empty)
Self {
childen: 0,
table: unsafe { MaybeUninit::zeroed().assume_init() },
}
}
}
/// Data page table entry can possibly point to
#[derive(Clone, Copy)]
#[repr(C, align(4096))]
pub union PtPointedData {
/// Node - next page table
pub pt: PageTable,
/// Leaf
pub page: u8,
}

View File

@ -1,53 +0,0 @@
macro_rules! impl_display {
(for $ty:ty => $(|$selfty:pat_param|)? $fmt:literal $(, $($param:expr),+)? $(,)?) => {
impl ::core::fmt::Display for $ty {
fn fmt(&self, f: &mut ::core::fmt::Formatter<'_>) -> ::core::fmt::Result {
$(let $selfty = self;)?
write!(f, $fmt, $($param),*)
}
}
};
(for $ty:ty => $str:literal) => {
impl ::core::fmt::Display for $ty {
fn fmt(&self, f: &mut ::core::fmt::Formatter<'_>) -> ::core::fmt::Result {
f.write_str($str)
}
}
};
(for $ty:ty => match {$(
$bind:pat => $($const:ident)? $fmt:literal $(,$($params:tt)*)?;
)*}) => {
impl ::core::fmt::Display for $ty {
fn fmt(&self, f: &mut ::core::fmt::Formatter<'_>) -> ::core::fmt::Result {
match self {
$(
$bind => $crate::utils::internal::impl_display_match_fragment!($($const,)? f, $fmt $(, $($params)*)?)
),*
}
}
}
}
}
#[doc(hidden)]
pub(crate) mod internal {
macro_rules! impl_display_match_fragment {
(const, $f:expr, $lit:literal) => {
$f.write_str($lit)
};
($f:expr, $fmt:literal $(, $($params:tt)*)?) => {
write!($f, $fmt, $($($params)*)?)
};
}
pub(crate) use impl_display_match_fragment;
}
macro_rules! static_assert(($expr:expr $(,)?) => {
const _: [(); !$expr as usize] = [];
});
pub(crate) use {impl_display, static_assert};

64
hbvm/src/validate.rs Normal file
View File

@ -0,0 +1,64 @@
//! Validate if program is sound to execute
/// Program validation error kind
#[derive(Clone, Copy, Debug, PartialEq, Eq)]
pub enum ErrorKind {
/// Unknown opcode
InvalidInstruction,
/// VM doesn't implement this valid opcode
Unimplemented,
/// Attempted to copy over register boundary
RegisterArrayOverflow,
}
/// Error
#[derive(Clone, Copy, Debug, PartialEq, Eq)]
pub struct Error {
/// Kind
pub kind: ErrorKind,
/// Location in bytecode
pub index: usize,
}
/// Perform bytecode validation. If it passes, the program should be
/// sound to execute.
pub fn validate(mut program: &[u8]) -> Result<(), Error> {
use hbbytecode::opcode::*;
let start = program;
loop {
// Match on instruction types and perform necessary checks
program = match program {
[] => return Ok(()),
[LD..=ST, reg, _, _, _, _, _, _, _, _, _, count, ..]
if usize::from(*reg) * 8 + usize::from(*count) > 2048 =>
{
return Err(Error {
kind: ErrorKind::RegisterArrayOverflow,
index: (program.as_ptr() as usize) - (start.as_ptr() as usize),
})
}
[BRC, src, dst, count, ..]
if src.checked_add(*count).is_none() || dst.checked_add(*count).is_none() =>
{
return Err(Error {
kind: ErrorKind::RegisterArrayOverflow,
index: (program.as_ptr() as usize) - (start.as_ptr() as usize),
})
}
[NOP | ECALL, rest @ ..]
| [DIR | DIRF, _, _, _, _, rest @ ..]
| [ADD..=CMPU | BRC | ADDF..=MULF, _, _, _, rest @ ..]
| [NEG..=NOT | CP..=SWA | NEGF..=FTI, _, _, rest @ ..]
| [LI | JMP, _, _, _, _, _, _, _, _, _, rest @ ..]
| [ADDI..=CMPUI | BMC | JEQ..=JGTU | ADDFI..=MULFI, _, _, _, _, _, _, _, _, _, _, rest @ ..]
| [LD..=ST, _, _, _, _, _, _, _, _, _, _, _, _, rest @ ..] => rest,
_ => {
return Err(Error {
kind: ErrorKind::InvalidInstruction,
index: (program.as_ptr() as usize) - (start.as_ptr() as usize),
})
}
}
}
}

View File

@ -1,88 +0,0 @@
//! HoleyBytes register value definition
use crate::utils::static_assert;
/// Define [`Value`] »union« (it's fake)
///
/// # Safety
/// Its variants have to be sound to byte-reinterpretate
/// between each other. Otherwise the behaviour is undefined.
macro_rules! value_def {
($($ty:ident),* $(,)?) => {
/// HBVM register value
#[derive(Copy, Clone)]
#[repr(transparent)]
pub struct Value(pub u64);
$(
impl From<$ty> for Value {
#[inline]
fn from(value: $ty) -> Self {
let mut new = core::mem::MaybeUninit::<u64>::zeroed();
unsafe {
new.as_mut_ptr().cast::<$ty>().write(value);
Self(new.assume_init())
}
}
}
static_assert!(core::mem::size_of::<$ty>() <= core::mem::size_of::<Value>());
impl private::Sealed for $ty {}
unsafe impl ValueVariant for $ty {}
)*
};
}
impl Value {
/// Byte reinterpret value to target variant
#[inline]
pub fn cast<V: ValueVariant>(self) -> V {
unsafe { core::mem::transmute_copy(&self.0) }
}
}
/// # Safety
/// - N/A, not to be implemented manually
pub unsafe trait ValueVariant: private::Sealed + Copy + Into<Value> {}
impl private::Sealed for Value {}
unsafe impl ValueVariant for Value {}
mod private {
pub trait Sealed {}
}
value_def!(u8, u16, u32, u64, i8, i16, i32, i64, f32, f64);
static_assert!(core::mem::size_of::<Value>() == 8);
impl core::fmt::Debug for Value {
fn fmt(&self, f: &mut core::fmt::Formatter<'_>) -> core::fmt::Result {
// Print formatted as hexadecimal, unsigned integer
write!(f, "{:x}", self.cast::<u64>())
}
}
pub(crate) trait CheckedDivRem {
fn checked_div(self, other: Self) -> Option<Self>
where
Self: Sized;
fn checked_rem(self, other: Self) -> Option<Self>
where
Self: Sized;
}
macro_rules! impl_checked_div_rem {
($($ty:ty),* $(,)?) => {
$(impl CheckedDivRem for $ty {
#[inline(always)]
fn checked_div(self, another: Self) -> Option<Self>
{ self.checked_div(another) }
#[inline(always)]
fn checked_rem(self, another: Self) -> Option<Self>
{ self.checked_rem(another) }
})*
};
}
impl_checked_div_rem!(u8, u16, u32, u64, i8, i16, i32, i64);

