encounter
/
ppc750cl
mirror of https://github.com/encounter/ppc750cl.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Rewrite the entire crate, add assembler 

- 10x faster disassembly performance
- Nearly feature-complete assembler
- `no_std` compatible
- Relicense to MIT/Apache-2.0
- Remove old crates (dol, flow-graph, etc)
- Remove Python bindings (for now, at least)
This commit is contained in:
Luke Street 2024-03-14 00:52:36 -06:00
parent f6e15052b1
commit c4af15ddc2
39 changed files with 18608 additions and 11531 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

580
Cargo.lock generated
View File

@ -2,13 +2,19 @@
# It is not intended for manual editing.
version = 3
[[package]]
name = "anyhow"
version = "1.0.80"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "5ad32ce52e4161730f7098c077cd2ed6229b5804ccf99e5366be1ab72a98b4e1"
[[package]]
name = "atty"
version = "0.2.14"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "d9b39be18770d11421cdb1b9947a45dd3f37e93092cbf377614828a319d5fee8"
dependencies = [
"hermit-abi",
"hermit-abi 0.1.19",
"libc",
"winapi",
]
@ -19,100 +25,72 @@ version = "1.1.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "d468802bab17cbc0cc575e9b053f41e72aa36bfa6b7f55e3529ffa43161b97fa"
[[package]]
name = "bincode"
version = "1.3.3"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "b1f45e9417d87227c7a56d22e471c6206462cba514c7590c09aff4cf6d1ddcad"
dependencies = [
"serde",
]
[[package]]
name = "bitflags"
version = "1.3.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "bef38d45163c2f1dde094a7dfd33ccf595c92905c8f8f4fdc18d06fb1037718a"
[[package]]
name = "cfg-if"
version = "1.0.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "baf1de4339761588bc0619e3cbc0120ee582ebb74b53b4efbf79117bd2da40fd"
[[package]]
name = "clap"
version = "3.1.8"
version = "3.2.25"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "71c47df61d9e16dc010b55dba1952a57d8c215dbb533fd13cdd13369aac73b1c"
checksum = "4ea181bf566f71cb9a5d17a59e1871af638180a18fb0035c92ae62b705207123"
dependencies = [
"atty",
"bitflags",
"indexmap",
"os_str_bytes",
"clap_lex",
"indexmap 1.9.3",
"strsim",
"termcolor",
"textwrap",
]
[[package]]
name = "ctor"
version = "0.1.22"
name = "clap_lex"
version = "0.2.4"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "f877be4f7c9f246b183111634f75baa039715e3f46ce860677d3b19a69fb229c"
checksum = "2850f2f5a82cbf437dd5af4d49848fbdfc27c157c3d010345776f952765261c5"
dependencies = [
"quote",
"syn",
"os_str_bytes",
]
[[package]]
name = "dol"
version = "0.1.0"
name = "colored"
version = "2.1.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "cbf2150cce219b664a8a70df7a1f933836724b503f8a413af9365b4dcc4d90b8"
dependencies = [
"bincode",
"serde",
"thiserror",
"lazy_static",
"windows-sys",
]
[[package]]
name = "either"
version = "1.6.1"
name = "deranged"
version = "0.3.11"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "e78d4f1cc4ae33bbfc157ed5d5a5ef3bc29227303d595861deb238fcec4e9457"
[[package]]
name = "fixedbitset"
version = "0.4.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "279fb028e20b3c4c320317955b77c5e0c9701f05a1d309905d6fc702cdc5053e"
[[package]]
name = "getrandom"
version = "0.2.6"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "9be70c98951c83b8d2f8f60d7065fa6d5146873094452a1008da8c2f1e4205ad"
checksum = "b42b6fa04a440b495c8b04d0e71b707c585f83cb9cb28cf8cd0d976c315e31b4"
dependencies = [
"cfg-if",
"libc",
"wasi",
"powerfmt",
]
[[package]]
name = "ghost"
version = "0.1.2"
name = "equivalent"
version = "1.0.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "1a5bcf1bbeab73aa4cf2fde60a846858dc036163c7c33bec309f8d17de785479"
dependencies = [
"proc-macro2",
"quote",
"syn",
]
checksum = "5443807d6dff69373d433ab9ef5378ad8df50ca6298caf15de6e52e24aaf54d5"
[[package]]
name = "hashbrown"
version = "0.11.2"
version = "0.12.3"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "ab5ef0d4909ef3724cc8cce6ccc8572c5c817592e9285f5464f8e86f8bd3726e"
checksum = "8a9ee70c43aaf417c914396645a0fa852624801b24ebb7ae78fe8272889ac888"
[[package]]
name = "hashbrown"
version = "0.14.3"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "290f1a1d9242c78d09ce40a5e87e7554ee637af1351968159f4952f028f75604"
[[package]]
name = "hermit-abi"
@ -124,181 +102,153 @@ dependencies = [
]
[[package]]
name = "indexmap"
version = "1.8.1"
name = "hermit-abi"
version = "0.3.9"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "0f647032dfaa1f8b6dc29bd3edb7bbef4861b8b8007ebb118d6db284fd59f6ee"
checksum = "d231dfb89cfffdbc30e7fc41579ed6066ad03abda9e567ccafae602b97ec5024"
[[package]]
name = "indexmap"
version = "1.9.3"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "bd070e393353796e801d209ad339e89596eb4c8d430d18ede6a1cced8fafbd99"
dependencies = [
"autocfg",
"hashbrown",
"hashbrown 0.12.3",
]
[[package]]
name = "indoc"
version = "1.0.4"
name = "indexmap"
version = "2.2.5"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "e7906a9fababaeacb774f72410e497a1d18de916322e33797bb2cd29baa23c9e"
checksum = "7b0b929d511467233429c45a44ac1dcaa21ba0f5ba11e4879e6ed28ddb4f9df4"
dependencies = [
"unindent",
"equivalent",
"hashbrown 0.14.3",
]
[[package]]
name = "instant"
version = "0.1.12"
name = "itoa"
version = "1.0.10"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "7a5bbe824c507c5da5956355e86a746d82e0e1464f65d862cc5e71da70e94b2c"
dependencies = [
"cfg-if",
]
checksum = "b1a46d1a171d865aa5f83f92695765caa047a9b4cbae2cbf37dbd613a793fd4c"
[[package]]
name = "inventory"
version = "0.2.2"
name = "lazy_static"
version = "1.4.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "ce6b5d8c669bfbad811d95ddd7a1c6cf9cfdbf2777e59928b6f3fa8ff54f72a0"
dependencies = [
"ctor",
"ghost",
]
[[package]]
name = "itertools"
version = "0.10.3"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "a9a9d19fa1e79b6215ff29b9d6880b706147f16e9b1dbb1e4e5947b5b02bc5e3"
dependencies = [
"either",
]
checksum = "e2abad23fbc42b3700f2f279844dc832adb2b2eb069b2df918f455c4e18cc646"
[[package]]
name = "libc"
version = "0.2.122"
version = "0.2.153"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "ec647867e2bf0772e28c8bcde4f0d19a9216916e890543b5a03ed8ef27b8f259"
checksum = "9c198f91728a82281a64e1f4f9eeb25d82cb32a5de251c6bd1b5154d63a8e7bd"
[[package]]
name = "linked-hash-map"
version = "0.5.4"
name = "log"
version = "0.4.21"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "7fb9b38af92608140b86b693604b9ffcc5824240a484d1ecd4795bacb2fe88f3"
checksum = "90ed8c1e510134f979dbc4f070f87d4313098b704861a105fe34231c70a3901c"
[[package]]
name = "lock_api"
version = "0.4.7"
name = "num-conv"
version = "0.1.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "327fa5b6a6940e4699ec49a9beae1ea4845c6bab9314e4f84ac68742139d8c53"
dependencies = [
"autocfg",
"scopeguard",
]
[[package]]
name = "memchr"
version = "2.4.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "308cc39be01b73d0d18f82a0e7b2a3df85245f84af96fdddc5d202d27e47b86a"
checksum = "51d515d32fb182ee37cda2ccdcb92950d6a3c2893aa280e540671c2cd0f3b1d9"
[[package]]
name = "num-traits"
version = "0.2.14"
version = "0.2.18"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "9a64b1ec5cda2586e284722486d802acf1f7dbdc623e2bfc57e65ca1cd099290"
checksum = "da0df0e5185db44f69b44f26786fe401b6c293d1907744beaa7fa62b2e5a517a"
dependencies = [
"autocfg",
]
[[package]]
name = "num_cpus"
version = "1.13.1"
version = "1.16.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "19e64526ebdee182341572e50e9ad03965aa510cd94427a4549448f285e957a1"
checksum = "4161fcb6d602d4d2081af7c3a45852d875a03dd337a6bfdd6e06407b61342a43"
dependencies = [
"hermit-abi",
"hermit-abi 0.3.9",
"libc",
]
[[package]]
name = "once_cell"
version = "1.10.0"
name = "num_threads"
version = "0.1.7"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "87f3e037eac156d1775da914196f0f37741a274155e34a0b7e427c35d2a2ecb9"
checksum = "5c7398b9c8b70908f6371f47ed36737907c87c52af34c268fed0bf0ceb92ead9"
dependencies = [
"libc",
]
[[package]]
name = "os_str_bytes"
version = "6.0.0"
version = "6.6.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "8e22443d1643a904602595ba1cd8f7d896afe56d26712531c5ff73a15b2fbf64"
dependencies = [
"memchr",
]
checksum = "e2355d85b9a3786f481747ced0e0ff2ba35213a1f9bd406ed906554d7af805a1"
[[package]]
name = "parking_lot"
name = "phf"
version = "0.11.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "7d17b78036a60663b797adeaee46f5c9dfebb86948d1255007a1d6be0271ff99"
checksum = "ade2d8b8f33c7333b51bcf0428d37e217e9f32192ae4772156f65063b8ce03dc"
dependencies = [
"instant",
"lock_api",
"parking_lot_core",
"phf_shared",
]
[[package]]
name = "parking_lot_core"
version = "0.8.5"
name = "phf_codegen"
version = "0.11.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "d76e8e1493bcac0d2766c42737f34458f1c8c50c0d23bcb24ea953affb273216"
checksum = "e8d39688d359e6b34654d328e262234662d16cc0f60ec8dcbe5e718709342a5a"
dependencies = [
"cfg-if",
"instant",
"libc",
"redox_syscall",
"smallvec",
"winapi",
"phf_generator",
"phf_shared",
]
[[package]]
name = "parse_int"
version = "0.6.0"
name = "phf_generator"
version = "0.11.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "2d695b79916a2c08bcff7be7647ab60d1402885265005a6658ffe6d763553c5a"
checksum = "48e4cc64c2ad9ebe670cb8fd69dd50ae301650392e81c05f9bfcb2d5bdbc24b0"
dependencies = [
"num-traits",
"phf_shared",
"rand",
]
[[package]]
name = "petgraph"
version = "0.6.0"
name = "phf_shared"
version = "0.11.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "4a13a2fa9d0b63e5f22328828741e523766fff0ee9e779316902290dff3f824f"
checksum = "90fcb95eef784c2ac79119d1dd819e162b5da872ce6f3c3abe1e8ca1c082f72b"
dependencies = [
"fixedbitset",
"indexmap",
"siphasher",
]
[[package]]
name = "powerfmt"
version = "0.2.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "439ee305def115ba05938db6eb1644ff94165c5ab5e9420d1c1bcedbba909391"
[[package]]
name = "ppc750cl"
version = "0.2.0"
dependencies = [
"num-traits",
"serde",
]
version = "0.3.0"
[[package]]
name = "ppc750cl-flow-graph"
version = "0.2.0"
name = "ppc750cl-asm"
version = "0.3.0"
dependencies = [
"clap",
"dol",
"itertools",
"parse_int",
"petgraph",
"ppc750cl",
"phf",
]
[[package]]
name = "ppc750cl-fuzz"
version = "0.2.0"
version = "0.3.0"
dependencies = [
"clap",
"num_cpus",
@ -307,113 +257,46 @@ dependencies = [
[[package]]
name = "ppc750cl-genisa"
version = "0.2.0"
version = "0.3.0"
dependencies = [
"itertools",
"anyhow",
"log",
"num-traits",
"phf",
"phf_codegen",
"prettyplease",
"proc-macro2",
"quote",
"serde",
"serde_yaml",
"simple_logger",
"syn",
]
[[package]]
name = "ppc750cl-py"
version = "0.2.0"
dependencies = [
"ppc750cl",
"pyo3",
]
[[package]]
name = "ppc750cl-rand"
version = "0.2.0"
dependencies = [
"ppc750cl",
"rand_core",
"sfmt",
]
[[package]]
name = "ppv-lite86"
name = "prettyplease"
version = "0.2.16"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "eb9f9e6e233e5c4a35559a617bf40a4ec447db2e84c20b55a6f83167b7e57872"
checksum = "a41cf62165e97c7f814d2221421dbb9afcbcdb0a88068e5ea206e19951c2cbb5"
dependencies = [
"proc-macro2",
"syn",
]
[[package]]
name = "proc-macro2"
version = "1.0.37"
version = "1.0.78"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "ec757218438d5fda206afc041538b2f6d889286160d649a86a24d37e1235afd1"
checksum = "e2422ad645d89c99f8f3e6b88a9fdeca7fabeac836b1002371c4367c8f984aae"
dependencies = [
"unicode-xid",
]
[[package]]
name = "pyo3"
version = "0.16.3"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "6b3e99c4c3e790e4fc365b42b70c1f7801f42eadc4ea648fa327e6f5ca29f215"
dependencies = [
"cfg-if",
"indoc",
"inventory",
"libc",
"parking_lot",
"pyo3-build-config",
"pyo3-ffi",
"pyo3-macros",
"unindent",
]
[[package]]
name = "pyo3-build-config"
version = "0.16.3"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "2486b96281859ff0a3929ba6467b13751627b974f7137362db38e2bed14b2094"
dependencies = [
"once_cell",
"target-lexicon",
]
[[package]]
name = "pyo3-ffi"
version = "0.16.3"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "dd9de1d94557751599f8bd321f10e6c1ef2801067acb58c91138deef2ae83a17"
dependencies = [
"libc",
"pyo3-build-config",
]
[[package]]
name = "pyo3-macros"
version = "0.16.3"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "0b9584049129b1cfb615243391a6345c726690271ae195ffd6aa3766177296aa"
dependencies = [
"proc-macro2",
"pyo3-macros-backend",
"quote",
"syn",
]
[[package]]
name = "pyo3-macros-backend"
version = "0.16.3"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "b6c4717e6a55c51a9958eda1f5481ff7f62cccd21f45309c10e4731cb7198dbc"
dependencies = [
"proc-macro2",
"quote",
"syn",
"unicode-ident",
]
[[package]]
name = "quote"
version = "1.0.17"
version = "1.0.35"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "632d02bff7f874a36f33ea8bb416cd484b90cc66c1194b1a1110d067a7013f58"
checksum = "291ec9ab5efd934aaf503a6466c5d5251535d108ee747472c3977cc5acc868ef"
dependencies = [
"proc-macro2",
]
@ -424,65 +307,35 @@ version = "0.8.5"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "34af8d1a0e25924bc5b7c43c079c942339d8f0a8b57c39049bef581b46327404"
dependencies = [
"libc",
"rand_chacha",
"rand_core",
]
[[package]]
name = "rand_chacha"
version = "0.3.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "e6c10a63a0fa32252be49d21e7709d4d4baf8d231c2dbce1eaa8141b9b127d88"
dependencies = [
"ppv-lite86",
"rand_core",
]
[[package]]
name = "rand_core"
version = "0.6.3"
version = "0.6.4"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "d34f1408f55294453790c48b2f1ebbb1c5b4b7563eb1f418bcfcfdbb06ebb4e7"
dependencies = [
"getrandom",
]
[[package]]
name = "redox_syscall"
version = "0.2.13"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "62f25bc4c7e55e0b0b7a1d43fb893f4fa1361d0abe38b9ce4f323c2adfe6ef42"
dependencies = [
"bitflags",
]
checksum = "ec0be4795e2f6a28069bec0b5ff3e2ac9bafc99e6a9a7dc3547996c5c816922c"
[[package]]
name = "ryu"
version = "1.0.9"
version = "1.0.17"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "73b4b750c782965c211b42f022f59af1fbceabdd026623714f104152f1ec149f"
[[package]]
name = "scopeguard"
version = "1.1.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "d29ab0c6d3fc0ee92fe66e2d99f700eab17a8d57d1c1d3b748380fb20baa78cd"
checksum = "e86697c916019a8588c99b5fac3cead74ec0b4b819707a682fd4d23fa0ce1ba1"
[[package]]
name = "serde"
version = "1.0.136"
version = "1.0.197"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "ce31e24b01e1e524df96f1c2fdd054405f8d7376249a5110886fb4b658484789"
checksum = "3fb1c873e1b9b056a4dc4c0c198b24c3ffa059243875552b2bd0933b1aee4ce2"
dependencies = [
"serde_derive",
]
[[package]]
name = "serde_derive"
version = "1.0.136"
version = "1.0.197"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "08597e7152fcd306f41838ed3e37be9eaeed2b61c42e2117266a554fab4662f9"
checksum = "7eb0b34b42edc17f6b7cac84a52a1c5f0e1bb2227e997ca9011ea3dd34e8610b"
dependencies = [
"proc-macro2",
"quote",
@ -491,31 +344,34 @@ dependencies = [
[[package]]
name = "serde_yaml"
version = "0.8.23"
version = "0.9.32"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "a4a521f2940385c165a24ee286aa8599633d162077a54bdcae2a6fd5a7bfa7a0"
checksum = "8fd075d994154d4a774f95b51fb96bdc2832b0ea48425c92546073816cda1f2f"
dependencies = [
"indexmap",
"indexmap 2.2.5",
"itoa",
"ryu",
"serde",
"yaml-rust",
"unsafe-libyaml",
]
[[package]]
name = "sfmt"
version = "0.7.0"
name = "simple_logger"
version = "4.3.3"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "e389a3c1536438f85612667cd992dfb7169f60784252342278458e90d37c7565"
checksum = "8e7e46c8c90251d47d08b28b8a419ffb4aede0f87c2eea95e17d1d5bacbf3ef1"
dependencies = [
"rand",
"rand_core",
"colored",
"log",
"time",
"windows-sys",
]
[[package]]
name = "smallvec"
version = "1.8.0"
name = "siphasher"
version = "0.3.11"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "f2dd574626839106c320a323308629dcb1acfc96e32a8cba364ddc61ac23ee83"
checksum = "38b58827f4464d87d377d175e90bf58eb00fd8716ff0a62f80356b5e61555d0d"
[[package]]
name = "strsim"
@ -525,73 +381,74 @@ checksum = "73473c0e59e6d5812c5dfe2a064a6444949f089e20eec9a2e5506596494e4623"
[[package]]
name = "syn"
version = "1.0.91"
version = "2.0.52"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "b683b2b825c8eef438b77c36a06dc262294da3d5a5813fac20da149241dcd44d"
checksum = "b699d15b36d1f02c3e7c69f8ffef53de37aefae075d8488d4ba1a7788d574a07"
dependencies = [
"proc-macro2",
"quote",
"unicode-xid",
"unicode-ident",
]
[[package]]
name = "target-lexicon"
version = "0.12.3"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "d7fa7e55043acb85fca6b3c01485a2eeb6b69c5d21002e273c79e465f43b7ac1"
[[package]]
name = "termcolor"
version = "1.1.3"
version = "1.4.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "bab24d30b911b2376f3a13cc2cd443142f0c81dda04c118693e35b3835757755"
checksum = "06794f8f6c5c898b3275aebefa6b8a1cb24cd2c6c79397ab15774837a0bc5755"
dependencies = [
"winapi-util",
]
[[package]]
name = "textwrap"
version = "0.15.0"
version = "0.16.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "b1141d4d61095b28419e22cb0bbf02755f5e54e0526f97f1e3d1d160e60885fb"
checksum = "23d434d3f8967a09480fb04132ebe0a3e088c173e6d0ee7897abbdf4eab0f8b9"
[[package]]
name = "thiserror"
version = "1.0.30"
name = "time"
version = "0.3.34"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "854babe52e4df1653706b98fcfc05843010039b406875930a70e4d9644e5c417"
checksum = "c8248b6521bb14bc45b4067159b9b6ad792e2d6d754d6c41fb50e29fefe38749"
dependencies = [
"thiserror-impl",
"deranged",
"itoa",
"libc",
"num-conv",
"num_threads",
"powerfmt",
"serde",
"time-core",
"time-macros",
]
[[package]]
name = "thiserror-impl"
version = "1.0.30"
name = "time-core"
version = "0.1.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "aa32fd3f627f367fe16f893e2597ae3c05020f8bba2666a4e6ea73d377e5714b"
checksum = "ef927ca75afb808a4d64dd374f00a2adf8d0fcff8e7b184af886c3c87ec4a3f3"
[[package]]
name = "time-macros"
version = "0.2.17"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "7ba3a3ef41e6672a2f0f001392bb5dcd3ff0a9992d618ca761a11c3121547774"
dependencies = [
"proc-macro2",
"quote",
"syn",
"num-conv",
"time-core",
]
[[package]]
name = "unicode-xid"
version = "0.2.2"
name = "unicode-ident"
version = "1.0.12"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "8ccb82d61f80a663efe1f787a51b16b5a51e3314d6ac365b08639f52387b33f3"
checksum = "3354b9ac3fae1ff6755cb6db53683adb661634f67557942dea4facebec0fee4b"
[[package]]
name = "unindent"
version = "0.1.8"
name = "unsafe-libyaml"
version = "0.2.10"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "514672a55d7380da379785a4d70ca8386c8883ff7eaae877be4d2081cebe73d8"
[[package]]
name = "wasi"
version = "0.10.2+wasi-snapshot-preview1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "fd6fbd9a79829dd1ad0cc20627bf1ed606756a7f77edff7b66b7064f9cb327c6"
checksum = "ab4c90930b95a82d00dc9e9ac071b4991924390d46cbd0dfe566148667605e4b"
[[package]]
name = "winapi"
@ -611,9 +468,9 @@ checksum = "ac3b87c63620426dd9b991e5ce0329eff545bccbbb34f3be09ff6fb6ab51b7b6"
[[package]]
name = "winapi-util"
version = "0.1.5"
version = "0.1.6"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "70ec6ce85bb158151cae5e5c87f95a8e97d2c0c4b001223f33a334e3ce5de178"
checksum = "f29e6f9198ba0d26b4c9f07dbe6f9ed633e1f3d5b8b414090084349e46a52596"
dependencies = [
"winapi",
]
@ -625,10 +482,67 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "712e227841d057c1ee1cd2fb22fa7e5a5461ae8e48fa2ca79ec42cfc1931183f"
[[package]]
name = "yaml-rust"
version = "0.4.5"
name = "windows-sys"
version = "0.48.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "56c1936c4cc7a1c9ab21a1ebb602eb942ba868cbd44a99cb7cdc5892335e1c85"
checksum = "677d2418bec65e3338edb076e806bc1ec15693c5d0104683f2efe857f61056a9"
dependencies = [
"linked-hash-map",
"windows-targets",
]
[[package]]
name = "windows-targets"
version = "0.48.5"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "9a2fa6e2155d7247be68c096456083145c183cbbbc2764150dda45a87197940c"
dependencies = [
"windows_aarch64_gnullvm",
"windows_aarch64_msvc",
"windows_i686_gnu",
"windows_i686_msvc",
"windows_x86_64_gnu",
"windows_x86_64_gnullvm",
"windows_x86_64_msvc",
]
[[package]]
name = "windows_aarch64_gnullvm"
version = "0.48.5"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "2b38e32f0abccf9987a4e3079dfb67dcd799fb61361e53e2882c3cbaf0d905d8"
[[package]]
name = "windows_aarch64_msvc"
version = "0.48.5"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "dc35310971f3b2dbbf3f0690a219f40e2d9afcf64f9ab7cc1be722937c26b4bc"
[[package]]
name = "windows_i686_gnu"
version = "0.48.5"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "a75915e7def60c94dcef72200b9a8e58e5091744960da64ec734a6c6e9b3743e"
[[package]]
name = "windows_i686_msvc"
version = "0.48.5"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "8f55c233f70c4b27f66c523580f78f1004e8b5a8b659e05a4eb49d4166cca406"
[[package]]
name = "windows_x86_64_gnu"
version = "0.48.5"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "53d40abd2583d23e4718fddf1ebec84dbff8381c07cae67ff7768bbf19c6718e"
[[package]]
name = "windows_x86_64_gnullvm"
version = "0.48.5"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "0b7b52767868a23d5bab768e390dc5f5c55825b6d30b86c844ff2dc7414044cc"
[[package]]
name = "windows_x86_64_msvc"
version = "0.48.5"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "ed94fce61571a4006852b7389a063ab983c02eb1bb37b47f8272ce92d06d9538"

18
Cargo.toml
View File

@ -1,11 +1,11 @@
[workspace]
members = ["asm", "disasm", "fuzz", "genisa"]
resolver = "2"
members = [
"disasm",
"disasm-py",
"dol",
"fuzz",
"genisa",
"flow-graph",
"rand",
]
[profile.release]
panic = "abort"
opt-level = "z"
[profile.release-lto]
inherits = "release"
lto = "thin"

