fix(ci): pass the upload file to curl, not its interpolation

.gitea/workflows/release.yml

@@ -342,7 +342,10 @@ jobs:
               my @cmd = (q{curl}, q{-sS}, q{-o}, q{/dev/null}, q{-w}, q{%{http_code}},
                 q{-H}, qq{Authorization: token $ENV{GITEA_TOKEN}},
                 q{-H}, q{Content-Type: application/octet-stream},
-                q{-X}, q{POST}, q{--data-binary}, qq{@$path},
+                # The @ must not sit inside a qq{} string: there it starts an
+                # array interpolation and the upload body collapses to empty,
+                # which Gitea stores as a 201-created zero-byte attachment.
+                q{-X}, q{POST}, q{--data-binary}, q{@} . $path,
                 qq{$ENV{GITEA_SERVER_URL}/api/v1/repos/$ENV{GITEA_REPOSITORY}/releases/$id/assets?name=$name});
               open(my $curl, q{-|}, @cmd) or die qq{curl: $!};
               my $code = <$curl>;

CHANGELOG.md

@@ -7,59 +7,33 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [development]
 
-### Fixed
+### Added
 
-- **The operand forms GOROOT writes.**  Numeric PC-relative jumps
-  (`JEQ 2(PC)`, the park loop `JMP 0(PC)`) resolve with the toolchain's
-  own instruction counting and fold jump-to-jump chains exactly as its
-  branch optimiser does; symbol immediates (`MOVQ $sym(SB), AX`)
-  assemble to the toolchain's RIP-relative LEA with an R_PCREL
-  relocation; negated constant expressions in operands (`ADJSP
-  $-(REGS - 8)`, the shape the cgo ABI macros write) fold; the TLS
-  access pair assembles as the toolchain's one-instruction form (the
-  bare `MOVQ TLS, r` load nops out and `off(r)(TLS*1)` folds to the
-  segment-prefixed absolute whose disp32 carries the R_TLSLE
-  relocation, per-GOOS); arm64 accepts the bare-register indirect branch
-  (`BL R9` beside `BL (R9)`, both BLR) and the zero-immediate store
-  (`MOVD $0, mem` through the zero register, rejecting non-zero immediates
-  as the toolchain does); `PCALIGN` now aligns on amd64, padding with the
-  toolchain's greedy single-instruction NOPs; the segment-absolute forms
-  (`MOVQ 0x30(GS), AX` and the store direction) and the absolute
-  crash-store (`MOVL $0xf1, 0xf1`) encode; and `gasm asm` predefines
-  the `GOARCH_<arch>` and `GOOS_<goos>` macros the go command passes to
-  `go tool asm`, so GOROOT headers' `#ifdef GOARCH_amd64` platform blocks
-  (`go_tls.h`'s `get_tls` and friends) select as intended.  The GOROOT
-  corpus measure moves to 291 of 353 files assembling for every target
-  architecture (82.4 %), 97.4 % of the real-code corpus, from 70.8 %
-  and 82.2 %.
+-
+
+## [0.35.0] - 2026-09-22
 