430
hbvm/src/vm/mem/mod.rs Normal file
View File

@ -0,0 +1,430 @@
//! Program memory implementation
pub mod paging;
use {
self::paging::{PageTable, Permission, PtEntry},
super::{trap::HandleTrap, VmRunError},
alloc::boxed::Box,
core::mem::MaybeUninit,
derive_more::Display,
};
/// HoleyBytes virtual memory
#[derive(Clone, Debug)]
pub struct Memory {
/// Root page table
root_pt: *mut PageTable,
}
impl Default for Memory {
fn default() -> Self {
Self {
root_pt: Box::into_raw(Box::default()),
}
}
}
impl Drop for Memory {
fn drop(&mut self) {
let _ = unsafe { Box::from_raw(self.root_pt) };
}
}
impl Memory {
// HACK: Just for allocation testing, will be removed when proper memory interfaces
// implemented.
pub fn insert_test_page(&mut self) {
unsafe {
let mut entry = PtEntry::new(
{
let layout = alloc::alloc::Layout::from_size_align_unchecked(4096, 4096);
let ptr = alloc::alloc::alloc_zeroed(layout);
if ptr.is_null() {
alloc::alloc::handle_alloc_error(layout);
}
core::ptr::write_bytes(ptr, 69, 10);
ptr.cast()
},
Permission::Write,
);
for _ in 0..4 {
let mut pt = Box::<PageTable>::default();
pt[0] = entry;
entry = PtEntry::new(Box::into_raw(pt) as _, Permission::Node);
}
(*self.root_pt)[0] = entry;
}
}
/// Load value from an address
///
/// # Safety
/// Applies same conditions as for [`core::ptr::copy_nonoverlapping`]
pub unsafe fn load(
&mut self,
addr: u64,
target: *mut u8,
count: usize,
traph: &mut impl HandleTrap,
) -> Result<(), LoadError> {
self.memory_access(
MemoryAccessReason::Load,
addr,
target,
count,
|perm| {
matches!(
perm,
Permission::Readonly | Permission::Write | Permission::Exec
)
},
|src, dst, count| core::ptr::copy_nonoverlapping(src, dst, count),
traph,
)
.map_err(LoadError)
}
/// Store value to an address
///
/// # Safety
/// Applies same conditions as for [`core::ptr::copy_nonoverlapping`]
pub unsafe fn store(
&mut self,
addr: u64,
source: *const u8,
count: usize,
traph: &mut impl HandleTrap,
) -> Result<(), StoreError> {
self.memory_access(
MemoryAccessReason::Store,
addr,
source.cast_mut(),
count,
|perm| perm == Permission::Write,
|dst, src, count| core::ptr::copy_nonoverlapping(src, dst, count),
traph,
)
.map_err(StoreError)
}
/// Copy a block of memory
///
/// # Safety
/// - Same as for [`Self::load`] and [`Self::store`]
/// - Your faith in the gods of UB
/// - Addr-san claims it's fine but who knows is she isn't lying :ferrisSus:
pub unsafe fn block_copy(
&mut self,
src: u64,
dst: u64,
count: usize,
traph: &mut impl HandleTrap,
) -> Result<(), BlkCopyError> {
// Yea, i know it is possible to do this more efficiently, but I am too lazy.
const STACK_BUFFER_SIZE: usize = 512;
// Decide if to use stack-allocated buffer or to heap allocate
// Deallocation is again decided on size at the end of the function
let mut buf = MaybeUninit::<[u8; STACK_BUFFER_SIZE]>::uninit();
let buf = if count <= STACK_BUFFER_SIZE {
buf.as_mut_ptr().cast()
} else {
unsafe {
let layout = core::alloc::Layout::from_size_align_unchecked(count, 1);
let ptr = alloc::alloc::alloc(layout);
if ptr.is_null() {
alloc::alloc::handle_alloc_error(layout);
}
ptr
}
};
// Perform memory block transfer
let status = (|| {
// Load to buffer
self.memory_access(
MemoryAccessReason::Load,
src,
buf,
count,
|perm| {
matches!(
perm,
Permission::Readonly | Permission::Write | Permission::Exec
)
},
|src, dst, count| core::ptr::copy(src, dst, count),
traph,
)
.map_err(|addr| BlkCopyError {
access_reason: MemoryAccessReason::Load,
addr,
})?;
// Store from buffer
self.memory_access(
MemoryAccessReason::Store,
dst,
buf,
count,
|perm| perm == Permission::Write,
|dst, src, count| core::ptr::copy(src, dst, count),
traph,
)
.map_err(|addr| BlkCopyError {
access_reason: MemoryAccessReason::Store,
addr,
})?;
Ok::<_, BlkCopyError>(())
})();
// Deallocate if used heap-allocated array
if count > STACK_BUFFER_SIZE {
alloc::alloc::dealloc(
buf,
core::alloc::Layout::from_size_align_unchecked(count, 1),
);
}
status
}
/// Split address to pages, check their permissions and feed pointers with offset
/// to a specified function.
///
/// If page is not found, execute page fault trap handler.
#[allow(clippy::too_many_arguments)] // Silence peasant
fn memory_access(
&mut self,
reason: MemoryAccessReason,
src: u64,
mut dst: *mut u8,
len: usize,
permission_check: fn(Permission) -> bool,
action: fn(*mut u8, *mut u8, usize),
traph: &mut impl HandleTrap,
) -> Result<(), u64> {
let mut pspl = AddrSplitter::new(src, len, self.root_pt);
loop {
match pspl.next() {
// Page found
Some(Ok(AddrSplitOk {
vaddr,
ptr,
size,
perm,
})) => {
if !permission_check(perm) {
return Err(vaddr);
}
// Perform memory action and bump dst pointer
action(ptr, dst, size);
dst = unsafe { dst.add(size) };
}
Some(Err(AddrSplitError { addr, size })) => {
// Execute page fault handler
if traph.page_fault(reason, self, addr, size, dst) {
// Shift the splitter address
pspl.bump(size);
// Bump dst pointer
dst = unsafe { dst.add(size as _) };
} else {
return Err(addr); // Unhandleable
}
}
None => return Ok(()),
}
}
}
}
/// Result from address split
struct AddrSplitOk {
/// Virtual address
vaddr: u64,
/// Pointer to the start for perform operation
ptr: *mut u8,
/// Size to the end of page / end of desired size
size: usize,
/// Page permission
perm: Permission,
}
struct AddrSplitError {
/// Address of failure
addr: u64,
/// Requested page size
size: PageSize,
}
/// Address splitter into pages
struct AddrSplitter {
/// Current address
addr: u64,
/// Size left
size: usize,
/// Page table
pagetable: *const PageTable,
}
impl AddrSplitter {
/// Create a new page splitter
pub const fn new(addr: u64, size: usize, pagetable: *const PageTable) -> Self {
Self {
addr,
size,
pagetable,
}
}
/// Bump address by size X
fn bump(&mut self, page_size: PageSize) {
self.addr += page_size as u64;
self.size = self.size.saturating_sub(page_size as _);
}
}
impl Iterator for AddrSplitter {
type Item = Result<AddrSplitOk, AddrSplitError>;
fn next(&mut self) -> Option<Self::Item> {
// The end, everything is fine
if self.size == 0 {
return None;
}
let (base, perm, size, offset) = 'a: {
let mut current_pt = self.pagetable;
// Walk the page table
for lvl in (0..5).rev() {
// Get an entry
unsafe {
let entry = (*current_pt).get_unchecked(
usize::try_from((self.addr >> (lvl * 9 + 12)) & ((1 << 9) - 1))
.expect("?conradluget a better CPU"),
);
let ptr = entry.ptr();
match entry.permission() {
// No page → page fault
Permission::Empty => {
return Some(Err(AddrSplitError {
addr: self.addr,
size: PageSize::from_lvl(lvl)?,
}))
}
// Node → proceed waking
Permission::Node => current_pt = ptr as _,
// Leaft → return relevant data
perm => {
break 'a (
// Pointer in host memory
ptr as *mut u8,
perm,
PageSize::from_lvl(lvl)?,
// In-page offset
self.addr as usize & ((1 << (lvl * 9 + 12)) - 1),
);
}
}
}
}
return None; // Reached the end (should not happen)
};
// Get available byte count in the selected page with offset
let avail = (size as usize - offset).clamp(0, self.size);
self.bump(size);
Some(Ok(AddrSplitOk {
vaddr: self.addr,
ptr: unsafe { base.add(offset) }, // Return pointer to the start of region
size: avail,
perm,
}))
}
}
/// Page size
#[derive(Clone, Copy, Debug, PartialEq, Eq)]
pub enum PageSize {
/// 4 KiB page (on level 0)
Size4K = 4096,
/// 2 MiB page (on level 1)
Size2M = 1024 * 1024 * 2,
/// 1 GiB page (on level 2)
Size1G = 1024 * 1024 * 1024,
}
impl PageSize {
/// Convert page table level to size of page
fn from_lvl(lvl: u8) -> Option<Self> {
match lvl {
0 => Some(PageSize::Size4K),
1 => Some(PageSize::Size2M),
2 => Some(PageSize::Size1G),
_ => None,
}
}
}
/// Unhandled load access trap
#[derive(Clone, Copy, Display, Debug, PartialEq, Eq)]
pub struct LoadError(u64);
/// Unhandled store access trap
#[derive(Clone, Copy, Display, Debug, PartialEq, Eq)]
pub struct StoreError(u64);
#[derive(Clone, Copy, Display, Debug, PartialEq, Eq)]
pub enum MemoryAccessReason {
Load,
Store,
}
#[derive(Clone, Copy, Debug, PartialEq, Eq)]
pub struct BlkCopyError {
access_reason: MemoryAccessReason,
addr: u64,
}
impl From<BlkCopyError> for VmRunError {
fn from(value: BlkCopyError) -> Self {
match value.access_reason {
MemoryAccessReason::Load => Self::LoadAccessEx(value.addr),
MemoryAccessReason::Store => Self::StoreAccessEx(value.addr),
}
}
}
impl From<LoadError> for VmRunError {
fn from(value: LoadError) -> Self {
Self::LoadAccessEx(value.0)
}
}
impl From<StoreError> for VmRunError {
fn from(value: StoreError) -> Self {
Self::StoreAccessEx(value.0)
}
}