674
LICENSE
View File

@ -1,674 +0,0 @@
GNU GENERAL PUBLIC LICENSE
Version 3, 29 June 2007
Copyright (C) 2007 Free Software Foundation, Inc. <https://fsf.org/>
Everyone is permitted to copy and distribute verbatim copies
of this license document, but changing it is not allowed.
Preamble
The GNU General Public License is a free, copyleft license for
software and other kinds of works.
The licenses for most software and other practical works are designed
to take away your freedom to share and change the works. By contrast,
the GNU General Public License is intended to guarantee your freedom to
share and change all versions of a program--to make sure it remains free
software for all its users. We, the Free Software Foundation, use the
GNU General Public License for most of our software; it applies also to
any other work released this way by its authors. You can apply it to
your programs, too.
When we speak of free software, we are referring to freedom, not
price. Our General Public Licenses are designed to make sure that you
have the freedom to distribute copies of free software (and charge for
them if you wish), that you receive source code or can get it if you
want it, that you can change the software or use pieces of it in new
free programs, and that you know you can do these things.
To protect your rights, we need to prevent others from denying you
these rights or asking you to surrender the rights. Therefore, you have
certain responsibilities if you distribute copies of the software, or if
you modify it: responsibilities to respect the freedom of others.
For example, if you distribute copies of such a program, whether
gratis or for a fee, you must pass on to the recipients the same
freedoms that you received. You must make sure that they, too, receive
or can get the source code. And you must show them these terms so they
know their rights.
Developers that use the GNU GPL protect your rights with two steps:
(1) assert copyright on the software, and (2) offer you this License
giving you legal permission to copy, distribute and/or modify it.
For the developers' and authors' protection, the GPL clearly explains
that there is no warranty for this free software. For both users' and
authors' sake, the GPL requires that modified versions be marked as
changed, so that their problems will not be attributed erroneously to
authors of previous versions.
Some devices are designed to deny users access to install or run
modified versions of the software inside them, although the manufacturer
can do so. This is fundamentally incompatible with the aim of
protecting users' freedom to change the software. The systematic
pattern of such abuse occurs in the area of products for individuals to
use, which is precisely where it is most unacceptable. Therefore, we
have designed this version of the GPL to prohibit the practice for those
products. If such problems arise substantially in other domains, we
stand ready to extend this provision to those domains in future versions
of the GPL, as needed to protect the freedom of users.
Finally, every program is threatened constantly by software patents.
States should not allow patents to restrict development and use of
software on general-purpose computers, but in those that do, we wish to
avoid the special danger that patents applied to a free program could
make it effectively proprietary. To prevent this, the GPL assures that
patents cannot be used to render the program non-free.
The precise terms and conditions for copying, distribution and
modification follow.
TERMS AND CONDITIONS
0. Definitions.
"This License" refers to version 3 of the GNU General Public License.
"Copyright" also means copyright-like laws that apply to other kinds of
works, such as semiconductor masks.
"The Program" refers to any copyrightable work licensed under this
License. Each licensee is addressed as "you". "Licensees" and
"recipients" may be individuals or organizations.
To "modify" a work means to copy from or adapt all or part of the work
in a fashion requiring copyright permission, other than the making of an
exact copy. The resulting work is called a "modified version" of the
earlier work or a work "based on" the earlier work.
A "covered work" means either the unmodified Program or a work based
on the Program.
To "propagate" a work means to do anything with it that, without
permission, would make you directly or secondarily liable for
infringement under applicable copyright law, except executing it on a
computer or modifying a private copy. Propagation includes copying,
distribution (with or without modification), making available to the
public, and in some countries other activities as well.
To "convey" a work means any kind of propagation that enables other
parties to make or receive copies. Mere interaction with a user through
a computer network, with no transfer of a copy, is not conveying.
An interactive user interface displays "Appropriate Legal Notices"
to the extent that it includes a convenient and prominently visible
feature that (1) displays an appropriate copyright notice, and (2)
tells the user that there is no warranty for the work (except to the
extent that warranties are provided), that licensees may convey the
work under this License, and how to view a copy of this License. If
the interface presents a list of user commands or options, such as a
menu, a prominent item in the list meets this criterion.
1. Source Code.
The "source code" for a work means the preferred form of the work
for making modifications to it. "Object code" means any non-source
form of a work.
A "Standard Interface" means an interface that either is an official
standard defined by a recognized standards body, or, in the case of
interfaces specified for a particular programming language, one that
is widely used among developers working in that language.
The "System Libraries" of an executable work include anything, other
than the work as a whole, that (a) is included in the normal form of
packaging a Major Component, but which is not part of that Major
Component, and (b) serves only to enable use of the work with that
Major Component, or to implement a Standard Interface for which an
implementation is available to the public in source code form. A
"Major Component", in this context, means a major essential component
(kernel, window system, and so on) of the specific operating system
(if any) on which the executable work runs, or a compiler used to
produce the work, or an object code interpreter used to run it.
The "Corresponding Source" for a work in object code form means all
the source code needed to generate, install, and (for an executable
work) run the object code and to modify the work, including scripts to
control those activities. However, it does not include the work's
System Libraries, or general-purpose tools or generally available free
programs which are used unmodified in performing those activities but
which are not part of the work. For example, Corresponding Source
includes interface definition files associated with source files for
the work, and the source code for shared libraries and dynamically
linked subprograms that the work is specifically designed to require,
such as by intimate data communication or control flow between those
subprograms and other parts of the work.
The Corresponding Source need not include anything that users
can regenerate automatically from other parts of the Corresponding
Source.
The Corresponding Source for a work in source code form is that
same work.
2. Basic Permissions.
All rights granted under this License are granted for the term of
copyright on the Program, and are irrevocable provided the stated
conditions are met. This License explicitly affirms your unlimited
permission to run the unmodified Program. The output from running a
covered work is covered by this License only if the output, given its
content, constitutes a covered work. This License acknowledges your
rights of fair use or other equivalent, as provided by copyright law.
You may make, run and propagate covered works that you do not
convey, without conditions so long as your license otherwise remains
in force. You may convey covered works to others for the sole purpose
of having them make modifications exclusively for you, or provide you
with facilities for running those works, provided that you comply with
the terms of this License in conveying all material for which you do
not control copyright. Those thus making or running the covered works
for you must do so exclusively on your behalf, under your direction
and control, on terms that prohibit them from making any copies of
your copyrighted material outside their relationship with you.
Conveying under any other circumstances is permitted solely under
the conditions stated below. Sublicensing is not allowed; section 10
makes it unnecessary.
3. Protecting Users' Legal Rights From Anti-Circumvention Law.
No covered work shall be deemed part of an effective technological
measure under any applicable law fulfilling obligations under article
11 of the WIPO copyright treaty adopted on 20 December 1996, or
similar laws prohibiting or restricting circumvention of such
measures.
When you convey a covered work, you waive any legal power to forbid
circumvention of technological measures to the extent such circumvention
is effected by exercising rights under this License with respect to
the covered work, and you disclaim any intention to limit operation or
modification of the work as a means of enforcing, against the work's
users, your or third parties' legal rights to forbid circumvention of
technological measures.
4. Conveying Verbatim Copies.
You may convey verbatim copies of the Program's source code as you
receive it, in any medium, provided that you conspicuously and
appropriately publish on each copy an appropriate copyright notice;
keep intact all notices stating that this License and any
non-permissive terms added in accord with section 7 apply to the code;
keep intact all notices of the absence of any warranty; and give all
recipients a copy of this License along with the Program.
You may charge any price or no price for each copy that you convey,
and you may offer support or warranty protection for a fee.
5. Conveying Modified Source Versions.
You may convey a work based on the Program, or the modifications to
produce it from the Program, in the form of source code under the
terms of section 4, provided that you also meet all of these conditions:
a) The work must carry prominent notices stating that you modified
it, and giving a relevant date.
b) The work must carry prominent notices stating that it is
released under this License and any conditions added under section
7. This requirement modifies the requirement in section 4 to
"keep intact all notices".
c) You must license the entire work, as a whole, under this
License to anyone who comes into possession of a copy. This
License will therefore apply, along with any applicable section 7
additional terms, to the whole of the work, and all its parts,
regardless of how they are packaged. This License gives no
permission to license the work in any other way, but it does not
invalidate such permission if you have separately received it.
d) If the work has interactive user interfaces, each must display
Appropriate Legal Notices; however, if the Program has interactive
interfaces that do not display Appropriate Legal Notices, your
work need not make them do so.
A compilation of a covered work with other separate and independent
works, which are not by their nature extensions of the covered work,
and which are not combined with it such as to form a larger program,
in or on a volume of a storage or distribution medium, is called an
"aggregate" if the compilation and its resulting copyright are not
used to limit the access or legal rights of the compilation's users
beyond what the individual works permit. Inclusion of a covered work
in an aggregate does not cause this License to apply to the other
parts of the aggregate.
6. Conveying Non-Source Forms.
You may convey a covered work in object code form under the terms
of sections 4 and 5, provided that you also convey the
machine-readable Corresponding Source under the terms of this License,
in one of these ways:
a) Convey the object code in, or embodied in, a physical product
(including a physical distribution medium), accompanied by the
Corresponding Source fixed on a durable physical medium
customarily used for software interchange.
b) Convey the object code in, or embodied in, a physical product
(including a physical distribution medium), accompanied by a
written offer, valid for at least three years and valid for as
long as you offer spare parts or customer support for that product
model, to give anyone who possesses the object code either (1) a
copy of the Corresponding Source for all the software in the
product that is covered by this License, on a durable physical
medium customarily used for software interchange, for a price no
more than your reasonable cost of physically performing this
conveying of source, or (2) access to copy the
Corresponding Source from a network server at no charge.
c) Convey individual copies of the object code with a copy of the
written offer to provide the Corresponding Source. This
alternative is allowed only occasionally and noncommercially, and
only if you received the object code with such an offer, in accord
with subsection 6b.
d) Convey the object code by offering access from a designated
place (gratis or for a charge), and offer equivalent access to the
Corresponding Source in the same way through the same place at no
further charge. You need not require recipients to copy the
Corresponding Source along with the object code. If the place to
copy the object code is a network server, the Corresponding Source
may be on a different server (operated by you or a third party)
that supports equivalent copying facilities, provided you maintain
clear directions next to the object code saying where to find the
Corresponding Source. Regardless of what server hosts the
Corresponding Source, you remain obligated to ensure that it is
available for as long as needed to satisfy these requirements.
e) Convey the object code using peer-to-peer transmission, provided
you inform other peers where the object code and Corresponding
Source of the work are being offered to the general public at no
charge under subsection 6d.
A separable portion of the object code, whose source code is excluded
from the Corresponding Source as a System Library, need not be
included in conveying the object code work.
A "User Product" is either (1) a "consumer product", which means any
tangible personal property which is normally used for personal, family,
or household purposes, or (2) anything designed or sold for incorporation
into a dwelling. In determining whether a product is a consumer product,
doubtful cases shall be resolved in favor of coverage. For a particular
product received by a particular user, "normally used" refers to a
typical or common use of that class of product, regardless of the status
of the particular user or of the way in which the particular user
actually uses, or expects or is expected to use, the product. A product
is a consumer product regardless of whether the product has substantial
commercial, industrial or non-consumer uses, unless such uses represent
the only significant mode of use of the product.
"Installation Information" for a User Product means any methods,
procedures, authorization keys, or other information required to install
and execute modified versions of a covered work in that User Product from
a modified version of its Corresponding Source. The information must
suffice to ensure that the continued functioning of the modified object
code is in no case prevented or interfered with solely because
modification has been made.
If you convey an object code work under this section in, or with, or
specifically for use in, a User Product, and the conveying occurs as
part of a transaction in which the right of possession and use of the
User Product is transferred to the recipient in perpetuity or for a
fixed term (regardless of how the transaction is characterized), the
Corresponding Source conveyed under this section must be accompanied
by the Installation Information. But this requirement does not apply
if neither you nor any third party retains the ability to install
modified object code on the User Product (for example, the work has
been installed in ROM).
The requirement to provide Installation Information does not include a
requirement to continue to provide support service, warranty, or updates
for a work that has been modified or installed by the recipient, or for
the User Product in which it has been modified or installed. Access to a
network may be denied when the modification itself materially and
adversely affects the operation of the network or violates the rules and
protocols for communication across the network.
Corresponding Source conveyed, and Installation Information provided,
in accord with this section must be in a format that is publicly
documented (and with an implementation available to the public in
source code form), and must require no special password or key for
unpacking, reading or copying.
7. Additional Terms.
"Additional permissions" are terms that supplement the terms of this
License by making exceptions from one or more of its conditions.
Additional permissions that are applicable to the entire Program shall
be treated as though they were included in this License, to the extent
that they are valid under applicable law. If additional permissions
apply only to part of the Program, that part may be used separately
under those permissions, but the entire Program remains governed by
this License without regard to the additional permissions.
When you convey a copy of a covered work, you may at your option
remove any additional permissions from that copy, or from any part of
it. (Additional permissions may be written to require their own
removal in certain cases when you modify the work.) You may place
additional permissions on material, added by you to a covered work,
for which you have or can give appropriate copyright permission.
Notwithstanding any other provision of this License, for material you
add to a covered work, you may (if authorized by the copyright holders of
that material) supplement the terms of this License with terms:
a) Disclaiming warranty or limiting liability differently from the
terms of sections 15 and 16 of this License; or
b) Requiring preservation of specified reasonable legal notices or
author attributions in that material or in the Appropriate Legal
Notices displayed by works containing it; or
c) Prohibiting misrepresentation of the origin of that material, or
requiring that modified versions of such material be marked in
reasonable ways as different from the original version; or
d) Limiting the use for publicity purposes of names of licensors or
authors of the material; or
e) Declining to grant rights under trademark law for use of some
trade names, trademarks, or service marks; or
f) Requiring indemnification of licensors and authors of that
material by anyone who conveys the material (or modified versions of
it) with contractual assumptions of liability to the recipient, for
any liability that these contractual assumptions directly impose on
those licensors and authors.
All other non-permissive additional terms are considered "further
restrictions" within the meaning of section 10. If the Program as you
received it, or any part of it, contains a notice stating that it is
governed by this License along with a term that is a further
restriction, you may remove that term. If a license document contains
a further restriction but permits relicensing or conveying under this
License, you may add to a covered work material governed by the terms
of that license document, provided that the further restriction does
not survive such relicensing or conveying.
If you add terms to a covered work in accord with this section, you
must place, in the relevant source files, a statement of the
additional terms that apply to those files, or a notice indicating
where to find the applicable terms.
Additional terms, permissive or non-permissive, may be stated in the
form of a separately written license, or stated as exceptions;
the above requirements apply either way.
8. Termination.
You may not propagate or modify a covered work except as expressly
provided under this License. Any attempt otherwise to propagate or
modify it is void, and will automatically terminate your rights under
this License (including any patent licenses granted under the third
paragraph of section 11).
However, if you cease all violation of this License, then your
license from a particular copyright holder is reinstated (a)
provisionally, unless and until the copyright holder explicitly and
finally terminates your license, and (b) permanently, if the copyright
holder fails to notify you of the violation by some reasonable means
prior to 60 days after the cessation.
Moreover, your license from a particular copyright holder is
reinstated permanently if the copyright holder notifies you of the
violation by some reasonable means, this is the first time you have
received notice of violation of this License (for any work) from that
copyright holder, and you cure the violation prior to 30 days after
your receipt of the notice.
Termination of your rights under this section does not terminate the
licenses of parties who have received copies or rights from you under
this License. If your rights have been terminated and not permanently
reinstated, you do not qualify to receive new licenses for the same
material under section 10.
9. Acceptance Not Required for Having Copies.
You are not required to accept this License in order to receive or
run a copy of the Program. Ancillary propagation of a covered work
occurring solely as a consequence of using peer-to-peer transmission
to receive a copy likewise does not require acceptance. However,
nothing other than this License grants you permission to propagate or
modify any covered work. These actions infringe copyright if you do
not accept this License. Therefore, by modifying or propagating a
covered work, you indicate your acceptance of this License to do so.
10. Automatic Licensing of Downstream Recipients.
Each time you convey a covered work, the recipient automatically
receives a license from the original licensors, to run, modify and
propagate that work, subject to this License. You are not responsible
for enforcing compliance by third parties with this License.
An "entity transaction" is a transaction transferring control of an
organization, or substantially all assets of one, or subdividing an
organization, or merging organizations. If propagation of a covered
work results from an entity transaction, each party to that
transaction who receives a copy of the work also receives whatever
licenses to the work the party's predecessor in interest had or could
give under the previous paragraph, plus a right to possession of the
Corresponding Source of the work from the predecessor in interest, if
the predecessor has it or can get it with reasonable efforts.
You may not impose any further restrictions on the exercise of the
rights granted or affirmed under this License. For example, you may
not impose a license fee, royalty, or other charge for exercise of
rights granted under this License, and you may not initiate litigation
(including a cross-claim or counterclaim in a lawsuit) alleging that
any patent claim is infringed by making, using, selling, offering for
sale, or importing the Program or any portion of it.
11. Patents.
A "contributor" is a copyright holder who authorizes use under this
License of the Program or a work on which the Program is based. The
work thus licensed is called the contributor's "contributor version".
A contributor's "essential patent claims" are all patent claims
owned or controlled by the contributor, whether already acquired or
hereafter acquired, that would be infringed by some manner, permitted
by this License, of making, using, or selling its contributor version,
but do not include claims that would be infringed only as a
consequence of further modification of the contributor version. For
purposes of this definition, "control" includes the right to grant
patent sublicenses in a manner consistent with the requirements of
this License.
Each contributor grants you a non-exclusive, worldwide, royalty-free
patent license under the contributor's essential patent claims, to
make, use, sell, offer for sale, import and otherwise run, modify and
propagate the contents of its contributor version.
In the following three paragraphs, a "patent license" is any express
agreement or commitment, however denominated, not to enforce a patent
(such as an express permission to practice a patent or covenant not to
sue for patent infringement). To "grant" such a patent license to a
party means to make such an agreement or commitment not to enforce a
patent against the party.
If you convey a covered work, knowingly relying on a patent license,
and the Corresponding Source of the work is not available for anyone
to copy, free of charge and under the terms of this License, through a
publicly available network server or other readily accessible means,
then you must either (1) cause the Corresponding Source to be so
available, or (2) arrange to deprive yourself of the benefit of the
patent license for this particular work, or (3) arrange, in a manner
consistent with the requirements of this License, to extend the patent
license to downstream recipients. "Knowingly relying" means you have
actual knowledge that, but for the patent license, your conveying the
covered work in a country, or your recipient's use of the covered work
in a country, would infringe one or more identifiable patents in that
country that you have reason to believe are valid.
If, pursuant to or in connection with a single transaction or
arrangement, you convey, or propagate by procuring conveyance of, a
covered work, and grant a patent license to some of the parties
receiving the covered work authorizing them to use, propagate, modify
or convey a specific copy of the covered work, then the patent license
you grant is automatically extended to all recipients of the covered
work and works based on it.
A patent license is "discriminatory" if it does not include within
the scope of its coverage, prohibits the exercise of, or is
conditioned on the non-exercise of one or more of the rights that are
specifically granted under this License. You may not convey a covered
work if you are a party to an arrangement with a third party that is
in the business of distributing software, under which you make payment
to the third party based on the extent of your activity of conveying
the work, and under which the third party grants, to any of the
parties who would receive the covered work from you, a discriminatory
patent license (a) in connection with copies of the covered work
conveyed by you (or copies made from those copies), or (b) primarily
for and in connection with specific products or compilations that
contain the covered work, unless you entered into that arrangement,
or that patent license was granted, prior to 28 March 2007.
Nothing in this License shall be construed as excluding or limiting
any implied license or other defenses to infringement that may
otherwise be available to you under applicable patent law.
12. No Surrender of Others' Freedom.
If conditions are imposed on you (whether by court order, agreement or
otherwise) that contradict the conditions of this License, they do not
excuse you from the conditions of this License. If you cannot convey a
covered work so as to satisfy simultaneously your obligations under this
License and any other pertinent obligations, then as a consequence you may
not convey it at all. For example, if you agree to terms that obligate you
to collect a royalty for further conveying from those to whom you convey
the Program, the only way you could satisfy both those terms and this
License would be to refrain entirely from conveying the Program.
13. Use with the GNU Affero General Public License.
Notwithstanding any other provision of this License, you have
permission to link or combine any covered work with a work licensed
under version 3 of the GNU Affero General Public License into a single
combined work, and to convey the resulting work. The terms of this
License will continue to apply to the part which is the covered work,
but the special requirements of the GNU Affero General Public License,
section 13, concerning interaction through a network will apply to the
combination as such.
14. Revised Versions of this License.
The Free Software Foundation may publish revised and/or new versions of
the GNU General Public License from time to time. Such new versions will
be similar in spirit to the present version, but may differ in detail to
address new problems or concerns.
Each version is given a distinguishing version number. If the
Program specifies that a certain numbered version of the GNU General
Public License "or any later version" applies to it, you have the
option of following the terms and conditions either of that numbered
version or of any later version published by the Free Software
Foundation. If the Program does not specify a version number of the
GNU General Public License, you may choose any version ever published
by the Free Software Foundation.
If the Program specifies that a proxy can decide which future
versions of the GNU General Public License can be used, that proxy's
public statement of acceptance of a version permanently authorizes you
to choose that version for the Program.
Later license versions may give you additional or different
permissions. However, no additional obligations are imposed on any
author or copyright holder as a result of your choosing to follow a
later version.
15. Disclaimer of Warranty.
THERE IS NO WARRANTY FOR THE PROGRAM, TO THE EXTENT PERMITTED BY
APPLICABLE LAW. EXCEPT WHEN OTHERWISE STATED IN WRITING THE COPYRIGHT
HOLDERS AND/OR OTHER PARTIES PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY
OF ANY KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING, BUT NOT LIMITED TO,
THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
PURPOSE. THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE OF THE PROGRAM
IS WITH YOU. SHOULD THE PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF
ALL NECESSARY SERVICING, REPAIR OR CORRECTION.
16. Limitation of Liability.
IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING
WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MODIFIES AND/OR CONVEYS
THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES, INCLUDING ANY
GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING OUT OF THE
USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED TO LOSS OF
DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY YOU OR THIRD
PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER PROGRAMS),
EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE POSSIBILITY OF
SUCH DAMAGES.
17. Interpretation of Sections 15 and 16.
If the disclaimer of warranty and limitation of liability provided
above cannot be given local legal effect according to their terms,
reviewing courts shall apply local law that most closely approximates
an absolute waiver of all civil liability in connection with the
Program, unless a warranty or assumption of liability accompanies a
copy of the Program in return for a fee.
END OF TERMS AND CONDITIONS
How to Apply These Terms to Your New Programs
If you develop a new program, and you want it to be of the greatest
possible use to the public, the best way to achieve this is to make it
free software which everyone can redistribute and change under these terms.
To do so, attach the following notices to the program. It is safest
to attach them to the start of each source file to most effectively
state the exclusion of warranty; and each file should have at least
the "copyright" line and a pointer to where the full notice is found.
<one line to give the program's name and a brief idea of what it does.>
Copyright (C) <year> <name of author>
This program is free software: you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
the Free Software Foundation, either version 3 of the License, or
(at your option) any later version.
This program is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
GNU General Public License for more details.
You should have received a copy of the GNU General Public License
along with this program. If not, see <https://www.gnu.org/licenses/>.
Also add information on how to contact you by electronic and paper mail.
If the program does terminal interaction, make it output a short
notice like this when it starts in an interactive mode:
<program> Copyright (C) <year> <name of author>
This program comes with ABSOLUTELY NO WARRANTY; for details type `show w'.
This is free software, and you are welcome to redistribute it
under certain conditions; type `show c' for details.
The hypothetical commands `show w' and `show c' should show the appropriate
parts of the General Public License. Of course, your program's commands
might be different; for a GUI interface, you would use an "about box".
You should also get your employer (if you work as a programmer) or school,
if any, to sign a "copyright disclaimer" for the program, if necessary.
For more information on this, and how to apply and follow the GNU GPL, see
<https://www.gnu.org/licenses/>.
The GNU General Public License does not permit incorporating your program
into proprietary programs. If your program is a subroutine library, you
may consider it more useful to permit linking proprietary applications with
the library. If this is what you want to do, use the GNU Lesser General
Public License instead of this License. But first, please read
<https://www.gnu.org/licenses/why-not-lgpl.html>.

201
LICENSE-APACHE Normal file
View File

@ -0,0 +1,201 @@
Apache License
Version 2.0, January 2004
http://www.apache.org/licenses/
TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
1. Definitions.
"License" shall mean the terms and conditions for use, reproduction,
and distribution as defined by Sections 1 through 9 of this document.
"Licensor" shall mean the copyright owner or entity authorized by
the copyright owner that is granting the License.
"Legal Entity" shall mean the union of the acting entity and all
other entities that control, are controlled by, or are under common
control with that entity. For the purposes of this definition,
"control" means (i) the power, direct or indirect, to cause the
direction or management of such entity, whether by contract or
otherwise, or (ii) ownership of fifty percent (50%) or more of the
outstanding shares, or (iii) beneficial ownership of such entity.
"You" (or "Your") shall mean an individual or Legal Entity
exercising permissions granted by this License.
"Source" form shall mean the preferred form for making modifications,
including but not limited to software source code, documentation
source, and configuration files.
"Object" form shall mean any form resulting from mechanical
transformation or translation of a Source form, including but
not limited to compiled object code, generated documentation,
and conversions to other media types.
"Work" shall mean the work of authorship, whether in Source or
Object form, made available under the License, as indicated by a
copyright notice that is included in or attached to the work
(an example is provided in the Appendix below).
"Derivative Works" shall mean any work, whether in Source or Object
form, that is based on (or derived from) the Work and for which the
editorial revisions, annotations, elaborations, or other modifications
represent, as a whole, an original work of authorship. For the purposes
of this License, Derivative Works shall not include works that remain
separable from, or merely link (or bind by name) to the interfaces of,
the Work and Derivative Works thereof.
"Contribution" shall mean any work of authorship, including
the original version of the Work and any modifications or additions
to that Work or Derivative Works thereof, that is intentionally
submitted to Licensor for inclusion in the Work by the copyright owner
or by an individual or Legal Entity authorized to submit on behalf of
the copyright owner. For the purposes of this definition, "submitted"
means any form of electronic, verbal, or written communication sent
to the Licensor or its representatives, including but not limited to
communication on electronic mailing lists, source code control systems,
and issue tracking systems that are managed by, or on behalf of, the
Licensor for the purpose of discussing and improving the Work, but
excluding communication that is conspicuously marked or otherwise
designated in writing by the copyright owner as "Not a Contribution."
"Contributor" shall mean Licensor and any individual or Legal Entity
on behalf of whom a Contribution has been received by Licensor and
subsequently incorporated within the Work.
2. Grant of Copyright License. Subject to the terms and conditions of
this License, each Contributor hereby grants to You a perpetual,
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
copyright license to reproduce, prepare Derivative Works of,
publicly display, publicly perform, sublicense, and distribute the
Work and such Derivative Works in Source or Object form.
3. Grant of Patent License. Subject to the terms and conditions of
this License, each Contributor hereby grants to You a perpetual,
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
(except as stated in this section) patent license to make, have made,
use, offer to sell, sell, import, and otherwise transfer the Work,
where such license applies only to those patent claims licensable
by such Contributor that are necessarily infringed by their
Contribution(s) alone or by combination of their Contribution(s)
with the Work to which such Contribution(s) was submitted. If You
institute patent litigation against any entity (including a
cross-claim or counterclaim in a lawsuit) alleging that the Work
or a Contribution incorporated within the Work constitutes direct
or contributory patent infringement, then any patent licenses
granted to You under this License for that Work shall terminate
as of the date such litigation is filed.
4. Redistribution. You may reproduce and distribute copies of the
Work or Derivative Works thereof in any medium, with or without
modifications, and in Source or Object form, provided that You
meet the following conditions:
(a) You must give any other recipients of the Work or
Derivative Works a copy of this License; and
(b) You must cause any modified files to carry prominent notices
stating that You changed the files; and
(c) You must retain, in the Source form of any Derivative Works
that You distribute, all copyright, patent, trademark, and
attribution notices from the Source form of the Work,
excluding those notices that do not pertain to any part of
the Derivative Works; and
(d) If the Work includes a "NOTICE" text file as part of its
distribution, then any Derivative Works that You distribute must
include a readable copy of the attribution notices contained
within such NOTICE file, excluding those notices that do not
pertain to any part of the Derivative Works, in at least one
of the following places: within a NOTICE text file distributed
as part of the Derivative Works; within the Source form or
documentation, if provided along with the Derivative Works; or,
within a display generated by the Derivative Works, if and
wherever such third-party notices normally appear. The contents
of the NOTICE file are for informational purposes only and
do not modify the License. You may add Your own attribution
notices within Derivative Works that You distribute, alongside
or as an addendum to the NOTICE text from the Work, provided
that such additional attribution notices cannot be construed
as modifying the License.
You may add Your own copyright statement to Your modifications and
may provide additional or different license terms and conditions
for use, reproduction, or distribution of Your modifications, or
for any such Derivative Works as a whole, provided Your use,
reproduction, and distribution of the Work otherwise complies with
the conditions stated in this License.
5. Submission of Contributions. Unless You explicitly state otherwise,
any Contribution intentionally submitted for inclusion in the Work
by You to the Licensor shall be under the terms and conditions of
this License, without any additional terms or conditions.
Notwithstanding the above, nothing herein shall supersede or modify
the terms of any separate license agreement you may have executed
with Licensor regarding such Contributions.
6. Trademarks. This License does not grant permission to use the trade
names, trademarks, service marks, or product names of the Licensor,
except as required for reasonable and customary use in describing the
origin of the Work and reproducing the content of the NOTICE file.
7. Disclaimer of Warranty. Unless required by applicable law or
agreed to in writing, Licensor provides the Work (and each
Contributor provides its Contributions) on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
implied, including, without limitation, any warranties or conditions
of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
PARTICULAR PURPOSE. You are solely responsible for determining the
appropriateness of using or redistributing the Work and assume any
risks associated with Your exercise of permissions under this License.
8. Limitation of Liability. In no event and under no legal theory,
whether in tort (including negligence), contract, or otherwise,
unless required by applicable law (such as deliberate and grossly
negligent acts) or agreed to in writing, shall any Contributor be
liable to You for damages, including any direct, indirect, special,
incidental, or consequential damages of any character arising as a
result of this License or out of the use or inability to use the
Work (including but not limited to damages for loss of goodwill,
work stoppage, computer failure or malfunction, or any and all
other commercial damages or losses), even if such Contributor
has been advised of the possibility of such damages.
9. Accepting Warranty or Additional Liability. While redistributing
the Work or Derivative Works thereof, You may choose to offer,
and charge a fee for, acceptance of support, warranty, indemnity,
or other liability obligations and/or rights consistent with this
License. However, in accepting such obligations, You may act only
on Your own behalf and on Your sole responsibility, not on behalf
of any other Contributor, and only if You agree to indemnify,
defend, and hold each Contributor harmless for any liability
incurred by, or claims asserted against, such Contributor by reason
of your accepting any such warranty or additional liability.
END OF TERMS AND CONDITIONS
APPENDIX: How to apply the Apache License to your work.
To apply the Apache License to your work, attach the following
boilerplate notice, with the fields enclosed by brackets "{}"
replaced with your own identifying information. (Don't include
the brackets!) The text should be enclosed in the appropriate
comment syntax for the file format. We also recommend that a
file or class name and description of purpose be included on the
same "printed page" as the copyright notice for easier
identification within third-party archives.
Copyright 2024 Luke Street.
Licensed under the Apache License, Version 2.0 (the "License");
you may not use this file except in compliance with the License.
You may obtain a copy of the License at
http://www.apache.org/licenses/LICENSE-2.0
Unless required by applicable law or agreed to in writing, software
distributed under the License is distributed on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
See the License for the specific language governing permissions and
limitations under the License.