 ### Added
 
-- **Per-architecture reference pages.**  [docs/asm/](docs/asm/README.md)
-  gains AMD64, ARM64, RISCV64 and LOONG64: the register files and the
-  roles the ABI fixes, addressing, operand order with every special form,
-  constants and materialisation, alignment, fences and the relocations
-  each target emits.  An instruction inventory appendix per architecture
-  is generated from the toolchain's own tables by `just gen`, and the
-  regenerated tables recognise 147 more mnemonics than the previous
-  release carried (arm64 107, riscv64 31, loong64 9).
-- **The Plan 9 assembly language reference.**  [docs/asm/](docs/asm/README.md)
-  opens the complete language reference with its common core: the lexicon,
-  statement structure and constant expressions, the operand grammar with
-  the pseudo-registers and symbol naming, the directives and the function
-  flag vocabulary, preprocessing with `#define` and `#include`, and the
-  Go-embedded layer (ABI0, prototypes, `go_asm.h`, `funcdata.h` and the
-  runtime contract).  Every claim is verified against `go tool asm` of
-  Go 1.27.1 and gasm's differential tests; the per-architecture pages and
-  generated instruction appendices follow.
-- **GOOBJ format specification.**  [docs/GOOBJ.md](docs/GOOBJ.md)
-  documents the Go object file format in full: both containers, the 96
-  byte header and all 19 blocks, every structure with its byte
-  offsets, symbol kinds and flag bits, all 106 relocation types with
-  the weak variants, aux symbols, the FuncInfo payload, the pc-value
-  table encoding, the content hashes and the builtin table, all
-  verified byte for byte against objects produced by Go 1.27.1's own
-  tools.
+- **The go_asm.h generator.**  `gasm asm` generates the package's go_asm.h
+  itself when an assembly file includes it: the Go files beside the source
+  are type-checked for the target architecture and the constants and field
+  offsets become assembler defines, so package-context files assemble with
+  no compiler and no `go build` in the loop.  `-GOOS` selects the
+  type-checking GOOS for GOOS-specific files, and the corpus audit derives
+  the GOOS from the file name.
+- **ELF data relocations on arm64, riscv64 and loong64.**  `gasm asm
+  --format elf` emits `.rela.data` for symbol-valued DATA initialisers on
+  every architecture (amd64 carried them already), so standalone ELF
+  objects link on all four targets.
+- **Corpus failure listing.**  `gasm audit-instructions --corpus --list`
+  prints every failing file with its failure reason, per architecture,
+  instead of one representative file per reason.
+- **DATA with symbol values and relaxed symbol spellings.**  DATA
+  initialisers accept `$symbol(SB)` values, laid down as an absolute
+  relocation at the data field (GOOBJ on all four architectures and ELF
+  on all four as of this release), and U+2215 is accepted inside symbol
+  package paths.
 - **Macro expansion and include splicing.**  `gasm asm`, `gasm diff` and
   `gasm audit-instructions` now preprocess assembly the way the
   toolchain does: object and parameterised `#define` macros expand at
@@ -100,21 +74,77 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
   ranges, index-only VSIB memory operands and bare trailing immediates;
   macro substitution reaches parameters used with element suffixes
   (`A.S4`), and `;` separates statements in plain files.
-- **`gasm asm -GOOS`.**  The go_asm.h generator type-checks per target
-  GOOS, so the darwin-only and windows-only runtime files assemble with
-  their own defines; the corpus audit derives the GOOS from the file
-  name.  DATA initialisers accept `$symbol(SB)` values (an absolute
-  relocation at the data field, GOOBJ on all four architectures and ELF
-  on amd64, arm64, riscv64 and loong64), and U+2215 is accepted inside
-  symbol package paths.
-- **The corpus audit measures honestly.**  Files named for Go ports gasm
-  does not target (arm, 386, s390x, ...) are no longer attempted for the
-  four supported architectures (no supported build compiles them), and
-  the headline rate is reported over attemptable files: 136 of 433 on
-  the full corpus (31.4 %), 135 of 383 on real code (35.2 %), from the
-  127 that the previous release measured.  The probe battery that
-  decides encodability gained the operand shapes the new families use.
--
+- **Per-architecture reference pages.**  [docs/asm/](docs/asm/README.md)
+  gains AMD64, ARM64, RISCV64 and LOONG64: the register files and the
+  roles the ABI fixes, addressing, operand order with every special form,
+  constants and materialisation, alignment, fences and the relocations
+  each target emits.  An instruction inventory appendix per architecture
+  is generated from the toolchain's own tables by `just gen`, and the
+  regenerated tables recognise 147 more mnemonics than the previous
+  release carried (arm64 107, riscv64 31, loong64 9).
+- **The Plan 9 assembly language reference.**  [docs/asm/](docs/asm/README.md)
+  opens the complete language reference with its common core: the lexicon,
+  statement structure and constant expressions, the operand grammar with
+  the pseudo-registers and symbol naming, the directives and the function
+  flag vocabulary, preprocessing with `#define` and `#include`, and the
+  Go-embedded layer (ABI0, prototypes, `go_asm.h`, `funcdata.h` and the
+  runtime contract).  Every claim is verified against `go tool asm` of
+  Go 1.27.1 and gasm's differential tests; the per-architecture pages and
+  generated instruction appendices follow.
+- **GOOBJ format specification.**  [docs/GOOBJ.md](docs/GOOBJ.md)
+  documents the Go object file format in full: both containers, the 96
+  byte header and all 19 blocks, every structure with its byte
+  offsets, symbol kinds and flag bits, all 106 relocation types with
+  the weak variants, aux symbols, the FuncInfo payload, the pc-value
+  table encoding, the content hashes and the builtin table, all
+  verified byte for byte against objects produced by Go 1.27.1's own
+  tools.
+
+### Changed
+
+- **The corpus audit measures like a build.**  Files named for a Go port
+  gasm does not target (arm, 386, s390x, ...) are never attempted, because
+  no supported build compiles them; the GOOS comes from the file name; and
+  each target's go_asm.h is generated on the fly.  The headline is reported
+  over attemptable files: 291 of 353 on the full corpus (82.4 %) assemble
+  for every target architecture and 295 of 303 on real code (97.4 %),
+  against 108 of 627 over all files (17.2 %) that the previous release
+  measured.
+
+### Fixed
+
+- **The operand forms GOROOT writes.**  Numeric PC-relative jumps
+  (`JEQ 2(PC)`, the park loop `JMP 0(PC)`) resolve with the toolchain's
+  own instruction counting and fold jump-to-jump chains exactly as its
+  branch optimiser does; symbol immediates (`MOVQ $sym(SB), AX`)
+  assemble to the toolchain's RIP-relative LEA with an R_PCREL
+  relocation; negated constant expressions in operands (`ADJSP
+  $-(REGS - 8)`, the shape the cgo ABI macros write) fold; the immediate
+  multiply (`IMULQ $1000000000, AX`) encodes with the toolchain's
+  0x69/0x6B selection; the TLS access pair assembles as the toolchain's
+  one-instruction form (the bare `MOVQ TLS, r` load nops out and
+  `off(r)(TLS*1)` folds to the segment-prefixed absolute whose disp32
+  carries the R_TLSLE relocation, per-GOOS); arm64 accepts the
+  bare-register indirect branch (`BL R9` beside `BL (R9)`, both BLR) and
+  the zero-immediate store (`MOVD $0, mem` through the zero register,
+  rejecting non-zero immediates as the toolchain does); `PCALIGN` now
+  aligns on amd64, padding with the toolchain's greedy
+  single-instruction NOPs; the segment-absolute forms (`MOVQ 0x30(GS),
+  AX` and the store direction) and the absolute crash-store
+  (`MOVL $0xf1, 0xf1`) encode; and `gasm asm` predefines the
+  `GOARCH_<arch>` and `GOOS_<goos>` macros the go command passes to
+  `go tool asm`, so GOROOT headers' `#ifdef GOARCH_amd64` platform
+  blocks (`go_tls.h`'s `get_tls` and friends) select as intended.  The
+  GOROOT corpus measure moves to 291 of 353 files assembling for every
+  target architecture (82.4 %), 97.4 % of the real-code corpus, from
+  70.8 % and 82.2 %.
+- **Tool corrections across the pipeline.**  The formatter keeps square
+  brackets in SIMD operands, statement separators and canonical macro
+  bodies; the linter drops false positives on shift counts, SETcc
+  spellings and ABIInternal references; the lexer treats a trailing
+  carriage return as a line end so comment text stays idempotent; and
+  arm64 rejects bare BTI with a diagnostic while accepting the full
+  family.
 