152
hbvm/src/vm/mem/paging.rs Normal file
View File

@ -0,0 +1,152 @@
//! Page table and associated structures implementation
use {
core::{
fmt::Debug,
mem::MaybeUninit,
ops::{Index, IndexMut},
slice::SliceIndex,
},
delegate::delegate,
};
/// Page entry permission
#[derive(Clone, Copy, Debug, Default, PartialEq, Eq)]
#[repr(u8)]
pub enum Permission {
/// No page present
#[default]
Empty,
/// Points to another pagetable
Node,
/// Page is read only
Readonly,
/// Page is readable and writable
Write,
/// Page is readable and executable
Exec,
}
/// Page table entry
#[derive(Clone, Copy, Default, PartialEq, Eq)]
pub struct PtEntry(u64);
impl PtEntry {
/// Create new
///
/// # Safety
/// - `ptr` has to point to valid data and shall not be deallocated
/// troughout the entry lifetime
#[inline]
pub unsafe fn new(ptr: *mut PtPointedData, permission: Permission) -> Self {
Self(ptr as u64 | permission as u64)
}
/// Get permission
#[inline]
pub fn permission(&self) -> Permission {
unsafe { core::mem::transmute(self.0 as u8 & 0b111) }
}
/// Get pointer to the data (leaf) or next page table (node)
#[inline]
pub fn ptr(&self) -> *mut PtPointedData {
(self.0 & !((1 << 12) - 1)) as _
}
}
impl Debug for PtEntry {
fn fmt(&self, f: &mut core::fmt::Formatter<'_>) -> core::fmt::Result {
f.debug_struct("PtEntry")
.field("ptr", &self.ptr())
.field("permission", &self.permission())
.finish()
}
}
/// Page table
#[derive(Clone, Copy, Debug, PartialEq, Eq)]
#[repr(align(4096))]
pub struct PageTable([PtEntry; 512]);
impl PageTable {
delegate!(to self.0 {
/// Returns a reference to an element or subslice depending on the type of
/// index.
///
/// - If given a position, returns a reference to the element at that
/// position or `None` if out of bounds.
/// - If given a range, returns the subslice corresponding to that range,
/// or `None` if out of bounds.
///
pub fn get<I>(&self, ix: I) -> Option<&I::Output>
where I: SliceIndex<[PtEntry]>;
/// Returns a mutable reference to an element or subslice depending on the
/// type of index (see [`get`]) or `None` if the index is out of bounds.
pub fn get_mut<I>(&mut self, ix: I) -> Option<&mut I::Output>
where I: SliceIndex<[PtEntry]>;
/// Returns a reference to an element or subslice, without doing bounds
/// checking.
///
/// For a safe alternative see [`get`].
///
/// # Safety
///
/// Calling this method with an out-of-bounds index is *[undefined behavior]*
/// even if the resulting reference is not used.
pub unsafe fn get_unchecked<I>(&self, index: I) -> &I::Output
where I: SliceIndex<[PtEntry]>;
/// Returns a mutable reference to an element or subslice, without doing
/// bounds checking.
///
/// For a safe alternative see [`get_mut`].
///
/// # Safety
///
/// Calling this method with an out-of-bounds index is *[undefined behavior]*
/// even if the resulting reference is not used.
pub unsafe fn get_unchecked_mut<I>(&mut self, index: I) -> &mut I::Output
where I: SliceIndex<[PtEntry]>;
});
}
impl<Idx> Index<Idx> for PageTable
where
Idx: SliceIndex<[PtEntry]>,
{
type Output = Idx::Output;
#[inline(always)]
fn index(&self, index: Idx) -> &Self::Output {
&self.0[index]
}
}
impl<Idx> IndexMut<Idx> for PageTable
where
Idx: SliceIndex<[PtEntry]>,
{
#[inline(always)]
fn index_mut(&mut self, index: Idx) -> &mut Self::Output {
&mut self.0[index]
}
}
impl Default for PageTable {
fn default() -> Self {
// SAFETY: It's fine, zeroed page table entry is valid (= empty)
Self(unsafe { MaybeUninit::zeroed().assume_init() })
}
}
/// Data page table entry can possibly point to
#[derive(Clone, Copy)]
#[repr(C, align(4096))]
pub union PtPointedData {
/// Node - next page table
pub pt: PageTable,
/// Leaf
pub page: u8,
}