21
LICENSE-MIT Normal file
View File

@ -0,0 +1,21 @@
MIT License
Copyright 2024 Luke Street.
Permission is hereby granted, free of charge, to any person obtaining a copy
of this software and associated documentation files (the "Software"), to deal
in the Software without restriction, including without limitation the rights
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
copies of the Software, and to permit persons to whom the Software is
furnished to do so, subject to the following conditions:
The above copyright notice and this permission notice shall be included in all
copies or substantial portions of the Software.
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
SOFTWARE.

36
README.md
View File

@ -5,35 +5,10 @@ Rust tools for working with the PowerPC 750CL family of processors.
### Rust crates
```shell
rustup components add rustfmt
cargo run --package ppc750cl-genisa
cargo build --release
```
### Python module
```shell
python -m venv env
source ./env/bin/activate
pip install maturin
maturin build -m ./disasm-py/Cargo.toml
```
Install module in dev env
```
maturin develop -m ./disasm-py/Cargo.toml
python
>>> import ppc750cl
>>> ins = ppc750cl.Ins(addr=0x80006969, code=0x10400420)
>>> str(ins)
'ps_merge00 f2, f0, f0'
>>> ins.fields()
[('frD', 2), ('frA', 0), ('frB', 0)]
>>> ins.frD
2
```
### Instruction Set
For those unfamiliar with PowerPC, here are some basics.
@ -48,7 +23,7 @@ For those unfamiliar with PowerPC, here are some basics.
The file [isa.yaml](./isa.yaml) contains a full definition of the PowerPC 750CL instruction set.
It powers the disassembler, assembler, and Rust/Python bindings code analysis tools.
It powers the disassembler and assembler.
Similarly to LLVM TableGen, the program `ppc750cl-genisa` generates a Rust file implementing an instruction decoder.
@ -57,10 +32,11 @@ Similarly to LLVM TableGen, the program `ppc750cl-genisa` generates a Rust file
- This project does not use `unsafe` Rust code outside of testing utils.
- The disassembler has been fuzzed over all ~4.29 billion possible instructions (via `ppc750cl-fuzz`).
- It is safe to run the disassembler over untrusted byte arrays.
- However no guarantees on correctness are made (yet). Expect bugs.
- However, no guarantees on correctness are made (yet). Expect bugs.
### Performance
- Performance isn't great but acceptable.
- Disassembling & printing: 600k insn/s (2.4 MB/s)
- Disassembling only: 6M insn/s (24 MB/s)
With a single thread on Ryzen 9 3900X:
- Disassembling & printing: ~5M insn/s (~20 MB/s)
- Disassembling only: ~50M insn/s (~200 MB/s)

174
analysis/cfa.md
View File

@ -1,174 +0,0 @@
---
date: 2022-04-10
status: draft
---
# Control-flow analysis
CFA analyses the entire `.text` section with linear complexity.
It has the following goals:
- Detect function boundaries
- Create the control-flow graph of each function
## Pass 1: Find control-flow intrinsics
Input:
- `.text` section
Output:
- Locations of compiler intrinsics
Rules
*savegpr/restgpr detection* (CodeWarrior only)
Find the following instructions in `.text`
```asm
_save_gpr:
stw r14, -0x48(r11)
stw r15, -0x44(r11)
stw r16, -0x40(r11)
stw r17, -0x3c(r11)
stw r18, -0x38(r11)
stw r19, -0x34(r11)
stw r20, -0x30(r11)
stw r21, -0x2c(r11)
stw r22, -0x28(r11)
stw r23, -0x24(r11)
stw r24, -0x20(r11)
stw r25, -0x1c(r11)
stw r26, -0x18(r11)
stw r27, -0x14(r11)
stw r28, -0x10(r11)
stw r29, -0xc(r11)
stw r30, -0x8(r11)
stw r31, -0x4(r11)
blr
_load_gpr:
lwz r14, -0x48(r11)
lwz r15, -0x44(r11)
lwz r16, -0x40(r11)
lwz r17, -0x3c(r11)
lwz r18, -0x38(r11)
lwz r19, -0x34(r11)
lwz r20, -0x30(r11)
lwz r21, -0x2c(r11)
lwz r22, -0x28(r11)
lwz r23, -0x24(r11)
lwz r24, -0x20(r11)
lwz r25, -0x1c(r11)
lwz r26, -0x18(r11)
lwz r27, -0x14(r11)
lwz r28, -0x10(r11)
lwz r29, -0xc(r11)
lwz r30, -0x8(r11)
lwz r31, -0x4(r11)
blr
```
## Pass 2: Branch analysis
Input:
- `.text` section
Output:
- Slices (cuts) from which basic blocks can be derived
- Forward edges between basic blocks
- Initial set of function boundaries
#### Branch instruction hints
- Iterate over all branch opcodes (b, bc, bcctr, bclr)
- Assume that branches with link register save …
- point to the start of another function;
- eventually return back to the call site.
- Assume that branches without link register save are …
- tail calls if their target precedes the function start of the call site;
- probably jumps to basic blocks within the function otherwise (might be wrong)
- Skip indirect local branches (bcctr, bclr) for now.
#### Stack frame detection (CodeWarrior only)
Detect patterns matching stack frames. They might be reordered due to instruction scheduling.
Since CodeWarrior will only emit one function epilogue and prologue per function,
we can use this hint (if present) to reliably detect function bounds.
- On function entry point:
- Execute instructions up to next branch
- Derive stack frame from changes in machine state
- If the stack changed, we found an epilog
- When a `blr` (function return) is encountered:
- Execute instructions in basic block of `blr`
- If stack-related machine state got reverted, assume this BB to contain the prolog
Example 0x80045de0 from RMCP01 (savegpr/restgpr sled):
```asm
# Stack
# +0x04..+0x08: ret addr to caller
# 0x00..+0x04: caller backchain <- caller r1
# -0x30.. 0x00: callee saved gprs <- callee r11
# -0x68..-0x30: callee stack
# -0x6c..-0x68: ret addr to callee
# -0x70..-0x6c: callee backchain <- callee r1
_alloc_stack_frame:
stwu r1, -0x70(r1) # store callee backchain & alloc stack frame
mflr r0
…
stw r0, 0x74(r1) # store ret addr to caller
…
la r11, 0x40(r1) # load ptr to callee saved gprs
bl _savegpr_22 # save gprs
mr r31, r1
…
_free_stack_frame:
mr r10, r31
la r11, 0x40(r10) # load ptr to callee saved gprs
bl _restgpr_22 # restore gprs
lwz r10, 0x0(r1) # load ptr to caller stack frame
lwz r0, 0x4(r10) # load ret addr to caller
mr r1, r10 # free stack frame
mtlr r0
blr # return to caller
```
Example 0x80228490 from RMCP01 (stmw/lmw):
```asm
# Stack
# +0x04..+0x08: ret addr to caller
# 0x00..+0x04: caller backchain <- caller r1
# -0x30.. 0x00: callee saved gprs <- callee r11
# -0x38..-0x30: callee stack
# -0x3c..-0x38: ret addr to callee
# -0x40..-0x3c: callee backchain <- callee r1
_alloc_stack_frame:
stwu r1, -0x40(r1) # store callee backchain & alloc stack frame
mflr r0
stw r0, 0x44(r1) # store ret addr to caller
stmw r20, -0x30(r1) # save gprs
…
_free_stack_frame:
lmw r20, -0x30(r1) # restore gprs
lwz r0, 0x44(r1) # load ret addr to caller
mtlr r0
la r1, 0x40(r1) # free stack frame
blr # return to caller
```
## TODO
Add the following rules:
- follow indirect local branches
- destructor detection
- vtable detection

16
asm/Cargo.toml Normal file
View File

@ -0,0 +1,16 @@
[package]
name = "ppc750cl-asm"
version = "0.3.0"
edition = "2021"
authors = ["Luke Street <luke@street.dev>"]
license = "MIT OR Apache-2.0"
description = "Assembler for PowerPC 750CL"
keywords = ["powerpc", "wii", "gamecube"]
repository = "https://github.com/encounter/ppc750cl"
[features]
default = ["std"]
std = []
[dependencies]
phf = "0.11"

4618
asm/src/generated.rs Normal file
View File

File diff suppressed because it is too large Load Diff

6
asm/src/lib.rs Normal file
View File

@ -0,0 +1,6 @@
#![cfg_attr(not(feature = "std"), no_std)]
mod generated;
mod types;
pub use generated::*;
pub use types::{Argument, ArgumentError};

94
asm/src/types.rs Normal file
View File

@ -0,0 +1,94 @@
use crate::Arguments;
use core::fmt::Formatter;
#[derive(Debug)]
pub enum ArgumentError {
ArgOutOfRangeUnsigned { index: usize, value: u32, start: u32, end: u32 },
ArgOutOfRangeSigned { index: usize, value: i32, start: i32, end: i32 },
ArgCount { value: usize, expected: usize },
UnknownMnemonic,
}
impl core::fmt::Display for ArgumentError {
fn fmt(&self, _f: &mut Formatter<'_>) -> core::fmt::Result {
todo!()
}
}
#[cfg(feature = "std")]
impl std::error::Error for ArgumentError {}
#[derive(Debug, Default, Clone, Copy, Eq, PartialEq)]
pub enum Argument {
#[default]
None,
Unsigned(u32),
Signed(i32),
}
pub const fn parse_unsigned(
args: &Arguments,
index: usize,
start: u32,
end: u32,
) -> Result<u32, ArgumentError> {
match args[index] {
Argument::Unsigned(value) => {
if value >= start && value <= end {
Ok(value)
} else {
Err(ArgumentError::ArgOutOfRangeUnsigned { index, value, start, end })
}
}
Argument::Signed(value) => {
if value >= start as i32 && value <= end as i32 {
Ok(value as u32)
} else {
Err(ArgumentError::ArgOutOfRangeUnsigned { index, value: value as u32, start, end })
}
}
Argument::None => Err(ArgumentError::ArgCount { value: index, expected: index + 1 }),
}
}
pub const fn parse_signed(
args: &Arguments,
index: usize,
start: i32,
end: i32,
) -> Result<i32, ArgumentError> {
match args[index] {
Argument::Unsigned(value) => {
if (start < 0 || value >= start as u32) && value <= end as u32 {
Ok(value as i32)
} else {
Err(ArgumentError::ArgOutOfRangeSigned { index, value: value as i32, start, end })
}
}
Argument::Signed(value) => {
if value >= start && value <= end {
Ok(value)
} else {
Err(ArgumentError::ArgOutOfRangeSigned { index, value, start, end })
}
}
Argument::None => Err(ArgumentError::ArgCount { value: index, expected: index + 1 }),
}
}
pub const fn arg_count(args: &Arguments) -> usize {
let mut i = 0;
while i < args.len() && !matches!(args[i], Argument::None) {
i += 1;
}
i
}
pub const fn check_arg_count(args: &Arguments, expected: usize) -> Result<(), ArgumentError> {
let value = arg_count(args);
if value == expected {
Ok(())
} else {
Err(ArgumentError::ArgCount { value, expected })
}
}

182
asm/tests/test_asm.rs Normal file
View File

@ -0,0 +1,182 @@
use ppc750cl_asm::*;
use Argument::{None, Signed as S, Unsigned as U};
macro_rules! assert_asm {
($mnemonic:literal, $arg1:expr, $arg2:expr, $arg3:expr, $arg4:expr, $arg5: expr, $code:literal) => {{
assert_eq!(assemble($mnemonic, &[$arg1, $arg2, $arg3, $arg4, $arg5]).unwrap(), $code)
}};
($mnemonic:literal, $arg1:expr, $arg2:expr, $arg3:expr, $arg4:expr, $code:literal) => {{
assert_eq!(assemble($mnemonic, &[$arg1, $arg2, $arg3, $arg4, None]).unwrap(), $code)
}};
($mnemonic:literal, $arg1:expr, $arg2:expr, $arg3:expr, $code:literal) => {{
assert_eq!(assemble($mnemonic, &[$arg1, $arg2, $arg3, None, None]).unwrap(), $code)
}};
($mnemonic:literal, $arg1:expr, $arg2:expr, $code:literal) => {{
assert_eq!(assemble($mnemonic, &[$arg1, $arg2, None, None, None]).unwrap(), $code)
}};
($mnemonic:literal, $arg1:expr, $code:literal) => {{
assert_eq!(assemble($mnemonic, &[$arg1, None, None, None, None]).unwrap(), $code)
}};
($mnemonic:literal, $code:literal) => {{
assert_eq!(assemble($mnemonic, &[None, None, None, None, None]).unwrap(), $code)
}};
}
#[test]
fn test_ins_add() {
assert_asm!("add", U(2), U(3), U(4), 0x7C432214); // add r2, r3, r4
assert_asm!("add.", U(7), U(6), U(5), 0x7CE62A15); // add. r7, r6, r5
assert_asm!("addo", U(31), U(31), U(31), 0x7FFFFE14); // addo r31, r31, r31
assert_asm!("addo.", U(28), U(29), U(30), 0x7F9DF615); // addo. r28, r29, r30
}
#[test]
fn test_ins_addc() {
assert_asm!("addc", U(2), U(3), U(4), 0x7C432014); // addc r2, r3, r4
assert_asm!("addc.", U(7), U(6), U(5), 0x7CE62815); // addc. r7, r6, r5
assert_asm!("addco", U(31), U(31), U(31), 0x7FFFFC14); // addco r31, r31, r31
assert_asm!("addco.", U(28), U(29), U(30), 0x7F9DF415); // addco. r28, r29, r30
}
#[test]
fn test_ins_addi() {
assert_asm!("addi", U(0), U(1), U(0x140), 0x38010140); // addi r0, r1, 0x140
assert_asm!("addi", U(0), U(4), S(-0x7000), 0x38049000); // addi r0, r4, -0x7000
assert_asm!("subi", U(0), U(4), S(0x7000), 0x38049000); // subi r0, r4, 0x7000
assert_asm!("li", U(5), U(0), 0x38A00000); // li r5, 0
}
#[test]
fn test_ins_b() {
assert_asm!("b", U(0), 0x48000000); // b 0x0
assert_asm!("b", U(4), 0x48000004); // b 0x4
assert_asm!("bl", U(0xA5C8), 0x4800A5C9); // bl 0xa5c8
assert_asm!("bl", U(0x23B4D8), 0x4823B4D9); // bl 0x23b4d8
assert_asm!("bl", S(-0x1FC368), 0x4BE03C99); // bl -0x1fc368
assert_asm!("bl", S(-0x23E5A8), 0x4BDC1A59); // bl -0x23e5a8
assert_asm!("bla", U(0x60), 0x48000063); // bla 0x60
assert_asm!("ba", U(0), 0x48000002); // ba 0x0
}
#[test]
fn test_ins_bc() {
assert_asm!("bge", U(0x8), 0x40800008); // bge 0x8
assert_asm!("bge", U(0x2350), 0x40802350); // bge 0x2350
assert_asm!("bge", S(-0x384), 0x4080FC7C); // bge -0x384
assert_asm!("ble", U(0xac), 0x408100AC); // ble 0xac
assert_asm!("ble", S(-0x878), 0x4081F788); // ble -0x878
assert_asm!("bne", U(0x1ba0), 0x40821BA0); // bne 0x1ba0
assert_asm!("bne", S(-0x1c3c), 0x4082E3C4); // bne -0x1c3c
assert_asm!("bne", U(1), U(0xd8), 0x408600D8); // bne cr1, 0xd8
assert_asm!("bne", U(1), S(-0x134), 0x4086FECC); // bne cr1, -0x134
assert_asm!("bge", U(7), U(0xc), 0x409C000C); // bge cr7, 0xc
assert_asm!("blt", U(0xc), 0x4180000C); // blt 0xc
assert_asm!("blt", S(-0x640), 0x4180F9C0); // blt -0x640
assert_asm!("bgt", U(0x21c), 0x4181021C); // bgt 0x21c
assert_asm!("bgt", S(-0x280), 0x4181FD80); // bgt -0x280
assert_asm!("beq", U(0x2304), 0x41822304); // beq 0x2304
assert_asm!("beq", S(-0x1c4), 0x4182FE3C); // beq -0x1c4
assert_asm!("blt", U(1), U(0x1ac), 0x418401AC); // blt cr1, 0x1ac
assert_asm!("blt", U(1), S(-0x31c), 0x4184FCE4); // blt cr1, -0x31c
assert_asm!("bgt", U(1), U(0xc0), 0x418500C0); // bgt cr1, 0xc0
assert_asm!("bgt", U(1), U(0x2e4), 0x418502E4); // bgt cr1, 0x2e4
assert_asm!("beq", U(6), U(0x138), 0x419A0138); // beq cr6, 0x138
assert_asm!("blt", U(7), U(0x8), 0x419C0008); // blt cr7, 0x8
assert_asm!("bdz", S(-0x10), 0x4240FFF0); // bdz -0x10
assert_asm!("bdnz", S(-0xaa0), 0x4200F560); // bdnz -0xaa0
assert_asm!("bdnzf", U(1), U(0x14), 0x40010014); // bdnzf gt, 0x14
assert_asm!("bdzfl", U(1), U(0x34), 0x40410035); // bdzfl gt, 0x34
assert_asm!("bdztla", U(3), U(0x20), 0x41430023); // bdztla un, 0x20
assert_asm!("bdnztla", U(8), S(-0x20), 0x4108FFE3); // bdnztla cr2lt, -0x20
assert_asm!("bne+", U(0x8), 0x40A20008); // bne+ 0x8
}
#[test]
fn test_ins_bcctr() {
assert_asm!("bctr", 0x4E800420); // bctr
assert_asm!("bctrl", 0x4E800421); // bctrl
assert_asm!("beqctr", 0x4D820420); // beqctr
assert_asm!("bgtctrl", U(3), 0x4D8D0421); // bgtctrl cr3
assert_asm!("beqctr+", 0x4DA20420); // beqctr+
assert_asm!("bgtctrl+", U(6), 0x4DB90421); // bgtctrl+ cr6
}
#[test]
fn test_ins_bclr() {
assert_asm!("bgelr", 0x4C800020); // bgelr
assert_asm!("bgelr+", 0x4CA00020); // bgelr+
assert_asm!("blelr", 0x4C810020); // blelr
assert_asm!("bnelr", 0x4C820020); // bnelr
assert_asm!("bnelr", U(7), 0x4C9E0020); // bnelr cr7
assert_asm!("bltlr", 0x4D800020); // bltlr
assert_asm!("bgtlr", 0x4D810020); // bgtlr
assert_asm!("beqlr", 0x4D820020); // beqlr
assert_asm!("beqlr", U(1), 0x4D860020); // beqlr cr1
assert_asm!("blr", 0x4E800020); // blr
assert_asm!("blrl", 0x4E800021); // blrl
assert_asm!("bdnztlr", U(0), 0x4D000020); // bdnztlr lt
assert_asm!("bdnzflrl", U(31), 0x4C1F0021); // bdnzflrl cr7un
}
#[test]
fn test_ins_cmpi() {
assert_asm!("cmpi", U(6), U(0), U(31), U(0), 0x2F1F0000); // cmpi r6, 0, 31, 0
assert_asm!("cmpwi", U(5), U(0xd00), 0x2C050D00); // cmpwi r5, 0xd00
assert_asm!("cmpwi", U(6), U(31), U(0), 0x2F1F0000); // cmpwi r6, 0
}
#[test]
fn test_ins_mfspr() {
assert_asm!("mfsrr0", U(16), 0x7E1A02A6); // mfsrr0 r16
assert_asm!("mfspr", U(3), U(1008), 0x7C70FAA6); // mfspr r3, HID0
assert_asm!("mfibatu", U(3), U(2), 0x7C7482A6); // mfibatu r3, 2
assert_asm!("mfibatl", U(3), U(3), 0x7C7782A6); // mfibatl r3, 3
}
#[test]
fn test_ins_rlwimi() {
assert_asm!("rlwimi", U(3), U(0), U(0), U(27), U(31), 0x500306FE); // rlwimi r3, r0, 0, 27, 31
assert_asm!("rlwimi", U(3), U(0), U(5), U(21), U(26), 0x50032D74); // rlwimi r3, r0, 5, 21, 26
assert_asm!("clrrwi.", U(0), U(0), U(0), 0x5400003F); // clrrwi. r0, r0, 0
}
#[test]
fn test_ins_rlwinm() {
assert_asm!("rlwinm", U(0), U(0), U(0), U(16), U(25), 0x54000432); // rlwinm r0, r0, 0, 16, 25
assert_asm!("rlwinm", U(9), U(0), U(12), U(8), U(19), 0x54096226); // rlwinm r9, r0, 12, 8, 19
assert_asm!("rlwinm.", U(0), U(0), U(0), U(16), U(17), 0x54000423); // rlwinm. r0, r0, 0, 16, 17
assert_asm!("slwi", U(5), U(31), U(2), 0x57E5103A); // slwi r5, r31, 2
assert_asm!("extlwi", U(3), U(4), U(20), U(4), 0x54832026); // extlwi r3, r4, 20, 4
assert_asm!("extrwi", U(3), U(4), U(20), U(1), 0x5483AB3E); // extrwi r3, r4, 20, 1
assert_asm!("extrwi", U(0), U(0), U(2), U(2), 0x540027BE); // extrwi r0, r0, 2, 2
assert_asm!("rlwinm", U(3), U(4), U(19), U(12), U(31), 0x54839B3E); // rlwinm r3, r4, 19, 12, 31
assert_asm!("rotlwi", U(3), U(4), U(4), 0x5483203E); // rotlwi r3, r4, 4
assert_asm!("rotrwi", U(3), U(4), U(4), 0x5483E03E); // rotrwi r3, r4, 4
assert_asm!("clrlwi", U(4), U(3), U(16), 0x5464043E); // clrlwi r4, r3, 16
assert_asm!("clrrwi", U(3), U(4), U(4), 0x54830036); // clrrwi r3, r4, 4
assert_asm!("clrlslwi", U(4), U(3), U(31), U(1), 0x54640FBC); // clrlslwi r4, r3, 31, 1
assert_asm!("clrlslwi", U(9), U(0), U(27), U(5), 0x54092DB4); // clrlslwi r9, r0, 27, 5
assert_asm!("clrlslwi", U(9), U(0), U(20), U(12), 0x54096226); // clrlslwi r9, r0, 20, 12
}
#[test]
fn test_tw() {
assert_asm!("tw", U(0), U(6), U(7), 0x7C063808); // tw 0, r6, r7
assert_asm!("tweq", U(4), U(5), 0x7C842808); // tweq r4, r5
assert_asm!("twlge", U(4), U(5), 0x7CA42808); // twlge r4, r5
assert_asm!("trap", 0x7FE00008); // trap
}
#[test]
fn test_twi() {
assert_asm!("twi", U(0), U(0), U(0), 0x0C000000); // twi 0, r0, 0x0
assert_asm!("twgti", U(7), S(-0x1), 0x0D07FFFF); // twgti r7, -0x1
assert_asm!("twllei", U(4), S(-0xff), 0x0CC4FF01); // twllei r4, -0xff
assert_asm!("twui", U(4), U(0x3), 0x0FE40003); // twui r4, 0x3
}
#[test]
fn test_ins_xor() {
assert_asm!("xor", U(5), U(0), U(5), 0x7C052A78); // xor r5, r0, r5
assert_asm!("xor.", U(7), U(9), U(10), 0x7D275279); // xor. r7, r9, r10
}

20
disasm-py/Cargo.toml
View File

@ -1,20 +0,0 @@
[package]
name = "ppc750cl-py"
version = "0.2.0"
edition = "2021"
authors = ["Richard Patel <me@terorie.dev>"]
license = "GPL-3.0-or-later"
description = "Python bindings for PowerPC 750CL Disassembler"
repository = "https://github.com/terorie/ppc750cl"
[lib]
name = "ppc750cl"
crate-type = ["cdylib"]
[features]
extension-module = ["pyo3/extension-module"]
default = ["extension-module"]
[dependencies]
pyo3 = { version = "0.16", features = ["multiple-pymethods"] }
ppc750cl = { version = "0.2.0", path = "../disasm" }