 ## [0.34.0] - 2026-09-20
 

README.md

@@ -81,7 +81,10 @@ to give that syntax the tooling it deserves.
   GOOBJ format, which needs the installed toolchain and which `go build`
   consumes in place of the toolchain's output.  Framed functions get the
   stack-split guard and the morestack block, byte-identical to the
-  toolchain's, so split functions link too.
+  toolchain's, so split functions link too.  The assembler preprocesses
+  like the toolchain (`#define`, `#include` with `-I`, `#ifdef`), generates
+  `go_asm.h` from the package's Go files, and carries `PCALIGN`, the
+  `LOCK`/`REP` prefixes and the literal-data pseudo-ops.
 - **Disassembler.**  `gasm dis` lists a `.s` file's functions at their real
   offsets after assembling, or disassembles raw bytes from a file or stdin.
 - **Dynamic verification.**  `gasm verify` JIT-loads assembled functions into
@@ -110,9 +113,9 @@ Four architectures, the four that matter in practice:
 | Architecture | GOARCH      | File suffix  | Instructions recognised                     |
 |--------------|-------------|--------------|---------------------------------------------|
 | AMD64        | `amd64`     | `_amd64.s`   | 1600 + common opcodes + traditional aliases |
-| ARM64        | `arm64`     | `_arm64.s`   | 538 + common opcodes                        |
-| RISC-V       | `riscv64`   | `_riscv64.s` | 961 + common opcodes                        |
-| LoongArch    | `loong64`   | `_loong64.s` | 799 + common opcodes                        |
+| ARM64        | `arm64`     | `_arm64.s`   | 645 + common opcodes                        |
+| RISC-V       | `riscv64`   | `_riscv64.s` | 992 + common opcodes                        |
+| LoongArch    | `loong64`   | `_loong64.s` | 808 + common opcodes                        |
 