373
hbvm/src/vm/mod.rs Normal file
View File

@ -0,0 +1,373 @@
//! HoleyBytes Virtual Machine
//!
//! All unsafe code here should be sound, if input bytecode passes validation.
// # General safety notice:
// - Validation has to assure there is 256 registers (r0 - r255)
// - Instructions have to be valid as specified (values and sizes)
// - Mapped pages should be at least 4 KiB
// - Yes, I am aware of the UB when jumping in-mid of instruction where
// the read byte corresponds to an instruction whose lenght exceets the
// program size. If you are (rightfully) worried about the UB, for now just
// append your program with 11 zeroes.
use self::trap::HandleTrap;
pub mod mem;
pub mod trap;
pub mod value;
use {
crate::validate,
core::ops,
hbbytecode::{OpParam, ParamBB, ParamBBB, ParamBBBB, ParamBBD, ParamBBDH, ParamBD},
mem::Memory,
static_assertions::assert_impl_one,
value::Value,
};
/// Extract a parameter from program
macro_rules! param {
($self:expr, $ty:ty) => {{
assert_impl_one!($ty: OpParam);
let data = $self
.program
.as_ptr()
.add($self.pc + 1)
.cast::<$ty>()
.read();
$self.pc += 1 + core::mem::size_of::<$ty>();
data
}};
}
/// Perform binary operation `#0 ← #1 OP #2`
macro_rules! binary_op {
($self:expr, $ty:ident, $handler:expr) => {{
let ParamBBB(tg, a0, a1) = param!($self, ParamBBB);
$self.write_reg(
tg,
$handler(
Value::$ty(&$self.read_reg(a0)),
Value::$ty(&$self.read_reg(a1)),
),
);
}};
}
/// Perform binary operation with immediate `#0 ← #1 OP imm #2`
macro_rules! binary_op_imm {
($self:expr, $ty:ident, $handler:expr) => {{
let ParamBBD(tg, a0, imm) = param!($self, ParamBBD);
$self.write_reg(
tg,
$handler(Value::$ty(&$self.read_reg(a0)), Value::$ty(&imm.into())),
);
}};
}
/// Jump at `#3` if ordering on `#0 <=> #1` is equal to expected
macro_rules! cond_jump {
($self:expr, $ty:ident, $expected:ident) => {{
let ParamBBD(a0, a1, jt) = param!($self, ParamBBD);
if core::cmp::Ord::cmp(&$self.read_reg(a0).as_u64(), &$self.read_reg(a1).as_u64())
== core::cmp::Ordering::$expected
{
$self.pc = jt as usize;
}
}};
}
/// HoleyBytes Virtual Machine
pub struct Vm<'a, T, const TIMER_QUOTIENT: usize> {
/// Holds 256 registers
///
/// Writing to register 0 is considered undefined behaviour
/// in terms of HoleyBytes program execution
pub registers: [Value; 256],
/// Memory implementation
pub memory: Memory,
/// Trap handler
pub traph: T,
// Program counter
pc: usize,
/// Program
program: &'a [u8],
/// Program timer
timer: usize,
}
impl<'a, T: HandleTrap, const TIMER_QUOTIENT: usize> Vm<'a, T, TIMER_QUOTIENT> {
/// Create a new VM with program and trap handler
///
/// # Safety
/// Program code has to be validated
pub unsafe fn new_unchecked(program: &'a [u8], traph: T) -> Self {
Self {
registers: [Value::from(0_u64); 256],
memory: Default::default(),
traph,
pc: 0,
program,
timer: 0,
}
}
/// Create a new VM with program and trap handler only if it passes validation
pub fn new_validated(program: &'a [u8], traph: T) -> Result<Self, validate::Error> {
validate::validate(program)?;
Ok(unsafe { Self::new_unchecked(program, traph) })
}
/// Execute program
///
/// Program can return [`VmRunError`] if a trap handling failed
pub fn run(&mut self) -> Result<VmRunOk, VmRunError> {
use hbbytecode::opcode::*;
loop {
// Fetch instruction
let Some(&opcode) = self.program.get(self.pc)
else { return Ok(VmRunOk::End) };
// Big match
unsafe {
match opcode {
NOP => param!(self, ()),
ADD => binary_op!(self, as_u64, u64::wrapping_add),
SUB => binary_op!(self, as_u64, u64::wrapping_sub),
MUL => binary_op!(self, as_u64, u64::wrapping_mul),
AND => binary_op!(self, as_u64, ops::BitAnd::bitand),
OR => binary_op!(self, as_u64, ops::BitOr::bitor),
XOR => binary_op!(self, as_u64, ops::BitXor::bitxor),
SL => binary_op!(self, as_u64, ops::Shl::shl),
SR => binary_op!(self, as_u64, ops::Shr::shr),
SRS => binary_op!(self, as_i64, ops::Shr::shr),
CMP => {
let ParamBBB(tg, a0, a1) = param!(self, ParamBBB);
self.write_reg(
tg,
self.read_reg(a0).as_i64().cmp(&self.read_reg(a1).as_i64()) as i64,
);
}
CMPU => {
let ParamBBB(tg, a0, a1) = param!(self, ParamBBB);
self.write_reg(
tg,
self.read_reg(a0).as_u64().cmp(&self.read_reg(a1).as_u64()) as i64,
);
}
NOT => {
let param = param!(self, ParamBB);
self.write_reg(param.0, !self.read_reg(param.1).as_u64());
}
NEG => {
let param = param!(self, ParamBB);
self.write_reg(
param.0,
match self.read_reg(param.1).as_u64() {
0 => 1_u64,
_ => 0,
},
);
}
DIR => {
let ParamBBBB(dt, rt, a0, a1) = param!(self, ParamBBBB);
let a0 = self.read_reg(a0).as_u64();
let a1 = self.read_reg(a1).as_u64();
self.write_reg(dt, a0.checked_div(a1).unwrap_or(u64::MAX));
self.write_reg(rt, a0.checked_rem(a1).unwrap_or(u64::MAX));
}
ADDI => binary_op_imm!(self, as_u64, ops::Add::add),
MULI => binary_op_imm!(self, as_u64, ops::Mul::mul),
ANDI => binary_op_imm!(self, as_u64, ops::BitAnd::bitand),
ORI => binary_op_imm!(self, as_u64, ops::BitOr::bitor),
XORI => binary_op_imm!(self, as_u64, ops::BitXor::bitxor),
SLI => binary_op_imm!(self, as_u64, ops::Shl::shl),
SRI => binary_op_imm!(self, as_u64, ops::Shr::shr),
SRSI => binary_op_imm!(self, as_i64, ops::Shr::shr),
CMPI => {
let ParamBBD(tg, a0, imm) = param!(self, ParamBBD);
self.write_reg(
tg,
self.read_reg(a0).as_i64().cmp(&Value::from(imm).as_i64()) as i64,
);
}
CMPUI => {
let ParamBBD(tg, a0, imm) = param!(self, ParamBBD);
self.write_reg(tg, self.read_reg(a0).as_u64().cmp(&imm) as i64);
}
CP => {
let param = param!(self, ParamBB);
self.write_reg(param.0, self.read_reg(param.1));
}
SWA => {
let ParamBB(src, dst) = param!(self, ParamBB);
if src + dst != 0 {
core::ptr::swap(
self.registers.get_unchecked_mut(usize::from(src)),
self.registers.get_unchecked_mut(usize::from(dst)),
);
}
}
LI => {
let param = param!(self, ParamBD);
self.write_reg(param.0, param.1);
}
LD => {
let ParamBBDH(dst, base, off, count) = param!(self, ParamBBDH);
let n: usize = match dst {
0 => 1,
_ => 0,
};
self.memory.load(
self.read_reg(base).as_u64() + off + n as u64,
self.registers.as_mut_ptr().add(usize::from(dst) + n).cast(),
usize::from(count).saturating_sub(n),
&mut self.traph,
)?;
}
ST => {
let ParamBBDH(dst, base, off, count) = param!(self, ParamBBDH);
self.memory.store(
self.read_reg(base).as_u64() + off,
self.registers.as_ptr().add(usize::from(dst)).cast(),
count.into(),
&mut self.traph,
)?;
}
BMC => {
let ParamBBD(src, dst, count) = param!(self, ParamBBD);
self.memory.block_copy(
self.read_reg(src).as_u64(),
self.read_reg(dst).as_u64(),
count as _,
&mut self.traph,
)?;
}
BRC => {
let ParamBBB(src, dst, count) = param!(self, ParamBBB);
core::ptr::copy(
self.registers.get_unchecked(usize::from(src)),
self.registers.get_unchecked_mut(usize::from(dst)),
usize::from(count * 8),
);
}
JMP => {
let ParamBD(reg, offset) = param!(self, ParamBD);
self.pc = (self.read_reg(reg).as_u64() + offset) as usize;
}
JEQ => cond_jump!(self, int, Equal),
JNE => {
let ParamBBD(a0, a1, jt) = param!(self, ParamBBD);
if self.read_reg(a0).as_u64() != self.read_reg(a1).as_u64() {
self.pc = jt as usize;
}
}
JLT => cond_jump!(self, int, Less),
JGT => cond_jump!(self, int, Greater),
JLTU => cond_jump!(self, sint, Less),
JGTU => cond_jump!(self, sint, Greater),
ECALL => {
param!(self, ());
self.traph
.ecall(&mut self.registers, &mut self.pc, &mut self.memory);
}
ADDF => binary_op!(self, as_f64, ops::Add::add),
SUBF => binary_op!(self, as_f64, ops::Sub::sub),
MULF => binary_op!(self, as_f64, ops::Mul::mul),
DIRF => {
let ParamBBBB(dt, rt, a0, a1) = param!(self, ParamBBBB);
let a0 = self.read_reg(a0).as_f64();
let a1 = self.read_reg(a1).as_f64();
self.write_reg(dt, a0 / a1);
self.write_reg(rt, a0 % a1);
}
FMAF => {
let ParamBBBB(dt, a0, a1, a2) = param!(self, ParamBBBB);
self.write_reg(
dt,
self.read_reg(a0).as_f64() * self.read_reg(a1).as_f64()
+ self.read_reg(a2).as_f64(),
);
}
NEGF => {
let ParamBB(dt, a0) = param!(self, ParamBB);
self.write_reg(dt, -self.read_reg(a0).as_f64());
}
ITF => {
let ParamBB(dt, a0) = param!(self, ParamBB);
self.write_reg(dt, self.read_reg(a0).as_i64() as f64);
}
FTI => {
let ParamBB(dt, a0) = param!(self, ParamBB);
self.write_reg(dt, self.read_reg(a0).as_f64() as i64);
}
ADDFI => binary_op_imm!(self, as_f64, ops::Add::add),
MULFI => binary_op_imm!(self, as_f64, ops::Mul::mul),
op => {
if !self.traph.invalid_op(
&mut self.registers,
&mut self.pc,
&mut self.memory,
op,
) {
return Err(VmRunError::InvalidOpcodeEx(op));
}
}
}
}
if TIMER_QUOTIENT != 0 {
self.timer = self.timer.wrapping_add(1);
if self.timer % TIMER_QUOTIENT == 0 {
return Ok(VmRunOk::Timer);
}
}
}
}
/// Read register
#[inline]
unsafe fn read_reg(&self, n: u8) -> Value {
*self.registers.get_unchecked(n as usize)
}
/// Write a register.
/// Writing to register 0 is no-op.
#[inline]
unsafe fn write_reg(&mut self, n: u8, value: impl Into<Value>) {
if n != 0 {
*self.registers.get_unchecked_mut(n as usize) = value.into();
}
}
}
/// Virtual machine halt error
#[derive(Copy, Clone, Debug, PartialEq, Eq)]
#[repr(u8)]
pub enum VmRunError {
/// Unhandled invalid opcode exceptions
InvalidOpcodeEx(u8),
/// Unhandled load access exception
LoadAccessEx(u64),
/// Unhandled store access exception
StoreAccessEx(u64),
}
/// Virtual machine halt ok
#[derive(Copy, Clone, Debug, PartialEq, Eq)]
pub enum VmRunOk {
/// Program has eached its end
End,
/// Program was interrupted by a timer
Timer,
}