257
disasm-py/src/lib.rs
View File

@ -1,257 +0,0 @@
use pyo3::prelude::*;
use pyo3::types::PyBytes;
use ppc750cl::formatter::FormattedIns;
#[pyclass]
struct Ins(ppc750cl::Ins);
#[pymethods]
impl Ins {
#[new]
fn new(code: u32, addr: u32) -> Self {
Ins(ppc750cl::Ins::new(code, addr))
}
#[getter]
fn code(&self) -> u32 {
self.0.code
}
#[getter]
fn addr(&self) -> u32 {
self.0.addr
}
#[getter]
fn opcode(&self) -> &'static str {
self.0.op.mnemonic()
}
fn __str__(&self) -> String {
FormattedIns(self.0.clone()).to_string()
}
fn fields(&self) -> Vec<(&'static str, i64)> {
self.0
.fields()
.iter()
.flat_map(|field| field.argument().map(|arg| (field.name(), arg.into())))
.collect()
}
}
#[allow(non_snake_case)]
#[pymethods]
impl Ins {
#[getter]
fn simm(&self) -> i64 {
self.0.field_simm() as i64
}
#[getter]
fn uimm(&self) -> i64 {
self.0.field_uimm() as i64
}
#[getter]
fn offset(&self) -> i64 {
self.0.field_offset() as i64
}
#[getter]
fn ps_offset(&self) -> i64 {
self.0.field_ps_offset() as i64
}
#[getter]
fn BO(&self) -> i64 {
self.0.field_BO() as i64
}
#[getter]
fn BI(&self) -> i64 {
self.0.field_BI() as i64
}
#[getter]
fn BD(&self) -> i64 {
self.0.field_BD() as i64
}
#[getter]
fn LI(&self) -> i64 {
self.0.field_LI() as i64
}
#[getter]
fn SH(&self) -> i64 {
self.0.field_SH() as i64
}
#[getter]
fn MB(&self) -> i64 {
self.0.field_SH() as i64
}
#[getter]
fn ME(&self) -> i64 {
self.0.field_SH() as i64
}
#[getter]
fn rS(&self) -> i64 {
self.0.field_rS() as i64
}
#[getter]
fn rD(&self) -> i64 {
self.0.field_rD() as i64
}
#[getter]
fn rA(&self) -> i64 {
self.0.field_rA() as i64
}
#[getter]
fn rB(&self) -> i64 {
self.0.field_rB() as i64
}
#[getter]
fn sr(&self) -> i64 {
self.0.field_sr() as i64
}
#[getter]
fn spr(&self) -> i64 {
self.0.field_spr() as i64
}
#[getter]
fn frS(&self) -> i64 {
self.0.field_frS() as i64
}
#[getter]
fn frD(&self) -> i64 {
self.0.field_frD() as i64
}
#[getter]
fn frA(&self) -> i64 {
self.0.field_frA() as i64
}
#[getter]
fn frB(&self) -> i64 {
self.0.field_frB() as i64
}
#[getter]
fn frC(&self) -> i64 {
self.0.field_frC() as i64
}
#[getter]
fn crbD(&self) -> i64 {
self.0.field_crbD() as i64
}
#[getter]
fn crbA(&self) -> i64 {
self.0.field_crbA() as i64
}
#[getter]
fn crbB(&self) -> i64 {
self.0.field_crbB() as i64
}
#[getter]
fn crfD(&self) -> i64 {
self.0.field_crfD() as i64
}
#[getter]
fn crfS(&self) -> i64 {
self.0.field_crfS() as i64
}
#[getter]
fn crm(&self) -> i64 {
self.0.field_crm() as i64
}
#[getter]
fn ps_I(&self) -> i64 {
self.0.field_ps_I() as i64
}
#[getter]
fn ps_IX(&self) -> i64 {
self.0.field_ps_IX() as i64
}
#[getter]
fn ps_W(&self) -> i64 {
self.0.field_ps_W() as i64
}
#[getter]
fn ps_WX(&self) -> i64 {
self.0.field_ps_WX() as i64
}
#[getter]
fn ps_NB(&self) -> i64 {
self.0.field_NB() as i64
}
#[getter]
fn tbr(&self) -> i64 {
self.0.field_tbr() as i64
}
#[getter]
fn mtfsf_FM(&self) -> i64 {
self.0.field_mtfsf_FM() as i64
}
#[getter]
fn mtfsf_IMM(&self) -> i64 {
self.0.field_mtfsf_IMM() as i64
}
#[getter]
fn TO(&self) -> i64 {
self.0.field_TO() as i64
}
}
impl From<ppc750cl::Ins> for Ins {
fn from(ins: ppc750cl::Ins) -> Self {
Self(ins)
}
}
#[pyclass]
struct DisasmIterator {
bytes: Py<PyBytes>,
addr: u32,
offset: u32,
left: usize,
}
#[pymethods]
impl DisasmIterator {
fn __iter__(slf: PyRef<Self>) -> PyRef<DisasmIterator> {
slf
}
fn __next__(mut slf: PyRefMut<Self>) -> PyResult<Option<Ins>> {
if slf.left < 4 {
return Ok(None);
}
let bytes = slf.bytes.as_ref(slf.py());
let code = ((bytes[(slf.offset) as usize] as u32) << 24)
| ((bytes[(slf.offset + 1) as usize] as u32) << 16)
| ((bytes[(slf.offset + 2) as usize] as u32) << 8)
| (bytes[(slf.offset + 3) as usize] as u32);
slf.offset += 4;
slf.left -= 4;
let ins = Ins::new(code, slf.addr);
slf.addr += 4;
Ok(Some(ins))
}
}
#[pyfunction(code, addr, offset = "0", size = "None")]
fn disasm_iter(
code: &PyBytes,
addr: u32,
offset: u32,
size: Option<u32>,
) -> PyResult<DisasmIterator> {
let left = match size {
None => code.as_bytes().len().saturating_sub(offset as usize),
Some(v) => v as usize,
};
Ok(DisasmIterator {
bytes: code.into(),
addr,
offset,
left,
})
}
#[pymodule]
fn ppc750cl(_: Python, m: &PyModule) -> PyResult<()> {
m.add_class::<Ins>()?;
m.add_wrapped(wrap_pyfunction!(disasm_iter))?;
Ok(())
}

11
disasm/Cargo.toml
View File

@ -1,13 +1,12 @@
[package]
name = "ppc750cl"
version = "0.2.0"
version = "0.3.0"
edition = "2021"
authors = ["Richard Patel <me@terorie.dev>"]
license = "GPL-3.0-or-later"
authors = ["Luke Street <luke@street.dev>"]
license = "MIT OR Apache-2.0"
description = "Disassembler for PowerPC 750CL"
keywords = ["powerpc", "wii", "gamecube"]
repository = "https://github.com/terorie/ppc750cl"
repository = "https://github.com/encounter/ppc750cl"
[dependencies]
num-traits = "0.2"
serde = "1.0"
# Intentionally left blank.

368
disasm/src/disasm.rs Normal file
View File

@ -0,0 +1,368 @@
use core::{
fmt,
fmt::{Display, Formatter, LowerHex},
};
use crate::generated::{
Arguments, Opcode, BASE_MNEMONICS, DEFS_FUNCTIONS, SIMPLIFIED_MNEMONICS, USES_FUNCTIONS,
};
/// A PowerPC 750CL instruction.
#[derive(Default, Clone, Debug, Eq, PartialEq)]
pub struct Ins {
pub code: u32,
pub op: Opcode,
}
impl Ins {
/// Create a new instruction from its raw code.
pub fn new(code: u32) -> Self {
Self { code, op: Opcode::_detect(code) }
}
/// Parse the instruction into a simplified mnemonic, if any match.
pub fn simplified(self) -> SimplifiedIns {
SimplifiedIns::new(self)
}
/// Parse the instruction into its basic form.
pub fn basic_form(self) -> SimplifiedIns {
SimplifiedIns::basic_form(self)
}
/// Returns all registers defined by the instruction.
pub fn defs(&self) -> Arguments {
DEFS_FUNCTIONS[self.op as usize](self)
}
/// Returns all registers used by the instruction.
pub fn uses(&self) -> Arguments {
USES_FUNCTIONS[self.op as usize](self)
}
/// Returns the relative branch offset of the instruction, if any.
pub fn branch_offset(&self) -> Option<i32> {
match self.op {
Opcode::B => Some(self.field_li()),
Opcode::Bc => Some(self.field_bd() as i32),
_ => None,
}
}
/// Returns the absolute branch destination of the instruction, if any.
pub fn branch_dest(&self, addr: u32) -> Option<u32> {
self.branch_offset().and_then(|offset| {
if self.field_aa() {
Some(offset as u32)
} else {
addr.checked_add_signed(offset)
}
})
}
/// Whether the instruction is any kind of branch.
pub fn is_branch(&self) -> bool {
matches!(self.op, Opcode::B | Opcode::Bc | Opcode::Bcctr | Opcode::Bclr)
}
/// Whether the instruction is a direct branch.
pub fn is_direct_branch(&self) -> bool {
matches!(self.op, Opcode::B | Opcode::Bc)
}
/// Whether the instruction is an unconditional branch.
pub fn is_unconditional_branch(&self) -> bool {
match self.op {
Opcode::B => true,
Opcode::Bc | Opcode::Bcctr | Opcode::Bclr => {
self.field_bo() == 20 && self.field_bi() == 0
}
_ => false,
}
}
/// Whether the instruction is a conditional branch.
pub fn is_conditional_branch(&self) -> bool {
self.is_branch() && !self.is_unconditional_branch()
}
/// Whether the instruction is a branch with link. (blr)
#[inline]
pub fn is_blr(&self) -> bool {
self.code == 0x4e800020
}
}
macro_rules! field_arg_no_display {
($name:ident, $typ:ident) => {
#[derive(Debug, Copy, Clone, Ord, PartialOrd, Eq, PartialEq)]
pub struct $name(pub $typ);
impl From<$name> for Argument {
fn from(x: $name) -> Argument {
Argument::$name(x)
}
}
impl From<$typ> for $name {
fn from(x: $typ) -> $name {
$name(x)
}
}
};
}
macro_rules! field_arg {
($name:ident, $typ:ident) => {
field_arg_no_display!($name, $typ);
impl Display for $name {
fn fmt(&self, f: &mut Formatter<'_>) -> fmt::Result {
write!(f, "{}", self.0)
}
}
};
($name:ident, $typ:ident, $format:literal) => {
field_arg_no_display!($name, $typ);
impl Display for $name {
fn fmt(&self, f: &mut Formatter<'_>) -> fmt::Result {
write!(f, $format, self.0)
}
}
};
($name:ident, $typ:ident, $format:literal, $format_arg:expr) => {
field_arg_no_display!($name, $typ);
impl Display for $name {
fn fmt(&self, f: &mut Formatter<'_>) -> fmt::Result {
write!(f, $format, $format_arg(self.0))
}
}
};
}
// General-purpose register.
field_arg!(GPR, u8, "r{}");
// Floating-point register (direct or paired-singles mode).
field_arg!(FPR, u8, "f{}");
// Segment register.
field_arg!(SR, u8);
// Special-purpose register.
field_arg_no_display!(SPR, u16);
impl Display for SPR {
fn fmt(&self, f: &mut Formatter<'_>) -> fmt::Result {
f.write_str(match self.0 {
1 => "XER",
8 => "LR",
9 => "CTR",
18 => "DSISR",
19 => "DAR",
22 => "DEC",
25 => "SDR1",
26 => "SRR0",
27 => "SRR1",
272 => "SPRG0",
273 => "SPRG1",
274 => "SPRG2",
275 => "SPRG3",
282 => "EAR",
287 => "PVR",
528 => "IBAT0U",
529 => "IBAT0L",
530 => "IBAT1U",
531 => "IBAT1L",
532 => "IBAT2U",
533 => "IBAT2L",
534 => "IBAT3U",
535 => "IBAT3L",
536 => "DBAT0U",
537 => "DBAT0L",
538 => "DBAT1U",
539 => "DBAT1L",
540 => "DBAT2U",
541 => "DBAT2L",
542 => "DBAT3U",
543 => "DBAT3L",
912 => "GQR0",
913 => "GQR1",
914 => "GQR2",
915 => "GQR3",
916 => "GQR4",
917 => "GQR5",
918 => "GQR6",
919 => "GQR7",
920 => "HID2",
921 => "WPAR",
922 => "DMA_U",
923 => "DMA_L",
936 => "UMMCR0",
937 => "UPMC1",
938 => "UPMC2",
939 => "USIA",
940 => "UMMCR1",
941 => "UPMC3",
942 => "UPMC4",
943 => "USDA",
952 => "MMCR0",
953 => "PMC1",
954 => "PMC2",
955 => "SIA",
956 => "MMCR1",
957 => "PMC3",
958 => "PMC4",
959 => "SDA",
1008 => "HID0",
1009 => "HID1",
1010 => "IABR",
1013 => "DABR",
1017 => "L2CR",
1019 => "ICTC",
1020 => "THRM1",
1021 => "THRM2",
1022 => "THRM3",
_ => return write!(f, "{}", self.0),
})
}
}
// Condition register field.
field_arg!(CRField, u8, "cr{}");
// Condition register bit (index + condition case).
field_arg_no_display!(CRBit, u8);
impl Display for CRBit {
fn fmt(&self, f: &mut Formatter<'_>) -> fmt::Result {
let cr = self.0 >> 2;
let cc = self.0 & 3;
if cr != 0 {
write!(f, "{}", CRField(cr))?;
}
const CR_NAMES: [&str; 4] = ["lt", "gt", "eq", "un"];
f.write_str(CR_NAMES[cc as usize])
}
}
// Paired-single graphics quantization register
field_arg!(GQR, u8, "qr{}");
// Unsigned immediate.
field_arg!(Uimm, u16, "{:#x}");
// Signed immediate.
field_arg!(Simm, i16, "{:#x}", SignedHexLiteral);
// Offset for indirect memory reference.
field_arg!(Offset, i16, "{:#x}", SignedHexLiteral);
// Branch destination.
field_arg!(BranchDest, i32, "{:#x}", SignedHexLiteral);
impl From<i16> for BranchDest {
fn from(x: i16) -> BranchDest {
BranchDest(x as i32)
}
}
// Unsigned opaque argument.
field_arg!(OpaqueU, u16);
impl From<u8> for OpaqueU {
fn from(x: u8) -> OpaqueU {
OpaqueU(x as u16)
}
}
#[derive(Debug, Default, Clone, Eq, PartialEq)]
pub enum Argument {
#[default]
None,
GPR(GPR),
FPR(FPR),
SR(SR),
SPR(SPR),
CRField(CRField),
CRBit(CRBit),
GQR(GQR),
Uimm(Uimm),
Simm(Simm),
Offset(Offset),
BranchDest(BranchDest),
OpaqueU(OpaqueU),
}
impl Display for Argument {
fn fmt(&self, f: &mut Formatter<'_>) -> fmt::Result {
match self {
Argument::None => Ok(()),
Argument::GPR(x) => x.fmt(f),
Argument::FPR(x) => x.fmt(f),
Argument::SR(x) => x.fmt(f),
Argument::SPR(x) => x.fmt(f),
Argument::CRField(x) => x.fmt(f),
Argument::CRBit(x) => x.fmt(f),
Argument::GQR(x) => x.fmt(f),
Argument::Uimm(x) => x.fmt(f),
Argument::Simm(x) => x.fmt(f),
Argument::Offset(x) => x.fmt(f),
Argument::BranchDest(x) => x.fmt(f),
Argument::OpaqueU(x) => x.fmt(f),
}
}
}
/// A simplified PowerPC 750CL instruction.
pub struct SimplifiedIns {
pub ins: Ins,
pub mnemonic: &'static str,
pub args: Arguments,
}
impl SimplifiedIns {
pub fn new(ins: Ins) -> Self {
let (mnemonic, args) = SIMPLIFIED_MNEMONICS[ins.op as usize](&ins);
Self { ins, mnemonic, args }
}
pub fn basic_form(ins: Ins) -> Self {
let (mnemonic, args) = BASE_MNEMONICS[ins.op as usize](&ins);
Self { ins, mnemonic, args }
}
}
impl Display for SimplifiedIns {
fn fmt(&self, f: &mut Formatter<'_>) -> fmt::Result {
write!(f, "{}", self.mnemonic)?;
let mut writing_offset = false;
for (i, argument) in self.args.iter().enumerate() {
if matches!(argument, Argument::None) {
break;
}
if i == 0 {
write!(f, " ")?;
} else if !writing_offset {
write!(f, ", ")?;
}
write!(f, "{}", argument)?;
if let Argument::Offset(_) = argument {
write!(f, "(")?;
writing_offset = true;
continue;
}
if writing_offset {
write!(f, ")")?;
writing_offset = false;
}
}
Ok(())
}
}
pub struct SignedHexLiteral<T>(pub T);
impl LowerHex for SignedHexLiteral<i16> {
fn fmt(&self, f: &mut Formatter<'_>) -> fmt::Result {
if self.0 < 0 {
write!(f, "-")?;
LowerHex::fmt(&-(self.0 as i32), f)
} else {
LowerHex::fmt(&self.0, f)
}
}
}
impl LowerHex for SignedHexLiteral<i32> {
fn fmt(&self, f: &mut Formatter<'_>) -> fmt::Result {
if self.0 < 0 {
write!(f, "-")?;
LowerHex::fmt(&-(self.0 as i64), f)
} else {
LowerHex::fmt(&self.0, f)
}
}
}

33
disasm/src/formatter.rs
View File

@ -1,33 +0,0 @@
use std::fmt::{Display, Formatter};
use crate::prelude::*;
pub struct FormattedIns(pub Ins);
impl Display for FormattedIns {
fn fmt(&self, f: &mut Formatter<'_>) -> std::fmt::Result {
let simple = self.0.clone().simplified();
write!(f, "{}{}", simple.mnemonic, simple.suffix)?;
let mut writing_offset = false;
for (i, arg) in simple.args.iter().enumerate() {
if i == 0 {
write!(f, " ")?;
}
if i > 0 && !writing_offset {
write!(f, ", ")?;
}
if let Argument::Offset(val) = arg {
write!(f, "{}(", val)?;
writing_offset = true;
continue;
} else {
write!(f, "{}", arg)?;
}
if writing_offset {
write!(f, ")")?;
writing_offset = false;
}
}
Ok(())
}
}

19292
disasm/src/generated.rs
View File

File diff suppressed because it is too large Load Diff

34
disasm/src/iter.rs
View File

@ -1,34 +0,0 @@
use crate::Ins;
/// Returns an iterator of instructions in the given byte slice.
pub fn disasm_iter(code: &[u8], addr: u32) -> DisasmIterator {
DisasmIterator { code, addr }
}
pub struct DisasmIterator<'a> {
code: &'a [u8],
addr: u32,
}
impl<'a> Iterator for DisasmIterator<'a> {
type Item = Ins;
fn next(&mut self) -> Option<Self::Item> {
if self.code.len() < 4 {
return None;
}
let code = ((self.code[0] as u32) << 24)
| ((self.code[1] as u32) << 16)
| ((self.code[2] as u32) << 8)
| (self.code[3] as u32);
self.code = &self.code[4..];
let addr = self.addr;
self.addr += 4;
Some(Ins::new(code, addr))
}
fn size_hint(&self) -> (usize, Option<usize>) {
let count = self.code.len() / 4;
(count, Some(count))
}
}

463
disasm/src/lib.rs
View File

@ -1,458 +1,9 @@
use std::fmt::{Display, Formatter, LowerHex, UpperHex, Write};
use std::ops::Range;
use num_traits::{AsPrimitive, PrimInt};
pub use crate::iter::{disasm_iter, DisasmIterator};
pub mod formatter;
#![no_std]
mod disasm;
mod generated;
mod iter;
pub use generated::*;
pub mod prelude {
pub use crate::formatter::FormattedIns;
pub use crate::Argument;
pub use crate::Field::*;
pub use crate::Ins;
pub use crate::Opcode::*;
pub use crate::SimplifiedIns;
pub use crate::{
Bit, BranchDest, CRBit, CRField, Offset, OpaqueU, Simm, Uimm, FPR, GPR, GQR, SPR, SR,
};
}
macro_rules! field_arg_no_display {
($name:ident, $typ:ident) => {
#[derive(Debug, Copy, Clone, Ord, PartialOrd, Eq, PartialEq)]
pub struct $name(pub $typ);
impl std::convert::From<$name> for Argument {
fn from(x: $name) -> Argument {
Argument::$name(x)
}
}
};
}
macro_rules! field_arg {
($name:ident, $typ:ident) => {
field_arg_no_display!($name, $typ);
impl Display for $name {
fn fmt(&self, f: &mut Formatter<'_>) -> std::fmt::Result {
write!(f, "{}", self.0)
}
}
};
($name:ident, $typ:ident, $format:literal) => {
field_arg_no_display!($name, $typ);
impl Display for $name {
fn fmt(&self, f: &mut Formatter<'_>) -> std::fmt::Result {
write!(f, $format, self.0)
}
}
};
($name:ident, $typ:ident, $format:literal, $format_arg:expr) => {
field_arg_no_display!($name, $typ);
impl Display for $name {
fn fmt(&self, f: &mut Formatter<'_>) -> std::fmt::Result {
write!(f, $format, $format_arg(self.0))
}
}
};
}
#[inline(always)]
fn bit(x: u32, idx: usize) -> bool {
((x >> (32 - idx - 1)) & 1) == 1
}
#[inline(always)]
fn bits<F>(x: u32, range: Range<usize>) -> F
where
F: 'static + std::marker::Copy,
u32: AsPrimitive<F>,
{
let masked: u32 = (x >> (32 - range.end)) & ((1 << range.len()) - 1);
masked.as_()
}
// https://stackoverflow.com/questions/44711012/how-do-i-format-a-signed-integer-to-a-sign-aware-hexadecimal-representation
struct ReallySigned<N: PrimInt>(N);
impl<N: PrimInt> LowerHex for ReallySigned<N> {
fn fmt(&self, f: &mut std::fmt::Formatter) -> std::fmt::Result {
let num = self.0.to_i32().unwrap();
let prefix = if f.alternate() { "0x" } else { "" };
let bare_hex = format!("{:x}", num.abs());
f.pad_integral(num >= 0, prefix, &bare_hex)
}
}
impl<N: PrimInt> UpperHex for ReallySigned<N> {
fn fmt(&self, f: &mut std::fmt::Formatter) -> std::fmt::Result {
let num = self.0.to_i32().unwrap();
let prefix = if f.alternate() { "0x" } else { "" };
let bare_hex = format!("{:X}", num.abs());
f.pad_integral(num >= 0, prefix, &bare_hex)
}
}
// General-purpose register.
field_arg!(GPR, u8, "r{}");
// Floating-point register (direct or paired-singles mode).
field_arg!(FPR, u8, "f{}");
// Segment register.
field_arg!(SR, u8);
// Special-purpose register.
field_arg_no_display!(SPR, u16);
impl Display for SPR {
fn fmt(&self, f: &mut Formatter<'_>) -> std::fmt::Result {
f.write_str(match self.0 {
1 => "XER",
8 => "LR",
9 => "CTR",
18 => "DSISR",
19 => "DAR",
22 => "DEC",
25 => "SDR1",
26 => "SRR0",
27 => "SRR1",
272 => "SPRG0",
273 => "SPRG1",
274 => "SPRG2",
275 => "SPRG3",
282 => "EAR",
287 => "PVR",
528 => "IBAT0U",
529 => "IBAT0L",
530 => "IBAT1U",
531 => "IBAT1L",
532 => "IBAT2U",
533 => "IBAT2L",
534 => "IBAT3U",
535 => "IBAT3L",
536 => "DBAT0U",
537 => "DBAT0L",
538 => "DBAT1U",
539 => "DBAT1L",
540 => "DBAT2U",
541 => "DBAT2L",
542 => "DBAT3U",
543 => "DBAT3L",
912 => "GQR0",
913 => "GQR1",
914 => "GQR2",
915 => "GQR3",
916 => "GQR4",
917 => "GQR5",
918 => "GQR6",
919 => "GQR7",
920 => "HID2",
921 => "WPAR",
922 => "DMA_U",
923 => "DMA_L",
936 => "UMMCR0",
937 => "UPMC1",
938 => "UPMC2",
939 => "USIA",
940 => "UMMCR1",
941 => "UPMC3",
942 => "UPMC4",
943 => "USDA",
952 => "MMCR0",
953 => "PMC1",
954 => "PMC2",
955 => "SIA",
956 => "MMCR1",
957 => "PMC3",
958 => "PMC4",
959 => "SDA",
1008 => "HID0",
1009 => "HID1",
1010 => "IABR",
1013 => "DABR",
1017 => "L2CR",
1019 => "ICTC",
1020 => "THRM1",
1021 => "THRM2",
1022 => "THRM3",
_ => return write!(f, "{}", self.0),
})
}
}
// Condition register field.
field_arg!(CRField, u8, "cr{}");
// Condition register bit (index + condition case).
field_arg_no_display!(CRBit, u8);
impl Display for CRBit {
fn fmt(&self, f: &mut Formatter<'_>) -> std::fmt::Result {
let cr = self.0 >> 2;
let cc = self.0 & 3;
if cr != 0 {
write!(f, "{}", CRField(cr))?;
}
const CR_NAMES: [&str; 4] = ["lt", "gt", "eq", "un"];
f.write_str(CR_NAMES[cc as usize])
}
}
// Paired-single graphics quantization register
field_arg!(GQR, u8, "qr{}");
// Unsigned immediate.
field_arg!(Uimm, u16, "{:#x}");
// Signed immediate.
field_arg!(Simm, i16, "{:#x}", ReallySigned);
// Offset for indirect memory reference.
field_arg!(Offset, i16, "{:#x}", ReallySigned);
// Branch destination.
field_arg!(BranchDest, i32, "{:#x}", ReallySigned);
// Opaque zero or one argument.
field_arg_no_display!(Bit, bool);
impl Display for Bit {
fn fmt(&self, f: &mut Formatter<'_>) -> std::fmt::Result {
f.write_char(if self.0 { '1' } else { '0' })
}
}
// Unsigned opaque argument.
field_arg!(OpaqueU, u32);
#[derive(Debug, Clone, Eq, PartialEq)]
pub enum Argument {
GPR(GPR),
FPR(FPR),
SR(SR),
SPR(SPR),
CRField(CRField),
CRBit(CRBit),
GQR(GQR),
Uimm(Uimm),
Simm(Simm),
Offset(Offset),
BranchDest(BranchDest),
Bit(Bit),
OpaqueU(OpaqueU),
}
impl Display for Argument {
fn fmt(&self, f: &mut Formatter<'_>) -> std::fmt::Result {
match self {
Argument::GPR(x) => x.fmt(f),
Argument::FPR(x) => x.fmt(f),
Argument::SR(x) => x.fmt(f),
Argument::SPR(x) => x.fmt(f),
Argument::CRField(x) => x.fmt(f),
Argument::CRBit(x) => x.fmt(f),
Argument::GQR(x) => x.fmt(f),
Argument::Uimm(x) => x.fmt(f),
Argument::Simm(x) => x.fmt(f),
Argument::Offset(x) => x.fmt(f),
Argument::BranchDest(x) => x.fmt(f),
Argument::Bit(x) => x.fmt(f),
Argument::OpaqueU(x) => x.fmt(f),
}
}
}
impl From<Argument> for i64 {
fn from(arg: Argument) -> Self {
match arg {
Argument::GPR(x) => x.0 as i64,
Argument::FPR(x) => x.0 as i64,
Argument::SR(x) => x.0 as i64,
Argument::SPR(x) => x.0 as i64,
Argument::CRField(x) => x.0 as i64,
Argument::CRBit(x) => x.0 as i64,
Argument::GQR(x) => x.0 as i64,
Argument::Uimm(x) => x.0 as i64,
Argument::Simm(x) => x.0 as i64,
Argument::Offset(x) => x.0 as i64,
Argument::BranchDest(x) => x.0 as i64,
Argument::Bit(x) => x.0 as i64,
Argument::OpaqueU(x) => x.0 as i64,
}
}
}
impl TryInto<Argument> for &Field {
type Error = ();
fn try_into(self) -> Result<Argument, Self::Error> {
self.argument().ok_or(())
}
}
impl Opcode {
/// Detects the opcode of a machine code instruction.
pub fn detect(code: u32) -> Self {
Self::_detect(code) // auto-generated
}
/// Prints the basic mnemonic of an opcode.
pub fn mnemonic(self) -> &'static str {
self._mnemonic() // auto-generated
}
}
impl Default for Opcode {
fn default() -> Self {
Opcode::Illegal
}
}
impl std::string::ToString for Opcode {
fn to_string(&self) -> String {
let mnemonic = self.mnemonic();
mnemonic.to_owned()
}
}
/// A PowerPC 750CL instruction.
#[derive(Default, Clone, Debug, Eq, PartialEq)]
pub struct Ins {
pub code: u32,
pub addr: u32,
pub op: Opcode,
}
impl Ins {
const BLR: u32 = 0x4e800020;
/// Constructs an instruction from the given machine code and address.
pub fn new(code: u32, addr: u32) -> Self {
Self {
code,
addr,
op: Opcode::detect(code),
}
}
/// Returns the simplified representation of an instruction.
pub fn simplified(self) -> SimplifiedIns {
self._simplified() // auto-generated
}
/// Gets the fields of an instruction.
pub fn fields(&self) -> Vec<Field> {
self._fields() // auto-generated
}
/// Gets the suffix of an instruction mnemonic.
pub fn suffix(&self) -> String {
self._suffix() // auto-generated
}
/// Gets the defs of an instruction.
pub fn defs(&self) -> Vec<Field> {
self._defs() // auto-generated
}
/// Gets the uses of an instruction.
pub fn uses(&self) -> Vec<Field> {
self._uses() // auto-generated
}
/// Gets the given bit from the machine code instruction.
pub fn bit(&self, idx: usize) -> bool {
bit(self.code, idx)
}
/// Gets the given range of btis from the machine code instruction.
pub fn bits(&self, range: Range<usize>) -> u32 {
bits(self.code, range)
}
pub fn branch_offset(&self) -> Option<i32> {
match self.op {
Opcode::B => Some(self.field_LI() as i32),
Opcode::Bc => Some(self.field_BD() as i32),
_ => None,
}
}
pub fn branch_dest(&self) -> Option<u32> {
self.branch_offset().and_then(|offset| {
if self.field_AA() {
Some(offset as u32)
} else if offset < 0 {
self.addr.checked_sub((-offset) as u32)
} else {
self.addr.checked_add(offset as u32)
}
})
}
pub fn is_branch(&self) -> bool {
matches!(
self.op,
Opcode::B | Opcode::Bc | Opcode::Bcctr | Opcode::Bclr
)
}
pub fn is_direct_branch(&self) -> bool {
matches!(self.op, Opcode::B | Opcode::Bc)
}
pub fn is_unconditional_branch(&self) -> bool {
match self.op {
Opcode::B => true,
Opcode::Bc | Opcode::Bcctr | Opcode::Bclr => {
self.field_BO() == 20 && self.field_BI() == 0
}
_ => false,
}
}
pub fn is_conditional_branch(&self) -> bool {
self.is_branch() && !self.is_unconditional_branch()
}
#[inline]
pub fn is_blr(&self) -> bool {
// self.op == Opcode::Bclr && self.is_unconditional_branch() && !self.field_LK()
self.code == Ins::BLR
}
}
/// A simplified PowerPC 750CL instruction.
pub struct SimplifiedIns {
pub ins: Ins,
pub mnemonic: &'static str,
pub suffix: String,
pub args: Vec<Argument>,
}
impl Display for SimplifiedIns {
fn fmt(&self, f: &mut Formatter<'_>) -> std::fmt::Result {
write!(f, "{}{} ", self.mnemonic, self.suffix)?;
let mut writing_offset = false;
for (i, argument) in self.args.iter().enumerate() {
write!(f, "{}", argument)?;
if let Argument::Offset(_) = argument {
write!(f, "(")?;
writing_offset = true;
continue;
}
if writing_offset {
write!(f, ")")?;
writing_offset = false;
}
if i != self.args.len() - 1 {
write!(f, ", ")?;
}
}
Ok(())
}
}
impl SimplifiedIns {
pub fn basic_form(ins: Ins) -> Self {
Self {
mnemonic: ins.op.mnemonic(),
suffix: ins.suffix(),
args: ins
.fields()
.iter()
.flat_map(|field| field.argument())
.collect(),
ins,
}
}
}
pub use disasm::{
Argument, BranchDest, CRBit, CRField, Ins, Offset, OpaqueU, Simm, SimplifiedIns, Uimm, FPR,
GPR, GQR, SPR, SR,
};
pub use generated::{Arguments, Opcode};