 "Common opcodes" are the instructions shared by every architecture (`RET`,
 `JMP`, `NOP`, `CALL`, `TEXT`, `FUNCDATA`, `PCDATA`, ...).  AMD64 additionally
@@ -124,8 +127,8 @@ can emit today is narrower, and a recognised but unencodable instruction is
 reported as an explicit error, never as a wrong byte.
 
 The same measurement runs over GOROOT's whole assembly corpus:
-`gasm audit-instructions --corpus` reports 136 of 433 attemptable files
-(31.4 %) assembling for every target architecture today (files named for
+`gasm audit-instructions --corpus` reports 291 of 353 attemptable files
+(82.4 %) assembling for every target architecture today (files named for
 other Go ports are counted but never attempted), with the top failure
 reasons per architecture; the number moves with every release.
 

SECURITY.md

@@ -7,7 +7,7 @@ releases do not receive them.
 
 | Version | Supported |
 |---|---|
-| 0.34.0 | yes |
+| 0.35.0 | yes |
 | older releases | no |
 
 ## Reporting a vulnerability

cmd/gasm/asmhdr_test.go

@@ -5,6 +5,7 @@ package main
 
 import (
 	"os"
+	"os/exec"
 	"path/filepath"
 	"strings"
 	"testing"
@@ -393,13 +394,20 @@ func TestRunCorpusAuditGOOS(t *testing.T) {
 }
 
 // TestGenerateGoAsmHeaderRuntime pins the generator against the real thing:
-// the runtime package, whose header the toolchain's own -asmhdr output was
-// sampled from.  Skipped in short mode: it type-checks the whole package.
+// the runtime package of the ambient toolchain, whose header the toolchain's
+// own -asmhdr output was sampled from.  Skipped in short mode: it type-checks
+// the whole package.  The GOROOT comes from the go command itself, so the
+// test follows whatever toolchain the host provides.
 func TestGenerateGoAsmHeaderRuntime(t *testing.T) {
 	if testing.Short() {
 		t.Skip("type-checks the whole runtime package")
 	}
-	dir, err := generateGoAsmHeader("/usr/local/go/src/runtime", "", "amd64", t.TempDir())
+	out, err := exec.Command("go", "env", "GOROOT").Output()
+	if err != nil {
+		t.Skipf("no Go toolchain: %v", err)
+	}
+	runtimeDir := filepath.Join(strings.TrimSpace(string(out)), "src", "runtime")
+	dir, err := generateGoAsmHeader(runtimeDir, "", "amd64", t.TempDir())
 	if err != nil {
 		t.Fatalf("generateGoAsmHeader(runtime): %v", err)
 	}

docs/ARCHITECTURE.md

@@ -119,6 +119,20 @@ identifier is a register or a label is an *architecture* question, so it is
 left to `arch` and resolved in the lint/lsp layers.  This keeps the parser
 arch-agnostic and its output deterministic.
 
+### Optional preprocessing
+
+With `Options{Expand: true}` the parser runs a pre-parse pass
+(`preproc.go`) that splices `#include` files (the source directory, then the
+`-I` directories), expands object and parameterised `#define` macros,
+applies `#undef` and the `#ifdef`/`#ifndef`/`#else`/`#endif` family, and
+folds constant expressions left in operands.  The go command's platform
+macros (`GOARCH_<arch>`, `GOOS_<goos>`) arrive through `Options.Predefines`.
+The assembly path (`asm`, `diff`, `audit`) expands; `lint`, `fmt` and the
+language server read the raw file.  The command layer adds the go_asm.h
+generator (`asmhdr.go`): a file that includes go_asm.h gets the package's
+defines type-checked out of its Go files for the target architecture and
+GOOS, with no compiler in the loop.
+
 ### `arch`
 
 Register files are generated programmatically (the regular `R8`-`R15`,