35
hbvm/src/vm/trap.rs Normal file
View File

@ -0,0 +1,35 @@
//! Program trap handling interfaces
use super::{
mem::{Memory, MemoryAccessReason, PageSize},
value::Value,
};
/// Handle VM traps
pub trait HandleTrap {
/// Handle page fault
fn page_fault(
&mut self,
reason: MemoryAccessReason,
memory: &mut Memory,
vaddr: u64,
size: PageSize,
dataptr: *mut u8,
) -> bool;
/// Handle invalid opcode exception
fn invalid_op(
&mut self,
regs: &mut [Value; 256],
pc: &mut usize,
memory: &mut Memory,
op: u8,
) -> bool
where
Self: Sized;
/// Handle environment calls
fn ecall(&mut self, regs: &mut [Value; 256], pc: &mut usize, memory: &mut Memory)
where
Self: Sized;
}

48
hbvm/src/vm/value.rs Normal file
View File

@ -0,0 +1,48 @@
//! HoleyBytes register value definition
use core::fmt::Debug;
/// Define [`Value`] union
///
/// # Safety
/// Union variants have to be sound to byte-reinterpretate
/// between each other. Otherwise the behaviour is undefined.
macro_rules! value_def {
($($ty:ident),* $(,)?) => {
/// HBVM register value
#[derive(Copy, Clone)]
#[repr(packed)]
pub union Value {
$(pub $ty: $ty),*
}
paste::paste! {
impl Value {$(
#[doc = "Byte-reinterpret [`Value`] as [`" $ty "`]"]
#[inline]
pub fn [<as_ $ty>](&self) -> $ty {
unsafe { self.$ty }
}
)*}
}
$(
impl From<$ty> for Value {
#[inline]
fn from(value: $ty) -> Self {
Self { $ty: value }
}
}
)*
};
}
value_def!(u64, i64, f64);
static_assertions::const_assert_eq!(core::mem::size_of::<Value>(), 8);
impl Debug for Value {
fn fmt(&self, f: &mut core::fmt::Formatter<'_>) -> core::fmt::Result {
// Print formatted as hexadecimal, unsigned integer
write!(f, "{:x}", self.as_u64())
}
}