74
disasm/tests/test_disasm.rs
View File

@ -1,12 +1,22 @@
use ppc750cl::prelude::*;
use ppc750cl::{Argument, Ins, Opcode, SimplifiedIns, FPR, GPR};
macro_rules! assert_asm {
($ins:ident, $disasm:literal) => {{
assert_eq!(format!("{}", FormattedIns($ins)), $disasm)
assert_eq!(format!("{}", SimplifiedIns::new($ins)), $disasm)
}};
($code:literal, $disasm:literal) => {{
let ins = Ins::new($code, 0x8000_0000);
assert_eq!(format!("{}", FormattedIns(ins)), $disasm)
let ins = Ins::new($code);
assert_eq!(format!("{}", SimplifiedIns::new(ins)), $disasm)
}};
}
macro_rules! assert_basic {
($ins:ident, $disasm:literal) => {{
assert_eq!(format!("{}", SimplifiedIns::basic_form($ins)), $disasm)
}};
($code:literal, $disasm:literal) => {{
let ins = Ins::new($code);
assert_eq!(format!("{}", SimplifiedIns::basic_form(ins)), $disasm)
}};
}
@ -20,9 +30,9 @@ fn test_ins_add() {
#[test]
fn test_ins_addc() {
let ins = Ins::new(0x7c002014, 0x8000_0000u32);
assert_eq!(ins.op, Addc);
assert_eq!(ins.fields(), vec![rD(GPR(0)), rA(GPR(0)), rB(GPR(4))]);
let ins = Ins::new(0x7c002014);
assert_eq!(ins.op, Opcode::Addc);
// assert_eq!(ins.fields(), vec![rD(GPR(0)), rA(GPR(0)), rB(GPR(4))]);
assert_asm!(ins, "addc r0, r0, r4");
assert_asm!(0x7C432014, "addc r2, r3, r4");
assert_asm!(0x7CE62815, "addc. r7, r6, r5");
@ -32,14 +42,20 @@ fn test_ins_addc() {
#[test]
fn test_ins_addi() {
let ins = Ins::new(0x38010140, 0x8000_0000u32);
assert_eq!(ins.op, Addi);
let ins = Ins::new(0x38010140);
assert_eq!(ins.op, Opcode::Addi);
// assert_eq!(
// ins.fields(),
// vec![rD(GPR(0)), rA(GPR(1)), simm(Simm(0x140))]
// );
assert_eq!(
ins.fields(),
vec![rD(GPR(0)), rA(GPR(1)), simm(Simm(0x140))]
ins.defs(),
[Argument::GPR(GPR(0)), Argument::None, Argument::None, Argument::None, Argument::None]
);
assert_eq!(
ins.uses(),
[Argument::GPR(GPR(1)), Argument::None, Argument::None, Argument::None, Argument::None]
);
assert_eq!(ins.defs(), vec![rD(GPR(0))]);
assert_eq!(ins.uses(), vec![rA(GPR(1))]);
assert_asm!(ins, "addi r0, r1, 0x140");
assert_asm!(0x38010008, "addi r0, r1, 0x8");
@ -48,6 +64,7 @@ fn test_ins_addi() {
assert_asm!(0x38010140, "addi r0, r1, 0x140");
assert_asm!(0x38049000, "subi r0, r4, 0x7000");
assert_asm!(0x38a00000, "li r5, 0x0");
assert_basic!(0x38a00000, "addi r5, r0, 0x0");
}
#[test]
@ -710,20 +727,26 @@ fn test_ins_psq_lu() {
#[test]
fn test_ins_psq_lx() {
let ins = Ins::new(0x1000000C, 0x8000_0000u32);
assert_eq!(ins.op, PsqLx);
let ins = Ins::new(0x1000000C);
assert_eq!(ins.op, Opcode::PsqLx);
// assert_eq!(
// ins.fields(),
// vec![
// frD(FPR(0)),
// rA(GPR(0)),
// rB(GPR(0)),
// ps_WX(OpaqueU(0)),
// ps_IX(GQR(0)),
// ]
// );
assert_eq!(
ins.fields(),
vec![
frD(FPR(0)),
rA(GPR(0)),
rB(GPR(0)),
ps_WX(OpaqueU(0)),
ps_IX(GQR(0)),
]
ins.defs(),
[Argument::FPR(FPR(0)), Argument::None, Argument::None, Argument::None, Argument::None]
);
assert_eq!(
ins.uses(),
[Argument::None, Argument::GPR(GPR(0)), Argument::None, Argument::None, Argument::None]
);
assert_eq!(ins.defs(), vec![frD(FPR(0))]);
assert_eq!(ins.uses(), vec![rB(GPR(0))]);
assert_asm!(0x1000000C, "psq_lx f0, r0, r0, 0, qr0");
}
@ -885,6 +908,7 @@ fn test_ins_rlwimi() {
fn test_ins_rlwinm() {
assert_asm!(0x54000423, "rlwinm. r0, r0, 0, 16, 17");
assert_asm!(0x54000432, "rlwinm r0, r0, 0, 16, 25");
assert_basic!(0x54096226, "rlwinm r9, r0, 12, 8, 19");
// mnemonics
assert_asm!(0x57E5103A, "slwi r5, r31, 2");

13
dol/Cargo.toml
View File

@ -1,13 +0,0 @@
[package]
name = "dol"
version = "0.1.0"
edition = "2021"
authors = ["Richard Patel <me@terorie.dev>"]
license = "GPL-3.0-or-later"
description = "Deserializer for the DOL executable format"
repository = "https://github.com/terorie/ppc750cl"
[dependencies]
bincode = "1.3"
serde = { version = "1.0", features = ["derive"] }
thiserror = "1.0"

237
dol/src/lib.rs
View File

@ -1,237 +0,0 @@
use std::io::{Read, Seek, SeekFrom};
use bincode::Options;
use serde::{Deserialize, Serialize};
use thiserror::Error;
/// A loaded DOL executable.
pub struct Dol {
pub header: DolHeader,
pub memory: Vec<u8>,
pub memory_offset: u32,
}
/// An error that can be raised during DOL parsing.
#[derive(Error, Debug)]
pub enum Error {
#[error("{0}")]
BincodeError(bincode::Error),
#[error("{0}")]
IOError(std::io::Error),
#[error("No sections in DOL")]
NoSections,
#[error("Overlapping sections: {0:8>X} {1:8>X}")]
OverlappingSections(u32, u32),
#[error("Section sizes too large")]
SectionsTooLarge,
#[error("Attempted to access {0:08X} past DOL bounds")]
OutOfBounds(u32),
}
impl From<bincode::Error> for Error {
fn from(e: bincode::Error) -> Self {
Self::BincodeError(e)
}
}
impl From<std::io::Error> for Error {
fn from(e: std::io::Error) -> Self {
Self::IOError(e)
}
}
/// The result of a DOL parsing.
pub type Result<V> = std::result::Result<V, Error>;
impl Dol {
/// Reads a DOL executable from a `Reader`.
pub fn read_from<R>(mut r: R) -> Result<Self>
where
R: Read + Seek,
{
// Read header.
let header_data = DolHeaderData::read_from(&mut r)?;
let header: DolHeader = (&header_data).into();
Dol::read_with_header(r, header)
}
/// Reads a DOL body from a `Reader` given a header.
pub fn read_with_header<R>(mut r: R, header: DolHeader) -> Result<Self>
where
R: Read + Seek,
{
let dol_start = r.stream_position()? - DolHeaderData::SERIALIZED_SIZE;
if header.sections.is_empty() {
return Err(Error::NoSections);
}
/*
// Verify that sections are not overlapping.
let mut end_target_addr = 0u32;
for section in &header.sections {
if section.target < end_target_addr {
return Err(Error::OverlappingSections(end_target_addr, section.target));
}
end_target_addr = section.target + section.size
}
*/
// Remember the memory offset of the first section.
// Then shift all sections to the beginning of memory.
let memory_offset = header.sections[0].target;
// Get the size of all sections combined.
let mut total_size = 0usize;
for section in &header.sections {
if let Some(sum) = total_size.checked_add(section.size as usize) {
total_size = sum;
} else {
return Err(Error::SectionsTooLarge);
}
}
// Cannot be larger than 24 MiB.
if total_size > 0x180_0000 {
return Err(Error::SectionsTooLarge);
}
// Create memory.
let mut memory = vec![0u8; total_size];
// Read sections into memory.
for section in &header.sections {
if section.kind == DolSectionType::Bss {
continue;
}
r.seek(SeekFrom::Start(dol_start + section.offset as u64))?;
let mem_start = (section.target - memory_offset) as usize;
let mem_end = mem_start + section.size as usize;
r.read_exact(&mut memory[mem_start..mem_end])?;
}
Ok(Self {
header,
memory,
memory_offset,
})
}
pub fn section_data(&self, section: &DolSection) -> &[u8] {
self.virtual_data_at(section.target, section.size).unwrap()
}
/// Returns a slice of DOL data. Does not support bss.
pub fn virtual_data_at(&self, virtual_addr: u32, read_len: u32) -> Result<&[u8]> {
if virtual_addr < self.memory_offset {
return Err(Error::OutOfBounds(virtual_addr));
}
let offset = (virtual_addr - self.memory_offset) as usize;
if offset + (read_len as usize) < self.memory.len() {
Ok(&self.memory[offset..offset + (read_len as usize)])
} else {
Err(Error::OutOfBounds(virtual_addr + read_len))
}
}
/// Reads bytes into a destination buffer given a virtual address.
pub fn virtual_read(&self, data: &mut [u8], virtual_addr: u32) -> Result<()> {
if virtual_addr < self.memory_offset {
return Err(Error::OutOfBounds(virtual_addr));
}
let offset = (virtual_addr - self.memory_offset) as usize;
let read_len = data.len();
if offset + read_len < self.memory.len() {
data.copy_from_slice(&self.memory[offset..offset + data.len()]);
Ok(())
} else {
Err(Error::OutOfBounds(virtual_addr + (read_len as u32)))
}
}
}
#[derive(Debug, Clone, Copy, Eq, PartialEq)]
pub enum DolSectionType {
Text,
Data,
Bss,
}
#[derive(Debug, Clone)]
pub struct DolSection {
pub kind: DolSectionType,
pub index: usize,
pub offset: u32,
pub target: u32,
pub size: u32,
}
pub struct DolHeader {
pub sections: Vec<DolSection>,
pub entry_point: u32,
}
impl From<&DolHeaderData> for DolHeader {
fn from(header: &DolHeaderData) -> Self {
let mut sections = Vec::with_capacity(DolHeaderData::SECTION_COUNT);
for i in 0..DolHeaderData::SECTION_COUNT {
let kind = if i < 7 {
DolSectionType::Text
} else {
DolSectionType::Data
};
if header.section_sizes[i] > 0 {
sections.push(DolSection {
kind,
index: i,
offset: header.section_offsets[i],
target: header.section_targets[i],
size: header.section_sizes[i],
});
}
}
if header.bss_target > 0 {
sections.push(DolSection {
kind: DolSectionType::Bss,
index: 0,
offset: 0,
target: header.bss_target,
size: header.bss_size,
})
}
// Sort sections by target address to prepare them for mapping.
sections.sort_by_key(|s| s.target);
Self {
sections,
entry_point: header.entry_point,
}
}
}
impl DolHeader {
pub fn section_at(&self, addr: u32) -> Option<&DolSection> {
self.sections
.iter()
.find(|&section| (section.target..(section.target + section.size)).contains(&addr))
}
}
#[derive(Debug, Serialize, Deserialize)]
pub struct DolHeaderData {
pub section_offsets: [u32; Self::SECTION_COUNT],
pub section_targets: [u32; Self::SECTION_COUNT],
pub section_sizes: [u32; Self::SECTION_COUNT],
pub bss_target: u32,
pub bss_size: u32,
pub entry_point: u32,
pub padding: [u8; 0x1c],
}
impl DolHeaderData {
const SECTION_COUNT: usize = 18;
const SERIALIZED_SIZE: u64 = 0x100;
/// Reads the DOL header from a `Reader`.
pub fn read_from<R: Read + Seek>(mut r: R) -> bincode::Result<Self> {
bincode::DefaultOptions::new()
.with_big_endian()
.allow_trailing_bytes()
.with_fixint_encoding()
.deserialize_from(&mut r)
}
}

16
flow-graph/Cargo.toml
View File

@ -1,16 +0,0 @@
[package]
name = "ppc750cl-flow-graph"
version = "0.2.0"
edition = "2021"
authors = ["riidefi <riidefi@rii.dev>", "Richard Patel <me@terorie.dev>"]
license = "GPL-3.0-or-later"
description = "Control flow graph analysis for PowerPC 750CL"
repository = "https://github.com/terorie/ppc750cl"
[dependencies]
clap = "3"
dol = { version = "0.1.0", path = "../dol" }
itertools = "0.10"
parse_int = "0.6"
petgraph = "0.6"
ppc750cl = { version = "0.2.0", path = "../disasm" }

178
flow-graph/src/flow.rs
View File

@ -1,178 +0,0 @@
use std::collections::{BTreeMap, HashMap};
use std::fmt::{Debug, Display, Formatter};
use std::hash::{Hash, Hasher};
use std::ops::{Index, Range};
use itertools::Itertools;
use petgraph::algo::dominators::Dominators;
use petgraph::graph::{DefaultIx, NodeIndex};
use petgraph::Graph;
use ppc750cl::formatter::FormattedIns;
use ppc750cl::{Ins, Opcode};
use crate::slices::{BasicSlices, CodeIdx};
#[derive(Default)]
pub struct BasicBlock<'a> {
pub range: Range<CodeIdx>,
pub code: &'a [Ins],
pub data_refs: HashMap<CodeIdx, u32>,
}
impl<'a> PartialEq for BasicBlock<'a> {
fn eq(&self, other: &Self) -> bool {
self.range == other.range
}
}
impl<'a> Eq for BasicBlock<'a> {}
impl<'a> Hash for BasicBlock<'a> {
fn hash<H: Hasher>(&self, state: &mut H) {
self.range.hash(state)
}
}
impl<'a> BasicBlock<'a> {
pub fn from_code_slice(range: Range<CodeIdx>, complete_code: &'a [Ins]) -> BasicBlock {
let start_idx = complete_code.first().unwrap().addr / 4;
assert!(start_idx <= range.start);
let offset = (range.start - start_idx) as usize;
let code = &complete_code[offset..(offset + (range.len() as usize))];
BasicBlock {
range,
code,
data_refs: Self::detect_data_refs(code),
}
}
/// Very simple algorithm to detect data references.
fn detect_data_refs(code: &[Ins]) -> HashMap<CodeIdx, u32> {
let mut defs = HashMap::<u8, u16>::new();
let mut data_refs = HashMap::<CodeIdx, u32>::new();
for ins in code {
match ins.op {
Opcode::Addis => {
if ins.field_rA() == 0 {
// lis
defs.insert(ins.field_rD() as u8, ins.field_uimm() as u16);
} else {
defs.remove(&(ins.field_rD() as u8));
}
}
Opcode::Addi => {
if let Some(hi) = defs.get(&(ins.field_rA() as u8)) {
data_refs.insert(
ins.addr / 4,
((*hi as u32) << 16) + (ins.field_uimm() as u32),
);
}
defs.remove(&(ins.field_rD() as u8));
}
_ => (),
}
}
data_refs
}
}
impl<'a> Display for BasicBlock<'a> {
fn fmt(&self, f: &mut Formatter<'_>) -> std::fmt::Result {
write!(f, "{:0>#8x}", self.range.start * 4)
}
}
impl<'a> Debug for BasicBlock<'a> {
fn fmt(&self, f: &mut Formatter<'_>) -> std::fmt::Result {
writeln!(
f,
"// {:0>#8x}..{:0>#8x}",
self.range.start * 4,
self.range.end * 4
)?;
for ins in self.code {
writeln!(f, "{}", FormattedIns(ins.clone()))?;
if let Some(addr) = self.data_refs.get(&(ins.addr / 4)) {
writeln!(f, " ref: {:0>#8x}", addr)?;
}
}
Ok(())
}
}
/// A control-flow graph of a function.
pub struct FlowGraph<'a> {
pub graph: Graph<BasicBlock<'a>, ()>,
pub root_idx: NodeIndex,
}
impl<'a> FlowGraph<'a> {
/// Creates a control-flow graph from basic slices.
pub fn from_basic_slices(slices: &BasicSlices, code: &'a [Ins]) -> Self {
assert!(!code.is_empty(), "Attempt to create empty flow graph");
// Walk set cuts and create basic blocks.
let mut graph = Graph::new();
let mut node_by_addr = BTreeMap::<u32, NodeIndex<DefaultIx>>::new();
let mut block_start: CodeIdx = code[0].addr / 4;
for cut in &slices.cuts {
if *cut > block_start {
node_by_addr.insert(
block_start,
graph.add_node(BasicBlock::from_code_slice(block_start..*cut, code)),
);
}
block_start = *cut;
}
// Last block.
let func_end: CodeIdx = (code.last().unwrap().addr / 4) + 1;
if func_end > block_start {
node_by_addr.insert(
block_start,
graph.add_node(BasicBlock::from_code_slice(block_start..func_end, code)),
);
}
// Walk set of branches and connect graph.
for branch in &slices.branches {
let src_node_idx = match node_by_addr.range(..branch.0 + 1).last() {
None => continue,
Some(idx) => *idx.1,
};
debug_assert!(graph[src_node_idx].range.contains(&branch.0));
let dst_node_idx = match node_by_addr.range(..branch.1 + 1).last() {
None => continue,
Some(idx) => *idx.1,
};
debug_assert!(graph[dst_node_idx].range.contains(&branch.1));
graph.add_edge(src_node_idx, dst_node_idx, ());
}
// Walk blocks and re-connect nodes that were split off.
for (src_node_idx, dst_node_idx) in node_by_addr.values().tuple_windows::<(_, _)>() {
// Get pairs of two blocks as a sliding window.
let src_block: &BasicBlock = &graph[*src_node_idx];
let dst_block: &BasicBlock = &graph[*dst_node_idx];
assert_eq!(src_block.range.end, dst_block.range.start);
// Get last instruction of left block.
// Unless it's an unconditional branch, we can connect the blocks.
let last_ins = &src_block.code.last().unwrap();
if last_ins.code == 0x4E800020
|| (last_ins.op == Opcode::B && last_ins.field_BO() == 0b10100)
{
continue;
}
// Execution can continue past the last instruction of a block,
// so re-connect two blocks that were split off.
if !graph.contains_edge(*src_node_idx, *dst_node_idx) {
graph.add_edge(*src_node_idx, *dst_node_idx, ());
}
}
Self {
graph,
root_idx: *node_by_addr.index(node_by_addr.keys().next().unwrap()),
}
}
pub fn dominators(&self) -> Dominators<NodeIndex> {
petgraph::algo::dominators::simple_fast(&self.graph, self.root_idx)
}
}

69
flow-graph/src/main.rs
View File

@ -1,69 +0,0 @@
use petgraph::dot::{Config as DotConfig, Dot};
use ppc750cl::{disasm_iter, Ins};
pub mod flow;
pub mod slices;
use crate::flow::FlowGraph;
use crate::slices::BasicSlices;
use dol::Dol;
fn main() {
let matches = clap::Command::new("ppc750cl-flow-graph")
.version("0.2.0")
.about("Control flow graph analysis for PowerPC 750CL")
.arg(
clap::Arg::new("START")
.long("--start")
.required(true)
.takes_value(true)
.help("Start address"),
)
.arg(
clap::Arg::new("STOP")
.long("--stop")
.required(true)
.takes_value(true)
.help("Stop address"),
)
.arg(
clap::Arg::new("INPUT")
.required(true)
.help("Binary input file"),
)
.get_matches();
let start_addr = matches.value_of("START").unwrap();
let start_addr: u32 = ::parse_int::parse(start_addr).expect("Invalid address flag");
let stop_addr = matches.value_of("STOP").unwrap();
let stop_addr: u32 = ::parse_int::parse(stop_addr).expect("Invalid address flag");
let file_path = matches.value_of("INPUT").unwrap();
let dol_file = std::fs::File::open(file_path).expect("Failed to read file");
let dol = Dol::read_from(&dol_file).expect("Invalid DOL file");
drop(dol_file);
let mut bytes = vec![0u8; (stop_addr - start_addr) as usize];
dol.virtual_read(&mut bytes, start_addr)
.expect("Invalid address range");
// Create control flow graph.
let ins_list: Vec<Ins> = disasm_iter(&bytes, start_addr).collect();
let basic_slices = BasicSlices::from_code(&ins_list);
let graph = FlowGraph::from_basic_slices(&basic_slices, &ins_list);
// Output graphviz.
let graphviz = Dot::with_config(
&graph.graph,
&[DotConfig::EdgeNoLabel, DotConfig::GraphContentOnly],
);
println!(
concat!(
"digraph func {{\n",
"node [shape=record fontname=Arial];\n",
"{:?}\n",
"}}"
),
graphviz
);
}

62
flow-graph/src/slices.rs
View File

@ -1,62 +0,0 @@
use std::collections::{BTreeSet, HashSet};
use ppc750cl::{Ins, Opcode};
/// The instruction address divided by four.
pub type CodeIdx = u32;
pub struct BasicSlices {
/// The indexes separating instructions into basic blocks.
/// Used to create a list of consecutive basic blocks.
pub cuts: BTreeSet<CodeIdx>,
/// The possible branches from one instruction to another.
/// Used to link together basic blocks into a directed graph.
pub branches: HashSet<(CodeIdx, CodeIdx)>,
}
impl BasicSlices {
/// Computes basic slices from instructions.
pub fn from_code(code: &[Ins]) -> Self {
let mut cuts = BTreeSet::<CodeIdx>::new();
let mut branches = HashSet::<(CodeIdx, CodeIdx)>::new();
for ins in code {
let cur_index = ins.addr / 4;
let is_control_flow_ins = match ins.op {
// Direct branches are control flow instructions if they don't save the link register.
// If they do, we encountered a function call.
Opcode::B | Opcode::Bc => !ins.field_LK(),
// Switch table
Opcode::Bcctr => panic!("jump tables not supported yet"),
_ => false,
};
if !is_control_flow_ins {
continue;
}
// We encountered some kind of control flow instruction.
if ins.field_BO() == 20 && ins.field_BI() == 0 {
// There's a possibility that branch can be taken.
// Branch destinations are always the first instruction of a block.
// Thus, we also found the end of another block.
let new_index = ins.branch_dest().unwrap() / 4;
cuts.insert(new_index);
branches.insert((cur_index, new_index));
}
if is_conditional_branch(ins) {
// There's a possibility that branch is not taken.
// End block anyways.
cuts.insert(cur_index + 1);
branches.insert((cur_index, cur_index + 1));
}
}
Self { cuts, branches }
}
}
fn is_conditional_branch(ins: &Ins) -> bool {
match ins.op {
Opcode::Bc | Opcode::Bcctr | Opcode::Bclr => (),
_ => return false,
};
// Check whether bits "branch always".
ins.field_BO() & 0b10100 != 0b10100
}

5
fuzz/Cargo.toml
View File

@ -1,13 +1,14 @@
[package]
name = "ppc750cl-fuzz"
version = "0.2.0"
version = "0.3.0"
edition = "2021"
authors = ["Richard Patel <me@terorie.dev>"]
license = "GPL-3.0-or-later"
description = "Complete fuzzer for ppc750cl"
repository = "https://github.com/terorie/ppc750cl"
publish = false
[dependencies]
clap = "3"
num_cpus = "1.13"
ppc750cl = { path = "../disasm", version = "0.2.0" }
ppc750cl = { path = "../disasm" }

10
fuzz/src/main.rs
View File

@ -5,7 +5,6 @@ use std::sync::atomic::{AtomicU32, Ordering};
use std::sync::Arc;
use std::time::{Duration, Instant};
use ppc750cl::formatter::FormattedIns;
use ppc750cl::Ins;
fn main() {
@ -91,10 +90,7 @@ struct Fuzzer {
impl Fuzzer {
fn new(range: Range<u32>) -> Self {
Self {
range,
counter: Arc::new(AtomicU32::new(0)),
}
Self { range, counter: Arc::new(AtomicU32::new(0)) }
}
fn dispatch(&self) -> std::thread::JoinHandle<()> {
@ -104,8 +100,8 @@ impl Fuzzer {
let range = self.range.clone();
std::thread::spawn(move || {
for x in range.clone() {
let ins = Ins::new(x, 0x8000_0000);
writeln!(&mut devnull, "{}", FormattedIns(ins)).unwrap();
let ins = Ins::new(x);
writeln!(&mut devnull, "{}", ins.simplified()).unwrap();
if x % (1 << 19) == 0 {
counter.store(x, Ordering::Relaxed);
}

22
genisa/Cargo.toml
View File

@ -1,17 +1,23 @@
[package]
name = "ppc750cl-genisa"
version = "0.2.0"
version = "0.3.0"
edition = "2021"
authors = ["Richard Patel <me@terorie.dev>"]
license = "GPL-3.0-or-later"
authors = ["Luke Street <luke@street.dev>"]
license = "MIT OR Apache-2.0"
description = "Rust code generator for ppc750cl"
repository = "https://github.com/terorie/ppc750cl"
repository = "https://github.com/encounter/ppc750cl"
publish = false
[dependencies]
itertools = "0.10"
anyhow = "1.0"
log = "0.4"
num-traits = "0.2"
prettyplease = "0.2"
proc-macro2 = "1.0"
quote = "1.0"
syn = "1.0"
serde = { version = "1.0", features = ["derive"] }
serde_yaml = "0.8"
serde_yaml = "0.9"
simple_logger = "4.3"
syn = { version = "2", default-features = false, features = ["full", "parsing"] }
phf = "0.11"
phf_codegen = "0.11"

306
genisa/src/asm.rs Normal file
View File

@ -0,0 +1,306 @@
use crate::condition::{parse_conditions, replace_fields, ConditionOp, ConditionValue};
use crate::isa::{
modifiers_iter, modifiers_valid, to_ident, Field, HexLiteral, Isa, Mnemonic, Opcode,
SignedHexLiteral,
};
use anyhow::{bail, Context, Result};
use proc_macro2::{Literal, TokenStream};
use quote::{format_ident, quote};
use std::collections::HashMap;
pub fn gen_asm(isa: &Isa, max_args: usize) -> Result<TokenStream> {
let mut functions = TokenStream::new();
let mut func_map = phf_codegen::Map::new();
for opcode in &isa.opcodes {
let name = format_ident!("gen_{}", opcode.ident());
let inner = gen_opcode(opcode, isa)?;
functions.extend(quote! {
fn #name(args: &Arguments, modifiers: u32) -> Result<u32, ArgumentError> { #inner }
});
}
let mut mnemonic_map = HashMap::<String, Vec<Mnemonic>>::new();
for mnemonic in &isa.mnemonics {
mnemonic_map.entry(mnemonic.name.clone()).or_default().push(mnemonic.clone());
}
for (name, mnemonics) in &mnemonic_map {
let fn_name = format!("gen_{}", to_ident(name));
let fn_ident = format_ident!("{}", fn_name);
let mut inner;
if mnemonics.len() > 1 {
inner = TokenStream::new();
let mut max_args = 0;
for mnemonic in mnemonics {
let gen = gen_mnemonic(mnemonic, isa, false)?;
let arg_n = Literal::usize_unsuffixed(mnemonic.args.len());
inner.extend(quote! {
#arg_n => { #gen }
});
max_args = max_args.max(mnemonic.args.len());
}
let max_args = Literal::usize_unsuffixed(max_args);
inner.extend(quote! {
value => Err(ArgumentError::ArgCount { value, expected: #max_args })
});
inner = quote! { match arg_count(args) { #inner } };
} else {
inner = gen_mnemonic(mnemonics.first().unwrap(), isa, true)?;
}
functions.extend(quote! {
fn #fn_ident(args: &Arguments, modifiers: u32) -> Result<u32, ArgumentError> { #inner }
});
}
for (opcode, modifiers) in isa.opcodes.iter().flat_map(|o| {
modifiers_iter(&o.modifiers, isa).filter(|m| modifiers_valid(m)).map(move |m| (o, m))
}) {
let suffix = modifiers.iter().map(|m| m.suffix).collect::<String>();
let mut pattern = 0;
for modifier in &modifiers {
pattern |= modifier.mask();
}
func_map.entry(
format!("{}{}", opcode.name, suffix),
&format!("(gen_{}, {:#x})", opcode.ident(), pattern),
);
}
for (mnemonic, modifiers) in mnemonic_map.iter().flat_map(|(_, mnemonics)| {
let mnemonic = mnemonics.first().unwrap();
let opcode = isa.find_opcode(&mnemonic.opcode).unwrap();
let modifiers = mnemonic.modifiers.as_deref().unwrap_or(&opcode.modifiers);
modifiers_iter(modifiers, isa).filter(|m| modifiers_valid(m)).map(move |m| (mnemonic, m))
}) {
let suffix = modifiers.iter().map(|m| m.suffix).collect::<String>();
let mut pattern = 0;
for modifier in &modifiers {
pattern |= modifier.mask();
}
func_map.entry(
format!("{}{}", mnemonic.name, suffix),
&format!("(gen_{}, {:#x})", to_ident(&mnemonic.name), pattern),
);
}
let func_map = syn::parse_str::<TokenStream>(&func_map.build().to_string())?;
let max_args = Literal::usize_unsuffixed(max_args);
Ok(quote! {
#![allow(unused)]
#![cfg_attr(rustfmt, rustfmt_skip)]
use crate::types::*;
pub type Arguments = [Argument; #max_args];
#functions
type MnemonicFn = fn(&Arguments, u32) -> Result<u32, ArgumentError>;
const MNEMONIC_MAP: phf::Map<&'static str, (MnemonicFn, u32)> = #func_map;
pub fn assemble(mnemonic: &str, args: &Arguments) -> Result<u32, ArgumentError> {
if let Some(&(fn_ptr, modifiers)) = MNEMONIC_MAP.get(mnemonic) {
fn_ptr(args, modifiers)
} else {
Err(ArgumentError::UnknownMnemonic)
}
}
})
}
fn gen_parse_field(field: &Field, i: usize) -> Result<(TokenStream, bool)> {
let Some(bits) = field.bits else { bail!("Field {} has no bits", field.name) };
let i = Literal::usize_unsuffixed(i);
Ok(if field.signed {
let max_value = 1 << (bits.len() - 1 + field.shift_left);
let min_value = SignedHexLiteral(-max_value);
let max_value = SignedHexLiteral(max_value);
(quote! { parse_signed(args, #i, #min_value, #max_value)? }, true)
} else {
let min_value = HexLiteral(0);
let max_value = HexLiteral(bits.max_value() << field.shift_left);
(quote! { parse_unsigned(args, #i, #min_value, #max_value)? }, false)
})
}
fn gen_field(
field: &Field,
mut accessor: TokenStream,
finalize: fn(TokenStream) -> TokenStream,
signed: bool,
) -> Result<TokenStream> {
let Some(bits) = field.bits else { bail!("Field {} has no bits", field.name) };
let mut shift_right = bits.shift();
let mut shift_left = field.shift_left;
if shift_right == shift_left {
// Optimization: these cancel each other out
// Adjust subsequent operations to operate on the full value
shift_right = 0;
shift_left = 0;
}
// Handle the operations (in reverse order from disassembly)
let mut operations = TokenStream::new();
let mut inner;
if signed {
accessor = quote! { #accessor as u32 };
}
// Swap 5-bit halves (SPR, TBR)
if field.split {
operations.extend(quote! {
value = ((value & 0b11111_00000) >> 5) | ((value & 0b00000_11111) << 5);
});
inner = quote! { value };
} else {
inner = accessor.clone();
}
// Handle left shift
if shift_left > 0 {
let shift_left = Literal::u8_unsuffixed(shift_left);
inner = quote! { (#inner >> #shift_left) };
}
// Mask
let mask = HexLiteral(bits.mask() >> shift_right);
inner = quote! { #inner & #mask };
// Shift right
if shift_right > 0 {
let shift = Literal::u8_unsuffixed(shift_right);
inner = quote! { (#inner) << #shift };
}
if operations.is_empty() {
Ok(finalize(inner))
} else {
inner = finalize(inner);
Ok(quote! {{
let mut value = #accessor;
#operations
#inner
}})
}
}
fn gen_opcode(opcode: &Opcode, isa: &Isa) -> Result<TokenStream> {
let mut args = TokenStream::new();
for (i, arg) in opcode.args.iter().enumerate() {
let field = isa.find_field(arg).unwrap();
let comment = format!(" {}", field.name);
let (accessor, signed) = gen_parse_field(field, i)?;
let value = gen_field(field, accessor, |s| s, signed)?;
args.extend(quote! {
#[comment = #comment]
code |= #value;
});
}
let arg_count = Literal::usize_unsuffixed(opcode.args.len());
let pattern = HexLiteral(opcode.pattern);
Ok(quote! {
check_arg_count(args, #arg_count)?;
let mut code = #pattern | modifiers;
#args
Ok(code)
})
}
fn gen_mnemonic(mnemonic: &Mnemonic, isa: &Isa, check_arg_count: bool) -> Result<TokenStream> {
let Some(opcode) = isa.find_opcode(&mnemonic.opcode) else {
bail!("Unknown opcode {}", mnemonic.opcode)
};
let mut args = TokenStream::new();
for (i, arg) in mnemonic.args.iter().enumerate() {
let comment = format!(" {}", arg);
let arg = gen_argument(&mnemonic.args, i, isa, mnemonic.replace_assemble.get(arg))?;
args.extend(quote! {
#[comment = #comment]
code |= #arg;
});
}
let mut pattern = opcode.pattern;
for condition in parse_conditions(&mnemonic.condition, isa)? {
if condition.op == ConditionOp::Eq {
match condition.value {
ConditionValue::ConstantUnsigned(value) => {
pattern |= condition.field.shift_value(value);
}
ConditionValue::ConstantSigned(value) => {
pattern |= condition.field.shift_value(value as u32);
}
ConditionValue::Field(in_field) => {
let comment = format!(" {}", condition.field.name);
let arg_n = mnemonic
.args
.iter()
.position(|a| a == &in_field.name)
.with_context(|| {
format!("Mnemonic {}: unknown field {}", mnemonic.name, in_field.name)
})?;
let (accessor, signed) = gen_parse_field(in_field, arg_n)?;
let arg = gen_field(condition.field, accessor, |s| s, signed)?;
args.extend(quote! {
#[comment = #comment]
code |= #arg;
});
}
ConditionValue::Complex(c) => {
let comment = format!(" {}", condition.field.name);
let mut any_signed = false;
let arg = replace_fields(c, isa, |f| {
let arg_n =
mnemonic.args.iter().position(|a| a == &f.name).with_context(|| {
format!("Mnemonic {}: unknown field {}", mnemonic.name, f.name)
})?;
let (s, signed) = gen_parse_field(f, arg_n)?;
any_signed |= signed;
Ok(s)
})?;
let arg = gen_field(condition.field, quote! { (#arg) }, |s| s, any_signed)?;
args.extend(quote! {
#[comment = #comment]
code |= #arg;
});
}
}
}
}
let arg_count = Literal::usize_unsuffixed(mnemonic.args.len());
let mut result = TokenStream::new();
if check_arg_count {
result.extend(quote! { check_arg_count(args, #arg_count)?; });
}
let pattern = HexLiteral(pattern);
result.extend(quote! {
let mut code = #pattern | modifiers;
#args
Ok(code)
});
Ok(result)
}
fn gen_argument(
args: &[String],
arg_n: usize,
isa: &Isa,
replace: Option<&String>,
) -> Result<TokenStream> {
let field = &args[arg_n];
let Some(field) = isa.find_field(field) else { bail!("Unknown field {}", field) };
if let Some(replace) = replace {
let mut any_signed = false;
let stream = replace_fields(replace, isa, |f| {
let arg_n = args.iter().position(|a| a == &f.name).with_context(|| {
format!("Field {} references unknown argument {}", field.name, f.name)
})?;
let (parse, signed) = gen_parse_field(field, arg_n)?;
any_signed |= signed;
Ok(parse)
})?;
gen_field(field, quote! { (#stream) }, |s| s, any_signed)
} else {
let (accessor, signed) = gen_parse_field(field, arg_n)?;
gen_field(field, accessor, |s| s, signed)
}
}

166
genisa/src/condition.rs Normal file
View File

@ -0,0 +1,166 @@
use std::str::FromStr;
use anyhow::{anyhow, Context, Result};
use proc_macro2::{Group, Ident, TokenStream, TokenTree};
use quote::quote;
use crate::isa::{parse_signed, parse_unsigned, Field, HexLiteral, Isa, SignedHexLiteral};
/// A condition that must be met for a modifier to be applied
/// or for a simplified mnemonic to be matched.
#[derive(Clone, Debug)]
pub struct Condition<'a> {
pub field: &'a Field,
pub field_mask: u32,
pub op: ConditionOp,
pub value: ConditionValue<'a>,
}
/// The operation of a complex condition.
#[derive(Copy, Clone, Debug, PartialEq, Eq)]
pub enum ConditionOp {
/// Equal to. (e.g. `MB == 0`)
Eq,
/// Not equal to. (e.g. `simm != -0x8000`)
Ne,
/// Less than. (e.g. `simm < 0`)
Lt,
/// Greater than. (e.g. `SH > 16`)
Gt,
/// Less than or equal to. (e.g. `SH <= 16`)
Lte,
/// Greater than or equal to. (e.g. `SH >= 32 - MB`)
Gte,
}
/// The value of a condition.
#[derive(Clone, Debug)]
pub enum ConditionValue<'a> {
/// A constant unsigned value. (e.g. `MB == 0`)
ConstantUnsigned(u32),
/// A constant signed value. (e.g. `simm != -0x8000`)
ConstantSigned(i32),
/// A field value. (e.g. `rB == rS`)
Field(&'a Field),
/// A complex condition. (e.g. `SH >= 32 - MB`)
Complex(&'a str),
}
/// Parse a condition string into a list of conditions. (e.g. `SH >= 32 - MB && MB == 0`)
/// Maybe turn this into a real lexer/parser if it gets more complex.
pub fn parse_conditions<'a>(condition: &'a str, isa: &'a Isa) -> Result<Vec<Condition<'a>>> {
let mut conditions = Vec::new();
for tok in condition.split(" && ") {
let (mut field, value, op) = if let Some((field, value)) = tok.split_once(" == ") {
(field, value, ConditionOp::Eq)
} else if let Some((field, value)) = tok.split_once(" != ") {
(field, value, ConditionOp::Ne)
} else if let Some((field, value)) = tok.split_once(" < ") {
(field, value, ConditionOp::Lt)
} else if let Some((field, value)) = tok.split_once(" > ") {
(field, value, ConditionOp::Gt)
} else if let Some((field, value)) = tok.split_once(" <= ") {
(field, value, ConditionOp::Lte)
} else if let Some((field, value)) = tok.split_once(" >= ") {
(field, value, ConditionOp::Gte)
} else {
log::error!("Invalid condition: {}", tok);
continue;
};
let mut field_mask = u32::MAX;
if let Some((n, mask)) = field.split_once(" & ") {
field = n;
field_mask = parse_unsigned(mask)?;
};
let field = isa
.find_field(field)
.with_context(|| format!("Condition references unknown field {}", field))?;
let value = if let Ok(value) = parse_unsigned(value) {
ConditionValue::ConstantUnsigned(value)
} else if let Ok(value) = parse_signed(value) {
ConditionValue::ConstantSigned(value)
} else if let Some(field) = isa.find_field(value) {
ConditionValue::Field(field)
} else {
ConditionValue::Complex(value)
};
conditions.push(Condition { field, field_mask, op, value });
}
Ok(conditions)
}
impl Condition<'_> {
pub fn to_token_stream(&self, isa: &Isa, self_ident: Ident) -> Result<TokenStream> {
// Accessor
let field = self.field;
let mut accessor = quote!(#self_ident.#field());
if self.field_mask != u32::MAX {
let mask = HexLiteral(self.field_mask);
accessor = quote! { (#accessor & #mask) };
}
// Operator
let op = match self.op {
ConditionOp::Eq => quote! { == },
ConditionOp::Ne => quote! { != },
ConditionOp::Lt => quote! { < },
ConditionOp::Gt => quote! { > },
ConditionOp::Lte => quote! { <= },
ConditionOp::Gte => quote! { >= },
};
// Value
let value = match self.value {
ConditionValue::ConstantUnsigned(v) => {
let v = HexLiteral(v);
quote! { #v }
}
ConditionValue::ConstantSigned(v) => {
let v = SignedHexLiteral(v);
quote! { #v }
}
ConditionValue::Field(f) => {
quote! { #self_ident.#f() }
}
ConditionValue::Complex(c) => {
replace_fields(c, isa, |f| Ok(quote! { #self_ident.#f() }))?
}
};
Ok(quote! { #accessor #op #value })
}
}
pub fn replace_fields(
s: &str,
isa: &Isa,
mut accessor: impl FnMut(&Field) -> Result<TokenStream>,
) -> Result<TokenStream> {
fn replace_inner(
s: TokenStream,
isa: &Isa,
accessor: &mut impl FnMut(&Field) -> Result<TokenStream>,
) -> Result<TokenStream> {
s.into_iter()
.map(|t| -> Result<TokenStream> {
match &t {
TokenTree::Ident(ident) => {
if let Some(field) = isa.find_field(&ident.to_string()) {
return accessor(field);
}
}
TokenTree::Group(g) => {
return Ok(TokenStream::from(TokenTree::Group(Group::new(
g.delimiter(),
replace_inner(g.stream(), isa, accessor)?,
))));
}
_ => {}
}
Ok(TokenStream::from(t))
})
.collect::<Result<TokenStream>>()
}
let stream = TokenStream::from_str(s).map_err(|e| anyhow!("{}", e))?;
replace_inner(stream, isa, &mut accessor)
}