View File

@ -1,578 +0,0 @@
//! Welcome to the land of The Great Dispatch Loop
//!
//! Have fun
use {
super::{bmc::BlockCopier, mem::Memory, value::ValueVariant, Vm, VmRunError, VmRunOk},
crate::{
mem::{addr::AddressOp, Address},
value::CheckedDivRem,
},
core::{cmp::Ordering, ops},
hbbytecode::{
OpsN, OpsO, OpsP, OpsRB, OpsRD, OpsRH, OpsRR, OpsRRA, OpsRRAH, OpsRRB, OpsRRD, OpsRRH,
OpsRRO, OpsRROH, OpsRRP, OpsRRPH, OpsRRR, OpsRRRR, OpsRW, RoundingMode,
},
};
macro_rules! handler {
($self:expr, |$ty:ident ($($ident:pat),* $(,)?)| $expr:expr) => {{
#[allow(unused_unsafe)]
let $ty($($ident),*) = unsafe { $self.decode::<$ty>() };
#[allow(clippy::no_effect)] let e = $expr;
$self.bump_pc::<$ty>();
e
}};
}
impl<Mem, const TIMER_QUOTIENT: usize> Vm<Mem, TIMER_QUOTIENT>
where
Mem: Memory,
{
/// Execute program
///
/// Program can return [`VmRunError`] if a trap handling failed
#[cfg_attr(feature = "nightly", repr(align(4096)))]
pub fn run(&mut self) -> Result<VmRunOk, VmRunError> {
use hbbytecode::opcode::*;
loop {
// Big match
//
// Contribution guide:
// - Zero register shall never be overwitten. It's value has to always be 0.
// - Prefer `Self::read_reg` and `Self::write_reg` functions
// - Try to use `handler!` macro for decoding and then bumping program counter
// - Prioritise speed over code size
// - Memory is cheap, CPUs not that much
// - Do not heap allocate at any cost
// - Yes, user-provided trap handler may allocate,
// but that is not our »fault«.
// - Unsafe is kinda must, but be sure you have validated everything
// - Your contributions have to pass sanitizers, fuzzer and Miri
// - Strictly follow the spec
// - The spec does not specify how you perform actions, in what order,
// just that the observable effects have to be performed in order and
// correctly.
// - Yes, we assume you run 64 bit CPU. Else ?conradluget a better CPU
// sorry 8 bit fans, HBVM won't run on your Speccy :(
unsafe {
match self.memory.prog_read::<u8>(self.pc as _) {
UN => {
self.bump_pc::<OpsN>();
return Err(VmRunError::Unreachable);
}
TX => {
self.bump_pc::<OpsN>();
return Ok(VmRunOk::End);
}
NOP => handler!(self, |OpsN()| ()),
ADD8 => self.binary_op(u8::wrapping_add),
ADD16 => self.binary_op(u16::wrapping_add),
ADD32 => self.binary_op(u32::wrapping_add),
ADD64 => self.binary_op(u64::wrapping_add),
SUB8 => self.binary_op(u8::wrapping_sub),
SUB16 => self.binary_op(u16::wrapping_sub),
SUB32 => self.binary_op(u32::wrapping_sub),
SUB64 => self.binary_op(u64::wrapping_sub),
MUL8 => self.binary_op(u8::wrapping_mul),
MUL16 => self.binary_op(u16::wrapping_mul),
MUL32 => self.binary_op(u32::wrapping_mul),
MUL64 => self.binary_op(u64::wrapping_mul),
AND => self.binary_op::<u64>(ops::BitAnd::bitand),
OR => self.binary_op::<u64>(ops::BitOr::bitor),
XOR => self.binary_op::<u64>(ops::BitXor::bitxor),
SLU8 => self.binary_op_shift::<u8>(u8::wrapping_shl),
SLU16 => self.binary_op_shift::<u16>(u16::wrapping_shl),
SLU32 => self.binary_op_shift::<u32>(u32::wrapping_shl),
SLU64 => self.binary_op_shift::<u64>(u64::wrapping_shl),
SRU8 => self.binary_op_shift::<u8>(u8::wrapping_shr),
SRU16 => self.binary_op_shift::<u16>(u16::wrapping_shr),
SRU32 => self.binary_op_shift::<u32>(u32::wrapping_shr),
SRU64 => self.binary_op_shift::<u64>(u64::wrapping_shr),
SRS8 => self.binary_op_shift::<i8>(i8::wrapping_shr),
SRS16 => self.binary_op_shift::<i16>(i16::wrapping_shr),
SRS32 => self.binary_op_shift::<i32>(i32::wrapping_shr),
SRS64 => self.binary_op_shift::<i64>(i64::wrapping_shr),
CMPU => handler!(self, |OpsRRR(tg, a0, a1)| self.cmp(
tg,
a0,
self.read_reg(a1).cast::<u64>()
)),
CMPS => handler!(self, |OpsRRR(tg, a0, a1)| self.cmp(
tg,
a0,
self.read_reg(a1).cast::<i64>()
)),
DIRU8 => self.dir::<u8>(),
DIRU16 => self.dir::<u16>(),
DIRU32 => self.dir::<u32>(),
DIRU64 => self.dir::<u64>(),
DIRS8 => self.dir::<i8>(),
DIRS16 => self.dir::<i16>(),
DIRS32 => self.dir::<i32>(),
DIRS64 => self.dir::<i64>(),
NEG => handler!(self, |OpsRR(tg, a0)| {
// Bit negation
self.write_reg(tg, !self.read_reg(a0).cast::<u64>())
}),
NOT => handler!(self, |OpsRR(tg, a0)| {
// Logical negation
self.write_reg(tg, u64::from(self.read_reg(a0).cast::<u64>() == 0));
}),
SXT8 => handler!(self, |OpsRR(tg, a0)| {
self.write_reg(tg, self.read_reg(a0).cast::<i8>() as i64)
}),
SXT16 => handler!(self, |OpsRR(tg, a0)| {
self.write_reg(tg, self.read_reg(a0).cast::<i16>() as i64)
}),
SXT32 => handler!(self, |OpsRR(tg, a0)| {
self.write_reg(tg, self.read_reg(a0).cast::<i32>() as i64)
}),
ADDI8 => self.binary_op_imm(u8::wrapping_add),
ADDI16 => self.binary_op_imm(u16::wrapping_add),
ADDI32 => self.binary_op_imm(u32::wrapping_add),
ADDI64 => self.binary_op_imm(u64::wrapping_add),
MULI8 => self.binary_op_imm(u8::wrapping_mul),
MULI16 => self.binary_op_imm(u16::wrapping_mul),
MULI32 => self.binary_op_imm(u32::wrapping_mul),
MULI64 => self.binary_op_imm(u64::wrapping_mul),
ANDI => self.binary_op_imm::<u64>(ops::BitAnd::bitand),
ORI => self.binary_op_imm::<u64>(ops::BitOr::bitor),
XORI => self.binary_op_imm::<u64>(ops::BitXor::bitxor),
SLUI8 => self.binary_op_ims::<u8>(u8::wrapping_shl),
SLUI16 => self.binary_op_ims::<u16>(u16::wrapping_shl),
SLUI32 => self.binary_op_ims::<u32>(u32::wrapping_shl),
SLUI64 => self.binary_op_ims::<u64>(u64::wrapping_shl),
SRUI8 => self.binary_op_ims::<u8>(u8::wrapping_shr),
SRUI16 => self.binary_op_ims::<u16>(u16::wrapping_shr),
SRUI32 => self.binary_op_ims::<u32>(u32::wrapping_shr),
SRUI64 => self.binary_op_ims::<u64>(u64::wrapping_shr),
SRSI8 => self.binary_op_ims::<i8>(i8::wrapping_shr),
SRSI16 => self.binary_op_ims::<i16>(i16::wrapping_shr),