416
genisa/src/disasm.rs Normal file
View File

@ -0,0 +1,416 @@
use crate::condition::{parse_conditions, replace_fields};
use crate::ident;
use crate::isa::{modifiers_iter, modifiers_valid, HexLiteral, Isa, Opcode};
use anyhow::{bail, ensure, Result};
use proc_macro2::{Literal, TokenStream};
use quote::{format_ident, quote};
use std::collections::HashMap;
pub fn gen_disasm(isa: &Isa, max_args: usize) -> Result<TokenStream> {
// The entry table allows us to quickly find the range of possible opcodes
// for a given 6-bit prefix. 2*64 bytes should fit in a cache line (or two).
struct OpcodeEntry {
start: u8,
count: u8,
}
let mut sorted_ops = Vec::<Opcode>::new();
let mut entries = Vec::<OpcodeEntry>::new();
for i in 0..64 {
let mut entry = OpcodeEntry { start: 0, count: 0 };
for opcode in &isa.opcodes {
if (opcode.pattern >> 26) as u8 == i {
if entry.count == 0 {
entry.start = sorted_ops.len() as u8;
}
// Sanity check for duplicate opcodes
if sorted_ops.iter().any(|op| op.name == opcode.name) {
bail!("Duplicate opcode: {}", opcode.name);
}
sorted_ops.push(opcode.clone());
entry.count += 1;
}
}
if entry.count > 1 {
log::info!("{:#X}: {} opcodes", i, entry.count);
} else if let Some(op) = (entry.count == 1).then(|| &sorted_ops[entry.start as usize]) {
log::info!("{:#X}: {}", i, op.name);
} else {
log::info!("{:#X}: <invalid>", i);
}
entries.push(entry);
}
ensure!(sorted_ops.len() == isa.opcodes.len());
// Generate the opcode entries table
let mut opcode_entries = TokenStream::new();
for entry in &entries {
let start = Literal::u8_unsuffixed(entry.start);
let end = Literal::u8_unsuffixed(entry.start + entry.count);
opcode_entries.extend(quote! { (#start, #end), });
}
// Generate the opcode tables
let mut opcode_patterns = TokenStream::new();
let mut opcode_enum = TokenStream::new();
let mut opcode_names = TokenStream::new();
for (idx, opcode) in sorted_ops.iter().enumerate() {
let bitmask = HexLiteral(opcode.mask(isa));
let pattern = HexLiteral(opcode.pattern);
let enum_idx = Literal::u8_unsuffixed(idx as u8);
let name = &opcode.name;
opcode_patterns.extend(quote! { (#bitmask, #pattern), });
opcode_names.extend(quote! { #name, });
let doc = opcode.doc();
let variant = opcode.variant();
opcode_enum.extend(quote! {
#[doc = #doc]
#variant = #enum_idx,
});
}
// Generate field and modifier accessors
let mut ins_fields = TokenStream::new();
for field in &isa.fields {
let Some(bits) = field.bits else {
continue;
};
// TODO get rid of .nz hack
if field.name.ends_with(".nz") {
continue;
}
let mut sign_bit = bits.len() - 1;
let mut shift_right = bits.shift();
let mut shift_left = field.shift_left;
if shift_right == shift_left {
// Optimization: these cancel each other out
// Adjust subsequent operations to operate on the full value
sign_bit += shift_left;
shift_right = 0;
shift_left = 0;
}
// Shift right and mask
let mut inner = quote! { self.code };
if shift_right > 0 {
let shift = Literal::u8_unsuffixed(shift_right);
inner = quote! { (#inner >> #shift) };
}
let mask = HexLiteral(bits.mask() >> shift_right);
inner = quote! { #inner & #mask };
// Determine the smallest integer type that can hold the value
let num_bits = bits.len() + field.shift_left;
let (out_type, cast) = match (num_bits, field.signed) {
(1..=8, false) => (ident!(u8), true),
(9..=16, false) => (ident!(u16), true),
(17..=32, false) => (ident!(u32), false),
(1..=8, true) => (ident!(i8), true),
(9..=16, true) => (ident!(i16), true),
(17..=32, true) => (ident!(i32), true),
(v, _) => bail!("Unsupported field size {v}"),
};
// Handle sign extension
if field.signed {
let sign_value = HexLiteral(1 << sign_bit);
inner = quote! { ((#inner) ^ #sign_value).wrapping_sub(#sign_value) as #out_type };
} else if cast {
inner = quote! { (#inner) as #out_type };
}
// Handle left shift
if shift_left > 0 {
let shift_left = Literal::u8_unsuffixed(shift_left);
inner = quote! { (#inner) << #shift_left };
}
// Swap 5-bit halves (SPR, TBR)
if field.split {
inner = quote! {
let value = #inner;
((value & 0b11111_00000) >> 5) | ((value & 0b00000_11111) << 5)
};
}
// Write the accessor
let doc = field.doc();
ins_fields.extend(quote! {
#[doc = #doc]
#[inline(always)]
pub const fn #field(&self) -> #out_type { #inner }
});
}
for modifier in &isa.modifiers {
let mask = HexLiteral(modifier.mask());
let mut inner = quote! { (self.code & #mask) == #mask };
if let Some(condition) = &modifier.condition {
for condition in parse_conditions(condition, isa)? {
let stream = condition.to_token_stream(isa, ident!(self))?;
inner.extend(quote! { && #stream });
}
};
// Write the accessor
let doc = modifier.doc();
ins_fields.extend(quote! {
#[doc = #doc]
#[inline(always)]
pub const fn #modifier(&self) -> bool { #inner }
});
}
// Generate simplified mnemonics
let mut mnemonic_functions = TokenStream::new();
let mut base_functions_ref = TokenStream::new();
let mut simplified_functions_ref = TokenStream::new();
for opcode in &sorted_ops {
let mnemonics =
isa.mnemonics.iter().filter(|m| m.opcode == opcode.name).collect::<Vec<_>>();
let mut mnemonic_conditions = TokenStream::new();
// Generate conditions for each simplified mnemonic
for mnemonic in &mnemonics {
let conditions = parse_conditions(&mnemonic.condition, isa)?
.iter()
.map(|c| c.to_token_stream(isa, ident!(ins)))
.collect::<Result<Vec<TokenStream>>>()?;
let modifiers = mnemonic.modifiers.as_deref().unwrap_or(&opcode.modifiers);
let inner = gen_mnemonic(
&mnemonic.name,
&mnemonic.args,
modifiers,
isa,
max_args,
Some(&mnemonic.replace),
)?;
mnemonic_conditions.extend(quote! {
if #(#conditions)&&* {
return #inner;
}
});
}
// Fallback to the base opcode name if no mnemonic matches
let inner =
gen_mnemonic(&opcode.name, &opcode.args, &opcode.modifiers, isa, max_args, None)?;
let base_name = format_ident!("base_{}", opcode.ident());
if mnemonics.is_empty() {
mnemonic_functions.extend(quote! {
const fn #base_name(ins: &Ins) -> (&'static str, Arguments) {
#inner
}
});
base_functions_ref.extend(quote! { #base_name, });
simplified_functions_ref.extend(quote! { #base_name, });
} else {
let simplified_name = format_ident!("simplified_{}", opcode.ident());
mnemonic_functions.extend(quote! {
#[inline(always)]
const fn #base_name(ins: &Ins) -> (&'static str, Arguments) {
#inner
}
const fn #simplified_name(ins: &Ins) -> (&'static str, Arguments) {
#mnemonic_conditions
#base_name(ins)
}
});
base_functions_ref.extend(quote! { #base_name, });
simplified_functions_ref.extend(quote! { #simplified_name, });
}
}
let mut none_args = TokenStream::new();
for _ in 0..max_args {
none_args.extend(quote! { Argument::None, });
}
mnemonic_functions.extend(quote! {
const fn mnemonic_illegal(_ins: &Ins) -> (&'static str, Arguments) {
("<illegal>", [#none_args])
}
});
// TODO rework defs/uses to account for modifiers and special registers (CTR, LR, etc)
let mut defs_uses_functions = TokenStream::new();
let mut defs_refs = TokenStream::new();
let mut uses_refs = TokenStream::new();
for opcode in &sorted_ops {
let mut defs = TokenStream::new();
let mut uses = TokenStream::new();
let mut defs_count = 0;
for def in &opcode.defs {
if isa.find_field(def).is_some_and(|f| f.arg.is_none()) {
continue;
}
let arg = gen_argument(def, isa, None)?;
defs.extend(quote! { #arg, });
defs_count += 1;
}
for _ in defs_count..max_args {
defs.extend(quote! { Argument::None, });
}
let mut use_count = 0;
for use_ in &opcode.uses {
if let Some(use_) = use_.strip_suffix(".nz") {
let Some(field) = isa.find_field(use_) else { bail!("Unknown field {}", use_) };
let ident = field.ident();
let arg = gen_argument(use_, isa, None)?;
uses.extend(quote! { if ins.#ident() != 0 { #arg } else { Argument::None }, });
use_count += 1;
continue;
} else if isa.find_field(use_).is_some_and(|f| f.arg.is_none()) {
continue;
}
let arg = gen_argument(use_, isa, None)?;
uses.extend(quote! { #arg, });
use_count += 1;
}
for _ in use_count..max_args {
uses.extend(quote! { Argument::None, });
}
let defs_name = format_ident!("defs_{}", opcode.ident());
let uses_name = format_ident!("uses_{}", opcode.ident());
defs_uses_functions.extend(quote! {
const fn #defs_name(ins: &Ins) -> Arguments { [#defs] }
const fn #uses_name(ins: &Ins) -> Arguments { [#uses] }
});
defs_refs.extend(quote! { #defs_name, });
uses_refs.extend(quote! { #uses_name, });
}
defs_uses_functions.extend(quote! {
const fn defs_uses_illegal(_ins: &Ins) -> Arguments { [#none_args] }
});
// Filling the tables to 256 entries to avoid bounds checks
for _ in sorted_ops.len()..256 {
opcode_patterns.extend(quote! { (0, 0), });
opcode_names.extend(quote! { "<illegal>", });
base_functions_ref.extend(quote! { mnemonic_illegal, });
simplified_functions_ref.extend(quote! { mnemonic_illegal, });
defs_refs.extend(quote! { defs_uses_illegal, });
uses_refs.extend(quote! { defs_uses_illegal, });
}
let max_args = Literal::usize_unsuffixed(max_args);
Ok(quote! {
#![allow(unused)]
#![cfg_attr(rustfmt, rustfmt_skip)]
use crate::disasm::*;
#[doc = " The entry table allows us to quickly find the range of possible opcodes for a"]
#[doc = " given 6-bit prefix. 2*64 bytes should fit in a cache line (or two)."]
const OPCODE_ENTRIES: [(u8, u8); 64] = [#opcode_entries];
#[doc = " The bitmask and pattern for each opcode."]
const OPCODE_PATTERNS: [(u32, u32); 256] = [#opcode_patterns];
#[doc = " The name of each opcode."]
const OPCODE_NAMES: [&str; 256] = [#opcode_names];
#[derive(Copy, Clone, Debug, Default, PartialEq, Eq)]
#[repr(u8)]
#[non_exhaustive]
pub enum Opcode {
#[doc = " An illegal or unknown opcode"]
#[default]
Illegal = u8::MAX,
#opcode_enum
}
impl Opcode {
#[inline]
pub const fn _mnemonic(self) -> &'static str {
OPCODE_NAMES[self as usize]
}
#[inline]
pub const fn _detect(code: u32) -> Self {
let entry = OPCODE_ENTRIES[(code >> 26) as usize];
let mut i = entry.0;
while i < entry.1 {
let pattern = OPCODE_PATTERNS[i as usize];
if (code & pattern.0) == pattern.1 {
#[comment = " Safety: The enum is repr(u8) and marked non_exhaustive"]
return unsafe { core::mem::transmute(i) };
}
i += 1;
}
Self::Illegal
}
}
impl Ins {
#ins_fields
}
pub type Arguments = [Argument; #max_args];
pub type MnemonicFunction = fn(&Ins) -> (&'static str, Arguments);
#mnemonic_functions
pub const BASE_MNEMONICS: [MnemonicFunction; 256] = [#base_functions_ref];
pub const SIMPLIFIED_MNEMONICS: [MnemonicFunction; 256] = [#simplified_functions_ref];
#defs_uses_functions
pub type DefsUsesFunction = fn(&Ins) -> Arguments;
pub const DEFS_FUNCTIONS: [DefsUsesFunction; 256] = [#defs_refs];
pub const USES_FUNCTIONS: [DefsUsesFunction; 256] = [#uses_refs];
})
}
fn modifier_names(name: &str, modifiers: &[String], isa: &Isa) -> Vec<String> {
// For every combination of modifiers, generate a name
let mut names = Vec::with_capacity(1 << modifiers.len());
for v in modifiers_iter(modifiers, isa) {
if modifiers_valid(&v) {
let mut name = name.to_string();
for modifier in &v {
name.push(modifier.suffix);
}
names.push(name);
} else {
names.push("<illegal>".to_string());
}
}
names
}
fn gen_argument(field: &str, isa: &Isa, replace: Option<&String>) -> Result<TokenStream> {
let Some(field) = isa.find_field(field) else { bail!("Unknown field {}", field) };
let Some(arg) = &field.arg else { bail!("Field {} has no argument", field.name) };
let value = if let Some(replace) = replace {
let stream = replace_fields(replace, isa, |f| Ok(quote! { ins.#f() }))?;
quote! { (#stream) }
} else {
quote! { ins.#field() }
};
let arg = format_ident!("{}", arg);
Ok(quote! { Argument::#arg(#arg(#value as _)) })
}
fn gen_mnemonic(
name: &str,
args: &[String],
modifiers: &[String],
isa: &Isa,
max_args: usize,
replace: Option<&HashMap<String, String>>,
) -> Result<TokenStream> {
let mut arguments = TokenStream::new();
for field in args {
let arg = gen_argument(field, isa, replace.and_then(|m| m.get(field)))?;
arguments.extend(quote! { #arg, });
}
for _ in args.len()..max_args {
arguments.extend(quote! { Argument::None, });
}
if modifiers.is_empty() {
Ok(quote! { (#name, [#arguments]) })
} else {
let names = modifier_names(name, modifiers, isa);
let mut bitset = quote! { 0 };
for (i, modifier) in modifiers.iter().enumerate() {
let modifier = isa.find_modifier(modifier).unwrap();
if i == 0 {
bitset = quote! { ins.#modifier() as usize };
} else {
let i = Literal::u8_unsuffixed(i as u8);
bitset.extend(quote! { | (ins.#modifier() as usize) << #i });
}
}
Ok(quote! { ([#(#names),*][#bitset], [#arguments]) })
}
}

416
genisa/src/isa.rs Normal file
View File

@ -0,0 +1,416 @@
use std::collections::HashMap;
use std::{fs::File, path::Path, str::FromStr};
use anyhow::{Context, Result};
use num_traits::PrimInt;
use proc_macro2::{Ident, Span, TokenStream};
use quote::{format_ident, ToTokens};
use serde::{Deserialize, Deserializer, Serialize};
pub fn load_isa(path: &Path) -> Result<Isa> {
let yaml_file =
File::open(path).with_context(|| format!("Failed to open file {}", path.display()))?;
let isa: Isa = serde_yaml::from_reader(yaml_file)
.with_context(|| format!("While parsing file {}", path.display()))?;
Ok(isa)
}
#[derive(Deserialize, Serialize, Clone, Debug, Default)]
#[serde(default)]
pub struct Isa {
pub fields: Vec<Field>,
pub modifiers: Vec<Modifier>,
pub opcodes: Vec<Opcode>,
pub mnemonics: Vec<Mnemonic>,
}
impl Isa {
pub fn find_field(&self, name: &str) -> Option<&Field> {
self.fields.iter().find(|f| f.name == name)
}
pub fn find_modifier(&self, name: &str) -> Option<&Modifier> {
self.modifiers.iter().find(|m| m.name == name)
}
pub fn find_opcode(&self, name: &str) -> Option<&Opcode> {
self.opcodes.iter().find(|o| o.name == name)
}
}
#[derive(Deserialize, Serialize, Clone, Debug, Default)]
#[serde(default)]
pub struct Field {
pub name: String,
pub desc: String,
#[serde(skip_serializing_if = "Option::is_none")]
pub bits: Option<BitRange>,
pub signed: bool,
pub split: bool,
#[serde(skip_serializing_if = "Option::is_none")]
pub arg: Option<String>,
pub shift_left: u8,
}
impl Field {
/// Calculate the field mask from its bit range
pub fn mask(&self) -> u32 {
self.bits.map(|b| b.mask()).unwrap_or(0)
}
/// Shift and mask a value according to the field
pub fn shift_value(&self, mut value: u32) -> u32 {
if self.split {
// Swap 5-bit halves (SPR, TBR)
value = ((value & 0b11111_00000u32) >> 5) | ((value & 0b00000_11111u32) << 5);
}
self.bits.map(|b| b.shift_value(value >> self.shift_left)).unwrap_or(0)
}
pub fn ident(&self) -> Ident {
format_ident!("field_{}", to_ident(&self.name))
}
pub fn doc(&self) -> String {
if self.desc.is_empty() {
format!(" {}", self.name)
} else {
format!(" {}: {}", self.name, self.desc)
}
}
}
impl ToTokens for Field {
fn to_tokens(&self, tokens: &mut TokenStream) {
self.ident().to_tokens(tokens)
}
}
#[derive(Deserialize, Serialize, Clone, Debug, Default)]
#[serde(default)]
pub struct Opcode {
pub name: String,
pub desc: String,
pub bitmask: u32,
pub pattern: u32,
#[serde(skip_serializing_if = "Vec::is_empty")]
pub modifiers: Vec<String>,
#[serde(skip_serializing_if = "Vec::is_empty")]
pub args: Vec<String>,
#[serde(skip_serializing_if = "Vec::is_empty")]
pub defs: Vec<String>,
#[serde(skip_serializing_if = "Vec::is_empty")]
pub uses: Vec<String>,
}
impl Opcode {
/// Calculate the opcode mask from its fields and modifiers
pub fn mask(&self, isa: &Isa) -> u32 {
let mut calc_bitmask = 0u32;
for arg_n in &self.args {
let Some(field) = isa.find_field(arg_n) else {
continue;
};
calc_bitmask |= field.mask();
}
for modifier_n in &self.modifiers {
let Some(modifier) = isa.find_modifier(modifier_n) else {
continue;
};
calc_bitmask |= modifier.mask();
}
!calc_bitmask
}
pub fn ident(&self) -> Ident {
Ident::new(&to_ident(&self.name), Span::call_site())
}
pub fn variant(&self) -> Ident {
Ident::new(&to_variant(&self.name), Span::call_site())
}
pub fn doc(&self) -> String {
if self.desc.is_empty() {
format!(" {}", self.name)
} else {
format!(" {}: {}", self.name, self.desc)
}
}
}
impl ToTokens for Opcode {
fn to_tokens(&self, tokens: &mut TokenStream) {
self.ident().to_tokens(tokens)
}
}
#[derive(Deserialize, Serialize, Clone, Debug, Default)]
#[serde(default)]
pub struct Mnemonic {
pub name: String,
pub desc: String,
pub opcode: String,
#[serde(skip_serializing_if = "Option::is_none")]
// Overrides modifier list from opcode
pub modifiers: Option<Vec<String>>,
#[serde(skip_serializing_if = "Vec::is_empty")]
pub args: Vec<String>,
pub condition: String,
#[serde(skip_serializing_if = "HashMap::is_empty")]
pub replace: HashMap<String, String>,
#[serde(skip_serializing_if = "HashMap::is_empty")]
pub replace_assemble: HashMap<String, String>,
}
#[derive(Deserialize, Serialize, Clone, Debug, Default)]
#[serde(default)]
pub struct Modifier {
pub name: String,
pub desc: String,
pub suffix: char,
pub bit: u8,
#[serde(skip_serializing_if = "Vec::is_empty")]
pub defs: Vec<String>,
#[serde(skip_serializing_if = "Option::is_none")]
pub condition: Option<String>,
}
impl Modifier {
/// Calculate the modifier mask from its bit
pub fn mask(&self) -> u32 {
1 << (31 - self.bit)
}
pub fn ident(&self) -> Ident {
format_ident!("field_{}", to_ident(&self.name))
}
pub fn doc(&self) -> String {
if self.desc.is_empty() {
format!(" {}", self.name)
} else {
format!(" {}: {}", self.name, self.desc)
}
}
}
impl ToTokens for Modifier {
fn to_tokens(&self, tokens: &mut TokenStream) {
self.ident().to_tokens(tokens)
}
}
/// A collection of modifiers
type Modifiers<'a> = Vec<&'a Modifier>;
/// Whether a collection of modifiers is valid (all bits are unique)
pub fn modifiers_valid(modifiers: &Modifiers) -> bool {
let bits = modifiers.iter().map(|m| m.bit).collect::<Vec<_>>();
bits.iter().all(|&b| bits.iter().filter(|&&x| x == b).count() == 1)
}
/// Iterate over all possible combinations of modifiers
pub fn modifiers_iter<'a>(
modifiers: &'a [String],
isa: &'a Isa,
) -> impl Iterator<Item = Modifiers<'a>> {
(0..=(1 << modifiers.len()) - 1).map(move |b| {
modifiers
.iter()
.enumerate()
.filter(|(i, _)| b & (1 << i) != 0)
.map(|(_, m)| isa.find_modifier(m).unwrap())
.collect::<Vec<_>>()
})
}
#[derive(Copy, Clone, Debug, Default)]
pub struct BitRange(pub (u8, u8));
impl BitRange {
#[inline]
pub fn new(start: u8, end: u8) -> Self {
Self((start, end))
}
#[inline]
pub fn start(&self) -> u8 {
self.0 .0
}
#[inline]
pub fn end(&self) -> u8 {
self.0 .1
}
/// Calculate the mask from the range
#[inline]
pub fn mask(&self) -> u32 {
self.max_value() << self.shift()
}
/// Number of bits to shift
#[inline]
pub fn shift(&self) -> u8 {
32 - self.end()
}
/// Number of bits in the range
#[inline]
pub fn len(&self) -> u8 {
self.end() - self.start()
}
/// Shift and mask a value according to the range
#[inline]
pub fn shift_value(&self, value: u32) -> u32 {
(value & self.max_value()) << self.shift()
}
/// Calculate the maximum value that can be represented by the range
#[inline]
pub fn max_value(&self) -> u32 {
(1 << self.len()) - 1
}
}
impl<'de> Deserialize<'de> for BitRange {
fn deserialize<D>(deserializer: D) -> Result<Self, D::Error>
where
D: Deserializer<'de>,
{
let range_str: String = Deserialize::deserialize(deserializer)?;
if let Some((start_str, end_str)) = range_str.split_once("..") {
let start = start_str.parse::<u8>().map_err(serde::de::Error::custom)?;
let end = end_str.parse::<u8>().map_err(serde::de::Error::custom)?;
Ok(Self::new(start, end))
} else {
let bit_idx = range_str.parse::<u8>().map_err(serde::de::Error::custom)?;
Ok(Self::new(bit_idx, bit_idx))
}
}
}
impl Serialize for BitRange {
fn serialize<S>(&self, serializer: S) -> Result<S::Ok, S::Error>
where
S: serde::Serializer,
{
if self.start() == self.end() {
self.start().serialize(serializer)
} else {
format!("{}..{}", self.start(), self.end()).serialize(serializer)
}
}
}
pub fn to_ident(key: &str) -> String {
key.to_ascii_lowercase().replace('.', "_").replace('+', "p").replace('-', "m")
}
pub fn to_variant(key: &str) -> String {
let mut s = String::new();
let mut chars = key.chars();
loop {
// Make first char uppercase.
let c = match chars.next() {
None => return s,
Some(c) => c,
};
s.push(match c {
'a'..='z' => c.to_ascii_uppercase(),
'A'..='Z' => c,
_ => panic!("invalid identifier: {}", key),
});
loop {
let c = match chars.next() {
None => return s,
Some(c) => c,
};
match c.to_ascii_lowercase() {
'0'..='9' | 'a'..='z' => s.push(c),
'_' => break,
'.' => {
s.push('_');
break;
}
_ => panic!("invalid character in variant: {}", key),
}
}
}
}
/// Parse an unsigned number in decimal, binary, or hexadecimal format.
pub fn parse_unsigned(mask: &str) -> Result<u32, std::num::ParseIntError> {
if let Some(mask) = mask.strip_prefix("0b") {
u32::from_str_radix(mask, 2)
} else if let Some(mask) = mask.strip_prefix("0x") {
u32::from_str_radix(mask, 16)
} else {
mask.parse::<u32>()
}
}
/// Parse a signed number in decimal, binary, or hexadecimal format.
pub fn parse_signed(mask: &str) -> Result<i32, std::num::ParseIntError> {
if let Some(mask) = mask.strip_prefix('-') {
if let Some(mask) = mask.strip_prefix("0b") {
i32::from_str_radix(mask, 2).map(|n| -n)
} else if let Some(mask) = mask.strip_prefix("0x") {
i32::from_str_radix(mask, 16).map(|n| -n)
} else {
mask.parse::<i32>().map(|n| -n)
}
} else {
parse_unsigned(mask).map(|n| n as i32)
}
}
pub struct HexLiteral<T>(pub T);
impl<T> std::fmt::LowerHex for HexLiteral<T>
where
T: std::fmt::LowerHex,
{
fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
std::fmt::LowerHex::fmt(&self.0, f)
}
}
impl<T> ToTokens for HexLiteral<T>
where
T: std::fmt::LowerHex,
{
fn to_tokens(&self, tokens: &mut TokenStream) {
let s = format!("{:#x}", self);
tokens.extend(TokenStream::from_str(&s).unwrap());
}
}
pub struct SignedHexLiteral<T>(pub T);
impl<T> std::fmt::LowerHex for SignedHexLiteral<T>
where
T: PrimInt + std::fmt::LowerHex,
{
fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
if self.0 < T::zero() {
write!(f, "-")?;
let int = self.0.to_i64().unwrap_or_default();
std::fmt::LowerHex::fmt(&-int, f)
} else {
std::fmt::LowerHex::fmt(&self.0, f)
}
}
}
impl<T> ToTokens for SignedHexLiteral<T>
where
T: PrimInt + std::fmt::LowerHex,
{
fn to_tokens(&self, tokens: &mut TokenStream) {
let s = format!("{:#x}", self);
tokens.extend(TokenStream::from_str(&s).unwrap());
}
}

909
genisa/src/main.rs
View File

@ -1,771 +1,162 @@
use std::collections::HashMap;
use std::fs::File;
use std::io::Write;
use std::ops::Range;
use std::process::{Command, Stdio};
use std::str::FromStr;
mod asm;
mod condition;
mod disasm;
mod isa;
use itertools::Itertools;
use proc_macro2::{Group, Ident, Literal, Span, TokenStream, TokenTree};
use quote::quote;
use serde::{Deserialize, Deserializer};
use syn::{LitChar, LitInt, LitStr};
use crate::asm::gen_asm;
use crate::disasm::gen_disasm;
use anyhow::{ensure, Context, Result};
use condition::{parse_conditions, ConditionOp, ConditionValue};
use isa::load_isa;
use std::path::Path;
macro_rules! token_stream {
($stream:ident) => {
TokenStream::from_iter($stream.into_iter())
/// Identifier literal.
#[macro_export]
macro_rules! ident {
($name:ident) => {
proc_macro2::Ident::new(stringify!($name), proc_macro2::Span::call_site())
};
}
fn main() {
if let Err(err) = _main() {
eprintln!("{}", err);
std::process::exit(1);
}
}
fn main() -> Result<()> {
simple_logger::SimpleLogger::new().env().init().unwrap();
type Error = Box<dyn std::error::Error>;
type Result<T> = std::result::Result<T, Error>;
let isa = load_isa(Path::new("isa.yaml"))?;
// Make sure we can fit the opcodes into a u8
ensure!(isa.opcodes.len() <= 255);
fn _main() -> Result<()> {
let isa = load_isa()?;
let mut unformatted_code = Vec::<u8>::new();
writeln!(
&mut unformatted_code,
"{}",
quote! {
use crate::prelude::*;
// Sanity check the opcodes and mnemonics
// Calculate the bitmask for each opcode and compare it to the stored bitmask
let mut max_args = 0;
for opcode in &isa.opcodes {
let mut calc_bitmask = opcode.mask(&isa);
if opcode.bitmask != calc_bitmask {
log::warn!(
"Opcode {}: Calculated bitmask mismatch: {:#010X} != {:#010X} ({:032b} != {:032b})",
opcode.name,
opcode.bitmask,
calc_bitmask,
opcode.bitmask,
calc_bitmask
);
}
if opcode.pattern & !opcode.bitmask != 0 {
log::warn!(
"Opcode {}: Pattern has bits set outside of bitmask: {:#010X} & !{:#010X} != 0 ({:032b} & !{:032b} != 0)",
opcode.name,
opcode.pattern,
opcode.bitmask,
opcode.pattern,
opcode.bitmask
);
}
)?;
writeln!(&mut unformatted_code, "{}", isa.gen_opcode_enum()?)?;
writeln!(&mut unformatted_code, "{}", isa.gen_field_enum()?)?;
writeln!(&mut unformatted_code, "{}", isa.gen_field_impl()?)?;
writeln!(&mut unformatted_code, "{}", isa.gen_ins_impl()?)?;
let formatted_code = rustfmt(unformatted_code);
File::create("./disasm/src/generated.rs")?.write_all(&formatted_code)?;
// Make sure we can account for every bit with fields and modifiers
for arg in &opcode.args {
let field = isa
.find_field(arg)
.with_context(|| format!("Opcode {}: unknown field {}", opcode.name, arg))?;
calc_bitmask |= field.mask();
}
for modifier_name in &opcode.modifiers {
let modifier = isa.find_modifier(modifier_name).with_context(|| {
format!("Opcode {}: unknown modifier {}", opcode.name, modifier_name)
})?;
if let Some(condition) = &modifier.condition {
for condition in parse_conditions(condition, &isa)? {
// Only check constant conditions
if condition.op == ConditionOp::Eq
&& matches!(
condition.value,
ConditionValue::ConstantUnsigned(_) | ConditionValue::ConstantSigned(_)
)
{
calc_bitmask |= condition.field.shift_value(condition.field_mask);
}
}
} else {
calc_bitmask |= modifier.mask();
}
}
if calc_bitmask != u32::MAX {
log::warn!(
"Opcode {}: Calculated bitmask is non-exhaustive: {:#010X}, {:032b}",
opcode.name,
calc_bitmask,
calc_bitmask
);
}
max_args = max_args.max(opcode.args.len());
}
// Check each mnemonic, make sure we can account for every bit
// with fields, modifiers, and conditions
for mnemonic in &isa.mnemonics {
let opcode = isa.find_opcode(&mnemonic.opcode).with_context(|| {
format!("Mnemonic {}: unknown opcode {}", mnemonic.name, mnemonic.opcode)
})?;
let mut calc_bitmask = opcode.mask(&isa);
for arg in &mnemonic.args {
let field = isa
.find_field(arg)
.with_context(|| format!("Mnemonic {}: unknown field {}", mnemonic.name, arg))?;
calc_bitmask |= field.mask();
}
for modifier_name in mnemonic.modifiers.as_deref().unwrap_or(&opcode.modifiers) {
let modifier = isa.find_modifier(modifier_name).with_context(|| {
format!("Mnemonic {}: unknown modifier {}", mnemonic.name, modifier_name)
})?;
if let Some(condition) = &modifier.condition {
for condition in parse_conditions(condition, &isa)? {
// Only check constant conditions
if condition.op == ConditionOp::Eq
&& matches!(
condition.value,
ConditionValue::ConstantUnsigned(_) | ConditionValue::ConstantSigned(_)
)
{
calc_bitmask |= condition.field.shift_value(condition.field_mask);
}
}
} else {
calc_bitmask |= modifier.mask();
}
}
for condition in parse_conditions(&mnemonic.condition, &isa)? {
if condition.op != ConditionOp::Eq {
continue;
}
let field_bitmask = condition.field.shift_value(condition.field_mask);
if calc_bitmask & field_bitmask != 0 {
log::warn!(
"Mnmemonic {}: {:#010X} & {:#010X} != 0",
mnemonic.name,
calc_bitmask,
field_bitmask,
);
}
calc_bitmask |= field_bitmask;
}
if calc_bitmask != u32::MAX {
log::warn!(
"Mnemonic {}: Calculated bitmask is non-exhaustive: {:#010X}, {:032b}",
mnemonic.name,
calc_bitmask,
calc_bitmask
);
}
}
let tokens = gen_disasm(&isa, max_args)?;
let file = syn::parse2(tokens)?;
let formatted = prettyplease::unparse(&file);
std::fs::write("disasm/src/generated.rs", formatted)?;
let tokens = gen_asm(&isa, max_args)?;
let file = syn::parse2(tokens)?;
let formatted = prettyplease::unparse(&file);
std::fs::write("asm/src/generated.rs", formatted)?;
Ok(())
}
fn rustfmt(code: Vec<u8>) -> Vec<u8> {
let mut rustfmt = Command::new("rustfmt")
.stdin(Stdio::piped())
.stdout(Stdio::piped())
.spawn()
.expect("failed to spawn rustfmt");
let mut stdin = rustfmt.stdin.take().unwrap();
std::thread::spawn(move || {
let _ = stdin.write_all(&code);
});
let rustfmt_res = rustfmt.wait_with_output().expect("failed to run rustfmt");
if !rustfmt_res.status.success() {
panic!("rustfmt failed");
}
rustfmt_res.stdout
}
#[derive(Default)]
pub(crate) struct BitRange(Range<u8>);
impl<'de> Deserialize<'de> for BitRange {
fn deserialize<D>(deserializer: D) -> std::result::Result<Self, D::Error>
where
D: Deserializer<'de>,
{
let range_str: String = Deserialize::deserialize(deserializer)?;
if let Some((start_str, stop_str)) = range_str.split_once("..") {
let start = start_str.parse::<u8>().map_err(serde::de::Error::custom)?;
let stop = stop_str.parse::<u8>().map_err(serde::de::Error::custom)?;
Ok(Self(start..stop))
} else {
let bit_idx = range_str.parse::<u8>().map_err(serde::de::Error::custom)?;
Ok(Self(bit_idx..bit_idx))
}
}
}
#[derive(Deserialize, Default)]
#[serde(default)]
pub(crate) struct Field {
name: String,
desc: String,
bits: BitRange,
signed: bool,
split: bool,
arg: Option<String>,
shift_left: u8,
}
impl Field {
fn variant_identifier(&self) -> Option<TokenTree> {
self.identifier("")
}
fn identifier(&self, prefix: &str) -> Option<TokenTree> {
if self.name.strip_suffix(".nz").is_none() {
Some(to_rust_ident(prefix, &self.name))
} else {
None
}
}
fn express_value(&self, code: TokenStream) -> TokenStream {
let mut val = quote!(#code);
let shift = 32 - self.bits.0.end;
if shift > 0 {
val = quote!((#val >> #shift));
}
let mask = (1u32 << self.bits.0.len()) - 1;
if mask != 0xFFFF_FFFF {
let mask = LitInt::new(&format!("0x{:x}", mask), Span::call_site());
val = quote!((#val & #mask));
}
if self.split {
val = quote!((((#val & 0b11111_00000u32) >> 5u32) | ((#val & 0b00000_11111u32) << 5u32)) as u32);
}
// https://graphics.stanford.edu/~seander/bithacks.html#VariableSignExtend
if self.signed {
let mask2 = 1u32 << (self.bits.0.len() - 1);
let mask2 = LitInt::new(&format!("0x{:x}", mask2), Span::call_site());
val = quote!((((#val ^ #mask2).wrapping_sub(#mask2)) as i32))
}
let val_shift = self.shift_left;
if val_shift > 0 {
val = quote!((#val << #val_shift));
}
val
}
fn express_value_self(&self) -> TokenStream {
self.express_value(quote!(self.code))
}
fn enum_variant_definition(&self) -> Option<TokenStream> {
let ident = self.variant_identifier()?;
Some(if let Some(arg) = &self.arg {
let arg = TokenTree::Ident(Ident::new(arg, Span::call_site()));
quote! {
#ident(#arg),
}
} else {
quote! {
#ident,
}
})
}
pub(crate) fn construct_variant(&self, code: TokenStream) -> TokenStream {
let field_variant = self.variant_identifier();
if let Some(arg) = &self.arg {
let field_arg = TokenTree::Ident(Ident::new(arg, Span::call_site()));
let value = self.express_value(code);
quote! {
Field::#field_variant(#field_arg(#value as _))
}
} else {
quote! {
Field::#field_variant
}
}
}
fn construct_variant_self(&self) -> TokenStream {
self.construct_variant(quote!(self.code))
}
fn construct_accessor(&self) -> TokenStream {
let field_variant = match self.identifier("field_") {
Some(v) => v,
None => return TokenStream::new(),
};
if self.arg.is_none() {
return TokenStream::new();
}
let value = self.express_value_self();
let ret_type = if self.signed {
quote!(isize)
} else {
quote!(usize)
};
quote! {
#[inline(always)]
pub fn #field_variant(&self) -> #ret_type {
#value as _
}
}
}
}
#[derive(Deserialize, Default)]
#[serde(default)]
pub(crate) struct Opcode {
name: String,
desc: String,
bitmask: u32,
pattern: u32,
modifiers: Vec<String>,
side_effects: Vec<String>,
args: Vec<String>,
defs: Vec<String>,
uses: Vec<String>,
}
impl Opcode {
fn variant_identifier(&self) -> Result<TokenTree> {
to_rust_variant(&self.name)
}
}
#[derive(Deserialize, Default)]
#[serde(default)]
pub(crate) struct Mnemonic {
name: String,
opcode: String,
// Overrides modifier list from opcode
modifiers: Option<Vec<String>>,
args: Vec<String>,
condition: String,
}
#[derive(Deserialize, Default)]
#[serde(default)]
pub(crate) struct Modifier {
name: String,
suffix: char,
bit: u8,
condition: String,
}
impl Modifier {
fn express_value_self(&self, field_by_name: &HashMap<String, &Field>) -> Result<TokenStream> {
if self.condition.is_empty() {
let modifier_bit = self.bit as usize;
Ok(quote!(self.bit(#modifier_bit)))
} else {
compile_mnemonic_condition(field_by_name, &self.condition)
}
}
fn construct_accessor(&self, field_by_name: &HashMap<String, &Field>) -> Result<TokenStream> {
let field_variant = to_rust_ident("field_", &self.name);
let value = self.express_value_self(field_by_name)?;
Ok(quote! {
#[inline(always)]
pub fn #field_variant(&self) -> bool {
#value
}
})
}
}
#[derive(Deserialize, Default)]
#[serde(default)]
pub(crate) struct Isa {
fields: Vec<Field>,
modifiers: Vec<Modifier>,
opcodes: Vec<Opcode>,
mnemonics: Vec<Mnemonic>,
}
fn load_isa() -> Result<Isa> {
let yaml_file = File::open("isa.yaml")?;
let isa: Isa = serde_yaml::from_reader(yaml_file)?;
Ok(isa)
}
impl Isa {
fn gen_opcode_enum(&self) -> Result<TokenStream> {
// Create enum variants.
let enum_variants = self
.opcodes
.iter()
.map(|opcode| -> Result<TokenStream> {
let ident = opcode.variant_identifier()?;
Ok(quote! {
#ident,
})
})
.try_collect::<TokenStream, Vec<TokenStream>, Error>()?;
let enum_variants = token_stream!(enum_variants);
// Create functions.
let mnemonic_fn = self.gen_mnemonic_fn()?;
let detect_fn = self.gen_opcode_detect()?;
// Create final enum.
let opcode_enum = quote! {
#[derive(Debug, Copy, Clone, Eq, PartialEq)]
pub enum Opcode {
Illegal = -1,
#enum_variants
}
#[allow(clippy::all)]
impl Opcode {
#mnemonic_fn
#detect_fn
}
};
Ok(opcode_enum)
}
fn gen_mnemonic_fn(&self) -> Result<TokenStream> {
// Create match arms.
let match_arms = self
.opcodes
.iter()
.map(|opcode| {
let variant = opcode.variant_identifier()?;
let literal = Literal::string(&opcode.name);
Ok(quote! {
Opcode::#variant => #literal,
})
})
.try_collect::<TokenStream, Vec<TokenStream>, Error>()?;
let match_arms = token_stream!(match_arms);
// Create final function.
let mnemonic_fn = quote! {
pub(crate) fn _mnemonic(self) -> &'static str {
match self {
Opcode::Illegal => "<illegal>",
#match_arms
}
}
};
Ok(mnemonic_fn)
}
fn gen_opcode_detect(&self) -> Result<TokenStream> {
// Generate if chain.
let if_chain = self
.opcodes
.iter()
.map(|opcode| {
let bitmask_str = format!("{:>#8x}", opcode.bitmask);
let bitmask = LitInt::new(&bitmask_str, Span::call_site());
let pattern_str = format!("{:>#8x}", opcode.pattern);
let pattern = LitInt::new(&pattern_str, Span::call_site());
let identifier = opcode.variant_identifier()?;
Ok(quote! {
if code & #bitmask == #pattern {
return Opcode::#identifier;
}
})
})
.try_collect::<TokenStream, Vec<TokenStream>, Error>()?;
let if_chain = token_stream!(if_chain);
// Generate function.
let func = quote! {
pub(crate) fn _detect(code: u32) -> Self {
#if_chain
Opcode::Illegal
}
};
Ok(func)
}
fn gen_field_enum(&self) -> Result<TokenStream> {
// Create enum variants.
let mut enum_variants = Vec::new();
for field in &self.fields {
if let Some(field) = field.enum_variant_definition() {
enum_variants.push(field);
}
}
let enum_variants = token_stream!(enum_variants);
// Create final enum.
let field_enum = quote! {
#[allow(non_camel_case_types)]
#[derive(Debug, Copy, Clone, Eq, PartialEq)]
pub enum Field {
#enum_variants
}
};
Ok(field_enum)
}
fn gen_field_argument(&self) -> Result<TokenStream> {
let mut match_arms = Vec::new();
for field in &self.fields {
if let Some(variant) = field.variant_identifier() {
if let Some(arg_str) = field.arg.as_ref() {
let arg = Ident::new(arg_str, Span::call_site());
match_arms.push(quote! { Field::#variant(x) => Some(Argument::#arg(*x)), });
}
}
}
let match_arms = token_stream!(match_arms);
Ok(quote! {
pub fn argument(&self) -> Option<Argument> {
match self {
#match_arms
_ => None,
}
}
})
}
fn gen_field_name(&self) -> Result<TokenStream> {
let mut match_arms = Vec::new();
for field in &self.fields {
if let Some(variant) = field.variant_identifier() {
let name = LitStr::new(&variant.to_string(), Span::call_site());
let arg = field.arg.as_ref().map(|_| quote!((_)));
match_arms.push(quote! { Field::#variant #arg => #name, });
}
}
let match_arms = token_stream!(match_arms);
Ok(quote! {
pub fn name(&self) -> &'static str {
match self {
#match_arms
}
}
})
}
fn gen_field_impl(&self) -> Result<TokenStream> {
let field_argument = self.gen_field_argument()?;
let field_name = self.gen_field_name()?;
Ok(quote! {
impl Field {
#field_argument
#field_name
}
})
}
fn gen_ins_impl(&self) -> Result<TokenStream> {
// Map fields by name.
let mut field_by_name = HashMap::<String, &Field>::new();
for field in &self.fields {
field_by_name.insert(field.name.clone(), field);
}
let mut modifier_by_name = HashMap::<String, &Modifier>::new();
for modifier in &self.modifiers {
modifier_by_name.insert(modifier.name.clone(), modifier);
}
// Map mnemonics by opcode.
let mut mnemonics_by_opcode = HashMap::<&String, Vec<&Mnemonic>>::new();
for simple in &self.mnemonics {
mnemonics_by_opcode
.entry(&simple.opcode)
.or_insert_with(Vec::new)
.push(simple)
}
// Generate match arms for each opcode.
let mut field_match_arms = Vec::new();
let mut def_match_arms = Vec::new();
let mut use_match_arms = Vec::new();
let mut suffix_match_arms = Vec::new();
let mut simplified_ins_match_arms = Vec::new();
for opcode in &self.opcodes {
// Generate fields of opcode.
let mut fields = Vec::new();
for arg in &opcode.args {
let field: &Field = field_by_name
.get(arg)
.ok_or_else(|| Error::from(format!("undefined field {}", arg)))?;
let variant = field.construct_variant_self();
fields.extend(quote! { #variant, })
}
let fields = token_stream!(fields);
// Emit match arm.
let ident = opcode.variant_identifier()?;
field_match_arms.push(quote! {
Opcode::#ident => vec![#fields],
});
// Generate modifiers.
let suffix = express_suffix(&modifier_by_name, &field_by_name, &opcode.modifiers)?;
suffix_match_arms.push(quote! {
Opcode::#ident => #suffix,
});
// Generate defs.
let mut defs = Vec::new();
for arg in &opcode.defs {
let field: &Field = field_by_name.get(arg).ok_or_else(|| {
syn::Error::new(Span::call_site(), format!("undefined field {}", arg))
})?;
let variant = field.construct_variant_self();
defs.extend(quote! { #variant, })
}
let defs = token_stream!(defs);
let ident = opcode.variant_identifier()?;
def_match_arms.push(quote! {
Opcode::#ident => vec![#defs],
});
// Generate uses.
let mut uses = Vec::new();
let mut special_uses = Vec::new();
for arg in &opcode.uses {
// Detect non-zero modifier.
let mut arg = arg.as_str();
let mut non_zero = false;
if let Some(substr) = arg.strip_suffix(".nz") {
non_zero = true;
arg = substr;
}
// Get underlying field.
let field: &Field = field_by_name.get(arg).ok_or_else(|| {
syn::Error::new(Span::call_site(), format!("undefined field {}", arg))
})?;
let variant = field.construct_variant_self();
if non_zero {
let value = field.express_value_self();
special_uses.extend(quote! {
if (#value) != 0 {
uses.push(#variant);
}
})
} else {
uses.extend(quote! {
#variant,
})
}
}
let uses = token_stream!(uses);
let ident = opcode.variant_identifier()?;
let special_uses = token_stream!(special_uses);
use_match_arms.push(quote! {
Opcode::#ident => {
let mut uses = vec![#uses];
#special_uses
uses
},
});
// Generate instruction simplification.
if let Some(mnemonics) = mnemonics_by_opcode.get(&opcode.name) {
let mut simplified_conditions = Vec::new();
for mnemonic in mnemonics {
if mnemonic.condition.is_empty() {
continue; // TODO else branch
}
simplified_conditions.push(quote!(if));
simplified_conditions.push(compile_mnemonic_condition(
&field_by_name,
&mnemonic.condition,
)?);
// Emit branch.
let mnemonic_lit = LitStr::new(&mnemonic.name, Span::call_site());
// Emit suffix.
let modifiers = mnemonic.modifiers.as_ref().unwrap_or(&opcode.modifiers);
let suffix = express_suffix(&modifier_by_name, &field_by_name, modifiers)?;
// Extract arguments.
let mut args = Vec::new();
for arg in &mnemonic.args {
let (field_name, expression) = arg.split_once('=').unwrap_or((arg, arg));
let field = field_by_name
.get(field_name)
.unwrap_or_else(|| panic!("field not found: {}", arg));
let variant = Ident::new(field.arg.as_ref().unwrap(), Span::call_site());
let value = compile_mnemonic_condition(&field_by_name, expression)?;
args.push(quote!(Argument::#variant(#variant((#value) as _)),));
}
let args = token_stream!(args);
simplified_conditions.push(quote! {
{
return SimplifiedIns {
mnemonic: #mnemonic_lit,
suffix: #suffix,
args: vec![#args],
ins: self,
};
}
});
}
let simplified_conditions = token_stream!(simplified_conditions);
simplified_ins_match_arms.push(quote! {
Opcode::#ident => {
#simplified_conditions
},
});
}
}
let field_match_arms = token_stream!(field_match_arms);
let def_match_arms = token_stream!(def_match_arms);
let use_match_arms = token_stream!(use_match_arms);
let suffix_match_arms = token_stream!(suffix_match_arms);
let simplified_ins_match_arms = token_stream!(simplified_ins_match_arms);
let field_accessors =
TokenStream::from_iter(self.fields.iter().map(|field| field.construct_accessor()));
let modifiers: Vec<TokenStream> = self
.modifiers
.iter()
.map(|modifier| modifier.construct_accessor(&field_by_name))
.try_collect()?;
let modifier_accessors = TokenStream::from_iter(modifiers);
// Generate final fields function.
let ins_impl = quote! {
#[allow(clippy::all, unused_mut)]
impl Ins {
pub(crate) fn _fields(&self) -> Vec<Field> {
match self.op {
Opcode::Illegal => vec![],
#field_match_arms
}
}
pub(crate) fn _defs(&self) -> Vec<Field> {
match self.op {
Opcode::Illegal => vec![],
#def_match_arms
}
}
pub(crate) fn _uses(&self) -> Vec<Field> {
match self.op {
Opcode::Illegal => vec![],
#use_match_arms
}
}
pub(crate) fn _suffix(&self) -> String {
match self.op {
Opcode::Illegal => String::new(),
#suffix_match_arms
}
}
pub(crate) fn _simplified(self) -> SimplifiedIns {
match self.op {
#simplified_ins_match_arms
_ => {}
}
SimplifiedIns::basic_form(self)
}
}
#[allow(clippy::all, non_snake_case)]
impl Ins {
#field_accessors
#modifier_accessors
}
};
Ok(ins_impl)
}
}
/// Converts the given key into an identifier.
fn to_rust_ident(prefix: &str, key: &str) -> TokenTree {
TokenTree::Ident(Ident::new(
&(prefix.to_owned() + &key.replace('.', "_")),
Span::call_site(),
))
}
/// Converts the given key into an enum variant key.
fn to_rust_variant(key: &str) -> Result<TokenTree> {
Ok(TokenTree::Ident(Ident::new(
&to_rust_variant_str(key)?,
Span::call_site(),
)))
}
fn to_rust_variant_str(key: &str) -> Result<String> {
let mut s = String::new();
let mut chars = key.chars();
loop {
// Make first char uppercase.
let c = match chars.next() {
None => return Ok(s),
Some(c) => c,
};
s.push(match c {
'a'..='z' => c.to_ascii_uppercase(),
'A'..='Z' => c,
_ => return Err(format!("invalid identifier: {}", key).into()),
});
loop {
let c = match chars.next() {
None => return Ok(s),
Some(c) => c,
};
match c.to_ascii_lowercase() {
'0'..='9' | 'a'..='z' => s.push(c),
'_' => break,
'.' => {
s.push('_');
break;
}
_ => return Err(format!("invalid character in opcode name: {}", key).into()),
}
}
}
}
/// Compiles conditions such as `S == B` into valid Rust expressions on a PowerPC instruction.
fn compile_mnemonic_condition(
field_by_name: &HashMap<String, &Field>,
code: &str,
) -> Result<TokenStream> {
let src_stream = TokenStream::from_str(code)?;
fn map_ident(field_by_name: &HashMap<String, &Field>, token: TokenTree) -> TokenStream {
match token {
TokenTree::Ident(ref ident) => {
if let Some(field) = field_by_name.get(&ident.to_string()) {
return field.express_value_self();
}
}
TokenTree::Group(ref group) => {
let iter = group
.stream()
.into_iter()
.flat_map(|token| map_ident(field_by_name, token));
let stream = TokenStream::from_iter(iter);
return TokenStream::from(TokenTree::Group(Group::new(group.delimiter(), stream)));
}
_ => {}
}
token.into()
}
let token_iter = src_stream
.into_iter()
.flat_map(|token| map_ident(field_by_name, token));
Ok(TokenStream::from_iter(token_iter))
}
fn express_suffix(
modifier_by_name: &HashMap<String, &Modifier>,
field_by_name: &HashMap<String, &Field>,
modifiers: &[String],
) -> Result<TokenStream> {
Ok(if modifiers.is_empty() {
quote!(String::new())
} else {
let mut chars = Vec::new();
for mod_name in modifiers {
let modifier: &Modifier = modifier_by_name
.get(mod_name)
.ok_or_else(|| Error::from(format!("undefined modifier {}", mod_name)))?;
let lit_char = LitChar::new(modifier.suffix, Span::call_site());
let modifier_bit = modifier.express_value_self(field_by_name)?;
chars.push(quote! {
if #modifier_bit {
s.push(#lit_char);
}
});
}
let chars = token_stream!(chars);
quote!({
{
let mut s = String::with_capacity(4);
#chars
s
}
})
})
}

111
isa.yaml
View File

@ -2,108 +2,134 @@ fields:
# Immediates
- name: simm
arg: Simm
desc: Signed Immediate
bits: 16..32
signed: true
- name: uimm
arg: Uimm
desc: Unsigned Immediate
bits: 16..32
- name: offset
arg: Offset
desc: Branch Offset
bits: 16..32
signed: true
- name: ps_offset
arg: Offset
desc: Paired Single Offset
bits: 20..32
signed: true
# Branch fields
- name: BO
arg: OpaqueU
desc: Branch Options
bits: 6..11
- name: BI
arg: CRBit
desc: Branch Condition Register Bit
bits: 11..16
- name: BD
arg: BranchDest
desc: Branch Destination (14-bit)
bits: 16..30
shift_left: 2
signed: true
- name: LI
arg: BranchDest
desc: Branch Destination (24-bit)
bits: 6..30
signed: true
shift_left: 2
# Shift/rotate type fields
- name: SH
arg: OpaqueU
desc: Shift
desc: Shift Amount
bits: 16..21
- name: MB
arg: OpaqueU
desc: Mask start
desc: Mask Begin
bits: 21..26
- name: ME
arg: OpaqueU
desc: Mask stop
desc: Mask End
bits: 26..31
# Registers
- name: rS
arg: GPR
desc: Source Register
bits: 6..11
- name: rD
arg: GPR
desc: Destination Register
bits: 6..11
- name: rA
arg: GPR
desc: Register A
bits: 11..16
- name: rA.nz
arg: GPR
desc: Register A (non-zero)
bits: 11..16
- name: rB
arg: GPR
desc: Register B
bits: 16..21
- name: sr
arg: SR
desc: Segment Register
bits: 12..16
- name: spr
arg: SPR
desc: Special Purpose Register
bits: 11..21
split: true
# Floating-point registers
- name: frS
arg: FPR
desc: Source Floating-Point Register
bits: 6..11
- name: frD
arg: FPR
desc: Destination Floating-Point Register
bits: 6..11
- name: frA
arg: FPR
desc: Floating-Point Register A
bits: 11..16
- name: frB
arg: FPR
desc: Floating-Point Register B
bits: 16..21
- name: frC
arg: FPR
desc: Floating-Point Register C
bits: 21..26
# Condition register bits
- name: crbD
arg: CRBit
desc: Condition Register Bit Destination
bits: 6..11
- name: crbA
arg: CRBit
desc: Condition Register Bit A
bits: 11..16
- name: crbB
arg: CRBit
desc: Condition Register Bit B
bits: 16..21
# Condition register fields
- name: crfD
arg: CRField
desc: Condition Register Field Destination
bits: 6..9
- name: crfS
arg: CRField
desc: Condition Register Field Source
bits: 11..14
# Condition register misc
- name: crm
arg: OpaqueU
desc: Condition Register Mask
bits: 12..20
# Paired single fields
- name: ps_I
@ -152,37 +178,46 @@ fields:
desc: Bitset for cmp, cmpi, cmpl, cmpli
bits: 10..11
- name: xer
desc: Fixed-Point Exception Register
- name: ctr
desc: Count Register
- name: lr
desc: Link Register
modifiers:
- name: OE
desc: Field used by XO-form instructions to enable setting OV and SO in the XER.
suffix: o
bit: 21
side_effects: [ xer ]
- name: Rc
desc: Record Bit
suffix: .
bit: 31
side_effects: [ cr0 ]
- name: LK
desc: Link Bit
suffix: l
bit: 31
side_effects: [ lr ]
- name: AA
desc: Absolute Address Bit
suffix: a
bit: 30
# Predict branch to be taken
- name: BP
desc: Predict branch to be taken
suffix: +
condition: BO & 1 == 1 && BD >= 0
# Predict branch not to be taken (fall through)
bit: 10
condition: BD >= 0
- name: BNP
desc: Predict branch not to be taken (fall through)
suffix: '-'
condition: BO & 1 == 1 && BD < 0
# Predict branch to be taken (implicit dest for LR/CTR)
bit: 10
condition: BD < 0
- name: BP_ND
desc: Predict branch to be taken (implicit dest for LR/CTR)
suffix: +
condition: BO & 1 == 1
bit: 10
opcodes:
- name: add
@ -1998,24 +2033,40 @@ mnemonics:
condition: rA == 0
- name: subis
opcode: addis
args: [ rD, rA, simm=-simm ]
args: [ rD, rA, simm ]
condition: simm < 0 && simm != -0x8000
replace:
simm: -simm
replace_assemble:
simm: -simm
- name: li
opcode: addi
args: [ rD, simm ]
condition: rA == 0
- name: subi
opcode: addi
args: [ rD, rA, simm=-simm ]
args: [ rD, rA, simm ]
condition: simm < 0 && simm != -0x8000
replace:
simm: -simm
replace_assemble:
simm: -simm
- name: subic
opcode: addic
args: [ rD, rA, simm=-simm ]
args: [ rD, rA, simm ]
condition: simm < 0 && simm != -0x8000
replace:
simm: -simm
replace_assemble:
simm: -simm
- name: subic.
opcode: addic.
args: [ rD, rA, simm=-simm ]
args: [ rD, rA, simm ]
condition: simm < 0 && simm != -0x8000
replace:
simm: -simm
replace_assemble:
simm: -simm
- name: mr
opcode: or
args: [ rA, rS ]
@ -2035,8 +2086,12 @@ mnemonics:
# Rotates/Shifts Immediate
- name: clrrwi
opcode: rlwinm
args: [ rA, rS, ME=31-ME ]
condition: SH == 0 && MB == 0 && ME < 32
args: [ rA, rS, ME ]
condition: SH == 0 && MB == 0
replace:
ME: 31 - ME
replace_assemble:
ME: 31 - ME
- name: clrlwi
opcode: rlwinm
args: [ rA, rS, MB ]
@ -2047,8 +2102,12 @@ mnemonics:
condition: MB == 0 && ME == 31 && SH <= 16
- name: rotrwi
opcode: rlwinm
args: [ rA, rS, SH=32-SH ]
args: [ rA, rS, SH ]
condition: MB == 0 && ME == 31 && SH > 16
replace:
SH: 32 - SH
replace_assemble:
SH: 32 - SH
- name: slwi
opcode: rlwinm
args: [ rA, rS, SH ]
@ -2059,16 +2118,30 @@ mnemonics:
condition: ME == 31 && SH == 32 - MB
- name: clrlslwi
opcode: rlwinm
args: [ rA, rS, MB=MB+SH, SH ]
args: [ rA, rS, MB, SH ]
condition: SH < 32 && ME == 31 - SH
replace:
MB: MB + SH
replace_assemble:
MB: MB - SH
- name: extlwi
opcode: rlwinm
args: [ rA, rS, ME=ME+1, SH ]
args: [ rA, rS, ME, SH ]
condition: MB == 0
replace:
ME: ME + 1
replace_assemble:
ME: ME - 1
- name: extrwi
opcode: rlwinm
args: [ rA, rS, MB=32-MB, SH=SH-(32-MB) ]
args: [ rA, rS, MB, SH ]
condition: ME == 31 && SH >= 32 - MB
replace:
MB: 32 - MB
SH: SH - (32 - MB)
replace_assemble:
MB: 32 - MB
SH: SH + MB
# Compares Word
- name: cmpwi

13
rand/Cargo.toml
View File

@ -1,13 +0,0 @@
[package]
name = "ppc750cl-rand"
version = "0.2.0"
edition = "2021"
authors = ["Richard Patel <me@terorie.dev>"]
license = "GPL-3.0-or-later"
description = "Generate random PowerPC 750CL instructions"
repository = "https://github.com/terorie/ppc750cl"
[dependencies]
ppc750cl = { path = "../disasm", version = "0.2.0" }
rand_core = "0.6"
sfmt = "0.7"

16
rand/src/main.rs
View File

@ -1,16 +0,0 @@
use rand_core::{RngCore, SeedableRng};
use sfmt::SFMT;
use ppc750cl::formatter::FormattedIns;
use ppc750cl::{Ins, Opcode};
fn main() {
let mut rng = SFMT::seed_from_u64(42);
loop {
let ins = Ins::new(rng.next_u32(), 0);
if ins.op == Opcode::Illegal {
continue;
}
println!("{}", FormattedIns(ins));
}
}

2
rustfmt.toml Normal file
View File

@ -0,0 +1,2 @@
use_field_init_shorthand = true
use_small_heuristics = "Max"