SRSI32 => self.binary_op_ims::<i32>(i32::wrapping_shr),
SRSI64 => self.binary_op_ims::<i64>(i64::wrapping_shr),
CMPUI => handler!(self, |OpsRRD(tg, a0, imm)| { self.cmp(tg, a0, imm) }),
CMPSI => handler!(self, |OpsRRD(tg, a0, imm)| { self.cmp(tg, a0, imm as i64) }),
CP => handler!(self, |OpsRR(tg, a0)| self.write_reg(tg, self.read_reg(a0))),
SWA => handler!(self, |OpsRR(r0, r1)| {
// Swap registers
match (r0, r1) {
(0, 0) => (),
(dst, 0) | (0, dst) => self.write_reg(dst, 0_u64),
(r0, r1) => {
core::ptr::swap(
self.registers.get_unchecked_mut(usize::from(r0)),
self.registers.get_unchecked_mut(usize::from(r1)),
);
}
}
}),
LI8 => handler!(self, |OpsRB(tg, imm)| self.write_reg(tg, imm)),
LI16 => handler!(self, |OpsRH(tg, imm)| self.write_reg(tg, imm)),
LI32 => handler!(self, |OpsRW(tg, imm)| self.write_reg(tg, imm)),
LI64 => handler!(self, |OpsRD(tg, imm)| self.write_reg(tg, imm)),
LRA => handler!(self, |OpsRRO(tg, reg, off)| self.write_reg(
tg,
self.pcrel(off)
.wrapping_add(self.read_reg(reg).cast::<i64>())
.get(),
)),
// Load. If loading more than register size, continue on adjecent registers
LD => handler!(self, |OpsRRAH(dst, base, off, count)| self
.load(dst, base, off, count)?),
// Store. Same rules apply as to LD
ST => handler!(self, |OpsRRAH(dst, base, off, count)| self
.store(dst, base, off, count)?),
LDR => handler!(self, |OpsRROH(dst, base, off, count)| self.load(
dst,
base,
self.pcrel(off).get(),
count
)?),
STR => handler!(self, |OpsRROH(dst, base, off, count)| self.store(
dst,
base,
self.pcrel(off).get(),
count
)?),
BMC => {
// Block memory copy
match if let Some(copier) = &mut self.copier {
// There is some copier, poll.
copier.poll(&mut self.memory)
} else {
// There is none, make one!
let OpsRRH(src, dst, count) = self.decode();
self.copier = Some(BlockCopier::new(
Address::new(self.read_reg(src).cast()),
Address::new(self.read_reg(dst).cast()),
count as _,
));
self.copier
.as_mut()
.unwrap_unchecked() // SAFETY: We just assigned there
.poll(&mut self.memory)
} {
// We are done, shift program counter
core::task::Poll::Ready(Ok(())) => {
self.copier = None;
self.bump_pc::<OpsRRH>();
}
// Error, shift program counter (for consistency)
// and yield error
core::task::Poll::Ready(Err(e)) => {
return Err(e.into());
}
// Not done yet, proceed to next cycle
core::task::Poll::Pending => (),
}
}
BRC => handler!(self, |OpsRRB(src, dst, count)| {
// Block register copy
if src.checked_add(count).is_none() || dst.checked_add(count).is_none() {
return Err(VmRunError::RegOutOfBounds);
}
core::ptr::copy(
self.registers.get_unchecked(usize::from(src)),
self.registers.get_unchecked_mut(usize::from(dst)),
usize::from(count),
);
}),
JMP => {
let OpsO(off) = self.decode();
self.pc = self.pc.wrapping_add(off);
}
JAL => {
// Jump and link. Save PC after this instruction to
// specified register and jump to reg + relative offset.
let OpsRRO(save, reg, offset) = self.decode();
self.write_reg(save, self.pc.next::<OpsRRO>());
self.pc = self
.pcrel(offset)
.wrapping_add(self.read_reg(reg).cast::<i64>());
}
JALA => {
// Jump and link. Save PC after this instruction to
// specified register and jump to reg
let OpsRRA(save, reg, offset) = self.decode();
self.write_reg(save, self.pc.next::<OpsRRA>());
self.pc =
Address::new(self.read_reg(reg).cast::<u64>().wrapping_add(offset));
}
// Conditional jumps, jump only to immediates
JEQ => self.cond_jmp::<u64>(Ordering::Equal),
JNE => {
let OpsRRP(a0, a1, ja) = self.decode();
if self.read_reg(a0).cast::<u64>() != self.read_reg(a1).cast::<u64>() {
self.pc = self.pcrel(ja);
} else {
self.bump_pc::<OpsRRP>();
}
}
JLTS => self.cond_jmp::<u64>(Ordering::Less),
JGTS => self.cond_jmp::<u64>(Ordering::Greater),
JLTU => self.cond_jmp::<i64>(Ordering::Less),
JGTU => self.cond_jmp::<i64>(Ordering::Greater),
ECA => {
// So we don't get timer interrupt after ECALL
if TIMER_QUOTIENT != 0 {
self.timer = self.timer.wrapping_add(1);
}
self.bump_pc::<OpsN>();
return Ok(VmRunOk::Ecall);
}
EBP => {
self.bump_pc::<OpsN>();
return Ok(VmRunOk::Breakpoint);
}
FADD32 => self.binary_op::<f32>(ops::Add::add),
FADD64 => self.binary_op::<f64>(ops::Add::add),
FSUB32 => self.binary_op::<f32>(ops::Sub::sub),
FSUB64 => self.binary_op::<f64>(ops::Sub::sub),
FMUL32 => self.binary_op::<f32>(ops::Mul::mul),
FMUL64 => self.binary_op::<f64>(ops::Mul::mul),
FDIV32 => self.binary_op::<f32>(ops::Div::div),
FDIV64 => self.binary_op::<f64>(ops::Div::div),
FMA32 => self.fma::<f32>(),
FMA64 => self.fma::<f64>(),
FINV32 => handler!(self, |OpsRR(tg, reg)| self
.write_reg(tg, 1. / self.read_reg(reg).cast::<f32>())),
FINV64 => handler!(self, |OpsRR(tg, reg)| self
.write_reg(tg, 1. / self.read_reg(reg).cast::<f64>())),
FCMPLT32 => self.fcmp::<f32>(Ordering::Less),
FCMPLT64 => self.fcmp::<f64>(Ordering::Less),
FCMPGT32 => self.fcmp::<f32>(Ordering::Greater),
FCMPGT64 => self.fcmp::<f64>(Ordering::Greater),
ITF32 => handler!(self, |OpsRR(tg, reg)| self
.write_reg(tg, self.read_reg(reg).cast::<i64>() as f32)),
ITF64 => handler!(self, |OpsRR(tg, reg)| self
.write_reg(tg, self.read_reg(reg).cast::<i64>() as f64)),
FTI32 => handler!(self, |OpsRRB(tg, reg, mode)| self.write_reg(
tg,
crate::float::f32toint(
self.read_reg(reg).cast::<f32>(),
RoundingMode::try_from(mode)
.map_err(|()| VmRunError::InvalidOperand)?,
),
)),
FTI64 => handler!(self, |OpsRRB(tg, reg, mode)| self.write_reg(
tg,
crate::float::f64toint(
self.read_reg(reg).cast::<f64>(),
RoundingMode::try_from(mode)
.map_err(|()| VmRunError::InvalidOperand)?,
),
)),
FC32T64 => handler!(self, |OpsRR(tg, reg)| self
.write_reg(tg, self.read_reg(reg).cast::<f32>() as f64)),
FC64T32 => handler!(self, |OpsRRB(tg, reg, mode)| self.write_reg(
tg,
crate::float::conv64to32(
self.read_reg(reg).cast(),
RoundingMode::try_from(mode)
.map_err(|()| VmRunError::InvalidOperand)?,
),
)),
LRA16 => handler!(self, |OpsRRP(tg, reg, imm)| self.write_reg(
tg,
(self.pc + self.read_reg(reg).cast::<u64>() + imm + 3_u16).get(),
)),
LDR16 => handler!(self, |OpsRRPH(dst, base, off, count)| self.load(
dst,
base,
self.pcrel(off).get(),
count
)?),
STR16 => handler!(self, |OpsRRPH(dst, base, off, count)| self.store(
dst,
base,
self.pcrel(off).get(),
count
)?),
JMP16 => {
let OpsP(off) = self.decode();
self.pc = self.pcrel(off);
}
op => return Err(VmRunError::InvalidOpcode(op)),
}
}
if TIMER_QUOTIENT != 0 {
self.timer = self.timer.wrapping_add(1);
if self.timer % TIMER_QUOTIENT == 0 {
return Ok(VmRunOk::Timer);
}
}
}
}
/// Bump instruction pointer
#[inline(always)]
fn bump_pc<T: Copy>(&mut self) {
self.pc = self
.pc
.wrapping_add(core::mem::size_of::<T>())
.wrapping_add(1);
}
/// Decode instruction operands
#[inline(always)]
unsafe fn decode<T: Copy>(&mut self) -> T {
unsafe { self.memory.prog_read::<T>(self.pc + 1_u64) }
}
/// Load
#[inline(always)]
unsafe fn load(
&mut self,
dst: u8,
base: u8,
offset: u64,
count: u16,
) -> Result<(), VmRunError> {
let n: u8 = match dst {
0 => 1,
_ => 0,
};
unsafe {
self.memory.load(
self.ldst_addr_uber(dst, base, offset, count, n)?,
self.registers
.as_mut_ptr()
.add(usize::from(dst) + usize::from(n))
.cast(),
usize::from(count).saturating_sub(n.into()),
)
}?;
Ok(())
}
/// Store
#[inline(always)]
unsafe fn store(
&mut self,
dst: u8,
base: u8,
offset: u64,
count: u16,
) -> Result<(), VmRunError> {
unsafe {
self.memory.store(
self.ldst_addr_uber(dst, base, offset, count, 0)?,
self.registers.as_ptr().add(usize::from(dst)).cast(),
count.into(),
)
}?;
Ok(())
}
/// Three-way comparsion
#[inline(always)]
unsafe fn cmp<T: ValueVariant + Ord>(&mut self, to: u8, reg: u8, val: T) {
self.write_reg(to, self.read_reg(reg).cast::<T>().cmp(&val) as i64);
}
/// Perform binary operating over two registers
#[inline(always)]
unsafe fn binary_op<T: ValueVariant>(&mut self, op: impl Fn(T, T) -> T) {
let OpsRRR(tg, a0, a1) = unsafe { self.decode() };
self.write_reg(
tg,
op(self.read_reg(a0).cast::<T>(), self.read_reg(a1).cast::<T>()),
);
self.bump_pc::<OpsRRR>();
}
/// Perform binary operation over register and immediate
#[inline(always)]
unsafe fn binary_op_imm<T: ValueVariant>(&mut self, op: impl Fn(T, T) -> T) {
#[derive(Clone, Copy)]
#[repr(packed)]
struct OpsRRImm<I>(OpsRR, I);
let OpsRRImm::<T>(OpsRR(tg, reg), imm) = unsafe { self.decode() };
self.write_reg(tg, op(self.read_reg(reg).cast::<T>(), imm));
self.bump_pc::<OpsRRImm<T>>();
}
/// Perform binary operation over register and shift immediate
#[inline(always)]
unsafe fn binary_op_shift<T: ValueVariant>(&mut self, op: impl Fn(T, u32) -> T) {
let OpsRRR(tg, a0, a1) = unsafe { self.decode() };
self.write_reg(
tg,
op(
self.read_reg(a0).cast::<T>(),
self.read_reg(a1).cast::<u32>(),
),
);
self.bump_pc::<OpsRRR>();
}
/// Perform binary operation over register and shift immediate
#[inline(always)]
unsafe fn binary_op_ims<T: ValueVariant>(&mut self, op: impl Fn(T, u32) -> T) {
let OpsRRB(tg, reg, imm) = unsafe { self.decode() };
self.write_reg(tg, op(self.read_reg(reg).cast::<T>(), imm.into()));
self.bump_pc::<OpsRRB>();
}
/// Fused division-remainder
#[inline(always)]
unsafe fn dir<T: ValueVariant + CheckedDivRem>(&mut self) {
handler!(self, |OpsRRRR(td, tr, a0, a1)| {
let a0 = self.read_reg(a0).cast::<T>();
let a1 = self.read_reg(a1).cast::<T>();
if let Some(div) = a0.checked_div(a1) {
self.write_reg(td, div);
} else {
self.write_reg(td, -1_i64);
}
if let Some(rem) = a0.checked_rem(a1) {
self.write_reg(tr, rem);
} else {
self.write_reg(tr, a0);
}
});
}
/// Fused multiply-add
#[inline(always)]
unsafe fn fma<T>(&mut self)
where
T: ValueVariant + core::ops::Mul<Output = T> + core::ops::Add<Output = T>,
{
handler!(self, |OpsRRRR(tg, a0, a1, a2)| {
let a0 = self.read_reg(a0).cast::<T>();
let a1 = self.read_reg(a1).cast::<T>();
let a2 = self.read_reg(a2).cast::<T>();
self.write_reg(tg, a0 * a1 + a2)
});
}
/// Float comparsion
#[inline(always)]
unsafe fn fcmp<T: PartialOrd + ValueVariant>(&mut self, nan: Ordering) {
handler!(self, |OpsRRR(tg, a0, a1)| {
let a0 = self.read_reg(a0).cast::<T>();
let a1 = self.read_reg(a1).cast::<T>();
self.write_reg(tg, (a0.partial_cmp(&a1).unwrap_or(nan) as i8 + 1) as u8)
});
}
/// Calculate pc-relative address
#[inline(always)]
fn pcrel(&self, offset: impl AddressOp) -> Address {
self.pc.wrapping_add(offset)
}
/// Jump at `PC + #3` if ordering on `#0 <=> #1` is equal to expected
#[inline(always)]
unsafe fn cond_jmp<T: ValueVariant + Ord>(&mut self, expected: Ordering) {
let OpsRRP(a0, a1, ja) = unsafe { self.decode() };
if self
.read_reg(a0)
.cast::<T>()
.cmp(&self.read_reg(a1).cast::<T>())
== expected
{
self.pc = self.pcrel(ja);
} else {
self.bump_pc::<OpsRRP>();
}
}
/// Load / Store Address check-computation überfunction
#[inline(always)]
unsafe fn ldst_addr_uber(
&self,
dst: u8,
base: u8,
offset: u64,
size: u16,
adder: u8,
) -> Result<Address, VmRunError> {
let reg = dst.checked_add(adder).ok_or(VmRunError::RegOutOfBounds)?;
if usize::from(reg) * 8 + usize::from(size) > 2048 {
Err(VmRunError::RegOutOfBounds)
} else {
self.read_reg(base)
.cast::<u64>()
.checked_add(offset)
.and_then(|x| x.checked_add(adder.into()))
.ok_or(VmRunError::AddrOutOfBounds)
.map(Address::new)
}
}
}

Some files were not shown because too many files have changed in this diff Show More